stringex 1.3.2 → 1.3.3

data/README.rdoc

@@ -14,11 +14,16 @@ which will populate the <tt>url</tt> attribute on the object with the converted
 <tt>:url_attribute</tt>:: The name of the attribute to use for storing the generated url string.
                           Default is <tt>:url</tt>
 <tt>:scope</tt>:: The name of model attribute to scope unique urls to. There is no default here.
-<tt>:only_when_blank</tt>:: If true, the url generation will only happen when <tt>:url_attribute</tt> is
-                            blank. Default is false (meaning url generation will happen always)
+<tt>:only_when_blank</tt>:: If set to true, the url generation will only happen when <tt>:url_attribute</tt> is
+                            blank. Default is false (meaning url generation will happen always).
 <tt>:sync_url</tt>:: If set to true, the url field will be updated when changes are made to the
                      attribute it is based on. Default is false.
 <tt>:allow_slash</tt>:: If set to true, the url field will not convert slashes. Default is false.
+<tt>:allow_duplicates</tt>:: If set to true, unique urls will not be enforced.
+                             Default is false. <em>NOTE: This is strongly not recommended
+                             if you are routing solely on the generated slug as you will no longer
+                             be guaranteed to lookup the expected record based on a duplicate slug.</em>
+
 
 In order to use the generated url attribute, you will probably want to override <tt>to_param</tt> like so, in your Model:
 
@@ -29,7 +34,7 @@ In order to use the generated url attribute, you will probably want to override
 
 Routing called via named routes like <tt>foo_path(@foo)</tt> will automatically use the url. In your controllers you will need to call <tt>Foo.find_by_url(params[:id])</tt> instead of the regular find. Don't look for <tt>params[:url]</tt> unless you set it explicitly in the routing, <tt>to_param</tt> will generate <tt>params[:id]</tt>.
 
-Note that if you add <tt>acts_as_url</tt> to an old model, the <tt>url</tt> database column will inititally be blank. To set this column for your old instances, you can use the <tt>initialize_urls</tt> method. So if your class is <tt>Post</tt>, just say <tt>Post.all.each{|p| p.initialize_urls}</tt>.
+Note that if you add <tt>acts_as_url</tt> to an old model, the <tt>url</tt> database column will inititally be blank. To set this column for your old instances, you can use the <tt>initialize_urls</tt> method. So if your class is <tt>Post</tt>, just say <tt>Post.initialize_urls</tt>.
 
 Unlike other permalink solutions, ActsAsUrl doesn't rely on Iconv (which is inconsistent across platforms and doesn't provide great transliteration as is) but instead uses a transliteration scheme (see the code for Unidecoder) which produces much better results for Unicode characters. It also mixes in some custom helpers to translate common characters into a more URI-friendly format rather than just dump them completely. Examples:
 

data/Rakefile

@@ -212,7 +212,7 @@ begin
     }
     gem.rdoc_options     = %w{--main README.rdoc --charset utf-8 --line-numbers}
     gem.extra_rdoc_files =  %w{MIT-LICENSE README.rdoc}
-    gem.version = "1.3.2"
+    gem.version = "1.3.3"
   end
 
   Jeweler::GemcutterTasks.new

data/lib/stringex.rb

@@ -4,7 +4,6 @@ require 'stringex/unidecoder'
 
 String.send :include, Stringex::StringExtensions
 
-if defined?(ActiveRecord)
-  require 'stringex/acts_as_url'
-  ActiveRecord::Base.send :include, Stringex::ActsAsUrl
-end
+require 'stringex/acts_as_url' if defined?(ActiveRecord) || defined?(Mongoid::Document)
+
+ActiveRecord::Base.send :include, Stringex::ActsAsUrl if defined?(ActiveRecord)

data/lib/stringex/acts_as_url.rb

@@ -33,6 +33,7 @@ module Stringex
         cattr_accessor :only_when_blank
         cattr_accessor :duplicate_count_separator
         cattr_accessor :allow_slash
+        cattr_accessor :allow_duplicates
 
         if options[:sync_url]
           before_validation(:ensure_unique_url)
@@ -50,6 +51,7 @@ module Stringex
         self.only_when_blank = options[:only_when_blank] || false
         self.duplicate_count_separator = options[:duplicate_count_separator] || "-"
         self.allow_slash = options[:allow_slash] || false
+        self.allow_duplicates = options[:allow_duplicates] || false
 
         class_eval <<-"END"
           def #{url_attribute}
@@ -95,12 +97,14 @@ module Stringex
       end
       url_owners = self.class.find(:all, :conditions => conditions)
       write_attribute url_attribute, base_url
-      if url_owners.any?{|owner| owner.send(url_attribute) == base_url}
-        n = 1
-        while url_owners.any?{|owner| owner.send(url_attribute) == "#{base_url}#{separator}#{n}"}
-          n = n.succ
+      unless self.class.allow_duplicates
+        if url_owners.any?{|owner| owner.send(url_attribute) == base_url}
+          n = 1
+          while url_owners.any?{|owner| owner.send(url_attribute) == "#{base_url}#{separator}#{n}"}
+            n = n.succ
+          end
+          write_attribute url_attribute, "#{base_url}#{separator}#{n}"
         end
-        write_attribute url_attribute, "#{base_url}#{separator}#{n}"
       end
     end
   end

data/lib/stringex/string_extensions.rb

@@ -42,7 +42,7 @@ module Stringex
     # Performs multiple text manipulations. Essentially a shortcut for typing them all. View source
     # below to see which methods are run.
     def remove_formatting(options = {})
-      strip_html_tags.convert_smart_punctuation.convert_accented_entities.convert_misc_entities.convert_misc_characters(options).to_ascii.collapse
+      strip_html_tags.convert_smart_punctuation.convert_accented_entities.convert_vulgar_fractions.convert_misc_entities.convert_misc_characters(options).to_ascii.collapse
     end
 
     # Removes HTML tags from text. This code is simplified from Tobias Luettke's regular expression
@@ -67,7 +67,7 @@ module Stringex
     # Note: This does not do any conversion of Unicode/ASCII accented-characters. For that
     # functionality please use <tt>to_ascii</tt>.
     def convert_accented_entities
-      gsub(/&([A-Za-z])(grave|acute|circ|tilde|uml|ring|cedil|slash);/, '\1')
+      gsub(/&([A-Za-z])(grave|acute|circ|tilde|uml|ring|cedil|slash);/, '\1').strip
     end
 
     # Converts HTML entities (taken from common Textile/RedCloth formattings) into plain text formats.
@@ -95,11 +95,37 @@ module Stringex
         "(#188|frac14)" => "one fourth",
         "(#189|frac12)" => "half",
         "(#190|frac34)" => "three fourths",
-        "(#176|deg)" => " degrees"
+        "(#176|deg)" => " degrees "
       }.each do |textiled, normal|
         dummy.gsub!(/&#{textiled};/, normal)
       end
-      dummy.gsub(/&[^;]+;/, "")
+      dummy.gsub(/&[^;]+;/, "").strip
+    end
+
+    # Converts vulgar fractions from supported html entities and unicode to
+    # plain text formats.
+    def convert_vulgar_fractions
+      dummy = dup
+      {
+        "(&#188;|&frac14;|¼)" => "one fourth",
+        "(&#189;|&frac12;|½)" => "half",
+        "(&#190;|&frac34;|¾)" => "three fourths",
+        "(&#8531;|⅓)" => "one third",
+        "(&#8532;|⅔)" => "two thirds",
+        "(&#8533;|⅕)" => "one fifth",
+        "(&#8534;|⅖)" => "two fifths",
+        "(&#8535;|⅗)" => "three fifths",
+        "(&#8536;|⅘)" => "four fifths",
+        "(&#8537;|⅙)" => "one sixth",
+        "(&#8538;|⅚)" => "five sixths",
+        "(&#8539;|⅛)" => "one eighth",
+        "(&#8540;|⅜)" => "three eighths",
+        "(&#8541;|⅝)" => "five eighths",
+        "(&#8542;|⅞)" => "seven eighths"
+      }.each do |textiled, normal|
+        dummy.gsub!(/#{textiled}/, normal)
+      end
+      dummy
     end
 
     # Converts MS Word 'smart punctuation' to ASCII
@@ -114,7 +140,7 @@ module Stringex
       }.each do |smart, normal|
         dummy.gsub!(/#{smart}/, normal)
       end
-      dummy
+      dummy.strip
     end
 
     # Converts various common plaintext characters to a more URI-friendly representation.
@@ -155,14 +181,15 @@ module Stringex
         /\s*\*\s*/ => "star",
         /\s*%\s*/ => "percent",
         /(\s*=\s*)/ => " equals ",
-        /\s*\+\s*/ => "plus"
+        /\s*\+\s*/ => "plus",
+        /\s*°\s*/ => "degrees"
       }
       misc_characters[/\s*(\\|\/)\s*/] = 'slash' unless options[:allow_slash]
       misc_characters.each do |found, replaced|
         replaced = " #{replaced} " unless replaced =~ /\\1/
         dummy.gsub!(found, replaced)
       end
-      dummy = dummy.gsub(/(^|\w)'(\w|$)/, '\1\2').gsub(/[\.,:;()\[\]\?!\^'"_]/, " ")
+      dummy = dummy.gsub(/(^|[[:alpha:]])'([[:alpha:]]|$)/, '\1\2').gsub(/[\.,:;()\[\]\/\?!\^'ʼ"_]/, " ").strip
     end
 
     # Replace runs of whitespace in string. Defaults to a single space but any replacement

data/stringex.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{stringex}
-  s.version = "1.3.2"
+  s.version = "1.3.3"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Russell Norris"]
-  s.date = %q{2012-02-16}
+  s.date = %q{2012-04-24}
   s.description = %q{Some [hopefully] useful extensions to Ruby's String class. Stringex is made up of three libraries: ActsAsUrl [permalink solution with better character translation], Unidecoder [Unicode to ASCII transliteration], and StringExtensions [miscellaneous helper methods for the String class].}
   s.email = %q{rsl@luckysneaks.com}
   s.extra_rdoc_files = [

data/test/acts_as_url_test.rb

@@ -49,6 +49,10 @@ ActiveRecord::Schema.define(:version => 1) do
   create_table :validatuments, :force => true do |t|
     t.string :title, :url, :other
   end
+  
+  create_table :ununiquments, :force => true do |t|
+    t.string :title, :url, :other
+  end
 end
 ActiveRecord::Migration.verbose = true
 
@@ -89,6 +93,10 @@ class Validatument < ActiveRecord::Base
   validates_presence_of :title
 end
 
+class Ununiqument < ActiveRecord::Base
+  acts_as_url :title, :allow_duplicates => true
+end
+
 class ActsAsUrlTest < Test::Unit::TestCase
   def test_should_create_url
     @doc = Document.create(:title => "Let's Make a Test Title, <em>Okay</em>?")
@@ -100,6 +108,12 @@ class ActsAsUrlTest < Test::Unit::TestCase
     @other_doc = Document.create!(:title => "Unique")
     assert_equal "unique-1", @other_doc.url
   end
+  
+  def test_should_not_create_unique_url
+    @doc = Ununiqument.create!(:title => "I am not a clone")
+    @other_doc = Ununiqument.create!(:title => "I am not a clone")
+    assert_equal "i-am-not-a-clone", @other_doc.url
+  end
 
   def test_should_not_succ_on_repeated_saves
     @doc = Document.new(:title => "Continuous or Constant")

data/test/string_extensions_test.rb

@@ -49,8 +49,26 @@ class StringExtensionsTest < Test::Unit::TestCase
         "im-just-making-sure-theres-nothing-wrong-with-things",
       "foo = bar and bar=foo" =>
         "foo-equals-bar-and-bar-equals-foo",
+      "Period.period" =>
+        "period-dot-period",
       "Will…This Work?" =>
-        "will-dot-dot-dot-this-work"
+        "will-dot-dot-dot-this-work",
+      "¼ pound with cheese" =>
+        "one-fourth-pound-with-cheese",
+      "Will's Ferrel" =>
+        "wills-ferrel",
+      "Капитал" => 
+        "kapital",
+      "Ελλάδα" => 
+        "ellada",
+      "中文" => 
+        "zhong-wen",
+      "Paul Cézanne" => 
+        "paul-cezanne",
+      "21'17ʼ51" => 
+        "21-17-51",
+      "ITCZ 1 (21°17ʼ51.78”N / 89°35ʼ28.18”O / 26-04-08 / 09:00 am)" => 
+        "itcz-1-21-degrees-17-51-dot-78-n-slash-89-degrees-35-28-dot-18-o-slash-26-04-08-slash-09-00-am"
     }.each do |html, plain|
       assert_equal plain, html.to_url
     end
@@ -95,6 +113,46 @@ class StringExtensionsTest < Test::Unit::TestCase
     end
   end
 
+  def test_convert_vulgar_fractions
+    {
+      "&frac14;" => "one fourth",
+      "¼" => "one fourth",
+      "&#188;" => "one fourth",
+      "&frac12;" => "half",
+      "½" => "half",
+      "&#189;" => "half",
+      "&frac34;" => "three fourths",
+      "¾" => "three fourths",
+      "&#190;" => "three fourths",
+      "⅓" => "one third",
+      "&#8531;" => "one third",
+      "⅔" => "two thirds",
+      "&#8532;" => "two thirds",
+      "⅕" => "one fifth",
+      "&#8533;" => "one fifth",
+      "⅖" => "two fifths",
+      "&#8534;" => "two fifths",
+      "⅗" => "three fifths",
+      "&#8535;" => "three fifths",
+      "⅘" => "four fifths",
+      "&#8536;" => "four fifths",
+      "⅙" => "one sixth",
+      "&#8537;" => "one sixth",
+      "⅚" => "five sixths",
+      "&#8538;" => "five sixths",
+      "⅛" => "one eighth",
+      "&#8539;" => "one eighth",
+      "⅜" => "three eighths",
+      "&#8540;" => "three eighths",
+      "⅝" => "five eighths",
+      "&#8541;" => "five eighths",
+      "⅞" => "seven eighths",
+      "&#8542;" => "seven eighths"
+    }.each do |entitied, plain|
+      assert_equal plain, entitied.convert_vulgar_fractions
+    end
+  end
+
   def test_convert_misc_entities
     {
       "America&#8482;" => "America(tm)",
@@ -102,7 +160,6 @@ class StringExtensionsTest < Test::Unit::TestCase
       "To be continued&#8230;" => "To be continued...",
       "Foo&nbsp;Bar" => "Foo Bar",
       "100&#163;" => "100 pound",
-      "&frac12; a dollar" => "half a dollar",
       "35&deg;" => "35 degrees"
     }.each do |entitied, plain|
       assert_equal plain, entitied.convert_misc_entities

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: stringex
 version: !ruby/object:Gem::Version 
-  hash: 31
+  hash: 29
   prerelease: 
   segments: 
   - 1
   - 3
-  - 2
-  version: 1.3.2
+  - 3
+  version: 1.3.3
 platform: ruby
 authors: 
 - Russell Norris
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2012-02-16 00:00:00 -05:00
+date: 2012-04-24 00:00:00 -04:00
 default_executable: 
 dependencies: []