kramdown 0.10.0 → 0.11.0

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

@@ -20,6 +20,8 @@
 #++
 #
 
+require 'kramdown/parser/kramdown/block_boundary'
+
 module Kramdown
   module Parser
     class Kramdown
@@ -28,13 +30,22 @@ module Kramdown
 
       # Parse the math block at the current location.
       def parse_block_math
-        if @src[1]
+        if !after_block_boundary?
+          return false
+        elsif @src[1]
           @src.scan(/^#{OPT_SPACE}\\/)
           return false
         end
+        orig_pos = @src.pos
         @src.pos += @src.matched_size
-        @tree.children << new_block_el(:math, @src[2], :category => :block)
-        true
+        data = @src[2]
+        if before_block_boundary?
+          @tree.children << new_block_el(:math, data)
+          true
+        else
+          @src.pos = orig_pos
+          false
+        end
       end
       define_parser(:block_math, BLOCK_MATH_START)
 
@@ -44,7 +55,7 @@ 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], :category => :span)
+        @tree.children << Element.new(:math, @src[1], nil, :category => :span)
       end
       define_parser(:inline_math, INLINE_MATH_START, '\$')
 

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

@@ -20,20 +20,31 @@
 #++
 #
 
+require 'kramdown/parser/kramdown/blank_line'
+require 'kramdown/parser/kramdown/attribute_list'
+require 'kramdown/parser/kramdown/eob'
+require 'kramdown/parser/kramdown/list'
+require 'kramdown/parser/kramdown/html'
+
 module Kramdown
   module Parser
     class Kramdown
 
+      LAZY_END_HTML_SPAN_ELEMENTS = HTML_SPAN_ELEMENTS + %w{script}
+      LAZY_END_HTML_START = /<(?>(?!(?:#{LAZY_END_HTML_SPAN_ELEMENTS.join('|')})\b)#{REXML::Parsers::BaseParser::UNAME_STR})\s*(?>\s+#{REXML::Parsers::BaseParser::UNAME_STR}\s*=\s*(["']).*?\1)*\s*\/?>/m
+      LAZY_END_HTML_STOP = /<\/(?!(?:#{LAZY_END_HTML_SPAN_ELEMENTS.join('|')})\b)#{REXML::Parsers::BaseParser::UNAME_STR}\s*>/m
+
       PARAGRAPH_START = /^#{OPT_SPACE}[^ \t].*?\n/
+      PARAGRAPH_MATCH = /(?:^.*\n)+?(?=#{BLANK_LINE}|#{IAL_BLOCK_START}|#{EOB_MARKER}|#{DEFINITION_LIST_START}|^#{OPT_SPACE}#{LAZY_END_HTML_STOP}|^#{OPT_SPACE}#{LAZY_END_HTML_START}|\Z)/
 
       # Parse the paragraph at the current location.
       def parse_paragraph
-        @src.pos += @src.matched_size
+        result = @src.scan(PARAGRAPH_MATCH)
         if @tree.children.last && @tree.children.last.type == :p
-          @tree.children.last.children.first.value << "\n" << @src.matched.chomp
+          @tree.children.last.children.first.value << "\n" << result.chomp
         else
           @tree.children << new_block_el(:p)
-          add_text(@src.matched.lstrip.chomp, @tree.children.last)
+          @tree.children.last.children << Element.new(@text_type, result.lstrip.chomp)
         end
         true
       end

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

@@ -20,25 +20,26 @@
 #++
 #
 
-require 'kramdown/parser/kramdown/blank_line'
-require 'kramdown/parser/kramdown/eob'
-require 'kramdown/parser/kramdown/horizontal_rule'
+require 'kramdown/parser/kramdown/block_boundary'
 
 module Kramdown
   module Parser
     class Kramdown
 
-      TABLE_SEP_LINE = /^#{OPT_SPACE}(?:\||\+)([ ]?:?-[+|: -]*)[ \t]*\n/
+      TABLE_SEP_LINE = /^([+|: -]*?-[+|: -]*?)[ \t]*\n/
       TABLE_HSEP_ALIGN = /[ ]?(:?)-+(:?)[ ]?/
-      TABLE_FSEP_LINE = /^#{OPT_SPACE}(\||\+)[ ]?:?=[+|: =]*[ \t]*\n/
-      TABLE_ROW_LINE = /^#{OPT_SPACE}\|(.*?)[ \t]*\n/
-      TABLE_START = /^#{OPT_SPACE}\|(?:-|(?!=))/
+      TABLE_FSEP_LINE = /^[+|: =]*?=[+|: =]*?[ \t]*\n/
+      TABLE_ROW_LINE = /^(.*?)[ \t]*\n/
+      TABLE_LINE = /(?:\||.*?[^\\\n]\|).*?\n/
+      TABLE_START = /^#{OPT_SPACE}(?=\S)#{TABLE_LINE}/
 
       # Parse the table at the current location.
       def parse_table
-        orig_pos = @src.pos
-        table = new_block_el(:table, nil, :alignment => [])
+        return false if !after_block_boundary?
 
+        orig_pos = @src.pos
+        table = new_block_el(:table, nil, nil, :alignment => [])
+        leading_pipe = (@src.check(TABLE_LINE) =~ /^\s*\|/)
         @src.scan(TABLE_SEP_LINE)
 
         rows = []
@@ -54,6 +55,7 @@ module Kramdown
         end
 
         while !@src.eos?
+          break if !@src.check(TABLE_LINE)
           if @src.scan(TABLE_SEP_LINE) && !rows.empty?
             if table.options[:alignment].empty? && !has_footer
               add_container.call(:thead, false)
@@ -79,6 +81,7 @@ module Kramdown
                 i += 1
               end
             end
+            cells.shift if leading_pipe && cells.first.strip.empty?
             cells.pop if cells.last.strip.empty?
             cells.each do |cell_text|
               tcell = Element.new(:td)
@@ -92,6 +95,11 @@ module Kramdown
           end
         end
 
+        if !before_block_boundary?
+          @src.pos = orig_pos
+          return false
+        end
+
         add_container.call(has_footer ? :tfoot : :tbody, false) if !rows.empty?
 
         if !table.children.any? {|c| c.type == :tbody}

data/lib/kramdown/utils.rb

@@ -30,6 +30,7 @@ module Kramdown
 
     autoload :Entities, 'kramdown/utils/entities'
     autoload :HTML, 'kramdown/utils/html'
+    autoload :OrderedHash, 'kramdown/utils/ordered_hash'
 
   end
 

data/lib/kramdown/utils/html.rb

@@ -42,7 +42,7 @@ module Kramdown
 
       # Return the string with the attributes of the element +el+.
       def html_attributes(el)
-        (el.options[:attr] || {}).map {|k,v| v.nil? ? '' : " #{k}=\"#{escape_html(v.to_s, :no_entities)}\"" }.sort.join('')
+        el.attr.map {|k,v| v.nil? ? '' : " #{k}=\"#{escape_html(v.to_s, :attribute)}\"" }.join('')
       end
 
       ESCAPE_MAP = {
@@ -51,19 +51,19 @@ module Kramdown
         '&' => '&',
         '"' => '"'
       }
-      ESCAPE_ALL_RE = Regexp.union(*ESCAPE_MAP.collect {|k,v| k})
-      ESCAPE_NO_ENTITIES_RE = Regexp.union(REXML::Parsers::BaseParser::REFERENCE_RE, ESCAPE_ALL_RE)
-      ESCAPE_NORMAL = Regexp.union(REXML::Parsers::BaseParser::REFERENCE_RE, /<|>|&/)
+      ESCAPE_ALL_RE = /<|>|&/
+      ESCAPE_TEXT_RE = Regexp.union(REXML::Parsers::BaseParser::REFERENCE_RE, /<|>|&/)
+      ESCAPE_ATTRIBUTE_RE = Regexp.union(REXML::Parsers::BaseParser::REFERENCE_RE, /<|>|&|"/)
       ESCAPE_RE_FROM_TYPE = {
         :all => ESCAPE_ALL_RE,
-        :no_entities => ESCAPE_NO_ENTITIES_RE,
-        :text => ESCAPE_NORMAL
+        :text => ESCAPE_TEXT_RE,
+        :attribute => ESCAPE_ATTRIBUTE_RE
       }
 
       # Escape the special HTML characters in the string +str+. The parameter +type+ specifies what
-      # is escaped: <tt>:all</tt> - all special HTML characters as well as entities,
-      # <tt>:no_entities</tt> - all special HTML characters but no entities, <tt>:text</tt> - all
-      # special HTML characters except the quotation mark but no entities.
+      # is escaped: <tt>:all</tt> - all special HTML characters as well as entities, <tt>:text</tt>
+      # - all special HTML characters except the quotation mark but no entities and
+      # <tt>:attribute</tt> - all special HTML characters including the quotation mark but no entities.
       def escape_html(str, type = :all)
         str.gsub(ESCAPE_RE_FROM_TYPE[type]) {|m| ESCAPE_MAP[m] || m}
       end

data/lib/kramdown/utils/ordered_hash.rb

@@ -0,0 +1,79 @@
+# -*- coding: utf-8 -*-
+#
+#--
+# Copyright (C) 2009-2010 Thomas Leitner <t_leitner@gmx.at>
+#
+# This file is part of kramdown.
+#
+# kramdown is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+#++
+#
+
+module Kramdown
+
+  module Utils
+
+    # A very simple class mimicking the most used methods of a Hash. The difference to a normal Hash
+    # is that a OrderedHash retains the insertion order of the keys.
+    class OrderedHash
+
+      include Enumerable
+
+      # Direct access to the hash with the key-value pairs. May not be used to modify the data!
+      attr_reader :data
+
+      # Initialize the OrderedHash object, optionally with an +hash+. If the optional +hash+ is
+      # used, there is no special order imposed on the keys (additionally set keys will be stored in
+      # insertion order). An OrderedHash object may be used instead of a hash to provide the initial
+      # data.
+      def initialize(hash = {})
+        if hash.kind_of?(OrderedHash)
+          @data, @order = hash.instance_eval { [@data.dup, @order.dup] }
+        else
+          @data = hash || {}
+          @order = @data.keys
+        end
+      end
+
+      # Iterate over the stored keys in insertion order.
+      def each
+        @order.each {|k| yield(k, @data[k])}
+      end
+
+      # Return the value for the +key+.
+      def [](key)
+        @data[key]
+      end
+
+      # Set the value for the +key+ to +val+.
+      def []=(key, val)
+        @order << key if !@data.has_key?(key)
+        @data[key] = val
+      end
+
+      # Delete the +key+.
+      def delete(key)
+        @order.delete(key)
+        @data.delete(key)
+      end
+
+      def inspect #:nodoc:
+        "{" + map {|k,v| "#{k.inspect}=>#{v.inspect}"}.join(" ") + "}"
+      end
+
+    end
+
+  end
+
+end

data/lib/kramdown/version.rb

@@ -23,6 +23,6 @@
 module Kramdown
 
   # The kramdown version.
-  VERSION = '0.10.0'
+  VERSION = '0.11.0'
 
 end

data/man/man1/kramdown.1

@@ -199,18 +199,6 @@ Default: style
 Used by: HTML converter
 
 
-.TP
-.B \-\-[no\-]numeric-entities
-
-DEPRECATED: Defines whether entities are output using names or numeric values
-
-Note that this option is deprecated and replaced by the entities option.
-This option will be removed in a future release.
-
-Default: false
-Used by: HTML converter, kramdown converter
-
-
 .TP
 .B \-\-entity-output ARG
 
@@ -237,6 +225,15 @@ Default: 0
 Used by: HTML/Latex converter
 
 
+.TP
+.B \-\-line-width ARG
+
+Defines the line width to be used when outputting a document
+
+Default: 72
+Used by: kramdown converter
+
+
 .SH EXIT STATUS
 The exit status is 0 if no error happened. Otherwise it is 1.
 .SH SEE ALSO

data/test/test_files.rb

@@ -53,7 +53,8 @@ class TestFiles < Test::Unit::TestCase
     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
+                          'test/testcases/block/09_html/simple.html', # bc of xml elements
+                          'test/testcases/span/03_codespan/highlighting.html', # bc of span elements inside code element
                          ]
     Dir[File.dirname(__FILE__) + '/testcases/**/*.html'].each do |html_file|
       next if EXCLUDE_HTML_FILES.any? {|f| html_file =~ /#{f}$/}
@@ -115,6 +116,8 @@ class TestFiles < Test::Unit::TestCase
                           'test/testcases/block/09_html/content_model/tables.text',  # bc of parse_block_html option
                           'test/testcases/block/09_html/html_to_native/header.text', # bc of auto_ids option that interferes
                           'test/testcases/block/09_html/simple.text',        # bc of webgen:block elements
+                          'test/testcases/block/11_ial/simple.text',         # bc of change of ordering of attributes in header
+                          'test/testcases/span/extension/comment.text',      # bc of comment text modifications (can this be avoided?)
                          ]
     Dir[File.dirname(__FILE__) + '/testcases/**/*.text'].each do |text_file|
       next if EXCLUDE_TEXT_FILES.any? {|f| text_file =~ /#{f}$/}
@@ -143,6 +146,8 @@ class TestFiles < Test::Unit::TestCase
                              'test/testcases/block/09_html/markdown_attr.html',   # bc of markdown attr
                              'test/testcases/block/09_html/html_to_native/table_simple.html', # bc of invalidly converted simple table
                              'test/testcases/block/06_codeblock/whitespace.html', # bc of entity to char conversion
+                             'test/testcases/block/11_ial/simple.html',           # bc of change of ordering of attributes in header
+                             'test/testcases/span/03_codespan/highlighting.html', # bc of span elements inside code element
                             ]
     Dir[File.dirname(__FILE__) + '/testcases/**/*.html'].each do |html_file|
       next if EXCLUDE_HTML_KD_FILES.any? {|f| html_file =~ /#{f}$/}

data/test/testcases/block/02_eob/middle.html

@@ -1,2 +1 @@
 
-

data/test/testcases/block/04_header/atx_header.html

@@ -10,6 +10,9 @@
 
 <h6>This is a header</h6>
 
+<h1>Header</h1>
+<h1>Header</h1>
+
 <h2>Header</h2>
 <blockquote>
   <p>blockquote</p>
@@ -19,9 +22,9 @@
 <p>paragraph</p>
 
 <blockquote>
-  <p>blockquote</p>
+  <p>blockquote
+### not a header</p>
 </blockquote>
-<p>### not a header</p>
 
 <h3 id="id">Header</h3>
 

data/test/testcases/block/04_header/atx_header.text

@@ -10,7 +10,9 @@
 
 ###### This is a header
 
-
+# Header
+^
+# Header
 
 ##Header   #####
 > blockquote

data/test/testcases/block/04_header/setext_header.html

@@ -5,9 +5,8 @@
 <h2>test</h2>
 <p>para</p>
 
-<pre><code>   header
+<pre><code>   header =
 </code></pre>
-<p>=</p>
 
 <p>=</p>
 
@@ -17,10 +16,10 @@ And not a header.
 =================</p>
 
 <blockquote>
-  <p>Blockquote.</p>
+  <p>Blockquote.
+Not a Header
+&mdash;</p>
 </blockquote>
-<p>Not a Header</p>
-<hr />
 
 <h2 id="id">header</h2>
 

data/test/testcases/block/04_header/setext_header.html.19

@@ -0,0 +1,30 @@
+<h2>test</h2>
+
+<h1>test2</h1>
+
+<h2>test</h2>
+<p>para</p>
+
+<pre><code>   header =
+</code></pre>
+
+<p>=</p>
+
+<p>This is a para.
+With two lines.
+And not a header.
+=================</p>
+
+<blockquote>
+  <p>Blockquote.
+Not a Header
+—</p>
+</blockquote>
+
+<h2 id="id">header</h2>
+
+<h1 id="id">header</h1>
+
+<h2>header{#noid}</h2>
+
+<h2>header</h2>

data/test/testcases/block/05_blockquote/lazy.html

@@ -0,0 +1,34 @@
+<blockquote>
+  <p>This is a long
+long line.</p>
+</blockquote>
+
+<blockquote>
+  <blockquote>
+    <p>Nested quote
+inside
+still inside</p>
+  </blockquote>
+</blockquote>
+
+<blockquote>
+  <blockquote>
+    <p>This is a subquote.
+over multipline lines.
+continuing
+here</p>
+  </blockquote>
+</blockquote>
+
+<blockquote>
+  <p>This is a quote
+    no code</p>
+</blockquote>
+
+<blockquote id="id">
+  <p>This is a quote</p>
+</blockquote>
+
+<blockquote>
+  <p>This is a quote</p>
+</blockquote>