@nitpicker/crawler 0.6.3 → 0.7.0

package/lib/qzilla.js

@@ -1,292 +0,0 @@
-import Archive from './archive/archive.js';
-import { cleanObject, EventEmitter, parseUrl, sortUrl } from './utils/index.js';
-import pkg from '../package.json' with { type: 'json' };
-import { Crawler } from './crawler/index.js';
-import { crawlerLog, log } from './debug.js';
-/**
- * Default list of external URL prefixes excluded from crawling.
- * Includes social media sharing endpoints that are commonly linked
- * but provide no useful crawl data.
- */
-export const DEFAULT_EXCLUDED_EXTERNAL_URLS = [
-    'https://social-plugins.line.me',
-    'https://access.line.me',
-    'https://lineit.line.me',
-    'https://line.me',
-    'https://plus.google.com',
-    'https://twitter.com',
-    'https://x.com',
-    'https://www.facebook.com/share.php',
-    'https://www.facebook.com/share/',
-    'https://www.facebook.com/sharer/',
-    'https://www.facebook.com/share_channel/',
-    'https://www.google.com',
-];
-/**
- * The main entry point for Qzilla web crawling and archiving.
- *
- * Qzilla orchestrates the full lifecycle of a crawl session: it creates an archive,
- * configures a {@link Crawler}, processes discovered pages and resources, and
- * writes the final archive file. It emits events defined by {@link QzillaEvent}.
- *
- * Instances are created via the static factory methods {@link Qzilla.crawling}
- * or {@link Qzilla.resume}; the constructor is private.
- * @example
- * ```ts
- * const qzilla = await Qzilla.crawling(['https://example.com'], { recursive: true });
- * await qzilla.write();
- * ```
- */
-export class Qzilla extends EventEmitter {
-    #archive;
-    #crawler;
-    #fromList;
-    /**
-     * The underlying archive instance used for storing crawl results.
-     */
-    get archive() {
-        return this.#archive;
-    }
-    // eslint-disable-next-line no-restricted-syntax
-    constructor(archive, options) {
-        super();
-        this.#fromList = !!options?.list;
-        this.#archive = archive;
-        this.#archive.on('error', (e) => {
-            this.#crawler.abort();
-            throw e;
-        });
-        this.#crawler = new Crawler({
-            interval: options?.interval || 0,
-            parallels: options?.parallels || 0,
-            isGettingImages: options?.image,
-            executablePath: options?.executablePath || null,
-            fetchExternal: options?.fetchExternal ?? true,
-            recursive: options?.recursive ?? true,
-            scope: options?.scope ?? [],
-            excludes: optMultiParam(options?.excludes),
-            excludeKeywords: optMultiParam(options?.excludeKeywords),
-            excludeUrls: [
-                ...DEFAULT_EXCLUDED_EXTERNAL_URLS,
-                ...optMultiParam(options?.excludeUrls),
-            ],
-            depthOnAvoid: options?.depthOnAvoid || 10,
-            disableQueries: options?.disableQueries,
-            screenshot: Archive.joinPath(archive.tmpDir, 'screenshots'),
-            verbose: options?.verbose ?? false,
-        });
-    }
-    /**
-     * Abort the current crawl and archive operations.
-     *
-     * Delegates to the archive's abort method, which stops all in-progress
-     * database writes and cleans up temporary resources.
-     * @returns The result of the archive abort operation.
-     */
-    abort() {
-        return this.#archive.abort();
-    }
-    /**
-     * Execute the crawl for the given list of URLs.
-     *
-     * Sets up event listeners on the crawler, starts crawling, and resolves
-     * when the crawl completes. Discovered pages, external pages, skipped pages,
-     * and resources are forwarded to the archive for storage.
-     * @param list - The list of parsed URLs to crawl. The first URL is used as the root.
-     * @returns A promise that resolves when crawling is complete.
-     * @throws {Error} If the URL list is empty.
-     */
-    async crawling(list) {
-        const root = list[0];
-        if (!root) {
-            throw new Error('URL is empty');
-        }
-        return new Promise((resolve, reject) => {
-            this.#crawler.on('error', (error) => {
-                crawlerLog('On error: %O', error);
-                void this.#archive.addError(error);
-                void this.emit('error', error);
-            });
-            this.#crawler.on('page', async ({ result }) => {
-                // const pageId =
-                await this.#archive.setPage(result).catch((error) => reject(error));
-                // await this.#crawler.screenshot(pageId, Archive.joinPath(this.#archive.tmpDir, 'screenshots'));
-            });
-            this.#crawler.on('externalPage', ({ result }) => {
-                this.#archive.setExternalPage(result).catch((error) => reject(error));
-            });
-            this.#crawler.on('skip', ({ url, reason, isExternal }) => {
-                this.#archive
-                    .setSkippedPage(url, reason, isExternal)
-                    .catch((error) => reject(error));
-            });
-            this.#crawler.on('response', ({ resource }) => {
-                this.#archive.setResources(resource).catch((error) => reject(error));
-            });
-            this.#crawler.on('responseReferrers', (resource) => {
-                this.#archive.setResourcesReferrers(resource).catch((error) => reject(error));
-            });
-            this.#crawler.on('crawlEnd', () => {
-                resolve();
-            });
-            if (this.#fromList) {
-                this.#crawler.startMultiple(list);
-            }
-            else {
-                this.#crawler.start(root);
-            }
-        });
-    }
-    /**
-     * Kill any zombie Chromium processes that were not properly cleaned up.
-     *
-     * Retrieves the list of undead process IDs from the crawler and sends
-     * a SIGTERM signal to each one. Chromium is intentionally sent SIGTERM
-     * (not SIGKILL) to avoid leaving zombie processes.
-     */
-    garbageCollect() {
-        const pidList = this.getUndeadPid();
-        log('Undead PIDs: %O', pidList);
-        for (const pid of pidList) {
-            try {
-                log('Garbage collect: kill PID:%d', pid);
-                // Chromium becomes a zombie process if SIGKILL signal.
-                process.kill(pid);
-            }
-            catch (error) {
-                log('Garbage collect: Failed killing PID:%d %O', pid, error);
-            }
-        }
-    }
-    /**
-     * Retrieve the list of process IDs for Chromium instances that are
-     * still running after crawling has ended.
-     * @returns An array of process IDs that should be terminated.
-     */
-    getUndeadPid() {
-        return this.#crawler.getUndeadPid();
-    }
-    /**
-     * Write the archive to its configured file path.
-     *
-     * Emits `writeFileStart` before writing and `writeFileEnd` after
-     * the write completes successfully.
-     */
-    async write() {
-        void this.emit('writeFileStart', { filePath: this.#archive.filePath });
-        await this.#archive.write();
-        void this.emit('writeFileEnd', { filePath: this.#archive.filePath });
-    }
-    /**
-     * Create a new Qzilla instance and start crawling the given URLs.
-     *
-     * This is the primary factory method for starting a fresh crawl. It:
-     * 1. Parses and sorts the input URLs
-     * 2. Creates an archive file
-     * 3. Saves the crawl configuration
-     * 4. Runs the optional initialized callback
-     * 5. Executes the crawl
-     * 6. Sorts the archived URLs in natural order
-     * @param url - One or more URL strings to crawl.
-     * @param options - Optional configuration overrides for the crawl session.
-     * @param initializedCallback - Optional callback invoked after initialization but before crawling starts.
-     * @returns A promise that resolves to the Qzilla instance after crawling completes.
-     * @throws {Error} If the URL list is empty or contains no valid URLs.
-     */
-    static async crawling(url, options, initializedCallback) {
-        const list = sortUrl(url, options);
-        const urlParsed = list[0];
-        if (!urlParsed) {
-            throw new Error('URL is empty');
-        }
-        const fileName = `${urlParsed.hostname}-${Archive.timestamp()}`;
-        const cwd = options?.cwd ?? process.cwd();
-        const filePath = Archive.joinPath(cwd, `${fileName}.${Archive.FILE_EXTENSION}`);
-        const disableQueries = options?.disableQueries || false;
-        const archive = await Archive.create({ filePath, cwd, disableQueries });
-        await archive.setConfig({
-            version: pkg.version,
-            name: fileName,
-            baseUrl: urlParsed.withoutHash,
-            recursive: options?.recursive ?? true,
-            fetchExternal: options?.fetchExternal ?? true,
-            image: options?.image ?? true,
-            interval: options?.interval || 0,
-            parallels: options?.parallels || 0,
-            scope: options?.scope ?? [],
-            // @ts-ignore TODO: Fix CLI arguments
-            excludes: optMultiParam(options?.exclude),
-            // @ts-ignore TODO: Fix CLI arguments
-            excludeKeywords: optMultiParam(options?.excludeKeyword),
-            excludeUrls: [
-                ...DEFAULT_EXCLUDED_EXTERNAL_URLS,
-                // @ts-ignore TODO: Fix CLI arguments
-                ...optMultiParam(options?.excludeUrl),
-            ],
-            depthOnAvoid: options?.depthOnAvoid || 10,
-            fromList: !!options?.list,
-            disableQueries,
-        });
-        const qzilla = new Qzilla(archive, options);
-        const config = await archive.getConfig();
-        if (initializedCallback) {
-            await initializedCallback(qzilla, config);
-        }
-        log('Start crawling');
-        log('URL %O', list.map((url) => url.href));
-        log('Config %O', config);
-        await qzilla.crawling(list);
-        log('Crawling complated');
-        log('Set order natural URL sort');
-        await archive.setUrlOrder();
-        log('Sorting done');
-        return qzilla;
-    }
-    /**
-     * Resume a previously interrupted crawl from an existing archive file.
-     *
-     * Restores the crawl state (pending URLs, scraped URLs, and resources)
-     * from the archive, merges any option overrides, and continues crawling
-     * from where it left off.
-     * @param stubPath - Path to the existing archive file to resume from.
-     * @param options - Optional configuration overrides to apply on top of the archived config.
-     * @param initializedCallback - Optional callback invoked after initialization but before crawling resumes.
-     * @returns A promise that resolves to the Qzilla instance after crawling completes.
-     * @throws {Error} If the archived URL is invalid.
-     */
-    static async resume(stubPath, options, initializedCallback) {
-        const archive = await Archive.resume(stubPath);
-        const archivedConfig = await archive.getConfig();
-        const config = {
-            ...archivedConfig,
-            ...cleanObject(options),
-        };
-        const qzilla = new Qzilla(archive, config);
-        const _url = await archive.getUrl();
-        const url = parseUrl(_url, config);
-        if (!url) {
-            throw new Error(`URL (${_url}) is invalid`);
-        }
-        const { scraped, pending } = await archive.getCrawlingState();
-        const resources = await archive.getResourceUrlList();
-        qzilla.#crawler.resume(pending, scraped, resources);
-        if (initializedCallback) {
-            await initializedCallback(qzilla, config);
-        }
-        log('Start resuming');
-        log('Data %s', stubPath);
-        log('URL %s', url.href);
-        log('Config %O', config);
-        await qzilla.crawling([url]);
-        return qzilla;
-    }
-}
-/**
- * Normalize an optional parameter that may be a single value, an array,
- * null, or undefined into a guaranteed array.
- * @param param - The parameter to normalize.
- * @returns An array containing the parameter value(s), or an empty array if absent.
- */
-function optMultiParam(param) {
-    return Array.isArray(param) ? param : param ? [param] : [];
-}

