echogarden/dist/utilities/WikipediaReader.js

An easy-to-use speech toolset. Includes tools for synthesis, recognition, alignment, speech translation, language detection, source separation and more.

import { splitToParagraphs, wordCharacterRegExp } from '../nlp/Segmentation.js';
import { Logger } from './Logger.js';
export async function parseWikipediaArticle(articleName, language) {
    const logger = new Logger();
    await logger.startAsync('Fetching Wikipedia article');
    const { default: wtf } = await import('wtf_wikipedia');
    const document = await wtf.fetch(articleName, language);
    if (!document) {
        throw new Error('Error fetching Wikipedia article');
    }
    const sections = document.sections();
    const sectionsText = [];
    for (const section of sections) {
        const sectionTitle = section.title();
        if (wordCharacterRegExp.test(sectionTitle)) {
            sectionsText.push(sectionTitle);
        }
        const sectionParagraphs = splitToParagraphs(section.text(), 'single', 'preserve');
        for (const paragraph of sectionParagraphs) {
            const paragraphText = paragraph;
            if (wordCharacterRegExp.test(paragraphText)) {
                sectionsText.push(paragraphText);
            }
        }
    }
    logger.end();
    return sectionsText;
}
//# sourceMappingURL=WikipediaReader.js.map