lokit-python 0.1.0__cp312-cp312-win32.whl

lokit/__init__.py

@@ -0,0 +1,128 @@
+from lokit.data.structure import (
+    AdjacentContext,
+    BaseStructure,
+    CodePart,
+    Comment,
+    Data,
+    Meta,
+    Origin,
+    Plural,
+    PluralCategory,
+    SegmentPart,
+    Tags,
+    TextPart,
+    TranslationStatus,
+)
+from lokit.data.tag_types import TieData, TieType
+from lokit.exporters import (
+    export_csv,
+    export_csv_async,
+    export_idml,
+    export_idml_async,
+    export_html,
+    export_html_async,
+    export_json_i18n,
+    export_json_i18n_async,
+    export_po,
+    export_po_async,
+    export_tmx,
+    export_tmx_from_json,
+    export_xliff,
+    export_xliff_async,
+    export_xliff_from_json,
+    export_xliff_from_json_async,
+    export_xlsx,
+    export_xlsx_async,
+)
+from lokit.importers import (
+    import_csv,
+    import_csv_async,
+    import_idml,
+    import_idml_async,
+    import_html,
+    import_html_async,
+    import_json_i18n,
+    import_json_i18n_async,
+    import_po,
+    import_po_async,
+    import_tmx,
+    import_tmx_async,
+    import_xliff,
+    import_xliff_async,
+    import_xlsx,
+    import_xlsx_async,
+)
+from lokit.io import load_lokit_json, load_lokit_json_bytes
+from lokit.logic import Lokit, MatchResult
+from lokit.parsers.csv.extraction import CsvExtractor
+from lokit.parsers.xlsx.extraction import XlsxExtractor
+from lokit.parsers.html.extraction import HtmlExtractor
+from lokit.parsers.po.extraction import PoExtractor
+from lokit.parsers.json_i18n.extraction import JsonI18nExtractor
+from lokit.parsers.idml.extraction import IdmlExtractor
+from lokit.parsers.tmx.extraction import TmxExtractor
+from lokit.parsers.xliff.extraction import XliffExtractor
+
+__all__ = [
+    "AdjacentContext",
+    "BaseStructure",
+    "CodePart",
+    "Comment",
+    "Data",
+    "Meta",
+    "Lokit",
+    "MatchResult",
+    "Origin",
+    "Plural",
+    "PluralCategory",
+    "SegmentPart",
+    "Tags",
+    "TextPart",
+    "TieData",
+    "TieType",
+    "TmxExtractor",
+    "TranslationStatus",
+    "XliffExtractor",
+    "CsvExtractor",
+    "XlsxExtractor",
+    "HtmlExtractor",
+    "PoExtractor",
+    "JsonI18nExtractor",
+    "IdmlExtractor",
+    "export_csv",
+    "export_csv_async",
+    "export_idml",
+    "export_idml_async",
+    "export_html",
+    "export_html_async",
+    "export_json_i18n",
+    "export_json_i18n_async",
+    "export_po",
+    "export_po_async",
+    "export_tmx",
+    "export_tmx_from_json",
+    "export_xliff",
+    "export_xliff_async",
+    "export_xliff_from_json",
+    "export_xliff_from_json_async",
+    "export_xlsx",
+    "export_xlsx_async",
+    "import_csv",
+    "import_csv_async",
+    "import_idml",
+    "import_idml_async",
+    "import_html",
+    "import_html_async",
+    "import_json_i18n",
+    "import_json_i18n_async",
+    "import_po",
+    "import_po_async",
+    "import_tmx",
+    "import_tmx_async",
+    "import_xliff",
+    "import_xliff_async",
+    "import_xlsx",
+    "import_xlsx_async",
+    "load_lokit_json",
+    "load_lokit_json_bytes",
+]

lokit/core/logger.py

@@ -0,0 +1,20 @@
+import logging
+import sys
+
+
+def setup_logger(name: str = "lokit") -> logging.Logger:
+    logger = logging.getLogger(name)
+    if not logger.hasHandlers():
+        handler = logging.StreamHandler(sys.stdout)
+        formatter = logging.Formatter(
+            fmt="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
+            datefmt="%Y-%m-%dT%H:%M:%SZ",
+        )
+        handler.setFormatter(formatter)
+        logger.addHandler(handler)
+        logger.setLevel(logging.INFO)
+        logger.propagate = False
+    return logger
+
+
+logger = setup_logger()

lokit/data/lang_codes.py

@@ -0,0 +1,455 @@
+from enum import StrEnum
+
+
+class Language(StrEnum):
+    aa = "Afar"
+    ab = "Abkhazian"
+    ae = "Avestan"
+    af = "Afrikaans"
+    ak = "Akan"
+    am = "Amharic"
+    an = "Aragonese"
+    ar = "Arabic"
+    as_ = "Assamese"
+    av = "Avaric"
+    ay = "Aymara"
+    az = "Azeri"
+    ba = "Bashkir"
+    be = "Belarusian"
+    bg = "Bulgarian"
+    bh = "Bihari"
+    bi = "Bislama"
+    bm = "Bambara"
+    bn = "Bengali"
+    bo = "Tibetan"
+    br = "Breton"
+    bs = "Bosnian"
+    ca = "Catalan"
+    ce = "Chechen"
+    ch = "Chamorro"
+    co = "Corsican"
+    cr = "Cree"
+    cs = "Czech"
+    cu = "Church Slavonic"
+    cv = "Chuvash"
+    cy = "Welsh"
+    da = "Danish"
+    de = "German"
+    div = "Divehi"
+    dv = "Divehi"
+    dz = "Bhutani"
+    ee = "Ewe"
+    el = "Greek"
+    en = "English"
+    eo = "Esperanto"
+    es = "Spanish"
+    et = "Estonian"
+    eu = "Basque"
+    fa = "Farsi"
+    ff = "Fulah"
+    fi = "Finnish"
+    fj = "Fiji"
+    fo = "Faroese"
+    fr = "French"
+    fy = "Frisian"
+    ga = "Irish"
+    gd = "Gaelic"
+    gl = "Galician"
+    gn = "Guarani"
+    gu = "Gujarati"
+    gv = "Manx"
+    ha = "Hausa"
+    he = "Hebrew"
+    hi = "Hindi"
+    ho = "Hiri Motu"
+    hr = "Croatian"
+    ht = "Haitian"
+    hu = "Hungarian"
+    hy = "Armenian"
+    hz = "Herero"
+    ia = "Interlingua"
+    id = "Indonesian"
+    ie = "Interlingue"
+    ig = "Igbo"
+    ii = "Sichuan Yi"
+    ik = "Inupiak"
+    in_ = "Indonesian"
+    io = "Ido"
+    is_ = "Icelandic"
+    it = "Italian"
+    iu = "Inuktitut"
+    iw = "Hebrew"
+    ja = "Japanese"
+    ji = "Yiddish"
+    jv = "Javanese"
+    jw = "Javanese"
+    ka = "Georgian"
+    kg = "Kongo"
+    ki = "Kikuyu"
+    kj = "Kuanyama"
+    kk = "Kazakh"
+    kl = "Greenlandic"
+    km = "Cambodian"
+    kn = "Kannada"
+    ko = "Korean"
+    kok = "Konkani"
+    kr = "Kanuri"
+    ks = "Kashmiri"
+    ku = "Kurdish"
+    kv = "Komi"
+    kw = "Cornish"
+    ky = "Kirghiz"
+    kz = "Kyrgyz"
+    la = "Latin"
+    lb = "Luxembourgish"
+    lg = "Ganda"
+    li = "Limburgan"
+    ln = "Lingala"
+    lo = "Laothian"
+    ls = "Slovenian"
+    lt = "Lithuanian"
+    lu = "Luba-Katanga"
+    lv = "Latvian"
+    mg = "Malagasy"
+    mh = "Marshallese"
+    mi = "Maori"
+    mk = "FYRO Macedonian"
+    ml = "Malayalam"
+    mn = "Mongolian"
+    mo = "Moldavian"
+    mr = "Marathi"
+    ms = "Malay"
+    mt = "Maltese"
+    my = "Burmese"
+    na = "Nauru"
+    nb = "Norwegian (Bokmal)"
+    nd = "North Ndebele"
+    ne = "Nepali (India)"
+    ng = "Ndonga"
+    nl = "Dutch"
+    nn = "Norwegian (Nynorsk)"
+    no = "Norwegian"
+    nr = "South Ndebele"
+    ns = "Northern Sotho"
+    nv = "Navajo"
+    ny = "Chichewa"
+    oc = "Occitan"
+    oj = "Ojibwa"
+    om = "(Afan)/Oromoor/Oriya"
+    or_ = "Oriya"
+    os = "Ossetian"
+    pa = "Punjabi"
+    pi = "Pali"
+    pl = "Polish"
+    ps = "Pashto/Pushto"
+    pt = "Portuguese"
+    qu = "Quechua"
+    rm = "Rhaeto-Romanic"
+    rn = "Kirundi"
+    ro = "Romanian"
+    ru = "Russian"
+    rw = "Kinyarwanda"
+    sa = "Sanskrit"
+    sb = "Sorbian"
+    sc = "Sardinian"
+    sd = "Sindhi"
+    se = "Sami"
+    sg = "Sangro"
+    sh = "Serbo-Croatian"
+    si = "Singhalese"
+    sk = "Slovak"
+    sl = "Slovenian"
+    sm = "Samoan"
+    sn = "Shona"
+    so = "Somali"
+    sq = "Albanian"
+    sr = "Serbian"
+    ss = "Siswati"
+    st = "Sesotho"
+    su = "Sundanese"
+    sv = "Swedish"
+    sw = "Swahili"
+    sx = "Sutu"
+    syr = "Syriac"
+    ta = "Tamil"
+    te = "Telugu"
+    tg = "Tajik"
+    th = "Thai"
+    ti = "Tigrinya"
+    tk = "Turkmen"
+    tl = "Tagalog"
+    tn = "Tswana"
+    to = "Tonga"
+    tr = "Turkish"
+    ts = "Tsonga"
+    tt = "Tatar"
+    tw = "Twi"
+    ty = "Tahitian"
+    ug = "Uighur"
+    uk = "Ukrainian"
+    ur = "Urdu"
+    us = "English"
+    uz = "Uzbek"
+    ve = "Venda"
+    vi = "Vietnamese"
+    vo = "Volapuk"
+    wa = "Walloon"
+    wo = "Wolof"
+    xh = "Xhosa"
+    yi = "Yiddish"
+    yo = "Yoruba"
+    za = "Zhuang"
+    zh = "Chinese"
+    zu = "Zulu"
+
+
+class Locale(StrEnum):
+    af = "Afghanistan"
+    ax = "Åland Islands"
+    al = "Albania"
+    dz = "Algeria"
+    as_ = "American Samoa"
+    ad = "Andorra"
+    ao = "Angola"
+    ai = "Anguilla"
+    aq = "Antarctica"
+    ag = "Antigua and Barbuda"
+    ar = "Argentina"
+    am = "Armenia"
+    aw = "Aruba"
+    au = "Australia"
+    at = "Austria"
+    az = "Azerbaijan"
+    bs = "Bahamas"
+    bh = "Bahrain"
+    bd = "Bangladesh"
+    bb = "Barbados"
+    by = "Belarus"
+    be = "Belgium"
+    bz = "Belize"
+    bj = "Benin"
+    bm = "Bermuda"
+    bt = "Bhutan"
+    bo = "Bolivia, Plurinational State of"
+    bq = "Bonaire, Sint Eustatius and Saba[d]"
+    ba = "Bosnia and Herzegovina"
+    bw = "Botswana"
+    bv = "Bouvet Island"
+    br = "Brazil"
+    io = "British Indian Ocean Territory"
+    bn = "Brunei Darussalam"
+    bg = "Bulgaria"
+    bf = "Burkina Faso"
+    bi = "Burundi"
+    cv = "Cabo Verde"
+    kh = "Cambodia"
+    cm = "Cameroon"
+    ca = "Canada"
+    ky = "Cayman Islands"
+    cf = "Central African Republic"
+    td = "Chad"
+    cl = "Chile"
+    cn = "China[c]"
+    cx = "Christmas Island"
+    cc = "Cocos (Keeling) Islands"
+    co = "Colombia"
+    km = "Comoros"
+    cg = "Congo"
+    cd = "Congo, Democratic Republic of the"
+    ck = "Cook Islands"
+    cr = "Costa Rica"
+    ci = "Côte d'Ivoire"
+    hr = "Croatia"
+    cu = "Cuba"
+    cw = "Curaçao"
+    cy = "Cyprus[c]"
+    cz = "Czechia"
+    dk = "Denmark"
+    dj = "Djibouti"
+    dm = "Dominica"
+    do = "Dominican Republic"
+    ec = "Ecuador"
+    eg = "Egypt"
+    sv = "El Salvador"
+    gq = "Equatorial Guinea"
+    er = "Eritrea"
+    ee = "Estonia"
+    sz = "Eswatini"
+    et = "Ethiopia"
+    fk = "Falkland Islands (Malvinas)[c]"
+    fo = "Faroe Islands"
+    fj = "Fiji"
+    fi = "Finland"
+    fr = "France"
+    gf = "French Guiana"
+    pf = "French Polynesia"
+    tf = "French Southern Territories"
+    ga = "Gabon"
+    gm = "Gambia"
+    ge = "Georgia"
+    de = "Germany"
+    gh = "Ghana"
+    gi = "Gibraltar"
+    gr = "Greece"
+    gl = "Greenland"
+    gd = "Grenada"
+    gp = "Guadeloupe"
+    gu = "Guam"
+    gt = "Guatemala"
+    gg = "Guernsey"
+    gn = "Guinea"
+    gw = "Guinea-Bissau"
+    gy = "Guyana"
+    ht = "Haiti"
+    hm = "Heard Island and McDonald Islands"
+    va = "Holy See"
+    hn = "Honduras"
+    hk = "Hong Kong"
+    hu = "Hungary"
+    is_ = "Iceland"
+    in_ = "India"
+    id = "Indonesia"
+    ir = "Iran, Islamic Republic of"
+    iq = "Iraq"
+    ie = "Ireland"
+    im = "Isle of Man"
+    il = "Israel"
+    it = "Italy"
+    jm = "Jamaica"
+    jp = "Japan"
+    je = "Jersey"
+    jo = "Jordan"
+    kz = "Kazakhstan"
+    ke = "Kenya"
+    ki = "Kiribati"
+    kp = "Korea, Democratic People's Republic of"
+    kr = "Korea, Republic of"
+    kw = "Kuwait"
+    kg = "Kyrgyzstan"
+    la = "Lao People's Democratic Republic"
+    lv = "Latvia"
+    lb = "Lebanon"
+    ls = "Lesotho"
+    lr = "Liberia"
+    ly = "Libya"
+    li = "Liechtenstein"
+    lt = "Lithuania"
+    lu = "Luxembourg"
+    mo = "Macao"
+    mg = "Madagascar"
+    mw = "Malawi"
+    my = "Malaysia"
+    mv = "Maldives"
+    ml = "Mali"
+    mt = "Malta"
+    mh = "Marshall Islands"
+    mq = "Martinique"
+    mr = "Mauritania"
+    mu = "Mauritius"
+    yt = "Mayotte"
+    mx = "Mexico"
+    fm = "Micronesia, Federated States of"
+    md = "Moldova, Republic of"
+    mc = "Monaco"
+    mn = "Mongolia"
+    me = "Montenegro"
+    ms = "Montserrat"
+    ma = "Morocco"
+    mz = "Mozambique"
+    mm = "Myanmar"
+    na = "Namibia"
+    nr = "Nauru"
+    np = "Nepal"
+    nl = "Netherlands, Kingdom of the"
+    nc = "New Caledonia"
+    nz = "New Zealand"
+    ni = "Nicaragua"
+    ne = "Niger"
+    ng = "Nigeria"
+    nu = "Niue"
+    nf = "Norfolk Island"
+    mk = "North Macedonia"
+    mp = "Northern Mariana Islands"
+    no = "Norway"
+    om = "Oman"
+    pk = "Pakistan"
+    pw = "Palau"
+    ps = "Palestine, State of[c]"
+    pa = "Panama"
+    pg = "Papua New Guinea"
+    py = "Paraguay"
+    pe = "Peru"
+    ph = "Philippines"
+    pn = "Pitcairn"
+    pl = "Poland"
+    pt = "Portugal"
+    pr = "Puerto Rico"
+    qa = "Qatar"
+    re = "Réunion"
+    ro = "Romania"
+    ru = "Russian Federation"
+    rw = "Rwanda"
+    bl = "Saint Barthélemy"
+    sh = "Saint Helena, Ascension and Tristan da Cunha[e]"
+    kn = "Saint Kitts and Nevis"
+    lc = "Saint Lucia"
+    mf = "Saint Martin (French part)"
+    pm = "Saint Pierre and Miquelon"
+    vc = "Saint Vincent and the Grenadines"
+    ws = "Samoa"
+    sm = "San Marino"
+    st = "Sao Tome and Principe"
+    sa = "Saudi Arabia"
+    sn = "Senegal"
+    rs = "Serbia"
+    sc = "Seychelles"
+    sl = "Sierra Leone"
+    sg = "Singapore"
+    sx = "Sint Maarten (Dutch part)"
+    sk = "Slovakia"
+    si = "Slovenia"
+    sb = "Solomon Islands"
+    so = "Somalia"
+    za = "South Africa"
+    gs = "South Georgia and the South Sandwich Islands"
+    ss = "South Sudan"
+    es = "Spain"
+    lk = "Sri Lanka"
+    sd = "Sudan"
+    sr = "Suriname"
+    sj = "Svalbard and Jan Mayen[f]"
+    se = "Sweden"
+    ch = "Switzerland"
+    sy = "Syrian Arab Republic"
+    tw = "Taiwan, Province of China[c]"
+    tj = "Tajikistan"
+    tz = "Tanzania, United Republic of"
+    th = "Thailand"
+    tl = "Timor-Leste"
+    tg = "Togo"
+    tk = "Tokelau"
+    to = "Tonga"
+    tt = "Trinidad and Tobago"
+    tn = "Tunisia"
+    tr = "Türkiye"
+    tm = "Turkmenistan"
+    tc = "Turks and Caicos Islands"
+    tv = "Tuvalu"
+    ug = "Uganda"
+    ua = "Ukraine"
+    ae = "United Arab Emirates"
+    gb = "United Kingdom of Great Britain and Northern Ireland"
+    us = "United States of America"
+    um = "United States Minor Outlying Islands[g]"
+    uy = "Uruguay"
+    uz = "Uzbekistan"
+    vu = "Vanuatu"
+    ve = "Venezuela, Bolivarian Republic of"
+    vn = "Viet Nam"
+    vg = "Virgin Islands (British)"
+    vi = "Virgin Islands (U.S.)"
+    wf = "Wallis and Futuna"
+    eh = "Western Sahara[c]"
+    ye = "Yemen"
+    zm = "Zambia"
+    zw = "Zimbabwe"