indonesian_stemmer 0.1.1 → 0.2.0
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/indonesian_stemmer/irregular_words.rb +51 -0
- data/lib/indonesian_stemmer/irregular_words/akhiran-i.txt +3508 -0
- data/lib/indonesian_stemmer/irregular_words/k.txt +734 -0
- data/lib/indonesian_stemmer/irregular_words/kah.txt +40 -0
- data/lib/indonesian_stemmer/irregular_words/ku.txt +28 -0
- data/lib/indonesian_stemmer/irregular_words/lah.txt +41 -0
- data/lib/indonesian_stemmer/irregular_words/mu.txt +8 -0
- data/lib/indonesian_stemmer/irregular_words/n.txt +96 -0
- data/lib/indonesian_stemmer/irregular_words/nya.txt +1 -0
- data/lib/indonesian_stemmer/irregular_words/p.txt +499 -0
- data/lib/indonesian_stemmer/irregular_words/pun.txt +6 -0
- data/lib/indonesian_stemmer/irregular_words/r.txt +527 -0
- data/lib/indonesian_stemmer/morphological_utility.rb +49 -79
- data/lib/indonesian_stemmer/version.rb +1 -1
- data/spec/indonesian_stemmer_spec.rb +2 -0
- data/spec/lib/indonesian_stemmer/morphological_utility_spec.rb +14 -0
- metadata +16 -4
@@ -0,0 +1,40 @@
|
|
1
|
+
bengkah
|
2
|
+
berkah
|
3
|
+
bingkah
|
4
|
+
bongkah
|
5
|
+
cekah
|
6
|
+
firkah
|
7
|
+
halakah
|
8
|
+
halkah
|
9
|
+
harakah
|
10
|
+
ingkah
|
11
|
+
jangkah
|
12
|
+
jerkah
|
13
|
+
kalah
|
14
|
+
kekah
|
15
|
+
kelakah
|
16
|
+
kerakah
|
17
|
+
kerkah
|
18
|
+
khalikah
|
19
|
+
langkah
|
20
|
+
lukah
|
21
|
+
markah
|
22
|
+
mukah
|
23
|
+
musyarakah
|
24
|
+
nafkah
|
25
|
+
naskah
|
26
|
+
nikah
|
27
|
+
pangkah
|
28
|
+
rakah
|
29
|
+
rekah
|
30
|
+
rengkah
|
31
|
+
sedekah
|
32
|
+
sekah
|
33
|
+
serakah
|
34
|
+
serkah
|
35
|
+
sungkah
|
36
|
+
takah
|
37
|
+
tekah
|
38
|
+
telingkah
|
39
|
+
tingkah
|
40
|
+
tongkah
|
@@ -0,0 +1,28 @@
|
|
1
|
+
awabeku
|
2
|
+
baku
|
3
|
+
bangku
|
4
|
+
beku
|
5
|
+
beluku
|
6
|
+
biku
|
7
|
+
buku
|
8
|
+
ceku
|
9
|
+
ciku
|
10
|
+
cuku
|
11
|
+
deku
|
12
|
+
jibaku
|
13
|
+
kaku
|
14
|
+
laku
|
15
|
+
leku
|
16
|
+
liku
|
17
|
+
luku
|
18
|
+
paku
|
19
|
+
pangku
|
20
|
+
peku
|
21
|
+
perilaku
|
22
|
+
saku
|
23
|
+
siku
|
24
|
+
suku
|
25
|
+
teleku
|
26
|
+
terungku
|
27
|
+
tungku
|
28
|
+
waluku
|
@@ -0,0 +1,41 @@
|
|
1
|
+
balah
|
2
|
+
belah
|
3
|
+
beslah
|
4
|
+
bilah
|
5
|
+
celah
|
6
|
+
galah
|
7
|
+
islah
|
8
|
+
istilah
|
9
|
+
jumlah
|
10
|
+
kalah
|
11
|
+
kelah
|
12
|
+
kilah
|
13
|
+
lalah
|
14
|
+
lelah
|
15
|
+
makalah
|
16
|
+
malah
|
17
|
+
masalah
|
18
|
+
muamalah
|
19
|
+
mujadalah
|
20
|
+
mukabalah
|
21
|
+
olah
|
22
|
+
onslah
|
23
|
+
oplah
|
24
|
+
pecahbelah
|
25
|
+
pecah-belah
|
26
|
+
pilah
|
27
|
+
milah
|
28
|
+
sekolah
|
29
|
+
rihlah
|
30
|
+
risalah
|
31
|
+
salah
|
32
|
+
serlah
|
33
|
+
silsilah
|
34
|
+
sudah
|
35
|
+
sulalah
|
36
|
+
telah
|
37
|
+
tulah
|
38
|
+
ulah
|
39
|
+
uzlah
|
40
|
+
walah
|
41
|
+
wasilah
|
@@ -0,0 +1,96 @@
|
|
1
|
+
nafar
|
2
|
+
nahak
|
3
|
+
naik
|
4
|
+
naikkelas
|
5
|
+
naka
|
6
|
+
nala
|
7
|
+
nanap
|
8
|
+
nangkring
|
9
|
+
nasakh
|
10
|
+
naung
|
11
|
+
nayap
|
12
|
+
nebeng
|
13
|
+
nenen
|
14
|
+
nenes
|
15
|
+
nganga
|
16
|
+
ngebut
|
17
|
+
ngeceng
|
18
|
+
ngeden
|
19
|
+
ngenas
|
20
|
+
ngoyo
|
21
|
+
nidera
|
22
|
+
nimbrung
|
23
|
+
nomplok
|
24
|
+
nongol
|
25
|
+
nukil
|
26
|
+
nunut
|
27
|
+
nuzul
|
28
|
+
nyana
|
29
|
+
nyanya
|
30
|
+
nyanyah
|
31
|
+
nyanyi
|
32
|
+
nyanyu
|
33
|
+
nyapnyap
|
34
|
+
nyentrik
|
35
|
+
nyenyeh
|
36
|
+
nyerocos
|
37
|
+
nyit
|
38
|
+
nyolnyolan
|
39
|
+
nyungsung
|
40
|
+
nyunyut
|
41
|
+
nyurengnafi
|
42
|
+
nafkah
|
43
|
+
najis
|
44
|
+
nakal
|
45
|
+
nalam
|
46
|
+
nalar
|
47
|
+
nama
|
48
|
+
nanah
|
49
|
+
nanar
|
50
|
+
nanti
|
51
|
+
napas
|
52
|
+
nas
|
53
|
+
nasihat
|
54
|
+
nasional
|
55
|
+
nasionalisasi
|
56
|
+
naturalisasi
|
57
|
+
nazam
|
58
|
+
nazar
|
59
|
+
negara
|
60
|
+
negosiasi
|
61
|
+
nekat
|
62
|
+
neon
|
63
|
+
neraka
|
64
|
+
netral
|
65
|
+
ngeong
|
66
|
+
ngeri
|
67
|
+
ngiang
|
68
|
+
niaga
|
69
|
+
niat
|
70
|
+
nihil
|
71
|
+
nikah
|
72
|
+
nikmat
|
73
|
+
nilai
|
74
|
+
ninabobo
|
75
|
+
ningrat
|
76
|
+
nisbi
|
77
|
+
nista
|
78
|
+
nobat
|
79
|
+
noda
|
80
|
+
nominasi
|
81
|
+
nomor
|
82
|
+
nonaktif
|
83
|
+
nonong
|
84
|
+
normal
|
85
|
+
normalisasi
|
86
|
+
novel
|
87
|
+
nubuat
|
88
|
+
nujum
|
89
|
+
nyala
|
90
|
+
nyalang
|
91
|
+
nyaman
|
92
|
+
nyaring
|
93
|
+
nyata
|
94
|
+
nyawa
|
95
|
+
nyonyong
|
96
|
+
nyonyor
|
@@ -0,0 +1 @@
|
|
1
|
+
tanya
|
@@ -0,0 +1,499 @@
|
|
1
|
+
pacek
|
2
|
+
pacik
|
3
|
+
pacok
|
4
|
+
pacuk
|
5
|
+
paes
|
6
|
+
pagas
|
7
|
+
pagut
|
8
|
+
pajan
|
9
|
+
pajang
|
10
|
+
pakai
|
11
|
+
paksa
|
12
|
+
pakuk
|
13
|
+
palar
|
14
|
+
pale
|
15
|
+
paling
|
16
|
+
palis
|
17
|
+
palun
|
18
|
+
pamer
|
19
|
+
pamit
|
20
|
+
pampang
|
21
|
+
pana
|
22
|
+
pancakara
|
23
|
+
pancal
|
24
|
+
pancar
|
25
|
+
pancit
|
26
|
+
panco
|
27
|
+
pancur
|
28
|
+
pancut
|
29
|
+
pangah
|
30
|
+
panggang
|
31
|
+
panggih
|
32
|
+
panggil
|
33
|
+
pangkah
|
34
|
+
pangkas
|
35
|
+
pangkek
|
36
|
+
pangku
|
37
|
+
pangkung
|
38
|
+
pangling
|
39
|
+
pangpet
|
40
|
+
panguk
|
41
|
+
panjat
|
42
|
+
pantak
|
43
|
+
pantik
|
44
|
+
panting
|
45
|
+
pantul
|
46
|
+
papah
|
47
|
+
papas
|
48
|
+
papras
|
49
|
+
parih
|
50
|
+
parkir
|
51
|
+
parun
|
52
|
+
pasrah
|
53
|
+
pasuk
|
54
|
+
patungan
|
55
|
+
paut
|
56
|
+
payu
|
57
|
+
pecah
|
58
|
+
pecat
|
59
|
+
peduli
|
60
|
+
pegang
|
61
|
+
pegari
|
62
|
+
pegat
|
63
|
+
pei
|
64
|
+
pejam
|
65
|
+
pekau
|
66
|
+
peking
|
67
|
+
pekis
|
68
|
+
pelanting
|
69
|
+
pelas
|
70
|
+
pelaspas
|
71
|
+
pelecok
|
72
|
+
peleh
|
73
|
+
pelekok
|
74
|
+
pelencit
|
75
|
+
pelengak
|
76
|
+
pelesat
|
77
|
+
peleset
|
78
|
+
pelesir
|
79
|
+
pelihara
|
80
|
+
pelintir
|
81
|
+
pelonco
|
82
|
+
pelorot
|
83
|
+
pelosot
|
84
|
+
pelotot
|
85
|
+
peluk
|
86
|
+
pencar
|
87
|
+
pencet
|
88
|
+
pencil
|
89
|
+
pencut
|
90
|
+
penda
|
91
|
+
pendam
|
92
|
+
penggal
|
93
|
+
pengin
|
94
|
+
pengkis
|
95
|
+
pensiun
|
96
|
+
pental
|
97
|
+
pentang
|
98
|
+
peper
|
99
|
+
pepet
|
100
|
+
perah
|
101
|
+
perai
|
102
|
+
peram
|
103
|
+
perangah
|
104
|
+
peranjat
|
105
|
+
perap
|
106
|
+
peras
|
107
|
+
perata
|
108
|
+
perbal
|
109
|
+
percaya
|
110
|
+
percit
|
111
|
+
percul
|
112
|
+
perenyak
|
113
|
+
peretel
|
114
|
+
pergi
|
115
|
+
pergok
|
116
|
+
periksa
|
117
|
+
perinci
|
118
|
+
peringis
|
119
|
+
perkosa
|
120
|
+
perleng
|
121
|
+
perlup
|
122
|
+
perlus
|
123
|
+
permak
|
124
|
+
perogol
|
125
|
+
perosok
|
126
|
+
persekusi
|
127
|
+
persil
|
128
|
+
pertal
|
129
|
+
peruak
|
130
|
+
peruk
|
131
|
+
perusa
|
132
|
+
petal
|
133
|
+
petia
|
134
|
+
petik
|
135
|
+
peting
|
136
|
+
piara
|
137
|
+
picing
|
138
|
+
picit
|
139
|
+
pidi
|
140
|
+
pijah
|
141
|
+
pijat
|
142
|
+
pijit
|
143
|
+
pikau
|
144
|
+
piknik
|
145
|
+
pilah
|
146
|
+
pilih
|
147
|
+
pimpin
|
148
|
+
pinar
|
149
|
+
pincut
|
150
|
+
pinda
|
151
|
+
pindah
|
152
|
+
pindai
|
153
|
+
pingit
|
154
|
+
pingkal
|
155
|
+
pingkau
|
156
|
+
pingsan
|
157
|
+
pinjam
|
158
|
+
pintal
|
159
|
+
pintang
|
160
|
+
pintas
|
161
|
+
pipil
|
162
|
+
pipis
|
163
|
+
pirau
|
164
|
+
pirik
|
165
|
+
pirsa
|
166
|
+
pisit
|
167
|
+
pitar
|
168
|
+
piting
|
169
|
+
pocok
|
170
|
+
polah
|
171
|
+
polang
|
172
|
+
poldan
|
173
|
+
polok
|
174
|
+
porot
|
175
|
+
poser
|
176
|
+
potel
|
177
|
+
potol
|
178
|
+
prakira
|
179
|
+
prangas
|
180
|
+
pretel
|
181
|
+
procot
|
182
|
+
puasa
|
183
|
+
puatang
|
184
|
+
pugak
|
185
|
+
pugar
|
186
|
+
pugas
|
187
|
+
pujut
|
188
|
+
pukah
|
189
|
+
pulang
|
190
|
+
pulih
|
191
|
+
pumpun
|
192
|
+
punggah
|
193
|
+
pungkang
|
194
|
+
pungkas
|
195
|
+
pungut
|
196
|
+
puntal
|
197
|
+
puntir
|
198
|
+
punya
|
199
|
+
pupuh
|
200
|
+
purik
|
201
|
+
puruk
|
202
|
+
pusing
|
203
|
+
putar
|
204
|
+
putuspacak
|
205
|
+
pacar
|
206
|
+
pacu
|
207
|
+
pacul
|
208
|
+
pada
|
209
|
+
padam
|
210
|
+
padan
|
211
|
+
padat
|
212
|
+
padu
|
213
|
+
pagar
|
214
|
+
paham
|
215
|
+
pahat
|
216
|
+
pahit
|
217
|
+
pair
|
218
|
+
pajak
|
219
|
+
pajuh
|
220
|
+
pakal
|
221
|
+
pakan
|
222
|
+
pakat
|
223
|
+
paku
|
224
|
+
palai
|
225
|
+
palak
|
226
|
+
palam
|
227
|
+
palang
|
228
|
+
palit
|
229
|
+
palsu
|
230
|
+
palu
|
231
|
+
palut
|
232
|
+
pampas
|
233
|
+
pampat
|
234
|
+
panah
|
235
|
+
panas
|
236
|
+
pancang
|
237
|
+
pancing
|
238
|
+
pancung
|
239
|
+
pandai
|
240
|
+
pandak
|
241
|
+
pandang
|
242
|
+
pandu
|
243
|
+
panen
|
244
|
+
panggak
|
245
|
+
panggul
|
246
|
+
panggung
|
247
|
+
pangkal
|
248
|
+
pangkat
|
249
|
+
pangkur
|
250
|
+
pangsa
|
251
|
+
pangur
|
252
|
+
panitia
|
253
|
+
panjang
|
254
|
+
panjing
|
255
|
+
panjut
|
256
|
+
pantai
|
257
|
+
pantang
|
258
|
+
pantas
|
259
|
+
pantat
|
260
|
+
pantau
|
261
|
+
pantek
|
262
|
+
pantis
|
263
|
+
pantun
|
264
|
+
papak
|
265
|
+
papan
|
266
|
+
papar
|
267
|
+
paraf
|
268
|
+
parafrasa
|
269
|
+
parah
|
270
|
+
parak
|
271
|
+
paran
|
272
|
+
parang
|
273
|
+
parap
|
274
|
+
parit
|
275
|
+
parodi
|
276
|
+
paruh
|
277
|
+
parut
|
278
|
+
pasang
|
279
|
+
pasar
|
280
|
+
pasok
|
281
|
+
pasti
|
282
|
+
pasung
|
283
|
+
patah
|
284
|
+
patar
|
285
|
+
paten
|
286
|
+
patih
|
287
|
+
patik
|
288
|
+
patil
|
289
|
+
pating
|
290
|
+
patok
|
291
|
+
patri
|
292
|
+
patroli
|
293
|
+
patuh
|
294
|
+
patuk
|
295
|
+
patung
|
296
|
+
patut
|
297
|
+
pauk
|
298
|
+
payah
|
299
|
+
payang
|
300
|
+
payar
|
301
|
+
payung
|
302
|
+
pecak
|
303
|
+
pecal
|
304
|
+
pecut
|
305
|
+
peda
|
306
|
+
pedang
|
307
|
+
pedas
|
308
|
+
pedih
|
309
|
+
pegal
|
310
|
+
pegas
|
311
|
+
pejal
|
312
|
+
peka
|
313
|
+
pekak
|
314
|
+
pekat
|
315
|
+
pekik
|
316
|
+
pekuk
|
317
|
+
pelan
|
318
|
+
pelana
|
319
|
+
pelet
|
320
|
+
pelisit
|
321
|
+
pelitur
|
322
|
+
pelopor
|
323
|
+
pemidang
|
324
|
+
penat
|
325
|
+
pencak
|
326
|
+
pendak
|
327
|
+
pendek
|
328
|
+
pengap
|
329
|
+
pengaruh
|
330
|
+
pengat
|
331
|
+
pengkol
|
332
|
+
pengos
|
333
|
+
pening
|
334
|
+
penjara
|
335
|
+
pentas
|
336
|
+
pentil
|
337
|
+
penting
|
338
|
+
pentung
|
339
|
+
penuh
|
340
|
+
pepah
|
341
|
+
pepak
|
342
|
+
pepas
|
343
|
+
pepat
|
344
|
+
pepes
|
345
|
+
peran
|
346
|
+
perang
|
347
|
+
perawan
|
348
|
+
perban
|
349
|
+
percik
|
350
|
+
pergol
|
351
|
+
peri
|
352
|
+
perih
|
353
|
+
perintah
|
354
|
+
perkara
|
355
|
+
perlahan
|
356
|
+
perli
|
357
|
+
perlu
|
358
|
+
permisi
|
359
|
+
pernis
|
360
|
+
perosot
|
361
|
+
persekot
|
362
|
+
persen
|
363
|
+
persepsi
|
364
|
+
personifikasi
|
365
|
+
persuasi
|
366
|
+
pertama
|
367
|
+
perum
|
368
|
+
perun
|
369
|
+
perut
|
370
|
+
pesam
|
371
|
+
pesan
|
372
|
+
pesona
|
373
|
+
pesong
|
374
|
+
pesta
|
375
|
+
pesuk
|
376
|
+
peta
|
377
|
+
petah
|
378
|
+
petak
|
379
|
+
petang
|
380
|
+
peti
|
381
|
+
petir
|
382
|
+
petuah
|
383
|
+
piagam
|
384
|
+
pialang
|
385
|
+
piang
|
386
|
+
piat
|
387
|
+
pica
|
388
|
+
picik
|
389
|
+
picu
|
390
|
+
pidana
|
391
|
+
pidato
|
392
|
+
pihak
|
393
|
+
pijak
|
394
|
+
pijar
|
395
|
+
pikat
|
396
|
+
pikir
|
397
|
+
pikul
|
398
|
+
pilin
|
399
|
+
pilis
|
400
|
+
pilot
|
401
|
+
pilu
|
402
|
+
pinang
|
403
|
+
pincang
|
404
|
+
pincuk
|
405
|
+
pinggang
|
406
|
+
pinggir
|
407
|
+
pipa
|
408
|
+
pipih
|
409
|
+
pipit
|
410
|
+
pisah
|
411
|
+
pistol
|
412
|
+
piuh
|
413
|
+
piutang
|
414
|
+
plombir
|
415
|
+
poces
|
416
|
+
pohon
|
417
|
+
pojok
|
418
|
+
pokok
|
419
|
+
pokrol
|
420
|
+
poles
|
421
|
+
polimer
|
422
|
+
politik
|
423
|
+
pompa
|
424
|
+
pompong
|
425
|
+
pondok
|
426
|
+
pondong
|
427
|
+
pongah
|
428
|
+
ponten
|
429
|
+
popok
|
430
|
+
populer
|
431
|
+
porah
|
432
|
+
posisi
|
433
|
+
positif
|
434
|
+
potong
|
435
|
+
potret
|
436
|
+
prakarsa
|
437
|
+
praktik
|
438
|
+
praperadilan
|
439
|
+
prasaran
|
440
|
+
prediksi
|
441
|
+
presentasi
|
442
|
+
pribadi
|
443
|
+
pribumi
|
444
|
+
prihatin
|
445
|
+
prioritas
|
446
|
+
privatisasi
|
447
|
+
produksi
|
448
|
+
program
|
449
|
+
proklamasi
|
450
|
+
promosi
|
451
|
+
propaganda
|
452
|
+
prosa
|
453
|
+
proses
|
454
|
+
protes
|
455
|
+
proyeksi
|
456
|
+
puas
|
457
|
+
publikasi
|
458
|
+
pucat
|
459
|
+
pudar
|
460
|
+
pudi
|
461
|
+
pudur
|
462
|
+
puing
|
463
|
+
puisi
|
464
|
+
puja
|
465
|
+
puji
|
466
|
+
pujuk
|
467
|
+
pukal
|
468
|
+
pukang
|
469
|
+
pukat
|
470
|
+
pukau
|
471
|
+
pulas
|
472
|
+
pulau
|
473
|
+
pulun
|
474
|
+
pulung
|
475
|
+
pulut
|
476
|
+
punah
|
477
|
+
puncak
|
478
|
+
pundi
|
479
|
+
punggal
|
480
|
+
punggung
|
481
|
+
pungkur
|
482
|
+
pungli
|
483
|
+
punjung
|
484
|
+
punjut
|
485
|
+
puntung
|
486
|
+
pupuk
|
487
|
+
pupur
|
488
|
+
pupus
|
489
|
+
puput
|
490
|
+
pusaka
|
491
|
+
pusat
|
492
|
+
puso
|
493
|
+
pusut
|
494
|
+
puter
|
495
|
+
putih
|
496
|
+
putra
|
497
|
+
puyeng
|
498
|
+
pecahbelah
|
499
|
+
putarbalik
|