update lang codes

README.md

@@ -1,202 +1,208 @@
 ---
 license: cc-by-nc-4.0
 language:
-  - ace
-  - acm
-  - acq
-  - aeb
-  - af
-  - ajp
-  - ak
-  - als
-  - am
-  - apc
-  - ar
-  - ars
-  - ary
-  - arz
-  - as
-  - ast
-  - awa
-  - ayr
-  - azb
-  - azj
-  - ba
-  - bm
-  - ban
-  - be
-  - bem
-  - bn
-  - bho
-  - bjn
-  - bo
-  - bs
-  - bug
-  - bg
-  - ca
-  - ceb
-  - cs
-  - cjk
-  - ckb
-  - crh
-  - cy
-  - da
-  - de
-  - dik
-  - dyu
-  - dz
-  - el
-  - en
-  - eo
-  - et
-  - eu
-  - ee
-  - fo
-  - fj
-  - fi
-  - fon
-  - fr
-  - fur
-  - fuv
-  - gaz
-  - gd
-  - ga
-  - gl
-  - gn
-  - gu
-  - ht
-  - ha
-  - he
-  - hi
-  - hne
-  - hr
-  - hu
-  - hy
-  - ig
-  - ilo
-  - id
-  - is
-  - it
-  - jv
-  - ja
-  - kab
-  - kac
-  - kam
-  - kn
-  - ks
-  - ka
-  - kk
-  - kbp
-  - kea
-  - khk
-  - km
-  - ki
-  - rw
-  - ky
-  - kmb
-  - kmr
-  - knc
-  - kg
-  - ko
-  - lo
-  - lij
-  - li
-  - ln
-  - lt
-  - lmo
-  - ltg
-  - lb
-  - lua
-  - lg
-  - luo
-  - lus
-  - lvs
-  - mag
-  - mai
-  - ml
-  - mar
-  - min
-  - mk
-  - mt
-  - mni
-  - mos
-  - mi
-  - my
-  - nl
-  - nn
-  - nb
-  - npi
-  - nso
-  - nus
-  - ny
-  - oc
-  - ory
-  - pag
-  - pa
-  - pap
-  - pbt
-  - pes
-  - plt
-  - pl
-  - pt
-  - prs
-  - quy
-  - ro
-  - rn
-  - ru
-  - sg
-  - sa
-  - sat
-  - scn
-  - shn
-  - si
-  - sk
-  - sl
-  - sm
-  - sn
-  - sd
-  - so
-  - st
-  - es
-  - sc
-  - sr
-  - ss
-  - su
-  - sv
-  - swh
-  - szl
-  - ta
-  - taq
-  - tt
-  - te
-  - tg
-  - tl
-  - th
-  - ti
-  - tpi
-  - tn
-  - ts
-  - tk
-  - tum
-  - tr
-  - tw
-  - tzm
-  - ug
-  - uk
-  - umb
-  - ur
-  - uzn
-  - vec
-  - vi
-  - war
-  - wo
-  - xh
-  - ydd
-  - yo
-  - yue
-  - zh
-  - zsm
-  - zu
+  - ace   # ace_Arab Acehnese (Arabic script)
+  - ace   # ace_Latn Acehnese (Latin script)
+  - acm  # acm_Arab Mesopotamian Arabic
+  - acq  # acq_Arab Ta’izzi-Adeni Arabic
+  - aeb  # aeb_Arab Tunisian Arabic
+  - af   # afr_Latn Afrikaans
+  - ajp  # ajp_Arab South Levantine Arabic
+  - ak   # aka_Latn Akan
+  - am   # amh_Ethi Amharic
+  - apc  # apc_Arab North Levantine Arabic
+  - ar   # arb_Arab Modern Standard Arabic
+  - ars  # ars_Arab Najdi Arabic
+  - ary  # ary_Arab Moroccan Arabic
+  - arz  # arz_Arab Egyptian Arabic
+  - as   # asm_Beng Assamese
+  - ast  # ast_Latn Asturian
+  - awa  # awa_Deva Awadhi
+  - ay   # ayr_Latn Central Aymara
+  - azb  # azb_Arab South Azerbaijani
+  - azj  # azj_Latn North Azerbaijani
+  - ba   # bak_Cyrl Bashkir
+  - bm   # bam_Latn Bambara
+  - ban  # ban_Latn Balinese
+  - be   # bel_Cyrl Belarusian
+  - bem  # bem_Latn Bemba
+  - bn   # ben_Beng Bengali
+  - bho  # bho_Deva Bhojpuri
+  - bjn  # bjn_Arab Banjar (Arabic script)
+  - bjn  # bjn_Latn Banjar (Latin script)
+  - bo   # bod_Tibt Standard Tibetan
+  - bs   # bos_Latn Bosnian
+  - bug  # bug_Latn Buginese
+  - bg   # bul_Cyrl Bulgarian
+  - ca   # cat_Latn Catalan
+  - ceb  # ceb_Latn Cebuano
+  - cs   # ces_Latn Czech
+  - cjk  # cjk_Latn Chokwe
+  - ckb  # ckb_Arab Central Kurdish
+  - crh  # crh_Latn Crimean Tatar
+  - cy   # cym_Latn Welsh
+  - da   # dan_Latn Danish
+  - de   # deu_Latn German
+  - dik  # dik_Latn Southwestern Dinka
+  - dyu  # dyu_Latn Dyula
+  - dz   # dzo_Tibt Dzongkha
+  - el   # ell_Grek Greek
+  - en   # eng_Latn English
+  - eo   # epo_Latn Esperanto
+  - et   # est_Latn Estonian
+  - eu   # eus_Latn Basque
+  - ee   # ewe_Latn Ewe
+  - fo   # fao_Latn Faroese
+  - fa   # pes_Arab Western Persian
+  - fj   # fij_Latn Fijian
+  - fi   # fin_Latn Finnish
+  - fon  # fon_Latn Fon
+  - fr   # fra_Latn French
+  - fur  # fur_Latn Friulian
+  - ff   # fuv_Latn Nigerian Fulfulde
+  - gd   # gla_Latn Scottish Gaelic
+  - ga   # gle_Latn Irish
+  - gl   # glg_Latn Galician
+  - gn   # grn_Latn Guarani
+  - gu   # guj_Gujr Gujarati
+  - ht   # hat_Latn Haitian Creole
+  - ha   # hau_Latn Hausa
+  - he   # heb_Hebr Hebrew
+  - hi   # hin_Deva Hindi
+  - hne  # hne_Deva Chhattisgarhi
+  - hr   # hrv_Latn Croatian
+  - hu   # hun_Latn Hungarian
+  - hy   # hye_Armn Armenian
+  - ig   # ibo_Latn Igbo
+  - ilo  # ilo_Latn Ilocano
+  - id   # ind_Latn Indonesian
+  - is   # isl_Latn Icelandic
+  - it   # ita_Latn Italian
+  - jv   # jav_Latn Javanese
+  - ja   # jpn_Jpan Japanese
+  - kab  # kab_Latn Kabyle
+  - kac  # kac_Latn Jingpho
+  - kam  # kam_Latn Kamba
+  - kn   # kan_Knda Kannada
+  - ks   # kas_Arab Kashmiri (Arabic script)
+  - ks   # kas_Deva Kashmiri (Devanagari script)
+  - ka   # kat_Geor Georgian
+  - kr   # knc_Arab Central Kanuri (Arabic script)
+  - kr   # knc_Latn Central Kanuri (Latin script)
+  - kk   # kaz_Cyrl Kazakh
+  - kbp  # kbp_Latn Kabiyè
+  - kea  # kea_Latn Kabuverdianu
+  - km   # khm_Khmr Khmer
+  - ki   # kik_Latn Kikuyu
+  - rw   # kin_Latn Kinyarwanda
+  - ky   # kir_Cyrl Kyrgyz
+  - kmb  # kmb_Latn Kimbundu
+  - kg   # kon_Latn Kikongo
+  - ko   # kor_Hang Korean
+  - kmr  # kmr_Latn Northern Kurdish
+  - lo   # lao_Laoo Lao
+  - lv   # lvs_Latn Standard Latvian
+  - lij  # lij_Latn Ligurian
+  - li   # lim_Latn Limburgish
+  - ln   # lin_Latn Lingala
+  - lt   # lit_Latn Lithuanian
+  - lmo  # lmo_Latn Lombard
+  - ltg  # ltg_Latn Latgalian
+  - lb   # ltz_Latn Luxembourgish
+  - lua  # lua_Latn Luba-Kasai
+  - lg   # lug_Latn Ganda
+  - luo  # luo_Latn Luo
+  - lus  # lus_Latn Mizo
+  - mag  # mag_Deva Magahi
+  - mai  # mai_Deva Maithili
+  - ml   # mal_Mlym Malayalam
+  - mr   # mar_Deva Marathi
+  - min  # min_Latn Minangkabau (Latin script)
+  - mk   # mkd_Cyrl Macedonian
+  - plt  # plt_Latn Plateau Malagasy
+  - mt   # mlt_Latn Maltese
+  - mni  # mni_Beng Meitei (Bengali script)
+  - mn   # khk_Cyrl Halh Mongolian
+  - mos  # mos_Latn Mossi
+  - mi   # mri_Latn Maori
+  - ms   # zsm_Latn Standard Malay
+  - my   # mya_Mymr Burmese
+  - nl   # nld_Latn Dutch
+  - nn   # nno_Latn Norwegian Nynorsk
+  - nb   # nob_Latn Norwegian Bokmål
+  - ne   # npi_Deva Nepali
+  - nso  # nso_Latn Northern Sotho
+  - nus  # nus_Latn Nuer
+  - ny   # nya_Latn Nyanja
+  - oc   # oci_Latn Occitan
+  - gaz  # gaz_Latn West Central Oromo
+  - ory  # ory_Orya Odia
+  - pag  # pag_Latn Pangasinan
+  - pa   # pan_Guru Eastern Panjabi
+  - pap  # pap_Latn Papiamento
+  - pl   # pol_Latn Polish
+  - pt   # por_Latn Portuguese
+  - prs  # prs_Arab Dari
+  - pbt  # pbt_Arab Southern Pashto
+  - qu   # quy_Latn Ayacucho Quechua
+  - ro   # ron_Latn Romanian
+  - rn   # run_Latn Rundi
+  - ru   # rus_Cyrl Russian
+  - sg   # sag_Latn Sango
+  - sa   # san_Deva Sanskrit
+  - sat  # sat_Beng ?
+  - scn  # scn_Latn Sicilian
+  - shn  # shn_Mymr Shan
+  - si   # sin_Sinh Sinhala
+  - sk   # slk_Latn Slovak
+  - sl   # slv_Latn Slovenian
+  - sm   # smo_Latn Samoan
+  - sn   # sna_Latn Shona
+  - sd   # snd_Arab Sindhi
+  - so   # som_Latn Somali
+  - st   # sot_Latn Southern Sotho
+  - es   # spa_Latn Spanish
+  - als  # als_Latn Tosk Albanian
+  - sc   # srd_Latn Sardinian
+  - sr   # srp_Cyrl Serbian
+  - ss   # ssw_Latn Swati
+  - su   # sun_Latn Sundanese
+  - sv   # swe_Latn Swedish
+  - sw   # swh_Latn Swahili
+  - szl  # szl_Latn Silesian
+  - ta   # tam_Taml Tamil
+  - tt   # tat_Cyrl Tatar
+  - te   # tel_Telu Telugu
+  - tg   # tgk_Cyrl Tajik
+  - tl   # tgl_Latn Tagalog
+  - th   # tha_Thai Thai
+  - ti   # tir_Ethi Tigrinya
+  - taq  # taq_Latn Tamasheq (Latin script)
+  - taq  # taq_Tfng Tamasheq (Tifinagh script)
+  - tpi  # tpi_Latn Tok Pisin
+  - tn   # tsn_Latn Tswana
+  - ts   # tso_Latn Tsonga
+  - tk   # tuk_Latn Turkmen
+  - tum  # tum_Latn Tumbuka
+  - tr   # tur_Latn Turkish
+  - tw   # twi_Latn Twi
+  - tzm  # tzm_Tfng Central Atlas Tamazight
+  - ug   # uig_Arab Uyghur
+  - uk   # ukr_Cyrl Ukrainian
+  - umb  # umb_Latn Umbundu
+  - ur   # urd_Arab Urdu
+  - uz   # uzn_Latn Northern Uzbek
+  - vec  # vec_Latn Venetian
+  - vi   # vie_Latn Vietnamese
+  - war  # war_Latn Waray
+  - wo   # wol_Latn Wolof
+  - xh   # xho_Latn Xhosa
+  - yi   # ydd_Hebr Eastern Yiddish
+  - yo   # yor_Latn Yoruba
+  - yue  # yue_Hant Yue Chinese
+  - zh   # zho_Hans Chinese (Simplified)
+  - zh   # zho_Hant Chinese (Traditional)
+  - zu   # zul_Latn Zulu
 language_details: >-
   ace_Arab, ace_Latn, acm_Arab, acq_Arab, aeb_Arab, afr_Latn, ajp_Arab,
   aka_Latn, amh_Ethi, apc_Arab, arb_Arab, ars_Arab, ary_Arab, arz_Arab,