Mercurial > cpython-lru_cache-weakref
annotate Tools/unicode/mkstringprep.py @ 87690:66c1c9f32567 default tip
Add use_weakref option to functools.lru_cache
The use_weakref option makes lru_cache create weak references to the function
arguments when creating the cache key, which prevents them from staying in the
memory forever even after all other references to them are gone.
This is a proof of concept for http://bugs.python.org/issue19859
| author | Radomir Dopieralski <devel@sheep.art.pl> |
|---|---|
| date | Tue, 03 Dec 2013 16:02:48 +0100 |
| parents | 8f95d77443da |
| children |
| rev | line source |
|---|---|
|
84066
8f95d77443da
Issue #15239: Make mkstringprep.py work again on Python 3.
Serhiy Storchaka <storchaka@gmail.com>
parents:
47103
diff
changeset
|
1 import re, sys |
|
8f95d77443da
Issue #15239: Make mkstringprep.py work again on Python 3.
Serhiy Storchaka <storchaka@gmail.com>
parents:
47103
diff
changeset
|
2 from unicodedata import ucd_3_2_0 as unicodedata |
|
28671
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: |
|
42715
e4ade16a694f
Convert raise statements in Tools/.
Collin Winter <collinw@gmail.com>
parents:
42427
diff
changeset
|
5 raise RuntimeError("need UCS-4 Python") |
|
28671
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): |
|
47103
63741c7521aa
More 2to3 fixes in the Tools directory. Fixes #2893.
Georg Brandl <georg@python.org>
parents:
42715
diff
changeset
|
9 if unicodedata.category(chr(i)) in cats: |
|
28671
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): |
|
47103
63741c7521aa
More 2to3 fixes in the Tools directory. Fixes #2893.
Georg Brandl <georg@python.org>
parents:
42715
diff
changeset
|
14 if unicodedata.bidirectional(chr(i)) in cats: |
|
28671
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) |
|
84066
8f95d77443da
Issue #15239: Make mkstringprep.py work again on Python 3.
Serhiy Storchaka <storchaka@gmail.com>
parents:
47103
diff
changeset
|
41 if not single and len(tuple) == 1: |
|
8f95d77443da
Issue #15239: Make mkstringprep.py work again on Python 3.
Serhiy Storchaka <storchaka@gmail.com>
parents:
47103
diff
changeset
|
42 tuple = "range(%d,%d)" % tuple[0] |
|
8f95d77443da
Issue #15239: Make mkstringprep.py work again on Python 3.
Serhiy Storchaka <storchaka@gmail.com>
parents:
47103
diff
changeset
|
43 else: |
|
8f95d77443da
Issue #15239: Make mkstringprep.py work again on Python 3.
Serhiy Storchaka <storchaka@gmail.com>
parents:
47103
diff
changeset
|
44 tuple = " + ".join("list(range(%d,%d))" % t for t in tuple) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
45 if not single: |
|
32125
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
46 return "set(%s)" % tuple |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
47 if not tuple: |
|
84066
8f95d77443da
Issue #15239: Make mkstringprep.py work again on Python 3.
Serhiy Storchaka <storchaka@gmail.com>
parents:
47103
diff
changeset
|
48 return "set(%r)" % (single,) |
|
8f95d77443da
Issue #15239: Make mkstringprep.py work again on Python 3.
Serhiy Storchaka <storchaka@gmail.com>
parents:
47103
diff
changeset
|
49 return "set(%r + %s)" % (single, tuple) |
|
28671
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 ############## Read the tables in the RFC ####################### |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
52 |
|
84066
8f95d77443da
Issue #15239: Make mkstringprep.py work again on Python 3.
Serhiy Storchaka <storchaka@gmail.com>
parents:
47103
diff
changeset
|
53 with open("rfc3454.txt") as f: |
|
8f95d77443da
Issue #15239: Make mkstringprep.py work again on Python 3.
Serhiy Storchaka <storchaka@gmail.com>
parents:
47103
diff
changeset
|
54 data = f.readlines() |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
55 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
56 tables = [] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
57 curname = None |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
58 for l in data: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
59 l = l.strip() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
60 if not l: |
|
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 # Skip RFC page breaks |
|
84066
8f95d77443da
Issue #15239: Make mkstringprep.py work again on Python 3.
Serhiy Storchaka <storchaka@gmail.com>
parents:
47103
diff
changeset
|
63 if l.startswith(("Hoffman & Blanchet", "RFC 3454")): |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
64 continue |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
65 # Find start/end lines |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
66 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
|
67 if m: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
68 if m.group(1) == "Start": |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
69 if curname: |
|
47103
63741c7521aa
More 2to3 fixes in the Tools directory. Fixes #2893.
Georg Brandl <georg@python.org>
parents:
42715
diff
changeset
|
70 raise RuntimeError("Double Start", (curname, l)) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
71 curname = m.group(2) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
72 table = {} |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
73 tables.append((curname, table)) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
74 continue |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
75 else: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
76 if not curname: |
|
47103
63741c7521aa
More 2to3 fixes in the Tools directory. Fixes #2893.
Georg Brandl <georg@python.org>
parents:
42715
diff
changeset
|
77 raise RuntimeError("End without start", l) |
|
84066
8f95d77443da
Issue #15239: Make mkstringprep.py work again on Python 3.
Serhiy Storchaka <storchaka@gmail.com>
parents:
47103
diff
changeset
|
78 if curname != m.group(2): |
|
8f95d77443da
Issue #15239: Make mkstringprep.py work again on Python 3.
Serhiy Storchaka <storchaka@gmail.com>
parents:
47103
diff
changeset
|
79 raise RuntimeError("Unexpected end", l) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
80 curname = None |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
81 continue |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
82 if not curname: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
83 continue |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
84 # Now we are in a table |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
85 fields = l.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 # Drop comment field |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
88 fields = fields[:-1] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
89 if len(fields) == 1: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
90 fields = fields[0].split("-") |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
91 if len(fields) > 1: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
92 # range |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
93 try: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
94 start, end = fields |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
95 except ValueError: |
|
47103
63741c7521aa
More 2to3 fixes in the Tools directory. Fixes #2893.
Georg Brandl <georg@python.org>
parents:
42715
diff
changeset
|
96 raise RuntimeError("Unpacking problem", l) |
|
28671
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 start = end = fields[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
99 start = int(start, 16) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
100 end = int(end, 16) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
101 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
|
102 table[i] = i |
|
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 code, value = fields |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
105 value = value.strip() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
106 if value: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
107 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
|
108 else: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
109 # table B.1 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
110 value = None |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
111 table[int(code, 16)] = value |
|
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 ########### 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
|
114 |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
115 print("""# This file is generated by mkstringprep.py. DO NOT EDIT. |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
116 \"\"\"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
|
117 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
118 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
|
119 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
|
120 \"\"\" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
121 |
|
84066
8f95d77443da
Issue #15239: Make mkstringprep.py work again on Python 3.
Serhiy Storchaka <storchaka@gmail.com>
parents:
47103
diff
changeset
|
122 from unicodedata import ucd_3_2_0 as unicodedata |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
123 """) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
124 |
|
84066
8f95d77443da
Issue #15239: Make mkstringprep.py work again on Python 3.
Serhiy Storchaka <storchaka@gmail.com>
parents:
47103
diff
changeset
|
125 print("assert unicodedata.unidata_version == %r" % (unicodedata.unidata_version,)) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
126 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
127 # 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
|
128 # 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
|
129 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
130 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
131 assert name == "A.1" |
|
32125
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
132 table = set(table.keys()) |
|
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
133 Cn = set(gen_category(["Cn"])) |
|
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 # 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
|
136 Cn -= set(range(0xFDD0, 0xFDF0)) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
137 # not a character |
|
32125
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
138 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
|
139 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
|
140 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
141 # assert table == Cn |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
142 |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
143 print(""" |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
144 def in_table_a1(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
145 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
|
146 c = ord(code) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
147 if 0xFDD0 <= c < 0xFDF0: return False |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
148 return (c & 0xFFFF) not in (0xFFFE, 0xFFFF) |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
149 """) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
150 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
151 # B.1 cannot easily be derived |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
152 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
153 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
154 assert name == "B.1" |
|
47103
63741c7521aa
More 2to3 fixes in the Tools directory. Fixes #2893.
Georg Brandl <georg@python.org>
parents:
42715
diff
changeset
|
155 table = sorted(table.keys()) |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
156 print(""" |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
157 b1_set = """ + compact_set(table) + """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
158 def in_table_b1(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
159 return ord(code) in b1_set |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
160 """) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
161 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
162 # 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
|
163 # 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
|
164 # 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
|
165 # 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
|
166 # 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
|
167 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
168 name, table_b2 = 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.2" |
|
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 name, table_b3 = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
173 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
174 assert name == "B.3" |
|
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 # 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
|
177 # 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
|
178 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
179 b3_exceptions = {} |
|
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 for k,v in table_b2.items(): |
|
84066
8f95d77443da
Issue #15239: Make mkstringprep.py work again on Python 3.
Serhiy Storchaka <storchaka@gmail.com>
parents:
47103
diff
changeset
|
182 if list(map(ord, chr(k).lower())) != v: |
|
8f95d77443da
Issue #15239: Make mkstringprep.py work again on Python 3.
Serhiy Storchaka <storchaka@gmail.com>
parents:
47103
diff
changeset
|
183 b3_exceptions[k] = "".join(map(chr,v)) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
184 |
|
47103
63741c7521aa
More 2to3 fixes in the Tools directory. Fixes #2893.
Georg Brandl <georg@python.org>
parents:
42715
diff
changeset
|
185 b3 = sorted(b3_exceptions.items()) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
186 |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
187 print(""" |
|
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
188 b3_exceptions = {""") |
|
84066
8f95d77443da
Issue #15239: Make mkstringprep.py work again on Python 3.
Serhiy Storchaka <storchaka@gmail.com>
parents:
47103
diff
changeset
|
189 for i, kv in enumerate(b3): |
|
8f95d77443da
Issue #15239: Make mkstringprep.py work again on Python 3.
Serhiy Storchaka <storchaka@gmail.com>
parents:
47103
diff
changeset
|
190 print("0x%x:%a," % kv, end=' ') |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
191 if i % 4 == 3: |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
192 print() |
|
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
193 print("}") |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
194 |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
195 print(""" |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
196 def map_table_b3(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
197 r = b3_exceptions.get(ord(code)) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
198 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
|
199 return code.lower() |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
200 """) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
201 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
202 def map_table_b3(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
203 r = b3_exceptions.get(ord(code)) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
204 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
|
205 return code.lower() |
|
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 # 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
|
208 # except where NormalizeWithKC(Fold(a)) != |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
209 # NormalizeWithKC(Fold(NormalizeWithKC(Fold(a)))) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
210 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
211 def map_table_b2(a): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
212 al = map_table_b3(a) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
213 b = unicodedata.normalize("NFKC", al) |
|
47103
63741c7521aa
More 2to3 fixes in the Tools directory. Fixes #2893.
Georg Brandl <georg@python.org>
parents:
42715
diff
changeset
|
214 bl = "".join([map_table_b3(ch) for ch in b]) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
215 c = unicodedata.normalize("NFKC", bl) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
216 if b != c: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
217 return c |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
218 else: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
219 return al |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
220 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
221 specials = {} |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
222 for k,v in table_b2.items(): |
|
47103
63741c7521aa
More 2to3 fixes in the Tools directory. Fixes #2893.
