Mercurial > cpython-lru_cache-weakref
annotate Tools/unicode/mkstringprep.py @ 33091:48100a01ac7c 2.3
Ignore the locale's encoding if it is an empty string.
| author | Martin v. Löwis <martin@v.loewis.de> |
|---|---|
| date | Thu, 12 Aug 2004 13:14:20 +0000 |
| parents | d41d8de9768f |
| children | b9edd3418a31 |
| rev | line source |
|---|---|
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
1 import re, unicodedata, sys, sets |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
2 from sets import Set |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
3 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
4 if sys.maxunicode == 65535: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
5 raise RuntimeError, "need UCS-4 Python" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
6 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
7 def gen_category(cats): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
8 for i in range(0, 0x110000): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
9 if unicodedata.category(unichr(i)) in cats: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
10 yield(i) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
11 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
12 def gen_bidirectional(cats): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
13 for i in range(0, 0x110000): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
14 if unicodedata.bidirectional(unichr(i)) in cats: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
15 yield(i) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
16 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
17 def compact_set(l): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
18 single = [] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
19 tuple = [] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
20 prev = None |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
21 span = 0 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
22 for e in l: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
23 if prev is None: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
24 prev = e |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
25 span = 0 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
26 continue |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
27 if prev+span+1 != e: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
28 if span > 2: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
29 tuple.append((prev,prev+span+1)) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
30 else: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
31 for i in range(prev, prev+span+1): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
32 single.append(i) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
33 prev = e |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
34 span = 0 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
35 else: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
36 span += 1 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
37 if span: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
38 tuple.append((prev,prev+span+1)) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
39 else: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
40 single.append(prev) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
41 tuple = " + ".join(["range(%d,%d)" % t for t in tuple]) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
42 if not single: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
43 return "sets.Set(%s)" % tuple |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
44 if not tuple: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
45 return "sets.Set(%s)" % repr(single) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
46 return "sets.Set(%s + %s)" % (repr(single),tuple) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
47 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
48 ############## Read the tables in the RFC ####################### |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
49 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
50 data = open("rfc3454.txt").readlines() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
51 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
52 tables = [] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
53 curname = None |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
54 for l in data: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
55 l = l.strip() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
56 if not l: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
57 continue |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
58 # Skip RFC page breaks |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
59 if l.startswith("Hoffman & Blanchet") or\ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
60 l.startswith("RFC 3454"): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
61 continue |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
62 # Find start/end lines |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
63 m = re.match("----- (Start|End) Table ([A-Z](.[0-9])+) -----", l) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
64 if m: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
65 if m.group(1) == "Start": |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
66 if curname: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
67 raise "Double Start",(curname, l) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
68 curname = m.group(2) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
69 table = {} |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
70 tables.append((curname, table)) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
71 continue |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
72 else: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
73 if not curname: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
74 raise "End without start", l |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
75 curname = None |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
76 continue |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
77 if not curname: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
78 continue |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
79 # Now we are in a table |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
80 fields = l.split(";") |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
81 if len(fields) > 1: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
82 # Drop comment field |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
83 fields = fields[:-1] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
84 if len(fields) == 1: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
85 fields = fields[0].split("-") |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
86 if len(fields) > 1: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
87 # range |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
88 try: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
89 start, end = fields |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
90 except ValueError: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
91 raise "Unpacking problem", l |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
92 else: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
93 start = end = fields[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
94 start = int(start, 16) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
95 end = int(end, 16) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
96 for i in range(start, end+1): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
97 table[i] = i |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
98 else: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
99 code, value = fields |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
100 value = value.strip() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
101 if value: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
102 value = [int(v, 16) for v in value.split(" ")] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
103 else: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
104 # table B.1 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
105 value = None |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
106 table[int(code, 16)] = value |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
107 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
108 ########### Generate compact Python versions of the tables ############# |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
109 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
110 print """# This file is generated by mkstringprep.py. DO NOT EDIT. |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
111 \"\"\"Library that exposes various tables found in the StringPrep RFC 3454. |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
112 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
113 There are two kinds of tables: sets, for which a member test is provided, |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
114 and mappings, for which a mapping function is provided. |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
115 \"\"\" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
116 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
117 import unicodedata, sets |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
118 """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
119 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
120 print "assert unicodedata.unidata_version == %s" % repr(unicodedata.unidata_version) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
121 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
122 # A.1 is the table of unassigned characters |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
123 # XXX Plane 15 PUA is listed as unassigned in Python. |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
124 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
125 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
126 assert name == "A.1" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
127 table = Set(table.keys()) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
128 Cn = Set(gen_category(["Cn"])) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
129 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
130 # FDD0..FDEF are process internal codes |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
131 Cn -= Set(range(0xFDD0, 0xFDF0)) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
132 # not a character |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
133 Cn -= Set(range(0xFFFE, 0x110000, 0x10000)) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
134 Cn -= Set(range(0xFFFF, 0x110000, 0x10000)) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
135 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
136 # assert table == Cn |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
137 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
138 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
139 def in_table_a1(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
140 if unicodedata.category(code) != 'Cn': return False |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
141 c = ord(code) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
142 if 0xFDD0 <= c < 0xFDF0: return False |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
143 return (c & 0xFFFF) not in (0xFFFE, 0xFFFF) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
144 """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
145 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
146 # B.1 cannot easily be derived |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
147 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
148 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
149 assert name == "B.1" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
150 table = table.keys() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
151 table.sort() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
152 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
153 b1_set = """ + compact_set(table) + """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
154 def in_table_b1(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
155 return ord(code) in b1_set |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
156 """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
157 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
158 # B.2 and B.3 is case folding. |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
159 # It takes CaseFolding.txt into account, which is |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
160 # not available in the Python database. Since |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
161 # B.2 is derived from B.3, we process B.3 first. |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
162 # B.3 supposedly *is* CaseFolding-3.2.0.txt. |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
163 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
164 name, table_b2 = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
165 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
166 assert name == "B.2" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
167 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
168 name, table_b3 = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
169 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
170 assert name == "B.3" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
171 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
172 # B.3 is mostly Python's .lower, except for a number |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
173 # of special cases, e.g. considering canonical forms. |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
174 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
175 b3_exceptions = {} |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
176 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
177 for k,v in table_b2.items(): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
178 if map(ord, unichr(k).lower()) != v: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
179 b3_exceptions[k] = u"".join(map(unichr,v)) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
180 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
181 b3 = b3_exceptions.items() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
182 b3.sort() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
183 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
184 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
185 b3_exceptions = {""" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
186 for i,(k,v) in enumerate(b3): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
187 print "0x%x:%s," % (k, repr(v)), |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
188 if i % 4 == 3: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
189 print |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
190 print "}" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
191 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
192 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
193 def map_table_b3(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
194 r = b3_exceptions.get(ord(code)) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
195 if r is not None: return r |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
196 return code.lower() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
197 """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
198 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
199 def map_table_b3(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
200 r = b3_exceptions.get(ord(code)) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
201 if r is not None: return r |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
202 return code.lower() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
203 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
204 # B.2 is case folding for NFKC. This is the same as B.3, |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
205 # except where NormalizeWithKC(Fold(a)) != |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
206 # NormalizeWithKC(Fold(NormalizeWithKC(Fold(a)))) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
207 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
208 def map_table_b2(a): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
209 al = map_table_b3(a) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
210 b = unicodedata.normalize("NFKC", al) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
211 bl = u"".join([map_table_b3(ch) for ch in b]) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
212 c = unicodedata.normalize("NFKC", bl) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
213 if b != c: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
214 return c |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
215 else: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
216 return al |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
217 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
218 specials = {} |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
219 for k,v in table_b2.items(): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
220 if map(ord, map_table_b2(unichr(k))) != v: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
221 specials[k] = v |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
222 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
223 # B.3 should not add any additional special cases |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
224 assert specials == {} |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
225 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
226 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
227 def map_table_b2(a): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
228 al = map_table_b3(a) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
229 b = unicodedata.normalize("NFKC", al) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
230 bl = u"".join([map_table_b3(ch) for ch in b]) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
231 c = unicodedata.normalize("NFKC", bl) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
232 if b != c: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
233 return c |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
234 else: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
235 return al |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
236 """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
237 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
238 # C.1.1 is a table with a single character |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
239 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
240 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
241 assert name == "C.1.1" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
242 assert table == {0x20:0x20} |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
243 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
244 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
245 def in_table_c11(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
246 return code == u" " |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
247 """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
248 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
249 # C.1.2 is the rest of all space characters |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
250 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
251 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
252 assert name == "C.1.2" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
253 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
254 # table = Set(table.keys()) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
255 # Zs = Set(gen_category(["Zs"])) - Set([0x20]) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
256 # assert Zs == table |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
257 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
258 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
259 def in_table_c12(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
260 return unicodedata.category(code) == "Zs" and code != u" " |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
261 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
262 def in_table_c11_c12(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
263 return unicodedata.category(code) == "Zs" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
264 """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
265 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
266 # C.2.1 ASCII control characters |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
267 name, table_c21 = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
268 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
269 assert name == "C.2.1" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
270 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
271 Cc = Set(gen_category(["Cc"])) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
272 Cc_ascii = Cc & Set(range(128)) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
273 table_c21 = Set(table_c21.keys()) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
274 assert Cc_ascii == table_c21 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
275 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
276 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
277 def in_table_c21(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
278 return ord(code) < 128 and unicodedata.category(code) == "Cc" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
279 """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
280 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
281 # C.2.2 Non-ASCII control characters. It also includes |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
282 # a number of characters in category Cf. |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
283 name, table_c22 = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
284 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
285 assert name == "C.2.2" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
286 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
287 Cc_nonascii = Cc - Cc_ascii |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
288 table_c22 = Set(table_c22.keys()) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
289 assert len(Cc_nonascii - table_c22) == 0 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
290 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
291 specials = list(table_c22 - Cc_nonascii) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
292 specials.sort() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
293 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
294 print """c22_specials = """ + compact_set(specials) + """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
295 def in_table_c22(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
296 c = ord(code) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
297 if c < 128: return False |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
298 if unicodedata.category(code) == "Cc": return True |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
299 return c in c22_specials |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
300 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
301 def in_table_c21_c22(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
302 return unicodedata.category(code) == "Cc" or \\ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
303 ord(code) in c22_specials |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
304 """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
305 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
306 # C.3 Private use |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
307 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
308 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
309 assert name == "C.3" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
310 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
311 Co = Set(gen_category(["Co"])) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
312 assert Set(table.keys()) == Co |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
313 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
314 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
315 def in_table_c3(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
316 return unicodedata.category(code) == "Co" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
317 """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
318 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
319 # C.4 Non-character code points, xFFFE, xFFFF |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
320 # plus process internal codes |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
321 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
322 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
323 assert name == "C.4" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
324 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
325 nonchar = Set(range(0xFDD0,0xFDF0) + |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
326 range(0xFFFE,0x110000,0x10000) + |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
327 range(0xFFFF,0x110000,0x10000)) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
328 table = Set(table.keys()) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
329 assert table == nonchar |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
330 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
331 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
332 def in_table_c4(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
333 c = ord(code) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
334 if c < 0xFDD0: return False |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
335 if c < 0xFDF0: return True |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
336 return (ord(code) & 0xFFFF) in (0xFFFE, 0xFFFF) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
337 """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
338 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
339 # C.5 Surrogate codes |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
340 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
341 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
342 assert name == "C.5" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
343 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
344 Cs = Set(gen_category(["Cs"])) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
345 assert Set(table.keys()) == Cs |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
346 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
347 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
348 def in_table_c5(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
349 return unicodedata.category(code) == "Cs" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
350 """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
351 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
352 # C.6 Inappropriate for plain text |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
353 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
354 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
355 assert name == "C.6" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
356 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
357 table = table.keys() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
358 table.sort() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
359 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
360 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
361 c6_set = """ + compact_set(table) + """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
362 def in_table_c6(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
363 return ord(code) in c6_set |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
364 """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
365 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
366 # C.7 Inappropriate for canonical representation |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
367 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
368 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
369 assert name == "C.7" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
370 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
371 table = table.keys() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
372 table.sort() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
373 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
374 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
375 c7_set = """ + compact_set(table) + """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
376 def in_table_c7(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
377 return ord(code) in c7_set |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
378 """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
379 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
380 # C.8 Change display properties or are deprecated |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
381 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
382 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
383 assert name == "C.8" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
384 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
385 table = table.keys() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
386 table.sort() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
387 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
388 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
389 c8_set = """ + compact_set(table) + """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
390 def in_table_c8(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
391 return ord(code) in c8_set |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
392 """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
393 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
394 # C.9 Tagging characters |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
395 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
396 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
397 assert name == "C.9" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
398 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
399 table = table.keys() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
400 table.sort() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
401 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
402 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
403 c9_set = """ + compact_set(table) + """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
404 def in_table_c9(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
405 return ord(code) in c9_set |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
406 """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
407 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
408 # D.1 Characters with bidirectional property "R" or "AL" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
409 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
410 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
411 assert name == "D.1" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
412 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
413 RandAL = Set(gen_bidirectional(["R","AL"])) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
414 assert Set(table.keys()) == RandAL |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
415 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
416 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
417 def in_table_d1(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
418 return unicodedata.bidirectional(code) in ("R","AL") |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
419 """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
420 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
421 # D.2 Characters with bidirectional property "L" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
422 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
423 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
424 assert name == "D.2" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
425 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
426 L = Set(gen_bidirectional(["L"])) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
427 assert Set(table.keys()) == L |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
428 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
429 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
430 def in_table_d2(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
431 return unicodedata.bidirectional(code) == "L" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
432 """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
433 |
