html_press 0.0.1

data/.gitignore

@@ -0,0 +1,5 @@
+*.gem
+.bundle
+Gemfile.lock
+pkg/*
+/.project

data/Gemfile

@@ -0,0 +1,4 @@
+source "http://rubygems.org"
+
+# Specify your gem's dependencies in html_press.gemspec
+gemspec

data/Rakefile

@@ -0,0 +1 @@
+require "bundler/gem_tasks"

data/Readme.md

@@ -0,0 +1,66 @@
+#html_press
+
+## Alternatives
+
+###Ruby
+
+  - https://github.com/completelynovel/html_compressor
+  - https://github.com/MadRabbit/frontcompiler
+
+###Other
+
+  - http://code.google.com/p/htmlcompressor/
+  - smarty `strip` tag
+  - W3 total cache (WP plugin from smashingmagazine contains html minifier)
+
+## TODO
+
+  - bin
+  - Support other minifiers (Closure, YUI compressor)
+  - htmlTydi
+
+## Usage
+
+### Jekyll
+
+Gemfile
+
+```ruby
+gem "jekyll"
+gem "html_press"
+```
+
+_plugins/strip_tag.rb
+
+```ruby
+module Jekyll
+  class StripTag < Liquid::Block
+    begin
+      require 'html_press'
+      def render(context)
+        text = super
+        HtmlPress.compress text
+      end
+    rescue LoadError => e
+      p "Unable to load 'html_press'"
+    end
+  end
+end
+
+Liquid::Template.register_tag('strip', Jekyll::StripTag)
+```
+
+In templates
+
+```liquid
+{% strip %}
+here goes text...
+{% endstrip %}
+```
+
+Run
+
+```
+bundle install
+bundle exec jelyll
+```

data/html_press.gemspec

@@ -0,0 +1,28 @@
+# -*- encoding: utf-8 -*-
+$:.push File.expand_path("../lib", __FILE__)
+require "html_press/version"
+
+Gem::Specification.new do |s|
+  s.name        = "html_press"
+  s.version     = HtmlPress::VERSION
+  s.authors     = ["stereobooster"]
+  s.email       = ["stereobooster@gmail.com"]
+  s.homepage    = "https://github.com/stereobooster/html_press"
+  s.summary     = %q{Compress html}
+  s.description = %q{Ruby gem for compressing html}
+
+  s.rubyforge_project = "html_press"
+
+  s.files         = `git ls-files`.split("\n")
+  s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  s.require_paths = ["lib"]
+
+  # s.add_dependency "nokogiri"
+
+  s.add_development_dependency "rspec"
+  s.add_development_dependency "rake"
+  
+  s.add_runtime_dependency "rainpress"
+  s.add_runtime_dependency "uglifier"
+end

data/lib/html_press/html.rb

@@ -0,0 +1,181 @@
+module HtmlPress
+  class Html
+
+    def self.compress text
+      Html.new.compile text
+    end
+
+    def compile (html)
+
+      out = html + ""
+
+      @replacement_hash = 'MINIFYHTML' + Time.now.to_i.to_s
+      @placeholders = []
+      @strip_crlf = false
+
+      # replace SCRIPTs (and minify) with placeholders
+      out.gsub! /\s*(<script\b[^>]*?>[\s\S]*?<\/script>)\s*/i do |m|
+        m.gsub!(/^\s+|\s+$/, '')
+        js = m.gsub(/\s*<script\b[^>]*?>([\s\S]*?)<\/script>\s*/i , "\\1")
+        begin
+          js_compressed = HtmlPress.js_compressor js
+          m.gsub!(js, js_compressed)
+        rescue Exception => e
+          # p e.message
+        end
+        reserve m
+      end
+
+      # replace STYLEs (and minify) with placeholders
+      out.gsub! /\s*(<style\b[^>]*?>[\s\S]*?<\/style>)\s*/i do |m|
+        m.gsub!(/^\s+|\s+$/, '')
+        css = m.gsub(/\s*<style\b[^>]*?>([\s\S]*?)<\/style>\s*/i, "\\1")
+        begin
+          css_compressed = HtmlPress.css_compressor css
+          m.gsub!(css, css_compressed)
+        rescue Exception => e
+          # p e.message
+        end
+        reserve m
+      end
+
+      # IE conditional comments
+      out.gsub! /\s*(<!--\[[^\]]+\]>[\s\S]*?<!\[[^\]]+\]-->)\s*/ do |m|
+        m.gsub!(/^\s+|\s+$/, '')
+        comment = m.gsub(/\s*<!--\[[^\]]+\]>([\s\S]*?)<!\[[^\]]+\]-->\s*/, "\\1")
+        comment_compressed = Html.new.compile(comment)
+        m.gsub!(comment, comment_compressed)
+        reserve m
+      end
+
+      # remove out comments (not containing IE conditional comments).
+      out.gsub! /<!--([\s\S]*?)-->/ do |m|
+        ''
+      end
+
+      # replace PREs with placeholders
+      out.gsub! /\s*(<pre\b[^>]*?>[\s\S]*?<\/pre>)\s*/i do |m|
+        pre = m.gsub(/\s*<pre\b[^>]*?>([\s\S]*?)<\/pre>\s*/i, "\\1")
+        pre_compressed = pre.gsub(/\s+$/, '')
+        m.gsub!(pre, pre_compressed)
+        reserve m
+      end
+
+      # replace TEXTAREAs with placeholders
+      out.gsub! /\s*(<textarea\b[^>]*?>[\s\S]*?<\/textarea>)\s*/i do |m|
+        reserve m
+      end
+
+      # trim each line.
+      # @todo take into account attribute values that span multiple lines.
+      out.gsub!(/^\s+|\s+$/m, '')
+
+      re = '\\s+(<\\/?(?:area|base(?:font)?|blockquote|body' +
+        '|caption|center|cite|col(?:group)?|dd|dir|div|dl|dt|fieldset|form' +
+        '|frame(?:set)?|h[1-6]|head|hr|out|legend|li|link|map|menu|meta' +
+        '|ol|opt(?:group|ion)|p|param|t(?:able|body|head|d|h|r|foot|itle)' +
+        '|ul)\\b[^>]*>)'
+
+      re = Regexp.new(re)
+      out.gsub!(re, '\\1')
+
+      # remove ws outside of all elements
+      out.gsub! />([^<]+)</ do |m|
+        m.gsub(/^\s+|\s+$/, ' ')
+      end
+
+      # use newlines before 1st attribute in open tags (to limit line lengths)
+      # out.gsub!(/(<[a-z\-:]+)\s+([^>]+>)/i, "\\1\n\\2")
+
+      # match attributes
+      out.gsub! /<[a-z\-:]+\s([^>]+)>/i do |m|
+        reserve attrs(m, '[a-z\-:]+', true)
+      end
+
+      out.gsub!(/[\r\n]+/, @strip_crlf ? ' ' : "\n")
+
+      out.gsub!(/\s+/, ' ')
+
+      # fill placeholders
+      re = Regexp.new('%' + @replacement_hash + '%(\d+)%')
+      out.gsub! re do |m|
+        m.gsub!(re, "\\1")
+        @placeholders[m.to_i]
+      end
+
+      out
+    end
+
+    def reserve(content)
+      @placeholders.push content
+      '%' + @replacement_hash + '%' + (@placeholders.size - 1).to_s + '%'
+    end
+
+    def attrs (m, tag_name, r)
+      re = "<(" + tag_name + ")(\s[^>]+)?>"
+      re = Regexp.new(re, true)
+      attributes = m.gsub(re, "\\2")
+      if r
+        tag = m.gsub(re, "\\1")
+      else
+        tag = tag_name
+      end
+      
+      if attributes.size > 0
+        attributes_compressed = attributes.gsub(/\s*([a-z\-_]+(="[^"]*")?(='[^']*')?)\s*/i, " \\1")
+  
+        attributes_compressed.gsub! /([a-z\-_]+="[^"]*")/ do |k|
+          attr k, "\"", tag
+        end
+  
+        attributes_compressed.gsub! /([a-z\-_]+='[^']*')/ do |k|
+          attr k, "'", tag
+        end
+  
+        return m.gsub(attributes, attributes_compressed)
+      end
+
+      return m
+    end
+
+    def attr(attribute, delimiter, tag)
+      re = "([a-z\\-_]+)(=" + delimiter + "[^" + delimiter + "]*" + delimiter + ")?"
+      re = Regexp.new re
+      value = attribute.gsub(re, "\\2")
+
+      if tag == "script"
+        name = attribute.gsub(re, "\\1")
+        if name == "type" || name == "language"
+          return ""
+        end
+      end
+
+      if value.size != 0
+
+        name = attribute.gsub(re, "\\1")
+
+        re = "^=" + delimiter + "|" + delimiter + "$"
+        re = Regexp.new re
+        value.gsub!(re, "")
+
+        if name == "style"
+          value = HtmlPress.css_compressor value
+        end
+
+        if name == "class"
+          value.gsub!(/\s+/, " ")
+          value.gsub!(/^\s+|\s+$/, "")
+        end
+
+        # if name == "onclick"
+          # value = HtmlPress.js_compressor value
+        # end
+
+        attribute = name + "=" + delimiter + value + delimiter
+      end
+
+      attribute
+    end
+
+  end
+end

data/lib/html_press/rainpress.rb

@@ -0,0 +1,12 @@
+module HtmlPress
+  begin
+    require 'rainpress'
+    def self.css_compressor (text)
+      Rainpress.compress(text).gsub(/^\s+/m, '')
+    end
+  rescue LoadError => e
+    def self.css_compressor (text)
+      text
+    end
+  end
+end

data/lib/html_press/uglifier.rb

@@ -0,0 +1,12 @@
+module HtmlPress
+  begin
+    require 'uglifier'
+    def self.js_compressor (text)
+      Uglifier.new.compile(text).gsub(/;$/,'')
+    end
+  rescue LoadError => e
+    def self.js_compressor (text)
+      text
+    end
+  end
+end

data/lib/html_press/version.rb

@@ -0,0 +1,3 @@
+module HtmlPress
+  VERSION = "0.0.1"
+end

data/lib/html_press.rb

@@ -0,0 +1,10 @@
+require "html_press/version"
+require "html_press/rainpress"
+require "html_press/uglifier"
+require "html_press/html"
+
+module HtmlPress
+    def self.compress(text)
+      self::Html.new.compile text
+    end
+end

data/spec/html_press_spec.rb

@@ -0,0 +1,98 @@
+# encoding: UTF-8
+
+require_relative "../lib/html_press"
+
+describe HtmlPress do
+  before :each do
+  end
+
+  it "should leave only one whitespace between inline tags" do
+    HtmlPress.compress("<p>lorem  <b>ipsum</b>  <i>dolor</i>  </p>").should eql "<p>lorem <b>ipsum</b> <i>dolor</i></p>"
+  end
+
+  it "should leave no whitespaces between block tags" do
+    HtmlPress.compress("<div></div> \t\r\n  <div></div>").should eql "<div></div><div></div>"
+  end
+
+  it "should leave only one whitespace in text" do
+    HtmlPress.compress("<p>a  a</p>").should eql "<p>a a</p>"
+  end
+
+  it "should leave newlines in pre tags and remove trailing spaces" do
+    HtmlPress.compress("<pre>a \t </pre>").should eql "<pre>a</pre>"
+    HtmlPress.compress("<pre>qwe   \nasd   </pre>").should eql "<pre>qwe\nasd</pre>"
+  end
+
+  it "should leave textareas as is" do
+    text = "<textarea> \t </textarea>"
+    HtmlPress.compress(text).should eql text
+  end
+
+  it "should compress js in script tags" do
+    script = "  (function(undefined){ \t\n var long_name = '  '; }())  \n \r"
+    compressed_script = "<script>" + HtmlPress.js_compressor(script) + "</script>"
+    script = "  <script>" + script + "</script>  "
+    HtmlPress.compress(script).should eql compressed_script
+  end
+
+  it "should compress css in style tags" do
+    style = "  div { margin: 0px 0px; \n}  "
+    compressed_style = "<style>" + HtmlPress.css_compressor(style) + "</style>"
+    style = "  <style>" + style + "</style>  "
+    HtmlPress.compress(style).should eql compressed_style
+  end
+
+  it "should remove html comments" do
+    HtmlPress.compress("<p></p><!-- comment  --><p></p>").should eql "<p></p><p></p>"
+  end
+
+  it "should leave IE conditional comments" do
+    text = "<!--[if IE]><html class=\"ie\"><![endif]--><div></div>"
+    HtmlPress.compress(text).should eql text
+  end
+
+  it "should remove unnecessary whitespaces between attributes" do
+    HtmlPress.compress("<p class=\"a\"   id=\"b\"></p>").should eql "<p class=\"a\" id=\"b\"></p>"
+  end
+
+  it "should leave whitespaces everywhere else" do
+    text = "<a onclick=\"alert('     ')\" unknown_attr='   a  a'>a</a>"
+    HtmlPress.compress(text).should eql text
+  end
+
+  it "should work with special utf-8 symbols" do
+    HtmlPress.compress("✪<p></p>  <p></p>").should eql "✪<p></p><p></p>"
+  end
+
+  it "should work with tags in upper case" do
+    HtmlPress.compress("<P>  </p>").should eql "<P></p>"
+  end
+
+  it "should remove whitespaces between IE conditional comments" do
+    text = "<p></p>  <!--[if IE]><html class=\"ie\">      <![endif]--> <!--[if IE]><html class=\"ie1\"><![endif]-->"
+    text2 = "<p></p><!--[if IE]><html class=\"ie\"><![endif]--><!--[if IE]><html class=\"ie1\"><![endif]-->"
+    HtmlPress.compress(text).should eql text2
+  end
+
+  it "should treat text inside IE conditional comments as it was without comments" do
+    text = "<div class=\"a\"   id=\"b\">    </div>    <p></p>"
+    text2 = HtmlPress.compress(text)
+    text = "<!--[if IE]>" + text + "<![endif]-->"
+    text2 = "<!--[if IE]>" + text2 + "<![endif]-->"
+    HtmlPress.compress(text).should eql text2
+  end
+
+  it "should remove unnecessary whitespaces in html attributes (class)" do
+    HtmlPress.compress("<p class=\"a  b\"></p>").should eql "<p class=\"a b\"></p>"
+    HtmlPress.compress("<p class='a  b'></p>").should eql "<p class='a b'></p>"
+  end
+
+  it "should remove unnecessary whitespaces in html attributes (style)" do
+    HtmlPress.compress("<p style=\"display: none;\"></p>").should eql "<p style=\"display:none;\"></p>"
+  end
+
+  # it "should remove unnecessary attributes" do
+    # HtmlPress.compress("<script type=\"text/javascript\">var a;</script>").should eql "<script>var a;</script>"
+  # end
+
+end

metadata

@@ -0,0 +1,100 @@
+--- !ruby/object:Gem::Specification
+name: html_press
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+  prerelease: 
+platform: ruby
+authors:
+- stereobooster
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2012-02-04 00:00:00.000000000Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: &19832364 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: *19832364
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: &20531592 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: *20531592
+- !ruby/object:Gem::Dependency
+  name: rainpress
+  requirement: &20756364 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *20756364
+- !ruby/object:Gem::Dependency
+  name: uglifier
+  requirement: &21077148 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *21077148
+description: Ruby gem for compressing html
+email:
+- stereobooster@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- Rakefile
+- Readme.md
+- html_press.gemspec
+- lib/html_press.rb
+- lib/html_press/html.rb
+- lib/html_press/rainpress.rb
+- lib/html_press/uglifier.rb
+- lib/html_press/version.rb
+- spec/html_press_spec.rb
+homepage: https://github.com/stereobooster/html_press
+licenses: []
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: html_press
+rubygems_version: 1.8.15
+signing_key: 
+specification_version: 3
+summary: Compress html
+test_files: []