string_normalizr 0.1 → 0.2

data/LICENSE

@@ -0,0 +1,24 @@
+Copyright (c) 2010, Carsten Zimmermann
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+    * Neither the name of the original author / copyright holder nor the
+      names of its contributors may be used to endorse or promote products
+      derived from this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
+ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER BE LIABLE FOR ANY
+DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

data/Manifest

@@ -1,8 +1,8 @@
+LICENSE
 README.rdoc
 Rakefile
 init.rb
 lib/string_normalizr.rb
 nbproject/private/rake-d.txt
-string_normalizr.gemspec
 test/string_normalizr_test.rb
 Manifest

data/README.rdoc

@@ -6,7 +6,7 @@ of your String instance.
 
 
 === Installation
- $ gem install carpodaster-string_normalizr --source http://gems.github.com
+ $ gem install string_normalizr
 
 Or use it as a plugin with your Rails app:
 
@@ -15,12 +15,14 @@ Or use it as a plugin with your Rails app:
 === Usage
  "hellö world".normalize
 
-=== Caveats
-* Tests seem to have difficulties with multibyte characters right now.
-
 === .plan
-* Add option-hash to customize the normalization
+* support custom collation hash
+* support more special chars by default
+* handle punctuation marks
 
+=== Changelog
+* 0.2: Normalization can now be customized via an options hash.
+* 0.1: Initial version
 
 ---
 

data/Rakefile

@@ -9,7 +9,7 @@ Rake::TestTask.new("test") do |t|
   t.verbose = false
 end
 
-Echoe.new('string_normalizr', '0.1') do |p|
+Echoe.new('string_normalizr', '0.2') do |p|
   p.description    = "Let String instances be conviently normalized"
   p.url            = "http://github.com/carpodaster/string_normalizr"
   p.author         = "Carsten Zimmermann"

data/lib/string_normalizr.rb

@@ -1,20 +1,110 @@
-module AegisNet
+# -*- coding: utf-8 -*-"
+require "rubygems"
+module AegisNet # :nodoc:
   module StringNormalizr
 
+    COLLATION = {
+      'Ä' => 'Ae',
+      'Æ' => 'Ae',
+      'Å' => 'A',
+      'À' => 'A',
+      'Á' => 'A',
+      'Â' => 'A',
+      'Ç' => 'C',
+      'È' => "E",
+      'É' => "E",
+      'Ê' => "E",
+      'Ë' => 'E',
+      'Í' => 'I',
+      'Ì' => 'I',
+      'Î' => 'I',
+      'Ï' => 'I',
+      'Ñ' => 'N',
+      'Ö' => 'Oe',
+      'Œ' => 'Oe',
+      'Ø' => 'O',
+      'Ô' => 'O',
+      'Ó' => 'O',
+      'Ò' => 'O',
+      'Ü' => 'Ue',
+      'Ú' => 'U',
+      'Ù' => 'U',
+      'Ÿ' => 'Y',
+      'ä' => 'ae',
+      'æ' => 'ae',
+      'å' => 'a',
+      'à' => 'a',
+      'á' => 'a',
+      'â' => 'a',
+      'ç' => 'c',
+      'è' => 'e',
+      'é' => 'e',
+      'ê' => 'e',
+      'ë' => 'e',
+      'í' => 'i',
+      'ì' => 'i',
+      'î' => 'i',
+      'ï' => 'i',
+      'ñ' => 'n',
+      'ö' => 'oe',
+      'œ' => 'oe',
+      'ø' => 'o',
+      'ô' => 'o',
+      'ó' => 'o',
+      'ò' => 'o',
+      'ü' => 'ue',
+      'ú' => 'u',
+      'ù' => 'u',
+      'ÿ' => 'y',
+      'ß' => 'ss',
+    }
+
     def self.included(base)
       base.send(:include, InstanceMethods)
     end
 
-
     module InstanceMethods
-      def normalize
-        self.strip.gsub('ä', 'ae').gsub('ö', 'oe').gsub('ü', 'ue').gsub('Ä', 'Ae').gsub('Ö', 'Oe').gsub('Ü', 'Ue').gsub("ß", "ss")
+
+      # Returns a new String based on pre-defined normalization rules
+      #
+      # == Parameters
+      # * +options+: optional Hash for normalization customization
+      #
+      # == Available options
+      # * <tt>:strip</tt> - trim leading and trailing whitespaces (true|false, default: true)
+      # * <tt>:replace_whitespaces</tt> - replace whitespaces within the string with +str+
+      #   or set to +false+ to leave whitespaces alone. Makes little
+      #   sense w/o :strip => true (str|false, default: "-")
+      #
+      # == Examples
+      #   "This is án exåmple".normalize
+      #    => "This-is-an-example
+      #
+      #   "Tëst string with träiling whitespaces   ".normalize(:replace_whitespaces => false)
+      #    => "Test string with traeiling whitespaces"
+      #
+      def normalize(options = {})
+        # shamelessly taken from ActiveSupport::ActiveSupport::Hash::Keys#assert_valid_keys
+        valid_keys = [:replace_whitespaces, :strip]
+        unknown_keys = options.keys - [valid_keys].flatten
+        raise(ArgumentError, "Unknown key(s): #{unknown_keys.join(", ")}") unless unknown_keys.empty?
+
+        # Default options
+        options = {
+          :downcase            => false,
+          :strip               => true,
+          :replace_whitespaces => "-"
+        }.merge(options)
+
+        n_str = AegisNet::StringNormalizr::COLLATION.inject(dup) {|str, (collate_from, collate_to)| str.gsub(collate_from, collate_to)}
+        n_str.strip!    if options[:strip]
+        n_str.gsub!(/\s+/, options[:replace_whitespaces]) if options[:replace_whitespaces]
+        n_str
       end
     end
-
   end
 end
 
-class String
+class String # :nodoc:
   include AegisNet::StringNormalizr
 end

data/string_normalizr.gemspec

@@ -2,15 +2,15 @@
 
 Gem::Specification.new do |s|
   s.name = %q{string_normalizr}
-  s.version = "0.1"
+  s.version = "0.2"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 1.2") if s.respond_to? :required_rubygems_version=
   s.authors = ["Carsten Zimmermann"]
-  s.date = %q{2010-09-17}
+  s.date = %q{2010-09-20}
   s.description = %q{Let String instances be conviently normalized}
   s.email = %q{carp@hacksocke.de}
-  s.extra_rdoc_files = ["README.rdoc", "lib/string_normalizr.rb"]
-  s.files = ["README.rdoc", "Rakefile", "init.rb", "lib/string_normalizr.rb", "nbproject/private/rake-d.txt", "string_normalizr.gemspec", "test/string_normalizr_test.rb", "Manifest"]
+  s.extra_rdoc_files = ["LICENSE", "README.rdoc", "lib/string_normalizr.rb"]
+  s.files = ["LICENSE", "README.rdoc", "Rakefile", "init.rb", "lib/string_normalizr.rb", "nbproject/private/rake-d.txt", "test/string_normalizr_test.rb", "Manifest", "string_normalizr.gemspec"]
   s.homepage = %q{http://github.com/carpodaster/string_normalizr}
   s.rdoc_options = ["--line-numbers", "--inline-source", "--title", "String_normalizr", "--main", "README.rdoc"]
   s.require_paths = ["lib"]

data/test/string_normalizr_test.rb

@@ -1,22 +1,89 @@
+# -*- coding: utf-8 -*-"
 require 'test/unit'
 require File.dirname(__FILE__) + "/../lib/string_normalizr"
 
 class StringNormalizrTest < Test::Unit::TestCase
-
+  
   def test_string_integration
     assert "some string".respond_to?(:normalize)
   end
 
   def test_whitespaces
+    assert_equal "This-is-an-example", "This is an example".normalize
+    assert_equal "This is an example", "This is an example".normalize(:replace_whitespaces => false)
+    assert_equal "This=is=an=example", "This is an example".normalize(:replace_whitespaces => "=")
+
     assert_equal "foo", " foo   \n \t".normalize
+    assert_equal "foo   \n \t", "foo   \n \t".normalize(:strip => false, :replace_whitespaces => false)
+  end
+
+  def test_accents
+    assert_equal "a", "á".normalize
+    assert_equal "a", "à".normalize
+    assert_equal "a", "â".normalize
+    assert_equal "A", "Á".normalize
+    assert_equal "A", "À".normalize
+    assert_equal "A", "Â".normalize
+    assert_equal "e", "é".normalize
+    assert_equal "e", "è".normalize
+    assert_equal "E", "É".normalize
+    assert_equal "E", "È".normalize
+    assert_equal "i", "í".normalize
+    assert_equal "i", "ì".normalize
+    assert_equal "i", "î".normalize
+    assert_equal "I", "Í".normalize
+    assert_equal "I", "Ì".normalize
+    assert_equal "I", "Î".normalize
+    assert_equal "o", "ó".normalize
+    assert_equal "o", "ò".normalize
+    assert_equal "o", "ô".normalize
+    assert_equal "O", "Ó".normalize
+    assert_equal "O", "Ò".normalize
+    assert_equal "O", "Ô".normalize
+    assert_equal "u", "ú".normalize
+    assert_equal "u", "ù".normalize
+    assert_equal "U", "Ú".normalize
+    assert_equal "U", "Ù".normalize
+  end
+
+  def test_umlauts
+    assert_equal "ae", "ä".normalize
+    assert_equal "Ae", "Ä".normalize
+    assert_equal "oe", "ö".normalize
+    assert_equal "Oe", "Ö".normalize
+    assert_equal "ue", "ü".normalize
+    assert_equal "Ue", "Ü".normalize
+  end
+
+  def test_spanish_chars
+    assert_equal "c", "ç".normalize
+    assert_equal "C", "Ç".normalize
+    assert_equal "n", "ñ".normalize
+    assert_equal "N", "Ñ".normalize
+  end
+
+  def test_scandinavian_chars
+    assert_equal "a", "å".normalize
+    assert_equal "A", "Å".normalize
+    assert_equal "o", "ø".normalize
+    assert_equal "O", "Ø".normalize
   end
 
-  def test_german_umlauts
-    assert_equal "foeOebaerueghbAerUegh", "föÖbärüghbÄrÜgh"
+  def test_ligatures
+    assert_equal "ae", "æ".normalize
+    assert_equal "Ae", "Æ".normalize
+    assert_equal "oe", "œ".normalize
+    assert_equal 'Oe', 'Œ'.normalize
+    assert_equal "ss", "ß".normalize
   end
 
-  def test_sz
-    assert_equal "Strasse", "Straße"
+  def test_diaresises
+    assert_equal "e", "ë".normalize
+    assert_equal "E", "Ë".normalize
+    assert_equal "i", "ï".normalize
+    assert_equal "I", "Ï".normalize
+    assert_equal "y", "ÿ".normalize
+    assert_equal "Y", "Ÿ".normalize
   end
 
 end

metadata

@@ -1,12 +1,12 @@
 --- !ruby/object:Gem::Specification 
 name: string_normalizr
 version: !ruby/object:Gem::Version 
-  hash: 9
+  hash: 15
   prerelease: false
   segments: 
   - 0
-  - 1
-  version: "0.1"
+  - 2
+  version: "0.2"
 platform: ruby
 authors: 
 - Carsten Zimmermann
@@ -14,7 +14,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-09-17 00:00:00 +02:00
+date: 2010-09-20 00:00:00 +02:00
 default_executable: 
 dependencies: []
 
@@ -25,17 +25,19 @@ executables: []
 extensions: []
 
 extra_rdoc_files: 
+- LICENSE
 - README.rdoc
 - lib/string_normalizr.rb
 files: 
+- LICENSE
 - README.rdoc
 - Rakefile
 - init.rb
 - lib/string_normalizr.rb
 - nbproject/private/rake-d.txt
-- string_normalizr.gemspec
 - test/string_normalizr_test.rb
 - Manifest
+- string_normalizr.gemspec
 has_rdoc: true
 homepage: http://github.com/carpodaster/string_normalizr
 licenses: []