truncate_html_chinese 0.1.0

data/spec/spec.opts

@@ -0,0 +1,2 @@
+--color
+--format progress

data/spec/spec_helper.rb

@@ -0,0 +1,11 @@
+ENV["RAILS_ENV"] ||= 'test'
+rails_root = File.expand_path('../rails_root', __FILE__)
+require rails_root + '/config/environment.rb'
+
+require 'rspec/rails'
+
+require File.expand_path('../../lib/truncate_html', __FILE__)
+
+RSpec.configure do |config|
+  config.mock_with :rspec
+end

data/spec/truncate_html/configuration_spec.rb

@@ -0,0 +1,17 @@
+require File.join(File.dirname(__FILE__), '..', 'spec_helper')
+
+describe TruncateHtml::Configuration do
+
+  describe 'self.configure' do
+
+    it 'yields the configuration object' do
+      lambda do
+        TruncateHtml.configure do |config|
+          config.should be_kind_of(TruncateHtml::Configuration)
+          throw :yay_it_yielded
+        end
+      end.should throw_symbol(:yay_it_yielded)
+    end
+
+  end
+end

data/spec/truncate_html/html_string_spec.rb

@@ -0,0 +1,80 @@
+require File.join(File.dirname(__FILE__), '..', 'spec_helper')
+
+describe TruncateHtml::HtmlString do
+
+  def html_string(original_string)
+    TruncateHtml::HtmlString.new(original_string)
+  end
+
+  describe '#html_tokens' do
+    it 'returns each token in the string as an array element removing any consecutive whitespace from the string' do
+      html = '<h1>Hi there</h1> <p>This          is sweet!</p>'
+      html_string(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
+      html_string('no tags').should_not be_html_tag
+    end
+
+    it 'returns true when the string parameter is an html tag' do
+      html_string('<img src="foo">').should be_html_tag
+      html_string('</img>').should be_html_tag
+    end
+
+    it 'is false for html comments' do
+      html_string('<!-- hi -->').should_not be_html_tag
+    end
+  end
+
+  describe '#open_tag?' do
+    it 'returns true if the tag is an open tag' do
+      html_string('<a>').should be_open_tag
+    end
+
+    context 'the tag is an open tag, and has whitespace and html properties' do
+      it 'returns true if it has single quotes' do
+        html_string(" <a href='http://awesomeful.net' >").should be_open_tag
+      end
+
+      it 'returns true if it has double quotes' do
+        html_string(' <a href="http://awesomeful.net">').should be_open_tag
+      end
+    end
+
+    it 'returns false if the tag is a close tag' do
+      html_string('</a>').should_not be_open_tag
+    end
+
+    it 'returns false if the string is not an html tag' do
+      html_string('foo bar').should_not be_open_tag
+    end
+
+    it 'returns false if it is a <script> tag' do
+      html_string('<script>').should_not be_open_tag
+    end
+  end
+
+  describe '#matching_close_tag' do
+    tag_pairs = { '<a>'            => '</a>',
+                  ' <div>'         => '</div>',
+                  '<h1>'           => '</h1>',
+                  '<a href="foo">' => '</a>' }
+
+    tag_pairs.each do |open_tag, close_tag|
+      it "closes a #{open_tag} and returns #{close_tag}" do
+        html_string(open_tag).matching_close_tag.should == close_tag
+      end
+    end
+  end
+
+  describe '#html_comment?' do
+    it 'is true for HTML comments' do
+      html_string('<!-- hi -->').should be_html_comment
+      html_string('<a>').should_not be_html_comment
+      html_string('</a>').should_not be_html_comment
+      html_string('foo').should_not be_html_comment
+    end
+  end
+end

data/spec/truncate_html/html_truncator_spec.rb

@@ -0,0 +1,203 @@
+# Encoding: UTF-8
+require File.join(File.dirname(__FILE__), '..', 'spec_helper')
+
+describe TruncateHtml::HtmlTruncator do
+
+  def truncate(html, opts = {})
+    html_string = TruncateHtml::HtmlString.new(html)
+    TruncateHtml::HtmlTruncator.new(html_string, opts).truncate
+  end
+
+  context 'when the word_boundary option is set to false' do
+    it 'truncates to the exact length specified' do
+      truncate('<div>123456789</div>', :length => 5, :omission => '', :word_boundary => false).should == '<div>12345</div>'
+    end
+
+    it 'retains the tags within the text' do
+      html = 'some text <span class="caps">CAPS</span> some text'
+      truncate(html, :length => 25, :word_boundary => false).should == 'some text <span class="caps">CAPS</span> some te...'
+    end
+
+    context 'and a custom omission value is passed' do
+      it 'retains the omission text' do
+        truncate("testtest", :length => 10, :omission => '..', :word_boundary => false).should == 'testtest..'
+      end
+
+      it 'handles multibyte characters' do
+        truncate("prüfenprüfen", :length => 8, :omission => '..', :word_boundary => false). should == 'prüfen..'
+      end
+    end
+  end
+
+  context 'when the word_boundary option is set to true' do
+    it 'truncates using the default word_boundary option' do
+      truncate('hello there. or maybe not?', :length => 16, :omission => '', :word_boundary => true).should == 'hello there. or'
+    end
+  end
+
+  context 'when the word_boundary option is a custom value (for splitting on sentences)' do
+    it 'truncates to the end of the nearest sentence' do
+      truncate('hello there. or maybe not?', :length => 16, :omission => '', :word_boundary => /\S[\.\?\!]/).should == 'hello there.'
+    end
+  end
+
+  it "includes the omission text's length in the returned truncated html" do
+    truncate('a b c', :length => 4, :omission => '...').should == 'a...'
+  end
+
+  it "includes omission even on the edge (issue #18)" do
+    opts = { :word_boundary => false, :length => 12 }
+    truncate('One two three', opts).should == 'One two t...'
+  end
+
+  it "never returns a string longer than :length" do
+    truncate("test this shit", :length => 10).should == 'test...'
+  end
+
+  it 'supports omissions longer than the maximum length' do
+    lambda { truncate('', :length => 1, :omission => '...') }.should_not raise_error
+  end
+
+  it 'returns the omission when the specified length is smaller than the omission' do
+    truncate('a b c', :length => 2, :omission => '...').should == '...'
+  end
+
+  it 'treats script tags as strings with no length' 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>"
+    truncate(input_html, :length => 23).should == expected_out
+  end
+
+  it 'in the middle of a link, truncates and closes the <a>, and closes any remaining open tags' do
+    html     = '<div><ul><li>Look at <a href = "foo">this</a> link </li></ul></div>'
+    expected = '<div><ul><li>Look at <a href = "foo">this...</a></li></ul></div>'
+    truncate(html, :length => 15).should == expected
+  end
+
+  %w(! @ # $ % ^ & * \( \) - _ + = [ ] { } \ | , . / ?).each do |char|
+    context "when the html has a #{char} character after a closing tag" do
+      it 'places the punctuation after the tag without any whitespace' do
+        html     = "<p>Look at <strong>this</strong>#{char} More words here</p>"
+        expected = "<p>Look at <strong>this</strong>#{char}...</p>"
+        truncate(html, :length => 19).should == expected
+      end
+    end
+  end
+
+  context 'when the html has a non punctuation character after a closing tag' do
+    it 'leaves a whitespace between the closing tag and the following word character' do
+      html     = '<p>Look at <a href = "awesomeful.net">this</a> link for randomness</p>'
+      expected = '<p>Look at <a href = "awesomeful.net">this</a> link...</p>'
+      truncate(html, :length => 21).should == expected
+    end
+  end
+
+  it 'handles multibyte characters and leaves them in the result' do
+    html     = '<p>Look at our multibyte characters ā ž <a href = "awesomeful.net">this</a> link for randomness ā ž</p>'
+    truncate(html, :length => html.length).should == html
+  end
+
+  #unusual, but just covering my ass
+  it 'recognizes the multiline html properly' do
+    html = <<-END_HTML
+      <div id="foo"
+            class="bar">
+      This is ugly html.
+      </div>
+    END_HTML
+    truncate(html, :length => 12).should == ' <div id="foo" class="bar"> This is...</div>'
+  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
+        it "does not close the #{unpaired_tag} tag" do
+          html      = "<div>Some before. <#{unpaired_tag}>and some after</div>"
