emelie/tidy-html5
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

Merge branch 'pedromorgan-pedro'

Browse source
This commit is contained in:
Jim Derry 2015-03-08 11:52:17 +08:00
parent fd7b4f8589 6099f132e7
commit 6d84c5a6ec
7 changed files with 457 additions and 33 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

198
build/documentation/DoxygenLayout.xml Normal file
View file

@ -0,0 +1,198 @@
<doxygenlayout version="1.0">
<!-- Generated by doxygen 1.8.9.1 -->
<!-- Navigation index tabs for HTML output -->
<navindex>
<tab type="mainpage" visible="yes" title="Tidy Home"/>
<tab type="user" url="quickref.html" title="Quick Ref"/>
<tab type="pages" visible="yes" title="Pages" intro=""/>
<tab type="modules" visible="yes" title="" intro=""/>
<tab type="namespaces" visible="yes" title="">
<tab type="namespacelist" visible="yes" title="" intro=""/>
<tab type="namespacemembers" visible="yes" title="" intro=""/>
</tab>
<tab type="classes" visible="yes" title="">
<tab type="classlist" visible="yes" title="" intro=""/>
<tab type="classindex" visible="$ALPHABETICAL_INDEX" title=""/>
<tab type="hierarchy" visible="yes" title="" intro=""/>
<tab type="classmembers" visible="yes" title="" intro=""/>
</tab>
<tab type="files" visible="yes" title="">
<tab type="filelist" visible="yes" title="" intro=""/>
<tab type="globals" visible="yes" title="" intro=""/>
</tab>
<tab type="examples" visible="yes" title="" intro=""/>
<tab type="user" url="https://github.com/htacg/tidy-html5" title="github"/>
<tab type="user" url="http://www.htacg.org/" title="htacg.org"/>
<tab type="user" url="http://www.html-tidy.org/" title="html-tidy.org"/>
</navindex>
<!-- Layout definition for a class page -->
<class>
<briefdescription visible="yes"/>
<includes visible="$SHOW_INCLUDE_FILES"/>
<inheritancegraph visible="$CLASS_GRAPH"/>
<collaborationgraph visible="$COLLABORATION_GRAPH"/>
<memberdecl>
<nestedclasses visible="yes" title=""/>
<publictypes title=""/>
<services title=""/>
<interfaces title=""/>
<publicslots title=""/>
<signals title=""/>
<publicmethods title=""/>
<publicstaticmethods title=""/>
<publicattributes title=""/>
<publicstaticattributes title=""/>
<protectedtypes title=""/>
<protectedslots title=""/>
<protectedmethods title=""/>
<protectedstaticmethods title=""/>
<protectedattributes title=""/>
<protectedstaticattributes title=""/>
<packagetypes title=""/>
<packagemethods title=""/>
<packagestaticmethods title=""/>
<packageattributes title=""/>
<packagestaticattributes title=""/>
<properties title=""/>
<events title=""/>
<privatetypes title=""/>
<privateslots title=""/>
<privatemethods title=""/>
<privatestaticmethods title=""/>
<privateattributes title=""/>
<privatestaticattributes title=""/>
<friends title=""/>
<related title="" subtitle=""/>
<membergroups visible="yes"/>
</memberdecl>
<detaileddescription title=""/>
<memberdef>
<inlineclasses title=""/>
<typedefs title=""/>
<enums title=""/>
<services title=""/>
<interfaces title=""/>
<constructors title=""/>
<functions title=""/>
<related title=""/>
<variables title=""/>
<properties title=""/>
<events title=""/>
</memberdef>
<allmemberslink visible="yes"/>
<usedfiles visible="$SHOW_USED_FILES"/>
<authorsection visible="yes"/>
</class>
<!-- Layout definition for a namespace page -->
<namespace>
<briefdescription visible="yes"/>
<memberdecl>
<nestednamespaces visible="yes" title=""/>
<constantgroups visible="yes" title=""/>
<classes visible="yes" title=""/>
<typedefs title=""/>
<enums title=""/>
<functions title=""/>
<variables title=""/>
<membergroups visible="yes"/>
</memberdecl>
<detaileddescription title=""/>
<memberdef>
<inlineclasses title=""/>
<typedefs title=""/>
<enums title=""/>
<functions title=""/>
<variables title=""/>
</memberdef>
<authorsection visible="yes"/>
</namespace>
<!-- Layout definition for a file page -->
<file>
<briefdescription visible="yes"/>
<includes visible="$SHOW_INCLUDE_FILES"/>
<includegraph visible="$INCLUDE_GRAPH"/>
<includedbygraph visible="$INCLUDED_BY_GRAPH"/>
<sourcelink visible="yes"/>
<memberdecl>
<classes visible="yes" title=""/>
<namespaces visible="yes" title=""/>
<constantgroups visible="yes" title=""/>
<defines title=""/>
<typedefs title=""/>
<enums title=""/>
<functions title=""/>
<variables title=""/>
<membergroups visible="yes"/>
</memberdecl>
<detaileddescription title=""/>
<memberdef>
<inlineclasses title=""/>
<defines title=""/>
<typedefs title=""/>
<enums title=""/>
<functions title=""/>
<variables title=""/>
</memberdef>
<authorsection/>
</file>
<!-- Layout definition for a group page -->
<group>
<briefdescription visible="yes"/>
<groupgraph visible="$GROUP_GRAPHS"/>
<memberdecl>
<nestedgroups visible="yes" title=""/>
<dirs visible="yes" title=""/>
<files visible="yes" title=""/>
<namespaces visible="yes" title=""/>
<classes visible="yes" title=""/>
<defines title=""/>
<typedefs title=""/>
<enums title=""/>
<enumvalues title=""/>
<functions title=""/>
<variables title=""/>
<signals title=""/>
<publicslots title=""/>
<protectedslots title=""/>
<privateslots title=""/>
<events title=""/>
<properties title=""/>
<friends title=""/>
<membergroups visible="yes"/>
</memberdecl>
<detaileddescription title=""/>
<memberdef>
<pagedocs/>
<inlineclasses title=""/>
<defines title=""/>
<typedefs title=""/>
<enums title=""/>
<enumvalues title=""/>
<functions title=""/>
<variables title=""/>
<signals title=""/>
<publicslots title=""/>
<protectedslots title=""/>
<privateslots title=""/>
<events title=""/>
<properties title=""/>
<friends title=""/>
</memberdef>
<authorsection visible="yes"/>
</group>
<!-- Layout definition for a directory page -->
<directory>
<briefdescription visible="yes"/>
<directorygraph visible="yes"/>
<memberdecl>
<dirs visible="yes"/>
<files visible="yes"/>
</memberdecl>
<detaileddescription title=""/>
</directory>
</doxygenlayout>

