reverse_markdown 0.5.1 → 0.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 2cd83465e91f441918e2b09ff1a9aca35b029e74
-  data.tar.gz: b605fad98b1666375bc80a1d16db02388a6aa43a
+  metadata.gz: 345b5116f393914034fa05e3ceae0f7cabbda791
+  data.tar.gz: ecc2a58d1b46fb2c338d95009d2866239b4de880
 SHA512:
-  metadata.gz: aad0b3de89e84616aa8c1de8af86949a3ae6559c90ed1361aac5e747f163b5e419fdebaab60288dfe0da3153890a5320fb80f0ee575800dcf3c7e49be5b0cc3d
-  data.tar.gz: dfde7c437ca43d2a87ed4d009b4870766b27e81e75a708092777b709eeac4795fd441c2e9652f2db91e59d02ec1131bf7016d0d6513e597d7618c93589c6b26c
+  metadata.gz: d509a043b014bd9e6f72e56bb728befc8923668646b054e7ea6b4cd8576e45e2130a51d1a3100e87c61b518be80e47078b1d19a741e3469ff835790cf901d543
+  data.tar.gz: f199c4efb681293e100f7c5bfbd7436c6ea194273b3a7e76509ec6387f689ceabdfeb1838de8a8e5de976802f6f7e3945f6458aaa6a01d71751c160d1402c286

data/.gitignore

@@ -3,6 +3,7 @@
 .rvmrc
 .ruby-version
 .ruby-gemset
+.codeclimate
 Gemfile.lock
 pkg/*
 coverage/*

data/.rspec

@@ -0,0 +1 @@
+--color

data/CHANGELOG.md

@@ -0,0 +1,32 @@
+# Change Log
+All notable changes to this project will be documented in this file.
+
+
+## 0.6.0 - September 2014
+### Added
+- Ignore `col` and `colgroup` tags
+- Bypass `thead` and `tbody` tags to show the tables correctly
+
+### Changed
+- Eliminate ruby warnings on load (thx @vsipuli)
+- Treat newlines within text nodes as space
+- Remove whitespace between inline tags and punctuation characters
+
+
+## 0.5.1 - April 2014
+### Added
+- Adds support for ruby versions 1.9.3 back in
+- More options for handling of unknown tags
+
+### Changed
+- Bugfixes in `li` indentation behavior
+
+
+## 0.5.0 - March 2014
+**There were some breaking changes, please make sure you don't miss them:**
+
+1. Only ruby versions 2.0.0 or above are supported
+2. There is no `Mapper` class any more. Just use `ReverseMarkdown.convert(input, options)`
+3. Config option `github_style_code_blocks` changed its name to `github_flavored`
+
+Please open an issue and let me know about it if you have any trouble with the new version.

data/README.md

@@ -6,22 +6,7 @@ Transform html into markdown. Useful for example if you want to import html into
 
 ## Changelog
 
-### 0.5.1 - April 2014
-
-1. Adds support for ruby versions 1.9.3 back in
-2. More options for handling of unknown tags
-3. Bugfixes in `li` indentation behavior
-
-### 0.5.0 - March 2014
-
-There were some breaking changes, please make sure you don't miss them:
-
-1. Only ruby versions 2.0.0 or above are supported
-2. There is no `Mapper` class any more. Just use `ReverseMarkdown.convert(input, options)`
-3. Config option `github_style_code_blocks` changed its name to `github_flavored`
-
-Please open an issue and let me know about it if you have any trouble with the new version.
-
+See [Change Log](CHANGELOG.md)
 
 ## Requirements
 

data/Rakefile

@@ -1,10 +1,14 @@
-require "bundler/gem_tasks"
+require 'bundler/gem_tasks'
+
+if File.exist?('.codeclimate')
+  ENV["CODECLIMATE_REPO_TOKEN"] = File.read('.codeclimate').strip
+end
 
 require 'rspec/core/rake_task'
 RSpec::Core::RakeTask.new(:spec)
 task :default => :spec
 
-desc "Open an irb session preloaded with this library"
+desc 'Open an irb session preloaded with this library'
 task :console do
-  sh "irb -rubygems -I lib -r reverse_markdown.rb"
+  sh 'irb -rubygems -I lib -r reverse_markdown.rb'
 end

data/lib/reverse_markdown/cleaner.rb

@@ -2,7 +2,11 @@ module ReverseMarkdown
   class Cleaner
 
     def tidy(string)
-      clean_tag_borders(remove_leading_newlines(remove_newlines(remove_inner_whitespaces(string))))
+      result = remove_inner_whitespaces(string)
+      result = remove_newlines(result)
+      result = remove_leading_newlines(result)
+      result = clean_tag_borders(result)
+      clean_punctuation_characters(result)
     end
 
     def remove_newlines(string)
@@ -10,7 +14,7 @@ module ReverseMarkdown
     end
 
     def remove_leading_newlines(string)
-      string.gsub /\A\n\n?/, ''
+      string.gsub(/\A\n+/, '')
     end
 
     def remove_inner_whitespaces(string)
@@ -22,35 +26,39 @@ module ReverseMarkdown
     end
 
     # Find non-asterisk content that is enclosed by two or
-    # more asterisks. Ensure that only one whitespace occur
+    # more asterisks. Ensure that only one whitespace occurs
     # in the border area.
     # Same for underscores and brackets.
     def clean_tag_borders(string)
-      result = string.gsub /\s?\*{2,}.*?\*{2,}\s?/ do |match|
+      result = string.gsub(/\s?\*{2,}.*?\*{2,}\s?/) do |match|
         preserve_border_whitespaces(match, default_border: ' ') do
           match.strip.sub('** ', '**').sub(' **', '**')
         end
       end
 
-      result = result.gsub /\s?\_{2,}.*?\_{2,}\s?/ do |match|
+      result = result.gsub(/\s?\_{2,}.*?\_{2,}\s?/) do |match|
         preserve_border_whitespaces(match, default_border: ' ') do
           match.strip.sub('__ ', '__').sub(' __', '__')
         end
       end
 
-      result = result.gsub /\s?~{2,}.*?~{2,}\s?/ do |match|
+      result = result.gsub(/\s?~{2,}.*?~{2,}\s?/) do |match|
         preserve_border_whitespaces(match, default_border: ' ') do
           match.strip.sub('~~ ', '~~').sub(' ~~', '~~')
         end
       end
 
-      result.gsub /\s?\[.*?\]\s?/ do |match|
+      result.gsub(/\s?\[.*?\]\s?/) do |match|
         preserve_border_whitespaces(match) do
           match.strip.sub('[ ', '[').sub(' ]', ']')
         end
       end
     end
 
+    def clean_punctuation_characters(string)
+      string.gsub(/(\*\*|~~|__)\s([\.!\?'"])/, "\\1".strip + "\\2")
+    end
+
     private
 
     def preserve_border_whitespaces(string, options = {}, &block)

data/lib/reverse_markdown/converters/bypass.rb

@@ -10,5 +10,7 @@ module ReverseMarkdown
     register :html,     Bypass.new
     register :body,     Bypass.new
     register :span,     Bypass.new
+    register :thead,    Bypass.new
+    register :tbody,    Bypass.new
   end
 end

data/lib/reverse_markdown/converters/ignore.rb

@@ -0,0 +1,12 @@
+module ReverseMarkdown
+  module Converters
+    class Ignore < Base
+      def convert(node)
+        '' # noop
+      end
+    end
+
+    register :colgroup, Ignore.new
+    register :col,      Ignore.new
+  end
+end

data/lib/reverse_markdown/converters/text.rb

@@ -9,6 +9,8 @@ module ReverseMarkdown
         end
       end
 
+      private
+
       def treat_empty(node)
         parent = node.parent.name.to_sym
         if [:ol, :ul].include?(parent)  # Otherwise the identation is broken
@@ -21,7 +23,17 @@ module ReverseMarkdown
       end
 
       def treat_text(node)
-        escape_keychars node.text.tr("\n\t", '').squeeze(' ')
+        text = remove_border_newlines(node.text)
+        text = remove_inner_newlines(text)
+        escape_keychars text
+      end
+
+      def remove_border_newlines(text)
+        text.gsub(/\A\n+/, '').gsub(/\n+\z/, '')
+      end
+
+      def remove_inner_newlines(text)
+        text.tr("\n\t", ' ').squeeze(' ')
       end
     end
 

data/lib/reverse_markdown/version.rb

@@ -1,3 +1,3 @@
 module ReverseMarkdown
-  VERSION = "0.5.1"
+  VERSION = "0.6.0"
 end

data/lib/reverse_markdown.rb

@@ -17,6 +17,7 @@ require 'reverse_markdown/converters/drop'
 require 'reverse_markdown/converters/em'
 require 'reverse_markdown/converters/h'
 require 'reverse_markdown/converters/hr'
+require 'reverse_markdown/converters/ignore'
 require 'reverse_markdown/converters/img'
 require 'reverse_markdown/converters/li'
 require 'reverse_markdown/converters/ol'

data/spec/assets/tables.html

@@ -3,21 +3,29 @@
     some text...
 
     <table>
-      <tr>
-        <th>header 1</th>
-        <th>header 2</th>
-        <th>header 3</th>
-      </tr>
-      <tr>
-        <td>data 1-1</td>
-        <td>data 2-1</td>
-        <td>data 3-1</td>
-      </tr>
-      <tr>
-        <td>data 1-2</td>
-        <td>data 2-2</td>
-        <td>data 3-2</td>
-      </tr>
+      <thead>
+        <colgroup>
+          <col span="2" style="background-color:red">
+          <col style="background-color:yellow">
+        </colgroup>
+      </thead>
+      <tbody>
+        <tr>
+          <th>header 1</th>
+          <th>header 2</th>
+          <th>header 3</th>
+        </tr>
+        <tr>
+          <td>data 1-1</td>
+          <td>data 2-1</td>
+          <td>data 3-1</td>
+        </tr>
+        <tr>
+          <td>data 1-2</td>
+          <td>data 2-2</td>
+          <td>data 3-2</td>
+        </tr>
+      </tbody>
     </table>
 
     <table>

data/spec/components/from_the_wild_spec.rb

@@ -7,8 +7,7 @@ describe ReverseMarkdown do
   subject { ReverseMarkdown.convert(input) }
 
   it "should make sense of strong-crazy markup (as seen in the wild)" do
-    subject.should ==
-      '** .' + "  \n" +
+    expect(subject).to eq '**.' + "  \n" +
       ' \*\*\* intentcast ** : logo design' + "   \n" +
       "**.**\n\n"
   end

data/spec/components/unknown_tags_spec.rb

@@ -9,7 +9,7 @@ describe ReverseMarkdown do
   context 'with unknown_tags = :pass_through' do
     before { ReverseMarkdown.config.unknown_tags = :pass_through }
 
-    it { result.should include "<foo><bar>Foo with bar</bar></foo>" }
+    it { expect(result).to include "<bar>Foo with bar</bar>" }
   end
 
   context 'with unknown_tags = :raise' do
@@ -21,13 +21,13 @@ describe ReverseMarkdown do
   context 'with unknown_tags = :drop' do
     before { ReverseMarkdown.config.unknown_tags = :drop }
 
-    it { result.should eq '' }
+    it { expect(result).to eq '' }
   end
 
   context 'with unknown_tags = :bypass' do
     before { ReverseMarkdown.config.unknown_tags = :bypass }
 
-    it { result.should eq "Foo with bar\n\n" }
+    it { expect(result).to eq "Foo with bar\n\n" }
   end
 
   context 'with unknown_tags = :something_wrong' do

data/spec/html_to_markdown_to_html_spec.rb

@@ -7,8 +7,9 @@ describe 'Round trip: HTML to markdown (via reverse_markdown) to HTML (via redca
 
   # helpers
 
-  def roundtrip_should_preserve(orig_html)
-    normalize_html(html2markdown2html orig_html).should == normalize_html(orig_html)
+  def roundtrip_should_preserve(input)
+    output = html2markdown2html input
+    expect(normalize_html(input)).to eq normalize_html(output)
   end
 
   def html2markdown2html(orig_html)

data/spec/lib/reverse_markdown/cleaner_spec.rb

@@ -6,44 +6,52 @@ describe ReverseMarkdown::Cleaner do
   describe '#remove_newlines' do
     it 'removes more than 2 subsequent newlines' do
       result = cleaner.remove_newlines("foo\n\n\nbar")
-      result.should eq "foo\n\nbar"
+      expect(result).to eq "foo\n\nbar"
     end
 
     it 'skips single and double newlines' do
       result = cleaner.remove_newlines("foo\nbar\n\nbaz")
-      result.should eq "foo\nbar\n\nbaz"
+      expect(result).to eq "foo\nbar\n\nbaz"
     end
   end
 
   describe '#remove_inner_whitespaces' do
     it 'removes duplicate whitespaces from the string' do
       result = cleaner.remove_inner_whitespaces('foo  bar')
-      result.should eq "foo bar"
+      expect(result).to eq "foo bar"
     end
 
     it 'performs changes for multiple lines' do
       result = cleaner.remove_inner_whitespaces("foo  bar\nbar  foo")
-      result.should eq "foo bar\nbar foo"
+      expect(result).to eq "foo bar\nbar foo"
     end
 
     it 'keeps leading whitespaces' do
       result = cleaner.remove_inner_whitespaces("    foo  bar\n    bar  foo")
-      result.should eq "    foo bar\n    bar foo"
+      expect(result).to eq "    foo bar\n    bar foo"
     end
 
     it 'keeps trailing whitespaces' do
       result = cleaner.remove_inner_whitespaces("foo  \n")
-      result.should eq "foo  \n"
+      expect(result).to eq "foo  \n"
     end
 
     it 'keeps trailing newlines' do
       result = cleaner.remove_inner_whitespaces("foo\n")
-      result.should eq "foo\n"
+      expect(result).to eq "foo\n"
     end
 
     it 'removes tabs as well' do
       result = cleaner.remove_inner_whitespaces("foo\t \tbar")
-      result.should eq "foo bar"
+      expect(result).to eq "foo bar"
+    end
+  end
+
+  describe '#clean_punctuation_characters' do
+    it 'removes whitespace between tag end and punctuation characters' do
+      input = "**fat** . ~~strike~~ ? __italic__ ! "
+      result = cleaner.clean_punctuation_characters(input)
+      expect(result).to eq "**fat**. ~~strike~~? __italic__! "
     end
   end
 
@@ -51,31 +59,31 @@ describe ReverseMarkdown::Cleaner do
     it 'removes not needed whitespaces from strong tags' do
       input = "foo ** foobar ** bar"
       result = cleaner.clean_tag_borders(input)
-      result.should eq "foo **foobar** bar"
+      expect(result).to eq "foo **foobar** bar"
     end
 
     it 'remotes leading or trailing whitespaces independently' do
       input = "1 **fat ** 2 ** fat** 3"
       result = cleaner.clean_tag_borders(input)
-      result.should eq "1 **fat** 2 **fat** 3"
+      expect(result).to eq "1 **fat** 2 **fat** 3"
     end
 
     it 'adds whitespaces if there are none' do
       input = "1**fat**2"
       result = cleaner.clean_tag_borders(input)
-      result.should eq "1 **fat** 2"
+      expect(result).to eq "1 **fat** 2"
     end
 
     it 'cleans italic stuff as well' do
       input = "1 __italic __ 2 __ italic__ 3__italic __4"
       result = cleaner.clean_tag_borders(input)
-      result.should eq "1 __italic__ 2 __italic__ 3 __italic__ 4"
+      expect(result).to eq "1 __italic__ 2 __italic__ 3 __italic__ 4"
     end
 
     it 'cleans strikethrough stuff as well' do
       input = "1 ~~italic ~~ 2 ~~ italic~~ 3~~italic ~~4"
       result = cleaner.clean_tag_borders(input)
-      result.should eq "1 ~~italic~~ 2 ~~italic~~ 3 ~~italic~~ 4"
+      expect(result).to eq "1 ~~italic~~ 2 ~~italic~~ 3 ~~italic~~ 4"
     end
   end
 

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

@@ -7,12 +7,12 @@ describe ReverseMarkdown::Converters::Blockquote do
   it 'converts nested elements as well' do
     input = Nokogiri::XML.parse("<blockquote><ul><li>foo</li></ul></blockquote>").root
     result = converter.convert(input)
-    result.should eq "> - foo"
+    expect(result).to eq "> - foo"
   end
 
   it 'can deal with paragraphs inside' do
     input = Nokogiri::XML.parse("<blockquote><p>Some text.</p><p>Some more text.</p></blockquote>").root
     result = converter.convert(input)
-    result.should eq "> Some text.\n> \n> Some more text."
+    expect(result).to eq "> Some text.\n> \n> Some more text."
   end
 end

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

@@ -4,6 +4,6 @@ describe ReverseMarkdown::Converters::Br do
   let(:converter) { ReverseMarkdown::Converters::Br.new }
 
   it 'just converts into two spaces and a newline' do
-    converter.convert(:anything).should eq "  \n"
+    expect(converter.convert(:anything)).to eq "  \n"
   end
 end

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

@@ -8,17 +8,17 @@ describe ReverseMarkdown::Converters::Del do
 
     it 'converts the input as expected' do
       input = Nokogiri::XML.parse('<del>deldeldel</del>').root
-      converter.convert(input).should eq '~~deldeldel~~'
+      expect(converter.convert(input)).to eq '~~deldeldel~~'
     end
 
     it 'skips empty tags' do
       input = Nokogiri::XML.parse('<del></del>').root
-      converter.convert(input).should eq ''
+      expect(converter.convert(input)).to eq ''
     end
 
     it 'knows about its enabled/disabled state' do
-      converter.should be_enabled
-      converter.should_not be_disabled
+      expect(converter).to be_enabled
+      expect(converter).not_to be_disabled
     end
   end
 
@@ -27,12 +27,12 @@ describe ReverseMarkdown::Converters::Del do
 
     it 'does not convert anything' do
       input = Nokogiri::XML.parse('<del>deldeldel</del>').root
-      converter.convert(input).should eq 'deldeldel'
+      expect(converter.convert(input)).to eq 'deldeldel'
     end
 
     it 'knows about its enabled/disabled state' do
-      converter.should_not be_enabled
-      converter.should be_disabled
+      expect(converter).not_to be_enabled
+      expect(converter).to be_disabled
     end
   end
 end

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

@@ -7,7 +7,7 @@ describe ReverseMarkdown::Converters::Li do
   it 'does not fail without a valid parent context' do
     input = Nokogiri::XML.parse("<li>foo</li>").root
     result = converter.convert(input)
-    result.should eq "- foo\n"
+    expect(result).to eq "- foo\n"
   end
 
 end

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

@@ -0,0 +1,25 @@
+require 'spec_helper'
+
+describe ReverseMarkdown::Converters::Text do
+
+  let(:converter) { ReverseMarkdown::Converters::Text.new }
+
+  it 'treats newline within text as a single whitespace' do
+    input = Nokogiri::XML.parse("<p>foo\nbar</p>").root
+    result = converter.convert(input)
+    expect(result).to eq 'foo bar'
+  end
+
+  it 'removes leading newlines' do
+    input = Nokogiri::XML.parse("<p>\n\nfoo bar</p>").root
+    result = converter.convert(input)
+    expect(result).to eq 'foo bar'
+  end
+
+  it 'removes trailing newlines' do
+    input = Nokogiri::XML.parse("<p>foo bar\n\n</p>").root
+    result = converter.convert(input)
+    expect(result).to eq 'foo bar'
+  end
+
+end

data/spec/lib/reverse_markdown_spec.rb

@@ -5,33 +5,33 @@ describe ReverseMarkdown do
   let(:document) { Nokogiri::HTML(input) }
 
   it "parses nokogiri documents" do
-    lambda { ReverseMarkdown.convert(document) }.should_not raise_error
+    expect { ReverseMarkdown.convert(document) }.not_to raise_error
   end
 
   it "parses nokogiri elements" do
-    lambda { ReverseMarkdown.convert(document.root) }.should_not raise_error
+    expect { ReverseMarkdown.convert(document.root) }.not_to raise_error
   end
 
   it "parses string input" do
-    lambda { ReverseMarkdown.convert(input) }.should_not raise_error
+    expect { ReverseMarkdown.convert(input) }.not_to raise_error
   end
 
   it "behaves in a sane way when root element is nil" do
-    ReverseMarkdown.convert(nil).should == ''
+    expect(ReverseMarkdown.convert(nil)).to eq ''
   end
 
   describe '#config' do
     it 'stores a given configuration option' do
       ReverseMarkdown.config.github_flavored = true
-      ReverseMarkdown.config.github_flavored.should be_true
+      expect(ReverseMarkdown.config.github_flavored).to eq true
     end
 
     it 'can be used as a block configurator as well' do
       ReverseMarkdown.config do |config|
-        config.github_flavored.should be_false
+        expect(config.github_flavored).to eq false
         config.github_flavored = true
       end
-      ReverseMarkdown.config.github_flavored.should be_true
+      expect(ReverseMarkdown.config.github_flavored).to eq true
     end
   end
 end

data/spec/spec_helper.rb

@@ -14,8 +14,6 @@ SimpleCov.start 'gem'
 require 'reverse_markdown'
 
 RSpec.configure do |config|
-  config.color_enabled = true
-
   config.after(:each) do
     ReverseMarkdown.config.reset
   end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: reverse_markdown
 version: !ruby/object:Gem::Version
-  version: 0.5.1
+  version: 0.6.0
 platform: ruby
 authors:
 - Johannes Opper
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-04-03 00:00:00.000000000 Z
+date: 2014-09-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -104,7 +104,9 @@ extensions: []
 extra_rdoc_files: []
 files:
 - ".gitignore"
+- ".rspec"
 - ".travis.yml"
+- CHANGELOG.md
 - Gemfile
 - LICENSE
 - README.md
@@ -126,6 +128,7 @@ files:
 - lib/reverse_markdown/converters/em.rb
 - lib/reverse_markdown/converters/h.rb
 - lib/reverse_markdown/converters/hr.rb
+- lib/reverse_markdown/converters/ignore.rb
 - lib/reverse_markdown/converters/img.rb
 - lib/reverse_markdown/converters/li.rb
 - lib/reverse_markdown/converters/ol.rb
@@ -170,6 +173,7 @@ files:
 - spec/lib/reverse_markdown/converters/br_spec.rb
 - spec/lib/reverse_markdown/converters/del_spec.rb
 - spec/lib/reverse_markdown/converters/li_spec.rb
+- spec/lib/reverse_markdown/converters/text_spec.rb
 - spec/lib/reverse_markdown_spec.rb
 - spec/spec_helper.rb
 homepage: http://github.com/xijo/reverse_markdown
@@ -226,5 +230,6 @@ test_files:
 - spec/lib/reverse_markdown/converters/br_spec.rb
 - spec/lib/reverse_markdown/converters/del_spec.rb
 - spec/lib/reverse_markdown/converters/li_spec.rb
+- spec/lib/reverse_markdown/converters/text_spec.rb
 - spec/lib/reverse_markdown_spec.rb
 - spec/spec_helper.rb