def cleanHTML(text, skipchars=[], extra_careful=True):
'''This is an attempt to get rid of " ä " etc within a string
Still working on it ... any help appreicated.'''
entitydefs_inverted = {}
for k, v in entitydefs.iteritems():
entitydefs_inverted[v] = k
badchars_regex = re.compile('|'.join(entitydefs.values()))
been_fixed_regex = re.compile('&\w+;|&#[0-9]+;')
# if extra_careful we don't attempt to do anything to
# the string if it might have been converted already.
if extra_careful and been_fixed_regex.findall(text):
return text
if type(skipchars) == type('s'):
skipchars = [skipchars]
keyholder = {}
for x in badchars_regex.findall(text):
if x not in skipchars:
keyholder[x] = 1
text = text.replace('&', '&')
text = text.replace('\x80', '€')
for key in keyholder.keys():
if key == '&':
continue
better = entitydefs_inverted[key]
if not better.startswith('&#'):
better = '&%s;' % entitydefs_inverted[each]
text = text.replace(key, better)
return text
def cleanHTML(text, skipchars=[], extra_careful=True):
'''This is an attempt to get rid of " ä " etc within a string
Still working on it ... any help appreicated.'''
entitydefs_inverted = {}
for k,v in entitydefs.iteritems():
entitydefs_inverted[v] = k
badchars_regex = re.compile('|'.join(entitydefs.values()))
been_fixed_regex = re.compile('&\w+;|&#[0-9]+;')
# if extra_careful we don't attempt to do anything to
# the string if it might have been converted already.
if extra_careful and been_fixed_regex.findall(text):
return text
if type(skipchars) == type('s'):
skipchars = [skipchars]
keyholder= {}
for x in badchars_regex.findall(text):
if x not in skipchars:
keyholder[x] = 1
text = text.replace('&','&')
text = text.replace('\x80', '€')
for key in keyholder.keys():
if key == '&':
continue
better = entitydefs_inverted[key]
if not better.startswith('&#'):
better = '&%s;' % entitydefs_inverted[each]
text = text.replace(key, better)
return text
if math.floor(size) == size:
return "%d %s" % (int(size), final_unit)
else:
return "%3.1f %s" % (size, final_unit)
if unit != "Yotta":
size /= 1024.0
return "%3.1f %s" % (size, final_unit)
entitydefs_inverted = {}
for k, v in entitydefs.items():
entitydefs_inverted[v] = k
_badchars_regex = re.compile("|".join(entitydefs.values()))
_been_fixed_regex = re.compile("&\w+;|&#[0-9]+;")
def html_entity_fixer(text, skipchars=[], extra_careful=1):
# if extra_careful we don't attempt to do anything to
# the string if it might have been converted already.
if extra_careful and _been_fixed_regex.findall(text):
return text
if type(skipchars) == type("s"):
skipchars = [skipchars]
keyholder = []
for char in _badchars_regex.findall(text):
if char not in skipchars:
joined = '%s<%s %s>' % (part1, tag, attribute)
joined += '%s%s</%s>%s</p>' % (dashes, _p_splitted[0], tag,
_p_splitted[1])
else:
joined = '%s<%s %s>%s%s</%s>' % (part1, tag, attribute, dashes,
part2, tag)
return joined
return text
def niceboolean(value):
falseness = ('', 'no', 'off', 'false', 'none', '0', 'f', 'n')
return str(value).lower().strip() not in falseness
_badchars_regex = re.compile('|'.join(entitydefs.values()))
_been_fixed_regex = re.compile('&\w+;|&#[0-9]+;')
def html_entity_fixer(text, skipchars=[], extra_careful=1):
""" return a text properly html fixed """
if not text:
# then don't even begin to try to do anything
return text
# if extra_careful we don't attempt to do anything to
# the string if it might have been converted already.
if extra_careful and _been_fixed_regex.findall(text):
return text
if isinstance(skipchars, basestring):
part.__init__(self, 'tr', style=style, attributes=attributes)
self.addPart('th', content=self.text)
self.addPart('td', content=self.field)
# need some functions for HTML
# ought to be somewhere else in Python?
# cgi.escape only seems to do <, >, and &
from htmlentitydefs import entitydefs
import re
entitydefs_inverted = {}
for k, v in entitydefs.items():
entitydefs_inverted[v] = k
needencoding = re.compile('|'.join(entitydefs.values()))
alreadyencoded = re.compile('&\w+;|&#[0-9]+;')
# encodes any special characters to their HTML equivalents
def encode(text, skip=None, once_only=1):
# if extra_careful, check to see if this text has already been converted
if not (once_only and alreadyencoded.findall(text)):
if not isinstance(skip, list):
skip = [skip]
# do ampersands on their own or we might end up converting our conversions
if '&' not in skip:
text = text.replace('&', '&')
skip.append('&')
self.addPiece(self.text)
self.addPiece(self.field)
else:
part.__init__(self, 'tr', style=style, attributes=attributes)
self.addPart('th', content=self.text)
self.addPart('td', content=self.field)
from htmlentitydefs import entitydefs
import re
entitydefs_inverted = {}
for k,v in entitydefs.items():
entitydefs_inverted[v] = k
needencoding = re.compile('|'.join(entitydefs.values()))
alreadyencoded = re.compile('&\w+;|&#[0-9]+;')
#need some functions for HTML
#ought to be somewhere else in Python?
#cgi.escape only seems to do <, >, and &
#encodes any special characters to their HTML equivalents
def encode(text, skip=None, once_only=1):
# if extra_careful, check to see if this text has already been converted
if not (once_only and alreadyencoded.findall(text)):
if not isinstance(skip, list):
skip = [skip]
#do ampersands on their own or we might end up converting our conversions
if '&' not in skip:
