// author: simon-pierre boucher <contact@spboucher.ai>
import { z } from "zod";

export const OutputFormatSchema = z.enum([
  "markdown",
  "html",
  "rawHtml",
  "links",
  "screenshot",
  "structured",
  "extract",
]);

export const ScrapeRequestSchema = z
  .object({
    url: z.string().url(),
    formats: z.array(OutputFormatSchema).default(["markdown"]),
    tier: z.enum(["auto", "http", "webkit", "safari"]).default("auto"),
    onlyMainContent: z.boolean().default(true),
    includeTags: z.array(z.string()).optional(),
    excludeTags: z.array(z.string()).optional(),
    waitFor: z.number().int().min(0).max(60_000).default(0),
    timeout: z.number().int().min(1_000).max(120_000).default(30_000),
    maxAge: z.number().int().min(0).default(0),
    headers: z.record(z.string()).optional(),
    maxBytes: z.number().int().min(1).optional(),
    respectRobots: z.boolean().default(true),
  })
  .strict();

export type ScrapeRequest = z.infer<typeof ScrapeRequestSchema>;

export const MapRequestSchema = z
  .object({
    url: z.string().url(),
    search: z.string().optional(),
    limit: z.number().int().min(1).max(50_000).default(5_000),
    includeSubdomains: z.boolean().default(false),
    sitemapOnly: z.boolean().default(false),
    ignoreSitemap: z.boolean().default(false),
  })
  .strict();

export type MapRequest = z.infer<typeof MapRequestSchema>;