lingua_rs 0.4.1 → 0.4.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: bd0dba860ee235a6acfc46afb3ba851ec08303df9499f403e47624c74b9396e7
-  data.tar.gz: b3d9faca1f0f12fb7abee0643b94f1f494ef02e6b4f2c92846fa88e94d503904
+  metadata.gz: 4c9b82b89f03f11a0675e53ffd21161a0b79d3f66e8ef4bdbdb96179439e7dd3
+  data.tar.gz: 44e5fba6b4cf30e1f651613e3f3631107d9823c831535622d5884dd5aae464ad
 SHA512:
-  metadata.gz: 2cae21715d81d650c71df5d55b18fb7b09eb86bcfe1356e5ace3b526a48e9ff31be39d852ee43abe342dffed711c7ea08ad3a9342702960b04a864a674df6068
-  data.tar.gz: 221eb0c62f4b7158d5c95b4d7c28490a2bcabc3f4cffe64914bea62c413c0d35fc8ceab1a6b6dc81a4750e75f8d7deac522bab1d0aa97b5c02cfd7d49e9eab40
+  metadata.gz: 6d681afb8de476d7f7da3ac14ac000ee51d7ef301f01eb22e033a3b4885f4d0c7e7dac6713fbfe56ee7d4bd5341011d9fe7abf329f5e8eb8b38b5ffb54d870bd
+  data.tar.gz: 7d3dc5c3c73bf30d11e8ddca1c92e49869bb87a98fef66865dc7ea35376294c08858633dc981da8f8a33c5a6f29c10b8fc62d79fb51457161e7b6efddd91dc12

data/README.md

@@ -1,9 +1,9 @@
 # LinguaRs
 
 [![CI](https://github.com/kochka/lingua_rs/actions/workflows/ci.yml/badge.svg)](https://github.com/kochka/lingua_rs/actions/workflows/ci.yml)
-[![Gem Version](https://badge.fury.io/rb/lingua_rs.svg)](https://badge.fury.io/rb/lingua_rs)
-[![Downloads](https://img.shields.io/gem/dt/lingua_rs)](https://rubygems.org/gems/lingua_rs)
-[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
+[![Gem Version](https://img.shields.io/gem/v/lingua_rs?color=cc342d)](https://rubygems.org/gems/lingua_rs)
+[![Downloads](https://img.shields.io/gem/dt/lingua_rs?color=0969da)](https://rubygems.org/gems/lingua_rs)
+[![License: MIT](https://img.shields.io/badge/License-MIT-6e7781.svg)](https://opensource.org/licenses/MIT)
 
 A Ruby gem wrapping the [Lingua](https://github.com/pemistahl/lingua-rs) Rust library for language detection.
 
@@ -213,21 +213,41 @@ end
 
 ## Optimization: selecting languages
 
-By default, all 75 languages are compiled into the native extension (~278 MB). If you only need a subset, set the `LINGUA_LANGUAGES` environment variable before installing to reduce binary size and improve detection speed:
+By default, all 75 languages are compiled into the native extension (~278 MB). If you only need a subset, select languages at build time to reduce binary size and improve detection speed.
+
+### Build option
+
+Use `--with-lingua-languages` to select languages. With Bundler you can persist the setting so it applies to every future `bundle install`:
 
 ```bash
-LINGUA_LANGUAGES=core bundle install
+bundle config set build.lingua_rs --with-lingua-languages=core
+bundle install
 ```
 
 This compiles only the selected language models (~29 MB for the `core` bundle). You can use individual language names or predefined bundles, and you can mix both in the same build.
 
-This also works with `gem install`, for example:
+The setting is saved in your local Bundler config (`~/.bundle/config` or `.bundle/config`) and is reused automatically on subsequent installs. To change it later:
 
 ```bash
-LINGUA_LANGUAGES=french,english,german gem install lingua_rs
+bundle config set build.lingua_rs --with-lingua-languages=europe_common,japanese
+bundle install
 ```
 
-Available bundles:
+To remove it and go back to all languages:
+
+```bash
+bundle config unset build.lingua_rs
+bundle install
+```
+
+This also works with `gem install`:
+
+```bash
+gem install lingua_rs -- --with-lingua-languages=french,english,german
+```
+
+
+### Available languages and bundles
 
 | Bundle | Languages |
 | --- | --- |
@@ -242,13 +262,17 @@ Available bundles:
 Examples:
 
 ```bash
-LINGUA_LANGUAGES=core bundle install
-LINGUA_LANGUAGES=europe_common,polish bundle install
-LINGUA_LANGUAGES=east_asia,english bundle install
+bundle config set build.lingua_rs --with-lingua-languages=core
+bundle config set build.lingua_rs --with-lingua-languages=europe_common,polish
+bundle config set build.lingua_rs --with-lingua-languages=east_asia,english
 ```
 
 Language and bundle names must match the Cargo features defined by this gem (lowercase, e.g. `french`, `english`, `german`, `core`, `europe_common`).
 
