buzzerstar - libraryv3 - textcat - LM-query - SOURCE CODE

<?php $ngrams = array (
  '_' => 3858218,
  'ا' => 1670370,
  'ل' => 1134183,
  'ي' => 799663,
  '_ا' => 737344,
  'ال' => 702486,
  'م' => 613496,
  '_ال' => 599510,
  'ر' => 557269,
  'ن' => 483517,
  'و' => 473112,
  'ب' => 373530,
  'ت' => 359290,
  'س' => 314050,
  'د' => 307193,
  'ع' => 301020,
  'ة' => 290842,
  'ة_' => 279739,
  'ف' => 243623,
  'ه' => 223765,
  'ك' => 204360,
  'ي_' => 189884,
  'ح' => 188006,
  '_م' => 186464,
  'ن_' => 175614,
  'ق' => 169421,
  'ج' => 158875,
  'لا' => 134738,
  'ر_' => 132407,
  'لم' => 126518,
  'ص' => 124491,
  'ل_' => 112953,
  'ه_' => 110921,
  'ش' => 109880,
  'م_' => 107306,
  'ان' => 107097,
  'ت_' => 104301,
  'ية' => 98341,
  'ية_' => 96430,
  'الم' => 96291,
  'ات' => 95329,
  'ط' => 94387,
  'د_' => 92672,
  'ز' => 92157,
  '_ع' => 91420,
  'ري' => 90466,
  '_ب' => 89630,
  '_ف' => 88112,
  'ا_' => 87588,

... [truncated, 9955 more lines] ...

<?php $ngrams = array (
  '_' => 100142,
  'а' => 34692,
  'и' => 29710,
  'е' => 23911,
  'о' => 23601,
  'н' => 22201,
  'р' => 19784,
  'т' => 16937,
  'с' => 13982,
  'л' => 12984,
  'к' => 12844,
  'в' => 12176,
  'а_' => 11814,
  'д' => 8273,
  'м' => 7979,
  'и_' => 7422,
  'п' => 6670,
  'на' => 5660,
  'г' => 5238,
  'у' => 5049,
  'б' => 4748,
  'з' => 4604,
  'я' => 4361,
  'ан' => 4339,
  'ъ' => 4254,
  'ни' => 4161,
  'ра' => 4146,
  'ен' => 4048,
  'на_' => 4003,
  '_с' => 3994,
  'ри' => 3596,
  'о_' => 3559,
  '_п' => 3540,
  'н_' => 3531,
  'ст' => 3515,
  'ка' => 3505,
  'е_' => 3492,
  '_н' => 3326,
  '_к' => 3228,
  'ов' => 3223,
  'ар' => 3102,
  'та' => 2855,
  'ч' => 2840,
  'в_' => 2831,
  'я_' => 2784,
  'ко' => 2681,
  'те' => 2671,
  'ия' => 2640,
  'ин' => 2638,

... [truncated, 9955 more lines] ...

<?php $ngrams = array (
  '_' => 123838,
  'া' => 41650,
  'র' => 26437,
  '্' => 23404,
  'ি' => 22861,
  'ন' => 18431,
  'ে' => 14967,
  'ব' => 14953,
  'ক' => 14475,
  'ম' => 13371,
  'ল' => 12986,
  'স' => 12609,
  'য' => 11068,
  'র_' => 9862,
  'ত' => 9817,
  'দ' => 8547,
  'প' => 7812,
  'ু' => 7693,
  'া_' => 7683,
  '_ব' => 7298,
  '়' => 6755,
  'ন_' => 6276,
  'জ' => 6228,
  'য়' => 6072,
  'ার' => 5858,
  '_স' => 5840,
  '_ক' => 5684,
  'শ' => 5532,
  'ি_' => 5206,
  'হ' => 5195,
  'ী' => 5193,
  '্র' => 5058,
  'ট' => 5040,
  'ো' => 4502,
  'গ' => 4489,
  '_ম' => 4455,
  '_প' => 4230,
  'ান' => 4087,
  'বা' => 3988,
  'ই' => 3737,
  'লা' => 3718,
  '্য' => 3659,
  'ের' => 3502,
  'মা' => 3263,
  'রা' => 3205,
  'আ' => 3159,
  'চ' => 3117,
  'কা' => 3097,
  'ের_' => 3053,

... [truncated, 9955 more lines] ...

<?php $ngrams = array (
  '_' => 1568501,
  'a' => 419148,
  'e' => 377696,
  'o' => 358086,
  'n' => 304128,
  'r' => 276059,
  'i' => 275302,
  't' => 243706,
  's' => 235648,
  'l' => 222363,
  'k' => 204345,
  'v' => 173287,
  'd' => 135748,
  'm' => 135145,
  'c' => 132713,
  'u' => 126170,
  'p' => 119658,
  'a_' => 113052,
  'h' => 99984,
  'y' => 90577,
  'í' => 82027,
  'b' => 80339,
  'á' => 79045,
  'e_' => 76320,
  'z' => 68379,
  '_s' => 64313,
  '_p' => 62430,
  'st' => 57270,
  'ov' => 52166,
  'y_' => 51887,
  'j' => 50512,
  'an' => 49788,
  'í_' => 48579,
  'ra' => 48101,
  'g' => 47099,
  'er' => 46361,
  'en' => 45489,
  '_v' => 44223,
  'ro' => 43828,
  '_m' => 40067,
  '_k' => 39716,
  'in' => 38736,
  'na' => 37652,
  'ní' => 37435,
  'sk' => 37434,
  'n_' => 37311,
  'ar' => 37290,
  'o_' => 35709,
  'f' => 35602,

... [truncated, 9955 more lines] ...

<?php $ngrams = array (
  '_' => 11898941,
  'e' => 5097240,
  'n' => 3131188,
  'a' => 3103871,
  'r' => 3098569,
  'i' => 2903510,
  's' => 2474295,
  't' => 2442136,
  'l' => 2007828,
  'o' => 1896660,
  'h' => 1544602,
  'u' => 1391540,
  'c' => 1245764,
  'd' => 1235407,
  'm' => 1135703,
  'er' => 1122215,
  'g' => 1084453,
  'e_' => 927749,
  'n_' => 878895,
  'en' => 830238,
  'k' => 807768,
  'b' => 799917,
  'ch' => 743886,
  'p' => 702490,
  'f' => 676088,
  'r_' => 610144,
  'te' => 542747,
  'an' => 524557,
  'in' => 516826,
  's_' => 474677,
  'er_' => 463252,
  'st' => 432145,
  't_' => 426115,
  'w' => 422588,
  'de' => 406220,
  'en_' => 399436,
  '_s' => 390517,
  'he' => 389916,
  'ie' => 366924,
  'z' => 363559,
  'on' => 363376,
  're' => 362907,
  'ei' => 359493,
  'el' => 349613,
  'ar' => 347792,
  'v' => 346857,
  'sc' => 346774,
  'is' => 342763,
  'le' => 330819,

... [truncated, 9955 more lines] ...

<?php $ngrams = array (
  '_' => 316005,
  'α' => 112528,
  'ο' => 95629,
  'ι' => 85402,
  'τ' => 63525,
  'ε' => 59686,
  'ν' => 55715,
  'ρ' => 54628,
  'σ' => 51956,
  'κ' => 43874,
  'λ' => 40993,
  'η' => 40743,
  'μ' => 36356,
  'υ' => 35639,
  'ς' => 34376,
  'ς_' => 33878,
  'π' => 32641,
  'α_' => 27388,
  'γ' => 23134,
  'ω' => 17910,
  'δ' => 17428,
  'ου' => 16499,
  'ικ' => 14764,
  'ια' => 13691,
  'η_' => 13536,
  '_π' => 13163,
  '_α' => 13153,
  '_τ' => 12977,
  'ί' => 12603,
  'ο_' => 12539,
  'το' => 12369,
  'ος' => 11957,
  'ος_' => 11836,
  'αν' => 11582,
  'χ' => 11457,
  'φ' => 11313,
  'τα' => 11280,
  'ι_' => 10882,
  '_ε' => 10490,
  'σ_' => 10367,
  'στ' => 10230,
  'ά' => 10196,
  'Α' => 10078,
  'ν_' => 10069,
  '_κ' => 10060,
  'ρο' => 9942,
  'θ' => 9732,
  'πο' => 9507,
  '_σ' => 9488,

... [truncated, 9955 more lines] ...

