UNPKG

pii-paladin

Version:

A Node.js package to censor PII in a string using a hybrid NER and Regex approach.

2,045 lines (2,044 loc) 844 kB
{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "[PAD]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 100, "content": "[UNK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 101, "content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 102, "content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 103, "content": "[MASK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true } ], "normalizer": { "type": "BertNormalizer", "clean_text": true, "handle_chinese_chars": true, "strip_accents": null, "lowercase": false }, "pre_tokenizer": { "type": "BertPreTokenizer" }, "post_processor": { "type": "TemplateProcessing", "single": [ { "SpecialToken": { "id": "[CLS]", "type_id": 0 } }, { "Sequence": { "id": "A", "type_id": 0 } }, { "SpecialToken": { "id": "[SEP]", "type_id": 0 } } ], "pair": [ { "SpecialToken": { "id": "[CLS]", "type_id": 0 } }, { "Sequence": { "id": "A", "type_id": 0 } }, { "SpecialToken": { "id": "[SEP]", "type_id": 0 } }, { "Sequence": { "id": "B", "type_id": 1 } }, { "SpecialToken": { "id": "[SEP]", "type_id": 1 } } ], "special_tokens": { "[CLS]": { "id": "[CLS]", "ids": [101], "tokens": ["[CLS]"] }, "[SEP]": { "id": "[SEP]", "ids": [102], "tokens": ["[SEP]"] } } }, "decoder": { "type": "WordPiece", "prefix": "##", "cleanup": true }, "model": { "type": "WordPiece", "unk_token": "[UNK]", "continuing_subword_prefix": "##", "max_input_chars_per_word": 100, "vocab": { "[PAD]": 0, "[unused1]": 1, "[unused2]": 2, "[unused3]": 3, "[unused4]": 4, "[unused5]": 5, "[unused6]": 6, "[unused7]": 7, "[unused8]": 8, "[unused9]": 9, "[unused10]": 10, "[unused11]": 11, "[unused12]": 12, "[unused13]": 13, "[unused14]": 14, "[unused15]": 15, "[unused16]": 16, "[unused17]": 17, "[unused18]": 18, "[unused19]": 19, "[unused20]": 20, "[unused21]": 21, "[unused22]": 22, "[unused23]": 23, "[unused24]": 24, "[unused25]": 25, "[unused26]": 26, "[unused27]": 27, "[unused28]": 28, "[unused29]": 29, "[unused30]": 30, "[unused31]": 31, "[unused32]": 32, "[unused33]": 33, "[unused34]": 34, "[unused35]": 35, "[unused36]": 36, "[unused37]": 37, "[unused38]": 38, "[unused39]": 39, "[unused40]": 40, "[unused41]": 41, "[unused42]": 42, "[unused43]": 43, "[unused44]": 44, "[unused45]": 45, "[unused46]": 46, "[unused47]": 47, "[unused48]": 48, "[unused49]": 49, "[unused50]": 50, "[unused51]": 51, "[unused52]": 52, "[unused53]": 53, "[unused54]": 54, "[unused55]": 55, "[unused56]": 56, "[unused57]": 57, "[unused58]": 58, "[unused59]": 59, "[unused60]": 60, "[unused61]": 61, "[unused62]": 62, "[unused63]": 63, "[unused64]": 64, "[unused65]": 65, "[unused66]": 66, "[unused67]": 67, "[unused68]": 68, "[unused69]": 69, "[unused70]": 70, "[unused71]": 71, "[unused72]": 72, "[unused73]": 73, "[unused74]": 74, "[unused75]": 75, "[unused76]": 76, "[unused77]": 77, "[unused78]": 78, "[unused79]": 79, "[unused80]": 80, "[unused81]": 81, "[unused82]": 82, "[unused83]": 83, "[unused84]": 84, "[unused85]": 85, "[unused86]": 86, "[unused87]": 87, "[unused88]": 88, "[unused89]": 89, "[unused90]": 90, "[unused91]": 91, "[unused92]": 92, "[unused93]": 93, "[unused94]": 94, "[unused95]": 95, "[unused96]": 96, "[unused97]": 97, "[unused98]": 98, "[unused99]": 99, "[UNK]": 100, "[CLS]": 101, "[SEP]": 102, "[MASK]": 103, "[unused100]": 104, "[unused101]": 105, "!": 106, "\"": 107, "#": 108, "$": 109, "%": 110, "&": 111, "'": 112, "(": 113, ")": 114, "*": 115, "+": 116, ",": 117, "-": 118, ".": 119, "/": 120, "0": 121, "1": 122, "2": 123, "3": 124, "4": 125, "5": 126, "6": 127, "7": 128, "8": 129, "9": 130, ":": 131, ";": 132, "<": 133, "=": 134, ">": 135, "?": 136, "@": 137, "A": 138, "B": 139, "C": 140, "D": 141, "E": 142, "F": 143, "G": 144, "H": 145, "I": 146, "J": 147, "K": 148, "L": 149, "M": 150, "N": 151, "O": 152, "P": 153, "Q": 154, "R": 155, "S": 156, "T": 157, "U": 158, "V": 159, "W": 160, "X": 161, "Y": 162, "Z": 163, "[": 164, "\\": 165, "]": 166, "^": 167, "_": 168, "`": 169, "a": 170, "b": 171, "c": 172, "d": 173, "e": 174, "f": 175, "g": 176, "h": 177, "i": 178, "j": 179, "k": 180, "l": 181, "m": 182, "n": 183, "o": 184, "p": 185, "q": 186, "r": 187, "s": 188, "t": 189, "u": 190, "v": 191, "w": 192, "x": 193, "y": 194, "z": 195, "{": 196, "|": 197, "}": 198, "~": 199, "¡": 200, "¢": 201, "£": 202, "¥": 203, "§": 204, "¨": 205, "©": 206, "ª": 207, "«": 208, "¬": 209, "®": 210, "°": 211, "±": 212, "²": 213, "³": 214, "´": 215, "µ": 216, "¶": 217, "·": 218, "¹": 219, "º": 220, "»": 221, "¼": 222, "½": 223, "¾": 224, "¿": 225, "À": 226, "Á": 227, "Â": 228, "Ä": 229, "Å": 230, "Æ": 231, "Ç": 232, "È": 233, "É": 234, "Í": 235, "Î": 236, "Ñ": 237, "Ó": 238, "Ö": 239, "×": 240, "Ø": 241, "Ú": 242, "Ü": 243, "Þ": 244, "ß": 245, "à": 246, "á": 247, "â": 248, "ã": 249, "ä": 250, "å": 251, "æ": 252, "ç": 253, "è": 254, "é": 255, "ê": 256, "ë": 257, "ì": 258, "í": 259, "î": 260, "ï": 261, "ð": 262, "ñ": 263, "ò": 264, "ó": 265, "ô": 266, "õ": 267, "ö": 268, "÷": 269, "ø": 270, "ù": 271, "ú": 272, "û": 273, "ü": 274, "ý": 275, "þ": 276, "ÿ": 277, "Ā": 278, "ā": 279, "ă": 280, "ą": 281, "Ć": 282, "ć": 283, "Č": 284, "č": 285, "ď": 286, "Đ": 287, "đ": 288, "ē": 289, "ė": 290, "ę": 291, "ě": 292, "ğ": 293, "ġ": 294, "Ħ": 295, "ħ": 296, "ĩ": 297, "Ī": 298, "ī": 299, "İ": 300, "ı": 301, "ļ": 302, "Ľ": 303, "ľ": 304, "Ł": 305, "ł": 306, "ń": 307, "ņ": 308, "ň": 309, "ŋ": 310, "Ō": 311, "ō": 312, "ŏ": 313, "ő": 314, "Œ": 315, "œ": 316, "ř": 317, "Ś": 318, "ś": 319, "Ş": 320, "ş": 321, "Š": 322, "š": 323, "Ţ": 324, "ţ": 325, "ť": 326, "ũ": 327, "ū": 328, "ŭ": 329, "ů": 330, "ű": 331, "ų": 332, "ŵ": 333, "ŷ": 334, "ź": 335, "Ż": 336, "ż": 337, "Ž": 338, "ž": 339, "Ə": 340, "ƒ": 341, "ơ": 342, "ư": 343, "ǎ": 344, "ǐ": 345, "ǒ": 346, "ǔ": 347, "ǫ": 348, "Ș": 349, "ș": 350, "Ț": 351, "ț": 352, "ɐ": 353, "ɑ": 354, "ɔ": 355, "ɕ": 356, "ə": 357, "ɛ": 358, "ɡ": 359, "ɣ": 360, "ɨ": 361, "ɪ": 362, "ɲ": 363, "ɾ": 364, "ʀ": 365, "ʁ": 366, "ʂ": 367, "ʃ": 368, "ʊ": 369, "ʋ": 370, "ʌ": 371, "ʐ": 372, "ʑ": 373, "ʒ": 374, "ʔ": 375, "ʰ": 376, "ʲ": 377, "ʳ": 378, "ʷ": 379, "ʻ": 380, "ʼ": 381, "ʾ": 382, "ʿ": 383, "ˈ": 384, "ː": 385, "ˡ": 386, "ˢ": 387, "ˣ": 388, "́": 389, "̃": 390, "̍": 391, "̯": 392, "͡": 393, "Α": 394, "Β": 