htmlbeautifier 0.0.2

data/README.txt

@@ -0,0 +1,16 @@
+= HTML Beautifier
+
+A normaliser/beautifier for HTML that also understands embedded Ruby. Ideal for tidying up Rails templates.
+
+== What it does
+
+* Normalises hard tabs to spaces
+* Removes trailing spaces
+* Indents after opening HTML elements
+* Outdents before closing elements
+* Collapses multiple whitespace
+* Indents after block-opening embedded Ruby (if, do etc.)
+* Outdents before closing Ruby blocks
+* Outdents elsif and then indents again
+* Indents the left-hand margin of JavaScript and CSS blocks to match the indentation level of the code
+

data/Rakefile

@@ -0,0 +1,93 @@
+require 'rake'
+require 'rake/testtask'
+
+task :default => :test
+
+Rake::TestTask.new(:test) do |t|
+  t.libs << 'lib'
+  t.pattern = 'test/test_*.rb'
+  t.verbose = true
+end
+
+desc 'Install libraries and command-line utility'
+task :install do |t|
+  sh 'ruby setup.rb'
+end
+
+desc 'Clean up files left over after installation'
+task :cleanup do |t|
+  rm_f 'InstalledFiles'
+  rm_f '.config'
+end
+
+
+require "rubygems"
+require "rake/gempackagetask"
+require "rake/rdoctask"
+
+task :default => :test
+
+require "rake/testtask"
+Rake::TestTask.new do |t|
+  t.libs << "test"
+  t.test_files = FileList["test/**/*_test.rb"]
+  t.verbose = true
+end
+
+# This builds the actual gem. For details of what all these options
+# mean, and other ones you can add, check the documentation here:
+#
+#   http://rubygems.org/read/chapter/20
+#
+require "lib/htmlbeautifier/version"
+spec = Gem::Specification.new do |s|
+
+  # Change these as appropriate
+  s.name              = "htmlbeautifier"
+  s.version           = HtmlBeautifier::VERSION::STRING
+  s.summary           = "A normaliser/beautifier for HTML that also understands embedded Ruby."
+  s.author            = "Paul Battley"
+  s.email             = "pbattley@gmail.com"
+  s.homepage          = "http://github.com/threedaymonk/htmlbeautifier"
+
+  s.has_rdoc          = true
+  s.extra_rdoc_files  = %w(README.txt)
+  s.rdoc_options      = %w(--main README.txt)
+
+  # Add any extra files to include in the gem
+  s.files             = %w(Rakefile README.txt) + Dir.glob("{bin,test,lib}/**/*")
+  s.executables       = FileList["bin/**"].map { |f| File.basename(f) }
+
+  s.require_paths     = ["lib"]
+
+  # If you want to depend on other gems, add them here, along with any
+  # relevant versions
+  # s.add_dependency("some_other_gem", "~> 0.1.0")
+
+  # If your tests use any gems, include them here
+  # s.add_development_dependency("mocha")
+end
+
+# This task actually builds the gem. We also regenerate a static
+# .gemspec file, which is useful if something (i.e. GitHub) will
+# be automatically building a gem for this project. If you're not
+# using GitHub, edit as appropriate.
+Rake::GemPackageTask.new(spec) do |pkg|
+  pkg.gem_spec = spec
+
+  # Generate the gemspec file for github.
+  file = File.dirname(__FILE__) + "/#{spec.name}.gemspec"
+  File.open(file, "w") {|f| f << spec.to_ruby }
+end
+
+# Generate documentation
+Rake::RDocTask.new do |rd|
+  rd.main = "README.txt"
+  rd.rdoc_files.include("README.txt", "lib/**/*.rb")
+  rd.rdoc_dir = "rdoc"
+end
+
+desc 'Clear out RDoc and generated packages'
+task :clean => [:clobber_rdoc, :clobber_package] do
+  rm "#{spec.name}.gemspec"
+end

data/bin/htmlbeautifier

@@ -0,0 +1,4 @@
+#!/usr/bin/env ruby
+require 'htmlbeautifier/beautifier'
+HtmlBeautifier::Beautifier.new($stdout).scan($stdin.read)
+$stdout << "\n"

data/lib/htmlbeautifier.rb

@@ -0,0 +1,5 @@
+$:.unshift File.dirname(__FILE__)
+
+module HtmlBeautifier
+
+end

data/lib/htmlbeautifier/beautifier.rb

@@ -0,0 +1,115 @@
+require 'htmlbeautifier/parser'
+
+module HtmlBeautifier
+  class Beautifier
+
+    RUBY_INDENT  =
+      %r{ ^ ( if | unless | while | begin | elsif )\b
+        | \b ( do | \{ ) ( \s* \| [^\|]+ \| )? $
+        }x
+    RUBY_OUTDENT =
+      %r{ ^ ( end | elsif |\} ) \b
+        }x
+    ELEMENT_CONTENT = %r{ (?:[^<>]|<%.*?%>)* }mx
+
+    def initialize(output)
+      @level = 0
+      @new_line = true
+      self.tab_stops = 2
+      @output = output
+    end
+
+    def tab_stops=(n)
+      @tab = ' ' * n
+    end
+
+    def indent
+      @level += 1
+    end
+
+    def outdent
+      @level -= 1
+      raise "Outdented too far" if @level < 0
+    end
+
+    def emit(s)
+      if (@new_line)
+        @output << (@tab * @level)
+      end
+      @output << s
+      @new_line = false
+    end
+
+    def whitespace(*x)
+      emit "\n"
+      @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
+    end
+
+    def foreign_block(opening, code, closing)
+      emit opening
+      unless code.empty?
+        indent
+
+        lines = code.split(/\n/)
+        lines.shift while lines.first.strip.empty?
+        lines.pop while lines.last.strip.empty?
+        indentation = lines.first[/^ +/]
+
+        whitespace
+        lines.each do |line|
+          emit line.rstrip.sub(/^#{indentation}/, '')
+          whitespace
+        end
+
+        outdent
+      end
+      emit closing
+    end
+
+    def standalone_element(e)
+      emit e
+    end
+
+    def close_element(e)
+      outdent
+      emit e
+    end
+
+    def open_element(e)
+      emit e
+      indent
+    end
+
+    def text(t)
+      emit(t.strip)
+      whitespace if t =~ /\s$/
+    end
+
+    def scan(html)
+      html = html.strip.gsub(/\t/, @tab)
+      parser = Parser.new do
+        map %r{(<%=?)(.*?)(%>)}m,                               :embed
+        map %r{<!--\[.*?\]>}m,                                  :open_element
+        map %r{<!\[.*?\]-->}m,                                  :close_element
+        map %r{<!--.*?-->}m,                                    :standalone_element
+        map %r{<!.*?>}m,                                        :standalone_element
+        map %r{(<script#{ELEMENT_CONTENT}>)(.*?)(</script>)}m,  :foreign_block
+        map %r{(<style#{ELEMENT_CONTENT}>)(.*?)(</style>)}m,    :foreign_block
+        map %r{<#{ELEMENT_CONTENT}/>}m,                         :standalone_element
+        map %r{</#{ELEMENT_CONTENT}>}m,                         :close_element
+        map %r{<#{ELEMENT_CONTENT}>}m,                          :open_element
+        map %r{\s+},                                            :whitespace
+        map %r{[^<]+},                                          :text
+      end
+      parser.scan(html, self)
+    end
+
+  end
+end

data/lib/htmlbeautifier/parser.rb

@@ -0,0 +1,53 @@
+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)
+      @maps = []
+      if block_given?
+        self.instance_eval(&blk)
+      end
+    end
+
+    def map(pattern, method)
+      @maps << [pattern, method]
+    end
+
+    def scan(subject, receiver)
+      scanner = StringScanner.new(subject)
+      until scanner.eos?
+        dispatch(scanner, receiver)
+      end
+    end
+
+    def dispatch(scanner, 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 #{match.inspect}"
+    end
+
+  end
+end

data/lib/htmlbeautifier/version.rb

@@ -0,0 +1,9 @@
+module HtmlBeautifier #:nodoc:
+  module VERSION #:nodoc:
+    MAJOR = 0
+    MINOR = 0
+    TINY  = 2
+
+    STRING = [MAJOR, MINOR, TINY].join('.')
+  end
+end

data/test/html_beautifier_test_utilities.rb

@@ -0,0 +1,19 @@
+module HtmlBeautifierTestUtilities
+
+  def code(str)
+    str = str.gsub(/\A\n|\n\s*\Z/, '')
+    indentation = str[/\A +/]
+    lines = str.split(/\n/)
+    lines.map{ |line| line.sub(/^#{indentation}/, '') }.join("\n")
+  end
+
+  def assert_beautifies(expected, source)
+    actual = ''
+    beautifier = HtmlBeautifier::Beautifier.new(actual)
+    beautifier.scan(source)
+    # puts expected
+    # puts actual
+    assert_equal expected, actual
+  end
+
+end

data/test/test_helper.rb

@@ -0,0 +1,3 @@
+require 'test/unit'
+require File.dirname(__FILE__) + '/html_beautifier_test_utilities'
+require File.dirname(__FILE__) + '/../lib/htmlbeautifier'

data/test/test_html_beautifier_integration.rb

@@ -0,0 +1,82 @@
+require File.dirname(__FILE__) + '/test_helper'
+
+class TestHtmlBeautifierIntegration < Test::Unit::TestCase
+  include HtmlBeautifierTestUtilities
+
+  def test_should_correctly_indent_mixed_document
+    source = code(%q(
+      <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
+      <html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en">
+      <head>
+      <meta http-equiv="content-type" content="text/html; charset=utf-8" />
+      <script src="/javascripts/prototype.js" type="text/javascript"></script>
+      <link rel="stylesheet" type="text/css" href="/stylesheets/screen.css" media="screen"/>
+      <!--[if IE 6]>
+      <link rel="stylesheet" href="/stylesheets/screen_ie6.css" type="text/css" />
+      <![endif]-->
+      <title>Title Goes Here</title>
+      <script type="text/javascript" charset="utf-8">
+      doSomething();
+      </script>
+      </head>
+      <body>
+      <div id="something">
+      <h1>
+      Heading 1
+      </h1>
+      </div>
+      <div id="somethingElse">
+      <p>Lorem Ipsum</p>
+      <% if @x %>
+      <% @ys.each do |y| %>
+      <p>
+      <%= h y %>
+      </p>
+      <% end %>
+      <% elsif @z %>
+      <hr />
+      <% end %>
+      </div>
+      </body>
+      </html>
+    ))
+    expected = code(%q(
+      <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
+      <html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en">
+        <head>
+          <meta http-equiv="content-type" content="text/html; charset=utf-8" />
+          <script src="/javascripts/prototype.js" type="text/javascript"></script>
+          <link rel="stylesheet" type="text/css" href="/stylesheets/screen.css" media="screen"/>
+          <!--[if IE 6]>
+            <link rel="stylesheet" href="/stylesheets/screen_ie6.css" type="text/css" />
+          <![endif]-->
+          <title>Title Goes Here</title>
+          <script type="text/javascript" charset="utf-8">
+            doSomething();
+          </script>
+        </head>
+        <body>
+          <div id="something">
+            <h1>
+              Heading 1
+            </h1>
+          </div>
+          <div id="somethingElse">
+            <p>Lorem Ipsum</p>
+            <% if @x %>
+              <% @ys.each do |y| %>
+                <p>
+                  <%= h y %>
+                </p>
+              <% end %>
+            <% elsif @z %>
+              <hr />
+            <% end %>
+          </div>
+        </body>
+      </html>
+    ))
+    assert_beautifies expected, source
+  end
+
+end

data/test/test_html_beautifier_regression.rb

@@ -0,0 +1,181 @@
+require File.dirname(__FILE__) + '/test_helper'
+require 'htmlbeautifier/beautifier'
+
+class HtmlBeautifierRegressionTest < Test::Unit::TestCase
+
+  include HtmlBeautifierTestUtilities
+
+  def setup
+    # HtmlBeautifier::Parser.debug_block{ |match, method| puts("#{match.inspect} => #{method}") }
+  end
+
+  def test_should_ignore_html_fragments_in_embedded_code
+    source = code(%q(
+      <div>
+        <%= a[:b].gsub("\n","<br />\n") %>
+      </div>
+    ))
+    expected = code(%q(
+      <div>
+        <%= a[:b].gsub("\n","<br />\n") %>
+      </div>
+    ))
+    assert_beautifies expected, source
+  end
+
+  def test_should_indent_scripts
+    source = code(%q(
+      <script>
+      function(f) {
+          g();
+          return 42;
+      }
+      </script>
+    ))
+    expected = code(%q(
+      <script>
+        function(f) {
+            g();
+            return 42;
+        }
+      </script>
+    ))
+    assert_beautifies expected, source
+  end
+
+  def test_should_remove_blank_lines_around_scripts
+    source = code(%q(
+      <script>
+
+        f();
+
+      </script>
+    ))
+    expected = code(%q(
+      <script>
+        f();
+      </script>
+    ))
+    assert_beautifies expected, source
+  end
+
+  def test_should_remove_trailing_space_from_script_lines
+    source = code(%q(
+      <script>
+        f();
+      </script>
+    ))
+    expected = code(%q(
+      <script>
+        f();
+      </script>
+    ))
+    assert_beautifies expected, source
+  end
+
+  def test_should_skip_over_empty_scripts
+    source = %q(<script src="/foo.js" type="text/javascript" charset="utf-8"></script>)
+    expected = source
+    assert_beautifies expected, source
+  end
+
+  def test_should_indent_styles
+    source = code(%q(
+      <style>
+      .foo{ margin: 0; }
+      .bar{
+        padding: 0;
+        margin: 0;
+      }
+      </style>
+    ))
+    expected = code(%q(
+      <style>
+        .foo{ margin: 0; }
+        .bar{
+          padding: 0;
+          margin: 0;
+        }
+      </style>
+    ))
+    assert_beautifies expected, source
+  end
+
+  def test_should_remove_blank_lines_around_styles
+    source = code(%q(
+      <style>
+
+        .foo{ margin: 0; }
+
+      </style>
+    ))
+    expected = code(%q(
+      <style>
+        .foo{ margin: 0; }
+      </style>
+    ))
+    assert_beautifies expected, source
+  end
+
+  def test_should_remove_trailing_space_from_style_lines
+    source = code(%q(
+      <style>
+        .foo{ margin: 0; }
+      </style>
+    ))
+    expected = code(%q(
+      <style>
+        .foo{ margin: 0; }
+      </style>
+    ))
+    assert_beautifies expected, source
+  end
+
+  def test_should_indent_divs_containing_standalone_elements
+    source = code(%q(
+      <div>
+        <div>
+          <img src="foo" alt="" />
+        </div>
+        <div>
+          <img src="foo" alt="" />
+        </div>
+      </div>
+    ))
+    expected = source
+    assert_beautifies expected, source
+  end
+
+  def test_should_not_break_line_on_embedded_code_within_script_opening_element
+    source = '<script src="<%= path %>" type="text/javascript"></script>'
+    expected = source
+    assert_beautifies expected, source
+  end
+
+  def test_should_not_break_line_on_embedded_code_within_normal_element
+    source = '<img src="<%= path %>" alt="foo" />'
+    expected = source
+    assert_beautifies expected, source
+  end
+
+  def test_should_indent_inside_IE_conditional_comments
+    source = code(%q(
+      <!--[if IE 6]>
+      <link rel="stylesheet" href="/stylesheets/ie6.css" type="text/css" />
+      <![endif]-->
+      <!--[if IE 5]>
+      <link rel="stylesheet" href="/stylesheets/ie5.css" type="text/css" />
+      <![endif]-->
+    ))
+    expected = code(%q(
+      <!--[if IE 6]>
+        <link rel="stylesheet" href="/stylesheets/ie6.css" type="text/css" />
+      <![endif]-->
+      <!--[if IE 5]>
+        <link rel="stylesheet" href="/stylesheets/ie5.css" type="text/css" />
+      <![endif]-->
+    ))
+    assert_beautifies expected, source
+  end
+
+end

data/test/test_parser.rb

@@ -0,0 +1,42 @@
+require File.dirname(__FILE__) + '/test_helper'
+require 'htmlbeautifier/parser'
+
+class TestParser < Test::Unit::TestCase
+
+  class Receiver
+    attr_reader :sequence
+
+    def initialize
+      @sequence = []
+    end
+
+    def method_missing(method, *params)
+      @sequence << [method, params]
+    end
+  end
+
+  def setup
+    # HtmlBeautifier::Parser.debug_block{ |match, method| puts("#{match.inspect} => #{method}") }
+  end
+
+  def test_should_dispatch_matching_sequence
+    receiver = Receiver.new
+    parser = HtmlBeautifier::Parser.new{
+      map %r{foo}, :foo
+      map %r{bar\s*}, :bar
+      map %r{\s+}, :whitespace
+    }
+    parser.scan('foo bar ', receiver)
+    assert_equal [[:foo, ['foo']], [:whitespace, [' ']], [:bar, ['bar ']]], receiver.sequence
+  end
+
+  def test_should_send_parenthesized_components_as_separate_parameters
+    receiver = Receiver.new
+    parser = HtmlBeautifier::Parser.new{
+      map %r{(foo)\((.*?)\)}, :foo
+    }
+    parser.scan('foo(bar)', receiver)
+    assert_equal [[:foo, ['foo', 'bar']]], receiver.sequence
+  end
+
+end

metadata

@@ -0,0 +1,67 @@
+--- !ruby/object:Gem::Specification 
+name: htmlbeautifier
+version: !ruby/object:Gem::Version 
+  version: 0.0.2
+platform: ruby
+authors: 
+- Paul Battley
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2009-10-11 00:00:00 +01:00
+default_executable: 
+dependencies: []
+
+description: 
+email: pbattley@gmail.com
+executables: 
+- htmlbeautifier
+extensions: []
+
+extra_rdoc_files: 
+- README.txt
+files: 
+- Rakefile
+- README.txt
+- bin/htmlbeautifier
+- test/test_html_beautifier_regression.rb
+- test/test_parser.rb
+- test/test_helper.rb
+- test/test_html_beautifier_integration.rb
+- test/html_beautifier_test_utilities.rb
+- lib/htmlbeautifier/parser.rb
+- lib/htmlbeautifier/beautifier.rb
+- lib/htmlbeautifier/version.rb
+- lib/htmlbeautifier.rb
+has_rdoc: true
+homepage: http://github.com/threedaymonk/htmlbeautifier
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --main
+- README.txt
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.5
+signing_key: 
+specification_version: 3
+summary: A normaliser/beautifier for HTML that also understands embedded Ruby.
+test_files: []
+