import {z} from 'zod'

export type TableParsingStrategy = 'tsr' | 'vlm' | 'unknown';

export type TableOutputMode = 'markdown' | 'html';

export type FormDetectionMode = 'vlm' | 'tsr' | 'unknown';

export type ChunkStrategy = 'page' | 'section' | 'fragment';

export type ModelProvider = 'tensorlake' | 'claude-3-5-sonnet-latest' | 'gpt-4o-mini';

export type Settings = {tableParsingMode?: TableParsingStrategy | undefined, tableOutputMode?: TableOutputMode | undefined, tableSummarization?: boolean | undefined, tableSummarizationPrompt?: (string | null) | undefined, figureSummarization?: boolean | undefined, figureSummarizationPrompt?: (string | null) | undefined, formDetectionMode?: FormDetectionMode | undefined, chunkStrategy?: (ChunkStrategy | null) | undefined, jsonSchema: unknown, structuredExtractionPrompt?: (string | null) | undefined, modelProvider?: (ModelProvider | null) | undefined, deliverWebhook?: boolean | undefined, detectSignature?: boolean | undefined, skewCorrection?: boolean | undefined, disableLayoutDetection?: boolean | undefined, structuredExtractionSkipOcr?: boolean | undefined, detectStrikethrough?: boolean | undefined};

export type CreateDatasetRequest = {name: string, description?: (string | null) | undefined, settings: Settings};

export type CreateApiDocumentsV1DatasetsArgs = {body: CreateDatasetRequest};

export type CreateApiDocumentsV1DatasetsOptions = {baseUrl?: string | undefined, bearerAuth?: string | undefined, fetch?: typeof fetch | undefined};

export const createDatasetResponse = z.object({id: z.string()});

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
};

/**
 * Create a new dataset. They are used in conjunction with the Structurued Data
 * or Documetn Parsing API requests. Behavior of datasets when used with the
 * APIs:
 * * Structured Extraction API - Structured Data from files are automatically
 *   inserted into datasets. A JSON schema is required to guide the extraction.
 * * Document Parsing API - Chunks of parsed documents from the Document
 *   Parsing API automatically.
 * 
 * POST /documents/v1/datasets
 */
export const createApiDocumentsV1Datasets = async (args: CreateApiDocumentsV1DatasetsArgs, options?: CreateApiDocumentsV1DatasetsOptions) => {
const {baseUrl = "https://api.tensorlake.ai", fetch: fetchFn = fetch, bearerAuth} = options ?? {}

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

if (bearerAuth !== undefined) headers.set('authorization', `Bearer ${bearerAuth}`)

const url = `${baseUrl.replace(/\/+$/, '')}/documents/v1/datasets${query.size > 0 ? `?${query}` : ''}`

const res = await fetchFn(url, {method: "POST", headers, body: JSON.stringify(args.body)})

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

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