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
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
|
#!/usr/bin/python
# ***** BEGIN LICENSE BLOCK *****
# Version: MPL 1.1/GPL 2.0/LGPL 2.1
#
# The contents of this file are subject to the Mozilla Public License Version
# 1.1 (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
# http://www.mozilla.org/MPL/
#
# Software distributed under the License is distributed on an "AS IS" basis,
# WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
# for the specific language governing rights and limitations under the
# License.
#
# The Original Code is Mozilla Thunderbird.
#
# The Initial Developer of the Original Code is Mozilla Japan.
# Portions created by the Initial Developer are Copyright (C) 2010
# the Initial Developer. All Rights Reserved.
#
# Contributor(s):
# Makoto Kato <m_kato@ga2.so-net.ne.jp>
# Andrew Sutherland <asutherland@asutherland.org>
#
# Alternatively, the contents of this file may be used under the terms of
# either the GNU General Public License Version 2 or later (the "GPL"), or
# the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
# in which case the provisions of the GPL or the LGPL are applicable instead
# of those above. If you wish to allow use of your version of this file only
# under the terms of either the GPL or the LGPL, and not to allow others to
# use your version of this file under the terms of the MPL, indicate your
# decision by deleting the provisions above and replace them with the notice
# and other provisions required by the GPL or the LGPL. If you do not delete
# the provisions above, a recipient may use your version of this file under
# the terms of any one of the MPL, the GPL or the LGPL.
#
# ***** END LICENSE BLOCK *****
import re
def printTable(f, t):
i = f
while i <= t:
c = array[i]
print "0x%04x," % c,
i = i + 1
if not i % 8:
print "\n\t",
print '''/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
/* ***** BEGIN LICENSE BLOCK *****
* Version: MPL 1.1/GPL 2.0/LGPL 2.1
*
* The contents of this file are subject to the Mozilla Public License Version
* 1.1 (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
* http://www.mozilla.org/MPL/
*
* Software distributed under the License is distributed on an "AS IS" basis,
* WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
* for the specific language governing rights and limitations under the
* License.
*
* The Original Code is mozilla.org code.
*
* The Initial Developer of the Original Code is Mozilla Japan.
* Portions created by the Initial Developer are Copyright (C) 2010
* the Initial Developer. All Rights Reserved.
*
* Contributor(s):
* Makoto Kato <m_kato@ga2.so-net.ne.jp>
* Andrew Sutherland <asutherland@asutherland.org>
*
* Alternatively, the contents of this file may be used under the terms of
* either of the GNU General Public License Version 2 or later (the "GPL"),
* or the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
* in which case the provisions of the GPL or the LGPL are applicable instead
* of those above. If you wish to allow use of your version of this file only
* under the terms of either the GPL or the LGPL, and not to allow others to
* use your version of this file under the terms of the MPL, indicate your
* decision by deleting the provisions above and replace them with the notice
* and other provisions required by the GPL or the LGPL. If you do not delete
* the provisions above, a recipient may use your version of this file under
* the terms of any one of the MPL, the GPL or the LGPL.
*
* ***** END LICENSE BLOCK ***** */
/* THIS FILE IS GENERATED BY generate_table.py. DON'T EDIT THIS */
'''
p = re.compile('([0-9A-F]{4,5})(?:\.\.([0-9A-F]{4,5}))?[=\>]([0-9A-F]{4,5})?')
G_FROM = 1
G_TO = 2
G_FIRSTVAL = 3
# Array whose value at index i is the unicode value unicode character i should
# map to.
array = []
# Contents of gNormalizeTable. We insert zero entries for sub-pages where we
# have no mappings. We insert references to the tables where we do have
# such tables.
globalTable = []
globalTable.append("0")
