import {z} from 'zod'

export type GetApiCrawlDataArgs = {name: string, format?: string | undefined, type?: string | undefined, num?: string | undefined};

export type GetApiCrawlDataOptions = {baseUrl?: string | undefined, Authorization?: string | undefined, fetch?: typeof fetch | undefined};

export const getApiCrawlDataResponse = z.array(z.object({sentiment: z.number().optional(), theCookie: z.string().optional(), humanLanguage: z.string().optional(), diffbotUri: z.string().optional(), siteName: z.string().optional(), pageUrl: z.string().optional(), html: z.string().optional(), text: z.string().optional(), type: z.string().optional(), title: z.string().optional(), docId: z.number().int().optional(), fromSeedUrl: z.string().optional(), seedUrlHash32: z.number().int().optional(), parentUrlDocId: z.number().int().optional(), gburl: z.string().optional(), lastCrawlTimeUTC: z.number().int().optional(), timestamp: z.string().optional()}));

export const validateResponse = async <Output>(
  schema: {
    readonly '~standard': {
      readonly validate: (value: unknown) => ({ readonly value: Output; readonly issues?: undefined } | { readonly issues: ReadonlyArray<{ readonly message: string; readonly path?: ReadonlyArray<PropertyKey | { readonly key: PropertyKey }> | undefined }> }) | Promise<{ readonly value: Output; readonly issues?: undefined } | { readonly issues: ReadonlyArray<{ readonly message: string; readonly path?: ReadonlyArray<PropertyKey | { readonly key: PropertyKey }> | undefined }> }>
    }
  },
  value: unknown
): Promise<Output> => {
  const result = await schema['~standard'].validate(value)

  if (result.issues !== undefined) {
    const detail = result.issues
      .map(({ message, path }) =>
        path?.length
          ? `${path.map((segment) => String(typeof segment === 'object' ? segment.key : segment)).join('.')}: ${message}`
          : message
      )
      .join('; ')

    throw new Error(`Response does not match the schema: ${detail}`, { cause: { issues: result.issues } })
  }

  return result.value
};

/**
 * Retrieve Crawl Job Data
 * 
 * GET /crawl/data
 */
export const getApiCrawlData = async (args: GetApiCrawlDataArgs, options?: GetApiCrawlDataOptions) => {
const {baseUrl = "https://llm.diffbot.com/api/v1/web_search", fetch: fetchFn = fetch, Authorization} = options ?? {}

const query = new URLSearchParams()
const headers = new Headers()
headers.set('accept', "application/json")

if (args.name != null) query.append("name", String(args.name))
if (args.format != null) query.append("format", String(args.format))
if (args.type != null) query.append("type", String(args.type))
if (args.num != null) query.append("num", String(args.num))
if (Authorization !== undefined) headers.set('authorization', `Bearer ${Authorization}`)

const url = `${baseUrl.replace(/\/+$/, '')}/crawl/data${query.size > 0 ? `?${query}` : ''}`

const res = await fetchFn(url, {method: "GET", headers})

if (!res.ok) throw new Error(`Request failed with status ${res.status}`, {cause: {status: res.status, body: await res.text()}})

return validateResponse(getApiCrawlDataResponse, await res.json())
};