qiita-markdown 0.2.2 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: a2246b9c7de465987d8096f8f06dff05874c31b1
-  data.tar.gz: 7f980024c9522ba903c7ffaa6da2964b4b78d907
+  metadata.gz: 180a959e88bbb1c45168ff83dcf6c3df486f12d7
+  data.tar.gz: b7e6dff4bf6b4810ccdc14fabb1ebb8c4c081053
 SHA512:
-  metadata.gz: c83fa85dced0ec7c9dc7f4962073b5576b9dc6ef6b6c2616cb3fd6bcb033ae56e1f85a77553b9f8d350c030f5f711b57fd0d0a337bfa0eaf6671cd142675b2e3
-  data.tar.gz: ae5a0ccaf8a142815d3fefc1030f24bda3cfab000abc75af67c698df4771b7cae64348908e0e53a419e637bbdba153a952aae34a42b7bdbdf2a1e43cb4b1e467
+  metadata.gz: c13f02a0d3b10205576e12233a80f880ac6b540897bcc5bc7ab8eefde14a1090055dd8c452ac09bad53e5b6b85e49bef74b1aabe03e2b3df7b87bca5f4babc0e
+  data.tar.gz: 1154d125bf9c9844e61242810b3610ace6b59b197edbd925228435246f0b3a49980686d51270d50ad9966b1449aadb1bb289f81623829f7c43de60b1f6f8b66c

data/.rubocop.yml

@@ -0,0 +1,7 @@
+inherit_from: .rubocop_todo.yml
+
+Style/StringLiterals:
+  EnforcedStyle: double_quotes
+
+Style/TrailingComma:
+  EnforcedStyleForMultiline: comma

data/.rubocop_todo.yml

@@ -0,0 +1,103 @@
+# This configuration was generated by `rubocop --auto-gen-config`
+# on 2015-03-12 12:56:25 +0900 using RuboCop version 0.29.1.
+# The point is for the user to remove these configuration records
+# one by one as the offenses are removed from the code base.
+# Note that changes in the inspected code, or installation of new
+# versions of RuboCop, may require this file to be generated again.
+
+# Offense count: 1
+Metrics/AbcSize:
+  Max: 21
+
+# Offense count: 1
+# Configuration parameters: CountComments.
+Metrics/ClassLength:
+  Max: 169
+
+# Offense count: 27
+# Configuration parameters: AllowURI, URISchemes.
+Metrics/LineLength:
+  Max: 122
+
+# Offense count: 3
+# Configuration parameters: CountComments.
+Metrics/MethodLength:
+  Max: 17
+
+# Offense count: 1
+# Cop supports --auto-correct.
+# Configuration parameters: EnforcedStyle, SupportedStyles.
+Style/AndOr:
+  Enabled: false
+
+# Offense count: 3
+# Cop supports --auto-correct.
+# Configuration parameters: EnforcedStyle, SupportedStyles.
+Style/BarePercentLiterals:
+  Enabled: false
+
+# Offense count: 1
+Style/ConstantName:
+  Enabled: false
+
+# Offense count: 10
+Style/Documentation:
+  Enabled: false
+
+# Offense count: 3
+Style/DoubleNegation:
+  Enabled: false
+
+# Offense count: 1
+# Configuration parameters: Exclude.
+Style/FileName:
+  Enabled: false
+
+# Offense count: 1
+# Configuration parameters: MinBodyLength.
+Style/GuardClause:
+  Enabled: false
+
+# Offense count: 1
+# Configuration parameters: EnforcedStyle, MinBodyLength, SupportedStyles.
+Style/Next:
+  Enabled: false
+
+# Offense count: 9
+# Cop supports --auto-correct.
+# Configuration parameters: PreferredDelimiters.
+Style/PercentLiteralDelimiters:
+  Enabled: false
+
+# Offense count: 1
+# Cop supports --auto-correct.
+Style/PerlBackrefs:
+  Enabled: false
+
+# Offense count: 10
+# Configuration parameters: NamePrefix, NamePrefixBlacklist.
+Style/PredicateName:
+  Enabled: false
+
+# Offense count: 2
+# Configuration parameters: MaxSlashes.
+Style/RegexpLiteral:
+  Enabled: false
+
+# Offense count: 2
+# Cop supports --auto-correct.
+# Configuration parameters: EnforcedStyle, SupportedStyles.
+Style/SignalException:
+  Enabled: false
+
+# Offense count: 2
+# Cop supports --auto-correct.
+# Configuration parameters: EnforcedStyleForMultiline, SupportedStyles.
+Style/TrailingComma:
+  Enabled: false
+
+# Offense count: 6
+# Cop supports --auto-correct.
+# Configuration parameters: WordRegex.
+Style/WordArray:
+  Enabled: false

data/CHANGELOG.md

@@ -1,3 +1,8 @@
+## Unreleased
+
+## 0.3.0
+- Introduce another processor Qiita::Markdown::SummaryProcessor, which is for rendering a summary of markdown document.
+
 ## 0.2.2
 - Fix a bug that raised error on rendering `<a>` tag with href for unknown fragment inside of `<sup>` tag (e.g. `<sup><a href="#foo.1">Link</a></sup>`)
 

data/Gemfile

@@ -1,4 +1,4 @@
-source 'https://rubygems.org'
+source "https://rubygems.org"
 
 # Specify your gem's dependencies in qiita-markdown.gemspec
 gemspec

data/README.md

@@ -12,7 +12,7 @@ Qiita-specified markdown processor.
 * Task list
 * Footnotes
 
-## Usage
+## Basic Usage
 Qiita::Markdown::Processor provides markdown rendering logic.
 
 ```ruby
@@ -62,3 +62,29 @@ processor.call(text)
 processor = Qiita::Markdown::Processor.new(asset_root: "http://example.com/assets")
 processor.call(text)
 ```
+
+## Rendering Summary
+There's another processor Qiita::Markdown::SummaryProcessor,
+which is for rendering a summary of markdown document.
+It simplifies a document by removing complex markups
+and also truncates it to a specific length without breaking the document structure.
+
+Note that this processor does not produce the `:codes` output in contrast to the Processor.
+
+### Context
+
+SummaryProcessor accepts the following context in addition to the Processor's context:
+
+```ruby
+{
+  truncate: {
+    length: 100,  # Documents will be truncated if it exceeds this character count. (Integer)
+    omission: '…' # A string added to the end of document when it's truncated. (String, nil)
+  }
+}
+```
+
+```ruby
+processor = Qiita::Markdown::SummaryProcessor.new(truncate: { length: 80 })
+processor.call(text)
+```

data/Rakefile

@@ -1,5 +1,7 @@
 require "bundler/gem_tasks"
 require "rspec/core/rake_task"
+require "rubocop/rake_task"
 
 RSpec::Core::RakeTask.new(:spec)
-task default: :spec
+RuboCop::RakeTask.new(:style)
+task default: [:spec, :style]

data/lib/qiita/markdown.rb

@@ -13,7 +13,10 @@ require "qiita/markdown/filters/footnote"
 require "qiita/markdown/filters/mention"
 require "qiita/markdown/filters/redcarpet"
 require "qiita/markdown/filters/sanitize"
+require "qiita/markdown/filters/simplify"
 require "qiita/markdown/filters/syntax_highlight"
 require "qiita/markdown/filters/toc"
+require "qiita/markdown/filters/truncate"
 require "qiita/markdown/processor"
+require "qiita/markdown/summary_processor"
 require "qiita/markdown/version"

data/lib/qiita/markdown/filters/code.rb

@@ -15,7 +15,7 @@ module Qiita
         def call
           result[:codes] ||= []
           doc.search("pre").each do |pre|
-            if code = pre.at("code")
+            if (code = pre.at("code"))
               label = Label.new(code["class"])
               filename = label.filename
               language = label.language

data/lib/qiita/markdown/filters/simplify.rb

@@ -0,0 +1,47 @@
+module Qiita
+  module Markdown
+    module Filters
+      # A filter for simplifying document structure by removing complex markups
+      # (mainly block elements) and complex contents.
+      #
+      # The logic of this filter is similar to the `Sanitize` filter, but this
+      # does not use the `sanitize` gem internally for the following reasons:
+      #
+      # * Each filter should do only its own responsibility, and this filter is
+      #   _not_ for sanitization.
+      #
+      # * The `sanitize` gem automatically adds extra transformers even if we
+      #   want to clean up only some elements, and they would be run in the
+      #   `Sanitize` filter later.
+      #   https://github.com/rgrove/sanitize/blob/v3.1.2/lib/sanitize.rb#L77-L100
+      class Simplify < HTML::Pipeline::Filter
+        SIMPLE_ELEMENTS = %w(a b code em i ins q s samp span strike strong sub sup var)
+
+        COMPLEX_CONTENT_ELEMENTS = %w(table)
+
+        def call
+          remove_complex_contents
+          clean_complex_markups
+          doc
+        end
+
+        private
+
+        # Remove complex elements along with their contents entirely.
+        def remove_complex_contents
+          selector = COMPLEX_CONTENT_ELEMENTS.join(",")
+          doc.search(selector).each(&:remove)
+        end
+
+        # Remove complex markups while keeping their contents.
+        def clean_complex_markups
+          doc.traverse do |node|
+            next unless node.element?
+            next if SIMPLE_ELEMENTS.include?(node.name)
+            node.replace(node.children)
+          end
+        end
+      end
+    end
+  end
+end

data/lib/qiita/markdown/filters/syntax_highlight.rb

@@ -32,7 +32,7 @@ module Qiita
 
           def call
             outer = Nokogiri::HTML.fragment(%Q[<div class="code-frame" data-lang="#{language}">])
-            frame = outer.at('div')
+            frame = outer.at("div")
             frame.add_child(filename_node) if filename
             frame.add_child(highlighted_node)
             @node.replace(outer)

data/lib/qiita/markdown/filters/toc.rb

@@ -47,7 +47,7 @@ module Qiita
           end
 
           def id
-            @node.text.downcase.gsub(/[^\p{Word}\- ]/u, '').gsub(' ', '-')
+            @node.text.downcase.gsub(/[^\p{Word}\- ]/u, "").gsub(" ", "-")
           end
 
           def increment

data/lib/qiita/markdown/filters/truncate.rb

@@ -0,0 +1,81 @@
+module Qiita
+  module Markdown
+    module Filters
+      # A filter for truncating a document without breaking the document
+      # structure.
+      #
+      # You can pass `:length` and `:omission` option to :truncate context.
+      #
+      # @example
+      #   Truncate.new(doc, truncate: { length: 50, omission: '... (continued)' })
+      class Truncate < HTML::Pipeline::Filter
+        DEFAULT_OPTIONS = {
+          length: 100,
+          omission: "…".freeze
+        }.freeze
+
+        def call
+          @current_length = 0
+          @previous_char_was_blank = false
+
+          traverse(doc) do |node|
+            if exceeded?
+              node.remove
+            elsif node.text?
+              process_text_node(node)
+            end
+          end
+
+          doc
+        end
+
+        private
+
+        # Traverse the given node recursively in the depth-first order.
+        # Note that we cannot use Nokogiri::XML::Node#traverse
+        # since it traverses the node's descendants _before_ the node itself.
+        # https://github.com/sparklemotion/nokogiri/blob/v1.6.6.2/lib/nokogiri/xml/node.rb#L571-L574
+        def traverse(node, &block)
+          block.call(node)
+
+          node.children.each do |child_node|
+            traverse(child_node, &block)
+          end
+        end
+
+        def exceeded?
+          @current_length > max_length
+        end
+
+        def process_text_node(node)
+          node.content.each_char.with_index do |char, index|
+            current_char_is_blank = char.strip.empty?
+
+            if !@previous_char_was_blank || !current_char_is_blank
+              @current_length += 1
+            end
+
+            @previous_char_was_blank = current_char_is_blank
+
+            if exceeded?
+              node.content = node.content.slice(0...(index - omission.size)) + omission
+              break
+            end
+          end
+        end
+
+        def max_length
+          options[:length]
+        end
+
+        def omission
+          options[:omission] || "".freeze
+        end
+
+        def options
+          @options ||= DEFAULT_OPTIONS.merge(context[:truncate] || {})
+        end
+      end
+    end
+  end
+end

data/lib/qiita/markdown/summary_processor.rb

@@ -0,0 +1,23 @@
+module Qiita
+  module Markdown
+    # A processor for rendering a summary of markdown document. This simplifies
+    # a document by removing complex markups and also truncates it to a
+    # specific length without breaking the document structure.
+    class SummaryProcessor < Processor
+      DEFAULT_FILTERS = [
+        Filters::Redcarpet,
+        Filters::Simplify,
+        HTML::Pipeline::EmojiFilter,
+        Filters::Mention,
+        Filters::Sanitize,
+        Filters::Truncate
+      ]
+
+      # @note Modify filters if you want.
+      # @return [Array<HTML::Pipeline::Filter>]
+      def filters
+        @filters ||= DEFAULT_FILTERS
+      end
+    end
+  end
+end

data/lib/qiita/markdown/version.rb

@@ -1,5 +1,5 @@
 module Qiita
   module Markdown
-    VERSION = "0.2.2"
+    VERSION = "0.3.0"
   end
 end

data/qiita-markdown.gemspec

@@ -29,4 +29,5 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency "pry"
   spec.add_development_dependency "rake", "~> 10.0"
   spec.add_development_dependency "rspec", "3.1.0"
+  spec.add_development_dependency "rubocop", "~> 0.29"
 end

data/spec/qiita/markdown/processor_spec.rb

@@ -256,13 +256,13 @@ describe Qiita::Markdown::Processor do
           @justin
           @justin
           @mallory@github
-          @#{?o * 33}
+          @#{'o' * 33}
           @oo
         EOS
       end
 
       it "extracts mentions correctly" do
-        expect(result[:mentioned_usernames]).to eq %W[
+        expect(result[:mentioned_usernames]).to eq %w[
           alice
           dave
           ell_en
@@ -522,7 +522,7 @@ describe Qiita::Markdown::Processor do
       end
     end
 
-    context 'with footenotes syntax' do
+    context "with footenotes syntax" do
       let(:markdown) do
         <<-EOS.strip_heredoc
           [^1]
@@ -548,7 +548,7 @@ describe Qiita::Markdown::Processor do
       end
     end
 
-    context 'with manually written link inside of <sup> tag' do
+    context "with manually written link inside of <sup> tag" do
       let(:markdown) do
         <<-EOS.strip_heredoc
           <sup>[Qiita](http://qiita.com/)</sup>
@@ -562,7 +562,7 @@ describe Qiita::Markdown::Processor do
       end
     end
 
-    context 'with manually written <a> tag with strange href inside of <sup> tag' do
+    context "with manually written <a> tag with strange href inside of <sup> tag" do
       let(:markdown) do
         <<-EOS.strip_heredoc
           <sup><a href="#foo.1">Link</a></sup>

data/spec/qiita/markdown/summary_processor_spec.rb

@@ -0,0 +1,235 @@
+require "active_support/core_ext/string/strip"
+
+describe Qiita::Markdown::SummaryProcessor do
+  describe "#call" do
+    subject(:html) do
+      result[:output].to_s
+    end
+
+    let(:context) do
+      {}
+    end
+
+    let(:markdown) do
+      fail NotImplementedError
+    end
+
+    let(:result) do
+      described_class.new(context).call(markdown)
+    end
+
+    context "with valid condition" do
+      let(:markdown) do
+        <<-EOS.strip_heredoc
+          example
+        EOS
+      end
+
+      it "returns a Hash with HTML output and other metadata but no codes" do
+        expect(result[:mentioned_usernames]).to be_an Array
+        expect(result[:output]).to be_a Nokogiri::HTML::DocumentFragment
+        expect(result).not_to have_key(:codes)
+      end
+    end
+
+    context "with HTML-characters" do
+      let(:markdown) do
+        "<>&"
+      end
+
+      it "sanitizes them" do
+        should eq <<-EOS.strip_heredoc
+          &lt;&gt;&amp;
+        EOS
+      end
+    end
+
+    context "with code" do
+      let(:markdown) do
+        <<-EOS.strip_heredoc
+          ```ruby
+          puts 'hello world'
+          ```
+        EOS
+      end
+
+      it "returns simple code element" do
+        should eq <<-EOS.strip_heredoc
+          <code class="ruby">puts 'hello world'
+          </code>
+        EOS
+      end
+    end
+
+    context "with emoji" do
+      let(:markdown) do
+        ":+1:"
+      end
+
+      it "replaces it with img element" do
+        should include("img")
+      end
+    end
+
+    context "with image" do
+      let(:markdown) do
+        <<-EOS.strip_heredoc
+          ![Qiita](http://qiita.com/icons/favicons/public/apple-touch-icon.png)
+        EOS
+      end
+
+      it "removes it" do
+        expect(html.strip).to be_empty
+      end
+    end
+
+    context "with line breaks" do
+      let(:markdown) do
+        <<-EOS.strip_heredoc
+          foo
+          bar
+        EOS
+      end
+
+      it "removes them" do
+        should eq <<-EOS.strip_heredoc
+          foo
+          bar
+        EOS
+      end
+    end
+
+    context "with paragraphs" do
+      let(:markdown) do
+        <<-EOS.strip_heredoc
+          Lorem ipsum dolor sit amet.
+
+          Consectetur adipisicing elit.
+        EOS
+      end
+
+      it "flattens them" do
+        should eq <<-EOS.strip_heredoc
+          Lorem ipsum dolor sit amet.
+
+          Consectetur adipisicing elit.
+        EOS
+      end
+    end
+
+    context "with normal list items" do
+      let(:markdown) do
+        <<-EOS.strip_heredoc
+          - foo
+          - bar
+        EOS
+      end
+
+      it "flattens them" do
+        should eq <<-EOS.strip_heredoc
+
+          foo
+          bar
+
+        EOS
+      end
+    end
+
+    context "with task list items" do
+      let(:markdown) do
+        <<-EOS.strip_heredoc
+          - [ ] foo
+          - [x] bar
+        EOS
+      end
+
+      it "flattens them without converting to checkboxes" do
+        should eq <<-EOS.strip_heredoc
+
+          [ ] foo
+          [x] bar
+
+        EOS
+      end
+    end
+
+    context "with table" do
+      let(:markdown) do
+        <<-EOS.strip_heredoc
+          | a | b | c |
+          |---|---|---|
+          | a | b | c |
+        EOS
+      end
+
+      it "removes it entirely" do
+        expect(html.strip).to be_empty
+      end
+    end
+
+    context "with a simple long document" do
+      before do
+        context[:truncate] = { length: 10 }
+      end
+
+      let(:markdown) do
+        <<-EOS.strip_heredoc
+          Lorem ipsum dolor sit amet.
+        EOS
+      end
+
+      it "truncates it to the specified length" do
+        should eq "Lorem ips…"
+      end
+    end
+
+    context "with a long document consisting of nested elements" do
+      before do
+        context[:truncate] = { length: 10 }
+      end
+
+      let(:markdown) do
+        <<-EOS.strip_heredoc
+          _[Qiita](http://qiita.com/) is **a technical knowledge sharing and collaboration platform for programmers**._
+        EOS
+      end
+
+      it "truncates it while honoring the document structure" do
+        should eq '<em><a href="http://qiita.com/">Qiita</a> is <strong>…</strong></em>'
+      end
+    end
+
+    context "with a long document including consecutive whitespaces" do
+      before do
+        context[:truncate] = { length: 10 }
+      end
+
+      let(:markdown) do
+        <<-EOS.strip_heredoc
+          **12**   4 [ 6](http://qiita.com/)_7
+          9_ 123
+        EOS
+      end
+
+      it "truncates it while counting the consecutive whilespaces as one" do
+        should eq "<strong>12</strong>   4 <a href=\"http://qiita.com/\"> 6</a><em>7\n9</em>…"
+      end
+    end
+
+    context "with truncate: { omission: nil } context" do
+      before do
+        context[:truncate] = { length: 10, omission: nil }
+      end
+
+      let(:markdown) do
+        <<-EOS.strip_heredoc
+          Lorem ipsum dolor sit amet.
+        EOS
+      end
+
+      it "does not add extra omission text" do
+        should eq "Lorem ipsu"
+      end
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -9,7 +9,7 @@ RSpec.configure do |config|
     mocks.verify_partial_doubles = true
   end
 
-  config.default_formatter = 'doc'
+  config.default_formatter = "doc"
   config.filter_run :focus
   config.run_all_when_everything_filtered = true
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: qiita-markdown
 version: !ruby/object:Gem::Version
-  version: 0.2.2
+  version: 0.3.0
 platform: ruby
 authors:
 - Ryo Nakamura
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-02-10 00:00:00.000000000 Z
+date: 2015-03-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport
@@ -192,6 +192,20 @@ dependencies:
     - - '='
       - !ruby/object:Gem::Version
         version: 3.1.0
+- !ruby/object:Gem::Dependency
+  name: rubocop
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.29'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.29'
 description: 
 email:
 - r7kamura@gmail.com
@@ -201,6 +215,8 @@ extra_rdoc_files: []
 files:
 - ".gitignore"
 - ".rspec"
+- ".rubocop.yml"
+- ".rubocop_todo.yml"
 - ".travis.yml"
 - CHANGELOG.md
 - Gemfile
@@ -215,12 +231,16 @@ files:
 - lib/qiita/markdown/filters/mention.rb
 - lib/qiita/markdown/filters/redcarpet.rb
 - lib/qiita/markdown/filters/sanitize.rb
+- lib/qiita/markdown/filters/simplify.rb
 - lib/qiita/markdown/filters/syntax_highlight.rb
 - lib/qiita/markdown/filters/toc.rb
+- lib/qiita/markdown/filters/truncate.rb
 - lib/qiita/markdown/processor.rb
+- lib/qiita/markdown/summary_processor.rb
 - lib/qiita/markdown/version.rb
 - qiita-markdown.gemspec
 - spec/qiita/markdown/processor_spec.rb
+- spec/qiita/markdown/summary_processor_spec.rb
 - spec/spec_helper.rb
 homepage: https://github.com/increments/qiita-markdown
 licenses:
@@ -248,5 +268,6 @@ specification_version: 4
 summary: Qiita-specified markdown processor.
 test_files:
 - spec/qiita/markdown/processor_spec.rb
+- spec/qiita/markdown/summary_processor_spec.rb
 - spec/spec_helper.rb
 has_rdoc: