[package]
edition = "2024"
name = "chunk"
version = "0.10.2"
build = false
exclude = [
"benches/data/*",
"packages/*",
"assets/*",
"scripts/*",
"*.png",
"*.svg",
]
autolib = false
autobins = false
autoexamples = false
autotests = false
autobenches = false
description = "The fastest semantic text chunking library — up to 1TB/s chunking throughput"
readme = "README.md"
keywords = [
"chunking",
"text",
"simd",
"nlp",
"tokenization",
]
categories = [
"text-processing",
"algorithms",
]
license = "MIT OR Apache-2.0"
repository = "https://github.com/chonkie-inc/chunk"
[lib]
name = "chunk"
path = "src/lib.rs"
[[example]]
name = "bench_pattern"
path = "examples/bench_pattern.rs"
[[example]]
name = "bench_split"
path = "examples/bench_split.rs"
[[bench]]
name = "chunk"
path = "benches/chunk.rs"
harness = false
[[bench]]
name = "kiru"
path = "benches/kiru.rs"
harness = false
[[bench]]
name = "multi_pattern"
path = "benches/multi_pattern.rs"
harness = false
[[bench]]
name = "text_splitter"
path = "benches/text_splitter.rs"
harness = false
[dependencies.daggrs]
version = "0.1"
[dependencies.memchr]
version = "2"
[dev-dependencies.criterion]
version = "0.5"
[dev-dependencies.kiru]
version = "0.1"
[dev-dependencies.text-splitter]
version = "0.18"