hunspell-reader/dist/IterableHunspellReaderLegacy.js

A library for reading Hunspell Dictionary Files

import * as fs from 'node:fs/promises';
import { genSequence } from 'gensequence';
import pkgIconvLite from 'iconv-lite';
import { parseAffFileToAffLegacy } from './affReader.js';
import { filterOrderedList } from './util.js';
const { decode } = pkgIconvLite;
// eslint-disable-next-line unicorn/text-encoding-identifier-case
const defaultEncoding = 'UTF-8';
export class IterableHunspellReaderLegacy {
    src;
    aff;
    constructor(src) {
        this.src = src;
        this.aff = src.aff;
    }
    get dic() {
        return this.src.dic;
    }
    set maxDepth(value) {
        this.aff.maxSuffixDepth = value;
    }
    get maxDepth() {
        return this.aff.maxSuffixDepth;
    }
    /** the number of .dic entries */
    get size() {
        return this.src.dic.length;
    }
    /**
     * @internal
     */
    dicWordsSeq() {
        return genSequence(this.src.dic).map((line) => {
            const [word, rules] = line.split('/', 2);
            return { word, rules, prefixes: [], suffixes: [] };
        });
    }
    /**
     * iterates through the root words of the dictionary
     */
    iterateRootWords() {
        return this.seqRootWords();
    }
    iterateWords() {
        return this.seqWords();
    }
    /**
     * Iterator for all the words in the dictionary. The words are in the order found in the .dic after the
     * transformations have been applied. Forbidden and CompoundOnly words are filtered out.
     */
    [Symbol.iterator]() {
        return this.wholeWords();
    }
    /**
     * create an iterable sequence of the words in the dictionary.
     *
     * @param tapPreApplyRules -- optional function to be called before rules are applied to a word.
     *                            It is mostly used for monitoring progress in combination with `size`.
     */
    seqAffWords(tapPreApplyRules, maxDepth) {
        return this.seqTransformDictionaryEntries(tapPreApplyRules, maxDepth).concatMap((a) => a);
    }
    /**
     * create an iterable sequence of the words in the dictionary.
     *
     * @param tapPreApplyRules -- optional function to be called before rules are applied to a word.
     *                            It is mostly used for monitoring progress in combination with `size`.
     */
    seqTransformDictionaryEntries(tapPreApplyRules, maxDepth) {
        const seq = genSequence(this.src.dic);
        let count = 0;
        const dicWords = tapPreApplyRules ? seq.map((a) => (tapPreApplyRules(a, count++), a)) : seq;
        return dicWords.map((dicWord) => this.aff.applyRulesToDicEntry(dicWord, maxDepth));
    }
    /**
     * Iterator for all the words in the dictionary. The words are in the order found in the .dic after the
     * transformations have been applied. Forbidden and CompoundOnly ARE INCLUDED.
     *
     * @internal
     */
    seqWords() {
        return this.seqAffWords()
            .map((w) => w.word)
            .filter(createMatchingWordsFilter());
    }
    /**
     * Returns an iterable that will only return stand alone words.
     */
    wholeWords() {
        return (this.seqAffWords()
            // Filter out words that are forbidden or only allowed in Compounds.
            .filter((w) => !w.flags.isForbiddenWord && !w.flags.isOnlyAllowedInCompound)
            .map((w) => w.word)
            .filter(createMatchingWordsFilter()));
    }
    /**
     * @internal
     */
    seqRootWords() {
        return this.dicWordsSeq().map((w) => w.word);
    }
    /**
     *
     * @param affFile - path to aff file.
     * @param dicFile - path to dic file.
     * @returns IterableHunspellReader
     */
    static async createFromFiles(affFile, dicFile) {
        const aff = await parseAffFileToAffLegacy(affFile, defaultEncoding);
        const buffer = await fs.readFile(dicFile);
        const dicFileContent = decode(buffer, aff.affInfo.SET);
        const dic = dicFileContent
            .split('\n')
            .slice(1) // The first entry is the count of entries.
            .map((a) => a.trim())
            .filter((line) => !!line);
        return new IterableHunspellReaderLegacy({ aff, dic });
    }
}
export function createMatchingWordsFilter() {
    return filterOrderedList((a, b) => a !== b);
}
//# sourceMappingURL=IterableHunspellReaderLegacy.js.map