@llml-browser/types/dist/routers/read.js

TypeScript types and schemas for the @llml-browser API

"use strict";
var __create = Object.create;
var __defProp = Object.defineProperty;
var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
var __getOwnPropNames = Object.getOwnPropertyNames;
var __getProtoOf = Object.getPrototypeOf;
var __hasOwnProp = Object.prototype.hasOwnProperty;
var __export = (target, all) => {
  for (var name in all)
    __defProp(target, name, { get: all[name], enumerable: true });
};
var __copyProps = (to, from, except, desc) => {
  if (from && typeof from === "object" || typeof from === "function") {
    for (let key of __getOwnPropNames(from))
      if (!__hasOwnProp.call(to, key) && key !== except)
        __defProp(to, key, { get: () => from[key], enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable });
  }
  return to;
};
var __toESM = (mod, isNodeMode, target) => (target = mod != null ? __create(__getProtoOf(mod)) : {}, __copyProps(
  // If the importer is in node compatibility mode or this is not an ESM
  // file that has been converted to a CommonJS file using a Babel-
  // compatible transform (i.e. "__esModule" has not been set), then set
  // "default" to the CommonJS "module.exports" for node compatibility.
  isNodeMode || !mod || !mod.__esModule ? __defProp(target, "default", { value: mod, enumerable: true }) : target,
  mod
));
var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: true }), mod);

// src/routers/read/index.ts
var read_exports = {};
__export(read_exports, {
  readOptionsSchema: () => readOptionsSchema
});
module.exports = __toCommonJS(read_exports);

// src/services/metadata/types.ts
var import_zod = require("zod");
var MetadataOptionsSchema = import_zod.z.object({
  title: import_zod.z.boolean().optional().default(true),
  description: import_zod.z.boolean().optional().default(true),
  language: import_zod.z.boolean().optional().default(true),
  canonical: import_zod.z.boolean().optional().default(true),
  robots: import_zod.z.boolean().optional().default(true),
  author: import_zod.z.boolean().optional().default(true),
  keywords: import_zod.z.boolean().optional().default(true),
  favicon: import_zod.z.boolean().optional().default(true),
  openGraph: import_zod.z.boolean().optional().default(true),
  twitter: import_zod.z.boolean().optional().default(true),
  isIframeAllowed: import_zod.z.boolean().optional().default(true)
});
var PageMetadataSchema = import_zod.z.object({
  // Basic metadata
  title: import_zod.z.string().optional(),
  description: import_zod.z.string().optional(),
  language: import_zod.z.string().optional(),
  canonical: import_zod.z.string().url().optional(),
  robots: import_zod.z.string().optional(),
  author: import_zod.z.string().optional(),
  keywords: import_zod.z.array(import_zod.z.string()).optional(),
  lastModified: import_zod.z.string().optional().nullable(),
  favicon: import_zod.z.string().url().optional(),
  // OpenGraph metadata (flattened)
  ogTitle: import_zod.z.string().optional(),
  ogDescription: import_zod.z.string().optional(),
  ogImage: import_zod.z.string().url().optional(),
  ogUrl: import_zod.z.string().url().optional(),
  ogType: import_zod.z.string().optional(),
  ogSiteName: import_zod.z.string().optional(),
  // Twitter Card metadata (flattened)
  twitterCard: import_zod.z.string().optional(),
  twitterSite: import_zod.z.string().optional(),
  twitterCreator: import_zod.z.string().optional(),
  twitterTitle: import_zod.z.string().optional(),
  twitterDescription: import_zod.z.string().optional(),
  twitterImage: import_zod.z.string().url().optional(),
  // iframe allowed
  isIframeAllowed: import_zod.z.boolean().optional()
});

// src/routers/read/types.ts
var import_zod2 = __toESM(require("zod"));
var readOptionsSchema = import_zod2.default.object({
  /**
   * The URL to scrape.
   * Must be a valid URL string.
   */
  url: import_zod2.default.string(),
  /**
   * Whether to extract metadata from the page.
   * Default: true
   */
  // default true if not set
  metadata: import_zod2.default.preprocess(
    (val) => val !== "false" && val !== false,
    import_zod2.default.boolean().optional()
  ),
  /**
   * Whether to extract markdown from the page.
   * Default: true
   */
  // default true if not set
  markdown: import_zod2.default.preprocess(
    (val) => val !== "false" && val !== false,
    import_zod2.default.boolean().optional()
  ),
  /**
   * Whether to return cleaned HTML.
   * Default: true
   */
  cleanedHtml: import_zod2.default.preprocess(
    (val) => val !== "false" && val !== false,
    import_zod2.default.boolean().optional()
  ),
  /**
   * Whether to fetch and parse robots.txt.
   * Default: false
   */
  robots: import_zod2.default.preprocess(
    (val) => val === "true" || val === true,
    import_zod2.default.boolean().optional()
  ),
  /**
   * Whether to return raw HTML.
   * Default: false
   */
  rawHtml: import_zod2.default.preprocess(
    (val) => val !== "false" && val !== false,
    import_zod2.default.boolean().optional()
  ),
  /**
   * Options for metadata extraction.
   * Controls how metadata like title, description, etc. are extracted.
   */
  metadataOptions: MetadataOptionsSchema.optional()
  /** DEPRECATED: AS WE ARE NOT USING HTMLREWRITE FOR CLEANING THE HTML FOR NOW, MAY BE REUSED THIS IN THE FUTURE
   * Options for HTML cleaning.
   * Controls how HTML is sanitized and cleaned.
   */
  // cleanedHtmlOptions: HTMLCleaningOptionsSchema.optional(),
});
// Annotate the CommonJS export names for ESM import in node:
0 && (module.exports = {
  readOptionsSchema
});
//# sourceMappingURL=read.js.map