diff --git "a/vocab.json" "b/vocab.json" new file mode 100644--- /dev/null +++ "b/vocab.json" @@ -0,0 +1,50259 @@ +{ + "!": 0, + "!!": 927, + "!!!": 3301, + "!!!!": 2376, + "!!!!!": 12626, + "!!!!!!": 18384, + "!!!!!!!": 24588, + "!!!!!!!!": 6576, + "!!!!!!!!!": 29336, + "!!!!!!!!!!": 48170, + "!!!!!!!!!!!!!!!!": 20496, + "!!)": 44767, + "!\"": 6950, + "!'": 32356, + "!(": 46075, + "!)": 31199, + "!--": 16953, + "!?": 36754, + "!?!": 46820, + "![": 15814, + "!^^": 29494, + "!âĢĿ": 44359, + "\"": 1, + "\"\"": 16575, + "\"%": 35523, + "\"(": 14075, + "\")": 8505, + "\"),": 33110, + "\").": 17157, + "\");": 9457, + "\",": 3346, + "\",\"": 21620, + "\".": 13525, + "\"...": 47110, + "\"/": 19966, + "\"/>": 25524, + "\":": 7006, + "\":\"": 34706, + "\";": 11120, + "\">": 4179, + "\"><": 17840, + "\">": 45177, + "']": 19561, + "'d": 9396, + "'ll": 9412, + "'m": 6963, + "'re": 7581, + "'s": 1734, + "'t": 2959, + "'ve": 9651, + "'}": 48198, + "'âĢ¦": 24390, + "(": 7, + "(\"": 7354, + "($": 20391, + "(&": 32348, + "('": 9797, + "((": 21215, + "()": 5678, + "())": 33086, + "());": 30941, + "(),": 30192, + "().": 25357, + "();": 9583, + "(*": 43510, + "(-": 7721, + "(?)": 31155, + "([": 41098, + "(\\": 5335, + "(\\[": 38811, + "(_": 45046, + "({": 36046, + "({\\": 26922, + ")": 8, + ")\"": 24020, + ")$": 5147, + ")$,": 21256, + ")$.": 18687, + ")'": 30855, + ")(": 13537, + "))": 6214, + ")))": 47374, + ")),": 49302, + ")).": 25550, + "));": 21810, + ")*": 14205, + ")*(": 34433, + ")*(-": 49318, + ")**": 23917, + ")+": 42387, + "),": 1955, + "),\\": 47624, + ")-": 19426, + ").": 2061, + ").$$": 50137, + ")/": 10017, + ")/(": 34039, + ")/(-": 29452, + "):": 11236, + ");": 2313, + ")=": 20056, + ")=\\": 33124, + ")?": 31077, + ")[": 26536, + ")\\": 8194, + ")]": 40854, + ")^": 24803, + ")^{": 34558, + ")_": 40534, + "){": 4780, + "){#": 20914, + ")|": 40543, + ")}": 17012, + ")}\\": 39594, + ")}{": 47496, + ")âĢĻ": 34165, + "*": 9, + "*(": 22070, + "*)": 19791, + "**": 1378, + "**(": 44436, + "**(-": 37284, + "**)": 27446, + "***": 14376, + "****": 3901, + "********": 7285, + "*********": 46299, + "****************": 13800, + "********************************": 34918, + "**,": 39748, + "**]{}": 36828, + "**]{},": 33041, + "*,": 15099, + "*-": 22811, + "*.": 22113, + "*/": 33147, + "*]{}": 28671, + "*^": 33646, + "*^^*": 29542, + "*~": 20457, + "+": 10, + "+%": 27081, + "+(": 36638, + "+)": 16306, + "++": 6291, + "++)": 19360, + "++++": 26030, + "++;": 35582, + "+,": 33561, + "+[": 37419, + "+\\": 13837, + "+_+": 