4
build/documentation/README.md
View file

@ -1,4 +1,4 @@
# DOCUMENTATION HOW-TO # Documentation HOWTO
**HTML Tidy** provides several types of documentation to suit different purposes. This **HTML Tidy** provides several types of documentation to suit different purposes. This
document describes how to generate the following: document describes how to generate the following:
@ -92,7 +92,7 @@ but any XSLT processor of your choice should work, too.
- This examples uses the `xsltproc` command to transform `tidy-help.xml` using the - This examples uses the `xsltproc` command to transform `tidy-help.xml` using the
rules in the `tidy1.xsl` stylesheet, and output it to `tidy.1`. rules in the `tidy1.xsl` stylesheet, and output it to `tidy.1`.
Note that `tidy1.xls` includes the file `tidy-config.xml` as part of the stylesheet, \note Note that `tidy1.xls` includes the file `tidy-config.xml` as part of the stylesheet,
and so although it does not appear in the command invocation, it is indeed required. and so although it does not appear in the command invocation, it is indeed required.

17
build/documentation/build_docs.sh
View file

@ -9,6 +9,8 @@
TIDY_PATH="./tidy5" # Current directory. TIDY_PATH="./tidy5" # Current directory.
TIDY_VERSION=`cat ../../version.txt`
cat << HEREDOC cat << HEREDOC
@ -71,7 +73,7 @@ if [ "$BUILD_XSLT" -eq 1 ]; then
xsltproc "quickref.xsl" "tidy-config.xml" > "$OUTP_DIR/quickref.html" xsltproc "quickref.xsl" "tidy-config.xml" > "$OUTP_DIR/quickref.html"
# 'tidy.1' # 'tidy.1'
xsltproc "tidy1.xsl" "$tidy-help.xml" > "$OUTP_DIR/tidy.1" xsltproc "tidy1.xsl" "tidy-help.xml" > "$OUTP_DIR/tidy.1"
# Cleanup - Note: to avoid issues with the tidy1.xsl finding the tidy-config.xml # Cleanup - Note: to avoid issues with the tidy1.xsl finding the tidy-config.xml
# document, they are created and read from the source directory instead of temp. # document, they are created and read from the source directory instead of temp.
@ -104,7 +106,18 @@ hash doxygen 2>/dev/null || { echo "- doxygen not found. This script requires do
if [ "$BUILD_API" -eq 1 ]; then if [ "$BUILD_API" -eq 1 ]; then
echo "The following is doxygen's stderr output. It doesn't indicate errors with this script:\n" echo "The following is doxygen's stderr output. It doesn't indicate errors with this script:\n"
doxygen "$DOXY_CFG" > /dev/null
# echo the output of tidy5 --help so we can include
$TIDY_PATH -h > "./$OUTP_DIR/tidy5.cmd.txt"
## this lot
# - echos and catches outputs the doxygen config
# - overwrites some vars but appending some to config an end
# - which are then passed to doxygen as stdin (instead of the path to a config.file)
( cat "$DOXY_CFG"; \
echo "PROJECT_NUMBER=$TIDY_VERSION"; \
echo "HTML_EXTRA_FILES=$OUTP_DIR/quickref.html ./$OUTP_DIR/tidy5.cmd.txt"; ) \
| doxygen - > /dev/null
echo "\nTidyLib API documentation has been built." echo "\nTidyLib API documentation has been built."
else else
echo "* $OUTP_DIR/tidylib_api/ was skipped because not all dependencies were satisfied." echo "* $OUTP_DIR/tidylib_api/ was skipped because not all dependencies were satisfied."

44
build/documentation/doxygen.cfg
View file

@ -113,7 +113,7 @@ ABBREVIATE_BRIEF =
# Doxygen will generate a detailed section even if there is only a brief # Doxygen will generate a detailed section even if there is only a brief
# description. # description.
ALWAYS_DETAILED_SEC = NO ALWAYS_DETAILED_SEC = YES
# If the INLINE_INHERITED_MEMB tag is set to YES, doxygen will show all # 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 # inherited members of a class in the documentation of that class as if those
@ -158,7 +158,7 @@ SHORT_NAMES = NO
# comments will behave just like regular Qt-style comments # comments will behave just like regular Qt-style comments
# (thus requiring an explicit @brief command for a brief description.) # (thus requiring an explicit @brief command for a brief description.)
JAVADOC_AUTOBRIEF = NO JAVADOC_AUTOBRIEF = YES
# If the QT_AUTOBRIEF tag is set to YES then Doxygen will # If the QT_AUTOBRIEF tag is set to YES then Doxygen will
# interpret the first line (until the first dot) of a Qt-style # interpret the first line (until the first dot) of a Qt-style
@ -166,7 +166,7 @@ JAVADOC_AUTOBRIEF = NO
# will behave just like regular Qt-style comments (thus requiring # will behave just like regular Qt-style comments (thus requiring
# an explicit \brief command for a brief description.) # an explicit \brief command for a brief description.)
QT_AUTOBRIEF = NO QT_AUTOBRIEF = YES
# The MULTILINE_CPP_IS_BRIEF tag can be set to YES to make Doxygen # 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 /// # treat a multi-line C++ special comment block (i.e. a block of //! or ///
@ -174,7 +174,7 @@ QT_AUTOBRIEF = NO
# The new default is to treat a multi-line C++ comment block as a detailed # 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 behaviour instead. # description. Set this tag to YES if you prefer the old behaviour instead.
MULTILINE_CPP_IS_BRIEF = NO MULTILINE_CPP_IS_BRIEF = YES
# If the INHERIT_DOCS tag is set to YES (the default) then an undocumented # If the INHERIT_DOCS tag is set to YES (the default) then an undocumented
# member inherits the documentation from any documented member that it # member inherits the documentation from any documented member that it
@ -307,7 +307,7 @@ SUBGROUPING = YES
# @ingroup) instead of on a separate page (for HTML and Man pages) or # @ingroup) instead of on a separate page (for HTML and Man pages) or
# section (for LaTeX and RTF). # section (for LaTeX and RTF).
INLINE_GROUPED_CLASSES = NO INLINE_GROUPED_CLASSES = YES
# When the INLINE_SIMPLE_STRUCTS tag is set to YES, structs, classes, and # When the INLINE_SIMPLE_STRUCTS tag is set to YES, structs, classes, and
# unions with only public data fields will be shown inline in the documentation # unions with only public data fields will be shown inline in the documentation
@ -316,7 +316,7 @@ INLINE_GROUPED_CLASSES = NO
# structs, classes, and unions are shown on a separate page (for HTML and Man # structs, classes, and unions are shown on a separate page (for HTML and Man
# pages) or section (for LaTeX and RTF). # pages) or section (for LaTeX and RTF).
INLINE_SIMPLE_STRUCTS = NO INLINE_SIMPLE_STRUCTS = YES
# When TYPEDEF_HIDES_STRUCT is enabled, a typedef of a struct, union, or enum # When TYPEDEF_HIDES_STRUCT is enabled, a typedef of a struct, union, or enum
# is documented as struct, union, or enum with the name of the typedef. So # is documented as struct, union, or enum with the name of the typedef. So
@ -350,23 +350,23 @@ LOOKUP_CACHE_SIZE = 0
# Private class members and static file members will be hidden unless # Private class members and static file members will be hidden unless
# the EXTRACT_PRIVATE and EXTRACT_STATIC tags are set to YES # the EXTRACT_PRIVATE and EXTRACT_STATIC tags are set to YES
EXTRACT_ALL = NO EXTRACT_ALL = YES
