diff --git a/lib/coderay/helpers/file_type.rb b/lib/coderay/helpers/file_type.rb
index 637001b8..39b741a7 100644
--- a/lib/coderay/helpers/file_type.rb
+++ b/lib/coderay/helpers/file_type.rb
@@ -84,6 +84,7 @@ def shebang filename
       'css'      => :css,
       'diff'     => :diff,
       'dpr'      => :delphi,
+      'e'        => :e,
       'erb'      => :erb,
       'gemspec'  => :ruby,
       'groovy'   => :groovy,
@@ -118,8 +119,13 @@ def shebang filename
       'rxml'     => :ruby,
       # 'sch'      => :scheme,
       'sql'      => :sql,
+      'sv'       => :systemverilog,
+      'svh'      => :systemverilog,
       # 'ss'       => :scheme,
       'tmproj'   => :xml,
+      'v'        => :systemverilog,
+      'vhd'      => :vhdl,
+      'vhdl'     => :vhdl,
       'xhtml'    => :html,
       'xml'      => :xml,
       'yaml'     => :yaml,
diff --git a/lib/coderay/scanners/_map.rb b/lib/coderay/scanners/_map.rb
index a240298d..60c011b8 100644
--- a/lib/coderay/scanners/_map.rb
+++ b/lib/coderay/scanners/_map.rb
@@ -2,21 +2,23 @@ module CodeRay
 module Scanners
   
   map \
-    :'c++'       => :cpp,
-    :cplusplus   => :cpp,
-    :ecmascript  => :java_script,
-    :ecma_script => :java_script,
-    :rhtml       => :erb,
-    :eruby       => :erb,
-    :irb         => :ruby,
-    :javascript  => :java_script,
-    :js          => :java_script,
-    :pascal      => :delphi,
-    :patch       => :diff,
-    :plain       => :text,
-    :plaintext   => :text,
-    :xhtml       => :html,
-    :yml         => :yaml
+    :'c++'         => :cpp,
+    :cplusplus     => :cpp,
+    :ecmascript    => :java_script,
+    :ecma_script   => :java_script,
+    :rhtml         => :erb,
+    :eruby         => :erb,
+    :irb           => :ruby,
+    :javascript    => :java_script,
+    :js            => :java_script,
+    :pascal        => :delphi,
+    :patch         => :diff,
+    :plain         => :text,
+    :plaintext     => :text,
+    :specman       => :e,
+    :verilog       => :systemverilog,
+    :xhtml         => :html,
+    :yml           => :yaml
   
   default :text
   
diff --git a/lib/coderay/scanners/e.rb b/lib/coderay/scanners/e.rb
new file mode 100644
index 00000000..c6fac2bc
--- /dev/null
+++ b/lib/coderay/scanners/e.rb
@@ -0,0 +1,247 @@
+module CodeRay
+module Scanners
+
+  # TODO: Review. Most of this code is copied from the C++ scanner and not
+  # applicable for e.
+
+  # Scanner for IEEE Std 1647 e
+  #
+  # Aliases: +specmen+
+  class E < Scanner
+
+    register_for :e
+    file_extension 'e'
+    title 'e'
+
+    # TODO: DUT'unique_name
+
+    # NOTE: e is an odd language in that the essential vocabulary of the
+    # language (like 'extend') are not actually reserved words. The following
+    # parser isn't smart enough to handle that; it pretends that these are
+    # reserved words.
+
+    KEYWORDS = [
+       'a', 'also', 'bits', 'cover', 'each', 'else', 'empty', 'extend', 'first', 'for', 'ignore', 'illegal', 'if', 'in', 'is', 'item', 'keep', 'like', 'list', 'not', 'only', 'package', 'per_instance', 'radix', 'result', 'return', 'rf_manager', 'soft', 'sys', 'type', 'unit', 'using', 'var', 'when'
+    ]  # :nodoc:
+    
+    PREDEFINED_TYPES = [
+       'bool', 'bit', 'event', 'rf_scalar', 'rf_type', 'string', 'uint'
+    ]  # :nodoc:
+    PREDEFINED_CONSTANTS = [
+       'FALSE', 'TRUE'
+    ]  # :nodoc:
+    PREDEFINED_VARIABLES = [
+    ]  # :nodoc:
+    DIRECTIVES = [
+    ]  # :nodoc:
+    
+    IDENT_KIND = WordList.new(:ident).
+      add(KEYWORDS, :keyword).
+      add(PREDEFINED_TYPES, :predefined_type).
+      add(PREDEFINED_VARIABLES, :local_variable).
+      add(DIRECTIVES, :directive).
+      add(PREDEFINED_CONSTANTS, :predefined_constant)  # :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 = :comment_segment
+      label_expected = true
+      case_expected = false
+      label_expected_before_preproc_line = nil
+      in_preproc_line = false
+
+      until eos?
+
+        case state
+
+        when :comment_segment
+          if match = scan(/^<'$/)            
+            encoder.text_token match, :operator
+            state = :code_segment
+          elsif match = scan(/^.+$/)             
+            encoder.text_token match, :comment
+          elsif match = scan(/\\\n/)
+            encoder.text_token match, :space
+          else
+            encoder.text_token getch, :error
+          end
+
+        when :code_segment
+          if match = scan(/^'>$/)            
+            encoder.text_token match, :operator
+            state = :comment_segment
+
+          elsif match = scan(/ \s+ | \\\n /x)
+            if in_preproc_line && match != "\\\n" && match.index(?\n)
+              in_preproc_line = 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(%r! -- [^\n\\]* (?: \\. [^\n\\]* )* !mx)
+            encoder.text_token match, :comment
+
+          elsif match = scan(/ \# \s* if \s* 0 /x)
+            match << scan_until(/ ^\# (?:elif|else|endif) .*? $ | \z /xm) unless eos?
+            encoder.text_token match, :comment
+
+            #########################
+            # 4.1.4.2 Sized numbers
+          elsif match = scan(/[0-9]+'[bB][0-1_]+/)
+            label_expected = false
+            encoder.text_token match, :binary
+          elsif match = scan(/[0-9]+'[oO][0-7_]+/)
+            label_expected = false
+            encoder.text_token match, :octal
+          elsif match = scan(/[0-9]+'[dD][0-9_a-f]+/)
+            label_expected = false
+            encoder.text_token match, :integer
+          elsif match = scan(/[0-9]+'[hxHX][0-9_a-f]+/)
+            label_expected = false
+            encoder.text_token match, :hex
+
+            #########################
+            # 4.1.4.1 Unsized numbers
+          elsif match = scan(/0x[0-9_a-f]+/)
+            label_expected = false
+            encoder.text_token match, :hex
+          elsif match = scan(/0o([0-7_]+)/)
+            label_expected = false
+            encoder.text_token match, :octal
+          elsif match = scan(/0b[0-1_]+/)
+            label_expected = false
+            encoder.text_token match, :binary
+          elsif match = scan(/\-?[0-9_]+[kmKM]?/)
+            label_expected = false
+            encoder.text_token match, :integer
+
+
+          elsif match = scan(/ [-+*=<>?:;,!&^|()\[\]{}~%]+ | \/=? | \.(?!\d) /x)
+            label_expected = match =~ /[;\{\}]/
+            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
+              match << matched
+            else
+              label_expected = false
+              if kind == :keyword
+                case match
+                when 'class'
+                  state = :class_name_expected
+                when 'case', 'default'
+                  case_expected = true
+                end
+              end
+            end
+            encoder.text_token match, kind
+
+          elsif match = scan(/\$/)
+            encoder.text_token match, :ident
+          
+          elsif match = scan(/L?"/)
+            encoder.begin_group :string
+            if match[0] == ?L
+              encoder.text_token match, 'L', :modifier
+              match = '"'
+            end
+            state = :string
+            encoder.text_token match, :delimiter
+
+          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} )? '? /ox)
+            label_expected = false
+            encoder.text_token match, :char
+
+          elsif match = scan(/\d[fF]?|\d*\.\d+(?:[eE][+-]?\d+)?[fF]?|\d+[eE][+-]?\d+[fF]?/)
+            label_expected = false
+            encoder.text_token match, :float
+
+          else
+            encoder.text_token getch, :error
+
+          end
+
+        when :string
+          if match = scan(/[^\\"]+/)
+            encoder.text_token match, :content
+          elsif match = scan(/"/)
+            encoder.text_token match, :delimiter
+            encoder.end_group :string
+            state = :code_segment
+            label_expected = false
+          elsif match = scan(/ \\ (?: #{ESCAPE} | #{UNICODE_ESCAPE} ) /mox)
+            encoder.text_token match, :char
+          elsif match = scan(/ \\ | $ /x)
+            encoder.end_group :string
+            encoder.text_token match, :error
+            state = :code_segment
+            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 = :code_segment
+
+          elsif match = scan(/\s+/)
+            encoder.text_token match, :space
+            state = :code_segment if match.index ?\n
+
+          else
+            state = :code_segment
+
+          end
+        
+        when :class_name_expected
+          if match = scan(/ [A-Za-z_][A-Za-z_0-9]* /x)
+            encoder.text_token match, :class
+            state = :code_segment
+
+          elsif match = scan(/\s+/)
+            encoder.text_token match, :space
+
+          else
+            encoder.text_token getch, :error
+            state = :code_segment
+
+          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/systemverilog.rb b/lib/coderay/scanners/systemverilog.rb
new file mode 100644
index 00000000..e076656b
--- /dev/null
+++ b/lib/coderay/scanners/systemverilog.rb
@@ -0,0 +1,207 @@
+module CodeRay
+module Scanners
+
+  # TODO: Review. Most of this code is copied from the C++ scanner and not
+  # applicable for SystemVerilog.
+
+  # Scanner for IEEE Standard 1800-2009 SystemVerilog
+  #
+  # Aliases: +verilog+
+  class SystemVerilog < Scanner
+
+    register_for :systemverilog
+    file_extension 'sv'
+    title 'SystemVerilog'
+
+    
+    KEYWORDS = [
+      'accept_on', 'alias', 'always', 'always_comb', 'always_ff', 'always_latch', 'and', 'assert', 'assign', 'assume', 'before', 'begin', 'bind', 'bins', 'binsof', 'break', 'buf', 'bufif0', 'bufif1', 'byte', 'case', 'casex', 'casez', 'cell', 'chandle', 'checker', 'class', 'clocking', 'cmos', 'config', 'const', 'constraint', 'context', 'continue', 'cover', 'covergroup', 'coverpoint', 'cross', 'deassign', 'default', 'defparam', 'design', 'disable', 'dist', 'do', 'edge', 'else', 'end', 'endcase', 'endchecker', 'endclass', 'endclocking', 'endconfig', 'endfunction', 'endgenerate', 'endgroup', 'endinterface', 'endmodule', 'endpackage', 'endprimitive', 'endprogram', 'endproperty', 'endsequence', 'endspecify', 'endtable', 'endtask', 'enum', 'event', 'eventually', 'expect', 'export', 'extends', 'extern', 'final', 'first_match', 'for', 'force', 'foreach', 'forever', 'fork', 'forkjoin', 'function', 'generate', 'genvar', 'global', 'highz0', 'highz1', 'if', 'iff', 'ifnone', 'ignore_bins', 'illegal_bins', 'implies', 'import', 'incdir', 'include', 'initial', 'inout', 'input', 'inside', 'instance', 'interface', 'intersect', 'join', 'join_any', 'join_none', 'large', 'let', 'liblist', 'library', 'local', 'localparam', 'macromodule', 'matches', 'medium', 'modport', 'module', 'nand', 'negedge', 'new', 'nexttime', 'nmos', 'nor', 'noshowcancelled', 'not', 'notif0', 'notif1', 'or', 'output', 'package', 'packed', 'parameter', 'pmos', 'posedge', 'primitive', 'priority', 'program', 'property', 'protected', 'pull0', 'pull1', 'pulldown', 'pullup', 'pulsestyle_ondetect', 'pulsestyle_onevent', 'pure', 'rand', 'randc', 'randcase', 'randsequence', 'rcmos', 'real', 'realtime', 'ref', 'reg', 'reject_on', 'release', 'repeat', 'restrict', 'return', 'rnmos', 'rpmos', 'rtran', 'rtranif0', 'rtranif1', 's_always', 's_eventually', 's_nexttime', 's_until', 's_until_with', 'scalared', 'sequence', 'shortint', 'shortreal', 'showcancelled', 'signed', 'small', 'solve', 'specify', 'specparam', 'static', 'strong', 'strong0', 'strong1', 'struct', 'super', 'supply0', 'supply1', 'sync_accept_on', 'sync_reject_on', 'table', 'tagged', 'task', 'throughout', 'time', 'timeprecision', 'timeunit', 'tran', 'tranif0', 'tranif1', 'tri', 'tri0', 'tri1', 'triand', 'trior', 'trireg', 'type', 'typedef', 'union', 'unique', 'unique0', 'unsigned', 'until', 'until_with', 'untyped', 'use', 'uwire', 'var', 'vectored', 'wait', 'wait_order', 'wand', 'weak', 'weak0', 'weak1', 'while', 'wildcard', 'with', 'within', 'wor', 'xnor', 'xor'
+    ]  # :nodoc:
+    
+    PREDEFINED_TYPES = [
+      'bit', 'int', 'integer', 'logic', 'longint', 'string', 'wire'
+    ]  # :nodoc:
+    PREDEFINED_CONSTANTS = [
+      'null'
+    ]  # :nodoc:
+    PREDEFINED_VARIABLES = [
+      'this',
+    ]  # :nodoc:
+    DIRECTIVES = [
+      'automatic', 'virtual', 'void'
+    ]  # :nodoc:
+    
+    IDENT_KIND = WordList.new(:ident).
+      add(KEYWORDS, :keyword).
+      add(PREDEFINED_TYPES, :predefined_type).
+      add(PREDEFINED_VARIABLES, :local_variable).
+      add(DIRECTIVES, :directive).
+      add(PREDEFINED_CONSTANTS, :predefined_constant)  # :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
+              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(/ \# \s* if \s* 0 /x)
+            match << scan_until(/ ^\# (?:elif|else|endif) .*? $ | \z /xm) unless eos?
+            encoder.text_token match, :comment
+
+          elsif match = scan(/ [-+*=<>?:;,!&^|()\[\]{}~%]+ | \/=? | \.(?!\d) /x)
+            label_expected = match =~ /[;\{\}]/
+            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
+              match << matched
+            else
+              label_expected = false
+              if kind == :keyword
+                case match
+                when 'class'
+                  state = :class_name_expected
+                when 'case', 'default'
+                  case_expected = true
+                end
+              end
+            end
+            encoder.text_token match, kind
+
+          elsif match = scan(/\$/)
+            encoder.text_token match, :ident
+          
+          elsif match = scan(/L?"/)
+            encoder.begin_group :string
+            if match[0] == ?L
+              encoder.text_token match, 'L', :modifier
+              match = '"'
+            end
+            state = :string
+            encoder.text_token match, :delimiter
+
+          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} )? '? /ox)
+            label_expected = false
+            encoder.text_token match, :char
+
+          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+)(?![.eEfF])L?L?/)
+            label_expected = false
+            encoder.text_token match, :integer
+
+          elsif match = scan(/\d[fF]?|\d*\.\d+(?:[eE][+-]?\d+)?[fF]?|\d+[eE][+-]?\d+[fF]?/)
+            label_expected = false
+            encoder.text_token match, :float
+
+          else
+            encoder.text_token getch, :error
+
+          end
+
+        when :string
+          if match = scan(/[^\\"]+/)
+            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.end_group :string
+            encoder.text_token match, :error
+            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
+        
+        when :class_name_expected
+          if match = scan(/ [A-Za-z_][A-Za-z_0-9]* /x)
+            encoder.text_token match, :class
+            state = :initial
+
+          elsif match = scan(/\s+/)
+            encoder.text_token match, :space
+
+          else
+            encoder.text_token getch, :error
+            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/vhdl.rb b/lib/coderay/scanners/vhdl.rb
new file mode 100644
index 00000000..924b0236
--- /dev/null
+++ b/lib/coderay/scanners/vhdl.rb
@@ -0,0 +1,201 @@
+module CodeRay
+module Scanners
+
+  # TODO: Review. Most of this code is copied from the C++ scanner and not
+  # applicable for VHDL.
+
+  # Scanner for IEEE Standard 1076-2002 VHDL
+  class VHDL < Scanner
+
+    register_for :vhdl
+    file_extension 'vhd'
+    title 'VHDL'
+
+    # From IEEE Std 1076-2002: Section 13.9 Reserved Words
+    KEYWORDS = [
+'abs', 'access', 'after', 'alias', 'all', 'and', 'architecture', 'array', 'assert', 'attribute', 'begin', 'block', 'body', 'case', 'component', 'configuration', 'disconnect', 'downto', 'else', 'elsif', 'end', 'entity', 'exit', 'file', 'for', 'function', 'generate', 'generic', 'group', 'guarded', 'if', 'inertial', 'is', 'label', 'library', 'literal', 'loop', 'map', 'mod', 'nand', 'new', 'next', 'nor', 'not', 'null', 'of', 'on', 'open', 'or', 'others', 'package', 'port', 'postponed', 'procedural', 'procedure', 'process', 'protected', 'range', 'record', 'reference', 'reject', 'rem', 'report', 'return', 'rol', 'ror', 'select', 'severity', 'signal', 'sla', 'sll', 'sra', 'srl', 'subtype', 'then', 'to', 'transport', 'type', 'unaffected', 'units', 'until', 'use', 'wait', 'when', 'while', 'with', 'xnor', 'xor'    ]  # :nodoc:
+    
+    PREDEFINED_TYPES = [
+    ]  # :nodoc:
+    PREDEFINED_CONSTANTS = [
+    ]  # :nodoc:
+    PREDEFINED_VARIABLES = [
+    ]  # :nodoc:
+    DIRECTIVES = [
+                  'buffer', 'bus', 'constant', 'impure', 'in', 'inout', 'linkage', 'out', 'pure', 'register', 'shared', 'variable'
+    ]  # :nodoc:
+    
+    IDENT_KIND = WordList.new(:ident).
+      add(KEYWORDS, :keyword).
+      add(PREDEFINED_TYPES, :predefined_type).
+      add(PREDEFINED_VARIABLES, :local_variable).
+      add(DIRECTIVES, :directive).
+      add(PREDEFINED_CONSTANTS, :predefined_constant)  # :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
+              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(/ \# \s* if \s* 0 /x)
+            match << scan_until(/ ^\# (?:elif|else|endif) .*? $ | \z /xm) unless eos?
+            encoder.text_token match, :comment
+
+          elsif match = scan(/ [-+*=<>?:;,!&^|()\[\]{}~%]+ | \/=? | \.(?!\d) /x)
+            label_expected = match =~ /[;\{\}]/
+            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
+              match << matched
+            else
+              label_expected = false
+              if kind == :keyword
+                case match
+                when 'class'
+                  state = :class_name_expected
+                when 'case', 'default'
+                  case_expected = true
+                end
+              end
+            end
+            encoder.text_token match, kind
+
+          elsif match = scan(/\$/)
+            encoder.text_token match, :ident
+          
+          elsif match = scan(/L?"/)
+            encoder.begin_group :string
+            if match[0] == ?L
+              encoder.text_token match, 'L', :modifier
+              match = '"'
+            end
+            state = :string
+            encoder.text_token match, :delimiter
+
+          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} )? '? /ox)
+            label_expected = false
+            encoder.text_token match, :char
+
+          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+)(?![.eEfF])L?L?/)
+            label_expected = false
+            encoder.text_token match, :integer
+
+          elsif match = scan(/\d[fF]?|\d*\.\d+(?:[eE][+-]?\d+)?[fF]?|\d+[eE][+-]?\d+[fF]?/)
+            label_expected = false
+            encoder.text_token match, :float
+
+          else
+            encoder.text_token getch, :error
+
+          end
+
+        when :string
+          if match = scan(/[^\\"]+/)
+            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.end_group :string
+            encoder.text_token match, :error
+            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
+        
+        when :class_name_expected
+          if match = scan(/ [A-Za-z_][A-Za-z_0-9]* /x)
+            encoder.text_token match, :class
+            state = :initial
+
+          elsif match = scan(/\s+/)
+            encoder.text_token match, :space
+
+          else
+            encoder.text_token getch, :error
+            state = :initial
+
+          end
+          
+        else
+          raise_inspect 'Unknown state', encoder
+
+        end
+
+      end
+
+      if state == :string
+        encoder.end_group :string
+      end
+
+      encoder
+    end
+
+  end
+
+end
+end