Abimael MartellandClaude Opus 4.6
8e8ab4a19d
Adds a new function that takes a PDF buffer and page+bbox regions (same interface as extractTextInRegions), runs heuristic table detection on items within each region, and returns markdown pipe-tables. Falls back to needs_ocr=true when no table structure is found or text quality is suspect. Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
51 lines
1.1 KiB
JSON
51 lines
1.1 KiB
JSON
{
|
|
"name": "firecrawl-pdf-inspector",
|
|
"version": "0.3.7",
|
|
"description": "Fast PDF classification and text extraction. Detect text-based vs scanned PDFs, extract text by region with quality checks. Native Rust performance via napi-rs.",
|
|
"main": "index.js",
|
|
"types": "index.d.ts",
|
|
"license": "MIT",
|
|
"keywords": [
|
|
"pdf",
|
|
"pdf-extraction",
|
|
"pdf-parser",
|
|
"text-extraction",
|
|
"ocr",
|
|
"pdf-classification",
|
|
"napi",
|
|
"rust",
|
|
"firecrawl"
|
|
],
|
|
"files": [
|
|
"index.js",
|
|
"index.d.ts",
|
|
"*.node",
|
|
"README.md"
|
|
],
|
|
"repository": {
|
|
"type": "git",
|
|
"url": "https://github.com/firecrawl/pdf-inspector"
|
|
},
|
|
"homepage": "https://github.com/firecrawl/pdf-inspector",
|
|
"publishConfig": {
|
|
"access": "public"
|
|
},
|
|
"napi": {
|
|
"binaryName": "pdf-inspector",
|
|
"targets": [
|
|
"x86_64-unknown-linux-gnu",
|
|
"aarch64-apple-darwin"
|
|
],
|
|
"package": {
|
|
"name": "@firecrawl/pdf-inspector-js"
|
|
}
|
|
},
|
|
"scripts": {
|
|
"build": "napi build --platform --release",
|
|
"build:debug": "napi build --platform"
|
|
},
|
|
"devDependencies": {
|
|
"@napi-rs/cli": "^3.4.1"
|
|
}
|
|
}
|