kramdown 1.2.0 → 1.3.0

data/lib/kramdown/parser/kramdown/header.rb

@@ -20,10 +20,11 @@ module Kramdown
       def parse_setext_header
         return false if !after_block_boundary?
 
+        start_line_number = @src.current_line_number
         @src.pos += @src.matched_size
         text, id, level = @src[1], @src[2], @src[3]
         text.strip!
-        el = new_block_el(:header, nil, nil, :level => (level == '-' ? 2 : 1), :raw_text => text)
+        el = new_block_el(:header, nil, nil, :level => (level == '-' ? 2 : 1), :raw_text => text, :location => start_line_number)
         add_text(text, el)
         el.attr['id'] = id if id
         @tree.children << el
@@ -39,12 +40,13 @@ module Kramdown
       def parse_atx_header
         return false if !after_block_boundary?
 
+        start_line_number = @src.current_line_number
         @src.check(ATX_HEADER_MATCH)
         level, text, id = @src[1], @src[2].to_s.strip, @src[3]
         return false if text.empty?
 
         @src.pos += @src.matched_size
-        el = new_block_el(:header, nil, nil, :level => level.length, :raw_text => text)
+        el = new_block_el(:header, nil, nil, :level => level.length, :raw_text => text, :location => start_line_number)
         add_text(text, el)
         el.attr['id'] = id if id
         @tree.children << el

data/lib/kramdown/parser/kramdown/horizontal_rule.rb

@@ -15,8 +15,9 @@ module Kramdown
 
       # Parse the horizontal rule at the current location.
       def parse_horizontal_rule
+        start_line_number = @src.current_line_number
         @src.pos += @src.matched_size
-        @tree.children << new_block_el(:hr)
+        @tree.children << new_block_el(:hr, nil, nil, :location => start_line_number)
         true
       end
       define_parser(:horizontal_rule, HR_START)

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

@@ -15,12 +15,14 @@ module Kramdown
 
       # Parse the HTML entity at the current location.
       def parse_html_entity
+        start_line_number = @src.current_line_number
         @src.pos += @src.matched_size
         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)
+                                        nil, :original => @src.matched, :location => start_line_number)
         rescue ::Kramdown::Error
-          @tree.children << Element.new(:entity, ::Kramdown::Utils::Entities.entity('amp'))
+          @tree.children << Element.new(:entity, ::Kramdown::Utils::Entities.entity('amp'),
+                                        nil, :location => start_line_number)
           add_text(@src.matched[1..-1])
         end
       end

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

@@ -22,7 +22,7 @@ module Kramdown
       def parse_link_definition
         @src.pos += @src.matched_size
         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]
+        warning("Duplicate link ID '#{link_id}' on line #{@src.current_line_number} - overwriting") if @link_defs[link_id]
         @link_defs[link_id] = [link_url, link_title]
         @tree.children << Element.new(:eob, :link_def)
         true
@@ -53,6 +53,7 @@ module Kramdown
       # Parse the link at the current scanner position. This method is used to parse normal links as
       # well as image links.
       def parse_link
+        start_line_number = @src.current_line_number
         result = @src.scan(LINK_START)
         reset_pos = @src.pos
 
@@ -63,7 +64,7 @@ module Kramdown
           add_text(result)
           return
         end
-        el = Element.new(link_type)
+        el = Element.new(link_type, nil, nil, :location => start_line_number)
 
         count = 1
         found = parse_spans(el, LINK_BRACKET_STOP_RE) do

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

@@ -46,8 +46,9 @@ module Kramdown
 
       # Parse the ordered or unordered list at the current location.
       def parse_list
+        start_line_number = @src.current_line_number
         type, list_start_re = (@src.check(LIST_START_UL) ? [:ul, LIST_START_UL] : [:ol, LIST_START_OL])
-        list = new_block_el(type)
+        list = new_block_el(type, nil, nil, :location => start_line_number)
 
         item = nil
         content_re, lazy_re, indent_re = nil
@@ -55,13 +56,14 @@ module Kramdown
         nested_list_found = false
         last_is_blank = false
         while !@src.eos?
+          start_line_number = @src.current_line_number
           if last_is_blank && @src.check(HR_START)
             break
           elsif @src.scan(EOB_MARKER)
             eob_found = true
             break
           elsif @src.scan(list_start_re)
-            item = Element.new(:li)
+            item = Element.new(:li, nil, nil, :location => start_line_number)
             item.value, indentation, content_re, lazy_re, indent_re = parse_first_list_line(@src[1].length, @src[2])
             list.children << item
 
@@ -96,7 +98,7 @@ module Kramdown
 
         last = nil
         list.children.each do |it|
-          temp = Element.new(:temp)
+          temp = Element.new(:temp, nil, nil, :location => it.options[:location])
           parse_blocks(temp, it.value)
           it.children = temp.children
           it.value = nil
@@ -146,8 +148,9 @@ module Kramdown
           para = @tree.children.pop
           first_as_para = true
         end
+        deflist.options[:location] = para.options[:location] # take location from preceding para which is the first definition term
         para.children.first.value.split(/\n/).each do |term|
-          el = Element.new(:dt)
+          el = Element.new(:dt, nil, nil, :location => @src.current_line_number)
           el.children << Element.new(:raw_text, term)
           deflist.children << el
         end
@@ -158,8 +161,9 @@ module Kramdown
         def_start_re = DEFINITION_LIST_START
         last_is_blank = false
         while !@src.eos?
+          start_line_number = @src.current_line_number
           if @src.scan(def_start_re)
-            item = Element.new(:dd)
+            item = Element.new(:dd, nil, nil, :location => start_line_number)
             item.options[:first_as_para] = first_as_para
             item.value, indentation, content_re, lazy_re, indent_re = parse_first_list_line(@src[1].length, @src[2])
             deflist.children << item

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

@@ -17,6 +17,7 @@ module Kramdown
 
       # Parse the math block at the current location.
       def parse_block_math
+        start_line_number = @src.current_line_number
         if !after_block_boundary?
           return false
         elsif @src[1]
@@ -28,7 +29,7 @@ module Kramdown
         @src.pos += @src.matched_size
         data = @src[2]
         if before_block_boundary?
-          @tree.children << new_block_el(:math, data, nil, :category => :block)
+          @tree.children << new_block_el(:math, data, nil, :category => :block, :location => start_line_number)
           true
         else
           @src.pos = orig_pos
@@ -38,12 +39,13 @@ module Kramdown
       define_parser(:block_math, BLOCK_MATH_START)
 
 
-      INLINE_MATH_START = /\$\$(.*?)\$\$/
+      INLINE_MATH_START = /\$\$(.*?)\$\$/m
 
       # Parse the inline math at the current location.
       def parse_inline_math
+        start_line_number = @src.current_line_number
         @src.pos += @src.matched_size
-        @tree.children << Element.new(:math, @src[1], nil, :category => :span)
+        @tree.children << Element.new(:math, @src[1], nil, :category => :span, :location => start_line_number)
       end
       define_parser(:inline_math, INLINE_MATH_START, '\$')
 

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

@@ -29,6 +29,7 @@ module Kramdown
 
       # Parse the paragraph at the current location.
       def parse_paragraph
+        start_line_number = @src.current_line_number
         result = @src.scan(PARAGRAPH_MATCH)
         while !@src.match?(self.class::PARAGRAPH_END)
           result << @src.scan(PARAGRAPH_MATCH)
@@ -37,7 +38,7 @@ module Kramdown
         if @tree.children.last && @tree.children.last.type == :p
           @tree.children.last.children.first.value << "\n" << result
         else
-          @tree.children << new_block_el(:p)
+          @tree.children << new_block_el(:p, nil, nil, :location => start_line_number)
           result.lstrip!
           @tree.children.last.children << Element.new(@text_type, result)
         end

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

@@ -26,7 +26,7 @@ module Kramdown
         return false if !after_block_boundary?
 
         orig_pos = @src.pos
-        table = new_block_el(:table, nil, nil, :alignment => [])
+        table = new_block_el(:table, nil, nil, :alignment => [], :location => @src.current_line_number)
         leading_pipe = (@src.check(TABLE_LINE) =~ /^\s*\|/)
         @src.scan(TABLE_SEP_LINE)
 
@@ -66,7 +66,7 @@ module Kramdown
               if i % 2 == 1
                 (cells.empty? ? cells : cells.last) << str
               else
-                reset_env(:src => StringScanner.new(str))
+                reset_env(:src => Kramdown::Utils::StringScanner.new(str, @src.current_line_number))
                 root = Element.new(:root)
                 parse_spans(root, nil, [:codespan])
 
@@ -110,7 +110,9 @@ module Kramdown
 
         # Parse all lines of the table with the code span parser
         env = save_env
-        reset_env(:src => StringScanner.new(extract_string(orig_pos...(@src.pos-1), @src)))
+        l_src = ::Kramdown::Utils::StringScanner.new(extract_string(orig_pos...(@src.pos-1), @src),
+                                                     @src.current_line_number)
+        reset_env(:src => l_src)
         root = Element.new(:root)
         parse_spans(root, nil, [:codespan])
         restore_env(env)

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

@@ -20,16 +20,21 @@ module Kramdown
 
       # Parse the typographic symbols at the current location.
       def parse_typographic_syms
+        start_line_number = @src.current_line_number
         @src.pos += @src.matched_size
         val = TYPOGRAPHIC_SYMS_SUBST[@src.matched]
         if val.kind_of?(Symbol)
-          @tree.children << Element.new(:typographic_sym, val)
+          @tree.children << Element.new(:typographic_sym, val, nil, :location => start_line_number)
         elsif @src.matched == '\\<<'
-          @tree.children << Element.new(:entity, ::Kramdown::Utils::Entities.entity('lt'))
-          @tree.children << Element.new(:entity, ::Kramdown::Utils::Entities.entity('lt'))
+          @tree.children << Element.new(:entity, ::Kramdown::Utils::Entities.entity('lt'),
+                                        nil, :location => start_line_number)
+          @tree.children << Element.new(:entity, ::Kramdown::Utils::Entities.entity('lt'),
+                                        nil, :location => start_line_number)
         else
-          @tree.children << Element.new(:entity, ::Kramdown::Utils::Entities.entity('gt'))
-          @tree.children << Element.new(:entity, ::Kramdown::Utils::Entities.entity('gt'))
+          @tree.children << Element.new(:entity, ::Kramdown::Utils::Entities.entity('gt'),
+                                        nil, :location => start_line_number)
+          @tree.children << Element.new(:entity, ::Kramdown::Utils::Entities.entity('gt'),
+                                        nil, :location => start_line_number)
         end
       end
       define_parser(:typographic_syms, TYPOGRAPHIC_SYMS_RE, '--|\\.\\.\\.|(?:\\\\| )?(?:<<|>>)')

data/lib/kramdown/utils.rb

@@ -19,6 +19,7 @@ module Kramdown
     autoload :Html, 'kramdown/utils/html'
     autoload :OrderedHash, 'kramdown/utils/ordered_hash'
     autoload :Unidecoder, 'kramdown/utils/unidecoder'
+    autoload :StringScanner, 'kramdown/utils/string_scanner'
 
     # Treat +name+ as if it were snake cased (e.g. snake_case) and camelize it (e.g. SnakeCase).
     def self.camelize(name)

data/lib/kramdown/utils/string_scanner.rb

@@ -0,0 +1,52 @@
+# -*- coding: utf-8 -*-
+
+require 'strscan'
+
+module Kramdown
+  module Utils
+
+    # This patched StringScanner adds line number information for current scan position and a
+    # start_line_number override for nested StringScanners.
+    class StringScanner < ::StringScanner
+
+      # The start line number. Used for nested StringScanners that scan a sub-string of the source
+      # document. The kramdown parser uses this, e.g., for span level parsers.
+      attr_reader :start_line_number
+
+      # Takes the start line number as optional second argument.
+      #
+      # Note: The original second argument is no longer used so this should be safe.
+      def initialize(string, start_line_number = 1)
+        super(string)
+        @start_line_number = start_line_number || 1
+      end
+
+      # To make this unicode (multibyte) aware, we have to use #charpos which was added in Ruby
+      # version 2.0.0.
+      #
+      # This method will work with older versions of Ruby, however it will report incorrect line
+      # numbers if the scanned string contains multibyte characters.
+      if instance_methods.include?(:charpos)
+        def best_pos
+          charpos
+        end
+      else
+        def best_pos
+          pos
+        end
+      end
+
+      # Returns the line number for current charpos.
+      #
+      # NOTE: Requires that all line endings are normalized to '\n'
+      #
+      # NOTE: Normally we'd have to add one to the count of newlines to get the correct line number.
+      # However we add the one indirectly by using a one-based start_line_number.
+      def current_line_number
+        string[0..best_pos].count("\n") + start_line_number
+      end
+
+    end
+
+  end
+end

data/lib/kramdown/version.rb

@@ -10,6 +10,6 @@
 module Kramdown
 
   # The kramdown version.
-  VERSION = '1.2.0'
+  VERSION = '1.3.0'
 
 end

data/man/man1/kramdown.1

@@ -38,6 +38,7 @@ Show the help.
 .B \-\-template ARG
 
 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
@@ -46,10 +47,13 @@ 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.
 
@@ -69,10 +73,26 @@ Default: true
 Used by: HTML/Latex converter
 
 
+.TP
+.B \-\-[no\-]auto-id-stripping
+
+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
+
+
 .TP
 .B \-\-auto-id-prefix ARG
 
-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
@@ -227,6 +247,9 @@ Used by: HTML converter
 
 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
 
@@ -357,10 +380,22 @@ Default: 0
 Used by: HTML converter, Kramdown converter, Latex converter
 
 
+.TP
+.B \-\-[no\-]hard-wrap
+
+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
+
+
 .SH EXIT STATUS
 The exit status is 0 if no error happened. Otherwise it is 1.
 .SH SEE ALSO
-The kramdown website, http://kramdown.rubyforge.org/ for more information, especially on the supported
+The kramdown website, http://kramdown.gettalong.org/ for more information, especially on the supported
 input syntax.
 .SH AUTHOR
 kramdown was written by Thomas Leitner <t_leitner@gmx.at>.

data/test/test_files.rb

@@ -7,14 +7,14 @@
 #++
 #
 
-require 'test/unit'
+require 'minitest/autorun'
 require 'kramdown'
 require 'yaml'
 require 'tmpdir'
 
 Encoding.default_external = 'utf-8' if RUBY_VERSION >= '1.9'
 
-class TestFiles < Test::Unit::TestCase
+class TestFiles < Minitest::Test
 
   EXCLUDE_KD_FILES = [('test/testcases/block/04_header/with_auto_ids.text' if RUBY_VERSION <= '1.8.6'), # bc of dep stringex not working
                      ].compact

data/test/test_location.rb

@@ -0,0 +1,158 @@
+# -*- coding: utf-8 -*-
+
+require 'minitest/autorun'
+require 'kramdown'
+
+Encoding.default_external = 'utf-8' if RUBY_VERSION >= '1.9'
+
+describe 'location' do
+
+  # checks that +element+'s :location option corresponds to the location stored
+  # in the element.attr['class']
+  def check_element_for_location(element)
+    if (match = /^line-(\d+)/.match(element.attr['class'] || ''))
+      expected_line = match[1].to_i
+      element.options[:location].must_equal(expected_line)
+    end
+    element.children.each do |child|
+      check_element_for_location(child)
+    end
+  end
+
+  # Test cases consist of a kramdown string that uses IALs to specify the expected
+  # line numbers for a given element.
+  test_cases = {
+    'autolink' => %(testing autolinks\n\n<http://kramdown.org>{:.line-3}),
+    'blockquote' => %(
+      > block quote1
+      >
+      > * {:.line-3} list item in block quote
+      > * {:.line-4} list item in block quote
+      > {:.line-3}
+      {:.line-1}
+
+      > block quote2
+      {:.line-8}
+    ),
+    'codeblock' => %(\na para\n\n~~~~\ntest code 1\n~~~~\n{:.line-3}\n\n    test code 2\n{:.line-8}\n),
+    'codespan' => %(a para\n\nanother para `<code>`{:.line-3} with code\n),
+    'emphasis' => %(
+      para *span*{:.line-1}
+      {:.line-1}
+
+      ## header *span*{:.line-4}
+      {:.line-4}
+
+      Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
+      tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
+      quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
+      consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse
+      cillum *short span on single line*{:.line-11}
+      dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non
+      *long span over multiple lines - proident, sunt in culpa qui officia deserunt
+      mollit anim id est laborum.*{:.line-13}
+      Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
+      tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
+      quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
+      `code span`{:.line-18}
+      Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
+      tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
+      quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
+      {:.line-7}
+    ),
+    'header' => %(
+      # header1
+      {:.line-1}
+
+      ## header2
+      {:.line-4}
+
+      ## header3
+      {:.line-7}
+
+      header4
+      =======
+      {:.line-10}
+
+      header5
+      -------
+      {:.line-14}
+    ),
+    'horizontal_rule' => %(\na para\n\n----\n{:.line-3}\n),
+    'html_entity' => "a para\n\nanother para with &amp;{:.line-3} html entity.\n",
+    'link' => %(
+      a para
+
+      This is [a link](http://rubyforge.org){:.line-3} to a page.
+
+      Here comes a ![smiley](../images/smiley.png){:.line-5}
+    ),
+    'list' => %(
+      * {:.line-1} list item
+      * {:.line-2} list item
+      * {:.line-3} list item
+      {:.line-1}
+
+      {:.line-7}
+      1. {:.line-7} list item
+      2. {:.line-8} list item
+      3. {:.line-9} list item
+
+      {:.line-12}
+      definition term 1
+      : {:.line-13} definition definition 1
+      definition term 2
+      : {:.line-15} definition definition 2
+    ),
+    'math_block' => %(\na para\n\n$$5+5$$\n{:.line-3}\n),
+    'math_inline' => %(\na para\n\nanother para with inline math $$5+5$${:.line-3}\n),
+    'paragraph' => %(
+      para1
+      {:.line-1}
+
+      para2
+      {:.line-4}
+
+      Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
+      tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
+      quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
+      consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse
+      {:.line-7}
+
+      {:.line-14}
+      para with leading IAL
+    ),
+    'table' => %(
+      a para
+
+      |first|second|third|
+      |-----|------|-----|
+      |a    |b     |c    |
+      {:.line-3}
+    ),
+    'typographic_symbol' => %(
+      a para
+
+      another para ---{:.line-3}
+
+      another para ...{:.line-5}
+    )
+  }
+  test_cases.each do |name, test_string|
+    it "Handles #{ name }" do
+      doc = Kramdown::Document.new(test_string.gsub(/^      /, '').strip)
+      check_element_for_location(doc.root)
+    end
+  end
+
+  it 'adds location info to duplicate abbreviation definition warnings' do
+    test_string = %(This snippet contains a duplicate abbreviation definition
+
+*[duplicate]: The first definition
+*[duplicate]: The second definition
+    )
+    doc = Kramdown::Document.new(test_string.strip)
+    doc.warnings.must_equal ["Duplicate abbreviation ID 'duplicate' on line 4 - overwriting"]
+  end
+
+end