what_you_say 0.4.3-arm64-darwin → 0.5.0-arm64-darwin

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 3842c012e3f3b3b19547b5ada41a64ddf57382ec18e1adb20293743edc5d51ca
-  data.tar.gz: feb79661d5dcba5d5e10aa7889eba503d6f6033e26e48ab1ffd6a7638f5ff48e
+  metadata.gz: 7cf702b1e0e1a7b4762e87660ca54df69c5ce8663cdc44a88af883e5847b8335
+  data.tar.gz: f6d915f445f334dc2bf328edec7bce398e4c32409253e0d08267f464054dc7fb
 SHA512:
-  metadata.gz: 634c2569a2f3247f0e1cec8bc19cb6a650a20194e1dd9e6f204832112396a250e0450dc5a57a2100455cc745cab631fd722f0428f30e83b2732672705dc7055c
-  data.tar.gz: 7310c7028255564e61528b0298596bfffb5acf6f6cc43f7ee6bb287b86148380c1bc8baeba6ceeae6e2654e0af366cec66ebb0ec56f11005c2872f769b393ffe
+  metadata.gz: 63ba3059d01bbb7c346223cb1b188e1c2e1d1f9651e15fbadff9c76b2ff1ec2b7a85d85083d91b9de3fcb9905f0d2de7548805ca95e06cbc3fca009ccc1a04b6
+  data.tar.gz: 0b2301e50dd3dd7ee6f5f58aeb2d9fcf5d5820268e63bf99ba25b84786eed01cd6b2437acf2aedfb7f8d4aa48e2dfff7b4e8c6ddfef05aad8a76ee1a01170f3b

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: arm64-darwin
 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: []