lindera-analysis 5.3.0

Text analysis chain (character filters, token filters, tokenizer) for Lindera.
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

# THIS FILE IS AUTOMATICALLY GENERATED BY CARGO
#
# When uploading crates to the registry Cargo will automatically
# "normalize" Cargo.toml files for maximal compatibility
# with all versions of Cargo and also rewrite `path` dependencies
# to registry (e.g., crates.io) dependencies.
#
# If you are reading this file be aware that the original Cargo.toml
# will likely look very different (and much more reasonable).
# See Cargo.toml.orig for the original contents.

[package]
edition = "2024"
name = "lindera-analysis"
version = "5.3.0"
build = false
autolib = false
autobins = false
autoexamples = false
autotests = false
autobenches = false
description = "Text analysis chain (character filters, token filters, tokenizer) for Lindera."
homepage = "https://github.com/lindera/lindera"
documentation = "https://docs.rs/lindera-analysis"
readme = "README.md"
keywords = [
    "morphological",
    "analysis",
    "tokenizer",
    "filter",
]
categories = ["text-processing"]
license = "MIT"
repository = "https://github.com/lindera/lindera"
resolver = "2"

[features]
default = []
embed-cc-cedict = ["lindera/embed-cc-cedict"]
embed-ipadic = ["lindera/embed-ipadic"]
embed-ipadic-neologd = ["lindera/embed-ipadic-neologd"]
embed-jieba = ["lindera/embed-jieba"]
embed-ko-dic = ["lindera/embed-ko-dic"]
embed-unidic = ["lindera/embed-unidic"]

[lib]
name = "lindera_analysis"
path = "src/lib.rs"

[[example]]
name = "tokenize"
path = "examples/tokenize.rs"

[[example]]
name = "tokenize_with_config"
path = "examples/tokenize_with_config.rs"

[[example]]
name = "tokenize_with_filters"
path = "examples/tokenize_with_filters.rs"

[[example]]
name = "tokenize_with_user_dict"
path = "examples/tokenize_with_user_dict.rs"

[[bench]]
name = "bench_analysis_ipadic"
path = "benches/bench_analysis_ipadic.rs"
harness = false
required-features = ["embed-ipadic"]

[dependencies.anyhow]
version = "1.0.104"

[dependencies.daachorse]
version = "4.0.0"

[dependencies.kanaria]
version = "0.2.0"

[dependencies.lindera]
version = "5.3.0"

[dependencies.regex]
version = "1.13.1"

[dependencies.serde]
version = "1.0.229"
features = ["derive"]

[dependencies.serde_json]
version = "1.0.151"

[dependencies.serde_yaml_ng]
version = "0.10.0"

[dependencies.unicode-blocks]
version = "0.1.10"

[dependencies.unicode-normalization]
version = "0.1.25"

[dependencies.unicode-segmentation]
version = "1.13.3"

[dev-dependencies.criterion]
version = "0.8.2"
features = ["html_reports"]
default-features = false

[dev-dependencies.lindera-dictionary]
version = "5.3.0"

[dev-dependencies.once_cell]
version = "1.21.4"

[dev-dependencies.serde_json]
version = "1.0.151"