[package]
edition = "2021"
name = "df-ocr-switcher"
version = "0.1.0"
authors = ["Dario Finardi <df@dariofinardi.it>"]
build = false
exclude = [
"tests/",
".env",
".env.*",
]
autolib = false
autobins = false
autoexamples = false
autotests = false
autobenches = false
description = "Document OCR pipeline in pure Rust: scanned PDF / multi-page TIFF / image → Markdown. PaddleOCR PP-OCRv6 and Tesseract 5.5 as interchangeable engines, PP-DocLayoutV3 layout for both."
homepage = "https://github.com/dariofinardi/df-ocr-switcher"
documentation = "https://docs.rs/df-ocr-switcher"
readme = "README.md"
keywords = [
"ocr",
"paddleocr",
"tesseract",
"document",
"markdown",
]
categories = [
"computer-vision",
"text-processing",
]
license = "MIT"
repository = "https://github.com/dariofinardi/df-ocr-switcher"
[features]
default = []
searchable-pdf = ["dep:lopdf"]
tesseract-engine = ["dep:tesseract5-rs"]
[lib]
name = "df_ocr_switcher"
path = "src/lib.rs"
[[bin]]
name = "ocr-doc"
path = "src/bin/ocr_doc.rs"
[[example]]
name = "basic_ocr"
path = "examples/basic_ocr.rs"
[[example]]
name = "with_tables"
path = "examples/with_tables.rs"
[dependencies.image]
version = "0.25"
[dependencies.lopdf]
version = "0.34"
optional = true
[dependencies.ort]
version = "=2.0.0-rc.9"
features = ["load-dynamic"]
default-features = false
[dependencies.ppocr-rs]
version = "0.7.3"
[dependencies.serde]
version = "1"
features = ["derive"]
[dependencies.serde_json]
version = "1"
[dependencies.tesseract5-rs]
version = "0.1.4"
optional = true
[dependencies.thiserror]
version = "2"
[dependencies.tiff]
version = "0.10"
[dev-dependencies.anyhow]
version = "1"