path: root/docs/manual.qbk

[book pugixml
    [quickbook 1.5]

    [version 0.9]
    [id manual]
    [copyright 2010 Arseny Kapoulkine]
    [license Distributed under the MIT License]
]

[template sbr[]'''<sbr/>''']
[template lbr[]'''<sbr/><sbr/>'''] [/ for empty lines in lists]
[template file[name]'''<filename>'''[name]'''</filename>''']
[template sref[name]'''<xref linkend="'''[name]'''" xrefstyle="select:title" />''']
[template anchor[name]'''<anchor id="'''[name]'''" />'''[^[name]]]
[template ftnt[id text]'''<footnote id="'''[id]'''"><para>'''[text]'''</para></footnote>''']

[section:overview Overview]

[section:introduction Introduction]

[@http://pugixml.org/ 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 [link manual.xpath XPath 1.0 implementation] for complex data-driven tree queries. Full Unicode support is also available, with [link manual.dom.unicode two Unicode interface variants] and conversions between different Unicode encodings (which happen automatically during parsing/saving). The library is [link manual.install.portability 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 [link manual.overview.license 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 [@quickstart.html read the quick start guide first].

[note No documentation is perfect, neither is this one. If you encounter a description that is unclear, please file an issue as described in [sref manual.overview.feedback]. Also if you can spare the time for a full proof-reading, including spelling and grammar, that would be great! Please [link email send me an e-mail]; as a token of appreciation, your name will be included into the [link manual.overview.thanks corresponding section] of this documentation.]

[endsect] [/introduction]

[section:feedback 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 [@http://code.google.com/p/pugixml/issues/entry 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, [@http://code.google.com/p/pugixml/issues/entry?template=Feature%20request 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 [@http://code.google.com/p/pugixml/issues/entry?template=Feature%20request file an issue]. You can include the relevant patches as issue attachments. 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.

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

[endsect] [/feedback]

[section:thanks 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 [link email 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.

[endsect] [/thanks]

[section:license License]

The pugixml library is distributed under the MIT license:

[:
Copyright (c) 2006-2010 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 (http://pugixml.org).'''<sbr />'''
pugixml is Copyright (C) 2006-2010 Arseny Kapoulkine.
]

[endsect] [/license]

[endsect] [/overview]
 
[section:install Installation]

[section:getting Getting pugixml]

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

[section:source Source distributions]

You can download the latest source distribution via one of the following links:

[pre
[@http://pugixml.googlecode.com/files/pugixml-0.9.zip]
[@http://pugixml.googlecode.com/files/pugixml-0.9.tar.gz]
]

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. The files have different line endings depending on the archive format - [file .zip] archive has Windows line endings, [file .tar.gz] archive has Unix line endings. Otherwise the files in both archives are identical.

If you need an older version, you can download it from the [@http://code.google.com/p/pugixml/downloads/list version archive].

[endsect] [/source]

[section:subversion Subversion repository]

The Subversion repository is located at [@http://pugixml.googlecode.com/svn/]. There is a Subversion tag "release-{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:

[pre svn checkout http://pugixml.googlecode.com/svn/tags/release-0.9 pugixml]

To checkout the latest version, you can use this command:

[pre svn checkout http://pugixml.googlecode.com/svn/tags/latest pugixml]

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

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

[endsect] [/subversion]

[endsect] [/getting]

[section:building 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, [file pugixml.cpp], and two header files, [file pugixml.hpp] and [file pugiconfig.hpp]. [file pugixml.hpp] is the primary header which you need to include in order to use pugixml classes/functions; [file pugiconfig.hpp] is a supplementary configuration file (see [sref manual.install.building.config]). The rest of this guide assumes that [file 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>`).
 
[section:embed Building pugixml as a part of another static library/executable]
 
The easiest way to build pugixml is to compile the source file, [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[ftnt trademarks All trademarks used are properties of their respective owners.], Apple Xcode, Code::Blocks or any other IDE, just add [file 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:

[pre 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 [file 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):

[table
[[
[@images/vs2005_pch1.png [$images/vs2005_pch1_thumb.png]]
[$images/next.png]
[@images/vs2005_pch2.png [$images/vs2005_pch2_thumb.png]]
[$images/next.png]
[@images/vs2005_pch3.png [$images/vs2005_pch3_thumb.png]]
[$images/next.png]
[@images/vs2005_pch4.png [$images/vs2005_pch4_thumb.png]]
]] ]
 
[endsect] [/embed]

[section:static 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 XCode3, 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 [sref manual.overview.feedback]. 

There are two projects for each version of Microsoft Visual Studio: one for dynamically linked CRT, which has a name like [file pugixml_vs2008.vcproj], and another one for statically linked CRT, which has a name like [file 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. [file 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.

[table
[[Microsoft Visual Studio 2005/2008][Microsoft Visual Studio 2010]]
[[
[@images/vs2005_link1.png [$images/vs2005_link1_thumb.png]]
[$images/next.png]
[@images/vs2005_link2.png [$images/vs2005_link2_thumb.png]]
][
[@images/vs2010_link1.png [$images/vs2010_link1_thumb.png]]
[$images/next.png]
[@images/vs2010_link2.png [$images/vs2010_link2_thumb.png]]
]] ]

[endsect] [/static]

[section:shared 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 [link PUGIXML_API] macro, i.e. via [file 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.]

[endsect] [/shared]
 
[section:config 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 [file 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 [file pugixml.hpp] (including pugixml sources) throughout the application. Adding defines to [file pugiconfig.hpp] lets you guarantee this, unless your macro definition is wrapped in preprocessor `#if`/`#ifdef` directive and this directive is not consistent. [file 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.

[anchor 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 [sref manual.dom.unicode] for more details.

[anchor 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.

[anchor 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.

[anchor 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.

[anchor PUGIXML_API], [anchor PUGIXML_CLASS] and [anchor 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 [sref manual.install.building.shared]).

[note In that example `PUGIXML_API` is inconsistent between several source files; this is an exception to the consistency rule.]
 
[endsect] [/config]

[endsect] [/building]

[section:portability Portability]

pugixml is written in standard-compliant C++ with some compiler-specific workarounds where appropriate. pugixml is compatible with the upcoming C++0x standard (verified using GCC 4.5). Each version is tested with a unit test suite (with code coverage about 99%) on the following platforms:

* Microsoft Windows:
    * Borland C++ Compiler 5.82
    * Digital Mars C++ Compiler 8.51
    * Intel C++ Compiler 8.0, 9.0 x86/x64, 10.0 x86/x64, 11.0 x86/x64
    * Metrowerks CodeWarrior 8.0
    * Microsoft Visual C++ 6.0, 7.0 (2002), 7.1 (2003), 8.0 (2005) x86/x64, 9.0 (2008) x86/x64, 10.0 (2010) x86/x64
    * MinGW (GCC) 3.4, 4.4, 4.5, 4.6 x64

* Linux (GCC 4.4.3 x86/x64)
* FreeBSD (GCC 4.2.1 x86/x64)
* Apple MacOSX (GCC 4.0.1 x86/x64/PowerPC)
* Microsoft Xbox 360
* Nintendo Wii (Metrowerks CodeWarrior 4.1)
* Sony Playstation Portable (GCC 3.4.2)
* Sony Playstation 3 (GCC 4.1.1, SNC 310.1)

[endsect] [/portability]

[endsect] [/install]

[section:dom 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).

[section:tree 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 [link xml_document]. Document has one or more child nodes, which correspond to C++ type [link 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 [link xml_attribute], and some additional data (i.e. name).

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

* Document node ([anchor node_document]) - this is the root of the tree, which consists of several child nodes. This node corresponds to [link xml_document] class; note that [link xml_document] is a sub-class of [link 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.
[lbr]

* Element/tag node ([anchor 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 ([anchor 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; for example, 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 ([anchor 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 ([anchor 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 [link parse_comments] flag.]

* Processing instruction node ([anchor 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 [link parse_pi] flag.]

* Declaration node ([anchor 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 [link 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 [link format_no_declaration] flag.]

* Document type declaration node ([anchor 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 [link parse_doctype] flag.]

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

[table

[[
``
    <?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?>
``
][
[@images/dom_tree.png [$images/dom_tree_thumb.png]]
]]]


[endsect] [/tree]

[section:cpp 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]
[#xml_document::document_element]
`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 [sref manual.loading]), saving functions (see [sref manual.saving]) 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.

[#xml_document::ctor]
[#xml_document::dtor]
[#xml_document::reset]
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 an empty one. 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]
[#xml_node::type]
`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 [link xml_node_type 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.

[#node_null]
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]
`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.

[#xml_attribute::ctor]
[#xml_node::ctor]
Both `xml_node` and `xml_attribute` have the default constructor which initializes them to null objects.

[#xml_attribute::comparison]
[#xml_node::comparison]
`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 themselves. 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).

[#xml_attribute::hash_value]
[#xml_node::hash_value]
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.

[#xml_attribute::unspecified_bool_type]
[#xml_node::unspecified_bool_type]
[#xml_attribute::empty]
[#xml_node::empty]
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 [link 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.

[endsect] [/cpp]

[section:unicode 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 [link PUGIXML_WCHAR_MODE] define; you can set it via [file pugiconfig.hpp] or via preprocessor options, as discussed in [sref manual.install.building.config]. 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);

[#char_t]
[#string_t]
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. 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.

[#as_utf8]
[#as_wide]
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 [link 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

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

you'll have to do

`pugi::xml_node node = doc.child(L"bookstore").find_child_by_attribute(L"book", L"id", L"12345");`]
 
[endsect] [/unicode]

[section:thread 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 [link set_memory_management_functions]; it modifies global variables and as such is not thread-safe. Its usage policy has more restrictions, see [sref manual.dom.memory.custom].

[endsect] [/thread]

[section:exception 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. [link xml_node::traverse] or [link xml_node::find_node]) do not provide any exception guarantees beyond the ones provided by the callback.

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

[endsect] [/exception]

[section:memory 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.

[section:custom Custom memory allocation/deallocation functions]

[#allocation_function]
[#deallocation_function]
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);

[#set_memory_management_functions]
[#get_memory_allocation_function]
[#get_memory_deallocation_function]
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 return null pointer (throwing an exception from allocation function results in undefined behavior).

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]):

[import samples/custom_memory_management.cpp]
[code_custom_memory_management_decl]
[code_custom_memory_management_call]

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.

[endsect] [/custom]

[section:internals Document memory management internals]

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

When the document is loaded from file/buffer, unless an inplace loading function is used (see [sref manual.loading.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 [link 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 kilobytes; 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.

[endsect] [/internals]

[endsect] [/memory]

[endsect] [/dom]

[section:loading 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 [sref manual.loading.options] for more information.

XML data is always converted to internal character format (see [sref manual.dom.unicode]) 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. Unless explicit encoding is specified, loading functions perform automatic encoding detection based on first few characters of XML data, so in almost all cases you do not have to specify document encoding. Encoding conversion is described in more detail in [sref manual.loading.encoding].

[section:file Loading document from file]

[#xml_document::load_file]
[#xml_document::load_file_wide]
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 [sref manual.loading.options]) and input data encoding (see [sref manual.loading.encoding]). 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 [link 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 [sref manual.loading.errors] for error handling details.

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

[import samples/load_file.cpp]
[code_load_file]

[endsect] [/file]

[section:memory Loading document from memory]

[#xml_document::load_buffer]
[#xml_document::load_buffer_inplace]
[#xml_document::load_buffer_inplace_own]
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 [sref manual.loading.options]) and input data encoding (see [sref manual.loading.encoding]). 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 [link 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.

[#xml_document::load_string]
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(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]):

[import samples/load_memory.cpp]
[code_load_memory_decl]
[code_load_memory_buffer]
[code_load_memory_buffer_inplace]
[code_load_memory_buffer_inplace_own]
[code_load_memory_string]

[endsect] [/memory]

[section:stream Loading document from C++ IOstreams]

[#xml_document::load_stream]
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 [link 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:

[import samples/load_stream.cpp]
[code_load_stream]

Stream loading requires working seek/tell functions and therefore may fail when used with some stream implementations like gzstream.

[endsect] [/stream]

[section:errors Handling parsing errors]

[#xml_parse_result]
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;
    };

[#xml_parse_status]
[#xml_parse_result::status]
Parsing status is represented as the `xml_parse_status` enumeration and can be one of the following:

* [anchor 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.
[lbr]

* [anchor status_file_not_found] is only returned by `load_file` function and means that file could not be opened.
* [anchor 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 occured during reading the file/stream.
* [anchor status_out_of_memory] means that there was not enough memory during some allocation; any allocation failure during parsing results in this error.
* [anchor status_internal_error] means that something went horribly wrong; currently this error does not occur
[lbr]

* [anchor 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 [^#].
* [anchor status_bad_pi] means that parsing stopped due to incorrect document declaration/processing instruction
* [anchor status_bad_comment], [anchor status_bad_cdata], [anchor status_bad_doctype] and [anchor status_bad_pcdata] mean that parsing stopped due to the invalid construct of the respective type
* [anchor status_bad_start_element] means that parsing stopped because starting tag either had no closing `>` symbol or contained some incorrect symbol
* [anchor 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)
* [anchor status_bad_end_element] means that parsing stopped because ending tag had incorrect syntax (i.e. extra non-whitespace symbols between tag name and `>`)
* [anchor 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

[#xml_parse_result::description]
`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.

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>`.

[#xml_parse_result::offset]
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 [link char_t 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.]

[#xml_parse_result::encoding]
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 [sref manual.loading.encoding] for more information.

[#xml_parse_result::bool]
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]):

[import samples/load_error_handling.cpp]
[code_load_error_handling]

[endsect] [/errors]

[section:options 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:

* [anchor parse_declaration] determines if XML document declaration (node with type [link 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.
[lbr]

* [anchor parse_doctype] determines if XML document type declaration (node with type [link 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.
[lbr]

* [anchor parse_pi] determines if processing instructions (nodes with type [link 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.
[lbr]

* [anchor parse_comments] determines if comments (nodes with type [link 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.
[lbr]

* [anchor parse_cdata] determines if CDATA sections (nodes with type [link 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.
[lbr]

* [anchor parse_ws_pcdata] determines if PCDATA nodes (nodes with type [link 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 [link node_pcdata] and value `" "`, child with type [link node_element] and name `"a"`, and another child with type [link node_pcdata] and value `" "`), and only one child when `parse_ws_pcdata` is not set. This flag is *off* by default.

These flags control the transformation of tree element contents:

* [anchor 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.
[lbr]

* [anchor parse_eol] determines if EOL handling (that is, replacing sequences `0x0d 0x0a` by a single `0x0a` character, and replacing all standalone `0x0d` characters by `0x0a`) is to be performed on input data (that is, comments contents, PCDATA/CDATA contents and attribute values). This flag is *on* by default.
[lbr]

* [anchor 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 [link parse_eol] is set, i.e. `\r\n` is converted to a single space.  This flag is *on* by default.
[lbr]

* [anchor 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 [link 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. The value of [link 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]; [link 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 [link parse_wconv_attribute] is the default option.]

