langdetect-ruby 0.1.1
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.
- checksums.yaml +7 -0
- data/CHANGELOG.md +9 -0
- data/LICENSE +21 -0
- data/README.md +33 -0
- data/Rakefile +11 -0
- data/langdetect-ruby.gemspec +33 -0
- data/lib/lingua_ruby/configuration.rb +15 -0
- data/lib/lingua_ruby/detector.rb +214 -0
- data/lib/lingua_ruby/ngram.rb +34 -0
- data/lib/lingua_ruby/profile.rb +31 -0
- data/lib/lingua_ruby/profile_loader.rb +39 -0
- data/lib/lingua_ruby/profiles/ar.json +302 -0
- data/lib/lingua_ruby/profiles/en.json +302 -0
- data/lib/lingua_ruby/profiles/id.json +402 -0
- data/lib/lingua_ruby/profiles/ja.json +302 -0
- data/lib/lingua_ruby/profiles/jv.json +302 -0
- data/lib/lingua_ruby/profiles/ko.json +302 -0
- data/lib/lingua_ruby/profiles/ms.json +402 -0
- data/lib/lingua_ruby/profiles/nl.json +302 -0
- data/lib/lingua_ruby/profiles/su.json +402 -0
- data/lib/lingua_ruby/profiles/zh.json +302 -0
- data/lib/lingua_ruby/result.rb +54 -0
- data/lib/lingua_ruby/version.rb +5 -0
- data/lib/lingua_ruby.rb +49 -0
- metadata +95 -0
|
@@ -0,0 +1,402 @@
|
|
|
1
|
+
{
|
|
2
|
+
"a": 0,
|
|
3
|
+
"n": 1,
|
|
4
|
+
"u": 2,
|
|
5
|
+
"a ": 3,
|
|
6
|
+
"i": 4,
|
|
7
|
+
"s": 5,
|
|
8
|
+
"d": 6,
|
|
9
|
+
"e": 7,
|
|
10
|
+
"r": 8,
|
|
11
|
+
"t": 9,
|
|
12
|
+
" s": 10,
|
|
13
|
+
"k": 11,
|
|
14
|
+
"un": 12,
|
|
15
|
+
"i ": 13,
|
|
16
|
+
"an": 14,
|
|
17
|
+
"b": 15,
|
|
18
|
+
"da": 16,
|
|
19
|
+
"sa": 17,
|
|
20
|
+
" b": 18,
|
|
21
|
+
"g": 19,
|
|
22
|
+
"ba": 20,
|
|
23
|
+
" k": 21,
|
|
24
|
+
" d": 22,
|
|
25
|
+
"eu": 23,
|
|
26
|
+
"nd": 24,
|
|
27
|
+
" su": 25,
|
|
28
|
+
"u ": 26,
|
|
29
|
+
"di": 27,
|
|
30
|
+
"sun": 28,
|
|
31
|
+
"und": 29,
|
|
32
|
+
"n ": 30,
|
|
33
|
+
"nda": 31,
|
|
34
|
+
"da ": 32,
|
|
35
|
+
" di": 33,
|
|
36
|
+
"ra": 34,
|
|
37
|
+
"ka": 35,
|
|
38
|
+
"m": 36,
|
|
39
|
+
"p": 37,
|
|
40
|
+
"as": 38,
|
|
41
|
+
"su": 39,
|
|
42
|
+
"asa": 40,
|
|
43
|
+
"ar": 41,
|
|
44
|
+
"a b": 42,
|
|
45
|
+
" ba": 43,
|
|
46
|
+
"na": 44,
|
|
47
|
+
" t": 45,
|
|
48
|
+
"h": 46,
|
|
49
|
+
"ng": 47,
|
|
50
|
+
"o": 48,
|
|
51
|
+
"ah": 49,
|
|
52
|
+
" ka": 50,
|
|
53
|
+
"eun": 51,
|
|
54
|
+
"bas": 52,
|
|
55
|
+
"sa ": 53,
|
|
56
|
+
"y": 54,
|
|
57
|
+
"ta": 55,
|
|
58
|
+
"ur": 56,
|
|
59
|
+
" a": 57,
|
|
60
|
+
"ang": 58,
|
|
61
|
+
"a d": 59,
|
|
62
|
+
"ay": 60,
|
|
63
|
+
" sa": 61,
|
|
64
|
+
"na ": 62,
|
|
65
|
+
"anu": 63,
|
|
66
|
+
"ya": 64,
|
|
67
|
+
"an ": 65,
|
|
68
|
+
" m": 66,
|
|
69
|
+
"j": 67,
|
|
70
|
+
"nu": 68,
|
|
71
|
+
"a s": 69,
|
|
72
|
+
" u": 70,
|
|
73
|
+
"nu ": 71,
|
|
74
|
+
"ne": 72,
|
|
75
|
+
"l": 73,
|
|
76
|
+
"ng ": 74,
|
|
77
|
+
"ni": 75,
|
|
78
|
+
"en": 76,
|
|
79
|
+
"se": 77,
|
|
80
|
+
"una": 78,
|
|
81
|
+
" ur": 79,
|
|
82
|
+
" j": 80,
|
|
83
|
+
"ke": 81,
|
|
84
|
+
"keu": 82,
|
|
85
|
+
"di ": 83,
|
|
86
|
+
"un ": 84,
|
|
87
|
+
"ti": 85,
|
|
88
|
+
" ku": 86,
|
|
89
|
+
"ku ": 87,
|
|
90
|
+
"ak": 88,
|
|
91
|
+
"ura": 89,
|
|
92
|
+
"ma": 90,
|
|
93
|
+
"ru": 91,
|
|
94
|
+
"pa": 92,
|
|
95
|
+
"ni ": 93,
|
|
96
|
+
"eni": 94,
|
|
97
|
+
"ku": 95,
|
|
98
|
+
"sen": 96,
|
|
99
|
+
" se": 97,
|
|
100
|
+
"i s": 98,
|
|
101
|
+
"ran": 99,
|
|
102
|
+
"ti ": 100,
|
|
103
|
+
"us": 101,
|
|
104
|
+
"a t": 102,
|
|
105
|
+
" n": 103,
|
|
106
|
+
"g ": 104,
|
|
107
|
+
"aya": 105,
|
|
108
|
+
"a a": 106,
|
|
109
|
+
" an": 107,
|
|
110
|
+
"at": 108,
|
|
111
|
+
"n k": 109,
|
|
112
|
+
"ka ": 110,
|
|
113
|
+
"ake": 111,
|
|
114
|
+
"nak": 112,
|
|
115
|
+
"aan": 113,
|
|
116
|
+
"gun": 114,
|
|
117
|
+
"igu": 115,
|
|
118
|
+
"dig": 116,
|
|
119
|
+
"a k": 117,
|
|
120
|
+
"n s": 118,
|
|
121
|
+
"a n": 119,
|
|
122
|
+
" ay": 120,
|
|
123
|
+
"us ": 121,
|
|
124
|
+
"i k": 122,
|
|
125
|
+
"pi ": 123,
|
|
126
|
+
"epi": 124,
|
|
127
|
+
"nep": 125,
|
|
128
|
+
" ne": 126,
|
|
129
|
+
"tar": 127,
|
|
130
|
+
" ta": 128,
|
|
131
|
+
"i t": 129,
|
|
132
|
+
"i m": 130,
|
|
133
|
+
" ti": 131,
|
|
134
|
+
"ya ": 132,
|
|
135
|
+
"day": 133,
|
|
136
|
+
"uda": 134,
|
|
137
|
+
"bud": 135,
|
|
138
|
+
"rna": 136,
|
|
139
|
+
"tur": 137,
|
|
140
|
+
"pan": 138,
|
|
141
|
+
"ahi": 139,
|
|
142
|
+
"ah ": 140,
|
|
143
|
+
"upa": 141,
|
|
144
|
+
"rup": 142,
|
|
145
|
+
"man": 143,
|
|
146
|
+
" ma": 144,
|
|
147
|
+
"u m": 145,
|
|
