hypertextmarkdown 0.0.1

data/.gitignore

@@ -0,0 +1 @@
+spec/fixtures.yml

data/Gemfile

@@ -0,0 +1,8 @@
+source :rubygems
+gemspec
+
+gem "bump"
+gem "rake"
+gem "rspec", "~>2"
+gem "nokogiri"
+

data/Gemfile.lock

@@ -0,0 +1,30 @@
+PATH
+  remote: .
+  specs:
+    hypertextmarkdown (0.0.1)
+
+GEM
+  remote: http://rubygems.org/
+  specs:
+    bump (0.3.5)
+    diff-lcs (1.1.3)
+    nokogiri (1.5.2)
+    rake (0.9.2.2)
+    rspec (2.11.0)
+      rspec-core (~> 2.11.0)
+      rspec-expectations (~> 2.11.0)
+      rspec-mocks (~> 2.11.0)
+    rspec-core (2.11.1)
+    rspec-expectations (2.11.3)
+      diff-lcs (~> 1.1.3)
+    rspec-mocks (2.11.3)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  bump
+  hypertextmarkdown!
+  nokogiri
+  rake
+  rspec (~> 2)

data/Rakefile

@@ -0,0 +1,6 @@
+require "bundler/gem_tasks"
+require "bump/tasks"
+
+task :default do
+  sh "rspec spec/"
+end

data/Readme.md

@@ -0,0 +1,15 @@
+# HyperTextMarkDown
+
+Convert html to markdown
+
+Usage
+=====
+
+    markdown = HyperTextMarkDown::to_markdown("<b>Goodbye world</b>")
+
+
+Author
+======
+[Jonathan Cheatham](http://github.com/jcheatham)<br/>
+coaxis@gmail.com<br/>
+License: MIT

data/hypertextmarkdown.gemspec

@@ -0,0 +1,12 @@
+$LOAD_PATH.unshift File.expand_path("../lib", __FILE__)
+name = "hypertextmarkdown"
+require "#{name}/version"
+
+Gem::Specification.new name, HyperTextMarkDown::VERSION do |s|
+  s.summary = "HTML to markdown converter"
+  s.authors = ["Jonathan Cheatham"]
+  s.email = "coaxis@gmail.com"
+  s.homepage = "http://github.com/jcheatham/#{name}"
+  s.files = `git ls-files`.split("\n")
+  s.license = "MIT"
+end

data/lib/hypertextmarkdown.rb

@@ -0,0 +1,93 @@
+# encoding: UTF-8
+require 'hypertextmarkdown/version'
+require 'nokogiri'
+
+module HyperTextMarkDown
+
+  class << self
+
+    def to_markdown(str)
+      html = Nokogiri::HTML(str)
+      # pre-processing / xpath selection here
+      html.children.map{|child| mark_element(child)}.join
+    end
+
+    private
+
+    def mark_element(element, opts={})
+      #puts "\nmark_element(#{element.inspect},#{opts.inspect})"
+      if element.is_a?(Nokogiri::XML::Text)
+        return "" if element.text.to_s.strip.empty?
+        return element.text
+      end
+
+      children = element.children
+
+      case element.name.downcase
+
+      when 'br'
+        "  \n"
+
+      when 'hr'
+        "\n****\n"
+
+      when 'a'
+        "[#{children.map{|child| mark_element(child,opts)}.join}](#{element['href']})"
+
+      when 'img'
+        "![#{element['alt']}](#{element['src']})"
+
+      when 'em', 'i'
+        "*#{children.map{|child| mark_element(child,opts)}.join}*"
+
+      when 'strong', 'b'
+        "**#{children.map{|child| mark_element(child,opts)}.join}**"
+
+      when 'span'
+        "#{children.map{|child| mark_element(child,opts)}.join}"
+
+      when 'p'
+        "#{opts[:indent]}#{children.map{|child| mark_element(child,opts)}.join}\n\n"
+
+      when 'code'
+        "\n\n```\n#{children.map{|child| mark_element(child,opts)}.join}\n```\n"
+
+      when 'pre'
+        new_indent = "#{opts[:indent]}    "
+        "#{opts[:indent]}#{children.map{|child| mark_element(child,opts.merge(:indent=>new_indent))}.join}\n"
+
+      when 'blockquote'
+        new_indent = "#{opts[:indent]}  > "
+        "#{children.map{|child| mark_element(child,opts.merge(:indent=>new_indent))}.join}"
+
+      when 'h1'
+        "# #{children.map{|child| mark_element(child,opts)}.join}\n"
+      when 'h2'
+        "## #{children.map{|child| mark_element(child,opts)}.join}\n"
+      when 'h3'
+        "### #{children.map{|child| mark_element(child,opts)}.join}\n"
+
+      when 'ul'
+        spacer = opts[:list_type] ? "" : "\n"
+        "#{spacer}#{children.map{|child| mark_element(child,opts.merge(:list_type=>:ul))}.join}"
+
+      when 'ol'
+        spacer = opts[:list_type] ? "" : "\n"
+        "#{spacer}#{children.map{|child| mark_element(child,opts.merge(:list_type=>:ol))}.join}"
+
+      when 'li'
+        li_prefix = (opts[:list_type] == :ol) ? "  - " : "  1. "
+        new_indent = "#{opts[:indent]}    "
+        "#{opts[:indent]}#{li_prefix}#{children.map{|child| mark_element(child,opts.merge(:indent=>new_indent))}.join}\n"
+
+      when 'script','style'
+        ""
+
+      else
+        "#{children.map{|child| mark_element(child,opts)}.join}"
+
+      end
+    end
+
+  end
+end

data/lib/hypertextmarkdown/version.rb

@@ -0,0 +1,3 @@
+module HyperTextMarkDown
+  VERSION = "0.0.1"
+end

data/spec/hypertextmarkdown_spec.rb

@@ -0,0 +1,36 @@
+require 'hypertextmarkdown'
+
+ROOT = File.expand_path('../../', __FILE__)
+
+describe "hypertextmarkdown" do
+  describe "convert html to markdown" do
+
+    it "handles a basic example" do
+      HyperTextMarkDown::to_markdown("1 how's <strong>IT</strong> going?").should == "1 how's **IT** going?\n\n"
+    end
+
+    it "ignores unknown tags" do
+      HyperTextMarkDown::to_markdown("2 how's <string>IT</string> going?").should == "2 how's IT going?\n\n"
+    end
+
+    it "kinda handles a broken tag" do
+      HyperTextMarkDown::to_markdown("3 how's <strong IT</strong> going?").should == "3 how's ** going?**\n\n"
+    end
+
+    it "kinda handles a different broken tag" do
+      HyperTextMarkDown::to_markdown("4 how's <strong>IT</stro\nng> going?").should == "4 how's **IT going?**\n\n"
+    end
+
+    it "converts a reasonable sample" do
+      html = "<html><body><div class=\"mail_main\"><span>Example</span><hr /><h3>Contact form</h3>\nHello<br />\n<ol>\n<li>Contact Info:\n<ul>\n<li>Name: <strong>Joe Somebody</strong></li>\n<li>E-mail: <a href=\"mailto:somebody@example.com\">somebody@example.com</a></li><li>Code sample: <code>\n#include &lt;stdio.h&gt;\n\nint main(int argc, char** argv) {\nprintf(\"blah\");\nreturn 0;\n}\n</code></li>\n<ul>\n</li>\n<li>Supplemental Info:\n<ul>\n<li>Favorite color: <span>teal</span></li>\n<li>Favorite image: <img alt=\"Fun\" src=\"http://upload.wikimedia.org/wikipedia/commons/e/ec/Happy_smiley_face.png\"/></li>\n</ul>\n</li>\n</ol>\n</div>\n</body></html>"
+
+      expected = "Example\n****\n### Contact form\n\nHello  \n\n  - Contact Info:\n      1. Name: **Joe Somebody**\n      1. E-mail: [somebody@example.com](mailto:somebody@example.com)\n      1. Code sample: \n\n```\n\n#include <stdio.h>\n\nint main(int argc, char** argv) {\nprintf(\"blah\");\nreturn 0;\n}\n\n```\n\n\n  - Supplemental Info:\n      1. Favorite color: teal\n      1. Favorite image: ![Fun](http://upload.wikimedia.org/wikipedia/commons/e/ec/Happy_smiley_face.png)\n\n"
+
+      markdown = HyperTextMarkDown::to_markdown(html)
+
+      markdown.should == expected
+    end
+  end
+
+end
+

data/spec/spec_helper.rb

@@ -0,0 +1 @@
+require "hypertextmarkdown"

metadata

@@ -0,0 +1,55 @@
+--- !ruby/object:Gem::Specification
+name: hypertextmarkdown
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+  prerelease: 
+platform: ruby
+authors:
+- Jonathan Cheatham
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-01-10 00:00:00.000000000 Z
+dependencies: []
+description: 
+email: coaxis@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- Gemfile.lock
+- Rakefile
+- Readme.md
+- hypertextmarkdown.gemspec
+- lib/hypertextmarkdown.rb
+- lib/hypertextmarkdown/version.rb
+- spec/hypertextmarkdown_spec.rb
+- spec/spec_helper.rb
+homepage: http://github.com/jcheatham/hypertextmarkdown
+licenses:
+- MIT
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.23
+signing_key: 
+specification_version: 3
+summary: HTML to markdown converter
+test_files: []