html_press 0.6.7 → 0.7.0

data/.gitignore

@@ -2,4 +2,5 @@
 .bundle
 Gemfile.lock
 pkg/*
+profile/reports/*
 /.project

data/Gemfile

@@ -2,3 +2,5 @@ source "http://rubygems.org"
 
 # Specify your gem's dependencies in html_press.gemspec
 gemspec
+
+gem "ruby-prof", :platforms => :mri

data/Rakefile

@@ -1,10 +1,10 @@
-require "bundler/gem_tasks"
-
-[:build, :install, :release].each do |task_name|
-  Rake::Task[task_name].prerequisites << :spec
-end
-
-require "rspec/core/rake_task"
-RSpec::Core::RakeTask.new
-
-task :default => :spec
+require "bundler/gem_tasks"
+
+[:build, :install, :release].each do |task_name|
+  Rake::Task[task_name].prerequisites << :spec
+end
+
+require "rspec/core/rake_task"
+RSpec::Core::RakeTask.new
+
+task :default => :spec

data/Readme.md

@@ -39,6 +39,9 @@ TODO :exclamation:
   - Support other js/css minifiers (Closure, YUI compressor)
   - htmlTydi
   - Rack plugin
+  - add script to benchmark real projects like amazon or stackoverflow
+  - support html5 tags
+  - add more options
 
 ## Alternatives
   - [html-minifier](https://github.com/kangax/html-minifier) (js), [test suite](https://github.com/kangax/html-minifier/blob/gh-pages/tests/index.html), ruby wrapper - [html_minifier](https://github.com/stereobooster/html_minifier)

data/html_press.gemspec

@@ -1,29 +1,29 @@
-# -*- encoding: utf-8 -*-
-$:.push File.expand_path("../lib", __FILE__)
-require "html_press/version"
-
-Gem::Specification.new do |s|
-  s.name        = "html_press"
-  s.version     = HtmlPress::VERSION
-  s.authors     = ["stereobooster"]
-  s.email       = ["stereobooster@gmail.com"]
-  s.homepage    = "https://github.com/stereobooster/html_press"
-  s.summary     = %q{Compress html}
-  s.description = %q{Ruby gem for compressing html}
-
-  s.rubyforge_project = "html_press"
-
-  s.files         = `git ls-files`.split("\n")
-  s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
-  s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
-  s.require_paths = ["lib"]
-
-  # s.add_dependency "nokogiri"
-
-  s.add_development_dependency "rspec"
-  s.add_development_dependency "rake"
-  
-  s.add_runtime_dependency "css_press", ">=0.3.2"
-  s.add_runtime_dependency "uglifier"
-  s.add_runtime_dependency "htmlentities"
-end
+# -*- encoding: utf-8 -*-
+$:.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 "css_press", ">=0.3.2"
+  s.add_runtime_dependency "uglifier"
+  s.add_runtime_dependency "htmlentities"
+end

data/lib/html_press/html.rb

@@ -4,7 +4,8 @@ module HtmlPress
     DEFAULTS = {
       :logger => false,
       :unquoted_attributes => false,
-      :drop_empty_values => false 
+      :drop_empty_values => false,
+      :strip_crlf => false
     }
 
     def initialize (options = {})
@@ -13,38 +14,62 @@ module HtmlPress
         @options[:drop_empty_values] = @options.delete(:dump_empty_values)
         warn "dump_empty_values deprecated use drop_empty_values"
       end
-    end
-
-    def log (text)
-      if @options[:logger] && @options[:logger].respond_to?(:call)
-        @options[:logger].call text
+      if @options[:logger] && !@options[:logger].respond_to?(:error)
+        raise ArgumentError, 'Logger has no error method'
       end
     end
 
     def press (html)
-
       out = html.respond_to?(:read) ? html.read : html.dup
 
       @replacement_hash = 'MINIFYHTML' + Time.now.to_i.to_s
       @placeholders = []
-      @strip_crlf = false
 
-      # 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)
+      out = process_ie_conditional_comments out
+      out = process_scripts out
+      out = process_styles out
+      out = process_html_comments out
+      out = process_pres out
+
+      out = HtmlPress.entities_compressor out
+
+      out = trim_lines out
+      out = process_block_elements out
+      out = process_textareas out
+
+      # use newlines before 1st attribute in open tags (to limit line lengths)
+      # out.gsub!(/(<[a-z\-:]+)\s+([^>]+>)/i, "\\1\n\\2")
+
+      out = process_attributes out
+      out = process_whitespaces out
+      out = fill_placeholders out
+
+      out
+    end
+
+    # for backward compatibility
+    alias :compile :press
+
+    protected
+
+    # IE conditional comments
+    def process_ie_conditional_comments (out)
+      out.gsub /(<!--\[[^\]]+\]>([\s\S]*?)<!\[[^\]]+\]-->)\s*/ do
+        m = $1
+        comment = $2
+        comment_compressed = Html.new.press(comment)
         m.gsub!(comment, comment_compressed)
         reserve m
       end
+    end
 
-      # replace SCRIPTs (and minify) with placeholders
-      out.gsub! /\s*(<script\b[^>]*?>[\s\S]*?<\/script>)\s*/i do |m|
-        m.gsub!(/^\s+|\s+$/, '')
-        m = m.gsub /^<script\s([^>]+)>/i do |m|
+    # replace SCRIPTs (and minify) with placeholders
+    def process_scripts (out)
+      out.gsub /(<script\b[^>]*?>([\s\S]*?)<\/script>)\s*/i do
+        js = $2
+        m = $1.gsub /^<script\s([^>]+)>/i do |m|
           attrs(m, 'script', true)
         end
-        js = m.gsub(/^<script\b[^>]*?>([\s\S]*?)<\/script>/i , "\\1")
         begin
           js_compressed = HtmlPress.js_compressor js
           m.gsub!(js, js_compressed)
@@ -53,14 +78,15 @@ module HtmlPress
         end
         reserve m
       end
+    end
 
-      # replace STYLEs (and minify) with placeholders
-      out.gsub! /\s*(<style\b[^>]*?>[\s\S]*?<\/style>)\s*/i do |m|
-        m.gsub!(/^\s+|\s+$/, '')
-        m = m.gsub /^<style\s([^>]+)>/i do |m|
+    # replace STYLEs (and minify) with placeholders
+    def process_styles (out)
+      out.gsub /(<style\b[^>]*?>([\s\S]*?)<\/style>)\s*/i do
+        css = $2
+        m = $1.gsub /^<style\s([^>]+)>/i do |m|
           attrs(m, 'style', true)
         end
-        css = m.gsub(/^<style\b[^>]*?>([\s\S]*?)<\/style>/i, "\\1")
         begin
           css_compressed = HtmlPress.style_compressor css
           m.gsub!(css, css_compressed)
@@ -69,31 +95,32 @@ module HtmlPress
         end
         reserve m
       end
+    end
 
-      # remove out comments (not containing IE conditional comments).
-      out.gsub! /<!--([\s\S]*?)-->/ do |m|
-        ''
-      end
+    # remove html comments (not IE conditional comments)
+    def process_html_comments (out)
+      out.gsub /<!--([\s\S]*?)-->/, ''
+    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")
+    # replace PREs with placeholders
+    def process_pres (out)
+      out.gsub /(<pre\b[^>]*?>([\s\S]*?)<\/pre>)\s*/i do
+        pre = $2
+        m = $1
         pre_compressed = pre.gsub(/\s+$/, '')
         pre_compressed = HtmlPress.entities_compressor pre_compressed
         m.gsub!(pre, pre_compressed)
         reserve m
       end
+    end
 
-      out = HtmlPress.entities_compressor out
-
-      # replace TEXTAREAs with placeholders
-      out.gsub! /\s*(<textarea\b[^>]*?>[\s\S]*?<\/textarea>)\s*/i do |m|
-        reserve m
-      end
-
-      # trim each line.
-      out.gsub!(/^\s+|\s+$/m, '')
+    # trim each line
+    def trim_lines (out)
+      out.gsub(/^\s+|\s+$/m, '')
+    end
 
+    # remove whitespaces outside of block elements
+    def process_block_elements (out)
       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|html|legend|li|link|map|menu|meta' +
@@ -103,34 +130,49 @@ module HtmlPress
       re = Regexp.new(re)
       out.gsub!(re, '\\1')
 
-      # remove ws outside of all elements
+      # remove whitespaces 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")
+      out
+    end
 
-      # match attributes
-      out.gsub! /<[a-z\-:]+\s([^>]+)>/i do |m|
-        reserve attrs(m, '[a-z\-:]+', true)
+    # replace TEXTAREAs with placeholders
+    def process_textareas (out)
+      out.gsub /(<textarea\b[^>]*?>[\s\S]*?<\/textarea>)\s*/i do |m|
+        reserve m
       end
+    end
 
-      out.gsub!(/[\r\n]+/, @strip_crlf ? ' ' : "\n")
+    # attributes
+    def process_attributes (out)
+      out.gsub /<[a-z\-:]+\s([^>]+)>/i do |m|
+        reserve attrs(m, '[a-z\-:]+', true)
+      end
+    end
 
+    # replace two or more whitespaces with one
+    def process_whitespaces (out)
+      out.gsub!(/[\r\n]+/, @options[:strip_crlf] ? ' ' : "\n")
       out.gsub!(/\s+/, ' ')
+      out
+    end
 
-      # fill placeholders
+    # fill placeholders
+    def fill_placeholders (out)
       re = Regexp.new('%' + @replacement_hash + '%(\d+)%')
-      out.gsub! re do |m|
+      out.gsub re do |m|
         m.gsub!(re, "\\1")
         @placeholders[m.to_i]
       end
+    end
 
-      out
+    def log (text)
+      @options[:logger].error text if @options[:logger]
     end
 
-    def reserve(content)
+    def reserve (content)
       @placeholders.push content
       '%' + @replacement_hash + '%' + (@placeholders.size - 1).to_s + '%'
     end
@@ -146,7 +188,7 @@ module HtmlPress
       end
       
       if attributes.size > 0
-        attributes_compressed = attributes.gsub(/\s*([a-z\-_:]+(="[^"]*")?(='[^']*')?)\s*/i, " \\1")
+        attributes_compressed = attributes.gsub(/([a-z\-_:]+(="[^"]*")?(='[^']*')?)\s*/i, " \\1")
   
         attributes_compressed.gsub! /([a-z\-_:]+="[^"]*")/i do |k|
           attr k, "\"", tag
@@ -278,8 +320,5 @@ module HtmlPress
       attribute
     end
 
-    # for backward compatibility
-    alias :compile :press
-
   end
 end

data/lib/html_press/version.rb

@@ -1,3 +1,3 @@
 module HtmlPress
-  VERSION = "0.6.7"
+  VERSION = "0.7.0"
 end

data/lib/html_press.rb

@@ -1,17 +1,17 @@
-require "html_press/version"
-require "html_press/css_press"
-require "html_press/uglifier"
-require "html_press/html_entities"
-require "html_press/html"
-
-module HtmlPress
-  def self.press(text, options = {})
-    HtmlPress::Html.new(options).press text
-  end
-
-  # for backward compatibility
-  def self.compress(text, options = {})
-    HtmlPress::Html.new(options).press text
-  end
-
-end
+require "html_press/version"
+require "html_press/css_press"
+require "html_press/uglifier"
+require "html_press/html_entities"
+require "html_press/html"
+
+module HtmlPress
+  def self.press(text, options = {})
+    HtmlPress::Html.new(options).press text
+  end
+
+  # for backward compatibility
+  def self.compress(text, options = {})
+    HtmlPress::Html.new(options).press text
+  end
+
+end