language_detector 0.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/README.rdoc +24 -0
- data/Rakefile +18 -0
- data/VERSION +1 -0
- data/lib/language_detector.rb +232 -0
- data/lib/model-fm.yml +52504 -0
- data/lib/model-tc.yml +53985 -0
- data/lib/textcat_ngrams/afrikaans.lm +400 -0
- data/lib/textcat_ngrams/albanian.lm +400 -0
- data/lib/textcat_ngrams/amharic-utf.lm +400 -0
- data/lib/textcat_ngrams/arabic-iso8859_6.lm +400 -0
- data/lib/textcat_ngrams/arabic-windows1256.lm +400 -0
- data/lib/textcat_ngrams/armenian.lm +400 -0
- data/lib/textcat_ngrams/basque.lm +400 -0
- data/lib/textcat_ngrams/belarus-windows1251.lm +400 -0
- data/lib/textcat_ngrams/bosnian.lm +400 -0
- data/lib/textcat_ngrams/breton.lm +400 -0
- data/lib/textcat_ngrams/bulgarian-iso8859_5.lm +400 -0
- data/lib/textcat_ngrams/catalan.lm +400 -0
- data/lib/textcat_ngrams/chinese-big5.lm +400 -0
- data/lib/textcat_ngrams/chinese-gb2312.lm +400 -0
- data/lib/textcat_ngrams/croatian-ascii.lm +400 -0
- data/lib/textcat_ngrams/czech-iso8859_2.lm +400 -0
- data/lib/textcat_ngrams/danish.lm +400 -0
- data/lib/textcat_ngrams/dutch.lm +400 -0
- data/lib/textcat_ngrams/english.lm +400 -0
- data/lib/textcat_ngrams/esperanto.lm +400 -0
- data/lib/textcat_ngrams/estonian.lm +400 -0
- data/lib/textcat_ngrams/finnish.lm +400 -0
- data/lib/textcat_ngrams/french.lm +400 -0
- data/lib/textcat_ngrams/frisian.lm +400 -0
- data/lib/textcat_ngrams/georgian.lm +400 -0
- data/lib/textcat_ngrams/german.lm +400 -0
- data/lib/textcat_ngrams/greek-iso8859-7.lm +400 -0
- data/lib/textcat_ngrams/hebrew-iso8859_8.lm +400 -0
- data/lib/textcat_ngrams/hindi.lm +400 -0
- data/lib/textcat_ngrams/hungarian.lm +400 -0
- data/lib/textcat_ngrams/icelandic.lm +400 -0
- data/lib/textcat_ngrams/indonesian.lm +400 -0
- data/lib/textcat_ngrams/irish.lm +400 -0
- data/lib/textcat_ngrams/italian.lm +400 -0
- data/lib/textcat_ngrams/japanese-euc_jp.lm +400 -0
- data/lib/textcat_ngrams/japanese-shift_jis.lm +400 -0
- data/lib/textcat_ngrams/korean.lm +400 -0
- data/lib/textcat_ngrams/latin.lm +400 -0
- data/lib/textcat_ngrams/latvian.lm +400 -0
- data/lib/textcat_ngrams/lithuanian.lm +400 -0
- data/lib/textcat_ngrams/malay.lm +400 -0
- data/lib/textcat_ngrams/manx.lm +400 -0
- data/lib/textcat_ngrams/marathi.lm +400 -0
- data/lib/textcat_ngrams/mingo.lm +400 -0
- data/lib/textcat_ngrams/nepali.lm +400 -0
- data/lib/textcat_ngrams/norwegian.lm +400 -0
- data/lib/textcat_ngrams/persian.lm +400 -0
- data/lib/textcat_ngrams/polish.lm +400 -0
- data/lib/textcat_ngrams/portuguese.lm +400 -0
- data/lib/textcat_ngrams/quechua.lm +400 -0
- data/lib/textcat_ngrams/romanian.lm +400 -0
- data/lib/textcat_ngrams/rumantsch.lm +400 -0
- data/lib/textcat_ngrams/russian-iso8859_5.lm +400 -0
- data/lib/textcat_ngrams/russian-koi8_r.lm +400 -0
- data/lib/textcat_ngrams/russian-windows1251.lm +400 -0
- data/lib/textcat_ngrams/sanskrit.lm +400 -0
- data/lib/textcat_ngrams/scots.lm +400 -0
- data/lib/textcat_ngrams/scots_gaelic.lm +400 -0
- data/lib/textcat_ngrams/serbian-ascii.lm +400 -0
- data/lib/textcat_ngrams/slovak-ascii.lm +400 -0
- data/lib/textcat_ngrams/slovak-windows1250.lm +400 -0
- data/lib/textcat_ngrams/slovenian-ascii.lm +400 -0
- data/lib/textcat_ngrams/slovenian-iso8859_2.lm +400 -0
- data/lib/textcat_ngrams/spanish.lm +400 -0
- data/lib/textcat_ngrams/swahili.lm +400 -0
- data/lib/textcat_ngrams/swedish.lm +400 -0
- data/lib/textcat_ngrams/tagalog.lm +400 -0
- data/lib/textcat_ngrams/tamil.lm +400 -0
- data/lib/textcat_ngrams/thai.lm +400 -0
- data/lib/textcat_ngrams/turkish.lm +400 -0
- data/lib/textcat_ngrams/ukrainian-koi8_u.lm +400 -0
- data/lib/textcat_ngrams/vietnamese.lm +400 -0
- data/lib/textcat_ngrams/welsh.lm +400 -0
- data/lib/textcat_ngrams/yiddish-utf.lm +400 -0
- data/lib/training_data/ar-utf8.txt +54 -0
- data/lib/training_data/bg-utf8.txt +26 -0
- data/lib/training_data/cs-utf8.txt +48 -0
- data/lib/training_data/da-utf8.txt +159 -0
- data/lib/training_data/de-utf8.txt +569 -0
- data/lib/training_data/el-utf8.txt +48 -0
- data/lib/training_data/en-utf8.txt +81 -0
- data/lib/training_data/es-utf8.txt +185 -0
- data/lib/training_data/et-utf8.txt +50 -0
- data/lib/training_data/fa-utf8.txt +42 -0
- data/lib/training_data/fi-utf8.txt +83 -0
- data/lib/training_data/fr-utf8.txt +191 -0
- data/lib/training_data/fy-utf8.txt +22 -0
- data/lib/training_data/ga-utf8.txt +109 -0
- data/lib/training_data/he-utf8.txt +116 -0
- data/lib/training_data/hi-utf8.txt +49 -0
- data/lib/training_data/hr-utf8.txt +80 -0
- data/lib/training_data/hu-utf8.txt +87 -0
- data/lib/training_data/io-utf8.txt +41 -0
- data/lib/training_data/is-utf8.txt +94 -0
- data/lib/training_data/it-utf8.txt +228 -0
- data/lib/training_data/ja-utf8.txt +200 -0
- data/lib/training_data/ko-utf8.txt +147 -0
- data/lib/training_data/nl-utf8.txt +215 -0
- data/lib/training_data/no-utf8.txt +281 -0
- data/lib/training_data/pl-utf8.txt +120 -0
- data/lib/training_data/pt-utf8.txt +214 -0
- data/lib/training_data/ro-utf8.txt +66 -0
- data/lib/training_data/ru-utf8.txt +310 -0
- data/lib/training_data/sl-utf8.txt +263 -0
- data/lib/training_data/sv-utf8.txt +174 -0
- data/lib/training_data/th-utf8.txt +49 -0
- data/lib/training_data/tk-utf8.txt +101 -0
- data/lib/training_data/todo/af.txt +114 -0
- data/lib/training_data/todo/amharic-utf.txt +95 -0
- data/lib/training_data/todo/arabic-windows1256.txt +157 -0
- data/lib/training_data/todo/armenian.txt +86 -0
- data/lib/training_data/todo/basque.txt +136 -0
- data/lib/training_data/todo/belarus-windows1251.txt +97 -0
- data/lib/training_data/todo/bosnian.txt +97 -0
- data/lib/training_data/todo/breton.txt +159 -0
- data/lib/training_data/todo/bulgarian-iso8859_5.txt +115 -0
- data/lib/training_data/todo/catalan.txt +93 -0
- data/lib/training_data/todo/croatian-ascii.txt +104 -0
- data/lib/training_data/todo/esperanto.txt +95 -0
- data/lib/training_data/todo/estonian.txt +218 -0
- data/lib/training_data/todo/frisian.txt +99 -0
- data/lib/training_data/todo/georgian.txt +86 -0
- data/lib/training_data/todo/greek-iso8859-7.txt +139 -0
- data/lib/training_data/todo/hawaian.txt +108 -0
- data/lib/training_data/todo/hebrew-iso8859_8.txt +79 -0
- data/lib/training_data/todo/hindi.txt +77 -0
- data/lib/training_data/todo/hungarian.txt +102 -0
- data/lib/training_data/todo/icelandic.txt +131 -0
- data/lib/training_data/todo/indonesian.txt +93 -0
- data/lib/training_data/todo/irish.txt +209 -0
- data/lib/training_data/todo/latin.txt +120 -0
- data/lib/training_data/todo/latvian.txt +126 -0
- data/lib/training_data/todo/lithuanian.txt +99 -0
- data/lib/training_data/todo/malay.txt +108 -0
- data/lib/training_data/todo/manx.txt +78 -0
- data/lib/training_data/todo/marathi.txt +100 -0
- data/lib/training_data/todo/mf.txt +100 -0
- data/lib/training_data/todo/middle_frisian.txt +102 -0
- data/lib/training_data/todo/mingo.txt +146 -0
- data/lib/training_data/todo/nepali.txt +131 -0
- data/lib/training_data/todo/persian.txt +73 -0
- data/lib/training_data/todo/quechua.txt +108 -0
- data/lib/training_data/todo/romanian.txt +103 -0
- data/lib/training_data/todo/rumantsch.txt +110 -0
- data/lib/training_data/todo/sanskrit.txt +135 -0
- data/lib/training_data/todo/scots.txt +490 -0
- data/lib/training_data/todo/scots_gaelic.txt +93 -0
- data/lib/training_data/todo/serbian-ascii.txt +121 -0
- data/lib/training_data/todo/slovak-ascii.txt +102 -0
- data/lib/training_data/todo/slovak-windows1250.txt +115 -0
- data/lib/training_data/todo/slovenian-ascii.txt +100 -0
- data/lib/training_data/todo/slovenian-iso8859_2.txt +96 -0
- data/lib/training_data/todo/sq.txt +110 -0
- data/lib/training_data/todo/swahili.txt +120 -0
- data/lib/training_data/todo/tagalog.txt +135 -0
- data/lib/training_data/todo/tamil.txt +123 -0
- data/lib/training_data/todo/turkish.txt +117 -0
- data/lib/training_data/todo/ukrainian-koi8_r.txt +214 -0
- data/lib/training_data/todo/vietnamese.txt +92 -0
- data/lib/training_data/todo/welsh.txt +148 -0
- data/lib/training_data/todo/yiddish-utf.txt +83 -0
- data/lib/training_data/uk-utf8.txt +75 -0
- data/lib/training_data/vi-utf8.txt +47 -0
- data/lib/training_data/zh-utf8.txt +228 -0
- data/test/language_detector_test.rb +78 -0
- metadata +232 -0
|
@@ -0,0 +1,400 @@
|
|
|
1
|
+
� 78988
|
|
2
|
+
� 57258
|
|
3
|
+
_ 34456
|
|
4
|
+
� 22280
|
|
5
|
+
� 18223
|
|
6
|
+
� 11290
|
|
7
|
+
� 11237
|
|
8
|
+
� 10621
|
|
9
|
+
� 9502
|
|
10
|
+
� 8859
|
|
11
|
+
� 8812
|
|
12
|
+
�� 8266
|
|
13
|
+
� 8180
|
|
14
|
+
� 7520
|
|
15
|
+
� 7325
|
|
16
|
+
� 6982
|
|
17
|
+
� 6930
|
|
18
|
+
� 6929
|
|
19
|
+
� 6896
|
|
20
|
+
� 6865
|
|
21
|
+
�� 6858
|
|
22
|
+
� 6261
|
|
23
|
+
�� 6067
|
|
24
|
+
�� 5926
|
|
25
|
+
��� 5888
|
|
26
|
+
� 5878
|
|
27
