mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-22 09:45:06 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 13

#23144: Make sure that HTMLParser.feed() returns all the data, even when convert_charrefs is True.

Browse source
This commit is contained in:
Ezio Melotti 2015-09-06 21:38:06 +03:00
parent 527ef0792f
commit 6f2bb98966
3 changed files with 25 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

10
Lib/html/parser.py
View file

@ -198,7 +198,15 @@ class HTMLParser(_markupbase.ParserBase):
if self.convert_charrefs and not self.cdata_elem:
j = rawdata.find('<', i)
if j < 0:
if not end:
# if we can't find the next <, either we are at the end
# or there's more text incoming. If the latter is True,
# we can't pass the text to handle_data in case we have
# a charref cut in half at end. Try to determine if
# this is the case before proceding by looking for an
# & near the end and see if it's followed by a space or ;.
amppos = rawdata.rfind('&', max(i, n-34))
if (amppos >= 0 and
not re.compile(r'[\s;]').search(rawdata, amppos)):
break # wait till we get all the text
j = n
else: