scylla 0.9.3 → 1.2.0

data/test/fixtures/lms/dutch.lm

@@ -0,0 +1,400 @@
+_	22244
+e	11500
+n	6122
+d	4278
+a	4090
+r	3921
+i	3793
+t	3567
+o	3449
+n_	3082
+e_	2627
+en	2502
+de	2434
+l	2396
+s	2267
+en_	1947
+er	1753
+_d	1731
+g	1730
+v	1472
+an	1401
+t_	1376
+de_	1366
+h	1342
+_de	1235
+k	1146
+_e	1135
+m	1078
+_v	1000
+u	930
+te	925
+nd	915
+w	908
+in	903
+ee	877
+ge	825
+b	820
+r_	805
+j	755
+p	754
+et	750
+_h	748
+s_	743
+he	732
+c	725
+d_	709
+or	709
+el	677
+et_	651
+st	648
+ij	646
+aa	646
+oo	645
+_i	632
+_o	610
+z	601
+ie	600
+la	578
+an_	577
+_he	565
+va	558
+_en	533
+_w	526
+_b	502
+van	501
+der	495
+_g	490
+het	486
+_va	484
+_n	483
+and	481
+ed	476
+on	461
+me	447
+_in	446
+lan	443
+rd	440
+_m	433
+oor	426
+nde	422
+ch	421
+re	420
+al	418
+er_	412
+_a	410
+le	407
+ng	406
+_t	400
+_z	399
+be	397
+ar	393
+ve	373
+li	372
+ne	371
+we	370
+g_	369
+is	368
+_s	368
+in_	366
+den	361
+f	356
+ede	355
+ro	353
+ke	351
+ri	349
+_ee	336
+een	336
+vo	335
+_ge	323
+ti	323
+it	320
+_be	319
+at	317
+l_	297
+rl	296
+di	290
+_l	282
+nd_	278
+na	277
+ste	275
+te_	273
+es	266
+aar	265
+k_	264
+op	254
+erl	249
+ui	248
+ver	248
+ing	248
+ra	246
+_me	237
+_vo	237
+erd	234
+zi	233
+jk	231
+ijk	231
+_ne	230
+nt	226
+wa	225
+ei	222
+rla	222
+ie_	220
+ten	219
+ter	219
+or_	218
+ned	215
+_k	215
+gr	212
+da	211
+_p	210
+se	210
+rs	208
+gen	207
+_we	205
+oe	199
+ot	196
+sc	196
+eg	195
+_ve	195
+ond	194
+sch	193
+is_	191
+id	188
+ng_	187
+_zi	183
+ig	182
+ta	182
+ni	181
+eer	178
+_wa	176
+_on	176
+_r	174
+rde	174
+_op	173
+ze	170
+bi	169
+ur	168
+ol	168
+ord	168
+ers	167
+ere	167
+p_	167
+ev	167
+voo	167
+lij	165
+_is	164
+ds	164
+to	160
+do	160
+cht	159
+_di	159
+ht	159
+om	158
+aan	158
+ls	154
+_te	152
+ma	152
+el_	152
+pe	152
+wo	150
+_la	149
+est	148
+ns	145
+wer	144
+rt	144
+uit	143
+ls_	142
+doo	142
+_al	142
+ek	141
+am	141
+ijn	140
+jn	140
+ts	140
+eu	139
+lo	138
+_da	137
+mi	137
+_do	135
+met	135
+gro	135
+nge	134
+rij	134
+eli	132
+no	132
+_gr	132
+zij	131
+op_	131
+ren	130
+ken	130
+se_	129
+ic	127
+zo	127
+og	127
+jn_	126
+nds	126
+m_	126
+als	126
+end	125
+a_	125
+rd_	123
+_na	123
+ar_	122
+ha	122
+die	122
+tr	122
+tie	121
+eel	121
+as	121
+men	120
+_st	120
+em	120
+ang	117
+_aa	116
+le_	116
+ke_	115
+it_	115
+_u	110
+ho	109
+ld	109
+_oo	108
+mee	108
+vi	107
+eid	107
+wor	106
+_to	106
+ind	106
+tu	105
+eb	105
+ege	105
+wi	105
+al_	105
+_wo	104
+f_	101
+ele	100
+_zo	100
+sta	99
+ec	98
