surname-transliterator 0.3.0 → 0.4.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 4df1e6b0864ab368780804751aa166c6b100be381011942fa0073d1cb4350d71
-  data.tar.gz: cb1118f3560a93dcd5e3bc0982bf0cca6a59680763dcf924c2a4bdaf98752643
+  metadata.gz: ea26f1b796400d4bd4f0fc9ee9cfbe7116e0520eb97769a47aa7e57c190bceb0
+  data.tar.gz: 94b1ec91e13d670fe22e1e95d91d6d08f5f7cae9fd5c393881ae9c72dd35eb15
 SHA512:
-  metadata.gz: 3d04bfb1abd3f73f08227dad6ce1e3a781fac2965e689ef1423a111e36e09519c23037d1c6db1e6e1f7a3aa57909c5992104735ec6b842577ac4fa15e5a1c29e
-  data.tar.gz: abb7da9ec167ada8b393fd86269baedc927384f87e2ed761299fb55f5a200c5bdda2397bb7d1821141912b7b51974e101e168028496f7d11e8fa4891a54057fe
+  metadata.gz: 40b4a8c3b1c88c34365e4e0631f93f738a93f58702adc2ad9f2423adf57aeb9cb9dcafd1cb2e602c9dbf11ffa7d233d2cb378d942cfb515e84d51a24f6d3c72b
+  data.tar.gz: 06d92b4c47e4b9d50daf524cda06b29e92ac2af1e8b03f6bea69c4ebc537690f981e37ef838a35241af926d342a637efe9198113ba846f564d1719d366804eac

data/CHANGELOG.md

@@ -5,10 +5,23 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.4.0] - 2025-01-01
+
+### Added
+- Support for additional polonization mappings: 'ak' → 'akas', 'cki' → 'ckis'/'ckas', 'owski' → 'ovicius'
+- Polish digraph handling in transliteration: 'sz' → 'š', 'cz' → 'č', 'rz' → 'ž'
+- W/V interchange variants for genealogical matching
+- Expanded test suite with more FN examples and edge cases
+- MFA requirement in gemspec for security
+
+### Changed
+- Improved transform_ending to handle multiple overlapping suffixes
+- Updated normalize_surname to include original transliterated forms
+- Enhanced gemspec metadata for better compliance
+
 ## [0.3.0] - 2025-01-01
 
 ### Changed
-- Moved gem to independent directory for standalone publishing
 - Require Ruby 3.1+ for compatibility
 
 ## [0.2.0] - 2025-01-01

data/README.md

@@ -13,13 +13,13 @@ TODO: Replace `UPDATE_WITH_YOUR_GEM_NAME_IMMEDIATELY_AFTER_RELEASE_TO_RUBYGEMS_O
 Install the gem and add to the application's Gemfile by executing:
 
 ```bash
-bundle add UPDATE_WITH_YOUR_GEM_NAME_IMMEDIATELY_AFTER_RELEASE_TO_RUBYGEMS_ORG
+bundle add surname-transliterator
 ```
 
 If bundler is not being used to manage dependencies, install the gem by executing:
 
 ```bash
-gem install UPDATE_WITH_YOUR_GEM_NAME_IMMEDIATELY_AFTER_RELEASE_TO_RUBYGEMS_ORG
+gem install surname-transliterator
 ```
 
 ## Usage

data/lib/surname/transliterator/version.rb

@@ -2,6 +2,6 @@
 
 module Surname
   module Transliterator
-    VERSION = '0.3.0'
+    VERSION = '0.4.1'
   end
 end

data/lib/surname/transliterator.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-require_relative "transliterator/version"
+require_relative 'transliterator/version'
 
 module Surname
   module Transliterator
@@ -87,22 +87,29 @@ module Surname
     # Polonization/de-polonization mappings for specific pairs (based on genealogical sources)
     POLONIZATION_MAPPINGS = {
       'polish_to_lithuanian' => {
-        'owicz' => 'avičius',
-        'owski' => 'auskas',
-        'ewski' => 'evskis',
-        'icki' => 'ickis',
-        'ski' => 'skis',
-        'cki' => 'ckis'
+        'owicz' => ['avičius'],
+        'owski' => %w[ovskis ovskas ovicius],
+        'ewski' => %w[evskis evskas],
+        'icki' => ['ickis'],
+        'ak' => ['akas'],
+        'ski' => %w[skis skas],
+        'cki' => %w[ckis ckas]
       },
       'lithuanian_to_polish' => {
-        'avičius' => 'owicz',
-        'auskas' => 'owski',
-        'evskis' => 'ewski',
-        'ickis' => 'icki',
-        'skis' => 'ski',
-        'ckis' => 'cki',
-        'onis' => 'owicz',  # e.g., Jonas → Janowicz
-        'aitis' => 'owicz'  # rarer, e.g., Kazlauskas variations
+        'avičius' => ['owicz'],
+        'ovskis' => ['owski'],
+        'ovskas' => ['owski'],
+        'ovicius' => ['owski'],
+        'evskis' => ['ewski'],
+        'evskas' => ['ewski'],
+        'ickis' => ['icki'],
+        'akas' => ['ak'],
+        'skis' => ['ski'],
+        'skas' => ['ski'],
+        'ckis' => ['cki'],
+        'ckas' => ['cki'],
+        'onis' => ['owicz'],  # e.g., Jonas → Janowicz
+        'aitis' => ['owicz']  # rarer, e.g., Kazlauskas variations
       },
       'polish_to_russian' => {
         'ski' => 'skii',
@@ -129,36 +136,63 @@ module Surname
         normalized = normalized.gsub(accented, base)
       end
 
+      # Handle Polish digraphs
+      normalized = normalized.gsub('sz', 'š').gsub('cz', 'č').gsub('rz', 'ž') if from_lang == 'polish'
+
       normalized.capitalize
     end
 
     # Polonization/de-polonization between languages
     def self.transform_ending(surname, from_lang, to_lang)
-      return surname if surname.nil? || surname.empty?
+      return [surname] if surname.nil? || surname.empty?
 
       key = "#{from_lang}_to_#{to_lang}"
       endings = POLONIZATION_MAPPINGS[key] || {}
 
       normalized = surname.downcase
-      endings.each do |from_ending, to_ending|
-        if normalized.end_with?(from_ending)
-          return normalized.sub(/#{from_ending}$/, to_ending).capitalize
+      variants = []
+      # Sort endings by length descending to match longest first
+      sorted_endings = endings.sort_by { |k, v| -k.length }
+      sorted_endings.each do |from_ending, to_endings|
+        next unless normalized.end_with?(from_ending)
+
+        Array(to_endings).each do |to_ending|
+          transformed = normalized.sub(/#{from_ending}$/, to_ending)
+          variants << transformed.capitalize
         end
+        # Break after first match to avoid overlapping
+        break
       end
 
-      surname
+      variants.uniq
     end
 
     # Full cross-language surname normalization
     def self.normalize_surname(surname, from_lang, to_lang)
-      # First, transliterate to remove diacritics
-      transliterated = transliterate(surname, from_lang)
-      # Then, transform endings if applicable
-      transformed = transform_ending(transliterated, from_lang, to_lang)
-      # Return variants: only add transformed if different from transliterated
-      variants = [ transliterated ]
-      variants << transformed if transformed != transliterated
-      variants.compact
+      # First, transform endings if applicable
+      transformed_variants = transform_ending(surname, from_lang, to_lang)
+      # Then, transliterate each variant to remove diacritics and handle digraphs
+      variants = transformed_variants.map { |v| transliterate(v, from_lang) }
+
+      # If no transformation, add the transliterated original
+      if transformed_variants == [surname]
+        # Already included
+      else
+        variants << transliterate(surname, from_lang)
+      end
+
+      # Add W/V interchange variants for genealogical matching
+      additional = []
+      variants.each do |v|
+        if v.start_with?('W')
+          additional << v.sub(/^W/, 'V')
+        elsif v.start_with?('V')
+          additional << v.sub(/^V/, 'W')
+        end
+      end
+      variants.concat(additional)
+
+      variants.uniq.reject { |v| v.nil? || v.empty? }
     end
 
     # Convenience methods

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: surname-transliterator
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 0.4.1
 platform: ruby
 authors:
 - Justyna Wojtczak
@@ -30,9 +30,10 @@ homepage: https://github.com/justine84/surname-transliterator
 licenses:
 - MIT
 metadata:
+  source_code_uri: https://github.com/justine84/surname-transliterator/tree/main
   homepage_uri: https://github.com/justine84/surname-transliterator
-  source_code_uri: https://github.com/justine84/surname-transliterator
   changelog_uri: https://github.com/justi-blue/surname-transliterator/blob/main/CHANGELOG.md
+  rubygems_mfa_required: 'true'
 rdoc_options: []
 require_paths:
 - lib