@spec all_languages() :: [language()]

Get the list of supported languages.

Example

iex> Lingua.all_languages()
[:afrikaans, :albanian, :arabic, :armenian, :azerbaijani, :basque, :belarusian,
 :bengali, :bokmal, :bosnian, :bulgarian, :catalan, :chinese, :croatian, :czech,
 :danish, :dutch, :english, :esperanto, :estonian, :finnish, :french, :ganda,
 :georgian, :german, :greek, :gujarati, :hebrew, :hindi, :hungarian, :icelandic,
 :indonesian, :irish, :italian, :japanese, :kazakh, :korean, :latin, :latvian,
 :lithuanian, :macedonian, :malay, :maori, :marathi, :mongolian, :nynorsk,
 :persian, :polish, :portuguese, :punjabi, :romanian, :russian, :serbian,
 :shona, :slovak, :slovene, :somali, :sotho, :spanish, :swahili, :swedish,
 :tagalog, :tamil, :telugu, :thai, :tsonga, :tswana, :turkish, :ukrainian,
 :urdu, :vietnamese, :welsh, :xhosa, :yoruba, :zulu]

@spec all_languages_with_arabic_script() :: [language()]

Get the list of supported languages using Arabic script.

Example

iex> Lingua.all_languages_with_arabic_script()
[:arabic, :persian, :urdu]

@spec all_languages_with_cyrillic_script() :: [language()]

Get the list of supported languages using Cyrillic script.

Example

iex> Lingua.all_languages_with_cyrillic_script()
[:belarusian, :bulgarian, :kazakh, :macedonian, :mongolian, :russian, :serbian, :ukrainian]

@spec all_languages_with_devanagari_script() :: [language()]

Get the list of supported languages using Devanagari script.

Example

iex> Lingua.all_languages_with_devanagari_script()
[:hindi, :marathi]

@spec all_languages_with_latin_script() :: [language()]

Get the list of supported languages using Latin script.

Example

iex> Lingua.all_languages_with_latin_script()
[:afrikaans, :albanian, :azerbaijani, :basque, :bokmal, :bosnian, :catalan,
 :croatian, :czech, :danish, :dutch, :english, :esperanto, :estonian, :finnish,
 :french, :ganda, :german, :hungarian, :icelandic, :indonesian, :irish,
 :italian, :latin, :latvian, :lithuanian, :malay, :maori, :nynorsk, :polish,
 :portuguese, :romanian, :shona, :slovak, :slovene, :somali, :sotho, :spanish,
 :swahili, :swedish, :tagalog, :tsonga, :tswana, :turkish, :vietnamese, :welsh,
 :xhosa, :yoruba, :zulu]

@spec all_spoken_languages() :: [language()]

Get the list of supported spoken languages.

Example

iex> Lingua.all_spoken_languages()
[:afrikaans, :albanian, :arabic, :armenian, :azerbaijani, :basque, :belarusian,
 :bengali, :bokmal, :bosnian, :bulgarian, :catalan, :chinese, :croatian, :czech,
 :danish, :dutch, :english, :esperanto, :estonian, :finnish, :french, :ganda,
 :georgian, :german, :greek, :gujarati, :hebrew, :hindi, :hungarian, :icelandic,
 :indonesian, :irish, :italian, :japanese, :kazakh, :korean, :latvian,
 :lithuanian, :macedonian, :malay, :maori, :marathi, :mongolian, :nynorsk,
 :persian, :polish, :portuguese, :punjabi, :romanian, :russian, :serbian,
 :shona, :slovak, :slovene, :somali, :sotho, :spanish, :swahili, :swedish,
 :tagalog, :tamil, :telugu, :thai, :tsonga, :tswana, :turkish, :ukrainian,
 :urdu, :vietnamese, :welsh, :xhosa, :yoruba, :zulu]

@spec detect(String.t(), [detect_option()]) :: detect_result()

Detect the language of the given input text. By default, all supported languages will be considered and the minimum relative distance is 0.0.

Returns the detected language, or a list of languages and their confidence values, or :no_match if the given text doesn't match a language.

Options

• builder_option: - can be one of the following (defaults to :all_languages):

  • :all_languages - consider every supported language
  • :all_spoken_languages - consider only currently spoken languages
  • :all_languages_with_arabic_script - consider only languages written in Arabic script
  • :all_languages_with_cyrillic_script - consider only languages written in Cyrillic script
  • :all_languages_with_devanagari_script - consider only languages written in Devanagari script
  • :all_languages_with_latin_script - consider only languages written in Latin script
  • :with_languages - consider only the languages supplied in the languages option
  • :without_languages - consider all languages except those supplied in the languages option

• languages: - specify two or more languages to consider or exclude depending on builder_option: (defaults to []). Accepts any combination of language names, ISO 639-1 codes (2-letter), or ISO 639-3 codes (3-letter). For example: [:english, :ru, :heb] mixes the language name with ISO 639-1 and ISO 639-3 codes.

• minimum_relative_distance: - specify the minimum relative distance (0.0 - 0.99) required for a language to be considered a match for the input. See the lingua-rs documentation for details. (defaults to 0.0)

• compute_language_confidence_values: - returns the full list of language matches for the input and their confidence values. (defaults to false)

• preload_language_models: - preload all language models instead of just those required for the match. (defaults to false)

• low_accuracy_mode: - use low accuracy mode for faster detection at the cost of accuracy. (defaults to false)

Return Values

• {:ok, language} - the detected language (e.g., {:ok, :english})
• {:ok, :no_match} - no language matched the input
• {:ok, [confidence_values]} - list of {language, confidence} tuples when compute_language_confidence_values: true
• {:error, :insufficient_languages} - fewer than 2 languages provided with :with_languages or :without_languages
• {:error, :out_of_range_minimum_relative_distance} - minimum_relative_distance not in range 0.0..0.99

Examples

iex> Lingua.detect("this is definitely English")
{:ok, :english}

iex> Lingua.detect("וזה בעברית")
{:ok, :hebrew}

iex> Lingua.detect("państwowych", builder_option: :with_languages, languages: [:english, :russian, :polish])
{:ok, :polish}

iex> Lingua.detect("ѕидови", builder_option: :all_languages_with_cyrillic_script)
{:ok, :macedonian}

iex> Lingua.detect("כלב", builder_option: :with_languages, languages: [:english, :russian, :polish])
{:ok, :no_match}

iex> Lingua.detect("what in the world is this", builder_option: :with_languages, languages: [:english, :russian, :hebrew], compute_language_confidence_values: true)
{:ok, [{:english, 1.0}, {:hebrew, 0.0}, {:russian, 0.0}]}

Using ISO codes in the languages list:

iex> Lingua.detect("hello world", builder_option: :with_languages, languages: [:en, :de])
{:ok, :english}

iex> Lingua.detect("hello world", builder_option: :with_languages, languages: [:eng, :deu])
{:ok, :english}

@spec detect!(String.t(), [detect_option()]) ::
  language() | :no_match | [confidence_value()]

Like detect/2, but returns the result value or raises an error.

Examples

iex> Lingua.detect!("this is definitely English")
:english

iex> Lingua.detect!("hello", builder_option: :with_languages, languages: [:english, :german])
:english

@spec init() :: :ok

Initialize the detector. Calling this is optional but it may come in handy in cases where you want lingua-rs to load the language corpora so that subsequent calls to detect are fast. The first time the detector is run it can take some time to load (~12 seconds on my Macbook Pro). See also the preload_language_models option below.

Example

iex> Lingua.init()
:ok

@spec iso_code_639_1_for_language(language()) ::
  {:ok, iso_639_1()} | {:error, :unrecognized_language}

Get the ISO 639-1 language code for the given language.

Example

iex> Lingua.iso_code_639_1_for_language(:english)
{:ok, :en}
iex> Lingua.iso_code_639_1_for_language(:nope)
{:error, :unrecognized_language}

@spec iso_code_639_3_for_language(language()) ::
  {:ok, iso_639_3()} | {:error, :unrecognized_language}

Get the ISO 639-3 language code for the given language.

Example

iex> Lingua.iso_code_639_3_for_language(:english)
{:ok, :eng}
iex> Lingua.iso_code_639_3_for_language(:nope)
{:error, :unrecognized_language}

@spec language_for_iso_code(iso_639_1() | iso_639_3()) ::
  {:ok, language()} | {:error, :unrecognized_iso_code}

Get the language for the given ISO 639-1 or 639-3 language code.

Example

iex> Lingua.language_for_iso_code(:en)
{:ok, :english}
iex> Lingua.language_for_iso_code(:eng)
{:ok, :english}
iex> Lingua.language_for_iso_code(:mop)
{:error, :unrecognized_iso_code}

@spec language_for_iso_code_639_1(iso_639_1()) ::
  {:ok, language()} | {:error, :unrecognized_iso_code}

Get the language for the given ISO 639-1 language code.

Example

iex> Lingua.language_for_iso_code_639_1(:en)
{:ok, :english}
iex> Lingua.language_for_iso_code_639_1(:er)
{:error, :unrecognized_iso_code}

@spec language_for_iso_code_639_3(iso_639_3()) ::
  {:ok, language()} | {:error, :unrecognized_iso_code}

Get the language for the given ISO 639-3 language code.

Example

iex> Lingua.language_for_iso_code_639_3(:eng)
{:ok, :english}
iex> Lingua.language_for_iso_code_639_3(:enr)
{:error, :unrecognized_iso_code}