#!/usr/bin/env python
# coding: utf-8
"""
python-creole utils
~~~~~~~~~~~~~~~~~~~
:copyleft: 2008-2011 by python-creole team, see AUTHORS for more details.
:license: GNU GPL v3 or above, see LICENSE for more details.
"""
import re
from creole.parser.html_parser_config import BLOCK_TAGS
strip_html_regex = re.compile(
r"""
\s*
<
(?P one \\n two one two bold italics bold italics a a a
\\n linebreak
linebreak preformated area
foo
a
preformated areafoo' >>> strip_html('
a image.
') 'a image.
' """ def strip_tag(match): block = match.group(0) end_tag = match.group("end") in ("/", "/") startend_tag = match.group("startend") in ("/", "/") tag = match.group("tag") # print("_"*40) # print(match.groupdict()) # print("block.......: %r" % block) # print("end_tag.....:", end_tag) # print("startend_tag:", startend_tag) # print("tag.........: %r" % tag) if tag in BLOCK_TAGS: return block.strip() space_start = block.startswith(" ") space_end = block.endswith(" ") result = block.strip() if end_tag: # It's a normal end tag e.g.: if space_start or space_end: result += " " elif startend_tag: # It's a closed start tag e.g.: