[package]
edition = "2021"
name = "rs-chunks"
version = "0.1.0"
authors = ["Ranjan Kudesia <ranjan.kudesia@gmail.com>"]
build = false
exclude = [
"/examples",
"/tests",
"/target",
"/.github",
]
autolib = false
autobins = false
autoexamples = false
autotests = false
autobenches = false
description = "Fast, high-fidelity document chunking for RAG — a pure-Rust engine covering 36 file formats (Office, OpenDocument, PDF, email, ebooks, notebooks, and more)."
homepage = "https://github.com/RanjanKudesia/rs-chunks"
documentation = "https://docs.rs/rs-chunks"
readme = "README.md"
keywords = [
"chunking",
"document",
"rag",
"pdf",
"docx",
]
categories = [
"text-processing",
"parsing",
]
license = "MIT"
repository = "https://github.com/RanjanKudesia/rs-chunks"
[features]
default = ["pdf-native"]
pdf-native = [
"dep:liteparse",
"dep:tokio",
]
[lib]
name = "chunks_rs"
path = "src/lib.rs"
[dependencies.base64]
version = "0.22"
[dependencies.calamine]
version = "0.26"
features = ["dates"]
[dependencies.cfb]
version = "0.10"
[dependencies.csv]
version = "1"
[dependencies.encoding_rs]
version = "0.8"
[dependencies.image]
version = "0.25"
features = ["png"]
default-features = false
[dependencies.liteparse]
version = "=2.9.0"
optional = true
default-features = false
[dependencies.mail-parser]
version = "0.11"
features = ["full_encoding"]
default-features = false
[dependencies.quick-xml]
version = "0.38"
[dependencies.rtf-parser]
version = "0.4"
[dependencies.serde]
version = "1"
features = ["derive"]
[dependencies.serde_json]
version = "1"
[dependencies.tokio]
version = "1"
features = ["rt"]
optional = true
[dependencies.zip]
version = "2"
features = ["deflate"]
default-features = false