diff options
| -rw-r--r-- | Lib/html/parser.py | 2 | ||||
| -rw-r--r-- | Lib/test/test_htmlparser.py | 10 | ||||
| -rw-r--r-- | Misc/NEWS.d/next/Library/2023-02-13-21-41-34.gh-issue-86155.ppIGSC.rst | 2 |
3 files changed, 13 insertions, 1 deletions
diff --git a/Lib/html/parser.py b/Lib/html/parser.py index 1b8b6ea0e5a..1e30956fe24 100644 --- a/Lib/html/parser.py +++ b/Lib/html/parser.py @@ -260,7 +260,7 @@ class HTMLParser(_markupbase.ParserBase): 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: diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py index 68649e9d6d5..61fa24fab57 100644 --- a/Lib/test/test_htmlparser.py +++ b/Lib/test/test_htmlparser.py @@ -317,6 +317,16 @@ text ("endtag", element_lower)], collector=Collector(convert_charrefs=False)) + def test_EOF_in_cdata(self): + content = """<!-- not a comment --> ¬-an-entity-ref; + <a href="" /> </p><p> <span></span></style> + '</script' + '>'""" + s = f'<script>{content}' + self._run_check(s, [ + ("starttag", 'script', []), + ("data", content) + ]) + def test_comments(self): html = ("<!-- I'm a valid comment -->" '<!--me too!-->' diff --git a/Misc/NEWS.d/next/Library/2023-02-13-21-41-34.gh-issue-86155.ppIGSC.rst b/Misc/NEWS.d/next/Library/2023-02-13-21-41-34.gh-issue-86155.ppIGSC.rst new file mode 100644 index 00000000000..bb85481b229 --- /dev/null +++ b/Misc/NEWS.d/next/Library/2023-02-13-21-41-34.gh-issue-86155.ppIGSC.rst @@ -0,0 +1,2 @@ +:meth:`html.parser.HTMLParser.close` no longer loses data when the +``<script>`` tag is not closed. Patch by Waylan Limberg. |