Commit 9d8a9ea8 by Rémi Verschelde

assimp: Clean and document buildsystem, prepare for unbundling

- Improve the SCsub to allow unbundling and remove unnecessary code. - Move files around to match upstream source. - Re-sync with upstream commit 308db73d0b3c2d1870cd3e465eaa283692a4cf23 to ensure we don't have local modifications. - Doesn't actually build against current version 5.0.1 due to the lack of the new ArmaturePopulate API that Gordon authored. We'll have to wait for a public release with that API (5.1?) to enable unbundling.
parent 1e255532
......@@ -136,6 +136,7 @@ opts.Add(BoolVariable('no_editor_splash', "Don't use the custom splash screen fo
opts.Add('system_certs_path', "Use this path as SSL certificates default for editor (for package maintainers)", '')
# Thirdparty libraries
#opts.Add(BoolVariable('builtin_assimp', "Use the built-in Assimp library", True))
opts.Add(BoolVariable('builtin_bullet', "Use the built-in Bullet library", True))
opts.Add(BoolVariable('builtin_certs', "Bundle default SSL certificates to be used if you don't specify an override in the project settings", True))
opts.Add(BoolVariable('builtin_enet', "Use the built-in ENet library", True))
......
......@@ -4,97 +4,91 @@ Import('env')
Import('env_modules')
env_assimp = env_modules.Clone()
env_assimp.Prepend(CPPPATH=['#thirdparty/assimp'])
env_assimp.Prepend(CPPPATH=['#thirdparty/assimp/include'])
env_assimp.Prepend(CPPPATH=['#thirdparty/assimp/code/Importer/IFC'])
env_assimp.Prepend(CPPPATH=['#thirdparty/misc'])
env_assimp.Prepend(CPPPATH=['#thirdparty/assimp/code'])
env_assimp.Prepend(CPPPATH=['#thirdparty/assimp/common'])
env_assimp.Prepend(CPPPATH=['#thirdparty/assimp/contrib/irrXML/'])
env_assimp.Prepend(CPPPATH=['#thirdparty/assimp/contrib/unzip/'])
env_assimp.Prepend(CPPPATH=['#thirdparty/assimp/code/Importer/STEPParser'])
env_assimp.Prepend(CPPPATH=['#thirdparty/assimp/'])
env_assimp.Prepend(CPPPATH=['#thirdparty/zlib/'])
env_assimp.Prepend(CPPPATH=['#thirdparty/assimp/contrib/openddlparser/include'])
env_assimp.Prepend(CPPPATH=['#thirdparty/assimp/contrib/rapidjson/include'])
env_assimp.Prepend(CPPPATH=['.'])
#env_assimp.Append(CPPDEFINES=['ASSIMP_DOUBLE_PRECISION']) # TODO default to what godot is compiled with for future double support
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_BOOST_WORKAROUND'])
env_assimp.Append(CPPDEFINES=['OPENDDLPARSER_BUILD'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_OWN_ZLIB'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_EXPORT'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_X_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_AMF_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_3DS_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_MD3_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_MD5_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_MDL_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_MD2_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_PLY_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_ASE_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_OBJ_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_HMP_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_SMD_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_MDC_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_MD5_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_STL_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_LWO_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_DXF_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_NFF_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_RAW_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_SIB_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_OFF_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_AC_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_BVH_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_IRRMESH_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_IRR_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_Q3D_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_B3D_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_COLLADA_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_TERRAGEN_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_CSM_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_3D_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_LWS_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_OGRE_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_OPENGEX_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_MS3D_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_COB_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_BLEND_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_Q3BSP_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_NDO_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_STEP_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_IFC_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_XGL_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_ASSBIN_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_C4D_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_3MF_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_X3D_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_GLTF_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_GLTF2_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_SINGLETHREADED'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_M3D_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_MMD_IMPORTER'])
# Force bundled version for now, there's no released version of Assimp with
# support for ArmaturePopulate which we use from their master branch.
if True: # env['builtin_assimp']:
thirdparty_dir = "#thirdparty/assimp"
if(env['platform'] == 'windows'):
env_assimp.Append(CPPDEFINES=['PLATFORM_WINDOWS'])
env_assimp.Append(CPPDEFINES=[('PLATFORM', 'WINDOWS')])
elif(env['platform'] == 'x11'):
env_assimp.Append(CPPDEFINES=['PLATFORM_LINUX'])
env_assimp.Append(CPPDEFINES=[('PLATFORM', 'LINUX')])
elif(env['platform'] == 'osx'):
env_assimp.Append(CPPDEFINES=['PLATFORM_DARWIN'])
env_assimp.Append(CPPDEFINES=[('PLATFORM', 'DARWIN')])
env_assimp.Prepend(CPPPATH=['#thirdparty/assimp'])
env_assimp.Prepend(CPPPATH=['#thirdparty/assimp/code'])
env_assimp.Prepend(CPPPATH=['#thirdparty/assimp/include'])
#env_assimp.Append(CPPDEFINES=['ASSIMP_DOUBLE_PRECISION']) # TODO default to what godot is compiled with for future double support
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_SINGLETHREADED'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_BOOST_WORKAROUND'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_OWN_ZLIB'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_EXPORT'])
# Importers we don't need
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_3D_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_3DS_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_3MF_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_AC_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_AMF_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_ASE_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_ASSBIN_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_B3D_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_BLEND_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_BVH_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_C4D_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_COB_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_COLLADA_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_CSM_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_DXF_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_GLTF2_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_GLTF_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_HMP_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_IFC_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_IRR_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_IRRMESH_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_LWO_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_LWS_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_M3D_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_MD2_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_MD3_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_MD5_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_MD5_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_MDC_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_MDL_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_MMD_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_MS3D_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_NDO_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_NFF_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_OBJ_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_OFF_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_OGRE_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_OPENGEX_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_PLY_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_Q3BSP_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_Q3D_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_RAW_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_SIB_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_SMD_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_STEP_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_STL_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_TERRAGEN_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_X3D_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_XGL_IMPORTER'])
env_assimp.Append(CPPDEFINES=['ASSIMP_BUILD_NO_X_IMPORTER'])
if(env['platform'] == 'windows'):
env_assimp.Append(CPPDEFINES=['PLATFORM_WINDOWS'])
env_assimp.Append(CPPDEFINES=[('PLATFORM', 'WINDOWS')])
elif(env['platform'] == 'x11'):
env_assimp.Append(CPPDEFINES=['PLATFORM_LINUX'])
env_assimp.Append(CPPDEFINES=[('PLATFORM', 'LINUX')])
elif(env['platform'] == 'osx'):
env_assimp.Append(CPPDEFINES=['PLATFORM_DARWIN'])
env_assimp.Append(CPPDEFINES=[('PLATFORM', 'DARWIN')])
env_thirdparty = env_assimp.Clone()
env_thirdparty.disable_warnings()
env_thirdparty.add_source_files(env.modules_sources, Glob('#thirdparty/assimp/code/Common/*.cpp'))
env_thirdparty.add_source_files(env.modules_sources, Glob('#thirdparty/assimp/code/PostProcessing/*.cpp'))
env_thirdparty.add_source_files(env.modules_sources, Glob('#thirdparty/assimp/code/Material/*.cpp'))
env_thirdparty.add_source_files(env.modules_sources, Glob('#thirdparty/assimp/code/FBX/*.cpp'))
env_thirdparty.add_source_files(env.modules_sources, Glob('#thirdparty/assimp/code/MMD/*.cpp'))
env_thirdparty.add_source_files(env.modules_sources, Glob('#thirdparty/assimp/code/glTF/*.cpp'))
env_thirdparty.add_source_files(env.modules_sources, Glob('#thirdparty/assimp/code/glTF2/*.cpp'))
env_thirdparty = env_assimp.Clone()
env_thirdparty.disable_warnings()
env_thirdparty.add_source_files(env.modules_sources, Glob('#thirdparty/assimp/code/CApi/*.cpp'))
env_thirdparty.add_source_files(env.modules_sources, Glob('#thirdparty/assimp/code/Common/*.cpp'))
env_thirdparty.add_source_files(env.modules_sources, Glob('#thirdparty/assimp/code/PostProcessing/*.cpp'))
env_thirdparty.add_source_files(env.modules_sources, Glob('#thirdparty/assimp/code/Material/*.cpp'))
env_thirdparty.add_source_files(env.modules_sources, Glob('#thirdparty/assimp/code/FBX/*.cpp'))
# Godot's own source files
env_assimp.add_source_files(env.modules_sources, "*.cpp")
......@@ -163,6 +163,10 @@ def configure(env):
sys.exit(255)
env.ParseConfig('pkg-config bullet --cflags --libs')
if False: # not env['builtin_assimp']:
# FIXME: Add min version check
env.ParseConfig('pkg-config assimp --cflags --libs')
if not env['builtin_enet']:
env.ParseConfig('pkg-config libenet --cflags --libs')
......
import os
import platform
import sys
from methods import using_gcc, using_clang
def is_active():
......@@ -226,6 +225,10 @@ def configure(env):
sys.exit(255)
env.ParseConfig('pkg-config bullet --cflags --libs')
if False: # not env['builtin_assimp']:
# FIXME: Add min version check
env.ParseConfig('pkg-config assimp --cflags --libs')
if not env['builtin_enet']:
env.ParseConfig('pkg-config libenet --cflags --libs')
......
......@@ -9,9 +9,20 @@ Subcategories (`###` level) where needed are separated by a single empty line.
## assimp
- Upstream: http://github.com/assimp/assimp
- Version: git (308db73d0b3c2d1870cd3e465eaa283692a4cf23)
- Version: git (308db73d0b3c2d1870cd3e465eaa283692a4cf23, 2019)
- License: BSD-3-Clause
Files extracted from upstream source:
- Run `cmake .` in root folder to generate files
- `code/{CApi,Common,FBX,Material,PostProcessing}/`
- `contrib/utf8cpp/source/`
- `include/`
- `revision.h`
- `CREDITS` and `LICENSE` files
- `rm -f code/Common/ZipArchiveIOSystem.cpp include/assimp/ZipArchiveIOSystem.h
include/assimp/irrXMLWrapper.h`
## basis_universal
......
utf8 cpp library
Release 2.3.4
A minor bug fix release. Thanks to all who reported bugs.
Note: Version 2.3.3 contained a regression, and therefore was removed.
Changes from version 2.3.2
- Bug fix [39]: checked.h Line 273 and unchecked.h Line 182 have an extra ';'
- Bug fix [36]: replace_invalid() only works with back_inserter
Files included in the release: utf8.h, core.h, checked.h, unchecked.h, utf8cpp.html, ReleaseNotes
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>
<head>
<meta name="generator" content=
"HTML Tidy for Linux/x86 (vers 1st November 2002), see www.w3.org">
<meta name="description" content=
"A simple, portable and lightweigt C++ library for easy handling of UTF-8 encoded strings">
<meta name="keywords" content="UTF-8 C++ portable utf8 unicode generic templates">
<meta name="author" content="Nemanja Trifunovic">
<title>
UTF8-CPP: UTF-8 with C++ in a Portable Way
</title>
<style type="text/css">
<!--
span.return_value {
color: brown;
}
span.keyword {
color: blue;
}
span.preprocessor {
color: navy;
}
span.literal {
color: olive;
}
span.comment {
color: green;
}
code {
font-weight: bold;
}
ul.toc {
list-style-type: none;
}
p.version {
font-size: small;
font-style: italic;
}
-->
</style>
</head>
<body>
<h1>
UTF8-CPP: UTF-8 with C++ in a Portable Way
</h1>
<p>
<a href="https://sourceforge.net/projects/utfcpp">The Sourceforge project page</a>
</p>
<div id="toc">
<h2>
Table of Contents
</h2>
<ul class="toc">
<li>
<a href="#introduction">Introduction</a>
</li>
<li>
<a href="#examples">Examples of Use</a>
<ul class="toc">
<li>
<a href=#introsample>Introductionary Sample </a>
</li>
<li>
<a href=#validfile>Checking if a file contains valid UTF-8 text</a>
</li>
<li>
<a href=#fixinvalid>Ensure that a string contains valid UTF-8 text</a>
</li>
</ul>
<li>
<a href="#reference">Reference</a>
<ul class="toc">
<li>
<a href="#funutf8">Functions From utf8 Namespace </a>
</li>
<li>
<a href="#typesutf8">Types From utf8 Namespace </a>
</li>
<li>
<a href="#fununchecked">Functions From utf8::unchecked Namespace </a>
</li>
<li>
<a href="#typesunchecked">Types From utf8::unchecked Namespace </a>
</li>
</ul>
</li>
<li>
<a href="#points">Points of Interest</a>
</li>
<li>
<a href="#links">Links</a>
</li>
</ul>
</div>
<h2 id="introduction">
Introduction
</h2>
<p>
Many C++ developers miss an easy and portable way of handling Unicode encoded
strings. The original C++ Standard (known as C++98 or C++03) is Unicode agnostic.
C++11 provides some support for Unicode on core language and library level:
u8, u, and U character and string literals, char16_t and char32_t character types,
u16string and u32string library classes, and codecvt support for conversions
between Unicode encoding forms.
In the meantime, developers use third party libraries like ICU, OS specific capabilities, or simply
roll out their own solutions.
</p>
<p>
In order to easily handle UTF-8 encoded Unicode strings, I came up with a small
generic library. For anybody used to work with STL algorithms and iterators, it should be
easy and natural to use. The code is freely available for any purpose - check out
the license at the beginning of the utf8.h file. If you run into
bugs or performance issues, please let me know and I'll do my best to address them.
</p>
<p>
The purpose of this article is not to offer an introduction to Unicode in general,
and UTF-8 in particular. If you are not familiar with Unicode, be sure to check out
<a href="http://www.unicode.org/">Unicode Home Page</a> or some other source of
information for Unicode. Also, it is not my aim to advocate the use of UTF-8
encoded strings in C++ programs; if you want to handle UTF-8 encoded strings from
C++, I am sure you have good reasons for it.
</p>
<h2 id="examples">
Examples of use
</h2>
<h3 id="introsample">
Introductionary Sample
</h3>
<p>
To illustrate the use of the library, let's start with a small but complete program
that opens a file containing UTF-8 encoded text, reads it line by line, checks each line
for invalid UTF-8 byte sequences, and converts it to UTF-16 encoding and back to UTF-8:
</p>
<pre>
<span class="preprocessor">#include &lt;fstream&gt;</span>
<span class="preprocessor">#include &lt;iostream&gt;</span>
<span class="preprocessor">#include &lt;string&gt;</span>
<span class="preprocessor">#include &lt;vector&gt;</span>
<span class="preprocessor">#include "utf8.h"</span>
<span class="keyword">using namespace</span> std;
<span class="keyword">int</span> main(<span class="keyword">int</span> argc, <span class="keyword">char</span>** argv)
{
<span class="keyword">if</span> (argc != <span class="literal">2</span>) {
cout &lt;&lt; <span class="literal">"\nUsage: docsample filename\n"</span>;
<span class="keyword">return</span> <span class="literal">0</span>;
}
<span class="keyword">const char</span>* test_file_path = argv[1];
<span class="comment">// Open the test file (contains UTF-8 encoded text)</span>
ifstream fs8(test_file_path);
<span class="keyword">if</span> (!fs8.is_open()) {
cout &lt;&lt; <span class=
"literal">"Could not open "</span> &lt;&lt; test_file_path &lt;&lt; endl;
<span class="keyword">return</span> <span class="literal">0</span>;
}
<span class="keyword">unsigned</span> line_count = <span class="literal">1</span>;
string line;
<span class="comment">// Play with all the lines in the file</span>
<span class="keyword">while</span> (getline(fs8, line)) {
<span class="comment">// check for invalid utf-8 (for a simple yes/no check, there is also utf8::is_valid function)</span>
string::iterator end_it = utf8::find_invalid(line.begin(), line.end());
<span class="keyword">if</span> (end_it != line.end()) {
cout &lt;&lt; <span class=
"literal">"Invalid UTF-8 encoding detected at line "</span> &lt;&lt; line_count &lt;&lt; <span
class="literal">"\n"</span>;
cout &lt;&lt; <span class=
"literal">"This part is fine: "</span> &lt;&lt; string(line.begin(), end_it) &lt;&lt; <span
class="literal">"\n"</span>;
}
<span class="comment">// Get the line length (at least for the valid part)</span>
<span class="keyword">int</span> length = utf8::distance(line.begin(), end_it);
cout &lt;&lt; <span class=
"literal">"Length of line "</span> &lt;&lt; line_count &lt;&lt; <span class=
"literal">" is "</span> &lt;&lt; length &lt;&lt; <span class="literal">"\n"</span>;
<span class="comment">// Convert it to utf-16</span>
vector&lt;unsigned short&gt; utf16line;
utf8::utf8to16(line.begin(), end_it, back_inserter(utf16line));
<span class="comment">// And back to utf-8</span>
string utf8line;
utf8::utf16to8(utf16line.begin(), utf16line.end(), back_inserter(utf8line));
<span class="comment">// Confirm that the conversion went OK:</span>
<span class="keyword">if</span> (utf8line != string(line.begin(), end_it))
cout &lt;&lt; <span class=
"literal">"Error in UTF-16 conversion at line: "</span> &lt;&lt; line_count &lt;&lt; <span
class="literal">"\n"</span>;
line_count++;
}
<span class="keyword">return</span> <span class="literal">0</span>;
}
</pre>
<p>
In the previous code sample, for each line we performed
a detection of invalid UTF-8 sequences with <code>find_invalid</code>; the number
of characters (more precisely - the number of Unicode code points, including the end
of line and even BOM if there is one) in each line was
determined with a use of <code>utf8::distance</code>; finally, we have converted
each line to UTF-16 encoding with <code>utf8to16</code> and back to UTF-8 with
<code>utf16to8</code>.
</p>
<h3 id="validfile">Checking if a file contains valid UTF-8 text</h3>
<p>
Here is a function that checks whether the content of a file is valid UTF-8 encoded text without
reading the content into the memory:
</p>
<pre>
<span class="keyword">bool</span> valid_utf8_file(i<span class="keyword">const char</span>* file_name)
{
ifstream ifs(file_name);
<span class="keyword">if</span> (!ifs)
<span class="keyword">return false</span>; <span class="comment">// even better, throw here</span>
istreambuf_iterator&lt;<span class="keyword">char</span>&gt; it(ifs.rdbuf());
istreambuf_iterator&lt;<span class="keyword">char</span>&gt; eos;
<span class="keyword">return</span> utf8::is_valid(it, eos);
}
</pre>
<p>
Because the function <code>utf8::is_valid()</code> works with input iterators, we were able
to pass an <code>istreambuf_iterator</code> to it and read the content of the file directly
without loading it to the memory first.</p>
<p>
Note that other functions that take input iterator arguments can be used in a similar way. For
instance, to read the content of a UTF-8 encoded text file and convert the text to UTF-16, just
do something like:
</p>
<pre>
utf8::utf8to16(it, eos, back_inserter(u16string));
</pre>
<h3 id="fixinvalid">Ensure that a string contains valid UTF-8 text</h3>
<p>
If we have some text that "probably" contains UTF-8 encoded text and we want to
replace any invalid UTF-8 sequence with a replacement character, something like
the following function may be used:
</p>
<pre>
<span class="keyword">void</span> fix_utf8_string(std::string&amp; str)
{
std::string temp;
utf8::replace_invalid(str.begin(), str.end(), back_inserter(temp));
str = temp;
}
</pre>
<p>The function will replace any invalid UTF-8 sequence with a Unicode replacement character.
There is an overloaded function that enables the caller to supply their own replacement character.
</p>
<h2 id="reference">
Reference
</h2>
<h3 id="funutf8">
Functions From utf8 Namespace
</h3>
<h4>
utf8::append
</h4>
<p class="version">
Available in version 1.0 and later.
</p>
<p>
Encodes a 32 bit code point as a UTF-8 sequence of octets and appends the sequence
to a UTF-8 string.
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> octet_iterator&gt;
octet_iterator append(uint32_t cp, octet_iterator result);
</pre>
<p>
<code>octet_iterator</code>: an output iterator.<br>
<code>cp</code>: a 32 bit integer representing a code point to append to the
sequence.<br>
<code>result</code>: an output iterator to the place in the sequence where to
append the code point.<br>
<span class="return_value">Return value</span>: an iterator pointing to the place
after the newly appended sequence.
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">unsigned char</span> u[<span class="literal">5</span>] = {<span
class="literal">0</span>,<span class="literal">0</span>,<span class=
"literal">0</span>,<span class="literal">0</span>,<span class="literal">0</span>};
<span class="keyword">unsigned char</span>* end = append(<span class=
"literal">0x0448</span>, u);
assert (u[<span class="literal">0</span>] == <span class=
"literal">0xd1</span> &amp;&amp; u[<span class="literal">1</span>] == <span class=
"literal">0x88</span> &amp;&amp; u[<span class="literal">2</span>] == <span class=
"literal">0</span> &amp;&amp; u[<span class="literal">3</span>] == <span class=
"literal">0</span> &amp;&amp; u[<span class="literal">4</span>] == <span class=
"literal">0</span>);
</pre>
<p>
Note that <code>append</code> does not allocate any memory - it is the burden of
the caller to make sure there is enough memory allocated for the operation. To make
things more interesting, <code>append</code> can add anywhere between 1 and 4
octets to the sequence. In practice, you would most often want to use
<code>std::back_inserter</code> to ensure that the necessary memory is allocated.
</p>
<p>
In case of an invalid code point, a <code>utf8::invalid_code_point</code> exception
is thrown.
</p>
<h4>
utf8::next
</h4>
<p class="version">
Available in version 1.0 and later.
</p>
<p>
Given the iterator to the beginning of the UTF-8 sequence, it returns the code
point and moves the iterator to the next position.
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> octet_iterator&gt;
uint32_t next(octet_iterator&amp; it, octet_iterator end);
</pre>
<p>
<code>octet_iterator</code>: an input iterator.<br>
<code>it</code>: a reference to an iterator pointing to the beginning of an UTF-8
encoded code point. After the function returns, it is incremented to point to the
beginning of the next code point.<br>
<code>end</code>: end of the UTF-8 sequence to be processed. If <code>it</code>
gets equal to <code>end</code> during the extraction of a code point, an
<code>utf8::not_enough_room</code> exception is thrown.<br>
<span class="return_value">Return value</span>: the 32 bit representation of the
processed UTF-8 code point.
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">char</span>* twochars = <span class=
"literal">"\xe6\x97\xa5\xd1\x88"</span>;
<span class="keyword">char</span>* w = twochars;
<span class="keyword">int</span> cp = next(w, twochars + <span class="literal">6</span>);
assert (cp == <span class="literal">0x65e5</span>);
assert (w == twochars + <span class="literal">3</span>);
</pre>
<p>
This function is typically used to iterate through a UTF-8 encoded string.
</p>
<p>
In case of an invalid UTF-8 seqence, a <code>utf8::invalid_utf8</code> exception is
thrown.
</p>
<h4>
utf8::peek_next
</h4>
<p class="version">
Available in version 2.1 and later.
</p>
<p>
Given the iterator to the beginning of the UTF-8 sequence, it returns the code
point for the following sequence without changing the value of the iterator.
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> octet_iterator&gt;
uint32_t peek_next(octet_iterator it, octet_iterator end);
</pre>
<p>
<code>octet_iterator</code>: an input iterator.<br>
<code>it</code>: an iterator pointing to the beginning of an UTF-8
encoded code point.<br>
<code>end</code>: end of the UTF-8 sequence to be processed. If <code>it</code>
gets equal to <code>end</code> during the extraction of a code point, an
<code>utf8::not_enough_room</code> exception is thrown.<br>
<span class="return_value">Return value</span>: the 32 bit representation of the
processed UTF-8 code point.
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">char</span>* twochars = <span class=
"literal">"\xe6\x97\xa5\xd1\x88"</span>;
<span class="keyword">char</span>* w = twochars;
<span class="keyword">int</span> cp = peek_next(w, twochars + <span class="literal">6</span>);
assert (cp == <span class="literal">0x65e5</span>);
assert (w == twochars);
</pre>
<p>
In case of an invalid UTF-8 seqence, a <code>utf8::invalid_utf8</code> exception is
thrown.
</p>
<h4>
utf8::prior
</h4>
<p class="version">
Available in version 1.02 and later.
</p>
<p>
Given a reference to an iterator pointing to an octet in a UTF-8 sequence, it
decreases the iterator until it hits the beginning of the previous UTF-8 encoded
code point and returns the 32 bits representation of the code point.
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> octet_iterator&gt;
uint32_t prior(octet_iterator&amp; it, octet_iterator start);
</pre>
<p>
<code>octet_iterator</code>: a bidirectional iterator.<br>
<code>it</code>: a reference pointing to an octet within a UTF-8 encoded string.
After the function returns, it is decremented to point to the beginning of the
previous code point.<br>
<code>start</code>: an iterator to the beginning of the sequence where the search
for the beginning of a code point is performed. It is a
safety measure to prevent passing the beginning of the string in the search for a
UTF-8 lead octet.<br>
<span class="return_value">Return value</span>: the 32 bit representation of the
previous code point.
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">char</span>* twochars = <span class=
"literal">"\xe6\x97\xa5\xd1\x88"</span>;
<span class="keyword">unsigned char</span>* w = twochars + <span class=
"literal">3</span>;
<span class="keyword">int</span> cp = prior (w, twochars);
assert (cp == <span class="literal">0x65e5</span>);
assert (w == twochars);
</pre>
<p>
This function has two purposes: one is two iterate backwards through a UTF-8
encoded string. Note that it is usually a better idea to iterate forward instead,
since <code>utf8::next</code> is faster. The second purpose is to find a beginning
of a UTF-8 sequence if we have a random position within a string. Note that in that
case <code>utf8::prior</code> may not detect an invalid UTF-8 sequence in some scenarios:
for instance if there are superfluous trail octets, it will just skip them.
</p>
<p>
<code>it</code> will typically point to the beginning of
a code point, and <code>start</code> will point to the
beginning of the string to ensure we don't go backwards too far. <code>it</code> is
decreased until it points to a lead UTF-8 octet, and then the UTF-8 sequence
beginning with that octet is decoded to a 32 bit representation and returned.
</p>
<p>
In case <code>start</code> is reached before a UTF-8 lead octet is hit, or if an
invalid UTF-8 sequence is started by the lead octet, an <code>invalid_utf8</code>
exception is thrown.
</p>
<p>In case <code>start</code> equals <code>it</code>, a <code>not_enough_room</code>
exception is thrown.
<h4>
utf8::previous
</h4>
<p class="version">
Deprecated in version 1.02 and later.
</p>
<p>
Given a reference to an iterator pointing to an octet in a UTF-8 seqence, it
decreases the iterator until it hits the beginning of the previous UTF-8 encoded
code point and returns the 32 bits representation of the code point.
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> octet_iterator&gt;
uint32_t previous(octet_iterator&amp; it, octet_iterator pass_start);
</pre>
<p>
<code>octet_iterator</code>: a random access iterator.<br>
<code>it</code>: a reference pointing to an octet within a UTF-8 encoded string.
After the function returns, it is decremented to point to the beginning of the
previous code point.<br>
<code>pass_start</code>: an iterator to the point in the sequence where the search
for the beginning of a code point is aborted if no result was reached. It is a
safety measure to prevent passing the beginning of the string in the search for a
UTF-8 lead octet.<br>
<span class="return_value">Return value</span>: the 32 bit representation of the
previous code point.
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">char</span>* twochars = <span class=
"literal">"\xe6\x97\xa5\xd1\x88"</span>;
<span class="keyword">unsigned char</span>* w = twochars + <span class=
"literal">3</span>;
<span class="keyword">int</span> cp = previous (w, twochars - <span class=
"literal">1</span>);
assert (cp == <span class="literal">0x65e5</span>);
assert (w == twochars);
</pre>
<p>
<code>utf8::previous</code> is deprecated, and <code>utf8::prior</code> should
be used instead, although the existing code can continue using this function.
The problem is the parameter <code>pass_start</code> that points to the position
just before the beginning of the sequence. Standard containers don't have the
concept of "pass start" and the function can not be used with their iterators.
</p>
<p>
<code>it</code> will typically point to the beginning of
a code point, and <code>pass_start</code> will point to the octet just before the
beginning of the string to ensure we don't go backwards too far. <code>it</code> is
decreased until it points to a lead UTF-8 octet, and then the UTF-8 sequence
beginning with that octet is decoded to a 32 bit representation and returned.
</p>
<p>
In case <code>pass_start</code> is reached before a UTF-8 lead octet is hit, or if an
invalid UTF-8 sequence is started by the lead octet, an <code>invalid_utf8</code>
exception is thrown
</p>
<h4>
utf8::advance
</h4>
<p class="version">
Available in version 1.0 and later.
</p>
<p>
Advances an iterator by the specified number of code points within an UTF-8
sequence.
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> octet_iterator, typename distance_type&gt;
<span class=
"keyword">void</span> advance (octet_iterator&amp; it, distance_type n, octet_iterator end);
</pre>
<p>
<code>octet_iterator</code>: an input iterator.<br>
<code>distance_type</code>: an integral type convertible to <code>octet_iterator</code>'s difference type.<br>
<code>it</code>: a reference to an iterator pointing to the beginning of an UTF-8
encoded code point. After the function returns, it is incremented to point to the
nth following code point.<br>
<code>n</code>: a positive integer that shows how many code points we want to
advance.<br>
<code>end</code>: end of the UTF-8 sequence to be processed. If <code>it</code>
gets equal to <code>end</code> during the extraction of a code point, an
<code>utf8::not_enough_room</code> exception is thrown.<br>
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">char</span>* twochars = <span class=
"literal">"\xe6\x97\xa5\xd1\x88"</span>;
<span class="keyword">unsigned char</span>* w = twochars;
advance (w, <span class="literal">2</span>, twochars + <span class="literal">6</span>);
assert (w == twochars + <span class="literal">5</span>);
</pre>
<p>
This function works only "forward". In case of a negative <code>n</code>, there is
no effect.
</p>
<p>
In case of an invalid code point, a <code>utf8::invalid_code_point</code> exception
is thrown.
</p>
<h4>
utf8::distance
</h4>
<p class="version">
Available in version 1.0 and later.
</p>
<p>
Given the iterators to two UTF-8 encoded code points in a seqence, returns the
number of code points between them.
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> octet_iterator&gt;
<span class=
"keyword">typename</span> std::iterator_traits&lt;octet_iterator&gt;::difference_type distance (octet_iterator first, octet_iterator last);
</pre>
<p>
<code>octet_iterator</code>: an input iterator.<br>
<code>first</code>: an iterator to a beginning of a UTF-8 encoded code point.<br>
<code>last</code>: an iterator to a "post-end" of the last UTF-8 encoded code
point in the sequence we are trying to determine the length. It can be the
beginning of a new code point, or not.<br>
<span class="return_value">Return value</span> the distance between the iterators,
in code points.
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">char</span>* twochars = <span class=
"literal">"\xe6\x97\xa5\xd1\x88"</span>;
size_t dist = utf8::distance(twochars, twochars + <span class="literal">5</span>);
assert (dist == <span class="literal">2</span>);
</pre>
<p>
This function is used to find the length (in code points) of a UTF-8 encoded
string. The reason it is called <em>distance</em>, rather than, say,
<em>length</em> is mainly because developers are used that <em>length</em> is an
O(1) function. Computing the length of an UTF-8 string is a linear operation, and
it looked better to model it after <code>std::distance</code> algorithm.
</p>
<p>
In case of an invalid UTF-8 seqence, a <code>utf8::invalid_utf8</code> exception is
thrown. If <code>last</code> does not point to the past-of-end of a UTF-8 seqence,
a <code>utf8::not_enough_room</code> exception is thrown.
</p>
<h4>
utf8::utf16to8
</h4>
<p class="version">
Available in version 1.0 and later.
</p>
<p>
Converts a UTF-16 encoded string to UTF-8.
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> u16bit_iterator, <span class=
"keyword">typename</span> octet_iterator&gt;
octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result);
</pre>
<p>
<code>u16bit_iterator</code>: an input iterator.<br>
<code>octet_iterator</code>: an output iterator.<br>
<code>start</code>: an iterator pointing to the beginning of the UTF-16 encoded
string to convert.<br>
<code>end</code>: an iterator pointing to pass-the-end of the UTF-16 encoded
string to convert.<br>
<code>result</code>: an output iterator to the place in the UTF-8 string where to
append the result of conversion.<br>
<span class="return_value">Return value</span>: An iterator pointing to the place
after the appended UTF-8 string.
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">unsigned short</span> utf16string[] = {<span class=
"literal">0x41</span>, <span class="literal">0x0448</span>, <span class=
"literal">0x65e5</span>, <span class="literal">0xd834</span>, <span class=
"literal">0xdd1e</span>};
vector&lt;<span class="keyword">unsigned char</span>&gt; utf8result;
utf16to8(utf16string, utf16string + <span class=
"literal">5</span>, back_inserter(utf8result));
assert (utf8result.size() == <span class="literal">10</span>);
</pre>
<p>
In case of invalid UTF-16 sequence, a <code>utf8::invalid_utf16</code> exception is
thrown.
</p>
<h4>
utf8::utf8to16
</h4>
<p class="version">
Available in version 1.0 and later.
</p>
<p>
Converts an UTF-8 encoded string to UTF-16
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> u16bit_iterator, typename octet_iterator&gt;
u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result);
</pre>
<p>
<code>octet_iterator</code>: an input iterator.<br>
<code>u16bit_iterator</code>: an output iterator.<br>
<code>start</code>: an iterator pointing to the beginning of the UTF-8 encoded
string to convert. &lt; br /&gt; <code>end</code>: an iterator pointing to
pass-the-end of the UTF-8 encoded string to convert.<br>
<code>result</code>: an output iterator to the place in the UTF-16 string where to
append the result of conversion.<br>
<span class="return_value">Return value</span>: An iterator pointing to the place
after the appended UTF-16 string.
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">char</span> utf8_with_surrogates[] = <span class=
"literal">"\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e"</span>;
vector &lt;<span class="keyword">unsigned short</span>&gt; utf16result;
utf8to16(utf8_with_surrogates, utf8_with_surrogates + <span class=
"literal">9</span>, back_inserter(utf16result));
assert (utf16result.size() == <span class="literal">4</span>);
assert (utf16result[<span class="literal">2</span>] == <span class=
"literal">0xd834</span>);
assert (utf16result[<span class="literal">3</span>] == <span class=
"literal">0xdd1e</span>);
</pre>
<p>
In case of an invalid UTF-8 seqence, a <code>utf8::invalid_utf8</code> exception is
thrown. If <code>end</code> does not point to the past-of-end of a UTF-8 seqence, a
<code>utf8::not_enough_room</code> exception is thrown.
</p>
<h4>
utf8::utf32to8
</h4>
<p class="version">
Available in version 1.0 and later.
</p>
<p>
Converts a UTF-32 encoded string to UTF-8.
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> octet_iterator, typename u32bit_iterator&gt;
octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result);
</pre>
<p>
<code>octet_iterator</code>: an output iterator.<br>
<code>u32bit_iterator</code>: an input iterator.<br>
<code>start</code>: an iterator pointing to the beginning of the UTF-32 encoded
string to convert.<br>
<code>end</code>: an iterator pointing to pass-the-end of the UTF-32 encoded
string to convert.<br>
<code>result</code>: an output iterator to the place in the UTF-8 string where to
append the result of conversion.<br>
<span class="return_value">Return value</span>: An iterator pointing to the place
after the appended UTF-8 string.
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">int</span> utf32string[] = {<span class=
"literal">0x448</span>, <span class="literal">0x65E5</span>, <span class=
"literal">0x10346</span>, <span class="literal">0</span>};
vector&lt;<span class="keyword">unsigned char</span>&gt; utf8result;
utf32to8(utf32string, utf32string + <span class=
"literal">3</span>, back_inserter(utf8result));
assert (utf8result.size() == <span class="literal">9</span>);
</pre>
<p>
In case of invalid UTF-32 string, a <code>utf8::invalid_code_point</code> exception
is thrown.
</p>
<h4>
utf8::utf8to32
</h4>
<p class="version">
Available in version 1.0 and later.
</p>
<p>
Converts a UTF-8 encoded string to UTF-32.
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> octet_iterator, <span class=
"keyword">typename</span> u32bit_iterator&gt;
u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result);
</pre>
<p>
<code>octet_iterator</code>: an input iterator.<br>
<code>u32bit_iterator</code>: an output iterator.<br>
<code>start</code>: an iterator pointing to the beginning of the UTF-8 encoded
string to convert.<br>
<code>end</code>: an iterator pointing to pass-the-end of the UTF-8 encoded string
to convert.<br>
<code>result</code>: an output iterator to the place in the UTF-32 string where to
append the result of conversion.<br>
<span class="return_value">Return value</span>: An iterator pointing to the place
after the appended UTF-32 string.
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">char</span>* twochars = <span class=
"literal">"\xe6\x97\xa5\xd1\x88"</span>;
vector&lt;<span class="keyword">int</span>&gt; utf32result;
utf8to32(twochars, twochars + <span class=
"literal">5</span>, back_inserter(utf32result));
assert (utf32result.size() == <span class="literal">2</span>);
</pre>
<p>
In case of an invalid UTF-8 seqence, a <code>utf8::invalid_utf8</code> exception is
thrown. If <code>end</code> does not point to the past-of-end of a UTF-8 seqence, a
<code>utf8::not_enough_room</code> exception is thrown.
</p>
<h4>
utf8::find_invalid
</h4>
<p class="version">
Available in version 1.0 and later.
</p>
<p>
Detects an invalid sequence within a UTF-8 string.
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> octet_iterator&gt;
octet_iterator find_invalid(octet_iterator start, octet_iterator end);
</pre>
<p>
<code>octet_iterator</code>: an input iterator.<br>
<code>start</code>: an iterator pointing to the beginning of the UTF-8 string to
test for validity.<br>
<code>end</code>: an iterator pointing to pass-the-end of the UTF-8 string to test
for validity.<br>
<span class="return_value">Return value</span>: an iterator pointing to the first
invalid octet in the UTF-8 string. In case none were found, equals
<code>end</code>.
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">char</span> utf_invalid[] = <span class=
"literal">"\xe6\x97\xa5\xd1\x88\xfa"</span>;
<span class=
"keyword">char</span>* invalid = find_invalid(utf_invalid, utf_invalid + <span class=
"literal">6</span>);
assert (invalid == utf_invalid + <span class="literal">5</span>);
</pre>
<p>
This function is typically used to make sure a UTF-8 string is valid before
processing it with other functions. It is especially important to call it if before
doing any of the <em>unchecked</em> operations on it.
</p>
<h4>
utf8::is_valid
</h4>
<p class="version">
Available in version 1.0 and later.
</p>
<p>
Checks whether a sequence of octets is a valid UTF-8 string.
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> octet_iterator&gt;
<span class="keyword">bool</span> is_valid(octet_iterator start, octet_iterator end);
</pre>
<p>
<code>octet_iterator</code>: an input iterator.<br>
<code>start</code>: an iterator pointing to the beginning of the UTF-8 string to
test for validity.<br>
<code>end</code>: an iterator pointing to pass-the-end of the UTF-8 string to test
for validity.<br>
<span class="return_value">Return value</span>: <code>true</code> if the sequence
is a valid UTF-8 string; <code>false</code> if not.
</p>
Example of use:
<pre>
<span class="keyword">char</span> utf_invalid[] = <span class=
"literal">"\xe6\x97\xa5\xd1\x88\xfa"</span>;
<span class="keyword">bool</span> bvalid = is_valid(utf_invalid, utf_invalid + <span
class="literal">6</span>);
assert (bvalid == false);
</pre>
<p>
<code>is_valid</code> is a shorthand for <code>find_invalid(start, end) ==
end;</code>. You may want to use it to make sure that a byte seqence is a valid
UTF-8 string without the need to know where it fails if it is not valid.
</p>
<h4>
utf8::replace_invalid
</h4>
<p class="version">
Available in version 2.0 and later.
