kramdown 1.2.0 → 1.3.0

data/lib/kramdown/document.rb

@@ -19,7 +19,7 @@
 # * output formats: HTML, kramdown, LaTeX (and therefore PDF)
 #
 # All the documentation on the available input and output formats is available at
-# http://kramdown.rubyforge.org.
+# http://kramdown.gettalong.org.
 #
 # == Usage
 #

data/lib/kramdown/element.rb

@@ -16,6 +16,9 @@ module Kramdown
   #
   # Following is a description of all supported element types.
   #
+  # Note that the option :location may contain the start line number of an element in the source
+  # document.
+  #
   # == Structural Elements
   #
   # === :root
@@ -459,6 +462,7 @@ module Kramdown
   #
   # The option :type can be set to an array of strings to define for which converters the raw string
   # is valid.
+  #
   class Element
 
     # A symbol representing the element type. For example, :p or :blockquote.

data/lib/kramdown/options.rb

@@ -79,8 +79,7 @@ module Kramdown
       temp = defaults
       hash.each do |k,v|
         k = k.to_sym
-        next unless @options.has_key?(k)
-        temp[k] = parse(k, v)
+        @options.has_key?(k) ? temp[k] = parse(k, v) : temp[k] = v
       end
       temp
     end
@@ -147,6 +146,7 @@ module Kramdown
 
     define(:template, String, '', <<EOF)
 The name of an ERB template file that should be used to wrap the output
+or the ERB template itself.
 
 This is used to wrap the output in an environment so that the output can
 be used as a stand-alone document. For example, an HTML template would
@@ -155,10 +155,13 @@ valid HTML file. If no template is specified, the output will be just
 the converted text.
 
 When resolving the template file, the given template name is used first.
-If such a file is not found, the converter extension is appended. If the
-file still cannot be found, the templates name is interpreted as a
-template name that is provided by kramdown (without the converter
-extension).
+If such a file is not found, the converter extension (the same as the
+converter name) is appended. If the file still cannot be found, the
+templates name is interpreted as a template name that is provided by
+kramdown (without the converter extension). If the file is still not
+found, the template name is checked if it starts with 'string://' and if
+it does, this prefix is removed and the rest is used as template
+content.
 
 kramdown provides a default template named 'document' for each converter.
 
@@ -174,10 +177,24 @@ generated if no ID is explicitly specified.
 
 Default: true
 Used by: HTML/Latex converter
+EOF
+
+    define(:auto_id_stripping, Boolean, false, <<EOF)
+Strip all formatting from header text for automatic ID generation
+
+If this option is `true`, only the text elements of a header are used
+for generating the ID later (in contrast to just using the raw header
+text line).
+
+This option will be removed in version 2.0 because this will be the
+default then.
+
+Default: false
+Used by: kramdown parser
 EOF
 
     define(:auto_id_prefix, String, '', <<EOF)
-Prefix used for automatically generated heaer IDs
+Prefix used for automatically generated header IDs
 
 This option can be used to set a prefix for the automatically generated
 header IDs so that there is no conflict when rendering multiple kramdown
@@ -321,12 +338,21 @@ The tab width used in highlighted code
 Used by: HTML converter
 EOF
 
-    define(:coderay_bold_every, Integer, 10, <<EOF)
+    define(:coderay_bold_every, Object, 10, <<EOF) do |val|
 Defines how often a line number should be made bold
 
+Can either be an integer or false (to turn off bold line numbers
+completely).
+
 Default: 10
 Used by: HTML converter
 EOF
+      if val == false || val.to_s == 'false'
+        false
+      else
+        Integer(val.to_s) rescue raise Kramdown::Error, "Invalid value for option 'coderay_bold_every'"
+      end
+end
 
     define(:coderay_css, Symbol, :style, <<EOF)
 Defines how the highlighted code gets styled
@@ -456,6 +482,16 @@ level 1 will be used. If c+n is greater than 6, level 6 will be used.
 
 Default: 0
 Used by: HTML converter, Kramdown converter, Latex converter
+EOF
+
+    define(:hard_wrap, Boolean, true, <<EOF)
+Interprets line breaks literally
+
+Insert HTML `<br />` tags inside paragraphs where the original Markdown
+document had newlines (by default, Markdown ignores these newlines).
+
+Default: true
+Used by: GFM parser
 EOF
 
   end

data/lib/kramdown/parser/base.rb

@@ -7,6 +7,8 @@
 #++
 #
 
+require 'kramdown/utils/string_scanner'
+
 module Kramdown
 
   module Parser
@@ -14,7 +16,7 @@ module Kramdown
     # == \Base class for parsers
     #
     # This class serves as base class for parsers. It provides common methods that can/should be
-    # used by all parsers, especially by those using StringScanner for parsing.
+    # used by all parsers, especially by those using StringScanner(Kramdown) for parsing.
     #
     # A parser object is used as a throw-away object, i.e. it is only used for storing the needed
     # state information during parsing. Therefore one can't instantiate a parser object directly but
@@ -49,7 +51,7 @@ module Kramdown
       def initialize(source, options)
         @source = source
         @options = Kramdown::Options.merge(options)
-        @root = Element.new(:root, nil, nil, :encoding => (source.encoding rescue nil))
+        @root = Element.new(:root, nil, nil, :encoding => (source.encoding rescue nil), :location => 1)
         @warnings = []
         @text_type = :text
       end

data/lib/kramdown/parser/gfm.rb

@@ -8,33 +8,40 @@ module Kramdown
 
       def initialize(source, options)
         super
+        @span_parsers.delete(:line_break)
         i = @block_parsers.index(:codeblock_fenced)
         @block_parsers.delete(:codeblock_fenced)
         @block_parsers.insert(i, :codeblock_fenced_gfm)
       end
 
+      def parse
+        super
+        add_hard_line_breaks(@root) if @options[:hard_wrap]
+      end
+
+      def add_hard_line_breaks(element)
+        element.children.map! do |child|
+          if child.type == :text && child.value =~ /\n/
+            children = []
+            lines = child.value.split(/\n(?=.)/)
+            lines.each_with_index do |line, index|
+              children << Element.new(:text, (index > 0 ? "\n#{line}" : line))
+              children << Element.new(:br) if index < lines.size - 1
+            end
+            children
+          elsif child.type == :html_element
+            child
+          else
+            add_hard_line_breaks(child)
+            child
+          end
+        end.flatten!
+      end
+
       FENCED_CODEBLOCK_MATCH = /^(([~`]){3,})\s*?(\w+)?\s*?\n(.*?)^\1\2*\s*?\n/m
 
       define_parser(:codeblock_fenced_gfm, /^[~`]{3,}/, nil, 'parse_codeblock_fenced')
 
-      def parse_paragraph
-        result = @src.scan(PARAGRAPH_MATCH)
-        while !@src.match?(self.class::PARAGRAPH_END)
-          result << @src.scan(PARAGRAPH_MATCH)
-        end
-        result.chomp!
-        unless @tree.children.last && @tree.children.last.type == :p
-          @tree.children << new_block_el(:p)
-        end
-        lines = result.lstrip.split(/\n/)
-        lines.each_with_index do |line, index|
-          @tree.children.last.children << Element.new(@text_type, line) << Element.new(:br) << Element.new(@text_type, "\n")
-        end
-        @tree.children.last.children.pop # added one \n too many
-        @tree.children.last.children.pop # added one :br too many
-        true
-      end
-
     end
   end
 end

data/lib/kramdown/parser/html.rb

@@ -243,7 +243,7 @@ module Kramdown
         # entities in entity elements.
         def process_text(raw, preserve = false)
           raw.gsub!(/\s+/, ' ') unless preserve
-          src = StringScanner.new(raw)
+          src = Kramdown::Utils::StringScanner.new(raw)
           result = []
           while !src.eos?
             if tmp = src.scan_until(/(?=#{HTML_ENTITY_RE})/)
@@ -533,7 +533,7 @@ module Kramdown
       # Parse the source string provided on initialization as HTML document.
       def parse
         @stack, @tree = [], @root
-        @src = StringScanner.new(adapt_source(source))
+        @src = Kramdown::Utils::StringScanner.new(adapt_source(source))
 
         while true
           if result = @src.scan(/\s*#{HTML_INSTRUCTION_RE}/)

data/lib/kramdown/parser/kramdown.rb

@@ -118,7 +118,8 @@ module Kramdown
       # Parse all block-level elements in +text+ into the element +el+.
       def parse_blocks(el, text = nil)
         @stack.push([@tree, @src, @block_ial])
-        @tree, @src, @block_ial = el, (text.nil? ? @src : StringScanner.new(text)), nil
+        @tree, @block_ial = el, nil
+        @src = (text.nil? ? @src : ::Kramdown::Utils::StringScanner.new(text, el.options[:location]))
 
         status = catch(:stop_block_parsing) do
           while !@src.eos?
@@ -148,7 +149,8 @@ module Kramdown
         element.children.map! do |child|
           if child.type == :raw_text
             last_blank = nil
-            reset_env(:src => StringScanner.new(child.value), :text_type => :text)
+            reset_env(:src => ::Kramdown::Utils::StringScanner.new(child.value, element.options[:location]),
+                      :text_type => :text)
             parse_spans(child)
             child.children
           elsif child.type == :eob
@@ -165,6 +167,7 @@ module Kramdown
             last_blank = nil
             update_tree(child)
             update_attr_with_ial(child.attr, child.options[:ial]) if child.options[:ial]
+            update_raw_header_text(child) if child.type == :header
             child
           end
         end.flatten!
@@ -253,6 +256,25 @@ module Kramdown
         end
       end
 
+      # Update the raw header text for automatic ID generation.
+      def update_raw_header_text(header)
+        # DEPRECATED: option auto_id_stripping will be removed in 2.0 because then this will be the
+        # default behaviour
+        return unless @options[:auto_id_stripping]
+        raw_text = ''
+
+        append_text = lambda do |child|
+          if child.type == :text
+            raw_text << child.value
+          else
+            child.children.each {|c| append_text.call(c)}
+          end
+        end
+
+        append_text.call(header)
+        header.options[:raw_text] = raw_text
+      end
+
       # Create a new block-level element, taking care of applying a preceding block IAL if it
       # exists. This method should always be used for creating a block-level element!
       def new_block_el(*args)

data/lib/kramdown/parser/kramdown/abbreviation.rb

@@ -15,10 +15,11 @@ module Kramdown
 
       # Parse the link definition at the current location.
       def parse_abbrev_definition
+        start_line_number = @src.current_line_number
         @src.pos += @src.matched_size
         abbrev_id, abbrev_text = @src[1], @src[2]
         abbrev_text.strip!
-        warning("Duplicate abbreviation ID '#{abbrev_id}' - overwriting") if @root.options[:abbrev_defs][abbrev_id]
+        warning("Duplicate abbreviation ID '#{abbrev_id}' on line #{start_line_number} - overwriting") if @root.options[:abbrev_defs][abbrev_id]
         @root.options[:abbrev_defs][abbrev_id] = abbrev_text
         @tree.children << Element.new(:eob, :abbrev_def)
         true
@@ -37,7 +38,7 @@ module Kramdown
           if child.type == :text
             if child.value =~ regexps.first
               result = []
-              strscan = StringScanner.new(child.value)
+              strscan = Kramdown::Utils::StringScanner.new(child.value)
               while temp = strscan.scan_until(regexps.last)
                 abbr = strscan.scan(regexps.first) # begin of line case of abbr with \W char as first one
                 if abbr.nil?

data/lib/kramdown/parser/kramdown/autolink.rb

@@ -23,9 +23,10 @@ module Kramdown
 
       # Parse the autolink at the current location.
       def parse_autolink
+        start_line_number = @src.current_line_number
         @src.pos += @src.matched_size
         href = (@src[2].nil? ? "mailto:#{@src[1]}" : @src[1])
-        el = Element.new(:a, nil, {'href' => href})
+        el = Element.new(:a, nil, {'href' => href}, :location => start_line_number)
         add_text(@src[1].sub(/^mailto:/, ''), el)
         @tree.children << el
       end

data/lib/kramdown/parser/kramdown/blockquote.rb

@@ -19,13 +19,14 @@ module Kramdown
 
       # Parse the blockquote at the current location.
       def parse_blockquote
+        start_line_number = @src.current_line_number
         result = @src.scan(PARAGRAPH_MATCH)
         while !@src.match?(self.class::LAZY_END)
           result << @src.scan(PARAGRAPH_MATCH)
         end
         result.gsub!(BLOCKQUOTE_START, '')
 
-        el = new_block_el(:blockquote)
+        el = new_block_el(:blockquote, nil, nil, :location => start_line_number)
         @tree.children << el
         parse_blocks(el, result)
         true

data/lib/kramdown/parser/kramdown/codeblock.rb

@@ -21,10 +21,11 @@ module Kramdown
 
       # Parse the indented codeblock at the current location.
       def parse_codeblock
+        start_line_number = @src.current_line_number
         data = @src.scan(self.class::CODEBLOCK_MATCH)
         data.gsub!(/\n( {0,3}\S)/, ' \\1')
         data.gsub!(INDENT, '')
-        @tree.children << new_block_el(:codeblock, data)
+        @tree.children << new_block_el(:codeblock, data, nil, :location => start_line_number)
         true
       end
       define_parser(:codeblock, CODEBLOCK_START)
@@ -36,8 +37,9 @@ module Kramdown
       # Parse the fenced codeblock at the current location.
       def parse_codeblock_fenced
         if @src.check(self.class::FENCED_CODEBLOCK_MATCH)
+          start_line_number = @src.current_line_number
           @src.pos += @src.matched_size
-          el = new_block_el(:codeblock, @src[4])
+          el = new_block_el(:codeblock, @src[4], nil, :location => start_line_number)
           lang = @src[3].to_s.strip
           el.attr['class'] = "language-#{lang}" unless lang.empty?
           @tree.children << el

data/lib/kramdown/parser/kramdown/codespan.rb

@@ -15,6 +15,7 @@ module Kramdown
 
       # Parse the codespan at the current scanner location.
       def parse_codespan
+        start_line_number = @src.current_line_number
         result = @src.scan(CODESPAN_DELIMITER)
         simple = (result.length == 1)
         reset_pos = @src.pos
@@ -30,7 +31,7 @@ module Kramdown
             text = text[1..-1] if text[0..0] == ' '
             text = text[0..-2] if text[-1..-1] == ' '
           end
-          @tree.children << Element.new(:codespan, text)
+          @tree.children << Element.new(:codespan, text, nil, :location => start_line_number)
         else
           @src.pos = reset_pos
           add_text(result)

data/lib/kramdown/parser/kramdown/emphasis.rb

@@ -15,6 +15,7 @@ module Kramdown
 
       # Parse the emphasis at the current location.
       def parse_emphasis
+        start_line_number = @src.current_line_number
         result = @src.scan(EMPHASIS_START)
         element = (result.length == 2 ? :strong : :em)
         type = result[0..0]
@@ -27,7 +28,7 @@ module Kramdown
         end
 
         sub_parse = lambda do |delim, elem|
-          el = Element.new(elem)
+          el = Element.new(elem, nil, nil, :location => start_line_number)
           stop_re = /#{Regexp.escape(delim)}/
           found = parse_spans(el, stop_re) do
             (@src.pre_match[-1, 1] !~ /\s/) &&

data/lib/kramdown/parser/kramdown/extensions.rb

@@ -16,7 +16,7 @@ module Kramdown
       # Parse the string +str+ and extract all attributes and add all found attributes to the hash
       # +opts+.
       def parse_attribute_list(str, opts)
-        return if str.strip.empty?
+        return if str.strip.empty? || str.strip == ':'
         attrs = str.scan(ALD_TYPE_ANY)
         attrs.each do |key, sep, val, ref, id_and_or_class, _, _|
           if ref
@@ -55,6 +55,7 @@ module Kramdown
       # or :span depending whether we parse a block or span extension tag.
       def parse_extension_start_tag(type)
         orig_pos = @src.pos
+        start_line_number = @src.current_line_number
         @src.pos += @src.matched_size
 
         error_block = lambda do |msg|
@@ -66,7 +67,7 @@ module Kramdown
 
         if @src[4] || @src.matched == '{:/}'
           name = (@src[4] ? "for '#{@src[4]}' " : '')
-          return error_block.call("Invalid extension stop tag #{name}found - ignoring it")
+          return error_block.call("Invalid extension stop tag #{name} found on line #{start_line_number} - ignoring it")
         end
 
         ext = @src[1]
@@ -80,12 +81,12 @@ module Kramdown
             body = result.sub!(stop_re, '')
             body.chomp! if type == :block
           else
-            return error_block.call("No stop tag for extension '#{ext}' found - ignoring it")
+            return error_block.call("No stop tag for extension '#{ext}' found on line #{start_line_number} - ignoring it")
           end
         end
 
         if !handle_extension(ext, opts, body, type)
-          error_block.call("Invalid extension with name '#{ext}' specified - ignoring it")
+          error_block.call("Invalid extension with name '#{ext}' specified on line #{start_line_number} - ignoring it")
         else
           true
         end

data/lib/kramdown/parser/kramdown/footnote.rb

@@ -19,13 +19,14 @@ module Kramdown
 
       # Parse the foot note definition at the current location.
       def parse_footnote_definition
+        start_line_number = @src.current_line_number
         @src.pos += @src.matched_size
 
-        el = Element.new(:footnote_def)
+        el = Element.new(:footnote_def, nil, nil, :location => start_line_number)
         parse_blocks(el, @src[2].gsub(INDENT, ''))
         warning("Duplicate footnote name '#{@src[1]}' - overwriting") if @footnotes[@src[1]]
         (@footnotes[@src[1]] = {})[:content] = el
-        @tree.children << Element.new(:eob, :footnote_def)
+        @tree.children << Element.new(:eob, :footnote_def, nil, :location => start_line_number)
         true
       end
       define_parser(:footnote_definition, FOOTNOTE_DEFINITION_START)
@@ -35,15 +36,16 @@ module Kramdown
 
       # Parse the footnote marker at the current location.
       def parse_footnote_marker
+        start_line_number = @src.current_line_number
         @src.pos += @src.matched_size
         fn_def = @footnotes[@src[1]]
         if fn_def
           fn_def[:marker] ||= []
-          fn_def[:marker].push(Element.new(:footnote, fn_def[:content], nil, :name => @src[1]))
+          fn_def[:marker].push(Element.new(:footnote, fn_def[:content], nil, :name => @src[1], :location => start_line_number))
           fn_def[:stack] = [@stack.map {|s| s.first}, @tree, fn_def[:marker]].flatten.compact
           @tree.children << fn_def[:marker].last
         else
-          warning("Footnote definition for '#{@src[1]}' not found")
+          warning("Footnote definition for '#{@src[1]}' not found on line #{start_line_number}")
           add_text(@src.matched)
         end
       end