* feat: expose per-page markdown extraction to Python and Node (#49) Implements the feature requested in issue #49: a list-of-pages markdown output from the Python API. Matching the existing project pattern, the feature lives in the Rust core and is surfaced through every binding. - Rust core: `extract_pages_markdown` (path) and `extract_pages_markdown_mem` (bytes) now take `Option<&[u32]>` — `None` returns every page in document order; a slice restricts and preserves caller order. - Python: new `extract_pages_markdown(path, pages=None)` and `extract_pages_markdown_bytes(data, pages=None)` functions plus `PageMarkdown` / `PagesExtractionResult` classes; stub file updated. - Node: `extractPagesMarkdown(buffer, pages?)` — `pages` is now optional. - Tests: 2 new Rust integration tests, 9 new Python tests, 2 new Node assertions. All 372 unit + 107 integration + 53 Python tests pass. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore: bump version from 1.3.0 to 1.4.0 Minor bump for the new per-page markdown extraction API exposed through the Python and Node bindings. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
56 lines
1.2 KiB
JSON
56 lines
1.2 KiB
JSON
{
|
|
"name": "@firecrawl/pdf-inspector",
|
|
"version": "1.4.0",
|
|
"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"
|
|
}
|
|
}
|