diff options
| author | Ezio Melotti <ezio.melotti@gmail.com> | 2014-02-01 19:21:01 (GMT) |
|---|---|---|
| committer | Ezio Melotti <ezio.melotti@gmail.com> | 2014-02-01 19:21:01 (GMT) |
| commit | f27b9a741ac7771aa1f6c1219d86a61222fdc20a (patch) | |
| tree | 517d3d39e33b79607e4135bdf1811a2ff908ccd1 /Lib | |
| parent | a479b7505e88947dd8eff82b6bff604636287893 (diff) | |
| download | cpython-f27b9a741ac7771aa1f6c1219d86a61222fdc20a.zip cpython-f27b9a741ac7771aa1f6c1219d86a61222fdc20a.tar.gz cpython-f27b9a741ac7771aa1f6c1219d86a61222fdc20a.tar.bz2 | |
#20288: fix handling of invalid numeric charrefs in HTMLParser.
Diffstat (limited to 'Lib')
| -rw-r--r-- | Lib/html/parser.py | 6 | ||||
| -rw-r--r-- | Lib/test/test_htmlparser.py | 6 |
2 files changed, 9 insertions, 3 deletions
diff --git a/Lib/html/parser.py b/Lib/html/parser.py index 2d3bef3..63fe774 100644 --- a/Lib/html/parser.py +++ b/Lib/html/parser.py @@ -228,9 +228,9 @@ class HTMLParser(_markupbase.ParserBase): i = self.updatepos(i, k) continue else: - if ";" in rawdata[i:]: #bail by consuming &# - self.handle_data(rawdata[0:2]) - i = self.updatepos(i, 2) + if ";" in rawdata[i:]: # bail by consuming &# + self.handle_data(rawdata[i:i+2]) + i = self.updatepos(i, i+2) break elif startswith('&', i): match = entityref.match(rawdata, i) diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py index c977a9d..11d9c9c 100644 --- a/Lib/test/test_htmlparser.py +++ b/Lib/test/test_htmlparser.py @@ -151,6 +151,12 @@ text ("data", "&#bad;"), ("endtag", "p"), ]) + # add the [] as a workaround to avoid buffering (see #20288) + self._run_check(["<div>&#bad;</div>"], [ + ("starttag", "div", []), + ("data", "&#bad;"), + ("endtag", "div"), + ]) def test_unclosed_entityref(self): self._run_check("&entityref foo", [ |