def __init__(self, source):
html5lib_Filter.__init__(self, source)
self.level = 2
self.max_level = 3
self.in_header = False
self.open_level = 0
self.in_hierarchy = False
def __init__(self, source, id, replace_source=None):
html5lib_Filter.__init__(self, source)
self.replace_source = replace_source
self.section_id = id
self.heading = None
self.heading_rank = None
self.open_level = 0
self.parent_level = None
self.in_section = False
self.next_in_section = False
self.replacement_emitted = False
def __init__(self, source, id, replace_source=None):
html5lib_Filter.__init__(self, source)
self.replace_source = replace_source
self.section_id = id
self.heading = None
self.heading_rank = None
self.open_level = 0
self.parent_level = None
self.in_section = False
self.next_in_section = False
self.replacement_emitted = False
def __iter__(self):
input = html5lib_Filter.__iter__(self)
for token in input:
if ('StartTag' == token['type']
and token['name'] in HEAD_TAGS_TOC):
self.in_header = True
out = ()
level_match = re.compile(r'^h(\d)$').match(token['name'])
level = int(level_match.group(1))
if level > self.level:
diff = level - self.level
for i in range(diff):
out += ({
'type': 'StartTag',
'name': 'ol',
'data': {}
}, )
self.level = level
elif level < self.level:
diff = self.level - level
for i in range(diff):
out += ({
'type': 'EndTag',
'name': 'li'
}, {
'type': 'EndTag',
'name': 'ol'
})
self.level = level
attrs = dict(token['data'])
id = attrs.get('id', None)
if id:
out += (
{
'type': 'StartTag',
'name': 'li',
'data': {}
},
{
'type': 'StartTag',
'name': 'a',
'data': {
'rel': 'internal',
'href': '#%s' % id,
}
},
)
for t in out:
yield t
elif ('Characters' == token['type'] and self.in_header):
yield token
elif ('EndTag' == token['type']
and token['name'] in HEAD_TAGS_TOC):
self.in_header = False
level_match = re.compile(r'^h(\d)$').match(token['name'])
level = int(level_match.group(1))
out = ({'type': 'EndTag', 'name': 'a'}, )
for t in out:
yield t
def __iter__(self):
input = html5lib_Filter.__iter__(self)
for token in input:
if "StartTag" == token["type"] and token["name"] in self.tag_attributes:
attrs = dict(token["data"])
# If the element has the attribute we're looking for
desired_attr = self.tag_attributes[token["name"]]
if desired_attr in attrs:
address = attrs[desired_attr]
if not address.startswith("http"):
if address.startswith("//") or address.startswith("{{"):
# Do nothing for absolute addresses or apparent
# template variable output
attrs[desired_attr] = address
elif address.startswith("/"):
# Starts with "/", so just add the base url
attrs[desired_attr] = self.base_url + address
else:
attrs[desired_attr] = self.base_url + "/" + address
token["data"] = attrs.items()
yield token
def __iter__(self):
input = html5lib_Filter.__iter__(self)
for token in input:
if (token['type'] == 'StartTag'
and token['name'] in self.tag_attributes):
attrs = dict(token['data'])
# If the element has the attribute we're looking for
desired_attr = self.tag_attributes[token['name']]
for (namespace, name), value in attrs.items():
if desired_attr == name:
if not value.startswith('http'):
if value.startswith('//') or value.startswith(
'{{'):
# Do nothing for absolute addresses or apparent
# template variable output
attrs[(namespace, name)] = value
elif value.startswith('/'):
# Starts with "/", so just add the base url
attrs[(namespace,
name)] = self.base_url + value
else:
attrs[(namespace,
name)] = self.base_url + '/' + value
token['data'] = attrs
break
yield token
def __iter__(self):
input = html5lib_Filter.__iter__(self)
for token in input:
if (token['type'] == 'StartTag' and
token['name'] in self.tag_attributes):
attrs = dict(token['data'])
# If the element has the attribute we're looking for
desired_attr = self.tag_attributes[token['name']]
for (namespace, name), value in attrs.items():
if desired_attr == name:
if not value.startswith('http'):
if value.startswith('//') or value.startswith('{{'):
# Do nothing for absolute addresses or apparent
# template variable output
attrs[(namespace, name)] = value
elif value.startswith('/'):
# Starts with "/", so just add the base url
attrs[(namespace, name)] = self.base_url + value
else:
attrs[(namespace, name)] = self.base_url + '/' + value
token['data'] = attrs
break
yield token
def __iter__(self):
input = html5lib_Filter.__iter__(self)
for token in input:
if token["type"] == "StartTag" and token["name"] in self.tag_attributes:
attrs = dict(token["data"])
# If the element has the attribute we're looking for
desired_attr = self.tag_attributes[token["name"]]
for (namespace, name), value in attrs.items():
if desired_attr == name:
if not value.startswith("http"):
if value.startswith("//") or value.startswith("{{"):
# Do nothing for absolute addresses or apparent
# template variable output
attrs[(namespace, name)] = value
elif value.startswith("/"):
# Starts with "/", so just add the base url
attrs[(namespace, name)] = self.base_url + value
else:
attrs[(namespace, name)] = self.base_url + "/" + value
token["data"] = attrs
break
yield token
def __iter__(self):
input = html5lib_Filter.__iter__(self)
for token in input:
if ('StartTag' == token['type'] and token['name'] in self.tag_attributes):
attrs = dict(token['data'])
# If the element has the attribute we're looking for
desired_attr = self.tag_attributes[token['name']]
if desired_attr in attrs:
address = attrs[desired_attr]
if not address.startswith('http'):
if address.startswith('//') or address.startswith('{{'):
# Do nothing for absolute addresses or apparent
# template variable output
attrs[desired_attr] = address
elif address.startswith('/'):
# Starts with "/", so just add the base url
attrs[desired_attr] = self.base_url + address
else:
attrs[desired_attr] = self.base_url + '/' + address
token['data'] = attrs.items()
yield token
def __iter__(self):
for token in HTML5LibFilterBase.__iter__(self):
type = token['type']
if type in ('StartTag', 'EmptyTag', 'EndTag'):
name = token['name']
if name in ('html', 'head', 'body'):
continue
yield token
def __iter__(self):
for token in html5lib_Filter.__iter__(self):
if "StartTag" == token["type"]:
# Strip out any attributes that start with "on"
token["data"] = [(k, v) for (k, v) in dict(token["data"]).items() if not k.startswith("on")]
yield token
def __iter__(self):
for token in html5lib_Filter.__iter__(self):
if token['type'] == 'StartTag':
# Strip out any attributes that start with "on"
attrs = {}
for (namespace, name), value in token['data'].items():
if name.startswith('on'):
continue
attrs[(namespace, name)] = value
token['data'] = attrs
yield token
def __iter__(self):
for token in html5lib_Filter.__iter__(self):
if token['type'] == 'StartTag':
# Strip out any attributes that start with "on"
attrs = {}
for (namespace, name), value in token['data'].items():
if name.startswith('on'):
continue
attrs[(namespace, name)] = value
token['data'] = attrs
yield token
def __iter__(self):
for token in html5lib_Filter.__iter__(self):
if token["type"] == "StartTag":
# Strip out any attributes that start with "on"
attrs = {}
for (namespace, name), value in token["data"].items():
if name.startswith("on"):
continue
attrs[(namespace, name)] = value
token["data"] = attrs
yield token
def __iter__(self):
for token in html5lib_Filter.__iter__(self):
if ('StartTag' == token['type']):
if 'iframe' == token['name']:
attrs = dict(token['data'])
src = attrs.get('src', '')
if src:
parts = urlparse(src)
if not parts.netloc or parts.netloc not in self.hosts:
attrs['src'] = ''
token['data'] = attrs.items()
yield token
def __iter__(self):
for token in html5lib_Filter.__iter__(self):
if token['type'] == 'StartTag' and token['name'] == 'a':
attrs = dict(token['data'])
for (namespace, name), value in attrs.items():
if name == 'href' and value:
if re.search(self.blocked_protocols, value):
attrs[(namespace, 'href')] = ''
token['data'] = attrs
yield token
else:
yield token
def __iter__(self):
for token in html5lib_Filter.__iter__(self):
if token["type"] == "StartTag" and token["name"] == "a":
attrs = dict(token["data"])
for (namespace, name), value in attrs.items():
if name == "href" and value:
if re.search(self.blocked_protocols, value):
attrs[(namespace, "href")] = ""
token["data"] = attrs
yield token
else:
yield token
def __iter__(self):
for token in html5lib_Filter.__iter__(self):
if token['type'] == 'StartTag' and token['name'] == 'a':
attrs = dict(token['data'])
for (namespace, name), value in attrs.items():
if name == 'href' and value:
if re.search(self.blocked_protocols, value):
attrs[(namespace, 'href')] = ''
token['data'] = attrs
yield token
else:
yield token
def __iter__(self):
for token in html5lib_Filter.__iter__(self):
if ('StartTag' == token['type']):
# Strip out any attributes that start with "on"
token['data'] = [(k, v)
for (k, v) in dict(token['data']).items()
if not k.startswith('on')]
yield token
def __iter__(self):
for token in html5lib_Filter.__iter__(self):
if ('StartTag' == token['type']):
if 'iframe' == token['name']:
attrs = dict(token['data'])
src = attrs.get('src', '')
if src:
parts = urlparse(src)
if not parts.netloc or parts.netloc not in self.hosts:
attrs['src'] = ''
token['data'] = attrs.items()
yield token
def __iter__(self):
for token in html5lib_Filter.__iter__(self):
if token['type'] == 'StartTag' and token['name'] == 'pre':
attrs = dict(token['data'])
for (namespace, name), value in attrs.items():
if name == 'function' and value:
m = MT_SYNTAX_RE.match(value)
if m:
lang = m.group(1).lower()
brush = MT_SYNTAX_BRUSH_MAP.get(lang, lang)
attrs[(namespace, u'class')] = "brush: %s" % brush
del attrs[(None, 'function')]
token['data'] = attrs
yield token
def __iter__(self):
for token in html5lib_Filter.__iter__(self):
if token['type'] == 'StartTag' and token['name'] == 'pre':
attrs = dict(token['data'])
for (namespace, name), value in attrs.items():
if name == 'function' and value:
m = MT_SYNTAX_RE.match(value)
if m:
lang = m.group(1).lower()
brush = MT_SYNTAX_BRUSH_MAP.get(lang, lang)
attrs[(namespace, u'class')] = "brush: %s" % brush
del attrs[(None, 'function')]
token['data'] = attrs
yield token
def __iter__(self):
for token in html5lib_Filter.__iter__(self):
if token["type"] == "StartTag" and token["name"] == "pre":
attrs = dict(token["data"])
for (namespace, name), value in attrs.items():
if name == "function" and value:
m = MT_SYNTAX_RE.match(value)
if m:
lang = m.group(1).lower()
brush = MT_SYNTAX_BRUSH_MAP.get(lang, lang)
attrs[(namespace, u"class")] = "brush: %s" % brush
del attrs[(None, "function")]
token["data"] = attrs
yield token
def __iter__(self):
input = html5lib_Filter.__iter__(self)
for token in input:
yield token
if (token['type'] == 'StartTag' and token['name'] in SECTION_TAGS):
attrs = dict(token['data'])
for (namespace, name), value in attrs.items():
if name == 'id' and value:
ts = ({
'type': 'StartTag',
'name': 'a',
'data': {
(None, u'title'):
ugettext('Edit section'),
(None, u'class'):
'edit-section',
(None, u'data-section-id'):
value,
(None, u'data-section-src-url'):
u'{0!s}?{1!s}'.format(
reverse('wiki.document',
args=[self.slug],
locale=self.locale),
urlencode({
'section': value.encode('utf-8'),
'raw': 'true'
})),
(None, u'href'):
u'{0!s}?{1!s}'.format(
reverse('wiki.edit',
args=[self.slug],
locale=self.locale),
urlencode({
'section': value.encode('utf-8'),
'edit_links': 'true'
}))
}
}, {
'type': 'Characters',
'data': ugettext(u'Edit')
}, {
'type': 'EndTag',
'name': 'a'
})
for t in ts:
yield t
def __iter__(self):
for token in html5lib_Filter.__iter__(self):
if ('StartTag' == token['type']):
if 'pre' == token['name']:
attrs = dict(token['data'])
function = attrs.get('function', None)
if function:
m = MT_SYNTAX_PAT.match(function)
if m:
lang = m.group(1).lower()
brush = MT_SYNTAX_BRUSH_MAP.get(lang, lang)
attrs['class'] = "brush: %s" % brush
del attrs['function']
token['data'] = attrs.items()
yield token
def __iter__(self):
for token in html5lib_Filter.__iter__(self):
if ('StartTag' == token['type']):
if 'pre' == token['name']:
attrs = dict(token['data'])
function = attrs.get('function', None)
if function:
m = MT_SYNTAX_PAT.match(function)
if m:
lang = m.group(1).lower()
brush = MT_SYNTAX_BRUSH_MAP.get(lang, lang)
attrs['class'] = "brush: %s" % brush
del attrs['function']
token['data'] = attrs.items()
yield token
def __iter__(self):
for token in html5lib_Filter.__iter__(self):
if "StartTag" == token["type"]:
if "pre" == token["name"]:
attrs = dict(token["data"])
function = attrs.get("function", None)
if function:
m = MT_SYNTAX_PAT.match(function)
if m:
lang = m.group(1).lower()
brush = MT_SYNTAX_BRUSH_MAP.get(lang, lang)
attrs["class"] = "brush: %s" % brush
del attrs["function"]
token["data"] = attrs.items()
yield token
def __iter__(self):
in_iframe = False
for token in html5lib_Filter.__iter__(self):
if token['type'] == 'StartTag' and token['name'] == 'iframe':
in_iframe = True
attrs = dict(token['data'])
for (namespace, name), value in attrs.items():
if name == 'src' and value:
if not re.search(self.hosts, value):
attrs[(namespace, 'src')] = ''
token['data'] = attrs
yield token
if token['type'] == 'EndTag' and token['name'] == 'iframe':
in_iframe = False
if not in_iframe:
yield token
def __iter__(self):
in_iframe = False
for token in html5lib_Filter.__iter__(self):
if token["type"] == "StartTag" and token["name"] == "iframe":
in_iframe = True
attrs = dict(token["data"])
for (namespace, name), value in attrs.items():
if name == "src" and value:
if not re.search(self.hosts, value):
attrs[(namespace, "src")] = ""
token["data"] = attrs
yield token
if token["type"] == "EndTag" and token["name"] == "iframe":
in_iframe = False
if not in_iframe:
yield token
def __iter__(self):
in_iframe = False
for token in html5lib_Filter.__iter__(self):
if token['type'] == 'StartTag' and token['name'] == 'iframe':
in_iframe = True
attrs = dict(token['data'])
for (namespace, name), value in attrs.items():
if name == 'src' and value:
if not re.search(self.hosts, value):
attrs[(namespace, 'src')] = ''
token['data'] = attrs
yield token
if token['type'] == 'EndTag' and token['name'] == 'iframe':
in_iframe = False
if not in_iframe:
yield token
def __iter__(self):
input = html5lib_Filter.__iter__(self)
for token in input:
yield token
if ('StartTag' == token['type'] and token['name'] in SECTION_TAGS):
attrs = dict(token['data'])
id = attrs.get('id', None)
if id:
out = ({
'type': 'StartTag',
'name': 'a',
'data': {
'title':
_('Edit section'),
'class':
'edit-section',
'data-section-id':
id,
'data-section-src-url':
u'%s?%s' % (reverse('wiki.document',
args=[self.full_path],
locale=self.locale),
urlencode({
'section': id.encode('utf-8'),
'raw': 'true'
})),
'href':
u'%s?%s' % (reverse('wiki.edit_document',
args=[self.full_path],
locale=self.locale),
urlencode({
'section': id.encode('utf-8'),
'edit_links': 'true'
}))
}
}, {
'type': 'Characters',
'data': _('Edit')
}, {
'type': 'EndTag',
'name': 'a'
})
for t in out:
yield t
def __iter__(self):
in_iframe = False
for token in html5lib_Filter.__iter__(self):
if ('StartTag' == token['type']):
if 'iframe' == token['name']:
in_iframe = True
attrs = dict(token['data'])
src = attrs.get('src', '')
if src:
if not re.search(self.hosts, src):
attrs['src'] = ''
token['data'] = attrs.items()
yield token
if ('EndTag' == token['type']):
if 'iframe' == token['name']:
in_iframe = False
if not in_iframe:
yield token
def __iter__(self):
in_iframe = False
for token in html5lib_Filter.__iter__(self):
if "StartTag" == token["type"]:
if "iframe" == token["name"]:
in_iframe = True
attrs = dict(token["data"])
src = attrs.get("src", "")
if src:
if not re.search(self.hosts, src):
attrs["src"] = ""
token["data"] = attrs.items()
yield token
if "EndTag" == token["type"]:
if "iframe" == token["name"]:
in_iframe = False
if not in_iframe:
yield token
def __iter__(self):
input = html5lib_Filter.__iter__(self)
for token in input:
if ('StartTag' == token['type'] and token['name'] in HEAD_TAGS_TOC):
self.in_header = True
out = ()
level_match = re.compile(r'^h(\d)$').match(token['name'])
level = int(level_match.group(1))
if level > self.level:
diff = level - self.level
for i in range(diff):
out += ({'type': 'StartTag', 'name': 'ol',
'data': {}},)
self.level = level
elif level < self.level:
diff = self.level - level
for i in range(diff):
out += ({'type': 'EndTag', 'name': 'li'},
{'type': 'EndTag', 'name': 'ol'})
self.level = level
attrs = dict(token['data'])
id = attrs.get('id', None)
if id:
out += (
{'type': 'StartTag', 'name': 'li', 'data': {}},
{'type': 'StartTag', 'name': 'a',
'data': {
'rel': 'internal',
'href': '#%s' % id,
}},
)
for t in out:
yield t
elif ('Characters' == token['type'] and self.in_header):
yield token
elif ('EndTag' == token['type'] and token['name'] in HEAD_TAGS_TOC):
self.in_header = False
level_match = re.compile(r'^h(\d)$').match(token['name'])
level = int(level_match.group(1))
out = ({'type': 'EndTag', 'name': 'a'},)
for t in out:
yield t
def __iter__(self):
input = html5lib_Filter.__iter__(self)
# Pass 1: Collect all known IDs from the stream
buffer = []
for token in input:
buffer.append(token)
if 'StartTag' == token['type']:
attrs = dict(token['data'])
if 'id' in attrs:
self.known_ids.add(attrs['id'])
# Pass 2: Sprinkle in IDs where they're missing
for token in buffer:
if ('StartTag' == token['type'] and
token['name'] in SECTION_EDIT_TAGS):
attrs = dict(token['data'])
id = attrs.get('id', None)
if not id:
attrs['id'] = self.gen_id()
token['data'] = attrs.items()
yield token
def __iter__(self):
input = html5lib_Filter.__iter__(self)
for token in input:
yield token
if ('StartTag' == token['type'] and
token['name'] in SECTION_TAGS):
attrs = dict(token['data'])
id = attrs.get('id', None)
if id:
out = (
{'type': 'StartTag', 'name': 'a',
'data': {
'title': _('Edit section'),
'class': 'edit-section',
'data-section-id': id,
'data-section-src-url': u'%s?%s' % (
reverse('wiki.document',
args=[self.full_path],
locale=self.locale),
urlencode({'section': id.encode('utf-8'),
'raw': 'true'})
),
'href': u'%s?%s' % (
reverse('wiki.edit_document',
args=[self.full_path],
locale=self.locale),
urlencode({'section': id.encode('utf-8'),
'edit_links': 'true'})
)
}},
{'type': 'Characters', 'data': _('Edit')},
{'type': 'EndTag', 'name': 'a'}
)
for t in out:
yield t
def __iter__(self):
input = html5lib_Filter.__iter__(self)
for token in input:
yield token
if (token['type'] == 'StartTag' and
token['name'] in SECTION_TAGS):
attrs = dict(token['data'])
for (namespace, name), value in attrs.items():
if name == 'id' and value:
ts = ({'type': 'StartTag',
'name': 'a',
'data': {
(None, u'title'): ugettext('Edit section'),
(None, u'class'): 'edit-section',
(None, u'data-section-id'): value,
(None, u'data-section-src-url'): u'%s?%s' % (
reverse('wiki.document',
args=[self.slug],
locale=self.locale),
urlencode({'section': value.encode('utf-8'),
'raw': 'true'})
),
(None, u'href'): u'%s?%s' % (
reverse('wiki.edit',
args=[self.slug],
locale=self.locale),
urlencode({'section': value.encode('utf-8'),
'edit_links': 'true'})
)
}},
{'type': 'Characters',
'data': ugettext(u'Edit')},
{'type': 'EndTag', 'name': 'a'})
for t in ts:
yield t
def __iter__(self):
input = html5lib_Filter.__iter__(self)
for token in input:
if "StartTag" == token["type"] and token["name"] in HEAD_TAGS_TOC:
self.in_header = True
out = ()
level_match = re.compile(r"^h(\d)$").match(token["name"])
level = int(level_match.group(1))
if level > self.level:
diff = level - self.level
for i in range(diff):
out += ({"type": "StartTag", "name": "ol", "data": {}},)
self.level = level
elif level < self.level:
diff = self.level - level
for i in range(diff):
out += ({"type": "EndTag", "name": "li"}, {"type": "EndTag", "name": "ol"})
self.level = level
attrs = dict(token["data"])
id = attrs.get("id", None)
if id:
out += (
{"type": "StartTag", "name": "li", "data": {}},
{"type": "StartTag", "name": "a", "data": {"rel": "internal", "href": "#%s" % id}},
)
for t in out:
yield t
elif "Characters" == token["type"] and self.in_header:
yield token
elif "EndTag" == token["type"] and token["name"] in HEAD_TAGS_TOC:
self.in_header = False
level_match = re.compile(r"^h(\d)$").match(token["name"])
level = int(level_match.group(1))
out = ({"type": "EndTag", "name": "a"},)
for t in out:
yield t
def __iter__(self):
input = html5lib_Filter.__iter__(self)
for token in input:
yield token
if token["type"] == "StartTag" and token["name"] in SECTION_TAGS:
attrs = dict(token["data"])
for (namespace, name), value in attrs.items():
if name == "id" and value:
ts = (
{
"type": "StartTag",
"name": "a",
"data": {
(None, u"title"): ugettext("Edit section"),
(None, u"class"): "edit-section",
(None, u"data-section-id"): value,
(None, u"data-section-src-url"): u"%s?%s"
% (
reverse("wiki.document", args=[self.slug], locale=self.locale),
urlencode({"section": value.encode("utf-8"), "raw": "true"}),
),
(None, u"href"): u"%s?%s"
% (
reverse("wiki.edit", args=[self.slug], locale=self.locale),
urlencode({"section": value.encode("utf-8"), "edit_links": "true"}),
),
},
},
{"type": "Characters", "data": ugettext(u"Edit")},
{"type": "EndTag", "name": "a"},
)
for t in ts:
yield t
def __iter__(self):
input = html5lib_Filter.__iter__(self)
for token in input:
yield token
if "StartTag" == token["type"] and token["name"] in SECTION_TAGS:
attrs = dict(token["data"])
id = attrs.get("id", None)
if id:
out = (
{
"type": "StartTag",
"name": "a",
"data": {
"title": _("Edit section"),
"class": "edit-section",
"data-section-id": id,
"data-section-src-url": u"%s?%s"
% (
reverse("wiki.document", args=[self.full_path], locale=self.locale),
urlencode({"section": id.encode("utf-8"), "raw": "true"}),
),
"href": u"%s?%s"
% (
reverse("wiki.edit_document", args=[self.full_path], locale=self.locale),
urlencode({"section": id.encode("utf-8"), "edit_links": "true"}),
),
},
},
{"type": "Characters", "data": _("Edit")},
{"type": "EndTag", "name": "a"},
)
for t in out:
yield t
def __iter__(self):
input = html5lib_Filter.__iter__(self)
for token in input:
# Section start was deferred, so start it now.
if self.next_in_section:
self.next_in_section = False
self.in_section = True
if 'StartTag' == token['type']:
attrs = dict(token['data'])
self.open_level += 1
# Have we encountered the section or heading element we're
# looking for?
if attrs.get('id', None) == self.section_id:
# If we encounter a section element that matches the ID,
# then we'll want to scoop up all its children as an
# explicit section.
if (self.parent_level is None and self._isSection(token)):
self.parent_level = self.open_level
# Defer the start of the section, so the section parent
# itself isn't included.
self.next_in_section = True
# If we encounter a heading element that matches the ID, we
# start an implicit section.
elif (self.heading is None and self._isHeading(token)):
self.heading = token
self.heading_rank = self._getHeadingRank(token)
self.parent_level = self.open_level - 1
self.in_section = True
# If started an implicit section, these rules apply to
# siblings...
elif (self.heading is not None
and self.open_level - 1 == self.parent_level):
# The implicit section should stop if we hit another
# sibling heading whose rank is equal or higher, since that
# starts a new implicit section
if (self._isHeading(token) and
self._getHeadingRank(token) <= self.heading_rank):
self.in_section = False
if 'EndTag' == token['type']:
self.open_level -= 1
# If the parent of the section has ended, end the section.
# This applies to both implicit and explicit sections.
if (self.parent_level is not None
and self.open_level < self.parent_level):
self.in_section = False
# If there's no replacement source, then this is a section
# extraction. So, emit tokens while we're in the section.
if not self.replace_source:
if self.in_section:
yield token
# If there is a replacement source, then this is a section
# replacement. Emit tokens of the source stream until we're in the
# section, then emit the replacement stream and ignore the rest of
# the source stream for the section..
else:
if not self.in_section:
yield token
elif not self.replacement_emitted:
for r_token in self.replace_source:
yield r_token
self.replacement_emitted = True
def __iter__(self):
from wiki.models import Document
input = html5lib_Filter.__iter__(self)
# Pass #1: Gather all the link URLs and prepare annotations
links = dict()
buffer = []
for token in input:
buffer.append(token)
if ('StartTag' == token['type'] and 'a' == token['name']):
attrs = dict(token['data'])
if not 'href' in attrs:
continue
href = attrs['href']
if href.startswith(self.base_url):
# Squash site-absolute URLs to site-relative paths.
href = '/%s' % href[len(self.base_url):]
# Prepare annotations record for this path.
links[href] = dict(classes=[])
# Run through all the links and check for annotatable conditions.
for href in links.keys():
# Is this an external URL?
is_external = False
for prefix in self.EXTERNAL_PREFIXES:
if href.startswith(prefix):
is_external = True
break
if is_external:
links[href]['classes'].append('external')
continue
# TODO: Should this also check for old-school mindtouch URLs? Or
# should we encourage editors to convert to new-style URLs to take
# advantage of link annotation? (I'd say the latter)
# Is this a kuma doc URL?
if '/docs/' in href:
# Check if this is a special docs path that's exempt from "new"
skip = False
for path in DOC_SPECIAL_PATHS:
if '/docs/%s' % path in href:
skip = True
if skip:
continue
href_locale, href_path = href.split(u'/docs/', 1)
if href_locale.startswith(u'/'):
href_locale = href_locale[1:]
if '#' in href_path:
# If present, discard the hash anchor
href_path, _, _ = href_path.partition('#')
# Handle any URL-encoded UTF-8 characters in the path
href_path = href_path.encode('utf-8', 'ignore')
href_path = urllib.unquote(href_path)
href_path = href_path.decode('utf-8', 'ignore')
# Try to sort out the locale and slug through some of our
# redirection logic.
locale, slug, needs_redirect = (
Document.locale_and_slug_from_path(
href_path, path_locale=href_locale))
# Does this locale and slug correspond to an existing document?
# If not, mark it as a "new" link.
#
# TODO: Should these DB queries be batched up into one big
# query? A page with hundreds of links will fire off hundreds
# of queries
ct = Document.objects.filter(locale=locale, slug=slug).count()
if ct == 0:
links[href]['classes'].append('new')
# Pass #2: Filter the content, annotating links
for token in buffer:
if ('StartTag' == token['type'] and 'a' == token['name']):
attrs = dict(token['data'])
if 'href' in attrs:
href = attrs['href']
if href.startswith(self.base_url):
# Squash site-absolute URLs to site-relative paths.
href = '/%s' % href[len(self.base_url):]
if href in links:
# Update class names on this link element.
if 'class' in attrs:
classes = set(attrs['class'].split(u' '))
else:
classes = set()
classes.update(links[href]['classes'])
if classes:
attrs['class'] = u' '.join(classes)
token['data'] = attrs.items()
yield token
def __init__(self, source):
html5lib_Filter.__init__(self, source)
self.id_cnt = 0
self.known_ids = set()
def __iter__(self):
input = html5lib_Filter.__iter__(self)
# Pass 1: Collect all known IDs from the stream
buffer = []
for token in input:
buffer.append(token)
if 'StartTag' == token['type']:
attrs = dict(token['data'])
if 'id' in attrs:
self.known_ids.add(attrs['id'])
if 'name' in attrs:
self.known_ids.add(attrs['name'])
# Pass 2: Sprinkle in IDs where they're needed
while len(buffer):
token = buffer.pop(0)
if not ('StartTag' == token['type']
and token['name'] in SECTION_TAGS):
yield token
else:
attrs = dict(token['data'])
# Treat a name attribute as a human-specified ID override
name = attrs.get('name', None)
if name:
attrs['id'] = name
token['data'] = attrs.items()
yield token
continue
# If this is not a header, then generate a section ID.
if token['name'] not in HEAD_TAGS:
attrs['id'] = self.gen_id()
token['data'] = attrs.items()
yield token
continue
# If this is a header, then scoop up the rest of the header and
# gather the text it contains.
start, text, tmp = token, [], []
while len(buffer):
token = buffer.pop(0)
tmp.append(token)
if token['type'] in ('Characters', 'SpaceCharacters'):
text.append(token['data'])
elif ('EndTag' == token['type']
and start['name'] == token['name']):
# Note: This is naive, and doesn't track other
# start/end tags nested in the header. Odd things might
# happen in a case like <h1><h1></h1></h1>. But, that's
# invalid markup and the worst case should be a
# truncated ID because all the text wasn't accumulated.
break
# Slugify the text we found inside the header, generate an ID
# as a last resort.
slug = self.slugify(u''.join(text))
if not slug:
slug = self.gen_id()
attrs['id'] = slug
start['data'] = attrs.items()
# Finally, emit the tokens we scooped up for the header.
yield start
for t in tmp:
yield t
def __iter__(self):
buffer = []
for token in html5lib_Filter.__iter__(self):
buffer.append(token)
while len(buffer):
token = buffer.pop(0)
if not ('StartTag' == token['type'] and 'span' == token['name']):
yield token
continue
attrs = dict(token['data'])
if attrs.get('class', '') != 'script':
yield token
continue
ds_call = []
while len(buffer):
token = buffer.pop(0)
if token['type'] in ('Characters', 'SpaceCharacters'):
ds_call.append(token['data'])
elif 'StartTag' == token['type']:
attrs = token['data']
if attrs:
a_out = (u' %s' % u' '.join(
(u'%s=%s' % (name, quoteattr(val))
for name, val in attrs)))
else:
a_out = u''
ds_call.append(u'<%s%s>' % (token['name'], a_out))
elif 'EndTag' == token['type']:
if 'span' == token['name']:
break
ds_call.append('</%s>' % token['name'])
ds_call = u''.join(ds_call).strip()
# Snip off any "template." prefixes
strip_prefixes = ('template.', 'wiki.')
for prefix in strip_prefixes:
if ds_call.lower().startswith(prefix):
ds_call = ds_call[len(prefix):]
# template("template name", [ "params" ])
wt_re = re.compile(
r'''^template\(['"]([^'"]+)['"],\s*\[([^\]]+)]''', re.I)
m = wt_re.match(ds_call)
if m:
ds_call = '%s(%s)' % (m.group(1), m.group(2).strip())
# template("template name")
wt_re = re.compile(r'''^template\(['"]([^'"]+)['"]''', re.I)
m = wt_re.match(ds_call)
if m:
ds_call = '%s()' % (m.group(1))
# HACK: This is dirty, but seems like the easiest way to
# reconstitute the token stream, including what gets parsed as
# markup in the middle of macro parameters.
#
# eg. {{ Note("This is <strong>strongly</strong> discouraged") }}
parsed = parse('{{ %s }}' % ds_call)
for token in parsed.stream:
yield token
def __init__(self, source, base_url):
html5lib_Filter.__init__(self, source)
self.base_url = base_url
def __init__(self, source, hosts):
html5lib_Filter.__init__(self, source)
self.hosts = hosts
def __iter__(self):
buffer = []
for token in html5lib_Filter.__iter__(self):
buffer.append(token)
while len(buffer):
token = buffer.pop(0)
if not ('StartTag' == token['type'] and
'span' == token['name']):
yield token
continue
attrs = dict(token['data'])
if attrs.get('class', '') != 'script':
yield token
continue
ds_call = []
while len(buffer):
token = buffer.pop(0)
if token['type'] in ('Characters', 'SpaceCharacters'):
ds_call.append(token['data'])
elif 'StartTag' == token['type']:
attrs = token['data']
if attrs:
a_out = (u' %s' % u' '.join(
(u'%s=%s' %
(name, quoteattr(val))
for name, val in attrs)))
else:
a_out = u''
ds_call.append(u'<%s%s>' % (token['name'], a_out))
elif 'EndTag' == token['type']:
if 'span' == token['name']:
break
ds_call.append('</%s>' % token['name'])
ds_call = u''.join(ds_call).strip()
# Snip off any "template." prefixes
strip_prefixes = ('template.', 'wiki.')
for prefix in strip_prefixes:
if ds_call.lower().startswith(prefix):
ds_call = ds_call[len(prefix):]
# template("template name", [ "params" ])
wt_re = re.compile(
r'''^template\(['"]([^'"]+)['"],\s*\[([^\]]+)]''', re.I)
m = wt_re.match(ds_call)
if m:
ds_call = '%s(%s)' % (m.group(1), m.group(2).strip())
# template("template name")
wt_re = re.compile(r'''^template\(['"]([^'"]+)['"]''', re.I)
m = wt_re.match(ds_call)
if m:
ds_call = '%s()' % (m.group(1))
# HACK: This is dirty, but seems like the easiest way to
# reconstitute the token stream, including what gets parsed as
# markup in the middle of macro parameters.
#
# eg. {{ Note("This is <strong>strongly</strong> discouraged") }}
parsed = parse('{{ %s }}' % ds_call)
for token in parsed.stream:
yield token
def __init__(self, source, base_url, tag_attributes):
html5lib_Filter.__init__(self, source)
self.base_url = base_url
self.tag_attributes = tag_attributes
def __iter__(self):
input = html5lib_Filter.__iter__(self)
for token in input:
if ('StartTag' == token['type']
and token['name'] in HEAD_TAGS_TOC):
self.in_header = True
out = ()
level_match = re.compile(r'^h(\d)$').match(token['name'])
level = int(level_match.group(1))
if level > self.level:
diff = level - self.level
for i in range(diff):
if (not self.in_hierarchy and i % 2 == 0):
out += ({
'type': 'StartTag',
'name': 'li',
'data': {}
}, )
out += ({
'type': 'StartTag',
'name': 'ol',
'data': {}
}, )
if (diff > 1 and i % 2 == 0 and i != diff - 1):
out += ({
'type': 'StartTag',
'name': 'li',
'data': {}
}, )
self.open_level += 1
self.level = level
elif level < self.level:
diff = self.level - level
for i in range(diff):
out += ({
'type': 'EndTag',
'name': 'ol'
}, {
'type': 'EndTag',
'name': 'li'
})
self.open_level -= 1
self.level = level
attrs = dict(token['data'])
id = attrs.get('id', None)
if id:
out += (
{
'type': 'StartTag',
'name': 'li',
'data': {}
},
{
'type': 'StartTag',
'name': 'a',
'data': {
'rel': 'internal',
'href': '#%s' % id,
}
},
)
self.in_hierarchy = True
for t in out:
yield t
elif ('StartTag' == token['type']
and token['name'] in TAGS_IN_TOC):
yield token
elif (token['type'] in ("Characters", "SpaceCharacters")
and self.in_header):
yield token
elif ('EndTag' == token['type'] and token['name'] in TAGS_IN_TOC):
yield token
elif ('EndTag' == token['type']
and token['name'] in HEAD_TAGS_TOC):
self.in_header = False
out = ({'type': 'EndTag', 'name': 'a'}, )
for t in out:
yield t
if self.open_level > 0:
out = ()
for i in range(self.open_level):
out += ({
'type': 'EndTag',
'name': 'ol'
}, {
'type': 'EndTag',
'name': 'li'
})
for t in out:
yield t
def __init__(self, source, base_url):
html5lib_Filter.__init__(self, source)
self.base_url = base_url
self.base_url_parsed = urlparse(base_url)
def __init__(self, source, full_path, locale):
html5lib_Filter.__init__(self, source)
self.full_path = full_path
self.locale = locale
def __iter__(self):
for token in html5lib_Filter.__iter__(self):
if 'SpaceCharacters' == token['type']:
continue
yield token
def __iter__(self):
from wiki.models import Document
input = html5lib_Filter.__iter__(self)
# Pass #1: Gather all the link URLs and prepare annotations
links = dict()
buffer = []
for token in input:
buffer.append(token)
if ('StartTag' == token['type'] and 'a' == token['name']):
attrs = dict(token['data'])
if not 'href' in attrs:
continue
href = attrs['href']
href_parsed = urlparse(href)
if href_parsed.netloc == self.base_url_parsed.netloc:
# Squash site-absolute URLs to site-relative paths.
href = href_parsed.path
# Prepare annotations record for this path.
links[href] = dict(
classes=[]
)
needs_existence_check = defaultdict(lambda: defaultdict(set))
# Run through all the links and check for annotatable conditions.
for href in links.keys():
# Is this an external URL?
is_external = False
for prefix in self.EXTERNAL_PREFIXES:
if href.startswith(prefix):
is_external = True
break
if is_external:
links[href]['classes'].append('external')
continue
# TODO: Should this also check for old-school mindtouch URLs? Or
# should we encourage editors to convert to new-style URLs to take
# advantage of link annotation? (I'd say the latter)
# Is this a kuma doc URL?
if '/docs/' in href:
# Check if this is a special docs path that's exempt from "new"
skip = False
for path in DOC_SPECIAL_PATHS:
if '/docs/%s' % path in href:
skip = True
if skip:
continue
href_locale, href_path = href.split(u'/docs/', 1)
if href_locale.startswith(u'/'):
href_locale = href_locale[1:]
if '#' in href_path:
# If present, discard the hash anchor
href_path, _, _ = href_path.partition('#')
# Handle any URL-encoded UTF-8 characters in the path
href_path = href_path.encode('utf-8', 'ignore')
href_path = urllib.unquote(href_path)
href_path = href_path.decode('utf-8', 'ignore')
# Try to sort out the locale and slug through some of our
# redirection logic.
locale, slug, needs_redirect = (Document
.locale_and_slug_from_path(href_path,
path_locale=href_locale))
# Gather up this link for existence check
needs_existence_check[locale.lower()][slug.lower()].add(href)
# Perform existence checks for all the links, using one DB query per
# locale for all the candidate slugs.
for locale, slug_hrefs in needs_existence_check.items():
existing_slugs = (Document.objects
.filter(locale=locale,
slug__in=slug_hrefs.keys())
.values_list('slug', flat=True))
# Remove the slugs that pass existence check.
for slug in existing_slugs:
lslug = slug.lower()
if lslug in slug_hrefs:
del slug_hrefs[lslug]
# Mark all the links whose slugs did not come back from the DB
# query as "new"
for slug, hrefs in slug_hrefs.items():
for href in hrefs:
links[href]['classes'].append('new')
# Pass #2: Filter the content, annotating links
for token in buffer:
if ('StartTag' == token['type'] and 'a' == token['name']):
attrs = dict(token['data'])
if 'href' in attrs:
href = attrs['href']
href_parsed = urlparse(href)
if href_parsed.netloc == self.base_url_parsed.netloc:
# Squash site-absolute URLs to site-relative paths.
href = href_parsed.path
if href in links:
# Update class names on this link element.
if 'class' in attrs:
classes = set(attrs['class'].split(u' '))
else:
classes = set()
classes.update(links[href]['classes'])
if classes:
attrs['class'] = u' '.join(classes)
token['data'] = attrs.items()
yield token
