cpjolicoeur-ClothBlue 0.2.2

data/README

@@ -0,0 +1,3 @@
+...coming soon... 
+
+...see lib/README.rdoc for now...

data/TODO

@@ -0,0 +1 @@
+*  make lists work better.  right now they all output as unordered lists.  make both <ul> and <ol> list items work correctly.

data/clothblue.gemspec

@@ -0,0 +1,14 @@
+Gem::Specification.new do |s|
+  s.name = "ClothBlue"
+  s.version = "0.2.2"
+  s.date = "Time.now"
+  s.summary = "HTML to Markdown converter"
+  s.email = "cpjolicoeur@gmail.com"
+  s.homepage = "http://github.com/cpjolicoeur/clothblue"
+  s.description = "ClothBlue is BlueCloth's evil twin.  It converts existing HTML into Markdown format for use with BlueCloth."
+  s.has_rdoc = true
+  s.authors = ["Craig P Jolicoeur"]
+  s.files = ["README", "TODO", "clothblue.gemspec", "lib/clothblue.rb", "lib/README.rdoc", "test/README", "test/test_entities.rb", "test/test_formatting.rb", "test/test_headings.rb", "test/test_lists.rb", "test/test_structure.rb", "test/test_tables.rb"]
+  s.test_files = ["test/test_entities.rb", "test/test_formatting.rb", "test/test_headings.rb", "test/test_lists.rb", "test/test_structure.rb", "test/test_tables.rb"]
+  s.rdoc_options = ["--main", "lib/README.rdoc"]
+end

data/lib/README.rdoc

@@ -0,0 +1,46 @@
+= ClothBlue HTML 2 Markdown converter
+
+== What it is
+
+A script to convert HTML into Markdown markup for use, for example, with BlueCloth.
+
+
+== Requirements
+
+All you need is Ruby.
+
+== Get it
+
+Available as a gem on GitHub:
+
+Or download from:
+
+Or get the source:
+
+
+== Features
+
+This is alpha software, and only a few Markdown rules have been implemented yet:
+ * font markup and weight (<b>, <strong>, ...)
+ * text formatting (<sub>, <sup>, <ins>,<del>)
+
+== Usage
+
+require 'clothblue'
+
+text = ClothBlue.new("<b>Bold</b> <em>HTML</em>!")
+text.to_markdown
+
+== Get Help
+
+Feel free to contact me, or peruse the homepage.
+
+ * http://craigjolicoeur.com/clothblue/
+ * http://github.com/cpjolicoeur/clothblue/
+
+== Acknowledgments
+
+ClothBlue is heavily copied from the ClothRed library (http://clothred.rubyforge.org/).  Much thanks to
+Phillip Gawlowski for the initial idea and code.  I basically just ported this HTML to Textile converter
+to work with Markdown instead of Textile.  The format of the code and README docs are pretty much exact
+clones as far as the format is concerned.

data/lib/clothblue.rb

@@ -0,0 +1,124 @@
+=begin rdoc
+Provides the methods to convert HTML into Markdown.
+*Please* *note*: ClothBlue creates UTF-8 output. To do so, it sets $KCODE to UTF-8. This will be globally available!
+#--
+TODO: enhance docs, as more methods come availlable
+#++
+
+Author:: Craig P Jolicoeur (mailto:cpjolicoeur@gmail.com)
+Copyright:: Copyright (c) 2008 Phillip Gawlowski
+License:: MIT
+=end
+
+require 'cgi'
+$KCODE = "U"
+
+class ClothBlue < String
+#--
+  TEXT_FORMATTING = [
+    ["<b>", "**"], ["</b>","**"], ["<em>","_"], ["</em>", "_"], ["<b>", "**"], 
+    ["</b>", "**"], ["<code>", "`"], ["<i>","_"], ["</i>", "_"],
+    ["</code>", "`"], ["<strong>", "**"], ["</strong>", "**"] 
+  ]
+
+  HEADINGS = [
+    ["<h1>","# "], ["</h1>", " #\n\n"], ["<h2>","## "], ["</h2>", " ##\n\n"], 
+    ["<h3>","### "], ["</h3>", " ###\n\n"], ["<h4>","#### "], ["</h4>", " ####\n\n"], 
+    ["<h5>","##### "], ["</h5>", " #####\n\n"], ["<h6>","###### "], ["</h6>", " ######\n\n"]
+  ]
+
+  STRUCTURES = [
+    ["<p>", "\n\n"],["</p>","\n\n"], ["<blockquote>", "> "], ["</blockquote>","\n"], 
+    ["<br />", "\n"], ["<br>", "\n"]
+  ]
+
+  ENTITIES = [
+    ["&#8220;", '"'], ["&#8221;", '"'], ["&#8212;", "--"], ["&#8212;", "--"], 
+    ["&#8211;","-"], ["&#8230;", "..."], ["&#215;", " x "], ["&#8482;","(TM)"], 
+    ["&#174;","(R)"], ["&#169;","(C)"], ["&#8217;", "'"]
+  ]
+  
+  LISTS = [
+    ["<ol>", ""], ["</ol>", "\n\n"], ["<ul>", ""], ["</ul>", "\n\n"], ["<li>", "+  "], ["</li>", "\n"]
+  ]
+
+  TABLES = [
+    ["<table>","\n\n<table>"], ["</table>","</table>\n\n"]
+  ]
+
+  def initialize (html)
+    super(html)
+    @workingcopy = html
+  end
+
+#++  
+  #Call all necessary methods to convert a string of HTML into Markdown markup.
+
+  def to_markdown
+    headings(@workingcopy)
+    structure(@workingcopy)
+    text_formatting(@workingcopy)
+    lists(@workingcopy)
+    entities(@workingcopy)
+    tables(@workingcopy)
+    @workingcopy = CGI::unescapeHTML(@workingcopy)
+    @workingcopy
+  end
+
+#--
+  #The conversion methods themselves are private.
+  private
+
+  def text_formatting(text)
+    TEXT_FORMATTING.each do |htmltag, markdowntag|
+      text.gsub!(htmltag, markdowntag)
+    end
+    text
+  end
+
+
+  def headings(text)
+    HEADINGS.each do |htmltag, markdowntag|
+      text.gsub!(htmltag, markdowntag)
+    end
+    text
+  end
+  
+  
+  def lists(text)
+    LISTS.each do |htmltag, markdowntag|
+      text.gsub!(htmltag, markdowntag)
+    end
+    text
+  end
+
+
+  def entities(text)
+    ENTITIES.each do |htmlentity, markdownentity|
+      text.gsub!(htmlentity, markdownentity)
+    end
+    text
+  end
+
+
+  def structure(text)
+    STRUCTURES.each do |htmltag, markdowntag|
+      text.gsub!(htmltag, markdowntag)
+    end
+    text
+  end
+
+  def tables(text)
+    TABLES.each do |htmltag, markdowntag|
+      text.gsub!(htmltag, markdowntag)
+    end
+    text
+  end
+
+
+  def css_styles(text)
+    #TODO: Translate CSS-styles
+    text
+  end
+#++
+end # end class ClothBlue

data/test/test_entities.rb

@@ -0,0 +1,31 @@
+# test_entities.rb
+# May 14, 2008
+#
+
+$:.unshift File.join(File.dirname(__FILE__),'..','lib')
+
+begin
+  require "rubygems"
+  require "clothblue"
+rescue LoadError 
+  require "clothblue"
+end
+
+require 'test/unit'
+
+class TestClothBlueEntities < Test::Unit::TestCase
+ 
+  ENTITIES_TEST = [
+    ["&#8220;", '"'], ["&#8221;", '"'], ["&#8212;", "--"], ["&#8212;", "--"], 
+    ["&#8211;","-"], ["&#8230;", "..."], ["&#215;", " x "], ["&#8482;","(TM)"], 
+    ["&#174;","(R)"], ["&#169;","(C)"], ["&#8217;", "'"]
+  ]
+  
+  def test_entities
+    ENTITIES_TEST.each do |html, markdown|
+      test_html = ClothBlue.new(html)
+      result = test_html.to_markdown
+      assert_equal(markdown,result)
+    end
+  end
+end

data/test/test_formatting.rb

@@ -0,0 +1,33 @@
+# test_formatting.rb
+# May 15, 2008
+#
+
+#circumventing a require Problem:
+$:.unshift File.join(File.dirname(__FILE__), "..", "lib")
+
+begin
+  require "rubygems"
+  require "clothblue"
+rescue LoadError
+  require "clothblue"
+end
+
+require "test/unit"
+
+class TestClothBlueFormatting <  Test::Unit::TestCase
+  
+  FORMATTING_STRINGS = [
+    ["<b>bold</b>","**bold**"], ["<strong>strong</strong>", "**strong**"], 
+    ["<em>emphasized</em>", "_emphasized_"],["<i>italics</i>", "_italics_"], 
+    ["<code>ClothBlue#to_markdown</code>", "`ClothBlue#to_markdown`"]
+  ]
+ 
+  def test_textformatting
+    FORMATTING_STRINGS.each do |html, markdown|
+      test_html = ClothBlue.new(html)
+      result = test_html.to_markdown
+      assert_equal(markdown,result)
+    end
+  end
+
+end

data/test/test_headings.rb

@@ -0,0 +1,46 @@
+# test_headings.rb
+# May 15, 2008
+#
+
+$:.unshift File.join(File.dirname(__FILE__),'..','lib')
+
+begin
+  require "rubygems"
+  require "clothblue"
+rescue LoadError
+  require "clothblue"
+end
+
+require 'test/unit'
+
+class TestClothBlueHeadings < Test::Unit::TestCase
+
+  HEADING_TEST = [
+  ["<h1>Heading 1</h1>","# Heading 1 #\n\n"], ["<h2>Heading 2</h2>", "## Heading 2 ##\n\n"],
+  ["<h3>Heading 3</h3>", "### Heading 3 ###\n\n"], ["<h4>Heading 4</h4>", "#### Heading 4 ####\n\n"],
+  ["<h5>Heading 5</h5>", "##### Heading 5 #####\n\n"], ["<h6>Heading 6</h6>", "###### Heading 6 ######\n\n"]
+  ]
+
+
+  def test_headings
+    HEADING_TEST.each do |html, markdown|
+      test_html = ClothBlue.new(html)
+      result = test_html.to_markdown
+      assert_equal(markdown,result)
+    end
+  end
+
+  MIST_TEST = [
+  ["<h1>Heading 1</h1><h2>Heading 2</h2>","# Heading 1 #\n\n## Heading 2 ##\n\n"],
+  ]
+
+
+  def test_mist_headings
+    MIST_TEST.each do |html, markdown|
+      test_html = ClothBlue.new(html)
+      result = test_html.to_markdown
+      assert_equal(markdown,result)
+    end
+  end
+
+end

data/test/test_lists.rb

@@ -0,0 +1,29 @@
+# test_lists.rb
+# May 15, 2008
+#
+
+$:.unshift File.join(File.dirname(__FILE__),'..','lib')
+
+begin
+  require "rubygems"
+  require "clothblue"
+rescue LoadError
+  require "clothblue"
+end
+
+require 'test/unit'
+
+class TestClothBlueLists < Test::Unit::TestCase
+ 
+LISTS_TEST = [
+    ["<ol>",""], ["</ol>","\n\n"], ["<li>","+  "], ["</li>","\n"], ["<ul>", ""], ["</ul>", "\n\n"]
+  ]
+  
+  def test_lists
+    LISTS_TEST.each do |html, markdown|
+      test_html = ClothBlue.new(html)
+      result = test_html.to_markdown
+      assert_equal(markdown,result)
+    end
+  end
+end

data/test/test_structure.rb

@@ -0,0 +1,32 @@
+# test_structure.rb
+# May 15, 2008
+#
+
+$:.unshift File.join(File.dirname(__FILE__),'..','lib')
+
+begin
+  require "rubygems"
+  require "clothblue"
+rescue LoadError
+  require "clothblue"
+end
+
+require 'test/unit'
+
+class TestClothBlueStructures < Test::Unit::TestCase
+ 
+  STRUCTURE_TEST = [
+  ["<blockquote>blockquote</blockquote>","> blockquote\n"],
+  ["<p>paragraph</p><p>another paragraph</p>", "\n\nparagraph\n\n\n\nanother paragraph\n\n"], 
+  ["HTML page break<br>", "HTML page break\n"], ["XHTML page break<br />", "XHTML page break\n"]
+  ]
+  
+  
+  def test_structures
+    STRUCTURE_TEST.each do |html, markdown|
+      test_html = ClothBlue.new(html)
+      result = test_html.to_markdown
+      assert_equal(markdown,result)
+    end
+  end
+end

data/test/test_tables.rb

@@ -0,0 +1,30 @@
+# test_tables.rb
+# May 15, 2008
+#
+
+$:.unshift File.join(File.dirname(__FILE__),'..','lib')
+
+begin
+  require "rubygems"
+  require "clothblue"
+rescue LoadError
+  require "clothblue"
+end
+
+require 'test/unit'
+
+class TestClothBlueTables < Test::Unit::TestCase
+ 
+  TABLES_TEST = [
+    ["<table><tr><td>name</td><td>age</td><td>sex</td></tr><tr><td>joan</td><td>24</td><td>f</td></tr></table>",
+    "\n\n<table><tr><td>name</td><td>age</td><td>sex</td></tr><tr><td>joan</td><td>24</td><td>f</td></tr></table>\n\n"]
+  ]
+  
+  def test_entities
+    TABLES_TEST.each do |html, markdown|
+      test_html = ClothBlue.new(html)
+      result = test_html.to_markdown
+      assert_equal(markdown,result)
+    end
+  end
+end

metadata

@@ -0,0 +1,70 @@
+--- !ruby/object:Gem::Specification 
+name: cpjolicoeur-ClothBlue
+version: !ruby/object:Gem::Version 
+  version: 0.2.2
+platform: ruby
+authors: 
+- Craig P Jolicoeur
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2008-05-14 13:03:28.160028 -07:00
+default_executable: 
+dependencies: []
+
+description: ClothBlue is BlueCloth's evil twin.  It converts existing HTML into Markdown format for use with BlueCloth.
+email: cpjolicoeur@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- README
+- TODO
+- clothblue.gemspec
+- lib/clothblue.rb
+- lib/README.rdoc
+- test/README
+- test/test_entities.rb
+- test/test_formatting.rb
+- test/test_headings.rb
+- test/test_lists.rb
+- test/test_structure.rb
+- test/test_tables.rb
+has_rdoc: true
+homepage: http://github.com/cpjolicoeur/clothblue
+post_install_message: 
+rdoc_options: 
+- --main
+- lib/README.rdoc
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.0.1
+signing_key: 
+specification_version: 2
+summary: HTML to Markdown converter
+test_files: 
+- test/test_entities.rb
+- test/test_formatting.rb
+- test/test_headings.rb
+- test/test_lists.rb
+- test/test_structure.rb
+- test/test_tables.rb