148
|
+
"at ": 146,
|
|
149
|
+
"ara": 147,
|
|
150
|
+
" ja": 148,
|
|
151
|
+
"i j": 149,
|
|
152
|
+
"g s": 150,
|
|
153
|
+
"pi": 151,
|
|
154
|
+
"ep": 152,
|
|
155
|
+
"ig": 153,
|
|
156
|
+
"aa": 154,
|
|
157
|
+
"up": 155,
|
|
158
|
+
"s ": 156,
|
|
159
|
+
"la": 157,
|
|
160
|
+
"h ": 158,
|
|
161
|
+
"hi": 159,
|
|
162
|
+
"r ": 160,
|
|
163
|
+
"ud": 161,
|
|
164
|
+
"gu": 162,
|
|
165
|
+
"in": 163,
|
|
166
|
+
"rn": 164,
|
|
167
|
+
"t ": 165,
|
|
168
|
+
" i": 166,
|
|
169
|
+
"po": 167,
|
|
170
|
+
"mi": 168,
|
|
171
|
+
"im": 169,
|
|
172
|
+
"er": 170,
|
|
173
|
+
"si": 171,
|
|
174
|
+
"ae": 172,
|
|
175
|
+
"bu": 173,
|
|
176
|
+
"ja": 174,
|
|
177
|
+
"ut": 175,
|
|
178
|
+
"tu": 176,
|
|
179
|
+
"sas": 177,
|
|
180
|
+
"ast": 178,
|
|
181
|
+
"aw": 179,
|
|
182
|
+
"str": 180,
|
|
183
|
+
"ju": 181,
|
|
184
|
+
"tra": 182,
|
|
185
|
+
"ra ": 183,
|
|
186
|
+
"kab": 184,
|
|
187
|
+
"abu": 185,
|
|
188
|
+
"yaa": 186,
|
|
189
|
+
"et": 187,
|
|
190
|
+
"ny": 188,
|
|
191
|
+
"a g": 189,
|
|
192
|
+
" ge": 190,
|
|
193
|
+
"geu": 191,
|
|
194
|
+
"eus": 192,
|
|
195
|
+
"c": 193,
|
|
196
|
+
"aka": 194,
|
|
197
|
+
"gha": 195,
|
|
198
|
+
"har": 196,
|
|
199
|
+
"arn": 197,
|
|
200
|
+
"lo": 198,
|
|
201
|
+
" l": 199,
|
|
202
|
+
"ji": 200,
|
|
203
|
+
" mi": 201,
|
|
204
|
+
"mim": 202,
|
|
205
|
+
"imi": 203,
|
|
206
|
+
"mit": 204,
|
|
207
|
+
"iti": 205,
|
|
208
|
+
"ij": 206,
|
|
209
|
+
"al": 207,
|
|
210
|
+
"gr": 208,
|
|
211
|
+
"ie": 209,
|
|
212
|
+
"ari": 210,
|
|
213
|
+
"ri ": 211,
|
|
214
|
+
" mu": 212,
|
|
215
|
+
"mus": 213,
|
|
216
|
+
"usi": 214,
|
|
217
|
+
"sik": 215,
|
|
218
|
+
"ik ": 216,
|
|
219
|
+
"k n": 217,
|
|
220
|
+
"wa": 218,
|
|
221
|
+
"kat": 219,
|
|
222
|
+
"t s": 220,
|
|
223
|
+
"aye": 221,
|
|
224
|
+
"yeu": 222,
|
|
225
|
+
"n d": 223,
|
|
226
|
+
"din": 224,
|
|
227
|
+
"ina": 225,
|
|
228
|
+
"kah": 226,
|
|
229
|
+
"hir": 227,
|
|
230
|
+
"iru": 228,
|
|
231
|
+
"sap": 229,
|
|
232
|
+
"apo": 230,
|
|
233
|
+
"pop": 231,
|
|
234
|
+
"opo": 232,
|
|
235
|
+
"poe": 233,
|
|
236
|
+
"oe ": 234,
|
|
237
|
+
"e k": 235,
|
|
238
|
+
"u j": 236,
|
|
239
|
+
" ju": 237,
|
|
240
|
+
"jut": 238,
|
|
241
|
+
"uta": 239,
|
|
242
|
+
"taa": 240,
|
|
243
|
+
"n u": 241,
|
|
244
|
+
"g d": 242,
|
|
245
|
+
"tat": 243,
|
|
246
|
+
"ata": 244,
|
|
247
|
+
"ar ": 245,
|
|
248
|
+
"r s": 246,
|
|
249
|
+
"s a": 247,
|
|
250
|
+
"w": 248,
|
|
251
|
+
"jam": 249,
|
|
252
|
+
"ama": 250,
|
|
253
|
+
"n b": 251,
|
|
254
|
+
"bah": 252,
|
|
255
|
+
"ahe": 253,
|
|
256
|
+
"heu": 254,
|
|
257
|
+
"eul": 255,
|
|
258
|
+
"ula": 256,
|
|
259
|
+
"la ": 257,
|
|
260
|
+
" tu": 258,
|
|
261
|
+
"ur ": 259,
|
|
262
|
+
"r t": 260,
|
|
263
|
+
" te": 261,
|
|
264
|
+
"ter": 262,
|
|
265
|
+
"eru": 263,
|
|
266
|
+
"rus": 264,
|
|
267
|
+
"s d": 265,
|
|
268
|
+
"dim": 266,
|
|
269
|
+
"ime": 267,
|
|
270
|
+
"mek": 268,
|
|
271
|
+
"eka": 269,
|
|
272
|
+
"kar": 270,
|
|
273
|
+
"ark": 271,
|
|
274
|
+
"rke": 272,
|
|
275
|
+
"mas": 273,
|
|
276
|
+
"sar": 274,
|
|
277
|
+
"rak": 275,
|
|
278
|
+
"ik": 276,
|
|
279
|
+
"mu": 277,
|
|
280
|
+
"ri": 278,
|
|
281
|
+
"it": 279,
|
|
282
|
+
"ha": 280,
|
|
283
|
+
"gh": 281,
|
|
284
|
+
"jaw": 282,
|
|
285
|
+
"awa": 283,
|
|
286
|
+
"wa ": 284,
|
|
287
|
+
"bar": 285,
|
|
288
|
+
"be": 286,
|
|
289
|
+
"rat": 287,
|
|
290
|
+
"id": 288,
|
|
291
|
+
"t b": 289,
|
|
292
|
+
"a i": 290,
|
|
293
|
+
" ie": 291,
|
|
294
|
+
"ieu": 292,
|
|
295
|
+
"eu ": 293,
|
|
296
|
+
"ci": 294,
|
|
297
|
+
"ac": 295,
|
|
298
|
+
"ngr": 296,
|
|
299
|
+
"gru": 297,
|
|
300
|
+
"ga": 298,
|
|
301
|
+
"pa ": 299,
|
|
302
|
+
"teu": 300,
|
|
303
|
+
"eut": 301,
|
|
304
|
+
"ute": 302,
|
|
305
|
+
" teu": 303,
|
|
306
|
+
"mah": 304,
|
|
307
|
+
"ahi": 305,
|
|
308
|
+
" mah": 306,
|
|
309
|
+
"kitu": 307,
|
|
310
|
+
"itu ": 308,
|
|
311
|
+
" kit": 309,
|
|
312
|
+
"ogé": 310,
|
|
313
|
+
"gé ": 311,
|
|
314
|
+
" og": 312,
|
|
315
|
+
"boga": 313,
|
|
316
|
+
"oga": 314,
|
|
317
|
+
" bog": 315,
|
|
318
|
+
"pis": 316,
|
|
319
|
+
"pisa": 317,
|
|
320
|
+
"isan": 318,
|
|
321
|
+
" pis": 319,
|
|
322
|
+
"ieu": 320,
|
|
323
|
+
"leu": 321,
|
|
324
|
+
"euh": 322,
|
|
325
|
+
" leu": 323,
|
|
326
|
+
"naon": 324,
|
|
327
|
+
"aon": 325,
|
|
328
|
+
"on ": 326,
|
|
329
|
+
" nao": 327,
|
|
330
|
+
"mung": 328,
|
|
331
|
+
"ung": 329,
|
|
332
|
+
"ngg": 330,
|
|
333
|
+
" mun": 331,
|
|
334
|
+
"sab": 332,
|
|
335
|
+
"aba": 333,
|
|
336
|
+
"bab": 334,
|
|
337
|
+
" sab": 335,
|
|
338
|
+
"tina": 336,
|
|
339
|
+
"ina ": 337,
|
|
340
|
+
" tin": 338,
|
|
341
|
+
"kana": 339,
|
|
342
|
+
"ana ": 340,
|
|
343
|
+
" kan": 341,
|
|
344
|
+
"dina": 342,
|
|
345
|
+
"ina": 343,
|
|
346
|
+
" din": 344,
|
|
347
|
+
"lamun": 345,
|
|
348
|
+
"amun": 346,
|
|
349
|
+
"mun ": 347,
|
|
350
|
+
" lam": 348,
|
|
351
|
+
"ayeu": 349,
|
|
352
|
+
"yeun": 350,
|
|
353
|
+
"euna": 351,
|
|
354
|
+
" aye": 352,
|
|
355
|
+
"upam": 353,
|
|
356
|
+
"pama": 354,
|
|
357
|
+
"amar": 355,
|
|
358
|
+
" upa": 356,
|
|
359
|
+
"oge": 357,
|
|
360
|
+
"geus": 358,
|
|
361
|
+
"eus ": 359,
|
|
362
|
+
" geu": 360,
|
|
363
|
+
"milu": 361,
|
|
364
|
+
"iluh": 362,
|
|
365
|
+
"luhu": 363,
|
|
366
|
+
"uhur": 364,
|
|
367
|
+
" mil": 365,
|
|
368
|
+
"hade": 366,
|
|
369
|
+
"adeu": 367,
|
|
370
|
+
"deun": 368,
|
|
371
|
+
" had": 369,
|
|
372
|
+
"sare": 370,
|
|
373
|
+
"areu": 371,
|
|
374
|
+
"reun": 372,
|
|
375
|
+
" sar": 373,
|
|
376
|
+
"ngan": 374,
|
|
377
|
+
"anga": 375,
|
|
378
|
+
"ngar": 376,
|
|
379
|
+
"gara": 377,
|
|
380
|
+
"sara": 378,
|
|
381
|
+
"uran": 379,
|
|
382
|
+
"rasa": 380,
|
|
383
|
+
" ras": 381,
|
|
384
|
+
"pang": 382,
|
|
385
|
+
"angg": 383,
|
|
386
|
+
"nggo": 384,
|
|
387
|
+
"ggo": 385,
|
|
388
|
+
" pan": 386,
|
|
389
|
+
"jeun": 387,
|
|
390
|
+
"eung": 388,
|
|
391
|
+
"ung ": 389,
|
|
392
|
+
" jeu": 390,
|
|
393
|
+
"dieu": 391,
|
|
394
|
+
"ieu ": 392,
|
|
395
|
+
" die": 393,
|
|
396
|
+
"wung": 394,
|
|
397
|
+
"ngku": 395,
|
|
398
|
+
"gkun": 396,
|
|
399
|
+
"kung": 397,
|
|
400
|
+
" ngk": 398,
|
|
401
|
+
"bae": 399
|
|
402
|
+
}
|
|
@@ -0,0 +1,302 @@
|
|
|
1
|
+
{
|
|
2
|
+
"中": 0,
|
|
3
|
+
"的": 1,
|
|
4
|
+
"国": 2,
|
|
5
|
+
" 中": 3,
|
|
6
|
+
"中国": 4,
|
|
7
|
+
"人": 5,
|
|
8
|
+
" 中国": 6,
|
|
9
|
+
"是": 7,
|
|
10
|
+
"文": 8,
|
|
11
|
+
"和": 9,
|
|
12
|
+
"多": 10,
|
|
13
|
+
"文化": 11,
|
|
14
|
+
"人民": 12,
|
|
15
|
+
"化": 13,
|
|
16
|
+
"是世": 14,
|
|
17
|
+
"世界": 15,
|
|
18
|
+
"界上": 16,
|
|
19
|
+
"是世界": 17,
|
|
20
|
+
"了": 18,
|
|
21
|
+
"世界上": 19,
|
|
22
|
+
"最多的": 20,
|
|
23
|
+
"国有着": 21,
|
|
24
|
+
"国的": 22,
|
|
25
|
+
"中国有": 23,
|
|
26
|
+
"国有": 24,
|
|
27
|
+
"年": 25,
|
|
28
|
+
"中国的": 26,
|
|
29
|
+
"民": 27,
|
|
30
|
+
"世": 28,
|
|
31
|
+
"有着": 29,
|
|
32
|
+
"着": 30,
|
|
33
|
+
"界": 31,
|
|
34
|
+
"多的": 32,
|
|
35
|
+
"有": 33,
|
|
36
|
+
"最": 34,
|
|
37
|
+
"最多": 35,
|
|
38
|
+
"上": 36,
|
|
39
|
+
"久历史": 37,
|
|
40
|
+
"悠久历": 38,
|
|
41
|
+
"的悠久": 39,
|
|
42
|
+
"年的悠": 40,
|
|
43
|
+
"千年的": 41,
|
|
44
|
+
"五千年": 42,
|
|
45
|
+
"着五千": 43,
|
|
46
|
+
"有着五": 44,
|
|
47
|
+
"人数最": 45,
|
|
48
|
+
"历史和": 46,
|
|
49
|
+
"史和灿": 47,
|
|
50
|
+
"和灿烂": 48,
|
|
51
|
+
"灿烂文": 49,
|
|
52
|
+
"烂文化": 50,
|
|
53
|
+
"文化 ": 51,
|
|
54
|
+
"化 中": 52,
|
|
55
|
+
" 中文": 53,
|
|
56
|
+
"中文是": 54,
|
|
57
|
+
"文是世": 55,
|
|
58
|
+
"界上使": 56,
|
|
59
|
+
"上使用": 57,
|
|
60
|
+
"使用人": 58,
|
|
61
|
+
"用人数": 59,
|
|
62
|
+
"一 中": 60,
|
|
63
|
+
"煌的": 61,
|
|
64
|
+
"辉煌": 62,
|
|
65
|
+
"了辉": 63,
|
|
66
|
+
"造了": 64,
|
|
67
|
+
"创造": 65,
|
|
68
|
+
" 创": 66,
|
|
69
|
+
"敢 ": 67,
|
|
70
|
+
"勇敢": 68,
|
|
71
|
+
"劳勇": 69,
|
|
72
|
+
"勤劳": 70,
|
|
73
|
+
"民勤": 71,
|
|
74
|
+
"国人": 72,
|
|
75
|
+
"境 ": 73,
|
|
76
|
+
"环境": 74,
|
|
77
|
+
"理环": 75,
|
|
78
|
+
"地理": 76,
|
|
79
|
+
"的地": 77,
|
|
80
|
+
"样的": 78,
|
|
81
|
+
"之一 ": 79,
|
|
82
|
+
"家之一": 80,
|
|
83
|
+
"国家之": 81,
|
|
84
|
+
"的国家": 82,
|
|
85
|
+
"多的国": 83,
|
|
86
|
+
"口最多": 84,
|
|
87
|
+
"人口最": 85,
|
|
88
|
+
"上人口": 86,
|
|
89
|
+
"界上人": 87,
|
|
90
|
+
"国是世": 88,
|
|
91
|
+
"和国是": 89,
|
|
92
|
+
"共和国": 90,
|
|
93
|
+
"民共和": 91,
|
|
94
|
+
"人民共": 92,
|
|
95
|
+
"华人民": 93,
|
|
96
|
+
"中华人": 94,
|
|
97
|
+
"文明": 95,
|
|
98
|
+
"的文": 96,
|
|
99
|
+
"地理环": 97,
|
|
100
|
+
"的地理": 98,
|
|
101
|
+
"样的地": 99,
|
|
102
|
+
"多样的": 100,
|
|
103
|
+
"和多样": 101,
|
|
104
|
+
"源和多": 102,
|
|
105
|
+
"资源和": 103,
|
|
106
|
+
"然资源": 104,
|
|
107
|
+
"自然资": 105,
|
|
108
|
+
"的自然": 106,
|
|
109
|
+
"富的自": 107,
|
|
110
|
+
"丰富的": 108,
|
|
111
|
+
"着丰富": 109,
|
|
112
|
+
"有着丰": 110,
|
|
113
|
+
"心 中": 111,
|
|
114
|
+
"中心 ": 112,
|
|
115
|
+
"化中心": 113,
|
|
116
|
+
"文化中": 114,
|
|
117
|
+
"的文明": 115,
|
|
118
|
+
"煌的文": 116,
|
|
119
|
+
"辉煌的": 117,
|
|
120
|
+
"了辉煌": 118,
|
|
121
|
+
"造了辉": 119,
|
|
122
|
+
"创造了": 120,
|
|
123
|
+
" 创造": 121,
|
|
124
|
+
"敢 创": 122,
|
|
125
|
+
"勇敢 ": 123,
|
|
126
|
+
"劳勇敢": 124,
|
|
127
|
+
"勤劳勇": 125,
|
|
128
|
+
"民勤劳": 126,
|
|
129
|
+
"人民勤": 127,
|
|
130
|
+
"国人民": 128,
|
|
131
|
+
"中国人": 129,
|
|
132
|
+
"境 中": 130,
|
|
133
|
+
"环境 ": 131,
|
|
134
|
+
"理环境": 132,
|
|
135
|
+
"得了巨": 133,
|
|
136
|
+
"取得了": 134,
|
|
137
|
+
"中取得": 135,
|
|
138
|
+
"年中取": 136,
|
|
139
|
+
"十年中": 137,
|
|
140
|
+
"几十年": 138,
|
|
141
|
+
"去几十": 139,
|
|
142
|
+
"过去几": 140,
|
|
143
|
+
"在过去": 141,
|
|
144
|
+
"济在过": 142,
|
|
145
|
+
"经济在": 143,
|
|
146
|
+
"的经济": 144,
|
|
147
|
+
"国的经": 145,
|
|
148
|
+
"言 中": 146,
|
|
149
|
+
"语言 ": 147,
|
|
150
|
+
"的语言": 148,
|
|
151
|
+
"多的语": 149,
|
|
152
|
+
"数最多": 150,
|
|
153
|
+
"治文化": 151,
|
|
154
|
+
"政治文": 152,
|
|
155
|
+
"是政治": 153,
|
|
156
|
+
"也是政": 154,
|
|
157
|
+
"都也是": 155,
|
|
158
|
+
"首都也": 156,
|
|
159
|
+
"的首都": 157,
|
|
160
|
+
"国的首": 158,
|
|
161
|
+
"是中国": 159,
|
|
162
|
+
"京是中": 160,
|
|
163
|
+
"北京是": 161,
|
|
164
|
+
" 北京": 162,
|
|
165
|
+
"展 北": 163,
|
|
166
|
+
"发展 ": 164,
|
|
167
|
+
"的发展": 165,
|
|
168
|
+
"大的发": 166,
|
|
169
|
+
"巨大的": 167,
|
|
170
|
+
"了巨大": 168,
|
|
171
|
+
"多样": 169,
|
|
172
|
+
"勤": 170,
|
|
173
|
+
"境": 171,
|
|
174
|
+
"环": 172,
|
|
175
|
+
"理": 173,
|
|
176
|
+
"地": 174,
|
|
177
|
+
"样": 175,
|
|
178
|
+
"源": 176,
|
|
179
|
+
"资": 177,
|
|
180
|
+
"然": 178,
|
|
181
|
+
"自": 179,
|
|
182
|
+
"富": 180,
|
|
183
|
+
"丰": 181,
|
|
184
|
+
"心": 182,
|
|
185
|
+
"治": 183,
|
|
186
|
+
"政": 184,
|
|
187
|
+
"也": 185,
|
|
188
|
+
"都": 186,
|
|
189
|
+
"口最": 187,
|
|
190
|
+
"人口": 188,
|
|
191
|
+
"上人": 189,
|
|
192
|
+
"国是": 190,
|
|
193
|
+
"和国": 191,
|
|
194
|
+
"共和": 192,
|
|
195
|
+
"民共": 193,
|
|
196
|
+
"华人": 194,
|
|
197
|
+
"中华": 195,
|
|
198
|
+
"明": 196,
|
|
199
|
+
"煌": 197,
|
|
200
|
+
"辉": 198,
|
|
201
|
+
"造": 199,
|
|
202
|
+
"创": 200,
|
|
203
|
+
"敢": 201,
|
|
204
|
+
"勇": 202,
|
|
205
|
+
"劳": 203,
|
|
206
|
+
"首": 204,
|
|
207
|
+
"数": 205,
|
|
208
|
+
"用": 206,
|
|
209
|
+
"使": 207,
|
|
210
|
+
"烂": 208,
|
|
211
|
+
"灿": 209,
|
|
212
|
+
"史": 210,
|
|
213
|
+
"历": 211,
|
|
214
|
+
"久": 212,
|
|
215
|
+
"悠": 213,
|
|
216
|
+
"千": 214,
|
|
217
|
+
"五": 215,
|
|
218
|
+
"一": 216,
|
|
219
|
+
"之": 217,
|
|
220
|
+
"家": 218,
|
|
221
|
+
"口": 219,
|
|
222
|
+
"共": 220,
|
|
223
|
+
"华": 221,
|
|
224
|
+
"京": 222,
|
|
225
|
+
"北": 223,
|
|
226
|
+
"展": 224,
|
|
227
|
+
"发": 225,
|
|
228
|
+
"大": 226,
|
|
229
|
+
"巨": 227,
|
|
230
|
+
"得": 228,
|
|
231
|
+
"取": 229,
|
|
232
|
+
"十": 230,
|
|
233
|
+
"几": 231,
|
|
234
|
+
"去": 232,
|
|
235
|
+
"过": 233,
|
|
236
|
+
"在": 234,
|
|
237
|
+
"济": 235,
|
|
238
|
+
"经": 236,
|
|
239
|
+
"言": 237,
|
|
240
|
+
"语": 238,
|
|
241
|
+
"首都": 239,
|
|
242
|
+
"的首": 240,
|
|
243
|
+
"是中": 241,
|
|
244
|
+
"京是": 242,
|
|
245
|
+
"北京": 243,
|
|
246
|
+
" 北": 244,
|
|
247
|
+
"展 ": 245,
|
|
248
|
+
"发展": 246,
|
|
249
|
+
"的发": 247,
|
|
250
|
+
"大的": 248,
|
|
251
|
+
"巨大": 249,
|
|
252
|
+
"了巨": 250,
|
|
253
|
+
"得了": 251,
|
|
254
|
+
"取得": 252,
|
|
255
|
+
"中取": 253,
|
|
256
|
+
"年中": 254,
|
|
257
|
+
"十年": 255,
|
|
258
|
+
"和多": 256,
|
|
259
|
+
"源和": 257,
|
|
260
|
+
"资源": 258,
|
|
261
|
+
"然资": 259,
|
|
262
|
+
"自然": 260,
|
|
263
|
+
"的自": 261,
|
|
264
|
+
"富的": 262,
|
|
265
|
+
"丰富": 263,
|
|
266
|
+
"着丰": 264,
|
|
267
|
+
"心 ": 265,
|
|
268
|
+
"中心": 266,
|
|
269
|
+
"化中": 267,
|
|
270
|
+
"治文": 268,
|
|
271
|
+
"政治": 269,
|
|
272
|
+
"是政": 270,
|
|
273
|
+
"也是": 271,
|
|
274
|
+
"都也": 272,
|
|
275
|
+
"几十": 273,
|
|
276
|
+
"烂文": 274,
|
|
277
|
+
"灿烂": 275,
|
|
278
|
+
"和灿": 276,
|
|
279
|
+
"史和": 277,
|
|
280
|
+
"历史": 278,
|
|
281
|
+
"久历": 279,
|
|
282
|
+
"悠久": 280,
|
|
283
|
+
"的悠": 281,
|
|
284
|
+
"年的": 282,
|
|
285
|
+
"千年": 283,
|
|
286
|
+
"五千": 284,
|
|
287
|
+
"着五": 285,
|
|
288
|
+
"一 ": 286,
|
|
289
|
+
"之一": 287,
|
|
290
|
+
"家之": 288,
|
|
291
|
+
"国家": 289,
|
|
292
|
+
"的国": 290,
|
|
293
|
+
"去几": 291,
|
|
294
|
+
"过去": 292,
|
|
295
|
+
"在过": 293,
|
|
296
|
+
"济在": 294,
|
|
297
|
+
"经济": 295,
|
|
298
|
+
"的经": 296,
|
|
299
|
+
"言 ": 297,
|
|
300
|
+
"语言": 298,
|
|
301
|
+
"的语": 299
|
|
302
|
+
}
|