Additionally there are three predefined option masks:

* [anchor 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 [link parse_default] is usually equally fast.
[lbr]

* [anchor 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.
[lbr]

* [anchor 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]):

[import samples/load_options.cpp]
[code_load_options]

[endsect] [/options]

[section:encoding Encodings]

[#xml_encoding]
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. Most loading functions accept the optional parameter `encoding`. This is a value of enumeration type `xml_encoding`, that can have the following values:

* [anchor 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.1 of XML recommendation; it tries to match the first few bytes of input data with the following patterns in strict order:
[lbr]
    * If first four bytes match UTF-32 BOM (Byte Order Mark), encoding is assumed to be UTF-32 with the endianness equal to that of BOM;
    * If first two bytes match UTF-16 BOM, encoding is assumed to be UTF-16 with the endianness equal to that of BOM;
    * If first three bytes match UTF-8 BOM, encoding is assumed to be UTF-8;
    * If first four bytes match UTF-32 representation of [^<], encoding is assumed to be UTF-32 with the corresponding endianness;
    * If first four bytes match UTF-16 representation of [^<?], encoding is assumed to be UTF-16 with the corresponding endianness;
    * If first two bytes match UTF-16 representation of [^<], encoding is assumed to be UTF-16 with the corresponding endianness (this guess may yield incorrect result, but it's better than UTF-8);
    * Otherwise encoding is assumed to be UTF-8.
    [lbr]

* [anchor 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.
* [anchor encoding_utf16_le] corresponds to little-endian UTF-16 encoding as defined in the Unicode standard; surrogate pairs are supported.
* [anchor encoding_utf16_be] corresponds to big-endian UTF-16 encoding as defined in the Unicode standard; surrogate pairs are supported.
* [anchor encoding_utf16] corresponds to UTF-16 encoding as defined in the Unicode standard; the endianness is assumed to be that of the target platform.
* [anchor encoding_utf32_le] corresponds to little-endian UTF-32 encoding as defined in the Unicode standard.
* [anchor encoding_utf32_be] corresponds to big-endian UTF-32 encoding as defined in the Unicode standard.
* [anchor encoding_utf32] corresponds to UTF-32 encoding as defined in the Unicode standard; the endianness is assumed to be that of the target platform.
* [anchor 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.

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.]

[endsect] [/encoding]

[section:w3c 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.
* All non-ASCII characters are treated in the same way as symbols of English alphabet, so some invalid tag names 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.

[endsect] [/w3c]

[endsect] [/loading]

[section:access 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 [sref manual.xpath] for XPath reference. As discussed in [sref manual.dom.cpp], there are two types of handles to tree data - [link xml_node] and [link xml_attribute]. The handles have special null (empty) values which propagate through various functions and thus are useful for writing more concise code; see [link node_null this description] for details. The documentation in this section will explicitly state the results of all function in case of null inputs.

[import samples/traverse_base.cpp]

[section:basic Basic traversal functions]

[#xml_node::parent][#xml_node::first_child][#xml_node::last_child][#xml_node::next_sibling][#xml_node::previous_sibling][#xml_node::first_attribute][#xml_node::last_attribute][#xml_attribute::next_attribute][#xml_attribute::previous_attribute]
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]):

[code_traverse_base_basic]

[endsect] [/basic]

[section:nodedata Getting node data]

[#xml_node::name][#xml_node::value]
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. [link node_document] nodes do not have a name or value, [link node_element] and [link node_declaration] nodes always have a name but never have a value, [link node_pcdata], [link node_cdata], [link node_comment] and [link node_doctype] nodes never have a name but always have a value (it may be empty though), [link 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.

[#xml_node::child_value]
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 [link node_pcdata] with value `"This is a node"`. pugixml provides two 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;

`child_value()` returns the value of the first child with type [link node_pcdata] or [link 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.

There is an example of using some of these functions [link code_traverse_base_data at the end of the next section].

[endsect] [/nodedata]

[section:attrdata Getting attribute data]

[#xml_attribute::name][#xml_attribute::value]
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.

[#xml_attribute::as_int][#xml_attribute::as_uint][#xml_attribute::as_double][#xml_attribute::as_float][#xml_attribute::as_bool]
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. The accessors are as follows:

    int xml_attribute::as_int() const;
    unsigned int xml_attribute::as_uint() const;
    double xml_attribute::as_double() const;
    float xml_attribute::as_float() const;
    bool xml_attribute::as_bool() const;

`as_int`, `as_uint`, `as_double` and `as_float` convert attribute values to numbers. If attribute handle is null or attribute value is empty, `0` is returned. Otherwise, all leading whitespace characters are truncated, and the remaining string is parsed as a decimal number (`as_int` or `as_uint`) or as a floating point number in either decimal or scientific form (`as_double` or `as_float`). Any extra characters are silently discarded, i.e. `as_int` will return `1` for string `"1abc"`.

In case the input string contains 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 or 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 There are no portable 64-bit types in C++, so there is no corresponding conversion function. If your platform has a 64-bit integer, you can easily write a conversion function yourself.]

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

[code_traverse_base_data]

[endsect] [/attrdata]

[section:contents Contents-based traversal functions]

[#xml_node::child][#xml_node::attribute][#xml_node::next_sibling_name][#xml_node::previous_sibling_name]
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"))

[#xml_node::find_child_by_attribute]
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]):

[code_traverse_base_contents]

[endsect] [/contents]

[section:iterators Traversing node/attribute lists via iterators]

[#xml_node_iterator][#xml_attribute_iterator][#xml_node::begin][#xml_node::end][#xml_node::attributes_begin][#xml_node::attributes_end]
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]):

[import samples/traverse_iter.cpp]
[code_traverse_iter]

[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 by 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.]

[endsect] [/iterators]

[section:walker Recursive traversal with xml_tree_walker]

[#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);

[#xml_tree_walker::begin][#xml_tree_walker::for_each][#xml_tree_walker::end][#xml_node::traverse]
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`.

[#xml_tree_walker::depth]
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]):

[import samples/traverse_walker.cpp]
[code_traverse_walker_impl]
[code_traverse_walker_traverse]

[endsect] [/walker]

[section:predicate Searching for nodes/attributes with predicates]

[#xml_node::find_attribute][#xml_node::find_child][#xml_node::find_node]
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]):

[import samples/traverse_predicate.cpp]
[code_traverse_predicate_decl]
[code_traverse_predicate_find]

[endsect] [/predicate]

[section:misc Miscellaneous functions]

[#xml_node::root]
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 [link 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).

[#xml_node::path]
[#xml_node::first_element_by_path]
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 [link PUGIXML_NO_STL] is defined.]

[#xml_node::offset_debug]
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 [link char_t pugi::char_t] units. For more information on parsing offsets, see [link xml_parse_result::offset parsing error handling documentation].

[endsect] [/misc]

[endsect] [/access]

[section:modify 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.

[import samples/modify_base.cpp]

[section:nodedata Setting node data]

[#xml_node::set_name][#xml_node::set_value]
As discussed before, nodes can have name and value, both of which are strings. Depending on node type, name or value may be absent. [link node_document] nodes do not have a name or value, [link node_element] and [link node_declaration] nodes always have a name but never have a value, [link node_pcdata], [link node_cdata], [link node_comment] and [link node_doctype] nodes never have a name but always have a value (it may be empty though), [link 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_value(const char_t* rhs);

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 [link 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.

There is no equivalent of [link xml_node::child_value child_value] function for modifying text children of the node.

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

[code_modify_base_node]

[endsect] [/nodedata]

[section:attrdata Setting attribute data]

[#xml_attribute::set_name][#xml_attribute::set_value]
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_value(const char_t* rhs);

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(double rhs);
    bool xml_attribute::set_value(bool 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 There are no portable 64-bit types in C++, so there is no corresponding `set_value` function. If your platform has a 64-bit integer, you can easily write such a function yourself.]

[#xml_attribute::assign]

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=(double rhs);
    xml_attribute& xml_attribute::operator=(bool 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]):

[code_modify_base_attr]

[endsect] [/attrdata]

[section:add Adding nodes/attributes]

[#xml_node::prepend_attribute][#xml_node::append_attribute][#xml_node::insert_attribute_after][#xml_node::insert_attribute_before][#xml_node::prepend_child][#xml_node::append_child][#xml_node::insert_child_after][#xml_node::insert_child_before]
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 ([link 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 [link node_element] nodes can contain attributes, so attribute adding fails if node is not an element;
* Only [link node_document] and [link node_element] nodes can contain children, so child node adding fails if the target node is not an element or a document;
* [link node_document] and [link node_null] nodes can not be inserted as children, so passing [link node_document] or [link node_null] value as `type` results in operation failure;
* [link 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]):

[import samples/modify_add.cpp]
[code_modify_add]

[endsect] [/add]

[section:remove Removing nodes/attributes]

[#xml_node::remove_attribute][#xml_node::remove_child]
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_child(const xml_node& n);

`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. 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]):

[import samples/modify_remove.cpp]
[code_modify_remove]

[endsect] [/remove]

[section:clone Cloning nodes/attributes]

[#xml_node::prepend_copy][#xml_node::append_copy][#xml_node::insert_copy_after][#xml_node::insert_copy_before]
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, [link xml_node::append_child 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 [link 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:

[import samples/include.cpp]
[code_include]

[endsect] [/clone]

[endsect] [/modify]

[section:saving 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 [sref manual.saving.options]), and also perform necessary encoding conversions (see [sref manual.saving.encoding]). 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. 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.

