truncate_html_chinese 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: e056fc0c049ba378ca51dba2e9e01d98e5d620c9
+  data.tar.gz: cfec7cee37d01bf83c29b9c8806ed62166ae2017
+SHA512:
+  metadata.gz: 0bd1b3d35c3fb20644fca74c7e2572a2363fb834d15830c50f807aabdd6c21e1d51c7625744ea3e206561388df7b1a8515e537a927a90eecd71e128605c27101
+  data.tar.gz: e00dbf6518fee91e88323fd0a58d1f93e997856499a14765186c31fc399141ef494a164ae7ed4ab324c745db47b6c73d3fd59745a338f46b466a230415dc24a3

data/.gitignore

@@ -0,0 +1,7 @@
+pkg
+coverage
+profiling
+tmp
+spec/rails_root/log/*
+log/*.log
+.bundle

data/.travis.yml

@@ -0,0 +1,4 @@
+language: ruby
+rvm:
+  - 1.9.2
+  - jruby-19mode # JRuby in 1.9 mode

data/Gemfile

@@ -0,0 +1,4 @@
+source "http://rubygems.org"
+
+# Specify your gem's dependencies in truncate_html.gemspec
+gemspec

data/Gemfile.lock

@@ -0,0 +1,92 @@
+PATH
+  remote: .
+  specs:
+    truncate_html (0.9.2)
+
+GEM
+  remote: http://rubygems.org/
+  specs:
+    abstract (1.0.0)
+    actionmailer (3.0.3)
+      actionpack (= 3.0.3)
+      mail (~> 2.2.9)
+    actionpack (3.0.3)
+      activemodel (= 3.0.3)
+      activesupport (= 3.0.3)
+      builder (~> 2.1.2)
+      erubis (~> 2.6.6)
+      i18n (~> 0.4)
+      rack (~> 1.2.1)
+      rack-mount (~> 0.6.13)
+      rack-test (~> 0.5.6)
+      tzinfo (~> 0.3.23)
+    activemodel (3.0.3)
+      activesupport (= 3.0.3)
+      builder (~> 2.1.2)
+      i18n (~> 0.4)
+    activerecord (3.0.3)
+      activemodel (= 3.0.3)
+      activesupport (= 3.0.3)
+      arel (~> 2.0.2)
+      tzinfo (~> 0.3.23)
+    activeresource (3.0.3)
+      activemodel (= 3.0.3)
+      activesupport (= 3.0.3)
+    activesupport (3.0.3)
+    arel (2.0.7)
+    builder (2.1.2)
+    diff-lcs (1.1.3)
+    erubis (2.6.6)
+      abstract (>= 1.0.0)
+    i18n (0.5.0)
+    mail (2.2.15)
+      activesupport (>= 2.3.6)
+      i18n (>= 0.4.0)
+      mime-types (~> 1.16)
+      treetop (~> 1.4.8)
+    mime-types (1.16)
+    polyglot (0.3.1)
+    rack (1.2.1)
+    rack-mount (0.6.13)
+      rack (>= 1.0.0)
+    rack-test (0.5.7)
+      rack (>= 1.0)
+    rails (3.0.3)
+      actionmailer (= 3.0.3)
+      actionpack (= 3.0.3)
+      activerecord (= 3.0.3)
+      activeresource (= 3.0.3)
+      activesupport (= 3.0.3)
+      bundler (~> 1.0)
+      railties (= 3.0.3)
+    railties (3.0.3)
+      actionpack (= 3.0.3)
+      activesupport (= 3.0.3)
+      rake (>= 0.8.7)
+      thor (~> 0.14.4)
+    rake (0.8.7)
+    rspec (2.9.0)
+      rspec-core (~> 2.9.0)
+      rspec-expectations (~> 2.9.0)
+      rspec-mocks (~> 2.9.0)
+    rspec-core (2.9.0)
+    rspec-expectations (2.9.1)
+      diff-lcs (~> 1.1.3)
+    rspec-mocks (2.9.0)
+    rspec-rails (2.9.0)
+      actionpack (>= 3.0)
+      activesupport (>= 3.0)
+      railties (>= 3.0)
+      rspec (~> 2.9.0)
+    thor (0.14.6)
+    treetop (1.4.9)
+      polyglot (>= 0.3.1)
+    tzinfo (0.3.24)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  rails (~> 3.0.3)
+  rspec-rails (~> 2.9)
+  truncate_html!

data/History.txt

@@ -0,0 +1,40 @@
+== 0.5.1 2011-04-08
+  * Ensure resulting string's length is never greater than supplied length (csquared)
+
+== 0.5.0 2011-01-26
+  * Multibyte support. (smix, parndt)
+
+== 0.4.0 2010-03-30
+  * Rails 3 support. This breaks rails 2 support.
+
+== 0.3.2 2010-03-23
+  * Fix for autoloading of classes in older Rails versions. (kball)
+  * Fix issue #5: autoloading of default configuration.
+
+== 0.3.1 2010-02-03
+  * Fixed minor typo on the word_boundary option name.
+
+== 0.3.0 2010-02-02
+  * Added the ability to set global configuration parameters
+  * Added the word_boundry option
+
+== 0.2.2 2009-12-23
+ * Fix issue #4: Handle case when supplied length is smaller than omission. (ghazel)
+
+== 0.2.1 2009-12-18
+ * Fix issue #3: Handle case when input html contins a script tag.
+
+== 0.2.0 2009-11-23
+ * Fix issue #2: The omission text's length is now included in the returned
+   string's calculation. This is more consistent with the rails truncate
+   helper's behavior.
+
+== 0.1.2 2009-09-25
+ * Fix issue #1: Handle case when input html is nil. (bcardarella)
+
+== 0.1.1 2009-08-25
+ * Fixed issue with regex which would not recognize <a> tags that contain slashes.
+ * Other refactoring and improvements to spec coverage.
+
+== 0.1.0 2009-08-03
+ * Wrote truncate_html. Initial release.

data/LICENSE

@@ -0,0 +1,21 @@
+The MIT License
+
+Copyright (c) 2009 - 2010 Harold A. Giménez
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+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 OR COPYRIGHT HOLDERS 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.

data/README.md

@@ -0,0 +1,93 @@
+TruncateHtml
+============
+
+[![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 cuts off a string of HTML and takes care of closing any lingering open tags. There are many ways to solve this. This library does not have any dependencies, and [parses HTML using regular expressions](http://stackoverflow.com/questions/1732348/regex-match-open-tags-except-xhtml-self-contained-tags/1732454#1732454).
+
+It can be used with or without Rails.
+
+Example
+-------
+
+```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:
+
+* By default, it will truncate on word boundary.
+  To truncate the HTML string strictly at the specified length, pass in the `:word_boundary => false` option.
+* 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`: /\S/
+
+You may also set global configuration options.
+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)'
+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.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
+------------
+
+The latest gem version for the Rails 2.x series is 0.3.2.
+To use truncate_html on a Rails 2 app, please install the 0.3.2 version:
+
+    gem install truncate_html -v 0.3.2
+
+For Rails 3, use the latest truncate_html:
+
+    gem install truncate_html
+
+Issues or Suggestions
+---------------------
+
+Found an issue or have a suggestion? Please report it on [Github's issue tracker](http://github.com/hgmnz/truncate_html/issues).
+
+Testing
+-------
+
+    bundle
+    rake
+
+All green? Go hack.
+
+Copyright (c) 2009 - 2010 Harold A. Giménez, released under the MIT license
+
+Thanks to all the [contributors](https://github.com/hgmnz/truncate_html/contributors)!

data/Rakefile

@@ -0,0 +1,50 @@
+require 'rake'
+
+begin
+  require 'rspec/core'
+  require 'rspec/core/rake_task'
+rescue MissingSourceFile
+  module RSpec
+    module Core
+      class RakeTask
+        def initialize(name)
+          task name do
+            # if rspec-rails is a configured gem, this will output helpful material and exit ...
+            require File.expand_path(File.dirname(__FILE__) + "/../../config/environment")
+            # ... otherwise, do this:
+            raise <<-MSG
+#{"*" * 80}
+*  You are trying to run an rspec rake task defined in
+*  #{__FILE__},
+*  but rspec can not be found in vendor/gems, vendor/plugins or system gems.
+#{"*" * 80}
+MSG
+          end
+        end
+      end
+    end
+  end
+end
+
+task :default => :spec
+task :stats => "spec:statsetup"
+
+desc "Run RSpec code examples"
+RSpec::Core::RakeTask.new(:spec) do |t|
+  t.pattern   = "./spec/**/*_spec.rb"
+end
+
+namespace :gem do
+  desc "Release to rubygems"
+  task :release do
+    require File.expand_path('lib/truncate_html/version', File.dirname(__FILE__))
+    version = TruncateHtml::VERSION
+    message = "Bump to version #{version}"
+    system "git tag -a -m '#{message}' v#{version}"
+    system "git push origin master"
+    system "git push origin $(git tag | tail -1)"
+    system "gem build truncate_html.gemspec"
+    system "gem push truncate_html-#{version}.gem"
+    system "rm truncate_html-#{version}.gem"
+  end
+end

data/VERSION

@@ -0,0 +1 @@
+0.5.1

data/init.rb

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

data/lib/app/helpers/truncate_html_helper.rb

@@ -0,0 +1,9 @@
+module TruncateHtmlHelper
+
+  def truncate_html(html, options={})
+    return '' if html.nil?
+    html_string = TruncateHtml::HtmlString.new(html)
+    TruncateHtml::HtmlTruncator.new(html_string, options).truncate.html_safe
+  end
+
+end

data/lib/truncate_html.rb

@@ -0,0 +1,13 @@
+require File.join(File.dirname(__FILE__), 'truncate_html', 'version')
+require File.join(File.dirname(__FILE__), 'truncate_html', 'html_truncator')
+require File.join(File.dirname(__FILE__), 'truncate_html', 'html_string')
+require File.join(File.dirname(__FILE__), 'truncate_html', 'configuration')
+require File.join(File.dirname(__FILE__), 'app', 'helpers', 'truncate_html_helper')
+
+TruncateHtml.configure do |config|
+  config.length       = 100
+  config.omission     = '...'
+  config.word_boundary = /\S/
+end
+
+ActionController::Base.helper(TruncateHtmlHelper)

data/lib/truncate_html/configuration.rb

@@ -0,0 +1,14 @@
+module TruncateHtml
+  class Configuration
+    attr_accessor :length, :omission, :word_boundary, :break_token
+  end
+
+  class << self
+    attr_accessor :configuration
+  end
+
+  def self.configure
+    self.configuration ||= Configuration.new
+    yield configuration
+  end
+end

data/lib/truncate_html/html_string.rb

@@ -0,0 +1,45 @@
+# encoding: utf-8
+module TruncateHtml
+  class HtmlString < String
+
+    UNPAIRED_TAGS = %w(br hr img).freeze
+
+    def initialize(original_html)
+      super(original_html)
+    end
+
+    def html_tokens
+      scan(regex).map do |token|
+        HtmlString.new(
+          token.gsub(
+            /\n/,'' #remove newline characters
+          ).gsub(
+            /\s+/, ' ' #clean out extra consecutive whitespace
+          )
+        )
+      end
+    end
+
+    def html_tag?
+      /<\/?[^>]+>/ === self && !html_comment?
+    end
+
+    def open_tag?
+      /<(?!(?:#{UNPAIRED_TAGS.join('|')}|script|\/))[^>]+>/i === self
+    end
+
+    def html_comment?
+      /<\s?!--.*-->/ === self
+    end
+
+    def matching_close_tag
+      gsub(/<(\w+)\s?.*>/, '</\1>').strip
+    end
+
+    private
+    def regex
+      /(?:<script.*>.*<\/script>)+|<\/?[^>]+>|[[[:alpha:]]\w\|`~!@#\$%^&*\(\)\-_\+=\[\]{}:;'",\.\/?]+|\s+|[[:punct:]]+|\P{P}/ #add \p{P}
+    end
+
+  end
+end

data/lib/truncate_html/html_truncator.rb

@@ -0,0 +1,91 @@
+module TruncateHtml
+  class HtmlTruncator
+
+    def initialize(original_html, options = {})
+      @original_html   = original_html
+      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 = [], ['']
+    end
+
+    def truncate
+      return @omission if @chars_remaining < 0
+      @original_html.html_tokens.each do |token|
+        if @chars_remaining <= 0 || truncate_token?(token)
+          close_open_tags
+          break
+        else
+          process_token(token)
+        end
+      end
+
+      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 word_boundary
+      if @word_boundary == true
+        TruncateHtml.configuration.word_boundary
+      else
+        @word_boundary
+      end
+    end
+
+    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
+      elsif !token.html_comment?
+        @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? || token.html_comment?
+        @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
+    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