@llml-browser/types/dist/chunk-XGNDRAIX.mjs

TypeScript types and schemas for the @llml-browser API

import {
  HTMLCleaningOptionsSchema
} from "./chunk-54IS4CR5.mjs";
import {
  LinkExtractionOptionsSchema
} from "./chunk-LAH43RYU.mjs";
import {
  MetadataOptionsSchema
} from "./chunk-5RX3GYMK.mjs";
import {
  __export
} from "./chunk-J5LGTIGS.mjs";

// src/routers/links/types.ts
var types_exports = {};
__export(types_exports, {
  contentOptionsSchema: () => contentOptionsSchema,
  linksOptionsSchema: () => linksOptionsSchema,
  treeOptionsSchema: () => treeOptionsSchema
});
import { z } from "zod";
var contentOptionsSchema = z.object({
  /**
   * Options for metadata extraction.
   * Controls how metadata like title, description, etc. are extracted.
   */
  metadataOptions: MetadataOptionsSchema.optional(),
  /**
   * Options for link extraction.
   * Controls how links are extracted and categorized.
   */
  linksOptions: LinkExtractionOptionsSchema.optional(),
  /**
   * Options for HTML cleaning.
   * Controls how HTML is sanitized and cleaned.
   */
  cleanedHtmlOptions: HTMLCleaningOptionsSchema.optional()
});
var treeOptionsSchema = z.object({
  /**
   * Whether to place folders before leaf nodes in the tree.
   * Default: true
   */
  folderFirst: z.preprocess(
    (val) => val !== "false" && val !== false,
    z.boolean().optional()
  ),
  /**
   * How to order links within each folder:
   *  - 'page'        preserve the original document order
   *  - 'alphabetical'  sort A→Z by URL
   * Default: 'page'
   */
  linksOrder: z.enum(["page", "alphabetical"]).optional(),
  /**
   * Whether to include extracted links for each node in the tree.
   * Default: true
   */
  extractedLinks: z.preprocess(
    (val) => val !== "false" && val !== false,
    z.boolean().optional()
  ),
  /**
   * Whether to exclude subdomain as root URL.
   * Default: true
   * e.g., if false: rootUrl: https://swr.vercel.app -> https://vercel.app
   */
  subdomainAsRootUrl: z.preprocess(
    (val) => val !== "false" && val !== false,
    z.boolean().optional()
  )
});
var linksOptionsSchema = z.object({
  /**
   * The URL to scrape.
   * Must be a valid URL string.
   */
  url: z.string(),
  /**
   * Whether to build a site map tree.
   * Default: true
   */
  // default true if not set
  tree: z.preprocess(
    (val) => val !== "false" && val !== false,
    z.boolean().optional()
  ),
  /**
   * Whether to extract metadata from the page.
   * Default: true
   */
  // default true if not set
  metadata: z.preprocess(
    (val) => val !== "false" && val !== false,
    z.boolean().optional()
  ),
  /**
   * Whether to return cleaned HTML.
   * Default: false
   */
  cleanedHtml: z.preprocess(
    (val) => val === "true" || val === true,
    z.boolean().optional()
  ),
  /**
   * Whether to fetch and parse robots.txt.
   * Default: false
   */
  robots: z.preprocess(
    (val) => val === "true" || val === true,
    z.boolean().optional()
  ),
  /**
   * Whether to fetch and parse sitemap.xml.
   * Default: false
   */
  sitemapXML: z.preprocess(
    (val) => val === "true" || val === true,
    z.boolean().optional()
  ),
  ...treeOptionsSchema.shape,
  ...contentOptionsSchema.shape
});

export {
  contentOptionsSchema,
  treeOptionsSchema,
  linksOptionsSchema,
  types_exports
};
//# sourceMappingURL=chunk-XGNDRAIX.mjs.map