Abimael MartellandClaude Opus 4.6
87d2bae0d9
Move the napi bridge from fire-pdf into pdf-inspector as `napi/`. Package name: @firecrawl/pdf-inspector-js, published to GitHub Packages (npm.pkg.github.com) as a public package on v* tags. Exposes two functions: - classifyPdf(buffer) → type, page count, pages needing OCR - extractTextInRegions(buffer, pageRegions) → per-region text with needsOcr quality flag (GID fonts, garbage, encoding issues) Includes publish workflow that builds linux-x64-gnu + darwin-arm64 binaries and publishes main + platform-specific packages. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
50 lines
1.5 KiB
TypeScript
50 lines
1.5 KiB
TypeScript
/* auto-generated by NAPI-RS */
|
|
/* eslint-disable */
|
|
/**
|
|
* Classify a PDF: detect type (TextBased/Scanned/Mixed/ImageBased),
|
|
* page count, and which pages need OCR. Takes PDF bytes as Buffer.
|
|
*/
|
|
export declare function classifyPdf(buffer: Buffer): PdfClassification
|
|
|
|
/**
|
|
* Extract text within bounding-box regions from a PDF.
|
|
*
|
|
* For hybrid OCR: layout model detects regions in rendered images,
|
|
* this extracts PDF text within those regions — skipping GPU OCR
|
|
* for text-based pages.
|
|
*
|
|
* Each region result includes `needs_ocr` — set when the extracted text
|
|
* is unreliable (empty, GID-encoded fonts, garbage, encoding issues).
|
|
*
|
|
* Coordinates are PDF points with top-left origin.
|
|
*/
|
|
export declare function extractTextInRegions(buffer: Buffer, pageRegions: Array<PageRegions>): Array<PageRegionTexts>
|
|
|
|
/** A page's regions for text extraction: (page_index_0based, bboxes). */
|
|
export interface PageRegions {
|
|
page: number
|
|
/** Each bbox is [x1, y1, x2, y2] in PDF points, top-left origin. */
|
|
regions: Array<Array<number>>
|
|
}
|
|
|
|
/** Extracted text for one page's regions. */
|
|
export interface PageRegionTexts {
|
|
page: number
|
|
regions: Array<RegionText>
|
|
}
|
|
|
|
/** Lightweight PDF classification result. */
|
|
export interface PdfClassification {
|
|
pdfType: string
|
|
pageCount: number
|
|
pagesNeedingOcr: Array<number>
|
|
confidence: number
|
|
}
|
|
|
|
/** Extracted text for a single region. */
|
|
export interface RegionText {
|
|
text: string
|
|
/** `true` when the text should not be trusted (empty, GID fonts, garbage, encoding issues). */
|
|
needsOcr: boolean
|
|
}
|