reverse_markdown 1.2.0 → 2.1.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 69b75c5dec924f267e5861ed24edafa23a8bb12f3e03cd7068e00ae19406424b
-  data.tar.gz: d53a1f8630a532183b491e982250a3bb175d9ed84188103535255e27ff8d39a7
+  metadata.gz: cffa2a16f5ad4187cb23a2e6a1015121b943f1c83a688308cf0a480ec15d3c49
+  data.tar.gz: 6941ad7c07005ff4d5c115fd894ee2a0cf40a09367833268f4c55c018f30263a
 SHA512:
-  metadata.gz: '02949ddc3b08f23f07148bbda7e00a07214d3bc423ec880284c938e30fa872e305ca66fe2b1a9af796c5225dc935fa06c4e19f4085c75d5eaa0b0023eca45961'
-  data.tar.gz: 7c58e5b6fc0560de0e3ef879685db3a8d8f541b07d471b7747492e9918a40334d84a66fcc1c8f76bff061990c661c9b53730e994b435aab28e634ff12cfd6968
+  metadata.gz: 620ce03beae7238accdc6836e025dc7b19fe308a7bcbcd7143dc7472d09e7d25758a3f6c2080d5d75e60fee662bc87ab200f177b5b6f41fa5958bde4b569a49e
+  data.tar.gz: ea69f20a1e70e4f41d6024502af362351ccaf6ec8936b4dcadc2414202e994cdf8ddf08ebbd829c0722c373bbe7e87a223c3c913bf6d845be9308ef418f3be75

data/.travis.yml

@@ -1,23 +1,17 @@
-# before_install:
-#   - gem install bundler
+language: ruby
+cache: bundler
 
 rvm:
-  - 1.9.3
-  - 2.0.0
-  - 2.1.0
-  - 2.1.5
-  - 2.2.0
-  - 2.2.4
-  - 2.2.5
-  - 2.3.0
-  - 2.3.1
-  - 2.4.2
-  - 2.5.3
-  - 2.6.2
+  - 2.0
+  - 2.1
+  - 2.2
+  - 2.3
+  - 2.4
+  - 2.5
+  - 2.6
+  - 2.7
   - jruby-9.2.8.0
 
-script: "bundle exec rake spec"
-
 notifications:
   disabled: false
   recipients:

data/CHANGELOG.md

@@ -1,6 +1,23 @@
 # Change Log
 All notable changes to this project will be documented in this file.
 
+## 2.1.1 - October 2021
+- Fixes unintentional newline characters within lists with paragraphs, thanks @diogoosorio, see #93
+- Lets \n to be present in <pre> tag. solves #77 #78, thanks @shivabhusal
+
+## 2.1.0 - May 2020
+- Add support for `figure` tags, see #86, thanks @anshul78
+
+## 2.0.0 - March 2020
+- BREAKING: Dropped support for ruby 1.9.3
+- Add support for `details` and `summary` tags, see #85
+
+## 1.4.0 – January 2020
+- BREAKING: jump links will no longer be ignored but treated as links, see #82
+
+## 1.3.0 - September 2019
+- Add support for `s` HTML tag, thanks @fauno
+
 ## 1.2.0 - August 2019
 - Handle windows `\r\n` within text blocks, thanks for reporting @krisdigital
 - Handle paragraphs in `li` tags, thanks @gstamp

data/README.md

@@ -2,7 +2,7 @@
 
 Transform html into markdown. Useful for example if you want to import html into your markdown based application.
 
-[![Build Status](https://secure.travis-ci.org/xijo/reverse_markdown.png?branch=master)](https://travis-ci.org/xijo/reverse_markdown) [![Gem Version](https://badge.fury.io/rb/reverse_markdown.png)](http://badge.fury.io/rb/reverse_markdown) [![Code Climate](https://codeclimate.com/github/xijo/reverse_markdown.png)](https://codeclimate.com/github/xijo/reverse_markdown) [![Code Climate](https://codeclimate.com/github/xijo/reverse_markdown/coverage.png)](https://codeclimate.com/github/xijo/reverse_markdown)
+[![Build Status](https://secure.travis-ci.org/xijo/reverse_markdown.svg?branch=master)](https://travis-ci.org/xijo/reverse_markdown) [![Gem Version](https://badge.fury.io/rb/reverse_markdown.svg)](http://badge.fury.io/rb/reverse_markdown) [![Code Climate](https://codeclimate.com/github/xijo/reverse_markdown.svg)](https://codeclimate.com/github/xijo/reverse_markdown) [![Code Climate](https://codeclimate.com/github/xijo/reverse_markdown/coverage.png)](https://codeclimate.com/github/xijo/reverse_markdown)
 
 ## Changelog
 
@@ -11,7 +11,7 @@ See [Change Log](CHANGELOG.md)
 ## Requirements
 
 1. [Nokogiri](http://nokogiri.org/)
-2. Ruby 1.9.3 or higher
+2. Ruby 2.0.0 or higher
 
 ## Installation
 
@@ -29,7 +29,7 @@ gem 'reverse_markdown'
 
 ## Features
 
-- Supports all the established html tags like `h1`, `h2`, `h3`, `h4`, `h5`, `h6`, `p`, `em`, `strong`, `i`, `b`, `blockquote`, `code`, `img`, `a`, `hr`, `li`, `ol`, `ul`, `table`, `tr`, `th`, `td`, `br`
+- Supports all the established html tags like `h1`, `h2`, `h3`, `h4`, `h5`, `h6`, `p`, `em`, `strong`, `i`, `b`, `blockquote`, `code`, `img`, `a`, `hr`, `li`, `ol`, `ul`, `table`, `tr`, `th`, `td`, `br`, `figure`
 - Module based - if you miss a tag, just add it
 - Can deal with nested lists
 - Inline and block code is supported

data/Rakefile

@@ -10,5 +10,5 @@ task :default => :spec
 
 desc 'Open an irb session preloaded with this library'
 task :console do
-  sh 'irb -rubygems -I lib -r reverse_markdown.rb'
+  sh 'irb -I lib -r reverse_markdown.rb'
 end

data/lib/reverse_markdown/cleaner.rb

@@ -59,6 +59,11 @@ module ReverseMarkdown
       string.gsub(/(\*\*|~~|__)\s([\.!\?'"])/, "\\1".strip + "\\2")
     end
 
+    def force_encoding(string)
+      ReverseMarkdown.config.force_encoding or return string
+      string.encode('UTF-8', 'binary', invalid: :replace, undef: :replace, replace: '')
+    end
+
     private
 
     def preserve_border_whitespaces(string, options = {}, &block)

data/lib/reverse_markdown/config.rb

@@ -1,10 +1,11 @@
 module ReverseMarkdown
   class Config
-    attr_accessor :unknown_tags, :github_flavored, :tag_border
+    attr_writer :unknown_tags, :github_flavored, :tag_border, :force_encoding
 
     def initialize
       @unknown_tags     = :pass_through
       @github_flavored  = false
+      @force_encoding   = false
       @em_delimiter     = '_'.freeze
       @strong_delimiter = '**'.freeze
       @inline_options   = {}
@@ -29,5 +30,9 @@ module ReverseMarkdown
     def tag_border
       @inline_options[:tag_border] || @tag_border
     end
+
+    def force_encoding
+      @inline_options[:force_encoding] || @force_encoding
+    end
   end
 end

data/lib/reverse_markdown/converters/a.rb

@@ -6,7 +6,7 @@ module ReverseMarkdown
         href  = node['href']
         title = extract_title(node)
 
-        if href.to_s.start_with?('#') || href.to_s.empty? || name.empty?
+        if href.to_s.empty? || name.empty?
           name
         else
           link = "[#{name}](#{href}#{title})"

data/lib/reverse_markdown/converters/del.rb

@@ -20,6 +20,7 @@ module ReverseMarkdown
     end
 
     register :strike, Del.new
+    register :s,      Del.new
     register :del,    Del.new
   end
 end

data/lib/reverse_markdown/converters/details.rb

@@ -0,0 +1,25 @@
+module ReverseMarkdown
+    module Converters
+      class Details < Base
+        def convert(node, state = {})
+          content = treat_children(node, state.merge(already_processed: true))
+          if disabled? || content.strip.empty? || state[:already_processed]
+            content
+          else
+            "##{content}"
+          end
+        end
+
+        def enabled?
+          ReverseMarkdown.config.github_flavored
+        end
+
+        def disabled?
+          !enabled?
+        end
+      end
+
+      register :details, Details.new
+      register :summary, Details.new
+    end
+end

data/lib/reverse_markdown/converters/figcaption.rb

@@ -0,0 +1,15 @@
+module ReverseMarkdown
+  module Converters
+    class FigCaption < Base
+      def convert(node, state = {})
+        if node.text.strip.empty?
+          ""
+        else
+          "\n" << "_#{node.text.strip}_" << "\n"
+        end
+      end
+    end
+
+    register :figcaption, FigCaption.new
+  end
+end

data/lib/reverse_markdown/converters/figure.rb

@@ -0,0 +1,12 @@
+module ReverseMarkdown
+  module Converters
+    class Figure < Base
+      def convert(node, state = {})
+        content = treat_children(node, state)
+        "\n#{content.strip}\n"
+      end
+    end
+
+    register :figure, Figure.new
+  end
+end

data/lib/reverse_markdown/converters/li.rb

@@ -2,8 +2,8 @@ module ReverseMarkdown
   module Converters
     class Li < Base
       def convert(node, state = {})
-        contains_child_paragraph = node.children.first ? node.children.first.name == 'p' : false
-        content_node             = contains_child_paragraph ? node.children.first : node
+        contains_child_paragraph = node.first_element_child ? node.first_element_child.name == 'p' : false
+        content_node             = contains_child_paragraph ? node.first_element_child : node
         content                  = treat_children(content_node, state)
         indentation              = indentation_from(state)
         prefix                   = prefix_for(node)

data/lib/reverse_markdown/converters/pre.rb

@@ -15,8 +15,8 @@ module ReverseMarkdown
       # Override #treat as proposed in https://github.com/xijo/reverse_markdown/pull/69
       def treat(node, state)
         case node.name
-        when 'code'
-          node.text
+        when 'code', 'text'
+          node.text.strip
         when 'br'
           "\n"
         else

data/lib/reverse_markdown/version.rb

@@ -1,3 +1,3 @@
 module ReverseMarkdown
-  VERSION = '1.2.0'
+  VERSION = '2.1.1'
 end

data/lib/reverse_markdown.rb

@@ -1,4 +1,3 @@
-require 'digest'
 require 'nokogiri'
 require 'reverse_markdown/version'
 require 'reverse_markdown/errors'
@@ -14,7 +13,10 @@ require 'reverse_markdown/converters/code'
 require 'reverse_markdown/converters/del'
 require 'reverse_markdown/converters/div'
 require 'reverse_markdown/converters/drop'
+require 'reverse_markdown/converters/details'
 require 'reverse_markdown/converters/em'
+require 'reverse_markdown/converters/figcaption'
+require 'reverse_markdown/converters/figure'
 require 'reverse_markdown/converters/h'
 require 'reverse_markdown/converters/hr'
 require 'reverse_markdown/converters/ignore'
@@ -33,15 +35,17 @@ require 'reverse_markdown/converters/tr'
 module ReverseMarkdown
 
   def self.convert(input, options = {})
-    root = case input
-      when String                  then Nokogiri::HTML(input).root
-      when Nokogiri::XML::Document then input.root
-      when Nokogiri::XML::Node     then input
-    end
+    config.with(options) do
+      input = cleaner.force_encoding(input.to_s)
 
-    root or return ''
+      root = case input
+        when String                  then Nokogiri::HTML(input).root
+        when Nokogiri::XML::Document then input.root
+        when Nokogiri::XML::Node     then input
+      end
+
+      root or return ''
 
-    config.with(options) do
       result = ReverseMarkdown::Converters.lookup(root.name).convert(root)
       cleaner.tidy(result)
     end

data/reverse_markdown.gemspec

@@ -11,7 +11,6 @@ Gem::Specification.new do |s|
   s.summary     = %q{Convert html code into markdown.}
   s.description = %q{Map simple html back into markdown, e.g. if you want to import existing html data in your application.}
   s.licenses    = ["WTFPL"]
-  s.rubyforge_project = "reverse_markdown"
 
   s.files         = `git ls-files`.split("\n")
   s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
@@ -24,6 +23,6 @@ Gem::Specification.new do |s|
   s.add_development_dependency 'simplecov'
   s.add_development_dependency 'rake'
   s.add_development_dependency 'kramdown'
-  # s.add_development_dependency 'byebug'
+  s.add_development_dependency 'byebug'
   s.add_development_dependency 'codeclimate-test-reporter'
 end

data/spec/assets/lists.html

@@ -44,6 +44,8 @@
       </li>
     </ul>
 
+    <ul><li> <p>I don't want to cleanup after the party!</p> </li></ul>
+
     <ul>
       <li>
         <p>li 1, p 1</p>

data/spec/components/anchors_spec.rb

@@ -20,7 +20,7 @@ describe ReverseMarkdown do
   context "links to ignore" do
     it { is_expected.to include ' ignore anchor tags with no link text ' }
     it { is_expected.to include ' not ignore [![An Image](image.png)](foo.html) anchor tags with images' }
-    it { is_expected.to include ' pass through the text of internal jumplinks without treating them as links ' }
+    it { is_expected.to include ' pass through the text of [internal jumplinks](#content) without treating them as links ' }
     it { is_expected.to include ' pass through the text of anchor tags with no href without treating them as links ' }
   end
 

data/spec/components/lists_spec.rb

@@ -35,7 +35,8 @@ describe ReverseMarkdown do
   end
 
   context "lists containing embedded <p> tags" do
-    xit { is_expected.to match /\n- I want to have a party at my house!\n/ }
+    it { is_expected.to match /\n- I want to have a party at my house!\n/ }
+    it { is_expected.to match /\n- I don't want to cleanup after the party!\n/ }
   end
 
   context "list item containing multiple <p> tags" do

data/spec/components/paragraphs_spec.rb

@@ -1,7 +1,6 @@
 require 'spec_helper'
 
 describe ReverseMarkdown do
-
   let(:input)    { File.read('spec/assets/paragraphs.html') }
   let(:document) { Nokogiri::HTML(input) }
   subject { ReverseMarkdown.convert(input) }

data/spec/components/quotation_spec.rb

@@ -1,12 +1,10 @@
 require 'spec_helper'
 
 describe ReverseMarkdown do
-
   let(:input)    { File.read('spec/assets/quotation.html') }
   let(:document) { Nokogiri::HTML(input) }
   subject { ReverseMarkdown.convert(input) }
 
   it { is_expected.to match /^    Block of code$/ }
   it { is_expected.to include "\n> First quoted paragraph\n> \n> Second quoted paragraph" }
-
 end

data/spec/lib/reverse_markdown/converters/del_spec.rb

@@ -11,6 +11,11 @@ describe ReverseMarkdown::Converters::Del do
       expect(converter.convert(input)).to eq '~~deldeldel~~'
     end
 
+    it 'converts the input as expected' do
+      input = node_for('<s>strike that</s>')
+      expect(converter.convert(input)).to eq '~~strike that~~'
+    end
+
     it 'skips empty tags' do
       input = node_for('<del></del>')
       expect(converter.convert(input)).to eq ''

data/spec/lib/reverse_markdown/converters/details_spec.rb

@@ -0,0 +1,23 @@
+require 'spec_helper'
+
+describe ReverseMarkdown::Converters::Details do
+  let(:converter) { ReverseMarkdown::Converters::Details.new }
+
+  context 'for standard markdown' do
+    before { ReverseMarkdown.config.github_flavored = false }
+
+    it 'handles details tags correctly' do
+      node = node_for("<details>foo</details>")
+      expect(converter.convert(node)).to include "foo"
+    end
+  end
+
+  context 'for github_flavored markdown' do
+    before { ReverseMarkdown.config.github_flavored = true }
+
+    it 'handles details tags correctly' do
+      node = node_for("<details>foo</details>")
+      expect(converter.convert(node)).to include "#foo"
+    end
+  end
+end

data/spec/lib/reverse_markdown/converters/figure_spec.rb

@@ -0,0 +1,17 @@
+require 'spec_helper'
+
+describe ReverseMarkdown::Converters::Figure do
+
+  let(:converter) { ReverseMarkdown::Converters::Figure.new }
+
+  it 'handles figure tags with figcaption correctly' do
+    node = node_for("<figure><img src='image.jpg' alt='img_alt'><figcaption>Figure Caption</figcaption></figure>")
+    expect(converter.convert(node)).to eq "\n![img_alt](image.jpg)\n_Figure Caption_\n"
+  end
+
+  it 'handles figure tags without figcaption correctly' do
+    node = node_for("<figure><img src='image.jpg' alt='img_alt'></figure>")
+    expect(converter.convert(node)).to eq "\n![img_alt](image.jpg)\n"
+  end
+
+end

data/spec/lib/reverse_markdown/converters/pre_spec.rb

@@ -12,10 +12,15 @@ describe ReverseMarkdown::Converters::Pre do
       expect(converter.convert(node)).to include "    puts foo\n"
     end
 
-    it 'preserves new lines' do
+    it 'preserves new lines as <br>' do
       node = node_for("<pre>one<br>two<br>three</pre>")
       expect(converter.convert(node)).to include "\n\n    one\n    two\n    three\n\n"
     end
+    
+    it 'preserves new lines as <br> and \n' do
+      node = node_for("<pre>one\ntwo\nthree<br>four</pre>")
+      expect(converter.convert(node)).to include "\n\n    one\n    two\n    three\n    four\n\n"
+    end
 
     it 'handles code tags correctly' do
       node = node_for("<pre><code>foobar</code></pre>")
@@ -41,6 +46,11 @@ describe ReverseMarkdown::Converters::Pre do
       expect(converter.convert(node)).to include "```\nfoo\nbar\n```"
     end
 
+    it 'preserves new lines as <br> and \n' do
+      node = node_for("<pre>one\ntwo\nthree<br>four</pre>")
+      expect(converter.convert(node)).to include "```\none\ntwo\nthree\nfour\n```"
+    end
+
     it 'handles code tags correctly' do
       node = node_for("<pre><code>foobar</code></pre>")
       expect(converter.convert(node)).to include "```\nfoobar\n```"

data/spec/lib/reverse_markdown_spec.rb

@@ -33,5 +33,15 @@ describe ReverseMarkdown do
       end
       expect(ReverseMarkdown.config.github_flavored).to eq true
     end
+
+    describe 'force_encoding option', jruby: :exclude do
+      it 'raises invalid byte sequence in UTF-8 exception' do
+        expect { ReverseMarkdown.convert("hi \255") }.to raise_error(ArgumentError)
+      end
+
+      it 'handles invalid byte sequence if option is set' do
+        expect(ReverseMarkdown.convert("hi \255", force_encoding: true)).to eq "hi\n\n"
+      end
+    end
   end
 end

data/spec/spec_helper.rb

@@ -14,6 +14,14 @@ RSpec.configure do |config|
   config.after(:each) do
     ReverseMarkdown.instance_variable_set(:@config, nil)
   end
+
+  config.around(jruby: :exclude) do |example|
+    if RUBY_ENGINE == 'jruby'
+      example.metadata[:skip] = true
+    else
+      example.call
+    end
+  end
 end
 
 def node_for(html)

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: reverse_markdown
 version: !ruby/object:Gem::Version
-  version: 1.2.0
+  version: 2.1.1
 platform: ruby
 authors:
 - Johannes Opper
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-08-22 00:00:00.000000000 Z
+date: 2021-10-31 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -80,6 +80,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: byebug
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: codeclimate-test-reporter
   requirement: !ruby/object:Gem::Requirement
@@ -123,9 +137,12 @@ files:
 - lib/reverse_markdown/converters/bypass.rb
 - lib/reverse_markdown/converters/code.rb
 - lib/reverse_markdown/converters/del.rb
+- lib/reverse_markdown/converters/details.rb
 - lib/reverse_markdown/converters/div.rb
 - lib/reverse_markdown/converters/drop.rb
 - lib/reverse_markdown/converters/em.rb
+- lib/reverse_markdown/converters/figcaption.rb
+- lib/reverse_markdown/converters/figure.rb
 - lib/reverse_markdown/converters/h.rb
 - lib/reverse_markdown/converters/hr.rb
 - lib/reverse_markdown/converters/ignore.rb
@@ -173,6 +190,8 @@ files:
 - spec/lib/reverse_markdown/converters/blockquote_spec.rb
 - spec/lib/reverse_markdown/converters/br_spec.rb
 - spec/lib/reverse_markdown/converters/del_spec.rb
+- spec/lib/reverse_markdown/converters/details_spec.rb
+- spec/lib/reverse_markdown/converters/figure_spec.rb
 - spec/lib/reverse_markdown/converters/li_spec.rb
 - spec/lib/reverse_markdown/converters/pre_spec.rb
 - spec/lib/reverse_markdown/converters/strong_spec.rb
@@ -199,7 +218,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.3
+rubygems_version: 3.1.4
 signing_key: 
 specification_version: 4
 summary: Convert html code into markdown.
@@ -234,6 +253,8 @@ test_files:
 - spec/lib/reverse_markdown/converters/blockquote_spec.rb
 - spec/lib/reverse_markdown/converters/br_spec.rb
 - spec/lib/reverse_markdown/converters/del_spec.rb
+- spec/lib/reverse_markdown/converters/details_spec.rb
+- spec/lib/reverse_markdown/converters/figure_spec.rb
 - spec/lib/reverse_markdown/converters/li_spec.rb
 - spec/lib/reverse_markdown/converters/pre_spec.rb
 - spec/lib/reverse_markdown/converters/strong_spec.rb