#
# Copyright (c) 2024-2026, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

"""Language conversion utilities for Azure services."""

from typing import Optional

from pipecat.transcriptions.language import Language, resolve_language


def language_to_azure_language(language: Language) -> Optional[str]:
    """Convert a Language enum to Azure language code.

    Args:
        language: The Language enum value to convert.

    Returns:
        The corresponding Azure language code, or None if not supported.
    """
    LANGUAGE_MAP = {
        # Afrikaans
        Language.AF: "af-ZA",
        Language.AF_ZA: "af-ZA",
        # Amharic
        Language.AM: "am-ET",
        Language.AM_ET: "am-ET",
        # Arabic
        Language.AR: "ar-AE",  # Default to UAE Arabic
        Language.AR_AE: "ar-AE",
        Language.AR_BH: "ar-BH",
        Language.AR_DZ: "ar-DZ",
        Language.AR_EG: "ar-EG",
        Language.AR_IQ: "ar-IQ",
        Language.AR_JO: "ar-JO",
        Language.AR_KW: "ar-KW",
        Language.AR_LB: "ar-LB",
        Language.AR_LY: "ar-LY",
        Language.AR_MA: "ar-MA",
        Language.AR_OM: "ar-OM",
        Language.AR_QA: "ar-QA",
        Language.AR_SA: "ar-SA",
        Language.AR_SY: "ar-SY",
        Language.AR_TN: "ar-TN",
        Language.AR_YE: "ar-YE",
        # Assamese
        Language.AS: "as-IN",
        Language.AS_IN: "as-IN",
        # Azerbaijani
        Language.AZ: "az-AZ",
        Language.AZ_AZ: "az-AZ",
        # Bulgarian
        Language.BG: "bg-BG",
        Language.BG_BG: "bg-BG",
        # Bengali
        Language.BN: "bn-IN",  # Default to Indian Bengali
        Language.BN_BD: "bn-BD",
        Language.BN_IN: "bn-IN",
        # Bosnian
        Language.BS: "bs-BA",
        Language.BS_BA: "bs-BA",
        # Catalan
        Language.CA: "ca-ES",
        Language.CA_ES: "ca-ES",
        # Czech
        Language.CS: "cs-CZ",
        Language.CS_CZ: "cs-CZ",
        # Welsh
        Language.CY: "cy-GB",
        Language.CY_GB: "cy-GB",
        # Danish
        Language.DA: "da-DK",
        Language.DA_DK: "da-DK",
        # German
        Language.DE: "de-DE",
        Language.DE_AT: "de-AT",
        Language.DE_CH: "de-CH",
        Language.DE_DE: "de-DE",
        # Greek
        Language.EL: "el-GR",
        Language.EL_GR: "el-GR",
        # English
        Language.EN: "en-US",  # Default to US English
        Language.EN_AU: "en-AU",
        Language.EN_CA: "en-CA",
        Language.EN_GB: "en-GB",
        Language.EN_HK: "en-HK",
        Language.EN_IE: "en-IE",
        Language.EN_IN: "en-IN",
        Language.EN_KE: "en-KE",
        Language.EN_NG: "en-NG",
        Language.EN_NZ: "en-NZ",
        Language.EN_PH: "en-PH",
        Language.EN_SG: "en-SG",
        Language.EN_TZ: "en-TZ",
        Language.EN_US: "en-US",
        Language.EN_ZA: "en-ZA",
        # Spanish
        Language.ES: "es-ES",  # Default to Spain Spanish
        Language.ES_AR: "es-AR",
        Language.ES_BO: "es-BO",
        Language.ES_CL: "es-CL",
        Language.ES_CO: "es-CO",
        Language.ES_CR: "es-CR",
        Language.ES_CU: "es-CU",
        Language.ES_DO: "es-DO",
        Language.ES_EC: "es-EC",
        Language.ES_ES: "es-ES",
        Language.ES_GQ: "es-GQ",
        Language.ES_GT: "es-GT",
        Language.ES_HN: "es-HN",
        Language.ES_MX: "es-MX",
        Language.ES_NI: "es-NI",
        Language.ES_PA: "es-PA",
        Language.ES_PE: "es-PE",
        Language.ES_PR: "es-PR",
        Language.ES_PY: "es-PY",
        Language.ES_SV: "es-SV",
        Language.ES_US: "es-US",
        Language.ES_UY: "es-UY",
        Language.ES_VE: "es-VE",
        # Estonian
        Language.ET: "et-EE",
        Language.ET_EE: "et-EE",
        # Basque
        Language.EU: "eu-ES",
        Language.EU_ES: "eu-ES",
        # Persian
        Language.FA: "fa-IR",
        Language.FA_IR: "fa-IR",
        # Finnish
        Language.FI: "fi-FI",
        Language.FI_FI: "fi-FI",
        # Filipino
        Language.FIL: "fil-PH",
        Language.FIL_PH: "fil-PH",
        # French
        Language.FR: "fr-FR",
        Language.FR_BE: "fr-BE",
        Language.FR_CA: "fr-CA",
        Language.FR_CH: "fr-CH",
        Language.FR_FR: "fr-FR",
        # Irish
        Language.GA: "ga-IE",
        Language.GA_IE: "ga-IE",
        # Galician
        Language.GL: "gl-ES",
        Language.GL_ES: "gl-ES",
        # Gujarati
        Language.GU: "gu-IN",
        Language.GU_IN: "gu-IN",
        # Hebrew
        Language.HE: "he-IL",
        Language.HE_IL: "he-IL",
        # Hindi
        Language.HI: "hi-IN",
        Language.HI_IN: "hi-IN",
        # Croatian
        Language.HR: "hr-HR",
        Language.HR_HR: "hr-HR",
        # Hungarian
        Language.HU: "hu-HU",
        Language.HU_HU: "hu-HU",
        # Armenian
        Language.HY: "hy-AM",
        Language.HY_AM: "hy-AM",
        # Indonesian
        Language.ID: "id-ID",
        Language.ID_ID: "id-ID",
        # Icelandic
        Language.IS: "is-IS",
        Language.IS_IS: "is-IS",
        # Italian
        Language.IT: "it-IT",
        Language.IT_IT: "it-IT",
        # Inuktitut
        Language.IU_CANS_CA: "iu-Cans-CA",
        Language.IU_LATN_CA: "iu-Latn-CA",
        # Japanese
        Language.JA: "ja-JP",
        Language.JA_JP: "ja-JP",
        # Javanese
        Language.JV: "jv-ID",
        Language.JV_ID: "jv-ID",
        # Georgian
        Language.KA: "ka-GE",
        Language.KA_GE: "ka-GE",
        # Kazakh
        Language.KK: "kk-KZ",
        Language.KK_KZ: "kk-KZ",
        # Khmer
        Language.KM: "km-KH",
        Language.KM_KH: "km-KH",
        # Kannada
        Language.KN: "kn-IN",
        Language.KN_IN: "kn-IN",
        # Korean
        Language.KO: "ko-KR",
        Language.KO_KR: "ko-KR",
        # Lao
        Language.LO: "lo-LA",
        Language.LO_LA: "lo-LA",
        # Lithuanian
        Language.LT: "lt-LT",
        Language.LT_LT: "lt-LT",
        # Latvian
        Language.LV: "lv-LV",
        Language.LV_LV: "lv-LV",
        # Macedonian
        Language.MK: "mk-MK",
        Language.MK_MK: "mk-MK",
        # Malayalam
        Language.ML: "ml-IN",
        Language.ML_IN: "ml-IN",
        # Mongolian
        Language.MN: "mn-MN",
        Language.MN_MN: "mn-MN",
        # Marathi
        Language.MR: "mr-IN",
        Language.MR_IN: "mr-IN",
        # Malay
        Language.MS: "ms-MY",
        Language.MS_MY: "ms-MY",
        # Maltese
        Language.MT: "mt-MT",
        Language.MT_MT: "mt-MT",
        # Burmese
        Language.MY: "my-MM",
        Language.MY_MM: "my-MM",
        # Norwegian
        Language.NB: "nb-NO",
        Language.NB_NO: "nb-NO",
        Language.NO: "nb-NO",
        # Nepali
        Language.NE: "ne-NP",
        Language.NE_NP: "ne-NP",
        # Dutch
        Language.NL: "nl-NL",
        Language.NL_BE: "nl-BE",
        Language.NL_NL: "nl-NL",
        # Odia
        Language.OR: "or-IN",
        Language.OR_IN: "or-IN",
        # Punjabi
        Language.PA: "pa-IN",
        Language.PA_IN: "pa-IN",
        # Polish
        Language.PL: "pl-PL",
        Language.PL_PL: "pl-PL",
        # Pashto
        Language.PS: "ps-AF",
        Language.PS_AF: "ps-AF",
        # Portuguese
        Language.PT: "pt-PT",
        Language.PT_BR: "pt-BR",
        Language.PT_PT: "pt-PT",
        # Romanian
        Language.RO: "ro-RO",
        Language.RO_RO: "ro-RO",
        # Russian
        Language.RU: "ru-RU",
        Language.RU_RU: "ru-RU",
        # Sinhala
        Language.SI: "si-LK",
        Language.SI_LK: "si-LK",
        # Slovak
        Language.SK: "sk-SK",
        Language.SK_SK: "sk-SK",
        # Slovenian
        Language.SL: "sl-SI",
        Language.SL_SI: "sl-SI",
        # Somali
        Language.SO: "so-SO",
        Language.SO_SO: "so-SO",
        # Albanian
        Language.SQ: "sq-AL",
        Language.SQ_AL: "sq-AL",
        # Serbian
        Language.SR: "sr-RS",
        Language.SR_RS: "sr-RS",
        Language.SR_LATN: "sr-Latn-RS",
        Language.SR_LATN_RS: "sr-Latn-RS",
        # Sundanese
        Language.SU: "su-ID",
        Language.SU_ID: "su-ID",
        # Swedish
        Language.SV: "sv-SE",
        Language.SV_SE: "sv-SE",
        # Swahili
        Language.SW: "sw-KE",
        Language.SW_KE: "sw-KE",
        Language.SW_TZ: "sw-TZ",
        # Tamil
        Language.TA: "ta-IN",
        Language.TA_IN: "ta-IN",
        Language.TA_LK: "ta-LK",
        Language.TA_MY: "ta-MY",
        Language.TA_SG: "ta-SG",
        # Telugu
        Language.TE: "te-IN",
        Language.TE_IN: "te-IN",
        # Thai
        Language.TH: "th-TH",
        Language.TH_TH: "th-TH",
        # Turkish
        Language.TR: "tr-TR",
        Language.TR_TR: "tr-TR",
        # Ukrainian
        Language.UK: "uk-UA",
        Language.UK_UA: "uk-UA",
        # Urdu
        Language.UR: "ur-IN",
        Language.UR_IN: "ur-IN",
        Language.UR_PK: "ur-PK",
        # Uzbek
        Language.UZ: "uz-UZ",
        Language.UZ_UZ: "uz-UZ",
        # Vietnamese
        Language.VI: "vi-VN",
        Language.VI_VN: "vi-VN",
        # Wu Chinese
        Language.WUU: "wuu-CN",
        Language.WUU_CN: "wuu-CN",
        # Yue Chinese
        Language.YUE: "yue-CN",
        Language.YUE_CN: "yue-CN",
        # Chinese
        Language.ZH: "zh-CN",
        Language.ZH_CN: "zh-CN",
        Language.ZH_CN_GUANGXI: "zh-CN-guangxi",
        Language.ZH_CN_HENAN: "zh-CN-henan",
        Language.ZH_CN_LIAONING: "zh-CN-liaoning",
        Language.ZH_CN_SHAANXI: "zh-CN-shaanxi",
        Language.ZH_CN_SHANDONG: "zh-CN-shandong",
        Language.ZH_CN_SICHUAN: "zh-CN-sichuan",
        Language.ZH_HK: "zh-HK",
        Language.ZH_TW: "zh-TW",
        # Zulu
        Language.ZU: "zu-ZA",
        Language.ZU_ZA: "zu-ZA",
    }
    return resolve_language(language, LANGUAGE_MAP, use_base_code=False)
