# HG changeset patch # User Paper # Date 1731902147 18000 # Node ID 8d45d892be880932e3d66e688ae6514f8a205f7f # Parent 886f66775f317a3842c49be91217636ce9a45443 *: instead of pugixml, use Qt XML features this means we have one extra Qt dependency though... diff -r 886f66775f31 -r 8d45d892be88 CMakeLists.txt --- a/CMakeLists.txt Sun Nov 17 19:56:01 2024 -0500 +++ b/CMakeLists.txt Sun Nov 17 22:55:47 2024 -0500 @@ -12,9 +12,6 @@ add_subdirectory(dep/animone) add_subdirectory(dep/anitomy) -add_subdirectory(dep/pugixml) -add_subdirectory(dep/utf8proc) -add_subdirectory(dep/fmt) # Fix for mingw64 list(APPEND CMAKE_FIND_LIBRARY_SUFFIXES ".dll.a" ".a") @@ -29,22 +26,44 @@ find_package(QT NAMES Qt6 Qt5 REQUIRED COMPONENTS Core) endif() -find_package(Qt${QT_VERSION_MAJOR} REQUIRED COMPONENTS Widgets LinguistTools) +find_package(Qt${QT_VERSION_MAJOR} REQUIRED COMPONENTS Widgets LinguistTools Xml) -# find_package(CURL) fails sometimes +# find_package(CURL) is dysfunctional find_package(PkgConfig REQUIRED) pkg_check_modules(CURL REQUIRED libcurl) +pkg_check_modules(UTF8PROC libutf8proc) +pkg_check_modules(FMT fmt) + +message("${FMT_LINK_LIBRARIES}") + +if(NOT UTF8PROC_FOUND) + add_subdirectory(dep/utf8proc) +endif() + +if(NOT FMT_FOUND) + add_subdirectory(dep/fmt) +endif() set(LIBRARIES - ${CURL_LIBRARIES} ${Qt${QT_VERSION_MAJOR}Widgets_LIBRARIES} + ${Qt${QT_VERSION_MAJOR}Xml_LIBRARIES} + ${CURL_LINK_LIBRARIES} anitomy animia - pugixml - utf8proc - fmt ) +if(UTF8PROC_FOUND) + list(APPEND LIBRARIES ${UTF8PROC_LINK_LIBRARIES}) +else() + list(APPEND LIBRARIES utf8proc) +endif() + +if(FMT_FOUND) + list(APPEND LIBRARIES ${FMT_LINK_LIBRARIES}) +else() + list(APPEND LIBRARIES fmt) +endif() + set(QT_MOC_FILES include/core/http.h include/core/session.h @@ -155,15 +174,27 @@ ) set(INCLUDE + ${Qt${QT_VERSION_MAJOR}Widgets_INCLUDE_DIRS} + ${Qt${QT_VERSION_MAJOR}Xml_INCLUDE_DIRS} + ${CURL_INCLUDE_DIRS} include - dep/pugixml/src dep/animia/include - dep/fmt/include - dep/utf8proc dep/anitomy dep ) +if(UTF8PROC_FOUND) + list(APPEND INCLUDE ${UTF8PROC_INCLUDE_DIRS}) +else() + list(APPEND INCLUDE dep/utf8proc) +endif() + +if(FMT_FOUND) + list(APPEND INCLUDE ${FMT_INCLUDE_DIRS}) +else() + list(APPEND INCLUDE dep/fmt/include) +endif() + set(TS_FILES rc/locale/en_GB.ts ) @@ -267,7 +298,7 @@ set_property(TARGET minori PROPERTY CXX_STANDARD 17) set_property(TARGET minori PROPERTY AUTORCC ON) -target_include_directories(minori PRIVATE ${Qt${QT_VERSION_MAJOR}Widgets_INCLUDE_DIRS} ${CURL_INCLUDE_DIRS} PUBLIC ${INCLUDE}) +target_include_directories(minori PRIVATE ${INCLUDE}) target_link_libraries(minori PRIVATE ${LIBRARIES}) target_compile_options(minori PRIVATE -Wall -Wpedantic -Wextra -Wsuggest-override -Wold-style-cast) target_compile_definitions(minori PRIVATE ${DEFINES}) diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/CMakeLists.txt --- a/dep/pugixml/CMakeLists.txt Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,279 +0,0 @@ -cmake_minimum_required(VERSION 3.5) - -# Policy configuration; this *MUST* be specified before project is defined -if(POLICY CMP0091) - cmake_policy(SET CMP0091 NEW) # Enables use of MSVC_RUNTIME_LIBRARY -endif() - -project(pugixml VERSION 1.14 LANGUAGES CXX) - -include(CMakePackageConfigHelpers) -include(CMakeDependentOption) -include(GNUInstallDirs) - -cmake_dependent_option(PUGIXML_USE_VERSIONED_LIBDIR - "Use a private subdirectory to install the headers and libraries" OFF - "CMAKE_SOURCE_DIR STREQUAL PROJECT_SOURCE_DIR" OFF) - -cmake_dependent_option(PUGIXML_USE_POSTFIX - "Use separate postfix for each configuration to make sure you can install multiple build outputs" OFF - "CMAKE_SOURCE_DIR STREQUAL PROJECT_SOURCE_DIR" OFF) - -cmake_dependent_option(PUGIXML_STATIC_CRT - "Use static MSVC RT libraries" OFF - "MSVC" OFF) - -cmake_dependent_option(PUGIXML_BUILD_TESTS - "Build pugixml tests" OFF - "CMAKE_SOURCE_DIR STREQUAL PROJECT_SOURCE_DIR" OFF) - -# Custom build defines -set(PUGIXML_BUILD_DEFINES CACHE STRING "Build defines for custom options") -separate_arguments(PUGIXML_BUILD_DEFINES) - -# Technically not needed for this file. This is builtin CMAKE global variable. -option(BUILD_SHARED_LIBS "Build shared instead of static library" OFF) - -# Expose option to build PUGIXML as static as well when the global BUILD_SHARED_LIBS variable is set -cmake_dependent_option(PUGIXML_BUILD_SHARED_AND_STATIC_LIBS - "Build both shared and static libraries" OFF - "BUILD_SHARED_LIBS" OFF) - -# Expose options from the pugiconfig.hpp -option(PUGIXML_WCHAR_MODE "Enable wchar_t mode" OFF) -option(PUGIXML_COMPACT "Enable compact mode" OFF) -option(PUGIXML_INSTALL "Enable installation rules" ON) - -# Advanced options from pugiconfig.hpp -option(PUGIXML_NO_XPATH "Disable XPath" OFF) -option(PUGIXML_NO_STL "Disable STL" OFF) -option(PUGIXML_NO_EXCEPTIONS "Disable Exceptions" OFF) -mark_as_advanced(PUGIXML_NO_XPATH PUGIXML_NO_STL PUGIXML_NO_EXCEPTIONS) - -set(PUGIXML_PUBLIC_DEFINITIONS - $<$:PUGIXML_WCHAR_MODE> - $<$:PUGIXML_COMPACT> - $<$:PUGIXML_NO_XPATH> - $<$:PUGIXML_NO_STL> - $<$:PUGIXML_NO_EXCEPTIONS>) - -# This is used to backport a CMake 3.15 feature, but is also forwards compatible -if (NOT DEFINED CMAKE_MSVC_RUNTIME_LIBRARY) - set(CMAKE_MSVC_RUNTIME_LIBRARY - MultiThreaded$<$:Debug>$<$>:DLL>) -endif() - -if (NOT DEFINED CMAKE_CXX_STANDARD_REQUIRED) - set(CMAKE_CXX_STANDARD_REQUIRED ON) -endif() - -if (NOT DEFINED CMAKE_CXX_STANDARD) - set(CMAKE_CXX_STANDARD 11) -endif() - -if (PUGIXML_USE_POSTFIX) - set(CMAKE_RELWITHDEBINFO_POSTFIX _r) - set(CMAKE_MINSIZEREL_POSTFIX _m) - set(CMAKE_DEBUG_POSTFIX _d) -endif() - -if (CMAKE_VERSION VERSION_LESS 3.15) - set(msvc-rt $) - - set(msvc-rt-mtd-shared $) - set(msvc-rt-mtd-static $) - set(msvc-rt-mt-shared $) - set(msvc-rt-mt-static $) - unset(msvc-rt) - - set(msvc-rt-mtd-shared $<${msvc-rt-mtd-shared}:-MDd>) - set(msvc-rt-mtd-static $<${msvc-rt-mtd-static}:-MTd>) - set(msvc-rt-mt-shared $<${msvc-rt-mt-shared}:-MD>) - set(msvc-rt-mt-static $<${msvc-rt-mt-static}:-MT>) -endif() - -set(versioned-dir $<$:/pugixml-${PROJECT_VERSION}>) - -set(libs) - -if (BUILD_SHARED_LIBS) - add_library(pugixml-shared SHARED - ${PROJECT_SOURCE_DIR}/scripts/pugixml_dll.rc - ${PROJECT_SOURCE_DIR}/src/pugixml.cpp) - add_library(pugixml::shared ALIAS pugixml-shared) - list(APPEND libs pugixml-shared) - string(CONCAT pugixml.msvc $, - $ - >) - - set_property(TARGET pugixml-shared PROPERTY EXPORT_NAME shared) - target_include_directories(pugixml-shared - PUBLIC - $) - target_compile_definitions(pugixml-shared - PUBLIC - ${PUGIXML_BUILD_DEFINES} - ${PUGIXML_PUBLIC_DEFINITIONS} - PRIVATE - PUGIXML_API=$ - ) - target_compile_options(pugixml-shared - PRIVATE - ${msvc-rt-mtd-shared} - ${msvc-rt-mtd-static} - ${msvc-rt-mt-shared} - ${msvc-rt-mt-static}) -endif() - -if (NOT BUILD_SHARED_LIBS OR PUGIXML_BUILD_SHARED_AND_STATIC_LIBS) - add_library(pugixml-static STATIC - ${PROJECT_SOURCE_DIR}/src/pugixml.cpp) - add_library(pugixml::static ALIAS pugixml-static) - list(APPEND libs pugixml-static) - - set_property(TARGET pugixml-static PROPERTY EXPORT_NAME static) - target_include_directories(pugixml-static - PUBLIC - $) - target_compile_definitions(pugixml-static - PUBLIC - ${PUGIXML_BUILD_DEFINES} - ${PUGIXML_PUBLIC_DEFINITIONS}) - target_compile_options(pugixml-static - PRIVATE - ${msvc-rt-mtd-shared} - ${msvc-rt-mtd-static} - ${msvc-rt-mt-shared} - ${msvc-rt-mt-static}) -endif() - -if (BUILD_SHARED_LIBS) - set(pugixml-alias pugixml-shared) -else() - set(pugixml-alias pugixml-static) -endif() -add_library(pugixml INTERFACE) -target_link_libraries(pugixml INTERFACE ${pugixml-alias}) -add_library(pugixml::pugixml ALIAS pugixml) - -set_target_properties(${libs} - PROPERTIES - MSVC_RUNTIME_LIBRARY ${CMAKE_MSVC_RUNTIME_LIBRARY} - EXCLUDE_FROM_ALL ON - POSITION_INDEPENDENT_CODE ON - SOVERSION ${PROJECT_VERSION_MAJOR} - VERSION ${PROJECT_VERSION} - OUTPUT_NAME pugixml) - -set_target_properties(${libs} - PROPERTIES - EXCLUDE_FROM_ALL OFF) -set(install-targets pugixml ${libs}) - -configure_package_config_file( - "${PROJECT_SOURCE_DIR}/scripts/pugixml-config.cmake.in" - "${PROJECT_BINARY_DIR}/pugixml-config.cmake" - INSTALL_DESTINATION ${CMAKE_INSTALL_LIBDIR} - NO_CHECK_REQUIRED_COMPONENTS_MACRO - NO_SET_AND_CHECK_MACRO) - -write_basic_package_version_file( - "${PROJECT_BINARY_DIR}/pugixml-config-version.cmake" - COMPATIBILITY SameMajorVersion) - -if (PUGIXML_USE_POSTFIX) - if(CMAKE_BUILD_TYPE MATCHES RelWithDebInfo) - set(LIB_POSTFIX ${CMAKE_RELWITHDEBINFO_POSTFIX}) - elseif(CMAKE_BUILD_TYPE MATCHES MinSizeRel) - set(LIB_POSTFIX ${CMAKE_MINSIZEREL_POSTFIX}) - elseif(CMAKE_BUILD_TYPE MATCHES Debug) - set(LIB_POSTFIX ${CMAKE_DEBUG_POSTFIX}) - endif() -endif() - -# Handle both relative and absolute paths (e.g. NixOS) for a relocatable package -if(IS_ABSOLUTE "${CMAKE_INSTALL_INCLUDEDIR}") - set(PUGIXML_PC_INCLUDEDIR "${CMAKE_INSTALL_INCLUDEDIR}") -else() - set(PUGIXML_PC_INCLUDEDIR "\${prefix}/${CMAKE_INSTALL_INCLUDEDIR}") -endif() -if(IS_ABSOLUTE "${CMAKE_INSTALL_LIBDIR}") - set(PUGIXML_PC_LIBDIR "${CMAKE_INSTALL_LIBDIR}") -else() - set(PUGIXML_PC_LIBDIR "\${exec_prefix}/${CMAKE_INSTALL_LIBDIR}") -endif() -configure_file(scripts/pugixml.pc.in pugixml.pc @ONLY) - -export(TARGETS ${install-targets} - NAMESPACE pugixml:: - FILE pugixml-targets.cmake) - -if(PUGIXML_INSTALL) - if (NOT DEFINED PUGIXML_RUNTIME_COMPONENT) - set(PUGIXML_RUNTIME_COMPONENT Runtime) - endif() - - if (NOT DEFINED PUGIXML_LIBRARY_COMPONENT) - set(PUGIXML_LIBRARY_COMPONENT Library) - endif() - - if (NOT DEFINED PUGIXML_DEVELOPMENT_COMPONENT) - set(PUGIXML_DEVELOPMENT_COMPONENT Development) - endif() - - set(namelink-component) - if (NOT CMAKE_VERSION VERSION_LESS 3.12) - set(namelink-component NAMELINK_COMPONENT ${PUGIXML_DEVELOPMENT_COMPONENT}) - endif() - install(TARGETS ${install-targets} - EXPORT pugixml-targets - RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR} COMPONENT ${PUGIXML_RUNTIME_COMPONENT} - LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR} COMPONENT ${PUGIXML_LIBRARY_COMPONENT} ${namelink-component} - ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR} COMPONENT ${PUGIXML_DEVELOPMENT_COMPONENT} - INCLUDES DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}${versioned-dir}) - - install(EXPORT pugixml-targets - NAMESPACE pugixml:: - DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/pugixml COMPONENT ${PUGIXML_DEVELOPMENT_COMPONENT}) - - install(FILES - "${PROJECT_BINARY_DIR}/pugixml-config-version.cmake" - "${PROJECT_BINARY_DIR}/pugixml-config.cmake" - DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/pugixml COMPONENT ${PUGIXML_DEVELOPMENT_COMPONENT}) - - install(FILES ${PROJECT_BINARY_DIR}/pugixml.pc - DESTINATION ${CMAKE_INSTALL_LIBDIR}/pkgconfig COMPONENT ${PUGIXML_DEVELOPMENT_COMPONENT}) - - install( - FILES - "${PROJECT_SOURCE_DIR}/src/pugiconfig.hpp" - "${PROJECT_SOURCE_DIR}/src/pugixml.hpp" - DESTINATION - ${CMAKE_INSTALL_INCLUDEDIR}${versioned-dir} COMPONENT ${PUGIXML_DEVELOPMENT_COMPONENT}) -endif() - -if (PUGIXML_BUILD_TESTS) - include(CTest) - set(fuzz-pattern "tests/fuzz_*.cpp") - set(test-pattern "tests/*.cpp") - if (CMAKE_VERSION VERSION_GREATER 3.11) - list(INSERT fuzz-pattern 0 CONFIGURE_DEPENDS) - list(INSERT test-pattern 0 CONFIGURE_DEPENDS) - endif() - file(GLOB test-sources ${test-pattern}) - file(GLOB fuzz-sources ${fuzz-pattern}) - list(REMOVE_ITEM test-sources ${fuzz-sources}) - - add_custom_target(check - COMMAND ${CMAKE_CTEST_COMMAND} --output-on-failure) - - add_executable(pugixml-check ${test-sources}) - add_test(NAME pugixml::test - COMMAND pugixml-check - WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}) - add_dependencies(check pugixml-check) - target_link_libraries(pugixml-check - PRIVATE - pugixml::pugixml) -endif() diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/LICENSE --- a/dep/pugixml/LICENSE Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,24 +0,0 @@ -MIT License - -Copyright (c) 2006-2023 Arseny Kapoulkine - -Permission is hereby granted, free of charge, to any person -obtaining a copy of this software and associated documentation -files (the "Software"), to deal in the Software without -restriction, including without limitation the rights to use, -copy, modify, merge, publish, distribute, sublicense, and/or sell -copies of the Software, and to permit persons to whom the -Software is furnished to do so, subject to the following -conditions: - -The above copyright notice and this permission notice shall be -included in all copies or substantial portions of the Software. - -THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, -EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES -OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND -NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT -HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, -WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING -FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR -OTHER DEALINGS IN THE SOFTWARE. diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/images/dom_tree.png Binary file dep/pugixml/docs/images/dom_tree.png has changed diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/images/vs2005_link1.png Binary file dep/pugixml/docs/images/vs2005_link1.png has changed diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/images/vs2005_link2.png Binary file dep/pugixml/docs/images/vs2005_link2.png has changed diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/images/vs2005_pch1.png Binary file dep/pugixml/docs/images/vs2005_pch1.png has changed diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/images/vs2005_pch2.png Binary file dep/pugixml/docs/images/vs2005_pch2.png has changed diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/images/vs2005_pch3.png Binary file dep/pugixml/docs/images/vs2005_pch3.png has changed diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/images/vs2005_pch4.png Binary file dep/pugixml/docs/images/vs2005_pch4.png has changed diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/images/vs2010_link1.png Binary file dep/pugixml/docs/images/vs2010_link1.png has changed diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/images/vs2010_link2.png Binary file dep/pugixml/docs/images/vs2010_link2.png has changed diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/manual.html --- a/dep/pugixml/docs/manual.html Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,6163 +0,0 @@ - - - - - - - - -pugixml 1.14 manual - - - - - - -
-
-

1. Overview

-
-
-

1.1. Introduction

-
-

pugixml is a light-weight C++ XML processing library. It consists of a DOM-like interface with rich traversal/modification capabilities, an extremely fast XML parser which constructs the DOM tree from an XML file/buffer, and an XPath 1.0 implementation for complex data-driven tree queries. Full Unicode support is also available, with two Unicode interface variants and conversions between different Unicode encodings (which happen automatically during parsing/saving). The library is extremely portable and easy to integrate and use. pugixml is developed and maintained since 2006 and has many users. All code is distributed under the MIT license, making it completely free to use in both open-source and proprietary applications.

-
-
-

pugixml enables very fast, convenient and memory-efficient XML document processing. However, since pugixml has a DOM parser, it can’t process XML documents that do not fit in memory; also the parser is a non-validating one, so if you need DTD or XML Schema validation, the library is not for you.

-
-
-

This is the complete manual for pugixml, which describes all features of the library in detail. If you want to start writing code as quickly as possible, you are advised to read the quick start guide first.

-
-
- - - - - -
-
Note
-		 -No documentation is perfect; neither is this one. If you find errors or omissions, please don’t hesitate to submit an issue or open a pull request with a fix. -
-
-
-
-

1.2. Feedback

-
-

If you believe you’ve found a bug in pugixml (bugs include compilation problems (errors/warnings), crashes, performance degradation and incorrect behavior), please file an issue via issue submission form. Be sure to include the relevant information so that the bug can be reproduced: the version of pugixml, compiler version and target architecture, the code that uses pugixml and exhibits the bug, etc.

-
-
-

Feature requests can be reported the same way as bugs, so if you’re missing some functionality in pugixml or if the API is rough in some places and you can suggest an improvement, file an issue. However please note that there are many factors when considering API changes (compatibility with previous versions, API redundancy, etc.), so generally features that can be implemented via a small function without pugixml modification are not accepted. However, all rules have exceptions.

-
-
-

If you have a contribution to pugixml, such as build script for some build system/IDE, or a well-designed set of helper functions, or a binding to some language other than C++, please file an issue or open a pull request. Your contribution has to be distributed under the terms of a license that’s compatible with pugixml license; i.e. GPL/LGPL licensed code is not accepted.

-
-
-

If filing an issue is not possible due to privacy or other concerns, you can contact pugixml author by e-mail directly: arseny.kapoulkine@gmail.com.

-
-
-
-

1.3. Acknowledgments

-
-

pugixml could not be developed without the help from many people; some of them are listed in this section. If you’ve played a part in pugixml development and you can not find yourself on this list, I’m truly sorry; please send me an e-mail so I can fix this.

-
-
-

Thanks to Kristen Wegner for pugxml parser, which was used as a basis for pugixml.

-
-
-

Thanks to Neville Franks for contributions to pugxml parser.

-
-
-

Thanks to Artyom Palvelev for suggesting a lazy gap contraction approach.

-
-
-

Thanks to Vyacheslav Egorov for documentation proofreading and fuzz testing.

-
-
-
-

1.4. License

-
-

The pugixml library is distributed under the MIT license:

-
-
-
-
Copyright (c) 2006-2023 Arseny Kapoulkine
-
-Permission is hereby granted, free of charge, to any person
-obtaining a copy of this software and associated documentation
-files (the "Software"), to deal in the Software without
-restriction, including without limitation the rights to use,
-copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the
-Software is furnished to do so, subject to the following
-conditions:
-
-The above copyright notice and this permission notice shall be
-included in all copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
-OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
-NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
-HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
-WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
-FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
-OTHER DEALINGS IN THE SOFTWARE.
-
-
-
-

This means that you can freely use pugixml in your applications, both open-source and proprietary. If you use pugixml in a product, it is sufficient to add an acknowledgment like this to the product distribution:

-
-
-
-
This software is based on pugixml library (https://pugixml.org).
-pugixml is Copyright (C) 2006-2023 Arseny Kapoulkine.
-
-
-
-
-
-
-

2. Installation

-
-
-

2.1. Getting pugixml

-
-

pugixml is distributed in source form. You can either download a source distribution or clone the Git repository.

-
-
-

2.1.1. Source distributions

-
-

You can download the latest source distribution as an archive:

-
-
-

pugixml-1.14.zip (Windows line endings) -/ -pugixml-1.14.tar.gz (Unix line endings)

-
-
-

The distribution contains library source, documentation (the manual you’re reading now and the quick start guide) and some code examples. After downloading the distribution, install pugixml by extracting all files from the compressed archive.

-
-
-

If you need an older version, you can download it from the version archive.

-
-
-
-

2.1.2. Git repository

-
-

The Git repository is located at https://github.com/zeux/pugixml/. There is a Git tag "v{version}" for each version; also there is the "latest" tag, which always points to the latest stable release.

-
-
-

For example, to checkout the current version, you can use this command:

-
-
-
-
git clone https://github.com/zeux/pugixml
-cd pugixml
-git checkout v1.14
-
-
-
-

The repository contains library source, documentation, code examples and full unit test suite.

-
-
-

Use latest tag if you want to automatically get new versions. Use other tags if you want to switch to new versions only explicitly. Also please note that the master branch contains the work-in-progress version of the code; while this means that you can get new features and bug fixes from master without waiting for a new release, this also means that occasionally the code can be broken in some configurations.

-
-
-
-

2.1.3. Subversion repository

-
-

You can access the Git repository via Subversion using https://github.com/zeux/pugixml URL. For example, to checkout the current version, you can use this command:

-
-
-
-
svn checkout https://github.com/zeux/pugixml/tags/v1.14 pugixml
-
-
-
-
-

2.1.4. Packages

-
-

pugixml is available as a package via various package managers. Note that most packages are maintained separately from the main repository so they do not necessarily contain the latest version.

-
-
-

Here’s an incomplete list of pugixml packages in various systems:

-
-
- -
-
-
-
-

2.2. Building pugixml

-
-

pugixml is distributed in source form without any pre-built binaries; you have to build them yourself.

-
-
-

The complete pugixml source consists of three files - one source file, pugixml.cpp, and two header files, pugixml.hpp and pugiconfig.hpp. pugixml.hpp is the primary header which you need to include in order to use pugixml classes/functions; pugiconfig.hpp is a supplementary configuration file (see Additional configuration options). The rest of this guide assumes that pugixml.hpp is either in the current directory or in one of include directories of your projects, so that #include "pugixml.hpp" can find the header; however you can also use relative path (i.e. #include "../libs/pugixml/src/pugixml.hpp") or include directory-relative path (i.e. #include <xml/thirdparty/pugixml/src/pugixml.hpp>).

-
-
-

2.2.1. Building pugixml as a part of another static library/executable

-
-

The easiest way to build pugixml is to compile the source file, pugixml.cpp, along with the existing library/executable. This process depends on the method of building your application; for example, if you’re using Microsoft Visual Studio [1], Apple Xcode, Code::Blocks or any other IDE, just add pugixml.cpp to one of your projects.

-
-
-

If you’re using Microsoft Visual Studio and the project has precompiled headers turned on, you’ll see the following error messages:

-
-
-
-
pugixml.cpp(3477) : fatal error C1010: unexpected end of file while looking for precompiled header. Did you forget to add '#include "stdafx.h"' to your source?
-
-
-
-

The correct way to resolve this is to disable precompiled headers for pugixml.cpp; you have to set "Create/Use Precompiled Header" option (Properties dialog → C/C++ → Precompiled Headers → Create/Use Precompiled Header) to "Not Using Precompiled Headers". You’ll have to do it for all project configurations/platforms (you can select Configuration "All Configurations" and Platform "All Platforms" before editing the option):

-
- ------ - - - - - - - - -
-
-vs2005 pch1 -
-
-
-vs2005 pch2 -
-
-
-vs2005 pch3 -
-
-
-vs2005 pch4 -
-
-
-
-

2.2.2. Building pugixml as a standalone static library

-
-

It’s possible to compile pugixml as a standalone static library. This process depends on the method of building your application; pugixml distribution comes with project files for several popular IDEs/build systems. There are project files for Apple XCode, Code::Blocks, Codelite, Microsoft Visual Studio 2005, 2008, 2010+, and configuration scripts for CMake and premake4. You’re welcome to submit project files/build scripts for other software; see Feedback.

-
-
-

There are two projects for each version of Microsoft Visual Studio: one for dynamically linked CRT, which has a name like pugixml_vs2008.vcproj, and another one for statically linked CRT, which has a name like pugixml_vs2008_static.vcproj. You should select the version that matches the CRT used in your application; the default option for new projects created by Microsoft Visual Studio is dynamically linked CRT, so unless you changed the defaults, you should use the version with dynamic CRT (i.e. pugixml_vs2008.vcproj for Microsoft Visual Studio 2008).

-
-
-

In addition to adding pugixml project to your workspace, you’ll have to make sure that your application links with pugixml library. If you’re using Microsoft Visual Studio 2005/2008, you can add a dependency from your application project to pugixml one. If you’re using Microsoft Visual Studio 2010+, you’ll have to add a reference to your application project instead. For other IDEs/systems, consult the relevant documentation.

-
- ------ - - - - - - - - - - - - - - -
Microsoft Visual Studio 2005/2008Microsoft Visual Studio 2010+
-
-vs2005 link1 -
-
-
-vs2005 link2 -
-
-
-vs2010 link1 -
-
-
-vs2010 link2 -
-
-
-
-

2.2.3. Building pugixml as a standalone shared library

-
-

It’s possible to compile pugixml as a standalone shared library. The process is usually similar to the static library approach; however, no preconfigured projects/scripts are included into pugixml distribution, so you’ll have to do it yourself. Generally, if you’re using GCC-based toolchain, the process does not differ from building any other library as DLL (adding -shared to compilation flags should suffice); if you’re using MSVC-based toolchain, you’ll have to explicitly mark exported symbols with a declspec attribute. You can do it by defining PUGIXML_API macro, i.e. via pugiconfig.hpp:

-
-
-
-
#ifdef _DLL
-    #define PUGIXML_API __declspec(dllexport)
-#else
-    #define PUGIXML_API __declspec(dllimport)
-#endif
-
-
-
- - - - - -
-
Caution
-		 -If you’re using STL-related functions, you should use the shared runtime library to ensure that a single heap is used for STL allocations in your application and in pugixml; in MSVC, this means selecting the 'Multithreaded DLL' or 'Multithreaded Debug DLL' to 'Runtime library' property (/MD or /MDd linker switch). You should also make sure that your runtime library choice is consistent between different projects. -
-
-
-
-

2.2.4. Using pugixml in header-only mode

-
-

It’s possible to use pugixml in header-only mode. This means that all source code for pugixml will be included in every translation unit that includes pugixml.hpp. This is how most of Boost and STL libraries work.

-
-
-

Note that there are advantages and drawbacks of this approach. Header mode may improve tree traversal/modification performance (because many simple functions will be inlined), if your compiler toolchain does not support link-time optimization, or if you have it turned off (with link-time optimization the performance should be similar to non-header mode). However, since compiler now has to compile pugixml source once for each translation unit that includes it, compilation times may increase noticeably. If you want to use pugixml in header mode but do not need XPath support, you can consider disabling it by using PUGIXML_NO_XPATH define to improve compilation time.

-
-
-

To enable header-only mode, you have to define PUGIXML_HEADER_ONLY. You can either do it in pugiconfig.hpp, or provide them via compiler command-line.

-
-
-

Note that it is safe to compile pugixml.cpp if PUGIXML_HEADER_ONLY is defined - so if you want to i.e. use header-only mode only in Release configuration, you -can include pugixml.cpp in your project (see Building pugixml as a part of another static library/executable), and conditionally enable header-only mode in pugiconfig.hpp like this:

-
-
-
-
#ifndef _DEBUG
-    #define PUGIXML_HEADER_ONLY
-#endif
-
-
-
-
-

2.2.5. Additional configuration options

-
-

pugixml uses several defines to control the compilation process. There are two ways to define them: either put the needed definitions to pugiconfig.hpp (it has some examples that are commented out) or provide them via compiler command-line. Consistency is important: the definitions should match in all source files that include pugixml.hpp (including pugixml sources) throughout the application. Adding defines to pugiconfig.hpp lets you guarantee this, unless your macro definition is wrapped in preprocessor #if/#ifdef directive and this directive is not consistent. pugiconfig.hpp will never contain anything but comments, which means that when upgrading to a new version, you can safely leave your modified version intact.

-
-
-

PUGIXML_WCHAR_MODE define toggles between UTF-8 style interface (the in-memory text encoding is assumed to be UTF-8, most functions use char as character type) and UTF-16/32 style interface (the in-memory text encoding is assumed to be UTF-16/32, depending on wchar_t size, most functions use wchar_t as character type). See Unicode interface for more details.

-
-
-

PUGIXML_COMPACT define activates a different internal representation of document storage that is much more memory efficient for documents with a lot of markup (i.e. nodes and attributes), but is slightly slower to parse and access. For details see Compact mode.

-
-
-

PUGIXML_NO_XPATH define disables XPath. Both XPath interfaces and XPath implementation are excluded from compilation. This option is provided in case you do not need XPath functionality and need to save code space.

-
-
-

PUGIXML_NO_STL define disables use of STL in pugixml. The functions that operate on STL types are no longer present (i.e. load/save via iostream) if this macro is defined. This option is provided in case your target platform does not have a standard-compliant STL implementation.

-
-
-

PUGIXML_NO_EXCEPTIONS define disables use of exceptions in pugixml. This option is provided in case your target platform does not have exception handling capabilities.

-
-
-

PUGIXML_API, PUGIXML_CLASS and PUGIXML_FUNCTION defines let you specify custom attributes (i.e. declspec or calling conventions) for pugixml classes and non-member functions. In absence of PUGIXML_CLASS or PUGIXML_FUNCTION definitions, PUGIXML_API definition is used instead. For example, to specify fixed calling convention, you can define PUGIXML_FUNCTION to i.e. __fastcall. Another example is DLL import/export attributes in MSVC (see Building pugixml as a standalone shared library).

-
-
- - - - - -
-
Note
-		 -In that example PUGIXML_API is inconsistent between several source files; this is an exception to the consistency rule. -
-
-
-

PUGIXML_MEMORY_PAGE_SIZE, PUGIXML_MEMORY_OUTPUT_STACK and PUGIXML_MEMORY_XPATH_PAGE_SIZE can be used to customize certain important sizes to optimize memory usage for the application-specific patterns. For details see Memory consumption tuning.

-
-
-

PUGIXML_HAS_LONG_LONG define enables support for long long type in pugixml. This define is automatically enabled if your platform is known to have long long support (i.e. has C++11 support or uses a reasonably modern version of a known compiler); if pugixml does not recognize that your platform supports long long but in fact it does, you can enable the define manually.

-
-
-
-
-

2.3. Portability

-
-

pugixml is written in standard-compliant C++ with some compiler-specific workarounds where appropriate. pugixml is compatible with the C++11 standard, but does not require C++11 support. Each version is tested with a unit test suite with code coverage exceeding 99%.

-
-
-

pugixml runs on a variety of desktop platforms (including Microsoft Windows, Linux, FreeBSD, Apple MacOSX and Sun Solaris), game consoles (inclusing Microsoft Xbox 360, Microsoft Xbox One, Nintendo Wii, Sony Playstation Portable and Sony Playstation 3) and mobile platforms (including Android, iOS, BlackBerry, Samsung bada and Microsoft Windows CE).

-
-
-

pugixml supports various architectures, such as x86/x86-64, PowerPC, ARM, MIPS and SPARC. In general it should run on any architecture since it does not use architecture-specific code and does not rely on features such as unaligned memory access.

-
-
-

pugixml can be compiled using any C++ compiler; it was tested with all versions of Microsoft Visual C++ from 6.0 up to 2015, GCC from 3.4 up to 5.2, Clang from 3.2 up to 3.7, as well as a variety of other compilers (e.g. Borland C++, Digital Mars C++, Intel C++, Metrowerks CodeWarrior and PathScale). The code is written to avoid compilation warnings even on reasonably high warning levels.

-
-
-

Note that some platforms may have very bare-bones support of C++; in some cases you’ll have to use PUGIXML_NO_STL and/or PUGIXML_NO_EXCEPTIONS to compile without issues. This mostly applies to old game consoles and embedded systems.

-
-
-
-
-
-

3. Document object model

-
-
-

pugixml stores XML data in DOM-like way: the entire XML document (both document structure and element data) is stored in memory as a tree. The tree can be loaded from a character stream (file, string, C++ I/O stream), then traversed with the special API or XPath expressions. The whole tree is mutable: both node structure and node/attribute data can be changed at any time. Finally, the result of document transformations can be saved to a character stream (file, C++ I/O stream or custom transport).

-
-
-

3.1. Tree structure

-
-

The XML document is represented with a tree data structure. The root of the tree is the document itself, which corresponds to C++ type xml_document. Document has one or more child nodes, which correspond to C++ type xml_node. Nodes have different types; depending on a type, a node can have a collection of child nodes, a collection of attributes, which correspond to C++ type xml_attribute, and some additional data (i.e. name).

-
-
-

The tree nodes can be of one of the following types (which together form the enumeration xml_node_type):

-
-
-
    -
  • -

    Document node (node_document) - this is the root of the tree, which consists of several child nodes. This node corresponds to xml_document class; note that xml_document is a sub-class of xml_node, so the entire node interface is also available. However, document node is special in several ways, which are covered below. There can be only one document node in the tree; document node does not have any XML representation. Document generally has one child element node (see document_element()), although documents parsed from XML fragments (see parse_fragment) can have more than one.

    -
    • -
  • -

    Element/tag node (node_element) - this is the most common type of node, which represents XML elements. Element nodes have a name, a collection of attributes and a collection of child nodes (both of which may be empty). The attribute is a simple name/value pair. The example XML representation of element nodes is as follows:

    -
    -
    -
    <node attr="value"><child/></node>
    -
    -
    -
    -

    There are two element nodes here: one has name "node", single attribute "attr" and single child "child", another has name "child" and does not have any attributes or child nodes.

    -
    -
    • -
  • -

    Plain character data nodes (node_pcdata) represent plain text in XML. PCDATA nodes have a value, but do not have a name or children/attributes. Note that plain character data is not a part of the element node but instead has its own node; an element node can have several child PCDATA nodes. The example XML representation of text nodes is as follows:

    -
    -
    -
    <node> text1 <child/> text2 </node>
    -
    -
    -
    -

    Here "node" element has three children, two of which are PCDATA nodes with values " text1 " and " text2 ".

    -
    -
    • -
  • -

    Character data nodes (node_cdata) represent text in XML that is quoted in a special way. CDATA nodes do not differ from PCDATA nodes except in XML representation - the above text example looks like this with CDATA:

    -
    -
    -
    <node> <![CDATA[text1]]> <child/> <![CDATA[text2]]> </node>
    -
    -
    -
    -

    CDATA nodes make it easy to include non-escaped <, & and > characters in plain text. CDATA value can not contain the character sequence ]]>, since it is used to determine the end of node contents.

    -
    -
    • -
  • -

    Comment nodes (node_comment) represent comments in XML. Comment nodes have a value, but do not have a name or children/attributes. The example XML representation of a comment node is as follows:

    -
    -
    -
    <!-- comment text -->
    -
    -
    -
    -

    Here the comment node has value "comment text". By default comment nodes are treated as non-essential part of XML markup and are not loaded during XML parsing. You can override this behavior with parse_comments flag.

    -
    -
    • -
  • -

    Processing instruction node (node_pi) represent processing instructions (PI) in XML. PI nodes have a name and an optional value, but do not have children/attributes. The example XML representation of a PI node is as follows:

    -
    -
    -
    <?name value?>
    -
    -
    -
    -

    Here the name (also called PI target) is "name", and the value is "value". By default PI nodes are treated as non-essential part of XML markup and are not loaded during XML parsing. You can override this behavior with parse_pi flag.

    -
    -
    • -
  • -

    Declaration node (node_declaration) represents document declarations in XML. Declaration nodes have a name ("xml") and an optional collection of attributes, but do not have value or children. There can be only one declaration node in a document; moreover, it should be the topmost node (its parent should be the document). The example XML representation of a declaration node is as follows:

    -
    -
    -
    <?xml version="1.0"?>
    -
    -
    -
    -

    Here the node has name "xml" and a single attribute with name "version" and value "1.0". By default declaration nodes are treated as non-essential part of XML markup and are not loaded during XML parsing. You can override this behavior with parse_declaration flag. Also, by default a dummy declaration is output when XML document is saved unless there is already a declaration in the document; you can disable this with format_no_declaration flag.

    -
    -
    • -
  • -

    Document type declaration node (node_doctype) represents document type declarations in XML. Document type declaration nodes have a value, which corresponds to the entire document type contents; no additional nodes are created for inner elements like <!ENTITY>. There can be only one document type declaration node in a document; moreover, it should be the topmost node (its parent should be the document). The example XML representation of a document type declaration node is as follows:

    -
    -
    -
    <!DOCTYPE greeting [ <!ELEMENT greeting (#PCDATA)> ]>
    -
    -
    -
    -

    Here the node has value "greeting [ <!ELEMENT greeting (#PCDATA)> ]". By default document type declaration nodes are treated as non-essential part of XML markup and are not loaded during XML parsing. You can override this behavior with parse_doctype flag.

    -
    -
    • -
-
-
-

Finally, here is a complete example of XML document and the corresponding tree representation (samples/tree.xml):

-
- ---- - - - - - - -
-
-
<?xml version="1.0"?>
-<mesh name="mesh_root">
-    <!-- here is a mesh node -->
-    some text
-    <![CDATA[someothertext]]>
-    some more text
-    <node attr1="value1" attr2="value2" />
-    <node attr1="value2">
-        <innernode/>
-    </node>
-</mesh>
-<?include somedata?>
-
-
-
-dom tree -
-
-
-
-

3.2. C++ interface

-
- - - - - -
-
Note
-		 -All pugixml classes and functions are located in the pugi namespace; you have to either use explicit name qualification (i.e. pugi::xml_node), or to gain access to relevant symbols via using directive (i.e. using pugi::xml_node; or using namespace pugi;). The namespace will be omitted from all declarations in this documentation hereafter; all code examples will use fully qualified names. -
-
-
-

Despite the fact that there are several node types, there are only three C++ classes representing the tree (xml_document, xml_node, xml_attribute); some operations on xml_node are only valid for certain node types. The classes are described below.

-
-
-

-xml_document is the owner of the entire document structure; it is a non-copyable class. The interface of xml_document consists of loading functions (see Loading document), saving functions (see Saving document) and the entire interface of xml_node, which allows for document inspection and/or modification. Note that while xml_document is a sub-class of xml_node, xml_node is not a polymorphic type; the inheritance is present only to simplify usage. Alternatively you can use the document_element function to get the element node that’s the immediate child of the document.

-
-
-

-Default constructor of xml_document initializes the document to the tree with only a root node (document node). You can then populate it with data using either tree modification functions or loading functions; all loading functions destroy the previous tree with all occupied memory, which puts existing node/attribute handles for this document to invalid state. If you want to destroy the previous tree, you can use the xml_document::reset function; it destroys the tree and replaces it with either an empty one or a copy of the specified document. Destructor of xml_document also destroys the tree, thus the lifetime of the document object should exceed the lifetimes of any node/attribute handles that point to the tree.

-
-
- - - - - -
-
Caution
-		 -While technically node/attribute handles can be alive when the tree they’re referring to is destroyed, calling any member function for these handles results in undefined behavior. Thus it is recommended to make sure that the document is destroyed only after all references to its nodes/attributes are destroyed. -
-
-
-

-xml_node is the handle to document node; it can point to any node in the document, including the document node itself. There is a common interface for nodes of all types; the actual node type can be queried via the xml_node::type() method. Note that xml_node is only a handle to the actual node, not the node itself - you can have several xml_node handles pointing to the same underlying object. Destroying xml_node handle does not destroy the node and does not remove it from the tree. The size of xml_node is equal to that of a pointer, so it is nothing more than a lightweight wrapper around a pointer; you can safely pass or return xml_node objects by value without additional overhead.

-
-
-

There is a special value of xml_node type, known as null node or empty node (such nodes have type node_null). It does not correspond to any node in any document, and thus resembles null pointer. However, all operations are defined on empty nodes; generally the operations don’t do anything and return empty nodes/attributes or empty strings as their result (see documentation for specific functions for more detailed information). This is useful for chaining calls; i.e. you can get the grandparent of a node like so: node.parent().parent(); if a node is a null node or it does not have a parent, the first parent() call returns null node; the second parent() call then also returns null node, which makes error handling easier.

-
-
-

xml_attribute is the handle to an XML attribute; it has the same semantics as xml_node, i.e. there can be several xml_attribute handles pointing to the same underlying object and there is a special null attribute value, which propagates to function results.

-
-
-

-Both xml_node and xml_attribute have the default constructor which initializes them to null objects.

-
-
-

-xml_node and xml_attribute try to behave like pointers, that is, they can be compared with other objects of the same type, making it possible to use them as keys in associative containers. All handles to the same underlying object are equal, and any two handles to different underlying objects are not equal. Null handles only compare as equal to null handles. The result of relational comparison can not be reliably determined from the order of nodes in file or in any other way. Do not use relational comparison operators except for search optimization (i.e. associative container keys).

-
-
-

-If you want to use xml_node or xml_attribute objects as keys in hash-based associative containers, you can use the hash_value member functions. They return the hash values that are guaranteed to be the same for all handles to the same underlying object. The hash value for null handles is 0. Note that hash value does not depend on the content of the node, only on the location of the underlying structure in memory - this means that loading the same document twice will likely produce different hash values, and copying the node will not preserve the hash.

-
-
-

-Finally handles can be implicitly cast to boolean-like objects, so that you can test if the node/attribute is empty with the following code: if (node) { …​ } or if (!node) { …​ } else { …​ }. Alternatively you can check if a given xml_node/xml_attribute handle is null by calling the following methods:

-
-
-
-
bool xml_attribute::empty() const;
-bool xml_node::empty() const;
-
-
-
-

Nodes and attributes do not exist without a document tree, so you can’t create them without adding them to some document. Once underlying node/attribute objects are destroyed, the handles to those objects become invalid. While this means that destruction of the entire tree invalidates all node/attribute handles, it also means that destroying a subtree (by calling xml_node::remove_child) or removing an attribute invalidates the corresponding handles. There is no way to check handle validity; you have to ensure correctness through external mechanisms.

-
-
-
-

3.3. Unicode interface

-
-

There are two choices of interface and internal representation when configuring pugixml: you can either choose the UTF-8 (also called char) interface or UTF-16/32 (also called wchar_t) one. The choice is controlled via PUGIXML_WCHAR_MODE define; you can set it via pugiconfig.hpp or via preprocessor options, as discussed in Additional configuration options. If this define is set, the wchar_t interface is used; otherwise (by default) the char interface is used. The exact wide character encoding is assumed to be either UTF-16 or UTF-32 and is determined based on the size of wchar_t type.

-
-
- - - - - -
-
Note
-		 -If the size of wchar_t is 2, pugixml assumes UTF-16 encoding instead of UCS-2, which means that some characters are represented as two code points. -
-
-
-

All tree functions that work with strings work with either C-style null terminated strings or STL strings of the selected character type. For example, node name accessors look like this in char mode:

-
-
-
-
const char* xml_node::name() const;
-bool xml_node::set_name(const char* value);
-
-
-
-

and like this in wchar_t mode:

-
-
-
-
const wchar_t* xml_node::name() const;
-bool xml_node::set_name(const wchar_t* value);
-
-
-
-

-There is a special type, pugi::char_t, that is defined as the character type and depends on the library configuration; it will be also used in the documentation hereafter. There is also a type pugi::string_t, which is defined as the STL string of the character type; it corresponds to std::string in char mode and to std::wstring in wchar_t mode.

-
-
-

In addition to the interface, the internal implementation changes to store XML data as pugi::char_t; this means that these two modes have different memory usage characteristics - generally UTF-8 mode is more memory and performance efficient, especially if sizeof(wchar_t) is 4. The conversion to pugi::char_t upon document loading and from pugi::char_t upon document saving happen automatically, which also carries minor performance penalty. The general advice however is to select the character mode based on usage scenario, i.e. if UTF-8 is inconvenient to process and most of your XML data is non-ASCII, wchar_t mode is probably a better choice.

-
-
-

-There are cases when you’ll have to convert string data between UTF-8 and wchar_t encodings; the following helper functions are provided for such purposes:

-
-
-
-
std::string as_utf8(const wchar_t* str);
-std::wstring as_wide(const char* str);
-
-
-
-

Both functions accept a null-terminated string as an argument str, and return the converted string. as_utf8 performs conversion from UTF-16/32 to UTF-8; as_wide performs conversion from UTF-8 to UTF-16/32. Invalid UTF sequences are silently discarded upon conversion. str has to be a valid string; passing null pointer results in undefined behavior. There are also two overloads with the same semantics which accept a string as an argument:

-
-
-
-
std::string as_utf8(const std::wstring& str);
-std::wstring as_wide(const std::string& str);
-
-
-
- - - - - -
-
Note
-		 -
-

Most examples in this documentation assume char interface and therefore will not compile with PUGIXML_WCHAR_MODE. This is done to simplify the documentation; usually the only changes you’ll have to make is to pass wchar_t string literals, i.e. instead of

-
-
-

xml_node node = doc.child("bookstore").find_child_by_attribute("book", "id", "12345");

-
-
-

you’ll have to use

-
-
-

xml_node node = doc.child(L"bookstore").find_child_by_attribute(L"book", L"id", L"12345");

-
-
-
-
-
-

3.4. Thread-safety guarantees

-
-

Almost all functions in pugixml have the following thread-safety guarantees:

-
-
-
    -
  • -

    it is safe to call free (non-member) functions from multiple threads

    -
    • -
  • -

    it is safe to perform concurrent read-only accesses to the same tree (all constant member functions do not modify the tree)

    -
    • -
  • -

    it is safe to perform concurrent read/write accesses, if there is only one read or write access to the single tree at a time

    -
    • -
-
-
-

Concurrent modification and traversing of a single tree requires synchronization, for example via reader-writer lock. Modification includes altering document structure and altering individual node/attribute data, i.e. changing names/values.

-
-
-

The only exception is set_memory_management_functions; it modifies global variables and as such is not thread-safe. Its usage policy has more restrictions, see Custom memory allocation/deallocation functions.

-
-
-
-

3.5. Exception guarantees

-
-

With the exception of XPath, pugixml itself does not throw any exceptions. Additionally, most pugixml functions have a no-throw exception guarantee.

-
-
-

This is not applicable to functions that operate on STL strings or IOstreams; such functions have either strong guarantee (functions that operate on strings) or basic guarantee (functions that operate on streams). Also functions that call user-defined callbacks (i.e. xml_node::traverse or xml_node::find_node) do not provide any exception guarantees beyond the ones provided by the callback.

-
-
-

If exception handling is not disabled with PUGIXML_NO_EXCEPTIONS define, XPath functions may throw xpath_exception on parsing errors; also, XPath functions may throw std::bad_alloc in low memory conditions. Still, XPath functions provide strong exception guarantee.

-
-
-
-

3.6. Memory management

-
-

pugixml requests the memory needed for document storage in big chunks, and allocates document data inside those chunks. This section discusses replacing functions used for chunk allocation and internal memory management implementation.

-
-
-

3.6.1. Custom memory allocation/deallocation functions

-
-

-All memory for tree structure, tree data and XPath objects is allocated via globally specified functions, which default to malloc/free. You can set your own allocation functions with set_memory_management function. The function interfaces are the same as that of malloc/free:

-
-
-
-
typedef void* (*allocation_function)(size_t size);
-typedef void (*deallocation_function)(void* ptr);
-
-
-
-

-You can use the following accessor functions to change or get current memory management functions:

-
-
-
-
void set_memory_management_functions(allocation_function allocate, deallocation_function deallocate);
-allocation_function get_memory_allocation_function();
-deallocation_function get_memory_deallocation_function();
-
-
-
-

Allocation function is called with the size (in bytes) as an argument and should return a pointer to a memory block with alignment that is suitable for storage of primitive types (usually a maximum of void* and double types alignment is sufficient) and size that is greater than or equal to the requested one. If the allocation fails, the function has to either return null pointer or to throw an exception.

-
-
-

Deallocation function is called with the pointer that was returned by some call to allocation function; it is never called with a null pointer. If memory management functions are not thread-safe, library thread safety is not guaranteed.

-
-
-

This is a simple example of custom memory management (samples/custom_memory_management.cpp):

-
-
-
-
void* custom_allocate(size_t size)
-{
-    return new (std::nothrow) char[size];
-}
-
-void custom_deallocate(void* ptr)
-{
-    delete[] static_cast<char*>(ptr);
-}
-
-
-
-
-
pugi::set_memory_management_functions(custom_allocate, custom_deallocate);
-
-
-
-

When setting new memory management functions, care must be taken to make sure that there are no live pugixml objects. Otherwise when the objects are destroyed, the new deallocation function will be called with the memory obtained by the old allocation function, resulting in undefined behavior.

-
-
-
-

3.6.2. Memory consumption tuning

-
-

There are several important buffering optimizations in pugixml that rely on predefined constants. These constants have default values that were tuned for common usage patterns; for some applications, changing these constants might improve memory consumption or increase performance. Changing these constants is not recommended unless their default values result in visible problems.

-
-
-

These constants can be tuned via configuration defines, as discussed in Additional configuration options; it is recommended to set them in pugiconfig.hpp.

-
-
-
    -
  • -

    PUGIXML_MEMORY_PAGE_SIZE controls the page size for document memory allocation. Memory for node/attribute objects is allocated in pages of the specified size. The default size is 32 Kb; for some applications the size is too large (i.e. embedded systems with little heap space or applications that keep lots of XML documents in memory). A minimum size of 1 Kb is recommended.

    -
    • -
  • -

    PUGIXML_MEMORY_OUTPUT_STACK controls the cumulative stack space required to output the node. Any output operation (i.e. saving a subtree to file) uses an internal buffering scheme for performance reasons. The default size is 10 Kb; if you’re using node output from threads with little stack space, decreasing this value can prevent stack overflows. A minimum size of 1 Kb is recommended.

    -
    • -
  • -

    PUGIXML_MEMORY_XPATH_PAGE_SIZE controls the page size for XPath memory allocation. Memory for XPath query objects as well as internal memory for XPath evaluation is allocated in pages of the specified size. The default size is 4 Kb; if you have a lot of resident XPath query objects, you might need to decrease the size to improve memory consumption. A minimum size of 256 bytes is recommended.

    -
    • -
-
-
-
-

3.6.3. Document memory management internals

-
-

Constructing a document object using the default constructor does not result in any allocations; document node is stored inside the xml_document object.

-
-
-

When the document is loaded from file/buffer, unless an inplace loading function is used (see Loading document from memory), a complete copy of character stream is made; all names/values of nodes and attributes are allocated in this buffer. This buffer is allocated via a single large allocation and is only freed when document memory is reclaimed (i.e. if the xml_document object is destroyed or if another document is loaded in the same object). Also when loading from file or stream, an additional large allocation may be performed if encoding conversion is required; a temporary buffer is allocated, and it is freed before load function returns.

-
-
-

All additional memory, such as memory for document structure (node/attribute objects) and memory for node/attribute names/values is allocated in pages on the order of 32 Kb; actual objects are allocated inside the pages using a memory management scheme optimized for fast allocation/deallocation of many small objects. Because of the scheme specifics, the pages are only destroyed if all objects inside them are destroyed; also, generally destroying an object does not mean that subsequent object creation will reuse the same memory. This means that it is possible to devise a usage scheme which will lead to higher memory usage than expected; one example is adding a lot of nodes, and them removing all even numbered ones; not a single page is reclaimed in the process. However this is an example specifically crafted to produce unsatisfying behavior; in all practical usage scenarios the memory consumption is less than that of a general-purpose allocator because allocation meta-data is very small in size.

-
-
-
-

3.6.4. Compact mode

-
-

By default nodes and attributes are optimized for efficiency of access. This can cause them to take a significant amount of memory - for documents with a lot of nodes and not a lot of contents (short attribute values/node text), and depending on the pointer size, the document structure can take noticeably more memory than the document itself (e.g. on a 64-bit platform in UTF-8 mode a markup-heavy document with the file size of 2.1 Mb can use 2.1 Mb for document buffer and 8.3 Mb for document structure).

-
-
-

If you are processing big documents or your platform is memory constrained and you’re willing to sacrifice a bit of performance for memory, you can compile pugixml with PUGIXML_COMPACT define which will activate compact mode. Compact mode uses a different representation of the document structure that assumes locality of reference between nodes and attributes to optimize memory usage. As a result you get significantly smaller node/attribute objects; usually most objects in most documents don’t require additional storage, but in the worst case - if assumptions about locality of reference don’t hold - additional memory will be allocated to store the extra data required.

-
-
-

The compact storage supports all existing operations - including tree modification - with the same amortized complexity (that is, all basic document manipulations are still O(1) on average). The operations are slightly slower; you can usually expect 10-50% slowdown in terms of processing time unless your processing was memory-bound.

-
-
-

On 32-bit architectures document structure in compact mode is typically reduced by around 2.5x; on 64-bit architectures the ratio is around 5x. Thus for big markup-heavy documents compact mode can make the difference between the processing of a multi-gigabyte document running completely from RAM vs requiring swapping to disk. Even if the document fits into memory, compact storage can use CPU caches more efficiently by taking less space and causing less cache/TLB misses.

-
-
-
-
-
-
-

4. Loading document

-
-
-

pugixml provides several functions for loading XML data from various places - files, C++ iostreams, memory buffers. All functions use an extremely fast non-validating parser. This parser is not fully W3C conformant - it can load any valid XML document, but does not perform some well-formedness checks. While considerable effort is made to reject invalid XML documents, some validation is not performed for performance reasons. Also some XML transformations (i.e. EOL handling or attribute value normalization) can impact parsing speed and thus can be disabled. However for vast majority of XML documents there is no performance difference between different parsing options. Parsing options also control whether certain XML nodes are parsed; see Parsing options for more information.

-
-
-

XML data is always converted to internal character format (see Unicode interface) before parsing. pugixml supports all popular Unicode encodings (UTF-8, UTF-16 (big and little endian), UTF-32 (big and little endian); UCS-2 is naturally supported since it’s a strict subset of UTF-16) as well as some non-Unicode encodings (Latin-1) and handles all encoding conversions automatically. Unless explicit encoding is specified, loading functions perform automatic encoding detection based on source XML data, so in most cases you do not have to specify document encoding. Encoding conversion is described in more detail in Encodings.

-
-
-

4.1. Loading document from file

-
-

-The most common source of XML data is files; pugixml provides dedicated functions for loading an XML document from file:

-
-
-
-
xml_parse_result xml_document::load_file(const char* path, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);
-xml_parse_result xml_document::load_file(const wchar_t* path, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);
-
-
-
-

These functions accept the file path as its first argument, and also two optional arguments, which specify parsing options (see Parsing options) and input data encoding (see Encodings). The path has the target operating system format, so it can be a relative or absolute one, it should have the delimiters of the target system, it should have the exact case if the target file system is case-sensitive, etc.

-
-
-

File path is passed to the system file opening function as is in case of the first function (which accepts const char* path); the second function either uses a special file opening function if it is provided by the runtime library or converts the path to UTF-8 and uses the system file opening function.

-
-
-

load_file destroys the existing document tree and then tries to load the new tree from the specified file. The result of the operation is returned in an xml_parse_result object; this object contains the operation status and the related information (i.e. last successfully parsed position in the input file, if parsing fails). See Handling parsing errors for error handling details.

-
-
-

This is an example of loading XML document from file (samples/load_file.cpp):

-
-
-
-
pugi::xml_document doc;
-
-pugi::xml_parse_result result = doc.load_file("tree.xml");
-
-std::cout << "Load result: " << result.description() << ", mesh name: " << doc.child("mesh").attribute("name").value() << std::endl;
-
-
-
-
-

4.2. Loading document from memory

-
-

-Sometimes XML data should be loaded from some other source than a file, i.e. HTTP URL; also you may want to load XML data from file using non-standard functions, i.e. to use your virtual file system facilities or to load XML from GZip-compressed files. All these scenarios require loading document from memory. First you should prepare a contiguous memory block with all XML data; then you have to invoke one of buffer loading functions. These functions will handle the necessary encoding conversions, if any, and then will parse the data into the corresponding XML tree. There are several buffer loading functions, which differ in the behavior and thus in performance/memory usage:

-
-
-
-
xml_parse_result xml_document::load_buffer(const void* contents, size_t size, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);
-xml_parse_result xml_document::load_buffer_inplace(void* contents, size_t size, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);
-xml_parse_result xml_document::load_buffer_inplace_own(void* contents, size_t size, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);
-
-
-
-

All functions accept the buffer which is represented by a pointer to XML data, contents, and data size in bytes. Also there are two optional arguments, which specify parsing options (see Parsing options) and input data encoding (see Encodings). The buffer does not have to be zero-terminated.

-
-
-

load_buffer function works with immutable buffer - it does not ever modify the buffer. Because of this restriction it has to create a private buffer and copy XML data to it before parsing (applying encoding conversions if necessary). This copy operation carries a performance penalty, so inplace functions are provided - load_buffer_inplace and load_buffer_inplace_own store the document data in the buffer, modifying it in the process. In order for the document to stay valid, you have to make sure that the buffer’s lifetime exceeds that of the tree if you’re using inplace functions. In addition to that, load_buffer_inplace does not assume ownership of the buffer, so you’ll have to destroy it yourself; load_buffer_inplace_own assumes ownership of the buffer and destroys it once it is not needed. This means that if you’re using load_buffer_inplace_own, you have to allocate memory with pugixml allocation function (you can get it via get_memory_allocation_function).

-
-
-

The best way from the performance/memory point of view is to load document using load_buffer_inplace_own; this function has maximum control of the buffer with XML data so it is able to avoid redundant copies and reduce peak memory usage while parsing. This is the recommended function if you have to load the document from memory and performance is critical.

-
-
-

There is also a simple helper function for cases when you want to load the XML document from null-terminated character string:

-
-
-
-
xml_parse_result xml_document::load_string(const char_t* contents, unsigned int options = parse_default);
-
-
-
-

It is equivalent to calling load_buffer with size being either strlen(contents) or wcslen(contents) * sizeof(wchar_t), depending on the character type. This function assumes native encoding for input data, so it does not do any encoding conversion. In general, this function is fine for loading small documents from string literals, but has more overhead and less functionality than the buffer loading functions.

-
-
-

This is an example of loading XML document from memory using different functions (samples/load_memory.cpp):

-
-
-
-
const char source[] = "<mesh name='sphere'><bounds>0 0 1 1</bounds></mesh>";
-size_t size = sizeof(source);
-
-
-
-
-
// You can use load_buffer to load document from immutable memory block:
-pugi::xml_parse_result result = doc.load_buffer(source, size);
-
-
-
-
-
// You can use load_buffer_inplace to load document from mutable memory block; the block's lifetime must exceed that of document
-char* buffer = new char[size];
-memcpy(buffer, source, size);
-
-// The block can be allocated by any method; the block is modified during parsing
-pugi::xml_parse_result result = doc.load_buffer_inplace(buffer, size);
-
-// You have to destroy the block yourself after the document is no longer used
-delete[] buffer;
-
-
-
-
-
// You can use load_buffer_inplace_own to load document from mutable memory block and to pass the ownership of this block
-// The block has to be allocated via pugixml allocation function - using i.e. operator new here is incorrect
-char* buffer = static_cast<char*>(pugi::get_memory_allocation_function()(size));
-memcpy(buffer, source, size);
-
-// The block will be deleted by the document
-pugi::xml_parse_result result = doc.load_buffer_inplace_own(buffer, size);
-
-
-
-
-
// You can use load to load document from null-terminated strings, for example literals:
-pugi::xml_parse_result result = doc.load_string("<mesh name='sphere'><bounds>0 0 1 1</bounds></mesh>");
-
-
-
-
-

4.3. Loading document from C++ IOstreams

-
-

To enhance interoperability, pugixml provides functions for loading document from any object which implements C++ std::istream interface. This allows you to load documents from any standard C++ stream (i.e. file stream) or any third-party compliant implementation (i.e. Boost Iostreams). There are two functions, one works with narrow character streams, another handles wide character ones:

-
-
-
-
xml_parse_result xml_document::load(std::istream& stream, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);
-xml_parse_result xml_document::load(std::wistream& stream, unsigned int options = parse_default);
-
-
-
-

load with std::istream argument loads the document from stream from the current read position to the end, treating the stream contents as a byte stream of the specified encoding (with encoding autodetection as necessary). Thus calling xml_document::load on an opened std::ifstream object is equivalent to calling xml_document::load_file.

-
-
-

load with std::wstream argument treats the stream contents as a wide character stream (encoding is always encoding_wchar). Because of this, using load with wide character streams requires careful (usually platform-specific) stream setup (i.e. using the imbue function). Generally use of wide streams is discouraged, however it provides you the ability to load documents from non-Unicode encodings, i.e. you can load Shift-JIS encoded data if you set the correct locale.

-
-
-

This is a simple example of loading XML document from file using streams (samples/load_stream.cpp); read the sample code for more complex examples involving wide streams and locales:

-
-
-
-
std::ifstream stream("weekly-utf-8.xml");
-pugi::xml_parse_result result = doc.load(stream);
-
-
-
-
-

4.4. Handling parsing errors

-
-

All document loading functions return the parsing result via xml_parse_result object. It contains parsing status, the offset of last successfully parsed character from the beginning of the source stream, and the encoding of the source stream:

-
-
-
-
struct xml_parse_result
-{
-    xml_parse_status status;
-    ptrdiff_t offset;
-    xml_encoding encoding;
-
-    operator bool() const;
-    const char* description() const;
-};
-
-
-
-

-Parsing status is represented as the xml_parse_status enumeration and can be one of the following:

-
-
-
    -
  • -

    status_ok means that no error was encountered during parsing; the source stream represents the valid XML document which was fully parsed and converted to a tree.

    -
    • -
  • -

    status_file_not_found is only returned by load_file function and means that file could not be opened.

    -
    • -
  • -

    status_io_error is returned by load_file function and by load functions with std::istream/std::wstream arguments; it means that some I/O error has occurred during reading the file/stream.

    -
    • -
  • -

    status_out_of_memory means that there was not enough memory during some allocation; any allocation failure during parsing results in this error.

    -
    • -
  • -

    status_internal_error means that something went horribly wrong; currently this error does not occur

    -
    • -
  • -

    status_unrecognized_tag means that parsing stopped due to a tag with either an empty name or a name which starts with incorrect character, such as #.

    -
    • -
  • -

    status_bad_pi means that parsing stopped due to incorrect document declaration/processing instruction

    -
    • -
  • -

    status_bad_comment, status_bad_cdata, status_bad_doctype and status_bad_pcdata mean that parsing stopped due to the invalid construct of the respective type

    -
    • -
  • -

    status_bad_start_element means that parsing stopped because starting tag either had no closing > symbol or contained some incorrect symbol

    -
    • -
  • -

    status_bad_attribute means that parsing stopped because there was an incorrect attribute, such as an attribute without value or with value that is not quoted (note that <node attr=1> is incorrect in XML)

    -
    • -
  • -

    status_bad_end_element means that parsing stopped because ending tag had incorrect syntax (i.e. extra non-whitespace symbols between tag name and >)

    -
    • -
  • -

    status_end_element_mismatch means that parsing stopped because the closing tag did not match the opening one (i.e. <node></nedo>) or because some tag was not closed at all

    -
    • -
  • -

    status_no_document_element means that no element nodes were discovered during parsing; this usually indicates an empty or invalid document

    -
    • -
-
-
-

description() member function can be used to convert parsing status to a string; the returned message is always in English, so you’ll have to write your own function if you need a localized string. However please note that the exact messages returned by description() function may change from version to version, so any complex status handling should be based on status value. Note that description() returns a char string even in PUGIXML_WCHAR_MODE; you’ll have to call as_wide to get the wchar_t string.

-
-
-

If parsing failed because the source data was not a valid XML, the resulting tree is not destroyed - despite the fact that load function returns error, you can use the part of the tree that was successfully parsed. Obviously, the last element may have an unexpected name/value; for example, if the attribute value does not end with the necessary quotation mark, like in <node attr="value>some data</node> example, the value of attribute attr will contain the string value>some data</node>.

-
-
-

In addition to the status code, parsing result has an offset member, which contains the offset of last successfully parsed character if parsing failed because of an error in source data; otherwise offset is 0. For parsing efficiency reasons, pugixml does not track the current line during parsing; this offset is in units of pugi::char_t (bytes for character mode, wide characters for wide character mode). Many text editors support 'Go To Position' feature - you can use it to locate the exact error position. Alternatively, if you’re loading the document from memory, you can display the error chunk along with the error description (see the example code below).

-
-
- - - - - -
-
Caution
-		 -Offset is calculated in the XML buffer in native encoding; if encoding conversion is performed during parsing, offset can not be used to reliably track the error position. -
-
-
-

Parsing result also has an encoding member, which can be used to check that the source data encoding was correctly guessed. It is equal to the exact encoding used during parsing (i.e. with the exact endianness); see Encodings for more information.

-
-
-

Parsing result object can be implicitly converted to bool; if you do not want to handle parsing errors thoroughly, you can just check the return value of load functions as if it was a bool: if (doc.load_file("file.xml")) { …​ } else { …​ }.

-
-
-

This is an example of handling loading errors (samples/load_error_handling.cpp):

-
-
-
-
pugi::xml_document doc;
-pugi::xml_parse_result result = doc.load_string(source);
-
-if (result)
-{
-    std::cout << "XML [" << source << "] parsed without errors, attr value: [" << doc.child("node").attribute("attr").value() << "]\n\n";
-}
-else
-{
-    std::cout << "XML [" << source << "] parsed with errors, attr value: [" << doc.child("node").attribute("attr").value() << "]\n";
-    std::cout << "Error description: " << result.description() << "\n";
-    std::cout << "Error offset: " << result.offset << " (error at [..." << (source + result.offset) << "]\n\n";
-}
-
-
-
-
-

4.5. Parsing options

-
-

All document loading functions accept the optional parameter options. This is a bitmask that customizes the parsing process: you can select the node types that are parsed and various transformations that are performed with the XML text. Disabling certain transformations can improve parsing performance for some documents; however, the code for all transformations is very well optimized, and thus the majority of documents won’t get any performance benefit. As a rule of thumb, only modify parsing flags if you want to get some nodes in the document that are excluded by default (i.e. declaration or comment nodes).

-
-
- - - - - -
-
Note
-		 -You should use the usual bitwise arithmetics to manipulate the bitmask: to enable a flag, use mask | flag; to disable a flag, use mask & ~flag. -
-
-
-

These flags control the resulting tree contents:

-
-
-
    -
  • -

    parse_declaration determines if XML document declaration (node with type node_declaration) is to be put in DOM tree. If this flag is off, it is not put in the tree, but is still parsed and checked for correctness. This flag is off by default.

    -
    • -
  • -

    parse_doctype determines if XML document type declaration (node with type node_doctype) is to be put in DOM tree. If this flag is off, it is not put in the tree, but is still parsed and checked for correctness. This flag is off by default.

    -
    • -
  • -

    parse_pi determines if processing instructions (nodes with type node_pi) are to be put in DOM tree. If this flag is off, they are not put in the tree, but are still parsed and checked for correctness. Note that <?xml …​?> (document declaration) is not considered to be a PI. This flag is off by default.

    -
    • -
  • -

    parse_comments determines if comments (nodes with type node_comment) are to be put in DOM tree. If this flag is off, they are not put in the tree, but are still parsed and checked for correctness. This flag is off by default.

    -
    • -
  • -

    parse_cdata determines if CDATA sections (nodes with type node_cdata) are to be put in DOM tree. If this flag is off, they are not put in the tree, but are still parsed and checked for correctness. This flag is on by default.

    -
    • -
  • -

    parse_trim_pcdata determines if leading and trailing whitespace characters are to be removed from PCDATA nodes. While for some applications leading/trailing whitespace is significant, often the application only cares about the non-whitespace contents so it’s easier to trim whitespace from text during parsing. This flag is off by default.

    -
    • -
  • -

    parse_ws_pcdata determines if PCDATA nodes (nodes with type node_pcdata) that consist only of whitespace characters are to be put in DOM tree. Often whitespace-only data is not significant for the application, and the cost of allocating and storing such nodes (both memory and speed-wise) can be significant. For example, after parsing XML string <node> <a/> </node>, <node> element will have three children when parse_ws_pcdata is set (child with type node_pcdata and value " ", child with type node_element and name "a", and another child with type node_pcdata and value " "), and only one child when parse_ws_pcdata is not set. This flag is off by default.

    -
    • -
  • -

    parse_ws_pcdata_single determines if whitespace-only PCDATA nodes that have no sibling nodes are to be put in DOM tree. In some cases application needs to parse the whitespace-only contents of nodes, i.e. <node> </node>, but is not interested in whitespace markup elsewhere. It is possible to use parse_ws_pcdata flag in this case, but it results in excessive allocations and complicates document processing; this flag can be used to avoid that. As an example, after parsing XML string <node> <a> </a> </node> with parse_ws_pcdata_single flag set, <node> element will have one child <a>, and <a> element will have one child with type node_pcdata and value " ". This flag has no effect if parse_ws_pcdata is enabled. This flag is off by default.

    -
    • -
  • -

    parse_embed_pcdata determines if PCDATA contents is to be saved as element values. Normally element nodes have names but not values; this flag forces the parser to store the contents as a value if PCDATA is the first child of the element node (otherwise PCDATA node is created as usual). This can significantly reduce the memory required for documents with many PCDATA nodes. To retrieve the data you can use xml_node::value() on the element nodes or any of the higher-level functions like child_value or text. This flag is off by default. -Since this flag significantly changes the DOM structure it is only recommended for parsing documents with many PCDATA nodes in memory-constrained environments. This flag is off by default.

    -
    • -
  • -

    parse_merge_pcdata determines if PCDATA contents is to be merged with the previous PCDATA node when no intermediary nodes are present between them. If the PCDATA contains CDATA sections, PI nodes, or comments in between, and either of the flags parse_cdata ,parse_pi ,parse_comments is not set, the contents of the PCDATA node will be merged with the previous one. This flag is off by default.

    -
    • -
  • -

    parse_fragment determines if document should be treated as a fragment of a valid XML. Parsing document as a fragment leads to top-level PCDATA content (i.e. text that is not located inside a node) to be added to a tree, and additionally treats documents without element nodes as valid and permits multiple top-level element nodes (currently multiple top-level element nodes are also permitted when the flag is off, but that behavior should not be relied on). This flag is off by default.

    -
    • -
-
-
- - - - - -
-
Caution
-		 -Using in-place parsing (load_buffer_inplace) with parse_fragment flag may result in the loss of the last character of the buffer if it is a part of PCDATA. Since PCDATA values are null-terminated strings, the only way to resolve this is to provide a null-terminated buffer as an input to load_buffer_inplace - i.e. doc.load_buffer_inplace("test\0", 5, pugi::parse_default | pugi::parse_fragment). -
-
-
-

These flags control the transformation of tree element contents:

-
-
-
    -
  • -

    parse_escapes determines if character and entity references are to be expanded during the parsing process. Character references have the form &#…​; or &#x…​; (…​ is Unicode numeric representation of character in either decimal (&#…​;) or hexadecimal (&#x…​;) form), entity references are &lt;, &gt;, &amp;, &apos; and &quot; (note that as pugixml does not handle DTD, the only allowed entities are predefined ones). If character/entity reference can not be expanded, it is left as is, so you can do additional processing later. Reference expansion is performed on attribute values and PCDATA content. This flag is on by default.

    -
    • -
  • -

    parse_eol determines if EOL handling (that is, replacing sequences \r\n by a single \n character, and replacing all standalone \r characters by \n) is to be performed on input data (that is, comment contents, PCDATA/CDATA contents and attribute values). This flag is on by default.

    -
    • -
  • -

    parse_wconv_attribute determines if attribute value normalization should be performed for all attributes. This means, that whitespace characters (new line, tab and space) are replaced with space (' '). New line characters are always treated as if parse_eol is set, i.e. \r\n is converted to a single space. This flag is on by default.

    -
    • -
  • -

    parse_wnorm_attribute determines if extended attribute value normalization should be performed for all attributes. This means, that after attribute values are normalized as if parse_wconv_attribute was set, leading and trailing space characters are removed, and all sequences of space characters are replaced by a single space character. parse_wconv_attribute has no effect if this flag is on. This flag is off by default.

    -
    • -
-
-
- - - - - -
-
Note
-		 -parse_wconv_attribute option performs transformations that are required by W3C specification for attributes that are declared as CDATA; parse_wnorm_attribute performs transformations required for NMTOKENS attributes. In the absence of document type declaration all attributes should behave as if they are declared as CDATA, thus parse_wconv_attribute is the default option. -
-
-
-

Additionally there are three predefined option masks:

-
-
-
    -
  • -

    parse_minimal has all options turned off. This option mask means that pugixml does not add declaration nodes, document type declaration nodes, PI nodes, CDATA sections and comments to the resulting tree and does not perform any conversion for input data, so theoretically it is the fastest mode. However, as mentioned above, in practice parse_default is usually equally fast.

    -
    • -
  • -

    parse_default is the default set of flags, i.e. it has all options set to their default values. It includes parsing CDATA sections (comments/PIs are not parsed), performing character and entity reference expansion, replacing whitespace characters with spaces in attribute values and performing EOL handling. Note, that PCDATA sections consisting only of whitespace characters are not parsed (by default) for performance reasons.

    -
    • -
  • -

    parse_full is the set of flags which adds nodes of all types to the resulting tree and performs default conversions for input data. It includes parsing CDATA sections, comments, PI nodes, document declaration node and document type declaration node, performing character and entity reference expansion, replacing whitespace characters with spaces in attribute values and performing EOL handling. Note, that PCDATA sections consisting only of whitespace characters are not parsed in this mode.

    -
    • -
-
-
-

This is an example of using different parsing options (samples/load_options.cpp):

-
-
-
-
const char* source = "<!--comment--><node>&lt;</node>";
-
-// Parsing with default options; note that comment node is not added to the tree, and entity reference &lt; is expanded
-doc.load_string(source);
-std::cout << "First node value: [" << doc.first_child().value() << "], node child value: [" << doc.child_value("node") << "]\n";
-
-// Parsing with additional parse_comments option; comment node is now added to the tree
-doc.load_string(source, pugi::parse_default | pugi::parse_comments);
-std::cout << "First node value: [" << doc.first_child().value() << "], node child value: [" << doc.child_value("node") << "]\n";
-
-// Parsing with additional parse_comments option and without the (default) parse_escapes option; &lt; is not expanded
-doc.load_string(source, (pugi::parse_default | pugi::parse_comments) & ~pugi::parse_escapes);
-std::cout << "First node value: [" << doc.first_child().value() << "], node child value: [" << doc.child_value("node") << "]\n";
-
-// Parsing with minimal option mask; comment node is not added to the tree, and &lt; is not expanded
-doc.load_string(source, pugi::parse_minimal);
-std::cout << "First node value: [" << doc.first_child().value() << "], node child value: [" << doc.child_value("node") << "]\n";
-
-
-
-
-

4.6. Encodings

-
-

pugixml supports all popular Unicode encodings (UTF-8, UTF-16 (big and little endian), UTF-32 (big and little endian); UCS-2 is naturally supported since it’s a strict subset of UTF-16) as well as some non-Unicode encodings (Latin-1) and handles all encoding conversions. Most loading functions accept the optional parameter encoding. This is a value of enumeration type xml_encoding, that can have the following values:

-
-
-
    -
  • -

    encoding_auto means that pugixml will try to guess the encoding based on source XML data. The algorithm is a modified version of the one presented in Appendix F of XML recommendation. It tries to find a Byte Order Mark of one of the supported encodings first; if that fails, it checks if the first few bytes of the input data look like a representation of < or <? in one of UTF-16 or UTF-32 variants; if that fails as well, encoding is assumed to be either UTF-8 or one of the non-Unicode encodings - to make the final decision the algorithm tries to parse the encoding attribute of the XML document declaration, ultimately falling back to UTF-8 if document declaration is not present or does not specify a supported encoding.

    -
    • -
  • -

    encoding_utf8 corresponds to UTF-8 encoding as defined in the Unicode standard; UTF-8 sequences with length equal to 5 or 6 are not standard and are rejected.

    -
    • -
  • -

    encoding_utf16_le corresponds to little-endian UTF-16 encoding as defined in the Unicode standard; surrogate pairs are supported.

    -
    • -
  • -

    encoding_utf16_be corresponds to big-endian UTF-16 encoding as defined in the Unicode standard; surrogate pairs are supported.

    -
    • -
  • -

    encoding_utf16 corresponds to UTF-16 encoding as defined in the Unicode standard; the endianness is assumed to be that of the target platform.

    -
    • -
  • -

    encoding_utf32_le corresponds to little-endian UTF-32 encoding as defined in the Unicode standard.

    -
    • -
  • -

    encoding_utf32_be corresponds to big-endian UTF-32 encoding as defined in the Unicode standard.

    -
    • -
  • -

    encoding_utf32 corresponds to UTF-32 encoding as defined in the Unicode standard; the endianness is assumed to be that of the target platform.

    -
    • -
  • -

    encoding_wchar corresponds to the encoding of wchar_t type; it has the same meaning as either encoding_utf16 or encoding_utf32, depending on wchar_t size.

    -
    • -
  • -

    encoding_latin1 corresponds to ISO-8859-1 encoding (also known as Latin-1).

    -
    • -
-
-
-

The algorithm used for encoding_auto correctly detects any supported Unicode encoding for all well-formed XML documents (since they start with document declaration) and for all other XML documents that start with <; if your XML document does not start with < and has encoding that is different from UTF-8, use the specific encoding.

-
-
- - - - - -
-
Note
-		 -The current behavior for Unicode conversion is to skip all invalid UTF sequences during conversion. This behavior should not be relied upon; moreover, in case no encoding conversion is performed, the invalid sequences are not removed, so you’ll get them as is in node/attribute contents. -
-
-
-
-

4.7. Conformance to W3C specification

-
-

pugixml is not fully W3C conformant - it can load any valid XML document, but does not perform some well-formedness checks. While considerable effort is made to reject invalid XML documents, some validation is not performed because of performance reasons.

-
-
-

There is only one non-conformant behavior when dealing with valid XML documents: pugixml does not use information supplied in document type declaration for parsing. This means that entities declared in DOCTYPE are not expanded, and all attribute/PCDATA values are always processed in a uniform way that depends only on parsing options.

-
-
-

As for rejecting invalid XML documents, there are a number of incompatibilities with W3C specification, including:

-
-
-
    -
  • -

    Multiple attributes of the same node can have equal names.

    -
    • -
  • -

    Tag and attribute names are not fully validated for consisting of allowed characters, so some invalid tags are not rejected

    -
    • -
  • -

    Attribute values which contain < are not rejected.

    -
    • -
  • -

    Invalid entity/character references are not rejected and are instead left as is.

    -
    • -
  • -

    Comment values can contain --.

    -
    • -
  • -

    XML data is not required to begin with document declaration; additionally, document declaration can appear after comments and other nodes.

    -
    • -
  • -

    Invalid document type declarations are silently ignored in some cases.

    -
    • -
  • -

    Unicode validation is not performed so invalid UTF sequences are not rejected.

    -
    • -
  • -

    Document can contain multiple top-level element nodes.

    -
    • -
-
-
-
-
-
-

5. Accessing document data

-
-
-

pugixml features an extensive interface for getting various types of data from the document and for traversing the document. This section provides documentation for all such functions that do not modify the tree except for XPath-related functions; see XPath for XPath reference. As discussed in C++ interface, there are two types of handles to tree data - xml_node and xml_attribute. The handles have special null (empty) values which propagate through various functions and thus are useful for writing more concise code; see this description for details. The documentation in this section will explicitly state the results of all function in case of null inputs.

-
-
-

Basic traversal functions

-
-

-The internal representation of the document is a tree, where each node has a list of child nodes (the order of children corresponds to their order in the XML representation), and additionally element nodes have a list of attributes, which is also ordered. Several functions are provided in order to let you get from one node in the tree to the other. These functions roughly correspond to the internal representation, and thus are usually building blocks for other methods of traversing (i.e. XPath traversals are based on these functions).

-
-
-
-
xml_node xml_node::parent() const;
-xml_node xml_node::first_child() const;
-xml_node xml_node::last_child() const;
-xml_node xml_node::next_sibling() const;
-xml_node xml_node::previous_sibling() const;
-
-xml_attribute xml_node::first_attribute() const;
-xml_attribute xml_node::last_attribute() const;
-xml_attribute xml_attribute::next_attribute() const;
-xml_attribute xml_attribute::previous_attribute() const;
-
-
-
-

parent function returns the node’s parent; all non-null nodes except the document have non-null parent. first_child and last_child return the first and last child of the node, respectively; note that only document nodes and element nodes can have non-empty child node list. If node has no children, both functions return null nodes. next_sibling and previous_sibling return the node that’s immediately to the right/left of this node in the children list, respectively - for example, in <a/><b/><c/>, calling next_sibling for a handle that points to <b/> results in a handle pointing to <c/>, and calling previous_sibling results in handle pointing to <a/>. If node does not have next/previous sibling (this happens if it is the last/first node in the list, respectively), the functions return null nodes. first_attribute, last_attribute, next_attribute and previous_attribute functions behave similarly to the corresponding child node functions and allow to iterate through attribute list in the same way.

-
-
- - - - - -
-
Note
-		 -Because of memory consumption reasons, attributes do not have a link to their parent nodes. Thus there is no xml_attribute::parent() function. -
-
-
-

Calling any of the functions above on the null handle results in a null handle - i.e. node.first_child().next_sibling() returns the second child of node, and null handle if node is null, has no children at all or if it has only one child node.

-
-
-

With these functions, you can iterate through all child nodes and display all attributes like this (samples/traverse_base.cpp):

-
-
-
-
for (pugi::xml_node tool = tools.first_child(); tool; tool = tool.next_sibling())
-{
-    std::cout << "Tool:";
-
-    for (pugi::xml_attribute attr = tool.first_attribute(); attr; attr = attr.next_attribute())
-    {
-        std::cout << " " << attr.name() << "=" << attr.value();
-    }
-
-    std::cout << std::endl;
-}
-
-
-
-
-

5.1. Getting node data

-
-

-Apart from structural information (parent, child nodes, attributes), nodes can have name and value, both of which are strings. Depending on node type, name or value may be absent. node_document nodes do not have a name or value, node_element and node_declaration nodes always have a name but never have a value, node_pcdata, node_cdata, node_comment and node_doctype nodes never have a name but always have a value (it may be empty though), node_pi nodes always have a name and a value (again, value may be empty). In order to get node’s name or value, you can use the following functions:

-
-
-
-
const char_t* xml_node::name() const;
-const char_t* xml_node::value() const;
-
-
-
-

In case node does not have a name or value or if the node handle is null, both functions return empty strings - they never return null pointers.

-
-
-

It is common to store data as text contents of some node - i.e. <node><description>This is a node</description></node>. In this case, <description> node does not have a value, but instead has a child of type node_pcdata with value "This is a node". pugixml provides several helper functions to parse such data:

-
-
-
-
const char_t* xml_node::child_value() const;
-const char_t* xml_node::child_value(const char_t* name) const;
-xml_text xml_node::text() const;
-
-
-
-

child_value() returns the value of the first child with type node_pcdata or node_cdata; child_value(name) is a simple wrapper for child(name).child_value(). For the above example, calling node.child_value("description") and description.child_value() will both produce string "This is a node". If there is no child with relevant type, or if the handle is null, child_value functions return empty string.

-
-
-

text() returns a special object that can be used for working with PCDATA contents in more complex cases than just retrieving the value; it is described in Working with text contents sections.

-
-
-

There is an example of using some of these functions at the end of the next section.

-
-
-
-

5.2. Getting attribute data

-
-

-All attributes have name and value, both of which are strings (value may be empty). There are two corresponding accessors, like for xml_node:

-
-
-
-
const char_t* xml_attribute::name() const;
-const char_t* xml_attribute::value() const;
-
-
-
-

In case the attribute handle is null, both functions return empty strings - they never return null pointers.

-
-
-

If you need a non-empty string if the attribute handle is null (for example, you need to get the option value from XML attribute, but if it is not specified, you need it to default to "sorted" instead of ""), you can use as_string accessor:

-
-
-
-
const char_t* xml_attribute::as_string(const char_t* def = "") const;
-
-
-
-

It returns def argument if the attribute handle is null. If you do not specify the argument, the function is equivalent to value().

-
-
-

-In many cases attribute values have types that are not strings - i.e. an attribute may always contain values that should be treated as integers, despite the fact that they are represented as strings in XML. pugixml provides several accessors that convert attribute value to some other type:

-
-
-
-
int xml_attribute::as_int(int def = 0) const;
-unsigned int xml_attribute::as_uint(unsigned int def = 0) const;
-double xml_attribute::as_double(double def = 0) const;
-float xml_attribute::as_float(float def = 0) const;
-bool xml_attribute::as_bool(bool def = false) const;
-long long xml_attribute::as_llong(long long def = 0) const;
-unsigned long long xml_attribute::as_ullong(unsigned long long def = 0) const;
-
-
-
-

as_int, as_uint, as_llong, as_ullong, as_double and as_float convert attribute values to numbers. If attribute handle is null def argument is returned (which is 0 by default). Otherwise, all leading whitespace characters are truncated, and the remaining string is parsed as an integer number in either decimal or hexadecimal form (applicable to as_int, as_uint, as_llong and as_ullong; hexadecimal format is used if the number has 0x or 0X prefix) or as a floating point number in either decimal or scientific form (as_double or as_float).

-
-
-

In case the input string contains a non-numeric character sequence or a number that is out of the target numeric range, the result is undefined.

-
-
- - - - - -
-
Caution
-		 -Number conversion functions depend on current C locale as set with setlocale, so may return unexpected results if the locale is different from "C". -
-
-
-

as_bool converts attribute value to boolean as follows: if attribute handle is null, def argument is returned (which is false by default). If attribute value is empty, false is returned. Otherwise, true is returned if the first character is one of '1', 't', 'T', 'y', 'Y'. This means that strings like "true" and "yes" are recognized as true, while strings like "false" and "no" are recognized as false. For more complex matching you’ll have to write your own function.

-
-
- - - - - -
-
Note
-		 -as_llong and as_ullong are only available if your platform has reliable support for the long long type, including string conversions. -
-
-
-

This is an example of using these functions, along with node data retrieval ones (samples/traverse_base.cpp):

-
-
-
-
for (pugi::xml_node tool = tools.child("Tool"); tool; tool = tool.next_sibling("Tool"))
-{
-    std::cout << "Tool " << tool.attribute("Filename").value();
-    std::cout << ": AllowRemote " << tool.attribute("AllowRemote").as_bool();
-    std::cout << ", Timeout " << tool.attribute("Timeout").as_int();
-    std::cout << ", Description '" << tool.child_value("Description") << "'\n";
-}
-
-
-
-
-

5.3. Contents-based traversal functions

-
-

-Since a lot of document traversal consists of finding the node/attribute with the correct name, there are special functions for that purpose:

-
-
-
-
xml_node xml_node::child(const char_t* name) const;
-xml_attribute xml_node::attribute(const char_t* name) const;
-xml_node xml_node::next_sibling(const char_t* name) const;
-xml_node xml_node::previous_sibling(const char_t* name) const;
-
-
-
-

child and attribute return the first child/attribute with the specified name; next_sibling and previous_sibling return the first sibling in the corresponding direction with the specified name. All string comparisons are case-sensitive. In case the node handle is null or there is no node/attribute with the specified name, null handle is returned.

-
-
-

child and next_sibling functions can be used together to loop through all child nodes with the desired name like this:

-
-
-
-
for (pugi::xml_node tool = tools.child("Tool"); tool; tool = tool.next_sibling("Tool"))
-
-
-
-

attribute function needs to look for the target attribute by name. If a node has many attributes, finding each by name can be time consuming. If you have an idea of how attributes are ordered in the node, you can use a faster function:

-
-
-
-
xml_attribute xml_node::attribute(const char_t* name, xml_attribute& hint) const;
-
-
-
-

The extra hint argument is used to guess where the attribute might be, and is updated to the location of the next attribute so that if you search for multiple attributes in the right order, the performance is maximized. Note that hint has to be either null or has to belong to the node, otherwise the behavior is undefined.

-
-
-

You can use this function as follows:

-
-
-
-
xml_attribute hint;
-xml_attribute id = node.attribute("id", hint);
-xml_attribute name = node.attribute("name", hint);
-xml_attribute version = node.attribute("version", hint);
-
-
-
-

This code is correct regardless of the order of the attributes, but it’s faster if "id", "name" and "version" occur in that order.

-
-
-

Occasionally the needed node is specified not by the unique name but instead by the value of some attribute; for example, it is common to have node collections with each node having a unique id: <group><item id="1"/> <item id="2"/></group>. There are two functions for finding child nodes based on the attribute values:

-
-
-
-
xml_node xml_node::find_child_by_attribute(const char_t* name, const char_t* attr_name, const char_t* attr_value) const;
-xml_node xml_node::find_child_by_attribute(const char_t* attr_name, const char_t* attr_value) const;
-
-
-
-

The three-argument function returns the first child node with the specified name which has an attribute with the specified name/value; the two-argument function skips the name test for the node, which can be useful for searching in heterogeneous collections. If the node handle is null or if no node is found, null handle is returned. All string comparisons are case-sensitive.

-
-
-

In all of the above functions, all arguments have to be valid strings; passing null pointers results in undefined behavior.

-
-
-

This is an example of using these functions (samples/traverse_base.cpp):

-
-
-
-
std::cout << "Tool for *.dae generation: " << tools.find_child_by_attribute("Tool", "OutputFileMasks", "*.dae").attribute("Filename").value() << "\n";
-
-for (pugi::xml_node tool = tools.child("Tool"); tool; tool = tool.next_sibling("Tool"))
-{
-    std::cout << "Tool " << tool.attribute("Filename").value() << "\n";
-}
-
-
-
-
-

5.4. Range-based for-loop support

-
-

-If your C++ compiler supports range-based for-loop (this is a C++11 feature, at the time of writing it’s supported by Microsoft Visual Studio 2012+, GCC 4.6+ and Clang 3.0+), you can use it to enumerate nodes/attributes. Additional helpers are provided to support this; note that they are also compatible with Boost Foreach, and possibly other pre-C++11 foreach facilities.

-
-
-
-
implementation-defined-type xml_node::children() const;
-implementation-defined-type xml_node::children(const char_t* name) const;
-implementation-defined-type xml_node::attributes() const;
-
-
-
-

children function allows you to enumerate all child nodes; children function with name argument allows you to enumerate all child nodes with a specific name; attributes function allows you to enumerate all attributes of the node. Note that you can also use node object itself in a range-based for construct, which is equivalent to using children().

-
-
-

This is an example of using these functions (samples/traverse_rangefor.cpp):

-
-
-
-
for (pugi::xml_node tool: tools.children("Tool"))
-{
-    std::cout << "Tool:";
-
-    for (pugi::xml_attribute attr: tool.attributes())
-    {
-        std::cout << " " << attr.name() << "=" << attr.value();
-    }
-
-    for (pugi::xml_node child: tool.children())
-    {
-        std::cout << ", child " << child.name();
-    }
-
-    std::cout << std::endl;
-}
-
-
-
-

While using children() makes the intent of the code clear, note that each node can be treated as a container of child nodes, since it provides begin()/end() member functions described in the next section. Because of this, you can iterate through node’s children simply by using the node itself:

-
-
-
-
for (pugi::xml_node child: tool)
-
-
-
-
-

5.5. Traversing node/attribute lists via iterators

-
-

-Child node lists and attribute lists are simply double-linked lists; while you can use previous_sibling/next_sibling and other such functions for iteration, pugixml additionally provides node and attribute iterators, so that you can treat nodes as containers of other nodes or attributes:

-
-
-
-
class xml_node_iterator;
-class xml_attribute_iterator;
-
-typedef xml_node_iterator xml_node::iterator;
-iterator xml_node::begin() const;
-iterator xml_node::end() const;
-
-typedef xml_attribute_iterator xml_node::attribute_iterator;
-attribute_iterator xml_node::attributes_begin() const;
-attribute_iterator xml_node::attributes_end() const;
-
-
-
-

begin and attributes_begin return iterators that point to the first node/attribute, respectively; end and attributes_end return past-the-end iterator for node/attribute list, respectively - this iterator can’t be dereferenced, but decrementing it results in an iterator pointing to the last element in the list (except for empty lists, where decrementing past-the-end iterator results in undefined behavior). Past-the-end iterator is commonly used as a termination value for iteration loops (see sample below). If you want to get an iterator that points to an existing handle, you can construct the iterator with the handle as a single constructor argument, like so: xml_node_iterator(node). For xml_attribute_iterator, you’ll have to provide both an attribute and its parent node.

-
-
-

begin and end return equal iterators if called on null node; such iterators can’t be dereferenced. attributes_begin and attributes_end behave the same way. For correct iterator usage this means that child node/attribute collections of null nodes appear to be empty.

-
-
-

Both types of iterators have bidirectional iterator semantics (i.e. they can be incremented and decremented, but efficient random access is not supported) and support all usual iterator operations - comparison, dereference, etc. The iterators are invalidated if the node/attribute objects they’re pointing to are removed from the tree; adding nodes/attributes does not invalidate any iterators.

-
-
-

Here is an example of using iterators for document traversal (samples/traverse_iter.cpp):

-
-
-
-
for (pugi::xml_node_iterator it = tools.begin(); it != tools.end(); ++it)
-{
-    std::cout << "Tool:";
-
-    for (pugi::xml_attribute_iterator ait = it->attributes_begin(); ait != it->attributes_end(); ++ait)
-    {
-        std::cout << " " << ait->name() << "=" << ait->value();
-    }
-
-    std::cout << std::endl;
-}
-
-
-
- - - - - -
-
Caution
-		 -Node and attribute iterators are somewhere in the middle between const and non-const iterators. While dereference operation yields a non-constant reference to the object, so that you can use it for tree modification operations, modifying this reference using assignment - i.e. passing iterators to a function like std::sort - will not give expected results, as assignment modifies local handle that’s stored in the iterator. -
-
-
-
-

5.6. Recursive traversal with xml_tree_walker

-
-

The methods described above allow traversal of immediate children of some node; if you want to do a deep tree traversal, you’ll have to do it via a recursive function or some equivalent method. However, pugixml provides a helper for depth-first traversal of a subtree. In order to use it, you have to implement xml_tree_walker interface and to call traverse function:

-
-
-
-
class xml_tree_walker
-{
-public:
-    virtual bool begin(xml_node& node);
-    virtual bool for_each(xml_node& node) = 0;
-    virtual bool end(xml_node& node);
-
-    int depth() const;
-};
-
-bool xml_node::traverse(xml_tree_walker& walker);
-
-
-
-

-The traversal is launched by calling traverse function on traversal root and proceeds as follows:

-
-
-
    -
  • -

    First, begin function is called with traversal root as its argument.

    -
    • -
  • -

    Then, for_each function is called for all nodes in the traversal subtree in depth first order, excluding the traversal root. Node is passed as an argument.

    -
    • -
  • -

    Finally, end function is called with traversal root as its argument.

    -
    • -
-
-
-

If begin, end or any of the for_each calls return false, the traversal is terminated and false is returned as the traversal result; otherwise, the traversal results in true. Note that you don’t have to override begin or end functions; their default implementations return true.

-
-
-

You can get the node’s depth relative to the traversal root at any point by calling depth function. It returns -1 if called from begin/end, and returns 0-based depth if called from for_each - depth is 0 for all children of the traversal root, 1 for all grandchildren and so on.

-
-
-

This is an example of traversing tree hierarchy with xml_tree_walker (samples/traverse_walker.cpp):

-
-
-
-
struct simple_walker: pugi::xml_tree_walker
-{
-    virtual bool for_each(pugi::xml_node& node)
-    {
-        for (int i = 0; i < depth(); ++i) std::cout << "  "; // indentation
-
-        std::cout << node_types[node.type()] << ": name='" << node.name() << "', value='" << node.value() << "'\n";
-
-        return true; // continue traversal
-    }
-};
-
-
-
-
-
simple_walker walker;
-doc.traverse(walker);
-
-
-
-
-

5.7. Searching for nodes/attributes with predicates

-
-

-While there are existing functions for getting a node/attribute with known contents, they are often not sufficient for simple queries. As an alternative for manual iteration through nodes/attributes until the needed one is found, you can make a predicate and call one of find_ functions:

-
-
-
-
template <typename Predicate> xml_attribute xml_node::find_attribute(Predicate pred) const;
-template <typename Predicate> xml_node xml_node::find_child(Predicate pred) const;
-template <typename Predicate> xml_node xml_node::find_node(Predicate pred) const;
-
-
-
-

The predicate should be either a plain function or a function object which accepts one argument of type xml_attribute (for find_attribute) or xml_node (for find_child and find_node), and returns bool. The predicate is never called with null handle as an argument.

-
-
-

find_attribute function iterates through all attributes of the specified node, and returns the first attribute for which the predicate returned true. If the predicate returned false for all attributes or if there were no attributes (including the case where the node is null), null attribute is returned.

-
-
-

find_child function iterates through all child nodes of the specified node, and returns the first node for which the predicate returned true. If the predicate returned false for all nodes or if there were no child nodes (including the case where the node is null), null node is returned.

-
-
-

find_node function performs a depth-first traversal through the subtree of the specified node (excluding the node itself), and returns the first node for which the predicate returned true. If the predicate returned false for all nodes or if subtree was empty, null node is returned.

-
-
-

This is an example of using predicate-based functions (samples/traverse_predicate.cpp):

-
-
-
-
bool small_timeout(pugi::xml_node node)
-{
-    return node.attribute("Timeout").as_int() < 20;
-}
-
-struct allow_remote_predicate
-{
-    bool operator()(pugi::xml_attribute attr) const
-    {
-        return strcmp(attr.name(), "AllowRemote") == 0;
-    }
-
-    bool operator()(pugi::xml_node node) const
-    {
-        return node.attribute("AllowRemote").as_bool();
-    }
-};
-
-
-
-
-
// Find child via predicate (looks for direct children only)
-std::cout << tools.find_child(allow_remote_predicate()).attribute("Filename").value() << std::endl;
-
-// Find node via predicate (looks for all descendants in depth-first order)
-std::cout << doc.find_node(allow_remote_predicate()).attribute("Filename").value() << std::endl;
-
-// Find attribute via predicate
-std::cout << tools.last_child().find_attribute(allow_remote_predicate()).value() << std::endl;
-
-// We can use simple functions instead of function objects
-std::cout << tools.find_child(small_timeout).attribute("Filename").value() << std::endl;
-
-
-
-
-

5.8. Working with text contents

-
-

It is common to store data as text contents of some node - i.e. <node><description>This is a node</description></node>. In this case, <description> node does not have a value, but instead has a child of type node_pcdata with value "This is a node". pugixml provides a special class, xml_text, to work with such data. Working with text objects to modify data is described in the documentation for modifying document data; this section describes the access interface of xml_text.

-
-
-

You can get the text object from a node by using text() method:

-
-
-
-
xml_text xml_node::text() const;
-
-
-
-

If the node has a type node_pcdata or node_cdata, then the node itself is used to return data; otherwise, a first child node of type node_pcdata or node_cdata is used.

-
-
-

-You can check if the text object is bound to a valid PCDATA/CDATA node by using it as a boolean value, i.e. if (text) { …​ } or if (!text) { …​ }. Alternatively you can check it by using the empty() method:

-
-
-
-
bool xml_text::empty() const;
-
-
-
-

Given a text object, you can get the contents (i.e. the value of PCDATA/CDATA node) by using the following function:

-
-
-
-
const char_t* xml_text::get() const;
-
-
-
-

In case text object is empty, the function returns an empty string - it never returns a null pointer.

-
-
-

-If you need a non-empty string if the text object is empty, or if the text contents is actually a number or a boolean that is stored as a string, you can use the following accessors:

-
-
-
-
const char_t* xml_text::as_string(const char_t* def = "") const;
-int xml_text::as_int(int def = 0) const;
-unsigned int xml_text::as_uint(unsigned int def = 0) const;
-double xml_text::as_double(double def = 0) const;
-float xml_text::as_float(float def = 0) const;
-bool xml_text::as_bool(bool def = false) const;
-long long xml_text::as_llong(long long def = 0) const;
-unsigned long long xml_text::as_ullong(unsigned long long def = 0) const;
-
-
-
-

All of the above functions have the same semantics as similar xml_attribute members: they return the default argument if the text object is empty, they convert the text contents to a target type using the same rules and restrictions. You can refer to documentation for the attribute functions for details.

-
-
-

xml_text is essentially a helper class that operates on xml_node values. It is bound to a node of type node_pcdata or node_cdata. You can use the following function to retrieve this node:

-
-
-
-
xml_node xml_text::data() const;
-
-
-
-

Essentially, assuming text is an xml_text object, calling text.get() is equivalent to calling text.data().value().

-
-
-

This is an example of using xml_text object (samples/text.cpp):

-
-
-
-
std::cout << "Project name: " << project.child("name").text().get() << std::endl;
-std::cout << "Project version: " << project.child("version").text().as_double() << std::endl;
-std::cout << "Project visibility: " << (project.child("public").text().as_bool(/* def= */ true) ? "public" : "private") << std::endl;
-std::cout << "Project description: " << project.child("description").text().get() << std::endl;
-
-
-
-
-

5.9. Miscellaneous functions

-
-

If you need to get the document root of some node, you can use the following function:

-
-
-
-
xml_node xml_node::root() const;
-
-
-
-

This function returns the node with type node_document, which is the root node of the document the node belongs to (unless the node is null, in which case null node is returned).

-
-
-

-While pugixml supports complex XPath expressions, sometimes a simple path handling facility is needed. There are two functions, for getting node path and for converting path to a node:

-
-
-
-
string_t xml_node::path(char_t delimiter = '/') const;
-xml_node xml_node::first_element_by_path(const char_t* path, char_t delimiter = '/') const;
-
-
-
-

Node paths consist of node names, separated with a delimiter (which is / by default); also paths can contain self (.) and parent (..) pseudo-names, so that this is a valid path: "../../foo/./bar". path returns the path to the node from the document root, first_element_by_path looks for a node represented by a given path; a path can be an absolute one (absolute paths start with the delimiter), in which case the rest of the path is treated as document root relative, and relative to the given node. For example, in the following document: <a><b><c/></b></a>, node <c/> has path "a/b/c"; calling first_element_by_path for document with path "a/b" results in node <b/>; calling first_element_by_path for node <a/> with path "../a/./b/../." results in node <a/>; calling first_element_by_path with path "/a" results in node <a/> for any node.

-
-
-

In case path component is ambiguous (if there are two nodes with given name), the first one is selected; paths are not guaranteed to uniquely identify nodes in a document. If any component of a path is not found, the result of first_element_by_path is null node; also first_element_by_path returns null node for null nodes, in which case the path does not matter. path returns an empty string for null nodes.

-
-
- - - - - -
-
Note
-		 -path function returns the result as STL string, and thus is not available if PUGIXML_NO_STL is defined. -
-
-
-

pugixml does not record row/column information for nodes upon parsing for efficiency reasons. However, if the node has not changed in a significant way since parsing (the name/value are not changed, and the node itself is the original one, i.e. it was not deleted from the tree and re-added later), it is possible to get the offset from the beginning of XML buffer:

-
-
-
-
ptrdiff_t xml_node::offset_debug() const;
-
-
-
-

If the offset is not available (this happens if the node is null, was not originally parsed from a stream, or has changed in a significant way), the function returns -1. Otherwise it returns the offset to node’s data from the beginning of XML buffer in pugi::char_t units. For more information on parsing offsets, see parsing error handling documentation.

-
-
-
-
-
-

6. Modifying document data

-
-
-

The document in pugixml is fully mutable: you can completely change the document structure and modify the data of nodes/attributes. This section provides documentation for the relevant functions. All functions take care of memory management and structural integrity themselves, so they always result in structurally valid tree - however, it is possible to create an invalid XML tree (for example, by adding two attributes with the same name or by setting attribute/node name to empty/invalid string). Tree modification is optimized for performance and for memory consumption, so if you have enough memory you can create documents from scratch with pugixml and later save them to file/stream instead of relying on error-prone manual text writing and without too much overhead.

-
-
-

All member functions that change node/attribute data or structure are non-constant and thus can not be called on constant handles. However, you can easily convert constant handle to non-constant one by simple assignment: void foo(const pugi::xml_node& n) { pugi::xml_node nc = n; }, so const-correctness here mainly provides additional documentation.

-
-
-

Setting node data

-
-

-As discussed before, nodes can have name and value, both of which are strings. Depending on node type, name or value may be absent. node_document nodes do not have a name or value, node_element and node_declaration nodes always have a name but never have a value, node_pcdata, node_cdata, node_comment and node_doctype nodes never have a name but always have a value (it may be empty though), node_pi nodes always have a name and a value (again, value may be empty). In order to set node’s name or value, you can use the following functions:

-
-
-
-
bool xml_node::set_name(const char_t* rhs);
-bool xml_node::set_name(const char_t* rhs, size_t sz)
-bool xml_node::set_value(const char_t* rhs);
-bool xml_node::set_value(const char_t* rhs, size_t size);
-
-
-
-

Both functions try to set the name/value to the specified string, and return the operation result. The operation fails if the node can not have name or value (for instance, when trying to call set_name on a node_pcdata node), if the node handle is null, or if there is insufficient memory to handle the request. The provided string is copied into document managed memory and can be destroyed after the function returns (for example, you can safely pass stack-allocated buffers to these functions). The name/value content is not verified, so take care to use only valid XML names, or the document may become malformed.

-
-
-

This is an example of setting node name and value (samples/modify_base.cpp):

-
-
-
-
pugi::xml_node node = doc.child("node");
-
-// change node name
-std::cout << node.set_name("notnode");
-std::cout << ", new node name: " << node.name() << std::endl;
-
-// change comment text
-std::cout << doc.last_child().set_value("useless comment");
-std::cout << ", new comment text: " << doc.last_child().value() << std::endl;
-
-// we can't change value of the element or name of the comment
-std::cout << node.set_value("1") << ", " << doc.last_child().set_name("2") << std::endl;
-
-
-
-
-

6.1. Setting attribute data

-
-

-All attributes have name and value, both of which are strings (value may be empty). You can set them with the following functions:

-
-
-
-
bool xml_attribute::set_name(const char_t* rhs);
-bool xml_attribute::set_name(const char_t* rhs, size_t sz)
-bool xml_attribute::set_value(const char_t* rhs);
-bool xml_attribute::set_value(const char_t* rhs, size_t size);
-
-
-
-

Both functions try to set the name/value to the specified string, and return the operation result. The operation fails if the attribute handle is null, or if there is insufficient memory to handle the request. The provided string is copied into document managed memory and can be destroyed after the function returns (for example, you can safely pass stack-allocated buffers to these functions). The name/value content is not verified, so take care to use only valid XML names, or the document may become malformed.

-
-
-

In addition to string functions, several functions are provided for handling attributes with numbers and booleans as values:

-
-
-
-
bool xml_attribute::set_value(int rhs);
-bool xml_attribute::set_value(unsigned int rhs);
-bool xml_attribute::set_value(long rhs);
-bool xml_attribute::set_value(unsigned long rhs);
-bool xml_attribute::set_value(double rhs);
-bool xml_attribute::set_value(double rhs, int precision);
-bool xml_attribute::set_value(float rhs);
-bool xml_attribute::set_value(float rhs, int precision);
-bool xml_attribute::set_value(bool rhs);
-bool xml_attribute::set_value(long long rhs);
-bool xml_attribute::set_value(unsigned long long rhs);
-
-
-
-

The above functions convert the argument to string and then call the base set_value function. Integers are converted to a decimal form, floating-point numbers are converted to either decimal or scientific form, depending on the number magnitude, boolean values are converted to either "true" or "false".

-
-
- - - - - -
-
Caution
-		 -Number conversion functions depend on current C locale as set with setlocale, so may generate unexpected results if the locale is different from "C". -
-
-
- - - - - -
-
Note
-		 -set_value overloads with long long type are only available if your platform has reliable support for the type, including string conversions. -
-
-
-

For convenience, all set_value functions have the corresponding assignment operators:

-
-
-
-
xml_attribute& xml_attribute::operator=(const char_t* rhs);
-xml_attribute& xml_attribute::operator=(int rhs);
-xml_attribute& xml_attribute::operator=(unsigned int rhs);
-xml_attribute& xml_attribute::operator=(long rhs);
-xml_attribute& xml_attribute::operator=(unsigned long rhs);
-xml_attribute& xml_attribute::operator=(double rhs);
-xml_attribute& xml_attribute::operator=(float rhs);
-xml_attribute& xml_attribute::operator=(bool rhs);
-xml_attribute& xml_attribute::operator=(long long rhs);
-xml_attribute& xml_attribute::operator=(unsigned long long rhs);
-
-
-
-

These operators simply call the right set_value function and return the attribute they’re called on; the return value of set_value is ignored, so errors are ignored.

-
-
-

This is an example of setting attribute name and value (samples/modify_base.cpp):

-
-
-
-
pugi::xml_attribute attr = node.attribute("id");
-
-// change attribute name/value
-std::cout << attr.set_name("key") << ", " << attr.set_value("345");
-std::cout << ", new attribute: " << attr.name() << "=" << attr.value() << std::endl;
-
-// we can use numbers or booleans
-attr.set_value(1.234);
-std::cout << "new attribute value: " << attr.value() << std::endl;
-
-// we can also use assignment operators for more concise code
-attr = true;
-std::cout << "final attribute value: " << attr.value() << std::endl;
-
-
-
-
-

6.2. Adding nodes/attributes

-
-

-Nodes and attributes do not exist without a document tree, so you can’t create them without adding them to some document. A node or attribute can be created at the end of node/attribute list or before/after some other node:

-
-
-
-
xml_attribute xml_node::append_attribute(const char_t* name);
-xml_attribute xml_node::prepend_attribute(const char_t* name);
-xml_attribute xml_node::insert_attribute_after(const char_t* name, const xml_attribute& attr);
-xml_attribute xml_node::insert_attribute_before(const char_t* name, const xml_attribute& attr);
-
-xml_node xml_node::append_child(xml_node_type type = node_element);
-xml_node xml_node::prepend_child(xml_node_type type = node_element);
-xml_node xml_node::insert_child_after(xml_node_type type, const xml_node& node);
-xml_node xml_node::insert_child_before(xml_node_type type, const xml_node& node);
-
-xml_node xml_node::append_child(const char_t* name);
-xml_node xml_node::prepend_child(const char_t* name);
-xml_node xml_node::insert_child_after(const char_t* name, const xml_node& node);
-xml_node xml_node::insert_child_before(const char_t* name, const xml_node& node);
-
-
-
-

append_attribute and append_child create a new node/attribute at the end of the corresponding list of the node the method is called on; prepend_attribute and prepend_child create a new node/attribute at the beginning of the list; insert_attribute_after, insert_attribute_before, insert_child_after and insert_attribute_before add the node/attribute before or after the specified node/attribute.

-
-
-

Attribute functions create an attribute with the specified name; you can specify the empty name and change the name later if you want to. Node functions with the type argument create the node with the specified type; since node type can’t be changed, you have to know the desired type beforehand. Also note that not all types can be added as children; see below for clarification. Node functions with the name argument create the element node (node_element) with the specified name.

-
-
-

All functions return the handle to the created object on success, and null handle on failure. There are several reasons for failure:

-
-
-
    -
  • -

    Adding fails if the target node is null;

    -
    • -
  • -

    Only node_element nodes can contain attributes, so attribute adding fails if node is not an element;

    -
    • -
  • -

    Only node_document and node_element nodes can contain children, so child node adding fails if the target node is not an element or a document;

    -
    • -
  • -

    node_document and node_null nodes can not be inserted as children, so passing node_document or node_null value as type results in operation failure;

    -
    • -
  • -

    node_declaration nodes can only be added as children of the document node; attempt to insert declaration node as a child of an element node fails;

    -
    • -
  • -

    Adding node/attribute results in memory allocation, which may fail;

    -
    • -
  • -

    Insertion functions fail if the specified node or attribute is null or is not in the target node’s children/attribute list.

    -
    • -
-
-
-

Even if the operation fails, the document remains in consistent state, but the requested node/attribute is not added.

-
-
- - - - - -
-
Caution
-		 -attribute() and child() functions do not add attributes or nodes to the tree, so code like node.attribute("id") = 123; will not do anything if node does not have an attribute with name "id". Make sure you’re operating with existing attributes/nodes by adding them if necessary. -
-
-
-

This is an example of adding new attributes/nodes to the document (samples/modify_add.cpp):

-
-
-
-
// add node with some name
-pugi::xml_node node = doc.append_child("node");
-
-// add description node with text child
-pugi::xml_node descr = node.append_child("description");
-descr.append_child(pugi::node_pcdata).set_value("Simple node");
-
-// add param node before the description
-pugi::xml_node param = node.insert_child_before("param", descr);
-
-// add attributes to param node
-param.append_attribute("name") = "version";
-param.append_attribute("value") = 1.1;
-param.insert_attribute_after("type", param.attribute("name")) = "float";
-
-
-
-
-

6.3. Removing nodes/attributes

-
-

-If you do not want your document to contain some node or attribute, you can remove it with one of the following functions:

-
-
-
-
bool xml_node::remove_attribute(const xml_attribute& a);
-bool xml_node::remove_attributes();
-bool xml_node::remove_child(const xml_node& n);
-bool xml_node::remove_children();
-
-
-
-

remove_attribute removes the attribute from the attribute list of the node, and returns the operation result. remove_child removes the child node with the entire subtree (including all descendant nodes and attributes) from the document, and returns the operation result. remove_attributes removes all the attributes of the node, and returns the operation result. remove_children removes all the child nodes of the node, and returns the operation result. Removing fails if one of the following is true:

-
-
-
    -
  • -

    The node the function is called on is null;

    -
    • -
  • -

    The attribute/node to be removed is null;

    -
    • -
  • -

    The attribute/node to be removed is not in the node’s attribute/child list.

    -
    • -
-
-
-

Removing the attribute or node invalidates all handles to the same underlying object, and also invalidates all iterators pointing to the same object. Removing node also invalidates all past-the-end iterators to its attribute or child node list. Be careful to ensure that all such handles and iterators either do not exist or are not used after the attribute/node is removed.

-
-
-

If you want to remove the attribute or child node by its name, two additional helper functions are available:

-
-
-
-
bool xml_node::remove_attribute(const char_t* name);
-bool xml_node::remove_child(const char_t* name);
-
-
-
-

These functions look for the first attribute or child with the specified name, and then remove it, returning the result. If there is no attribute or child with such name, the function returns false; if there are two nodes with the given name, only the first node is deleted. If you want to delete all nodes with the specified name, you can use code like this: while (node.remove_child("tool")) ;.

-
-
-

This is an example of removing attributes/nodes from the document (samples/modify_remove.cpp):

-
-
-
-
// remove description node with the whole subtree
-pugi::xml_node node = doc.child("node");
-node.remove_child("description");
-
-// remove id attribute
-pugi::xml_node param = node.child("param");
-param.remove_attribute("value");
-
-// we can also remove nodes/attributes by handles
-pugi::xml_attribute id = param.attribute("name");
-param.remove_attribute(id);
-
-
-
-
-

6.4. Working with text contents

-
-

pugixml provides a special class, xml_text, to work with text contents stored as a value of some node, i.e. <node><description>This is a node</description></node>. Working with text objects to retrieve data is described in the documentation for accessing document data; this section describes the modification interface of xml_text.

-
-
-

Once you have an xml_text object, you can set the text contents using the following function:

-
-
-
-
bool xml_text::set(const char_t* rhs);
-bool xml_text::set(const char_t* rhs, size_t size);
-
-
-
-

This function tries to set the contents to the specified string, and returns the operation result. The operation fails if the text object was retrieved from a node that can not have a value and is not an element node (i.e. it is a node_declaration node), if the text object is empty, or if there is insufficient memory to handle the request. The provided string is copied into document managed memory and can be destroyed after the function returns (for example, you can safely pass stack-allocated buffers to this function). Note that if the text object was retrieved from an element node, this function creates the PCDATA child node if necessary (i.e. if the element node does not have a PCDATA/CDATA child already).

-
-
-

In addition to a string function, several functions are provided for handling text with numbers and booleans as contents:

-
-
-
-
bool xml_text::set(int rhs);
-bool xml_text::set(unsigned int rhs);
-bool xml_text::set(long rhs);
-bool xml_text::set(unsigned long rhs);
-bool xml_text::set(double rhs);
-bool xml_text::set(double rhs, int precision);
-bool xml_text::set(float rhs);
-bool xml_text::set(float rhs, int precision);
-bool xml_text::set(bool rhs);
-bool xml_text::set(long long rhs);
-bool xml_text::set(unsigned long long rhs);
-
-
-
-

The above functions convert the argument to string and then call the base set function. These functions have the same semantics as similar xml_attribute functions. You can refer to documentation for the attribute functions for details.

-
-
-

For convenience, all set functions have the corresponding assignment operators:

-
-
-
-
xml_text& xml_text::operator=(const char_t* rhs);
-xml_text& xml_text::operator=(int rhs);
-xml_text& xml_text::operator=(unsigned int rhs);
-xml_text& xml_text::operator=(long rhs);
-xml_text& xml_text::operator=(unsigned long rhs);
-xml_text& xml_text::operator=(double rhs);
-xml_text& xml_text::operator=(float rhs);
-xml_text& xml_text::operator=(bool rhs);
-xml_text& xml_text::operator=(long long rhs);
-xml_text& xml_text::operator=(unsigned long long rhs);
-
-
-
-

These operators simply call the right set function and return the attribute they’re called on; the return value of set is ignored, so errors are ignored.

-
-
-

This is an example of using xml_text object to modify text contents (samples/text.cpp):

-
-
-
-
// change project version
-project.child("version").text() = 1.2;
-
-// add description element and set the contents
-// note that we do not have to explicitly add the node_pcdata child
-project.append_child("description").text().set("a test project");
-
-
-
-
-

6.5. Cloning nodes/attributes

-
-

-With the help of previously described functions, it is possible to create trees with any contents and structure, including cloning the existing data. However since this is an often needed operation, pugixml provides built-in node/attribute cloning facilities. Since nodes and attributes do not exist without a document tree, you can’t create a standalone copy - you have to immediately insert it somewhere in the tree. For this, you can use one of the following functions:

-
-
-
-
xml_attribute xml_node::append_copy(const xml_attribute& proto);
-xml_attribute xml_node::prepend_copy(const xml_attribute& proto);
-xml_attribute xml_node::insert_copy_after(const xml_attribute& proto, const xml_attribute& attr);
-xml_attribute xml_node::insert_copy_before(const xml_attribute& proto, const xml_attribute& attr);
-
-xml_node xml_node::append_copy(const xml_node& proto);
-xml_node xml_node::prepend_copy(const xml_node& proto);
-xml_node xml_node::insert_copy_after(const xml_node& proto, const xml_node& node);
-xml_node xml_node::insert_copy_before(const xml_node& proto, const xml_node& node);
-
-
-
-

These functions mirror the structure of append_child, prepend_child, insert_child_before and related functions - they take the handle to the prototype object, which is to be cloned, insert a new attribute/node at the appropriate place, and then copy the attribute data or the whole node subtree to the new object. The functions return the handle to the resulting duplicate object, or null handle on failure.

-
-
-

The attribute is copied along with the name and value; the node is copied along with its type, name and value; additionally attribute list and all children are recursively cloned, resulting in the deep subtree clone. The prototype object can be a part of the same document, or a part of any other document.

-
-
-

The failure conditions resemble those of append_child, insert_child_before and related functions, consult their documentation for more information. There are additional caveats specific to cloning functions:

-
-
-
    -
  • -

    Cloning null handles results in operation failure;

    -
    • -
  • -

    Node cloning starts with insertion of the node of the same type as that of the prototype; for this reason, cloning functions can not be directly used to clone entire documents, since node_document is not a valid insertion type. The example below provides a workaround.

    -
    • -
  • -

    It is possible to copy a subtree as a child of some node inside this subtree, i.e. node.append_copy(node.parent().parent());. This is a valid operation, and it results in a clone of the subtree in the state before cloning started, i.e. no infinite recursion takes place.

    -
    • -
-
-
-

This is an example with one possible implementation of include tags in XML (samples/include.cpp). It illustrates node cloning and usage of other document modification functions:

-
-
-
-
bool load_preprocess(pugi::xml_document& doc, const char* path);
-
-bool preprocess(pugi::xml_node node)
-{
-    for (pugi::xml_node child = node.first_child(); child; )
-    {
-        if (child.type() == pugi::node_pi && strcmp(child.name(), "include") == 0)
-        {
-            pugi::xml_node include = child;
-
-            // load new preprocessed document (note: ideally this should handle relative paths)
-            const char* path = include.value();
-
-            pugi::xml_document doc;
-            if (!load_preprocess(doc, path)) return false;
-
-            // insert the comment marker above include directive
-            node.insert_child_before(pugi::node_comment, include).set_value(path);
-
-            // copy the document above the include directive (this retains the original order!)
-            for (pugi::xml_node ic = doc.first_child(); ic; ic = ic.next_sibling())
-            {
-                node.insert_copy_before(ic, include);
-            }
-
-            // remove the include node and move to the next child
-            child = child.next_sibling();
-
-            node.remove_child(include);
-        }
-        else
-        {
-            if (!preprocess(child)) return false;
-
-            child = child.next_sibling();
-        }
-    }
-
-    return true;
-}
-
-bool load_preprocess(pugi::xml_document& doc, const char* path)
-{
-    pugi::xml_parse_result result = doc.load_file(path, pugi::parse_default | pugi::parse_pi); // for <?include?>
-
-    return result ? preprocess(doc) : false;
-}
-
-
-
-
-

6.6. Moving nodes

-
-

-Sometimes instead of cloning a node you need to move an existing node to a different position in a tree. This can be accomplished by copying the node and removing the original; however, this is expensive since it results in a lot of extra operations. For moving nodes within the same document tree, you can use of the following functions instead:

-
-
-
-
xml_node xml_node::append_move(const xml_node& moved);
-xml_node xml_node::prepend_move(const xml_node& moved);
-xml_node xml_node::insert_move_after(const xml_node& moved, const xml_node& node);
-xml_node xml_node::insert_move_before(const xml_node& moved, const xml_node& node);
-
-
-
-

These functions mirror the structure of append_copy, prepend_copy, insert_copy_before and insert_copy_after - they take the handle to the moved object and move it to the appropriate place with all attributes and/or child nodes. The functions return the handle to the resulting object (which is the same as the moved object), or null handle on failure.

-
-
-

The failure conditions resemble those of append_child, insert_child_before and related functions, consult their documentation for more information. There are additional caveats specific to moving functions:

-
-
-
    -
  • -

    Moving null handles results in operation failure;

    -
    • -
  • -

    Moving is only possible for nodes that belong to the same document; attempting to move nodes between documents will fail.

    -
    • -
  • -

    insert_move_after and insert_move_before functions fail if the moved node is the same as the node argument (this operation would be a no-op otherwise).

    -
    • -
  • -

    It is impossible to move a subtree to a child of some node inside this subtree, i.e. node.append_move(node.parent().parent()); will fail.

    -
    • -
-
-
-
-

6.7. Assembling document from fragments

-
-

pugixml provides several ways to assemble an XML document from other XML documents. Assuming there is a set of document fragments, represented as in-memory buffers, the implementation choices are as follows:

-
-
-
    -
  • -

    Use a temporary document to parse the data from a string, then clone the nodes to a destination node. For example:

    -
    -
    -
    bool append_fragment(pugi::xml_node target, const char* buffer, size_t size)
-{
-    pugi::xml_document doc;
-    if (!doc.load_buffer(buffer, size)) return false;
-
-    for (pugi::xml_node child = doc.first_child(); child; child = child.next_sibling())
-        target.append_copy(child);
-}
    -
    -
    -
    • -
  • -

    Cache the parsing step - instead of keeping in-memory buffers, keep document objects that already contain the parsed fragment:

    -
    -
    -
    bool append_fragment(pugi::xml_node target, const pugi::xml_document& cached_fragment)
-{
-    for (pugi::xml_node child = cached_fragment.first_child(); child; child = child.next_sibling())
-        target.append_copy(child);
-}
    -
    -
    -
    • -
  • -

    Use xml_node::append_buffer directly:

    -
    -
    -
    xml_parse_result xml_node::append_buffer(const void* contents, size_t size, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);
    -
    -
    -
    • -
-
-
-

The first method is more convenient, but slower than the other two. The relative performance of append_copy and append_buffer depends on the buffer format - usually append_buffer is faster if the buffer is in native encoding (UTF-8 or wchar_t, depending on PUGIXML_WCHAR_MODE). At the same time it might be less efficient in terms of memory usage - the implementation makes a copy of the provided buffer, and the copy has the same lifetime as the document - the memory used by that copy will be reclaimed after the document is destroyed, but no sooner. Even deleting all nodes in the document, including the appended ones, won’t reclaim the memory.

-
-
-

append_buffer behaves in the same way as xml_document::load_buffer - the input buffer is a byte buffer, with size in bytes; the buffer is not modified and can be freed after the function returns.

-
-
-

Since append_buffer needs to append child nodes to the current node, it only works if the current node is either document or element node. Calling append_buffer on a node with any other type results in an error with status_append_invalid_root status.

-
-
-
-
-
-

7. Saving document

-
-
-

Often after creating a new document or loading the existing one and processing it, it is necessary to save the result back to file. Also it is occasionally useful to output the whole document or a subtree to some stream; use cases include debug printing, serialization via network or other text-oriented medium, etc. pugixml provides several functions to output any subtree of the document to a file, stream or another generic transport interface; these functions allow to customize the output format (see Output options), and also perform necessary encoding conversions (see Encodings). This section documents the relevant functionality.

-
-
-

Before writing to the destination the node/attribute data is properly formatted according to the node type; all special XML symbols, such as < and &, are properly escaped (unless format_no_escapes flag is set). In order to guard against forgotten node/attribute names, empty node/attribute names are printed as ":anonymous". For well-formed output, make sure all node and attribute names are set to meaningful values.

-
-
-

CDATA sections with values that contain "]]>" are split into several sections as follows: section with value "pre]]>post" is written as <![CDATA[pre]]]]><![CDATA[>post]]>. While this alters the structure of the document (if you load the document after saving it, there will be two CDATA sections instead of one), this is the only way to escape CDATA contents.

-
-
-

7.1. Saving document to a file

-
-

-If you want to save the whole document to a file, you can use one of the following functions:

-
-
-
-
bool xml_document::save_file(const char* path, const char_t* indent = "\t", unsigned int flags = format_default, xml_encoding encoding = encoding_auto) const;
-bool xml_document::save_file(const wchar_t* path, const char_t* indent = "\t", unsigned int flags = format_default, xml_encoding encoding = encoding_auto) const;
-
-
-
-

These functions accept file path as its first argument, and also three optional arguments, which specify indentation and other output options (see Output options) and output data encoding (see Encodings). The path has the target operating system format, so it can be a relative or absolute one, it should have the delimiters of the target system, it should have the exact case if the target file system is case-sensitive, etc. The functions return true on success and false if the file could not be opened or written to.

-
-
-

File path is passed to the system file opening function as is in case of the first function (which accepts const char* path); the second function either uses a special file opening function if it is provided by the runtime library or converts the path to UTF-8 and uses the system file opening function.

-
-
-

save_file opens the target file for writing, outputs the requested header (by default a document declaration is output, unless the document already has one), and then saves the document contents. Calling save_file is equivalent to creating an xml_writer_file object with FILE* handle as the only constructor argument and then calling save; see Saving document via writer interface for writer interface details.

-
-
-

This is a simple example of saving XML document to file (samples/save_file.cpp):

-
-
-
-
// save document to file
-std::cout << "Saving result: " << doc.save_file("save_file_output.xml") << std::endl;
-
-
-
-
-

7.2. Saving document to C++ IOstreams

-
-

To enhance interoperability pugixml provides functions for saving document to any object which implements C++ std::ostream interface. This allows you to save documents to any standard C++ stream (i.e. file stream) or any third-party compliant implementation (i.e. Boost Iostreams). Most notably, this allows for easy debug output, since you can use std::cout stream as saving target. There are two functions, one works with narrow character streams, another handles wide character ones:

-
-
-
-
void xml_document::save(std::ostream& stream, const char_t* indent = "\t", unsigned int flags = format_default, xml_encoding encoding = encoding_auto) const;
-void xml_document::save(std::wostream& stream, const char_t* indent = "\t", unsigned int flags = format_default) const;
-
-
-
-

save with std::ostream argument saves the document to the stream in the same way as save_file (i.e. with requested header and with encoding conversions). On the other hand, save with std::wstream argument saves the document to the wide stream with encoding_wchar encoding. Because of this, using save with wide character streams requires careful (usually platform-specific) stream setup (i.e. using the imbue function). Generally use of wide streams is discouraged, however it provides you with the ability to save documents to non-Unicode encodings, i.e. you can save Shift-JIS encoded data if you set the correct locale.

-
-
-

Calling save with stream target is equivalent to creating an xml_writer_stream object with stream as the only constructor argument and then calling save; see Saving document via writer interface for writer interface details.

-
-
-

This is a simple example of saving XML document to standard output (samples/save_stream.cpp):

-
-
-
-
// save document to standard output
-std::cout << "Document:\n";
-doc.save(std::cout);
-
-
-
-
-

7.3. Saving document via writer interface

-
-

-All of the above saving functions are implemented in terms of writer interface. This is a simple interface with a single function, which is called several times during output process with chunks of document data as input:

-
-
-
-
class xml_writer
-{
-public:
-    virtual void write(const void* data, size_t size) = 0;
-};
-
-void xml_document::save(xml_writer& writer, const char_t* indent = "\t", unsigned int flags = format_default, xml_encoding encoding = encoding_auto) const;
-
-
-
-

In order to output the document via some custom transport, for example sockets, you should create an object which implements xml_writer interface and pass it to save function. xml_writer::write function is called with a buffer as an input, where data points to buffer start, and size is equal to the buffer size in bytes. write implementation must write the buffer to the transport; it can not save the passed buffer pointer, as the buffer contents will change after write returns. The buffer contains the chunk of document data in the desired encoding.

-
-
-

write function is called with relatively large blocks (size is usually several kilobytes, except for the last block that may be small), so there is often no need for additional buffering in the implementation.

-
-
-

This is a simple example of custom writer for saving document data to STL string (samples/save_custom_writer.cpp); read the sample code for more complex examples:

-
-
-
-
struct xml_string_writer: pugi::xml_writer
-{
-    std::string result;
-
-    virtual void write(const void* data, size_t size)
-    {
-        result.append(static_cast<const char*>(data), size);
-    }
-};
-
-
-
-
-

7.4. Saving a single subtree

-
-

-While the previously described functions save the whole document to the destination, it is easy to save a single subtree. The following functions are provided:

-
-
-
-
void xml_node::print(std::ostream& os, const char_t* indent = "\t", unsigned int flags = format_default, xml_encoding encoding = encoding_auto, unsigned int depth = 0) const;
-void xml_node::print(std::wostream& os, const char_t* indent = "\t", unsigned int flags = format_default, unsigned int depth = 0) const;
-void xml_node::print(xml_writer& writer, const char_t* indent = "\t", unsigned int flags = format_default, xml_encoding encoding = encoding_auto, unsigned int depth = 0) const;
-
-
-
-

These functions have the same arguments with the same meaning as the corresponding xml_document::save functions, and allow you to save the subtree to either a C++ IOstream or to any object that implements xml_writer interface.

-
-
-

Saving a subtree differs from saving the whole document: the process behaves as if format_write_bom is off, and format_no_declaration is on, even if actual values of the flags are different. This means that BOM is not written to the destination, and document declaration is only written if it is the node itself or is one of node’s children. Note that this also holds if you’re saving a document; this example (samples/save_subtree.cpp) illustrates the difference:

-
-
-
-
// get a test document
-pugi::xml_document doc;
-doc.load_string("<foo bar='baz'><call>hey</call></foo>");
-
-// print document to standard output (prints <?xml version="1.0"?><foo bar="baz"><call>hey</call></foo>)
-doc.save(std::cout, "", pugi::format_raw);
-std::cout << std::endl;
-
-// print document to standard output as a regular node (prints <foo bar="baz"><call>hey</call></foo>)
-doc.print(std::cout, "", pugi::format_raw);
-std::cout << std::endl;
-
-// print a subtree to standard output (prints <call>hey</call>)
-doc.child("foo").child("call").print(std::cout, "", pugi::format_raw);
-std::cout << std::endl;
-
-
-
-
-

7.5. Output options

-
-

All saving functions accept the optional parameter flags. This is a bitmask that customizes the output format; you can select the way the document nodes are printed and select the needed additional information that is output before the document contents.

-
-
- - - - - -
-
Note
-		 -You should use the usual bitwise arithmetics to manipulate the bitmask: to enable a flag, use mask | flag; to disable a flag, use mask & ~flag. -
-
-
-

These flags control the resulting tree contents:

-
-
-
    -
  • -

    format_indent determines if all nodes should be indented with the indentation string (this is an additional parameter for all saving functions, and is "\t" by default). If this flag is on, the indentation string is printed several times before every node, where the amount of indentation depends on the node’s depth relative to the output subtree. This flag has no effect if format_raw is enabled. This flag is on by default.

    -
    • -
  • -

    format_indent_attributes determines if all attributes should be printed on a new line, indented with the indentation string according to the attribute’s depth. This flag implies format_indent. This flag has no effect if format_raw is enabled. This flag is off by default.

    -
    • -
  • -

    format_raw switches between formatted and raw output. If this flag is on, the nodes are not indented in any way, and also no newlines that are not part of document text are printed. Raw mode can be used for serialization where the result is not intended to be read by humans; also it can be useful if the document was parsed with parse_ws_pcdata flag, to preserve the original document formatting as much as possible. This flag is off by default.

    -
    • -
  • -

    format_no_escapes disables output escaping for attribute values and PCDATA contents. If this flag is off, special symbols (", &, <, >) and all non-printable characters (those with codepoint values less than 32) are converted to XML escape sequences (i.e. &amp;) during output. If this flag is on, no text processing is performed; therefore, output XML can be malformed if output contents contains invalid symbols (i.e. having a stray < in the PCDATA will make the output malformed). This flag is off by default.

    -
    • -
  • -

    format_no_empty_element_tags determines if start/end tags should be output instead of empty element tags for empty elements (that is, elements with no children). This flag is off by default.

    -
    • -
  • -

    format_skip_control_chars enables skipping characters belonging to range [0; 32) instead of "&#xNN;" encoding. This flag is off by default.

    -
    • -
  • -

    format_attribute_single_quote enables using single quotes ' instead of double quotes " for enclosing attribute values. This flag is off by default.

    -
    • -
-
-
-

These flags control the additional output information:

-
-
-
    -
  • -

    format_no_declaration disables default node declaration output. By default, if the document is saved via save or save_file function, and it does not have any document declaration, a default declaration is output before the document contents. Enabling this flag disables this declaration. This flag has no effect in xml_node::print functions: they never output the default declaration. This flag is off by default.

    -
    • -
  • -

    format_write_bom enables Byte Order Mark (BOM) output. By default, no BOM is output, so in case of non UTF-8 encodings the resulting document’s encoding may not be recognized by some parsers and text editors, if they do not implement sophisticated encoding detection. Enabling this flag adds an encoding-specific BOM to the output. This flag has no effect in xml_node::print functions: they never output the BOM. This flag is off by default.

    -
    • -
  • -

    format_save_file_text changes the file mode when using save_file function. By default, file is opened in binary mode, which means that the output file will -contain platform-independent newline \n (ASCII 10). If this flag is on, file is opened in text mode, which on some systems changes the newline format (i.e. on Windows you can use this flag to output XML documents with \r\n (ASCII 13 10) newlines. This flag is off by default.

    -
    • -
-
-
-

Additionally, there is one predefined option mask:

-
-
-
    -
  • -

    format_default is the default set of flags, i.e. it has all options set to their default values. It sets formatted output with indentation, without BOM and with default node declaration, if necessary.

    -
    • -
-
-
-

This is an example that shows the outputs of different output options (samples/save_options.cpp):

-
-
-
-
// get a test document
-pugi::xml_document doc;
-doc.load_string("<foo bar='baz'><call>hey</call></foo>");
-
-// default options; prints
-// <?xml version="1.0"?>
-// <foo bar="baz">
-//         <call>hey</call>
-// </foo>
-doc.save(std::cout);
-std::cout << std::endl;
-
-// default options with custom indentation string; prints
-// <?xml version="1.0"?>
-// <foo bar="baz">
-// --<call>hey</call>
-// </foo>
-doc.save(std::cout, "--");
-std::cout << std::endl;
-
-// default options without indentation; prints
-// <?xml version="1.0"?>
-// <foo bar="baz">
-// <call>hey</call>
-// </foo>
-doc.save(std::cout, "\t", pugi::format_default & ~pugi::format_indent); // can also pass "" instead of indentation string for the same effect
-std::cout << std::endl;
-
-// raw output; prints
-// <?xml version="1.0"?><foo bar="baz"><call>hey</call></foo>
-doc.save(std::cout, "\t", pugi::format_raw);
-std::cout << std::endl << std::endl;
-
-// raw output without declaration; prints
-// <foo bar="baz"><call>hey</call></foo>
-doc.save(std::cout, "\t", pugi::format_raw | pugi::format_no_declaration);
-std::cout << std::endl;
-
-
-
-
-

7.6. Encodings

-
-

pugixml supports all popular Unicode encodings (UTF-8, UTF-16 (big and little endian), UTF-32 (big and little endian); UCS-2 is naturally supported since it’s a strict subset of UTF-16) and handles all encoding conversions during output. The output encoding is set via the encoding parameter of saving functions, which is of type xml_encoding. The possible values for the encoding are documented in Encodings; the only flag that has a different meaning is encoding_auto.

-
-
-

While all other flags set the exact encoding, encoding_auto is meant for automatic encoding detection. The automatic detection does not make sense for output encoding, since there is usually nothing to infer the actual encoding from, so here encoding_auto means UTF-8 encoding, which is the most popular encoding for XML data storage. This is also the default value of output encoding; specify another value if you do not want UTF-8 encoded output.

-
-
-

Also note that wide stream saving functions do not have encoding argument and always assume encoding_wchar encoding.

-
-
- - - - - -
-
Note
-		 -The current behavior for Unicode conversion is to skip all invalid UTF sequences during conversion. This behavior should not be relied upon; if your node/attribute names do not contain any valid UTF sequences, they may be output as if they are empty, which will result in malformed XML document. -
-
-
-
-

7.7. Customizing document declaration

-
-

When you are saving the document using xml_document::save() or xml_document::save_file(), a default XML document declaration is output, if format_no_declaration is not specified and if the document does not have a declaration node. However, the default declaration is not customizable. If you want to customize the declaration output, you need to create the declaration node yourself.

-
-
- - - - - -
-
Note
-		 -By default the declaration node is not added to the document during parsing. If you just need to preserve the original declaration node, you have to add the flag parse_declaration to the parsing flags; the resulting document will contain the original declaration node, which will be output during saving. -
-
-
-

Declaration node is a node with type node_declaration; it behaves like an element node in that it has attributes with values (but it does not have child nodes). Therefore setting custom version, encoding or standalone declaration involves adding attributes and setting attribute values.

-
-
-

This is an example that shows how to create a custom declaration node (samples/save_declaration.cpp):

-
-
-
-
// get a test document
-pugi::xml_document doc;
-doc.load_string("<foo bar='baz'><call>hey</call></foo>");
-
-// add a custom declaration node
-pugi::xml_node decl = doc.prepend_child(pugi::node_declaration);
-decl.append_attribute("version") = "1.0";
-decl.append_attribute("encoding") = "UTF-8";
-decl.append_attribute("standalone") = "no";
-
-// <?xml version="1.0" encoding="UTF-8" standalone="no"?>
-// <foo bar="baz">
-//         <call>hey</call>
-// </foo>
-doc.save(std::cout);
-std::cout << std::endl;
-
-
-
-
-
-
-

8. XPath

-
-
-

If the task at hand is to select a subset of document nodes that match some criteria, it is possible to code a function using the existing traversal functionality for any practical criteria. However, often either a data-driven approach is desirable, in case the criteria are not predefined and come from a file, or it is inconvenient to use traversal interfaces and a higher-level DSL is required. There is a standard language for XML processing, XPath, that can be useful for these cases. pugixml implements an almost complete subset of XPath 1.0. Because of differences in document object model and some performance implications, there are minor violations of the official specifications, which can be found in Conformance to W3C specification. The rest of this section describes the interface for XPath functionality. Please note that if you wish to learn to use XPath language, you have to look for other tutorials or manuals; for example, you can read W3Schools XPath tutorial or the XPath 1.0 specification.

-
-
-

8.1. XPath types

-
-

-Each XPath expression can have one of the following types: boolean, number, string or node set. Boolean type corresponds to bool type, number type corresponds to double type, string type corresponds to either std::string or std::wstring, depending on whether wide character interface is enabled, and node set corresponds to xpath_node_set type. There is an enumeration, xpath_value_type, which can take the values xpath_type_boolean, xpath_type_number, xpath_type_string or xpath_type_node_set, accordingly.

-
-
-

-Because an XPath node can be either a node or an attribute, there is a special type, xpath_node, which is a discriminated union of these types. A value of this type contains two node handles, one of xml_node type, and another one of xml_attribute type; at most one of them can be non-null. The accessors to get these handles are available:

-
-
-
-
xml_node xpath_node::node() const;
-xml_attribute xpath_node::attribute() const;
-
-
-
-

XPath nodes can be null, in which case both accessors return null handles.

-
-
-

Note that as per XPath specification, each XPath node has a parent, which can be retrieved via this function:

-
-
-
-
xml_node xpath_node::parent() const;
-
-
-
-

parent function returns the node’s parent if the XPath node corresponds to xml_node handle (equivalent to node().parent()), or the node to which the attribute belongs to, if the XPath node corresponds to xml_attribute handle. For null nodes, parent returns null handle.

-
-
-

-Like node and attribute handles, XPath node handles can be implicitly cast to boolean-like object to check if it is a null node, and also can be compared for equality with each other.

-
-
-

You can also create XPath nodes with one of the three constructors: the default constructor, the constructor that takes node argument, and the constructor that takes attribute and node arguments (in which case the attribute must belong to the attribute list of the node). The constructor from xml_node is implicit, so you can usually pass xml_node to functions that expect xpath_node. Apart from that you usually don’t need to create your own XPath node objects, since they are returned to you via selection functions.

-
-
-

XPath expressions operate not on single nodes, but instead on node sets. A node set is a collection of nodes, which can be optionally ordered in either a forward document order or a reverse one. Document order is defined in XPath specification; an XPath node is before another node in document order if it appears before it in XML representation of the corresponding document.

-
-
-

-Node sets are represented by xpath_node_set object, which has an interface that resembles one of sequential random-access containers. It has an iterator type along with usual begin/past-the-end iterator accessors:

-
-
-
-
typedef const xpath_node* xpath_node_set::const_iterator;
-const_iterator xpath_node_set::begin() const;
-const_iterator xpath_node_set::end() const;
-
-
-
-

-And it also can be iterated via indices, just like std::vector:

-
-
-
-
const xpath_node& xpath_node_set::operator[](size_t index) const;
-size_t xpath_node_set::size() const;
-bool xpath_node_set::empty() const;
-
-
-
-

All of the above operations have the same semantics as that of std::vector: the iterators are random-access, all of the above operations are constant time, and accessing the element at index that is greater or equal than the set size results in undefined behavior. You can use both iterator-based and index-based access for iteration, however the iterator-based one can be faster.

-
-
-

-The order of iteration depends on the order of nodes inside the set; the order can be queried via the following function:

-
-
-
-
enum xpath_node_set::type_t {type_unsorted, type_sorted, type_sorted_reverse};
-type_t xpath_node_set::type() const;
-
-
-
-

type function returns the current order of nodes; type_sorted means that the nodes are in forward document order, type_sorted_reverse means that the nodes are in reverse document order, and type_unsorted means that neither order is guaranteed (nodes can accidentally be in a sorted order even if type() returns type_unsorted). If you require a specific order of iteration, you can change it via sort function:

-
-
-
-
void xpath_node_set::sort(bool reverse = false);
-
-
-
-

Calling sort sorts the nodes in either forward or reverse document order, depending on the argument; after this call type() will return type_sorted or type_sorted_reverse.

-
-
-

Often the actual iteration is not needed; instead, only the first element in document order is required. For this, a special accessor is provided:

-
-
-
-
xpath_node xpath_node_set::first() const;
-
-
-
-

This function returns the first node in forward document order from the set, or null node if the set is empty. Note that while the result of the node does not depend on the order of nodes in the set (i.e. on the result of type()), the complexity does - if the set is sorted, the complexity is constant, otherwise it is linear in the number of elements or worse.

-
-
-

While in the majority of cases the node set is returned by XPath functions, sometimes there is a need to manually construct a node set. For such cases, a constructor is provided which takes an iterator range (const_iterator is a typedef for const xpath_node*), and an optional type:

-
-
-
-
xpath_node_set::xpath_node_set(const_iterator begin, const_iterator end, type_t type = type_unsorted);
-
-
-
-

The constructor copies the specified range and sets the specified type. The objects in the range are not checked in any way; you’ll have to ensure that the range contains no duplicates, and that the objects are sorted according to the type parameter. Otherwise XPath operations with this set may produce unexpected results.

-
-
-
-

8.2. Selecting nodes via XPath expression

-
-

-If you want to select nodes that match some XPath expression, you can do it with the following functions:

-
-
-
-
xpath_node xml_node::select_node(const char_t* query, xpath_variable_set* variables = 0) const;
-xpath_node_set xml_node::select_nodes(const char_t* query, xpath_variable_set* variables = 0) const;
-
-
-
-

select_nodes function compiles the expression and then executes it with the node as a context node, and returns the resulting node set. select_node returns only the first node in document order from the result, and is equivalent to calling select_nodes(query).first(). If the XPath expression does not match anything, or the node handle is null, select_nodes returns an empty set, and select_node returns null XPath node.

-
-
-

If exception handling is not disabled, both functions throw xpath_exception if the query can not be compiled or if it returns a value with type other than node set; see Error handling for details.

-
-
-

-While compiling expressions is fast, the compilation time can introduce a significant overhead if the same expression is used many times on small subtrees. If you’re doing many similar queries, consider compiling them into query objects (see Using query objects for further reference). Once you get a compiled query object, you can pass it to select functions instead of an expression string:

-
-
-
-
xpath_node xml_node::select_node(const xpath_query& query) const;
-xpath_node_set xml_node::select_nodes(const xpath_query& query) const;
-
-
-
-

If exception handling is not disabled, both functions throw xpath_exception if the query returns a value with type other than node set.

-
-
-

This is an example of selecting nodes using XPath expressions (samples/xpath_select.cpp):

-
-
-
-
pugi::xpath_node_set tools = doc.select_nodes("/Profile/Tools/Tool[@AllowRemote='true' and @DeriveCaptionFrom='lastparam']");
-
-std::cout << "Tools:\n";
-
-for (pugi::xpath_node_set::const_iterator it = tools.begin(); it != tools.end(); ++it)
-{
-    pugi::xpath_node node = *it;
-    std::cout << node.node().attribute("Filename").value() << "\n";
-}
-
-pugi::xpath_node build_tool = doc.select_node("//Tool[contains(Description, 'build system')]");
-
-if (build_tool)
-    std::cout << "Build tool: " << build_tool.node().attribute("Filename").value() << "\n";
-
-
-
-
-

8.3. Using query objects

-
-

When you call select_nodes with an expression string as an argument, a query object is created behind the scenes. A query object represents a compiled XPath expression. Query objects can be needed in the following circumstances:

-
-
-
    -
  • -

    You can precompile expressions to query objects to save compilation time if it becomes an issue;

    -
    • -
  • -

    You can use query objects to evaluate XPath expressions which result in booleans, numbers or strings;

    -
    • -
  • -

    You can get the type of expression value via query object.

    -
    • -
-
-
-

Query objects correspond to xpath_query type. They are immutable and non-copyable: they are bound to the expression at creation time and can not be cloned. If you want to put query objects in a container, either allocate them on heap via new operator and store pointers to xpath_query in the container, or use a C11 compiler (query objects are movable in C11).

-
-
-

You can create a query object with the constructor that takes XPath expression as an argument:

-
-
-
-
explicit xpath_query::xpath_query(const char_t* query, xpath_variable_set* variables = 0);
-
-
-
-

The expression is compiled and the compiled representation is stored in the new query object. If compilation fails, xpath_exception is thrown if exception handling is not disabled (see Error handling for details). After the query is created, you can query the type of the evaluation result using the following function:

-
-
-
-
xpath_value_type xpath_query::return_type() const;
-
-
-
-

-You can evaluate the query using one of the following functions:

-
-
-
-
bool xpath_query::evaluate_boolean(const xpath_node& n) const;
-double xpath_query::evaluate_number(const xpath_node& n) const;
-string_t xpath_query::evaluate_string(const xpath_node& n) const;
-xpath_node_set xpath_query::evaluate_node_set(const xpath_node& n) const;
-xpath_node xpath_query::evaluate_node(const xpath_node& n) const;
-
-
-
-

All functions take the context node as an argument, compute the expression and return the result, converted to the requested type. According to XPath specification, value of any type can be converted to boolean, number or string value, but no type other than node set can be converted to node set. Because of this, evaluate_boolean, evaluate_number and evaluate_string always return a result, but evaluate_node_set and evaluate_node result in an error if the return type is not node set (see Error handling).

-
-
- - - - - -
-
Note
-		 -Calling node.select_nodes("query") is equivalent to calling xpath_query("query").evaluate_node_set(node). Calling node.select_node("query") is equivalent to calling xpath_query("query").evaluate_node(node). -
-
-
-

Note that evaluate_string function returns the STL string; as such, it’s not available in PUGIXML_NO_STL mode and also usually allocates memory. There is another string evaluation function:

-
-
-
-
size_t xpath_query::evaluate_string(char_t* buffer, size_t capacity, const xpath_node& n) const;
-
-
-
-

This function evaluates the string, and then writes the result to buffer (but at most capacity characters); then it returns the full size of the result in characters, including the terminating zero. If capacity is not 0, the resulting buffer is always zero-terminated. You can use this function as follows:

-
-
-
    -
  • -

    First call the function with buffer = 0 and capacity = 0; then allocate the returned amount of characters, and call the function again, passing the allocated storage and the amount of characters;

    -
    • -
  • -

    First call the function with small buffer and buffer capacity; then, if the result is larger than the capacity, the output has been trimmed, so allocate a larger buffer and call the function again.

    -
    • -
-
-
-

This is an example of using query objects (samples/xpath_query.cpp):

-
-
-
-
// Select nodes via compiled query
-pugi::xpath_query query_remote_tools("/Profile/Tools/Tool[@AllowRemote='true']");
-
-pugi::xpath_node_set tools = query_remote_tools.evaluate_node_set(doc);
-std::cout << "Remote tool: ";
-tools[2].node().print(std::cout);
-
-// Evaluate numbers via compiled query
-pugi::xpath_query query_timeouts("sum(//Tool/@Timeout)");
-std::cout << query_timeouts.evaluate_number(doc) << std::endl;
-
-// Evaluate strings via compiled query for different context nodes
-pugi::xpath_query query_name_valid("string-length(substring-before(@Filename, '_')) > 0 and @OutputFileMasks");
-pugi::xpath_query query_name("concat(substring-before(@Filename, '_'), ' produces ', @OutputFileMasks)");
-
-for (pugi::xml_node tool = doc.first_element_by_path("Profile/Tools/Tool"); tool; tool = tool.next_sibling())
-{
-    std::string s = query_name.evaluate_string(tool);
-
-    if (query_name_valid.evaluate_boolean(tool)) std::cout << s << std::endl;
-}
-
-
-
-
-

8.4. Using variables

-
-

XPath queries may contain references to variables; this is useful if you want to use queries that depend on some dynamic parameter without manually preparing the complete query string, or if you want to reuse the same query object for similar queries.

-
-
-

Variable references have the form $name; in order to use them, you have to provide a variable set, which includes all variables present in the query with correct types. This set is passed to xpath_query constructor or to select_nodes/select_node functions:

-
-
-
-
explicit xpath_query::xpath_query(const char_t* query, xpath_variable_set* variables = 0);
-xpath_node xml_node::select_node(const char_t* query, xpath_variable_set* variables = 0) const;
-xpath_node_set xml_node::select_nodes(const char_t* query, xpath_variable_set* variables = 0) const;
-
-
-
-

If you’re using query objects, you can change the variable values before evaluate/select calls to change the query behavior.

-
-
- - - - - -
-
Note
-		 -The variable set pointer is stored in the query object; you have to ensure that the lifetime of the set exceeds that of query object. -
-
-
-

Variable sets correspond to xpath_variable_set type, which is essentially a variable container.

-
-
-

You can add new variables with the following function:

-
-
-
-
xpath_variable* xpath_variable_set::add(const char_t* name, xpath_value_type type);
-
-
-
-

The function tries to add a new variable with the specified name and type; if the variable with such name does not exist in the set, the function adds a new variable and returns the variable handle; if there is already a variable with the specified name, the function returns the variable handle if variable has the specified type. Otherwise the function returns null pointer; it also returns null pointer on allocation failure.

-
-
-

New variables are assigned the default value which depends on the type: 0 for numbers, false for booleans, empty string for strings and empty set for node sets.

-
-
-

You can get the existing variables with the following functions:

-
-
-
-
xpath_variable* xpath_variable_set::get(const char_t* name);
-const xpath_variable* xpath_variable_set::get(const char_t* name) const;
-
-
-
-

The functions return the variable handle, or null pointer if the variable with the specified name is not found.

-
-
-

Additionally, there are the helper functions for setting the variable value by name; they try to add the variable with the corresponding type, if it does not exist, and to set the value. If the variable with the same name but with different type is already present, they return false; they also return false on allocation failure. Note that these functions do not perform any type conversions.

-
-
-
-
bool xpath_variable_set::set(const char_t* name, bool value);
-bool xpath_variable_set::set(const char_t* name, double value);
-bool xpath_variable_set::set(const char_t* name, const char_t* value);
-bool xpath_variable_set::set(const char_t* name, const xpath_node_set& value);
-
-
-
-

The variable values are copied to the internal variable storage, so you can modify or destroy them after the functions return.

-
-
-

If setting variables by name is not efficient enough, or if you have to inspect variable information or get variable values, you can use variable handles. A variable corresponds to the xpath_variable type, and a variable handle is simply a pointer to xpath_variable.

-
-
-

-In order to get variable information, you can use one of the following functions:

-
-
-
-
const char_t* xpath_variable::name() const;
-xpath_value_type xpath_variable::type() const;
-
-
-
-

Note that each variable has a distinct type which is specified upon variable creation and can not be changed later.

-
-
-

-In order to get variable value, you should use one of the following functions, depending on the variable type:

-
-
-
-
bool xpath_variable::get_boolean() const;
-double xpath_variable::get_number() const;
-const char_t* xpath_variable::get_string() const;
-const xpath_node_set& xpath_variable::get_node_set() const;
-
-
-
-

These functions return the value of the variable. Note that no type conversions are performed; if the type mismatch occurs, a dummy value is returned (false for booleans, NaN for numbers, empty string for strings and empty set for node sets).

-
-
-

In order to set variable value, you should use one of the following functions, depending on the variable type:

-
-
-
-
bool xpath_variable::set(bool value);
-bool xpath_variable::set(double value);
-bool xpath_variable::set(const char_t* value);
-bool xpath_variable::set(const xpath_node_set& value);
-
-
-
-

These functions modify the variable value. Note that no type conversions are performed; if the type mismatch occurs, the functions return false; they also return false on allocation failure. The variable values are copied to the internal variable storage, so you can modify or destroy them after the functions return.

-
-
-

This is an example of using variables in XPath queries (samples/xpath_variables.cpp):

-
-
-
-
// Select nodes via compiled query
-pugi::xpath_variable_set vars;
-vars.add("remote", pugi::xpath_type_boolean);
-
-pugi::xpath_query query_remote_tools("/Profile/Tools/Tool[@AllowRemote = string($remote)]", &vars);
-
-vars.set("remote", true);
-pugi::xpath_node_set tools_remote = query_remote_tools.evaluate_node_set(doc);
-
-vars.set("remote", false);
-pugi::xpath_node_set tools_local = query_remote_tools.evaluate_node_set(doc);
-
-std::cout << "Remote tool: ";
-tools_remote[2].node().print(std::cout);
-
-std::cout << "Local tool: ";
-tools_local[0].node().print(std::cout);
-
-// You can pass the context directly to select_nodes/select_node
-pugi::xpath_node_set tools_local_imm = doc.select_nodes("/Profile/Tools/Tool[@AllowRemote = string($remote)]", &vars);
-
-std::cout << "Local tool imm: ";
-tools_local_imm[0].node().print(std::cout);
-
-
-
-
-

8.5. Error handling

-
-

There are two different mechanisms for error handling in XPath implementation; the mechanism used depends on whether exception support is disabled (this is controlled with PUGIXML_NO_EXCEPTIONS define).

-
-
-

-By default, XPath functions throw xpath_exception object in case of errors; additionally, in the event any memory allocation fails, an std::bad_alloc exception is thrown. Also xpath_exception is thrown if the query is evaluated to a node set, but the return type is not node set. If the query constructor succeeds (i.e. no exception is thrown), the query object is valid. Otherwise you can get the error details via one of the following functions:

-
-
-
-
virtual const char* xpath_exception::what() const throw();
-const xpath_parse_result& xpath_exception::result() const;
-
-
-
-

-If exceptions are disabled, then in the event of parsing failure the query is initialized to invalid state; you can test if the query object is valid by using it in a boolean expression: if (query) { …​ }. Additionally, you can get parsing result via the result() accessor:

-
-
-
-
const xpath_parse_result& xpath_query::result() const;
-
-
-
-

Without exceptions, evaluating invalid query results in false, empty string, NaN or an empty node set, depending on the type; evaluating a query as a node set results in an empty node set if the return type is not node set.

-
-
-

The information about parsing result is returned via xpath_parse_result object. It contains parsing status and the offset of last successfully parsed character from the beginning of the source stream:

-
-
-
-
struct xpath_parse_result
-{
-    const char* error;
-    ptrdiff_t offset;
-
-    operator bool() const;
-    const char* description() const;
-};
-
-
-
-

Parsing result is represented as the error message; it is either a null pointer, in case there is no error, or the error message in the form of ASCII zero-terminated string.

-
-
-

description() member function can be used to get the error message; it never returns the null pointer, so you can safely use description() even if query parsing succeeded. Note that description() returns a char string even in PUGIXML_WCHAR_MODE; you’ll have to call as_wide to get the wchar_t string.

-
-
-

In addition to the error message, parsing result has an offset member, which contains the offset of last successfully parsed character. This offset is in units of pugi::char_t (bytes for character mode, wide characters for wide character mode).

-
-
-

Parsing result object can be implicitly converted to bool like this: if (result) { …​ } else { …​ }.

-
-
-

This is an example of XPath error handling (samples/xpath_error.cpp):

-
-
-
-
// Exception is thrown for incorrect query syntax
-try
-{
-    doc.select_nodes("//nodes[#true()]");
-}
-catch (const pugi::xpath_exception& e)
-{
-    std::cout << "Select failed: " << e.what() << std::endl;
-}
-
-// Exception is thrown for incorrect query semantics
-try
-{
-    doc.select_nodes("(123)/next");
-}
-catch (const pugi::xpath_exception& e)
-{
-    std::cout << "Select failed: " << e.what() << std::endl;
-}
-
-// Exception is thrown for query with incorrect return type
-try
-{
-    doc.select_nodes("123");
-}
-catch (const pugi::xpath_exception& e)
-{
-    std::cout << "Select failed: " << e.what() << std::endl;
-}
-
-
-
-
-

8.6. Conformance to W3C specification

-
-

Because of the differences in document object models, performance considerations and implementation complexity, pugixml does not provide a fully conformant XPath 1.0 implementation. This is the current list of incompatibilities:

-
-
-
    -
  • -

    Consecutive text nodes sharing the same parent are not merged, i.e. in <node>text1 <![CDATA[data]]> text2</node> node should have one text node child, but instead has three.

    -
    • -
  • -

    Since the document type declaration is not used for parsing, id() function always returns an empty node set.

    -
    • -
  • -

    Namespace nodes are not supported (affects namespace:: axis).

    -
    • -
  • -

    Name tests are performed on QNames in XML document instead of expanded names; for <foo xmlns:ns1='uri' xmlns:ns2='uri'><ns1:child/><ns2:child/></foo>, query foo/ns1:* will return only the first child, not both of them. Compliant XPath implementations can return both nodes if the user provides appropriate namespace declarations.

    -
    • -
  • -

    String functions consider a character to be either a single char value or a single wchar_t value, depending on the library configuration; this means that some string functions are not fully Unicode-aware. This affects substring(), string-length() and translate() functions.

    -
    • -
-
-
-
-
-
-

9. Changelog

-
-
-

v1.14 2023-10-01

-
-

Maintenance release. Changes:

-
-
-
    -
  • -

    Improvements:

    -
    -
      -
    1. -

      xml_attribute::set_name and xml_node::set_name now have overloads that accept pointer to non-null-terminated string and size

      -
      2. -
    2. -

      Implement parse_merge_pcdata parsing mode in which PCDATA contents is merged into a single node when original document had comments that were skipped during parsing

      -
      3. -
    3. -

      xml_document::load_file now returns a more consistent error status when given a path to a folder

      -
      4. -
    -
    -
    • -
  • -

    Bug fixes:

    -
    -
      -
    1. -

      Fix assertion in XPath number→string conversion when using non-English locales

      -
      2. -
    2. -

      Fix PUGIXML_STATIC_CRT CMake option to correctly select static CRT when using MSVC and recent CMake

      -
      3. -
    -
    -
    • -
  • -

    Compatibility improvements:

    -
    -
      -
    1. -

      Fix GCC 2.95/3.3 builds

      -
      2. -
    2. -

      Fix CMake 3.27 deprecation warnings

      -
      3. -
    3. -

      Fix XCode 14 sprintf deprecation warning when compiling in C++03 mode

      -
      4. -
    4. -

      Fix clang/gcc warnings -Wweak-vtables, -Wreserved-macro-identifier

      -
      5. -
    -
    -
    • -
-
-
-
-

v1.13 2022-11-01

-
-

Maintenance release. Changes:

-
-
-
    -
  • -

    Improvements:

    -
    -
      -
    1. -

      xml_attribute::set_value, xml_node::set_value and xml_text::set now have overloads that accept pointer to non-null-terminated string and size

      -
      2. -
    2. -

      Improve performance of tree traversal when using compact mode (PUGIXML_COMPACT)

      -
      3. -
    -
    -
    • -
  • -

    Bug fixes:

    -
    -
      -
    1. -

      Fix error handling in xml_document::save_file that could result in the function succeeding while running out of disk space

      -
      2. -
    2. -

      Fix memory leak during error handling of some out-of-memory conditions during xml_document::load

      -
      3. -
    -
    -
    • -
  • -

    Compatibility improvements:

    -
    -
      -
    1. -

      Fix exported symbols in CMake DLL builds when using CMake

      -
      2. -
    2. -

      Fix exported symbols in CMake shared object builds when using -fvisibility=hidden

      -
      3. -
    -
    -
    • -
-
-
-
-

v1.12 2022-02-09

-
-

Maintenance release. Changes:

-
-
-
    -
  • -

    Bug fixes:

    -
    -
      -
    1. -

      Fix a bug in xml_document move construction when the source of the move is empty

      -
      2. -
    2. -

      Fix const-correctness issues with iterator objects to support C++20 ranges

      -
      3. -
    -
    -
    • -
  • -

    XPath improvements:

    -
    -
      -
    1. -

      Improved detection of overly complex queries that may result in stack overflow during parsing

      -
      2. -
    -
    -
    • -
  • -

    Compatibility improvements:

    -
    -
      -
    1. -

      Fix Cygwin support for DLL builds

      -
      2. -
    2. -

      Fix Windows CE support

      -
      3. -
    3. -

      Add NuGet builds and project files for VS2022

      -
      4. -
    -
    -
    • -
  • -

    Build system changes

    -
    -
      -
    1. -

      All CMake options now have the prefix PUGIXML_. This may require changing dependent build configurations.

      -
      2. -
    2. -

      Many build settings are now exposed via CMake settings, most notably PUGIXML_COMPACT and PUGIXML_WCHAR_MODE can be set without changing pugiconfig.hpp

      -
      3. -
    -
    -
    • -
-
-
-
-

v1.11 2020-11-26

-
-

Maintenance release. Changes:

-
-
-
    -
  • -

    New features:

    -
    -
      -
    1. -

      Add xml_node::remove_attributes and xml_node::remove_children

      -
      2. -
    2. -

      Add a way to customize floating point precision via xml_attribute::set and xml_text::set overloads

      -
      3. -
    -
    -
    • -
  • -

    XPath improvements:

    -
    -
      -
    1. -

      XPath parser now limits recursion depth which prevents stack overflow on malicious queries

      -
      2. -
    -
    -
    • -
  • -

    Compatibility improvements:

    -
    -
      -
    1. -

      Fix Visual Studio warnings when built using clang-cl compiler

      -
      2. -
    2. -

      Fix Wconversion warnings in gcc

      -
      3. -
    3. -

      Fix Wzero-as-null-pointer-constant warnings in pugixml.hpp

      -
      4. -
    4. -

      Work around several static analysis false positives

      -
      5. -
    -
    -
    • -
  • -

    Build system changes

    -
    -
      -
    1. -

      The CMake package for pugixml now provides a pugixml::pugixml target rather than a pugixml target. A compatibility pugixml target is provided if at least version 1.11 is not requested.

      -
      2. -
    -
    -
    • -
-
-
-
-

v1.10 2019-09-15

-
-

Maintenance release. Changes:

-
-
-
    -
  • -

    Behavior changes:

    -
    -
      -
    1. -

      Tab characters (ASCII 9) in attribute values are now encoded as '&#9;' to survive roundtripping

      -
      2. -
    2. -

      > characters are no longer escaped in attribute values

      -
      3. -
    -
    -
    • -
  • -

    New features:

    -
    -
      -
    1. -

      Add Visual Studio .natvis files to improve debugging experience

      -
      2. -
    2. -

      CMake improvements (USE_POSTFIX and BUILD_SHARED_AND_STATIC_LIBS options for building multiple versions and pkg-config tweaks)

      -
      3. -
    3. -

      Add format_skip_control_chars formatting flag to skip non-printable ASCII characters that are invalid to use in well-formed XML files

      -
      4. -
    4. -

      Add format_attribute_single_quote formatting flag to use single quotes for attribute values instead of default double quotes.

      -
      5. -
    -
    -
    • -
  • -

    XPath improvements:

    -
    -
      -
    1. -

      XPath union now results in a stable order that doesn’t depend on memory allocations; crucially, this may require sorting the output of XPath query operation if you rely on the document-ordered traversal

      -
      2. -
    2. -

      Improve performance of XPath union operation, making it ~2x faster

      -
      3. -
    -
    -
    • -
  • -

    Compatibility improvements:

    -
    -
      -
    1. -

      Fix Visual Studio warnings when built in a DLL configuration

      -
      2. -
    2. -

      Fix static analysis false positives in Coverity and clang

      -
      3. -
    3. -

      Fix Wdouble-promotion warnings in gcc

      -
      4. -
    4. -

      Add Visual Studio 2019 support for NuGet packages

      -
      5. -
    -
    -
    • -
-
-
-
-

v1.9 2018-04-04

-
-

Maintenance release. Changes:

-
-
-
    -
  • -

    Specification changes:

    -
    -
      -
    1. -

      xml_document::load(const char*) (deprecated in 1.5) now has deprecated attribute; use xml_document::load_string instead

      -
      2. -
    2. -

      xml_node::select_single_node (deprecated in 1.5) now has deprecated attribute; use xml_node::select_node instead

      -
      3. -
    -
    -
    • -
  • -

    New features:

    -
    -
      -
    1. -

      Add move semantics support for xml_document and improve move semantics support for other objects

      -
      2. -
    2. -

      CMake build now exports include directories

      -
      3. -
    3. -

      CMake build with BUILD_SHARED_LIBS=ON now uses dllexport attribute for MSVC

      -
      4. -
    -
    -
    • -
  • -

    XPath improvements:

    -
    -
      -
    1. -

      Rework parser/evaluator to not rely on exceptional control flow; longjmp is no longer used when exceptions are disabled

      -
      2. -
    2. -

      Improve error messages for certain invalid expressions such as .[1] or (1

      -
      3. -
    3. -

      Minor performance improvements

      -
      4. -
    -
    -
    • -
  • -

    Compatibility improvements:

    -
    -
      -
    1. -

      Fix Texas Instruments compiler warnings

      -
      2. -
    2. -

      Fix compilation issues with limits.h for some versions of gcc

      -
      3. -
    3. -

      Fix compilation issues with Clang/C2

      -
      4. -
    4. -

      Fix implicit fallthrough warnings in gcc 7

      -
      5. -
    5. -

      Fix unknown attribute directive warnings in gcc 8

      -
      6. -
    6. -

      Fix cray++ compiler errors

      -
      7. -
    7. -

      Fix unsigned integer overflow errors with -fsanitize=integer

      -
      8. -
    8. -

      Fix undefined behavior sanitizer issues in compact mode

      -
      9. -
    -
    -
    • -
-
-
-
-

v1.8 2016-11-24

-
-

Maintenance release. Changes:

-
-
-
    -
  • -

    Specification changes:

    -
    -
      -
    1. -

      When printing empty elements, a space is no longer added before / in format_raw mode

      -
      2. -
    -
    -
    • -
  • -

    New features:

    -
    -
      -
    1. -

      Added parse_embed_pcdata parsing mode in which PCDATA value is stored in the element node if possible (significantly reducing memory consumption for some documents)

      -
      2. -
    2. -

      Added auto-detection support for Latin-1 (ISO-8859-1) encoding during parsing

      -
      3. -
    3. -

      Added format_no_empty_element_tags formatting flag that outputs start/end tags instead of empty element tags for empty elements

      -
      4. -
    -
    -
    • -
  • -

    Performance improvements:

    -
    -
      -
    1. -

      Minor memory allocation improvements (yielding up to 1% memory savings in some cases)

      -
      2. -
    -
    -
    • -
  • -

    Compatibility improvements:

    -
    -
      -
    1. -

      Fixed compilation issues for Borland C++ 5.4

      -
      2. -
    2. -

      Fixed compilation issues for some distributions of MinGW 3.8

      -
      3. -
    3. -

      Fixed various Clang/GCC warnings

      -
      4. -
    4. -

      Enabled move semantics support for XPath objects for MSVC 2010 and above

      -
      5. -
    -
    -
    • -
-
-
-
-

v1.7 2015-10-19

-
-

Major release, featuring performance and memory improvements along with some new features. Changes:

-
-
-
    -
  • -

    Compact mode:

    -
    -
      -
    1. -

      Introduced a new tree storage mode that takes significantly less memory (2-5x smaller DOM) at some performance cost.

      -
      2. -
    2. -

      The mode can be enabled using PUGIXML_COMPACT define.

      -
      3. -
    -
    -
    • -
  • -

    New integer parsing/formatting implementation:

    -
    -
      -
    1. -

      Functions that convert from and to integers (e.g. as_int/set_value) do not rely on CRT any more.

      -
      2. -
    2. -

      New implementation is 3-5x faster and is always correct wrt overflow or underflow. This is a behavior change - where previously as_uint() would return UINT_MAX on a value "-1", it now returns 0.

      -
      3. -
    -
    -
    • -
  • -

    New features:

    -
    -
      -
    1. -

      XPath objects (xpath_query, xpath_node_set, xpath_variable_set) are now movable if your compiler supports C++11. Additionally, xpath_variable_set is copyable.

      -
      2. -
    2. -

      Added format_indent_attributes that makes the resulting XML friendlier to line diff/merge tools.

      -
      3. -
    3. -

      Added a variant of xml_node::attribute function with a hint that can improve lookup performance.

      -
      4. -
    4. -

      Custom allocation functions are now allowed (but not required) to throw instead of returning a null pointer.

      -
      5. -
    -
    -
    • -
  • -

    Bug fixes:

    -
    -
      -
    1. -

      Fix Clang 3.7 crashes in out-of-memory cases (C++ DR 1748)

      -
      2. -
    2. -

      Fix XPath crashes on SPARC64 (and other 32-bit architectures where doubles have to be aligned to 8 bytes)

      -
      3. -
    3. -

      Fix xpath_node_set assignment to provide strong exception guarantee

      -
      4. -
    4. -

      Fix saving for custom xml_writer implementations that can throw from write()

      -
      5. -
    -
    -
    • -
-
-
-
-

v1.6 2015-04-10

-
-

Maintenance release. Changes:

-
-
-
    -
  • -

    Specification changes:

    -
    -
      -
    1. -

      Attribute/text values now use more digits when printing floating point numbers to guarantee round-tripping.

      -
      2. -
    2. -

      Text nodes no longer get extra surrounding whitespace when pretty-printing nodes with mixed contents

      -
      3. -
    -
    -
    • -
  • -

    Bug fixes:

    -
    -
      -
    1. -

      Fixed translate and normalize-space XPath functions to no longer return internal NUL characters

      -
      2. -
    2. -

      Fixed buffer overrun on malformed comments inside DOCTYPE sections

      -
      3. -
    3. -

      DOCTYPE parsing can no longer run out of stack space on malformed inputs (XML parsing is now using bounded stack space)

      -
      4. -
    4. -

      Adjusted processing instruction output to avoid malformed documents if the PI value contains ?>

      -
      5. -
    -
    -
    • -
-
-
-
-

v1.5 2014-11-27

-
-

Major release, featuring a lot of performance improvements and some new features.

-
-
-
    -
  • -

    Specification changes:

    -
    -
      -
    1. -

      xml_document::load(const char_t*) was renamed to load_string; the old method is still available and will be deprecated in a future release

      -
      2. -
    2. -

      xml_node::select_single_node was renamed to select_node; the old method is still available and will be deprecated in a future release.

      -
      3. -
    -
    -
    • -
  • -

    New features:

    -
    -
      -
    1. -

      Added xml_node::append_move and other functions for moving nodes within a document

      -
      2. -
    2. -

      Added xpath_query::evaluate_node for evaluating queries with a single node as a result

      -
      3. -
    -
    -
    • -
  • -

    Performance improvements:

    -
    -
      -
    1. -

      Optimized XML parsing (10-40% faster with clang/gcc, up to 10% faster with MSVC)

      -
      2. -
    2. -

      Optimized memory consumption when copying nodes in the same document (string contents is now shared)

      -
      3. -
    3. -

      Optimized node copying (10% faster for cross-document copies, 3x faster for inter-document copies; also it now consumes a constant amount of stack space)

      -
      4. -
    4. -

      Optimized node output (60% faster; also it now consumes a constant amount of stack space)

      -
      5. -
    5. -

      Optimized XPath allocation (query evaluation now results in fewer temporary allocations)

      -
      6. -
    6. -

      Optimized XPath sorting (node set sorting is 2-3x faster in some cases)

      -
      7. -
    7. -

      Optimized XPath evaluation (XPathMark suite is 100x faster; some commonly used queries are 3-4x faster)

      -
      8. -
    -
    -
    • -
  • -

    Compatibility improvements:

    -
    -
      -
    1. -

      Fixed xml_node::offset_debug for corner cases

      -
      2. -
    2. -

      Fixed undefined behavior while calling memcpy in some cases

      -
      3. -
    3. -

      Fixed MSVC 2015 compilation warnings

      -
      4. -
    4. -

      Fixed contrib/foreach.hpp for Boost 1.56.0

      -
      5. -
    -
    -
    • -
  • -

    Bug fixes

    -
    -
      -
    1. -

      Adjusted comment output to avoid malformed documents if the comment value contains --

      -
      2. -
    2. -

      Fix XPath sorting for documents that were constructed using append_buffer

      -
      3. -
    3. -

      Fix load_file for wide-character paths with non-ASCII characters in MinGW with C++11 mode enabled

      -
      4. -
    -
    -
    • -
-
-
-
-

v1.4 2014-02-27

-
-

Major release, featuring various new features, bug fixes and compatibility improvements.

-
-
-
    -
  • -

    Specification changes:

    -
    -
      -
    1. -

      Documents without element nodes are now rejected with status_no_document_element error, unless parse_fragment option is used

      -
      2. -
    -
    -
    • -
  • -

    New features:

    -
    -
      -
    1. -

      Added XML fragment parsing (parse_fragment flag)

      -
      2. -
    2. -

      Added PCDATA whitespace trimming (parse_trim_pcdata flag)

      -
      3. -
    3. -

      Added long long support for xml_attribute and xml_text (as_llong, as_ullong and set_value/set overloads)

      -
      4. -
    4. -

      Added hexadecimal integer parsing support for as_int/as_uint/as_llong/as_ullong

      -
      5. -
    5. -

      Added xml_node::append_buffer to improve performance of assembling documents from fragments

      -
      6. -
    6. -

      xml_named_node_iterator is now bidirectional

      -
      7. -
    7. -

      Reduced XPath stack consumption during compilation and evaluation (useful for embedded systems)

      -
      8. -
    -
    -
    • -
  • -

    Compatibility improvements:

    -
    -
      -
    1. -

      Improved support for platforms without wchar_t support

      -
      2. -
    2. -

      Fixed several false positives in clang static analysis

      -
      3. -
    3. -

      Fixed several compilation warnings for various GCC versions

      -
      4. -
    -
    -
    • -
  • -

    Bug fixes:

    -
    -
      -
    1. -

      Fixed undefined pointer arithmetic in XPath implementation

      -
      2. -
    2. -

      Fixed non-seekable iostream support for certain stream types, i.e. Boost file_source with pipe input

      -
      3. -
    3. -

      Fixed xpath_query::return_type for some expressions

      -
      4. -
    4. -

      Fixed dllexport issues with xml_named_node_iterator

      -
      5. -
    5. -

      Fixed find_child_by_attribute assertion for attributes with null name/value

      -
      6. -
    -
    -
    • -
-
-
-
-

v1.2 2012-05-01

-
-

Major release, featuring header-only mode, various interface enhancements (i.e. PCDATA manipulation and C++11 iteration), many other features and compatibility improvements.

-
-
-
    -
  • -

    New features:

    -
    -
      -
    1. -

      Added xml_text helper class for working with PCDATA/CDATA contents of an element node

      -
      2. -
    2. -

      Added optional header-only mode (controlled by PUGIXML_HEADER_ONLY define)

      -
      3. -
    3. -

      Added xml_node::children() and xml_node::attributes() for C++11 ranged for loop or BOOST_FOREACH

      -
      4. -
    4. -

      Added support for Latin-1 (ISO-8859-1) encoding conversion during loading and saving

      -
      5. -
    5. -

      Added custom default values for xml_attribute::as_* (they are returned if the attribute does not exist)

      -
      6. -
    6. -

      Added parse_ws_pcdata_single flag for preserving whitespace-only PCDATA in case it’s the only child

      -
      7. -
    7. -

      Added format_save_file_text for xml_document::save_file to open files as text instead of binary (changes newlines on Windows)

      -
      8. -
    8. -

      Added format_no_escapes flag to disable special symbol escaping (complements ~parse_escapes)

      -
      9. -
    9. -

      Added support for loading document from streams that do not support seeking

      -
      10. -
    10. -

      Added PUGIXML_MEMORY_* constants for tweaking allocation behavior (useful for embedded systems)

      -
      11. -
    11. -

      Added PUGIXML_VERSION preprocessor define

      -
      12. -
    -
    -
    • -
  • -

    Compatibility improvements:

    -
    -
      -
    1. -

      Parser does not require setjmp support (improves compatibility with some embedded platforms, enables /clr:pure compilation)

      -
      2. -
    2. -

      STL forward declarations are no longer used (fixes SunCC/RWSTL compilation, fixes clang compilation in C++11 mode)

      -
      3. -
    3. -

      Fixed AirPlay SDK, Android, Windows Mobile (WinCE) and C++/CLI compilation

      -
      4. -
    4. -

      Fixed several compilation warnings for various GCC versions, Intel C++ compiler and Clang

      -
      5. -
    -
    -
    • -
  • -

    Bug fixes:

    -
    -
      -
    1. -

      Fixed unsafe bool conversion to avoid problems on C++/CLI

      -
      2. -
    2. -

      Iterator dereference operator is const now (fixes Boost filter_iterator support)

      -
      3. -
    3. -

      xml_document::save_file now checks for file I/O errors during saving

      -
      4. -
    -
    -
    • -
-
-
-
-

v1.0 2010-11-01

-
-

Major release, featuring many XPath enhancements, wide character filename support, miscellaneous performance improvements, bug fixes and more.

-
-
-
    -
  • -

    XPath:

    -
    -
      -
    1. -

      XPath implementation is moved to pugixml.cpp (which is the only source file now); use PUGIXML_NO_XPATH if you want to disable XPath to reduce code size

      -
      2. -
    2. -

      XPath is now supported without exceptions (PUGIXML_NO_EXCEPTIONS); the error handling mechanism depends on the presence of exception support

      -
      3. -
    3. -

      XPath is now supported without STL (PUGIXML_NO_STL)

      -
      4. -
    4. -

      Introduced variable support

      -
      5. -
    5. -

      Introduced new xpath_query::evaluate_string, which works without STL

      -
      6. -
    6. -

      Introduced new xpath_node_set constructor (from an iterator range)

      -
      7. -
    7. -

      Evaluation function now accept attribute context nodes

      -
      8. -
    8. -

      All internal allocations use custom allocation functions

      -
      9. -
    9. -

      Improved error reporting; now a last parsed offset is returned together with the parsing error

      -
      10. -
    -
    -
    • -
  • -

    Bug fixes:

    -
    -
      -
    1. -

      Fixed memory leak for loading from streams with stream exceptions turned on

      -
      2. -
    2. -

      Fixed custom deallocation function calling with null pointer in one case

      -
      3. -
    3. -

      Fixed missing attributes for iterator category functions; all functions/classes can now be DLL-exported

      -
      4. -
    4. -

      Worked around Digital Mars compiler bug, which lead to minor read overfetches in several functions

      -
      5. -
    5. -

      load_file now works with 2+ Gb files in MSVC/MinGW

      -
      6. -
    6. -

      XPath: fixed memory leaks for incorrect queries

      -
      7. -
    7. -

      XPath: fixed xpath_node() attribute constructor with empty attribute argument

      -
      8. -
    8. -

      XPath: fixed lang() function for non-ASCII arguments

      -
      9. -
    -
    -
    • -
  • -

    Specification changes:

    -
    -
      -
    1. -

      CDATA nodes containing ]]> are printed as several nodes; while this changes the internal structure, this is the only way to escape CDATA contents

      -
      2. -
    2. -

      Memory allocation errors during parsing now preserve last parsed offset (to give an idea about parsing progress)

      -
      3. -
    3. -

      If an element node has the only child, and it is of CDATA type, then the extra indentation is omitted (previously this behavior only held for PCDATA children)

      -
      4. -
    -
    -
    • -
  • -

    Additional functionality:

    -
    -
      -
    1. -

      Added xml_parse_result default constructor

      -
      2. -
    2. -

      Added xml_document::load_file and xml_document::save_file with wide character paths

      -
      3. -
    3. -

      Added as_utf8 and as_wide overloads for std::wstring/std::string arguments

      -
      4. -
    4. -

      Added DOCTYPE node type (node_doctype) and a special parse flag, parse_doctype, to add such nodes to the document during parsing

      -
      5. -
    5. -

      Added parse_full parse flag mask, which extends parse_default with all node type parsing flags except parse_ws_pcdata

      -
      6. -
    6. -

      Added xml_node::hash_value() and xml_attribute::hash_value() functions for use in hash-based containers

      -
      7. -
    7. -

      Added internal_object() and additional constructor for both xml_node and xml_attribute for easier marshalling (useful for language bindings)

      -
      8. -
    8. -

      Added xml_document::document_element() function

      -
      9. -
    9. -

      Added xml_node::prepend_attribute, xml_node::prepend_child and xml_node::prepend_copy functions

      -
      10. -
    10. -

      Added xml_node::append_child, xml_node::prepend_child, xml_node::insert_child_before and xml_node::insert_child_after overloads for element nodes (with name instead of type)

      -
      11. -
    11. -

      Added xml_document::reset() function

      -
      12. -
    -
    -
    • -
  • -

    Performance improvements:

    -
    -
      -
    1. -

      xml_node::root() and xml_node::offset_debug() are now O(1) instead of O(logN)

      -
      2. -
    2. -

      Minor parsing optimizations

      -
      3. -
    3. -

      Minor memory optimization for strings in DOM tree (set_name/set_value)

      -
      4. -
    4. -

      Memory optimization for string memory reclaiming in DOM tree (set_name/set_value now reallocate the buffer if memory waste is too big)

      -
      5. -
    5. -

      XPath: optimized document order sorting

      -
      6. -
    6. -

      XPath: optimized child/attribute axis step

      -
      7. -
    7. -

      XPath: optimized number-to-string conversions in MSVC

      -
      8. -
    8. -

      XPath: optimized concat for many arguments

      -
      9. -
    9. -

      XPath: optimized evaluation allocation mechanism: constant and document strings are not heap-allocated

      -
      10. -
    10. -

      XPath: optimized evaluation allocation mechanism: all temporaries' allocations use fast stack-like allocator

      -
      11. -
    -
    -
    • -
  • -

    Compatibility:

    -
    -
      -
    1. -

      Removed wildcard functions (xml_node::child_w, xml_node::attribute_w, etc.)

      -
      2. -
    2. -

      Removed xml_node::all_elements_by_name

      -
      3. -
    3. -

      Removed xpath_type_t enumeration; use xpath_value_type instead

      -
      4. -
    4. -

      Removed format_write_bom_utf8 enumeration; use format_write_bom instead

      -
      5. -
    5. -

      Removed xml_document::precompute_document_order, xml_attribute::document_order and xml_node::document_order functions; document order sort optimization is now automatic

      -
      6. -
    6. -

      Removed xml_document::parse functions and transfer_ownership struct; use xml_document::load_buffer_inplace and xml_document::load_buffer_inplace_own instead

      -
      7. -
    7. -

      Removed as_utf16 function; use as_wide instead

      -
      8. -
    -
    -
    • -
-
-
-
-

v0.9 2010-07-01

-
-

Major release, featuring extended and improved Unicode support, miscellaneous performance improvements, bug fixes and more.

-
-
-
    -
  • -

    Major Unicode improvements:

    -
    -
      -
    1. -

      Introduced encoding support (automatic/manual encoding detection on load, manual encoding selection on save, conversion from/to UTF8, UTF16 LE/BE, UTF32 LE/BE)

      -
      2. -
    2. -

      Introduced wchar_t mode (you can set PUGIXML_WCHAR_MODE define to switch pugixml internal encoding from UTF8 to wchar_t; all functions are switched to their Unicode variants)

      -
      3. -
    3. -

      Load/save functions now support wide streams

      -
      4. -
    -
    -
    • -
  • -

    Bug fixes:

    -
    -
      -
    1. -

      Fixed document corruption on failed parsing bug

      -
      2. -
    2. -

      XPath string/number conversion improvements (increased precision, fixed crash for huge numbers)

      -
      3. -
    3. -

      Improved DOCTYPE parsing: now parser recognizes all well-formed DOCTYPE declarations

      -
      4. -
    4. -

      Fixed xml_attribute::as_uint() for large numbers (i.e. 232-1)

      -
      5. -
    5. -

      Fixed xml_node::first_element_by_path for path components that are prefixes of node names, but are not exactly equal to them.

      -
      6. -
    -
    -
    • -
  • -

    Specification changes:

    -
    -
      -
    1. -

      parse() API changed to load_buffer/load_buffer_inplace/load_buffer_inplace_own; load_buffer APIs do not require zero-terminated strings.

      -
      2. -
    2. -

      Renamed as_utf16 to as_wide

      -
      3. -
    3. -

      Changed xml_node::offset_debug return type and xml_parse_result::offset type to ptrdiff_t

      -
      4. -
    4. -

      Nodes/attributes with empty names are now printed as :anonymous

      -
      5. -
    -
    -
    • -
  • -

    Performance improvements:

    -
    -
      -
    1. -

      Optimized document parsing and saving

      -
      2. -
    2. -

      Changed internal memory management: internal allocator is used for both metadata and name/value data; allocated pages are deleted if all allocations from them are deleted

      -
      3. -
    3. -

      Optimized memory consumption: sizeof(xml_node_struct) reduced from 40 bytes to 32 bytes on x86

      -
      4. -
    4. -

      Optimized debug mode parsing/saving by order of magnitude

      -
      5. -
    -
    -
    • -
  • -

    Miscellaneous:

    -
    -
      -
    1. -

      All STL includes except <exception> in pugixml.hpp are replaced with forward declarations

      -
      2. -
    2. -

      xml_node::remove_child and xml_node::remove_attribute now return the operation result

      -
      3. -
    -
    -
    • -
  • -

    Compatibility:

    -
    -
      -
    1. -

      parse() and as_utf16 are left for compatibility (these functions are deprecated and will be removed in version 1.0)

      -
      2. -
    2. -

      Wildcard functions, document_order/precompute_document_order functions, all_elements_by_name function and format_write_bom_utf8 flag are deprecated and will be removed in version 1.0

      -
      3. -
    3. -

      xpath_type_t enumeration was renamed to xpath_value_type; xpath_type_t is deprecated and will be removed in version 1.0

      -
      4. -
    -
    -
    • -
-
-
-
-

v0.5 2009-11-08

-
-

Major bugfix release. Changes:

-
-
-
    -
  • -

    XPath bugfixes:

    -
    -
      -
    1. -

      Fixed translate(), lang() and concat() functions (infinite loops/crashes)

      -
      2. -
    2. -

      Fixed compilation of queries with empty literal strings ("")

      -
      3. -
    3. -

      Fixed axis tests: they never add empty nodes/attributes to the resulting node set now

      -
      4. -
    4. -

      Fixed string-value evaluation for node-set (the result excluded some text descendants)

      -
      5. -
    5. -

      Fixed self:: axis (it behaved like ancestor-or-self::)

      -
      6. -
    6. -

      Fixed following:: and preceding:: axes (they included descendent and ancestor nodes, respectively)

      -
      7. -
    7. -

      Minor fix for namespace-uri() function (namespace declaration scope includes the parent element of namespace declaration attribute)

      -
      8. -
    8. -

      Some incorrect queries are no longer parsed now (i.e. foo: *)

      -
      9. -
    9. -

      Fixed text()/etc. node test parsing bug (i.e. foo[text()] failed to compile)

      -
      10. -
    10. -

      Fixed root step (/) - it now selects empty node set if query is evaluated on empty node

      -
      11. -
    11. -

      Fixed string to number conversion ("123 " converted to NaN, "123 .456" converted to 123.456 - now the results are 123 and NaN, respectively)

      -
      12. -
    12. -

      Node set copying now preserves sorted type; leads to better performance on some queries

      -
      13. -
    -
    -
    • -
  • -

    Miscellaneous bugfixes:

    -
    -
      -
    1. -

      Fixed xml_node::offset_debug for PI nodes

      -
      2. -
    2. -

      Added empty attribute checks to xml_node::remove_attribute

      -
      3. -
    3. -

      Fixed node_pi and node_declaration copying

      -
      4. -
    4. -

      Const-correctness fixes

      -
      5. -
    -
    -
    • -
  • -

    Specification changes:

    -
    -
      -
    1. -

      xpath_node::select_nodes() and related functions now throw exception if expression return type is not node set (instead of assertion)

      -
      2. -
    2. -

      xml_node::traverse() now sets depth to -1 for both begin() and end() callbacks (was 0 at begin() and -1 at end())

      -
      3. -
    3. -

      In case of non-raw node printing a newline is output after PCDATA inside nodes if the PCDATA has siblings

      -
      4. -
    4. -

      UTF8 → wchar_t conversion now considers 5-byte UTF8-like sequences as invalid

      -
      5. -
    -
    -
    • -
  • -

    New features:

    -
    -
      -
    1. -

      Added xpath_node_set::operator[] for index-based iteration

      -
      2. -
    2. -

      Added xpath_query::return_type()

      -
      3. -
    3. -

      Added getter accessors for memory-management functions

      -
      4. -
    -
    -
    • -
-
-
-
-

v0.42 2009-09-17

-
-

Maintenance release. Changes:

-
-
-
    -
  • -

    Bug fixes:

    -
    -
      -
    1. -

      Fixed deallocation in case of custom allocation functions or if delete[] / free are incompatible

      -
      2. -
    2. -

      XPath parser fixed for incorrect queries (i.e. incorrect XPath queries should now always fail to compile)

      -
      3. -
    3. -

      Const-correctness fixes for find_child_by_attribute

      -
      4. -
    4. -

      Improved compatibility (miscellaneous warning fixes, fixed <cstring> include dependency for GCC)

      -
      5. -
    5. -

      Fixed iterator begin/end and print function to work correctly for empty nodes

      -
      6. -
    -
    -
    • -
  • -

    New features:

    -
    -
      -
    1. -

      Added PUGIXML_API/PUGIXML_CLASS/PUGIXML_FUNCTION configuration macros to control class/function attributes

      -
      2. -
    2. -

      Added xml_attribute::set_value overloads for different types

      -
      3. -
    -
    -
    • -
-
-
-
-

v0.41 2009-02-08

-
-

Maintenance release. Changes:

-
-
-
    -
  • -

    Bug fixes:

    -
    -
      -
    1. -

      Fixed bug with node printing (occasionally some content was not written to output stream)

      -
      2. -
    -
    -
    • -
-
-
-
-

v0.4 2009-01-18

-
-

Changes:

-
-
-
    -
  • -

    Bug fixes:

    -
    -
      -
    1. -

      Documentation fix in samples for parse() with manual lifetime control

      -
      2. -
    2. -

      Fixed document order sorting in XPath (it caused wrong order of nodes after xpath_node_set::sort and wrong results of some XPath queries)

      -
      3. -
    -
    -
    • -
  • -

    Node printing changes:

    -
    -
      -
    1. -

      Single quotes are no longer escaped when printing nodes

      -
      2. -
    2. -

      Symbols in second half of ASCII table are no longer escaped when printing nodes; because of this, format_utf8 flag is deleted as it’s no longer needed and format_write_bom is renamed to format_write_bom_utf8.

      -
      3. -
    3. -

      Reworked node printing - now it works via xml_writer interface; implementations for FILE* and std::ostream are available. As a side-effect, xml_document::save_file now works without STL.

      -
      4. -
    -
    -
    • -
  • -

    New features:

    -
    -
      -
    1. -

      Added unsigned integer support for attributes (xml_attribute::as_uint, xml_attribute::operator=)

      -
      2. -
    2. -

      Now document declaration (<?xml …​?>) is parsed as node with type node_declaration when parse_declaration flag is specified (access to encoding/version is performed as if they were attributes, i.e. doc.child("xml").attribute("version").as_float()); corresponding flags for node printing were also added

      -
      3. -
    3. -

      Added support for custom memory management (see set_memory_management_functions for details)

      -
      4. -
    4. -

      Implemented node/attribute copying (see xml_node::insert_copy_* and xml_node::append_copy for details)

      -
      5. -
    5. -

      Added find_child_by_attribute and find_child_by_attribute_w to simplify parsing code in some cases (i.e. COLLADA files)

      -
      6. -
    6. -

      Added file offset information querying for debugging purposes (now you’re able to determine exact location of any xml_node in parsed file, see xml_node::offset_debug for details)

      -
      7. -
    7. -

      Improved error handling for parsing - now load(), load_file() and parse() return xml_parse_result, which contains error code and last parsed offset; this does not break old interface as xml_parse_result can be implicitly casted to bool.

      -
      8. -
    -
    -
    • -
-
-
-
-

v0.34 2007-10-31

-
-

Maintenance release. Changes:

-
-
-
    -
  • -

    Bug fixes:

    -
    -
      -
    1. -

      Fixed bug with loading from text-mode iostreams

      -
      2. -
    2. -

      Fixed leak when transfer_ownership is true and parsing is failing

      -
      3. -
    3. -

      Fixed bug in saving (\r and \n are now escaped in attribute values)

      -
      4. -
    4. -

      Renamed free() to destroy() - some macro conflicts were reported

      -
      5. -
    -
    -
    • -
  • -

    New features:

    -
    -
      -
    1. -

      Improved compatibility (supported Digital Mars C++, MSVC 6, CodeWarrior 8, PGI C++, Comeau, supported PS3 and XBox360)

      -
      2. -
    2. -

      PUGIXML_NO_EXCEPTION flag for platforms without exception handling

      -
      3. -
    -
    -
    • -
-
-
-
-

v0.3 2007-02-21

-
-

Refactored, reworked and improved version. Changes:

-
-
-
    -
  • -

    Interface:

    -
    -
      -
    1. -

      Added XPath

      -
      2. -
    2. -

      Added tree modification functions

      -
      3. -
    3. -

      Added no STL compilation mode

      -
      4. -
    4. -

      Added saving document to file

      -
      5. -
    5. -

      Refactored parsing flags

      -
      6. -
    6. -

      Removed xml_parser class in favor of xml_document

      -
      7. -
    7. -

      Added transfer ownership parsing mode

      -
      8. -
    8. -

      Modified the way xml_tree_walker works

      -
      9. -
    9. -

      Iterators are now non-constant

      -
      10. -
    -
    -
    • -
  • -

    Implementation:

    -
    -
      -
    1. -

      Support of several compilers and platforms

      -
      2. -
    2. -

      Refactored and sped up parsing core

      -
      3. -
    3. -

      Improved standard compliancy

      -
      4. -
    4. -

      Added XPath implementation

      -
      5. -
    5. -

      Fixed several bugs

      -
      6. -
    -
    -
    • -
-
-
-
-

v0.2 2006-11-06

-
-

First public release. Changes:

-
-
-
    -
  • -

    Bug fixes:

    -
    -
      -
    1. -

      Fixed child_value() (for empty nodes)

      -
      2. -
    2. -

      Fixed xml_parser_impl warning at W4

      -
      3. -
    -
    -
    • -
  • -

    New features:

    -
    -
      -
    1. -

      Introduced child_value(name) and child_value_w(name)

      -
      2. -
    2. -

      parse_eol_pcdata and parse_eol_attribute flags + parse_minimal optimizations

      -
      3. -
    3. -

      Optimizations of strconv_t

      -
      4. -
    -
    -
    • -
-
-
-
-

v0.1 2006-07-15

-
-

First private release for testing purposes

-
-
-
-
-
-

10. API Reference

-
-
-

This is the reference for all macros, types, enumerations, classes and functions in pugixml. Each symbol is a link that leads to the relevant section of the manual.

-
-
-

10.1. Macros

-
-
-
#define PUGIXML_WCHAR_MODE
-#define PUGIXML_COMPACT
-#define PUGIXML_NO_XPATH
-#define PUGIXML_NO_STL
-#define PUGIXML_NO_EXCEPTIONS
-#define PUGIXML_API
-#define PUGIXML_CLASS
-#define PUGIXML_FUNCTION
-#define PUGIXML_MEMORY_PAGE_SIZE
-#define PUGIXML_MEMORY_OUTPUT_STACK
-#define PUGIXML_MEMORY_XPATH_PAGE_SIZE
-#define PUGIXML_HEADER_ONLY
-#define PUGIXML_HAS_LONG_LONG
-
-
-
-
-

10.2. Types

-
-
-
typedef configuration-defined-type char_t;
-typedef configuration-defined-type string_t;
-typedef void* (*allocation_function)(size_t size);
-typedef void (*deallocation_function)(void* ptr);
-
-
-
-
-

10.3. Enumerations

-
-
-
enum xml_node_type
-    node_null
-    node_document
-    node_element
-    node_pcdata
-    node_cdata
-    node_comment
-    node_pi
-    node_declaration
-    node_doctype
-
-enum xml_parse_status
-    status_ok
-    status_file_not_found
-    status_io_error
-    status_out_of_memory
-    status_internal_error
-    status_unrecognized_tag
-    status_bad_pi
-    status_bad_comment
-    status_bad_cdata
-    status_bad_doctype
-    status_bad_pcdata
-    status_bad_start_element
-    status_bad_attribute
-    status_bad_end_element
-    status_end_element_mismatch
-    status_append_invalid_root
-    status_no_document_element
-
-enum xml_encoding
-    encoding_auto
-    encoding_utf8
-    encoding_utf16_le
-    encoding_utf16_be
-    encoding_utf16
-    encoding_utf32_le
-    encoding_utf32_be
-    encoding_utf32
-    encoding_wchar
-    encoding_latin1
-
-enum xpath_value_type
-    xpath_type_none
-    xpath_type_node_set
-    xpath_type_number
-    xpath_type_string
-    xpath_type_boolean
-
-
-
-
-

10.4. Constants

-
-
-
// Formatting options bit flags:
-const unsigned int format_attribute_single_quote
-const unsigned int format_default
-const unsigned int format_indent
-const unsigned int format_indent_attributes
-const unsigned int format_no_declaration
-const unsigned int format_no_empty_element_tags
-const unsigned int format_no_escapes
-const unsigned int format_raw
-const unsigned int format_save_file_text
-const unsigned int format_skip_control_chars
-const unsigned int format_write_bom
-
-// Parsing options bit flags:
-const unsigned int parse_cdata
-const unsigned int parse_comments
-const unsigned int parse_declaration
-const unsigned int parse_default
-const unsigned int parse_doctype
-const unsigned int parse_eol
-const unsigned int parse_escapes
-const unsigned int parse_fragment
-const unsigned int parse_full
-const unsigned int parse_minimal
-const unsigned int parse_pi
-const unsigned int parse_trim_pcdata
-const unsigned int parse_ws_pcdata
-const unsigned int parse_ws_pcdata_single
-const unsigned int parse_embed_pcdata
-const unsigned int parse_merge_pcdata
-const unsigned int parse_wconv_attribute
-const unsigned int parse_wnorm_attribute
-
-
-
-
-

10.5. Classes

-
-
-
class xml_attribute
-    xml_attribute();
-
-    bool empty() const;
-    operator unspecified_bool_type() const;
-
-    bool operator==(const xml_attribute& r) const;
-    bool operator!=(const xml_attribute& r) const;
-    bool operator<(const xml_attribute& r) const;
-    bool operator>(const xml_attribute& r) const;
-    bool operator<=(const xml_attribute& r) const;
-    bool operator>=(const xml_attribute& r) const;
-
-    size_t hash_value() const;
-
-    xml_attribute next_attribute() const;
-    xml_attribute previous_attribute() const;
-
-    const char_t* name() const;
-    const char_t* value() const;
-
-    const char_t* as_string(const char_t* def = "") const;
-    int as_int(int def = 0) const;
-    unsigned int as_uint(unsigned int def = 0) const;
-    double as_double(double def = 0) const;
-    float as_float(float def = 0) const;
-    bool as_bool(bool def = false) const;
-    long long as_llong(long long def = 0) const;
-    unsigned long long as_ullong(unsigned long long def = 0) const;
-
-    bool set_name(const char_t* rhs);
-    bool set_name(const char_t* rhs, size_t size);
-    bool set_value(const char_t* rhs);
-    bool set_value(const char_t* rhs, size_t size);
-    bool set_value(int rhs);
-    bool set_value(unsigned int rhs);
-    bool set_value(long rhs);
-    bool set_value(unsigned long rhs);
-    bool set_value(double rhs);
-    bool set_value(float rhs);
-    bool set_value(bool rhs);
-    bool set_value(long long rhs);
-    bool set_value(unsigned long long rhs);
-
-    xml_attribute& operator=(const char_t* rhs);
-    xml_attribute& operator=(int rhs);
-    xml_attribute& operator=(unsigned int rhs);
-    xml_attribute& operator=(long rhs);
-    xml_attribute& operator=(unsigned long rhs);
-    xml_attribute& operator=(double rhs);
-    xml_attribute& operator=(float rhs);
-    xml_attribute& operator=(bool rhs);
-    xml_attribute& operator=(long long rhs);
-    xml_attribute& operator=(unsnigned long long rhs);
-
-class xml_node
-    xml_node();
-
-    bool empty() const;
-    operator unspecified_bool_type() const;
-
-    bool operator==(const xml_node& r) const;
-    bool operator!=(const xml_node& r) const;
-    bool operator<(const xml_node& r) const;
-    bool operator>(const xml_node& r) const;
-    bool operator<=(const xml_node& r) const;
-    bool operator>=(const xml_node& r) const;
-
-    size_t hash_value() const;
-
-    xml_node_type type() const;
-
-    const char_t* name() const;
-    const char_t* value() const;
-
-    xml_node parent() const;
-    xml_node first_child() const;
-    xml_node last_child() const;
-    xml_node next_sibling() const;
-    xml_node previous_sibling() const;
-
-    xml_attribute first_attribute() const;
-    xml_attribute last_attribute() const;
-
-    implementation-defined-type children() const;
-    implementation-defined-type children(const char_t* name) const;
-    implementation-defined-type attributes() const;
-
-    xml_node child(const char_t* name) const;
-    xml_attribute attribute(const char_t* name) const;
-    xml_node next_sibling(const char_t* name) const;
-    xml_node previous_sibling(const char_t* name) const;
-
-    xml_attribute attribute(const char_t* name, xml_attribute& hint) const;
-
-    xml_node find_child_by_attribute(const char_t* name, const char_t* attr_name, const char_t* attr_value) const;
-    xml_node find_child_by_attribute(const char_t* attr_name, const char_t* attr_value) const;
-
-    const char_t* child_value() const;
-    const char_t* child_value(const char_t* name) const;
-    xml_text text() const;
-
-    typedef xml_node_iterator iterator;
-    iterator begin() const;
-    iterator end() const;
-
-    typedef xml_attribute_iterator attribute_iterator;
-    attribute_iterator attributes_begin() const;
-    attribute_iterator attributes_end() const;
-
-    bool traverse(xml_tree_walker& walker);
-
-    template <typename Predicate> xml_attribute find_attribute(Predicate pred) const;
-    template <typename Predicate> xml_node find_child(Predicate pred) const;
-    template <typename Predicate> xml_node find_node(Predicate pred) const;
-
-    string_t path(char_t delimiter = '/') const;
-    xml_node xml_node::first_element_by_path(const char_t* path, char_t delimiter = '/') const;
-    xml_node root() const;
-    ptrdiff_t offset_debug() const;
-
-    bool set_name(const char_t* rhs);
-    bool set_name(const char_t* rhs, size_t size);
-    bool set_value(const char_t* rhs);
-    bool set_value(const char_t* rhs, size_t size);
-
-    xml_attribute append_attribute(const char_t* name);
-    xml_attribute prepend_attribute(const char_t* name);
-    xml_attribute insert_attribute_after(const char_t* name, const xml_attribute& attr);
-    xml_attribute insert_attribute_before(const char_t* name, const xml_attribute& attr);
-
-    xml_node append_child(xml_node_type type = node_element);
-    xml_node prepend_child(xml_node_type type = node_element);
-    xml_node insert_child_after(xml_node_type type, const xml_node& node);
-    xml_node insert_child_before(xml_node_type type, const xml_node& node);
-
-    xml_node append_child(const char_t* name);
-    xml_node prepend_child(const char_t* name);
-    xml_node insert_child_after(const char_t* name, const xml_node& node);
-    xml_node insert_child_before(const char_t* name, const xml_node& node);
-
-    xml_attribute append_copy(const xml_attribute& proto);
-    xml_attribute prepend_copy(const xml_attribute& proto);
-    xml_attribute insert_copy_after(const xml_attribute& proto, const xml_attribute& attr);
-    xml_attribute insert_copy_before(const xml_attribute& proto, const xml_attribute& attr);
-
-    xml_node append_copy(const xml_node& proto);
-    xml_node prepend_copy(const xml_node& proto);
-    xml_node insert_copy_after(const xml_node& proto, const xml_node& node);
-    xml_node insert_copy_before(const xml_node& proto, const xml_node& node);
-
-    xml_node append_move(const xml_node& moved);
-    xml_node prepend_move(const xml_node& moved);
-    xml_node insert_move_after(const xml_node& moved, const xml_node& node);
-    xml_node insert_move_before(const xml_node& moved, const xml_node& node);
-
-    bool remove_attribute(const xml_attribute& a);
-    bool remove_attribute(const char_t* name);
-    bool remove_attributes();
-    bool remove_child(const xml_node& n);
-    bool remove_child(const char_t* name);
-    bool remove_children();
-
-    xml_parse_result append_buffer(const void* contents, size_t size, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);
-
-    void print(xml_writer& writer, const char_t* indent = "\t", unsigned int flags = format_default, xml_encoding encoding = encoding_auto, unsigned int depth = 0) const;
-    void print(std::ostream& os, const char_t* indent = "\t", unsigned int flags = format_default, xml_encoding encoding = encoding_auto, unsigned int depth = 0) const;
-    void print(std::wostream& os, const char_t* indent = "\t", unsigned int flags = format_default, unsigned int depth = 0) const;
-
-    xpath_node select_node(const char_t* query, xpath_variable_set* variables = 0) const;
-    xpath_node select_node(const xpath_query& query) const;
-    xpath_node_set select_nodes(const char_t* query, xpath_variable_set* variables = 0) const;
-    xpath_node_set select_nodes(const xpath_query& query) const;
-
-class xml_document
-    xml_document();
-    ~xml_document();
-
-    void reset();
-    void reset(const xml_document& proto);
-
-    xml_parse_result load(std::istream& stream, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);
-    xml_parse_result load(std::wistream& stream, unsigned int options = parse_default);
-
-    xml_parse_result load_string(const char_t* contents, unsigned int options = parse_default);
-
-    xml_parse_result load_file(const char* path, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);
-    xml_parse_result load_file(const wchar_t* path, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);
-
-    xml_parse_result load_buffer(const void* contents, size_t size, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);
-    xml_parse_result load_buffer_inplace(void* contents, size_t size, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);
-    xml_parse_result load_buffer_inplace_own(void* contents, size_t size, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);
-
-    bool save_file(const char* path, const char_t* indent = "\t", unsigned int flags = format_default, xml_encoding encoding = encoding_auto) const;
-    bool save_file(const wchar_t* path, const char_t* indent = "\t", unsigned int flags = format_default, xml_encoding encoding = encoding_auto) const;
-
-    void save(std::ostream& stream, const char_t* indent = "\t", unsigned int flags = format_default, xml_encoding encoding = encoding_auto) const;
-    void save(std::wostream& stream, const char_t* indent = "\t", unsigned int flags = format_default) const;
-
-    void save(xml_writer& writer, const char_t* indent = "\t", unsigned int flags = format_default, xml_encoding encoding = encoding_auto) const;
-
-    xml_node document_element() const;
-
-struct xml_parse_result
-    xml_parse_status status;
-    ptrdiff_t offset;
-    xml_encoding encoding;
-
-    operator bool() const;
-    const char* description() const;
-
-class xml_node_iterator
-class xml_attribute_iterator
-
-class xml_tree_walker
-    virtual bool begin(xml_node& node);
-    virtual bool for_each(xml_node& node) = 0;
-    virtual bool end(xml_node& node);
-
-    int depth() const;
-
-class xml_text
-    bool empty() const;
-    operator xml_text::unspecified_bool_type() const;
-
-    const char_t* xml_text::get() const;
-
-    const char_t* as_string(const char_t* def = "") const;
-    int as_int(int def = 0) const;
-    unsigned int as_uint(unsigned int def = 0) const;
-    double as_double(double def = 0) const;
-    float as_float(float def = 0) const;
-    bool as_bool(bool def = false) const;
-    long long as_llong(long long def = 0) const;
-    unsigned long long as_ullong(unsigned long long def = 0) const;
-
-    bool set(const char_t* rhs);
-    bool set(const char_t* rhs, size_t size);
-
-    bool set(int rhs);
-    bool set(unsigned int rhs);
-    bool set(long rhs);
-    bool set(unsigned long rhs);
-    bool set(double rhs);
-    bool set(float rhs);
-    bool set(bool rhs);
-    bool set(long long rhs);
-    bool set(unsigned long long rhs);
-
-    xml_text& operator=(const char_t* rhs);
-    xml_text& operator=(int rhs);
-    xml_text& operator=(unsigned int rhs);
-    xml_text& operator=(long rhs);
-    xml_text& operator=(unsigned long rhs);
-    xml_text& operator=(double rhs);
-    xml_text& operator=(float rhs);
-    xml_text& operator=(bool rhs);
-    xml_text& operator=(long long rhs);
-    xml_text& operator=(unsigned long long rhs);
-
-    xml_node data() const;
-
-class xml_writer
-    virtual void write(const void* data, size_t size) = 0;
-
-class xml_writer_file: public xml_writer
-    xml_writer_file(void* file);
-
-class xml_writer_stream: public xml_writer
-    xml_writer_stream(std::ostream& stream);
-    xml_writer_stream(std::wostream& stream);
-
-struct xpath_parse_result
-    const char* error;
-    ptrdiff_t offset;
-
-    operator bool() const;
-    const char* description() const;
-
-class xpath_query
-    explicit xpath_query(const char_t* query, xpath_variable_set* variables = 0);
-
-    bool evaluate_boolean(const xpath_node& n) const;
-    double evaluate_number(const xpath_node& n) const;
-    string_t evaluate_string(const xpath_node& n) const;
-    size_t evaluate_string(char_t* buffer, size_t capacity, const xpath_node& n) const;
-    xpath_node_set evaluate_node_set(const xpath_node& n) const;
-    xpath_node evaluate_node(const xpath_node& n) const;
-
-    xpath_value_type return_type() const;
-
-    const xpath_parse_result& result() const;
-    operator unspecified_bool_type() const;
-
-class xpath_exception: public std::exception
-    virtual const char* what() const throw();
-
-    const xpath_parse_result& result() const;
-
-class xpath_node
-    xpath_node();
-    xpath_node(const xml_node& node);
-    xpath_node(const xml_attribute& attribute, const xml_node& parent);
-
-    xml_node node() const;
-    xml_attribute attribute() const;
-    xml_node parent() const;
-
-    operator unspecified_bool_type() const;
-    bool operator==(const xpath_node& n) const;
-    bool operator!=(const xpath_node& n) const;
-
-class xpath_node_set
-    xpath_node_set();
-    xpath_node_set(const_iterator begin, const_iterator end, type_t type = type_unsorted);
-
-    typedef const xpath_node* const_iterator;
-    const_iterator begin() const;
-    const_iterator end() const;
-
-    const xpath_node& operator[](size_t index) const;
-    size_t size() const;
-    bool empty() const;
-
-    xpath_node first() const;
-
-    enum type_t {type_unsorted, type_sorted, type_sorted_reverse};
-    type_t type() const;
-    void sort(bool reverse = false);
-
-class xpath_variable
-    const char_t* name() const;
-    xpath_value_type type() const;
-
-    bool get_boolean() const;
-    double get_number() const;
-    const char_t* get_string() const;
-    const xpath_node_set& get_node_set() const;
-
-    bool set(bool value);
-    bool set(double value);
-    bool set(const char_t* value);
-    bool set(const xpath_node_set& value);
-
-class xpath_variable_set
-    xpath_variable* add(const char_t* name, xpath_value_type type);
-
-    bool set(const char_t* name, bool value);
-    bool set(const char_t* name, double value);
-    bool set(const char_t* name, const char_t* value);
-    bool set(const char_t* name, const xpath_node_set& value);
-
-    xpath_variable* get(const char_t* name);
-    const xpath_variable* get(const char_t* name) const;
-
-
-
-
-

10.6. Functions

-
-
-
std::string as_utf8(const wchar_t* str);
-std::string as_utf8(const std::wstring& str);
-std::wstring as_wide(const char* str);
-std::wstring as_wide(const std::string& str);
-void set_memory_management_functions(allocation_function allocate, deallocation_function deallocate);
-allocation_function get_memory_allocation_function();
-deallocation_function get_memory_deallocation_function();
-
-
-
-
-
-
-
-
-
-1. All trademarks used are properties of their respective owners. -
-
- - - \ No newline at end of file diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/quickstart.html --- a/dep/pugixml/docs/quickstart.html Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,1108 +0,0 @@ - - - - - - - - -pugixml 1.14 quick start guide - - - - - - -
-
-

Introduction

-
-
-

pugixml is a light-weight C++ XML processing library. It consists of a DOM-like interface with rich traversal/modification capabilities, an extremely fast XML parser which constructs the DOM tree from an XML file/buffer, and an XPath 1.0 implementation for complex data-driven tree queries. Full Unicode support is also available, with two Unicode interface variants and conversions between different Unicode encodings (which happen automatically during parsing/saving). The library is extremely portable and easy to integrate and use. pugixml is developed and maintained since 2006 and has many users. All code is distributed under the MIT license, making it completely free to use in both open-source and proprietary applications.

-
-
-

pugixml enables very fast, convenient and memory-efficient XML document processing. However, since pugixml has a DOM parser, it can’t process XML documents that do not fit in memory; also the parser is a non-validating one, so if you need DTD/Schema validation, the library is not for you.

-
-
-

This is the quick start guide for pugixml, which purpose is to enable you to start using the library quickly. Many important library features are either not described at all or only mentioned briefly; for more complete information you should read the complete manual.

-
-
- - - - - -
-
Note
-		 -No documentation is perfect; neither is this one. If you find errors or omissions, please don’t hesitate to submit an issue or open a pull request with a fix. -
-
-
-
-
-

Installation

-
-
-

You can download the latest source distribution as an archive:

-
-
-

pugixml-1.14.zip (Windows line endings) -/ -pugixml-1.14.tar.gz (Unix line endings)

-
-
-

The distribution contains library source, documentation (the guide you’re reading now and the manual) and some code examples. After downloading the distribution, install pugixml by extracting all files from the compressed archive.

-
-
-

The complete pugixml source consists of three files - one source file, pugixml.cpp, and two header files, pugixml.hpp and pugiconfig.hpp. pugixml.hpp is the primary header which you need to include in order to use pugixml classes/functions. The rest of this guide assumes that pugixml.hpp is either in the current directory or in one of include directories of your projects, so that #include "pugixml.hpp" can find the header; however you can also use relative path (i.e. #include "../libs/pugixml/src/pugixml.hpp") or include directory-relative path (i.e. #include <xml/thirdparty/pugixml/src/pugixml.hpp>).

-
-
-

The easiest way to build pugixml is to compile the source file, pugixml.cpp, along with the existing library/executable. This process depends on the method of building your application; for example, if you’re using Microsoft Visual Studio [1], Apple Xcode, Code::Blocks or any other IDE, just add pugixml.cpp to one of your projects. There are other building methods available, including building pugixml as a standalone static/shared library; read the manual for further information.

-
-
-
-
-

Document object model

-
-
-

pugixml stores XML data in DOM-like way: the entire XML document (both document structure and element data) is stored in memory as a tree. The tree can be loaded from character stream (file, string, C++ I/O stream), then traversed via special API or XPath expressions. The whole tree is mutable: both node structure and node/attribute data can be changed at any time. Finally, the result of document transformations can be saved to a character stream (file, C++ I/O stream or custom transport).

-
-
-

The root of the tree is the document itself, which corresponds to C++ type xml_document. Document has one or more child nodes, which correspond to C++ type xml_node. Nodes have different types; depending on a type, a node can have a collection of child nodes, a collection of attributes, which correspond to C++ type xml_attribute, and some additional data (i.e. name).

-
-
-

The most common node types are:

-
-
-
    -
  • -

    Document node (node_document) - this is the root of the tree, which consists of several child nodes. This node corresponds to xml_document class; note that xml_document is a sub-class of xml_node, so the entire node interface is also available.

    -
    • -
  • -

    Element/tag node (node_element) - this is the most common type of node, which represents XML elements. Element nodes have a name, a collection of attributes and a collection of child nodes (both of which may be empty). The attribute is a simple name/value pair.

    -
    • -
  • -

    Plain character data nodes (node_pcdata) represent plain text in XML. PCDATA nodes have a value, but do not have name or children/attributes. Note that plain character data is not a part of the element node but instead has its own node; for example, an element node can have several child PCDATA nodes.

    -
    • -
-
-
-

Despite the fact that there are several node types, there are only three C++ types representing the tree (xml_document, xml_node, xml_attribute); some operations on xml_node are only valid for certain node types. They are described below.

-
-
- - - - - -
-
Note
-		 -All pugixml classes and functions are located in pugi namespace; you have to either use explicit name qualification (i.e. pugi::xml_node), or to gain access to relevant symbols via using directive (i.e. using pugi::xml_node; or using namespace pugi;). -
-
-
-

xml_document is the owner of the entire document structure; destroying the document destroys the whole tree. The interface of xml_document consists of loading functions, saving functions and the entire interface of xml_node, which allows for document inspection and/or modification. Note that while xml_document is a sub-class of xml_node, xml_node is not a polymorphic type; the inheritance is present only to simplify usage.

-
-
-

xml_node is the handle to document node; it can point to any node in the document, including document itself. There is a common interface for nodes of all types. Note that xml_node is only a handle to the actual node, not the node itself - you can have several xml_node handles pointing to the same underlying object. Destroying xml_node handle does not destroy the node and does not remove it from the tree.

-
-
-

There is a special value of xml_node type, known as null node or empty node. It does not correspond to any node in any document, and thus resembles null pointer. However, all operations are defined on empty nodes; generally the operations don’t do anything and return empty nodes/attributes or empty strings as their result. This is useful for chaining calls; i.e. you can get the grandparent of a node like so: node.parent().parent(); if a node is a null node or it does not have a parent, the first parent() call returns null node; the second parent() call then also returns null node, so you don’t have to check for errors twice. You can test if a handle is null via implicit boolean cast: if (node) { …​ } or if (!node) { …​ }.

-
-
-

xml_attribute is the handle to an XML attribute; it has the same semantics as xml_node, i.e. there can be several xml_attribute handles pointing to the same underlying object and there is a special null attribute value, which propagates to function results.

-
-
-

There are two choices of interface and internal representation when configuring pugixml: you can either choose the UTF-8 (also called char) interface or UTF-16/32 (also called wchar_t) one. The choice is controlled via PUGIXML_WCHAR_MODE define; you can set it via pugiconfig.hpp or via preprocessor options. All tree functions that work with strings work with either C-style null terminated strings or STL strings of the selected character type. Read the manual for additional information on Unicode interface.

-
-
-
-
-

Loading document

-
-
-

pugixml provides several functions for loading XML data from various places - files, C++ iostreams, memory buffers. All functions use an extremely fast non-validating parser. This parser is not fully W3C conformant - it can load any valid XML document, but does not perform some well-formedness checks. While considerable effort is made to reject invalid XML documents, some validation is not performed because of performance reasons. XML data is always converted to internal character format before parsing. pugixml supports all popular Unicode encodings (UTF-8, UTF-16 (big and little endian), UTF-32 (big and little endian); UCS-2 is naturally supported since it’s a strict subset of UTF-16) and handles all encoding conversions automatically.

-
-
-

The most common source of XML data is files; pugixml provides a separate function for loading XML document from file. This function accepts file path as its first argument, and also two optional arguments, which specify parsing options and input data encoding, which are described in the manual.

-
-
-

This is an example of loading XML document from file (samples/load_file.cpp):

-
-
-
-
pugi::xml_document doc;
-
-pugi::xml_parse_result result = doc.load_file("tree.xml");
-
-std::cout << "Load result: " << result.description() << ", mesh name: " << doc.child("mesh").attribute("name").value() << std::endl;
-
-
-
-

load_file, as well as other loading functions, destroys the existing document tree and then tries to load the new tree from the specified file. The result of the operation is returned in an xml_parse_result object; this object contains the operation status, and the related information (i.e. last successfully parsed position in the input file, if parsing fails).

-
-
-

Parsing result object can be implicitly converted to bool; if you do not want to handle parsing errors thoroughly, you can just check the return value of load functions as if it was a bool: if (doc.load_file("file.xml")) { …​ } else { …​ }. Otherwise you can use the status member to get parsing status, or the description() member function to get the status in a string form.

-
-
-

This is an example of handling loading errors (samples/load_error_handling.cpp):

-
-
-
-
pugi::xml_document doc;
-pugi::xml_parse_result result = doc.load_string(source);
-
-if (result)
-{
-    std::cout << "XML [" << source << "] parsed without errors, attr value: [" << doc.child("node").attribute("attr").value() << "]\n\n";
-}
-else
-{
-    std::cout << "XML [" << source << "] parsed with errors, attr value: [" << doc.child("node").attribute("attr").value() << "]\n";
-    std::cout << "Error description: " << result.description() << "\n";
-    std::cout << "Error offset: " << result.offset << " (error at [..." << (source + result.offset) << "]\n\n";
-}
-
-
-
-

Sometimes XML data should be loaded from some other source than file, i.e. HTTP URL; also you may want to load XML data from file using non-standard functions, i.e. to use your virtual file system facilities or to load XML from gzip-compressed files. These scenarios either require loading document from memory, in which case you should prepare a contiguous memory block with all XML data and to pass it to one of buffer loading functions, or loading document from C++ IOstream, in which case you should provide an object which implements std::istream or std::wistream interface.

-
-
-

There are different functions for loading document from memory; they treat the passed buffer as either an immutable one (load_buffer), a mutable buffer which is owned by the caller (load_buffer_inplace), or a mutable buffer which ownership belongs to pugixml (load_buffer_inplace_own). There is also a simple helper function, xml_document::load, for cases when you want to load the XML document from null-terminated character string.

-
-
-

This is an example of loading XML document from memory using one of these functions (samples/load_memory.cpp); read the sample code for more examples:

-
-
-
-
const char source[] = "<mesh name='sphere'><bounds>0 0 1 1</bounds></mesh>";
-size_t size = sizeof(source);
-
-
-
-
-
// You can use load_buffer_inplace to load document from mutable memory block; the block's lifetime must exceed that of document
-char* buffer = new char[size];
-memcpy(buffer, source, size);
-
-// The block can be allocated by any method; the block is modified during parsing
-pugi::xml_parse_result result = doc.load_buffer_inplace(buffer, size);
-
-// You have to destroy the block yourself after the document is no longer used
-delete[] buffer;
-
-
-
-

This is a simple example of loading XML document from file using streams (samples/load_stream.cpp); read the sample code for more complex examples involving wide streams and locales:

-
-
-
-
std::ifstream stream("weekly-utf-8.xml");
-pugi::xml_parse_result result = doc.load(stream);
-
-
-
-
-
-

Accessing document data

-
-
-

pugixml features an extensive interface for getting various types of data from the document and for traversing the document. You can use various accessors to get node/attribute data, you can traverse the child node/attribute lists via accessors or iterators, you can do depth-first traversals with xml_tree_walker objects, and you can use XPath for complex data-driven queries.

-
-
-

You can get node or attribute name via name() accessor, and value via value() accessor. Note that both functions never return null pointers - they either return a string with the relevant content, or an empty string if name/value is absent or if the handle is null. Also there are two notable things for reading values:

-
-
-
    -
  • -

    It is common to store data as text contents of some node - i.e. <node><description>This is a node</description></node>. In this case, <description> node does not have a value, but instead has a child of type node_pcdata with value "This is a node". pugixml provides child_value() and text() helper functions to parse such data.

    -
    • -
  • -

    In many cases attribute values have types that are not strings - i.e. an attribute may always contain values that should be treated as integers, despite the fact that they are represented as strings in XML. pugixml provides several accessors that convert attribute value to some other type.

    -
    • -
-
-
-

This is an example of using these functions (samples/traverse_base.cpp):

-
-
-
-
for (pugi::xml_node tool = tools.child("Tool"); tool; tool = tool.next_sibling("Tool"))
-{
-    std::cout << "Tool " << tool.attribute("Filename").value();
-    std::cout << ": AllowRemote " << tool.attribute("AllowRemote").as_bool();
-    std::cout << ", Timeout " << tool.attribute("Timeout").as_int();
-    std::cout << ", Description '" << tool.child_value("Description") << "'\n";
-}
-
-
-
-

Since a lot of document traversal consists of finding the node/attribute with the correct name, there are special functions for that purpose. For example, child("Tool") returns the first node which has the name "Tool", or null handle if there is no such node. This is an example of using such functions (samples/traverse_base.cpp):

-
-
-
-
std::cout << "Tool for *.dae generation: " << tools.find_child_by_attribute("Tool", "OutputFileMasks", "*.dae").attribute("Filename").value() << "\n";
-
-for (pugi::xml_node tool = tools.child("Tool"); tool; tool = tool.next_sibling("Tool"))
-{
-    std::cout << "Tool " << tool.attribute("Filename").value() << "\n";
-}
-
-
-
-

Child node lists and attribute lists are simply double-linked lists; while you can use previous_sibling/next_sibling and other such functions for iteration, pugixml additionally provides node and attribute iterators, so that you can treat nodes as containers of other nodes or attributes. All iterators are bidirectional and support all usual iterator operations. The iterators are invalidated if the node/attribute objects they’re pointing to are removed from the tree; adding nodes/attributes does not invalidate any iterators.

-
-
-

Here is an example of using iterators for document traversal (samples/traverse_iter.cpp):

-
-
-
-
for (pugi::xml_node_iterator it = tools.begin(); it != tools.end(); ++it)
-{
-    std::cout << "Tool:";
-
-    for (pugi::xml_attribute_iterator ait = it->attributes_begin(); ait != it->attributes_end(); ++ait)
-    {
-        std::cout << " " << ait->name() << "=" << ait->value();
-    }
-
-    std::cout << std::endl;
-}
-
-
-
-

If your C++ compiler supports range-based for-loop (this is a C++11 feature, at the time of writing it’s supported by Microsoft Visual Studio 11 Beta, GCC 4.6 and Clang 3.0), you can use it to enumerate nodes/attributes. Additional helpers are provided to support this; note that they are also compatible with Boost Foreach, and possibly other pre-C++11 foreach facilities.

-
-
-

Here is an example of using C++11 range-based for loop for document traversal (samples/traverse_rangefor.cpp):

-
-
-
-
for (pugi::xml_node tool: tools.children("Tool"))
-{
-    std::cout << "Tool:";
-
-    for (pugi::xml_attribute attr: tool.attributes())
-    {
-        std::cout << " " << attr.name() << "=" << attr.value();
-    }
-
-    for (pugi::xml_node child: tool.children())
-    {
-        std::cout << ", child " << child.name();
-    }
-
-    std::cout << std::endl;
-}
-
-
-
-

The methods described above allow traversal of immediate children of some node; if you want to do a deep tree traversal, you’ll have to do it via a recursive function or some equivalent method. However, pugixml provides a helper for depth-first traversal of a subtree. In order to use it, you have to implement xml_tree_walker interface and to call traverse function.

-
-
-

This is an example of traversing tree hierarchy with xml_tree_walker (samples/traverse_walker.cpp):

-
-
-
-
struct simple_walker: pugi::xml_tree_walker
-{
-    virtual bool for_each(pugi::xml_node& node)
-    {
-        for (int i = 0; i < depth(); ++i) std::cout << "  "; // indentation
-
-        std::cout << node_types[node.type()] << ": name='" << node.name() << "', value='" << node.value() << "'\n";
-
-        return true; // continue traversal
-    }
-};
-
-
-
-
-
simple_walker walker;
-doc.traverse(walker);
-
-
-
-

Finally, for complex queries often a higher-level DSL is needed. pugixml provides an implementation of XPath 1.0 language for such queries. The complete description of XPath usage can be found in the manual, but here are some examples:

-
-
-
-
pugi::xpath_node_set tools = doc.select_nodes("/Profile/Tools/Tool[@AllowRemote='true' and @DeriveCaptionFrom='lastparam']");
-
-std::cout << "Tools:\n";
-
-for (pugi::xpath_node_set::const_iterator it = tools.begin(); it != tools.end(); ++it)
-{
-    pugi::xpath_node node = *it;
-    std::cout << node.node().attribute("Filename").value() << "\n";
-}
-
-pugi::xpath_node build_tool = doc.select_node("//Tool[contains(Description, 'build system')]");
-
-if (build_tool)
-    std::cout << "Build tool: " << build_tool.node().attribute("Filename").value() << "\n";
-
-
-
- - - - - -
-
Caution
-		 -XPath functions throw xpath_exception objects on error; the sample above does not catch these exceptions. -
-
-
-
-
-

Modifying document data

-
-
-

The document in pugixml is fully mutable: you can completely change the document structure and modify the data of nodes/attributes. All functions take care of memory management and structural integrity themselves, so they always result in structurally valid tree - however, it is possible to create an invalid XML tree (for example, by adding two attributes with the same name or by setting attribute/node name to empty/invalid string). Tree modification is optimized for performance and for memory consumption, so if you have enough memory you can create documents from scratch with pugixml and later save them to file/stream instead of relying on error-prone manual text writing and without too much overhead.

-
-
-

All member functions that change node/attribute data or structure are non-constant and thus can not be called on constant handles. However, you can easily convert constant handle to non-constant one by simple assignment: void foo(const pugi::xml_node& n) { pugi::xml_node nc = n; }, so const-correctness here mainly provides additional documentation.

-
-
-

As discussed before, nodes can have name and value, both of which are strings. Depending on node type, name or value may be absent. You can use set_name and set_value member functions to set them. Similar functions are available for attributes; however, the set_value function is overloaded for some other types except strings, like floating-point numbers. Also, attribute value can be set using an assignment operator. This is an example of setting node/attribute name and value (samples/modify_base.cpp):

-
-
-
-
pugi::xml_node node = doc.child("node");
-
-// change node name
-std::cout << node.set_name("notnode");
-std::cout << ", new node name: " << node.name() << std::endl;
-
-// change comment text
-std::cout << doc.last_child().set_value("useless comment");
-std::cout << ", new comment text: " << doc.last_child().value() << std::endl;
-
-// we can't change value of the element or name of the comment
-std::cout << node.set_value("1") << ", " << doc.last_child().set_name("2") << std::endl;
-
-
-
-
-
pugi::xml_attribute attr = node.attribute("id");
-
-// change attribute name/value
-std::cout << attr.set_name("key") << ", " << attr.set_value("345");
-std::cout << ", new attribute: " << attr.name() << "=" << attr.value() << std::endl;
-
-// we can use numbers or booleans
-attr.set_value(1.234);
-std::cout << "new attribute value: " << attr.value() << std::endl;
-
-// we can also use assignment operators for more concise code
-attr = true;
-std::cout << "final attribute value: " << attr.value() << std::endl;
-
-
-
-

Nodes and attributes do not exist without a document tree, so you can’t create them without adding them to some document. A node or attribute can be created at the end of node/attribute list or before/after some other node. All insertion functions return the handle to newly created object on success, and null handle on failure. Even if the operation fails (for example, if you’re trying to add a child node to PCDATA node), the document remains in consistent state, but the requested node/attribute is not added.

-
-
- - - - - -
-
Caution
-		 -attribute() and child() functions do not add attributes or nodes to the tree, so code like node.attribute("id") = 123; will not do anything if node does not have an attribute with name "id". Make sure you’re operating with existing attributes/nodes by adding them if necessary. -
-
-
-

This is an example of adding new attributes/nodes to the document (samples/modify_add.cpp):

-
-
-
-
// add node with some name
-pugi::xml_node node = doc.append_child("node");
-
-// add description node with text child
-pugi::xml_node descr = node.append_child("description");
-descr.append_child(pugi::node_pcdata).set_value("Simple node");
-
-// add param node before the description
-pugi::xml_node param = node.insert_child_before("param", descr);
-
-// add attributes to param node
-param.append_attribute("name") = "version";
-param.append_attribute("value") = 1.1;
-param.insert_attribute_after("type", param.attribute("name")) = "float";
-
-
-
-

If you do not want your document to contain some node or attribute, you can remove it with remove_attribute and remove_child functions. Removing the attribute or node invalidates all handles to the same underlying object, and also invalidates all iterators pointing to the same object. Removing node also invalidates all past-the-end iterators to its attribute or child node list. Be careful to ensure that all such handles and iterators either do not exist or are not used after the attribute/node is removed.

-
-
-

This is an example of removing attributes/nodes from the document (samples/modify_remove.cpp):

-
-
-
-
// remove description node with the whole subtree
-pugi::xml_node node = doc.child("node");
-node.remove_child("description");
-
-// remove id attribute
-pugi::xml_node param = node.child("param");
-param.remove_attribute("value");
-
-// we can also remove nodes/attributes by handles
-pugi::xml_attribute id = param.attribute("name");
-param.remove_attribute(id);
-
-
-
-
-
-

Saving document

-
-
-

Often after creating a new document or loading the existing one and processing it, it is necessary to save the result back to file. Also it is occasionally useful to output the whole document or a subtree to some stream; use cases include debug printing, serialization via network or other text-oriented medium, etc. pugixml provides several functions to output any subtree of the document to a file, stream or another generic transport interface; these functions allow to customize the output format, and also perform necessary encoding conversions.

-
-
-

Before writing to the destination the node/attribute data is properly formatted according to the node type; all special XML symbols, such as < and &, are properly escaped. In order to guard against forgotten node/attribute names, empty node/attribute names are printed as ":anonymous". For well-formed output, make sure all node and attribute names are set to meaningful values.

-
-
-

If you want to save the whole document to a file, you can use the save_file function, which returns true on success. This is a simple example of saving XML document to file (samples/save_file.cpp):

-
-
-
-
// save document to file
-std::cout << "Saving result: " << doc.save_file("save_file_output.xml") << std::endl;
-
-
-
-

To enhance interoperability pugixml provides functions for saving document to any object which implements C++ std::ostream interface. This allows you to save documents to any standard C++ stream (i.e. file stream) or any third-party compliant implementation (i.e. Boost Iostreams). Most notably, this allows for easy debug output, since you can use std::cout stream as saving target. There are two functions, one works with narrow character streams, another handles wide character ones.

-
-
-

This is a simple example of saving XML document to standard output (samples/save_stream.cpp):

-
-
-
-
// save document to standard output
-std::cout << "Document:\n";
-doc.save(std::cout);
-
-
-
-

All of the above saving functions are implemented in terms of writer interface. This is a simple interface with a single function, which is called several times during output process with chunks of document data as input. In order to output the document via some custom transport, for example sockets, you should create an object which implements xml_writer_file interface and pass it to xml_document::save function.

-
-
-

This is a simple example of custom writer for saving document data to STL string (samples/save_custom_writer.cpp); read the sample code for more complex examples:

-
-
-
-
struct xml_string_writer: pugi::xml_writer
-{
-    std::string result;
-
-    virtual void write(const void* data, size_t size)
-    {
-        result.append(static_cast<const char*>(data), size);
-    }
-};
-
-
-
-

While the previously described functions save the whole document to the destination, it is easy to save a single subtree. Instead of calling xml_document::save, just call xml_node::print function on the target node. You can save node contents to C++ IOstream object or custom writer in this way. Saving a subtree slightly differs from saving the whole document; read the manual for more information.

-
-
-
-
-

Feedback

-
-
-

If you believe you’ve found a bug in pugixml, please file an issue via issue submission form. Be sure to include the relevant information so that the bug can be reproduced: the version of pugixml, compiler version and target architecture, the code that uses pugixml and exhibits the bug, etc. Feature requests and contributions can be filed as issues, too.

-
-
-

If filing an issue is not possible due to privacy or other concerns, you can contact pugixml author by e-mail directly: arseny.kapoulkine@gmail.com.

-
-
-
-
-

License

-
-
-

The pugixml library is distributed under the MIT license:

-
-
-
-
Copyright (c) 2006-2023 Arseny Kapoulkine
-
-Permission is hereby granted, free of charge, to any person
-obtaining a copy of this software and associated documentation
-files (the "Software"), to deal in the Software without
-restriction, including without limitation the rights to use,
-copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the
-Software is furnished to do so, subject to the following
-conditions:
-
-The above copyright notice and this permission notice shall be
-included in all copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
-OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
-NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
-HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
-WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
-FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
-OTHER DEALINGS IN THE SOFTWARE.
-
-
-
-

This means that you can freely use pugixml in your applications, both open-source and proprietary. If you use pugixml in a product, it is sufficient to add an acknowledgment like this to the product distribution:

-
-
-
-
This software is based on pugixml library (https://pugixml.org).
-pugixml is Copyright (C) 2006-2023 Arseny Kapoulkine.
-
-
-
-
-
-
-
-
-1. All trademarks used are properties of their respective owners. -
-
- - - \ No newline at end of file diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/character.xml --- a/dep/pugixml/docs/samples/character.xml Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,8 +0,0 @@ - - - - - - - - diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/custom_memory_management.cpp --- a/dep/pugixml/docs/samples/custom_memory_management.cpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,27 +0,0 @@ -#include "pugixml.hpp" - -#include - -// tag::decl[] -void* custom_allocate(size_t size) -{ - return new (std::nothrow) char[size]; -} - -void custom_deallocate(void* ptr) -{ - delete[] static_cast(ptr); -} -// end::decl[] - -int main() -{ -// tag::call[] - pugi::set_memory_management_functions(custom_allocate, custom_deallocate); -// end::call[] - - pugi::xml_document doc; - doc.load_string(""); -} - -// vim:et diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/include.cpp --- a/dep/pugixml/docs/samples/include.cpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,64 +0,0 @@ -#include "pugixml.hpp" - -#include -#include - -// tag::code[] -bool load_preprocess(pugi::xml_document& doc, const char* path); - -bool preprocess(pugi::xml_node node) -{ - for (pugi::xml_node child = node.first_child(); child; ) - { - if (child.type() == pugi::node_pi && strcmp(child.name(), "include") == 0) - { - pugi::xml_node include = child; - - // load new preprocessed document (note: ideally this should handle relative paths) - const char* path = include.value(); - - pugi::xml_document doc; - if (!load_preprocess(doc, path)) return false; - - // insert the comment marker above include directive - node.insert_child_before(pugi::node_comment, include).set_value(path); - - // copy the document above the include directive (this retains the original order!) - for (pugi::xml_node ic = doc.first_child(); ic; ic = ic.next_sibling()) - { - node.insert_copy_before(ic, include); - } - - // remove the include node and move to the next child - child = child.next_sibling(); - - node.remove_child(include); - } - else - { - if (!preprocess(child)) return false; - - child = child.next_sibling(); - } - } - - return true; -} - -bool load_preprocess(pugi::xml_document& doc, const char* path) -{ - pugi::xml_parse_result result = doc.load_file(path, pugi::parse_default | pugi::parse_pi); // for - - return result ? preprocess(doc) : false; -} -// end::code[] - -int main() -{ - pugi::xml_document doc; - if (!load_preprocess(doc, "character.xml")) return -1; - - doc.print(std::cout); -} - -// vim:et diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/load_error_handling.cpp --- a/dep/pugixml/docs/samples/load_error_handling.cpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,33 +0,0 @@ -#include "pugixml.hpp" - -#include - -void check_xml(const char* source) -{ -// tag::code[] - pugi::xml_document doc; - pugi::xml_parse_result result = doc.load_string(source); - - if (result) - { - std::cout << "XML [" << source << "] parsed without errors, attr value: [" << doc.child("node").attribute("attr").value() << "]\n\n"; - } - else - { - std::cout << "XML [" << source << "] parsed with errors, attr value: [" << doc.child("node").attribute("attr").value() << "]\n"; - std::cout << "Error description: " << result.description() << "\n"; - std::cout << "Error offset: " << result.offset << " (error at [..." << (source + result.offset) << "]\n\n"; - } -// end::code[] -} - -int main() -{ - check_xml("text"); - check_xml("text"); - check_xml("text"); - check_xml("<#tag />"); -} - -// vim:et diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/load_file.cpp --- a/dep/pugixml/docs/samples/load_file.cpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,16 +0,0 @@ -#include "pugixml.hpp" - -#include - -int main() -{ -// tag::code[] - pugi::xml_document doc; - - pugi::xml_parse_result result = doc.load_file("tree.xml"); - - std::cout << "Load result: " << result.description() << ", mesh name: " << doc.child("mesh").attribute("name").value() << std::endl; -// end::code[] -} - -// vim:et diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/load_memory.cpp --- a/dep/pugixml/docs/samples/load_memory.cpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,66 +0,0 @@ -#include "pugixml.hpp" - -#include -#include - -int main() -{ -// tag::decl[] - const char source[] = "0 0 1 1"; - size_t size = sizeof(source); -// end::decl[] - - pugi::xml_document doc; - - { - // tag::load_buffer[] - // You can use load_buffer to load document from immutable memory block: - pugi::xml_parse_result result = doc.load_buffer(source, size); - // end::load_buffer[] - - std::cout << "Load result: " << result.description() << ", mesh name: " << doc.child("mesh").attribute("name").value() << std::endl; - } - - { - // tag::load_buffer_inplace_begin[] - // You can use load_buffer_inplace to load document from mutable memory block; the block's lifetime must exceed that of document - char* buffer = new char[size]; - memcpy(buffer, source, size); - - // The block can be allocated by any method; the block is modified during parsing - pugi::xml_parse_result result = doc.load_buffer_inplace(buffer, size); - // end::load_buffer_inplace_begin[] - - std::cout << "Load result: " << result.description() << ", mesh name: " << doc.child("mesh").attribute("name").value() << std::endl; - - // tag::load_buffer_inplace_end[] - // You have to destroy the block yourself after the document is no longer used - delete[] buffer; - // end::load_buffer_inplace_end[] - } - - { - // tag::load_buffer_inplace_own[] - // You can use load_buffer_inplace_own to load document from mutable memory block and to pass the ownership of this block - // The block has to be allocated via pugixml allocation function - using i.e. operator new here is incorrect - char* buffer = static_cast(pugi::get_memory_allocation_function()(size)); - memcpy(buffer, source, size); - - // The block will be deleted by the document - pugi::xml_parse_result result = doc.load_buffer_inplace_own(buffer, size); - // end::load_buffer_inplace_own[] - - std::cout << "Load result: " << result.description() << ", mesh name: " << doc.child("mesh").attribute("name").value() << std::endl; - } - - { - // tag::load_string[] - // You can use load to load document from null-terminated strings, for example literals: - pugi::xml_parse_result result = doc.load_string("0 0 1 1"); - // end::load_string[] - - std::cout << "Load result: " << result.description() << ", mesh name: " << doc.child("mesh").attribute("name").value() << std::endl; - } -} - -// vim:et diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/load_options.cpp --- a/dep/pugixml/docs/samples/load_options.cpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,30 +0,0 @@ -#include "pugixml.hpp" - -#include - -int main() -{ - pugi::xml_document doc; - -// tag::code[] - const char* source = "<"; - - // Parsing with default options; note that comment node is not added to the tree, and entity reference < is expanded - doc.load_string(source); - std::cout << "First node value: [" << doc.first_child().value() << "], node child value: [" << doc.child_value("node") << "]\n"; - - // Parsing with additional parse_comments option; comment node is now added to the tree - doc.load_string(source, pugi::parse_default | pugi::parse_comments); - std::cout << "First node value: [" << doc.first_child().value() << "], node child value: [" << doc.child_value("node") << "]\n"; - - // Parsing with additional parse_comments option and without the (default) parse_escapes option; < is not expanded - doc.load_string(source, (pugi::parse_default | pugi::parse_comments) & ~pugi::parse_escapes); - std::cout << "First node value: [" << doc.first_child().value() << "], node child value: [" << doc.child_value("node") << "]\n"; - - // Parsing with minimal option mask; comment node is not added to the tree, and < is not expanded - doc.load_string(source, pugi::parse_minimal); - std::cout << "First node value: [" << doc.first_child().value() << "], node child value: [" << doc.child_value("node") << "]\n"; -// end::code[] -} - -// vim:et diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/load_stream.cpp --- a/dep/pugixml/docs/samples/load_stream.cpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,97 +0,0 @@ -#include "pugixml.hpp" - -#include -#include -#include - -void print_doc(const char* message, const pugi::xml_document& doc, const pugi::xml_parse_result& result) -{ - std::cout - << message - << "\t: load result '" << result.description() << "'" - << ", first character of root name: U+" << std::hex << std::uppercase << std::setw(4) << std::setfill('0') << pugi::as_wide(doc.first_child().name())[0] - << ", year: " << doc.first_child().first_child().first_child().child_value() - << std::endl; -} - -bool try_imbue(std::wistream& stream, const char* name) -{ - try - { - stream.imbue(std::locale(name)); - - return true; - } - catch (const std::exception&) - { - return false; - } -} - -int main() -{ - pugi::xml_document doc; - - { - // tag::code[] - std::ifstream stream("weekly-utf-8.xml"); - pugi::xml_parse_result result = doc.load(stream); - // end::code[] - - // first character of root name: U+9031, year: 1997 - print_doc("UTF8 file from narrow stream", doc, result); - } - - { - std::ifstream stream("weekly-utf-16.xml"); - pugi::xml_parse_result result = doc.load(stream); - - // first character of root name: U+9031, year: 1997 - print_doc("UTF16 file from narrow stream", doc, result); - } - - { - // Since wide streams are treated as UTF-16/32 ones, you can't load the UTF-8 file from a wide stream - // directly if you have localized characters; you'll have to provide a UTF8 locale (there is no - // standard one; you can use utf8_codecvt_facet from Boost or codecvt_utf8 from C++0x) - std::wifstream stream("weekly-utf-8.xml"); - - if (try_imbue(stream, "en_US.UTF-8")) // try Linux encoding - { - pugi::xml_parse_result result = doc.load(stream); - - // first character of root name: U+00E9, year: 1997 - print_doc("UTF8 file from wide stream", doc, result); - } - else - { - std::cout << "UTF-8 locale is not available\n"; - } - } - - { - // Since wide streams are treated as UTF-16/32 ones, you can't load the UTF-16 file from a wide stream without - // using custom codecvt; you can use codecvt_utf16 from C++0x - } - - { - // Since encoding names are non-standard, you can't load the Shift-JIS (or any other non-ASCII) file - // from a wide stream portably - std::wifstream stream("weekly-shift_jis.xml"); - - if (try_imbue(stream, ".932") || // try Microsoft encoding - try_imbue(stream, "ja_JP.SJIS")) // try Linux encoding; run "localedef -i ja_JP -c -f SHIFT_JIS /usr/lib/locale/ja_JP.SJIS" to get it - { - pugi::xml_parse_result result = doc.load(stream); - - // first character of root name: U+9031, year: 1997 - print_doc("Shift-JIS file from wide stream", doc, result); - } - else - { - std::cout << "Shift-JIS locale is not available\n"; - } - } -} - -// vim:et diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/modify_add.cpp --- a/dep/pugixml/docs/samples/modify_add.cpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,29 +0,0 @@ -#include "pugixml.hpp" - -#include - -int main() -{ - pugi::xml_document doc; - - // tag::code[] - // add node with some name - pugi::xml_node node = doc.append_child("node"); - - // add description node with text child - pugi::xml_node descr = node.append_child("description"); - descr.append_child(pugi::node_pcdata).set_value("Simple node"); - - // add param node before the description - pugi::xml_node param = node.insert_child_before("param", descr); - - // add attributes to param node - param.append_attribute("name") = "version"; - param.append_attribute("value") = 1.1; - param.insert_attribute_after("type", param.attribute("name")) = "float"; - // end::code[] - - doc.print(std::cout); -} - -// vim:et diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/modify_base.cpp --- a/dep/pugixml/docs/samples/modify_base.cpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,43 +0,0 @@ -#include "pugixml.hpp" - -#include -#include - -int main() -{ - pugi::xml_document doc; - if (!doc.load_string("text", pugi::parse_default | pugi::parse_comments)) return -1; - - // tag::node[] - pugi::xml_node node = doc.child("node"); - - // change node name - std::cout << node.set_name("notnode"); - std::cout << ", new node name: " << node.name() << std::endl; - - // change comment text - std::cout << doc.last_child().set_value("useless comment"); - std::cout << ", new comment text: " << doc.last_child().value() << std::endl; - - // we can't change value of the element or name of the comment - std::cout << node.set_value("1") << ", " << doc.last_child().set_name("2") << std::endl; - // end::node[] - - // tag::attr[] - pugi::xml_attribute attr = node.attribute("id"); - - // change attribute name/value - std::cout << attr.set_name("key") << ", " << attr.set_value("345"); - std::cout << ", new attribute: " << attr.name() << "=" << attr.value() << std::endl; - - // we can use numbers or booleans - attr.set_value(1.234); - std::cout << "new attribute value: " << attr.value() << std::endl; - - // we can also use assignment operators for more concise code - attr = true; - std::cout << "final attribute value: " << attr.value() << std::endl; - // end::attr[] -} - -// vim:et diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/modify_remove.cpp --- a/dep/pugixml/docs/samples/modify_remove.cpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,27 +0,0 @@ -#include "pugixml.hpp" - -#include - -int main() -{ - pugi::xml_document doc; - if (!doc.load_string("Simple node")) return -1; - - // tag::code[] - // remove description node with the whole subtree - pugi::xml_node node = doc.child("node"); - node.remove_child("description"); - - // remove id attribute - pugi::xml_node param = node.child("param"); - param.remove_attribute("value"); - - // we can also remove nodes/attributes by handles - pugi::xml_attribute id = param.attribute("name"); - param.remove_attribute(id); - // end::code[] - - doc.print(std::cout); -} - -// vim:et diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/save_custom_writer.cpp --- a/dep/pugixml/docs/samples/save_custom_writer.cpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,116 +0,0 @@ -#include "pugixml.hpp" - -#include -#include -#include - -// tag::code[] -struct xml_string_writer: pugi::xml_writer -{ - std::string result; - - virtual void write(const void* data, size_t size) - { - result.append(static_cast(data), size); - } -}; -// end::code[] - -struct xml_memory_writer: pugi::xml_writer -{ - char* buffer; - size_t capacity; - - size_t result; - - xml_memory_writer(): buffer(0), capacity(0), result(0) - { - } - - xml_memory_writer(char* buffer, size_t capacity): buffer(buffer), capacity(capacity), result(0) - { - } - - size_t written_size() const - { - return result < capacity ? result : capacity; - } - - virtual void write(const void* data, size_t size) - { - if (result < capacity) - { - size_t chunk = (capacity - result < size) ? capacity - result : size; - - memcpy(buffer + result, data, chunk); - } - - result += size; - } -}; - -std::string node_to_string(pugi::xml_node node) -{ - xml_string_writer writer; - node.print(writer); - - return writer.result; -} - -char* node_to_buffer(pugi::xml_node node, char* buffer, size_t size) -{ - if (size == 0) return buffer; - - // leave one character for null terminator - xml_memory_writer writer(buffer, size - 1); - node.print(writer); - - // null terminate - buffer[writer.written_size()] = 0; - - return buffer; -} - -char* node_to_buffer_heap(pugi::xml_node node) -{ - // first pass: get required memory size - xml_memory_writer counter; - node.print(counter); - - // allocate necessary size (+1 for null termination) - char* buffer = new char[counter.result + 1]; - - // second pass: actual printing - xml_memory_writer writer(buffer, counter.result); - node.print(writer); - - // null terminate - buffer[writer.written_size()] = 0; - - return buffer; -} - -int main() -{ - // get a test document - pugi::xml_document doc; - doc.load_string("hey"); - - // get contents as std::string (single pass) - std::cout << "contents: [" << node_to_string(doc) << "]\n"; - - // get contents into fixed-size buffer (single pass) - char large_buf[128]; - std::cout << "contents: [" << node_to_buffer(doc, large_buf, sizeof(large_buf)) << "]\n"; - - // get contents into fixed-size buffer (single pass, shows truncating behavior) - char small_buf[22]; - std::cout << "contents: [" << node_to_buffer(doc, small_buf, sizeof(small_buf)) << "]\n"; - - // get contents into heap-allocated buffer (two passes) - char* heap_buf = node_to_buffer_heap(doc); - std::cout << "contents: [" << heap_buf << "]\n"; - delete[] heap_buf; -} - -// vim:et diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/save_declaration.cpp --- a/dep/pugixml/docs/samples/save_declaration.cpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,27 +0,0 @@ -#include "pugixml.hpp" - -#include - -int main() -{ - // tag::code[] - // get a test document - pugi::xml_document doc; - doc.load_string("hey"); - - // add a custom declaration node - pugi::xml_node decl = doc.prepend_child(pugi::node_declaration); - decl.append_attribute("version") = "1.0"; - decl.append_attribute("encoding") = "UTF-8"; - decl.append_attribute("standalone") = "no"; - - // - // - // hey - // - doc.save(std::cout); - std::cout << std::endl; - // end::code[] -} - -// vim:et diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/save_file.cpp --- a/dep/pugixml/docs/samples/save_file.cpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,17 +0,0 @@ -#include "pugixml.hpp" - -#include - -int main() -{ - // get a test document - pugi::xml_document doc; - doc.load_string("hey"); - - // tag::code[] - // save document to file - std::cout << "Saving result: " << doc.save_file("save_file_output.xml") << std::endl; - // end::code[] -} - -// vim:et diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/save_options.cpp --- a/dep/pugixml/docs/samples/save_options.cpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,48 +0,0 @@ -#include "pugixml.hpp" - -#include - -int main() -{ - // tag::code[] - // get a test document - pugi::xml_document doc; - doc.load_string("hey"); - - // default options; prints - // - // - // hey - // - doc.save(std::cout); - std::cout << std::endl; - - // default options with custom indentation string; prints - // - // - // --hey - // - doc.save(std::cout, "--"); - std::cout << std::endl; - - // default options without indentation; prints - // - // - // hey - // - doc.save(std::cout, "\t", pugi::format_default & ~pugi::format_indent); // can also pass "" instead of indentation string for the same effect - std::cout << std::endl; - - // raw output; prints - // hey - doc.save(std::cout, "\t", pugi::format_raw); - std::cout << std::endl << std::endl; - - // raw output without declaration; prints - // hey - doc.save(std::cout, "\t", pugi::format_raw | pugi::format_no_declaration); - std::cout << std::endl; - // end::code[] -} - -// vim:et diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/save_stream.cpp --- a/dep/pugixml/docs/samples/save_stream.cpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,18 +0,0 @@ -#include "pugixml.hpp" - -#include - -int main() -{ - // get a test document - pugi::xml_document doc; - doc.load_string("hey"); - - // tag::code[] - // save document to standard output - std::cout << "Document:\n"; - doc.save(std::cout); - // end::code[] -} - -// vim:et diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/save_subtree.cpp --- a/dep/pugixml/docs/samples/save_subtree.cpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,26 +0,0 @@ -#include "pugixml.hpp" - -#include - -int main() -{ - // tag::code[] - // get a test document - pugi::xml_document doc; - doc.load_string("hey"); - - // print document to standard output (prints hey) - doc.save(std::cout, "", pugi::format_raw); - std::cout << std::endl; - - // print document to standard output as a regular node (prints hey) - doc.print(std::cout, "", pugi::format_raw); - std::cout << std::endl; - - // print a subtree to standard output (prints hey) - doc.child("foo").child("call").print(std::cout, "", pugi::format_raw); - std::cout << std::endl; - // end::code[] -} - -// vim:et diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/text.cpp --- a/dep/pugixml/docs/samples/text.cpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,35 +0,0 @@ -#include "pugixml.hpp" - -#include - -int main() -{ - pugi::xml_document doc; - - // get a test document - doc.load_string("test1.1yes"); - - pugi::xml_node project = doc.child("project"); - - // tag::access[] - std::cout << "Project name: " << project.child("name").text().get() << std::endl; - std::cout << "Project version: " << project.child("version").text().as_double() << std::endl; - std::cout << "Project visibility: " << (project.child("public").text().as_bool(/* def= */ true) ? "public" : "private") << std::endl; - std::cout << "Project description: " << project.child("description").text().get() << std::endl; - // end::access[] - - std::cout << std::endl; - - // tag::modify[] - // change project version - project.child("version").text() = 1.2; - - // add description element and set the contents - // note that we do not have to explicitly add the node_pcdata child - project.append_child("description").text().set("a test project"); - // end::modify[] - - doc.save(std::cout); -} - -// vim:et diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/transitions.xml --- a/dep/pugixml/docs/samples/transitions.xml Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,7 +0,0 @@ - - - - - - - diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/traverse_base.cpp --- a/dep/pugixml/docs/samples/traverse_base.cpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,51 +0,0 @@ -#include "pugixml.hpp" - -#include -#include - -int main() -{ - pugi::xml_document doc; - if (!doc.load_file("xgconsole.xml")) return -1; - - pugi::xml_node tools = doc.child("Profile").child("Tools"); - - // tag::basic[] - for (pugi::xml_node tool = tools.first_child(); tool; tool = tool.next_sibling()) - { - std::cout << "Tool:"; - - for (pugi::xml_attribute attr = tool.first_attribute(); attr; attr = attr.next_attribute()) - { - std::cout << " " << attr.name() << "=" << attr.value(); - } - - std::cout << std::endl; - } - // end::basic[] - - std::cout << std::endl; - - // tag::data[] - for (pugi::xml_node tool = tools.child("Tool"); tool; tool = tool.next_sibling("Tool")) - { - std::cout << "Tool " << tool.attribute("Filename").value(); - std::cout << ": AllowRemote " << tool.attribute("AllowRemote").as_bool(); - std::cout << ", Timeout " << tool.attribute("Timeout").as_int(); - std::cout << ", Description '" << tool.child_value("Description") << "'\n"; - } - // end::data[] - - std::cout << std::endl; - - // tag::contents[] - std::cout << "Tool for *.dae generation: " << tools.find_child_by_attribute("Tool", "OutputFileMasks", "*.dae").attribute("Filename").value() << "\n"; - - for (pugi::xml_node tool = tools.child("Tool"); tool; tool = tool.next_sibling("Tool")) - { - std::cout << "Tool " << tool.attribute("Filename").value() << "\n"; - } - // end::contents[] -} - -// vim:et diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/traverse_iter.cpp --- a/dep/pugixml/docs/samples/traverse_iter.cpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,27 +0,0 @@ -#include "pugixml.hpp" - -#include - -int main() -{ - pugi::xml_document doc; - if (!doc.load_file("xgconsole.xml")) return -1; - - pugi::xml_node tools = doc.child("Profile").child("Tools"); - - // tag::code[] - for (pugi::xml_node_iterator it = tools.begin(); it != tools.end(); ++it) - { - std::cout << "Tool:"; - - for (pugi::xml_attribute_iterator ait = it->attributes_begin(); ait != it->attributes_end(); ++ait) - { - std::cout << " " << ait->name() << "=" << ait->value(); - } - - std::cout << std::endl; - } - // end::code[] -} - -// vim:et diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/traverse_predicate.cpp --- a/dep/pugixml/docs/samples/traverse_predicate.cpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,48 +0,0 @@ -#include "pugixml.hpp" - -#include -#include - -// tag::decl[] -bool small_timeout(pugi::xml_node node) -{ - return node.attribute("Timeout").as_int() < 20; -} - -struct allow_remote_predicate -{ - bool operator()(pugi::xml_attribute attr) const - { - return strcmp(attr.name(), "AllowRemote") == 0; - } - - bool operator()(pugi::xml_node node) const - { - return node.attribute("AllowRemote").as_bool(); - } -}; -// end::decl[] - -int main() -{ - pugi::xml_document doc; - if (!doc.load_file("xgconsole.xml")) return -1; - - pugi::xml_node tools = doc.child("Profile").child("Tools"); - - // tag::find[] - // Find child via predicate (looks for direct children only) - std::cout << tools.find_child(allow_remote_predicate()).attribute("Filename").value() << std::endl; - - // Find node via predicate (looks for all descendants in depth-first order) - std::cout << doc.find_node(allow_remote_predicate()).attribute("Filename").value() << std::endl; - - // Find attribute via predicate - std::cout << tools.last_child().find_attribute(allow_remote_predicate()).value() << std::endl; - - // We can use simple functions instead of function objects - std::cout << tools.find_child(small_timeout).attribute("Filename").value() << std::endl; - // end::find[] -} - -// vim:et diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/traverse_rangefor.cpp --- a/dep/pugixml/docs/samples/traverse_rangefor.cpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,32 +0,0 @@ -#include "pugixml.hpp" - -#include - -int main() -{ - pugi::xml_document doc; - if (!doc.load_file("xgconsole.xml")) return -1; - - pugi::xml_node tools = doc.child("Profile").child("Tools"); - - // tag::code[] - for (pugi::xml_node tool: tools.children("Tool")) - { - std::cout << "Tool:"; - - for (pugi::xml_attribute attr: tool.attributes()) - { - std::cout << " " << attr.name() << "=" << attr.value(); - } - - for (pugi::xml_node child: tool.children()) - { - std::cout << ", child " << child.name(); - } - - std::cout << std::endl; - } - // end::code[] -} - -// vim:et diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/traverse_walker.cpp --- a/dep/pugixml/docs/samples/traverse_walker.cpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,35 +0,0 @@ -#include "pugixml.hpp" - -#include - -const char* node_types[] = -{ - "null", "document", "element", "pcdata", "cdata", "comment", "pi", "declaration" -}; - -// tag::impl[] -struct simple_walker: pugi::xml_tree_walker -{ - virtual bool for_each(pugi::xml_node& node) - { - for (int i = 0; i < depth(); ++i) std::cout << " "; // indentation - - std::cout << node_types[node.type()] << ": name='" << node.name() << "', value='" << node.value() << "'\n"; - - return true; // continue traversal - } -}; -// end::impl[] - -int main() -{ - pugi::xml_document doc; - if (!doc.load_file("tree.xml")) return -1; - - // tag::traverse[] - simple_walker walker; - doc.traverse(walker); - // end::traverse[] -} - -// vim:et diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/tree.xml --- a/dep/pugixml/docs/samples/tree.xml Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,12 +0,0 @@ - - - - some text - - some more text - - - - - - diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/weekly-shift_jis.xml --- a/dep/pugixml/docs/samples/weekly-shift_jis.xml Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,78 +0,0 @@ - - - -<ŹT•ń> - <”NŚŽŹT> - <”N“x>1997 - <ŚŽ“x>1 - <ŹT>1 - - - <Ž–Ľ> - <Ž>ŽR“c - <–Ľ>‘ľY - - - <‹Ć–±•ńŤŠXg> - <‹Ć–±•ńŤ> - <‹Ć–±–Ľ>XMLGfB^[‚ĚŤě¬ - <‹Ć–±R[h>X3355-23 - <ŤH”ŠÇ—ť> - <Ś©Ď‚ŕ‚čŤH”>1600 - <ŽŔŃŤH”>320 - <“–ŚŽŚ©Ď‚ŕ‚čŤH”>160 - <“–ŚŽŽŔŃŤH”>24 - - <—\’荀–ÚŠXg> - <—\’荀–Ú> -

XMLGfB^[‚ĚŠî–{Žd—l‚ĚŤě¬

- - - <ŽŔŽ{Ž–Ť€ŠXg> - <ŽŔŽ{Ž–Ť€> -

XMLGfB^[‚ĚŠî–{Žd—l‚ĚŤě¬

- - <ŽŔŽ{Ž–Ť€> -

‹ŁŤ‡‘ĽŽĐ»•i‚Ě‹@”\’˛Ť¸

- - - <Źă’·‚Ö‚Ě—vżŽ–Ť€ŠXg> - <Źă’·‚Ö‚Ě—vżŽ–Ť€> -

“Á‚É‚Č‚µ

- - - <–â‘č“_‘ÎŤô> -

XML‚Ƃ͉˝‚©‚í‚©‚ç‚Č‚˘B

- - - - <‹Ć–±•ńŤ> - <‹Ć–±–Ľ>ŚźŤőG“W“‚ĚŠJ”­ - <‹Ć–±R[h>S8821-76 - <ŤH”ŠÇ—ť> - <Ś©Ď‚ŕ‚čŤH”>120 - <ŽŔŃŤH”>6 - <“–ŚŽŚ©Ď‚ŕ‚čŤH”>32 - <“–ŚŽŽŔŃŤH”>2 - - <—\’荀–ÚŠXg> - <—\’荀–Ú> -

goo‚Ě‹@”\‚𒲂ׂĂ݂é

- - - <ŽŔŽ{Ž–Ť€ŠXg> - <ŽŔŽ{Ž–Ť€> -

ŤX‚ÉA‚Ç‚¤‚˘‚¤ŚźŤőG“W“‚Ş‚ ‚é‚©’˛Ť¸‚·‚é

- - - <Źă’·‚Ö‚Ě—vżŽ–Ť€ŠXg> - <Źă’·‚Ö‚Ě—vżŽ–Ť€> -

ŠJ”­‚đ‚·‚é‚Ě‚Í‚ß‚ń‚Ç‚¤‚Č‚Ě‚ĹAYahoo!‚đ”Žű‚µ‚ĉş‚ł‚˘B

- - - <–â‘č“_‘ÎŤô> -

ŚźŤőG“W“‚ĹŽÔ‚đ‘–‚ç‚ą‚邱‚Ć‚Ş‚Ĺ‚«‚Č‚˘Bi—v’˛Ť¸j

- - - - diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/weekly-utf-16.xml Binary file dep/pugixml/docs/samples/weekly-utf-16.xml has changed diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/weekly-utf-8.xml --- a/dep/pugixml/docs/samples/weekly-utf-8.xml Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,78 +0,0 @@ - - - -<週報> - <ĺą´ćśé€±> - <年度>1997 - <ćśĺş¦>1 - <週>1 - - - <ć°ŹĺŤ> - <ć°Ź>山田 - <ĺŤ>ĺ¤ŞéŽ - - - <業務報告ăŞă‚ąă> - <業務報告> - <業務ĺŤ>XMLエă‡ă‚Łă‚żăĽă®ä˝ść - <業務コăĽă‰>X3355-23 - <工数管ç†> - <見積もり工数>1600 - <実績工数>320 - <当ćśč¦‹ç©Ťă‚‚ă‚Šĺ·Ąć•°>160 - <当ćśĺ®źç¸ľĺ·Ąć•°>24 - - <äşĺ®šé …ç›®ăŞă‚ąă> - <äşĺ®šé …ç›®> -

XMLエă‡ă‚Łă‚żăĽă®ĺźşćś¬ä»•ć§ă®ä˝ść

- - - <実施事項ăŞă‚ąă> - <実施事項> -

XMLエă‡ă‚Łă‚żăĽă®ĺźşćś¬ä»•ć§ă®ä˝ść

- - <実施事項> -

競ĺ他社製ĺ“ă®ć©źč˝čŞżćź»

- - - <上長ă¸ă®č¦č«‹äş‹é …ăŞă‚ąă> - <上長ă¸ă®č¦č«‹äş‹é …> -

特ă«ăŞă—

- - - <問題点対策> -

XMLă¨ăŻä˝•ă‹ă‚Źă‹ă‚‰ăŞă„。

- - - - <業務報告> - <業務ĺŤ>検索エăłă‚¸ăłă®é–‹ç™ş - <業務コăĽă‰>S8821-76 - <工数管ç†> - <見積もり工数>120 - <実績工数>6 - <当ćśč¦‹ç©Ťă‚‚ă‚Šĺ·Ąć•°>32 - <当ćśĺ®źç¸ľĺ·Ąć•°>2 - - <äşĺ®šé …ç›®ăŞă‚ąă> - <äşĺ®šé …ç›®> -

gooă®ć©źč˝ă‚’調ăąă¦ăżă‚‹

- - - <実施事項ăŞă‚ąă> - <実施事項> -

ć›´ă«ă€ă©ă†ă„ă†ć¤śç´˘ă‚¨ăłă‚¸ăłăŚă‚ă‚‹ă‹čŞżćź»ă™ă‚‹

- - - <上長ă¸ă®č¦č«‹äş‹é …ăŞă‚ąă> - <上長ă¸ă®č¦č«‹äş‹é …> -

開発をă™ă‚‹ă®ăŻă‚ă‚“ă©ă†ăŞă®ă§ă€Yahoo!を買収ă—ă¦ä¸‹ă•ă„。

- - - <問題点対策> -

検索エăłă‚¸ăłă§č»Šă‚’走らă›ă‚‹ă“ă¨ăŚă§ăŤăŞă„。ďĽč¦čŞżćź»ďĽ‰

- - - - diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/xgconsole.xml --- a/dep/pugixml/docs/samples/xgconsole.xml Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,12 +0,0 @@ - - - - - Jamplus build system - - - - - - - diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/xpath_error.cpp --- a/dep/pugixml/docs/samples/xpath_error.cpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,43 +0,0 @@ -#include "pugixml.hpp" - -#include - -int main() -{ - pugi::xml_document doc; - if (!doc.load_file("xgconsole.xml")) return -1; - -// tag::code[] - // Exception is thrown for incorrect query syntax - try - { - doc.select_nodes("//nodes[#true()]"); - } - catch (const pugi::xpath_exception& e) - { - std::cout << "Select failed: " << e.what() << std::endl; - } - - // Exception is thrown for incorrect query semantics - try - { - doc.select_nodes("(123)/next"); - } - catch (const pugi::xpath_exception& e) - { - std::cout << "Select failed: " << e.what() << std::endl; - } - - // Exception is thrown for query with incorrect return type - try - { - doc.select_nodes("123"); - } - catch (const pugi::xpath_exception& e) - { - std::cout << "Select failed: " << e.what() << std::endl; - } -// end::code[] -} - -// vim:et diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/xpath_query.cpp --- a/dep/pugixml/docs/samples/xpath_query.cpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,36 +0,0 @@ -#include "pugixml.hpp" - -#include -#include - -int main() -{ - pugi::xml_document doc; - if (!doc.load_file("xgconsole.xml")) return -1; - -// tag::code[] - // Select nodes via compiled query - pugi::xpath_query query_remote_tools("/Profile/Tools/Tool[@AllowRemote='true']"); - - pugi::xpath_node_set tools = query_remote_tools.evaluate_node_set(doc); - std::cout << "Remote tool: "; - tools[2].node().print(std::cout); - - // Evaluate numbers via compiled query - pugi::xpath_query query_timeouts("sum(//Tool/@Timeout)"); - std::cout << query_timeouts.evaluate_number(doc) << std::endl; - - // Evaluate strings via compiled query for different context nodes - pugi::xpath_query query_name_valid("string-length(substring-before(@Filename, '_')) > 0 and @OutputFileMasks"); - pugi::xpath_query query_name("concat(substring-before(@Filename, '_'), ' produces ', @OutputFileMasks)"); - - for (pugi::xml_node tool = doc.first_element_by_path("Profile/Tools/Tool"); tool; tool = tool.next_sibling()) - { - std::string s = query_name.evaluate_string(tool); - - if (query_name_valid.evaluate_boolean(tool)) std::cout << s << std::endl; - } -// end::code[] -} - -// vim:et diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/xpath_select.cpp --- a/dep/pugixml/docs/samples/xpath_select.cpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,28 +0,0 @@ -#include "pugixml.hpp" - -#include - -int main() -{ - pugi::xml_document doc; - if (!doc.load_file("xgconsole.xml")) return -1; - -// tag::code[] - pugi::xpath_node_set tools = doc.select_nodes("/Profile/Tools/Tool[@AllowRemote='true' and @DeriveCaptionFrom='lastparam']"); - - std::cout << "Tools:\n"; - - for (pugi::xpath_node_set::const_iterator it = tools.begin(); it != tools.end(); ++it) - { - pugi::xpath_node node = *it; - std::cout << node.node().attribute("Filename").value() << "\n"; - } - - pugi::xpath_node build_tool = doc.select_node("//Tool[contains(Description, 'build system')]"); - - if (build_tool) - std::cout << "Build tool: " << build_tool.node().attribute("Filename").value() << "\n"; -// end::code[] -} - -// vim:et diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/docs/samples/xpath_variables.cpp --- a/dep/pugixml/docs/samples/xpath_variables.cpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,38 +0,0 @@ -#include "pugixml.hpp" - -#include -#include - -int main() -{ - pugi::xml_document doc; - if (!doc.load_file("xgconsole.xml")) return -1; - -// tag::code[] - // Select nodes via compiled query - pugi::xpath_variable_set vars; - vars.add("remote", pugi::xpath_type_boolean); - - pugi::xpath_query query_remote_tools("/Profile/Tools/Tool[@AllowRemote = string($remote)]", &vars); - - vars.set("remote", true); - pugi::xpath_node_set tools_remote = query_remote_tools.evaluate_node_set(doc); - - vars.set("remote", false); - pugi::xpath_node_set tools_local = query_remote_tools.evaluate_node_set(doc); - - std::cout << "Remote tool: "; - tools_remote[2].node().print(std::cout); - - std::cout << "Local tool: "; - tools_local[0].node().print(std::cout); - - // You can pass the context directly to select_nodes/select_node - pugi::xpath_node_set tools_local_imm = doc.select_nodes("/Profile/Tools/Tool[@AllowRemote = string($remote)]", &vars); - - std::cout << "Local tool imm: "; - tools_local_imm[0].node().print(std::cout); -// end::code[] -} - -// vim:et diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/pugixml-config-version.cmake --- a/dep/pugixml/pugixml-config-version.cmake Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,65 +0,0 @@ -# This is a basic version file for the Config-mode of find_package(). -# It is used by write_basic_package_version_file() as input file for configure_file() -# to create a version-file which can be installed along a config.cmake file. -# -# The created file sets PACKAGE_VERSION_EXACT if the current version string and -# the requested version string are exactly the same and it sets -# PACKAGE_VERSION_COMPATIBLE if the current version is >= requested version, -# but only if the requested major version is the same as the current one. -# The variable CVF_VERSION must be set before calling configure_file(). - - -set(PACKAGE_VERSION "1.14") - -if(PACKAGE_VERSION VERSION_LESS PACKAGE_FIND_VERSION) - set(PACKAGE_VERSION_COMPATIBLE FALSE) -else() - - if("1.14" MATCHES "^([0-9]+)\\.") - set(CVF_VERSION_MAJOR "${CMAKE_MATCH_1}") - if(NOT CVF_VERSION_MAJOR VERSION_EQUAL 0) - string(REGEX REPLACE "^0+" "" CVF_VERSION_MAJOR "${CVF_VERSION_MAJOR}") - endif() - else() - set(CVF_VERSION_MAJOR "1.14") - endif() - - if(PACKAGE_FIND_VERSION_RANGE) - # both endpoints of the range must have the expected major version - math (EXPR CVF_VERSION_MAJOR_NEXT "${CVF_VERSION_MAJOR} + 1") - if (NOT PACKAGE_FIND_VERSION_MIN_MAJOR STREQUAL CVF_VERSION_MAJOR - OR ((PACKAGE_FIND_VERSION_RANGE_MAX STREQUAL "INCLUDE" AND NOT PACKAGE_FIND_VERSION_MAX_MAJOR STREQUAL CVF_VERSION_MAJOR) - OR (PACKAGE_FIND_VERSION_RANGE_MAX STREQUAL "EXCLUDE" AND NOT PACKAGE_FIND_VERSION_MAX VERSION_LESS_EQUAL CVF_VERSION_MAJOR_NEXT))) - set(PACKAGE_VERSION_COMPATIBLE FALSE) - elseif(PACKAGE_FIND_VERSION_MIN_MAJOR STREQUAL CVF_VERSION_MAJOR - AND ((PACKAGE_FIND_VERSION_RANGE_MAX STREQUAL "INCLUDE" AND PACKAGE_VERSION VERSION_LESS_EQUAL PACKAGE_FIND_VERSION_MAX) - OR (PACKAGE_FIND_VERSION_RANGE_MAX STREQUAL "EXCLUDE" AND PACKAGE_VERSION VERSION_LESS PACKAGE_FIND_VERSION_MAX))) - set(PACKAGE_VERSION_COMPATIBLE TRUE) - else() - set(PACKAGE_VERSION_COMPATIBLE FALSE) - endif() - else() - if(PACKAGE_FIND_VERSION_MAJOR STREQUAL CVF_VERSION_MAJOR) - set(PACKAGE_VERSION_COMPATIBLE TRUE) - else() - set(PACKAGE_VERSION_COMPATIBLE FALSE) - endif() - - if(PACKAGE_FIND_VERSION STREQUAL PACKAGE_VERSION) - set(PACKAGE_VERSION_EXACT TRUE) - endif() - endif() -endif() - - -# if the installed or the using project don't have CMAKE_SIZEOF_VOID_P set, ignore it: -if("${CMAKE_SIZEOF_VOID_P}" STREQUAL "" OR "8" STREQUAL "") - return() -endif() - -# check that the installed version has the same 32/64bit-ness as the one which is currently searching: -if(NOT CMAKE_SIZEOF_VOID_P STREQUAL "8") - math(EXPR installedBits "8 * 8") - set(PACKAGE_VERSION "${PACKAGE_VERSION} (${installedBits}bit)") - set(PACKAGE_VERSION_UNSUITABLE TRUE) -endif() diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/pugixml-config.cmake --- a/dep/pugixml/pugixml-config.cmake Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,19 +0,0 @@ - -####### Expanded from @PACKAGE_INIT@ by configure_package_config_file() ####### -####### Any changes to this file will be overwritten by the next CMake run #### -####### The input file was pugixml-config.cmake.in ######## - -get_filename_component(PACKAGE_PREFIX_DIR "${CMAKE_CURRENT_LIST_DIR}/../" ABSOLUTE) - -#################################################################################### - -include("${CMAKE_CURRENT_LIST_DIR}/pugixml-targets.cmake") - -# If the user is not requiring 1.11 (either by explicitly requesting an older -# version or not requesting one at all), provide the old imported target name -# for compatibility. -if (NOT TARGET pugixml AND (NOT DEFINED PACKAGE_FIND_VERSION OR PACKAGE_FIND_VERSION VERSION_LESS "1.11")) - add_library(pugixml INTERFACE IMPORTED) - # Equivalent to target_link_libraries INTERFACE, but compatible with CMake 3.10 - set_target_properties(pugixml PROPERTIES INTERFACE_LINK_LIBRARIES pugixml::pugixml) -endif () diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/pugixml.pc --- a/dep/pugixml/pugixml.pc Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,11 +0,0 @@ -prefix=/usr -exec_prefix=${prefix} -includedir=/usr/include -libdir=/usr/lib - -Name: pugixml -Description: Light-weight, simple and fast XML parser for C++ with XPath support. -URL: https://pugixml.org/ -Version: 1.14 -Cflags: -I${includedir} -Libs: -L${libdir} -lpugixml diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/readme.txt --- a/dep/pugixml/readme.txt Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,50 +0,0 @@ -pugixml 1.14 - an XML processing library - -Copyright (C) 2006-2023, by Arseny Kapoulkine (arseny.kapoulkine@gmail.com) -Report bugs and download new versions at https://pugixml.org/ - -This is the distribution of pugixml, which is a C++ XML processing library, -which consists of a DOM-like interface with rich traversal/modification -capabilities, an extremely fast XML parser which constructs the DOM tree from -an XML file/buffer, and an XPath 1.0 implementation for complex data-driven -tree queries. Full Unicode support is also available, with Unicode interface -variants and conversions between different Unicode encodings (which happen -automatically during parsing/saving). - -The distribution contains the following folders: - - docs/ - documentation - docs/samples - pugixml usage examples - docs/quickstart.html - quick start guide - docs/manual.html - complete manual - - scripts/ - project files for IDE/build systems - - src/ - header and source files - - readme.txt - this file. - -This library is distributed under the MIT License: - -Copyright (c) 2006-2023 Arseny Kapoulkine - -Permission is hereby granted, free of charge, to any person -obtaining a copy of this software and associated documentation -files (the "Software"), to deal in the Software without -restriction, including without limitation the rights to use, -copy, modify, merge, publish, distribute, sublicense, and/or sell -copies of the Software, and to permit persons to whom the -Software is furnished to do so, subject to the following -conditions: - -The above copyright notice and this permission notice shall be -included in all copies or substantial portions of the Software. - -THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, -EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES -OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND -NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT -HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, -WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING -FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR -OTHER DEALINGS IN THE SOFTWARE. diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/cocoapods_push.sh --- a/dep/pugixml/scripts/cocoapods_push.sh Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,4 +0,0 @@ -#!/bin/bash - -#Push to igagis repo for now -pod repo push igagis pugixml.podspec --use-libraries --verbose diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/natvis/pugixml.natvis --- a/dep/pugixml/scripts/natvis/pugixml.natvis Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,77 +0,0 @@ - - - - {_root} - none - - _root - - - - - {(pugi::xml_node_type)(header & 0xf),en} name={name,na} value={value,na} - {(pugi::xml_node_type)(header & 0xf),en} name={name,na} - {(pugi::xml_node_type)(header & 0xf),en} value={value,na} - {(pugi::xml_node_type)(header & 0xf),en} - - value,na - - - - - - - curr,view(child)na - curr = curr->next_attribute - - - - - - first_child - next_sibling - this,na - - - - - - {_attr} - none - - _attr - - - - - {name,na} = {value,na} - {value,na} - - name,na - value,na - - - - - {_node,na} "{_attribute._attr->name,na}"="{_attribute._attr->value,na}" - {_node,na} - {_attribute} - empty - - _node - _attribute - _node,na - _attribute,na - - - - - - _type - - _end - _begin - _begin - - - - \ No newline at end of file diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/natvis/pugixml_compact.natvis --- a/dep/pugixml/scripts/natvis/pugixml_compact.natvis Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,506 +0,0 @@ - - - - {_root} - none - - _root - - - - - {_attr} - none - - _attr - - - - - - (pugi::xml_node_type)(header._flags & 15) - name,na - value,na - - - ... - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - h = h ^ (h >> 16) - h = h * (0x85ebca6bu) - h = h ^ (h >> 13) - h = h * (0xc2b2ae35u) - h = h ^ (h >> 16) - - bucket = h & hashmod - - - - probe_item = (size_t*)_items + bucket * 2 - - - attribute_real = *(pugi::xml_attribute_struct**)(probe_item + 1) - - - - bucket = (bucket + probe + 1) & hashmod - probe++ - - - attribute_data_copy = attribute_data - - - *attribute_real,view(child) - attribute_this = (size_t)&(*attribute_real).next_attribute - attribute_data = (*attribute_real).next_attribute._data - - - *attribute_short,view(child) - attribute_this = (size_t)&(*attribute_short).next_attribute - attribute_data = (*attribute_short).next_attribute._data - - - - attribute_T1 = 7 - attribute_T2 = 0 - - - h = (unsigned)attribute_this - bucket = 0 - - probe = 0 - probe_item = (size_t*)0 - - attribute_real = (pugi::xml_attribute_struct*)0 - attribute_short = (pugi::xml_attribute_struct*)(((size_t)attribute_this & ~(compact_alignment - 1)) + (attribute_data - 1 + attribute_T2) * compact_alignment) - - number++ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - h = h ^ (h >> 16) - h = h * (0x85ebca6bu) - h = h ^ (h >> 13) - h = h * (0xc2b2ae35u) - h = h ^ (h >> 16) - - bucket = h & hashmod - - - - probe_item = (size_t*)_items + bucket * 2 - - - child_real = *(pugi::xml_node_struct**)(probe_item + 1) - - - - bucket = (bucket + probe + 1) & hashmod - probe++ - - - child_data_copy = child_data - - - *child_real,view(child) - child_this = (size_t)&(*child_real).next_sibling - child_data = (*child_real).next_sibling._data - - - *child_short,view(child) - child_this = (size_t)&(*child_short).next_sibling - child_data = (*child_short).next_sibling._data - - - - child_T1 = 10 - child_T2 = 0 - - - h = (unsigned)child_this - bucket = 0 - - probe = 0 - probe_item = (size_t*)0 - - child_real = (pugi::xml_node_struct*)0 - child_short = (pugi::xml_node_struct*)(((size_t)child_this & ~(compact_alignment - 1)) + (child_data - 1 + child_T2) * compact_alignment) - - number++ - - - - next_sibling - - - - - - name,na - value,na - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - h = h ^ (h >> 16) - h = h * (0x85ebca6bu) - h = h ^ (h >> 13) - h = h * (0xc2b2ae35u) - h = h ^ (h >> 16) - - bucket = h & hashmod - - - - probe_item = (size_t*)_items + bucket * 2 - - - attribute_real = *(pugi::xml_attribute_struct**)(probe_item + 1) - - - - bucket = (bucket + probe + 1) & hashmod - probe++ - - - - *attribute_real - - - *attribute_short - - - - - - - - - - - - - - - - - - - - (pugi::char_t*)(compact_string_base + offset * sizeof(pugi::char_t)),na - - - - - - - - - - - - - - - - - - - - - - - - - - - - h = h ^ (h >> 16) - h = h * (0x85ebca6bu) - h = h ^ (h >> 13) - h = h * (0xc2b2ae35u) - h = h ^ (h >> 16) - - bucket = h & hashmod - - - - probe_item = (size_t*)_items + bucket * 2 - - - *(pugi::char_t**)(probe_item + 1) - - - - bucket = (bucket + probe + 1) & hashmod - probe++ - - - - - - - nullptr - ... - - - - - - - *(pugi::xml_node_struct*)(((size_t)this & ~(compact_alignment - 1)) + (_data - 1 + $T2) * compact_alignment) - - - - - - - - - - - - - - - - - - - - - - - - - - - - h = h ^ (h >> 16) - h = h * (0x85ebca6bu) - h = h ^ (h >> 13) - h = h * (0xc2b2ae35u) - h = h ^ (h >> 16) - - bucket = h & hashmod - - - - probe_item = (size_t*)_items + bucket * 2 - - - **(pugi::xml_node_struct**)(probe_item + 1) - - - - bucket = (bucket + probe + 1) & hashmod - probe++ - - - - - - - nullptr - ... - - - - - - - *(pugi::xml_attribute_struct*)(((size_t)this & ~(compact_alignment - 1)) + (_data - 1 + $T2) * compact_alignment) - - - - - - - - - - - - - - - - - - - - - - - - - - - - h = h ^ (h >> 16) - h = h * (0x85ebca6bu) - h = h ^ (h >> 13) - h = h * (0xc2b2ae35u) - h = h ^ (h >> 16) - - bucket = h & hashmod - - - - probe_item = (size_t*)_items + bucket * 2 - - - **(pugi::xml_attribute_struct**)(probe_item + 1) - - - - bucket = (bucket + probe + 1) & hashmod - probe++ - - - - - - - {_node,na} {_attribute,na} - {_node,na} - {_attribute} - empty - - - _node - _attribute - - _node,na - _attribute,na - - - - - - _type - - _end - _begin - _begin - - - - \ No newline at end of file diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/nuget/build/native/pugixml-propertiesui.xml --- a/dep/pugixml/scripts/nuget/build/native/pugixml-propertiesui.xml Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,17 +0,0 @@ - - - - - - - - - - - - - - - - - diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/nuget/build/native/pugixml.targets --- a/dep/pugixml/scripts/nuget/build/native/pugixml.targets Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,28 +0,0 @@ - - - - dynamic - Debug - Release - - - - - - - PUGIXML_HEADER_ONLY;%(PreprocessorDefinitions) - $(MSBuildThisFileDirectory)include;%(AdditionalIncludeDirectories) - - - $(MSBuildThisFileDirectory)include;%(AdditionalIncludeDirectories) - - - - - - - - $(MSBuildThisFileDirectory)lib/$(Platform)\$(PlatformToolset.Split('_')[0])\$(Linkage-pugixml)\$(Configuration-pugixml)\pugixml.lib;%(AdditionalDependencies) - - - diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/nuget/pugixml.nuspec --- a/dep/pugixml/scripts/nuget/pugixml.nuspec Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,20 +0,0 @@ - - - - pugixml - 1.14.0-appveyor - pugixml - Arseny Kapoulkine - Arseny Kapoulkine - false - MIT - https://pugixml.org/ - pugixml is a C++ XML processing library, which consists of a DOM-like interface with rich traversal/modification capabilities, an extremely fast XML parser which constructs the DOM tree from an XML file/buffer, and an XPath 1.0 implementation for complex data-driven tree queries. Full Unicode support is also available, with Unicode interface variants and conversions between different Unicode encodings (which happen automatically during parsing/saving). -pugixml is used by a lot of projects, both open-source and proprietary, for performance and easy-to-use interface. -This package contains builds for VS2013, VS2015, VS2017, VS2019 and VS2022, for both statically linked and DLL CRT; you can switch the CRT linkage in Project -> Properties -> Referenced Packages -> pugixml. - Light-weight, simple and fast XML parser for C++ with XPath support - https://pugixml.org/docs/manual.html#changes - Copyright (c) 2006-2023 Arseny Kapoulkine - native nativepackage - - diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/nuget_build.ps1 --- a/dep/pugixml/scripts/nuget_build.ps1 Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,70 +0,0 @@ -function Run-Command([string]$cmd) -{ - Invoke-Expression $cmd - if ($LastExitCode) { exit $LastExitCode } -} - -function Force-Copy([string]$from, [string]$to) -{ - Write-Host $from "->" $to - New-Item -Force $to | Out-Null - Copy-Item -Force $from $to - if (! $?) { exit 1 } -} - -function Build-Version([string]$vs, [string]$toolset, [string]$linkage) -{ - $prjsuffix = if ($linkage -eq "static") { "_static" } else { "" } - $cfgsuffix = if ($linkage -eq "static") { "Static" } else { "" } - - foreach ($configuration in "Debug","Release") - { - Run-Command "msbuild pugixml_$vs$prjsuffix.vcxproj /t:Rebuild /p:Configuration=$configuration /p:Platform=x86 /v:minimal /nologo" - Run-Command "msbuild pugixml_$vs$prjsuffix.vcxproj /t:Rebuild /p:Configuration=$configuration /p:Platform=x64 /v:minimal /nologo" - - Force-Copy "$vs/Win32_$configuration$cfgsuffix/pugixml.lib" "nuget/build/native/lib/Win32/$toolset/$linkage/$configuration/pugixml.lib" - Force-Copy "$vs/x64_$configuration$cfgsuffix/pugixml.lib" "nuget/build/native/lib/x64/$toolset/$linkage/$configuration/pugixml.lib" - } -} - -Push-Location -$scriptdir = Split-Path $MyInvocation.MyCommand.Path -cd $scriptdir - -Force-Copy "../src/pugiconfig.hpp" "nuget/build/native/include/pugiconfig.hpp" -Force-Copy "../src/pugixml.hpp" "nuget/build/native/include/pugixml.hpp" -Force-Copy "../src/pugixml.cpp" "nuget/build/native/include/pugixml.cpp" - -if ($args[0] -eq 2022){ - Build-Version "vs2022" "v143" "dynamic" - Build-Version "vs2022" "v143" "static" - -} elseif ($args[0] -eq 2019){ - Build-Version "vs2019" "v142" "dynamic" - Build-Version "vs2019" "v142" "static" - -} elseif ($args[0] -eq 2017){ - Build-Version "vs2017" "v141" "dynamic" - Build-Version "vs2017" "v141" "static" - - Build-Version "vs2015" "v140" "dynamic" - Build-Version "vs2015" "v140" "static" - - Build-Version "vs2013" "v120" "dynamic" - Build-Version "vs2013" "v120" "static" - -} elseif($args[0] -eq 2015){ - Build-Version "vs2015" "v140" "dynamic" - Build-Version "vs2015" "v140" "static" - - Build-Version "vs2013" "v120" "dynamic" - Build-Version "vs2013" "v120" "static" - -} elseif($args[0] -eq 2013){ - Build-Version "vs2013" "v120" "dynamic" - Build-Version "vs2013" "v120" "static" -} - -Run-Command "nuget pack nuget" - -Pop-Location diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/premake4.lua --- a/dep/pugixml/scripts/premake4.lua Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,92 +0,0 @@ --- Reset RNG seed to get consistent results across runs (i.e. XCode) -math.randomseed(12345) - -local static = _ARGS[1] == 'static' -local action = premake.action.current() - -if string.startswith(_ACTION, "vs") then - if action then - -- Disable solution generation - function action.onsolution(sln) - sln.vstudio_configs = premake.vstudio_buildconfigs(sln) - end - - -- Rename output file - function action.onproject(prj) - local name = "%%_" .. _ACTION .. (static and "_static" or "") - - if static then - for k, v in pairs(prj.project.__configs) do - v.objectsdir = v.objectsdir .. "Static" - end - end - - if _ACTION == "vs2010" then - premake.generate(prj, name .. ".vcxproj", premake.vs2010_vcxproj) - else - premake.generate(prj, name .. ".vcproj", premake.vs200x_vcproj) - end - end - end -elseif _ACTION == "codeblocks" then - action.onsolution = nil - - function action.onproject(prj) - premake.generate(prj, "%%_" .. _ACTION .. ".cbp", premake.codeblocks_cbp) - end -elseif _ACTION == "codelite" then - action.onsolution = nil - - function action.onproject(prj) - premake.generate(prj, "%%_" .. _ACTION .. ".project", premake.codelite_project) - end -end - -solution "pugixml" - objdir(_ACTION) - targetdir(_ACTION) - -if string.startswith(_ACTION, "vs") then - if _ACTION ~= "vs2002" and _ACTION ~= "vs2003" then - platforms { "x32", "x64" } - - configuration "x32" targetdir(_ACTION .. "/x32") - configuration "x64" targetdir(_ACTION .. "/x64") - end - - configurations { "Debug", "Release" } - - if static then - configuration "Debug" targetsuffix "sd" - configuration "Release" targetsuffix "s" - else - configuration "Debug" targetsuffix "d" - end -else - if _ACTION == "xcode3" then - platforms "universal" - end - - configurations { "Debug", "Release" } - - configuration "Debug" targetsuffix "d" -end - -project "pugixml" - kind "StaticLib" - language "C++" - files { "../src/pugixml.hpp", "../src/pugiconfig.hpp", "../src/pugixml.cpp" } - flags { "NoPCH", "NoMinimalRebuild", "NoEditAndContinue", "Symbols" } - uuid "89A1E353-E2DC-495C-B403-742BE206ACED" - -configuration "Debug" - defines { "_DEBUG" } - -configuration "Release" - defines { "NDEBUG" } - flags { "Optimize" } - -if static then - configuration "*" - flags { "StaticRuntime" } -end diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/pugixml-config.cmake.in --- a/dep/pugixml/scripts/pugixml-config.cmake.in Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,12 +0,0 @@ -@PACKAGE_INIT@ - -include("${CMAKE_CURRENT_LIST_DIR}/pugixml-targets.cmake") - -# If the user is not requiring 1.11 (either by explicitly requesting an older -# version or not requesting one at all), provide the old imported target name -# for compatibility. -if (NOT TARGET pugixml AND (NOT DEFINED PACKAGE_FIND_VERSION OR PACKAGE_FIND_VERSION VERSION_LESS "1.11")) - add_library(pugixml INTERFACE IMPORTED) - # Equivalent to target_link_libraries INTERFACE, but compatible with CMake 3.10 - set_target_properties(pugixml PROPERTIES INTERFACE_LINK_LIBRARIES pugixml::pugixml) -endif () diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/pugixml.pc.in --- a/dep/pugixml/scripts/pugixml.pc.in Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,11 +0,0 @@ -prefix=@CMAKE_INSTALL_PREFIX@ -exec_prefix=${prefix} -includedir=@CMAKE_INSTALL_FULL_INCLUDEDIR@@INSTALL_SUFFIX@ -libdir=@CMAKE_INSTALL_FULL_LIBDIR@@INSTALL_SUFFIX@ - -Name: pugixml -Description: Light-weight, simple and fast XML parser for C++ with XPath support. -URL: https://pugixml.org/ -Version: @pugixml_VERSION@ -Cflags: -I${includedir} -Libs: -L${libdir} -lpugixml@LIB_POSTFIX@ diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/pugixml.podspec --- a/dep/pugixml/scripts/pugixml.podspec Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,14 +0,0 @@ -Pod::Spec.new do |s| - s.name = "pugixml" - s.version = "1.14" - s.summary = "C++ XML parser library." - s.homepage = "https://pugixml.org" - s.license = "MIT" - s.author = { "Arseny Kapoulkine" => "arseny.kapoulkine@gmail.com" } - s.platform = :ios, "7.0" - - s.source = { :git => "https://github.com/zeux/pugixml.git", :tag => "v" + s.version.to_s } - - s.source_files = "src/**/*.{hpp,cpp}" - s.header_mappings_dir = "src" -end diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/pugixml.xcodeproj/project.pbxproj --- a/dep/pugixml/scripts/pugixml.xcodeproj/project.pbxproj Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,212 +0,0 @@ -// !$*UTF8*$! -{ - archiveVersion = 1; - classes = { - }; - objectVersion = 45; - objects = { - -/* Begin PBXBuildFile section */ - 0424128F67AB5C730232235E /* pugixml.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 47481C4F0E03673E0E780637 /* pugixml.cpp */; }; -/* End PBXBuildFile section */ - -/* Begin PBXFileReference section */ - 0B66463C5F896E6449051D38 /* pugiconfig.hpp */ = {isa = PBXFileReference; lastKnownFileType = text; name = "pugiconfig.hpp"; path = "pugiconfig.hpp"; sourceTree = ""; }; - 47481C4F0E03673E0E780637 /* pugixml.cpp */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.cpp.cpp; name = "pugixml.cpp"; path = "pugixml.cpp"; sourceTree = ""; }; - 6C911F0460FC44CD3B1B5624 /* pugixml.hpp */ = {isa = PBXFileReference; lastKnownFileType = text; name = "pugixml.hpp"; path = "pugixml.hpp"; sourceTree = ""; }; - 1DA04ADC64C3566D16C45B6D /* libpugixmld.a */ = {isa = PBXFileReference; explicitFileType = archive.ar; includeInIndex = 0; name = "libpugixmld.a"; path = "libpugixmld.a"; sourceTree = BUILT_PRODUCTS_DIR; }; -/* End PBXFileReference section */ - -/* Begin PBXFrameworksBuildPhase section */ - 2BA00212518037166623673F /* Frameworks */ = { - isa = PBXFrameworksBuildPhase; - buildActionMask = 2147483647; - files = ( - ); - runOnlyForDeploymentPostprocessing = 0; - }; -/* End PBXFrameworksBuildPhase section */ - -/* Begin PBXGroup section */ - 19E0517F3CF26ED63AE23641 /* pugixml */ = { - isa = PBXGroup; - children = ( - 578963B4309E714F05E01D71 /* src */, - 219F66186DDF392149043810 /* Products */, - ); - name = "pugixml"; - sourceTree = ""; - }; - 578963B4309E714F05E01D71 /* src */ = { - isa = PBXGroup; - children = ( - 0B66463C5F896E6449051D38 /* pugiconfig.hpp */, - 47481C4F0E03673E0E780637 /* pugixml.cpp */, - 6C911F0460FC44CD3B1B5624 /* pugixml.hpp */, - ); - name = "src"; - path = ../src; - sourceTree = ""; - }; - 219F66186DDF392149043810 /* Products */ = { - isa = PBXGroup; - children = ( - 1DA04ADC64C3566D16C45B6D /* libpugixmld.a */, - ); - name = "Products"; - sourceTree = ""; - }; -/* End PBXGroup section */ - -/* Begin PBXNativeTarget section */ - 6B55152571905B6C3A6F39D0 /* pugixml */ = { - isa = PBXNativeTarget; - buildConfigurationList = 73BF376C14AA1ECC0AC517ED /* Build configuration list for PBXNativeTarget "pugixml" */; - buildPhases = ( - 6CA66B9B6252229A36E8733C /* Resources */, - 287808486FBF545206A47CC1 /* Sources */, - 2BA00212518037166623673F /* Frameworks */, - ); - buildRules = ( - ); - dependencies = ( - ); - name = "pugixml"; - productName = "pugixml"; - productReference = 1DA04ADC64C3566D16C45B6D /* libpugixmld.a */; - productType = "com.apple.product-type.library.static"; - }; -/* End PBXNativeTarget section */ - -/* Begin PBXProject section */ - 08FB7793FE84155DC02AAC07 /* Project object */ = { - isa = PBXProject; - buildConfigurationList = 1DEB928908733DD80010E9CD /* Build configuration list for PBXProject "pugixml" */; - compatibilityVersion = "Xcode 3.1"; - hasScannedForEncodings = 1; - mainGroup = 19E0517F3CF26ED63AE23641 /* pugixml */; - projectDirPath = ""; - projectRoot = ""; - targets = ( - 6B55152571905B6C3A6F39D0 /* libpugixmld.a */, - ); - }; -/* End PBXProject section */ - -/* Begin PBXResourcesBuildPhase section */ - 6CA66B9B6252229A36E8733C /* Resources */ = { - isa = PBXResourcesBuildPhase; - buildActionMask = 2147483647; - files = ( - ); - runOnlyForDeploymentPostprocessing = 0; - }; -/* End PBXResourcesBuildPhase section */ - -/* Begin PBXSourcesBuildPhase section */ - 287808486FBF545206A47CC1 /* Sources */ = { - isa = PBXSourcesBuildPhase; - buildActionMask = 2147483647; - files = ( - 0424128F67AB5C730232235E /* pugixml.cpp in Sources */, - ); - runOnlyForDeploymentPostprocessing = 0; - }; -/* End PBXSourcesBuildPhase section */ - -/* Begin PBXVariantGroup section */ -/* End PBXVariantGroup section */ - -/* Begin XCBuildConfiguration section */ - 4FDB54E4253E36FC55CE27E8 /* Debug */ = { - isa = XCBuildConfiguration; - buildSettings = { - ALWAYS_SEARCH_USER_PATHS = NO; - CONFIGURATION_BUILD_DIR = xcode3; - GCC_DYNAMIC_NO_PIC = NO; - GCC_MODEL_TUNING = G5; - INSTALL_PATH = /usr/local/lib; - PRODUCT_NAME = "pugixmld"; - }; - name = "Debug"; - }; - 0A4C28F553990E0405306C15 /* Release */ = { - isa = XCBuildConfiguration; - buildSettings = { - ALWAYS_SEARCH_USER_PATHS = NO; - CONFIGURATION_BUILD_DIR = xcode3; - GCC_DYNAMIC_NO_PIC = NO; - GCC_MODEL_TUNING = G5; - INSTALL_PATH = /usr/local/lib; - PRODUCT_NAME = "pugixml"; - }; - name = "Release"; - }; - 65DB0F6D27EA20852B6E3BB4 /* Debug */ = { - isa = XCBuildConfiguration; - buildSettings = { - ARCHS = "$(ARCHS_STANDARD_32_64_BIT)"; - CONFIGURATION_BUILD_DIR = "$(SYMROOT)"; - CONFIGURATION_TEMP_DIR = "$(OBJROOT)"; - COPY_PHASE_STRIP = NO; - GCC_C_LANGUAGE_STANDARD = gnu99; - GCC_OPTIMIZATION_LEVEL = 0; - GCC_PREPROCESSOR_DEFINITIONS = ( - "_DEBUG", - ); - GCC_WARN_ABOUT_RETURN_TYPE = YES; - GCC_WARN_UNUSED_VARIABLE = YES; - OBJROOT = "xcode3/Universal/Debug"; - ONLY_ACTIVE_ARCH = NO; - PREBINDING = NO; - SYMROOT = "xcode3"; - }; - name = "Debug"; - }; - 5314084032B57C1A11945858 /* Release */ = { - isa = XCBuildConfiguration; - buildSettings = { - ARCHS = "$(ARCHS_STANDARD_32_64_BIT)"; - CONFIGURATION_BUILD_DIR = "$(SYMROOT)"; - CONFIGURATION_TEMP_DIR = "$(OBJROOT)"; - COPY_PHASE_STRIP = NO; - GCC_C_LANGUAGE_STANDARD = gnu99; - GCC_OPTIMIZATION_LEVEL = s; - GCC_PREPROCESSOR_DEFINITIONS = ( - "NDEBUG", - ); - GCC_WARN_ABOUT_RETURN_TYPE = YES; - GCC_WARN_UNUSED_VARIABLE = YES; - OBJROOT = "xcode3/Universal/Release"; - ONLY_ACTIVE_ARCH = NO; - PREBINDING = NO; - SYMROOT = "xcode3"; - }; - name = "Release"; - }; -/* End XCBuildConfiguration section */ - -/* Begin XCConfigurationList section */ - 73BF376C14AA1ECC0AC517ED /* Build configuration list for PBXNativeTarget "libpugixmld.a" */ = { - isa = XCConfigurationList; - buildConfigurations = ( - 4FDB54E4253E36FC55CE27E8 /* Debug */, - 0A4C28F553990E0405306C15 /* Release */, - ); - defaultConfigurationIsVisible = 0; - defaultConfigurationName = "Debug"; - }; - 1DEB928908733DD80010E9CD /* Build configuration list for PBXProject "pugixml" */ = { - isa = XCConfigurationList; - buildConfigurations = ( - 65DB0F6D27EA20852B6E3BB4 /* Debug */, - 5314084032B57C1A11945858 /* Release */, - ); - defaultConfigurationIsVisible = 0; - defaultConfigurationName = "Debug"; - }; -/* End XCConfigurationList section */ - - }; - rootObject = 08FB7793FE84155DC02AAC07 /* Project object */; -} diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/pugixml_airplay.mkf --- a/dep/pugixml/scripts/pugixml_airplay.mkf Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,13 +0,0 @@ -includepaths -{ -"../src" -} - -files -{ -("../src") -pugiconfig.hpp -pugixml.cpp -pugixml.hpp -} - diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/pugixml_codeblocks.cbp --- a/dep/pugixml/scripts/pugixml_codeblocks.cbp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,44 +0,0 @@ - - - - - - - diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/pugixml_codelite.project --- a/dep/pugixml/scripts/pugixml_codelite.project Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,56 +0,0 @@ - - - - - - - - - - - - - - - - - - - - - - None - - - - - - - - - - - - - - - - - - - - - None - - - - - - - - - - - - - diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/pugixml_dll.rc --- a/dep/pugixml/scripts/pugixml_dll.rc Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,45 +0,0 @@ -#include - -#define PUGIXML_VERSION_MAJOR 1 -#define PUGIXML_VERSION_MINOR 14 -#define PUGIXML_VERSION_PATCH 0 -#define PUGIXML_VERSION_NUMBER "1.14.0\0" - -#if defined(GCC_WINDRES) || defined(__MINGW32__) || defined(__CYGWIN__) -VS_VERSION_INFO VERSIONINFO -#else -VS_VERSION_INFO VERSIONINFO MOVEABLE IMPURE LOADONCALL DISCARDABLE -#endif - FILEVERSION PUGIXML_VERSION_MAJOR,PUGIXML_VERSION_MINOR,PUGIXML_VERSION_PATCH,0 - PRODUCTVERSION PUGIXML_VERSION_MAJOR,PUGIXML_VERSION_MINOR,PUGIXML_VERSION_PATCH,0 - FILEFLAGSMASK VS_FFI_FILEFLAGSMASK -#ifdef _DEBUG - FILEFLAGS 1 -#else - FILEFLAGS 0 -#endif - FILEOS VOS__WINDOWS32 - FILETYPE VFT_DLL - FILESUBTYPE 0 // not used -BEGIN - BLOCK "StringFileInfo" - BEGIN - BLOCK "040904E4" - //language ID = U.S. English, char set = Windows, Multilingual - BEGIN - VALUE "CompanyName", "zeux/pugixml\0" - VALUE "FileDescription", "pugixml library\0" - VALUE "FileVersion", PUGIXML_VERSION_NUMBER - VALUE "InternalName", "pugixml.dll\0" - VALUE "LegalCopyright", "Copyright (C) 2006-2023, by Arseny Kapoulkine\0" - VALUE "OriginalFilename", "pugixml.dll\0" - VALUE "ProductName", "pugixml\0" - VALUE "ProductVersion", PUGIXML_VERSION_NUMBER - VALUE "Comments", "For more information visit https://github.com/zeux/pugixml/\0" - END - END - BLOCK "VarFileInfo" - BEGIN - VALUE "Translation", 0x0409, 1252 - END -END diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/pugixml_vs2005.vcproj --- a/dep/pugixml/scripts/pugixml_vs2005.vcproj Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,343 +0,0 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/pugixml_vs2005_static.vcproj --- a/dep/pugixml/scripts/pugixml_vs2005_static.vcproj Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,343 +0,0 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/pugixml_vs2008.vcproj --- a/dep/pugixml/scripts/pugixml_vs2008.vcproj Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,339 +0,0 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/pugixml_vs2008_static.vcproj --- a/dep/pugixml/scripts/pugixml_vs2008_static.vcproj Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,339 +0,0 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/pugixml_vs2010.vcxproj --- a/dep/pugixml/scripts/pugixml_vs2010.vcxproj Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,191 +0,0 @@ - - - - - Debug - Win32 - - - Debug - x64 - - - Release - Win32 - - - Release - x64 - - - - {89A1E353-E2DC-495C-B403-742BE206ACED} - pugixml - Win32Proj - - - - StaticLibrary - MultiByte - true - - - StaticLibrary - MultiByte - true - - - StaticLibrary - MultiByte - true - false - - - StaticLibrary - MultiByte - true - false - - - - - - - - - - - - - - - - - - - <_ProjectFileVersion>10.0.30319.1 - vs2010\Win32_Debug\ - vs2010\Win32_Debug\ - pugixml - vs2010\x64_Debug\ - vs2010\x64_Debug\ - pugixml - vs2010\Win32_Release\ - vs2010\Win32_Release\ - pugixml - vs2010\x64_Release\ - vs2010\x64_Release\ - pugixml - - - - Disabled - _DEBUG;%(PreprocessorDefinitions) - false - EnableFastChecks - MultiThreadedDebugDLL - true - - Level3 - ProgramDatabase - - - _DEBUG;%(PreprocessorDefinitions) - - - $(OutDir)pugixml.lib - - - Windows - true - $(OutDir)pugixml.pdb - - - - - Disabled - _DEBUG;%(PreprocessorDefinitions) - false - EnableFastChecks - MultiThreadedDebugDLL - true - - Level3 - ProgramDatabase - - - _DEBUG;%(PreprocessorDefinitions) - - - $(OutDir)pugixml.lib - - - Windows - true - $(OutDir)pugixml.pdb - - - - - Full - NDEBUG;%(PreprocessorDefinitions) - false - true - MultiThreadedDLL - true - - Level3 - ProgramDatabase - - - NDEBUG;%(PreprocessorDefinitions) - - - $(OutDir)pugixml.lib - - - Windows - true - true - true - $(OutDir)pugixml.pdb - - - - - Full - NDEBUG;%(PreprocessorDefinitions) - false - true - MultiThreadedDLL - true - - Level3 - ProgramDatabase - - - NDEBUG;%(PreprocessorDefinitions) - - - $(OutDir)pugixml.lib - - - Windows - true - true - true - $(OutDir)pugixml.pdb - - - - - - - - - - - - - - diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/pugixml_vs2010_static.vcxproj --- a/dep/pugixml/scripts/pugixml_vs2010_static.vcxproj Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,191 +0,0 @@ - - - - - Debug - Win32 - - - Debug - x64 - - - Release - Win32 - - - Release - x64 - - - - {89A1E353-E2DC-495C-B403-742BE206ACED} - pugixml - Win32Proj - - - - StaticLibrary - MultiByte - true - - - StaticLibrary - MultiByte - true - - - StaticLibrary - MultiByte - true - false - - - StaticLibrary - MultiByte - true - false - - - - - - - - - - - - - - - - - - - <_ProjectFileVersion>10.0.30319.1 - vs2010\Win32_DebugStatic\ - vs2010\Win32_DebugStatic\ - pugixml - vs2010\x64_DebugStatic\ - vs2010\x64_DebugStatic\ - pugixml - vs2010\Win32_ReleaseStatic\ - vs2010\Win32_ReleaseStatic\ - pugixml - vs2010\x64_ReleaseStatic\ - vs2010\x64_ReleaseStatic\ - pugixml - - - - Disabled - _DEBUG;%(PreprocessorDefinitions) - false - EnableFastChecks - MultiThreadedDebug - true - - Level3 - ProgramDatabase - - - _DEBUG;%(PreprocessorDefinitions) - - - $(OutDir)pugixml.lib - - - Windows - true - $(OutDir)pugixml.pdb - - - - - Disabled - _DEBUG;%(PreprocessorDefinitions) - false - EnableFastChecks - MultiThreadedDebug - true - - Level3 - ProgramDatabase - - - _DEBUG;%(PreprocessorDefinitions) - - - $(OutDir)pugixml.lib - - - Windows - true - $(OutDir)pugixml.pdb - - - - - Full - NDEBUG;%(PreprocessorDefinitions) - false - true - MultiThreaded - true - - Level3 - ProgramDatabase - - - NDEBUG;%(PreprocessorDefinitions) - - - $(OutDir)pugixml.lib - - - Windows - true - true - true - $(OutDir)pugixml.pdb - - - - - Full - NDEBUG;%(PreprocessorDefinitions) - false - true - MultiThreaded - true - - Level3 - ProgramDatabase - - - NDEBUG;%(PreprocessorDefinitions) - - - $(OutDir)pugixml.lib - - - Windows - true - true - true - $(OutDir)pugixml.pdb - - - - - - - - - - - - - - diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/pugixml_vs2013.vcxproj --- a/dep/pugixml/scripts/pugixml_vs2013.vcxproj Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,199 +0,0 @@ - - - - - Debug - Win32 - - - Debug - x64 - - - Release - Win32 - - - Release - x64 - - - - {89A1E353-E2DC-495C-B403-742BE206ACED} - pugixml - Win32Proj - - - - StaticLibrary - MultiByte - true - v120 - - - StaticLibrary - MultiByte - true - v120 - - - StaticLibrary - MultiByte - true - false - v120 - - - StaticLibrary - MultiByte - true - false - v120 - - - - - - - - - - - - - - - - - - - <_ProjectFileVersion>10.0.30319.1 - vs2013\Win32_Debug\ - vs2013\Win32_Debug\ - pugixml - vs2013\x64_Debug\ - vs2013\x64_Debug\ - pugixml - vs2013\Win32_Release\ - vs2013\Win32_Release\ - pugixml - vs2013\x64_Release\ - vs2013\x64_Release\ - pugixml - - - - Disabled - _DEBUG;%(PreprocessorDefinitions) - false - EnableFastChecks - MultiThreadedDebugDLL - true - - - Level3 - OldStyle - - - _DEBUG;%(PreprocessorDefinitions) - - - $(OutDir)pugixml.lib - - - Windows - true - $(OutDir)pugixml.pdb - - - - - Disabled - _DEBUG;%(PreprocessorDefinitions) - false - EnableFastChecks - MultiThreadedDebugDLL - true - - - Level3 - OldStyle - - - _DEBUG;%(PreprocessorDefinitions) - - - $(OutDir)pugixml.lib - - - Windows - true - $(OutDir)pugixml.pdb - - - - - Full - NDEBUG;%(PreprocessorDefinitions) - false - true - MultiThreadedDLL - true - - - Level3 - OldStyle - - - NDEBUG;%(PreprocessorDefinitions) - - - $(OutDir)pugixml.lib - - - Windows - true - true - true - $(OutDir)pugixml.pdb - - - - - Full - NDEBUG;%(PreprocessorDefinitions) - false - true - MultiThreadedDLL - true - - - Level3 - OldStyle - - - NDEBUG;%(PreprocessorDefinitions) - - - $(OutDir)pugixml.lib - - - Windows - true - true - true - $(OutDir)pugixml.pdb - - - - - - - - - - - - - - diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/pugixml_vs2013_static.vcxproj --- a/dep/pugixml/scripts/pugixml_vs2013_static.vcxproj Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,199 +0,0 @@ - - - - - Debug - Win32 - - - Debug - x64 - - - Release - Win32 - - - Release - x64 - - - - {89A1E353-E2DC-495C-B403-742BE206ACED} - pugixml - Win32Proj - - - - StaticLibrary - MultiByte - true - v120 - - - StaticLibrary - MultiByte - true - v120 - - - StaticLibrary - MultiByte - true - false - v120 - - - StaticLibrary - MultiByte - true - false - v120 - - - - - - - - - - - - - - - - - - - <_ProjectFileVersion>10.0.30319.1 - vs2013\Win32_DebugStatic\ - vs2013\Win32_DebugStatic\ - pugixml - vs2013\x64_DebugStatic\ - vs2013\x64_DebugStatic\ - pugixml - vs2013\Win32_ReleaseStatic\ - vs2013\Win32_ReleaseStatic\ - pugixml - vs2013\x64_ReleaseStatic\ - vs2013\x64_ReleaseStatic\ - pugixml - - - - Disabled - _DEBUG;%(PreprocessorDefinitions) - false - EnableFastChecks - MultiThreadedDebug - true - - - Level3 - OldStyle - - - _DEBUG;%(PreprocessorDefinitions) - - - $(OutDir)pugixml.lib - - - Windows - true - $(OutDir)pugixml.pdb - - - - - Disabled - _DEBUG;%(PreprocessorDefinitions) - false - EnableFastChecks - MultiThreadedDebug - true - - - Level3 - OldStyle - - - _DEBUG;%(PreprocessorDefinitions) - - - $(OutDir)pugixml.lib - - - Windows - true - $(OutDir)pugixml.pdb - - - - - Full - NDEBUG;%(PreprocessorDefinitions) - false - true - MultiThreaded - true - - - Level3 - OldStyle - - - NDEBUG;%(PreprocessorDefinitions) - - - $(OutDir)pugixml.lib - - - Windows - true - true - true - $(OutDir)pugixml.pdb - - - - - Full - NDEBUG;%(PreprocessorDefinitions) - false - true - MultiThreaded - true - - - Level3 - OldStyle - - - NDEBUG;%(PreprocessorDefinitions) - - - $(OutDir)pugixml.lib - - - Windows - true - true - true - $(OutDir)pugixml.pdb - - - - - - - - - - - - - - diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/pugixml_vs2015.vcxproj --- a/dep/pugixml/scripts/pugixml_vs2015.vcxproj Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,172 +0,0 @@ - - - - - Debug - Win32 - - - Release - Win32 - - - Debug - x64 - - - Release - x64 - - - - {07CF01C0-B887-499D-AD9C-799CB6A9FE64} - Win32Proj - pugixml - 8.1 - - - - StaticLibrary - true - v140 - Unicode - - - StaticLibrary - false - v140 - true - Unicode - - - StaticLibrary - true - v140 - Unicode - - - StaticLibrary - false - v140 - true - Unicode - - - - - - - - - - - - - - - - - - - - - vs2015\$(Platform)_$(Configuration)\ - vs2015\$(Platform)_$(Configuration)\ - pugixml - - - vs2015\$(Platform)_$(Configuration)\ - vs2015\$(Platform)_$(Configuration)\ - pugixml - - - vs2015\$(Platform)_$(Configuration)\ - vs2015\$(Platform)_$(Configuration)\ - pugixml - - - vs2015\$(Platform)_$(Configuration)\ - vs2015\$(Platform)_$(Configuration)\ - pugixml - - - - - - Level3 - Disabled - WIN32;_DEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - false - - - Windows - true - - - - - - - Level3 - Disabled - _DEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - false - - - Windows - true - - - - - Level3 - - - MaxSpeed - true - true - WIN32;NDEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - - - Windows - true - true - true - - - - - Level3 - - - MaxSpeed - true - true - NDEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - - - Windows - true - true - true - - - - - - - - - - - - - \ No newline at end of file diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/pugixml_vs2015_static.vcxproj --- a/dep/pugixml/scripts/pugixml_vs2015_static.vcxproj Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,176 +0,0 @@ - - - - - Debug - Win32 - - - Release - Win32 - - - Debug - x64 - - - Release - x64 - - - - {07CF01C0-B887-499D-AD9C-799CB6A9FE64} - Win32Proj - pugixml - 8.1 - - - - StaticLibrary - true - v140 - Unicode - - - StaticLibrary - false - v140 - true - Unicode - - - StaticLibrary - true - v140 - Unicode - - - StaticLibrary - false - v140 - true - Unicode - - - - - - - - - - - - - - - - - - - - - vs2015\$(Platform)_$(Configuration)Static\ - vs2015\$(Platform)_$(Configuration)Static\ - pugixml - - - vs2015\$(Platform)_$(Configuration)Static\ - vs2015\$(Platform)_$(Configuration)Static\ - pugixml - - - vs2015\$(Platform)_$(Configuration)Static\ - vs2015\$(Platform)_$(Configuration)Static\ - pugixml - - - vs2015\$(Platform)_$(Configuration)Static\ - vs2015\$(Platform)_$(Configuration)Static\ - pugixml - - - - - - Level3 - Disabled - WIN32;_DEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - false - MultiThreadedDebug - - - Windows - true - - - - - - - Level3 - Disabled - _DEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - false - MultiThreadedDebug - - - Windows - true - - - - - Level3 - - - MaxSpeed - true - true - WIN32;NDEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - MultiThreaded - - - Windows - true - true - true - - - - - Level3 - - - MaxSpeed - true - true - NDEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - MultiThreaded - - - Windows - true - true - true - - - - - - - - - - - - - diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/pugixml_vs2017.vcxproj --- a/dep/pugixml/scripts/pugixml_vs2017.vcxproj Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,172 +0,0 @@ - - - - - Debug - Win32 - - - Release - Win32 - - - Debug - x64 - - - Release - x64 - - - - {07CF01C0-B887-499D-AD9C-799CB6A9FE64} - Win32Proj - pugixml - 8.1 - - - - StaticLibrary - true - v141 - Unicode - - - StaticLibrary - false - v141 - false - Unicode - - - StaticLibrary - true - v141 - Unicode - - - StaticLibrary - false - v141 - false - Unicode - - - - - - - - - - - - - - - - - - - - - vs2017\$(Platform)_$(Configuration)\ - vs2017\$(Platform)_$(Configuration)\ - pugixml - - - vs2017\$(Platform)_$(Configuration)\ - vs2017\$(Platform)_$(Configuration)\ - pugixml - - - vs2017\$(Platform)_$(Configuration)\ - vs2017\$(Platform)_$(Configuration)\ - pugixml - - - vs2017\$(Platform)_$(Configuration)\ - vs2017\$(Platform)_$(Configuration)\ - pugixml - - - - - - Level3 - Disabled - WIN32;_DEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - false - - - Windows - true - - - - - - - Level3 - Disabled - _DEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - false - - - Windows - true - - - - - Level3 - - - MaxSpeed - true - true - WIN32;NDEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - - - Windows - true - true - true - - - - - Level3 - - - MaxSpeed - true - true - NDEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - - - Windows - true - true - true - - - - - - - - - - - - - diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/pugixml_vs2017_static.vcxproj --- a/dep/pugixml/scripts/pugixml_vs2017_static.vcxproj Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,176 +0,0 @@ - - - - - Debug - Win32 - - - Release - Win32 - - - Debug - x64 - - - Release - x64 - - - - {07CF01C0-B887-499D-AD9C-799CB6A9FE64} - Win32Proj - pugixml - 8.1 - - - - StaticLibrary - true - v141 - Unicode - - - StaticLibrary - false - v141 - false - Unicode - - - StaticLibrary - true - v141 - Unicode - - - StaticLibrary - false - v141 - false - Unicode - - - - - - - - - - - - - - - - - - - - - vs2017\$(Platform)_$(Configuration)Static\ - vs2017\$(Platform)_$(Configuration)Static\ - pugixml - - - vs2017\$(Platform)_$(Configuration)Static\ - vs2017\$(Platform)_$(Configuration)Static\ - pugixml - - - vs2017\$(Platform)_$(Configuration)Static\ - vs2017\$(Platform)_$(Configuration)Static\ - pugixml - - - vs2017\$(Platform)_$(Configuration)Static\ - vs2017\$(Platform)_$(Configuration)Static\ - pugixml - - - - - - Level3 - Disabled - WIN32;_DEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - false - MultiThreadedDebug - - - Windows - true - - - - - - - Level3 - Disabled - _DEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - false - MultiThreadedDebug - - - Windows - true - - - - - Level3 - - - MaxSpeed - true - true - WIN32;NDEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - MultiThreaded - - - Windows - true - true - true - - - - - Level3 - - - MaxSpeed - true - true - NDEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - MultiThreaded - - - Windows - true - true - true - - - - - - - - - - - - - diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/pugixml_vs2019.vcxproj --- a/dep/pugixml/scripts/pugixml_vs2019.vcxproj Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,172 +0,0 @@ - - - - - Debug - Win32 - - - Release - Win32 - - - Debug - x64 - - - Release - x64 - - - - {07CF01C0-B887-499D-AD9C-799CB6A9FE64} - Win32Proj - pugixml - 10.0 - - - - StaticLibrary - true - v142 - Unicode - - - StaticLibrary - false - v142 - false - Unicode - - - StaticLibrary - true - v142 - Unicode - - - StaticLibrary - false - v142 - false - Unicode - - - - - - - - - - - - - - - - - - - - - vs2019\$(Platform)_$(Configuration)\ - vs2019\$(Platform)_$(Configuration)\ - pugixml - - - vs2019\$(Platform)_$(Configuration)\ - vs2019\$(Platform)_$(Configuration)\ - pugixml - - - vs2019\$(Platform)_$(Configuration)\ - vs2019\$(Platform)_$(Configuration)\ - pugixml - - - vs2019\$(Platform)_$(Configuration)\ - vs2019\$(Platform)_$(Configuration)\ - pugixml - - - - - - Level3 - Disabled - WIN32;_DEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - false - - - Windows - true - - - - - - - Level3 - Disabled - _DEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - false - - - Windows - true - - - - - Level3 - - - MaxSpeed - true - true - WIN32;NDEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - - - Windows - true - true - true - - - - - Level3 - - - MaxSpeed - true - true - NDEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - - - Windows - true - true - true - - - - - - - - - - - - - diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/pugixml_vs2019_static.vcxproj --- a/dep/pugixml/scripts/pugixml_vs2019_static.vcxproj Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,176 +0,0 @@ - - - - - Debug - Win32 - - - Release - Win32 - - - Debug - x64 - - - Release - x64 - - - - {07CF01C0-B887-499D-AD9C-799CB6A9FE64} - Win32Proj - pugixml - 10.0 - - - - StaticLibrary - true - v142 - Unicode - - - StaticLibrary - false - v142 - false - Unicode - - - StaticLibrary - true - v142 - Unicode - - - StaticLibrary - false - v142 - false - Unicode - - - - - - - - - - - - - - - - - - - - - vs2019\$(Platform)_$(Configuration)Static\ - vs2019\$(Platform)_$(Configuration)Static\ - pugixml - - - vs2019\$(Platform)_$(Configuration)Static\ - vs2019\$(Platform)_$(Configuration)Static\ - pugixml - - - vs2019\$(Platform)_$(Configuration)Static\ - vs2019\$(Platform)_$(Configuration)Static\ - pugixml - - - vs2019\$(Platform)_$(Configuration)Static\ - vs2019\$(Platform)_$(Configuration)Static\ - pugixml - - - - - - Level3 - Disabled - WIN32;_DEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - false - MultiThreadedDebug - - - Windows - true - - - - - - - Level3 - Disabled - _DEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - false - MultiThreadedDebug - - - Windows - true - - - - - Level3 - - - MaxSpeed - true - true - WIN32;NDEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - MultiThreaded - - - Windows - true - true - true - - - - - Level3 - - - MaxSpeed - true - true - NDEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - MultiThreaded - - - Windows - true - true - true - - - - - - - - - - - - - diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/pugixml_vs2022.vcxproj --- a/dep/pugixml/scripts/pugixml_vs2022.vcxproj Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,172 +0,0 @@ - - - - - Debug - Win32 - - - Release - Win32 - - - Debug - x64 - - - Release - x64 - - - - {07CF01C0-B887-499D-AD9C-799CB6A9FE64} - Win32Proj - pugixml - 10.0 - - - - StaticLibrary - true - v143 - Unicode - - - StaticLibrary - false - v143 - false - Unicode - - - StaticLibrary - true - v143 - Unicode - - - StaticLibrary - false - v143 - false - Unicode - - - - - - - - - - - - - - - - - - - - - vs2022\$(Platform)_$(Configuration)\ - vs2022\$(Platform)_$(Configuration)\ - pugixml - - - vs2022\$(Platform)_$(Configuration)\ - vs2022\$(Platform)_$(Configuration)\ - pugixml - - - vs2022\$(Platform)_$(Configuration)\ - vs2022\$(Platform)_$(Configuration)\ - pugixml - - - vs2022\$(Platform)_$(Configuration)\ - vs2022\$(Platform)_$(Configuration)\ - pugixml - - - - - - Level3 - Disabled - WIN32;_DEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - false - - - Windows - true - - - - - - - Level3 - Disabled - _DEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - false - - - Windows - true - - - - - Level3 - - - MaxSpeed - true - true - WIN32;NDEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - - - Windows - true - true - true - - - - - Level3 - - - MaxSpeed - true - true - NDEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - - - Windows - true - true - true - - - - - - - - - - - - - diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/scripts/pugixml_vs2022_static.vcxproj --- a/dep/pugixml/scripts/pugixml_vs2022_static.vcxproj Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,176 +0,0 @@ - - - - - Debug - Win32 - - - Release - Win32 - - - Debug - x64 - - - Release - x64 - - - - {07CF01C0-B887-499D-AD9C-799CB6A9FE64} - Win32Proj - pugixml - 10.0 - - - - StaticLibrary - true - v143 - Unicode - - - StaticLibrary - false - v143 - false - Unicode - - - StaticLibrary - true - v143 - Unicode - - - StaticLibrary - false - v143 - false - Unicode - - - - - - - - - - - - - - - - - - - - - vs2022\$(Platform)_$(Configuration)Static\ - vs2022\$(Platform)_$(Configuration)Static\ - pugixml - - - vs2022\$(Platform)_$(Configuration)Static\ - vs2022\$(Platform)_$(Configuration)Static\ - pugixml - - - vs2022\$(Platform)_$(Configuration)Static\ - vs2022\$(Platform)_$(Configuration)Static\ - pugixml - - - vs2022\$(Platform)_$(Configuration)Static\ - vs2022\$(Platform)_$(Configuration)Static\ - pugixml - - - - - - Level3 - Disabled - WIN32;_DEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - false - MultiThreadedDebug - - - Windows - true - - - - - - - Level3 - Disabled - _DEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - false - MultiThreadedDebug - - - Windows - true - - - - - Level3 - - - MaxSpeed - true - true - WIN32;NDEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - MultiThreaded - - - Windows - true - true - true - - - - - Level3 - - - MaxSpeed - true - true - NDEBUG;_LIB;%(PreprocessorDefinitions) - $(IntDir)$(TargetName).pdb - OldStyle - MultiThreaded - - - Windows - true - true - true - - - - - - - - - - - - - diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/src/pugiconfig.hpp --- a/dep/pugixml/src/pugiconfig.hpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,77 +0,0 @@ -/** - * pugixml parser - version 1.14 - * -------------------------------------------------------- - * Copyright (C) 2006-2023, by Arseny Kapoulkine (arseny.kapoulkine@gmail.com) - * Report bugs and download new versions at https://pugixml.org/ - * - * This library is distributed under the MIT License. See notice at the end - * of this file. - * - * This work is based on the pugxml parser, which is: - * Copyright (C) 2003, by Kristen Wegner (kristen@tima.net) - */ - -#ifndef HEADER_PUGICONFIG_HPP -#define HEADER_PUGICONFIG_HPP - -// Uncomment this to enable wchar_t mode -// #define PUGIXML_WCHAR_MODE - -// Uncomment this to enable compact mode -// #define PUGIXML_COMPACT - -// Uncomment this to disable XPath -// #define PUGIXML_NO_XPATH - -// Uncomment this to disable STL -// #define PUGIXML_NO_STL - -// Uncomment this to disable exceptions -// #define PUGIXML_NO_EXCEPTIONS - -// Set this to control attributes for public classes/functions, i.e.: -// #define PUGIXML_API __declspec(dllexport) // to export all public symbols from DLL -// #define PUGIXML_CLASS __declspec(dllimport) // to import all classes from DLL -// #define PUGIXML_FUNCTION __fastcall // to set calling conventions to all public functions to fastcall -// In absence of PUGIXML_CLASS/PUGIXML_FUNCTION definitions PUGIXML_API is used instead - -// Tune these constants to adjust memory-related behavior -// #define PUGIXML_MEMORY_PAGE_SIZE 32768 -// #define PUGIXML_MEMORY_OUTPUT_STACK 10240 -// #define PUGIXML_MEMORY_XPATH_PAGE_SIZE 4096 - -// Tune this constant to adjust max nesting for XPath queries -// #define PUGIXML_XPATH_DEPTH_LIMIT 1024 - -// Uncomment this to switch to header-only version -// #define PUGIXML_HEADER_ONLY - -// Uncomment this to enable long long support -// #define PUGIXML_HAS_LONG_LONG - -#endif - -/** - * Copyright (c) 2006-2023 Arseny Kapoulkine - * - * Permission is hereby granted, free of charge, to any person - * obtaining a copy of this software and associated documentation - * files (the "Software"), to deal in the Software without - * restriction, including without limitation the rights to use, - * copy, modify, merge, publish, distribute, sublicense, and/or sell - * copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following - * conditions: - * - * The above copyright notice and this permission notice shall be - * included in all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES - * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT - * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, - * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - */ diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/src/pugixml.cpp --- a/dep/pugixml/src/pugixml.cpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,13226 +0,0 @@ -/** - * pugixml parser - version 1.14 - * -------------------------------------------------------- - * Copyright (C) 2006-2023, by Arseny Kapoulkine (arseny.kapoulkine@gmail.com) - * Report bugs and download new versions at https://pugixml.org/ - * - * This library is distributed under the MIT License. See notice at the end - * of this file. - * - * This work is based on the pugxml parser, which is: - * Copyright (C) 2003, by Kristen Wegner (kristen@tima.net) - */ - -#ifndef SOURCE_PUGIXML_CPP -#define SOURCE_PUGIXML_CPP - -#include "pugixml.hpp" - -#include -#include -#include -#include -#include - -#ifdef PUGIXML_WCHAR_MODE -# include -#endif - -#ifndef PUGIXML_NO_XPATH -# include -# include -#endif - -#ifndef PUGIXML_NO_STL -# include -# include -# include -#endif - -// For placement new -#include - -// For load_file -#if defined(__linux__) || defined(__APPLE__) -#include -#endif - -#ifdef _MSC_VER -# pragma warning(push) -# pragma warning(disable: 4127) // conditional expression is constant -# pragma warning(disable: 4324) // structure was padded due to __declspec(align()) -# pragma warning(disable: 4702) // unreachable code -# pragma warning(disable: 4996) // this function or variable may be unsafe -#endif - -#if defined(_MSC_VER) && defined(__c2__) -# pragma clang diagnostic push -# pragma clang diagnostic ignored "-Wdeprecated" // this function or variable may be unsafe -#endif - -#ifdef __INTEL_COMPILER -# pragma warning(disable: 177) // function was declared but never referenced -# pragma warning(disable: 279) // controlling expression is constant -# pragma warning(disable: 1478 1786) // function was declared "deprecated" -# pragma warning(disable: 1684) // conversion from pointer to same-sized integral type -#endif - -#if defined(__BORLANDC__) && defined(PUGIXML_HEADER_ONLY) -# pragma warn -8080 // symbol is declared but never used; disabling this inside push/pop bracket does not make the warning go away -#endif - -#ifdef __BORLANDC__ -# pragma option push -# pragma warn -8008 // condition is always false -# pragma warn -8066 // unreachable code -#endif - -#ifdef __SNC__ -// Using diag_push/diag_pop does not disable the warnings inside templates due to a compiler bug -# pragma diag_suppress=178 // function was declared but never referenced -# pragma diag_suppress=237 // controlling expression is constant -#endif - -#ifdef __TI_COMPILER_VERSION__ -# pragma diag_suppress 179 // function was declared but never referenced -#endif - -// Inlining controls -#if defined(_MSC_VER) && _MSC_VER >= 1300 -# define PUGI_IMPL_NO_INLINE __declspec(noinline) -#elif defined(__GNUC__) -# define PUGI_IMPL_NO_INLINE __attribute__((noinline)) -#else -# define PUGI_IMPL_NO_INLINE -#endif - -// Branch weight controls -#if defined(__GNUC__) && !defined(__c2__) -# define PUGI_IMPL_UNLIKELY(cond) __builtin_expect(cond, 0) -#else -# define PUGI_IMPL_UNLIKELY(cond) (cond) -#endif - -// Simple static assertion -#define PUGI_IMPL_STATIC_ASSERT(cond) { static const char condition_failed[(cond) ? 1 : -1] = {0}; (void)condition_failed[0]; } - -// Digital Mars C++ bug workaround for passing char loaded from memory via stack -#ifdef __DMC__ -# define PUGI_IMPL_DMC_VOLATILE volatile -#else -# define PUGI_IMPL_DMC_VOLATILE -#endif - -// Integer sanitizer workaround; we only apply this for clang since gcc8 has no_sanitize but not unsigned-integer-overflow and produces "attribute directive ignored" warnings -#if defined(__clang__) && defined(__has_attribute) -# if __has_attribute(no_sanitize) -# define PUGI_IMPL_UNSIGNED_OVERFLOW __attribute__((no_sanitize("unsigned-integer-overflow"))) -# else -# define PUGI_IMPL_UNSIGNED_OVERFLOW -# endif -#else -# define PUGI_IMPL_UNSIGNED_OVERFLOW -#endif - -// Borland C++ bug workaround for not defining ::memcpy depending on header include order (can't always use std::memcpy because some compilers don't have it at all) -#if defined(__BORLANDC__) && !defined(__MEM_H_USING_LIST) -using std::memcpy; -using std::memmove; -using std::memset; -#endif - -// Old versions of GCC do not define ::malloc and ::free depending on header include order -#if defined(__GNUC__) && (__GNUC__ < 3 || (__GNUC__ == 3 && __GNUC_MINOR__ < 4)) -using std::malloc; -using std::free; -#endif - -// Some MinGW/GCC versions have headers that erroneously omit LLONG_MIN/LLONG_MAX/ULLONG_MAX definitions from limits.h in some configurations -#if defined(PUGIXML_HAS_LONG_LONG) && defined(__GNUC__) && !defined(LLONG_MAX) && !defined(LLONG_MIN) && !defined(ULLONG_MAX) -# define LLONG_MIN (-LLONG_MAX - 1LL) -# define LLONG_MAX __LONG_LONG_MAX__ -# define ULLONG_MAX (LLONG_MAX * 2ULL + 1ULL) -#endif - -// In some environments MSVC is a compiler but the CRT lacks certain MSVC-specific features -#if defined(_MSC_VER) && !defined(__S3E__) && !defined(_WIN32_WCE) -# define PUGI_IMPL_MSVC_CRT_VERSION _MSC_VER -#elif defined(_WIN32_WCE) -# define PUGI_IMPL_MSVC_CRT_VERSION 1310 // MSVC7.1 -#endif - -// Not all platforms have snprintf; we define a wrapper that uses snprintf if possible. This only works with buffers with a known size. -#if __cplusplus >= 201103 -# define PUGI_IMPL_SNPRINTF(buf, ...) snprintf(buf, sizeof(buf), __VA_ARGS__) -#elif defined(PUGI_IMPL_MSVC_CRT_VERSION) && PUGI_IMPL_MSVC_CRT_VERSION >= 1400 -# define PUGI_IMPL_SNPRINTF(buf, ...) _snprintf_s(buf, _countof(buf), _TRUNCATE, __VA_ARGS__) -#elif defined(__APPLE__) && __clang_major__ >= 14 // Xcode 14 marks sprintf as deprecated while still using C++98 by default -# define PUGI_IMPL_SNPRINTF(buf, fmt, arg1, arg2) snprintf(buf, sizeof(buf), fmt, arg1, arg2) -#else -# define PUGI_IMPL_SNPRINTF sprintf -#endif - -// We put implementation details into an anonymous namespace in source mode, but have to keep it in non-anonymous namespace in header-only mode to prevent binary bloat. -#ifdef PUGIXML_HEADER_ONLY -# define PUGI_IMPL_NS_BEGIN namespace pugi { namespace impl { -# define PUGI_IMPL_NS_END } } -# define PUGI_IMPL_FN inline -# define PUGI_IMPL_FN_NO_INLINE inline -#else -# if defined(_MSC_VER) && _MSC_VER < 1300 // MSVC6 seems to have an amusing bug with anonymous namespaces inside namespaces -# define PUGI_IMPL_NS_BEGIN namespace pugi { namespace impl { -# define PUGI_IMPL_NS_END } } -# else -# define PUGI_IMPL_NS_BEGIN namespace pugi { namespace impl { namespace { -# define PUGI_IMPL_NS_END } } } -# endif -# define PUGI_IMPL_FN -# define PUGI_IMPL_FN_NO_INLINE PUGI_IMPL_NO_INLINE -#endif - -// uintptr_t -#if (defined(_MSC_VER) && _MSC_VER < 1600) || (defined(__BORLANDC__) && __BORLANDC__ < 0x561) -namespace pugi -{ -# ifndef _UINTPTR_T_DEFINED - typedef size_t uintptr_t; -# endif - - typedef unsigned __int8 uint8_t; - typedef unsigned __int16 uint16_t; - typedef unsigned __int32 uint32_t; -} -#else -# include -#endif - -// Memory allocation -PUGI_IMPL_NS_BEGIN - PUGI_IMPL_FN void* default_allocate(size_t size) - { - return malloc(size); - } - - PUGI_IMPL_FN void default_deallocate(void* ptr) - { - free(ptr); - } - - template - struct xml_memory_management_function_storage - { - static allocation_function allocate; - static deallocation_function deallocate; - }; - - // Global allocation functions are stored in class statics so that in header mode linker deduplicates them - // Without a template<> we'll get multiple definitions of the same static - template allocation_function xml_memory_management_function_storage::allocate = default_allocate; - template deallocation_function xml_memory_management_function_storage::deallocate = default_deallocate; - - typedef xml_memory_management_function_storage xml_memory; -PUGI_IMPL_NS_END - -// String utilities -PUGI_IMPL_NS_BEGIN - // Get string length - PUGI_IMPL_FN size_t strlength(const char_t* s) - { - assert(s); - - #ifdef PUGIXML_WCHAR_MODE - return wcslen(s); - #else - return strlen(s); - #endif - } - - // Compare two strings - PUGI_IMPL_FN bool strequal(const char_t* src, const char_t* dst) - { - assert(src && dst); - - #ifdef PUGIXML_WCHAR_MODE - return wcscmp(src, dst) == 0; - #else - return strcmp(src, dst) == 0; - #endif - } - - // Compare lhs with [rhs_begin, rhs_end) - PUGI_IMPL_FN bool strequalrange(const char_t* lhs, const char_t* rhs, size_t count) - { - for (size_t i = 0; i < count; ++i) - if (lhs[i] != rhs[i]) - return false; - - return lhs[count] == 0; - } - - // Get length of wide string, even if CRT lacks wide character support - PUGI_IMPL_FN size_t strlength_wide(const wchar_t* s) - { - assert(s); - - #ifdef PUGIXML_WCHAR_MODE - return wcslen(s); - #else - const wchar_t* end = s; - while (*end) end++; - return static_cast(end - s); - #endif - } -PUGI_IMPL_NS_END - -// auto_ptr-like object for exception recovery -PUGI_IMPL_NS_BEGIN - template struct auto_deleter - { - typedef void (*D)(T*); - - T* data; - D deleter; - - auto_deleter(T* data_, D deleter_): data(data_), deleter(deleter_) - { - } - - ~auto_deleter() - { - if (data) deleter(data); - } - - T* release() - { - T* result = data; - data = 0; - return result; - } - }; -PUGI_IMPL_NS_END - -#ifdef PUGIXML_COMPACT -PUGI_IMPL_NS_BEGIN - class compact_hash_table - { - public: - compact_hash_table(): _items(0), _capacity(0), _count(0) - { - } - - void clear() - { - if (_items) - { - xml_memory::deallocate(_items); - _items = 0; - _capacity = 0; - _count = 0; - } - } - - void* find(const void* key) - { - if (_capacity == 0) return 0; - - item_t* item = get_item(key); - assert(item); - assert(item->key == key || (item->key == 0 && item->value == 0)); - - return item->value; - } - - void insert(const void* key, void* value) - { - assert(_capacity != 0 && _count < _capacity - _capacity / 4); - - item_t* item = get_item(key); - assert(item); - - if (item->key == 0) - { - _count++; - item->key = key; - } - - item->value = value; - } - - bool reserve(size_t extra = 16) - { - if (_count + extra >= _capacity - _capacity / 4) - return rehash(_count + extra); - - return true; - } - - private: - struct item_t - { - const void* key; - void* value; - }; - - item_t* _items; - size_t _capacity; - - size_t _count; - - bool rehash(size_t count); - - item_t* get_item(const void* key) - { - assert(key); - assert(_capacity > 0); - - size_t hashmod = _capacity - 1; - size_t bucket = hash(key) & hashmod; - - for (size_t probe = 0; probe <= hashmod; ++probe) - { - item_t& probe_item = _items[bucket]; - - if (probe_item.key == key || probe_item.key == 0) - return &probe_item; - - // hash collision, quadratic probing - bucket = (bucket + probe + 1) & hashmod; - } - - assert(false && "Hash table is full"); // unreachable - return 0; - } - - static PUGI_IMPL_UNSIGNED_OVERFLOW unsigned int hash(const void* key) - { - unsigned int h = static_cast(reinterpret_cast(key) & 0xffffffff); - - // MurmurHash3 32-bit finalizer - h ^= h >> 16; - h *= 0x85ebca6bu; - h ^= h >> 13; - h *= 0xc2b2ae35u; - h ^= h >> 16; - - return h; - } - }; - - PUGI_IMPL_FN_NO_INLINE bool compact_hash_table::rehash(size_t count) - { - size_t capacity = 32; - while (count >= capacity - capacity / 4) - capacity *= 2; - - compact_hash_table rt; - rt._capacity = capacity; - rt._items = static_cast(xml_memory::allocate(sizeof(item_t) * capacity)); - - if (!rt._items) - return false; - - memset(rt._items, 0, sizeof(item_t) * capacity); - - for (size_t i = 0; i < _capacity; ++i) - if (_items[i].key) - rt.insert(_items[i].key, _items[i].value); - - if (_items) - xml_memory::deallocate(_items); - - _capacity = capacity; - _items = rt._items; - - assert(_count == rt._count); - - return true; - } - -PUGI_IMPL_NS_END -#endif - -PUGI_IMPL_NS_BEGIN -#ifdef PUGIXML_COMPACT - static const uintptr_t xml_memory_block_alignment = 4; -#else - static const uintptr_t xml_memory_block_alignment = sizeof(void*); -#endif - - // extra metadata bits - static const uintptr_t xml_memory_page_contents_shared_mask = 64; - static const uintptr_t xml_memory_page_name_allocated_mask = 32; - static const uintptr_t xml_memory_page_value_allocated_mask = 16; - static const uintptr_t xml_memory_page_type_mask = 15; - - // combined masks for string uniqueness - static const uintptr_t xml_memory_page_name_allocated_or_shared_mask = xml_memory_page_name_allocated_mask | xml_memory_page_contents_shared_mask; - static const uintptr_t xml_memory_page_value_allocated_or_shared_mask = xml_memory_page_value_allocated_mask | xml_memory_page_contents_shared_mask; - -#ifdef PUGIXML_COMPACT - #define PUGI_IMPL_GETHEADER_IMPL(object, page, flags) // unused - #define PUGI_IMPL_GETPAGE_IMPL(header) (header).get_page() -#else - #define PUGI_IMPL_GETHEADER_IMPL(object, page, flags) (((reinterpret_cast(object) - reinterpret_cast(page)) << 8) | (flags)) - // this macro casts pointers through void* to avoid 'cast increases required alignment of target type' warnings - #define PUGI_IMPL_GETPAGE_IMPL(header) static_cast(const_cast(static_cast(reinterpret_cast(&header) - (header >> 8)))) -#endif - - #define PUGI_IMPL_GETPAGE(n) PUGI_IMPL_GETPAGE_IMPL((n)->header) - #define PUGI_IMPL_NODETYPE(n) static_cast((n)->header & impl::xml_memory_page_type_mask) - - struct xml_allocator; - - struct xml_memory_page - { - static xml_memory_page* construct(void* memory) - { - xml_memory_page* result = static_cast(memory); - - result->allocator = 0; - result->prev = 0; - result->next = 0; - result->busy_size = 0; - result->freed_size = 0; - - #ifdef PUGIXML_COMPACT - result->compact_string_base = 0; - result->compact_shared_parent = 0; - result->compact_page_marker = 0; - #endif - - return result; - } - - xml_allocator* allocator; - - xml_memory_page* prev; - xml_memory_page* next; - - size_t busy_size; - size_t freed_size; - - #ifdef PUGIXML_COMPACT - char_t* compact_string_base; - void* compact_shared_parent; - uint32_t* compact_page_marker; - #endif - }; - - static const size_t xml_memory_page_size = - #ifdef PUGIXML_MEMORY_PAGE_SIZE - (PUGIXML_MEMORY_PAGE_SIZE) - #else - 32768 - #endif - - sizeof(xml_memory_page); - - struct xml_memory_string_header - { - uint16_t page_offset; // offset from page->data - uint16_t full_size; // 0 if string occupies whole page - }; - - struct xml_allocator - { - xml_allocator(xml_memory_page* root): _root(root), _busy_size(root->busy_size) - { - #ifdef PUGIXML_COMPACT - _hash = 0; - #endif - } - - xml_memory_page* allocate_page(size_t data_size) - { - size_t size = sizeof(xml_memory_page) + data_size; - - // allocate block with some alignment, leaving memory for worst-case padding - void* memory = xml_memory::allocate(size); - if (!memory) return 0; - - // prepare page structure - xml_memory_page* page = xml_memory_page::construct(memory); - assert(page); - - assert(this == _root->allocator); - page->allocator = this; - - return page; - } - - static void deallocate_page(xml_memory_page* page) - { - xml_memory::deallocate(page); - } - - void* allocate_memory_oob(size_t size, xml_memory_page*& out_page); - - void* allocate_memory(size_t size, xml_memory_page*& out_page) - { - if (PUGI_IMPL_UNLIKELY(_busy_size + size > xml_memory_page_size)) - return allocate_memory_oob(size, out_page); - - void* buf = reinterpret_cast(_root) + sizeof(xml_memory_page) + _busy_size; - - _busy_size += size; - - out_page = _root; - - return buf; - } - - #ifdef PUGIXML_COMPACT - void* allocate_object(size_t size, xml_memory_page*& out_page) - { - void* result = allocate_memory(size + sizeof(uint32_t), out_page); - if (!result) return 0; - - // adjust for marker - ptrdiff_t offset = static_cast(result) - reinterpret_cast(out_page->compact_page_marker); - - if (PUGI_IMPL_UNLIKELY(static_cast(offset) >= 256 * xml_memory_block_alignment)) - { - // insert new marker - uint32_t* marker = static_cast(result); - - *marker = static_cast(reinterpret_cast(marker) - reinterpret_cast(out_page)); - out_page->compact_page_marker = marker; - - // since we don't reuse the page space until we reallocate it, we can just pretend that we freed the marker block - // this will make sure deallocate_memory correctly tracks the size - out_page->freed_size += sizeof(uint32_t); - - return marker + 1; - } - else - { - // roll back uint32_t part - _busy_size -= sizeof(uint32_t); - - return result; - } - } - #else - void* allocate_object(size_t size, xml_memory_page*& out_page) - { - return allocate_memory(size, out_page); - } - #endif - - void deallocate_memory(void* ptr, size_t size, xml_memory_page* page) - { - if (page == _root) page->busy_size = _busy_size; - - assert(ptr >= reinterpret_cast(page) + sizeof(xml_memory_page) && ptr < reinterpret_cast(page) + sizeof(xml_memory_page) + page->busy_size); - (void)!ptr; - - page->freed_size += size; - assert(page->freed_size <= page->busy_size); - - if (page->freed_size == page->busy_size) - { - if (page->next == 0) - { - assert(_root == page); - - // top page freed, just reset sizes - page->busy_size = 0; - page->freed_size = 0; - - #ifdef PUGIXML_COMPACT - // reset compact state to maximize efficiency - page->compact_string_base = 0; - page->compact_shared_parent = 0; - page->compact_page_marker = 0; - #endif - - _busy_size = 0; - } - else - { - assert(_root != page); - assert(page->prev); - - // remove from the list - page->prev->next = page->next; - page->next->prev = page->prev; - - // deallocate - deallocate_page(page); - } - } - } - - char_t* allocate_string(size_t length) - { - static const size_t max_encoded_offset = (1 << 16) * xml_memory_block_alignment; - - PUGI_IMPL_STATIC_ASSERT(xml_memory_page_size <= max_encoded_offset); - - // allocate memory for string and header block - size_t size = sizeof(xml_memory_string_header) + length * sizeof(char_t); - - // round size up to block alignment boundary - size_t full_size = (size + (xml_memory_block_alignment - 1)) & ~(xml_memory_block_alignment - 1); - - xml_memory_page* page; - xml_memory_string_header* header = static_cast(allocate_memory(full_size, page)); - - if (!header) return 0; - - // setup header - ptrdiff_t page_offset = reinterpret_cast(header) - reinterpret_cast(page) - sizeof(xml_memory_page); - - assert(page_offset % xml_memory_block_alignment == 0); - assert(page_offset >= 0 && static_cast(page_offset) < max_encoded_offset); - header->page_offset = static_cast(static_cast(page_offset) / xml_memory_block_alignment); - - // full_size == 0 for large strings that occupy the whole page - assert(full_size % xml_memory_block_alignment == 0); - assert(full_size < max_encoded_offset || (page->busy_size == full_size && page_offset == 0)); - header->full_size = static_cast(full_size < max_encoded_offset ? full_size / xml_memory_block_alignment : 0); - - // round-trip through void* to avoid 'cast increases required alignment of target type' warning - // header is guaranteed a pointer-sized alignment, which should be enough for char_t - return static_cast(static_cast(header + 1)); - } - - void deallocate_string(char_t* string) - { - // this function casts pointers through void* to avoid 'cast increases required alignment of target type' warnings - // we're guaranteed the proper (pointer-sized) alignment on the input string if it was allocated via allocate_string - - // get header - xml_memory_string_header* header = static_cast(static_cast(string)) - 1; - assert(header); - - // deallocate - size_t page_offset = sizeof(xml_memory_page) + header->page_offset * xml_memory_block_alignment; - xml_memory_page* page = reinterpret_cast(static_cast(reinterpret_cast(header) - page_offset)); - - // if full_size == 0 then this string occupies the whole page - size_t full_size = header->full_size == 0 ? page->busy_size : header->full_size * xml_memory_block_alignment; - - deallocate_memory(header, full_size, page); - } - - bool reserve() - { - #ifdef PUGIXML_COMPACT - return _hash->reserve(); - #else - return true; - #endif - } - - xml_memory_page* _root; - size_t _busy_size; - - #ifdef PUGIXML_COMPACT - compact_hash_table* _hash; - #endif - }; - - PUGI_IMPL_FN_NO_INLINE void* xml_allocator::allocate_memory_oob(size_t size, xml_memory_page*& out_page) - { - const size_t large_allocation_threshold = xml_memory_page_size / 4; - - xml_memory_page* page = allocate_page(size <= large_allocation_threshold ? xml_memory_page_size : size); - out_page = page; - - if (!page) return 0; - - if (size <= large_allocation_threshold) - { - _root->busy_size = _busy_size; - - // insert page at the end of linked list - page->prev = _root; - _root->next = page; - _root = page; - - _busy_size = size; - } - else - { - // insert page before the end of linked list, so that it is deleted as soon as possible - // the last page is not deleted even if it's empty (see deallocate_memory) - assert(_root->prev); - - page->prev = _root->prev; - page->next = _root; - - _root->prev->next = page; - _root->prev = page; - - page->busy_size = size; - } - - return reinterpret_cast(page) + sizeof(xml_memory_page); - } -PUGI_IMPL_NS_END - -#ifdef PUGIXML_COMPACT -PUGI_IMPL_NS_BEGIN - static const uintptr_t compact_alignment_log2 = 2; - static const uintptr_t compact_alignment = 1 << compact_alignment_log2; - - class compact_header - { - public: - compact_header(xml_memory_page* page, unsigned int flags) - { - PUGI_IMPL_STATIC_ASSERT(xml_memory_block_alignment == compact_alignment); - - ptrdiff_t offset = (reinterpret_cast(this) - reinterpret_cast(page->compact_page_marker)); - assert(offset % compact_alignment == 0 && static_cast(offset) < 256 * compact_alignment); - - _page = static_cast(offset >> compact_alignment_log2); - _flags = static_cast(flags); - } - - void operator&=(uintptr_t mod) - { - _flags &= static_cast(mod); - } - - void operator|=(uintptr_t mod) - { - _flags |= static_cast(mod); - } - - uintptr_t operator&(uintptr_t mod) const - { - return _flags & mod; - } - - xml_memory_page* get_page() const - { - // round-trip through void* to silence 'cast increases required alignment of target type' warnings - const char* page_marker = reinterpret_cast(this) - (_page << compact_alignment_log2); - const char* page = page_marker - *reinterpret_cast(static_cast(page_marker)); - - return const_cast(reinterpret_cast(static_cast(page))); - } - - private: - unsigned char _page; - unsigned char _flags; - }; - - PUGI_IMPL_FN xml_memory_page* compact_get_page(const void* object, int header_offset) - { - const compact_header* header = reinterpret_cast(static_cast(object) - header_offset); - - return header->get_page(); - } - - template PUGI_IMPL_FN_NO_INLINE T* compact_get_value(const void* object) - { - return static_cast(compact_get_page(object, header_offset)->allocator->_hash->find(object)); - } - - template PUGI_IMPL_FN_NO_INLINE void compact_set_value(const void* object, T* value) - { - compact_get_page(object, header_offset)->allocator->_hash->insert(object, value); - } - - template class compact_pointer - { - public: - compact_pointer(): _data(0) - { - } - - void operator=(const compact_pointer& rhs) - { - *this = rhs + 0; - } - - void operator=(T* value) - { - if (value) - { - // value is guaranteed to be compact-aligned; 'this' is not - // our decoding is based on 'this' aligned to compact alignment downwards (see operator T*) - // so for negative offsets (e.g. -3) we need to adjust the diff by compact_alignment - 1 to - // compensate for arithmetic shift rounding for negative values - ptrdiff_t diff = reinterpret_cast(value) - reinterpret_cast(this); - ptrdiff_t offset = ((diff + int(compact_alignment - 1)) >> compact_alignment_log2) - start; - - if (static_cast(offset) <= 253) - _data = static_cast(offset + 1); - else - { - compact_set_value(this, value); - - _data = 255; - } - } - else - _data = 0; - } - - operator T*() const - { - if (_data) - { - if (_data < 255) - { - uintptr_t base = reinterpret_cast(this) & ~(compact_alignment - 1); - - return reinterpret_cast(base + (_data - 1 + start) * compact_alignment); - } - else - return compact_get_value(this); - } - else - return 0; - } - - T* operator->() const - { - return *this; - } - - private: - unsigned char _data; - }; - - template class compact_pointer_parent - { - public: - compact_pointer_parent(): _data(0) - { - } - - void operator=(const compact_pointer_parent& rhs) - { - *this = rhs + 0; - } - - void operator=(T* value) - { - if (value) - { - // value is guaranteed to be compact-aligned; 'this' is not - // our decoding is based on 'this' aligned to compact alignment downwards (see operator T*) - // so for negative offsets (e.g. -3) we need to adjust the diff by compact_alignment - 1 to - // compensate for arithmetic shift behavior for negative values - ptrdiff_t diff = reinterpret_cast(value) - reinterpret_cast(this); - ptrdiff_t offset = ((diff + int(compact_alignment - 1)) >> compact_alignment_log2) + 65533; - - if (static_cast(offset) <= 65533) - { - _data = static_cast(offset + 1); - } - else - { - xml_memory_page* page = compact_get_page(this, header_offset); - - if (PUGI_IMPL_UNLIKELY(page->compact_shared_parent == 0)) - page->compact_shared_parent = value; - - if (page->compact_shared_parent == value) - { - _data = 65534; - } - else - { - compact_set_value(this, value); - - _data = 65535; - } - } - } - else - { - _data = 0; - } - } - - operator T*() const - { - if (_data) - { - if (_data < 65534) - { - uintptr_t base = reinterpret_cast(this) & ~(compact_alignment - 1); - - return reinterpret_cast(base + (_data - 1 - 65533) * compact_alignment); - } - else if (_data == 65534) - return static_cast(compact_get_page(this, header_offset)->compact_shared_parent); - else - return compact_get_value(this); - } - else - return 0; - } - - T* operator->() const - { - return *this; - } - - private: - uint16_t _data; - }; - - template class compact_string - { - public: - compact_string(): _data(0) - { - } - - void operator=(const compact_string& rhs) - { - *this = rhs + 0; - } - - void operator=(char_t* value) - { - if (value) - { - xml_memory_page* page = compact_get_page(this, header_offset); - - if (PUGI_IMPL_UNLIKELY(page->compact_string_base == 0)) - page->compact_string_base = value; - - ptrdiff_t offset = value - page->compact_string_base; - - if (static_cast(offset) < (65535 << 7)) - { - // round-trip through void* to silence 'cast increases required alignment of target type' warnings - uint16_t* base = reinterpret_cast(static_cast(reinterpret_cast(this) - base_offset)); - - if (*base == 0) - { - *base = static_cast((offset >> 7) + 1); - _data = static_cast((offset & 127) + 1); - } - else - { - ptrdiff_t remainder = offset - ((*base - 1) << 7); - - if (static_cast(remainder) <= 253) - { - _data = static_cast(remainder + 1); - } - else - { - compact_set_value(this, value); - - _data = 255; - } - } - } - else - { - compact_set_value(this, value); - - _data = 255; - } - } - else - { - _data = 0; - } - } - - operator char_t*() const - { - if (_data) - { - if (_data < 255) - { - xml_memory_page* page = compact_get_page(this, header_offset); - - // round-trip through void* to silence 'cast increases required alignment of target type' warnings - const uint16_t* base = reinterpret_cast(static_cast(reinterpret_cast(this) - base_offset)); - assert(*base); - - ptrdiff_t offset = ((*base - 1) << 7) + (_data - 1); - - return page->compact_string_base + offset; - } - else - { - return compact_get_value(this); - } - } - else - return 0; - } - - private: - unsigned char _data; - }; -PUGI_IMPL_NS_END -#endif - -#ifdef PUGIXML_COMPACT -namespace pugi -{ - struct xml_attribute_struct - { - xml_attribute_struct(impl::xml_memory_page* page): header(page, 0), namevalue_base(0) - { - PUGI_IMPL_STATIC_ASSERT(sizeof(xml_attribute_struct) == 8); - } - - impl::compact_header header; - - uint16_t namevalue_base; - - impl::compact_string<4, 2> name; - impl::compact_string<5, 3> value; - - impl::compact_pointer prev_attribute_c; - impl::compact_pointer next_attribute; - }; - - struct xml_node_struct - { - xml_node_struct(impl::xml_memory_page* page, xml_node_type type): header(page, type), namevalue_base(0) - { - PUGI_IMPL_STATIC_ASSERT(sizeof(xml_node_struct) == 12); - } - - impl::compact_header header; - - uint16_t namevalue_base; - - impl::compact_string<4, 2> name; - impl::compact_string<5, 3> value; - - impl::compact_pointer_parent parent; - - impl::compact_pointer first_child; - - impl::compact_pointer prev_sibling_c; - impl::compact_pointer next_sibling; - - impl::compact_pointer first_attribute; - }; -} -#else -namespace pugi -{ - struct xml_attribute_struct - { - xml_attribute_struct(impl::xml_memory_page* page): name(0), value(0), prev_attribute_c(0), next_attribute(0) - { - header = PUGI_IMPL_GETHEADER_IMPL(this, page, 0); - } - - uintptr_t header; - - char_t* name; - char_t* value; - - xml_attribute_struct* prev_attribute_c; - xml_attribute_struct* next_attribute; - }; - - struct xml_node_struct - { - xml_node_struct(impl::xml_memory_page* page, xml_node_type type): name(0), value(0), parent(0), first_child(0), prev_sibling_c(0), next_sibling(0), first_attribute(0) - { - header = PUGI_IMPL_GETHEADER_IMPL(this, page, type); - } - - uintptr_t header; - - char_t* name; - char_t* value; - - xml_node_struct* parent; - - xml_node_struct* first_child; - - xml_node_struct* prev_sibling_c; - xml_node_struct* next_sibling; - - xml_attribute_struct* first_attribute; - }; -} -#endif - -PUGI_IMPL_NS_BEGIN - struct xml_extra_buffer - { - char_t* buffer; - xml_extra_buffer* next; - }; - - struct xml_document_struct: public xml_node_struct, public xml_allocator - { - xml_document_struct(xml_memory_page* page): xml_node_struct(page, node_document), xml_allocator(page), buffer(0), extra_buffers(0) - { - } - - const char_t* buffer; - - xml_extra_buffer* extra_buffers; - - #ifdef PUGIXML_COMPACT - compact_hash_table hash; - #endif - }; - - template inline xml_allocator& get_allocator(const Object* object) - { - assert(object); - - return *PUGI_IMPL_GETPAGE(object)->allocator; - } - - template inline xml_document_struct& get_document(const Object* object) - { - assert(object); - - return *static_cast(PUGI_IMPL_GETPAGE(object)->allocator); - } -PUGI_IMPL_NS_END - -// Low-level DOM operations -PUGI_IMPL_NS_BEGIN - inline xml_attribute_struct* allocate_attribute(xml_allocator& alloc) - { - xml_memory_page* page; - void* memory = alloc.allocate_object(sizeof(xml_attribute_struct), page); - if (!memory) return 0; - - return new (memory) xml_attribute_struct(page); - } - - inline xml_node_struct* allocate_node(xml_allocator& alloc, xml_node_type type) - { - xml_memory_page* page; - void* memory = alloc.allocate_object(sizeof(xml_node_struct), page); - if (!memory) return 0; - - return new (memory) xml_node_struct(page, type); - } - - inline void destroy_attribute(xml_attribute_struct* a, xml_allocator& alloc) - { - if (a->header & impl::xml_memory_page_name_allocated_mask) - alloc.deallocate_string(a->name); - - if (a->header & impl::xml_memory_page_value_allocated_mask) - alloc.deallocate_string(a->value); - - alloc.deallocate_memory(a, sizeof(xml_attribute_struct), PUGI_IMPL_GETPAGE(a)); - } - - inline void destroy_node(xml_node_struct* n, xml_allocator& alloc) - { - if (n->header & impl::xml_memory_page_name_allocated_mask) - alloc.deallocate_string(n->name); - - if (n->header & impl::xml_memory_page_value_allocated_mask) - alloc.deallocate_string(n->value); - - for (xml_attribute_struct* attr = n->first_attribute; attr; ) - { - xml_attribute_struct* next = attr->next_attribute; - - destroy_attribute(attr, alloc); - - attr = next; - } - - for (xml_node_struct* child = n->first_child; child; ) - { - xml_node_struct* next = child->next_sibling; - - destroy_node(child, alloc); - - child = next; - } - - alloc.deallocate_memory(n, sizeof(xml_node_struct), PUGI_IMPL_GETPAGE(n)); - } - - inline void append_node(xml_node_struct* child, xml_node_struct* node) - { - child->parent = node; - - xml_node_struct* head = node->first_child; - - if (head) - { - xml_node_struct* tail = head->prev_sibling_c; - - tail->next_sibling = child; - child->prev_sibling_c = tail; - head->prev_sibling_c = child; - } - else - { - node->first_child = child; - child->prev_sibling_c = child; - } - } - - inline void prepend_node(xml_node_struct* child, xml_node_struct* node) - { - child->parent = node; - - xml_node_struct* head = node->first_child; - - if (head) - { - child->prev_sibling_c = head->prev_sibling_c; - head->prev_sibling_c = child; - } - else - child->prev_sibling_c = child; - - child->next_sibling = head; - node->first_child = child; - } - - inline void insert_node_after(xml_node_struct* child, xml_node_struct* node) - { - xml_node_struct* parent = node->parent; - - child->parent = parent; - - xml_node_struct* next = node->next_sibling; - - if (next) - next->prev_sibling_c = child; - else - parent->first_child->prev_sibling_c = child; - - child->next_sibling = next; - child->prev_sibling_c = node; - - node->next_sibling = child; - } - - inline void insert_node_before(xml_node_struct* child, xml_node_struct* node) - { - xml_node_struct* parent = node->parent; - - child->parent = parent; - - xml_node_struct* prev = node->prev_sibling_c; - - if (prev->next_sibling) - prev->next_sibling = child; - else - parent->first_child = child; - - child->prev_sibling_c = prev; - child->next_sibling = node; - - node->prev_sibling_c = child; - } - - inline void remove_node(xml_node_struct* node) - { - xml_node_struct* parent = node->parent; - - xml_node_struct* next = node->next_sibling; - xml_node_struct* prev = node->prev_sibling_c; - - if (next) - next->prev_sibling_c = prev; - else - parent->first_child->prev_sibling_c = prev; - - if (prev->next_sibling) - prev->next_sibling = next; - else - parent->first_child = next; - - node->parent = 0; - node->prev_sibling_c = 0; - node->next_sibling = 0; - } - - inline void append_attribute(xml_attribute_struct* attr, xml_node_struct* node) - { - xml_attribute_struct* head = node->first_attribute; - - if (head) - { - xml_attribute_struct* tail = head->prev_attribute_c; - - tail->next_attribute = attr; - attr->prev_attribute_c = tail; - head->prev_attribute_c = attr; - } - else - { - node->first_attribute = attr; - attr->prev_attribute_c = attr; - } - } - - inline void prepend_attribute(xml_attribute_struct* attr, xml_node_struct* node) - { - xml_attribute_struct* head = node->first_attribute; - - if (head) - { - attr->prev_attribute_c = head->prev_attribute_c; - head->prev_attribute_c = attr; - } - else - attr->prev_attribute_c = attr; - - attr->next_attribute = head; - node->first_attribute = attr; - } - - inline void insert_attribute_after(xml_attribute_struct* attr, xml_attribute_struct* place, xml_node_struct* node) - { - xml_attribute_struct* next = place->next_attribute; - - if (next) - next->prev_attribute_c = attr; - else - node->first_attribute->prev_attribute_c = attr; - - attr->next_attribute = next; - attr->prev_attribute_c = place; - place->next_attribute = attr; - } - - inline void insert_attribute_before(xml_attribute_struct* attr, xml_attribute_struct* place, xml_node_struct* node) - { - xml_attribute_struct* prev = place->prev_attribute_c; - - if (prev->next_attribute) - prev->next_attribute = attr; - else - node->first_attribute = attr; - - attr->prev_attribute_c = prev; - attr->next_attribute = place; - place->prev_attribute_c = attr; - } - - inline void remove_attribute(xml_attribute_struct* attr, xml_node_struct* node) - { - xml_attribute_struct* next = attr->next_attribute; - xml_attribute_struct* prev = attr->prev_attribute_c; - - if (next) - next->prev_attribute_c = prev; - else - node->first_attribute->prev_attribute_c = prev; - - if (prev->next_attribute) - prev->next_attribute = next; - else - node->first_attribute = next; - - attr->prev_attribute_c = 0; - attr->next_attribute = 0; - } - - PUGI_IMPL_FN_NO_INLINE xml_node_struct* append_new_node(xml_node_struct* node, xml_allocator& alloc, xml_node_type type = node_element) - { - if (!alloc.reserve()) return 0; - - xml_node_struct* child = allocate_node(alloc, type); - if (!child) return 0; - - append_node(child, node); - - return child; - } - - PUGI_IMPL_FN_NO_INLINE xml_attribute_struct* append_new_attribute(xml_node_struct* node, xml_allocator& alloc) - { - if (!alloc.reserve()) return 0; - - xml_attribute_struct* attr = allocate_attribute(alloc); - if (!attr) return 0; - - append_attribute(attr, node); - - return attr; - } -PUGI_IMPL_NS_END - -// Helper classes for code generation -PUGI_IMPL_NS_BEGIN - struct opt_false - { - enum { value = 0 }; - }; - - struct opt_true - { - enum { value = 1 }; - }; -PUGI_IMPL_NS_END - -// Unicode utilities -PUGI_IMPL_NS_BEGIN - inline uint16_t endian_swap(uint16_t value) - { - return static_cast(((value & 0xff) << 8) | (value >> 8)); - } - - inline uint32_t endian_swap(uint32_t value) - { - return ((value & 0xff) << 24) | ((value & 0xff00) << 8) | ((value & 0xff0000) >> 8) | (value >> 24); - } - - struct utf8_counter - { - typedef size_t value_type; - - static value_type low(value_type result, uint32_t ch) - { - // U+0000..U+007F - if (ch < 0x80) return result + 1; - // U+0080..U+07FF - else if (ch < 0x800) return result + 2; - // U+0800..U+FFFF - else return result + 3; - } - - static value_type high(value_type result, uint32_t) - { - // U+10000..U+10FFFF - return result + 4; - } - }; - - struct utf8_writer - { - typedef uint8_t* value_type; - - static value_type low(value_type result, uint32_t ch) - { - // U+0000..U+007F - if (ch < 0x80) - { - *result = static_cast(ch); - return result + 1; - } - // U+0080..U+07FF - else if (ch < 0x800) - { - result[0] = static_cast(0xC0 | (ch >> 6)); - result[1] = static_cast(0x80 | (ch & 0x3F)); - return result + 2; - } - // U+0800..U+FFFF - else - { - result[0] = static_cast(0xE0 | (ch >> 12)); - result[1] = static_cast(0x80 | ((ch >> 6) & 0x3F)); - result[2] = static_cast(0x80 | (ch & 0x3F)); - return result + 3; - } - } - - static value_type high(value_type result, uint32_t ch) - { - // U+10000..U+10FFFF - result[0] = static_cast(0xF0 | (ch >> 18)); - result[1] = static_cast(0x80 | ((ch >> 12) & 0x3F)); - result[2] = static_cast(0x80 | ((ch >> 6) & 0x3F)); - result[3] = static_cast(0x80 | (ch & 0x3F)); - return result + 4; - } - - static value_type any(value_type result, uint32_t ch) - { - return (ch < 0x10000) ? low(result, ch) : high(result, ch); - } - }; - - struct utf16_counter - { - typedef size_t value_type; - - static value_type low(value_type result, uint32_t) - { - return result + 1; - } - - static value_type high(value_type result, uint32_t) - { - return result + 2; - } - }; - - struct utf16_writer - { - typedef uint16_t* value_type; - - static value_type low(value_type result, uint32_t ch) - { - *result = static_cast(ch); - - return result + 1; - } - - static value_type high(value_type result, uint32_t ch) - { - uint32_t msh = static_cast(ch - 0x10000) >> 10; - uint32_t lsh = static_cast(ch - 0x10000) & 0x3ff; - - result[0] = static_cast(0xD800 + msh); - result[1] = static_cast(0xDC00 + lsh); - - return result + 2; - } - - static value_type any(value_type result, uint32_t ch) - { - return (ch < 0x10000) ? low(result, ch) : high(result, ch); - } - }; - - struct utf32_counter - { - typedef size_t value_type; - - static value_type low(value_type result, uint32_t) - { - return result + 1; - } - - static value_type high(value_type result, uint32_t) - { - return result + 1; - } - }; - - struct utf32_writer - { - typedef uint32_t* value_type; - - static value_type low(value_type result, uint32_t ch) - { - *result = ch; - - return result + 1; - } - - static value_type high(value_type result, uint32_t ch) - { - *result = ch; - - return result + 1; - } - - static value_type any(value_type result, uint32_t ch) - { - *result = ch; - - return result + 1; - } - }; - - struct latin1_writer - { - typedef uint8_t* value_type; - - static value_type low(value_type result, uint32_t ch) - { - *result = static_cast(ch > 255 ? '?' : ch); - - return result + 1; - } - - static value_type high(value_type result, uint32_t ch) - { - (void)ch; - - *result = '?'; - - return result + 1; - } - }; - - struct utf8_decoder - { - typedef uint8_t type; - - template static inline typename Traits::value_type process(const uint8_t* data, size_t size, typename Traits::value_type result, Traits) - { - const uint8_t utf8_byte_mask = 0x3f; - - while (size) - { - uint8_t lead = *data; - - // 0xxxxxxx -> U+0000..U+007F - if (lead < 0x80) - { - result = Traits::low(result, lead); - data += 1; - size -= 1; - - // process aligned single-byte (ascii) blocks - if ((reinterpret_cast(data) & 3) == 0) - { - // round-trip through void* to silence 'cast increases required alignment of target type' warnings - while (size >= 4 && (*static_cast(static_cast(data)) & 0x80808080) == 0) - { - result = Traits::low(result, data[0]); - result = Traits::low(result, data[1]); - result = Traits::low(result, data[2]); - result = Traits::low(result, data[3]); - data += 4; - size -= 4; - } - } - } - // 110xxxxx -> U+0080..U+07FF - else if (static_cast(lead - 0xC0) < 0x20 && size >= 2 && (data[1] & 0xc0) == 0x80) - { - result = Traits::low(result, ((lead & ~0xC0) << 6) | (data[1] & utf8_byte_mask)); - data += 2; - size -= 2; - } - // 1110xxxx -> U+0800-U+FFFF - else if (static_cast(lead - 0xE0) < 0x10 && size >= 3 && (data[1] & 0xc0) == 0x80 && (data[2] & 0xc0) == 0x80) - { - result = Traits::low(result, ((lead & ~0xE0) << 12) | ((data[1] & utf8_byte_mask) << 6) | (data[2] & utf8_byte_mask)); - data += 3; - size -= 3; - } - // 11110xxx -> U+10000..U+10FFFF - else if (static_cast(lead - 0xF0) < 0x08 && size >= 4 && (data[1] & 0xc0) == 0x80 && (data[2] & 0xc0) == 0x80 && (data[3] & 0xc0) == 0x80) - { - result = Traits::high(result, ((lead & ~0xF0) << 18) | ((data[1] & utf8_byte_mask) << 12) | ((data[2] & utf8_byte_mask) << 6) | (data[3] & utf8_byte_mask)); - data += 4; - size -= 4; - } - // 10xxxxxx or 11111xxx -> invalid - else - { - data += 1; - size -= 1; - } - } - - return result; - } - }; - - template struct utf16_decoder - { - typedef uint16_t type; - - template static inline typename Traits::value_type process(const uint16_t* data, size_t size, typename Traits::value_type result, Traits) - { - while (size) - { - uint16_t lead = opt_swap::value ? endian_swap(*data) : *data; - - // U+0000..U+D7FF - if (lead < 0xD800) - { - result = Traits::low(result, lead); - data += 1; - size -= 1; - } - // U+E000..U+FFFF - else if (static_cast(lead - 0xE000) < 0x2000) - { - result = Traits::low(result, lead); - data += 1; - size -= 1; - } - // surrogate pair lead - else if (static_cast(lead - 0xD800) < 0x400 && size >= 2) - { - uint16_t next = opt_swap::value ? endian_swap(data[1]) : data[1]; - - if (static_cast(next - 0xDC00) < 0x400) - { - result = Traits::high(result, 0x10000 + ((lead & 0x3ff) << 10) + (next & 0x3ff)); - data += 2; - size -= 2; - } - else - { - data += 1; - size -= 1; - } - } - else - { - data += 1; - size -= 1; - } - } - - return result; - } - }; - - template struct utf32_decoder - { - typedef uint32_t type; - - template static inline typename Traits::value_type process(const uint32_t* data, size_t size, typename Traits::value_type result, Traits) - { - while (size) - { - uint32_t lead = opt_swap::value ? endian_swap(*data) : *data; - - // U+0000..U+FFFF - if (lead < 0x10000) - { - result = Traits::low(result, lead); - data += 1; - size -= 1; - } - // U+10000..U+10FFFF - else - { - result = Traits::high(result, lead); - data += 1; - size -= 1; - } - } - - return result; - } - }; - - struct latin1_decoder - { - typedef uint8_t type; - - template static inline typename Traits::value_type process(const uint8_t* data, size_t size, typename Traits::value_type result, Traits) - { - while (size) - { - result = Traits::low(result, *data); - data += 1; - size -= 1; - } - - return result; - } - }; - - template struct wchar_selector; - - template <> struct wchar_selector<2> - { - typedef uint16_t type; - typedef utf16_counter counter; - typedef utf16_writer writer; - typedef utf16_decoder decoder; - }; - - template <> struct wchar_selector<4> - { - typedef uint32_t type; - typedef utf32_counter counter; - typedef utf32_writer writer; - typedef utf32_decoder decoder; - }; - - typedef wchar_selector::counter wchar_counter; - typedef wchar_selector::writer wchar_writer; - - struct wchar_decoder - { - typedef wchar_t type; - - template static inline typename Traits::value_type process(const wchar_t* data, size_t size, typename Traits::value_type result, Traits traits) - { - typedef wchar_selector::decoder decoder; - - return decoder::process(reinterpret_cast(data), size, result, traits); - } - }; - -#ifdef PUGIXML_WCHAR_MODE - PUGI_IMPL_FN void convert_wchar_endian_swap(wchar_t* result, const wchar_t* data, size_t length) - { - for (size_t i = 0; i < length; ++i) - result[i] = static_cast(endian_swap(static_cast::type>(data[i]))); - } -#endif -PUGI_IMPL_NS_END - -PUGI_IMPL_NS_BEGIN - enum chartype_t - { - ct_parse_pcdata = 1, // \0, &, \r, < - ct_parse_attr = 2, // \0, &, \r, ', " - ct_parse_attr_ws = 4, // \0, &, \r, ', ", \n, tab - ct_space = 8, // \r, \n, space, tab - ct_parse_cdata = 16, // \0, ], >, \r - ct_parse_comment = 32, // \0, -, >, \r - ct_symbol = 64, // Any symbol > 127, a-z, A-Z, 0-9, _, :, -, . - ct_start_symbol = 128 // Any symbol > 127, a-z, A-Z, _, : - }; - - static const unsigned char chartype_table[256] = - { - 55, 0, 0, 0, 0, 0, 0, 0, 0, 12, 12, 0, 0, 63, 0, 0, // 0-15 - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 16-31 - 8, 0, 6, 0, 0, 0, 7, 6, 0, 0, 0, 0, 0, 96, 64, 0, // 32-47 - 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 192, 0, 1, 0, 48, 0, // 48-63 - 0, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, // 64-79 - 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 0, 0, 16, 0, 192, // 80-95 - 0, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, // 96-111 - 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 0, 0, 0, 0, 0, // 112-127 - - 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, // 128+ - 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, - 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, - 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, - 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, - 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, - 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, - 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192, 192 - }; - - enum chartypex_t - { - ctx_special_pcdata = 1, // Any symbol >= 0 and < 32 (except \t, \r, \n), &, <, > - ctx_special_attr = 2, // Any symbol >= 0 and < 32, &, <, ", ' - ctx_start_symbol = 4, // Any symbol > 127, a-z, A-Z, _ - ctx_digit = 8, // 0-9 - ctx_symbol = 16 // Any symbol > 127, a-z, A-Z, 0-9, _, -, . - }; - - static const unsigned char chartypex_table[256] = - { - 3, 3, 3, 3, 3, 3, 3, 3, 3, 2, 2, 3, 3, 2, 3, 3, // 0-15 - 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, // 16-31 - 0, 0, 2, 0, 0, 0, 3, 2, 0, 0, 0, 0, 0, 16, 16, 0, // 32-47 - 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 0, 0, 3, 0, 1, 0, // 48-63 - - 0, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, // 64-79 - 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 0, 0, 0, 0, 20, // 80-95 - 0, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, // 96-111 - 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 0, 0, 0, 0, 0, // 112-127 - - 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, // 128+ - 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, - 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, - 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, - 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, - 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, - 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, - 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20 - }; - -#ifdef PUGIXML_WCHAR_MODE - #define PUGI_IMPL_IS_CHARTYPE_IMPL(c, ct, table) ((static_cast(c) < 128 ? table[static_cast(c)] : table[128]) & (ct)) -#else - #define PUGI_IMPL_IS_CHARTYPE_IMPL(c, ct, table) (table[static_cast(c)] & (ct)) -#endif - - #define PUGI_IMPL_IS_CHARTYPE(c, ct) PUGI_IMPL_IS_CHARTYPE_IMPL(c, ct, chartype_table) - #define PUGI_IMPL_IS_CHARTYPEX(c, ct) PUGI_IMPL_IS_CHARTYPE_IMPL(c, ct, chartypex_table) - - PUGI_IMPL_FN bool is_little_endian() - { - unsigned int ui = 1; - - return *reinterpret_cast(&ui) == 1; - } - - PUGI_IMPL_FN xml_encoding get_wchar_encoding() - { - PUGI_IMPL_STATIC_ASSERT(sizeof(wchar_t) == 2 || sizeof(wchar_t) == 4); - - if (sizeof(wchar_t) == 2) - return is_little_endian() ? encoding_utf16_le : encoding_utf16_be; - else - return is_little_endian() ? encoding_utf32_le : encoding_utf32_be; - } - - PUGI_IMPL_FN bool parse_declaration_encoding(const uint8_t* data, size_t size, const uint8_t*& out_encoding, size_t& out_length) - { - #define PUGI_IMPL_SCANCHAR(ch) { if (offset >= size || data[offset] != ch) return false; offset++; } - #define PUGI_IMPL_SCANCHARTYPE(ct) { while (offset < size && PUGI_IMPL_IS_CHARTYPE(data[offset], ct)) offset++; } - - // check if we have a non-empty XML declaration - if (size < 6 || !((data[0] == '<') & (data[1] == '?') & (data[2] == 'x') & (data[3] == 'm') & (data[4] == 'l') && PUGI_IMPL_IS_CHARTYPE(data[5], ct_space))) - return false; - - // scan XML declaration until the encoding field - for (size_t i = 6; i + 1 < size; ++i) - { - // declaration can not contain ? in quoted values - if (data[i] == '?') - return false; - - if (data[i] == 'e' && data[i + 1] == 'n') - { - size_t offset = i; - - // encoding follows the version field which can't contain 'en' so this has to be the encoding if XML is well formed - PUGI_IMPL_SCANCHAR('e'); PUGI_IMPL_SCANCHAR('n'); PUGI_IMPL_SCANCHAR('c'); PUGI_IMPL_SCANCHAR('o'); - PUGI_IMPL_SCANCHAR('d'); PUGI_IMPL_SCANCHAR('i'); PUGI_IMPL_SCANCHAR('n'); PUGI_IMPL_SCANCHAR('g'); - - // S? = S? - PUGI_IMPL_SCANCHARTYPE(ct_space); - PUGI_IMPL_SCANCHAR('='); - PUGI_IMPL_SCANCHARTYPE(ct_space); - - // the only two valid delimiters are ' and " - uint8_t delimiter = (offset < size && data[offset] == '"') ? '"' : '\''; - - PUGI_IMPL_SCANCHAR(delimiter); - - size_t start = offset; - - out_encoding = data + offset; - - PUGI_IMPL_SCANCHARTYPE(ct_symbol); - - out_length = offset - start; - - PUGI_IMPL_SCANCHAR(delimiter); - - return true; - } - } - - return false; - - #undef PUGI_IMPL_SCANCHAR - #undef PUGI_IMPL_SCANCHARTYPE - } - - PUGI_IMPL_FN xml_encoding guess_buffer_encoding(const uint8_t* data, size_t size) - { - // skip encoding autodetection if input buffer is too small - if (size < 4) return encoding_utf8; - - uint8_t d0 = data[0], d1 = data[1], d2 = data[2], d3 = data[3]; - - // look for BOM in first few bytes - if (d0 == 0 && d1 == 0 && d2 == 0xfe && d3 == 0xff) return encoding_utf32_be; - if (d0 == 0xff && d1 == 0xfe && d2 == 0 && d3 == 0) return encoding_utf32_le; - if (d0 == 0xfe && d1 == 0xff) return encoding_utf16_be; - if (d0 == 0xff && d1 == 0xfe) return encoding_utf16_le; - if (d0 == 0xef && d1 == 0xbb && d2 == 0xbf) return encoding_utf8; - - // look for <, (contents); - - return guess_buffer_encoding(data, size); - } - - PUGI_IMPL_FN bool get_mutable_buffer(char_t*& out_buffer, size_t& out_length, const void* contents, size_t size, bool is_mutable) - { - size_t length = size / sizeof(char_t); - - if (is_mutable) - { - out_buffer = static_cast(const_cast(contents)); - out_length = length; - } - else - { - char_t* buffer = static_cast(xml_memory::allocate((length + 1) * sizeof(char_t))); - if (!buffer) return false; - - if (contents) - memcpy(buffer, contents, length * sizeof(char_t)); - else - assert(length == 0); - - buffer[length] = 0; - - out_buffer = buffer; - out_length = length + 1; - } - - return true; - } - -#ifdef PUGIXML_WCHAR_MODE - PUGI_IMPL_FN bool need_endian_swap_utf(xml_encoding le, xml_encoding re) - { - return (le == encoding_utf16_be && re == encoding_utf16_le) || (le == encoding_utf16_le && re == encoding_utf16_be) || - (le == encoding_utf32_be && re == encoding_utf32_le) || (le == encoding_utf32_le && re == encoding_utf32_be); - } - - PUGI_IMPL_FN bool convert_buffer_endian_swap(char_t*& out_buffer, size_t& out_length, const void* contents, size_t size, bool is_mutable) - { - const char_t* data = static_cast(contents); - size_t length = size / sizeof(char_t); - - if (is_mutable) - { - char_t* buffer = const_cast(data); - - convert_wchar_endian_swap(buffer, data, length); - - out_buffer = buffer; - out_length = length; - } - else - { - char_t* buffer = static_cast(xml_memory::allocate((length + 1) * sizeof(char_t))); - if (!buffer) return false; - - convert_wchar_endian_swap(buffer, data, length); - buffer[length] = 0; - - out_buffer = buffer; - out_length = length + 1; - } - - return true; - } - - template PUGI_IMPL_FN bool convert_buffer_generic(char_t*& out_buffer, size_t& out_length, const void* contents, size_t size, D) - { - const typename D::type* data = static_cast(contents); - size_t data_length = size / sizeof(typename D::type); - - // first pass: get length in wchar_t units - size_t length = D::process(data, data_length, 0, wchar_counter()); - - // allocate buffer of suitable length - char_t* buffer = static_cast(xml_memory::allocate((length + 1) * sizeof(char_t))); - if (!buffer) return false; - - // second pass: convert utf16 input to wchar_t - wchar_writer::value_type obegin = reinterpret_cast(buffer); - wchar_writer::value_type oend = D::process(data, data_length, obegin, wchar_writer()); - - assert(oend == obegin + length); - *oend = 0; - - out_buffer = buffer; - out_length = length + 1; - - return true; - } - - PUGI_IMPL_FN bool convert_buffer(char_t*& out_buffer, size_t& out_length, xml_encoding encoding, const void* contents, size_t size, bool is_mutable) - { - // get native encoding - xml_encoding wchar_encoding = get_wchar_encoding(); - - // fast path: no conversion required - if (encoding == wchar_encoding) - return get_mutable_buffer(out_buffer, out_length, contents, size, is_mutable); - - // only endian-swapping is required - if (need_endian_swap_utf(encoding, wchar_encoding)) - return convert_buffer_endian_swap(out_buffer, out_length, contents, size, is_mutable); - - // source encoding is utf8 - if (encoding == encoding_utf8) - return convert_buffer_generic(out_buffer, out_length, contents, size, utf8_decoder()); - - // source encoding is utf16 - if (encoding == encoding_utf16_be || encoding == encoding_utf16_le) - { - xml_encoding native_encoding = is_little_endian() ? encoding_utf16_le : encoding_utf16_be; - - return (native_encoding == encoding) ? - convert_buffer_generic(out_buffer, out_length, contents, size, utf16_decoder()) : - convert_buffer_generic(out_buffer, out_length, contents, size, utf16_decoder()); - } - - // source encoding is utf32 - if (encoding == encoding_utf32_be || encoding == encoding_utf32_le) - { - xml_encoding native_encoding = is_little_endian() ? encoding_utf32_le : encoding_utf32_be; - - return (native_encoding == encoding) ? - convert_buffer_generic(out_buffer, out_length, contents, size, utf32_decoder()) : - convert_buffer_generic(out_buffer, out_length, contents, size, utf32_decoder()); - } - - // source encoding is latin1 - if (encoding == encoding_latin1) - return convert_buffer_generic(out_buffer, out_length, contents, size, latin1_decoder()); - - assert(false && "Invalid encoding"); // unreachable - return false; - } -#else - template PUGI_IMPL_FN bool convert_buffer_generic(char_t*& out_buffer, size_t& out_length, const void* contents, size_t size, D) - { - const typename D::type* data = static_cast(contents); - size_t data_length = size / sizeof(typename D::type); - - // first pass: get length in utf8 units - size_t length = D::process(data, data_length, 0, utf8_counter()); - - // allocate buffer of suitable length - char_t* buffer = static_cast(xml_memory::allocate((length + 1) * sizeof(char_t))); - if (!buffer) return false; - - // second pass: convert utf16 input to utf8 - uint8_t* obegin = reinterpret_cast(buffer); - uint8_t* oend = D::process(data, data_length, obegin, utf8_writer()); - - assert(oend == obegin + length); - *oend = 0; - - out_buffer = buffer; - out_length = length + 1; - - return true; - } - - PUGI_IMPL_FN size_t get_latin1_7bit_prefix_length(const uint8_t* data, size_t size) - { - for (size_t i = 0; i < size; ++i) - if (data[i] > 127) - return i; - - return size; - } - - PUGI_IMPL_FN bool convert_buffer_latin1(char_t*& out_buffer, size_t& out_length, const void* contents, size_t size, bool is_mutable) - { - const uint8_t* data = static_cast(contents); - size_t data_length = size; - - // get size of prefix that does not need utf8 conversion - size_t prefix_length = get_latin1_7bit_prefix_length(data, data_length); - assert(prefix_length <= data_length); - - const uint8_t* postfix = data + prefix_length; - size_t postfix_length = data_length - prefix_length; - - // if no conversion is needed, just return the original buffer - if (postfix_length == 0) return get_mutable_buffer(out_buffer, out_length, contents, size, is_mutable); - - // first pass: get length in utf8 units - size_t length = prefix_length + latin1_decoder::process(postfix, postfix_length, 0, utf8_counter()); - - // allocate buffer of suitable length - char_t* buffer = static_cast(xml_memory::allocate((length + 1) * sizeof(char_t))); - if (!buffer) return false; - - // second pass: convert latin1 input to utf8 - memcpy(buffer, data, prefix_length); - - uint8_t* obegin = reinterpret_cast(buffer); - uint8_t* oend = latin1_decoder::process(postfix, postfix_length, obegin + prefix_length, utf8_writer()); - - assert(oend == obegin + length); - *oend = 0; - - out_buffer = buffer; - out_length = length + 1; - - return true; - } - - PUGI_IMPL_FN bool convert_buffer(char_t*& out_buffer, size_t& out_length, xml_encoding encoding, const void* contents, size_t size, bool is_mutable) - { - // fast path: no conversion required - if (encoding == encoding_utf8) - return get_mutable_buffer(out_buffer, out_length, contents, size, is_mutable); - - // source encoding is utf16 - if (encoding == encoding_utf16_be || encoding == encoding_utf16_le) - { - xml_encoding native_encoding = is_little_endian() ? encoding_utf16_le : encoding_utf16_be; - - return (native_encoding == encoding) ? - convert_buffer_generic(out_buffer, out_length, contents, size, utf16_decoder()) : - convert_buffer_generic(out_buffer, out_length, contents, size, utf16_decoder()); - } - - // source encoding is utf32 - if (encoding == encoding_utf32_be || encoding == encoding_utf32_le) - { - xml_encoding native_encoding = is_little_endian() ? encoding_utf32_le : encoding_utf32_be; - - return (native_encoding == encoding) ? - convert_buffer_generic(out_buffer, out_length, contents, size, utf32_decoder()) : - convert_buffer_generic(out_buffer, out_length, contents, size, utf32_decoder()); - } - - // source encoding is latin1 - if (encoding == encoding_latin1) - return convert_buffer_latin1(out_buffer, out_length, contents, size, is_mutable); - - assert(false && "Invalid encoding"); // unreachable - return false; - } -#endif - - PUGI_IMPL_FN size_t as_utf8_begin(const wchar_t* str, size_t length) - { - // get length in utf8 characters - return wchar_decoder::process(str, length, 0, utf8_counter()); - } - - PUGI_IMPL_FN void as_utf8_end(char* buffer, size_t size, const wchar_t* str, size_t length) - { - // convert to utf8 - uint8_t* begin = reinterpret_cast(buffer); - uint8_t* end = wchar_decoder::process(str, length, begin, utf8_writer()); - - assert(begin + size == end); - (void)!end; - (void)!size; - } - -#ifndef PUGIXML_NO_STL - PUGI_IMPL_FN std::string as_utf8_impl(const wchar_t* str, size_t length) - { - // first pass: get length in utf8 characters - size_t size = as_utf8_begin(str, length); - - // allocate resulting string - std::string result; - result.resize(size); - - // second pass: convert to utf8 - if (size > 0) as_utf8_end(&result[0], size, str, length); - - return result; - } - - PUGI_IMPL_FN std::basic_string as_wide_impl(const char* str, size_t size) - { - const uint8_t* data = reinterpret_cast(str); - - // first pass: get length in wchar_t units - size_t length = utf8_decoder::process(data, size, 0, wchar_counter()); - - // allocate resulting string - std::basic_string result; - result.resize(length); - - // second pass: convert to wchar_t - if (length > 0) - { - wchar_writer::value_type begin = reinterpret_cast(&result[0]); - wchar_writer::value_type end = utf8_decoder::process(data, size, begin, wchar_writer()); - - assert(begin + length == end); - (void)!end; - } - - return result; - } -#endif - - template - inline bool strcpy_insitu_allow(size_t length, const Header& header, uintptr_t header_mask, char_t* target) - { - // never reuse shared memory - if (header & xml_memory_page_contents_shared_mask) return false; - - size_t target_length = strlength(target); - - // always reuse document buffer memory if possible - if ((header & header_mask) == 0) return target_length >= length; - - // reuse heap memory if waste is not too great - const size_t reuse_threshold = 32; - - return target_length >= length && (target_length < reuse_threshold || target_length - length < target_length / 2); - } - - template - PUGI_IMPL_FN bool strcpy_insitu(String& dest, Header& header, uintptr_t header_mask, const char_t* source, size_t source_length) - { - assert((header & header_mask) == 0 || dest); // header bit indicates whether dest was previously allocated - - if (source_length == 0) - { - // empty string and null pointer are equivalent, so just deallocate old memory - xml_allocator* alloc = PUGI_IMPL_GETPAGE_IMPL(header)->allocator; - - if (header & header_mask) alloc->deallocate_string(dest); - - // mark the string as not allocated - dest = 0; - header &= ~header_mask; - - return true; - } - else if (dest && strcpy_insitu_allow(source_length, header, header_mask, dest)) - { - // we can reuse old buffer, so just copy the new data (including zero terminator) - memcpy(dest, source, source_length * sizeof(char_t)); - dest[source_length] = 0; - - return true; - } - else - { - xml_allocator* alloc = PUGI_IMPL_GETPAGE_IMPL(header)->allocator; - - if (!alloc->reserve()) return false; - - // allocate new buffer - char_t* buf = alloc->allocate_string(source_length + 1); - if (!buf) return false; - - // copy the string (including zero terminator) - memcpy(buf, source, source_length * sizeof(char_t)); - buf[source_length] = 0; - - // deallocate old buffer (*after* the above to protect against overlapping memory and/or allocation failures) - if (header & header_mask) alloc->deallocate_string(dest); - - // the string is now allocated, so set the flag - dest = buf; - header |= header_mask; - - return true; - } - } - - struct gap - { - char_t* end; - size_t size; - - gap(): end(0), size(0) - { - } - - // Push new gap, move s count bytes further (skipping the gap). - // Collapse previous gap. - void push(char_t*& s, size_t count) - { - if (end) // there was a gap already; collapse it - { - // Move [old_gap_end, new_gap_start) to [old_gap_start, ...) - assert(s >= end); - memmove(end - size, end, reinterpret_cast(s) - reinterpret_cast(end)); - } - - s += count; // end of current gap - - // "merge" two gaps - end = s; - size += count; - } - - // Collapse all gaps, return past-the-end pointer - char_t* flush(char_t* s) - { - if (end) - { - // Move [old_gap_end, current_pos) to [old_gap_start, ...) - assert(s >= end); - memmove(end - size, end, reinterpret_cast(s) - reinterpret_cast(end)); - - return s - size; - } - else return s; - } - }; - - PUGI_IMPL_FN char_t* strconv_escape(char_t* s, gap& g) - { - char_t* stre = s + 1; - - switch (*stre) - { - case '#': // &#... - { - unsigned int ucsc = 0; - - if (stre[1] == 'x') // &#x... (hex code) - { - stre += 2; - - char_t ch = *stre; - - if (ch == ';') return stre; - - for (;;) - { - if (static_cast(ch - '0') <= 9) - ucsc = 16 * ucsc + (ch - '0'); - else if (static_cast((ch | ' ') - 'a') <= 5) - ucsc = 16 * ucsc + ((ch | ' ') - 'a' + 10); - else if (ch == ';') - break; - else // cancel - return stre; - - ch = *++stre; - } - - ++stre; - } - else // &#... (dec code) - { - char_t ch = *++stre; - - if (ch == ';') return stre; - - for (;;) - { - if (static_cast(ch - '0') <= 9) - ucsc = 10 * ucsc + (ch - '0'); - else if (ch == ';') - break; - else // cancel - return stre; - - ch = *++stre; - } - - ++stre; - } - - #ifdef PUGIXML_WCHAR_MODE - s = reinterpret_cast(wchar_writer::any(reinterpret_cast(s), ucsc)); - #else - s = reinterpret_cast(utf8_writer::any(reinterpret_cast(s), ucsc)); - #endif - - g.push(s, stre - s); - return stre; - } - - case 'a': // &a - { - ++stre; - - if (*stre == 'm') // &am - { - if (*++stre == 'p' && *++stre == ';') // & - { - *s++ = '&'; - ++stre; - - g.push(s, stre - s); - return stre; - } - } - else if (*stre == 'p') // &ap - { - if (*++stre == 'o' && *++stre == 's' && *++stre == ';') // ' - { - *s++ = '\''; - ++stre; - - g.push(s, stre - s); - return stre; - } - } - break; - } - - case 'g': // &g - { - if (*++stre == 't' && *++stre == ';') // > - { - *s++ = '>'; - ++stre; - - g.push(s, stre - s); - return stre; - } - break; - } - - case 'l': // &l - { - if (*++stre == 't' && *++stre == ';') // < - { - *s++ = '<'; - ++stre; - - g.push(s, stre - s); - return stre; - } - break; - } - - case 'q': // &q - { - if (*++stre == 'u' && *++stre == 'o' && *++stre == 't' && *++stre == ';') // " - { - *s++ = '"'; - ++stre; - - g.push(s, stre - s); - return stre; - } - break; - } - - default: - break; - } - - return stre; - } - - // Parser utilities - #define PUGI_IMPL_ENDSWITH(c, e) ((c) == (e) || ((c) == 0 && endch == (e))) - #define PUGI_IMPL_SKIPWS() { while (PUGI_IMPL_IS_CHARTYPE(*s, ct_space)) ++s; } - #define PUGI_IMPL_OPTSET(OPT) ( optmsk & (OPT) ) - #define PUGI_IMPL_PUSHNODE(TYPE) { cursor = append_new_node(cursor, *alloc, TYPE); if (!cursor) PUGI_IMPL_THROW_ERROR(status_out_of_memory, s); } - #define PUGI_IMPL_POPNODE() { cursor = cursor->parent; } - #define PUGI_IMPL_SCANFOR(X) { while (*s != 0 && !(X)) ++s; } - #define PUGI_IMPL_SCANWHILE(X) { while (X) ++s; } - #define PUGI_IMPL_SCANWHILE_UNROLL(X) { for (;;) { char_t ss = s[0]; if (PUGI_IMPL_UNLIKELY(!(X))) { break; } ss = s[1]; if (PUGI_IMPL_UNLIKELY(!(X))) { s += 1; break; } ss = s[2]; if (PUGI_IMPL_UNLIKELY(!(X))) { s += 2; break; } ss = s[3]; if (PUGI_IMPL_UNLIKELY(!(X))) { s += 3; break; } s += 4; } } - #define PUGI_IMPL_ENDSEG() { ch = *s; *s = 0; ++s; } - #define PUGI_IMPL_THROW_ERROR(err, m) return error_offset = m, error_status = err, static_cast(0) - #define PUGI_IMPL_CHECK_ERROR(err, m) { if (*s == 0) PUGI_IMPL_THROW_ERROR(err, m); } - - PUGI_IMPL_FN char_t* strconv_comment(char_t* s, char_t endch) - { - gap g; - - while (true) - { - PUGI_IMPL_SCANWHILE_UNROLL(!PUGI_IMPL_IS_CHARTYPE(ss, ct_parse_comment)); - - if (*s == '\r') // Either a single 0x0d or 0x0d 0x0a pair - { - *s++ = '\n'; // replace first one with 0x0a - - if (*s == '\n') g.push(s, 1); - } - else if (s[0] == '-' && s[1] == '-' && PUGI_IMPL_ENDSWITH(s[2], '>')) // comment ends here - { - *g.flush(s) = 0; - - return s + (s[2] == '>' ? 3 : 2); - } - else if (*s == 0) - { - return 0; - } - else ++s; - } - } - - PUGI_IMPL_FN char_t* strconv_cdata(char_t* s, char_t endch) - { - gap g; - - while (true) - { - PUGI_IMPL_SCANWHILE_UNROLL(!PUGI_IMPL_IS_CHARTYPE(ss, ct_parse_cdata)); - - if (*s == '\r') // Either a single 0x0d or 0x0d 0x0a pair - { - *s++ = '\n'; // replace first one with 0x0a - - if (*s == '\n') g.push(s, 1); - } - else if (s[0] == ']' && s[1] == ']' && PUGI_IMPL_ENDSWITH(s[2], '>')) // CDATA ends here - { - *g.flush(s) = 0; - - return s + 1; - } - else if (*s == 0) - { - return 0; - } - else ++s; - } - } - - typedef char_t* (*strconv_pcdata_t)(char_t*); - - template struct strconv_pcdata_impl - { - static char_t* parse(char_t* s) - { - gap g; - - char_t* begin = s; - - while (true) - { - PUGI_IMPL_SCANWHILE_UNROLL(!PUGI_IMPL_IS_CHARTYPE(ss, ct_parse_pcdata)); - - if (*s == '<') // PCDATA ends here - { - char_t* end = g.flush(s); - - if (opt_trim::value) - while (end > begin && PUGI_IMPL_IS_CHARTYPE(end[-1], ct_space)) - --end; - - *end = 0; - - return s + 1; - } - else if (opt_eol::value && *s == '\r') // Either a single 0x0d or 0x0d 0x0a pair - { - *s++ = '\n'; // replace first one with 0x0a - - if (*s == '\n') g.push(s, 1); - } - else if (opt_escape::value && *s == '&') - { - s = strconv_escape(s, g); - } - else if (*s == 0) - { - char_t* end = g.flush(s); - - if (opt_trim::value) - while (end > begin && PUGI_IMPL_IS_CHARTYPE(end[-1], ct_space)) - --end; - - *end = 0; - - return s; - } - else ++s; - } - } - }; - - PUGI_IMPL_FN strconv_pcdata_t get_strconv_pcdata(unsigned int optmask) - { - PUGI_IMPL_STATIC_ASSERT(parse_escapes == 0x10 && parse_eol == 0x20 && parse_trim_pcdata == 0x0800); - - switch (((optmask >> 4) & 3) | ((optmask >> 9) & 4)) // get bitmask for flags (trim eol escapes); this simultaneously checks 3 options from assertion above - { - case 0: return strconv_pcdata_impl::parse; - case 1: return strconv_pcdata_impl::parse; - case 2: return strconv_pcdata_impl::parse; - case 3: return strconv_pcdata_impl::parse; - case 4: return strconv_pcdata_impl::parse; - case 5: return strconv_pcdata_impl::parse; - case 6: return strconv_pcdata_impl::parse; - case 7: return strconv_pcdata_impl::parse; - default: assert(false); return 0; // unreachable - } - } - - typedef char_t* (*strconv_attribute_t)(char_t*, char_t); - - template struct strconv_attribute_impl - { - static char_t* parse_wnorm(char_t* s, char_t end_quote) - { - gap g; - - // trim leading whitespaces - if (PUGI_IMPL_IS_CHARTYPE(*s, ct_space)) - { - char_t* str = s; - - do ++str; - while (PUGI_IMPL_IS_CHARTYPE(*str, ct_space)); - - g.push(s, str - s); - } - - while (true) - { - PUGI_IMPL_SCANWHILE_UNROLL(!PUGI_IMPL_IS_CHARTYPE(ss, ct_parse_attr_ws | ct_space)); - - if (*s == end_quote) - { - char_t* str = g.flush(s); - - do *str-- = 0; - while (PUGI_IMPL_IS_CHARTYPE(*str, ct_space)); - - return s + 1; - } - else if (PUGI_IMPL_IS_CHARTYPE(*s, ct_space)) - { - *s++ = ' '; - - if (PUGI_IMPL_IS_CHARTYPE(*s, ct_space)) - { - char_t* str = s + 1; - while (PUGI_IMPL_IS_CHARTYPE(*str, ct_space)) ++str; - - g.push(s, str - s); - } - } - else if (opt_escape::value && *s == '&') - { - s = strconv_escape(s, g); - } - else if (!*s) - { - return 0; - } - else ++s; - } - } - - static char_t* parse_wconv(char_t* s, char_t end_quote) - { - gap g; - - while (true) - { - PUGI_IMPL_SCANWHILE_UNROLL(!PUGI_IMPL_IS_CHARTYPE(ss, ct_parse_attr_ws)); - - if (*s == end_quote) - { - *g.flush(s) = 0; - - return s + 1; - } - else if (PUGI_IMPL_IS_CHARTYPE(*s, ct_space)) - { - if (*s == '\r') - { - *s++ = ' '; - - if (*s == '\n') g.push(s, 1); - } - else *s++ = ' '; - } - else if (opt_escape::value && *s == '&') - { - s = strconv_escape(s, g); - } - else if (!*s) - { - return 0; - } - else ++s; - } - } - - static char_t* parse_eol(char_t* s, char_t end_quote) - { - gap g; - - while (true) - { - PUGI_IMPL_SCANWHILE_UNROLL(!PUGI_IMPL_IS_CHARTYPE(ss, ct_parse_attr)); - - if (*s == end_quote) - { - *g.flush(s) = 0; - - return s + 1; - } - else if (*s == '\r') - { - *s++ = '\n'; - - if (*s == '\n') g.push(s, 1); - } - else if (opt_escape::value && *s == '&') - { - s = strconv_escape(s, g); - } - else if (!*s) - { - return 0; - } - else ++s; - } - } - - static char_t* parse_simple(char_t* s, char_t end_quote) - { - gap g; - - while (true) - { - PUGI_IMPL_SCANWHILE_UNROLL(!PUGI_IMPL_IS_CHARTYPE(ss, ct_parse_attr)); - - if (*s == end_quote) - { - *g.flush(s) = 0; - - return s + 1; - } - else if (opt_escape::value && *s == '&') - { - s = strconv_escape(s, g); - } - else if (!*s) - { - return 0; - } - else ++s; - } - } - }; - - PUGI_IMPL_FN strconv_attribute_t get_strconv_attribute(unsigned int optmask) - { - PUGI_IMPL_STATIC_ASSERT(parse_escapes == 0x10 && parse_eol == 0x20 && parse_wconv_attribute == 0x40 && parse_wnorm_attribute == 0x80); - - switch ((optmask >> 4) & 15) // get bitmask for flags (wnorm wconv eol escapes); this simultaneously checks 4 options from assertion above - { - case 0: return strconv_attribute_impl::parse_simple; - case 1: return strconv_attribute_impl::parse_simple; - case 2: return strconv_attribute_impl::parse_eol; - case 3: return strconv_attribute_impl::parse_eol; - case 4: return strconv_attribute_impl::parse_wconv; - case 5: return strconv_attribute_impl::parse_wconv; - case 6: return strconv_attribute_impl::parse_wconv; - case 7: return strconv_attribute_impl::parse_wconv; - case 8: return strconv_attribute_impl::parse_wnorm; - case 9: return strconv_attribute_impl::parse_wnorm; - case 10: return strconv_attribute_impl::parse_wnorm; - case 11: return strconv_attribute_impl::parse_wnorm; - case 12: return strconv_attribute_impl::parse_wnorm; - case 13: return strconv_attribute_impl::parse_wnorm; - case 14: return strconv_attribute_impl::parse_wnorm; - case 15: return strconv_attribute_impl::parse_wnorm; - default: assert(false); return 0; // unreachable - } - } - - inline xml_parse_result make_parse_result(xml_parse_status status, ptrdiff_t offset = 0) - { - xml_parse_result result; - result.status = status; - result.offset = offset; - - return result; - } - - struct xml_parser - { - xml_allocator* alloc; - char_t* error_offset; - xml_parse_status error_status; - - xml_parser(xml_allocator* alloc_): alloc(alloc_), error_offset(0), error_status(status_ok) - { - } - - // DOCTYPE consists of nested sections of the following possible types: - // , , "...", '...' - // - // - // First group can not contain nested groups - // Second group can contain nested groups of the same type - // Third group can contain all other groups - char_t* parse_doctype_primitive(char_t* s) - { - if (*s == '"' || *s == '\'') - { - // quoted string - char_t ch = *s++; - PUGI_IMPL_SCANFOR(*s == ch); - if (!*s) PUGI_IMPL_THROW_ERROR(status_bad_doctype, s); - - s++; - } - else if (s[0] == '<' && s[1] == '?') - { - // - s += 2; - PUGI_IMPL_SCANFOR(s[0] == '?' && s[1] == '>'); // no need for ENDSWITH because ?> can't terminate proper doctype - if (!*s) PUGI_IMPL_THROW_ERROR(status_bad_doctype, s); - - s += 2; - } - else if (s[0] == '<' && s[1] == '!' && s[2] == '-' && s[3] == '-') - { - s += 4; - PUGI_IMPL_SCANFOR(s[0] == '-' && s[1] == '-' && s[2] == '>'); // no need for ENDSWITH because --> can't terminate proper doctype - if (!*s) PUGI_IMPL_THROW_ERROR(status_bad_doctype, s); - - s += 3; - } - else PUGI_IMPL_THROW_ERROR(status_bad_doctype, s); - - return s; - } - - char_t* parse_doctype_ignore(char_t* s) - { - size_t depth = 0; - - assert(s[0] == '<' && s[1] == '!' && s[2] == '['); - s += 3; - - while (*s) - { - if (s[0] == '<' && s[1] == '!' && s[2] == '[') - { - // nested ignore section - s += 3; - depth++; - } - else if (s[0] == ']' && s[1] == ']' && s[2] == '>') - { - // ignore section end - s += 3; - - if (depth == 0) - return s; - - depth--; - } - else s++; - } - - PUGI_IMPL_THROW_ERROR(status_bad_doctype, s); - } - - char_t* parse_doctype_group(char_t* s, char_t endch) - { - size_t depth = 0; - - assert((s[0] == '<' || s[0] == 0) && s[1] == '!'); - s += 2; - - while (*s) - { - if (s[0] == '<' && s[1] == '!' && s[2] != '-') - { - if (s[2] == '[') - { - // ignore - s = parse_doctype_ignore(s); - if (!s) return s; - } - else - { - // some control group - s += 2; - depth++; - } - } - else if (s[0] == '<' || s[0] == '"' || s[0] == '\'') - { - // unknown tag (forbidden), or some primitive group - s = parse_doctype_primitive(s); - if (!s) return s; - } - else if (*s == '>') - { - if (depth == 0) - return s; - - depth--; - s++; - } - else s++; - } - - if (depth != 0 || endch != '>') PUGI_IMPL_THROW_ERROR(status_bad_doctype, s); - - return s; - } - - char_t* parse_exclamation(char_t* s, xml_node_struct* cursor, unsigned int optmsk, char_t endch) - { - // parse node contents, starting with exclamation mark - ++s; - - if (*s == '-') // 'value = s; // Save the offset. - } - - if (PUGI_IMPL_OPTSET(parse_eol) && PUGI_IMPL_OPTSET(parse_comments)) - { - s = strconv_comment(s, endch); - - if (!s) PUGI_IMPL_THROW_ERROR(status_bad_comment, cursor->value); - } - else - { - // Scan for terminating '-->'. - PUGI_IMPL_SCANFOR(s[0] == '-' && s[1] == '-' && PUGI_IMPL_ENDSWITH(s[2], '>')); - PUGI_IMPL_CHECK_ERROR(status_bad_comment, s); - - if (PUGI_IMPL_OPTSET(parse_comments)) - *s = 0; // Zero-terminate this segment at the first terminating '-'. - - s += (s[2] == '>' ? 3 : 2); // Step over the '\0->'. - } - } - else PUGI_IMPL_THROW_ERROR(status_bad_comment, s); - } - else if (*s == '[') - { - // 'value = s; // Save the offset. - - if (PUGI_IMPL_OPTSET(parse_eol)) - { - s = strconv_cdata(s, endch); - - if (!s) PUGI_IMPL_THROW_ERROR(status_bad_cdata, cursor->value); - } - else - { - // Scan for terminating ']]>'. - PUGI_IMPL_SCANFOR(s[0] == ']' && s[1] == ']' && PUGI_IMPL_ENDSWITH(s[2], '>')); - PUGI_IMPL_CHECK_ERROR(status_bad_cdata, s); - - *s++ = 0; // Zero-terminate this segment. - } - } - else // Flagged for discard, but we still have to scan for the terminator. - { - // Scan for terminating ']]>'. - PUGI_IMPL_SCANFOR(s[0] == ']' && s[1] == ']' && PUGI_IMPL_ENDSWITH(s[2], '>')); - PUGI_IMPL_CHECK_ERROR(status_bad_cdata, s); - - ++s; - } - - s += (s[1] == '>' ? 2 : 1); // Step over the last ']>'. - } - else PUGI_IMPL_THROW_ERROR(status_bad_cdata, s); - } - else if (s[0] == 'D' && s[1] == 'O' && s[2] == 'C' && s[3] == 'T' && s[4] == 'Y' && s[5] == 'P' && PUGI_IMPL_ENDSWITH(s[6], 'E')) - { - s -= 2; - - if (cursor->parent) PUGI_IMPL_THROW_ERROR(status_bad_doctype, s); - - char_t* mark = s + 9; - - s = parse_doctype_group(s, endch); - if (!s) return s; - - assert((*s == 0 && endch == '>') || *s == '>'); - if (*s) *s++ = 0; - - if (PUGI_IMPL_OPTSET(parse_doctype)) - { - while (PUGI_IMPL_IS_CHARTYPE(*mark, ct_space)) ++mark; - - PUGI_IMPL_PUSHNODE(node_doctype); - - cursor->value = mark; - } - } - else if (*s == 0 && endch == '-') PUGI_IMPL_THROW_ERROR(status_bad_comment, s); - else if (*s == 0 && endch == '[') PUGI_IMPL_THROW_ERROR(status_bad_cdata, s); - else PUGI_IMPL_THROW_ERROR(status_unrecognized_tag, s); - - return s; - } - - char_t* parse_question(char_t* s, xml_node_struct*& ref_cursor, unsigned int optmsk, char_t endch) - { - // load into registers - xml_node_struct* cursor = ref_cursor; - char_t ch = 0; - - // parse node contents, starting with question mark - ++s; - - // read PI target - char_t* target = s; - - if (!PUGI_IMPL_IS_CHARTYPE(*s, ct_start_symbol)) PUGI_IMPL_THROW_ERROR(status_bad_pi, s); - - PUGI_IMPL_SCANWHILE(PUGI_IMPL_IS_CHARTYPE(*s, ct_symbol)); - PUGI_IMPL_CHECK_ERROR(status_bad_pi, s); - - // determine node type; stricmp / strcasecmp is not portable - bool declaration = (target[0] | ' ') == 'x' && (target[1] | ' ') == 'm' && (target[2] | ' ') == 'l' && target + 3 == s; - - if (declaration ? PUGI_IMPL_OPTSET(parse_declaration) : PUGI_IMPL_OPTSET(parse_pi)) - { - if (declaration) - { - // disallow non top-level declarations - if (cursor->parent) PUGI_IMPL_THROW_ERROR(status_bad_pi, s); - - PUGI_IMPL_PUSHNODE(node_declaration); - } - else - { - PUGI_IMPL_PUSHNODE(node_pi); - } - - cursor->name = target; - - PUGI_IMPL_ENDSEG(); - - // parse value/attributes - if (ch == '?') - { - // empty node - if (!PUGI_IMPL_ENDSWITH(*s, '>')) PUGI_IMPL_THROW_ERROR(status_bad_pi, s); - s += (*s == '>'); - - PUGI_IMPL_POPNODE(); - } - else if (PUGI_IMPL_IS_CHARTYPE(ch, ct_space)) - { - PUGI_IMPL_SKIPWS(); - - // scan for tag end - char_t* value = s; - - PUGI_IMPL_SCANFOR(s[0] == '?' && PUGI_IMPL_ENDSWITH(s[1], '>')); - PUGI_IMPL_CHECK_ERROR(status_bad_pi, s); - - if (declaration) - { - // replace ending ? with / so that 'element' terminates properly - *s = '/'; - - // we exit from this function with cursor at node_declaration, which is a signal to parse() to go to LOC_ATTRIBUTES - s = value; - } - else - { - // store value and step over > - cursor->value = value; - - PUGI_IMPL_POPNODE(); - - PUGI_IMPL_ENDSEG(); - - s += (*s == '>'); - } - } - else PUGI_IMPL_THROW_ERROR(status_bad_pi, s); - } - else - { - // scan for tag end - PUGI_IMPL_SCANFOR(s[0] == '?' && PUGI_IMPL_ENDSWITH(s[1], '>')); - PUGI_IMPL_CHECK_ERROR(status_bad_pi, s); - - s += (s[1] == '>' ? 2 : 1); - } - - // store from registers - ref_cursor = cursor; - - return s; - } - - char_t* parse_tree(char_t* s, xml_node_struct* root, unsigned int optmsk, char_t endch) - { - strconv_attribute_t strconv_attribute = get_strconv_attribute(optmsk); - strconv_pcdata_t strconv_pcdata = get_strconv_pcdata(optmsk); - - char_t ch = 0; - xml_node_struct* cursor = root; - char_t* mark = s; - char_t* merged_pcdata = s; - - while (*s != 0) - { - if (*s == '<') - { - ++s; - - LOC_TAG: - if (PUGI_IMPL_IS_CHARTYPE(*s, ct_start_symbol)) // '<#...' - { - PUGI_IMPL_PUSHNODE(node_element); // Append a new node to the tree. - - cursor->name = s; - - PUGI_IMPL_SCANWHILE_UNROLL(PUGI_IMPL_IS_CHARTYPE(ss, ct_symbol)); // Scan for a terminator. - PUGI_IMPL_ENDSEG(); // Save char in 'ch', terminate & step over. - - if (ch == '>') - { - // end of tag - } - else if (PUGI_IMPL_IS_CHARTYPE(ch, ct_space)) - { - LOC_ATTRIBUTES: - while (true) - { - PUGI_IMPL_SKIPWS(); // Eat any whitespace. - - if (PUGI_IMPL_IS_CHARTYPE(*s, ct_start_symbol)) // <... #... - { - xml_attribute_struct* a = append_new_attribute(cursor, *alloc); // Make space for this attribute. - if (!a) PUGI_IMPL_THROW_ERROR(status_out_of_memory, s); - - a->name = s; // Save the offset. - - PUGI_IMPL_SCANWHILE_UNROLL(PUGI_IMPL_IS_CHARTYPE(ss, ct_symbol)); // Scan for a terminator. - PUGI_IMPL_ENDSEG(); // Save char in 'ch', terminate & step over. - - if (PUGI_IMPL_IS_CHARTYPE(ch, ct_space)) - { - PUGI_IMPL_SKIPWS(); // Eat any whitespace. - - ch = *s; - ++s; - } - - if (ch == '=') // '<... #=...' - { - PUGI_IMPL_SKIPWS(); // Eat any whitespace. - - if (*s == '"' || *s == '\'') // '<... #="...' - { - ch = *s; // Save quote char to avoid breaking on "''" -or- '""'. - ++s; // Step over the quote. - a->value = s; // Save the offset. - - s = strconv_attribute(s, ch); - - if (!s) PUGI_IMPL_THROW_ERROR(status_bad_attribute, a->value); - - // After this line the loop continues from the start; - // Whitespaces, / and > are ok, symbols and EOF are wrong, - // everything else will be detected - if (PUGI_IMPL_IS_CHARTYPE(*s, ct_start_symbol)) PUGI_IMPL_THROW_ERROR(status_bad_attribute, s); - } - else PUGI_IMPL_THROW_ERROR(status_bad_attribute, s); - } - else PUGI_IMPL_THROW_ERROR(status_bad_attribute, s); - } - else if (*s == '/') - { - ++s; - - if (*s == '>') - { - PUGI_IMPL_POPNODE(); - s++; - break; - } - else if (*s == 0 && endch == '>') - { - PUGI_IMPL_POPNODE(); - break; - } - else PUGI_IMPL_THROW_ERROR(status_bad_start_element, s); - } - else if (*s == '>') - { - ++s; - - break; - } - else if (*s == 0 && endch == '>') - { - break; - } - else PUGI_IMPL_THROW_ERROR(status_bad_start_element, s); - } - - // !!! - } - else if (ch == '/') // '<#.../' - { - if (!PUGI_IMPL_ENDSWITH(*s, '>')) PUGI_IMPL_THROW_ERROR(status_bad_start_element, s); - - PUGI_IMPL_POPNODE(); // Pop. - - s += (*s == '>'); - } - else if (ch == 0) - { - // we stepped over null terminator, backtrack & handle closing tag - --s; - - if (endch != '>') PUGI_IMPL_THROW_ERROR(status_bad_start_element, s); - } - else PUGI_IMPL_THROW_ERROR(status_bad_start_element, s); - } - else if (*s == '/') - { - ++s; - - mark = s; - - char_t* name = cursor->name; - if (!name) PUGI_IMPL_THROW_ERROR(status_end_element_mismatch, mark); - - while (PUGI_IMPL_IS_CHARTYPE(*s, ct_symbol)) - { - if (*s++ != *name++) PUGI_IMPL_THROW_ERROR(status_end_element_mismatch, mark); - } - - if (*name) - { - if (*s == 0 && name[0] == endch && name[1] == 0) PUGI_IMPL_THROW_ERROR(status_bad_end_element, s); - else PUGI_IMPL_THROW_ERROR(status_end_element_mismatch, mark); - } - - PUGI_IMPL_POPNODE(); // Pop. - - PUGI_IMPL_SKIPWS(); - - if (*s == 0) - { - if (endch != '>') PUGI_IMPL_THROW_ERROR(status_bad_end_element, s); - } - else - { - if (*s != '>') PUGI_IMPL_THROW_ERROR(status_bad_end_element, s); - ++s; - } - } - else if (*s == '?') // 'first_child) continue; - } - } - - if (!PUGI_IMPL_OPTSET(parse_trim_pcdata)) - s = mark; - - if (cursor->parent || PUGI_IMPL_OPTSET(parse_fragment)) - { - char_t* parsed_pcdata = s; - - s = strconv_pcdata(s); - - if (PUGI_IMPL_OPTSET(parse_embed_pcdata) && cursor->parent && !cursor->first_child && !cursor->value) - { - cursor->value = parsed_pcdata; // Save the offset. - } - else if (PUGI_IMPL_OPTSET(parse_merge_pcdata) && cursor->first_child && PUGI_IMPL_NODETYPE(cursor->first_child->prev_sibling_c) == node_pcdata) - { - assert(merged_pcdata >= cursor->first_child->prev_sibling_c->value); - - // Catch up to the end of last parsed value; only needed for the first fragment. - merged_pcdata += strlength(merged_pcdata); - - size_t length = strlength(parsed_pcdata); - - // Must use memmove instead of memcpy as this move may overlap - memmove(merged_pcdata, parsed_pcdata, (length + 1) * sizeof(char_t)); - merged_pcdata += length; - } - else - { - xml_node_struct* prev_cursor = cursor; - PUGI_IMPL_PUSHNODE(node_pcdata); // Append a new node on the tree. - - cursor->value = parsed_pcdata; // Save the offset. - merged_pcdata = parsed_pcdata; // Used for parse_merge_pcdata above, cheaper to save unconditionally - - cursor = prev_cursor; // Pop since this is a standalone. - } - - if (!*s) break; - } - else - { - PUGI_IMPL_SCANFOR(*s == '<'); // '...<' - if (!*s) break; - - ++s; - } - - // We're after '<' - goto LOC_TAG; - } - } - - // check that last tag is closed - if (cursor != root) PUGI_IMPL_THROW_ERROR(status_end_element_mismatch, s); - - return s; - } - - #ifdef PUGIXML_WCHAR_MODE - static char_t* parse_skip_bom(char_t* s) - { - unsigned int bom = 0xfeff; - return (s[0] == static_cast(bom)) ? s + 1 : s; - } - #else - static char_t* parse_skip_bom(char_t* s) - { - return (s[0] == '\xef' && s[1] == '\xbb' && s[2] == '\xbf') ? s + 3 : s; - } - #endif - - static bool has_element_node_siblings(xml_node_struct* node) - { - while (node) - { - if (PUGI_IMPL_NODETYPE(node) == node_element) return true; - - node = node->next_sibling; - } - - return false; - } - - static xml_parse_result parse(char_t* buffer, size_t length, xml_document_struct* xmldoc, xml_node_struct* root, unsigned int optmsk) - { - // early-out for empty documents - if (length == 0) - return make_parse_result(PUGI_IMPL_OPTSET(parse_fragment) ? status_ok : status_no_document_element); - - // get last child of the root before parsing - xml_node_struct* last_root_child = root->first_child ? root->first_child->prev_sibling_c + 0 : 0; - - // create parser on stack - xml_parser parser(static_cast(xmldoc)); - - // save last character and make buffer zero-terminated (speeds up parsing) - char_t endch = buffer[length - 1]; - buffer[length - 1] = 0; - - // skip BOM to make sure it does not end up as part of parse output - char_t* buffer_data = parse_skip_bom(buffer); - - // perform actual parsing - parser.parse_tree(buffer_data, root, optmsk, endch); - - xml_parse_result result = make_parse_result(parser.error_status, parser.error_offset ? parser.error_offset - buffer : 0); - assert(result.offset >= 0 && static_cast(result.offset) <= length); - - if (result) - { - // since we removed last character, we have to handle the only possible false positive (stray <) - if (endch == '<') - return make_parse_result(status_unrecognized_tag, length - 1); - - // check if there are any element nodes parsed - xml_node_struct* first_root_child_parsed = last_root_child ? last_root_child->next_sibling + 0 : root->first_child + 0; - - if (!PUGI_IMPL_OPTSET(parse_fragment) && !has_element_node_siblings(first_root_child_parsed)) - return make_parse_result(status_no_document_element, length - 1); - } - else - { - // roll back offset if it occurs on a null terminator in the source buffer - if (result.offset > 0 && static_cast(result.offset) == length - 1 && endch == 0) - result.offset--; - } - - return result; - } - }; - - // Output facilities - PUGI_IMPL_FN xml_encoding get_write_native_encoding() - { - #ifdef PUGIXML_WCHAR_MODE - return get_wchar_encoding(); - #else - return encoding_utf8; - #endif - } - - PUGI_IMPL_FN xml_encoding get_write_encoding(xml_encoding encoding) - { - // replace wchar encoding with utf implementation - if (encoding == encoding_wchar) return get_wchar_encoding(); - - // replace utf16 encoding with utf16 with specific endianness - if (encoding == encoding_utf16) return is_little_endian() ? encoding_utf16_le : encoding_utf16_be; - - // replace utf32 encoding with utf32 with specific endianness - if (encoding == encoding_utf32) return is_little_endian() ? encoding_utf32_le : encoding_utf32_be; - - // only do autodetection if no explicit encoding is requested - if (encoding != encoding_auto) return encoding; - - // assume utf8 encoding - return encoding_utf8; - } - - template PUGI_IMPL_FN size_t convert_buffer_output_generic(typename T::value_type dest, const char_t* data, size_t length, D, T) - { - PUGI_IMPL_STATIC_ASSERT(sizeof(char_t) == sizeof(typename D::type)); - - typename T::value_type end = D::process(reinterpret_cast(data), length, dest, T()); - - return static_cast(end - dest) * sizeof(*dest); - } - - template PUGI_IMPL_FN size_t convert_buffer_output_generic(typename T::value_type dest, const char_t* data, size_t length, D, T, bool opt_swap) - { - PUGI_IMPL_STATIC_ASSERT(sizeof(char_t) == sizeof(typename D::type)); - - typename T::value_type end = D::process(reinterpret_cast(data), length, dest, T()); - - if (opt_swap) - { - for (typename T::value_type i = dest; i != end; ++i) - *i = endian_swap(*i); - } - - return static_cast(end - dest) * sizeof(*dest); - } - -#ifdef PUGIXML_WCHAR_MODE - PUGI_IMPL_FN size_t get_valid_length(const char_t* data, size_t length) - { - if (length < 1) return 0; - - // discard last character if it's the lead of a surrogate pair - return (sizeof(wchar_t) == 2 && static_cast(static_cast(data[length - 1]) - 0xD800) < 0x400) ? length - 1 : length; - } - - PUGI_IMPL_FN size_t convert_buffer_output(char_t* r_char, uint8_t* r_u8, uint16_t* r_u16, uint32_t* r_u32, const char_t* data, size_t length, xml_encoding encoding) - { - // only endian-swapping is required - if (need_endian_swap_utf(encoding, get_wchar_encoding())) - { - convert_wchar_endian_swap(r_char, data, length); - - return length * sizeof(char_t); - } - - // convert to utf8 - if (encoding == encoding_utf8) - return convert_buffer_output_generic(r_u8, data, length, wchar_decoder(), utf8_writer()); - - // convert to utf16 - if (encoding == encoding_utf16_be || encoding == encoding_utf16_le) - { - xml_encoding native_encoding = is_little_endian() ? encoding_utf16_le : encoding_utf16_be; - - return convert_buffer_output_generic(r_u16, data, length, wchar_decoder(), utf16_writer(), native_encoding != encoding); - } - - // convert to utf32 - if (encoding == encoding_utf32_be || encoding == encoding_utf32_le) - { - xml_encoding native_encoding = is_little_endian() ? encoding_utf32_le : encoding_utf32_be; - - return convert_buffer_output_generic(r_u32, data, length, wchar_decoder(), utf32_writer(), native_encoding != encoding); - } - - // convert to latin1 - if (encoding == encoding_latin1) - return convert_buffer_output_generic(r_u8, data, length, wchar_decoder(), latin1_writer()); - - assert(false && "Invalid encoding"); // unreachable - return 0; - } -#else - PUGI_IMPL_FN size_t get_valid_length(const char_t* data, size_t length) - { - if (length < 5) return 0; - - for (size_t i = 1; i <= 4; ++i) - { - uint8_t ch = static_cast(data[length - i]); - - // either a standalone character or a leading one - if ((ch & 0xc0) != 0x80) return length - i; - } - - // there are four non-leading characters at the end, sequence tail is broken so might as well process the whole chunk - return length; - } - - PUGI_IMPL_FN size_t convert_buffer_output(char_t* /* r_char */, uint8_t* r_u8, uint16_t* r_u16, uint32_t* r_u32, const char_t* data, size_t length, xml_encoding encoding) - { - if (encoding == encoding_utf16_be || encoding == encoding_utf16_le) - { - xml_encoding native_encoding = is_little_endian() ? encoding_utf16_le : encoding_utf16_be; - - return convert_buffer_output_generic(r_u16, data, length, utf8_decoder(), utf16_writer(), native_encoding != encoding); - } - - if (encoding == encoding_utf32_be || encoding == encoding_utf32_le) - { - xml_encoding native_encoding = is_little_endian() ? encoding_utf32_le : encoding_utf32_be; - - return convert_buffer_output_generic(r_u32, data, length, utf8_decoder(), utf32_writer(), native_encoding != encoding); - } - - if (encoding == encoding_latin1) - return convert_buffer_output_generic(r_u8, data, length, utf8_decoder(), latin1_writer()); - - assert(false && "Invalid encoding"); // unreachable - return 0; - } -#endif - - class xml_buffered_writer - { - xml_buffered_writer(const xml_buffered_writer&); - xml_buffered_writer& operator=(const xml_buffered_writer&); - - public: - xml_buffered_writer(xml_writer& writer_, xml_encoding user_encoding): writer(writer_), bufsize(0), encoding(get_write_encoding(user_encoding)) - { - PUGI_IMPL_STATIC_ASSERT(bufcapacity >= 8); - } - - size_t flush() - { - flush(buffer, bufsize); - bufsize = 0; - return 0; - } - - void flush(const char_t* data, size_t size) - { - if (size == 0) return; - - // fast path, just write data - if (encoding == get_write_native_encoding()) - writer.write(data, size * sizeof(char_t)); - else - { - // convert chunk - size_t result = convert_buffer_output(scratch.data_char, scratch.data_u8, scratch.data_u16, scratch.data_u32, data, size, encoding); - assert(result <= sizeof(scratch)); - - // write data - writer.write(scratch.data_u8, result); - } - } - - void write_direct(const char_t* data, size_t length) - { - // flush the remaining buffer contents - flush(); - - // handle large chunks - if (length > bufcapacity) - { - if (encoding == get_write_native_encoding()) - { - // fast path, can just write data chunk - writer.write(data, length * sizeof(char_t)); - return; - } - - // need to convert in suitable chunks - while (length > bufcapacity) - { - // get chunk size by selecting such number of characters that are guaranteed to fit into scratch buffer - // and form a complete codepoint sequence (i.e. discard start of last codepoint if necessary) - size_t chunk_size = get_valid_length(data, bufcapacity); - assert(chunk_size); - - // convert chunk and write - flush(data, chunk_size); - - // iterate - data += chunk_size; - length -= chunk_size; - } - - // small tail is copied below - bufsize = 0; - } - - memcpy(buffer + bufsize, data, length * sizeof(char_t)); - bufsize += length; - } - - void write_buffer(const char_t* data, size_t length) - { - size_t offset = bufsize; - - if (offset + length <= bufcapacity) - { - memcpy(buffer + offset, data, length * sizeof(char_t)); - bufsize = offset + length; - } - else - { - write_direct(data, length); - } - } - - void write_string(const char_t* data) - { - // write the part of the string that fits in the buffer - size_t offset = bufsize; - - while (*data && offset < bufcapacity) - buffer[offset++] = *data++; - - // write the rest - if (offset < bufcapacity) - { - bufsize = offset; - } - else - { - // backtrack a bit if we have split the codepoint - size_t length = offset - bufsize; - size_t extra = length - get_valid_length(data - length, length); - - bufsize = offset - extra; - - write_direct(data - extra, strlength(data) + extra); - } - } - - void write(char_t d0) - { - size_t offset = bufsize; - if (offset > bufcapacity - 1) offset = flush(); - - buffer[offset + 0] = d0; - bufsize = offset + 1; - } - - void write(char_t d0, char_t d1) - { - size_t offset = bufsize; - if (offset > bufcapacity - 2) offset = flush(); - - buffer[offset + 0] = d0; - buffer[offset + 1] = d1; - bufsize = offset + 2; - } - - void write(char_t d0, char_t d1, char_t d2) - { - size_t offset = bufsize; - if (offset > bufcapacity - 3) offset = flush(); - - buffer[offset + 0] = d0; - buffer[offset + 1] = d1; - buffer[offset + 2] = d2; - bufsize = offset + 3; - } - - void write(char_t d0, char_t d1, char_t d2, char_t d3) - { - size_t offset = bufsize; - if (offset > bufcapacity - 4) offset = flush(); - - buffer[offset + 0] = d0; - buffer[offset + 1] = d1; - buffer[offset + 2] = d2; - buffer[offset + 3] = d3; - bufsize = offset + 4; - } - - void write(char_t d0, char_t d1, char_t d2, char_t d3, char_t d4) - { - size_t offset = bufsize; - if (offset > bufcapacity - 5) offset = flush(); - - buffer[offset + 0] = d0; - buffer[offset + 1] = d1; - buffer[offset + 2] = d2; - buffer[offset + 3] = d3; - buffer[offset + 4] = d4; - bufsize = offset + 5; - } - - void write(char_t d0, char_t d1, char_t d2, char_t d3, char_t d4, char_t d5) - { - size_t offset = bufsize; - if (offset > bufcapacity - 6) offset = flush(); - - buffer[offset + 0] = d0; - buffer[offset + 1] = d1; - buffer[offset + 2] = d2; - buffer[offset + 3] = d3; - buffer[offset + 4] = d4; - buffer[offset + 5] = d5; - bufsize = offset + 6; - } - - // utf8 maximum expansion: x4 (-> utf32) - // utf16 maximum expansion: x2 (-> utf32) - // utf32 maximum expansion: x1 - enum - { - bufcapacitybytes = - #ifdef PUGIXML_MEMORY_OUTPUT_STACK - PUGIXML_MEMORY_OUTPUT_STACK - #else - 10240 - #endif - , - bufcapacity = bufcapacitybytes / (sizeof(char_t) + 4) - }; - - char_t buffer[bufcapacity]; - - union - { - uint8_t data_u8[4 * bufcapacity]; - uint16_t data_u16[2 * bufcapacity]; - uint32_t data_u32[bufcapacity]; - char_t data_char[bufcapacity]; - } scratch; - - xml_writer& writer; - size_t bufsize; - xml_encoding encoding; - }; - - PUGI_IMPL_FN void text_output_escaped(xml_buffered_writer& writer, const char_t* s, chartypex_t type, unsigned int flags) - { - while (*s) - { - const char_t* prev = s; - - // While *s is a usual symbol - PUGI_IMPL_SCANWHILE_UNROLL(!PUGI_IMPL_IS_CHARTYPEX(ss, type)); - - writer.write_buffer(prev, static_cast(s - prev)); - - switch (*s) - { - case 0: break; - case '&': - writer.write('&', 'a', 'm', 'p', ';'); - ++s; - break; - case '<': - writer.write('&', 'l', 't', ';'); - ++s; - break; - case '>': - writer.write('&', 'g', 't', ';'); - ++s; - break; - case '"': - if (flags & format_attribute_single_quote) - writer.write('"'); - else - writer.write('&', 'q', 'u', 'o', 't', ';'); - ++s; - break; - case '\'': - if (flags & format_attribute_single_quote) - writer.write('&', 'a', 'p', 'o', 's', ';'); - else - writer.write('\''); - ++s; - break; - default: // s is not a usual symbol - { - unsigned int ch = static_cast(*s++); - assert(ch < 32); - - if (!(flags & format_skip_control_chars)) - writer.write('&', '#', static_cast((ch / 10) + '0'), static_cast((ch % 10) + '0'), ';'); - } - } - } - } - - PUGI_IMPL_FN void text_output(xml_buffered_writer& writer, const char_t* s, chartypex_t type, unsigned int flags) - { - if (flags & format_no_escapes) - writer.write_string(s); - else - text_output_escaped(writer, s, type, flags); - } - - PUGI_IMPL_FN void text_output_cdata(xml_buffered_writer& writer, const char_t* s) - { - do - { - writer.write('<', '!', '[', 'C', 'D'); - writer.write('A', 'T', 'A', '['); - - const char_t* prev = s; - - // look for ]]> sequence - we can't output it as is since it terminates CDATA - while (*s && !(s[0] == ']' && s[1] == ']' && s[2] == '>')) ++s; - - // skip ]] if we stopped at ]]>, > will go to the next CDATA section - if (*s) s += 2; - - writer.write_buffer(prev, static_cast(s - prev)); - - writer.write(']', ']', '>'); - } - while (*s); - } - - PUGI_IMPL_FN void text_output_indent(xml_buffered_writer& writer, const char_t* indent, size_t indent_length, unsigned int depth) - { - switch (indent_length) - { - case 1: - { - for (unsigned int i = 0; i < depth; ++i) - writer.write(indent[0]); - break; - } - - case 2: - { - for (unsigned int i = 0; i < depth; ++i) - writer.write(indent[0], indent[1]); - break; - } - - case 3: - { - for (unsigned int i = 0; i < depth; ++i) - writer.write(indent[0], indent[1], indent[2]); - break; - } - - case 4: - { - for (unsigned int i = 0; i < depth; ++i) - writer.write(indent[0], indent[1], indent[2], indent[3]); - break; - } - - default: - { - for (unsigned int i = 0; i < depth; ++i) - writer.write_buffer(indent, indent_length); - } - } - } - - PUGI_IMPL_FN void node_output_comment(xml_buffered_writer& writer, const char_t* s) - { - writer.write('<', '!', '-', '-'); - - while (*s) - { - const char_t* prev = s; - - // look for -\0 or -- sequence - we can't output it since -- is illegal in comment body - while (*s && !(s[0] == '-' && (s[1] == '-' || s[1] == 0))) ++s; - - writer.write_buffer(prev, static_cast(s - prev)); - - if (*s) - { - assert(*s == '-'); - - writer.write('-', ' '); - ++s; - } - } - - writer.write('-', '-', '>'); - } - - PUGI_IMPL_FN void node_output_pi_value(xml_buffered_writer& writer, const char_t* s) - { - while (*s) - { - const char_t* prev = s; - - // look for ?> sequence - we can't output it since ?> terminates PI - while (*s && !(s[0] == '?' && s[1] == '>')) ++s; - - writer.write_buffer(prev, static_cast(s - prev)); - - if (*s) - { - assert(s[0] == '?' && s[1] == '>'); - - writer.write('?', ' ', '>'); - s += 2; - } - } - } - - PUGI_IMPL_FN void node_output_attributes(xml_buffered_writer& writer, xml_node_struct* node, const char_t* indent, size_t indent_length, unsigned int flags, unsigned int depth) - { - const char_t* default_name = PUGIXML_TEXT(":anonymous"); - const char_t enquotation_char = (flags & format_attribute_single_quote) ? '\'' : '"'; - - for (xml_attribute_struct* a = node->first_attribute; a; a = a->next_attribute) - { - if ((flags & (format_indent_attributes | format_raw)) == format_indent_attributes) - { - writer.write('\n'); - - text_output_indent(writer, indent, indent_length, depth + 1); - } - else - { - writer.write(' '); - } - - writer.write_string(a->name ? a->name + 0 : default_name); - writer.write('=', enquotation_char); - - if (a->value) - text_output(writer, a->value, ctx_special_attr, flags); - - writer.write(enquotation_char); - } - } - - PUGI_IMPL_FN bool node_output_start(xml_buffered_writer& writer, xml_node_struct* node, const char_t* indent, size_t indent_length, unsigned int flags, unsigned int depth) - { - const char_t* default_name = PUGIXML_TEXT(":anonymous"); - const char_t* name = node->name ? node->name + 0 : default_name; - - writer.write('<'); - writer.write_string(name); - - if (node->first_attribute) - node_output_attributes(writer, node, indent, indent_length, flags, depth); - - // element nodes can have value if parse_embed_pcdata was used - if (!node->value) - { - if (!node->first_child) - { - if (flags & format_no_empty_element_tags) - { - writer.write('>', '<', '/'); - writer.write_string(name); - writer.write('>'); - - return false; - } - else - { - if ((flags & format_raw) == 0) - writer.write(' '); - - writer.write('/', '>'); - - return false; - } - } - else - { - writer.write('>'); - - return true; - } - } - else - { - writer.write('>'); - - text_output(writer, node->value, ctx_special_pcdata, flags); - - if (!node->first_child) - { - writer.write('<', '/'); - writer.write_string(name); - writer.write('>'); - - return false; - } - else - { - return true; - } - } - } - - PUGI_IMPL_FN void node_output_end(xml_buffered_writer& writer, xml_node_struct* node) - { - const char_t* default_name = PUGIXML_TEXT(":anonymous"); - const char_t* name = node->name ? node->name + 0 : default_name; - - writer.write('<', '/'); - writer.write_string(name); - writer.write('>'); - } - - PUGI_IMPL_FN void node_output_simple(xml_buffered_writer& writer, xml_node_struct* node, unsigned int flags) - { - const char_t* default_name = PUGIXML_TEXT(":anonymous"); - - switch (PUGI_IMPL_NODETYPE(node)) - { - case node_pcdata: - text_output(writer, node->value ? node->value + 0 : PUGIXML_TEXT(""), ctx_special_pcdata, flags); - break; - - case node_cdata: - text_output_cdata(writer, node->value ? node->value + 0 : PUGIXML_TEXT("")); - break; - - case node_comment: - node_output_comment(writer, node->value ? node->value + 0 : PUGIXML_TEXT("")); - break; - - case node_pi: - writer.write('<', '?'); - writer.write_string(node->name ? node->name + 0 : default_name); - - if (node->value) - { - writer.write(' '); - node_output_pi_value(writer, node->value); - } - - writer.write('?', '>'); - break; - - case node_declaration: - writer.write('<', '?'); - writer.write_string(node->name ? node->name + 0 : default_name); - node_output_attributes(writer, node, PUGIXML_TEXT(""), 0, flags | format_raw, 0); - writer.write('?', '>'); - break; - - case node_doctype: - writer.write('<', '!', 'D', 'O', 'C'); - writer.write('T', 'Y', 'P', 'E'); - - if (node->value) - { - writer.write(' '); - writer.write_string(node->value); - } - - writer.write('>'); - break; - - default: - assert(false && "Invalid node type"); // unreachable - } - } - - enum indent_flags_t - { - indent_newline = 1, - indent_indent = 2 - }; - - PUGI_IMPL_FN void node_output(xml_buffered_writer& writer, xml_node_struct* root, const char_t* indent, unsigned int flags, unsigned int depth) - { - size_t indent_length = ((flags & (format_indent | format_indent_attributes)) && (flags & format_raw) == 0) ? strlength(indent) : 0; - unsigned int indent_flags = indent_indent; - - xml_node_struct* node = root; - - do - { - assert(node); - - // begin writing current node - if (PUGI_IMPL_NODETYPE(node) == node_pcdata || PUGI_IMPL_NODETYPE(node) == node_cdata) - { - node_output_simple(writer, node, flags); - - indent_flags = 0; - } - else - { - if ((indent_flags & indent_newline) && (flags & format_raw) == 0) - writer.write('\n'); - - if ((indent_flags & indent_indent) && indent_length) - text_output_indent(writer, indent, indent_length, depth); - - if (PUGI_IMPL_NODETYPE(node) == node_element) - { - indent_flags = indent_newline | indent_indent; - - if (node_output_start(writer, node, indent, indent_length, flags, depth)) - { - // element nodes can have value if parse_embed_pcdata was used - if (node->value) - indent_flags = 0; - - node = node->first_child; - depth++; - continue; - } - } - else if (PUGI_IMPL_NODETYPE(node) == node_document) - { - indent_flags = indent_indent; - - if (node->first_child) - { - node = node->first_child; - continue; - } - } - else - { - node_output_simple(writer, node, flags); - - indent_flags = indent_newline | indent_indent; - } - } - - // continue to the next node - while (node != root) - { - if (node->next_sibling) - { - node = node->next_sibling; - break; - } - - node = node->parent; - - // write closing node - if (PUGI_IMPL_NODETYPE(node) == node_element) - { - depth--; - - if ((indent_flags & indent_newline) && (flags & format_raw) == 0) - writer.write('\n'); - - if ((indent_flags & indent_indent) && indent_length) - text_output_indent(writer, indent, indent_length, depth); - - node_output_end(writer, node); - - indent_flags = indent_newline | indent_indent; - } - } - } - while (node != root); - - if ((indent_flags & indent_newline) && (flags & format_raw) == 0) - writer.write('\n'); - } - - PUGI_IMPL_FN bool has_declaration(xml_node_struct* node) - { - for (xml_node_struct* child = node->first_child; child; child = child->next_sibling) - { - xml_node_type type = PUGI_IMPL_NODETYPE(child); - - if (type == node_declaration) return true; - if (type == node_element) return false; - } - - return false; - } - - PUGI_IMPL_FN bool is_attribute_of(xml_attribute_struct* attr, xml_node_struct* node) - { - for (xml_attribute_struct* a = node->first_attribute; a; a = a->next_attribute) - if (a == attr) - return true; - - return false; - } - - PUGI_IMPL_FN bool allow_insert_attribute(xml_node_type parent) - { - return parent == node_element || parent == node_declaration; - } - - PUGI_IMPL_FN bool allow_insert_child(xml_node_type parent, xml_node_type child) - { - if (parent != node_document && parent != node_element) return false; - if (child == node_document || child == node_null) return false; - if (parent != node_document && (child == node_declaration || child == node_doctype)) return false; - - return true; - } - - PUGI_IMPL_FN bool allow_move(xml_node parent, xml_node child) - { - // check that child can be a child of parent - if (!allow_insert_child(parent.type(), child.type())) - return false; - - // check that node is not moved between documents - if (parent.root() != child.root()) - return false; - - // check that new parent is not in the child subtree - xml_node cur = parent; - - while (cur) - { - if (cur == child) - return false; - - cur = cur.parent(); - } - - return true; - } - - template - PUGI_IMPL_FN void node_copy_string(String& dest, Header& header, uintptr_t header_mask, char_t* source, Header& source_header, xml_allocator* alloc) - { - assert(!dest && (header & header_mask) == 0); // copies are performed into fresh nodes - - if (source) - { - if (alloc && (source_header & header_mask) == 0) - { - dest = source; - - // since strcpy_insitu can reuse document buffer memory we need to mark both source and dest as shared - header |= xml_memory_page_contents_shared_mask; - source_header |= xml_memory_page_contents_shared_mask; - } - else - strcpy_insitu(dest, header, header_mask, source, strlength(source)); - } - } - - PUGI_IMPL_FN void node_copy_contents(xml_node_struct* dn, xml_node_struct* sn, xml_allocator* shared_alloc) - { - node_copy_string(dn->name, dn->header, xml_memory_page_name_allocated_mask, sn->name, sn->header, shared_alloc); - node_copy_string(dn->value, dn->header, xml_memory_page_value_allocated_mask, sn->value, sn->header, shared_alloc); - - for (xml_attribute_struct* sa = sn->first_attribute; sa; sa = sa->next_attribute) - { - xml_attribute_struct* da = append_new_attribute(dn, get_allocator(dn)); - - if (da) - { - node_copy_string(da->name, da->header, xml_memory_page_name_allocated_mask, sa->name, sa->header, shared_alloc); - node_copy_string(da->value, da->header, xml_memory_page_value_allocated_mask, sa->value, sa->header, shared_alloc); - } - } - } - - PUGI_IMPL_FN void node_copy_tree(xml_node_struct* dn, xml_node_struct* sn) - { - xml_allocator& alloc = get_allocator(dn); - xml_allocator* shared_alloc = (&alloc == &get_allocator(sn)) ? &alloc : 0; - - node_copy_contents(dn, sn, shared_alloc); - - xml_node_struct* dit = dn; - xml_node_struct* sit = sn->first_child; - - while (sit && sit != sn) - { - // loop invariant: dit is inside the subtree rooted at dn - assert(dit); - - // when a tree is copied into one of the descendants, we need to skip that subtree to avoid an infinite loop - if (sit != dn) - { - xml_node_struct* copy = append_new_node(dit, alloc, PUGI_IMPL_NODETYPE(sit)); - - if (copy) - { - node_copy_contents(copy, sit, shared_alloc); - - if (sit->first_child) - { - dit = copy; - sit = sit->first_child; - continue; - } - } - } - - // continue to the next node - do - { - if (sit->next_sibling) - { - sit = sit->next_sibling; - break; - } - - sit = sit->parent; - dit = dit->parent; - - // loop invariant: dit is inside the subtree rooted at dn while sit is inside sn - assert(sit == sn || dit); - } - while (sit != sn); - } - - assert(!sit || dit == dn->parent); - } - - PUGI_IMPL_FN void node_copy_attribute(xml_attribute_struct* da, xml_attribute_struct* sa) - { - xml_allocator& alloc = get_allocator(da); - xml_allocator* shared_alloc = (&alloc == &get_allocator(sa)) ? &alloc : 0; - - node_copy_string(da->name, da->header, xml_memory_page_name_allocated_mask, sa->name, sa->header, shared_alloc); - node_copy_string(da->value, da->header, xml_memory_page_value_allocated_mask, sa->value, sa->header, shared_alloc); - } - - inline bool is_text_node(xml_node_struct* node) - { - xml_node_type type = PUGI_IMPL_NODETYPE(node); - - return type == node_pcdata || type == node_cdata; - } - - // get value with conversion functions - template PUGI_IMPL_FN PUGI_IMPL_UNSIGNED_OVERFLOW U string_to_integer(const char_t* value, U minv, U maxv) - { - U result = 0; - const char_t* s = value; - - while (PUGI_IMPL_IS_CHARTYPE(*s, ct_space)) - s++; - - bool negative = (*s == '-'); - - s += (*s == '+' || *s == '-'); - - bool overflow = false; - - if (s[0] == '0' && (s[1] | ' ') == 'x') - { - s += 2; - - // since overflow detection relies on length of the sequence skip leading zeros - while (*s == '0') - s++; - - const char_t* start = s; - - for (;;) - { - if (static_cast(*s - '0') < 10) - result = result * 16 + (*s - '0'); - else if (static_cast((*s | ' ') - 'a') < 6) - result = result * 16 + ((*s | ' ') - 'a' + 10); - else - break; - - s++; - } - - size_t digits = static_cast(s - start); - - overflow = digits > sizeof(U) * 2; - } - else - { - // since overflow detection relies on length of the sequence skip leading zeros - while (*s == '0') - s++; - - const char_t* start = s; - - for (;;) - { - if (static_cast(*s - '0') < 10) - result = result * 10 + (*s - '0'); - else - break; - - s++; - } - - size_t digits = static_cast(s - start); - - PUGI_IMPL_STATIC_ASSERT(sizeof(U) == 8 || sizeof(U) == 4 || sizeof(U) == 2); - - const size_t max_digits10 = sizeof(U) == 8 ? 20 : sizeof(U) == 4 ? 10 : 5; - const char_t max_lead = sizeof(U) == 8 ? '1' : sizeof(U) == 4 ? '4' : '6'; - const size_t high_bit = sizeof(U) * 8 - 1; - - overflow = digits >= max_digits10 && !(digits == max_digits10 && (*start < max_lead || (*start == max_lead && result >> high_bit))); - } - - if (negative) - { - // Workaround for crayc++ CC-3059: Expected no overflow in routine. - #ifdef _CRAYC - return (overflow || result > ~minv + 1) ? minv : ~result + 1; - #else - return (overflow || result > 0 - minv) ? minv : 0 - result; - #endif - } - else - return (overflow || result > maxv) ? maxv : result; - } - - PUGI_IMPL_FN int get_value_int(const char_t* value) - { - return string_to_integer(value, static_cast(INT_MIN), INT_MAX); - } - - PUGI_IMPL_FN unsigned int get_value_uint(const char_t* value) - { - return string_to_integer(value, 0, UINT_MAX); - } - - PUGI_IMPL_FN double get_value_double(const char_t* value) - { - #ifdef PUGIXML_WCHAR_MODE - return wcstod(value, 0); - #else - return strtod(value, 0); - #endif - } - - PUGI_IMPL_FN float get_value_float(const char_t* value) - { - #ifdef PUGIXML_WCHAR_MODE - return static_cast(wcstod(value, 0)); - #else - return static_cast(strtod(value, 0)); - #endif - } - - PUGI_IMPL_FN bool get_value_bool(const char_t* value) - { - // only look at first char - char_t first = *value; - - // 1*, t* (true), T* (True), y* (yes), Y* (YES) - return (first == '1' || first == 't' || first == 'T' || first == 'y' || first == 'Y'); - } - -#ifdef PUGIXML_HAS_LONG_LONG - PUGI_IMPL_FN long long get_value_llong(const char_t* value) - { - return string_to_integer(value, static_cast(LLONG_MIN), LLONG_MAX); - } - - PUGI_IMPL_FN unsigned long long get_value_ullong(const char_t* value) - { - return string_to_integer(value, 0, ULLONG_MAX); - } -#endif - - template PUGI_IMPL_FN PUGI_IMPL_UNSIGNED_OVERFLOW char_t* integer_to_string(char_t* begin, char_t* end, U value, bool negative) - { - char_t* result = end - 1; - U rest = negative ? 0 - value : value; - - do - { - *result-- = static_cast('0' + (rest % 10)); - rest /= 10; - } - while (rest); - - assert(result >= begin); - (void)begin; - - *result = '-'; - - return result + !negative; - } - - // set value with conversion functions - template - PUGI_IMPL_FN bool set_value_ascii(String& dest, Header& header, uintptr_t header_mask, char* buf) - { - #ifdef PUGIXML_WCHAR_MODE - char_t wbuf[128]; - assert(strlen(buf) < sizeof(wbuf) / sizeof(wbuf[0])); - - size_t offset = 0; - for (; buf[offset]; ++offset) wbuf[offset] = buf[offset]; - - return strcpy_insitu(dest, header, header_mask, wbuf, offset); - #else - return strcpy_insitu(dest, header, header_mask, buf, strlen(buf)); - #endif - } - - template - PUGI_IMPL_FN bool set_value_integer(String& dest, Header& header, uintptr_t header_mask, U value, bool negative) - { - char_t buf[64]; - char_t* end = buf + sizeof(buf) / sizeof(buf[0]); - char_t* begin = integer_to_string(buf, end, value, negative); - - return strcpy_insitu(dest, header, header_mask, begin, end - begin); - } - - template - PUGI_IMPL_FN bool set_value_convert(String& dest, Header& header, uintptr_t header_mask, float value, int precision) - { - char buf[128]; - PUGI_IMPL_SNPRINTF(buf, "%.*g", precision, double(value)); - - return set_value_ascii(dest, header, header_mask, buf); - } - - template - PUGI_IMPL_FN bool set_value_convert(String& dest, Header& header, uintptr_t header_mask, double value, int precision) - { - char buf[128]; - PUGI_IMPL_SNPRINTF(buf, "%.*g", precision, value); - - return set_value_ascii(dest, header, header_mask, buf); - } - - template - PUGI_IMPL_FN bool set_value_bool(String& dest, Header& header, uintptr_t header_mask, bool value) - { - return strcpy_insitu(dest, header, header_mask, value ? PUGIXML_TEXT("true") : PUGIXML_TEXT("false"), value ? 4 : 5); - } - - PUGI_IMPL_FN xml_parse_result load_buffer_impl(xml_document_struct* doc, xml_node_struct* root, void* contents, size_t size, unsigned int options, xml_encoding encoding, bool is_mutable, bool own, char_t** out_buffer) - { - // check input buffer - if (!contents && size) return make_parse_result(status_io_error); - - // get actual encoding - xml_encoding buffer_encoding = impl::get_buffer_encoding(encoding, contents, size); - - // if convert_buffer below throws bad_alloc, we still need to deallocate contents if we own it - auto_deleter contents_guard(own ? contents : 0, xml_memory::deallocate); - - // get private buffer - char_t* buffer = 0; - size_t length = 0; - - // coverity[var_deref_model] - if (!impl::convert_buffer(buffer, length, buffer_encoding, contents, size, is_mutable)) return impl::make_parse_result(status_out_of_memory); - - // after this we either deallocate contents (below) or hold on to it via doc->buffer, so we don't need to guard it - contents_guard.release(); - - // delete original buffer if we performed a conversion - if (own && buffer != contents && contents) impl::xml_memory::deallocate(contents); - - // grab onto buffer if it's our buffer, user is responsible for deallocating contents himself - if (own || buffer != contents) *out_buffer = buffer; - - // store buffer for offset_debug - doc->buffer = buffer; - - // parse - xml_parse_result res = impl::xml_parser::parse(buffer, length, doc, root, options); - - // remember encoding - res.encoding = buffer_encoding; - - return res; - } - - // we need to get length of entire file to load it in memory; the only (relatively) sane way to do it is via seek/tell trick - PUGI_IMPL_FN xml_parse_status get_file_size(FILE* file, size_t& out_result) - { - #if defined(__linux__) || defined(__APPLE__) - // this simultaneously retrieves the file size and file mode (to guard against loading non-files) - struct stat st; - if (fstat(fileno(file), &st) != 0) return status_io_error; - - // anything that's not a regular file doesn't have a coherent length - if (!S_ISREG(st.st_mode)) return status_io_error; - - typedef off_t length_type; - length_type length = st.st_size; - #elif defined(PUGI_IMPL_MSVC_CRT_VERSION) && PUGI_IMPL_MSVC_CRT_VERSION >= 1400 - // there are 64-bit versions of fseek/ftell, let's use them - typedef __int64 length_type; - - _fseeki64(file, 0, SEEK_END); - length_type length = _ftelli64(file); - _fseeki64(file, 0, SEEK_SET); - #elif defined(__MINGW32__) && !defined(__NO_MINGW_LFS) && (!defined(__STRICT_ANSI__) || defined(__MINGW64_VERSION_MAJOR)) - // there are 64-bit versions of fseek/ftell, let's use them - typedef off64_t length_type; - - fseeko64(file, 0, SEEK_END); - length_type length = ftello64(file); - fseeko64(file, 0, SEEK_SET); - #else - // if this is a 32-bit OS, long is enough; if this is a unix system, long is 64-bit, which is enough; otherwise we can't do anything anyway. - typedef long length_type; - - fseek(file, 0, SEEK_END); - length_type length = ftell(file); - fseek(file, 0, SEEK_SET); - #endif - - // check for I/O errors - if (length < 0) return status_io_error; - - // check for overflow - size_t result = static_cast(length); - - if (static_cast(result) != length) return status_out_of_memory; - - // finalize - out_result = result; - - return status_ok; - } - - // This function assumes that buffer has extra sizeof(char_t) writable bytes after size - PUGI_IMPL_FN size_t zero_terminate_buffer(void* buffer, size_t size, xml_encoding encoding) - { - // We only need to zero-terminate if encoding conversion does not do it for us - #ifdef PUGIXML_WCHAR_MODE - xml_encoding wchar_encoding = get_wchar_encoding(); - - if (encoding == wchar_encoding || need_endian_swap_utf(encoding, wchar_encoding)) - { - size_t length = size / sizeof(char_t); - - static_cast(buffer)[length] = 0; - return (length + 1) * sizeof(char_t); - } - #else - if (encoding == encoding_utf8) - { - static_cast(buffer)[size] = 0; - return size + 1; - } - #endif - - return size; - } - - PUGI_IMPL_FN xml_parse_result load_file_impl(xml_document_struct* doc, FILE* file, unsigned int options, xml_encoding encoding, char_t** out_buffer) - { - if (!file) return make_parse_result(status_file_not_found); - - // get file size (can result in I/O errors) - size_t size = 0; - xml_parse_status size_status = get_file_size(file, size); - if (size_status != status_ok) return make_parse_result(size_status); - - size_t max_suffix_size = sizeof(char_t); - - // allocate buffer for the whole file - char* contents = static_cast(xml_memory::allocate(size + max_suffix_size)); - if (!contents) return make_parse_result(status_out_of_memory); - - // read file in memory - size_t read_size = fread(contents, 1, size, file); - - if (read_size != size) - { - xml_memory::deallocate(contents); - return make_parse_result(status_io_error); - } - - xml_encoding real_encoding = get_buffer_encoding(encoding, contents, size); - - return load_buffer_impl(doc, doc, contents, zero_terminate_buffer(contents, size, real_encoding), options, real_encoding, true, true, out_buffer); - } - - PUGI_IMPL_FN void close_file(FILE* file) - { - fclose(file); - } - -#ifndef PUGIXML_NO_STL - template struct xml_stream_chunk - { - static xml_stream_chunk* create() - { - void* memory = xml_memory::allocate(sizeof(xml_stream_chunk)); - if (!memory) return 0; - - return new (memory) xml_stream_chunk(); - } - - static void destroy(xml_stream_chunk* chunk) - { - // free chunk chain - while (chunk) - { - xml_stream_chunk* next_ = chunk->next; - - xml_memory::deallocate(chunk); - - chunk = next_; - } - } - - xml_stream_chunk(): next(0), size(0) - { - } - - xml_stream_chunk* next; - size_t size; - - T data[xml_memory_page_size / sizeof(T)]; - }; - - template PUGI_IMPL_FN xml_parse_status load_stream_data_noseek(std::basic_istream& stream, void** out_buffer, size_t* out_size) - { - auto_deleter > chunks(0, xml_stream_chunk::destroy); - - // read file to a chunk list - size_t total = 0; - xml_stream_chunk* last = 0; - - while (!stream.eof()) - { - // allocate new chunk - xml_stream_chunk* chunk = xml_stream_chunk::create(); - if (!chunk) return status_out_of_memory; - - // append chunk to list - if (last) last = last->next = chunk; - else chunks.data = last = chunk; - - // read data to chunk - stream.read(chunk->data, static_cast(sizeof(chunk->data) / sizeof(T))); - chunk->size = static_cast(stream.gcount()) * sizeof(T); - - // read may set failbit | eofbit in case gcount() is less than read length, so check for other I/O errors - if (stream.bad() || (!stream.eof() && stream.fail())) return status_io_error; - - // guard against huge files (chunk size is small enough to make this overflow check work) - if (total + chunk->size < total) return status_out_of_memory; - total += chunk->size; - } - - size_t max_suffix_size = sizeof(char_t); - - // copy chunk list to a contiguous buffer - char* buffer = static_cast(xml_memory::allocate(total + max_suffix_size)); - if (!buffer) return status_out_of_memory; - - char* write = buffer; - - for (xml_stream_chunk* chunk = chunks.data; chunk; chunk = chunk->next) - { - assert(write + chunk->size <= buffer + total); - memcpy(write, chunk->data, chunk->size); - write += chunk->size; - } - - assert(write == buffer + total); - - // return buffer - *out_buffer = buffer; - *out_size = total; - - return status_ok; - } - - template PUGI_IMPL_FN xml_parse_status load_stream_data_seek(std::basic_istream& stream, void** out_buffer, size_t* out_size) - { - // get length of remaining data in stream - typename std::basic_istream::pos_type pos = stream.tellg(); - stream.seekg(0, std::ios::end); - std::streamoff length = stream.tellg() - pos; - stream.seekg(pos); - - if (stream.fail() || pos < 0) return status_io_error; - - // guard against huge files - size_t read_length = static_cast(length); - - if (static_cast(read_length) != length || length < 0) return status_out_of_memory; - - size_t max_suffix_size = sizeof(char_t); - - // read stream data into memory (guard against stream exceptions with buffer holder) - auto_deleter buffer(xml_memory::allocate(read_length * sizeof(T) + max_suffix_size), xml_memory::deallocate); - if (!buffer.data) return status_out_of_memory; - - stream.read(static_cast(buffer.data), static_cast(read_length)); - - // read may set failbit | eofbit in case gcount() is less than read_length (i.e. line ending conversion), so check for other I/O errors - if (stream.bad() || (!stream.eof() && stream.fail())) return status_io_error; - - // return buffer - size_t actual_length = static_cast(stream.gcount()); - assert(actual_length <= read_length); - - *out_buffer = buffer.release(); - *out_size = actual_length * sizeof(T); - - return status_ok; - } - - template PUGI_IMPL_FN xml_parse_result load_stream_impl(xml_document_struct* doc, std::basic_istream& stream, unsigned int options, xml_encoding encoding, char_t** out_buffer) - { - void* buffer = 0; - size_t size = 0; - xml_parse_status status = status_ok; - - // if stream has an error bit set, bail out (otherwise tellg() can fail and we'll clear error bits) - if (stream.fail()) return make_parse_result(status_io_error); - - // load stream to memory (using seek-based implementation if possible, since it's faster and takes less memory) - if (stream.tellg() < 0) - { - stream.clear(); // clear error flags that could be set by a failing tellg - status = load_stream_data_noseek(stream, &buffer, &size); - } - else - status = load_stream_data_seek(stream, &buffer, &size); - - if (status != status_ok) return make_parse_result(status); - - xml_encoding real_encoding = get_buffer_encoding(encoding, buffer, size); - - return load_buffer_impl(doc, doc, buffer, zero_terminate_buffer(buffer, size, real_encoding), options, real_encoding, true, true, out_buffer); - } -#endif - -#if defined(PUGI_IMPL_MSVC_CRT_VERSION) || defined(__BORLANDC__) || (defined(__MINGW32__) && (!defined(__STRICT_ANSI__) || defined(__MINGW64_VERSION_MAJOR))) - PUGI_IMPL_FN FILE* open_file_wide(const wchar_t* path, const wchar_t* mode) - { -#if defined(PUGI_IMPL_MSVC_CRT_VERSION) && PUGI_IMPL_MSVC_CRT_VERSION >= 1400 - FILE* file = 0; - return _wfopen_s(&file, path, mode) == 0 ? file : 0; -#else - return _wfopen(path, mode); -#endif - } -#else - PUGI_IMPL_FN char* convert_path_heap(const wchar_t* str) - { - assert(str); - - // first pass: get length in utf8 characters - size_t length = strlength_wide(str); - size_t size = as_utf8_begin(str, length); - - // allocate resulting string - char* result = static_cast(xml_memory::allocate(size + 1)); - if (!result) return 0; - - // second pass: convert to utf8 - as_utf8_end(result, size, str, length); - - // zero-terminate - result[size] = 0; - - return result; - } - - PUGI_IMPL_FN FILE* open_file_wide(const wchar_t* path, const wchar_t* mode) - { - // there is no standard function to open wide paths, so our best bet is to try utf8 path - char* path_utf8 = convert_path_heap(path); - if (!path_utf8) return 0; - - // convert mode to ASCII (we mirror _wfopen interface) - char mode_ascii[4] = {0}; - for (size_t i = 0; mode[i]; ++i) mode_ascii[i] = static_cast(mode[i]); - - // try to open the utf8 path - FILE* result = fopen(path_utf8, mode_ascii); - - // free dummy buffer - xml_memory::deallocate(path_utf8); - - return result; - } -#endif - - PUGI_IMPL_FN FILE* open_file(const char* path, const char* mode) - { -#if defined(PUGI_IMPL_MSVC_CRT_VERSION) && PUGI_IMPL_MSVC_CRT_VERSION >= 1400 - FILE* file = 0; - return fopen_s(&file, path, mode) == 0 ? file : 0; -#else - return fopen(path, mode); -#endif - } - - PUGI_IMPL_FN bool save_file_impl(const xml_document& doc, FILE* file, const char_t* indent, unsigned int flags, xml_encoding encoding) - { - if (!file) return false; - - xml_writer_file writer(file); - doc.save(writer, indent, flags, encoding); - - return fflush(file) == 0 && ferror(file) == 0; - } - - struct name_null_sentry - { - xml_node_struct* node; - char_t* name; - - name_null_sentry(xml_node_struct* node_): node(node_), name(node_->name) - { - node->name = 0; - } - - ~name_null_sentry() - { - node->name = name; - } - }; -PUGI_IMPL_NS_END - -namespace pugi -{ - PUGI_IMPL_FN xml_writer::~xml_writer() - { - } - - PUGI_IMPL_FN xml_writer_file::xml_writer_file(void* file_): file(file_) - { - } - - PUGI_IMPL_FN void xml_writer_file::write(const void* data, size_t size) - { - size_t result = fwrite(data, 1, size, static_cast(file)); - (void)!result; // unfortunately we can't do proper error handling here - } - -#ifndef PUGIXML_NO_STL - PUGI_IMPL_FN xml_writer_stream::xml_writer_stream(std::basic_ostream >& stream): narrow_stream(&stream), wide_stream(0) - { - } - - PUGI_IMPL_FN xml_writer_stream::xml_writer_stream(std::basic_ostream >& stream): narrow_stream(0), wide_stream(&stream) - { - } - - PUGI_IMPL_FN void xml_writer_stream::write(const void* data, size_t size) - { - if (narrow_stream) - { - assert(!wide_stream); - narrow_stream->write(reinterpret_cast(data), static_cast(size)); - } - else - { - assert(wide_stream); - assert(size % sizeof(wchar_t) == 0); - - wide_stream->write(reinterpret_cast(data), static_cast(size / sizeof(wchar_t))); - } - } -#endif - - PUGI_IMPL_FN xml_tree_walker::xml_tree_walker(): _depth(0) - { - } - - PUGI_IMPL_FN xml_tree_walker::~xml_tree_walker() - { - } - - PUGI_IMPL_FN int xml_tree_walker::depth() const - { - return _depth; - } - - PUGI_IMPL_FN bool xml_tree_walker::begin(xml_node&) - { - return true; - } - - PUGI_IMPL_FN bool xml_tree_walker::end(xml_node&) - { - return true; - } - - PUGI_IMPL_FN xml_attribute::xml_attribute(): _attr(0) - { - } - - PUGI_IMPL_FN xml_attribute::xml_attribute(xml_attribute_struct* attr): _attr(attr) - { - } - - PUGI_IMPL_FN static void unspecified_bool_xml_attribute(xml_attribute***) - { - } - - PUGI_IMPL_FN xml_attribute::operator xml_attribute::unspecified_bool_type() const - { - return _attr ? unspecified_bool_xml_attribute : 0; - } - - PUGI_IMPL_FN bool xml_attribute::operator!() const - { - return !_attr; - } - - PUGI_IMPL_FN bool xml_attribute::operator==(const xml_attribute& r) const - { - return (_attr == r._attr); - } - - PUGI_IMPL_FN bool xml_attribute::operator!=(const xml_attribute& r) const - { - return (_attr != r._attr); - } - - PUGI_IMPL_FN bool xml_attribute::operator<(const xml_attribute& r) const - { - return (_attr < r._attr); - } - - PUGI_IMPL_FN bool xml_attribute::operator>(const xml_attribute& r) const - { - return (_attr > r._attr); - } - - PUGI_IMPL_FN bool xml_attribute::operator<=(const xml_attribute& r) const - { - return (_attr <= r._attr); - } - - PUGI_IMPL_FN bool xml_attribute::operator>=(const xml_attribute& r) const - { - return (_attr >= r._attr); - } - - PUGI_IMPL_FN xml_attribute xml_attribute::next_attribute() const - { - if (!_attr) return xml_attribute(); - return xml_attribute(_attr->next_attribute); - } - - PUGI_IMPL_FN xml_attribute xml_attribute::previous_attribute() const - { - if (!_attr) return xml_attribute(); - xml_attribute_struct* prev = _attr->prev_attribute_c; - return prev->next_attribute ? xml_attribute(prev) : xml_attribute(); - } - - PUGI_IMPL_FN const char_t* xml_attribute::as_string(const char_t* def) const - { - if (!_attr) return def; - const char_t* value = _attr->value; - return value ? value : def; - } - - PUGI_IMPL_FN int xml_attribute::as_int(int def) const - { - if (!_attr) return def; - const char_t* value = _attr->value; - return value ? impl::get_value_int(value) : def; - } - - PUGI_IMPL_FN unsigned int xml_attribute::as_uint(unsigned int def) const - { - if (!_attr) return def; - const char_t* value = _attr->value; - return value ? impl::get_value_uint(value) : def; - } - - PUGI_IMPL_FN double xml_attribute::as_double(double def) const - { - if (!_attr) return def; - const char_t* value = _attr->value; - return value ? impl::get_value_double(value) : def; - } - - PUGI_IMPL_FN float xml_attribute::as_float(float def) const - { - if (!_attr) return def; - const char_t* value = _attr->value; - return value ? impl::get_value_float(value) : def; - } - - PUGI_IMPL_FN bool xml_attribute::as_bool(bool def) const - { - if (!_attr) return def; - const char_t* value = _attr->value; - return value ? impl::get_value_bool(value) : def; - } - -#ifdef PUGIXML_HAS_LONG_LONG - PUGI_IMPL_FN long long xml_attribute::as_llong(long long def) const - { - if (!_attr) return def; - const char_t* value = _attr->value; - return value ? impl::get_value_llong(value) : def; - } - - PUGI_IMPL_FN unsigned long long xml_attribute::as_ullong(unsigned long long def) const - { - if (!_attr) return def; - const char_t* value = _attr->value; - return value ? impl::get_value_ullong(value) : def; - } -#endif - - PUGI_IMPL_FN bool xml_attribute::empty() const - { - return !_attr; - } - - PUGI_IMPL_FN const char_t* xml_attribute::name() const - { - if (!_attr) return PUGIXML_TEXT(""); - const char_t* name = _attr->name; - return name ? name : PUGIXML_TEXT(""); - } - - PUGI_IMPL_FN const char_t* xml_attribute::value() const - { - if (!_attr) return PUGIXML_TEXT(""); - const char_t* value = _attr->value; - return value ? value : PUGIXML_TEXT(""); - } - - PUGI_IMPL_FN size_t xml_attribute::hash_value() const - { - return static_cast(reinterpret_cast(_attr) / sizeof(xml_attribute_struct)); - } - - PUGI_IMPL_FN xml_attribute_struct* xml_attribute::internal_object() const - { - return _attr; - } - - PUGI_IMPL_FN xml_attribute& xml_attribute::operator=(const char_t* rhs) - { - set_value(rhs); - return *this; - } - - PUGI_IMPL_FN xml_attribute& xml_attribute::operator=(int rhs) - { - set_value(rhs); - return *this; - } - - PUGI_IMPL_FN xml_attribute& xml_attribute::operator=(unsigned int rhs) - { - set_value(rhs); - return *this; - } - - PUGI_IMPL_FN xml_attribute& xml_attribute::operator=(long rhs) - { - set_value(rhs); - return *this; - } - - PUGI_IMPL_FN xml_attribute& xml_attribute::operator=(unsigned long rhs) - { - set_value(rhs); - return *this; - } - - PUGI_IMPL_FN xml_attribute& xml_attribute::operator=(double rhs) - { - set_value(rhs); - return *this; - } - - PUGI_IMPL_FN xml_attribute& xml_attribute::operator=(float rhs) - { - set_value(rhs); - return *this; - } - - PUGI_IMPL_FN xml_attribute& xml_attribute::operator=(bool rhs) - { - set_value(rhs); - return *this; - } - -#ifdef PUGIXML_HAS_LONG_LONG - PUGI_IMPL_FN xml_attribute& xml_attribute::operator=(long long rhs) - { - set_value(rhs); - return *this; - } - - PUGI_IMPL_FN xml_attribute& xml_attribute::operator=(unsigned long long rhs) - { - set_value(rhs); - return *this; - } -#endif - - PUGI_IMPL_FN bool xml_attribute::set_name(const char_t* rhs) - { - if (!_attr) return false; - - return impl::strcpy_insitu(_attr->name, _attr->header, impl::xml_memory_page_name_allocated_mask, rhs, impl::strlength(rhs)); - } - - PUGI_IMPL_FN bool xml_attribute::set_name(const char_t* rhs, size_t size) - { - if (!_attr) return false; - - return impl::strcpy_insitu(_attr->name, _attr->header, impl::xml_memory_page_name_allocated_mask, rhs, size); - } - - PUGI_IMPL_FN bool xml_attribute::set_value(const char_t* rhs) - { - if (!_attr) return false; - - return impl::strcpy_insitu(_attr->value, _attr->header, impl::xml_memory_page_value_allocated_mask, rhs, impl::strlength(rhs)); - } - - PUGI_IMPL_FN bool xml_attribute::set_value(const char_t* rhs, size_t size) - { - if (!_attr) return false; - - return impl::strcpy_insitu(_attr->value, _attr->header, impl::xml_memory_page_value_allocated_mask, rhs, size); - } - - PUGI_IMPL_FN bool xml_attribute::set_value(int rhs) - { - if (!_attr) return false; - - return impl::set_value_integer(_attr->value, _attr->header, impl::xml_memory_page_value_allocated_mask, rhs, rhs < 0); - } - - PUGI_IMPL_FN bool xml_attribute::set_value(unsigned int rhs) - { - if (!_attr) return false; - - return impl::set_value_integer(_attr->value, _attr->header, impl::xml_memory_page_value_allocated_mask, rhs, false); - } - - PUGI_IMPL_FN bool xml_attribute::set_value(long rhs) - { - if (!_attr) return false; - - return impl::set_value_integer(_attr->value, _attr->header, impl::xml_memory_page_value_allocated_mask, rhs, rhs < 0); - } - - PUGI_IMPL_FN bool xml_attribute::set_value(unsigned long rhs) - { - if (!_attr) return false; - - return impl::set_value_integer(_attr->value, _attr->header, impl::xml_memory_page_value_allocated_mask, rhs, false); - } - - PUGI_IMPL_FN bool xml_attribute::set_value(double rhs) - { - if (!_attr) return false; - - return impl::set_value_convert(_attr->value, _attr->header, impl::xml_memory_page_value_allocated_mask, rhs, default_double_precision); - } - - PUGI_IMPL_FN bool xml_attribute::set_value(double rhs, int precision) - { - if (!_attr) return false; - - return impl::set_value_convert(_attr->value, _attr->header, impl::xml_memory_page_value_allocated_mask, rhs, precision); - } - - PUGI_IMPL_FN bool xml_attribute::set_value(float rhs) - { - if (!_attr) return false; - - return impl::set_value_convert(_attr->value, _attr->header, impl::xml_memory_page_value_allocated_mask, rhs, default_float_precision); - } - - PUGI_IMPL_FN bool xml_attribute::set_value(float rhs, int precision) - { - if (!_attr) return false; - - return impl::set_value_convert(_attr->value, _attr->header, impl::xml_memory_page_value_allocated_mask, rhs, precision); - } - - PUGI_IMPL_FN bool xml_attribute::set_value(bool rhs) - { - if (!_attr) return false; - - return impl::set_value_bool(_attr->value, _attr->header, impl::xml_memory_page_value_allocated_mask, rhs); - } - -#ifdef PUGIXML_HAS_LONG_LONG - PUGI_IMPL_FN bool xml_attribute::set_value(long long rhs) - { - if (!_attr) return false; - - return impl::set_value_integer(_attr->value, _attr->header, impl::xml_memory_page_value_allocated_mask, rhs, rhs < 0); - } - - PUGI_IMPL_FN bool xml_attribute::set_value(unsigned long long rhs) - { - if (!_attr) return false; - - return impl::set_value_integer(_attr->value, _attr->header, impl::xml_memory_page_value_allocated_mask, rhs, false); - } -#endif - -#ifdef __BORLANDC__ - PUGI_IMPL_FN bool operator&&(const xml_attribute& lhs, bool rhs) - { - return (bool)lhs && rhs; - } - - PUGI_IMPL_FN bool operator||(const xml_attribute& lhs, bool rhs) - { - return (bool)lhs || rhs; - } -#endif - - PUGI_IMPL_FN xml_node::xml_node(): _root(0) - { - } - - PUGI_IMPL_FN xml_node::xml_node(xml_node_struct* p): _root(p) - { - } - - PUGI_IMPL_FN static void unspecified_bool_xml_node(xml_node***) - { - } - - PUGI_IMPL_FN xml_node::operator xml_node::unspecified_bool_type() const - { - return _root ? unspecified_bool_xml_node : 0; - } - - PUGI_IMPL_FN bool xml_node::operator!() const - { - return !_root; - } - - PUGI_IMPL_FN xml_node::iterator xml_node::begin() const - { - return iterator(_root ? _root->first_child + 0 : 0, _root); - } - - PUGI_IMPL_FN xml_node::iterator xml_node::end() const - { - return iterator(0, _root); - } - - PUGI_IMPL_FN xml_node::attribute_iterator xml_node::attributes_begin() const - { - return attribute_iterator(_root ? _root->first_attribute + 0 : 0, _root); - } - - PUGI_IMPL_FN xml_node::attribute_iterator xml_node::attributes_end() const - { - return attribute_iterator(0, _root); - } - - PUGI_IMPL_FN xml_object_range xml_node::children() const - { - return xml_object_range(begin(), end()); - } - - PUGI_IMPL_FN xml_object_range xml_node::children(const char_t* name_) const - { - return xml_object_range(xml_named_node_iterator(child(name_)._root, _root, name_), xml_named_node_iterator(0, _root, name_)); - } - - PUGI_IMPL_FN xml_object_range xml_node::attributes() const - { - return xml_object_range(attributes_begin(), attributes_end()); - } - - PUGI_IMPL_FN bool xml_node::operator==(const xml_node& r) const - { - return (_root == r._root); - } - - PUGI_IMPL_FN bool xml_node::operator!=(const xml_node& r) const - { - return (_root != r._root); - } - - PUGI_IMPL_FN bool xml_node::operator<(const xml_node& r) const - { - return (_root < r._root); - } - - PUGI_IMPL_FN bool xml_node::operator>(const xml_node& r) const - { - return (_root > r._root); - } - - PUGI_IMPL_FN bool xml_node::operator<=(const xml_node& r) const - { - return (_root <= r._root); - } - - PUGI_IMPL_FN bool xml_node::operator>=(const xml_node& r) const - { - return (_root >= r._root); - } - - PUGI_IMPL_FN bool xml_node::empty() const - { - return !_root; - } - - PUGI_IMPL_FN const char_t* xml_node::name() const - { - if (!_root) return PUGIXML_TEXT(""); - const char_t* name = _root->name; - return name ? name : PUGIXML_TEXT(""); - } - - PUGI_IMPL_FN xml_node_type xml_node::type() const - { - return _root ? PUGI_IMPL_NODETYPE(_root) : node_null; - } - - PUGI_IMPL_FN const char_t* xml_node::value() const - { - if (!_root) return PUGIXML_TEXT(""); - const char_t* value = _root->value; - return value ? value : PUGIXML_TEXT(""); - } - - PUGI_IMPL_FN xml_node xml_node::child(const char_t* name_) const - { - if (!_root) return xml_node(); - - for (xml_node_struct* i = _root->first_child; i; i = i->next_sibling) - { - const char_t* iname = i->name; - if (iname && impl::strequal(name_, iname)) - return xml_node(i); - } - - return xml_node(); - } - - PUGI_IMPL_FN xml_attribute xml_node::attribute(const char_t* name_) const - { - if (!_root) return xml_attribute(); - - for (xml_attribute_struct* i = _root->first_attribute; i; i = i->next_attribute) - { - const char_t* iname = i->name; - if (iname && impl::strequal(name_, iname)) - return xml_attribute(i); - } - - return xml_attribute(); - } - - PUGI_IMPL_FN xml_node xml_node::next_sibling(const char_t* name_) const - { - if (!_root) return xml_node(); - - for (xml_node_struct* i = _root->next_sibling; i; i = i->next_sibling) - { - const char_t* iname = i->name; - if (iname && impl::strequal(name_, iname)) - return xml_node(i); - } - - return xml_node(); - } - - PUGI_IMPL_FN xml_node xml_node::next_sibling() const - { - return _root ? xml_node(_root->next_sibling) : xml_node(); - } - - PUGI_IMPL_FN xml_node xml_node::previous_sibling(const char_t* name_) const - { - if (!_root) return xml_node(); - - for (xml_node_struct* i = _root->prev_sibling_c; i->next_sibling; i = i->prev_sibling_c) - { - const char_t* iname = i->name; - if (iname && impl::strequal(name_, iname)) - return xml_node(i); - } - - return xml_node(); - } - - PUGI_IMPL_FN xml_attribute xml_node::attribute(const char_t* name_, xml_attribute& hint_) const - { - xml_attribute_struct* hint = hint_._attr; - - // if hint is not an attribute of node, behavior is not defined - assert(!hint || (_root && impl::is_attribute_of(hint, _root))); - - if (!_root) return xml_attribute(); - - // optimistically search from hint up until the end - for (xml_attribute_struct* i = hint; i; i = i->next_attribute) - { - const char_t* iname = i->name; - if (iname && impl::strequal(name_, iname)) - { - // update hint to maximize efficiency of searching for consecutive attributes - hint_._attr = i->next_attribute; - - return xml_attribute(i); - } - } - - // wrap around and search from the first attribute until the hint - // 'j' null pointer check is technically redundant, but it prevents a crash in case the assertion above fails - for (xml_attribute_struct* j = _root->first_attribute; j && j != hint; j = j->next_attribute) - { - const char_t* jname = j->name; - if (jname && impl::strequal(name_, jname)) - { - // update hint to maximize efficiency of searching for consecutive attributes - hint_._attr = j->next_attribute; - - return xml_attribute(j); - } - } - - return xml_attribute(); - } - - PUGI_IMPL_FN xml_node xml_node::previous_sibling() const - { - if (!_root) return xml_node(); - xml_node_struct* prev = _root->prev_sibling_c; - return prev->next_sibling ? xml_node(prev) : xml_node(); - } - - PUGI_IMPL_FN xml_node xml_node::parent() const - { - return _root ? xml_node(_root->parent) : xml_node(); - } - - PUGI_IMPL_FN xml_node xml_node::root() const - { - return _root ? xml_node(&impl::get_document(_root)) : xml_node(); - } - - PUGI_IMPL_FN xml_text xml_node::text() const - { - return xml_text(_root); - } - - PUGI_IMPL_FN const char_t* xml_node::child_value() const - { - if (!_root) return PUGIXML_TEXT(""); - - // element nodes can have value if parse_embed_pcdata was used - if (PUGI_IMPL_NODETYPE(_root) == node_element && _root->value) - return _root->value; - - for (xml_node_struct* i = _root->first_child; i; i = i->next_sibling) - { - const char_t* ivalue = i->value; - if (impl::is_text_node(i) && ivalue) - return ivalue; - } - - return PUGIXML_TEXT(""); - } - - PUGI_IMPL_FN const char_t* xml_node::child_value(const char_t* name_) const - { - return child(name_).child_value(); - } - - PUGI_IMPL_FN xml_attribute xml_node::first_attribute() const - { - if (!_root) return xml_attribute(); - return xml_attribute(_root->first_attribute); - } - - PUGI_IMPL_FN xml_attribute xml_node::last_attribute() const - { - if (!_root) return xml_attribute(); - xml_attribute_struct* first = _root->first_attribute; - return first ? xml_attribute(first->prev_attribute_c) : xml_attribute(); - } - - PUGI_IMPL_FN xml_node xml_node::first_child() const - { - if (!_root) return xml_node(); - return xml_node(_root->first_child); - } - - PUGI_IMPL_FN xml_node xml_node::last_child() const - { - if (!_root) return xml_node(); - xml_node_struct* first = _root->first_child; - return first ? xml_node(first->prev_sibling_c) : xml_node(); - } - - PUGI_IMPL_FN bool xml_node::set_name(const char_t* rhs) - { - xml_node_type type_ = _root ? PUGI_IMPL_NODETYPE(_root) : node_null; - - if (type_ != node_element && type_ != node_pi && type_ != node_declaration) - return false; - - return impl::strcpy_insitu(_root->name, _root->header, impl::xml_memory_page_name_allocated_mask, rhs, impl::strlength(rhs)); - } - - PUGI_IMPL_FN bool xml_node::set_name(const char_t* rhs, size_t size) - { - xml_node_type type_ = _root ? PUGI_IMPL_NODETYPE(_root) : node_null; - - if (type_ != node_element && type_ != node_pi && type_ != node_declaration) - return false; - - return impl::strcpy_insitu(_root->name, _root->header, impl::xml_memory_page_name_allocated_mask, rhs, size); - } - - PUGI_IMPL_FN bool xml_node::set_value(const char_t* rhs) - { - xml_node_type type_ = _root ? PUGI_IMPL_NODETYPE(_root) : node_null; - - if (type_ != node_pcdata && type_ != node_cdata && type_ != node_comment && type_ != node_pi && type_ != node_doctype) - return false; - - return impl::strcpy_insitu(_root->value, _root->header, impl::xml_memory_page_value_allocated_mask, rhs, impl::strlength(rhs)); - } - - PUGI_IMPL_FN bool xml_node::set_value(const char_t* rhs, size_t size) - { - xml_node_type type_ = _root ? PUGI_IMPL_NODETYPE(_root) : node_null; - - if (type_ != node_pcdata && type_ != node_cdata && type_ != node_comment && type_ != node_pi && type_ != node_doctype) - return false; - - return impl::strcpy_insitu(_root->value, _root->header, impl::xml_memory_page_value_allocated_mask, rhs, size); - } - - PUGI_IMPL_FN xml_attribute xml_node::append_attribute(const char_t* name_) - { - if (!impl::allow_insert_attribute(type())) return xml_attribute(); - - impl::xml_allocator& alloc = impl::get_allocator(_root); - if (!alloc.reserve()) return xml_attribute(); - - xml_attribute a(impl::allocate_attribute(alloc)); - if (!a) return xml_attribute(); - - impl::append_attribute(a._attr, _root); - - a.set_name(name_); - - return a; - } - - PUGI_IMPL_FN xml_attribute xml_node::prepend_attribute(const char_t* name_) - { - if (!impl::allow_insert_attribute(type())) return xml_attribute(); - - impl::xml_allocator& alloc = impl::get_allocator(_root); - if (!alloc.reserve()) return xml_attribute(); - - xml_attribute a(impl::allocate_attribute(alloc)); - if (!a) return xml_attribute(); - - impl::prepend_attribute(a._attr, _root); - - a.set_name(name_); - - return a; - } - - PUGI_IMPL_FN xml_attribute xml_node::insert_attribute_after(const char_t* name_, const xml_attribute& attr) - { - if (!impl::allow_insert_attribute(type())) return xml_attribute(); - if (!attr || !impl::is_attribute_of(attr._attr, _root)) return xml_attribute(); - - impl::xml_allocator& alloc = impl::get_allocator(_root); - if (!alloc.reserve()) return xml_attribute(); - - xml_attribute a(impl::allocate_attribute(alloc)); - if (!a) return xml_attribute(); - - impl::insert_attribute_after(a._attr, attr._attr, _root); - - a.set_name(name_); - - return a; - } - - PUGI_IMPL_FN xml_attribute xml_node::insert_attribute_before(const char_t* name_, const xml_attribute& attr) - { - if (!impl::allow_insert_attribute(type())) return xml_attribute(); - if (!attr || !impl::is_attribute_of(attr._attr, _root)) return xml_attribute(); - - impl::xml_allocator& alloc = impl::get_allocator(_root); - if (!alloc.reserve()) return xml_attribute(); - - xml_attribute a(impl::allocate_attribute(alloc)); - if (!a) return xml_attribute(); - - impl::insert_attribute_before(a._attr, attr._attr, _root); - - a.set_name(name_); - - return a; - } - - PUGI_IMPL_FN xml_attribute xml_node::append_copy(const xml_attribute& proto) - { - if (!proto) return xml_attribute(); - if (!impl::allow_insert_attribute(type())) return xml_attribute(); - - impl::xml_allocator& alloc = impl::get_allocator(_root); - if (!alloc.reserve()) return xml_attribute(); - - xml_attribute a(impl::allocate_attribute(alloc)); - if (!a) return xml_attribute(); - - impl::append_attribute(a._attr, _root); - impl::node_copy_attribute(a._attr, proto._attr); - - return a; - } - - PUGI_IMPL_FN xml_attribute xml_node::prepend_copy(const xml_attribute& proto) - { - if (!proto) return xml_attribute(); - if (!impl::allow_insert_attribute(type())) return xml_attribute(); - - impl::xml_allocator& alloc = impl::get_allocator(_root); - if (!alloc.reserve()) return xml_attribute(); - - xml_attribute a(impl::allocate_attribute(alloc)); - if (!a) return xml_attribute(); - - impl::prepend_attribute(a._attr, _root); - impl::node_copy_attribute(a._attr, proto._attr); - - return a; - } - - PUGI_IMPL_FN xml_attribute xml_node::insert_copy_after(const xml_attribute& proto, const xml_attribute& attr) - { - if (!proto) return xml_attribute(); - if (!impl::allow_insert_attribute(type())) return xml_attribute(); - if (!attr || !impl::is_attribute_of(attr._attr, _root)) return xml_attribute(); - - impl::xml_allocator& alloc = impl::get_allocator(_root); - if (!alloc.reserve()) return xml_attribute(); - - xml_attribute a(impl::allocate_attribute(alloc)); - if (!a) return xml_attribute(); - - impl::insert_attribute_after(a._attr, attr._attr, _root); - impl::node_copy_attribute(a._attr, proto._attr); - - return a; - } - - PUGI_IMPL_FN xml_attribute xml_node::insert_copy_before(const xml_attribute& proto, const xml_attribute& attr) - { - if (!proto) return xml_attribute(); - if (!impl::allow_insert_attribute(type())) return xml_attribute(); - if (!attr || !impl::is_attribute_of(attr._attr, _root)) return xml_attribute(); - - impl::xml_allocator& alloc = impl::get_allocator(_root); - if (!alloc.reserve()) return xml_attribute(); - - xml_attribute a(impl::allocate_attribute(alloc)); - if (!a) return xml_attribute(); - - impl::insert_attribute_before(a._attr, attr._attr, _root); - impl::node_copy_attribute(a._attr, proto._attr); - - return a; - } - - PUGI_IMPL_FN xml_node xml_node::append_child(xml_node_type type_) - { - if (!impl::allow_insert_child(type(), type_)) return xml_node(); - - impl::xml_allocator& alloc = impl::get_allocator(_root); - if (!alloc.reserve()) return xml_node(); - - xml_node n(impl::allocate_node(alloc, type_)); - if (!n) return xml_node(); - - impl::append_node(n._root, _root); - - if (type_ == node_declaration) n.set_name(PUGIXML_TEXT("xml")); - - return n; - } - - PUGI_IMPL_FN xml_node xml_node::prepend_child(xml_node_type type_) - { - if (!impl::allow_insert_child(type(), type_)) return xml_node(); - - impl::xml_allocator& alloc = impl::get_allocator(_root); - if (!alloc.reserve()) return xml_node(); - - xml_node n(impl::allocate_node(alloc, type_)); - if (!n) return xml_node(); - - impl::prepend_node(n._root, _root); - - if (type_ == node_declaration) n.set_name(PUGIXML_TEXT("xml")); - - return n; - } - - PUGI_IMPL_FN xml_node xml_node::insert_child_before(xml_node_type type_, const xml_node& node) - { - if (!impl::allow_insert_child(type(), type_)) return xml_node(); - if (!node._root || node._root->parent != _root) return xml_node(); - - impl::xml_allocator& alloc = impl::get_allocator(_root); - if (!alloc.reserve()) return xml_node(); - - xml_node n(impl::allocate_node(alloc, type_)); - if (!n) return xml_node(); - - impl::insert_node_before(n._root, node._root); - - if (type_ == node_declaration) n.set_name(PUGIXML_TEXT("xml")); - - return n; - } - - PUGI_IMPL_FN xml_node xml_node::insert_child_after(xml_node_type type_, const xml_node& node) - { - if (!impl::allow_insert_child(type(), type_)) return xml_node(); - if (!node._root || node._root->parent != _root) return xml_node(); - - impl::xml_allocator& alloc = impl::get_allocator(_root); - if (!alloc.reserve()) return xml_node(); - - xml_node n(impl::allocate_node(alloc, type_)); - if (!n) return xml_node(); - - impl::insert_node_after(n._root, node._root); - - if (type_ == node_declaration) n.set_name(PUGIXML_TEXT("xml")); - - return n; - } - - PUGI_IMPL_FN xml_node xml_node::append_child(const char_t* name_) - { - xml_node result = append_child(node_element); - - result.set_name(name_); - - return result; - } - - PUGI_IMPL_FN xml_node xml_node::prepend_child(const char_t* name_) - { - xml_node result = prepend_child(node_element); - - result.set_name(name_); - - return result; - } - - PUGI_IMPL_FN xml_node xml_node::insert_child_after(const char_t* name_, const xml_node& node) - { - xml_node result = insert_child_after(node_element, node); - - result.set_name(name_); - - return result; - } - - PUGI_IMPL_FN xml_node xml_node::insert_child_before(const char_t* name_, const xml_node& node) - { - xml_node result = insert_child_before(node_element, node); - - result.set_name(name_); - - return result; - } - - PUGI_IMPL_FN xml_node xml_node::append_copy(const xml_node& proto) - { - xml_node_type type_ = proto.type(); - if (!impl::allow_insert_child(type(), type_)) return xml_node(); - - impl::xml_allocator& alloc = impl::get_allocator(_root); - if (!alloc.reserve()) return xml_node(); - - xml_node n(impl::allocate_node(alloc, type_)); - if (!n) return xml_node(); - - impl::append_node(n._root, _root); - impl::node_copy_tree(n._root, proto._root); - - return n; - } - - PUGI_IMPL_FN xml_node xml_node::prepend_copy(const xml_node& proto) - { - xml_node_type type_ = proto.type(); - if (!impl::allow_insert_child(type(), type_)) return xml_node(); - - impl::xml_allocator& alloc = impl::get_allocator(_root); - if (!alloc.reserve()) return xml_node(); - - xml_node n(impl::allocate_node(alloc, type_)); - if (!n) return xml_node(); - - impl::prepend_node(n._root, _root); - impl::node_copy_tree(n._root, proto._root); - - return n; - } - - PUGI_IMPL_FN xml_node xml_node::insert_copy_after(const xml_node& proto, const xml_node& node) - { - xml_node_type type_ = proto.type(); - if (!impl::allow_insert_child(type(), type_)) return xml_node(); - if (!node._root || node._root->parent != _root) return xml_node(); - - impl::xml_allocator& alloc = impl::get_allocator(_root); - if (!alloc.reserve()) return xml_node(); - - xml_node n(impl::allocate_node(alloc, type_)); - if (!n) return xml_node(); - - impl::insert_node_after(n._root, node._root); - impl::node_copy_tree(n._root, proto._root); - - return n; - } - - PUGI_IMPL_FN xml_node xml_node::insert_copy_before(const xml_node& proto, const xml_node& node) - { - xml_node_type type_ = proto.type(); - if (!impl::allow_insert_child(type(), type_)) return xml_node(); - if (!node._root || node._root->parent != _root) return xml_node(); - - impl::xml_allocator& alloc = impl::get_allocator(_root); - if (!alloc.reserve()) return xml_node(); - - xml_node n(impl::allocate_node(alloc, type_)); - if (!n) return xml_node(); - - impl::insert_node_before(n._root, node._root); - impl::node_copy_tree(n._root, proto._root); - - return n; - } - - PUGI_IMPL_FN xml_node xml_node::append_move(const xml_node& moved) - { - if (!impl::allow_move(*this, moved)) return xml_node(); - - impl::xml_allocator& alloc = impl::get_allocator(_root); - if (!alloc.reserve()) return xml_node(); - - // disable document_buffer_order optimization since moving nodes around changes document order without changing buffer pointers - impl::get_document(_root).header |= impl::xml_memory_page_contents_shared_mask; - - impl::remove_node(moved._root); - impl::append_node(moved._root, _root); - - return moved; - } - - PUGI_IMPL_FN xml_node xml_node::prepend_move(const xml_node& moved) - { - if (!impl::allow_move(*this, moved)) return xml_node(); - - impl::xml_allocator& alloc = impl::get_allocator(_root); - if (!alloc.reserve()) return xml_node(); - - // disable document_buffer_order optimization since moving nodes around changes document order without changing buffer pointers - impl::get_document(_root).header |= impl::xml_memory_page_contents_shared_mask; - - impl::remove_node(moved._root); - impl::prepend_node(moved._root, _root); - - return moved; - } - - PUGI_IMPL_FN xml_node xml_node::insert_move_after(const xml_node& moved, const xml_node& node) - { - if (!impl::allow_move(*this, moved)) return xml_node(); - if (!node._root || node._root->parent != _root) return xml_node(); - if (moved._root == node._root) return xml_node(); - - impl::xml_allocator& alloc = impl::get_allocator(_root); - if (!alloc.reserve()) return xml_node(); - - // disable document_buffer_order optimization since moving nodes around changes document order without changing buffer pointers - impl::get_document(_root).header |= impl::xml_memory_page_contents_shared_mask; - - impl::remove_node(moved._root); - impl::insert_node_after(moved._root, node._root); - - return moved; - } - - PUGI_IMPL_FN xml_node xml_node::insert_move_before(const xml_node& moved, const xml_node& node) - { - if (!impl::allow_move(*this, moved)) return xml_node(); - if (!node._root || node._root->parent != _root) return xml_node(); - if (moved._root == node._root) return xml_node(); - - impl::xml_allocator& alloc = impl::get_allocator(_root); - if (!alloc.reserve()) return xml_node(); - - // disable document_buffer_order optimization since moving nodes around changes document order without changing buffer pointers - impl::get_document(_root).header |= impl::xml_memory_page_contents_shared_mask; - - impl::remove_node(moved._root); - impl::insert_node_before(moved._root, node._root); - - return moved; - } - - PUGI_IMPL_FN bool xml_node::remove_attribute(const char_t* name_) - { - return remove_attribute(attribute(name_)); - } - - PUGI_IMPL_FN bool xml_node::remove_attribute(const xml_attribute& a) - { - if (!_root || !a._attr) return false; - if (!impl::is_attribute_of(a._attr, _root)) return false; - - impl::xml_allocator& alloc = impl::get_allocator(_root); - if (!alloc.reserve()) return false; - - impl::remove_attribute(a._attr, _root); - impl::destroy_attribute(a._attr, alloc); - - return true; - } - - PUGI_IMPL_FN bool xml_node::remove_attributes() - { - if (!_root) return false; - - impl::xml_allocator& alloc = impl::get_allocator(_root); - if (!alloc.reserve()) return false; - - for (xml_attribute_struct* attr = _root->first_attribute; attr; ) - { - xml_attribute_struct* next = attr->next_attribute; - - impl::destroy_attribute(attr, alloc); - - attr = next; - } - - _root->first_attribute = 0; - - return true; - } - - PUGI_IMPL_FN bool xml_node::remove_child(const char_t* name_) - { - return remove_child(child(name_)); - } - - PUGI_IMPL_FN bool xml_node::remove_child(const xml_node& n) - { - if (!_root || !n._root || n._root->parent != _root) return false; - - impl::xml_allocator& alloc = impl::get_allocator(_root); - if (!alloc.reserve()) return false; - - impl::remove_node(n._root); - impl::destroy_node(n._root, alloc); - - return true; - } - - PUGI_IMPL_FN bool xml_node::remove_children() - { - if (!