Stowage/cpython
2
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-10-24 02:13:49 +00:00
Code Issues Projects Releases Packages Wiki Activity

gh-118350: Fix support of elements "textarea" and "title" in HTMLParser (#135310)

Browse source 
Co-authored-by: Serhiy Storchaka <storchaka@gmail.com>
Co-authored-by: Łukasz Langa <lukasz@langa.pl>
This commit is contained in:
Timon Viola 2025-07-22 13:27:13 +02:00 • committed by GitHub
parent c933a6bb32
commit 4d02f31cdd
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

96
Lib/test/test_htmlparser.py
View file

@ -317,6 +317,49 @@ def test_style_content(self, content):
("data", content),
("endtag", "style")])
@support.subTests('content', [
'<!-- not a comment -->',
"<not a='start tag'>",
'<![CDATA[not a cdata]]>',
'<!not a bogus comment>',
'</not a bogus comment>',
'\u2603',
'< /title>',
'</ title>',
'</titled>',
'</title\v>',
'</title\xa0>',
'</tıtle>',
])
def test_title_content(self, content):
source = f"<title>{content}</title>"
self._run_check(source, [
("starttag", "title", []),
("data", content),
("endtag", "title"),
])
@support.subTests('content', [
'<!-- not a comment -->',
"<not a='start tag'>",
'<![CDATA[not a cdata]]>',
'<!not a bogus comment>',
'</not a bogus comment>',
'\u2603',
'< /textarea>',
'</ textarea>',
'</textareable>',
'</textarea\v>',
'</textarea\xa0>',
])
def test_textarea_content(self, content):
source = f"<textarea>{content}</textarea>"
self._run_check(source, [
("starttag", "textarea", []),
("data", content),
("endtag", "textarea"),
])
@support.subTests('endtag', ['script', 'SCRIPT', 'script ', 'script\n',
'script/', 'script foo=bar', 'script foo=">"'])
def test_script_closing_tag(self, endtag):
@ -346,6 +389,38 @@ def test_style_closing_tag(self, endtag):
("endtag", "style")],
collector=EventCollectorNoNormalize(convert_charrefs=False))
@support.subTests('endtag', ['title', 'TITLE', 'title ', 'title\n',
'title/', 'title foo=bar', 'title foo=">"'])
def test_title_closing_tag(self, endtag):
content = "<!-- not a comment --><i>Egg &amp; Spam</i>"
s = f'<TitLe>{content}</{endtag}>'
self._run_check(s, [("starttag", "title", []),
('data', '<!-- not a comment --><i>Egg & Spam</i>'),
("endtag", "title")],
collector=EventCollectorNoNormalize(convert_charrefs=True))
self._run_check(s, [("starttag", "title", []),
('data', '<!-- not a comment --><i>Egg '),
('entityref', 'amp'),
('data', ' Spam</i>'),
("endtag", "title")],
collector=EventCollectorNoNormalize(convert_charrefs=False))
@support.subTests('endtag', ['textarea', 'TEXTAREA', 'textarea ', 'textarea\n',
'textarea/', 'textarea foo=bar', 'textarea foo=">"'])
def test_textarea_closing_tag(self, endtag):
content = "<!-- not a comment --><i>Egg &amp; Spam</i>"
s = f'<TexTarEa>{content}</{endtag}>'
self._run_check(s, [("starttag", "textarea", []),
('data', '<!-- not a comment --><i>Egg & Spam</i>'),
("endtag", "textarea")],
collector=EventCollectorNoNormalize(convert_charrefs=True))
self._run_check(s, [("starttag", "textarea", []),
('data', '<!-- not a comment --><i>Egg '),
('entityref', 'amp'),
('data', ' Spam</i>'),
("endtag", "textarea")],
collector=EventCollectorNoNormalize(convert_charrefs=False))
@support.subTests('tail,end', [
('', False),
('<', False),
@ -363,6 +438,27 @@ def test_eof_in_script(self, tail, end):
("data", content if end else content + tail)],
collector=EventCollectorNoNormalize(convert_charrefs=False))
@support.subTests('tail,end', [
('', False),
('<', False),
('</', False),
('</t', False),
('</title', False),
('</title ', True),
('</title foo=bar', True),
('</title foo=">', True),
])
def test_eof_in_title(self, tail, end):
s = f'<TitLe>Egg &amp; Spam{tail}'
self._run_check(s, [("starttag", "title", []),
("data", "Egg & Spam" + ('' if end else tail))],
collector=EventCollectorNoNormalize(convert_charrefs=True))
self._run_check(s, [("starttag", "title", []),
('data', 'Egg '),
('entityref', 'amp'),
('data', ' Spam' + ('' if end else tail))],
collector=EventCollectorNoNormalize(convert_charrefs=False))
def test_comments(self):
html = ("<!-- I'm a valid comment -->"
'<!--me too!-->'