23981, + "+|": 48980, + "+âĢ¦": 42688, + "+âĢ¦+âĢ¦": 48807, + ",": 11, + ",\"": 5036, + ",#": 49794, + ",'": 19968, + ",,": 3284, + ",,,": 14925, + ",,,,": 8381, + ",,,,,,": 33482, + ",,,,,,,": 25222, + ",,,,,,,,": 43844, + ",-": 35204, + ",\\": 7481, + ",_": 35298, + ",âĢĿ": 9709, + "-": 12, + "-!": 25273, + "-%": 30138, + "-'": 37870, + "-(": 11874, + "-)": 8773, + "-,": 29271, + "--": 525, + "--\"": 46784, + "---": 5829, + "----": 828, + "-----": 16015, + "------": 13737, + "-------": 17237, + "--------": 1228, + "---------": 50235, + "----------": 39774, + "-----------": 50195, + "------------": 49086, + "----------------": 2070, + "--------------------": 48319, + "-----------------------": 48541, + "------------------------": 6966, + "-------------------------": 8420, + "--------------------------------": 5044, + "----------------------------------------------------------------": 12111, + "--------------------------------------------------------------------------------------------------------------------------------": 31707, + "-->": 21471, + "-.": 15935, + "->": 3606, + "->[": 24325, + "-[": 28238, + "-\\": 11597, + "-^": 15620, + "-_-": 15446, + "-_-;;": 50004, + ".": 13, + ".!": 11890, + ".!!": 21965, + ".\"": 1821, + ".$$": 29081, + ".'": 11011, + ".(": 13159, + ".)": 9217, + ".*": 18353, + ".**": 38398, + ".,": 4657, + ".-": 27069, + "..": 460, + "..!": 17041, + "..!!": 32893, + "..!!!": 50084, + "..\"": 19099, + "..'": 37582, + "..(": 19896, + "..)": 11524, + "...": 1196, + "...!": 47384, + "...\"": 15047, + "...(": 42693, + "...)": 22269, + "...,": 46352, + "....": 1385, + ".....": 4469, + "......": 8277, + ".......": 12090, + "........": 3566, + ".........": 14389, + "..........": 25976, + "...........": 32312, + "............": 37270, + ".............": 43023, + "..............": 47857, + "................": 10980, + ".........................": 27573, + "................................": 40986, + "...?": 25934, + "...^^": 39991, + "../": 14476, + "../../": 22112, + "..;;": 36718, + "..?": 8448, + "..??": 42191, + "..^^": 14245, + "./": 31976, + ".:": 49611, + ".;": 26855, + ".;;": 23695, + ".<": 19462, + ".": 41762, + ";&#": 18456, + ";)": 28007, + ";;": 1829, + ";;)": 25642, + ";;;": 6350, + ";;;;": 9828, + ";;;;;": 38539, + ";;;;;;;;": 36984, + ";\\": 32838, + "<": 27, + "": 17016, + "Ġ->": 5668, + "Ġ-\\": 44052, + "Ġ-_-": 17010, + "Ġ.": 1390, + "Ġ..": 15958, + "Ġ...": 8670, + "Ġ....": 41553, + "Ġ/": 1247, + "Ġ/*": 23632, + "Ġ/**": 31896, + "Ġ//": 7734, + "Ġ///": 36070, + "Ġ/>": 