tartan 0.1.1 → 0.2.0

data/History.txt

@@ -0,0 +1,11 @@
+= 0.1.2 2007-01-22 (r181)
+* Refactored for "Tartan::" name space
+* Strip out html scripts in the span context.
+* Added select and option to the sets of span and block html tags.
+* Fixed problem with multiple embedded bullet-lists.
+-
+= 0.1.1 2006-08-21 (r177)
+* First gem
+* Initial version of parsing engine
+* Initial Markdown rules
+

data/Manifest.txt

@@ -0,0 +1,42 @@
+History.txt
+MIT-LICENSE
+Manifest.txt
+README.txt
+Rakefile
+TODO
+lib/core_ext.rb
+lib/core_ext/array.rb
+lib/core_ext/file.rb
+lib/core_ext/hash.rb
+lib/core_ext/match_data.rb
+lib/core_ext/module.rb
+lib/core_ext/regexp.rb
+lib/core_ext/symbolize.rb
+lib/tartan.rb
+lib/tartan/markdown.rb
+lib/tartan/markdown/markdown.yml
+lib/tartan/markdown/rules.rb
+lib/tartan/table/rules.rb
+lib/tartan/table/table.yml
+lib/tartan/test/base_rules.rb
+lib/tartan/test/test_base.yml
+lib/tartan/test/wiki-test.rb
+lib/tartan/wiki_rule.rb
+lib/tartan/wikilink/rules.rb
+lib/tartan/wikilink/wikilink.yml
+test/test-combo.rb
+test/test-combo.yml
+test/test-hash.rb
+test/test-markdown-and-wikilink.rb
+test/test-markdown-and-wikilink.yml
+test/test-markdown.rb
+test/test-markdown.yml
+test/test-match-data.rb
+test/test-readme-example.rb
+test/test-regexp.rb
+test/test-tables.rb
+test/test-tables.yml
+test/test-tartan.rb
+test/test-wikilink.rb
+test/test-wikilink.yml
+test/wikilink-test-helper.rb

data/{README → README.txt}

@@ -30,7 +30,7 @@ how you do it:
   # require 'rubygems' # if you are pulling Tartan in as a gem
   require 'tartan_markdown'
   
-  html = TartanMarkdown.new("* howdy\n* doody").to_html
+  html = Tartan::Markdown::Parser.new("* howdy\n* doody").to_html
   # => "<ul>\n<li>howdy</li>\n<li>doody</li>\n</ul>"
 
 Other parsers would have similar names and would have the same usage. In
@@ -49,19 +49,23 @@ have a specification for table mark-up. You can combine them by creating a new
 class that layers the tables onto the Markdown[http://daringfireball.net/projects/markdown/] definition as follows in a file
 called <tt>tartan_markdown_tables.rb</tt>:
 
-  require 'tartan_markdown_def'
-  require 'tartan_table_def'
+  require 'tartan/markdown/rules'
+  require 'tartan/table/rules'
   
-  class TartanMarkdownTables < Tartan
-    include TartanMarkdownDef
-    include TartanTableDef
+  modules Tartan
+    modules MarkdownTables
+      class Parser < Tartan::Parser
+        include TartanMarkdownDef
+        include TartanTableDef
+      end
+    end
   end
   
 In another file you could use this new parser:
 
   require 'tartan_markdown_tables'
   
-  html = TartanMarkdownTables.new("[|*happy*||**days**|]").to_html
+  html = Tartan::MarkdownTables::Parser.new("[|*happy*||**days**|]").to_html
   # => "<table class=\"\">
         <tr><td><em>happy</em></td><td><strong>days</strong></td></tr>
         </table>"
@@ -204,7 +208,7 @@ So, to add this syntax parsing, you would create the following specification:
 
 That's it for the mix-in specification.  Now we add these to the previous set.  We didn't touch on file naming of specifications before, but now we need to.  Let's say that we put the previous specification in a file called <tt>example-parser.yml</tt> and we put the new spec in <tt>entities.yml</tt>.  To combine them, we would create a new Ruby class like this:
 
-  class ExampleParserWithEntities < Tartan
+  class ExampleParserWithEntities < Tartan::Parser
     yaml "example-parser.yml"
     yaml "entities.yml"
   end

data/Rakefile

@@ -0,0 +1,78 @@
+# $Id$
+
+$:.push("lib", "test")
+
+require 'rubygems'
+require 'rake'
+require 'rake/clean'
+require 'rake/testtask'
+require 'rake/gempackagetask'
+require 'rake/rdoctask'
+require 'hoe'
+
+def version
+  if ENV['GEM_VERSION']: return ENV['GEM_VERSION']
+  elsif ENV['PWD'] =~ %r|tags/((?:[[:alnum:]]+\.)+[[:alnum:]]+)|: return $1
+  end
+
+  return nil
+end
+
+def name
+  "tartan"
+end
+namespace :build do
+  namespace :check do
+    task :manifest do
+      man_files = File.read('')
+    end
+  end
+
+  Hoe.new(name, version||"0.0.0") do |p|
+    p.summary = 'A library for building text parsers'
+    p.description = <<-TEXT_END
+  A text parsing engine. The syntax is defined outside the engine as regex-based
+  rules, in YAML or Ruby. It supports layering and multiple output types. Rules
+  for Markdown to HTML are included, with optional layered extensions for tables
+  and wikilinks.
+  TEXT_END
+    p.email = 'tartan@folklogic.com'
+    p.url = 'http://tartan.rubyforge.com/'
+    p.author = "Larry Baltz and David B. Anderson"
+  #  p.files += extra_files
+    p.changes = p.paragraphs_of('History.txt', 0..1).join("\n\n")
+    p.test_globs = 'test/test-*.rb'
+  end
+end
+
+def extra_files
+  %w(README TODO MIT-LICENSE)
+end
+
+def rdoc_extra
+  ['README']
+end
+
+def test_files
+  FileList['test/test*.rb']
+end
+
+namespace :test do
+  test_files.each do |file|
+    test_name = file.match(/^test\/test[-_]?(.*?)\.rb/)[1]
+    desc "Run #{test_name} tests"
+    task (test_name.to_sym) {ruby "-w -I test #{file}"}
+  end
+end
+
+task :default => [:test]
+
+task :version_check do
+  if version.nil?
+      raise "can't figure out build version"
+  end
+end
+
+task :version do
+  p version
+end

data/lib/core_ext/array.rb

@@ -1,12 +1,11 @@
 class Array
-    alias :old_index :index
-    def index(*args, &block)
-        if not args.empty?
-            old_index(*args)
-        else
-            result = find_all(&block).map { |item| old_index(item) }
-            return nil if result.empty?
-            return result[0]
-        end
+  alias :old_index :index
+  def index(*args, &block)
+    if block_given?
+      each_with_index { |v,i| return i if yield(v) }
+      return nil
+    else 
+      old_index(*args)
     end
-end
+  end
+end

data/lib/core_ext/module.rb

@@ -4,6 +4,8 @@ class Module
     @arg_sets[method_name] = [args, block]
   end
 
+  alias :tartan_included :included
+  
   def included(klass)
     return unless defined? @arg_sets
     @arg_sets.each do |method, (args, block)|

data/lib/core_ext.rb

@@ -0,0 +1,7 @@
+require 'core_ext/array'
+require 'core_ext/file'
+require 'core_ext/hash'
+require 'core_ext/match_data'
+require 'core_ext/module'
+require 'core_ext/regexp'
+require 'core_ext/symbolize'

data/lib/{markdown.yml → tartan/markdown/markdown.yml}

@@ -6,6 +6,13 @@
 #   handle return (\r) characters properly (especially in \r\n combo)
 
 span:
+  - title: html_script
+    shelve: true
+    match: /<script.*?\/script>/m
+    html:
+      start_mark: ''
+      end_mark: ''
+    
   - title: backtick_2
     shelve: true
     match: /`` ?(.+?) ?``/
@@ -26,6 +33,8 @@ span:
       start_mark: '<code>'
       end_mark: '</code>'
 
+  - title: code_done
+  
   - title: ref_image
     shelve: true
     match: /!\[(.*?)\][ ]?\[(.*?)\]/
@@ -50,7 +59,7 @@ span:
       / <\/?
           (?:span|cite|del|em|strong|dfn|code|samp|kbd|var|abbr
             |acronym|b|i|font|a|img|object|tt|big|small|strike|s|u
-            |sup|sub|q)
+            |sup|sub|q|select|option)
           (:?\s+[^\s>][^>]*?)?
         >/x
     html:
@@ -64,6 +73,30 @@ span:
       start_mark: ''
       end_mark: ''
 
+  - title: inline_image_with_title
+    shelve: true
+    match: /!\[(.+?)\]\((.+??)\s+"(.+?)"\)/
+    html:
+      replace: '<img src="\2" alt="\1" title="\3" />'
+
+  - title: inline_image
+    shelve: true
+    match: /!\[(.+?)\]\((.*?)\)/
+    html:
+      replace: '<img src="\2" alt="\1" />'
+
+  - title: link_with_title
+    shelve: true
+    match: /\[(.+?)\]\(<?(.+??)>?\s+"(.+?)"\)/
+    html:
+      replace: '<a href="\2" title="\3">\1</a>'
+
+  - title: link
+    shelve: true
+    match: /\[(.+?)\]\(<?(.*?)>?\)/
+    html:
+      replace: '<a href="\2">\1</a>'
+
   - title: amp
     match: /&/
     html:
@@ -116,7 +149,7 @@ span:
 
   - title: link_with_title
     shelve: true
-    match: /\[(.+?)\]\((.+??)\s+"(.+?)"\)/
+    match: /\[(.+?)\]\(<?(.+??)>?\s+"(.+?)"\)/
     html:
       replace: '<a href="\2" title="\3">\1</a>'
   - rescan
@@ -279,7 +312,7 @@ block:
 
   - title: bulletListSpaced
     match: >
-      / (?>\A(\s*)|\n(\n))
+      / (?>\A(\s*)|(\n)[ \t]*(\n))
                   (
                     [-*+](?>[ ]+|\t)[^\n]*
                     (?>\n(?>[ ]{4}|\t)?[^\n]+)*
@@ -301,20 +334,20 @@ block:
                   )/xm
     subparse:
       context: listSpaced
-      match_group: 3
+      match_group: 4
     html:
-      start_mark: "\\1\\2<ul>\n"
+      start_mark: "\\1\\2\\3<ul>\n"
       end_mark: "\n</ul>" 
 
   - title: bulletListClose
     match: >
-      / (?:\A(\s*)|(\n\n))
-                  ([-*+](?:[ ]+|\t)[^\n]+(:?\n[ \t]*[^\s][^\n]*)*)/xm
+      / (?:\A(\s*)|(\n)[ \t]*(\n))
+                  ([-*+][ \t]+[^\n]+(:?\n[ \t]*\S[^\n]*)*)/xm
     subparse:
       context: listClose
-      match_group: 3
+      match_group: 4
     html:
-      start_mark: "\\1\\2<ul>\n"
+      start_mark: "\\1\\2\\3<ul>\n"
       end_mark: "\n</ul>" 
 
   - title: numberedListSpaced
@@ -365,10 +398,16 @@ block:
       start_mark: "\\1\\2<ol>\n"
       end_mark: "\n</ol>" 
 
+  - title: html_self_closing
+    shelve: true
+    match: >
+      / ^[ ]{0,3}<input.*?>/x
+    html: true
+
   - title: html_block
     shelve: true
     match: >
-      / ^[ ]{0,3}<(script|table|div|pre|center|blockquote|p|ul|ol|h[1-6])(?:[^>]*)?>
+      / ^[ ]{0,3}<(select|script|table|div|pre|center|blockquote|p|ul|ol|h[1-6])(?:[^>]*)?>
         .*?
         <\/\1>/xm
     html: true
@@ -391,8 +430,10 @@ block:
       end_mark: "\n</code></pre>"
 
   - title: paragraph
-    match: '/((?:^\S.*?$)(?:\n\S[^\n]*)*)/m'
-    subparse: span
+    match: '/^[ ]{0,3}((:?\S.*?$)(?:\n[ ]*\S[^\n]*)*)/m'
+    subparse: 
+      context: span
+      match_group: 1
     html:
       start_mark: '<p>'
       end_mark: '</p>'
@@ -437,8 +478,8 @@ embeddedBlock:
 
   - title: embeddedPara
     position: first
-    match: 
-      /\A (?:(?![*+-]|[[:digit:]]))
+    match: >
+      /\A (?:(?!(?:[*+-]|[[:digit:]]\.)(:?[ ]+|\t)))
           (?:(?:\S[^\n]*)(?:\n\S[^\n]*)*)
           \n?\z/xm
     subparse: span
@@ -462,7 +503,11 @@ listSpaced:
           (?:\n[^-*+[:digit:]\n][^\n]*)*
         )*/xm
     strip:
-      match: '/^(([-*+]|[[:digit:]]\.)\s*|(?:    |\t))/'
+      match: >
+        /^(?:
+            (?:[-*+]|[[:digit:]]\.)\s*
+            |(?:[ ]{1,4}|\t)
+          )/x
       replace: ''
     subparse: block
     html:
@@ -477,18 +522,15 @@ listSpaced:
 listClose:
   - title: closeListItem
     match: >
-      /^(
-          (?:
-            (?:[-*+]|[[:digit:]+]\.)
-            (?:[ ]+|\t).*?$
-          )
-          (?:\n(?![-*+\n]|[[:digit:]]+\.)[^\n]*)*
-        )/xm
+      /^(?:[-*+]|[[:digit:]+]\.)[ \t]+(.*?$
+        (?:\n(?![-*+\n]|[[:digit:]]+\.)[^\n]*)*)
+      /xm
     strip:
       match: >
-        /^( (?:[-*+]|[[:digit:]]+\.)\s*
-            |(?:[ ]+|\t)
-          )/x
+        /^(?:(?:[-*+]|[[:digit:]]+\.)\s*
+             |(?:[ ]{1,4}|\t)
+          )
+        /x
       replace: ''
     subparse: embeddedBlock
     html:

data/lib/tartan/markdown/rules.rb

@@ -0,0 +1,11 @@
+#$Id: rules.rb 182 2007-01-28 21:32:51Z bitherder $
+
+require 'core_ext'
+
+module Tartan
+  module Markdown
+    module Rules
+      yaml 'tartan/markdown/markdown.yml'
+    end
+  end
+end

data/lib/tartan/markdown.rb

@@ -0,0 +1,14 @@
+#$Id: markdown.rb 186 2007-02-12 16:36:17Z bitherder $
+
+baseDir = File.dirname(__FILE__)
+
+require 'tartan'
+require 'tartan/markdown/rules'
+
+module Tartan
+  module Markdown
+    class Parser < Parser
+      include Rules
+    end
+  end
+end

data/lib/tartan/table/rules.rb

@@ -0,0 +1,11 @@
+require 'core_ext'
+
+# This module should be included into a Tartan subclass to add table mark-up.
+
+module Tartan
+  module Table
+    module Rules
+      yaml "tartan/table/table.yml"
+    end
+  end
+end

data/lib/{table.yml → tartan/table/table.yml}

@@ -5,7 +5,7 @@ block:
       end_mark: </table>
     after: html_comment
     match: |-
-      / (?:\[([\w]*)[|!](?:.*?)\|\])
+      /^[ ]{0,3} (?:\[([\w]*)[|!](?:.*?)\|\])
         (?:\s*)
         (?:(?:\[[|!](?:.*?)\|\])(?:\s*))*/mx
     subparse: table

data/lib/tartan/test/base_rules.rb

@@ -0,0 +1,9 @@
+require 'core_ext'
+
+module Tartan
+  module Test
+    module BaseRules
+      yaml "tartan/test/test_base.yml"
+    end
+  end
+end

data/lib/{wiki-test.rb → tartan/test/wiki-test.rb}

@@ -1,13 +1,16 @@
-#$Id: wiki-test.rb 159 2006-07-24 08:13:02Z larry $
+#$Id: wiki-test.rb 193 2007-04-18 15:27:15Z alpinegizmo $
 
 require 'test/unit'
 require 'yaml'
 require 'benchmark'
-require 'breakpoint'
 require 'core_ext/file'
 
 class WikiTestCases
-  def initialize(parserKlass, testfiles, targets=[:html, :db])
+  def self.get_input(doc, type)
+    doc['in'].gsub(/\{\{\{(.*?)\}\}\}/) {|sub| subs[$1]}
+  end
+
+  def initialize(parserKlass, testfiles, targets=[:html])
 
     # if either the testfile or target argument is a single value, turn
     # it into a single element array
@@ -21,12 +24,17 @@ class WikiTestCases
         parserKlass
       end
 
-      def assert_wiki(expected, wiki_text, options, type=:html)
+      def test_parser(doc, options, type, type_name)
+        input = WikiTestCases.get_input(doc, type)
+
+        expected \
+          = doc[type_name].gsub(/\{\{\{(.*?)\}\}\}/) {|sub| subs[$1]}
+        
         # time limit in seconds
         time_limit = options['time_limit'] ? options['time_limit'] : 1.0
 
-        parser = parserClass.new(wiki_text, options)
-
+        parser = parserClass.new(input, options)
+        
         out = nil
         wtimes = Benchmark.measure do
           out = parser.to_type(type)
@@ -70,8 +78,6 @@ class WikiTestCases
 
           next unless doc['in']
           
-          input = doc['in'].gsub(/\{\{\{(.*?)\}\}\}/) {|sub| subs[$1]}
-
           title = doc['title'] ? doc['title'] : (sequence += 1).to_s
 
           targets.each do |target| 
@@ -80,11 +86,8 @@ class WikiTestCases
 
             next unless doc[target_name]
 
-            expected \
-              = doc[target_name].gsub(/\{\{\{(.*?)\}\}\}/) {|sub| subs[$1]}
-
             define_method  "test_#{target_name}_" + title do
-              assert_wiki expected, input, options.dup, target
+              test_parser doc, options.dup, target, target_name
             end # define_method
           end # targests.each
         end # YAML::load_documents