Update web-platform-tests to revision 0d318188757a9c996e20b82db201fd04de5aa255

tests/wpt/web-platform-tests/tools/html5lib/doc/Makefile

@@ -0,0 +1,177 @@
+# Makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line.
+SPHINXOPTS    =
+SPHINXBUILD   = sphinx-build
+PAPER         =
+BUILDDIR      = _build
+
+# User-friendly check for sphinx-build
+ifeq ($(shell which $(SPHINXBUILD) >/dev/null 2>&1; echo $$?), 1)
+$(error The '$(SPHINXBUILD)' command was not found. Make sure you have Sphinx installed, then set the SPHINXBUILD environment variable to point to the full path of the '$(SPHINXBUILD)' executable. Alternatively you can add the directory with the executable to your PATH. If you don't have Sphinx installed, grab it from http://sphinx-doc.org/)
+endif
+
+# Internal variables.
+PAPEROPT_a4     = -D latex_paper_size=a4
+PAPEROPT_letter = -D latex_paper_size=letter
+ALLSPHINXOPTS   = -d $(BUILDDIR)/doctrees $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) .
+# the i18n builder cannot share the environment and doctrees with the others
+I18NSPHINXOPTS  = $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) .
+
+.PHONY: help clean html dirhtml singlehtml pickle json htmlhelp qthelp devhelp epub latex latexpdf text man changes linkcheck doctest gettext
+
+help:
+	@echo "Please use \`make <target>' where <target> is one of"
+	@echo "  html       to make standalone HTML files"
+	@echo "  dirhtml    to make HTML files named index.html in directories"
+	@echo "  singlehtml to make a single large HTML file"
+	@echo "  pickle     to make pickle files"
+	@echo "  json       to make JSON files"
+	@echo "  htmlhelp   to make HTML files and a HTML help project"
+	@echo "  qthelp     to make HTML files and a qthelp project"
+	@echo "  devhelp    to make HTML files and a Devhelp project"
+	@echo "  epub       to make an epub"
+	@echo "  latex      to make LaTeX files, you can set PAPER=a4 or PAPER=letter"
+	@echo "  latexpdf   to make LaTeX files and run them through pdflatex"
+	@echo "  latexpdfja to make LaTeX files and run them through platex/dvipdfmx"
+	@echo "  text       to make text files"
+	@echo "  man        to make manual pages"
+	@echo "  texinfo    to make Texinfo files"
+	@echo "  info       to make Texinfo files and run them through makeinfo"
+	@echo "  gettext    to make PO message catalogs"
+	@echo "  changes    to make an overview of all changed/added/deprecated items"
+	@echo "  xml        to make Docutils-native XML files"
+	@echo "  pseudoxml  to make pseudoxml-XML files for display purposes"
+	@echo "  linkcheck  to check all external links for integrity"
+	@echo "  doctest    to run all doctests embedded in the documentation (if enabled)"
+
+clean:
+	rm -rf $(BUILDDIR)/*
+
+html:
+	$(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html
+	@echo
+	@echo "Build finished. The HTML pages are in $(BUILDDIR)/html."
+
+dirhtml:
+	$(SPHINXBUILD) -b dirhtml $(ALLSPHINXOPTS) $(BUILDDIR)/dirhtml
+	@echo
+	@echo "Build finished. The HTML pages are in $(BUILDDIR)/dirhtml."
+
+singlehtml:
+	$(SPHINXBUILD) -b singlehtml $(ALLSPHINXOPTS) $(BUILDDIR)/singlehtml
+	@echo
+	@echo "Build finished. The HTML page is in $(BUILDDIR)/singlehtml."
+
+pickle:
+	$(SPHINXBUILD) -b pickle $(ALLSPHINXOPTS) $(BUILDDIR)/pickle
+	@echo
+	@echo "Build finished; now you can process the pickle files."
+
+json:
+	$(SPHINXBUILD) -b json $(ALLSPHINXOPTS) $(BUILDDIR)/json
+	@echo
+	@echo "Build finished; now you can process the JSON files."
+
+htmlhelp:
+	$(SPHINXBUILD) -b htmlhelp $(ALLSPHINXOPTS) $(BUILDDIR)/htmlhelp
+	@echo
+	@echo "Build finished; now you can run HTML Help Workshop with the" \
+	      ".hhp project file in $(BUILDDIR)/htmlhelp."
+
+qthelp:
+	$(SPHINXBUILD) -b qthelp $(ALLSPHINXOPTS) $(BUILDDIR)/qthelp
+	@echo
+	@echo "Build finished; now you can run "qcollectiongenerator" with the" \
+	      ".qhcp project file in $(BUILDDIR)/qthelp, like this:"
+	@echo "# qcollectiongenerator $(BUILDDIR)/qthelp/html5lib.qhcp"
+	@echo "To view the help file:"
+	@echo "# assistant -collectionFile $(BUILDDIR)/qthelp/html5lib.qhc"
+
+devhelp:
+	$(SPHINXBUILD) -b devhelp $(ALLSPHINXOPTS) $(BUILDDIR)/devhelp
+	@echo
+	@echo "Build finished."
+	@echo "To view the help file:"
+	@echo "# mkdir -p $$HOME/.local/share/devhelp/html5lib"
+	@echo "# ln -s $(BUILDDIR)/devhelp $$HOME/.local/share/devhelp/html5lib"
+	@echo "# devhelp"
+
+epub:
+	$(SPHINXBUILD) -b epub $(ALLSPHINXOPTS) $(BUILDDIR)/epub
+	@echo
+	@echo "Build finished. The epub file is in $(BUILDDIR)/epub."
+
+latex:
+	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
+	@echo
+	@echo "Build finished; the LaTeX files are in $(BUILDDIR)/latex."
+	@echo "Run \`make' in that directory to run these through (pdf)latex" \
+	      "(use \`make latexpdf' here to do that automatically)."
+
+latexpdf:
+	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
+	@echo "Running LaTeX files through pdflatex..."
+	$(MAKE) -C $(BUILDDIR)/latex all-pdf
+	@echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex."
+
+latexpdfja:
+	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
+	@echo "Running LaTeX files through platex and dvipdfmx..."
+	$(MAKE) -C $(BUILDDIR)/latex all-pdf-ja
+	@echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex."
+
+text:
+	$(SPHINXBUILD) -b text $(ALLSPHINXOPTS) $(BUILDDIR)/text
+	@echo
+	@echo "Build finished. The text files are in $(BUILDDIR)/text."
+
+man:
+	$(SPHINXBUILD) -b man $(ALLSPHINXOPTS) $(BUILDDIR)/man
+	@echo
+	@echo "Build finished. The manual pages are in $(BUILDDIR)/man."
+
+texinfo:
+	$(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo
+	@echo
+	@echo "Build finished. The Texinfo files are in $(BUILDDIR)/texinfo."
+	@echo "Run \`make' in that directory to run these through makeinfo" \
+	      "(use \`make info' here to do that automatically)."
+
+info:
+	$(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo
+	@echo "Running Texinfo files through makeinfo..."
+	make -C $(BUILDDIR)/texinfo info
+	@echo "makeinfo finished; the Info files are in $(BUILDDIR)/texinfo."
+
+gettext:
+	$(SPHINXBUILD) -b gettext $(I18NSPHINXOPTS) $(BUILDDIR)/locale
+	@echo
+	@echo "Build finished. The message catalogs are in $(BUILDDIR)/locale."
+
+changes:
+	$(SPHINXBUILD) -b changes $(ALLSPHINXOPTS) $(BUILDDIR)/changes
+	@echo
+	@echo "The overview file is in $(BUILDDIR)/changes."
+
+linkcheck:
+	$(SPHINXBUILD) -b linkcheck $(ALLSPHINXOPTS) $(BUILDDIR)/linkcheck
+	@echo
+	@echo "Link check complete; look for any errors in the above output " \
+	      "or in $(BUILDDIR)/linkcheck/output.txt."
+
+doctest:
+	$(SPHINXBUILD) -b doctest $(ALLSPHINXOPTS) $(BUILDDIR)/doctest
+	@echo "Testing of doctests in the sources finished, look at the " \
+	      "results in $(BUILDDIR)/doctest/output.txt."
+
+xml:
+	$(SPHINXBUILD) -b xml $(ALLSPHINXOPTS) $(BUILDDIR)/xml
+	@echo
+	@echo "Build finished. The XML files are in $(BUILDDIR)/xml."
+
+pseudoxml:
+	$(SPHINXBUILD) -b pseudoxml $(ALLSPHINXOPTS) $(BUILDDIR)/pseudoxml
+	@echo
+	@echo "Build finished. The pseudo-XML files are in $(BUILDDIR)/pseudoxml."

