Abimael MartellandClaude Opus 4.6
506b2a0c70
Both bindings now expose the same 6 function families: process, detect, classify, extractText, extractTextWithPositions, and extractTextInRegions. Bumps PyO3 from 0.22 to 0.25 for Python 3.14 support. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
95 lines
2.9 KiB
TypeScript
95 lines
2.9 KiB
TypeScript
/* auto-generated by NAPI-RS */
|
|
/* eslint-disable */
|
|
/**
|
|
* Lightweight PDF classification — returns type, page count, and OCR pages.
|
|
* Faster than detectPdf as it skips building the full PdfResult.
|
|
* Pages in pagesNeedingOcr are 0-indexed.
|
|
*/
|
|
export declare function classifyPdf(buffer: Buffer): PdfClassification
|
|
|
|
/** Fast detection only — no text extraction or markdown. */
|
|
export declare function detectPdf(buffer: Buffer): PdfResult
|
|
|
|
/** Extract plain text from a PDF Buffer. */
|
|
export declare function extractText(buffer: Buffer): string
|
|
|
|
/**
|
|
* 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 `needsOcr` — 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>
|
|
|
|
/** Extract text with position information from a PDF Buffer. */
|
|
export declare function extractTextWithPositions(buffer: Buffer, pages?: Array<number> | undefined | null): Array<TextItem>
|
|
|
|
/** 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
|
|
/** 0-indexed page numbers that need OCR. */
|
|
pagesNeedingOcr: Array<number>
|
|
confidence: number
|
|
}
|
|
|
|
/** Full PDF processing result with markdown and metadata. */
|
|
export interface PdfResult {
|
|
pdfType: string
|
|
markdown?: string
|
|
pageCount: number
|
|
processingTimeMs: number
|
|
/** 1-indexed page numbers that need OCR. */
|
|
pagesNeedingOcr: Array<number>
|
|
title?: string
|
|
confidence: number
|
|
isComplexLayout: boolean
|
|
pagesWithTables: Array<number>
|
|
pagesWithColumns: Array<number>
|
|
hasEncodingIssues: boolean
|
|
}
|
|
|
|
/** Process a PDF from a Buffer: detect type, extract text, and convert to Markdown. */
|
|
export declare function processPdf(buffer: Buffer, pages?: Array<number> | undefined | null): PdfResult
|
|
|
|
/** 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
|
|
}
|
|
|
|
/** A positioned text item extracted from a PDF. */
|
|
export interface TextItem {
|
|
text: string
|
|
x: number
|
|
y: number
|
|
width: number
|
|
height: number
|
|
font: string
|
|
fontSize: number
|
|
page: number
|
|
isBold: boolean
|
|
isItalic: boolean
|
|
itemType: string
|
|
}
|