kramdown 0.7.0 → 0.8.0

data/lib/kramdown/parser/kramdown/html_entity.rb

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 #
 #--
-# Copyright (C) 2009 Thomas Leitner <t_leitner@gmx.at>
+# Copyright (C) 2009-2010 Thomas Leitner <t_leitner@gmx.at>
 #
 # This file is part of kramdown.
 #
@@ -20,18 +20,18 @@
 #++
 #
 
+require 'kramdown/parser/html'
+
 module Kramdown
   module Parser
     class Kramdown
 
-      HTML_ENTITY_RE = /&([\w:][\-\w\d\.:]*);|&#(\d+);|&\#x([0-9a-fA-F]+);/
-
       # Parse the HTML entity at the current location.
       def parse_html_entity
         @src.pos += @src.matched_size
         @tree.children << Element.new(:entity, @src[1] || (@src[2] && @src[2].to_i) || @src[3].hex)
       end
-      define_parser(:html_entity, HTML_ENTITY_RE, '&')
+      define_parser(:html_entity, Kramdown::Parser::Html::Constants::HTML_ENTITY_RE, '&')
 
     end
   end

data/lib/kramdown/parser/kramdown/line_break.rb

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 #
 #--
-# Copyright (C) 2009 Thomas Leitner <t_leitner@gmx.at>
+# Copyright (C) 2009-2010 Thomas Leitner <t_leitner@gmx.at>
 #
 # This file is part of kramdown.
 #

data/lib/kramdown/parser/kramdown/link.rb

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 #
 #--
-# Copyright (C) 2009 Thomas Leitner <t_leitner@gmx.at>
+# Copyright (C) 2009-2010 Thomas Leitner <t_leitner@gmx.at>
 #
 # This file is part of kramdown.
 #
@@ -91,7 +91,7 @@ module Kramdown
           add_text(result)
           return
         end
-        alt_text = extract_string(reset_pos...@src.pos)
+        alt_text = extract_string(reset_pos...@src.pos, @src)
         conv_link_id = alt_text.gsub(/(\s|\n)+/m, ' ').gsub(LINK_ID_NON_CHARS, '').downcase
         @src.scan(stop_re)
 

data/lib/kramdown/parser/kramdown/list.rb

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 #
 #--
-# Copyright (C) 2009 Thomas Leitner <t_leitner@gmx.at>
+# Copyright (C) 2009-2010 Thomas Leitner <t_leitner@gmx.at>
 #
 # This file is part of kramdown.
 #
@@ -123,8 +123,6 @@ module Kramdown
             text = it.children.shift.children.first
             text.value += "\n" if !it.children.empty? && it.children[0].type != :blank
             it.children.unshift(text)
-          else
-            it.options[:first_is_block] = true
           end
 
           if it.children.last.type == :blank
@@ -160,7 +158,7 @@ module Kramdown
         end
         para.children.first.value.split("\n").each do |term|
           el = Element.new(:dt)
-          el.children << Element.new(:text, term)
+          el.children << Element.new(:raw_text, term)
           deflist.children << el
         end
 
@@ -207,8 +205,6 @@ module Kramdown
             text = it.children.shift.children.first
             text.value += "\n" if !it.children.empty?
             it.children.unshift(text)
-          else
-            it.options[:first_is_block] = true
           end
         end
 

data/lib/kramdown/parser/kramdown/math.rb

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 #
 #--
-# Copyright (C) 2009 Thomas Leitner <t_leitner@gmx.at>
+# Copyright (C) 2009-2010 Thomas Leitner <t_leitner@gmx.at>
 #
 # This file is part of kramdown.
 #
@@ -33,7 +33,7 @@ module Kramdown
           return false
         end
         @src.pos += @src.matched_size
-        @tree.children << new_block_el(:math, @src[2], :type => :block)
+        @tree.children << new_block_el(:math, @src[2], :category => :block)
         true
       end
       define_parser(:block_math, BLOCK_MATH_START)
@@ -44,7 +44,7 @@ module Kramdown
       # Parse the inline math at the current location.
       def parse_inline_math
         @src.pos += @src.matched_size
-        @tree.children << Element.new(:math, @src[1], :type => :inline)
+        @tree.children << Element.new(:math, @src[1], :category => :inline)
       end
       define_parser(:inline_math, INLINE_MATH_START, '\$')
 

data/lib/kramdown/parser/kramdown/paragraph.rb

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 #
 #--
-# Copyright (C) 2009 Thomas Leitner <t_leitner@gmx.at>
+# Copyright (C) 2009-2010 Thomas Leitner <t_leitner@gmx.at>
 #
 # This file is part of kramdown.
 #

data/lib/kramdown/parser/kramdown/smart_quotes.rb

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 #
 #--
-# Copyright (C) 2009 Thomas Leitner <t_leitner@gmx.at>
+# Copyright (C) 2009-2010 Thomas Leitner <t_leitner@gmx.at>
 #
 # This file is part of kramdown.
 #
@@ -17,8 +17,9 @@
 #
 # You should have received a copy of the GNU General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
+#++
 #
-#
+#--
 # Parts of this file are based on code from Maruku by Andrea Censi.
 # The needed license statements follow:
 #

data/lib/kramdown/parser/kramdown/table.rb

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 #
 #--
-# Copyright (C) 2010 Thomas Leitner <t_leitner@gmx.at>
+# Copyright (C) 2009-2010 Thomas Leitner <t_leitner@gmx.at>
 #
 # This file is part of kramdown.
 #
@@ -82,7 +82,7 @@ module Kramdown
             cells.pop if cells.last.strip.empty?
             cells.each do |cell_text|
               tcell = Element.new(:td)
-              tcell.children << Element.new(:text, cell_text.strip)
+              tcell.children << Element.new(:raw_text, cell_text.strip)
               trow.children << tcell
             end
             columns = [columns, cells.length].max
@@ -106,6 +106,7 @@ module Kramdown
             (columns - row.children.length).times do
               row.children << Element.new(:td)
             end
+            row.children.each {|el| el.type = :th} if kind.type == :thead
           end
         end
         if table.options[:alignment].length > columns

data/lib/kramdown/parser/kramdown/typographic_symbol.rb

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 #
 #--
-# Copyright (C) 2009 Thomas Leitner <t_leitner@gmx.at>
+# Copyright (C) 2009-2010 Thomas Leitner <t_leitner@gmx.at>
 #
 # This file is part of kramdown.
 #
@@ -24,7 +24,7 @@ module Kramdown
   module Parser
     class Kramdown
 
-      TYPOGRAPHIC_SYMS = [['---', :mdash], ['--', :ndash], ['...', :ellipsis],
+      TYPOGRAPHIC_SYMS = [['---', :mdash], ['--', :ndash], ['...', :hellip],
                           ['\\<<', '&lt;&lt;'], ['\\>>', '&gt;&gt;'],
                           ['<< ', :laquo_space], [' >>', :raquo_space],
                           ['<<', :laquo], ['>>', :raquo]]
@@ -37,8 +37,12 @@ module Kramdown
         val = TYPOGRAPHIC_SYMS_SUBST[@src.matched]
         if val.kind_of?(Symbol)
           @tree.children << Element.new(:typographic_sym, val)
+        elsif @src.matched == '\\<<'
+          @tree.children << Element.new(:entity, 'lt')
+          @tree.children << Element.new(:entity, 'lt')
         else
-          add_text(val.dup)
+          @tree.children << Element.new(:entity, 'gt')
+          @tree.children << Element.new(:entity, 'gt')
         end
       end
       define_parser(:typographic_syms, TYPOGRAPHIC_SYMS_RE, '--|\\.\\.\\.|(?:\\\\| )?(?:<<|>>)')

data/lib/kramdown/version.rb

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 #
 #--
-# Copyright (C) 2009 Thomas Leitner <t_leitner@gmx.at>
+# Copyright (C) 2009-2010 Thomas Leitner <t_leitner@gmx.at>
 #
 # This file is part of kramdown.
 #
@@ -23,6 +23,6 @@
 module Kramdown
 
   # The kramdown version.
-  VERSION = '0.7.0'
+  VERSION = '0.8.0'
 
 end

data/man/man1/kramdown.1

@@ -104,6 +104,23 @@ Default: true
 Used by: kramdown parser
 
 
+.TP
+.B \-\-[no\-]html_to_native
+
+Convert HTML elements to native elements
+
+If this option is `true`, the parser converts HTML elements to native
+elements. For example, when parsing `<em>hallo</em>` the emphasis tag
+would normally be converted to an `:html` element with tag type `:em`.
+If `html_to_native` is `true`, then the emphasis would be converted to a
+native `:em` element.
+
+This is useful for converters that cannot deal with HTML elements.
+
+Default: false
+Used by: kramdown parser
+
+
 .TP
 .B \-\-footnote_nr ARG
 
@@ -119,6 +136,8 @@ Used by: HTML converter
 .TP
 .B \-\-filter_html ARG
 
+NOTE: This option is deprecated and will be removed in a future release!
+
 An array of HTML tags that should be filtered from the output
 
 The value can either be specified as array or as a space separated

data/test/run_tests.rb

@@ -44,6 +44,7 @@ Dir[arg].each {|f| fwidth = [fwidth, f.length + 10].max }.each do |file|
 
   html_file = file.sub('.text', '.html')
   opts_file = file.sub('.text', '.options')
+  opts_file = File.join(File.dirname(file), 'options') if !File.exist?(opts_file)
   options = File.exist?(opts_file) ? YAML::load(File.read(opts_file)) : {:auto_ids => false, :filter_html => [], :footnote_nr => 1}
   doc = Kramdown::Document.new(File.read(file), options)
   begin

data/test/test_files.rb

@@ -23,16 +23,77 @@
 require 'test/unit'
 require 'kramdown'
 require 'yaml'
+require 'tmpdir'
 
 class TestFiles < Test::Unit::TestCase
 
-  Dir[File.dirname(__FILE__) + '/testcases/**/*.text'].each do |file|
-    define_method('test_' + file.tr('.', '_')) do
-      html_file = file.sub('.text', '.html')
-      opts_file = file.sub('.text', '.options')
-      options = File.exist?(opts_file) ? YAML::load(File.read(opts_file)) : {:auto_ids => false, :filter_html => [], :footnote_nr => 1}
-      doc = Kramdown::Document.new(File.read(file), options)
-      assert_equal(File.read(html_file), doc.to_html, "Failed test #{file}")
+  # Generate test methods for kramdown-to-xxx conversion
+  Dir[File.dirname(__FILE__) + '/testcases/**/*.text'].each do |text_file|
+    basename = text_file.sub(/\.text$/, '')
+    opts_file = text_file.sub(/\.text$/, '.options')
+    (Dir[basename + ".*"] - [text_file, opts_file]).each do |output_file|
+      output_format = File.extname(output_file)[1..-1]
+      next if !Kramdown::Converter.const_defined?(output_format[0..0].upcase + output_format[1..-1])
+      define_method('test_' + text_file.tr('.', '_') + "_to_#{output_format}") do
+        opts_file = File.join(File.dirname(text_file), 'options') if !File.exist?(opts_file)
+        options = File.exist?(opts_file) ? YAML::load(File.read(opts_file)) : {:auto_ids => false, :filter_html => [], :footnote_nr => 1}
+        doc = Kramdown::Document.new(File.read(text_file), options)
+        assert_equal(File.read(output_file), doc.send("to_#{output_format}"))
+      end
+    end
+  end
+
+  # Generate test methods for html-to-html conversion
+  `tidy -v 2>&1`
+  if $?.exitstatus != 0
+    warn("Skipping html-to-html tests because tidy executable is missing")
+  else
+    EXCLUDE_HTML_FILES = ['test/testcases/block/06_codeblock/whitespace.html', # bc of span inside pre
+                          'test/testcases/block/09_html/simple.html' # bc of xml elements
+                         ]
+    Dir[File.dirname(__FILE__) + '/testcases/**/*.html'].each do |html_file|
+      next if EXCLUDE_HTML_FILES.any? {|f| html_file =~ /#{f}$/}
+      define_method('test_' + html_file.tr('.', '_') + "_to_html") do
+        doc = Kramdown::Document.new(File.read(html_file), :input => 'html', :auto_ids => false, :footnote_nr => 1)
+        assert_equal(tidy_output(File.read(html_file)), tidy_output(doc.to_html))
+      end
+    end
+  end
+
+  def tidy_output(out)
+    result = IO.popen("tidy -q -raw 2>/dev/null", 'r+') do |io|
+      io.write(out)
+      io.close_write
+      io.read
+    end
+    if $?.exitstatus == 2
+      raise "Problem using tidy"
+    end
+    result
+  end
+
+  # Generate test methods for text-to-latex conversion and compilation
+  `latex -v 2>&1`
+  if $?.exitstatus != 0
+    warn("Skipping latex compilation tests because latex executable is missing")
+  else
+    EXCLUDE_LATEX_FILES = ['test/testcases/span/01_link/image_in_a.text', # bc of image link
+                           'test/testcases/span/01_link/imagelinks.text', # bc of image links
+                           'test/testcases/span/04_footnote/markers.text', # bc of footnote in header
+                          ]
+    Dir[File.dirname(__FILE__) + '/testcases/**/*.text'].each do |text_file|
+      next if EXCLUDE_LATEX_FILES.any? {|f| text_file =~ /#{f}$/}
+      define_method('test_' + text_file.tr('.', '_') + "_to_latex_compilation") do
+        latex =  Kramdown::Document.new(File.read(text_file),
+                                                          :auto_ids => false, :footnote_nr => 1,
+                                                          :template => 'document').to_latex
+        result = IO.popen("latex -output-directory='#{Dir.tmpdir}' 2>/dev/null", 'r+') do |io|
+          io.write(latex)
+          io.close_write
+          io.read
+        end
+        assert($?.exitstatus == 0, result.scan(/^!(.*\n.*)/).join("\n"))
+      end
     end
   end
 

data/test/testcases/block/09_html/comment.html

@@ -11,3 +11,8 @@ Blah
 Blah
 -->
 <p>para</p>
+
+<blockquote>
+  <p>This is</p>
+  <!-- a comment -->
+</blockquote>

data/test/testcases/block/09_html/comment.text

@@ -10,3 +10,6 @@ para2
 Blah
 Blah
 --> para
+
+> This is
+> <!-- a comment -->

data/test/testcases/block/09_html/content_model/tables.html

@@ -2,8 +2,8 @@
   <tr>
     <th><em>Usage</em></th>
     <th>
-      <p>Output</p>
-    </th>
+Output
+  </th>
   </tr>
   <tr>
     <td>Some <em>data</em></td>

data/test/testcases/block/09_html/html_to_native/code.html

@@ -0,0 +1,10 @@
+<p>This is a <code>code span with &lt;entities&gt; that should be preserved</code>.
+This is a <code>simple code</code> span.</p>
+
+<p>Some <code>&lt;</code></p>
+
+<pre><code>Some very important &lt; thing
+</code></pre>
+
+<pre><code>Some code&sdot;&sdot;
+</code></pre>

data/test/testcases/block/09_html/html_to_native/code.text

@@ -0,0 +1,9 @@
+This is a <code>code span <b>with</b> &lt;entities&gt; that should be preserved</code>.
+This is a <code>simple code</code> span.
+
+<p>Some <code>&lt;</code></p>
+
+<pre>Some very important <b>&lt;</b> thing</pre>
+
+<pre><code>Some code<span>&sdot;</span>&sdot;
+</code></pre>

data/test/testcases/block/09_html/html_to_native/comment.html

@@ -0,0 +1,7 @@
+<div>
+  <!--comment-->
+  <!--
+Blah
+Blah
+-->
+</div>

data/test/testcases/block/09_html/html_to_native/comment.text

@@ -0,0 +1,8 @@
+<div>
+  <!--comment-->
+
+  <!--
+Blah
+Blah
+-->
+</div>

data/test/testcases/block/09_html/html_to_native/emphasis.html

@@ -0,0 +1 @@
+<p>This is <em>sized<strong>hallo</strong></em>.</p>

data/test/testcases/block/09_html/html_to_native/emphasis.text

@@ -0,0 +1 @@
+This is <em>sized<strong>hallo</strong></em>.

data/test/testcases/block/09_html/html_to_native/entity.html

@@ -0,0 +1 @@
+<p>This is *raw* HTML text containing &lt; entities!</p>

data/test/testcases/block/09_html/html_to_native/entity.text

@@ -0,0 +1 @@
+<p>This is *raw* HTML text containing &lt; entities!</p>

data/test/testcases/block/09_html/html_to_native/header.html

@@ -0,0 +1,6 @@
+<h1 id="some-headerhere">Some <em class="cls">header</em>here!</h1>
+<h2 id="test">hallo</h2>
+<h3 id="hallo">hallo</h3>
+<h4 id="hallo-1">hallo</h4>
+<h5 id="hallo-2">hallo</h5>
+<h6 id="hallo-3">hallo</h6>

data/test/testcases/block/09_html/html_to_native/header.options

@@ -0,0 +1,2 @@
+:auto_ids: true
+:html_to_native: true