what_you_say 0.4.3-x86_64-linux → 0.5.0-x86_64-linux

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ae20a6009ad491c7db47d8525414ff9980f412ffd54ef29ab68839fdfabf4f56
-  data.tar.gz: e66734381fbf502ae268302a9451d2995d620fa09ffb4222dffc0f2a0dd3c592
+  metadata.gz: 8099bd3e732c8a2326f182380767e936309963f8a342aaf1c8e818c71a6c7b68
+  data.tar.gz: ba4478637f8ebf1352a46e408a594e7bfc5eca6b11965431baec76e70d855fd1
 SHA512:
-  metadata.gz: d0903c017c39484428a097b20161e2a3141197bb9cf4abe6b70693fece3c40ee6d85b66fab7008f986fea4bd71605250eabda8083cc4fd837e5cab2ae7c6e467
-  data.tar.gz: b56c30eb6f4933f49c65eb47eac76686ea616c363f1b78a36b9f77b44a899a72db3ec9c87889f2e02af0428a6f374c669bf48289af720fc052c0229e9377eef5
+  metadata.gz: bbb5e94b91406fcb0d583ad0813ba8e2096804cebc242ae2e1aed2021f4a8a85a452a06131558cb64dde4cd8edaeaebab228a691fb88d80274e451e833cfc6f1
+  data.tar.gz: 075d4c7f99d809ef438c81864358242b93fbc6bdcd951908f155c07a9cd1a2ab6e458aefa8c39f9b1bc60f62e1f1092ee68dc6f52629d241f28235bb356700e9

data/README.md

@@ -1,14 +1,12 @@
 # WhatYouSay
 
-Quick and easy natural language detection wrapping the [Whatlang Rust crate](https://github.com/greyblake/whatlang-rs). Instantly identify the source language of a piece of text.
+Quick and easy natural language detection wrapping the [lingua-rs Rust crate](https://github.com/pemistahl/lingua-rs). Instantly identify the source language of a piece of text.
 
 ![What you say!!](https://user-images.githubusercontent.com/64050/224237944-ceb2570c-d544-474a-8c91-41433efdee43.png)
 
-- Supports [69 languages](https://github.com/greyblake/whatlang-rs/blob/master/SUPPORTED_LANGUAGES.md) (nice!)
+- Supports [75+ languages](https://github.com/pemistahl/lingua-rs/tree/main#3-which-languages-are-supported)
 - Core library is written in Rust; this is a Ruby wrapper to it
 - Lightweight, fast, and simple
-- Recognizes not only a language, but also a script (Latin, Cyrillic, etc)
-- Provides reliability information
 
 ## Installation
 
@@ -22,25 +20,52 @@ If bundler is not being used to manage dependencies, install the gem by executin
 
 ## Usage
 
-The method to call is `_?`. Why? Because. Pass in the text whose language you want to detect:
+The method to call is `detect_language`.
+
+Pass in the text whose language you want to detect:
 
 ```ruby
 require "what_you_say"
 
 text = "Ĉu vi ne volas eklerni Esperanton? Bonvolu! Estas unu de la plej bonaj aferoj!"
 
-result = WhatYouSay._?(text)
+result = WhatYouSay.new.detect_language(text)
 
-assert_equal("epo", result.code)
-assert_equal("esperanto", result.eng_name)
+assert_equal("epo", result.lang.code)
+assert_equal("esperanto", result.lang.eng_name)
 ```
 
 You also have to opportunity to `inspect` some output:
 
 ```ruby
 text = "Եվ ահա ես ստանում եմ մի զանգ պատահական տղայից"
-WhatYouSay._?(text).inspect
-#=> #<WhatYouSay::Lang code="hye" eng_name="Armenian">
+WhatYouSay.new.detect_language(text).inspect
+#=> #<WhatYouSay::Lang code="hye" eng_name="armenian">
+```
+
+Not everything in life is perfect, and neither is this lib. Sometimes language detection will be wildly mistaken. You
+can attempt to correct this by passing in an `allowlist` of supported languages:
+
+```ruby
+text = "สวัสดี Rágis hello"
+result = WhatYouSay.new.detect_language(text)
+
+assert_equal("spanish", result.eng_name)
+
+result = WhatYouSay.new(allowlist: ["English", "Thai"]).detect_language(text)
+
+assert_equal("eng", result.code)
+```
+
+If a language truly cannot be detected, the `Unknown` language type is returned:
+
+```ruby
+text = "日本語"
+
+result = WhatYouSay.new(allowlist: ["English", "Thai"]).detect_language(text)
+
+assert_equal("???", result.code)
+assert_equal("unknown", result.eng_name)
 ```
 
 ## Development

data/lib/what_you_say/lang.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-module WhatYouSay
+class WhatYouSay
   class Lang
   end
 end

data/lib/what_you_say/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
-module WhatYouSay
-  VERSION = "0.4.3"
+class WhatYouSay
+  VERSION = "0.5.0"
 end

data/lib/what_you_say.rb

@@ -9,13 +9,11 @@ if ENV.fetch("DEBUG", false)
   require "debug"
 end
 
-module WhatYouSay
-  class << self
-    def _?(text)
-      raise TypeError, "text must be a String; got a #{text.class}!" unless text.is_a?(String)
-      raise TypeError, "text must be UTF-8 encoded; got #{text.encoding}!" unless text.encoding.name == "UTF-8"
+class WhatYouSay
+  def detect_language(text)
+    raise TypeError, "text must be a String; got a #{text.class}!" unless text.is_a?(String)
+    raise TypeError, "text must be UTF-8 encoded; got #{text.encoding}!" unless text.encoding.name == "UTF-8"
 
-      detect(text, options: {})
-    end
+    detect_text(text)
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: what_you_say
 version: !ruby/object:Gem::Version
-  version: 0.4.3
+  version: 0.5.0
 platform: x86_64-linux
 authors:
 - Garen J. Torikian
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2023-04-11 00:00:00.000000000 Z
+date: 2023-04-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -38,8 +38,8 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '1.2'
-description: Natural language detectio with a focus on simplicity and performance.
-  Currently wraps the whatlang Rust crate.
+description: Natural language detection with a focus on simplicity and performance.
+  Currently wraps the lingua-rs Rust crate.
 email:
 - gjtorikian@users.noreply.github.com
 executables: []