medieval_latina 3.1.2 → 3.2.0

data/lexicons/Latin08.pls

@@ -1,132 +1,4 @@
 <lexicon version='1.0' xmlns='http://www.w3.org/2005/01/pronunciation-lexicon' alphabet='ipa' xml:lang='en-US'>
-  <lexeme>
-    <grapheme>
-      conscius
-    </grapheme>
-    <phoneme>
-      ˈkɔnskɪʊs
-    </phoneme>
-  </lexeme>
-  <lexeme>
-    <grapheme>
-      crudelis
-    </grapheme>
-    <phoneme>
-      ˈkrudɛlɪs
-    </phoneme>
-  </lexeme>
-  <lexeme>
-    <grapheme>
-      cupidus
-    </grapheme>
-    <phoneme>
-      ˈkupɪdʊs
-    </phoneme>
-  </lexeme>
-  <lexeme>
-    <grapheme>
-      demens
-    </grapheme>
-    <phoneme>
-      ˈdɛmɛns
-    </phoneme>
-  </lexeme>
-  <lexeme>
-    <grapheme>
-      desidiosus
-    </grapheme>
-    <phoneme>
-      dɛsɪˈdjɔsʊs
-    </phoneme>
-  </lexeme>
-  <lexeme>
-    <grapheme>
-      dignus
-    </grapheme>
-    <phoneme>
-      ˈdɪɲnʊs
-    </phoneme>
-  </lexeme>
-  <lexeme>
-    <grapheme>
-      doctus
-    </grapheme>
-    <phoneme>
-      ˈdɔktʊs
-    </phoneme>
-  </lexeme>
-  <lexeme>
-    <grapheme>
-      eloquens
-    </grapheme>
-    <phoneme>
-      ɛˈlɔkwɛns
-    </phoneme>
-  </lexeme>
-  <lexeme>
-    <grapheme>
-      eximius
-    </grapheme>
-    <phoneme>
-      ɛkˈsɪmɪʊs
-    </phoneme>
-  </lexeme>
-  <lexeme>
-    <grapheme>
-      fortunatus
-    </grapheme>
-    <phoneme>
-      fɔrtʊˈnatʊs
-    </phoneme>
-  </lexeme>
-  <lexeme>
-    <grapheme>
-      humilis
-    </grapheme>
-    <phoneme>
-      ˈhʊmɪlɪs
-    </phoneme>
-  </lexeme>
-  <lexeme>
-    <grapheme>
-      immortalis
-    </grapheme>
-    <phoneme>
-      ɪmˈmɔrtalɪs
-    </phoneme>
-  </lexeme>
-  <lexeme>
-    <grapheme>
-      inanis
-    </grapheme>
-    <phoneme>
-      ɪˈnanɪs
-    </phoneme>
-  </lexeme>
-  <lexeme>
-    <grapheme>
-      incertus
-    </grapheme>
-    <phoneme>
-      ɪnˈkɛrtʊs
-    </phoneme>
-  </lexeme>
-  <lexeme>
-    <grapheme>
-      infirmus
-    </grapheme>
-    <phoneme>
-      ɪnˈfɪrmʊs
-    </phoneme>
-  </lexeme>
-  <lexeme>
-    <grapheme>
-      informis
-    </grapheme>
-    <phoneme>
-      ɪnˈfɔrmɪs
-    </phoneme>
-  </lexeme>
   <lexeme>
     <grapheme>
       iniustus
@@ -2175,36 +2047,4 @@
       uˈsur.po
     </phoneme>
   </lexeme>
-  <lexeme>
-    <grapheme>
-      vagor
-    </grapheme>
-    <phoneme>
-      ˈva.gor
-    </phoneme>
-  </lexeme>
-  <lexeme>
-    <grapheme>
-      versor
-    </grapheme>
-    <phoneme>
-      ˈver.sor
-    </phoneme>
-  </lexeme>
-  <lexeme>
-    <grapheme>
-      verto
-    </grapheme>
-    <phoneme>
-      ˈver.to
-    </phoneme>
-  </lexeme>
-  <lexeme>
-    <grapheme>
-      vigilo
-    </grapheme>
-    <phoneme>
-      viˈdʒi.lo
-    </phoneme>
-  </lexeme>
 </lexicon>

data/lexicons/Latin09.pls

@@ -1,4 +1,36 @@
 <lexicon version='1.0' xmlns='http://www.w3.org/2005/01/pronunciation-lexicon' alphabet='ipa' xml:lang='en-US'>
+  <lexeme>
+    <grapheme>
+      vagor
+    </grapheme>
+    <phoneme>
+      ˈva.gor
+    </phoneme>
+  </lexeme>
+  <lexeme>
+    <grapheme>
+      versor
+    </grapheme>
+    <phoneme>
+      ˈver.sor
+    </phoneme>
+  </lexeme>
+  <lexeme>
+    <grapheme>
+      verto
+    </grapheme>
+    <phoneme>
+      ˈver.to
+    </phoneme>
+  </lexeme>
+  <lexeme>
+    <grapheme>
+      vigilo
+    </grapheme>
+    <phoneme>
+      viˈdʒi.lo
+    </phoneme>
+  </lexeme>
   <lexeme>
     <grapheme>
       vulnero
@@ -7,4 +39,12 @@
       ˈvul.ne.ro
     </phoneme>
   </lexeme>
+  <lexeme>
+    <grapheme>
+      caelis
+    </grapheme>
+    <phoneme>
+      tʃɛlis
+    </phoneme>
+  </lexeme>
 </lexicon>

data/lib/medieval_latina/lexicon_builder.rb

@@ -5,13 +5,14 @@ class MedievalLatina
   class LexiconBuilder
     include REXML
 
-    def initialize(words)
+    def initialize(words, lang: "en-US")
       @document = Document.new
       @words = words
+      @lang = lang
     end
 
     def call
-      document.add_element "lexicon", SPECIFICATION
+      document.add_element "lexicon", SPECIFICATION.merge("xml:lang" => lang)
 
       words.each do |word, pronunciation|
         lexeme = Element.new("lexeme")
@@ -32,13 +33,12 @@ class MedievalLatina
 
     private
 
-    attr_reader :document, :words
+    attr_reader :document, :words, :lang
 
     SPECIFICATION = {
       "version" => "1.0",
       "xmlns" => "http://www.w3.org/2005/01/pronunciation-lexicon",
-      "alphabet" => "ipa",
-      "xml:lang" => "en-US"
+      "alphabet" => "ipa"
     }.freeze
   end
 end

data/lib/medieval_latina/version.rb

@@ -1,3 +1,3 @@
 class MedievalLatina
-  VERSION = "3.1.2".freeze
+  VERSION = "3.2.0".freeze
 end

data/lib/medieval_latina.rb

@@ -8,7 +8,7 @@ class MedievalLatina
   def self.[](text)
     prepared_words = prepare_text(text).map do |string|
       if word?(string)
-        metadata = DICTIONARY.fetch(string, {})
+        metadata = entry_for(string) || {}
 
         if metadata.key?("pronunciation")
           metadata["pronunciation"]
@@ -46,20 +46,31 @@ class MedievalLatina
     word.gsub(/\P{Alnum}+/, " ").strip.downcase
   end
 
+  # Exact spelling first, then a macron-stripped fallback.
+  def self.entry_for(word)
+    key = word.to_s.downcase
+    DICTIONARY[key] || NORMALIZED[I18n.transliterate(key)]
+  end
+
   def self.adjective?(word)
-    adjectives.key?(prepare_word(word))
+    part?(word, "Adjective")
   end
 
   def self.adverb?(word)
-    adverbs.key?(prepare_word(word))
+    part?(word, "Adverb")
   end
 
   def self.noun?(word)
-    nouns.key?(prepare_word(word))
+    part?(word, "Noun")
   end
 
   def self.verb?(word)
-    verbs.key?(prepare_word(word))
+    part?(word, "Verb")
+  end
+
+  def self.part?(word, part)
+    entry = entry_for(prepare_word(word))
+    !entry.nil? && entry["part"] == part
   end
 
   def self.adjectives
@@ -82,7 +93,7 @@ class MedievalLatina
 
   def self.pronunciations_for(words)
     words.map(&:downcase).each_with_object({}) do |word, hash|
-      metadata = DICTIONARY[word]
+      metadata = entry_for(word)
 
       if metadata && metadata["ipa"]
         hash[word] = metadata["ipa"]
@@ -200,12 +211,13 @@ class MedievalLatina
 
   class Error < StandardError; end
 
-  DICTIONARY = dictionary.each_with_object({}) do |(word, metadata), hash|
-    hash[word] = metadata
+  DICTIONARY = dictionary
 
-    sanitized_word = I18n.transliterate(word)
-    unless hash.key?(sanitized_word)
-      hash[sanitized_word] = metadata
-    end
+  # Macron-stripped fallback; exact keys win, earliest entry wins on collision.
+  NORMALIZED = DICTIONARY.each_with_object({}) do |(word, metadata), hash|
+    normalized = I18n.transliterate(word)
+    next if DICTIONARY.key?(normalized)
+
+    hash[normalized] ||= metadata
   end
 end

data/medieval_latina.gemspec

@@ -23,7 +23,7 @@ Gem::Specification.new do |spec|
   # 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.
   spec.files = Dir.chdir(File.expand_path("..", __FILE__)) do
-    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features|audio)/}) }
   end
   spec.bindir = "exe"
   spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: medieval_latina
 version: !ruby/object:Gem::Version
-  version: 3.1.2
+  version: 3.2.0
 platform: ruby
 authors:
 - Jayson Virissimo
 bindir: exe
 cert_chain: []
-date: 2025-09-29 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: i18n
@@ -109,6 +109,7 @@ files:
 - ".rspec"
 - ".standard.yml"
 - ".tool-versions"
+- AGENTS.md
 - CLAUDE.md
 - Gemfile
 - Gemfile.lock
@@ -118,6 +119,7 @@ files:
 - bin/build
 - bin/console
 - bin/lint
+- bin/sample_audio
 - bin/setup
 - data/dictionary.json
 - lexicons/Latin00.pls
@@ -158,7 +160,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.6.2
+rubygems_version: 4.0.10
 specification_version: 4
 summary: Transform medieval Latin text into phonetic English
 test_files: []