+          html_caps = "<div>Some before. <#{unpaired_tag.capitalize}>and some after</div>"
+          truncate(html, :length => 19).should == "<div>Some before. <#{unpaired_tag}>and...</div>"
+          truncate(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
+        it "does not close the #{unpaired_tag} tag" do
+          html      = "<div>Some before. <#{unpaired_tag} />and some after</div>"
+          html_caps = "<div>Some before. <#{unpaired_tag.capitalize} />and some after</div>"
+          truncate(html, :length => 19).should == "<div>Some before. <#{unpaired_tag} />and...</div>"
+          truncate(html_caps, :length => 19).should == "<div>Some before. <#{unpaired_tag.capitalize} />and...</div>"
+        end
+      end
+
+    end
+  end
+
+  it 'does not truncate quotes off when input contains chinese characters' do
+    html = "<p>“我现在使用的是中文的拼音。”<br>
+    测试一下具体的truncate<em>html功能。<br>
+    “我现在使用的是中文的拼音。”<br>
+    测试一下具体的truncate</em>html功能。<br>
+    “我现在使用的是中文的拼音。”<br>
+    测试一下具体的truncate<em>html功能。<br>
+    “我现在使用的是中文的拼音。”<br>
+    测试一下具体的truncate</em>html功能。</p>"
+
+    result = truncate(html, :omission => "", :length => 50)
+    result.should include "<p>“我现在使用的是中文的拼音。”<br>"
+  end
+
+  context 'when the break_token option is set as <!-- truncate -->' do
+    it 'does not truncate abnormally if the break_token is not present' do
+      truncate('This is line one. This is line two.', :length => 30, :break_token => '<!-- truncate -->').should == 'This is line one. This is...'
+    end
+    it 'does not truncate abnormally if the break_token is present, but beyond the length param' do
+      truncate('This is line one. This is line <!-- truncate --> two.', :length => 30, :break_token => '<!-- truncate -->').should == 'This is line one. This is...'
+    end
+    it 'truncates before the length param if the break_token is before the token at "length"' do
+      truncate('This is line one. <!-- truncate --> This is line two.', :length => 30, :break_token => '<!-- truncate -->').should == 'This is line one.'
+    end
+  end
+
+  context 'when the break_token option is customized as a comment' do
+    it 'does not truncate abnormally if the break_token is not present' do
+      truncate('This is line one. This is line two.', :length => 30, :break_token => '<!-- break -->').should == 'This is line one. This is...'
+    end
+    it 'does not truncate abnormally if the break_token is present, but beyond the length param' do
+      truncate('This is line one. This is line <!-- break --> two.', :length => 30, :break_token => '<!-- break -->').should == 'This is line one. This is...'
+    end
+    it 'truncates before the length param if the break_token is before the token at "length"' do
+      truncate('This is line one. <!-- break --> This is line two.', :length => 30, :break_token => '<!-- break -->').should == 'This is line one.'
+    end
+  end
+
+  context 'when the break_token option is customized as an html tag' do
+    it 'does not truncate abnormally if the break_token is not present' do
+      truncate('This is line one. This is line two.', :length => 30, :break_token => '<break />').should == 'This is line one. This is...'
+    end
+    it 'does not truncate abnormally if the break_token is present, but beyond the length param' do
+      truncate('This is line one. This is line <break /> two.', :length => 30, :break_token => '<break />').should == 'This is line one. This is...'
+    end
+    it 'truncates before the length param if the break_token is before the token at "length"' do
+      truncate('This is line one. <break /> This is line two.', :length => 30, :break_token => '<break />').should == 'This is line one.'
+    end
+  end
+
+  context 'when the break_token option is customized as a word' do
+    it 'does not truncate abnormally if the break_token is not present' do
+      truncate('This is line one. This is line two.', :length => 30, :break_token => 'foobar').should == 'This is line one. This is...'
+    end
+    it 'does not truncate abnormally if the break_token is present, but beyond the length param' do
+      truncate('This is line one. This is line foobar two.', :length => 30, :break_token => 'foobar').should == 'This is line one. This is...'
+    end
+    it 'truncates before the length param if the break_token is before the token at "length"' do
+      truncate('This is line one. foobar This is line two.', :length => 30, :break_token => 'foobar').should == 'This is line one.'
+    end
+  end
+
+  context 'a string with comments' do
+    it 'does not duplicate comments (issue #32)' do
+      truncate('<h1>hello <!-- stuff --> and <!-- la --> goodbye</h1>', length: 15).should ==
+        '<h1>hello <!-- stuff --> and <!-- la -->...</h1>'
+    end
+  end
+end

data/truncate_html.gemspec

@@ -0,0 +1,23 @@
+# -*- encoding: utf-8 -*-
+$:.push File.expand_path("../lib", __FILE__)
+require "truncate_html/version"
+
+Gem::Specification.new do |s|
+  s.name        = "truncate_html_chinese"
+  s.version     = '0.1.0'
+  s.authors     = ["pobing"]
+  s.email       = ["cn.jdong@gmail.com"]
+  s.homepage    = "https://github.com/pobing/truncate_html_chinese"
+  s.summary     = %q{Uses an API similar to Rails' truncate helper to truncate HTML and close any lingering open tags.}
+  s.description = %q{Truncates html so you don't have to,support chinese}
+
+  s.files         = `git ls-files`.split("\n")
+  s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  s.require_paths = ["lib"]
+
+  s.required_ruby_version = '>= 1.9'
+
+  s.add_development_dependency "rspec-rails", "~> 2.9"
+  s.add_development_dependency "rails", "~> 3.0.3"
+end

metadata

@@ -0,0 +1,117 @@
+--- !ruby/object:Gem::Specification
+name: truncate_html_chinese
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- pobing
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-05-02 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rspec-rails
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.9'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.9'
+- !ruby/object:Gem::Dependency
+  name: rails
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 3.0.3
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 3.0.3
+description: Truncates html so you don't have to,support chinese
+email:
+- cn.jdong@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- .travis.yml
+- Gemfile
+- Gemfile.lock
+- History.txt
+- LICENSE
+- README.md
+- Rakefile
+- VERSION
+- init.rb
+- lib/app/helpers/truncate_html_helper.rb
+- lib/truncate_html.rb
+- lib/truncate_html/configuration.rb
+- lib/truncate_html/html_string.rb
+- lib/truncate_html/html_truncator.rb
+- lib/truncate_html/version.rb
+- spec/helpers/truncate_html_helper_spec.rb
+- spec/rails_root/Gemfile
+- spec/rails_root/Gemfile.lock
+- spec/rails_root/app/controllers/application_controller.rb
+- spec/rails_root/app/helpers/application_helper.rb
+- spec/rails_root/config/application.rb
+- spec/rails_root/config/boot.rb
+- spec/rails_root/config/database.yml
+- spec/rails_root/config/environment.rb
+- spec/rails_root/config/environments/development.rb
+- spec/rails_root/config/environments/production.rb
+- spec/rails_root/config/environments/test.rb
+- spec/rails_root/config/initializers/backtrace_silencers.rb
+- spec/rails_root/config/initializers/inflections.rb
+- spec/rails_root/config/initializers/mime_types.rb
+- spec/rails_root/config/initializers/new_rails_defaults.rb
+- spec/rails_root/config/initializers/session_store.rb
+- spec/rails_root/config/locales/en.yml
+- spec/rails_root/config/routes.rb
+- spec/rails_root/init.rb
+- spec/rails_root/lib/app/helpers/truncate_html_helper.rb
+- spec/rails_root/lib/tasks/rspec.rake
+- spec/spec.opts
+- spec/spec_helper.rb
+- spec/truncate_html/configuration_spec.rb
+- spec/truncate_html/html_string_spec.rb
+- spec/truncate_html/html_truncator_spec.rb
+- truncate_html-0.9.2.gem
+- truncate_html.gemspec
+homepage: https://github.com/pobing/truncate_html_chinese
+licenses: []
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '1.9'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.0.3
+signing_key: 
+specification_version: 4
+summary: Uses an API similar to Rails' truncate helper to truncate HTML and close
+  any lingering open tags.
+test_files: []