Languages

A human written or spoken language, defined by an ISO-639 three-letter code. This list is arbitrarily limited for some weird upstream technical reasons, but we'll happily accept pull requests for additional languages once there is a specific need for them to be supported.

Additional values can be introduced in FtM type enumerations within minor releases.

Attribute	Value	Detail
name	language	Used in schema definitions
label	Language	plural: Languages
group	languages	Used in search indexing to query all properties of a given type
matchable		Suitable for use in entity matching
pivot		Suitable for use as a pivot point for connecting to other entities

Data reference

Code	Label
ara	Arabic
nor	Norwegian
cnr	Montenegrin
afr	Afrikaans
amh	Amharic
aze	Azerbaijani
bel	Belarusian
ben	Bangla
bos	Bosnian
bul	Bulgarian
cat	Catalan
ces	Czech
dan	Danish
deu	German
ell	Greek
eng	English
est	Estonian
fas	Persian
fil	Filipino
fin	Finnish
fra	French
gle	Irish
heb	Hebrew
hin	Hindi
hrv	Croatian
hun	Hungarian
hye	Armenian
ind	Indonesian
isl	Icelandic
ita	Italian
jpn	Japanese
kan	Kannada
kat	Georgian
kaz	Kazakh
khm	Khmer
kir	Kyrgyz
kor	Korean
lao	Lao
lav	Latvian
lit	Lithuanian
ltz	Luxembourgish
mkd	Macedonian
mlt	Maltese
mon	Mongolian
msa	Malay
mya	Burmese
nep	Nepali
nld	Dutch
pol	Polish
por	Portuguese
pus	Pashto
ron	Romanian
rus	Russian
sin	Sinhala
slk	Slovak
slv	Slovenian
spa	Spanish
sqi	Albanian
srp	Serbian
swa	Swahili
swe	Swedish
tam	Tamil
tel	Telugu
tgk	Tajik
tgl	Tagalog
tha	Thai
tuk	Turkmen
tur	Turkish
ukr	Ukrainian
urd	Urdu
uzb	Uzbek
vie	Vietnamese
zho	Chinese

followthemoney.types.LanguageType

Bases: EnumType

A human written language. This list is arbitrarily limited for some weird upstream technical reasons, but we'll happily accept pull requests for additional languages once there is a specific need for them to be supported.

Source code in followthemoney/types/language.py

class LanguageType(EnumType):
    """A human written language. This list is arbitrarily limited for some
    weird upstream technical reasons, but we'll happily accept pull requests
    for additional languages once there is a specific need for them to be
    supported."""

    name = "language"
    group = "languages"
    label = _("Language")
    plural = _("Languages")
    matchable = False
    max_length = 16

    # Language whitelist
    LANGUAGES = [
        "afr",
        "amh",
        "ara",
        "aze",
        "bel",
        "ben",
        "bos",
        "bul",
        "cat",
        "ces",
        "cnr",
        "dan",
        "deu",
        "ell",
        "eng",
        "est",
        "fas",
        "fil",
        "fin",
        "fra",
        "gle",
        "heb",
        "hin",
        "hrv",
        "hun",
        "hye",
        "ind",
        "isl",
        "ita",
        "jpn",
        "kan",
        "kat",
        "kaz",
        "khm",
        "kir",
        "kor",
        "lao",
        "lav",
        "lit",
        "ltz",
        "mkd",
        "mlt",
        "mon",
        "msa",
        "mya",
        "nep",
        "nld",
        "nor",
        "pol",
        "por",
        "pus",
        "ron",
        "rus",
        "sin",
        "slk",
        "slv",
        "spa",
        "sqi",
        "srp",
        "swa",
        "swe",
        "tam",
        "tel",
        "tgk",
        "tgl",
        "tha",
        "tuk",
        "tur",
        "ukr",
        "urd",
        "uzb",
        "vie",
        "zho",
    ]
    LANGUAGES = get_env_list("FTM_LANGUAGES", LANGUAGES)
    LANGUAGES = [lang.lower().strip() for lang in LANGUAGES]

    def _locale_names(self, locale: Locale) -> EnumValues:
        names = {
            "ara": gettext("Arabic"),
            "nor": gettext("Norwegian"),
            "cnr": gettext("Montenegrin"),
        }
        for lang in self.LANGUAGES:
            if lang not in names:
                names[lang] = lang
        for code, label in locale.languages.items():
            code = iso_639_alpha3(code)
            if code in self.LANGUAGES and names[code] == code:
                names[code] = label
        return names

    def clean_text(
        self,
        text: str,
        fuzzy: bool = False,
        format: Optional[str] = None,
        proxy: Optional["EntityProxy"] = None,
    ) -> Optional[str]:
        code = iso_639_alpha3(text)
        if code not in self.LANGUAGES:
            return None
        return code