# If the EXTRACT_PRIVATE tag is set to YES all private members of a class # If the EXTRACT_PRIVATE tag is set to YES all private members of a class
# will be included in the documentation. # will be included in the documentation.
EXTRACT_PRIVATE = NO EXTRACT_PRIVATE = YES
# If the EXTRACT_PACKAGE tag is set to YES, all members with package or # If the EXTRACT_PACKAGE tag is set to YES, all members with package or
# internal scope will be included in the documentation. # internal scope will be included in the documentation.
# The default value is: NO. # The default value is: NO.
EXTRACT_PACKAGE = NO EXTRACT_PACKAGE = YES
# If the EXTRACT_STATIC tag is set to YES all static members of a file # If the EXTRACT_STATIC tag is set to YES all static members of a file
# will be included in the documentation. # will be included in the documentation.
EXTRACT_STATIC = NO EXTRACT_STATIC = YES
# If the EXTRACT_LOCAL_CLASSES tag is set to YES classes (and structs) # If the EXTRACT_LOCAL_CLASSES tag is set to YES classes (and structs)
# defined locally in source files will be included in the documentation. # defined locally in source files will be included in the documentation.
@ -379,7 +379,7 @@ EXTRACT_LOCAL_CLASSES = YES
# the interface are included in the documentation. # the interface are included in the documentation.
# If set to NO (the default) only methods in the interface are included. # If set to NO (the default) only methods in the interface are included.
EXTRACT_LOCAL_METHODS = NO EXTRACT_LOCAL_METHODS = YES
# If this flag is set to YES, the members of anonymous namespaces will be # If this flag is set to YES, the members of anonymous namespaces will be
# extracted and appear in the documentation as a namespace called # extracted and appear in the documentation as a namespace called
@ -475,14 +475,14 @@ INLINE_INFO = YES
# alphabetically by member name. If set to NO the members will appear in # alphabetically by member name. If set to NO the members will appear in
# declaration order. # declaration order.
SORT_MEMBER_DOCS = NO SORT_MEMBER_DOCS = YES
# If the SORT_BRIEF_DOCS tag is set to YES then doxygen will sort the # If the SORT_BRIEF_DOCS tag is set to YES then doxygen will sort the
# brief documentation of file, namespace and class members alphabetically # brief documentation of file, namespace and class members alphabetically
# by member name. If set to NO (the default) the members will appear in # by member name. If set to NO (the default) the members will appear in
# declaration order. # declaration order.
SORT_BRIEF_DOCS = NO SORT_BRIEF_DOCS = YES
# If the SORT_MEMBERS_CTORS_1ST tag is set to YES then doxygen # 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 # will sort the (brief and detailed) documentation of class members so that
@ -498,7 +498,7 @@ SORT_MEMBERS_CTORS_1ST = NO
# hierarchy of group names into alphabetical order. If set to NO (the default) # hierarchy of group names into alphabetical order. If set to NO (the default)
# the group names will appear in their defined order. # the group names will appear in their defined order.
SORT_GROUP_NAMES = NO SORT_GROUP_NAMES = YES
# If the SORT_BY_SCOPE_NAME tag is set to YES, the class list will be # 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 # sorted by fully-qualified names, including namespaces. If set to
@ -508,7 +508,7 @@ SORT_GROUP_NAMES = NO
# Note: This option applies only to the class list, not to the # Note: This option applies only to the class list, not to the
# alphabetical list. # alphabetical list.
SORT_BY_SCOPE_NAME = NO SORT_BY_SCOPE_NAME = YES
# If the STRICT_PROTO_MATCHING option is enabled and doxygen fails to # 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 # do proper type resolution of all parameters of a function it will reject a
@ -594,7 +594,7 @@ FILE_VERSION_FILTER =
