[package]
edition = "2021"
rust-version = "1.75"
name = "textprep"
version = "0.1.3"
authors = ["Arc"]
build = false
autolib = false
autobins = false
autoexamples = false
autotests = false
autobenches = false
description = "Text preprocessing primitives: normalization, tokenization, and fast keyword matching."
homepage = "https://github.com/arclabs561/textprep"
documentation = "https://docs.rs/textprep"
readme = "README.md"
keywords = [
"text-processing",
"tokenization",
"normalization",
"aho-corasick",
]
categories = ["text-processing"]
license = "MIT OR Apache-2.0"
repository = "https://github.com/arclabs561/textprep"
[features]
casefold = ["dep:unicode-casefold"]
default = []
serde = ["dep:serde"]
[lib]
name = "textprep"
path = "src/lib.rs"
[[example]]
name = "fuzzy_token_match"
path = "examples/fuzzy_token_match.rs"
[[test]]
name = "property_tests"
path = "tests/property_tests.rs"
[[bench]]
name = "textprep_bench"
path = "benches/textprep_bench.rs"
harness = false
[dependencies.aho-corasick]
version = "1.1"
[dependencies.serde]
version = "1.0"
features = ["derive"]
optional = true
[dependencies.unicode-casefold]
version = "0.2"
optional = true
[dependencies.unicode-normalization]
version = "0.1"
[dependencies.unicode-segmentation]
version = "1.10"
[dev-dependencies.criterion]
version = "0.7"
[dev-dependencies.gramdex]
version = "0.1"
[dev-dependencies.proptest]
version = "1.9"
[dev-dependencies.serde_json]
version = "1.0"