Skip to content

Commit

Permalink
get optionaltags tests working again
Browse files Browse the repository at this point in the history 
--HG--
extra : convert_revision : svn%3Aacbfec75-9323-0410-a652-858a13e371e0/trunk%40655
  • Loading branch information
@rubys
rubys committed May 31, 2007
1 parent 7e8123a commit c98097f
Show file tree
Hide file tree
Showing 2 changed files with 177 additions and 168 deletions.
344 changes: 177 additions & 167 deletions src/serializer.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -45,13 +45,182 @@ def htmlentityreplace_errors(exc):

del register_error

def _slide(iterator):
previous = None
for token in iterator:
if previous is not None:
yield previous, token
previous = token
yield previous, None
class OptionalTagFilter:
def __init__(self, source):
self.source = source

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.
return type == "StartTag"
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 == "StartTag":
# 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', 'option', '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.
# An option element's end tag may be omitted if the option
# element is immediately followed by another option 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, blockquote, dl, fieldset,
# form, h1, h2, h3, h4, h5, h6, hr, menu, ol, p, pre, table,
# or ul element, or if there is no more content in the parent
# element.
if type == "StartTag":
return next["name"] in ('address', 'blockquote', \
'dl', 'fieldset', 'form', 'h1', 'h2', 'h3', 'h4', 'h5', \
'h6', 'hr', 'menu', 'ol', 'p', 'pre', 'table', 'ul')
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

class HTMLSerializer(object):
cdata_elements = frozenset(("style", "script", "xmp", "iframe", "noembed", "noframes", "noscript"))
Expand Down Expand Up @@ -89,7 +258,7 @@ def serialize(self, treewalker, encoding=None):
if self.strip_whitespace:
treewalker = self.filter_whitespace(treewalker)
if self.omit_optional_tags:
treewalker = self.filter_optional_tags(treewalker)
treewalker = OptionalTagFilter(treewalker)
for token in treewalker:
type = token["type"]
if type == "Doctype":
Expand Down Expand Up @@ -218,165 +387,6 @@ def filter_inject_meta_charset(self, treewalker, encoding):
def filter_whitespace(self, treewalker):
raise NotImplementedError

def filter_optional_tags(self, treewalker):
for token, next in _slide(treewalker):
type = token["type"]
if type == "StartTag":
if token["data"] or not self.is_optional_start(token["name"], 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, 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.
return type == "StartTag"
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 == "StartTag":
# 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":
# XXX: we do not look at the preceding event, so instead we never
# omit the thead and tfoot elements' end tag when they are
# immediately followed by a tbody element. See is_optional_end.
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', 'option', '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.
# An option element's end tag may be omitted if the option
# element is immediately followed by another option 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, blockquote, dl, fieldset,
# form, h1, h2, h3, h4, h5, h6, hr, menu, ol, p, pre, table,
# or ul element, or if there is no more content in the parent
# element.
if type == "StartTag":
return next["name"] in ('address', 'blockquote', \
'dl', 'fieldset', 'form', 'h1', 'h2', 'h3', 'h4', 'h5', \
'h6', 'hr', 'menu', 'ol', 'p', 'pre', 'table', 'ul')
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"] == '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.
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

def SerializeError(Exception):
"""Error in serialized tree"""
pass
1 change: 0 additions & 1 deletion tests/test_serializer.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -77,7 +77,6 @@ def serialize_html(self, input, options):

def test_serializer():
for filename in glob.glob('serializer/*.test'):
if filename.find('optionaltags')>=0: continue # TODO
tests = simplejson.load(file(filename))
for test in tests['tests']:
yield test
Expand Down

0 comments on commit c98097f

Please sign in to comment.