kramdown 0.12.0 → 0.13.1

data/lib/kramdown/parser/kramdown.rb

@@ -84,10 +84,10 @@ module Kramdown
         @link_defs = {}
         @footnotes = {}
 
-        @block_parsers = [:blank_line, :codeblock, :codeblock_fenced, :blockquote, :table, :atx_header,
-                          :setext_header, :horizontal_rule, :list, :definition_list, :link_definition, :block_html,
-                          :footnote_definition, :abbrev_definition, :block_extensions, :block_math,
-                          :eob_marker, :paragraph]
+        @block_parsers = [:blank_line, :codeblock, :codeblock_fenced, :blockquote, :atx_header,
+                          :setext_header, :horizontal_rule, :list, :definition_list, :block_html,
+                          :table, :footnote_definition, :link_definition, :abbrev_definition,
+                          :block_extensions, :block_math, :eob_marker, :paragraph]
         @span_parsers =  [:emphasis, :codespan, :autolink, :span_html, :footnote_marker, :link, :smart_quotes, :inline_math,
                          :span_extensions, :html_entity, :typographic_syms, :line_break, :escaped_chars]
 

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

@@ -29,8 +29,13 @@ module Kramdown
       # Parse the HTML entity at the current location.
       def parse_html_entity
         @src.pos += @src.matched_size
-        @tree.children << Element.new(:entity, ::Kramdown::Utils::Entities.entity(@src[1] || (@src[2] && @src[2].to_i) || @src[3].hex),
-                                      nil, :original => @src.matched)
+        begin
+          @tree.children << Element.new(:entity, ::Kramdown::Utils::Entities.entity(@src[1] || (@src[2] && @src[2].to_i) || @src[3].hex),
+                                        nil, :original => @src.matched)
+        rescue ::Kramdown::Error
+          @tree.children << Element.new(:entity, ::Kramdown::Utils::Entities.entity('amp'))
+          add_text(@src.matched[1..-1])
+        end
       end
       define_parser(:html_entity, Kramdown::Parser::Html::Constants::HTML_ENTITY_RE, '&')
 

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

@@ -24,15 +24,17 @@ module Kramdown
   module Parser
     class Kramdown
 
-      PUNCTUATION_CHARS = "_.:,;!?-"
-      LINK_ID_CHARS = /[a-zA-Z0-9 #{PUNCTUATION_CHARS}]/
-      LINK_ID_NON_CHARS = /[^a-zA-Z0-9 #{PUNCTUATION_CHARS}]/
-      LINK_DEFINITION_START = /^#{OPT_SPACE}\[(#{LINK_ID_CHARS}+)\]:[ \t]*(?:<(.*?)>|([^'"\n]*?\S[^'"\n]*?))[ \t]*?(?:\n?[ \t]*?(["'])(.+?)\4[ \t]*?)?\n/
+      # Normalize the link identifier.
+      def normalize_link_id(id)
+        id.gsub(/(\s|\n)+/, ' ').downcase
+      end
+
+      LINK_DEFINITION_START = /^#{OPT_SPACE}\[([^\n\]]+)\]:[ \t]*(?:<(.*?)>|([^'"\n]*?\S[^'"\n]*?))[ \t]*?(?:\n?[ \t]*?(["'])(.+?)\4[ \t]*?)?\n/
 
       # Parse the link definition at the current location.
       def parse_link_definition
         @src.pos += @src.matched_size
-        link_id, link_url, link_title = @src[1].downcase, @src[2] || @src[3], @src[5]
+        link_id, link_url, link_title = normalize_link_id(@src[1]), @src[2] || @src[3], @src[5]
         warning("Duplicate link ID '#{link_id}' - overwriting") if @link_defs[link_id]
         @link_defs[link_id] = [link_url, link_title]
         @tree.children << Element.new(:eob, :link_def)
@@ -57,7 +59,7 @@ module Kramdown
 
       LINK_BRACKET_STOP_RE = /(\])|!?\[/
       LINK_PAREN_STOP_RE = /(\()|(\))|\s(?=['"])/
-      LINK_INLINE_ID_RE = /\s*?\[(#{LINK_ID_CHARS}+)?\]/
+      LINK_INLINE_ID_RE = /\s*?\[([^\]]+)?\]/
       LINK_INLINE_TITLE_RE = /\s*?(["'])(.+?)\1\s*?\)/
       LINK_START = /!?\[(?=[^^])/
 
@@ -91,7 +93,7 @@ module Kramdown
 
         # reference style link or no link url
         if @src.scan(LINK_INLINE_ID_RE) || !@src.check(/\(/)
-          link_id = (@src[1] || alt_text.gsub(/(\s|\n)+/, ' ').gsub(LINK_ID_NON_CHARS, '')).downcase
+          link_id = normalize_link_id(@src[1] || alt_text)
           if @link_defs.has_key?(link_id)
             add_link(el, @link_defs[link_id].first, @link_defs[link_id].last, alt_text)
           else

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

@@ -29,12 +29,13 @@ module Kramdown
   module Parser
     class Kramdown
 
-      LIST_ITEM_IAL = /^\s*(#{IAL_SPAN_START})?\s*\n/
+      LIST_ITEM_IAL = /^\s*(?:\{:(?!(?:#{ALD_ID_NAME})?:|\/)(#{ALD_ANY_CHARS}+)\})\s*/
+      LIST_ITEM_IAL_CHECK = /^#{LIST_ITEM_IAL}?\s*\n/
 
       # Used for parsing the first line of a list item or a definition, i.e. the line with list item
       # marker or the definition marker.
       def parse_first_list_line(indentation, content)
-        if content =~ self.class::LIST_ITEM_IAL
+        if content =~ self.class::LIST_ITEM_IAL_CHECK
           indentation = 4
         else
           while content =~ /^ *\t/
@@ -77,7 +78,7 @@ module Kramdown
             item.value, indentation, content_re, lazy_re, indent_re = parse_first_list_line(@src[1].length, @src[2])
             list.children << item
 
-            item.value.sub!(/^#{self.class::IAL_SPAN_START}\s*/) do |match|
+            item.value.sub!(self.class::LIST_ITEM_IAL) do |match|
               parse_attribute_list($1, item.options[:ial] ||= {})
               ''
             end
@@ -175,7 +176,7 @@ module Kramdown
             item.value, indentation, content_re, lazy_re, indent_re = parse_first_list_line(@src[1].length, @src[2])
             deflist.children << item
 
-            item.value.sub!(/^#{IAL_SPAN_START}\s*/) do |match|
+            item.value.sub!(self.class::LIST_ITEM_IAL) do |match|
               parse_attribute_list($1, item.options[:ial] ||= {})
               ''
             end

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

@@ -72,30 +72,35 @@ module Kramdown
           elsif @src.scan(TABLE_ROW_LINE)
             trow = Element.new(:tr)
 
-            # parse possible code spans on the line
+            # parse possible code spans on the line and correctly split the line into cells
             env = save_env
-            reset_env(:src => StringScanner.new(@src[1] + ' '))
-            root = Element.new(:root)
-            parse_spans(root, nil, [:codespan])
-            restore_env(env)
-
-            # correctly split the line into cells
             cells = []
-            root.children.each do |c|
-              if c.type == :raw_text
-                # Only on Ruby 1.9: f, *l = c.value.split(/(?<!\\)\|/).map {|t| t.gsub(/\\\|/, '|')}
-                f, *l = c.value.split(/\\\|/).map {|t| t.split(/\|/)}.inject([]) do |memo, t|
-                  memo.last << "|" << t.shift if memo.size > 0
-                  memo.concat(t)
-                end
-                (cells.empty? ? cells : cells.last) << f
-                cells.concat(l)
+            (@src[1] + ' ').split(/(<code.*?>.*?<\/code>)/).each_with_index do |str, i|
+              if i % 2 == 1
+                (cells.empty? ? cells : cells.last) << str
               else
-                delim = (c.value.scan(/`+/).max || '') + '`'
-                tmp = "#{delim}#{' ' if delim.size > 1}#{c.value}#{' ' if delim.size > 1}#{delim}"
-                (cells.empty? ? cells : cells.last) << tmp
+                reset_env(:src => StringScanner.new(str))
+                root = Element.new(:root)
+                parse_spans(root, nil, [:codespan])
+
+                root.children.each do |c|
+                  if c.type == :raw_text
+                    # Only on Ruby 1.9: f, *l = c.value.split(/(?<!\\)\|/).map {|t| t.gsub(/\\\|/, '|')}
+                    f, *l = c.value.split(/\\\|/).map {|t| t.split(/\|/)}.inject([]) do |memo, t|
+                      memo.last << "|" << t.shift if memo.size > 0
+                      memo.concat(t)
+                    end
+                    (cells.empty? ? cells : cells.last) << f
+                    cells.concat(l)
+                  else
+                    delim = (c.value.scan(/`+/).max || '') + '`'
+                    tmp = "#{delim}#{' ' if delim.size > 1}#{c.value}#{' ' if delim.size > 1}#{delim}"
+                    (cells.empty? ? cells : cells.last) << tmp
+                  end
+                end
               end
             end
+            restore_env(env)
 
             cells.shift if leading_pipe && cells.first.strip.empty?
             cells.pop if cells.last.strip.empty?

data/lib/kramdown/utils/entities.rb

@@ -310,6 +310,10 @@ module Kramdown
                       [156, 339],
                       [158, 382],
                       [159, 376],
+
+                      [8194, 'ensp'],
+                      [8195, 'emsp'],
+                      [8201, 'thinsp'],
                      ]
 
       # Contains the mapping of code point (or name) to the actual Entity object.

data/lib/kramdown/version.rb

@@ -23,6 +23,6 @@
 module Kramdown
 
   # The kramdown version.
-  VERSION = '0.12.0'
+  VERSION = '0.13.1'
 
 end

data/man/man1/kramdown.1

@@ -50,7 +50,7 @@ file still cannot be found, the templates name is interpreted as a
 template name that is provided by kramdown (without the converter
 extension).
 
-kramdown provides a default template named 'default' for each converter.
+kramdown provides a default template named 'document' for each converter.
 
 Default: ''
 Used by: all converters
@@ -214,19 +214,6 @@ Default: :as_char
 Used by: HTML converter, kramdown converter
 
 
-.TP
-.B \-\-toc-depth ARG
-
-DEPRECATED: Defines the maximum level of headers which will be used to generate the table of
-contents. For instance, with a value of 2, toc entries will be generated for h1
-and h2 headers but not for h3, h4, etc. A value of 0 uses all header levels.
-
-Use option toc_levels instead!
-
-Default: -1
-Used by: HTML/Latex converter
-
-
 .TP
 .B \-\-toc-levels ARG
 
@@ -261,6 +248,20 @@ Default: section,subsection,subsubsection,paragraph,subparagraph,subsubparagraph
 Used by: Latex converter
 
 
+.TP
+.B \-\-smart-quotes ARG
+
+Defines the HTML entity names or code points for smart quote output
+
+The entities identified by entity name or code point that should be
+used for, in order, a left single quote, a right single quote, a left
+double and a right double quote are specified by separating them with
+commas.
+
+Default: lsquo,rsquo,ldquo,rdquo
+Used by: HTML/Latex converter
+
+
 .SH EXIT STATUS
 The exit status is 0 if no error happened. Otherwise it is 1.
 .SH SEE ALSO

data/test/testcases/block/08_list/item_ial.html

@@ -4,4 +4,7 @@ continued</li>
   <li>another {:.cls}</li>
   <li class="cls">IAL at last
     code</li>
+  <li>X
+  test</li>
+  <li>X OK</li>
 </ul>

data/test/testcases/block/08_list/item_ial.text

@@ -3,3 +3,6 @@
 * another {:.cls}
 * {:.cls} IAL at last
       code
+* {::nomarkdown type="html"}X{:/nomarkdown}
+    test
+* {::nomarkdown type="html"}X{:/nomarkdown} OK

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

@@ -1,3 +1,5 @@
 <p>This is <em>sized<strong>hallo</strong></em>.</p>
 
 <p>This is <strong>strong<em>italic</em>, yes!</strong>.</p>
+
+<p>This is <em> not</em> converted, as <em>is </em> this.</p>

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

@@ -1,3 +1,6 @@
 This is <em>sized<strong>hallo</strong></em>.
 
 This is <b>strong<i>italic</i>, yes!</b>.
+
+This is <em> not</em> converted, as <em>is
+</em> this.

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

@@ -1,3 +1,5 @@
+<p>baz { |qux| quux }</p>
+
 <p>This is some para.
 <script type="javascript">
 This *text* must not be converted.

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

@@ -1,3 +1,5 @@
+<p>baz { |qux| quux }</p>
+
 This is some para.
 <script type="javascript">
 This *text* must not be converted.

data/test/testcases/block/14_table/simple.html

@@ -60,6 +60,25 @@
   </tbody>
 </table>
 
+<p>Table with code elements</p>
+
+<table>
+  <tbody>
+    <tr>
+      <td>This is a <code>span | with</code> a pipe.</td>
+      <td>&nbsp;</td>
+      <td>&nbsp;</td>
+      <td>&nbsp;</td>
+    </tr>
+    <tr>
+      <td>Some <em>span</em></td>
+      <td>&lt;/em&gt; here</td>
+      <td>a <code>span | with</code> a</td>
+      <td>pipe.</td>
+    </tr>
+  </tbody>
+</table>
+
 <table class="cls">
   <tbody>
     <tr>

data/test/testcases/block/14_table/simple.html.19

@@ -60,6 +60,25 @@
   </tbody>
 </table>
 
+<p>Table with code elements</p>
+
+<table>
+  <tbody>
+    <tr>
+      <td>This is a <code>span | with</code> a pipe.</td>
+      <td> </td>
+      <td> </td>
+      <td> </td>
+    </tr>
+    <tr>
+      <td>Some <em>span</em></td>
+      <td>&lt;/em&gt; here</td>
+      <td>a <code>span | with</code> a</td>
+      <td>pipe.</td>
+    </tr>
+  </tbody>
+</table>
+
 <table class="cls">
   <tbody>
     <tr>

data/test/testcases/block/14_table/simple.text

@@ -15,6 +15,11 @@ Escaped pipe characters
 | cell1          | cell2 \|
 | cell1 `|` con | cell2
 
+Table with code elements
+
+| This is a <code>span | with</code> a pipe.
+| Some <em>span | </em> here | a <code>span | with</code> a | pipe.
+
 {:.cls}
 | table | with | ial
 

data/test/testcases/span/01_link/reference.html

@@ -20,8 +20,7 @@ the text</a></p>
 
 <p>bad [no URL] d <a href="someurl.html">isurl</a></p>
 
-<p>[no % url]: invalid.html
-[no url] invalid.html
+<p>[no url] invalid.html
 [no url]:</p>
 
 <p>&ldquo;title&rdquo;</p>
@@ -33,3 +32,5 @@ test [urldef]</p>
 
 <p>some <a href="with spaces.html" title="title">with spaces</a></p>
 
+<p>this <a href="occasion.html">is a &lsquo;special&rsquo; occasion for /all/ of us</a></p>
+

data/test/testcases/span/01_link/reference.html.19

@@ -20,8 +20,7 @@ the text</a></p>
 
 <p>bad [no URL] d <a href="someurl.html">isurl</a></p>
 
-<p>[no % url]: invalid.html
-[no url] invalid.html
+<p>[no url] invalid.html
 [no url]:</p>
 
 <p>“title”</p>
@@ -33,3 +32,5 @@ test [urldef]</p>
 
 <p>some <a href="with spaces.html" title="title">with spaces</a></p>
 
+<p>this <a href="occasion.html">is a ‘special’ occasion for /all/ of us</a></p>
+

data/test/testcases/span/01_link/reference.text

@@ -28,7 +28,6 @@ a [Link with_BIG] letters
 
 bad [no URL] d [isurl]
 
-[no % url]: invalid.html
 [no url] invalid.html
 [no url]:
 
@@ -45,3 +44,7 @@ test [urldef]
 some [with spaces]
 
 [with spaces]: with spaces.html "title"
+
+this [is a 'special' occasion for /all/ of us]
+
+[is a 'special' occasion for /all/ of us]: occasion.html

data/test/testcases/span/05_html/normal.html

@@ -1,3 +1,5 @@
+<p>Empty <a name="anchor" id="anchor"></a>!</p>
+
 <p><a href="test">title</a> is a title.</p>
 
 <p>This is <? a PI ?>.</p>

data/test/testcases/span/05_html/normal.text

@@ -1,3 +1,5 @@
+Empty <a name="anchor" id="anchor"></a>!
+
 <a href="test">title</a> is a title.
 
 This is <? a PI ?>.

data/test/testcases/span/text_substitutions/entities.html

@@ -2,3 +2,5 @@
 As well \& as this. Some ŗ other
 values may ¯ may also show but
 not st. like &amp;#xYZ;.</p>
+
+<p>This is BS&amp;T; done!</p>

data/test/testcases/span/text_substitutions/entities.text

@@ -2,3 +2,5 @@ This is the A&O. © 2008 by me
 As well \& as this. Some ŗ other
 values may ¯ may also show but
 not st. like &#xYZ;.
+
+This is BS&T; done!

metadata

@@ -4,9 +4,9 @@ version: !ruby/object:Gem::Version
   prerelease: false
   segments: 
   - 0
-  - 12
-  - 0
-  version: 0.12.0
+  - 13
+  - 1
+  version: 0.13.1
 platform: ruby
 authors: 
 - Thomas Leitner
@@ -14,7 +14,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-11-01 00:00:00 +01:00
+date: 2011-01-22 00:00:00 +01:00
 default_executable: kramdown
 dependencies: []