diff --git "a/data/Afro-Asiatic.json" "b/data/Afro-Asiatic.json" --- "a/data/Afro-Asiatic.json" +++ "b/data/Afro-Asiatic.json" @@ -1,18 +1,22 @@ { "name": "Afro-Asiatic", + "depth": 0, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Berber", + "depth": 1, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Guanche", + "depth": 2, "iso_1_code": null, "iso_3_code": "gnc", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "11", "native_tokenizers": [], @@ -20,19 +24,23 @@ }, { "name": "Eastern", + "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Awjila-Sokna", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Awjilah", + "depth": 4, "iso_1_code": null, "iso_3_code": "auj", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "14", "native_tokenizers": [], @@ -40,15 +48,18 @@ }, { "name": "Sawknah", + "depth": 4, "iso_1_code": null, "iso_3_code": "swn", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "15", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "13", "native_tokenizers": [], @@ -56,26 +67,31 @@ }, { "name": "Siwa", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Siwi", + "depth": 4, "iso_1_code": null, "iso_3_code": "siz", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "17", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "16", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "12", "native_tokenizers": [], @@ -83,14 +99,17 @@ }, { "name": "Northern", + "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Chenoua", + "depth": 3, "iso_1_code": null, "iso_3_code": "cnu", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "19", "native_tokenizers": [], @@ -98,14 +117,17 @@ }, { "name": "Atlas", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Judeo-Berber", + "depth": 4, "iso_1_code": null, "iso_3_code": "jbe", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "21", "native_tokenizers": [], @@ -113,18 +135,12 @@ }, { "name": "Tachelhit", + "depth": 4, "iso_1_code": null, "iso_3_code": "shi", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "22", "native_tokenizers": [], "scripts": [ @@ -133,9 +149,11 @@ }, { "name": "Tamazight, Central Atlas", + "depth": 4, "iso_1_code": null, "iso_3_code": "tzm", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "23", "native_tokenizers": [], @@ -145,9 +163,11 @@ }, { "name": "Tamazight, Standard Moroccan", + "depth": 4, "iso_1_code": null, "iso_3_code": "zgh", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "24", "native_tokenizers": [], @@ -156,38 +176,26 @@ ] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "20", "native_tokenizers": [], "scripts": [] }, { "name": "Kabyle", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kabyle", + "depth": 4, "iso_1_code": null, "iso_3_code": "kab", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "26", "native_tokenizers": [], "scripts": [ @@ -195,34 +203,31 @@ ] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "25", "native_tokenizers": [], "scripts": [] }, { "name": "Zenati", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "East", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ghadam\u00e8s", + "depth": 5, "iso_1_code": null, "iso_3_code": "gha", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "29", "native_tokenizers": [], @@ -230,9 +235,11 @@ }, { "name": "Nafusi", + "depth": 5, "iso_1_code": null, "iso_3_code": "jbn", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "30", "native_tokenizers": [], @@ -240,15 +247,18 @@ }, { "name": "Sened", + "depth": 5, "iso_1_code": null, "iso_3_code": "sds", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "31", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "28", "native_tokenizers": [], @@ -256,20 +266,24 @@ }, { "name": "Ghomara", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ghomara", + "depth": 5, "iso_1_code": null, "iso_3_code": "gho", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "33", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "32", "native_tokenizers": [], @@ -277,14 +291,17 @@ }, { "name": "Mzab-Wargla", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Taznatit", + "depth": 5, "iso_1_code": null, "iso_3_code": "grr", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "35", "native_tokenizers": [], @@ -292,9 +309,11 @@ }, { "name": "Tumzabt", + "depth": 5, "iso_1_code": null, "iso_3_code": "mzb", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "36", "native_tokenizers": [], @@ -302,9 +321,11 @@ }, { "name": "Tagargrent", + "depth": 5, "iso_1_code": null, "iso_3_code": "oua", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "37", "native_tokenizers": [], @@ -312,15 +333,18 @@ }, { "name": "Tamazight, Temacine", + "depth": 5, "iso_1_code": null, "iso_3_code": "tjo", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "38", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "34", "native_tokenizers": [], @@ -328,14 +352,17 @@ }, { "name": "Riff", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Tarifit", + "depth": 5, "iso_1_code": null, "iso_3_code": "rif", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "40", "native_tokenizers": [], @@ -343,15 +370,18 @@ }, { "name": "Senhaja Berber", + "depth": 5, "iso_1_code": null, "iso_3_code": "sjs", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "41", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "39", "native_tokenizers": [], @@ -359,20 +389,24 @@ }, { "name": "Shawiya", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Tachawit", + "depth": 5, "iso_1_code": null, "iso_3_code": "shy", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "43", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "42", "native_tokenizers": [], @@ -380,69 +414,63 @@ }, { "name": "Tidikelt", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Tamazight, Tidikelt", + "depth": 5, "iso_1_code": null, "iso_3_code": "tia", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "45", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "44", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "27", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "18", "native_tokenizers": [], "scripts": [] }, { "name": "Tamasheq", + "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Northern", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Tamahaq, Tahaggart", + "depth": 4, "iso_1_code": null, "iso_3_code": "thv", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "48", "native_tokenizers": [], "scripts": [ @@ -450,38 +478,26 @@ ] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "47", "native_tokenizers": [], "scripts": [] }, { "name": "Southern", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Tamasheq", + "depth": 4, "iso_1_code": null, "iso_3_code": "taq", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "50", "native_tokenizers": [], "scripts": [ @@ -491,9 +507,11 @@ }, { "name": "Tamajeq, Tayart", + "depth": 4, "iso_1_code": null, "iso_3_code": "thz", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "51", "native_tokenizers": [], @@ -501,18 +519,12 @@ }, { "name": "Tamajaq, Tawallammat", + "depth": 4, "iso_1_code": null, "iso_3_code": "ttq", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "52", "native_tokenizers": [], "scripts": [ @@ -521,43 +533,32 @@ ] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "49", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "46", "native_tokenizers": [], "scripts": [] }, { "name": "Zenaga", + "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Tetserret", + "depth": 3, "iso_1_code": null, "iso_3_code": "tez", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "54", "native_tokenizers": [], @@ -565,64 +566,67 @@ }, { "name": "Zenaga", + "depth": 3, "iso_1_code": null, "iso_3_code": "zen", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "55", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "53", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "10", "native_tokenizers": [], "scripts": [] }, { "name": "Chadic", + "depth": 1, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Biu-Mandara", + "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "A", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "A.1", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Eastern", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Boga", + "depth": 6, "iso_1_code": null, "iso_3_code": "bvw", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "61", "native_tokenizers": [], @@ -630,9 +634,11 @@ }, { "name": "Ga\u2019anda", + "depth": 6, "iso_1_code": null, "iso_3_code": "gqa", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "62", "native_tokenizers": [], @@ -640,15 +646,18 @@ }, { "name": "Hwana", + "depth": 6, "iso_1_code": null, "iso_3_code": "hwo", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "63", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "60", "native_tokenizers": [], @@ -656,14 +665,17 @@ }, { "name": "Western", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Jara", + "depth": 6, "iso_1_code": null, "iso_3_code": "jaf", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "65", "native_tokenizers": [], @@ -671,21 +683,25 @@ }, { "name": "Tera", + "depth": 6, "iso_1_code": null, "iso_3_code": "ttr", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "66", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "64", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "59", "native_tokenizers": [], @@ -693,14 +709,17 @@ }, { "name": "A.2", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Nggwahyi", + "depth": 5, "iso_1_code": null, "iso_3_code": "ngx", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "68", "native_tokenizers": [], @@ -708,14 +727,17 @@ }, { "name": "1", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bura-Pabir", + "depth": 6, "iso_1_code": null, "iso_3_code": "bwr", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "70", "native_tokenizers": [], @@ -723,9 +745,11 @@ }, { "name": "Kibaku", + "depth": 6, "iso_1_code": null, "iso_3_code": "ckl", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "71", "native_tokenizers": [], @@ -733,9 +757,11 @@ }, { "name": "Kofa", + "depth": 6, "iso_1_code": null, "iso_3_code": "kso", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "72", "native_tokenizers": [], @@ -743,15 +769,18 @@ }, { "name": "Putai", + "depth": 6, "iso_1_code": null, "iso_3_code": "mfl", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "73", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "69", "native_tokenizers": [], @@ -759,14 +788,17 @@ }, { "name": "2", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Nya Huba", + "depth": 6, "iso_1_code": null, "iso_3_code": "hbb", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "75", "native_tokenizers": [], @@ -774,9 +806,11 @@ }, { "name": "Marghi South", + "depth": 6, "iso_1_code": null, "iso_3_code": "mfm", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "76", "native_tokenizers": [], @@ -784,21 +818,25 @@ }, { "name": "Marghi Central", + "depth": 6, "iso_1_code": null, "iso_3_code": "mrt", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "77", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "74", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "67", "native_tokenizers": [], @@ -806,23 +844,18 @@ }, { "name": "A.3", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bana", + "depth": 5, "iso_1_code": null, "iso_3_code": "bcw", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "79", "native_tokenizers": [], "scripts": [ @@ -831,9 +864,11 @@ }, { "name": "Kirya-Konzel", + "depth": 5, "iso_1_code": null, "iso_3_code": "fkk", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "80", "native_tokenizers": [], @@ -841,18 +876,12 @@ }, { "name": "Kamwe", + "depth": 5, "iso_1_code": null, "iso_3_code": "hig", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "81", "native_tokenizers": [], "scripts": [ @@ -861,9 +890,11 @@ }, { "name": "Hya", + "depth": 5, "iso_1_code": null, "iso_3_code": "hya", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "82", "native_tokenizers": [], @@ -871,18 +902,12 @@ }, { "name": "Psikye", + "depth": 5, "iso_1_code": null, "iso_3_code": "kvj", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "83", "native_tokenizers": [], "scripts": [ @@ -890,34 +915,31 @@ ] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "78", "native_tokenizers": [], "scripts": [] }, { "name": "A.4", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Lamang", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Lamang", + "depth": 6, "iso_1_code": null, "iso_3_code": "hia", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "86", "native_tokenizers": [], @@ -925,9 +947,11 @@ }, { "name": "Vemgo-Mabas", + "depth": 6, "iso_1_code": null, "iso_3_code": "vem", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "87", "native_tokenizers": [], @@ -935,18 +959,12 @@ }, { "name": "Hdi", + "depth": 6, "iso_1_code": null, "iso_3_code": "xed", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "88", "native_tokenizers": [], "scripts": [ @@ -954,34 +972,31 @@ ] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "85", "native_tokenizers": [], "scripts": [] }, { "name": "Mandara Proper", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Glavda", + "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Cineni", + "depth": 7, "iso_1_code": null, "iso_3_code": "cie", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "91", "native_tokenizers": [], @@ -989,9 +1004,11 @@ }, { "name": "Dghwede", + "depth": 7, "iso_1_code": null, "iso_3_code": "dgh", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "92", "native_tokenizers": [], @@ -999,9 +1016,11 @@ }, { "name": "Guduf-Gava", + "depth": 7, "iso_1_code": null, "iso_3_code": "gdf", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "93", "native_tokenizers": [], @@ -1009,9 +1028,11 @@ }, { "name": "Glavda", + "depth": 7, "iso_1_code": null, "iso_3_code": "glw", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "94", "native_tokenizers": [], @@ -1019,15 +1040,18 @@ }, { "name": "Gvoko", + "depth": 7, "iso_1_code": null, "iso_3_code": "ngs", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "95", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "90", "native_tokenizers": [], @@ -1035,23 +1059,18 @@ }, { "name": "Mandara", + "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Wandala", + "depth": 7, "iso_1_code": null, "iso_3_code": "mfi", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "97", "native_tokenizers": [], "scripts": [ @@ -1059,38 +1078,26 @@ ] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "96", "native_tokenizers": [], "scripts": [] }, { "name": "Podoko", + "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Parkwa", + "depth": 7, "iso_1_code": null, "iso_3_code": "pbi", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "99", "native_tokenizers": [], "scripts": [ @@ -1098,57 +1105,39 @@ ] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "98", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "89", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "84", "native_tokenizers": [], "scripts": [] }, { "name": "A.5", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Baldemu", + "depth": 5, "iso_1_code": null, "iso_3_code": "bdn", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "101", "native_tokenizers": [], @@ -1156,9 +1145,11 @@ }, { "name": "Cuvok", + "depth": 5, "iso_1_code": null, "iso_3_code": "cuv", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "102", "native_tokenizers": [], @@ -1166,9 +1157,11 @@ }, { "name": "Dugwor", + "depth": 5, "iso_1_code": null, "iso_3_code": "dme", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "103", "native_tokenizers": [], @@ -1176,9 +1169,11 @@ }, { "name": "Giziga, North", + "depth": 5, "iso_1_code": null, "iso_3_code": "gis", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "104", "native_tokenizers": [], @@ -1186,18 +1181,12 @@ }, { "name": "Giziga", + "depth": 5, "iso_1_code": null, "iso_3_code": "giz", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "105", "native_tokenizers": [], "scripts": [ @@ -1206,18 +1195,12 @@ }, { "name": "Zulgo-Gemzek", + "depth": 5, "iso_1_code": null, "iso_3_code": "gnd", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "106", "native_tokenizers": [], "scripts": [ @@ -1226,18 +1209,12 @@ }, { "name": "Mafa", + "depth": 5, "iso_1_code": null, "iso_3_code": "maf", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "107", "native_tokenizers": [], "scripts": [ @@ -1246,18 +1223,12 @@ }, { "name": "Merey", + "depth": 5, "iso_1_code": null, "iso_3_code": "meq", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "108", "native_tokenizers": [], "scripts": [ @@ -1266,18 +1237,12 @@ }, { "name": "Matal", + "depth": 5, "iso_1_code": null, "iso_3_code": "mfh", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "109", "native_tokenizers": [], "scripts": [ @@ -1286,9 +1251,11 @@ }, { "name": "Mefele", + "depth": 5, "iso_1_code": null, "iso_3_code": "mfj", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "110", "native_tokenizers": [], @@ -1296,18 +1263,12 @@ }, { "name": "Mofu, North", + "depth": 5, "iso_1_code": null, "iso_3_code": "mfk", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "111", "native_tokenizers": [], "scripts": [ @@ -1316,18 +1277,12 @@ }, { "name": "Mofu-Gudur", + "depth": 5, "iso_1_code": null, "iso_3_code": "mif", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "112", "native_tokenizers": [], "scripts": [ @@ -1336,9 +1291,11 @@ }, { "name": "Vame", + "depth": 5, "iso_1_code": null, "iso_3_code": "mlr", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "113", "native_tokenizers": [], @@ -1346,9 +1303,11 @@ }, { "name": "Moloko", + "depth": 5, "iso_1_code": null, "iso_3_code": "mlw", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "114", "native_tokenizers": [], @@ -1356,18 +1315,12 @@ }, { "name": "Mbuko", + "depth": 5, "iso_1_code": null, "iso_3_code": "mqb", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "115", "native_tokenizers": [], "scripts": [ @@ -1376,18 +1329,12 @@ }, { "name": "Muyang", + "depth": 5, "iso_1_code": null, "iso_3_code": "muy", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "116", "native_tokenizers": [], "scripts": [ @@ -1396,9 +1343,11 @@ }, { "name": "Mada", + "depth": 5, "iso_1_code": null, "iso_3_code": "mxu", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "117", "native_tokenizers": [], @@ -1406,44 +1355,43 @@ }, { "name": "Wuzlam", + "depth": 5, "iso_1_code": null, "iso_3_code": "udl", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "118", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "100", "native_tokenizers": [], "scripts": [] }, { "name": "A.6", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Sukur", + "depth": 5, "iso_1_code": null, "iso_3_code": "syk", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "120", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "119", "native_tokenizers": [], @@ -1451,14 +1399,17 @@ }, { "name": "A.7", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Buwal", + "depth": 5, "iso_1_code": null, "iso_3_code": "bhs", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "122", "native_tokenizers": [], @@ -1466,18 +1417,12 @@ }, { "name": "Daba", + "depth": 5, "iso_1_code": null, "iso_3_code": "dbq", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "123", "native_tokenizers": [], "scripts": [ @@ -1486,9 +1431,11 @@ }, { "name": "Mazagway-Hidi", + "depth": 5, "iso_1_code": null, "iso_3_code": "dkx", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "124", "native_tokenizers": [], @@ -1496,9 +1443,11 @@ }, { "name": "Gavar", + "depth": 5, "iso_1_code": null, "iso_3_code": "gou", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "125", "native_tokenizers": [], @@ -1506,9 +1455,11 @@ }, { "name": "Mina", + "depth": 5, "iso_1_code": null, "iso_3_code": "hna", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "126", "native_tokenizers": [], @@ -1516,38 +1467,36 @@ }, { "name": "Mbudum", + "depth": 5, "iso_1_code": null, "iso_3_code": "xmd", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "127", "native_tokenizers": [], - "scripts": [] - } - ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" + "scripts": [] } - }, + ], + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "121", "native_tokenizers": [], "scripts": [] }, { "name": "A.8", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bacama", + "depth": 5, "iso_1_code": null, "iso_3_code": "bcy", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "129", "native_tokenizers": [], @@ -1555,9 +1504,11 @@ }, { "name": "Bata", + "depth": 5, "iso_1_code": null, "iso_3_code": "bta", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "130", "native_tokenizers": [], @@ -1565,9 +1516,11 @@ }, { "name": "Fali Muchella", + "depth": 5, "iso_1_code": null, "iso_3_code": "fli", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "131", "native_tokenizers": [], @@ -1575,18 +1528,12 @@ }, { "name": "Gude", + "depth": 5, "iso_1_code": null, "iso_3_code": "gde", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "132", "native_tokenizers": [], "scripts": [ @@ -1595,9 +1542,11 @@ }, { "name": "Gudu", + "depth": 5, "iso_1_code": null, "iso_3_code": "gdu", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "133", "native_tokenizers": [], @@ -1605,9 +1554,11 @@ }, { "name": "Holma", + "depth": 5, "iso_1_code": null, "iso_3_code": "hod", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "134", "native_tokenizers": [], @@ -1615,9 +1566,11 @@ }, { "name": "Jimjimen", + "depth": 5, "iso_1_code": null, "iso_3_code": "jim", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "135", "native_tokenizers": [], @@ -1625,9 +1578,11 @@ }, { "name": "Ngwaba", + "depth": 5, "iso_1_code": null, "iso_3_code": "ngw", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "136", "native_tokenizers": [], @@ -1635,9 +1590,11 @@ }, { "name": "Nzanyi", + "depth": 5, "iso_1_code": null, "iso_3_code": "nja", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "137", "native_tokenizers": [], @@ -1645,9 +1602,11 @@ }, { "name": "Sharwa", + "depth": 5, "iso_1_code": null, "iso_3_code": "swq", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "138", "native_tokenizers": [], @@ -1655,9 +1614,11 @@ }, { "name": "Tsuvan", + "depth": 5, "iso_1_code": null, "iso_3_code": "tsh", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "139", "native_tokenizers": [], @@ -1665,57 +1626,49 @@ }, { "name": "Zizilivakan", + "depth": 5, "iso_1_code": null, "iso_3_code": "ziz", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "140", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "128", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "58", "native_tokenizers": [], "scripts": [] }, { "name": "B", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "B.1", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Auyokawa", + "depth": 5, "iso_1_code": null, "iso_3_code": "auo", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "143", "native_tokenizers": [], @@ -1723,9 +1676,11 @@ }, { "name": "Jilbe", + "depth": 5, "iso_1_code": null, "iso_3_code": "jie", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "144", "native_tokenizers": [], @@ -1733,20 +1688,24 @@ }, { "name": "Buduma", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Buduma", + "depth": 6, "iso_1_code": null, "iso_3_code": "bdm", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "146", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "145", "native_tokenizers": [], @@ -1754,14 +1713,17 @@ }, { "name": "Jina", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Jina", + "depth": 6, "iso_1_code": null, "iso_3_code": "jia", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "148", "native_tokenizers": [], @@ -1769,15 +1731,18 @@ }, { "name": "Majera", + "depth": 6, "iso_1_code": null, "iso_3_code": "xmj", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "149", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "147", "native_tokenizers": [], @@ -1785,19 +1750,23 @@ }, { "name": "Kotoko Proper", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "North", + "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Afade", + "depth": 7, "iso_1_code": null, "iso_3_code": "aal", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "152", "native_tokenizers": [], @@ -1805,9 +1774,11 @@ }, { "name": "Mpade", + "depth": 7, "iso_1_code": null, "iso_3_code": "mpi", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "153", "native_tokenizers": [], @@ -1815,9 +1786,11 @@ }, { "name": "Maslam", + "depth": 7, "iso_1_code": null, "iso_3_code": "msv", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "154", "native_tokenizers": [], @@ -1825,15 +1798,18 @@ }, { "name": "Malgbe", + "depth": 7, "iso_1_code": null, "iso_3_code": "mxf", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "155", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "151", "native_tokenizers": [], @@ -1841,14 +1817,17 @@ }, { "name": "South", + "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Lagwan", + "depth": 7, "iso_1_code": null, "iso_3_code": "kot", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "157", "native_tokenizers": [], @@ -1856,27 +1835,32 @@ }, { "name": "Mser", + "depth": 7, "iso_1_code": null, "iso_3_code": "kqx", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "158", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "156", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "150", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "142", "native_tokenizers": [], @@ -1884,14 +1868,17 @@ }, { "name": "B.2", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Muskum", + "depth": 5, "iso_1_code": null, "iso_3_code": "mje", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "160", "native_tokenizers": [], @@ -1899,9 +1886,11 @@ }, { "name": "Mbara", + "depth": 5, "iso_1_code": null, "iso_3_code": "mpk", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "161", "native_tokenizers": [], @@ -1909,18 +1898,12 @@ }, { "name": "Musgu", + "depth": 5, "iso_1_code": null, "iso_3_code": "mug", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "162", "native_tokenizers": [], "scripts": [ @@ -1928,52 +1911,33 @@ ] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "159", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "141", "native_tokenizers": [], "scripts": [] }, { "name": "C", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Gidar", + "depth": 4, "iso_1_code": null, "iso_3_code": "gid", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "164", "native_tokenizers": [], "scripts": [ @@ -1981,53 +1945,44 @@ ] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "163", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "57", "native_tokenizers": [], "scripts": [] }, { "name": "East", + "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "A", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "A.1", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Buso", + "depth": 5, "iso_1_code": null, "iso_3_code": "bso", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "168", "native_tokenizers": [], @@ -2035,14 +1990,17 @@ }, { "name": "1", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mulgi", + "depth": 6, "iso_1_code": null, "iso_3_code": "mvh", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "170", "native_tokenizers": [], @@ -2050,9 +2008,11 @@ }, { "name": "Ndam", + "depth": 6, "iso_1_code": null, "iso_3_code": "ndm", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "171", "native_tokenizers": [], @@ -2060,9 +2020,11 @@ }, { "name": "Soumraye", + "depth": 6, "iso_1_code": null, "iso_3_code": "sor", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "172", "native_tokenizers": [], @@ -2070,18 +2032,12 @@ }, { "name": "Tumak", + "depth": 6, "iso_1_code": null, "iso_3_code": "tmc", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "173", "native_tokenizers": [], "scripts": [ @@ -2089,29 +2045,25 @@ ] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "169", "native_tokenizers": [], "scripts": [] }, { "name": "2", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Boor", + "depth": 6, "iso_1_code": null, "iso_3_code": "bvf", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "175", "native_tokenizers": [], @@ -2119,9 +2071,11 @@ }, { "name": "Gadang", + "depth": 6, "iso_1_code": null, "iso_3_code": "gdk", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "176", "native_tokenizers": [], @@ -2129,9 +2083,11 @@ }, { "name": "Miltu", + "depth": 6, "iso_1_code": null, "iso_3_code": "mlj", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "177", "native_tokenizers": [], @@ -2139,58 +2095,50 @@ }, { "name": "Sarua", + "depth": 6, "iso_1_code": null, "iso_3_code": "swy", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "178", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "174", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "167", "native_tokenizers": [], "scripts": [] }, { "name": "A.2", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "1", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kimr\u00e9", + "depth": 6, "iso_1_code": null, "iso_3_code": "kqp", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "181", "native_tokenizers": [], "scripts": [ @@ -2199,18 +2147,12 @@ }, { "name": "Lele", + "depth": 6, "iso_1_code": null, "iso_3_code": "lln", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "182", "native_tokenizers": [], "scripts": [ @@ -2219,38 +2161,36 @@ }, { "name": "Nancere", + "depth": 6, "iso_1_code": null, "iso_3_code": "nnc", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "183", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "180", "native_tokenizers": [], "scripts": [] }, { "name": "2", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Gabri", + "depth": 6, "iso_1_code": null, "iso_3_code": "gab", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "185", "native_tokenizers": [], @@ -2258,9 +2198,11 @@ }, { "name": "Kabalai", + "depth": 6, "iso_1_code": null, "iso_3_code": "kvf", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "186", "native_tokenizers": [], @@ -2268,53 +2210,44 @@ }, { "name": "Tobanga", + "depth": 6, "iso_1_code": null, "iso_3_code": "tng", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "187", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "184", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "179", "native_tokenizers": [], "scripts": [] }, { "name": "A.3", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kera", + "depth": 5, "iso_1_code": null, "iso_3_code": "ker", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "189", "native_tokenizers": [], "scripts": [ @@ -2323,62 +2256,55 @@ }, { "name": "Kwang", + "depth": 5, "iso_1_code": null, "iso_3_code": "kvi", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "190", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "188", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "166", "native_tokenizers": [], "scripts": [] }, { "name": "B", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "B.1", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "1", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bidiyo", + "depth": 6, "iso_1_code": null, "iso_3_code": "bid", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "194", "native_tokenizers": [], @@ -2386,18 +2312,12 @@ }, { "name": "Dangal\u00e9at", + "depth": 6, "iso_1_code": null, "iso_3_code": "daa", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "195", "native_tokenizers": [], "scripts": [ @@ -2406,9 +2326,11 @@ }, { "name": "Jonkor Bourmataguil", + "depth": 6, "iso_1_code": null, "iso_3_code": "jeu", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "196", "native_tokenizers": [], @@ -2416,9 +2338,11 @@ }, { "name": "Mawa", + "depth": 6, "iso_1_code": null, "iso_3_code": "mcw", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "197", "native_tokenizers": [], @@ -2426,9 +2350,11 @@ }, { "name": "Migaama", + "depth": 6, "iso_1_code": null, "iso_3_code": "mmy", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "198", "native_tokenizers": [], @@ -2436,9 +2362,11 @@ }, { "name": "Mogum", + "depth": 6, "iso_1_code": null, "iso_3_code": "mou", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "199", "native_tokenizers": [], @@ -2446,9 +2374,11 @@ }, { "name": "Mabire", + "depth": 6, "iso_1_code": null, "iso_3_code": "muj", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "200", "native_tokenizers": [], @@ -2456,38 +2386,36 @@ }, { "name": "Ubi", + "depth": 6, "iso_1_code": null, "iso_3_code": "ubi", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "201", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "193", "native_tokenizers": [], "scripts": [] }, { "name": "2", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Birgit", + "depth": 6, "iso_1_code": null, "iso_3_code": "btf", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "203", "native_tokenizers": [], @@ -2495,9 +2423,11 @@ }, { "name": "Kajakse", + "depth": 6, "iso_1_code": null, "iso_3_code": "ckq", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "204", "native_tokenizers": [], @@ -2505,9 +2435,11 @@ }, { "name": "Masmaje", + "depth": 6, "iso_1_code": null, "iso_3_code": "mes", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "205", "native_tokenizers": [], @@ -2515,9 +2447,11 @@ }, { "name": "Mubi", + "depth": 6, "iso_1_code": null, "iso_3_code": "mub", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "206", "native_tokenizers": [], @@ -2525,9 +2459,11 @@ }, { "name": "Toram", + "depth": 6, "iso_1_code": null, "iso_3_code": "trj", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "207", "native_tokenizers": [], @@ -2535,50 +2471,50 @@ }, { "name": "Zerenkel", + "depth": 6, "iso_1_code": null, "iso_3_code": "zrn", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "208", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "202", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "192", "native_tokenizers": [], "scripts": [] }, { "name": "B.2", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mukulu", + "depth": 5, "iso_1_code": null, "iso_3_code": "moz", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "210", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "209", "native_tokenizers": [], @@ -2586,14 +2522,17 @@ }, { "name": "B.3", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Barein", + "depth": 5, "iso_1_code": null, "iso_3_code": "bva", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "212", "native_tokenizers": [], @@ -2601,9 +2540,11 @@ }, { "name": "Saba", + "depth": 5, "iso_1_code": null, "iso_3_code": "saa", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "213", "native_tokenizers": [], @@ -2611,9 +2552,11 @@ }, { "name": "Sokoro", + "depth": 5, "iso_1_code": null, "iso_3_code": "sok", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "214", "native_tokenizers": [], @@ -2621,58 +2564,50 @@ }, { "name": "Tamki", + "depth": 5, "iso_1_code": null, "iso_3_code": "tax", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "215", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "211", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "191", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "165", "native_tokenizers": [], "scripts": [] }, { "name": "Masa", + "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Herd\u00e9", + "depth": 3, "iso_1_code": null, "iso_3_code": "hed", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "217", "native_tokenizers": [], @@ -2680,9 +2615,11 @@ }, { "name": "P\u00e9v\u00e9", + "depth": 3, "iso_1_code": null, "iso_3_code": "lme", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "218", "native_tokenizers": [], @@ -2690,18 +2627,12 @@ }, { "name": "Masana", + "depth": 3, "iso_1_code": null, "iso_3_code": "mcn", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "219", "native_tokenizers": [], "scripts": [ @@ -2710,38 +2641,26 @@ }, { "name": "Marba", + "depth": 3, "iso_1_code": null, "iso_3_code": "mpg", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "220", "native_tokenizers": [], "scripts": [ "Latn" - ] - }, - { - "name": "Musey", - "iso_1_code": null, - "iso_3_code": "mse", - "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + ] + }, + { + "name": "Musey", + "depth": 3, + "iso_1_code": null, + "iso_3_code": "mse", + "children": [], + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "221", "native_tokenizers": [], "scripts": [ @@ -2750,9 +2669,11 @@ }, { "name": "Ngete", + "depth": 3, "iso_1_code": null, "iso_3_code": "nnn", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "222", "native_tokenizers": [], @@ -2760,9 +2681,11 @@ }, { "name": "Mesme", + "depth": 3, "iso_1_code": null, "iso_3_code": "zim", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "223", "native_tokenizers": [], @@ -2770,48 +2693,48 @@ }, { "name": "Zumaya", + "depth": 3, "iso_1_code": null, "iso_3_code": "zuy", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "224", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "216", "native_tokenizers": [], "scripts": [] }, { "name": "West", + "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "A", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "A.1", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Gwandara", + "depth": 5, "iso_1_code": null, "iso_3_code": "gwn", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "228", "native_tokenizers": [], @@ -2819,18 +2742,12 @@ }, { "name": "Hausa", + "depth": 5, "iso_1_code": "ha", "iso_3_code": "hau", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "229", "native_tokenizers": [], "scripts": [ @@ -2838,39 +2755,37 @@ ] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "227", "native_tokenizers": [], "scripts": [] }, { "name": "A.2", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bole", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bole Proper", + "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bole", + "depth": 7, "iso_1_code": null, "iso_3_code": "bol", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "233", "native_tokenizers": [], @@ -2878,9 +2793,11 @@ }, { "name": "Bure", + "depth": 7, "iso_1_code": null, "iso_3_code": "bvh", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "234", "native_tokenizers": [], @@ -2888,9 +2805,11 @@ }, { "name": "Beele", + "depth": 7, "iso_1_code": null, "iso_3_code": "bxq", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "235", "native_tokenizers": [], @@ -2898,9 +2817,11 @@ }, { "name": "Deno", + "depth": 7, "iso_1_code": null, "iso_3_code": "dbb", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "236", "native_tokenizers": [], @@ -2908,9 +2829,11 @@ }, { "name": "Daza", + "depth": 7, "iso_1_code": null, "iso_3_code": "dzd", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "237", "native_tokenizers": [], @@ -2918,9 +2841,11 @@ }, { "name": "Geruma", + "depth": 7, "iso_1_code": null, "iso_3_code": "gea", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "238", "native_tokenizers": [], @@ -2928,9 +2853,11 @@ }, { "name": "Gera", + "depth": 7, "iso_1_code": null, "iso_3_code": "gew", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "239", "native_tokenizers": [], @@ -2938,9 +2865,11 @@ }, { "name": "Galambi", + "depth": 7, "iso_1_code": null, "iso_3_code": "glo", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "240", "native_tokenizers": [], @@ -2948,9 +2877,11 @@ }, { "name": "Giiwo", + "depth": 7, "iso_1_code": null, "iso_3_code": "kks", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "241", "native_tokenizers": [], @@ -2958,9 +2889,11 @@ }, { "name": "Kubi", + "depth": 7, "iso_1_code": null, "iso_3_code": "kof", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "242", "native_tokenizers": [], @@ -2968,9 +2901,11 @@ }, { "name": "Kholok", + "depth": 7, "iso_1_code": null, "iso_3_code": "ktc", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "243", "native_tokenizers": [], @@ -2978,9 +2913,11 @@ }, { "name": "Maaka", + "depth": 7, "iso_1_code": null, "iso_3_code": "mew", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "244", "native_tokenizers": [], @@ -2988,9 +2925,11 @@ }, { "name": "Ngamo", + "depth": 7, "iso_1_code": null, "iso_3_code": "nbh", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "245", "native_tokenizers": [], @@ -2998,15 +2937,18 @@ }, { "name": "Nyam", + "depth": 7, "iso_1_code": null, "iso_3_code": "nmi", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "246", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "232", "native_tokenizers": [], @@ -3014,26 +2956,31 @@ }, { "name": "Karekare", + "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Karekare", + "depth": 7, "iso_1_code": null, "iso_3_code": "kai", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "248", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "247", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "231", "native_tokenizers": [], @@ -3041,25 +2988,30 @@ }, { "name": "Tangale", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Dera", + "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Dera", + "depth": 7, "iso_1_code": null, "iso_3_code": "kna", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "251", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "250", "native_tokenizers": [], @@ -3067,14 +3019,17 @@ }, { "name": "Tangale Proper", + "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kutto", + "depth": 7, "iso_1_code": null, "iso_3_code": "kpa", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "253", "native_tokenizers": [], @@ -3082,9 +3037,11 @@ }, { "name": "Kwaami", + "depth": 7, "iso_1_code": null, "iso_3_code": "ksq", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "254", "native_tokenizers": [], @@ -3092,9 +3049,11 @@ }, { "name": "Kushi", + "depth": 7, "iso_1_code": null, "iso_3_code": "kuh", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "255", "native_tokenizers": [], @@ -3102,9 +3061,11 @@ }, { "name": "Pero", + "depth": 7, "iso_1_code": null, "iso_3_code": "pip", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "256", "native_tokenizers": [], @@ -3112,9 +3073,11 @@ }, { "name": "Piya-Kwonci", + "depth": 7, "iso_1_code": null, "iso_3_code": "piy", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "257", "native_tokenizers": [], @@ -3122,27 +3085,32 @@ }, { "name": "Tangale", + "depth": 7, "iso_1_code": null, "iso_3_code": "tan", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "258", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "252", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "249", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "230", "native_tokenizers": [], @@ -3150,19 +3118,23 @@ }, { "name": "A.3", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Angas Proper", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Jakattoe", + "depth": 6, "iso_1_code": null, "iso_3_code": "jrt", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "261", "native_tokenizers": [], @@ -3170,14 +3142,17 @@ }, { "name": "1", + "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ngas", + "depth": 7, "iso_1_code": null, "iso_3_code": "anc", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "263", "native_tokenizers": [], @@ -3185,9 +3160,11 @@ }, { "name": "Cakfem-Mushere", + "depth": 7, "iso_1_code": null, "iso_3_code": "cky", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "264", "native_tokenizers": [], @@ -3195,9 +3172,11 @@ }, { "name": "Belning", + "depth": 7, "iso_1_code": null, "iso_3_code": "glb", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "265", "native_tokenizers": [], @@ -3205,9 +3184,11 @@ }, { "name": "Kofyar", + "depth": 7, "iso_1_code": null, "iso_3_code": "kwl", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "266", "native_tokenizers": [], @@ -3215,9 +3196,11 @@ }, { "name": "Miship", + "depth": 7, "iso_1_code": null, "iso_3_code": "mjs", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "267", "native_tokenizers": [], @@ -3225,9 +3208,11 @@ }, { "name": "Nteng", + "depth": 7, "iso_1_code": null, "iso_3_code": "nqt", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "268", "native_tokenizers": [], @@ -3235,18 +3220,12 @@ }, { "name": "Mwaghavul", + "depth": 7, "iso_1_code": null, "iso_3_code": "sur", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "269", "native_tokenizers": [], "scripts": [ @@ -3254,29 +3233,25 @@ ] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "262", "native_tokenizers": [], "scripts": [] }, { "name": "2", + "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Goemai", + "depth": 7, "iso_1_code": null, "iso_3_code": "ank", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "271", "native_tokenizers": [], @@ -3284,9 +3259,11 @@ }, { "name": "Koenoem", + "depth": 7, "iso_1_code": null, "iso_3_code": "kcs", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "272", "native_tokenizers": [], @@ -3294,9 +3271,11 @@ }, { "name": "Tehl", + "depth": 7, "iso_1_code": null, "iso_3_code": "mtl", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "273", "native_tokenizers": [], @@ -3304,9 +3283,11 @@ }, { "name": "Piapung", + "depth": 7, "iso_1_code": null, "iso_3_code": "pcw", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "274", "native_tokenizers": [], @@ -3314,84 +3295,81 @@ }, { "name": "Tal", + "depth": 7, "iso_1_code": null, "iso_3_code": "tal", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "275", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "270", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "260", "native_tokenizers": [], "scripts": [] }, { "name": "Yiwom", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ywom", + "depth": 6, "iso_1_code": null, "iso_3_code": "gek", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "277", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "276", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "259", "native_tokenizers": [], "scripts": [] }, { "name": "A.4", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Fyer", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Fyer", + "depth": 6, "iso_1_code": null, "iso_3_code": "fie", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "280", "native_tokenizers": [], @@ -3399,15 +3377,18 @@ }, { "name": "Rom", + "depth": 6, "iso_1_code": null, "iso_3_code": "tdk", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "281", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "279", "native_tokenizers": [], @@ -3415,14 +3396,17 @@ }, { "name": "Ron Proper", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ron", + "depth": 6, "iso_1_code": null, "iso_3_code": "cla", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "283", "native_tokenizers": [], @@ -3430,9 +3414,11 @@ }, { "name": "Duhwa", + "depth": 6, "iso_1_code": null, "iso_3_code": "kbz", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "284", "native_tokenizers": [], @@ -3440,9 +3426,11 @@ }, { "name": "Kulere", + "depth": 6, "iso_1_code": null, "iso_3_code": "kul", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "285", "native_tokenizers": [], @@ -3450,9 +3438,11 @@ }, { "name": "Mindat", + "depth": 6, "iso_1_code": null, "iso_3_code": "mmf", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "286", "native_tokenizers": [], @@ -3460,55 +3450,56 @@ }, { "name": "Sya", + "depth": 6, "iso_1_code": null, "iso_3_code": "scw", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "287", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "282", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "278", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "226", "native_tokenizers": [], "scripts": [] }, { "name": "B", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "B.1", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Teshenawa", + "depth": 5, "iso_1_code": null, "iso_3_code": "twc", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "290", "native_tokenizers": [], @@ -3516,14 +3507,17 @@ }, { "name": "Bade Proper", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bade", + "depth": 6, "iso_1_code": null, "iso_3_code": "bde", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "292", "native_tokenizers": [], @@ -3531,15 +3525,18 @@ }, { "name": "Ngizim", + "depth": 6, "iso_1_code": null, "iso_3_code": "ngi", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "293", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "291", "native_tokenizers": [], @@ -3547,26 +3544,31 @@ }, { "name": "Duwai", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Duwai", + "depth": 6, "iso_1_code": null, "iso_3_code": "dbp", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "295", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "294", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "289", "native_tokenizers": [], @@ -3574,14 +3576,17 @@ }, { "name": "B.2", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ajawa", + "depth": 5, "iso_1_code": null, "iso_3_code": "ajw", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "297", "native_tokenizers": [], @@ -3589,9 +3594,11 @@ }, { "name": "Burku", + "depth": 5, "iso_1_code": null, "iso_3_code": "bbt", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "298", "native_tokenizers": [], @@ -3599,9 +3606,11 @@ }, { "name": "Dirya", + "depth": 5, "iso_1_code": null, "iso_3_code": "dwa", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "299", "native_tokenizers": [], @@ -3609,9 +3618,11 @@ }, { "name": "Zibinju", + "depth": 5, "iso_1_code": null, "iso_3_code": "jmb", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "300", "native_tokenizers": [], @@ -3619,9 +3630,11 @@ }, { "name": "Kariya", + "depth": 5, "iso_1_code": null, "iso_3_code": "kil", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "301", "native_tokenizers": [], @@ -3629,9 +3642,11 @@ }, { "name": "Vune mi", + "depth": 5, "iso_1_code": null, "iso_3_code": "mkf", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "302", "native_tokenizers": [], @@ -3639,9 +3654,11 @@ }, { "name": "Pa\u2019anci", + "depth": 5, "iso_1_code": null, "iso_3_code": "pqa", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "303", "native_tokenizers": [], @@ -3649,9 +3666,11 @@ }, { "name": "Siri", + "depth": 5, "iso_1_code": null, "iso_3_code": "sir", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "304", "native_tokenizers": [], @@ -3659,9 +3678,11 @@ }, { "name": "Choogen", + "depth": 5, "iso_1_code": null, "iso_3_code": "tgd", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "305", "native_tokenizers": [], @@ -3669,15 +3690,18 @@ }, { "name": "Warji", + "depth": 5, "iso_1_code": null, "iso_3_code": "wji", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "306", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "296", "native_tokenizers": [], @@ -3685,14 +3709,17 @@ }, { "name": "B.3", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Dass", + "depth": 5, "iso_1_code": null, "iso_3_code": "dot", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "308", "native_tokenizers": [], @@ -3700,14 +3727,17 @@ }, { "name": "Boghom", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Boghom", + "depth": 6, "iso_1_code": null, "iso_3_code": "bux", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "310", "native_tokenizers": [], @@ -3715,9 +3745,11 @@ }, { "name": "Kir-Balar", + "depth": 6, "iso_1_code": null, "iso_3_code": "kkr", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "311", "native_tokenizers": [], @@ -3725,15 +3757,18 @@ }, { "name": "Mansi", + "depth": 6, "iso_1_code": null, "iso_3_code": "zns", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "312", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "309", "native_tokenizers": [], @@ -3741,20 +3776,24 @@ }, { "name": "Eastern", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Jimi", + "depth": 6, "iso_1_code": null, "iso_3_code": "jmi", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "314", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "313", "native_tokenizers": [], @@ -3762,14 +3801,17 @@ }, { "name": "Guruntum", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Guruntum-Mbaaru", + "depth": 6, "iso_1_code": null, "iso_3_code": "grd", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "316", "native_tokenizers": [], @@ -3777,9 +3819,11 @@ }, { "name": "Juu", + "depth": 6, "iso_1_code": null, "iso_3_code": "juu", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "317", "native_tokenizers": [], @@ -3787,9 +3831,11 @@ }, { "name": "Tala", + "depth": 6, "iso_1_code": null, "iso_3_code": "tak", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "318", "native_tokenizers": [], @@ -3797,15 +3843,18 @@ }, { "name": "Zamwal", + "depth": 6, "iso_1_code": null, "iso_3_code": "zah", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "319", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "315", "native_tokenizers": [], @@ -3813,14 +3862,17 @@ }, { "name": "Zaar Proper", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Cha\u2019ari", + "depth": 6, "iso_1_code": null, "iso_3_code": "cxh", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "321", "native_tokenizers": [], @@ -3828,9 +3880,11 @@ }, { "name": "Dokshi", + "depth": 6, "iso_1_code": null, "iso_3_code": "dsk", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "322", "native_tokenizers": [], @@ -3838,9 +3892,11 @@ }, { "name": "Dyarim", + "depth": 6, "iso_1_code": null, "iso_3_code": "dyr", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "323", "native_tokenizers": [], @@ -3848,9 +3904,11 @@ }, { "name": "Gyaazi", + "depth": 6, "iso_1_code": null, "iso_3_code": "gyz", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "324", "native_tokenizers": [], @@ -3858,9 +3916,11 @@ }, { "name": "Luri", + "depth": 6, "iso_1_code": null, "iso_3_code": "ldd", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "325", "native_tokenizers": [], @@ -3868,9 +3928,11 @@ }, { "name": "Dir-Nyamzak-Mbarimi", + "depth": 6, "iso_1_code": null, "iso_3_code": "nzr", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "326", "native_tokenizers": [], @@ -3878,9 +3940,11 @@ }, { "name": "Pesse", + "depth": 6, "iso_1_code": null, "iso_3_code": "pze", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "327", "native_tokenizers": [], @@ -3888,18 +3952,12 @@ }, { "name": "Saya", + "depth": 6, "iso_1_code": null, "iso_3_code": "say", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "328", "native_tokenizers": [], "scripts": [ @@ -3908,9 +3966,11 @@ }, { "name": "Tulai", + "depth": 6, "iso_1_code": null, "iso_3_code": "tvi", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "329", "native_tokenizers": [], @@ -3918,9 +3978,11 @@ }, { "name": "Buli", + "depth": 6, "iso_1_code": null, "iso_3_code": "uly", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "330", "native_tokenizers": [], @@ -3928,9 +3990,11 @@ }, { "name": "Zari", + "depth": 6, "iso_1_code": null, "iso_3_code": "zaz", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "331", "native_tokenizers": [], @@ -3938,9 +4002,11 @@ }, { "name": "Bu", + "depth": 6, "iso_1_code": null, "iso_3_code": "zbu", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "332", "native_tokenizers": [], @@ -3948,9 +4014,11 @@ }, { "name": "Zeem", + "depth": 6, "iso_1_code": null, "iso_3_code": "zem", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "333", "native_tokenizers": [], @@ -3958,110 +4026,83 @@ }, { "name": "Zul", + "depth": 6, "iso_1_code": null, "iso_3_code": "zlu", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "334", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "320", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "307", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "288", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "225", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "56", "native_tokenizers": [], "scripts": [] }, { "name": "Cushitic", + "depth": 1, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Central", + "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Eastern", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Xamtanga", + "depth": 4, "iso_1_code": null, "iso_3_code": "xan", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "338", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "337", "native_tokenizers": [], @@ -4069,20 +4110,24 @@ }, { "name": "Northern", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bilen", + "depth": 4, "iso_1_code": null, "iso_3_code": "byn", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "340", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "339", "native_tokenizers": [], @@ -4090,20 +4135,24 @@ }, { "name": "Southern", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Awngi", + "depth": 4, "iso_1_code": null, "iso_3_code": "awn", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "342", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "341", "native_tokenizers": [], @@ -4111,26 +4160,31 @@ }, { "name": "Western", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Qimant", + "depth": 4, "iso_1_code": null, "iso_3_code": "ahg", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "344", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "343", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "336", "native_tokenizers": [], @@ -4138,14 +4192,17 @@ }, { "name": "East", + "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Boon", + "depth": 3, "iso_1_code": null, "iso_3_code": "bnl", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "346", "native_tokenizers": [], @@ -4153,14 +4210,17 @@ }, { "name": "Dullay", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ale", + "depth": 4, "iso_1_code": null, "iso_3_code": "gwd", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "348", "native_tokenizers": [], @@ -4168,15 +4228,18 @@ }, { "name": "Tsamai", + "depth": 4, "iso_1_code": null, "iso_3_code": "tsb", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "349", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "347", "native_tokenizers": [], @@ -4184,14 +4247,17 @@ }, { "name": "Highland", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Alaba-K\u2019abeena", + "depth": 4, "iso_1_code": null, "iso_3_code": "alw", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "351", "native_tokenizers": [], @@ -4199,9 +4265,11 @@ }, { "name": "Burji", + "depth": 4, "iso_1_code": null, "iso_3_code": "bji", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "352", "native_tokenizers": [], @@ -4209,9 +4277,11 @@ }, { "name": "Gedeo", + "depth": 4, "iso_1_code": null, "iso_3_code": "drs", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "353", "native_tokenizers": [], @@ -4219,9 +4289,11 @@ }, { "name": "Hadiyya", + "depth": 4, "iso_1_code": null, "iso_3_code": "hdy", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "354", "native_tokenizers": [], @@ -4229,18 +4301,12 @@ }, { "name": "Kambaata", + "depth": 4, "iso_1_code": null, "iso_3_code": "ktb", "children": [], - "tokenizers": { - "Ethi": { - "full_object": "SpaCyTokenizer(\"am\")", - "original_lang_name": "amharic", - "original_lang_code": "amh", - "script": "Ethi", - "class_name": "SpaCyTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "355", "native_tokenizers": [], "scripts": [ @@ -4249,9 +4315,11 @@ }, { "name": "Libido", + "depth": 4, "iso_1_code": null, "iso_3_code": "liq", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "356", "native_tokenizers": [], @@ -4259,18 +4327,12 @@ }, { "name": "Sidamo", + "depth": 4, "iso_1_code": null, "iso_3_code": "sid", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "357", "native_tokenizers": [], "scripts": [ @@ -4278,36 +4340,25 @@ ] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - }, - "Ethi": { - "full_object": "SpaCyTokenizer(\"am\")", - "original_lang_name": "amharic", - "original_lang_code": "amh", - "script": "Ethi", - "class_name": "SpaCyTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "350", "native_tokenizers": [], "scripts": [] }, { "name": "Konso-Gidole", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mositacha", + "depth": 4, "iso_1_code": null, "iso_3_code": "dox", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "359", "native_tokenizers": [], @@ -4315,9 +4366,11 @@ }, { "name": "Dirasha", + "depth": 4, "iso_1_code": null, "iso_3_code": "gdl", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "360", "native_tokenizers": [], @@ -4325,18 +4378,12 @@ }, { "name": "Konso", + "depth": 4, "iso_1_code": null, "iso_3_code": "kxc", "children": [], - "tokenizers": { - "Ethi": { - "full_object": "SpaCyTokenizer(\"am\")", - "original_lang_name": "amharic", - "original_lang_code": "amh", - "script": "Ethi", - "class_name": "SpaCyTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "361", "native_tokenizers": [], "scripts": [ @@ -4344,29 +4391,25 @@ ] } ], - "tokenizers": { - "Ethi": { - "full_object": "SpaCyTokenizer(\"am\")", - "original_lang_name": "amharic", - "original_lang_code": "amh", - "script": "Ethi", - "class_name": "SpaCyTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "358", "native_tokenizers": [], "scripts": [] }, { "name": "Oromo", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Oromo, Borana-Arsi-Guji", + "depth": 4, "iso_1_code": "om", "iso_3_code": "gax", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "363", "native_tokenizers": [], @@ -4374,18 +4417,12 @@ }, { "name": "Oromo, West Central", + "depth": 4, "iso_1_code": "om", "iso_3_code": "gaz", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "364", "native_tokenizers": [], "scripts": [ @@ -4394,18 +4431,12 @@ }, { "name": "Oromo, Eastern", + "depth": 4, "iso_1_code": "om", "iso_3_code": "hae", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "365", "native_tokenizers": [], "scripts": [ @@ -4414,9 +4445,11 @@ }, { "name": "Orma", + "depth": 4, "iso_1_code": "om", "iso_3_code": "orc", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "366", "native_tokenizers": [], @@ -4424,38 +4457,36 @@ }, { "name": "Waata", + "depth": 4, "iso_1_code": null, "iso_3_code": "ssn", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "367", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "362", "native_tokenizers": [], "scripts": [] }, { "name": "Rendille-Boni", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Aweer", + "depth": 4, "iso_1_code": null, "iso_3_code": "bob", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "369", "native_tokenizers": [], @@ -4463,18 +4494,12 @@ }, { "name": "Rendille", + "depth": 4, "iso_1_code": null, "iso_3_code": "rel", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "370", "native_tokenizers": [], "scripts": [ @@ -4482,29 +4507,25 @@ ] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "368", "native_tokenizers": [], "scripts": [] }, { "name": "Saho-Afar", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Afar", + "depth": 4, "iso_1_code": "aa", "iso_3_code": "aar", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "372", "native_tokenizers": [], @@ -4512,15 +4533,18 @@ }, { "name": "Saho", + "depth": 4, "iso_1_code": null, "iso_3_code": "ssy", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "373", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "371", "native_tokenizers": [], @@ -4528,14 +4552,17 @@ }, { "name": "Somali", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Dabarre", + "depth": 4, "iso_1_code": null, "iso_3_code": "dbr", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "375", "native_tokenizers": [], @@ -4543,9 +4570,11 @@ }, { "name": "Garre", + "depth": 4, "iso_1_code": null, "iso_3_code": "gex", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "376", "native_tokenizers": [], @@ -4553,9 +4582,11 @@ }, { "name": "Girirra", + "depth": 4, "iso_1_code": null, "iso_3_code": "gii", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "377", "native_tokenizers": [], @@ -4563,9 +4594,11 @@ }, { "name": "Jiiddu", + "depth": 4, "iso_1_code": null, "iso_3_code": "jii", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "378", "native_tokenizers": [], @@ -4573,18 +4606,12 @@ }, { "name": "Somali", + "depth": 4, "iso_1_code": "so", "iso_3_code": "som", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "379", "native_tokenizers": [], "scripts": [ @@ -4593,9 +4620,11 @@ }, { "name": "Tunni", + "depth": 4, "iso_1_code": null, "iso_3_code": "tqq", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "380", "native_tokenizers": [], @@ -4603,38 +4632,36 @@ }, { "name": "Maay", + "depth": 4, "iso_1_code": null, "iso_3_code": "ymm", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "381", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "374", "native_tokenizers": [], "scripts": [] }, { "name": "Western Omo-Tana", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Arbore", + "depth": 4, "iso_1_code": null, "iso_3_code": "arv", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "383", "native_tokenizers": [], @@ -4642,9 +4669,11 @@ }, { "name": "Baiso", + "depth": 4, "iso_1_code": null, "iso_3_code": "bsw", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "384", "native_tokenizers": [], @@ -4652,18 +4681,12 @@ }, { "name": "Daasanach", + "depth": 4, "iso_1_code": null, "iso_3_code": "dsh", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "385", "native_tokenizers": [], "scripts": [ @@ -4672,86 +4695,75 @@ }, { "name": "El Molo", + "depth": 4, "iso_1_code": null, "iso_3_code": "elo", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "386", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "382", "native_tokenizers": [], "scripts": [] }, { "name": "Yaaku", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Yaaku", + "depth": 4, "iso_1_code": null, "iso_3_code": "muu", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "388", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "387", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - }, - "Ethi": { - "full_object": "SpaCyTokenizer(\"am\")", - "original_lang_name": "amharic", - "original_lang_code": "amh", - "script": "Ethi", - "class_name": "SpaCyTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "345", "native_tokenizers": [], "scripts": [] }, { "name": "North", + "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bedawiyet", + "depth": 3, "iso_1_code": null, "iso_3_code": "bej", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "390", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "389", "native_tokenizers": [], @@ -4759,14 +4771,17 @@ }, { "name": "South", + "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Aas\u00e1x", + "depth": 3, "iso_1_code": null, "iso_3_code": "aas", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "392", "native_tokenizers": [], @@ -4774,9 +4789,11 @@ }, { "name": "Burunge", + "depth": 3, "iso_1_code": null, "iso_3_code": "bds", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "393", "native_tokenizers": [], @@ -4784,9 +4801,11 @@ }, { "name": "Dahalo", + "depth": 3, "iso_1_code": null, "iso_3_code": "dal", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "394", "native_tokenizers": [], @@ -4794,9 +4813,11 @@ }, { "name": "Gorowa", + "depth": 3, "iso_1_code": null, "iso_3_code": "gow", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "395", "native_tokenizers": [], @@ -4804,18 +4825,12 @@ }, { "name": "Iraqw", + "depth": 3, "iso_1_code": null, "iso_3_code": "irk", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "396", "native_tokenizers": [], "scripts": [ @@ -4824,9 +4839,11 @@ }, { "name": "Alagwa", + "depth": 3, "iso_1_code": null, "iso_3_code": "wbj", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "397", "native_tokenizers": [], @@ -4834,59 +4851,43 @@ }, { "name": "Kw\u2019adza", + "depth": 3, "iso_1_code": null, "iso_3_code": "wka", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "398", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "391", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - }, - "Ethi": { - "full_object": "SpaCyTokenizer(\"am\")", - "original_lang_name": "amharic", - "original_lang_code": "amh", - "script": "Ethi", - "class_name": "SpaCyTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "335", "native_tokenizers": [], "scripts": [] }, { "name": "Egyptian", + "depth": 1, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Coptic", + "depth": 2, "iso_1_code": null, "iso_3_code": "cop", "children": [], + "family": "Afro-Asiatic", "tokenizers": { "Copt": { "full_object": "StanzaTokenizer(\"cop\")", @@ -4905,6 +4906,7 @@ ] } ], + "family": "Afro-Asiatic", "tokenizers": { "Copt": { "full_object": "StanzaTokenizer(\"cop\")", @@ -4920,24 +4922,29 @@ }, { "name": "Omotic", + "depth": 1, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "North", + "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Dizoid", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Dizin", + "depth": 4, "iso_1_code": null, "iso_3_code": "mdx", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "404", "native_tokenizers": [], @@ -4945,9 +4952,11 @@ }, { "name": "Nayi", + "depth": 4, "iso_1_code": null, "iso_3_code": "noz", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "405", "native_tokenizers": [], @@ -4955,15 +4964,18 @@ }, { "name": "Sheko", + "depth": 4, "iso_1_code": null, "iso_3_code": "she", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "406", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "403", "native_tokenizers": [], @@ -4971,30 +4983,36 @@ }, { "name": "Gonga-Gimojan", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Gimojan", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Janjero", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Yemsa", + "depth": 6, "iso_1_code": null, "iso_3_code": "jnj", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "410", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "409", "native_tokenizers": [], @@ -5002,25 +5020,30 @@ }, { "name": "Ometo-Gimira", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Chara", + "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Tsaara", + "depth": 7, "iso_1_code": null, "iso_3_code": "cra", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "413", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "412", "native_tokenizers": [], @@ -5028,20 +5051,24 @@ }, { "name": "Gimira", + "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bench", + "depth": 7, "iso_1_code": null, "iso_3_code": "bcq", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "415", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "414", "native_tokenizers": [], @@ -5049,23 +5076,18 @@ }, { "name": "Ometo", + "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Male", + "depth": 7, "iso_1_code": null, "iso_3_code": "mdy", "children": [], - "tokenizers": { - "Ethi": { - "full_object": "SpaCyTokenizer(\"am\")", - "original_lang_name": "amharic", - "original_lang_code": "amh", - "script": "Ethi", - "class_name": "SpaCyTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "417", "native_tokenizers": [], "scripts": [ @@ -5074,14 +5096,17 @@ }, { "name": "Central", + "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Dorze", + "depth": 8, "iso_1_code": null, "iso_3_code": "doz", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "419", "native_tokenizers": [], @@ -5089,18 +5114,12 @@ }, { "name": "Dawro", + "depth": 8, "iso_1_code": null, "iso_3_code": "dwr", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "420", "native_tokenizers": [], "scripts": [ @@ -5109,25 +5128,12 @@ }, { "name": "Gamo", + "depth": 8, "iso_1_code": null, "iso_3_code": "gmv", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - }, - "Ethi": { - "full_object": "SpaCyTokenizer(\"am\")", - "original_lang_name": "amharic", - "original_lang_code": "amh", - "script": "Ethi", - "class_name": "SpaCyTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "421", "native_tokenizers": [], "scripts": [ @@ -5137,25 +5143,12 @@ }, { "name": "Gofa", + "depth": 8, "iso_1_code": null, "iso_3_code": "gof", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - }, - "Ethi": { - "full_object": "SpaCyTokenizer(\"am\")", - "original_lang_name": "amharic", - "original_lang_code": "amh", - "script": "Ethi", - "class_name": "SpaCyTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "422", "native_tokenizers": [], "scripts": [ @@ -5165,9 +5158,11 @@ }, { "name": "Melo", + "depth": 8, "iso_1_code": null, "iso_3_code": "mfx", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "423", "native_tokenizers": [], @@ -5175,9 +5170,11 @@ }, { "name": "Oyda", + "depth": 8, "iso_1_code": null, "iso_3_code": "oyd", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "424", "native_tokenizers": [], @@ -5185,25 +5182,12 @@ }, { "name": "Wolaytta", + "depth": 8, "iso_1_code": null, "iso_3_code": "wal", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - }, - "Ethi": { - "full_object": "SpaCyTokenizer(\"am\")", - "original_lang_name": "amharic", - "original_lang_code": "amh", - "script": "Ethi", - "class_name": "SpaCyTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "425", "native_tokenizers": [], "scripts": [ @@ -5212,36 +5196,25 @@ ] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - }, - "Ethi": { - "full_object": "SpaCyTokenizer(\"am\")", - "original_lang_name": "amharic", - "original_lang_code": "amh", - "script": "Ethi", - "class_name": "SpaCyTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "418", "native_tokenizers": [], "scripts": [] }, { "name": "East", + "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kachama-Ganjule", + "depth": 8, "iso_1_code": null, "iso_3_code": "kcx", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "427", "native_tokenizers": [], @@ -5249,18 +5222,12 @@ }, { "name": "Koorete", + "depth": 8, "iso_1_code": null, "iso_3_code": "kqy", "children": [], - "tokenizers": { - "Ethi": { - "full_object": "SpaCyTokenizer(\"am\")", - "original_lang_name": "amharic", - "original_lang_code": "amh", - "script": "Ethi", - "class_name": "SpaCyTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "428", "native_tokenizers": [], "scripts": [ @@ -5269,133 +5236,95 @@ }, { "name": "Zayse", + "depth": 8, "iso_1_code": null, "iso_3_code": "zay", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "429", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Ethi": { - "full_object": "SpaCyTokenizer(\"am\")", - "original_lang_name": "amharic", - "original_lang_code": "amh", - "script": "Ethi", - "class_name": "SpaCyTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "426", "native_tokenizers": [], "scripts": [] }, { "name": "West", + "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Basketo", + "depth": 8, "iso_1_code": null, "iso_3_code": "bst", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "431", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "430", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - }, - "Ethi": { - "full_object": "SpaCyTokenizer(\"am\")", - "original_lang_name": "amharic", - "original_lang_code": "amh", - "script": "Ethi", - "class_name": "SpaCyTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "416", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - }, - "Ethi": { - "full_object": "SpaCyTokenizer(\"am\")", - "original_lang_name": "amharic", - "original_lang_code": "amh", - "script": "Ethi", - "class_name": "SpaCyTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "411", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - }, - "Ethi": { - "full_object": "SpaCyTokenizer(\"am\")", - "original_lang_name": "amharic", - "original_lang_code": "amh", - "script": "Ethi", - "class_name": "SpaCyTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "408", "native_tokenizers": [], "scripts": [] }, { "name": "Gonga", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Central", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Anfillo", + "depth": 6, "iso_1_code": null, "iso_3_code": "myo", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "434", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "433", "native_tokenizers": [], @@ -5403,20 +5332,24 @@ }, { "name": "North", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Borna", + "depth": 6, "iso_1_code": null, "iso_3_code": "bwo", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "436", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "435", "native_tokenizers": [], @@ -5424,23 +5357,18 @@ }, { "name": "South", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Kafa", + "depth": 6, "iso_1_code": null, "iso_3_code": "kbr", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "438", "native_tokenizers": [], "scripts": [ @@ -5449,73 +5377,50 @@ }, { "name": "Shekkacho", + "depth": 6, "iso_1_code": null, "iso_3_code": "moy", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "439", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "437", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "432", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - }, - "Ethi": { - "full_object": "SpaCyTokenizer(\"am\")", - "original_lang_name": "amharic", - "original_lang_code": "amh", - "script": "Ethi", - "class_name": "SpaCyTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "407", "native_tokenizers": [], "scripts": [] }, { "name": "Mao", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ganza", + "depth": 4, "iso_1_code": null, "iso_3_code": "gza", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "441", "native_tokenizers": [], @@ -5523,9 +5428,11 @@ }, { "name": "Hozo", + "depth": 4, "iso_1_code": null, "iso_3_code": "hoz", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "442", "native_tokenizers": [], @@ -5533,9 +5440,11 @@ }, { "name": "Mawes Aasse", + "depth": 4, "iso_1_code": null, "iso_3_code": "myf", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "443", "native_tokenizers": [], @@ -5543,51 +5452,43 @@ }, { "name": "Seze", + "depth": 4, "iso_1_code": null, "iso_3_code": "sze", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "444", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "440", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - }, - "Ethi": { - "full_object": "SpaCyTokenizer(\"am\")", - "original_lang_name": "amharic", - "original_lang_code": "amh", - "script": "Ethi", - "class_name": "SpaCyTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "402", "native_tokenizers": [], "scripts": [] }, { "name": "South", + "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Aari", + "depth": 3, "iso_1_code": null, "iso_3_code": "aiw", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "446", "native_tokenizers": [], @@ -5595,18 +5496,12 @@ }, { "name": "Hamer-Banna", + "depth": 3, "iso_1_code": null, "iso_3_code": "amf", "children": [], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "447", "native_tokenizers": [], "scripts": [ @@ -5615,9 +5510,11 @@ }, { "name": "Dime", + "depth": 3, "iso_1_code": null, "iso_3_code": "dim", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "448", "native_tokenizers": [], @@ -5625,9 +5522,11 @@ }, { "name": "Gayil", + "depth": 3, "iso_1_code": null, "iso_3_code": "gyl", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "449", "native_tokenizers": [], @@ -5635,64 +5534,49 @@ }, { "name": "Karo", + "depth": 3, "iso_1_code": null, "iso_3_code": "kxh", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "450", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "445", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - }, - "Ethi": { - "full_object": "SpaCyTokenizer(\"am\")", - "original_lang_name": "amharic", - "original_lang_code": "amh", - "script": "Ethi", - "class_name": "SpaCyTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "401", "native_tokenizers": [], "scripts": [] }, { "name": "Semitic", + "depth": 1, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Central", + "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Faifi", + "depth": 3, "iso_1_code": null, "iso_3_code": "fif", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "453", "native_tokenizers": [], @@ -5700,9 +5584,11 @@ }, { "name": "R\u0101zi\u1e25\u012b", + "depth": 3, "iso_1_code": null, "iso_3_code": "rzh", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "454", "native_tokenizers": [], @@ -5710,19 +5596,23 @@ }, { "name": "Aramaic", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Eastern", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Syriac", + "depth": 5, "iso_1_code": null, "iso_3_code": "syc", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "457", "native_tokenizers": [], @@ -5732,19 +5622,23 @@ }, { "name": "Central", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Northeastern", + "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Assyrian Neo-Aramaic", + "depth": 7, "iso_1_code": null, "iso_3_code": "aii", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "460", "native_tokenizers": [], @@ -5754,9 +5648,11 @@ }, { "name": "Bohtan Neo-Aramaic", + "depth": 7, "iso_1_code": null, "iso_3_code": "bhn", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "461", "native_tokenizers": [], @@ -5764,9 +5660,11 @@ }, { "name": "Barzani-Sandu Jewish Neo-Aramaic", + "depth": 7, "iso_1_code": null, "iso_3_code": "bjf", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "462", "native_tokenizers": [], @@ -5774,9 +5672,11 @@ }, { "name": "Chaldean Neo-Aramaic", + "depth": 7, "iso_1_code": null, "iso_3_code": "cld", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "463", "native_tokenizers": [], @@ -5784,9 +5684,11 @@ }, { "name": "H\u00e9rtevin", + "depth": 7, "iso_1_code": null, "iso_3_code": "hrt", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "464", "native_tokenizers": [], @@ -5794,9 +5696,11 @@ }, { "name": "Koy Sanjaq Surat", + "depth": 7, "iso_1_code": null, "iso_3_code": "kqd", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "465", "native_tokenizers": [], @@ -5804,9 +5708,11 @@ }, { "name": "Senaya", + "depth": 7, "iso_1_code": null, "iso_3_code": "syn", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "466", "native_tokenizers": [], @@ -5814,9 +5720,11 @@ }, { "name": "Jewish Babylonian Aramaic", + "depth": 7, "iso_1_code": null, "iso_3_code": "tmr", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "467", "native_tokenizers": [], @@ -5824,14 +5732,17 @@ }, { "name": "Trans-Zab", + "depth": 7, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Inter-Zab Jewish Neo-Aramaic", + "depth": 8, "iso_1_code": null, "iso_3_code": "aij", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "469", "native_tokenizers": [], @@ -5839,9 +5750,11 @@ }, { "name": "Hulaul\u00e1", + "depth": 8, "iso_1_code": null, "iso_3_code": "huy", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "470", "native_tokenizers": [], @@ -5849,9 +5762,11 @@ }, { "name": "Lishana Deni", + "depth": 8, "iso_1_code": null, "iso_3_code": "lsd", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "471", "native_tokenizers": [], @@ -5859,21 +5774,25 @@ }, { "name": "Lish\u00e1n Noshan", + "depth": 8, "iso_1_code": null, "iso_3_code": "trg", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "472", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "468", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "459", "native_tokenizers": [], @@ -5881,14 +5800,17 @@ }, { "name": "Northwestern", + "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Mlahs\u00f6", + "depth": 7, "iso_1_code": null, "iso_3_code": "lhs", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "474", "native_tokenizers": [], @@ -5896,21 +5818,25 @@ }, { "name": "Turoyo", + "depth": 7, "iso_1_code": null, "iso_3_code": "tru", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "475", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "473", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "458", "native_tokenizers": [], @@ -5918,14 +5844,17 @@ }, { "name": "Mandaic", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Neo-Mandaic", + "depth": 6, "iso_1_code": null, "iso_3_code": "mid", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "477", "native_tokenizers": [], @@ -5933,21 +5862,25 @@ }, { "name": "Mandaic, Classical", + "depth": 6, "iso_1_code": null, "iso_3_code": "myz", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "478", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "476", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "456", "native_tokenizers": [], @@ -5955,14 +5888,17 @@ }, { "name": "Western", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Western Neo-Aramaic", + "depth": 5, "iso_1_code": null, "iso_3_code": "amw", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "480", "native_tokenizers": [], @@ -5970,21 +5906,25 @@ }, { "name": "Samaritan Aramaic", + "depth": 5, "iso_1_code": null, "iso_3_code": "sam", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "481", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "479", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "455", "native_tokenizers": [], @@ -5992,19 +5932,23 @@ }, { "name": "South", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Arabic", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Arabic, Algerian Saharan", + "depth": 5, "iso_1_code": "ar", "iso_3_code": "aao", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "484", "native_tokenizers": [], @@ -6012,9 +5956,11 @@ }, { "name": "Arabic, Tajiki", + "depth": 5, "iso_1_code": "ar", "iso_3_code": "abh", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "485", "native_tokenizers": [], @@ -6022,9 +5968,11 @@ }, { "name": "Arabic, Baharna", + "depth": 5, "iso_1_code": "ar", "iso_3_code": "abv", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "486", "native_tokenizers": [], @@ -6032,9 +5980,11 @@ }, { "name": "Arabic, Mesopotamian", + "depth": 5, "iso_1_code": "ar", "iso_3_code": "acm", "children": [], + "family": "Afro-Asiatic", "tokenizers": { "Arab": { "full_object": "SpaCyTokenizer(\"ar\")", @@ -6054,9 +6004,11 @@ }, { "name": "Arabic, Ta\u2019izzi-Adeni", + "depth": 5, "iso_1_code": "ar", "iso_3_code": "acq", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "488", "native_tokenizers": [], @@ -6064,9 +6016,11 @@ }, { "name": "Arabic, Hijazi", + "depth": 5, "iso_1_code": "ar", "iso_3_code": "acw", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "489", "native_tokenizers": [], @@ -6074,9 +6028,11 @@ }, { "name": "Arabic, Omani", + "depth": 5, "iso_1_code": "ar", "iso_3_code": "acx", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "490", "native_tokenizers": [], @@ -6084,9 +6040,11 @@ }, { "name": "Arabic, Cypriot", + "depth": 5, "iso_1_code": "ar", "iso_3_code": "acy", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "491", "native_tokenizers": [], @@ -6094,9 +6052,11 @@ }, { "name": "Arabic, Dhofari", + "depth": 5, "iso_1_code": "ar", "iso_3_code": "adf", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "492", "native_tokenizers": [], @@ -6104,9 +6064,11 @@ }, { "name": "Arabic, Tunisian", + "depth": 5, "iso_1_code": "ar", "iso_3_code": "aeb", "children": [], + "family": "Afro-Asiatic", "tokenizers": { "Arab": { "full_object": "SpaCyTokenizer(\"ar\")", @@ -6126,9 +6088,11 @@ }, { "name": "Arabic, Sa\u2019idi", + "depth": 5, "iso_1_code": "ar", "iso_3_code": "aec", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "494", "native_tokenizers": [], @@ -6136,9 +6100,11 @@ }, { "name": "Arabic, Gulf", + "depth": 5, "iso_1_code": "ar", "iso_3_code": "afb", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "495", "native_tokenizers": [], @@ -6146,9 +6112,11 @@ }, { "name": "Arabic, Judeo-Moroccan", + "depth": 5, "iso_1_code": null, "iso_3_code": "aju", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "496", "native_tokenizers": [], @@ -6156,9 +6124,11 @@ }, { "name": "Arabic, Levantine", + "depth": 5, "iso_1_code": "ar", "iso_3_code": "apc", "children": [], + "family": "Afro-Asiatic", "tokenizers": { "Arab": { "full_object": "SpaCyTokenizer(\"ar\")", @@ -6178,9 +6148,11 @@ }, { "name": "Arabic, Sudanese", + "depth": 5, "iso_1_code": "ar", "iso_3_code": "apd", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "498", "native_tokenizers": [], @@ -6188,9 +6160,11 @@ }, { "name": "Arabic, Standard", + "depth": 5, "iso_1_code": "ar", "iso_3_code": "arb", "children": [], + "family": "Afro-Asiatic", "tokenizers": { "Arab": { "full_object": "SpaCyTokenizer(\"ar\")", @@ -6218,9 +6192,11 @@ }, { "name": "Arabic, Algerian", + "depth": 5, "iso_1_code": "ar", "iso_3_code": "arq", "children": [], + "family": "Afro-Asiatic", "tokenizers": { "Arab": { "full_object": "SpaCyTokenizer(\"ar\")", @@ -6240,9 +6216,11 @@ }, { "name": "Arabic, Najdi", + "depth": 5, "iso_1_code": "ar", "iso_3_code": "ars", "children": [], + "family": "Afro-Asiatic", "tokenizers": { "Arab": { "full_object": "SpaCyTokenizer(\"ar\")", @@ -6262,9 +6240,11 @@ }, { "name": "Arabic, Moroccan", + "depth": 5, "iso_1_code": "ar", "iso_3_code": "ary", "children": [], + "family": "Afro-Asiatic", "tokenizers": { "Arab": { "full_object": "SpaCyTokenizer(\"ar\")", @@ -6284,9 +6264,11 @@ }, { "name": "Arabic, Egyptian", + "depth": 5, "iso_1_code": "ar", "iso_3_code": "arz", "children": [], + "family": "Afro-Asiatic", "tokenizers": { "Arab": { "full_object": "SpaCyTokenizer(\"ar\")", @@ -6306,9 +6288,11 @@ }, { "name": "Arabic, Uzbeki", + "depth": 5, "iso_1_code": "ar", "iso_3_code": "auz", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "504", "native_tokenizers": [], @@ -6316,9 +6300,11 @@ }, { "name": "Arabic, Eastern Egyptian Bedawi", + "depth": 5, "iso_1_code": "ar", "iso_3_code": "avl", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "505", "native_tokenizers": [], @@ -6326,9 +6312,11 @@ }, { "name": "Arabic, Hadrami", + "depth": 5, "iso_1_code": "ar", "iso_3_code": "ayh", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "506", "native_tokenizers": [], @@ -6336,9 +6324,11 @@ }, { "name": "Arabic, Libyan", + "depth": 5, "iso_1_code": "ar", "iso_3_code": "ayl", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "507", "native_tokenizers": [], @@ -6346,9 +6336,11 @@ }, { "name": "Arabic, Sanaani", + "depth": 5, "iso_1_code": "ar", "iso_3_code": "ayn", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "508", "native_tokenizers": [], @@ -6356,9 +6348,11 @@ }, { "name": "Arabic, North Mesopotamian", + "depth": 5, "iso_1_code": "ar", "iso_3_code": "ayp", "children": [], + "family": "Afro-Asiatic", "tokenizers": { "Arab": { "full_object": "SpaCyTokenizer(\"ar\")", @@ -6378,9 +6372,11 @@ }, { "name": "Arabic, Judeo-Yemeni", + "depth": 5, "iso_1_code": null, "iso_3_code": "jye", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "510", "native_tokenizers": [], @@ -6388,9 +6384,11 @@ }, { "name": "Hassaniyya", + "depth": 5, "iso_1_code": null, "iso_3_code": "mey", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "511", "native_tokenizers": [], @@ -6398,9 +6396,11 @@ }, { "name": "Maltese", + "depth": 5, "iso_1_code": "mt", "iso_3_code": "mlt", "children": [], + "family": "Afro-Asiatic", "tokenizers": { "Latn": { "full_object": "StanzaTokenizer(\"mt\")", @@ -6420,9 +6420,11 @@ }, { "name": "Arabic, Chadian", + "depth": 5, "iso_1_code": "ar", "iso_3_code": "shu", "children": [], + "family": "Afro-Asiatic", "tokenizers": { "Arab": { "full_object": "SpaCyTokenizer(\"ar\")", @@ -6442,9 +6444,11 @@ }, { "name": "Arabic, Shihhi", + "depth": 5, "iso_1_code": "ar", "iso_3_code": "ssh", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "514", "native_tokenizers": [], @@ -6452,9 +6456,11 @@ }, { "name": "Arabic, Judeo-Iraqi", + "depth": 5, "iso_1_code": null, "iso_3_code": "yhd", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "515", "native_tokenizers": [], @@ -6462,15 +6468,18 @@ }, { "name": "Arabic, Judeo-Tripolitanian", + "depth": 5, "iso_1_code": null, "iso_3_code": "yud", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "516", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": { "Arab": { "full_object": "SpaCyTokenizer(\"ar\")", @@ -6493,14 +6502,17 @@ }, { "name": "Canaanite", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Hebrew, Ancient", + "depth": 5, "iso_1_code": null, "iso_3_code": "hbo", "children": [], + "family": "Afro-Asiatic", "tokenizers": { "Hebr": { "full_object": "StanzaTokenizer(\"hbo\")", @@ -6520,9 +6532,11 @@ }, { "name": "Hebrew", + "depth": 5, "iso_1_code": "he", "iso_3_code": "heb", "children": [], + "family": "Afro-Asiatic", "tokenizers": { "Hebr": { "full_object": "SpaCyTokenizer(\"he\")", @@ -6542,15 +6556,18 @@ }, { "name": "Samaritan Hebrew", + "depth": 5, "iso_1_code": null, "iso_3_code": "smp", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "520", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": { "Hebr": { "full_object": "SpaCyTokenizer(\"he\")", @@ -6565,6 +6582,7 @@ "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": { "Arab": { "full_object": "SpaCyTokenizer(\"ar\")", @@ -6593,6 +6611,7 @@ "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": { "Arab": { "full_object": "SpaCyTokenizer(\"ar\")", @@ -6622,24 +6641,29 @@ }, { "name": "South", + "depth": 2, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ethiopian", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "North", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Dahalik", + "depth": 5, "iso_1_code": null, "iso_3_code": "dlk", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "524", "native_tokenizers": [], @@ -6647,9 +6671,11 @@ }, { "name": "Geez", + "depth": 5, "iso_1_code": null, "iso_3_code": "gez", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "525", "native_tokenizers": [], @@ -6657,9 +6683,11 @@ }, { "name": "Tigr\u00e9", + "depth": 5, "iso_1_code": null, "iso_3_code": "tig", "children": [], + "family": "Afro-Asiatic", "tokenizers": { "Ethi": { "full_object": "SpaCyTokenizer(\"ti\")", @@ -6677,9 +6705,11 @@ }, { "name": "Tigrigna", + "depth": 5, "iso_1_code": "ti", "iso_3_code": "tir", "children": [], + "family": "Afro-Asiatic", "tokenizers": { "Ethi": { "full_object": "SpaCyTokenizer(\"ti\")", @@ -6698,6 +6728,7 @@ ] } ], + "family": "Afro-Asiatic", "tokenizers": { "Ethi": { "full_object": "SpaCyTokenizer(\"ti\")", @@ -6713,24 +6744,29 @@ }, { "name": "South", + "depth": 4, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Outer", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "n-Group", + "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Gafat", + "depth": 7, "iso_1_code": null, "iso_3_code": "gft", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "531", "native_tokenizers": [], @@ -6738,15 +6774,18 @@ }, { "name": "Kistane", + "depth": 7, "iso_1_code": null, "iso_3_code": "gru", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "532", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "530", "native_tokenizers": [], @@ -6754,14 +6793,17 @@ }, { "name": "tt-Group", + "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Inor", + "depth": 7, "iso_1_code": null, "iso_3_code": "ior", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "534", "native_tokenizers": [], @@ -6769,9 +6811,11 @@ }, { "name": "Mesqan", + "depth": 7, "iso_1_code": null, "iso_3_code": "mvz", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "535", "native_tokenizers": [], @@ -6779,9 +6823,11 @@ }, { "name": "Mesmes", + "depth": 7, "iso_1_code": null, "iso_3_code": "mys", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "536", "native_tokenizers": [], @@ -6789,9 +6835,11 @@ }, { "name": "Sebat Bet Gurage", + "depth": 7, "iso_1_code": null, "iso_3_code": "sgw", "children": [], + "family": "Afro-Asiatic", "tokenizers": { "Ethi": { "full_object": "SpaCyTokenizer(\"am\")", @@ -6808,6 +6856,7 @@ ] } ], + "family": "Afro-Asiatic", "tokenizers": { "Ethi": { "full_object": "SpaCyTokenizer(\"am\")", @@ -6822,6 +6871,7 @@ "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": { "Ethi": { "full_object": "SpaCyTokenizer(\"am\")", @@ -6837,19 +6887,23 @@ }, { "name": "Transversal", + "depth": 5, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Amharic-Argobba", + "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Argobba", + "depth": 7, "iso_1_code": null, "iso_3_code": "agj", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "540", "native_tokenizers": [], @@ -6857,9 +6911,11 @@ }, { "name": "Amharic", + "depth": 7, "iso_1_code": "am", "iso_3_code": "amh", "children": [], + "family": "Afro-Asiatic", "tokenizers": { "Ethi": { "full_object": "SpaCyTokenizer(\"am\")", @@ -6878,6 +6934,7 @@ ] } ], + "family": "Afro-Asiatic", "tokenizers": { "Ethi": { "full_object": "SpaCyTokenizer(\"am\")", @@ -6893,14 +6950,17 @@ }, { "name": "Harari-East Gurage", + "depth": 6, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Harari", + "depth": 7, "iso_1_code": null, "iso_3_code": "har", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "543", "native_tokenizers": [], @@ -6908,9 +6968,11 @@ }, { "name": "Silt\u2019e", + "depth": 7, "iso_1_code": null, "iso_3_code": "stv", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "544", "native_tokenizers": [], @@ -6918,9 +6980,11 @@ }, { "name": "Wolane", + "depth": 7, "iso_1_code": null, "iso_3_code": "wle", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "545", "native_tokenizers": [], @@ -6928,21 +6992,25 @@ }, { "name": "Zay", + "depth": 7, "iso_1_code": null, "iso_3_code": "zwa", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "546", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "542", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": { "Ethi": { "full_object": "SpaCyTokenizer(\"am\")", @@ -6957,6 +7025,7 @@ "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": { "Ethi": { "full_object": "SpaCyTokenizer(\"am\")", @@ -6971,6 +7040,7 @@ "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": { "Ethi": { "full_object": "SpaCyTokenizer(\"am\")", @@ -6986,14 +7056,17 @@ }, { "name": "South Arabian", + "depth": 3, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Bathari", + "depth": 4, "iso_1_code": null, "iso_3_code": "bhm", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "548", "native_tokenizers": [], @@ -7001,9 +7074,11 @@ }, { "name": "Mehri", + "depth": 4, "iso_1_code": null, "iso_3_code": "gdq", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "549", "native_tokenizers": [], @@ -7011,9 +7086,11 @@ }, { "name": "Hoby\u00f3t", + "depth": 4, "iso_1_code": null, "iso_3_code": "hoh", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "550", "native_tokenizers": [], @@ -7021,9 +7098,11 @@ }, { "name": "Harsusi", + "depth": 4, "iso_1_code": null, "iso_3_code": "hss", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "551", "native_tokenizers": [], @@ -7031,9 +7110,11 @@ }, { "name": "Shehri", + "depth": 4, "iso_1_code": null, "iso_3_code": "shv", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "552", "native_tokenizers": [], @@ -7041,21 +7122,25 @@ }, { "name": "Soqotri", + "depth": 4, "iso_1_code": null, "iso_3_code": "sqt", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "553", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "547", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": { "Ethi": { "full_object": "SpaCyTokenizer(\"am\")", @@ -7070,6 +7155,7 @@ "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": { "Arab": { "full_object": "SpaCyTokenizer(\"ar\")", @@ -7106,63 +7192,32 @@ }, { "name": "Unclassified", + "depth": 1, "iso_1_code": null, "iso_3_code": null, "children": [ { "name": "Ongota", + "depth": 2, "iso_1_code": null, "iso_3_code": "bxe", "children": [], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "555", "native_tokenizers": [], "scripts": [] } ], + "family": "Afro-Asiatic", "tokenizers": {}, "node_i": "554", "native_tokenizers": [], "scripts": [] } ], - "tokenizers": { - "Copt": { - "full_object": "StanzaTokenizer(\"cop\")", - "original_lang_name": "coptic", - "original_lang_code": "cop", - "script": "Copt", - "class_name": "StanzaTokenizer" - }, - "Arab": { - "full_object": "SpaCyTokenizer(\"ar\")", - "original_lang_name": "arabic", - "original_lang_code": "ara", - "script": "Arab", - "class_name": "SpaCyTokenizer" - }, - "Latn": { - "full_object": "StanzaTokenizer(\"mt\")", - "original_lang_name": "maltese", - "original_lang_code": "mlt", - "script": "Latn", - "class_name": "StanzaTokenizer" - }, - "Hebr": { - "full_object": "SpaCyTokenizer(\"he\")", - "original_lang_name": "hebrew", - "original_lang_code": "heb", - "script": "Hebr", - "class_name": "SpaCyTokenizer" - }, - "Ethi": { - "full_object": "SpaCyTokenizer(\"am\")", - "original_lang_name": "amharic", - "original_lang_code": "amh", - "script": "Ethi", - "class_name": "SpaCyTokenizer" - } - }, + "family": "Afro-Asiatic", + "tokenizers": {}, "node_i": "9", "native_tokenizers": [], "scripts": []