taipa/lib/util.js

Taiwanese morphological parsing library

"use strict";
Object.defineProperty(exports, "__esModule", { value: true });
exports.getSyllablesEnd = exports.getSyllablesStart = exports.getSyllablesInclude = exports.getDesinence = exports.getStem = exports.pairsToString = exports.getLemmas = exports.getStandaloneForms = exports.analyzeIntoSequence = exports.analyzeIntoSyllables = exports.getLetterSoundPairsSyllabic = exports.getLetterSoundPairsSequential = void 0;
const client_1 = require("./client");
const analyzer_1 = require("./unchange/analyzer");
const metaplasm_1 = require("./unchange/metaplasm");
const lemmatizer_1 = require("./unchange/lemmatizer");
const syllablelists_1 = require("./tonal/syllablelists");
/** Turn sounds into a sequence of letter-sound pairs */
function getLetterSoundPairsSequential(soundSeqs) {
    return soundSeqs
        .flatMap((v) => {
        return v;
    })
        .map((v) => [v.toString(), v.name]);
}
exports.getLetterSoundPairsSequential = getLetterSoundPairsSequential;
/** Turn sounds into syllabic letter-sound pairs. */
function getLetterSoundPairsSyllabic(soundSeqs) {
    return soundSeqs.map((v) => {
        return v.map((v) => [v.toString(), v.name]);
    });
}
exports.getLetterSoundPairsSyllabic = getLetterSoundPairsSyllabic;
/** Analyze an input into syllabic letter-sound pairs. */
function analyzeIntoSyllables(input) {
    if (!input)
        return [];
    const cli = new client_1.Client();
    const tla = analyzer_1.tonalLemmatizationAnalyzer;
    const ta = cli.processTonal(input);
    const wrd = ta.word;
    const pairs = getLetterSoundPairsSyllabic(tla
        .morphAnalyze(wrd.literal, new metaplasm_1.TonalStandaloneForms([]))
        .map((x) => x.sounds));
    return pairs;
}
exports.analyzeIntoSyllables = analyzeIntoSyllables;
/** Analyze an input into a sequence of letter-sound-pairs. */
function analyzeIntoSequence(input) {
    if (!input)
        return [];
    const cli = new client_1.Client();
    const tla = analyzer_1.tonalLemmatizationAnalyzer;
    const ta = cli.processTonal(input);
    const wrd = ta.word;
    const pairs = getLetterSoundPairsSequential(tla
        .morphAnalyze(wrd.literal, new metaplasm_1.TonalStandaloneForms([]))
        .map((x) => x.sounds));
    return pairs;
}
exports.analyzeIntoSequence = analyzeIntoSequence;
/** Get the standalone forms of a syllable. */
function getStandaloneForms(syl) {
    if (!syl)
        return [];
    const cli = new client_1.Client();
    const tla = analyzer_1.tonalLemmatizationAnalyzer;
    const ta = cli.processTonal(syl);
    const wrd = ta.word;
    return tla
        .morphAnalyze(wrd.literal, new metaplasm_1.TonalStandaloneForms([]))
        .flatMap((mrfm) => mrfm.getForms().map((frm) => frm.literal));
}
exports.getStandaloneForms = getStandaloneForms;
/** Get lemmas of the word. */
function getLemmas(input) {
    if (!input)
        return [];
    const lxLemma = (0, lemmatizer_1.lemmatize)(input);
    return lxLemma.getLemmas().map((x) => x.literal);
}
exports.getLemmas = getLemmas;
/** Join the letters in each tuple. */
function pairsToString(pairs) {
    const chars = pairs.map((pair) => {
        return pair[0];
    });
    const syl = chars.join('');
    return syl;
}
exports.pairsToString = pairsToString;
/** Get the stem of a word. */
function getStem(input) {
    const lxLemma = (0, lemmatizer_1.lemmatize)(input);
    const literal = lxLemma.word.literal;
    const ending = lxLemma.getInflectionalEnding();
    if (literal.length - ending.length != 0) {
        return literal.substring(0, literal.length - ending.length);
    }
    return '';
}
exports.getStem = getStem;
/** Get the inflectional suffix of a word. */
function getDesinence(input) {
    const lxLemma = (0, lemmatizer_1.lemmatize)(input);
    return lxLemma.getInflectionalEnding();
}
exports.getDesinence = getDesinence;
/** Get the syllables whose substring is matched. */
function getSyllablesInclude(input) {
    const syls = [];
    syllablelists_1.basicSyllables.forEach((it) => {
        if (it.includes(input)) {
            syls.push(it);
        }
    });
    syllablelists_1.missingSyllables.forEach((it) => {
        if (it.includes(input)) {
            syls.push(it);
        }
    });
    syllablelists_1.syllabicLoanwords.forEach((it) => {
        if (it.includes(input)) {
            syls.push(it);
        }
    });
    return syls;
}
exports.getSyllablesInclude = getSyllablesInclude;
/** Get the syllables that matched from the beginning. */
function getSyllablesStart(input) {
    const syls = [];
    syllablelists_1.basicSyllables.forEach((it) => {
        if (it.startsWith(input, 0)) {
            syls.push(it);
        }
    });
    syllablelists_1.missingSyllables.forEach((it) => {
        if (it.startsWith(input, 0)) {
            syls.push(it);
        }
    });
    syllablelists_1.syllabicLoanwords.forEach((it) => {
        if (it.startsWith(input, 0)) {
            syls.push(it);
        }
    });
    return syls;
}
exports.getSyllablesStart = getSyllablesStart;
/** Get the syllables that matched to the end. */
function getSyllablesEnd(input) {
    const syls = [];
    syllablelists_1.basicSyllables.forEach((it) => {
        if (it.endsWith(input, it.length)) {
            syls.push(it);
        }
    });
    syllablelists_1.missingSyllables.forEach((it) => {
        if (it.endsWith(input, it.length)) {
            syls.push(it);
        }
    });
    syllablelists_1.syllabicLoanwords.forEach((it) => {
        if (it.endsWith(input, it.length)) {
            syls.push(it);
        }
    });
    return syls;
}
exports.getSyllablesEnd = getSyllablesEnd;
//# sourceMappingURL=util.js.map