Skip to content

[3.9] gh-135661: Fix parsing start and end tags in HTMLParser according to the HTML5 standard (GH-135930) (GH-136268) #136293

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 1 commit into
base: 3.9
Choose a base branch
from
+222 −120
Open

[3.9] gh-135661: Fix parsing start and end tags in HTMLParser according to the HTML5 standard (GH-135930) (GH-136268) #136293

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
145 changes: 70 additions & 75 deletions Lib/html/parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,15 +29,43 @@
piclose = re.compile('>')
commentclose = re.compile(r'--\s*>')
# Note:
# 1) if you change tagfind/attrfind remember to update locatestarttagend too;
# 2) if you change tagfind/attrfind and/or locatestarttagend the parser will
# 1) if you change tagfind/attrfind remember to update locatetagend too;
# 2) if you change tagfind/attrfind and/or locatetagend the parser will
# 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|/(?!>))*')
# see the HTML5 specs section "13.2.5.6 Tag open state",
# "13.2.5.8 Tag name state" and "13.2.5.33 Attribute name state".
# https://html.spec.whatwg.org/multipage/parsing.html#tag-open-state
# https://html.spec.whatwg.org/multipage/parsing.html#tag-name-state
# https://html.spec.whatwg.org/multipage/parsing.html#attribute-name-state
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
)
)?
(?:[\t\n\r\f ]|/(?!>))* # possibly followed by a space
""", re.VERBOSE)
locatetagend = 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)
# The following variables are not used, but are temporarily left for
# backward compatibility.
locatestarttagend_tolerant = re.compile(r"""
<[a-zA-Z][^\t\n\r\f />\x00]* # tag name
(?:[\s/]* # optional whitespace before attribute name
Expand All @@ -54,8 +82,6 @@
\s* # trailing whitespace
""", 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*>')


Expand Down Expand Up @@ -122,7 +148,8 @@ 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 @@ -147,7 +174,7 @@ 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 @@ -260,7 +287,7 @@ def goahead(self, end):
else:
assert 0, "interesting.search() lied"
# end while
if end and i < n and not self.cdata_elem:
if end and i < n:
if self.convert_charrefs and not self.cdata_elem:
self.handle_data(unescape(rawdata[i:n]))
else:
Expand Down Expand Up @@ -291,7 +318,7 @@ def parse_html_declaration(self, i):
return self.parse_bogus_comment(i)

# Internal -- parse bogus comment, return length or -1 if not terminated
# see http://www.w3.org/TR/html5/tokenization.html#bogus-comment-state
# see https://html.spec.whatwg.org/multipage/parsing.html#bogus-comment-state
def parse_bogus_comment(self, i, report=1):
rawdata = self.rawdata
assert rawdata[i:i+2] in ('<!', '</'), ('unexpected call to '
Expand All @@ -317,6 +344,8 @@ def parse_pi(self, i):

# Internal -- handle starttag, return end or -1 if not terminated
def parse_starttag(self, i):
# See the HTML5 specs section "13.2.5.8 Tag name state"
# https://html.spec.whatwg.org/multipage/parsing.html#tag-name-state
self.__starttag_text = None
endpos = self.check_for_whole_start_tag(i)
if endpos < 0:
Expand Down Expand Up @@ -369,76 +398,42 @@ 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.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):
# See the HTML5 specs section "13.2.5.7 End tag open state"
# https://html.spec.whatwg.org/multipage/parsing.html#end-tag-open-state
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: # fast check
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
if rawdata[i+2:i+3] == '>': # </> is ignored
# "missing-end-tag-name" parser error
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.match(rawdata, i+2)
assert match
j = match.end()
if rawdata[j-1] != ">":
return -1

self.handle_endtag(elem)
# find the name: "13.2.5.8 Tag name state"
# https://html.spec.whatwg.org/multipage/parsing.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
25 changes: 25 additions & 0 deletions Lib/test/support/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1551,6 +1551,31 @@ def check_sizeof(test, o, size):
% (type(o), result, size)
test.assertEqual(result, size, msg)

def subTests(arg_names, arg_values, /, *, _do_cleanups=False):
"""Run multiple subtests with different parameters.
"""
single_param = False
if isinstance(arg_names, str):
arg_names = arg_names.replace(',',' ').split()
if len(arg_names) == 1:
single_param = True
arg_values = tuple(arg_values)
def decorator(func):
if isinstance(func, type):
raise TypeError('subTests() can only decorate methods, not classes')
@functools.wraps(func)
def wrapper(self, /, *args, **kwargs):
for values in arg_values:
if single_param:
values = (values,)
subtest_kwargs = dict(zip(arg_names, values))
with self.subTest(**subtest_kwargs):
func(self, *args, **kwargs, **subtest_kwargs)
if _do_cleanups:
self.doCleanups()
return wrapper
return decorator

#=======================================================================
# Decorator for running a function in a different locale, correctly resetting
# it afterwards.
Expand Down
Loading
Loading