rustam 0.1.0

Full Persian NLP pipeline for Rust — normalization, tokenization, stemming, lemmatization, conjugation, spell correction, and more
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42

[package]
name = "rustam"
version = "0.1.0"
edition = "2021"
authors = ["Amirhossein Ghanipour <d3v1ll3n@gmail.com>"]
description = "Full Persian NLP pipeline for Rust — normalization, tokenization, stemming, lemmatization, conjugation, spell correction, and more"
license = "MIT"
keywords = ["nlp", "persian", "farsi", "nlp-library", "text-processing"]
categories = ["text-processing", "science"]
homepage = "https://github.com/amirhosseinghanipour/rustam"
repository = "https://github.com/amirhosseinghanipour/rustam"
documentation = "https://docs.rs/rustam"
readme = "README.md"
rust-version = "1.70"
exclude = [".github/", "tests/"]

[features]
## Enables POSTagger and Chunker from the crftag crate.
pos = ["dep:crftag"]
## Enables NerTagger from the nerrs crate.
ner = ["dep:nerrs"]
## Enables PipelineParser (POSTagger + Lemmatizer → DependencyParser).
dep-parsing = ["dep:arc-eager", "pos"]
## Enables rustam::download() for fetching models from HF Hub.
hf-hub = ["dep:hf-hub"]
## Enables all optional NLP components.
full = ["pos", "ner", "dep-parsing", "hf-hub"]

[dependencies]
fancy-regex = "0.14"
once_cell = "1"
thiserror = "2"
quick-xml = { version = "0.37", features = ["encoding"] }
crftag    = { package = "crftag",    version = "0.1", optional = true }
nerrs     = { package = "nerrs",     version = "0.1", optional = true }
arc-eager = { package = "arc-eager", version = "0.1", optional = true }
hf-hub    = { version = "0.3",       optional = true }

[dev-dependencies]
crftag    = { package = "crftag",    version = "0.1" }
nerrs     = { package = "nerrs",     version = "0.1" }
arc-eager = { package = "arc-eager", version = "0.1" }