|
+
� 5806
|
|
28
|
+
� 5562
|
|
29
|
+
� 5426
|
|
30
|
+
� 5314
|
|
31
|
+
�� 5228
|
|
32
|
+
� 5011
|
|
33
|
+
� 4836
|
|
34
|
+
�� 4775
|
|
35
|
+
� 4385
|
|
36
|
+
�_ 4323
|
|
37
|
+
�� 4310
|
|
38
|
+
�� 4305
|
|
39
|
+
��_ 4294
|
|
40
|
+
� 4253
|
|
41
|
+
�� 4090
|
|
42
|
+
�� 4075
|
|
43
|
+
� 4032
|
|
44
|
+
� 4029
|
|
45
|
+
� 3975
|
|
46
|
+
� 3947
|
|
47
|
+
� 3923
|
|
48
|
+
� 3853
|
|
49
|
+
� 3845
|
|
50
|
+
� 3759
|
|
51
|
+
� 3583
|
|
52
|
+
�� 3485
|
|
53
|
+
�� 3475
|
|
54
|
+
� 3367
|
|
55
|
+
� 3366
|
|
56
|
+
� 3366
|
|
57
|
+
�� 3314
|
|
58
|
+
� 3313
|
|
59
|
+
� 3282
|
|
60
|
+
� 3273
|
|
61
|
+
�� 3255
|
|
62
|
+
� 3207
|
|
63
|
+
å 3188
|
|
64
|
+
�� 3182
|
|
65
|
+
�� 3175
|
|
66
|
+
�å 3170
|
|
67
|
+
�� 3131
|
|
68
|
+
� 3058
|
|
69
|
+
�� 3035
|
|
70
|
+
�� 3024
|
|
71
|
+
��� 3000
|
|
72
|
+
롣 2952
|
|
73
|
+
롣_ 2948
|
|
74
|
+
�롣 2947
|
|
75
|
+
�롣_ 2943
|
|
76
|
+
� 2905
|
|
77
|
+
� 2893
|
|
78
|
+
�� 2865
|
|
79
|
+
�� 2848
|
|
80
|
+
� 2819
|
|
81
|
+
Ȥ 2791
|
|
82
|
+
�� 2776
|
|
83
|
+
��� 2749
|
|
84
|
+
���� 2730
|
|
85
|
+
���� 2729
|
|
86
|
+
����� 2729
|
|
87
|
+
� 2697
|
|
88
|
+
� 2689
|
|
89
|
+
� 2545
|
|
90
|
+
�� 2543
|
|
91
|
+
�� 2525
|
|
92
|
+
��� 2473
|
|
93
|
+
����� 2459
|
|
94
|
+
�� 2399
|
|
95
|
+
. 2395
|
|
96
|
+
� 2381
|
|
97
|
+
, 2380
|
|
98
|
+
�� 2357
|
|
99
|
+
�� 2346
|
|
100
|
+
� 2340
|
|
101
|
+
� 2328
|
|
102
|
+
�� 2326
|
|
103
|
+
�� 2316
|
|
104
|
+
� 2314
|
|
105
|
+
� 2293
|
|
106
|
+
���� 2283
|
|
107
|
+
��� 2283
|
|
108
|
+
�� 2253
|
|
109
|
+
._ 2251
|
|
110
|
+
�� 2227
|
|
111
|
+
��� 2222
|
|
112
|
+
�� 2200
|
|
113
|
+
_� 2189
|
|
114
|
+
Ǥ 2172
|
|
115
|
+
�� 2145
|
|
116
|
+
ӥ 2137
|
|
117
|
+
�� 2112
|
|
118
|
+
���� 2110
|
|
119
|
+
��� 2110
|
|
120
|
+
� 2100
|
|
121
|
+
�� 2061
|
|
122
|
+
�� 2027
|
|
123
|
+
� 2017
|
|
124
|
+
�� 2011
|
|
125
|
+
�� 2007
|
|
126
|
+
�ӥ 2002
|
|
127
|
+
ˤ 1995
|
|
128
|
+
��� 1983
|
|
129
|
+
���� 1983
|
|
130
|
+
� 1947
|
|
131
|
+
� 1913
|
|
132
|
+
� 1861
|
|
133
|
+
�� 1847
|
|
134
|
+
�� 1834
|
|
135
|
+
�� 1834
|
|
136
|
+
�� 1826
|
|
137
|
+
� 1795
|
|
138
|
+
��� 1791
|
|
139
|
+
� 1782
|
|
140
|
+
� 1782
|
|
141
|
+
�ˤ 1763
|
|
142
|
+
�Ȥ 1760
|
|
143
|
+
�� 1716
|
|
144
|
+
�� 1713
|
|
145
|
+
� 1709
|
|
146
|
+
� 1696
|
|
147
|
+
ʤ 1691
|
|
148
|
+
�� 1688
|
|
149
|
+
_� 1686
|
|
150
|
+
�� 1679
|
|
151
|
+
��� 1669
|
|
152
|
+
�� 1668
|
|
153
|
+
� 1666
|
|
154
|
+
�� 1659
|
|
155
|
+
�Ǥ 1655
|
|
156
|
+
�� 1638
|
|
157
|
+
� 1637
|
|
158
|
+
�� 1612
|
|
159
|
+
��� 1598
|
|
160
|
+
��� 1584
|
|
161
|
+
���� 1584
|
|
162
|
+
�ʤ 1570
|
|
163
|
+
�� 1568
|
|
164
|
+
�� 1565
|
|
165
|
+
�� 1562
|
|
166
|
+
�� 1554
|
|
167
|
+
� 1544
|
|
168
|
+
Ƥ 1541
|
|
169
|
+
ƥ 1538
|
|
170
|
+
�� 1526
|
|
171
|
+
�� 1525
|
|
172
|
+
�� 1523
|
|
173
|
+
��� 1523
|
|
174
|
+
� 1517
|
|
175
|
+
�� 1510
|
|
176
|
+
��� 1509
|
|
177
|
+
- 1490
|
|
178
|
+
�� 1476
|
|
179
|
+
�� 1465
|
|
180
|
+
�� 1465
|
|
181
|
+
� 1464
|
|
182
|
+
��� 1454
|
|
183
|
+
�� 1454
|
|
184
|
+
��å 1453
|
|
185
|
+
�� 1453
|
|
186
|
+
����� 1453
|
|
187
|
+
�å� 1453
|
|
188
|
+
� 1453
|
|
189
|
+
���� 1453
|
|
190
|
+
�å� 1453
|
|
191
|
+
���� 1453
|
|
192
|
+
��� 1453
|
|
193
|
+
�å 1453
|
|
194
|
+
å� 1453
|
|
195
|
+
�� 1453
|
|
196
|
+
��� 1453
|
|
197
|
+
����� 1452
|
|
198
|
+
� 1450
|
|
199
|
+
� 1445
|
|
200
|
+
� 1441
|
|
201
|
+
�� 1420
|
|
202
|
+
� 1419
|
|
203
|
+
� 1418
|
|
204
|
+
��� 1415
|
|
205
|
+
���� 1413
|
|
206
|
+
���� 1413
|
|
207
|
+
����� 1413
|
|
208
|
+
��� 1413
|
|
209
|
+
�� 1413
|
|
210
|
+
�� 1411
|
|
211
|
+
ӥ� 1406
|
|
212
|
+
��ӥ 1406
|
|
213
|
+
���ӥ 1406
|
|
214
|
+
�ӥ� 1406
|
|
215
|
+
���� 1406
|
|
216
|
+
��� 1406
|
|
217
|
+
�� 1403
|
|
218
|
+
����� 1403
|
|
219
|
+
��ӥ� 1403
|
|
220
|
+
�ƥ 1396
|
|
221
|
+
��� 1392
|
|
222
|
+
��� 1383
|
|
223
|
+
� 1378
|
|
224
|
+
�� 1372
|
|
225
|
+
_� 1368
|
|
226
|
+
Υ 1358
|
|
227
|
+
T 1354
|
|
228
|
+
ϡ 1341
|
|
229
|
+
�� 1338
|
|
230
|
+
�� 1337
|
|
231
|
+
�� 1325
|
|
232
|
+
� 1323
|
|
233
|
+
Τ 1314
|
|
234
|
+
�Υ 1312
|
|
235
|
+
��� 1311
|
|
236
|
+
���� 1311
|
|
237
|
+
Ԥ 1308
|
|
238
|
+
) 1302
|
|
239
|
+
_. 1297
|
|
240
|
+
� 1294
|
|
241
|
+
�� 1294
|
|
242
|
+
��� 1292
|
|
243
|
+
�� 1289
|
|
244
|
+
��� 1284
|
|
245
|
+
�Ƥ 1284
|
|
246
|
+
�� 1273
|
|
247
|
+
�� 1260
|
|
248
|
+
_._ 1244
|
|
249
|
+
� 1244
|
|
250
|
+
� 1238
|
|
251
|
+
��� 1211
|
|
252
|
+
�� 1190
|
|
253
|
+
� 1182
|
|
254
|
+
_� 1182
|
|
255
|
+
��� 1152
|
|
256
|
+
ȥ 1151
|
|
257
|
+
�� 1145
|
|
258
|
+
���� 1130
|
|
259
|
+
ǽ 1129
|
|
260
|
+
ե 1126
|
|
261
|
+
� 1120
|
|
262
|
+
�ե 1113
|
|
263
|
+
�ϡ 1105
|
|
264
|
+
�� 1103
|
|
265
|
+
� 1101
|
|
266
|
+
� 1084
|
|
267
|
+
�� 1080
|
|
268
|
+
�� 1062
|
|
269
|
+
� 1060
|
|
270
|
+
�� 1051
|
|
271
|
+
�� 1050
|
|
272
|
+
��� 1043
|
|
273
|
+
�� 1033
|
|
274
|
+
�� 1033
|
|
275
|
+
��� 1033
|
|
276
|
+
��� 1032
|
|
277
|
+
���� 1032
|
|
278
|
+
ϡ� 1030
|
|
279
|
+
�ϡ� 1030
|
|
280
|
+
Ǥ� 1022
|
|
281
|
+
�Ǥ� 1021
|
|
282
|
+
Ǥ�� 1021
|
|
283
|
+
�Ǥ�� 1020
|
|
284
|
+
ǥ 1012
|
|
285
|
+
� 1006
|
|
286
|
+
�� 997
|
|
287
|
+
�� 995
|
|
288
|
+
�� 991
|
|
289
|
+
ͣ 988
|
|
290
|
+
��� 985
|
|
291
|
+
�� 984
|
|
292
|
+
�ͣ 983
|
|
293
|
+
�� 981
|
|
294
|
+
�� 976
|
|
295
|
+
��� 974
|
|
296
|
+
�Τ 971
|
|
297
|
+
��� 971
|
|
298
|
+
�� 962
|
|
299
|
+
��� 955
|
|
300
|
+
� 955
|
|
301
|
+
� 954
|
|
302
|
+
�ȥ 953
|
|
303
|
+
�ǥ 951
|
|
304
|
+
�� 942
|
|
305
|
+
�� 929
|
|
306
|
+
�� 920
|
|
307
|
+
� 918
|
|
308
|
+
� 909
|
|
309
|
+
�� 904
|
|
310
|
+
� 904
|
|
311
|
+
�Ԥ 903
|
|
312
|
+
���� 900
|
|
313
|
+
��� 900
|
|
314
|
+
�_ 894
|
|
315
|
+
�� 893
|
|
316
|
+
-_ 892
|
|
317
|
+
�, 887
|
|
318
|
+
�Ȥ 886
|
|
319
|
+
��, 886
|
|
320
|
+
��_ 884
|
|
321
|
+
�� 881
|
|
322
|
+
�� 881
|
|
323
|
+
( 878
|
|
324
|
+
C 877
|
|
325
|
+
Ǥ��� 877
|
|
326
|
+
I 877
|
|
327
|
+
�� 875
|
|
328
|
+
��롣 875
|
|
329
|
+
i 872
|
|
330
|
+
�� 865
|
|
331
|
+
�� 860
|
|
332
|
+
֤ 857
|
|
333
|
+
� 856
|
|
334
|
+
�� 855
|
|
335
|
+
�� 855
|
|
336
|
+
�� 846
|
|
337
|
+
�� 841
|
|
338
|
+
ޤ 834
|
|
339
|
+
��� 834
|
|
340
|
+
e 825
|
|
341
|
+
��� 825
|
|
342
|
+
�� 819
|
|
343
|
+
���� 818
|
|
344
|
+
��� 818
|
|
345
|
+
�� 808
|
|
346
|
+
�� 802
|
|
347
|
+
�ǥ� 796
|
|
348
|
+
ǥ� 796
|
|
349
|
+
_� 792
|
|
350
|
+
a 776
|
|
351
|
+
�å� 771
|
|
352
|
+
å� 771
|
|
353
|
+
���� 770
|
|
354
|
+
��� 770
|
|
355
|
+
�� 767
|
|
356
|
+
Ѥ 748
|
|
357
|
+
��� 743
|
|
358
|
+
�� 743
|
|
359
|
+
�ǥ�� 741
|
|
360
|
+
ǥ�� 741
|
|
361
|
+
�_ 738
|
|
362
|
+
��� 732
|
|
363
|
+
N 729
|
|
364
|
+
�� 728
|
|
365
|
+
�� 728
|
|
366
|
+
�� 727
|
|
367
|
+
�� 724
|
|
368
|
+
�롣 722
|
|
369
|
+
��� 718
|
|
370
|
+
ˤ� 716
|
|
371
|
+
ˤ� 716
|
|
372
|
+
�ˤ� 715
|
|
373
|
+
����� 715
|
|
374
|
+
���� 715
|
|
375
|
+
�ˤ� 715
|
|
376
|
+
ץ 715
|
|
377
|
+
�ץ 711
|
|
378
|
+
����� 710
|
|
379
|
+
���� 710
|
|
380
|
+
����� 710
|
|
381
|
+
Ĥ 705
|
|
382
|
+
� 702
|
|
383
|
+
� 701
|
|
384
|
+
_�� 699
|
|
385
|
+
��� 696
|
|
386
|
+
��_ 694
|
|
387
|
+
�� 694
|
|
388
|
+
��� 692
|
|
389
|
+
���� 692
|
|
390
|
+
���� 692
|
|
391
|
+
��� 686
|
|
392
|
+
�Ѥ 685
|
|
393
|
+
�ʤ� 685
|
|
394
|
+
ʤ� 685
|
|
395
|
+
�� 684
|
|
396
|
+
Ƥ� 684
|
|
397
|
+
n 682
|
|
398
|
+
� 682
|
|
399
|
+
�� 681
|
|
400
|
+
�� 681
|
|
@@ -0,0 +1,400 @@
|
|
|
1
|
+
� 9970
|
|
2
|
+
� 2204
|
|
3
|
+
_ 1555
|
|
4
|
+
� 1214
|
|
5
|
+
� 891
|
|
6
|
+
A 885
|
|
7
|
+
� 846
|
|
8
|
+
� 836
|
|
9
|
+
�A 831
|
|
10
|
+
� 818
|
|
11
|
+
� 815
|
|
12
|
+
�� 790
|
|
13
|
+
� 739
|
|
14
|
+
� 729
|
|
15
|
+
� 618
|
|
16
|
+
� 607
|
|
17
|
+
� 589
|
|
18
|
+
� 568
|
|
19
|
+
� 566
|
|
20
|
+
� 555
|
|
21
|
+
� 552
|
|
22
|
+
� 528
|
|
23
|
+
�� 527
|
|
24
|
+
�� 500
|
|
25
|
+
� 489
|
|
26
|
+
� 481
|
|
27
|
+
� 461
|
|
28
|
+
� 460
|
|
29
|
+
� 453
|
|
30
|
+
� 449
|
|
31
|
+
�� 449
|
|
32
|
+
� 445
|
|
33
|
+
� 440
|
|
34
|
+
B 419
|
|
35
|
+
� 411
|
|
36
|
+
�B 405
|
|
37
|
+
� 404
|
|
38
|
+
�� 404
|
|
39
|
+
�� 401
|
|
40
|
+
� 396
|
|
41
|
+
� 389
|
|
42
|
+
�� 387
|
|
43
|
+
� 368
|
|
44
|
+
� 366
|
|
45
|
+
�� 363
|
|
46
|
+
�� 361
|
|
47
|
+
��� 357
|
|
48
|
+
�� 352
|
|
49
|
+
�� 352
|
|
50
|
+
�� 349
|
|
51
|
+
�� 345
|
|
52
|
+
� 330
|
|
53
|
+
�� 321
|
|
54
|
+
� 320
|
|
55
|
+
�� 320
|
|
56
|
+
��� 306
|
|
57
|
+
�� 305
|
|
58
|
+
� 292
|
|
59
|
+
� 284
|
|
60
|
+
@ 282
|
|
61
|
+
_� 281
|
|
62
|
+
܂ 275
|
|
63
|
+
�� 268
|
|
64
|
+
v 263
|
|
65
|
+
�܂ 258
|
|
66
|
+
Ȃ 256
|
|
67
|
+
� 251
|
|
68
|
+
�Ȃ 240
|
|
69
|
+
�� 239
|
|
70
|
+
� 238
|
|
71
|
+
Ă 234
|
|
72
|
+
� 232
|
|
73
|
+
Ƃ 231
|
|
74
|
+
ł 226
|
|
75
|
+
�@ 220
|
|
76
|
+
�� 217
|
|
77
|
+
�Ƃ 214
|
|
78
|
+
�ł 211
|
|
79
|
+
_� 210
|
|
80
|
+
�à 205
|
|
81
|
+
�� 204
|
|
82
|
+
�� 203
|
|
83
|
+
��� 199
|
|
84
|
+
� 198
|
|
85
|
+
̂ 195
|
|
86
|
+
� 194
|
|
87
|
+
� 194
|
|
88
|
+
��� 182
|
|
89
|
+
� 182
|
|
90
|
+
� 181
|
|
91
|
+
� 180
|
|
92
|
+
ɂ 180
|
|
93
|
+
A� 176
|
|
94
|
+
� 176
|
|
95
|
+
� 173
|
|
96
|
+
�ɂ 172
|
|
97
|
+
�̂ 172
|
|
98
|
+
v� 169
|
|
99
|
+
� 169
|
|
100
|
+
�� 167
|
|
101
|
+
� 167
|
|
102
|
+
�B_ 166
|
|
103
|
+
N 166
|
|
104
|
+
B_ 166
|
|
105
|
+
O 165
|
|
106
|
+
� 165
|
|
107
|
+
�A� 165
|
|
108
|
+
�� 164
|
|
109
|
+
P 163
|
|
110
|
+
� 163
|
|
111
|
+
�� 159
|
|
112
|
+
� 159
|
|
113
|
+
_�@ 157
|
|
114
|
+
�� 156
|
|
115
|
+
��� 155
|
|
116
|
+
[ 153
|
|
117
|
+
�� 153
|
|
118
|
+
X 153
|
|
119
|
+
� 148
|
|
120
|
+
i 148
|
|
121
|
+
�� 148
|
|
122
|
+
�� 147
|
|
123
|
+
��B 146
|
|
124
|
+
�� 146
|
|
125
|
+
���B 145
|
|
126
|
+
j 142
|
|
127
|
+
��� 142
|
|
128
|
+
�P 141
|
|
129
|
+
��� 141
|
|
130
|
+
���� 141
|
|
131
|
+
͂ 141
|
|
132
|
+
�� 141
|
|
133
|
+
��� 137
|
|
134
|
+
V 137
|
|
135
|
+
�� 135
|
|
136
|
+
�� 135
|
|
137
|
+
� 134
|
|
138
|
+
u 133
|
|
139
|
+
�[ 132
|
|
140
|
+
�� 131
|
|
141
|
+
l 129
|
|
142
|
+
� 129
|
|
143
|
+
s 128
|
|
144
|
+
� 128
|
|
145
|
+
� 125
|
|
146
|
+
�� 125
|
|
147
|
+
S 125
|
|
148
|
+
g 124
|
|
149
|
+
�� 123
|
|
150
|
+
�� 123
|
|
151
|
+
� 123
|
|
152
|
+
��� 122
|
|
153
|
+
�� 122
|
|
154
|
+
� 120
|
|
155
|
+
�� 120
|
|
156
|
+
�� 120
|
|
157
|
+
� 120
|
|
158
|
+
\ 119
|
|
159
|
+
́ 119
|
|
160
|
+
�u 119
|
|
161
|
+
�v 119
|
|
162
|
+
�� 119
|
|
163
|
+
߂ 118
|
|
164
|
+
W 118
|
|
165
|
+
�́ 117
|
|
166
|
+
�܂� 117
|
|
167
|
+
R 117
|
|
168
|
+
��� 117
|
|
169
|
+
܂� 117
|
|
170
|
+
� 114
|
|
171
|
+
� 114
|
|
172
|
+
� 113
|
|
173
|
+
� 113
|
|
174
|
+
{ 113
|
|
175
|
+
�N 112
|
|
176
|
+
�� 111
|
|
177
|
+
� 111
|
|
178
|
+
��� 111
|
|
179
|
+
o 108
|
|
180
|
+
�܂�� 107
|
|
181
|
+
܂�� 107
|
|
182
|
+
Q 106
|
|
183
|
+
� 106
|
|
184
|
+
�� 105
|
|
185
|
+
܂��B 104
|
|
186
|
+
�� 103
|
|
187
|
+
�� 103
|
|
188
|
+
� 103
|
|
189
|
+
�� 103
|
|
190
|
+
� 102
|
|
191
|
+
�� 102
|
|
192
|
+
��� 100
|
|
193
|
+
�� 100
|
|
194
|
+
�� 100
|
|
195
|
+
�߂ 99
|
|
196
|
+
���� 98
|
|
197
|
+
��� 98
|
|
198
|
+
� 97
|
|
199
|
+
�� 96
|
|
200
|
+
� 96
|
|
201
|
+
�� 96
|
|
202
|
+
I 95
|
|
203
|
+
[� 95
|
|
204
|
+
�[� 95
|
|
205
|
+
�́A 94
|
|
206
|
+
�� 94
|
|
207
|
+
́A 94
|
|
208
|
+
�� 93
|
|
209
|
+
�� 92
|
|
210
|
+
� 92
|
|
211
|
+
� 92
|
|
212
|
+
�� 92
|
|
213
|
+
E 92
|
|
214
|
+
�Q 91
|
|
215
|
+
� 90
|
|
216
|
+
w 90
|
|
217
|
+
��� 89
|
|
218
|
+
�� 89
|
|
219
|
+
� 89
|
|
220
|
+
� 88
|
|
221
|
+
�� 87
|
|
222
|
+
x 87
|
|
223
|
+
�� 86
|
|
224
|
+
P� 86
|
|
225
|
+
� 86
|
|
226
|
+
��� 86
|
|
227
|
+
n 86
|
|
228
|
+
� 85
|
|
229
|
+
��� 85
|
|
230
|
+
���� 85
|
|
231
|
+
��� 84
|
|
232
|
+
�� 84
|
|
233
|
+
� 84
|
|
234
|
+
�͂ 84
|
|
235
|
+
� 84
|
|
236
|
+
�� 83
|
|
237
|
+
���B 83
|
|
238
|
+
��B 83
|
|
239
|
+
� 83
