markup_parser 0.0.1

data/.gitignore

@@ -0,0 +1,17 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp

data/Gemfile

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

data/Rakefile

@@ -0,0 +1,2 @@
+#!/usr/bin/env rake
+require "bundler/gem_tasks"

data/lib/markup_parser.rb

@@ -0,0 +1,11 @@
+require "markup_parser/version"
+
+module MarkupParser
+  puts "\n**************\nMarkupParser loaded\n**************\n"
+
+  self.parser_path = File.join(File.dirname(__FILE__), 'markup_parser')
+
+  def self.parsers
+    @parsers ||= Dir.glob( File.join(@parser_path, '*.rb') ).collect {|f| File.basename(f, '.rb') } - ["default"]
+  end
+end

data/lib/markup_parser/default.rb

@@ -0,0 +1,109 @@
+module MarkupParser
+  class Default
+    puts "\n**************\nMarkupParser::Default loaded\n**************\n"
+    attr_reader :original_text, :nokoguri_parser, :html_text, :lexer_proc
+
+    def initialize(text='', &lexer)
+      @original_text = hot_fixes(text)
+      @lexer_proc = lexer || default_lexer
+    end
+
+
+    # Returns the fully stylized and sanitized HTML
+    def to_html
+      begin
+        nokoguri_parser.to_xhtml(:save_with => Nokogiri::XML::Node::SaveOptions::AS_XHTML)
+      rescue => e
+        puts "
+        \n******************
+        Error in #{self.class}#to_html.
+        Reason: #{e.message}.
+        Putting error message into the output.
+        ******************\n"
+        return "<p class='parse_error'>Error in parsing in #{self.class}: #{e.message}.</p>"
+      end
+    end
+
+
+    # Instantiates a Nokoguri::HTML fragment parser
+    def nokoguri_parser
+      begin
+        @nokoguri_parser ||= Nokogiri::HTML::DocumentFragment.parse(html_text)
+      rescue => e
+        puts "
+        \n******************
+        Error in #{self.class}#nokoguri_parser.
+        Reason: #{e.message}.
+        Putting error message into the output.
+        ******************\n"
+        @nokoguri_parser = Nokogiri::HTML::DocumentFragment.parse("<p class='parse_error'>Error in parsing in #{self.class}: #{e.message}.</p>")
+      end
+    end
+
+    # Instantiates the html_text via this markup parser
+    def html_text
+      begin
+        @html_text ||= parse(@original_text)
+      rescue => e
+          puts "
+          \n******************
+          Error in #{self.class}#html_text.
+          Reason: #{e.message}.
+          Putting error message into the output.
+          ******************\n"
+          @html_text = "<p class='parse_error'>Error in parsing in #{self.class}: #{e.message}.</p>"
+      end
+    end
+
+    # Stylizes the code blocks in the html_text.
+    # Uses either a passed in lexer Proc or the default_lexer
+    def stylize_code_blocks
+        nokoguri_parser.search('pre').each do |node|
+          begin
+            next unless lang = node['lang']
+            text = node.inner_text
+            html = @lexer_proc.call(text, lang)
+            node.replace(html)
+          rescue => e
+            puts "
+            \n******************
+            Error in parsing <pre lang=''> block.
+            Reason: #{e.message}.
+            Continueing code block parsing.
+            ******************\n"
+          end
+        end
+      self
+    end
+
+
+
+
+    private
+
+    # Default Lexer Proc
+    def default_lexer
+      Proc.new {|code, lang| Uv.parse(code, "xhtml", lang, false, "railscasts") }
+    end
+
+
+
+    ######################################################################
+    # TO BE OVERRIDDEN
+
+    # Markup specific Parser invokation
+    def parse(text)
+      text
+    end
+
+
+    # Performs hotfixes on a per-markup basis
+    def hot_fixes(text)
+      text
+    end
+
+    ######################################################################
+
+
+  end
+end

data/lib/markup_parser/html.rb

@@ -0,0 +1,13 @@
+module MarkupParser
+  class Html < MarkupParser::Default
+    puts "\n**************\nMarkupParser::Html loaded\n**************\n"
+
+    private
+
+    # Performs my html hotfixes
+    def hot_fixes(text)
+      text
+    end
+
+  end
+end

data/lib/markup_parser/markdown.rb

@@ -0,0 +1,116 @@
+module MarkupParser
+  class Markdown < MarkupParser::Default
+    puts "\n**************\nMarkupParser::Markdown loaded\n**************\n"
+
+    # HTML renderer with Ultraviolet Code Lexer
+    class UvHtmlRender < Redcarpet::Render::HTML
+      puts "\n**************\nMarkupParser::Markdown::UvHtmlRender loaded\n**************\n"
+      def block_code(code, language)
+        Uv.parse(code, "xhtml", language, false, "railscasts")
+      end
+    end
+
+
+    # Only loads the Markdown parser once
+    def self.html_parser_with_code_lexer
+      @@html_parser_with_code_lexer ||= Redcarpet::Markdown.new(UvHtmlRender, OPTIONS)
+    end
+
+
+    # Only loads the Markdown parser once
+    def self.html_parser
+      @@parser_with_code_blocks ||= Redcarpet::Markdown.new(Redcarpet::Render::HTML, OPTIONS)
+    end
+
+    # Selected Markdown Options
+    OPTIONS = {
+      autolink: true, #parse links even when they are not enclosed in `<>` characters. Autolinks for the http, https and ftp
+                 #protocols will be automatically detected. Email addresses are also handled, and http links without protocol, but
+                 #starting with `www.`
+      no_intraemphasis: true, #will stop underscores within words from being treated as the start or end of emphasis blocks
+                        #and will therefore stop Ruby method or variable names with underscores in them from triggering the emphasis
+      lax_html_blocks: true,  #HTML blocks do not require to be surrounded by an empty line as in the Markdown standard.
+      strikethrough: true, #parse strikethrough, PHP-Markdown style Two `~` characters mark the start of a strikethrough, e.g. `this is ~~good~~ bad`
+      fenced_code_blocks: true, #renders fenced code (```) and (~~~)
+      tables: true, #parse tables, PHP-Markdown style
+    }
+
+
+
+
+
+
+
+    # Returns the fully stylized HTML for this markdown text
+    def html_text
+      @html_text ||= parser.render(@original_text)
+    end
+
+    # Sets the parser to include as code lexer
+    def stylize_code_blocks
+      @parser = Markdown.html_parser_with_code_lexer
+      self
+    end
+
+
+
+
+    private
+
+    # Instantiates the parser for this Markdown instance.
+    # Defaults to @@html_parser
+    def parser
+      @parser ||= Markdown.html_parser
+    end
+
+    # Hacks parse to return this instence's parser for a later call
+    def parse(text)
+      parser
+    end
+
+    # Performs my markdown hotfixes
+    def hot_fixes(text)
+      text.standardize_newlines!
+      text.convert_tabs_to_spaces!
+      text.correct_gh_code_syntax!
+      text
+    end
+
+  end
+end
+
+
+
+
+# Adds classes to String class...
+class String
+
+  # Corrects the gh code block syntax mistake where one would write '~~~ .ruby'
+  # and the correct code should be '~~~ruby'
+  def correct_gh_code_syntax!
+    self.gsub!(/~~~\s\.([a-zA-Z]*)/, '~~~\1')
+  end
+
+  # Corrects the ol list elements: which only except the syntax: '1. ...'.
+  # Corrected syntaxes: '1)'
+  def correct_ol_list_parenth!
+    self.gsub!(/(\s*)(\d)\)/,'\1\2.')
+  end
+
+  # Converts tabs (\t) to 2 spaces
+  def convert_tabs_to_spaces!
+    self.gsub!(/\t/, "  ")
+  end
+
+  # Standardize line endings
+  def standardize_newlines!
+    self.gsub!("\r\n", "\n")
+    self.gsub!("\r", "\n")
+  end
+
+  # Corrects the newlines by stripping the leading whitespace.
+  # NOTE: this is a hack to workaround the strange Gollum editor indentation behavior
+  def sub_newlines!
+    self.gsub!(/([\r\n|\n])[\ ]*(.)/,'\1\2')
+  end
+end

data/lib/markup_parser/rdoc.rb

@@ -0,0 +1,26 @@
+require 'rdoc/markup/to_html'
+module MarkupParser
+  class Rdoc < MarkupParser::Default
+    puts "\n**************\nMarkupParser::Rdoc loaded\n**************\n"
+
+
+
+    private
+
+    # Returns the fully stylized HTML for this text
+    # Forces UTF-8 encoding since Rdoc seems to return ASCII-8BIT
+    def parse(text)
+      Rdoc.parser.convert(text).force_encoding("UTF-8")
+    end
+
+    # Memorized Parser
+    def self.parser
+      @@parser ||= RDoc::Markup::ToHtml.new
+    end
+
+    # Performs my rdoc hotfixes
+    def hot_fixes(text)
+      text
+    end
+  end
+end

data/lib/markup_parser/version.rb

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

data/markup_parser.gemspec

@@ -0,0 +1,19 @@
+# -*- encoding: utf-8 -*-
+require File.expand_path('../lib/markup_parser/version', __FILE__)
+
+Gem::Specification.new do |gem|
+  gem.authors       = ["Quinn"]
+  gem.email         = ["chaffeqa@gmail.com"]
+  gem.description   = %q{Standardized markup parsers to use a single format: an object.  Instantiate a specific markup class with text to output formated Html.  Allows for easy code block highlighting using a Proc; defaults to Uv (ruby Ultraviolet)}
+  gem.summary       = %q{Standardized markup parsers to a single format.  Sole use is for converting markup text to Html. }
+  gem.homepage      = "https://github.com/chaffeqa/markup_parser"
+
+  gem.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  gem.files         = `git ls-files`.split("\n")
+  gem.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  gem.name          = "markup_parser"
+  gem.require_paths = ["lib"]
+  gem.version       = MarkupParser::VERSION
+
+  gem.add_dependency "uv"
+end

metadata

@@ -0,0 +1,69 @@
+--- !ruby/object:Gem::Specification
+name: markup_parser
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+  prerelease: 
+platform: ruby
+authors:
+- Quinn
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2011-09-28 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: uv
+  requirement: &70102402385260 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *70102402385260
+description: ! 'Standardized markup parsers to use a single format: an object.  Instantiate
+  a specific markup class with text to output formated Html.  Allows for easy code
+  block highlighting using a Proc; defaults to Uv (ruby Ultraviolet)'
+email:
+- chaffeqa@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- Rakefile
+- lib/markup_parser.rb
+- lib/markup_parser/default.rb
+- lib/markup_parser/html.rb
+- lib/markup_parser/markdown.rb
+- lib/markup_parser/rdoc.rb
+- lib/markup_parser/version.rb
+- markup_parser.gemspec
+homepage: https://github.com/chaffeqa/markup_parser
+licenses: []
+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: 1.8.10
+signing_key: 
+specification_version: 3
+summary: Standardized markup parsers to a single format.  Sole use is for converting
+  markup text to Html.
+test_files: []