395, "Γ": 396, "Δ": 397, "Ε": 398, "Η": 399, "Θ": 400, "Ι": 401, "Κ": 402, "Λ": 403, "Μ": 404, "Ν": 405, "Ο": 406, "Π": 407, "Σ": 408, "Τ": 409, "Φ": 410, "Χ": 411, "Ψ": 412, "Ω": 413, "ά": 414, "έ": 415, "ή": 416, "ί": 417, "α": 418, "β": 419, "γ": 420, "δ": 421, "ε": 422, "ζ": 423, "η": 424, "θ": 425, "ι": 426, "κ": 427, "λ": 428, "μ": 429, "ν": 430, "ξ": 431, "ο": 432, "π": 433, "ρ": 434, "ς": 435, "σ": 436, "τ": 437, "υ": 438, "φ": 439, "χ": 440, "ψ": 441, "ω": 442, "ό": 443, "ύ": 444, "ώ": 445, "І": 446, "Ј": 447, "А": 448, "Б": 449, "В": 450, "Г": 451, "Д": 452, "Е": 453, "Ж": 454, "З": 455, "И": 456, "К": 457, "Л": 458, "М": 459, "Н": 460, "О": 461, "П": 462, "Р": 463, "С": 464, "Т": 465, "У": 466, "Ф": 467, "Х": 468, "Ц": 469, "Ч": 470, "Ш": 471, "Э": 472, "Ю": 473, "Я": 474, "а": 475, "б": 476, "в": 477, "г": 478, "д": 479, "е": 480, "ж": 481, "з": 482, "и": 483, "й": 484, "к": 485, "л": 486, "м": 487, "н": 488, "о": 489, "п": 490, "р": 491, "с": 492, "т": 493, "у": 494, "ф": 495, "х": 496, "ц": 497, "ч": 498, "ш": 499, "щ": 500, "ъ": 501, "ы": 502, "ь": 503, "э": 504, "ю": 505, "я": 506, "ё": 507, "і": 508, "ї": 509, "ј": 510, "њ": 511, "ћ": 512, "Ա": 513, "Հ": 514, "ա": 515, "ե": 516, "ի": 517, "կ": 518, "մ": 519, "յ": 520, "ն": 521, "ո": 522, "ս": 523, "տ": 524, "ր": 525, "ւ": 526, "ְ": 527, "ִ": 528, "ֵ": 529, "ֶ": 530, "ַ": 531, "ָ": 532, "ֹ": 533, "ּ": 534, "א": 535, "ב": 536, "ג": 537, "ד": 538, "ה": 539, "ו": 540, "ז": 541, "ח": 542, "ט": 543, "י": 544, "כ": 545, "ל": 546, "ם": 547, "מ": 548, "ן": 549, "נ": 550, "ס": 551, "ע": 552, "פ": 553, "צ": 554, "ק": 555, "ר": 556, "ש": 557, "ת": 558, "،": 559, "ء": 560, "آ": 561, "أ": 562, "إ": 563, "ئ": 564, "ا": 565, "ب": 566, "ة": 567, "ت": 568, "ث": 569, "ج": 570, "ح": 571, "خ": 572, "د": 573, "ذ": 574, "ر": 575, "ز": 576, "س": 577, "ش": 578, "ص": 579, "ض": 580, "ط": 581, "ظ": 582, "ع": 583, "غ": 584, "ف": 585, "ق": 586, "ك": 587, "ل": 588, "م": 589, "ن": 590, "ه": 591, "و": 592, "ى": 593, "ي": 594, "َ": 595, "ِ": 596, "ٹ": 597, "پ": 598, "چ": 599, "ک": 600, "گ": 601, "ہ": 602, "ی": 603, "ے": 604, "ं": 605, "आ": 606, "क": 607, "ग": 608, "च": 609, "ज": 610, "ण": 611, "त": 612, "द": 613, "ध": 614, "न": 615, "प": 616, "ब": 617, "भ": 618, "म": 619, "य": 620, "र": 621, "ल": 622, "व": 623, "श": 624, "ष": 625, "स": 626, "ह": 627, "ा": 628, "ि": 629, "ी": 630, "ु": 631, "े": 632, "ो": 633, "्": 634, "।": 635, "॥": 636, "আ": 637, "ই": 638, "এ": 639, "ও": 640, "ক": 641, "খ": 642, "গ": 643, "চ": 644, "ছ": 645, "জ": 646, "ট": 647, "ত": 648, "থ": 649, "দ": 650, "ধ": 651, "ন": 652, "প": 653, "ব": 654, "ম": 655, "য": 656, "র": 657, "ল": 658, "শ": 659, "স": 660, "হ": 661, "়": 662, "া": 663, "ি": 664, "ী": 665, "ু": 666, "ে": 667, "ো": 668, "্": 669, "য়": 670, "க": 671, "த": 672, "ப": 673, "ம": 674, "ய": 675, "ர": 676, "ல": 677, "வ": 678, "ா": 679, "ி": 680, "ு": 681, "்": 682, "ร": 683, "་": 684, "ག": 685, "ང": 686, "ད": 687, "ན": 688, "བ": 689, "མ": 690, "ར": 691, "ལ": 692, "ས": 693, "ི": 694, "ུ": 695, "ེ": 696, "ོ": 697, "ა": 698, "ე": 699, "ი": 700, "ლ": 701, "ნ": 702, "ო": 703, "რ": 704, "ს": 705, "ᴬ": 706, "ᴵ": 707, "ᵀ": 708, "ᵃ": 709, "ᵇ": 710, "ᵈ": 711, "ᵉ": 712, "ᵍ": 713, "ᵏ": 714, "ᵐ": 715, "ᵒ": 716, "ᵖ": 717, "ᵗ": 718, "ᵘ": 719, "ᵢ": 720, "ᵣ": 721, "ᵤ": 722, "ᵥ": 723, "ᶜ": 724, "ᶠ": 725, "ḍ": 726, "Ḥ": 727, "ḥ": 728, "Ḩ": 729, "ḩ": 730, "ḳ": 731, "ṃ": 732, "ṅ": 733, "ṇ": 734, "ṛ": 735, "ṣ": 736, "ṭ": 737, "ạ": 738, "ả": 739, "ấ": 740, "ầ": 741, "ẩ": 742, "ậ": 743, "ắ": 744, "ế": 745, "ề": 746, "ể": 747, "ễ": 748, "ệ": 749, "ị": 750, "ọ": 751, "ố": 752, "ồ": 753, "ổ": 754, "ộ": 755, "ớ": 756, "ờ": 757, "ợ": 758, "ụ": 759, "ủ": 760, "ứ": 761, "ừ": 762, "ử": 763, "ữ": 764, "ự": 765, "ỳ": 766, "ỹ": 767, "ἀ": 768, "ἐ": 769, "ὁ": 770, "ὐ": 771, "ὰ": 772, "ὶ": 773, "ὸ": 774, "ῆ": 775, "ῖ": 776, "ῦ": 777, "ῶ": 778, "‐": 779, "‑": 780, "‒": 781, "–": 782, "—": 783, "―": 784, "‖": 785, "‘": 786, "’": 787, "‚": 788, "“": 789, "”": 790, "„": 791, "†": 792, "‡": 793, "•": 794, "…": 795, "‰": 796, "′": 797, "″": 798, "⁄": 799, "⁰": 800, "ⁱ": 801, "⁴": 802, "⁵": 803, "⁶": 804, "⁷": 805, "⁸": 806, "⁹": 807, "⁺": 808, "⁻": 809, "ⁿ": 810, "₀": 811, "₁": 812, "₂": 813, "₃": 814, "₄": 815, "₅": 816, "₆": 817, "₇": 818, "₈": 819, "₉": 820, "₊": 821, "₍": 822, "₎": 823, "ₐ": 824, "ₑ": 825, "ₒ": 826, "ₓ": 827, "ₕ": 828, "ₖ": 829, "ₘ": 830, "ₙ": 831, "ₚ": 832, "ₛ": 833, "ₜ": 834, "₤": 835, "€": 836, "₱": 837, "₹": 838, "ℓ": 839, "№": 840, "ℝ": 841, "⅓": 842, "←": 843, "↑": 844, "→": 845, "↔": 846, "⇌": 847, "⇒": 848, "∂": 849, "∈": 850, "−": 851, "∗": 852, "∘": 853, "√": 854, "∞": 855, "∧": 856, "∨": 857, "∩": 858, "∪": 859, "≈": 860, "≠": 861, "≡": 862, "≤": 863, "≥": 864, "⊂": 865, "⊆": 866, "⊕": 867, "⋅": 868, "─": 869, "│": 870, "■": 871, "●": 872, "★": 873, "☆": 874, "☉": 875, "♠": 876, "♣": 877, "♥": 878, "♦": 879, "♭": 880, "♯": 881, "⟨": 882, "⟩": 883, "ⱼ": 884, "、": 885, "。": 886, "《": 887, "》": 888, "「": 889, "」": 890, "『": 891, "』": 892, "〜": 893, "い": 894, "う": 895, "え": 896, "お": 897, "か": 898, "き": 899, "く": 900, "け": 901, "こ": 902, "さ": 903, "し": 904, "す": 905, "せ": 906, "そ": 907, "た": 908, "ち": 909, "つ": 910, "て": 911, "と": 912, "な": 913, "に": 914, "の": 915, "は": 916, "ひ": 917, "ま": 918, "み": 919, "む": 920, "め": 921, "も": 922, "や": 923, "ゆ": 924, "よ": 925, "ら": 926, "り": 927, "る": 928, "れ": 929, "ん": 930, "ア": 931, "ィ": 932, "イ": 933, "ウ": 934, "エ": 935, "オ": 936, "カ": 937, "ガ": 938, "キ": 939, "ク": 940, "グ": 941, "コ": 942, "サ": 943, "シ": 944, "ジ": 945, "ス": 946, "ズ": 947, "タ": 948, "ダ": 949, "ッ": 950, "テ": 951, "デ": 952, "ト": 953, "ド": 954, "ナ": 955, "ニ": 956, "ハ": 957, "バ": 958, "パ": 959, "フ": 960, "ブ": 961, "プ": 962, "マ": 963, "ミ": 964, "ム": 965, "ャ": 966, "ュ": 967, "ラ": 968, "リ": 969, "ル": 970, "レ": 971, "ロ": 972, "ン": 973, "・": 974, "ー": 975, "一": 976, "三": 977, "上": 978, "下": 979, "中": 980, "事": 981, "二": 982, "井": 983, "京": 984, "人": 985, "亻": 986, "仁": 987, "佐": 988, "侍": 989, "光": 990, "公": 991, "力": 992, "北": 993, "十": 994, "南": 995, "原": 996, "口": 997, "史": 998, "司": 999, "吉": 1000, "同": 1001, "和": 1002, "囗": 1003, "国": 1004, "國": 1005, "土": 1006, "城": 1007, "士": 1008, "大": 1009, "天": 1010, "太": 1011, "夫": 1012, "女": 1013, "子": 1014, "宀": 1015, "安": 1016, "宮": 1017, "宿": 1018, "小": 1019, "尚": 1020, "山": 1021, "島": 1022, "川": 1023, "州": 1024, "平": 1025, "年": 1026, "心": 1027, "愛": 1028, "戸": 1029, "文": 1030, "新": 1031, "方": 1032, "日": 1033, "明": 1034, "星": 1035, "書": 1036, "月": 1037, "木": 1038, "本": 1039, "李": 1040, "村": 1041, "東": 1042, "松": 1043, "林": 1044, "正": 1045, "武": 1046, "氏": 1047, "水": 1048, "氵": 1049, "江": 1050, "河": 1051, "海": 1052, "版": 1053, "犬": 1054, "王": 1055, "生": 1056, "田": 1057, "白": 1058, "皇": 1059, "省": 1060, "真": 1061, "石": 1062, "社": 1063, "神": 1064, "竹": 1065, "美": 1066, "義": 1067, "花": 1068, "藤": 1069, "西": 1070, "谷": 1071, "車": 1072, "辶": 1073, "道": 1074, "郎": 1075, "郡": 1076, "部": 1077, "野": 1078, "金": 1079, "長": 1080, "門": 1081, "陽": 1082, "青": 1083, "食": 1084, "馬": 1085, "高": 1086, "龍": 1087, "龸": 1088, "사": 1089, "씨": 1090, "의": 1091, "이": 1092, "한": 1093, "fi": 1094, "fl": 1095, "!": 1096, "(": 1097, ")": 1098, ",": 1099, "-": 1100, "/": 1101, ":": 1102, "the": 1103, "of": 1104, "and": 1105, "to": 1106, "in": 1107, "was": 1108, "The": 1109, "is": 1110, "for": 1111, "as": 1112, "on": 1113, "with": 1114, "that": 1115, "##s": 1116, "his": 1117, "by": 1118, "he": 1119, "at": 1120, "from": 1121, "it": 1122, "her": 1123, "He": 1124, "had": 1125, "an": 1126, "were": 1127, "you": 1128, "be": 1129, "In": 1130, "she": 1131, "are": 1132, "but": 1133, "which": 1134, "It": 1135, "not": 1136, "or": 1137, "have": 1138, "my": 1139, "him": 1140, "one": 1141, "this": 1142, "me": 1143, "has": 1144, "also": 1145, "up": 1146, "their": 1147, "first": 1148, "out": 1149, "who": 1150, "been": 1151, "they": 1152, "She": 1153, "into": 1154, "all": 1155, "would": 1156, "its": 1157, "##ing": 1158, "time": 1159, "two": 1160, "##a": 1161, "##e": 1162, "said": 1163, "about": 1164, "when": 1165, "over": 1166, "more": 1167, "other": 1168, "can": 1169, "after": 1170, "back": 1171, "them": 1172, "then": 1173, "##ed": 1174, "there": 1175, "like": 1176, "so": 1177, "only": 1178, "##n": 1179, "could": 1180, "##d": 1181, "##i": 1182, "##y": 1183, "what": 1184, "no": 1185, "##o": 1186, "where": 1187, "This": 1188, "made": 1189, "than": 1190, "if": 1191, "You": 1192, "##ly": 1193, "through": 1194, "we": 1195, "before": 1196, "##r": 1197, "just": 1198, "some": 1199, "##er": 1200, "years": 1201, "do": 1202, "New": 1203, "##t": 1204, "down": 1205, "between": 1206, "new": 1207, "now": 1208, "will": 1209, "three": 1210, "most": 1211, "On": 1212, "around": 1213, "year": 1214, "used": 1215, "such": 1216, "being": 1217, "well": 1218, "during": 1219, "They": 1220, "know": 1221, "against": 1222, "under": 1223, "later": 1224, "did": 1225, "part": 1226, "known": 1227, "off": 1228, "while": 1229, "His": 1230, "re": 1231, "...": 1232, "##l": 1233, "people": 1234, "until": 1235, "way": 1236, "American": 1237, "didn": 1238, "University": 1239, "your": 1240, "both": 1241, "many": 1242, "get": 1243, "United": 1244, "became": 1245, "head": 1246, "There": 1247, "second": 1248, "As": 1249, "work": 1250, "any": 1251, "But": 1252, "still": 1253, "again": 1254, "born": 1255, "even": 1256, "eyes": 1257, "After": 1258, "including": 1259, "de": 1260, "took": 1261, "And": 1262, "long": 1263, "team": 1264, "season": 1265, "family": 1266, "see": 1267, "right": 1268, "same": 1269, "called": 1270, "name": 1271, "because": 1272, "film": 1273, "don": 1274, "10": 1275, "found": 1276, "much": 1277, "school": 1278, "##es": 1279, "going": 1280, "won": 1281, "place": 1282, "away": 1283, "We": 1284, "day": 1285, "left": 1286, "John": 1287, "000": 1288, "hand": 1289, "since": 1290, "World": 1291, "these": 1292, "how": 1293, "make": 1294, "number": 1295, "each": 1296, "life": 1297, "area": 1298, "man": 1299, "four": 1300, "go": 1301, "No": 1302, "here": 1303, "very": 1304, "National": 1305, "##m": 1306, "played": 1307, "released": 1308, "never": 1309, "began": 1310, "States": 1311, "album": 1312, "home": 1313, "last": 1314, "too": 1315, "held": 1316, "several": 1317, "May": 1318, "own": 1319, "##on": 1320, "take": 1321, "end": 1322, "School": 1323, "##h": 1324, "ll": 1325, "series": 1326, "What": 1327, "want": 1328, "use": 1329, "another": 1330, "city": 1331, "When": 1332, "2010": 1333, "side": 1334, "At": 1335, "may": 1336, "That": 1337, "came": 1338, "face": 1339, "June": 1340, "think": 1341, "game": 1342, "those": 1343, "high": 1344, "March": 1345, "early": 1346, "September": 1347, "##al": 1348, "2011": 1349, "looked": 1350, "July": 1351, "state": 1352, "small": 1353, "thought": 1354, "went": 1355, "January": 1356, "October": 1357, "##u": 1358, "based": 1359, "August": 1360, "##us": 1361, "world": 1362, "good": 1363, "April": 1364, "York": 1365, "us": 1366, "12": 1367, "2012": 1368, "2008": 1369, "For": 1370, "2009": 1371, "group": 1372, "along": 1373, "few": 1374, "South": 1375, "little": 1376, "##k": 1377, "following": 1378, "November": 1379, "something": 1380, "2013": 1381, "December": 1382, "set": 1383, "2007": 1384, "old": 1385, "2006": 1386, "2014": 1387, "located": 1388, "##an": 1389, "music": 1390, "County": 1391, "City": 1392, "former": 1393, "##in": 1394, "room": 1395, "ve": 1396, "next": 1397, "All": 1398, "##man": 1399, "got": 1400, "father": 1401, "house": 1402, "##g": 1403, "body": 1404, "15": 1405, "20": 1406, "18": 1407, "started": 1408, "If": 1409, "2015": 1410, "town": 1411, "our": 1412, "line": 1413, "War": 1414, "large": 1415, "population": 1416, "named": 1417, "British": 1418, "company": 1419, "member": 1420, "five": 1421, "My": 1422, "single": 1423, "##en": 1424, "age": 1425, "State": 1426, "moved": 1427, "February": 1428, "11": 1429, "Her": 1430, "should": 1431, "century": 1432, "government": 1433, "built": 1434, "come": 1435, "best": 1436, "show": 1437, "However": 1438, "within": 1439, "look": 1440, "men": 1441, "door": 1442, "without": 1443, "need": 1444, "wasn": 1445, "2016": 1446, "water": 1447, "One": 1448, "system": 1449, "knew": 1450, "every": 1451, "died": 1452, "League": 1453, "turned": 1454, "asked": 1455, "North": 1456, "St": 1457, "wanted": 1458, "building": 1459, "received": 1460, "song": 1461, "served": 1462, "though": 1463, "felt": 1464, "##ia": 1465, "station": 1466, "band": 1467, "##ers": 1468, "local": 1469, "public": 1470, "himself": 1471, "different": 1472, "death": 1473, "say": 1474, "##1": 1475, "30": 1476, "##2": 1477, "2005": 1478, "16": 1479, "night": 1480, "behind": 1481, "children": 1482, "English": 1483, "members": 1484, "near": 1485, "saw": 1486, "together": 1487, "son": 1488, "14": 1489, "voice": 1490, "village": 1491, "13": 1492, "hands": 1493, "help": 1494, "##3": 1495, "due": 1496, "French": 1497, "London": 1498, "top": 1499, "told": 1500, "open": 1501, "published": 1502, "third": 1503, "2017": 1504, "play": 1505, "across": 1506, "During": 1507, "put": 1508, "final": 1509, "often": 1510, "include": 1511, "25": 1512, "##le": 1513, "main": 1514, "having": 1515, "2004": 1516, "once": 1517, "ever": 1518, "let": 1519, "book": 1520, "led": 1521, "gave": 1522, "late": 1523, "front": 1524, "find": 1525, "club": 1526, "##4": 1527, "German": 1528, "included": 1529, "species": 1530, "College": 1531, "form": 1532, "opened": 1533, "mother": 1534, "women": 1535, "enough": 1536, "West": 1537, "must": 1538, "2000": 1539, "power": 1540, "really": 1541, "17": 1542, "making": 1543, "half": 1544, "##6": 1545, "order": 1546, "might": 1547, "##is": 1548, "given": 1549, "million": 1550, "times": 1551, "days": 1552, "point": 1553, "full": 1554, "service": 1555, "With": 1556, "km": 1557, "major": 1558, "##7": 1559, "original": 1560, "become": 1561, "seen": 1562, "II": 1563, "north": 1564, "six": 1565, "##te": 1566, "love": 1567, "##0": 1568, "national": 1569, "International": 1570, "##5": 1571, "24": 1572, "So": 1573, "District": 1574, "lost": 1575, "run": 1576, "couldn": 1577, "career": 1578, "always": 1579, "##9": 1580, "2003": 1581, "##th": 1582, "country": 1583, "##z": 1584, "House": 1585, "air": 1586, "tell": 1587, "south": 1588, "worked": 1589, "woman": 1590, "player": 1591, "##A": 1592, "almost": 1593, "war": 1594, "River": 1595, "##ic": 1596, "married": 1597, "continued": 1598, "Then": 1599, "James": 1600, "close": 1601, "black": 1602, "short": 1603, "##8": 1604, "##na": 1605, "using": 1606, "history": 1607, "returned": 1608, "light": 1609, "car": 1610, "##ra": 1611, "sure": 1612, "William": 1613, "things": 1614, "General": 1615, "##ry": 1616, "2002": 1617, "better": 1618, "support": 1619, "100": 1620, "among": 1621, "From": 1622, "feet": 1623, "King": 1624, "anything": 1625, "21": 1626, "19": 1627, "established": 1628, "district": 1629, "2001": 1630, "feel": 1631, "great": 1632, "##ton": 1633, "level": 1634, "Cup": 1635, "These": 1636, "written": 1637, "games": 1638, "others": 1639, "already": 1640, "title": 1641, "story": 1642, "##p": 1643, "law": 1644, "thing": 1645, "US": 1646, "record": 1647, "role": 1648, "however": 1649, "By": 1650, "students": 1651, "England": 1652, "white": 1653, "control": 1654, "least": 1655, "inside": 1656, "land": 1657, "##C": 1658, "22": 1659, "give": 1660, "community": 1661, "hard": 1662, "##ie": 1663, "non": 1664, "##c": 1665, "produced": 1666, "George": 1667, "round": 1668, "period": 1669, "Park": 1670, "business": 1671, "various": 1672, "##ne": 1673, "does": 1674, "present": 1675, "wife": 1676, "far": 1677, "taken": 1678, "per": 1679, "reached": 1680, "David": 1681, "able": 1682, "version": 1683, "working": 1684, "young": 1685, "live": 1686, "created": 1687, "joined": 1688, "East": 1689, "living": 1690, "appeared": 1691, "case": 1692, "High": 1693, "done": 1694, "23": 1695, "important": 1696, "President": 1697, "Award": 1698, "France": 1699, "position": 1700, "office": 1701, "looking": 1702, "total": 1703, "general": 1704, "class": 1705, "To": 1706, "production": 1707, "##S": 1708, "football": 1709, "party": 1710, "brother": 1711, "keep": 1712, "mind": 1713, "free": 1714, "Street": 1715, "hair": 1716, "announced": 1717, "development": 1718, "either": 1719, "nothing": 1720, "moment": 1721, "Church": 1722, "followed": 1723, "wrote": 1724, "why": 1725, "India": 1726, "San": 1727, "election": 1728, "1999": 1729, "lead": 1730, "How": 1731, "##ch": 1732, "##rs": 1733, "words": 1734, "European": 1735, "course": 1736, "considered": 1737, "America": 1738, "arms": 1739, "Army": 1740, "political": 1741, "##la": 1742, "28": 1743, "26": 1744, "west": 1745, "east": 1746, "ground": 1747, "further": 1748, "church": 1749, "less": 1750, "site": 1751, "First": 1752, "Not": 1753, "Australia": 1754, "toward": 1755, "California": 1756, "##ness": 1757, "described": 1758, "works": 1759, "An": 1760, "Council": 1761, "heart": 1762, "past": 1763, "military": 1764, "27": 1765, "##or": 1766, "heard": 1767, "field": 1768, "human": 1769, "soon": 1770, "founded": 1771, "1998": 1772, "playing": 1773, "trying": 1774, "##x": 1775, "##ist": 1776, "##ta": 1777, "television": 1778, "mouth": 1779, "although": 1780, "taking": 1781, "win": 1782, "fire": 1783, "Division": 1784, "##ity": 1785, "Party": 1786, "Royal": 1787, "program": 1788, "Some": 1789, "Don": 1790, "Association": 1791, "According": 1792, "tried": 1793, "TV": 1794, "Paul": 1795, "outside": 1796, "daughter": 1797, "Best": 1798, "While": 1799, "someone": 1800, "match": 1801, "recorded": 1802, "Canada": 1803, "closed": 1804, "region": 1805, "Air": 1806, "above": 1807, "months": 1808, "elected": 1809, "##da": 1810, "##ian": 1811, "road": 1812, "##ar": 1813, "brought": 1814, "move": 1815, "1997": 1816, "leave": 1817, "##um": 1818, "Thomas": 1819, "1996": 1820, "am": 1821, "low": 1822, "Robert": 1823, "formed": 1824, "person": 1825, "services": 1826, "points": 1827, "Mr": 1828, "miles": 1829, "##b": 1830, "stop": 1831, "rest": 1832, "doing": 1833, "needed": 1834, "international": 1835, "release": 1836, "floor": 1837, "start": 1838, "sound": 1839, "call": 1840, "killed": 1841, "real": 1842, "dark": 1843, "research": 1844, "finished": 1845, "language": 1846, "Michael": 1847, "professional": 1848, "change": 1849, "sent": 1850, "50": 1851, "upon": 1852, "29": 1853, "track": 1854, "hit": 1855, "event": 1856, "2018": 1857, "term": 1858, "example": 1859, "Germany": 1860, "similar": 1861, "return": 1862, "##ism": 1863, "fact": 1864, "pulled": 1865, "stood": 1866, "says": 1867, "ran": 1868, "information": 1869, "yet": 1870, "result": 1871, "developed": 1872, "girl": 1873, "##re": 1874, "God": 1875, "1995": 1876, "areas": 1877, "signed": 1878, "decided": 1879, "##ment": 1880, "Company": 1881, "seemed": 1882, "##el": 1883, "co": 1884, "turn": 1885, "race": 1886, "common": 1887, "video": 1888, "Charles": 1889, "Indian": 1890, "##ation": 1891, "blood": 1892, "art": 1893, "red": 1894, "##able": 1895, "added": 1896, "rather": 1897, "1994": 1898, "met": 1899, "director": 1900, "addition": 1901, "design": 1902, "average": 1903, "minutes": 1904,