25243, + "Ġ0": 1063, + "Ġ00": 4744, + "Ġ000": 29111, + "Ġ003": 45604, + "Ġ01": 10491, + "Ġ010": 7305, + "Ġ02": 7311, + "Ġ03": 14238, + "Ġ031": 18418, + "Ġ032": 38129, + "Ġ04": 14844, + "Ġ05": 14036, + "Ġ0507": 16289, + "Ġ051": 37199, + "Ġ053": 43723, + "Ġ055": 48687, + "Ġ06": 15145, + "Ġ07": 14999, + "Ġ070": 32928, + "Ġ08": 13928, + "Ġ09": 11557, + "Ġ1": 371, + "Ġ10": 987, + "Ġ100": 1700, + "Ġ1000": 5194, + "Ġ10000": 28308, + "Ġ101": 12866, + "Ġ102": 19070, + "Ġ103": 20937, + "Ġ104": 21362, + "Ġ105": 17111, + "Ġ106": 20869, + "Ġ107": 24947, + "Ġ108": 20912, + "Ġ1080": 47017, + "Ġ109": 23616, + "Ġ11": 1523, + "Ġ110": 10799, + "Ġ1100": 28807, + "Ġ111": 20009, + "Ġ112": 17205, + "Ġ113": 27231, + "Ġ114": 23359, + "Ġ115": 22390, + "Ġ116": 27323, + "Ġ117": 28232, + "Ġ118": 25580, + "Ġ119": 14915, + "Ġ12": 1388, + "Ġ120": 6676, + "Ġ1200": 18026, + "Ġ121": 27774, + "Ġ122": 28088, + "Ġ123": 22839, + "Ġ124": 29756, + "Ġ125": 18848, + "Ġ126": 28672, + "Ġ127": 27471, + "Ġ128": 16452, + "Ġ129": 29465, + "Ġ13": 2073, + "Ġ130": 11431, + "Ġ1300": 27849, + "Ġ131": 33106, + "Ġ132": 28962, + "Ġ133": 30938, + "Ġ134": 32835, + "Ġ135": 24303, + "Ġ136": 34137, + "Ġ137": 33397, + "Ġ138": 33751, + "Ġ139": 35887, + "Ġ14": 2100, + "Ġ140": 12032, + "Ġ1400": 31100, + "Ġ141": 36640, + "Ġ142": 34340, + "Ġ143": 36761, + "Ġ144": 23606, + "Ġ145": 28660, + "Ġ146": 37070, + "Ġ147": 36504, + "Ġ148": 34622, + "Ġ149": 36384, + "Ġ15": 1635, + "Ġ150": 6090, + "Ġ1500": 13685, + "Ġ15000": 41358, + "Ġ151": 36576, + "Ġ152": 33335, + "Ġ153": 33652, + "Ġ154": 34512, + "Ġ155": 28297, + "Ġ156": 34151, + "Ġ157": 35979, + "Ġ158": 35060, + "Ġ1588": 30868, + "Ġ159": 36423, + "Ġ16": 1966, + "Ġ160": 13062, + "Ġ1600": 23026, + "Ġ161": 37897, + "Ġ162": 33112, + "Ġ163": 34901, + "Ġ164": 37133, + "Ġ165": 25142, + "Ġ166": 36158, + "Ġ167": 36539, + "Ġ168": 30990, + "Ġ169": 37061, + "Ġ17": 2183, + "Ġ170": 16073, + "Ġ1700": 34310, + "Ġ171": 40763, + "Ġ172": 36149, + "Ġ173": 38039, + "Ġ174": 37640, + "Ġ175": 27377, + "Ġ176": 37381, + "Ġ177": 38250, + "Ġ178": 35644, + "Ġ179": 41581, + "Ġ18": 1883, + "Ġ180": 9973, + "Ġ1800": 24018, + "Ġ181": 42058, + "Ġ182": 39568, + "Ġ183": 40044, + "Ġ184": 41327, + "Ġ185": 33574, + "Ġ186": 43485, + "Ġ187": 44087, + "Ġ188": 42028, + "Ġ189": 43840, + "Ġ19": 1132, + "Ġ190": 22311, + "Ġ1900": 30021, + "Ġ191": 47670, + "Ġ1910": 42186, + "Ġ1919": 43815, + "Ġ192": 30662, + "Ġ1920": 22663, + "Ġ193": 46209, + "Ġ1930": 27921, + "Ġ1933": 49540, + "Ġ1936": 48661, + "Ġ1937": 48285, + "Ġ1938": 48957, + "Ġ1939": 45758, + "Ġ194": 48104, + "Ġ1940": 