diff --git a/lib/bleach/__init__.py b/lib/bleach/__init__.py
index aec2d340..d619fb2c 100644
--- a/lib/bleach/__init__.py
+++ b/lib/bleach/__init__.py
@@ -1,401 +1,131 @@
# -*- coding: utf-8 -*-
-from __future__ import unicode_literals
-import logging
-import re
+import packaging.version
-import html5lib
-from html5lib.sanitizer import HTMLSanitizer
-from html5lib.serializer.htmlserializer import HTMLSerializer
-
-from . import callbacks as linkify_callbacks
-from .encoding import force_unicode
-from .sanitizer import BleachSanitizer
+from bleach.linkifier import (
+ DEFAULT_CALLBACKS,
+ Linker,
+)
+from bleach.sanitizer import (
+ ALLOWED_ATTRIBUTES,
+ ALLOWED_PROTOCOLS,
+ ALLOWED_STYLES,
+ ALLOWED_TAGS,
+ Cleaner,
+)
-VERSION = (1, 4, 2)
-__version__ = '.'.join([str(n) for n in VERSION])
-
-__all__ = ['clean', 'linkify']
-
-log = logging.getLogger('bleach')
-
-ALLOWED_TAGS = [
- 'a',
- 'abbr',
- 'acronym',
- 'b',
- 'blockquote',
- 'code',
- 'em',
- 'i',
- 'li',
- 'ol',
- 'strong',
- 'ul',
-]
-
-ALLOWED_ATTRIBUTES = {
- 'a': ['href', 'title'],
- 'abbr': ['title'],
- 'acronym': ['title'],
-}
-
-ALLOWED_STYLES = []
-
-ALLOWED_PROTOCOLS = ['http', 'https', 'mailto']
-
-TLDS = """ac ad ae aero af ag ai al am an ao aq ar arpa as asia at au aw ax az
- ba bb bd be bf bg bh bi biz bj bm bn bo br bs bt bv bw by bz ca cat
- cc cd cf cg ch ci ck cl cm cn co com coop cr cu cv cx cy cz de dj dk
- dm do dz ec edu ee eg er es et eu fi fj fk fm fo fr ga gb gd ge gf gg
- gh gi gl gm gn gov gp gq gr gs gt gu gw gy hk hm hn hr ht hu id ie il
- im in info int io iq ir is it je jm jo jobs jp ke kg kh ki km kn kp
- kr kw ky kz la lb lc li lk lr ls lt lu lv ly ma mc md me mg mh mil mk
- ml mm mn mo mobi mp mq mr ms mt mu museum mv mw mx my mz na name nc ne
- net nf ng ni nl no np nr nu nz om org pa pe pf pg ph pk pl pm pn post
- pr pro ps pt pw py qa re ro rs ru rw sa sb sc sd se sg sh si sj sk sl
- sm sn so sr ss st su sv sx sy sz tc td tel tf tg th tj tk tl tm tn to
- tp tr travel tt tv tw tz ua ug uk us uy uz va vc ve vg vi vn vu wf ws
- xn xxx ye yt yu za zm zw""".split()
-
-# Make sure that .com doesn't get matched by .co first
-TLDS.reverse()
-
-PROTOCOLS = HTMLSanitizer.acceptable_protocols
-
-url_re = re.compile(
- r"""\(* # Match any opening parentheses.
- \b(?"]*)?
- # /path/zz (excluding "unsafe" chars from RFC 1738,
- # except for # and ~, which happen in practice)
- """.format('|'.join(PROTOCOLS), '|'.join(TLDS)),
- re.IGNORECASE | re.VERBOSE | re.UNICODE)
-
-proto_re = re.compile(r'^[\w-]+:/{0,3}', re.IGNORECASE)
-
-punct_re = re.compile(r'([\.,]+)$')
-
-email_re = re.compile(
- r"""(? tag replaced by the text within it
- adj = replace_nodes(tree, _text, node,
- current_child)
- current_child -= 1
- # pull back current_child by 1 to scan the
- # new nodes again.
- else:
- text = force_unicode(attrs.pop('_text'))
- for attr_key, attr_val in attrs.items():
- node.set(attr_key, attr_val)
-
- for n in reversed(list(node)):
- node.remove(n)
- text = parser.parseFragment(text)
- node.text = text.text
- for n in text:
- node.append(n)
- _seen.add(node)
-
- elif current_child >= 0:
- if node.tag == ETREE_TAG('pre') and skip_pre:
- linkify_nodes(node, False)
- elif not (node in _seen):
- linkify_nodes(node, True)
-
- current_child += 1
-
- def email_repl(match):
- addr = match.group(0).replace('"', '"')
- link = {
- '_text': addr,
- 'href': 'mailto:{0!s}'.format(addr),
- }
- link = apply_callbacks(link, True)
-
- if link is None:
- return addr
-
- _href = link.pop('href')
- _text = link.pop('_text')
-
- repl = '{2!s} '
- attr = '{0!s}="{1!s}"'
- attribs = ' '.join(attr.format(k, v) for k, v in link.items())
- return repl.format(_href, attribs, _text)
-
- def link_repl(match):
- url = match.group(0)
- open_brackets = close_brackets = 0
- if url.startswith('('):
- _wrapping = strip_wrapping_parentheses(url)
- url, open_brackets, close_brackets = _wrapping
- end = ''
- m = re.search(punct_re, url)
- if m:
- end = m.group(0)
- url = url[0:m.start()]
- if re.search(proto_re, url):
- href = url
- else:
- href = ''.join(['http://', url])
-
- link = {
- '_text': url,
- 'href': href,
- }
-
- link = apply_callbacks(link, True)
-
- if link is None:
- return '(' * open_brackets + url + ')' * close_brackets
-
- _text = link.pop('_text')
- _href = link.pop('href')
-
- repl = '{0!s}{3!s} {4!s}{5!s}'
- attr = '{0!s}="{1!s}"'
- attribs = ' '.join(attr.format(k, v) for k, v in link.items())
-
- return repl.format('(' * open_brackets,
- _href, attribs, _text, end,
- ')' * close_brackets)
-
- try:
- linkify_nodes(forest)
- except RuntimeError as e:
- # If we hit the max recursion depth, just return what we've got.
- log.exception('Probable recursion error: {0!r}'.format(e))
-
- return _render(forest)
-
-
-def _render(tree):
- """Try rendering as HTML, then XML, then give up."""
- return force_unicode(_serialize(tree))
-
-
-def _serialize(domtree):
- walker = html5lib.treewalkers.getTreeWalker('etree')
- stream = walker(domtree)
- serializer = HTMLSerializer(quote_attr_values=True,
- alphabetical_attributes=True,
- omit_optional_tags=False)
- return serializer.render(stream)
+ linker = Linker(callbacks=callbacks, skip_tags=skip_tags, parse_email=parse_email)
+ return linker.linkify(text)
diff --git a/lib/bleach/_vendor/README.rst b/lib/bleach/_vendor/README.rst
new file mode 100644
index 00000000..e53aede0
--- /dev/null
+++ b/lib/bleach/_vendor/README.rst
@@ -0,0 +1,61 @@
+=======================
+Vendored library policy
+=======================
+
+To simplify Bleach development, we're now vendoring certain libraries that
+we use.
+
+Vendored libraries must follow these rules:
+
+1. Vendored libraries must be pure Python--no compiling.
+2. Source code for the libary is included in this directory.
+3. License must be included in this repo and in the Bleach distribution.
+4. Requirements of the library become requirements of Bleach.
+5. No modifications to the library may be made.
+
+
+Adding/Updating a vendored library
+==================================
+
+Way to vendor a library or update a version:
+
+1. Update ``vendor.txt`` with the library, version, and hash. You can use
+ `hashin Hello World!")
+
+By default, the ``document`` will be an ``xml.etree`` element instance.
+Whenever possible, html5lib chooses the accelerated ``ElementTree``
+implementation (i.e. ``xml.etree.cElementTree`` on Python 2.x).
+
+Two other tree types are supported: ``xml.dom.minidom`` and
+``lxml.etree``. To use an alternative format, specify the name of
+a treebuilder:
+
+.. code-block:: python
+
+ import html5lib
+ with open("mydocument.html", "rb") as f:
+ lxml_etree_document = html5lib.parse(f, treebuilder="lxml")
+
+When using with ``urllib2`` (Python 2), the charset from HTTP should be
+pass into html5lib as follows:
+
+.. code-block:: python
+
+ from contextlib import closing
+ from urllib2 import urlopen
+ import html5lib
+
+ with closing(urlopen("http://example.com/")) as f:
+ document = html5lib.parse(f, transport_encoding=f.info().getparam("charset"))
+
+When using with ``urllib.request`` (Python 3), the charset from HTTP
+should be pass into html5lib as follows:
+
+.. code-block:: python
+
+ from urllib.request import urlopen
+ import html5lib
+
+ with urlopen("http://example.com/") as f:
+ document = html5lib.parse(f, transport_encoding=f.info().get_content_charset())
+
+To have more control over the parser, create a parser object explicitly.
+For instance, to make the parser raise exceptions on parse errors, use:
+
+.. code-block:: python
+
+ import html5lib
+ with open("mydocument.html", "rb") as f:
+ parser = html5lib.HTMLParser(strict=True)
+ document = parser.parse(f)
+
+When you're instantiating parser objects explicitly, pass a treebuilder
+class as the ``tree`` keyword argument to use an alternative document
+format:
+
+.. code-block:: python
+
+ import html5lib
+ parser = html5lib.HTMLParser(tree=html5lib.getTreeBuilder("dom"))
+ minidom_document = parser.parse("
Hello World!")
+
+More documentation is available at https://html5lib.readthedocs.io/.
+
+
+Installation
+------------
+
+html5lib works on CPython 2.7+, CPython 3.5+ and PyPy. To install:
+
+.. code-block:: bash
+
+ $ pip install html5lib
+
+The goal is to support a (non-strict) superset of the versions that `pip
+supports
+`_.
+
+Optional Dependencies
+---------------------
+
+The following third-party libraries may be used for additional
+functionality:
+
+- ``lxml`` is supported as a tree format (for both building and
+ walking) under CPython (but *not* PyPy where it is known to cause
+ segfaults);
+
+- ``genshi`` has a treewalker (but not builder); and
+
+- ``chardet`` can be used as a fallback when character encoding cannot
+ be determined.
+
+
+Bugs
+----
+
+Please report any bugs on the `issue tracker
+`_.
+
+
+Tests
+-----
+
+Unit tests require the ``pytest`` and ``mock`` libraries and can be
+run using the ``py.test`` command in the root directory.
+
+Test data are contained in a separate `html5lib-tests
+`_ repository and included
+as a submodule, thus for git checkouts they must be initialized::
+
+ $ git submodule init
+ $ git submodule update
+
+If you have all compatible Python implementations available on your
+system, you can run tests on all of them using the ``tox`` utility,
+which can be found on PyPI.
+
+
+Questions?
+----------
+
+There's a mailing list available for support on Google Groups,
+`html5lib-discuss `_,
+though you may get a quicker response asking on IRC in `#whatwg on
+irc.freenode.net `_.
+
+Change Log
+----------
+
+1.1
+~~~
+
+UNRELEASED
+
+Breaking changes:
+
+* Drop support for Python 3.3. (#358)
+* Drop support for Python 3.4. (#421)
+
+Deprecations:
+
+* Deprecate the ``html5lib`` sanitizer (``html5lib.serialize(sanitize=True)`` and
+ ``html5lib.filters.sanitizer``). We recommend users migrate to `Bleach
+ `. Please let us know if Bleach doesn't suffice for your
+ use. (#443)
+
+Other changes:
+
+* Try to import from ``collections.abc`` to remove DeprecationWarning and ensure
+ ``html5lib`` keeps working in future Python versions. (#403)
+* Drop optional ``datrie`` dependency. (#442)
+
+
+1.0.1
+~~~~~
+
+Released on December 7, 2017
+
+Breaking changes:
+
+* Drop support for Python 2.6. (#330) (Thank you, Hugo, Will Kahn-Greene!)
+* Remove ``utils/spider.py`` (#353) (Thank you, Jon Dufresne!)
+
+Features:
+
+* Improve documentation. (#300, #307) (Thank you, Jon Dufresne, Tom Most,
+ Will Kahn-Greene!)
+* Add iframe seamless boolean attribute. (Thank you, Ritwik Gupta!)
+* Add itemscope as a boolean attribute. (#194) (Thank you, Jonathan Vanasco!)
+* Support Python 3.6. (#333) (Thank you, Jon Dufresne!)
+* Add CI support for Windows using AppVeyor. (Thank you, John Vandenberg!)
+* Improve testing and CI and add code coverage (#323, #334), (Thank you, Jon
+ Dufresne, John Vandenberg, Sam Sneddon, Will Kahn-Greene!)
+* Semver-compliant version number.
+
+Bug fixes:
+
+* Add support for setuptools < 18.5 to support environment markers. (Thank you,
+ John Vandenberg!)
+* Add explicit dependency for six >= 1.9. (Thank you, Eric Amorde!)
+* Fix regexes to work with Python 3.7 regex adjustments. (#318, #379) (Thank
+ you, Benedikt Morbach, Ville Skyttä, Mark Vasilkov!)
+* Fix alphabeticalattributes filter namespace bug. (#324) (Thank you, Will
+ Kahn-Greene!)
+* Include license file in generated wheel package. (#350) (Thank you, Jon
+ Dufresne!)
+* Fix annotation-xml typo. (#339) (Thank you, Will Kahn-Greene!)
+* Allow uppercase hex chararcters in CSS colour check. (#377) (Thank you,
+ Komal Dembla, Hugo!)
+
+
+1.0
+~~~
+
+Released and unreleased on December 7, 2017. Badly packaged release.
+
+
+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 sanitizer. 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.
+
+* Expose treewalkers.pprint as a public API.
+
+* Add a documentEncoding property to HTML5Parser, fix #121.
+
+
+0.999
+~~~~~
+
+Released on December 23, 2013
+
+* Fix #127: add work-around for CPython issue #20007: .read(0) on
+ http.client.HTTPResponse drops the rest of the content.
+
+* Fix #115: lxml treewalker can now deal with fragments containing, at
+ their root level, text nodes with non-ASCII characters on Python 2.
+
+
+0.99
+~~~~
+
+Released on September 10, 2013
+
+* No library changes from 1.0b3; released as 0.99 as pip has changed
+ behaviour from 1.4 to avoid installing pre-release versions per
+ PEP 440.
+
+
+1.0b3
+~~~~~
+
+Released on July 24, 2013
+
+* Removed ``RecursiveTreeWalker`` from ``treewalkers._base``. Any
+ implementation using it should be moved to
+ ``NonRecursiveTreeWalker``, as everything bundled with html5lib has
+ for years.
+
+* Fix #67 so that ``BufferedStream`` to correctly returns a bytes
+ object, thereby fixing any case where html5lib is passed a
+ non-seekable RawIOBase-like object.
+
+
+1.0b2
+~~~~~
+
+Released on June 27, 2013
+
+* Removed reordering of attributes within the serializer. There is now
+ an ``alphabetical_attributes`` option which preserves the previous
+ behaviour through a new filter. This allows attribute order to be
+ preserved through html5lib if the tree builder preserves order.
+
+* Removed ``dom2sax`` from DOM treebuilders. It has been replaced by
+ ``treeadapters.sax.to_sax`` which is generic and supports any
+ treewalker; it also resolves all known bugs with ``dom2sax``.
+
+* Fix treewalker assertions on hitting bytes strings on
+ Python 2. Previous to 1.0b1, treewalkers coped with mixed
+ bytes/unicode data on Python 2; this reintroduces this prior
+ behaviour on Python 2. Behaviour is unchanged on Python 3.
+
+
+1.0b1
+~~~~~
+
+Released on May 17, 2013
+
+* Implementation updated to implement the `HTML specification
+ causes infinite loop;
+
+ * `Google Code 215
+ `_: Properly
+ detect seekable streams;
+
+ * `Google Code 206
+ `_: add
+ support for , ;
+
+ * `Google Code 205
+ `_: add
+ support for ;
+
+ * `Google Code 202
+ `_: Unicode
+ file breaks InputStream.
+
+* Source code is now mostly PEP 8 compliant.
+
+* Test harness has been improved and now depends on ``nose``.
+
+* Documentation updated and moved to https://html5lib.readthedocs.io/.
+
+
+0.95
+~~~~
+
+Released on February 11, 2012
+
+
+0.90
+~~~~
+
+Released on January 17, 2010
+
+
+0.11.1
+~~~~~~
+
+Released on June 12, 2008
+
+
+0.11
+~~~~
+
+Released on June 10, 2008
+
+
+0.10
+~~~~
+
+Released on October 7, 2007
+
+
+0.9
+~~~
+
+Released on March 11, 2007
+
+
+0.2
+~~~
+
+Released on January 8, 2007
+
+
diff --git a/lib/bleach/_vendor/html5lib-1.1.dist-info/RECORD b/lib/bleach/_vendor/html5lib-1.1.dist-info/RECORD
new file mode 100644
index 00000000..cabdc1de
--- /dev/null
+++ b/lib/bleach/_vendor/html5lib-1.1.dist-info/RECORD
@@ -0,0 +1,41 @@
+html5lib-1.1.dist-info/AUTHORS.rst,sha256=DrNAMifoDpuQyJn-KW-H6K8Tt2a5rKnV2UF4-DRrGUI,983
+html5lib-1.1.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+html5lib-1.1.dist-info/LICENSE,sha256=FqOZkWGekvGGgJMtoqkZn999ld8-yu3FLqBiGKq6_W8,1084
+html5lib-1.1.dist-info/METADATA,sha256=Y3w-nd_22HQnQRy3yypVsV_ke2FF94uUD4-vGpc2DnI,16076
+html5lib-1.1.dist-info/RECORD,,
+html5lib-1.1.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+html5lib-1.1.dist-info/WHEEL,sha256=kGT74LWyRUZrL4VgLh6_g12IeVl_9u9ZVhadrgXZUEY,110
+html5lib-1.1.dist-info/top_level.txt,sha256=XEX6CHpskSmvjJB4tP6m4Q5NYXhIf_0ceMc0PNbzJPQ,9
+html5lib/__init__.py,sha256=pWnYcfZ69wNLrdQL7bpr49FUi8O8w0KhKCOHsyRgYGQ,1143
+html5lib/_ihatexml.py,sha256=ifOwF7pXqmyThIXc3boWc96s4MDezqRrRVp7FwDYUFs,16728
+html5lib/_inputstream.py,sha256=IKuMiY8rzb7pqIGCpbvTqsxysLEpgEHWYvYEFu4LUAI,32300
+html5lib/_tokenizer.py,sha256=WvJQa2Mli4NtTmhLXkX8Jy5FcWttqCaiDTiKyaw8D-k,77028
+html5lib/_trie/__init__.py,sha256=nqfgO910329BEVJ5T4psVwQtjd2iJyEXQ2-X8c1YxwU,109
+html5lib/_trie/_base.py,sha256=CaybYyMro8uERQYjby2tTeSUatnWDfWroUN9N7ety5w,1013
+html5lib/_trie/py.py,sha256=zg7RZSHxJ8mLmuI_7VEIV8AomISrgkvqCP477AgXaG0,1763
+html5lib/_utils.py,sha256=AxAJSG15eyarCgKMnlUwzs1X6jFHXqEvhlYEOxAFmis,4919
+html5lib/constants.py,sha256=Ll-yzLU_jcjyAI_h57zkqZ7aQWE5t5xA4y_jQgoUUhw,83464
+html5lib/filters/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+html5lib/filters/alphabeticalattributes.py,sha256=lViZc2JMCclXi_5gduvmdzrRxtO5Xo9ONnbHBVCsykU,919
+html5lib/filters/base.py,sha256=z-IU9ZAYjpsVsqmVt7kuWC63jR11hDMr6CVrvuao8W0,286
+html5lib/filters/inject_meta_charset.py,sha256=egDXUEHXmAG9504xz0K6ALDgYkvUrC2q15YUVeNlVQg,2945
+html5lib/filters/lint.py,sha256=upXATs6By7cot7o0bnNqR15sPq2Fn6Vnjvoy3gyO_rY,3631
+html5lib/filters/optionaltags.py,sha256=8lWT75J0aBOHmPgfmqTHSfPpPMp01T84NKu0CRedxcE,10588
+html5lib/filters/sanitizer.py,sha256=XGNSdzIqDTaHot1V-rRj1V_XOolApJ7n95tHP9JcgNU,26885
+html5lib/filters/whitespace.py,sha256=8eWqZxd4UC4zlFGW6iyY6f-2uuT8pOCSALc3IZt7_t4,1214
+html5lib/html5parser.py,sha256=w5hZJh0cvD3g4CS196DiTmuGpSKCMYe1GS46-yf_WZQ,117174
+html5lib/serializer.py,sha256=K2kfoLyMPMFPfdusfR30SrxNkf0mJB92-P5_RntyaaI,15747
+html5lib/treeadapters/__init__.py,sha256=18hyI-at2aBsdKzpwRwa5lGF1ipgctaTYXoU9En2ZQg,650
+html5lib/treeadapters/genshi.py,sha256=CH27pAsDKmu4ZGkAUrwty7u0KauGLCZRLPMzaO3M5vo,1715
+html5lib/treeadapters/sax.py,sha256=BKS8woQTnKiqeffHsxChUqL4q2ZR_wb5fc9MJ3zQC8s,1776
+html5lib/treebuilders/__init__.py,sha256=AysSJyvPfikCMMsTVvaxwkgDieELD5dfR8FJIAuq7hY,3592
+html5lib/treebuilders/base.py,sha256=oeZNGEB-kt90YJGVH05gb5a8E7ids2AbYwGRsVCieWk,14553
+html5lib/treebuilders/dom.py,sha256=22whb0C71zXIsai5mamg6qzBEiigcBIvaDy4Asw3at0,8925
+html5lib/treebuilders/etree.py,sha256=EbmHx-wQ-11MVucTPtF7Ul92-mQGN3Udu_KfDn-Ifhk,12824
+html5lib/treebuilders/etree_lxml.py,sha256=OazDHZGO_q4FnVs4Dhs4hzzn2JwGAOs-rfV8LAlUGW4,14754
+html5lib/treewalkers/__init__.py,sha256=OBPtc1TU5mGyy18QDMxKEyYEz0wxFUUNj5v0-XgmYhY,5719
+html5lib/treewalkers/base.py,sha256=ouiOsuSzvI0KgzdWP8PlxIaSNs9falhbiinAEc_UIJY,7476
+html5lib/treewalkers/dom.py,sha256=EHyFR8D8lYNnyDU9lx_IKigVJRyecUGua0mOi7HBukc,1413
+html5lib/treewalkers/etree.py,sha256=gkD4tfEfRWPsEGvgHHJxZmKZXUvBzVVGz3v5C_MIiOE,4539
+html5lib/treewalkers/etree_lxml.py,sha256=eLedbn6nPjlpebibsWVijey7WEpzDwxU3ubwUoudBuA,6345
+html5lib/treewalkers/genshi.py,sha256=4D2PECZ5n3ZN3qu3jMl9yY7B81jnQApBQSVlfaIuYbA,2309
diff --git a/lib/bleach/_vendor/html5lib-1.1.dist-info/WHEEL b/lib/bleach/_vendor/html5lib-1.1.dist-info/WHEEL
new file mode 100644
index 00000000..ef99c6cf
--- /dev/null
+++ b/lib/bleach/_vendor/html5lib-1.1.dist-info/WHEEL
@@ -0,0 +1,6 @@
+Wheel-Version: 1.0
+Generator: bdist_wheel (0.34.2)
+Root-Is-Purelib: true
+Tag: py2-none-any
+Tag: py3-none-any
+
diff --git a/lib/bleach/_vendor/html5lib-1.1.dist-info/top_level.txt b/lib/bleach/_vendor/html5lib-1.1.dist-info/top_level.txt
new file mode 100644
index 00000000..6bcef8ab
--- /dev/null
+++ b/lib/bleach/_vendor/html5lib-1.1.dist-info/top_level.txt
@@ -0,0 +1 @@
+html5lib
diff --git a/lib/bleach/_vendor/html5lib/__init__.py b/lib/bleach/_vendor/html5lib/__init__.py
new file mode 100644
index 00000000..320e0c3b
--- /dev/null
+++ b/lib/bleach/_vendor/html5lib/__init__.py
@@ -0,0 +1,35 @@
+"""
+HTML parsing library based on the `WHATWG HTML specification
+`_. The parser is designed to be compatible with
+existing HTML found in the wild and implements well-defined error recovery that
+is largely compatible with modern desktop web browsers.
+
+Example usage::
+
+ import html5lib
+ with open("my_document.html", "rb") as f:
+ tree = html5lib.parse(f)
+
+For convenience, this module re-exports the following names:
+
+* :func:`~.html5parser.parse`
+* :func:`~.html5parser.parseFragment`
+* :class:`~.html5parser.HTMLParser`
+* :func:`~.treebuilders.getTreeBuilder`
+* :func:`~.treewalkers.getTreeWalker`
+* :func:`~.serializer.serialize`
+"""
+
+from __future__ import absolute_import, division, unicode_literals
+
+from .html5parser import HTMLParser, parse, parseFragment
+from .treebuilders import getTreeBuilder
+from .treewalkers import getTreeWalker
+from .serializer import serialize
+
+__all__ = ["HTMLParser", "parse", "parseFragment", "getTreeBuilder",
+ "getTreeWalker", "serialize"]
+
+# this has to be at the top level, see how setup.py parses this
+#: Distribution version number.
+__version__ = "1.1"
diff --git a/lib/bleach/_vendor/html5lib/_ihatexml.py b/lib/bleach/_vendor/html5lib/_ihatexml.py
new file mode 100644
index 00000000..3ff803c1
--- /dev/null
+++ b/lib/bleach/_vendor/html5lib/_ihatexml.py
@@ -0,0 +1,289 @@
+from __future__ import absolute_import, division, unicode_literals
+
+import re
+import warnings
+
+from .constants import DataLossWarning
+
+baseChar = """
+[#x0041-#x005A] | [#x0061-#x007A] | [#x00C0-#x00D6] | [#x00D8-#x00F6] |
+[#x00F8-#x00FF] | [#x0100-#x0131] | [#x0134-#x013E] | [#x0141-#x0148] |
+[#x014A-#x017E] | [#x0180-#x01C3] | [#x01CD-#x01F0] | [#x01F4-#x01F5] |
+[#x01FA-#x0217] | [#x0250-#x02A8] | [#x02BB-#x02C1] | #x0386 |
+[#x0388-#x038A] | #x038C | [#x038E-#x03A1] | [#x03A3-#x03CE] |
+[#x03D0-#x03D6] | #x03DA | #x03DC | #x03DE | #x03E0 | [#x03E2-#x03F3] |
+[#x0401-#x040C] | [#x040E-#x044F] | [#x0451-#x045C] | [#x045E-#x0481] |
+[#x0490-#x04C4] | [#x04C7-#x04C8] | [#x04CB-#x04CC] | [#x04D0-#x04EB] |
+[#x04EE-#x04F5] | [#x04F8-#x04F9] | [#x0531-#x0556] | #x0559 |
+[#x0561-#x0586] | [#x05D0-#x05EA] | [#x05F0-#x05F2] | [#x0621-#x063A] |
+[#x0641-#x064A] | [#x0671-#x06B7] | [#x06BA-#x06BE] | [#x06C0-#x06CE] |
+[#x06D0-#x06D3] | #x06D5 | [#x06E5-#x06E6] | [#x0905-#x0939] | #x093D |
+[#x0958-#x0961] | [#x0985-#x098C] | [#x098F-#x0990] | [#x0993-#x09A8] |
+[#x09AA-#x09B0] | #x09B2 | [#x09B6-#x09B9] | [#x09DC-#x09DD] |
+[#x09DF-#x09E1] | [#x09F0-#x09F1] | [#x0A05-#x0A0A] | [#x0A0F-#x0A10] |
+[#x0A13-#x0A28] | [#x0A2A-#x0A30] | [#x0A32-#x0A33] | [#x0A35-#x0A36] |
+[#x0A38-#x0A39] | [#x0A59-#x0A5C] | #x0A5E | [#x0A72-#x0A74] |
+[#x0A85-#x0A8B] | #x0A8D | [#x0A8F-#x0A91] | [#x0A93-#x0AA8] |
+[#x0AAA-#x0AB0] | [#x0AB2-#x0AB3] | [#x0AB5-#x0AB9] | #x0ABD | #x0AE0 |
+[#x0B05-#x0B0C] | [#x0B0F-#x0B10] | [#x0B13-#x0B28] | [#x0B2A-#x0B30] |
+[#x0B32-#x0B33] | [#x0B36-#x0B39] | #x0B3D | [#x0B5C-#x0B5D] |
+[#x0B5F-#x0B61] | [#x0B85-#x0B8A] | [#x0B8E-#x0B90] | [#x0B92-#x0B95] |
+[#x0B99-#x0B9A] | #x0B9C | [#x0B9E-#x0B9F] | [#x0BA3-#x0BA4] |
+[#x0BA8-#x0BAA] | [#x0BAE-#x0BB5] | [#x0BB7-#x0BB9] | [#x0C05-#x0C0C] |
+[#x0C0E-#x0C10] | [#x0C12-#x0C28] | [#x0C2A-#x0C33] | [#x0C35-#x0C39] |
+[#x0C60-#x0C61] | [#x0C85-#x0C8C] | [#x0C8E-#x0C90] | [#x0C92-#x0CA8] |
+[#x0CAA-#x0CB3] | [#x0CB5-#x0CB9] | #x0CDE | [#x0CE0-#x0CE1] |
+[#x0D05-#x0D0C] | [#x0D0E-#x0D10] | [#x0D12-#x0D28] | [#x0D2A-#x0D39] |
+[#x0D60-#x0D61] | [#x0E01-#x0E2E] | #x0E30 | [#x0E32-#x0E33] |
+[#x0E40-#x0E45] | [#x0E81-#x0E82] | #x0E84 | [#x0E87-#x0E88] | #x0E8A |
+#x0E8D | [#x0E94-#x0E97] | [#x0E99-#x0E9F] | [#x0EA1-#x0EA3] | #x0EA5 |
+#x0EA7 | [#x0EAA-#x0EAB] | [#x0EAD-#x0EAE] | #x0EB0 | [#x0EB2-#x0EB3] |
+#x0EBD | [#x0EC0-#x0EC4] | [#x0F40-#x0F47] | [#x0F49-#x0F69] |
+[#x10A0-#x10C5] | [#x10D0-#x10F6] | #x1100 | [#x1102-#x1103] |
+[#x1105-#x1107] | #x1109 | [#x110B-#x110C] | [#x110E-#x1112] | #x113C |
+#x113E | #x1140 | #x114C | #x114E | #x1150 | [#x1154-#x1155] | #x1159 |
+[#x115F-#x1161] | #x1163 | #x1165 | #x1167 | #x1169 | [#x116D-#x116E] |
+[#x1172-#x1173] | #x1175 | #x119E | #x11A8 | #x11AB | [#x11AE-#x11AF] |
+[#x11B7-#x11B8] | #x11BA | [#x11BC-#x11C2] | #x11EB | #x11F0 | #x11F9 |
+[#x1E00-#x1E9B] | [#x1EA0-#x1EF9] | [#x1F00-#x1F15] | [#x1F18-#x1F1D] |
+[#x1F20-#x1F45] | [#x1F48-#x1F4D] | [#x1F50-#x1F57] | #x1F59 | #x1F5B |
+#x1F5D | [#x1F5F-#x1F7D] | [#x1F80-#x1FB4] | [#x1FB6-#x1FBC] | #x1FBE |
+[#x1FC2-#x1FC4] | [#x1FC6-#x1FCC] | [#x1FD0-#x1FD3] | [#x1FD6-#x1FDB] |
+[#x1FE0-#x1FEC] | [#x1FF2-#x1FF4] | [#x1FF6-#x1FFC] | #x2126 |
+[#x212A-#x212B] | #x212E | [#x2180-#x2182] | [#x3041-#x3094] |
+[#x30A1-#x30FA] | [#x3105-#x312C] | [#xAC00-#xD7A3]"""
+
+ideographic = """[#x4E00-#x9FA5] | #x3007 | [#x3021-#x3029]"""
+
+combiningCharacter = """
+[#x0300-#x0345] | [#x0360-#x0361] | [#x0483-#x0486] | [#x0591-#x05A1] |
+[#x05A3-#x05B9] | [#x05BB-#x05BD] | #x05BF | [#x05C1-#x05C2] | #x05C4 |
+[#x064B-#x0652] | #x0670 | [#x06D6-#x06DC] | [#x06DD-#x06DF] |
+[#x06E0-#x06E4] | [#x06E7-#x06E8] | [#x06EA-#x06ED] | [#x0901-#x0903] |
+#x093C | [#x093E-#x094C] | #x094D | [#x0951-#x0954] | [#x0962-#x0963] |
+[#x0981-#x0983] | #x09BC | #x09BE | #x09BF | [#x09C0-#x09C4] |
+[#x09C7-#x09C8] | [#x09CB-#x09CD] | #x09D7 | [#x09E2-#x09E3] | #x0A02 |
+#x0A3C | #x0A3E | #x0A3F | [#x0A40-#x0A42] | [#x0A47-#x0A48] |
+[#x0A4B-#x0A4D] | [#x0A70-#x0A71] | [#x0A81-#x0A83] | #x0ABC |
+[#x0ABE-#x0AC5] | [#x0AC7-#x0AC9] | [#x0ACB-#x0ACD] | [#x0B01-#x0B03] |
+#x0B3C | [#x0B3E-#x0B43] | [#x0B47-#x0B48] | [#x0B4B-#x0B4D] |
+[#x0B56-#x0B57] | [#x0B82-#x0B83] | [#x0BBE-#x0BC2] | [#x0BC6-#x0BC8] |
+[#x0BCA-#x0BCD] | #x0BD7 | [#x0C01-#x0C03] | [#x0C3E-#x0C44] |
+[#x0C46-#x0C48] | [#x0C4A-#x0C4D] | [#x0C55-#x0C56] | [#x0C82-#x0C83] |
+[#x0CBE-#x0CC4] | [#x0CC6-#x0CC8] | [#x0CCA-#x0CCD] | [#x0CD5-#x0CD6] |
+[#x0D02-#x0D03] | [#x0D3E-#x0D43] | [#x0D46-#x0D48] | [#x0D4A-#x0D4D] |
+#x0D57 | #x0E31 | [#x0E34-#x0E3A] | [#x0E47-#x0E4E] | #x0EB1 |
+[#x0EB4-#x0EB9] | [#x0EBB-#x0EBC] | [#x0EC8-#x0ECD] | [#x0F18-#x0F19] |
+#x0F35 | #x0F37 | #x0F39 | #x0F3E | #x0F3F | [#x0F71-#x0F84] |
+[#x0F86-#x0F8B] | [#x0F90-#x0F95] | #x0F97 | [#x0F99-#x0FAD] |
+[#x0FB1-#x0FB7] | #x0FB9 | [#x20D0-#x20DC] | #x20E1 | [#x302A-#x302F] |
+#x3099 | #x309A"""
+
+digit = """
+[#x0030-#x0039] | [#x0660-#x0669] | [#x06F0-#x06F9] | [#x0966-#x096F] |
+[#x09E6-#x09EF] | [#x0A66-#x0A6F] | [#x0AE6-#x0AEF] | [#x0B66-#x0B6F] |
+[#x0BE7-#x0BEF] | [#x0C66-#x0C6F] | [#x0CE6-#x0CEF] | [#x0D66-#x0D6F] |
+[#x0E50-#x0E59] | [#x0ED0-#x0ED9] | [#x0F20-#x0F29]"""
+
+extender = """
+#x00B7 | #x02D0 | #x02D1 | #x0387 | #x0640 | #x0E46 | #x0EC6 | #x3005 |
+#[#x3031-#x3035] | [#x309D-#x309E] | [#x30FC-#x30FE]"""
+
+letter = " | ".join([baseChar, ideographic])
+
+# Without the
+name = " | ".join([letter, digit, ".", "-", "_", combiningCharacter,
+ extender])
+nameFirst = " | ".join([letter, "_"])
+
+reChar = re.compile(r"#x([\d|A-F]{4,4})")
+reCharRange = re.compile(r"\[#x([\d|A-F]{4,4})-#x([\d|A-F]{4,4})\]")
+
+
+def charStringToList(chars):
+ charRanges = [item.strip() for item in chars.split(" | ")]
+ rv = []
+ for item in charRanges:
+ foundMatch = False
+ for regexp in (reChar, reCharRange):
+ match = regexp.match(item)
+ if match is not None:
+ rv.append([hexToInt(item) for item in match.groups()])
+ if len(rv[-1]) == 1:
+ rv[-1] = rv[-1] * 2
+ foundMatch = True
+ break
+ if not foundMatch:
+ assert len(item) == 1
+
+ rv.append([ord(item)] * 2)
+ rv = normaliseCharList(rv)
+ return rv
+
+
+def normaliseCharList(charList):
+ charList = sorted(charList)
+ for item in charList:
+ assert item[1] >= item[0]
+ rv = []
+ i = 0
+ while i < len(charList):
+ j = 1
+ rv.append(charList[i])
+ while i + j < len(charList) and charList[i + j][0] <= rv[-1][1] + 1:
+ rv[-1][1] = charList[i + j][1]
+ j += 1
+ i += j
+ return rv
+
+
+# We don't really support characters above the BMP :(
+max_unicode = int("FFFF", 16)
+
+
+def missingRanges(charList):
+ rv = []
+ if charList[0] != 0:
+ rv.append([0, charList[0][0] - 1])
+ for i, item in enumerate(charList[:-1]):
+ rv.append([item[1] + 1, charList[i + 1][0] - 1])
+ if charList[-1][1] != max_unicode:
+ rv.append([charList[-1][1] + 1, max_unicode])
+ return rv
+
+
+def listToRegexpStr(charList):
+ rv = []
+ for item in charList:
+ if item[0] == item[1]:
+ rv.append(escapeRegexp(chr(item[0])))
+ else:
+ rv.append(escapeRegexp(chr(item[0])) + "-" +
+ escapeRegexp(chr(item[1])))
+ return "[%s]" % "".join(rv)
+
+
+def hexToInt(hex_str):
+ return int(hex_str, 16)
+
+
+def escapeRegexp(string):
+ specialCharacters = (".", "^", "$", "*", "+", "?", "{", "}",
+ "[", "]", "|", "(", ")", "-")
+ for char in specialCharacters:
+ string = string.replace(char, "\\" + char)
+
+ return string
+
+# output from the above
+nonXmlNameBMPRegexp = re.compile('[\x00-,/:-@\\[-\\^`\\{-\xb6\xb8-\xbf\xd7\xf7\u0132-\u0133\u013f-\u0140\u0149\u017f\u01c4-\u01cc\u01f1-\u01f3\u01f6-\u01f9\u0218-\u024f\u02a9-\u02ba\u02c2-\u02cf\u02d2-\u02ff\u0346-\u035f\u0362-\u0385\u038b\u038d\u03a2\u03cf\u03d7-\u03d9\u03db\u03dd\u03df\u03e1\u03f4-\u0400\u040d\u0450\u045d\u0482\u0487-\u048f\u04c5-\u04c6\u04c9-\u04ca\u04cd-\u04cf\u04ec-\u04ed\u04f6-\u04f7\u04fa-\u0530\u0557-\u0558\u055a-\u0560\u0587-\u0590\u05a2\u05ba\u05be\u05c0\u05c3\u05c5-\u05cf\u05eb-\u05ef\u05f3-\u0620\u063b-\u063f\u0653-\u065f\u066a-\u066f\u06b8-\u06b9\u06bf\u06cf\u06d4\u06e9\u06ee-\u06ef\u06fa-\u0900\u0904\u093a-\u093b\u094e-\u0950\u0955-\u0957\u0964-\u0965\u0970-\u0980\u0984\u098d-\u098e\u0991-\u0992\u09a9\u09b1\u09b3-\u09b5\u09ba-\u09bb\u09bd\u09c5-\u09c6\u09c9-\u09ca\u09ce-\u09d6\u09d8-\u09db\u09de\u09e4-\u09e5\u09f2-\u0a01\u0a03-\u0a04\u0a0b-\u0a0e\u0a11-\u0a12\u0a29\u0a31\u0a34\u0a37\u0a3a-\u0a3b\u0a3d\u0a43-\u0a46\u0a49-\u0a4a\u0a4e-\u0a58\u0a5d\u0a5f-\u0a65\u0a75-\u0a80\u0a84\u0a8c\u0a8e\u0a92\u0aa9\u0ab1\u0ab4\u0aba-\u0abb\u0ac6\u0aca\u0ace-\u0adf\u0ae1-\u0ae5\u0af0-\u0b00\u0b04\u0b0d-\u0b0e\u0b11-\u0b12\u0b29\u0b31\u0b34-\u0b35\u0b3a-\u0b3b\u0b44-\u0b46\u0b49-\u0b4a\u0b4e-\u0b55\u0b58-\u0b5b\u0b5e\u0b62-\u0b65\u0b70-\u0b81\u0b84\u0b8b-\u0b8d\u0b91\u0b96-\u0b98\u0b9b\u0b9d\u0ba0-\u0ba2\u0ba5-\u0ba7\u0bab-\u0bad\u0bb6\u0bba-\u0bbd\u0bc3-\u0bc5\u0bc9\u0bce-\u0bd6\u0bd8-\u0be6\u0bf0-\u0c00\u0c04\u0c0d\u0c11\u0c29\u0c34\u0c3a-\u0c3d\u0c45\u0c49\u0c4e-\u0c54\u0c57-\u0c5f\u0c62-\u0c65\u0c70-\u0c81\u0c84\u0c8d\u0c91\u0ca9\u0cb4\u0cba-\u0cbd\u0cc5\u0cc9\u0cce-\u0cd4\u0cd7-\u0cdd\u0cdf\u0ce2-\u0ce5\u0cf0-\u0d01\u0d04\u0d0d\u0d11\u0d29\u0d3a-\u0d3d\u0d44-\u0d45\u0d49\u0d4e-\u0d56\u0d58-\u0d5f\u0d62-\u0d65\u0d70-\u0e00\u0e2f\u0e3b-\u0e3f\u0e4f\u0e5a-\u0e80\u0e83\u0e85-\u0e86\u0e89\u0e8b-\u0e8c\u0e8e-\u0e93\u0e98\u0ea0\u0ea4\u0ea6\u0ea8-\u0ea9\u0eac\u0eaf\u0eba\u0ebe-\u0ebf\u0ec5\u0ec7\u0ece-\u0ecf\u0eda-\u0f17\u0f1a-\u0f1f\u0f2a-\u0f34\u0f36\u0f38\u0f3a-\u0f3d\u0f48\u0f6a-\u0f70\u0f85\u0f8c-\u0f8f\u0f96\u0f98\u0fae-\u0fb0\u0fb8\u0fba-\u109f\u10c6-\u10cf\u10f7-\u10ff\u1101\u1104\u1108\u110a\u110d\u1113-\u113b\u113d\u113f\u1141-\u114b\u114d\u114f\u1151-\u1153\u1156-\u1158\u115a-\u115e\u1162\u1164\u1166\u1168\u116a-\u116c\u116f-\u1171\u1174\u1176-\u119d\u119f-\u11a7\u11a9-\u11aa\u11ac-\u11ad\u11b0-\u11b6\u11b9\u11bb\u11c3-\u11ea\u11ec-\u11ef\u11f1-\u11f8\u11fa-\u1dff\u1e9c-\u1e9f\u1efa-\u1eff\u1f16-\u1f17\u1f1e-\u1f1f\u1f46-\u1f47\u1f4e-\u1f4f\u1f58\u1f5a\u1f5c\u1f5e\u1f7e-\u1f7f\u1fb5\u1fbd\u1fbf-\u1fc1\u1fc5\u1fcd-\u1fcf\u1fd4-\u1fd5\u1fdc-\u1fdf\u1fed-\u1ff1\u1ff5\u1ffd-\u20cf\u20dd-\u20e0\u20e2-\u2125\u2127-\u2129\u212c-\u212d\u212f-\u217f\u2183-\u3004\u3006\u3008-\u3020\u3030\u3036-\u3040\u3095-\u3098\u309b-\u309c\u309f-\u30a0\u30fb\u30ff-\u3104\u312d-\u4dff\u9fa6-\uabff\ud7a4-\uffff]') # noqa
+
+nonXmlNameFirstBMPRegexp = re.compile('[\x00-@\\[-\\^`\\{-\xbf\xd7\xf7\u0132-\u0133\u013f-\u0140\u0149\u017f\u01c4-\u01cc\u01f1-\u01f3\u01f6-\u01f9\u0218-\u024f\u02a9-\u02ba\u02c2-\u0385\u0387\u038b\u038d\u03a2\u03cf\u03d7-\u03d9\u03db\u03dd\u03df\u03e1\u03f4-\u0400\u040d\u0450\u045d\u0482-\u048f\u04c5-\u04c6\u04c9-\u04ca\u04cd-\u04cf\u04ec-\u04ed\u04f6-\u04f7\u04fa-\u0530\u0557-\u0558\u055a-\u0560\u0587-\u05cf\u05eb-\u05ef\u05f3-\u0620\u063b-\u0640\u064b-\u0670\u06b8-\u06b9\u06bf\u06cf\u06d4\u06d6-\u06e4\u06e7-\u0904\u093a-\u093c\u093e-\u0957\u0962-\u0984\u098d-\u098e\u0991-\u0992\u09a9\u09b1\u09b3-\u09b5\u09ba-\u09db\u09de\u09e2-\u09ef\u09f2-\u0a04\u0a0b-\u0a0e\u0a11-\u0a12\u0a29\u0a31\u0a34\u0a37\u0a3a-\u0a58\u0a5d\u0a5f-\u0a71\u0a75-\u0a84\u0a8c\u0a8e\u0a92\u0aa9\u0ab1\u0ab4\u0aba-\u0abc\u0abe-\u0adf\u0ae1-\u0b04\u0b0d-\u0b0e\u0b11-\u0b12\u0b29\u0b31\u0b34-\u0b35\u0b3a-\u0b3c\u0b3e-\u0b5b\u0b5e\u0b62-\u0b84\u0b8b-\u0b8d\u0b91\u0b96-\u0b98\u0b9b\u0b9d\u0ba0-\u0ba2\u0ba5-\u0ba7\u0bab-\u0bad\u0bb6\u0bba-\u0c04\u0c0d\u0c11\u0c29\u0c34\u0c3a-\u0c5f\u0c62-\u0c84\u0c8d\u0c91\u0ca9\u0cb4\u0cba-\u0cdd\u0cdf\u0ce2-\u0d04\u0d0d\u0d11\u0d29\u0d3a-\u0d5f\u0d62-\u0e00\u0e2f\u0e31\u0e34-\u0e3f\u0e46-\u0e80\u0e83\u0e85-\u0e86\u0e89\u0e8b-\u0e8c\u0e8e-\u0e93\u0e98\u0ea0\u0ea4\u0ea6\u0ea8-\u0ea9\u0eac\u0eaf\u0eb1\u0eb4-\u0ebc\u0ebe-\u0ebf\u0ec5-\u0f3f\u0f48\u0f6a-\u109f\u10c6-\u10cf\u10f7-\u10ff\u1101\u1104\u1108\u110a\u110d\u1113-\u113b\u113d\u113f\u1141-\u114b\u114d\u114f\u1151-\u1153\u1156-\u1158\u115a-\u115e\u1162\u1164\u1166\u1168\u116a-\u116c\u116f-\u1171\u1174\u1176-\u119d\u119f-\u11a7\u11a9-\u11aa\u11ac-\u11ad\u11b0-\u11b6\u11b9\u11bb\u11c3-\u11ea\u11ec-\u11ef\u11f1-\u11f8\u11fa-\u1dff\u1e9c-\u1e9f\u1efa-\u1eff\u1f16-\u1f17\u1f1e-\u1f1f\u1f46-\u1f47\u1f4e-\u1f4f\u1f58\u1f5a\u1f5c\u1f5e\u1f7e-\u1f7f\u1fb5\u1fbd\u1fbf-\u1fc1\u1fc5\u1fcd-\u1fcf\u1fd4-\u1fd5\u1fdc-\u1fdf\u1fed-\u1ff1\u1ff5\u1ffd-\u2125\u2127-\u2129\u212c-\u212d\u212f-\u217f\u2183-\u3006\u3008-\u3020\u302a-\u3040\u3095-\u30a0\u30fb-\u3104\u312d-\u4dff\u9fa6-\uabff\ud7a4-\uffff]') # noqa
+
+# Simpler things
+nonPubidCharRegexp = re.compile("[^\x20\x0D\x0Aa-zA-Z0-9\\-'()+,./:=?;!*#@$_%]")
+
+
+class InfosetFilter(object):
+ replacementRegexp = re.compile(r"U[\dA-F]{5,5}")
+
+ def __init__(self,
+ dropXmlnsLocalName=False,
+ dropXmlnsAttrNs=False,
+ preventDoubleDashComments=False,
+ preventDashAtCommentEnd=False,
+ replaceFormFeedCharacters=True,
+ preventSingleQuotePubid=False):
+
+ self.dropXmlnsLocalName = dropXmlnsLocalName
+ self.dropXmlnsAttrNs = dropXmlnsAttrNs
+
+ self.preventDoubleDashComments = preventDoubleDashComments
+ self.preventDashAtCommentEnd = preventDashAtCommentEnd
+
+ self.replaceFormFeedCharacters = replaceFormFeedCharacters
+
+ self.preventSingleQuotePubid = preventSingleQuotePubid
+
+ self.replaceCache = {}
+
+ def coerceAttribute(self, name, namespace=None):
+ if self.dropXmlnsLocalName and name.startswith("xmlns:"):
+ warnings.warn("Attributes cannot begin with xmlns", DataLossWarning)
+ return None
+ elif (self.dropXmlnsAttrNs and
+ namespace == "http://www.w3.org/2000/xmlns/"):
+ warnings.warn("Attributes cannot be in the xml namespace", DataLossWarning)
+ return None
+ else:
+ return self.toXmlName(name)
+
+ def coerceElement(self, name):
+ return self.toXmlName(name)
+
+ def coerceComment(self, data):
+ if self.preventDoubleDashComments:
+ while "--" in data:
+ warnings.warn("Comments cannot contain adjacent dashes", DataLossWarning)
+ data = data.replace("--", "- -")
+ if data.endswith("-"):
+ warnings.warn("Comments cannot end in a dash", DataLossWarning)
+ data += " "
+ return data
+
+ def coerceCharacters(self, data):
+ if self.replaceFormFeedCharacters:
+ for _ in range(data.count("\x0C")):
+ warnings.warn("Text cannot contain U+000C", DataLossWarning)
+ data = data.replace("\x0C", " ")
+ # Other non-xml characters
+ return data
+
+ def coercePubid(self, data):
+ dataOutput = data
+ for char in nonPubidCharRegexp.findall(data):
+ warnings.warn("Coercing non-XML pubid", DataLossWarning)
+ replacement = self.getReplacementCharacter(char)
+ dataOutput = dataOutput.replace(char, replacement)
+ if self.preventSingleQuotePubid and dataOutput.find("'") >= 0:
+ warnings.warn("Pubid cannot contain single quote", DataLossWarning)
+ dataOutput = dataOutput.replace("'", self.getReplacementCharacter("'"))
+ return dataOutput
+
+ def toXmlName(self, name):
+ nameFirst = name[0]
+ nameRest = name[1:]
+ m = nonXmlNameFirstBMPRegexp.match(nameFirst)
+ if m:
+ warnings.warn("Coercing non-XML name: %s" % name, DataLossWarning)
+ nameFirstOutput = self.getReplacementCharacter(nameFirst)
+ else:
+ nameFirstOutput = nameFirst
+
+ nameRestOutput = nameRest
+ replaceChars = set(nonXmlNameBMPRegexp.findall(nameRest))
+ for char in replaceChars:
+ warnings.warn("Coercing non-XML name: %s" % name, DataLossWarning)
+ replacement = self.getReplacementCharacter(char)
+ nameRestOutput = nameRestOutput.replace(char, replacement)
+ return nameFirstOutput + nameRestOutput
+
+ def getReplacementCharacter(self, char):
+ if char in self.replaceCache:
+ replacement = self.replaceCache[char]
+ else:
+ replacement = self.escapeChar(char)
+ return replacement
+
+ def fromXmlName(self, name):
+ for item in set(self.replacementRegexp.findall(name)):
+ name = name.replace(item, self.unescapeChar(item))
+ return name
+
+ def escapeChar(self, char):
+ replacement = "U%05X" % ord(char)
+ self.replaceCache[char] = replacement
+ return replacement
+
+ def unescapeChar(self, charcode):
+ return chr(int(charcode[1:], 16))
diff --git a/lib/bleach/_vendor/html5lib/_inputstream.py b/lib/bleach/_vendor/html5lib/_inputstream.py
new file mode 100644
index 00000000..0207dd21
--- /dev/null
+++ b/lib/bleach/_vendor/html5lib/_inputstream.py
@@ -0,0 +1,918 @@
+from __future__ import absolute_import, division, unicode_literals
+
+from six import text_type
+from six.moves import http_client, urllib
+
+import codecs
+import re
+from io import BytesIO, StringIO
+
+import webencodings
+
+from .constants import EOF, spaceCharacters, asciiLetters, asciiUppercase
+from .constants import _ReparseException
+from . import _utils
+
+# Non-unicode versions of constants for use in the pre-parser
+spaceCharactersBytes = frozenset([item.encode("ascii") for item in spaceCharacters])
+asciiLettersBytes = frozenset([item.encode("ascii") for item in asciiLetters])
+asciiUppercaseBytes = frozenset([item.encode("ascii") for item in asciiUppercase])
+spacesAngleBrackets = spaceCharactersBytes | frozenset([b">", b"<"])
+
+
+invalid_unicode_no_surrogate = "[\u0001-\u0008\u000B\u000E-\u001F\u007F-\u009F\uFDD0-\uFDEF\uFFFE\uFFFF\U0001FFFE\U0001FFFF\U0002FFFE\U0002FFFF\U0003FFFE\U0003FFFF\U0004FFFE\U0004FFFF\U0005FFFE\U0005FFFF\U0006FFFE\U0006FFFF\U0007FFFE\U0007FFFF\U0008FFFE\U0008FFFF\U0009FFFE\U0009FFFF\U000AFFFE\U000AFFFF\U000BFFFE\U000BFFFF\U000CFFFE\U000CFFFF\U000DFFFE\U000DFFFF\U000EFFFE\U000EFFFF\U000FFFFE\U000FFFFF\U0010FFFE\U0010FFFF]" # noqa
+
+if _utils.supports_lone_surrogates:
+ # Use one extra step of indirection and create surrogates with
+ # eval. Not using this indirection would introduce an illegal
+ # unicode literal on platforms not supporting such lone
+ # surrogates.
+ assert invalid_unicode_no_surrogate[-1] == "]" and invalid_unicode_no_surrogate.count("]") == 1
+ invalid_unicode_re = re.compile(invalid_unicode_no_surrogate[:-1] +
+ eval('"\\uD800-\\uDFFF"') + # pylint:disable=eval-used
+ "]")
+else:
+ invalid_unicode_re = re.compile(invalid_unicode_no_surrogate)
+
+non_bmp_invalid_codepoints = {0x1FFFE, 0x1FFFF, 0x2FFFE, 0x2FFFF, 0x3FFFE,
+ 0x3FFFF, 0x4FFFE, 0x4FFFF, 0x5FFFE, 0x5FFFF,
+ 0x6FFFE, 0x6FFFF, 0x7FFFE, 0x7FFFF, 0x8FFFE,
+ 0x8FFFF, 0x9FFFE, 0x9FFFF, 0xAFFFE, 0xAFFFF,
+ 0xBFFFE, 0xBFFFF, 0xCFFFE, 0xCFFFF, 0xDFFFE,
+ 0xDFFFF, 0xEFFFE, 0xEFFFF, 0xFFFFE, 0xFFFFF,
+ 0x10FFFE, 0x10FFFF}
+
+ascii_punctuation_re = re.compile("[\u0009-\u000D\u0020-\u002F\u003A-\u0040\u005C\u005B-\u0060\u007B-\u007E]")
+
+# Cache for charsUntil()
+charsUntilRegEx = {}
+
+
+class BufferedStream(object):
+ """Buffering for streams that do not have buffering of their own
+
+ The buffer is implemented as a list of chunks on the assumption that
+ joining many strings will be slow since it is O(n**2)
+ """
+
+ def __init__(self, stream):
+ self.stream = stream
+ self.buffer = []
+ self.position = [-1, 0] # chunk number, offset
+
+ def tell(self):
+ pos = 0
+ for chunk in self.buffer[:self.position[0]]:
+ pos += len(chunk)
+ pos += self.position[1]
+ return pos
+
+ def seek(self, pos):
+ assert pos <= self._bufferedBytes()
+ offset = pos
+ i = 0
+ while len(self.buffer[i]) < offset:
+ offset -= len(self.buffer[i])
+ i += 1
+ self.position = [i, offset]
+
+ def read(self, bytes):
+ if not self.buffer:
+ return self._readStream(bytes)
+ elif (self.position[0] == len(self.buffer) and
+ self.position[1] == len(self.buffer[-1])):
+ return self._readStream(bytes)
+ else:
+ return self._readFromBuffer(bytes)
+
+ def _bufferedBytes(self):
+ return sum([len(item) for item in self.buffer])
+
+ def _readStream(self, bytes):
+ data = self.stream.read(bytes)
+ self.buffer.append(data)
+ self.position[0] += 1
+ self.position[1] = len(data)
+ return data
+
+ def _readFromBuffer(self, bytes):
+ remainingBytes = bytes
+ rv = []
+ bufferIndex = self.position[0]
+ bufferOffset = self.position[1]
+ while bufferIndex < len(self.buffer) and remainingBytes != 0:
+ assert remainingBytes > 0
+ bufferedData = self.buffer[bufferIndex]
+
+ if remainingBytes <= len(bufferedData) - bufferOffset:
+ bytesToRead = remainingBytes
+ self.position = [bufferIndex, bufferOffset + bytesToRead]
+ else:
+ bytesToRead = len(bufferedData) - bufferOffset
+ self.position = [bufferIndex, len(bufferedData)]
+ bufferIndex += 1
+ rv.append(bufferedData[bufferOffset:bufferOffset + bytesToRead])
+ remainingBytes -= bytesToRead
+
+ bufferOffset = 0
+
+ if remainingBytes:
+ rv.append(self._readStream(remainingBytes))
+
+ return b"".join(rv)
+
+
+def HTMLInputStream(source, **kwargs):
+ # Work around Python bug #20007: read(0) closes the connection.
+ # http://bugs.python.org/issue20007
+ if (isinstance(source, http_client.HTTPResponse) or
+ # Also check for addinfourl wrapping HTTPResponse
+ (isinstance(source, urllib.response.addbase) and
+ isinstance(source.fp, http_client.HTTPResponse))):
+ isUnicode = False
+ elif hasattr(source, "read"):
+ isUnicode = isinstance(source.read(0), text_type)
+ else:
+ isUnicode = isinstance(source, text_type)
+
+ if isUnicode:
+ encodings = [x for x in kwargs if x.endswith("_encoding")]
+ if encodings:
+ raise TypeError("Cannot set an encoding with a unicode input, set %r" % encodings)
+
+ return HTMLUnicodeInputStream(source, **kwargs)
+ else:
+ return HTMLBinaryInputStream(source, **kwargs)
+
+
+class HTMLUnicodeInputStream(object):
+ """Provides a unicode stream of characters to the HTMLTokenizer.
+
+ This class takes care of character encoding and removing or replacing
+ incorrect byte-sequences and also provides column and line tracking.
+
+ """
+
+ _defaultChunkSize = 10240
+
+ def __init__(self, source):
+ """Initialises the HTMLInputStream.
+
+ HTMLInputStream(source, [encoding]) -> Normalized stream from source
+ for use by html5lib.
+
+ source can be either a file-object, local filename or a string.
+
+ The optional encoding parameter must be a string that indicates
+ the encoding. If specified, that encoding will be used,
+ regardless of any BOM or later declaration (such as in a meta
+ element)
+
+ """
+
+ if not _utils.supports_lone_surrogates:
+ # Such platforms will have already checked for such
+ # surrogate errors, so no need to do this checking.
+ self.reportCharacterErrors = None
+ elif len("\U0010FFFF") == 1:
+ self.reportCharacterErrors = self.characterErrorsUCS4
+ else:
+ self.reportCharacterErrors = self.characterErrorsUCS2
+
+ # List of where new lines occur
+ self.newLines = [0]
+
+ self.charEncoding = (lookupEncoding("utf-8"), "certain")
+ self.dataStream = self.openStream(source)
+
+ self.reset()
+
+ def reset(self):
+ self.chunk = ""
+ self.chunkSize = 0
+ self.chunkOffset = 0
+ self.errors = []
+
+ # number of (complete) lines in previous chunks
+ self.prevNumLines = 0
+ # number of columns in the last line of the previous chunk
+ self.prevNumCols = 0
+
+ # Deal with CR LF and surrogates split over chunk boundaries
+ self._bufferedCharacter = None
+
+ def openStream(self, source):
+ """Produces a file object from source.
+
+ source can be either a file object, local filename or a string.
+
+ """
+ # Already a file object
+ if hasattr(source, 'read'):
+ stream = source
+ else:
+ stream = StringIO(source)
+
+ return stream
+
+ def _position(self, offset):
+ chunk = self.chunk
+ nLines = chunk.count('\n', 0, offset)
+ positionLine = self.prevNumLines + nLines
+ lastLinePos = chunk.rfind('\n', 0, offset)
+ if lastLinePos == -1:
+ positionColumn = self.prevNumCols + offset
+ else:
+ positionColumn = offset - (lastLinePos + 1)
+ return (positionLine, positionColumn)
+
+ def position(self):
+ """Returns (line, col) of the current position in the stream."""
+ line, col = self._position(self.chunkOffset)
+ return (line + 1, col)
+
+ def char(self):
+ """ Read one character from the stream or queue if available. Return
+ EOF when EOF is reached.
+ """
+ # Read a new chunk from the input stream if necessary
+ if self.chunkOffset >= self.chunkSize:
+ if not self.readChunk():
+ return EOF
+
+ chunkOffset = self.chunkOffset
+ char = self.chunk[chunkOffset]
+ self.chunkOffset = chunkOffset + 1
+
+ return char
+
+ def readChunk(self, chunkSize=None):
+ if chunkSize is None:
+ chunkSize = self._defaultChunkSize
+
+ self.prevNumLines, self.prevNumCols = self._position(self.chunkSize)
+
+ self.chunk = ""
+ self.chunkSize = 0
+ self.chunkOffset = 0
+
+ data = self.dataStream.read(chunkSize)
+
+ # Deal with CR LF and surrogates broken across chunks
+ if self._bufferedCharacter:
+ data = self._bufferedCharacter + data
+ self._bufferedCharacter = None
+ elif not data:
+ # We have no more data, bye-bye stream
+ return False
+
+ if len(data) > 1:
+ lastv = ord(data[-1])
+ if lastv == 0x0D or 0xD800 <= lastv <= 0xDBFF:
+ self._bufferedCharacter = data[-1]
+ data = data[:-1]
+
+ if self.reportCharacterErrors:
+ self.reportCharacterErrors(data)
+
+ # Replace invalid characters
+ data = data.replace("\r\n", "\n")
+ data = data.replace("\r", "\n")
+
+ self.chunk = data
+ self.chunkSize = len(data)
+
+ return True
+
+ def characterErrorsUCS4(self, data):
+ for _ in range(len(invalid_unicode_re.findall(data))):
+ self.errors.append("invalid-codepoint")
+
+ def characterErrorsUCS2(self, data):
+ # Someone picked the wrong compile option
+ # You lose
+ skip = False
+ for match in invalid_unicode_re.finditer(data):
+ if skip:
+ continue
+ codepoint = ord(match.group())
+ pos = match.start()
+ # Pretty sure there should be endianness issues here
+ if _utils.isSurrogatePair(data[pos:pos + 2]):
+ # We have a surrogate pair!
+ char_val = _utils.surrogatePairToCodepoint(data[pos:pos + 2])
+ if char_val in non_bmp_invalid_codepoints:
+ self.errors.append("invalid-codepoint")
+ skip = True
+ elif (codepoint >= 0xD800 and codepoint <= 0xDFFF and
+ pos == len(data) - 1):
+ self.errors.append("invalid-codepoint")
+ else:
+ skip = False
+ self.errors.append("invalid-codepoint")
+
+ def charsUntil(self, characters, opposite=False):
+ """ Returns a string of characters from the stream up to but not
+ including any character in 'characters' or EOF. 'characters' must be
+ a container that supports the 'in' method and iteration over its
+ characters.
+ """
+
+ # Use a cache of regexps to find the required characters
+ try:
+ chars = charsUntilRegEx[(characters, opposite)]
+ except KeyError:
+ if __debug__:
+ for c in characters:
+ assert(ord(c) < 128)
+ regex = "".join(["\\x%02x" % ord(c) for c in characters])
+ if not opposite:
+ regex = "^%s" % regex
+ chars = charsUntilRegEx[(characters, opposite)] = re.compile("[%s]+" % regex)
+
+ rv = []
+
+ while True:
+ # Find the longest matching prefix
+ m = chars.match(self.chunk, self.chunkOffset)
+ if m is None:
+ # If nothing matched, and it wasn't because we ran out of chunk,
+ # then stop
+ if self.chunkOffset != self.chunkSize:
+ break
+ else:
+ end = m.end()
+ # If not the whole chunk matched, return everything
+ # up to the part that didn't match
+ if end != self.chunkSize:
+ rv.append(self.chunk[self.chunkOffset:end])
+ self.chunkOffset = end
+ break
+ # If the whole remainder of the chunk matched,
+ # use it all and read the next chunk
+ rv.append(self.chunk[self.chunkOffset:])
+ if not self.readChunk():
+ # Reached EOF
+ break
+
+ r = "".join(rv)
+ return r
+
+ def unget(self, char):
+ # Only one character is allowed to be ungotten at once - it must
+ # be consumed again before any further call to unget
+ if char is not EOF:
+ if self.chunkOffset == 0:
+ # unget is called quite rarely, so it's a good idea to do
+ # more work here if it saves a bit of work in the frequently
+ # called char and charsUntil.
+ # So, just prepend the ungotten character onto the current
+ # chunk:
+ self.chunk = char + self.chunk
+ self.chunkSize += 1
+ else:
+ self.chunkOffset -= 1
+ assert self.chunk[self.chunkOffset] == char
+
+
+class HTMLBinaryInputStream(HTMLUnicodeInputStream):
+ """Provides a unicode stream of characters to the HTMLTokenizer.
+
+ This class takes care of character encoding and removing or replacing
+ incorrect byte-sequences and also provides column and line tracking.
+
+ """
+
+ def __init__(self, source, override_encoding=None, transport_encoding=None,
+ same_origin_parent_encoding=None, likely_encoding=None,
+ default_encoding="windows-1252", useChardet=True):
+ """Initialises the HTMLInputStream.
+
+ HTMLInputStream(source, [encoding]) -> Normalized stream from source
+ for use by html5lib.
+
+ source can be either a file-object, local filename or a string.
+
+ The optional encoding parameter must be a string that indicates
+ the encoding. If specified, that encoding will be used,
+ regardless of any BOM or later declaration (such as in a meta
+ element)
+
+ """
+ # Raw Stream - for unicode objects this will encode to utf-8 and set
+ # self.charEncoding as appropriate
+ self.rawStream = self.openStream(source)
+
+ HTMLUnicodeInputStream.__init__(self, self.rawStream)
+
+ # Encoding Information
+ # Number of bytes to use when looking for a meta element with
+ # encoding information
+ self.numBytesMeta = 1024
+ # Number of bytes to use when using detecting encoding using chardet
+ self.numBytesChardet = 100
+ # Things from args
+ self.override_encoding = override_encoding
+ self.transport_encoding = transport_encoding
+ self.same_origin_parent_encoding = same_origin_parent_encoding
+ self.likely_encoding = likely_encoding
+ self.default_encoding = default_encoding
+
+ # Determine encoding
+ self.charEncoding = self.determineEncoding(useChardet)
+ assert self.charEncoding[0] is not None
+
+ # Call superclass
+ self.reset()
+
+ def reset(self):
+ self.dataStream = self.charEncoding[0].codec_info.streamreader(self.rawStream, 'replace')
+ HTMLUnicodeInputStream.reset(self)
+
+ def openStream(self, source):
+ """Produces a file object from source.
+
+ source can be either a file object, local filename or a string.
+
+ """
+ # Already a file object
+ if hasattr(source, 'read'):
+ stream = source
+ else:
+ stream = BytesIO(source)
+
+ try:
+ stream.seek(stream.tell())
+ except Exception:
+ stream = BufferedStream(stream)
+
+ return stream
+
+ def determineEncoding(self, chardet=True):
+ # BOMs take precedence over everything
+ # This will also read past the BOM if present
+ charEncoding = self.detectBOM(), "certain"
+ if charEncoding[0] is not None:
+ return charEncoding
+
+ # If we've been overridden, we've been overridden
+ charEncoding = lookupEncoding(self.override_encoding), "certain"
+ if charEncoding[0] is not None:
+ return charEncoding
+
+ # Now check the transport layer
+ charEncoding = lookupEncoding(self.transport_encoding), "certain"
+ if charEncoding[0] is not None:
+ return charEncoding
+
+ # Look for meta elements with encoding information
+ charEncoding = self.detectEncodingMeta(), "tentative"
+ if charEncoding[0] is not None:
+ return charEncoding
+
+ # Parent document encoding
+ charEncoding = lookupEncoding(self.same_origin_parent_encoding), "tentative"
+ if charEncoding[0] is not None and not charEncoding[0].name.startswith("utf-16"):
+ return charEncoding
+
+ # "likely" encoding
+ charEncoding = lookupEncoding(self.likely_encoding), "tentative"
+ if charEncoding[0] is not None:
+ return charEncoding
+
+ # Guess with chardet, if available
+ if chardet:
+ try:
+ from chardet.universaldetector import UniversalDetector
+ except ImportError:
+ pass
+ else:
+ buffers = []
+ detector = UniversalDetector()
+ while not detector.done:
+ buffer = self.rawStream.read(self.numBytesChardet)
+ assert isinstance(buffer, bytes)
+ if not buffer:
+ break
+ buffers.append(buffer)
+ detector.feed(buffer)
+ detector.close()
+ encoding = lookupEncoding(detector.result['encoding'])
+ self.rawStream.seek(0)
+ if encoding is not None:
+ return encoding, "tentative"
+
+ # Try the default encoding
+ charEncoding = lookupEncoding(self.default_encoding), "tentative"
+ if charEncoding[0] is not None:
+ return charEncoding
+
+ # Fallback to html5lib's default if even that hasn't worked
+ return lookupEncoding("windows-1252"), "tentative"
+
+ def changeEncoding(self, newEncoding):
+ assert self.charEncoding[1] != "certain"
+ newEncoding = lookupEncoding(newEncoding)
+ if newEncoding is None:
+ return
+ if newEncoding.name in ("utf-16be", "utf-16le"):
+ newEncoding = lookupEncoding("utf-8")
+ assert newEncoding is not None
+ elif newEncoding == self.charEncoding[0]:
+ self.charEncoding = (self.charEncoding[0], "certain")
+ else:
+ self.rawStream.seek(0)
+ self.charEncoding = (newEncoding, "certain")
+ self.reset()
+ raise _ReparseException("Encoding changed from %s to %s" % (self.charEncoding[0], newEncoding))
+
+ def detectBOM(self):
+ """Attempts to detect at BOM at the start of the stream. If
+ an encoding can be determined from the BOM return the name of the
+ encoding otherwise return None"""
+ bomDict = {
+ codecs.BOM_UTF8: 'utf-8',
+ codecs.BOM_UTF16_LE: 'utf-16le', codecs.BOM_UTF16_BE: 'utf-16be',
+ codecs.BOM_UTF32_LE: 'utf-32le', codecs.BOM_UTF32_BE: 'utf-32be'
+ }
+
+ # Go to beginning of file and read in 4 bytes
+ string = self.rawStream.read(4)
+ assert isinstance(string, bytes)
+
+ # Try detecting the BOM using bytes from the string
+ encoding = bomDict.get(string[:3]) # UTF-8
+ seek = 3
+ if not encoding:
+ # Need to detect UTF-32 before UTF-16
+ encoding = bomDict.get(string) # UTF-32
+ seek = 4
+ if not encoding:
+ encoding = bomDict.get(string[:2]) # UTF-16
+ seek = 2
+
+ # Set the read position past the BOM if one was found, otherwise
+ # set it to the start of the stream
+ if encoding:
+ self.rawStream.seek(seek)
+ return lookupEncoding(encoding)
+ else:
+ self.rawStream.seek(0)
+ return None
+
+ def detectEncodingMeta(self):
+ """Report the encoding declared by the meta element
+ """
+ buffer = self.rawStream.read(self.numBytesMeta)
+ assert isinstance(buffer, bytes)
+ parser = EncodingParser(buffer)
+ self.rawStream.seek(0)
+ encoding = parser.getEncoding()
+
+ if encoding is not None and encoding.name in ("utf-16be", "utf-16le"):
+ encoding = lookupEncoding("utf-8")
+
+ return encoding
+
+
+class EncodingBytes(bytes):
+ """String-like object with an associated position and various extra methods
+ If the position is ever greater than the string length then an exception is
+ raised"""
+ def __new__(self, value):
+ assert isinstance(value, bytes)
+ return bytes.__new__(self, value.lower())
+
+ def __init__(self, value):
+ # pylint:disable=unused-argument
+ self._position = -1
+
+ def __iter__(self):
+ return self
+
+ def __next__(self):
+ p = self._position = self._position + 1
+ if p >= len(self):
+ raise StopIteration
+ elif p < 0:
+ raise TypeError
+ return self[p:p + 1]
+
+ def next(self):
+ # Py2 compat
+ return self.__next__()
+
+ def previous(self):
+ p = self._position
+ if p >= len(self):
+ raise StopIteration
+ elif p < 0:
+ raise TypeError
+ self._position = p = p - 1
+ return self[p:p + 1]
+
+ def setPosition(self, position):
+ if self._position >= len(self):
+ raise StopIteration
+ self._position = position
+
+ def getPosition(self):
+ if self._position >= len(self):
+ raise StopIteration
+ if self._position >= 0:
+ return self._position
+ else:
+ return None
+
+ position = property(getPosition, setPosition)
+
+ def getCurrentByte(self):
+ return self[self.position:self.position + 1]
+
+ currentByte = property(getCurrentByte)
+
+ def skip(self, chars=spaceCharactersBytes):
+ """Skip past a list of characters"""
+ p = self.position # use property for the error-checking
+ while p < len(self):
+ c = self[p:p + 1]
+ if c not in chars:
+ self._position = p
+ return c
+ p += 1
+ self._position = p
+ return None
+
+ def skipUntil(self, chars):
+ p = self.position
+ while p < len(self):
+ c = self[p:p + 1]
+ if c in chars:
+ self._position = p
+ return c
+ p += 1
+ self._position = p
+ return None
+
+ def matchBytes(self, bytes):
+ """Look for a sequence of bytes at the start of a string. If the bytes
+ are found return True and advance the position to the byte after the
+ match. Otherwise return False and leave the position alone"""
+ rv = self.startswith(bytes, self.position)
+ if rv:
+ self.position += len(bytes)
+ return rv
+
+ def jumpTo(self, bytes):
+ """Look for the next sequence of bytes matching a given sequence. If
+ a match is found advance the position to the last byte of the match"""
+ try:
+ self._position = self.index(bytes, self.position) + len(bytes) - 1
+ except ValueError:
+ raise StopIteration
+ return True
+
+
+class EncodingParser(object):
+ """Mini parser for detecting character encoding from meta elements"""
+
+ def __init__(self, data):
+ """string - the data to work on for encoding detection"""
+ self.data = EncodingBytes(data)
+ self.encoding = None
+
+ def getEncoding(self):
+ if b"")
+
+ def handleMeta(self):
+ if self.data.currentByte not in spaceCharactersBytes:
+ # if we have optgroup
+ # element, or if there is no more content in the parent
+ # element.
+ if type == "StartTag":
+ return next["name"] in ('option', 'optgroup')
+ else:
+ return type == "EndTag" or type is None
+ elif tagname in ('rt', 'rp'):
+ # An rt element's end tag may be omitted if the rt element is
+ # immediately followed by an rt or rp element, or if there is
+ # no more content in the parent element.
+ # An rp element's end tag may be omitted if the rp element is
+ # immediately followed by an rt or rp element, or if there is
+ # no more content in the parent element.
+ if type == "StartTag":
+ return next["name"] in ('rt', 'rp')
+ else:
+ return type == "EndTag" or type is None
+ elif tagname == 'colgroup':
+ # A colgroup element's end tag may be omitted if the colgroup
+ # element is not immediately followed by a space character or
+ # a comment.
+ if type in ("Comment", "SpaceCharacters"):
+ return False
+ elif type == "StartTag":
+ # XXX: we also look for an immediately following colgroup
+ # element. See is_optional_start.
+ return next["name"] != 'colgroup'
+ else:
+ return True
+ elif tagname in ('thead', 'tbody'):
+ # A thead element's end tag may be omitted if the thead element
+ # is immediately followed by a tbody or tfoot element.
+ # A tbody element's end tag may be omitted if the tbody element
+ # is immediately followed by a tbody or tfoot element, or if
+ # there is no more content in the parent element.
+ # A tfoot element's end tag may be omitted if the tfoot element
+ # is immediately followed by a tbody element, or if there is no
+ # more content in the parent element.
+ # XXX: we never omit the end tag when the following element is
+ # a tbody. See is_optional_start.
+ if type == "StartTag":
+ return next["name"] in ['tbody', 'tfoot']
+ elif tagname == 'tbody':
+ return type == "EndTag" or type is None
+ else:
+ return False
+ elif tagname == 'tfoot':
+ # A tfoot element's end tag may be omitted if the tfoot element
+ # is immediately followed by a tbody element, or if there is no
+ # more content in the parent element.
+ # XXX: we never omit the end tag when the following element is
+ # a tbody. See is_optional_start.
+ if type == "StartTag":
+ return next["name"] == 'tbody'
+ else:
+ return type == "EndTag" or type is None
+ elif tagname in ('td', 'th'):
+ # A td element's end tag may be omitted if the td element is
+ # immediately followed by a td or th element, or if there is
+ # no more content in the parent element.
+ # A th element's end tag may be omitted if the th element is
+ # immediately followed by a td or th element, or if there is
+ # no more content in the parent element.
+ if type == "StartTag":
+ return next["name"] in ('td', 'th')
+ else:
+ return type == "EndTag" or type is None
+ return False
diff --git a/lib/bleach/_vendor/html5lib/filters/sanitizer.py b/lib/bleach/_vendor/html5lib/filters/sanitizer.py
new file mode 100644
index 00000000..70ef9066
--- /dev/null
+++ b/lib/bleach/_vendor/html5lib/filters/sanitizer.py
@@ -0,0 +1,916 @@
+"""Deprecated from html5lib 1.1.
+
+See `here `_ for
+information about its deprecation; `Bleach `_
+is recommended as a replacement. Please let us know in the aforementioned issue
+if Bleach is unsuitable for your needs.
+
+"""
+from __future__ import absolute_import, division, unicode_literals
+
+import re
+import warnings
+from xml.sax.saxutils import escape, unescape
+
+from six.moves import urllib_parse as urlparse
+
+from . import base
+from ..constants import namespaces, prefixes
+
+__all__ = ["Filter"]
+
+
+_deprecation_msg = (
+ "html5lib's sanitizer is deprecated; see " +
+ "https://github.com/html5lib/html5lib-python/issues/443 and please let " +
+ "us know if Bleach is unsuitable for your needs"
+)
+
+warnings.warn(_deprecation_msg, DeprecationWarning)
+
+allowed_elements = frozenset((
+ (namespaces['html'], 'a'),
+ (namespaces['html'], 'abbr'),
+ (namespaces['html'], 'acronym'),
+ (namespaces['html'], 'address'),
+ (namespaces['html'], 'area'),
+ (namespaces['html'], 'article'),
+ (namespaces['html'], 'aside'),
+ (namespaces['html'], 'audio'),
+ (namespaces['html'], 'b'),
+ (namespaces['html'], 'big'),
+ (namespaces['html'], 'blockquote'),
+ (namespaces['html'], 'br'),
+ (namespaces['html'], 'button'),
+ (namespaces['html'], 'canvas'),
+ (namespaces['html'], 'caption'),
+ (namespaces['html'], 'center'),
+ (namespaces['html'], 'cite'),
+ (namespaces['html'], 'code'),
+ (namespaces['html'], 'col'),
+ (namespaces['html'], 'colgroup'),
+ (namespaces['html'], 'command'),
+ (namespaces['html'], 'datagrid'),
+ (namespaces['html'], 'datalist'),
+ (namespaces['html'], 'dd'),
+ (namespaces['html'], 'del'),
+ (namespaces['html'], 'details'),
+ (namespaces['html'], 'dfn'),
+ (namespaces['html'], 'dialog'),
+ (namespaces['html'], 'dir'),
+ (namespaces['html'], 'div'),
+ (namespaces['html'], 'dl'),
+ (namespaces['html'], 'dt'),
+ (namespaces['html'], 'em'),
+ (namespaces['html'], 'event-source'),
+ (namespaces['html'], 'fieldset'),
+ (namespaces['html'], 'figcaption'),
+ (namespaces['html'], 'figure'),
+ (namespaces['html'], 'footer'),
+ (namespaces['html'], 'font'),
+ (namespaces['html'], 'form'),
+ (namespaces['html'], 'header'),
+ (namespaces['html'], 'h1'),
+ (namespaces['html'], 'h2'),
+ (namespaces['html'], 'h3'),
+ (namespaces['html'], 'h4'),
+ (namespaces['html'], 'h5'),
+ (namespaces['html'], 'h6'),
+ (namespaces['html'], 'hr'),
+ (namespaces['html'], 'i'),
+ (namespaces['html'], 'img'),
+ (namespaces['html'], 'input'),
+ (namespaces['html'], 'ins'),
+ (namespaces['html'], 'keygen'),
+ (namespaces['html'], 'kbd'),
+ (namespaces['html'], 'label'),
+ (namespaces['html'], 'legend'),
+ (namespaces['html'], 'li'),
+ (namespaces['html'], 'm'),
+ (namespaces['html'], 'map'),
+ (namespaces['html'], 'menu'),
+ (namespaces['html'], 'meter'),
+ (namespaces['html'], 'multicol'),
+ (namespaces['html'], 'nav'),
+ (namespaces['html'], 'nextid'),
+ (namespaces['html'], 'ol'),
+ (namespaces['html'], 'output'),
+ (namespaces['html'], 'optgroup'),
+ (namespaces['html'], 'option'),
+ (namespaces['html'], 'p'),
+ (namespaces['html'], 'pre'),
+ (namespaces['html'], 'progress'),
+ (namespaces['html'], 'q'),
+ (namespaces['html'], 's'),
+ (namespaces['html'], 'samp'),
+ (namespaces['html'], 'section'),
+ (namespaces['html'], 'select'),
+ (namespaces['html'], 'small'),
+ (namespaces['html'], 'sound'),
+ (namespaces['html'], 'source'),
+ (namespaces['html'], 'spacer'),
+ (namespaces['html'], 'span'),
+ (namespaces['html'], 'strike'),
+ (namespaces['html'], 'strong'),
+ (namespaces['html'], 'sub'),
+ (namespaces['html'], 'sup'),
+ (namespaces['html'], 'table'),
+ (namespaces['html'], 'tbody'),
+ (namespaces['html'], 'td'),
+ (namespaces['html'], 'textarea'),
+ (namespaces['html'], 'time'),
+ (namespaces['html'], 'tfoot'),
+ (namespaces['html'], 'th'),
+ (namespaces['html'], 'thead'),
+ (namespaces['html'], 'tr'),
+ (namespaces['html'], 'tt'),
+ (namespaces['html'], 'u'),
+ (namespaces['html'], 'ul'),
+ (namespaces['html'], 'var'),
+ (namespaces['html'], 'video'),
+ (namespaces['mathml'], 'maction'),
+ (namespaces['mathml'], 'math'),
+ (namespaces['mathml'], 'merror'),
+ (namespaces['mathml'], 'mfrac'),
+ (namespaces['mathml'], 'mi'),
+ (namespaces['mathml'], 'mmultiscripts'),
+ (namespaces['mathml'], 'mn'),
+ (namespaces['mathml'], 'mo'),
+ (namespaces['mathml'], 'mover'),
+ (namespaces['mathml'], 'mpadded'),
+ (namespaces['mathml'], 'mphantom'),
+ (namespaces['mathml'], 'mprescripts'),
+ (namespaces['mathml'], 'mroot'),
+ (namespaces['mathml'], 'mrow'),
+ (namespaces['mathml'], 'mspace'),
+ (namespaces['mathml'], 'msqrt'),
+ (namespaces['mathml'], 'mstyle'),
+ (namespaces['mathml'], 'msub'),
+ (namespaces['mathml'], 'msubsup'),
+ (namespaces['mathml'], 'msup'),
+ (namespaces['mathml'], 'mtable'),
+ (namespaces['mathml'], 'mtd'),
+ (namespaces['mathml'], 'mtext'),
+ (namespaces['mathml'], 'mtr'),
+ (namespaces['mathml'], 'munder'),
+ (namespaces['mathml'], 'munderover'),
+ (namespaces['mathml'], 'none'),
+ (namespaces['svg'], 'a'),
+ (namespaces['svg'], 'animate'),
+ (namespaces['svg'], 'animateColor'),
+ (namespaces['svg'], 'animateMotion'),
+ (namespaces['svg'], 'animateTransform'),
+ (namespaces['svg'], 'clipPath'),
+ (namespaces['svg'], 'circle'),
+ (namespaces['svg'], 'defs'),
+ (namespaces['svg'], 'desc'),
+ (namespaces['svg'], 'ellipse'),
+ (namespaces['svg'], 'font-face'),
+ (namespaces['svg'], 'font-face-name'),
+ (namespaces['svg'], 'font-face-src'),
+ (namespaces['svg'], 'g'),
+ (namespaces['svg'], 'glyph'),
+ (namespaces['svg'], 'hkern'),
+ (namespaces['svg'], 'linearGradient'),
+ (namespaces['svg'], 'line'),
+ (namespaces['svg'], 'marker'),
+ (namespaces['svg'], 'metadata'),
+ (namespaces['svg'], 'missing-glyph'),
+ (namespaces['svg'], 'mpath'),
+ (namespaces['svg'], 'path'),
+ (namespaces['svg'], 'polygon'),
+ (namespaces['svg'], 'polyline'),
+ (namespaces['svg'], 'radialGradient'),
+ (namespaces['svg'], 'rect'),
+ (namespaces['svg'], 'set'),
+ (namespaces['svg'], 'stop'),
+ (namespaces['svg'], 'svg'),
+ (namespaces['svg'], 'switch'),
+ (namespaces['svg'], 'text'),
+ (namespaces['svg'], 'title'),
+ (namespaces['svg'], 'tspan'),
+ (namespaces['svg'], 'use'),
+))
+
+allowed_attributes = frozenset((
+ # HTML attributes
+ (None, 'abbr'),
+ (None, 'accept'),
+ (None, 'accept-charset'),
+ (None, 'accesskey'),
+ (None, 'action'),
+ (None, 'align'),
+ (None, 'alt'),
+ (None, 'autocomplete'),
+ (None, 'autofocus'),
+ (None, 'axis'),
+ (None, 'background'),
+ (None, 'balance'),
+ (None, 'bgcolor'),
+ (None, 'bgproperties'),
+ (None, 'border'),
+ (None, 'bordercolor'),
+ (None, 'bordercolordark'),
+ (None, 'bordercolorlight'),
+ (None, 'bottompadding'),
+ (None, 'cellpadding'),
+ (None, 'cellspacing'),
+ (None, 'ch'),
+ (None, 'challenge'),
+ (None, 'char'),
+ (None, 'charoff'),
+ (None, 'choff'),
+ (None, 'charset'),
+ (None, 'checked'),
+ (None, 'cite'),
+ (None, 'class'),
+ (None, 'clear'),
+ (None, 'color'),
+ (None, 'cols'),
+ (None, 'colspan'),
+ (None, 'compact'),
+ (None, 'contenteditable'),
+ (None, 'controls'),
+ (None, 'coords'),
+ (None, 'data'),
+ (None, 'datafld'),
+ (None, 'datapagesize'),
+ (None, 'datasrc'),
+ (None, 'datetime'),
+ (None, 'default'),
+ (None, 'delay'),
+ (None, 'dir'),
+ (None, 'disabled'),
+ (None, 'draggable'),
+ (None, 'dynsrc'),
+ (None, 'enctype'),
+ (None, 'end'),
+ (None, 'face'),
+ (None, 'for'),
+ (None, 'form'),
+ (None, 'frame'),
+ (None, 'galleryimg'),
+ (None, 'gutter'),
+ (None, 'headers'),
+ (None, 'height'),
+ (None, 'hidefocus'),
+ (None, 'hidden'),
+ (None, 'high'),
+ (None, 'href'),
+ (None, 'hreflang'),
+ (None, 'hspace'),
+ (None, 'icon'),
+ (None, 'id'),
+ (None, 'inputmode'),
+ (None, 'ismap'),
+ (None, 'keytype'),
+ (None, 'label'),
+ (None, 'leftspacing'),
+ (None, 'lang'),
+ (None, 'list'),
+ (None, 'longdesc'),
+ (None, 'loop'),
+ (None, 'loopcount'),
+ (None, 'loopend'),
+ (None, 'loopstart'),
+ (None, 'low'),
+ (None, 'lowsrc'),
+ (None, 'max'),
+ (None, 'maxlength'),
+ (None, 'media'),
+ (None, 'method'),
+ (None, 'min'),
+ (None, 'multiple'),
+ (None, 'name'),
+ (None, 'nohref'),
+ (None, 'noshade'),
+ (None, 'nowrap'),
+ (None, 'open'),
+ (None, 'optimum'),
+ (None, 'pattern'),
+ (None, 'ping'),
+ (None, 'point-size'),
+ (None, 'poster'),
+ (None, 'pqg'),
+ (None, 'preload'),
+ (None, 'prompt'),
+ (None, 'radiogroup'),
+ (None, 'readonly'),
+ (None, 'rel'),
+ (None, 'repeat-max'),
+ (None, 'repeat-min'),
+ (None, 'replace'),
+ (None, 'required'),
+ (None, 'rev'),
+ (None, 'rightspacing'),
+ (None, 'rows'),
+ (None, 'rowspan'),
+ (None, 'rules'),
+ (None, 'scope'),
+ (None, 'selected'),
+ (None, 'shape'),
+ (None, 'size'),
+ (None, 'span'),
+ (None, 'src'),
+ (None, 'start'),
+ (None, 'step'),
+ (None, 'style'),
+ (None, 'summary'),
+ (None, 'suppress'),
+ (None, 'tabindex'),
+ (None, 'target'),
