kramdown 0.14.2 → 2.3.0

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

@@ -1,22 +1,9 @@
-# -*- coding: utf-8 -*-
+# -*- coding: utf-8; frozen_string_literal: true -*-
 #
 #--
-# Copyright (C) 2009-2012 Thomas Leitner <t_leitner@gmx.at>
+# Copyright (C) 2009-2019 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/>.
+# This file is part of kramdown which is licensed under the MIT.
 #++
 #
 
@@ -32,38 +19,41 @@ 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]]
+        if @footnotes[@src[1]]
+          warning("Duplicate footnote name '#{@src[1]}' on line #{start_line_number} - overwriting")
+        end
+        @tree.children << new_block_el(:eob, :footnote_def)
         (@footnotes[@src[1]] = {})[:content] = el
-        @tree.children << Element.new(:eob, :footnote_def)
+        @footnotes[@src[1]][:eob] = @tree.children.last
         true
       end
       define_parser(:footnote_definition, FOOTNOTE_DEFINITION_START)
 
-
       FOOTNOTE_MARKER_START = /\[\^(#{ALD_ID_NAME})\]/
 
       # 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
-          valid = fn_def[:marker] && fn_def[:stack][0..-2].zip(fn_def[:stack][1..-1]).all? do |par, child|
-            par.children.include?(child)
-          end
-          if !fn_def[:marker] || !valid
-            fn_def[:marker] = Element.new(:footnote, fn_def[:content], nil, :name => @src[1])
-            fn_def[:stack] = [@stack.map {|s| s.first}, @tree, fn_def[:marker]].flatten.compact
-            @tree.children << fn_def[:marker]
-          else
-            warning("Footnote marker '#{@src[1]}' already appeared in document, ignoring newly found marker")
-            add_text(@src.matched)
+          if fn_def[:eob]
+            update_attr_with_ial(fn_def[:eob].attr, fn_def[:eob].options[:ial] || {})
+            fn_def[:attr] = fn_def[:eob].attr
+            fn_def[:options] = fn_def[:eob].options
+            fn_def.delete(:eob)
           end
+          fn_def[:marker] ||= []
+          fn_def[:marker].push(Element.new(:footnote, fn_def[:content], fn_def[:attr],
+                                           fn_def[:options].merge(name: @src[1], location: start_line_number)))
+          @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

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

@@ -1,69 +1,69 @@
-# -*- coding: utf-8 -*-
+# -*- coding: utf-8; frozen_string_literal: true -*-
 #
 #--
-# Copyright (C) 2009-2012 Thomas Leitner <t_leitner@gmx.at>
+# Copyright (C) 2009-2019 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/>.
+# This file is part of kramdown which is licensed under the MIT.
 #++
 #
 
 require 'kramdown/parser/kramdown/block_boundary'
+require 'rexml/xmltokens'
 
 module Kramdown
   module Parser
     class Kramdown
 
-      HEADER_ID=/(?:[ \t]\{#(\w[\w-]*)\})?/
-      SETEXT_HEADER_START = /^(#{OPT_SPACE}[^ \t].*?)#{HEADER_ID}[ \t]*?\n(-|=)+\s*?\n/
+      SETEXT_HEADER_START = /^#{OPT_SPACE}(?<contents>[^ \t].*)\n(?<level>[-=])[-=]*[ \t\r\f\v]*\n/
 
       # Parse the Setext header at the current location.
       def parse_setext_header
-        return false if !after_block_boundary?
-
-        @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)
-        add_text(text, el)
-        el.attr['id'] = id if id
-        @tree.children << el
+        return false unless after_block_boundary?
+        text, id = parse_header_contents
+        return false if text.empty?
+        add_header(@src["level"] == '-' ? 2 : 1, text, id)
         true
       end
       define_parser(:setext_header, SETEXT_HEADER_START)
 
-
-      ATX_HEADER_START = /^\#{1,6}/
-      ATX_HEADER_MATCH = /^(\#{1,6})(.+?)\s*?#*#{HEADER_ID}\s*?\n/
+      ATX_HEADER_START = /^(?<level>\#{1,6})[\t ]*(?<contents>[^ \t].*)\n/
 
       # Parse the Atx header at the current location.
       def parse_atx_header
-        return false if !after_block_boundary?
-
-        @src.check(ATX_HEADER_MATCH)
-        level, text, id = @src[1], @src[2].to_s.strip, @src[3]
+        return false unless after_block_boundary?
+        text, id = parse_header_contents
+        text.sub!(/(?<!\\)#+\z/, '') && text.rstrip!
         return false if text.empty?
+        add_header(@src["level"].length, text, id)
+        true
+      end
+      define_parser(:atx_header, ATX_HEADER_START)
+
+      protected
 
+      HEADER_ID = /[\t ]{#(?<id>#{REXML::XMLTokens::NAME_START_CHAR}#{REXML::XMLTokens::NAME_CHAR}*)}\z/
+
+      # Returns header text and optional ID.
+      def parse_header_contents
+        text = @src["contents"]
+        text.rstrip!
+        id_match = HEADER_ID.match(text)
+        if id_match
+          id = id_match["id"]
+          text = text[0...-id_match[0].length]
+          text.rstrip!
+        end
+        [text, id]
+      end
+
+      def add_header(level, text, id)
+        start_line_number = @src.current_line_number
         @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, raw_text: text, location: start_line_number)
         add_text(text, el)
         el.attr['id'] = id if id
         @tree.children << el
-        true
       end
-      define_parser(:atx_header, ATX_HEADER_START)
 
     end
   end

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

@@ -1,22 +1,9 @@
-# -*- coding: utf-8 -*-
+# -*- coding: utf-8; frozen_string_literal: true -*-
 #
 #--
-# Copyright (C) 2009-2012 Thomas Leitner <t_leitner@gmx.at>
+# Copyright (C) 2009-2019 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/>.
+# This file is part of kramdown which is licensed under the MIT.
 #++
 #
 
@@ -28,8 +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.rb

@@ -1,22 +1,9 @@
-# -*- coding: utf-8 -*-
+# -*- coding: utf-8; frozen_string_literal: true -*-
 #
 #--
-# Copyright (C) 2009-2012 Thomas Leitner <t_leitner@gmx.at>
+# Copyright (C) 2009-2019 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/>.
+# This file is part of kramdown which is licensed under the MIT.
 #++
 #
 
@@ -36,14 +23,17 @@ module Kramdown
       TRAILING_WHITESPACE = /[ \t]*\n/
 
       def handle_kramdown_html_tag(el, closed, handle_body)
-        el.options[:ial] = @block_ial if @block_ial
+        if @block_ial
+          el.options[:ial] = @block_ial
+          @block_ial = nil
+        end
 
         content_model = if @tree.type != :html_element || @tree.options[:content_model] != :raw
                           (@options[:parse_block_html] ? HTML_CONTENT_MODEL[el.value] : :raw)
                         else
                           :raw
                         end
-        if val = HTML_MARKDOWN_ATTR_MAP[el.attr.delete('markdown')]
+        if (val = HTML_MARKDOWN_ATTR_MAP[el.attr.delete('markdown')])
           content_model = (val == :default ? HTML_CONTENT_MODEL[el.value] : val)
         end
 
@@ -53,8 +43,8 @@ module Kramdown
 
         if !closed && handle_body
           if content_model == :block
-            if !parse_blocks(el)
-              warning("Found no end tag for '#{el.value}' - auto-closing it")
+            unless parse_blocks(el)
+              warning("Found no end tag for '#{el.value}' (line #{el.options[:location]}) - auto-closing it")
             end
           elsif content_model == :span
             curpos = @src.pos
@@ -64,35 +54,33 @@ module Kramdown
             else
               add_text(@src.rest, el)
               @src.terminate
-              warning("Found no end tag for '#{el.value}' - auto-closing it")
+              warning("Found no end tag for '#{el.value}' (line #{el.options[:location]}) - auto-closing it")
             end
           else
             parse_raw_html(el, &method(:handle_kramdown_html_tag))
           end
-          @src.scan(TRAILING_WHITESPACE) unless (@tree.type == :html_element && @tree.options[:content_model] == :raw)
+          unless @tree.type == :html_element && @tree.options[:content_model] == :raw
+            @src.scan(TRAILING_WHITESPACE)
+          end
         end
       end
 
-
-      HTML_BLOCK_START = /^#{OPT_SPACE}<(#{REXML::Parsers::BaseParser::UNAME_STR}|\?|!--|\/)/
+      HTML_BLOCK_START = /^#{OPT_SPACE}<(#{REXML::Parsers::BaseParser::UNAME_STR}|!--|\/)/
 
       # Parse the HTML at the current position as block-level HTML.
       def parse_block_html
-        if result = @src.scan(HTML_COMMENT_RE)
-          @tree.children << Element.new(:xml_comment, result, nil, :category => :block)
-          @src.scan(TRAILING_WHITESPACE)
-          true
-        elsif result = @src.scan(HTML_INSTRUCTION_RE)
-          @tree.children << Element.new(:xml_pi, result, nil, :category => :block)
+        line = @src.current_line_number
+        if (result = @src.scan(HTML_COMMENT_RE))
+          @tree.children << Element.new(:xml_comment, result, nil, category: :block, location: line)
           @src.scan(TRAILING_WHITESPACE)
           true
         else
-          if result = @src.check(/^#{OPT_SPACE}#{HTML_TAG_RE}/) && !HTML_SPAN_ELEMENTS.include?(@src[1].downcase)
+          if @src.check(/^#{OPT_SPACE}#{HTML_TAG_RE}/o) && !HTML_SPAN_ELEMENTS.include?(@src[1].downcase)
             @src.pos += @src.matched_size
-            handle_html_start_tag(&method(:handle_kramdown_html_tag))
+            handle_html_start_tag(line, &method(:handle_kramdown_html_tag))
             Kramdown::Parser::Html::ElementConverter.convert(@root, @tree.children.last) if @options[:html_to_native]
             true
-          elsif result = @src.check(/^#{OPT_SPACE}#{HTML_TAG_CLOSE_RE}/) && !HTML_SPAN_ELEMENTS.include?(@src[1].downcase)
+          elsif @src.check(/^#{OPT_SPACE}#{HTML_TAG_CLOSE_RE}/o) && !HTML_SPAN_ELEMENTS.include?(@src[1].downcase)
             name = @src[1].downcase
 
             if @tree.type == :html_element && @tree.value == name
@@ -108,33 +96,37 @@ module Kramdown
       end
       define_parser(:block_html, HTML_BLOCK_START)
 
-
-      HTML_SPAN_START = /<(#{REXML::Parsers::BaseParser::UNAME_STR}|\?|!--|\/)/
+      HTML_SPAN_START = /<(#{REXML::Parsers::BaseParser::UNAME_STR}|!--|\/)/
 
       # Parse the HTML at the current position as span-level HTML.
       def parse_span_html
-        if result = @src.scan(HTML_COMMENT_RE)
-          @tree.children << Element.new(:xml_comment, result, nil, :category => :span)
-        elsif result = @src.scan(HTML_INSTRUCTION_RE)
-          @tree.children << Element.new(:xml_pi, result, nil, :category => :span)
-        elsif result = @src.scan(HTML_TAG_CLOSE_RE)
-          warning("Found invalidly used HTML closing tag for '#{@src[1]}'")
+        line = @src.current_line_number
+        if (result = @src.scan(HTML_COMMENT_RE))
+          @tree.children << Element.new(:xml_comment, result, nil, category: :span, location: line)
+        elsif (result = @src.scan(HTML_TAG_CLOSE_RE))
+          warning("Found invalidly used HTML closing tag for '#{@src[1]}' on line #{line}")
           add_text(result)
-        elsif result = @src.scan(HTML_TAG_RE)
-          tag_name = @src[1].downcase
+        elsif (result = @src.scan(HTML_TAG_RE))
+          tag_name = @src[1]
+          tag_name.downcase! if HTML_ELEMENT[tag_name.downcase]
           if HTML_BLOCK_ELEMENTS.include?(tag_name)
-            warning("Found block HTML tag '#{tag_name}' in span-level text")
+            warning("Found block HTML tag '#{tag_name}' in span-level text on line #{line}")
             add_text(result)
             return
           end
 
-          attrs = Utils::OrderedHash.new
-          @src[2].scan(HTML_ATTRIBUTE_RE).each {|name,sep,val| attrs[name.downcase] = (val || '').gsub(/\n+/, ' ')}
+          attrs = parse_html_attributes(@src[2], line, HTML_ELEMENT[tag_name])
+          attrs.each_value {|value| value.gsub!(/\n+/, ' ') unless value.empty? }
 
-          do_parsing = (HTML_CONTENT_MODEL[tag_name] == :raw || @tree.options[:content_model] == :raw ? false : @options[:parse_span_html])
-          if val = HTML_MARKDOWN_ATTR_MAP[attrs.delete('markdown')]
+          do_parsing = if HTML_CONTENT_MODEL[tag_name] == :raw || @tree.options[:content_model] == :raw
+                         false
+                       else
+                         @options[:parse_span_html]
+                       end
+          if (val = HTML_MARKDOWN_ATTR_MAP[attrs.delete('markdown')])
             if val == :block
-              warning("Cannot use block-level parsing in span-level HTML tag - using default mode")
+              warning("Cannot use block-level parsing in span-level HTML tag (line #{line}) " \
+                      "- using default mode")
             elsif val == :span
               do_parsing = true
             elsif val == :default
@@ -144,17 +136,16 @@ module Kramdown
             end
           end
 
-          el = Element.new(:html_element, tag_name, attrs, :category => :span,
-                           :content_model => (do_parsing ? :span : :raw), :is_closed => !!@src[4])
+          el = Element.new(:html_element, tag_name, attrs, category: :span, location: line,
+                           content_model: (do_parsing ? :span : :raw), is_closed: !!@src[4])
           @tree.children << el
-          stop_re = /<\/#{Regexp.escape(tag_name)}\s*>/i
-          if !@src[4] && HTML_ELEMENTS_WITHOUT_BODY.include?(el.value)
-            warning("The HTML tag '#{el.value}' cannot have any content - auto-closing it")
-          elsif !@src[4]
+          stop_re = /<\/#{Regexp.escape(tag_name)}\s*>/
+          stop_re = Regexp.new(stop_re.source, Regexp::IGNORECASE) if HTML_ELEMENT[tag_name]
+          if !@src[4] && !HTML_ELEMENTS_WITHOUT_BODY.include?(el.value)
             if parse_spans(el, stop_re, (do_parsing ? nil : [:span_html]))
               @src.scan(stop_re)
             else
-              warning("Found no end tag for '#{el.value}' - auto-closing it")
+              warning("Found no end tag for '#{el.value}' (line #{line}) - auto-closing it")
               add_text(@src.rest, el)
               @src.terminate
             end

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

@@ -1,22 +1,9 @@
-# -*- coding: utf-8 -*-
+# -*- coding: utf-8; frozen_string_literal: true -*-
 #
 #--
-# Copyright (C) 2009-2012 Thomas Leitner <t_leitner@gmx.at>
+# Copyright (C) 2009-2019 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/>.
+# This file is part of kramdown which is licensed under the MIT.
 #++
 #
 
@@ -28,12 +15,15 @@ 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)
+          value = ::Kramdown::Utils::Entities.entity(@src[1] || (@src[2]&.to_i) || @src[3].hex)
+          @tree.children << Element.new(:entity, value,
+                                        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