script_detector_2 0.3.0 → 0.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 9709f6c83f82a3bf7073bb8b9cfc95a1edea6885e0f596ef6e93f01a62c26dbb
-  data.tar.gz: 3ed583c8487617e9687b3c776116f0cc22140993ef9debf4f8542057e9f9f232
+  metadata.gz: 37ab1716845b98ca15a072e67cd900f5854dadd3c3641667fb5887c1626c4a85
+  data.tar.gz: 5142f341e40601f3d1fff211ff1fa566047f6353d0d3f6bc5062653827e759db
 SHA512:
-  metadata.gz: 5d17c19eee4868b540af844e08c95133415de8ccf0293dd208c11a29c14315b716c1563c45fd22081fbbf604147c837fa14bc98772a4103b2df080e4d09f89fa
-  data.tar.gz: 4a7894f23f49494f9debcafc967217ccb00549234014166f9fe4f1fe3d13b12b15fbe63eac426b164dfa763acbc9b4e15dfa8cd616de84720f1b2ea3249abfde
+  metadata.gz: 35b1771a4d8898d6ca02f38b4a016adc927600e7456b0a41ae515f88e85c846d8a41951ce78fa12c7a2851fc596a13ab48a3537dd97ff4579e8cd45d19b50ccf
+  data.tar.gz: ea6da32d1c4b9a10a4c04208fda4bee7bc6bad7d8ffa635f163c608e256160b4115fe3c1a8f4e7c9ec8b65f435ddca1fcb7af9f857a82042edd11457685d7424

data/.rubocop_todo.yml

@@ -1,22 +1,27 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config`
-# on 2021-10-11 07:56:31 UTC using RuboCop version 1.21.0.
+# on 2021-11-24 02:35:34 UTC using RuboCop version 1.23.0.
 # The point is for the user to remove these configuration records
 # one by one as the offenses are removed from the code base.
 # Note that changes in the inspected code, or installation of new
 # versions of RuboCop, may require this file to be generated again.
 
-# Offense count: 1
+# Offense count: 2
+# Configuration parameters: IgnoredMethods, CountRepeatedAttributes.
+Metrics/AbcSize:
+  Max: 20
+
+# Offense count: 2
 # Configuration parameters: IgnoredMethods.
 Metrics/CyclomaticComplexity:
-  Max: 10
+  Max: 13
 
 # Offense count: 2
 # Configuration parameters: CountComments, CountAsOne, ExcludedMethods, IgnoredMethods.
 Metrics/MethodLength:
-  Max: 14
+  Max: 15
 
 # Offense count: 1
 # Configuration parameters: IgnoredMethods.
 Metrics/PerceivedComplexity:
-  Max: 11
+  Max: 14

data/CHANGELOG.md

@@ -1,5 +1,10 @@
 ## [Unreleased]
 
+## [0.4.0] - 2021-11-24
+
+- Add `identify_scripts` method
+- Improve accuracy of `identify_script` method
+
 ## [0.3.0] - 2021-10-13
 
 - Add `kana?` and `hangul?` methods

data/Gemfile.lock

@@ -1,14 +1,14 @@
 PATH
   remote: .
   specs:
-    script_detector_2 (0.3.0)
+    script_detector_2 (0.4.0)
 
 GEM
   remote: https://rubygems.org/
   specs:
     ast (2.4.2)
     backport (1.2.0)
-    benchmark (0.1.1)
+    benchmark (0.2.0)
     byebug (11.1.3)
     diff-lcs (1.4.4)
     e2mmap (0.1.0)
@@ -23,14 +23,14 @@ GEM
     parallel (1.21.0)
     parser (3.0.2.0)
       ast (~> 2.4.1)
-    racc (1.5.2)
+    racc (1.6.0)
     rainbow (3.0.0)
     rake (13.0.6)
     regexp_parser (2.1.1)
-    reverse_markdown (2.0.0)
+    reverse_markdown (2.1.1)
       nokogiri
     rexml (3.2.5)
-    rubocop (1.22.1)
+    rubocop (1.23.0)
       parallel (~> 1.10)
       parser (>= 3.0.0.0)
       rainbow (>= 2.2.2, < 4.0)
@@ -39,11 +39,11 @@ GEM
       rubocop-ast (>= 1.12.0, < 2.0)
       ruby-progressbar (~> 1.7)
       unicode-display_width (>= 1.4.0, < 3.0)
-    rubocop-ast (1.12.0)
+    rubocop-ast (1.13.0)
       parser (>= 3.0.1.1)
     ruby-progressbar (1.11.0)
     rubyzip (2.3.2)
-    solargraph (0.44.0)
+    solargraph (0.44.2)
       backport (~> 1.2)
       benchmark
       bundler (>= 1.17.2)
@@ -76,4 +76,4 @@ DEPENDENCIES
   solargraph
 
 BUNDLED WITH
-   2.2.29
+   2.2.32

data/README.md

@@ -42,6 +42,7 @@ The main detection methods are:
 - `ScriptDetector2.simplified_chinese?`
 - `ScriptDetector2.traditional_chinese?`
 - `ScriptDetector2.identify_script`
+- `ScriptDetector2.identify_scripts`
 
 Regexp patterns are used to identify the script to which Han characters belong.
 These can be used directly as well:

data/lib/script_detector_2/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module ScriptDetector2
-  VERSION = '0.3.0'
+  VERSION = '0.4.0'
 end

data/lib/script_detector_2.rb

@@ -8,7 +8,7 @@ require_relative 'script_detector_2/string'
 module ScriptDetector2
   class << self
     # @param string [String]
-    # @return [Boolean]
+    # @return [Boolean] true if +string+ appears to be Japanese
     def japanese?(string)
       return true if kana?(string)
       return false if hangul?(string)
@@ -20,13 +20,14 @@ module ScriptDetector2
     end
 
     # @param string [String]
-    # @return [Boolean]
+    # @return [Boolean] true if +string+ contains Hiragana or Katakana
     def kana?(string)
       /[\p{Hiragana}\p{Katakana}]/.match?(string)
     end
 
     # @param string [String]
-    # @return [Boolean]
+    # @return [Boolean] true if +string+ appears to be Chinese (either
+    #   Simplified or Traditional)
     def chinese?(string)
       return false if string =~ /[\p{Hiragana}\p{Katakana}\p{Hangul}]/
 
@@ -34,7 +35,7 @@ module ScriptDetector2
     end
 
     # @param string [String]
-    # @return [Boolean]
+    # @return [Boolean] true if +string+ appears to be Simplified Chinese
     def simplified_chinese?(string)
       return false if string =~ /[\p{Hiragana}\p{Katakana}\p{Hangul}]/
 
@@ -45,7 +46,7 @@ module ScriptDetector2
     end
 
     # @param string [String]
-    # @return [Boolean]
+    # @return [Boolean] true if +string+ appears to be Traditional Chinese
     def traditional_chinese?(string)
       return false if string =~ /[\p{Hiragana}\p{Katakana}\p{Hangul}]/
 
@@ -56,7 +57,7 @@ module ScriptDetector2
     end
 
     # @param string [String]
-    # @return [Boolean]
+    # @return [Boolean] true if +string+ appears to be Korean
     def korean?(string)
       return true if hangul?(string)
       return false if kana?(string)
@@ -68,11 +69,24 @@ module ScriptDetector2
     end
 
     # @param string [String]
-    # @return [Boolean]
+    # @return [Boolean] true if +string+ contains Hangul
     def hangul?(string)
       /\p{Hangul}/.match?(string)
     end
 
+    # Make a best-effort attempt to guess the singular script of +string+.
+    # Result is a symbol representing one of the scripts defined by ISO 15924,
+    # namely one of:
+    # - Hans (Simplified Chinese)
+    # - Hant (Traditional Chinese)
+    # - Hani (Unspecified Han)
+    # - Jpan (Japanese: Han, Hiragana, Katakana)
+    # - Kore (Korean: Hangul, Han)
+    # - Zyyy (Undetermined)
+    #
+    # Note that this is likely to give poor results for very short strings,
+    # which are often inherently ambiguous.
+    #
     # @param string [String]
     # @return [Symbol]
     def identify_script(string)
@@ -81,15 +95,50 @@ module ScriptDetector2
 
       is_hant = traditional_chinese?(string)
       is_hans = simplified_chinese?(string)
-      if is_hant && is_hans then :Hani
-      elsif is_hans then :Hans
+      return :Hani if is_hant && is_hans
+
+      is_japanese = japanese?(string)
+      return :Hani if is_japanese && (is_hant || is_hans)
+
+      # At this point we have determined that the string does not contain
+      # Hangul; for such a string to be Korean would be unusual. Allowing Korean
+      # to dilute the result to Hani is going to be a loss on average, so we
+      # don't handle it like Japanese above.
+
+      if is_hans then :Hans
       elsif is_hant then :Hant
-      elsif japanese?(string) then :Jpan
+      elsif is_japanese then :Jpan
       elsif korean?(string) then :Kore
-      elsif chinese?(string) then :Hani # rubocop:disable Lint/DuplicateBranch
+      elsif chinese?(string) then :Hani
       else
         :Zyyy
       end
     end
+
+    # Identify all CJK scripts represented in +string+. Result is a list of symbols
+    # representing scripts defined by ISO 15924, namely one or more of:
+    # - Hans (Simplified Chinese)
+    # - Hant (Traditional Chinese)
+    # - Hani (Unspecified Chinese)
+    # - Jpan (Japanese: Han, Hiragana, Katakana)
+    # - Kore (Korean: Hangul, Han)
+    # - Zyyy (Undetermined)
+    #
+    # This method does not attempt to identify other scripts such as Latn.
+    #
+    # @param string [String]
+    # @return [Array<Symbol>]
+    def identify_scripts(string)
+      result = []
+
+      result << :Hans if simplified_chinese?(string)
+      result << :Hant if traditional_chinese?(string)
+      result << :Jpan if japanese?(string)
+      result << :Kore if korean?(string)
+      result << :Hani if chinese?(string) && result.empty?
+      result << :Zyyy if result.empty?
+
+      result
+    end
   end
 end

data/script_detector_2.gemspec

@@ -17,6 +17,7 @@ Gem::Specification.new do |spec|
 
   spec.metadata['homepage_uri'] = spec.homepage
   spec.metadata['source_code_uri'] = 'https://github.com/amake/script_detector_2.git'
+  spec.metadata['rubygems_mfa_required'] = 'true'
 
   # Specify which files should be added to the gem when it is released.
   # The `git ls-files -z` loads the files in the RubyGem that have been added into git.

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: script_detector_2
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 0.4.0
 platform: ruby
 authors:
 - Aaron Madlon-Kay
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2021-10-13 00:00:00.000000000 Z
+date: 2021-11-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: byebug
@@ -100,6 +100,7 @@ licenses:
 metadata:
   homepage_uri: https://github.com/amake/script_detector_2
   source_code_uri: https://github.com/amake/script_detector_2.git
+  rubygems_mfa_required: 'true'
 post_install_message: 
 rdoc_options: []
 require_paths: