From 453c46df0038aaf221db2d3238f864d43c0d3ee0 Mon Sep 17 00:00:00 2001
From: JonnyWong16 <Jonny.Wong.16@gmail.com>
Date: Wed, 4 May 2016 17:45:48 -0700
Subject: [PATCH] Add bleach library to clean notification HTML

---
 lib/bleach/__init__.py  | 401 ++++++++++++++++++++++++++++++++++++++++
 lib/bleach/callbacks.py |  20 ++
 lib/bleach/encoding.py  |  62 +++++++
 lib/bleach/sanitizer.py | 148 +++++++++++++++
 4 files changed, 631 insertions(+)
 create mode 100644 lib/bleach/__init__.py
 create mode 100644 lib/bleach/callbacks.py
 create mode 100644 lib/bleach/encoding.py
 create mode 100644 lib/bleach/sanitizer.py

diff --git a/lib/bleach/__init__.py b/lib/bleach/__init__.py
new file mode 100644
index 00000000..aec2d340
--- /dev/null
+++ b/lib/bleach/__init__.py
@@ -0,0 +1,401 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import unicode_literals
+import logging
+import re
+
+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
+
+
+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(?<![@.])(?:(?:{0}):/{{0,3}}(?:(?:\w+:)?\w+@)?)?  # http://
+    ([\w-]+\.)+(?:{1})(?:\:\d+)?(?!\.\w)\b   # xx.yy.tld(:##)?
+    (?:[/?][^\s\{{\}}\|\\\^\[\]`<>"]*)?
+        # /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'([\.,]+)$')
+
+email_re = re.compile(
+    r"""(?<!//)
+    (([-!#$%&'*+/=?^_`{0!s}|~0-9A-Z]+
+        (\.[-!#$%&'*+/=?^_`{1!s}|~0-9A-Z]+)*  # dot-atom
+    |^"([\001-\010\013\014\016-\037!#-\[\]-\177]
+        |\\[\001-011\013\014\016-\177])*"  # quoted-string
+    )@(?:[A-Z0-9](?:[A-Z0-9-]{0,61}[A-Z0-9])?\.)+[A-Z]{2,6})\.?  # domain
+    """,
+    re.IGNORECASE | re.MULTILINE | re.VERBOSE)
+
+NODE_TEXT = 4  # The numeric ID of a text node in simpletree.
+
+ETREE_TAG = lambda x: "".join(['{http://www.w3.org/1999/xhtml}', x])
+# a simple routine that returns the tag name with the namespace prefix
+# as returned by etree's Element.tag attribute
+
+DEFAULT_CALLBACKS = [linkify_callbacks.nofollow]
+
+
+def clean(text, tags=ALLOWED_TAGS, attributes=ALLOWED_ATTRIBUTES,
+          styles=ALLOWED_STYLES, protocols=ALLOWED_PROTOCOLS, strip=False,
+          strip_comments=True):
+    """Clean an HTML fragment and return it
+
+    :arg text: the text to clean
+    :arg tags: whitelist of allowed tags; defaults to
+        ``bleach.ALLOWED_TAGS``
+    :arg attributes: whitelist of allowed attributes; defaults to
+        ``bleach.ALLOWED_ATTRIBUTES``
+    :arg styles: whitelist of allowed css; defaults to
+        ``bleach.ALLOWED_STYLES``
+    :arg protocols: whitelist of allowed protocols for links; defaults
+        to ``bleach.ALLOWED_PROTOCOLS``
+    :arg strip: whether or not to strip disallowed elements
+    :arg strip_comments: whether or not to strip HTML comments
+
+    """
+    if not text:
+        return ''
+
+    text = force_unicode(text)
+
+    class s(BleachSanitizer):
+        allowed_elements = tags
+        allowed_attributes = attributes
+        allowed_css_properties = styles
+        allowed_protocols = protocols
+        strip_disallowed_elements = strip
+        strip_html_comments = strip_comments
+
+    parser = html5lib.HTMLParser(tokenizer=s)
+
+    return _render(parser.parseFragment(text))
+
+
+def linkify(text, callbacks=DEFAULT_CALLBACKS, skip_pre=False,
+            parse_email=False, tokenizer=HTMLSanitizer):
+    """Convert URL-like strings in an HTML fragment to links.
+
+    linkify() converts strings that look like URLs or domain names in a
+    blob of text that may be an HTML fragment to links, while preserving
+    (a) links already in the string, (b) urls found in attributes, and
+    (c) email addresses.
+    """
+    text = force_unicode(text)
+
+    if not text:
+        return ''
+
+    parser = html5lib.HTMLParser(tokenizer=tokenizer)
+
+    forest = parser.parseFragment(text)
+    _seen = set([])
+
+    def replace_nodes(tree, new_frag, node, index=0):
+        """
+        Doesn't really replace nodes, but inserts the nodes contained in
+        new_frag into the treee at position index and returns the number
+        of nodes inserted.
