1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
|
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# Copyright 2010-2013 Various Authors
# Copyright 2010 Johannes Weißl
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License as
# published by the Free Software Foundation; either version 2 of the
# License, or (at your option) any later version.
#
# This program is distributed in the hope that it will be useful, but
# WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
# General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, see <http://www.gnu.org/licenses/>.
import sys
import re
import os.path
import urllib2
from optparse import OptionParser
# Some letters don't have a decomposition, but can't be composed on all
# keyboards. This dictionary maps them to an ASCII character which
# *looks* similar.
special_decompositions = {
u'Æ': u'A',
u'Ð': u'D',
u'×': u'x',
u'Ø': u'O',
u'Þ': u'P',
u'ß': u'B',
u'æ': u'a',
u'ð': u'd',
u'ø': u'o',
u'þ': u'p',
# Various punctation/quotation characters
u'‐': u'-',
u'‒': u'-',
u'–': u'-',
u'−': u'-',
u'—': u'-',
u'―': u'-',
u'‘': u"'",
u'’': u"'",
u'′': u"'",
u'“': u'"',
u'”': u'"',
u'″': u'"',
u'〃': u'"',
u'…': u'.',
}
def parse_unidata(f):
u = {}
for line in f:
d = line.rstrip('\n').split(';')
cp = int(d[0], 16)
u[cp] = {}
u[cp]['name'] = d[1]
decomp = d[5]
if decomp:
m = re.match(r'<.*> (.*)', decomp)
u[cp]['compat'] = bool(m)
if m:
decomp = m.group(1)
u[cp]['decomp'] = [int(x, 16) for x in decomp.split(' ')]
else:
u[cp]['decomp'] = []
return u
def unidata_expand_decomp(unidata):
def recurse(k):
if k not in unidata or not unidata[k]['decomp']:
return [k]
exp = []
for d in unidata[k]['decomp']:
exp += recurse(d)
return exp
for k in unidata.keys():
exp = recurse(k)
if exp != [k]:
unidata[k]['decomp'] = exp
def unidata_add_mapping(unidata, mapping):
for k, v in mapping.items():
unidata[ord(k)]['decomp'] = [ord(v)]
def is_diacritical_mark(c):
return c >= 0x0300 and c <= 0x036F
def filter_unidata(unidata, include):
for k, v in unidata.items():
if k in include:
continue
if not v['decomp']:
del unidata[k]
continue
b = v['decomp'][0]
if unichr(b) == u' ' or is_diacritical_mark(b):
del unidata[k]
continue
has_accents = False
for d in v['decomp'][1:]:
if is_diacritical_mark(d):
has_accents = True
break
if not has_accents:
del unidata[k]
def output(unidata, f):
buf = '''/* This file is automatically generated. DO NOT EDIT!
Instead, edit %s and re-run. */
static struct {
uchar composed;
uchar base;
} unidecomp_map[] = {
''' % os.path.basename(sys.argv[0])
for k in sorted(unidata.keys()):
b = unidata[k]['decomp'][0]
buf += ('\t{ %#6x, %#6x },\t// %s -> %s,\t%s' % \
(k, b,
unichr(k).encode('utf-8'),
unichr(b).encode('utf-8'),
', '.join([' %s (%x)' %
(unichr(d).encode('utf-8'), d)
for d in unidata[k]['decomp'][1:]]))).rstrip() + '\n'
buf += '};'
f.write(buf+'\n')
def main(argv=None):
if not argv:
argv = sys.argv
parser = OptionParser(usage='usage: %prog [-w] [-o unidecomp.h]')
parser.add_option('-w', '--wget', action='store_true',
help='get unicode data from unicode.org')
parser.add_option('-o', '--output',
help='output file, default stdout')
(options, args) = parser.parse_args(argv[1:])
urlbase = 'http://unicode.org/Public/UNIDATA/'
unidata_filename = 'UnicodeData.txt'
if not os.path.exists(unidata_filename) and not options.wget:
parser.error('''need %s in the current directory, download
from unicode.org or use `--wget' option.''' % unidata_filename)
if options.wget:
unidata_file = urllib2.urlopen(urlbase+unidata_filename)
else:
unidata_file = open(unidata_filename, 'rb')
unidata = parse_unidata(unidata_file)
unidata_file.close()
unidata_add_mapping(unidata, special_decompositions)
unidata_expand_decomp(unidata)
filter_unidata(unidata, [ord(x) for x in special_decompositions])
outfile = sys.stdout
if options.output:
outfile = open(options.output, 'wb')
output(unidata, outfile)
if options.output:
outfile.close()
if __name__ == '__main__':
sys.exit(main())
|