Stowage/cpython
2
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-10-31 13:41:24 +00:00
Code Issues Projects Releases Packages Wiki Activity

SF bug #1504333: sgmlib should allow angle brackets in quoted values

Browse source 
(modified patch by Sam Ruby; changed to use separate REs for start and end
 tags to reduce matching cost for end tags; extended tests; updated to avoid
 breaking previous changes to support IPv6 addresses in unquoted attribute
 values)
This commit is contained in:
Fred Drake 2006-06-29 00:51:53 +00:00
parent 960a3f88e5
commit a136210a9f
2 changed files with 25 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

19
Lib/sgmllib.py
View file

@ -29,7 +29,12 @@
shorttagopen = re.compile('<[a-zA-Z][-.a-zA-Z0-9]*/') shorttagopen = re.compile('<[a-zA-Z][-.a-zA-Z0-9]*/')
shorttag = re.compile('<([a-zA-Z][-.a-zA-Z0-9]*)/([^/]*)/') shorttag = re.compile('<([a-zA-Z][-.a-zA-Z0-9]*)/([^/]*)/')
piclose = re.compile('>') piclose = re.compile('>')
endbracket = re.compile('[<>]') starttag = re.compile(r'<[a-zA-Z][-_.:a-zA-Z0-9]*\s*('
r'\s*([a-zA-Z_][-:.a-zA-Z_0-9]*)(\s*=\s*'
r'(\'[^\']*\'|"[^"]*"|[-a-zA-Z0-9./,:;+*%?!&$\(\)_#=~@]'
r'[][\-a-zA-Z0-9./,:;+*%?!&$\(\)_#=~\'"@]*(?=[\s>/<])))?'
r')*\s*/?\s*(?=[<>])')
endtag = re.compile(r'</?[a-zA-Z][-_.:a-zA-Z0-9]*\s*/?\s*(?=[<>])')
tagfind = re.compile('[a-zA-Z][-_.a-zA-Z0-9]*') tagfind = re.compile('[a-zA-Z][-_.a-zA-Z0-9]*')
attrfind = re.compile( attrfind = re.compile(
r'\s*([a-zA-Z_][-:.a-zA-Z_0-9]*)(\s*=\s*' r'\s*([a-zA-Z_][-:.a-zA-Z_0-9]*)(\s*=\s*'
@ -249,14 +254,10 @@ def parse_starttag(self, i):
self.finish_shorttag(tag, data) self.finish_shorttag(tag, data)
self.__starttag_text = rawdata[start_pos:match.end(1) + 1] self.__starttag_text = rawdata[start_pos:match.end(1) + 1]
return k return k
# XXX The following should skip matching quotes (' or ") match = starttag.match(rawdata, i)
# As a shortcut way to exit, this isn't so bad, but shouldn't
# be used to locate the actual end of the start tag since the
# < or > characters may be embedded in an attribute value.
match = endbracket.search(rawdata, i+1)
if not match: if not match:
return -1 return -1
j = match.start(0) j = match.end(0)
# Now parse the data between i+1 and j into a tag and attrs # Now parse the data between i+1 and j into a tag and attrs
attrs = [] attrs = []
if rawdata[i:i+2] == '<>': if rawdata[i:i+2] == '<>':
@ -305,10 +306,10 @@ def _convert_ref(self, match):
# Internal -- parse endtag # Internal -- parse endtag
def parse_endtag(self, i): def parse_endtag(self, i):
rawdata = self.rawdata rawdata = self.rawdata
match = endbracket.search(rawdata, i+1) match = endtag.match(rawdata, i)
if not match: if not match:
return -1 return -1
j = match.start(0) j = match.end(0)
tag = rawdata[i+2:j].strip().lower() tag = rawdata[i+2:j].strip().lower()
if rawdata[j] == '>': if rawdata[j] == '>':
j = j+1 j = j+1

15
Lib/test/test_sgmllib.py
View file

@ -286,6 +286,21 @@ def test_convert_overrides(self):
('codepoint', 'convert', 42), ('codepoint', 'convert', 42),
]) ])
def test_attr_values_quoted_markup(self):
"""Multi-line and markup in attribute values"""
self.check_events("""<a title='foo\n<br>bar'>text</a>""",
[("starttag", "a", [("title", "foo\n<br>bar")]),
("data", "text"),
("endtag", "a")])
self.check_events("""<a title='less < than'>text</a>""",
[("starttag", "a", [("title", "less < than")]),
("data", "text"),
("endtag", "a")])
self.check_events("""<a title='greater > than'>text</a>""",
[("starttag", "a", [("title", "greater > than")]),
("data", "text"),
("endtag", "a")])
def test_attr_funky_names(self): def test_attr_funky_names(self):
self.check_events("""<a a.b='v' c:d=v e-f=v>""", [ self.check_events("""<a a.b='v' c:d=v e-f=v>""", [
("starttag", "a", [("a.b", "v"), ("c:d", "v"), ("e-f", "v")]), ("starttag", "a", [("a.b", "v"), ("c:d", "v"), ("e-f", "v")]),