harmorp 0.1.2

Enhanced Nazief-Adriani Indonesian stemmer: iterative ECS, nasal-assimilation restoration, phonotactic guards, FST dictionary, zero-alloc hot path
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
43
44
45
46
47
48
49
50
51
52
53
54
55
56

[package]
name = "harmorp"
version = "0.1.2"
edition = "2021"
authors = ["HARMorph Team"]
description = "Enhanced Nazief-Adriani Indonesian stemmer: iterative ECS, nasal-assimilation restoration, phonotactic guards, FST dictionary, zero-alloc hot path"
license = "MIT"
repository = "https://github.com/masdevid/harmorp.git"
keywords = ["indonesian", "stemmer", "nlp", "morphology"]
categories = ["text-processing"]

[features]
default = []
python = ["pyo3"]

[dependencies]
# FST dictionary (zero-heap mmap lookup)
fst = "0.4"
memmap2 = "0.9"

# Avoid heap allocation in hot path for candidate lists
smallvec = { version = "1.13", features = ["const_generics"] }

# Thread-safe memoization cache
dashmap = "6"

# PyO3 Python bindings (optional, feature-gated)
pyo3 = { version = "0.21", features = ["extension-module"], optional = true }

# Serialization for config/rules
serde = { version = "1.0", features = ["derive"] }
serde_json = "1.0"

[dev-dependencies]
pretty_assertions = "1.4"
criterion = { version = "0.5", features = ["html_reports"] }
sastrawi = "0.1"

[[bench]]
name = "stemmer_bench"
harness = false

[[bench]]
name = "compare_bench"
harness = false

[lib]
name = "harmorp"
path = "src/lib.rs"
crate-type = ["cdylib", "rlib"]

[profile.release]
opt-level = 3
lto = "fat"
codegen-units = 1
panic = "abort"