arabic_normalizer 0.1.0 → 0.1.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 084a93775f2ff33d26782e6ff7a0ac71faae8359
-  data.tar.gz: db45f2e595f9965a86e26b856b6623a27c36acac
+  metadata.gz: 595779d3887e6b4c0785c2ccd35e2d428809d118
+  data.tar.gz: 08b6b15c78cc24ff59d41c0bb9015b81e04901a5
 SHA512:
-  metadata.gz: 7202d85d202569b2de4034af2002b4952535853cb33605d95dfb20452dbf9acecab851e2ddaa078d3fc78ffb8e8ac358811f228733e3e31720c056097dfaadda
-  data.tar.gz: 0ea11e87913ab2aba14eb05396a90e314a3549518bf8749bc4a829ec1c5873c07ead1c3c9a63724d746897a167fdf854196a53148b5f45007e0f8debbe00852e
+  metadata.gz: 2db268cf7d49a480126bbe1e56d8c517c98fbe22b38270511537f43fb40be1eda15e1b9bc27db3a7c4f19a93c83d64b6d18297adb1b0759b17a95d87b13d6e14
+  data.tar.gz: c31c17c2e523ab80d53cbbfc41135875a752e030bb63f7e6db513696127b5febd3d9b6eb6cfe2730f5cd2c145d09bc6d9184d2dd6ef58daaea2346a4588c94c4

data/README.md

@@ -7,7 +7,7 @@ ArabicNormalizer is pure Ruby port of Arabic Normalizer from Lucene.
 Add this line to your application's Gemfile:
 
 ```ruby
-gem 'arabicNormalizer'
+gem 'arabic_normalizer'
 ```
 
 And then execute:
@@ -16,11 +16,11 @@ And then execute:
 
 Or install it yourself as:
 
-    $ gem install arabicNormalizer
+    $ gem install arabic_normalizer
 
 ## Usage
 ```
-require 'arabicNormalizer'
+require 'arabic_normalizer'
 
 ArabicNormalizer::normalize("مكتبٌ")
 => "مكتب"

data/lib/arabic_normalizer.rb

@@ -27,19 +27,17 @@ module ArabicNormalizer
   SHADDA = "\u0651"
   SUKUN = "\u0652"
 
+  NORMALIZATION_RULES = {
+    ALEF_MADDA => ALEF, ALEF_HAMZA_ABOVE => ALEF, ALEF_HAMZA_BELOW => ALEF,
+    YEH_HAMZA => YEH, DOTLESS_YEH => YEH,
+    TEH_MARBOUTA => HEH,
+    WAW_HAMZA => WAW,
+    TATWEEL => '', FATHATAN => '', DAMMATAN => '', KASRATAN => '', FATHA => '', DAMMA => '', KASRA => '', SHADDA => '', SUKUN => ''
+  }
+
+  NORMALIZATION_REGEX = /[#{NORMALIZATION_RULES.keys.join}]/.freeze
+
   def self.normalize(string)
-    string.gsub(/[
-      #{ALEF_MADDA}#{ALEF_HAMZA_ABOVE}#{ALEF_HAMZA_BELOW}
-      #{YEH_HAMZA}#{DOTLESS_YEH}
-      #{TEH_MARBOUTA}
-      #{WAW_HAMZA}
-      #{TATWEEL}#{FATHATAN}#{DAMMATAN}#{KASRATAN}#{FATHA}#{DAMMA}#{KASRA}#{SHADDA}#{SUKUN}
-    ]/x,
-      ALEF_MADDA => ALEF, ALEF_HAMZA_ABOVE => ALEF, ALEF_HAMZA_BELOW => ALEF,
-      YEH_HAMZA => YEH, DOTLESS_YEH => YEH,
-      TEH_MARBOUTA => HEH,
-      WAW_HAMZA => WAW,
-      TATWEEL => '', FATHATAN => '', DAMMATAN => '', KASRATAN => '', FATHA => '', DAMMA => '', KASRA => '', SHADDA => '', SUKUN => ''
-    )
+    string.gsub(NORMALIZATION_REGEX, NORMALIZATION_RULES)
   end
 end

data/lib/arabic_normalizer/version.rb

@@ -1,3 +1,3 @@
 module ArabicNormalizer
-  VERSION = "0.1.0"
+  VERSION = "0.1.1"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: arabic_normalizer
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.1.1
 platform: ruby
 authors:
 - Jean Debs
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2016-03-22 00:00:00.000000000 Z
+date: 2016-03-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler