greeklish_iso843 0.1.0 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c8a9b1c75a4cdfe88d93923e74db0df32b6919c0baf57bc5d926e0335e523e3f
-  data.tar.gz: d6faf9868e79e861e61e4d0945deb58293a482b473aacc9cc647a4d3d908b48b
+  metadata.gz: 07ec5fdb5be2bca43018f9afc095163e3f83db8ca2306efa4d00e57154a400cf
+  data.tar.gz: 4c367180883ffe24351544e5566a580ff38d500cc7a51c1b180a757bd4985483
 SHA512:
-  metadata.gz: 1c758ab1affd37f13dbdfacd79fac463a6f123dcff40053703477922ee347293d85c4ec8f2d837533f944bf7afd728b52fd27f1a12ca7008c9ec3d903e70e792
-  data.tar.gz: adbcf58e1273386cd5e10ece84ec549bbd9907d3200ca84b4f9da42ae8659c92e686badbe32e8e2df9b60439d5dcac2c33419649e9509c82975a9f7c6c08c798
+  metadata.gz: ab641750790707f68e497156645459dac086bf068d517cc48cc4bb4774bf9e6bb3b8ae0314f90e0319a29403075c0ec17870c511fd94e0b222da6d2b4d7ed860
+  data.tar.gz: 4c5a6c023fb1a2c5c88ce15558dc43b8c5f7216a0eb673bd22973ac9166607b7042e49725dfea4669c50b42642cb61cd983643a1a201a92f3488e677fe3e42b9

data/CHANGELOG.md

@@ -7,10 +7,22 @@ The format is based on [Keep a Changelog][] and this project adheres to
 
 ## [Unreleased][]
 
-## 0.1.0 - 2021-03-04
+## [0.2.0][] - 2021-03-04
+
+### Changed
+
+- Fix transliteration of `ευ` followed by a vowel or `β`, `γ`, `δ`, `ζ`, `λ`,
+  `μ`, `ν`, `ρ`. For example, `Ευάγγελος` used to be converted to `Efangelos`
+  and now it's `Evangelos`. `άνευ` remains `anef`.
+- Use precompiled `Regexp` for replacements to speed things up.
+  [#1](https://github.com/agorf/greeklish_iso843/pull/1) by
+  [@iridakos](https://github.com/iridakos)
+
+## 0.1.0 - 2021-03-03
 
 Initial release.
 
 [Keep a Changelog]: http://keepachangelog.com/en/1.0.0/
 [Semantic Versioning]: http://semver.org/spec/v2.0.0.html
-[Unreleased]: https://github.com/agorf/feedigest/compare/0.1.0...HEAD
+[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

data/README.md

@@ -1,12 +1,11 @@
 # greeklish_iso843
 
 A [Ruby][] library that converts Greek text to [Greeklish][], conforming to the
-[ISO 843][] (ELOT 743) standard [used by the Greek State][state].
+[ISO 843][] (ELOT 743) standard used by the Greek State.
 
 [Ruby]: https://www.ruby-lang.org/en/
 [Greeklish]: https://en.wikipedia.org/wiki/Greeklish
 [ISO 843]: https://www.iso.org/standard/5215.html
-[state]: http://www.passport.gov.gr/passports/GrElotConverter/GrElotConverter.html
 
 ## Installation
 
@@ -31,7 +30,8 @@ Then you can use it to convert text:
 ```ruby
 GreeklishIso843::Converter.convert("Μπάμπης") # => "Bampis"
 GreeklishIso843::Converter.convert("Άγγελος") # => "Angelos"
-GreeklishIso843::Converter.convert("Ευάγγελος") # => "Efangelos"
+GreeklishIso843::Converter.convert("Ευάγγελος") # => "Evangelos"
+GreeklishIso843::Converter.convert("άνευ αποδοχών") # => "anef apodochon"
 ```
 
 Alternatively, you can require the `String` core extension for more convenience:
@@ -44,8 +44,6 @@ Then you can use it to convert text:
 
 ```ruby
 "Μπάμπης".to_greeklish # => "Bampis"
-"Άγγελος".to_greeklish # => "Angelos"
-"Ευάγγελος".to_greeklish # => "Efangelos"
 ```
 
 There's also a command line utility that accepts Greek text from the standard
@@ -54,20 +52,18 @@ input and prints the corresponding Greeklish text to the standard output:
 ```sh
 $ greeklish_iso843
 Μπάμπης
-Άγγελος
-Ευάγγελος
 ^D
 Bampis
-Angelos
-Efangelos
 $
 ```
 
 Note: `^D` represents the EOF (End Of File) character, emitted with `Ctrl-D`.
 
-## To-do
+## Acknowledgements
 
-- Tests 😅
+This library was based on [an official implementation in JavaScript][js].
+
+[js]: http://www.passport.gov.gr/passports/GrElotConverter/GrElotConverter.html
 
 ## License
 

data/lib/greeklish_iso843/converter.rb

@@ -64,6 +64,8 @@ class GreeklishIso843::Converter
     'ώ' => 'o'
   }.freeze
 
+  REPLACEMENTS_REGEXP = /#{REPLACEMENTS.keys.join('|')}/i.freeze
+
   BLANK_REGEXP = /\A[[:space:]]*\z/.freeze
 
   attr_reader :text
@@ -77,19 +79,18 @@ class GreeklishIso843::Converter
   end
 
   def convert
-    text.gsub(/#{REPLACEMENTS.keys.join('|')}/i) do |match|
+    text.gsub(REPLACEMENTS_REGEXP) do |match|
       match_data = Regexp.last_match
-      replacement = REPLACEMENTS[match.downcase]
+      greeklish = REPLACEMENTS[match.downcase]
+      prev_char = match_data.pre_match[-1]&.downcase
+      next_char = match_data.post_match[0]&.downcase
 
-      if replacement
-        greeklish = replacement
-        greek = match + match_data.post_match[0].to_s
+      if greeklish
+        greek = match + next_char.to_s
       elsif match.casecmp?('μπ')
         greeklish =
-          if present?(match_data.pre_match) &&
-              GREEK_LOWER[match_data.pre_match[0].downcase] &&
-              present?(match_data.post_match) &&
-              GREEK_LOWER[match_data.post_match[0].downcase]
+          if prev_char && GREEK_LOWER[prev_char] &&
+              next_char && GREEK_LOWER[next_char]
             'mp'
           else
             'b'
@@ -99,9 +100,13 @@ class GreeklishIso843::Converter
         greeklish = 'ts'
         greek = match
       else
-        index = match_data.offset(0)[0]
-        greeklish = REPLACEMENTS[match[0].downcase] +
-          ('αβγδεζηλιμνορω'[text[index...index + 2].downcase] ? 'v' : 'f')
+        greeklish =
+          REPLACEMENTS[match[0].downcase] +
+          if next_char && 'αάεέηήιίϊΐοόυύϋΰωώβγδζλμνρ'[next_char]
+            'v'
+          else
+            'f'
+          end
         greek = match
       end
 
@@ -114,14 +119,14 @@ class GreeklishIso843::Converter
   end
 
   private def fix_case(greeklish, greek)
-    if capitalized?(greek[0])
-      if greek.length == 1 || capitalized?(greek[1])
-        greeklish.upcase
-      else
-        greeklish[0].upcase + greeklish[1..-1]
-      end
+    if !capitalized?(greek[0])
+      return greeklish
+    end
+
+    if greek.length == 1 || capitalized?(greek[1])
+      greeklish.upcase
     else
-      greeklish
+      greeklish[0].upcase + greeklish[1..-1]
     end
   end
 

data/lib/greeklish_iso843/version.rb

@@ -1,3 +1,3 @@
 module GreeklishIso843
-  VERSION = '0.1.0'.freeze
+  VERSION = '0.2.0'.freeze
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: greeklish_iso843
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors:
 - Angelos Orfanakos
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2021-03-03 00:00:00.000000000 Z
+date: 2021-03-04 00:00:00.000000000 Z
 dependencies: []
 description: 
 email: rubygems@angelos.dev