Merge branch 'master' into master

Author: RitwikGupta

.coveragerc

@@ -0,0 +1,8 @@
+[run]
+branch = True
+source = html5lib
+
+[paths]
+source =
+   html5lib
+   .tox/*/lib/python*/site-packages/html5lib

.gitignore

@@ -1,20 +1,82 @@
-# Because we never want compiled Python
+# Copyright (c) 2014 GitHub, Inc.
+#
+# Permission is hereby granted,  free of charge,  to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to  use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+# DEALINGS IN THE SOFTWARE.
+
+# Byte-compiled / optimized / DLL files
 __pycache__/
-*.pyc
+*.py[cod]
+*$py.class
 
-# Ignore stuff produced by distutils
-/build/
-/dist/
-/MANIFEST
+# C extensions
+*.so
 
-# Generated by parse.py -p
-stats.prof
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
 
-# From cover (esp. in combination with nose)
+# Unit test / coverage reports
+htmlcov/
+.tox/
 .coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*,cover
 
-# Because tox's data is inherently local
-/.tox/
+# Translations
+*.mo
+*.pot
 
-# We have no interest in built Sphinx files
-/doc/_build
+# Django stuff:
+*.log
+
+# Sphinx documentation
+doc/_build/
+
+# PyBuilder
+target/
+
+# Generated by parse.py -p
+stats.prof

.prospector.yaml

@@ -0,0 +1,21 @@
+strictness: veryhigh
+doc-warnings: false
+test-warnings: false
+
+max-line-length: 139
+
+requirements:
+  - requirements.txt
+  - requirements-test.txt
+  - requirements-optional.txt
+
+ignore-paths:
+  - parse.py
+  - utils/
+
+python-targets:
+  - 2
+  - 3
+
+mccabe:
+  run: false

.pylintrc

@@ -0,0 +1,10 @@
+[MASTER]
+ignore=tests
+
+[MESSAGES CONTROL]
+# messages up to fixme should probably be fixed somehow
+disable = redefined-builtin,attribute-defined-outside-init,anomalous-backslash-in-string,no-self-use,redefined-outer-name,bad-continuation,wrong-import-order,superfluous-parens,no-member,duplicate-code,super-init-not-called,abstract-method,property-on-old-class,wrong-import-position,no-name-in-module,no-init,bad-mcs-classmethod-argument,bad-classmethod-argument,fixme,invalid-name,import-error,too-few-public-methods,too-many-ancestors,too-many-arguments,too-many-boolean-expressions,too-many-branches,too-many-instance-attributes,too-many-locals,too-many-lines,too-many-public-methods,too-many-return-statements,too-many-statements,missing-docstring,line-too-long,locally-disabled,locally-enabled,bad-builtin,deprecated-lambda
+
+[FORMAT]
+max-line-length=139
+single-line-if-stmt=no

.pytest.expect

@@ -2,36 +2,30 @@ language: python
 python:
   - "2.6"
   - "2.7"
-  - "3.2"
   - "3.3"
   - "3.4"
+  - "3.5"
   - "pypy"
 
+sudo: false
+
+cache: pip
+
 env:
   - USE_OPTIONAL=true
   - USE_OPTIONAL=false
-
-matrix:
-  exclude:
-    - python: "2.7"
-      env: USE_OPTIONAL=false
-    - python: "3.4"
-      env: USE_OPTIONAL=false
-  include:
-    - python: "2.7"
-      env: USE_OPTIONAL=false FLAKE=true
-    - python: "3.4"
-      env: USE_OPTIONAL=false FLAKE=true
-
-before_install:
-  - git submodule update --init --recursive
+  - SIX_VERSION=1.9 USE_OPTIONAL=true
 
 install:
-  - bash requirements-install.sh
+  - ./requirements-install.sh
 
 script:
-  - nosetests
+  - if [[ $TRAVIS_PYTHON_VERSION == pypy* ]]; then py.test; fi
+  - if [[ $TRAVIS_PYTHON_VERSION != pypy* ]]; then coverage run -m pytest; fi
   - bash flake8-run.sh
 
 after_script:
   - python debug-info.py
+
+after_success:
+  - if [[ $TRAVIS_PYTHON_VERSION != pypy* ]]; then coverage combine && codecov; fi

.travis.yml

@@ -16,20 +16,30 @@ Patches and suggestions
 - Lachlan Hunt
 - lantis63
 - Sam Ruby
-- Tim Fletcher
 - Thomas Broyer
+- Tim Fletcher
 - Mark Pilgrim
-- Philip Taylor
 - Ryan King
+- Philip Taylor
 - Edward Z. Yang
 - fantasai
+- Mike West
 - Philip Jägenstedt
 - Ms2ger
+- Mohammad Taha Jahangir
 - Andy Wingo
+- Juan Carlos Garcia Segovia
 - Andreas Madsack
 - Karim Valiev
-- Mohammad Taha Jahangir
-- Juan Carlos Garcia Segovia
-- Mike West
 - Marc DM
 - Ritwik Gupta
+- Tony Lopes
+- lilbludevil
+- Simon Sapin
+- Jon Dufresne
+- Drew Hubl
+- Austin Kumbera
+- Jim Baker
+- Michael[tm] Smith
+- Marc Abramowitz
+- Jon Dufresne

AUTHORS.rst

@@ -1,12 +1,134 @@
 Change Log
 ----------
 
-0.9999
-~~~~~~
+* Added the seamless attribute for iframes.
+
+0.999999999/1.0b10
+~~~~~~~~~~~~~~~~~~
+
+Released on July 15, 2016
+
+* Fix attribute order going to the tree builder to be document order
+  instead of reverse document order(!).
+
+
+0.99999999/1.0b9
+~~~~~~~~~~~~~~~~
+
+Released on July 14, 2016
+
+* **Added ordereddict as a mandatory dependency on Python 2.6.**
+
+* Added ``lxml``, ``genshi``, ``datrie``, ``charade``, and ``all``
+  extras that will do the right thing based on the specific
+  interpreter implementation.
+
+* Now requires the ``mock`` package for the testsuite.
+
+* Cease supporting DATrie under PyPy.
+
+* **Remove ``PullDOM`` support, as this hasn't ever been properly
+  tested, doesn't entirely work, and as far as I can tell is
+  completely unused by anyone.**
+
+* Move testsuite to ``py.test``.
+
+* **Fix #124: move to webencodings for decoding the input byte stream;
+  this makes html5lib compliant with the Encoding Standard, and
+  introduces a required dependency on webencodings.**
+
+* **Cease supporting Python 3.2 (in both CPython and PyPy forms).**
+
+* **Fix comments containing double-dash with lxml 3.5 and above.**
+
+* **Use scripting disabled by default (as we don't implement
+  scripting).**
+
+* **Fix #11, avoiding the XSS bug potentially caused by serializer
+  allowing attribute values to be escaped out of in old browser versions,
+  changing the quote_attr_values option on serializer to take one of
+  three values, "always" (the old True value), "legacy" (the new option,
+  and the new default), and "spec" (the old False value, and the old
+  default).**
+
+* **Fix #72 by rewriting the sanitizer to apply only to treewalkers
+  (instead of the tokenizer); as such, this will require amending all
+  callers of it to use it via the treewalker API.**
+
+* **Drop support of charade, now that chardet is supported once more.**
+
+* **Replace the charset keyword argument on parse and related methods
+  with a set of keyword arguments: override_encoding, transport_encoding,
+  same_origin_parent_encoding, likely_encoding, and default_encoding.**
+
+* **Move filters._base, treebuilder._base, and treewalkers._base to .base
+  to clarify their status as public.**
+
+* **Get rid of the sanitizer package. Merge sanitizer.sanitize into the
+  sanitizer.htmlsanitizer module and move that to saniziter. This means
+  anyone who used sanitizer.sanitize or sanitizer.HTMLSanitizer needs no
+  code changes.**
+
+* **Rename treewalkers.lxmletree to .etree_lxml and
+  treewalkers.genshistream to .genshi to have a consistent API.**
+
+* Move a whole load of stuff (inputstream, ihatexml, trie, tokenizer,
+  utils) to be underscore prefixed to clarify their status as private.
+
+
+0.9999999/1.0b8
+~~~~~~~~~~~~~~~
+
+Released on September 10, 2015
+
+* Fix #195: fix the sanitizer to drop broken URLs (it threw an
+  exception between 0.9999 and 0.999999).
+
+
+0.999999/1.0b7
+~~~~~~~~~~~~~~
+
+Released on July 7, 2015
+
+* Fix #189: fix the sanitizer to allow relative URLs again (as it did
+  prior to 0.9999/1.0b5).
+
+
+0.99999/1.0b6
+~~~~~~~~~~~~~
+
+Released on April 30, 2015
+
+* Fix #188: fix the sanitizer to not throw an exception when sanitizing
+  bogus data URLs.
+
+
+0.9999/1.0b5
+~~~~~~~~~~~~
+
+Released on April 29, 2015
+
+* Fix #153: Sanitizer fails to treat some attributes as URLs. Despite how
+  this sounds, this has no known security implications.  No known version
+  of IE (5.5 to current), Firefox (3 to current), Safari (6 to current),
+  Chrome (1 to current), or Opera (12 to current) will run any script
+  provided in these attributes.
+
+* Pass error message to the ParseError exception in strict parsing mode.
+
+* Allow data URIs in the sanitizer, with a whitelist of content-types.
+
+* Add support for Python implementations that don't support lone
+  surrogates (read: Jython). Fixes #2.
+
+* Remove localization of error messages. This functionality was totally
+  unused (and untested that everything was localizable), so we may as
+  well follow numerous browsers in not supporting translating technical
+  strings.
 
-Released on XXX, 2014
+* Expose treewalkers.pprint as a public API.
 
-* Fix #XXX: added the seamless attribute for iframes.
+* Add a documentEncoding property to HTML5Parser, fix #121.
 
 
 0.999
@@ -126,7 +248,7 @@ Released on May 17, 2013
 
 * Test harness has been improved and now depends on ``nose``.
 
-* Documentation updated and moved to http://html5lib.readthedocs.org/.
+* Documentation updated and moved to https://html5lib.readthedocs.io/.
 
 
 0.95

CHANGES.rst

@@ -1,6 +1,10 @@
 include LICENSE
+include AUTHORS.rst
 include CHANGES.rst
 include README.rst
 include requirements*.txt
+include .pytest.expect
+include tox.ini
+include pytest.ini
 graft html5lib/tests/testdata
 recursive-include html5lib/tests *.py