Library update
This commit is contained in:
Ruud
@@ -0,0 +1,10 @@
|
||||
|
||||
class Filter(object):
|
||||
def __init__(self, source):
|
||||
self.source = source
|
||||
|
||||
def __iter__(self):
|
||||
return iter(self.source)
|
||||
|
||||
def __getattr__(self, name):
|
||||
return getattr(self.source, name)
|
||||
@@ -0,0 +1,127 @@
|
||||
#
|
||||
# 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
|
||||
@@ -0,0 +1,62 @@
|
||||
import _base
|
||||
|
||||
class Filter(_base.Filter):
|
||||
def __init__(self, source, encoding):
|
||||
_base.Filter.__init__(self, source)
|
||||
self.encoding = encoding
|
||||
|
||||
def __iter__(self):
|
||||
state = "pre_head"
|
||||
meta_found = (self.encoding is None)
|
||||
pending = []
|
||||
|
||||
for token in _base.Filter.__iter__(self):
|
||||
type = token["type"]
|
||||
if type == "StartTag":
|
||||
if token["name"].lower() == u"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
|
||||
|
||||
elif token["name"].lower() == u"head" and not meta_found:
|
||||
# insert meta into empty head
|
||||
yield {"type": "StartTag", "name": u"head",
|
||||
"data": token["data"]}
|
||||
yield {"type": "EmptyTag", "name": u"meta",
|
||||
"data": {(None, u"charset"): self.encoding}}
|
||||
yield {"type": "EndTag", "name": u"head"}
|
||||
meta_found = True
|
||||
continue
|
||||
|
||||
elif type == "EndTag":
|
||||
if token["name"].lower() == u"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}}
|
||||
while pending:
|
||||
yield pending.pop(0)
|
||||
meta_found = True
|
||||
state = "post_head"
|
||||
|
||||
if state == "in_head":
|
||||
pending.append(token)
|
||||
else:
|
||||
yield token
|
||||
@@ -0,0 +1,88 @@
|
||||
from gettext import gettext
|
||||
_ = gettext
|
||||
|
||||
import _base
|
||||
from html5lib.constants import cdataElements, rcdataElements, voidElements
|
||||
|
||||
from html5lib.constants import spaceCharacters
|
||||
spaceCharacters = u"".join(spaceCharacters)
|
||||
|
||||
class LintError(Exception): pass
|
||||
|
||||
class Filter(_base.Filter):
|
||||
def __iter__(self):
|
||||
open_elements = []
|
||||
contentModelFlag = "PCDATA"
|
||||
for token in _base.Filter.__iter__(self):
|
||||
type = token["type"]
|
||||
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)
|
||||
if not name:
|
||||
raise LintError(_(u"Empty tag name"))
|
||||
if type == "StartTag" and name in voidElements:
|
||||
raise LintError(_(u"Void element reported as StartTag token: %s") % name)
|
||||
elif type == "EmptyTag" and name not in voidElements:
|
||||
raise LintError(_(u"Non-void element reported as EmptyTag token: %s") % 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 name:
|
||||
raise LintError(_(u"Empty attribute name"))
|
||||
if not isinstance(value, unicode):
|
||||
raise LintError(_("Attribute value is not a string: %r") % value)
|
||||
if name in cdataElements:
|
||||
contentModelFlag = "CDATA"
|
||||
elif name in rcdataElements:
|
||||
contentModelFlag = "RCDATA"
|
||||
elif name == "plaintext":
|
||||
contentModelFlag = "PLAINTEXT"
|
||||
|
||||
elif type == "EndTag":
|
||||
name = token["name"]
|
||||
if not isinstance(name, unicode):
|
||||
raise LintError(_(u"Tag name is not a string: %r") % name)
|
||||
if not name:
|
||||
raise LintError(_(u"Empty tag name"))
|
||||
if name in voidElements:
|
||||
raise LintError(_(u"Void element reported as EndTag token: %s") % name)
|
||||
start_name = open_elements.pop()
|
||||
if start_name != name:
|
||||
raise LintError(_(u"EndTag (%s) does not match StartTag (%s)") % (name, start_name))
|
||||
contentModelFlag = "PCDATA"
|
||||
|
||||
elif type == "Comment":
|
||||
if contentModelFlag != "PCDATA":
|
||||
raise LintError(_("Comment not in PCDATA content model flag"))
|
||||
|
||||
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 data:
|
||||
raise LintError(_(u"%s token with empty data") % type)
|
||||
if type == "SpaceCharacters":
|
||||
data = data.strip(spaceCharacters)
|
||||
if data:
|
||||
raise LintError(_(u"Non-space character(s) found in SpaceCharacters 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)
|
||||
# XXX: what to do with token["data"] ?
|
||||
|
||||
elif type in ("ParseError", "SerializeError"):
|
||||
pass
|
||||
|
||||
else:
|
||||
raise LintError(_(u"Unknown token type: %s") % type)
|
||||
|
||||
yield token
|
||||
@@ -0,0 +1,202 @@
|
||||
import _base
|
||||
|
||||
class Filter(_base.Filter):
|
||||
def slider(self):
|
||||
previous1 = previous2 = None
|
||||
for token in self.source:
|
||||
if previous1 is not None:
|
||||
yield previous2, previous1, token
|
||||
previous2 = previous1
|
||||
previous1 = token
|
||||
yield previous2, previous1, None
|
||||
|
||||
def __iter__(self):
|
||||
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)):
|
||||
yield token
|
||||
elif type == "EndTag":
|
||||
if not self.is_optional_end(token["name"], next):
|
||||
yield token
|
||||
else:
|
||||
yield token
|
||||
|
||||
def is_optional_start(self, tagname, previous, next):
|
||||
type = next and next["type"] or None
|
||||
if tagname in 'html':
|
||||
# An html element's start tag may be omitted if the first thing
|
||||
# inside the html element is not a space character or a comment.
|
||||
return type not in ("Comment", "SpaceCharacters")
|
||||
elif tagname == 'head':
|
||||
# A head element's start tag may be omitted if the first thing
|
||||
# inside the head element is an element.
|
||||
# XXX: we also omit the start tag if the head element is empty
|
||||
if type in ("StartTag", "EmptyTag"):
|
||||
return True
|
||||
elif type == "EndTag":
|
||||
return next["name"] == "head"
|
||||
elif tagname == 'body':
|
||||
# A body element's start tag may be omitted if the first thing
|
||||
# inside the body element is not a space character or a comment,
|
||||
# except if the first thing inside the body element is a script
|
||||
# or style element and the node immediately preceding the body
|
||||
# element is a head element whose end tag has been omitted.
|
||||
if type in ("Comment", "SpaceCharacters"):
|
||||
return False
|
||||
elif type == "StartTag":
|
||||
# XXX: we do not look at the preceding event, so we never omit
|
||||
# the body element's start tag if it's followed by a script or
|
||||
# a style element.
|
||||
return next["name"] not in ('script', 'style')
|
||||
else:
|
||||
return True
|
||||
elif tagname == 'colgroup':
|
||||
# A colgroup element's start tag may be omitted if the first thing
|
||||
# inside the colgroup element is a col element, and if the element
|
||||
# is not immediately preceeded by another colgroup element whose
|
||||
# end tag has been omitted.
|
||||
if type in ("StartTag", "EmptyTag"):
|
||||
# XXX: we do not look at the preceding event, so instead we never
|
||||
# omit the colgroup element's end tag when it is immediately
|
||||
# followed by another colgroup element. See is_optional_end.
|
||||
return next["name"] == "col"
|
||||
else:
|
||||
return False
|
||||
elif tagname == 'tbody':
|
||||
# A tbody element's start tag may be omitted if the first thing
|
||||
# inside the tbody element is a tr element, and if the element is
|
||||
# not immediately preceeded by a tbody, thead, or tfoot element
|
||||
# whose end tag has been omitted.
|
||||
if type == "StartTag":
|
||||
# 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'):
|
||||
return False
|
||||
return next["name"] == 'tr'
|
||||
else:
|
||||
return False
|
||||
return False
|
||||
|
||||
def is_optional_end(self, tagname, next):
|
||||
type = next and next["type"] or None
|
||||
if tagname in ('html', 'head', 'body'):
|
||||
# An html element's end tag may be omitted if the html element
|
||||
# is not immediately followed by a space character or a comment.
|
||||
return type not in ("Comment", "SpaceCharacters")
|
||||
elif tagname in ('li', 'optgroup', 'tr'):
|
||||
# A li element's end tag may be omitted if the li element is
|
||||
# immediately followed by another li element or if there is
|
||||
# no more content in the parent element.
|
||||
# An optgroup element's end tag may be omitted if the optgroup
|
||||
# element is immediately followed by another optgroup element,
|
||||
# or if there is no more content in the parent element.
|
||||
# A tr element's end tag may be omitted if the tr element is
|
||||
# immediately followed by another tr element, or if there is
|
||||
# no more content in the parent element.
|
||||
if type == "StartTag":
|
||||
return next["name"] == tagname
|
||||
else:
|
||||
return type == "EndTag" or type is None
|
||||
elif tagname in ('dt', 'dd'):
|
||||
# A dt element's end tag may be omitted if the dt element is
|
||||
# immediately followed by another dt element or a dd element.
|
||||
# A dd element's end tag may be omitted if the dd element is
|
||||
# immediately followed by another dd element or a dt element,
|
||||
# or if there is no more content in the parent element.
|
||||
if type == "StartTag":
|
||||
return next["name"] in ('dt', 'dd')
|
||||
elif tagname == 'dd':
|
||||
return type == "EndTag" or type is None
|
||||
else:
|
||||
return False
|
||||
elif tagname == 'p':
|
||||
# A p element's end tag may be omitted if the p element is
|
||||
# immediately followed by an address, article, aside,
|
||||
# blockquote, datagrid, dialog, dir, div, dl, fieldset,
|
||||
# footer, form, h1, h2, h3, h4, h5, h6, header, hr, menu,
|
||||
# nav, ol, p, pre, section, table, or ul, element, or if
|
||||
# there is no more content in the parent element.
|
||||
if type in ("StartTag", "EmptyTag"):
|
||||
return next["name"] in ('address', 'article', 'aside',
|
||||
'blockquote', 'datagrid', 'dialog',
|
||||
'dir', 'div', 'dl', 'fieldset', 'footer',
|
||||
'form', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6',
|
||||
'header', 'hr', 'menu', 'nav', 'ol',
|
||||
'p', 'pre', 'section', 'table', 'ul')
|
||||
else:
|
||||
return type == "EndTag" or type is None
|
||||
elif tagname == 'option':
|
||||
# An option element's end tag may be omitted if the option
|
||||
# element is immediately followed by another option element,
|
||||
# or if it is immediately followed by an <code>optgroup</code>
|
||||
# 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
|
||||
@@ -0,0 +1,8 @@
|
||||
import _base
|
||||
from html5lib.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
|
||||
@@ -0,0 +1,41 @@
|
||||
try:
|
||||
frozenset
|
||||
except NameError:
|
||||
# Import from the sets module for python 2.3
|
||||
from sets import ImmutableSet as frozenset
|
||||
|
||||
import re
|
||||
|
||||
import _base
|
||||
from html5lib.constants import rcdataElements, spaceCharacters
|
||||
spaceCharacters = u"".join(spaceCharacters)
|
||||
|
||||
SPACES_REGEX = re.compile(u"[%s]+" % spaceCharacters)
|
||||
|
||||
class Filter(_base.Filter):
|
||||
|
||||
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"] = u" "
|
||||
|
||||
elif not preserve and type == "Characters":
|
||||
token["data"] = collapse_spaces(token["data"])
|
||||
|
||||
yield token
|
||||
|
||||
def collapse_spaces(text):
|
||||
return SPACES_REGEX.sub(' ', text)
|
||||
|
||||
Reference in New Issue
Block a user