[Doc-SIG] CharEnt support in HTML4css1.py
David Priest
priest@sfu.ca
Thu, 20 Mar 2003 13:17:16 -0800
The following replacement code allows HTML4css1.py to support the use of
charents. It can be easily adapted to the other writers, I'm sure.
def encode(self, text):
"""Encode special characters in `text` & return."""
# @@@ A codec to do these and all other HTML entities would be
nice.
# text = text.replace("&", "&")
# match standard charent forms (# &xHEXNUM; and &namedEntity;)
text = re.sub(r'&(?!(([a-zA-Z]{2,};)|(#(x|X)?[0-9a-fA-F]{2,4};)))',
r'&', text)
text = text.replace("<", "<")
text = text.replace('"', """)
text = text.replace(">", ">")
text = text.replace("@", "@") # may thwart some address
harvesters
return text