icu_segmenter 2.1.2

Unicode line breaking and text segmentation algorithms for text boundaries analysis
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
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140

[[bench]]
harness = false
name = "bench"
path = "benches/bench.rs"

[dependencies.core_maths]
default-features = false
optional = true
version = "0.1.0"

[dependencies.databake]
default-features = false
features = ["derive"]
optional = true
version = "0.2.0"

[dependencies.icu_collections]
default-features = false
version = "~2.1.1"

[dependencies.icu_locale]
default-features = false
optional = true
version = "~2.1.1"

[dependencies.icu_provider]
default-features = false
version = "2.1.1"

[dependencies.icu_segmenter_data]
default-features = false
optional = true
version = "~2.1.1"

[dependencies.potential_utf]
default-features = false
features = ["alloc", "zerovec"]
version = "0.1.3"

[dependencies.serde]
default-features = false
features = ["derive", "alloc"]
optional = true
version = "1.0.220"

[dependencies.utf8_iter]
default-features = false
version = "1.0.2"

[dependencies.zerovec]
default-features = false
features = ["alloc", "yoke"]
version = "0.11.3"

[dev-dependencies.icu_locale_core]
default-features = false
version = "2.1.1"

[dev-dependencies.itertools]
version = "0.14.0"

[dev-dependencies.ndarray]
version = "0.16.0"

[dev-dependencies.serde]
default-features = false
features = ["derive"]
version = "1.0.220"

[dev-dependencies.serde_json]
version = "1.0.45"

[features]
auto = ["lstm"]
compiled_data = ["dep:icu_segmenter_data", "dep:icu_locale", "icu_locale?/compiled_data", "icu_provider/baked"]
datagen = ["serde", "dep:databake", "potential_utf/databake", "zerovec/databake", "icu_collections/databake", "icu_provider/export"]
default = ["compiled_data", "auto"]
lstm = ["dep:core_maths"]
serde = ["dep:serde", "potential_utf/serde", "zerovec/serde", "icu_collections/serde", "icu_provider/serde"]

[lib]
bench = false
name = "icu_segmenter"
path = "src/lib.rs"

[package]
authors = ["The ICU4X Project Developers"]
autobenches = false
autobins = false
autoexamples = false
autolib = false
autotests = false
build = false
categories = ["internationalization"]
description = "Unicode line breaking and text segmentation algorithms for text boundaries analysis"
edition = "2021"
homepage = "https://icu4x.unicode.org"
include = ["data/**/*", "src/**/*", "examples/**/*", "benches/**/*", "tests/**/*", "Cargo.toml", "LICENSE", "README.md", "build.rs"]
license = "Unicode-3.0"
name = "icu_segmenter"
readme = "README.md"
repository = "https://github.com/unicode-org/icu4x"
rust-version = "1.83"
version = "2.1.2"

[package.metadata.docs.rs]
all-features = true

[target.'cfg(not(target_arch = "wasm32"))'.dev-dependencies.criterion]
version = "0.5.0"

[[test]]
name = "cnn"
path = "tests/cnn/main.rs"
required-features = []

[[test]]
name = "complex_word"
path = "tests/complex_word.rs"
required-features = ["auto"]

[[test]]
name = "css_line_break"
path = "tests/css_line_break.rs"

[[test]]
name = "css_word_break"
path = "tests/css_word_break.rs"

[[test]]
name = "locale"
path = "tests/locale.rs"

[[test]]
name = "spec_test"
path = "tests/spec_test.rs"

[[test]]
name = "word_rule_status"
path = "tests/word_rule_status.rs"