+Supported languages (from [Lingua Rust's official list](https://github.com/pemistahl/lingua-rs?tab=readme-ov-file#3-which-languages-are-supported)):
+
+`afrikaans`, `albanian`, `arabic`, `armenian`, `azerbaijani`, `basque`, `belarusian`, `bengali`, `bokmal`, `bosnian`, `bulgarian`, `catalan`, `chinese`, `croatian`, `czech`, `danish`, `dutch`, `english`, `esperanto`, `estonian`, `finnish`, `french`, `ganda`, `georgian`, `german`, `greek`, `gujarati`, `hebrew`, `hindi`, `hungarian`, `icelandic`, `indonesian`, `irish`, `italian`, `japanese`, `kazakh`, `korean`, `latin`, `latvian`, `lithuanian`, `macedonian`, `malay`, `maori`, `marathi`, `mongolian`, `nynorsk`, `persian`, `polish`, `portuguese`, `punjabi`, `romanian`, `russian`, `serbian`, `shona`, `slovak`, `slovene`, `somali`, `sotho`, `spanish`, `swahili`, `swedish`, `tagalog`, `tamil`, `telugu`, `thai`, `tsonga`, `tswana`, `turkish`, `ukrainian`, `urdu`, `vietnamese`, `welsh`, `xhosa`, `yoruba`, `zulu`
+
 ## Development
 
 After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake compile` to build the native extension and `rake test` to run the tests.

data/ext/lingua/extconf.rb

@@ -4,8 +4,11 @@ require 'mkmf'
 require 'rb_sys/mkmf'
 
 # Allow users to select specific languages to reduce binary size.
+# Supports both --with-lingua-languages build option and LINGUA_LANGUAGES env var.
+# Example: bundle config set build.lingua_rs --with-lingua-languages=core
 # Example: LINGUA_LANGUAGES=french,english,german bundle install
-languages = ENV.fetch('LINGUA_LANGUAGES', '').split(',').map { |lang| lang.strip.downcase }
+selection = with_config('lingua-languages', nil) || ENV.fetch('LINGUA_LANGUAGES', '')
+languages = selection.to_s.split(',').map { |lang| lang.strip.downcase }.reject(&:empty?)
 
 create_rust_makefile('lingua/lingua') do |r|
   unless languages.empty?

data/ext/lingua/src/detector.rs

@@ -122,6 +122,12 @@ pub fn build_detector_from_options(
             })?;
             languages.push(lang);
         }
+        if languages.is_empty() {
+            return Err(magnus::Error::new(
+                ruby.exception_arg_error(),
+                "languages must contain at least 1 language",
+            ));
+        }
         LanguageDetectorBuilder::from_languages(&languages)
     } else {
         LanguageDetectorBuilder::from_all_languages()
@@ -129,6 +135,12 @@ pub fn build_detector_from_options(
 
     if let Some(opts) = options {
         if let Some(dist) = fetch_option::<f64>(ruby, opts, "minimum_relative_distance") {
+            if !(0.0..=0.99).contains(&dist) {
+                return Err(magnus::Error::new(
+                    ruby.exception_arg_error(),
+                    "minimum_relative_distance must be between 0.0 and 0.99",
+                ));
+            }
             builder.with_minimum_relative_distance(dist);
         }
         if fetch_option::<bool>(ruby, opts, "is_every_language_model_preloaded").unwrap_or(false) {

data/lib/lingua/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Lingua
-  VERSION = '0.4.1'
+  VERSION = '0.4.3'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: lingua_rs
 version: !ruby/object:Gem::Version
-  version: 0.4.1
+  version: 0.4.3
 platform: ruby
 authors:
 - Sébastien Vrillaud
@@ -37,8 +37,9 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: 1.3.0
-description: Native Ruby bindings for the Lingua Rust library. Detects languages with
-  confidence scores, ISO 639-1/639-3 support, and configurable accuracy modes.
+description: Native Ruby bindings for the Lingua Rust library, bringing highly accurate
+  language detection for short text and mixed-language text to Ruby, with confidence
+  scores and ISO 639-1/639-3 language codes.
 email:
 - kochka@gmail.com
 executables: []
@@ -86,5 +87,5 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements: []
 rubygems_version: 3.6.9
 specification_version: 4
-summary: Fast language detection for Ruby, powered by Lingua (Rust).
+summary: High-accuracy language detection powered by Lingua (Rust).
 test_files: []