Merge branch 'master' into upstream

9 files changed, 600 insertions, 42 deletions

diff --git a/lib/coderay/scanners/css.rb b/lib/coderay/scanners/css.rb
index 7b731ef..732f9c5 100644
--- a/lib/coderay/scanners/css.rb
+++ b/lib/coderay/scanners/css.rb
@@ -7,27 +7,25 @@ module Scanners
     
     KINDS_NOT_LOC = [
       :comment,
-      :class, :pseudo_class, :type,
-      :constant, :directive,
+      :class, :pseudo_class, :tag,
+      :id, :directive,
       :key, :value, :operator, :color, :float, :string,
-      :error, :important,
+      :error, :important, :type,
     ]  # :nodoc:
     
     module RE  # :nodoc:
       Hex = /[0-9a-fA-F]/
-      Unicode = /\\#{Hex}{1,6}(?:\r\n|\s)?/ # differs from standard because it allows uppercase hex too
-      Escape = /#{Unicode}|\\[^\r\n\f0-9a-fA-F]/
-      NMChar = /[-_a-zA-Z0-9]|#{Escape}/
-      NMStart = /[_a-zA-Z]|#{Escape}/
-      NL = /\r\n|\r|\n|\f/
-      String1 = /"(?:[^\n\r\f\\"]|\\#{NL}|#{Escape})*"?/  # TODO: buggy regexp
-      String2 = /'(?:[^\n\r\f\\']|\\#{NL}|#{Escape})*'?/  # TODO: buggy regexp
+      Unicode = /\\#{Hex}{1,6}\b/ # differs from standard because it allows uppercase hex too
+      Escape = /#{Unicode}|\\[^\n0-9a-fA-F]/
+      NMChar = /[-_a-zA-Z0-9]/
+      NMStart = /[_a-zA-Z]/
+      String1 = /"(?:[^\n\\"]+|\\\n|#{Escape})*"?/  # TODO: buggy regexp
+      String2 = /'(?:[^\n\\']+|\\\n|#{Escape})*'?/  # TODO: buggy regexp
       String = /#{String1}|#{String2}/
       
       HexColor = /#(?:#{Hex}{6}|#{Hex}{3})/
-      Color = /#{HexColor}/
       
-      Num = /-?(?:[0-9]+|[0-9]*\.[0-9]+)/
+      Num = /-?(?:[0-9]*\.[0-9]+|[0-9]+)/
       Name = /#{NMChar}+/
       Ident = /-?#{NMStart}#{NMChar}*/
       AtKeyword = /@#{Ident}/
@@ -35,16 +33,15 @@ module Scanners
       
       reldimensions = %w[em ex px]
       absdimensions = %w[in cm mm pt pc]
-      Unit = Regexp.union(*(reldimensions + absdimensions + %w[s]))
+      Unit = Regexp.union(*(reldimensions + absdimensions + %w[s dpi dppx deg]))
       
       Dimension = /#{Num}#{Unit}/
       
-      Comment = %r! /\* (?: .*? \*/ | .* ) !mx
-      Function = /(?:url|alpha|attr|counters?)\((?:[^)\n\r\f]|\\\))*\)?/
+      Function = /(?:url|alpha|attr|counters?)\((?:[^)\n]|\\\))*\)?/
       
-      Id = /##{Name}/
+      Id = /(?!#{HexColor}\b(?!-))##{Name}/
       Class = /\.#{Name}/
-      PseudoClass = /:#{Name}/
+      PseudoClass = /::?#{Ident}/
       AttributeSelector = /\[[^\]]*\]?/
     end
     
@@ -52,7 +49,7 @@ module Scanners
     
     def setup
       @state = :initial
-      @value_expected = nil
+      @value_expected = false
     end
     
     def scan_tokens encoder, options
@@ -67,13 +64,13 @@ module Scanners
         elsif case states.last
           when :initial, :media
             if match = scan(/(?>#{RE::Ident})(?!\()|\*/ox)
-              encoder.text_token match, :type
+              encoder.text_token match, :tag
               next
             elsif match = scan(RE::Class)
               encoder.text_token match, :class
               next
             elsif match = scan(RE::Id)
-              encoder.text_token match, :constant
+              encoder.text_token match, :id
               next
             elsif match = scan(RE::PseudoClass)
               encoder.text_token match, :pseudo_class
@@ -158,7 +155,7 @@ module Scanners
         elsif match = scan(/(?: #{RE::Dimension} | #{RE::Percentage} | #{RE::Num} )/ox)
           encoder.text_token match, :float
           
-        elsif match = scan(/#{RE::Color}/o)
+        elsif match = scan(/#{RE::HexColor}/o)
           encoder.text_token match, :color
           
         elsif match = scan(/! *important/)
@@ -170,7 +167,7 @@ module Scanners
         elsif match = scan(RE::AtKeyword)
           encoder.text_token match, :directive
           
-        elsif match = scan(/ [+>:;,.=()\/] /x)
+        elsif match = scan(/ [+>~:;,.=()\/] /x)
           if match == ':'
             value_expected = true
           elsif match == ';'
diff --git a/lib/coderay/scanners/diff.rb b/lib/coderay/scanners/diff.rb
index 38efaf4..af0f755 100644
--- a/lib/coderay/scanners/diff.rb
+++ b/lib/coderay/scanners/diff.rb
@@ -45,7 +45,7 @@ module Scanners
           if match = scan(/--- |\+\+\+ |=+|_+/)
             encoder.begin_line line_kind = :head
             encoder.text_token match, :head
-            if match = scan(/.*?(?=$|[\t\n\x00]|  \(revision)/)
+            if match = scan(/[^\x00\n]+?(?=$|[\t\n]|  \(revision)/)
               encoder.text_token match, :filename
               if options[:highlight_code] && match != '/dev/null'
                 file_type = CodeRay::FileType.fetch(match, :text)
diff --git a/lib/coderay/scanners/java_script.rb b/lib/coderay/scanners/java_script.rb
index 92e3dfa..9eb0a0a 100644
--- a/lib/coderay/scanners/java_script.rb
+++ b/lib/coderay/scanners/java_script.rb
@@ -54,10 +54,17 @@ module Scanners
     
   protected
     
+    def setup
+      @state = :initial
+    end
+    
     def scan_tokens encoder, options
       
-      state = :initial
-      string_delimiter = nil
+      state, string_delimiter = options[:state] || @state
+      if string_delimiter
+        encoder.begin_group state
+      end
+      
       value_expected = true
       key_expected = false
       function_expected = false
@@ -72,9 +79,10 @@ module Scanners
             value_expected = true if !value_expected && match.index(?\n)
             encoder.text_token match, :space
             
-          elsif match = scan(%r! // [^\n\\]* (?: \\. [^\n\\]* )* | /\* (?: .*? \*/ | .* ) !mx)
+          elsif match = scan(%r! // [^\n\\]* (?: \\. [^\n\\]* )* | /\* (?: .*? \*/ | .*() ) !mx)
             value_expected = true
             encoder.text_token match, :comment
+            state = :open_multi_line_comment if self[1]
             
           elsif check(/\.?\d/)
             key_expected = value_expected = false
@@ -176,19 +184,35 @@ module Scanners
           elsif match = scan(/ \\ | $ /x)
             encoder.end_group state
             encoder.text_token match, :error unless match.empty?
+            string_delimiter = nil
             key_expected = value_expected = false
             state = :initial
           else
             raise_inspect "else case #{string_delimiter} reached; %p not handled." % peek(1), encoder
           end
           
+        when :open_multi_line_comment
+          if match = scan(%r! .*? \*/ !mx)
+            state = :initial
+          else
+            match = scan(%r! .+ !mx)
+          end
+          value_expected = true
+          encoder.text_token match, :comment if match
+          
         else
-          raise_inspect 'Unknown state', encoder
+          #:nocov:
+          raise_inspect 'Unknown state: %p' % [state], encoder
+          #:nocov:
           
         end
         
       end
       
+      if options[:keep_state]
+        @state = state, string_delimiter
+      end
+      
       if [:string, :regexp].include? state
         encoder.end_group state
       end
diff --git a/lib/coderay/scanners/json.rb b/lib/coderay/scanners/json.rb
index 4e0f462..3754a9b 100644
--- a/lib/coderay/scanners/json.rb
+++ b/lib/coderay/scanners/json.rb
@@ -14,15 +14,17 @@ 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 = :initial
-      stack = []
-      key_expected = false
+      state = options[:state] || @state
       
       until eos?
         
@@ -32,18 +34,11 @@ 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 +77,10 @@ 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..25bebbe
--- /dev/null
+++ b/lib/coderay/scanners/lua.rb
@@ -0,0 +1,275 @@
+# 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
+      
+      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
+    
+  end
+  
+end
+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/ruby.rb b/lib/coderay/scanners/ruby.rb
index c5cf1e2..c282f31 100644
--- a/lib/coderay/scanners/ruby.rb
+++ b/lib/coderay/scanners/ruby.rb
@@ -96,7 +96,7 @@ module Scanners
                                       /#{patterns::METHOD_NAME}/o)
               
               kind = patterns::IDENT_KIND[match]
-              if kind == :ident && value_expected != :colon_expected && scan(/:(?!:)/)
+              if value_expected != :colon_expected && scan(/:(?!:)/)
                 value_expected = true
                 encoder.text_token match, :key
                 encoder.text_token ':',   :operator
diff --git a/lib/coderay/scanners/sass.rb b/lib/coderay/scanners/sass.rb
new file mode 100644
index 0000000..167051d
--- /dev/null
+++ b/lib/coderay/scanners/sass.rb
@@ -0,0 +1,227 @@
+module CodeRay
+module Scanners
+  
+  # A scanner for Sass.
+  class Sass < CSS
+    
+    register_for :sass
+    file_extension 'sass'
+    
+    STRING_CONTENT_PATTERN = {
+      "'" => /(?:[^\n\'\#]+|\\\n|#{RE::Escape}|#(?!\{))+/,
+      '"' => /(?:[^\n\"\#]+|\\\n|#{RE::Escape}|#(?!\{))+/,
+    }
+    
+  protected
+    
+    def setup
+      @state = :initial
+    end
+    
+    def scan_tokens encoder, options
+      states = Array(options[:state] || @state)
+      string_delimiter = nil
+      
+      until eos?
+        
+        if bol? && (match = scan(/(?>( +)?(\/[\*\/])(.+)?)(?=\n)/))
+          encoder.text_token self[1], :space if self[1]
+          encoder.begin_group :comment
+          encoder.text_token self[2], :delimiter
+          encoder.text_token self[3], :content if self[3]
+          if match = scan(/(?:\n+#{self[1]} .*)+/)
+            encoder.text_token match, :content
+          end
+          encoder.end_group :comment
+        elsif match = scan(/\n|[^\n\S]+\n?/)
+          encoder.text_token match, :space
+          if match.index(/\n/)
+            value_expected = false
+            states.pop if states.last == :include
+          end
+        
+        elsif states.last == :sass_inline && (match = scan(/\}/))
+          encoder.text_token match, :inline_delimiter
+          encoder.end_group :inline
+          states.pop
+        
+        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)
+              next
+            elsif !value_expected && (match = scan(/\*/))
+              encoder.text_token match, :tag
+              next
+            elsif match = scan(RE::Class)
+              encoder.text_token match, :class
+              next
+            elsif match = scan(RE::Id)
+              encoder.text_token match, :id
+              next
+            elsif match = scan(RE::PseudoClass)
+              encoder.text_token match, :pseudo_class
+              next
+            elsif match = scan(RE::AttributeSelector)
+              # TODO: Improve highlighting inside of attribute selectors.
+              encoder.text_token match[0,1], :operator
+              encoder.text_token match[1..-2], :attribute_name if match.size > 2
+              encoder.text_token match[-1,1], :operator if match[-1] == ?]
+              next
+            elsif match = scan(/(\=|@mixin +)#{RE::Ident}/o)
+              encoder.text_token match, :function
+              next
+            elsif match = scan(/@import\b/)
+              encoder.text_token match, :directive
+              states << :include
+              next
+            elsif match = scan(/@media\b/)
+              encoder.text_token match, :directive
+              # states.push :media_before_name
+              next
+            end
+          
+          when :block
+            if match = scan(/(?>#{RE::Ident})(?!\()/ox)
+              if value_expected
+                encoder.text_token match, :value
+              else
+                encoder.text_token match, :key
+              end
+              next
+            end
+            
+          when :string
+            if match = scan(STRING_CONTENT_PATTERN[string_delimiter])
+              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.text_token match, :error unless match.empty?
+              states.pop
+            else
+              raise_inspect "else case #{string_delimiter} reached; %p not handled." % peek(1), encoder
+            end
+          
+          when :include
+            if match = scan(/[^\s'",]+/)
+              encoder.text_token match, :include
+              next
+            end
+          
+          else
+            #:nocov:
+            raise_inspect 'Unknown state', encoder
+            #:nocov:
+            
+          end
+          
+        elsif match = scan(/\$#{RE::Ident}/o)
+          encoder.text_token match, :variable
+          next
+        
+        elsif match = scan(/&/)
+          encoder.text_token match, :local_variable
+          
+        elsif match = scan(/\+#{RE::Ident}/o)
+          encoder.text_token match, :include
+          value_expected = true
+          
+        elsif match = scan(/\/\*(?:.*?\*\/|.*)|\/\/.*/)
+          encoder.text_token match, :comment
+          
+        elsif match = scan(/#\{/)
+          encoder.begin_group :inline
+          encoder.text_token match, :inline_delimiter
+          states.push :sass_inline
+          
+        elsif match = scan(/\{/)
+          value_expected = false
+          encoder.text_token match, :operator
+          states.push :block
+          
+        elsif match = scan(/\}/)
+          value_expected = false
+          encoder.text_token match, :operator
+          if states.last == :block || states.last == :media
+            states.pop
+          end
+          
+        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)/)
+            encoder.text_token content, :content unless content.empty?
+            encoder.text_token string_delimiter, :delimiter if scan(/#{string_delimiter}/)
+            encoder.end_group :string
+          else
+            states.push :string
+          end
+          
+        elsif match = scan(/#{RE::Function}/o)
+          encoder.begin_group :function
+          start = match[/^[-\w]+\(/]
+          encoder.text_token start, :delimiter
+          if match[-1] == ?)
+            encoder.text_token match[start.size..-2], :content
+            encoder.text_token ')', :delimiter
+          else
+            encoder.text_token match[start.size..-1], :content
+          end
+          encoder.end_group :function
+          
+        elsif match = scan(/[a-z][-a-z_]*(?=\()/o)
+          encoder.text_token match, :predefined
+          
+        elsif match = scan(/(?: #{RE::Dimension} | #{RE::Percentage} | #{RE::Num} )/ox)
+          encoder.text_token match, :float
+          
+        elsif match = scan(/#{RE::HexColor}/o)
+          encoder.text_token match, :color
+          
+        elsif match = scan(/! *(?:important|optional)/)
+          encoder.text_token match, :important
+          
+        elsif match = scan(/(?:rgb|hsl)a?\([^()\n]*\)?/)
+          encoder.text_token match, :color
+          
+        elsif match = scan(/@else if\b|#{RE::AtKeyword}/)
+          encoder.text_token match, :directive
+          value_expected = true
+          
+        elsif match = scan(/ == | != | [-+*\/>~:;,.=()] /x)
+          if match == ':'
+            value_expected = true
+          elsif match == ';'
+            value_expected = false
+          end
+          encoder.text_token match, :operator
+          
+        else
+          encoder.text_token getch, :error
+          
+        end
+        
+      end
+      
+      if options[:keep_state]
+        @state = states
+      end
+      
+      encoder
+    end
+    
+  end
+  
+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