Upload code_flores_latest.py

code_flores_latest.py

@@ -0,0 +1,222 @@
+codes_as_string_new = '''Acehnese (Arabic script)	ace_Arab
+Acehnese (Latin script)	ace_Latn
+Mesopotamian Arabic	acm_Arab
+Ta’izzi-Adeni Arabic	acq_Arab
+Tunisian Arabic	aeb_Arab
+Afrikaans	afr_Latn
+Albanian (Tosk)	als_Latn
+Amharic	amh_Ethi
+Levantine Arabic (North)	apc_Arab
+Levantine Arabic (South)	apc_Arab
+Modern Standard Arabic	arb_Arab
+Modern Standard Arabic (Romanized)	arb_Latn
+Najdi Arabic	ars_Arab
+Moroccan Arabic	ary_Arab
+Egyptian Arabic	arz_Arab
+Assamese	asm_Beng
+Asturian	ast_Latn
+Awadhi	awa_Deva
+Central Aymara	ayr_Latn
+South Azerbaijani	azb_Arab
+North Azerbaijani	azj_Latn
+Bashkir	bak_Cyrl
+Bambara	bam_Latn
+Balinese	ban_Latn
+Belarusian	bel_Cyrl
+Bemba	bem_Latn
+Bengali	ben_Beng
+Bhojpuri	bho_Deva
+Banjar (Jawi script)	bjn_Arab
+Banjar (Latin script)	bjn_Latn
+Lhasa Tibetan	bod_Tibt
+Bosnian	bos_Latn
+Bodo	brx_Deva
+Buginese	bug_Latn
+Bulgarian	bul_Cyrl
+Catalan	cat_Latn
+Cebuano	ceb_Latn
+Czech	ces_Latn
+Chuvash	chv_Cyrl
+Chokwe	cjk_Latn
+Central Kurdish	ckb_Arab
+Mandarin Chinese (Standard Beijing)	cmn_Hans
+Mandarin Chinese (Taiwanese)	cmn_Hant
+Crimean Tatar	crh_Latn
+Welsh	cym_Latn
+Danish	dan_Latn
+German	deu_Latn
+Dogri	dgo_Deva
+Southwestern Dinka	dik_Latn
+Dyula	dyu_Latn
+Dzongkha	dzo_Tibt
+Estonian	ekk_Latn
+Greek	ell_Grek
+English	eng_Latn
+Esperanto	epo_Latn
+Basque	eus_Latn
+Ewe	ewe_Latn
+Faroese	fao_Latn
+Fijian	fij_Latn
+Filipino	fil_Latn
+Finnish	fin_Latn
+Fon	fon_Latn
+French	fra_Latn
+Friulian	fur_Latn
+Nigerian Fulfulde	fuv_Latn
+West Central Oromo	gaz_Latn
+Scottish Gaelic	gla_Latn
+Irish	gle_Latn
+Galician	glg_Latn
+Goan Konkani	gom_Deva
+Paraguayan Guaraní	gug_Latn
+Gujarati	guj_Gujr
+Haitian Creole	hat_Latn
+Hausa	hau_Latn
+Hebrew	heb_Hebr
+Hindi	hin_Deva
+Chhattisgarhi	hne_Deva
+Croatian	hrv_Latn
+Hungarian	hun_Latn
+Armenian	hye_Armn
+Igbo	ibo_Latn
+Ilocano	ilo_Latn
+Indonesian	ind_Latn
+Icelandic	isl_Latn
+Italian	ita_Latn
+Javanese	jav_Latn
+Japanese	jpn_Jpan
+Kabyle	kab_Latn
+Jingpho	kac_Latn
+Kamba	kam_Latn
+Kannada	kan_Knda
+Kashmiri (Arabic script)	kas_Arab
+Kashmiri (Devanagari script)	kas_Deva
+Georgian	kat_Geor
+Kazakh	kaz_Cyrl
+Kabiyè	kbp_Latn
+Kabuverdianu	kea_Latn
+Halh Mongolian	khk_Cyrl
+Khmer (Central)	khm_Khmr
+Kikuyu	kik_Latn
+Kinyarwanda	kin_Latn
+Kyrgyz	kir_Cyrl
+Kimbundu	kmb_Latn
+Northern Kurdish	kmr_Latn
+Central Kanuri (Arabic script)	knc_Arab
+Central Kanuri (Latin script)	knc_Latn
+Korean	kor_Hang
+Kituba (DRC)	ktu_Latn
+Lao	lao_Laoo
+Ligurian (Genoese)	lij_Latn
+Limburgish	lim_Latn
+Lingala	lin_Latn
+Lithuanian	lit_Latn
+Lombard	lmo_Latn
+Latgalian	ltg_Latn
+Luxembourgish	ltz_Latn
+Luba-Kasai	lua_Latn
+Ganda	lug_Latn
+Luo	luo_Latn
+Mizo	lus_Latn
+Standard Latvian	lvs_Latn
+Magahi	mag_Deva
+Maithili	mai_Deva
+Malayalam	mal_Mlym
+Marathi	mar_Deva
+Meadow Mari	mhr_Cyrl
+Minangkabau (Jawi script)	min_Arab
+Minangkabau (Latin script)	min_Latn
+Macedonian	mkd_Cyrl
+Maltese	mlt_Latn
+Meitei (Manipuri, Bengali script)	mni_Beng
+Meitei (Manipuri, Meitei script)	mni_Mtei
+Mossi	mos_Latn
+Maori	mri_Latn
+Burmese	mya_Mymr
+Dutch	nld_Latn
+Norwegian Nynorsk	nno_Latn
+Norwegian Bokmål	nob_Latn
+Nepali	npi_Deva
+Nko	nqo_Nkoo
+Northern Sotho	nso_Latn
+Nuer	nus_Latn
+Nyanja	nya_Latn
+Occitan	oci_Latn
+Odia	ory_Orya
+Pangasinan	pag_Latn
+Eastern Panjabi	pan_Guru
+Papiamento	pap_Latn
+Southern Pashto	pbt_Arab
+Western Persian	pes_Arab
+Plateau Malagasy	plt_Latn
+Polish	pol_Latn
+Portuguese (Brazilian)	por_Latn
+Dari	prs_Arab
+Ayacucho Quechua	quy_Latn
+Romanian	ron_Latn
+Rundi	run_Latn
+Russian	rus_Cyrl
+Sango	sag_Latn
+Sanskrit	san_Deva
+Santali	sat_Olck
+Sicilian	scn_Latn
+Shan	shn_Mymr
+Sinhala	sin_Sinh
+Slovak	slk_Latn
+Slovenian	slv_Latn
+Samoan	smo_Latn
+Shona	sna_Latn
+Sindhi (Arabic script)	snd_Arab
+Sindhi (Devanagari script)	snd_Deva
+Somali	som_Latn
+Southern Sotho	sot_Latn
+Spanish (Latin American)	spa_Latn
+Sardinian	srd_Latn
+Serbian	srp_Cyrl
+Swati	ssw_Latn
+Sundanese	sun_Latn
+Swedish	swe_Latn
+Swahili	swh_Latn
+Silesian	szl_Latn
+Tamil	tam_Taml
+Tamasheq (Latin script)	taq_Latn
+Tamasheq (Tifinagh script)	taq_Tfng
+Tatar	tat_Cyrl
+Telugu	tel_Telu
+Tajik	tgk_Cyrl
+Thai	tha_Thai
+Tigrinya	tir_Ethi
+Tok Pisin	tpi_Latn
+Tswana	tsn_Latn
+Tsonga	tso_Latn
+Turkmen	tuk_Latn
+Tumbuka	tum_Latn
+Turkish	tur_Latn
+Akuapem Twi	twi_Latn
+Asante Twi	twi_Latn
+Uyghur	uig_Arab
+Ukrainian	ukr_Cyrl
+Umbundu	umb_Latn
+Urdu	urd_Arab
+Northern Uzbek	uzn_Latn
+Venetian	vec_Latn
+Vietnamese	vie_Latn
+Waray	war_Latn
+Wolof	wol_Latn
+Xhosa	xho_Latn
+Eastern Yiddish	ydd_Hebr
+Yoruba	yor_Latn
+Yue Chinese (Hong Kong Cantonese)	yue_Hant
+Standard Moroccan Tamazight	zgh_Tfng
+Standard Malay	zsm_Latn
+Zulu	zul_Latn '''
+codes_as_string = codes_as_string_new.split('\n')
+
+flores_codes_latest = {}
+for code in codes_as_string:
+    code = code.strip()  # Remove leading and trailing whitespace
+    print("Processing code:", code)
+    lang, lang_code = code.split('\t')
+    flores_codes_latest[lang] = lang_code
+
+