icu_segmenter 1.5.0

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

# This file is part of ICU4X. For terms of use, please see the file
# called LICENSE at the top level of the ICU4X source tree
# (online at: https://github.com/unicode-org/icu4x/blob/main/LICENSE ).

[package]
name = "icu_segmenter"
description = "Unicode line breaking and text segmentation algorithms for text boundaries analysis"

authors.workspace = true
categories.workspace = true
edition.workspace = true
homepage.workspace = true
include.workspace = true
license.workspace = true
repository.workspace = true
rust-version.workspace = true
version.workspace = true

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

[dependencies]
displaydoc = { workspace = true }
icu_collections = { workspace = true }
icu_locid = { workspace = true }
icu_provider = { workspace = true, features = ["macros"] }
utf8_iter = { workspace = true }
zerovec = { workspace = true, features = ["yoke"] }

databake = { workspace = true, optional = true, features = ["derive"] }
serde = { workspace = true, features = ["derive", "alloc"], optional = true }

core_maths = { workspace = true, optional = true }

icu_segmenter_data = { workspace = true, optional = true }
icu_locid_transform = { workspace = true, optional = true, features = ["compiled_data"] }

[dev-dependencies]
icu = { path = "../../components/icu", default-features = false }
icu_properties = { path = "../properties", features = ["compiled_data"] }
itertools = { workspace = true }
serde = { workspace = true, features = ["derive"] }
serde_json = { workspace = true }

[target.'cfg(not(target_arch = "wasm32"))'.dev-dependencies]
criterion = { workspace = true }

[features]
default = ["compiled_data", "auto"]
std = ["icu_collections/std", "icu_locid/std", "icu_provider/std"]
serde = ["dep:serde", "zerovec/serde", "icu_collections/serde", "icu_provider/serde"]
datagen = ["serde", "dep:databake", "zerovec/databake", "icu_collections/databake"]
lstm = ["dep:core_maths"]
auto = ["lstm"] # Enabled try_new_auto_unstable constructors
compiled_data = ["dep:icu_segmenter_data"]
bench = []

[lib]
bench = false  # This option is required for Benchmark CI

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

[[test]]
name = "complex_word"
required-features = ["auto"]