rubb 0.9.0

data/.gitignore

@@ -0,0 +1,5 @@
+*.sw?
+.DS_Store
+coverage
+pkg
+doc

data/LICENSE

@@ -0,0 +1,19 @@
+Copyright (c) 2010 Peter Jihoon Kim
+
+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.rdoc

@@ -0,0 +1,37 @@
+= RuBB
+
+BBCode Parser for Ruby.
+
+RuBB parses BBCode by generating a parse tree, so it is able to handle nested BBCode tags properly.
+
+== Usage
+
+  RuBB.to_html('[b]hello[/b]')
+  
+  '[b]hello[/b]'.to_html
+
+== BBCode Tags
+
+RuBB supports the following BBCode tags:
+
+  [b]text[/b]
+  [i]text[/i]
+  [u]text[/u]
+  [s]text[/s]
+  [size=10]text[/size]
+  [color=#ff0000]text[/color]
+  [center]text[/center]
+  [quote]text[/quote]
+  [quote=someone]text[/quote]
+  [url]http://github.com/petejkim/rubb/[/url]
+  [url=http://github.com/petejkim/rubb/]RuBB[/url]
+  [img]http://test.com/test.jpg[/img]
+  [img=640x480]http://test.com/test.jpg[/img]
+  [ul][li]text[/li][/ul]
+  [ol][li]text[/li][/ol]
+  [code]text[/code]
+  [table][tr][th]text[/th][/tr][tr][td]text[/td][/tr][/table]
+
+== Copyright
+
+Copyright (c) 2010 Peter Jihoon Kim. See LICENSE for details.

data/Rakefile

@@ -0,0 +1,28 @@
+require 'rake'
+require 'rake/testtask'
+
+begin
+  require 'jeweler'
+  
+  Jeweler::Tasks.new do |s|
+    s.name              = "rubb"
+    s.summary           = "BBCode Parser for Ruby that supports nested BBCode tags."
+    s.description       = s.summary
+    s.homepage          = "http://github.com/petejkim/rubb"
+    s.authors           = ["Peter Jihoon Kim"]
+    s.email             = "raingrove@gmail.com"
+  end
+
+  Jeweler::GemcutterTasks.new
+rescue LoadError
+  puts "Jeweler - or one of its dependencies - is not available. " <<
+  "Install it with: sudo gem install jeweler -s http://gemcutter.org"
+end
+
+Rake::TestTask.new do |t|
+  t.libs << 'lib'
+  t.pattern = 'test/**/test_*.rb'
+  t.verbose = true
+end
+
+task :default => :test

data/VERSION

@@ -0,0 +1 @@
+0.9.0

data/init.rb

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

data/lib/rubb.rb

@@ -0,0 +1,22 @@
+module RuBB
+  class << self
+    def parse(bbcode)
+      Parser.parse(Parser.escape_html(bbcode), nil)
+    end
+  
+    def to_html(bbcode)
+      parse(bbcode).to_html
+    end
+  end
+end
+
+class String
+  def bb_to_html
+    RuBB.to_html(self)
+  end
+end
+
+$: << (File.dirname(__FILE__)) unless $:.include?(File.dirname(__FILE__)) || $:.include?(File.expand_path(File.dirname(__FILE__)))
+
+require 'rubb/node'
+require 'rubb/parser'

data/lib/rubb/node.rb

@@ -0,0 +1,25 @@
+module RuBB
+  class Node
+    attr_accessor :children
+    attr_accessor :leftover
+  
+    def initialize(options={})
+      @children = options[:children] || []
+      @leftover = options[:leftover]
+    end
+  
+    def <<(child)
+      @children << child
+    end
+  
+    def to_html
+      html = ''
+      @children.each do |child|
+        html += child ? child.to_html : ''
+      end
+      html
+    end
+  end
+end
+
+Dir.glob(File.join(File.dirname(__FILE__), 'node/*.rb')).each {|f| require f }  

data/lib/rubb/node/image.rb

@@ -0,0 +1,25 @@
+module RuBB
+  class Node
+    class Image < Node
+      attr_accessor :width
+      attr_accessor :height
+      
+      def initialize(options={})
+        super(options)
+        @width = options[:width]
+        @height = options[:height]
+      end
+      
+      def to_html
+        if(@width && @height)
+          url = Parser.escape_quotes(@children.map {|c| c ? c.to_html : '' }.join)
+          html = "<img src=\"#{url}\" style=\"width: #{@width}px; height: #{@height}px;\" alt=\"\" />"
+        else
+          url = Parser.escape_quotes(@children.map {|c| c ? c.to_html : '' }.join)
+          html = "<img src=\"#{url}\" alt=\"\" />"
+        end
+      end
+    end
+  end
+end
+

data/lib/rubb/node/quote.rb

@@ -0,0 +1,22 @@
+module RuBB
+  class Node
+    class Quote < Node
+      attr_accessor :who
+      
+      def initialize(options={})
+        super(options)
+        @who = options[:who] || ''
+      end
+      
+      def to_html
+        html = '<p class="rubb_quote_header">Quote:</p><blockquote>'
+        html += "<p class=\"rubb_quote_who\">Originally Posted by <strong>#{Parser.escape_quotes(@who)}</strong></p>" unless(@who.empty?)
+        html += '<p class="rubb_quote_content">'
+        @children.each do |child|
+          html += child ? child.to_html : ''
+        end
+        html + '</p></blockquote>'
+      end
+    end
+  end
+end

data/lib/rubb/node/simple.rb

@@ -0,0 +1,21 @@
+module RuBB
+  class Node
+    class Simple < Node
+      attr_accessor :html_tag_name
+      
+      def initialize(options={})
+        super(options)
+        @html_tag_name = options[:html_tag_name] || ''
+      end
+      
+      def to_html
+        html = "<#{@html_tag_name}>"
+        @children.each do |child|
+          html += child ? child.to_html : ''
+        end
+        html + "</#{@html_tag_name}>"
+      end
+    end
+  end
+end
+

data/lib/rubb/node/styled.rb

@@ -0,0 +1,28 @@
+module RuBB
+  class Node
+    class Styled < Node
+      attr_accessor :style_hash
+      
+      def initialize(options={})
+        super(options)
+        @style_hash = options[:style_hash] || {}
+      end
+      
+      def to_html
+        html = '<span style="'
+        @style_hash.each do |k,v|
+          if(v) # if v is not nil
+            v = v[/\A([^;]*);/,1] if v.include?(';') # ignore semicolons and any trailing text
+            html += "#{k}: #{v};"
+          end
+        end
+        html += '">'
+        @children.each do |child|
+          html += child ? child.to_html : ''
+        end
+        html + "</span>"
+      end
+    end
+  end
+end
+

data/lib/rubb/node/text.rb

@@ -0,0 +1,22 @@
+module RuBB
+  class Node
+    class Text < Node
+      attr_accessor :text
+      attr_accessor :ignore_whitespace
+      
+      def initialize(options={})
+        super(options)
+        @text = options[:text] || ''
+        @ignore_whitespace = options[:ignore_whitespace] || false
+      end
+  
+      def to_html
+        if(@ignore_whitespace)
+          @text.gsub(/\s/, '')
+        else
+          @text.gsub(/\r\n?/, "\n").gsub(/\n/, '<br />')
+        end
+      end
+    end
+  end
+end

data/lib/rubb/node/url.rb

@@ -0,0 +1,26 @@
+module RuBB
+  class Node
+    class URL < Node
+      attr_accessor :url
+      
+      def initialize(options={})
+        super(options)
+        @url = options[:url] || ''
+      end
+      
+      def to_html
+        unless(@url.empty?)
+          html = "<a href=\"#{Parser.escape_quotes(@url)}\">"
+          @children.each do |child|
+            html += child ? child.to_html : ''
+          end
+          html + '</a>'
+        else
+          url = Parser.escape_quotes(@children.map {|c| c ? c.to_html : '' }.join)
+          html = "<a href=\"#{url}\">#{url}</a>"
+        end
+      end
+    end
+  end
+end
+

data/lib/rubb/parser.rb

@@ -0,0 +1,128 @@
+module RuBB
+  class Parser
+    TEXT_REGEXP = /\A([^\[]+)/
+    BB_REGEXP = /\A\[([^\]]*)\]/
+    
+    class << self
+      def escape_html(code)
+        code.gsub(/&/,'&amp;').gsub(/</,'&lt;').gsub(/>/,'&gt;')
+      end
+      
+      def escape_quotes(code)
+        code.gsub(/"/, "\\\"").gsub(/'/, "\\\\'")
+      end
+      
+      def remove_wrapping_quotes(code)
+        if code[0] == "\"" && code[code.length-1] == "\""
+          return code[/\A"(.*)"\z/,1]
+        elsif code[0] == "\'" && code[code.length-1] == "\'"
+          return code[/\A'(.*)'\z/,1]
+        end
+        code
+      end
+      
+      def parse(code, current_tag_name, extra_params={})
+        return nil if code.length == 0
+        
+        ignore_bbcode_in_children = false
+        
+        node = case current_tag_name
+        when 'b'
+          Node::Simple.new(:html_tag_name => 'strong')
+        when 'i'
+          Node::Simple.new(:html_tag_name => 'em')
+        when 'u'
+          Node::Simple.new(:html_tag_name => 'ins')
+        when 's'
+          Node::Simple.new(:html_tag_name => 'del')
+        when 'code'
+          ignore_bbcode_in_children = true 
+          Node::Simple.new(:html_tag_name => 'pre')
+        when 'ul', 'ol', 'li', 'table', 'tr', 'th', 'td'
+          Node::Simple.new(:html_tag_name => current_tag_name)
+        when 'size'
+          Node::Styled.new(:style_hash => {'font-size' => (extra_params[:param] ? extra_params[:param].to_f.to_s + 'px' : nil)})
+        when 'color'
+          Node::Styled.new(:style_hash => {'color' => (extra_params[:param] || nil)})
+        when 'center'
+          Node::Styled.new(:style_hash => {'text-align' => 'center'})
+        when 'quote'
+          Node::Quote.new(:who => (extra_params[:param] || ''))
+        when 'url'
+          ignore_bbcode_in_children = true if extra_params[:param].nil?
+          Node::URL.new(:url => (extra_params[:param] || ''))
+        when 'img'
+          ignore_bbcode_in_children = true
+          if(extra_params[:param] && (dimensions = extra_params[:param].split('x')).size >= 2)
+            Node::Image.new(:width => dimensions[0].to_i, :height => dimensions[1].to_i)
+          else
+            Node::Image.new
+          end
+        else
+          Node.new
+        end
+    
+        until code.empty?
+          match_data = code.match(TEXT_REGEXP)
+
+          if(match_data)
+            code.replace(match_data.post_match)
+            case current_tag_name
+            when 'ul', 'ol', 'table', 'tr' # ignore orphaned text within these tags
+              # do nothing
+            else
+              node << Node::Text.new(:text => match_data[1], :ignore_whitespace => ignore_bbcode_in_children)
+            end
+          else
+            match_data = code.match(BB_REGEXP)
+            if(match_data)
+              tag = match_data[1].sub(/\s*=\s*/,' = ').split(' ')
+              tag_name = tag.first.downcase
+              
+              code.replace(match_data.post_match)
+              if(current_tag_name && tag_name == ('/' + current_tag_name))
+                return node
+              else
+                case current_tag_name
+                when 'ul', 'ol' # if current tag is a list tag, expect only li tag
+                  if(tag_name == 'li')
+                    node << parse(code, tag_name)
+                  end
+                when 'table'
+                  if(tag_name == 'tr')
+                    node << parse(code, tag_name)
+                  end
+                when 'tr'
+                  if(tag_name == 'th' || tag_name == 'td')
+                    node << parse(code, tag_name)
+                  end
+                else # if current tag is not a list tag
+                  if(ignore_bbcode_in_children)
+                    node << Node::Text.new(:text => match_data[0], :ignore_whitespace => true)
+                  else
+                    case tag_name
+                    when 'b', 'i', 'u', 's', 'code', 'center', 'ul', 'ol', 'table'
+                      node << parse(code, tag_name)
+                    when 'url', 'img', 'size', 'color', 'quote'
+                      if(tag[1] == '=' && tag.size > 2) # param is present
+                        param = remove_wrapping_quotes(tag[2..(tag.size)].join(' '))
+                        node << parse(code, tag_name, {:param => param})
+                      else
+                        node << parse(code, tag_name)
+                      end
+                    else
+                      node << Node::Text.new(:text => match_data[0])
+                    end
+                  end
+                end
+              end
+            end
+          end
+        end
+        node
+      end
+    end
+  end
+end
+
+Dir.glob(File.join(File.dirname(__FILE__), 'parser/*.rb')).each {|f| require f }  

data/test/test_helper.rb

@@ -0,0 +1,2 @@
+require 'test/unit'
+require 'rubb'

data/test/test_rubb.rb

@@ -0,0 +1,187 @@
+$: << (File.dirname(__FILE__)) unless $:.include?(File.dirname(__FILE__)) || $:.include?(File.expand_path(File.dirname(__FILE__)))
+require 'test_helper'
+
+class RuBBTest < Test::Unit::TestCase
+  def setup
+  end
+
+  def test_escape
+    bb   = "<p>tom & jerry kids</p>"
+    html = "&lt;p&gt;tom &amp; jerry kids&lt;/p&gt;"
+    assert_equal html, bb.bb_to_html
+  end
+  
+  def test_text
+    bb   = "hello\nbye"
+    html = "hello<br />bye"
+    assert_equal html, bb.bb_to_html
+  end
+  
+  def test_b
+    bb   = '[b]hello[/b]'
+    html = '<strong>hello</strong>'
+    assert_equal html, bb.bb_to_html
+  end
+  
+  def test_i
+    bb   = '[i]hello[/i]'
+    html = '<em>hello</em>'
+    assert_equal html, bb.bb_to_html
+  end
+  
+  def test_u
+    bb   = '[u]hello[/u]'
+    html = '<ins>hello</ins>'
+    assert_equal html, bb.bb_to_html
+  end
+  
+  def test_s
+    bb   = '[s]hello[/s]'
+    html = '<del>hello</del>'
+    assert_equal html, bb.bb_to_html
+  end
+  
+  def test_code
+    bb   = '[code]<p>hi</p>[b]hi[/b][/code]'
+    html = '<pre>&lt;p&gt;hi&lt;/p&gt;[b]hi[/b]</pre>'
+    assert_equal html, bb.bb_to_html
+  end
+  
+  def test_center
+    bb   = '[center]hello[/center]'
+    html = '<span style="text-align: center;">hello</span>'
+    assert_equal html, bb.bb_to_html
+  end
+  
+  def test_quote
+    bb   = '[quote]hello world![/quote]'
+    html = '<p class="rubb_quote_header">Quote:</p><blockquote><p class="rubb_quote_content">hello world!</p></blockquote>'
+    assert_equal html, bb.bb_to_html
+  end
+  
+  def test_named_quote
+    bb   = '[quote=raingrove]hello world![/quote]'
+    html = '<p class="rubb_quote_header">Quote:</p><blockquote><p class="rubb_quote_who">Originally Posted by <strong>raingrove</strong></p><p class="rubb_quote_content">hello world!</p></blockquote>'
+    assert_equal html, bb.bb_to_html
+  end
+  
+  def test_size
+    bb   = '[size=16]hello[/size]'
+    html = '<span style="font-size: 16.0px;">hello</span>'
+    assert_equal html, bb.bb_to_html
+  end
+  
+  def test_semicolon
+    bb   = '[size=16;display: none;]hello[/size]'
+    html = '<span style="font-size: 16.0px;">hello</span>'
+    assert_equal html, bb.bb_to_html
+  end
+  
+  def test_color
+    bb   = '[color=#ff0000]hello[/color]'
+    html = '<span style="color: #ff0000;">hello</span>'
+    assert_equal html, bb.bb_to_html
+  end
+  
+  def test_url_simple
+    bb   = '[url]http://test.com/[/url]'
+    html = '<a href="http://test.com/">http://test.com/</a>'
+    assert_equal html, bb.bb_to_html
+  end
+  
+  def test_url_named
+    bb   = '[url=http://test.com/]Test[/url]'
+    html = '<a href="http://test.com/">Test</a>'
+    assert_equal html, bb.bb_to_html
+  end
+  
+  def test_url_named_with_single_quotes
+    bb   = "[url=\'http://test.com/\']Test[/url]"
+    html = '<a href="http://test.com/">Test</a>'
+    assert_equal html, bb.bb_to_html
+  end
+
+  def test_url_named_with_double_quotes
+    bb   = '[url="http://test.com/"]Test[/url]'
+    html = '<a href="http://test.com/">Test</a>'
+    assert_equal html, bb.bb_to_html
+  end
+  
+  def test_escape_quotes
+    bb   = "[url=hello\">hello<p class='test'>hi</p><a href=\"]hello[/url]"
+    html = "<a href=\"hello\\\"&gt;hello&lt;p class=\\\'test\\\'&gt;hi&lt;/p&gt;&lt;a href=\\\"\">hello</a>"
+    assert_equal html, bb.bb_to_html
+  end
+  
+  def test_img_simple
+    bb   = '[img]http://test.com/hello.jpg[/img]'
+    html = '<img src="http://test.com/hello.jpg" alt="" />'
+    assert_equal html, bb.bb_to_html
+  end
+  
+  def test_img_with_dimensions
+    bb   = '[img=100x200]http://test.com/hello.jpg[/img]'
+    html = '<img src="http://test.com/hello.jpg" style="width: 100px; height: 200px;" alt="" />'
+    assert_equal html, bb.bb_to_html
+  end
+  
+  def test_img_with_dimensions_with_quotes
+    bb   = '[img="100x200"]http://test.com/hello.jpg[/img]'
+    html = '<img src="http://test.com/hello.jpg" style="width: 100px; height: 200px;" alt="" />'
+    assert_equal html, bb.bb_to_html
+  end
+  
+  def test_img_with_invalid_dimensions
+    bb   = '[img="100"]http://test.com/hello.jpg[/img]'
+    html = '<img src="http://test.com/hello.jpg" alt="" />'
+    assert_equal html, bb.bb_to_html
+  end
+  
+  def test_ul
+    bb   = '[ul][li]item1[/li][li]item2[/li][/ul]'
+    html = '<ul><li>item1</li><li>item2</li></ul>'
+    assert_equal html, bb.bb_to_html
+  end
+
+  def test_ol
+    bb   = '[ol][li]item1[/li][li]item2[/li][/ol]'
+    html = '<ol><li>item1</li><li>item2</li></ol>'
+    assert_equal html, bb.bb_to_html
+  end
+  
+  def test_list_with_extraneous_stuff
+    bb   = '[ul]blah[li]item1[/li][li]item2[/li]blah[b]blah[/b]blah[/ul]'
+    html = '<ul><li>item1</li><li>item2</li></ul>'
+    assert_equal html, bb.bb_to_html
+  end
+
+  def test_table
+    bb   = '[table][tr][th]col1[/th][th]col2[/th][/tr][tr][td]data1[/td][td]data2[/td][/tr][/table]'
+    html = '<table><tr><th>col1</th><th>col2</th></tr><tr><td>data1</td><td>data2</td></tr></table>'
+    assert_equal html, bb.bb_to_html
+  end
+
+  def test_table_with_extraneous_stuff
+    bb   = '[table]blah[tr]blah[th]col1[/th]blah[th]col2[/th]blah[/tr]blah[tr]blah[td]data1[/td]blah[td]data2[/td]blah[/tr]blah[/table]'
+    html = '<table><tr><th>col1</th><th>col2</th></tr><tr><td>data1</td><td>data2</td></tr></table>'
+    assert_equal html, bb.bb_to_html
+  end
+  
+  def test_str_around
+    bb   = 'aaa[b]bbb[/b]ccc'
+    html = 'aaa<strong>bbb</strong>ccc'
+    assert_equal html, bb.bb_to_html
+  end
+  
+  def test_nested
+    bb   = '[b]aaa[b]bbb[/b]ccc[/b]'
+    html = '<strong>aaa<strong>bbb</strong>ccc</strong>'
+    assert_equal html, bb.bb_to_html
+  end
+  
+  def test_complex
+    bb   = "xx[s]aaa[b]bbb[u]eee[/u]ff\nff[/b]ccc[i]ggg[/i]hhh[/s]yy"
+    html = 'xx<del>aaa<strong>bbb<ins>eee</ins>ff<br />ff</strong>ccc<em>ggg</em>hhh</del>yy'
+    assert_equal html, bb.bb_to_html
+  end
+end

metadata

@@ -0,0 +1,82 @@
+--- !ruby/object:Gem::Specification 
+name: rubb
+version: !ruby/object:Gem::Version 
+  prerelease: false
+  segments: 
+  - 0
+  - 9
+  - 0
+  version: 0.9.0
+platform: ruby
+authors: 
+- Peter Jihoon Kim
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2010-07-12 00:00:00 +09:00
+default_executable: 
+dependencies: []
+
+description: BBCode Parser for Ruby that supports nested BBCode tags.
+email: raingrove@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- LICENSE
+- README.rdoc
+files: 
+- .gitignore
+- LICENSE
+- README.rdoc
+- Rakefile
+- VERSION
+- init.rb
+- lib/rubb.rb
+- lib/rubb/node.rb
+- lib/rubb/node/image.rb
+- lib/rubb/node/quote.rb
+- lib/rubb/node/simple.rb
+- lib/rubb/node/styled.rb
+- lib/rubb/node/text.rb
+- lib/rubb/node/url.rb
+- lib/rubb/parser.rb
+- test/test_helper.rb
+- test/test_rubb.rb
+has_rdoc: true
+homepage: http://github.com/petejkim/rubb
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --charset=UTF-8
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.7
+signing_key: 
+specification_version: 3
+summary: BBCode Parser for Ruby that supports nested BBCode tags.
+test_files: 
+- test/test_helper.rb
+- test/test_rubb.rb