|
1 #!/usr/local/bin/python |
|
2 """ Utility for parsing HTML entity definitions available from: |
|
3 |
|
4 http://www.w3.org/ as e.g. |
|
5 http://www.w3.org/TR/REC-html40/HTMLlat1.ent |
|
6 |
|
7 Input is read from stdin, output is written to stdout in form of a |
|
8 Python snippet defining a dictionary "entitydefs" mapping literal |
|
9 entity name to character or numeric entity. |
|
10 |
|
11 Marc-Andre Lemburg, mal@lemburg.com, 1999. |
|
12 Use as you like. NO WARRANTIES. |
|
13 |
|
14 """ |
|
15 import re,sys |
|
16 import TextTools |
|
17 |
|
18 entityRE = re.compile('<!ENTITY +(\w+) +CDATA +"([^"]+)" +-- +((?:.|\n)+?) *-->') |
|
19 |
|
20 def parse(text,pos=0,endpos=None): |
|
21 |
|
22 pos = 0 |
|
23 if endpos is None: |
|
24 endpos = len(text) |
|
25 d = {} |
|
26 while 1: |
|
27 m = entityRE.search(text,pos,endpos) |
|
28 if not m: |
|
29 break |
|
30 name,charcode,comment = m.groups() |
|
31 d[name] = charcode,comment |
|
32 pos = m.end() |
|
33 return d |
|
34 |
|
35 def writefile(f,defs): |
|
36 |
|
37 f.write("entitydefs = {\n") |
|
38 items = defs.items() |
|
39 items.sort() |
|
40 for name,(charcode,comment) in items: |
|
41 if charcode[:2] == '&#': |
|
42 code = int(charcode[2:-1]) |
|
43 if code < 256: |
|
44 charcode = "'\%o'" % code |
|
45 else: |
|
46 charcode = repr(charcode) |
|
47 else: |
|
48 charcode = repr(charcode) |
|
49 comment = TextTools.collapse(comment) |
|
50 f.write(" '%s':\t%s, \t# %s\n" % (name,charcode,comment)) |
|
51 f.write('\n}\n') |
|
52 |
|
53 if __name__ == '__main__': |
|
54 if len(sys.argv) > 1: |
|
55 infile = open(sys.argv[1]) |
|
56 else: |
|
57 infile = sys.stdin |
|
58 if len(sys.argv) > 2: |
|
59 outfile = open(sys.argv[2],'w') |
|
60 else: |
|
61 outfile = sys.stdout |
|
62 text = infile.read() |
|
63 defs = parse(text) |
|
64 writefile(outfile,defs) |