ghazel-truncate_html 0.2.1.1

data/.gitignore

@@ -0,0 +1,2 @@
+pkg
+coverage

data/README.markdown

@@ -0,0 +1,53 @@
+TruncateHtml
+============
+
+truncate_html is a Rails helper plugin that [cuts off](http://www.youtube.com/watch?v=6XG4DIOA7nU) a string of HTML and takes care of closing any lingering open tags. There are many possible solutions to this. This plugin does not have any dependencies, and does all it's work via [regular expressions](http://xkcd.com/208/).
+
+The API is very similar to Rails' own truncate method.
+
+
+Example
+-------
+
+    some_html = '<ul><li><a href="http://whatever">This is a link</a></li></ul>'
+
+    truncate_html(some_html, :length => 5, :omission => '...(continued)')
+
+      => <ul><li><a href="http://whatever">This is...(continued)</a></li></ul>
+
+
+A few notes:
+
+* It will truncate on a word boundary.
+* The default options are:
+  * :length => 100
+  * :omission => '...'
+
+Installation
+------------
+
+#### As a gem
+Add this to your <code>config/environment.rb</code>:
+
+    config.gem 'truncate_html',
+      :source => 'http://gemcutter.org'
+
+Then either
+<code>sudo rake gems:install</code>
+or
+<code>sudo gem install truncate_html</code>
+
+#### As a plugin:
+<code>script/plugin install git://github.com/hgimenez/truncate_html.git</code>
+
+Issues
+------
+
+Found an issue? Please report it on [Github's issue tracker](http://github.com/hgimenez/truncate_html/issues).
+
+Testing
+-------
+
+The plugin is tested using RSpec. [Install it](http://wiki.github.com/dchelimsky/rspec/rails) on your app if you wish to run the tests.
+
+Copyright (c) 2009 Harold A. Giménez, released under the MIT license

data/Rakefile

@@ -0,0 +1,36 @@
+require 'rake'
+require 'spec/rake/spectask'
+
+desc 'Default: run specs.'
+task :default => :spec
+
+desc 'Run the specs'
+Spec::Rake::SpecTask.new(:spec) do |t|
+  t.spec_opts = ['--colour --format progress --loadby mtime --reverse']
+  t.spec_files = FileList['spec/**/*_spec.rb']
+end
+
+Spec::Rake::SpecTask.new(:rcov) do |spec|
+  spec.libs << 'lib' << 'spec'
+  spec.pattern = 'spec/**/*_spec.rb'
+  spec.rcov = true
+end
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gem|
+    gem.name = "truncate_html"
+    gem.summary = %Q{Uses an API similar to Rails' truncate helper to truncate HTML and close any lingering open tags.}
+    gem.description = %Q{Truncates html so you don't have to}
+    gem.email = "harold.gimenez@gmail.com"
+    gem.homepage = "http://github.com/hgimenez/truncate_html"
+    gem.authors = ["hgimenez"]
+    # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
+  end
+  Jeweler::GemcutterTasks.new
+
+rescue LoadError
+  puts "Jeweler (or a dependency) not available. Install it with: sudo gem install jeweler"
+end
+
+

data/VERSION

@@ -0,0 +1 @@
+0.2.1

data/init.rb

@@ -0,0 +1 @@
+require 'truncate_html'

data/install.rb

@@ -0,0 +1 @@
+# Install hook code here

data/lib/app/helpers/truncate_html_helper.rb

@@ -0,0 +1,7 @@
+module TruncateHtmlHelper
+
+  def truncate_html(html, options={})
+    TruncateHtml::HtmlTruncator.new(html).truncate(options)
+  end
+
+end

data/lib/truncate_html.rb

@@ -0,0 +1,10 @@
+path =  File.join(File.dirname(__FILE__), 'app', 'helpers')  
+$LOAD_PATH << path 
+ActiveSupport::Dependencies.load_paths << path 
+ActiveSupport::Dependencies.load_once_paths.delete(path) 
+
+require File.join(File.dirname(__FILE__), 'truncate_html', 'html_truncator')
+
+ActionView::Base.class_eval do
+  include TruncateHtmlHelper
+end

data/lib/truncate_html/html_truncator.rb

@@ -0,0 +1,74 @@
+module TruncateHtml
+  class HtmlTruncator
+
+    UNPAIRED_TAGS = %w(br hr img)
+
+    def initialize(original_html)
+      @original_html = original_html
+    end
+
+    def truncate(options = {})
+      return '' if @original_html.nil?
+      options[:length] ||= 100
+      options[:omission] ||= '...'
+      @chars_remaining = options[:length] - options[:omission].length
+      @open_tags, result = [], ['']
+
+      html_tokens.each do |str|
+        if @chars_remaining > 0
+          if html_tag?(str)
+            if open_tag?(str)
+              @open_tags << str
+            else
+              open_tags = remove_latest_open_tag(str)
+            end
+          else
+            @chars_remaining -= str.length
+          end
+          result << str
+        else
+          result[-1] = result[-1].rstrip + options[:omission]
+          @open_tags.reverse_each do |open_tag|
+            result << matching_close_tag(open_tag)
+          end
+          break
+        end
+      end
+      result.join('')
+    end
+
+    def html_tokens
+      @original_html.scan(/(?:<script.*>.*<\/script>)+|<\/?[^>]+>|[\w\|`~!@#\$%^&*\(\)\-_\+=\[\]{}:;'",\.\/?]+|\s+/).map do
+        |t| t.gsub(
+          #remove newline characters
+            /\n/,''
+        ).gsub(
+          #clean out extra consecutive whitespace
+            /\s+/, ' '
+        )
+      end
+    end
+
+    def html_tag?(string)
+      string =~ /<\/?[^>]+>/ ? true : false
+    end
+
+    def open_tag?(html_tag)
+      html_tag =~ /<(?!(?:#{UNPAIRED_TAGS.join('|')}|script|\/))[^>]+>/i ? true : false
+    end
+
+    def remove_latest_open_tag(close_tag)
+      (0...@open_tags.length).to_a.reverse.each do |i|
+        if matching_close_tag(@open_tags[i]) == close_tag
+          @open_tags.delete_at(i)
+          break
+        end
+      end
+    end
+
+    def matching_close_tag(open_tag)
+      open_tag.gsub(/<(\w+)\s?.*>/, '</\1>').strip
+    end
+
+  end
+end

data/spec/helpers/truncate_html_helper_spec.rb

@@ -0,0 +1,113 @@
+require File.join(File.dirname(__FILE__), '..', 'spec_helper')
+
+include TruncateHtmlHelper
+
+describe TruncateHtmlHelper do
+
+  it 'is included in ActionView::Base' do
+    ActionView::Base.included_modules.should include(TruncateHtmlHelper)
+  end
+
+  describe '#truncate_html' do
+
+    it "includes the omission text's length in the returned truncated html" do
+      truncate_html('a b c', :length => 4, :omission => '...').should == 'a...'
+    end
+
+    it "supports omisions longer than the maximum length" do
+      truncate_html('a b c', :length => 2, :omission => '...').should == '...'
+    end
+
+    context 'the input html is nil' do
+      it 'returns an empty string' do
+        truncate_html(nil).should be_empty
+        truncate_html(nil).should be_kind_of(String)
+      end
+    end
+
+    context 'the input html contains a script tag' do
+      before(:each) do
+        @input_html = "<p>I have a script <script type=text/javascript>document.write('lum dee dum');</script> and more text</p>"
+        @expected_out = "<p>I have a script <script type=text/javascript>document.write('lum dee dum');</script> and...</p>"
+      end
+      it 'treats the script tag as lengthless string' do
+        truncate_html(@input_html, :length => 23).should == @expected_out
+      end
+    end
+
+    context 'truncating in the middle of a link' do
+      before(:each) do
+        @html = '<div><ul><li>Look at <a href="foo">this</a> link </li></ul></div>'
+      end
+
+      it 'truncates, and closes the <a>, and closes any remaining open tags' do
+        truncate_html(@html, :length => 14).should == '<div><ul><li>Look at <a href="foo">this...</a></li></ul></div>'
+      end
+    end
+
+    %w(! @ # $ % ^ & * \( \) - _ + = [ ] { } \ | , . / ?).each do |char|
+      context "when the html has a #{char} character after a closing tag" do
+        before(:each) do
+          @html = "<p>Look at <strong>this</strong>#{char} More words here</p>"
+        end
+        it 'places the punctuation after the tag without any whitespace' do
+          truncate_html(@html, :length => 19).should == "<p>Look at <strong>this</strong>#{char} More...</p>"
+        end
+      end
+    end
+
+    context 'when the html has a non punctuation character after a closing tag' do
+      before(:each) do
+        @html = '<p>Look at <a href="awesomeful.net">this</a> link for randomness</p>'
+      end
+      it 'leaves a whitespace between the closing tag and the following word character' do
+        truncate_html(@html, :length => 21).should == '<p>Look at <a href="awesomeful.net">this</a> link...</p>'
+      end
+    end
+
+    #unusual, but just covering my ass
+    context 'when the HTML tags are multiline' do 
+      before(:each) do
+        @html = <<-END_HTML
+          <div id="foo"
+                class="bar">
+          This is ugly html.
+          </div>
+        END_HTML
+      end
+
+      it 'recognizes the multiline html properly' do
+        truncate_html(@html, :length => 12).should == ' <div id="foo" class="bar"> This is...</div>'
+      end
+    end
+
+    %w(br hr img).each do |unpaired_tag|
+      context "when the html contains a #{unpaired_tag} tag" do
+
+        context "and the #{unpaired_tag} does not have the closing slash" do
+          before(:each) do
+            @html = "<div>Some before. <#{unpaired_tag}>and some after</div>"
+            @html_caps = "<div>Some before. <#{unpaired_tag.capitalize}>and some after</div>"
+          end
+          it "does not close the #{unpaired_tag} tag" do
+            truncate_html(@html, :length => 19).should == "<div>Some before. <#{unpaired_tag}>and...</div>"
+            truncate_html(@html_caps, :length => 19).should == "<div>Some before. <#{unpaired_tag.capitalize}>and...</div>"
+          end
+        end
+
+        context "and the #{unpaired_tag} does have the closing slash" do
+          before(:each) do
+            @html = "<div>Some before. <#{unpaired_tag} />and some after</div>"
+            @html_caps = "<div>Some before. <#{unpaired_tag.capitalize} />and some after</div>"
+          end
+          it "does not close the #{unpaired_tag} tag" do
+            truncate_html(@html, :length => 19).should == "<div>Some before. <#{unpaired_tag} />and...</div>"
+            truncate_html(@html_caps, :length => 19).should == "<div>Some before. <#{unpaired_tag.capitalize} />and...</div>"
+          end
+        end
+
+      end
+    end
+  end
+
+end

data/spec/spec_helper.rb

@@ -0,0 +1,9 @@
+begin
+  require File.dirname(__FILE__) + '/../../../../spec/spec_helper'
+rescue LoadError
+  puts "You need to install rspec in your base app"
+  exit
+end
+
+plugin_spec_dir = File.dirname(__FILE__)
+require File.join(File.dirname(__FILE__), '..', 'lib', 'app', 'helpers', 'truncate_html_helper')

data/spec/truncate_html/html_truncator_spec.rb

@@ -0,0 +1,75 @@
+require File.join(File.dirname(__FILE__), '..', 'spec_helper')
+
+describe TruncateHtml::HtmlTruncator do
+
+  def truncator(html = nil)
+    @truncator ||= TruncateHtml::HtmlTruncator.new(html)
+  end
+
+  describe '#html_tokens' do
+    before(:each) do
+      @html = '<h1>Hi there</h1> <p>This          is sweet!</p>'
+    end
+
+    it 'returns each token in the string as an array element removing any consecutive whitespace from the string' do
+      truncator(@html).html_tokens.should == ['<h1>', 'Hi', ' ', 'there', '</h1>', ' ', '<p>', 'This', ' ', 'is', ' ', 'sweet!', '</p>']
+    end
+
+  end
+
+  describe '#html_tag?' do
+
+    it 'returns false when the string parameter is not an html tag' do
+      truncator.html_tag?('no tags').should be_false
+    end
+
+    it 'returns true when the string parameter is an html tag' do
+      truncator.html_tag?('<img src="foo">').should be_true
+      truncator.html_tag?('</img>').should be_true
+    end
+
+  end
+
+  describe '#open_tag?' do
+
+    it 'returns true if the tag is an open tag' do
+      truncator.open_tag?('<a>').should be_true
+    end
+
+    it 'returns true if the tag is an open tag, and has whitespace and html properties with either single or double quotes' do
+      truncator.open_tag?(' <a href="http://awesomeful.net">').should be_true
+      truncator.open_tag?(" <a href='http://awesomeful.net' >").should be_true
+    end
+
+    it 'returns false if the tag is a close tag' do
+      truncator.open_tag?('</a>').should be_false
+    end
+
+    it 'returns false if the string is not an html tag' do
+      truncator.open_tag?('foo bar').should be_false
+    end
+
+    it 'returns false if it is a <script> tag' do
+      truncator.open_tag?('<script>').should be_false
+    end
+  end
+
+  describe '#matching_close_tag' do
+
+    it 'closes a tag given an open tag' do
+      truncator.matching_close_tag('<a>').should == '</a>'
+      truncator.matching_close_tag(' <div>').should == '</div>'
+      truncator.matching_close_tag('<h1>').should == '</h1>'
+      truncator.matching_close_tag('<a href="foo">').should == '</a>'
+    end
+  end
+
+  describe 'nil string' do
+
+    it 'returns an empty string' do
+      truncator(nil).truncate.should be_empty
+      truncator(nil).truncate.should be_kind_of(String)
+    end
+  end
+
+end

data/tasks/truncate_html_tasks.rake

@@ -0,0 +1,4 @@
+# desc "Explaining what the task does"
+# task :truncate_html do
+#   # Task goes here
+# end

data/truncate_html.gemspec

@@ -0,0 +1,55 @@
+# Generated by jeweler
+# DO NOT EDIT THIS FILE
+# Instead, edit Jeweler::Tasks in Rakefile, and run `rake gemspec`
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{ghazel-truncate_html}
+  s.version = "0.2.1.1"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["hgimenez"]
+  s.date = %q{2009-12-18}
+  s.description = %q{Truncates html so you don't have to}
+  s.email = %q{harold.gimenez@gmail.com}
+  s.extra_rdoc_files = [
+    "README.markdown"
+  ]
+  s.files = [
+    ".gitignore",
+     "README.markdown",
+     "Rakefile",
+     "VERSION",
+     "init.rb",
+     "install.rb",
+     "lib/app/helpers/truncate_html_helper.rb",
+     "lib/truncate_html.rb",
+     "lib/truncate_html/html_truncator.rb",
+     "spec/helpers/truncate_html_helper_spec.rb",
+     "spec/spec_helper.rb",
+     "spec/truncate_html/html_truncator_spec.rb",
+     "tasks/truncate_html_tasks.rake",
+     "truncate_html.gemspec",
+     "uninstall.rb"
+  ]
+  s.homepage = %q{http://github.com/hgimenez/truncate_html}
+  s.rdoc_options = ["--charset=UTF-8"]
+  s.require_paths = ["lib"]
+  s.rubygems_version = %q{1.3.5}
+  s.summary = %q{Uses an API similar to Rails' truncate helper to truncate HTML and close any lingering open tags.}
+  s.test_files = [
+    "spec/helpers/truncate_html_helper_spec.rb",
+     "spec/spec_helper.rb",
+     "spec/truncate_html/html_truncator_spec.rb"
+  ]
+
+  if s.respond_to? :specification_version then
+    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
+    s.specification_version = 3
+
+    if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
+    else
+    end
+  else
+  end
+end

data/uninstall.rb

@@ -0,0 +1 @@
+# Uninstall hook code here

metadata

@@ -0,0 +1,71 @@
+--- !ruby/object:Gem::Specification 
+name: ghazel-truncate_html
+version: !ruby/object:Gem::Version 
+  version: 0.2.1.1
+platform: ruby
+authors: 
+- hgimenez
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2009-12-18 00:00:00 -08:00
+default_executable: 
+dependencies: []
+
+description: Truncates html so you don't have to
+email: harold.gimenez@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- README.markdown
+files: 
+- .gitignore
+- README.markdown
+- Rakefile
+- VERSION
+- init.rb
+- install.rb
+- lib/app/helpers/truncate_html_helper.rb
+- lib/truncate_html.rb
+- lib/truncate_html/html_truncator.rb
+- spec/helpers/truncate_html_helper_spec.rb
+- spec/spec_helper.rb
+- spec/truncate_html/html_truncator_spec.rb
+- tasks/truncate_html_tasks.rake
+- truncate_html.gemspec
+- uninstall.rb
+has_rdoc: true
+homepage: http://github.com/hgimenez/truncate_html
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --charset=UTF-8
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.5
+signing_key: 
+specification_version: 3
+summary: Uses an API similar to Rails' truncate helper to truncate HTML and close any lingering open tags.
+test_files: 
+- spec/helpers/truncate_html_helper_spec.rb
+- spec/spec_helper.rb
+- spec/truncate_html/html_truncator_spec.rb