kramdown-parser-gfm 1.0.1 → 1.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c3856f442e4f25e0cd69a7a6b0302634673ada7b16592abee13d5461150129ba
-  data.tar.gz: 8ab357991ab37fa96ce81d36c1cd9ac1a13e2257d5570be7b309651890486e8f
+  metadata.gz: 12b3b498708f289068f922756799bda525f86c09e90b7ce711543b979aab8f6b
+  data.tar.gz: 9af4b649b95b0a3edc022936d8d8b373aff33c44ef4e2da0fd77864d32ada944
 SHA512:
-  metadata.gz: be89c6b85f0db3cde488514d56479180d73761af392fdce84b8edd72359566fcb0f53d3b6c33a1e6d3e92b19e8bf72537fed04bd1ea29f079487557cffc9b940
-  data.tar.gz: 19c2d1c58f2c76a4d36466bbad27b6a400b25ac1486bba33351a6be1a4d06df829d8285e27705831c9ff32a405064ef64ca2e388caed519c32709f86260c3099
+  metadata.gz: bbe45d4a04461082c451f6bb3de41a6b24f8682b5e0b1111c1e4bd61aefe7b9408adad0d910441ebc0b25f8e7c6bb7eb14096a5c4531e5492f39117755de935e
+  data.tar.gz: 892b44df78e01fd92858615fd0c79dad35093f05f0f929a1c00bc2d4fd1743570cc7773858c2b883d3ad3f1802c8034dbe74eac47b55ccfcb37c28bdd4a014ad

data/CONTRIBUTERS

@@ -1,3 +1,4 @@
-  Count Name
+Count Name
 ======= ====
-      4 Thomas Leitner <t_leitner@gmx.at>
+     15 Ashwin Maroli <ashmaroli@gmail.com>
+      5 Thomas Leitner <t_leitner@gmx.at>

data/VERSION

@@ -1 +1 @@
-1.0.1
+1.1.0

data/lib/kramdown-parser-gfm.rb

@@ -7,4 +7,4 @@
 #++
 #
 
-require 'kramdown/parser/gfm'
+require_relative 'kramdown/parser/gfm'

data/lib/kramdown/parser/gfm.rb

@@ -10,77 +10,32 @@
 require 'kramdown/options'
 require 'kramdown/parser/kramdown'
 
-module Kramdown
-  module Options
-
-    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
-
-    define(:gfm_quirks, Object, [:paragraph_end], <<EOF) do |val|
-Enables a set of GFM specific quirks
-
-The way how GFM is transformed on Github often differs from the way
-kramdown does things. Many of these differences are negligible but
-others are not.
-
-This option allows one to enable/disable certain GFM quirks, i.e. ways
-in which GFM parsing differs from kramdown parsing.
-
-The value has to be a list of quirk names that should be enabled,
-separated by commas. Possible names are:
-
-* paragraph_end
-
-  Disables the kramdown restriction that at least one blank line has to
-  be used after a paragraph before a new block element can be started.
-
-  Note that if this quirk is used, lazy line wrapping does not fully
-  work anymore!
-
-* no_auto_typographic
-
-  Disables automatic conversion of some characters into their
-  corresponding typographic symbols (like `--` to em-dash etc).
-  This helps to achieve results closer to what GitHub Flavored
-  Markdown produces.
-
-Default: paragraph_end
-Used by: GFM parser
-EOF
-      val = simple_array_validator(val, :gfm_quirks)
-      val.map! {|v| str_to_sym(v.to_s)}
-      val
-    end
-
-  end
+require_relative 'gfm/options'
 
+module Kramdown
   module Parser
 
     # This class provides a parser implementation for the GFM dialect of Markdown.
     class GFM < Kramdown::Parser::Kramdown
 
-      VERSION = '1.0.1'
+      VERSION = '1.1.0'
+
+      attr_reader :paragraph_end
 
       def initialize(source, options)
         super
         @options[:auto_id_stripping] = true
         @id_counter = Hash.new(-1)
 
-        @span_parsers.delete(:line_break) if @options[:hard_wrap]
+        @span_parsers.delete(:line_break)       if @options[:hard_wrap]
         @span_parsers.delete(:typographic_syms) if @options[:gfm_quirks].include?(:no_auto_typographic)
+
         if @options[:gfm_quirks].include?(:paragraph_end)
           atx_header_parser = :atx_header_gfm_quirk
-          @paragraph_end = self.class::PARAGRAPH_END_GFM
+          @paragraph_end    = self.class::PARAGRAPH_END_GFM
         else
           atx_header_parser = :atx_header_gfm
-          @paragraph_end = self.class::PARAGRAPH_END
+          @paragraph_end    = self.class::PARAGRAPH_END
         end
 
         {codeblock_fenced: :codeblock_fenced_gfm,
@@ -93,6 +48,8 @@ EOF
         i = @span_parsers.index(:escaped_chars)
         @span_parsers[i] = :escaped_chars_gfm if i
         @span_parsers << :strikethrough_gfm
+
+        @hard_line_break = "#{@options[:hard_wrap] ? '' : '\\'}\n"
       end
 
       def parse
@@ -102,20 +59,8 @@ EOF
 
       def update_elements(element)
         element.children.map! do |child|
-          if child.type == :text &&
-              child.value.include?(hard_line_break = "#{@options[:hard_wrap] ? '' : '\\'}\n")
-            children = []
-            lines = child.value.split(hard_line_break, -1)
-            omit_trailing_br = (Kramdown::Element.category(element) == :block &&
-                                element.children[-1] == child && lines[-1].empty?)
-            lines.each_with_index do |line, index|
-              new_element_options = {location: child.options[:location] + index}
-
-              children << Element.new(:text, (index > 0 ? "\n#{line}" : line), nil, new_element_options)
-              children << Element.new(:br, nil, nil, new_element_options) if index < lines.size - 2 ||
-                (index == lines.size - 2 && !omit_trailing_br)
-            end
-            children
+          if child.type == :text && child.value.include?(@hard_line_break)
+            update_text_type(element, child)
           elsif child.type == :html_element
             child
           elsif child.type == :header && @options[:auto_ids] && !child.attr.key?('id')
@@ -133,22 +78,24 @@ EOF
         raw_text = +''
 
         append_text = lambda do |child|
-          if child.type == :text || child.type == :codespan || child.type == :math
+          case child.type
+          when :text, :codespan, :math
             raw_text << child.value
-          elsif child.type == :entity
+          when :entity
             raw_text << child.value.char
-          elsif child.type == :smart_quote
+          when :smart_quote
             raw_text << ::Kramdown::Utils::Entities.entity(child.value.to_s).char
-          elsif child.type == :typographic_sym
-            raw_text << if child.value == :laquo_space
+          when :typographic_sym
+            raw_text << case child.value
+                        when :laquo_space
                           "« "
-                        elsif child.value == :raquo_space
+                        when :raquo_space
                           " »"
                         else
                           ::Kramdown::Utils::Entities.entity(child.value.to_s).char
                         end
           else
-            child.children.each {|c| append_text.call(c) }
+            child.children.each { |c| append_text.call(c) }
           end
         end
 
@@ -156,18 +103,21 @@ EOF
         item.options[:raw_text] = raw_text
       end
 
-      NON_WORD_RE = /[^\p{Word}\- \t]/
+      NON_WORD_RE = /[^\p{Word}\- \t]/.freeze
 
       def generate_gfm_header_id(text)
         result = text.downcase
         result.gsub!(NON_WORD_RE, '')
         result.tr!(" \t", '-')
+
         @id_counter[result] += 1
-        result << (@id_counter[result] > 0 ? "-#{@id_counter[result]}" : '')
+        counter_result = @id_counter[result]
+        result << "-#{counter_result}" if counter_result > 0
+
         @options[:auto_id_prefix] + result
       end
 
-      ATX_HEADER_START = /^(?<level>\#{1,6})[\t ]+(?<contents>.*)\n/
+      ATX_HEADER_START = /^(?<level>\#{1,6})[\t ]+(?<contents>.*)\n/.freeze
       define_parser(:atx_header_gfm, ATX_HEADER_START, nil, 'parse_atx_header')
       define_parser(:atx_header_gfm_quirk, ATX_HEADER_START)
 
@@ -176,16 +126,17 @@ EOF
         text, id = parse_header_contents
         text.sub!(/[\t ]#+\z/, '') && text.rstrip!
         return false if text.empty?
+
         add_header(@src["level"].length, text, id)
         true
       end
 
-      FENCED_CODEBLOCK_START = /^[ ]{0,3}[~`]{3,}/
-      FENCED_CODEBLOCK_MATCH = /^[ ]{0,3}(([~`]){3,})\s*?((\S+?)(?:\?\S*)?)?\s*?\n(.*?)^[ ]{0,3}\1\2*\s*?\n/m
+      FENCED_CODEBLOCK_START = /^[ ]{0,3}[~`]{3,}/.freeze
+      FENCED_CODEBLOCK_MATCH = /^[ ]{0,3}(([~`]){3,})\s*?((\S+?)(?:\?\S*)?)?\s*?\n(.*?)^[ ]{0,3}\1\2*\s*?\n/m.freeze
       define_parser(:codeblock_fenced_gfm, FENCED_CODEBLOCK_START, nil, 'parse_codeblock_fenced')
 
-      STRIKETHROUGH_DELIM = /~~/
-      STRIKETHROUGH_MATCH = /#{STRIKETHROUGH_DELIM}[^\s~](.*?)[^\s~]#{STRIKETHROUGH_DELIM}/m
+      STRIKETHROUGH_DELIM = /~~/.freeze
+      STRIKETHROUGH_MATCH = /#{STRIKETHROUGH_DELIM}(?!\s|~).*?[^\s~]#{STRIKETHROUGH_DELIM}/m.freeze
       define_parser(:strikethrough_gfm, STRIKETHROUGH_MATCH, '~~')
 
       def parse_strikethrough_gfm
@@ -204,24 +155,29 @@ EOF
         el
       end
 
+      LIST_TYPES = [:ul, :ol].freeze
+
       # To handle task-lists we override the parse method for lists, converting matching text into
       # checkbox input elements where necessary (as well as applying classes to the ul/ol and li
       # elements).
       def parse_list
         super
-        current_list = @tree.children.select {|element| [:ul, :ol].include?(element.type) }.last
+        current_list = @tree.children.select { |element| LIST_TYPES.include?(element.type) }.last
 
-        is_tasklist = false
+        is_tasklist   = false
         box_unchecked = '<input type="checkbox" class="task-list-item-checkbox" disabled="disabled" />'
-        box_checked = '<input type="checkbox" class="task-list-item-checkbox" ' \
+        box_checked   = '<input type="checkbox" class="task-list-item-checkbox" ' \
           'disabled="disabled" checked="checked" />'
 
         current_list.children.each do |li|
-          next unless !li.children.empty? && li.children[0].type == :p
+          list_items = li.children
+          next unless !list_items.empty? && list_items[0].type == :p
+
           # li -> p -> raw_text
-          checked = li.children[0].children[0].value.gsub!(/\A\s*\[ \]\s+/, box_unchecked)
-          unchecked = li.children[0].children[0].value.gsub!(/\A\s*\[x\]\s+/i, box_checked)
-          is_tasklist ||= (!checked.nil? || !unchecked.nil?)
+          descendant = list_items[0].children[0].value
+          checked    = descendant.gsub!(/\A\s*\[ \]\s+/,  box_unchecked)
+          unchecked  = descendant.gsub!(/\A\s*\[x\]\s+/i, box_checked)
+          is_tasklist ||= checked || unchecked
 
           li.attr['class'] = 'task-list-item' if is_tasklist
         end
@@ -231,14 +187,32 @@ EOF
         true
       end
 
-      ESCAPED_CHARS_GFM = /\\([\\.*_+`<>()\[\]{}#!:\|"'\$=\-~])/
+      ESCAPED_CHARS_GFM = /\\([\\.*_+`<>()\[\]{}#!:\|"'\$=\-~])/.freeze
       define_parser(:escaped_chars_gfm, ESCAPED_CHARS_GFM, '\\\\', :parse_escaped_chars)
 
-      PARAGRAPH_END_GFM = /#{LAZY_END}|#{LIST_START}|#{ATX_HEADER_START}|
-                           #{DEFINITION_LIST_START}|#{BLOCKQUOTE_START}|#{FENCED_CODEBLOCK_START}/x
+      PARAGRAPH_END_GFM = Regexp.union(
+        LAZY_END, LIST_START, ATX_HEADER_START, DEFINITION_LIST_START,
+        BLOCKQUOTE_START, FENCED_CODEBLOCK_START
+      )
+
+      private
+
+      def update_text_type(element, child)
+        children = []
+        lines = child.value.split(@hard_line_break, -1)
+        omit_trailing_br = (lines[-1].empty? && Kramdown::Element.category(element) == :block &&
+                            element.children[-1] == child)
+
+        lines.each_with_index do |line, index|
+          new_element_options = {location: child.options[:location] + index}
+          children << Element.new(:text, (index > 0 ? "\n#{line}" : line), nil, new_element_options)
+
+          if index < lines.size - 2 || (index == lines.size - 2 && !omit_trailing_br)
+            children << Element.new(:br, nil, nil, new_element_options)
+          end
+        end
 
-      def paragraph_end
-        @paragraph_end
+        children
       end
 
     end

data/lib/kramdown/parser/gfm/options.rb

@@ -0,0 +1,60 @@
+# -*- coding: utf-8; frozen_string_literal: true -*-
+#
+#--
+# Copyright (C) 2019 Thomas Leitner <t_leitner@gmx.at>
+#
+# This file is part of kramdown-parser-gfm which is licensed under the MIT.
+#++
+#
+
+module Kramdown
+  module Options
+
+    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
+
+    define(:gfm_quirks, Object, [:paragraph_end], <<~EOF) do |val|
+      Enables a set of GFM specific quirks
+
+      The way how GFM is transformed on Github often differs from the way
+      kramdown does things. Many of these differences are negligible but
+      others are not.
+
+      This option allows one to enable/disable certain GFM quirks, i.e. ways
+      in which GFM parsing differs from kramdown parsing.
+
+      The value has to be a list of quirk names that should be enabled,
+      separated by commas. Possible names are:
+
+      * paragraph_end
+
+        Disables the kramdown restriction that at least one blank line has to
+        be used after a paragraph before a new block element can be started.
+
+        Note that if this quirk is used, lazy line wrapping does not fully
+        work anymore!
+
+      * no_auto_typographic
+
+        Disables automatic conversion of some characters into their
+        corresponding typographic symbols (like `--` to em-dash etc).
+        This helps to achieve results closer to what GitHub Flavored
+        Markdown produces.
+
+      Default: paragraph_end
+      Used by: GFM parser
+    EOF
+      val = simple_array_validator(val, :gfm_quirks)
+      val.map! { |v| str_to_sym(v.to_s) }
+      val
+    end
+
+  end
+end

data/test/test_files.rb

@@ -18,13 +18,13 @@ Encoding.default_external = 'utf-8'
 class TestFiles < Minitest::Test
 
   # Generate test methods for gfm-to-html conversion
-  Dir[File.dirname(__FILE__) + '/testcases/**/*.text'].each do |text_file|
+  Dir[__dir__ + '/testcases/**/*.text'].each do |text_file|
     basename = text_file.sub(/\.text$/, '')
 
     html_file = basename + '.html'
     next unless File.exist?(html_file)
 
-    define_method('test_gfm_' + text_file.tr('.', '_') + "_to_html") do
+    define_method('test_gfm_' + File.basename(text_file, '.*') + '_to_html') do
       opts_file = basename + '.options'
       opts_file = File.join(File.dirname(html_file), 'options') if !File.exist?(opts_file)
       options = File.exist?(opts_file) ? YAML::load(File.read(opts_file)) : {auto_ids: false, footnote_nr: 1}

data/test/testcases/backticks_syntax.html

@@ -7,14 +7,8 @@
 <pre><code>Unbalanced bottom heavy
 </code></pre>
 
-<div class="language-ruby highlighter-coderay"><div class="CodeRay">
-  <div class="code"><pre><span class="line-numbers"><a href="#n1" name="n1">1</a></span>language no space
-</pre></div>
-</div>
-</div>
+<div class="language-ruby highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">language</span> <span class="n">no</span> <span class="n">space</span>
+</code></pre></div></div>
 
-<div class="language-ruby highlighter-coderay"><div class="CodeRay">
-  <div class="code"><pre><span class="line-numbers"><a href="#n1" name="n1">1</a></span>language with space
-</pre></div>
-</div>
-</div>
+<div class="language-ruby highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">language</span> <span class="n">with</span> <span class="n">space</span>
+</code></pre></div></div>

data/test/testcases/codeblock_fenced.html

@@ -1,9 +1,9 @@
 <p>normal</p>
 
-<pre><code class="language-ruby">require 'kramdown'
+<div class="language-ruby highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="nb">require</span> <span class="s1">'kramdown'</span>
 
-Kramdown::Document.new(text).to_html
-</code></pre>
+<span class="no">Kramdown</span><span class="o">::</span><span class="no">Document</span><span class="p">.</span><span class="nf">new</span><span class="p">(</span><span class="n">text</span><span class="p">).</span><span class="nf">to_html</span>
+</code></pre></div></div>
 
 <p>indent with tab</p>
 
@@ -16,5 +16,5 @@ Kramdown::Document.new(text).to_html
 
 <p>indent with 2 spaces</p>
 
-<pre><code class="language-js">  console.log("hello");
-</code></pre>
+<div class="language-js highlighter-rouge"><div class="highlight"><pre class="highlight"><code>  <span class="nx">console</span><span class="p">.</span><span class="nx">log</span><span class="p">(</span><span class="s2">"hello"</span><span class="p">);</span>
+</code></pre></div></div>

data/test/testcases/strikethrough.html

@@ -25,3 +25,9 @@ test<br />
 <p>This should ~~not be struck.</p>
 
 <p>This <del>is a complex <em>strike</em> through *test ~~with nesting</del> involved* here~~.</p>
+
+<p>This <del>is a complex <em>strike</em> through *test</del> with apparent nesting <del>involved* here</del>.</p>
+
+<p><del>中文</del></p>
+
+<p><del>a</del></p>

data/test/testcases/strikethrough.text

@@ -25,3 +25,9 @@ I ~~don't even~~~ have an extra tilde.
 This should ~~not be struck.
 
 This ~~is a complex *strike* through *test ~~with nesting~~ involved* here~~.
+
+This ~~is a complex *strike* through *test~~ with apparent nesting ~~involved* here~~.
+
+~~中文~~
+
+~~a~~

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: kramdown-parser-gfm
 version: !ruby/object:Gem::Version
-  version: 1.0.1
+  version: 1.1.0
 platform: ruby
 authors:
 - Thomas Leitner
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-01-13 00:00:00.000000000 Z
+date: 2019-05-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: kramdown
@@ -35,13 +35,12 @@ files:
 - VERSION
 - lib/kramdown-parser-gfm.rb
 - lib/kramdown/parser/gfm.rb
+- lib/kramdown/parser/gfm/options.rb
 - test/test_files.rb
 - test/testcases/atx_header.html
 - test/testcases/atx_header.text
-- test/testcases/backticks_disable_highlighting.html
-- test/testcases/backticks_disable_highlighting.options
-- test/testcases/backticks_disable_highlighting.text
 - test/testcases/backticks_syntax.html
+- test/testcases/backticks_syntax.options
 - test/testcases/backticks_syntax.text
 - test/testcases/codeblock_fenced.html
 - test/testcases/codeblock_fenced.options

data/test/testcases/backticks_disable_highlighting.html

@@ -1,2 +0,0 @@
-<pre><code class="language-ruby">Kramdown::Document.new(text, :input =&gt; 'GFM')
-</code></pre>

data/test/testcases/backticks_disable_highlighting.text

@@ -1,3 +0,0 @@
-```ruby
-Kramdown::Document.new(text, :input => 'GFM')
-```