<?php $ngrams = array (
  '_' => 19409660,
  'a' => 6250760,
  'e' => 6042100,
  'o' => 4539597,
  'i' => 4231041,
  'n' => 3442312,
  'r' => 3434825,
  's' => 3415876,
  'l' => 2955111,
  'c' => 2613093,
  'd' => 2432502,
  't' => 2398149,
  'u' => 1859497,
  'a_' => 1829139,
  's_' => 1615900,
  'e_' => 1590514,
  'm' => 1545636,
  'o_' => 1243164,
  'de' => 1240782,
  '_d' => 1228075,
  'p' => 1180813,
  '_de' => 1037643,
  'n_' => 883800,
  'g' => 861577,
  'es' => 860111,
  'de_' => 832908,
  'en' => 821188,
  '_de_' => 787006,
  '_c' => 783891,
  '_e' => 763522,
  'b' => 753411,
  'on' => 752491,
  'la' => 734120,
  'er' => 725186,
  'ra' => 674329,
  'an' => 668236,
  'os' => 660114,
  '_l' => 645179,
  'l_' => 619712,
  'ar' => 606635,
  'ci' => 590265,
  'as' => 588839,
  '_p' => 576340,
  'f' => 567202,
  'el' => 564934,
  'ca' => 558789,
  'al' => 551807,
  'ic' => 543162,
  'co' => 539757,

... [truncated, 9955 more lines] ...

<?php $ngrams = array (
  '_' => 1250304,
  'ا' => 418834,
  'ی' => 291557,
  'ر' => 251925,
  'ن' => 211472,
  'و' => 173592,
  'م' => 158365,
  'د' => 146903,
  'ت' => 138049,
  'ه' => 134378,
  'س' => 121977,
  'ی_' => 117153,
  'ل' => 114491,
  'ب' => 98092,
  'ن_' => 80755,
  '_ا' => 79633,
  'ک' => 79489,
  'ان' => 77420,
  'ه_' => 69676,
  'ش' => 63142,
  '_م' => 59461,
  'ز' => 59047,
  'ر_' => 54932,
  'ف' => 49748,
  'ای' => 45854,
  'ار' => 43854,
  '_ب' => 43400,
  'گ' => 42707,
  'ع' => 41232,
  '_د' => 40663,
  'ت_' => 40015,
  'ان_' => 38289,
  'را' => 38177,
  'د_' => 34952,
  'ج' => 34391,
  'ری' => 33713,
  '_س' => 33611,
  'پ' => 33068,
  'خ' => 32191,
  '_ک' => 32066,
  'ق' => 32056,
  '_ت' => 30465,
  'ا_' => 29129,
  'ي' => 28194,
  'م_' => 28102,
  'ال' => 27654,
  'ها' => 26983,
  'ح' => 26613,
  'ل_' => 25528,

... [truncated, 9955 more lines] ...

<?php $ngrams = array (
  '_' => 9199406,
  'e' => 3417327,
  'a' => 2253350,
  'i' => 2010426,
  'r' => 1792564,
  'n' => 1742433,
  'o' => 1615464,
  's' => 1530355,
  't' => 1488482,
  'l' => 1417841,
  'e_' => 1399394,
  'u' => 1124651,
  'd' => 961115,
  'c' => 904768,
  'm' => 799655,
  's_' => 602252,
  'p' => 598452,
  '_d' => 533941,
  'h' => 491073,
  'g' => 458287,
  'de' => 413293,
  'n_' => 405014,
  'on' => 399449,
  'es' => 390976,
  'b' => 376341,
  'le' => 370255,
  'an' => 361708,
  're' => 353732,
  '_l' => 350111,
  'er' => 341155,
  'f' => 317635,
  'en' => 315703,
  '_de' => 310118,
  't_' => 307984,
  '_c' => 301653,
  'v' => 290342,
  'es_' => 286846,
  'in' => 282349,
  'de_' => 274230,
  'é' => 273474,
  'a_' => 268380,
  '_p' => 259781,
  'te' => 258484,
  'ar' => 249765,
  'ti' => 248706,
  '_s' => 243852,
  'r_' => 241831,
  '_a' => 240426,
  'la' => 237751,

... [truncated, 9955 more lines] ...

