pygments.rb 1.2.0 → 2.1.0

data/vendor/pygments-main/pygments/lexers/graphviz.py

@@ -0,0 +1,57 @@
+"""
+    pygments.lexers.graphviz
+    ~~~~~~~~~~~~~~~~~~~~~~~~
+
+    Lexer for the DOT language (graphviz).
+
+    :copyright: Copyright 2006-2021 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.lexer import RegexLexer, bygroups
+from pygments.token import Comment, Keyword, Operator, Name, String, Number, Punctuation, Whitespace
+
+
+__all__ = ['GraphvizLexer']
+
+
+class GraphvizLexer(RegexLexer):
+    """
+    For graphviz DOT graph description language.
+
+    .. versionadded:: 2.8
+    """
+    name = 'Graphviz'
+    aliases = ['graphviz', 'dot']
+    filenames = ['*.gv', '*.dot']
+    mimetypes = ['text/x-graphviz', 'text/vnd.graphviz']
+    tokens = {
+        'root': [
+            (r'\s+', Whitespace),
+            (r'(#|//).*?$', Comment.Single),
+            (r'/(\\\n)?[*](.|\n)*?[*](\\\n)?/', Comment.Multiline),
+            (r'(?i)(node|edge|graph|digraph|subgraph|strict)\b', Keyword),
+            (r'--|->', Operator),
+            (r'[{}[\]:;,]', Punctuation),
+            (r'(\b\D\w*)(\s*)(=)(\s*)',
+                bygroups(Name.Attribute, Whitespace, Punctuation, Whitespace),
+                'attr_id'),
+            (r'\b(n|ne|e|se|s|sw|w|nw|c|_)\b', Name.Builtin),
+            (r'\b\D\w*', Name.Tag), # node
+            (r'[-]?((\.[0-9]+)|([0-9]+(\.[0-9]*)?))', Number),
+            (r'"(\\"|[^"])*?"', Name.Tag), # quoted node
+            (r'<', Punctuation, 'xml'),
+        ],
+        'attr_id': [
+            (r'\b\D\w*', String, '#pop'),
+            (r'[-]?((\.[0-9]+)|([0-9]+(\.[0-9]*)?))', Number, '#pop'),
+            (r'"(\\"|[^"])*?"', String.Double, '#pop'),
+            (r'<', Punctuation, ('#pop', 'xml')),
+        ],
+        'xml': [
+            (r'<', Punctuation, '#push'),
+            (r'>', Punctuation, '#pop'),
+            (r'\s+', Whitespace),
+            (r'[^<>\s]', Name.Tag),
+        ]
+    }

data/vendor/pygments-main/pygments/lexers/haskell.py

@@ -1,23 +1,22 @@
-# -*- coding: utf-8 -*-
 """
     pygments.lexers.haskell
     ~~~~~~~~~~~~~~~~~~~~~~~
 
     Lexers for Haskell and related languages.
 
-    :copyright: Copyright 2006-2017 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2021 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
 import re
 
 from pygments.lexer import Lexer, RegexLexer, bygroups, do_insertions, \
-    default, include
+    default, include, inherit
 from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
     Number, Punctuation, Generic
 from pygments import unistring as uni
 
-__all__ = ['HaskellLexer', 'IdrisLexer', 'AgdaLexer', 'CryptolLexer',
+__all__ = ['HaskellLexer', 'HspecLexer', 'IdrisLexer', 'AgdaLexer', 'CryptolLexer',
            'LiterateHaskellLexer', 'LiterateIdrisLexer', 'LiterateAgdaLexer',
            'LiterateCryptolLexer', 'KokaLexer']
 
@@ -66,17 +65,22 @@ class HaskellLexer(RegexLexer):
             (r"(')[" + uni.Lu + r"][\w\']*", Keyword.Type),
             (r"(')\[[^\]]*\]", Keyword.Type),  # tuples and lists get special treatment in GHC
             (r"(')\([^)]*\)", Keyword.Type),  # ..
+            (r"(')[:!#$%&*+.\\/<=>?@^|~-]+", Keyword.Type),  # promoted type operators
             #  Operators
             (r'\\(?![:!#$%&*+.\\/<=>?@^|~-]+)', Name.Function),  # lambda operator
             (r'(<-|::|->|=>|=)(?![:!#$%&*+.\\/<=>?@^|~-]+)', Operator.Word),  # specials
             (r':[:!#$%&*+.\\/<=>?@^|~-]*', Keyword.Type),  # Constructor operators
             (r'[:!#$%&*+.\\/<=>?@^|~-]+', Operator),  # Other operators
             #  Numbers
-            (r'\d+[eE][+-]?\d+', Number.Float),
-            (r'\d+\.\d+([eE][+-]?\d+)?', Number.Float),
-            (r'0[oO][0-7]+', Number.Oct),
-            (r'0[xX][\da-fA-F]+', Number.Hex),
-            (r'\d+', Number.Integer),
+            (r'0[xX]_*[\da-fA-F](_*[\da-fA-F])*_*[pP][+-]?\d(_*\d)*', Number.Float),
+            (r'0[xX]_*[\da-fA-F](_*[\da-fA-F])*\.[\da-fA-F](_*[\da-fA-F])*'
+             r'(_*[pP][+-]?\d(_*\d)*)?', Number.Float),
+            (r'\d(_*\d)*_*[eE][+-]?\d(_*\d)*', Number.Float),
+            (r'\d(_*\d)*\.\d(_*\d)*(_*[eE][+-]?\d(_*\d)*)?', Number.Float),
+            (r'0[bB]_*[01](_*[01])*', Number.Bin),
+            (r'0[oO]_*[0-7](_*[0-7])*', Number.Oct),
+            (r'0[xX]_*[\da-fA-F](_*[\da-fA-F])*', Number.Hex),
+            (r'\d(_*\d)*', Number.Integer),
             #  Character/String Literals
             (r"'", String.Char, 'character'),
             (r'"', String, 'string'),
@@ -154,6 +158,28 @@ class HaskellLexer(RegexLexer):
     }
 
 
+class HspecLexer(HaskellLexer):
+    """
+    A Haskell lexer with support for Hspec constructs.
+
+    .. versionadded:: 2.4.0
+    """
+
+    name = 'Hspec'
+    aliases = ['hspec']
+    filenames = []
+    mimetypes = []
+
+    tokens = {
+        'root': [
+            (r'(it\s*)("[^"]*")', bygroups(Text, String.Doc)),
+            (r'(describe\s*)("[^"]*")', bygroups(Text, String.Doc)),
+            (r'(context\s*)("[^"]*")', bygroups(Text, String.Doc)),
+            inherit,
+        ],
+    }
+
+
 class IdrisLexer(RegexLexer):
     """
     A lexer for the dependently typed programming language Idris.
@@ -171,6 +197,7 @@ class IdrisLexer(RegexLexer):
                 'if', 'in', 'infix[lr]?', 'instance', 'rewrite', 'auto',
                 'namespace', 'codata', 'mutual', 'private', 'public', 'abstract',
                 'total', 'partial',
+                'interface', 'implementation', 'export', 'covering', 'constructor',
                 'let', 'proof', 'of', 'then', 'static', 'where', '_', 'with',
                 'pattern',  'term',  'syntax', 'prefix',
                 'postulate', 'parameters', 'record', 'dsl', 'impossible', 'implicit',
@@ -187,7 +214,7 @@ class IdrisLexer(RegexLexer):
     tokens = {
         'root': [
             # Comments
-            (r'^(\s*)(%%%s)' % '|'.join(directives),
+            (r'^(\s*)(%%(%s))' % '|'.join(directives),
              bygroups(Text, Keyword.Reserved)),
             (r'(\s*)(--(?![!#$%&*+./<=>?@^|_~:\\]).*?)$', bygroups(Text, Comment.Single)),
             (r'(\s*)(\|{3}.*?)$', bygroups(Text, Comment.Single)),
@@ -299,10 +326,10 @@ class AgdaLexer(RegexLexer):
             #  Identifiers
             (r'\b(%s)(?!\')\b' % '|'.join(reserved), Keyword.Reserved),
             (r'(import|module)(\s+)', bygroups(Keyword.Reserved, Text), 'module'),
-            (r'\b(Set|Prop)\b', Keyword.Type),
+            (r'\b(Set|Prop)[\u2080-\u2089]*\b', Keyword.Type),
             #  Special Symbols
             (r'(\(|\)|\{|\})', Operator),
-            (u'(\\.{1,3}|\\||\u039B|\u2200|\u2192|:|=|->)', Operator.Word),
+            (r'(\.{1,3}|\||\u03BB|\u2200|\u2192|:|=|->)', Operator.Word),
             #  Numbers
             (r'\d+[eE][+-]?\d+', Number.Float),
             (r'\d+\.\d+([eE][+-]?\d+)?', Number.Float),
@@ -418,8 +445,8 @@ class CryptolLexer(RegexLexer):