Georg Brandl <georg@python.org>
parents:
42715
diff
changeset
|
223 if list(map(ord, map_table_b2(chr(k)))) != v: |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
224 specials[k] = v |
|
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 # 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
|
227 assert specials == {} |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
228 |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
229 print(""" |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
230 def map_table_b2(a): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
231 al = map_table_b3(a) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
232 b = unicodedata.normalize("NFKC", al) |
|
84066
8f95d77443da
Issue #15239: Make mkstringprep.py work again on Python 3.
Serhiy Storchaka <storchaka@gmail.com>
parents:
47103
diff
changeset
|
233 bl = "".join([map_table_b3(ch) for ch in b]) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
234 c = unicodedata.normalize("NFKC", bl) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
235 if b != c: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
236 return c |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
237 else: |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
238 return al |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
239 """) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
240 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
241 # 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
|
242 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
243 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
244 assert name == "C.1.1" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
245 assert table == {0x20:0x20} |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
246 |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
247 print(""" |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
248 def in_table_c11(code): |
|
84066
8f95d77443da
Issue #15239: Make mkstringprep.py work again on Python 3.
Serhiy Storchaka <storchaka@gmail.com>
parents:
47103
diff
changeset
|
249 return code == " " |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
250 """) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
251 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
252 # 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
|
253 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
254 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
255 assert name == "C.1.2" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
256 |
|
32125
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
257 # table = set(table.keys()) |
|
84066
8f95d77443da
Issue #15239: Make mkstringprep.py work again on Python 3.
Serhiy Storchaka <storchaka@gmail.com>
parents:
47103
diff
changeset
|
258 # Zs = set(gen_category(["Zs"])) - {0x20} |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
259 # assert Zs == table |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
260 |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
261 print(""" |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
262 def in_table_c12(code): |
|
84066
8f95d77443da
Issue #15239: Make mkstringprep.py work again on Python 3.
Serhiy Storchaka <storchaka@gmail.com>
parents:
47103
diff
changeset
|
263 return unicodedata.category(code) == "Zs" and code != " " |
|
28671
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 def in_table_c11_c12(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
266 return unicodedata.category(code) == "Zs" |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
267 """) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
268 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
269 # C.2.1 ASCII control characters |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
270 name, table_c21 = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
271 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
272 assert name == "C.2.1" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
273 |
|
32125
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
274 Cc = set(gen_category(["Cc"])) |
|
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
275 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
|
276 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
|
277 assert Cc_ascii == table_c21 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
278 |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
279 print(""" |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
280 def in_table_c21(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
281 return ord(code) < 128 and unicodedata.category(code) == "Cc" |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
282 """) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
283 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
284 # 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
|
285 # 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
|
286 name, table_c22 = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
287 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
288 assert name == "C.2.2" |
|
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 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
|
291 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
|
292 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
|
293 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
294 specials = list(table_c22 - Cc_nonascii) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
295 specials.sort() |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
296 |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
297 print("""c22_specials = """ + compact_set(specials) + """ |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
298 def in_table_c22(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
299 c = ord(code) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
300 if c < 128: return False |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
301 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
|
302 return c 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 def in_table_c21_c22(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
305 return unicodedata.category(code) == "Cc" or \\ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
306 ord(code) in c22_specials |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
307 """) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
308 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
309 # C.3 Private use |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
310 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
311 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
312 assert name == "C.3" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
313 |
|
32125
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
314 Co = set(gen_category(["Co"])) |
|
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
315 assert set(table.keys()) == Co |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
316 |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
317 print(""" |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
318 def in_table_c3(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
319 return unicodedata.category(code) == "Co" |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
320 """) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
321 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
322 # 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
|
323 # plus process internal codes |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
324 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
325 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
326 assert name == "C.4" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
327 |
|
47103
63741c7521aa
More 2to3 fixes in the Tools directory. Fixes #2893.
Georg Brandl <georg@python.org>
parents:
42715
diff
changeset
|
328 nonchar = set(range(0xFDD0,0xFDF0)) |
|
63741c7521aa
More 2to3 fixes in the Tools directory. Fixes #2893.
Georg Brandl <georg@python.org>
parents:
42715
diff
changeset
|
329 nonchar.update(range(0xFFFE,0x110000,0x10000)) |
|
63741c7521aa
More 2to3 fixes in the Tools directory. Fixes #2893.
Georg Brandl <georg@python.org>
parents:
42715
diff
changeset
|
330 nonchar.update(range(0xFFFF,0x110000,0x10000)) |
|
32125
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
331 table = set(table.keys()) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
332 assert table == nonchar |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
333 |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
334 print(""" |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
335 def in_table_c4(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
336 c = ord(code) |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
337 if c < 0xFDD0: return False |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
338 if c < 0xFDF0: return True |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
339 return (ord(code) & 0xFFFF) in (0xFFFE, 0xFFFF) |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
340 """) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
341 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
342 # C.5 Surrogate codes |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
343 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
344 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
345 assert name == "C.5" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
346 |
|
32125
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
347 Cs = set(gen_category(["Cs"])) |
|
b9edd3418a31
Applying SF patch #949329 on behalf of Raymond Hettinger.
Armin Rigo <arigo@tunes.org>
parents:
28671
diff
changeset
|
348 assert set(table.keys()) == Cs |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
349 |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
350 print(""" |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
351 def in_table_c5(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
352 return unicodedata.category(code) == "Cs" |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
353 """) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
354 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
355 # C.6 Inappropriate for plain text |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
356 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
357 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
358 assert name == "C.6" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
359 |
|
47103
63741c7521aa
More 2to3 fixes in the Tools directory. Fixes #2893.
Georg Brandl <georg@python.org>
parents:
42715
diff
changeset
|
360 table = sorted(table.keys()) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
361 |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
362 print(""" |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
363 c6_set = """ + compact_set(table) + """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
364 def in_table_c6(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
365 return ord(code) in c6_set |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
366 """) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
367 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
368 # C.7 Inappropriate for canonical representation |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
369 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
370 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
371 assert name == "C.7" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
372 |
|
47103
63741c7521aa
More 2to3 fixes in the Tools directory. Fixes #2893.
Georg Brandl <georg@python.org>
parents:
42715
diff
changeset
|
373 table = sorted(table.keys()) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
374 |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
375 print(""" |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
376 c7_set = """ + compact_set(table) + """ |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
377 def in_table_c7(code): |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
378 return ord(code) in c7_set |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
379 """) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
380 |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
381 # 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
|
382 name, table = tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
383 del tables[0] |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
384 assert name == "C.8" |
|
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
385 |
|
47103
63741c7521aa
More 2to3 fixes in the Tools directory. Fixes #2893.
Georg Brandl <georg@python.org>
parents:
42715
diff
changeset
|
386 table = sorted(table.keys()) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
387 |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
388 print(""" |
|
28671
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 |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
392 """) |
|
28671
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 |
|
47103
63741c7521aa
More 2to3 fixes in the Tools directory. Fixes #2893.
Georg Brandl <georg@python.org>
parents:
42715
diff
changeset
|
399 table = sorted(table.keys()) |
|
28671
d41d8de9768f
Implement IDNA (Internationalized Domain Names in Applications).
Martin v. Löwis <martin@v.loewis.de>
parents:
diff
changeset
|
400 |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
401 print(""" |
|
28671
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 |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
405 """) |
|
28671
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 |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
415 print(""" |
|
28671
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") |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
418 """) |
|
28671
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 |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
428 print(""" |
|
28671
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" |
|
42427
46625e6122e9
Convert print statements to function calls in Tools/.
Collin Winter <collinw@gmail.com>
parents:
41642
diff
changeset
|
431 """) |