+_ui	98
+ok	95
+rm	95
+st_	94
+jke	94
+ll	93
+j_	93
+rk	93
+ich	93
+_ma	92
+ij_	92
+ko	91
+kt	90
+at_	90
+jk_	90
+ak	90
+nk	90
+waa	89
+_c	89
+ot_	88
+pa	88
+ge_	87
+ag	86
+uw	86
+il	86
+_f	86
+len	85
+erk	85
+bij	84
+geb	84
+eld	84
+re_	83
+del	83
+_er	82
+eri	82
+ov	82
+af	82
+pr	81
+ez	81
+ela	81
+gi	80
+aat	80
+hi	79
+ch_	79
+h_	79
+ati	79
+po	78
+gel	78
+id_	77
+ac	77
+_bi	77
+_re	76
+ent	76
+ens	76
+bel	75
+_mi	75
+ok_	75
+rg	75
+rs_	75
+dt	75
+vol	74
+ale	74
+dt_	74
+lle	74
+si	73
+isc	73
+ook	73
+uu	72
+_no	72
+uur	71
+nte	71
+ite	71
+tot	71
+taa	71
+du	70
+ep	70
+jd	70
+ijd	70
+_ze	69
+_j	69
+io	69
+un	69
+_ko	68
+ad	68
+eke	68
+ied	68
+che	68
+ran	68
+od	68
+ru	67
+ort	67
+dee	67
+maa	67
+so	67
+per	66
+ist	66
+ige	66
+tw	66
+ote	64
+as_	64
+tij	64
+ier	64
+ove	63
+sp	63
+gev	63
+ed_	63
+ew	63
+ht_	62
+of	62
+tuu	62
+euw	62
+zic	62
+roo	62
+ame	62
+_ho	61
+kel	61
+rb	61
+ach	61
+orm	61
+rot	61
+ja	60
+rdt	60

data/test/fixtures/lms/english.lm

@@ -1,400 +1,400 @@
-_	2598
-e	779
-i	547
-t	538
-a	512
-o	496
-s	459
-n	427
-r	397
-u	339
-l	290
-m	241
-e_	229
-d	228
-c	213
-h	192
-p	184
-s_	171
-t_	150
-_t	144
-re	135
-_a	132
-in	128
-m_	119
-_i	114
-f	104
-or	103
-b	102
-th	97
-n_	93
-g	90
-d_	90
-_o	88
-_e	84
-er	83
-_th	83
-he	81
-y	80
-at	79
-an	79
-_s	78
-on	74
-te	74
-es	72
-_p	70
-r_	69
-is	69
-se	66
-o_	66
-v	65
-it	64
-w	63
-the	63
-um	63
-en	62
-_the	61
-_c	59
-ti	59
-_b	58
-nd	58
-_d	58
-_l	57
-a_	53
-um_	52
-ur	52
-as	52
-y_	52
-lo	51
-nt	51
-su	50
-re_	49
-qu	49
-q	49
-he_	48
-_w	48
-us	46
-the_	46
-le	46
-em	45
-f_	45
-of	44
-si	43
-_m	43
-ta	43
-ore	42
-k	42
-_of	42
-_in	42
-ed	42
-to	42
-li	42
-et	41
-in_	41
-_r	41
-lor	40
-ng	40
-of_	39
-is_	39
-ea	39
-_h	39
-and	39
-_of_	39
-st	38
-la	38
-ed_	38
-_f	38
-ol	38
-de	37
-es_	36
-_an	36
-io	35
-ri	35
-_n	35
-ar	34
-ve	34
-co	33
-ing	33
-ra	33
-ou	33
-ce	33
-g_	32
-ec	32
-ng_	32
-l_	32
-nd_	32
-al	32
-em_	32
-ro	32
-to_	31
-ut	31
-ip	31
-ing_	31
-_to	31
-ha	31
-no	31
-ne	30
-ni	30
-el	30
-_u	30
-ci	29
-pa	29
-di	29
-lore	29
-it_	29
-om	29
-_v	29
-ic	28
-_re	28
-ma	28
-ns	28
-and_	28
-ct	28
-am	28
-ai	28
-on_	27
-_to_	27
-_and	27
-rem	27
-ion	27
-do	27
-ll	27
-_lo	27
-_a_	26
-_qu	26
-_co	26
-_q	26
-sum	26
-ia	26
-sum_	25
-_pa	25
-ips	25
-il	25
-ru	25
-ps	25
-tio	25
-et_	25
-x	25
-pl	24
-ati	24
-me	24
-_in_	24
-ui	24
-un	24
-rem_	23
-tr	23
-hi	23
-or_	23
-_ips	23
-h_	23
-_ip	23
-ut_	23
-ex	23
-psum	23
-i_	23
-at_	23
-se_	23
-ss	23
-ipsu	23
-tion	23
-psu	23
-orem	23
-_do	23
-ac	22
-id	22
-us_	22
-im	22
-mo	22
-ure	22
-nc	21
-nt_	21
-_ma	21
-ur_	21
-ons	20
-_lor	20
-qui	20
-ge	20
-_si	20
-_no	20
-tu	20
-pt	19
-er_	19
-bu	19
-ain	18
-pe	18
-ho	18
-ect	18
-_et	18
-ca	18
-_de	18
-ab	18
-as_	18
-be	18
-ple	18
-du	17
-_it	17
-_is	17
-rum_	17
-_wh	17
-rs	17
-_be	17
-sa	17
-_qui	17
-up	17
-eas	17
-vo	17
-ch	17
-wh	17
-pr	17
-am_	17
-rum	17
-ure_	17
-bl	17
-_ex	17
-ag	16
-ep	16
-tur	16
-na	16
-ua	16
-po	16
-bo	16
-ere	16
-lu	16
-ul	16
-_et_	16
-con	16
-cu	16
-olo	16
-ate	16
-_con	16
-lea	16
-ent	16
-au	16
-_dol	15
-leas	15
-ter	15
-_pl	15
-olor	15
-os	15
-dolo	15
-_is_	15
-dol	15
-tat	15
-ver	15
-_se	15
-en_	14
-_la	14
-te_	14
-so	14
-_ple	14
-_g	14
-int	14
-qua	14
-_ha	14
-wi	14
-sur	14
-plea	14
-ke	14
-ue	14
-_it_	13
-vol	13
-_by	13
-ain_	13
-ir	13
-_ve	13
-sure	13
-by	13
-res	13
-_al	13
-her	13
-fi	13
-olu	13
-le_	13
-_te	13
-ion_	13
-atio	13
-od	13
-_mo	13
-upt	13
-by_	13
-_by_	13
-olup	12
-_pr	12
-sin	12
-pta	12
-unt	12
-lup	12
-fr	12
-_vo	12
-lupt	12
-asu	12
-da	12
-est	12
-easu	12
-cc	12
-nte	12
-age	12
-upta	12
-_vol	12
-volu	12
-_li	12
-ore_	12
-ly	12
-_wi	12
-mp	12
-ae	12
-ly_	12
-_fr	12
-asur	12
-oo	12
-tur_	11
-nce	11
-k_	11
-pain	11
-fo	11
-_on	11
-oru	11
-ib	11
-oi	11
-pai	11
-_us	11
-equ	11
-_y	11
-eq	11
-_pai	11
-yo	11
-here	11
-tem	11
-orum	11
-cons	11
-tin	11
-ini	10
-use	10
-_es	10
-st_	10
-lat	10
-pu	10
-atu	10
-ll_	10
-ass	10
-ome	10
-ns_	10
-ess	10
-que	10
-rat	10
-_tr	10
-ill	10
-ble	10
-rom	10
-_he	10
-_or	10
-res_	10
-ere_	10
-rd	10
-ev	10
-ce_	10
-_su	10
-_so	10
-ibu	10
-om_	10
-for	10
+_	19026
+e	5658
+t	4138
+n	3839
+a	3693
+i	3421
+o	3229
+s	2963
+r	2878
+h	2469
+e_	2091
+d	1994
+l	1971
+_t	1697
+th	1590
+c	1418
+s_	1392
+he	1376
+_th	1342
+_a	1278
+d_	1264
+the	1260
+u	1163
+he_	1078
+g	1067
+in	1053
+m	1032
+f	978
+an	974
+n_	894
+p	830
+_i	809
+nd	776
+w	738
+re	710
+_o	653
+nd_	645
+y	643
+er	640
+t_	638
+en	628
+and	620
+on	605
+b	605
+_s	601
+ng	589
+y_	535
+_w	519
+ar	518
+es	508
+ed	502
+is	496
+_an	482
+_in	480
+_c	478
+ed_	475
+_e	464
+or	459
+ti	449
+st	443
+it	440
+of	429
+la	425
+f_	425
+_of	422
+h_	421
+te	418
+as	416
+_b	410
+of_	409
+nt	407
+v	398
+r_	392
+at	391
+ri	382
+_f	375
+al	368
+in_	368
+_p	358
+ro	326
+ing	310
+as_	307
+re_	301
+to	296
+_m	288
+co	287
+de	283
+o_	282
+g_	282
+ng_	277
+io	267
+l_	266
+es_	263
+le	263
+om	262
+ou	258
+li	255
+_l	253
+se	251
+_r	251
+ve	248
+me	244
+_h	244
+ea	242
+_en	242
+ch	242
+on_	241
+ur	234
+ion	230
+is_	229
+a_	229
+ce	223
+gl	221
+ic	221
+lan	220
+_co	217
+ent	217
+er_	217
+ngl	217
+eng	215
+_to	213
+_d	207
+to_	206
+hi	203
+st_	202
+_ar	199
+ha	198
+ra	197
+si	197
+k	195
+_is	193
+un	193
+al_	183
+nc	181
+m_	180
+_n	174
+_a_	174
+ns	174
+fo	173
+tr	169
+wa	162
+_re	162
+pe	161
+ma	159
+ll	159
+_fo	158
+ne	155
+th_	154
+ly	154
+her	153
+rt	153
+ly_	152
+po	151
+are	151
+el	151
+tio	150
+be	150
+na	150
+ca	147
+gla	147
+ec	147
+ge	144
+_as	144
+ho	144
+sh	144
+ol	144
+mo	143
+ere	143
+no	142
+ie	141
+_wa	140
+ni	140
+_u	137
+ch_	136
+lo	134
+ta	133
+we	132
+est	131
+il	129
+_be	128
+ts	126
+ted	125
+om_	125
+wh	124
+pr	124
+tu	123
+di	122
+ot	122
+pa	122
+ct	121
+ate	120
+os	119
+ati	119
+ts_	119
+op	119
+rs	119
+rom	118
+_wh	117
+wi	117
+fr	116
+_ha	115
+ai	115
+an_	115
+for	115
+or_	114
+_fr	113
+am	113
+ter	112
+us	111
+ia	111
+nt_	110
+su	110
+ry	110
+ish	109
+ow	109
+_mo	107
+_pr	107
+_by	105
+by_	105
+_s_	105
+by	105
+iv	104
+_wi	104
+ry_	104
+con	102
+so	102
+_la	101
+em	100
+le_	100
+_g	100
+was	99
+ut	99
+ad	99
+et	98
+_it	97
+cl	97
+ns_	96
+ul	96
+me_	95
+mi	95
+wo	95
+ac	95
+ee	95
+inc	94
+ig	94
+do	94
+ons	94
+oun	94
+ir	93
+sh_	93
+ci	93
+ver	93
+tur	92
+uc	92
+fro	92
+_ma	91
+ce_	90
+ies	90
+_pa	89
+ith	87
+_on	87
+du	86
+_we	86
+wit	85
+lis	85
+tin	84
+rl	84
+iti	84
+nce	84
+at_	84
+_de	84
+mp	83
+en_	83
+ev	82
+id	82
+ld	82
+all	82
+lu	82
+_k	82
+_su	80
+pl	80
+fi	79
+sp	78
+_se	78
+par	77
+_no	77
+rs_	76
+im	76
+ov	76
+rea	76
+te_	76
+gh	75
+vi	75
+_un	75
+ss	75
+man	74
+x	74
+art	74
+ite	73
+gi	72
+rit	71
+ain	71
+od	71
+it_	71
+ag	71
+und	70
+whi	70
+br	70
+ve_	69
+res	69
+ntr	68
+rn	68
+ist	68
+gli	67
+_wo	65
+_st	65
+cen	65
+_so	64
+der	64
+ive	64
+ba	63
+int	63
+lar	63
+_si	63
+ost	63
+_po	63
+eg	62
+ki	62
+ud	62
+ty	62
+ove	62
+men	62
+nti	62
+ers	61
+_ce	61
+cou	61
+pro	60
+ld_	60
+rin	60
+has	60
+_br	60
+rm	60
+rd	59
+ame	59
+ern	59
+_al	59
+ort	59
+lat	58
+gr	58
+_pe	58
+bo	58
+ug	58
+ine	58
+ica	57
+wor	57
+rou	57
+ect	56
+uri	56
+kin	56
+clu	56
+sc	56
+oth	56
+ue	56
+av	55
+_le	55
+_lo	55
+uch	55
+eve	54
+se_	54
+bri	54
+cal	54
+com	53
+rie	53
+uni	53
+ex	53
+wer	53
+his	53
+ear	53
+eat	53
+cr	52
+c_	52
+ori	52
+_at	51
+ona	51
+nal	51
+tra	51
+sed	51
+ls	51
+rc	51
+ncl	51
+ide	51
+rg	50
+hic	50
+ga	50
+lud	50
+unt	50
+bl	50
+suc	50
+_ki	50
+de_	49