<?php $ngrams = array (
  '_' => 536667,
  'י' => 167564,
  'ו' => 135411,
  'ר' => 87741,
  'ה' => 86932,
  'ל' => 74712,
  'מ' => 67129,
  'א' => 62253,
  'ת' => 59581,
  'ב' => 57930,
  'נ' => 50086,
  'ש' => 43073,
  'ד' => 37940,
  'ה_' => 37781,
  '_ה' => 37453,
  'ת_' => 37199,
  'ק' => 35641,
  'ס' => 35592,
  'פ' => 34048,
  '_מ' => 30518,
  'ם' => 29749,
  'ח' => 28962,
  'ם_' => 28314,
  'ט' => 28125,
  'ע' => 27733,
  'ג' => 27464,
  'י_' => 26261,
  '_א' => 25282,
  'ן' => 24832,
  'ן_' => 23002,
  'כ' => 21796,
  '_ב' => 21099,
  'ל_' => 19992,
  'ים' => 19392,
  'ים_' => 19033,
  'ר_' => 18256,
  'צ' => 17444,
  '_ש' => 16450,
  'ות' => 15819,
  'רי' => 15512,
  'ור' => 14817,
  'לי' => 14226,
  'ות_' => 14061,
  'ז' => 14031,
  'ני' => 13016,
  '_ל' => 12162,
  'רו' => 11681,
  'יי' => 11087,
  '_י' => 10868,

... [truncated, 9955 more lines] ...

<?php $ngrams = array (
  '_' => 72420,
  'ा' => 18577,
  'र' => 12428,
  '्' => 10812,
  'क' => 10394,
  'ि' => 8477,
  'न' => 7804,
  'स' => 7229,
  'ी' => 6857,
  'म' => 6553,
  'े' => 6512,
  'त' => 5995,
  '_क' => 5944,
  'ा_' => 5686,
  'ल' => 5410,
  'व' => 5016,
  'य' => 4698,
  'प' => 4471,
  'ी_' => 4328,
  'ं' => 3939,
  'द' => 3920,
  'ह' => 3786,
  'ो' => 3586,
  '_स' => 3477,
  'ज' => 3413,
  'ु' => 3271,
  'र_' => 3100,
  'ब' => 3073,
  'े_' => 2931,
  'ग' => 2843,
  '_म' => 2761,
  '_प' => 2564,
  'ार' => 2395,
  'न_' => 2370,
  '्र' => 2339,
  'श' => 2289,
  'का' => 2261,
  'ट' => 2037,
  'च' => 1896,
  'रा' => 1808,
  'ड' => 1736,
  '_ब' => 1669,
  '_व' => 1609,
  'भ' => 1562,
  '्य' => 1555,
  'ान' => 1528,
  '_का' => 1525,
  '_ह' => 1487,
  'ध' => 1448,

... [truncated, 9955 more lines] ...

<?php $ngrams = array (
  '_' => 52227,
  'ա' => 29432,
  'ն' => 16556,
  'ո' => 13552,
  'ր' => 13538,
  'ի' => 11445,
  'ե' => 10974,
  'ւ' => 7803,
  'ու' => 7312,
  'ան' => 6877,
  'կ' => 6368,
  'ն_' => 5961,
  'տ' => 5791,
  'մ' => 5728,
  'յ' => 5463,
  'ս' => 5183,
  'եր' => 3861,
  'ի_' => 3781,
  'ար' => 3760,
  'լ' => 3616,
  'վ' => 3446,
  'թ' => 3190,
  'հ' => 3128,
  'գ' => 3114,
  'ան_' => 2990,
  'դ' => 2845,
  'կա' => 2733,
  'ակ' => 2558,
  'ր_' => 2544,
  'բ' => 2345,
  '_ա' => 2332,
  'րա' => 2250,
  'ք' => 2236,
  'նե' => 2122,
  'մա' => 2076,
  'ց' => 2055,
  '_հ' => 2016,
  'ին' => 2004,
  'պ' => 1984,
  'ղ' => 1971,
  'ռ' => 1884,
  'այ' => 1875,
  'ւն' => 1844,
  'նա' => 1825,
  'ուն' => 1777,
  'յո' => 1703,
  'յա' => 1694,
  'տա' => 1663,
  'հա' => 1653,

... [truncated, 9955 more lines] ...

<?php $ngrams = array (
  '_' => 3571554,
  'a' => 1174179,
  'i' => 1131289,
  'e' => 993963,
  'o' => 913117,
  'r' => 699782,
  'n' => 687783,
  't' => 616498,
  'l' => 597504,
  's' => 487668,
  'c' => 438391,
  'd' => 335508,
  'a_' => 327328,
  'm' => 315874,
  'e_' => 301142,
  'o_' => 296455,
  'u' => 262467,
  'i_' => 255910,
  'p' => 235537,
  'g' => 230982,
  'an' => 166517,
  '_d' => 156150,
  'er' => 153482,
  'on' => 146754,
  'b' => 144953,
  'h' => 137153,
  '_c' => 136405,
  'in' => 130729,
  'f' => 130267,
  'v' => 129005,
  'ri' => 128878,
  '_s' => 127184,
  'ar' => 121572,
  'al' => 115668,
  'ra' => 114989,
  'ia' => 113782,
  'to' => 110752,
  'io' => 109940,
  'li' => 109093,
  're' => 108824,
  'di' => 107532,
  'or' => 102645,
  'z' => 102634,
  '_p' => 102554,
  '_a' => 100760,
  'ta' => 98933,
  'el' => 98506,
  'ti' => 98040,
  '_m' => 98014,

... [truncated, 9955 more lines] ...

<?php $ngrams = array (
  '_' => 1729277,
  'ー' => 169851,
  'ン' => 132357,
  'ス' => 76569,
  'ル' => 73419,
  'の' => 65285,
  'イ' => 63989,
  'ト' => 58894,
  'ラ' => 54385,
  'リ' => 53396,
  'ア' => 51931,
  'ッ' => 48755,
  'ク' => 47330,
  'い' => 36677,
  'ー_' => 35736,
  'ド' => 35634,
  'ン_' => 34410,
  'シ' => 32884,
  'フ' => 31120,
  'ロ' => 30726,
  'ん' => 30436,
  'タ' => 30083,
  'レ' => 29466,
  'マ' => 29342,
  'ジ' => 28571,
  'カ' => 28128,
  '・' => 28001,
  'か' => 26165,
  'ィ' => 24392,
  'な' => 23909,
  'し' => 23824,
  'う' => 23107,
  'テ' => 22918,
  'ウ' => 22097,
  'た' => 21810,
  'バ' => 21682,
  'と' => 20979,
  'ル_' => 20911,
  'ス_' => 20887,
  'り' => 20651,
  'コ' => 20535,
  'グ' => 20491,
  '_ア' => 20274,
  'エ' => 20221,
  'る' => 20081,
  'オ' => 20024,
  'ブ' => 19423,
  'ト_' => 19350,
  'ニ' => 19302,

... [truncated, 9955 more lines] ...

<?php $ngrams = array (
  '_' => 112872,
  'ი' => 58803,
  'ა' => 54517,
  'ე' => 36572,
  'რ' => 27597,
  'ს' => 25644,
  'ო' => 22456,
  'ი_' => 22376,
  'ლ' => 20445,
  'ნ' => 18778,
  'მ' => 16379,
  'ბ' => 15194,
  'ვ' => 12844,
  'ა_' => 11999,
  'უ' => 11410,
  'დ' => 11197,
  'ის' => 10365,
  'ს_' => 10309,
  'ტ' => 10260,
  'ლი' => 8686,
  'კ' => 8440,
  'თ' => 8090,
  'ებ' => 7950,
  'ის_' => 7894,
  'გ' => 7534,
  'არ' => 7180,
  'რი' => 7108,
  'ბი' => 6432,
  '_მ' => 6045,
  'ან' => 5950,
  '_ს' => 5851,
  'ქ' => 5186,
  'ელ' => 5124,
  'ლი_' => 5032,
  'ხ' => 4952,
  'ნი' => 4949,
  'სა' => 4902,
  'ები' => 4887,
  'შ' => 4577,
  'ფ' => 4426,
  'ია' => 4387,
  'რა' => 4325,
  'ერ' => 4199,
  'ზ' => 4050,
  'პ' => 4024,
  'ბა' => 3973,
  '_ა' => 3954,
  'ბი_' => 3890,
  'და' => 3872,

... [truncated, 9955 more lines] ...

<?php $ngrams = array (
  '_' => 574565,
  '이' => 21079,
  '스' => 20061,
  '리' => 16279,
  '의' => 13115,
  '사' => 12036,
  '아' => 11210,
  '대' => 10214,
  '기' => 10073,
  '의_' => 9763,
  '시' => 9613,
  '국' => 9603,
  '라' => 8965,
  '지' => 8947,
  '트' => 8502,
  '스_' => 8090,
  '도' => 7837,
  '드' => 7746,
  '자' => 7739,
  '인' => 7727,
  '전' => 7718,
  '로' => 7607,
  '수' => 7258,
  '제' => 7169,
  '정' => 7097,
  '마' => 7067,
  '가' => 6891,
  '성' => 6675,
  '화' => 6372,
  '구' => 6015,
  '미' => 5953,
  '나' => 5792,
  '한' => 5775,
  '주' => 5747,
  '고' => 5653,
  '일' => 5586,
  '동' => 5584,
  '오' => 5539,
  '프' => 5314,
  '조' => 5205,
  '원' => 5146,
  '_이' => 5045,
  '유' => 5021,
  '산' => 5006,
  '공' => 4988,
  '소' => 4880,
  '리_' => 4878,
  '학' => 4852,
  '르' => 4839,

... [truncated, 9955 more lines] ...

<?php $ngrams = array (
  '_' => 3138412,
  'e' => 1425888,
  'n' => 792844,
  'a' => 755167,
  'i' => 652962,
  'r' => 651881,
  'o' => 562623,
  't' => 536609,
  's' => 497079,
  'l' => 438862,
  'd' => 385272,
  'n_' => 300214,
  'e_' => 282746,
  'en' => 267881,
  'u' => 246015,
  'g' => 242719,
  'm' => 235033,
  'er' => 234658,
  'h' => 231666,
  'c' => 216614,
  'k' => 208484,
  'an' => 178583,
  'v' => 168485,
  'p' => 167694,
  'en_' => 157325,
  'b' => 155435,
  'de' => 153761,
  's_' => 136929,
  'in' => 130614,
  't_' => 127287,
  'te' => 117832,
  'el' => 108008,
  'w' => 105894,
  'r_' => 104756,
  'ie' => 102652,
  'f' => 97790,
  '_d' => 96591,
  'j' => 96098,
  'st' => 94277,
  'ch' => 88400,
  '_v' => 87383,
  'nd' => 84697,
  'ar' => 83277,
  'ge' => 80712,
  're' => 80064,
  'on' => 79175,
  'ri' => 78266,
  'le' => 77303,
  'or' => 76242,

... [truncated, 9955 more lines] ...

<?php $ngrams = array (
  '_' => 2495513,
  'a' => 804957,
  'i' => 618260,
  'e' => 613233,
  'o' => 577606,
  'r' => 452488,
  'n' => 438617,
  's' => 385724,
  'k' => 325212,
  't' => 322787,
  'z' => 300082,
  'c' => 289690,
  'w' => 281400,
  'l' => 276403,
  'a_' => 241988,
  'y' => 234557,
  'd' => 215869,
  'm' => 208609,
  'p' => 205724,
  'u' => 190191,
  'e_' => 144214,
  'ie' => 142904,
  'g' => 127849,
  'j' => 127497,
  'b' => 119985,
  '_p' => 112076,
  'h' => 105940,
  'ni' => 98818,
  'i_' => 96126,
  'y_' => 94581,
  '_s' => 92257,
  'an' => 86731,
  '_w' => 82299,
  'er' => 78945,
  'ow' => 77981,
  'na' => 76550,
  'ar' => 74784,
  'ki' => 73652,
  'st' => 71416,
  'ł' => 70592,
  'ra' => 68488,
  'ro' => 67893,
  '_k' => 67460,
  'o_' => 65574,
  'ka' => 65365,
  'ia' => 64940,
  '_m' => 64405,
  'cz' => 62474,
  'sk' => 61584,

... [truncated, 9955 more lines] ...

<?php $ngrams = array (
  '_' => 6442488,
  'a' => 2138400,
  'o' => 1736777,
  'e' => 1712529,
  'i' => 1383749,
  'r' => 1154468,
  's' => 1139428,
  'n' => 933191,
  'd' => 838982,
  't' => 787349,
  'o_' => 686363,
  'c' => 685082,
  'l' => 666478,
  'a_' => 663608,
  'm' => 613492,
  'u' => 591398,
  'e_' => 492505,
  's_' => 485779,
  '_d' => 418514,
  'p' => 391717,
  'g' => 312468,
  'de' => 293809,
  'ra' => 248893,
  'b' => 237547,
  '_c' => 222524,
  'f' => 219020,
  '_a' => 217810,
  'es' => 214092,
  'an' => 209631,
  'os' => 205905,
  'de_' => 204599,
  'v' => 201219,
  'do' => 200140,
  '_p' => 196647,
  'as' => 196079,
  '_de' => 195263,
  'er' => 189122,
  '_e' => 189097,
  'ca' => 188147,
  'h' => 183763,
  'ri' => 178832,
  'or' => 178790,
  'en' => 177890,
  'ar' => 176299,
  'ia' => 172417,
  'da' => 171940,
  'co' => 171087,
  're' => 168477,
  '_de_' => 164352,

... [truncated, 9955 more lines] ...

<?php $ngrams = array (
  '_' => 6448251,
  'а' => 1974973,
  'о' => 1873999,
  'и' => 1763740,
  'е' => 1622540,
  'н' => 1410450,
  'р' => 1331843,
  'с' => 1091424,
  'т' => 1073939,
  'к' => 966657,
  'л' => 923301,
  'в' => 818665,
  'м' => 596283,
  'д' => 558957,
  'п' => 480051,
  'у' => 448980,
  'а_' => 436120,
  'я' => 401016,
  'г' => 375723,
  'й' => 355697,
  'ы' => 332296,
  'б' => 321167,
  'ь' => 307862,
  'з' => 285323,
  'я_' => 283022,
  'е_' => 256177,
  'и_' => 255076,
  'ст' => 251378,
  '_с' => 249248,
  '_п' => 248941,
  'ов' => 246649,
  'ан' => 244206,
  'ра' => 242974,
  'й_' => 240758,
  'ен' => 234624,
  'ер' => 232973,
  'на' => 230514,
  'ро' => 227977,
  'ч' => 223748,
  'ни' => 223272,
  'ка' => 215071,
  'ко' => 209391,
  '_к' => 205765,
  'ор' => 194427,
  'ск' => 191445,
  '_в' => 186557,
  'ин' => 184829,
  'о_' => 182781,
  'но' => 174688,

... [truncated, 9955 more lines] ...

<?php $ngrams = array (
  '_' => 861062,
  'a' => 259534,
  'e' => 247217,
  'r' => 224201,
  'n' => 215754,
  'i' => 184306,
  's' => 183592,
  't' => 173841,
  'l' => 155672,
  'o' => 145578,
  'd' => 96402,
  'k' => 93604,
  'm' => 85598,
  'g' => 82358,
  'u' => 68315,
  'n_' => 55924,
  'er' => 55501,
  'p' => 53927,
  'h' => 52436,
  'a_' => 50593,
  'b' => 50026,
  'v' => 49463,
  'c' => 45515,
  'r_' => 45418,
  'f' => 44546,
  'an' => 42766,
  'en' => 42309,
  'in' => 37895,
  'ar' => 37447,
  'e_' => 36718,
  '_s' => 36432,
  's_' => 35584,
  't_' => 32954,
  'st' => 32764,
  'y' => 30699,
  'ä' => 28924,
  'ri' => 27564,
  'on' => 27129,
  'te' => 26972,
  'la' => 24843,
  'ra' => 24167,
  'or' => 23971,
  'de' => 23416,
  'ö' => 23256,
  're' => 23090,
  'j' => 22817,
  'ng' => 22739,
  'al' => 22223,
  'er_' => 22131,

... [truncated, 9955 more lines] ...