Abimael MartellandClaude Opus 4.5
135ce518c1
- Smart PDF type detection (text vs scanned) without full document load - Text extraction using lopdf directly - Markdown conversion with header/list/code detection - CLI tools: detect-pdf, pdf2md Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
35 lines
568 B
TOML
35 lines
568 B
TOML
[package]
|
|
name = "pdf-to-markdown"
|
|
version = "0.1.0"
|
|
edition = "2021"
|
|
authors = ["Firecrawl Team"]
|
|
description = "Fast PDF to Markdown conversion with smart detection"
|
|
license = "MIT"
|
|
|
|
[dependencies]
|
|
# PDF parsing - use local firecrawl lopdf
|
|
lopdf = { path = "../../lopdf", features = ["rayon"] }
|
|
|
|
# Error handling
|
|
thiserror = "2.0"
|
|
|
|
# Parallel processing
|
|
rayon = "1.10"
|
|
|
|
# Logging
|
|
log = "0.4"
|
|
|
|
[dev-dependencies]
|
|
tempfile = "3.3"
|
|
|
|
[features]
|
|
default = []
|
|
|
|
[[bin]]
|
|
name = "pdf2md"
|
|
path = "src/bin/pdf2md.rs"
|
|
|
|
[[bin]]
|
|
name = "detect-pdf"
|
|
path = "src/bin/detect_pdf.rs"
|