def clean_text(self, text):
# Remove excessive \p tags
text = re.sub(r'\\p\s*\\p', '', text)
# Remove anchors that do not have links
anchors = set(re.findall(r'(?<=\\Q=").+?(?=")', text))
links = set(re.findall(r'(?<=\\q="#).+?(?=")', text))
for unused in anchors.difference(links):
text = text.replace('\\Q="%s"' % unused, '')
# Remove \Cn tags that are within \x and \Xn tags
text = re.sub(
unicode_type(
r'(?msu)(?P<t>\\(x|X[0-4]))(?P<a>.*?)(?P<c>\\C[0-4]\s*=\s*"[^"]*")(?P<b>.*?)(?P=t)'
), '\\g<t>\\g<a>\\g<b>\\g<t>', text)
# Replace bad characters.
text = text.replace(u'\xc2', '')
text = text.replace(u'\xa0', ' ')
# Turn all characters that cannot be represented by themself into their
# PML code equivelent
text = re.sub('[^\x00-\x7f]', lambda x: unipmlcode(x.group()), text)
# Remove excess spaces at beginning and end of lines
text = re.sub('(?m)^[ ]+', '', text)
text = re.sub('(?m)[ ]+$', '', text)
# Remove excessive spaces
text = re.sub('[ ]{2,}', ' ', text)
# Condense excessive \c empty line sequences.
text = re.sub(r'(\\c\s*\\c\s*){2,}', r'\\c \n\\c\n', text)
# Remove excessive newlines.
text = re.sub('\n[ ]+\n', '\n\n', text)
if self.opts.remove_paragraph_spacing:
text = re.sub('\n{2,}', '\n', text)
# Only indent lines that don't have special formatting
text = re.sub(
'(?imu)^(?P<text>.+)$', lambda mo: mo.group('text')
if re.search(r'\\[XxCmrctTp]', mo.group('text')) else
' %s' % mo.group('text'), text)
else:
text = re.sub('\n{3,}', '\n\n', text)
return text
def clean_text(self, text):
# Remove excessive \p tags
text = re.sub(r'\\p\s*\\p', '', text)
# Remove anchors that do not have links
anchors = set(re.findall(r'(?<=\\Q=").+?(?=")', text))
links = set(re.findall(r'(?<=\\q="#).+?(?=")', text))
for unused in anchors.difference(links):
text = text.replace('\\Q="%s"' % unused, '')
# Remove \Cn tags that are within \x and \Xn tags
text = re.sub(ur'(?msu)(?P<t>\\(x|X[0-4]))(?P<a>.*?)(?P<c>\\C[0-4]\s*=\s*"[^"]*")(?P<b>.*?)(?P=t)', '\g<t>\g<a>\g<b>\g<t>', text)
# Replace bad characters.
text = text.replace(u'\xc2', '')
text = text.replace(u'\xa0', ' ')
# Turn all characters that cannot be represented by themself into their
# PML code equivelent
text = re.sub('[^\x00-\x7f]', lambda x: unipmlcode(x.group()), text)
# Remove excess spaces at beginning and end of lines
text = re.sub('(?m)^[ ]+', '', text)
text = re.sub('(?m)[ ]+$', '', text)
# Remove excessive spaces
text = re.sub('[ ]{2,}', ' ', text)
# Condense excessive \c empty line sequences.
text = re.sub('(\\c\s*\\c\s*){2,}', '\\c \n\\c\n', text)
# Remove excessive newlines.
text = re.sub('\n[ ]+\n', '\n\n', text)
if self.opts.remove_paragraph_spacing:
text = re.sub('\n{2,}', '\n', text)
# Only indent lines that don't have special formatting
text = re.sub('(?imu)^(?P<text>.+)$', lambda mo: mo.group('text')
if re.search(r'\\[XxCmrctTp]', mo.group('text')) else ' %s' % mo.group('text'), text)
else:
text = re.sub('\n{3,}', '\n\n', text)
return text
