Abimael MartellandCursor
28decf15d6
PDFs carry no underline font flag — underlines are stroked horizontal lines or thin filled rects drawn under the baseline. Correlate those graphics (already parsed from the content stream) with text items in a post-pass: a rule within ~0.35em below the baseline covering >=60% of an item's width marks is_underline. Exposed through the napi and python bindings. Verified on real docs: 4/4 underlined sentences flagged on a Japanese report, links/headings flagged on 8 of 10 underline-bearing eval docs, zero flags on docs without underlines. Known FP source (table cell borders) documented — downstream applies inline styling only to plain-text regions. napi 1.9.8 -> 1.9.9. Co-authored-by: Cursor <cursoragent@cursor.com>
56 lines
1.2 KiB
JSON
56 lines
1.2 KiB
JSON
{
|
|
"name": "@firecrawl/pdf-inspector",
|
|
"version": "1.9.9",
|
|
"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",
|
|
"bin": {
|
|
"pdf-inspector": "bin/pdf-inspector.mjs"
|
|
},
|
|
"license": "MIT",
|
|
"keywords": [
|
|
"pdf",
|
|
"pdf-extraction",
|
|
"pdf-parser",
|
|
"text-extraction",
|
|
"ocr",
|
|
"pdf-classification",
|
|
"napi",
|
|
"rust",
|
|
"firecrawl"
|
|
],
|
|
"files": [
|
|
"index.js",
|
|
"index.d.ts",
|
|
"*.node",
|
|
"bin/",
|
|
"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",
|
|
"x86_64-pc-windows-msvc"
|
|
],
|
|
"package": {
|
|
"name": "@firecrawl/pdf-inspector-js"
|
|
}
|
|
},
|
|
"scripts": {
|
|
"build": "napi build --platform --release",
|
|
"build:debug": "napi build --platform"
|
|
},
|
|
"devDependencies": {
|
|
"@napi-rs/cli": "^3.4.1"
|
|
}
|
|
}
|