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
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
|
#!/usr/bin/python
# -*- coding: utf-8 -*-
# @author Philip
import tarfile, zipfile
import os, re, shutil, sys, platform
pyversion = platform.python_version()
islinux = platform.system().lower() == 'linux' or False
if pyversion[:3] in ['2.5', '2.6', '2.7']:
import urllib as urllib_request
import codecs
uniopen = codecs.open
def unichr2(i):
if sys.maxunicode >= 0x10000 or i < 0x10000:
return unichr(i)
else:
return unichr(0xD7C0+(i>>10)) + unichr(0xDC00+(i&0x3FF))
elif pyversion[:2] == '3.':
import urllib.request as urllib_request
uniopen = open
unichr2 = chr
# DEFINE
SF_MIRROR = 'easynews'
SCIM_TABLES_VER = '0.5.9'
SCIM_PINYIN_VER = '0.5.91'
LIBTABE_VER = '0.2.3'
# END OF DEFINE
def GetFileFromURL( url, dest ):
if os.path.isfile(dest):
print( 'File %s up to date.' % dest )
return
global islinux
if islinux:
# we use wget instead urlretrieve under Linux,
# because wget will display details like download progress
os.system('wget %s' % url)
else:
print( 'Downloading from [%s] ...' % url )
urllib_request.urlretrieve( url, dest )
print( 'Download complete.\n' )
return
def GetFileFromUnihan( path ):
print( 'Extracting files from %s ...' % path )
text = zipfile.ZipFile(path).read('Unihan_Variants.txt')
uhfile = uniopen('Unihan_Variants.txt', 'w')
uhfile.write(text)
uhfile.close()
return
def GetFileFromTar( path, member, rename ):
print( 'Extracting %s from %s ...' % (rename, path) )
tarfile.open(path, 'r:gz').extract(member)
shutil.move(member, rename)
tree_rmv = member.split('/')[0]
shutil.rmtree(tree_rmv)
return
def ReadBIG5File( dest ):
print( 'Reading and decoding %s ...' % dest )
f1 = uniopen( dest, 'r', encoding='big5hkscs', errors='replace' )
text = f1.read()
text = text.replace( '\ufffd', '\n' )
f1.close()
f2 = uniopen( dest, 'w', encoding='utf8' )
f2.write(text)
f2.close()
return text
def ReadFile( dest ):
print( 'Reading and decoding %s ...' % dest )
f = uniopen( dest, 'r', encoding='utf8' )
ret = f.read()
f.close()
return ret
def ReadUnihanFile( dest ):
print( 'Reading and decoding %s ...' % dest )
f = uniopen( dest, 'r', encoding='utf8' )
t2s_code = []
s2t_code = []
while True:
line = f.readline()
if line:
if line.startswith('#'):
continue
elif not line.find('kSimplifiedVariant') == -1:
temp = line.split('kSimplifiedVariant')
t2s_code.append( ( temp[0].strip(), temp[1].strip() ) )
elif not line.find('kTraditionalVariant') == -1:
temp = line.split('kTraditionalVariant')
s2t_code.append( ( temp[0].strip(), temp[1].strip() ) )
else:
break
f.close()
return ( t2s_code, s2t_code )
def RemoveRows( text, num ):
text = re.sub( '.*\s*', '', text, num)
return text
def RemoveOneCharConv( text ):
preg = re.compile('^.\s*$', re.MULTILINE)
text = preg.sub( '', text )
return text
def ConvertToChar( code ):
code = code.split('<')[0]
return unichr2( int( code[2:], 16 ) )
def GetDefaultTable( code_table ):
char_table = {}
for ( f, t ) in code_table:
if f and t:
from_char = ConvertToChar( f )
to_chars = [ConvertToChar( code ) for code in t.split()]
char_table[from_char] = to_chars
return char_table
def GetManualTable( dest ):
text = ReadFile( dest )
temp1 = text.split()
char_table = {}
for elem in temp1:
elem = elem.strip('|')
if elem:
temp2 = elem.split( '|', 1 )
from_char = unichr2( int( temp2[0][2:7], 16 ) )
to_chars = [unichr2( int( code[2:7], 16 ) ) for code in temp2[1].split('|')]
