Merge branch 'master' into paint-integrationpaint-integration

18 files changed, 753 insertions, 136 deletions

diff --git a/lib/coderay/scanners/css.rb b/lib/coderay/scanners/css.rb
index 732f9c5..55d5239 100644
--- a/lib/coderay/scanners/css.rb
+++ b/lib/coderay/scanners/css.rb
@@ -25,7 +25,7 @@ module Scanners
       
       HexColor = /#(?:#{Hex}{6}|#{Hex}{3})/
       
-      Num = /-?(?:[0-9]*\.[0-9]+|[0-9]+)/
+      Num = /-?(?:[0-9]*\.[0-9]+|[0-9]+)n?/
       Name = /#{NMChar}+/
       Ident = /-?#{NMStart}#{NMChar}*/
       AtKeyword = /@#{Ident}/
@@ -53,7 +53,7 @@ module Scanners
     end
     
     def scan_tokens encoder, options
-      states = Array(options[:state] || @state)
+      states = Array(options[:state] || @state).dup
       value_expected = @value_expected
       
       until eos?
@@ -145,10 +145,10 @@ module Scanners
           start = match[/^\w+\(/]
           encoder.text_token start, :delimiter
           if match[-1] == ?)
-            encoder.text_token match[start.size..-2], :content
+            encoder.text_token match[start.size..-2], :content if match.size > start.size + 1
             encoder.text_token ')', :delimiter
           else
-            encoder.text_token match[start.size..-1], :content
+            encoder.text_token match[start.size..-1], :content if match.size > start.size
           end
           encoder.end_group :function
           
diff --git a/lib/coderay/scanners/debug.rb b/lib/coderay/scanners/debug.rb
index 566bfa7..83ede9a 100644
--- a/lib/coderay/scanners/debug.rb
+++ b/lib/coderay/scanners/debug.rb
@@ -1,9 +1,11 @@
+require 'set'
+
 module CodeRay
 module Scanners
   
   # = Debug Scanner
   # 
-  # Interprets the output of the Encoders::Debug encoder.
+  # Interprets the output of the Encoders::Debug encoder (basically the inverse function).
   class Debug < Scanner
     
     register_for :debug
@@ -11,6 +13,11 @@ module Scanners
     
   protected
     
+    def setup
+      super
+      @known_token_kinds = TokenKinds.keys.map(&:to_s).to_set
+    end
+    
     def scan_tokens encoder, options
       
       opened_tokens = []
@@ -21,16 +28,19 @@ module Scanners
           encoder.text_token match, :space
           
         elsif match = scan(/ (\w+) \( ( [^\)\\]* ( \\. [^\)\\]* )* ) \)? /x)
-          kind = self[1].to_sym
-          match = self[2].gsub(/\\(.)/m, '\1')
-          unless TokenKinds.has_key? kind
-            kind = :error
-            match = matched
+          if @known_token_kinds.include? self[1]
+            encoder.text_token self[2].gsub(/\\(.)/m, '\1'), self[1].to_sym
+          else
+            encoder.text_token matched, :unknown
           end
-          encoder.text_token match, kind
           
         elsif match = scan(/ (\w+) ([<\[]) /x)
-          kind = self[1].to_sym
+          if @known_token_kinds.include? self[1]
+            kind = self[1].to_sym
+          else
+            kind = :unknown
+          end
+          
           opened_tokens << kind
           case self[2]
           when '<'
diff --git a/lib/coderay/scanners/diff.rb b/lib/coderay/scanners/diff.rb
index af0f755..74a6c27 100644
--- a/lib/coderay/scanners/diff.rb
+++ b/lib/coderay/scanners/diff.rb
@@ -69,7 +69,7 @@ module Scanners
             state = :added
           elsif match = scan(/\\ .*/)
             encoder.text_token match, :comment
-          elsif match = scan(/@@(?>[^@\n]*)@@/)
+          elsif match = scan(/@@(?>[^@\n]+)@@/)
             content_scanner.state = :initial unless match?(/\n\+/)
             content_scanner_entry_state = nil
             if check(/\n|$/)
@@ -100,7 +100,7 @@ module Scanners
             next
           elsif match = scan(/-/)
             deleted_lines_count += 1
-            if options[:inline_diff] && deleted_lines_count == 1 && (changed_lines_count = 1 + check(/.*(?:\n\-.*)*/).count("\n")) && match?(/(?>.*(?:\n\-.*){#{changed_lines_count - 1}}(?:\n\+.*){#{changed_lines_count}})$(?!\n\+)/)
+            if options[:inline_diff] && deleted_lines_count == 1 && (changed_lines_count = 1 + check(/.*(?:\n\-.*)*/).count("\n")) && changed_lines_count <= 100_000 && match?(/(?>.*(?:\n\-.*){#{changed_lines_count - 1}}(?:\n\+.*){#{changed_lines_count}})$(?!\n\+)/)
               deleted_lines  = Array.new(changed_lines_count) { |i| skip(/\n\-/) if i > 0; scan(/.*/) }
               inserted_lines = Array.new(changed_lines_count) { |i| skip(/\n\+/)         ; scan(/.*/) }
               
diff --git a/lib/coderay/scanners/go.rb b/lib/coderay/scanners/go.rb
new file mode 100644
index 0000000..99fdd63
--- /dev/null
+++ b/lib/coderay/scanners/go.rb
@@ -0,0 +1,208 @@
+module CodeRay
+module Scanners
+  
+  class Go < Scanner
+    
+    register_for :go
+    file_extension 'go'
+    
+    # http://golang.org/ref/spec#Keywords
+    KEYWORDS = [
+      'break', 'default', 'func', 'interface', 'select',
+      'case', 'defer', 'go', 'map', 'struct',
+      'chan', 'else', 'goto', 'package', 'switch',
+      'const', 'fallthrough', 'if', 'range', 'type',
+      'continue', 'for', 'import', 'return', 'var',
+    ]  # :nodoc:
+    
+    # http://golang.org/ref/spec#Types
+    PREDEFINED_TYPES = [
+      'bool',
+      'uint8', 'uint16', 'uint32', 'uint64',
+      'int8', 'int16', 'int32', 'int64',
+      'float32', 'float64',
+      'complex64', 'complex128',
+      'byte', 'rune', 'string', 'error',
+      'uint', 'int', 'uintptr',
+    ]  # :nodoc:
+    
+    PREDEFINED_CONSTANTS = [
+      'nil', 'iota',
+      'true', 'false',
+    ]  # :nodoc:
+    
+    PREDEFINED_FUNCTIONS = %w[
+      append cap close complex copy delete imag len
+      make new panic print println real recover
+    ] # :nodoc:
+    
+    IDENT_KIND = WordList.new(:ident).
+      add(KEYWORDS, :keyword).
+      add(PREDEFINED_TYPES, :predefined_type).
+      add(PREDEFINED_CONSTANTS, :predefined_constant).
+      add(PREDEFINED_FUNCTIONS, :predefined)  # :nodoc:
+    
+    ESCAPE = / [rbfntv\n\\'"] | x[a-fA-F0-9]{1,2} | [0-7]{1,3} /x  # :nodoc:
+    UNICODE_ESCAPE = / u[a-fA-F0-9]{4} | U[a-fA-F0-9]{8} /x  # :nodoc:
+    
+    protected
+    
+    def scan_tokens encoder, options
+      
+      state = :initial
+      label_expected = true
+      case_expected = false
+      label_expected_before_preproc_line = nil
+      in_preproc_line = false
+      
+      until eos?
+        
+        case state
+        
+        when :initial
+          
+          if match = scan(/ \s+ | \\\n /x)
+            if in_preproc_line && match != "\\\n" && match.index(?\n)
+              in_preproc_line = false
+              case_expected = false
+              label_expected = label_expected_before_preproc_line
+            end
+            encoder.text_token match, :space
+          
+          elsif match = scan(%r! // [^\n\\]* (?: \\. [^\n\\]* )* | /\* (?: .*? \*/ | .* ) !mx)
+            encoder.text_token match, :comment
+          
+          elsif match = scan(/ <?- (?![\d.]) | [+*=<>?:;,!&^|()\[\]{}~%]+ | \/=? | \.(?!\d) /x)
+            if case_expected
+              label_expected = true if match == ':'
+              case_expected = false
+            end
+            encoder.text_token match, :operator
+          
+          elsif match = scan(/ [A-Za-z_][A-Za-z_0-9]* /x)
+            kind = IDENT_KIND[match]
+            if kind == :ident && label_expected && !in_preproc_line && scan(/:(?!:)/)
+              kind = :label
+              label_expected = false
+              match << matched
+            else
+              label_expected = false
+              if kind == :keyword
+                case match
+                when 'case', 'default'
+                  case_expected = true
+                end
+              end
+            end
+            encoder.text_token match, kind
+          
+          elsif match = scan(/L?"/)
+            encoder.begin_group :string
+            if match[0] == ?L
+              encoder.text_token 'L', :modifier
+              match = '"'
+            end
+            encoder.text_token match, :delimiter
+            state = :string
+          
+          elsif match = scan(/ ` ([^`]+)? (`)? /x)
+            encoder.begin_group :shell
+            encoder.text_token '`', :delimiter
+            encoder.text_token self[1], :content if self[1]
+            encoder.text_token self[2], :delimiter if self[2]
+            encoder.end_group :shell
+          
+          elsif match = scan(/ \# \s* if \s* 0 /x)
+            match << scan_until(/ ^\# (?:elif|else|endif) .*? $ | \z /xm) unless eos?
+            encoder.text_token match, :comment
+          
+          elsif match = scan(/#[ \t]*(\w*)/)
+            encoder.text_token match, :preprocessor
+            in_preproc_line = true
+            label_expected_before_preproc_line = label_expected
+            state = :include_expected if self[1] == 'include'
+          
+          elsif match = scan(/ L?' (?: [^\'\n\\] | \\ (?: #{ESCAPE} | #{UNICODE_ESCAPE} ) )? '? /ox)
+            label_expected = false
+            encoder.text_token match, :char
+          
+          elsif match = scan(/\$/)
+            encoder.text_token match, :ident
+          
+          elsif match = scan(/-?\d*(\.\d*)?([eE][+-]?\d+)?i/)
+            label_expected = false
+            encoder.text_token match, :imaginary
+          
+          elsif match = scan(/-?0[xX][0-9A-Fa-f]+/)
+            label_expected = false
+            encoder.text_token match, :hex
+          
+          elsif match = scan(/-?(?:0[0-7]+)(?![89.eEfF])/)
+            label_expected = false
+            encoder.text_token match, :octal
+          
+          elsif match = scan(/-?(?:\d*\.\d+|\d+\.)(?:[eE][+-]?\d+)?|\d+[eE][+-]?\d+/)
+            label_expected = false
+            encoder.text_token match, :float
+          
+          elsif match = scan(/-?(?:\d+)(?![.eEfF])L?L?/)
+            label_expected = false
+            encoder.text_token match, :integer
+          
+          else
+            encoder.text_token getch, :error
+          
+          end
+        
+        when :string
+          if match = scan(/[^\\\n"]+/)
+            encoder.text_token match, :content
+          elsif match = scan(/"/)
+            encoder.text_token match, :delimiter
+            encoder.end_group :string
+            state = :initial
+            label_expected = false
+          elsif match = scan(/ \\ (?: #{ESCAPE} | #{UNICODE_ESCAPE} ) /mox)
+            encoder.text_token match, :char
+          elsif match = scan(/ \\ /x)
+            encoder.text_token match, :error
+          elsif match = scan(/$/)
+            encoder.end_group :string
+            state = :initial
+            label_expected = false
+          else
+            raise_inspect "else case \" reached; %p not handled." % peek(1), encoder
+          end
+        
+        when :include_expected
+          if match = scan(/<[^>\n]+>?|"[^"\n\\]*(?:\\.[^"\n\\]*)*"?/)
+            encoder.text_token match, :include
+            state = :initial
+          
+          elsif match = scan(/\s+/)
+            encoder.text_token match, :space
+            state = :initial if match.index ?\n
+          
+          else
+            state = :initial
+          
+          end
+        
+        else
+          raise_inspect 'Unknown state', encoder
+        
+        end
+        
+      end
+      
+      if state == :string
+        encoder.end_group :string
+      end
+      
+      encoder
+    end
+    
+  end
+  
+end
+end
diff --git a/lib/coderay/scanners/groovy.rb b/lib/coderay/scanners/groovy.rb
index cf55daf..c64454f 100644
--- a/lib/coderay/scanners/groovy.rb
+++ b/lib/coderay/scanners/groovy.rb
@@ -36,9 +36,12 @@ module Scanners
     
   protected
     
+    def setup
+      @state = :initial
+    end
+    
     def scan_tokens encoder, options
-      
-      state = :initial
+      state = options[:state] || @state
       inline_block_stack = []
       inline_block_paren_depth = nil
       string_delimiter = nil
@@ -223,7 +226,7 @@ module Scanners
             encoder.text_token match, :content  # TODO: Shouldn't this be :error?
             
           elsif match = scan(/ \\ | \n /x)
-            encoder.end_group state
+            encoder.end_group state == :regexp ? :regexp : :string
             encoder.text_token match, :error
             after_def = value_expected = false
             state = :initial
@@ -243,7 +246,17 @@ module Scanners
       end
       
       if [:multiline_string, :string, :regexp].include? state
-        encoder.end_group state
+        encoder.end_group state == :regexp ? :regexp : :string
+      end
+      
+      if options[:keep_state]
+        @state = state
+      end
+      
+      until inline_block_stack.empty?
+        state, = *inline_block_stack.pop
+        encoder.end_group :inline
+        encoder.end_group state == :regexp ? :regexp : :string
       end
       
       encoder
diff --git a/lib/coderay/scanners/html.rb b/lib/coderay/scanners/html.rb
index 3ba3b79..ebe7b01 100644
--- a/lib/coderay/scanners/html.rb
+++ b/lib/coderay/scanners/html.rb
@@ -1,13 +1,13 @@
 module CodeRay
 module Scanners
-
+  
   # HTML Scanner
   # 
   # Alias: +xhtml+
   # 
   # See also: Scanners::XML
   class HTML < Scanner
-
+    
     register_for :html
     
     KINDS_NOT_LOC = [
@@ -33,7 +33,8 @@ module Scanners
     )
     
     IN_ATTRIBUTE = WordList::CaseIgnoring.new(nil).
-      add(EVENT_ATTRIBUTES, :script)
+      add(EVENT_ATTRIBUTES, :script).
+      add(['style'], :style)
     
     ATTR_NAME = /[\w.:-]+/  # :nodoc:
     TAG_END = /\/?>/  # :nodoc:
@@ -75,9 +76,14 @@ module Scanners
     def scan_java_script encoder, code
       if code && !code.empty?
         @java_script_scanner ||= Scanners::JavaScript.new '', :keep_tokens => true
-        # encoder.begin_group :inline
         @java_script_scanner.tokenize code, :tokens => encoder
-        # encoder.end_group :inline
+      end
+    end
+    
+    def scan_css encoder, code, state = [:initial]
+      if code && !code.empty?
+        @css_scanner ||= Scanners::CSS.new '', :keep_tokens => true
+        @css_scanner.tokenize code, :tokens => encoder, :state => state
       end
     end
     
@@ -99,7 +105,15 @@ module Scanners
           case state
           
           when :initial
-            if match = scan(/<!--(?:.*?-->|.*)/m)
+            if match = scan(/<!\[CDATA\[/)
+              encoder.text_token match, :inline_delimiter
+              if match = scan(/.*?\]\]>/m)
+                encoder.text_token match[0..-4], :plain
+                encoder.text_token ']]>', :inline_delimiter
+              elsif match = scan(/.+/)
+                encoder.text_token match, :error
+              end
+            elsif match = scan(/<!--(?:.*?-->|.*)/m)
               encoder.text_token match, :comment
             elsif match = scan(/<!(\w+)(?:.*?>|.*)|\]>/m)
               encoder.text_token match, :doctype
@@ -110,7 +124,7 @@ module Scanners
             elsif match = scan(/<\/[-\w.:]*>?/m)
               in_tag = nil
               encoder.text_token match, :tag
-            elsif match = scan(/<(?:(script)|[-\w.:]+)(>)?/m)
+            elsif match = scan(/<(?:(script|style)|[-\w.:]+)(>)?/m)
               encoder.text_token match, :tag
               in_tag = self[1]
               if self[2]
@@ -161,17 +175,21 @@ module Scanners
               encoder.text_token match, :attribute_value
               state = :attribute
             elsif match = scan(/["']/)
-              if in_attribute == :script
-                encoder.begin_group :inline
-                encoder.text_token match, :inline_delimiter
+              if in_attribute == :script || in_attribute == :style
+                encoder.begin_group :string
+                encoder.text_token match, :delimiter
                 if scan(/javascript:[ \t]*/)
                   encoder.text_token matched, :comment
                 end
                 code = scan_until(match == '"' ? /(?="|\z)/ : /(?='|\z)/)
-                scan_java_script encoder, code
+                if in_attribute == :script
+                  scan_java_script encoder, code
+                else
+                  scan_css encoder, code, [:block]
+                end
                 match = scan(/["']/)
-                encoder.text_token match, :inline_delimiter if match
-                encoder.end_group :inline
+                encoder.text_token match, :delimiter if match
+                encoder.end_group :string
                 state = :attribute
                 in_attribute = nil
               else
@@ -206,19 +224,23 @@ module Scanners
             
           when :in_special_tag
             case in_tag
-            when 'script'
+            when 'script', 'style'
               encoder.text_token match, :space if match = scan(/[ \t]*\n/)
               if scan(/(\s*<!--)(?:(.*?)(-->)|(.*))/m)
                 code = self[2] || self[4]
                 closing = self[3]
                 encoder.text_token self[1], :comment
               else
-                code = scan_until(/(?=(?:\n\s*)?<\/script>)|\z/)
+                code = scan_until(/(?=(?:\n\s*)?<\/#{in_tag}>)|\z/)
                 closing = false
               end
               unless code.empty?
                 encoder.begin_group :inline
-                scan_java_script encoder, code
+                if in_tag == 'script'
+                  scan_java_script encoder, code
+                else
+                  scan_css encoder, code
+                end
                 encoder.end_group :inline
               end
               encoder.text_token closing, :comment if closing
diff --git a/lib/coderay/scanners/json.rb b/lib/coderay/scanners/json.rb
index 4e0f462..b09970c 100644
--- a/lib/coderay/scanners/json.rb
+++ b/lib/coderay/scanners/json.rb
@@ -14,15 +14,21 @@ module Scanners
     
     ESCAPE = / [bfnrt\\"\/] /x  # :nodoc:
     UNICODE_ESCAPE = / u[a-fA-F0-9]{4} /x  # :nodoc:
+    KEY = / (?> (?: [^\\"]+ | \\. )* ) " \s* : /x
     
   protected
     
+    def setup
+      @state = :initial
+    end
+    
     # See http://json.org/ for a definition of the JSON lexic/grammar.
     def scan_tokens encoder, options
+      state = options[:state] || @state
       
-      state = :initial
-      stack = []
-      key_expected = false
+      if [:string, :key].include? state
+        encoder.begin_group state
+      end
       
       until eos?
         
@@ -32,18 +38,11 @@ module Scanners
           if match = scan(/ \s+ /x)
             encoder.text_token match, :space
           elsif match = scan(/"/)
-            state = key_expected ? :key : :string
+            state = check(/#{KEY}/o) ? :key : :string
             encoder.begin_group state
             encoder.text_token match, :delimiter
           elsif match = scan(/ [:,\[{\]}] /x)
             encoder.text_token match, :operator
-            case match
-            when ':' then key_expected = false
-            when ',' then key_expected = true if stack.last == :object
-            when '{' then stack << :object; key_expected = true
-            when '[' then stack << :array
-            when '}', ']' then stack.pop  # no error recovery, but works for valid JSON
-            end
           elsif match = scan(/ true | false | null /x)
             encoder.text_token match, :value
           elsif match = scan(/ -? (?: 0 | [1-9]\d* ) /x)
@@ -82,6 +81,10 @@ module Scanners
         end
       end
       
+      if options[:keep_state]
+        @state = state
+      end
+      
       if [:string, :key].include? state
         encoder.end_group state
       end
diff --git a/lib/coderay/scanners/lua.rb b/lib/coderay/scanners/lua.rb
new file mode 100644
index 0000000..fb1e45a
--- /dev/null
+++ b/lib/coderay/scanners/lua.rb
@@ -0,0 +1,280 @@
+# encoding: utf-8
+
+module CodeRay
+module Scanners
+
+  # Scanner for the Lua[http://lua.org] programming lanuage.
+  #
+  # The language’s complete syntax is defined in
+  # {the Lua manual}[http://www.lua.org/manual/5.2/manual.html],
+  # which is what this scanner tries to conform to.
+  class Lua < Scanner
+    
+    register_for :lua
+    file_extension 'lua'
+    title 'Lua'
+    
+    # Keywords used in Lua.
+    KEYWORDS = %w[and break do else elseif end
+      for function goto if in
+      local not or repeat return
+      then until while
+    ]
+    
+    # Constants set by the Lua core.
+    PREDEFINED_CONSTANTS = %w[false true nil]
+    
+    # The expressions contained in this array are parts of Lua’s `basic'
+    # library. Although it’s not entirely necessary to load that library,
+    # it is highly recommended and one would have to provide own implementations
+    # of some of these expressions if one does not do so. They however aren’t
+    # keywords, neither are they constants, but nearly predefined, so they
+    # get tagged as `predefined' rather than anything else.
+    #
+    # This list excludes values of form `_UPPERCASE' because the Lua manual
+    # requires such identifiers to be reserved by Lua anyway and they are
+    # highlighted directly accordingly, without the need for specific
+    # identifiers to be listed here.
+    PREDEFINED_EXPRESSIONS = %w[
+      assert collectgarbage dofile error getmetatable
+      ipairs load loadfile next pairs pcall print
+      rawequal rawget rawlen rawset select setmetatable
+      tonumber tostring type xpcall
+    ]
+    
+    # Automatic token kind selection for normal words.
+    IDENT_KIND = CodeRay::WordList.new(:ident).
+      add(KEYWORDS, :keyword).
+      add(PREDEFINED_CONSTANTS, :predefined_constant).
+      add(PREDEFINED_EXPRESSIONS, :predefined)
+    
+    protected
+    
+    # Scanner initialization.
+    def setup
+      @state = :initial
+      @brace_depth = 0
+    end
+    
+    # CodeRay entry hook. Starts parsing.
+    def scan_tokens(encoder, options)
+      state = options[:state] || @state
+      brace_depth = @brace_depth
+      num_equals = nil
+      
+      until eos?
+        case state
+        
+        when :initial
+          if match = scan(/\-\-\[\=*\[/)   #--[[ long (possibly multiline) comment ]]
+            num_equals = match.count("=") # Number must match for comment end
+            encoder.begin_group(:comment)
+            encoder.text_token(match, :delimiter)
+            state = :long_comment
+          
+          elsif match = scan(/--.*$/) # --Lua comment
+            encoder.text_token(match, :comment)
+          
+          elsif match = scan(/\[=*\[/)     # [[ long (possibly multiline) string ]]
+            num_equals = match.count("=") # Number must match for comment end
+            encoder.begin_group(:string)
+            encoder.text_token(match, :delimiter)
+            state = :long_string
+          
+          elsif match = scan(/::\s*[a-zA-Z_][a-zA-Z0-9_]+\s*::/) # ::goto_label::
+            encoder.text_token(match, :label)
+          
+          elsif match = scan(/_[A-Z]+/) # _UPPERCASE are names reserved for Lua
+            encoder.text_token(match, :predefined)
+          
+          elsif match = scan(/[a-zA-Z_][a-zA-Z0-9_]*/) # Normal letters (or letters followed by digits)
+            kind = IDENT_KIND[match]
+            
+            # Extra highlighting for entities following certain keywords
+            if kind == :keyword and match == "function"
+              state = :function_expected
+            elsif kind == :keyword and match == "goto"
+              state = :goto_label_expected
+            elsif kind == :keyword and match == "local"
+              state = :local_var_expected
+            end
+            
+            encoder.text_token(match, kind)
+          
+          elsif match = scan(/\{/) # Opening table brace {
+            encoder.begin_group(:map)
+            encoder.text_token(match, brace_depth >= 1 ? :inline_delimiter : :delimiter)
+            brace_depth += 1
+            state        = :map
+          
+          elsif match = scan(/\}/) # Closing table brace }
+            if brace_depth == 1
+              brace_depth = 0
+              encoder.text_token(match, :delimiter)
+              encoder.end_group(:map)
+            elsif brace_depth == 0 # Mismatched brace
+              encoder.text_token(match, :error)
+            else
+              brace_depth -= 1
+              encoder.text_token(match, :inline_delimiter)
+              encoder.end_group(:map)
+              state = :map
+            end
+          
+          elsif match = scan(/["']/) # String delimiters " and '
+            encoder.begin_group(:string)
+            encoder.text_token(match, :delimiter)
+            start_delim = match
+            state       = :string
+          
+                            # ↓Prefix                hex number ←|→ decimal number
+          elsif match = scan(/-? (?:0x\h* \. \h+ (?:p[+\-]?\d+)? | \d*\.\d+ (?:e[+\-]?\d+)?)/ix) # hexadecimal constants have no E power, decimal ones no P power
+            encoder.text_token(match, :float)
+          
+                            # ↓Prefix         hex number ←|→ decimal number
+          elsif match = scan(/-? (?:0x\h+ (?:p[+\-]?\d+)? | \d+ (?:e[+\-]?\d+)?)/ix) # hexadecimal constants have no E power, decimal ones no P power
+            encoder.text_token(match, :integer)
+          
+          elsif match = scan(/[\+\-\*\/%^\#=~<>\(\)\[\]:;,] | \.(?!\d)/x) # Operators
+            encoder.text_token(match, :operator)
+          
+          elsif match = scan(/\s+/) # Space
+            encoder.text_token(match, :space)
+          
+          else # Invalid stuff. Note that Lua doesn’t accept multibyte chars outside of strings, hence these are also errors.
+            encoder.text_token(getch, :error)
+          end
+          
+          # It may be that we’re scanning a full-blown subexpression of a table
+          # (tables can contain full expressions in parts).
+          # If this is the case, return to :map scanning state.
+          state = :map if state == :initial && brace_depth >= 1
+        
+        when :function_expected
+          if match = scan(/\(.*?\)/m) # x = function() # "Anonymous" function without explicit name
+            encoder.text_token(match, :operator)
+            state = :initial
+          elsif match = scan(/[a-zA-Z_] (?:[a-zA-Z0-9_\.] (?!\.\d))* [\.\:]/x) # function tbl.subtbl.foo() | function tbl:foo() # Colon only allowed as last separator
+            encoder.text_token(match, :ident)
+          elsif match = scan(/[a-zA-Z_][a-zA-Z0-9_]*/) # function foo()
+            encoder.text_token(match, :function)
+            state = :initial
+          elsif match = scan(/\s+/) # Between the `function' keyword and the ident may be any amount of whitespace
+            encoder.text_token(match, :space)
+          else
+            encoder.text_token(getch, :error)
+            state = :initial
+          end
+        
+        when :goto_label_expected
+          if match = scan(/[a-zA-Z_][a-zA-Z0-9_]*/)
+            encoder.text_token(match, :label)
+            state = :initial
+          elsif match = scan(/\s+/) # Between the `goto' keyword and the label may be any amount of whitespace
+            encoder.text_token(match, :space)
+          else
+            encoder.text_token(getch, :error)
+          end
+        
+        when :local_var_expected
+          if match = scan(/function/) # local function ...
+            encoder.text_token(match, :keyword)
+            state = :function_expected
+          elsif match = scan(/[a-zA-Z_][a-zA-Z0-9_]*/)
+            encoder.text_token(match, :local_variable)
+          elsif match = scan(/,/)
+            encoder.text_token(match, :operator)
+          elsif match = scan(/\=/)
+            encoder.text_token(match, :operator)
+            # After encountering the equal sign, arbitrary expressions are
+            # allowed again, so just return to the main state for further
+            # parsing.
+            state = :initial
+          elsif match = scan(/\n/)
+            encoder.text_token(match, :space)
+            state = :initial
+          elsif match = scan(/\s+/)
+            encoder.text_token(match, :space)
+          else
+            encoder.text_token(getch, :error)
+          end
+        
+        when :long_comment
+          if match = scan(/.*?(?=\]={#{num_equals}}\])/m)
+            encoder.text_token(match, :content)
+            
+            delim = scan(/\]={#{num_equals}}\]/)
+            encoder.text_token(delim, :delimiter)
+          else # No terminator found till EOF
+            encoder.text_token(rest, :error)
+            terminate
+          end
+          encoder.end_group(:comment)
+          state = :initial
+        
+        when :long_string
+          if match = scan(/.*?(?=\]={#{num_equals}}\])/m) # Long strings do not interpret any escape sequences
+            encoder.text_token(match, :content)
+            
+            delim = scan(/\]={#{num_equals}}\]/)
+            encoder.text_token(delim, :delimiter)
+          else # No terminator found till EOF
+            encoder.text_token(rest, :error)
+            terminate
+          end
+          encoder.end_group(:string)
+          state = :initial
+        
+        when :string
+          if match = scan(/[^\\#{start_delim}\n]+/) # Everything except \ and the start delimiter character is string content (newlines are only allowed if preceeded by \ or \z)
+            encoder.text_token(match, :content)
+          elsif match = scan(/\\(?:['"abfnrtv\\]|z\s*|x\h\h|\d{1,3}|\n)/m)
+            encoder.text_token(match, :char)
+          elsif match = scan(Regexp.compile(start_delim))
+            encoder.text_token(match, :delimiter)
+            encoder.end_group(:string)
+            state = :initial
+          elsif match = scan(/\n/) # Lua forbids unescaped newlines in normal non-long strings
+            encoder.text_token("\\n\n", :error) # Visually appealing error indicator--otherwise users may wonder whether the highlighter cannot highlight multine strings
+            encoder.end_group(:string)
+            state = :initial
+          else
+            encoder.text_token(getch, :error)
+          end
+        
+        when :map
+          if match = scan(/[,;]/)
+            encoder.text_token(match, :operator)
+          elsif match = scan(/[a-zA-Z_][a-zA-Z0-9_]* (?=\s*=)/x)
+            encoder.text_token(match, :key)
+            encoder.text_token(scan(/\s+/), :space) if check(/\s+/)
+            encoder.text_token(scan(/\=/), :operator)
+            state = :initial
+          elsif match = scan(/\s+/m)
+            encoder.text_token(match, :space)
+          else
+            # Note this clause doesn’t advance the scan pointer, it’s a kind of
+            # "retry with other options" (the :initial state then of course
+            # advances the pointer).
+            state = :initial
+          end
+        else
+          raise
+        end
+        
+      end
+      
+      if options[:keep_state]
+        @state = state
+      end
+      
+      encoder.end_group :string if [:string].include? state
+      brace_depth.times { encoder.end_group :map }
+      
+      encoder
+    end
+    
+  end
+  
+end
+end
diff --git a/lib/coderay/scanners/php.rb b/lib/coderay/scanners/php.rb
index 6c68834..7a8d75d 100644
--- a/lib/coderay/scanners/php.rb
+++ b/lib/coderay/scanners/php.rb
@@ -265,7 +265,7 @@ module Scanners
             @html_scanner.tokenize match unless match.empty?
           end
         
-        when :php
+        when :php, :php_inline
           if match = scan(/\s+/)
             encoder.text_token match, :space
           
@@ -332,7 +332,7 @@ module Scanners
             if states.size == 1
               encoder.text_token match, :error
             else
-              states.pop
+              state = states.pop
               if states.last.is_a?(::Array)
                 delimiter = states.last[1]
                 states[-1] = states.last[0]
@@ -340,6 +340,7 @@ module Scanners
                 encoder.end_group :inline
               else
                 encoder.text_token match, :operator
+                encoder.end_group :inline if state == :php_inline
                 label_expected = true
               end
             end
@@ -350,7 +351,14 @@ module Scanners
           
           elsif match = scan(RE::PHP_END)
             encoder.text_token match, :inline_delimiter
-            states = [:initial]
+            while state = states.pop
+              encoder.end_group :string if [:sqstring, :dqstring].include? state
+              if state.is_a? Array
+                encoder.end_group :inline
+                encoder.end_group :string if [:sqstring, :dqstring].include? state.first
+              end
+            end
+            states << :initial
           
           elsif match = scan(/<<<(?:(#{RE::IDENTIFIER})|"(#{RE::IDENTIFIER})"|'(#{RE::IDENTIFIER})')/o)
             encoder.begin_group :string
@@ -400,6 +408,7 @@ module Scanners
           elsif match = scan(/\\/)
             encoder.text_token match, :error
           else
+            encoder.end_group :string
             states.pop
           end
         
@@ -459,7 +468,7 @@ module Scanners
               encoder.begin_group :inline
               states[-1] = [states.last, delimiter]
               delimiter = nil
-              states.push :php
+              states.push :php_inline
               encoder.text_token match, :delimiter
             else
               encoder.text_token match, :content
@@ -469,6 +478,7 @@ module Scanners
           elsif match = scan(/\$/)
             encoder.text_token match, :content
           else
+            encoder.end_group :string
             states.pop
           end
         
@@ -500,6 +510,14 @@ module Scanners
         
       end
       
+      while state = states.pop
+        encoder.end_group :string if [:sqstring, :dqstring].include? state
+        if state.is_a? Array
+          encoder.end_group :inline
+          encoder.end_group :string if [:sqstring, :dqstring].include? state.first
+        end
+      end
+      
       encoder
     end
     
diff --git a/lib/coderay/scanners/python.rb b/lib/coderay/scanners/python.rb
index a9492ab..09c8b6e 100644
--- a/lib/coderay/scanners/python.rb
+++ b/lib/coderay/scanners/python.rb
@@ -157,12 +157,12 @@ module Scanners
             encoder.text_token match, :operator
           
           elsif match = scan(/(u?r?|b)?("""|"|'''|')/i)
+            modifiers = self[1]
             string_delimiter = self[2]
-            string_type = docstring_coming ? :docstring : :string
+            string_type = docstring_coming ? :docstring : (modifiers == 'b' ? :binary : :string)
             docstring_coming = false if docstring_coming
             encoder.begin_group string_type
             string_raw = false
-            modifiers = self[1]
             unless modifiers.empty?
               string_raw = !!modifiers.index(?r)
               encoder.text_token modifiers, :modifier
diff --git a/lib/coderay/scanners/raydebug.rb b/lib/coderay/scanners/raydebug.rb
index 7a21354..1effdc8 100644
--- a/lib/coderay/scanners/raydebug.rb
+++ b/lib/coderay/scanners/raydebug.rb
@@ -1,23 +1,30 @@
+require 'set'
+
 module CodeRay
 module Scanners
-
-  # = Debug Scanner
+  
+  # = Raydebug Scanner
   # 
-  # Parses the output of the Encoders::Debug encoder.
+  # Highlights the output of the Encoders::Debug encoder.
   class Raydebug < Scanner
-
+    
     register_for :raydebug
     file_extension 'raydebug'
     title 'CodeRay Token Dump'
     
   protected
     
+    def setup
+      super
+      @known_token_kinds = TokenKinds.keys.map(&:to_s).to_set
+    end
+    
     def scan_tokens encoder, options
-
+      
       opened_tokens = []
-
+      
       until eos?
-
+        
         if match = scan(/\s+/)
           encoder.text_token match, :space
           
@@ -26,20 +33,22 @@ module Scanners
           encoder.text_token kind, :class
           encoder.text_token '(', :operator
           match = self[2]
-          encoder.text_token match, kind.to_sym
+          unless match.empty?
+            if @known_token_kinds.include? kind
+              encoder.text_token match, kind.to_sym
+            else
+              encoder.text_token match, :plain
+            end
+          end
           encoder.text_token match, :operator if match = scan(/\)/)
           
         elsif match = scan(/ (\w+) ([<\[]) /x)
-          kind = self[1]
-          case self[2]
-          when '<'
-            encoder.text_token kind, :class
-          when '['
-            encoder.text_token kind, :class
+          encoder.text_token self[1], :class
+          if @known_token_kinds.include? self[1]
+            kind = self[1].to_sym
           else
-            raise 'CodeRay bug: This case should not be reached.'
+            kind = :unknown
           end
-          kind = kind.to_sym
           opened_tokens << kind
           encoder.begin_group kind
           encoder.text_token self[2], :operator
@@ -59,8 +68,8 @@ module Scanners
       
       encoder
     end
-
+    
   end
-
+  
 end
 end
diff --git a/lib/coderay/scanners/ruby.rb b/lib/coderay/scanners/ruby.rb
index c282f31..5b8de42 100644
--- a/lib/coderay/scanners/ruby.rb
+++ b/lib/coderay/scanners/ruby.rb
@@ -164,15 +164,19 @@ module Scanners
               end
               
             elsif match = scan(/ ' (?:(?>[^'\\]*) ')? | " (?:(?>[^"\\\#]*) ")? /mx)
-              encoder.begin_group :string
               if match.size == 1
+                kind = check(self.class::StringState.simple_key_pattern(match)) ? :key : :string
+                encoder.begin_group kind
                 encoder.text_token match, :delimiter
-                state = self.class::StringState.new :string, match == '"', match  # important for streaming
+                state = self.class::StringState.new kind, match == '"', match  # important for streaming
               else
+                kind = value_expected == true && scan(/:/) ? :key : :string
+                encoder.begin_group kind
                 encoder.text_token match[0,1], :delimiter
                 encoder.text_token match[1..-2], :content if match.size > 2
                 encoder.text_token match[-1,1], :delimiter
-                encoder.end_group :string
+                encoder.end_group kind
+                encoder.text_token ':', :operator if kind == :key
                 value_expected = false
               end
               
@@ -191,11 +195,14 @@ module Scanners
                 encoder.text_token match, :error
                 method_call_expected = false
               else
-                encoder.text_token match, self[1] ? :float : :integer  # TODO: send :hex/:octal/:binary
+                kind = self[1] ? :float : :integer  # TODO: send :hex/:octal/:binary
+                match << 'r' if match !~ /e/i && scan(/r/)
+                match << 'i' if scan(/i/)
+                encoder.text_token match, kind
               end
               value_expected = false
               
-            elsif match = scan(/ [-+!~^\/]=? | [:;] | [*|&]{1,2}=? | >>? /x)
+            elsif match = scan(/ [-+!~^\/]=? | [:;] | &\. | [*|&]{1,2}=? | >>? /x)
               value_expected = true
               encoder.text_token match, :operator
               
@@ -208,7 +215,7 @@ module Scanners
               encoder.end_group kind
               heredocs ||= []  # create heredocs if empty
               heredocs << self.class::StringState.new(kind, quote != "'", delim,
-                self[1] == '-' ? :indented : :linestart)
+                self[1] ? :indented : :linestart)
               value_expected = false
               
             elsif value_expected && match = scan(/#{patterns::FANCY_STRING_START}/o)
@@ -269,7 +276,7 @@ module Scanners
             end
             
             if last_state
-              state = last_state
+              state = last_state unless state.is_a?(StringState)  # otherwise, a simple 'def"' results in unclosed tokens
               last_state = nil
             end
             
diff --git a/lib/coderay/scanners/ruby/patterns.rb b/lib/coderay/scanners/ruby/patterns.rb
index ed071d2..e5a156d 100644
--- a/lib/coderay/scanners/ruby/patterns.rb
+++ b/lib/coderay/scanners/ruby/patterns.rb
@@ -114,7 +114,7 @@ module Scanners
     # NOTE: This is not completely correct, but
     # nobody needs heredoc delimiters ending with \n.
     HEREDOC_OPEN = /
-      << (-)?              # $1 = float
+      << ([-~])?           # $1 = float
       (?:
         ( [A-Za-z_0-9]+ )  # $2 = delim
       |
@@ -157,13 +157,16 @@ module Scanners
       yield
     ])
     
-    FANCY_STRING_START = / % ( [QqrsWwx] | (?![a-zA-Z0-9]) ) ([^a-zA-Z0-9]) /x
+    FANCY_STRING_START = / % ( [iIqQrswWx] | (?![a-zA-Z0-9]) ) ([^a-zA-Z0-9]) /x
     FANCY_STRING_KIND = Hash.new(:string).merge({
+      'i' => :symbol,
+      'I' => :symbol,
       'r' => :regexp,
       's' => :symbol,
       'x' => :shell,
     })
     FANCY_STRING_INTERPRETED = Hash.new(true).merge({
+      'i' => false,
       'q' => false,
       's' => false,
       'w' => false,
diff --git a/lib/coderay/scanners/ruby/string_state.rb b/lib/coderay/scanners/ruby/string_state.rb
index 2f398d1..95f1e83 100644
--- a/lib/coderay/scanners/ruby/string_state.rb
+++ b/lib/coderay/scanners/ruby/string_state.rb
@@ -16,7 +16,6 @@ module Scanners
       
       STRING_PATTERN = Hash.new do |h, k|
         delim, interpreted = *k
-        # delim = delim.dup  # workaround for old Ruby
         delim_pattern = Regexp.escape(delim)
         if closing_paren = CLOSING_PAREN[delim]
           delim_pattern << Regexp.escape(closing_paren)
@@ -29,12 +28,21 @@ module Scanners
         #     '| [|?*+(){}\[\].^$]'
         #   end
         
-        h[k] =
-          if interpreted && delim != '#'
-            / (?= [#{delim_pattern}] | \# [{$@] ) /mx
-          else
-            / (?= [#{delim_pattern}] ) /mx
-          end
+        if interpreted && delim != '#'
+          / (?= [#{delim_pattern}] | \# [{$@] ) /mx
+        else
+          / (?= [#{delim_pattern}] ) /mx
+        end.tap do |pattern|
+          h[k] = pattern if (delim.respond_to?(:ord) ? delim.ord : delim[0]) < 256
+        end
+      end
+      
+      def self.simple_key_pattern delim
+        if delim == "'"
+          / (?> (?: [^\\']+ | \\. )* ) ' : /mx
+        else
+          / (?> (?: [^\\"\#]+ | \\. | \#\$[\\"] | \#\{[^\{\}]+\} | \#(?!\{) )* ) " : /mx
+        end
       end
       
       def initialize kind, interpreted, delim, heredoc = false
diff --git a/lib/coderay/scanners/sass.rb b/lib/coderay/scanners/sass.rb
index 167051d..e3296b9 100644
--- a/lib/coderay/scanners/sass.rb
+++ b/lib/coderay/scanners/sass.rb
@@ -7,11 +7,6 @@ module Scanners
     register_for :sass
     file_extension 'sass'
     
-    STRING_CONTENT_PATTERN = {
-      "'" => /(?:[^\n\'\#]+|\\\n|#{RE::Escape}|#(?!\{))+/,
-      '"' => /(?:[^\n\"\#]+|\\\n|#{RE::Escape}|#(?!\{))+/,
-    }
-    
   protected
     
     def setup
@@ -19,8 +14,9 @@ module Scanners
     end
     
     def scan_tokens encoder, options
-      states = Array(options[:state] || @state)
-      string_delimiter = nil
+      states = Array(options[:state] || @state).dup
+      
+      encoder.begin_group :string if states.last == :sqstring || states.last == :dqstring
       
       until eos?
         
@@ -48,7 +44,7 @@ module Scanners
         elsif case states.last
           when :initial, :media, :sass_inline
             if match = scan(/(?>#{RE::Ident})(?!\()/ox)
-              encoder.text_token match, value_expected ? :value : (check(/.*:/) ? :key : :tag)
+              encoder.text_token match, value_expected ? :value : (check(/.*:(?![a-z])/) ? :key : :tag)
               next
             elsif !value_expected && (match = scan(/\*/))
               encoder.text_token match, :tag
@@ -91,24 +87,23 @@ module Scanners
               next
             end
             
-          when :string
-            if match = scan(STRING_CONTENT_PATTERN[string_delimiter])
+          when :sqstring, :dqstring
+            if match = scan(states.last == :sqstring ? /(?:[^\n\'\#]+|\\\n|#{RE::Escape}|#(?!\{))+/o : /(?:[^\n\"\#]+|\\\n|#{RE::Escape}|#(?!\{))+/o)
               encoder.text_token match, :content
             elsif match = scan(/['"]/)
               encoder.text_token match, :delimiter
               encoder.end_group :string
-              string_delimiter = nil
               states.pop
             elsif match = scan(/#\{/)
               encoder.begin_group :inline
               encoder.text_token match, :inline_delimiter
               states.push :sass_inline
             elsif match = scan(/ \\ | $ /x)
-              encoder.end_group :string
+              encoder.end_group states.last
               encoder.text_token match, :error unless match.empty?
               states.pop
             else
-              raise_inspect "else case #{string_delimiter} reached; %p not handled." % peek(1), encoder
+              raise_inspect "else case #{states.last} reached; %p not handled." % peek(1), encoder
             end
           
           when :include
@@ -119,7 +114,7 @@ module Scanners
           
           else
             #:nocov:
-            raise_inspect 'Unknown state', encoder
+            raise_inspect 'Unknown state: %p' % [states.last], encoder
             #:nocov:
             
           end
@@ -157,15 +152,15 @@ module Scanners
           
         elsif match = scan(/['"]/)
           encoder.begin_group :string
-          string_delimiter = match
           encoder.text_token match, :delimiter
           if states.include? :sass_inline
-            content = scan_until(/(?=#{string_delimiter}|\}|\z)/)
+            # no nesting, just scan the string until delimiter
+            content = scan_until(/(?=#{match}|\}|\z)/)
             encoder.text_token content, :content unless content.empty?
-            encoder.text_token string_delimiter, :delimiter if scan(/#{string_delimiter}/)
+            encoder.text_token match, :delimiter if scan(/#{match}/)
             encoder.end_group :string
           else
-            states.push :string
+            states.push match == "'" ? :sqstring : :dqstring
           end
           
         elsif match = scan(/#{RE::Function}/o)
@@ -176,7 +171,7 @@ module Scanners
             encoder.text_token match[start.size..-2], :content
             encoder.text_token ')', :delimiter
           else
-            encoder.text_token match[start.size..-1], :content
+            encoder.text_token match[start.size..-1], :content if start.size < match.size
           end
           encoder.end_group :function
           
@@ -195,7 +190,7 @@ module Scanners
         elsif match = scan(/(?:rgb|hsl)a?\([^()\n]*\)?/)
           encoder.text_token match, :color
           
-        elsif match = scan(/@else if\b|#{RE::AtKeyword}/)
+        elsif match = scan(/@else if\b|#{RE::AtKeyword}/o)
           encoder.text_token match, :directive
           value_expected = true
           
@@ -214,8 +209,18 @@ module Scanners
         
       end
       
+      states.pop if states.last == :include
+      
       if options[:keep_state]
-        @state = states
+        @state = states.dup
+      end
+      
+      while state = states.pop
+        if state == :sass_inline
+          encoder.end_group :inline
+        elsif state == :sqstring || state == :dqstring
+          encoder.end_group :string
+        end
       end
       
       encoder
diff --git a/lib/coderay/scanners/sql.rb b/lib/coderay/scanners/sql.rb
index b757278..7d57f77 100644
--- a/lib/coderay/scanners/sql.rb
+++ b/lib/coderay/scanners/sql.rb
@@ -1,8 +1,9 @@
-module CodeRay module Scanners
+module CodeRay
+module Scanners
   
   # by Josh Goebel
   class SQL < Scanner
-
+    
     register_for :sql
     
     KEYWORDS = %w(
@@ -56,6 +57,12 @@ module CodeRay module Scanners
     
     STRING_PREFIXES = /[xnb]|_\w+/i
     
+    STRING_CONTENT_PATTERN = {
+      '"' => / (?: [^\\"] | "" )+ /x,
+      "'" => / (?: [^\\'] | '' )+ /x,
+      '`' => / (?: [^\\`] | `` )+ /x,
+    }
+    
     def scan_tokens encoder, options
       
       state = :initial
@@ -89,7 +96,7 @@ module CodeRay module Scanners
             state = :string
             encoder.text_token match, :delimiter
             
-          elsif match = scan(/ @? [A-Za-z_][A-Za-z_0-9]* /x)
+          elsif match = scan(/ @? [A-Za-z_][A-Za-z_0-9\$]* /x)
             encoder.text_token match, name_expected ? :ident : (match[0] == ?@ ? :variable : IDENT_KIND[match])
             name_expected = false
             
@@ -114,41 +121,28 @@ module CodeRay module Scanners
           end
           
         elsif state == :string
-          if match = scan(/[^\\"'`]+/)
-            string_content << match
-            next
+          if match = scan(STRING_CONTENT_PATTERN[string_type])
+            encoder.text_token match, :content
           elsif match = scan(/["'`]/)
             if string_type == match
               if peek(1) == string_type  # doubling means escape
-                string_content << string_type << getch
-                next
-              end
-              unless string_content.empty?
-                encoder.text_token string_content, :content
-                string_content = ''
+                encoder.text_token match + getch, :content
+              else
+                encoder.text_token match, :delimiter
+                encoder.end_group :string
+                state = :initial
+                string_type = nil
               end
-              encoder.text_token match, :delimiter
-              encoder.end_group :string
-              state = :initial
-              string_type = nil
             else
-              string_content << match
+              encoder.text_token match, :content
             end
           elsif match = scan(/ \\ (?: #{ESCAPE} | #{UNICODE_ESCAPE} ) /mox)
-            unless string_content.empty?
-              encoder.text_token string_content, :content
-              string_content = ''
-            end
             encoder.text_token match, :char
           elsif match = scan(/ \\ . /mox)
-            string_content << match
-            next
+            encoder.text_token match, :content
           elsif match = scan(/ \\ | $ /x)
-            unless string_content.empty?
-              encoder.text_token string_content, :content
-              string_content = ''
-            end
             encoder.text_token match, :error unless match.empty?
+            encoder.end_group :string
             state = :initial
           else
             raise "else case \" reached; %p not handled." % peek(1), encoder
@@ -171,4 +165,5 @@ module CodeRay module Scanners
     
   end
   
-end end
\ No newline at end of file
+end
+end
diff --git a/lib/coderay/scanners/taskpaper.rb b/lib/coderay/scanners/taskpaper.rb
new file mode 100644
index 0000000..42670bc
--- /dev/null
+++ b/lib/coderay/scanners/taskpaper.rb
@@ -0,0 +1,36 @@
+module CodeRay
+module Scanners
+  
+  class Taskpaper < Scanner
+    
+    register_for :taskpaper
+    file_extension 'taskpaper'
+    
+  protected
+    
+    def scan_tokens encoder, options
+      until eos?
+        if match = scan(/\S.*:.*$/)                  # project
+          encoder.text_token(match, :namespace)
+        elsif match = scan(/-.+@done.*/)             # completed task
+          encoder.text_token(match, :done)
+        elsif match = scan(/-(?:[^@\n]+|@(?!due))*/) # task
+          encoder.text_token(match, :plain)
+        elsif match = scan(/@due.*/)                 # comment
+          encoder.text_token(match, :important)
+        elsif match = scan(/.+/)                     # comment
+          encoder.text_token(match, :comment)
+        elsif match = scan(/\s+/)                    # space
+          encoder.text_token(match, :space)
+        else                                         # other
+          encoder.text_token getch, :error
+        end
+      end
+      
+      encoder
+    end
+    
+  end
+  
+end
+end
diff --git a/lib/coderay/scanners/yaml.rb b/lib/coderay/scanners/yaml.rb
index 96f4e93..32c8e2c 100644
--- a/lib/coderay/scanners/yaml.rb
+++ b/lib/coderay/scanners/yaml.rb
@@ -47,7 +47,7 @@ module Scanners
           when !check(/(?:"[^"]*")(?=: |:$)/) && match = scan(/"/)
             encoder.begin_group :string
             encoder.text_token match, :delimiter
-            encoder.text_token match, :content if match = scan(/ [^"\\]* (?: \\. [^"\\]* )* /mx)
+            encoder.text_token match, :content if (match = scan(/ [^"\\]* (?: \\. [^"\\]* )* /mx)) && !match.empty?
             encoder.text_token match, :delimiter if match = scan(/"/)
             encoder.end_group :string
             next
@@ -84,7 +84,7 @@ module Scanners
           when match = scan(/(?:"[^"\n]*"|'[^'\n]*')(?= *:(?: |$))/)
             encoder.begin_group :key
             encoder.text_token match[0,1], :delimiter
-            encoder.text_token match[1..-2], :content
+            encoder.text_token match[1..-2], :content if match.size > 2
             encoder.text_token match[-1,1], :delimiter
             encoder.end_group :key
             key_indent = column(pos - match.size) - 1