_root) return false; - - impl::xml_allocator& alloc = impl::get_allocator(_root); - if (!alloc.reserve()) return false; - - for (xml_node_struct* cur = _root->first_child; cur; ) - { - xml_node_struct* next = cur->next_sibling; - - impl::destroy_node(cur, alloc); - - cur = next; - } - - _root->first_child = 0; - - return true; - } - - PUGI_IMPL_FN xml_parse_result xml_node::append_buffer(const void* contents, size_t size, unsigned int options, xml_encoding encoding) - { - // append_buffer is only valid for elements/documents - if (!impl::allow_insert_child(type(), node_element)) return impl::make_parse_result(status_append_invalid_root); - - // append buffer can not merge PCDATA into existing PCDATA nodes - if ((options & parse_merge_pcdata) != 0 && last_child().type() == node_pcdata) return impl::make_parse_result(status_append_invalid_root); - - // get document node - impl::xml_document_struct* doc = &impl::get_document(_root); - - // disable document_buffer_order optimization since in a document with multiple buffers comparing buffer pointers does not make sense - doc->header |= impl::xml_memory_page_contents_shared_mask; - - // get extra buffer element (we'll store the document fragment buffer there so that we can deallocate it later) - impl::xml_memory_page* page = 0; - impl::xml_extra_buffer* extra = static_cast(doc->allocate_memory(sizeof(impl::xml_extra_buffer) + sizeof(void*), page)); - (void)page; - - if (!extra) return impl::make_parse_result(status_out_of_memory); - - #ifdef PUGIXML_COMPACT - // align the memory block to a pointer boundary; this is required for compact mode where memory allocations are only 4b aligned - // note that this requires up to sizeof(void*)-1 additional memory, which the allocation above takes into account - extra = reinterpret_cast((reinterpret_cast(extra) + (sizeof(void*) - 1)) & ~(sizeof(void*) - 1)); - #endif - - // add extra buffer to the list - extra->buffer = 0; - extra->next = doc->extra_buffers; - doc->extra_buffers = extra; - - // name of the root has to be NULL before parsing - otherwise closing node mismatches will not be detected at the top level - impl::name_null_sentry sentry(_root); - - return impl::load_buffer_impl(doc, _root, const_cast(contents), size, options, encoding, false, false, &extra->buffer); - } - - PUGI_IMPL_FN xml_node xml_node::find_child_by_attribute(const char_t* name_, const char_t* attr_name, const char_t* attr_value) const - { - if (!_root) return xml_node(); - - for (xml_node_struct* i = _root->first_child; i; i = i->next_sibling) - { - const char_t* iname = i->name; - if (iname && impl::strequal(name_, iname)) - { - for (xml_attribute_struct* a = i->first_attribute; a; a = a->next_attribute) - { - const char_t* aname = a->name; - if (aname && impl::strequal(attr_name, aname)) - { - const char_t* avalue = a->value; - if (impl::strequal(attr_value, avalue ? avalue : PUGIXML_TEXT(""))) - return xml_node(i); - } - } - } - } - - return xml_node(); - } - - PUGI_IMPL_FN xml_node xml_node::find_child_by_attribute(const char_t* attr_name, const char_t* attr_value) const - { - if (!_root) return xml_node(); - - for (xml_node_struct* i = _root->first_child; i; i = i->next_sibling) - for (xml_attribute_struct* a = i->first_attribute; a; a = a->next_attribute) - { - const char_t* aname = a->name; - if (aname && impl::strequal(attr_name, aname)) - { - const char_t* avalue = a->value; - if (impl::strequal(attr_value, avalue ? avalue : PUGIXML_TEXT(""))) - return xml_node(i); - } - } - - return xml_node(); - } - -#ifndef PUGIXML_NO_STL - PUGI_IMPL_FN string_t xml_node::path(char_t delimiter) const - { - if (!_root) return string_t(); - - size_t offset = 0; - - for (xml_node_struct* i = _root; i; i = i->parent) - { - const char_t* iname = i->name; - offset += (i != _root); - offset += iname ? impl::strlength(iname) : 0; - } - - string_t result; - result.resize(offset); - - for (xml_node_struct* j = _root; j; j = j->parent) - { - if (j != _root) - result[--offset] = delimiter; - - const char_t* jname = j->name; - if (jname) - { - size_t length = impl::strlength(jname); - - offset -= length; - memcpy(&result[offset], jname, length * sizeof(char_t)); - } - } - - assert(offset == 0); - - return result; - } -#endif - - PUGI_IMPL_FN xml_node xml_node::first_element_by_path(const char_t* path_, char_t delimiter) const - { - xml_node context = path_[0] == delimiter ? root() : *this; - - if (!context._root) return xml_node(); - - const char_t* path_segment = path_; - - while (*path_segment == delimiter) ++path_segment; - - const char_t* path_segment_end = path_segment; - - while (*path_segment_end && *path_segment_end != delimiter) ++path_segment_end; - - if (path_segment == path_segment_end) return context; - - const char_t* next_segment = path_segment_end; - - while (*next_segment == delimiter) ++next_segment; - - if (*path_segment == '.' && path_segment + 1 == path_segment_end) - return context.first_element_by_path(next_segment, delimiter); - else if (*path_segment == '.' && *(path_segment+1) == '.' && path_segment + 2 == path_segment_end) - return context.parent().first_element_by_path(next_segment, delimiter); - else - { - for (xml_node_struct* j = context._root->first_child; j; j = j->next_sibling) - { - const char_t* jname = j->name; - if (jname && impl::strequalrange(jname, path_segment, static_cast(path_segment_end - path_segment))) - { - xml_node subsearch = xml_node(j).first_element_by_path(next_segment, delimiter); - - if (subsearch) return subsearch; - } - } - - return xml_node(); - } - } - - PUGI_IMPL_FN bool xml_node::traverse(xml_tree_walker& walker) - { - walker._depth = -1; - - xml_node arg_begin(_root); - if (!walker.begin(arg_begin)) return false; - - xml_node_struct* cur = _root ? _root->first_child + 0 : 0; - - if (cur) - { - ++walker._depth; - - do - { - xml_node arg_for_each(cur); - if (!walker.for_each(arg_for_each)) - return false; - - if (cur->first_child) - { - ++walker._depth; - cur = cur->first_child; - } - else if (cur->next_sibling) - cur = cur->next_sibling; - else - { - while (!cur->next_sibling && cur != _root && cur->parent) - { - --walker._depth; - cur = cur->parent; - } - - if (cur != _root) - cur = cur->next_sibling; - } - } - while (cur && cur != _root); - } - - assert(walker._depth == -1); - - xml_node arg_end(_root); - return walker.end(arg_end); - } - - PUGI_IMPL_FN size_t xml_node::hash_value() const - { - return static_cast(reinterpret_cast(_root) / sizeof(xml_node_struct)); - } - - PUGI_IMPL_FN xml_node_struct* xml_node::internal_object() const - { - return _root; - } - - PUGI_IMPL_FN void xml_node::print(xml_writer& writer, const char_t* indent, unsigned int flags, xml_encoding encoding, unsigned int depth) const - { - if (!_root) return; - - impl::xml_buffered_writer buffered_writer(writer, encoding); - - impl::node_output(buffered_writer, _root, indent, flags, depth); - - buffered_writer.flush(); - } - -#ifndef PUGIXML_NO_STL - PUGI_IMPL_FN void xml_node::print(std::basic_ostream >& stream, const char_t* indent, unsigned int flags, xml_encoding encoding, unsigned int depth) const - { - xml_writer_stream writer(stream); - - print(writer, indent, flags, encoding, depth); - } - - PUGI_IMPL_FN void xml_node::print(std::basic_ostream >& stream, const char_t* indent, unsigned int flags, unsigned int depth) const - { - xml_writer_stream writer(stream); - - print(writer, indent, flags, encoding_wchar, depth); - } -#endif - - PUGI_IMPL_FN ptrdiff_t xml_node::offset_debug() const - { - if (!_root) return -1; - - impl::xml_document_struct& doc = impl::get_document(_root); - - // we can determine the offset reliably only if there is exactly once parse buffer - if (!doc.buffer || doc.extra_buffers) return -1; - - switch (type()) - { - case node_document: - return 0; - - case node_element: - case node_declaration: - case node_pi: - return _root->name && (_root->header & impl::xml_memory_page_name_allocated_or_shared_mask) == 0 ? _root->name - doc.buffer : -1; - - case node_pcdata: - case node_cdata: - case node_comment: - case node_doctype: - return _root->value && (_root->header & impl::xml_memory_page_value_allocated_or_shared_mask) == 0 ? _root->value - doc.buffer : -1; - - default: - assert(false && "Invalid node type"); // unreachable - return -1; - } - } - -#ifdef __BORLANDC__ - PUGI_IMPL_FN bool operator&&(const xml_node& lhs, bool rhs) - { - return (bool)lhs && rhs; - } - - PUGI_IMPL_FN bool operator||(const xml_node& lhs, bool rhs) - { - return (bool)lhs || rhs; - } -#endif - - PUGI_IMPL_FN xml_text::xml_text(xml_node_struct* root): _root(root) - { - } - - PUGI_IMPL_FN xml_node_struct* xml_text::_data() const - { - if (!_root || impl::is_text_node(_root)) return _root; - - // element nodes can have value if parse_embed_pcdata was used - if (PUGI_IMPL_NODETYPE(_root) == node_element && _root->value) - return _root; - - for (xml_node_struct* node = _root->first_child; node; node = node->next_sibling) - if (impl::is_text_node(node)) - return node; - - return 0; - } - - PUGI_IMPL_FN xml_node_struct* xml_text::_data_new() - { - xml_node_struct* d = _data(); - if (d) return d; - - return xml_node(_root).append_child(node_pcdata).internal_object(); - } - - PUGI_IMPL_FN xml_text::xml_text(): _root(0) - { - } - - PUGI_IMPL_FN static void unspecified_bool_xml_text(xml_text***) - { - } - - PUGI_IMPL_FN xml_text::operator xml_text::unspecified_bool_type() const - { - return _data() ? unspecified_bool_xml_text : 0; - } - - PUGI_IMPL_FN bool xml_text::operator!() const - { - return !_data(); - } - - PUGI_IMPL_FN bool xml_text::empty() const - { - return _data() == 0; - } - - PUGI_IMPL_FN const char_t* xml_text::get() const - { - xml_node_struct* d = _data(); - if (!d) return PUGIXML_TEXT(""); - const char_t* value = d->value; - return value ? value : PUGIXML_TEXT(""); - } - - PUGI_IMPL_FN const char_t* xml_text::as_string(const char_t* def) const - { - xml_node_struct* d = _data(); - if (!d) return def; - const char_t* value = d->value; - return value ? value : def; - } - - PUGI_IMPL_FN int xml_text::as_int(int def) const - { - xml_node_struct* d = _data(); - if (!d) return def; - const char_t* value = d->value; - return value ? impl::get_value_int(value) : def; - } - - PUGI_IMPL_FN unsigned int xml_text::as_uint(unsigned int def) const - { - xml_node_struct* d = _data(); - if (!d) return def; - const char_t* value = d->value; - return value ? impl::get_value_uint(value) : def; - } - - PUGI_IMPL_FN double xml_text::as_double(double def) const - { - xml_node_struct* d = _data(); - if (!d) return def; - const char_t* value = d->value; - return value ? impl::get_value_double(value) : def; - } - - PUGI_IMPL_FN float xml_text::as_float(float def) const - { - xml_node_struct* d = _data(); - if (!d) return def; - const char_t* value = d->value; - return value ? impl::get_value_float(value) : def; - } - - PUGI_IMPL_FN bool xml_text::as_bool(bool def) const - { - xml_node_struct* d = _data(); - if (!d) return def; - const char_t* value = d->value; - return value ? impl::get_value_bool(value) : def; - } - -#ifdef PUGIXML_HAS_LONG_LONG - PUGI_IMPL_FN long long xml_text::as_llong(long long def) const - { - xml_node_struct* d = _data(); - if (!d) return def; - const char_t* value = d->value; - return value ? impl::get_value_llong(value) : def; - } - - PUGI_IMPL_FN unsigned long long xml_text::as_ullong(unsigned long long def) const - { - xml_node_struct* d = _data(); - if (!d) return def; - const char_t* value = d->value; - return value ? impl::get_value_ullong(value) : def; - } -#endif - - PUGI_IMPL_FN bool xml_text::set(const char_t* rhs) - { - xml_node_struct* dn = _data_new(); - - return dn ? impl::strcpy_insitu(dn->value, dn->header, impl::xml_memory_page_value_allocated_mask, rhs, impl::strlength(rhs)) : false; - } - - PUGI_IMPL_FN bool xml_text::set(const char_t* rhs, size_t size) - { - xml_node_struct* dn = _data_new(); - - return dn ? impl::strcpy_insitu(dn->value, dn->header, impl::xml_memory_page_value_allocated_mask, rhs, size) : false; - } - - PUGI_IMPL_FN bool xml_text::set(int rhs) - { - xml_node_struct* dn = _data_new(); - - return dn ? impl::set_value_integer(dn->value, dn->header, impl::xml_memory_page_value_allocated_mask, rhs, rhs < 0) : false; - } - - PUGI_IMPL_FN bool xml_text::set(unsigned int rhs) - { - xml_node_struct* dn = _data_new(); - - return dn ? impl::set_value_integer(dn->value, dn->header, impl::xml_memory_page_value_allocated_mask, rhs, false) : false; - } - - PUGI_IMPL_FN bool xml_text::set(long rhs) - { - xml_node_struct* dn = _data_new(); - - return dn ? impl::set_value_integer(dn->value, dn->header, impl::xml_memory_page_value_allocated_mask, rhs, rhs < 0) : false; - } - - PUGI_IMPL_FN bool xml_text::set(unsigned long rhs) - { - xml_node_struct* dn = _data_new(); - - return dn ? impl::set_value_integer(dn->value, dn->header, impl::xml_memory_page_value_allocated_mask, rhs, false) : false; - } - - PUGI_IMPL_FN bool xml_text::set(float rhs) - { - xml_node_struct* dn = _data_new(); - - return dn ? impl::set_value_convert(dn->value, dn->header, impl::xml_memory_page_value_allocated_mask, rhs, default_float_precision) : false; - } - - PUGI_IMPL_FN bool xml_text::set(float rhs, int precision) - { - xml_node_struct* dn = _data_new(); - - return dn ? impl::set_value_convert(dn->value, dn->header, impl::xml_memory_page_value_allocated_mask, rhs, precision) : false; - } - - PUGI_IMPL_FN bool xml_text::set(double rhs) - { - xml_node_struct* dn = _data_new(); - - return dn ? impl::set_value_convert(dn->value, dn->header, impl::xml_memory_page_value_allocated_mask, rhs, default_double_precision) : false; - } - - PUGI_IMPL_FN bool xml_text::set(double rhs, int precision) - { - xml_node_struct* dn = _data_new(); - - return dn ? impl::set_value_convert(dn->value, dn->header, impl::xml_memory_page_value_allocated_mask, rhs, precision) : false; - } - - PUGI_IMPL_FN bool xml_text::set(bool rhs) - { - xml_node_struct* dn = _data_new(); - - return dn ? impl::set_value_bool(dn->value, dn->header, impl::xml_memory_page_value_allocated_mask, rhs) : false; - } - -#ifdef PUGIXML_HAS_LONG_LONG - PUGI_IMPL_FN bool xml_text::set(long long rhs) - { - xml_node_struct* dn = _data_new(); - - return dn ? impl::set_value_integer(dn->value, dn->header, impl::xml_memory_page_value_allocated_mask, rhs, rhs < 0) : false; - } - - PUGI_IMPL_FN bool xml_text::set(unsigned long long rhs) - { - xml_node_struct* dn = _data_new(); - - return dn ? impl::set_value_integer(dn->value, dn->header, impl::xml_memory_page_value_allocated_mask, rhs, false) : false; - } -#endif - - PUGI_IMPL_FN xml_text& xml_text::operator=(const char_t* rhs) - { - set(rhs); - return *this; - } - - PUGI_IMPL_FN xml_text& xml_text::operator=(int rhs) - { - set(rhs); - return *this; - } - - PUGI_IMPL_FN xml_text& xml_text::operator=(unsigned int rhs) - { - set(rhs); - return *this; - } - - PUGI_IMPL_FN xml_text& xml_text::operator=(long rhs) - { - set(rhs); - return *this; - } - - PUGI_IMPL_FN xml_text& xml_text::operator=(unsigned long rhs) - { - set(rhs); - return *this; - } - - PUGI_IMPL_FN xml_text& xml_text::operator=(double rhs) - { - set(rhs); - return *this; - } - - PUGI_IMPL_FN xml_text& xml_text::operator=(float rhs) - { - set(rhs); - return *this; - } - - PUGI_IMPL_FN xml_text& xml_text::operator=(bool rhs) - { - set(rhs); - return *this; - } - -#ifdef PUGIXML_HAS_LONG_LONG - PUGI_IMPL_FN xml_text& xml_text::operator=(long long rhs) - { - set(rhs); - return *this; - } - - PUGI_IMPL_FN xml_text& xml_text::operator=(unsigned long long rhs) - { - set(rhs); - return *this; - } -#endif - - PUGI_IMPL_FN xml_node xml_text::data() const - { - return xml_node(_data()); - } - -#ifdef __BORLANDC__ - PUGI_IMPL_FN bool operator&&(const xml_text& lhs, bool rhs) - { - return (bool)lhs && rhs; - } - - PUGI_IMPL_FN bool operator||(const xml_text& lhs, bool rhs) - { - return (bool)lhs || rhs; - } -#endif - - PUGI_IMPL_FN xml_node_iterator::xml_node_iterator() - { - } - - PUGI_IMPL_FN xml_node_iterator::xml_node_iterator(const xml_node& node): _wrap(node), _parent(node.parent()) - { - } - - PUGI_IMPL_FN xml_node_iterator::xml_node_iterator(xml_node_struct* ref, xml_node_struct* parent): _wrap(ref), _parent(parent) - { - } - - PUGI_IMPL_FN bool xml_node_iterator::operator==(const xml_node_iterator& rhs) const - { - return _wrap._root == rhs._wrap._root && _parent._root == rhs._parent._root; - } - - PUGI_IMPL_FN bool xml_node_iterator::operator!=(const xml_node_iterator& rhs) const - { - return _wrap._root != rhs._wrap._root || _parent._root != rhs._parent._root; - } - - PUGI_IMPL_FN xml_node& xml_node_iterator::operator*() const - { - assert(_wrap._root); - return _wrap; - } - - PUGI_IMPL_FN xml_node* xml_node_iterator::operator->() const - { - assert(_wrap._root); - return const_cast(&_wrap); // BCC5 workaround - } - - PUGI_IMPL_FN xml_node_iterator& xml_node_iterator::operator++() - { - assert(_wrap._root); - _wrap._root = _wrap._root->next_sibling; - return *this; - } - - PUGI_IMPL_FN xml_node_iterator xml_node_iterator::operator++(int) - { - xml_node_iterator temp = *this; - ++*this; - return temp; - } - - PUGI_IMPL_FN xml_node_iterator& xml_node_iterator::operator--() - { - _wrap = _wrap._root ? _wrap.previous_sibling() : _parent.last_child(); - return *this; - } - - PUGI_IMPL_FN xml_node_iterator xml_node_iterator::operator--(int) - { - xml_node_iterator temp = *this; - --*this; - return temp; - } - - PUGI_IMPL_FN xml_attribute_iterator::xml_attribute_iterator() - { - } - - PUGI_IMPL_FN xml_attribute_iterator::xml_attribute_iterator(const xml_attribute& attr, const xml_node& parent): _wrap(attr), _parent(parent) - { - } - - PUGI_IMPL_FN xml_attribute_iterator::xml_attribute_iterator(xml_attribute_struct* ref, xml_node_struct* parent): _wrap(ref), _parent(parent) - { - } - - PUGI_IMPL_FN bool xml_attribute_iterator::operator==(const xml_attribute_iterator& rhs) const - { - return _wrap._attr == rhs._wrap._attr && _parent._root == rhs._parent._root; - } - - PUGI_IMPL_FN bool xml_attribute_iterator::operator!=(const xml_attribute_iterator& rhs) const - { - return _wrap._attr != rhs._wrap._attr || _parent._root != rhs._parent._root; - } - - PUGI_IMPL_FN xml_attribute& xml_attribute_iterator::operator*() const - { - assert(_wrap._attr); - return _wrap; - } - - PUGI_IMPL_FN xml_attribute* xml_attribute_iterator::operator->() const - { - assert(_wrap._attr); - return const_cast(&_wrap); // BCC5 workaround - } - - PUGI_IMPL_FN xml_attribute_iterator& xml_attribute_iterator::operator++() - { - assert(_wrap._attr); - _wrap._attr = _wrap._attr->next_attribute; - return *this; - } - - PUGI_IMPL_FN xml_attribute_iterator xml_attribute_iterator::operator++(int) - { - xml_attribute_iterator temp = *this; - ++*this; - return temp; - } - - PUGI_IMPL_FN xml_attribute_iterator& xml_attribute_iterator::operator--() - { - _wrap = _wrap._attr ? _wrap.previous_attribute() : _parent.last_attribute(); - return *this; - } - - PUGI_IMPL_FN xml_attribute_iterator xml_attribute_iterator::operator--(int) - { - xml_attribute_iterator temp = *this; - --*this; - return temp; - } - - PUGI_IMPL_FN xml_named_node_iterator::xml_named_node_iterator(): _name(0) - { - } - - PUGI_IMPL_FN xml_named_node_iterator::xml_named_node_iterator(const xml_node& node, const char_t* name): _wrap(node), _parent(node.parent()), _name(name) - { - } - - PUGI_IMPL_FN xml_named_node_iterator::xml_named_node_iterator(xml_node_struct* ref, xml_node_struct* parent, const char_t* name): _wrap(ref), _parent(parent), _name(name) - { - } - - PUGI_IMPL_FN bool xml_named_node_iterator::operator==(const xml_named_node_iterator& rhs) const - { - return _wrap._root == rhs._wrap._root && _parent._root == rhs._parent._root; - } - - PUGI_IMPL_FN bool xml_named_node_iterator::operator!=(const xml_named_node_iterator& rhs) const - { - return _wrap._root != rhs._wrap._root || _parent._root != rhs._parent._root; - } - - PUGI_IMPL_FN xml_node& xml_named_node_iterator::operator*() const - { - assert(_wrap._root); - return _wrap; - } - - PUGI_IMPL_FN xml_node* xml_named_node_iterator::operator->() const - { - assert(_wrap._root); - return const_cast(&_wrap); // BCC5 workaround - } - - PUGI_IMPL_FN xml_named_node_iterator& xml_named_node_iterator::operator++() - { - assert(_wrap._root); - _wrap = _wrap.next_sibling(_name); - return *this; - } - - PUGI_IMPL_FN xml_named_node_iterator xml_named_node_iterator::operator++(int) - { - xml_named_node_iterator temp = *this; - ++*this; - return temp; - } - - PUGI_IMPL_FN xml_named_node_iterator& xml_named_node_iterator::operator--() - { - if (_wrap._root) - _wrap = _wrap.previous_sibling(_name); - else - { - _wrap = _parent.last_child(); - - if (!impl::strequal(_wrap.name(), _name)) - _wrap = _wrap.previous_sibling(_name); - } - - return *this; - } - - PUGI_IMPL_FN xml_named_node_iterator xml_named_node_iterator::operator--(int) - { - xml_named_node_iterator temp = *this; - --*this; - return temp; - } - - PUGI_IMPL_FN xml_parse_result::xml_parse_result(): status(status_internal_error), offset(0), encoding(encoding_auto) - { - } - - PUGI_IMPL_FN xml_parse_result::operator bool() const - { - return status == status_ok; - } - - PUGI_IMPL_FN const char* xml_parse_result::description() const - { - switch (status) - { - case status_ok: return "No error"; - - case status_file_not_found: return "File was not found"; - case status_io_error: return "Error reading from file/stream"; - case status_out_of_memory: return "Could not allocate memory"; - case status_internal_error: return "Internal error occurred"; - - case status_unrecognized_tag: return "Could not determine tag type"; - - case status_bad_pi: return "Error parsing document declaration/processing instruction"; - case status_bad_comment: return "Error parsing comment"; - case status_bad_cdata: return "Error parsing CDATA section"; - case status_bad_doctype: return "Error parsing document type declaration"; - case status_bad_pcdata: return "Error parsing PCDATA section"; - case status_bad_start_element: return "Error parsing start element tag"; - case status_bad_attribute: return "Error parsing element attribute"; - case status_bad_end_element: return "Error parsing end element tag"; - case status_end_element_mismatch: return "Start-end tags mismatch"; - - case status_append_invalid_root: return "Unable to append nodes: root is not an element or document"; - - case status_no_document_element: return "No document element found"; - - default: return "Unknown error"; - } - } - - PUGI_IMPL_FN xml_document::xml_document(): _buffer(0) - { - _create(); - } - - PUGI_IMPL_FN xml_document::~xml_document() - { - _destroy(); - } - -#ifdef PUGIXML_HAS_MOVE - PUGI_IMPL_FN xml_document::xml_document(xml_document&& rhs) PUGIXML_NOEXCEPT_IF_NOT_COMPACT: _buffer(0) - { - _create(); - _move(rhs); - } - - PUGI_IMPL_FN xml_document& xml_document::operator=(xml_document&& rhs) PUGIXML_NOEXCEPT_IF_NOT_COMPACT - { - if (this == &rhs) return *this; - - _destroy(); - _create(); - _move(rhs); - - return *this; - } -#endif - - PUGI_IMPL_FN void xml_document::reset() - { - _destroy(); - _create(); - } - - PUGI_IMPL_FN void xml_document::reset(const xml_document& proto) - { - reset(); - - impl::node_copy_tree(_root, proto._root); - } - - PUGI_IMPL_FN void xml_document::_create() - { - assert(!_root); - - #ifdef PUGIXML_COMPACT - // space for page marker for the first page (uint32_t), rounded up to pointer size; assumes pointers are at least 32-bit - const size_t page_offset = sizeof(void*); - #else - const size_t page_offset = 0; - #endif - - // initialize sentinel page - PUGI_IMPL_STATIC_ASSERT(sizeof(impl::xml_memory_page) + sizeof(impl::xml_document_struct) + page_offset <= sizeof(_memory)); - - // prepare page structure - impl::xml_memory_page* page = impl::xml_memory_page::construct(_memory); - assert(page); - - page->busy_size = impl::xml_memory_page_size; - - // setup first page marker - #ifdef PUGIXML_COMPACT - // round-trip through void* to avoid 'cast increases required alignment of target type' warning - page->compact_page_marker = reinterpret_cast(static_cast(reinterpret_cast(page) + sizeof(impl::xml_memory_page))); - *page->compact_page_marker = sizeof(impl::xml_memory_page); - #endif - - // allocate new root - _root = new (reinterpret_cast(page) + sizeof(impl::xml_memory_page) + page_offset) impl::xml_document_struct(page); - _root->prev_sibling_c = _root; - - // setup sentinel page - page->allocator = static_cast(_root); - - // setup hash table pointer in allocator - #ifdef PUGIXML_COMPACT - page->allocator->_hash = &static_cast(_root)->hash; - #endif - - // verify the document allocation - assert(reinterpret_cast(_root) + sizeof(impl::xml_document_struct) <= _memory + sizeof(_memory)); - } - - PUGI_IMPL_FN void xml_document::_destroy() - { - assert(_root); - - // destroy static storage - if (_buffer) - { - impl::xml_memory::deallocate(_buffer); - _buffer = 0; - } - - // destroy extra buffers (note: no need to destroy linked list nodes, they're allocated using document allocator) - for (impl::xml_extra_buffer* extra = static_cast(_root)->extra_buffers; extra; extra = extra->next) - { - if (extra->buffer) impl::xml_memory::deallocate(extra->buffer); - } - - // destroy dynamic storage, leave sentinel page (it's in static memory) - impl::xml_memory_page* root_page = PUGI_IMPL_GETPAGE(_root); - assert(root_page && !root_page->prev); - assert(reinterpret_cast(root_page) >= _memory && reinterpret_cast(root_page) < _memory + sizeof(_memory)); - - for (impl::xml_memory_page* page = root_page->next; page; ) - { - impl::xml_memory_page* next = page->next; - - impl::xml_allocator::deallocate_page(page); - - page = next; - } - - #ifdef PUGIXML_COMPACT - // destroy hash table - static_cast(_root)->hash.clear(); - #endif - - _root = 0; - } - -#ifdef PUGIXML_HAS_MOVE - PUGI_IMPL_FN void xml_document::_move(xml_document& rhs) PUGIXML_NOEXCEPT_IF_NOT_COMPACT - { - impl::xml_document_struct* doc = static_cast(_root); - impl::xml_document_struct* other = static_cast(rhs._root); - - // save first child pointer for later; this needs hash access - xml_node_struct* other_first_child = other->first_child; - - #ifdef PUGIXML_COMPACT - // reserve space for the hash table up front; this is the only operation that can fail - // if it does, we have no choice but to throw (if we have exceptions) - if (other_first_child) - { - size_t other_children = 0; - for (xml_node_struct* node = other_first_child; node; node = node->next_sibling) - other_children++; - - // in compact mode, each pointer assignment could result in a hash table request - // during move, we have to relocate document first_child and parents of all children - // normally there's just one child and its parent has a pointerless encoding but - // we assume the worst here - if (!other->_hash->reserve(other_children + 1)) - { - #ifdef PUGIXML_NO_EXCEPTIONS - return; - #else - throw std::bad_alloc(); - #endif - } - } - #endif - - // move allocation state - // note that other->_root may point to the embedded document page, in which case we should keep original (empty) state - if (other->_root != PUGI_IMPL_GETPAGE(other)) - { - doc->_root = other->_root; - doc->_busy_size = other->_busy_size; - } - - // move buffer state - doc->buffer = other->buffer; - doc->extra_buffers = other->extra_buffers; - _buffer = rhs._buffer; - - #ifdef PUGIXML_COMPACT - // move compact hash; note that the hash table can have pointers to other but they will be "inactive", similarly to nodes removed with remove_child - doc->hash = other->hash; - doc->_hash = &doc->hash; - - // make sure we don't access other hash up until the end when we reinitialize other document - other->_hash = 0; - #endif - - // move page structure - impl::xml_memory_page* doc_page = PUGI_IMPL_GETPAGE(doc); - assert(doc_page && !doc_page->prev && !doc_page->next); - - impl::xml_memory_page* other_page = PUGI_IMPL_GETPAGE(other); - assert(other_page && !other_page->prev); - - // relink pages since root page is embedded into xml_document - if (impl::xml_memory_page* page = other_page->next) - { - assert(page->prev == other_page); - - page->prev = doc_page; - - doc_page->next = page; - other_page->next = 0; - } - - // make sure pages point to the correct document state - for (impl::xml_memory_page* page = doc_page->next; page; page = page->next) - { - assert(page->allocator == other); - - page->allocator = doc; - - #ifdef PUGIXML_COMPACT - // this automatically migrates most children between documents and prevents ->parent assignment from allocating - if (page->compact_shared_parent == other) - page->compact_shared_parent = doc; - #endif - } - - // move tree structure - assert(!doc->first_child); - - doc->first_child = other_first_child; - - for (xml_node_struct* node = other_first_child; node; node = node->next_sibling) - { - #ifdef PUGIXML_COMPACT - // most children will have migrated when we reassigned compact_shared_parent - assert(node->parent == other || node->parent == doc); - - node->parent = doc; - #else - assert(node->parent == other); - node->parent = doc; - #endif - } - - // reset other document - new (other) impl::xml_document_struct(PUGI_IMPL_GETPAGE(other)); - rhs._buffer = 0; - } -#endif - -#ifndef PUGIXML_NO_STL - PUGI_IMPL_FN xml_parse_result xml_document::load(std::basic_istream >& stream, unsigned int options, xml_encoding encoding) - { - reset(); - - return impl::load_stream_impl(static_cast(_root), stream, options, encoding, &_buffer); - } - - PUGI_IMPL_FN xml_parse_result xml_document::load(std::basic_istream >& stream, unsigned int options) - { - reset(); - - return impl::load_stream_impl(static_cast(_root), stream, options, encoding_wchar, &_buffer); - } -#endif - - PUGI_IMPL_FN xml_parse_result xml_document::load_string(const char_t* contents, unsigned int options) - { - // Force native encoding (skip autodetection) - #ifdef PUGIXML_WCHAR_MODE - xml_encoding encoding = encoding_wchar; - #else - xml_encoding encoding = encoding_utf8; - #endif - - return load_buffer(contents, impl::strlength(contents) * sizeof(char_t), options, encoding); - } - - PUGI_IMPL_FN xml_parse_result xml_document::load(const char_t* contents, unsigned int options) - { - return load_string(contents, options); - } - - PUGI_IMPL_FN xml_parse_result xml_document::load_file(const char* path_, unsigned int options, xml_encoding encoding) - { - reset(); - - using impl::auto_deleter; // MSVC7 workaround - auto_deleter file(impl::open_file(path_, "rb"), impl::close_file); - - return impl::load_file_impl(static_cast(_root), file.data, options, encoding, &_buffer); - } - - PUGI_IMPL_FN xml_parse_result xml_document::load_file(const wchar_t* path_, unsigned int options, xml_encoding encoding) - { - reset(); - - using impl::auto_deleter; // MSVC7 workaround - auto_deleter file(impl::open_file_wide(path_, L"rb"), impl::close_file); - - return impl::load_file_impl(static_cast(_root), file.data, options, encoding, &_buffer); - } - - PUGI_IMPL_FN xml_parse_result xml_document::load_buffer(const void* contents, size_t size, unsigned int options, xml_encoding encoding) - { - reset(); - - return impl::load_buffer_impl(static_cast(_root), _root, const_cast(contents), size, options, encoding, false, false, &_buffer); - } - - PUGI_IMPL_FN xml_parse_result xml_document::load_buffer_inplace(void* contents, size_t size, unsigned int options, xml_encoding encoding) - { - reset(); - - return impl::load_buffer_impl(static_cast(_root), _root, contents, size, options, encoding, true, false, &_buffer); - } - - PUGI_IMPL_FN xml_parse_result xml_document::load_buffer_inplace_own(void* contents, size_t size, unsigned int options, xml_encoding encoding) - { - reset(); - - return impl::load_buffer_impl(static_cast(_root), _root, contents, size, options, encoding, true, true, &_buffer); - } - - PUGI_IMPL_FN void xml_document::save(xml_writer& writer, const char_t* indent, unsigned int flags, xml_encoding encoding) const - { - impl::xml_buffered_writer buffered_writer(writer, encoding); - - if ((flags & format_write_bom) && encoding != encoding_latin1) - { - // BOM always represents the codepoint U+FEFF, so just write it in native encoding - #ifdef PUGIXML_WCHAR_MODE - unsigned int bom = 0xfeff; - buffered_writer.write(static_cast(bom)); - #else - buffered_writer.write('\xef', '\xbb', '\xbf'); - #endif - } - - if (!(flags & format_no_declaration) && !impl::has_declaration(_root)) - { - buffered_writer.write_string(PUGIXML_TEXT("'); - if (!(flags & format_raw)) buffered_writer.write('\n'); - } - - impl::node_output(buffered_writer, _root, indent, flags, 0); - - buffered_writer.flush(); - } - -#ifndef PUGIXML_NO_STL - PUGI_IMPL_FN void xml_document::save(std::basic_ostream >& stream, const char_t* indent, unsigned int flags, xml_encoding encoding) const - { - xml_writer_stream writer(stream); - - save(writer, indent, flags, encoding); - } - - PUGI_IMPL_FN void xml_document::save(std::basic_ostream >& stream, const char_t* indent, unsigned int flags) const - { - xml_writer_stream writer(stream); - - save(writer, indent, flags, encoding_wchar); - } -#endif - - PUGI_IMPL_FN bool xml_document::save_file(const char* path_, const char_t* indent, unsigned int flags, xml_encoding encoding) const - { - using impl::auto_deleter; // MSVC7 workaround - auto_deleter file(impl::open_file(path_, (flags & format_save_file_text) ? "w" : "wb"), impl::close_file); - - return impl::save_file_impl(*this, file.data, indent, flags, encoding) && fclose(file.release()) == 0; - } - - PUGI_IMPL_FN bool xml_document::save_file(const wchar_t* path_, const char_t* indent, unsigned int flags, xml_encoding encoding) const - { - using impl::auto_deleter; // MSVC7 workaround - auto_deleter file(impl::open_file_wide(path_, (flags & format_save_file_text) ? L"w" : L"wb"), impl::close_file); - - return impl::save_file_impl(*this, file.data, indent, flags, encoding) && fclose(file.release()) == 0; - } - - PUGI_IMPL_FN xml_node xml_document::document_element() const - { - assert(_root); - - for (xml_node_struct* i = _root->first_child; i; i = i->next_sibling) - if (PUGI_IMPL_NODETYPE(i) == node_element) - return xml_node(i); - - return xml_node(); - } - -#ifndef PUGIXML_NO_STL - PUGI_IMPL_FN std::string PUGIXML_FUNCTION as_utf8(const wchar_t* str) - { - assert(str); - - return impl::as_utf8_impl(str, impl::strlength_wide(str)); - } - - PUGI_IMPL_FN std::string PUGIXML_FUNCTION as_utf8(const std::basic_string& str) - { - return impl::as_utf8_impl(str.c_str(), str.size()); - } - - PUGI_IMPL_FN std::basic_string PUGIXML_FUNCTION as_wide(const char* str) - { - assert(str); - - return impl::as_wide_impl(str, strlen(str)); - } - - PUGI_IMPL_FN std::basic_string PUGIXML_FUNCTION as_wide(const std::string& str) - { - return impl::as_wide_impl(str.c_str(), str.size()); - } -#endif - - PUGI_IMPL_FN void PUGIXML_FUNCTION set_memory_management_functions(allocation_function allocate, deallocation_function deallocate) - { - impl::xml_memory::allocate = allocate; - impl::xml_memory::deallocate = deallocate; - } - - PUGI_IMPL_FN allocation_function PUGIXML_FUNCTION get_memory_allocation_function() - { - return impl::xml_memory::allocate; - } - - PUGI_IMPL_FN deallocation_function PUGIXML_FUNCTION get_memory_deallocation_function() - { - return impl::xml_memory::deallocate; - } -} - -#if !defined(PUGIXML_NO_STL) && (defined(_MSC_VER) || defined(__ICC)) -namespace std -{ - // Workarounds for (non-standard) iterator category detection for older versions (MSVC7/IC8 and earlier) - PUGI_IMPL_FN std::bidirectional_iterator_tag _Iter_cat(const pugi::xml_node_iterator&) - { - return std::bidirectional_iterator_tag(); - } - - PUGI_IMPL_FN std::bidirectional_iterator_tag _Iter_cat(const pugi::xml_attribute_iterator&) - { - return std::bidirectional_iterator_tag(); - } - - PUGI_IMPL_FN std::bidirectional_iterator_tag _Iter_cat(const pugi::xml_named_node_iterator&) - { - return std::bidirectional_iterator_tag(); - } -} -#endif - -#if !defined(PUGIXML_NO_STL) && defined(__SUNPRO_CC) -namespace std -{ - // Workarounds for (non-standard) iterator category detection - PUGI_IMPL_FN std::bidirectional_iterator_tag __iterator_category(const pugi::xml_node_iterator&) - { - return std::bidirectional_iterator_tag(); - } - - PUGI_IMPL_FN std::bidirectional_iterator_tag __iterator_category(const pugi::xml_attribute_iterator&) - { - return std::bidirectional_iterator_tag(); - } - - PUGI_IMPL_FN std::bidirectional_iterator_tag __iterator_category(const pugi::xml_named_node_iterator&) - { - return std::bidirectional_iterator_tag(); - } -} -#endif - -#ifndef PUGIXML_NO_XPATH -// STL replacements -PUGI_IMPL_NS_BEGIN - struct equal_to - { - template bool operator()(const T& lhs, const T& rhs) const - { - return lhs == rhs; - } - }; - - struct not_equal_to - { - template bool operator()(const T& lhs, const T& rhs) const - { - return lhs != rhs; - } - }; - - struct less - { - template bool operator()(const T& lhs, const T& rhs) const - { - return lhs < rhs; - } - }; - - struct less_equal - { - template bool operator()(const T& lhs, const T& rhs) const - { - return lhs <= rhs; - } - }; - - template inline void swap(T& lhs, T& rhs) - { - T temp = lhs; - lhs = rhs; - rhs = temp; - } - - template PUGI_IMPL_FN I min_element(I begin, I end, const Pred& pred) - { - I result = begin; - - for (I it = begin + 1; it != end; ++it) - if (pred(*it, *result)) - result = it; - - return result; - } - - template PUGI_IMPL_FN void reverse(I begin, I end) - { - while (end - begin > 1) - swap(*begin++, *--end); - } - - template PUGI_IMPL_FN I unique(I begin, I end) - { - // fast skip head - while (end - begin > 1 && *begin != *(begin + 1)) - begin++; - - if (begin == end) - return begin; - - // last written element - I write = begin++; - - // merge unique elements - while (begin != end) - { - if (*begin != *write) - *++write = *begin++; - else - begin++; - } - - // past-the-end (write points to live element) - return write + 1; - } - - template PUGI_IMPL_FN void insertion_sort(T* begin, T* end, const Pred& pred) - { - if (begin == end) - return; - - for (T* it = begin + 1; it != end; ++it) - { - T val = *it; - T* hole = it; - - // move hole backwards - while (hole > begin && pred(val, *(hole - 1))) - { - *hole = *(hole - 1); - hole--; - } - - // fill hole with element - *hole = val; - } - } - - template inline I median3(I first, I middle, I last, const Pred& pred) - { - if (pred(*middle, *first)) - swap(middle, first); - if (pred(*last, *middle)) - swap(last, middle); - if (pred(*middle, *first)) - swap(middle, first); - - return middle; - } - - template PUGI_IMPL_FN void partition3(T* begin, T* end, T pivot, const Pred& pred, T** out_eqbeg, T** out_eqend) - { - // invariant: array is split into 4 groups: = < ? > (each variable denotes the boundary between the groups) - T* eq = begin; - T* lt = begin; - T* gt = end; - - while (lt < gt) - { - if (pred(*lt, pivot)) - lt++; - else if (*lt == pivot) - swap(*eq++, *lt++); - else - swap(*lt, *--gt); - } - - // we now have just 4 groups: = < >; move equal elements to the middle - T* eqbeg = gt; - - for (T* it = begin; it != eq; ++it) - swap(*it, *--eqbeg); - - *out_eqbeg = eqbeg; - *out_eqend = gt; - } - - template PUGI_IMPL_FN void sort(I begin, I end, const Pred& pred) - { - // sort large chunks - while (end - begin > 16) - { - // find median element - I middle = begin + (end - begin) / 2; - I median = median3(begin, middle, end - 1, pred); - - // partition in three chunks (< = >) - I eqbeg, eqend; - partition3(begin, end, *median, pred, &eqbeg, &eqend); - - // loop on larger half - if (eqbeg - begin > end - eqend) - { - sort(eqend, end, pred); - end = eqbeg; - } - else - { - sort(begin, eqbeg, pred); - begin = eqend; - } - } - - // insertion sort small chunk - insertion_sort(begin, end, pred); - } - - PUGI_IMPL_FN bool hash_insert(const void** table, size_t size, const void* key) - { - assert(key); - - unsigned int h = static_cast(reinterpret_cast(key)); - - // MurmurHash3 32-bit finalizer - h ^= h >> 16; - h *= 0x85ebca6bu; - h ^= h >> 13; - h *= 0xc2b2ae35u; - h ^= h >> 16; - - size_t hashmod = size - 1; - size_t bucket = h & hashmod; - - for (size_t probe = 0; probe <= hashmod; ++probe) - { - if (table[bucket] == 0) - { - table[bucket] = key; - return true; - } - - if (table[bucket] == key) - return false; - - // hash collision, quadratic probing - bucket = (bucket + probe + 1) & hashmod; - } - - assert(false && "Hash table is full"); // unreachable - return false; - } -PUGI_IMPL_NS_END - -// Allocator used for AST and evaluation stacks -PUGI_IMPL_NS_BEGIN - static const size_t xpath_memory_page_size = - #ifdef PUGIXML_MEMORY_XPATH_PAGE_SIZE - PUGIXML_MEMORY_XPATH_PAGE_SIZE - #else - 4096 - #endif - ; - - static const uintptr_t xpath_memory_block_alignment = sizeof(double) > sizeof(void*) ? sizeof(double) : sizeof(void*); - - struct xpath_memory_block - { - xpath_memory_block* next; - size_t capacity; - - union - { - char data[xpath_memory_page_size]; - double alignment; - }; - }; - - struct xpath_allocator - { - xpath_memory_block* _root; - size_t _root_size; - bool* _error; - - xpath_allocator(xpath_memory_block* root, bool* error = 0): _root(root), _root_size(0), _error(error) - { - } - - void* allocate(size_t size) - { - // round size up to block alignment boundary - size = (size + xpath_memory_block_alignment - 1) & ~(xpath_memory_block_alignment - 1); - - if (_root_size + size <= _root->capacity) - { - void* buf = &_root->data[0] + _root_size; - _root_size += size; - return buf; - } - else - { - // make sure we have at least 1/4th of the page free after allocation to satisfy subsequent allocation requests - size_t block_capacity_base = sizeof(_root->data); - size_t block_capacity_req = size + block_capacity_base / 4; - size_t block_capacity = (block_capacity_base > block_capacity_req) ? block_capacity_base : block_capacity_req; - - size_t block_size = block_capacity + offsetof(xpath_memory_block, data); - - xpath_memory_block* block = static_cast(xml_memory::allocate(block_size)); - if (!block) - { - if (_error) *_error = true; - return 0; - } - - block->next = _root; - block->capacity = block_capacity; - - _root = block; - _root_size = size; - - return block->data; - } - } - - void* reallocate(void* ptr, size_t old_size, size_t new_size) - { - // round size up to block alignment boundary - old_size = (old_size + xpath_memory_block_alignment - 1) & ~(xpath_memory_block_alignment - 1); - new_size = (new_size + xpath_memory_block_alignment - 1) & ~(xpath_memory_block_alignment - 1); - - // we can only reallocate the last object - assert(ptr == 0 || static_cast(ptr) + old_size == &_root->data[0] + _root_size); - - // try to reallocate the object inplace - if (ptr && _root_size - old_size + new_size <= _root->capacity) - { - _root_size = _root_size - old_size + new_size; - return ptr; - } - - // allocate a new block - void* result = allocate(new_size); - if (!result) return 0; - - // we have a new block - if (ptr) - { - // copy old data (we only support growing) - assert(new_size >= old_size); - memcpy(result, ptr, old_size); - - // free the previous page if it had no other objects - assert(_root->data == result); - assert(_root->next); - - if (_root->next->data == ptr) - { - // deallocate the whole page, unless it was the first one - xpath_memory_block* next = _root->next->next; - - if (next) - { - xml_memory::deallocate(_root->next); - _root->next = next; - } - } - } - - return result; - } - - void revert(const xpath_allocator& state) - { - // free all new pages - xpath_memory_block* cur = _root; - - while (cur != state._root) - { - xpath_memory_block* next = cur->next; - - xml_memory::deallocate(cur); - - cur = next; - } - - // restore state - _root = state._root; - _root_size = state._root_size; - } - - void release() - { - xpath_memory_block* cur = _root; - assert(cur); - - while (cur->next) - { - xpath_memory_block* next = cur->next; - - xml_memory::deallocate(cur); - - cur = next; - } - } - }; - - struct xpath_allocator_capture - { - xpath_allocator_capture(xpath_allocator* alloc): _target(alloc), _state(*alloc) - { - } - - ~xpath_allocator_capture() - { - _target->revert(_state); - } - - xpath_allocator* _target; - xpath_allocator _state; - }; - - struct xpath_stack - { - xpath_allocator* result; - xpath_allocator* temp; - }; - - struct xpath_stack_data - { - xpath_memory_block blocks[2]; - xpath_allocator result; - xpath_allocator temp; - xpath_stack stack; - bool oom; - - xpath_stack_data(): result(blocks + 0, &oom), temp(blocks + 1, &oom), oom(false) - { - blocks[0].next = blocks[1].next = 0; - blocks[0].capacity = blocks[1].capacity = sizeof(blocks[0].data); - - stack.result = &result; - stack.temp = &temp; - } - - ~xpath_stack_data() - { - result.release(); - temp.release(); - } - }; -PUGI_IMPL_NS_END - -// String class -PUGI_IMPL_NS_BEGIN - class xpath_string - { - const char_t* _buffer; - bool _uses_heap; - size_t _length_heap; - - static char_t* duplicate_string(const char_t* string, size_t length, xpath_allocator* alloc) - { - char_t* result = static_cast(alloc->allocate((length + 1) * sizeof(char_t))); - if (!result) return 0; - - memcpy(result, string, length * sizeof(char_t)); - result[length] = 0; - - return result; - } - - xpath_string(const char_t* buffer, bool uses_heap_, size_t length_heap): _buffer(buffer), _uses_heap(uses_heap_), _length_heap(length_heap) - { - } - - public: - static xpath_string from_const(const char_t* str) - { - return xpath_string(str, false, 0); - } - - static xpath_string from_heap_preallocated(const char_t* begin, const char_t* end) - { - assert(begin <= end && *end == 0); - - return xpath_string(begin, true, static_cast(end - begin)); - } - - static xpath_string from_heap(const char_t* begin, const char_t* end, xpath_allocator* alloc) - { - assert(begin <= end); - - if (begin == end) - return xpath_string(); - - size_t length = static_cast(end - begin); - const char_t* data = duplicate_string(begin, length, alloc); - - return data ? xpath_string(data, true, length) : xpath_string(); - } - - xpath_string(): _buffer(PUGIXML_TEXT("")), _uses_heap(false), _length_heap(0) - { - } - - void append(const xpath_string& o, xpath_allocator* alloc) - { - // skip empty sources - if (!*o._buffer) return; - - // fast append for constant empty target and constant source - if (!*_buffer && !_uses_heap && !o._uses_heap) - { - _buffer = o._buffer; - } - else - { - // need to make heap copy - size_t target_length = length(); - size_t source_length = o.length(); - size_t result_length = target_length + source_length; - - // allocate new buffer - char_t* result = static_cast(alloc->reallocate(_uses_heap ? const_cast(_buffer) : 0, (target_length + 1) * sizeof(char_t), (result_length + 1) * sizeof(char_t))); - if (!result) return; - - // append first string to the new buffer in case there was no reallocation - if (!_uses_heap) memcpy(result, _buffer, target_length * sizeof(char_t)); - - // append second string to the new buffer - memcpy(result + target_length, o._buffer, source_length * sizeof(char_t)); - result[result_length] = 0; - - // finalize - _buffer = result; - _uses_heap = true; - _length_heap = result_length; - } - } - - const char_t* c_str() const - { - return _buffer; - } - - size_t length() const - { - return _uses_heap ? _length_heap : strlength(_buffer); - } - - char_t* data(xpath_allocator* alloc) - { - // make private heap copy - if (!_uses_heap) - { - size_t length_ = strlength(_buffer); - const char_t* data_ = duplicate_string(_buffer, length_, alloc); - - if (!data_) return 0; - - _buffer = data_; - _uses_heap = true; - _length_heap = length_; - } - - return const_cast(_buffer); - } - - bool empty() const - { - return *_buffer == 0; - } - - bool operator==(const xpath_string& o) const - { - return strequal(_buffer, o._buffer); - } - - bool operator!=(const xpath_string& o) const - { - return !strequal(_buffer, o._buffer); - } - - bool uses_heap() const - { - return _uses_heap; - } - }; -PUGI_IMPL_NS_END - -PUGI_IMPL_NS_BEGIN - PUGI_IMPL_FN bool starts_with(const char_t* string, const char_t* pattern) - { - while (*pattern && *string == *pattern) - { - string++; - pattern++; - } - - return *pattern == 0; - } - - PUGI_IMPL_FN const char_t* find_char(const char_t* s, char_t c) - { - #ifdef PUGIXML_WCHAR_MODE - return wcschr(s, c); - #else - return strchr(s, c); - #endif - } - - PUGI_IMPL_FN const char_t* find_substring(const char_t* s, const char_t* p) - { - #ifdef PUGIXML_WCHAR_MODE - // MSVC6 wcsstr bug workaround (if s is empty it always returns 0) - return (*p == 0) ? s : wcsstr(s, p); - #else - return strstr(s, p); - #endif - } - - // Converts symbol to lower case, if it is an ASCII one - PUGI_IMPL_FN char_t tolower_ascii(char_t ch) - { - return static_cast(ch - 'A') < 26 ? static_cast(ch | ' ') : ch; - } - - PUGI_IMPL_FN xpath_string string_value(const xpath_node& na, xpath_allocator* alloc) - { - if (na.attribute()) - return xpath_string::from_const(na.attribute().value()); - else - { - xml_node n = na.node(); - - switch (n.type()) - { - case node_pcdata: - case node_cdata: - case node_comment: - case node_pi: - return xpath_string::from_const(n.value()); - - case node_document: - case node_element: - { - xpath_string result; - - // element nodes can have value if parse_embed_pcdata was used - if (n.value()[0]) - result.append(xpath_string::from_const(n.value()), alloc); - - xml_node cur = n.first_child(); - - while (cur && cur != n) - { - if (cur.type() == node_pcdata || cur.type() == node_cdata) - result.append(xpath_string::from_const(cur.value()), alloc); - - if (cur.first_child()) - cur = cur.first_child(); - else if (cur.next_sibling()) - cur = cur.next_sibling(); - else - { - while (!cur.next_sibling() && cur != n) - cur = cur.parent(); - - if (cur != n) cur = cur.next_sibling(); - } - } - - return result; - } - - default: - return xpath_string(); - } - } - } - - PUGI_IMPL_FN bool node_is_before_sibling(xml_node_struct* ln, xml_node_struct* rn) - { - assert(ln->parent == rn->parent); - - // there is no common ancestor (the shared parent is null), nodes are from different documents - if (!ln->parent) return ln < rn; - - // determine sibling order - xml_node_struct* ls = ln; - xml_node_struct* rs = rn; - - while (ls && rs) - { - if (ls == rn) return true; - if (rs == ln) return false; - - ls = ls->next_sibling; - rs = rs->next_sibling; - } - - // if rn sibling chain ended ln must be before rn - return !rs; - } - - PUGI_IMPL_FN bool node_is_before(xml_node_struct* ln, xml_node_struct* rn) - { - // find common ancestor at the same depth, if any - xml_node_struct* lp = ln; - xml_node_struct* rp = rn; - - while (lp && rp && lp->parent != rp->parent) - { - lp = lp->parent; - rp = rp->parent; - } - - // parents are the same! - if (lp && rp) return node_is_before_sibling(lp, rp); - - // nodes are at different depths, need to normalize heights - bool left_higher = !lp; - - while (lp) - { - lp = lp->parent; - ln = ln->parent; - } - - while (rp) - { - rp = rp->parent; - rn = rn->parent; - } - - // one node is the ancestor of the other - if (ln == rn) return left_higher; - - // find common ancestor... again - while (ln->parent != rn->parent) - { - ln = ln->parent; - rn = rn->parent; - } - - return node_is_before_sibling(ln, rn); - } - - PUGI_IMPL_FN bool node_is_ancestor(xml_node_struct* parent, xml_node_struct* node) - { - while (node && node != parent) node = node->parent; - - return parent && node == parent; - } - - PUGI_IMPL_FN const void* document_buffer_order(const xpath_node& xnode) - { - xml_node_struct* node = xnode.node().internal_object(); - - if (node) - { - if ((get_document(node).header & xml_memory_page_contents_shared_mask) == 0) - { - if (node->name && (node->header & impl::xml_memory_page_name_allocated_or_shared_mask) == 0) return node->name; - if (node->value && (node->header & impl::xml_memory_page_value_allocated_or_shared_mask) == 0) return node->value; - } - - return 0; - } - - xml_attribute_struct* attr = xnode.attribute().internal_object(); - - if (attr) - { - if ((get_document(attr).header & xml_memory_page_contents_shared_mask) == 0) - { - if ((attr->header & impl::xml_memory_page_name_allocated_or_shared_mask) == 0) return attr->name; - if ((attr->header & impl::xml_memory_page_value_allocated_or_shared_mask) == 0) return attr->value; - } - - return 0; - } - - return 0; - } - - struct document_order_comparator - { - bool operator()(const xpath_node& lhs, const xpath_node& rhs) const - { - // optimized document order based check - const void* lo = document_buffer_order(lhs); - const void* ro = document_buffer_order(rhs); - - if (lo && ro) return lo < ro; - - // slow comparison - xml_node ln = lhs.node(), rn = rhs.node(); - - // compare attributes - if (lhs.attribute() && rhs.attribute()) - { - // shared parent - if (lhs.parent() == rhs.parent()) - { - // determine sibling order - for (xml_attribute a = lhs.attribute(); a; a = a.next_attribute()) - if (a == rhs.attribute()) - return true; - - return false; - } - - // compare attribute parents - ln = lhs.parent(); - rn = rhs.parent(); - } - else if (lhs.attribute()) - { - // attributes go after the parent element - if (lhs.parent() == rhs.node()) return false; - - ln = lhs.parent(); - } - else if (rhs.attribute()) - { - // attributes go after the parent element - if (rhs.parent() == lhs.node()) return true; - - rn = rhs.parent(); - } - - if (ln == rn) return false; - - if (!ln || !rn) return ln < rn; - - return node_is_before(ln.internal_object(), rn.internal_object()); - } - }; - - PUGI_IMPL_FN double gen_nan() - { - #if defined(__STDC_IEC_559__) || ((FLT_RADIX - 0 == 2) && (FLT_MAX_EXP - 0 == 128) && (FLT_MANT_DIG - 0 == 24)) - PUGI_IMPL_STATIC_ASSERT(sizeof(float) == sizeof(uint32_t)); - typedef uint32_t UI; // BCC5 workaround - union { float f; UI i; } u; - u.i = 0x7fc00000; - return double(u.f); - #else - // fallback - const volatile double zero = 0.0; - return zero / zero; - #endif - } - - PUGI_IMPL_FN bool is_nan(double value) - { - #if defined(PUGI_IMPL_MSVC_CRT_VERSION) || defined(__BORLANDC__) - return !!_isnan(value); - #elif defined(fpclassify) && defined(FP_NAN) - return fpclassify(value) == FP_NAN; - #else - // fallback - const volatile double v = value; - return v != v; - #endif - } - - PUGI_IMPL_FN const char_t* convert_number_to_string_special(double value) - { - #if defined(PUGI_IMPL_MSVC_CRT_VERSION) || defined(__BORLANDC__) - if (_finite(value)) return (value == 0) ? PUGIXML_TEXT("0") : 0; - if (_isnan(value)) return PUGIXML_TEXT("NaN"); - return value > 0 ? PUGIXML_TEXT("Infinity") : PUGIXML_TEXT("-Infinity"); - #elif defined(fpclassify) && defined(FP_NAN) && defined(FP_INFINITE) && defined(FP_ZERO) - switch (fpclassify(value)) - { - case FP_NAN: - return PUGIXML_TEXT("NaN"); - - case FP_INFINITE: - return value > 0 ? PUGIXML_TEXT("Infinity") : PUGIXML_TEXT("-Infinity"); - - case FP_ZERO: - return PUGIXML_TEXT("0"); - - default: - return 0; - } - #else - // fallback - const volatile double v = value; - - if (v == 0) return PUGIXML_TEXT("0"); - if (v != v) return PUGIXML_TEXT("NaN"); - if (v * 2 == v) return value > 0 ? PUGIXML_TEXT("Infinity") : PUGIXML_TEXT("-Infinity"); - return 0; - #endif - } - - PUGI_IMPL_FN bool convert_number_to_boolean(double value) - { - return (value != 0 && !is_nan(value)); - } - - PUGI_IMPL_FN void truncate_zeros(char* begin, char* end) - { - while (begin != end && end[-1] == '0') end--; - - *end = 0; - } - - // gets mantissa digits in the form of 0.xxxxx with 0. implied and the exponent -#if defined(PUGI_IMPL_MSVC_CRT_VERSION) && PUGI_IMPL_MSVC_CRT_VERSION >= 1400 - PUGI_IMPL_FN void convert_number_to_mantissa_exponent(double value, char (&buffer)[32], char** out_mantissa, int* out_exponent) - { - // get base values - int sign, exponent; - _ecvt_s(buffer, sizeof(buffer), value, DBL_DIG + 1, &exponent, &sign); - - // truncate redundant zeros - truncate_zeros(buffer, buffer + strlen(buffer)); - - // fill results - *out_mantissa = buffer; - *out_exponent = exponent; - } -#else - PUGI_IMPL_FN void convert_number_to_mantissa_exponent(double value, char (&buffer)[32], char** out_mantissa, int* out_exponent) - { - // get a scientific notation value with IEEE DBL_DIG decimals - PUGI_IMPL_SNPRINTF(buffer, "%.*e", DBL_DIG, value); - - // get the exponent (possibly negative) - char* exponent_string = strchr(buffer, 'e'); - assert(exponent_string); - - int exponent = atoi(exponent_string + 1); - - // extract mantissa string: skip sign - char* mantissa = buffer[0] == '-' ? buffer + 1 : buffer; - assert(mantissa[0] != '0' && (mantissa[1] == '.' || mantissa[1] == ',')); - - // divide mantissa by 10 to eliminate integer part - mantissa[1] = mantissa[0]; - mantissa++; - exponent++; - - // remove extra mantissa digits and zero-terminate mantissa - truncate_zeros(mantissa, exponent_string); - - // fill results - *out_mantissa = mantissa; - *out_exponent = exponent; - } -#endif - - PUGI_IMPL_FN xpath_string convert_number_to_string(double value, xpath_allocator* alloc) - { - // try special number conversion - const char_t* special = convert_number_to_string_special(value); - if (special) return xpath_string::from_const(special); - - // get mantissa + exponent form - char mantissa_buffer[32]; - - char* mantissa; - int exponent; - convert_number_to_mantissa_exponent(value, mantissa_buffer, &mantissa, &exponent); - - // allocate a buffer of suitable length for the number - size_t result_size = strlen(mantissa_buffer) + (exponent > 0 ? exponent : -exponent) + 4; - char_t* result = static_cast(alloc->allocate(sizeof(char_t) * result_size)); - if (!result) return xpath_string(); - - // make the number! - char_t* s = result; - - // sign - if (value < 0) *s++ = '-'; - - // integer part - if (exponent <= 0) - { - *s++ = '0'; - } - else - { - while (exponent > 0) - { - assert(*mantissa == 0 || static_cast(*mantissa - '0') <= 9); - *s++ = *mantissa ? *mantissa++ : '0'; - exponent--; - } - } - - // fractional part - if (*mantissa) - { - // decimal point - *s++ = '.'; - - // extra zeroes from negative exponent - while (exponent < 0) - { - *s++ = '0'; - exponent++; - } - - // extra mantissa digits - while (*mantissa) - { - assert(static_cast(*mantissa - '0') <= 9); - *s++ = *mantissa++; - } - } - - // zero-terminate - assert(s < result + result_size); - *s = 0; - - return xpath_string::from_heap_preallocated(result, s); - } - - PUGI_IMPL_FN bool check_string_to_number_format(const char_t* string) - { - // parse leading whitespace - while (PUGI_IMPL_IS_CHARTYPE(*string, ct_space)) ++string; - - // parse sign - if (*string == '-') ++string; - - if (!*string) return false; - - // if there is no integer part, there should be a decimal part with at least one digit - if (!PUGI_IMPL_IS_CHARTYPEX(string[0], ctx_digit) && (string[0] != '.' || !PUGI_IMPL_IS_CHARTYPEX(string[1], ctx_digit))) return false; - - // parse integer part - while (PUGI_IMPL_IS_CHARTYPEX(*string, ctx_digit)) ++string; - - // parse decimal part - if (*string == '.') - { - ++string; - - while (PUGI_IMPL_IS_CHARTYPEX(*string, ctx_digit)) ++string; - } - - // parse trailing whitespace - while (PUGI_IMPL_IS_CHARTYPE(*string, ct_space)) ++string; - - return *string == 0; - } - - PUGI_IMPL_FN double convert_string_to_number(const char_t* string) - { - // check string format - if (!check_string_to_number_format(string)) return gen_nan(); - - // parse string - #ifdef PUGIXML_WCHAR_MODE - return wcstod(string, 0); - #else - return strtod(string, 0); - #endif - } - - PUGI_IMPL_FN bool convert_string_to_number_scratch(char_t (&buffer)[32], const char_t* begin, const char_t* end, double* out_result) - { - size_t length = static_cast(end - begin); - char_t* scratch = buffer; - - if (length >= sizeof(buffer) / sizeof(buffer[0])) - { - // need to make dummy on-heap copy - scratch = static_cast(xml_memory::allocate((length + 1) * sizeof(char_t))); - if (!scratch) return false; - } - - // copy string to zero-terminated buffer and perform conversion - memcpy(scratch, begin, length * sizeof(char_t)); - scratch[length] = 0; - - *out_result = convert_string_to_number(scratch); - - // free dummy buffer - if (scratch != buffer) xml_memory::deallocate(scratch); - - return true; - } - - PUGI_IMPL_FN double round_nearest(double value) - { - return floor(value + 0.5); - } - - PUGI_IMPL_FN double round_nearest_nzero(double value) - { - // same as round_nearest, but returns -0 for [-0.5, -0] - // ceil is used to differentiate between +0 and -0 (we return -0 for [-0.5, -0] and +0 for +0) - return (value >= -0.5 && value <= 0) ? ceil(value) : floor(value + 0.5); - } - - PUGI_IMPL_FN const char_t* qualified_name(const xpath_node& node) - { - return node.attribute() ? node.attribute().name() : node.node().name(); - } - - PUGI_IMPL_FN const char_t* local_name(const xpath_node& node) - { - const char_t* name = qualified_name(node); - const char_t* p = find_char(name, ':'); - - return p ? p + 1 : name; - } - - struct namespace_uri_predicate - { - const char_t* prefix; - size_t prefix_length; - - namespace_uri_predicate(const char_t* name) - { - const char_t* pos = find_char(name, ':'); - - prefix = pos ? name : 0; - prefix_length = pos ? static_cast(pos - name) : 0; - } - - bool operator()(xml_attribute a) const - { - const char_t* name = a.name(); - - if (!starts_with(name, PUGIXML_TEXT("xmlns"))) return false; - - return prefix ? name[5] == ':' && strequalrange(name + 6, prefix, prefix_length) : name[5] == 0; - } - }; - - PUGI_IMPL_FN const char_t* namespace_uri(xml_node node) - { - namespace_uri_predicate pred = node.name(); - - xml_node p = node; - - while (p) - { - xml_attribute a = p.find_attribute(pred); - - if (a) return a.value(); - - p = p.parent(); - } - - return PUGIXML_TEXT(""); - } - - PUGI_IMPL_FN const char_t* namespace_uri(xml_attribute attr, xml_node parent) - { - namespace_uri_predicate pred = attr.name(); - - // Default namespace does not apply to attributes - if (!pred.prefix) return PUGIXML_TEXT(""); - - xml_node p = parent; - - while (p) - { - xml_attribute a = p.find_attribute(pred); - - if (a) return a.value(); - - p = p.parent(); - } - - return PUGIXML_TEXT(""); - } - - PUGI_IMPL_FN const char_t* namespace_uri(const xpath_node& node) - { - return node.attribute() ? namespace_uri(node.attribute(), node.parent()) : namespace_uri(node.node()); - } - - PUGI_IMPL_FN char_t* normalize_space(char_t* buffer) - { - char_t* write = buffer; - - for (char_t* it = buffer; *it; ) - { - char_t ch = *it++; - - if (PUGI_IMPL_IS_CHARTYPE(ch, ct_space)) - { - // replace whitespace sequence with single space - while (PUGI_IMPL_IS_CHARTYPE(*it, ct_space)) it++; - - // avoid leading spaces - if (write != buffer) *write++ = ' '; - } - else *write++ = ch; - } - - // remove trailing space - if (write != buffer && PUGI_IMPL_IS_CHARTYPE(write[-1], ct_space)) write--; - - // zero-terminate - *write = 0; - - return write; - } - - PUGI_IMPL_FN char_t* translate(char_t* buffer, const char_t* from, const char_t* to, size_t to_length) - { - char_t* write = buffer; - - while (*buffer) - { - PUGI_IMPL_DMC_VOLATILE char_t ch = *buffer++; - - const char_t* pos = find_char(from, ch); - - if (!pos) - *write++ = ch; // do not process - else if (static_cast(pos - from) < to_length) - *write++ = to[pos - from]; // replace - } - - // zero-terminate - *write = 0; - - return write; - } - - PUGI_IMPL_FN unsigned char* translate_table_generate(xpath_allocator* alloc, const char_t* from, const char_t* to) - { - unsigned char table[128] = {0}; - - while (*from) - { - unsigned int fc = static_cast(*from); - unsigned int tc = static_cast(*to); - - if (fc >= 128 || tc >= 128) - return 0; - - // code=128 means "skip character" - if (!table[fc]) - table[fc] = static_cast(tc ? tc : 128); - - from++; - if (tc) to++; - } - - for (int i = 0; i < 128; ++i) - if (!table[i]) - table[i] = static_cast(i); - - void* result = alloc->allocate(sizeof(table)); - if (!result) return 0; - - memcpy(result, table, sizeof(table)); - - return static_cast(result); - } - - PUGI_IMPL_FN char_t* translate_table(char_t* buffer, const unsigned char* table) - { - char_t* write = buffer; - - while (*buffer) - { - char_t ch = *buffer++; - unsigned int index = static_cast(ch); - - if (index < 128) - { - unsigned char code = table[index]; - - // code=128 means "skip character" (table size is 128 so 128 can be a special value) - // this code skips these characters without extra branches - *write = static_cast(code); - write += 1 - (code >> 7); - } - else - { - *write++ = ch; - } - } - - // zero-terminate - *write = 0; - - return write; - } - - inline bool is_xpath_attribute(const char_t* name) - { - return !(starts_with(name, PUGIXML_TEXT("xmlns")) && (name[5] == 0 || name[5] == ':')); - } - - struct xpath_variable_boolean: xpath_variable - { - xpath_variable_boolean(): xpath_variable(xpath_type_boolean), value(false) - { - } - - bool value; - char_t name[1]; - }; - - struct xpath_variable_number: xpath_variable - { - xpath_variable_number(): xpath_variable(xpath_type_number), value(0) - { - } - - double value; - char_t name[1]; - }; - - struct xpath_variable_string: xpath_variable - { - xpath_variable_string(): xpath_variable(xpath_type_string), value(0) - { - } - - ~xpath_variable_string() - { - if (value) xml_memory::deallocate(value); - } - - char_t* value; - char_t name[1]; - }; - - struct xpath_variable_node_set: xpath_variable - { - xpath_variable_node_set(): xpath_variable(xpath_type_node_set) - { - } - - xpath_node_set value; - char_t name[1]; - }; - - static const xpath_node_set dummy_node_set; - - PUGI_IMPL_FN PUGI_IMPL_UNSIGNED_OVERFLOW unsigned int hash_string(const char_t* str) - { - // Jenkins one-at-a-time hash (http://en.wikipedia.org/wiki/Jenkins_hash_function#one-at-a-time) - unsigned int result = 0; - - while (*str) - { - result += static_cast(*str++); - result += result << 10; - result ^= result >> 6; - } - - result += result << 3; - result ^= result >> 11; - result += result << 15; - - return result; - } - - template PUGI_IMPL_FN T* new_xpath_variable(const char_t* name) - { - size_t length = strlength(name); - if (length == 0) return 0; // empty variable names are invalid - - // $$ we can't use offsetof(T, name) because T is non-POD, so we just allocate additional length characters - void* memory = xml_memory::allocate(sizeof(T) + length * sizeof(char_t)); - if (!memory) return 0; - - T* result = new (memory) T(); - - memcpy(result->name, name, (length + 1) * sizeof(char_t)); - - return result; - } - - PUGI_IMPL_FN xpath_variable* new_xpath_variable(xpath_value_type type, const char_t* name) - { - switch (type) - { - case xpath_type_node_set: - return new_xpath_variable(name); - - case xpath_type_number: - return new_xpath_variable(name); - - case xpath_type_string: - return new_xpath_variable(name); - - case xpath_type_boolean: - return new_xpath_variable(name); - - default: - return 0; - } - } - - template PUGI_IMPL_FN void delete_xpath_variable(T* var) - { - var->~T(); - xml_memory::deallocate(var); - } - - PUGI_IMPL_FN void delete_xpath_variable(xpath_value_type type, xpath_variable* var) - { - switch (type) - { - case xpath_type_node_set: - delete_xpath_variable(static_cast(var)); - break; - - case xpath_type_number: - delete_xpath_variable(static_cast(var)); - break; - - case xpath_type_string: - delete_xpath_variable(static_cast(var)); - break; - - case xpath_type_boolean: - delete_xpath_variable(static_cast(var)); - break; - - default: - assert(false && "Invalid variable type"); // unreachable - } - } - - PUGI_IMPL_FN bool copy_xpath_variable(xpath_variable* lhs, const xpath_variable* rhs) - { - switch (rhs->type()) - { - case xpath_type_node_set: - return lhs->set(static_cast(rhs)->value); - - case xpath_type_number: - return lhs->set(static_cast(rhs)->value); - - case xpath_type_string: - return lhs->set(static_cast(rhs)->value); - - case xpath_type_boolean: - return lhs->set(static_cast(rhs)->value); - - default: - assert(false && "Invalid variable type"); // unreachable - return false; - } - } - - PUGI_IMPL_FN bool get_variable_scratch(char_t (&buffer)[32], xpath_variable_set* set, const char_t* begin, const char_t* end, xpath_variable** out_result) - { - size_t length = static_cast(end - begin); - char_t* scratch = buffer; - - if (length >= sizeof(buffer) / sizeof(buffer[0])) - { - // need to make dummy on-heap copy - scratch = static_cast(xml_memory::allocate((length + 1) * sizeof(char_t))); - if (!scratch) return false; - } - - // copy string to zero-terminated buffer and perform lookup - memcpy(scratch, begin, length * sizeof(char_t)); - scratch[length] = 0; - - *out_result = set->get(scratch); - - // free dummy buffer - if (scratch != buffer) xml_memory::deallocate(scratch); - - return true; - } -PUGI_IMPL_NS_END - -// Internal node set class -PUGI_IMPL_NS_BEGIN - PUGI_IMPL_FN xpath_node_set::type_t xpath_get_order(const xpath_node* begin, const xpath_node* end) - { - if (end - begin < 2) - return xpath_node_set::type_sorted; - - document_order_comparator cmp; - - bool first = cmp(begin[0], begin[1]); - - for (const xpath_node* it = begin + 1; it + 1 < end; ++it) - if (cmp(it[0], it[1]) != first) - return xpath_node_set::type_unsorted; - - return first ? xpath_node_set::type_sorted : xpath_node_set::type_sorted_reverse; - } - - PUGI_IMPL_FN xpath_node_set::type_t xpath_sort(xpath_node* begin, xpath_node* end, xpath_node_set::type_t type, bool rev) - { - xpath_node_set::type_t order = rev ? xpath_node_set::type_sorted_reverse : xpath_node_set::type_sorted; - - if (type == xpath_node_set::type_unsorted) - { - xpath_node_set::type_t sorted = xpath_get_order(begin, end); - - if (sorted == xpath_node_set::type_unsorted) - { - sort(begin, end, document_order_comparator()); - - type = xpath_node_set::type_sorted; - } - else - type = sorted; - } - - if (type != order) reverse(begin, end); - - return order; - } - - PUGI_IMPL_FN xpath_node xpath_first(const xpath_node* begin, const xpath_node* end, xpath_node_set::type_t type) - { - if (begin == end) return xpath_node(); - - switch (type) - { - case xpath_node_set::type_sorted: - return *begin; - - case xpath_node_set::type_sorted_reverse: - return *(end - 1); - - case xpath_node_set::type_unsorted: - return *min_element(begin, end, document_order_comparator()); - - default: - assert(false && "Invalid node set type"); // unreachable - return xpath_node(); - } - } - - class xpath_node_set_raw - { - xpath_node_set::type_t _type; - - xpath_node* _begin; - xpath_node* _end; - xpath_node* _eos; - - public: - xpath_node_set_raw(): _type(xpath_node_set::type_unsorted), _begin(0), _end(0), _eos(0) - { - } - - xpath_node* begin() const - { - return _begin; - } - - xpath_node* end() const - { - return _end; - } - - bool empty() const - { - return _begin == _end; - } - - size_t size() const - { - return static_cast(_end - _begin); - } - - xpath_node first() const - { - return xpath_first(_begin, _end, _type); - } - - void push_back_grow(const xpath_node& node, xpath_allocator* alloc); - - void push_back(const xpath_node& node, xpath_allocator* alloc) - { - if (_end != _eos) - *_end++ = node; - else - push_back_grow(node, alloc); - } - - void append(const xpath_node* begin_, const xpath_node* end_, xpath_allocator* alloc) - { - if (begin_ == end_) return; - - size_t size_ = static_cast(_end - _begin); - size_t capacity = static_cast(_eos - _begin); - size_t count = static_cast(end_ - begin_); - - if (size_ + count > capacity) - { - // reallocate the old array or allocate a new one - xpath_node* data = static_cast(alloc->reallocate(_begin, capacity * sizeof(xpath_node), (size_ + count) * sizeof(xpath_node))); - if (!data) return; - - // finalize - _begin = data; - _end = data + size_; - _eos = data + size_ + count; - } - - memcpy(_end, begin_, count * sizeof(xpath_node)); - _end += count; - } - - void sort_do() - { - _type = xpath_sort(_begin, _end, _type, false); - } - - void truncate(xpath_node* pos) - { - assert(_begin <= pos && pos <= _end); - - _end = pos; - } - - void remove_duplicates(xpath_allocator* alloc) - { - if (_type == xpath_node_set::type_unsorted && _end - _begin > 2) - { - xpath_allocator_capture cr(alloc); - - size_t size_ = static_cast(_end - _begin); - - size_t hash_size = 1; - while (hash_size < size_ + size_ / 2) hash_size *= 2; - - const void** hash_data = static_cast(alloc->allocate(hash_size * sizeof(void**))); - if (!hash_data) return; - - memset(hash_data, 0, hash_size * sizeof(const void**)); - - xpath_node* write = _begin; - - for (xpath_node* it = _begin; it != _end; ++it) - { - const void* attr = it->attribute().internal_object(); - const void* node = it->node().internal_object(); - const void* key = attr ? attr : node; - - if (key && hash_insert(hash_data, hash_size, key)) - { - *write++ = *it; - } - } - - _end = write; - } - else - { - _end = unique(_begin, _end); - } - } - - xpath_node_set::type_t type() const - { - return _type; - } - - void set_type(xpath_node_set::type_t value) - { - _type = value; - } - }; - - PUGI_IMPL_FN_NO_INLINE void xpath_node_set_raw::push_back_grow(const xpath_node& node, xpath_allocator* alloc) - { - size_t capacity = static_cast(_eos - _begin); - - // get new capacity (1.5x rule) - size_t new_capacity = capacity + capacity / 2 + 1; - - // reallocate the old array or allocate a new one - xpath_node* data = static_cast(alloc->reallocate(_begin, capacity * sizeof(xpath_node), new_capacity * sizeof(xpath_node))); - if (!data) return; - - // finalize - _begin = data; - _end = data + capacity; - _eos = data + new_capacity; - - // push - *_end++ = node; - } -PUGI_IMPL_NS_END - -PUGI_IMPL_NS_BEGIN - struct xpath_context - { - xpath_node n; - size_t position, size; - - xpath_context(const xpath_node& n_, size_t position_, size_t size_): n(n_), position(position_), size(size_) - { - } - }; - - enum lexeme_t - { - lex_none = 0, - lex_equal, - lex_not_equal, - lex_less, - lex_greater, - lex_less_or_equal, - lex_greater_or_equal, - lex_plus, - lex_minus, - lex_multiply, - lex_union, - lex_var_ref, - lex_open_brace, - lex_close_brace, - lex_quoted_string, - lex_number, - lex_slash, - lex_double_slash, - lex_open_square_brace, - lex_close_square_brace, - lex_string, - lex_comma, - lex_axis_attribute, - lex_dot, - lex_double_dot, - lex_double_colon, - lex_eof - }; - - struct xpath_lexer_string - { - const char_t* begin; - const char_t* end; - - xpath_lexer_string(): begin(0), end(0) - { - } - - bool operator==(const char_t* other) const - { - size_t length = static_cast(end - begin); - - return strequalrange(other, begin, length); - } - }; - - class xpath_lexer - { - const char_t* _cur; - const char_t* _cur_lexeme_pos; - xpath_lexer_string _cur_lexeme_contents; - - lexeme_t _cur_lexeme; - - public: - explicit xpath_lexer(const char_t* query): _cur(query) - { - next(); - } - - const char_t* state() const - { - return _cur; - } - - void next() - { - const char_t* cur = _cur; - - while (PUGI_IMPL_IS_CHARTYPE(*cur, ct_space)) ++cur; - - // save lexeme position for error reporting - _cur_lexeme_pos = cur; - - switch (*cur) - { - case 0: - _cur_lexeme = lex_eof; - break; - - case '>': - if (*(cur+1) == '=') - { - cur += 2; - _cur_lexeme = lex_greater_or_equal; - } - else - { - cur += 1; - _cur_lexeme = lex_greater; - } - break; - - case '<': - if (*(cur+1) == '=') - { - cur += 2; - _cur_lexeme = lex_less_or_equal; - } - else - { - cur += 1; - _cur_lexeme = lex_less; - } - break; - - case '!': - if (*(cur+1) == '=') - { - cur += 2; - _cur_lexeme = lex_not_equal; - } - else - { - _cur_lexeme = lex_none; - } - break; - - case '=': - cur += 1; - _cur_lexeme = lex_equal; - - break; - - case '+': - cur += 1; - _cur_lexeme = lex_plus; - - break; - - case '-': - cur += 1; - _cur_lexeme = lex_minus; - - break; - - case '*': - cur += 1; - _cur_lexeme = lex_multiply; - - break; - - case '|': - cur += 1; - _cur_lexeme = lex_union; - - break; - - case '$': - cur += 1; - - if (PUGI_IMPL_IS_CHARTYPEX(*cur, ctx_start_symbol)) - { - _cur_lexeme_contents.begin = cur; - - while (PUGI_IMPL_IS_CHARTYPEX(*cur, ctx_symbol)) cur++; - - if (cur[0] == ':' && PUGI_IMPL_IS_CHARTYPEX(cur[1], ctx_symbol)) // qname - { - cur++; // : - - while (PUGI_IMPL_IS_CHARTYPEX(*cur, ctx_symbol)) cur++; - } - - _cur_lexeme_contents.end = cur; - - _cur_lexeme = lex_var_ref; - } - else - { - _cur_lexeme = lex_none; - } - - break; - - case '(': - cur += 1; - _cur_lexeme = lex_open_brace; - - break; - - case ')': - cur += 1; - _cur_lexeme = lex_close_brace; - - break; - - case '[': - cur += 1; - _cur_lexeme = lex_open_square_brace; - - break; - - case ']': - cur += 1; - _cur_lexeme = lex_close_square_brace; - - break; - - case ',': - cur += 1; - _cur_lexeme = lex_comma; - - break; - - case '/': - if (*(cur+1) == '/') - { - cur += 2; - _cur_lexeme = lex_double_slash; - } - else - { - cur += 1; - _cur_lexeme = lex_slash; - } - break; - - case '.': - if (*(cur+1) == '.') - { - cur += 2; - _cur_lexeme = lex_double_dot; - } - else if (PUGI_IMPL_IS_CHARTYPEX(*(cur+1), ctx_digit)) - { - _cur_lexeme_contents.begin = cur; // . - - ++cur; - - while (PUGI_IMPL_IS_CHARTYPEX(*cur, ctx_digit)) cur++; - - _cur_lexeme_contents.end = cur; - - _cur_lexeme = lex_number; - } - else - { - cur += 1; - _cur_lexeme = lex_dot; - } - break; - - case '@': - cur += 1; - _cur_lexeme = lex_axis_attribute; - - break; - - case '"': - case '\'': - { - char_t terminator = *cur; - - ++cur; - - _cur_lexeme_contents.begin = cur; - while (*cur && *cur != terminator) cur++; - _cur_lexeme_contents.end = cur; - - if (!*cur) - _cur_lexeme = lex_none; - else - { - cur += 1; - _cur_lexeme = lex_quoted_string; - } - - break; - } - - case ':': - if (*(cur+1) == ':') - { - cur += 2; - _cur_lexeme = lex_double_colon; - } - else - { - _cur_lexeme = lex_none; - } - break; - - default: - if (PUGI_IMPL_IS_CHARTYPEX(*cur, ctx_digit)) - { - _cur_lexeme_contents.begin = cur; - - while (PUGI_IMPL_IS_CHARTYPEX(*cur, ctx_digit)) cur++; - - if (*cur == '.') - { - cur++; - - while (PUGI_IMPL_IS_CHARTYPEX(*cur, ctx_digit)) cur++; - } - - _cur_lexeme_contents.end = cur; - - _cur_lexeme = lex_number; - } - else if (PUGI_IMPL_IS_CHARTYPEX(*cur, ctx_start_symbol)) - { - _cur_lexeme_contents.begin = cur; - - while (PUGI_IMPL_IS_CHARTYPEX(*cur, ctx_symbol)) cur++; - - if (cur[0] == ':') - { - if (cur[1] == '*') // namespace test ncname:* - { - cur += 2; // :* - } - else if (PUGI_IMPL_IS_CHARTYPEX(cur[1], ctx_symbol)) // namespace test qname - { - cur++; // : - - while (PUGI_IMPL_IS_CHARTYPEX(*cur, ctx_symbol)) cur++; - } - } - - _cur_lexeme_contents.end = cur; - - _cur_lexeme = lex_string; - } - else - { - _cur_lexeme = lex_none; - } - } - - _cur = cur; - } - - lexeme_t current() const - { - return _cur_lexeme; - } - - const char_t* current_pos() const - { - return _cur_lexeme_pos; - } - - const xpath_lexer_string& contents() const - { - assert(_cur_lexeme == lex_var_ref || _cur_lexeme == lex_number || _cur_lexeme == lex_string || _cur_lexeme == lex_quoted_string); - - return _cur_lexeme_contents; - } - }; - - enum ast_type_t - { - ast_unknown, - ast_op_or, // left or right - ast_op_and, // left and right - ast_op_equal, // left = right - ast_op_not_equal, // left != right - ast_op_less, // left < right - ast_op_greater, // left > right - ast_op_less_or_equal, // left <= right - ast_op_greater_or_equal, // left >= right - ast_op_add, // left + right - ast_op_subtract, // left - right - ast_op_multiply, // left * right - ast_op_divide, // left / right - ast_op_mod, // left % right - ast_op_negate, // left - right - ast_op_union, // left | right - ast_predicate, // apply predicate to set; next points to next predicate - ast_filter, // select * from left where right - ast_string_constant, // string constant - ast_number_constant, // number constant - ast_variable, // variable - ast_func_last, // last() - ast_func_position, // position() - ast_func_count, // count(left) - ast_func_id, // id(left) - ast_func_local_name_0, // local-name() - ast_func_local_name_1, // local-name(left) - ast_func_namespace_uri_0, // namespace-uri() - ast_func_namespace_uri_1, // namespace-uri(left) - ast_func_name_0, // name() - ast_func_name_1, // name(left) - ast_func_string_0, // string() - ast_func_string_1, // string(left) - ast_func_concat, // concat(left, right, siblings) - ast_func_starts_with, // starts_with(left, right) - ast_func_contains, // contains(left, right) - ast_func_substring_before, // substring-before(left, right) - ast_func_substring_after, // substring-after(left, right) - ast_func_substring_2, // substring(left, right) - ast_func_substring_3, // substring(left, right, third) - ast_func_string_length_0, // string-length() - ast_func_string_length_1, // string-length(left) - ast_func_normalize_space_0, // normalize-space() - ast_func_normalize_space_1, // normalize-space(left) - ast_func_translate, // translate(left, right, third) - ast_func_boolean, // boolean(left) - ast_func_not, // not(left) - ast_func_true, // true() - ast_func_false, // false() - ast_func_lang, // lang(left) - ast_func_number_0, // number() - ast_func_number_1, // number(left) - ast_func_sum, // sum(left) - ast_func_floor, // floor(left) - ast_func_ceiling, // ceiling(left) - ast_func_round, // round(left) - ast_step, // process set left with step - ast_step_root, // select root node - - ast_opt_translate_table, // translate(left, right, third) where right/third are constants - ast_opt_compare_attribute // @name = 'string' - }; - - enum axis_t - { - axis_ancestor, - axis_ancestor_or_self, - axis_attribute, - axis_child, - axis_descendant, - axis_descendant_or_self, - axis_following, - axis_following_sibling, - axis_namespace, - axis_parent, - axis_preceding, - axis_preceding_sibling, - axis_self - }; - - enum nodetest_t - { - nodetest_none, - nodetest_name, - nodetest_type_node, - nodetest_type_comment, - nodetest_type_pi, - nodetest_type_text, - nodetest_pi, - nodetest_all, - nodetest_all_in_namespace - }; - - enum predicate_t - { - predicate_default, - predicate_posinv, - predicate_constant, - predicate_constant_one - }; - - enum nodeset_eval_t - { - nodeset_eval_all, - nodeset_eval_any, - nodeset_eval_first - }; - - template struct axis_to_type - { - static const axis_t axis; - }; - - template const axis_t axis_to_type::axis = N; - - class xpath_ast_node - { - private: - // node type - char _type; - char _rettype; - - // for ast_step - char _axis; - - // for ast_step/ast_predicate/ast_filter - char _test; - - // tree node structure - xpath_ast_node* _left; - xpath_ast_node* _right; - xpath_ast_node* _next; - - union - { - // value for ast_string_constant - const char_t* string; - // value for ast_number_constant - double number; - // variable for ast_variable - xpath_variable* variable; - // node test for ast_step (node name/namespace/node type/pi target) - const char_t* nodetest; - // table for ast_opt_translate_table - const unsigned char* table; - } _data; - - xpath_ast_node(const xpath_ast_node&); - xpath_ast_node& operator=(const xpath_ast_node&); - - template static bool compare_eq(xpath_ast_node* lhs, xpath_ast_node* rhs, const xpath_context& c, const xpath_stack& stack, const Comp& comp) - { - xpath_value_type lt = lhs->rettype(), rt = rhs->rettype(); - - if (lt != xpath_type_node_set && rt != xpath_type_node_set) - { - if (lt == xpath_type_boolean || rt == xpath_type_boolean) - return comp(lhs->eval_boolean(c, stack), rhs->eval_boolean(c, stack)); - else if (lt == xpath_type_number || rt == xpath_type_number) - return comp(lhs->eval_number(c, stack), rhs->eval_number(c, stack)); - else if (lt == xpath_type_string || rt == xpath_type_string) - { - xpath_allocator_capture cr(stack.result); - - xpath_string ls = lhs->eval_string(c, stack); - xpath_string rs = rhs->eval_string(c, stack); - - return comp(ls, rs); - } - } - else if (lt == xpath_type_node_set && rt == xpath_type_node_set) - { - xpath_allocator_capture cr(stack.result); - - xpath_node_set_raw ls = lhs->eval_node_set(c, stack, nodeset_eval_all); - xpath_node_set_raw rs = rhs->eval_node_set(c, stack, nodeset_eval_all); - - for (const xpath_node* li = ls.begin(); li != ls.end(); ++li) - for (const xpath_node* ri = rs.begin(); ri != rs.end(); ++ri) - { - xpath_allocator_capture cri(stack.result); - - if (comp(string_value(*li, stack.result), string_value(*ri, stack.result))) - return true; - } - - return false; - } - else - { - if (lt == xpath_type_node_set) - { - swap(lhs, rhs); - swap(lt, rt); - } - - if (lt == xpath_type_boolean) - return comp(lhs->eval_boolean(c, stack), rhs->eval_boolean(c, stack)); - else if (lt == xpath_type_number) - { - xpath_allocator_capture cr(stack.result); - - double l = lhs->eval_number(c, stack); - xpath_node_set_raw rs = rhs->eval_node_set(c, stack, nodeset_eval_all); - - for (const xpath_node* ri = rs.begin(); ri != rs.end(); ++ri) - { - xpath_allocator_capture cri(stack.result); - - if (comp(l, convert_string_to_number(string_value(*ri, stack.result).c_str()))) - return true; - } - - return false; - } - else if (lt == xpath_type_string) - { - xpath_allocator_capture cr(stack.result); - - xpath_string l = lhs->eval_string(c, stack); - xpath_node_set_raw rs = rhs->eval_node_set(c, stack, nodeset_eval_all); - - for (const xpath_node* ri = rs.begin(); ri != rs.end(); ++ri) - { - xpath_allocator_capture cri(stack.result); - - if (comp(l, string_value(*ri, stack.result))) - return true; - } - - return false; - } - } - - assert(false && "Wrong types"); // unreachable - return false; - } - - static bool eval_once(xpath_node_set::type_t type, nodeset_eval_t eval) - { - return type == xpath_node_set::type_sorted ? eval != nodeset_eval_all : eval == nodeset_eval_any; - } - - template static bool compare_rel(xpath_ast_node* lhs, xpath_ast_node* rhs, const xpath_context& c, const xpath_stack& stack, const Comp& comp) - { - xpath_value_type lt = lhs->rettype(), rt = rhs->rettype(); - - if (lt != xpath_type_node_set && rt != xpath_type_node_set) - return comp(lhs->eval_number(c, stack), rhs->eval_number(c, stack)); - else if (lt == xpath_type_node_set && rt == xpath_type_node_set) - { - xpath_allocator_capture cr(stack.result); - - xpath_node_set_raw ls = lhs->eval_node_set(c, stack, nodeset_eval_all); - xpath_node_set_raw rs = rhs->eval_node_set(c, stack, nodeset_eval_all); - - for (const xpath_node* li = ls.begin(); li != ls.end(); ++li) - { - xpath_allocator_capture cri(stack.result); - - double l = convert_string_to_number(string_value(*li, stack.result).c_str()); - - for (const xpath_node* ri = rs.begin(); ri != rs.end(); ++ri) - { - xpath_allocator_capture crii(stack.result); - - if (comp(l, convert_string_to_number(string_value(*ri, stack.result).c_str()))) - return true; - } - } - - return false; - } - else if (lt != xpath_type_node_set && rt == xpath_type_node_set) - { - xpath_allocator_capture cr(stack.result); - - double l = lhs->eval_number(c, stack); - xpath_node_set_raw rs = rhs->eval_node_set(c, stack, nodeset_eval_all); - - for (const xpath_node* ri = rs.begin(); ri != rs.end(); ++ri) - { - xpath_allocator_capture cri(stack.result); - - if (comp(l, convert_string_to_number(string_value(*ri, stack.result).c_str()))) - return true; - } - - return false; - } - else if (lt == xpath_type_node_set && rt != xpath_type_node_set) - { - xpath_allocator_capture cr(stack.result); - - xpath_node_set_raw ls = lhs->eval_node_set(c, stack, nodeset_eval_all); - double r = rhs->eval_number(c, stack); - - for (const xpath_node* li = ls.begin(); li != ls.end(); ++li) - { - xpath_allocator_capture cri(stack.result); - - if (comp(convert_string_to_number(string_value(*li, stack.result).c_str()), r)) - return true; - } - - return false; - } - else - { - assert(false && "Wrong types"); // unreachable - return false; - } - } - - static void apply_predicate_boolean(xpath_node_set_raw& ns, size_t first, xpath_ast_node* expr, const xpath_stack& stack, bool once) - { - assert(ns.size() >= first); - assert(expr->rettype() != xpath_type_number); - - size_t i = 1; - size_t size = ns.size() - first; - - xpath_node* last = ns.begin() + first; - - // remove_if... or well, sort of - for (xpath_node* it = last; it != ns.end(); ++it, ++i) - { - xpath_context c(*it, i, size); - - if (expr->eval_boolean(c, stack)) - { - *last++ = *it; - - if (once) break; - } - } - - ns.truncate(last); - } - - static void apply_predicate_number(xpath_node_set_raw& ns, size_t first, xpath_ast_node* expr, const xpath_stack& stack, bool once) - { - assert(ns.size() >= first); - assert(expr->rettype() == xpath_type_number); - - size_t i = 1; - size_t size = ns.size() - first; - - xpath_node* last = ns.begin() + first; - - // remove_if... or well, sort of - for (xpath_node* it = last; it != ns.end(); ++it, ++i) - { - xpath_context c(*it, i, size); - - if (expr->eval_number(c, stack) == static_cast(i)) - { - *last++ = *it; - - if (once) break; - } - } - - ns.truncate(last); - } - - static void apply_predicate_number_const(xpath_node_set_raw& ns, size_t first, xpath_ast_node* expr, const xpath_stack& stack) - { - assert(ns.size() >= first); - assert(expr->rettype() == xpath_type_number); - - size_t size = ns.size() - first; - - xpath_node* last = ns.begin() + first; - - xpath_node cn; - xpath_context c(cn, 1, size); - - double er = expr->eval_number(c, stack); - - if (er >= 1.0 && er <= static_cast(size)) - { - size_t eri = static_cast(er); - - if (er == static_cast(eri)) - { - xpath_node r = last[eri - 1]; - - *last++ = r; - } - } - - ns.truncate(last); - } - - void apply_predicate(xpath_node_set_raw& ns, size_t first, const xpath_stack& stack, bool once) - { - if (ns.size() == first) return; - - assert(_type == ast_filter || _type == ast_predicate); - - if (_test == predicate_constant || _test == predicate_constant_one) - apply_predicate_number_const(ns, first, _right, stack); - else if (_right->rettype() == xpath_type_number) - apply_predicate_number(ns, first, _right, stack, once); - else - apply_predicate_boolean(ns, first, _right, stack, once); - } - - void apply_predicates(xpath_node_set_raw& ns, size_t first, const xpath_stack& stack, nodeset_eval_t eval) - { - if (ns.size() == first) return; - - bool last_once = eval_once(ns.type(), eval); - - for (xpath_ast_node* pred = _right; pred; pred = pred->_next) - pred->apply_predicate(ns, first, stack, !pred->_next && last_once); - } - - bool step_push(xpath_node_set_raw& ns, xml_attribute_struct* a, xml_node_struct* parent, xpath_allocator* alloc) - { - assert(a); - - const char_t* name = a->name ? a->name + 0 : PUGIXML_TEXT(""); - - switch (_test) - { - case nodetest_name: - if (strequal(name, _data.nodetest) && is_xpath_attribute(name)) - { - ns.push_back(xpath_node(xml_attribute(a), xml_node(parent)), alloc); - return true; - } - break; - - case nodetest_type_node: - case nodetest_all: - if (is_xpath_attribute(name)) - { - ns.push_back(xpath_node(xml_attribute(a), xml_node(parent)), alloc); - return true; - } - break; - - case nodetest_all_in_namespace: - if (starts_with(name, _data.nodetest) && is_xpath_attribute(name)) - { - ns.push_back(xpath_node(xml_attribute(a), xml_node(parent)), alloc); - return true; - } - break; - - default: - ; - } - - return false; - } - - bool step_push(xpath_node_set_raw& ns, xml_node_struct* n, xpath_allocator* alloc) - { - assert(n); - - xml_node_type type = PUGI_IMPL_NODETYPE(n); - - switch (_test) - { - case nodetest_name: - if (type == node_element && n->name && strequal(n->name, _data.nodetest)) - { - ns.push_back(xml_node(n), alloc); - return true; - } - break; - - case nodetest_type_node: - ns.push_back(xml_node(n), alloc); - return true; - - case nodetest_type_comment: - if (type == node_comment) - { - ns.push_back(xml_node(n), alloc); - return true; - } - break; - - case nodetest_type_text: - if (type == node_pcdata || type == node_cdata) - { - ns.push_back(xml_node(n), alloc); - return true; - } - break; - - case nodetest_type_pi: - if (type == node_pi) - { - ns.push_back(xml_node(n), alloc); - return true; - } - break; - - case nodetest_pi: - if (type == node_pi && n->name && strequal(n->name, _data.nodetest)) - { - ns.push_back(xml_node(n), alloc); - return true; - } - break; - - case nodetest_all: - if (type == node_element) - { - ns.push_back(xml_node(n), alloc); - return true; - } - break; - - case nodetest_all_in_namespace: - if (type == node_element && n->name && starts_with(n->name, _data.nodetest)) - { - ns.push_back(xml_node(n), alloc); - return true; - } - break; - - default: - assert(false && "Unknown axis"); // unreachable - } - - return false; - } - - template void step_fill(xpath_node_set_raw& ns, xml_node_struct* n, xpath_allocator* alloc, bool once, T) - { - const axis_t axis = T::axis; - - switch (axis) - { - case axis_attribute: - { - for (xml_attribute_struct* a = n->first_attribute; a; a = a->next_attribute) - if (step_push(ns, a, n, alloc) & once) - return; - - break; - } - - case axis_child: - { - for (xml_node_struct* c = n->first_child; c; c = c->next_sibling) - if (step_push(ns, c, alloc) & once) - return; - - break; - } - - case axis_descendant: - case axis_descendant_or_self: - { - if (axis == axis_descendant_or_self) - if (step_push(ns, n, alloc) & once) - return; - - xml_node_struct* cur = n->first_child; - - while (cur) - { - if (step_push(ns, cur, alloc) & once) - return; - - if (cur->first_child) - cur = cur->first_child; - else - { - while (!cur->next_sibling) - { - cur = cur->parent; - - if (cur == n) return; - } - - cur = cur->next_sibling; - } - } - - break; - } - - case axis_following_sibling: - { - for (xml_node_struct* c = n->next_sibling; c; c = c->next_sibling) - if (step_push(ns, c, alloc) & once) - return; - - break; - } - - case axis_preceding_sibling: - { - for (xml_node_struct* c = n->prev_sibling_c; c->next_sibling; c = c->prev_sibling_c) - if (step_push(ns, c, alloc) & once) - return; - - break; - } - - case axis_following: - { - xml_node_struct* cur = n; - - // exit from this node so that we don't include descendants - while (!cur->next_sibling) - { - cur = cur->parent; - - if (!cur) return; - } - - cur = cur->next_sibling; - - while (cur) - { - if (step_push(ns, cur, alloc) & once) - return; - - if (cur->first_child) - cur = cur->first_child; - else - { - while (!cur->next_sibling) - { - cur = cur->parent; - - if (!cur) return; - } - - cur = cur->next_sibling; - } - } - - break; - } - - case axis_preceding: - { - xml_node_struct* cur = n; - - // exit from this node so that we don't include descendants - while (!cur->prev_sibling_c->next_sibling) - { - cur = cur->parent; - - if (!cur) return; - } - - cur = cur->prev_sibling_c; - - while (cur) - { - if (cur->first_child) - cur = cur->first_child->prev_sibling_c; - else - { - // leaf node, can't be ancestor - if (step_push(ns, cur, alloc) & once) - return; - - while (!cur->prev_sibling_c->next_sibling) - { - cur = cur->parent; - - if (!cur) return; - - if (!node_is_ancestor(cur, n)) - if (step_push(ns, cur, alloc) & once) - return; - } - - cur = cur->prev_sibling_c; - } - } - - break; - } - - case axis_ancestor: - case axis_ancestor_or_self: - { - if (axis == axis_ancestor_or_self) - if (step_push(ns, n, alloc) & once) - return; - - xml_node_struct* cur = n->parent; - - while (cur) - { - if (step_push(ns, cur, alloc) & once) - return; - - cur = cur->parent; - } - - break; - } - - case axis_self: - { - step_push(ns, n, alloc); - - break; - } - - case axis_parent: - { - if (n->parent) - step_push(ns, n->parent, alloc); - - break; - } - - default: - assert(false && "Unimplemented axis"); // unreachable - } - } - - template void step_fill(xpath_node_set_raw& ns, xml_attribute_struct* a, xml_node_struct* p, xpath_allocator* alloc, bool once, T v) - { - const axis_t axis = T::axis; - - switch (axis) - { - case axis_ancestor: - case axis_ancestor_or_self: - { - if (axis == axis_ancestor_or_self && _test == nodetest_type_node) // reject attributes based on principal node type test - if (step_push(ns, a, p, alloc) & once) - return; - - xml_node_struct* cur = p; - - while (cur) - { - if (step_push(ns, cur, alloc) & once) - return; - - cur = cur->parent; - } - - break; - } - - case axis_descendant_or_self: - case axis_self: - { - if (_test == nodetest_type_node) // reject attributes based on principal node type test - step_push(ns, a, p, alloc); - - break; - } - - case axis_following: - { - xml_node_struct* cur = p; - - while (cur) - { - if (cur->first_child) - cur = cur->first_child; - else - { - while (!cur->next_sibling) - { - cur = cur->parent; - - if (!cur) return; - } - - cur = cur->next_sibling; - } - - if (step_push(ns, cur, alloc) & once) - return; - } - - break; - } - - case axis_parent: - { - step_push(ns, p, alloc); - - break; - } - - case axis_preceding: - { - // preceding:: axis does not include attribute nodes and attribute ancestors (they are the same as parent's ancestors), so we can reuse node preceding - step_fill(ns, p, alloc, once, v); - break; - } - - default: - assert(false && "Unimplemented axis"); // unreachable - } - } - - template void step_fill(xpath_node_set_raw& ns, const xpath_node& xn, xpath_allocator* alloc, bool once, T v) - { - const axis_t axis = T::axis; - const bool axis_has_attributes = (axis == axis_ancestor || axis == axis_ancestor_or_self || axis == axis_descendant_or_self || axis == axis_following || axis == axis_parent || axis == axis_preceding || axis == axis_self); - - if (xn.node()) - step_fill(ns, xn.node().internal_object(), alloc, once, v); - else if (axis_has_attributes && xn.attribute() && xn.parent()) - step_fill(ns, xn.attribute().internal_object(), xn.parent().internal_object(), alloc, once, v); - } - - template xpath_node_set_raw step_do(const xpath_context& c, const xpath_stack& stack, nodeset_eval_t eval, T v) - { - const axis_t axis = T::axis; - const bool axis_reverse = (axis == axis_ancestor || axis == axis_ancestor_or_self || axis == axis_preceding || axis == axis_preceding_sibling); - const xpath_node_set::type_t axis_type = axis_reverse ? xpath_node_set::type_sorted_reverse : xpath_node_set::type_sorted; - - bool once = - (axis == axis_attribute && _test == nodetest_name) || - (!_right && eval_once(axis_type, eval)) || - // coverity[mixed_enums] - (_right && !_right->_next && _right->_test == predicate_constant_one); - - xpath_node_set_raw ns; - ns.set_type(axis_type); - - if (_left) - { - xpath_node_set_raw s = _left->eval_node_set(c, stack, nodeset_eval_all); - - // self axis preserves the original order - if (axis == axis_self) ns.set_type(s.type()); - - for (const xpath_node* it = s.begin(); it != s.end(); ++it) - { - size_t size = ns.size(); - - // in general, all axes generate elements in a particular order, but there is no order guarantee if axis is applied to two nodes - if (axis != axis_self && size != 0) ns.set_type(xpath_node_set::type_unsorted); - - step_fill(ns, *it, stack.result, once, v); - if (_right) apply_predicates(ns, size, stack, eval); - } - } - else - { - step_fill(ns, c.n, stack.result, once, v); - if (_right) apply_predicates(ns, 0, stack, eval); - } - - // child, attribute and self axes always generate unique set of nodes - // for other axis, if the set stayed sorted, it stayed unique because the traversal algorithms do not visit the same node twice - if (axis != axis_child && axis != axis_attribute && axis != axis_self && ns.type() == xpath_node_set::type_unsorted) - ns.remove_duplicates(stack.temp); - - return ns; - } - - public: - xpath_ast_node(ast_type_t type, xpath_value_type rettype_, const char_t* value): - _type(static_cast(type)), _rettype(static_cast(rettype_)), _axis(0), _test(0), _left(0), _right(0), _next(0) - { - assert(type == ast_string_constant); - _data.string = value; - } - - xpath_ast_node(ast_type_t type, xpath_value_type rettype_, double value): - _type(static_cast(type)), _rettype(static_cast(rettype_)), _axis(0), _test(0), _left(0), _right(0), _next(0) - { - assert(type == ast_number_constant); - _data.number = value; - } - - xpath_ast_node(ast_type_t type, xpath_value_type rettype_, xpath_variable* value): - _type(static_cast(type)), _rettype(static_cast(rettype_)), _axis(0), _test(0), _left(0), _right(0), _next(0) - { - assert(type == ast_variable); - _data.variable = value; - } - - xpath_ast_node(ast_type_t type, xpath_value_type rettype_, xpath_ast_node* left = 0, xpath_ast_node* right = 0): - _type(static_cast(type)), _rettype(static_cast(rettype_)), _axis(0), _test(0), _left(left), _right(right), _next(0) - { - } - - xpath_ast_node(ast_type_t type, xpath_ast_node* left, axis_t axis, nodetest_t test, const char_t* contents): - _type(static_cast(type)), _rettype(xpath_type_node_set), _axis(static_cast(axis)), _test(static_cast(test)), _left(left), _right(0), _next(0) - { - assert(type == ast_step); - _data.nodetest = contents; - } - - xpath_ast_node(ast_type_t type, xpath_ast_node* left, xpath_ast_node* right, predicate_t test): - _type(static_cast(type)), _rettype(xpath_type_node_set), _axis(0), _test(static_cast(test)), _left(left), _right(right), _next(0) - { - assert(type == ast_filter || type == ast_predicate); - } - - void set_next(xpath_ast_node* value) - { - _next = value; - } - - void set_right(xpath_ast_node* value) - { - _right = value; - } - - bool eval_boolean(const xpath_context& c, const xpath_stack& stack) - { - switch (_type) - { - case ast_op_or: - return _left->eval_boolean(c, stack) || _right->eval_boolean(c, stack); - - case ast_op_and: - return _left->eval_boolean(c, stack) && _right->eval_boolean(c, stack); - - case ast_op_equal: - return compare_eq(_left, _right, c, stack, equal_to()); - - case ast_op_not_equal: - return compare_eq(_left, _right, c, stack, not_equal_to()); - - case ast_op_less: - return compare_rel(_left, _right, c, stack, less()); - - case ast_op_greater: - return compare_rel(_right, _left, c, stack, less()); - - case ast_op_less_or_equal: - return compare_rel(_left, _right, c, stack, less_equal()); - - case ast_op_greater_or_equal: - return compare_rel(_right, _left, c, stack, less_equal()); - - case ast_func_starts_with: - { - xpath_allocator_capture cr(stack.result); - - xpath_string lr = _left->eval_string(c, stack); - xpath_string rr = _right->eval_string(c, stack); - - return starts_with(lr.c_str(), rr.c_str()); - } - - case ast_func_contains: - { - xpath_allocator_capture cr(stack.result); - - xpath_string lr = _left->eval_string(c, stack); - xpath_string rr = _right->eval_string(c, stack); - - return find_substring(lr.c_str(), rr.c_str()) != 0; - } - - case ast_func_boolean: - return _left->eval_boolean(c, stack); - - case ast_func_not: - return !_left->eval_boolean(c, stack); - - case ast_func_true: - return true; - - case ast_func_false: - return false; - - case ast_func_lang: - { - if (c.n.attribute()) return false; - - xpath_allocator_capture cr(stack.result); - - xpath_string lang = _left->eval_string(c, stack); - - for (xml_node n = c.n.node(); n; n = n.parent()) - { - xml_attribute a = n.attribute(PUGIXML_TEXT("xml:lang")); - - if (a) - { - const char_t* value = a.value(); - - // strnicmp / strncasecmp is not portable - for (const char_t* lit = lang.c_str(); *lit; ++lit) - { - if (tolower_ascii(*lit) != tolower_ascii(*value)) return false; - ++value; - } - - return *value == 0 || *value == '-'; - } - } - - return false; - } - - case ast_opt_compare_attribute: - { - const char_t* value = (_right->_type == ast_string_constant) ? _right->_data.string : _right->_data.variable->get_string(); - - xml_attribute attr = c.n.node().attribute(_left->_data.nodetest); - - return attr && strequal(attr.value(), value) && is_xpath_attribute(attr.name()); - } - - case ast_variable: - { - assert(_rettype == _data.variable->type()); - - if (_rettype == xpath_type_boolean) - return _data.variable->get_boolean(); - - // variable needs to be converted to the correct type, this is handled by the fallthrough block below - break; - } - - default: - ; - } - - // none of the ast types that return the value directly matched, we need to perform type conversion - switch (_rettype) - { - case xpath_type_number: - return convert_number_to_boolean(eval_number(c, stack)); - - case xpath_type_string: - { - xpath_allocator_capture cr(stack.result); - - return !eval_string(c, stack).empty(); - } - - case xpath_type_node_set: - { - xpath_allocator_capture cr(stack.result); - - return !eval_node_set(c, stack, nodeset_eval_any).empty(); - } - - default: - assert(false && "Wrong expression for return type boolean"); // unreachable - return false; - } - } - - double eval_number(const xpath_context& c, const xpath_stack& stack) - { - switch (_type) - { - case ast_op_add: - return _left->eval_number(c, stack) + _right->eval_number(c, stack); - - case ast_op_subtract: - return _left->eval_number(c, stack) - _right->eval_number(c, stack); - - case ast_op_multiply: - return _left->eval_number(c, stack) * _right->eval_number(c, stack); - - case ast_op_divide: - return _left->eval_number(c, stack) / _right->eval_number(c, stack); - - case ast_op_mod: - return fmod(_left->eval_number(c, stack), _right->eval_number(c, stack)); - - case ast_op_negate: - return -_left->eval_number(c, stack); - - case ast_number_constant: - return _data.number; - - case ast_func_last: - return static_cast(c.size); - - case ast_func_position: - return static_cast(c.position); - - case ast_func_count: - { - xpath_allocator_capture cr(stack.result); - - return static_cast(_left->eval_node_set(c, stack, nodeset_eval_all).size()); - } - - case ast_func_string_length_0: - { - xpath_allocator_capture cr(stack.result); - - return static_cast(string_value(c.n, stack.result).length()); - } - - case ast_func_string_length_1: - { - xpath_allocator_capture cr(stack.result); - - return static_cast(_left->eval_string(c, stack).length()); - } - - case ast_func_number_0: - { - xpath_allocator_capture cr(stack.result); - - return convert_string_to_number(string_value(c.n, stack.result).c_str()); - } - - case ast_func_number_1: - return _left->eval_number(c, stack); - - case ast_func_sum: - { - xpath_allocator_capture cr(stack.result); - - double r = 0; - - xpath_node_set_raw ns = _left->eval_node_set(c, stack, nodeset_eval_all); - - for (const xpath_node* it = ns.begin(); it != ns.end(); ++it) - { - xpath_allocator_capture cri(stack.result); - - r += convert_string_to_number(string_value(*it, stack.result).c_str()); - } - - return r; - } - - case ast_func_floor: - { - double r = _left->eval_number(c, stack); - - return r == r ? floor(r) : r; - } - - case ast_func_ceiling: - { - double r = _left->eval_number(c, stack); - - return r == r ? ceil(r) : r; - } - - case ast_func_round: - return round_nearest_nzero(_left->eval_number(c, stack)); - - case ast_variable: - { - assert(_rettype == _data.variable->type()); - - if (_rettype == xpath_type_number) - return _data.variable->get_number(); - - // variable needs to be converted to the correct type, this is handled by the fallthrough block below - break; - } - - default: - ; - } - - // none of the ast types that return the value directly matched, we need to perform type conversion - switch (_rettype) - { - case xpath_type_boolean: - return eval_boolean(c, stack) ? 1 : 0; - - case xpath_type_string: - { - xpath_allocator_capture cr(stack.result); - - return convert_string_to_number(eval_string(c, stack).c_str()); - } - - case xpath_type_node_set: - { - xpath_allocator_capture cr(stack.result); - - return convert_string_to_number(eval_string(c, stack).c_str()); - } - - default: - assert(false && "Wrong expression for return type number"); // unreachable - return 0; - } - } - - xpath_string eval_string_concat(const xpath_context& c, const xpath_stack& stack) - { - assert(_type == ast_func_concat); - - xpath_allocator_capture ct(stack.temp); - - // count the string number - size_t count = 1; - for (xpath_ast_node* nc = _right; nc; nc = nc->_next) count++; - - // allocate a buffer for temporary string objects - xpath_string* buffer = static_cast(stack.temp->allocate(count * sizeof(xpath_string))); - if (!buffer) return xpath_string(); - - // evaluate all strings to temporary stack - xpath_stack swapped_stack = {stack.temp, stack.result}; - - buffer[0] = _left->eval_string(c, swapped_stack); - - size_t pos = 1; - for (xpath_ast_node* n = _right; n; n = n->_next, ++pos) buffer[pos] = n->eval_string(c, swapped_stack); - assert(pos == count); - - // get total length - size_t length = 0; - for (size_t i = 0; i < count; ++i) length += buffer[i].length(); - - // create final string - char_t* result = static_cast(stack.result->allocate((length + 1) * sizeof(char_t))); - if (!result) return xpath_string(); - - char_t* ri = result; - - for (size_t j = 0; j < count; ++j) - for (const char_t* bi = buffer[j].c_str(); *bi; ++bi) - *ri++ = *bi; - - *ri = 0; - - return xpath_string::from_heap_preallocated(result, ri); - } - - xpath_string eval_string(const xpath_context& c, const xpath_stack& stack) - { - switch (_type) - { - case ast_string_constant: - return xpath_string::from_const(_data.string); - - case ast_func_local_name_0: - { - xpath_node na = c.n; - - return xpath_string::from_const(local_name(na)); - } - - case ast_func_local_name_1: - { - xpath_allocator_capture cr(stack.result); - - xpath_node_set_raw ns = _left->eval_node_set(c, stack, nodeset_eval_first); - xpath_node na = ns.first(); - - return xpath_string::from_const(local_name(na)); - } - - case ast_func_name_0: - { - xpath_node na = c.n; - - return xpath_string::from_const(qualified_name(na)); - } - - case ast_func_name_1: - { - xpath_allocator_capture cr(stack.result); - - xpath_node_set_raw ns = _left->eval_node_set(c, stack, nodeset_eval_first); - xpath_node na = ns.first(); - - return xpath_string::from_const(qualified_name(na)); - } - - case ast_func_namespace_uri_0: - { - xpath_node na = c.n; - - return xpath_string::from_const(namespace_uri(na)); - } - - case ast_func_namespace_uri_1: - { - xpath_allocator_capture cr(stack.result); - - xpath_node_set_raw ns = _left->eval_node_set(c, stack, nodeset_eval_first); - xpath_node na = ns.first(); - - return xpath_string::from_const(namespace_uri(na)); - } - - case ast_func_string_0: - return string_value(c.n, stack.result); - - case ast_func_string_1: - return _left->eval_string(c, stack); - - case ast_func_concat: - return eval_string_concat(c, stack); - - case ast_func_substring_before: - { - xpath_allocator_capture cr(stack.temp); - - xpath_stack swapped_stack = {stack.temp, stack.result}; - - xpath_string s = _left->eval_string(c, swapped_stack); - xpath_string p = _right->eval_string(c, swapped_stack); - - const char_t* pos = find_substring(s.c_str(), p.c_str()); - - return pos ? xpath_string::from_heap(s.c_str(), pos, stack.result) : xpath_string(); - } - - case ast_func_substring_after: - { - xpath_allocator_capture cr(stack.temp); - - xpath_stack swapped_stack = {stack.temp, stack.result}; - - xpath_string s = _left->eval_string(c, swapped_stack); - xpath_string p = _right->eval_string(c, swapped_stack); - - const char_t* pos = find_substring(s.c_str(), p.c_str()); - if (!pos) return xpath_string(); - - const char_t* rbegin = pos + p.length(); - const char_t* rend = s.c_str() + s.length(); - - return s.uses_heap() ? xpath_string::from_heap(rbegin, rend, stack.result) : xpath_string::from_const(rbegin); - } - - case ast_func_substring_2: - { - xpath_allocator_capture cr(stack.temp); - - xpath_stack swapped_stack = {stack.temp, stack.result}; - - xpath_string s = _left->eval_string(c, swapped_stack); - size_t s_length = s.length(); - - double first = round_nearest(_right->eval_number(c, stack)); - - if (is_nan(first)) return xpath_string(); // NaN - else if (first >= static_cast(s_length + 1)) return xpath_string(); - - size_t pos = first < 1 ? 1 : static_cast(first); - assert(1 <= pos && pos <= s_length + 1); - - const char_t* rbegin = s.c_str() + (pos - 1); - const char_t* rend = s.c_str() + s.length(); - - return s.uses_heap() ? xpath_string::from_heap(rbegin, rend, stack.result) : xpath_string::from_const(rbegin); - } - - case ast_func_substring_3: - { - xpath_allocator_capture cr(stack.temp); - - xpath_stack swapped_stack = {stack.temp, stack.result}; - - xpath_string s = _left->eval_string(c, swapped_stack); - size_t s_length = s.length(); - - double first = round_nearest(_right->eval_number(c, stack)); - double last = first + round_nearest(_right->_next->eval_number(c, stack)); - - if (is_nan(first) || is_nan(last)) return xpath_string(); - else if (first >= static_cast(s_length + 1)) return xpath_string(); - else if (first >= last) return xpath_string(); - else if (last < 1) return xpath_string(); - - size_t pos = first < 1 ? 1 : static_cast(first); - size_t end = last >= static_cast(s_length + 1) ? s_length + 1 : static_cast(last); - - assert(1 <= pos && pos <= end && end <= s_length + 1); - const char_t* rbegin = s.c_str() + (pos - 1); - const char_t* rend = s.c_str() + (end - 1); - - return (end == s_length + 1 && !s.uses_heap()) ? xpath_string::from_const(rbegin) : xpath_string::from_heap(rbegin, rend, stack.result); - } - - case ast_func_normalize_space_0: - { - xpath_string s = string_value(c.n, stack.result); - - char_t* begin = s.data(stack.result); - if (!begin) return xpath_string(); - - char_t* end = normalize_space(begin); - - return xpath_string::from_heap_preallocated(begin, end); - } - - case ast_func_normalize_space_1: - { - xpath_string s = _left->eval_string(c, stack); - - char_t* begin = s.data(stack.result); - if (!begin) return xpath_string(); - - char_t* end = normalize_space(begin); - - return xpath_string::from_heap_preallocated(begin, end); - } - - case ast_func_translate: - { - xpath_allocator_capture cr(stack.temp); - - xpath_stack swapped_stack = {stack.temp, stack.result}; - - xpath_string s = _left->eval_string(c, stack); - xpath_string from = _right->eval_string(c, swapped_stack); - xpath_string to = _right->_next->eval_string(c, swapped_stack); - - char_t* begin = s.data(stack.result); - if (!begin) return xpath_string(); - - char_t* end = translate(begin, from.c_str(), to.c_str(), to.length()); - - return xpath_string::from_heap_preallocated(begin, end); - } - - case ast_opt_translate_table: - { - xpath_string s = _left->eval_string(c, stack); - - char_t* begin = s.data(stack.result); - if (!begin) return xpath_string(); - - char_t* end = translate_table(begin, _data.table); - - return xpath_string::from_heap_preallocated(begin, end); - } - - case ast_variable: - { - assert(_rettype == _data.variable->type()); - - if (_rettype == xpath_type_string) - return xpath_string::from_const(_data.variable->get_string()); - - // variable needs to be converted to the correct type, this is handled by the fallthrough block below - break; - } - - default: - ; - } - - // none of the ast types that return the value directly matched, we need to perform type conversion - switch (_rettype) - { - case xpath_type_boolean: - return xpath_string::from_const(eval_boolean(c, stack) ? PUGIXML_TEXT("true") : PUGIXML_TEXT("false")); - - case xpath_type_number: - return convert_number_to_string(eval_number(c, stack), stack.result); - - case xpath_type_node_set: - { - xpath_allocator_capture cr(stack.temp); - - xpath_stack swapped_stack = {stack.temp, stack.result}; - - xpath_node_set_raw ns = eval_node_set(c, swapped_stack, nodeset_eval_first); - return ns.empty() ? xpath_string() : string_value(ns.first(), stack.result); - } - - default: - assert(false && "Wrong expression for return type string"); // unreachable - return xpath_string(); - } - } - - xpath_node_set_raw eval_node_set(const xpath_context& c, const xpath_stack& stack, nodeset_eval_t eval) - { - switch (_type) - { - case ast_op_union: - { - xpath_allocator_capture cr(stack.temp); - - xpath_stack swapped_stack = {stack.temp, stack.result}; - - xpath_node_set_raw ls = _left->eval_node_set(c, stack, eval); - xpath_node_set_raw rs = _right->eval_node_set(c, swapped_stack, eval); - - // we can optimize merging two sorted sets, but this is a very rare operation, so don't bother - ls.set_type(xpath_node_set::type_unsorted); - - ls.append(rs.begin(), rs.end(), stack.result); - ls.remove_duplicates(stack.temp); - - return ls; - } - - case ast_filter: - { - xpath_node_set_raw set = _left->eval_node_set(c, stack, _test == predicate_constant_one ? nodeset_eval_first : nodeset_eval_all); - - // either expression is a number or it contains position() call; sort by document order - if (_test != predicate_posinv) set.sort_do(); - - bool once = eval_once(set.type(), eval); - - apply_predicate(set, 0, stack, once); - - return set; - } - - case ast_func_id: - return xpath_node_set_raw(); - - case ast_step: - { - switch (_axis) - { - case axis_ancestor: - return step_do(c, stack, eval, axis_to_type()); - - case axis_ancestor_or_self: - return step_do(c, stack, eval, axis_to_type()); - - case axis_attribute: - return step_do(c, stack, eval, axis_to_type()); - - case axis_child: - return step_do(c, stack, eval, axis_to_type()); - - case axis_descendant: - return step_do(c, stack, eval, axis_to_type()); - - case axis_descendant_or_self: - return step_do(c, stack, eval, axis_to_type()); - - case axis_following: - return step_do(c, stack, eval, axis_to_type()); - - case axis_following_sibling: - return step_do(c, stack, eval, axis_to_type()); - - case axis_namespace: - // namespaced axis is not supported - return xpath_node_set_raw(); - - case axis_parent: - return step_do(c, stack, eval, axis_to_type()); - - case axis_preceding: - return step_do(c, stack, eval, axis_to_type()); - - case axis_preceding_sibling: - return step_do(c, stack, eval, axis_to_type()); - - case axis_self: - return step_do(c, stack, eval, axis_to_type()); - - default: - assert(false && "Unknown axis"); // unreachable - return xpath_node_set_raw(); - } - } - - case ast_step_root: - { - assert(!_right); // root step can't have any predicates - - xpath_node_set_raw ns; - - ns.set_type(xpath_node_set::type_sorted); - - if (c.n.node()) ns.push_back(c.n.node().root(), stack.result); - else if (c.n.attribute()) ns.push_back(c.n.parent().root(), stack.result); - - return ns; - } - - case ast_variable: - { - assert(_rettype == _data.variable->type()); - - if (_rettype == xpath_type_node_set) - { - const xpath_node_set& s = _data.variable->get_node_set(); - - xpath_node_set_raw ns; - - ns.set_type(s.type()); - ns.append(s.begin(), s.end(), stack.result); - - return ns; - } - - // variable needs to be converted to the correct type, this is handled by the fallthrough block below - break; - } - - default: - ; - } - - // none of the ast types that return the value directly matched, but conversions to node set are invalid - assert(false && "Wrong expression for return type node set"); // unreachable - return xpath_node_set_raw(); - } - - void optimize(xpath_allocator* alloc) - { - if (_left) - _left->optimize(alloc); - - if (_right) - _right->optimize(alloc); - - if (_next) - _next->optimize(alloc); - - // coverity[var_deref_model] - optimize_self(alloc); - } - - void optimize_self(xpath_allocator* alloc) - { - // Rewrite [position()=expr] with [expr] - // Note that this step has to go before classification to recognize [position()=1] - if ((_type == ast_filter || _type == ast_predicate) && - _right && // workaround for clang static analyzer (_right is never null for ast_filter/ast_predicate) - _right->_type == ast_op_equal && _right->_left->_type == ast_func_position && _right->_right->_rettype == xpath_type_number) - { - _right = _right->_right; - } - - // Classify filter/predicate ops to perform various optimizations during evaluation - if ((_type == ast_filter || _type == ast_predicate) && _right) // workaround for clang static analyzer (_right is never null for ast_filter/ast_predicate) - { - assert(_test == predicate_default); - - if (_right->_type == ast_number_constant && _right->_data.number == 1.0) - _test = predicate_constant_one; - else if (_right->_rettype == xpath_type_number && (_right->_type == ast_number_constant || _right->_type == ast_variable || _right->_type == ast_func_last)) - _test = predicate_constant; - else if (_right->_rettype != xpath_type_number && _right->is_posinv_expr()) - _test = predicate_posinv; - } - - // Rewrite descendant-or-self::node()/child::foo with descendant::foo - // The former is a full form of //foo, the latter is much faster since it executes the node test immediately - // Do a similar kind of rewrite for self/descendant/descendant-or-self axes - // Note that we only rewrite positionally invariant steps (//foo[1] != /descendant::foo[1]) - if (_type == ast_step && (_axis == axis_child || _axis == axis_self || _axis == axis_descendant || _axis == axis_descendant_or_self) && - _left && _left->_type == ast_step && _left->_axis == axis_descendant_or_self && _left->_test == nodetest_type_node && !_left->_right && - is_posinv_step()) - { - if (_axis == axis_child || _axis == axis_descendant) - _axis = axis_descendant; - else - _axis = axis_descendant_or_self; - - _left = _left->_left; - } - - // Use optimized lookup table implementation for translate() with constant arguments - if (_type == ast_func_translate && - _right && // workaround for clang static analyzer (_right is never null for ast_func_translate) - _right->_type == ast_string_constant && _right->_next->_type == ast_string_constant) - { - unsigned char* table = translate_table_generate(alloc, _right->_data.string, _right->_next->_data.string); - - if (table) - { - _type = ast_opt_translate_table; - _data.table = table; - } - } - - // Use optimized path for @attr = 'value' or @attr = $value - if (_type == ast_op_equal && - _left && _right && // workaround for clang static analyzer and Coverity (_left and _right are never null for ast_op_equal) - // coverity[mixed_enums] - _left->_type == ast_step && _left->_axis == axis_attribute && _left->_test == nodetest_name && !_left->_left && !_left->_right && - (_right->_type == ast_string_constant || (_right->_type == ast_variable && _right->_rettype == xpath_type_string))) - { - _type = ast_opt_compare_attribute; - } - } - - bool is_posinv_expr() const - { - switch (_type) - { - case ast_func_position: - case ast_func_last: - return false; - - case ast_string_constant: - case ast_number_constant: - case ast_variable: - return true; - - case ast_step: - case ast_step_root: - return true; - - case ast_predicate: - case ast_filter: - return true; - - default: - if (_left && !_left->is_posinv_expr()) return false; - - for (xpath_ast_node* n = _right; n; n = n->_next) - if (!n->is_posinv_expr()) return false; - - return true; - } - } - - bool is_posinv_step() const - { - assert(_type == ast_step); - - for (xpath_ast_node* n = _right; n; n = n->_next) - { - assert(n->_type == ast_predicate); - - if (n->_test != predicate_posinv) - return false; - } - - return true; - } - - xpath_value_type rettype() const - { - return static_cast(_rettype); - } - }; - - static const size_t xpath_ast_depth_limit = - #ifdef PUGIXML_XPATH_DEPTH_LIMIT - PUGIXML_XPATH_DEPTH_LIMIT - #else - 1024 - #endif - ; - - struct xpath_parser - { - xpath_allocator* _alloc; - xpath_lexer _lexer; - - const char_t* _query; - xpath_variable_set* _variables; - - xpath_parse_result* _result; - - char_t _scratch[32]; - - size_t _depth; - - xpath_ast_node* error(const char* message) - { - _result->error = message; - _result->offset = _lexer.current_pos() - _query; - - return 0; - } - - xpath_ast_node* error_oom() - { - assert(_alloc->_error); - *_alloc->_error = true; - - return 0; - } - - xpath_ast_node* error_rec() - { - return error("Exceeded maximum allowed query depth"); - } - - void* alloc_node() - { - return _alloc->allocate(sizeof(xpath_ast_node)); - } - - xpath_ast_node* alloc_node(ast_type_t type, xpath_value_type rettype, const char_t* value) - { - void* memory = alloc_node(); - return memory ? new (memory) xpath_ast_node(type, rettype, value) : 0; - } - - xpath_ast_node* alloc_node(ast_type_t type, xpath_value_type rettype, double value) - { - void* memory = alloc_node(); - return memory ? new (memory) xpath_ast_node(type, rettype, value) : 0; - } - - xpath_ast_node* alloc_node(ast_type_t type, xpath_value_type rettype, xpath_variable* value) - { - void* memory = alloc_node(); - return memory ? new (memory) xpath_ast_node(type, rettype, value) : 0; - } - - xpath_ast_node* alloc_node(ast_type_t type, xpath_value_type rettype, xpath_ast_node* left = 0, xpath_ast_node* right = 0) - { - void* memory = alloc_node(); - return memory ? new (memory) xpath_ast_node(type, rettype, left, right) : 0; - } - - xpath_ast_node* alloc_node(ast_type_t type, xpath_ast_node* left, axis_t axis, nodetest_t test, const char_t* contents) - { - void* memory = alloc_node(); - return memory ? new (memory) xpath_ast_node(type, left, axis, test, contents) : 0; - } - - xpath_ast_node* alloc_node(ast_type_t type, xpath_ast_node* left, xpath_ast_node* right, predicate_t test) - { - void* memory = alloc_node(); - return memory ? new (memory) xpath_ast_node(type, left, right, test) : 0; - } - - const char_t* alloc_string(const xpath_lexer_string& value) - { - if (!value.begin) - return PUGIXML_TEXT(""); - - size_t length = static_cast(value.end - value.begin); - - char_t* c = static_cast(_alloc->allocate((length + 1) * sizeof(char_t))); - if (!c) return 0; - - memcpy(c, value.begin, length * sizeof(char_t)); - c[length] = 0; - - return c; - } - - xpath_ast_node* parse_function(const xpath_lexer_string& name, size_t argc, xpath_ast_node* args[2]) - { - switch (name.begin[0]) - { - case 'b': - if (name == PUGIXML_TEXT("boolean") && argc == 1) - return alloc_node(ast_func_boolean, xpath_type_boolean, args[0]); - - break; - - case 'c': - if (name == PUGIXML_TEXT("count") && argc == 1) - { - if (args[0]->rettype() != xpath_type_node_set) return error("Function has to be applied to node set"); - return alloc_node(ast_func_count, xpath_type_number, args[0]); - } - else if (name == PUGIXML_TEXT("contains") && argc == 2) - return alloc_node(ast_func_contains, xpath_type_boolean, args[0], args[1]); - else if (name == PUGIXML_TEXT("concat") && argc >= 2) - return alloc_node(ast_func_concat, xpath_type_string, args[0], args[1]); - else if (name == PUGIXML_TEXT("ceiling") && argc == 1) - return alloc_node(ast_func_ceiling, xpath_type_number, args[0]); - - break; - - case 'f': - if (name == PUGIXML_TEXT("false") && argc == 0) - return alloc_node(ast_func_false, xpath_type_boolean); - else if (name == PUGIXML_TEXT("floor") && argc == 1) - return alloc_node(ast_func_floor, xpath_type_number, args[0]); - - break; - - case 'i': - if (name == PUGIXML_TEXT("id") && argc == 1) - return alloc_node(ast_func_id, xpath_type_node_set, args[0]); - - break; - - case 'l': - if (name == PUGIXML_TEXT("last") && argc == 0) - return alloc_node(ast_func_last, xpath_type_number); - else if (name == PUGIXML_TEXT("lang") && argc == 1) - return alloc_node(ast_func_lang, xpath_type_boolean, args[0]); - else if (name == PUGIXML_TEXT("local-name") && argc <= 1) - { - if (argc == 1 && args[0]->rettype() != xpath_type_node_set) return error("Function has to be applied to node set"); - return alloc_node(argc == 0 ? ast_func_local_name_0 : ast_func_local_name_1, xpath_type_string, args[0]); - } - - break; - - case 'n': - if (name == PUGIXML_TEXT("name") && argc <= 1) - { - if (argc == 1 && args[0]->rettype() != xpath_type_node_set) return error("Function has to be applied to node set"); - return alloc_node(argc == 0 ? ast_func_name_0 : ast_func_name_1, xpath_type_string, args[0]); - } - else if (name == PUGIXML_TEXT("namespace-uri") && argc <= 1) - { - if (argc == 1 && args[0]->rettype() != xpath_type_node_set) return error("Function has to be applied to node set"); - return alloc_node(argc == 0 ? ast_func_namespace_uri_0 : ast_func_namespace_uri_1, xpath_type_string, args[0]); - } - else if (name == PUGIXML_TEXT("normalize-space") && argc <= 1) - return alloc_node(argc == 0 ? ast_func_normalize_space_0 : ast_func_normalize_space_1, xpath_type_string, args[0], args[1]); - else if (name == PUGIXML_TEXT("not") && argc == 1) - return alloc_node(ast_func_not, xpath_type_boolean, args[0]); - else if (name == PUGIXML_TEXT("number") && argc <= 1) - return alloc_node(argc == 0 ? ast_func_number_0 : ast_func_number_1, xpath_type_number, args[0]); - - break; - - case 'p': - if (name == PUGIXML_TEXT("position") && argc == 0) - return alloc_node(ast_func_position, xpath_type_number); - - break; - - case 'r': - if (name == PUGIXML_TEXT("round") && argc == 1) - return alloc_node(ast_func_round, xpath_type_number, args[0]); - - break; - - case 's': - if (name == PUGIXML_TEXT("string") && argc <= 1) - return alloc_node(argc == 0 ? ast_func_string_0 : ast_func_string_1, xpath_type_string, args[0]); - else if (name == PUGIXML_TEXT("string-length") && argc <= 1) - return alloc_node(argc == 0 ? ast_func_string_length_0 : ast_func_string_length_1, xpath_type_number, args[0]); - else if (name == PUGIXML_TEXT("starts-with") && argc == 2) - return alloc_node(ast_func_starts_with, xpath_type_boolean, args[0], args[1]); - else if (name == PUGIXML_TEXT("substring-before") && argc == 2) - return alloc_node(ast_func_substring_before, xpath_type_string, args[0], args[1]); - else if (name == PUGIXML_TEXT("substring-after") && argc == 2) - return alloc_node(ast_func_substring_after, xpath_type_string, args[0], args[1]); - else if (name == PUGIXML_TEXT("substring") && (argc == 2 || argc == 3)) - return alloc_node(argc == 2 ? ast_func_substring_2 : ast_func_substring_3, xpath_type_string, args[0], args[1]); - else if (name == PUGIXML_TEXT("sum") && argc == 1) - { - if (args[0]->rettype() != xpath_type_node_set) return error("Function has to be applied to node set"); - return alloc_node(ast_func_sum, xpath_type_number, args[0]); - } - - break; - - case 't': - if (name == PUGIXML_TEXT("translate") && argc == 3) - return alloc_node(ast_func_translate, xpath_type_string, args[0], args[1]); - else if (name == PUGIXML_TEXT("true") && argc == 0) - return alloc_node(ast_func_true, xpath_type_boolean); - - break; - - default: - break; - } - - return error("Unrecognized function or wrong parameter count"); - } - - axis_t parse_axis_name(const xpath_lexer_string& name, bool& specified) - { - specified = true; - - switch (name.begin[0]) - { - case 'a': - if (name == PUGIXML_TEXT("ancestor")) - return axis_ancestor; - else if (name == PUGIXML_TEXT("ancestor-or-self")) - return axis_ancestor_or_self; - else if (name == PUGIXML_TEXT("attribute")) - return axis_attribute; - - break; - - case 'c': - if (name == PUGIXML_TEXT("child")) - return axis_child; - - break; - - case 'd': - if (name == PUGIXML_TEXT("descendant")) - return axis_descendant; - else if (name == PUGIXML_TEXT("descendant-or-self")) - return axis_descendant_or_self; - - break; - - case 'f': - if (name == PUGIXML_TEXT("following")) - return axis_following; - else if (name == PUGIXML_TEXT("following-sibling")) - return axis_following_sibling; - - break; - - case 'n': - if (name == PUGIXML_TEXT("namespace")) - return axis_namespace; - - break; - - case 'p': - if (name == PUGIXML_TEXT("parent")) - return axis_parent; - else if (name == PUGIXML_TEXT("preceding")) - return axis_preceding; - else if (name == PUGIXML_TEXT("preceding-sibling")) - return axis_preceding_sibling; - - break; - - case 's': - if (name == PUGIXML_TEXT("self")) - return axis_self; - - break; - - default: - break; - } - - specified = false; - return axis_child; - } - - nodetest_t parse_node_test_type(const xpath_lexer_string& name) - { - switch (name.begin[0]) - { - case 'c': - if (name == PUGIXML_TEXT("comment")) - return nodetest_type_comment; - - break; - - case 'n': - if (name == PUGIXML_TEXT("node")) - return nodetest_type_node; - - break; - - case 'p': - if (name == PUGIXML_TEXT("processing-instruction")) - return nodetest_type_pi; - - break; - - case 't': - if (name == PUGIXML_TEXT("text")) - return nodetest_type_text; - - break; - - default: - break; - } - - return nodetest_none; - } - - // PrimaryExpr ::= VariableReference | '(' Expr ')' | Literal | Number | FunctionCall - xpath_ast_node* parse_primary_expression() - { - switch (_lexer.current()) - { - case lex_var_ref: - { - xpath_lexer_string name = _lexer.contents(); - - if (!_variables) - return error("Unknown variable: variable set is not provided"); - - xpath_variable* var = 0; - if (!get_variable_scratch(_scratch, _variables, name.begin, name.end, &var)) - return error_oom(); - - if (!var) - return error("Unknown variable: variable set does not contain the given name"); - - _lexer.next(); - - return alloc_node(ast_variable, var->type(), var); - } - - case lex_open_brace: - { - _lexer.next(); - - xpath_ast_node* n = parse_expression(); - if (!n) return 0; - - if (_lexer.current() != lex_close_brace) - return error("Expected ')' to match an opening '('"); - - _lexer.next(); - - return n; - } - - case lex_quoted_string: - { - const char_t* value = alloc_string(_lexer.contents()); - if (!value) return 0; - - _lexer.next(); - - return alloc_node(ast_string_constant, xpath_type_string, value); - } - - case lex_number: - { - double value = 0; - - if (!convert_string_to_number_scratch(_scratch, _lexer.contents().begin, _lexer.contents().end, &value)) - return error_oom(); - - _lexer.next(); - - return alloc_node(ast_number_constant, xpath_type_number, value); - } - - case lex_string: - { - xpath_ast_node* args[2] = {0}; - size_t argc = 0; - - xpath_lexer_string function = _lexer.contents(); - _lexer.next(); - - xpath_ast_node* last_arg = 0; - - if (_lexer.current() != lex_open_brace) - return error("Unrecognized function call"); - _lexer.next(); - - size_t old_depth = _depth; - - while (_lexer.current() != lex_close_brace) - { - if (argc > 0) - { - if (_lexer.current() != lex_comma) - return error("No comma between function arguments"); - _lexer.next(); - } - - if (++_depth > xpath_ast_depth_limit) - return error_rec(); - - xpath_ast_node* n = parse_expression(); - if (!n) return 0; - - if (argc < 2) args[argc] = n; - else last_arg->set_next(n); - - argc++; - last_arg = n; - } - - _lexer.next(); - - _depth = old_depth; - - return parse_function(function, argc, args); - } - - default: - return error("Unrecognizable primary expression"); - } - } - - // FilterExpr ::= PrimaryExpr | FilterExpr Predicate - // Predicate ::= '[' PredicateExpr ']' - // PredicateExpr ::= Expr - xpath_ast_node* parse_filter_expression() - { - xpath_ast_node* n = parse_primary_expression(); - if (!n) return 0; - - size_t old_depth = _depth; - - while (_lexer.current() == lex_open_square_brace) - { - _lexer.next(); - - if (++_depth > xpath_ast_depth_limit) - return error_rec(); - - if (n->rettype() != xpath_type_node_set) - return error("Predicate has to be applied to node set"); - - xpath_ast_node* expr = parse_expression(); - if (!expr) return 0; - - n = alloc_node(ast_filter, n, expr, predicate_default); - if (!n) return 0; - - if (_lexer.current() != lex_close_square_brace) - return error("Expected ']' to match an opening '['"); - - _lexer.next(); - } - - _depth = old_depth; - - return n; - } - - // Step ::= AxisSpecifier NodeTest Predicate* | AbbreviatedStep - // AxisSpecifier ::= AxisName '::' | '@'? - // NodeTest ::= NameTest | NodeType '(' ')' | 'processing-instruction' '(' Literal ')' - // NameTest ::= '*' | NCName ':' '*' | QName - // AbbreviatedStep ::= '.' | '..' - xpath_ast_node* parse_step(xpath_ast_node* set) - { - if (set && set->rettype() != xpath_type_node_set) - return error("Step has to be applied to node set"); - - bool axis_specified = false; - axis_t axis = axis_child; // implied child axis - - if (_lexer.current() == lex_axis_attribute) - { - axis = axis_attribute; - axis_specified = true; - - _lexer.next(); - } - else if (_lexer.current() == lex_dot) - { - _lexer.next(); - - if (_lexer.current() == lex_open_square_brace) - return error("Predicates are not allowed after an abbreviated step"); - - return alloc_node(ast_step, set, axis_self, nodetest_type_node, 0); - } - else if (_lexer.current() == lex_double_dot) - { - _lexer.next(); - - if (_lexer.current() == lex_open_square_brace) - return error("Predicates are not allowed after an abbreviated step"); - - return alloc_node(ast_step, set, axis_parent, nodetest_type_node, 0); - } - - nodetest_t nt_type = nodetest_none; - xpath_lexer_string nt_name; - - if (_lexer.current() == lex_string) - { - // node name test - nt_name = _lexer.contents(); - _lexer.next(); - - // was it an axis name? - if (_lexer.current() == lex_double_colon) - { - // parse axis name - if (axis_specified) - return error("Two axis specifiers in one step"); - - axis = parse_axis_name(nt_name, axis_specified); - - if (!axis_specified) - return error("Unknown axis"); - - // read actual node test - _lexer.next(); - - if (_lexer.current() == lex_multiply) - { - nt_type = nodetest_all; - nt_name = xpath_lexer_string(); - _lexer.next(); - } - else if (_lexer.current() == lex_string) - { - nt_name = _lexer.contents(); - _lexer.next(); - } - else - { - return error("Unrecognized node test"); - } - } - - if (nt_type == nodetest_none) - { - // node type test or processing-instruction - if (_lexer.current() == lex_open_brace) - { - _lexer.next(); - - if (_lexer.current() == lex_close_brace) - { - _lexer.next(); - - nt_type = parse_node_test_type(nt_name); - - if (nt_type == nodetest_none) - return error("Unrecognized node type"); - - nt_name = xpath_lexer_string(); - } - else if (nt_name == PUGIXML_TEXT("processing-instruction")) - { - if (_lexer.current() != lex_quoted_string) - return error("Only literals are allowed as arguments to processing-instruction()"); - - nt_type = nodetest_pi; - nt_name = _lexer.contents(); - _lexer.next(); - - if (_lexer.current() != lex_close_brace) - return error("Unmatched brace near processing-instruction()"); - _lexer.next(); - } - else - { - return error("Unmatched brace near node type test"); - } - } - // QName or NCName:* - else - { - if (nt_name.end - nt_name.begin > 2 && nt_name.end[-2] == ':' && nt_name.end[-1] == '*') // NCName:* - { - nt_name.end--; // erase * - - nt_type = nodetest_all_in_namespace; - } - else - { - nt_type = nodetest_name; - } - } - } - } - else if (_lexer.current() == lex_multiply) - { - nt_type = nodetest_all; - _lexer.next(); - } - else - { - return error("Unrecognized node test"); - } - - const char_t* nt_name_copy = alloc_string(nt_name); - if (!nt_name_copy) return 0; - - xpath_ast_node* n = alloc_node(ast_step, set, axis, nt_type, nt_name_copy); - if (!n) return 0; - - size_t old_depth = _depth; - - xpath_ast_node* last = 0; - - while (_lexer.current() == lex_open_square_brace) - { - _lexer.next(); - - if (++_depth > xpath_ast_depth_limit) - return error_rec(); - - xpath_ast_node* expr = parse_expression(); - if (!expr) return 0; - - xpath_ast_node* pred = alloc_node(ast_predicate, 0, expr, predicate_default); - if (!pred) return 0; - - if (_lexer.current() != lex_close_square_brace) - return error("Expected ']' to match an opening '['"); - _lexer.next(); - - if (last) last->set_next(pred); - else n->set_right(pred); - - last = pred; - } - - _depth = old_depth; - - return n; - } - - // RelativeLocationPath ::= Step | RelativeLocationPath '/' Step | RelativeLocationPath '//' Step - xpath_ast_node* parse_relative_location_path(xpath_ast_node* set) - { - xpath_ast_node* n = parse_step(set); - if (!n) return 0; - - size_t old_depth = _depth; - - while (_lexer.current() == lex_slash || _lexer.current() == lex_double_slash) - { - lexeme_t l = _lexer.current(); - _lexer.next(); - - if (l == lex_double_slash) - { - n = alloc_node(ast_step, n, axis_descendant_or_self, nodetest_type_node, 0); - if (!n) return 0; - - ++_depth; - } - - if (++_depth > xpath_ast_depth_limit) - return error_rec(); - - n = parse_step(n); - if (!n) return 0; - } - - _depth = old_depth; - - return n; - } - - // LocationPath ::= RelativeLocationPath | AbsoluteLocationPath - // AbsoluteLocationPath ::= '/' RelativeLocationPath? | '//' RelativeLocationPath - xpath_ast_node* parse_location_path() - { - if (_lexer.current() == lex_slash) - { - _lexer.next(); - - xpath_ast_node* n = alloc_node(ast_step_root, xpath_type_node_set); - if (!n) return 0; - - // relative location path can start from axis_attribute, dot, double_dot, multiply and string lexemes; any other lexeme means standalone root path - lexeme_t l = _lexer.current(); - - if (l == lex_string || l == lex_axis_attribute || l == lex_dot || l == lex_double_dot || l == lex_multiply) - return parse_relative_location_path(n); - else - return n; - } - else if (_lexer.current() == lex_double_slash) - { - _lexer.next(); - - xpath_ast_node* n = alloc_node(ast_step_root, xpath_type_node_set); - if (!n) return 0; - - n = alloc_node(ast_step, n, axis_descendant_or_self, nodetest_type_node, 0); - if (!n) return 0; - - return parse_relative_location_path(n); - } - - // else clause moved outside of if because of bogus warning 'control may reach end of non-void function being inlined' in gcc 4.0.1 - return parse_relative_location_path(0); - } - - // PathExpr ::= LocationPath - // | FilterExpr - // | FilterExpr '/' RelativeLocationPath - // | FilterExpr '//' RelativeLocationPath - // UnionExpr ::= PathExpr | UnionExpr '|' PathExpr - // UnaryExpr ::= UnionExpr | '-' UnaryExpr - xpath_ast_node* parse_path_or_unary_expression() - { - // Clarification. - // PathExpr begins with either LocationPath or FilterExpr. - // FilterExpr begins with PrimaryExpr - // PrimaryExpr begins with '$' in case of it being a variable reference, - // '(' in case of it being an expression, string literal, number constant or - // function call. - if (_lexer.current() == lex_var_ref || _lexer.current() == lex_open_brace || - _lexer.current() == lex_quoted_string || _lexer.current() == lex_number || - _lexer.current() == lex_string) - { - if (_lexer.current() == lex_string) - { - // This is either a function call, or not - if not, we shall proceed with location path - const char_t* state = _lexer.state(); - - while (PUGI_IMPL_IS_CHARTYPE(*state, ct_space)) ++state; - - if (*state != '(') - return parse_location_path(); - - // This looks like a function call; however this still can be a node-test. Check it. - if (parse_node_test_type(_lexer.contents()) != nodetest_none) - return parse_location_path(); - } - - xpath_ast_node* n = parse_filter_expression(); - if (!n) return 0; - - if (_lexer.current() == lex_slash || _lexer.current() == lex_double_slash) - { - lexeme_t l = _lexer.current(); - _lexer.next(); - - if (l == lex_double_slash) - { - if (n->rettype() != xpath_type_node_set) - return error("Step has to be applied to node set"); - - n = alloc_node(ast_step, n, axis_descendant_or_self, nodetest_type_node, 0); - if (!n) return 0; - } - - // select from location path - return parse_relative_location_path(n); - } - - return n; - } - else if (_lexer.current() == lex_minus) - { - _lexer.next(); - - // precedence 7+ - only parses union expressions - xpath_ast_node* n = parse_expression(7); - if (!n) return 0; - - return alloc_node(ast_op_negate, xpath_type_number, n); - } - else - { - return parse_location_path(); - } - } - - struct binary_op_t - { - ast_type_t asttype; - xpath_value_type rettype; - int precedence; - - binary_op_t(): asttype(ast_unknown), rettype(xpath_type_none), precedence(0) - { - } - - binary_op_t(ast_type_t asttype_, xpath_value_type rettype_, int precedence_): asttype(asttype_), rettype(rettype_), precedence(precedence_) - { - } - - static binary_op_t parse(xpath_lexer& lexer) - { - switch (lexer.current()) - { - case lex_string: - if (lexer.contents() == PUGIXML_TEXT("or")) - return binary_op_t(ast_op_or, xpath_type_boolean, 1); - else if (lexer.contents() == PUGIXML_TEXT("and")) - return binary_op_t(ast_op_and, xpath_type_boolean, 2); - else if (lexer.contents() == PUGIXML_TEXT("div")) - return binary_op_t(ast_op_divide, xpath_type_number, 6); - else if (lexer.contents() == PUGIXML_TEXT("mod")) - return binary_op_t(ast_op_mod, xpath_type_number, 6); - else - return binary_op_t(); - - case lex_equal: - return binary_op_t(ast_op_equal, xpath_type_boolean, 3); - - case lex_not_equal: - return binary_op_t(ast_op_not_equal, xpath_type_boolean, 3); - - case lex_less: - return binary_op_t(ast_op_less, xpath_type_boolean, 4); - - case lex_greater: - return binary_op_t(ast_op_greater, xpath_type_boolean, 4); - - case lex_less_or_equal: - return binary_op_t(ast_op_less_or_equal, xpath_type_boolean, 4); - - case lex_greater_or_equal: - return binary_op_t(ast_op_greater_or_equal, xpath_type_boolean, 4); - - case lex_plus: - return binary_op_t(ast_op_add, xpath_type_number, 5); - - case lex_minus: - return binary_op_t(ast_op_subtract, xpath_type_number, 5); - - case lex_multiply: - return binary_op_t(ast_op_multiply, xpath_type_number, 6); - - case lex_union: - return binary_op_t(ast_op_union, xpath_type_node_set, 7); - - default: - return binary_op_t(); - } - } - }; - - xpath_ast_node* parse_expression_rec(xpath_ast_node* lhs, int limit) - { - binary_op_t op = binary_op_t::parse(_lexer); - - while (op.asttype != ast_unknown && op.precedence >= limit) - { - _lexer.next(); - - if (++_depth > xpath_ast_depth_limit) - return error_rec(); - - xpath_ast_node* rhs = parse_path_or_unary_expression(); - if (!rhs) return 0; - - binary_op_t nextop = binary_op_t::parse(_lexer); - - while (nextop.asttype != ast_unknown && nextop.precedence > op.precedence) - { - rhs = parse_expression_rec(rhs, nextop.precedence); - if (!rhs) return 0; - - nextop = binary_op_t::parse(_lexer); - } - - if (op.asttype == ast_op_union && (lhs->rettype() != xpath_type_node_set || rhs->rettype() != xpath_type_node_set)) - return error("Union operator has to be applied to node sets"); - - lhs = alloc_node(op.asttype, op.rettype, lhs, rhs); - if (!lhs) return 0; - - op = binary_op_t::parse(_lexer); - } - - return lhs; - } - - // Expr ::= OrExpr - // OrExpr ::= AndExpr | OrExpr 'or' AndExpr - // AndExpr ::= EqualityExpr | AndExpr 'and' EqualityExpr - // EqualityExpr ::= RelationalExpr - // | EqualityExpr '=' RelationalExpr - // | EqualityExpr '!=' RelationalExpr - // RelationalExpr ::= AdditiveExpr - // | RelationalExpr '<' AdditiveExpr - // | RelationalExpr '>' AdditiveExpr - // | RelationalExpr '<=' AdditiveExpr - // | RelationalExpr '>=' AdditiveExpr - // AdditiveExpr ::= MultiplicativeExpr - // | AdditiveExpr '+' MultiplicativeExpr - // | AdditiveExpr '-' MultiplicativeExpr - // MultiplicativeExpr ::= UnaryExpr - // | MultiplicativeExpr '*' UnaryExpr - // | MultiplicativeExpr 'div' UnaryExpr - // | MultiplicativeExpr 'mod' UnaryExpr - xpath_ast_node* parse_expression(int limit = 0) - { - size_t old_depth = _depth; - - if (++_depth > xpath_ast_depth_limit) - return error_rec(); - - xpath_ast_node* n = parse_path_or_unary_expression(); - if (!n) return 0; - - n = parse_expression_rec(n, limit); - - _depth = old_depth; - - return n; - } - - xpath_parser(const char_t* query, xpath_variable_set* variables, xpath_allocator* alloc, xpath_parse_result* result): _alloc(alloc), _lexer(query), _query(query), _variables(variables), _result(result), _depth(0) - { - } - - xpath_ast_node* parse() - { - xpath_ast_node* n = parse_expression(); - if (!n) return 0; - - assert(_depth == 0); - - // check if there are unparsed tokens left - if (_lexer.current() != lex_eof) - return error("Incorrect query"); - - return n; - } - - static xpath_ast_node* parse(const char_t* query, xpath_variable_set* variables, xpath_allocator* alloc, xpath_parse_result* result) - { - xpath_parser parser(query, variables, alloc, result); - - return parser.parse(); - } - }; - - struct xpath_query_impl - { - static xpath_query_impl* create() - { - void* memory = xml_memory::allocate(sizeof(xpath_query_impl)); - if (!memory) return 0; - - return new (memory) xpath_query_impl(); - } - - static void destroy(xpath_query_impl* impl) - { - // free all allocated pages - impl->alloc.release(); - - // free allocator memory (with the first page) - xml_memory::deallocate(impl); - } - - xpath_query_impl(): root(0), alloc(&block, &oom), oom(false) - { - block.next = 0; - block.capacity = sizeof(block.data); - } - - xpath_ast_node* root; - xpath_allocator alloc; - xpath_memory_block block; - bool oom; - }; - - PUGI_IMPL_FN impl::xpath_ast_node* evaluate_node_set_prepare(xpath_query_impl* impl) - { - if (!impl) return 0; - - if (impl->root->rettype() != xpath_type_node_set) - { - #ifdef PUGIXML_NO_EXCEPTIONS - return 0; - #else - xpath_parse_result res; - res.error = "Expression does not evaluate to node set"; - - throw xpath_exception(res); - #endif - } - - return impl->root; - } -PUGI_IMPL_NS_END - -namespace pugi -{ -#ifndef PUGIXML_NO_EXCEPTIONS - PUGI_IMPL_FN xpath_exception::xpath_exception(const xpath_parse_result& result_): _result(result_) - { - assert(_result.error); - } - - PUGI_IMPL_FN const char* xpath_exception::what() const throw() - { - return _result.error; - } - - PUGI_IMPL_FN const xpath_parse_result& xpath_exception::result() const - { - return _result; - } -#endif - - PUGI_IMPL_FN xpath_node::xpath_node() - { - } - - PUGI_IMPL_FN xpath_node::xpath_node(const xml_node& node_): _node(node_) - { - } - - PUGI_IMPL_FN xpath_node::xpath_node(const xml_attribute& attribute_, const xml_node& parent_): _node(attribute_ ? parent_ : xml_node()), _attribute(attribute_) - { - } - - PUGI_IMPL_FN xml_node xpath_node::node() const - { - return _attribute ? xml_node() : _node; - } - - PUGI_IMPL_FN xml_attribute xpath_node::attribute() const - { - return _attribute; - } - - PUGI_IMPL_FN xml_node xpath_node::parent() const - { - return _attribute ? _node : _node.parent(); - } - - PUGI_IMPL_FN static void unspecified_bool_xpath_node(xpath_node***) - { - } - - PUGI_IMPL_FN xpath_node::operator xpath_node::unspecified_bool_type() const - { - return (_node || _attribute) ? unspecified_bool_xpath_node : 0; - } - - PUGI_IMPL_FN bool xpath_node::operator!() const - { - return !(_node || _attribute); - } - - PUGI_IMPL_FN bool xpath_node::operator==(const xpath_node& n) const - { - return _node == n._node && _attribute == n._attribute; - } - - PUGI_IMPL_FN bool xpath_node::operator!=(const xpath_node& n) const - { - return _node != n._node || _attribute != n._attribute; - } - -#ifdef __BORLANDC__ - PUGI_IMPL_FN bool operator&&(const xpath_node& lhs, bool rhs) - { - return (bool)lhs && rhs; - } - - PUGI_IMPL_FN bool operator||(const xpath_node& lhs, bool rhs) - { - return (bool)lhs || rhs; - } -#endif - - PUGI_IMPL_FN void xpath_node_set::_assign(const_iterator begin_, const_iterator end_, type_t type_) - { - assert(begin_ <= end_); - - size_t size_ = static_cast(end_ - begin_); - - // use internal buffer for 0 or 1 elements, heap buffer otherwise - xpath_node* storage = (size_ <= 1) ? _storage : static_cast(impl::xml_memory::allocate(size_ * sizeof(xpath_node))); - - if (!storage) - { - #ifdef PUGIXML_NO_EXCEPTIONS - return; - #else - throw std::bad_alloc(); - #endif - } - - // deallocate old buffer - if (_begin != _storage) - impl::xml_memory::deallocate(_begin); - - // size check is necessary because for begin_ = end_ = nullptr, memcpy is UB - if (size_) - memcpy(storage, begin_, size_ * sizeof(xpath_node)); - - _begin = storage; - _end = storage + size_; - _type = type_; - } - -#ifdef PUGIXML_HAS_MOVE - PUGI_IMPL_FN void xpath_node_set::_move(xpath_node_set& rhs) PUGIXML_NOEXCEPT - { - _type = rhs._type; - _storage[0] = rhs._storage[0]; - _begin = (rhs._begin == rhs._storage) ? _storage : rhs._begin; - _end = _begin + (rhs._end - rhs._begin); - - rhs._type = type_unsorted; - rhs._begin = rhs._storage; - rhs._end = rhs._storage; - } -#endif - - PUGI_IMPL_FN xpath_node_set::xpath_node_set(): _type(type_unsorted), _begin(_storage), _end(_storage) - { - } - - PUGI_IMPL_FN xpath_node_set::xpath_node_set(const_iterator begin_, const_iterator end_, type_t type_): _type(type_unsorted), _begin(_storage), _end(_storage) - { - _assign(begin_, end_, type_); - } - - PUGI_IMPL_FN xpath_node_set::~xpath_node_set() - { - if (_begin != _storage) - impl::xml_memory::deallocate(_begin); - } - - PUGI_IMPL_FN xpath_node_set::xpath_node_set(const xpath_node_set& ns): _type(type_unsorted), _begin(_storage), _end(_storage) - { - _assign(ns._begin, ns._end, ns._type); - } - - PUGI_IMPL_FN xpath_node_set& xpath_node_set::operator=(const xpath_node_set& ns) - { - if (this == &ns) return *this; - - _assign(ns._begin, ns._end, ns._type); - - return *this; - } - -#ifdef PUGIXML_HAS_MOVE - PUGI_IMPL_FN xpath_node_set::xpath_node_set(xpath_node_set&& rhs) PUGIXML_NOEXCEPT: _type(type_unsorted), _begin(_storage), _end(_storage) - { - _move(rhs); - } - - PUGI_IMPL_FN xpath_node_set& xpath_node_set::operator=(xpath_node_set&& rhs) PUGIXML_NOEXCEPT - { - if (this == &rhs) return *this; - - if (_begin != _storage) - impl::xml_memory::deallocate(_begin); - - _move(rhs); - - return *this; - } -#endif - - PUGI_IMPL_FN xpath_node_set::type_t xpath_node_set::type() const - { - return _type; - } - - PUGI_IMPL_FN size_t xpath_node_set::size() const - { - return _end - _begin; - } - - PUGI_IMPL_FN bool xpath_node_set::empty() const - { - return _begin == _end; - } - - PUGI_IMPL_FN const xpath_node& xpath_node_set::operator[](size_t index) const - { - assert(index < size()); - return _begin[index]; - } - - PUGI_IMPL_FN xpath_node_set::const_iterator xpath_node_set::begin() const - { - return _begin; - } - - PUGI_IMPL_FN xpath_node_set::const_iterator xpath_node_set::end() const - { - return _end; - } - - PUGI_IMPL_FN void xpath_node_set::sort(bool reverse) - { - _type = impl::xpath_sort(_begin, _end, _type, reverse); - } - - PUGI_IMPL_FN xpath_node xpath_node_set::first() const - { - return impl::xpath_first(_begin, _end, _type); - } - - PUGI_IMPL_FN xpath_parse_result::xpath_parse_result(): error("Internal error"), offset(0) - { - } - - PUGI_IMPL_FN xpath_parse_result::operator bool() const - { - return error == 0; - } - - PUGI_IMPL_FN const char* xpath_parse_result::description() const - { - return error ? error : "No error"; - } - - PUGI_IMPL_FN xpath_variable::xpath_variable(xpath_value_type type_): _type(type_), _next(0) - { - } - - PUGI_IMPL_FN const char_t* xpath_variable::name() const - { - switch (_type) - { - case xpath_type_node_set: - return static_cast(this)->name; - - case xpath_type_number: - return static_cast(this)->name; - - case xpath_type_string: - return static_cast(this)->name; - - case xpath_type_boolean: - return static_cast(this)->name; - - default: - assert(false && "Invalid variable type"); // unreachable - return 0; - } - } - - PUGI_IMPL_FN xpath_value_type xpath_variable::type() const - { - return _type; - } - - PUGI_IMPL_FN bool xpath_variable::get_boolean() const - { - return (_type == xpath_type_boolean) ? static_cast(this)->value : false; - } - - PUGI_IMPL_FN double xpath_variable::get_number() const - { - return (_type == xpath_type_number) ? static_cast(this)->value : impl::gen_nan(); - } - - PUGI_IMPL_FN const char_t* xpath_variable::get_string() const - { - const char_t* value = (_type == xpath_type_string) ? static_cast(this)->value : 0; - return value ? value : PUGIXML_TEXT(""); - } - - PUGI_IMPL_FN const xpath_node_set& xpath_variable::get_node_set() const - { - return (_type == xpath_type_node_set) ? static_cast(this)->value : impl::dummy_node_set; - } - - PUGI_IMPL_FN bool xpath_variable::set(bool value) - { - if (_type != xpath_type_boolean) return false; - - static_cast(this)->value = value; - return true; - } - - PUGI_IMPL_FN bool xpath_variable::set(double value) - { - if (_type != xpath_type_number) return false; - - static_cast(this)->value = value; - return true; - } - - PUGI_IMPL_FN bool xpath_variable::set(const char_t* value) - { - if (_type != xpath_type_string) return false; - - impl::xpath_variable_string* var = static_cast(this); - - // duplicate string - size_t size = (impl::strlength(value) + 1) * sizeof(char_t); - - char_t* copy = static_cast(impl::xml_memory::allocate(size)); - if (!copy) return false; - - memcpy(copy, value, size); - - // replace old string - if (var->value) impl::xml_memory::deallocate(var->value); - var->value = copy; - - return true; - } - - PUGI_IMPL_FN bool xpath_variable::set(const xpath_node_set& value) - { - if (_type != xpath_type_node_set) return false; - - static_cast(this)->value = value; - return true; - } - - PUGI_IMPL_FN xpath_variable_set::xpath_variable_set() - { - for (size_t i = 0; i < sizeof(_data) / sizeof(_data[0]); ++i) - _data[i] = 0; - } - - PUGI_IMPL_FN xpath_variable_set::~xpath_variable_set() - { - for (size_t i = 0; i < sizeof(_data) / sizeof(_data[0]); ++i) - _destroy(_data[i]); - } - - PUGI_IMPL_FN xpath_variable_set::xpath_variable_set(const xpath_variable_set& rhs) - { - for (size_t i = 0; i < sizeof(_data) / sizeof(_data[0]); ++i) - _data[i] = 0; - - _assign(rhs); - } - - PUGI_IMPL_FN xpath_variable_set& xpath_variable_set::operator=(const xpath_variable_set& rhs) - { - if (this == &rhs) return *this; - - _assign(rhs); - - return *this; - } - -#ifdef PUGIXML_HAS_MOVE - PUGI_IMPL_FN xpath_variable_set::xpath_variable_set(xpath_variable_set&& rhs) PUGIXML_NOEXCEPT - { - for (size_t i = 0; i < sizeof(_data) / sizeof(_data[0]); ++i) - { - _data[i] = rhs._data[i]; - rhs._data[i] = 0; - } - } - - PUGI_IMPL_FN xpath_variable_set& xpath_variable_set::operator=(xpath_variable_set&& rhs) PUGIXML_NOEXCEPT - { - for (size_t i = 0; i < sizeof(_data) / sizeof(_data[0]); ++i) - { - _destroy(_data[i]); - - _data[i] = rhs._data[i]; - rhs._data[i] = 0; - } - - return *this; - } -#endif - - PUGI_IMPL_FN void xpath_variable_set::_assign(const xpath_variable_set& rhs) - { - xpath_variable_set temp; - - for (size_t i = 0; i < sizeof(_data) / sizeof(_data[0]); ++i) - if (rhs._data[i] && !_clone(rhs._data[i], &temp._data[i])) - return; - - _swap(temp); - } - - PUGI_IMPL_FN void xpath_variable_set::_swap(xpath_variable_set& rhs) - { - for (size_t i = 0; i < sizeof(_data) / sizeof(_data[0]); ++i) - { - xpath_variable* chain = _data[i]; - - _data[i] = rhs._data[i]; - rhs._data[i] = chain; - } - } - - PUGI_IMPL_FN xpath_variable* xpath_variable_set::_find(const char_t* name) const - { - const size_t hash_size = sizeof(_data) / sizeof(_data[0]); - size_t hash = impl::hash_string(name) % hash_size; - - // look for existing variable - for (xpath_variable* var = _data[hash]; var; var = var->_next) - if (impl::strequal(var->name(), name)) - return var; - - return 0; - } - - PUGI_IMPL_FN bool xpath_variable_set::_clone(xpath_variable* var, xpath_variable** out_result) - { - xpath_variable* last = 0; - - while (var) - { - // allocate storage for new variable - xpath_variable* nvar = impl::new_xpath_variable(var->_type, var->name()); - if (!nvar) return false; - - // link the variable to the result immediately to handle failures gracefully - if (last) - last->_next = nvar; - else - *out_result = nvar; - - last = nvar; - - // copy the value; this can fail due to out-of-memory conditions - if (!impl::copy_xpath_variable(nvar, var)) return false; - - var = var->_next; - } - - return true; - } - - PUGI_IMPL_FN void xpath_variable_set::_destroy(xpath_variable* var) - { - while (var) - { - xpath_variable* next = var->_next; - - impl::delete_xpath_variable(var->_type, var); - - var = next; - } - } - - PUGI_IMPL_FN xpath_variable* xpath_variable_set::add(const char_t* name, xpath_value_type type) - { - const size_t hash_size = sizeof(_data) / sizeof(_data[0]); - size_t hash = impl::hash_string(name) % hash_size; - - // look for existing variable - for (xpath_variable* var = _data[hash]; var; var = var->_next) - if (impl::strequal(var->name(), name)) - return var->type() == type ? var : 0; - - // add new variable - xpath_variable* result = impl::new_xpath_variable(type, name); - - if (result) - { - result->_next = _data[hash]; - - _data[hash] = result; - } - - return result; - } - - PUGI_IMPL_FN bool xpath_variable_set::set(const char_t* name, bool value) - { - xpath_variable* var = add(name, xpath_type_boolean); - return var ? var->set(value) : false; - } - - PUGI_IMPL_FN bool xpath_variable_set::set(const char_t* name, double value) - { - xpath_variable* var = add(name, xpath_type_number); - return var ? var->set(value) : false; - } - - PUGI_IMPL_FN bool xpath_variable_set::set(const char_t* name, const char_t* value) - { - xpath_variable* var = add(name, xpath_type_string); - return var ? var->set(value) : false; - } - - PUGI_IMPL_FN bool xpath_variable_set::set(const char_t* name, const xpath_node_set& value) - { - xpath_variable* var = add(name, xpath_type_node_set); - return var ? var->set(value) : false; - } - - PUGI_IMPL_FN xpath_variable* xpath_variable_set::get(const char_t* name) - { - return _find(name); - } - - PUGI_IMPL_FN const xpath_variable* xpath_variable_set::get(const char_t* name) const - { - return _find(name); - } - - PUGI_IMPL_FN xpath_query::xpath_query(const char_t* query, xpath_variable_set* variables): _impl(0) - { - impl::xpath_query_impl* qimpl = impl::xpath_query_impl::create(); - - if (!qimpl) - { - #ifdef PUGIXML_NO_EXCEPTIONS - _result.error = "Out of memory"; - #else - throw std::bad_alloc(); - #endif - } - else - { - using impl::auto_deleter; // MSVC7 workaround - auto_deleter impl(qimpl, impl::xpath_query_impl::destroy); - - qimpl->root = impl::xpath_parser::parse(query, variables, &qimpl->alloc, &_result); - - if (qimpl->root) - { - qimpl->root->optimize(&qimpl->alloc); - - _impl = impl.release(); - _result.error = 0; - } - else - { - #ifdef PUGIXML_NO_EXCEPTIONS - if (qimpl->oom) _result.error = "Out of memory"; - #else - if (qimpl->oom) throw std::bad_alloc(); - throw xpath_exception(_result); - #endif - } - } - } - - PUGI_IMPL_FN xpath_query::xpath_query(): _impl(0) - { - } - - PUGI_IMPL_FN xpath_query::~xpath_query() - { - if (_impl) - impl::xpath_query_impl::destroy(static_cast(_impl)); - } - -#ifdef PUGIXML_HAS_MOVE - PUGI_IMPL_FN xpath_query::xpath_query(xpath_query&& rhs) PUGIXML_NOEXCEPT - { - _impl = rhs._impl; - _result = rhs._result; - rhs._impl = 0; - rhs._result = xpath_parse_result(); - } - - PUGI_IMPL_FN xpath_query& xpath_query::operator=(xpath_query&& rhs) PUGIXML_NOEXCEPT - { - if (this == &rhs) return *this; - - if (_impl) - impl::xpath_query_impl::destroy(static_cast(_impl)); - - _impl = rhs._impl; - _result = rhs._result; - rhs._impl = 0; - rhs._result = xpath_parse_result(); - - return *this; - } -#endif - - PUGI_IMPL_FN xpath_value_type xpath_query::return_type() const - { - if (!_impl) return xpath_type_none; - - return static_cast(_impl)->root->rettype(); - } - - PUGI_IMPL_FN bool xpath_query::evaluate_boolean(const xpath_node& n) const - { - if (!_impl) return false; - - impl::xpath_context c(n, 1, 1); - impl::xpath_stack_data sd; - - bool r = static_cast(_impl)->root->eval_boolean(c, sd.stack); - - if (sd.oom) - { - #ifdef PUGIXML_NO_EXCEPTIONS - return false; - #else - throw std::bad_alloc(); - #endif - } - - return r; - } - - PUGI_IMPL_FN double xpath_query::evaluate_number(const xpath_node& n) const - { - if (!_impl) return impl::gen_nan(); - - impl::xpath_context c(n, 1, 1); - impl::xpath_stack_data sd; - - double r = static_cast(_impl)->root->eval_number(c, sd.stack); - - if (sd.oom) - { - #ifdef PUGIXML_NO_EXCEPTIONS - return impl::gen_nan(); - #else - throw std::bad_alloc(); - #endif - } - - return r; - } - -#ifndef PUGIXML_NO_STL - PUGI_IMPL_FN string_t xpath_query::evaluate_string(const xpath_node& n) const - { - if (!_impl) return string_t(); - - impl::xpath_context c(n, 1, 1); - impl::xpath_stack_data sd; - - impl::xpath_string r = static_cast(_impl)->root->eval_string(c, sd.stack); - - if (sd.oom) - { - #ifdef PUGIXML_NO_EXCEPTIONS - return string_t(); - #else - throw std::bad_alloc(); - #endif - } - - return string_t(r.c_str(), r.length()); - } -#endif - - PUGI_IMPL_FN size_t xpath_query::evaluate_string(char_t* buffer, size_t capacity, const xpath_node& n) const - { - impl::xpath_context c(n, 1, 1); - impl::xpath_stack_data sd; - - impl::xpath_string r = _impl ? static_cast(_impl)->root->eval_string(c, sd.stack) : impl::xpath_string(); - - if (sd.oom) - { - #ifdef PUGIXML_NO_EXCEPTIONS - r = impl::xpath_string(); - #else - throw std::bad_alloc(); - #endif - } - - size_t full_size = r.length() + 1; - - if (capacity > 0) - { - size_t size = (full_size < capacity) ? full_size : capacity; - assert(size > 0); - - memcpy(buffer, r.c_str(), (size - 1) * sizeof(char_t)); - buffer[size - 1] = 0; - } - - return full_size; - } - - PUGI_IMPL_FN xpath_node_set xpath_query::evaluate_node_set(const xpath_node& n) const - { - impl::xpath_ast_node* root = impl::evaluate_node_set_prepare(static_cast(_impl)); - if (!root) return xpath_node_set(); - - impl::xpath_context c(n, 1, 1); - impl::xpath_stack_data sd; - - impl::xpath_node_set_raw r = root->eval_node_set(c, sd.stack, impl::nodeset_eval_all); - - if (sd.oom) - { - #ifdef PUGIXML_NO_EXCEPTIONS - return xpath_node_set(); - #else - throw std::bad_alloc(); - #endif - } - - return xpath_node_set(r.begin(), r.end(), r.type()); - } - - PUGI_IMPL_FN xpath_node xpath_query::evaluate_node(const xpath_node& n) const - { - impl::xpath_ast_node* root = impl::evaluate_node_set_prepare(static_cast(_impl)); - if (!root) return xpath_node(); - - impl::xpath_context c(n, 1, 1); - impl::xpath_stack_data sd; - - impl::xpath_node_set_raw r = root->eval_node_set(c, sd.stack, impl::nodeset_eval_first); - - if (sd.oom) - { - #ifdef PUGIXML_NO_EXCEPTIONS - return xpath_node(); - #else - throw std::bad_alloc(); - #endif - } - - return r.first(); - } - - PUGI_IMPL_FN const xpath_parse_result& xpath_query::result() const - { - return _result; - } - - PUGI_IMPL_FN static void unspecified_bool_xpath_query(xpath_query***) - { - } - - PUGI_IMPL_FN xpath_query::operator xpath_query::unspecified_bool_type() const - { - return _impl ? unspecified_bool_xpath_query : 0; - } - - PUGI_IMPL_FN bool xpath_query::operator!() const - { - return !_impl; - } - - PUGI_IMPL_FN xpath_node xml_node::select_node(const char_t* query, xpath_variable_set* variables) const - { - xpath_query q(query, variables); - return q.evaluate_node(*this); - } - - PUGI_IMPL_FN xpath_node xml_node::select_node(const xpath_query& query) const - { - return query.evaluate_node(*this); - } - - PUGI_IMPL_FN xpath_node_set xml_node::select_nodes(const char_t* query, xpath_variable_set* variables) const - { - xpath_query q(query, variables); - return q.evaluate_node_set(*this); - } - - PUGI_IMPL_FN xpath_node_set xml_node::select_nodes(const xpath_query& query) const - { - return query.evaluate_node_set(*this); - } - - PUGI_IMPL_FN xpath_node xml_node::select_single_node(const char_t* query, xpath_variable_set* variables) const - { - xpath_query q(query, variables); - return q.evaluate_node(*this); - } - - PUGI_IMPL_FN xpath_node xml_node::select_single_node(const xpath_query& query) const - { - return query.evaluate_node(*this); - } -} - -#endif - -#ifdef __BORLANDC__ -# pragma option pop -#endif - -// Intel C++ does not properly keep warning state for function templates, -// so popping warning state at the end of translation unit leads to warnings in the middle. -#if defined(_MSC_VER) && !defined(__INTEL_COMPILER) -# pragma warning(pop) -#endif - -#if defined(_MSC_VER) && defined(__c2__) -# pragma clang diagnostic pop -#endif - -// Undefine all local macros (makes sure we're not leaking macros in header-only mode) -#undef PUGI_IMPL_NO_INLINE -#undef PUGI_IMPL_UNLIKELY -#undef PUGI_IMPL_STATIC_ASSERT -#undef PUGI_IMPL_DMC_VOLATILE -#undef PUGI_IMPL_UNSIGNED_OVERFLOW -#undef PUGI_IMPL_MSVC_CRT_VERSION -#undef PUGI_IMPL_SNPRINTF -#undef PUGI_IMPL_NS_BEGIN -#undef PUGI_IMPL_NS_END -#undef PUGI_IMPL_FN -#undef PUGI_IMPL_FN_NO_INLINE -#undef PUGI_IMPL_GETHEADER_IMPL -#undef PUGI_IMPL_GETPAGE_IMPL -#undef PUGI_IMPL_GETPAGE -#undef PUGI_IMPL_NODETYPE -#undef PUGI_IMPL_IS_CHARTYPE_IMPL -#undef PUGI_IMPL_IS_CHARTYPE -#undef PUGI_IMPL_IS_CHARTYPEX -#undef PUGI_IMPL_ENDSWITH -#undef PUGI_IMPL_SKIPWS -#undef PUGI_IMPL_OPTSET -#undef PUGI_IMPL_PUSHNODE -#undef PUGI_IMPL_POPNODE -#undef PUGI_IMPL_SCANFOR -#undef PUGI_IMPL_SCANWHILE -#undef PUGI_IMPL_SCANWHILE_UNROLL -#undef PUGI_IMPL_ENDSEG -#undef PUGI_IMPL_THROW_ERROR -#undef PUGI_IMPL_CHECK_ERROR - -#endif - -/** - * Copyright (c) 2006-2023 Arseny Kapoulkine - * - * Permission is hereby granted, free of charge, to any person - * obtaining a copy of this software and associated documentation - * files (the "Software"), to deal in the Software without - * restriction, including without limitation the rights to use, - * copy, modify, merge, publish, distribute, sublicense, and/or sell - * copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following - * conditions: - * - * The above copyright notice and this permission notice shall be - * included in all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES - * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT - * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, - * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - */ diff -r 886f66775f31 -r 8d45d892be88 dep/pugixml/src/pugixml.hpp --- a/dep/pugixml/src/pugixml.hpp Sun Nov 17 19:56:01 2024 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,1516 +0,0 @@ -/** - * pugixml parser - version 1.14 - * -------------------------------------------------------- - * Copyright (C) 2006-2023, by Arseny Kapoulkine (arseny.kapoulkine@gmail.com) - * Report bugs and download new versions at https://pugixml.org/ - * - * This library is distributed under the MIT License. See notice at the end - * of this file. - * - * This work is based on the pugxml parser, which is: - * Copyright (C) 2003, by Kristen Wegner (kristen@tima.net) - */ - -// Define version macro; evaluates to major * 1000 + minor * 10 + patch so that it's safe to use in less-than comparisons -// Note: pugixml used major * 100 + minor * 10 + patch format up until 1.9 (which had version identifier 190); starting from pugixml 1.10, the minor version number is two digits -#ifndef PUGIXML_VERSION -# define PUGIXML_VERSION 1140 // 1.14 -#endif - -// Include user configuration file (this can define various configuration macros) -#include "pugiconfig.hpp" - -#ifndef HEADER_PUGIXML_HPP -#define HEADER_PUGIXML_HPP - -// Include stddef.h for size_t and ptrdiff_t -#include - -// Include exception header for XPath -#if !defined(PUGIXML_NO_XPATH) && !defined(PUGIXML_NO_EXCEPTIONS) -# include -#endif - -// Include STL headers -#ifndef PUGIXML_NO_STL -# include -# include -# include -#endif - -// Macro for deprecated features -#ifndef PUGIXML_DEPRECATED -# if defined(__GNUC__) -# define PUGIXML_DEPRECATED __attribute__((deprecated)) -# elif defined(_MSC_VER) && _MSC_VER >= 1300 -# define PUGIXML_DEPRECATED __declspec(deprecated) -# else -# define PUGIXML_DEPRECATED -# endif -#endif - -// If no API is defined, assume default -#ifndef PUGIXML_API -# define PUGIXML_API -#endif - -// If no API for classes is defined, assume default -#ifndef PUGIXML_CLASS -# define PUGIXML_CLASS PUGIXML_API -#endif - -// If no API for functions is defined, assume default -#ifndef PUGIXML_FUNCTION -# define PUGIXML_FUNCTION PUGIXML_API -#endif - -// If the platform is known to have long long support, enable long long functions -#ifndef PUGIXML_HAS_LONG_LONG -# if __cplusplus >= 201103 -# define PUGIXML_HAS_LONG_LONG -# elif defined(_MSC_VER) && _MSC_VER >= 1400 -# define PUGIXML_HAS_LONG_LONG -# endif -#endif - -// If the platform is known to have move semantics support, compile move ctor/operator implementation -#ifndef PUGIXML_HAS_MOVE -# if __cplusplus >= 201103 -# define PUGIXML_HAS_MOVE -# elif defined(_MSC_VER) && _MSC_VER >= 1600 -# define PUGIXML_HAS_MOVE -# endif -#endif - -// If C++ is 2011 or higher, add 'noexcept' specifiers -#ifndef PUGIXML_NOEXCEPT -# if __cplusplus >= 201103 -# define PUGIXML_NOEXCEPT noexcept -# elif defined(_MSC_VER) && _MSC_VER >= 1900 -# define PUGIXML_NOEXCEPT noexcept -# else -# define PUGIXML_NOEXCEPT -# endif -#endif - -// Some functions can not be noexcept in compact mode -#ifdef PUGIXML_COMPACT -# define PUGIXML_NOEXCEPT_IF_NOT_COMPACT -#else -# define PUGIXML_NOEXCEPT_IF_NOT_COMPACT PUGIXML_NOEXCEPT -#endif - -// If C++ is 2011 or higher, add 'override' qualifiers -#ifndef PUGIXML_OVERRIDE -# if __cplusplus >= 201103 -# define PUGIXML_OVERRIDE override -# elif defined(_MSC_VER) && _MSC_VER >= 1700 -# define PUGIXML_OVERRIDE override -# else -# define PUGIXML_OVERRIDE -# endif -#endif - -// If C++ is 2011 or higher, use 'nullptr' -#ifndef PUGIXML_NULL -# if __cplusplus >= 201103 -# define PUGIXML_NULL nullptr -# elif defined(_MSC_VER) && _MSC_VER >= 1600 -# define PUGIXML_NULL nullptr -# else -# define PUGIXML_NULL 0 -# endif -#endif - -// Character interface macros -#ifdef PUGIXML_WCHAR_MODE -# define PUGIXML_TEXT(t) L ## t -# define PUGIXML_CHAR wchar_t -#else -# define PUGIXML_TEXT(t) t -# define PUGIXML_CHAR char -#endif - -namespace pugi -{ - // Character type used for all internal storage and operations; depends on PUGIXML_WCHAR_MODE - typedef PUGIXML_CHAR char_t; - -#ifndef PUGIXML_NO_STL - // String type used for operations that work with STL string; depends on PUGIXML_WCHAR_MODE - typedef std::basic_string, std::allocator > string_t; -#endif -} - -// The PugiXML namespace -namespace pugi -{ - // Tree node types - enum xml_node_type - { - node_null, // Empty (null) node handle - node_document, // A document tree's absolute root - node_element, // Element tag, i.e. '' - node_pcdata, // Plain character data, i.e. 'text' - node_cdata, // Character data, i.e. '' - node_comment, // Comment tag, i.e. '' - node_pi, // Processing instruction, i.e. '' - node_declaration, // Document declaration, i.e. '' - node_doctype // Document type declaration, i.e. '' - }; - - // Parsing options - - // Minimal parsing mode (equivalent to turning all other flags off). - // Only elements and PCDATA sections are added to the DOM tree, no text conversions are performed. - const unsigned int parse_minimal = 0x0000; - - // This flag determines if processing instructions (node_pi) are added to the DOM tree. This flag is off by default. - const unsigned int parse_pi = 0x0001; - - // This flag determines if comments (node_comment) are added to the DOM tree. This flag is off by default. - const unsigned int parse_comments = 0x0002; - - // This flag determines if CDATA sections (node_cdata) are added to the DOM tree. This flag is on by default. - const unsigned int parse_cdata = 0x0004; - - // This flag determines if plain character data (node_pcdata) that consist only of whitespace are added to the DOM tree. - // This flag is off by default; turning it on usually results in slower parsing and more memory consumption. - const unsigned int parse_ws_pcdata = 0x0008; - - // This flag determines if character and entity references are expanded during parsing. This flag is on by default. - const unsigned int parse_escapes = 0x0010; - - // This flag determines if EOL characters are normalized (converted to #xA) during parsing. This flag is on by default. - const unsigned int parse_eol = 0x0020; - - // This flag determines if attribute values are normalized using CDATA normalization rules during parsing. This flag is on by default. - const unsigned int parse_wconv_attribute = 0x0040; - - // This flag determines if attribute values are normalized using NMTOKENS normalization rules during parsing. This flag is off by default. - const unsigned int parse_wnorm_attribute = 0x0080; - - // This flag determines if document declaration (node_declaration) is added to the DOM tree. This flag is off by default. - const unsigned int parse_declaration = 0x0100; - - // This flag determines if document type declaration (node_doctype) is added to the DOM tree. This flag is off by default. - const unsigned int parse_doctype = 0x0200; - - // This flag determines if plain character data (node_pcdata) that is the only child of the parent node and that consists only - // of whitespace is added to the DOM tree. - // This flag is off by default; turning it on may result in slower parsing and more memory consumption. - const unsigned int parse_ws_pcdata_single = 0x0400; - - // This flag determines if leading and trailing whitespace is to be removed from plain character data. This flag is off by default. - const unsigned int parse_trim_pcdata = 0x0800; - - // This flag determines if plain character data that does not have a parent node is added to the DOM tree, and if an empty document - // is a valid document. This flag is off by default. - const unsigned int parse_fragment = 0x1000; - - // This flag determines if plain character data is be stored in the parent element's value. This significantly changes the structure of - // the document; this flag is only recommended for parsing documents with many PCDATA nodes in memory-constrained environments. - // This flag is off by default. - const unsigned int parse_embed_pcdata = 0x2000; - - // This flag determines whether determines whether the the two pcdata should be merged or not, if no intermediatory data are parsed in the document. - // This flag is off by default. - const unsigned int parse_merge_pcdata = 0x4000; - - // The default parsing mode. - // Elements, PCDATA and CDATA sections are added to the DOM tree, character/reference entities are expanded, - // End-of-Line characters are normalized, attribute values are normalized using CDATA normalization rules. - const unsigned int parse_default = parse_cdata | parse_escapes | parse_wconv_attribute | parse_eol; - - // The full parsing mode. - // Nodes of all types are added to the DOM tree, character/reference entities are expanded, - // End-of-Line characters are normalized, attribute values are normalized using CDATA normalization rules. - const unsigned int parse_full = parse_default | parse_pi | parse_comments | parse_declaration | parse_doctype; - - // These flags determine the encoding of input data for XML document - enum xml_encoding - { - encoding_auto, // Auto-detect input encoding using BOM or < / class xml_object_range - { - public: - typedef It const_iterator; - typedef It iterator; - - xml_object_range(It b, It e): _begin(b), _end(e) - { - } - - It begin() const { return _begin; } - It end() const { return _end; } - - bool empty() const { return _begin == _end; } - - private: - It _begin, _end; - }; - - // Writer interface for node printing (see xml_node::print) - class PUGIXML_CLASS xml_writer - { - public: - virtual ~xml_writer(); - - // Write memory chunk into stream/file/whatever - virtual void write(const void* data, size_t size) = 0; - }; - - // xml_writer implementation for FILE* - class PUGIXML_CLASS xml_writer_file: public xml_writer - { - public: - // Construct writer from a FILE* object; void* is used to avoid header dependencies on stdio - xml_writer_file(void* file); - - virtual void write(const void* data, size_t size) PUGIXML_OVERRIDE; - - private: - void* file; - }; - - #ifndef PUGIXML_NO_STL - // xml_writer implementation for streams - class PUGIXML_CLASS xml_writer_stream: public xml_writer - { - public: - // Construct writer from an output stream object - xml_writer_stream(std::basic_ostream >& stream); - xml_writer_stream(std::basic_ostream >& stream); - - virtual void write(const void* data, size_t size) PUGIXML_OVERRIDE; - - private: - std::basic_ostream >* narrow_stream; - std::basic_ostream >* wide_stream; - }; - #endif - - // A light-weight handle for manipulating attributes in DOM tree - class PUGIXML_CLASS xml_attribute - { - friend class xml_attribute_iterator; - friend class xml_node; - - private: - xml_attribute_struct* _attr; - - typedef void (*unspecified_bool_type)(xml_attribute***); - - public: - // Default constructor. Constructs an empty attribute. - xml_attribute(); - - // Constructs attribute from internal pointer - explicit xml_attribute(xml_attribute_struct* attr); - - // Safe bool conversion operator - operator unspecified_bool_type() const; - - // Borland C++ workaround - bool operator!() const; - - // Comparison operators (compares wrapped attribute pointers) - bool operator==(const xml_attribute& r) const; - bool operator!=(const xml_attribute& r) const; - bool operator<(const xml_attribute& r) const; - bool operator>(const xml_attribute& r) const; - bool operator<=(const xml_attribute& r) const; - bool operator>=(const xml_attribute& r) const; - - // Check if attribute is empty - bool empty() const; - - // Get attribute name/value, or "" if attribute is empty - const char_t* name() const; - const char_t* value() const; - - // Get attribute value, or the default value if attribute is empty - const char_t* as_string(const char_t* def = PUGIXML_TEXT("")) const; - - // Get attribute value as a number, or the default value if conversion did not succeed or attribute is empty - int as_int(int def = 0) const; - unsigned int as_uint(unsigned int def = 0) const; - double as_double(double def = 0) const; - float as_float(float def = 0) const; - - #ifdef PUGIXML_HAS_LONG_LONG - long long as_llong(long long def = 0) const; - unsigned long long as_ullong(unsigned long long def = 0) const; - #endif - - // Get attribute value as bool (returns true if first character is in '1tTyY' set), or the default value if attribute is empty - bool as_bool(bool def = false) const; - - // Set attribute name/value (returns false if attribute is empty or there is not enough memory) - bool set_name(const char_t* rhs); - bool set_name(const char_t* rhs, size_t size); - bool set_value(const char_t* rhs); - bool set_value(const char_t* rhs, size_t size); - - // Set attribute value with type conversion (numbers are converted to strings, boolean is converted to "true"/"false") - bool set_value(int rhs); - bool set_value(unsigned int rhs); - bool set_value(long rhs); - bool set_value(unsigned long rhs); - bool set_value(double rhs); - bool set_value(double rhs, int precision); - bool set_value(float rhs); - bool set_value(float rhs, int precision); - bool set_value(bool rhs); - - #ifdef PUGIXML_HAS_LONG_LONG - bool set_value(long long rhs); - bool set_value(unsigned long long rhs); - #endif - - // Set attribute value (equivalent to set_value without error checking) - xml_attribute& operator=(const char_t* rhs); - xml_attribute& operator=(int rhs); - xml_attribute& operator=(unsigned int rhs); - xml_attribute& operator=(long rhs); - xml_attribute& operator=(unsigned long rhs); - xml_attribute& operator=(double rhs); - xml_attribute& operator=(float rhs); - xml_attribute& operator=(bool rhs); - - #ifdef PUGIXML_HAS_LONG_LONG - xml_attribute& operator=(long long rhs); - xml_attribute& operator=(unsigned long long rhs); - #endif - - // Get next/previous attribute in the attribute list of the parent node - xml_attribute next_attribute() const; - xml_attribute previous_attribute() const; - - // Get hash value (unique for handles to the same object) - size_t hash_value() const; - - // Get internal pointer - xml_attribute_struct* internal_object() const; - }; - -#ifdef __BORLANDC__ - // Borland C++ workaround - bool PUGIXML_FUNCTION operator&&(const xml_attribute& lhs, bool rhs); - bool PUGIXML_FUNCTION operator||(const xml_attribute& lhs, bool rhs); -#endif - - // A light-weight handle for manipulating nodes in DOM tree - class PUGIXML_CLASS xml_node - { - friend class xml_attribute_iterator; - friend class xml_node_iterator; - friend class xml_named_node_iterator; - - protected: - xml_node_struct* _root; - - typedef void (*unspecified_bool_type)(xml_node***); - - public: - // Default constructor. Constructs an empty node. - xml_node(); - - // Constructs node from internal pointer - explicit xml_node(xml_node_struct* p); - - // Safe bool conversion operator - operator unspecified_bool_type() const; - - // Borland C++ workaround - bool operator!() const; - - // Comparison operators (compares wrapped node pointers) - bool operator==(const xml_node& r) const; - bool operator!=(const xml_node& r) const; - bool operator<(const xml_node& r) const; - bool operator>(const xml_node& r) const; - bool operator<=(const xml_node& r) const; - bool operator>=(const xml_node& r) const; - - // Check if node is empty. - bool empty() const; - - // Get node type - xml_node_type type() const; - - // Get node name, or "" if node is empty or it has no name - const char_t* name() const; - - // Get node value, or "" if node is empty or it has no value - // Note: For text node.value() does not return "text"! Use child_value() or text() methods to access text inside nodes. - const char_t* value() const; - - // Get attribute list - xml_attribute first_attribute() const; - xml_attribute last_attribute() const; - - // Get children list - xml_node first_child() const; - xml_node last_child() const; - - // Get next/previous sibling in the children list of the parent node - xml_node next_sibling() const; - xml_node previous_sibling() const; - - // Get parent node - xml_node parent() const; - - // Get root of DOM tree this node belongs to - xml_node root() const; - - // Get text object for the current node - xml_text text() const; - - // Get child, attribute or next/previous sibling with the specified name - xml_node child(const char_t* name) const; - xml_attribute attribute(const char_t* name) const; - xml_node next_sibling(const char_t* name) const; - xml_node previous_sibling(const char_t* name) const; - - // Get attribute, starting the search from a hint (and updating hint so that searching for a sequence of attributes is fast) - xml_attribute attribute(const char_t* name, xml_attribute& hint) const; - - // Get child value of current node; that is, value of the first child node of type PCDATA/CDATA - const char_t* child_value() const; - - // Get child value of child with specified name. Equivalent to child(name).child_value(). - const char_t* child_value(const char_t* name) const; - - // Set node name/value (returns false if node is empty, there is not enough memory, or node can not have name/value) - bool set_name(const char_t* rhs); - bool set_name(const char_t* rhs, size_t size); - bool set_value(const char_t* rhs); - bool set_value(const char_t* rhs, size_t size); - - // Add attribute with specified name. Returns added attribute, or empty attribute on errors. - xml_attribute append_attribute(const char_t* name); - xml_attribute prepend_attribute(const char_t* name); - xml_attribute insert_attribute_after(const char_t* name, const xml_attribute& attr); - xml_attribute insert_attribute_before(const char_t* name, const xml_attribute& attr); - - // Add a copy of the specified attribute. Returns added attribute, or empty attribute on errors. - xml_attribute append_copy(const xml_attribute& proto); - xml_attribute prepend_copy(const xml_attribute& proto); - xml_attribute insert_copy_after(const xml_attribute& proto, const xml_attribute& attr); - xml_attribute insert_copy_before(const xml_attribute& proto, const xml_attribute& attr); - - // Add child node with specified type. Returns added node, or empty node on errors. - xml_node append_child(xml_node_type type = node_element); - xml_node prepend_child(xml_node_type type = node_element); - xml_node insert_child_after(xml_node_type type, const xml_node& node); - xml_node insert_child_before(xml_node_type type, const xml_node& node); - - // Add child element with specified name. Returns added node, or empty node on errors. - xml_node append_child(const char_t* name); - xml_node prepend_child(const char_t* name); - xml_node insert_child_after(const char_t* name, const xml_node& node); - xml_node insert_child_before(const char_t* name, const xml_node& node); - - // Add a copy of the specified node as a child. Returns added node, or empty node on errors. - xml_node append_copy(const xml_node& proto); - xml_node prepend_copy(const xml_node& proto); - xml_node insert_copy_after(const xml_node& proto, const xml_node& node); - xml_node insert_copy_before(const xml_node& proto, const xml_node& node); - - // Move the specified node to become a child of this node. Returns moved node, or empty node on errors. - xml_node append_move(const xml_node& moved); - xml_node prepend_move(const xml_node& moved); - xml_node insert_move_after(const xml_node& moved, const xml_node& node); - xml_node insert_move_before(const xml_node& moved, const xml_node& node); - - // Remove specified attribute - bool remove_attribute(const xml_attribute& a); - bool remove_attribute(const char_t* name); - - // Remove all attributes - bool remove_attributes(); - - // Remove specified child - bool remove_child(const xml_node& n); - bool remove_child(const char_t* name); - - // Remove all children - bool remove_children(); - - // Parses buffer as an XML document fragment and appends all nodes as children of the current node. - // Copies/converts the buffer, so it may be deleted or changed after the function returns. - // Note: append_buffer allocates memory that has the lifetime of the owning document; removing the appended nodes does not immediately reclaim that memory. - xml_parse_result append_buffer(const void* contents, size_t size, unsigned int options = parse_default, xml_encoding encoding = encoding_auto); - - // Find attribute using predicate. Returns first attribute for which predicate returned true. - template xml_attribute find_attribute(Predicate pred) const - { - if (!_root) return xml_attribute(); - - for (xml_attribute attrib = first_attribute(); attrib; attrib = attrib.next_attribute()) - if (pred(attrib)) - return attrib; - - return xml_attribute(); - } - - // Find child node using predicate. Returns first child for which predicate returned true. - template xml_node find_child(Predicate pred) const - { - if (!_root) return xml_node(); - - for (xml_node node = first_child(); node; node = node.next_sibling()) - if (pred(node)) - return node; - - return xml_node(); - } - - // Find node from subtree using predicate. Returns first node from subtree (depth-first), for which predicate returned true. - template xml_node find_node(Predicate pred) const - { - if (!_root) return xml_node(); - - xml_node cur = first_child(); - - while (cur._root && cur._root != _root) - { - if (pred(cur)) return cur; - - if (cur.first_child()) cur = cur.first_child(); - else if (cur.next_sibling()) cur = cur.next_sibling(); - else - { - while (!cur.next_sibling() && cur._root != _root) cur = cur.parent(); - - if (cur._root != _root) cur = cur.next_sibling(); - } - } - - return xml_node(); - } - - // Find child node by attribute name/value - xml_node find_child_by_attribute(const char_t* name, const char_t* attr_name, const char_t* attr_value) const; - xml_node find_child_by_attribute(const char_t* attr_name, const char_t* attr_value) const; - - #ifndef PUGIXML_NO_STL - // Get the absolute node path from root as a text string. - string_t path(char_t delimiter = '/') const; - #endif - - // Search for a node by path consisting of node names and . or .. elements. - xml_node first_element_by_path(const char_t* path, char_t delimiter = '/') const; - - // Recursively traverse subtree with xml_tree_walker - bool traverse(xml_tree_walker& walker); - - #ifndef PUGIXML_NO_XPATH - // Select single node by evaluating XPath query. Returns first node from the resulting node set. - xpath_node select_node(const char_t* query, xpath_variable_set* variables = PUGIXML_NULL) const; - xpath_node select_node(const xpath_query& query) const; - - // Select node set by evaluating XPath query - xpath_node_set select_nodes(const char_t* query, xpath_variable_set* variables = PUGIXML_NULL) const; - xpath_node_set select_nodes(const xpath_query& query) const; - - // (deprecated: use select_node instead) Select single node by evaluating XPath query. - PUGIXML_DEPRECATED xpath_node select_single_node(const char_t* query, xpath_variable_set* variables = PUGIXML_NULL) const; - PUGIXML_DEPRECATED xpath_node select_single_node(const xpath_query& query) const; - - #endif - - // Print subtree using a writer object - void print(xml_writer& writer, const char_t* indent = PUGIXML_TEXT("\t"), unsigned int flags = format_default, xml_encoding encoding = encoding_auto, unsigned int depth = 0) const; - - #ifndef PUGIXML_NO_STL - // Print subtree to stream - void print(std::basic_ostream >& os, const char_t* indent = PUGIXML_TEXT("\t"), unsigned int flags = format_default, xml_encoding encoding = encoding_auto, unsigned int depth = 0) const; - void print(std::basic_ostream >& os, const char_t* indent = PUGIXML_TEXT("\t"), unsigned int flags = format_default, unsigned int depth = 0) const; - #endif - - // Child nodes iterators - typedef xml_node_iterator iterator; - - iterator begin() const; - iterator end() const; - - // Attribute iterators - typedef xml_attribute_iterator attribute_iterator; - - attribute_iterator attributes_begin() const; - attribute_iterator attributes_end() const; - - // Range-based for support - xml_object_range children() const; - xml_object_range attributes() const; - - // Range-based for support for all children with the specified name - // Note: name pointer must have a longer lifetime than the returned object; be careful with passing temporaries! - xml_object_range children(const char_t* name) const; - - // Get node offset in parsed file/string (in char_t units) for debugging purposes - ptrdiff_t offset_debug() const; - - // Get hash value (unique for handles to the same object) - size_t hash_value() const; - - // Get internal pointer - xml_node_struct* internal_object() const; - }; - -#ifdef __BORLANDC__ - // Borland C++ workaround - bool PUGIXML_FUNCTION operator&&(const xml_node& lhs, bool rhs); - bool PUGIXML_FUNCTION operator||(const xml_node& lhs, bool rhs); -#endif - - // A helper for working with text inside PCDATA nodes - class PUGIXML_CLASS xml_text - { - friend class xml_node; - - xml_node_struct* _root; - - typedef void (*unspecified_bool_type)(xml_text***); - - explicit xml_text(xml_node_struct* root); - - xml_node_struct* _data_new(); - xml_node_struct* _data() const; - - public: - // Default constructor. Constructs an empty object. - xml_text(); - - // Safe bool conversion operator - operator unspecified_bool_type() const; - - // Borland C++ workaround - bool operator!() const; - - // Check if text object is empty - bool empty() const; - - // Get text, or "" if object is empty - const char_t* get() const; - - // Get text, or the default value if object is empty - const char_t* as_string(const char_t* def = PUGIXML_TEXT("")) const; - - // Get text as a number, or the default value if conversion did not succeed or object is empty - int as_int(int def = 0) const; - unsigned int as_uint(unsigned int def = 0) const; - double as_double(double def = 0) const; - float as_float(float def = 0) const; - - #ifdef PUGIXML_HAS_LONG_LONG - long long as_llong(long long def = 0) const; - unsigned long long as_ullong(unsigned long long def = 0) const; - #endif - - // Get text as bool (returns true if first character is in '1tTyY' set), or the default value if object is empty - bool as_bool(bool def = false) const; - - // Set text (returns false if object is empty or there is not enough memory) - bool set(const char_t* rhs); - bool set(const char_t* rhs, size_t size); - - // Set text with type conversion (numbers are converted to strings, boolean is converted to "true"/"false") - bool set(int rhs); - bool set(unsigned int rhs); - bool set(long rhs); - bool set(unsigned long rhs); - bool set(double rhs); - bool set(double rhs, int precision); - bool set(float rhs); - bool set(float rhs, int precision); - bool set(bool rhs); - - #ifdef PUGIXML_HAS_LONG_LONG - bool set(long long rhs); - bool set(unsigned long long rhs); - #endif - - // Set text (equivalent to set without error checking) - xml_text& operator=(const char_t* rhs); - xml_text& operator=(int rhs); - xml_text& operator=(unsigned int rhs); - xml_text& operator=(long rhs); - xml_text& operator=(unsigned long rhs); - xml_text& operator=(double rhs); - xml_text& operator=(float rhs); - xml_text& operator=(bool rhs); - - #ifdef PUGIXML_HAS_LONG_LONG - xml_text& operator=(long long rhs); - xml_text& operator=(unsigned long long rhs); - #endif - - // Get the data node (node_pcdata or node_cdata) for this object - xml_node data() const; - }; - -#ifdef __BORLANDC__ - // Borland C++ workaround - bool PUGIXML_FUNCTION operator&&(const xml_text& lhs, bool rhs); - bool PUGIXML_FUNCTION operator||(const xml_text& lhs, bool rhs); -#endif - - // Child node iterator (a bidirectional iterator over a collection of xml_node) - class PUGIXML_CLASS xml_node_iterator - { - friend class xml_node; - - private: - mutable xml_node _wrap; - xml_node _parent; - - xml_node_iterator(xml_node_struct* ref, xml_node_struct* parent); - - public: - // Iterator traits - typedef ptrdiff_t difference_type; - typedef xml_node value_type; - typedef xml_node* pointer; - typedef xml_node& reference; - - #ifndef PUGIXML_NO_STL - typedef std::bidirectional_iterator_tag iterator_category; - #endif - - // Default constructor - xml_node_iterator(); - - // Construct an iterator which points to the specified node - xml_node_iterator(const xml_node& node); - - // Iterator operators - bool operator==(const xml_node_iterator& rhs) const; - bool operator!=(const xml_node_iterator& rhs) const; - - xml_node& operator*() const; - xml_node* operator->() const; - - xml_node_iterator& operator++(); - xml_node_iterator operator++(int); - - xml_node_iterator& operator--(); - xml_node_iterator operator--(int); - }; - - // Attribute iterator (a bidirectional iterator over a collection of xml_attribute) - class PUGIXML_CLASS xml_attribute_iterator - { - friend class xml_node; - - private: - mutable xml_attribute _wrap; - xml_node _parent; - - xml_attribute_iterator(xml_attribute_struct* ref, xml_node_struct* parent); - - public: - // Iterator traits - typedef ptrdiff_t difference_type; - typedef xml_attribute value_type; - typedef xml_attribute* pointer; - typedef xml_attribute& reference; - - #ifndef PUGIXML_NO_STL - typedef std::bidirectional_iterator_tag iterator_category; - #endif - - // Default constructor - xml_attribute_iterator(); - - // Construct an iterator which points to the specified attribute - xml_attribute_iterator(const xml_attribute& attr, const xml_node& parent); - - // Iterator operators - bool operator==(const xml_attribute_iterator& rhs) const; - bool operator!=(const xml_attribute_iterator& rhs) const; - - xml_attribute& operator*() const; - xml_attribute* operator->() const; - - xml_attribute_iterator& operator++(); - xml_attribute_iterator operator++(int); - - xml_attribute_iterator& operator--(); - xml_attribute_iterator operator--(int); - }; - - // Named node range helper - class PUGIXML_CLASS xml_named_node_iterator - { - friend class xml_node; - - public: - // Iterator traits - typedef ptrdiff_t difference_type; - typedef xml_node value_type; - typedef xml_node* pointer; - typedef xml_node& reference; - - #ifndef PUGIXML_NO_STL - typedef std::bidirectional_iterator_tag iterator_category; - #endif - - // Default constructor - xml_named_node_iterator(); - - // Construct an iterator which points to the specified node - // Note: name pointer is stored in the iterator and must have a longer lifetime than iterator itself - xml_named_node_iterator(const xml_node& node, const char_t* name); - - // Iterator operators - bool operator==(const xml_named_node_iterator& rhs) const; - bool operator!=(const xml_named_node_iterator& rhs) const; - - xml_node& operator*() const; - xml_node* operator->() const; - - xml_named_node_iterator& operator++(); - xml_named_node_iterator operator++(int); - - xml_named_node_iterator& operator--(); - xml_named_node_iterator operator--(int); - - private: - mutable xml_node _wrap; - xml_node _parent; - const char_t* _name; - - xml_named_node_iterator(xml_node_struct* ref, xml_node_struct* parent, const char_t* name); - }; - - // Abstract tree walker class (see xml_node::traverse) - class PUGIXML_CLASS xml_tree_walker - { - friend class xml_node; - - private: - int _depth; - - protected: - // Get current traversal depth - int depth() const; - - public: - xml_tree_walker(); - virtual ~xml_tree_walker(); - - // Callback that is called when traversal begins - virtual bool begin(xml_node& node); - - // Callback that is called for each node traversed - virtual bool for_each(xml_node& node) = 0; - - // Callback that is called when traversal ends - virtual bool end(xml_node& node); - }; - - // Parsing status, returned as part of xml_parse_result object - enum xml_parse_status - { - status_ok = 0, // No error - - status_file_not_found, // File was not found during load_file() - status_io_error, // Error reading from file/stream - status_out_of_memory, // Could not allocate memory - status_internal_error, // Internal error occurred - - status_unrecognized_tag, // Parser could not determine tag type - - status_bad_pi, // Parsing error occurred while parsing document declaration/processing instruction - status_bad_comment, // Parsing error occurred while parsing comment - status_bad_cdata, // Parsing error occurred while parsing CDATA section - status_bad_doctype, // Parsing error occurred while parsing document type declaration - status_bad_pcdata, // Parsing error occurred while parsing PCDATA section - status_bad_start_element, // Parsing error occurred while parsing start element tag - status_bad_attribute, // Parsing error occurred while parsing element attribute - status_bad_end_element, // Parsing error occurred while parsing end element tag - status_end_element_mismatch,// There was a mismatch of start-end tags (closing tag had incorrect name, some tag was not closed or there was an excessive closing tag) - - status_append_invalid_root, // Unable to append nodes since root type is not node_element or node_document (exclusive to xml_node::append_buffer) - - status_no_document_element // Parsing resulted in a document without element nodes - }; - - // Parsing result - struct PUGIXML_CLASS xml_parse_result - { - // Parsing status (see xml_parse_status) - xml_parse_status status; - - // Last parsed offset (in char_t units from start of input data) - ptrdiff_t offset; - - // Source document encoding - xml_encoding encoding; - - // Default constructor, initializes object to failed state - xml_parse_result(); - - // Cast to bool operator - operator bool() const; - - // Get error description - const char* description() const; - }; - - // Document class (DOM tree root) - class PUGIXML_CLASS xml_document: public xml_node - { - private: - char_t* _buffer; - - char _memory[192]; - - // Non-copyable semantics - xml_document(const xml_document&); - xml_document& operator=(const xml_document&); - - void _create(); - void _destroy(); - void _move(xml_document& rhs) PUGIXML_NOEXCEPT_IF_NOT_COMPACT; - - public: - // Default constructor, makes empty document - xml_document(); - - // Destructor, invalidates all node/attribute handles to this document - ~xml_document(); - - #ifdef PUGIXML_HAS_MOVE - // Move semantics support - xml_document(xml_document&& rhs) PUGIXML_NOEXCEPT_IF_NOT_COMPACT; - xml_document& operator=(xml_document&& rhs) PUGIXML_NOEXCEPT_IF_NOT_COMPACT; - #endif - - // Removes all nodes, leaving the empty document - void reset(); - - // Removes all nodes, then copies the entire contents of the specified document - void reset(const xml_document& proto); - - #ifndef PUGIXML_NO_STL - // Load document from stream. - xml_parse_result load(std::basic_istream >& stream, unsigned int options = parse_default, xml_encoding encoding = encoding_auto); - xml_parse_result load(std::basic_istream >& stream, unsigned int options = parse_default); - #endif - - // (deprecated: use load_string instead) Load document from zero-terminated string. No encoding conversions are applied. - PUGIXML_DEPRECATED xml_parse_result load(const char_t* contents, unsigned int options = parse_default); - - // Load document from zero-terminated string. No encoding conversions are applied. - xml_parse_result load_string(const char_t* contents, unsigned int options = parse_default); - - // Load document from file - xml_parse_result load_file(const char* path, unsigned int options = parse_default, xml_encoding encoding = encoding_auto); - xml_parse_result load_file(const wchar_t* path, unsigned int options = parse_default, xml_encoding encoding = encoding_auto); - - // Load document from buffer. Copies/converts the buffer, so it may be deleted or changed after the function returns. - xml_parse_result load_buffer(const void* contents, size_t size, unsigned int options = parse_default, xml_encoding encoding = encoding_auto); - - // Load document from buffer, using the buffer for in-place parsing (the buffer is modified and used for storage of document data). - // You should ensure that buffer data will persist throughout the document's lifetime, and free the buffer memory manually once document is destroyed. - xml_parse_result load_buffer_inplace(void* contents, size_t size, unsigned int options = parse_default, xml_encoding encoding = encoding_auto); - - // Load document from buffer, using the buffer for in-place parsing (the buffer is modified and used for storage of document data). - // You should allocate the buffer with pugixml allocation function; document will free the buffer when it is no longer needed (you can't use it anymore). - xml_parse_result load_buffer_inplace_own(void* contents, size_t size, unsigned int options = parse_default, xml_encoding encoding = encoding_auto); - - // Save XML document to writer (semantics is slightly different from xml_node::print, see documentation for details). - void save(xml_writer& writer, const char_t* indent = PUGIXML_TEXT("\t"), unsigned int flags = format_default, xml_encoding encoding = encoding_auto) const; - - #ifndef PUGIXML_NO_STL - // Save XML document to stream (semantics is slightly different from xml_node::print, see documentation for details). - void save(std::basic_ostream >& stream, const char_t* indent = PUGIXML_TEXT("\t"), unsigned int flags = format_default, xml_encoding encoding = encoding_auto) const; - void save(std::basic_ostream >& stream, const char_t* indent = PUGIXML_TEXT("\t"), unsigned int flags = format_default) const; - #endif - - // Save XML to file - bool save_file(const char* path, const char_t* indent = PUGIXML_TEXT("\t"), unsigned int flags = format_default, xml_encoding encoding = encoding_auto) const; - bool save_file(const wchar_t* path, const char_t* indent = PUGIXML_TEXT("\t"), unsigned int flags = format_default, xml_encoding encoding = encoding_auto) const; - - // Get document element - xml_node document_element() const; - }; - -#ifndef PUGIXML_NO_XPATH - // XPath query return type - enum xpath_value_type - { - xpath_type_none, // Unknown type (query failed to compile) - xpath_type_node_set, // Node set (xpath_node_set) - xpath_type_number, // Number - xpath_type_string, // String - xpath_type_boolean // Boolean - }; - - // XPath parsing result - struct PUGIXML_CLASS xpath_parse_result - { - // Error message (0 if no error) - const char* error; - - // Last parsed offset (in char_t units from string start) - ptrdiff_t offset; - - // Default constructor, initializes object to failed state - xpath_parse_result(); - - // Cast to bool operator - operator bool() const; - - // Get error description - const char* description() const; - }; - - // A single XPath variable - class PUGIXML_CLASS xpath_variable - { - friend class xpath_variable_set; - - protected: - xpath_value_type _type; - xpath_variable* _next; - - xpath_variable(xpath_value_type type); - - // Non-copyable semantics - xpath_variable(const xpath_variable&); - xpath_variable& operator=(const xpath_variable&); - - public: - // Get variable name - const char_t* name() const; - - // Get variable type - xpath_value_type type() const; - - // Get variable value; no type conversion is performed, default value (false, NaN, empty string, empty node set) is returned on type mismatch error - bool get_boolean() const; - double get_number() const; - const char_t* get_string() const; - const xpath_node_set& get_node_set() const; - - // Set variable value; no type conversion is performed, false is returned on type mismatch error - bool set(bool value); - bool set(double value); - bool set(const char_t* value); - bool set(const xpath_node_set& value); - }; - - // A set of XPath variables - class PUGIXML_CLASS xpath_variable_set - { - private: - xpath_variable* _data[64]; - - void _assign(const xpath_variable_set& rhs); - void _swap(xpath_variable_set& rhs); - - xpath_variable* _find(const char_t* name) const; - - static bool _clone(xpath_variable* var, xpath_variable** out_result); - static void _destroy(xpath_variable* var); - - public: - // Default constructor/destructor - xpath_variable_set(); - ~xpath_variable_set(); - - // Copy constructor/assignment operator - xpath_variable_set(const xpath_variable_set& rhs); - xpath_variable_set& operator=(const xpath_variable_set& rhs); - - #ifdef PUGIXML_HAS_MOVE - // Move semantics support - xpath_variable_set(xpath_variable_set&& rhs) PUGIXML_NOEXCEPT; - xpath_variable_set& operator=(xpath_variable_set&& rhs) PUGIXML_NOEXCEPT; - #endif - - // Add a new variable or get the existing one, if the types match - xpath_variable* add(const char_t* name, xpath_value_type type); - - // Set value of an existing variable; no type conversion is performed, false is returned if there is no such variable or if types mismatch - bool set(const char_t* name, bool value); - bool set(const char_t* name, double value); - bool set(const char_t* name, const char_t* value); - bool set(const char_t* name, const xpath_node_set& value); - - // Get existing variable by name - xpath_variable* get(const char_t* name); - const xpath_variable* get(const char_t* name) const; - }; - - // A compiled XPath query object - class PUGIXML_CLASS xpath_query - { - private: - void* _impl; - xpath_parse_result _result; - - typedef void (*unspecified_bool_type)(xpath_query***); - - // Non-copyable semantics - xpath_query(const xpath_query&); - xpath_query& operator=(const xpath_query&); - - public: - // Construct a compiled object from XPath expression. - // If PUGIXML_NO_EXCEPTIONS is not defined, throws xpath_exception on compilation errors. - explicit xpath_query(const char_t* query, xpath_variable_set* variables = PUGIXML_NULL); - - // Constructor - xpath_query(); - - // Destructor - ~xpath_query(); - - #ifdef PUGIXML_HAS_MOVE - // Move semantics support - xpath_query(xpath_query&& rhs) PUGIXML_NOEXCEPT; - xpath_query& operator=(xpath_query&& rhs) PUGIXML_NOEXCEPT; - #endif - - // Get query expression return type - xpath_value_type return_type() const; - - // Evaluate expression as boolean value in the specified context; performs type conversion if necessary. - // If PUGIXML_NO_EXCEPTIONS is not defined, throws std::bad_alloc on out of memory errors. - bool evaluate_boolean(const xpath_node& n) const; - - // Evaluate expression as double value in the specified context; performs type conversion if necessary. - // If PUGIXML_NO_EXCEPTIONS is not defined, throws std::bad_alloc on out of memory errors. - double evaluate_number(const xpath_node& n) const; - - #ifndef PUGIXML_NO_STL - // Evaluate expression as string value in the specified context; performs type conversion if necessary. - // If PUGIXML_NO_EXCEPTIONS is not defined, throws std::bad_alloc on out of memory errors. - string_t evaluate_string(const xpath_node& n) const; - #endif - - // Evaluate expression as string value in the specified context; performs type conversion if necessary. - // At most capacity characters are written to the destination buffer, full result size is returned (includes terminating zero). - // If PUGIXML_NO_EXCEPTIONS is not defined, throws std::bad_alloc on out of memory errors. - // If PUGIXML_NO_EXCEPTIONS is defined, returns empty set instead. - size_t evaluate_string(char_t* buffer, size_t capacity, const xpath_node& n) const; - - // Evaluate expression as node set in the specified context. - // If PUGIXML_NO_EXCEPTIONS is not defined, throws xpath_exception on type mismatch and std::bad_alloc on out of memory errors. - // If PUGIXML_NO_EXCEPTIONS is defined, returns empty node set instead. - xpath_node_set evaluate_node_set(const xpath_node& n) const; - - // Evaluate expression as node set in the specified context. - // Return first node in document order, or empty node if node set is empty. - // If PUGIXML_NO_EXCEPTIONS is not defined, throws xpath_exception on type mismatch and std::bad_alloc on out of memory errors. - // If PUGIXML_NO_EXCEPTIONS is defined, returns empty node instead. - xpath_node evaluate_node(const xpath_node& n) const; - - // Get parsing result (used to get compilation errors in PUGIXML_NO_EXCEPTIONS mode) - const xpath_parse_result& result() const; - - // Safe bool conversion operator - operator unspecified_bool_type() const; - - // Borland C++ workaround - bool operator!() const; - }; - - #ifndef PUGIXML_NO_EXCEPTIONS - #if defined(_MSC_VER) - // C4275 can be ignored in Visual C++ if you are deriving - // from a type in the Standard C++ Library - #pragma warning(push) - #pragma warning(disable: 4275) - #endif - // XPath exception class - class PUGIXML_CLASS xpath_exception: public std::exception - { - private: - xpath_parse_result _result; - - public: - // Construct exception from parse result - explicit xpath_exception(const xpath_parse_result& result); - - // Get error message - virtual const char* what() const throw() PUGIXML_OVERRIDE; - - // Get parse result - const xpath_parse_result& result() const; - }; - #if defined(_MSC_VER) - #pragma warning(pop) - #endif - #endif - - // XPath node class (either xml_node or xml_attribute) - class PUGIXML_CLASS xpath_node - { - private: - xml_node _node; - xml_attribute _attribute; - - typedef void (*unspecified_bool_type)(xpath_node***); - - public: - // Default constructor; constructs empty XPath node - xpath_node(); - - // Construct XPath node from XML node/attribute - xpath_node(const xml_node& node); - xpath_node(const xml_attribute& attribute, const xml_node& parent); - - // Get node/attribute, if any - xml_node node() const; - xml_attribute attribute() const; - - // Get parent of contained node/attribute - xml_node parent() const; - - // Safe bool conversion operator - operator unspecified_bool_type() const; - - // Borland C++ workaround - bool operator!() const; - - // Comparison operators - bool operator==(const xpath_node& n) const; - bool operator!=(const xpath_node& n) const; - }; - -#ifdef __BORLANDC__ - // Borland C++ workaround - bool PUGIXML_FUNCTION operator&&(const xpath_node& lhs, bool rhs); - bool PUGIXML_FUNCTION operator||(const xpath_node& lhs, bool rhs); -#endif - - // A fixed-size collection of XPath nodes - class PUGIXML_CLASS xpath_node_set - { - public: - // Collection type - enum type_t - { - type_unsorted, // Not ordered - type_sorted, // Sorted by document order (ascending) - type_sorted_reverse // Sorted by document order (descending) - }; - - // Constant iterator type - typedef const xpath_node* const_iterator; - - // We define non-constant iterator to be the same as constant iterator so that various generic algorithms (i.e. boost foreach) work - typedef const xpath_node* iterator; - - // Default constructor. Constructs empty set. - xpath_node_set(); - - // Constructs a set from iterator range; data is not checked for duplicates and is not sorted according to provided type, so be careful - xpath_node_set(const_iterator begin, const_iterator end, type_t type = type_unsorted); - - // Destructor - ~xpath_node_set(); - - // Copy constructor/assignment operator - xpath_node_set(const xpath_node_set& ns); - xpath_node_set& operator=(const xpath_node_set& ns); - - #ifdef PUGIXML_HAS_MOVE - // Move semantics support - xpath_node_set(xpath_node_set&& rhs) PUGIXML_NOEXCEPT; - xpath_node_set& operator=(xpath_node_set&& rhs) PUGIXML_NOEXCEPT; - #endif - - // Get collection type - type_t type() const; - - // Get collection size - size_t size() const; - - // Indexing operator - const xpath_node& operator[](size_t index) const; - - // Collection iterators - const_iterator begin() const; - const_iterator end() const; - - // Sort the collection in ascending/descending order by document order - void sort(bool reverse = false); - - // Get first node in the collection by document order - xpath_node first() const; - - // Check if collection is empty - bool empty() const; - - private: - type_t _type; - - xpath_node _storage[1]; - - xpath_node* _begin; - xpath_node* _end; - - void _assign(const_iterator begin, const_iterator end, type_t type); - void _move(xpath_node_set& rhs) PUGIXML_NOEXCEPT; - }; -#endif - -#ifndef PUGIXML_NO_STL - // Convert wide string to UTF8 - std::basic_string, std::allocator > PUGIXML_FUNCTION as_utf8(const wchar_t* str); - std::basic_string, std::allocator > PUGIXML_FUNCTION as_utf8(const std::basic_string, std::allocator >& str); - - // Convert UTF8 to wide string - std::basic_string, std::allocator > PUGIXML_FUNCTION as_wide(const char* str); - std::basic_string, std::allocator > PUGIXML_FUNCTION as_wide(const std::basic_string, std::allocator >& str); -#endif - - // Memory allocation function interface; returns pointer to allocated memory or NULL on failure - typedef void* (*allocation_function)(size_t size); - - // Memory deallocation function interface - typedef void (*deallocation_function)(void* ptr); - - // Override default memory management functions. All subsequent allocations/deallocations will be performed via supplied functions. - void PUGIXML_FUNCTION set_memory_management_functions(allocation_function allocate, deallocation_function deallocate); - - // Get current memory management functions - allocation_function PUGIXML_FUNCTION get_memory_allocation_function(); - deallocation_function PUGIXML_FUNCTION get_memory_deallocation_function(); -} - -#if !defined(PUGIXML_NO_STL) && (defined(_MSC_VER) || defined(__ICC)) -namespace std -{ - // Workarounds for (non-standard) iterator category detection for older versions (MSVC7/IC8 and earlier) - std::bidirectional_iterator_tag PUGIXML_FUNCTION _Iter_cat(const pugi::xml_node_iterator&); - std::bidirectional_iterator_tag PUGIXML_FUNCTION _Iter_cat(const pugi::xml_attribute_iterator&); - std::bidirectional_iterator_tag PUGIXML_FUNCTION _Iter_cat(const pugi::xml_named_node_iterator&); -} -#endif - -#if !defined(PUGIXML_NO_STL) && defined(__SUNPRO_CC) -namespace std -{ - // Workarounds for (non-standard) iterator category detection - std::bidirectional_iterator_tag PUGIXML_FUNCTION __iterator_category(const pugi::xml_node_iterator&); - std::bidirectional_iterator_tag PUGIXML_FUNCTION __iterator_category(const pugi::xml_attribute_iterator&); - std::bidirectional_iterator_tag PUGIXML_FUNCTION __iterator_category(const pugi::xml_named_node_iterator&); -} -#endif - -#endif - -// Make sure implementation is included in header-only mode -// Use macro expansion in #include to work around QMake (QTBUG-11923) -#if defined(PUGIXML_HEADER_ONLY) && !defined(PUGIXML_SOURCE) -# define PUGIXML_SOURCE "pugixml.cpp" -# include PUGIXML_SOURCE -#endif - -/** - * Copyright (c) 2006-2023 Arseny Kapoulkine - * - * Permission is hereby granted, free of charge, to any person - * obtaining a copy of this software and associated documentation - * files (the "Software"), to deal in the Software without - * restriction, including without limitation the rights to use, - * copy, modify, merge, publish, distribute, sublicense, and/or sell - * copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following - * conditions: - * - * The above copyright notice and this permission notice shall be - * included in all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES - * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT - * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, - * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - */ diff -r 886f66775f31 -r 8d45d892be88 rc/licenses.qrc --- a/rc/licenses.qrc Sun Nov 17 19:56:01 2024 -0500 +++ b/rc/licenses.qrc Sun Nov 17 22:55:47 2024 -0500 @@ -6,7 +6,6 @@ ../dep/anitomy/LICENSE ../dep/fmt/LICENSE ../dep/json/LICENSE - ../dep/pugixml/LICENSE ../dep/semver/LICENSE ../dep/toml11/LICENSE ../dep/utf8proc/LICENSE.md diff -r 886f66775f31 -r 8d45d892be88 scripts/osx/deploy_build.sh --- a/scripts/osx/deploy_build.sh Sun Nov 17 19:56:01 2024 -0500 +++ b/scripts/osx/deploy_build.sh Sun Nov 17 22:55:47 2024 -0500 @@ -24,7 +24,7 @@ macdeployqt "$BUNDLE_NAME.app" -no-strip if $FRAMEWORK_MODE; then - for i in QtCore QtGui QtWidgets; do + for i in QtCore QtGui QtWidgets QtXml; do install_name_tool -id @executable_path/../Frameworks/$i.framework/Versions/5/$i $BUNDLE_NAME.app/Contents/Frameworks/$i.framework/Versions/5/$i install_name_tool -change @rpath/$i.framework/Versions/5/$i @executable_path/../Frameworks/$i.framework/Versions/5/$i $BUNDLE_NAME.app/Contents/MacOS/minori done diff -r 886f66775f31 -r 8d45d892be88 src/gui/dialog/about.cc --- a/src/gui/dialog/about.cc Sun Nov 17 19:56:01 2024 -0500 +++ b/src/gui/dialog/about.cc Sun Nov 17 22:55:47 2024 -0500 @@ -5,10 +5,8 @@ #include "core/strings.h" #include "gui/widgets/text.h" -#include "pugixml.hpp" - #include "utf8proc.h" - +#include #include #include @@ -30,11 +28,10 @@ } static constexpr semver::version fmt_version{FMT_VERSION / 10000, FMT_VERSION / 100 % 100, FMT_VERSION % 100}; -static constexpr semver::version pugixml_version{PUGIXML_VERSION / 1000 % 10, PUGIXML_VERSION / 10 % 100, - PUGIXML_VERSION % 10}; static constexpr semver::version json_version{NLOHMANN_JSON_VERSION_MAJOR, NLOHMANN_JSON_VERSION_MINOR, NLOHMANN_JSON_VERSION_PATCH}; static constexpr semver::version semver_version{SEMVER_VERSION_MAJOR, SEMVER_VERSION_MINOR, SEMVER_VERSION_PATCH}; +static constexpr semver::version toml11_version{TOML11_VERSION_MAJOR, TOML11_VERSION_MINOR, TOML11_VERSION_PATCH}; static constexpr semver::version fugue_icons_version{3, 5, 6}; const char* get_curl_version() { @@ -51,11 +48,11 @@ "Fugue Icons v{}, " "Anitomy, " "JSON for Modern C++ v{}, " - "pugixml v{}, " "semver v{}, " "utf8proc v{}, " "fmt v{}, " - "parts of Anisthesia" + "toml11 v{}, " + "and parts of Anisthesia" "

" "Special thanks:" "
    " @@ -74,7 +71,7 @@ QVBoxLayout* layout = new QVBoxLayout(this); - std::string html = fmt::format(about_template, session.version.to_string(), get_curl_version(), fugue_icons_version.to_string(), json_version.to_string(), pugixml_version.to_string(), semver_version.to_string(), utf8proc_version(), fmt_version.to_string()); + std::string html = fmt::format(about_template, session.version.to_string(), get_curl_version(), fugue_icons_version.to_string(), json_version.to_string(), semver_version.to_string(), utf8proc_version(), fmt_version.to_string(), toml11_version.to_string()); setBackgroundRole(QPalette::Base); diff -r 886f66775f31 -r 8d45d892be88 src/gui/dialog/licenses.cc --- a/src/gui/dialog/licenses.cc Sun Nov 17 19:56:01 2024 -0500 +++ b/src/gui/dialog/licenses.cc Sun Nov 17 22:55:47 2024 -0500 @@ -4,10 +4,6 @@ #include "core/strings.h" #include "gui/widgets/text.h" -#include "pugixml.hpp" - -#include "utf8proc.h" - #include #include @@ -88,7 +84,6 @@ create_basic_license(tab_widget, ":/licenses/LICENSE.anitomy", tr("Anitomy")); create_basic_license(tab_widget, ":/licenses/LICENSE.fmt", tr("fmt")); create_basic_license(tab_widget, ":/licenses/LICENSE.nlohmann", tr("JSON for Modern C++")); - create_basic_license(tab_widget, ":/licenses/LICENSE.pugixml", tr("pugixml")); create_basic_license(tab_widget, ":/licenses/LICENSE.semver", tr("semver")); create_basic_license(tab_widget, ":/licenses/LICENSE.toml11", tr("toml11")); create_basic_license(tab_widget, ":/licenses/LICENSE.utf8proc", tr("utf8proc")); diff -r 886f66775f31 -r 8d45d892be88 src/gui/pages/search.cc --- a/src/gui/pages/search.cc Sun Nov 17 19:56:01 2024 -0500 +++ b/src/gui/pages/search.cc Sun Nov 17 22:55:47 2024 -0500 @@ -23,9 +23,6 @@ #include #include -#include "anitomy/anitomy.h" -#include "pugixml.hpp" - SearchPageSearchThread::SearchPageSearchThread(QObject* parent) : QThread(parent) { } diff -r 886f66775f31 -r 8d45d892be88 src/gui/pages/torrents.cc --- a/src/gui/pages/torrents.cc Sun Nov 17 19:56:01 2024 -0500 +++ b/src/gui/pages/torrents.cc Sun Nov 17 22:55:47 2024 -0500 @@ -16,13 +16,14 @@ #include #include +#include + #include #include #include #include #include "anitomy/anitomy.h" -#include "pugixml.hpp" /* This file is very, very similar to the anime list page. * @@ -126,11 +127,19 @@ } void TorrentsPageListModel::ParseTorrentList(const QByteArray& ba) { - std::istringstream stdstream(Strings::ToUtf8String(ba)); + QDomDocument doc; + QDomNode node; + QDomNodeList node_nodes; + { + QString err; + int err_ln; + int err_col; - pugi::xml_document doc; - if (!doc.load(stdstream)) - return; // peace out + if (!doc.setContent(ba, &err, &err_ln, &err_col)) { + session.SetStatusBar(Strings::ToUtf8String(tr("Torrents: Failed to parse XML with error %1 at line %2, column %3").arg(err, QString::number(err_ln), QString::number(err_col)))); + return; // peace out + } + } /* my extra special dumb hack. */ if (!rowCount(index(0))) { @@ -141,10 +150,36 @@ beginResetModel(); list.clear(); - /* this is just an rss parser; it should be in a separate class... */ - for (pugi::xml_node item : doc.child("rss").child("channel").children("item")) { + + node = doc; + + for (const auto& n : {"rss", "channel"}) { + node = node.namedItem(n); + if (node.isNull()) { std::cout << n << std::endl; goto end; } + } + + if (!node.hasChildNodes()) { std::cout << "no child nodes" << std::endl; goto end; } + + node_nodes = node.childNodes(); + + for (int c = 0; c < node_nodes.count(); c++) { + const QDomNode item = node_nodes.at(c); + if (!item.isElement() || item.nodeName() != "item") + continue; + + const QDomNode title = item.namedItem("title"); + if (!title.isElement()) continue; + const QDomNode description = item.namedItem("description"); + if (!description.isElement()) continue; + const QDomNode link = item.namedItem("link"); + if (!link.isElement()) continue; + const QDomNode guid = item.namedItem("guid"); + if (!guid.isElement()) continue; + const QDomNode pubDate = item.namedItem("pubDate"); + if (!pubDate.isElement()) continue; + TorrentModelItem torrent; - torrent.SetFilename(item.child_value("title")); /* "title" == filename */ + torrent.SetFilename(Strings::ToUtf8String(title.toElement().text())); /* "title" == filename */ { anitomy::Anitomy anitomy; anitomy.Parse(torrent.GetFilename()); @@ -160,19 +195,17 @@ torrent.SetResolution(Strings::ToUtf8String(elements.get(anitomy::kElementVideoResolution))); } - std::string description = item.child_value("description"); - Strings::TextifySynopsis(description); - ParseFeedDescription(description, torrent); + std::string description_s = Strings::ToUtf8String(description.toElement().text()); + Strings::TextifySynopsis(description_s); + ParseFeedDescription(description_s, torrent); - torrent.SetLink(item.child_value("link")); - torrent.SetGuid(item.child_value("guid")); - { - const QString date_str = Strings::ToQString(item.child_value("pubDate")); - torrent.SetDate(QDateTime::fromString(date_str, "ddd, dd MMM yyyy HH:mm:ss t")); - } + torrent.SetLink(Strings::ToUtf8String(link.toElement().text())); + torrent.SetGuid(Strings::ToUtf8String(guid.toElement().text())); + torrent.SetDate(QDateTime::fromString(pubDate.toElement().text(), "ddd, dd MMM yyyy HH:mm:ss t")); list.push_back(torrent); } +end: endResetModel(); }