punkt/dist/esm/languageVars.d.ts

A port of NLTK's Punkt sentence tokenizer to JS.

/**
 * Stores variables, mostly regular expressions, which may be
 * language-dependent for correct application of the algorithm.
 * An extension of this class may modify its properties to suit
 * a language other than English; an instance can then be passed
 * as an argument to PunktSentenceTokenizer and PunktTrainer
 * constructors.
 */
export default class PunktLanguageVars {
    /**
     * Characters which are candidates for sentence boundaries
     */
    sentEndChars: string[];
    /**
     * Regular expression for boundary realignment
     */
    reBoundaryRealignment: RegExp;
    /**
     * Excludes some characters from starting word tokens
     */
    reWordStart: RegExp;
    /**
     * Hyphen and ellipsis are multi-character punctuation
     */
    reMultiCharPunct: RegExp;
    /**
     * Characters which are candidates for sentence boundaries
     */
    reSentEndChars: RegExp;
    /**
     * Regular expression for non-word characters
     */
    reNonWordChars: RegExp;
    /**
     * Regular expression for word tokenization
     */
    reWordTokenizer: RegExp;
    /**
     * Regular expression to find contexts including possible sentence boundaries.
     */
    rePeriodContext: RegExp;
    constructor();
}
//# sourceMappingURL=languageVars.d.ts.map