From 03a4e8854af437dc8d99170a5ae59c6f4ab25feb Mon Sep 17 00:00:00 2001 From: Jonas Fonseca Date: Tue, 17 Mar 2015 11:58:48 -0400 Subject: Fix #26: use doxygen for generating API docs --- .gitignore | 1 + Doxyfile | 1528 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ utf8proc.c | 10 +- utf8proc.h | 725 ++++++++++++++++------------ 4 files changed, 1949 insertions(+), 315 deletions(-) create mode 100644 Doxyfile diff --git a/.gitignore b/.gitignore index e505266..39da333 100644 --- a/.gitignore +++ b/.gitignore @@ -12,6 +12,7 @@ data/*.txt data/*.ttf data/*.sfd +/docs/ bench/bench bench/icu bench/unistring diff --git a/Doxyfile b/Doxyfile new file mode 100644 index 0000000..9b3b9cd --- /dev/null +++ b/Doxyfile @@ -0,0 +1,1528 @@ +# Doxyfile 1.8.9.1 + +# This file describes the settings to be used by the documentation system +# doxygen (www.doxygen.org) for a project. +# +# All text after a double hash (##) is considered a comment and is placed in +# front of the TAG it is preceding. +# +# All text after a single hash (#) is considered a comment and will be ignored. +# The format is: +# TAG = value [value, ...] +# For lists, items can also be appended using: +# TAG += value [value, ...] +# Values that contain spaces should be placed between quotes (\" \"). + +#--------------------------------------------------------------------------- +# Project related configuration options +#--------------------------------------------------------------------------- + +# This tag specifies the encoding used for all characters in the config file +# that follow. The default is UTF-8 which is also the encoding used for all text +# before the first occurrence of this tag. Doxygen uses libiconv (or the iconv +# built into libc) for the transcoding. See http://www.gnu.org/software/libiconv +# for the list of possible encodings. +# The default value is: UTF-8. + +DOXYFILE_ENCODING = UTF-8 + +# The PROJECT_NAME tag is a single word (or a sequence of words surrounded by +# double-quotes, unless you are using Doxywizard) that should identify the +# project for which the documentation is generated. This name is used in the +# title of most generated pages and in a few other places. +# The default value is: My Project. + +PROJECT_NAME = "utf8proc" + +# The PROJECT_NUMBER tag can be used to enter a project or revision number. This +# could be handy for archiving the generated documentation or if some version +# control system is used. + +PROJECT_NUMBER = + +# Using the PROJECT_BRIEF tag one can provide an optional one line description +# for a project that appears at the top of each page and should give viewer a +# quick idea about the purpose of the project. Keep the description short. + +PROJECT_BRIEF = "C library for processing UTF-8 Unicode data" + +# With the PROJECT_LOGO tag one can specify a logo or an icon that is included +# in the documentation. The maximum height of the logo should not exceed 55 +# pixels and the maximum width should not exceed 200 pixels. Doxygen will copy +# the logo to the output directory. + +PROJECT_LOGO = + +# The OUTPUT_DIRECTORY tag is used to specify the (relative or absolute) path +# into which the generated documentation will be written. If a relative path is +# entered, it will be relative to the location where doxygen was started. If +# left blank the current directory will be used. + +OUTPUT_DIRECTORY = docs + +# If the CREATE_SUBDIRS tag is set to YES then doxygen will create 4096 sub- +# directories (in 2 levels) under the output directory of each output format and +# will distribute the generated files over these directories. Enabling this +# option can be useful when feeding doxygen a huge amount of source files, where +# putting all generated files in the same directory would otherwise causes +# performance problems for the file system. +# The default value is: NO. + +CREATE_SUBDIRS = NO + +# If the ALLOW_UNICODE_NAMES tag is set to YES, doxygen will allow non-ASCII +# characters to appear in the names of generated files. If set to NO, non-ASCII +# characters will be escaped, for example _xE3_x81_x84 will be used for Unicode +# U+3044. +# The default value is: NO. + +ALLOW_UNICODE_NAMES = NO + +# The OUTPUT_LANGUAGE tag is used to specify the language in which all +# documentation generated by doxygen is written. Doxygen will use this +# information to generate all constant output in the proper language. +# Possible values are: Afrikaans, Arabic, Armenian, Brazilian, Catalan, Chinese, +# Chinese-Traditional, Croatian, Czech, Danish, Dutch, English (United States), +# Esperanto, Farsi (Persian), Finnish, French, German, Greek, Hungarian, +# Indonesian, Italian, Japanese, Japanese-en (Japanese with English messages), +# Korean, Korean-en (Korean with English messages), Latvian, Lithuanian, +# Macedonian, Norwegian, Persian (Farsi), Polish, Portuguese, Romanian, Russian, +# Serbian, Serbian-Cyrillic, Slovak, Slovene, Spanish, Swedish, Turkish, +# Ukrainian and Vietnamese. +# The default value is: English. + +OUTPUT_LANGUAGE = English + +# If the BRIEF_MEMBER_DESC tag is set to YES, doxygen will include brief member +# descriptions after the members that are listed in the file and class +# documentation (similar to Javadoc). Set to NO to disable this. +# The default value is: YES. + +BRIEF_MEMBER_DESC = YES + +# If the REPEAT_BRIEF tag is set to YES, doxygen will prepend the brief +# description of a member or function before the detailed description +# +# Note: If both HIDE_UNDOC_MEMBERS and BRIEF_MEMBER_DESC are set to NO, the +# brief descriptions will be completely suppressed. +# The default value is: YES. + +REPEAT_BRIEF = YES + +# This tag implements a quasi-intelligent brief description abbreviator that is +# used to form the text in various listings. Each string in this list, if found +# as the leading text of the brief description, will be stripped from the text +# and the result, after processing the whole list, is used as the annotated +# text. Otherwise, the brief description is used as-is. If left blank, the +# following values are used ($name is automatically replaced with the name of +# the entity):The $name class, The $name widget, The $name file, is, provides, +# specifies, contains, represents, a, an and the. + +ABBREVIATE_BRIEF = + +# If the ALWAYS_DETAILED_SEC and REPEAT_BRIEF tags are both set to YES then +# doxygen will generate a detailed section even if there is only a brief +# description. +# The default value is: NO. + +ALWAYS_DETAILED_SEC = NO + +# If the INLINE_INHERITED_MEMB tag is set to YES, doxygen will show all +# inherited members of a class in the documentation of that class as if those +# members were ordinary class members. Constructors, destructors and assignment +# operators of the base classes will not be shown. +# The default value is: NO. + +INLINE_INHERITED_MEMB = NO + +# If the FULL_PATH_NAMES tag is set to YES, doxygen will prepend the full path +# before files name in the file list and in the header files. If set to NO the +# shortest path that makes the file name unique will be used +# The default value is: YES. + +FULL_PATH_NAMES = YES + +# The STRIP_FROM_PATH tag can be used to strip a user-defined part of the path. +# Stripping is only done if one of the specified strings matches the left-hand +# part of the path. The tag can be used to show relative paths in the file list. +# If left blank the directory from which doxygen is run is used as the path to +# strip. +# +# Note that you can specify absolute paths here, but also relative paths, which +# will be relative from the directory where doxygen is started. +# This tag requires that the tag FULL_PATH_NAMES is set to YES. + +STRIP_FROM_PATH = + +# The STRIP_FROM_INC_PATH tag can be used to strip a user-defined part of the +# path mentioned in the documentation of a class, which tells the reader which +# header file to include in order to use a class. If left blank only the name of +# the header file containing the class definition is used. Otherwise one should +# specify the list of include paths that are normally passed to the compiler +# using the -I flag. + +STRIP_FROM_INC_PATH = + +# If the SHORT_NAMES tag is set to YES, doxygen will generate much shorter (but +# less readable) file names. This can be useful is your file systems doesn't +# support long names like on DOS, Mac, or CD-ROM. +# The default value is: NO. + +SHORT_NAMES = NO + +# If the JAVADOC_AUTOBRIEF tag is set to YES then doxygen will interpret the +# first line (until the first dot) of a Javadoc-style comment as the brief +# description. If set to NO, the Javadoc-style will behave just like regular Qt- +# style comments (thus requiring an explicit @brief command for a brief +# description.) +# The default value is: NO. + +JAVADOC_AUTOBRIEF = NO + +# If the QT_AUTOBRIEF tag is set to YES then doxygen will interpret the first +# line (until the first dot) of a Qt-style comment as the brief description. If +# set to NO, the Qt-style will behave just like regular Qt-style comments (thus +# requiring an explicit \brief command for a brief description.) +# The default value is: NO. + +QT_AUTOBRIEF = NO + +# The MULTILINE_CPP_IS_BRIEF tag can be set to YES to make doxygen treat a +# multi-line C++ special comment block (i.e. a block of //! or /// comments) as +# a brief description. This used to be the default behavior. The new default is +# to treat a multi-line C++ comment block as a detailed description. Set this +# tag to YES if you prefer the old behavior instead. +# +# Note that setting this tag to YES also means that rational rose comments are +# not recognized any more. +# The default value is: NO. + +MULTILINE_CPP_IS_BRIEF = NO + +# If the INHERIT_DOCS tag is set to YES then an undocumented member inherits the +# documentation from any documented member that it re-implements. +# The default value is: YES. + +INHERIT_DOCS = YES + +# If the SEPARATE_MEMBER_PAGES tag is set to YES then doxygen will produce a new +# page for each member. If set to NO, the documentation of a member will be part +# of the file/class/namespace that contains it. +# The default value is: NO. + +SEPARATE_MEMBER_PAGES = NO + +# The TAB_SIZE tag can be used to set the number of spaces in a tab. Doxygen +# uses this value to replace tabs by spaces in code fragments. +# Minimum value: 1, maximum value: 16, default value: 4. + +TAB_SIZE = 4 + +# This tag can be used to specify a number of aliases that act as commands in +# the documentation. An alias has the form: +# name=value +# For example adding +# "sideeffect=@par Side Effects:\n" +# will allow you to put the command \sideeffect (or @sideeffect) in the +# documentation, which will result in a user-defined paragraph with heading +# "Side Effects:". You can put \n's in the value part of an alias to insert +# newlines. + +ALIASES = + +# This tag can be used to specify a number of word-keyword mappings (TCL only). +# A mapping has the form "name=value". For example adding "class=itcl::class" +# will allow you to use the command class in the itcl::class meaning. + +TCL_SUBST = + +# Set the OPTIMIZE_OUTPUT_FOR_C tag to YES if your project consists of C sources +# only. Doxygen will then generate output that is more tailored for C. For +# instance, some of the names that are used will be different. The list of all +# members will be omitted, etc. +# The default value is: NO. + +OPTIMIZE_OUTPUT_FOR_C = YES + +# Set the OPTIMIZE_OUTPUT_JAVA tag to YES if your project consists of Java or +# Python sources only. Doxygen will then generate output that is more tailored +# for that language. For instance, namespaces will be presented as packages, +# qualified scopes will look different, etc. +# The default value is: NO. + +OPTIMIZE_OUTPUT_JAVA = NO + +# Set the OPTIMIZE_FOR_FORTRAN tag to YES if your project consists of Fortran +# sources. Doxygen will then generate output that is tailored for Fortran. +# The default value is: NO. + +OPTIMIZE_FOR_FORTRAN = NO + +# Set the OPTIMIZE_OUTPUT_VHDL tag to YES if your project consists of VHDL +# sources. Doxygen will then generate output that is tailored for VHDL. +# The default value is: NO. + +OPTIMIZE_OUTPUT_VHDL = NO + +# Doxygen selects the parser to use depending on the extension of the files it +# parses. With this tag you can assign which parser to use for a given +# extension. Doxygen has a built-in mapping, but you can override or extend it +# using this tag. The format is ext=language, where ext is a file extension, and +# language is one of the parsers supported by doxygen: IDL, Java, Javascript, +# C#, C, C++, D, PHP, Objective-C, Python, Fortran (fixed format Fortran: +# FortranFixed, free formatted Fortran: FortranFree, unknown formatted Fortran: +# Fortran. In the later case the parser tries to guess whether the code is fixed +# or free formatted code, this is the default for Fortran type files), VHDL. For +# instance to make doxygen treat .inc files as Fortran files (default is PHP), +# and .f files as C (default is Fortran), use: inc=Fortran f=C. +# +# Note: For files without extension you can use no_extension as a placeholder. +# +# Note that for custom extensions you also need to set FILE_PATTERNS otherwise +# the files are not read by doxygen. + +EXTENSION_MAPPING = + +# If the MARKDOWN_SUPPORT tag is enabled then doxygen pre-processes all comments +# according to the Markdown format, which allows for more readable +# documentation. See http://daringfireball.net/projects/markdown/ for details. +# The output of markdown processing is further processed by doxygen, so you can +# mix doxygen, HTML, and XML commands with Markdown formatting. Disable only in +# case of backward compatibilities issues. +# The default value is: YES. + +MARKDOWN_SUPPORT = YES + +# When enabled doxygen tries to link words that correspond to documented +# classes, or namespaces to their corresponding documentation. Such a link can +# be prevented in individual cases by putting a % sign in front of the word or +# globally by setting AUTOLINK_SUPPORT to NO. +# The default value is: YES. + +AUTOLINK_SUPPORT = YES + +# If you use STL classes (i.e. std::string, std::vector, etc.) but do not want +# to include (a tag file for) the STL sources as input, then you should set this +# tag to YES in order to let doxygen match functions declarations and +# definitions whose arguments contain STL classes (e.g. func(std::string); +# versus func(std::string) {}). This also make the inheritance and collaboration +# diagrams that involve STL classes more complete and accurate. +# The default value is: NO. + +BUILTIN_STL_SUPPORT = NO + +# If you use Microsoft's C++/CLI language, you should set this option to YES to +# enable parsing support. +# The default value is: NO. + +CPP_CLI_SUPPORT = NO + +# Set the SIP_SUPPORT tag to YES if your project consists of sip (see: +# http://www.riverbankcomputing.co.uk/software/sip/intro) sources only. Doxygen +# will parse them like normal C++ but will assume all classes use public instead +# of private inheritance when no explicit protection keyword is present. +# The default value is: NO. + +SIP_SUPPORT = NO + +# For Microsoft's IDL there are propget and propput attributes to indicate +# getter and setter methods for a property. Setting this option to YES will make +# doxygen to replace the get and set methods by a property in the documentation. +# This will only work if the methods are indeed getting or setting a simple +# type. If this is not the case, or you want to show the methods anyway, you +# should set this option to NO. +# The default value is: YES. + +IDL_PROPERTY_SUPPORT = YES + +# If member grouping is used in the documentation and the DISTRIBUTE_GROUP_DOC +# tag is set to YES then doxygen will reuse the documentation of the first +# member in the group (if any) for the other members of the group. By default +# all members of a group must be documented explicitly. +# The default value is: NO. + +DISTRIBUTE_GROUP_DOC = NO + +# Set the SUBGROUPING tag to YES to allow class member groups of the same type +# (for instance a group of public functions) to be put as a subgroup of that +# type (e.g. under the Public Functions section). Set it to NO to prevent +# subgrouping. Alternatively, this can be done per class using the +# \nosubgrouping command. +# The default value is: YES. + +SUBGROUPING = YES + +# When the INLINE_GROUPED_CLASSES tag is set to YES, classes, structs and unions +# are shown inside the group in which they are included (e.g. using \ingroup) +# instead of on a separate page (for HTML and Man pages) or section (for LaTeX +# and RTF). +# +# Note that this feature does not work in combination with +# SEPARATE_MEMBER_PAGES. +# The default value is: NO. + +INLINE_GROUPED_CLASSES = NO + +# When the INLINE_SIMPLE_STRUCTS tag is set to YES, structs, classes, and unions +# with only public data fields or simple typedef fields will be shown inline in +# the documentation of the scope in which they are defined (i.e. file, +# namespace, or group documentation), provided this scope is documented. If set +# to NO, structs, classes, and unions are shown on a separate page (for HTML and +# Man pages) or section (for LaTeX and RTF). +# The default value is: NO. + +INLINE_SIMPLE_STRUCTS = NO + +# When TYPEDEF_HIDES_STRUCT tag is enabled, a typedef of a struct, union, or +# enum is documented as struct, union, or enum with the name of the typedef. So +# typedef struct TypeS {} TypeT, will appear in the documentation as a struct +# with name TypeT. When disabled the typedef will appear as a member of a file, +# namespace, or class. And the struct will be named TypeS. This can typically be +# useful for C code in case the coding convention dictates that all compound +# types are typedef'ed and only the typedef is referenced, never the tag name. +# The default value is: NO. + +TYPEDEF_HIDES_STRUCT = NO + +# The size of the symbol lookup cache can be set using LOOKUP_CACHE_SIZE. This +# cache is used to resolve symbols given their name and scope. Since this can be +# an expensive process and often the same symbol appears multiple times in the +# code, doxygen keeps a cache of pre-resolved symbols. If the cache is too small +# doxygen will become slower. If the cache is too large, memory is wasted. The +# cache size is given by this formula: 2^(16+LOOKUP_CACHE_SIZE). The valid range +# is 0..9, the default is 0, corresponding to a cache size of 2^16=65536 +# symbols. At the end of a run doxygen will report the cache usage and suggest +# the optimal cache size from a speed point of view. +# Minimum value: 0, maximum value: 9, default value: 0. + +LOOKUP_CACHE_SIZE = 0 + +#--------------------------------------------------------------------------- +# Build related configuration options +#--------------------------------------------------------------------------- + +# If the EXTRACT_ALL tag is set to YES, doxygen will assume all entities in +# documentation are documented, even if no documentation was available. Private +# class members and static file members will be hidden unless the +# EXTRACT_PRIVATE respectively EXTRACT_STATIC tags are set to YES. +# Note: This will also disable the warnings about undocumented members that are +# normally produced when WARNINGS is set to YES. +# The default value is: NO. + +EXTRACT_ALL = NO + +# If the EXTRACT_PRIVATE tag is set to YES, all private members of a class will +# be included in the documentation. +# The default value is: NO. + +EXTRACT_PRIVATE = NO + +# If the EXTRACT_PACKAGE tag is set to YES, all members with package or internal +# scope will be included in the documentation. +# The default value is: NO. + +EXTRACT_PACKAGE = NO + +# If the EXTRACT_STATIC tag is set to YES, all static members of a file will be +# included in the documentation. +# The default value is: NO. + +EXTRACT_STATIC = NO + +# If the EXTRACT_LOCAL_CLASSES tag is set to YES, classes (and structs) defined +# locally in source files will be included in the documentation. If set to NO, +# only classes defined in header files are included. Does not have any effect +# for Java sources. +# The default value is: YES. + +EXTRACT_LOCAL_CLASSES = YES + +# This flag is only useful for Objective-C code. If set to YES, local methods, +# which are defined in the implementation section but not in the interface are +# included in the documentation. If set to NO, only methods in the interface are +# included. +# The default value is: NO. + +EXTRACT_LOCAL_METHODS = NO + +# If this flag is set to YES, the members of anonymous namespaces will be +# extracted and appear in the documentation as a namespace called +# 'anonymous_namespace{file}', where file will be replaced with the base name of +# the file that contains the anonymous namespace. By default anonymous namespace +# are hidden. +# The default value is: NO. + +EXTRACT_ANON_NSPACES = NO + +# If the HIDE_UNDOC_MEMBERS tag is set to YES, doxygen will hide all +# undocumented members inside documented classes or files. If set to NO these +# members will be included in the various overviews, but no documentation +# section is generated. This option has no effect if EXTRACT_ALL is enabled. +# The default value is: NO. + +HIDE_UNDOC_MEMBERS = NO + +# If the HIDE_UNDOC_CLASSES tag is set to YES, doxygen will hide all +# undocumented classes that are normally visible in the class hierarchy. If set +# to NO, these classes will be included in the various overviews. This option +# has no effect if EXTRACT_ALL is enabled. +# The default value is: NO. + +HIDE_UNDOC_CLASSES = NO + +# If the HIDE_FRIEND_COMPOUNDS tag is set to YES, doxygen will hide all friend +# (class|struct|union) declarations. If set to NO, these declarations will be +# included in the documentation. +# The default value is: NO. + +HIDE_FRIEND_COMPOUNDS = NO + +# If the HIDE_IN_BODY_DOCS tag is set to YES, doxygen will hide any +# documentation blocks found inside the body of a function. If set to NO, these +# blocks will be appended to the function's detailed documentation block. +# The default value is: NO. + +HIDE_IN_BODY_DOCS = NO + +# The INTERNAL_DOCS tag determines if documentation that is typed after a +# \internal command is included. If the tag is set to NO then the documentation +# will be excluded. Set it to YES to include the internal documentation. +# The default value is: NO. + +INTERNAL_DOCS = NO + +# If the CASE_SENSE_NAMES tag is set to NO then doxygen will only generate file +# names in lower-case letters. If set to YES, upper-case letters are also +# allowed. This is useful if you have classes or files whose names only differ +# in case and if your file system supports case sensitive file names. Windows +# and Mac users are advised to set this option to NO. +# The default value is: system dependent. + +CASE_SENSE_NAMES = NO + +# If the HIDE_SCOPE_NAMES tag is set to NO then doxygen will show members with +# their full class and namespace scopes in the documentation. If set to YES, the +# scope will be hidden. +# The default value is: NO. + +HIDE_SCOPE_NAMES = NO + +# If the HIDE_COMPOUND_REFERENCE tag is set to NO (default) then doxygen will +# append additional text to a page's title, such as Class Reference. If set to +# YES the compound reference will be hidden. +# The default value is: NO. + +HIDE_COMPOUND_REFERENCE= NO + +# If the SHOW_INCLUDE_FILES tag is set to YES then doxygen will put a list of +# the files that are included by a file in the documentation of that file. +# The default value is: YES. + +SHOW_INCLUDE_FILES = YES + +# If the SHOW_GROUPED_MEMB_INC tag is set to YES then Doxygen will add for each +# grouped member an include statement to the documentation, telling the reader +# which file to include in order to use the member. +# The default value is: NO. + +SHOW_GROUPED_MEMB_INC = NO + +# If the FORCE_LOCAL_INCLUDES tag is set to YES then doxygen will list include +# files with double quotes in the documentation rather than with sharp brackets. +# The default value is: NO. + +FORCE_LOCAL_INCLUDES = NO + +# If the INLINE_INFO tag is set to YES then a tag [inline] is inserted in the +# documentation for inline members. +# The default value is: YES. + +INLINE_INFO = YES + +# If the SORT_MEMBER_DOCS tag is set to YES then doxygen will sort the +# (detailed) documentation of file and class members alphabetically by member +# name. If set to NO, the members will appear in declaration order. +# The default value is: YES. + +SORT_MEMBER_DOCS = YES + +# If the SORT_BRIEF_DOCS tag is set to YES then doxygen will sort the brief +# descriptions of file, namespace and class members alphabetically by member +# name. If set to NO, the members will appear in declaration order. Note that +# this will also influence the order of the classes in the class list. +# The default value is: NO. + +SORT_BRIEF_DOCS = NO + +# If the SORT_MEMBERS_CTORS_1ST tag is set to YES then doxygen will sort the +# (brief and detailed) documentation of class members so that constructors and +# destructors are listed first. If set to NO the constructors will appear in the +# respective orders defined by SORT_BRIEF_DOCS and SORT_MEMBER_DOCS. +# Note: If SORT_BRIEF_DOCS is set to NO this option is ignored for sorting brief +# member documentation. +# Note: If SORT_MEMBER_DOCS is set to NO this option is ignored for sorting +# detailed member documentation. +# The default value is: NO. + +SORT_MEMBERS_CTORS_1ST = NO + +# If the SORT_GROUP_NAMES tag is set to YES then doxygen will sort the hierarchy +# of group names into alphabetical order. If set to NO the group names will +# appear in their defined order. +# The default value is: NO. + +SORT_GROUP_NAMES = NO + +# If the SORT_BY_SCOPE_NAME tag is set to YES, the class list will be sorted by +# fully-qualified names, including namespaces. If set to NO, the class list will +# be sorted only by class name, not including the namespace part. +# Note: This option is not very useful if HIDE_SCOPE_NAMES is set to YES. +# Note: This option applies only to the class list, not to the alphabetical +# list. +# The default value is: NO. + +SORT_BY_SCOPE_NAME = NO + +# If the STRICT_PROTO_MATCHING option is enabled and doxygen fails to do proper +# type resolution of all parameters of a function it will reject a match between +# the prototype and the implementation of a member function even if there is +# only one candidate or it is obvious which candidate to choose by doing a +# simple string match. By disabling STRICT_PROTO_MATCHING doxygen will still +# accept a match between prototype and implementation in such cases. +# The default value is: NO. + +STRICT_PROTO_MATCHING = NO + +# The GENERATE_TODOLIST tag can be used to enable (YES) or disable (NO) the todo +# list. This list is created by putting \todo commands in the documentation. +# The default value is: YES. + +GENERATE_TODOLIST = YES + +# The GENERATE_TESTLIST tag can be used to enable (YES) or disable (NO) the test +# list. This list is created by putting \test commands in the documentation. +# The default value is: YES. + +GENERATE_TESTLIST = YES + +# The GENERATE_BUGLIST tag can be used to enable (YES) or disable (NO) the bug +# list. This list is created by putting \bug commands in the documentation. +# The default value is: YES. + +GENERATE_BUGLIST = YES + +# The GENERATE_DEPRECATEDLIST tag can be used to enable (YES) or disable (NO) +# the deprecated list. This list is created by putting \deprecated commands in +# the documentation. +# The default value is: YES. + +GENERATE_DEPRECATEDLIST= YES + +# The ENABLED_SECTIONS tag can be used to enable conditional documentation +# sections, marked by \if ... \endif and \cond +# ... \endcond blocks. + +ENABLED_SECTIONS = + +# The MAX_INITIALIZER_LINES tag determines the maximum number of lines that the +# initial value of a variable or macro / define can have for it to appear in the +# documentation. If the initializer consists of more lines than specified here +# it will be hidden. Use a value of 0 to hide initializers completely. The +# appearance of the value of individual variables and macros / defines can be +# controlled using \showinitializer or \hideinitializer command in the +# documentation regardless of this setting. +# Minimum value: 0, maximum value: 10000, default value: 30. + +MAX_INITIALIZER_LINES = 30 + +# Set the SHOW_USED_FILES tag to NO to disable the list of files generated at +# the bottom of the documentation of classes and structs. If set to YES, the +# list will mention the files that were used to generate the documentation. +# The default value is: YES. + +SHOW_USED_FILES = YES + +# Set the SHOW_FILES tag to NO to disable the generation of the Files page. This +# will remove the Files entry from the Quick Index and from the Folder Tree View +# (if specified). +# The default value is: YES. + +SHOW_FILES = YES + +# Set the SHOW_NAMESPACES tag to NO to disable the generation of the Namespaces +# page. This will remove the Namespaces entry from the Quick Index and from the +# Folder Tree View (if specified). +# The default value is: YES. + +SHOW_NAMESPACES = YES + +# The FILE_VERSION_FILTER tag can be used to specify a program or script that +# doxygen should invoke to get the current version for each file (typically from +# the version control system). Doxygen will invoke the program by executing (via +# popen()) the command command input-file, where command is the value of the +# FILE_VERSION_FILTER tag, and input-file is the name of an input file provided +# by doxygen. Whatever the program writes to standard output is used as the file +# version. For an example see the documentation. + +FILE_VERSION_FILTER = + +# The LAYOUT_FILE tag can be used to specify a layout file which will be parsed +# by doxygen. The layout file controls the global structure of the generated +# output files in an output format independent way. To create the layout file +# that represents doxygen's defaults, run doxygen with the -l option. You can +# optionally specify a file name after the option, if omitted DoxygenLayout.xml +# will be used as the name of the layout file. +# +# Note that if you run doxygen from a directory containing a file called +# DoxygenLayout.xml, doxygen will parse it automatically even if the LAYOUT_FILE +# tag is left empty. + +LAYOUT_FILE = + +# The CITE_BIB_FILES tag can be used to specify one or more bib files containing +# the reference definitions. This must be a list of .bib files. The .bib +# extension is automatically appended if omitted. This requires the bibtex tool +# to be installed. See also http://en.wikipedia.org/wiki/BibTeX for more info. +# For LaTeX the style of the bibliography can be controlled using +# LATEX_BIB_STYLE. To use this feature you need bibtex and perl available in the +# search path. See also \cite for info how to create references. + +CITE_BIB_FILES = + +#--------------------------------------------------------------------------- +# Configuration options related to warning and progress messages +#--------------------------------------------------------------------------- + +# The QUIET tag can be used to turn on/off the messages that are generated to +# standard output by doxygen. If QUIET is set to YES this implies that the +# messages are off. +# The default value is: NO. + +QUIET = YES + +# The WARNINGS tag can be used to turn on/off the warning messages that are +# generated to standard error (stderr) by doxygen. If WARNINGS is set to YES +# this implies that the warnings are on. +# +# Tip: Turn warnings on while writing the documentation. +# The default value is: YES. + +WARNINGS = YES + +# If the WARN_IF_UNDOCUMENTED tag is set to YES then doxygen will generate +# warnings for undocumented members. If EXTRACT_ALL is set to YES then this flag +# will automatically be disabled. +# The default value is: YES. + +WARN_IF_UNDOCUMENTED = YES + +# If the WARN_IF_DOC_ERROR tag is set to YES, doxygen will generate warnings for +# potential errors in the documentation, such as not documenting some parameters +# in a documented function, or documenting parameters that don't exist or using +# markup commands wrongly. +# The default value is: YES. + +WARN_IF_DOC_ERROR = YES + +# This WARN_NO_PARAMDOC option can be enabled to get warnings for functions that +# are documented, but have no documentation for their parameters or return +# value. If set to NO, doxygen will only warn about wrong or incomplete +# parameter documentation, but not about the absence of documentation. +# The default value is: NO. + +WARN_NO_PARAMDOC = NO + +# The WARN_FORMAT tag determines the format of the warning messages that doxygen +# can produce. The string should contain the $file, $line, and $text tags, which +# will be replaced by the file and line number from which the warning originated +# and the warning text. Optionally the format may contain $version, which will +# be replaced by the version of the file (if it could be obtained via +# FILE_VERSION_FILTER) +# The default value is: $file:$line: $text. + +WARN_FORMAT = "$file:$line: $text" + +# The WARN_LOGFILE tag can be used to specify a file to which warning and error +# messages should be written. If left blank the output is written to standard +# error (stderr). + +WARN_LOGFILE = + +#--------------------------------------------------------------------------- +# Configuration options related to the input files +#--------------------------------------------------------------------------- + +# The INPUT tag is used to specify the files and/or directories that contain +# documented source files. You may enter file names like myfile.cpp or +# directories like /usr/src/myproject. Separate the files or directories with +# spaces. +# Note: If this tag is empty the current directory is searched. + +INPUT = + +# This tag can be used to specify the character encoding of the source files +# that doxygen parses. Internally doxygen uses the UTF-8 encoding. Doxygen uses +# libiconv (or the iconv built into libc) for the transcoding. See the libiconv +# documentation (see: http://www.gnu.org/software/libiconv) for the list of +# possible encodings. +# The default value is: UTF-8. + +INPUT_ENCODING = UTF-8 + +# If the value of the INPUT tag contains directories, you can use the +# FILE_PATTERNS tag to specify one or more wildcard patterns (like *.cpp and +# *.h) to filter out the source-files in the directories. If left blank the +# following patterns are tested:*.c, *.cc, *.cxx, *.cpp, *.c++, *.java, *.ii, +# *.ixx, *.ipp, *.i++, *.inl, *.idl, *.ddl, *.odl, *.h, *.hh, *.hxx, *.hpp, +# *.h++, *.cs, *.d, *.php, *.php4, *.php5, *.phtml, *.inc, *.m, *.markdown, +# *.md, *.mm, *.dox, *.py, *.f90, *.f, *.for, *.tcl, *.vhd, *.vhdl, *.ucf, +# *.qsf, *.as and *.js. + +FILE_PATTERNS = + +# The RECURSIVE tag can be used to specify whether or not subdirectories should +# be searched for input files as well. +# The default value is: NO. + +RECURSIVE = NO + +# The EXCLUDE tag can be used to specify files and/or directories that should be +# excluded from the INPUT source files. This way you can easily exclude a +# subdirectory from a directory tree whose root is specified with the INPUT tag. +# +# Note that relative paths are relative to the directory from which doxygen is +# run. + +EXCLUDE = NEWS.md lump.md + +# The EXCLUDE_SYMLINKS tag can be used to select whether or not files or +# directories that are symbolic links (a Unix file system feature) are excluded +# from the input. +# The default value is: NO. + +EXCLUDE_SYMLINKS = NO + +# If the value of the INPUT tag contains directories, you can use the +# EXCLUDE_PATTERNS tag to specify one or more wildcard patterns to exclude +# certain files from those directories. +# +# Note that the wildcards are matched against the file with absolute path, so to +# exclude all test directories for example use the pattern */test/* + +EXCLUDE_PATTERNS = + +# The EXCLUDE_SYMBOLS tag can be used to specify one or more symbol names +# (namespaces, classes, functions, etc.) that should be excluded from the +# output. The symbol name can be a fully qualified name, a word, or if the +# wildcard * is used, a substring. Examples: ANamespace, AClass, +# AClass::ANamespace, ANamespace::*Test +# +# Note that the wildcards are matched against the file with absolute path, so to +# exclude all test directories use the pattern */test/* + +EXCLUDE_SYMBOLS = DLLEXPORT SSIZE_MAX + +# The EXAMPLE_PATH tag can be used to specify one or more files or directories +# that contain example code fragments that are included (see the \include +# command). + +EXAMPLE_PATH = + +# If the value of the EXAMPLE_PATH tag contains directories, you can use the +# EXAMPLE_PATTERNS tag to specify one or more wildcard pattern (like *.cpp and +# *.h) to filter out the source-files in the directories. If left blank all +# files are included. + +EXAMPLE_PATTERNS = + +# If the EXAMPLE_RECURSIVE tag is set to YES then subdirectories will be +# searched for input files to be used with the \include or \dontinclude commands +# irrespective of the value of the RECURSIVE tag. +# The default value is: NO. + +EXAMPLE_RECURSIVE = NO + +# The IMAGE_PATH tag can be used to specify one or more files or directories +# that contain images that are to be included in the documentation (see the +# \image command). + +IMAGE_PATH = + +# The INPUT_FILTER tag can be used to specify a program that doxygen should +# invoke to filter for each input file. Doxygen will invoke the filter program +# by executing (via popen()) the command: +# +# +# +# where is the value of the INPUT_FILTER tag, and is the +# name of an input file. Doxygen will then use the output that the filter +# program writes to standard output. If FILTER_PATTERNS is specified, this tag +# will be ignored. +# +# Note that the filter must not add or remove lines; it is applied before the +# code is scanned, but not when the output code is generated. If lines are added +# or removed, the anchors will not be placed correctly. + +INPUT_FILTER = + +# The FILTER_PATTERNS tag can be used to specify filters on a per file pattern +# basis. Doxygen will compare the file name with each pattern and apply the +# filter if there is a match. The filters are a list of the form: pattern=filter +# (like *.cpp=my_cpp_filter). See INPUT_FILTER for further information on how +# filters are used. If the FILTER_PATTERNS tag is empty or if none of the +# patterns match the file name, INPUT_FILTER is applied. + +FILTER_PATTERNS = + +# If the FILTER_SOURCE_FILES tag is set to YES, the input filter (if set using +# INPUT_FILTER) will also be used to filter the input files that are used for +# producing the source files to browse (i.e. when SOURCE_BROWSER is set to YES). +# The default value is: NO. + +FILTER_SOURCE_FILES = NO + +# The FILTER_SOURCE_PATTERNS tag can be used to specify source filters per file +# pattern. A pattern will override the setting for FILTER_PATTERN (if any) and +# it is also possible to disable source filtering for a specific pattern using +# *.ext= (so without naming a filter). +# This tag requires that the tag FILTER_SOURCE_FILES is set to YES. + +FILTER_SOURCE_PATTERNS = + +# If the USE_MDFILE_AS_MAINPAGE tag refers to the name of a markdown file that +# is part of the input, its contents will be placed on the main page +# (index.html). This can be useful if you have a project on for instance GitHub +# and want to reuse the introduction page also for the doxygen output. + +USE_MDFILE_AS_MAINPAGE = + +#--------------------------------------------------------------------------- +# Configuration options related to source browsing +#--------------------------------------------------------------------------- + +# If the SOURCE_BROWSER tag is set to YES then a list of source files will be +# generated. Documented entities will be cross-referenced with these sources. +# +# Note: To get rid of all source code in the generated output, make sure that +# also VERBATIM_HEADERS is set to NO. +# The default value is: NO. + +SOURCE_BROWSER = NO + +# Setting the INLINE_SOURCES tag to YES will include the body of functions, +# classes and enums directly into the documentation. +# The default value is: NO. + +INLINE_SOURCES = NO + +# Setting the STRIP_CODE_COMMENTS tag to YES will instruct doxygen to hide any +# special comment blocks from generated source code fragments. Normal C, C++ and +# Fortran comments will always remain visible. +# The default value is: YES. + +STRIP_CODE_COMMENTS = YES + +# If the REFERENCED_BY_RELATION tag is set to YES then for each documented +# function all documented functions referencing it will be listed. +# The default value is: NO. + +REFERENCED_BY_RELATION = NO + +# If the REFERENCES_RELATION tag is set to YES then for each documented function +# all documented entities called/used by that function will be listed. +# The default value is: NO. + +REFERENCES_RELATION = NO + +# If the REFERENCES_LINK_SOURCE tag is set to YES and SOURCE_BROWSER tag is set +# to YES then the hyperlinks from functions in REFERENCES_RELATION and +# REFERENCED_BY_RELATION lists will link to the source code. Otherwise they will +# link to the documentation. +# The default value is: YES. + +REFERENCES_LINK_SOURCE = YES + +# If SOURCE_TOOLTIPS is enabled (the default) then hovering a hyperlink in the +# source code will show a tooltip with additional information such as prototype, +# brief description and links to the definition and documentation. Since this +# will make the HTML file larger and loading of large files a bit slower, you +# can opt to disable this feature. +# The default value is: YES. +# This tag requires that the tag SOURCE_BROWSER is set to YES. + +SOURCE_TOOLTIPS = YES + +# If the USE_HTAGS tag is set to YES then the references to source code will +# point to the HTML generated by the htags(1) tool instead of doxygen built-in +# source browser. The htags tool is part of GNU's global source tagging system +# (see http://www.gnu.org/software/global/global.html). You will need version +# 4.8.6 or higher. +# +# To use it do the following: +# - Install the latest version of global +# - Enable SOURCE_BROWSER and USE_HTAGS in the config file +# - Make sure the INPUT points to the root of the source tree +# - Run doxygen as normal +# +# Doxygen will invoke htags (and that will in turn invoke gtags), so these +# tools must be available from the command line (i.e. in the search path). +# +# The result: instead of the source browser generated by doxygen, the links to +# source code will now point to the output of htags. +# The default value is: NO. +# This tag requires that the tag SOURCE_BROWSER is set to YES. + +USE_HTAGS = NO + +# If the VERBATIM_HEADERS tag is set the YES then doxygen will generate a +# verbatim copy of the header file for each class for which an include is +# specified. Set to NO to disable this. +# See also: Section \class. +# The default value is: YES. + +VERBATIM_HEADERS = YES + +#--------------------------------------------------------------------------- +# Configuration options related to the alphabetical class index +#--------------------------------------------------------------------------- + +# If the ALPHABETICAL_INDEX tag is set to YES, an alphabetical index of all +# compounds will be generated. Enable this if the project contains a lot of +# classes, structs, unions or interfaces. +# The default value is: YES. + +ALPHABETICAL_INDEX = YES + +# The COLS_IN_ALPHA_INDEX tag can be used to specify the number of columns in +# which the alphabetical index list will be split. +# Minimum value: 1, maximum value: 20, default value: 5. +# This tag requires that the tag ALPHABETICAL_INDEX is set to YES. + +COLS_IN_ALPHA_INDEX = 5 + +# In case all classes in a project start with a common prefix, all classes will +# be put under the same header in the alphabetical index. The IGNORE_PREFIX tag +# can be used to specify a prefix (or a list of prefixes) that should be ignored +# while generating the index headers. +# This tag requires that the tag ALPHABETICAL_INDEX is set to YES. + +IGNORE_PREFIX = + +#--------------------------------------------------------------------------- +# Configuration options related to the HTML output +#--------------------------------------------------------------------------- + +# If the GENERATE_HTML tag is set to YES, doxygen will generate HTML output +# The default value is: YES. + +GENERATE_HTML = YES + +# The HTML_OUTPUT tag is used to specify where the HTML docs will be put. If a +# relative path is entered the value of OUTPUT_DIRECTORY will be put in front of +# it. +# The default directory is: html. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_OUTPUT = html + +# The HTML_FILE_EXTENSION tag can be used to specify the file extension for each +# generated HTML page (for example: .htm, .php, .asp). +# The default value is: .html. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_FILE_EXTENSION = .html + +# The HTML_HEADER tag can be used to specify a user-defined HTML header file for +# each generated HTML page. If the tag is left blank doxygen will generate a +# standard header. +# +# To get valid HTML the header file that includes any scripts and style sheets +# that doxygen needs, which is dependent on the configuration options used (e.g. +# the setting GENERATE_TREEVIEW). It is highly recommended to start with a +# default header using +# doxygen -w html new_header.html new_footer.html new_stylesheet.css +# YourConfigFile +# and then modify the file new_header.html. See also section "Doxygen usage" +# for information on how to generate the default header that doxygen normally +# uses. +# Note: The header is subject to change so you typically have to regenerate the +# default header when upgrading to a newer version of doxygen. For a description +# of the possible markers and block names see the documentation. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_HEADER = + +# The HTML_FOOTER tag can be used to specify a user-defined HTML footer for each +# generated HTML page. If the tag is left blank doxygen will generate a standard +# footer. See HTML_HEADER for more information on how to generate a default +# footer and what special commands can be used inside the footer. See also +# section "Doxygen usage" for information on how to generate the default footer +# that doxygen normally uses. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_FOOTER = + +# The HTML_STYLESHEET tag can be used to specify a user-defined cascading style +# sheet that is used by each HTML page. It can be used to fine-tune the look of +# the HTML output. If left blank doxygen will generate a default style sheet. +# See also section "Doxygen usage" for information on how to generate the style +# sheet that doxygen normally uses. +# Note: It is recommended to use HTML_EXTRA_STYLESHEET instead of this tag, as +# it is more robust and this tag (HTML_STYLESHEET) will in the future become +# obsolete. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_STYLESHEET = + +# The HTML_EXTRA_STYLESHEET tag can be used to specify additional user-defined +# cascading style sheets that are included after the standard style sheets +# created by doxygen. Using this option one can overrule certain style aspects. +# This is preferred over using HTML_STYLESHEET since it does not replace the +# standard style sheet and is therefore more robust against future updates. +# Doxygen will copy the style sheet files to the output directory. +# Note: The order of the extra style sheet files is of importance (e.g. the last +# style sheet in the list overrules the setting of the previous ones in the +# list). For an example see the documentation. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_EXTRA_STYLESHEET = + +# The HTML_EXTRA_FILES tag can be used to specify one or more extra images or +# other source files which should be copied to the HTML output directory. Note +# that these files will be copied to the base HTML output directory. Use the +# $relpath^ marker in the HTML_HEADER and/or HTML_FOOTER files to load these +# files. In the HTML_STYLESHEET file, use the file name only. Also note that the +# files will be copied as-is; there are no commands or markers available. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_EXTRA_FILES = + +# The HTML_COLORSTYLE_HUE tag controls the color of the HTML output. Doxygen +# will adjust the colors in the style sheet and background images according to +# this color. Hue is specified as an angle on a colorwheel, see +# http://en.wikipedia.org/wiki/Hue for more information. For instance the value +# 0 represents red, 60 is yellow, 120 is green, 180 is cyan, 240 is blue, 300 +# purple, and 360 is red again. +# Minimum value: 0, maximum value: 359, default value: 220. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_COLORSTYLE_HUE = 220 + +# The HTML_COLORSTYLE_SAT tag controls the purity (or saturation) of the colors +# in the HTML output. For a value of 0 the output will use grayscales only. A +# value of 255 will produce the most vivid colors. +# Minimum value: 0, maximum value: 255, default value: 100. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_COLORSTYLE_SAT = 100 + +# The HTML_COLORSTYLE_GAMMA tag controls the gamma correction applied to the +# luminance component of the colors in the HTML output. Values below 100 +# gradually make the output lighter, whereas values above 100 make the output +# darker. The value divided by 100 is the actual gamma applied, so 80 represents +# a gamma of 0.8, The value 220 represents a gamma of 2.2, and 100 does not +# change the gamma. +# Minimum value: 40, maximum value: 240, default value: 80. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_COLORSTYLE_GAMMA = 80 + +# If the HTML_TIMESTAMP tag is set to YES then the footer of each generated HTML +# page will contain the date and time when the page was generated. Setting this +# to NO can help when comparing the output of multiple runs. +# The default value is: YES. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_TIMESTAMP = YES + +# If the HTML_DYNAMIC_SECTIONS tag is set to YES then the generated HTML +# documentation will contain sections that can be hidden and shown after the +# page has loaded. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_DYNAMIC_SECTIONS = NO + +# With HTML_INDEX_NUM_ENTRIES one can control the preferred number of entries +# shown in the various tree structured indices initially; the user can expand +# and collapse entries dynamically later on. Doxygen will expand the tree to +# such a level that at most the specified number of entries are visible (unless +# a fully collapsed tree already exceeds this amount). So setting the number of +# entries 1 will produce a full collapsed tree by default. 0 is a special value +# representing an infinite number of entries and will result in a full expanded +# tree by default. +# Minimum value: 0, maximum value: 9999, default value: 100. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_INDEX_NUM_ENTRIES = 100 + +# If the GENERATE_DOCSET tag is set to YES, additional index files will be +# generated that can be used as input for Apple's Xcode 3 integrated development +# environment (see: http://developer.apple.com/tools/xcode/), introduced with +# OSX 10.5 (Leopard). To create a documentation set, doxygen will generate a +# Makefile in the HTML output directory. Running make will produce the docset in +# that directory and running make install will install the docset in +# ~/Library/Developer/Shared/Documentation/DocSets so that Xcode will find it at +# startup. See http://developer.apple.com/tools/creatingdocsetswithdoxygen.html +# for more information. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +GENERATE_DOCSET = NO + +# This tag determines the name of the docset feed. A documentation feed provides +# an umbrella under which multiple documentation sets from a single provider +# (such as a company or product suite) can be grouped. +# The default value is: Doxygen generated docs. +# This tag requires that the tag GENERATE_DOCSET is set to YES. + +DOCSET_FEEDNAME = "Doxygen generated docs" + +# This tag specifies a string that should uniquely identify the documentation +# set bundle. This should be a reverse domain-name style string, e.g. +# com.mycompany.MyDocSet. Doxygen will append .docset to the name. +# The default value is: org.doxygen.Project. +# This tag requires that the tag GENERATE_DOCSET is set to YES. + +DOCSET_BUNDLE_ID = org.doxygen.Project + +# The DOCSET_PUBLISHER_ID tag specifies a string that should uniquely identify +# the documentation publisher. This should be a reverse domain-name style +# string, e.g. com.mycompany.MyDocSet.documentation. +# The default value is: org.doxygen.Publisher. +# This tag requires that the tag GENERATE_DOCSET is set to YES. + +DOCSET_PUBLISHER_ID = org.doxygen.Publisher + +# The DOCSET_PUBLISHER_NAME tag identifies the documentation publisher. +# The default value is: Publisher. +# This tag requires that the tag GENERATE_DOCSET is set to YES. + +DOCSET_PUBLISHER_NAME = Publisher + +# If the GENERATE_HTMLHELP tag is set to YES then doxygen generates three +# additional HTML index files: index.hhp, index.hhc, and index.hhk. The +# index.hhp is a project file that can be read by Microsoft's HTML Help Workshop +# (see: http://www.microsoft.com/en-us/download/details.aspx?id=21138) on +# Windows. +# +# The HTML Help Workshop contains a compiler that can convert all HTML output +# generated by doxygen into a single compiled HTML file (.chm). Compiled HTML +# files are now used as the Windows 98 help format, and will replace the old +# Windows help format (.hlp) on all Windows platforms in the future. Compressed +# HTML files also contain an index, a table of contents, and you can search for +# words in the documentation. The HTML workshop also contains a viewer for +# compressed HTML files. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +GENERATE_HTMLHELP = NO + +# The CHM_FILE tag can be used to specify the file name of the resulting .chm +# file. You can add a path in front of the file if the result should not be +# written to the html output directory. +# This tag requires that the tag GENERATE_HTMLHELP is set to YES. + +CHM_FILE = + +# The HHC_LOCATION tag can be used to specify the location (absolute path +# including file name) of the HTML help compiler (hhc.exe). If non-empty, +# doxygen will try to run the HTML help compiler on the generated index.hhp. +# The file has to be specified with full path. +# This tag requires that the tag GENERATE_HTMLHELP is set to YES. + +HHC_LOCATION = + +# The GENERATE_CHI flag controls if a separate .chi index file is generated +# (YES) or that it should be included in the master .chm file (NO). +# The default value is: NO. +# This tag requires that the tag GENERATE_HTMLHELP is set to YES. + +GENERATE_CHI = NO + +# The CHM_INDEX_ENCODING is used to encode HtmlHelp index (hhk), content (hhc) +# and project file content. +# This tag requires that the tag GENERATE_HTMLHELP is set to YES. + +CHM_INDEX_ENCODING = + +# The BINARY_TOC flag controls whether a binary table of contents is generated +# (YES) or a normal table of contents (NO) in the .chm file. Furthermore it +# enables the Previous and Next buttons. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTMLHELP is set to YES. + +BINARY_TOC = NO + +# The TOC_EXPAND flag can be set to YES to add extra items for group members to +# the table of contents of the HTML help documentation and to the tree view. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTMLHELP is set to YES. + +TOC_EXPAND = NO + +# If the GENERATE_QHP tag is set to YES and both QHP_NAMESPACE and +# QHP_VIRTUAL_FOLDER are set, an additional index file will be generated that +# can be used as input for Qt's qhelpgenerator to generate a Qt Compressed Help +# (.qch) of the generated HTML documentation. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +GENERATE_QHP = NO + +# If the QHG_LOCATION tag is specified, the QCH_FILE tag can be used to specify +# the file name of the resulting .qch file. The path specified is relative to +# the HTML output folder. +# This tag requires that the tag GENERATE_QHP is set to YES. + +QCH_FILE = + +# The QHP_NAMESPACE tag specifies the namespace to use when generating Qt Help +# Project output. For more information please see Qt Help Project / Namespace +# (see: http://qt-project.org/doc/qt-4.8/qthelpproject.html#namespace). +# The default value is: org.doxygen.Project. +# This tag requires that the tag GENERATE_QHP is set to YES. + +QHP_NAMESPACE = org.doxygen.Project + +# The QHP_VIRTUAL_FOLDER tag specifies the namespace to use when generating Qt +# Help Project output. For more information please see Qt Help Project / Virtual +# Folders (see: http://qt-project.org/doc/qt-4.8/qthelpproject.html#virtual- +# folders). +# The default value is: doc. +# This tag requires that the tag GENERATE_QHP is set to YES. + +QHP_VIRTUAL_FOLDER = doc + +# If the QHP_CUST_FILTER_NAME tag is set, it specifies the name of a custom +# filter to add. For more information please see Qt Help Project / Custom +# Filters (see: http://qt-project.org/doc/qt-4.8/qthelpproject.html#custom- +# filters). +# This tag requires that the tag GENERATE_QHP is set to YES. + +QHP_CUST_FILTER_NAME = + +# The QHP_CUST_FILTER_ATTRS tag specifies the list of the attributes of the +# custom filter to add. For more information please see Qt Help Project / Custom +# Filters (see: http://qt-project.org/doc/qt-4.8/qthelpproject.html#custom- +# filters). +# This tag requires that the tag GENERATE_QHP is set to YES. + +QHP_CUST_FILTER_ATTRS = + +# The QHP_SECT_FILTER_ATTRS tag specifies the list of the attributes this +# project's filter section matches. Qt Help Project / Filter Attributes (see: +# http://qt-project.org/doc/qt-4.8/qthelpproject.html#filter-attributes). +# This tag requires that the tag GENERATE_QHP is set to YES. + +QHP_SECT_FILTER_ATTRS = + +# The QHG_LOCATION tag can be used to specify the location of Qt's +# qhelpgenerator. If non-empty doxygen will try to run qhelpgenerator on the +# generated .qhp file. +# This tag requires that the tag GENERATE_QHP is set to YES. + +QHG_LOCATION = + +# If the GENERATE_ECLIPSEHELP tag is set to YES, additional index files will be +# generated, together with the HTML files, they form an Eclipse help plugin. To +# install this plugin and make it available under the help contents menu in +# Eclipse, the contents of the directory containing the HTML and XML files needs +# to be copied into the plugins directory of eclipse. The name of the directory +# within the plugins directory should be the same as the ECLIPSE_DOC_ID value. +# After copying Eclipse needs to be restarted before the help appears. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +GENERATE_ECLIPSEHELP = NO + +# A unique identifier for the Eclipse help plugin. When installing the plugin +# the directory name containing the HTML and XML files should also have this +# name. Each documentation set should have its own identifier. +# The default value is: org.doxygen.Project. +# This tag requires that the tag GENERATE_ECLIPSEHELP is set to YES. + +ECLIPSE_DOC_ID = org.doxygen.Project + +# If you want full control over the layout of the generated HTML pages it might +# be necessary to disable the index and replace it with your own. The +# DISABLE_INDEX tag can be used to turn on/off the condensed index (tabs) at top +# of each HTML page. A value of NO enables the index and the value YES disables +# it. Since the tabs in the index contain the same information as the navigation +# tree, you can set this option to YES if you also set GENERATE_TREEVIEW to YES. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +DISABLE_INDEX = NO + +# The GENERATE_TREEVIEW tag is used to specify whether a tree-like index +# structure should be generated to display hierarchical information. If the tag +# value is set to YES, a side panel will be generated containing a tree-like +# index structure (just like the one that is generated for HTML Help). For this +# to work a browser that supports JavaScript, DHTML, CSS and frames is required +# (i.e. any modern browser). Windows users are probably better off using the +# HTML help feature. Via custom style sheets (see HTML_EXTRA_STYLESHEET) one can +# further fine-tune the look of the index. As an example, the default style +# sheet generated by doxygen has an example that shows how to put an image at +# the root of the tree instead of the PROJECT_NAME. Since the tree basically has +# the same information as the tab index, you could consider setting +# DISABLE_INDEX to YES when enabling this option. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +GENERATE_TREEVIEW = NO + +# The ENUM_VALUES_PER_LINE tag can be used to set the number of enum values that +# doxygen will group on one line in the generated HTML documentation. +# +# Note that a value of 0 will completely suppress the enum values from appearing +# in the overview section. +# Minimum value: 0, maximum value: 20, default value: 4. +# This tag requires that the tag GENERATE_HTML is set to YES. + +ENUM_VALUES_PER_LINE = 1 + +# If the treeview is enabled (see GENERATE_TREEVIEW) then this tag can be used +# to set the initial width (in pixels) of the frame in which the tree is shown. +# Minimum value: 0, maximum value: 1500, default value: 250. +# This tag requires that the tag GENERATE_HTML is set to YES. + +TREEVIEW_WIDTH = 250 + +# If the EXT_LINKS_IN_WINDOW option is set to YES, doxygen will open links to +# external symbols imported via tag files in a separate window. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +EXT_LINKS_IN_WINDOW = NO + +#--------------------------------------------------------------------------- +# Configuration options related to the man page output +#--------------------------------------------------------------------------- + +GENERATE_MAN = YES +MAN_EXTENSION = .3 + +#--------------------------------------------------------------------------- +# Configuration options related to the preprocessor +#--------------------------------------------------------------------------- + +# If the ENABLE_PREPROCESSING tag is set to YES, doxygen will evaluate all +# C-preprocessor directives found in the sources and include files. +# The default value is: YES. + +ENABLE_PREPROCESSING = YES + +# If the MACRO_EXPANSION tag is set to YES, doxygen will expand all macro names +# in the source code. If set to NO, only conditional compilation will be +# performed. Macro expansion can be done in a controlled way by setting +# EXPAND_ONLY_PREDEF to YES. +# The default value is: NO. +# This tag requires that the tag ENABLE_PREPROCESSING is set to YES. + +MACRO_EXPANSION = YES + +# If the EXPAND_ONLY_PREDEF and MACRO_EXPANSION tags are both set to YES then +# the macro expansion is limited to the macros specified with the PREDEFINED and +# EXPAND_AS_DEFINED tags. +# The default value is: NO. +# This tag requires that the tag ENABLE_PREPROCESSING is set to YES. + +EXPAND_ONLY_PREDEF = NO + +# If the SEARCH_INCLUDES tag is set to YES, the include files in the +# INCLUDE_PATH will be searched if a #include is found. +# The default value is: YES. +# This tag requires that the tag ENABLE_PREPROCESSING is set to YES. + +SEARCH_INCLUDES = YES + +# The INCLUDE_PATH tag can be used to specify one or more directories that +# contain include files that are not input files but should be processed by the +# preprocessor. +# This tag requires that the tag SEARCH_INCLUDES is set to YES. + +INCLUDE_PATH = + +# You can use the INCLUDE_FILE_PATTERNS tag to specify one or more wildcard +# patterns (like *.h and *.hpp) to filter out the header-files in the +# directories. If left blank, the patterns specified with FILE_PATTERNS will be +# used. +# This tag requires that the tag ENABLE_PREPROCESSING is set to YES. + +INCLUDE_FILE_PATTERNS = + +# The PREDEFINED tag can be used to specify one or more macro names that are +# defined before the preprocessor is started (similar to the -D option of e.g. +# gcc). The argument of the tag is a list of macros of the form: name or +# name=definition (no spaces). If the definition and the "=" are omitted, "=1" +# is assumed. To prevent a macro definition from being undefined via #undef or +# recursively expanded use the := operator instead of the = operator. +# This tag requires that the tag ENABLE_PREPROCESSING is set to YES. + +PREDEFINED = + +# If the MACRO_EXPANSION and EXPAND_ONLY_PREDEF tags are set to YES then this +# tag can be used to specify a list of macro names that should be expanded. The +# macro definition that is found in the sources will be used. Use the PREDEFINED +# tag if you want to use a different macro definition that overrules the +# definition found in the source code. +# This tag requires that the tag ENABLE_PREPROCESSING is set to YES. + +EXPAND_AS_DEFINED = + +# If the SKIP_FUNCTION_MACROS tag is set to YES then doxygen's preprocessor will +# remove all references to function-like macros that are alone on a line, have +# an all uppercase name, and do not end with a semicolon. Such function macros +# are typically used for boiler-plate code, and will confuse the parser if not +# removed. +# The default value is: YES. +# This tag requires that the tag ENABLE_PREPROCESSING is set to YES. + +SKIP_FUNCTION_MACROS = YES + +#--------------------------------------------------------------------------- +# Configuration options related to external references +#--------------------------------------------------------------------------- + +# The TAGFILES tag can be used to specify one or more tag files. For each tag +# file the location of the external documentation should be added. The format of +# a tag file without this location is as follows: +# TAGFILES = file1 file2 ... +# Adding location for the tag files is done as follows: +# TAGFILES = file1=loc1 "file2 = loc2" ... +# where loc1 and loc2 can be relative or absolute paths or URLs. See the +# section "Linking to external documentation" for more information about the use +# of tag files. +# Note: Each tag file must have a unique name (where the name does NOT include +# the path). If a tag file is not located in the directory in which doxygen is +# run, you must also specify the path to the tagfile here. + +TAGFILES = + +# When a file name is specified after GENERATE_TAGFILE, doxygen will create a +# tag file that is based on the input files it reads. See section "Linking to +# external documentation" for more information about the usage of tag files. + +GENERATE_TAGFILE = + +# If the ALLEXTERNALS tag is set to YES, all external class will be listed in +# the class index. If set to NO, only the inherited external classes will be +# listed. +# The default value is: NO. + +ALLEXTERNALS = NO + +# If the EXTERNAL_GROUPS tag is set to YES, all external groups will be listed +# in the modules index. If set to NO, only the current project's groups will be +# listed. +# The default value is: YES. + +EXTERNAL_GROUPS = YES + +# If the EXTERNAL_PAGES tag is set to YES, all external pages will be listed in +# the related pages index. If set to NO, only the current project's pages will +# be listed. +# The default value is: YES. + +EXTERNAL_PAGES = YES diff --git a/utf8proc.c b/utf8proc.c index 6df92c2..b0c68e7 100644 --- a/utf8proc.c +++ b/utf8proc.c @@ -234,7 +234,7 @@ DLLEXPORT int utf8proc_charwidth(int32_t c) { return utf8proc_get_property(c)->charwidth; } -DLLEXPORT int utf8proc_category(int32_t c) { +DLLEXPORT utf8proc_category_t utf8proc_category(int32_t c) { return utf8proc_get_property(c)->category; } @@ -247,7 +247,7 @@ DLLEXPORT const char *utf8proc_category_string(int32_t c) { return utf8proc_decompose_char((replacement_uc), dst, bufsize, \ options & ~UTF8PROC_LUMP, last_boundclass) -DLLEXPORT ssize_t utf8proc_decompose_char(int32_t uc, int32_t *dst, ssize_t bufsize, int options, int *last_boundclass) { +DLLEXPORT ssize_t utf8proc_decompose_char(int32_t uc, int32_t *dst, ssize_t bufsize, utf8proc_option_t options, int *last_boundclass) { const utf8proc_property_t *property; utf8proc_propval_t category; int32_t hangul_sindex; @@ -353,7 +353,7 @@ DLLEXPORT ssize_t utf8proc_decompose_char(int32_t uc, int32_t *dst, ssize_t bufs DLLEXPORT ssize_t utf8proc_decompose( const uint8_t *str, ssize_t strlen, - int32_t *buffer, ssize_t bufsize, int options + int32_t *buffer, ssize_t bufsize, utf8proc_option_t options ) { /* strlen will be ignored, if UTF8PROC_NULLTERM is set in options */ ssize_t wpos = 0; @@ -413,7 +413,7 @@ DLLEXPORT ssize_t utf8proc_decompose( return wpos; } -DLLEXPORT ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, int options) { +DLLEXPORT ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, utf8proc_option_t options) { /* UTF8PROC_NULLTERM option will be ignored, 'length' is never ignored ASSERT: 'buffer' has one spare byte of free space at the end! */ if (options & (UTF8PROC_NLF2LS | UTF8PROC_NLF2PS | UTF8PROC_STRIPCC)) { @@ -529,7 +529,7 @@ DLLEXPORT ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, int options } DLLEXPORT ssize_t utf8proc_map( - const uint8_t *str, ssize_t strlen, uint8_t **dstptr, int options + const uint8_t *str, ssize_t strlen, uint8_t **dstptr, utf8proc_option_t options ) { int32_t *buffer; ssize_t result; diff --git a/utf8proc.h b/utf8proc.h index 82002e3..8c63a00 100644 --- a/utf8proc.h +++ b/utf8proc.h @@ -1,52 +1,55 @@ /* - * Copyright (c) 2009 Public Software Group e. V., Berlin, Germany + * Copyright (c) 2009 Public Software Group e. V., Berlin, Germany * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. */ -/* - * File name: utf8proc.h +/** + * @mainpage + * + * uf8proc is a mapping tool for UTF-8 strings with the following features: + * + * - decomposing and composing of strings + * - replacing compatibility characters with their equivalents + * - stripping of "default ignorable characters" + * like SOFT-HYPHEN or ZERO-WIDTH-SPACE + * - folding of certain characters for string comparison + * (e.g. HYPHEN U+2010 and MINUS U+2212 to ASCII "-") + * (see "LUMP" option) + * - optional rejection of strings containing non-assigned code points + * - stripping of control characters + * - stripping of character marks (accents, etc.) + * - transformation of LF, CRLF, CR and NEL to line-feed (LF) + * or to the unicode chararacters for paragraph separation (PS) + * or line separation (LS). + * - unicode case folding (for case insensitive string comparisons) + * - rejection of illegal UTF-8 data + * (i.e. UTF-8 encoded UTF-16 surrogates) + * - support for korean hangul characters + * + * Unicode Version 7.0.0 is supported. * - * Description: - * Header files for utf8proc, which is a mapping tool for UTF-8 strings - * with following features: - * - decomposing and composing of strings - * - replacing compatibility characters with their equivalents - * - stripping of "default ignorable characters" - * like SOFT-HYPHEN or ZERO-WIDTH-SPACE - * - folding of certain characters for string comparison - * (e.g. HYPHEN U+2010 and MINUS U+2212 to ASCII "-") - * (see "LUMP" option) - * - optional rejection of strings containing non-assigned code points - * - stripping of control characters - * - stripping of character marks (accents, etc.) - * - transformation of LF, CRLF, CR and NEL to line-feed (LF) - * or to the unicode chararacters for paragraph separation (PS) - * or line separation (LS). - * - unicode case folding (for case insensitive string comparisons) - * - rejection of illegal UTF-8 data - * (i.e. UTF-8 encoded UTF-16 surrogates) - * - support for korean hangul characters - * Unicode Version 7.0.0 is supported. + * See @ref utf8proc.h for the API. */ +/** @file */ #ifndef UTF8PROC_H #define UTF8PROC_H @@ -95,79 +98,111 @@ extern "C" { #define SSIZE_MAX ((size_t)SIZE_MAX/2) #endif -#define UTF8PROC_NULLTERM (1<<0) -#define UTF8PROC_STABLE (1<<1) -#define UTF8PROC_COMPAT (1<<2) -#define UTF8PROC_COMPOSE (1<<3) -#define UTF8PROC_DECOMPOSE (1<<4) -#define UTF8PROC_IGNORE (1<<5) -#define UTF8PROC_REJECTNA (1<<6) -#define UTF8PROC_NLF2LS (1<<7) -#define UTF8PROC_NLF2PS (1<<8) -#define UTF8PROC_NLF2LF (UTF8PROC_NLF2LS | UTF8PROC_NLF2PS) -#define UTF8PROC_STRIPCC (1<<9) -#define UTF8PROC_CASEFOLD (1<<10) -#define UTF8PROC_CHARBOUND (1<<11) -#define UTF8PROC_LUMP (1<<12) -#define UTF8PROC_STRIPMARK (1<<13) -/* - * Flags being regarded by several functions in the library: - * NULLTERM: The given UTF-8 input is NULL terminated. - * STABLE: Unicode Versioning Stability has to be respected. - * COMPAT: Compatibility decomposition - * (i.e. formatting information is lost) - * COMPOSE: Return a result with composed characters. - * DECOMPOSE: Return a result with decomposed characters. - * IGNORE: Strip "default ignorable characters" - * REJECTNA: Return an error, if the input contains unassigned - * code points. - * NLF2LS: Indicating that NLF-sequences (LF, CRLF, CR, NEL) are - * representing a line break, and should be converted to the - * unicode character for line separation (LS). - * NLF2PS: Indicating that NLF-sequences are representing a paragraph - * break, and should be converted to the unicode character for - * paragraph separation (PS). - * NLF2LF: Indicating that the meaning of NLF-sequences is unknown. - * STRIPCC: Strips and/or convers control characters. - * NLF-sequences are transformed into space, except if one of - * the NLF2LS/PS/LF options is given. - * HorizontalTab (HT) and FormFeed (FF) are treated as a - * NLF-sequence in this case. - * All other control characters are simply removed. - * CASEFOLD: Performs unicode case folding, to be able to do a - * case-insensitive string comparison. - * CHARBOUND: Inserts 0xFF bytes at the beginning of each sequence which - * is representing a single grapheme cluster (see UAX#29). - * LUMP: Lumps certain characters together - * (e.g. HYPHEN U+2010 and MINUS U+2212 to ASCII "-"). - * (See lump.md for details.) - * If NLF2LF is set, this includes a transformation of - * paragraph and line separators to ASCII line-feed (LF). - * STRIPMARK: Strips all character markings - * (non-spacing, spacing and enclosing) (i.e. accents) - * NOTE: this option works only with COMPOSE or DECOMPOSE +/** + * Option flags used by several functions in the library. */ - +typedef enum { + /** The given UTF-8 input is NULL terminated. */ + UTF8PROC_NULLTERM = (1<<0), + /** Unicode Versioning Stability has to be respected. */ + UTF8PROC_STABLE = (1<<1), + /** Compatibility decomposition (i.e. formatting information is lost). */ + UTF8PROC_COMPAT = (1<<2), + /** Return a result with decomposed characters. */ + UTF8PROC_COMPOSE = (1<<3), + /** Return a result with decomposed characters. */ + UTF8PROC_DECOMPOSE = (1<<4), + /** Strip "default ignorable characters". */ + UTF8PROC_IGNORE = (1<<5), + /** Return an error, if the input contains unassigned code points. */ + UTF8PROC_REJECTNA = (1<<6), + /** + * Indicating that NLF-sequences (LF, CRLF, CR, NEL) are representing a + * line break, and should be converted to the codepoint for line + * separation (LS). + */ + UTF8PROC_NLF2LS = (1<<7), + /** + * Indicating that NLF-sequences are representing a paragraph break, and + * should be converted to the codepoint for paragraph separation + * (PS). + */ + UTF8PROC_NLF2PS = (1<<8), + /** Indicating that the meaning of NLF-sequences is unknown. */ + UTF8PROC_NLF2LF = (UTF8PROC_NLF2LS | UTF8PROC_NLF2PS), + /** Strips and/or convers control characters. + * + * NLF-sequences are transformed into space, except if one of the + * NLF2LS/PS/LF options is given. HorizontalTab (HT) and FormFeed (FF) + * are treated as a NLF-sequence in this case. All other control + * characters are simply removed. + */ + UTF8PROC_STRIPCC = (1<<9), + /** + * Performs unicode case folding, to be able to do a case-insensitive + * string comparison. + */ + UTF8PROC_CASEFOLD = (1<<10), + /** + * Inserts 0xFF bytes at the beginning of each sequence which is + * representing a single grapheme cluster (see UAX#29). + */ + UTF8PROC_CHARBOUND = (1<<11), + /** Lumps certain characters together. + * + * E.g. HYPHEN U+2010 and MINUS U+2212 to ASCII "-". See lump.md for details. + * + * If NLF2LF is set, this includes a transformation of paragraph and + * line separators to ASCII line-feed (LF). + */ + UTF8PROC_LUMP = (1<<12), + /** Strips all character markings. + * + * This includes non-spacing, spacing and enclosing (i.e. accents). + * @note This option works only with @ref UTF8PROC_COMPOSE or + * @ref UTF8PROC_DECOMPOSE + */ + UTF8PROC_STRIPMARK = (1<<13), +} utf8proc_option_t; + +/** @name Error codes + * Error codes being returned by almost all functions. + */ +/** @{ */ +/** Memory could not be allocated. */ #define UTF8PROC_ERROR_NOMEM -1 +/** The given string is too long to be processed. */ #define UTF8PROC_ERROR_OVERFLOW -2 +/** The given string is not a legal UTF-8 string. */ #define UTF8PROC_ERROR_INVALIDUTF8 -3 +/** The @ref UTF8PROC_REJECTNA flag was set and an unassigned code point was found. */ #define UTF8PROC_ERROR_NOTASSIGNED -4 +/** Invalid options have been used. */ #define UTF8PROC_ERROR_INVALIDOPTS -5 -/* - * Error codes being returned by almost all functions: - * ERROR_NOMEM: Memory could not be allocated. - * ERROR_OVERFLOW: The given string is too long to be processed. - * ERROR_INVALIDUTF8: The given string is not a legal UTF-8 string. - * ERROR_NOTASSIGNED: The REJECTNA flag was set, - * and an unassigned code point was found. - * ERROR_INVALIDOPTS: Invalid options have been used. - */ +/** @} */ + +/* @name Types */ +/** Holds the value of a property. */ typedef int16_t utf8proc_propval_t; + +/** Struct containing information about a codepoint. */ typedef struct utf8proc_property_struct { + /** + * Unicode category. + * @see utf8proc_category_t. + */ utf8proc_propval_t category; utf8proc_propval_t combining_class; + /** + * Bidirectional class. + * @see utf8proc_bidi_class_t. + */ utf8proc_propval_t bidi_class; + /** + * @anchor Decomposition type. + * @see utf8proc_decomp_type_t. + */ utf8proc_propval_t decomp_type; const int32_t *decomp_mapping; const int32_t *casefold_mapping; @@ -178,256 +213,326 @@ typedef struct utf8proc_property_struct { int32_t comb2nd_index; unsigned bidi_mirrored:1; unsigned comp_exclusion:1; + /** + * Can this codepoint be ignored? + * + * Used by @ref utf8proc_decompose_char when @ref UTF8PROC_IGNORE is + * passed as an option. + */ unsigned ignorable:1; unsigned control_boundary:1; + /** + * Boundclass. + * @see utf8proc_boundclass_t. + */ unsigned boundclass:4; + /** The width of the codepoint. */ unsigned charwidth:2; } utf8proc_property_t; -#define UTF8PROC_CATEGORY_CN 0 -#define UTF8PROC_CATEGORY_LU 1 -#define UTF8PROC_CATEGORY_LL 2 -#define UTF8PROC_CATEGORY_LT 3 -#define UTF8PROC_CATEGORY_LM 4 -#define UTF8PROC_CATEGORY_LO 5 -#define UTF8PROC_CATEGORY_MN 6 -#define UTF8PROC_CATEGORY_MC 7 -#define UTF8PROC_CATEGORY_ME 8 -#define UTF8PROC_CATEGORY_ND 9 -#define UTF8PROC_CATEGORY_NL 10 -#define UTF8PROC_CATEGORY_NO 11 -#define UTF8PROC_CATEGORY_PC 12 -#define UTF8PROC_CATEGORY_PD 13 -#define UTF8PROC_CATEGORY_PS 14 -#define UTF8PROC_CATEGORY_PE 15 -#define UTF8PROC_CATEGORY_PI 16 -#define UTF8PROC_CATEGORY_PF 17 -#define UTF8PROC_CATEGORY_PO 18 -#define UTF8PROC_CATEGORY_SM 19 -#define UTF8PROC_CATEGORY_SC 20 -#define UTF8PROC_CATEGORY_SK 21 -#define UTF8PROC_CATEGORY_SO 22 -#define UTF8PROC_CATEGORY_ZS 23 -#define UTF8PROC_CATEGORY_ZL 24 -#define UTF8PROC_CATEGORY_ZP 25 -#define UTF8PROC_CATEGORY_CC 26 -#define UTF8PROC_CATEGORY_CF 27 -#define UTF8PROC_CATEGORY_CS 28 -#define UTF8PROC_CATEGORY_CO 29 -#define UTF8PROC_BIDI_CLASS_L 1 -#define UTF8PROC_BIDI_CLASS_LRE 2 -#define UTF8PROC_BIDI_CLASS_LRO 3 -#define UTF8PROC_BIDI_CLASS_R 4 -#define UTF8PROC_BIDI_CLASS_AL 5 -#define UTF8PROC_BIDI_CLASS_RLE 6 -#define UTF8PROC_BIDI_CLASS_RLO 7 -#define UTF8PROC_BIDI_CLASS_PDF 8 -#define UTF8PROC_BIDI_CLASS_EN 9 -#define UTF8PROC_BIDI_CLASS_ES 10 -#define UTF8PROC_BIDI_CLASS_ET 11 -#define UTF8PROC_BIDI_CLASS_AN 12 -#define UTF8PROC_BIDI_CLASS_CS 13 -#define UTF8PROC_BIDI_CLASS_NSM 14 -#define UTF8PROC_BIDI_CLASS_BN 15 -#define UTF8PROC_BIDI_CLASS_B 16 -#define UTF8PROC_BIDI_CLASS_S 17 -#define UTF8PROC_BIDI_CLASS_WS 18 -#define UTF8PROC_BIDI_CLASS_ON 19 -#define UTF8PROC_BIDI_CLASS_LRI 20 /* new in Unicode 6.3 */ -#define UTF8PROC_BIDI_CLASS_RLI 21 /* new in Unicode 6.3 */ -#define UTF8PROC_BIDI_CLASS_FSI 22 /* new in Unicode 6.3 */ -#define UTF8PROC_BIDI_CLASS_PDI 23 /* new in Unicode 6.3 */ -#define UTF8PROC_DECOMP_TYPE_FONT 1 -#define UTF8PROC_DECOMP_TYPE_NOBREAK 2 -#define UTF8PROC_DECOMP_TYPE_INITIAL 3 -#define UTF8PROC_DECOMP_TYPE_MEDIAL 4 -#define UTF8PROC_DECOMP_TYPE_FINAL 5 -#define UTF8PROC_DECOMP_TYPE_ISOLATED 6 -#define UTF8PROC_DECOMP_TYPE_CIRCLE 7 -#define UTF8PROC_DECOMP_TYPE_SUPER 8 -#define UTF8PROC_DECOMP_TYPE_SUB 9 -#define UTF8PROC_DECOMP_TYPE_VERTICAL 10 -#define UTF8PROC_DECOMP_TYPE_WIDE 11 -#define UTF8PROC_DECOMP_TYPE_NARROW 12 -#define UTF8PROC_DECOMP_TYPE_SMALL 13 -#define UTF8PROC_DECOMP_TYPE_SQUARE 14 -#define UTF8PROC_DECOMP_TYPE_FRACTION 15 -#define UTF8PROC_DECOMP_TYPE_COMPAT 16 - -/* values for boundclass property: */ -#define UTF8PROC_BOUNDCLASS_START 0 -#define UTF8PROC_BOUNDCLASS_OTHER 1 -#define UTF8PROC_BOUNDCLASS_CR 2 -#define UTF8PROC_BOUNDCLASS_LF 3 -#define UTF8PROC_BOUNDCLASS_CONTROL 4 -#define UTF8PROC_BOUNDCLASS_EXTEND 5 -#define UTF8PROC_BOUNDCLASS_L 6 -#define UTF8PROC_BOUNDCLASS_V 7 -#define UTF8PROC_BOUNDCLASS_T 8 -#define UTF8PROC_BOUNDCLASS_LV 9 -#define UTF8PROC_BOUNDCLASS_LVT 10 -#define UTF8PROC_BOUNDCLASS_REGIONAL_INDICATOR 11 -#define UTF8PROC_BOUNDCLASS_SPACINGMARK 12 - +/** Unicode categories. */ +typedef enum { + UTF8PROC_CATEGORY_CN = 0, /**< Other, not assigned */ + UTF8PROC_CATEGORY_LU = 1, /**< Letter, uppercase */ + UTF8PROC_CATEGORY_LL = 2, /**< Letter, lowercase */ + UTF8PROC_CATEGORY_LT = 3, /**< Letter, titlecase */ + UTF8PROC_CATEGORY_LM = 4, /**< Letter, modifier */ + UTF8PROC_CATEGORY_LO = 5, /**< Letter, other */ + UTF8PROC_CATEGORY_MN = 6, /**< Mark, nonspacing */ + UTF8PROC_CATEGORY_MC = 7, /**< Mark, spacing combining */ + UTF8PROC_CATEGORY_ME = 8, /**< Mark, enclosing */ + UTF8PROC_CATEGORY_ND = 9, /**< Number, decimal digit */ + UTF8PROC_CATEGORY_NL = 10, /**< Number, letter */ + UTF8PROC_CATEGORY_NO = 11, /**< Number, other */ + UTF8PROC_CATEGORY_PC = 12, /**< Punctuation, connector */ + UTF8PROC_CATEGORY_PD = 13, /**< Punctuation, dash */ + UTF8PROC_CATEGORY_PS = 14, /**< Punctuation, open */ + UTF8PROC_CATEGORY_PE = 15, /**< Punctuation, close */ + UTF8PROC_CATEGORY_PI = 16, /**< Punctuation, initial quote */ + UTF8PROC_CATEGORY_PF = 17, /**< Punctuation, final quote */ + UTF8PROC_CATEGORY_PO = 18, /**< Punctuation, other */ + UTF8PROC_CATEGORY_SM = 19, /**< Symbol, math */ + UTF8PROC_CATEGORY_SC = 20, /**< Symbol, currency */ + UTF8PROC_CATEGORY_SK = 21, /**< Symbol, modifier */ + UTF8PROC_CATEGORY_SO = 22, /**< Symbol, other */ + UTF8PROC_CATEGORY_ZS = 23, /**< Separator, space */ + UTF8PROC_CATEGORY_ZL = 24, /**< Separator, line */ + UTF8PROC_CATEGORY_ZP = 25, /**< Separator, paragraph */ + UTF8PROC_CATEGORY_CC = 26, /**< Other, control */ + UTF8PROC_CATEGORY_CF = 27, /**< Other, format */ + UTF8PROC_CATEGORY_CS = 28, /**< Other, surrogate */ + UTF8PROC_CATEGORY_CO = 29, /**< Other, private use */ +} utf8proc_category_t; + +/** Bidirectional character classes. */ +typedef enum { + UTF8PROC_BIDI_CLASS_L = 1, /**< Left-to-Right */ + UTF8PROC_BIDI_CLASS_LRE = 2, /**< Left-to-Right Embedding */ + UTF8PROC_BIDI_CLASS_LRO = 3, /**< Left-to-Right Override */ + UTF8PROC_BIDI_CLASS_R = 4, /**< Right-to-Left */ + UTF8PROC_BIDI_CLASS_AL = 5, /**< Right-to-Left Arabic */ + UTF8PROC_BIDI_CLASS_RLE = 6, /**< Right-to-Left Embedding */ + UTF8PROC_BIDI_CLASS_RLO = 7, /**< Right-to-Left Override */ + UTF8PROC_BIDI_CLASS_PDF = 8, /**< Pop Directional Format */ + UTF8PROC_BIDI_CLASS_EN = 9, /**< European Number */ + UTF8PROC_BIDI_CLASS_ES = 10, /**< European Separator */ + UTF8PROC_BIDI_CLASS_ET = 11, /**< European Number Terminator */ + UTF8PROC_BIDI_CLASS_AN = 12, /**< Arabic Number */ + UTF8PROC_BIDI_CLASS_CS = 13, /**< Common Number Separator */ + UTF8PROC_BIDI_CLASS_NSM = 14, /**< Nonspacing Mark */ + UTF8PROC_BIDI_CLASS_BN = 15, /**< Boundary Neutral */ + UTF8PROC_BIDI_CLASS_B = 16, /**< Paragraph Separator */ + UTF8PROC_BIDI_CLASS_S = 17, /**< Segment Separator */ + UTF8PROC_BIDI_CLASS_WS = 18, /**< Whitespace */ + UTF8PROC_BIDI_CLASS_ON = 19, /**< Other Neutrals */ + UTF8PROC_BIDI_CLASS_LRI = 20, /**< Left-to-Right Isolate */ + UTF8PROC_BIDI_CLASS_RLI = 21, /**< Right-to-Left Isolate */ + UTF8PROC_BIDI_CLASS_FSI = 22, /**< First Strong Isolate */ + UTF8PROC_BIDI_CLASS_PDI = 23, /**< Pop Directional Isolate */ +} utf8proc_bidi_class_t; + +/** Decomposition type. */ +typedef enum { + UTF8PROC_DECOMP_TYPE_FONT = 1, /**< Font */ + UTF8PROC_DECOMP_TYPE_NOBREAK = 2, /**< Nobreak */ + UTF8PROC_DECOMP_TYPE_INITIAL = 3, /**< Initial */ + UTF8PROC_DECOMP_TYPE_MEDIAL = 4, /**< Medial */ + UTF8PROC_DECOMP_TYPE_FINAL = 5, /**< Final */ + UTF8PROC_DECOMP_TYPE_ISOLATED = 6, /**< Isolated */ + UTF8PROC_DECOMP_TYPE_CIRCLE = 7, /**< Circle */ + UTF8PROC_DECOMP_TYPE_SUPER = 8, /**< Super */ + UTF8PROC_DECOMP_TYPE_SUB = 9, /**< Sub */ + UTF8PROC_DECOMP_TYPE_VERTICAL = 10, /**< Vertical */ + UTF8PROC_DECOMP_TYPE_WIDE = 11, /**< Wide */ + UTF8PROC_DECOMP_TYPE_NARROW = 12, /**< Narrow */ + UTF8PROC_DECOMP_TYPE_SMALL = 13, /**< Small */ + UTF8PROC_DECOMP_TYPE_SQUARE = 14, /**< Square */ + UTF8PROC_DECOMP_TYPE_FRACTION = 15, /**< Fraction */ + UTF8PROC_DECOMP_TYPE_COMPAT = 16, /**< Compat */ +} utf8proc_decomp_type_t; + +/** Boundclass property. */ +typedef enum { + UTF8PROC_BOUNDCLASS_START = 0, /**< Start */ + UTF8PROC_BOUNDCLASS_OTHER = 1, /**< Other */ + UTF8PROC_BOUNDCLASS_CR = 2, /**< Cr */ + UTF8PROC_BOUNDCLASS_LF = 3, /**< Lf */ + UTF8PROC_BOUNDCLASS_CONTROL = 4, /**< Control */ + UTF8PROC_BOUNDCLASS_EXTEND = 5, /**< Extend */ + UTF8PROC_BOUNDCLASS_L = 6, /**< L */ + UTF8PROC_BOUNDCLASS_V = 7, /**< V */ + UTF8PROC_BOUNDCLASS_T = 8, /**< T */ + UTF8PROC_BOUNDCLASS_LV = 9, /**< Lv */ + UTF8PROC_BOUNDCLASS_LVT = 10, /**< Lvt */ + UTF8PROC_BOUNDCLASS_REGIONAL_INDICATOR = 11, /**< Regional indicator */ + UTF8PROC_BOUNDCLASS_SPACINGMARK = 12, /**< Spacingmark */ +} utf8proc_boundclass_t; + +/** + * Array containing the byte lengths of a UTF-8 encoded codepoint based + * on the first byte. + */ DLLEXPORT extern const int8_t utf8proc_utf8class[256]; +/** + * Returns the version as a string. + */ DLLEXPORT const char *utf8proc_version(void); -DLLEXPORT const char *utf8proc_errmsg(ssize_t errcode); -/* - * Returns a static error string for the given error code. +/** + * Con + * Returns a static error string for the given error code. */ +DLLEXPORT const char *utf8proc_errmsg(ssize_t errcode); -DLLEXPORT ssize_t utf8proc_iterate(const uint8_t *str, ssize_t strlen, int32_t *dst); -/* - * Reads a single char from the UTF-8 sequence being pointed to by 'str'. - * The maximum number of bytes read is 'strlen', unless 'strlen' is - * negative. - * If a valid unicode char could be read, it is stored in the variable - * being pointed to by 'dst', otherwise that variable will be set to -1. - * In case of success the number of bytes read is returned, otherwise a - * negative error code is returned. +/** + * Reads a single codepoint from the UTF-8 sequence being pointed to by 'str'. + * The maximum number of bytes read is 'strlen', unless 'strlen' is + * negative (in which case up to 4 bytes are read). + * + * If a valid codepoint could be read, it is stored in the variable + * being pointed to by 'codepoint_ref', otherwise that variable will be set to -1. + * In case of success the number of bytes read is returned, otherwise a + * negative error code is returned. */ +DLLEXPORT ssize_t utf8proc_iterate(const uint8_t *str, ssize_t strlen, int32_t *codepoint_ref); -DLLEXPORT bool utf8proc_codepoint_valid(int32_t uc); -/* - * Returns 1, if the given unicode code-point is valid, otherwise 0. +/** + * Check if a codepoint is valid. + * + * @return 1, if the given codepoint is valid, otherwise 0. */ +DLLEXPORT bool utf8proc_codepoint_valid(int32_t codepoint); -DLLEXPORT ssize_t utf8proc_encode_char(int32_t uc, uint8_t *dst); -/* - * Encodes the unicode char with the code point 'uc' as an UTF-8 string in - * the byte array being pointed to by 'dst'. This array has to be at least - * 4 bytes long. - * In case of success the number of bytes written is returned, - * otherwise 0. - * This function does not check if 'uc' is a valid unicode code point. +/** + * Encodes the codepoint as an UTF-8 string in + * the byte array being pointed to by 'dst'. This array has to be at least + * 4 bytes long. + * + * In case of success the number of bytes written is returned, + * otherwise 0. + * + * This function does not check if the codepoint is a valid unicode code point. */ +DLLEXPORT ssize_t utf8proc_encode_char(int32_t codepoint, uint8_t *dst); -DLLEXPORT const utf8proc_property_t *utf8proc_get_property(int32_t uc); -/* - * Returns a pointer to a (constant) struct containing information about - * the unicode char with the given code point 'uc'. - * If the character is not existent a pointer to a special struct is - * returned, where 'category' is 0 (UTF8PROC_CATEGORY_CN). +/** + * Lookup the properties for a given codepoint. + * + * @param codepoint The codepoint. + * + * @returns + * A pointer to a (constant) struct containing information about + * the codepoint. + * @par + * If the codepoint is not existent a pointer to a special struct is + * returned, where `category` is 0 (@ref UTF8PROC_CATEGORY_CN). */ +DLLEXPORT const utf8proc_property_t *utf8proc_get_property(int32_t codepoint); +/** Decompose a codepoint into an array of codepoints. + * + * @param codepoint the codepoint. + * @param dst the destination buffer. + * @param bufsize the size of the destination buffer. + * @param options one or more of the following flags: + * - @ref UTF8PROC_REJECTNA - return an error `codepoint` is unassigned + * - @ref UTF8PROC_IGNORE - strip "default ignorable" codepoints + * - @ref UTF8PROC_CASEFOLD - apply Unicode casefolding + * - @ref UTF8PROC_COMPAT - replace certain codepoints with their + * compatibility decomposition + * - @ref UTF8PROC_CHARBOUND - insert 0xFF bytes before each grapheme cluster + * - @ref UTF8PROC_LUMP - lump certain different codepoints together + * - @ref UTF8PROC_STRIPMARK - remove all character marks + * @param last_boundclass + * This pointer has to point to an integer variable which is storing + * the last codepoint's boundary class, if the @ref UTF8PROC_CHARBOUND + * option is used. + * + * @return + * In case of success the number of codepoints written is returned, in case + * of an error, a negative error code is returned. + * @par + * If the number of written codepoints would be bigger than 'bufsize', the + * buffer (up to 'bufsize') has inpredictable data, and the needed + * buffer size is returned. + */ DLLEXPORT ssize_t utf8proc_decompose_char( - int32_t uc, int32_t *dst, ssize_t bufsize, - int options, int *last_boundclass + int32_t codepoint, int32_t *dst, ssize_t bufsize, + utf8proc_option_t options, int *last_boundclass ); -/* - * Writes a decomposition of the unicode char 'uc' into the array being - * pointed to by 'dst'. - * Following flags in the 'options' field are regarded: - * REJECTNA: an unassigned unicode code point leads to an error - * IGNORE: "default ignorable" chars are stripped - * CASEFOLD: unicode casefolding is applied - * COMPAT: replace certain characters with their - * compatibility decomposition - * CHARBOUND: Inserts 0xFF bytes before each grapheme cluster - * LUMP: lumps certain different characters together - * STRIPMARK: removes all character marks - * The pointer 'last_boundclass' has to point to an integer variable which - * is storing the last character boundary class, if the CHARBOUND option - * is used. - * In case of success the number of chars written is returned, - * in case of an error, a negative error code is returned. - * If the number of written chars would be bigger than 'bufsize', - * the buffer (up to 'bufsize') has inpredictable data, and the needed - * buffer size is returned. - */ +/** + * Does the same as 'utf8proc_decompose_char', but acts on a whole UTF-8 + * string, and orders the decomposed sequences correctly. + * + * If the @ref UTF8PROC_NULLTERM flag in 'options' is set, processing will be stopped, + * when a NULL byte is encounted, otherwise 'strlen' bytes are processed. + * The result in form of unicode code points is written into the buffer + * being pointed to by 'buffer', having the length of 'bufsize' entries. + * In case of success the number of codepoints written is returned, + * in case of an error, a negative error code is returned. + * + * If the number of written codepoints would be bigger than 'bufsize', + * the buffer (up to 'bufsize') has inpredictable data, and the needed + * buffer size is returned. + */ DLLEXPORT ssize_t utf8proc_decompose( const uint8_t *str, ssize_t strlen, - int32_t *buffer, ssize_t bufsize, int options + int32_t *buffer, ssize_t bufsize, utf8proc_option_t options ); -/* - * Does the same as 'utf8proc_decompose_char', but acts on a whole UTF-8 - * string, and orders the decomposed sequences correctly. - * If the NULLTERM flag in 'options' is set, processing will be stopped, - * when a NULL byte is encounted, otherwise 'strlen' bytes are processed. - * The result in form of unicode code points is written into the buffer - * being pointed to by 'buffer', having the length of 'bufsize' entries. - * In case of success the number of chars written is returned, - * in case of an error, a negative error code is returned. - * If the number of written chars would be bigger than 'bufsize', - * the buffer (up to 'bufsize') has inpredictable data, and the needed - * buffer size is returned. - */ -DLLEXPORT ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, int options); -/* - * Reencodes the sequence of unicode characters given by the pointer - * 'buffer' and 'length' as UTF-8. - * The result is stored in the same memory area where the data is read. - * Following flags in the 'options' field are regarded: - * NLF2LS: converts LF, CRLF, CR and NEL into LS - * NLF2PS: converts LF, CRLF, CR and NEL into PS - * NLF2LF: converts LF, CRLF, CR and NEL into LF - * STRIPCC: strips or converts all non-affected control characters - * COMPOSE: tries to combine decomposed characters into composite - * characters - * STABLE: prohibits combining characters which would violate - * the unicode versioning stability - * In case of success the length of the resulting UTF-8 string is - * returned, otherwise a negative error code is returned. - * WARNING: The amount of free space being pointed to by 'buffer', has to - * exceed the amount of the input data by one byte, and the - * entries of the array pointed to by 'str' have to be in the - * range of 0x0000 to 0x10FFFF, otherwise the program might - * crash! +/** + * Reencodes the sequence of codepoints given by the pointer + * 'buffer' and 'length' as UTF-8. + * + * The result is stored in the same memory area where the data is read. + * + * @param buffer the (native-endian UTF-32) unicode codepoints to re-encode. + * @param length the length (in codepoints) of the buffer. + * @param options one or more of the following flags: + * - @ref UTF8PROC_NLF2LS - convert LF, CRLF, CR and NEL into LS + * - @ref UTF8PROC_NLF2PS - convert LF, CRLF, CR and NEL into PS + * - @ref UTF8PROC_NLF2LF - convert LF, CRLF, CR and NEL into LF + * - @ref UTF8PROC_STRIPCC - strip or convert all non-affected control characters + * - @ref UTF8PROC_COMPOSE - try to combine decomposed codepoints into composite + * codepoints + * - @ref UTF8PROC_STABLE - prohibit combining characters which would violate + * the unicode versioning stability + * + * @return + * In case of success the length of the resulting UTF-8 string is + * returned, otherwise a negative error code is returned. + * + * @warning The amount of free space being pointed to by 'buffer', has to + * exceed the amount of the input data by one byte, and the + * entries of the array pointed to by 'str' have to be in the + * range of 0x0000 to 0x10FFFF, otherwise the program might + * crash! */ +DLLEXPORT ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, utf8proc_option_t options); -DLLEXPORT bool utf8proc_grapheme_break(int32_t c1, int32_t c2); -/* - * Given a pair of consecutive codepoints (c1,c2), return whether a grapheme break is +/** + * Given a pair of consecutive codepoints, return whether a grapheme break is * permitted between them (as defined by the extended grapheme clusters in UAX#29). */ +DLLEXPORT bool utf8proc_grapheme_break(int32_t codepoint1, int32_t codepoint2); + +/** + * Given a codepoint, return a character width analogous to wcwidth(codepoint), + * except that a width of 0 is returned for non-printable codepoints + * instead of -1 as in wcwidth. + * + * @note + * If you want to check for particular types of non-printable characters, + * (analogous to isprint or iscntrl), use @ref utf8proc_category. */ +DLLEXPORT int utf8proc_charwidth(int32_t codepoint); + +/** + * Return the Unicode category for the codepoint (one of the + * @ref utf8proc_category_t constants.) + */ +DLLEXPORT utf8proc_category_t utf8proc_category(int32_t codepoint); -DLLEXPORT int utf8proc_charwidth(int32_t c); -/* Given a codepoint c, return a character width analogous to wcwidth(c), - except that a width of 0 is returned for non-printable characters - instead of -1 as in wcwidth. - - If you want to check for particular types of non-printable characters, - (analogous to isprint or iscntrl), use utf8proc_category(c). */ - -DLLEXPORT int utf8proc_category(int32_t c); -/* Return the Unicode character category for c (one of the - UTF8PROC_CATEGORY_* constants.) */ - -DLLEXPORT const char *utf8proc_category_string(int32_t c); -/* Return the two-letter (nul-terminated) Unicode category string for - c (e.g. "Lu" or "Co"). */ +/** + * Return the two-letter (nul-terminated) Unicode category string for + * the codepoint (e.g. "Lu" or "Co"). + */ +DLLEXPORT const char *utf8proc_category_string(int32_t codepoint); +/** + * Maps the given UTF-8 string being pointed to by 'str' to a new UTF-8 + * string, which is allocated dynamically, and afterwards pointed to by + * the pointer being pointed to by 'dstptr'. + * + * If the @ref UTF8PROC_NULLTERM flag in the 'options' field is set, the length is + * determined by a NULL terminator, otherwise the parameter 'strlen' is + * evaluated to determine the string length, but in any case the result + * will be NULL terminated (though it might contain NULL characters + * before). Other flags in the 'options' field are passed to the + * functions defined above, and regarded as described. + * + * In case of success the length of the new string is returned, + * otherwise a negative error code is returned. + * + * *NOTICE*: The memory of the new UTF-8 string will have been allocated + * with 'malloc', and has theirfore to be freed with 'free'. + */ DLLEXPORT ssize_t utf8proc_map( - const uint8_t *str, ssize_t strlen, uint8_t **dstptr, int options + const uint8_t *str, ssize_t strlen, uint8_t **dstptr, utf8proc_option_t options ); -/* - * Maps the given UTF-8 string being pointed to by 'str' to a new UTF-8 - * string, which is allocated dynamically, and afterwards pointed to by - * the pointer being pointed to by 'dstptr'. - * If the NULLTERM flag in the 'options' field is set, the length is - * determined by a NULL terminator, otherwise the parameter 'strlen' is - * evaluated to determine the string length, but in any case the result - * will be NULL terminated (though it might contain NULL characters - * before). Other flags in the 'options' field are passed to the functions - * defined above, and regarded as described. - * In case of success the length of the new string is returned, - * otherwise a negative error code is returned. - * NOTICE: The memory of the new UTF-8 string will have been allocated with - * 'malloc', and has theirfore to be freed with 'free'. - */ +/** @name Normalized versions. + * + * Returns a pointer to newly allocated memory of a NFD, NFC, NFKD or NFKC + * normalized version of the null-terminated string 'str'. + */ +/** @{ */ DLLEXPORT uint8_t *utf8proc_NFD(const uint8_t *str); DLLEXPORT uint8_t *utf8proc_NFC(const uint8_t *str); DLLEXPORT uint8_t *utf8proc_NFKD(const uint8_t *str); DLLEXPORT uint8_t *utf8proc_NFKC(const uint8_t *str); -/* - * Returns a pointer to newly allocated memory of a NFD, NFC, NFKD or NFKC - * normalized version of the null-terminated string 'str'. - */ +/** @} */ #ifdef __cplusplus } -- cgit v1.2.3