unicode_titlecase 0.0.1 → 0.0.2

data/.travis.yml

@@ -0,0 +1,3 @@
+language: ruby
+rvm:
+  - 1.9.3

data/README.md

@@ -1,13 +1,18 @@
 # unicode_titlecase gem
+[![Gem Version](https://badge.fury.io/rb/unicode_titlecase.png)](http://badge.fury.io/rb/unicode_titlecase)
+[![Code Climate](https://codeclimate.com/github/cantab/unicode_titlecase.png)](https://codeclimate.com/github/cantab/unicode_titlecase)
+[![Build Status](https://travis-ci.org/cantab/unicode_titlecase.png?branch=master)](https://travis-ci.org/cantab/unicode_titlecase)
 
-A set of methods added onto the String class to allow easy title casing of strings with Unicode text.
+Gem to enable easy title casing of strings containing Unicode text.
+
+## Introduction
+This gem patches the String class to provide a unicode_titlecase method, which returns a string that is 'title cased': the first letter in each significant word is in capitals with the rest in lowercase.
 
 ## Features
+* handles text containing Unicode characters
+* handles words that should always be left capitalised (e.g., 'HIV')
+* handles words that should always be left in lower case (e.g., 'to')
 
-* handles Unicode text
-* specify words that should always be left capitalised
-* specify words that should always be left in lower case
-	
 ## Installation
 
 Add this line to your application's Gemfile:
@@ -20,21 +25,20 @@ And then execute:
 
 Or install it yourself as:
 
-    $ gem install unicode_titlecase e'.
+    $ gem install unicode_titlecase
 
 ## Usage
 
-This gem patches the String class to provide a unicode_titlecase method, which returns a string that is 'title cased': the first letter in each significant word is in capitals with the rest in lowercase.
 
 To use, just call the unicode_titlecase method on any string you want to titlecase.
 
 For example,
 
     require 'unicode_titlecase'
-    
+
     s = "the rain in spain stays mainly in the plain"
     puts s.unicode_titlecase
-    
+
 gives
 
     "The Rain in Spain Stays Mainly in the Plain"
@@ -45,9 +49,15 @@ More examples are set out in the YAML files in the /spec/examples directory.
 
 With the help of the unicode-utils gem, we can properly handle title casing of Unicode text.
 
-For example, the string 'W Hiszpanii mży, gdy dżdżyste przyjdą dni' will be titlecased to 'W Hiszpanii Mży, Gdy Dżdżyste Przyjdą Dni'.
+For example, the string 
+
+	W Hiszpanii mży, gdy dżdżyste przyjdą dni
 
-Note: the source text may contain Unicode, or it may consist solely of ASCII. The unicode_titlecase method will work with either.
+is titlecased to
+
+	W Hiszpanii Mży, Gdy Dżdżyste Przyjdą Dni
+
+More examples [here](https://github.com/cantab/unicode_titlecase/blob/master/spec/examples/unicode_examples.yaml).
 
 ## 'Big Words'
 
@@ -55,13 +65,33 @@ In some circumstances, you may have source text that contains words that should
 
 The unicode_titlecase gem allows you to set up a list of 'big words' which it will keep upper-cased.
 
+	"DNA vs RNA - difference and comparison".unicode_titlecase
+
+produces
+
+	"DNA vs RNA - Difference and Comparison"
+	
+More examples [here](https://github.com/cantab/unicode_titlecase/blob/master/spec/examples/bigword_examples.yaml).
+
 ## 'Small Words'
 
 Similarly, you source text may contain words that should always be in lower case.
 
-By convention, a number of short words such as 'is', 'of' and 'by' are considered to look better in text if they remain in lower case.
+For example, in English, a number of short words such as 'is', 'of' and 'by' might be considered to look better in title cased text if they remain in lower case.
 
-For example, the phrase 'a government by the people for the people' might be title cased to 'A Government by the People for the People'.
+So
+
+	'a government by the people for the people'.unicode_titlecase
+	
+will give
+
+	'A Government by the People for the People'
+	
+More examples [here](https://github.com/cantab/unicode_titlecase/blob/master/spec/examples/standard_examples.yaml).
+
+## Troubleshooting
+
+- [irb does not display Unicode] (https://github.com/cantab/unicode_titlecase/wiki/Displaying-Unicode-Text-in-irb)
 
 ## Sources and Acknowledgements
 
@@ -80,10 +110,10 @@ Much of the source is based on Sam Souder's 'titlecase' gem at [samsouder/titlec
   - implemented rules in Ruby
   - [Github repo] (http://github.com/samsouder/titlecase)
   - [Rubygems.org] (http://rubygems.org/gems/titlecase)
- 
+
 #### Others
   - Jim Nanney ([Github](https://github.com/jimnanney)) contributed to some of the code (go remote pairing!)
-  
+
 ## Further Features?
 Here's a list of things we'd like to see in a future version of the unicode_titlecase gem. Please feel free to take any of these on (see [Contributing] (http://github.com/cantab/unicode_titlecase#contributing) below).
   - handle strings with 'mixed case words' such as GmbH
@@ -101,3 +131,26 @@ Feel free to drop us a line to let us know you would like to work on something o
 5. Create a new [Pull Request] (https://help.github.com/articles/using-pull-requests).
 
 More details on how to contribute can be found at this great Thoughtbot blogpost [8 (new) steps for fixing other people's code] (http://robots.thoughtbot.com/8-new-steps-for-fixing-other-peoples-code).
+
+## License
+
+Copyright (c) 2013 Chong-Yee Khoo, released under the MIT License.
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/lib/unicode_titlecase/core_ext/string.rb

@@ -6,37 +6,33 @@ module UnicodeTitlecase
   module CoreExt
     module String
 
+      # List of exceptions: SMALL_WORDS are words that should always be in lowercase; BIG_WORDS are words that should always be in uppercase
+      SMALL_WORDS = %w(a an and as at but by be for if in is of on or the to v v. via vs vs.)
+      BIG_WORDS = %w(AB A.B. A/B AS A.S. A/S S.A. KG LLC LLP DNA RNA HBV HIV I II III IV V VI VII VIII IX X AC DC Q&A AT&T)
+
       def unicode_titlecase
-        # List of exceptions: small_words are words that should always be in lowercase; big_words are words that should always be in uppercase
-        small_words = %w(a an and as at but by be for if in is of on or the to v v. via vs vs.)
-        big_words = %w(AB A.B. A/B AS A.S. A/S S.A. KG LLC LLP DNA RNA HBV HIV I II III IV V VI VII VIII IX X AC DC Q&A AT&T)
 
-        x = split(" ").map do |word|
+        component_words = split(" ").map do |word|
           # note: word could contain non-word characters!
           # downcase all small_words, upcase all big words, smart capitalize the rest
 
-          word.replace(UnicodeUtils.downcase(word)) if word.all_caps? and not big_words.include?(word)
+          word.unicode_downcase! if word.all_caps? and not word.is_big_word?
 
-          if small_words.include?(UnicodeUtils.downcase(word.gsub(/\W/, "")))
-            word.replace(UnicodeUtils.downcase(word))
+          if word.strip_non_word_chars.unicode_downcase.is_small_word?
+            word.unicode_downcase!
           else
-            if big_words.include?(UnicodeUtils.upcase(word.gsub(/\W/, "")))
-              word.replace(UnicodeUtils.upcase(word))
+            if word.strip_non_word_chars.unicode_upcase.is_big_word?
+              word.unicode_upcase!
             else
               word.smart_capitalize!
             end
           end
         end
 
-        x = x - [' ']
-
-        # capitalize first and last words
-        x.first.to_s.smart_capitalize!
-        # Uncomment the next line if you want the last word to be always initial caps
-        x.last.to_s.smart_capitalize!
-
-        # small words after colons are capitalized
-        x.join(" ").gsub(/:\s?(\W*#{small_words.join("|")}\W*)\s/) { ": #{$1.smart_capitalize} " }
+        component_words = strip_spaces(component_words)
+        smart_capitalize_ends!(component_words)
+        result = component_words.join(" ")
+        capitalize_small_words_after_colons(result)
       end
 
       def unicode_titlecase!
@@ -46,10 +42,10 @@ module UnicodeTitlecase
       def smart_capitalize
         # ignore any leading crazy characters and capitalize the first real character
         if self =~ /^['"\(\[']*(\S)/
-          i = index($1)
-          x = self[i,self.length]
+          start_of_word = index($1)
+          word = self[start_of_word, self.length]
           # word with capitals and periods mid-word are left alone
-          self[i,1] = UnicodeUtils.upcase(self[i,1]) unless self.has_caps? or x =~ /\.\w+/
+          self[start_of_word, 1] = UnicodeUtils.upcase(self[start_of_word, 1]) unless self.has_caps? or word =~ /\.\w+/
         end
         self
       end
@@ -59,13 +55,56 @@ module UnicodeTitlecase
       end
 
       def has_caps?
-        return !UnicodeUtils.downcase(self) == self
+        return !(UnicodeUtils.downcase(self) == self)
       end
 
       def all_caps?
         return UnicodeUtils.upcase(self) == self
       end
 
+      def is_big_word?
+        BIG_WORDS.include?(self)
+      end
+
+      def is_small_word?
+        SMALL_WORDS.include?(self)
+      end
+
+      def unicode_downcase
+        UnicodeUtils.downcase(self)
+      end
+
+      def unicode_downcase!
+        replace(unicode_downcase)
+      end
+
+      def unicode_upcase
+        UnicodeUtils.upcase(self)
+      end
+
+      def unicode_upcase!
+        replace(unicode_upcase)
+      end
+
+      def smart_capitalize_ends!(ary)
+        # capitalize first and last words
+        ary.first.to_s.smart_capitalize!
+        # Uncomment the next line if you want the last word to be always initial caps
+        ary.last.to_s.smart_capitalize!
+      end
+
+      def capitalize_small_words_after_colons(str)
+        # small words after colons are capitalized
+        str.gsub(/:\s?(\W*#{SMALL_WORDS.join("|")}\W*)\s/) { ": #{$1.smart_capitalize} " }
+      end
+
+      def strip_spaces(ary)
+        ary - [' ']
+      end
+
+      def strip_non_word_chars
+        self.gsub(/\W/, "")
+      end
     end
   end
 end

data/lib/unicode_titlecase/version.rb

@@ -1,3 +1,3 @@
 module UnicodeTitlecase
-  VERSION = "0.0.1"
+  VERSION = "0.0.2"
 end

data/spec/string_misc_methods_spec.rb

@@ -0,0 +1,234 @@
+#encoding: UTF-8
+
+require 'spec_helper'
+
+describe String do
+
+  describe "has_caps? method" do
+
+    context "word with capital letter" do
+
+      it "identifies it as having caps" do
+        string = 'fluVial'
+        expect(string.has_caps?).to be_true
+      end
+    end
+
+    context "word without capital letter" do
+
+      it "identifies it has not having caps" do
+        string = 'fluvial'
+        expect(string.has_caps?).to be_false
+      end
+    end
+  end
+
+  describe "all_caps? method" do
+
+    context "word completely in uppercase" do
+
+      it "identifies it as having all caps" do
+        string = 'FLUVIAL'
+        expect(string.all_caps?).to be_true
+      end
+    end
+
+    context "word not completely in uppercase" do
+
+      it "identifies it has not having all caps" do
+        string = 'FLUvIAL'
+        expect(string.all_caps?).to be_false
+      end
+    end
+
+    context "word in lowercase" do
+
+      it "identifies it has not having all caps" do
+        string = 'fluvial'
+        expect(string.all_caps?).to be_false
+      end
+    end
+  end
+
+  describe "is_big_word? method" do
+
+    context "word in big words list" do
+
+      it "identifies it as being a big word" do
+        string = 'HIV'
+        expect(string.is_big_word?).to be_true
+      end
+    end
+
+    context "word not in big words list" do
+
+      it "identifies it as not being a big word" do
+        string = 'SIV'
+        expect(string.is_big_word?).to be_false
+      end
+    end
+  end
+
+  describe "is_small_word? method" do
+
+    context "word in small words list" do
+
+      it "identifies it as being a small word" do
+        string = 'is'
+        expect(string.is_small_word?).to be_true
+      end
+    end
+
+    context "word not in small words list" do
+
+      it "identifies it as not being a small word" do
+        string = 'tis'
+        expect(string.is_small_word?).to be_false
+      end
+    end
+  end
+
+  describe "unicode_downcase method" do
+
+    it "downcases the word" do
+      string = 'Dżdżyste'
+      expect(string.unicode_downcase).to eq('dżdżyste')
+    end
+  end
+
+  describe "unicode_downcase! method" do
+
+    it "downcases the word in place" do
+      string = 'Dżdżyste'
+      string.unicode_downcase!
+      expect(string).to eq('dżdżyste')
+    end
+  end
+
+  describe "unicode_upcase method" do
+
+    it "upcases the word" do
+      string = 'dżdżyste'
+      expect(string.unicode_upcase).to eq('DŻDŻYSTE')
+    end
+  end
+
+  describe "unicode_upcase! method" do
+
+    it "upcases the word in place" do
+      string = 'dżdżyste'
+      string.unicode_upcase!
+      expect(string).to eq('DŻDŻYSTE')
+    end
+  end
+
+  describe "smart_capitalize method" do
+
+    context "word with leading single quote mark" do
+
+      it "capitalizes word properly" do
+        expect("'fluvial".smart_capitalize).to eq("'Fluvial")
+      end
+
+      context "and internal capital letter" do
+        it "is left alone" do
+          expect("'flUvial".smart_capitalize).to eq("'flUvial")
+        end
+      end
+
+      context "and internal period" do
+        it "is left alone" do
+          expect("'fl.vial".smart_capitalize).to eq("'fl.vial")
+        end
+      end
+    end
+
+    context "word with leading double quote mark" do
+
+      it "capitalizes word properly" do
+        expect('"fluvial'.smart_capitalize).to eq('"Fluvial')
+      end
+
+      context "and internal capital letter" do
+        it "is left alone" do
+          expect('"flUvial'.smart_capitalize).to eq('"flUvial')
+        end
+      end
+
+      context "and internal period" do
+        it "is left alone" do
+          expect('"fl.vial'.smart_capitalize).to eq('"fl.vial')
+        end
+      end
+    end
+
+    context "word with leading open bracket" do
+      it "capitalizes word properly" do
+        expect('(fluvial'.smart_capitalize).to eq('(Fluvial')
+      end
+
+      context "and internal capital letter" do
+        it "is left alone" do
+          expect('(flUvial'.smart_capitalize).to eq('(flUvial')
+        end
+      end
+
+      context "and internal period" do
+        it "is left alone" do
+          expect('(fl.vial'.smart_capitalize).to eq('(fl.vial')
+        end
+      end
+    end
+
+    context "word with leading open square bracket" do
+      it "capitalizes word properly" do
+        expect('[fluvial'.smart_capitalize).to eq('[Fluvial')
+      end
+
+      context "and internal capital letter" do
+        it "is left alone" do
+          expect('[flUvial'.smart_capitalize).to eq('[flUvial')
+        end
+      end
+
+      context "and internal period" do
+        it "is left alone" do
+          expect('[fl.vial'.smart_capitalize).to eq('[fl.vial')
+        end
+      end
+    end
+
+    describe "smart_capitalize_ends! method" do
+
+      it "capitalizes first and last members of an array of words" do
+        array = ['fee', 'fi', 'fo', 'fum']
+        String.new.smart_capitalize_ends!(array)
+        expect(array).to eq(['Fee', 'fi', 'fo', 'Fum'])
+      end
+    end
+
+    describe "capitalize_small_words_after_colons method" do
+
+      it "capitalizes small words after colons" do
+        string = 'end: a begining'
+        expect(String.new.capitalize_small_words_after_colons(string)).to eq('end: A begining')
+      end
+    end
+
+    describe "strip_spaces method" do
+
+      it "strips members of array which are spaces" do
+        array = ['the', ' ', 'rain', ' ', 'in', ' ', 'spain', ' ']
+        expect(String.new.strip_spaces(array)).to eq(['the', 'rain', 'in', 'spain'])
+      end
+    end
+
+    describe "strip_non_word_chars method" do
+
+      it "strips characters in a string which are not words" do
+        string = "T!h\"e r£ai$n i%n Spa^in st&*a(y)s ma-in=!ly in t@+he p{}l[]ai#n"
+        expect(string.strip_non_word_chars).to eq("TheraininSpainstaysmainlyintheplain")
+      end
+    end
+  end
+end

data/unicode_titlecase.gemspec

@@ -6,11 +6,13 @@ require 'unicode_titlecase/version'
 Gem::Specification.new do |gem|
   gem.name          = "unicode_titlecase"
   gem.version       = UnicodeTitlecase::VERSION
-  gem.authors       = ["Chong-Yee Khoo"]
+  gem.authors       = ["Dr Chong-Yee Khoo"]
   gem.email         = ["mail@cykhoo.com"]
-  gem.description   = %q{Titlecaser with Unicode smarts}
-  gem.summary       = %q{Change text, including in Unicode, to title case}
-  gem.homepage      = "http://github.com/cykhoo/unicode_titlecase"
+  gem.description   = %q{Gem to enable easy title casing of strings containing Unicode text.}
+  gem.summary       = %q{This gem patches the String class to provide a unicode_titlecase method, \
+                         which returns a string that is 'title cased': the first letter in each \
+                         significant word is in capitals with the rest in lowercase.}
+  gem.homepage      = "http://github.com/cantab/unicode_titlecase"
 
   gem.files         = `git ls-files`.split($/)
   gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }

metadata

@@ -1,15 +1,15 @@
 --- !ruby/object:Gem::Specification
 name: unicode_titlecase
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.2
   prerelease: 
 platform: ruby
 authors:
-- Chong-Yee Khoo
+- Dr Chong-Yee Khoo
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-11-01 00:00:00.000000000 Z
+date: 2013-11-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -59,7 +59,7 @@ dependencies:
     - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
-description: Titlecaser with Unicode smarts
+description: Gem to enable easy title casing of strings containing Unicode text.
 email:
 - mail@cykhoo.com
 executables: []
@@ -69,6 +69,7 @@ files:
 - .gitignore
 - .rspec
 - .ruby-version
+- .travis.yml
 - Gemfile
 - LICENSE.txt
 - README.md
@@ -82,9 +83,10 @@ files:
 - spec/examples/standard_examples.yaml
 - spec/examples/unicode_examples.yaml
 - spec/spec_helper.rb
+- spec/string_misc_methods_spec.rb
 - spec/unicode_titlecase_spec.rb
 - unicode_titlecase.gemspec
-homepage: http://github.com/cykhoo/unicode_titlecase
+homepage: http://github.com/cantab/unicode_titlecase
 licenses: []
 post_install_message: 
 rdoc_options: []
@@ -98,7 +100,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: -1860229550247952293
+      hash: -3799941477510380033
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
@@ -107,13 +109,15 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: -1860229550247952293
+      hash: -3799941477510380033
 requirements: []
 rubyforge_project: 
 rubygems_version: 1.8.23
 signing_key: 
 specification_version: 3
-summary: Change text, including in Unicode, to title case
+summary: ! 'This gem patches the String class to provide a unicode_titlecase method,
+  \ which returns a string that is ''title cased'': the first letter in each \ significant
+  word is in capitals with the rest in lowercase.'
 test_files:
 - spec/examples/bigword_examples.yaml
 - spec/examples/capitalisation_examples.yaml
@@ -121,4 +125,5 @@ test_files:
 - spec/examples/standard_examples.yaml
 - spec/examples/unicode_examples.yaml
 - spec/spec_helper.rb
+- spec/string_misc_methods_spec.rb
 - spec/unicode_titlecase_spec.rb