             (r'[A-Z]\w*', Keyword.Type),
             (r'(_[\w\']+|[a-z][\w\']*)', Name.Function),
             # TODO: these don't match the comments in docs, remove.
-            #(r'--(?![!#$%&*+./<=>?@^|_~:\\]).*?$', Comment.Single),
-            #(r'{-', Comment.Multiline, 'comment'),
+            # (r'--(?![!#$%&*+./<=>?@^|_~:\\]).*?$', Comment.Single),
+            # (r'{-', Comment.Multiline, 'comment'),
             (r',', Punctuation),
             (r'[:!#$%&*+.\\/<=>?@^|~-]+', Operator),
             # (HACK, but it makes sense to push two instances, believe me)
@@ -455,10 +482,10 @@ class CryptolLexer(RegexLexer):
         ],
     }
 
-    EXTRA_KEYWORDS = set(('join', 'split', 'reverse', 'transpose', 'width',
-                          'length', 'tail', '<<', '>>', '<<<', '>>>', 'const',
-                          'reg', 'par', 'seq', 'ASSERT', 'undefined', 'error',
-                          'trace'))
+    EXTRA_KEYWORDS = {'join', 'split', 'reverse', 'transpose', 'width',
+                      'length', 'tail', '<<', '>>', '<<<', '>>>', 'const',
+                      'reg', 'par', 'seq', 'ASSERT', 'undefined', 'error',
+                      'trace'}
 
     def get_tokens_unprocessed(self, text):
         stack = ['root']
@@ -531,8 +558,7 @@ class LiterateLexer(Lexer):
                     latex += line
             insertions.append((len(code),
                                list(lxlexer.get_tokens_unprocessed(latex))))
-        for item in do_insertions(insertions, self.baselexer.get_tokens_unprocessed(code)):
-            yield item
+        yield from do_insertions(insertions, self.baselexer.get_tokens_unprocessed(code))
 
 
 class LiterateHaskellLexer(LiterateLexer):
@@ -677,10 +703,10 @@ class KokaLexer(RegexLexer):
     symbols = r'[$%&*+@!/\\^~=.:\-?|<>]+'
 
     # symbol boundary: an operator keyword should not be followed by any of these
-    sboundary = '(?!'+symbols+')'
+    sboundary = '(?!' + symbols + ')'
 
     # name boundary: a keyword should not be followed by any of these
-    boundary = '(?![\w/])'
+    boundary = r'(?![\w/])'
 
     # koka token abstractions
     tokenType = Name.Attribute

data/vendor/pygments-main/pygments/lexers/haxe.py

@@ -1,11 +1,10 @@
-# -*- coding: utf-8 -*-
 """
     pygments.lexers.haxe
     ~~~~~~~~~~~~~~~~~~~~
 
     Lexers for Haxe and related stuff.
 
-    :copyright: Copyright 2006-2017 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2021 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
@@ -43,7 +42,7 @@ class HaxeLexer(ExtendedRegexLexer):
     typeid = r'_*[A-Z]\w*'
 
     # combined ident and dollar and idtype
-    ident = r'(?:_*[a-z]\w*|_+[0-9]\w*|' + typeid + '|_+|\$\w+)'
+    ident = r'(?:_*[a-z]\w*|_+[0-9]\w*|' + typeid + r'|_+|\$\w+)'
 
     binop = (r'(?:%=|&=|\|=|\^=|\+=|\-=|\*=|/=|<<=|>\s*>\s*=|>\s*>\s*>\s*=|==|'
              r'!=|<=|>\s*=|&&|\|\||<<|>>>|>\s*>|\.\.\.|<|>|%|&|\||\^|\+|\*|'
@@ -182,7 +181,7 @@ class HaxeLexer(ExtendedRegexLexer):
             (r'[0-9]+[eE][+\-]?[0-9]+', Number.Float),
             (r'[0-9]+\.[0-9]*[eE][+\-]?[0-9]+', Number.Float),
             (r'[0-9]+\.[0-9]+', Number.Float),
-            (r'[0-9]+\.(?!' + ident + '|\.\.)', Number.Float),
+            (r'[0-9]+\.(?!' + ident + r'|\.\.)', Number.Float),
 
             # Int
             (r'0x[0-9a-fA-F]+', Number.Hex),
@@ -219,7 +218,7 @@ class HaxeLexer(ExtendedRegexLexer):
             (r'[0-9]+[eE][+\-]?[0-9]+', Number.Float, ('#pop', 'preproc-expr-chain')),
             (r'[0-9]+\.[0-9]*[eE][+\-]?[0-9]+', Number.Float, ('#pop', 'preproc-expr-chain')),
             (r'[0-9]+\.[0-9]+', Number.Float, ('#pop', 'preproc-expr-chain')),
-            (r'[0-9]+\.(?!' + ident + '|\.\.)', Number.Float, ('#pop', 'preproc-expr-chain')),
+            (r'[0-9]+\.(?!' + ident + r'|\.\.)', Number.Float, ('#pop', 'preproc-expr-chain')),
 
             # Int
             (r'0x[0-9a-fA-F]+', Number.Hex, ('#pop', 'preproc-expr-chain')),
@@ -456,7 +455,7 @@ class HaxeLexer(ExtendedRegexLexer):
             (r'[0-9]+[eE][+\-]?[0-9]+', Number.Float, ('#pop', 'expr-chain')),
             (r'[0-9]+\.[0-9]*[eE][+\-]?[0-9]+', Number.Float, ('#pop', 'expr-chain')),
             (r'[0-9]+\.[0-9]+', Number.Float, ('#pop', 'expr-chain')),
-            (r'[0-9]+\.(?!' + ident + '|\.\.)', Number.Float, ('#pop', 'expr-chain')),
+            (r'[0-9]+\.(?!' + ident + r'|\.\.)', Number.Float, ('#pop', 'expr-chain')),
 
             # Int
             (r'0x[0-9a-fA-F]+', Number.Hex, ('#pop', 'expr-chain')),
@@ -467,7 +466,7 @@ class HaxeLexer(ExtendedRegexLexer):
             (r'"', String.Double, ('#pop', 'expr-chain', 'string-double')),
 
             # EReg
-            (r'~/(\\\\|\\/|[^/\n])*/[gimsu]*', String.Regex, ('#pop', 'expr-chain')),
+            (r'~/(\\\\|\\[^\\]|[^/\\\n])*/[gimsu]*', String.Regex, ('#pop', 'expr-chain')),
 
             # Array
             (r'\[', Punctuation, ('#pop', 'expr-chain', 'array-decl')),
@@ -711,7 +710,7 @@ class HaxeLexer(ExtendedRegexLexer):
             (r'[0-9]+[eE][+\-]?[0-9]+', Number.Float, '#pop'),
             (r'[0-9]+\.[0-9]*[eE][+\-]?[0-9]+', Number.Float, '#pop'),
             (r'[0-9]+\.[0-9]+', Number.Float, '#pop'),
-            (r'[0-9]+\.(?!' + ident + '|\.\.)', Number.Float, '#pop'),
+            (r'[0-9]+\.(?!' + ident + r'|\.\.)', Number.Float, '#pop'),
 
             # Int
             (r'0x[0-9a-fA-F]+', Number.Hex, '#pop'),
@@ -722,7 +721,7 @@ class HaxeLexer(ExtendedRegexLexer):
             (r'"', String.Double, ('#pop', 'string-double')),
 
             # EReg
-            (r'~/(\\\\|\\/|[^/\n])*/[gim]*', String.Regex, '#pop'),
+            (r'~/(\\\\|\\[^\\]|[^/\\\n])*/[gim]*', String.Regex, '#pop'),
 
             # Array
             (r'\[', Operator, ('#pop', 'array-decl')),

data/vendor/pygments-main/pygments/lexers/hdl.py

@@ -1,11 +1,10 @@
-# -*- coding: utf-8 -*-
 """
     pygments.lexers.hdl
     ~~~~~~~~~~~~~~~~~~~
 
     Lexers for hardware descriptor languages.
 
-    :copyright: Copyright 2006-2017 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2021 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
@@ -13,7 +12,7 @@ import re
 
 from pygments.lexer import RegexLexer, bygroups, include, using, this, words
 from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
-    Number, Punctuation, Error
+    Number, Punctuation
 
 __all__ = ['VerilogLexer', 'SystemVerilogLexer', 'VhdlLexer']
 
@@ -51,7 +50,6 @@ class VerilogLexer(RegexLexer):
             (r'([0-9]+)|(\'o)[0-7]+', Number.Oct),
             (r'\'[01xz]', Number),
             (r'\d+[Ll]?', Number.Integer),
-            (r'\*/', Error),
             (r'[~!%^&*+=|?:<>/-]', Operator),
             (r'[()\[\],.;\']', Punctuation),
             (r'`[a-zA-Z_]\w*', Name.Constant),
@@ -105,11 +103,12 @@ class VerilogLexer(RegexLexer):
             (words((
                 'byte', 'shortint', 'int', 'longint', 'integer', 'time',
                 'bit', 'logic', 'reg', 'supply0', 'supply1', 'tri', 'triand',
-                'trior', 'tri0', 'tri1', 'trireg', 'uwire', 'wire', 'wand', 'wo'
+                'trior', 'tri0', 'tri1', 'trireg', 'uwire', 'wire', 'wand', 'wor'
                 'shortreal', 'real', 'realtime'), suffix=r'\b'),
              Keyword.Type),
             (r'[a-zA-Z_]\w*:(?!:)', Name.Label),
             (r'\$?[a-zA-Z_]\w*', Name),
+            (r'\\(\S+)', Name),
         ],
         'string': [
             (r'"', String, '#pop'),
@@ -131,14 +130,18 @@ class VerilogLexer(RegexLexer):
         ]
     }
 
-    def get_tokens_unprocessed(self, text):
-        for index, token, value in \
-                RegexLexer.get_tokens_unprocessed(self, text):
-            # Convention: mark all upper case names as constants
-            if token is Name:
-                if value.isupper():
-                    token = Name.Constant
-            yield index, token, value
+    def analyse_text(text):
+        """Verilog code will use one of reg/wire/assign for sure, and that
+        is not common elsewhere."""
+        result = 0
+        if 'reg' in text:
+            result += 0.1
+        if 'wire' in text:
+            result += 0.1
+        if 'assign' in text:
+            result += 0.1
+
+        return result
 
 
 class SystemVerilogLexer(RegexLexer):
@@ -170,91 +173,183 @@ class SystemVerilogLexer(RegexLexer):
             (r'[{}#@]', Punctuation),
             (r'L?"', String, 'string'),
             (r"L?'(\\.|\\[0-7]{1,3}|\\x[a-fA-F0-9]{1,2}|[^\\\'\n])'", String.Char),
+
             (r'(\d+\.\d*|\.\d+|\d+)[eE][+-]?\d+[lL]?', Number.Float),
             (r'(\d+\.\d*|\.\d+|\d+[fF])[fF]?', Number.Float),
-            (r'([0-9]+)|(\'h)[0-9a-fA-F]+', Number.Hex),
-            (r'([0-9]+)|(\'b)[01]+', Number.Bin),
-            (r'([0-9]+)|(\'d)[0-9]+', Number.Integer),
-            (r'([0-9]+)|(\'o)[0-7]+', Number.Oct),
-            (r'\'[01xz]', Number),
-            (r'\d+[Ll]?', Number.Integer),
-            (r'\*/', Error),
+
+            (r'([1-9][_0-9]*)?\s*\'[sS]?[bB]\s*[xXzZ?01][_xXzZ?01]*',
+             Number.Bin),
+            (r'([1-9][_0-9]*)?\s*\'[sS]?[oO]\s*[xXzZ?0-7][_xXzZ?0-7]*',
+             Number.Oct),
+            (r'([1-9][_0-9]*)?\s*\'[sS]?[dD]\s*[xXzZ?0-9][_xXzZ?0-9]*',
+             Number.Integer),
+            (r'([1-9][_0-9]*)?\s*\'[sS]?[hH]\s*[xXzZ?0-9a-fA-F][_xXzZ?0-9a-fA-F]*',
+             Number.Hex),
+
+            (r'\'[01xXzZ]', Number),
+            (r'[0-9][_0-9]*', Number.Integer),
+
             (r'[~!%^&*+=|?:<>/-]', Operator),
-            (r'[()\[\],.;\']', Punctuation),
+            (words(('inside', 'dist'), suffix=r'\b'), Operator.Word),
+
+            (r'[()\[\],.;\'$]', Punctuation),
             (r'`[a-zA-Z_]\w*', Name.Constant),
 
             (words((
-                'accept_on', 'alias', 'always', 'always_comb', 'always_ff', 'always_latch',
-                'and', 'assert', 'assign', 'assume', 'automatic', 'before', 'begin', 'bind', 'bins',
-                'binsof', 'bit', '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', 'int', 'integer', 'interface',
-                'intersect', 'join', 'join_any', 'join_none', 'large', 'let', 'liblist', 'library',
-                'local', 'localparam', 'logic', 'longint', 'macromodule', 'matches', 'medium',
-                'modport', 'module', 'nand', 'negedge', 'new', 'nexttime', 'nmos', 'nor', 'noshowcancelled',
-                'not', 'notif0', 'notif1', 'null', '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',
-                'string', 'strong', 'strong0', 'strong1', 'struct', 'super', 'supply0', 'supply1',
-                'sync_accept_on', 'sync_reject_on', 'table', 'tagged', 'task', 'this', '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',
-                'virtual', 'void', 'wait', 'wait_order', 'wand', 'weak', 'weak0', 'weak1', 'while',
-                'wildcard', 'wire', 'with', 'within', 'wor', 'xnor', 'xor'), suffix=r'\b'),
+                'accept_on', 'alias', 'always', 'always_comb', 'always_ff',
+                'always_latch', 'and', 'assert', 'assign', 'assume', 'automatic',
+                'before', 'begin', 'bind', 'bins', 'binsof', 'break', 'buf',
+                'bufif0', 'bufif1', 'case', 'casex', 'casez', 'cell',
+                'checker', 'clocking', 'cmos', 'config',
+                'constraint', 'context', 'continue', 'cover', 'covergroup',
+                'coverpoint', 'cross', 'deassign', 'default', 'defparam', 'design',
+                'disable', 'do', 'edge', 'else', 'end', 'endcase',
+                'endchecker', 'endclocking', 'endconfig', 'endfunction',
+                'endgenerate', 'endgroup', 'endinterface', 'endmodule', 'endpackage',
+                'endprimitive', 'endprogram', 'endproperty', 'endsequence',
+                'endspecify', 'endtable', 'endtask', 'enum', 'eventually',
+                'expect', 'export', 'extern', 'final', 'first_match',
+                'for', 'force', 'foreach', 'forever', 'fork', 'forkjoin', 'function',
+                'generate', 'genvar', 'global', 'highz0', 'highz1', 'if', 'iff',
+                'ifnone', 'ignore_bins', 'illegal_bins', 'implies', 'implements', 'import',
+                'incdir', 'include', 'initial', 'inout', 'input',
+                'instance', 'interconnect', 'interface', 'intersect', 'join',
+                'join_any', 'join_none', 'large', 'let', 'liblist', 'library',
+                'local', 'localparam', 'macromodule', 'matches',
+                'medium', 'modport', 'module', 'nand', 'negedge', 'nettype', 'new', 'nexttime',
+                'nmos', 'nor', 'noshowcancelled', 'not', 'notif0', 'notif1', 'null',
+                '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', 'ref',
+                'reject_on', 'release', 'repeat', 'restrict', 'return', 'rnmos',
+                'rpmos', 'rtran', 'rtranif0', 'rtranif1', 's_always', 's_eventually',
+                's_nexttime', 's_until', 's_until_with', 'scalared', 'sequence',
+                'showcancelled', 'small', 'soft', 'solve',
+                'specify', 'specparam', 'static', 'strong', 'strong0',
+                'strong1', 'struct', 'super', 'sync_accept_on',
+                'sync_reject_on', 'table', 'tagged', 'task', 'this', 'throughout',
+                'timeprecision', 'timeunit', 'tran', 'tranif0', 'tranif1',
+                'typedef', 'union', 'unique', 'unique0', 'until',
+                'until_with', 'untyped', 'use', 'vectored',
+                'virtual', 'wait', 'wait_order', 'weak', 'weak0',
+                'weak1', 'while', 'wildcard', 'with', 'within',
+                'xnor', 'xor'),
+                suffix=r'\b'),
              Keyword),
 
+            (r'(class)(\s+)([a-zA-Z_]\w*)',
+             bygroups(Keyword.Declaration, Text, Name.Class)),
+            (r'(extends)(\s+)([a-zA-Z_]\w*)',
+             bygroups(Keyword.Declaration, Text, Name.Class)),
+            (r'(endclass\b)(?:(\s*)(:)(\s*)([a-zA-Z_]\w*))?',
+             bygroups(Keyword.Declaration, Text, Punctuation, Text, Name.Class)),
+
             (words((
-                '`__FILE__', '`__LINE__', '`begin_keywords', '`celldefine', '`default_nettype',
-                '`define', '`else', '`elsif', '`end_keywords', '`endcelldefine', '`endif',
-                '`ifdef', '`ifndef', '`include', '`line', '`nounconnected_drive', '`pragma',
-                '`resetall', '`timescale', '`unconnected_drive', '`undef', '`undefineall'),
+                # Variable types
+                'bit', 'byte', 'chandle', 'const', 'event', 'int', 'integer',
+                'logic', 'longint', 'real', 'realtime', 'reg', 'shortint',
+                'shortreal', 'signed', 'string', 'time', 'type', 'unsigned',
+                'var', 'void',
+                # Net types
+                'supply0', 'supply1', 'tri', 'triand', 'trior', 'trireg',
+                'tri0', 'tri1', 'uwire', 'wand', 'wire', 'wor'),
+                suffix=r'\b'),
+             Keyword.Type),
+
+            (words((
+                '`__FILE__', '`__LINE__', '`begin_keywords', '`celldefine',
+                '`default_nettype', '`define', '`else', '`elsif', '`end_keywords',
+                '`endcelldefine', '`endif', '`ifdef', '`ifndef', '`include',
+                '`line', '`nounconnected_drive', '`pragma', '`resetall',
+                '`timescale', '`unconnected_drive', '`undef', '`undefineall'),
                 suffix=r'\b'),
              Comment.Preproc),
 
             (words((
-                '$display', '$displayb', '$displayh', '$displayo', '$dumpall', '$dumpfile',
-                '$dumpflush', '$dumplimit', '$dumpoff', '$dumpon', '$dumpports',
-                '$dumpportsall', '$dumpportsflush', '$dumpportslimit', '$dumpportsoff',
-                '$dumpportson', '$dumpvars', '$fclose', '$fdisplay', '$fdisplayb',
-                '$fdisplayh', '$fdisplayo', '$feof', '$ferror', '$fflush', '$fgetc',
-                '$fgets', '$finish', '$fmonitor', '$fmonitorb', '$fmonitorh', '$fmonitoro',
-                '$fopen', '$fread', '$fscanf', '$fseek', '$fstrobe', '$fstrobeb', '$fstrobeh',
-                '$fstrobeo', '$ftell', '$fwrite', '$fwriteb', '$fwriteh', '$fwriteo',
-                '$monitor', '$monitorb', '$monitorh', '$monitoro', '$monitoroff',
-                '$monitoron', '$plusargs', '$random', '$readmemb', '$readmemh', '$rewind',
-                '$sformat', '$sformatf', '$sscanf', '$strobe', '$strobeb', '$strobeh', '$strobeo',
-                '$swrite', '$swriteb', '$swriteh', '$swriteo', '$test', '$ungetc',
-                '$value$plusargs', '$write', '$writeb', '$writeh', '$writememb',
-                '$writememh', '$writeo'), suffix=r'\b'),
+                # Simulation control tasks (20.2)
+                '$exit', '$finish', '$stop',
+                # Simulation time functions (20.3)
+                '$realtime', '$stime', '$time',
+                # Timescale tasks (20.4)
+                '$printtimescale', '$timeformat',
+                # Conversion functions
+                '$bitstoreal', '$bitstoshortreal', '$cast', '$itor',
+                '$realtobits', '$rtoi', '$shortrealtobits', '$signed',
+                '$unsigned',
+                # Data query functions (20.6)
+                '$bits', '$isunbounded', '$typename',
+                # Array query functions (20.7)
+                '$dimensions', '$high', '$increment', '$left', '$low', '$right',
+                '$size', '$unpacked_dimensions',
+                # Math functions (20.8)
+                '$acos', '$acosh', '$asin', '$asinh', '$atan', '$atan2',
+                '$atanh', '$ceil', '$clog2', '$cos', '$cosh', '$exp', '$floor',
+                '$hypot', '$ln', '$log10', '$pow', '$sin', '$sinh', '$sqrt',
+                '$tan', '$tanh',
+                # Bit vector system functions (20.9)
+                '$countbits', '$countones', '$isunknown', '$onehot', '$onehot0',
+                # Severity tasks (20.10)
+                '$info', '$error', '$fatal', '$warning',
+                # Assertion control tasks (20.12)
+                '$assertcontrol', '$assertfailoff', '$assertfailon',
+                '$assertkill', '$assertnonvacuouson', '$assertoff', '$asserton',
+                '$assertpassoff', '$assertpasson', '$assertvacuousoff',
+                # Sampled value system functions (20.13)
+                '$changed', '$changed_gclk', '$changing_gclk', '$falling_gclk',
+                '$fell', '$fell_gclk', '$future_gclk', '$past', '$past_gclk',
+                '$rising_gclk', '$rose', '$rose_gclk', '$sampled', '$stable',
+                '$stable_gclk', '$steady_gclk',
+                # Coverage control functions (20.14)
+                '$coverage_control', '$coverage_get', '$coverage_get_max',
+                '$coverage_merge', '$coverage_save', '$get_coverage',
+                '$load_coverage_db', '$set_coverage_db_name',
+                # Probabilistic distribution functions (20.15)
+                '$dist_chi_square', '$dist_erlang', '$dist_exponential',
+                '$dist_normal', '$dist_poisson', '$dist_t', '$dist_uniform',
+                '$random',
+                # Stochastic analysis tasks and functions (20.16)
+                '$q_add', '$q_exam', '$q_full', '$q_initialize', '$q_remove',
+                # PLA modeling tasks (20.17)
+                '$async$and$array', '$async$and$plane', '$async$nand$array',
+                '$async$nand$plane', '$async$nor$array', '$async$nor$plane',
+                '$async$or$array', '$async$or$plane', '$sync$and$array',
+                '$sync$and$plane', '$sync$nand$array', '$sync$nand$plane',
+                '$sync$nor$array', '$sync$nor$plane', '$sync$or$array',
+                '$sync$or$plane',
+                # Miscellaneous tasks and functions (20.18)
+                '$system',
+                # Display tasks (21.2)
+                '$display', '$displayb', '$displayh', '$displayo', '$monitor',
+                '$monitorb', '$monitorh', '$monitoro', '$monitoroff',
+                '$monitoron', '$strobe', '$strobeb', '$strobeh', '$strobeo',
+                '$write', '$writeb', '$writeh', '$writeo',
+                # File I/O tasks and functions (21.3)
+                '$fclose', '$fdisplay', '$fdisplayb', '$fdisplayh',
+                '$fdisplayo', '$feof', '$ferror', '$fflush', '$fgetc', '$fgets',
+                '$fmonitor', '$fmonitorb', '$fmonitorh', '$fmonitoro', '$fopen',
+                '$fread', '$fscanf', '$fseek', '$fstrobe', '$fstrobeb',
+                '$fstrobeh', '$fstrobeo', '$ftell', '$fwrite', '$fwriteb',
+                '$fwriteh', '$fwriteo', '$rewind', '$sformat', '$sformatf',
+                '$sscanf', '$swrite', '$swriteb', '$swriteh', '$swriteo',
+                '$ungetc',
+                # Memory load tasks (21.4)
+                '$readmemb', '$readmemh',
+                # Memory dump tasks (21.5)
+                '$writememb', '$writememh',
+                # Command line input (21.6)
+                '$test$plusargs', '$value$plusargs',
+                # VCD tasks (21.7)
+                '$dumpall', '$dumpfile', '$dumpflush', '$dumplimit', '$dumpoff',
+                '$dumpon', '$dumpports', '$dumpportsall', '$dumpportsflush',
+                '$dumpportslimit', '$dumpportsoff', '$dumpportson', '$dumpvars',
+                ), suffix=r'\b'),
              Name.Builtin),
 
-            (r'(class)(\s+)', bygroups(Keyword, Text), 'classname'),
-            (words((
-                'byte', 'shortint', 'int', 'longint', 'integer', 'time',
-                'bit', 'logic', 'reg', 'supply0', 'supply1', 'tri', 'triand',
-                'trior', 'tri0', 'tri1', 'trireg', 'uwire', 'wire', 'wand', 'wo'
-                'shortreal', 'real', 'realtime'), suffix=r'\b'),
-             Keyword.Type),
             (r'[a-zA-Z_]\w*:(?!:)', Name.Label),
             (r'\$?[a-zA-Z_]\w*', Name),
-        ],
-        'classname': [
-            (r'[a-zA-Z_]\w*', Name.Class, '#pop'),
+            (r'\\(\S+)', Name),
         ],
         'string': [
             (r'"', String, '#pop'),
@@ -276,15 +371,6 @@ class SystemVerilogLexer(RegexLexer):
         ]
     }
 
-    def get_tokens_unprocessed(self, text):
-        for index, token, value in \
-                RegexLexer.get_tokens_unprocessed(self, text):
-            # Convention: mark all upper case names as constants
-            if token is Name:
-                if value.isupper():
-                    token = Name.Constant
-            yield index, token, value
-
 
 class VhdlLexer(RegexLexer):
     """