diff --git "a/data/Afro-Asiatic.json" "b/data/Afro-Asiatic.json" new file mode 100644--- /dev/null +++ "b/data/Afro-Asiatic.json" @@ -0,0 +1,6172 @@ +{ + "name": "Afro-Asiatic", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "bottom", + "children": [ + { + "name": "Berber", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Guanche", + "iso_1_code": null, + "iso_3_code": "gnc", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Eastern", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Awjila-Sokna", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Awjilah", + "iso_1_code": null, + "iso_3_code": "auj", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Sawknah", + "iso_1_code": null, + "iso_3_code": "swn", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Siwa", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Siwi", + "iso_1_code": null, + "iso_3_code": "siz", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "Northern", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Chenoua", + "iso_1_code": null, + "iso_3_code": "cnu", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Atlas", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Judeo-Berber", + "iso_1_code": null, + "iso_3_code": "jbe", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Tachelhit", + "iso_1_code": null, + "iso_3_code": "shi", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Tamazight, Central Atlas", + "iso_1_code": null, + "iso_3_code": "tzm", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Tamazight, Standard Moroccan", + "iso_1_code": null, + "iso_3_code": "zgh", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Kabyle", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Kabyle", + "iso_1_code": null, + "iso_3_code": "kab", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Zenati", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "East", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Ghadam\u00e8s", + "iso_1_code": null, + "iso_3_code": "gha", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Nafusi", + "iso_1_code": null, + "iso_3_code": "jbn", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Sened", + "iso_1_code": null, + "iso_3_code": "sds", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Ghomara", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Ghomara", + "iso_1_code": null, + "iso_3_code": "gho", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Mzab-Wargla", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Taznatit", + "iso_1_code": null, + "iso_3_code": "grr", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Tumzabt", + "iso_1_code": null, + "iso_3_code": "mzb", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Tagargrent", + "iso_1_code": null, + "iso_3_code": "oua", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Tamazight, Temacine", + "iso_1_code": null, + "iso_3_code": "tjo", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Riff", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Tarifit", + "iso_1_code": null, + "iso_3_code": "rif", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Senhaja Berber", + "iso_1_code": null, + "iso_3_code": "sjs", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Shawiya", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Tachawit", + "iso_1_code": null, + "iso_3_code": "shy", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Tidikelt", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Tamazight, Tidikelt", + "iso_1_code": null, + "iso_3_code": "tia", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + } + ] + }, + { + "name": "Tamasheq", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Northern", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Tamahaq, Tahaggart", + "iso_1_code": null, + "iso_3_code": "thv", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Southern", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Tamasheq", + "iso_1_code": null, + "iso_3_code": "taq", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Tamajeq, Tayart", + "iso_1_code": null, + "iso_3_code": "thz", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Tamajaq, Tawallammat", + "iso_1_code": null, + "iso_3_code": "ttq", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "Zenaga", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Tetserret", + "iso_1_code": null, + "iso_3_code": "tez", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Zenaga", + "iso_1_code": null, + "iso_3_code": "zen", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "Chadic", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Biu-Mandara", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "A", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "A.1", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Eastern", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Boga", + "iso_1_code": null, + "iso_3_code": "bvw", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Ga\u2019anda", + "iso_1_code": null, + "iso_3_code": "gqa", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Hwana", + "iso_1_code": null, + "iso_3_code": "hwo", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Western", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Jara", + "iso_1_code": null, + "iso_3_code": "jaf", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Tera", + "iso_1_code": null, + "iso_3_code": "ttr", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "A.2", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Nggwahyi", + "iso_1_code": null, + "iso_3_code": "ngx", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "1", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Bura-Pabir", + "iso_1_code": null, + "iso_3_code": "bwr", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kibaku", + "iso_1_code": null, + "iso_3_code": "ckl", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kofa", + "iso_1_code": null, + "iso_3_code": "kso", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Putai", + "iso_1_code": null, + "iso_3_code": "mfl", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "2", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Nya Huba", + "iso_1_code": null, + "iso_3_code": "hbb", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Marghi South", + "iso_1_code": null, + "iso_3_code": "mfm", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Marghi Central", + "iso_1_code": null, + "iso_3_code": "mrt", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "A.3", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Bana", + "iso_1_code": null, + "iso_3_code": "bcw", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kirya-Konzel", + "iso_1_code": null, + "iso_3_code": "fkk", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kamwe", + "iso_1_code": null, + "iso_3_code": "hig", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Hya", + "iso_1_code": null, + "iso_3_code": "hya", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Psikye", + "iso_1_code": null, + "iso_3_code": "kvj", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "A.4", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Lamang", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Lamang", + "iso_1_code": null, + "iso_3_code": "hia", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Vemgo-Mabas", + "iso_1_code": null, + "iso_3_code": "vem", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Hdi", + "iso_1_code": null, + "iso_3_code": "xed", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Mandara Proper", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Glavda", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Cineni", + "iso_1_code": null, + "iso_3_code": "cie", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Dghwede", + "iso_1_code": null, + "iso_3_code": "dgh", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Guduf-Gava", + "iso_1_code": null, + "iso_3_code": "gdf", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Glavda", + "iso_1_code": null, + "iso_3_code": "glw", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Gvoko", + "iso_1_code": null, + "iso_3_code": "ngs", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Mandara", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Wandala", + "iso_1_code": null, + "iso_3_code": "mfi", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Podoko", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Parkwa", + "iso_1_code": null, + "iso_3_code": "pbi", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + } + ] + }, + { + "name": "A.5", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Baldemu", + "iso_1_code": null, + "iso_3_code": "bdn", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Cuvok", + "iso_1_code": null, + "iso_3_code": "cuv", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Dugwor", + "iso_1_code": null, + "iso_3_code": "dme", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Giziga, North", + "iso_1_code": null, + "iso_3_code": "gis", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Giziga", + "iso_1_code": null, + "iso_3_code": "giz", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Zulgo-Gemzek", + "iso_1_code": null, + "iso_3_code": "gnd", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mafa", + "iso_1_code": null, + "iso_3_code": "maf", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Merey", + "iso_1_code": null, + "iso_3_code": "meq", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Matal", + "iso_1_code": null, + "iso_3_code": "mfh", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mefele", + "iso_1_code": null, + "iso_3_code": "mfj", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mofu, North", + "iso_1_code": null, + "iso_3_code": "mfk", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mofu-Gudur", + "iso_1_code": null, + "iso_3_code": "mif", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Vame", + "iso_1_code": null, + "iso_3_code": "mlr", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Moloko", + "iso_1_code": null, + "iso_3_code": "mlw", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mbuko", + "iso_1_code": null, + "iso_3_code": "mqb", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Muyang", + "iso_1_code": null, + "iso_3_code": "muy", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mada", + "iso_1_code": null, + "iso_3_code": "mxu", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Wuzlam", + "iso_1_code": null, + "iso_3_code": "udl", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "A.6", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Sukur", + "iso_1_code": null, + "iso_3_code": "syk", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "A.7", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Buwal", + "iso_1_code": null, + "iso_3_code": "bhs", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Daba", + "iso_1_code": null, + "iso_3_code": "dbq", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mazagway-Hidi", + "iso_1_code": null, + "iso_3_code": "dkx", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Gavar", + "iso_1_code": null, + "iso_3_code": "gou", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mina", + "iso_1_code": null, + "iso_3_code": "hna", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mbudum", + "iso_1_code": null, + "iso_3_code": "xmd", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "A.8", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Bacama", + "iso_1_code": null, + "iso_3_code": "bcy", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Bata", + "iso_1_code": null, + "iso_3_code": "bta", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Fali Muchella", + "iso_1_code": null, + "iso_3_code": "fli", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Gude", + "iso_1_code": null, + "iso_3_code": "gde", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Gudu", + "iso_1_code": null, + "iso_3_code": "gdu", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Holma", + "iso_1_code": null, + "iso_3_code": "hod", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Jimjimen", + "iso_1_code": null, + "iso_3_code": "jim", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Ngwaba", + "iso_1_code": null, + "iso_3_code": "ngw", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Nzanyi", + "iso_1_code": null, + "iso_3_code": "nja", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Sharwa", + "iso_1_code": null, + "iso_3_code": "swq", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Tsuvan", + "iso_1_code": null, + "iso_3_code": "tsh", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Zizilivakan", + "iso_1_code": null, + "iso_3_code": "ziz", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "B", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "B.1", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Auyokawa", + "iso_1_code": null, + "iso_3_code": "auo", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Jilbe", + "iso_1_code": null, + "iso_3_code": "jie", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Buduma", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Buduma", + "iso_1_code": null, + "iso_3_code": "bdm", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Jina", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Jina", + "iso_1_code": null, + "iso_3_code": "jia", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Majera", + "iso_1_code": null, + "iso_3_code": "xmj", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Kotoko Proper", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "North", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Afade", + "iso_1_code": null, + "iso_3_code": "aal", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mpade", + "iso_1_code": null, + "iso_3_code": "mpi", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Maslam", + "iso_1_code": null, + "iso_3_code": "msv", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Malgbe", + "iso_1_code": null, + "iso_3_code": "mxf", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "South", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Lagwan", + "iso_1_code": null, + "iso_3_code": "kot", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mser", + "iso_1_code": null, + "iso_3_code": "kqx", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + } + ] + }, + { + "name": "B.2", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Muskum", + "iso_1_code": null, + "iso_3_code": "mje", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mbara", + "iso_1_code": null, + "iso_3_code": "mpk", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Musgu", + "iso_1_code": null, + "iso_3_code": "mug", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "C", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Gidar", + "iso_1_code": null, + "iso_3_code": "gid", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "East", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "A", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "A.1", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Buso", + "iso_1_code": null, + "iso_3_code": "bso", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "1", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Mulgi", + "iso_1_code": null, + "iso_3_code": "mvh", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Ndam", + "iso_1_code": null, + "iso_3_code": "ndm", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Soumraye", + "iso_1_code": null, + "iso_3_code": "sor", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Tumak", + "iso_1_code": null, + "iso_3_code": "tmc", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "2", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Boor", + "iso_1_code": null, + "iso_3_code": "bvf", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Gadang", + "iso_1_code": null, + "iso_3_code": "gdk", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Miltu", + "iso_1_code": null, + "iso_3_code": "mlj", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Sarua", + "iso_1_code": null, + "iso_3_code": "swy", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "A.2", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "1", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Kimr\u00e9", + "iso_1_code": null, + "iso_3_code": "kqp", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Lele", + "iso_1_code": null, + "iso_3_code": "lln", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Nancere", + "iso_1_code": null, + "iso_3_code": "nnc", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "2", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Gabri", + "iso_1_code": null, + "iso_3_code": "gab", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kabalai", + "iso_1_code": null, + "iso_3_code": "kvf", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Tobanga", + "iso_1_code": null, + "iso_3_code": "tng", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "A.3", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Kera", + "iso_1_code": null, + "iso_3_code": "ker", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kwang", + "iso_1_code": null, + "iso_3_code": "kvi", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "B", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "B.1", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "1", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Bidiyo", + "iso_1_code": null, + "iso_3_code": "bid", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Dangal\u00e9at", + "iso_1_code": null, + "iso_3_code": "daa", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Jonkor Bourmataguil", + "iso_1_code": null, + "iso_3_code": "jeu", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mawa", + "iso_1_code": null, + "iso_3_code": "mcw", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Migaama", + "iso_1_code": null, + "iso_3_code": "mmy", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mogum", + "iso_1_code": null, + "iso_3_code": "mou", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mabire", + "iso_1_code": null, + "iso_3_code": "muj", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Ubi", + "iso_1_code": null, + "iso_3_code": "ubi", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "2", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Birgit", + "iso_1_code": null, + "iso_3_code": "btf", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kajakse", + "iso_1_code": null, + "iso_3_code": "ckq", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Masmaje", + "iso_1_code": null, + "iso_3_code": "mes", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mubi", + "iso_1_code": null, + "iso_3_code": "mub", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Toram", + "iso_1_code": null, + "iso_3_code": "trj", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Zerenkel", + "iso_1_code": null, + "iso_3_code": "zrn", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "B.2", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Mukulu", + "iso_1_code": null, + "iso_3_code": "moz", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "B.3", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Barein", + "iso_1_code": null, + "iso_3_code": "bva", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Saba", + "iso_1_code": null, + "iso_3_code": "saa", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Sokoro", + "iso_1_code": null, + "iso_3_code": "sok", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Tamki", + "iso_1_code": null, + "iso_3_code": "tax", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + } + ] + }, + { + "name": "Masa", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Herd\u00e9", + "iso_1_code": null, + "iso_3_code": "hed", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "P\u00e9v\u00e9", + "iso_1_code": null, + "iso_3_code": "lme", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Masana", + "iso_1_code": null, + "iso_3_code": "mcn", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Marba", + "iso_1_code": null, + "iso_3_code": "mpg", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Musey", + "iso_1_code": null, + "iso_3_code": "mse", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Ngete", + "iso_1_code": null, + "iso_3_code": "nnn", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mesme", + "iso_1_code": null, + "iso_3_code": "zim", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Zumaya", + "iso_1_code": null, + "iso_3_code": "zuy", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "West", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "A", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "A.1", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Gwandara", + "iso_1_code": null, + "iso_3_code": "gwn", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Hausa", + "iso_1_code": "ha", + "iso_3_code": "hau", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "A.2", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Bole", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Bole Proper", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Bole", + "iso_1_code": null, + "iso_3_code": "bol", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Bure", + "iso_1_code": null, + "iso_3_code": "bvh", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Beele", + "iso_1_code": null, + "iso_3_code": "bxq", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Deno", + "iso_1_code": null, + "iso_3_code": "dbb", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Daza", + "iso_1_code": null, + "iso_3_code": "dzd", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Geruma", + "iso_1_code": null, + "iso_3_code": "gea", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Gera", + "iso_1_code": null, + "iso_3_code": "gew", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Galambi", + "iso_1_code": null, + "iso_3_code": "glo", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Giiwo", + "iso_1_code": null, + "iso_3_code": "kks", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kubi", + "iso_1_code": null, + "iso_3_code": "kof", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kholok", + "iso_1_code": null, + "iso_3_code": "ktc", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Maaka", + "iso_1_code": null, + "iso_3_code": "mew", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Ngamo", + "iso_1_code": null, + "iso_3_code": "nbh", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Nyam", + "iso_1_code": null, + "iso_3_code": "nmi", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Karekare", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Karekare", + "iso_1_code": null, + "iso_3_code": "kai", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "Tangale", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Dera", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Dera", + "iso_1_code": null, + "iso_3_code": "kna", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Tangale Proper", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Kutto", + "iso_1_code": null, + "iso_3_code": "kpa", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kwaami", + "iso_1_code": null, + "iso_3_code": "ksq", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kushi", + "iso_1_code": null, + "iso_3_code": "kuh", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Pero", + "iso_1_code": null, + "iso_3_code": "pip", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Piya-Kwonci", + "iso_1_code": null, + "iso_3_code": "piy", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Tangale", + "iso_1_code": null, + "iso_3_code": "tan", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + } + ] + }, + { + "name": "A.3", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Angas Proper", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Jakattoe", + "iso_1_code": null, + "iso_3_code": "jrt", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "1", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Ngas", + "iso_1_code": null, + "iso_3_code": "anc", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Cakfem-Mushere", + "iso_1_code": null, + "iso_3_code": "cky", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Belning", + "iso_1_code": null, + "iso_3_code": "glb", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kofyar", + "iso_1_code": null, + "iso_3_code": "kwl", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Miship", + "iso_1_code": null, + "iso_3_code": "mjs", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Nteng", + "iso_1_code": null, + "iso_3_code": "nqt", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mwaghavul", + "iso_1_code": null, + "iso_3_code": "sur", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "2", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Goemai", + "iso_1_code": null, + "iso_3_code": "ank", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Koenoem", + "iso_1_code": null, + "iso_3_code": "kcs", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Tehl", + "iso_1_code": null, + "iso_3_code": "mtl", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Piapung", + "iso_1_code": null, + "iso_3_code": "pcw", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Tal", + "iso_1_code": null, + "iso_3_code": "tal", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "Yiwom", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Ywom", + "iso_1_code": null, + "iso_3_code": "gek", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "A.4", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Fyer", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Fyer", + "iso_1_code": null, + "iso_3_code": "fie", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Rom", + "iso_1_code": null, + "iso_3_code": "tdk", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Ron Proper", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Ron", + "iso_1_code": null, + "iso_3_code": "cla", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Duhwa", + "iso_1_code": null, + "iso_3_code": "kbz", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kulere", + "iso_1_code": null, + "iso_3_code": "kul", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mindat", + "iso_1_code": null, + "iso_3_code": "mmf", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Sya", + "iso_1_code": null, + "iso_3_code": "scw", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + } + ] + }, + { + "name": "B", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "B.1", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Teshenawa", + "iso_1_code": null, + "iso_3_code": "twc", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Bade Proper", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Bade", + "iso_1_code": null, + "iso_3_code": "bde", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Ngizim", + "iso_1_code": null, + "iso_3_code": "ngi", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Duwai", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Duwai", + "iso_1_code": null, + "iso_3_code": "dbp", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "B.2", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Ajawa", + "iso_1_code": null, + "iso_3_code": "ajw", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Burku", + "iso_1_code": null, + "iso_3_code": "bbt", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Dirya", + "iso_1_code": null, + "iso_3_code": "dwa", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Zibinju", + "iso_1_code": null, + "iso_3_code": "jmb", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kariya", + "iso_1_code": null, + "iso_3_code": "kil", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Vune mi", + "iso_1_code": null, + "iso_3_code": "mkf", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Pa\u2019anci", + "iso_1_code": null, + "iso_3_code": "pqa", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Siri", + "iso_1_code": null, + "iso_3_code": "sir", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Choogen", + "iso_1_code": null, + "iso_3_code": "tgd", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Warji", + "iso_1_code": null, + "iso_3_code": "wji", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "B.3", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Dass", + "iso_1_code": null, + "iso_3_code": "dot", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Boghom", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Boghom", + "iso_1_code": null, + "iso_3_code": "bux", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kir-Balar", + "iso_1_code": null, + "iso_3_code": "kkr", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mansi", + "iso_1_code": null, + "iso_3_code": "zns", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Eastern", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Jimi", + "iso_1_code": null, + "iso_3_code": "jmi", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Guruntum", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Guruntum-Mbaaru", + "iso_1_code": null, + "iso_3_code": "grd", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Juu", + "iso_1_code": null, + "iso_3_code": "juu", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Tala", + "iso_1_code": null, + "iso_3_code": "tak", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Zamwal", + "iso_1_code": null, + "iso_3_code": "zah", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Zaar Proper", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Cha\u2019ari", + "iso_1_code": null, + "iso_3_code": "cxh", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Dokshi", + "iso_1_code": null, + "iso_3_code": "dsk", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Dyarim", + "iso_1_code": null, + "iso_3_code": "dyr", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Gyaazi", + "iso_1_code": null, + "iso_3_code": "gyz", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Luri", + "iso_1_code": null, + "iso_3_code": "ldd", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Dir-Nyamzak-Mbarimi", + "iso_1_code": null, + "iso_3_code": "nzr", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Pesse", + "iso_1_code": null, + "iso_3_code": "pze", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Saya", + "iso_1_code": null, + "iso_3_code": "say", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Tulai", + "iso_1_code": null, + "iso_3_code": "tvi", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Buli", + "iso_1_code": null, + "iso_3_code": "uly", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Zari", + "iso_1_code": null, + "iso_3_code": "zaz", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Bu", + "iso_1_code": null, + "iso_3_code": "zbu", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Zeem", + "iso_1_code": null, + "iso_3_code": "zem", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Zul", + "iso_1_code": null, + "iso_3_code": "zlu", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + } + ] + } + ] + } + ] + }, + { + "name": "Cushitic", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Central", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Eastern", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Xamtanga", + "iso_1_code": null, + "iso_3_code": "xan", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Northern", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Bilen", + "iso_1_code": null, + "iso_3_code": "byn", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Southern", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Awngi", + "iso_1_code": null, + "iso_3_code": "awn", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Western", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Qimant", + "iso_1_code": null, + "iso_3_code": "ahg", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "East", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Boon", + "iso_1_code": null, + "iso_3_code": "bnl", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Dullay", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Ale", + "iso_1_code": null, + "iso_3_code": "gwd", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Tsamai", + "iso_1_code": null, + "iso_3_code": "tsb", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Highland", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Alaba-K\u2019abeena", + "iso_1_code": null, + "iso_3_code": "alw", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Burji", + "iso_1_code": null, + "iso_3_code": "bji", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Gedeo", + "iso_1_code": null, + "iso_3_code": "drs", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Hadiyya", + "iso_1_code": null, + "iso_3_code": "hdy", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kambaata", + "iso_1_code": null, + "iso_3_code": "ktb", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Libido", + "iso_1_code": null, + "iso_3_code": "liq", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Sidamo", + "iso_1_code": null, + "iso_3_code": "sid", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Konso-Gidole", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Mositacha", + "iso_1_code": null, + "iso_3_code": "dox", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Dirasha", + "iso_1_code": null, + "iso_3_code": "gdl", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Konso", + "iso_1_code": null, + "iso_3_code": "kxc", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Oromo", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Oromo, Borana-Arsi-Guji", + "iso_1_code": "om", + "iso_3_code": "gax", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Oromo, West Central", + "iso_1_code": "om", + "iso_3_code": "gaz", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Oromo, Eastern", + "iso_1_code": "om", + "iso_3_code": "hae", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Orma", + "iso_1_code": "om", + "iso_3_code": "orc", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Waata", + "iso_1_code": null, + "iso_3_code": "ssn", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Rendille-Boni", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Aweer", + "iso_1_code": null, + "iso_3_code": "bob", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Rendille", + "iso_1_code": null, + "iso_3_code": "rel", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Saho-Afar", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Afar", + "iso_1_code": "aa", + "iso_3_code": "aar", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Saho", + "iso_1_code": null, + "iso_3_code": "ssy", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Somali", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Dabarre", + "iso_1_code": null, + "iso_3_code": "dbr", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Garre", + "iso_1_code": null, + "iso_3_code": "gex", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Girirra", + "iso_1_code": null, + "iso_3_code": "gii", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Jiiddu", + "iso_1_code": null, + "iso_3_code": "jii", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Somali", + "iso_1_code": "so", + "iso_3_code": "som", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Tunni", + "iso_1_code": null, + "iso_3_code": "tqq", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Maay", + "iso_1_code": null, + "iso_3_code": "ymm", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Western Omo-Tana", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Arbore", + "iso_1_code": null, + "iso_3_code": "arv", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Baiso", + "iso_1_code": null, + "iso_3_code": "bsw", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Daasanach", + "iso_1_code": null, + "iso_3_code": "dsh", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "El Molo", + "iso_1_code": null, + "iso_3_code": "elo", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Yaaku", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Yaaku", + "iso_1_code": null, + "iso_3_code": "muu", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "North", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Bedawiyet", + "iso_1_code": null, + "iso_3_code": "bej", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "South", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Aas\u00e1x", + "iso_1_code": null, + "iso_3_code": "aas", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Burunge", + "iso_1_code": null, + "iso_3_code": "bds", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Dahalo", + "iso_1_code": null, + "iso_3_code": "dal", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Gorowa", + "iso_1_code": null, + "iso_3_code": "gow", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Iraqw", + "iso_1_code": null, + "iso_3_code": "irk", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Alagwa", + "iso_1_code": null, + "iso_3_code": "wbj", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kw\u2019adza", + "iso_1_code": null, + "iso_3_code": "wka", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "Egyptian", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "coptic", + "tokenizer": "StanzaTokenizer(\"cop\")" + }, + "source": "bottom", + "children": [ + { + "name": "Coptic", + "iso_1_code": null, + "iso_3_code": "cop", + "tokenizer": { + "name": "coptic", + "tokenizer": "StanzaTokenizer(\"cop\")" + }, + "source": "own", + "children": [] + } + ] + }, + { + "name": "Omotic", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "North", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Dizoid", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Dizin", + "iso_1_code": null, + "iso_3_code": "mdx", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Nayi", + "iso_1_code": null, + "iso_3_code": "noz", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Sheko", + "iso_1_code": null, + "iso_3_code": "she", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Gonga-Gimojan", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Gimojan", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Janjero", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Yemsa", + "iso_1_code": null, + "iso_3_code": "jnj", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Ometo-Gimira", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Chara", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Tsaara", + "iso_1_code": null, + "iso_3_code": "cra", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Gimira", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Bench", + "iso_1_code": null, + "iso_3_code": "bcq", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Ometo", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Male", + "iso_1_code": null, + "iso_3_code": "mdy", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Central", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Dorze", + "iso_1_code": null, + "iso_3_code": "doz", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Dawro", + "iso_1_code": null, + "iso_3_code": "dwr", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Gamo", + "iso_1_code": null, + "iso_3_code": "gmv", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Gofa", + "iso_1_code": null, + "iso_3_code": "gof", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Melo", + "iso_1_code": null, + "iso_3_code": "mfx", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Oyda", + "iso_1_code": null, + "iso_3_code": "oyd", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Wolaytta", + "iso_1_code": null, + "iso_3_code": "wal", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "East", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Kachama-Ganjule", + "iso_1_code": null, + "iso_3_code": "kcx", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Koorete", + "iso_1_code": null, + "iso_3_code": "kqy", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Zayse", + "iso_1_code": null, + "iso_3_code": "zay", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "West", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Basketo", + "iso_1_code": null, + "iso_3_code": "bst", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + } + ] + } + ] + }, + { + "name": "Gonga", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Central", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Anfillo", + "iso_1_code": null, + "iso_3_code": "myo", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "North", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Borna", + "iso_1_code": null, + "iso_3_code": "bwo", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "South", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Kafa", + "iso_1_code": null, + "iso_3_code": "kbr", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Shekkacho", + "iso_1_code": null, + "iso_3_code": "moy", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + } + ] + }, + { + "name": "Mao", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Ganza", + "iso_1_code": null, + "iso_3_code": "gza", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Hozo", + "iso_1_code": null, + "iso_3_code": "hoz", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mawes Aasse", + "iso_1_code": null, + "iso_3_code": "myf", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Seze", + "iso_1_code": null, + "iso_3_code": "sze", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "South", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Aari", + "iso_1_code": null, + "iso_3_code": "aiw", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Hamer-Banna", + "iso_1_code": null, + "iso_3_code": "amf", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Dime", + "iso_1_code": null, + "iso_3_code": "dim", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Gayil", + "iso_1_code": null, + "iso_3_code": "gyl", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Karo", + "iso_1_code": null, + "iso_3_code": "kxh", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "Semitic", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "bottom", + "children": [ + { + "name": "Central", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "bottom", + "children": [ + { + "name": "Faifi", + "iso_1_code": null, + "iso_3_code": "fif", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "R\u0101zi\u1e25\u012b", + "iso_1_code": null, + "iso_3_code": "rzh", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Aramaic", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Eastern", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Syriac", + "iso_1_code": null, + "iso_3_code": "syc", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Central", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Northeastern", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Assyrian Neo-Aramaic", + "iso_1_code": null, + "iso_3_code": "aii", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Bohtan Neo-Aramaic", + "iso_1_code": null, + "iso_3_code": "bhn", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Barzani-Sandu Jewish Neo-Aramaic", + "iso_1_code": null, + "iso_3_code": "bjf", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Chaldean Neo-Aramaic", + "iso_1_code": null, + "iso_3_code": "cld", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "H\u00e9rtevin", + "iso_1_code": null, + "iso_3_code": "hrt", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Koy Sanjaq Surat", + "iso_1_code": null, + "iso_3_code": "kqd", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Senaya", + "iso_1_code": null, + "iso_3_code": "syn", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Jewish Babylonian Aramaic", + "iso_1_code": null, + "iso_3_code": "tmr", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Trans-Zab", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Inter-Zab Jewish Neo-Aramaic", + "iso_1_code": null, + "iso_3_code": "aij", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Hulaul\u00e1", + "iso_1_code": null, + "iso_3_code": "huy", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Lishana Deni", + "iso_1_code": null, + "iso_3_code": "lsd", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Lish\u00e1n Noshan", + "iso_1_code": null, + "iso_3_code": "trg", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "Northwestern", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Mlahs\u00f6", + "iso_1_code": null, + "iso_3_code": "lhs", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Turoyo", + "iso_1_code": null, + "iso_3_code": "tru", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "Mandaic", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Neo-Mandaic", + "iso_1_code": null, + "iso_3_code": "mid", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mandaic, Classical", + "iso_1_code": null, + "iso_3_code": "myz", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "Western", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Western Neo-Aramaic", + "iso_1_code": null, + "iso_3_code": "amw", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Samaritan Aramaic", + "iso_1_code": null, + "iso_3_code": "sam", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "South", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "bottom", + "children": [ + { + "name": "Arabic", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "bottom", + "children": [ + { + "name": "Arabic, Algerian Saharan", + "iso_1_code": "ar", + "iso_3_code": "aao", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "macrolanguage", + "children": [] + }, + { + "name": "Arabic, Tajiki", + "iso_1_code": "ar", + "iso_3_code": "abh", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "macrolanguage", + "children": [] + }, + { + "name": "Arabic, Baharna", + "iso_1_code": "ar", + "iso_3_code": "abv", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "macrolanguage", + "children": [] + }, + { + "name": "Arabic, Mesopotamian", + "iso_1_code": "ar", + "iso_3_code": "acm", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "macrolanguage", + "children": [] + }, + { + "name": "Arabic, Ta\u2019izzi-Adeni", + "iso_1_code": "ar", + "iso_3_code": "acq", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "macrolanguage", + "children": [] + }, + { + "name": "Arabic, Hijazi", + "iso_1_code": "ar", + "iso_3_code": "acw", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "macrolanguage", + "children": [] + }, + { + "name": "Arabic, Omani", + "iso_1_code": "ar", + "iso_3_code": "acx", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "macrolanguage", + "children": [] + }, + { + "name": "Arabic, Cypriot", + "iso_1_code": "ar", + "iso_3_code": "acy", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "macrolanguage", + "children": [] + }, + { + "name": "Arabic, Dhofari", + "iso_1_code": "ar", + "iso_3_code": "adf", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "macrolanguage", + "children": [] + }, + { + "name": "Arabic, Tunisian", + "iso_1_code": "ar", + "iso_3_code": "aeb", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "macrolanguage", + "children": [] + }, + { + "name": "Arabic, Sa\u2019idi", + "iso_1_code": "ar", + "iso_3_code": "aec", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "macrolanguage", + "children": [] + }, + { + "name": "Arabic, Gulf", + "iso_1_code": "ar", + "iso_3_code": "afb", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "macrolanguage", + "children": [] + }, + { + "name": "Arabic, Judeo-Moroccan", + "iso_1_code": null, + "iso_3_code": "aju", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Arabic, Levantine", + "iso_1_code": "ar", + "iso_3_code": "apc", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "macrolanguage", + "children": [] + }, + { + "name": "Arabic, Sudanese", + "iso_1_code": "ar", + "iso_3_code": "apd", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "macrolanguage", + "children": [] + }, + { + "name": "Arabic, Standard", + "iso_1_code": "ar", + "iso_3_code": "arb", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "macrolanguage", + "children": [] + }, + { + "name": "Arabic, Algerian", + "iso_1_code": "ar", + "iso_3_code": "arq", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "macrolanguage", + "children": [] + }, + { + "name": "Arabic, Najdi", + "iso_1_code": "ar", + "iso_3_code": "ars", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "macrolanguage", + "children": [] + }, + { + "name": "Arabic, Moroccan", + "iso_1_code": "ar", + "iso_3_code": "ary", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "macrolanguage", + "children": [] + }, + { + "name": "Arabic, Egyptian", + "iso_1_code": "ar", + "iso_3_code": "arz", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "macrolanguage", + "children": [] + }, + { + "name": "Arabic, Uzbeki", + "iso_1_code": "ar", + "iso_3_code": "auz", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "macrolanguage", + "children": [] + }, + { + "name": "Arabic, Eastern Egyptian Bedawi", + "iso_1_code": "ar", + "iso_3_code": "avl", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "macrolanguage", + "children": [] + }, + { + "name": "Arabic, Hadrami", + "iso_1_code": "ar", + "iso_3_code": "ayh", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "macrolanguage", + "children": [] + }, + { + "name": "Arabic, Libyan", + "iso_1_code": "ar", + "iso_3_code": "ayl", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "macrolanguage", + "children": [] + }, + { + "name": "Arabic, Sanaani", + "iso_1_code": "ar", + "iso_3_code": "ayn", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "macrolanguage", + "children": [] + }, + { + "name": "Arabic, North Mesopotamian", + "iso_1_code": "ar", + "iso_3_code": "ayp", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "macrolanguage", + "children": [] + }, + { + "name": "Arabic, Judeo-Yemeni", + "iso_1_code": null, + "iso_3_code": "jye", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Hassaniyya", + "iso_1_code": null, + "iso_3_code": "mey", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Maltese", + "iso_1_code": "mt", + "iso_3_code": "mlt", + "tokenizer": { + "name": "maltese", + "tokenizer": "StanzaTokenizer(\"mt\")" + }, + "source": "own", + "children": [] + }, + { + "name": "Arabic, Chadian", + "iso_1_code": "ar", + "iso_3_code": "shu", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "macrolanguage", + "children": [] + }, + { + "name": "Arabic, Shihhi", + "iso_1_code": "ar", + "iso_3_code": "ssh", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "macrolanguage", + "children": [] + }, + { + "name": "Arabic, Judeo-Iraqi", + "iso_1_code": null, + "iso_3_code": "yhd", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Arabic, Judeo-Tripolitanian", + "iso_1_code": null, + "iso_3_code": "yud", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Canaanite", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "hebrew", + "tokenizer": "SpaCyTokenizer(\"he\")" + }, + "source": "bottom", + "children": [ + { + "name": "Hebrew, Ancient", + "iso_1_code": null, + "iso_3_code": "hbo", + "tokenizer": { + "name": "ancient_hebrew", + "tokenizer": "StanzaTokenizer(\"hbo\")" + }, + "source": "own", + "children": [] + }, + { + "name": "Hebrew", + "iso_1_code": "he", + "iso_3_code": "heb", + "tokenizer": { + "name": "hebrew", + "tokenizer": "SpaCyTokenizer(\"he\")" + }, + "source": "own", + "children": [] + }, + { + "name": "Samaritan Hebrew", + "iso_1_code": null, + "iso_3_code": "smp", + "tokenizer": { + "name": "hebrew", + "tokenizer": "SpaCyTokenizer(\"he\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + } + ] + }, + { + "name": "South", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "tigrinya", + "tokenizer": "SpaCyTokenizer(\"ti\")" + }, + "source": "bottom", + "children": [ + { + "name": "Ethiopian", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "tigrinya", + "tokenizer": "SpaCyTokenizer(\"ti\")" + }, + "source": "bottom", + "children": [ + { + "name": "North", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "tigrinya", + "tokenizer": "SpaCyTokenizer(\"ti\")" + }, + "source": "bottom", + "children": [ + { + "name": "Dahalik", + "iso_1_code": null, + "iso_3_code": "dlk", + "tokenizer": { + "name": "tigrinya", + "tokenizer": "SpaCyTokenizer(\"ti\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Geez", + "iso_1_code": null, + "iso_3_code": "gez", + "tokenizer": { + "name": "tigrinya", + "tokenizer": "SpaCyTokenizer(\"ti\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Tigr\u00e9", + "iso_1_code": null, + "iso_3_code": "tig", + "tokenizer": { + "name": "tigrinya", + "tokenizer": "SpaCyTokenizer(\"ti\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Tigrigna", + "iso_1_code": "ti", + "iso_3_code": "tir", + "tokenizer": { + "name": "tigrinya", + "tokenizer": "SpaCyTokenizer(\"ti\")" + }, + "source": "own", + "children": [] + } + ] + }, + { + "name": "South", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "amharic", + "tokenizer": "SpaCyTokenizer(\"am\")" + }, + "source": "bottom", + "children": [ + { + "name": "Outer", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "amharic", + "tokenizer": "SpaCyTokenizer(\"am\")" + }, + "source": "down", + "children": [ + { + "name": "n-Group", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "amharic", + "tokenizer": "SpaCyTokenizer(\"am\")" + }, + "source": "down", + "children": [ + { + "name": "Gafat", + "iso_1_code": null, + "iso_3_code": "gft", + "tokenizer": { + "name": "amharic", + "tokenizer": "SpaCyTokenizer(\"am\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kistane", + "iso_1_code": null, + "iso_3_code": "gru", + "tokenizer": { + "name": "amharic", + "tokenizer": "SpaCyTokenizer(\"am\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "tt-Group", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "amharic", + "tokenizer": "SpaCyTokenizer(\"am\")" + }, + "source": "down", + "children": [ + { + "name": "Inor", + "iso_1_code": null, + "iso_3_code": "ior", + "tokenizer": { + "name": "amharic", + "tokenizer": "SpaCyTokenizer(\"am\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mesqan", + "iso_1_code": null, + "iso_3_code": "mvz", + "tokenizer": { + "name": "amharic", + "tokenizer": "SpaCyTokenizer(\"am\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mesmes", + "iso_1_code": null, + "iso_3_code": "mys", + "tokenizer": { + "name": "amharic", + "tokenizer": "SpaCyTokenizer(\"am\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Sebat Bet Gurage", + "iso_1_code": null, + "iso_3_code": "sgw", + "tokenizer": { + "name": "amharic", + "tokenizer": "SpaCyTokenizer(\"am\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "Transversal", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "amharic", + "tokenizer": "SpaCyTokenizer(\"am\")" + }, + "source": "bottom", + "children": [ + { + "name": "Amharic-Argobba", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "amharic", + "tokenizer": "SpaCyTokenizer(\"am\")" + }, + "source": "bottom", + "children": [ + { + "name": "Argobba", + "iso_1_code": null, + "iso_3_code": "agj", + "tokenizer": { + "name": "amharic", + "tokenizer": "SpaCyTokenizer(\"am\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Amharic", + "iso_1_code": "am", + "iso_3_code": "amh", + "tokenizer": { + "name": "amharic", + "tokenizer": "SpaCyTokenizer(\"am\")" + }, + "source": "own", + "children": [] + } + ] + }, + { + "name": "Harari-East Gurage", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "amharic", + "tokenizer": "SpaCyTokenizer(\"am\")" + }, + "source": "down", + "children": [ + { + "name": "Harari", + "iso_1_code": null, + "iso_3_code": "har", + "tokenizer": { + "name": "amharic", + "tokenizer": "SpaCyTokenizer(\"am\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Silt\u2019e", + "iso_1_code": null, + "iso_3_code": "stv", + "tokenizer": { + "name": "amharic", + "tokenizer": "SpaCyTokenizer(\"am\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Wolane", + "iso_1_code": null, + "iso_3_code": "wle", + "tokenizer": { + "name": "amharic", + "tokenizer": "SpaCyTokenizer(\"am\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Zay", + "iso_1_code": null, + "iso_3_code": "zwa", + "tokenizer": { + "name": "amharic", + "tokenizer": "SpaCyTokenizer(\"am\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + } + ] + } + ] + }, + { + "name": "South Arabian", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "tigrinya", + "tokenizer": "SpaCyTokenizer(\"ti\")" + }, + "source": "down", + "children": [ + { + "name": "Bathari", + "iso_1_code": null, + "iso_3_code": "bhm", + "tokenizer": { + "name": "tigrinya", + "tokenizer": "SpaCyTokenizer(\"ti\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mehri", + "iso_1_code": null, + "iso_3_code": "gdq", + "tokenizer": { + "name": "tigrinya", + "tokenizer": "SpaCyTokenizer(\"ti\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Hoby\u00f3t", + "iso_1_code": null, + "iso_3_code": "hoh", + "tokenizer": { + "name": "tigrinya", + "tokenizer": "SpaCyTokenizer(\"ti\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Harsusi", + "iso_1_code": null, + "iso_3_code": "hss", + "tokenizer": { + "name": "tigrinya", + "tokenizer": "SpaCyTokenizer(\"ti\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Shehri", + "iso_1_code": null, + "iso_3_code": "shv", + "tokenizer": { + "name": "tigrinya", + "tokenizer": "SpaCyTokenizer(\"ti\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Soqotri", + "iso_1_code": null, + "iso_3_code": "sqt", + "tokenizer": { + "name": "tigrinya", + "tokenizer": "SpaCyTokenizer(\"ti\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + } + ] + }, + { + "name": "Unclassified", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [ + { + "name": "Ongota", + "iso_1_code": null, + "iso_3_code": "bxe", + "tokenizer": { + "name": "arabic", + "tokenizer": "SpaCyTokenizer(\"ar\")" + }, + "source": "down", + "children": [] + } + ] + } + ] +} \ No newline at end of file