Mercurial > cpython-lru_cache-weakref
annotate Tools/unicode/mkstringprep.py @ 49955:878d40468c4e legacy-trunk
Issue #4384: Added logging integration with warnings module using captureWarnings(). This change includes a NullHandler which does nothing; it will be of use to library developers who want to avoid the "No handlers could be found for logger XXX" message which can appear if the library user doesn't configure logging.
| author | Vinay Sajip <vinay_sajip@yahoo.co.uk> |
|---|---|
| date | Wed, 03 Dec 2008 23:22:58 +0000 |
| parents | c3a096bfbd6b |
| children | c51929233e19 8aa5530e8407 a6eb6acfe04a |
| rev | line source |
|---|---|
|
32125
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
1 import re, unicodedata, sys |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
2 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
3 if sys.maxunicode == 65535: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
4 raise RuntimeError, "need UCS-4 Python" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
5 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
6 def gen_category(cats): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
7 for i in range(0, 0x110000): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
8 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
|
9 yield(i) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
10 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
11 def gen_bidirectional(cats): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
12 for i in range(0, 0x110000): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
13 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
|
14 yield(i) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
15 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
16 def compact_set(l): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
17 single = [] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
18 tuple = [] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
19 prev = None |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
20 span = 0 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
21 for e in l: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
22 if prev is None: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
23 prev = e |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
24 span = 0 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
25 continue |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
26 if prev+span+1 != e: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
27 if span > 2: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
28 tuple.append((prev,prev+span+1)) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
29 else: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
30 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
|
31 single.append(i) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
32 prev = e |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
33 span = 0 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
34 else: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
35 span += 1 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
36 if span: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
37 tuple.append((prev,prev+span+1)) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
38 else: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
39 single.append(prev) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
40 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
|
41 if not single: |
|
32125
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
42 return "set(%s)" % tuple |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
43 if not tuple: |
|
32125
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
44 return "set(%s)" % repr(single) |
|
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
45 return "set(%s + %s)" % (repr(single),tuple) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
46 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
47 ############## Read the tables in the RFC ####################### |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
48 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
49 data = open("rfc3454.txt").readlines() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
50 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
51 tables = [] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
52 curname = None |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
53 for l in data: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
54 l = l.strip() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
55 if not l: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
56 continue |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
57 # Skip RFC page breaks |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
58 if l.startswith("Hoffman & Blanchet") or\ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
59 l.startswith("RFC 3454"): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
60 continue |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
61 # Find start/end lines |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
62 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
|
63 if m: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
64 if m.group(1) == "Start": |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
65 if curname: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
66 raise "Double Start",(curname, l) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
67 curname = m.group(2) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
68 table = {} |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
69 tables.append((curname, table)) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
70 continue |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
71 else: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
72 if not curname: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
73 raise "End without start", l |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
74 curname = None |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
75 continue |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
76 if not curname: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
77 continue |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
78 # Now we are in a table |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
79 fields = l.split(";") |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
80 if len(fields) > 1: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
81 # Drop comment field |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
82 fields = fields[:-1] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
83 if len(fields) == 1: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
84 fields = fields[0].split("-") |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
85 if len(fields) > 1: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
86 # range |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
87 try: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
88 start, end = fields |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
89 except ValueError: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
90 raise "Unpacking problem", l |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
91 else: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
92 start = end = fields[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
93 start = int(start, 16) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
94 end = int(end, 16) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
95 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
|
96 table[i] = i |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
97 else: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
98 code, value = fields |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
99 value = value.strip() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
100 if value: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
101 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
|
102 else: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
103 # table B.1 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
104 value = None |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
105 table[int(code, 16)] = value |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
106 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
107 ########### 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
|
108 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
109 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
|
110 \"\"\"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
|
111 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
112 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
|
113 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
|
114 \"\"\" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
115 |
|
32125
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
116 import unicodedata |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
117 """ |
|
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 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
|
120 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
121 # 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
|
122 # 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
|
123 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
124 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
125 assert name == "A.1" |
|
32125
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
126 table = set(table.keys()) |
|
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
127 Cn = set(gen_category(["Cn"])) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
128 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
129 # FDD0..FDEF are process internal codes |
|
32125
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
130 Cn -= set(range(0xFDD0, 0xFDF0)) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
131 # not a character |
|
32125
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
132 Cn -= set(range(0xFFFE, 0x110000, 0x10000)) |
|
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
133 Cn -= set(range(0xFFFF, 0x110000, 0x10000)) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
134 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
135 # assert table == Cn |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
136 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
137 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
138 def in_table_a1(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
139 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
|
140 c = ord(code) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
141 if 0xFDD0 <= c < 0xFDF0: return False |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
142 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
|
143 """ |
|
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 # B.1 cannot easily be derived |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
146 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
147 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
148 assert name == "B.1" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
149 table = table.keys() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
150 table.sort() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
151 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
152 b1_set = """ + compact_set(table) + """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
153 def in_table_b1(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
154 return ord(code) in b1_set |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
155 """ |
|
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 # 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
|
158 # 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
|
159 # 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
|
160 # 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
|
161 # 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
|
162 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
163 name, table_b2 = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
164 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
165 assert name == "B.2" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
166 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
167 name, table_b3 = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
168 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
169 assert name == "B.3" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
170 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
171 # 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
|
172 # 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
|
173 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
174 b3_exceptions = {} |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
175 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
176 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
|
177 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
|
178 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
|
179 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
180 b3 = b3_exceptions.items() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
181 b3.sort() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
182 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
183 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
184 b3_exceptions = {""" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
185 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
|
186 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
|
187 if i % 4 == 3: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
188 print |
|
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 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
191 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
192 def map_table_b3(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
193 r = b3_exceptions.get(ord(code)) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
194 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
|
195 return code.lower() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
196 """ |
|
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 def map_table_b3(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
199 r = b3_exceptions.get(ord(code)) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
200 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
|
201 return code.lower() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
202 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
203 # 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
|
204 # except where NormalizeWithKC(Fold(a)) != |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
205 # NormalizeWithKC(Fold(NormalizeWithKC(Fold(a)))) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
206 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
207 def map_table_b2(a): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
208 al = map_table_b3(a) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
209 b = unicodedata.normalize("NFKC", al) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
210 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
|
211 c = unicodedata.normalize("NFKC", bl) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
212 if b != c: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
213 return c |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
214 else: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
215 return al |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
216 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
217 specials = {} |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
218 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
|
219 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
|
220 specials[k] = v |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
221 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
222 # 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
|
223 assert specials == {} |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
224 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
225 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
226 def map_table_b2(a): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
227 al = map_table_b3(a) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
228 b = unicodedata.normalize("NFKC", al) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
229 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
|
230 c = unicodedata.normalize("NFKC", bl) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
231 if b != c: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
232 return c |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
233 else: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
234 return al |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
235 """ |
|
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 # 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
|
238 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
239 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
240 assert name == "C.1.1" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
241 assert table == {0x20:0x20} |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
242 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
243 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
244 def in_table_c11(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
245 return code == u" " |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
246 """ |
|
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 # 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
|
249 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
250 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
251 assert name == "C.1.2" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
252 |
|
32125
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
253 # table = set(table.keys()) |
|
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
254 # Zs = set(gen_category(["Zs"])) - set([0x20]) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
255 # assert Zs == table |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
256 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
257 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
258 def in_table_c12(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
259 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
|
260 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
261 def in_table_c11_c12(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
262 return unicodedata.category(code) == "Zs" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
263 """ |
|
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 # C.2.1 ASCII control characters |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
266 name, table_c21 = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
267 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
268 assert name == "C.2.1" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
269 |
|
32125
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
270 Cc = set(gen_category(["Cc"])) |
|
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
271 Cc_ascii = Cc & set(range(128)) |
|
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
272 table_c21 = set(table_c21.keys()) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
273 assert Cc_ascii == table_c21 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
274 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
275 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
276 def in_table_c21(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
277 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
|
278 """ |
|
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 # 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
|
281 # 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
|
282 name, table_c22 = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
283 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
284 assert name == "C.2.2" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
285 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
286 Cc_nonascii = Cc - Cc_ascii |
|
32125
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
287 table_c22 = set(table_c22.keys()) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
288 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
|
289 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
290 specials = list(table_c22 - Cc_nonascii) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
291 specials.sort() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
292 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
293 print """c22_specials = """ + compact_set(specials) + """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
294 def in_table_c22(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
295 c = ord(code) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
296 if c < 128: return False |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
297 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
|
298 return c in c22_specials |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
299 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
300 def in_table_c21_c22(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
301 return unicodedata.category(code) == "Cc" or \\ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
302 ord(code) in c22_specials |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
303 """ |
|
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 # C.3 Private use |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
306 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
307 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
308 assert name == "C.3" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
309 |
|
32125
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
310 Co = set(gen_category(["Co"])) |
|
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
311 assert set(table.keys()) == Co |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
312 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
313 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
314 def in_table_c3(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
315 return unicodedata.category(code) == "Co" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
316 """ |
|
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 # 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
|
319 # plus process internal codes |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
320 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
321 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
322 assert name == "C.4" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
323 |
|
32125
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
324 nonchar = set(range(0xFDD0,0xFDF0) + |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
325 range(0xFFFE,0x110000,0x10000) + |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
326 range(0xFFFF,0x110000,0x10000)) |
|
32125
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
327 table = set(table.keys()) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
328 assert table == nonchar |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
329 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
330 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
331 def in_table_c4(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
332 c = ord(code) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
333 if c < 0xFDD0: return False |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
334 if c < 0xFDF0: return True |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
335 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
|
336 """ |
|
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 # C.5 Surrogate codes |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
339 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
340 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
341 assert name == "C.5" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
342 |
|
32125
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
343 Cs = set(gen_category(["Cs"])) |
|
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
344 assert set(table.keys()) == Cs |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
345 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
346 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
347 def in_table_c5(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
348 return unicodedata.category(code) == "Cs" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
349 """ |
|
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 # C.6 Inappropriate for plain text |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
352 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
353 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
354 assert name == "C.6" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
355 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
356 table = table.keys() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
357 table.sort() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
358 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
359 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
360 c6_set = """ + compact_set(table) + """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
361 def in_table_c6(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
362 return ord(code) in c6_set |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
363 """ |
|
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 # C.7 Inappropriate for canonical representation |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
366 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
367 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
368 assert name == "C.7" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
369 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
370 table = table.keys() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
371 table.sort() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
372 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
373 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
374 c7_set = """ + compact_set(table) + """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
375 def in_table_c7(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
376 return ord(code) in c7_set |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
377 """ |
|
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 # 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
|
380 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
381 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
382 assert name == "C.8" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
383 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
384 table = table.keys() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
385 table.sort() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
386 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
387 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
388 c8_set = """ + compact_set(table) + """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
389 def in_table_c8(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
390 return ord(code) in c8_set |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
391 """ |
|
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 # C.9 Tagging characters |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
394 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
395 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
396 assert name == "C.9" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
397 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
398 table = table.keys() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
399 table.sort() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
400 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
401 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
402 c9_set = """ + compact_set(table) + """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
403 def in_table_c9(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
404 return ord(code) in c9_set |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
405 """ |
|
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 # 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
|
408 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
409 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
410 assert name == "D.1" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
411 |
|
32125
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
412 RandAL = set(gen_bidirectional(["R","AL"])) |
|
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
413 assert set(table.keys()) == RandAL |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
414 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
415 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
416 def in_table_d1(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
417 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
|
418 """ |
|
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 # 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
|
421 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
422 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
423 assert name == "D.2" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
424 |
|
32125
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
425 L = set(gen_bidirectional(["L"])) |
|
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
426 assert set(table.keys()) == L |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
427 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
428 print """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
429 def in_table_d2(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
430 return unicodedata.bidirectional(code) == "L" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
431 """ |
