mirror of
https://github.com/firecrawl/anydoc.git
synced 2026-09-14 14:18:33 +08:00
tomsideguide
37 lines
1.2 KiB
TypeScript
37 lines
1.2 KiB
TypeScript
/* auto-generated by NAPI-RS */
|
|
/* eslint-disable */
|
|
/**
|
|
* `code` on the `Error` a failed conversion rejects with. Conversion fails
|
|
* only when no complete Markdown could be produced; producer quirks are
|
|
* recovered or skipped instead.
|
|
*/
|
|
export type ConvertErrorCode =
|
|
/** Unknown format, or one that cannot be converted. */
|
|
| 'unsupported'
|
|
/**
|
|
* Pages of a PDF are scanned or image-only and need OCR, which anydoc does
|
|
* not do. The error is a `NeedsOcrError` naming them.
|
|
*/
|
|
| 'needsOcr'
|
|
/** Structurally unusable: no meaningful content could be extracted. */
|
|
| 'malformed'
|
|
/** Encrypted or password-protected. */
|
|
| 'encrypted'
|
|
/** Crossed a fixed safety limit (decompression, nesting, node count). */
|
|
| 'resourceLimit'
|
|
/** A part required for any meaningful output is absent. */
|
|
| 'missingPart'
|
|
/** The file could not be read, from `toMarkdown` only. */
|
|
| 'io'
|
|
/** `ocr: 'hosted'` could not get the document through Firecrawl Parse. */
|
|
| 'hosted'
|
|
|
|
/** The rejection for a PDF with pages that need OCR. */
|
|
export interface NeedsOcrError extends Error {
|
|
code: 'needsOcr'
|
|
/** 1-indexed pages that need OCR. */
|
|
pages: number[]
|
|
/** Pages in the document. */
|
|
pageCount: number
|
|
}
|