dinislage/CouchPotatoServer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update libs

Browse Source
This commit is contained in:
Ruud
2013-11-22 16:09:15 +01:00
parent f53364eb6c
commit 88d6148500
119 changed files with 18448 additions and 8923 deletions
Download Patch File Download Diff File Expand all files Collapse all files
libs/html5lib/filters/_base.py
+2
View File
@@ -1,3 +1,5 @@
from __future__ import absolute_import, division, unicode_literals
class Filter(object):
def __init__(self, source):
libs/html5lib/filters/alphabeticalattributes.py
+20
View File
@@ -0,0 +1,20 @@
from __future__ import absolute_import, division, unicode_literals
from . import _base
try:
from collections import OrderedDict
except ImportError:
from ordereddict import OrderedDict
class Filter(_base.Filter):
def __iter__(self):
for token in _base.Filter.__iter__(self):
if token["type"] in ("StartTag", "EmptyTag"):
attrs = OrderedDict()
for name, value in sorted(token["data"].items(),
key=lambda x: x[0]):
attrs[name] = value
token["data"] = attrs
yield token
libs/html5lib/filters/formfiller.py
-127
View File
@@ -1,127 +0,0 @@
#
# The goal is to finally have a form filler where you pass data for
# each form, using the algorithm for "Seeding a form with initial values"
# See http://www.whatwg.org/specs/web-forms/current-work/#seeding
#
import _base
from html5lib.constants import spaceCharacters
spaceCharacters = u"".join(spaceCharacters)
class SimpleFilter(_base.Filter):
def __init__(self, source, fieldStorage):
_base.Filter.__init__(self, source)
self.fieldStorage = fieldStorage
def __iter__(self):
field_indices = {}
state = None
field_name = None
for token in _base.Filter.__iter__(self):
type = token["type"]
if type in ("StartTag", "EmptyTag"):
name = token["name"].lower()
if name == "input":
field_name = None
field_type = None
input_value_index = -1
input_checked_index = -1
for i,(n,v) in enumerate(token["data"]):
n = n.lower()
if n == u"name":
field_name = v.strip(spaceCharacters)
elif n == u"type":
field_type = v.strip(spaceCharacters)
elif n == u"checked":
input_checked_index = i
elif n == u"value":
input_value_index = i
value_list = self.fieldStorage.getlist(field_name)
field_index = field_indices.setdefault(field_name, 0)
if field_index < len(value_list):
value = value_list[field_index]
else:
value = ""
if field_type in (u"checkbox", u"radio"):
if value_list:
if token["data"][input_value_index][1] == value:
if input_checked_index < 0:
token["data"].append((u"checked", u""))
field_indices[field_name] = field_index + 1
elif input_checked_index >= 0:
del token["data"][input_checked_index]
elif field_type not in (u"button", u"submit", u"reset"):
if input_value_index >= 0:
token["data"][input_value_index] = (u"value", value)
else:
token["data"].append((u"value", value))
field_indices[field_name] = field_index + 1
field_type = None
field_name = None
elif name == "textarea":
field_type = "textarea"
field_name = dict((token["data"])[::-1])["name"]
elif name == "select":
field_type = "select"
attributes = dict(token["data"][::-1])
field_name = attributes.get("name")
is_select_multiple = "multiple" in attributes
is_selected_option_found = False
elif field_type == "select" and field_name and name == "option":
option_selected_index = -1
option_value = None
for i,(n,v) in enumerate(token["data"]):
n = n.lower()
if n == "selected":
option_selected_index = i
elif n == "value":
option_value = v.strip(spaceCharacters)
if option_value is None:
raise NotImplementedError("<option>s without a value= attribute")
else:
value_list = self.fieldStorage.getlist(field_name)
if value_list:
field_index = field_indices.setdefault(field_name, 0)
if field_index < len(value_list):
value = value_list[field_index]
else:
value = ""
if (is_select_multiple or not is_selected_option_found) and option_value == value:
if option_selected_index < 0:
token["data"].append((u"selected", u""))
field_indices[field_name] = field_index + 1
is_selected_option_found = True
elif option_selected_index >= 0:
del token["data"][option_selected_index]
elif field_type is not None and field_name and type == "EndTag":
name = token["name"].lower()
if name == field_type:
if name == "textarea":
value_list = self.fieldStorage.getlist(field_name)
if value_list:
field_index = field_indices.setdefault(field_name, 0)
if field_index < len(value_list):
value = value_list[field_index]
else:
value = ""
yield {"type": "Characters", "data": value}
field_indices[field_name] = field_index + 1
field_name = None
elif name == "option" and field_type == "select":
pass # TODO: part of "option without value= attribute" processing
elif field_type == "textarea":
continue # ignore token
yield token
libs/html5lib/filters/inject_meta_charset.py
+29 -26
View File
@@ -1,4 +1,7 @@
import _base
from __future__ import absolute_import, division, unicode_literals
from . import _base
class Filter(_base.Filter):
def __init__(self, source, encoding):
@@ -13,44 +16,44 @@ class Filter(_base.Filter):
for token in _base.Filter.__iter__(self):
type = token["type"]
if type == "StartTag":
if token["name"].lower() == u"head":
if token["name"].lower() == "head":
state = "in_head"
elif type == "EmptyTag":
if token["name"].lower() == u"meta":
# replace charset with actual encoding
has_http_equiv_content_type = False
for (namespace,name),value in token["data"].iteritems():
if namespace != None:
continue
elif name.lower() == u'charset':
token["data"][(namespace,name)] = self.encoding
meta_found = True
break
elif name == u'http-equiv' and value.lower() == u'content-type':
has_http_equiv_content_type = True
else:
if has_http_equiv_content_type and (None, u"content") in token["data"]:
token["data"][(None, u"content")] = u'text/html; charset=%s' % self.encoding
meta_found = True
if token["name"].lower() == "meta":
# replace charset with actual encoding
has_http_equiv_content_type = False
for (namespace, name), value in token["data"].items():
if namespace is not None:
continue
elif name.lower() == 'charset':
token["data"][(namespace, name)] = self.encoding
meta_found = True
break
elif name == 'http-equiv' and value.lower() == 'content-type':
has_http_equiv_content_type = True
else:
if has_http_equiv_content_type and (None, "content") in token["data"]:
token["data"][(None, "content")] = 'text/html; charset=%s' % self.encoding
meta_found = True
elif token["name"].lower() == u"head" and not meta_found:
elif token["name"].lower() == "head" and not meta_found:
# insert meta into empty head
yield {"type": "StartTag", "name": u"head",
yield {"type": "StartTag", "name": "head",
"data": token["data"]}
yield {"type": "EmptyTag", "name": u"meta",
"data": {(None, u"charset"): self.encoding}}
yield {"type": "EndTag", "name": u"head"}
yield {"type": "EmptyTag", "name": "meta",
"data": {(None, "charset"): self.encoding}}
yield {"type": "EndTag", "name": "head"}
meta_found = True
continue
elif type == "EndTag":
if token["name"].lower() == u"head" and pending:
if token["name"].lower() == "head" and pending:
# insert meta into head (if necessary) and flush pending queue
yield pending.pop(0)
if not meta_found:
yield {"type": "EmptyTag", "name": u"meta",
"data": {(None, u"charset"): self.encoding}}
yield {"type": "EmptyTag", "name": "meta",
"data": {(None, "charset"): self.encoding}}
while pending:
yield pending.pop(0)
meta_found = True
libs/html5lib/filters/lint.py
+34 -29
View File
@@ -1,13 +1,18 @@
from __future__ import absolute_import, division, unicode_literals
from gettext import gettext
_ = gettext
import _base
from html5lib.constants import cdataElements, rcdataElements, voidElements
from . import _base
from ..constants import cdataElements, rcdataElements, voidElements
from html5lib.constants import spaceCharacters
spaceCharacters = u"".join(spaceCharacters)
from ..constants import spaceCharacters
spaceCharacters = "".join(spaceCharacters)
class LintError(Exception):
pass
class LintError(Exception): pass
class Filter(_base.Filter):
def __iter__(self):
@@ -18,24 +23,24 @@ class Filter(_base.Filter):
if type in ("StartTag", "EmptyTag"):
name = token["name"]
if contentModelFlag != "PCDATA":
raise LintError(_("StartTag not in PCDATA content model flag: %s") % name)
if not isinstance(name, unicode):
raise LintError(_(u"Tag name is not a string: %r") % name)
raise LintError(_("StartTag not in PCDATA content model flag: %(tag)s") % {"tag": name})
if not isinstance(name, str):
raise LintError(_("Tag name is not a string: %(tag)r") % {"tag": name})
if not name:
raise LintError(_(u"Empty tag name"))
raise LintError(_("Empty tag name"))
if type == "StartTag" and name in voidElements:
raise LintError(_(u"Void element reported as StartTag token: %s") % name)
raise LintError(_("Void element reported as StartTag token: %(tag)s") % {"tag": name})
elif type == "EmptyTag" and name not in voidElements:
raise LintError(_(u"Non-void element reported as EmptyTag token: %s") % token["name"])
raise LintError(_("Non-void element reported as EmptyTag token: %(tag)s") % {"tag": token["name"]})
if type == "StartTag":
open_elements.append(name)
for name, value in token["data"]:
if not isinstance(name, unicode):
raise LintError(_("Attribute name is not a string: %r") % name)
if not isinstance(name, str):
raise LintError(_("Attribute name is not a string: %(name)r") % {"name": name})
if not name:
raise LintError(_(u"Empty attribute name"))
if not isinstance(value, unicode):
raise LintError(_("Attribute value is not a string: %r") % value)
raise LintError(_("Empty attribute name"))
if not isinstance(value, str):
raise LintError(_("Attribute value is not a string: %(value)r") % {"value": value})
if name in cdataElements:
contentModelFlag = "CDATA"
elif name in rcdataElements:
@@ -45,15 +50,15 @@ class Filter(_base.Filter):
elif type == "EndTag":
name = token["name"]
if not isinstance(name, unicode):
raise LintError(_(u"Tag name is not a string: %r") % name)
if not isinstance(name, str):
raise LintError(_("Tag name is not a string: %(tag)r") % {"tag": name})
if not name:
raise LintError(_(u"Empty tag name"))
raise LintError(_("Empty tag name"))
if name in voidElements:
raise LintError(_(u"Void element reported as EndTag token: %s") % name)
raise LintError(_("Void element reported as EndTag token: %(tag)s") % {"tag": name})
start_name = open_elements.pop()
if start_name != name:
raise LintError(_(u"EndTag (%s) does not match StartTag (%s)") % (name, start_name))
raise LintError(_("EndTag (%(end)s) does not match StartTag (%(start)s)") % {"end": name, "start": start_name})
contentModelFlag = "PCDATA"
elif type == "Comment":
@@ -62,27 +67,27 @@ class Filter(_base.Filter):
elif type in ("Characters", "SpaceCharacters"):
data = token["data"]
if not isinstance(data, unicode):
raise LintError(_("Attribute name is not a string: %r") % data)
if not isinstance(data, str):
raise LintError(_("Attribute name is not a string: %(name)r") % {"name": data})
if not data:
raise LintError(_(u"%s token with empty data") % type)
raise LintError(_("%(type)s token with empty data") % {"type": type})
if type == "SpaceCharacters":
data = data.strip(spaceCharacters)
if data:
raise LintError(_(u"Non-space character(s) found in SpaceCharacters token: ") % data)
raise LintError(_("Non-space character(s) found in SpaceCharacters token: %(token)r") % {"token": data})
elif type == "Doctype":
name = token["name"]
if contentModelFlag != "PCDATA":
raise LintError(_("Doctype not in PCDATA content model flag: %s") % name)
if not isinstance(name, unicode):
raise LintError(_(u"Tag name is not a string: %r") % name)
raise LintError(_("Doctype not in PCDATA content model flag: %(name)s") % {"name": name})
if not isinstance(name, str):
raise LintError(_("Tag name is not a string: %(tag)r") % {"tag": name})
# XXX: what to do with token["data"] ?
elif type in ("ParseError", "SerializeError"):
pass
else:
raise LintError(_(u"Unknown token type: %s") % type)
raise LintError(_("Unknown token type: %(type)s") % {"type": type})
yield token
libs/html5lib/filters/optionaltags.py
+9 -6
View File
@@ -1,4 +1,7 @@
import _base
from __future__ import absolute_import, division, unicode_literals
from . import _base
class Filter(_base.Filter):
def slider(self):
@@ -14,8 +17,8 @@ class Filter(_base.Filter):
for previous, token, next in self.slider():
type = token["type"]
if type == "StartTag":
if (token["data"] or
not self.is_optional_start(token["name"], previous, next)):
if (token["data"] or
not self.is_optional_start(token["name"], previous, next)):
yield token
elif type == "EndTag":
if not self.is_optional_end(token["name"], next):
@@ -73,7 +76,7 @@ class Filter(_base.Filter):
# omit the thead and tfoot elements' end tag when they are
# immediately followed by a tbody element. See is_optional_end.
if previous and previous['type'] == 'EndTag' and \
previous['name'] in ('tbody','thead','tfoot'):
previous['name'] in ('tbody', 'thead', 'tfoot'):
return False
return next["name"] == 'tr'
else:
@@ -121,10 +124,10 @@ class Filter(_base.Filter):
# there is no more content in the parent element.
if type in ("StartTag", "EmptyTag"):
return next["name"] in ('address', 'article', 'aside',
'blockquote', 'datagrid', 'dialog',
'blockquote', 'datagrid', 'dialog',
'dir', 'div', 'dl', 'fieldset', 'footer',
'form', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6',
'header', 'hr', 'menu', 'nav', 'ol',
'header', 'hr', 'menu', 'nav', 'ol',
'p', 'pre', 'section', 'table', 'ul')
else:
return type == "EndTag" or type is None
libs/html5lib/filters/sanitizer.py
+7 -3
View File
@@ -1,8 +1,12 @@
import _base
from html5lib.sanitizer import HTMLSanitizerMixin
from __future__ import absolute_import, division, unicode_literals
from . import _base
from ..sanitizer import HTMLSanitizerMixin
class Filter(_base.Filter, HTMLSanitizerMixin):
def __iter__(self):
for token in _base.Filter.__iter__(self):
token = self.sanitize_token(token)
if token: yield token
if token:
yield token
libs/html5lib/filters/whitespace.py
+9 -12
View File
@@ -1,16 +1,13 @@
try:
frozenset
except NameError:
# Import from the sets module for python 2.3
from sets import ImmutableSet as frozenset
from __future__ import absolute_import, division, unicode_literals
import re
import _base
from html5lib.constants import rcdataElements, spaceCharacters
spaceCharacters = u"".join(spaceCharacters)
from . import _base
from ..constants import rcdataElements, spaceCharacters
spaceCharacters = "".join(spaceCharacters)
SPACES_REGEX = re.compile("[%s]+" % spaceCharacters)
SPACES_REGEX = re.compile(u"[%s]+" % spaceCharacters)
class Filter(_base.Filter):
@@ -21,7 +18,7 @@ class Filter(_base.Filter):
for token in _base.Filter.__iter__(self):
type = token["type"]
if type == "StartTag" \
and (preserve or token["name"] in self.spacePreserveElements):
and (preserve or token["name"] in self.spacePreserveElements):
preserve += 1
elif type == "EndTag" and preserve:
@@ -29,13 +26,13 @@ class Filter(_base.Filter):
elif not preserve and type == "SpaceCharacters" and token["data"]:
# Test on token["data"] above to not introduce spaces where there were not
token["data"] = u" "
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)