[section:file Saving document to a file]

[#xml_document::save_file]
[#xml_document::save_file_wide]
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 [sref manual.saving.options]) and output data encoding (see [sref manual.saving.encoding]). 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.

[#xml_writer_file]
`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. If the file could not be opened, the function returns `false`. 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 [sref manual.saving.writer] for writer interface details.

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

[import samples/save_file.cpp]
[code_save_file]

[endsect] [/file]

[section:stream Saving document to C++ IOstreams]

[#xml_document::save_stream]
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 [link 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.

[#xml_writer_stream]
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 [sref manual.saving.writer] for writer interface details.

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

[import samples/save_stream.cpp]
[code_save_stream]

[endsect] [/stream]

[section:writer Saving document via writer interface]

[#xml_document::save][#xml_writer][#xml_writer::write]
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_file` interface and pass it to `save` function. `xml_writer_file::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 first block with BOM, which is output only if [link format_write_bom] is set, and last block, which 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:

[import samples/save_custom_writer.cpp]
[code_save_custom_writer]

[endsect] [/writer]

[section:subtree Saving a single subtree]

[#xml_node::print][#xml_node::print_stream]
While the previously described functions saved 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 [link format_write_bom] is off, and [link 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:

[import samples/save_subtree.cpp]
[code_save_subtree]

[endsect] [/subtree]

[section:options 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:

* [anchor 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, before every node the indentation string is output several times, where the amount of indentation depends on the node's depth relative to the output subtree. This flag has no effect if [link format_raw] is enabled. This flag is *on* by default.
[lbr]

* [anchor 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 [link parse_ws_pcdata] flag, to preserve the original document formatting as much as possible. This flag is *off* by default.

These flags control the additional output information:

* [anchor format_no_declaration] allows to disable 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.
[lbr]

* [anchor format_write_bom] allows to enable 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.

Additionally, there is one predefined option mask:

* [anchor 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]):

[import samples/save_options.cpp]
[code_save_options]

[endsect] [/options]

[section:encoding 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 [sref manual.loading.encoding]; 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 [link 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.]

[endsect] [/encoding]

[endsect] [/saving]

[section:xpath 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 [sref manual.xpath.w3c]. 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 [@http://www.w3schools.com/xpath/ W3Schools XPath tutorial], [@http://www.tizag.com/xmlTutorial/xpathtutorial.php XPath tutorial at tizag.com], and [@http://www.w3.org/TR/xpath/ the XPath 1.0 specification].

[section:types XPath types]

[#xpath_value_type][#xpath_type_number][#xpath_type_string][#xpath_type_boolean][#xpath_type_node_set][#xpath_type_none]
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 [link manual.dom.unicode wide character interface is enabled], and node set corresponds to [link 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.

[#xpath_node][#xpath_node::node][#xpath_node::attribute][#xpath_node::parent]
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.

[#xpath_node::unspecified_bool_type][#xpath_node::comparison]
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.

[#xpath_node::ctor]
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_node_set]
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.

[#xpath_node_set::const_iterator][#xpath_node_set::begin][#xpath_node_set::end]
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;

[#xpath_node_set::index][#xpath_node_set::size][#xpath_node_set::empty]
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.

[#xpath_node_set::type][#xpath_node_set::type_unsorted][#xpath_node_set::type_sorted][#xpath_node_set::type_sorted_reverse][#xpath_node_set::sort]
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`.

[#xpath_node_set::first]
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.

[#xpath_node_set::ctor]
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.

[endsect] [/types]

[section:select Selecting nodes via XPath expression]

[#xml_node::select_single_node][#xml_node::select_nodes]
If you want to select nodes that match some XPath expression, you can do it with the following functions:

    xpath_node xml_node::select_single_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_single_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_single_node` returns null XPath node.

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

[#xml_node::select_single_node_precomp][#xml_node::select_nodes_precomp]
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 [sref manual.xpath.query] 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_single_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 [link 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]):

[import samples/xpath_select.cpp]
[code_xpath_select]

[endsect] [/select]

[section:query Using query objects]

[#xpath_query]
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, allocate them on heap via `new` operator and store pointers to `xpath_query` in the container.

[#xpath_query::ctor]
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);

[#xpath_query::return_type]
The expression is compiled and the compiled representation is stored in the new query object. If compilation fails, [link xpath_exception] is thrown if exception handling is not disabled (see [sref manual.xpath.errors] 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;

[#xpath_query::evaluate_boolean][#xpath_query::evaluate_number][#xpath_query::evaluate_string][#xpath_query::evaluate_node_set]
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;

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` results in an error if the return type is not node set (see [sref manual.xpath.errors]).

[note Calling `node.select_nodes("query")` is equivalent to calling `xpath_query("query").evaluate_node_set(node)`.]

[#xpath_query::evaluate_string_buffer]
Note that `evaluate_string` function returns the STL string; as such, it's not available in [link 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]):

[import samples/xpath_query.cpp]
[code_xpath_query]

[endsect] [/query]

[section:variables 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 '''<code><phrase role="identifier">$name</phrase></code>'''; 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_single_node` functions:

    explicit xpath_query::xpath_query(const char_t* query, xpath_variable_set* variables = 0);
    xpath_node xml_node::select_single_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.]

[#xpath_variable_set]
Variable sets correspond to `xpath_variable_set` type, which is essentially a variable container.

[#xpath_variable_set::add]
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.

[#xpath_variable_set::get]
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.

[#xpath_variable_set::set]
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.

[#xpath_variable]
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`.

[#xpath_variable::type][#xpath_variable::name]
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.

[#xpath_variable::get_boolean][#xpath_variable::get_number][#xpath_variable::get_string][#xpath_variable::get_node_set]
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).

[#xpath_variable::set]
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 function 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]):

[import samples/xpath_variables.cpp]
[code_xpath_variables]

[endsect] [/variables]

[section:errors 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 [link PUGIXML_NO_EXCEPTIONS] define).

[#xpath_exception]
[#xpath_exception::result]
[#xpath_exception::what]
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;

[#xpath_query::unspecified_bool_type]
[#xpath_query::result]
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.

[#xpath_parse_result]
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;
    };

[#xpath_parse_result::error]
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.

[#xpath_parse_result::description]
`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.

[#xpath_parse_result::offset]
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 [link char_t pugi::char_t] (bytes for character mode, wide characters for wide character mode).

[#xpath_parse_result::bool]
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]):

[import samples/xpath_error.cpp]
[code_xpath_error]

[endsect] [/errors]

[section:w3c 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 children, 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.

