diff options
| author | Ezio Melotti <ezio.melotti@gmail.com> | 2011-11-18 16:00:40 (GMT) |
|---|---|---|
| committer | Ezio Melotti <ezio.melotti@gmail.com> | 2011-11-18 16:00:40 (GMT) |
| commit | 00dc60beee3bf4b68fd658716616f25503a3a9eb (patch) | |
| tree | f229f62cf4c74e6692181a0cc91a1fc12fd06e63 /Lib/HTMLParser.py | |
| parent | 93bbb6a9a641d54c242651e97948c15be911c9bb (diff) | |
| download | cpython-00dc60beee3bf4b68fd658716616f25503a3a9eb.zip cpython-00dc60beee3bf4b68fd658716616f25503a3a9eb.tar.gz cpython-00dc60beee3bf4b68fd658716616f25503a3a9eb.tar.bz2 | |
#13358: HTMLParser now calls handle_data only once for each CDATA.
Diffstat (limited to 'Lib/HTMLParser.py')
| -rw-r--r-- | Lib/HTMLParser.py | 7 |
1 files changed, 4 insertions, 3 deletions
diff --git a/Lib/HTMLParser.py b/Lib/HTMLParser.py index cd353f8..1c6989e 100644 --- a/Lib/HTMLParser.py +++ b/Lib/HTMLParser.py @@ -14,7 +14,6 @@ import re # Regular expressions used for parsing interesting_normal = re.compile('[&<]') -interesting_cdata = re.compile(r'<(/|\Z)') incomplete = re.compile('&[a-zA-Z#]') entityref = re.compile('&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]') @@ -125,8 +124,8 @@ class HTMLParser(markupbase.ParserBase): return self.__starttag_text def set_cdata_mode(self, elem): - self.interesting = interesting_cdata self.cdata_elem = elem.lower() + self.interesting = re.compile(r'</\s*%s\s*>' % self.cdata_elem, re.I) def clear_cdata_mode(self): self.interesting = interesting_normal @@ -144,6 +143,8 @@ class HTMLParser(markupbase.ParserBase): if match: j = match.start() else: + if self.cdata_elem: + break j = n if i < j: self.handle_data(rawdata[i:j]) i = self.updatepos(i, j) @@ -212,7 +213,7 @@ class HTMLParser(markupbase.ParserBase): else: assert 0, "interesting.search() lied" # end while - if end and i < n: + if end and i < n and not self.cdata_elem: self.handle_data(rawdata[i:n]) i = self.updatepos(i, n) self.rawdata = rawdata[i:] |