Abimael MartellandClaude Fable 5
673fbe998f
Concise Features list and the opendataloader-bench comparison table on each registry readme, adapted per ecosystem. Bump all three versions (crate 0.1.6, python 0.2.5, npm 1.11.1) to republish the pages. Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
71 lines
1.5 KiB
TOML
71 lines
1.5 KiB
TOML
[package]
|
|
name = "pdf-inspector"
|
|
version = "0.1.6"
|
|
edition = "2021"
|
|
autobins = false
|
|
authors = ["Firecrawl Team"]
|
|
description = "Fast PDF inspection, classification, and text extraction with smart scanned vs text-based detection"
|
|
license = "MIT"
|
|
repository = "https://github.com/firecrawl/pdf-inspector"
|
|
readme = "docs/rust-api.md"
|
|
# Explicit allowlist: crates.io caps uploads at 10 MiB and tests/fixtures
|
|
# alone exceeds that. external/bcmaps ships in the crate — tounicode.rs
|
|
# loads it at runtime relative to CARGO_MANIFEST_DIR.
|
|
include = [
|
|
"src/**",
|
|
"external/bcmaps/**",
|
|
"docs/rust-api.md",
|
|
"LICENSE",
|
|
# maturin derives the sdist file list from this allowlist; the stub must
|
|
# ship so wheels built from the sdist keep their type hints.
|
|
"pdf_inspector.pyi",
|
|
]
|
|
|
|
[lib]
|
|
name = "pdf_inspector"
|
|
crate-type = ["lib", "cdylib"]
|
|
|
|
[dependencies]
|
|
# Python bindings
|
|
pyo3 = { version = "0.25", features = ["extension-module", "abi3-py38"], optional = true }
|
|
|
|
# PDF parsing
|
|
lopdf = { version = "0.41.0", features = ["rayon"] }
|
|
|
|
# Error handling
|
|
thiserror = "2.0"
|
|
|
|
# Parallel processing
|
|
rayon = "1.10"
|
|
|
|
# Logging
|
|
log = "0.4"
|
|
env_logger = "0.11"
|
|
|
|
# Text processing
|
|
regex = "1.10"
|
|
once_cell = "1.19"
|
|
unicode-normalization = "0.1"
|
|
|
|
# TrueType font parsing (for Identity-H CID font cmap extraction)
|
|
ttf-parser = "0.25"
|
|
|
|
[dev-dependencies]
|
|
tempfile = "3.3"
|
|
|
|
[features]
|
|
default = []
|
|
python = ["pyo3"]
|
|
|
|
[[bin]]
|
|
name = "pdf2md"
|
|
path = "src/bin/pdf2md.rs"
|
|
|
|
[[bin]]
|
|
name = "detect-pdf"
|
|
path = "src/bin/detect_pdf.rs"
|
|
|
|
[[bin]]
|
|
name = "dump_ops"
|
|
path = "src/bin/dump_ops.rs"
|