Skip to content

gh-135661: Fix parsing start and end tags in HTMLParser #135930

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

gh-135661: Fix parsing start and end tags in HTMLParser #135930

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7171803
gh-135661: Fix parsing start and end tags in HTMLParser
serhiy-storchaka Jun 13, 2025
182b16f
Fix Sphinx errors.
serhiy-storchaka Jun 25, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
136 changes: 52 additions & 84 deletions Lib/html/parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,29 +36,33 @@
# explode, so don't do it.
# see http://www.w3.org/TR/html5/tokenization.html#tag-open-state
# and http://www.w3.org/TR/html5/tokenization.html#tag-name-state
tagfind_tolerant = re.compile(r'([a-zA-Z][^\t\n\r\f />\x00]*)(?:\s|/(?!>))*')
attrfind_tolerant = re.compile(
r'((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*'
r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*')
locatestarttagend_tolerant = re.compile(r"""
<[a-zA-Z][^\t\n\r\f />\x00]* # tag name
(?:[\s/]* # optional whitespace before attribute name
(?:(?<=['"\s/])[^\s/>][^\s/=>]* # attribute name
(?:\s*=+\s* # value indicator
(?:'[^']*' # LITA-enclosed value
|"[^"]*" # LIT-enclosed value
|(?!['"])[^>\s]* # bare value
)
\s* # possibly followed by a space
)?(?:\s|/(?!>))*
)*
tagfind_tolerant = re.compile(r'([a-zA-Z][^\t\n\r\f />]*)(?:[\t\n\r\f ]|/(?!>))*')
attrfind_tolerant = re.compile(r"""
(
(?<=['"\t\n\r\f /])[^\t\n\r\f />][^\t\n\r\f /=>]* # attribute name
)
(= # value indicator
('[^']*' # LITA-enclosed value
|"[^"]*" # LIT-enclosed value
|(?!['"])[^>\t\n\r\f ]* # bare value
)
)?
\s* # trailing whitespace
(?:[\t\n\r\f ]|/(?!>))* # possibly followed by a space
""", re.VERBOSE)
locatetagend_tolerant = re.compile(r"""
[a-zA-Z][^\t\n\r\f />]* # tag name
[\t\n\r\f /]* # optional whitespace before attribute name
(?:(?<=['"\t\n\r\f /])[^\t\n\r\f />][^\t\n\r\f /=>]* # attribute name
(?:= # value indicator
(?:'[^']*' # LITA-enclosed value
|"[^"]*" # LIT-enclosed value
|(?!['"])[^>\t\n\r\f ]* # bare value
)
)?
[\t\n\r\f /]* # possibly followed by a space
)*
>?
""", re.VERBOSE)
endendtag = re.compile('>')
# the HTML 5 spec, section 8.1.2.2, doesn't allow spaces between
# </ and the tag name, so maybe this should be fixed
endtagfind = re.compile(r'</\s*([a-zA-Z][-.a-zA-Z0-9:_]*)\s*>')

# Character reference processing logic specific to attribute values
# See: https://html.spec.whatwg.org/multipage/parsing.html#named-character-reference-state
Expand Down Expand Up @@ -141,7 +145,8 @@ def get_starttag_text(self):

def set_cdata_mode(self, elem):
self.cdata_elem = elem.lower()
self.interesting = re.compile(r'</\s*%s\s*>' % self.cdata_elem, re.I)
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
Expand All @@ -166,7 +171,7 @@ def goahead(self, end):
# & 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)):
not re.compile(r'[\t\n\r\f ;]').search(rawdata, amppos)):
break # wait till we get all the text
j = n
else:
Expand Down Expand Up @@ -381,76 +386,39 @@ def parse_starttag(self, i):
# or -1 if incomplete.
def check_for_whole_start_tag(self, i):
rawdata = self.rawdata
m = locatestarttagend_tolerant.match(rawdata, i)
if m:
j = m.end()
next = rawdata[j:j+1]
if next == ">":
return j + 1
if next == "/":
if rawdata.startswith("/>", j):
return j + 2
if rawdata.startswith("/", j):
# buffer boundary
return -1
# else bogus input
if j > i:
return j
else:
return i + 1
if next == "":
# end of input
return -1
if next in ("abcdefghijklmnopqrstuvwxyz=/"
"ABCDEFGHIJKLMNOPQRSTUVWXYZ"):
# end of input in or before attribute value, or we have the
# '/' from a '/>' ending
return -1
if j > i:
return j
else:
return i + 1
raise AssertionError("we should not get here!")
match = locatetagend_tolerant.match(rawdata, i+1)
assert match
j = match.end()
if rawdata[j-1] != ">":
return -1
return j

# Internal -- parse endtag, return end or -1 if incomplete
def parse_endtag(self, i):
rawdata = self.rawdata
assert rawdata[i:i+2] == "</", "unexpected call to parse_endtag"
match = endendtag.search(rawdata, i+1) # >
if not match:
if rawdata.find('>', i+2) < 0:
return -1
gtpos = match.end()
match = endtagfind.match(rawdata, i) # </ + tag + >
if not match:
if self.cdata_elem is not None:
self.handle_data(rawdata[i:gtpos])
return gtpos
# find the name: w3.org/TR/html5/tokenization.html#tag-name-state
namematch = tagfind_tolerant.match(rawdata, i+2)
if not namematch:
# w3.org/TR/html5/tokenization.html#end-tag-open-state
if rawdata[i:i+3] == '</>':
return i+3
else:
return self.parse_bogus_comment(i)
tagname = namematch.group(1).lower()
# consume and ignore other stuff between the name and the >
# Note: this is not 100% correct, since we might have things like
# </tag attr=">">, but looking for > after the name should cover
# most of the cases and is much simpler
gtpos = rawdata.find('>', namematch.end())
self.handle_endtag(tagname)
return gtpos+1
if not endtagopen.match(rawdata, i): # </ + letter
# w3.org/TR/html5/tokenization.html#end-tag-open-state
if rawdata[i+2:i+3] == '>':
return i+3
else:
return self.parse_bogus_comment(i)

elem = match.group(1).lower() # script or style
if self.cdata_elem is not None:
if elem != self.cdata_elem:
self.handle_data(rawdata[i:gtpos])
return gtpos
match = locatetagend_tolerant.match(rawdata, i+2)
assert match
j = match.end()
if rawdata[j-1] != ">":
return -1

self.handle_endtag(elem)
# find the name: w3.org/TR/html5/tokenization.html#tag-name-state
match = tagfind_tolerant.match(rawdata, i+2)
assert match
tag = match.group(1).lower()
self.handle_endtag(tag)
self.clear_cdata_mode()
return gtpos
return j

# Overridable -- finish processing of start+end tag: <tag.../>
def handle_startendtag(self, tag, attrs):
Expand Down
Loading
Loading