@signalwire/docusaurus-plugin-llms-txt/lib/transformation/title-extractor.js

Generate Markdown versions of Docusaurus HTML pages and an llms.txt index file

/**
 * Title extraction strategies
 * Multiple strategies for extracting document titles from HTML
 */
import { DEFAULT_DOCUMENT_TITLE, HTML_SELECTORS } from '../constants';
import { selectText } from '../utils/html';
/**
 * Extract title from first h1 element found anywhere on the page
 * @internal
 */
const extractFirstH1 = (tree) => {
    const firstH1 = selectText(tree, HTML_SELECTORS.H1);
    return firstH1 || null;
};
/**
 * Extract title from document title tag
 * @internal
 */
const extractDocumentTitle = (tree) => {
    const fullTitle = selectText(tree, HTML_SELECTORS.TITLE);
    if (fullTitle) {
        const parts = fullTitle.split('|');
        if (parts.length > 1 && parts[0]) {
            return parts[0].trim();
        }
        return fullTitle.trim();
    }
    return null;
};
/**
 * Default title extractor strategy chain
 * @internal
 */
const defaultTitleExtractors = [extractFirstH1, extractDocumentTitle];
/**
 * Extract title using a strategy chain approach
 * @internal
 */
export function extractTitle(tree, extractors = defaultTitleExtractors) {
    for (const extractor of extractors) {
        const title = extractor(tree);
        if (title) {
            return title;
        }
    }
    return DEFAULT_DOCUMENT_TITLE;
}