+        If node is passed in, it is removed from the tree
+        """
+        count = 0
+        new_tree = parser.parseFragment(new_frag)
+        # capture any non-tag text at the start of the fragment
+        if new_tree.text:
+            if index == 0:
+                tree.text = tree.text or ''
+                tree.text += new_tree.text
+            else:
+                tree[index - 1].tail = tree[index - 1].tail or ''
+                tree[index - 1].tail += new_tree.text
+        # the put in the tagged elements into the old tree
+        for n in new_tree:
+            if n.tag == ETREE_TAG('a'):
+                _seen.add(n)
+            tree.insert(index + count, n)
+            count += 1
+        # if we got a node to remove...
+        if node is not None:
+            tree.remove(node)
+        return count
+
+    def strip_wrapping_parentheses(fragment):
+        """Strips wrapping parentheses.
+
+        Returns a tuple of the following format::
+
+            (string stripped from wrapping parentheses,
+             count of stripped opening parentheses,
+             count of stripped closing parentheses)
+        """
+        opening_parentheses = closing_parentheses = 0
+        # Count consecutive opening parentheses
+        # at the beginning of the fragment (string).
+        for char in fragment:
+            if char == '(':
+                opening_parentheses += 1
+            else:
+                break
+
+        if opening_parentheses:
+            newer_frag = ''
+            # Cut the consecutive opening brackets from the fragment.
+            fragment = fragment[opening_parentheses:]
+            # Reverse the fragment for easier detection of parentheses
+            # inside the URL.
+            reverse_fragment = fragment[::-1]
+            skip = False
+            for char in reverse_fragment:
+                # Remove the closing parentheses if it has a matching
+                # opening parentheses (they are balanced).
+                if (char == ')' and
+                        closing_parentheses < opening_parentheses and
+                        not skip):
+                    closing_parentheses += 1
+                    continue
+                # Do not remove ')' from the URL itself.
+                elif char != ')':
+                    skip = True
+                newer_frag += char
+            fragment = newer_frag[::-1]
+
+        return fragment, opening_parentheses, closing_parentheses
+
+    def apply_callbacks(attrs, new):
+        for cb in callbacks:
+            attrs = cb(attrs, new)
+            if attrs is None:
+                return None
+        return attrs
+
+    def _render_inner(node):
+        out = ['' if node.text is None else node.text]
+        for subnode in node:
+            out.append(_render(subnode))
+            if subnode.tail:
+                out.append(subnode.tail)
+        return ''.join(out)
+
+    def linkify_nodes(tree, parse_text=True):
+        children = len(tree)
+        current_child = -1
+        # start at -1 to process the parent first
+        while current_child < len(tree):
+            if current_child < 0:
+                node = tree
+                if parse_text and node.text:
+                    new_txt = old_txt = node.text
+                    if parse_email:
+                        new_txt = re.sub(email_re, email_repl, node.text)
+                        if new_txt and new_txt != node.text:
+                            node.text = ''
+                            adj = replace_nodes(tree, new_txt, None, 0)
+                            children += adj
+                            current_child += adj
+                            linkify_nodes(tree, True)
+                            continue
+
+                    new_txt = re.sub(url_re, link_repl, new_txt)
+                    if new_txt != old_txt:
+                        node.text = ''
+                        adj = replace_nodes(tree, new_txt, None, 0)
+                        children += adj
+                        current_child += adj
+                        continue
+            else:
+                node = tree[current_child]
+
+            if parse_text and node.tail:
+                new_tail = old_tail = node.tail
+                if parse_email:
+                    new_tail = re.sub(email_re, email_repl, new_tail)
+                    if new_tail != node.tail:
+                        node.tail = ''
+                        adj = replace_nodes(tree, new_tail, None,
+                                            current_child + 1)
+                        # Insert the new nodes made from my tail into
+                        # the tree right after me. current_child+1
+                        children += adj
+                        continue
+
+                new_tail = re.sub(url_re, link_repl, new_tail)
+                if new_tail != old_tail:
+                    node.tail = ''
+                    adj = replace_nodes(tree, new_tail, None,
+                                        current_child + 1)
+                    children += adj
+
+            if node.tag == ETREE_TAG('a') and not (node in _seen):
+                if not node.get('href', None) is None:
+                    attrs = dict(node.items())
+
+                    _text = attrs['_text'] = _render_inner(node)
+
+                    attrs = apply_callbacks(attrs, False)
+
+                    if attrs is None:
+                        # <a> 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('"', '&quot;')
+        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 = '<a href="{0!s}" {1!s}>{2!s}</a>'
+        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}<a href="{1!s}" {2!s}>{3!s}</a>{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)
diff --git a/lib/bleach/callbacks.py b/lib/bleach/callbacks.py
new file mode 100644
index 00000000..3cb82c25
--- /dev/null
+++ b/lib/bleach/callbacks.py
@@ -0,0 +1,20 @@
+"""A set of basic callbacks for bleach.linkify."""
+from __future__ import unicode_literals
+
+
+def nofollow(attrs, new=False):
+    if attrs['href'].startswith('mailto:'):
+        return attrs
+    rel = [x for x in attrs.get('rel', '').split(' ') if x]
+    if 'nofollow' not in [x.lower() for x in rel]:
+        rel.append('nofollow')
+    attrs['rel'] = ' '.join(rel)
+
+    return attrs
+
+
+def target_blank(attrs, new=False):
+    if attrs['href'].startswith('mailto:'):
+        return attrs
+    attrs['target'] = '_blank'
+    return attrs
diff --git a/lib/bleach/encoding.py b/lib/bleach/encoding.py
new file mode 100644
index 00000000..707adaa2
--- /dev/null
+++ b/lib/bleach/encoding.py
@@ -0,0 +1,62 @@
+import datetime
+from decimal import Decimal
+import types
+import six
+
+
+def is_protected_type(obj):
+    """Determine if the object instance is of a protected type.
+
+    Objects of protected types are preserved as-is when passed to
+    force_unicode(strings_only=True).
+    """
+    return isinstance(obj, (
+        six.integer_types +
+        (types.NoneType,
+         datetime.datetime, datetime.date, datetime.time,
+         float, Decimal))
+    )
+
+
+def force_unicode(s, encoding='utf-8', strings_only=False, errors='strict'):
+    """
+    Similar to smart_text, except that lazy instances are resolved to
+    strings, rather than kept as lazy objects.
+
+    If strings_only is True, don't convert (some) non-string-like objects.
+    """
+    # Handle the common case first, saves 30-40% when s is an instance of
+    # six.text_type. This function gets called often in that setting.
+    if isinstance(s, six.text_type):
+        return s
+    if strings_only and is_protected_type(s):
+        return s
+    try:
+        if not isinstance(s, six.string_types):
+            if hasattr(s, '__unicode__'):
+                s = s.__unicode__()
+            else:
+                if six.PY3:
+                    if isinstance(s, bytes):
+                        s = six.text_type(s, encoding, errors)
+                    else:
+                        s = six.text_type(s)
+                else:
+                    s = six.text_type(bytes(s), encoding, errors)
+        else:
+            # Note: We use .decode() here, instead of six.text_type(s,
+            # encoding, errors), so that if s is a SafeBytes, it ends up being
+            # a SafeText at the end.
+            s = s.decode(encoding, errors)
+    except UnicodeDecodeError as e:
+        if not isinstance(s, Exception):
+            raise UnicodeDecodeError(*e.args)
+        else:
+            # If we get to here, the caller has passed in an Exception
+            # subclass populated with non-ASCII bytestring data without a
+            # working unicode method. Try to handle this without raising a
+            # further exception by individually forcing the exception args
+            # to unicode.
+            s = ' '.join([force_unicode(arg, encoding, strings_only,
+                          errors) for arg in s])
+    return s
diff --git a/lib/bleach/sanitizer.py b/lib/bleach/sanitizer.py
new file mode 100644
index 00000000..8bdca752
--- /dev/null
+++ b/lib/bleach/sanitizer.py
@@ -0,0 +1,148 @@
+from __future__ import unicode_literals
+import re
+from xml.sax.saxutils import escape, unescape
+
+from html5lib.constants import tokenTypes
+from html5lib.sanitizer import HTMLSanitizerMixin
+from html5lib.tokenizer import HTMLTokenizer
+
+
+PROTOS = HTMLSanitizerMixin.acceptable_protocols
+PROTOS.remove('feed')
+
+
+class BleachSanitizerMixin(HTMLSanitizerMixin):
+    """Mixin to replace sanitize_token() and sanitize_css()."""
+
+    allowed_svg_properties = []
+
+    def sanitize_token(self, token):
+        """Sanitize a token either by HTML-encoding or dropping.
+
+        Unlike HTMLSanitizerMixin.sanitize_token, allowed_attributes can be
+        a dict of {'tag': ['attribute', 'pairs'], 'tag': callable}.
+
+        Here callable is a function with two arguments of attribute name
+        and value. It should return true of false.
+
+        Also gives the option to strip tags instead of encoding.
+
+        """
+        if (getattr(self, 'wildcard_attributes', None) is None and
+                isinstance(self.allowed_attributes, dict)):
+            self.wildcard_attributes = self.allowed_attributes.get('*', [])
+
+        if token['type'] in (tokenTypes['StartTag'], tokenTypes['EndTag'],
+                             tokenTypes['EmptyTag']):
+            if token['name'] in self.allowed_elements:
+                if 'data' in token:
+                    if isinstance(self.allowed_attributes, dict):
+                        allowed_attributes = self.allowed_attributes.get(
+                            token['name'], [])
+                        print callable(allowed_attributes)
+                        if not callable(allowed_attributes):
+                            allowed_attributes += self.wildcard_attributes
+                    else:
+                        allowed_attributes = self.allowed_attributes
+                    attrs = dict([(name, val) for name, val in
+                                  token['data'][::-1]
+                                  if (allowed_attributes(name, val)
+                                      if callable(allowed_attributes)
+                                      else name in allowed_attributes)])
+                    for attr in self.attr_val_is_uri:
+                        if attr not in attrs:
+                            continue
+                        val_unescaped = re.sub("[`\000-\040\177-\240\s]+", '',
+                                               unescape(attrs[attr])).lower()
+                        # Remove replacement characters from unescaped
+                        # characters.
+                        val_unescaped = val_unescaped.replace("\ufffd", "")
+                        if (re.match(r'^[a-z0-9][-+.a-z0-9]*:', val_unescaped)
+                            and (val_unescaped.split(':')[0] not in
+                                 self.allowed_protocols)):
+                            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
+                            'xlink:href' in attrs and
+                            re.search(r'^\s*[^#\s].*', attrs['xlink:href'])):
+                        del attrs['xlink:href']
+                    if 'style' in attrs:
+                        attrs['style'] = self.sanitize_css(attrs['style'])
+                    token['data'] = [(name, val) for name, val in
+                                     attrs.items()]
+                return token
+            elif self.strip_disallowed_elements:
+                pass
+            else:
+                if token['type'] == tokenTypes['EndTag']:
+                    token['data'] = '</{0!s}>'.format(token['name'])
+                elif token['data']:
+                    attr = ' {0!s}="{1!s}"'
+                    attrs = ''.join([attr.format(k, escape(v)) for k, v in
+                                    token['data']])
+                    token['data'] = '<{0!s}{1!s}>'.format(token['name'], attrs)
+                else:
+                    token['data'] = '<{0!s}>'.format(token['name'])
+                if token['selfClosing']:
+                    token['data'] = token['data'][:-1] + '/>'
+                token['type'] = tokenTypes['Characters']
+                del token["name"]
+                return token
+        elif token['type'] == tokenTypes['Comment']:
+            if not self.strip_html_comments:
+                return token
+        else:
+            return token
+
+    def sanitize_css(self, style):
+        """HTMLSanitizerMixin.sanitize_css replacement.
+
+        HTMLSanitizerMixin.sanitize_css always whitelists background-*,
+        border-*, margin-*, and padding-*. We only whitelist what's in
+        the whitelist.
+
+        """
+        # disallow urls
+        style = re.compile('url\s*\(\s*[^\s)]+?\s*\)\s*').sub(' ', style)
+
+        # gauntlet
+        # TODO: Make sure this does what it's meant to - I *think* it wants to
+        # validate style attribute contents.
+        parts = style.split(';')
+        gauntlet = re.compile("""^([-/:,#%.'"\sa-zA-Z0-9!]|\w-\w|'[\s\w]+'"""
+                              """\s*|"[\s\w]+"|\([\d,%\.\s]+\))*$""")
+        for part in parts:
+            if not gauntlet.match(part):
+                return ''
+
+        if not re.match("^\s*([-\w]+\s*:[^:;]*(;\s*|$))*$", style):
+            return ''
+
+        clean = []
+        for prop, value in re.findall('([-\w]+)\s*:\s*([^:;]*)', style):
+            if not value:
+                continue
+            if prop.lower() in self.allowed_css_properties:
+                clean.append(prop + ': ' + value + ';')
+            elif prop.lower() in self.allowed_svg_properties:
+                clean.append(prop + ': ' + value + ';')
+
+        return ' '.join(clean)
+
+
+class BleachSanitizer(HTMLTokenizer, BleachSanitizerMixin):
+    def __init__(self, stream, encoding=None, parseMeta=True, useChardet=True,
+                 lowercaseElementName=True, lowercaseAttrName=True, **kwargs):
+        HTMLTokenizer.__init__(self, stream, encoding, parseMeta, useChardet,
+                               lowercaseElementName, lowercaseAttrName,
+                               **kwargs)
+
+    def __iter__(self):
+        for token in HTMLTokenizer.__iter__(self):
+            token = self.sanitize_token(token)
+            if token:
+                yield token