pygments.rb 0.6.3 → 1.0.0

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

@@ -0,0 +1,333 @@
+# -*- coding: utf-8 -*-
+"""
+    pygments.lexers.julia
+    ~~~~~~~~~~~~~~~~~~~~~
+
+    Lexers for the Julia language.
+
+    :copyright: Copyright 2006-2015 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import re
+
+from pygments.lexer import Lexer, RegexLexer, bygroups, do_insertions, \
+    words, include
+from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
+    Number, Punctuation, Generic
+from pygments.util import shebang_matches, unirange
+
+__all__ = ['JuliaLexer', 'JuliaConsoleLexer']
+
+allowed_variable = (
+    u'(?:[a-zA-Z_\u00A1-\uffff]|%s)(?:[a-zA-Z_0-9\u00A1-\uffff]|%s)*!*' %
+    ((unirange(0x10000, 0x10ffff),) * 2))
+
+
+class JuliaLexer(RegexLexer):
+    """
+    For `Julia <http://julialang.org/>`_ source code.
+
+    .. versionadded:: 1.6
+    """
+
+    name = 'Julia'
+    aliases = ['julia', 'jl']
+    filenames = ['*.jl']
+    mimetypes = ['text/x-julia', 'application/x-julia']
+
+    flags = re.MULTILINE | re.UNICODE
+
+    tokens = {
+        'root': [
+            (r'\n', Text),
+            (r'[^\S\n]+', Text),
+            (r'#=', Comment.Multiline, "blockcomment"),
+            (r'#.*$', Comment),
+            (r'[\[\]{}(),;]', Punctuation),
+
+            # keywords
+            (r'in\b', Keyword.Pseudo),
+            (r'(true|false)\b', Keyword.Constant),
+            (r'(local|global|const)\b', Keyword.Declaration),
+            (words([
+                'function', 'type', 'typealias', 'abstract', 'immutable',
+                'baremodule', 'begin', 'bitstype', 'break', 'catch', 'ccall',
+                'continue', 'do', 'else', 'elseif', 'end', 'export', 'finally',
+                'for', 'if', 'import', 'importall', 'let', 'macro', 'module',
+                'quote', 'return', 'try', 'using', 'while'],
+                suffix=r'\b'), Keyword),
+
+            # NOTE
+            # Patterns below work only for definition sites and thus hardly reliable.
+            #
+            # functions
+            # (r'(function)(\s+)(' + allowed_variable + ')',
+            #  bygroups(Keyword, Text, Name.Function)),
+            #
+            # types
+            # (r'(type|typealias|abstract|immutable)(\s+)(' + allowed_variable + ')',
+            #  bygroups(Keyword, Text, Name.Class)),
+
+            # type names
+            (words([
+                'ANY', 'ASCIIString', 'AbstractArray', 'AbstractChannel',
+                'AbstractFloat', 'AbstractMatrix', 'AbstractRNG',
+                'AbstractSparseArray', 'AbstractSparseMatrix',
+                'AbstractSparseVector', 'AbstractString', 'AbstractVecOrMat',
+                'AbstractVector', 'Any', 'ArgumentError', 'Array',
+                'AssertionError', 'Associative', 'Base64DecodePipe',
+                'Base64EncodePipe', 'Bidiagonal', 'BigFloat', 'BigInt',
+                'BitArray', 'BitMatrix', 'BitVector', 'Bool', 'BoundsError',
+                'Box', 'BufferStream', 'CapturedException', 'CartesianIndex',
+                'CartesianRange', 'Cchar', 'Cdouble', 'Cfloat', 'Channel',
+                'Char', 'Cint', 'Cintmax_t', 'Clong', 'Clonglong',
+                'ClusterManager', 'Cmd', 'Coff_t', 'Colon', 'Complex',
+                'Complex128', 'Complex32', 'Complex64', 'CompositeException',
+                'Condition', 'Cptrdiff_t', 'Cshort', 'Csize_t', 'Cssize_t',
+                'Cstring', 'Cuchar', 'Cuint', 'Cuintmax_t', 'Culong',
+                'Culonglong', 'Cushort', 'Cwchar_t', 'Cwstring', 'DataType',
+                'Date', 'DateTime', 'DenseArray', 'DenseMatrix',
+                'DenseVecOrMat', 'DenseVector', 'Diagonal', 'Dict',
+                'DimensionMismatch', 'Dims', 'DirectIndexString', 'Display',
+                'DivideError', 'DomainError', 'EOFError', 'EachLine', 'Enum',
+                'Enumerate', 'ErrorException', 'Exception', 'Expr',
+                'Factorization', 'FileMonitor', 'FileOffset', 'Filter',
+                'Float16', 'Float32', 'Float64', 'FloatRange', 'Function',
+                'GenSym', 'GlobalRef', 'GotoNode', 'HTML', 'Hermitian', 'IO',
+                'IOBuffer', 'IOStream', 'IPv4', 'IPv6', 'InexactError',
+                'InitError', 'Int', 'Int128', 'Int16', 'Int32', 'Int64', 'Int8',
+                'IntSet', 'Integer', 'InterruptException', 'IntrinsicFunction',
+                'InvalidStateException', 'Irrational', 'KeyError', 'LabelNode',
+                'LambdaStaticData', 'LinSpace', 'LineNumberNode', 'LoadError',
+                'LocalProcess', 'LowerTriangular', 'MIME', 'Matrix',
+                'MersenneTwister', 'Method', 'MethodError', 'MethodTable',
+                'Module', 'NTuple', 'NewvarNode', 'NullException', 'Nullable',
+                'Number', 'ObjectIdDict', 'OrdinalRange', 'OutOfMemoryError',
+                'OverflowError', 'Pair', 'ParseError', 'PartialQuickSort',
+                'Pipe', 'PollingFileWatcher', 'ProcessExitedException',
+                'ProcessGroup', 'Ptr', 'QuoteNode', 'RandomDevice', 'Range',
+                'Rational', 'RawFD', 'ReadOnlyMemoryError', 'Real',
+                'ReentrantLock', 'Ref', 'Regex', 'RegexMatch',
+                'RemoteException', 'RemoteRef', 'RepString', 'RevString',
+                'RopeString', 'RoundingMode', 'SegmentationFault',
+                'SerializationState', 'Set', 'SharedArray', 'SharedMatrix',
+                'SharedVector', 'Signed', 'SimpleVector', 'SparseMatrixCSC',
+                'StackOverflowError', 'StatStruct', 'StepRange', 'StridedArray',
+                'StridedMatrix', 'StridedVecOrMat', 'StridedVector', 'SubArray',
+                'SubString', 'SymTridiagonal', 'Symbol', 'SymbolNode',
+                'Symmetric', 'SystemError', 'TCPSocket', 'Task', 'Text',
+                'TextDisplay', 'Timer', 'TopNode', 'Tridiagonal', 'Tuple',
+                'Type', 'TypeConstructor', 'TypeError', 'TypeName', 'TypeVar',
+                'UDPSocket', 'UInt', 'UInt128', 'UInt16', 'UInt32', 'UInt64',
+                'UInt8', 'UTF16String', 'UTF32String', 'UTF8String',
+                'UndefRefError', 'UndefVarError', 'UnicodeError', 'UniformScaling',
+                'Union', 'UnitRange', 'Unsigned', 'UpperTriangular', 'Val',
+                'Vararg', 'VecOrMat', 'Vector', 'VersionNumber', 'Void', 'WString',
+                'WeakKeyDict', 'WeakRef', 'WorkerConfig', 'Zip'], suffix=r'\b'),
+                Keyword.Type),
+
+            # builtins
+            (words([
+                u'ARGS', u'CPU_CORES', u'C_NULL', u'DevNull', u'ENDIAN_BOM',
+                u'ENV', u'I', u'Inf', u'Inf16', u'Inf32', u'Inf64',
+                u'InsertionSort', u'JULIA_HOME', u'LOAD_PATH', u'MergeSort',
+                u'NaN', u'NaN16', u'NaN32', u'NaN64', u'OS_NAME',
+                u'QuickSort', u'RoundDown', u'RoundFromZero', u'RoundNearest',
+                u'RoundNearestTiesAway', u'RoundNearestTiesUp',
+                u'RoundToZero', u'RoundUp', u'STDERR', u'STDIN', u'STDOUT',
+                u'VERSION', u'WORD_SIZE', u'catalan', u'e', u'eu',
+                u'eulergamma', u'golden', u'im', u'nothing', u'pi', u'γ',
+                u'π', u'φ'],
+                suffix=r'\b'), Name.Builtin),
+
+            # operators
+            # see: https://github.com/JuliaLang/julia/blob/master/src/julia-parser.scm
+            (words([
+                # prec-assignment
+                u'=', u':=', u'+=', u'-=', u'*=', u'/=', u'//=', u'.//=', u'.*=', u'./=',
+                u'\=', u'.\=', u'^=', u'.^=', u'÷=', u'.÷=', u'%=', u'.%=', u'|=', u'&=',
+                u'$=', u'=>', u'<<=', u'>>=', u'>>>=', u'~', u'.+=', u'.-=',
+                # prec-conditional
+                u'?',
+                # prec-arrow
+                u'--', u'-->',
+                # prec-lazy-or
+                u'||',
+                # prec-lazy-and
+                u'&&',
+                # prec-comparison
+                u'>', u'<', u'>=', u'≥', u'<=', u'≤', u'==', u'===', u'≡', u'!=', u'≠',
+                u'!==', u'≢', u'.>', u'.<', u'.>=', u'.≥', u'.<=', u'.≤', u'.==', u'.!=',
+                u'.≠', u'.=', u'.!', u'<:', u'>:', u'∈', u'∉', u'∋', u'∌', u'⊆',
+                u'⊈', u'⊂',
+                u'⊄', u'⊊',
+                # prec-pipe
+                u'|>', u'<|',
+                # prec-colon
+                u':',
+                # prec-plus
+                u'+', u'-', u'.+', u'.-', u'|', u'∪', u'$',
+                # prec-bitshift
+                u'<<', u'>>', u'>>>', u'.<<', u'.>>', u'.>>>',
+                # prec-times
+                u'*', u'/', u'./', u'÷', u'.÷', u'%', u'⋅', u'.%', u'.*', u'\\', u'.\\', u'&', u'∩',
+                # prec-rational
+                u'//', u'.//',
+                # prec-power
+                u'^', u'.^',
+                # prec-decl
+                u'::',
+                # prec-dot
+                u'.',
+                # unary op
+                u'+', u'-', u'!', u'~', u'√', u'∛', u'∜'
+            ]), Operator),
+
+            # chars
+            (r"'(\\.|\\[0-7]{1,3}|\\x[a-fA-F0-9]{1,3}|\\u[a-fA-F0-9]{1,4}|"
+             r"\\U[a-fA-F0-9]{1,6}|[^\\\'\n])'", String.Char),
+
+            # try to match trailing transpose
+            (r'(?<=[.\w)\]])\'+', Operator),
+
+            # strings
+            (r'"""', String, 'tqstring'),
+            (r'"', String, 'string'),
+
+            # regular expressions
+            (r'r"""', String.Regex, 'tqregex'),
+            (r'r"', String.Regex, 'regex'),
+
+            # backticks
+            (r'`', String.Backtick, 'command'),
+
+            # names
+            (allowed_variable, Name),
+            (r'@' + allowed_variable, Name.Decorator),
+
+            # numbers
+            (r'(\d+(_\d+)+\.\d*|\d*\.\d+(_\d+)+)([eEf][+-]?[0-9]+)?', Number.Float),
+            (r'(\d+\.\d*|\d*\.\d+)([eEf][+-]?[0-9]+)?', Number.Float),
+            (r'\d+(_\d+)+[eEf][+-]?[0-9]+', Number.Float),
+            (r'\d+[eEf][+-]?[0-9]+', Number.Float),
+            (r'0b[01]+(_[01]+)+', Number.Bin),
+            (r'0b[01]+', Number.Bin),
+            (r'0o[0-7]+(_[0-7]+)+', Number.Oct),
+            (r'0o[0-7]+', Number.Oct),
+            (r'0x[a-fA-F0-9]+(_[a-fA-F0-9]+)+', Number.Hex),
+            (r'0x[a-fA-F0-9]+', Number.Hex),
+            (r'\d+(_\d+)+', Number.Integer),
+            (r'\d+', Number.Integer)
+        ],
+
+        "blockcomment": [
+            (r'[^=#]', Comment.Multiline),
+            (r'#=', Comment.Multiline, '#push'),
+            (r'=#', Comment.Multiline, '#pop'),
+            (r'[=#]', Comment.Multiline),
+        ],
+
+        'string': [
+            (r'"', String, '#pop'),
+            # FIXME: This escape pattern is not perfect.
+            (r'\\([\\"\'\$nrbtfav]|(x|u|U)[a-fA-F0-9]+|\d+)', String.Escape),
+            # Interpolation is defined as "$" followed by the shortest full
+            # expression, which is something we can't parse.
+            # Include the most common cases here: $word, and $(paren'd expr).
+            (r'\$' + allowed_variable, String.Interpol),
+            # (r'\$[a-zA-Z_]+', String.Interpol),
+            (r'(\$)(\()', bygroups(String.Interpol, Punctuation), 'in-intp'),
+            # @printf and @sprintf formats
+            (r'%[-#0 +]*([0-9]+|[*])?(\.([0-9]+|[*]))?[hlL]?[E-GXc-giorsux%]',
+             String.Interpol),
+            (r'.|\s', String),
+        ],
+
+        'tqstring': [
+            (r'"""', String, '#pop'),
+            (r'\\([\\"\'\$nrbtfav]|(x|u|U)[a-fA-F0-9]+|\d+)', String.Escape),
+            (r'\$' + allowed_variable, String.Interpol),
+            (r'(\$)(\()', bygroups(String.Interpol, Punctuation), 'in-intp'),
+            (r'.|\s', String),
+        ],
+
+        'regex': [
+            (r'"', String.Regex, '#pop'),
+            (r'\\"', String.Regex),
+            (r'.|\s', String.Regex),
+        ],
+
+        'tqregex': [
+            (r'"""', String.Regex, '#pop'),
+            (r'.|\s', String.Regex),
+        ],
+
+        'command': [
+            (r'`', String.Backtick, '#pop'),
+            (r'\$' + allowed_variable, String.Interpol),
+            (r'(\$)(\()', bygroups(String.Interpol, Punctuation), 'in-intp'),
+            (r'.|\s', String.Backtick)
+        ],
+
+        'in-intp': [
+            (r'\(', Punctuation, '#push'),
+            (r'\)', Punctuation, '#pop'),
+            include('root'),
+        ]
+    }
+
+    def analyse_text(text):
+        return shebang_matches(text, r'julia')
+
+
+class JuliaConsoleLexer(Lexer):
+    """
+    For Julia console sessions. Modeled after MatlabSessionLexer.
+
+    .. versionadded:: 1.6
+    """
+    name = 'Julia console'
+    aliases = ['jlcon']
+
+    def get_tokens_unprocessed(self, text):
+        jllexer = JuliaLexer(**self.options)
+        start = 0
+        curcode = ''
+        insertions = []
+        output = False
+        error = False
+
+        for line in text.splitlines(True):
+            if line.startswith('julia>'):
+                insertions.append((len(curcode), [(0, Generic.Prompt, line[:6])]))
+                curcode += line[6:]
+                output = False
+                error = False
+            elif line.startswith('help?>') or line.startswith('shell>'):
+                yield start, Generic.Prompt, line[:6]
+                yield start + 6, Text, line[6:]
+                output = False
+                error = False
+            elif line.startswith('      ') and not output:
+                insertions.append((len(curcode), [(0, Text, line[:6])]))
+                curcode += line[6:]
+            else:
+                if curcode:
+                    for item in do_insertions(
+                            insertions, jllexer.get_tokens_unprocessed(curcode)):
+                        yield item
+                    curcode = ''
+                    insertions = []
+                if line.startswith('ERROR: ') or error:
+                    yield start, Generic.Error, line
+                    error = True
+                else:
+                    yield start, Generic.Output, line
+                output = True
+            start += len(line)
+
+        if curcode:
+            for item in do_insertions(
+                    insertions, jllexer.get_tokens_unprocessed(curcode)):
+                yield item

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

@@ -5,19 +5,19 @@
 
     Pygments lexers for JVM languages.
 
-    :copyright: Copyright 2006-2014 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2015 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
 import re
 
 from pygments.lexer import Lexer, RegexLexer, include, bygroups, using, \
-     this, combined, default
+    this, combined, default, words
 from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
-     Number, Punctuation
+    Number, Punctuation
+from pygments.util import shebang_matches
 from pygments import unistring as uni
 
-
 __all__ = ['JavaLexer', 'ScalaLexer', 'GosuLexer', 'GosuTemplateLexer',
            'GroovyLexer', 'IokeLexer', 'ClojureLexer', 'ClojureScriptLexer',
            'KotlinLexer', 'XtendLexer', 'AspectJLexer', 'CeylonLexer',
@@ -41,37 +41,50 @@ class JavaLexer(RegexLexer):
             (r'[^\S\n]+', Text),
             (r'//.*?\n', Comment.Single),
             (r'/\*.*?\*/', Comment.Multiline),
-            # method names
-            (r'((?:(?:[^\W\d]|\$)[\w\.\[\]\$<>]*\s+)+?)' # return arguments
-             r'((?:[^\W\d]|\$)[\w\$]*)'                  # method name
-             r'(\s*)(\()',                               # signature start
-             bygroups(using(this), Name.Function, Text, Operator)),
-            (r'@[^\W\d][\w\.]*', Name.Decorator),
+            # keywords: go before method names to avoid lexing "throw new XYZ"
+            # as a method signature
             (r'(assert|break|case|catch|continue|default|do|else|finally|for|'
              r'if|goto|instanceof|new|return|switch|this|throw|try|while)\b',
              Keyword),
+            # method names
+            (r'((?:(?:[^\W\d]|\$)[\w.\[\]$<>]*\s+)+?)'  # return arguments
+             r'((?:[^\W\d]|\$)[\w$]*)'                  # method name
+             r'(\s*)(\()',                              # signature start
+             bygroups(using(this), Name.Function, Text, Operator)),
+            (r'@[^\W\d][\w.]*', Name.Decorator),
             (r'(abstract|const|enum|extends|final|implements|native|private|'
              r'protected|public|static|strictfp|super|synchronized|throws|'
              r'transient|volatile)\b', Keyword.Declaration),
             (r'(boolean|byte|char|double|float|int|long|short|void)\b',
              Keyword.Type),
-            (r'(package)(\s+)', bygroups(Keyword.Namespace, Text)),
+            (r'(package)(\s+)', bygroups(Keyword.Namespace, Text), 'import'),
             (r'(true|false|null)\b', Keyword.Constant),
-            (r'(class|interface)(\s+)', bygroups(Keyword.Declaration, Text), 'class'),
-            (r'(import)(\s+)', bygroups(Keyword.Namespace, Text), 'import'),
+            (r'(class|interface)(\s+)', bygroups(Keyword.Declaration, Text),
+             'class'),
+            (r'(import(?:\s+static)?)(\s+)', bygroups(Keyword.Namespace, Text),
+             'import'),
             (r'"(\\\\|\\"|[^"])*"', String),
             (r"'\\.'|'[^\\]'|'\\u[0-9a-fA-F]{4}'", String.Char),
-            (r'(\.)((?:[^\W\d]|\$)[\w\$]*)', bygroups(Operator, Name.Attribute)),
-            (r'([^\W\d]|\$)[\w\$]*:', Name.Label),
-            (r'([^\W\d]|\$)[\w\$]*', Name),
-            (r'[~\^\*!%&\[\]\(\)\{\}<>\|+=:;,./?-]', Operator),
-            (r'[0-9][0-9]*\.[0-9]+([eE][0-9]+)?[fd]?', Number.Float),
-            (r'0x[0-9a-fA-F]+', Number.Hex),
-            (r'[0-9]+(_+[0-9]+)*L?', Number.Integer),
+            (r'(\.)((?:[^\W\d]|\$)[\w$]*)', bygroups(Operator, Name.Attribute)),
+            (r'^\s*([^\W\d]|\$)[\w$]*:', Name.Label),
+            (r'([^\W\d]|\$)[\w$]*', Name),
+            (r'([0-9][0-9_]*\.([0-9][0-9_]*)?|'
+             r'\.[0-9][0-9_]*)'
+             r'([eE][+\-]?[0-9][0-9_]*)?[fFdD]?|'
+             r'[0-9][eE][+\-]?[0-9][0-9_]*[fFdD]?|'
+             r'[0-9]([eE][+\-]?[0-9][0-9_]*)?[fFdD]|'
+             r'0[xX]([0-9a-fA-F][0-9a-fA-F_]*\.?|'
+             r'([0-9a-fA-F][0-9a-fA-F_]*)?\.[0-9a-fA-F][0-9a-fA-F_]*)'
+             r'[pP][+\-]?[0-9][0-9_]*[fFdD]?', Number.Float),
+            (r'0[xX][0-9a-fA-F][0-9a-fA-F_]*[lL]?', Number.Hex),
+            (r'0[bB][01][01_]*[lL]?', Number.Bin),
+            (r'0[0-7_]+[lL]?', Number.Oct),
+            (r'0|[1-9][0-9_]*[lL]?', Number.Integer),
+            (r'[~^*!%&\[\](){}<>|+=:;,./?-]', Operator),
             (r'\n', Text)
         ],
         'class': [
-            (r'([^\W\d]|\$)[\w\$]*', Name.Class, '#pop')
+            (r'([^\W\d]|\$)[\w$]*', Name.Class, '#pop')
         ],
         'import': [
             (r'[\w.]+\*?', Name.Namespace, '#pop')
@@ -91,7 +104,7 @@ class AspectJLexer(JavaLexer):
     filenames = ['*.aj']
     mimetypes = ['text/x-aspectj']
 
-    aj_keywords = [
+    aj_keywords = set((
         'aspect', 'pointcut', 'privileged', 'call', 'execution',
         'initialization', 'preinitialization', 'handler', 'get', 'set',
         'staticinitialization', 'target', 'args', 'within', 'withincode',
@@ -101,9 +114,9 @@ class AspectJLexer(JavaLexer):
         'thisJoinPointStaticPart', 'thisEnclosingJoinPointStaticPart',
         'issingleton', 'perthis', 'pertarget', 'percflow', 'percflowbelow',
         'pertypewithin', 'lock', 'unlock', 'thisAspectInstance'
-    ]
-    aj_inter_type = ['parents:', 'warning:', 'error:', 'soft:', 'precedence:']
-    aj_inter_type_annotation = ['@type', '@method', '@constructor', '@field']
+    ))
+    aj_inter_type = set(('parents:', 'warning:', 'error:', 'soft:', 'precedence:'))
+    aj_inter_type_annotation = set(('@type', '@method', '@constructor', '@field'))
 
     def get_tokens_unprocessed(self, text):
         for index, token, value in JavaLexer.get_tokens_unprocessed(self, text):
@@ -244,12 +257,12 @@ class ScalaLexer(RegexLexer):
              u'\ua77d-\ua77e\ua780\ua782\ua784\ua786\ua78b\uff21-\uff3a]')
 
     idrest = u'%s(?:%s|[0-9])*(?:(?<=_)%s)?' % (letter, letter, op)
+    letter_letter_digit = u'%s(?:%s|\d)*' % (letter, letter)
 
     tokens = {
         'root': [
             # method names
             (r'(class|trait|object)(\s+)', bygroups(Keyword, Text), 'class'),
-            (u"'%s" % idrest, Text.Symbol),
             (r'[^\S\n]+', Text),
             (r'//.*?\n', Comment.Single),
             (r'/\*', Comment.Multiline, 'comment'),
@@ -268,12 +281,16 @@ class ScalaLexer(RegexLexer):
             (r'""".*?"""(?!")', String),
             (r'"(\\\\|\\"|[^"])*"', String),
             (r"'\\.'|'[^\\]'|'\\u[0-9a-fA-F]{4}'", String.Char),
-#            (ur'(\.)(%s|%s|`[^`]+`)' % (idrest, op), bygroups(Operator,
-#             Name.Attribute)),
+            (u"'%s" % idrest, Text.Symbol),
+            (r'[fs]"""', String, 'interptriplestring'),  # interpolated strings
+            (r'[fs]"', String, 'interpstring'),  # interpolated strings
+            (r'raw"(\\\\|\\"|[^"])*"', String),  # raw strings
+            # (ur'(\.)(%s|%s|`[^`]+`)' % (idrest, op), bygroups(Operator,
+            # Name.Attribute)),
             (idrest, Name),
             (r'`[^`]+`', Name),
             (r'\[', Operator, 'typeparam'),
-            (r'[\(\)\{\};,.#]', Operator),
+            (r'[(){};,.#]', Operator),
             (op, Operator),
             (r'([0-9][0-9]*\.[0-9]*|\.[0-9]+)([eE][+-]?[0-9]+)?[fFdD]?',
              Number.Float),
@@ -285,16 +302,16 @@ class ScalaLexer(RegexLexer):
             (u'(%s|%s|`[^`]+`)(\\s*)(\\[)' % (idrest, op),
              bygroups(Name.Class, Text, Operator), 'typeparam'),
             (r'\s+', Text),
-            (r'{', Operator, '#pop'),
+            (r'\{', Operator, '#pop'),
             (r'\(', Operator, '#pop'),
             (r'//.*?\n', Comment.Single, '#pop'),
             (u'%s|%s|`[^`]+`' % (idrest, op), Name.Class, '#pop'),
         ],
         'type': [
             (r'\s+', Text),
-            (u'<[%:]|>:|[#_\u21D2]|forSome|type', Keyword),
-            (r'([,\);}]|=>|=)(\s*)', bygroups(Operator, Text), '#pop'),
-            (r'[\(\{]', Operator, '#push'),
+            (r'<[%:]|>:|[#_]|forSome|type', Keyword),
+            (u'([,);}]|=>|=|\u21d2)(\\s*)', bygroups(Operator, Text), '#pop'),
+            (r'[({]', Operator, '#push'),
             (u'((?:%s|%s|`[^`]+`)(?:\\.(?:%s|%s|`[^`]+`))*)(\\s*)(\\[)' %
              (idrest, op, idrest, op),
              bygroups(Keyword.Type, Text, Operator), ('#pop', 'typeparam')),
@@ -307,12 +324,12 @@ class ScalaLexer(RegexLexer):
         'typeparam': [
             (r'[\s,]+', Text),
             (u'<[%:]|=>|>:|[#_\u21D2]|forSome|type', Keyword),
-            (r'([\]\)\}])', Operator, '#pop'),
-            (r'[\(\[\{]', Operator, '#push'),
+            (r'([\])}])', Operator, '#pop'),
+            (r'[(\[{]', Operator, '#push'),
             (u'\\.|%s|%s|`[^`]+`' % (idrest, op), Keyword.Type)
         ],
         'comment': [
-            (r'[^/\*]+', Comment.Multiline),
+            (r'[^/*]+', Comment.Multiline),
             (r'/\*', Comment.Multiline, '#push'),
             (r'\*/', Comment.Multiline, '#pop'),
             (r'[*/]', Comment.Multiline)
@@ -320,6 +337,27 @@ class ScalaLexer(RegexLexer):
         'import': [
             (u'(%s|\\.)+' % idrest, Name.Namespace, '#pop')
         ],
+        'interpstringcommon': [
+            (r'[^"$\\]+', String),
+            (r'\$\$', String),
+            (r'\$' + letter_letter_digit, String.Interpol),
+            (r'\$\{', String.Interpol, 'interpbrace'),
+            (r'\\.', String),
+        ],
+        'interptriplestring': [
+            (r'"""(?!")', String, '#pop'),
+            (r'"', String),
+            include('interpstringcommon'),
+        ],
+        'interpstring': [
+            (r'"', String, '#pop'),
+            include('interpstringcommon'),
+        ],
+        'interpbrace': [
+            (r'\}', String.Interpol, '#pop'),
+            (r'\{', String.Interpol, '#push'),
+            include('root'),
+        ],
     }
 
 
@@ -340,14 +378,14 @@ class GosuLexer(RegexLexer):
     tokens = {
         'root': [
             # method names
-            (r'^(\s*(?:[a-zA-Z_][\w\.\[\]]*\s+)+?)' # modifiers etc.
-             r'([a-zA-Z_]\w*)'                      # method name
-             r'(\s*)(\()',                          # signature start
+            (r'^(\s*(?:[a-zA-Z_][\w.\[\]]*\s+)+?)'  # modifiers etc.
+             r'([a-zA-Z_]\w*)'                       # method name
+             r'(\s*)(\()',                           # signature start
              bygroups(using(this), Name.Function, Text, Operator)),
             (r'[^\S\n]+', Text),
             (r'//.*?\n', Comment.Single),
             (r'/\*.*?\*/', Comment.Multiline),
-            (r'@[a-zA-Z_][\w\.]*', Name.Decorator),
+            (r'@[a-zA-Z_][\w.]*', Name.Decorator),
             (r'(in|as|typeof|statictypeof|typeis|typeas|if|else|foreach|for|'
              r'index|while|do|continue|break|return|try|catch|finally|this|'
              r'throw|new|switch|case|default|eval|super|outer|classpath|'
@@ -365,39 +403,39 @@ class GosuLexer(RegexLexer):
             (r'(uses)(\s+)([\w.]+\*?)',
              bygroups(Keyword.Namespace, Text, Name.Namespace)),
             (r'"', String, 'string'),
-            (r'(\??[\.#])([a-zA-Z_]\w*)',
+            (r'(\??[.#])([a-zA-Z_]\w*)',
              bygroups(Operator, Name.Attribute)),
             (r'(:)([a-zA-Z_]\w*)',
              bygroups(Operator, Name.Attribute)),
-            (r'[a-zA-Z_\$]\w*', Name),
-            (r'and|or|not|[\\~\^\*!%&\[\]\(\)\{\}<>\|+=:;,./?-]', Operator),
+            (r'[a-zA-Z_$]\w*', Name),
+            (r'and|or|not|[\\~^*!%&\[\](){}<>|+=:;,./?-]', Operator),
             (r'[0-9][0-9]*\.[0-9]+([eE][0-9]+)?[fd]?', Number.Float),
             (r'[0-9]+', Number.Integer),
             (r'\n', Text)
         ],
         'templateText': [
-          (r'(\\<)|(\\\$)', String),
-          (r'(<%@\s+)(extends|params)',
-           bygroups(Operator, Name.Decorator), 'stringTemplate'),
-          (r'<%!--.*?--%>', Comment.Multiline),
-          (r'(<%)|(<%=)', Operator, 'stringTemplate'),
-          (r'\$\{', Operator, 'stringTemplateShorthand'),
-          (r'.', String)
+            (r'(\\<)|(\\\$)', String),
+            (r'(<%@\s+)(extends|params)',
+             bygroups(Operator, Name.Decorator), 'stringTemplate'),
+            (r'<%!--.*?--%>', Comment.Multiline),
+            (r'(<%)|(<%=)', Operator, 'stringTemplate'),
+            (r'\$\{', Operator, 'stringTemplateShorthand'),
+            (r'.', String)
         ],
         'string': [
-          (r'"', String, '#pop'),
-          include('templateText')
+            (r'"', String, '#pop'),
+            include('templateText')
         ],
         'stringTemplate': [
-          (r'"', String, 'string'),
-          (r'%>', Operator, '#pop'),
-          include('root')
+            (r'"', String, 'string'),
+            (r'%>', Operator, '#pop'),
+            include('root')
         ],
         'stringTemplateShorthand': [
-          (r'"', String, 'string'),
-          (r'\{', Operator, 'stringTemplateShorthand'),
-          (r'\}', Operator, '#pop'),
-          include('root')
+            (r'"', String, 'string'),
+            (r'\{', Operator, 'stringTemplateShorthand'),
+            (r'\}', Operator, '#pop'),
+            include('root')
         ],
     }
 
@@ -413,11 +451,11 @@ class GosuTemplateLexer(Lexer):
     aliases = ['gst']
     filenames = ['*.gst']
     mimetypes = ['text/x-gosu-template']
-    lexer = GosuLexer()
 
     def get_tokens_unprocessed(self, text):
+        lexer = GosuLexer()
         stack = ['templateText']
-        for item in self.lexer.get_tokens_unprocessed(text, stack):
+        for item in lexer.get_tokens_unprocessed(text, stack):
             yield item
 
 
@@ -430,7 +468,7 @@ class GroovyLexer(RegexLexer):
 
     name = 'Groovy'
     aliases = ['groovy']
-    filenames = ['*.groovy']
+    filenames = ['*.groovy','*.gradle']
     mimetypes = ['text/x-groovy']
 
     flags = re.MULTILINE | re.DOTALL
@@ -443,14 +481,14 @@ class GroovyLexer(RegexLexer):
         ],
         'base': [
             # method names
-            (r'^(\s*(?:[a-zA-Z_][\w\.\[\]]*\s+)+?)' # return arguments
+            (r'^(\s*(?:[a-zA-Z_][\w.\[\]]*\s+)+?)'  # return arguments
              r'([a-zA-Z_]\w*)'                      # method name
              r'(\s*)(\()',                          # signature start
              bygroups(using(this), Name.Function, Text, Operator)),
             (r'[^\S\n]+', Text),
             (r'//.*?\n', Comment.Single),
             (r'/\*.*?\*/', Comment.Multiline),
-            (r'@[a-zA-Z_][\w\.]*', Name.Decorator),
+            (r'@[a-zA-Z_][\w.]*', Name.Decorator),
             (r'(assert|break|case|catch|continue|default|do|else|finally|for|'
              r'if|goto|instanceof|new|return|switch|this|throw|try|while|in|as)\b',
              Keyword),
@@ -464,6 +502,8 @@ class GroovyLexer(RegexLexer):
             (r'(class|interface)(\s+)', bygroups(Keyword.Declaration, Text),
              'class'),
             (r'(import)(\s+)', bygroups(Keyword.Namespace, Text), 'import'),
+            (r'""".*?"""', String.Double),
+            (r"'''.*?'''", String.Single),
             (r'"(\\\\|\\"|[^"])*"', String.Double),
             (r"'(\\\\|\\'|[^'])*'", String.Single),
             (r'\$/((?!/\$).)*/\$', String),
@@ -471,8 +511,8 @@ class GroovyLexer(RegexLexer):
             (r"'\\.'|'[^\\]'|'\\u[0-9a-fA-F]{4}'", String.Char),
             (r'(\.)([a-zA-Z_]\w*)', bygroups(Operator, Name.Attribute)),
             (r'[a-zA-Z_]\w*:', Name.Label),
-            (r'[a-zA-Z_\$]\w*', Name),
-            (r'[~\^\*!%&\[\]\(\)\{\}<>\|+=:;,./?-]', Operator),
+            (r'[a-zA-Z_$]\w*', Name),
+            (r'[~^*!%&\[\](){}<>|+=:;,./?-]', Operator),
             (r'[0-9][0-9]*\.[0-9]+([eE][0-9]+)?[fd]?', Number.Float),
             (r'0x[0-9a-fA-F]+', Number.Hex),
             (r'[0-9]+L?', Number.Integer),
@@ -505,45 +545,45 @@ class IokeLexer(RegexLexer):
         'interpolatableText': [
             (r'(\\b|\\e|\\t|\\n|\\f|\\r|\\"|\\\\|\\#|\\\Z|\\u[0-9a-fA-F]{1,4}'
              r'|\\[0-3]?[0-7]?[0-7])', String.Escape),
-            (r'#{', Punctuation, 'textInterpolationRoot')
-            ],
+            (r'#\{', Punctuation, 'textInterpolationRoot')
+        ],
 
         'text': [
             (r'(?<!\\)"', String, '#pop'),
             include('interpolatableText'),
             (r'[^"]', String)
-            ],
+        ],
 
         'documentation': [
             (r'(?<!\\)"', String.Doc, '#pop'),
             include('interpolatableText'),
             (r'[^"]', String.Doc)
-            ],
+        ],
 
         'textInterpolationRoot': [
-            (r'}', Punctuation, '#pop'),
+            (r'\}', Punctuation, '#pop'),
             include('root')
-            ],
+        ],
 
         'slashRegexp': [
-            (r'(?<!\\)/[oxpniums]*', String.Regex, '#pop'),
+            (r'(?<!\\)/[im-psux]*', String.Regex, '#pop'),
             include('interpolatableText'),
             (r'\\/', String.Regex),
             (r'[^/]', String.Regex)
-            ],
+        ],
 
         'squareRegexp': [
-            (r'(?<!\\)][oxpniums]*', String.Regex, '#pop'),
+            (r'(?<!\\)][im-psux]*', String.Regex, '#pop'),
             include('interpolatableText'),
             (r'\\]', String.Regex),
             (r'[^\]]', String.Regex)
-            ],
+        ],
 
         'squareText': [
             (r'(?<!\\)]', String, '#pop'),
             include('interpolatableText'),
             (r'[^\]]', String)
-            ],
+        ],
 
         'root': [
             (r'\n', Text),
@@ -553,86 +593,86 @@ class IokeLexer(RegexLexer):
             (r';(.*?)\n', Comment),
             (r'\A#!(.*?)\n', Comment),
 
-            #Regexps
+            # Regexps
             (r'#/', String.Regex, 'slashRegexp'),
             (r'#r\[', String.Regex, 'squareRegexp'),
 
-            #Symbols
+            # Symbols
             (r':[\w!:?]+', String.Symbol),
             (r'[\w!:?]+:(?![\w!?])', String.Other),
             (r':"(\\\\|\\"|[^"])*"', String.Symbol),
 
-            #Documentation
+            # Documentation
             (r'((?<=fn\()|(?<=fnx\()|(?<=method\()|(?<=macro\()|(?<=lecro\()'
              r'|(?<=syntax\()|(?<=dmacro\()|(?<=dlecro\()|(?<=dlecrox\()'
              r'|(?<=dsyntax\())\s*"', String.Doc, 'documentation'),
 
-            #Text
+            # Text
             (r'"', String, 'text'),
             (r'#\[', String, 'squareText'),
 
-            #Mimic
-            (r'\w[a-zA-Z0-9!?_:]+(?=\s*=.*mimic\s)', Name.Entity),
+            # Mimic
+            (r'\w[\w!:?]+(?=\s*=.*mimic\s)', Name.Entity),
 
-            #Assignment
+            # Assignment
             (r'[a-zA-Z_][\w!:?]*(?=[\s]*[+*/-]?=[^=].*($|\.))',
              Name.Variable),
 
             # keywords
             (r'(break|cond|continue|do|ensure|for|for:dict|for:set|if|let|'
              r'loop|p:for|p:for:dict|p:for:set|return|unless|until|while|'
-             r'with)(?![a-zA-Z0-9!:_?])', Keyword.Reserved),
+             r'with)(?![\w!:?])', Keyword.Reserved),
 
             # Origin
-            (r'(eval|mimic|print|println)(?![a-zA-Z0-9!:_?])', Keyword),
+            (r'(eval|mimic|print|println)(?![\w!:?])', Keyword),
 
             # Base
             (r'(cell\?|cellNames|cellOwner\?|cellOwner|cells|cell|'
              r'documentation|hash|identity|mimic|removeCell\!|undefineCell\!)'
-             r'(?![a-zA-Z0-9!:_?])', Keyword),
+             r'(?![\w!:?])', Keyword),
 
             # Ground
-            (r'(stackTraceAsText)(?![a-zA-Z0-9!:_?])', Keyword),
+            (r'(stackTraceAsText)(?![\w!:?])', Keyword),
 
-            #DefaultBehaviour Literals
-            (r'(dict|list|message|set)(?![a-zA-Z0-9!:_?])', Keyword.Reserved),
+            # DefaultBehaviour Literals
+            (r'(dict|list|message|set)(?![\w!:?])', Keyword.Reserved),
 
-            #DefaultBehaviour Case
+            # DefaultBehaviour Case
             (r'(case|case:and|case:else|case:nand|case:nor|case:not|case:or|'
-             r'case:otherwise|case:xor)(?![a-zA-Z0-9!:_?])', Keyword.Reserved),
+             r'case:otherwise|case:xor)(?![\w!:?])', Keyword.Reserved),
 
-            #DefaultBehaviour Reflection
+            # DefaultBehaviour Reflection
             (r'(asText|become\!|derive|freeze\!|frozen\?|in\?|is\?|kind\?|'
              r'mimic\!|mimics|mimics\?|prependMimic\!|removeAllMimics\!|'
              r'removeMimic\!|same\?|send|thaw\!|uniqueHexId)'
-             r'(?![a-zA-Z0-9!:_?])', Keyword),
+             r'(?![\w!:?])', Keyword),
 
-            #DefaultBehaviour Aspects
-            (r'(after|around|before)(?![a-zA-Z0-9!:_?])', Keyword.Reserved),
+            # DefaultBehaviour Aspects
+            (r'(after|around|before)(?![\w!:?])', Keyword.Reserved),
 
             # DefaultBehaviour
             (r'(kind|cellDescriptionDict|cellSummary|genSym|inspect|notice)'
-             r'(?![a-zA-Z0-9!:_?])', Keyword),
+             r'(?![\w!:?])', Keyword),
             (r'(use|destructuring)', Keyword.Reserved),
 
-            #DefaultBehavior BaseBehavior
+            # DefaultBehavior BaseBehavior
             (r'(cell\?|cellOwner\?|cellOwner|cellNames|cells|cell|'
              r'documentation|identity|removeCell!|undefineCell)'
-             r'(?![a-zA-Z0-9!:_?])', Keyword),
+             r'(?![\w!:?])', Keyword),
 
-            #DefaultBehavior Internal
+            # DefaultBehavior Internal
             (r'(internal:compositeRegexp|internal:concatenateText|'
              r'internal:createDecimal|internal:createNumber|'
              r'internal:createRegexp|internal:createText)'
-             r'(?![a-zA-Z0-9!:_?])', Keyword.Reserved),
+             r'(?![\w!:?])', Keyword.Reserved),
 
-            #DefaultBehaviour Conditions
+            # DefaultBehaviour Conditions
             (r'(availableRestarts|bind|error\!|findRestart|handle|'
              r'invokeRestart|rescue|restart|signal\!|warn\!)'
-             r'(?![a-zA-Z0-9!:_?])', Keyword.Reserved),
+             r'(?![\w!:?])', Keyword.Reserved),
 
             # constants
-            (r'(nil|false|true)(?![a-zA-Z0-9!:_?])', Name.Constant),
+            (r'(nil|false|true)(?![\w!:?])', Name.Constant),
 
             # names
             (r'(Arity|Base|Call|Condition|DateTime|Aspects|Pointcut|'
@@ -644,12 +684,12 @@ class IokeLexer(RegexLexer):
              r'LexicalBlock|LexicalMacro|List|Message|Method|Mixins|'
              r'NativeMethod|Number|Origin|Pair|Range|Reflector|Regexp Match|'
              r'Regexp|Rescue|Restart|Runtime|Sequence|Set|Symbol|'
-             r'System|Text|Tuple)(?![a-zA-Z0-9!:_?])', Name.Builtin),
+             r'System|Text|Tuple)(?![\w!:?])', Name.Builtin),
 
             # functions
             (u'(generateMatchMethod|aliasMethod|\u03bb|\u028E|fnx|fn|method|'
              u'dmacro|dlecro|syntax|macro|dlecrox|lecrox|lecro|syntax)'
-             u'(?![a-zA-Z0-9!:_?])', Name.Function),
+             u'(?![\w!:?])', Name.Function),
 
             # Numbers
             (r'-?0[xX][0-9a-fA-F]+', Number.Hex),
@@ -658,7 +698,7 @@ class IokeLexer(RegexLexer):
 
             (r'#\(', Punctuation),
 
-             # Operators
+            # Operators
             (r'(&&>>|\|\|>>|\*\*>>|:::|::|\.\.\.|===|\*\*>|\*\*=|&&>|&&=|'
              r'\|\|>|\|\|=|\->>|\+>>|!>>|<>>>|<>>|&>>|%>>|#>>|@>>|/>>|\*>>|'
              r'\?>>|\|>>|\^>>|~>>|\$>>|=>>|<<=|>>=|<=>|<\->|=~|!~|=>|\+\+|'
@@ -670,12 +710,12 @@ class IokeLexer(RegexLexer):
              Operator),
 
             # Punctuation
-            (r'(\`\`|\`|\'\'|\'|\.|\,|@@|@|\[|\]|\(|\)|{|})', Punctuation),
+            (r'(\`\`|\`|\'\'|\'|\.|\,|@@|@|\[|\]|\(|\)|\{|\})', Punctuation),
 
-            #kinds
+            # kinds
             (r'[A-Z][\w!:?]*', Name.Class),
 
-            #default cellnames
+            # default cellnames
             (r'[a-z_][\w!:?]*', Name)
         ]
     }
@@ -692,19 +732,19 @@ class ClojureLexer(RegexLexer):
     filenames = ['*.clj']
     mimetypes = ['text/x-clojure', 'application/x-clojure']
 
-    special_forms = [
+    special_forms = (
         '.', 'def', 'do', 'fn', 'if', 'let', 'new', 'quote', 'var', 'loop'
-    ]
+    )
 
     # It's safe to consider 'ns' a declaration thing because it defines a new
     # namespace.
-    declarations = [
+    declarations = (
         'def-', 'defn', 'defn-', 'defmacro', 'defmulti', 'defmethod',
         'defstruct', 'defonce', 'declare', 'definline', 'definterface',
         'defprotocol', 'defrecord', 'deftype', 'defproject', 'ns'
-    ]
+    )
 
-    builtins = [
+    builtins = (
         '*', '+', '-', '->', '/', '<', '<=', '=', '==', '>', '>=', '..',
         'accessor', 'agent', 'agent-errors', 'aget', 'alength', 'all-ns',
         'alter', 'and', 'append-child', 'apply', 'array-map', 'aset',
@@ -753,7 +793,7 @@ class ClojureLexer(RegexLexer):
         'val', 'vals', 'var-get', 'var-set', 'var?', 'vector', 'vector-zip',
         'vector?', 'when', 'when-first', 'when-let', 'when-not',
         'with-local-vars', 'with-meta', 'with-open', 'with-out-str',
-        'xml-seq', 'xml-zip', 'zero?', 'zipmap', 'zipper']
+        'xml-seq', 'xml-zip', 'zero?', 'zipmap', 'zipper')
 
     # valid names for identifiers
     # well, names can only not consist fully of numbers
@@ -763,9 +803,6 @@ class ClojureLexer(RegexLexer):
     # but that's hard, so just pretend / is part of the name
     valid_name = r'(?!#)[\w!$%*+<=>?/.#-]+'
 
-    def _multi_escape(entries):
-        return '(%s)' % ('|'.join(re.escape(entry) + ' ' for entry in entries))
-
     tokens = {
         'root': [
             # the comments - always starting with semicolon
@@ -792,17 +829,17 @@ class ClojureLexer(RegexLexer):
             (r'~@|[`\'#^~&@]', Operator),
 
             # highlight the special forms
-            (_multi_escape(special_forms), Keyword),
+            (words(special_forms, suffix=' '), Keyword),
 
             # Technically, only the special forms are 'keywords'. The problem
             # is that only treating them as keywords means that things like
             # 'defn' and 'ns' need to be highlighted as builtins. This is ugly
             # and weird for most styles. So, as a compromise we're going to
             # highlight them as Keyword.Declarations.
-            (_multi_escape(declarations), Keyword.Declaration),
+            (words(declarations, suffix=' '), Keyword.Declaration),
 
             # highlight the builtins
-            (_multi_escape(builtins), Name.Builtin),
+            (words(builtins, suffix=' '), Name.Builtin),
 
             # the remaining functions
             (r'(?<=\()' + valid_name, Name.Function),
@@ -848,9 +885,9 @@ class TeaLangLexer(RegexLexer):
     tokens = {
         'root': [
             # method names
-            (r'^(\s*(?:[a-zA-Z_][\w\.\[\]]*\s+)+?)' # return arguments
-             r'([a-zA-Z_]\w*)'                      # method name
-             r'(\s*)(\()',                          # signature start
+            (r'^(\s*(?:[a-zA-Z_][\w\.\[\]]*\s+)+?)'  # return arguments
+             r'([a-zA-Z_]\w*)'                       # method name
+             r'(\s*)(\()',                           # signature start
              bygroups(using(this), Name.Function, Text, Operator)),
             (r'[^\S\n]+', Text),
             (r'//.*?\n', Comment.Single),
@@ -902,24 +939,24 @@ class CeylonLexer(RegexLexer):
     tokens = {
         'root': [
             # method names
-            (r'^(\s*(?:[a-zA-Z_][\w\.\[\]]*\s+)+?)' # return arguments
+            (r'^(\s*(?:[a-zA-Z_][\w.\[\]]*\s+)+?)'  # return arguments
              r'([a-zA-Z_]\w*)'                      # method name
              r'(\s*)(\()',                          # signature start
              bygroups(using(this), Name.Function, Text, Operator)),
             (r'[^\S\n]+', Text),
             (r'//.*?\n', Comment.Single),
             (r'/\*', Comment.Multiline, 'comment'),
-            (r'(variable|shared|abstract|doc|by|formal|actual|late|native)',
-             Name.Decorator),
-            (r'(break|case|catch|continue|default|else|finally|for|in|'
-             r'variable|if|return|switch|this|throw|try|while|is|exists|dynamic|'
-             r'nonempty|then|outer|assert)\b', Keyword),
-            (r'(abstracts|extends|satisfies|adapts|'
-             r'super|given|of|out|assign|'
-             r'transient|volatile)\b', Keyword.Declaration),
-            (r'(function|value|void)\b',
+            (r'(shared|abstract|formal|default|actual|variable|deprecated|small|'
+             r'late|literal|doc|by|see|throws|optional|license|tagged|final|native|'
+             r'annotation|sealed)\b', Name.Decorator),
+            (r'(break|case|catch|continue|else|finally|for|in|'
+             r'if|return|switch|this|throw|try|while|is|exists|dynamic|'
+             r'nonempty|then|outer|assert|let)\b', Keyword),
+            (r'(abstracts|extends|satisfies|'
+             r'super|given|of|out|assign)\b', Keyword.Declaration),
+            (r'(function|value|void|new)\b',
              Keyword.Type),
-            (r'(package)(\s+)', bygroups(Keyword.Namespace, Text)),
+            (r'(assembly|module|package)(\s+)', bygroups(Keyword.Namespace, Text)),
             (r'(true|false|null)\b', Keyword.Constant),
             (r'(class|interface|object|alias)(\s+)',
              bygroups(Keyword.Declaration, Text), 'class'),
@@ -931,7 +968,7 @@ class CeylonLexer(RegexLexer):
              bygroups(Operator, Name.Attribute)),
             (r'[a-zA-Z_]\w*:', Name.Label),
             (r'[a-zA-Z_]\w*', Name),
-            (r'[~\^\*!%&\[\]\(\)\{\}<>\|+=:;,./?-]', Operator),
+            (r'[~^*!%&\[\](){}<>|+=:;,./?-]', Operator),
             (r'\d{1,3}(_\d{3})+\.\d{1,3}(_\d{3})+[kMGTPmunpf]?', Number.Float),
             (r'\d{1,3}(_\d{3})+\.[0-9]+([eE][+-]?[0-9]+)?[kMGTPmunpf]?',
              Number.Float),
@@ -964,7 +1001,7 @@ class CeylonLexer(RegexLexer):
 
 class KotlinLexer(RegexLexer):
     """
-    For `Kotlin <http://kotlin.jetbrains.org/>`_
+    For `Kotlin <http://kotlinlang.org/>`_
     source code.
 
     .. versionadded:: 1.5
@@ -977,16 +1014,16 @@ class KotlinLexer(RegexLexer):
 
     flags = re.MULTILINE | re.DOTALL | re.UNICODE
 
-    kt_name = ('@?[_' + uni.Lu + uni.Ll + uni.Lt + uni.Lm + uni.Nl + ']' +
-               '[' + uni.Lu + uni.Ll + uni.Lt + uni.Lm + uni.Nl + uni.Nd +
-               uni.Pc + uni.Cf + uni.Mn + uni.Mc + ']*')
+    kt_name = ('@?[_' + uni.combine('Lu', 'Ll', 'Lt', 'Lm', 'Nl') + ']' +
+               '[' + uni.combine('Lu', 'Ll', 'Lt', 'Lm', 'Nl', 'Nd', 'Pc', 'Cf',
+                                 'Mn', 'Mc') + ']*')
     kt_id = '(' + kt_name + '|`' + kt_name + '`)'
 
     tokens = {
         'root': [
             (r'^\s*\[.*?\]', Name.Attribute),
             (r'[^\S\n]+', Text),
-            (r'\\\n', Text), # line continuation
+            (r'\\\n', Text),  # line continuation
             (r'//.*?\n', Comment.Single),
             (r'/[*].*?[*]/', Comment.Multiline),
             (r'\n', Text),
@@ -999,15 +1036,17 @@ class KotlinLexer(RegexLexer):
             (r"[0-9](\.[0-9]*)?([eE][+-][0-9]+)?[flFL]?|"
              r"0[xX][0-9a-fA-F]+[Ll]?", Number),
             (r'(class)(\s+)(object)', bygroups(Keyword, Text, Keyword)),
-            (r'(class|trait|object)(\s+)', bygroups(Keyword, Text), 'class'),
+            (r'(class|interface|object)(\s+)', bygroups(Keyword, Text), 'class'),
             (r'(package|import)(\s+)', bygroups(Keyword, Text), 'package'),
             (r'(val|var)(\s+)', bygroups(Keyword, Text), 'property'),
             (r'(fun)(\s+)', bygroups(Keyword, Text), 'function'),
-            (r'(abstract|annotation|as|break|by|catch|class|continue|do|else|'
-             r'enum|false|final|finally|for|fun|get|if|import|in|inner|'
-             r'internal|is|null|object|open|out|override|package|private|'
-             r'protected|public|reified|return|set|super|this|throw|trait|'
-             r'true|try|type|val|var|vararg|when|where|while|This)\b', Keyword),
+            (r'(abstract|annotation|as|break|by|catch|class|companion|const|'
+             r'constructor|continue|crossinline|data|do|dynamic|else|enum|'
+             r'external|false|final|finally|for|fun|get|if|import|in|infix|'
+             r'inline|inner|interface|internal|is|lateinit|noinline|null|'
+             r'object|open|operator|out|override|package|private|protected|'
+             r'public|reified|return|sealed|set|super|tailrec|this|throw|'
+             r'true|try|val|var|vararg|when|where|while)\b', Keyword),
             (kt_id, Name),
         ],
         'package': [
@@ -1042,14 +1081,14 @@ class XtendLexer(RegexLexer):
     tokens = {
         'root': [
             # method names
-            (r'^(\s*(?:[a-zA-Z_][\w\.\[\]]*\s+)+?)' # return arguments
+            (r'^(\s*(?:[a-zA-Z_][\w.\[\]]*\s+)+?)'  # return arguments
              r'([a-zA-Z_$][\w$]*)'                  # method name
              r'(\s*)(\()',                          # signature start
              bygroups(using(this), Name.Function, Text, Operator)),
             (r'[^\S\n]+', Text),
             (r'//.*?\n', Comment.Single),
             (r'/\*.*?\*/', Comment.Multiline),
-            (r'@[a-zA-Z_][\w\.]*', Name.Decorator),
+            (r'@[a-zA-Z_][\w.]*', Name.Decorator),
             (r'(assert|break|case|catch|continue|default|do|else|finally|for|'
              r'if|goto|instanceof|new|return|switch|this|throw|try|while|IF|'
              r'ELSE|ELSEIF|ENDIF|FOR|ENDFOR|SEPARATOR|BEFORE|AFTER)\b',
@@ -1069,8 +1108,8 @@ class XtendLexer(RegexLexer):
             (r'"(\\\\|\\"|[^"])*"', String),
             (r"'(\\\\|\\'|[^'])*'", String),
             (r'[a-zA-Z_]\w*:', Name.Label),
-            (r'[a-zA-Z_\$]\w*', Name),
-            (r'[~\^\*!%&\[\]\(\)\{\}<>\|+=:;,./?-]', Operator),
+            (r'[a-zA-Z_$]\w*', Name),
+            (r'[~^*!%&\[\](){}<>\|+=:;,./?-]', Operator),
             (r'[0-9][0-9]*\.[0-9]+([eE][0-9]+)?[fd]?', Number.Float),
             (r'0x[0-9a-fA-F]+', Number.Hex),
             (r'[0-9]+L?', Number.Integer),
@@ -1089,6 +1128,7 @@ class XtendLexer(RegexLexer):
         ],
     }
 
+
 class PigLexer(RegexLexer):
     """
     For `Pig Latin <https://pig.apache.org/>`_ source code.
@@ -1116,15 +1156,15 @@ class PigLexer(RegexLexer):
             include('builtins'),
             include('punct'),
             include('operators'),
-            (r'[0-9]*\.[0-9]+([eE][0-9]+)?[fd]?', Number.Float),
+            (r'[0-9]*\.[0-9]+(e[0-9]+)?[fd]?', Number.Float),
             (r'0x[0-9a-f]+', Number.Hex),
             (r'[0-9]+L?', Number.Integer),
             (r'\n', Text),
             (r'([a-z_]\w*)(\s*)(\()',
              bygroups(Name.Function, Text, Punctuation)),
             (r'[()#:]', Text),
-            (r'[^(:#\'\")\s]+', Text),
-            (r'\S+\s+', Text) # TODO: make tests pass without \s+
+            (r'[^(:#\'")\s]+', Text),
+            (r'\S+\s+', Text)   # TODO: make tests pass without \s+
         ],
         'keywords': [
             (r'(assert|and|any|all|arrange|as|asc|bag|by|cache|CASE|cat|cd|cp|'
@@ -1219,6 +1259,7 @@ class GoloLexer(RegexLexer):
             (r'-?\d[\d_]*', Number.Integer),
 
             ('`?[a-zA-Z_][\w$]*', Name),
+            (r'@[a-zA-Z_][\w$.]*', Name.Decorator),
 
             (r'"""', String, combined('stringescape', 'triplestring')),
             (r'"', String, combined('stringescape', 'doublestring')),
@@ -1244,7 +1285,7 @@ class GoloLexer(RegexLexer):
             (r'[\'"\\]', String)
         ],
         'stringescape': [
-            (r'\\([\\abfnrtv"\']|\n|N{.*?}|u[a-fA-F0-9]{4}|'
+            (r'\\([\\abfnrtv"\']|\n|N\{.*?\}|u[a-fA-F0-9]{4}|'
              r'U[a-fA-F0-9]{8}|x[a-fA-F0-9]{2}|[0-7]{1,3})', String.Escape)
         ],
         'triplestring': [
@@ -1327,41 +1368,44 @@ class JasminLexer(RegexLexer):
             (r'method%s' % _break, Keyword.Reserved, 'enclosing-method'),
 
             # Instructions
-            (r'(aaload|aastore|aconst_null|aload|aload_0|aload_1|aload_2|'
-             r'aload_3|aload_w|areturn|arraylength|astore|astore_0|astore_1|'
-             r'astore_2|astore_3|astore_w|athrow|baload|bastore|bipush|'
-             r'breakpoint|caload|castore|d2f|d2i|d2l|dadd|daload|dastore|'
-             r'dcmpg|dcmpl|dconst_0|dconst_1|ddiv|dload|dload_0|dload_1|'
-             r'dload_2|dload_3|dload_w|dmul|dneg|drem|dreturn|dstore|dstore_0|'
-             r'dstore_1|dstore_2|dstore_3|dstore_w|dsub|dup|dup2|dup2_x1|'
-             r'dup2_x2|dup_x1|dup_x2|f2d|f2i|f2l|fadd|faload|fastore|fcmpg|'
-             r'fcmpl|fconst_0|fconst_1|fconst_2|fdiv|fload|fload_0|fload_1|'
-             r'fload_2|fload_3|fload_w|fmul|fneg|frem|freturn|fstore|fstore_0|'
-             r'fstore_1|fstore_2|fstore_3|fstore_w|fsub|i2b|i2c|i2d|i2f|i2l|'
-             r'i2s|iadd|iaload|iand|iastore|iconst_0|iconst_1|iconst_2|'
-             r'iconst_3|iconst_4|iconst_5|iconst_m1|idiv|iinc|iinc_w|iload|'
-             r'iload_0|iload_1|iload_2|iload_3|iload_w|imul|ineg|int2byte|'
-             r'int2char|int2short|ior|irem|ireturn|ishl|ishr|istore|istore_0|'
-             r'istore_1|istore_2|istore_3|istore_w|isub|iushr|ixor|l2d|l2f|'
-             r'l2i|ladd|laload|land|lastore|lcmp|lconst_0|lconst_1|ldc2_w|'
-             r'ldiv|lload|lload_0|lload_1|lload_2|lload_3|lload_w|lmul|lneg|'
-             r'lookupswitch|lor|lrem|lreturn|lshl|lshr|lstore|lstore_0|'
-             r'lstore_1|lstore_2|lstore_3|lstore_w|lsub|lushr|lxor|'
-             r'monitorenter|monitorexit|nop|pop|pop2|ret|ret_w|return|saload|'
-             r'sastore|sipush|swap)%s' % _break, Keyword.Reserved),
+            (words((
+                'aaload', 'aastore', 'aconst_null', 'aload', 'aload_0', 'aload_1', 'aload_2',
+                'aload_3', 'aload_w', 'areturn', 'arraylength', 'astore', 'astore_0', 'astore_1',
+                'astore_2', 'astore_3', 'astore_w', 'athrow', 'baload', 'bastore', 'bipush',
+                'breakpoint', 'caload', 'castore', 'd2f', 'd2i', 'd2l', 'dadd', 'daload', 'dastore',
+                'dcmpg', 'dcmpl', 'dconst_0', 'dconst_1', 'ddiv', 'dload', 'dload_0', 'dload_1',
+                'dload_2', 'dload_3', 'dload_w', 'dmul', 'dneg', 'drem', 'dreturn', 'dstore', 'dstore_0',
+                'dstore_1', 'dstore_2', 'dstore_3', 'dstore_w', 'dsub', 'dup', 'dup2', 'dup2_x1',
+                'dup2_x2', 'dup_x1', 'dup_x2', 'f2d', 'f2i', 'f2l', 'fadd', 'faload', 'fastore', 'fcmpg',
+                'fcmpl', 'fconst_0', 'fconst_1', 'fconst_2', 'fdiv', 'fload', 'fload_0', 'fload_1',
+                'fload_2', 'fload_3', 'fload_w', 'fmul', 'fneg', 'frem', 'freturn', 'fstore', 'fstore_0',
+                'fstore_1', 'fstore_2', 'fstore_3', 'fstore_w', 'fsub', 'i2b', 'i2c', 'i2d', 'i2f', 'i2l',
+                'i2s', 'iadd', 'iaload', 'iand', 'iastore', 'iconst_0', 'iconst_1', 'iconst_2',
+                'iconst_3', 'iconst_4', 'iconst_5', 'iconst_m1', 'idiv', 'iinc', 'iinc_w', 'iload',
+                'iload_0', 'iload_1', 'iload_2', 'iload_3', 'iload_w', 'imul', 'ineg', 'int2byte',
+                'int2char', 'int2short', 'ior', 'irem', 'ireturn', 'ishl', 'ishr', 'istore', 'istore_0',
+                'istore_1', 'istore_2', 'istore_3', 'istore_w', 'isub', 'iushr', 'ixor', 'l2d', 'l2f',
+                'l2i', 'ladd', 'laload', 'land', 'lastore', 'lcmp', 'lconst_0', 'lconst_1', 'ldc2_w',
+                'ldiv', 'lload', 'lload_0', 'lload_1', 'lload_2', 'lload_3', 'lload_w', 'lmul', 'lneg',
+                'lookupswitch', 'lor', 'lrem', 'lreturn', 'lshl', 'lshr', 'lstore', 'lstore_0',
+                'lstore_1', 'lstore_2', 'lstore_3', 'lstore_w', 'lsub', 'lushr', 'lxor',
+                'monitorenter', 'monitorexit', 'nop', 'pop', 'pop2', 'ret', 'ret_w', 'return', 'saload',
+                'sastore', 'sipush', 'swap'), suffix=_break), Keyword.Reserved),
             (r'(anewarray|checkcast|instanceof|ldc|ldc_w|new)%s' % _break,
              Keyword.Reserved, 'class/no-dots'),
-            (r'(invokedynamic|invokeinterface|invokenonvirtual|invokespecial|'
-             r'invokestatic|invokevirtual)%s' % _break, Keyword.Reserved,
+            (r'invoke(dynamic|interface|nonvirtual|special|'
+             r'static|virtual)%s' % _break, Keyword.Reserved,
              'invocation'),
             (r'(getfield|putfield)%s' % _break, Keyword.Reserved,
              ('descriptor/no-dots', 'field')),
             (r'(getstatic|putstatic)%s' % _break, Keyword.Reserved,
              ('descriptor/no-dots', 'static')),
-            (r'(goto|goto_w|if_acmpeq|if_acmpne|if_icmpeq|if_icmpge|if_icmpgt|'
-             r'if_icmple|if_icmplt|if_icmpne|ifeq|ifge|ifgt|ifle|iflt|ifne|'
-             r'ifnonnull|ifnull|jsr|jsr_w)%s' % _break, Keyword.Reserved,
-             'label'),
+            (words((
+                'goto', 'goto_w', 'if_acmpeq', 'if_acmpne', 'if_icmpeq',
+                'if_icmpge', 'if_icmpgt', 'if_icmple', 'if_icmplt', 'if_icmpne',
+                'ifeq', 'ifge', 'ifgt', 'ifle', 'iflt', 'ifne', 'ifnonnull',
+                'ifnull', 'jsr', 'jsr_w'), suffix=_break),
+             Keyword.Reserved, 'label'),
             (r'(multianewarray|newarray)%s' % _break, Keyword.Reserved,
              'descriptor/convert-dots'),
             (r'tableswitch%s' % _break, Keyword.Reserved, 'table')
@@ -1435,7 +1479,8 @@ class JasminLexer(RegexLexer):
             (r'(L)((?:%s[/.])*)(%s?)(;)' % (_unqualified_name, _name),
              bygroups(Keyword.Type, Name.Namespace, Name.Class, Punctuation),
              '#pop'),
-            (r'[^%s\[)L]*' % _separator, Keyword.Type, '#pop')
+            (r'[^%s\[)L]+' % _separator, Keyword.Type, '#pop'),
+            default('#pop')
         ],
         'descriptor/no-dots': [
             include('default'),
@@ -1443,7 +1488,8 @@ class JasminLexer(RegexLexer):
             (r'(L)((?:%s/)*)(%s)(;)' % (_unqualified_name, _name),
              bygroups(Keyword.Type, Name.Namespace, Name.Class, Punctuation),
              '#pop'),
-            (r'[^%s\[)L]*' % _separator, Keyword.Type, '#pop')
+            (r'[^%s\[)L]+' % _separator, Keyword.Type, '#pop'),
+            default('#pop')
         ],
         'descriptors/convert-dots': [
             (r'\)', Punctuation, '#pop'),