cpython/Tools/scripts/parseentities.py

65 lines
1.7 KiB
Python
Raw Normal View History

#!/usr/bin/env python
""" Utility for parsing HTML entity definitions available from:
http://www.w3.org/ as e.g.
http://www.w3.org/TR/REC-html40/HTMLlat1.ent
Input is read from stdin, output is written to stdout in form of a
Python snippet defining a dictionary "entitydefs" mapping literal
entity name to character or numeric entity.
2001-01-17 04:48:39 -04:00
Marc-Andre Lemburg, mal@lemburg.com, 1999.
Use as you like. NO WARRANTIES.
"""
import re,sys
import TextTools
entityRE = re.compile('<!ENTITY +(\w+) +CDATA +"([^"]+)" +-- +((?:.|\n)+?) *-->')
def parse(text,pos=0,endpos=None):
pos = 0
if endpos is None:
2000-09-17 22:46:01 -03:00
endpos = len(text)
d = {}
while 1:
2000-09-17 22:46:01 -03:00
m = entityRE.search(text,pos,endpos)
if not m:
break
name,charcode,comment = m.groups()
d[name] = charcode,comment
pos = m.end()
return d
def writefile(f,defs):
f.write("entitydefs = {\n")
items = defs.items()
items.sort()
for name,(charcode,comment) in items:
2000-09-17 22:46:01 -03:00
if charcode[:2] == '&#':
code = int(charcode[2:-1])
if code < 256:
charcode = "'\%o'" % code
else:
charcode = repr(charcode)
else:
charcode = repr(charcode)
comment = TextTools.collapse(comment)
f.write(" '%s':\t%s, \t# %s\n" % (name,charcode,comment))
f.write('\n}\n')
if __name__ == '__main__':
if len(sys.argv) > 1:
2000-09-17 22:46:01 -03:00
infile = open(sys.argv[1])
else:
2000-09-17 22:46:01 -03:00
infile = sys.stdin
if len(sys.argv) > 2:
2000-09-17 22:46:01 -03:00
outfile = open(sys.argv[2],'w')
else:
2000-09-17 22:46:01 -03:00
outfile = sys.stdout
text = infile.read()
defs = parse(text)
writefile(outfile,defs)