surname-transliterator 0.4.0 → 0.4.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c6d5ceefee22590bad215a0c6d5a1a8749f8d244f3ca6f734bb4ad6911de6c48
-  data.tar.gz: f17c9186d02d35238754bf6a01a8e8e8dad8a003b2fa269b45363b4e3f6f2695
+  metadata.gz: 3b89068379dd610abf4b713b922fb2a10859f0bdbd9212bd62df1cf78a6de22e
+  data.tar.gz: 96f02a045635b271baa5b95dd5d731f0165d1634de1c4be5e7d2d74fb9e88c16
 SHA512:
-  metadata.gz: 16143d3c5c7e15bcede3372209f74264f594203d4d086d42e277de5babe044f95e11a52dfbf0b72f37141d835238e09762474f23c480b8304bfd20df46ca9433
-  data.tar.gz: a3051c7dc46b3739d967b99a3fef1f15d0c80d4a8283478b73d2331913d49fa4a5bae8a1dfd7df6ed2bf234eaa43037040de534a395bf115953c53c03dceb009
+  metadata.gz: a4767ed01232c158e6090e04744ea0156d2c87191622b7b1e626eac916285f4529f0281f3cb374978cc7f757c5c358713323fe39c4c11f40c812bdc504dffcda
+  data.tar.gz: c68d19e198eccc518e86998d057e45b7ffc35034de5f71c303d7677940acdfcebac0e5d227af35e6099c04b32c1068e93d115cc095853b353b5900fbe6e0a750

data/CHANGELOG.md

@@ -5,6 +5,20 @@ 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

data/lib/surname/transliterator/version.rb

@@ -2,6 +2,6 @@
 
 module Surname
   module Transliterator
-    VERSION = '0.4.0'
+    VERSION = '0.4.2'
   end
 end

data/lib/surname/transliterator.rb

@@ -88,22 +88,26 @@ module Surname
     POLONIZATION_MAPPINGS = {
       'polish_to_lithuanian' => {
         'owicz' => ['avičius'],
-        'owski' => %w[ovskis ovskas],
+        'owski' => %w[ovskis ovskas ovicius],
         'ewski' => %w[evskis evskas],
         'icki' => ['ickis'],
+        'ak' => ['akas'],
         'ski' => %w[skis skas],
-        'cki' => ['ckis']
+        'cki' => %w[ckis ckas]
       },
       'lithuanian_to_polish' => {
         '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
       },
@@ -133,7 +137,7 @@ module Surname
       end
 
       # Handle Polish digraphs
-      normalized = normalized.gsub('sz', 's') if from_lang == 'polish'
+      normalized = normalized.gsub('sz', 'š').gsub('cz', 'č').gsub('rz', 'ž') if from_lang == 'polish'
 
       normalized.capitalize
     end
@@ -147,13 +151,17 @@ module Surname
 
       normalized = surname.downcase
       variants = []
-      endings.each do |from_ending, to_endings|
+      # 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
 
       variants.uniq
@@ -161,12 +169,17 @@ module Surname
 
     # 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_variants = transform_ending(transliterated, from_lang, to_lang)
-      # Return variants: transliterated plus transformed variants
-      variants = [transliterated] + transformed_variants
+      # 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 = []

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: surname-transliterator
 version: !ruby/object:Gem::Version
-  version: 0.4.0
+  version: 0.4.2
 platform: ruby
 authors:
 - Justyna Wojtczak
@@ -26,13 +26,14 @@ files:
 - lib/surname/transliterator.rb
 - lib/surname/transliterator/version.rb
 - sig/surname/transliterator.rbs
-homepage: https://github.com/justine84/surname-transliterator
+homepage: https://github.com/justi-blue/surname-transliterator
 licenses:
 - MIT
 metadata:
-  homepage_uri: https://github.com/justine84/surname-transliterator
-  source_code_uri: https://github.com/justine84/surname-transliterator/tree/main
+  source_code_uri: https://github.com/justi-blue/surname-transliterator/tree/main
+  homepage_uri: https://github.com/justi-blue/surname-transliterator
   changelog_uri: https://github.com/justi-blue/surname-transliterator/blob/main/CHANGELOG.md
+  rubygems_mfa_required: 'true'
 rdoc_options: []
 require_paths:
 - lib