</p>
<p>
Replaces all invalid UTF-8 sequences within a string with a replacement marker.
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> octet_iterator, <span class=
"keyword">typename</span> output_iterator&gt;
output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out, uint32_t replacement);
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> octet_iterator, <span class=
"keyword">typename</span> output_iterator&gt;
output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out);
</pre>
<p>
<code>octet_iterator</code>: an input iterator.<br>
<code>output_iterator</code>: an output iterator.<br>
<code>start</code>: an iterator pointing to the beginning of the UTF-8 string to
look for invalid UTF-8 sequences.<br>
<code>end</code>: an iterator pointing to pass-the-end of the UTF-8 string to look
for invalid UTF-8 sequences.<br>
<code>out</code>: An output iterator to the range where the result of replacement
is stored.<br>
<code>replacement</code>: A Unicode code point for the replacement marker. The
version without this parameter assumes the value <code>0xfffd</code><br>
<span class="return_value">Return value</span>: An iterator pointing to the place
after the UTF-8 string with replaced invalid sequences.
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">char</span> invalid_sequence[] = <span class=
"literal">"a\x80\xe0\xa0\xc0\xaf\xed\xa0\x80z"</span>;
vector&lt;<span class="keyword">char</span>&gt; replace_invalid_result;
replace_invalid (invalid_sequence, invalid_sequence + sizeof(invalid_sequence), back_inserter(replace_invalid_result), <span
class="literal">'?'</span>);
bvalid = is_valid(replace_invalid_result.begin(), replace_invalid_result.end());
assert (bvalid);
<span class="keyword">char</span>* fixed_invalid_sequence = <span class=
"literal">"a????z"</span>;
assert (std::equal(replace_invalid_result.begin(), replace_invalid_result.end(), fixed_invalid_sequence));
</pre>
<p>
<code>replace_invalid</code> does not perform in-place replacement of invalid
sequences. Rather, it produces a copy of the original string with the invalid
sequences replaced with a replacement marker. Therefore, <code>out</code> must not
be in the <code>[start, end]</code> range.
</p>
<p>
If <code>end</code> does not point to the past-of-end of a UTF-8 sequence, a
<code>utf8::not_enough_room</code> exception is thrown.
</p>
<h4>
utf8::starts_with_bom
</h4>
<p class="version">
Available in version 2.3 and later. Relaces deprecated <code>is_bom()</code> function.
</p>
<p>
Checks whether an octet sequence starts with a UTF-8 byte order mark (BOM)
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> octet_iterator&gt;
<span class="keyword">bool</span> starts_with_bom (octet_iterator it, octet_iterator end);
</pre>
<p>
<code>octet_iterator</code>: an input iterator.<br>
<code>it</code>: beginning of the octet sequence to check<br>
<code>end</code>: pass-end of the sequence to check<br>
<span class="return_value">Return value</span>: <code>true</code> if the sequence
starts with a UTF-8 byte order mark; <code>false</code> if not.
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">unsigned char</span> byte_order_mark[] = {<span class=
"literal">0xef</span>, <span class="literal">0xbb</span>, <span class=
"literal">0xbf</span>};
<span class="keyword">bool</span> bbom = starts_with_bom(byte_order_mark, byte_order_mark + <span class="keyword">sizeof</span>(byte_order_mark));
assert (bbom == <span class="literal">true</span>);
</pre>
<p>
The typical use of this function is to check the first three bytes of a file. If
they form the UTF-8 BOM, we want to skip them before processing the actual UTF-8
encoded text.
</p>
<h4>
utf8::is_bom
</h4>
<p class="version">
Available in version 1.0 and later. Deprecated in version 2.3. <code>starts_with_bom()</code> should be used
instead.
</p>
<p>
Checks whether a sequence of three octets is a UTF-8 byte order mark (BOM)
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> octet_iterator&gt;
<span class="keyword">bool</span> is_bom (octet_iterator it); <span class="comment"> // Deprecated</span>
</pre>
<p>
<code>octet_iterator</code>: an input iterator.<br>
<code>it</code>: beginning of the 3-octet sequence to check<br>
<span class="return_value">Return value</span>: <code>true</code> if the sequence
is UTF-8 byte order mark; <code>false</code> if not.
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">unsigned char</span> byte_order_mark[] = {<span class=
"literal">0xef</span>, <span class="literal">0xbb</span>, <span class=
"literal">0xbf</span>};
<span class="keyword">bool</span> bbom = is_bom(byte_order_mark);
assert (bbom == <span class="literal">true</span>);
</pre>
<p>
The typical use of this function is to check the first three bytes of a file. If
they form the UTF-8 BOM, we want to skip them before processing the actual UTF-8
encoded text.
</p>
<p>
If a sequence is
shorter than three bytes, an invalid iterator will be dereferenced. Therefore, this function is deprecated
in favor of <code>starts_with_bom()</code>that takes the end of sequence as an argument.
</p>
<h3 id="typesutf8">
Types From utf8 Namespace
</h3>
<h4>utf8::exception
</h4>
<p class="version">
Available in version 2.3 and later.
</p>
<p>
Base class for the exceptions thrown by UTF CPP library functions.
</p>
<pre>
<span class="keyword">class</span> exception : <span class="keyword">public</span> std::exception {};
</pre>
<p>
Example of use:
</p>
<pre>
<span class="keyword">try</span> {
code_that_uses_utf_cpp_library();
}
<span class="keyword">catch</span>(<span class="keyword">const</span> utf8::exception&amp; utfcpp_ex) {
cerr &lt;&lt; utfcpp_ex.what();
}
</pre>
<h4>utf8::invalid_code_point
</h4>
<p class="version">
Available in version 1.0 and later.
</p>
<p>
Thrown by UTF8 CPP functions such as <code>advance</code> and <code>next</code> if an UTF-8 sequence represents and invalid code point.
</p>
<pre>
<span class="keyword">class</span> invalid_code_point : <span class="keyword">public</span> exception {
<span class="keyword">public</span>:
uint32_t code_point() <span class="keyword">const</span>;
};
</pre>
<p>
Member function <code>code_point()</code> can be used to determine the invalid code point that
caused the exception to be thrown.
</p>
<h4>utf8::invalid_utf8
</h4>
<p class="version">
Available in version 1.0 and later.
</p>
<p>
Thrown by UTF8 CPP functions such as <code>next</code> and <code>prior</code> if an invalid UTF-8 sequence
is detected during decoding.
</p>
<pre>
<span class="keyword">class</span> invalid_utf8 : <span class="keyword">public</span> exception {
<span class="keyword">public</span>:
uint8_t utf8_octet() <span class="keyword">const</span>;
};
</pre>
<p>
Member function <code>utf8_octet()</code> can be used to determine the beginning of the byte
sequence that caused the exception to be thrown.
</p>
</pre>
<h4>utf8::invalid_utf16
</h4>
<p class="version">
Available in version 1.0 and later.
</p>
<p>
Thrown by UTF8 CPP function <code>utf16to8</code> if an invalid UTF-16 sequence
is detected during decoding.
</p>
<pre>
<span class="keyword">class</span> invalid_utf16 : <span class="keyword">public</span> exception {
<span class="keyword">public</span>:
uint16_t utf16_word() <span class="keyword">const</span>;
};
</pre>
<p>
Member function <code>utf16_word()</code> can be used to determine the UTF-16 code unit
that caused the exception to be thrown.
</p>
<h4>utf8::not_enough_room
</h4>
<p class="version">
Available in version 1.0 and later.
</p>
<p>
Thrown by UTF8 CPP functions such as <code>next</code> if the end of the decoded UTF-8 sequence
was reached before the code point was decoded.
</p>
<pre>
<span class="keyword">class</span> not_enough_room : <span class="keyword">public</span> exception {};
</pre>
<h4>
utf8::iterator
</h4>
<p class="version">
Available in version 2.0 and later.
</p>
<p>
Adapts the underlying octet iterator to iterate over the sequence of code points,
rather than raw octets.
</p>
<pre>
<span class="keyword">template</span> &lt;<span class="keyword">typename</span> octet_iterator&gt;
<span class="keyword">class</span> iterator;
</pre>
<h5>Member functions</h5>
<dl>
<dt><code>iterator();</code> <dd> the deafult constructor; the underlying <code>octet_iterator</code> is
constructed with its default constructor.
<dt><code><span class="keyword">explicit</span> iterator (const octet_iterator&amp; octet_it,
const octet_iterator&amp; range_start,
const octet_iterator&amp; range_end);</code> <dd> a constructor
that initializes the underlying <code>octet_iterator</code> with <code>octet_it</code>
and sets the range in which the iterator is considered valid.
<dt><code>octet_iterator base () <span class="keyword">const</span>;</code> <dd> returns the
underlying <code>octet_iterator</code>.
<dt><code>uint32_t operator * () <span class="keyword">const</span>;</code> <dd> decodes the utf-8 sequence
the underlying <code>octet_iterator</code> is pointing to and returns the code point.
<dt><code><span class="keyword">bool operator</span> == (const iterator&amp; rhs)
<span class="keyword">const</span>;</code> <dd> returns <span class="keyword">true</span>
if the two underlaying iterators are equal.
<dt><code><span class="keyword">bool operator</span> != (const iterator&amp; rhs)
<span class="keyword">const</span>;</code> <dd> returns <span class="keyword">true</span>
if the two underlaying iterators are not equal.
<dt><code>iterator&amp; <span class="keyword">operator</span> ++ (); </code> <dd> the prefix increment - moves
the iterator to the next UTF-8 encoded code point.
<dt><code>iterator <span class="keyword">operator</span> ++ (<span class="keyword">int</span>); </code> <dd>
the postfix increment - moves the iterator to the next UTF-8 encoded code point and returns the current one.
<dt><code>iterator&amp; <span class="keyword">operator</span> -- (); </code> <dd> the prefix decrement - moves
the iterator to the previous UTF-8 encoded code point.
<dt><code>iterator <span class="keyword">operator</span> -- (<span class="keyword">int</span>); </code> <dd>
the postfix decrement - moves the iterator to the previous UTF-8 encoded code point and returns the current one.
</dl>
<p>
Example of use:
</p>
<pre>
<span class="keyword">char</span>* threechars = <span class="literal">"\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"</span>;
utf8::iterator&lt;<span class="keyword">char</span>*&gt; it(threechars, threechars, threechars + <span class="literal">9</span>);
utf8::iterator&lt;<span class="keyword">char</span>*&gt; it2 = it;
assert (it2 == it);
assert (*it == <span class="literal">0x10346</span>);
assert (*(++it) == <span class="literal">0x65e5</span>);
assert ((*it++) == <span class="literal">0x65e5</span>);
assert (*it == <span class="literal">0x0448</span>);
assert (it != it2);
utf8::iterator&lt;<span class="keyword">char</span>*&gt; endit (threechars + <span class="literal">9</span>, threechars, threechars + <span class="literal">9</span>);
assert (++it == endit);
assert (*(--it) == <span class="literal">0x0448</span>);
assert ((*it--) == <span class="literal">0x0448</span>);
assert (*it == <span class="literal">0x65e5</span>);
assert (--it == utf8::iterator&lt;<span class="keyword">char</span>*&gt;(threechars, threechars, threechars + <span class="literal">9</span>));
assert (*it == <span class="literal">0x10346</span>);
</pre>
<p>
The purpose of <code>utf8::iterator</code> adapter is to enable easy iteration as well as the use of STL
algorithms with UTF-8 encoded strings. Increment and decrement operators are implemented in terms of
<code>utf8::next()</code> and <code>utf8::prior()</code> functions.
</p>
<p>
Note that <code>utf8::iterator</code> adapter is a checked iterator. It operates on the range specified in
the constructor; any attempt to go out of that range will result in an exception. Even the comparison operators
require both iterator object to be constructed against the same range - otherwise an exception is thrown. Typically,
the range will be determined by sequence container functions <code>begin</code> and <code>end</code>, i.e.:
</p>
<pre>
std::string s = <span class="literal">"example"</span>;
utf8::iterator i (s.begin(), s.begin(), s.end());
</pre>
<h3 id="fununchecked">
Functions From utf8::unchecked Namespace
</h3>
<h4>
utf8::unchecked::append
</h4>
<p class="version">
Available in version 1.0 and later.
</p>
<p>
Encodes a 32 bit code point as a UTF-8 sequence of octets and appends the sequence
to a UTF-8 string.
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> octet_iterator&gt;
octet_iterator append(uint32_t cp, octet_iterator result);
</pre>
<p>
<code>cp</code>: A 32 bit integer representing a code point to append to the
sequence.<br>
<code>result</code>: An output iterator to the place in the sequence where to
append the code point.<br>
<span class="return_value">Return value</span>: An iterator pointing to the place
after the newly appended sequence.
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">unsigned char</span> u[<span class="literal">5</span>] = {<span
class="literal">0</span>,<span class="literal">0</span>,<span class=
"literal">0</span>,<span class="literal">0</span>,<span class="literal">0</span>};
<span class="keyword">unsigned char</span>* end = unchecked::append(<span class=
"literal">0x0448</span>, u);
assert (u[<span class="literal">0</span>] == <span class=
"literal">0xd1</span> &amp;&amp; u[<span class="literal">1</span>] == <span class=
"literal">0x88</span> &amp;&amp; u[<span class="literal">2</span>] == <span class=
"literal">0</span> &amp;&amp; u[<span class="literal">3</span>] == <span class=
"literal">0</span> &amp;&amp; u[<span class="literal">4</span>] == <span class=
"literal">0</span>);
</pre>
<p>
This is a faster but less safe version of <code>utf8::append</code>. It does not
check for validity of the supplied code point, and may produce an invalid UTF-8
sequence.