char_table[from_char] = to_chars
return char_table
def GetValidTable( src_table ):
valid_table = {}
for f, t in src_table.items():
valid_table[f] = t[0]
return valid_table
def GetToManyRules( src_table ):
tomany_table = {}
for f, t in src_table.items():
for i in range(1, len(t)):
tomany_table[t[i]] = True
return tomany_table
def RemoveRules( dest, table ):
text = ReadFile( dest )
temp1 = text.split()
for elem in temp1:
f = ''
t = ''
elem = elem.strip().replace( '"', '' ).replace( '\'', '' )
if '=>' in elem:
if elem.startswith( '=>' ):
t = elem.replace( '=>', '' ).strip()
elif elem.endswith( '=>' ):
f = elem.replace( '=>', '' ).strip()
else:
temp2 = elem.split( '=>' )
f = temp2[0].strip()
t = temp2[1].strip()
try:
table.pop(f, t)
continue
except:
continue
else:
f = t = elem
if f:
try:
table.pop(f)
except:
x = 1
if t:
for temp_f, temp_t in table.copy().items():
if temp_t == t:
table.pop(temp_f)
return table
def DictToSortedList1( src_table ):
return sorted( src_table.items(), key = lambda m: m[0] ) #sorted( temp_table, key = lambda m: len( m[0] ) )
def DictToSortedList2( src_table ):
return sorted( src_table.items(), key = lambda m: m[1] )
def Converter( string, conv_table ):
i = 0
while i < len(string):
for j in range(len(string) - i, 0, -1):
f = string[i:][:j]
t = conv_table.get( f )
if t:
string = string[:i] + t + string[i:][j:]
i += len(t) - 1
break
i += 1
return string
def GetDefaultWordsTable( src_wordlist, src_tomany, char_conv_table, char_reconv_table ):
wordlist = list( set( src_wordlist ) )
wordlist.sort( key = len, reverse = True )
word_conv_table = {}
word_reconv_table = {}
while wordlist:
conv_table = {}
reconv_table = {}
conv_table.update( word_conv_table )
conv_table.update( char_conv_table )
reconv_table.update( word_reconv_table )
reconv_table.update( char_reconv_table )
word = wordlist.pop()
new_word_len = word_len = len(word)
while new_word_len == word_len:
rvt_test = False
for char in word:
rvt_test = rvt_test or src_tomany.get(char)
test_word = Converter( word, reconv_table )
new_word = Converter( word, conv_table )
if not reconv_table.get( new_word ):
if not test_word == word:
word_conv_table[word] = new_word
word_reconv_table[new_word] = word
elif rvt_test:
rvt_word = Converter( new_word, reconv_table )
if not rvt_word == word:
word_conv_table[word] = new_word
word_reconv_table[new_word] = word
try:
word = wordlist.pop()
except IndexError:
break
new_word_len = len(word)
return word_reconv_table
def GetManualWordsTable( src_wordlist, conv_table ):
src_wordlist = [items.split('#')[0].strip() for items in src_wordlist]
wordlist = list( set( src_wordlist ) )
wordlist.sort( key = len, reverse = True )
reconv_table = {}
while wordlist:
word = wordlist.pop()
new_word = Converter( word, conv_table )
reconv_table[new_word] = word
return reconv_table
def CustomRules( dest ):
text = ReadFile( dest )
temp = text.split()
ret = dict()
for i in range( 0, len( temp ), 2 ):
ret[temp[i]] = temp[i + 1]
return ret
def GetPHPArray( table ):
lines = ['\'%s\' => \'%s\',' % (f, t) for (f, t) in table if f and t]
#lines = ['"%s"=>"%s",' % (f, t) for (f, t) in table]
return '\n'.join(lines)
def RemoveSameChar( src_table ):
dst_table = {}
for f, t in src_table.items():
if f != t:
dst_table[f] = t
return dst_table
def main():
#Get Unihan.zip:
url = 'http://www.unicode.org/Public/UNIDATA/Unihan.zip'
han_dest = 'Unihan.zip'
GetFileFromURL( url, han_dest )
# Get scim-tables-$(SCIM_TABLES_VER).tar.gz:
url = 'http://%s.dl.sourceforge.net/sourceforge/scim/scim-tables-%s.tar.gz' % ( SF_MIRROR, SCIM_TABLES_VER )
tbe_dest = 'scim-tables-%s.tar.gz' % SCIM_TABLES_VER
GetFileFromURL( url, tbe_dest )
# Get scim-pinyin-$(SCIM_PINYIN_VER).tar.gz:
url = 'http://%s.dl.sourceforge.net/sourceforge/scim/scim-pinyin-%s.tar.gz' % ( SF_MIRROR, SCIM_PINYIN_VER )
pyn_dest = 'scim-pinyin-%s.tar.gz' % SCIM_PINYIN_VER
GetFileFromURL( url, pyn_dest )
# Get libtabe-$(LIBTABE_VER).tgz:
url = 'http://%s.dl.sourceforge.net/sourceforge/libtabe/libtabe-%s.tgz' % ( SF_MIRROR, LIBTABE_VER )
lbt_dest = 'libtabe-%s.tgz' % LIBTABE_VER
GetFileFromURL( url, lbt_dest )
# Extract the file from a comressed files
# Unihan.txt Simp. & Trad
GetFileFromUnihan( han_dest )
# Make word lists
t_wordlist = []
s_wordlist = []
# EZ.txt.in Trad
src = 'scim-tables-%s/tables/zh/EZ-Big.txt.in' % SCIM_TABLES_VER
dst = 'EZ.txt.in'
GetFileFromTar( tbe_dest, src, dst )
text = ReadFile( dst )
text = text.split( 'BEGIN_TABLE' )[1].strip()
text = text.split( 'END_TABLE' )[0].strip()
text = re.sub( '.*\t', '', text )
text = RemoveOneCharConv( text )
t_wordlist.extend( text.split() )
# Wubi.txt.in Simp
src = 'scim-tables-%s/tables/zh/Wubi.txt.in' % SCIM_TABLES_VER
dst = 'Wubi.txt.in'
GetFileFromTar( tbe_dest, src, dst )
text = ReadFile( dst )
text = text.split( 'BEGIN_TABLE' )[1].strip()
text = text.split( 'END_TABLE' )[0].strip()
text = re.sub( '.*\t(.*?)\t\d*', '\g<1>', text )
text = RemoveOneCharConv( text )
s_wordlist.extend( text.split() )
# Ziranma.txt.in Simp
src = 'scim-tables-%s/tables/zh/Ziranma.txt.in' % SCIM_TABLES_VER
dst = 'Ziranma.txt.in'
GetFileFromTar( tbe_dest, src, dst )
text = ReadFile( dst )
text = text.split( 'BEGIN_TABLE' )[1].strip()
text = text.split( 'END_TABLE' )[0].strip()
text = re.sub( '.*\t(.*?)\t\d*', '\g<1>', text )
text = RemoveOneCharConv( text )
s_wordlist.extend( text.split() )
# phrase_lib.txt Simp
src = 'scim-pinyin-%s/data/phrase_lib.txt' % SCIM_PINYIN_VER
dst = 'phrase_lib.txt'
GetFileFromTar( pyn_dest, src, dst )
text = ReadFile( 'phrase_lib.txt' )
text = re.sub( '(.*)\t\d\d*.*', '\g<1>', text)
text = RemoveRows( text, 5 )
text = RemoveOneCharConv( text )
s_wordlist.extend( text.split() )
# tsi.src Trad
src = 'libtabe/tsi-src/tsi.src'
dst = 'tsi.src'
GetFileFromTar( lbt_dest, src, dst )
text = ReadBIG5File( 'tsi.src' )
text = re.sub( ' \d.*', '', text.replace('# ', ''))
text = RemoveOneCharConv( text )
t_wordlist.extend( text.split() )
# remove duplicate elements
t_wordlist = list( set( t_wordlist ) )
s_wordlist = list( set( s_wordlist ) )
# simpphrases_exclude.manual Simp
text = ReadFile( 'simpphrases_exclude.manual' )
temp = text.split()
s_string = '\n'.join( s_wordlist )
for elem in temp:
s_string = re.sub( '.*%s.*\n' % elem, '', s_string )
s_wordlist = s_string.split('\n')
# tradphrases_exclude.manual Trad
text = ReadFile( 'tradphrases_exclude.manual' )
temp = text.split()
t_string = '\n'.join( t_wordlist )
for elem in temp:
t_string = re.sub( '.*%s.*\n' % elem, '', t_string )
t_wordlist = t_string.split('\n')
# Make char to char convertion table
# Unihan.txt, dict t2s_code, s2t_code = { 'U+XXXX': 'U+YYYY( U+ZZZZ) ... ', ... }
( t2s_code, s2t_code ) = ReadUnihanFile( 'Unihan_Variants.txt' )
# dict t2s_1tomany = { '\uXXXX': '\uYYYY\uZZZZ ... ', ... }
t2s_1tomany = {}
t2s_1tomany.update( GetDefaultTable( t2s_code ) )
t2s_1tomany.update( GetManualTable( 'trad2simp.manual' ) )
# dict s2t_1tomany
s2t_1tomany = {}
s2t_1tomany.update( GetDefaultTable( s2t_code ) )
s2t_1tomany.update( GetManualTable( 'simp2trad.manual' ) )
# dict t2s_1to1 = { '\uXXXX': '\uYYYY', ... }; t2s_trans = { 'ddddd': '', ... }
t2s_1to1 = GetValidTable( t2s_1tomany )
s_tomany = GetToManyRules( t2s_1tomany )
# dict s2t_1to1; s2t_trans
s2t_1to1 = GetValidTable( s2t_1tomany )
t_tomany = GetToManyRules( s2t_1tomany )
# remove noconvert rules
t2s_1to1 = RemoveRules( 'trad2simp_noconvert.manual', t2s_1to1 )
s2t_1to1 = RemoveRules( 'simp2trad_noconvert.manual', s2t_1to1 )
# Make word to word convertion table
t2s_1to1_supp = t2s_1to1.copy()
s2t_1to1_supp = s2t_1to1.copy()
# trad2simp_supp_set.manual
t2s_1to1_supp.update( CustomRules( 'trad2simp_supp_set.manual' ) )
# simp2trad_supp_set.manual
s2t_1to1_supp.update( CustomRules( 'simp2trad_supp_set.manual' ) )
# simpphrases.manual
text = ReadFile( 'simpphrases.manual' )
s_wordlist_manual = text.split('\n')
t2s_word2word_manual = GetManualWordsTable(s_wordlist_manual, s2t_1to1_supp)
t2s_word2word_manual.update( CustomRules( 'toSimp.manual' ) )
# tradphrases.manual
text = ReadFile( 'tradphrases.manual' )
t_wordlist_manual = text.split('\n')
s2t_word2word_manual = GetManualWordsTable(t_wordlist_manual, t2s_1to1_supp)
s2t_word2word_manual.update( CustomRules( 'toTrad.manual' ) )
# t2s_word2word
s2t_supp = s2t_1to1_supp.copy()
s2t_supp.update( s2t_word2word_manual )
t2s_supp = t2s_1to1_supp.copy()
t2s_supp.update( t2s_word2word_manual )
t2s_word2word = GetDefaultWordsTable( s_wordlist, s_tomany, s2t_1to1_supp, t2s_supp )
## toSimp.manual
t2s_word2word.update( t2s_word2word_manual )
# s2t_word2word
s2t_word2word = GetDefaultWordsTable( t_wordlist, t_tomany, t2s_1to1_supp, s2t_supp )
## toTrad.manual
s2t_word2word.update( s2t_word2word_manual )
# Final tables
# sorted list toHans
t2s_1to1 = RemoveSameChar( t2s_1to1 )
s2t_1to1 = RemoveSameChar( s2t_1to1 )
toHans = DictToSortedList1( t2s_1to1 ) + DictToSortedList2( t2s_word2word )
# sorted list toHant
toHant = DictToSortedList1( s2t_1to1 ) + DictToSortedList2( s2t_word2word )
# sorted list toCN
toCN = DictToSortedList2( CustomRules( 'toCN.manual' ) )
# sorted list toHK
toHK = DictToSortedList2( CustomRules( 'toHK.manual' ) )
# sorted list toSG
toSG = DictToSortedList2( CustomRules( 'toSG.manual' ) )
# sorted list toTW
toTW = DictToSortedList2( CustomRules( 'toTW.manual' ) )
# Get PHP Array
php = '''<?php
/**
* Simplified / Traditional Chinese conversion tables
*
* Automatically generated using code and data in includes/zhtable/
* Do not modify directly!
*/
$zh2Hant = array(\n'''
php += GetPHPArray( toHant )
php += '\n);\n\n$zh2Hans = array(\n'
php += GetPHPArray( toHans )
php += '\n);\n\n$zh2TW = array(\n'
php += GetPHPArray( toTW )
php += '\n);\n\n$zh2HK = array(\n'
php += GetPHPArray( toHK )
php += '\n);\n\n$zh2CN = array(\n'
php += GetPHPArray( toCN )
php += '\n);\n\n$zh2SG = array(\n'
php += GetPHPArray( toSG )
php += '\n);'
f = uniopen( 'ZhConversion.php', 'w', encoding = 'utf8' )
print ('Writing ZhConversion.php ... ')
f.write( php )
f.close()
#Remove temp files
print ('Deleting temp files ... ')
os.remove('EZ.txt.in')
os.remove('phrase_lib.txt')
os.remove('tsi.src')
os.remove('Unihan_Variants.txt')
os.remove('Wubi.txt.in')
os.remove('Ziranma.txt.in')
if __name__ == '__main__':
main()
|