medieval_latina 1.3.1 → 2.0.0

data/lib/medieval_latina/initializer.rb

@@ -0,0 +1,3 @@
+require "i18n"
+
+I18n.config.available_locales = :en

data/lib/medieval_latina/version.rb

@@ -1,3 +1,3 @@
 class MedievalLatina
-  VERSION = "1.3.1".freeze
+  VERSION = "2.0.0".freeze
 end

data/lib/medieval_latina.rb

@@ -1,22 +1,39 @@
 require "medieval_latina/dictionary"
+require "medieval_latina/initializer"
 require "medieval_latina/version"
 require "set"
 
 class MedievalLatina
   def self.[](text)
-    prepare_text(text).map do |word|
-      DICTIONARY[word] || new(word).call
-    end.join(" ")
+    prepared_words = prepare_text(text).map do |string|
+      if word?(string)
+        metadata = DICTIONARY.fetch(string, {})
+
+        if metadata.key?(:pronunciation)
+          metadata[:pronunciation]
+        else
+          new(string).call
+        end
+      else
+        string
+      end
+    end
+
+    rejoin_words(prepared_words)
   end
 
   def self.prepare_text(text)
-    text.split(" ").map do |word|
-      prepare_word(word)
+    text.scan(/[\p{Alnum}'-]+|[[:punct:]]+/).map do |string|
+      if word?(string)
+        prepare_word(string)
+      else
+        string
+      end
     end
   end
 
   def self.prepare_word(word)
-    word.gsub(/\W+/, " ").strip.downcase
+    word.gsub(/\P{Alnum}+/, " ").strip.downcase
   end
 
   def self.adjective?(word)
@@ -47,17 +64,30 @@ class MedievalLatina
     NOUNS
   end
 
+  def self.rejoin_words(array)
+    array
+      .join(" ")
+      .gsub(/ +?,/, ",")
+      .gsub(/ +?;/, ";")
+      .gsub(/ +?\./, ".")
+      .gsub(/ +?\?/, "?")
+  end
+
   def self.verbs
     VERBS
   end
 
+  def self.word?(string)
+    string.match?(/\w/)
+  end
+
   def self.words
     ADJECTIVES | ADVERBS | Set.new(DICTIONARY.keys) | NOUNS | VERBS
   end
 
   def initialize(word)
     @index = 0
-    @word = word.downcase
+    @word = I18n.transliterate(word.downcase)
   end
 
   def call
@@ -123,7 +153,7 @@ class MedievalLatina
 
     def initialize(text, index)
       @character = text[index]
-      @rest = text[index + 1..-1].chars.join
+      @rest = text[index + 1..].chars.join
     end
 
     def to_team
@@ -132,4 +162,13 @@ class MedievalLatina
   end
 
   class Error < StandardError; end
+
+  DICTIONARY = FREQUENCY_LIST.each_with_object({}) do |(word, metadata), hash|
+    hash[word] = metadata
+
+    sanitized_word = I18n.transliterate(word)
+    unless hash.key?(sanitized_word)
+      hash[sanitized_word] = metadata
+    end
+  end
 end

data/medieval_latina.gemspec

@@ -15,7 +15,7 @@ Gem::Specification.new do |spec|
   spec.description = description
   spec.homepage = "https://github.com/jaysonvirissimo/medieval_latina"
   spec.license = "MIT"
-  spec.required_ruby_version = Gem::Requirement.new(">= 2.6.0")
+  spec.required_ruby_version = Gem::Requirement.new(">= 2.7.0")
   spec.metadata["allowed_push_host"] = "https://rubygems.org/"
   spec.metadata["homepage_uri"] = spec.homepage
   spec.metadata["source_code_uri"] = github_uri
@@ -28,4 +28,5 @@ Gem::Specification.new do |spec|
   spec.bindir = "exe"
   spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ["lib"]
+  spec.add_dependency "i18n"
 end

metadata

@@ -1,15 +1,29 @@
 --- !ruby/object:Gem::Specification
 name: medieval_latina
 version: !ruby/object:Gem::Version
-  version: 1.3.1
+  version: 2.0.0
 platform: ruby
 authors:
 - Jayson Virissimo
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2022-12-27 00:00:00.000000000 Z
-dependencies: []
+date: 2023-08-20 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: i18n
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 description: |
   There are good text-to-speech engines for English and classical Latin, but none for medieval Latin.
   MedievalLatina converts Latin text to a kind of phonetic spelling that can be read by English text-to-speech engines.
@@ -22,6 +36,7 @@ files:
 - ".github/workflows/tests.yml"
 - ".gitignore"
 - ".rspec"
+- ".standard.yml"
 - ".tool-versions"
 - Gemfile
 - Gemfile.lock
@@ -32,6 +47,7 @@ files:
 - bin/setup
 - lib/medieval_latina.rb
 - lib/medieval_latina/dictionary.rb
+- lib/medieval_latina/initializer.rb
 - lib/medieval_latina/version.rb
 - medieval_latina.gemspec
 homepage: https://github.com/jaysonvirissimo/medieval_latina
@@ -50,7 +66,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 2.6.0
+      version: 2.7.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="