package/lib/utils/array/index.d.ts

@@ -1 +0,0 @@
-export { eachSplitted } from './each-splitted.js';

package/lib/utils/array/index.js

@@ -1 +0,0 @@
-export { eachSplitted } from './each-splitted.js';

package/lib/utils/async/index.d.ts

@@ -1 +0,0 @@
-export { delay } from '@d-zero/shared/delay';

package/lib/utils/async/index.js

@@ -1 +0,0 @@
-export { delay } from '@d-zero/shared/delay';

package/lib/utils/error/index.d.ts

@@ -1,3 +0,0 @@
-export { DOMEvaluationError } from './dom-evaluation-error.js';
-export { ErrorEmitter } from './error-emitter.js';
-export type { ErrorEvent } from './error-emitter.js';

package/lib/utils/error/index.js

@@ -1,2 +0,0 @@
-export { DOMEvaluationError } from './dom-evaluation-error.js';
-export { ErrorEmitter } from './error-emitter.js';

package/lib/utils/event-emitter/index.d.ts

@@ -1,6 +0,0 @@
-/**
- * A typed, async-capable event emitter re-exported from `@d-zero/shared`.
- * Provides type-safe `emit`, `on`, and `off` methods where event names
- * and their payload types are enforced at compile time.
- */
-export { TypedAwaitEventEmitter as EventEmitter } from '@d-zero/shared/typed-await-event-emitter';

package/lib/utils/event-emitter/index.js

@@ -1,6 +0,0 @@
-/**
- * A typed, async-capable event emitter re-exported from `@d-zero/shared`.
- * Provides type-safe `emit`, `on`, and `off` methods where event names
- * and their payload types are enforced at compile time.
- */
-export { TypedAwaitEventEmitter as EventEmitter } from '@d-zero/shared/typed-await-event-emitter';

package/lib/utils/index.d.ts

@@ -1,5 +0,0 @@
-export * from './types/index.js';
-export * from './array/index.js';
-export * from './error/index.js';
-export * from './object/index.js';
-export { globalLog as log } from './debug.js';

package/lib/utils/index.js

@@ -1,5 +0,0 @@
-export * from './types/index.js';
-export * from './array/index.js';
-export * from './error/index.js';
-export * from './object/index.js';
-export { globalLog as log } from './debug.js';

package/lib/utils/network/index.d.ts

@@ -1 +0,0 @@
-export { isError } from '@nitpicker/beholder';

package/lib/utils/network/index.js

@@ -1 +0,0 @@
-export { isError } from '@nitpicker/beholder';

package/lib/utils/object/index.d.ts

@@ -1 +0,0 @@
-export * from './clean-object.js';

package/lib/utils/object/index.js

@@ -1 +0,0 @@
-export * from './clean-object.js';

package/lib/utils/path/index.d.ts

@@ -1 +0,0 @@
-export { safeFilePath } from '@d-zero/shared/safe-filepath';

package/lib/utils/path/index.js

@@ -1 +0,0 @@
-export { safeFilePath } from '@d-zero/shared/safe-filepath';

package/lib/utils/path/safe-filepath.d.ts

@@ -1,7 +0,0 @@
-/**
- * Sanitizes a file path by decoding URI-encoded characters and replacing
- * any characters that are unsafe for use in filenames with underscores.
- * @param filePath - The raw file path string (possibly URI-encoded) to sanitize.
- * @returns A sanitized file path string that is safe for use as a filename.
- */
-export declare function safeFilePath(filePath: string): string;

package/lib/utils/path/safe-filepath.js

@@ -1,12 +0,0 @@
-import sanitize from 'sanitize-filename';
-/**
- * Sanitizes a file path by decoding URI-encoded characters and replacing
- * any characters that are unsafe for use in filenames with underscores.
- * @param filePath - The raw file path string (possibly URI-encoded) to sanitize.
- * @returns A sanitized file path string that is safe for use as a filename.
- */
-export function safeFilePath(filePath) {
-    return sanitize(decodeURI(filePath), {
-        replacement: '_',
-    });
-}

package/lib/utils/regexp/index.d.ts

@@ -1 +0,0 @@
-export { strToRegex } from '@d-zero/shared/str-to-regex';

package/lib/utils/regexp/index.js

@@ -1 +0,0 @@
-export { strToRegex } from '@d-zero/shared/str-to-regex';

package/lib/utils/retryable/index.d.ts

@@ -1,2 +0,0 @@
-export { retry as retryable } from '@d-zero/shared/retry';
-export type { RetryDecoratorOptions as RetryableDecoratorOptions } from '@d-zero/shared/retry';

package/lib/utils/retryable/index.js

@@ -1 +0,0 @@
-export { retry as retryable } from '@d-zero/shared/retry';

package/lib/utils/sort/index.d.ts

@@ -1,14 +0,0 @@
-import type { ExURL, ParseURLOptions } from '@d-zero/shared/parse-url';
-/**
- * Compares two URLs using a natural sorting algorithm. The comparison order is:
- * hostname, path directories, basename (with index files prioritized), file extension,
- * query string, hash, protocol, and finally the original URL string as a tiebreaker.
- * Numeric segments within path components are compared numerically rather than
- * lexicographically.
- * @param url1 - The first URL string or ExURL to compare.
- * @param url2 - The second URL string or ExURL to compare.
- * @param options - Optional URL parsing options.
- * @returns `0` if the URLs are equal, `-1` if url1 should come before url2,
- *          or `1` if url1 should come after url2.
- */
-export declare function naturalURLSort(url1: string | ExURL, url2: string | ExURL, options?: ParseURLOptions): 0 | -1 | 1;

package/lib/utils/sort/index.js

@@ -1,61 +0,0 @@
-import { alphabeticalComparator } from '@d-zero/shared/sort/alphabetical';
-import { dirComparator } from '@d-zero/shared/sort/dir';
-import { numericalComparator } from '@d-zero/shared/sort/numerical';
-import { parseUrl } from '../url/index.js';
-/**
- * Compares two URLs using a natural sorting algorithm. The comparison order is:
- * hostname, path directories, basename (with index files prioritized), file extension,
- * query string, hash, protocol, and finally the original URL string as a tiebreaker.
- * Numeric segments within path components are compared numerically rather than
- * lexicographically.
- * @param url1 - The first URL string or ExURL to compare.
- * @param url2 - The second URL string or ExURL to compare.
- * @param options - Optional URL parsing options.
- * @returns `0` if the URLs are equal, `-1` if url1 should come before url2,
- *          or `1` if url1 should come after url2.
- */
-export function naturalURLSort(url1, url2, options) {
-    const u1 = typeof url1 === 'string' ? parseUrl(url1, options) : url1;
-    const u2 = typeof url2 === 'string' ? parseUrl(url2, options) : url2;
-    if (!u1 || !u2) {
-        return 0;
-    }
-    if (u1.href === u2.href) {
-        return alphabeticalComparator(u1._originUrlString, u2._originUrlString);
-    }
-    const rHost = alphabeticalComparator(u1.hostname, u2.hostname);
-    if (rHost) {
-        return rHost;
-    }
-    const rPaths = dirComparator(u1.paths, u2.paths);
-    if (rPaths) {
-        return rPaths;
-    }
-    if (u1.basename !== u2.basename) {
-        if (u1.isIndex)
-            return -1;
-        if (u2.isIndex)
-            return 1;
-        const rBasename = numericalComparator(u1.basename, u2.basename);
-        if (rBasename) {
-            return rBasename;
-        }
-    }
-    const rExtname = numericalComparator(u1.extname, u2.extname);
-    if (rExtname) {
-        return rExtname;
-    }
-    const rSearch = numericalComparator(u1.query, u2.query);
-    if (rSearch) {
-        return rSearch;
-    }
-    const rHash = numericalComparator(u1.hash, u2.hash);
-    if (rHash) {
-        return rHash;
-    }
-    const rProtocol = alphabeticalComparator(u1.protocol, u2.protocol);
-    if (rProtocol) {
-        return rProtocol;
-    }
-    return numericalComparator(u1._originUrlString, u2._originUrlString);
-}

package/lib/utils/sort/remove-matches.d.ts

@@ -1,9 +0,0 @@
-/**
- * Strips the common leading prefix from two strings (case-insensitive comparison).
- * Returns a tuple of the remaining suffixes after the shared prefix is removed.
- * If the strings are identical (ignoring case), returns `['', '']`.
- * @param t1 - The first string.
- * @param t2 - The second string.
- * @returns A tuple of the two strings with their common leading characters removed.
- */
-export declare function removeMatches(t1: string, t2: string): [string, string];

package/lib/utils/sort/remove-matches.js

@@ -1,23 +0,0 @@
-/**
- * Strips the common leading prefix from two strings (case-insensitive comparison).
- * Returns a tuple of the remaining suffixes after the shared prefix is removed.
- * If the strings are identical (ignoring case), returns `['', '']`.
- * @param t1 - The first string.
- * @param t2 - The second string.
- * @returns A tuple of the two strings with their common leading characters removed.
- */
-export function removeMatches(t1, t2) {
-    let loopCount = Math.max(t1.length, t2.length);
-    t1 = t1.toLowerCase();
-    t2 = t2.toLowerCase();
-    const a1 = [...t1];
-    const a2 = [...t2];
-    while (loopCount--) {
-        if (a1[0] !== a2[0]) {
-            return [a1.join(''), a2.join('')];
-        }
-        a1.shift();
-        a2.shift();
-    }
-    return ['', ''];
-}

package/lib/utils/types/index.d.ts

@@ -1 +0,0 @@
-export * from './types.js';

package/lib/utils/types/index.js

@@ -1 +0,0 @@
-export * from './types.js';

package/lib/utils/url/index.d.ts

@@ -1,5 +0,0 @@
-export { tryParseUrl as parseUrl } from '@d-zero/shared/parse-url';
-export { isLowerLayer } from '@d-zero/shared/is-lower-layer';
-export { pathMatch } from '@d-zero/shared/path-match';
-export { urlPartialMatch } from '@d-zero/shared/url-partial-match';
-export { sortUrl } from '@d-zero/shared/sort-url';

package/lib/utils/url/index.js

@@ -1,5 +0,0 @@
-export { tryParseUrl as parseUrl } from '@d-zero/shared/parse-url';
-export { isLowerLayer } from '@d-zero/shared/is-lower-layer';
-export { pathMatch } from '@d-zero/shared/path-match';
-export { urlPartialMatch } from '@d-zero/shared/url-partial-match';
-export { sortUrl } from '@d-zero/shared/sort-url';

package/lib/utils/url/is-lower-layer.d.ts

@@ -1,15 +0,0 @@
-import type { ExURL, ParseURLOptions } from '@d-zero/shared/parse-url';
-/**
- * Determines whether the target URL is at the same level or a deeper (lower) layer
- * in the path hierarchy relative to the base URL. Both URLs must share the same hostname.
- *
- * For example, if the base is `https://example.com/docs/`, then
- * `https://example.com/docs/getting-started` is considered a lower layer,
- * while `https://example.com/about` is not.
- * @param target - The target URL string or ExURL to check.
- * @param base - The base URL string or ExURL to compare against.
- * @param options - Optional URL parsing options.
- * @returns `true` if the target URL is at the same level or deeper than the base URL
- *          within the same hostname; `false` otherwise.
- */
-export declare function isLowerLayer(target: string | ExURL, base: string | ExURL, options?: ParseURLOptions): boolean;

package/lib/utils/url/is-lower-layer.js

@@ -1,55 +0,0 @@
-import { parseUrl } from './parse-url.js';
-/**
- * Determines whether the target URL is at the same level or a deeper (lower) layer
- * in the path hierarchy relative to the base URL. Both URLs must share the same hostname.
- *
- * For example, if the base is `https://example.com/docs/`, then
- * `https://example.com/docs/getting-started` is considered a lower layer,
- * while `https://example.com/about` is not.
- * @param target - The target URL string or ExURL to check.
- * @param base - The base URL string or ExURL to compare against.
- * @param options - Optional URL parsing options.
- * @returns `true` if the target URL is at the same level or deeper than the base URL
- *          within the same hostname; `false` otherwise.
- */
-export function isLowerLayer(target, base, options) {
-    const a = typeof target === 'string' ? parseUrl(target, options) : target;
-    const b = typeof base === 'string' ? parseUrl(base, options) : base;
-    if (!a || !b) {
-        return false;
-    }
-    if (a.href === b.href) {
-        return true;
-    }
-    const aPathIsEmpty = a.paths.length === 1 && a.paths[0] === '';
-    const bPathIsEmpty = b.paths.length === 1 && b.paths[0] === '';
-    if (a.hostname !== b.hostname) {
-        return false;
-    }
-    if (aPathIsEmpty && bPathIsEmpty) {
-        return true;
-    }
-    if (a.paths == null && b.paths == null) {
-        return true;
-    }
-    if (a.paths && b.paths == null) {
-        return true;
-    }
-    if (!a.paths || !b.paths) {
-        return false;
-    }
-    if (a.paths.length < b.paths.length) {
-        return false;
-    }
-    while (Math.max(a.paths.length, b.paths.length)) {
-        const i1 = a.paths.shift();
-        const i2 = b.paths.shift();
-        if (i1 && !i2) {
-            return true;
-        }
-        if (i1 !== i2) {
-            return false;
-        }
-    }
-    return false;
-}

package/lib/utils/url/parse-url.d.ts

@@ -1,11 +0,0 @@
-import type { ExURL, ParseURLOptions } from '@d-zero/shared/parse-url';
-/**
- * Parses a URL string into an ExURL object, filtering out non-HTTP URLs
- * that lack a hostname and protocol. If the input is already an ExURL object,
- * it is returned as-is without re-parsing.
- * @param url - The URL string to parse, or an already-parsed ExURL object.
- * @param options - Optional parsing options forwarded to the underlying parser.
- * @returns The parsed ExURL object, or `null` if the URL is not a valid HTTP URL
- *          and has no hostname or protocol.
- */
-export declare function parseUrl(url: string | ExURL, options?: ParseURLOptions): ExURL | null;

package/lib/utils/url/parse-url.js

@@ -1,20 +0,0 @@
-import { parseUrl as sharedParseUrl } from '@d-zero/shared/parse-url';
-/**
- * Parses a URL string into an ExURL object, filtering out non-HTTP URLs
- * that lack a hostname and protocol. If the input is already an ExURL object,
- * it is returned as-is without re-parsing.
- * @param url - The URL string to parse, or an already-parsed ExURL object.
- * @param options - Optional parsing options forwarded to the underlying parser.
- * @returns The parsed ExURL object, or `null` if the URL is not a valid HTTP URL
- *          and has no hostname or protocol.
- */
-export function parseUrl(url, options) {
-    if (typeof url !== 'string') {
-        return url;
-    }
-    const result = sharedParseUrl(url, options);
-    if (!result.isHTTP && !result.hostname && !result.protocol) {
-        return null;
-    }
-    return result;
-}

package/lib/utils/url/path-match.d.ts

@@ -1,11 +0,0 @@
-import type { ExURL, ParseURLOptions } from '@d-zero/shared/parse-url';
-/**
- * Tests whether the pathname portion of a URL matches a given glob pattern.
- * Uses micromatch for glob matching.
- * @param targetPath - The URL string or ExURL whose pathname will be tested.
- * @param pattern - The glob pattern to match against the pathname (e.g., `"/docs/**"`).
- * @param options - Optional URL parsing options.
- * @returns `true` if the URL's pathname matches the pattern; `false` otherwise
- *          (also returns `false` if the URL cannot be parsed).
- */
-export declare function pathMatch(targetPath: string | ExURL, pattern: string, options?: ParseURLOptions): boolean;