diff options
| author | Ezio Melotti <ezio.melotti@gmail.com> | 2015-09-06 18:49:48 (GMT) |
|---|---|---|
| committer | Ezio Melotti <ezio.melotti@gmail.com> | 2015-09-06 18:49:48 (GMT) |
| commit | 564cf7b62ced76a3cc87b16a8a278f0612673690 (patch) | |
| tree | 4595fab1818ef207ad3abd6b0f0323ee6e9b5a5a /Lib/html/parser.py | |
| parent | 56f6e76c680f47ad2b11bed9406305a000a1889a (diff) | |
| parent | 20a2c6482e28a2ca8d257ba646f2b8ead4837387 (diff) | |
| download | cpython-564cf7b62ced76a3cc87b16a8a278f0612673690.zip cpython-564cf7b62ced76a3cc87b16a8a278f0612673690.tar.gz cpython-564cf7b62ced76a3cc87b16a8a278f0612673690.tar.bz2 | |
#23144: merge with 3.5.
Diffstat (limited to 'Lib/html/parser.py')
| -rw-r--r-- | Lib/html/parser.py | 10 |
1 files changed, 9 insertions, 1 deletions
diff --git a/Lib/html/parser.py b/Lib/html/parser.py index 390d4cc..43e6411 100644 --- a/Lib/html/parser.py +++ b/Lib/html/parser.py @@ -139,7 +139,15 @@ class HTMLParser(_markupbase.ParserBase): if self.convert_charrefs and not self.cdata_elem: j = rawdata.find('<', i) if j < 0: - if not end: + # if we can't find the next <, either we are at the end + # or there's more text incoming. If the latter is True, + # we can't pass the text to handle_data in case we have + # a charref cut in half at end. Try to determine if + # this is the case before proceding by looking for an + # & 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)): break # wait till we get all the text j = n else: |