truncate_html 0.5.3 → 0.5.4

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    truncate_html (0.5.3)
+    truncate_html (0.5.4)
 
 GEM
   remote: http://rubygems.org/

data/lib/truncate_html/configuration.rb

@@ -11,5 +11,4 @@ module TruncateHtml
     self.configuration ||= Configuration.new
     yield configuration
   end
-
 end

data/lib/truncate_html/html_string.rb

@@ -1,7 +1,8 @@
+# encoding: utf-8
 module TruncateHtml
   class HtmlString < String
 
-    UNPAIRED_TAGS = %w(br hr img)
+    UNPAIRED_TAGS = %w(br hr img).freeze
 
     def initialize(original_html)
       super(original_html)
@@ -33,7 +34,7 @@ module TruncateHtml
 
     private
     def regex
-      /(?:<script.*>.*<\/script>)+|<\/?[^>]+>|[#{"[[:alpha:]]" if RUBY_VERSION >= '1.9'}\w\|`~!@#\$%^&*\(\)\-_\+=\[\]{}:;'",\.\/?]+|\s+/
+      /(?:<script.*>.*<\/script>)+|<\/?[^>]+>|[#{"[[:alpha:]]" if RUBY_VERSION >= '1.9'}\w\|`~!@#\$%^&*\(\)\-_\+=\[\]{}:;'",\.\/?]+|\s+|\p{P}/
     end
 
   end

data/lib/truncate_html/version.rb

@@ -1,3 +1,3 @@
 module TruncateHtml
-  VERSION = "0.5.3"
+  VERSION = "0.5.4"
 end

data/spec/truncate_html/html_string_spec.rb

@@ -7,70 +7,61 @@ describe TruncateHtml::HtmlString do
   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
-      html_string(@html).html_tokens.should == ['<h1>', 'Hi', ' ', 'there', '</h1>', ' ', '<p>', 'This', ' ', 'is', ' ', 'sweet!', '</p>']
+      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').html_tag?.should be_false
+      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">').html_tag?.should be_true
-      html_string('</img>').html_tag?.should be_true
+      html_string('<img src="foo">').should be_html_tag
+      html_string('</img>').should be_html_tag
     end
-
   end
 
   describe '#open_tag?' do
-
     it 'returns true if the tag is an open tag' do
-      html_string('<a>').open_tag?.should be_true
+      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' >").open_tag?.should be_true
+        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">').open_tag?.should be_true
+        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>').open_tag?.should be_false
+      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').open_tag?.should be_false
+      html_string('foo bar').should_not be_open_tag
     end
 
     it 'returns false if it is a <script> tag' do
-      html_string('<script>').open_tag?.should be_false
+      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 = { '<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
-
 end

data/spec/truncate_html/html_truncator_spec.rb

@@ -8,128 +8,115 @@ describe TruncateHtml::HtmlTruncator do
     TruncateHtml::HtmlTruncator.new(html_string).truncate(opts)
   end
 
-  describe '#truncate' do
-
-    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 '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 "includes the omission text's length in the returned truncated html" do
-      truncate('a b c', :length => 4, :omission => '...').should == 'a...'
+    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
+  end
 
-    it "never returns a string longer than :length" do
-      truncate("test this shit", :length => 10).should == 'test...'
-    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 'supports omissions longer than the maximum length' do
-      lambda { truncate('', :length => 1, :omission => '...') }.should_not raise_error
-    end
+  it "never returns a string longer than :length" do
+    truncate("test this shit", :length => 10).should == 'test...'
+  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 'supports omissions longer than the maximum length' do
+    lambda { truncate('', :length => 1, :omission => '...') }.should_not raise_error
+  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(@input_html, :length => 23).should == @expected_out
-      end
-    end
+  it 'returns the omission when the specified length is smaller than the omission' do
+    truncate('a b c', :length => 2, :omission => '...').should == '...'
+  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 '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 'truncates, and closes the <a>, and closes any remaining open tags' do
-        truncate(@html, :length => 15).should == '<div><ul><li>Look at <a href="foo">this...</a></li></ul></div>'
-      end
-    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
-        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, :length => 19).should == "<p>Look at <strong>this</strong>#{char}...</p>"
-        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
-      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, :length => 21).should == '<p>Look at <a href="awesomeful.net">this</a> link...</p>'
-      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
 
-    context 'when the characters are multibyte' do
-      before(:each) do
-        @html = '<p>Look at our multibyte characters ā ž <a href="awesomeful.net">this</a> link for randomness ā ž</p>'
-      end
-
-      it 'leaves the multibyte characters after truncation' do
-        truncate(@html, :length => @html.length).should == '<p>Look at our multibyte characters ā ž <a href="awesomeful.net">this</a> link for randomness ā ž</p>'
-      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
-    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
+  #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
 
-      it 'recognizes the multiline html properly' do
-        truncate(@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
 
-    %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, :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
+      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
-          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, :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
+      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 == "<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> “</em></p>"
+  end
+
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: truncate_html
 version: !ruby/object:Gem::Version
-  version: 0.5.3
+  version: 0.5.4
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-02-21 00:00:00.000000000Z
+date: 2012-02-25 00:00:00.000000000Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec-rails
-  requirement: &70176512127820 !ruby/object:Gem::Requirement
+  requirement: &70113472188980 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -21,10 +21,10 @@ dependencies:
         version: '2.3'
   type: :development
   prerelease: false
-  version_requirements: *70176512127820
+  version_requirements: *70113472188980
 - !ruby/object:Gem::Dependency
   name: rails
-  requirement: &70176512127320 !ruby/object:Gem::Requirement
+  requirement: &70113472185140 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -32,7 +32,7 @@ dependencies:
         version: 3.0.3
   type: :development
   prerelease: false
-  version_requirements: *70176512127320
+  version_requirements: *70113472185140
 description: Truncates html so you don't have to
 email:
 - harold.gimenez@gmail.com
@@ -99,7 +99,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: -3004529323348749608
+      hash: 2378599619304365096
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
@@ -108,7 +108,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: -3004529323348749608
+      hash: 2378599619304365096
 requirements: []
 rubyforge_project: 
 rubygems_version: 1.8.10