htmlbeautifier 1.1.0 → 1.1.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: eb927f5efa5cd85b002af5945bd03106b0fc7c31
-  data.tar.gz: a2dfedd5c2565b7245d1473d77fd729f621e0f0c
+  metadata.gz: 3b82dd8d2489286ab4474e1690d0a47ff91ffce8
+  data.tar.gz: e20a70c076be7e6eda31e456b0fd56715c1554ce
 SHA512:
-  metadata.gz: 2a06c094220e541614b3026403dfe017207d2b09821044720a5bb4093fc580007c638b746022739d1ba75a22b96e6a9a46bb21eeab293bc84c1a313bacd4f0ed
-  data.tar.gz: 1d29ae0712bed379920a1c1a3e3431d7ffc5404388b1bad04e8b32ae542efdb10f14605fc39e03028a852ddab060ac3e216dcafa5be48fca8c7940736b7ee40a
+  metadata.gz: 9da8945658fddb13a0af61e5d61e05b381ffdb8168247d22fe6026043c41822cce4bce45910e844cb8f5183f01a790836a209802531cd4e13a1bbd67b0092877
+  data.tar.gz: 224c74e0769b2e208505cd0d1461f4c971ed9a264f2ed78bf27c6311c5fa037e40295b8beb607fed7edf114e354138805cec3e766432b9a3a8e08e0b66a86950

data/README.md

@@ -1,11 +1,9 @@
-HTML Beautifier
-===============
+# HTML Beautifier
 
 A normaliser/beautifier for HTML that also understands embedded Ruby.
 Ideal for tidying up Rails templates.
 
-What it does
-------------
+## What it does
 
 * Normalises hard tabs to spaces
 * Removes trailing spaces
@@ -18,8 +16,7 @@ What it does
 * Indents the left-hand margin of JavaScript and CSS blocks to match the
   indentation level of the code
 
-Usage
------
+## Usage
 
 ### From the command line
 
@@ -35,7 +32,7 @@ or to operate on standard input and output:
 $ htmlbeautifier < input > output
 ```
 
-## In your code
+### In your code
 
 ```ruby
 require 'htmlbeautifier'
@@ -48,3 +45,27 @@ You can also specify the number of spaces to indent (the default is 2):
 ```ruby
 beautiful = HtmlBeautifier.beautify(messy, tab_stops: 4)
 ```
+
+## Installation
+
+This is a Ruby gem.
+To install the command-line tool (you may need `sudo`):
+
+```sh
+$ gem install htmlbeautifier
+```
+
+To use the gem with Bundler, add to your `Gemfile`:
+
+```ruby
+gem 'htmlbeautifier'
+```
+
+## Contributing
+
+1. Follow [these guidelines][git-commit] when writing commit messages (briefly,
+   the first line should begin with a capital letter, use the imperative mood,
+   be no more than 50 characters, and not end with a period).
+2. Include tests.
+
+[git-commit]:http://tbaggery.com/2008/04/19/a-note-about-git-commit-messages.html

data/Rakefile

@@ -7,3 +7,10 @@ RSpec::Core::RakeTask.new do |t|
 end
 
 task :default => [:spec]
+
+if Gem.loaded_specs.key?('rubocop')
+  require 'rubocop/rake_task'
+  RuboCop::RakeTask.new
+
+  task(:default).prerequisites << task(:rubocop)
+end

data/bin/htmlbeautifier

@@ -1,7 +1,7 @@
 #!/usr/bin/env ruby
-require 'htmlbeautifier'
-require 'optparse'
-require 'fileutils'
+require "htmlbeautifier"
+require "optparse"
+require "fileutils"
 
 def beautify(name, input, output, options)
   output.puts HtmlBeautifier.beautify(input, options)
@@ -11,7 +11,7 @@ end
 
 executable = File.basename(__FILE__)
 
-options = {:tab_stops => 2}
+options = { tab_stops: 2 }
 parser = OptionParser.new do |opts|
   opts.banner = "Usage: #{executable} [options] [file ...]"
   opts.separator <<END

data/lib/htmlbeautifier.rb

@@ -1,9 +1,9 @@
-require 'htmlbeautifier/builder'
-require 'htmlbeautifier/html_parser'
-require 'htmlbeautifier/version'
+require "htmlbeautifier/builder"
+require "htmlbeautifier/html_parser"
+require "htmlbeautifier/version"
 
 module HtmlBeautifier
-
+  #
   # Returns a beautified HTML/HTML+ERB document as a String.
   # html must be an object that responds to +#to_s+.
   #
@@ -13,7 +13,7 @@ module HtmlBeautifier
   # is false, i.e. continue to process the rest of the document.
   #
   def self.beautify(html, options = {})
-    ''.tap { |output|
+    "".tap { |output|
       HtmlParser.new.scan html.to_s, Builder.new(output, options)
     }
   end

data/lib/htmlbeautifier/builder.rb

@@ -1,17 +1,8 @@
-require 'htmlbeautifier/parser'
+require "htmlbeautifier/parser"
+require "htmlbeautifier/ruby_indenter"
 
 module HtmlBeautifier
   class Builder
-
-    RUBY_INDENT  =
-      %r{ ^ ( if | unless | while | begin | elsif | else )\b
-        | \b ( do | \{ ) ( \s* \| [^\|]+ \| )? $
-        }x
-    RUBY_OUTDENT =
-      %r{ ^ ( end | elsif | else |\} ) \b
-        }x
-    ELEMENT_CONTENT = %r{ (?:[^<>]|<%.*?%>)* }mx
-
     DEFAULT_OPTIONS = {
       tab_stops: 2,
       stop_on_errors: false
@@ -19,20 +10,21 @@ module HtmlBeautifier
 
     def initialize(output, options = {})
       options = DEFAULT_OPTIONS.merge(options)
+      @tab = " " * options[:tab_stops]
+      @stop_on_errors = options[:stop_on_errors]
       @level = 0
       @new_line = false
-      @tab = ' ' * options[:tab_stops]
-      @stop_on_errors = options[:stop_on_errors]
-      @output = output
       @empty = true
       @ie_cc_levels = []
+      @output = output
+      @embedded_indenter = RubyIndenter.new
     end
 
   private
 
     def error(text)
       return unless @stop_on_errors
-      raise RuntimeError, text
+      raise text
     end
 
     def indent
@@ -44,75 +36,62 @@ module HtmlBeautifier
       @level = [@level - 1, 0].max
     end
 
-    def emit(s)
-      if @new_line && !@empty
-        @output << ("\n" + @tab * @level)
-      end
-      @output << s
+    def emit(*strings)
+      @output << ("\n" + @tab * @level) if @new_line && !@empty
+      @output << strings.join("")
       @new_line = false
       @empty = false
     end
 
-    def new_line(*_args)
+    def new_line(*)
       @new_line = true
     end
 
     def embed(opening, code, closing)
-      lines = code.split(/\n/).map{ |l| l.strip }
-      outdent if lines.first =~ RUBY_OUTDENT
-      emit opening + code + closing
-      indent if lines.last =~ RUBY_INDENT
+      lines = code.split(%r{\n}).map(&:strip)
+      outdent if @embedded_indenter.outdent?(lines)
+      emit opening, code, closing
+      indent if @embedded_indenter.indent?(lines)
     end
 
     def foreign_block(opening, code, closing)
       emit opening
-      unless code.strip.empty?
-        indent
+      emit_reindented_block_content code unless code.strip.empty?
+      emit closing
+    end
 
-        lines = code.split(/\n/)
-        lines.shift while lines.first.strip.empty?
-        lines.pop while lines.last.strip.empty?
-        indentation = lines.first[/^ +/]
+    def emit_reindented_block_content(code)
+      lines = code.strip.split(%r{\n})
+      indentation = lines.first[%r{^\s+}]
 
+      indent
+      new_line
+      lines.each do |line|
+        emit line.rstrip.sub(%r{^#{indentation}}, "")
         new_line
-        lines.each do |line|
-          emit line.rstrip.sub(/^#{indentation}/, '')
-          new_line
-        end
-
-        outdent
       end
-      emit closing
+      outdent
     end
 
     def preformatted_block(opening, content, closing)
       new_line
-      emit opening
-      emit content
-      emit closing
+      emit opening, content, closing
       new_line
     end
 
     def standalone_element(e)
       emit e
-      new_line if e =~ /^<br[^\w]/
+      new_line if e =~ %r{^<br[^\w]}
     end
 
-    def close_block_element(e)
+    def close_element(e)
       outdent
       emit e
-      new_line
     end
 
-    def open_block_element(e)
+    def close_block_element(e)
+      close_element e
       new_line
-      emit e
-      indent
-    end
-
-    def close_element(e)
-      outdent
-      emit e
     end
 
     def open_element(e)
@@ -120,6 +99,11 @@ module HtmlBeautifier
       indent
     end
 
+    def open_block_element(e)
+      new_line
+      open_element e
+    end
+
     def close_ie_cc(e)
       if @ie_cc_levels.empty?
         error "Unclosed conditional comment"
@@ -137,7 +121,7 @@ module HtmlBeautifier
 
     def text(t)
       emit t.chomp
-      new_line if t.end_with? $/
+      new_line if t.end_with?("\n")
     end
   end
 end

data/lib/htmlbeautifier/html_parser.rb

@@ -1,4 +1,4 @@
-require 'htmlbeautifier/parser'
+require "htmlbeautifier/parser"
 
 module HtmlBeautifier
   class HtmlParser < Parser
@@ -14,38 +14,45 @@ module HtmlBeautifier
       pre | section | table | tbody | td | tfoot | th | thead | tr | ul | video
     )}mix
 
+    MAPPINGS = [
+      [%r{(<%-?=?)(.*?)(-?%>)}om,
+       :embed],
+      [%r{<!--\[.*?\]>}om,
+       :open_ie_cc],
+      [%r{<!\[.*?\]-->}om,
+       :close_ie_cc],
+      [%r{<!--.*?-->}om,
+       :standalone_element],
+      [%r{<!.*?>}om,
+       :standalone_element],
+      [%r{(<script#{ELEMENT_CONTENT}>)(.*?)(</script>)}omi,
+       :foreign_block],
+      [%r{(<style#{ELEMENT_CONTENT}>)(.*?)(</style>)}omi,
+       :foreign_block],
+      [%r{(<pre#{ELEMENT_CONTENT}>)(.*?)(</pre>)}omi,
+       :preformatted_block],
+      [%r{(<textarea#{ELEMENT_CONTENT}>)(.*?)(</textarea>)}omi,
+       :preformatted_block],
+      [%r{<#{HTML_VOID_ELEMENTS}(?: #{ELEMENT_CONTENT})?/?>}om,
+       :standalone_element],
+      [%r{</#{HTML_BLOCK_ELEMENTS}>}om,
+       :close_block_element],
+      [%r{<#{HTML_BLOCK_ELEMENTS}(?: #{ELEMENT_CONTENT})?>}om,
+       :open_block_element],
+      [%r{</#{ELEMENT_CONTENT}>}om,
+       :close_element],
+      [%r{<#{ELEMENT_CONTENT}>}om,
+       :open_element],
+      [%r{\s*\r?\n\s*}om,
+       :new_line],
+      [%r{[^<]+},
+       :text]]
+
     def initialize
       super do |p|
-        p.map %r{(<%-?=?)(.*?)(-?%>)}m,
-          :embed
-        p.map %r{<!--\[.*?\]>}m,
-          :open_ie_cc
-        p.map %r{<!\[.*?\]-->}m,
-          :close_ie_cc
-        p.map %r{<!--.*?-->}m,
-          :standalone_element
-        p.map %r{<!.*?>}m,
-          :standalone_element
-        p.map %r{(<script#{ELEMENT_CONTENT}>)(.*?)(</script>)}mi,
-          :foreign_block
-        p.map %r{(<style#{ELEMENT_CONTENT}>)(.*?)(</style>)}mi,
-          :foreign_block
-        p.map %r{(<pre#{ELEMENT_CONTENT}>)(.*?)(</pre>)}mi,
-          :preformatted_block
-        p.map %r{<#{HTML_VOID_ELEMENTS}(?: #{ELEMENT_CONTENT})?/?>}m,
-          :standalone_element
-        p.map %r{</#{HTML_BLOCK_ELEMENTS}>}m,
-          :close_block_element
-        p.map %r{<#{HTML_BLOCK_ELEMENTS}(?: #{ELEMENT_CONTENT})?>}m,
-          :open_block_element
-        p.map %r{</#{ELEMENT_CONTENT}>}m,
-          :close_element
-        p.map %r{<#{ELEMENT_CONTENT}>}m,
-          :open_element
-        p.map %r{\s*\r?\n\s*}m,
-          :new_line
-        p.map %r{[^<]+},
-          :text
+        MAPPINGS.each do |regexp, method|
+          p.map regexp, method
+        end
       end
     end
   end

data/lib/htmlbeautifier/parser.rb

@@ -1,19 +1,8 @@
-require 'strscan'
+require "strscan"
 
 module HtmlBeautifier
   class Parser
-
-    def self.debug_block(&blk)
-      @debug_block = blk
-    end
-
-    def self.debug(match, method)
-      if defined? @debug_block
-        @debug_block.call(match, method)
-      end
-    end
-
-    def initialize(&blk)
+    def initialize
       @maps = []
       yield self if block_given?
     end
@@ -24,9 +13,7 @@ module HtmlBeautifier
 
     def scan(subject, receiver)
       @scanner = StringScanner.new(subject)
-      until @scanner.eos?
-        dispatch(receiver)
-      end
+      dispatch(receiver) until @scanner.eos?
     end
 
     def source_so_far
@@ -34,28 +21,28 @@ module HtmlBeautifier
     end
 
     def source_line_number
-      [source_so_far.chomp.split(/\n/).count, 1].max
+      [source_so_far.chomp.split(%r{\n}).count, 1].max
     end
 
   private
+
     def dispatch(receiver)
-      @maps.each do |pattern, method|
-        if @scanner.scan(pattern)
-          params = []
-          i = 1
-          while @scanner[i]
-            params << @scanner[i]
-            i += 1
-          end
-          params = [@scanner[0]] if params.empty?
-          self.class.debug(@scanner[0], method)
-          receiver.__send__(method, *params)
-          return
-        end
-      end
-      raise "Unmatched sequence"
+      _, method = @maps.find { |pattern, _| @scanner.scan(pattern) }
+      raise "Unmatched sequence" unless method
+      receiver.__send__(method, *extract_params(@scanner))
     rescue => ex
       raise "#{ex.message} on line #{source_line_number}"
     end
+
+    def extract_params(scanner)
+      return [scanner[0]] unless scanner[1]
+      params = []
+      i = 1
+      while scanner[i]
+        params << scanner[i]
+        i += 1
+      end
+      params
+    end
   end
 end

data/lib/htmlbeautifier/ruby_indenter.rb

@@ -0,0 +1,19 @@
+module HtmlBeautifier
+  class RubyIndenter
+    INDENT_KEYWORDS = %w[ if elsif else unless while until begin for ]
+    OUTDENT_KEYWORDS = %w[ elsif else end ]
+    RUBY_INDENT  = %r{
+      ^ ( #{INDENT_KEYWORDS.join("|")} )\b
+      | \b ( do | \{ ) ( \s* \| [^\|]+ \| )? $
+    }xo
+    RUBY_OUTDENT = %r{ ^ ( #{OUTDENT_KEYWORDS.join("|")} | \} ) \b }xo
+
+    def outdent?(lines)
+      lines.first =~ RUBY_OUTDENT
+    end
+
+    def indent?(lines)
+      lines.last =~ RUBY_INDENT
+    end
+  end
+end

data/lib/htmlbeautifier/version.rb

@@ -2,8 +2,8 @@ module HtmlBeautifier #:nodoc:
   module VERSION #:nodoc:
     MAJOR = 1
     MINOR = 1
-    TINY  = 0
+    TINY  = 1
 
-    STRING = [MAJOR, MINOR, TINY].join('.')
+    STRING = [MAJOR, MINOR, TINY].join(".")
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: htmlbeautifier
 version: !ruby/object:Gem::Version
-  version: 1.1.0
+  version: 1.1.1
 platform: ruby
 authors:
 - Paul Battley
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-03-07 00:00:00.000000000 Z
+date: 2015-07-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -38,6 +38,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '3'
+- !ruby/object:Gem::Dependency
+  name: rubocop
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.30.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.30.0
 description: A normaliser/beautifier for HTML that also understands embedded Ruby.
 email: pbattley@gmail.com
 executables:
@@ -52,6 +66,7 @@ files:
 - lib/htmlbeautifier/builder.rb
 - lib/htmlbeautifier/html_parser.rb
 - lib/htmlbeautifier/parser.rb
+- lib/htmlbeautifier/ruby_indenter.rb
 - lib/htmlbeautifier/version.rb
 homepage: http://github.com/threedaymonk/htmlbeautifier
 licenses:
@@ -73,7 +88,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.2.2
+rubygems_version: 2.4.5
 signing_key: 
 specification_version: 4
 summary: HTML/ERB beautifier