|
|
240
|
+
�� 83
|
|
241
|
+
� 82
|
|
242
|
+
� 82
|
|
243
|
+
�v� 80
|
|
244
|
+
�� 80
|
|
245
|
+
�P� 80
|
|
246
|
+
��� 79
|
|
247
|
+
� 79
|
|
248
|
+
A� 77
|
|
249
|
+
� 77
|
|
250
|
+
� 77
|
|
251
|
+
�� 77
|
|
252
|
+
���à 77
|
|
253
|
+
��à 77
|
|
254
|
+
� 76
|
|
255
|
+
B� 75
|
|
256
|
+
�X 75
|
|
257
|
+
���� 75
|
|
258
|
+
��� 74
|
|
259
|
+
c 74
|
|
260
|
+
� 74
|
|
261
|
+
�O 73
|
|
262
|
+
�� 73
|
|
263
|
+
�� 72
|
|
264
|
+
i� 72
|
|
265
|
+
��� 71
|
|
266
|
+
�� 71
|
|
267
|
+
�B� 71
|
|
268
|
+
�� 70
|
|
269
|
+
�� 70
|
|
270
|
+
� 70
|
|
271
|
+
y 70
|
|
272
|
+
ǂ 69
|
|
273
|
+
T 69
|
|
274
|
+
p 69
|
|
275
|
+
� 68
|
|
276
|
+
�� 68
|
|
277
|
+
��� 68
|
|
278
|
+
���B_ 67
|
|
279
|
+
�l 67
|
|
280
|
+
Z 67
|
|
281
|
+
�� 67
|
|
282
|
+
�� 67
|
|
283
|
+
�� 67
|
|
284
|
+
� 67
|
|
285
|
+
��B_ 67
|
|
286
|
+
� 67
|
|
287
|
+
X� 66
|
|
288
|
+
� 66
|
|
289
|
+
��� 66
|
|
290
|
+
� 66
|
|
291
|
+
�� 66
|
|
292
|
+
A� 66
|
|
293
|
+
�� 65
|
|
294
|
+
��� 65
|
|
295
|
+
�A� 65
|
|
296
|
+
U 65
|
|
297
|
+
�� 64
|
|
298
|
+
� 64
|
|
299
|
+
�� 63
|
|
300
|
+
��� 62
|
|
301
|
+
C 62
|
|
302
|
+
���� 62
|
|
303
|
+
�� 62
|
|
304
|
+
�R 62
|
|
305
|
+
�� 62
|
|
306
|
+
��� 62
|
|
307
|
+
���� 62
|
|
308
|
+
��� 62
|
|
309
|
+
_� 61
|
|
310
|
+
�܂ 61
|
|
311
|
+
��� 61
|
|
312
|
+
�� 61
|
|
313
|
+
^ 61
|
|
314
|
+
�� 61
|
|
315
|
+
��܂ 61
|
|
316
|
+
� 61
|
|
317
|
+
l� 61
|
|
318
|
+
�� 61
|
|
319
|
+
�� 60
|
|
320
|
+
���v 60
|
|
321
|
+
�� 60
|
|
322
|
+
��� 60
|
|
323
|
+
�v 60
|
|
324
|
+
��v 60
|
|
325
|
+
� 60
|
|
326
|
+
�� 60
|
|
327
|
+
��� 60
|
|
328
|
+
� 60
|
|
329
|
+
�A� 60
|
|
330
|
+
� 59
|
|
331
|
+
�� 59
|
|
332
|
+
�Ȃ� 59
|
|
333
|
+
Ȃ� 59
|
|
334
|
+
�� 59
|
|
335
|
+
�� 59
|
|
336
|
+
W� 59
|
|
337
|
+
�� 58
|
|
338
|
+
�i 58
|
|
339
|
+
���� 58
|
|
340
|
+
Q� 58
|
|
341
|
+
�j 58
|
|
342
|
+
�� 58
|
|
343
|
+
N� 58
|
|
344
|
+
�{ 57
|
|
345
|
+
��� 57
|
|
346
|
+
�� 57
|
|
347
|
+
� 57
|
|
348
|
+
��� 57
|
|
349
|
+
̐ 56
|
|
350
|
+
Ɂ 56
|
|
351
|
+
���A 56
|
|
352
|
+
e 56
|
|
353
|
+
�g 56
|
|
354
|
+
��A 56
|
|
355
|
+
ʂ 56
|
|
356
|
+
@� 56
|
|
357
|
+
55
|
|
358
|
+
z 55
|
|
359
|
+
�I 55
|
|
360
|
+
Y 55
|
|
361
|
+
ł� 55
|
|
362
|
+
�� 55
|
|
363
|
+
�A 55
|
|
364
|
+
A� 55
|
|
365
|
+
��� 54
|
|
366
|
+
�� 54
|
|
367
|
+
�X 54
|
|
368
|
+
��� 54
|
|
369
|
+
t 54
|
|
370
|
+
�ł� 54
|
|
371
|
+
�j 54
|
|
372
|
+
��� 53
|
|
373
|
+
�Ɂ 53
|
|
374
|
+
��Ƃ 53
|
|
375
|
+
� 53
|
|
376
|
+
���Ƃ 53
|
|
377
|
+
� 53
|
|
378
|
+
I� 53
|
|
379
|
+
�� 53
|
|
380
|
+
�� 53
|
|
381
|
+
�A� 53
|
|
382
|
+
�U 53
|
|
383
|
+
~ 53
|
|
384
|
+
�� 52
|
|
385
|
+
A� 52
|
|
386
|
+
x� 52
|
|
387
|
+
��A 52
|
|
388
|
+
�̐ 52
|
|
389
|
+
�n 52
|
|
390
|
+
S� 51
|
|
391
|
+
�A� 51
|
|
392
|
+
b 51
|
|
393
|
+
j� 51
|
|
394
|
+
�ǂ 51
|
|
395
|
+
�Q� 51
|
|
396
|
+
��� 51
|
|
397
|
+
�E 51
|
|
398
|
+
� 51
|
|
399
|
+
A� 51
|
|
400
|
+
�� 51
|