pasta 0.0.1

data/lib/pasta/ingredients/empty_lines.rb

@@ -0,0 +1,13 @@
+module Pasta
+  module Ingredients
+    
+    EMPTY_LINE = /\A\s*[\n\r]+/
+    
+    def empty_lines(text, html)
+      text.sub!(EMPTY_LINE) do |match|
+        match = ''
+      end
+      [text, html]
+    end
+  end
+end

data/lib/pasta/ingredients/html_entities.rb

@@ -0,0 +1,17 @@
+module Pasta
+  module Ingredients
+     
+    HTML_ENTITIES = {
+      '&' => '&' 
+    }
+    
+    def html_entities(text, html)
+      HTML_ENTITIES.each do |entity, transformation|
+        html = text.gsub(/[#{entity}]/) do |match|
+          match = transformation
+        end
+      end
+      [text, html]
+    end
+  end
+end

data/lib/pasta/ingredients/links.rb

@@ -0,0 +1,58 @@
+module Pasta
+  module Ingredients
+    
+    # Parses both links and images
+    # $1 => "!", $2 => link text, $4 => inline url, $5 => reference id
+    LINKS = /([!]*)\[(.+?)\](\((.+?)\)|\s?\[(.*?)\])/
+    
+    LINK_DEFINITION = /^ {0,3}\[([\w\s]+?)\]: (.+?)(^\s*[\n\r]|\z)/m
+    
+    def links(text, html)
+      find_link_definitions(text)
+      
+      text.gsub!(LINKS) do |match|
+        link_text, target = $2, ''
+        if $4
+          # It's an inline link
+          target = $4
+        else
+          # It's a reference link
+          id = $5 == '' ? $2.downcase : $5.downcase
+          break unless @link_definitions && @link_definitions.key?(id)
+          target = @link_definitions[id][:target]
+        end
+        # format image or link
+        url, title = parse_link target
+        if $1 == '!'
+          match = "<img src=\"#{url}\" alt=\"#{link_text}\"#{title} />"
+        else
+          match = "<a href=\"#{url}\"#{title}>#{link_text}</a>"
+        end
+      end
+      
+      text = clean_link_definitions(text)
+      [text, html]
+    end
+    
+    def find_link_definitions(text)
+      @link_definitions = {}
+      text.gsub(LINK_DEFINITION) do |match|
+        @link_definitions[$1.downcase] = {target: $2, used: false}
+      end
+    end 
+    
+    def clean_link_definitions(text)
+      @link_definitions.each do |key,val|
+        text.gsub!(/^ {0,3}\[#{key}\]: (.+?)(^\s*[\n\r]|\z)/mi, '')
+      end
+      text
+    end
+    
+    def parse_link(text)
+      target = text.split(' ')
+      url = target[0].gsub(/[<>]/, '')
+      title = " title=#{target[1..-1].join(' ').strip}" if target.length > 1
+      [url, title]
+    end
+  end
+end

data/lib/pasta/ingredients/lists.rb

@@ -0,0 +1,31 @@
+module Pasta
+  module Ingredients
+    
+    LIST = /\A\s{0,3}(([-*+]|([0-9]+)\.) .+?)((^\s*[\n\r])|\z)/m
+    
+    def lists(text, html)
+      text.sub!(LIST) do |match|
+        inner_text, inner_html, list_type = $1, '', 'ul'
+        
+        # determine the list_type
+        list_type = 'ol' unless %w{- * +}.include? $1.strip[0]
+        
+        # extract list items
+        inner_html = list_items(inner_text)
+        
+        html << "<#{list_type}>\n#{inner_html}</#{list_type}>\n\n"
+        match = ''
+      end
+      [text, html]
+    end
+    
+    def list_items(text)
+      html = ''
+      text.gsub(/^([-*+]|\d+\.) (.+?)$(?=([\n\r]([*+-]|(\d+\.))|\z))/m) do |match| 
+        html << "<li>#{$2.gsub(/\n\s+/, ' ').strip}</li>\n"
+        match = ''
+      end
+      html
+    end
+  end
+end

data/lib/pasta/ingredients/page_breaks.rb

@@ -0,0 +1,14 @@
+module Pasta
+  module Ingredients
+   
+    PAGE_BREAK = /\A([*-_]\s?){3,}$/
+    
+    def page_breaks(text, html)
+      text.sub!(PAGE_BREAK) do |match|
+        html << "<hr />"
+        match = ''
+      end
+      [text, html]
+    end
+  end
+end

data/lib/pasta/ingredients/paragraphs.rb

@@ -0,0 +1,27 @@
+module Pasta
+  module Ingredients
+
+    PARAGRAPH   = /\A(?![>])(.+?)((^\s*[\n\r])|\z)/m
+  
+    def paragraphs(text, html)
+      text.sub!(PARAGRAPH) do |match| 
+
+        inner_text, inner_html = $1, ''
+        inner_text.gsub!(/[ ]{2,}[\n\r]/, "<br />\n")      
+        inner_text.strip!
+
+        if grammars.key? :paragraphs
+          grammars[:paragraphs].each do |rule|
+            inner_text, inner_html = send(rule, inner_text, '')
+          end
+          inner_text = inner_html unless inner_html == ''
+        end
+
+        html << "<p>#{inner_text}</p>\n\n" unless inner_text == ''
+        match = ''
+      end
+      [text, html]  
+    end 
+
+  end
+end

data/lib/pasta/ingredients/setext_headings.rb

@@ -0,0 +1,20 @@
+module Pasta
+  module Ingredients
+    
+    SETEXT_HEADING = /\A(.+?)[\n\r]([=|-]+)([\n\r]|\z)/
+   
+    def setext_headings(text, html)    
+      text.sub!(SETEXT_HEADING) do |match| 
+        if grammars.key? :heading
+          grammars[:heading].each do |rule|
+            inner = send(rule, $1, '')
+          end
+        end
+        level = ($2[0] == '=') ? 1 : 2
+        html << "<h#{level}>#{$1}</h#{level}>\n" unless $1.nil?
+        match = ''
+      end    
+      [text, html]
+    end
+  end
+end

data/lib/pasta/recipes/base.rb

@@ -0,0 +1,40 @@
+require 'pasta/ingredients'
+
+module Pasta
+  module Recipes
+    class Base
+      
+      include Pasta::Ingredients
+                        
+      # Public. Generic to_x parser that converts a string to the specified output format.
+      #   Uses a depth first strategy to parse a text according to incredient rules as defined in a grammar
+      #   Raises a Pasta::Error if a grammar has not been defined
+      #
+      # text - a String to be parsed
+      #
+      # Example
+      #   to_html('some yummy text')
+      #   # => '<p>some yummy text</p>'
+      #
+      # Returns a String
+      def method_missing(method, *args, &block)
+        if method.to_s =~ /^to_(.+)$/
+          # ensure a grammar has been defined
+          raise Pasta::Error.new "A grammar for #{$1} has not been defined in recipe #{self.class.name}" if grammars($1.to_sym).nil?
+        
+          # Depth first parsing - each ingredient should accept and return an input and output
+          input, output = args[0], ''
+          while input != "" do
+            grammars($1.to_sym).each do |rule| 
+              input, output = send(rule, input, output)
+            end
+          end
+          output.strip  # remove any trailing whitespace
+        else
+          super
+        end
+      end
+        
+    end
+  end
+end

data/lib/pasta/recipes/gruber.rb

@@ -0,0 +1,27 @@
+module Pasta
+  module Recipes
+    class Gruber < Base
+
+      # Define the grammars
+      grammar(:html) { 
+        [:automatic_links, :links, :empty_lines, :page_breaks, :codeblocks, :blockquotes, :lists, :atx_headings, :setext_headings, :paragraphs] 
+      }
+      grammar(:blockquotes) { 
+        [:empty_lines, :page_breaks, :codeblocks, :blockquotes, :lists, :atx_headings, :setext_headings, :paragraphs] 
+      }
+      grammar(:lists) { 
+        [:empty_lines, :codeblocks, :blockquotes, :lists, :atx_headings, :setext_headings, :paragraphs] 
+      }
+      grammar(:atx_headings) { 
+        [:emphasis] 
+      }
+      grammar(:setext_headings) { 
+        [:emphasis] 
+      }
+      grammar(:paragraphs) { 
+        [:code, :emphasis] 
+      }
+
+    end
+  end
+end

data/lib/pasta/recipes/markdown.rb

@@ -0,0 +1,11 @@
+module Pasta
+  module Recipes
+    class Markdown < Gruber
+
+      # This is currently identical to the Gruber recipe.  
+      # TODO: Extract the specs from http://www.w3.org/community/markdown/ and rewrite the grammar
+
+
+    end
+  end
+end

data/lib/pasta/version.rb

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

data/pasta.gemspec

@@ -0,0 +1,24 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'pasta/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "pasta"
+  spec.version       = Pasta::VERSION
+  spec.authors       = ["Dave Kinkead"]
+  spec.email         = ["dave@kinkead.com.au"]
+  spec.description   = %q{À la carte markdown parsing}
+  spec.summary       = %q{Pasta is an extensible markdown text parser with a delicious menu of options}
+  spec.homepage      = "https://github.com/davekinkead"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files`.split($/)
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|specs|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.3"
+  spec.add_development_dependency "rake"
+  spec.add_development_dependency "markdown-testsuite"
+end

data/specs/base_spec.rb

@@ -0,0 +1,8 @@
+require 'spec_helper'
+
+describe Pasta::Recipes::Base do
+  let(:base) { Pasta::Recipes::Base.new }
+    
+  specify { ->{ base.to_nothing }.must_raise Pasta::Error }
+  specify { ->{ base.to_html 'some yummy text' }.must_raise Pasta::Error }
+end

data/specs/dish_spec.rb

@@ -0,0 +1,30 @@
+require "spec_helper"
+
+describe Pasta::Dish do
+
+  specify {  ->{ Pasta::Dish.new }.must_raise ArgumentError }
+  
+  let(:spaghetti) { Pasta::Dish.new 'Long, thin, cylindrical strings of durum' }
+  
+  specify { spaghetti.must_be_kind_of Pasta::Dish }
+  specify { spaghetti.must_respond_to :with }
+  specify { spaghetti.must_respond_to :make }
+  
+  let(:fettuccine) { Pasta::Dish.new 'Flat, thick, strings of egg and durum'}
+  
+  describe "#with" do
+    it "raises an error if a recipe can't be found" do
+      ->{ fettuccine.with(:unknown) }.must_raise Pasta::Error
+    end
+  end
+  
+  describe "#make" do
+    it "raises an error if a recipe can't be found" do
+      ->{ fettuccine.make(:unknown) }.must_raise Pasta::Error
+    end
+    
+    it "converts the sauce text into a string" do
+      fettuccine.make(:html).must_be_kind_of String
+    end
+  end
+end

data/specs/dsl_spec.rb

@@ -0,0 +1,12 @@
+require "spec_helper"
+
+describe Pasta do
+  specify { Pasta.must_respond_to :prepare }
+  specify { ->{ Pasta.prepare }.must_raise ArgumentError } 
+  specify { Pasta.prepare('some yummy text').must_be_kind_of Pasta::Dish }
+  specify { Pasta.prepare('a handful of text').with(:gruber).make(:html).must_equal '<p>a handful of text</p>' }
+  
+  it "uses :markdown as the default recipe" do
+    Pasta.prepare('thick, soft balls of flour and egg').make(:html).must_equal '<p>thick, soft balls of flour and egg</p>'
+  end
+end

data/specs/recipes/gruber/automatic_links.yml

@@ -0,0 +1,12 @@
+overview: |
+  Markdown supports a shortcut style for creating “automatic” links for URLs and email addresses: simply surround the URL or email address with angle brackets. What this means is that if you want to show the actual text of a URL or email address, and also have it be a clickable link.
+  
+  http://daringfireball.net/projects/markdown/syntax
+tests:    
+  - name: Automatic Links
+    desc: URL inside html tags are automatically parsed
+    text: | 
+      <http://example.com/>
+    html: |
+      <p><a href="http://example.com/">http://example.com/</a></p>
+  

data/specs/recipes/gruber/blockquotes.yml

@@ -0,0 +1,112 @@
+overview: |
+  Markdown uses email-style > characters for blockquoting. If you’re familiar with quoting passages of text in an email message, then you know how to create a blockquote in Markdown. It looks best if you hard wrap the text and put a > before every line:
+
+  > This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet,
+  > consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus.
+  > Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus.
+  > 
+  > Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse
+  > id sem consectetuer libero luctus adipiscing.
+
+  Markdown allows you to be lazy and only put the > before the first line of a hard-wrapped paragraph:
+
+  > This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet,
+  consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus.
+  Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus.
+
+  > Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse
+  id sem consectetuer libero luctus adipiscing.
+
+  Blockquotes can be nested (i.e. a blockquote-in-a-blockquote) by adding additional levels of >:
+
+  > This is the first level of quoting.
+  >
+  > > This is nested blockquote.
+  >
+  > Back to the first level.
+
+  Blockquotes can contain other Markdown elements, including headers, lists, and code blocks:
+
+  > ## This is a header.
+  > 
+  > 1.   This is the first list item.
+  > 2.   This is the second list item.
+  > 
+  > Here's some example code:
+  > 
+  >     return shell_exec("echo $input | $markdown_script");
+
+  Any decent text editor should make email-style quoting easy. For example, with BBEdit, you can make a selection and choose Increase Quote Level from the Text menu.
+  
+  http://daringfireball.net/projects/markdown/syntax
+tests:
+  - name: Single line block quote
+    desc: Quoting a single line of text
+    text: |
+      > This is a snazzy quote
+    html: |
+      <blockquote>
+      <p>This is a snazzy quote</p>
+      </blockquote>
+      
+  - name: Double line block quote
+    desc: Quoting a two paragraphs of text
+    text: |
+      > This is a snazzy quote
+      >
+      > It's longer than you think!
+    html: |
+      <blockquote>
+      <p>This is a snazzy quote</p>
+      
+      <p>It's longer than you think!</p>
+      </blockquote>
+      
+  - name: Lazy double quotes
+    desc: Quoting two lines of text with only lead >
+    text: |
+      > This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, 
+      consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. 
+      Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus.
+    html: |
+      <blockquote>
+      <p>This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, 
+      consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. 
+      Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus.</p>
+      </blockquote>
+
+  - name: Multiple blockquotes
+    desc: Using multiple blockquotes in succession 
+    text: |
+      > This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, 
+      consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus.
+      
+      > Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus.
+    html: |
+      <blockquote>
+      <p>This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, 
+      consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus.</p>
+      </blockquote>
+      
+      <blockquote>
+      <p>Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus.</p>
+      </blockquote>
+
+  - name: Nested blockquotes
+    desc: Blockquotes can contain blockquotes 
+    text: |
+      > This is the first level of quoting.
+      >
+      > > This is nested blockquote.
+      >
+      > Back to the first level.
+    html: |
+      <blockquote>
+      <p>This is the first level of quoting.</p>
+      
+      <blockquote>
+      <p>This is nested blockquote.</p>
+      </blockquote>
+      
+      <p>Back to the first level.</p>
+      </blockquote>