mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-07-09 20:35:26 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 12

#13358: HTMLParser now calls handle_data only once for each CDATA.

Browse source
This commit is contained in:
Ezio Melotti 2011-11-18 18:01:49 +02:00
parent 8008f2aba0
commit 15cb489234
3 changed files with 26 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

7
Lib/html/parser.py
View file

@ -14,7 +14,6 @@ import re
# Regular expressions used for parsing
interesting_normal = re.compile('[&<]')
interesting_cdata = re.compile(r'<(/|\Z)')
incomplete = re.compile('&[a-zA-Z#]')
entityref = re.compile('&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]')
@ -149,8 +148,8 @@ class HTMLParser(_markupbase.ParserBase):
return self.__starttag_text
def set_cdata_mode(self, elem):
self.interesting = interesting_cdata
self.cdata_elem = elem.lower()
self.interesting = re.compile(r'</\s*%s\s*>' % self.cdata_elem, re.I)
def clear_cdata_mode(self):
self.interesting = interesting_normal
@ -168,6 +167,8 @@ class HTMLParser(_markupbase.ParserBase):
if match:
j = match.start()
else:
if self.cdata_elem:
break
j = n
if i < j: self.handle_data(rawdata[i:j])
i = self.updatepos(i, j)
@ -250,7 +251,7 @@ class HTMLParser(_markupbase.ParserBase):
else:
assert 0, "interesting.search() lied"
# end while
if end and i < n:
if end and i < n and not self.cdata_elem:
self.handle_data(rawdata[i:n])
i = self.updatepos(i, n)
self.rawdata = rawdata[i:]