greeklish_iso843 0.2.0 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 07ec5fdb5be2bca43018f9afc095163e3f83db8ca2306efa4d00e57154a400cf
-  data.tar.gz: 4c367180883ffe24351544e5566a580ff38d500cc7a51c1b180a757bd4985483
+  metadata.gz: 3d4c26155ee5e66d06b9a44cc5a452bcac2ed78a9f5ed889c6ec9540a9fc5853
+  data.tar.gz: 22c733cff1a29127b39a36ca69caa9cd73d96b6e55009ebb017d0fa517484d01
 SHA512:
-  metadata.gz: ab641750790707f68e497156645459dac086bf068d517cc48cc4bb4774bf9e6bb3b8ae0314f90e0319a29403075c0ec17870c511fd94e0b222da6d2b4d7ed860
-  data.tar.gz: 4c5a6c023fb1a2c5c88ce15558dc43b8c5f7216a0eb673bd22973ac9166607b7042e49725dfea4669c50b42642cb61cd983643a1a201a92f3488e677fe3e42b9
+  metadata.gz: 46c846c9b550c56a8530c232bc4db7d1eb561484d716758e62a23a4dd50956f63a29df91c99410ef7f9b4028f315660c42b21e4607b5200f3a9ea254dd2a2cc2
+  data.tar.gz: 802ac4eef5af569b492991de5316e7390cf2377acd05d04f3dbcacc8b0adba528d9835be250fd34b64231c9d7ef2917e9f6e614c22cb2289e9fae3b6f886417d

data/CHANGELOG.md

@@ -7,6 +7,14 @@ The format is based on [Keep a Changelog][] and this project adheres to
 
 ## [Unreleased][]
 
+## [0.3.0][] - 2021-03-06
+
+### Changed
+
+- Test text conversion thoroughly with over 100 test cases
+- Change API from `GreeklishIso843::Converter.convert(text)` to
+  `GreeklishIso843::GreekText.to_greeklish(text)`
+
 ## [0.2.0][] - 2021-03-04
 
 ### Changed
@@ -25,4 +33,5 @@ Initial release.
 [Keep a Changelog]: http://keepachangelog.com/en/1.0.0/
 [Semantic Versioning]: http://semver.org/spec/v2.0.0.html
 [0.2.0]: https://github.com/agorf/greeklish_iso843/compare/0.1.0...0.2.0
-[Unreleased]: https://github.com/agorf/greeklish_iso843/compare/0.2.0...HEAD
+[0.3.0]: https://github.com/agorf/greeklish_iso843/compare/0.2.0...0.3.0
+[Unreleased]: https://github.com/agorf/greeklish_iso843/compare/0.3.0...HEAD

data/README.md

@@ -1,4 +1,4 @@
-# greeklish_iso843
+# greeklish_iso843 [![Gem](https://img.shields.io/gem/v/greeklish_iso843?color=blue)](https://rubygems.org/gems/greeklish_iso843/) [![RuboCop](https://github.com/agorf/greeklish_iso843/actions/workflows/rubocop.yml/badge.svg)](https://github.com/agorf/greeklish_iso843/actions/workflows/rubocop.yml) [![Tests](https://github.com/agorf/greeklish_iso843/actions/workflows/tests.yml/badge.svg)](https://github.com/agorf/greeklish_iso843/actions/workflows/tests.yml)
 
 A [Ruby][] library that converts Greek text to [Greeklish][], conforming to the
 [ISO 843][] (ELOT 743) standard used by the Greek State.
@@ -28,10 +28,10 @@ require 'greeklish_iso843'
 Then you can use it to convert text:
 
 ```ruby
-GreeklishIso843::Converter.convert("Μπάμπης") # => "Bampis"
-GreeklishIso843::Converter.convert("Άγγελος") # => "Angelos"
-GreeklishIso843::Converter.convert("Ευάγγελος") # => "Evangelos"
-GreeklishIso843::Converter.convert("άνευ αποδοχών") # => "anef apodochon"
+GreeklishIso843::GreekText.to_greeklish("Μπάμπης") # => "Bampis"
+GreeklishIso843::GreekText.to_greeklish("Άγγελος") # => "Angelos"
+GreeklishIso843::GreekText.to_greeklish("Ευάγγελος") # => "Evangelos"
+GreeklishIso843::GreekText.to_greeklish("ξεσκεπάζω την ψυχοφθόρα σας βδελυγμία") # => "xeskepazo tin psychofthora sas vdelygmia"
 ```
 
 Alternatively, you can require the `String` core extension for more convenience:
@@ -59,9 +59,14 @@ $
 
 Note: `^D` represents the EOF (End Of File) character, emitted with `Ctrl-D`.
 
+## Tests
+
+You can run the tests with `rake test` or `rake  test TESTOPTS='-v'` for a more
+verbose output.
+
 ## Acknowledgements
 
-This library was based on [an official implementation in JavaScript][js].
+This library was based on [an official, buggy implementation in JavaScript][js].
 
 [js]: http://www.passport.gov.gr/passports/GrElotConverter/GrElotConverter.html
 

data/bin/greeklish_iso843

@@ -3,7 +3,7 @@
 require 'greeklish_iso843'
 
 begin
-  print GreeklishIso843::Converter.convert($stdin.read)
+  print GreeklishIso843::GreekText.to_greeklish($stdin.read)
 rescue Interrupt # Ctrl-C
   puts
 end

data/lib/greeklish_iso843.rb

@@ -1,3 +1,3 @@
 module GreeklishIso843; end
 
-require 'greeklish_iso843/converter'
+require 'greeklish_iso843/greek_text'

data/lib/greeklish_iso843/core_ext/string.rb

@@ -2,6 +2,6 @@ require 'greeklish_iso843'
 
 class String
   def to_greeklish
-    GreeklishIso843::Converter.convert(self)
+    GreeklishIso843::GreekText.to_greeklish(self)
   end
 end

data/lib/greeklish_iso843/{converter.rb → greek_text.rb}

@@ -1,8 +1,12 @@
-class GreeklishIso843::Converter
+class GreeklishIso843::GreekText
   GREEK_UPPER = 'ΑΆΒΓΔΕΈΖΗΉΘΙΊΪΚΛΜΝΞΟΌΠΡΣΤΥΎΫΦΧΨΩΏ'.freeze
 
   GREEK_LOWER = 'αάβγδεέζηήθιίϊΐκλμνξοόπρσςτυύϋΰφχψωώ'.freeze
 
+  GREEK_VOWELS = 'αάεέηήιίϊΐοόυύϋΰωώ'.freeze
+
+  GREEK_LETTERS_AFTER_V = "#{GREEK_VOWELS}βγδζλμνρ".freeze
+
   REPLACEMENTS = {
     'αι' => 'ai',
     'αί' => 'ai',
@@ -66,48 +70,27 @@ class GreeklishIso843::Converter
 
   REPLACEMENTS_REGEXP = /#{REPLACEMENTS.keys.join('|')}/i.freeze
 
-  BLANK_REGEXP = /\A[[:space:]]*\z/.freeze
-
   attr_reader :text
 
-  def self.convert(text)
-    new(text).convert
+  def self.to_greeklish(text)
+    new(text).to_greeklish
   end
 
   def initialize(text)
     @text = text
   end
 
-  def convert
+  def to_greeklish
     text.gsub(REPLACEMENTS_REGEXP) do |match|
       match_data = Regexp.last_match
-      greeklish = REPLACEMENTS[match.downcase]
-      prev_char = match_data.pre_match[-1]&.downcase
       next_char = match_data.post_match[0]&.downcase
+      greeklish = REPLACEMENTS[match.downcase]
+      greek = match
 
       if greeklish
         greek = match + next_char.to_s
-      elsif match.casecmp?('μπ')
-        greeklish =
-          if prev_char && GREEK_LOWER[prev_char] &&
-              next_char && GREEK_LOWER[next_char]
-            'mp'
-          else
-            'b'
-          end
-        greek = match
-      elsif match.casecmp?('τς')
-        greeklish = 'ts'
-        greek = match
       else
-        greeklish =
-          REPLACEMENTS[match[0].downcase] +
-          if next_char && 'αάεέηήιίϊΐοόυύϋΰωώβγδζλμνρ'[next_char]
-            'v'
-          else
-            'f'
-          end
-        greek = match
+        greeklish = convert_to_greeklish(match, match_data, next_char)
       end
 
       fix_case(greeklish, greek)
@@ -118,10 +101,12 @@ class GreeklishIso843::Converter
     GREEK_UPPER[text[0]]
   end
 
+  private def lowercase_char?(char)
+    GREEK_LOWER[char]
+  end
+
   private def fix_case(greeklish, greek)
-    if !capitalized?(greek[0])
-      return greeklish
-    end
+    return greeklish if !capitalized?(greek[0])
 
     if greek.length == 1 || capitalized?(greek[1])
       greeklish.upcase
@@ -130,7 +115,32 @@ class GreeklishIso843::Converter
     end
   end
 
-  private def present?(text)
-    text.to_s !~ BLANK_REGEXP
+  private def convert_mp_or_b(prev_char, next_char)
+    if prev_char && lowercase_char?(prev_char) && # *μπ
+        next_char && lowercase_char?(next_char) # and μπ*
+      'mp'
+    else # μπ* or *μπ
+      'b'
+    end
+  end
+
+  private def convert_v_or_f(next_char)
+    if next_char && GREEK_LETTERS_AFTER_V[next_char]
+      'v'
+    else
+      'f'
+    end
+  end
+
+  private def convert_to_greeklish(match, match_data, next_char)
+    return 'ts' if match.casecmp?('τς')
+
+    if match.casecmp?('μπ')
+      prev_char = match_data.pre_match[-1]&.downcase
+      return convert_mp_or_b(prev_char, next_char)
+    end
+
+    # αυ αύ ευ εύ ηυ ηύ
+    REPLACEMENTS[match[0].downcase] + convert_v_or_f(next_char)
   end
 end

data/lib/greeklish_iso843/version.rb

@@ -1,3 +1,3 @@
 module GreeklishIso843
-  VERSION = '0.2.0'.freeze
+  VERSION = '0.3.0'.freeze
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: greeklish_iso843
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.3.0
 platform: ruby
 authors:
 - Angelos Orfanakos
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2021-03-04 00:00:00.000000000 Z
+date: 2021-03-06 00:00:00.000000000 Z
 dependencies: []
 description: 
 email: rubygems@angelos.dev
@@ -22,8 +22,8 @@ files:
 - README.md
 - bin/greeklish_iso843
 - lib/greeklish_iso843.rb
-- lib/greeklish_iso843/converter.rb
 - lib/greeklish_iso843/core_ext/string.rb
+- lib/greeklish_iso843/greek_text.rb
 - lib/greeklish_iso843/version.rb
 homepage: https://github.com/agorf/greeklish_iso843
 licenses: