truncate_html 0.5.5 → 0.9

data/.travis.yml

@@ -1,5 +1,4 @@
 language: ruby
 rvm:
-  - 1.8.7
   - 1.9.2
   - jruby-19mode # JRuby in 1.9 mode

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    truncate_html (0.5.5)
+    truncate_html (0.9)
 
 GEM
   remote: http://rubygems.org/

data/README.markdown

@@ -1,7 +1,8 @@
 TruncateHtml
 ============
 
-[![Build Status](https://secure.travis-ci.org/hgimenez/truncate_html.png?branch=master)](http://travis-ci.org/hgimenez/truncate_html)
+[![Build Status](https://secure.travis-ci.org/hgmnz/truncate_html.png?branch=master)](http://travis-ci.org/hgmnz/truncate_html)
+[![Code Climate](https://codeclimate.com/badge.png)](https://codeclimate.com/github/hgmnz/truncate_html)
 
 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/).
 
@@ -11,9 +12,11 @@ The API is very similar to Rails' own <code>truncate()</code> method.
 Example
 -------
 
-    some_html = '<ul><li><a href="http://whatever">This is a link</a></li></ul>'
-    truncate_html(some_html, :length => 15, :omission => '...(continued)')
-      => <ul><li><a href="http://whatever">This...(continued)</a></li></ul>
+```ruby
+some_html = '<ul><li><a href="http://whatever">This is a link</a></li></ul>'
+truncate_html(some_html, :length => 15, :omission => '...(continued)')
+  => <ul><li><a href="http://whatever">This...(continued)</a></li></ul>
+```
 
 A few notes:
 
@@ -22,21 +25,49 @@ A few notes:
 * If the input HTML is nil, it will return an empty string.
 * The omission text's length does count toward the resulting string's length.
 * `<script>` tags will pass right through - they will not count toward the resulting string's length, or be truncated.
+
 * The default options are:
   * :length => 100
   * :omission => '...'
   * :word_boundary => true
 
 You may also set global configuration options.
-For example, place the following on a sensible place,
-like `config/initializers/truncate_html.rb`
-
-    TruncateHtml.configure do |config|
-      config.length       = 50
-      config.omission     = '...(continued)'
-      config.word_boundary = false
-    end
-
+For example, place the following on application boot,
+something like `config/initializers/truncate_html.rb`
+
+```ruby
+TruncateHtml.configure do |config|
+  config.length        = 50
+  config.omission      = '...(continued)'
+  config.word_boundary = false
+  config.break_token   = '<!-- break -->'
+end
+```
+
+If you really want, you can even set a custom word boundary regexp.
+For example, to truncate at the end of the nearest sentence:
+
+```ruby
+TruncateHtml.configure do |config|
+  config.length        = 50
+  config.omission      = ''
+  config.word_boundary = /\S[\.\?\!]/
+end
+```
+
+You can also truncate the html at a specific point not based on length but content.
+To do that, place the `:break_token` in your source. This allows the truncation to be
+data driven, breaking after a leading paragraph or sentence. If the
+`:break_token` is in your content before the specified :length, :length will be
+ignored and the content truncated at :break_token
+If the `:break_token` is in your content after the specified :length,
+`:break_token` will be ignored and the content truncated at :length
+
+```ruby
+TruncateHtml.configure do |config|
+  config.break_token = '<!-- truncate -->
+end
+```
 Installation
 ------------
 
@@ -52,7 +83,7 @@ For Rails 3, use the latest truncate_html:
 Issues or Suggestions
 ---------------------
 
-Found an issue or have a suggestion? Please report it on [Github's issue tracker](http://github.com/hgimenez/truncate_html/issues).
+Found an issue or have a suggestion? Please report it on [Github's issue tracker](http://github.com/hgmnz/truncate_html/issues).
 
 Testing
 -------
@@ -64,4 +95,4 @@ All green? Go hack.
 
 Copyright (c) 2009 - 2010 Harold A. Giménez, released under the MIT license
 
-Thanks to all the [contributors](https://github.com/hgimenez/truncate_html/contributors)!
+Thanks to all the [contributors](https://github.com/hgmnz/truncate_html/contributors)!

data/lib/truncate_html.rb

@@ -7,7 +7,7 @@ require File.join(File.dirname(__FILE__), 'app', 'helpers', 'truncate_html_helpe
 TruncateHtml.configure do |config|
   config.length       = 100
   config.omission     = '...'
-  config.word_boundary = true
+  config.word_boundary = /\S/
 end
 
 ActionController::Base.helper(TruncateHtmlHelper)

data/lib/truncate_html/configuration.rb

@@ -1,6 +1,6 @@
 module TruncateHtml
   class Configuration
-    attr_accessor :length, :omission, :word_boundary
+    attr_accessor :length, :omission, :word_boundary, :break_token
   end
 
   class << self

data/lib/truncate_html/html_string.rb

@@ -34,8 +34,7 @@ module TruncateHtml
 
     private
     def regex
-      punctuation = if RUBY_VERSION < '1.9' then "\\p\\{P\\}" else "[[:punct:]]" end
-      /(?:<script.*>.*<\/script>)+|<\/?[^>]+>|[#{"[[:alpha:]]" if RUBY_VERSION >= '1.9'}\w\|`~!@#\$%^&*\(\)\-_\+=\[\]{}:;'",\.\/?]+|\s+|#{punctuation}/
+      /(?:<script.*>.*<\/script>)+|<\/?[^>]+>|[[[:alpha:]]\w\|`~!@#\$%^&*\(\)\-_\+=\[\]{}:;'",\.\/?]+|\s+|[[:punct:]]/
     end
 
   end

data/lib/truncate_html/html_truncator.rb

@@ -6,67 +6,79 @@ module TruncateHtml
     end
 
     def truncate(options = {})
-      length        = options[:length]       || TruncateHtml.configuration.length
-      @omission     = options[:omission]     || TruncateHtml.configuration.omission
-      @word_boundary = (options.has_key?(:word_boundary) ? options[:word_boundary] : TruncateHtml.configuration.word_boundary)
+      length           = options[:length]       || TruncateHtml.configuration.length
+      @omission        = options[:omission]     || TruncateHtml.configuration.omission
+      @word_boundary   = (options.has_key?(:word_boundary) ? options[:word_boundary] : TruncateHtml.configuration.word_boundary)
+      @break_token     = options[:break_token] || TruncateHtml.configuration.break_token || nil
       @chars_remaining = length - @omission.length
       @open_tags, @truncated_html = [], ['']
 
       return @omission if @chars_remaining < 0
       @original_html.html_tokens.each do |token|
-        #if truncate_more?(token)
-        if @chars_remaining > 0
-          process_token(token)
-        else
+        if @chars_remaining <= 0 || truncate_token?(token)
           close_open_tags
           break
+        else
+          process_token(token)
         end
       end
-      @truncated_html.join
+
+      out = @truncated_html.join
+
+      if @word_boundary
+        term_regexp = Regexp.new("^.*#{@word_boundary.source}")
+        match = out.match(term_regexp)
+        match ? match[0] : out
+      else
+        out
+      end
     end
 
     private
 
-      def process_token(token)
-        append_to_result(token)
-        if token.html_tag?
-          if token.open_tag?
-            @open_tags << token
-          else
-            remove_latest_open_tag(token)
-          end
+    def process_token(token)
+      append_to_result(token)
+      if token.html_tag?
+        if token.open_tag?
+          @open_tags << token
         else
-          @chars_remaining -= (@word_boundary ? token.length : token[0, @chars_remaining].length)
-          if @chars_remaining <= 0
-            @truncated_html[-1] = @truncated_html[-1].rstrip + @omission
-          end
+          remove_latest_open_tag(token)
+        end
+      else
+        @chars_remaining -= (@word_boundary ? token.length : token[0, @chars_remaining].length)
+        if @chars_remaining <= 0
+          @truncated_html[-1] = @truncated_html[-1].rstrip + @omission
         end
       end
+    end
 
-      def append_to_result(token)
-        if token.html_tag?
-          @truncated_html << token
-        elsif @word_boundary
-          @truncated_html << token if (@chars_remaining - token.length) >= 0
-        else
-          @truncated_html << token[0, @chars_remaining]
-        end
+    def append_to_result(token)
+      if token.html_tag?
+        @truncated_html << token
+      elsif @word_boundary
+        @truncated_html << token if (@chars_remaining - token.length) >= 0
+      else
+        @truncated_html << token[0, @chars_remaining]
       end
+    end
 
-      def close_open_tags
-        @open_tags.reverse_each do |open_tag|
-          @truncated_html << open_tag.matching_close_tag
-        end
+    def close_open_tags
+      @open_tags.reverse_each do |open_tag|
+        @truncated_html << open_tag.matching_close_tag
       end
+    end
 
-      def remove_latest_open_tag(close_tag)
-        (0...@open_tags.length).to_a.reverse.each do |index|
-          if @open_tags[index].matching_close_tag == close_tag
-            @open_tags.delete_at(index)
-            break
-          end
+    def remove_latest_open_tag(close_tag)
+      (0...@open_tags.length).to_a.reverse.each do |index|
+        if @open_tags[index].matching_close_tag == close_tag
+          @open_tags.delete_at(index)
+          break
         end
       end
+    end
 
+    def truncate_token?(token)
+      @break_token and token == @break_token
+    end
   end
 end

data/lib/truncate_html/version.rb

@@ -1,3 +1,3 @@
 module TruncateHtml
-  VERSION = "0.5.5"
+  VERSION = "0.9"
 end

data/spec/truncate_html/html_truncator_spec.rb

@@ -17,6 +17,22 @@ describe TruncateHtml::HtmlTruncator 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_html("testtest", :length => 10, :omission => '..', :word_boundary => false).should == 'testtest..'
+      end
+
+      it 'handles multibyte characters' do
+        truncate_html("prüfenprüfen", :length => 8, :omission => '..', :word_boundary => false). should == 'prüfen..'
+      end
+    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_html('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
@@ -124,4 +140,52 @@ describe TruncateHtml::HtmlTruncator do
     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
+
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: truncate_html
 version: !ruby/object:Gem::Version
-  version: 0.5.5
+  version: '0.9'
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-04-24 00:00:00.000000000 Z
+date: 2013-01-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec-rails
-  requirement: &70108244979240 !ruby/object:Gem::Requirement
+  requirement: &70117859351640 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -21,10 +21,10 @@ dependencies:
         version: '2.9'
   type: :development
   prerelease: false
-  version_requirements: *70108244979240
+  version_requirements: *70117859351640
 - !ruby/object:Gem::Dependency
   name: rails
-  requirement: &70108244978720 !ruby/object:Gem::Requirement
+  requirement: &70117859350560 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -32,7 +32,7 @@ dependencies:
         version: 3.0.3
   type: :development
   prerelease: false
-  version_requirements: *70108244978720
+  version_requirements: *70117859350560
 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: -2387288071087328503
+      hash: 2344297215831564369
 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: -2387288071087328503
+      hash: 2344297215831564369
 requirements: []
 rubyforge_project: 
 rubygems_version: 1.8.10