import {z} from 'zod'

export type GetApiCrawlArgs = {token: string, name?: string | undefined, roundStart?: string | undefined, pause?: string | undefined, restart?: string | undefined, delete?: string | undefined};

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

export const getApiCrawlResponse = z.union([z.object({response: z.string().optional(), jobs: z.array(z.object({jobStatus: z.object({message: z.string().optional(), status: z.number().int().optional()}).optional(), maxHops: z.number().int().optional(), downloadJson: z.string().optional(), urlProcessPattern: z.string().optional(), jobCompletionTimeUTC: z.number().int().optional(), maxRounds: z.number().int().optional(), type: z.string().optional(), pageCrawlSuccessesThisRound: z.number().int().optional(), urlCrawlRegEx: z.string().optional(), pageProcessPattern: z.string().optional(), apiUrl: z.string().optional(), useCanonical: z.number().int().optional(), jobCreationTimeUTC: z.number().int().optional(), repeat: z.number().int().optional(), downloadUrls: z.string().optional(), obeyRobots: z.number().int().optional(), roundsCompleted: z.number().int().optional(), pageCrawlAttempts: z.number().int().optional(), notifyWebhook: z.string().optional(), pageProcessSuccessesThisRound: z.number().int().optional(), customHeaders: z.object({}).optional(), objectsFound: z.number().int().optional(), roundStartTime: z.number().int().optional(), urlCrawlPattern: z.string().optional(), seedRecrawlFrequency: z.number().int().optional(), urlProcessRegEx: z.string().optional(), pageProcessSuccesses: z.number().int().optional(), urlsHarvested: z.number().int().optional(), crawlDelay: z.number().int().optional(), currentTime: z.number().int().optional(), useProxies: z.number().int().optional(), sentJobDoneNotification: z.number().int().optional(), currentTimeUTC: z.number().int().optional(), name: z.string().optional(), notifyEmail: z.string().optional(), pageCrawlSuccesses: z.number().int().optional(), pageProcessAttempts: z.number().int().optional()})).optional()}), z.object({response: z.string().optional(), jobs: z.array(z.object({jobStatus: z.object({message: z.string().optional(), status: z.number().int().optional()}).optional(), maxHops: z.number().int().optional(), downloadJson: z.string().optional(), urlProcessPattern: z.string().optional(), jobCompletionTimeUTC: z.number().int().optional(), maxRounds: z.number().int().optional(), type: z.string().optional(), pageCrawlSuccessesThisRound: z.number().int().optional(), urlCrawlRegEx: z.string().optional(), pageProcessPattern: z.string().optional(), apiUrl: z.string().optional(), useCanonical: z.number().int().optional(), jobCreationTimeUTC: z.number().int().optional(), repeat: z.number().int().optional(), downloadUrls: z.string().optional(), obeyRobots: z.number().int().optional(), roundsCompleted: z.number().int().optional(), pageCrawlAttempts: z.number().int().optional(), notifyWebhook: z.string().optional(), pageProcessSuccessesThisRound: z.number().int().optional(), customHeaders: z.object({}).optional(), objectsFound: z.number().int().optional(), roundStartTime: z.number().int().optional(), urlCrawlPattern: z.string().optional(), seedRecrawlFrequency: z.number().int().optional(), urlProcessRegEx: z.string().optional(), pageProcessSuccesses: z.number().int().optional(), urlsHarvested: z.number().int().optional(), crawlDelay: z.number().int().optional(), currentTime: z.number().int().optional(), useProxies: z.number().int().optional(), sentJobDoneNotification: z.number().int().optional(), currentTimeUTC: z.number().int().optional(), name: z.string().optional(), notifyEmail: z.string().optional(), pageCrawlSuccesses: z.number().int().optional(), pageProcessAttempts: z.number().int().optional()})).optional()}), z.object({response: z.string().optional()}), z.object({jobs: z.array(z.object({jobStatus: z.object({message: z.string().optional(), status: z.number().int().optional()}).optional(), maxHops: z.number().int().optional(), downloadJson: z.string().optional(), urlProcessPattern: z.string().optional(), jobCompletionTimeUTC: z.number().int().optional(), maxRounds: z.number().int().optional(), type: z.string().optional(), pageCrawlSuccessesThisRound: z.number().int().optional(), urlCrawlRegEx: z.string().optional(), pageProcessPattern: z.string().optional(), apiUrl: z.string().optional(), useCanonical: z.number().int().optional(), jobCreationTimeUTC: z.number().int().optional(), repeat: z.number().int().optional(), downloadUrls: z.string().optional(), obeyRobots: z.number().int().optional(), roundsCompleted: z.number().int().optional(), pageCrawlAttempts: z.number().int().optional(), notifyWebhook: z.string().optional(), pageProcessSuccessesThisRound: z.number().int().optional(), customHeaders: z.object({}).optional(), objectsFound: z.number().int().optional(), roundStartTime: z.number().int().optional(), urlCrawlPattern: z.string().optional(), seedRecrawlFrequency: z.number().int().optional(), urlProcessRegEx: z.string().optional(), pageProcessSuccesses: z.number().int().optional(), urlsHarvested: z.number().int().optional(), crawlDelay: z.number().int().optional(), currentTime: z.number().int().optional(), useProxies: z.number().int().optional(), sentJobDoneNotification: z.number().int().optional(), currentTimeUTC: z.number().int().optional(), name: z.string().optional(), notifyEmail: z.string().optional(), pageCrawlSuccesses: z.number().int().optional(), pageProcessAttempts: z.number().int().optional()})).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
};

/**
 * Manage a Crawl Job
 * 
 * GET /crawl
 */
export const getApiCrawl = async (args: GetApiCrawlArgs, options?: GetApiCrawlOptions) => {
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.token != null) query.append("token", String(args.token))
if (args.name != null) query.append("name", String(args.name))
if (args.roundStart != null) query.append("roundStart", String(args.roundStart))
if (args.pause != null) query.append("pause", String(args.pause))
if (args.restart != null) query.append("restart", String(args.restart))
if (args.delete != null) query.append("delete", String(args.delete))
if (Authorization !== undefined) headers.set('authorization', `Bearer ${Authorization}`)

const url = `${baseUrl.replace(/\/+$/, '')}/crawl${query.size > 0 ? `?${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(getApiCrawlResponse, await res.json())
};