# The (exclusive) upper bound of the conversion table, unicode character-wise.
# This is 0x10000 because our generated table is only 16-bit. This also limits
# the values we can map to; we perform an identity mapping for target values
# that >= maxmapping.
maxmapping = 0x10000
sizePerTable = 64
# Map characters that the mapping tells us to obliterate to the NUKE_CHAR
# (such lines look like "FFF0..FFF8>")
# We do this because if we didn't do this, we would emit these characters as
# part of a token, which we definitely don't want.
NUKE_CHAR = 0x20
# --- load case folding table
# entries in the file look like:
# 0041>0061
# 02D8>0020 0306
# 2000..200A>0020
#
# The 0041 (uppercase A) tells us it lowercases to 0061 (lowercase a).
# The 02D8 is a "spacing clone[s] of diacritic" breve which gets decomposed into
# a space character and a breve. This entry/type of entry also shows up in
# 'nfkc.txt'.
# The 2000..200A covers a range of space characters and maps them down to the
# 'normal' space character.
file = open('nfkc_cf.txt')
m = None
line = "\n"
i = 0x0
while i < maxmapping and line:
if not m:
line = file.readline()
m = p.match(line)
if not m:
continue
low = int(m.group(G_FROM), 16)
# if G_TO is present, use it, otherwise fallback to low
high = m.group(G_TO) and int(m.group(G_TO), 16) or low
# if G_FIRSTVAL is present use it, otherwise use NUKE_CHAR
val = (m.group(G_FIRSTVAL) and int(m.group(G_FIRSTVAL), 16)
or NUKE_CHAR)
continue
if i >= low and i <= high:
if val >= maxmapping:
array.append(i)
else:
array.append(val)
if i == high:
m = None
else:
array.append(i)
i = i + 1
file.close()
# --- load normalization / decomposition table
# It is important that this file gets processed second because the other table
# will tell us about mappings from uppercase U with diaeresis to lowercase u
# with diaeresis. We obviously don't want that clobbering our value. (Although
# this would work out if we propagated backwards rather than forwards...)
#
# - entries in this file that we care about look like:
# 00A0>0020
# 0100=0041 0304
#
# They are found in the "Canonical and compatibility decomposition mappings"
# section.
#
# The 00A0 is mapping NBSP to the normal space character.
# The 0100 (a capital A with a bar over top of) is equivalent to 0041 (capital
# A) plus a 0304 (combining overline). We do not care about the combining
# marks which is why our regular expression does not capture it.
#
#
# - entries that we do not care about look like:
# 0300..0314:230
#
# These map marks to their canonical combining class which appears to be a way
# of specifying the precedence / order in which marks should be combined. The
# key thing is we don't care about them.
file = open('nfkc.txt')
line = file.readline()
m = p.match(line)
while line:
if not m:
line = file.readline()
m = p.match(line)
continue
low = int(m.group(G_FROM), 16)
# if G_TO is present, use it, otherwise fallback to low
high = m.group(G_TO) and int(m.group(G_TO), 16) or low
# if G_FIRSTVAL is present use it, otherwise fall back to NUKE_CHAR
val = m.group(G_FIRSTVAL) and int(m.group(G_FIRSTVAL), 16) or NUKE_CHAR
for i in range(low, high+1):
if i < maxmapping and val < maxmapping:
array[i] = val
m = None
file.close()
# --- generate a normalized table to support case and accent folding
i = 0
needTerm = False;
while i < maxmapping:
if not i % sizePerTable:
# table is empty?
j = i
while j < i + sizePerTable:
if array[j] != j:
break
j += 1
if j == i + sizePerTable:
if i:
globalTable.append("0")
i += sizePerTable
continue
if needTerm:
print "};\n"
globalTable.append("gNormalizeTable%04x" % i)
print "static const unsigned short gNormalizeTable%04x[] = {\n\t" % i,
print "/* U+%04x */\n\t" % i,
needTerm = True
# Decomposition does not case-fold, so we want to compensate by
# performing a lookup here. Because decomposition chains can be
# example: 01d5, a capital U with a diaeresis and a bar. yes, really.
# 01d5 -> 00dc -> 0055 (U) -> 0075 (u)
c = array[i]
while c != array[c]:
c = array[c]
if c >= 0x41 and c <= 0x5a:
raise Exception('got an uppercase character somehow: %x => %x'
% (i, c))
print "0x%04x," % c,
i = i + 1
if not i % 8:
print "\n\t",
print "};\n\nstatic const unsigned short* gNormalizeTable[] = {",
i = 0
while i < (maxmapping / sizePerTable):
if not i % 4:
print "\n\t",
print globalTable[i] + ",",
i += 1
print '''
};
unsigned int normalize_character(const unsigned int c)
{
if (c >= ''' + ('0x%x' % (maxmapping,)) + ''' || !gNormalizeTable[c >> 6])
return c;
return gNormalizeTable[c >> 6][c & 0x3f];
}
'''
|
