titlify 0.2.0 → 0.3.0

data/.gitignore

@@ -6,3 +6,6 @@ doc/*
 
 # OS X Crap
 .DS_Store
+
+# Build Gems
+pkg/*

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    titlify (0.1.0)
+    titlify (0.3.0)
 
 GEM
   remote: http://rubygems.org/

data/README.markdown

@@ -1,11 +1,11 @@
 Titlify
 =======
 
-The best damn titlecase function. (Or at least on its way.)
+The best damn titlecase function. (Or at least on its way.) Titlify will be moving closer to adhere to the [AP Stylebook](http://www.apstylebook.com/). It is the most commonly used style guide in the United States in journalism. Because I expect this gem will be used in situations more similar to journalism, I think the AP Stylebook makes sense. However, if there's enough support for Chicago Manual of Style and Elements of Typographic Style, I'll reconsider. It's still early on.
 
 Credits
 -------
-The most thorough titlecasing function I found was Patrick Hogan's in his [sterile gem](https://github.com/pbhogan/sterile). I started with his titlecasing function and expanded to include some more logic to bring it closer to the AP guidelines and handle more fringe cases.
+The most thorough titlecasing function I found was Patrick Hogan's in his [sterile gem](https://github.com/pbhogan/sterile). I started with his titlecasing function which was an expansion on John Gruber's Perl titlecasing function.
 
 Usage
 -----
@@ -35,7 +35,6 @@ Format text appropriately for titles. This method is much smarter than ActiveSup
 
 Installation
 ------------
-__Not Yet Published__
 
 Install with RubyGems:
 
@@ -44,5 +43,34 @@ Install with RubyGems:
 License
 -------
 
-Copyright (c) 2012 Josh Hepworth, released under the MIT License.
+__Sterile__
+
+Copyright (c) 2011 Patrick Hogan, released under the MIT License
 http://www.opensource.org/licenses/mit-license
+
+__Titlify__
+
+This is free and unencumbered software released into the public domain.
+
+Anyone is free to copy, modify, publish, use, compile, sell, or
+distribute this software, either in source code form or as a compiled
+binary, for any purpose, commercial or non-commercial, and by any
+means.
+
+In jurisdictions that recognize copyright laws, the author or authors
+of this software dedicate any and all copyright interest in the
+software to the public domain. We make this dedication for the benefit
+of the public at large and to the detriment of our heirs and
+successors. We intend this dedication to be an overt act of
+relinquishment in perpetuity of all present and future rights to this
+software under copyright law.
+
+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 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.
+
+For more information, please refer to <http://unlicense.org/>

data/Rakefile

@@ -0,0 +1 @@
+Bundler::GemHelper.install_tasks

data/lib/titlify/data/smart_format_rules.rb

@@ -1,7 +1,6 @@
 # encoding: UTF-8
 
 module Titlify
-  # @private
   class Data
     def self.smart_format_rules
       [

data/lib/titlify/data/word_lists.rb

@@ -0,0 +1,32 @@
+# encoding: utf-8
+
+module Titlify
+  class Data
+    def self.articles
+      %w(a an the some)
+    end
+
+    def self.coordinating_conjunctions
+      %w(and but or nor for yet so)
+    end
+
+    def self.prepositions
+      %w(a abaft aboard about above absent across afore after against along alongside amid amidst among amongst an apropos around as aside astride athwart atop barring before behind below beneath beside besides between betwixt beyond but by circa concerning despite down during except excluding failing following for from given in including inside into lest like mid midst minus modulo near next notwithstanding of off on onto opposite out outside over pace past per plus pro qua regarding round sans save since than through throughout till to toward towards under underneath unlike until up upon versus via vice with within without worth)
+
+      # Not included because same spelling is more commonly a different part of speech
+      # times
+
+      # Included in special cases
+      # at
+    end
+
+    def self.special_cases
+      # I bet this is going to get out of control...
+      %w(at(?!&t) v[.]? vs[.]?)
+    end
+
+    def self.word_list
+      Data.articles | Data.coordinating_conjunctions | Data.prepositions | Data.special_cases
+    end
+  end
+end

data/lib/titlify/titlecase.rb

@@ -19,7 +19,7 @@ module Titlify
       string.gsub!(/\s+/, " ")
       string.downcase! unless string =~ /[[:lower:]]/
 
-      small_words = %w{ a an and as at(?!&t) but by en for if in nor of on or the to v[.]? via vs[.]? }.join("|")
+      small_words = word_list.join("|")
       apos = / (?: ['#{rsquo}] [[:lower:]]* )? /xu
 
       string.gsub!(
@@ -39,23 +39,52 @@ module Titlify
       string.gsub!(
         /
           \b
-          ([_\*]*)
+          ([_\*]*)                                          # [1]
           (?:
-            ( [-\+\w]+ [@.\:\/] [-\w@.\:\/]+ #{apos} )      # URL, domain, or email
+            (                                               # [2] entire matched URL
+              (?:[A-Za-z0-9]+[\.]{1})+(?:ac|ad|ae|aero|af|ag|ai|al|am|an|ao|aq|ar|arpa|as|asia|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|biz|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cat|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|com|coop|cr|cu|cv|cw|cx|cy|cz|de|dj|dk|dm|do|dz|ec|edu|ee|eg|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gov|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|info|int|io|iq|ir|is|it|je|jm|jo|jobs|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mil|mk|ml|mm|mn|mo|mobi|mp|mq|mr|ms|mt|mu|museum|mv|mw|mx|my|mz|na|name|nc|ne|net|nf|ng|ni|nl|no|np|nr|nu|nz|om|org|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|pro|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|sk|sl|sm|sn|so|sr|st|su|sv|sx|sy|sz|tc|td|tel|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|travel|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|xn|xxx|ye|yt|za|zm|zw)
+              |
+              (?:
+                (?:
+                  [a-z][\w-]+:
+                  (?:
+                    \/{1,3}
+                    |
+                    [a-z0-9%]
+                  )
+                  |
+                  www\d{0,3}[.]
+                  |
+                  [a-z0-9.\-]+[.][a-z]{2,4}\/
+                )
+                (?:
+                  [^\s()<>]+
+                  |
+                  \([^\s()<>]+|\([^\s()<>]+\)*\)
+                )+
+                (?:
+                  \([^\s()<>]+|\([^\s()<>]+\)*\)
+                  |
+                  [^\s`!()\[\]{};:'".,<>?«»“”‘’]
+                )
+              )
+            )
+            |
+            ((?:[\w-\.]+)@(?:[\w]+\.)+(?:[a-zA-Z]){2,4})        # [3] email
             |
-            ( (?i: #{small_words} ) #{apos} )               # or small word, case-insensitive
+            ( (?i: #{small_words} ) #{apos} )               # [4] or small word, case-insensitive
             |
-            ( [[:alpha:]] [[:lower:]'#{rsquo}()\[\]{}]* #{apos} )  # or word without internal caps
+            ( [[:alpha:]] [[:lower:]'#{rsquo}()\[\]{}]* #{apos} )  # [5] or word without internal caps
             |
-            ( [[:alpha:]] [[:alpha:]'#{rsquo}()\[\]{}]* #{apos} )  # or some other word
+            ( [[:alpha:]] [[:alpha:]'#{rsquo}()\[\]{}]* #{apos} )  # [6] or some other word
           )
-          ([_\*]*)
+          ([_\*]*)                                                 # [7]
           \b
         /xu
       ) do
         ($1 ? $1 : "") +
-        ($2 ? $2 : ($3 ? $3.downcase : ($4 ? $4.downcase.capitalize : $5))) +
-        ($6 ? $6 : "")
+        ($2 ? $2 : ($3 ? $3.downcase : ($4 ? $4.downcase : ($5 ? $5.downcase.capitalize : $6)))) +
+        ($7 ? $7 : "")
       end
 
       if RUBY_VERSION < "1.9.0"
@@ -125,9 +154,16 @@ module Titlify
     # Lazy load smart formatting rules
     def smart_format_rules
       @smart_format_rules ||= begin
-        require "titlify/data/smart_format_rules"
-        Data.smart_format_rules
-      end
+                                require "titlify/data/smart_format_rules"
+                                Data.smart_format_rules
+                              end
+    end
+
+    def word_list
+      @word_list ||= begin
+                       require "titlify/data/word_lists"
+                       Data.word_list
+                     end
     end
 
   end

data/lib/titlify/version.rb

@@ -1,5 +1,5 @@
 # encoding: UTF-8
 
 module Titlify
-  VERSION = "0.2.0"
+  VERSION = "0.3.0"
 end

data/spec/titlify_spec.rb

@@ -26,11 +26,54 @@ describe Titlify do
 
   it "capitalizes the first letter after a hyphen" do
     title = "that shit-faced guy fell over the curb".titlify
-    title.should eq("That Shit-Faced Guy Fell Over the Curb")
+    title.should eq("That Shit-Faced Guy Fell over the Curb")
   end
 
   it "capitalizes the first word following a colon" do
     title = "the big guns: a little man's tale".titlify
     title.should eq("The Big Guns: A Little Man's Tale")
   end
+
+  it "capitalizes words that begin with small words" do
+    # Without punctuation
+    title = "another ardvark used a thesaurus in overgrowth".titlify
+    title.should eq("Another Ardvark Used a Thesaurus in Overgrowth")
+  end
+
+  it "capitalizes the first letter when '/' is used" do
+    title = "this is a cat/dog thing".titlify
+    title.should eq("This Is a Cat/Dog Thing")
+  end
+
+  it "capitalizes the New York Times correctly" do
+    title = "the new york times prints a newspaper".titlify
+    title.should eq("The New York Times Prints a Newspaper")
+  end
+
+  it "capitalizes words in quotes correctly" do
+    title = 'the "best" are in the cards'.titlify
+    title.should eq('The "Best" Are in the Cards')
+    title = 'sometimes "more than one thing ends up in quotes" and stuff'.titlify
+    title.should eq('Sometimes "More than One Thing Ends up in Quotes" and Stuff')
+  end
+
+  it "keeps domain names in lowercase n stuff" do
+    # With HTTP
+    title = "look at http://www.wikipedia.org sometime".titlify
+    title.should eq("Look at http://www.wikipedia.org Sometime")
+
+    # With www, without HTTP
+    title = "look at www.wikipedia.org sometime".titlify
+    title.should eq("Look at www.wikipedia.org Sometime")
+
+    # Without www and HTTP
+    title = "look at en.wikipedia.org sometime".titlify
+    title.should eq("Look at en.wikipedia.org Sometime")
+
+    title = "look at wikipedia.org sometime".titlify
+    title.should eq("Look at wikipedia.org Sometime")
+
+    title = "look at wikipedia.co.uk sometime".titlify
+    title.should eq("Look at wikipedia.co.uk Sometime")
+  end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: titlify
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.3.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-02-14 00:00:00.000000000 Z
+date: 2012-02-21 00:00:00.000000000 Z
 dependencies: []
 description: Gonna be the best damn titlecasing function around.
 email:
@@ -24,8 +24,10 @@ files:
 - Gemfile.lock
 - Guardfile
 - README.markdown
+- Rakefile
 - lib/titlify.rb
 - lib/titlify/data/smart_format_rules.rb
+- lib/titlify/data/word_lists.rb
 - lib/titlify/string_extensions.rb
 - lib/titlify/titlecase.rb
 - lib/titlify/version.rb
@@ -44,12 +46,18 @@ required_ruby_version: !ruby/object:Gem::Requirement
   - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
+      segments:
+      - 0
+      hash: 327711217174080911
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
   - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
+      segments:
+      - 0
+      hash: 327711217174080911
 requirements: []
 rubyforge_project: titlify
 rubygems_version: 1.8.11
@@ -59,4 +67,3 @@ summary: Gonna be the best damn titlecasing function around.
 test_files:
 - spec/spec_helper.rb
 - spec/titlify_spec.rb
-has_rdoc: