Merge branch 'possible-speedups' into dsl

6 files changed, 57 insertions, 38 deletions

diff --git a/lib/coderay/encoders/html.rb b/lib/coderay/encoders/html.rb
index 942b9c8..55b1291 100644
--- a/lib/coderay/encoders/html.rb
+++ b/lib/coderay/encoders/html.rb
@@ -129,11 +129,10 @@ module Encoders
     
     def self.make_html_escape_hash
       {
-        '&' => '&',
-        '"' => '"',
-        '>' => '>',
-        '<' => '&lt;',
-        # "\t" => will be set to ' ' * options[:tab_width] during setup
+        '&'  => '&amp;',
+        '>'  => '&gt;',
+        '<'  => '&lt;',
+        "\t" => ' ' * DEFAULT_OPTIONS[:tab_width],
       }.tap do |hash|
         # Escape ASCII control codes except \x9 == \t and \xA == \n.
         (Array(0x00..0x8) + Array(0xB..0x1F)).each { |invalid| hash[invalid.chr] = ' ' }
@@ -141,7 +140,7 @@ module Encoders
     end
     
     HTML_ESCAPE = make_html_escape_hash
-    HTML_ESCAPE_PATTERN = /[\t"&><\0-\x8\xB-\x1F]/
+    HTML_ESCAPE_PATTERN = /[\t&><\0-\x8\xB-\x1F]/
     
     TOKEN_KIND_TO_INFO = Hash.new do |h, kind|
       h[kind] = kind.to_s.gsub(/_/, ' ').gsub(/\b\w/) { $&.capitalize }
@@ -181,7 +180,7 @@ module Encoders
       
       @break_lines = (options[:break_lines] == true)
       
-      @HTML_ESCAPE = HTML_ESCAPE.merge("\t" => options[:tab_width] ? ' ' * options[:tab_width] : "\t")
+      @escape_cache = make_escape_cache(options)
       
       @opened = []
       @last_opened = nil
@@ -198,7 +197,7 @@ module Encoders
         @last_opened = nil
       end
       
-      if @out.respond_to? :to_str
+      if options[:wrap] || options[:line_numbers]
         @out.extend Output
         @out.css = @css
         if options[:line_numbers]
@@ -221,7 +220,7 @@ module Encoders
     def text_token text, kind
       style = @span_for_kinds[@last_opened ? [kind, *@opened] : kind]
       
-      text = text.gsub(/#{HTML_ESCAPE_PATTERN}/o) { |m| @HTML_ESCAPE[m] } if text =~ /#{HTML_ESCAPE_PATTERN}/o
+      text = @escape_cache[text] if text.size <= 1 || text =~ /#{HTML_ESCAPE_PATTERN}/o
       text = break_lines(text, style) if @break_lines && (style || @opened.size > 0) && text.index("\n")
       
       if style
@@ -277,6 +276,26 @@ module Encoders
       options[:break_lines] = true if options[:line_numbers] == :inline
     end
     
+    def make_escape_cache options
+      html_escape =
+        if options[:tab_width] == DEFAULT_OPTIONS[:tab_width]
+          HTML_ESCAPE
+        else
+          HTML_ESCAPE.merge("\t" => options[:tab_width] ? ' ' * options[:tab_width] : "\t")
+        end
+      
+      Hash.new do |cache, text|
+        cache.clear if cache.size >= 100
+        
+        cache[text] =
+          if text =~ /#{HTML_ESCAPE_PATTERN}/o
+            text.gsub(/#{HTML_ESCAPE_PATTERN}/o) { |m| html_escape[m] }
+          else
+            text
+          end
+      end
+    end
+    
     def css_class_for_kinds kinds
       TokenKinds[kinds.is_a?(Symbol) ? kinds : kinds.first]
     end
diff --git a/lib/coderay/encoders/html/css.rb b/lib/coderay/encoders/html/css.rb
index 164d7f8..e06c486 100644
--- a/lib/coderay/encoders/html/css.rb
+++ b/lib/coderay/encoders/html/css.rb
@@ -3,25 +3,23 @@ module Encoders
 
   class HTML
     class CSS  # :nodoc:
+      def initialize style_name = :default
+        @style_name = style_name
+      end
 
-      attr :stylesheet
-
-      def CSS.load_stylesheet style = nil
-        CodeRay::Styles[style]
+      def style
+        @style ||= CodeRay::Styles[@style_name]
       end
 
-      def initialize style = :default
-        @styles = Hash.new
-        style = CSS.load_stylesheet style
-        @stylesheet = [
+      def stylesheet
+        @css ||= [
           style::CSS_MAIN_STYLES,
           style::TOKEN_COLORS.gsub(/^(?!$)/, '.CodeRay ')
         ].join("\n")
-        parse style::TOKEN_COLORS
       end
 
       def get_style_for_css_classes css_classes
-        cl = @styles[css_classes.first]
+        cl = styles[css_classes.first]
         return '' unless cl
         style = ''
         1.upto css_classes.size do |offset|
@@ -31,7 +29,7 @@ module Encoders
         return style
       end
 
-    private
+      private
 
       CSS_CLASS_PATTERN = /
         (                    # $1 = selectors
@@ -46,14 +44,16 @@ module Encoders
       |
         ( [^\n]+ )           # $3 = error
       /mx
-      def parse stylesheet
-        stylesheet.scan CSS_CLASS_PATTERN do |selectors, style, error|
-          raise "CSS parse error: '#{error.inspect}' not recognized" if error
-          for selector in selectors.split(',')
-            classes = selector.scan(/[-\w]+/)
-            cl = classes.pop
-            @styles[cl] ||= Hash.new
-            @styles[cl][classes] = style.to_s.strip.delete(' ').chomp(';')
+      def styles
+        @styles ||= Hash.new.tap do |styles|
+          style::TOKEN_COLORS.scan CSS_CLASS_PATTERN do |selectors, style, error|
+            raise "CSS parse error: '#{error.inspect}' not recognized" if error
+            for selector in selectors.split(',')
+              classes = selector.scan(/[-\w]+/)
+              cl = classes.pop
+              styles[cl] ||= Hash.new
+              styles[cl][classes] = style.to_s.strip.delete(' ').chomp(';')
+            end
           end
         end
       end
diff --git a/test/functional/basic.rb b/test/functional/basic.rb
index 752d4ba..917b5ff 100755
--- a/test/functional/basic.rb
+++ b/test/functional/basic.rb
@@ -46,8 +46,8 @@ class BasicTest < Test::Unit::TestCase
     end
   end
   
-  RUBY_TEST_HTML = 'puts <span class="string"><span class="delimiter">&quot;</span>' + 
-    '<span class="content">Hello, World!</span><span class="delimiter">&quot;</span></span>'
+  RUBY_TEST_HTML = 'puts <span class="string"><span class="delimiter">"</span>' +
+    '<span class="content">Hello, World!</span><span class="delimiter">"</span></span>'
   def test_simple_highlight
     assert_nothing_raised do
       assert_equal RUBY_TEST_HTML, CodeRay.scan(RUBY_TEST_CODE, :ruby).html
diff --git a/test/functional/examples.rb b/test/functional/examples.rb
index 985ef87..8da4fc7 100755
--- a/test/functional/examples.rb
+++ b/test/functional/examples.rb
@@ -10,7 +10,7 @@ class ExamplesTest < Test::Unit::TestCase
     div = CodeRay.scan('puts "Hello, world!"', :ruby).div
     assert_equal <<-DIV, div
 <div class="CodeRay">
-  <div class="code"><pre>puts <span style="background-color:hsla(0,100%,50%,0.05)"><span style="color:#710">&quot;</span><span style="color:#D20">Hello, world!</span><span style="color:#710">&quot;</span></span></pre></div>
+  <div class="code"><pre>puts <span style="background-color:hsla(0,100%,50%,0.05)"><span style="color:#710">"</span><span style="color:#D20">Hello, world!</span><span style="color:#710">"</span></span></pre></div>
 </div>
     DIV
     
@@ -40,7 +40,7 @@ end
 <table class="CodeRay"><tr>
   <td class="line-numbers"><pre><a href="#n1" name="n1">1</a>
 </pre></td>
-  <td class="code"><pre>puts <span class="string"><span class="delimiter">&quot;</span><span class="content">Hello, world!</span><span class="delimiter">&quot;</span></span></pre></td>
+  <td class="code"><pre>puts <span class="string"><span class="delimiter">"</span><span class="content">Hello, world!</span><span class="delimiter">"</span></span></pre></td>
 </tr></table>
 
 </body>
@@ -92,7 +92,7 @@ Token Types (7):
     div = tokens.div(:css => :class)
     assert_equal <<-DIV, div
 <div class="CodeRay">
-  <div class="code"><pre>{ <span class="key"><span class="delimiter">&quot;</span><span class="content">just</span><span class="delimiter">&quot;</span></span>: <span class="string"><span class="delimiter">&quot;</span><span class="content">an</span><span class="delimiter">&quot;</span></span>, <span class="key"><span class="delimiter">&quot;</span><span class="content">example</span><span class="delimiter">&quot;</span></span>: <span class="integer">42</span> }</pre></div>
+  <div class="code"><pre>{ <span class="key"><span class="delimiter">"</span><span class="content">just</span><span class="delimiter">"</span></span>: <span class="string"><span class="delimiter">"</span><span class="content">an</span><span class="delimiter">"</span></span>, <span class="key"><span class="delimiter">"</span><span class="content">example</span><span class="delimiter">"</span></span>: <span class="integer">42</span> }</pre></div>
 </div>
     DIV
     
@@ -121,7 +121,7 @@ Token Types (7):
     div = ruby_highlighter.encode('puts "Hello, world!"')
     assert_equal <<-DIV, div
 <div class="CodeRay">
-  <div class="code"><pre>puts <span style="background-color:hsla(0,100%,50%,0.05)"><span style="color:#710">&quot;</span><span style="color:#D20">Hello, world!</span><span style="color:#710">&quot;</span></span></pre></div>
+  <div class="code"><pre>puts <span style="background-color:hsla(0,100%,50%,0.05)"><span style="color:#710">"</span><span style="color:#D20">Hello, world!</span><span style="color:#710">"</span></span></pre></div>
 </div>
     DIV
   end
diff --git a/test/functional/for_redcloth.rb b/test/functional/for_redcloth.rb
index 9fd244e..eebf19c 100644
--- a/test/functional/for_redcloth.rb
+++ b/test/functional/for_redcloth.rb
@@ -16,11 +16,11 @@ class BasicTest < Test::Unit::TestCase
   
   def test_for_redcloth
     require 'coderay/for_redcloth'
-    assert_equal "<p><span lang=\"ruby\" class=\"CodeRay\">puts <span style=\"background-color:hsla(0,100%,50%,0.05)\"><span style=\"color:#710\">&quot;</span><span style=\"color:#D20\">Hello, World!</span><span style=\"color:#710\">&quot;</span></span></span></p>",
+    assert_equal "<p><span lang=\"ruby\" class=\"CodeRay\">puts <span style=\"background-color:hsla(0,100%,50%,0.05)\"><span style=\"color:#710\">\"</span><span style=\"color:#D20\">Hello, World!</span><span style=\"color:#710\">\"</span></span></span></p>",
       RedCloth.new('@[ruby]puts "Hello, World!"@').to_html
     assert_equal <<-BLOCKCODE.chomp,
 <div lang="ruby" class="CodeRay">
-  <div class="code"><pre>puts <span style="background-color:hsla(0,100%,50%,0.05)"><span style="color:#710">&quot;</span><span style="color:#D20">Hello, World!</span><span style="color:#710">&quot;</span></span></pre></div>
+  <div class="code"><pre>puts <span style="background-color:hsla(0,100%,50%,0.05)"><span style="color:#710">"</span><span style="color:#D20">Hello, World!</span><span style="color:#710">"</span></span></pre></div>
 </div>
       BLOCKCODE
       RedCloth.new('bc[ruby]. puts "Hello, World!"').to_html
diff --git a/test/unit/html.rb b/test/unit/html.rb
index 0072635..750b6c9 100644
--- a/test/unit/html.rb
+++ b/test/unit/html.rb
@@ -60,7 +60,7 @@ public class Test {
  * used to test the
  */</span>
 <span class=\"directive\">public</span> <span class=\"type\">class</span> <span class=\"class\">Test</span> {
-  <span class=\"directive\">public</span> <span class=\"directive\">static</span> <span class=\"directive\">final</span> <span class=\"predefined-type\">String</span> MESSAGE = <span class=\"string\"><span class=\"delimiter\">&quot;</span><span class=\"content\">My message    To the world</span><span class=\"delimiter\">&quot;</span></span>;
+  <span class=\"directive\">public</span> <span class=\"directive\">static</span> <span class=\"directive\">final</span> <span class=\"predefined-type\">String</span> MESSAGE = <span class=\"string\"><span class=\"delimiter\">\"</span><span class=\"content\">My message    To the world</span><span class=\"delimiter\">\"</span></span>;
 
   <span class=\"directive\">static</span> <span class=\"type\">void</span> main() {
     <span class=\"comment\">/*
@@ -80,7 +80,7 @@ public class Test {
 <span class=\"comment\"> * used to test the</span>
 <span class=\"comment\"> */</span>
 <span class=\"directive\">public</span> <span class=\"type\">class</span> <span class=\"class\">Test</span> {
-  <span class=\"directive\">public</span> <span class=\"directive\">static</span> <span class=\"directive\">final</span> <span class=\"predefined-type\">String</span> MESSAGE = <span class=\"string\"><span class=\"delimiter\">&quot;</span><span class=\"content\">My message    To the world</span><span class=\"delimiter\">&quot;</span></span>;
+  <span class=\"directive\">public</span> <span class=\"directive\">static</span> <span class=\"directive\">final</span> <span class=\"predefined-type\">String</span> MESSAGE = <span class=\"string\"><span class=\"delimiter\">\"</span><span class=\"content\">My message    To the world</span><span class=\"delimiter\">\"</span></span>;
 
   <span class=\"directive\">static</span> <span class=\"type\">void</span> main() {
     <span class=\"comment\">/*</span>