lingua_rs 0.4.4 → 0.4.5

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (5) hide show
  1. checksums.yaml +4 -4
  2. data/README.md +12 -23
  3. data/lib/lingua/version.rb +1 -1
  4. metadata +2 -3
  5. data/ext/lingua/Cargo.lock +0 -289
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: 151633d9585ecca170847b63a380b257178573a6f8fcb395d8ff731acfc0df4d
4
- data.tar.gz: 97ddfa0dcf4cf4943afcf65cb4240dd3f7e7d0b39936d36f38deb1a5224d3994
3
+ metadata.gz: 953c59791dc0b1234e1264f3e75881319edfd752a537a3bb0fd02c9830cb63ea
4
+ data.tar.gz: 6cf3ce511f0026deb1090c531771a843bb15e0fc4c7637e974f1d50b65330106
5
5
  SHA512:
6
- metadata.gz: 634d5762de12f35056462e61160e7b2dc730f9970ba9a4248c13daf8c93ab5d6c35d010576a2b1cf5255756e0319ec0409b3cd21fedf36aff970c7ac22e2efeb
7
- data.tar.gz: f27c9d123beee999fc57d13ab41f2b3029855bb957e363621092dafb9e6ccad8246a37a097b0b5ee4a5025762df04048e70d8a292984f856558fd67b8ece8855
6
+ metadata.gz: 067a63ee83c014a358fa48f0df452c626123d8039862cb9dac57b4e733fb379fc6af97102613bd8c664b3762105123223a488b962896bfc419195d237ff6135f
7
+ data.tar.gz: 4336e0b72d1dff76ddf28d2721025b4a36a4f6dd031252a09bdfa1eb10fdfc6982dcbc1bbd01d223a84e0f5256c06a98190c4c47a0f154ba06696e4a60abfce7
data/README.md CHANGED
@@ -5,7 +5,7 @@
5
5
  [![Downloads](https://img.shields.io/gem/dt/lingua_rs?color=0969da)](https://rubygems.org/gems/lingua_rs)
6
6
  [![License: MIT](https://img.shields.io/badge/License-MIT-6e7781.svg)](https://opensource.org/licenses/MIT)
7
7
 
8
- A Ruby gem wrapping the [Lingua](https://github.com/pemistahl/lingua-rs) Rust library for language detection.
8
+ Native Ruby bindings for the [Lingua](https://github.com/pemistahl/lingua-rs) Rust library, bringing highly accurate language detection for short text and mixed-language text, with confidence scores and ISO 639-1/639-3 language codes.
9
9
 
10
10
  ## Installation
11
11
 
@@ -25,12 +25,7 @@ Then run `bundle install`.
25
25
 
26
26
  ### Build requirements
27
27
 
28
- A Rust toolchain is required to compile the native extension. `rb-sys` currently depends on `bindgen 0.69` which does not support LLVM 22+. If your system uses LLVM 22+, point to LLVM 21:
29
-
30
- ```bash
31
- export LIBCLANG_PATH=/usr/lib/llvm21/lib
32
- export PATH=/usr/lib/llvm21/bin:$PATH
33
- ```
28
+ A Rust toolchain is required to compile the native extension.
34
29
 
35
30
  ## Usage
36
31
 
@@ -148,6 +143,12 @@ Lingua::Language['fra'] # => #<Lingua::Language French>
148
143
  Lingua::Language['xxx'] # => nil
149
144
  ```
150
145
 
146
+ | Method | Return type | Description |
147
+ |---|---|---|
148
+ | `Lingua::Language.all` | `Array<Lingua::Language>` | All supported languages |
149
+ | `Lingua::Language.names` | `Array<String>` | All language names (e.g. `'French'`) |
150
+ | `Lingua::Language.iso_codes` | `Array<String>` | All ISO 639-1 codes (e.g. `'fr'`) |
151
+
151
152
  | Method | Return type | Example |
152
153
  |---|---|---|
153
154
  | `name` | `String` | `'French'` |
@@ -157,19 +158,11 @@ Lingua::Language['xxx'] # => nil
157
158
  | `to_iso` | `String` | `'fr'` (alias for `to_iso6391`) |
158
159
  | `to_iso6391` | `String` | `'fr'` |
159
160
  | `to_iso6393` | `String` | `'fra'` |
160
- | `french?` | `Boolean` | `true` (works with name, ISO 639-1 or ISO 639-3: `fr?`, `fra?`) |
161
+ | `<name>?` | `Boolean` | Dynamic predicate for any language (`french?`, `fr?`, `fra?`) |
161
162
  | `inspect` | `String` | `'#<Lingua::Language French>'` |
162
163
  | `==` | `Boolean` | Compare two languages |
163
164
  | `hash` | `Integer` | Hash value (usable as Hash key) |
164
165
 
165
- Class methods:
166
-
167
- | Method | Return type | Description |
168
- |---|---|---|
169
- | `Lingua::Language.all` | `Array<Lingua::Language>` | All supported languages |
170
- | `Lingua::Language.names` | `Array<String>` | All language names (e.g. `'French'`) |
171
- | `Lingua::Language.iso_codes` | `Array<String>` | All ISO 639-1 codes (e.g. `'fr'`) |
172
-
173
166
  ### `Lingua::ConfidenceResult` methods
174
167
 
175
168
  Returned by `confidence_values`.
@@ -200,14 +193,10 @@ Returned by `detect_multiple`.
200
193
  `Lingua::UnknownLanguageError` (subclass of `ArgumentError`) is raised when an unrecognized language name or code is passed:
201
194
 
202
195
  ```ruby
203
- Lingua.detect('Hello', languages: %w[en zzzz])
204
- # => Lingua::UnknownLanguageError: unknown language: "zzzz"
205
-
206
- # Can also be rescued as ArgumentError
207
196
  begin
208
- Lingua.detect('Hello', languages: %w[zzzz])
209
- rescue ArgumentError => e
210
- puts e.message
197
+ Lingua.detect('Hello', languages: %w[en zzzz])
198
+ rescue Lingua::UnknownLanguageError => e
199
+ puts e.message # => unknown language: "zzzz"
211
200
  end
212
201
  ```
213
202
 
data/lib/lingua/version.rb CHANGED
@@ -1,5 +1,5 @@
1
1
  # frozen_string_literal: true
2
2
 
3
3
  module Lingua
4
- VERSION = '0.4.4'
4
+ VERSION = '0.4.5'
5
5
  end
metadata CHANGED
@@ -1,13 +1,13 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: lingua_rs
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.4.4
4
+ version: 0.4.5
5
5
  platform: ruby
6
6
  authors:
7
7
  - Sébastien Vrillaud
8
8
  bindir: exe
9
9
  cert_chain: []
10
- date: 2026-04-06 00:00:00.000000000 Z
10
+ date: 2026-04-08 00:00:00.000000000 Z
11
11
  dependencies:
12
12
  - !ruby/object:Gem::Dependency
13
13
  name: rb_sys
@@ -50,7 +50,6 @@ files:
50
50
  - LICENSE.txt
51
51
  - README.md
52
52
  - Rakefile
53
- - ext/lingua/Cargo.lock
54
53
  - ext/lingua/Cargo.toml
55
54
  - ext/lingua/extconf.rb
56
55
  - ext/lingua/src/confidence_result.rs
data/ext/lingua/Cargo.lock DELETED
@@ -1,289 +0,0 @@
1
- # This file is automatically @generated by Cargo.
2
- # It is not intended for manual editing.
3
- version = 4
4
-
5
- [[package]]
6
- name = "aho-corasick"
7
- version = "1.1.4"
8
- source = "registry+https://github.com/rust-lang/crates.io-index"
9
- checksum = "ddd31a130427c27518df266943a5308ed92d4b226cc639f5a8f1002816174301"
10
- dependencies = [
11
- "memchr",
12
- ]
13
-
14
- [[package]]
15
- name = "bindgen"
16
- version = "0.69.5"
17
- source = "registry+https://github.com/rust-lang/crates.io-index"
18
- checksum = "271383c67ccabffb7381723dea0672a673f292304fcb45c01cc648c7a8d58088"
19
- dependencies = [
20
- "bitflags",
21
- "cexpr",
22
- "clang-sys",
23
- "itertools",
24
- "lazy_static",
25
- "lazycell",
26
- "proc-macro2",
27
- "quote",
28
- "regex",
29
- "rustc-hash",
30
- "shlex",
31
- "syn",
32
- ]
33
-
34
- [[package]]
35
- name = "bitflags"
36
- version = "2.11.0"
37
- source = "registry+https://github.com/rust-lang/crates.io-index"
38
- checksum = "843867be96c8daad0d758b57df9392b6d8d271134fce549de6ce169ff98a92af"
39
-
40
- [[package]]
41
- name = "cexpr"
42
- version = "0.6.0"
43
- source = "registry+https://github.com/rust-lang/crates.io-index"
44
- checksum = "6fac387a98bb7c37292057cffc56d62ecb629900026402633ae9160df93a8766"
45
- dependencies = [
46
- "nom",
47
- ]
48
-
49
- [[package]]
50
- name = "cfg-if"
51
- version = "1.0.4"
52
- source = "registry+https://github.com/rust-lang/crates.io-index"
53
- checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801"
54
-
55
- [[package]]
56
- name = "clang-sys"
57
- version = "1.8.1"
58
- source = "registry+https://github.com/rust-lang/crates.io-index"
59
- checksum = "0b023947811758c97c59bf9d1c188fd619ad4718dcaa767947df1cadb14f39f4"
60
- dependencies = [
61
- "glob",
62
- "libc",
63
- "libloading",
64
- ]
65
-
66
- [[package]]
67
- name = "either"
68
- version = "1.15.0"
69
- source = "registry+https://github.com/rust-lang/crates.io-index"
70
- checksum = "48c757948c5ede0e46177b7add2e67155f70e33c07fea8284df6576da70b3719"
71
-
72
- [[package]]
73
- name = "glob"
74
- version = "0.3.3"
75
- source = "registry+https://github.com/rust-lang/crates.io-index"
76
- checksum = "0cc23270f6e1808e30a928bdc84dea0b9b4136a8bc82338574f23baf47bbd280"
77
-
78
- [[package]]
79
- name = "itertools"
80
- version = "0.12.1"
81
- source = "registry+https://github.com/rust-lang/crates.io-index"
82
- checksum = "ba291022dbbd398a455acf126c1e341954079855bc60dfdda641363bd6922569"
83
- dependencies = [
84
- "either",
85
- ]
86
-
87
- [[package]]
88
- name = "lazy_static"
89
- version = "1.5.0"
90
- source = "registry+https://github.com/rust-lang/crates.io-index"
91
- checksum = "bbd2bcb4c963f2ddae06a2efc7e9f3591312473c50c6685e1f298068316e66fe"
92
-
93
- [[package]]
94
- name = "lazycell"
95
- version = "1.3.0"
96
- source = "registry+https://github.com/rust-lang/crates.io-index"
97
- checksum = "830d08ce1d1d941e6b30645f1a0eb5643013d835ce3779a5fc208261dbe10f55"
98
-
99
- [[package]]
100
- name = "libc"
101
- version = "0.2.183"
102
- source = "registry+https://github.com/rust-lang/crates.io-index"
103
- checksum = "b5b646652bf6661599e1da8901b3b9522896f01e736bad5f723fe7a3a27f899d"
104
-
105
- [[package]]
106
- name = "libloading"
107
- version = "0.8.9"
108
- source = "registry+https://github.com/rust-lang/crates.io-index"
109
- checksum = "d7c4b02199fee7c5d21a5ae7d8cfa79a6ef5bb2fc834d6e9058e89c825efdc55"
110
- dependencies = [
111
- "cfg-if",
112
- "windows-link",
113
- ]
114
-
115
- [[package]]
116
- name = "lingua"
117
- version = "0.1.0"
118
- dependencies = [
119
- "magnus",
120
- ]
121
-
122
- [[package]]
123
- name = "magnus"
124
- version = "0.8.2"
125
- source = "registry+https://github.com/rust-lang/crates.io-index"
126
- checksum = "3b36a5b126bbe97eb0d02d07acfeb327036c6319fd816139a49824a83b7f9012"
127
- dependencies = [
128
- "magnus-macros",
129
- "rb-sys",
130
- "rb-sys-env",
131
- "seq-macro",
132
- ]
133
-
134
- [[package]]
135
- name = "magnus-macros"
136
- version = "0.8.0"
137
- source = "registry+https://github.com/rust-lang/crates.io-index"
138
- checksum = "47607461fd8e1513cb4f2076c197d8092d921a1ea75bd08af97398f593751892"
139
- dependencies = [
140
- "proc-macro2",
141
- "quote",
142
- "syn",
143
- ]
144
-
145
- [[package]]
146
- name = "memchr"
147
- version = "2.8.0"
148
- source = "registry+https://github.com/rust-lang/crates.io-index"
149
- checksum = "f8ca58f447f06ed17d5fc4043ce1b10dd205e060fb3ce5b979b8ed8e59ff3f79"
150
-
151
- [[package]]
152
- name = "minimal-lexical"
153
- version = "0.2.1"
154
- source = "registry+https://github.com/rust-lang/crates.io-index"
155
- checksum = "68354c5c6bd36d73ff3feceb05efa59b6acb7626617f4962be322a825e61f79a"
156
-
157
- [[package]]
158
- name = "nom"
159
- version = "7.1.3"
160
- source = "registry+https://github.com/rust-lang/crates.io-index"
161
- checksum = "d273983c5a657a70a3e8f2a01329822f3b8c8172b73826411a55751e404a0a4a"