[endsect] [/w3c]

[endsect] [/xpath]

[section:changes Changelog]

[h5 1.11.2010 - version 1.0]

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

* XPath:
    # 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
    # XPath is now supported without exceptions (PUGIXML_NO_EXCEPTIONS); the error handling mechanism depends on the presence of exception support
    # XPath is now supported without STL (PUGIXML_NO_STL)
    # Introduced variable support
    # Introduced new xpath_query::evaluate_string, which works without STL
    # Introduced new xpath_node_set constructor (from an iterator range)
    # Evaluation function now accept attribute context nodes
    # All internal allocations use custom allocation functions
    # Improved error reporting; now a last parsed offset is returned together with the parsing error

* Bug fixes:
    # Fixed memory leak for loading from streams with stream exceptions turned on
    # Fixed custom deallocation function calling with null pointer in one case
    # Fixed missing attributes for iterator category functions; all functions/classes can now be DLL-exported
    # Worked around Digital Mars compiler bug, which lead to minor read overfetches in several functions
    # load_file now works with 2+ Gb files in MSVC/MinGW
    # XPath: fixed memory leaks for incorrect queries
    # XPath: fixed xpath_node() attribute constructor with empty attribute argument
    # XPath: fixed lang() function for non-ASCII arguments

* Specification changes:
    # CDATA nodes containing ]]> are printed as several nodes; while this changes the internal structure, this is the only way to escape CDATA contents
    # Memory allocation errors during parsing now preserve last parsed offset (to give an idea about parsing progress)
    # 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)

* Additional functionality:
    # Added xml_parse_result default constructor
    # Added xml_document::load_file and xml_document::save_file with wide character paths
    # Added as_utf8 and as_wide overloads for std::wstring/std::string arguments
    # Added DOCTYPE node type (node_doctype) and a special parse flag, parse_doctype, to add such nodes to the document during parsing
    # Added parse_full parse flag mask, which extends parse_default with all node type parsing flags except parse_ws_pcdata
    # Added xml_node::hash_value() and xml_attribute::hash_value() functions for use in hash-based containers
    # Added internal_object() and additional constructor for both xml_node and xml_attribute for easier marshalling (useful for language bindings)
    # Added xml_document::document_element() function
    # Added xml_node::prepend_attribute, xml_node::prepend_child and xml_node::prepend_copy functions
    # 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)
    # Added xml_document::reset() function

* Performance improvements:
    # xml_node::root() and xml_node::offset_debug() are now O(1) instead of O(logN)
    # Minor parsing optimizations
    # Minor memory optimization for strings in DOM tree (set_name/set_value)
    # Memory optimization for string memory reclaiming in DOM tree (set_name/set_value now reallocate the buffer if memory waste is too big)
    # XPath: optimized document order sorting
    # XPath: optimized child/attribute axis step
    # XPath: optimized number-to-string conversions in MSVC
    # XPath: optimized concat for many arguments
    # XPath: optimized evaluation allocation mechanism: constant and document strings are not heap-allocated
    # XPath: optimized evaluation allocation mechanism: all temporaries' allocations use fast stack-like allocator

* Compatibility:
    # Removed wildcard functions (xml_node::child_w, xml_node::attribute_w, etc.)
    # Removed xml_node::all_elements_by_name
    # Removed xpath_type_t enumeration; use xpath_value_type instead
    # Removed format_write_bom_utf8 enumeration; use format_write_bom instead
    # Removed xml_document::precompute_document_order, xml_attribute::document_order and xml_node::document_order functions; document order sort optimization is now automatic
    # Removed xml_document::parse functions and transfer_ownership struct; use xml_document::load_buffer_inplace and xml_document::load_buffer_inplace_own instead
    # Removed as_utf16 function; use as_wide instead

[h5 1.07.2010 - version 0.9]

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

* Major Unicode improvements:
    # Introduced encoding support (automatic/manual encoding detection on load, manual encoding selection on save, conversion from/to UTF8, UTF16 LE/BE, UTF32 LE/BE)
    # 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)
    # Load/save functions now support wide streams

* Bug fixes:
    # Fixed document corruption on failed parsing bug
    # XPath string <-> number conversion improvements (increased precision, fixed crash for huge numbers)
    # Improved DOCTYPE parsing: now parser recognizes all well-formed DOCTYPE declarations
    # Fixed xml_attribute::as_uint() for large numbers (i.e. 2^32-1)
    # Fixed xml_node::first_element_by_path for path components that are prefixes of node names, but are not exactly equal to them.

* Specification changes:
    # parse() API changed to load_buffer/load_buffer_inplace/load_buffer_inplace_own; load_buffer APIs do not require zero-terminated strings.
    # Renamed as_utf16 to as_wide
    # Changed xml_node::offset_debug return type and xml_parse_result::offset type to ptrdiff_t
    # Nodes/attributes with empty names are now printed as :anonymous

* Performance improvements:
    # Optimized document parsing and saving
    # 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
    # Optimized memory consumption: sizeof(xml_node_struct) reduced from 40 bytes to 32 bytes on x86
    # Optimized debug mode parsing/saving by order of magnitude

* Miscellaneous:
    # All STL includes except <exception> in pugixml.hpp are replaced with forward declarations
    # xml_node::remove_child and xml_node::remove_attribute now return the operation result

* Compatibility:
    # parse() and as_utf16 are left for compatibility (these functions are deprecated and will be removed in version 1.0)
    # 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
    # xpath_type_t enumeration was renamed to xpath_value_type; xpath_type_t is deprecated and will be removed in version 1.0

[h5 8.11.2009 - version 0.5]

Major bugfix release. Changes:

* XPath bugfixes:
    # Fixed translate(), lang() and concat() functions (infinite loops/crashes)
    # Fixed compilation of queries with empty literal strings ("")
    # Fixed axis tests: they never add empty nodes/attributes to the resulting node set now
    # Fixed string-value evaluation for node-set (the result excluded some text descendants)
    # Fixed self:: axis (it behaved like ancestor-or-self::)
    # Fixed following:: and preceding:: axes (they included descendent and ancestor nodes, respectively)
    # Minor fix for namespace-uri() function (namespace declaration scope includes the parent element of namespace declaration attribute)
    # Some incorrect queries are no longer parsed now (i.e. foo: *)
    # Fixed text()/etc. node test parsing bug (i.e. foo[text()] failed to compile)
    # Fixed root step (/) - it now selects empty node set if query is evaluated on empty node
    # Fixed string to number conversion ("123 " converted to NaN, "123 .456" converted to 123.456 - now the results are 123 and NaN, respectively)
    # Node set copying now preserves sorted type; leads to better performance on some queries

* Miscellaneous bugfixes:
    # Fixed xml_node::offset_debug for PI nodes
    # Added empty attribute checks to xml_node::remove_attribute
    # Fixed node_pi and node_declaration copying
    # Const-correctness fixes

* Specification changes:
    # xpath_node::select_nodes() and related functions now throw exception if expression return type is not node set (instead of assertion)
    # xml_node::traverse() now sets depth to -1 for both begin() and end() callbacks (was 0 at begin() and -1 at end())
    # In case of non-raw node printing a newline is output after PCDATA inside nodes if the PCDATA has siblings
    # UTF8 -> wchar_t conversion now considers 5-byte UTF8-like sequences as invalid

* New features:
    # Added xpath_node_set::operator[] for index-based iteration
    # Added xpath_query::return_type()
    # Added getter accessors for memory-management functions

[h5 17.09.2009 - version 0.42]

Maintenance release. Changes:

* Bug fixes:
    # Fixed deallocation in case of custom allocation functions or if delete[] / free are incompatible
    # XPath parser fixed for incorrect queries (i.e. incorrect XPath queries should now always fail to compile)
    # Const-correctness fixes for find_child_by_attribute
    # Improved compatibility (miscellaneous warning fixes, fixed cstring include dependency for GCC)
    # Fixed iterator begin/end and print function to work correctly for empty nodes

* New features:
    # Added PUGIXML_API/PUGIXML_CLASS/PUGIXML_FUNCTION configuration macros to control class/function attributes
    # Added xml_attribute::set_value overloads for different types

[h5 8.02.2009 - version 0.41]

Maintenance release. Changes:

* Bug fixes:
    # Fixed bug with node printing (occasionally some content was not written to output stream)

[h5 18.01.2009 - version 0.4]

Changes:

* Bug fixes:
    # Documentation fix in samples for parse() with manual lifetime control
    # Fixed document order sorting in XPath (it caused wrong order of nodes after xpath_node_set::sort and wrong results of some XPath queries)

* Node printing changes:
    # Single quotes are no longer escaped when printing nodes
    # 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.
    # 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.

* New features:
    # Added unsigned integer support for attributes (xml_attribute::as_uint, xml_attribute::operator=)
    # 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
    # Added support for custom memory management (see set_memory_management_functions for details)
    # Implemented node/attribute copying (see xml_node::insert\_copy_* and xml_node::append_copy for details)
    # Added find_child_by_attribute and find_child_by_attribute_w to simplify parsing code in some cases (i.e. COLLADA files)
    # 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)
    # 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.

[h5 31.10.2007 - version 0.34]

Maintenance release. Changes:

* Bug fixes:
    # Fixed bug with loading from text-mode iostreams
    # Fixed leak when transfer_ownership is true and parsing is failing
    # Fixed bug in saving (\\r and \\n are now escaped in attribute values)
    # Renamed free() to destroy() - some macro conflicts were reported

* New features:
    # Improved compatibility (supported Digital Mars C++, MSVC 6, CodeWarrior 8, PGI C++, Comeau, supported PS3 and XBox360)
    # PUGIXML_NO_EXCEPTION flag for platforms without exception handling

[h5 21.02.2007 - version 0.3]

Refactored, reworked and improved version. Changes:

* Interface:
    # Added XPath
    # Added tree modification functions
    # Added no STL compilation mode
    # Added saving document to file
    # Refactored parsing flags
    # Removed xml_parser class in favor of xml_document
    # Added transfer ownership parsing mode
    # Modified the way xml_tree_walker works
    # Iterators are now non-constant

* Implementation:
    # Support of several compilers and platforms
    # Refactored and sped up parsing core
    # Improved standard compliancy
    # Added XPath implementation
    # Fixed several bugs

[h5 6.11.2006 - version 0.2]

First public release. Changes:

* Bug fixes:
    # Fixed child_value() (for empty nodes)
    # Fixed xml_parser_impl warning at W4

* New features:
    # Introduced child_value(name) and child_value_w(name)
    # parse_eol_pcdata and parse_eol_attribute flags + parse_minimal optimizations
    # Optimizations of strconv_t

[h5 15.07.2006 - version 0.1]

First private release for testing purposes

[endsect] [/changes]

[section:apiref 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.

Macros:

* `#define `[link PUGIXML_WCHAR_MODE]
* `#define `[link PUGIXML_NO_XPATH]
* `#define `[link PUGIXML_NO_STL]
* `#define `[link PUGIXML_NO_EXCEPTIONS]
* `#define `[link PUGIXML_API]
* `#define `[link PUGIXML_CLASS]
* `#define `[link PUGIXML_FUNCTION]

Types:

* `typedef `/configuration-defined type/` `[link char_t]`;`
* `typedef `/configuration-defined type/` `[link string_t]`;`
* `typedef void* (*`[link allocation_function]`)(size_t size);`
* `typedef void (*`[link deallocation_function]`)(void* ptr);`

Enumerations:

* `enum `[link xml_node_type]
    * [link node_null]
    * [link node_document]
    * [link node_element]
    * [link node_pcdata]
    * [link node_cdata]
    * [link node_comment]
    * [link node_pi]
    * [link node_declaration]
    * [link node_doctype]
    [lbr]

* `enum `[link xml_parse_status]
    * [link status_ok]
    * [link status_file_not_found]
    * [link status_io_error]
    * [link status_out_of_memory]
    * [link status_internal_error]
    * [link status_unrecognized_tag]
    * [link status_bad_pi]
    * [link status_bad_comment]
    * [link status_bad_cdata]
    * [link status_bad_doctype]
    * [link status_bad_pcdata]
    * [link status_bad_start_element]
    * [link status_bad_attribute]
    * [link status_bad_end_element]
    * [link status_end_element_mismatch]
    [lbr]

* `enum `[link xml_encoding]
    * [link encoding_auto]
    * [link encoding_utf8]
    * [link encoding_utf16_le]
    * [link encoding_utf16_be]
    * [link encoding_utf16]
    * [link encoding_utf32_le]
    * [link encoding_utf32_be]
    * [link encoding_utf32]
    * [link encoding_wchar]
    [lbr]

* `enum `[link xpath_value_type]
    * [link xpath_type_none]
    * [link xpath_type_node_set]
    * [link xpath_type_number]
    * [link xpath_type_string]
    * [link xpath_type_boolean]

Constants:

* Formatting options bit flags:
    * [link format_default]
    * [link format_indent]
    * [link format_no_declaration]
    * [link format_raw]
    * [link format_write_bom]
    [lbr]

* Parsing options bit flags:
    * [link parse_cdata]
    * [link parse_comments]
    * [link parse_declaration]
    * [link parse_default]
    * [link parse_doctype]
    * [link parse_eol]
    * [link parse_escapes]
    * [link parse_full]
    * [link parse_minimal]
    * [link parse_pi]
    * [link parse_ws_pcdata]
    * [link parse_wconv_attribute]
    * [link parse_wnorm_attribute]
        
Classes:

* `class `[link xml_attribute]
    * [link xml_attribute::ctor xml_attribute]`();`
    [lbr]

    * `bool `[link xml_attribute::empty empty]`() const;`
    * `operator `[link xml_attribute::unspecified_bool_type unspecified_bool_type]`() const;`
    [lbr]

    * `bool `[link xml_attribute::comparison operator==]`(const xml_attribute& r) const;`
    * `bool `[link xml_attribute::comparison operator!=]`(const xml_attribute& r) const;`
    * `bool `[link xml_attribute::comparison operator<]`(const xml_attribute& r) const;`
    * `bool `[link xml_attribute::comparison operator>]`(const xml_attribute& r) const;`
    * `bool `[link xml_attribute::comparison operator<=]`(const xml_attribute& r) const;`
    * `bool `[link xml_attribute::comparison operator>=]`(const xml_attribute& r) const;`
    [lbr]

    * `size_t `[link xml_attribute::hash_value hash_value]`() const;`
    [lbr]

    * `xml_attribute `[link xml_attribute::next_attribute next_attribute]`() const;`
    * `xml_attribute `[link xml_attribute::previous_attribute previous_attribute]`() const;`
    [lbr]

    * `const char_t* `[link xml_attribute::name name]`() const;`
    * `const char_t* `[link xml_attribute::value value]`() const;`
    [lbr]

    * `int `[link xml_attribute::as_int as_int]`() const;`
    * `unsigned int `[link xml_attribute::as_uint as_uint]`() const;`
    * `double `[link xml_attribute::as_double as_double]`() const;`
    * `float `[link xml_attribute::as_float as_float]`() const;`
    * `bool `[link xml_attribute::as_bool as_bool]`() const;`
    [lbr]

    * `bool `[link xml_attribute::set_name set_name]`(const char_t* rhs);`
    * `bool `[link xml_attribute::set_value set_value]`(const char_t* rhs);`
    * `bool `[link xml_attribute::set_value set_value]`(int rhs);`
    * `bool `[link xml_attribute::set_value set_value]`(unsigned int rhs);`
    * `bool `[link xml_attribute::set_value set_value]`(double rhs);`
    * `bool `[link xml_attribute::set_value set_value]`(bool rhs);`
    [lbr]

    * `xml_attribute& `[link xml_attribute::assign operator=]`(const char_t* rhs);`
    * `xml_attribute& `[link xml_attribute::assign operator=]`(int rhs);`
    * `xml_attribute& `[link xml_attribute::assign operator=]`(unsigned int rhs);`
    * `xml_attribute& `[link xml_attribute::assign operator=]`(double rhs);`
    * `xml_attribute& `[link xml_attribute::assign operator=]`(bool rhs);`
    [lbr]

* `class `[link xml_node]
    * [link xml_node::ctor xml_node]`();`
    [lbr]

    * `bool `[link xml_node::empty empty]`() const;`
    * `operator `[link xml_node::unspecified_bool_type unspecified_bool_type]`() const;`
    [lbr]

    * `bool `[link xml_node::comparison operator==]`(const xml_node& r) const;`
    * `bool `[link xml_node::comparison operator!=]`(const xml_node& r) const;`
    * `bool `[link xml_node::comparison operator<]`(const xml_node& r) const;`
    * `bool `[link xml_node::comparison operator>]`(const xml_node& r) const;`
    * `bool `[link xml_node::comparison operator<=]`(const xml_node& r) const;`
    * `bool `[link xml_node::comparison operator>=]`(const xml_node& r) const;`
    [lbr]

    * `size_t `[link xml_node::hash_value hash_value]`() const;`
    [lbr]

    * `xml_node_type `[link xml_node::type type]`() const;`
    [lbr]

    * `const char_t* `[link xml_node::name name]`() const;`
    * `const char_t* `[link xml_node::value value]`() const;`
    [lbr]

    * `xml_node `[link xml_node::parent parent]`() const;`
    * `xml_node `[link xml_node::first_child first_child]`() const;`
    * `xml_node `[link xml_node::last_child last_child]`() const;`
    * `xml_node `[link xml_node::next_sibling next_sibling]`() const;`
    * `xml_node `[link xml_node::previous_sibling previous_sibling]`() const;`
    [lbr]

    * `xml_attribute `[link xml_node::first_attribute first_attribute]`() const;`
    * `xml_attribute `[link xml_node::last_attribute last_attribute]`() const;`
    [lbr]

    * `xml_node `[link xml_node::child child]`(const char_t* name) const;`
    * `xml_attribute `[link xml_node::attribute attribute]`(const char_t* name) const;`
    * `xml_node `[link xml_node::next_sibling_name next_sibling]`(const char_t* name) const;`
    * `xml_node `[link xml_node::previous_sibling_name previous_sibling]`(const char_t* name) const;`
    * `xml_node `[link xml_node::find_child_by_attribute find_child_by_attribute]`(const char_t* name, const char_t* attr_name, const char_t* attr_value) const;`
    * `xml_node `[link xml_node::find_child_by_attribute find_child_by_attribute]`(const char_t* attr_name, const char_t* attr_value) const;`
    [lbr]

    * `const char_t* `[link xml_node::child_value child_value]`() const;`
    * `const char_t* `[link xml_node::child_value child_value]`(const char_t* name) const;`
    [lbr]

    * `typedef xml_node_iterator `[link xml_node_iterator iterator]`;`
    * `iterator `[link xml_node::begin begin]`() const;`
    * `iterator `[link xml_node::end end]`() const;`
    [lbr]

    * `typedef xml_attribute_iterator `[link xml_attribute_iterator attribute_iterator]`;`
    * `attribute_iterator `[link xml_node::attributes_begin attributes_begin]`() const;`
    * `attribute_iterator `[link xml_node::attributes_end attributes_end]`() const;`
    [lbr]

    * `bool `[link xml_node::traverse traverse]`(xml_tree_walker& walker);`
    [lbr]

    * `template <typename Predicate> xml_attribute `[link xml_node::find_attribute find_attribute]`(Predicate pred) const;`
    * `template <typename Predicate> xml_node `[link xml_node::find_child find_child]`(Predicate pred) const;`
    * `template <typename Predicate> xml_node `[link xml_node::find_node find_node]`(Predicate pred) const;`
    [lbr]

    * `string_t `[link xml_node::path path]`(char_t delimiter = '/') const;`
    * `xml_node `[link xml_node::first_element_by_path]`(const char_t* path, char_t delimiter = '/') const;`
    * `xml_node `[link xml_node::root root]`() const;`
    * `ptrdiff_t `[link xml_node::offset_debug offset_debug]`() const;`
    [lbr]

    * `bool `[link xml_node::set_name set_name]`(const char_t* rhs);`
    * `bool `[link xml_node::set_value set_value]`(const char_t* rhs);`
    [lbr]

    * `xml_attribute `[link xml_node::append_attribute append_attribute]`(const char_t* name);`
    * `xml_attribute `[link xml_node::prepend_attribute prepend_attribute]`(const char_t* name);`
    * `xml_attribute `[link xml_node::insert_attribute_after insert_attribute_after]`(const char_t* name, const xml_attribute& attr);`
    * `xml_attribute `[link xml_node::insert_attribute_before insert_attribute_before]`(const char_t* name, const xml_attribute& attr);`
    [lbr]

    * `xml_node `[link xml_node::append_child append_child]`(xml_node_type type = node_element);`
    * `xml_node `[link xml_node::prepend_child prepend_child]`(xml_node_type type = node_element);`
    * `xml_node `[link xml_node::insert_child_after insert_child_after]`(xml_node_type type, const xml_node& node);`
    * `xml_node `[link xml_node::insert_child_before insert_child_before]`(xml_node_type type, const xml_node& node);`
    [lbr]

    * `xml_node `[link xml_node::append_child append_child]`(const char_t* name);`
    * `xml_node `[link xml_node::prepend_child prepend_child]`(const char_t* name);`
    * `xml_node `[link xml_node::insert_child_after insert_child_after]`(const char_t* name, const xml_node& node);`
    * `xml_node `[link xml_node::insert_child_before insert_child_before]`(const char_t* name, const xml_node& node);`
    [lbr]

    * `xml_attribute `[link xml_node::append_copy append_copy]`(const xml_attribute& proto);`
    * `xml_attribute `[link xml_node::prepend_copy prepend_copy]`(const xml_attribute& proto);`
    * `xml_attribute `[link xml_node::insert_copy_after insert_copy_after]`(const xml_attribute& proto, const xml_attribute& attr);`
    * `xml_attribute `[link xml_node::insert_copy_before insert_copy_before]`(const xml_attribute& proto, const xml_attribute& attr);`
    [lbr]

    * `xml_node `[link xml_node::append_copy append_copy]`(const xml_node& proto);`
    * `xml_node `[link xml_node::prepend_copy prepend_copy]`(const xml_node& proto);`
    * `xml_node `[link xml_node::insert_copy_after insert_copy_after]`(const xml_node& proto, const xml_node& node);`
    * `xml_node `[link xml_node::insert_copy_before insert_copy_before]`(const xml_node& proto, const xml_node& node);`
    [lbr]

    * `bool `[link xml_node::remove_attribute remove_attribute]`(const xml_attribute& a);`
    * `bool `[link xml_node::remove_attribute remove_attribute]`(const char_t* name);`
    * `bool `[link xml_node::remove_child remove_child]`(const xml_node& n);`
    * `bool `[link xml_node::remove_child remove_child]`(const char_t* name);`
    [lbr]

    * `void `[link xml_node::print 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 `[link xml_node::print_stream 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 `[link xml_node::print_stream print]`(std::wostream& os, const char_t* indent = "\t", unsigned int flags = format_default, unsigned int depth = 0) const;`
    [lbr]

    * `xpath_node `[link xml_node::select_single_node select_single_node]`(const char_t* query, xpath_variable_set* variables = 0) const;`
    * `xpath_node `[link xml_node::select_single_node_precomp select_single_node]`(const xpath_query& query) const;`
    * `xpath_node_set `[link xml_node::select_nodes select_nodes]`(const char_t* query, xpath_variable_set* variables = 0) const;`
    * `xpath_node_set `[link xml_node::select_nodes_precomp select_nodes]`(const xpath_query& query) const;`
    [lbr]

* `class `[link xml_document]
    * [link xml_document::ctor xml_document]`();`
    * `~`[link xml_document::dtor xml_document]`();`
    [lbr]

    * `void `[link xml_document::reset reset]`();`
    [lbr]

    * `xml_parse_result `[link xml_document::load_stream load]`(std::istream& stream, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);`
    * `xml_parse_result `[link xml_document::load_stream load]`(std::wistream& stream, unsigned int options = parse_default);`
    [lbr]

    * `xml_parse_result `[link xml_document::load_string load]`(const char_t* contents, unsigned int options = parse_default);`
    [lbr]

    * `xml_parse_result `[link xml_document::load_file load_file]`(const char* path, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);`
    * `xml_parse_result `[link xml_document::load_file_wide load_file]`(const wchar_t* path, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);`
    [lbr]

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

    * `bool `[link xml_document::save_file save_file]`(const char* path, const char_t* indent = "\t", unsigned int flags = format_default, xml_encoding encoding = encoding_auto) const;`
    * `bool `[link xml_document::save_file_wide save_file]`(const wchar_t* path, const char_t* indent = "\t", unsigned int flags = format_default, xml_encoding encoding = encoding_auto) const;`
    [lbr]

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

    * `void `[link xml_document::save save]`(xml_writer& writer, const char_t* indent = "\t", unsigned int flags = format_default, xml_encoding encoding = encoding_auto) const;`
    [lbr]

    * `xml_node `[link xml_document::document_element document_element]`() const;`
    [lbr]

* `struct `[link xml_parse_result]
    * `xml_parse_status `[link xml_parse_result::status status]`;`
    * `ptrdiff_t `[link xml_parse_result::offset offset]`;`
    * `xml_encoding `[link xml_parse_result::encoding encoding]`;`
    [lbr]

    * `operator `[link xml_parse_result::bool bool]`() const;`
    * `const char* `[link xml_parse_result::description description]`() const;`
    [lbr]

* `class `[link xml_node_iterator]
* `class `[link xml_attribute_iterator]
[lbr]

* `class `[link xml_tree_walker]
    * `virtual bool `[link xml_tree_walker::begin begin]`(xml_node& node);`
    * `virtual bool `[link xml_tree_walker::for_each for_each]`(xml_node& node) = 0;`
    * `virtual bool `[link xml_tree_walker::end end]`(xml_node& node);`
    [lbr]

    * `int `[link xml_tree_walker::depth depth]`() const;`
    [lbr]

* `class `[link xml_writer]
    * `virtual void `[link xml_writer::write write]`(const void* data, size_t size) = 0;`
    [lbr]

* `class `[link xml_writer_file]`: public xml_writer`
    * [link xml_writer_file]`(void* file);`
    [lbr]

* `class `[link xml_writer_stream]`: public xml_writer`
    * [link xml_writer_stream]`(std::ostream& stream);`
    * [link xml_writer_stream]`(std::wostream& stream);`
    [lbr]

* `struct `[link xpath_parse_result]
    * `const char* `[link xpath_parse_result::error error]`;`
    * `ptrdiff_t `[link xpath_parse_result::offset offset]`;`

    * `operator `[link xpath_parse_result::bool bool]`() const;`
    * `const char* `[link xpath_parse_result::description description]`() const;`
	[lbr]

* `class `[link xpath_query]
    * `explicit `[link xpath_query::ctor xpath_query]`(const char_t* query, xpath_variable_set* variables = 0);`
    [lbr]

    * `bool `[link xpath_query::evaluate_boolean evaluate_boolean]`(const xpath_node& n) const;`
    * `double `[link xpath_query::evaluate_number evaluate_number]`(const xpath_node& n) const;`
    * `string_t `[link xpath_query::evaluate_string evaluate_string]`(const xpath_node& n) const;`
	* `size_t `[link xpath_query::evaluate_string_buffer evaluate_string]`(char_t* buffer, size_t capacity, const xpath_node& n) const;`
    * `xpath_node_set `[link xpath_query::evaluate_node_set evaluate_node_set]`(const xpath_node& n) const;`
    [lbr]

    * `xpath_value_type `[link xpath_query::return_type return_type]`() const;`
    [lbr]

    * `const xpath_parse_result& `[link xpath_query::result result]`() const;`
	* `operator `[link xpath_query::unspecified_bool_type unspecified_bool_type]`() const;`
    [lbr]

* `class `[link xpath_exception]`: public std::exception`
    * `virtual const char* `[link xpath_exception::what what]`() const throw();`
    [lbr]

	* `const xpath_parse_result& `[link xpath_exception::result result]`() const;`
    [lbr]

* `class `[link xpath_node]
    * [link xpath_node::ctor xpath_node]`();`
    * [link xpath_node::ctor xpath_node]`(const xml_node& node);`
    * [link xpath_node::ctor xpath_node]`(const xml_attribute& attribute, const xml_node& parent);`
    [lbr]

    * `xml_node `[link xpath_node::node node]`() const;`
    * `xml_attribute `[link xpath_node::attribute attribute]`() const;`
    * `xml_node `[link xpath_node::parent parent]`() const;`
    [lbr]

    * `operator `[link xpath_node::unspecified_bool_type unspecified_bool_type]`() const;`
    * `bool `[link xpath_node::comparison operator==]`(const xpath_node& n) const;`
    * `bool `[link xpath_node::comparison operator!=]`(const xpath_node& n) const;`
    [lbr]

* `class `[link xpath_node_set]
	* [link xpath_node_set::ctor xpath_node_set]`();`
	* [link xpath_node_set::ctor xpath_node_set]`(const_iterator begin, const_iterator end, type_t type = type_unsorted);`
    [lbr]

    * `typedef const xpath_node* `[link xpath_node_set::const_iterator const_iterator]`;`
    * `const_iterator `[link xpath_node_set::begin begin]`() const;`
    * `const_iterator `[link xpath_node_set::end end]`() const;`
    [lbr]

    * `const xpath_node& `[link xpath_node_set::index operator\[\]]`(size_t index) const;`
    * `size_t `[link xpath_node_set::size size]`() const;`
    * `bool `[link xpath_node_set::empty empty]`() const;`
    [lbr]

    * `xpath_node `[link xpath_node_set::first first]`() const;`
    [lbr]

    * `enum type_t {`[link xpath_node_set::type_unsorted type_unsorted], [link xpath_node_set::type_sorted type_sorted], [link xpath_node_set::type_sorted_reverse type_sorted_reverse]`};`
    * `type_t `[link xpath_node_set::type type]`() const;`
    * `void `[link xpath_node_set::sort sort]`(bool reverse = false);`
    [lbr]

* `class `[link xpath_variable]
    * `const char_t* `[link xpath_variable::name name]`() const;`
    * `xpath_value_type `[link xpath_variable::type type]`() const;`
    [lbr]

    * `bool `[link xpath_variable::get_boolean get_boolean]`() const;`
    * `double `[link xpath_variable::get_number get_number]`() const;`
    * `const char_t* `[link xpath_variable::get_string get_string]`() const;`
    * `const xpath_node_set& `[link xpath_variable::get_node_set get_node_set]`() const;`
    [lbr]

    * `bool `[link xpath_variable::set set]`(bool value);`
    * `bool `[link xpath_variable::set set]`(double value);`
    * `bool `[link xpath_variable::set set]`(const char_t* value);`
    * `bool `[link xpath_variable::set set]`(const xpath_node_set& value);`
    [lbr]

* `class `[link xpath_variable_set]
    * `xpath_variable* `[link xpath_variable_set::add add]`(const char_t* name, xpath_value_type type);`
    [lbr]

    * `bool `[link xpath_variable_set::set set]`(const char_t* name, bool value);`
    * `bool `[link xpath_variable_set::set set]`(const char_t* name, double value);`
    * `bool `[link xpath_variable_set::set set]`(const char_t* name, const char_t* value);`
    * `bool `[link xpath_variable_set::set set]`(const char_t* name, const xpath_node_set& value);`
    [lbr]

    * `xpath_variable* `[link xpath_variable_set::get get]`(const char_t* name);`
    * `const xpath_variable* `[link xpath_variable_set::get get]`(const char_t* name) const;`
    [lbr]

Functions:

* `std::string `[link as_utf8]`(const wchar_t* str);`
* `std::string `[link as_utf8]`(const std::wstring& str);`
* `std::wstring `[link as_wide]`(const char* str);`
* `std::wstring `[link as_wide]`(const std::string& str);`
* `void `[link set_memory_management_functions]`(allocation_function allocate, deallocation_function deallocate);`
* `allocation_function `[link get_memory_allocation_function]`();`
* `deallocation_function `[link get_memory_deallocation_function]`();`

[endsect] [/apiref]

[section:toc Table of Contents]

toc-placeholder

[endsect] [/toc]

[/ vim:et ]