mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-09-11 11:17:16 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 13

[3.13] gh-118350: Fix support of elements "textarea" and "title" in HTMLParser (GH-135310) (GH-136985)

Browse source 
(cherry picked from commit 4d02f31cdd)

Co-authored-by: Timon Viola <44016238+timonviola@users.noreply.github.com>
Co-authored-by: Serhiy Storchaka <storchaka@gmail.com>
Co-authored-by: Łukasz Langa <lukasz@langa.pl>
This commit is contained in:
Miss Islington (bot) 2025-07-22 14:17:59 +02:00 • committed by GitHub
parent 4999cdbced
commit 8de88e0840
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 113 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

20
Lib/html/parser.py
View file

@ -128,6 +128,7 @@ class HTMLParser(_markupbase.ParserBase):
"""
CDATA_CONTENT_ELEMENTS = ("script", "style")
RCDATA_CONTENT_ELEMENTS = ("textarea", "title")
def __init__(self, *, convert_charrefs=True):
"""Initialize and reset this instance.
@ -145,6 +146,7 @@ class HTMLParser(_markupbase.ParserBase):
self.lasttag = '???'
self.interesting = interesting_normal
self.cdata_elem = None
self._escapable = True
super().reset()
def feed(self, data):
@ -166,14 +168,20 @@ class HTMLParser(_markupbase.ParserBase):
"""Return full source of start tag: '<...>'."""
return self.__starttag_text
def set_cdata_mode(self, elem):
def set_cdata_mode(self, elem, *, escapable=False):
self.cdata_elem = elem.lower()
self.interesting = re.compile(r'</%s(?=[\t\n\r\f />])' % self.cdata_elem,
re.IGNORECASE|re.ASCII)
self._escapable = escapable
if escapable and not self.convert_charrefs:
self.interesting = re.compile(r'&|</%s(?=[\t\n\r\f />])' % self.cdata_elem,
re.IGNORECASE|re.ASCII)
else:
self.interesting = re.compile(r'</%s(?=[\t\n\r\f />])' % self.cdata_elem,
re.IGNORECASE|re.ASCII)
def clear_cdata_mode(self):
self.interesting = interesting_normal
self.cdata_elem = None
self._escapable = True
# Internal -- handle data as far as reasonable. May leave state
# and data to be processed by a subsequent call. If 'end' is
@ -206,7 +214,7 @@ class HTMLParser(_markupbase.ParserBase):
break
j = n
if i < j:
if self.convert_charrefs and not self.cdata_elem:
if self.convert_charrefs and self._escapable:
self.handle_data(unescape(rawdata[i:j]))
else:
self.handle_data(rawdata[i:j])
@ -308,7 +316,7 @@ class HTMLParser(_markupbase.ParserBase):
assert 0, "interesting.search() lied"
# end while
if end and i < n:
if self.convert_charrefs and not self.cdata_elem:
if self.convert_charrefs and self._escapable:
self.handle_data(unescape(rawdata[i:n]))
else:
self.handle_data(rawdata[i:n])
@ -420,6 +428,8 @@ class HTMLParser(_markupbase.ParserBase):
self.handle_starttag(tag, attrs)
if tag in self.CDATA_CONTENT_ELEMENTS:
self.set_cdata_mode(tag)
elif tag in self.RCDATA_CONTENT_ELEMENTS:
self.set_cdata_mode(tag, escapable=True)
return endpos
# Internal -- check to see if we have a complete starttag; return end