# You can optionally specify a file name after the option, if omitted # You can optionally specify a file name after the option, if omitted
# DoxygenLayout.xml will be used as the name of the layout file. # DoxygenLayout.xml will be used as the name of the layout file.
LAYOUT_FILE = LAYOUT_FILE = DoxygenLayout.xml
# The CITE_BIB_FILES tag can be used to specify one or more bib files # The CITE_BIB_FILES tag can be used to specify one or more bib files
# containing the references data. This must be a list of .bib files. The # containing the references data. This must be a list of .bib files. The
@ -665,7 +665,7 @@ WARN_LOGFILE =
# directories like "/usr/src/myproject". Separate the files or directories # directories like "/usr/src/myproject". Separate the files or directories
# with spaces. # with spaces.
INPUT = "../../include" INPUT = "../../include" "./"
# This tag can be used to specify the character encoding of the source files # This tag can be used to specify the character encoding of the source files
# that doxygen parses. Internally doxygen uses the UTF-8 encoding, which is # that doxygen parses. Internally doxygen uses the UTF-8 encoding, which is
@ -724,7 +724,7 @@ EXCLUDE_SYMBOLS =
# directories that contain example code fragments that are included (see # directories that contain example code fragments that are included (see
# the \include command). # the \include command).
EXAMPLE_PATH = EXAMPLE_PATH = "./" "./temp/"
# If the value of the EXAMPLE_PATH tag contains directories, you can use the # 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 # EXAMPLE_PATTERNS tag to specify one or more wildcard pattern (like *.cpp
@ -798,7 +798,7 @@ USE_MDFILE_AS_MAINPAGE =
# Note: To get rid of all source code in the generated output, make sure also # Note: To get rid of all source code in the generated output, make sure also
# VERBATIM_HEADERS is set to NO. # VERBATIM_HEADERS is set to NO.
SOURCE_BROWSER = NO SOURCE_BROWSER = YES
# Setting the INLINE_SOURCES tag to YES will include the body # Setting the INLINE_SOURCES tag to YES will include the body
# of functions and classes directly in the documentation. # of functions and classes directly in the documentation.
@ -978,7 +978,7 @@ HTML_COLORSTYLE_HUE = 220
# the colors in the HTML output. For a value of 0 the output will use # 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. # grayscales only. A value of 255 will produce the most vivid colors.
HTML_COLORSTYLE_SAT = 100 HTML_COLORSTYLE_SAT = 50
# The HTML_COLORSTYLE_GAMMA tag controls the gamma correction applied to # The HTML_COLORSTYLE_GAMMA tag controls the gamma correction applied to
# the luminance component of the colors in the HTML output. Values below # the luminance component of the colors in the HTML output. Values below
@ -987,7 +987,7 @@ HTML_COLORSTYLE_SAT = 100
# so 80 represents a gamma of 0.8, The value 220 represents a gamma of 2.2, # so 80 represents a gamma of 0.8, The value 220 represents a gamma of 2.2,
# and 100 does not change the gamma. # and 100 does not change the gamma.
HTML_COLORSTYLE_GAMMA = 80 HTML_COLORSTYLE_GAMMA = 100
# If the HTML_TIMESTAMP tag is set to YES then the footer of each generated HTML # 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 # page will contain the date and time when the page was generated. Setting
@ -1171,7 +1171,7 @@ ECLIPSE_DOC_ID = org.doxygen.Project
# top of each HTML page. The value NO (the default) enables the index and # top of each HTML page. The value NO (the default) enables the index and
# the value YES disables it. # the value YES disables it.
DISABLE_INDEX = YES DISABLE_INDEX = NO
# The GENERATE_TREEVIEW tag is used to specify whether a tree-like index # The GENERATE_TREEVIEW tag is used to specify whether a tree-like index
# structure should be generated to display hierarchical information. # structure should be generated to display hierarchical information.

49
build/documentation/example.1.c Normal file
View file

@ -0,0 +1,49 @@
#include <tidy.h>;
#include <buffio.h>;
#include <stdio.h>;
#include <errno.h>;
int main(int argc, char **argv )
{
const char* input = "<title>Hello</title><p>World!";
TidyBuffer output = {0};
TidyBuffer errbuf = {0};
int rc = -1;
Bool ok;
// Initialize "document"
TidyDoc tdoc = tidyCreate();
printf( "Tidying:\t%s\n", input );
// Convert to XHTML
ok = tidyOptSetBool( tdoc, TidyXhtmlOut, yes );
if ( ok )
rc = tidySetErrorBuffer( tdoc, &errbuf ); // Capture diagnostics
if ( rc >= 0 )
rc = tidyParseString( tdoc, input ); // Parse the input
if ( rc >= 0 )
rc = tidyCleanAndRepair( tdoc ); // Tidy it up!
if ( rc >= 0 )
rc = tidyRunDiagnostics( tdoc ); // Kvetch
if ( rc > 1 ) // If error, force output.
rc = ( tidyOptSetBool(tdoc, TidyForceOutput, yes) ? rc : -1 );
if ( rc >= 0 )
rc = tidySaveBuffer( tdoc, &output ); // Pretty Print
if ( rc >= 0 )
{
if ( rc > 0 )
printf( "\nDiagnostics:\n\n%s", errbuf.bp );
printf( "\nAnd here is the result:\n\n%s", output.bp );
}
else
printf( "A severe error (%d) occurred.\n", rc );
tidyBufFree( &output );
tidyBufFree( &errbuf );
tidyRelease( tdoc );
return rc;
}

164
build/documentation/tidy_docs.dox Normal file
View file

@ -0,0 +1,164 @@
/*!
\mainpage Tidy home
\note The repository <a href="https://github.com/htacg/tidy-html5">github.com/htacg/tidy-html5</a> and this documentation should be considered canonical for HTML Tidy as of 2015-January-15.
<h4>What is tidy ?</h4>
- \b `tidy`
- is a console application for Mac OS X, Linux, Windows, UNIX, and more.
- It corrects and cleans up HTML and XML documents by fixing markup errors and upgrading legacy code to modern standards.
- \b `tidylib`
- is a C static or dynamic library that developers can integrate into their applications
in order to bring all of Tidy’s power to your favorite tools.
- `tidylib` is used today in desktop applications, web servers, and more.
\section content Contents
- \ref tidy5_cmd
- \ref building_tidy
- \ref history
\page tidy5_cmd `tidy5` command
<pre>
\htmlinclude tidy5.cmd.txt
</pre>
\page TidyLib TidyLib
- \b TidyLib - is easy to integrate. Because of the near universal adoption of C linkage, a C interface may be called from a great number of programming languages.
- \b TidyLib - is designed to use opaque types in the public interface. This allows the application to just pass an integer around and the need to transform data types in different languages is minimized. As a results it’s straight-forward to write very thin library wrappers for C++, Pascal, and COM/ATL.
- \b TidyLib - eats its own dogfood. HTML Tidy links directly to TidyLib.
- \b TidyLib - is Thread Safe and Re-entrant. Because there are many uses for HTML Tidy - from content validation, content scraping, conversion to XHTML - it was important to make TidyLib run reasonably well within server applications as well as client side.
- \b TidyLib - uses adaptable I/O. As part of the larger integration strategy it was decided to fully abstract all I/O. This means a (relatively) clean separation between character encoding processing and shovelling bytes back and forth. Internally, the library reads from sources and writes to sinks. This abstraction is used for both markup and configuration “files”. Concrete implementations are provided for file and memory I/O, and new sources and sinks may be provided via the public interface.
\section example_hello Example
\include example.1.c
\page building_tidy Building Tidy
\section Prerequisites
- \b git - <a href="http://git-scm.com/book/en/v2/Getting-Started-Installing-Git">git-scm.com/book/en/v2/Getting-Started-Installing-Git</a>
- \b cmake - <a href="http://www.cmake.org/download/">cmake.org/download/</a>
- Appropriate build tools for the platform
CMake comes in two forms - command line and gui. Some installations only install one or the other, but sometimes both. The build
commands below are only for the command line use.
Also the actual build tools vary for each platform. But that is one of the great features of cmake, it can generate
variuous 'native' build files. Running cmake without any parameters will list the generators
available on that platform. For sure one of the common ones is "Unix Makefiles", which needs autotools
make installed, but many other generators are supported.
In windows cmake offers various versions of MSVC. Again below only the command line use of MSVC is shown, but the
tidy solution (*.sln) file can be loaded into the MSVC IDE, and the building done in there.
\section get_source Get the source code
Tidy’s sourcecode can be found at <a href="https://github.com/htacg/tidy-html5">github.com/htacg/tidy-html5</a>. There are sometimes
several branches, but in general `master` is the most recently updated version.
\note Note that as “cutting edge,” it may have bugs or other
unstable behavior. If you prefer a stable, officially released version, be sure to have a look
at Releases on the github page.
In general you can use the <b>Download ZIP</b> button on the github page to download the most recent version of a branch. If you prefer
Git then you can clone the repository to a working machine with:
\code{.sh}
git clone git@github.com:htacg/tidy-html5.git
\endcode
\section compile Compile
<h4>Enter the `build/cmake` directory</h4>
\code{.sh}
# *nix
cd {your-tidy-html5-directory}/build/cmake
# windows
cd {your-tidy-html5-directory}\build\cmake
\endcode
<h4>Configure the build</h4>
\code{.sh}
# *nix
cmake ../../ [-DCMAKE_INSTALL_PREFIX=/path/for/install]
# windows
cmake ..\..\
\endcode
By default cmake sets the install path to `/usr/local` in unix.
If you wanted the binary in say `/usr/bin` instead, then use `-DCMAKE_INSTALL_PREFIX=/usr`
On windows the default install is to `C:\Program Files\tidy5`, or `C:/Program Files (x86)/tidy5`, which is not very useful. After
the build the `tidy[n].exe` is in the `Release\` directory, and can be copied to any directory in your `PATH` environment variable, for global use.
If you need the tidy library built as a 'shared' (DLL) library, then in add the command `-DBUILD_SHARED_LIB:BOOL=ON`.
This option is `OFF` by default, so the static library is built and linked with the command line tool for convenience.
<h4>Compile</h4>
\code{.sh}
# *nix
make
# windows
cmake --build . --config Release
\endcode
<h4>Install</h4>
\code{.sh}
# *nix
[sudo] make install
# windows
cmake --build . --config Release --target INSTALL
\endcode
\page history History
- This repository originally transferred from w3c.github.com/tidy-html5.
- First moved to <a href="https://github.com/htacg/tidy-html5">Github</a> from <a href="http://tidy.sourceforge.net/">tidy.sourceforge.net</a>
<p><strong>HTML Tidy</strong> was created by the <a href="http://www.w3.org/">W3C’s</a> own <a href="http://www.w3.org/People/Raggett/">Dave Raggett</a> back in the
dawn of the Internet age. His original Internet page is still available and
gives a sense of the early history: <a href="http://www.w3.org/People/Raggett/tidy/">Clean up your Web pages with HTML TIDY</a>.</p>
<p>Satisfied with his work Dave passed the torch to a dedicated group of
maintainers at <a href="http://tidy.sourceforge.net/">tidy.sourceforge.net</a> where the important tasks of turning
<strong>Tidy</strong> into a C library and keeping up with developing standards was
performed.</p>
<p>W3C members took a renewed interest in <strong>Tidy</strong> in 2011 and forked the
project to <a href="https://github.com/w3c/tidy-html5">github</a> (now redirects to new maintainers), where it featured
compatibility with HTML5 via a <a href="https://lists.w3.org/Archives/Public/www-archive/2011Nov/0007.html">key contribution</a> from one of the SourceForge
key members.</p>
<p>In 2015 a group of concerned developers, users, and software integrators formed
<a href="http://www.htacg.org">HTACG</a> with the goal of revitalizing <strong>Tidy</strong>, which had fallen into a
non-maintained state. As a W3C Community Group, HTACG was deemed worthy by the
W3C, and W3C passed ownership of their project to HTACG, where it is currently
being developed and prepped for a new, stable, and modern release.</p>
<p>HTACG is also working diligently with the SourceForge maintainers in an effort
to harmonize <strong>HTML Tidy</strong> into a single, stable, solid release once again.</p>
*/

12
include/tidy.h
View file

@ -187,7 +187,7 @@ struct _TidyAllocatorVtbl {
/** An allocator. To create your own allocator, do something like /** An allocator. To create your own allocator, do something like
the following: the following:
\code
typedef struct _MyAllocator { typedef struct _MyAllocator {
TidyAllocator base; TidyAllocator base;
...other custom allocator state... ...other custom allocator state...
@ -213,7 +213,7 @@ struct _TidyAllocatorVtbl {
allocator.base.vtbl = &amp;MyAllocatorVtbl; allocator.base.vtbl = &amp;MyAllocatorVtbl;
...initialise allocator specific state... ...initialise allocator specific state...
doc = tidyCreateWithAllocator(&allocator); doc = tidyCreateWithAllocator(&allocator);
... \endcode
Although this looks slightly long winded, the advantage is that to create Although this looks slightly long winded, the advantage is that to create
a custom allocator you simply need to set the vtbl pointer correctly. a custom allocator you simply need to set the vtbl pointer correctly.
@ -261,10 +261,10 @@ TIDY_EXPORT Bool TIDY_CALL tidySetPanicCall( TidyPanic fpanic );
The following is a short example program. The following is a short example program.
<pre> <pre>
#include &lt;tidy.h&gt; \#include &lt;tidy.h&gt;
#include &lt;buffio.h&gt; \#include &lt;buffio.h&gt;
#include &lt;stdio.h&gt; \#include &lt;stdio.h&gt;
#include &lt;errno.h&gt; \#include &lt;errno.h&gt;
int main(int argc, char **argv ) int main(int argc, char **argv )