</p>
<h4>
utf8::unchecked::next
</h4>
<p class="version">
Available in version 1.0 and later.
</p>
<p>
Given the iterator to the beginning of a UTF-8 sequence, it returns the code point
and moves the iterator to the next position.
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> octet_iterator&gt;
uint32_t next(octet_iterator&amp; it);
</pre>
<p>
<code>it</code>: a reference to an iterator pointing to the beginning of an UTF-8
encoded code point. After the function returns, it is incremented to point to the
beginning of the next code point.<br>
<span class="return_value">Return value</span>: the 32 bit representation of the
processed UTF-8 code point.
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">char</span>* twochars = <span class=
"literal">"\xe6\x97\xa5\xd1\x88"</span>;
<span class="keyword">char</span>* w = twochars;
<span class="keyword">int</span> cp = unchecked::next(w);
assert (cp == <span class="literal">0x65e5</span>);
assert (w == twochars + <span class="literal">3</span>);
</pre>
<p>
This is a faster but less safe version of <code>utf8::next</code>. It does not
check for validity of the supplied UTF-8 sequence.
</p>
<h4>
utf8::unchecked::peek_next
</h4>
<p class="version">
Available in version 2.1 and later.
</p>
<p>
Given the iterator to the beginning of a UTF-8 sequence, it returns the code point.
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> octet_iterator&gt;
uint32_t peek_next(octet_iterator it);
</pre>
<p>
<code>it</code>: an iterator pointing to the beginning of an UTF-8
encoded code point.<br>
<span class="return_value">Return value</span>: the 32 bit representation of the
processed UTF-8 code point.
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">char</span>* twochars = <span class=
"literal">"\xe6\x97\xa5\xd1\x88"</span>;
<span class="keyword">char</span>* w = twochars;
<span class="keyword">int</span> cp = unchecked::peek_next(w);
assert (cp == <span class="literal">0x65e5</span>);
assert (w == twochars);
</pre>
<p>
This is a faster but less safe version of <code>utf8::peek_next</code>. It does not
check for validity of the supplied UTF-8 sequence.
</p>
<h4>
utf8::unchecked::prior
</h4>
<p class="version">
Available in version 1.02 and later.
</p>
<p>
Given a reference to an iterator pointing to an octet in a UTF-8 seqence, it
decreases the iterator until it hits the beginning of the previous UTF-8 encoded
code point and returns the 32 bits representation of the code point.
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> octet_iterator&gt;
uint32_t prior(octet_iterator&amp; it);
</pre>
<p>
<code>it</code>: a reference pointing to an octet within a UTF-8 encoded string.
After the function returns, it is decremented to point to the beginning of the
previous code point.<br>
<span class="return_value">Return value</span>: the 32 bit representation of the
previous code point.
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">char</span>* twochars = <span class=
"literal">"\xe6\x97\xa5\xd1\x88"</span>;
<span class="keyword">char</span>* w = twochars + <span class="literal">3</span>;
<span class="keyword">int</span> cp = unchecked::prior (w);
assert (cp == <span class="literal">0x65e5</span>);
assert (w == twochars);
</pre>
<p>
This is a faster but less safe version of <code>utf8::prior</code>. It does not
check for validity of the supplied UTF-8 sequence and offers no boundary checking.
</p>
<h4>
utf8::unchecked::previous (deprecated, see utf8::unchecked::prior)
</h4>
<p class="version">
Deprecated in version 1.02 and later.
</p>
<p>
Given a reference to an iterator pointing to an octet in a UTF-8 seqence, it
decreases the iterator until it hits the beginning of the previous UTF-8 encoded
code point and returns the 32 bits representation of the code point.
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> octet_iterator&gt;
uint32_t previous(octet_iterator&amp; it);
</pre>
<p>
<code>it</code>: a reference pointing to an octet within a UTF-8 encoded string.
After the function returns, it is decremented to point to the beginning of the
previous code point.<br>
<span class="return_value">Return value</span>: the 32 bit representation of the
previous code point.
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">char</span>* twochars = <span class=
"literal">"\xe6\x97\xa5\xd1\x88"</span>;
<span class="keyword">char</span>* w = twochars + <span class="literal">3</span>;
<span class="keyword">int</span> cp = unchecked::previous (w);
assert (cp == <span class="literal">0x65e5</span>);
assert (w == twochars);
</pre>
<p>
The reason this function is deprecated is just the consistency with the "checked"
versions, where <code>prior</code> should be used instead of <code>previous</code>.
In fact, <code>unchecked::previous</code> behaves exactly the same as <code>
unchecked::prior</code>
</p>
<p>
This is a faster but less safe version of <code>utf8::previous</code>. It does not
check for validity of the supplied UTF-8 sequence and offers no boundary checking.
</p>
<h4>
utf8::unchecked::advance
</h4>
<p class="version">
Available in version 1.0 and later.
</p>
<p>
Advances an iterator by the specified number of code points within an UTF-8
sequence.
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> octet_iterator, typename distance_type&gt;
<span class="keyword">void</span> advance (octet_iterator&amp; it, distance_type n);
</pre>
<p>
<code>it</code>: a reference to an iterator pointing to the beginning of an UTF-8
encoded code point. After the function returns, it is incremented to point to the
nth following code point.<br>
<code>n</code>: a positive integer that shows how many code points we want to
advance.<br>
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">char</span>* twochars = <span class=
"literal">"\xe6\x97\xa5\xd1\x88"</span>;
<span class="keyword">char</span>* w = twochars;
unchecked::advance (w, <span class="literal">2</span>);
assert (w == twochars + <span class="literal">5</span>);
</pre>
<p>
This function works only "forward". In case of a negative <code>n</code>, there is
no effect.
</p>
<p>
This is a faster but less safe version of <code>utf8::advance</code>. It does not
check for validity of the supplied UTF-8 sequence and offers no boundary checking.
</p>
<h4>
utf8::unchecked::distance
</h4>
<p class="version">
Available in version 1.0 and later.
</p>
<p>
Given the iterators to two UTF-8 encoded code points in a seqence, returns the
number of code points between them.
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> octet_iterator&gt;
<span class=
"keyword">typename</span> std::iterator_traits&lt;octet_iterator&gt;::difference_type distance (octet_iterator first, octet_iterator last);
</pre>
<p>
<code>first</code>: an iterator to a beginning of a UTF-8 encoded code point.<br>
<code>last</code>: an iterator to a "post-end" of the last UTF-8 encoded code
point in the sequence we are trying to determine the length. It can be the
beginning of a new code point, or not.<br>
<span class="return_value">Return value</span> the distance between the iterators,
in code points.
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">char</span>* twochars = <span class=
"literal">"\xe6\x97\xa5\xd1\x88"</span>;
size_t dist = utf8::unchecked::distance(twochars, twochars + <span class=
"literal">5</span>);
assert (dist == <span class="literal">2</span>);
</pre>
<p>
This is a faster but less safe version of <code>utf8::distance</code>. It does not
check for validity of the supplied UTF-8 sequence.
</p>
<h4>
utf8::unchecked::utf16to8
</h4>
<p class="version">
Available in version 1.0 and later.
</p>
<p>
Converts a UTF-16 encoded string to UTF-8.
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> u16bit_iterator, <span class=
"keyword">typename</span> octet_iterator&gt;
octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result);
</pre>
<p>
<code>start</code>: an iterator pointing to the beginning of the UTF-16 encoded
string to convert.<br>
<code>end</code>: an iterator pointing to pass-the-end of the UTF-16 encoded
string to convert.<br>
<code>result</code>: an output iterator to the place in the UTF-8 string where to
append the result of conversion.<br>
<span class="return_value">Return value</span>: An iterator pointing to the place
after the appended UTF-8 string.
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">unsigned short</span> utf16string[] = {<span class=
"literal">0x41</span>, <span class="literal">0x0448</span>, <span class=
"literal">0x65e5</span>, <span class="literal">0xd834</span>, <span class=
"literal">0xdd1e</span>};
vector&lt;<span class="keyword">unsigned char</span>&gt; utf8result;
unchecked::utf16to8(utf16string, utf16string + <span class=
"literal">5</span>, back_inserter(utf8result));
assert (utf8result.size() == <span class="literal">10</span>);
</pre>
<p>
This is a faster but less safe version of <code>utf8::utf16to8</code>. It does not
check for validity of the supplied UTF-16 sequence.
</p>
<h4>
utf8::unchecked::utf8to16
</h4>
<p class="version">
Available in version 1.0 and later.
</p>
<p>
Converts an UTF-8 encoded string to UTF-16
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> u16bit_iterator, typename octet_iterator&gt;
u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result);
</pre>
<p>
<code>start</code>: an iterator pointing to the beginning of the UTF-8 encoded
string to convert. &lt; br /&gt; <code>end</code>: an iterator pointing to
pass-the-end of the UTF-8 encoded string to convert.<br>
<code>result</code>: an output iterator to the place in the UTF-16 string where to
append the result of conversion.<br>
<span class="return_value">Return value</span>: An iterator pointing to the place
after the appended UTF-16 string.
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">char</span> utf8_with_surrogates[] = <span class=
"literal">"\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e"</span>;
vector &lt;<span class="keyword">unsigned short</span>&gt; utf16result;
unchecked::utf8to16(utf8_with_surrogates, utf8_with_surrogates + <span class=
"literal">9</span>, back_inserter(utf16result));
assert (utf16result.size() == <span class="literal">4</span>);
assert (utf16result[<span class="literal">2</span>] == <span class=
"literal">0xd834</span>);
assert (utf16result[<span class="literal">3</span>] == <span class=
"literal">0xdd1e</span>);
</pre>
<p>
This is a faster but less safe version of <code>utf8::utf8to16</code>. It does not
check for validity of the supplied UTF-8 sequence.
</p>
<h4>
utf8::unchecked::utf32to8
</h4>
<p class="version">
Available in version 1.0 and later.
</p>
<p>
Converts a UTF-32 encoded string to UTF-8.
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> octet_iterator, <span class=
"keyword">typename</span> u32bit_iterator&gt;
octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result);
</pre>
<p>
<code>start</code>: an iterator pointing to the beginning of the UTF-32 encoded
string to convert.<br>
<code>end</code>: an iterator pointing to pass-the-end of the UTF-32 encoded
string to convert.<br>
<code>result</code>: an output iterator to the place in the UTF-8 string where to
append the result of conversion.<br>
<span class="return_value">Return value</span>: An iterator pointing to the place
after the appended UTF-8 string.
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">int</span> utf32string[] = {<span class=
"literal">0x448</span>, <span class="literal">0x65e5</span>, <span class=
"literal">0x10346</span>, <span class="literal">0</span>};
vector&lt;<span class="keyword">unsigned char</span>&gt; utf8result;
utf32to8(utf32string, utf32string + <span class=
"literal">3</span>, back_inserter(utf8result));
assert (utf8result.size() == <span class="literal">9</span>);
</pre>
<p>
This is a faster but less safe version of <code>utf8::utf32to8</code>. It does not
check for validity of the supplied UTF-32 sequence.
</p>
<h4>
utf8::unchecked::utf8to32
</h4>
<p class="version">
Available in version 1.0 and later.
</p>
<p>
Converts a UTF-8 encoded string to UTF-32.
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> octet_iterator, typename u32bit_iterator&gt;
u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result);
</pre>
<p>
<code>start</code>: an iterator pointing to the beginning of the UTF-8 encoded
string to convert.<br>
<code>end</code>: an iterator pointing to pass-the-end of the UTF-8 encoded string
to convert.<br>
<code>result</code>: an output iterator to the place in the UTF-32 string where to
append the result of conversion.<br>
<span class="return_value">Return value</span>: An iterator pointing to the place
after the appended UTF-32 string.
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">char</span>* twochars = <span class=
"literal">"\xe6\x97\xa5\xd1\x88"</span>;
vector&lt;<span class="keyword">int</span>&gt; utf32result;
unchecked::utf8to32(twochars, twochars + <span class=
"literal">5</span>, back_inserter(utf32result));
assert (utf32result.size() == <span class="literal">2</span>);
</pre>
<p>
This is a faster but less safe version of <code>utf8::utf8to32</code>. It does not
check for validity of the supplied UTF-8 sequence.
</p>
<h3 id="typesunchecked">
Types From utf8::unchecked Namespace
</h3>
<h4>
utf8::iterator
</h4>
<p class="version">
Available in version 2.0 and later.
</p>
<p>
Adapts the underlying octet iterator to iterate over the sequence of code points,
rather than raw octets.
</p>
<pre>
<span class="keyword">template</span> &lt;<span class="keyword">typename</span> octet_iterator&gt;
<span class="keyword">class</span> iterator;
</pre>
<h5>Member functions</h5>
<dl>
<dt><code>iterator();</code> <dd> the deafult constructor; the underlying <code>octet_iterator</code> is
constructed with its default constructor.
<dt><code><span class="keyword">explicit</span> iterator (const octet_iterator&amp; octet_it);
</code> <dd> a constructor
that initializes the underlying <code>octet_iterator</code> with <code>octet_it</code>
<dt><code>octet_iterator base () <span class="keyword">const</span>;</code> <dd> returns the
underlying <code>octet_iterator</code>.
<dt><code>uint32_t operator * () <span class="keyword">const</span>;</code> <dd> decodes the utf-8 sequence
the underlying <code>octet_iterator</code> is pointing to and returns the code point.
<dt><code><span class="keyword">bool operator</span> == (const iterator&amp; rhs)
<span class="keyword">const</span>;</code> <dd> returns <span class="keyword">true</span>
if the two underlaying iterators are equal.
<dt><code><span class="keyword">bool operator</span> != (const iterator&amp; rhs)
<span class="keyword">const</span>;</code> <dd> returns <span class="keyword">true</span>
if the two underlaying iterators are not equal.
<dt><code>iterator&amp; <span class="keyword">operator</span> ++ (); </code> <dd> the prefix increment - moves
the iterator to the next UTF-8 encoded code point.
<dt><code>iterator <span class="keyword">operator</span> ++ (<span class="keyword">int</span>); </code> <dd>
the postfix increment - moves the iterator to the next UTF-8 encoded code point and returns the current one.
<dt><code>iterator&amp; <span class="keyword">operator</span> -- (); </code> <dd> the prefix decrement - moves
the iterator to the previous UTF-8 encoded code point.
<dt><code>iterator <span class="keyword">operator</span> -- (<span class="keyword">int</span>); </code> <dd>
the postfix decrement - moves the iterator to the previous UTF-8 encoded code point and returns the current one.
</dl>
<p>
Example of use:
</p>
<pre>
<span class="keyword">char</span>* threechars = <span class="literal">"\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"</span>;
utf8::unchecked::iterator&lt;<span class="keyword">char</span>*&gt; un_it(threechars);
utf8::unchecked::iterator&lt;<span class="keyword">char</span>*&gt; un_it2 = un_it;
assert (un_it2 == un_it);
assert (*un_it == <span class="literal">0x10346</span>);
assert (*(++un_it) == <span class="literal">0x65e5</span>);
assert ((*un_it++) == <span class="literal">0x65e5</span>);
assert (*un_it == <span class="literal">0x0448</span>);
assert (un_it != un_it2);
utf8::::unchecked::iterator&lt;<span class="keyword">char</span>*&gt; un_endit (threechars + <span class="literal">9</span>);
assert (++un_it == un_endit);
assert (*(--un_it) == <span class="literal">0x0448</span>);
assert ((*un_it--) == <span class="literal">0x0448</span>);
assert (*un_it == <span class="literal">0x65e5</span>);
assert (--un_it == utf8::unchecked::iterator&lt;<span class="keyword">char</span>*&gt;(threechars));
assert (*un_it == <span class="literal">0x10346</span>);
</pre>
<p>
This is an unchecked version of <code>utf8::iterator</code>. It is faster in many cases, but offers
no validity or range checks.
</p>
<h2 id="points">
Points of interest
</h2>
<h4>
Design goals and decisions
</h4>
<p>
The library was designed to be:
</p>
<ol>
<li>
Generic: for better or worse, there are many C++ string classes out there, and
the library should work with as many of them as possible.
</li>
<li>
Portable: the library should be portable both accross different platforms and
compilers. The only non-portable code is a small section that declares unsigned
integers of different sizes: three typedefs. They can be changed by the users of
the library if they don't match their platform. The default setting should work
for Windows (both 32 and 64 bit), and most 32 bit and 64 bit Unix derivatives.
</li>
<li>
Lightweight: follow the "pay only for what you use" guideline.
</li>
<li>
Unintrusive: avoid forcing any particular design or even programming style on the
user. This is a library, not a framework.
</li>
</ol>
<h4>
Alternatives
</h4>
<p>
In case you want to look into other means of working with UTF-8 strings from C++,
here is the list of solutions I am aware of:
</p>
<ol>
<li>
<a href="http://icu.sourceforge.net/">ICU Library</a>. It is very powerful,
complete, feature-rich, mature, and widely used. Also big, intrusive,
non-generic, and doesn't play well with the Standard Library. I definitelly
recommend looking at ICU even if you don't plan to use it.
</li>
<li>
C++11 language and library features. Still far from complete, and not widely
supported by compiler vendors.
</li>
<li>
<a href=
"http://www.gtkmm.org/gtkmm2/docs/tutorial/html/ch03s04.html">Glib::ustring</a>.
A class specifically made to work with UTF-8 strings, and also feel like
<code>std::string</code>. If you prefer to have yet another string class in your
code, it may be worth a look. Be aware of the licensing issues, though.
</li>
<li>
Platform dependent solutions: Windows and POSIX have functions to convert strings
from one encoding to another. That is only a subset of what my library offers,
but if that is all you need it may be good enough.
</li>
</ol>
<h2 id="links">
Links
</h2>
<ol>
<li>
<a href="http://www.unicode.org/">The Unicode Consortium</a>.
</li>
<li>
<a href="http://icu.sourceforge.net/">ICU Library</a>.
</li>
<li>
<a href="http://en.wikipedia.org/wiki/UTF-8">UTF-8 at Wikipedia</a>
</li>
<li>
<a href="http://www.cl.cam.ac.uk/~mgk25/unicode.html">UTF-8 and Unicode FAQ for
Unix/Linux</a>
</li>
</ol>
</body>
</html>
......@@ -60,6 +60,7 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
#ifndef AI_CONFIG_H_INC
#define AI_CONFIG_H_INC
// ###########################################################################
// LIBRARY SETTINGS
// General, global settings
......@@ -75,8 +76,9 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
* Property type: bool. Default value: false.
*/
#define AI_CONFIG_GLOB_MEASURE_TIME \
"GLOB_MEASURE_TIME"
#define AI_CONFIG_GLOB_MEASURE_TIME \
"GLOB_MEASURE_TIME"
// ---------------------------------------------------------------------------
/** @brief Global setting to disable generation of skeleton dummy meshes
......@@ -87,9 +89,11 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
// ---------------------------------------------------------------------------
#define AI_CONFIG_IMPORT_NO_SKELETON_MESHES \
"IMPORT_NO_SKELETON_MESHES"
"IMPORT_NO_SKELETON_MESHES"
#if 0 // not implemented yet
# if 0 // not implemented yet
// ---------------------------------------------------------------------------
/** @brief Set Assimp's multithreading policy.
*
......@@ -105,8 +109,8 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
* For more information, see the @link threading Threading page@endlink.
* Property type: int, default value: -1.
*/
#define AI_CONFIG_GLOB_MULTITHREADING \
"GLOB_MULTITHREADING"
#define AI_CONFIG_GLOB_MULTITHREADING \
"GLOB_MULTITHREADING"
#endif
// ###########################################################################
......@@ -114,6 +118,7 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
// Various stuff to fine-tune the behavior of a specific post processing step.
// ###########################################################################
// ---------------------------------------------------------------------------
/** @brief Maximum bone count per mesh for the SplitbyBoneCount step.
*
......@@ -124,13 +129,15 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
// ---------------------------------------------------------------------------
#define AI_CONFIG_PP_SBBC_MAX_BONES \
"PP_SBBC_MAX_BONES"
"PP_SBBC_MAX_BONES"
// default limit for bone count
#if (!defined AI_SBBC_DEFAULT_MAX_BONES)
#define AI_SBBC_DEFAULT_MAX_BONES 60
# define AI_SBBC_DEFAULT_MAX_BONES 60
#endif
// ---------------------------------------------------------------------------
/** @brief Specifies the maximum angle that may be between two vertex tangents
* that their tangents and bi-tangents are smoothed.
......@@ -140,7 +147,7 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
* Property type: float. Default value: 45 degrees
*/
#define AI_CONFIG_PP_CT_MAX_SMOOTHING_ANGLE \
"PP_CT_MAX_SMOOTHING_ANGLE"
"PP_CT_MAX_SMOOTHING_ANGLE"
// ---------------------------------------------------------------------------
/** @brief Source UV channel for tangent space computation.
......@@ -150,7 +157,7 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
// ---------------------------------------------------------------------------
#define AI_CONFIG_PP_CT_TEXTURE_CHANNEL_INDEX \
"PP_CT_TEXTURE_CHANNEL_INDEX"
"PP_CT_TEXTURE_CHANNEL_INDEX"
// ---------------------------------------------------------------------------
/** @brief Specifies the maximum angle that may be between two face normals
......@@ -165,7 +172,8 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
* the output quality may be reduced.
*/
#define AI_CONFIG_PP_GSN_MAX_SMOOTHING_ANGLE \
"PP_GSN_MAX_SMOOTHING_ANGLE"
"PP_GSN_MAX_SMOOTHING_ANGLE"
// ---------------------------------------------------------------------------
/** @brief Sets the colormap (= palette) to be used to decode embedded
......@@ -177,8 +185,8 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
* a default palette (from Quake 1) is used.
* Property type: string.
*/
#define AI_CONFIG_IMPORT_MDL_COLORMAP \
"IMPORT_MDL_COLORMAP"
#define AI_CONFIG_IMPORT_MDL_COLORMAP \
"IMPORT_MDL_COLORMAP"
// ---------------------------------------------------------------------------
/** @brief Configures the #aiProcess_RemoveRedundantMaterials step to
......@@ -199,8 +207,8 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
* @note Linefeeds, tabs or carriage returns are treated as whitespace.
* Material names are case sensitive.
*/
#define AI_CONFIG_PP_RRM_EXCLUDE_LIST \
"PP_RRM_EXCLUDE_LIST"
#define AI_CONFIG_PP_RRM_EXCLUDE_LIST \
"PP_RRM_EXCLUDE_LIST"
// ---------------------------------------------------------------------------
/** @brief Configures the #aiProcess_PreTransformVertices step to
......@@ -214,8 +222,8 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
* any transformations.
* Property type: bool. Default value: false.
*/
#define AI_CONFIG_PP_PTV_KEEP_HIERARCHY \
"PP_PTV_KEEP_HIERARCHY"
#define AI_CONFIG_PP_PTV_KEEP_HIERARCHY \
"PP_PTV_KEEP_HIERARCHY"
// ---------------------------------------------------------------------------
/** @brief Configures the #aiProcess_PreTransformVertices step to normalize
......@@ -224,8 +232,8 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
* meshes are scaled appropriately (uniformly of course!).
* This might be useful if you don't know the spatial dimension of the input
* data*/
#define AI_CONFIG_PP_PTV_NORMALIZE \
"PP_PTV_NORMALIZE"
#define AI_CONFIG_PP_PTV_NORMALIZE \
"PP_PTV_NORMALIZE"
// ---------------------------------------------------------------------------
/** @brief Configures the #aiProcess_PreTransformVertices step to use
......@@ -233,8 +241,8 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
* transforming vertices.
* Property type: bool. Default value: false.
*/
#define AI_CONFIG_PP_PTV_ADD_ROOT_TRANSFORMATION \
"PP_PTV_ADD_ROOT_TRANSFORMATION"
#define AI_CONFIG_PP_PTV_ADD_ROOT_TRANSFORMATION \
"PP_PTV_ADD_ROOT_TRANSFORMATION"
// ---------------------------------------------------------------------------
/** @brief Configures the #aiProcess_PreTransformVertices step to use
......@@ -243,8 +251,8 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
* of the transformation matrix.
* Property type: aiMatrix4x4.
*/
#define AI_CONFIG_PP_PTV_ROOT_TRANSFORMATION \
"PP_PTV_ROOT_TRANSFORMATION"
#define AI_CONFIG_PP_PTV_ROOT_TRANSFORMATION \
"PP_PTV_ROOT_TRANSFORMATION"
// ---------------------------------------------------------------------------
/** @brief Configures the #aiProcess_FindDegenerates step to
......@@ -257,7 +265,7 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
* Property type: bool. Default value: false.
*/
#define AI_CONFIG_PP_FD_REMOVE \
"PP_FD_REMOVE"
"PP_FD_REMOVE"
// ---------------------------------------------------------------------------
/**
......@@ -266,7 +274,7 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
* be removed if #AI_CONFIG_PP_FD_REMOVE is set to true.
*/
#define AI_CONFIG_PP_FD_CHECKAREA \
"PP_FD_CHECKAREA"
"PP_FD_CHECKAREA"
// ---------------------------------------------------------------------------
/** @brief Configures the #aiProcess_OptimizeGraph step to preserve nodes
......@@ -286,8 +294,8 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
* @note Linefeeds, tabs or carriage returns are treated as whitespace.
* Node names are case sensitive.
*/
#define AI_CONFIG_PP_OG_EXCLUDE_LIST \
"PP_OG_EXCLUDE_LIST"
#define AI_CONFIG_PP_OG_EXCLUDE_LIST \
"PP_OG_EXCLUDE_LIST"
// ---------------------------------------------------------------------------
/** @brief Set the maximum number of triangles in a mesh.
......@@ -298,11 +306,11 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
* Property type: integer.
*/
#define AI_CONFIG_PP_SLM_TRIANGLE_LIMIT \
"PP_SLM_TRIANGLE_LIMIT"
"PP_SLM_TRIANGLE_LIMIT"
// default value for AI_CONFIG_PP_SLM_TRIANGLE_LIMIT
#if (!defined AI_SLM_DEFAULT_MAX_TRIANGLES)
#define AI_SLM_DEFAULT_MAX_TRIANGLES 1000000
# define AI_SLM_DEFAULT_MAX_TRIANGLES 1000000
#endif
// ---------------------------------------------------------------------------
......@@ -314,11 +322,11 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
* Property type: integer.
*/
#define AI_CONFIG_PP_SLM_VERTEX_LIMIT \
"PP_SLM_VERTEX_LIMIT"
"PP_SLM_VERTEX_LIMIT"
// default value for AI_CONFIG_PP_SLM_VERTEX_LIMIT
#if (!defined AI_SLM_DEFAULT_MAX_VERTICES)
#define AI_SLM_DEFAULT_MAX_VERTICES 1000000
# define AI_SLM_DEFAULT_MAX_VERTICES 1000000
#endif
// ---------------------------------------------------------------------------
......@@ -327,12 +335,12 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
* This is used by the #aiProcess_LimitBoneWeights PostProcess-Step.
* @note The default value is AI_LMW_MAX_WEIGHTS
* Property type: integer.*/
#define AI_CONFIG_PP_LBW_MAX_WEIGHTS \
"PP_LBW_MAX_WEIGHTS"
#define AI_CONFIG_PP_LBW_MAX_WEIGHTS \
"PP_LBW_MAX_WEIGHTS"
// default value for AI_CONFIG_PP_LBW_MAX_WEIGHTS
#if (!defined AI_LMW_MAX_WEIGHTS)
#define AI_LMW_MAX_WEIGHTS 0x4
# define AI_LMW_MAX_WEIGHTS 0x4
#endif // !! AI_LMW_MAX_WEIGHTS
// ---------------------------------------------------------------------------
......@@ -342,11 +350,11 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
* @note The default value is AI_DEBONE_THRESHOLD
* Property type: float.*/
#define AI_CONFIG_PP_DB_THRESHOLD \
"PP_DB_THRESHOLD"
"PP_DB_THRESHOLD"
// default value for AI_CONFIG_PP_LBW_MAX_WEIGHTS
#if (!defined AI_DEBONE_THRESHOLD)
#define AI_DEBONE_THRESHOLD 1.0f
# define AI_DEBONE_THRESHOLD 1.0f
#endif // !! AI_DEBONE_THRESHOLD
// ---------------------------------------------------------------------------
......@@ -356,12 +364,12 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
* @note The default value is 0
* Property type: bool.*/
#define AI_CONFIG_PP_DB_ALL_OR_NONE \
"PP_DB_ALL_OR_NONE"
"PP_DB_ALL_OR_NONE"
/** @brief Default value for the #AI_CONFIG_PP_ICL_PTCACHE_SIZE property
*/
#ifndef PP_ICL_PTCACHE_SIZE
#define PP_ICL_PTCACHE_SIZE 12
# define PP_ICL_PTCACHE_SIZE 12
#endif
// ---------------------------------------------------------------------------
......@@ -375,7 +383,7 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
* performance improvements for most nVidia/AMD cards since 2002.
* Property type: integer.
*/
#define AI_CONFIG_PP_ICL_PTCACHE_SIZE "PP_ICL_PTCACHE_SIZE"
#define AI_CONFIG_PP_ICL_PTCACHE_SIZE "PP_ICL_PTCACHE_SIZE"
// ---------------------------------------------------------------------------
/** @brief Enumerates components of the aiScene and aiMesh data structures
......@@ -383,71 +391,73 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
* See the documentation to #aiProcess_RemoveComponent for more details.
*/
enum aiComponent {
/** Normal vectors */
enum aiComponent
{
/** Normal vectors */
#ifdef SWIG
aiComponent_NORMALS = 0x2,
#else
aiComponent_NORMALS = 0x2u,
aiComponent_NORMALS = 0x2u,
#endif
/** Tangents and bitangents go always together ... */
/** Tangents and bitangents go always together ... */
#ifdef SWIG
aiComponent_TANGENTS_AND_BITANGENTS = 0x4,
#else
aiComponent_TANGENTS_AND_BITANGENTS = 0x4u,
aiComponent_TANGENTS_AND_BITANGENTS = 0x4u,
#endif
/** ALL color sets
/** ALL color sets
* Use aiComponent_COLORn(N) to specify the N'th set */
aiComponent_COLORS = 0x8,
aiComponent_COLORS = 0x8,
/** ALL texture UV sets
/** ALL texture UV sets
* aiComponent_TEXCOORDn(N) to specify the N'th set */
aiComponent_TEXCOORDS = 0x10,
aiComponent_TEXCOORDS = 0x10,
/** Removes all bone weights from all meshes.
/** Removes all bone weights from all meshes.
* The scenegraph nodes corresponding to the bones are NOT removed.
* use the #aiProcess_OptimizeGraph step to do this */
aiComponent_BONEWEIGHTS = 0x20,
aiComponent_BONEWEIGHTS = 0x20,
/** Removes all node animations (aiScene::mAnimations).
/** Removes all node animations (aiScene::mAnimations).
* The corresponding scenegraph nodes are NOT removed.
* use the #aiProcess_OptimizeGraph step to do this */
aiComponent_ANIMATIONS = 0x40,
aiComponent_ANIMATIONS = 0x40,
/** Removes all embedded textures (aiScene::mTextures) */
aiComponent_TEXTURES = 0x80,
/** Removes all embedded textures (aiScene::mTextures) */
aiComponent_TEXTURES = 0x80,
/** Removes all light sources (aiScene::mLights).
/** Removes all light sources (aiScene::mLights).
* The corresponding scenegraph nodes are NOT removed.
* use the #aiProcess_OptimizeGraph step to do this */
aiComponent_LIGHTS = 0x100,
aiComponent_LIGHTS = 0x100,
/** Removes all cameras (aiScene::mCameras).
/** Removes all cameras (aiScene::mCameras).
* The corresponding scenegraph nodes are NOT removed.
* use the #aiProcess_OptimizeGraph step to do this */
aiComponent_CAMERAS = 0x200,
aiComponent_CAMERAS = 0x200,
/** Removes all meshes (aiScene::mMeshes). */
aiComponent_MESHES = 0x400,
/** Removes all meshes (aiScene::mMeshes). */
aiComponent_MESHES = 0x400,
/** Removes all materials. One default material will
/** Removes all materials. One default material will
* be generated, so aiScene::mNumMaterials will be 1. */
aiComponent_MATERIALS = 0x800,
aiComponent_MATERIALS = 0x800,
/** This value is not used. It is just there to force the
/** This value is not used. It is just there to force the
* compiler to map this enum to a 32 Bit integer. */
#ifndef SWIG
_aiComponent_Force32Bit = 0x9fffffff
_aiComponent_Force32Bit = 0x9fffffff
#endif
};
// Remove a specific color channel 'n'
#define aiComponent_COLORSn(n) (1u << (n + 20u))
#define aiComponent_COLORSn(n) (1u << (n+20u))
// Remove a specific UV channel 'n'
#define aiComponent_TEXCOORDSn(n) (1u << (n + 25u))
#define aiComponent_TEXCOORDSn(n) (1u << (n+25u))
// ---------------------------------------------------------------------------
/** @brief Input parameter to the #aiProcess_RemoveComponent step:
......@@ -461,8 +471,8 @@ enum aiComponent {
* of the flags defined above) the import FAILS. Mainly because there is
* no data to work on anymore ...
*/
#define AI_CONFIG_PP_RVC_FLAGS \
"PP_RVC_FLAGS"
#define AI_CONFIG_PP_RVC_FLAGS \
"PP_RVC_FLAGS"
// ---------------------------------------------------------------------------
/** @brief Input parameter to the #aiProcess_SortByPType step:
......@@ -473,8 +483,8 @@ enum aiComponent {
* be to exclude all line and point meshes from the import. This
* is an integer property, its default value is 0.
*/
#define AI_CONFIG_PP_SBP_REMOVE \
"PP_SBP_REMOVE"
#define AI_CONFIG_PP_SBP_REMOVE \
"PP_SBP_REMOVE"
// ---------------------------------------------------------------------------
/** @brief Input parameter to the #aiProcess_FindInvalidData step:
......@@ -485,8 +495,16 @@ enum aiComponent {
* abs(n0-n1)>epsilon holds true for all vector respectively quaternion
* components. The default value is 0.f - comparisons are exact then.
*/
#define AI_CONFIG_PP_FID_ANIM_ACCURACY \
"PP_FID_ANIM_ACCURACY"
#define AI_CONFIG_PP_FID_ANIM_ACCURACY \
"PP_FID_ANIM_ACCURACY"
// ---------------------------------------------------------------------------
/** @brief Input parameter to the #aiProcess_FindInvalidData step:
* Set to true to ignore texture coordinates. This may be useful if you have
* to assign different kind of textures like one for the summer or one for the winter.
*/
#define AI_CONFIG_PP_FID_IGNORE_TEXTURECOORDS \
"PP_FID_IGNORE_TEXTURECOORDS"
// TransformUVCoords evaluates UV scalings
#define AI_UVTRAFO_SCALING 0x1
......@@ -501,14 +519,6 @@ enum aiComponent {
#define AI_UVTRAFO_ALL (AI_UVTRAFO_SCALING | AI_UVTRAFO_ROTATION | AI_UVTRAFO_TRANSLATION)
// ---------------------------------------------------------------------------
/** @brief Input parameter to the #aiProcess_FindInvalidData step:
* Set to true to ignore texture coordinates. This may be useful if you have
* to assign different kind of textures like one for the summer or one for the winter.
*/
#define AI_CONFIG_PP_FID_IGNORE_TEXTURECOORDS \
"PP_FID_IGNORE_TEXTURECOORDS"
// ---------------------------------------------------------------------------
/** @brief Input parameter to the #aiProcess_TransformUVCoords step:
* Specifies which UV transformations are evaluated.
*
......@@ -516,8 +526,8 @@ enum aiComponent {
* property, of course). By default all transformations are enabled
* (AI_UVTRAFO_ALL).
*/
#define AI_CONFIG_PP_TUV_EVALUATE \
"PP_TUV_EVALUATE"
#define AI_CONFIG_PP_TUV_EVALUATE \
"PP_TUV_EVALUATE"
// ---------------------------------------------------------------------------
/** @brief A hint to assimp to favour speed against import quality.
......@@ -528,14 +538,16 @@ enum aiComponent {
* This property is expected to be an integer, != 0 stands for true.
* The default value is 0.
*/
#define AI_CONFIG_FAVOUR_SPEED \
"FAVOUR_SPEED"
#define AI_CONFIG_FAVOUR_SPEED \
"FAVOUR_SPEED"
// ###########################################################################
// IMPORTER SETTINGS
// Various stuff to fine-tune the behaviour of specific importer plugins.
// ###########################################################################
// ---------------------------------------------------------------------------
/** @brief Set whether the fbx importer will merge all geometry layers present
* in the source file or take only the first.
......@@ -544,7 +556,7 @@ enum aiComponent {
* Property type: bool
*/
#define AI_CONFIG_IMPORT_FBX_READ_ALL_GEOMETRY_LAYERS \
"IMPORT_FBX_READ_ALL_GEOMETRY_LAYERS"
"IMPORT_FBX_READ_ALL_GEOMETRY_LAYERS"
// ---------------------------------------------------------------------------
/** @brief Set whether the fbx importer will read all materials present in the
......@@ -556,7 +568,7 @@ enum aiComponent {
* Property type: bool
*/
#define AI_CONFIG_IMPORT_FBX_READ_ALL_MATERIALS \
"IMPORT_FBX_READ_ALL_MATERIALS"
"IMPORT_FBX_READ_ALL_MATERIALS"
// ---------------------------------------------------------------------------
/** @brief Set whether the fbx importer will read materials.
......@@ -565,7 +577,7 @@ enum aiComponent {
* Property type: bool
*/
#define AI_CONFIG_IMPORT_FBX_READ_MATERIALS \
"IMPORT_FBX_READ_MATERIALS"
"IMPORT_FBX_READ_MATERIALS"
// ---------------------------------------------------------------------------
/** @brief Set whether the fbx importer will read embedded textures.
......@@ -574,7 +586,7 @@ enum aiComponent {
* Property type: bool
*/
#define AI_CONFIG_IMPORT_FBX_READ_TEXTURES \
"IMPORT_FBX_READ_TEXTURES"
"IMPORT_FBX_READ_TEXTURES"
// ---------------------------------------------------------------------------
/** @brief Set whether the fbx importer will read cameras.
......@@ -583,7 +595,7 @@ enum aiComponent {
* Property type: bool
*/
#define AI_CONFIG_IMPORT_FBX_READ_CAMERAS \
"IMPORT_FBX_READ_CAMERAS"
"IMPORT_FBX_READ_CAMERAS"
// ---------------------------------------------------------------------------
/** @brief Set whether the fbx importer will read light sources.
......@@ -592,7 +604,7 @@ enum aiComponent {
* Property type: bool
*/
#define AI_CONFIG_IMPORT_FBX_READ_LIGHTS \
"IMPORT_FBX_READ_LIGHTS"
"IMPORT_FBX_READ_LIGHTS"
// ---------------------------------------------------------------------------
/** @brief Set whether the fbx importer will read animations.
......@@ -601,7 +613,7 @@ enum aiComponent {
* Property type: bool
*/
#define AI_CONFIG_IMPORT_FBX_READ_ANIMATIONS \
"IMPORT_FBX_READ_ANIMATIONS"
"IMPORT_FBX_READ_ANIMATIONS"
// ---------------------------------------------------------------------------
/** @brief Set whether the fbx importer will act in strict mode in which only
......@@ -613,7 +625,7 @@ enum aiComponent {
* Property type: bool
*/
#define AI_CONFIG_IMPORT_FBX_STRICT_MODE \
"IMPORT_FBX_STRICT_MODE"
"IMPORT_FBX_STRICT_MODE"
// ---------------------------------------------------------------------------
/** @brief Set whether the fbx importer will preserve pivot points for
......@@ -624,7 +636,7 @@ enum aiComponent {
* Property type: bool
*/
#define AI_CONFIG_IMPORT_FBX_PRESERVE_PIVOTS \
"IMPORT_FBX_PRESERVE_PIVOTS"
"IMPORT_FBX_PRESERVE_PIVOTS"
// ---------------------------------------------------------------------------
/** @brief Specifies whether the importer will drop empty animation curves or
......@@ -635,26 +647,26 @@ enum aiComponent {
* Property type: bool
*/
#define AI_CONFIG_IMPORT_FBX_OPTIMIZE_EMPTY_ANIMATION_CURVES \
"IMPORT_FBX_OPTIMIZE_EMPTY_ANIMATION_CURVES"
"IMPORT_FBX_OPTIMIZE_EMPTY_ANIMATION_CURVES"
// ---------------------------------------------------------------------------
/** @brief Set whether the fbx importer will use the legacy embedded texture naming.
*
* The default value is false (0)
* Property type: bool
*/
*
* The default value is false (0)
* Property type: bool
*/
#define AI_CONFIG_IMPORT_FBX_EMBEDDED_TEXTURES_LEGACY_NAMING \
"AI_CONFIG_IMPORT_FBX_EMBEDDED_TEXTURES_LEGACY_NAMING"
// ---------------------------------------------------------------------------
/** @brief Set wether the FBX importer shall not remove empty bones.
*
/** @brief Set wether the importer shall not remove empty bones.
*
* Empty bone are often used to define connections for other models.
*/
#define AI_CONFIG_IMPORT_REMOVE_EMPTY_BONES \
"AI_CONFIG_IMPORT_REMOVE_EMPTY_BONES"
// ---------------------------------------------------------------------------
/** @brief Set wether the FBX importer shall convert the unit from cm to m.
*/
......@@ -674,14 +686,14 @@ enum aiComponent {
* want to override the global setting).
* Property type: integer.
*/
#define AI_CONFIG_IMPORT_GLOBAL_KEYFRAME "IMPORT_GLOBAL_KEYFRAME"
#define AI_CONFIG_IMPORT_GLOBAL_KEYFRAME "IMPORT_GLOBAL_KEYFRAME"
#define AI_CONFIG_IMPORT_MD3_KEYFRAME "IMPORT_MD3_KEYFRAME"
#define AI_CONFIG_IMPORT_MD2_KEYFRAME "IMPORT_MD2_KEYFRAME"
#define AI_CONFIG_IMPORT_MDL_KEYFRAME "IMPORT_MDL_KEYFRAME"
#define AI_CONFIG_IMPORT_MDC_KEYFRAME "IMPORT_MDC_KEYFRAME"
#define AI_CONFIG_IMPORT_SMD_KEYFRAME "IMPORT_SMD_KEYFRAME"
#define AI_CONFIG_IMPORT_UNREAL_KEYFRAME "IMPORT_UNREAL_KEYFRAME"
#define AI_CONFIG_IMPORT_MD3_KEYFRAME "IMPORT_MD3_KEYFRAME"
#define AI_CONFIG_IMPORT_MD2_KEYFRAME "IMPORT_MD2_KEYFRAME"
#define AI_CONFIG_IMPORT_MDL_KEYFRAME "IMPORT_MDL_KEYFRAME"
#define AI_CONFIG_IMPORT_MDC_KEYFRAME "IMPORT_MDC_KEYFRAME"
#define AI_CONFIG_IMPORT_SMD_KEYFRAME "IMPORT_SMD_KEYFRAME"
#define AI_CONFIG_IMPORT_UNREAL_KEYFRAME "IMPORT_UNREAL_KEYFRAME"
// ---------------------------------------------------------------------------
/** Smd load multiple animations
......@@ -697,7 +709,7 @@ enum aiComponent {
* Property type: bool. Default value: true.
*/
#define AI_CONFIG_IMPORT_AC_SEPARATE_BFCULL \
"IMPORT_AC_SEPARATE_BFCULL"
"IMPORT_AC_SEPARATE_BFCULL"
// ---------------------------------------------------------------------------
/** @brief Configures whether the AC loader evaluates subdivision surfaces (
......@@ -707,8 +719,8 @@ enum aiComponent {
*
* * Property type: bool. Default value: true.
*/
#define AI_CONFIG_IMPORT_AC_EVAL_SUBDIVISION \
"IMPORT_AC_EVAL_SUBDIVISION"
#define AI_CONFIG_IMPORT_AC_EVAL_SUBDIVISION \
"IMPORT_AC_EVAL_SUBDIVISION"
// ---------------------------------------------------------------------------
/** @brief Configures the UNREAL 3D loader to separate faces with different
......@@ -717,7 +729,7 @@ enum aiComponent {
* * Property type: bool. Default value: true.
*/
#define AI_CONFIG_IMPORT_UNREAL_HANDLE_FLAGS \
"UNREAL_HANDLE_FLAGS"
"UNREAL_HANDLE_FLAGS"
// ---------------------------------------------------------------------------
/** @brief Configures the terragen import plugin to compute uv's for
......@@ -730,7 +742,7 @@ enum aiComponent {
* * Property type: bool. Default value: false.
*/
#define AI_CONFIG_IMPORT_TER_MAKE_UVS \
"IMPORT_TER_MAKE_UVS"
"IMPORT_TER_MAKE_UVS"
// ---------------------------------------------------------------------------
/** @brief Configures the ASE loader to always reconstruct normal vectors
......@@ -739,8 +751,8 @@ enum aiComponent {
* Some ASE files have carry invalid normals, other don't.
* * Property type: bool. Default value: true.
*/
#define AI_CONFIG_IMPORT_ASE_RECONSTRUCT_NORMALS \
"IMPORT_ASE_RECONSTRUCT_NORMALS"
#define AI_CONFIG_IMPORT_ASE_RECONSTRUCT_NORMALS \
"IMPORT_ASE_RECONSTRUCT_NORMALS"
// ---------------------------------------------------------------------------
/** @brief Configures the M3D loader to detect and process multi-part
......@@ -752,7 +764,7 @@ enum aiComponent {
* Property type: bool. Default value: true.
*/
#define AI_CONFIG_IMPORT_MD3_HANDLE_MULTIPART \
"IMPORT_MD3_HANDLE_MULTIPART"
"IMPORT_MD3_HANDLE_MULTIPART"
// ---------------------------------------------------------------------------
/** @brief Tells the MD3 loader which skin files to load.
......@@ -764,7 +776,7 @@ enum aiComponent {
* Property type: String. Default value: "default".
*/
#define AI_CONFIG_IMPORT_MD3_SKIN_NAME \
"IMPORT_MD3_SKIN_NAME"
"IMPORT_MD3_SKIN_NAME"
// ---------------------------------------------------------------------------
/** @brief Specify the Quake 3 shader file to be used for a particular
......@@ -782,7 +794,7 @@ enum aiComponent {
* Property type: String. Default value: n/a.
*/
#define AI_CONFIG_IMPORT_MD3_SHADER_SRC \
"IMPORT_MD3_SHADER_SRC"
"IMPORT_MD3_SHADER_SRC"
// ---------------------------------------------------------------------------
/** @brief Configures the LWO loader to load just one layer from the model.
......@@ -795,8 +807,8 @@ enum aiComponent {
* layer name may not be empty.<br>
* Property type: Integer. Default value: all layers are loaded.
*/
#define AI_CONFIG_IMPORT_LWO_ONE_LAYER_ONLY \
"IMPORT_LWO_ONE_LAYER_ONLY"
#define AI_CONFIG_IMPORT_LWO_ONE_LAYER_ONLY \
"IMPORT_LWO_ONE_LAYER_ONLY"
// ---------------------------------------------------------------------------
/** @brief Configures the MD5 loader to not load the MD5ANIM file for
......@@ -809,8 +821,8 @@ enum aiComponent {
*
* * Property type: bool. Default value: false.
*/
#define AI_CONFIG_IMPORT_MD5_NO_ANIM_AUTOLOAD \
"IMPORT_MD5_NO_ANIM_AUTOLOAD"
#define AI_CONFIG_IMPORT_MD5_NO_ANIM_AUTOLOAD \
"IMPORT_MD5_NO_ANIM_AUTOLOAD"
// ---------------------------------------------------------------------------
/** @brief Defines the begin of the time range for which the LWS loader
......@@ -828,10 +840,10 @@ enum aiComponent {
*
* @see AI_CONFIG_IMPORT_LWS_ANIM_END - end of the imported time range
*/
#define AI_CONFIG_IMPORT_LWS_ANIM_START \
"IMPORT_LWS_ANIM_START"
#define AI_CONFIG_IMPORT_LWS_ANIM_END \
"IMPORT_LWS_ANIM_END"
#define AI_CONFIG_IMPORT_LWS_ANIM_START \
"IMPORT_LWS_ANIM_START"
#define AI_CONFIG_IMPORT_LWS_ANIM_END \
"IMPORT_LWS_ANIM_END"
// ---------------------------------------------------------------------------
/** @brief Defines the output frame rate of the IRR loader.
......@@ -841,8 +853,8 @@ enum aiComponent {
* are returned by the converter.<br>
* Property type: integer. Default value: 100
*/
#define AI_CONFIG_IMPORT_IRR_ANIM_FPS \
"IMPORT_IRR_ANIM_FPS"
#define AI_CONFIG_IMPORT_IRR_ANIM_FPS \
"IMPORT_IRR_ANIM_FPS"
// ---------------------------------------------------------------------------
/** @brief Ogre Importer will try to find referenced materials from this file.
......@@ -855,7 +867,7 @@ enum aiComponent {
* Property type: String. Default value: Scene.material.
*/
#define AI_CONFIG_IMPORT_OGRE_MATERIAL_FILE \
"IMPORT_OGRE_MATERIAL_FILE"
"IMPORT_OGRE_MATERIAL_FILE"
// ---------------------------------------------------------------------------
/** @brief Ogre Importer detect the texture usage from its filename.
......@@ -875,15 +887,15 @@ enum aiComponent {
* Property type: Bool. Default value: false.
*/
#define AI_CONFIG_IMPORT_OGRE_TEXTURETYPE_FROM_FILENAME \
"IMPORT_OGRE_TEXTURETYPE_FROM_FILENAME"
"IMPORT_OGRE_TEXTURETYPE_FROM_FILENAME"
/** @brief Specifies whether the Android JNI asset extraction is supported.
/** @brief Specifies whether the Android JNI asset extraction is supported.
*
* Turn on this option if you want to manage assets in native
* Android application without having to keep the internal directory and asset
* manager pointer.
*/
#define AI_CONFIG_ANDROID_JNI_ASSIMP_MANAGER_SUPPORT "AI_CONFIG_ANDROID_JNI_ASSIMP_MANAGER_SUPPORT"
#define AI_CONFIG_ANDROID_JNI_ASSIMP_MANAGER_SUPPORT "AI_CONFIG_ANDROID_JNI_ASSIMP_MANAGER_SUPPORT"
// ---------------------------------------------------------------------------
/** @brief Specifies whether the IFC loader skips over IfcSpace elements.
......@@ -922,7 +934,7 @@ enum aiComponent {
// default value for AI_CONFIG_IMPORT_IFC_SMOOTHING_ANGLE
#if (!defined AI_IMPORT_IFC_DEFAULT_SMOOTHING_ANGLE)
#define AI_IMPORT_IFC_DEFAULT_SMOOTHING_ANGLE 10.0f
# define AI_IMPORT_IFC_DEFAULT_SMOOTHING_ANGLE 10.0f
#endif
// ---------------------------------------------------------------------------
......@@ -938,7 +950,7 @@ enum aiComponent {
// default value for AI_CONFIG_IMPORT_IFC_CYLINDRICAL_TESSELLATION
#if (!defined AI_IMPORT_IFC_DEFAULT_CYLINDRICAL_TESSELLATION)
#define AI_IMPORT_IFC_DEFAULT_CYLINDRICAL_TESSELLATION 32
# define AI_IMPORT_IFC_DEFAULT_CYLINDRICAL_TESSELLATION 32
#endif
// ---------------------------------------------------------------------------
......@@ -969,8 +981,12 @@ enum aiComponent {
#define AI_CONFIG_EXPORT_XFILE_64BIT "EXPORT_XFILE_64BIT"
/**
*
/** @brief Specifies whether the assimp export shall be able to export point clouds
*
* When this flag is not defined the render data has to contain valid faces.
* Point clouds are only a collection of vertices which have nor spatial organization
* by a face and the validation process will remove them. Enabling this feature will
* switch off the flag and enable the functionality to export pure point clouds.
*/
#define AI_CONFIG_EXPORT_POINT_CLOUDS "EXPORT_POINT_CLOUDS"
......@@ -980,7 +996,7 @@ enum aiComponent {
#define AI_CONFIG_GLOBAL_SCALE_FACTOR_KEY "GLOBAL_SCALE_FACTOR"
#if (!defined AI_CONFIG_GLOBAL_SCALE_FACTOR_DEFAULT)
#define AI_CONFIG_GLOBAL_SCALE_FACTOR_DEFAULT 1.0f
# define AI_CONFIG_GLOBAL_SCALE_FACTOR_DEFAULT 1.0f
#endif // !! AI_DEBONE_THRESHOLD
#define AI_CONFIG_APP_SCALE_KEY "APP_SCALE_FACTOR"
......@@ -997,7 +1013,6 @@ enum aiComponent {
* Property type: Bool. Default value: undefined.
*/
/* #cmakedefine ASSIMP_DOUBLE_PRECISION 1 */
/* #undef ASSIMP_DOUBLE_PRECISION */
#endif // !! AI_CONFIG_H_INC
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment