kramdown 0.14.2 → 2.3.0

data/lib/kramdown/parser/kramdown/math.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.
 #++
 #
 
@@ -30,33 +17,34 @@ 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]
-          @src.scan(/^#{OPT_SPACE}\\/) if @src[3]
+          @src.scan(/^#{OPT_SPACE}\\/o) if @src[3]
           return false
         end
 
-        orig_pos = @src.pos
+        saved_pos = @src.save_pos
         @src.pos += @src.matched_size
-        data = @src[2]
+        data = @src[2].strip
         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
+          @src.revert_pos(saved_pos)
           false
         end
       end
       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].strip, nil, category: :span, location: start_line_number)
       end
       define_parser(:inline_math, INLINE_MATH_START, '\$')
 

data/lib/kramdown/parser/kramdown/paragraph.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.
 #++
 #
 
@@ -30,8 +17,8 @@ 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_SPAN_ELEMENTS = HTML_SPAN_ELEMENTS + %w[script]
+      LAZY_END_HTML_START = /<(?>(?!(?:#{LAZY_END_HTML_SPAN_ELEMENTS.join('|')})\b)#{REXML::Parsers::BaseParser::UNAME_STR})/
       LAZY_END_HTML_STOP = /<\/(?!(?:#{LAZY_END_HTML_SPAN_ELEMENTS.join('|')})\b)#{REXML::Parsers::BaseParser::UNAME_STR}\s*>/m
 
       LAZY_END = /#{BLANK_LINE}|#{IAL_BLOCK_START}|#{EOB_MARKER}|^#{OPT_SPACE}#{LAZY_END_HTML_STOP}|^#{OPT_SPACE}#{LAZY_END_HTML_START}|\Z/
@@ -42,22 +29,34 @@ module Kramdown
 
       # Parse the paragraph at the current location.
       def parse_paragraph
+        pos = @src.pos
+        start_line_number = @src.current_line_number
         result = @src.scan(PARAGRAPH_MATCH)
-        while !@src.match?(self.class::PARAGRAPH_END)
+        until @src.match?(paragraph_end)
           result << @src.scan(PARAGRAPH_MATCH)
         end
-        result.chomp!
-        if @tree.children.last && @tree.children.last.type == :p
-          @tree.children.last.children.first.value << "\n" << result
+        result.rstrip!
+        if (last_child = @tree.children.last) && last_child.type == :p
+          last_item_in_para = last_child.children.last
+          if last_item_in_para && last_item_in_para.type == @text_type
+            joiner = (extract_string((pos - 3)...pos, @src) == "  \n" ? "  \n" : "\n")
+            last_item_in_para.value << joiner << result
+          else
+            add_text(result, last_child)
+          end
         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)
+          add_text(result, @tree.children.last)
         end
         true
       end
       define_parser(:paragraph, PARAGRAPH_START)
 
+      def paragraph_end
+        self.class::PARAGRAPH_END
+      end
+
     end
   end
 end

data/lib/kramdown/parser/kramdown/smart_quotes.rb

@@ -1,55 +1,13 @@
-# -*- 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.
 #++
 #
 #--
-# Parts of this file are based on code from Maruku by Andrea Censi.
-# The needed license statements follow:
-#
-#   Copyright (C) 2006  Andrea Censi  <andrea (at) rubyforge.org>
-#
-#   Maruku 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 2 of the License, or
-#   (at your option) any later version.
-#
-#   Maruku 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 Maruku; if not, write to the Free Software
-#   Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
-#
-# NOTA BENE:
-#
-# The following algorithm is a rip-off of RubyPants written by
-# Christian Neukirchen.
-#
-# RubyPants is a Ruby port of SmartyPants written by John Gruber.
-#
-# This file is distributed under the GPL, which I guess is compatible
-# with the terms of the RubyPants license.
-#
-# -- Andrea Censi
+# Parts of this file are based on code from RubyPants:
 #
 # = RubyPants -- SmartyPants ported to Ruby
 #
@@ -164,24 +122,25 @@ module Kramdown
       SQ_CLOSE = %![^\ \\\\\t\r\n\\[{(-]!
 
       SQ_RULES = [
-                  [/("|')(?=#{SQ_PUNCT}\B)/, [:rquote1]],
-                  # Special case for double sets of quotes, e.g.:
-                  #   <p>He said, "'Quoted' words in a larger quote."</p>
-                  [/(\s?)"'(?=\w)/, [1, :ldquo, :lsquo]],
-                  [/(\s?)'"(?=\w)/, [1, :lsquo, :ldquo]],
-                  # Special case for decade abbreviations (the '80s):
-                  [/(\s?)'(?=\d\ds)/, [1, :rsquo]],
+        [/("|')(?=[_*]{1,2}\S)/, [:lquote1]],
+        [/("|')(?=#{SQ_PUNCT}(?!\.\.)\B)/, [:rquote1]],
+        # Special case for double sets of quotes, e.g.:
+        #   <p>He said, "'Quoted' words in a larger quote."</p>
+        [/(\s?)"'(?=\w)/, [1, :ldquo, :lsquo]],
+        [/(\s?)'"(?=\w)/, [1, :lsquo, :ldquo]],
+        # Special case for decade abbreviations (the '80s):
+        [/(\s?)'(?=\d\ds)/, [1, :rsquo]],
 
-                  # Get most opening single/double quotes:
-                  [/(\s)('|")(?=\w)/, [1, :lquote2]],
-                  # Single/double closing quotes:
-                  [/(#{SQ_CLOSE})('|")/, [1, :rquote2]],
-                  # Special case for e.g. "<i>Custer</i>'s Last Stand."
-                  [/("|')(\s|s\b|$)/, [:rquote1, 2]],
-                  # Any remaining single quotes should be opening ones:
-                  [/(.?)'/m, [1, :lsquo]],
-                  [/(.?)"/m, [1, :ldquo]],
-                 ] #'"
+        # Get most opening single/double quotes:
+        [/(\s)('|")(?=\w)/, [1, :lquote2]],
+        # Single/double closing quotes:
+        [/(#{SQ_CLOSE})('|")/, [1, :rquote2]],
+        # Special case for e.g. "<i>Custer</i>'s Last Stand."
+        [/("|')(?=\s|s\b|$)/, [:rquote1]],
+        # Any remaining single quotes should be opening ones:
+        [/(.?)'/m, [1, :lsquo]],
+        [/(.?)"/m, [1, :ldquo]],
+      ] # '"
 
       SQ_SUBSTS = {
         [:rquote1, '"'] => :rdquo,
@@ -197,13 +156,14 @@ module Kramdown
 
       # Parse the smart quotes at current location.
       def parse_smart_quotes
-        substs = SQ_RULES.find {|reg, subst| @src.scan(reg)}[1]
+        start_line_number = @src.current_line_number
+        substs = SQ_RULES.find {|reg, _subst| @src.scan(reg) }[1]
         substs.each do |subst|
           if subst.kind_of?(Integer)
             add_text(@src[subst])
           else
-            val = SQ_SUBSTS[[subst, @src[subst.to_s[-1,1].to_i]]] || subst
-            @tree.children << Element.new(:smart_quote, val)
+            val = SQ_SUBSTS[[subst, @src[subst.to_s[-1, 1].to_i]]] || subst
+            @tree.children << Element.new(:smart_quote, val, nil, location: start_line_number)
           end
         end
       end

data/lib/kramdown/parser/kramdown/table.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.
 #++
 #
 
@@ -26,9 +13,9 @@ module Kramdown
   module Parser
     class Kramdown
 
-      TABLE_SEP_LINE = /^([+|: -]*?-[+|: -]*?)[ \t]*\n/
-      TABLE_HSEP_ALIGN = /[ ]?(:?)-+(:?)[ ]?/
-      TABLE_FSEP_LINE = /^[+|: =]*?=[+|: =]*?[ \t]*\n/
+      TABLE_SEP_LINE = /^([+|: \t-]*?-[+|: \t-]*?)[ \t]*\n/
+      TABLE_HSEP_ALIGN = /[ \t]?(:?)-+(:?)[ \t]?/
+      TABLE_FSEP_LINE = /^[+|: \t=]*?=[+|: \t=]*?[ \t]*\n/
       TABLE_ROW_LINE = /^(.*?)[ \t]*\n/
       TABLE_PIPE_CHECK = /(?:\||.*?[^\\\n]\|)/
       TABLE_LINE = /#{TABLE_PIPE_CHECK}.*?\n/
@@ -36,10 +23,11 @@ module Kramdown
 
       # Parse the table at the current location.
       def parse_table
-        return false if !after_block_boundary?
+        return false unless after_block_boundary?
 
+        saved_pos = @src.save_pos
         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)
 
@@ -55,19 +43,22 @@ module Kramdown
           end
         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
+        until @src.eos?
+          break unless @src.check(TABLE_LINE)
+          if @src.scan(TABLE_SEP_LINE)
+            if rows.empty?
+              # nothing to do, ignoring multiple consecutive separator lines
+            elsif table.options[:alignment].empty? && !has_footer
               add_container.call(:thead, false)
               table.options[:alignment] = @src[1].scan(TABLE_HSEP_ALIGN).map do |left, right|
-                (left.empty? && right.empty? && :default) || (right.empty? && :left) || (left.empty? && :right) || :center
+                (left.empty? && right.empty? && :default) || (right.empty? && :left) ||
+                  (left.empty? && :right) || :center
               end
             else # treat as normal separator line
               add_container.call(:tbody, false)
             end
           elsif @src.scan(TABLE_FSEP_LINE)
-            add_container.call(:tbody, true) if !rows.empty?
+            add_container.call(:tbody, true) unless rows.empty?
             has_footer = true
           elsif @src.scan(TABLE_ROW_LINE)
             trow = Element.new(:tr)
@@ -76,25 +67,21 @@ module Kramdown
             env = save_env
             cells = []
             @src[1].split(/(<code.*?>.*?<\/code>)/).each_with_index do |str, i|
-              if i % 2 == 1
+              if i.odd?
                 (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])
 
                 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(/\\\|/, -1).map {|t| t.split(/\|/, -1)}.inject([]) do |memo, t|
-                      memo.last << "|#{t.shift}" if memo.size > 0
-                      memo.concat(t)
-                    end
+                    f, *l = c.value.split(/(?<!\\)\|/, -1).map {|t| t.gsub(/\\\|/, '|') }
                     (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}"
+                    tmp = +"#{delim}#{' ' if delim.size > 1}#{c.value}#{' ' if delim.size > 1}#{delim}"
                     (cells.empty? ? cells : cells.last) << tmp
                   end
                 end
@@ -116,22 +103,28 @@ module Kramdown
           end
         end
 
-        if !before_block_boundary?
-          @src.pos = orig_pos
+        unless before_block_boundary?
+          @src.revert_pos(saved_pos)
           return false
         end
 
         # 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])
+        parse_spans(root, nil, [:codespan, :span_html])
         restore_env(env)
 
-        # Check if each line has at least one unescaped backslash that is not inside a code span
+        # Check if each line has at least one unescaped pipe that is not inside a code span/code
+        # HTML element
+        # Note: It doesn't matter that we parse *all* span HTML elements because the row splitting
+        # algorithm above only takes <code> elements into account!
         pipe_on_line = false
         while (c = root.children.shift)
-          lines = c.value.split(/\n/)
+          next unless (lines = c.value)
+          lines = lines.split("\n")
           if c.type == :codespan
             if lines.size > 2 || (lines.size == 2 && !pipe_on_line)
               break
@@ -139,17 +132,17 @@ module Kramdown
               pipe_on_line = false
             end
           else
-            break if lines.size > 1 && !pipe_on_line && lines.first !~ /^#{TABLE_PIPE_CHECK}/
-            pipe_on_line = (lines.size > 1 ? false : pipe_on_line) || (lines.last =~ /^#{TABLE_PIPE_CHECK}/)
+            break if lines.size > 1 && !pipe_on_line && lines.first !~ /^#{TABLE_PIPE_CHECK}/o
+            pipe_on_line = (lines.size > 1 ? false : pipe_on_line) || (lines.last =~ /^#{TABLE_PIPE_CHECK}/o)
           end
         end
-        @src.pos = orig_pos and return false if !pipe_on_line
+        @src.revert_pos(saved_pos) and return false unless pipe_on_line
 
-        add_container.call(has_footer ? :tfoot : :tbody, false) if !rows.empty?
+        add_container.call(has_footer ? :tfoot : :tbody, false) unless rows.empty?
 
-        if !table.children.any? {|el| el.type == :tbody}
-          warning("Found table without body - ignoring it")
-          @src.pos = orig_pos
+        if table.children.none? {|el| el.type == :tbody }
+          warning("Found table without body on line #{table.options[:location]} - ignoring it")
+          @src.revert_pos(saved_pos)
           return false
         end
 

data/lib/kramdown/parser/kramdown/typographic_symbol.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.
 #++
 #
 
@@ -29,20 +16,25 @@ module Kramdown
                           ['<< ', :laquo_space], [' >>', :raquo_space],
                           ['<<', :laquo], ['>>', :raquo]]
       TYPOGRAPHIC_SYMS_SUBST = Hash[*TYPOGRAPHIC_SYMS.flatten]
-      TYPOGRAPHIC_SYMS_RE = /#{TYPOGRAPHIC_SYMS.map {|k,v| Regexp.escape(k)}.join('|')}/
+      TYPOGRAPHIC_SYMS_RE = /#{TYPOGRAPHIC_SYMS.map {|k, _v| Regexp.escape(k) }.join('|')}/
 
       # 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, '--|\\.\\.\\.|(?:\\\\| )?(?:<<|>>)')