+ (None, 'template'),
+ (None, 'title'),
+ (None, 'toppadding'),
+ (None, 'type'),
+ (None, 'unselectable'),
+ (None, 'usemap'),
+ (None, 'urn'),
+ (None, 'valign'),
+ (None, 'value'),
+ (None, 'variable'),
+ (None, 'volume'),
+ (None, 'vspace'),
+ (None, 'vrml'),
+ (None, 'width'),
+ (None, 'wrap'),
+ (namespaces['xml'], 'lang'),
+ # MathML attributes
+ (None, 'actiontype'),
+ (None, 'align'),
+ (None, 'columnalign'),
+ (None, 'columnalign'),
+ (None, 'columnalign'),
+ (None, 'columnlines'),
+ (None, 'columnspacing'),
+ (None, 'columnspan'),
+ (None, 'depth'),
+ (None, 'display'),
+ (None, 'displaystyle'),
+ (None, 'equalcolumns'),
+ (None, 'equalrows'),
+ (None, 'fence'),
+ (None, 'fontstyle'),
+ (None, 'fontweight'),
+ (None, 'frame'),
+ (None, 'height'),
+ (None, 'linethickness'),
+ (None, 'lspace'),
+ (None, 'mathbackground'),
+ (None, 'mathcolor'),
+ (None, 'mathvariant'),
+ (None, 'mathvariant'),
+ (None, 'maxsize'),
+ (None, 'minsize'),
+ (None, 'other'),
+ (None, 'rowalign'),
+ (None, 'rowalign'),
+ (None, 'rowalign'),
+ (None, 'rowlines'),
+ (None, 'rowspacing'),
+ (None, 'rowspan'),
+ (None, 'rspace'),
+ (None, 'scriptlevel'),
+ (None, 'selection'),
+ (None, 'separator'),
+ (None, 'stretchy'),
+ (None, 'width'),
+ (None, 'width'),
+ (namespaces['xlink'], 'href'),
+ (namespaces['xlink'], 'show'),
+ (namespaces['xlink'], 'type'),
+ # SVG attributes
+ (None, 'accent-height'),
+ (None, 'accumulate'),
+ (None, 'additive'),
+ (None, 'alphabetic'),
+ (None, 'arabic-form'),
+ (None, 'ascent'),
+ (None, 'attributeName'),
+ (None, 'attributeType'),
+ (None, 'baseProfile'),
+ (None, 'bbox'),
+ (None, 'begin'),
+ (None, 'by'),
+ (None, 'calcMode'),
+ (None, 'cap-height'),
+ (None, 'class'),
+ (None, 'clip-path'),
+ (None, 'color'),
+ (None, 'color-rendering'),
+ (None, 'content'),
+ (None, 'cx'),
+ (None, 'cy'),
+ (None, 'd'),
+ (None, 'dx'),
+ (None, 'dy'),
+ (None, 'descent'),
+ (None, 'display'),
+ (None, 'dur'),
+ (None, 'end'),
+ (None, 'fill'),
+ (None, 'fill-opacity'),
+ (None, 'fill-rule'),
+ (None, 'font-family'),
+ (None, 'font-size'),
+ (None, 'font-stretch'),
+ (None, 'font-style'),
+ (None, 'font-variant'),
+ (None, 'font-weight'),
+ (None, 'from'),
+ (None, 'fx'),
+ (None, 'fy'),
+ (None, 'g1'),
+ (None, 'g2'),
+ (None, 'glyph-name'),
+ (None, 'gradientUnits'),
+ (None, 'hanging'),
+ (None, 'height'),
+ (None, 'horiz-adv-x'),
+ (None, 'horiz-origin-x'),
+ (None, 'id'),
+ (None, 'ideographic'),
+ (None, 'k'),
+ (None, 'keyPoints'),
+ (None, 'keySplines'),
+ (None, 'keyTimes'),
+ (None, 'lang'),
+ (None, 'marker-end'),
+ (None, 'marker-mid'),
+ (None, 'marker-start'),
+ (None, 'markerHeight'),
+ (None, 'markerUnits'),
+ (None, 'markerWidth'),
+ (None, 'mathematical'),
+ (None, 'max'),
+ (None, 'min'),
+ (None, 'name'),
+ (None, 'offset'),
+ (None, 'opacity'),
+ (None, 'orient'),
+ (None, 'origin'),
+ (None, 'overline-position'),
+ (None, 'overline-thickness'),
+ (None, 'panose-1'),
+ (None, 'path'),
+ (None, 'pathLength'),
+ (None, 'points'),
+ (None, 'preserveAspectRatio'),
+ (None, 'r'),
+ (None, 'refX'),
+ (None, 'refY'),
+ (None, 'repeatCount'),
+ (None, 'repeatDur'),
+ (None, 'requiredExtensions'),
+ (None, 'requiredFeatures'),
+ (None, 'restart'),
+ (None, 'rotate'),
+ (None, 'rx'),
+ (None, 'ry'),
+ (None, 'slope'),
+ (None, 'stemh'),
+ (None, 'stemv'),
+ (None, 'stop-color'),
+ (None, 'stop-opacity'),
+ (None, 'strikethrough-position'),
+ (None, 'strikethrough-thickness'),
+ (None, 'stroke'),
+ (None, 'stroke-dasharray'),
+ (None, 'stroke-dashoffset'),
+ (None, 'stroke-linecap'),
+ (None, 'stroke-linejoin'),
+ (None, 'stroke-miterlimit'),
+ (None, 'stroke-opacity'),
+ (None, 'stroke-width'),
+ (None, 'systemLanguage'),
+ (None, 'target'),
+ (None, 'text-anchor'),
+ (None, 'to'),
+ (None, 'transform'),
+ (None, 'type'),
+ (None, 'u1'),
+ (None, 'u2'),
+ (None, 'underline-position'),
+ (None, 'underline-thickness'),
+ (None, 'unicode'),
+ (None, 'unicode-range'),
+ (None, 'units-per-em'),
+ (None, 'values'),
+ (None, 'version'),
+ (None, 'viewBox'),
+ (None, 'visibility'),
+ (None, 'width'),
+ (None, 'widths'),
+ (None, 'x'),
+ (None, 'x-height'),
+ (None, 'x1'),
+ (None, 'x2'),
+ (namespaces['xlink'], 'actuate'),
+ (namespaces['xlink'], 'arcrole'),
+ (namespaces['xlink'], 'href'),
+ (namespaces['xlink'], 'role'),
+ (namespaces['xlink'], 'show'),
+ (namespaces['xlink'], 'title'),
+ (namespaces['xlink'], 'type'),
+ (namespaces['xml'], 'base'),
+ (namespaces['xml'], 'lang'),
+ (namespaces['xml'], 'space'),
+ (None, 'y'),
+ (None, 'y1'),
+ (None, 'y2'),
+ (None, 'zoomAndPan'),
+))
+
+attr_val_is_uri = frozenset((
+ (None, 'href'),
+ (None, 'src'),
+ (None, 'cite'),
+ (None, 'action'),
+ (None, 'longdesc'),
+ (None, 'poster'),
+ (None, 'background'),
+ (None, 'datasrc'),
+ (None, 'dynsrc'),
+ (None, 'lowsrc'),
+ (None, 'ping'),
+ (namespaces['xlink'], 'href'),
+ (namespaces['xml'], 'base'),
+))
+
+svg_attr_val_allows_ref = frozenset((
+ (None, 'clip-path'),
+ (None, 'color-profile'),
+ (None, 'cursor'),
+ (None, 'fill'),
+ (None, 'filter'),
+ (None, 'marker'),
+ (None, 'marker-start'),
+ (None, 'marker-mid'),
+ (None, 'marker-end'),
+ (None, 'mask'),
+ (None, 'stroke'),
+))
+
+svg_allow_local_href = frozenset((
+ (None, 'altGlyph'),
+ (None, 'animate'),
+ (None, 'animateColor'),
+ (None, 'animateMotion'),
+ (None, 'animateTransform'),
+ (None, 'cursor'),
+ (None, 'feImage'),
+ (None, 'filter'),
+ (None, 'linearGradient'),
+ (None, 'pattern'),
+ (None, 'radialGradient'),
+ (None, 'textpath'),
+ (None, 'tref'),
+ (None, 'set'),
+ (None, 'use')
+))
+
+allowed_css_properties = frozenset((
+ 'azimuth',
+ 'background-color',
+ 'border-bottom-color',
+ 'border-collapse',
+ 'border-color',
+ 'border-left-color',
+ 'border-right-color',
+ 'border-top-color',
+ 'clear',
+ 'color',
+ 'cursor',
+ 'direction',
+ 'display',
+ 'elevation',
+ 'float',
+ 'font',
+ 'font-family',
+ 'font-size',
+ 'font-style',
+ 'font-variant',
+ 'font-weight',
+ 'height',
+ 'letter-spacing',
+ 'line-height',
+ 'overflow',
+ 'pause',
+ 'pause-after',
+ 'pause-before',
+ 'pitch',
+ 'pitch-range',
+ 'richness',
+ 'speak',
+ 'speak-header',
+ 'speak-numeral',
+ 'speak-punctuation',
+ 'speech-rate',
+ 'stress',
+ 'text-align',
+ 'text-decoration',
+ 'text-indent',
+ 'unicode-bidi',
+ 'vertical-align',
+ 'voice-family',
+ 'volume',
+ 'white-space',
+ 'width',
+))
+
+allowed_css_keywords = frozenset((
+ 'auto',
+ 'aqua',
+ 'black',
+ 'block',
+ 'blue',
+ 'bold',
+ 'both',
+ 'bottom',
+ 'brown',
+ 'center',
+ 'collapse',
+ 'dashed',
+ 'dotted',
+ 'fuchsia',
+ 'gray',
+ 'green',
+ '!important',
+ 'italic',
+ 'left',
+ 'lime',
+ 'maroon',
+ 'medium',
+ 'none',
+ 'navy',
+ 'normal',
+ 'nowrap',
+ 'olive',
+ 'pointer',
+ 'purple',
+ 'red',
+ 'right',
+ 'solid',
+ 'silver',
+ 'teal',
+ 'top',
+ 'transparent',
+ 'underline',
+ 'white',
+ 'yellow',
+))
+
+allowed_svg_properties = frozenset((
+ 'fill',
+ 'fill-opacity',
+ 'fill-rule',
+ 'stroke',
+ 'stroke-width',
+ 'stroke-linecap',
+ 'stroke-linejoin',
+ 'stroke-opacity',
+))
+
+allowed_protocols = frozenset((
+ 'ed2k',
+ 'ftp',
+ 'http',
+ 'https',
+ 'irc',
+ 'mailto',
+ 'news',
+ 'gopher',
+ 'nntp',
+ 'telnet',
+ 'webcal',
+ 'xmpp',
+ 'callto',
+ 'feed',
+ 'urn',
+ 'aim',
+ 'rsync',
+ 'tag',
+ 'ssh',
+ 'sftp',
+ 'rtsp',
+ 'afs',
+ 'data',
+))
+
+allowed_content_types = frozenset((
+ 'image/png',
+ 'image/jpeg',
+ 'image/gif',
+ 'image/webp',
+ 'image/bmp',
+ 'text/plain',
+))
+
+
+data_content_type = re.compile(r'''
+ ^
+ # Match a content type /
+ (?P[-a-zA-Z0-9.]+/[-a-zA-Z0-9.]+)
+ # Match any character set and encoding
+ (?:(?:;charset=(?:[-a-zA-Z0-9]+)(?:;(?:base64))?)
+ |(?:;(?:base64))?(?:;charset=(?:[-a-zA-Z0-9]+))?)
+ # Assume the rest is data
+ ,.*
+ $
+ ''',
+ re.VERBOSE)
+
+
+class Filter(base.Filter):
+ """Sanitizes token stream of XHTML+MathML+SVG and of inline style attributes"""
+ def __init__(self,
+ source,
+ allowed_elements=allowed_elements,
+ allowed_attributes=allowed_attributes,
+ allowed_css_properties=allowed_css_properties,
+ allowed_css_keywords=allowed_css_keywords,
+ allowed_svg_properties=allowed_svg_properties,
+ allowed_protocols=allowed_protocols,
+ allowed_content_types=allowed_content_types,
+ attr_val_is_uri=attr_val_is_uri,
+ svg_attr_val_allows_ref=svg_attr_val_allows_ref,
+ svg_allow_local_href=svg_allow_local_href):
+ """Creates a Filter
+
+ :arg allowed_elements: set of elements to allow--everything else will
+ be escaped
+
+ :arg allowed_attributes: set of attributes to allow in
+ elements--everything else will be stripped
+
+ :arg allowed_css_properties: set of CSS properties to allow--everything
+ else will be stripped
+
+ :arg allowed_css_keywords: set of CSS keywords to allow--everything
+ else will be stripped
+
+ :arg allowed_svg_properties: set of SVG properties to allow--everything
+ else will be removed
+
+ :arg allowed_protocols: set of allowed protocols for URIs
+
+ :arg allowed_content_types: set of allowed content types for ``data`` URIs.
+
+ :arg attr_val_is_uri: set of attributes that have URI values--values
+ that have a scheme not listed in ``allowed_protocols`` are removed
+
+ :arg svg_attr_val_allows_ref: set of SVG attributes that can have
+ references
+
+ :arg svg_allow_local_href: set of SVG elements that can have local
+ hrefs--these are removed
+
+ """
+ super(Filter, self).__init__(source)
+
+ warnings.warn(_deprecation_msg, DeprecationWarning)
+
+ self.allowed_elements = allowed_elements
+ self.allowed_attributes = allowed_attributes
+ self.allowed_css_properties = allowed_css_properties
+ self.allowed_css_keywords = allowed_css_keywords
+ self.allowed_svg_properties = allowed_svg_properties
+ self.allowed_protocols = allowed_protocols
+ self.allowed_content_types = allowed_content_types
+ self.attr_val_is_uri = attr_val_is_uri
+ self.svg_attr_val_allows_ref = svg_attr_val_allows_ref
+ self.svg_allow_local_href = svg_allow_local_href
+
+ def __iter__(self):
+ for token in base.Filter.__iter__(self):
+ token = self.sanitize_token(token)
+ if token:
+ yield token
+
+ # Sanitize the +html+, escaping all elements not in ALLOWED_ELEMENTS, and
+ # stripping out all attributes not in ALLOWED_ATTRIBUTES. Style attributes
+ # are parsed, and a restricted set, specified by ALLOWED_CSS_PROPERTIES and
+ # ALLOWED_CSS_KEYWORDS, are allowed through. attributes in ATTR_VAL_IS_URI
+ # are scanned, and only URI schemes specified in ALLOWED_PROTOCOLS are
+ # allowed.
+ #
+ # sanitize_html('')
+ # => <script> do_nasty_stuff() </script>
+ # sanitize_html('Click here for $100 ')
+ # => Click here for $100
+ def sanitize_token(self, token):
+
+ # accommodate filters which use token_type differently
+ token_type = token["type"]
+ if token_type in ("StartTag", "EndTag", "EmptyTag"):
+ name = token["name"]
+ namespace = token["namespace"]
+ if ((namespace, name) in self.allowed_elements or
+ (namespace is None and
+ (namespaces["html"], name) in self.allowed_elements)):
+ return self.allowed_token(token)
+ else:
+ return self.disallowed_token(token)
+ elif token_type == "Comment":
+ pass
+ else:
+ return token
+
+ def allowed_token(self, token):
+ if "data" in token:
+ attrs = token["data"]
+ attr_names = set(attrs.keys())
+
+ # Remove forbidden attributes
+ for to_remove in (attr_names - self.allowed_attributes):
+ del token["data"][to_remove]
+ attr_names.remove(to_remove)
+
+ # Remove attributes with disallowed URL values
+ for attr in (attr_names & self.attr_val_is_uri):
+ assert attr in attrs
+ # I don't have a clue where this regexp comes from or why it matches those
+ # characters, nor why we call unescape. I just know it's always been here.
+ # Should you be worried by this comment in a sanitizer? Yes. On the other hand, all
+ # this will do is remove *more* than it otherwise would.