33950, + "Ġ1941": 45163, + "Ġ1942": 48776, + "Ġ1943": 49662, + "Ġ1944": 45243, + "Ġ1945": 30314, + "Ġ1946": 40028, + "Ġ1947": 43237, + "Ġ1948": 35758, + "Ġ1949": 39442, + "Ġ195": 40566, + "Ġ1950": 21016, + "Ġ1951": 45049, + "Ġ1952": 44236, + "Ġ1953": 39773, + "Ġ1954": 41597, + "Ġ1955": 39018, + "Ġ1956": 39907, + "Ġ1957": 41460, + "Ġ1958": 39408, + "Ġ1959": 39934, + "Ġ196": 47797, + "Ġ1960": 17854, + "Ġ1961": 35898, + "Ġ1962": 31732, + "Ġ1963": 30225, + "Ġ1964": 33730, + "Ġ1965": 31931, + "Ġ1966": 33351, + "Ġ1967": 31768, + "Ġ1968": 29773, + "Ġ1969": 29197, + "Ġ197": 49275, + "Ġ1970": 15120, + "Ġ1971": 28156, + "Ġ1972": 26576, + "Ġ1973": 25008, + "Ġ1974": 26479, + "Ġ1975": 25670, + "Ġ1976": 26502, + "Ġ1977": 26282, + "Ġ1978": 24842, + "Ġ1979": 22760, + "Ġ198": 43872, + "Ġ1980": 12244, + "Ġ1981": 22094, + "Ġ1982": 21534, + "Ġ1983": 20981, + "Ġ1984": 19875, + "Ġ1985": 19758, + "Ġ1986": 19266, + "Ġ1987": 17787, + "Ġ1988": 16936, + "Ġ1989": 16832, + "Ġ199": 2427, + "Ġ1990": 10238, + "Ġ1991": 15060, + "Ġ1992": 14454, + "Ġ1993": 14643, + "Ġ1994": 13045, + "Ġ1995": 11925, + "Ġ1996": 11991, + "Ġ1997": 10836, + "Ġ1998": 10716, + "Ġ1999": 10234, + "Ġ2": 420, + "Ġ20": 1163, + "Ġ200": 1433, + "Ġ2000": 4626, + "Ġ20000": 49078, + "Ġ2001": 8789, + "Ġ2002": 8280, + "Ġ2003": 7987, + "Ġ2004": 7565, + "Ġ2005": 6880, + "Ġ2006": 6595, + "Ġ2007": 6002, + "Ġ2008": 5513, + "Ġ2009": 5456, + "Ġ201": 1131, + "Ġ2010": 4876, + "Ġ2011": 5051, + "Ġ2012": 4860, + "Ġ2013": 4815, + "Ġ2014": 4660, + "Ġ2015": 4384, + "Ġ2016": 4417, + "Ġ2017": 4295, + "Ġ2018": 4270, + "Ġ2019": 4368, + "Ġ202": 34974, + "Ġ2020": 4002, + "Ġ2021": 4849, + "Ġ2022": 9487, + "Ġ2023": 25679, + "Ġ2024": 37687, + "Ġ2025": 28454, + "Ġ203": 39323, + "Ġ2030": 20583, + "Ġ204": 38492, + "Ġ205": 39430, + "Ġ2050": 45914, + "Ġ206": 43968, + "Ġ207": 42108, + "Ġ208": 45683, + "Ġ209": 45668, + "Ġ21": 2976, + "Ġ210": 22697, + "Ġ2100": 44159, + "Ġ211": 43990, + "Ġ212": 42763, + "Ġ213": 47304, + "Ġ214": 45262, + "Ġ215": 41656, + "Ġ216": 45907, + "Ġ218": 49736, + "Ġ22": 3169, + "Ġ220": 17533, + "Ġ2200": 41197, + "Ġ221": 45196, + "Ġ222": 41116, + "Ġ223": 47484, + "Ġ224": 45494, + "Ġ225": 29348, + "Ġ226": 48644, + "Ġ228": 49156, + "Ġ23": 2967, + "Ġ230": 19540, + "Ġ232": 46002, + "Ġ233": 48813, + "Ġ235": 36179, + "Ġ24": 2407, + "Ġ240": 16215, + "Ġ2400": 38603, + "Ġ245": 38774, + "Ġ25": 2276, + "Ġ250": 9153, + "Ġ2500": 20423, + "Ġ255": 31580, + "Ġ256": 16728, + "Ġ26": 3273, + "Ġ260": 24663, + "Ġ2600": 42125, + "Ġ264": 46236, + "Ġ265": 46616, + "Ġ27": 3296, + "Ġ270": 24244, + "Ġ2700": 49598, + "Ġ275": 42156, + "Ġ28": 3261, + "Ġ280": 24254, + "Ġ29": 3599, + "Ġ290": 35335, + "Ġ299": 45802, + "Ġ3": 571, + "Ġ30": 1526, + "Ġ300": 4639, + "Ġ3000": 9255, + "Ġ301": 41046, + "Ġ302": 47598, + "Ġ304": 47369, + "Ġ305": 45275, + "Ġ31": 4374, + "Ġ310": 36420, + "Ġ313": 49864, + "Ġ315": 46505, + "Ġ32": 5847, + "Ġ320": 21689, + "Ġ3200": 39780, + "Ġ33": 6654, + "Ġ330": 26853, + "Ġ34": 7219, + "Ġ340": 32116, + "Ġ35": 4480, + "Ġ350": 16144, + "Ġ3500": 25710, + "Ġ355": 45226, + "Ġ36": 5884, + "Ġ360": 16865, + "Ġ3600": 36256, + "Ġ365": 18587, + "Ġ37": 7124, + "Ġ370": 38770, + "Ġ38": 7572, + "Ġ380": 33477, + "Ġ39": 7676, + "Ġ390": 46065, + "Ġ4": 725, + "Ġ40": 2463, + "Ġ400": 6956, + "Ġ4000": 14358, + "Ġ401": 40758, + "Ġ41": 9662, + "Ġ410": 46679, + "Ġ412": 41721, + "Ġ42": 8384, + "Ġ420": 32938, + "Ġ43": 9260, + "Ġ430": 42859, + "Ġ44": 9111, + "Ġ440": 39658, + "Ġ45": 5103, + "Ġ450": 20010, + "Ġ4500": 36013, + "Ġ46": 9695, + "Ġ460": 45651, + "Ġ47": 9813, + "Ġ470": 49836, + "Ġ48": 7807, + "Ġ480": 35565, + "Ġ49": 9549, + "Ġ5": 729, + "Ġ50": 2054, + "Ġ500": 4237, + "Ġ5000": 9208, + "Ġ51": 11071, + "Ġ510": 48937, + "Ġ512": 22912, + "Ġ52": 9477, + "Ġ520": 32887, + "Ġ53": 11373, + "Ġ530": 42813, + "Ġ54": 11135, + "Ġ540": 43973, + "Ġ55": 7529, + "Ġ550": 26591, + "Ġ5500": 45171, + "Ġ56": 10984, + "Ġ560": 47488, + "Ġ57": 11721, + "Ġ58": 11704, + "Ġ59": 10129, + "Ġ6": 908, + "Ġ60": 3029, + "Ġ600": 8706, + "Ġ6000": 17712, + "Ġ61": 13593, + "Ġ62": 12800, + "Ġ63": 12286, + "Ġ630": 49162, + "Ġ64": 9284, + "Ġ640": 41378, + "Ġ65": 7811, + "Ġ650": 30131, + "Ġ6500": 50136, + "Ġ66": 11716, + "Ġ660": 47939, + "Ġ67": 13307, + "Ġ68": 13037, + "Ġ69": 13846, + "Ġ7": 1002, + "Ġ70": 3659, + "Ġ700": 11137, + "Ġ7000": 19616, + "Ġ71": 15569, + "Ġ72": 11277, + "Ġ720": 42230, + "Ġ73": 14773, + "Ġ74": 14061, + "Ġ75": 7903, + "Ġ750": 24520, + "Ġ76": 14430, + "Ġ77": 13585, + "Ġ78": 14413, + "Ġ79": 15363, + "Ġ8": 1032, + "Ġ80": 3513, + "Ġ800": 10643, + "Ġ8000": 19115, + "Ġ802": 29435, + "Ġ81": 16009, + "Ġ82": 15477, + "Ġ83": 15686, + "Ġ84": 10780, + "Ġ85": 9296, + "Ġ850": 36286, + "Ġ86": 15086, + "Ġ87": 15268, + "Ġ88": 13309, + "Ġ89": 15356, + "Ġ9": 1095, + "Ġ90": 4178, + "Ġ900": 15738, + "Ġ9000": 26398, + "Ġ91": 16810, + "Ġ92": 15549, + "Ġ93": 16110, + "Ġ94": 15178, + "Ġ95": 8481, + "Ġ950": 46951, + "Ġ96": 13543, + "Ġ97": 13047, + "Ġ970": 48931, + "Ġ98": 13049, + "Ġ99": 8979, + "Ġ:": 869, + "Ġ:)": 14846, + "Ġ:-)": 46103, + "Ġ::": 42360, + "Ġ:=": 19786, + "Ġ;": 7367, + "Ġ;)": 45930, + "Ġ;;": 14621, + "Ġ;;;": 36038, + "Ġ<": 1392, + "Ġ