@spec add_stop_word(language(), String.t()) :: :ok

Adds a new stop word to the specified language's stop words set.

Updates the in-memory cache (does not persist to file).

Examples

iex> ExNlp.Stopwords.add_stop_word(:english, "custom")
:ok
iex> ExNlp.Stopwords.get_stop_words(:english) |> MapSet.member?("custom")
true

@spec clear_cache() :: :ok

Clears the stop words cache, forcing reload from files.

Examples

iex> ExNlp.Stopwords.clear_cache()
:ok

@spec get_stop_words(language()) :: MapSet.t(String.t())

Returns a MapSet of stop words for the specified language.

Loads from cache or file if not already cached.

Examples

iex> stopwords = ExNlp.Stopwords.get_stop_words(:english)
iex> MapSet.member?(stopwords, "the")
true

@spec is_stopword?(String.t(), language()) :: boolean()

Checks if a word is a stopword in the given language.

Arguments

• word - The word to check (will be lowercased)
• language - The language atom

Returns

true if the word is a stopword, false otherwise.

Examples

iex> ExNlp.Stopwords.is_stopword?("the", :english)
true

iex> ExNlp.Stopwords.is_stopword?("running", :english)
false

@spec list(language()) :: [String.t()]

Gets the complete list of stopwords for a language.

Examples

iex> stopwords = ExNlp.Stopwords.list(:english)
iex> Enum.member?(stopwords, "the")
true

@spec remove([String.t() | token()], language()) :: [String.t() | token()]

Removes stopwords from a list of words or tokens.

Supports both lists of strings and lists of Token structs.

Examples

# With strings
iex> words = ["the", "quick", "brown", "fox", "the"]
iex> ExNlp.Stopwords.remove(words, :english)
["quick", "brown", "fox"]

# With tokens
iex> tokens = [%ExNlp.Token{text: "the"}, %ExNlp.Token{text: "quick"}]
iex> ExNlp.Stopwords.remove(tokens, :english)
[%ExNlp.Token{text: "quick"}]

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

Returns the list of supported languages.

Examples

iex> languages = ExNlp.Stopwords.supported_languages()
iex> :english in languages
true