+ val_unescaped = re.sub("[`\x00-\x20\x7f-\xa0\\s]+", '',
+ unescape(attrs[attr])).lower()
+ # remove replacement characters from unescaped characters
+ val_unescaped = val_unescaped.replace("\ufffd", "")
+ try:
+ uri = urlparse.urlparse(val_unescaped)
+ except ValueError:
+ uri = None
+ del attrs[attr]
+ if uri and uri.scheme:
+ if uri.scheme not in self.allowed_protocols:
+ del attrs[attr]
+ if uri.scheme == 'data':
+ m = data_content_type.match(uri.path)
+ if not m:
+ del attrs[attr]
+ elif m.group('content_type') not in self.allowed_content_types:
+ del attrs[attr]
+
+ for attr in self.svg_attr_val_allows_ref:
+ if attr in attrs:
+ attrs[attr] = re.sub(r'url\s*\(\s*[^#\s][^)]+?\)',
+ ' ',
+ unescape(attrs[attr]))
+ if (token["name"] in self.svg_allow_local_href and
+ (namespaces['xlink'], 'href') in attrs and re.search(r'^\s*[^#\s].*',
+ attrs[(namespaces['xlink'], 'href')])):
+ del attrs[(namespaces['xlink'], 'href')]
+ if (None, 'style') in attrs:
+ attrs[(None, 'style')] = self.sanitize_css(attrs[(None, 'style')])
+ token["data"] = attrs
+ return token
+
+ def disallowed_token(self, token):
+ token_type = token["type"]
+ if token_type == "EndTag":
+ token["data"] = "" % token["name"]
+ elif token["data"]:
+ assert token_type in ("StartTag", "EmptyTag")
+ attrs = []
+ for (ns, name), v in token["data"].items():
+ attrs.append(' %s="%s"' % (name if ns is None else "%s:%s" % (prefixes[ns], name), escape(v)))
+ token["data"] = "<%s%s>" % (token["name"], ''.join(attrs))
+ else:
+ token["data"] = "<%s>" % token["name"]
+ if token.get("selfClosing"):
+ token["data"] = token["data"][:-1] + "/>"
+
+ token["type"] = "Characters"
+
+ del token["name"]
+ return token
+
+ def sanitize_css(self, style):
+ # disallow urls
+ style = re.compile(r'url\s*\(\s*[^\s)]+?\s*\)\s*').sub(' ', style)
+
+ # gauntlet
+ if not re.match(r"""^([:,;#%.\sa-zA-Z0-9!]|\w-\w|'[\s\w]+'|"[\s\w]+"|\([\d,\s]+\))*$""", style):
+ return ''
+ if not re.match(r"^\s*([-\w]+\s*:[^:;]*(;\s*|$))*$", style):
+ return ''
+
+ clean = []
+ for prop, value in re.findall(r"([-\w]+)\s*:\s*([^:;]*)", style):
+ if not value:
+ continue
+ if prop.lower() in self.allowed_css_properties:
+ clean.append(prop + ': ' + value + ';')
+ elif prop.split('-')[0].lower() in ['background', 'border', 'margin',
+ 'padding']:
+ for keyword in value.split():
+ if keyword not in self.allowed_css_keywords and \
+ not re.match(r"^(#[0-9a-fA-F]+|rgb\(\d+%?,\d*%?,?\d*%?\)?|\d{0,2}\.?\d{0,2}(cm|em|ex|in|mm|pc|pt|px|%|,|\))?)$", keyword): # noqa
+ break
+ else:
+ clean.append(prop + ': ' + value + ';')
+ elif prop.lower() in self.allowed_svg_properties:
+ clean.append(prop + ': ' + value + ';')
+
+ return ' '.join(clean)
diff --git a/lib/bleach/_vendor/html5lib/filters/whitespace.py b/lib/bleach/_vendor/html5lib/filters/whitespace.py
new file mode 100644
index 00000000..0d12584b
--- /dev/null
+++ b/lib/bleach/_vendor/html5lib/filters/whitespace.py
@@ -0,0 +1,38 @@
+from __future__ import absolute_import, division, unicode_literals
+
+import re
+
+from . import base
+from ..constants import rcdataElements, spaceCharacters
+spaceCharacters = "".join(spaceCharacters)
+
+SPACES_REGEX = re.compile("[%s]+" % spaceCharacters)
+
+
+class Filter(base.Filter):
+ """Collapses whitespace except in pre, textarea, and script elements"""
+ spacePreserveElements = frozenset(["pre", "textarea"] + list(rcdataElements))
+
+ def __iter__(self):
+ preserve = 0
+ for token in base.Filter.__iter__(self):
+ type = token["type"]
+ if type == "StartTag" \
+ and (preserve or token["name"] in self.spacePreserveElements):
+ preserve += 1
+
+ elif type == "EndTag" and preserve:
+ preserve -= 1
+
+ elif not preserve and type == "SpaceCharacters" and token["data"]:
+ # Test on token["data"] above to not introduce spaces where there were not
+ token["data"] = " "
+
+ elif not preserve and type == "Characters":
+ token["data"] = collapse_spaces(token["data"])
+
+ yield token
+
+
+def collapse_spaces(text):
+ return SPACES_REGEX.sub(' ', text)
diff --git a/lib/bleach/_vendor/html5lib/html5parser.py b/lib/bleach/_vendor/html5lib/html5parser.py
new file mode 100644
index 00000000..74d829d9
--- /dev/null
+++ b/lib/bleach/_vendor/html5lib/html5parser.py
@@ -0,0 +1,2795 @@
+from __future__ import absolute_import, division, unicode_literals
+from six import with_metaclass, viewkeys
+
+import types
+
+from . import _inputstream
+from . import _tokenizer
+
+from . import treebuilders
+from .treebuilders.base import Marker
+
+from . import _utils
+from .constants import (
+ spaceCharacters, asciiUpper2Lower,
+ specialElements, headingElements, cdataElements, rcdataElements,
+ tokenTypes, tagTokenTypes,
+ namespaces,
+ htmlIntegrationPointElements, mathmlTextIntegrationPointElements,
+ adjustForeignAttributes as adjustForeignAttributesMap,
+ adjustMathMLAttributes, adjustSVGAttributes,
+ E,
+ _ReparseException
+)
+
+
+def parse(doc, treebuilder="etree", namespaceHTMLElements=True, **kwargs):
+ """Parse an HTML document as a string or file-like object into a tree
+
+ :arg doc: the document to parse as a string or file-like object
+
+ :arg treebuilder: the treebuilder to use when parsing
+
+ :arg namespaceHTMLElements: whether or not to namespace HTML elements
+
+ :returns: parsed tree
+
+ Example:
+
+ >>> from html5lib.html5parser import parse
+ >>> parse('This is a doc
')
+
+
+ """
+ tb = treebuilders.getTreeBuilder(treebuilder)
+ p = HTMLParser(tb, namespaceHTMLElements=namespaceHTMLElements)
+ return p.parse(doc, **kwargs)
+
+
+def parseFragment(doc, container="div", treebuilder="etree", namespaceHTMLElements=True, **kwargs):
+ """Parse an HTML fragment as a string or file-like object into a tree
+
+ :arg doc: the fragment to parse as a string or file-like object
+
+ :arg container: the container context to parse the fragment in
+
+ :arg treebuilder: the treebuilder to use when parsing
+
+ :arg namespaceHTMLElements: whether or not to namespace HTML elements
+
+ :returns: parsed tree
+
+ Example:
+
+ >>> from html5lib.html5libparser import parseFragment
+ >>> parseFragment('this is a fragment ')
+
+
+ """
+ tb = treebuilders.getTreeBuilder(treebuilder)
+ p = HTMLParser(tb, namespaceHTMLElements=namespaceHTMLElements)
+ return p.parseFragment(doc, container=container, **kwargs)
+
+
+def method_decorator_metaclass(function):
+ class Decorated(type):
+ def __new__(meta, classname, bases, classDict):
+ for attributeName, attribute in classDict.items():
+ if isinstance(attribute, types.FunctionType):
+ attribute = function(attribute)
+
+ classDict[attributeName] = attribute
+ return type.__new__(meta, classname, bases, classDict)
+ return Decorated
+
+
+class HTMLParser(object):
+ """HTML parser
+
+ Generates a tree structure from a stream of (possibly malformed) HTML.
+
+ """
+
+ def __init__(self, tree=None, strict=False, namespaceHTMLElements=True, debug=False):
+ """
+ :arg tree: a treebuilder class controlling the type of tree that will be
+ returned. Built in treebuilders can be accessed through
+ html5lib.treebuilders.getTreeBuilder(treeType)
+
+ :arg strict: raise an exception when a parse error is encountered
+
+ :arg namespaceHTMLElements: whether or not to namespace HTML elements
+
+ :arg debug: whether or not to enable debug mode which logs things
+
+ Example:
+
+ >>> from html5lib.html5parser import HTMLParser
+ >>> parser = HTMLParser() # generates parser with etree builder
+ >>> parser = HTMLParser('lxml', strict=True) # generates parser with lxml builder which is strict
+
+ """
+
+ # Raise an exception on the first error encountered
+ self.strict = strict
+
+ if tree is None:
+ tree = treebuilders.getTreeBuilder("etree")
+ self.tree = tree(namespaceHTMLElements)
+ self.errors = []
+
+ self.phases = {name: cls(self, self.tree) for name, cls in
+ getPhases(debug).items()}
+
+ def _parse(self, stream, innerHTML=False, container="div", scripting=False, **kwargs):
+
+ self.innerHTMLMode = innerHTML
+ self.container = container
+ self.scripting = scripting
+ self.tokenizer = _tokenizer.HTMLTokenizer(stream, parser=self, **kwargs)
+ self.reset()
+
+ try:
+ self.mainLoop()
+ except _ReparseException:
+ self.reset()
+ self.mainLoop()
+
+ def reset(self):
+ self.tree.reset()
+ self.firstStartTag = False
+ self.errors = []
+ self.log = [] # only used with debug mode
+ # "quirks" / "limited quirks" / "no quirks"
+ self.compatMode = "no quirks"
+
+ if self.innerHTMLMode:
+ self.innerHTML = self.container.lower()
+
+ if self.innerHTML in cdataElements:
+ self.tokenizer.state = self.tokenizer.rcdataState
+ elif self.innerHTML in rcdataElements:
+ self.tokenizer.state = self.tokenizer.rawtextState
+ elif self.innerHTML == 'plaintext':
+ self.tokenizer.state = self.tokenizer.plaintextState
+ else:
+ # state already is data state
+ # self.tokenizer.state = self.tokenizer.dataState
+ pass
+ self.phase = self.phases["beforeHtml"]
+ self.phase.insertHtmlElement()
+ self.resetInsertionMode()
+ else:
+ self.innerHTML = False # pylint:disable=redefined-variable-type
+ self.phase = self.phases["initial"]
+
+ self.lastPhase = None
+
+ self.beforeRCDataPhase = None
+
+ self.framesetOK = True
+
+ @property
+ def documentEncoding(self):
+ """Name of the character encoding that was used to decode the input stream, or
+ :obj:`None` if that is not determined yet
+
+ """
+ if not hasattr(self, 'tokenizer'):
+ return None
+ return self.tokenizer.stream.charEncoding[0].name
+
+ def isHTMLIntegrationPoint(self, element):
+ if (element.name == "annotation-xml" and
+ element.namespace == namespaces["mathml"]):
+ return ("encoding" in element.attributes and
+ element.attributes["encoding"].translate(
+ asciiUpper2Lower) in
+ ("text/html", "application/xhtml+xml"))
+ else:
+ return (element.namespace, element.name) in htmlIntegrationPointElements
+
+ def isMathMLTextIntegrationPoint(self, element):
+ return (element.namespace, element.name) in mathmlTextIntegrationPointElements
+
+ def mainLoop(self):
+ CharactersToken = tokenTypes["Characters"]
+ SpaceCharactersToken = tokenTypes["SpaceCharacters"]
+ StartTagToken = tokenTypes["StartTag"]
+ EndTagToken = tokenTypes["EndTag"]
+ CommentToken = tokenTypes["Comment"]
+ DoctypeToken = tokenTypes["Doctype"]
+ ParseErrorToken = tokenTypes["ParseError"]
+
+ for token in self.tokenizer:
+ prev_token = None
+ new_token = token
+ while new_token is not None:
+ prev_token = new_token
+ currentNode = self.tree.openElements[-1] if self.tree.openElements else None
+ currentNodeNamespace = currentNode.namespace if currentNode else None
+ currentNodeName = currentNode.name if currentNode else None
+
+ type = new_token["type"]
+
+ if type == ParseErrorToken:
+ self.parseError(new_token["data"], new_token.get("datavars", {}))
+ new_token = None
+ else:
+ if (len(self.tree.openElements) == 0 or
+ currentNodeNamespace == self.tree.defaultNamespace or
+ (self.isMathMLTextIntegrationPoint(currentNode) and
+ ((type == StartTagToken and
+ token["name"] not in frozenset(["mglyph", "malignmark"])) or
+ type in (CharactersToken, SpaceCharactersToken))) or
+ (currentNodeNamespace == namespaces["mathml"] and
+ currentNodeName == "annotation-xml" and
+ type == StartTagToken and
+ token["name"] == "svg") or
+ (self.isHTMLIntegrationPoint(currentNode) and
+ type in (StartTagToken, CharactersToken, SpaceCharactersToken))):
+ phase = self.phase
+ else:
+ phase = self.phases["inForeignContent"]
+
+ if type == CharactersToken:
+ new_token = phase.processCharacters(new_token)
+ elif type == SpaceCharactersToken:
+ new_token = phase.processSpaceCharacters(new_token)
+ elif type == StartTagToken:
+ new_token = phase.processStartTag(new_token)
+ elif type == EndTagToken:
+ new_token = phase.processEndTag(new_token)
+ elif type == CommentToken:
+ new_token = phase.processComment(new_token)
+ elif type == DoctypeToken:
+ new_token = phase.processDoctype(new_token)
+
+ if (type == StartTagToken and prev_token["selfClosing"] and
+ not prev_token["selfClosingAcknowledged"]):
+ self.parseError("non-void-element-with-trailing-solidus",
+ {"name": prev_token["name"]})
+
+ # When the loop finishes it's EOF
+ reprocess = True
+ phases = []
+ while reprocess:
+ phases.append(self.phase)
+ reprocess = self.phase.processEOF()
+ if reprocess:
+ assert self.phase not in phases
+
+ def parse(self, stream, *args, **kwargs):
+ """Parse a HTML document into a well-formed tree
+
+ :arg stream: a file-like object or string containing the HTML to be parsed
+
+ The optional encoding parameter must be a string that indicates
+ the encoding. If specified, that encoding will be used,
+ regardless of any BOM or later declaration (such as in a meta
+ element).
+
+ :arg scripting: treat noscript elements as if JavaScript was turned on
+
+ :returns: parsed tree
+
+ Example:
+
+ >>> from html5lib.html5parser import HTMLParser
+ >>> parser = HTMLParser()
+ >>> parser.parse('This is a doc
')
+
+
+ """
+ self._parse(stream, False, None, *args, **kwargs)
+ return self.tree.getDocument()
+
+ def parseFragment(self, stream, *args, **kwargs):
+ """Parse a HTML fragment into a well-formed tree fragment
+
+ :arg container: name of the element we're setting the innerHTML
+ property if set to None, default to 'div'
+
+ :arg stream: a file-like object or string containing the HTML to be parsed
+
+ The optional encoding parameter must be a string that indicates
+ the encoding. If specified, that encoding will be used,
+ regardless of any BOM or later declaration (such as in a meta
+ element)
+
+ :arg scripting: treat noscript elements as if JavaScript was turned on
+
+ :returns: parsed tree
+
+ Example:
+
+ >>> from html5lib.html5libparser import HTMLParser
+ >>> parser = HTMLParser()
+ >>> parser.parseFragment('this is a fragment ')
+
+
+ """
+ self._parse(stream, True, *args, **kwargs)
+ return self.tree.getFragment()
+
+ def parseError(self, errorcode="XXX-undefined-error", datavars=None):
+ # XXX The idea is to make errorcode mandatory.
+ if datavars is None:
+ datavars = {}
+ self.errors.append((self.tokenizer.stream.position(), errorcode, datavars))
+ if self.strict:
+ raise ParseError(E[errorcode] % datavars)
+
+ def adjustMathMLAttributes(self, token):
+ adjust_attributes(token, adjustMathMLAttributes)
+
+ def adjustSVGAttributes(self, token):
+ adjust_attributes(token, adjustSVGAttributes)
+
+ def adjustForeignAttributes(self, token):
+ adjust_attributes(token, adjustForeignAttributesMap)
+
+ def reparseTokenNormal(self, token):
+ # pylint:disable=unused-argument
+ self.parser.phase()
+
+ def resetInsertionMode(self):
+ # The name of this method is mostly historical. (It's also used in the
+ # specification.)
+ last = False
+ newModes = {
+ "select": "inSelect",
+ "td": "inCell",
+ "th": "inCell",
+ "tr": "inRow",
+ "tbody": "inTableBody",
+ "thead": "inTableBody",
+ "tfoot": "inTableBody",
+ "caption": "inCaption",
+ "colgroup": "inColumnGroup",
+ "table": "inTable",
+ "head": "inBody",
+ "body": "inBody",
+ "frameset": "inFrameset",
+ "html": "beforeHead"
+ }
+ for node in self.tree.openElements[::-1]:
+ nodeName = node.name
+ new_phase = None
+ if node == self.tree.openElements[0]:
+ assert self.innerHTML
+ last = True
+ nodeName = self.innerHTML
+ # Check for conditions that should only happen in the innerHTML
+ # case
+ if nodeName in ("select", "colgroup", "head", "html"):
+ assert self.innerHTML
+
+ if not last and node.namespace != self.tree.defaultNamespace:
+ continue
+
+ if nodeName in newModes:
+ new_phase = self.phases[newModes[nodeName]]
+ break
+ elif last:
+ new_phase = self.phases["inBody"]
+ break
+
+ self.phase = new_phase
+
+ def parseRCDataRawtext(self, token, contentType):
+ # Generic RCDATA/RAWTEXT Parsing algorithm
+ assert contentType in ("RAWTEXT", "RCDATA")
+
+ self.tree.insertElement(token)
+
+ if contentType == "RAWTEXT":
+ self.tokenizer.state = self.tokenizer.rawtextState
+ else:
+ self.tokenizer.state = self.tokenizer.rcdataState
+
+ self.originalPhase = self.phase
+
+ self.phase = self.phases["text"]
+
+
+@_utils.memoize
+def getPhases(debug):
+ def log(function):
+ """Logger that records which phase processes each token"""
+ type_names = {value: key for key, value in tokenTypes.items()}
+
+ def wrapped(self, *args, **kwargs):
+ if function.__name__.startswith("process") and len(args) > 0:
+ token = args[0]
+ info = {"type": type_names[token['type']]}
+ if token['type'] in tagTokenTypes:
+ info["name"] = token['name']
+
+ self.parser.log.append((self.parser.tokenizer.state.__name__,
+ self.parser.phase.__class__.__name__,
+ self.__class__.__name__,
+ function.__name__,
+ info))
+ return function(self, *args, **kwargs)
+ else:
+ return function(self, *args, **kwargs)
+ return wrapped
+
+ def getMetaclass(use_metaclass, metaclass_func):
+ if use_metaclass:
+ return method_decorator_metaclass(metaclass_func)
+ else:
+ return type
+
+ # pylint:disable=unused-argument
+ class Phase(with_metaclass(getMetaclass(debug, log))):
+ """Base class for helper object that implements each phase of processing
+ """
+ __slots__ = ("parser", "tree", "__startTagCache", "__endTagCache")
+
+ def __init__(self, parser, tree):
+ self.parser = parser
+ self.tree = tree
+ self.__startTagCache = {}
+ self.__endTagCache = {}
+
+ def processEOF(self):
+ raise NotImplementedError
+
+ def processComment(self, token):
+ # For most phases the following is correct. Where it's not it will be
+ # overridden.
+ self.tree.insertComment(token, self.tree.openElements[-1])
+
+ def processDoctype(self, token):
+ self.parser.parseError("unexpected-doctype")
+
+ def processCharacters(self, token):
+ self.tree.insertText(token["data"])
+
+ def processSpaceCharacters(self, token):
+ self.tree.insertText(token["data"])
+
+ def processStartTag(self, token):
+ # Note the caching is done here rather than BoundMethodDispatcher as doing it there
+ # requires a circular reference to the Phase, and this ends up with a significant
+ # (CPython 2.7, 3.8) GC cost when parsing many short inputs
+ name = token["name"]
+ # In Py2, using `in` is quicker in general than try/except KeyError
+ # In Py3, `in` is quicker when there are few cache hits (typically short inputs)
+ if name in self.__startTagCache:
+ func = self.__startTagCache[name]
+ else:
+ func = self.__startTagCache[name] = self.startTagHandler[name]
+ # bound the cache size in case we get loads of unknown tags
+ while len(self.__startTagCache) > len(self.startTagHandler) * 1.1:
+ # this makes the eviction policy random on Py < 3.7 and FIFO >= 3.7
+ self.__startTagCache.pop(next(iter(self.__startTagCache)))
+ return func(token)
+
+ def startTagHtml(self, token):
+ if not self.parser.firstStartTag and token["name"] == "html":
+ self.parser.parseError("non-html-root")
+ # XXX Need a check here to see if the first start tag token emitted is
+ # this token... If it's not, invoke self.parser.parseError().
+ for attr, value in token["data"].items():
+ if attr not in self.tree.openElements[0].attributes:
+ self.tree.openElements[0].attributes[attr] = value
+ self.parser.firstStartTag = False
+
+ def processEndTag(self, token):
+ # Note the caching is done here rather than BoundMethodDispatcher as doing it there
+ # requires a circular reference to the Phase, and this ends up with a significant
+ # (CPython 2.7, 3.8) GC cost when parsing many short inputs
+ name = token["name"]
+ # In Py2, using `in` is quicker in general than try/except KeyError
+ # In Py3, `in` is quicker when there are few cache hits (typically short inputs)
+ if name in self.__endTagCache:
+ func = self.__endTagCache[name]
+ else:
+ func = self.__endTagCache[name] = self.endTagHandler[name]
+ # bound the cache size in case we get loads of unknown tags
+ while len(self.__endTagCache) > len(self.endTagHandler) * 1.1:
+ # this makes the eviction policy random on Py < 3.7 and FIFO >= 3.7
+ self.__endTagCache.pop(next(iter(self.__endTagCache)))
+ return func(token)
+
+ class InitialPhase(Phase):
+ __slots__ = tuple()
+
+ def processSpaceCharacters(self, token):
+ pass
+
+ def processComment(self, token):
+ self.tree.insertComment(token, self.tree.document)
+
+ def processDoctype(self, token):
+ name = token["name"]
+ publicId = token["publicId"]
+ systemId = token["systemId"]
+ correct = token["correct"]
+
+ if (name != "html" or publicId is not None or
+ systemId is not None and systemId != "about:legacy-compat"):
+ self.parser.parseError("unknown-doctype")
+
+ if publicId is None:
+ publicId = ""
+
+ self.tree.insertDoctype(token)
+
+ if publicId != "":
+ publicId = publicId.translate(asciiUpper2Lower)
+
+ if (not correct or token["name"] != "html" or
+ publicId.startswith(
+ ("+//silmaril//dtd html pro v0r11 19970101//",
+ "-//advasoft ltd//dtd html 3.0 aswedit + extensions//",
+ "-//as//dtd html 3.0 aswedit + extensions//",
+ "-//ietf//dtd html 2.0 level 1//",
+ "-//ietf//dtd html 2.0 level 2//",
+ "-//ietf//dtd html 2.0 strict level 1//",
+ "-//ietf//dtd html 2.0 strict level 2//",
+ "-//ietf//dtd html 2.0 strict//",
+ "-//ietf//dtd html 2.0//",
+ "-//ietf//dtd html 2.1e//",
+ "-//ietf//dtd html 3.0//",
+ "-//ietf//dtd html 3.2 final//",
+ "-//ietf//dtd html 3.2//",
+ "-//ietf//dtd html 3//",
+ "-//ietf//dtd html level 0//",
+ "-//ietf//dtd html level 1//",
+ "-//ietf//dtd html level 2//",
+ "-//ietf//dtd html level 3//",
+ "-//ietf//dtd html strict level 0//",
+ "-//ietf//dtd html strict level 1//",
+ "-//ietf//dtd html strict level 2//",
+ "-//ietf//dtd html strict level 3//",
+ "-//ietf//dtd html strict//",
+ "-//ietf//dtd html//",
+ "-//metrius//dtd metrius presentational//",
+ "-//microsoft//dtd internet explorer 2.0 html strict//",
+ "-//microsoft//dtd internet explorer 2.0 html//",
+ "-//microsoft//dtd internet explorer 2.0 tables//",
+ "-//microsoft//dtd internet explorer 3.0 html strict//",
+ "-//microsoft//dtd internet explorer 3.0 html//",
+ "-//microsoft//dtd internet explorer 3.0 tables//",
+ "-//netscape comm. corp.//dtd html//",
+ "-//netscape comm. corp.//dtd strict html//",
+ "-//o'reilly and associates//dtd html 2.0//",
+ "-//o'reilly and associates//dtd html extended 1.0//",
+ "-//o'reilly and associates//dtd html extended relaxed 1.0//",
+ "-//softquad software//dtd hotmetal pro 6.0::19990601::extensions to html 4.0//",
+ "-//softquad//dtd hotmetal pro 4.0::19971010::extensions to html 4.0//",
+ "-//spyglass//dtd html 2.0 extended//",
+ "-//sq//dtd html 2.0 hotmetal + extensions//",
+ "-//sun microsystems corp.//dtd hotjava html//",
+ "-//sun microsystems corp.//dtd hotjava strict html//",
+ "-//w3c//dtd html 3 1995-03-24//",
+ "-//w3c//dtd html 3.2 draft//",
+ "-//w3c//dtd html 3.2 final//",
+ "-//w3c//dtd html 3.2//",
+ "-//w3c//dtd html 3.2s draft//",
+ "-//w3c//dtd html 4.0 frameset//",
+ "-//w3c//dtd html 4.0 transitional//",
+ "-//w3c//dtd html experimental 19960712//",
+ "-//w3c//dtd html experimental 970421//",
+ "-//w3c//dtd w3 html//",
+ "-//w3o//dtd w3 html 3.0//",
+ "-//webtechs//dtd mozilla html 2.0//",
+ "-//webtechs//dtd mozilla html//")) or
+ publicId in ("-//w3o//dtd w3 html strict 3.0//en//",
+ "-/w3c/dtd html 4.0 transitional/en",
+ "html") or
+ publicId.startswith(
+ ("-//w3c//dtd html 4.01 frameset//",
+ "-//w3c//dtd html 4.01 transitional//")) and
+ systemId is None or
+ systemId and systemId.lower() == "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd"):
+ self.parser.compatMode = "quirks"
+ elif (publicId.startswith(
+ ("-//w3c//dtd xhtml 1.0 frameset//",
+ "-//w3c//dtd xhtml 1.0 transitional//")) or
+ publicId.startswith(
+ ("-//w3c//dtd html 4.01 frameset//",
+ "-//w3c//dtd html 4.01 transitional//")) and
+ systemId is not None):
+ self.parser.compatMode = "limited quirks"
+
+ self.parser.phase = self.parser.phases["beforeHtml"]
+
+ def anythingElse(self):
+ self.parser.compatMode = "quirks"
+ self.parser.phase = self.parser.phases["beforeHtml"]
+
+ def processCharacters(self, token):
+ self.parser.parseError("expected-doctype-but-got-chars")
+ self.anythingElse()
+ return token
+
+ def processStartTag(self, token):
+ self.parser.parseError("expected-doctype-but-got-start-tag",
+ {"name": token["name"]})
+ self.anythingElse()
+ return token
+
+ def processEndTag(self, token):
+ self.parser.parseError("expected-doctype-but-got-end-tag",
+ {"name": token["name"]})
+ self.anythingElse()
+ return token
+
+ def processEOF(self):
+ self.parser.parseError("expected-doctype-but-got-eof")
+ self.anythingElse()
+ return True
+
+ class BeforeHtmlPhase(Phase):
+ __slots__ = tuple()
+
+ # helper methods
+ def insertHtmlElement(self):
+ self.tree.insertRoot(impliedTagToken("html", "StartTag"))
+ self.parser.phase = self.parser.phases["beforeHead"]
+
+ # other
+ def processEOF(self):
+ self.insertHtmlElement()
+ return True
+
+ def processComment(self, token):
+ self.tree.insertComment(token, self.tree.document)
+
+ def processSpaceCharacters(self, token):
+ pass
+
+ def processCharacters(self, token):
+ self.insertHtmlElement()
+ return token
+
+ def processStartTag(self, token):
+ if token["name"] == "html":
+ self.parser.firstStartTag = True
+ self.insertHtmlElement()
+ return token
+
+ def processEndTag(self, token):
+ if token["name"] not in ("head", "body", "html", "br"):
+ self.parser.parseError("unexpected-end-tag-before-html",
+ {"name": token["name"]})
+ else:
+ self.insertHtmlElement()
+ return token
+
+ class BeforeHeadPhase(Phase):
+ __slots__ = tuple()
+
+ def processEOF(self):
+ self.startTagHead(impliedTagToken("head", "StartTag"))
+ return True
+
+ def processSpaceCharacters(self, token):
+ pass
+
+ def processCharacters(self, token):
+ self.startTagHead(impliedTagToken("head", "StartTag"))
+ return token
+
+ def startTagHtml(self, token):
+ return self.parser.phases["inBody"].processStartTag(token)
+
+ def startTagHead(self, token):
+ self.tree.insertElement(token)
+ self.tree.headPointer = self.tree.openElements[-1]
+ self.parser.phase = self.parser.phases["inHead"]
+
+ def startTagOther(self, token):
+ self.startTagHead(impliedTagToken("head", "StartTag"))
+ return token
+
+ def endTagImplyHead(self, token):
+ self.startTagHead(impliedTagToken("head", "StartTag"))
+ return token
+
+ def endTagOther(self, token):
+ self.parser.parseError("end-tag-after-implied-root",
+ {"name": token["name"]})
+
+ startTagHandler = _utils.MethodDispatcher([
+ ("html", startTagHtml),
+ ("head", startTagHead)
+ ])
+ startTagHandler.default = startTagOther
+
+ endTagHandler = _utils.MethodDispatcher([
+ (("head", "body", "html", "br"), endTagImplyHead)
+ ])
+ endTagHandler.default = endTagOther
+
+ class InHeadPhase(Phase):
+ __slots__ = tuple()
+
+ # the real thing
+ def processEOF(self):
+ self.anythingElse()
+ return True
+
+ def processCharacters(self, token):
+ self.anythingElse()
+ return token
+
+ def startTagHtml(self, token):
+ return self.parser.phases["inBody"].processStartTag(token)
+
+ def startTagHead(self, token):
+ self.parser.parseError("two-heads-are-not-better-than-one")
+
+ def startTagBaseLinkCommand(self, token):
+ self.tree.insertElement(token)
+ self.tree.openElements.pop()
+ token["selfClosingAcknowledged"] = True
+
+ def startTagMeta(self, token):
+ self.tree.insertElement(token)
+ self.tree.openElements.pop()
+ token["selfClosingAcknowledged"] = True
+
+ attributes = token["data"]
+ if self.parser.tokenizer.stream.charEncoding[1] == "tentative":
+ if "charset" in attributes:
+ self.parser.tokenizer.stream.changeEncoding(attributes["charset"])
+ elif ("content" in attributes and
+ "http-equiv" in attributes and
+ attributes["http-equiv"].lower() == "content-type"):
+ # Encoding it as UTF-8 here is a hack, as really we should pass
+ # the abstract Unicode string, and just use the
+ # ContentAttrParser on that, but using UTF-8 allows all chars
+ # to be encoded and as a ASCII-superset works.
+ data = _inputstream.EncodingBytes(attributes["content"].encode("utf-8"))
+ parser = _inputstream.ContentAttrParser(data)
+ codec = parser.parse()
+ self.parser.tokenizer.stream.changeEncoding(codec)
+
+ def startTagTitle(self, token):
+ self.parser.parseRCDataRawtext(token, "RCDATA")
+
+ def startTagNoFramesStyle(self, token):
+ # Need to decide whether to implement the scripting-disabled case
+ self.parser.parseRCDataRawtext(token, "RAWTEXT")
+
+ def startTagNoscript(self, token):
+ if self.parser.scripting:
+ self.parser.parseRCDataRawtext(token, "RAWTEXT")
+ else:
+ self.tree.insertElement(token)
+ self.parser.phase = self.parser.phases["inHeadNoscript"]
+
+ def startTagScript(self, token):
+ self.tree.insertElement(token)
+ self.parser.tokenizer.state = self.parser.tokenizer.scriptDataState
+ self.parser.originalPhase = self.parser.phase
+ self.parser.phase = self.parser.phases["text"]
+
+ def startTagOther(self, token):
+ self.anythingElse()
+ return token
+
+ def endTagHead(self, token):
+ node = self.parser.tree.openElements.pop()
+ assert node.name == "head", "Expected head got %s" % node.name
+ self.parser.phase = self.parser.phases["afterHead"]
+
+ def endTagHtmlBodyBr(self, token):
+ self.anythingElse()
+ return token
+
+ def endTagOther(self, token):
+ self.parser.parseError("unexpected-end-tag", {"name": token["name"]})
+
+ def anythingElse(self):
+ self.endTagHead(impliedTagToken("head"))
+
+ startTagHandler = _utils.MethodDispatcher([
+ ("html", startTagHtml),
+ ("title", startTagTitle),
+ (("noframes", "style"), startTagNoFramesStyle),
+ ("noscript", startTagNoscript),
+ ("script", startTagScript),
+ (("base", "basefont", "bgsound", "command", "link"),
+ startTagBaseLinkCommand),
+ ("meta", startTagMeta),
+ ("head", startTagHead)
+ ])
+ startTagHandler.default = startTagOther
+
+ endTagHandler = _utils.MethodDispatcher([
+ ("head", endTagHead),
+ (("br", "html", "body"), endTagHtmlBodyBr)
+ ])
+ endTagHandler.default = endTagOther
+
+ class InHeadNoscriptPhase(Phase):
+ __slots__ = tuple()
+
+ def processEOF(self):
+ self.parser.parseError("eof-in-head-noscript")
+ self.anythingElse()
+ return True
+
+ def processComment(self, token):
+ return self.parser.phases["inHead"].processComment(token)
+
+ def processCharacters(self, token):
+ self.parser.parseError("char-in-head-noscript")
+ self.anythingElse()
+ return token
+
+ def processSpaceCharacters(self, token):
+ return self.parser.phases["inHead"].processSpaceCharacters(token)
+
+ def startTagHtml(self, token):
+ return self.parser.phases["inBody"].processStartTag(token)
+
+ def startTagBaseLinkCommand(self, token):
+ return self.parser.phases["inHead"].processStartTag(token)
+
+ def startTagHeadNoscript(self, token):
+ self.parser.parseError("unexpected-start-tag", {"name": token["name"]})
+
+ def startTagOther(self, token):
+ self.parser.parseError("unexpected-inhead-noscript-tag", {"name": token["name"]})
+ self.anythingElse()
+ return token
+
+ def endTagNoscript(self, token):
+ node = self.parser.tree.openElements.pop()
+ assert node.name == "noscript", "Expected noscript got %s" % node.name
+ self.parser.phase = self.parser.phases["inHead"]
+
+ def endTagBr(self, token):
+ self.parser.parseError("unexpected-inhead-noscript-tag", {"name": token["name"]})
+ self.anythingElse()
+ return token
+
+ def endTagOther(self, token):
+ self.parser.parseError("unexpected-end-tag", {"name": token["name"]})
+
+ def anythingElse(self):
+ # Caller must raise parse error first!
+ self.endTagNoscript(impliedTagToken("noscript"))
+
+ startTagHandler = _utils.MethodDispatcher([
+ ("html", startTagHtml),
+ (("basefont", "bgsound", "link", "meta", "noframes", "style"), startTagBaseLinkCommand),
+ (("head", "noscript"), startTagHeadNoscript),
+ ])
+ startTagHandler.default = startTagOther
+
+ endTagHandler = _utils.MethodDispatcher([
+ ("noscript", endTagNoscript),
+ ("br", endTagBr),
+ ])
+ endTagHandler.default = endTagOther
+
+ class AfterHeadPhase(Phase):
+ __slots__ = tuple()
+
+ def processEOF(self):
+ self.anythingElse()
+ return True
+
+ def processCharacters(self, token):
+ self.anythingElse()
+ return token
+
+ def startTagHtml(self, token):
+ return self.parser.phases["inBody"].processStartTag(token)
+
+ def startTagBody(self, token):
+ self.parser.framesetOK = False
+ self.tree.insertElement(token)
+ self.parser.phase = self.parser.phases["inBody"]
+
+ def startTagFrameset(self, token):
+ self.tree.insertElement(token)
+ self.parser.phase = self.parser.phases["inFrameset"]
+
+ def startTagFromHead(self, token):
+ self.parser.parseError("unexpected-start-tag-out-of-my-head",
+ {"name": token["name"]})
+ self.tree.openElements.append(self.tree.headPointer)
+ self.parser.phases["inHead"].processStartTag(token)
+ for node in self.tree.openElements[::-1]:
+ if node.name == "head":
+ self.tree.openElements.remove(node)
+ break
+
+ def startTagHead(self, token):
+ self.parser.parseError("unexpected-start-tag", {"name": token["name"]})
+
+ def startTagOther(self, token):
+ self.anythingElse()
+ return token
+
+ def endTagHtmlBodyBr(self, token):
+ self.anythingElse()
+ return token
+
+ def endTagOther(self, token):
+ self.parser.parseError("unexpected-end-tag", {"name": token["name"]})
+
+ def anythingElse(self):
+ self.tree.insertElement(impliedTagToken("body", "StartTag"))
+ self.parser.phase = self.parser.phases["inBody"]
+ self.parser.framesetOK = True
+
+ startTagHandler = _utils.MethodDispatcher([
+ ("html", startTagHtml),
+ ("body", startTagBody),
+ ("frameset", startTagFrameset),
+ (("base", "basefont", "bgsound", "link", "meta", "noframes", "script",
+ "style", "title"),
+ startTagFromHead),
+ ("head", startTagHead)
+ ])
+ startTagHandler.default = startTagOther
+ endTagHandler = _utils.MethodDispatcher([(("body", "html", "br"),
+ endTagHtmlBodyBr)])
+ endTagHandler.default = endTagOther
+
+ class InBodyPhase(Phase):
+ # http://www.whatwg.org/specs/web-apps/current-work/#parsing-main-inbody
+ # the really-really-really-very crazy mode
+ __slots__ = ("processSpaceCharacters",)
+
+ def __init__(self, *args, **kwargs):
+ super(InBodyPhase, self).__init__(*args, **kwargs)
+ # Set this to the default handler
+ self.processSpaceCharacters = self.processSpaceCharactersNonPre
+
+ def isMatchingFormattingElement(self, node1, node2):
+ return (node1.name == node2.name and
+ node1.namespace == node2.namespace and
+ node1.attributes == node2.attributes)
+
+ # helper
+ def addFormattingElement(self, token):
+ self.tree.insertElement(token)
+ element = self.tree.openElements[-1]
+
+ matchingElements = []
+ for node in self.tree.activeFormattingElements[::-1]:
+ if node is Marker:
+ break
+ elif self.isMatchingFormattingElement(node, element):
+ matchingElements.append(node)
+
+ assert len(matchingElements) <= 3
+ if len(matchingElements) == 3:
+ self.tree.activeFormattingElements.remove(matchingElements[-1])
+ self.tree.activeFormattingElements.append(element)
+
+ # the real deal
+ def processEOF(self):
+ allowed_elements = frozenset(("dd", "dt", "li", "p", "tbody", "td",
+ "tfoot", "th", "thead", "tr", "body",
+ "html"))
+ for node in self.tree.openElements[::-1]:
+ if node.name not in allowed_elements:
+ self.parser.parseError("expected-closing-tag-but-got-eof")
+ break
+ # Stop parsing
+
+ def processSpaceCharactersDropNewline(self, token):
+ # Sometimes (start of , , and