162
- dependencies = [
163
- "memchr",
164
- "minimal-lexical",
165
- ]
166
-
167
- [[package]]
168
- name = "proc-macro2"
169
- version = "1.0.106"
170
- source = "registry+https://github.com/rust-lang/crates.io-index"
171
- checksum = "8fd00f0bb2e90d81d1044c2b32617f68fcb9fa3bb7640c23e9c748e53fb30934"
172
- dependencies = [
173
- "unicode-ident",
174
- ]
175
-
176
- [[package]]
177
- name = "quote"
178
- version = "1.0.45"
179
- source = "registry+https://github.com/rust-lang/crates.io-index"
180
- checksum = "41f2619966050689382d2b44f664f4bc593e129785a36d6ee376ddf37259b924"
181
- dependencies = [
182
- "proc-macro2",
183
- ]
184
-
185
- [[package]]
186
- name = "rb-sys"
187
- version = "0.9.124"
188
- source = "registry+https://github.com/rust-lang/crates.io-index"
189
- checksum = "c85c4188462601e2aa1469def389c17228566f82ea72f137ed096f21591bc489"
190
- dependencies = [
191
- "rb-sys-build",
192
- ]
193
-
194
- [[package]]
195
- name = "rb-sys-build"
196
- version = "0.9.124"
197
- source = "registry+https://github.com/rust-lang/crates.io-index"
198
- checksum = "568068db4102230882e6d4ae8de6632e224ca75fe5970f6e026a04e91ed635d3"
199
- dependencies = [
200
- "bindgen",
201
- "lazy_static",
202
- "proc-macro2",
203
- "quote",
204
- "regex",
205
- "shell-words",
206
- "syn",
207
- ]
208
-
209
- [[package]]
210
- name = "rb-sys-env"
211
- version = "0.2.3"
212
- source = "registry+https://github.com/rust-lang/crates.io-index"
213
- checksum = "cca7ad6a7e21e72151d56fe2495a259b5670e204c3adac41ee7ef676ea08117a"
214
-
215
- [[package]]
216
- name = "regex"
217
- version = "1.12.3"
218
- source = "registry+https://github.com/rust-lang/crates.io-index"
219
- checksum = "e10754a14b9137dd7b1e3e5b0493cc9171fdd105e0ab477f51b72e7f3ac0e276"
220
- dependencies = [
221
- "aho-corasick",
222
- "memchr",
223
- "regex-automata",
224
- "regex-syntax",
225
- ]
226
-
227
- [[package]]
228
- name = "regex-automata"
229
- version = "0.4.14"
230
- source = "registry+https://github.com/rust-lang/crates.io-index"
231
- checksum = "6e1dd4122fc1595e8162618945476892eefca7b88c52820e74af6262213cae8f"
232
- dependencies = [
233
- "aho-corasick",
234
- "memchr",
235
- "regex-syntax",
236
- ]
237
-
238
- [[package]]
239
- name = "regex-syntax"
240
- version = "0.8.10"
241
- source = "registry+https://github.com/rust-lang/crates.io-index"
242
- checksum = "dc897dd8d9e8bd1ed8cdad82b5966c3e0ecae09fb1907d58efaa013543185d0a"
243
-
244
- [[package]]
245
- name = "rustc-hash"
246
- version = "1.1.0"
247
- source = "registry+https://github.com/rust-lang/crates.io-index"
248
- checksum = "08d43f7aa6b08d49f382cde6a7982047c3426db949b1424bc4b7ec9ae12c6ce2"
249
-
250
- [[package]]
251
- name = "seq-macro"
252
- version = "0.3.6"
253
- source = "registry+https://github.com/rust-lang/crates.io-index"
254
- checksum = "1bc711410fbe7399f390ca1c3b60ad0f53f80e95c5eb935e52268a0e2cd49acc"
255
-
256
- [[package]]
257
- name = "shell-words"
258
- version = "1.1.1"
259
- source = "registry+https://github.com/rust-lang/crates.io-index"
260
- checksum = "dc6fe69c597f9c37bfeeeeeb33da3530379845f10be461a66d16d03eca2ded77"
261
-
262
- [[package]]
263
- name = "shlex"
264
- version = "1.3.0"
265
- source = "registry+https://github.com/rust-lang/crates.io-index"
266
- checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
267
-
268
- [[package]]
269
- name = "syn"
270
- version = "2.0.117"
271
- source = "registry+https://github.com/rust-lang/crates.io-index"
272
- checksum = "e665b8803e7b1d2a727f4023456bbbbe74da67099c585258af0ad9c5013b9b99"
273
- dependencies = [
274
- "proc-macro2",
275
- "quote",
276
- "unicode-ident",
277
- ]
278
-
279
- [[package]]
280
- name = "unicode-ident"
281
- version = "1.0.24"
282
- source = "registry+https://github.com/rust-lang/crates.io-index"
283
- checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75"
284
-
285
- [[package]]
286
- name = "windows-link"
287
- version = "0.2.1"
288
- source = "registry+https://github.com/rust-lang/crates.io-index"
289
- checksum = "f0805222e57f7521d6a62e36fa9163bc891acd422f971defe97d64e70d0a4fe5"