tests/wpt/web-platform-tests/tools/html5lib/doc/changes.rst

@@ -0,0 +1,3 @@
+.. :changelog:
+
+.. include:: ../CHANGES.rst

tests/wpt/web-platform-tests/tools/html5lib/doc/conf.py

@@ -0,0 +1,280 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+#
+# html5lib documentation build configuration file, created by
+# sphinx-quickstart on Wed May  8 00:04:49 2013.
+#
+# This file is execfile()d with the current directory set to its containing dir.
+#
+# Note that not all possible configuration values are present in this
+# autogenerated file.
+#
+# All configuration values have a default; values that are commented out
+# serve to show the default.
+
+import sys, os
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+#sys.path.insert(0, os.path.abspath('.'))
+
+# -- General configuration -----------------------------------------------------
+
+# If your documentation needs a minimal Sphinx version, state it here.
+#needs_sphinx = '1.0'
+
+# Add any Sphinx extension module names here, as strings. They can be extensions
+# coming with Sphinx (named 'sphinx.ext.*') or your custom ones.
+extensions = ['sphinx.ext.autodoc', 'sphinx.ext.doctest', 'sphinx.ext.viewcode']
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ['_templates']
+
+# The suffix of source filenames.
+source_suffix = '.rst'
+
+# The encoding of source files.
+#source_encoding = 'utf-8-sig'
+
+# The master toctree document.
+master_doc = 'index'
+
+# General information about the project.
+project = 'html5lib'
+copyright = '2006 - 2013, James Graham, Geoffrey Sneddon, and contributors'
+
+# The version info for the project you're documenting, acts as replacement for
+# |version| and |release|, also used in various other places throughout the
+# built documents.
+#
+# The short X.Y version.
+version = '1.0'
+# The full version, including alpha/beta/rc tags.
+sys.path.append(os.path.abspath('..'))
+from html5lib import __version__
+release = __version__
+
+# The language for content autogenerated by Sphinx. Refer to documentation
+# for a list of supported languages.
+#language = 'en'
+
+# There are two options for replacing |today|: either, you set today to some
+# non-false value, then it is used:
+#today = ''
+# Else, today_fmt is used as the format for a strftime call.
+#today_fmt = '%B %d, %Y'
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+exclude_patterns = ['_build', 'theme']
+
+# The reST default role (used for this markup: `text`) to use for all documents.
+#default_role = None
+
+# If true, '()' will be appended to :func: etc. cross-reference text.
+#add_function_parentheses = True
+
+# If true, the current module name will be prepended to all description
+# unit titles (such as .. function::).
+#add_module_names = True
+
+# If true, sectionauthor and moduleauthor directives will be shown in the
+# output. They are ignored by default.
+#show_authors = False
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = 'sphinx'
+
+# A list of ignored prefixes for module index sorting.
+#modindex_common_prefix = []
+
+# If true, keep warnings as "system message" paragraphs in the built documents.
+#keep_warnings = False
+
+
+# -- Options for HTML output ---------------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+html_theme = 'default'
+
+# Theme options are theme-specific and customize the look and feel of a theme
+# further.  For a list of options available for each theme, see the
+# documentation.
+#html_theme_options = {}
+
+# Add any paths that contain custom themes here, relative to this directory.
+#html_theme_path = []
+
+# The name for this set of Sphinx documents.  If None, it defaults to
+# "<project> v<release> documentation".
+#html_title = None
+
+# A shorter title for the navigation bar.  Default is the same as html_title.
+#html_short_title = None
+
+# The name of an image file (relative to this directory) to place at the top
+# of the sidebar.
+#html_logo = None
+
+# The name of an image file (within the static path) to use as favicon of the
+# docs.  This file should be a Windows icon file (.ico) being 16x16 or 32x32
+# pixels large.
+#html_favicon = None
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = ['_static']
+
+# If not '', a 'Last updated on:' timestamp is inserted at every page bottom,
+# using the given strftime format.
+#html_last_updated_fmt = '%b %d, %Y'
+
+# If true, SmartyPants will be used to convert quotes and dashes to
+# typographically correct entities.
+#html_use_smartypants = True
+
+# Custom sidebar templates, maps document names to template names.
+#html_sidebars = {}
+
+# Additional templates that should be rendered to pages, maps page names to
+# template names.
+#html_additional_pages = {}
+
+# If false, no module index is generated.
+#html_domain_indices = True
+
+# If false, no index is generated.
+#html_use_index = True
+
+# If true, the index is split into individual pages for each letter.
+#html_split_index = False
+
+# If true, links to the reST sources are added to the pages.
+#html_show_sourcelink = True
+
+# If true, "Created using Sphinx" is shown in the HTML footer. Default is True.
+#html_show_sphinx = True
+
+# If true, "(C) Copyright ..." is shown in the HTML footer. Default is True.
+#html_show_copyright = True
+
+# If true, an OpenSearch description file will be output, and all pages will
+# contain a <link> tag referring to it.  The value of this option must be the
+# base URL from which the finished HTML is served.
+#html_use_opensearch = ''
+
+# This is the file name suffix for HTML files (e.g. ".xhtml").
+#html_file_suffix = None
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = 'html5libdoc'
+
+
+# -- Options for LaTeX output --------------------------------------------------
+
+latex_elements = {
+# The paper size ('letterpaper' or 'a4paper').
+#'papersize': 'letterpaper',
+
+# The font size ('10pt', '11pt' or '12pt').
+#'pointsize': '10pt',
+
+# Additional stuff for the LaTeX preamble.
+#'preamble': '',
+}
+
+# Grouping the document tree into LaTeX files. List of tuples
+# (source start file, target name, title, author, documentclass [howto/manual]).
+latex_documents = [
+  ('index', 'html5lib.tex', 'html5lib Documentation',
+   'James Graham, Geoffrey Sneddon, and contributors', 'manual'),
+]
+
+# The name of an image file (relative to this directory) to place at the top of
+# the title page.
+#latex_logo = None
+
+# For "manual" documents, if this is true, then toplevel headings are parts,
+# not chapters.
+#latex_use_parts = False
+
+# If true, show page references after internal links.
+#latex_show_pagerefs = False
+
+# If true, show URL addresses after external links.
+#latex_show_urls = False
+
+# Documents to append as an appendix to all manuals.
+#latex_appendices = []
+
+# If false, no module index is generated.
+#latex_domain_indices = True
+
+
+# -- Options for manual page output --------------------------------------------
+
+# One entry per manual page. List of tuples
+# (source start file, name, description, authors, manual section).
+man_pages = [
+    ('index', 'html5lib', 'html5lib Documentation',
+     ['James Graham, Geoffrey Sneddon, and contributors'], 1)
+]
+
+# If true, show URL addresses after external links.
+#man_show_urls = False
+
+
+# -- Options for Texinfo output ------------------------------------------------
+
+# Grouping the document tree into Texinfo files. List of tuples
+# (source start file, target name, title, author,
+#  dir menu entry, description, category)
+texinfo_documents = [
+  ('index', 'html5lib', 'html5lib Documentation',
+   'James Graham, Geoffrey Sneddon, and contributors', 'html5lib', 'One line description of project.',
+   'Miscellaneous'),
+]
+
+# Documents to append as an appendix to all manuals.
+#texinfo_appendices = []
+
+# If false, no module index is generated.
+#texinfo_domain_indices = True
+
+# How to display URL addresses: 'footnote', 'no', or 'inline'.
+#texinfo_show_urls = 'footnote'
+
+# If true, do not generate a @detailmenu in the "Top" node's menu.
+#texinfo_no_detailmenu = False
+
+class CExtMock(object):
+    """Required for autodoc on readthedocs.org where you cannot build C extensions."""
+    def __init__(self, *args, **kwargs):
+        pass
+
+    def __call__(self, *args, **kwargs):
+        return CExtMock()
+
+    @classmethod
+    def __getattr__(cls, name):
+        if name in ('__file__', '__path__'):
+            return '/dev/null'
+        else:
+            return CExtMock()
+
+try:
+    import lxml   # flake8: noqa
+except ImportError:
+    sys.modules['lxml'] = CExtMock()
+    sys.modules['lxml.etree'] = CExtMock()
+    print("warning: lxml modules mocked.")
+
+try:
+    import genshi   # flake8: noqa
+except ImportError:
+    sys.modules['genshi'] = CExtMock()
+    sys.modules['genshi.core'] = CExtMock()
+    print("warning: genshi modules mocked.")

tests/wpt/web-platform-tests/tools/html5lib/doc/html5lib.filters.rst

@@ -0,0 +1,59 @@
+filters Package
+===============
+
+:mod:`_base` Module
+-------------------
+
+.. automodule:: html5lib.filters._base
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+:mod:`alphabeticalattributes` Module
+------------------------------------
+
+.. automodule:: html5lib.filters.alphabeticalattributes
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+:mod:`inject_meta_charset` Module
+---------------------------------
+
+.. automodule:: html5lib.filters.inject_meta_charset
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+:mod:`lint` Module
+------------------
+
+.. automodule:: html5lib.filters.lint
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+:mod:`optionaltags` Module
+--------------------------
+
+.. automodule:: html5lib.filters.optionaltags
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+:mod:`sanitizer` Module
+-----------------------
+
+.. automodule:: html5lib.filters.sanitizer
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+:mod:`whitespace` Module
+------------------------
+
+.. automodule:: html5lib.filters.whitespace
+    :members:
+    :undoc-members:
+    :show-inheritance:
+

tests/wpt/web-platform-tests/tools/html5lib/doc/html5lib.rst

@@ -0,0 +1,77 @@
+html5lib Package
+================
+
+:mod:`html5lib` Package
+-----------------------
+
+.. automodule:: html5lib.__init__
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+:mod:`constants` Module
+-----------------------
+
+.. automodule:: html5lib.constants
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+:mod:`html5parser` Module
+-------------------------
+
+.. automodule:: html5lib.html5parser
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+:mod:`ihatexml` Module
+----------------------
+
+.. automodule:: html5lib.ihatexml
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+:mod:`inputstream` Module
+-------------------------
+
+.. automodule:: html5lib.inputstream
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+:mod:`sanitizer` Module
+-----------------------
+
+.. automodule:: html5lib.sanitizer
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+:mod:`tokenizer` Module
+-----------------------
+
+.. automodule:: html5lib.tokenizer
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+:mod:`utils` Module
+-------------------
+
+.. automodule:: html5lib.utils
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+Subpackages
+-----------
+
+.. toctree::
+
+    html5lib.filters
+    html5lib.serializer
+    html5lib.treebuilders
+    html5lib.treewalkers
+

tests/wpt/web-platform-tests/tools/html5lib/doc/html5lib.serializer.rst

@@ -0,0 +1,19 @@
+serializer Package
+==================
+
+:mod:`serializer` Package
+-------------------------
+
+.. automodule:: html5lib.serializer
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+:mod:`htmlserializer` Module
+----------------------------
+
+.. automodule:: html5lib.serializer.htmlserializer
+    :members:
+    :undoc-members:
+    :show-inheritance:
+

tests/wpt/web-platform-tests/tools/html5lib/doc/html5lib.treebuilders.rst

@@ -0,0 +1,43 @@
+treebuilders Package
+====================
+
+:mod:`treebuilders` Package
+---------------------------
+
+.. automodule:: html5lib.treebuilders
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+:mod:`_base` Module
+-------------------
+
+.. automodule:: html5lib.treebuilders._base
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+:mod:`dom` Module
+-----------------
+
+.. automodule:: html5lib.treebuilders.dom
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+:mod:`etree` Module
+-------------------
+
+.. automodule:: html5lib.treebuilders.etree
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+:mod:`etree_lxml` Module
+------------------------
+
+.. automodule:: html5lib.treebuilders.etree_lxml
+    :members:
+    :undoc-members:
+    :show-inheritance:
+

tests/wpt/web-platform-tests/tools/html5lib/doc/html5lib.treewalkers.rst

@@ -0,0 +1,59 @@
+treewalkers Package
+===================
+
+:mod:`treewalkers` Package
+--------------------------
+
+.. automodule:: html5lib.treewalkers
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+:mod:`_base` Module
+-------------------
+
+.. automodule:: html5lib.treewalkers._base
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+:mod:`dom` Module
+-----------------
+
+.. automodule:: html5lib.treewalkers.dom
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+:mod:`etree` Module
+-------------------
+
+.. automodule:: html5lib.treewalkers.etree
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+:mod:`genshistream` Module
+--------------------------
+
+.. automodule:: html5lib.treewalkers.genshistream
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+:mod:`lxmletree` Module
+-----------------------
+
+.. automodule:: html5lib.treewalkers.lxmletree
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+:mod:`pulldom` Module
+---------------------
+
+.. automodule:: html5lib.treewalkers.pulldom
+    :members:
+    :undoc-members:
+    :show-inheritance:
+

tests/wpt/web-platform-tests/tools/html5lib/doc/index.rst

@@ -0,0 +1,21 @@
+Overview
+========
+
+.. include:: ../README.rst
+   :start-line: 6
+
+.. toctree::
+   :maxdepth: 2
+
+   movingparts
+   changes
+   License <license>
+
+
+Indices and tables
+==================
+
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`
+

tests/wpt/web-platform-tests/tools/html5lib/doc/license.rst

@@ -0,0 +1,4 @@
+License
+=======
+
+.. include:: ../LICENSE

tests/wpt/web-platform-tests/tools/html5lib/doc/make.bat

@@ -0,0 +1,242 @@
+@ECHO OFF
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=sphinx-build
+)
+set BUILDDIR=_build
+set ALLSPHINXOPTS=-d %BUILDDIR%/doctrees %SPHINXOPTS% .
+set I18NSPHINXOPTS=%SPHINXOPTS% .
+if NOT "%PAPER%" == "" (
+	set ALLSPHINXOPTS=-D latex_paper_size=%PAPER% %ALLSPHINXOPTS%
+	set I18NSPHINXOPTS=-D latex_paper_size=%PAPER% %I18NSPHINXOPTS%
+)
+
+if "%1" == "" goto help
+
+if "%1" == "help" (
+	:help
+	echo.Please use `make ^<target^>` where ^<target^> is one of
+	echo.  html       to make standalone HTML files
+	echo.  dirhtml    to make HTML files named index.html in directories
+	echo.  singlehtml to make a single large HTML file
+	echo.  pickle     to make pickle files
+	echo.  json       to make JSON files
+	echo.  htmlhelp   to make HTML files and a HTML help project
+	echo.  qthelp     to make HTML files and a qthelp project
+	echo.  devhelp    to make HTML files and a Devhelp project
+	echo.  epub       to make an epub
+	echo.  latex      to make LaTeX files, you can set PAPER=a4 or PAPER=letter
+	echo.  text       to make text files
+	echo.  man        to make manual pages
+	echo.  texinfo    to make Texinfo files
+	echo.  gettext    to make PO message catalogs
+	echo.  changes    to make an overview over all changed/added/deprecated items
+	echo.  xml        to make Docutils-native XML files
+	echo.  pseudoxml  to make pseudoxml-XML files for display purposes
+	echo.  linkcheck  to check all external links for integrity
+	echo.  doctest    to run all doctests embedded in the documentation if enabled
+	goto end
+)
+
+if "%1" == "clean" (
+	for /d %%i in (%BUILDDIR%\*) do rmdir /q /s %%i
+	del /q /s %BUILDDIR%\*
+	goto end
+)
+
+
+%SPHINXBUILD% 2> nul
+if errorlevel 9009 (
+	echo.
+	echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
+	echo.installed, then set the SPHINXBUILD environment variable to point
+	echo.to the full path of the 'sphinx-build' executable. Alternatively you
+	echo.may add the Sphinx directory to PATH.
+	echo.
+	echo.If you don't have Sphinx installed, grab it from
+	echo.http://sphinx-doc.org/
+	exit /b 1
+)
+
+if "%1" == "html" (
+	%SPHINXBUILD% -b html %ALLSPHINXOPTS% %BUILDDIR%/html
+	if errorlevel 1 exit /b 1
+	echo.
+	echo.Build finished. The HTML pages are in %BUILDDIR%/html.
+	goto end
+)
+
+if "%1" == "dirhtml" (
+	%SPHINXBUILD% -b dirhtml %ALLSPHINXOPTS% %BUILDDIR%/dirhtml
+	if errorlevel 1 exit /b 1
+	echo.
+	echo.Build finished. The HTML pages are in %BUILDDIR%/dirhtml.
+	goto end
+)
+
+if "%1" == "singlehtml" (
+	%SPHINXBUILD% -b singlehtml %ALLSPHINXOPTS% %BUILDDIR%/singlehtml
+	if errorlevel 1 exit /b 1
+	echo.
+	echo.Build finished. The HTML pages are in %BUILDDIR%/singlehtml.
+	goto end
+)
+
+if "%1" == "pickle" (
+	%SPHINXBUILD% -b pickle %ALLSPHINXOPTS% %BUILDDIR%/pickle
+	if errorlevel 1 exit /b 1
+	echo.
+	echo.Build finished; now you can process the pickle files.
+	goto end
+)
+
+if "%1" == "json" (
+	%SPHINXBUILD% -b json %ALLSPHINXOPTS% %BUILDDIR%/json
+	if errorlevel 1 exit /b 1
+	echo.
+	echo.Build finished; now you can process the JSON files.
+	goto end
+)
+
+if "%1" == "htmlhelp" (
+	%SPHINXBUILD% -b htmlhelp %ALLSPHINXOPTS% %BUILDDIR%/htmlhelp
+	if errorlevel 1 exit /b 1
+	echo.
+	echo.Build finished; now you can run HTML Help Workshop with the ^
+.hhp project file in %BUILDDIR%/htmlhelp.
+	goto end
+)
+
+if "%1" == "qthelp" (
+	%SPHINXBUILD% -b qthelp %ALLSPHINXOPTS% %BUILDDIR%/qthelp
+	if errorlevel 1 exit /b 1
+	echo.
+	echo.Build finished; now you can run "qcollectiongenerator" with the ^
+.qhcp project file in %BUILDDIR%/qthelp, like this:
+	echo.^> qcollectiongenerator %BUILDDIR%\qthelp\html5lib.qhcp
+	echo.To view the help file:
+	echo.^> assistant -collectionFile %BUILDDIR%\qthelp\html5lib.ghc
+	goto end
+)
+
+if "%1" == "devhelp" (
+	%SPHINXBUILD% -b devhelp %ALLSPHINXOPTS% %BUILDDIR%/devhelp
+	if errorlevel 1 exit /b 1
+	echo.
+	echo.Build finished.
+	goto end
+)
+
+if "%1" == "epub" (
+	%SPHINXBUILD% -b epub %ALLSPHINXOPTS% %BUILDDIR%/epub
+	if errorlevel 1 exit /b 1
+	echo.
+	echo.Build finished. The epub file is in %BUILDDIR%/epub.
+	goto end
+)
+
+if "%1" == "latex" (
+	%SPHINXBUILD% -b latex %ALLSPHINXOPTS% %BUILDDIR%/latex
+	if errorlevel 1 exit /b 1
+	echo.
+	echo.Build finished; the LaTeX files are in %BUILDDIR%/latex.
+	goto end
+)
+
+if "%1" == "latexpdf" (
+	%SPHINXBUILD% -b latex %ALLSPHINXOPTS% %BUILDDIR%/latex
+	cd %BUILDDIR%/latex
+	make all-pdf
+	cd %BUILDDIR%/..
+	echo.
+	echo.Build finished; the PDF files are in %BUILDDIR%/latex.
+	goto end
+)
+
+if "%1" == "latexpdfja" (
+	%SPHINXBUILD% -b latex %ALLSPHINXOPTS% %BUILDDIR%/latex
+	cd %BUILDDIR%/latex
+	make all-pdf-ja
+	cd %BUILDDIR%/..
+	echo.
+	echo.Build finished; the PDF files are in %BUILDDIR%/latex.
+	goto end
+)
+
+if "%1" == "text" (
+	%SPHINXBUILD% -b text %ALLSPHINXOPTS% %BUILDDIR%/text
+	if errorlevel 1 exit /b 1
+	echo.
+	echo.Build finished. The text files are in %BUILDDIR%/text.
+	goto end
+)
+
+if "%1" == "man" (
+	%SPHINXBUILD% -b man %ALLSPHINXOPTS% %BUILDDIR%/man
+	if errorlevel 1 exit /b 1
+	echo.
+	echo.Build finished. The manual pages are in %BUILDDIR%/man.
+	goto end
+)
+
+if "%1" == "texinfo" (
+	%SPHINXBUILD% -b texinfo %ALLSPHINXOPTS% %BUILDDIR%/texinfo
+	if errorlevel 1 exit /b 1
+	echo.
+	echo.Build finished. The Texinfo files are in %BUILDDIR%/texinfo.
+	goto end
+)
+
+if "%1" == "gettext" (
+	%SPHINXBUILD% -b gettext %I18NSPHINXOPTS% %BUILDDIR%/locale
+	if errorlevel 1 exit /b 1
+	echo.
+	echo.Build finished. The message catalogs are in %BUILDDIR%/locale.
+	goto end
+)
+
+if "%1" == "changes" (
+	%SPHINXBUILD% -b changes %ALLSPHINXOPTS% %BUILDDIR%/changes
+	if errorlevel 1 exit /b 1
+	echo.
+	echo.The overview file is in %BUILDDIR%/changes.
+	goto end
+)
+
+if "%1" == "linkcheck" (
+	%SPHINXBUILD% -b linkcheck %ALLSPHINXOPTS% %BUILDDIR%/linkcheck
+	if errorlevel 1 exit /b 1
+	echo.
+	echo.Link check complete; look for any errors in the above output ^
+or in %BUILDDIR%/linkcheck/output.txt.
+	goto end
+)
+
+if "%1" == "doctest" (
+	%SPHINXBUILD% -b doctest %ALLSPHINXOPTS% %BUILDDIR%/doctest
+	if errorlevel 1 exit /b 1
+	echo.
+	echo.Testing of doctests in the sources finished, look at the ^
+results in %BUILDDIR%/doctest/output.txt.
+	goto end
+)
+
+if "%1" == "xml" (
+	%SPHINXBUILD% -b xml %ALLSPHINXOPTS% %BUILDDIR%/xml
+	if errorlevel 1 exit /b 1
+	echo.
+	echo.Build finished. The XML files are in %BUILDDIR%/xml.
+	goto end
+)
+
+if "%1" == "pseudoxml" (
+	%SPHINXBUILD% -b pseudoxml %ALLSPHINXOPTS% %BUILDDIR%/pseudoxml
+	if errorlevel 1 exit /b 1
+	echo.
+	echo.Build finished. The pseudo-XML files are in %BUILDDIR%/pseudoxml.
+	goto end
+)
+
+:end

tests/wpt/web-platform-tests/tools/html5lib/doc/modules.rst

@@ -0,0 +1,7 @@
+html5lib
+========
+
+.. toctree::
+   :maxdepth: 4
+
+   html5lib

tests/wpt/web-platform-tests/tools/html5lib/doc/movingparts.rst

@@ -0,0 +1,209 @@
+The moving parts
+================
+
+html5lib consists of a number of components, which are responsible for
+handling its features.
+
+
+Tree builders
+-------------
+
+The parser reads HTML by tokenizing the content and building a tree that
+the user can later access. There are three main types of trees that
+html5lib can build:
+
+* ``etree`` - this is the default; builds a tree based on ``xml.etree``,
+  which can be found in the standard library. Whenever possible, the
+  accelerated ``ElementTree`` implementation (i.e.
+  ``xml.etree.cElementTree`` on Python 2.x) is used.
+
+* ``dom`` - builds a tree based on ``xml.dom.minidom``.
+
+* ``lxml.etree`` - uses lxml's implementation of the ``ElementTree``
+  API.  The performance gains are relatively small compared to using the
+  accelerated ``ElementTree`` module.
+
+You can specify the builder by name when using the shorthand API:
+
+.. code-block:: python
+
+  import html5lib
+  with open("mydocument.html", "rb") as f:
+      lxml_etree_document = html5lib.parse(f, treebuilder="lxml")
+
+When instantiating a parser object, you have to pass a tree builder
+class in the ``tree`` keyword attribute:
+
+.. code-block:: python
+
+  import html5lib
+  parser = html5lib.HTMLParser(tree=SomeTreeBuilder)
+  document = parser.parse("<p>Hello World!")
+
+To get a builder class by name, use the ``getTreeBuilder`` function:
+
+.. code-block:: python
+
+  import html5lib
+  parser = html5lib.HTMLParser(tree=html5lib.getTreeBuilder("dom"))
+  minidom_document = parser.parse("<p>Hello World!")
+
+The implementation of builders can be found in `html5lib/treebuilders/
+<https://github.com/html5lib/html5lib-python/tree/master/html5lib/treebuilders>`_.
+
+
+Tree walkers
+------------
+
+Once a tree is ready, you can work on it either manually, or using
+a tree walker, which provides a streaming view of the tree. html5lib
+provides walkers for all three supported types of trees (``etree``,
+``dom`` and ``lxml``).
+
+The implementation of walkers can be found in `html5lib/treewalkers/
+<https://github.com/html5lib/html5lib-python/tree/master/html5lib/treewalkers>`_.
+
+Walkers make consuming HTML easier. html5lib uses them to provide you
+with has a couple of handy tools.
+
+
+HTMLSerializer
+~~~~~~~~~~~~~~
+
+The serializer lets you write HTML back as a stream of bytes.
+
+.. code-block:: pycon
+
+  >>> import html5lib
+  >>> element = html5lib.parse('<p xml:lang="pl">Witam wszystkich')
+  >>> walker = html5lib.getTreeWalker("etree")
+  >>> stream = walker(element)
+  >>> s = html5lib.serializer.HTMLSerializer()
+  >>> output = s.serialize(stream)
+  >>> for item in output:
+  ...   print("%r" % item)
+  '<p'
+  ' '
+  'xml:lang'
+  '='
+  'pl'
+  '>'
+  'Witam wszystkich'
+
+You can customize the serializer behaviour in a variety of ways, consult
+the :class:`~html5lib.serializer.htmlserializer.HTMLSerializer`
+documentation.
+
+
+Filters
+~~~~~~~
+
+You can alter the stream content with filters provided by html5lib:
+
+* :class:`alphabeticalattributes.Filter
+  <html5lib.filters.alphabeticalattributes.Filter>` sorts attributes on
+  tags to be in alphabetical order
+
+* :class:`inject_meta_charset.Filter
+  <html5lib.filters.inject_meta_charset.Filter>` sets a user-specified
+  encoding in the correct ``<meta>`` tag in the ``<head>`` section of
+  the document
+
+* :class:`lint.Filter <html5lib.filters.lint.Filter>` raises
+  ``LintError`` exceptions on invalid tag and attribute names, invalid
+  PCDATA, etc.
+
+* :class:`optionaltags.Filter <html5lib.filters.optionaltags.Filter>`
+  removes tags from the stream which are not necessary to produce valid
+  HTML
+
+* :class:`sanitizer.Filter <html5lib.filters.sanitizer.Filter>` removes
+  unsafe markup and CSS. Elements that are known to be safe are passed
+  through and the rest is converted to visible text. The default
+  configuration of the sanitizer follows the `WHATWG Sanitization Rules
+  <http://wiki.whatwg.org/wiki/Sanitization_rules>`_.
+
+* :class:`whitespace.Filter <html5lib.filters.whitespace.Filter>`
+  collapses all whitespace characters to single spaces unless they're in
+  ``<pre/>`` or ``textarea`` tags.
+
+To use a filter, simply wrap it around a stream:
+
+.. code-block:: python
+
+  >>> import html5lib
+  >>> from html5lib.filters import sanitizer
+  >>> dom = html5lib.parse("<p><script>alert('Boo!')", treebuilder="dom")
+  >>> walker = html5lib.getTreeWalker("dom")
+  >>> stream = walker(dom)
+  >>> sane_stream = sanitizer.Filter(stream) clean_stream = sanitizer.Filter(stream)
+
+
+Tree adapters
+-------------
+
+Used to translate one type of tree to another. More documentation
+pending, sorry.
+
+
+Encoding discovery
+------------------
+
+Parsed trees are always Unicode. However a large variety of input
+encodings are supported. The encoding of the document is determined in
+the following way:
+
+* The encoding may be explicitly specified by passing the name of the
+  encoding as the encoding parameter to the
+  :meth:`~html5lib.html5parser.HTMLParser.parse` method on
+  ``HTMLParser`` objects.
+
+* If no encoding is specified, the parser will attempt to detect the
+  encoding from a ``<meta>``  element in the first 512 bytes of the
+  document (this is only a partial implementation of the current HTML
+  5 specification).
+
+* If no encoding can be found and the chardet library is available, an
+  attempt will be made to sniff the encoding from the byte pattern.
+
+* If all else fails, the default encoding will be used. This is usually
+  `Windows-1252 <http://en.wikipedia.org/wiki/Windows-1252>`_, which is
+  a common fallback used by Web browsers.
+
+
+Tokenizers
+----------
+
+The part of the parser responsible for translating a raw input stream
+into meaningful tokens is the tokenizer. Currently html5lib provides
+two.
+
+To set up a tokenizer, simply pass it when instantiating
+a :class:`~html5lib.html5parser.HTMLParser`:
+
+.. code-block:: python
+
+  import html5lib
+  from html5lib import sanitizer
+
+  p = html5lib.HTMLParser(tokenizer=sanitizer.HTMLSanitizer)
+  p.parse("<p>Surprise!<script>alert('Boo!');</script>")
+
+HTMLTokenizer
+~~~~~~~~~~~~~
+
+This is the default tokenizer, the heart of html5lib. The implementation
+can be found in `html5lib/tokenizer.py
+<https://github.com/html5lib/html5lib-python/blob/master/html5lib/tokenizer.py>`_.
+
+HTMLSanitizer
+~~~~~~~~~~~~~
+
+This is a tokenizer that removes unsafe markup and CSS styles from the
+input. Elements that are known to be safe are passed through and the
+rest is converted to visible text. The default configuration of the
+sanitizer follows the `WHATWG Sanitization Rules
+<http://wiki.whatwg.org/wiki/Sanitization_rules>`_.
+
+The implementation can be found in `html5lib/sanitizer.py
+<https://github.com/html5lib/html5lib-python/blob/master/html5lib/sanitizer.py>`_.