pygments.rb 0.6.3 → 1.0.0

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

@@ -0,0 +1,318 @@
+# -*- coding: utf-8 -*-
+"""
+    pygments.lexers.archetype
+    ~~~~~~~~~~~~~~~~~~~~~~~~~
+
+    Lexer for Archetype-related syntaxes, including:
+
+    - ODIN syntax <https://github.com/openEHR/odin>
+    - ADL syntax <http://www.openehr.org/releases/trunk/architecture/am/adl2.pdf>
+    - cADL sub-syntax of ADL
+
+    For uses of this syntax, see the openEHR archetypes <http://www.openEHR.org/ckm>
+
+    Contributed by Thomas Beale <https://github.com/wolandscat>,
+    <https://bitbucket.org/thomas_beale>.
+
+    :copyright: Copyright 2006-2015 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.lexer import RegexLexer, include, bygroups, using, default
+from pygments.token import Text, Comment, Name, Literal, Number, String, \
+    Punctuation, Keyword, Operator, Generic
+
+__all__ = ['OdinLexer', 'CadlLexer', 'AdlLexer']
+
+
+class AtomsLexer(RegexLexer):
+    """
+    Lexer for Values used in ADL and ODIN.
+
+    .. versionadded:: 2.1
+    """
+
+    tokens = {
+        # ----- pseudo-states for inclusion -----
+        'whitespace': [
+            (r'\n', Text),
+            (r'\s+', Text),
+            (r'[ \t]*--.*$', Comment),
+        ],
+        'archetype_id': [
+            (r'[ \t]*([a-zA-Z]\w+(\.[a-zA-Z]\w+)*::)?[a-zA-Z]\w+(-[a-zA-Z]\w+){2}'
+             r'\.\w+[\w-]*\.v\d+(\.\d+){,2}((-[a-z]+)(\.\d+)?)?', Name.Decorator),
+        ],
+        'date_constraints': [
+            # ISO 8601-based date/time constraints
+            (r'[Xx?YyMmDdHhSs\d]{2,4}([:-][Xx?YyMmDdHhSs\d]{2}){2}', Literal.Date),
+            # ISO 8601-based duration constraints + optional trailing slash
+            (r'(P[YyMmWwDd]+(T[HhMmSs]+)?|PT[HhMmSs]+)/?', Literal.Date),
+        ],
+        'ordered_values': [
+            # ISO 8601 date with optional 'T' ligature
+            (r'\d{4}-\d{2}-\d{2}T?', Literal.Date),
+            # ISO 8601 time
+            (r'\d{2}:\d{2}:\d{2}(\.\d+)?([+-]\d{4}|Z)?', Literal.Date),
+            # ISO 8601 duration
+            (r'P((\d*(\.\d+)?[YyMmWwDd]){1,3}(T(\d*(\.\d+)?[HhMmSs]){,3})?|'
+             r'T(\d*(\.\d+)?[HhMmSs]){,3})', Literal.Date),
+            (r'[+-]?(\d+\.\d*|\.\d+|\d+)[eE][+-]?\d+', Number.Float),
+            (r'[+-]?(\d+)*\.\d+%?', Number.Float),
+            (r'0x[0-9a-fA-F]+', Number.Hex),
+            (r'[+-]?\d+%?', Number.Integer),
+        ],
+        'values': [
+            include('ordered_values'),
+            (r'([Tt]rue|[Ff]alse)', Literal),
+            (r'"', String, 'string'),
+            (r"'(\\.|\\[0-7]{1,3}|\\x[a-fA-F0-9]{1,2}|[^\\\'\n])'", String.Char),
+            (r'[a-z][a-z0-9+.-]*:', Literal, 'uri'),
+            # term code
+            (r'(\[)(\w[\w-]*(?:\([^)\n]+\))?)(::)(\w[\w-]*)(\])',
+             bygroups(Punctuation, Name.Decorator, Punctuation, Name.Decorator,
+                      Punctuation)),
+            (r'\|', Punctuation, 'interval'),
+            # list continuation
+            (r'\.\.\.', Punctuation),
+        ],
+        'constraint_values': [
+            (r'(\[)(\w[\w-]*(?:\([^)\n]+\))?)(::)',
+             bygroups(Punctuation, Name.Decorator, Punctuation), 'adl14_code_constraint'),
+            # ADL 1.4 ordinal constraint
+            (r'(\d*)(\|)(\[\w[\w-]*::\w[\w-]*\])((?:[,;])?)',
+             bygroups(Number, Punctuation, Name.Decorator, Punctuation)),
+            include('date_constraints'),
+            include('values'),
+        ],
+
+        # ----- real states -----
+        'string': [
+            ('"', String, '#pop'),
+            (r'\\([\\abfnrtv"\']|x[a-fA-F0-9]{2,4}|'
+             r'u[a-fA-F0-9]{4}|U[a-fA-F0-9]{8}|[0-7]{1,3})', String.Escape),
+            # all other characters
+            (r'[^\\"]+', String),
+            # stray backslash
+            (r'\\', String),
+        ],
+        'uri': [
+            # effective URI terminators
+            (r'[,>\s]', Punctuation, '#pop'),
+            (r'[^>\s,]+', Literal),
+        ],
+        'interval': [
+            (r'\|', Punctuation, '#pop'),
+            include('ordered_values'),
+            (r'\.\.', Punctuation),
+            (r'[<>=] *', Punctuation),
+            # handle +/-
+            (r'\+/-', Punctuation),
+            (r'\s+', Text),
+        ],
+        'any_code': [
+            include('archetype_id'),
+            # if it is a code
+            (r'[a-z_]\w*[0-9.]+(@[^\]]+)?', Name.Decorator),
+            # if it is tuple with attribute names
+            (r'[a-z_]\w*', Name.Class),
+            # if it is an integer, i.e. Xpath child index
+            (r'[0-9]+', Text),
+            (r'\|', Punctuation, 'code_rubric'),
+            (r'\]', Punctuation, '#pop'),
+            # handle use_archetype statement
+            (r'\s*,\s*', Punctuation),
+        ],
+        'code_rubric': [
+            (r'\|', Punctuation, '#pop'),
+            (r'[^|]+', String),
+        ],
+        'adl14_code_constraint': [
+            (r'\]', Punctuation, '#pop'),
+            (r'\|', Punctuation, 'code_rubric'),
+            (r'(\w[\w-]*)([;,]?)', bygroups(Name.Decorator, Punctuation)),
+            include('whitespace'),
+        ],
+    }
+
+
+class OdinLexer(AtomsLexer):
+    """
+    Lexer for ODIN syntax.
+
+    .. versionadded:: 2.1
+    """
+    name = 'ODIN'
+    aliases = ['odin']
+    filenames = ['*.odin']
+    mimetypes = ['text/odin']
+
+    tokens = {
+        'path': [
+            (r'>', Punctuation, '#pop'),
+            # attribute name
+            (r'[a-z_]\w*', Name.Class),
+            (r'/', Punctuation),
+            (r'\[', Punctuation, 'key'),
+            (r'\s*,\s*', Punctuation, '#pop'),
+            (r'\s+', Text, '#pop'),
+        ],
+        'key': [
+            include('values'),
+            (r'\]', Punctuation, '#pop'),
+        ],
+        'type_cast': [
+            (r'\)', Punctuation, '#pop'),
+            (r'[^)]+',  Name.Class),
+        ],
+        'root': [
+            include('whitespace'),
+            (r'([Tt]rue|[Ff]alse)', Literal),
+            include('values'),
+            # x-ref path
+            (r'/', Punctuation, 'path'),
+            # x-ref path starting with key
+            (r'\[', Punctuation, 'key'),
+            # attribute name
+            (r'[a-z_]\w*', Name.Class),
+            (r'=', Operator),
+            (r'\(', Punctuation, 'type_cast'),
+            (r',', Punctuation),
+            (r'<', Punctuation),
+            (r'>', Punctuation),
+            (r';', Punctuation),
+        ],
+    }
+
+
+class CadlLexer(AtomsLexer):
+    """
+    Lexer for cADL syntax.
+
+    .. versionadded:: 2.1
+    """
+    name = 'cADL'
+    aliases = ['cadl']
+    filenames = ['*.cadl']
+
+    tokens = {
+        'path': [
+            # attribute name
+            (r'[a-z_]\w*', Name.Class),
+            (r'/', Punctuation),
+            (r'\[', Punctuation, 'any_code'),
+            (r'\s+', Punctuation, '#pop'),
+        ],
+        'root': [
+            include('whitespace'),
+            (r'(cardinality|existence|occurrences|group|include|exclude|'
+             r'allow_archetype|use_archetype|use_node)\W', Keyword.Type),
+            (r'(and|or|not|there_exists|xor|implies|for_all)\W', Keyword.Type),
+            (r'(after|before|closed)\W', Keyword.Type),
+            (r'(not)\W', Operator),
+            (r'(matches|is_in)\W', Operator),
+            # is_in / not is_in char
+            (u'(\u2208|\u2209)', Operator),
+            # there_exists / not there_exists / for_all / and / or
+            (u'(\u2203|\u2204|\u2200|\u2227|\u2228|\u22BB|\223C)',
+             Operator),
+            # regex in slot or as string constraint
+            (r'(\{)(\s*/[^}]+/\s*)(\})',
+             bygroups(Punctuation, String.Regex, Punctuation)),
+            # regex in slot or as string constraint
+            (r'(\{)(\s*\^[^}]+\^\s*)(\})',
+             bygroups(Punctuation, String.Regex, Punctuation)),
+            (r'/', Punctuation, 'path'),
+            # for cardinality etc
+            (r'(\{)((?:\d+\.\.)?(?:\d+|\*))'
+             r'((?:\s*;\s*(?:ordered|unordered|unique)){,2})(\})',
+             bygroups(Punctuation, Number, Number, Punctuation)),
+            # [{ is start of a tuple value
+            (r'\[\{', Punctuation),
+            (r'\}\]', Punctuation),
+            (r'\{', Punctuation),
+            (r'\}', Punctuation),
+            include('constraint_values'),
+            # type name
+            (r'[A-Z]\w+(<[A-Z]\w+([A-Za-z_<>]*)>)?',  Name.Class),
+            # attribute name
+            (r'[a-z_]\w*', Name.Class),
+            (r'\[', Punctuation, 'any_code'),
+            (r'(~|//|\\\\|\+|-|/|\*|\^|!=|=|<=|>=|<|>]?)', Operator),
+            (r'\(', Punctuation),
+            (r'\)', Punctuation),
+            # for lists of values
+            (r',', Punctuation),
+            (r'"', String, 'string'),
+            # for assumed value
+            (r';', Punctuation),
+        ],
+    }
+
+
+class AdlLexer(AtomsLexer):
+    """
+    Lexer for ADL syntax.
+
+    .. versionadded:: 2.1
+    """
+
+    name = 'ADL'
+    aliases = ['adl']
+    filenames = ['*.adl', '*.adls', '*.adlf', '*.adlx']
+
+    tokens = {
+        'whitespace': [
+            # blank line ends
+            (r'\s*\n', Text),
+            # comment-only line
+            (r'^[ \t]*--.*$', Comment),
+        ],
+        'odin_section': [
+            # repeating the following two rules from the root state enable multi-line
+            # strings that start in the first column to be dealt with
+            (r'^(language|description|ontology|terminology|annotations|'
+             r'component_terminologies|revision_history)[ \t]*\n', Generic.Heading),
+            (r'^(definition)[ \t]*\n', Generic.Heading, 'cadl_section'),
+            (r'^([ \t]*|[ \t]+.*)\n', using(OdinLexer)),
+            (r'^([^"]*")(>[ \t]*\n)', bygroups(String, Punctuation)),
+            # template overlay delimiter
+            (r'^----------*\n', Text, '#pop'),
+            (r'^.*\n', String),
+            default('#pop'),
+        ],
+        'cadl_section': [
+            (r'^([ \t]*|[ \t]+.*)\n', using(CadlLexer)),
+            default('#pop'),
+        ],
+        'rules_section': [
+            (r'^[ \t]+.*\n', using(CadlLexer)),
+            default('#pop'),
+        ],
+        'metadata': [
+            (r'\)', Punctuation, '#pop'),
+            (r';', Punctuation),
+            (r'([Tt]rue|[Ff]alse)', Literal),
+            # numbers and version ids
+            (r'\d+(\.\d+)*', Literal),
+            # Guids
+            (r'(\d|[a-fA-F])+(-(\d|[a-fA-F])+){3,}', Literal),
+            (r'\w+', Name.Class),
+            (r'"', String, 'string'),
+            (r'=', Operator),
+            (r'[ \t]+', Text),
+            default('#pop'),
+        ],
+        'root': [
+            (r'^(archetype|template_overlay|operational_template|template|'
+             r'speciali[sz]e)', Generic.Heading),
+            (r'^(language|description|ontology|terminology|annotations|'
+             r'component_terminologies|revision_history)[ \t]*\n',
+             Generic.Heading, 'odin_section'),
+            (r'^(definition)[ \t]*\n', Generic.Heading, 'cadl_section'),
+            (r'^(rules)[ \t]*\n', Generic.Heading, 'rules_section'),
+            include('archetype_id'),
+            (r'[ \t]*\(', Punctuation, 'metadata'),
+            include('whitespace'),
+        ],
+    }

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

@@ -5,19 +5,22 @@
 
     Lexers for assembly 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 RegexLexer, include, bygroups, using, DelegatingLexer
-from pygments.lexers.compiled import DLexer, CppLexer, CLexer
+from pygments.lexer import RegexLexer, include, bygroups, using, words, \
+    DelegatingLexer
+from pygments.lexers.c_cpp import CppLexer, CLexer
+from pygments.lexers.d import DLexer
 from pygments.token import Text, Name, Number, String, Comment, Punctuation, \
-     Other, Keyword, Operator
+    Other, Keyword, Operator
 
-__all__ = ['GasLexer', 'ObjdumpLexer','DObjdumpLexer', 'CppObjdumpLexer',
-           'CObjdumpLexer', 'LlvmLexer', 'NasmLexer', 'NasmObjdumpLexer', 'Ca65Lexer']
+__all__ = ['GasLexer', 'ObjdumpLexer', 'DObjdumpLexer', 'CppObjdumpLexer',
+           'CObjdumpLexer', 'HsailLexer', 'LlvmLexer', 'NasmLexer',
+           'NasmObjdumpLexer', 'TasmLexer', 'Ca65Lexer']
 
 
 class GasLexer(RegexLexer):
@@ -31,7 +34,7 @@ class GasLexer(RegexLexer):
 
     #: optional Comment or Whitespace
     string = r'"(\\"|[^"])*"'
-    char = r'[a-zA-Z$._0-9@-]'
+    char = r'[\w$.@-]'
     identifier = r'(?:[a-zA-Z$_]' + char + '*|\.' + char + '+)'
     number = r'(?:0[xX][a-zA-Z0-9]+|\d+)'
 
@@ -85,7 +88,7 @@ class GasLexer(RegexLexer):
             (r'#.*?\n', Comment)
         ],
         'punctuation': [
-            (r'[-*,.():]+', Punctuation)
+            (r'[-*,.()\[\]!:]+', Punctuation)
         ]
     }
 
@@ -154,11 +157,9 @@ class ObjdumpLexer(RegexLexer):
     filenames = ['*.objdump']
     mimetypes = ['text/x-objdump']
 
-
     tokens = _objdump_lexer_tokens(GasLexer)
 
 
-
 class DObjdumpLexer(DelegatingLexer):
     """
     For the output of 'objdump -Sr on compiled D files'
@@ -198,6 +199,141 @@ class CObjdumpLexer(DelegatingLexer):
         super(CObjdumpLexer, self).__init__(CLexer, ObjdumpLexer, **options)
 
 
+class HsailLexer(RegexLexer):
+    """
+    For HSAIL assembly code.
+
+    .. versionadded:: 2.2
+    """
+    name = 'HSAIL'
+    aliases = ['hsail', 'hsa']
+    filenames = ['*.hsail']
+    mimetypes = ['text/x-hsail']
+
+    string = r'"[^"]*?"'
+    identifier = r'[a-zA-Z_][\w.]*'
+    # Registers
+    register_number = r'[0-9]+'
+    register = r'(\$(c|s|d|q)' + register_number + ')'
+    # Qualifiers
+    alignQual = r'(align\(\d+\))'
+    widthQual = r'(width\((\d+|all)\))'
+    allocQual = r'(alloc\(agent\))'
+    # Instruction Modifiers
+    roundingMod = (r'((_ftz)?(_up|_down|_zero|_near))')
+    datatypeMod = (r'_('
+                   # packedTypes
+                   r'u8x4|s8x4|u16x2|s16x2|u8x8|s8x8|u16x4|s16x4|u32x2|s32x2|'
+                   r'u8x16|s8x16|u16x8|s16x8|u32x4|s32x4|u64x2|s64x2|'
+                   r'f16x2|f16x4|f16x8|f32x2|f32x4|f64x2|'
+                   # baseTypes
+                   r'u8|s8|u16|s16|u32|s32|u64|s64|'
+                   r'b128|b8|b16|b32|b64|b1|'
+                   r'f16|f32|f64|'
+                   # opaqueType
+                   r'roimg|woimg|rwimg|samp|sig32|sig64)')
+
+    # Numeric Constant
+    float = r'((\d+\.)|(\d*\.\d+))[eE][+-]?\d+'
+    hexfloat = r'0[xX](([0-9a-fA-F]+\.[0-9a-fA-F]*)|([0-9a-fA-F]*\.[0-9a-fA-F]+))[pP][+-]?\d+'
+    ieeefloat = r'0((h|H)[0-9a-fA-F]{4}|(f|F)[0-9a-fA-F]{8}|(d|D)[0-9a-fA-F]{16})'
+
+    tokens = {
+        'root': [
+            include('whitespace'),
+            include('comments'),
+
+            (string, String),
+
+            (r'@' + identifier + ':?', Name.Label),
+
+            (register, Name.Variable.Anonymous),
+
+            include('keyword'),
+
+            (r'&' + identifier, Name.Variable.Global),
+            (r'%' + identifier, Name.Variable),
+
+            (hexfloat, Number.Hex),
+            (r'0[xX][a-fA-F0-9]+', Number.Hex),
+            (ieeefloat, Number.Float),
+            (float, Number.Float),
+            ('\d+', Number.Integer),
+
+            (r'[=<>{}\[\]()*.,:;!]|x\b', Punctuation)
+        ],
+        'whitespace': [
+            (r'(\n|\s)+', Text),
+        ],
+        'comments': [
+            (r'/\*.*?\*/', Comment.Multiline),
+            (r'//.*?\n', Comment.Singleline),
+        ],
+        'keyword': [
+            # Types
+            (r'kernarg' + datatypeMod, Keyword.Type),
+
+            # Regular keywords
+            (r'\$(full|base|small|large|default|zero|near)', Keyword),
+            (words((
+                'module', 'extension', 'pragma', 'prog', 'indirect', 'signature',
+                'decl', 'kernel', 'function', 'enablebreakexceptions',
+                'enabledetectexceptions', 'maxdynamicgroupsize', 'maxflatgridsize',
+                'maxflatworkgroupsize', 'requireddim', 'requiredgridsize',
+                'requiredworkgroupsize', 'requirenopartialworkgroups'),
+                   suffix=r'\b'), Keyword),
+
+            # instructions
+            (roundingMod, Keyword),
+            (datatypeMod, Keyword),
+            (r'_(' + alignQual + '|' + widthQual + ')', Keyword),
+            (r'_kernarg', Keyword),
+            (r'(nop|imagefence)\b', Keyword),
+            (words((
+                'cleardetectexcept', 'clock', 'cuid', 'debugtrap', 'dim',
+                'getdetectexcept', 'groupbaseptr', 'kernargbaseptr', 'laneid',
+                'maxcuid', 'maxwaveid', 'packetid', 'setdetectexcept', 'waveid',
+                'workitemflatabsid', 'workitemflatid', 'nullptr', 'abs', 'bitrev',
+                'currentworkgroupsize', 'currentworkitemflatid', 'fract', 'ncos',
+                'neg', 'nexp2', 'nlog2', 'nrcp', 'nrsqrt', 'nsin', 'nsqrt',
+                'gridgroups', 'gridsize', 'not', 'sqrt', 'workgroupid',
+                'workgroupsize', 'workitemabsid', 'workitemid', 'ceil', 'floor',
+                'rint', 'trunc', 'add', 'bitmask', 'borrow', 'carry', 'copysign',
+                'div', 'rem', 'sub', 'shl', 'shr', 'and', 'or', 'xor', 'unpackhi',
+                'unpacklo', 'max', 'min', 'fma', 'mad', 'bitextract', 'bitselect',
+                'shuffle', 'cmov', 'bitalign', 'bytealign', 'lerp', 'nfma', 'mul',
+                'mulhi', 'mul24hi', 'mul24', 'mad24', 'mad24hi', 'bitinsert',
+                'combine', 'expand', 'lda', 'mov', 'pack', 'unpack', 'packcvt',
+                'unpackcvt', 'sad', 'sementp', 'ftos', 'stof', 'cmp', 'ld', 'st',
+                '_eq', '_ne', '_lt', '_le', '_gt', '_ge', '_equ', '_neu', '_ltu',
+                '_leu', '_gtu', '_geu', '_num', '_nan', '_seq', '_sne', '_slt',
+                '_sle', '_sgt', '_sge', '_snum', '_snan', '_sequ', '_sneu', '_sltu',
+                '_sleu', '_sgtu', '_sgeu', 'atomic', '_ld', '_st', '_cas', '_add',
+                '_and', '_exch', '_max', '_min', '_or', '_sub', '_wrapdec',
+                '_wrapinc', '_xor', 'ret', 'cvt', '_readonly', '_kernarg', '_global',
+                'br', 'cbr', 'sbr', '_scacq', '_screl', '_scar', '_rlx', '_wave',
+                '_wg', '_agent', '_system', 'ldimage', 'stimage', '_v2', '_v3', '_v4',
+                '_1d', '_2d', '_3d', '_1da', '_2da', '_1db', '_2ddepth', '_2dadepth',
+                '_width', '_height', '_depth', '_array', '_channelorder',
+                '_channeltype', 'querysampler', '_coord', '_filter', '_addressing',
+                'barrier', 'wavebarrier', 'initfbar', 'joinfbar', 'waitfbar',
+                'arrivefbar', 'leavefbar', 'releasefbar', 'ldf', 'activelaneid',
+                'activelanecount', 'activelanemask', 'activelanepermute', 'call',
+                'scall', 'icall', 'alloca', 'packetcompletionsig',
+                'addqueuewriteindex', 'casqueuewriteindex', 'ldqueuereadindex',
+                'stqueuereadindex', 'readonly', 'global', 'private', 'group',
+                'spill', 'arg', '_upi', '_downi', '_zeroi', '_neari', '_upi_sat',
+                '_downi_sat', '_zeroi_sat', '_neari_sat', '_supi', '_sdowni',
+                '_szeroi', '_sneari', '_supi_sat', '_sdowni_sat', '_szeroi_sat',
+                '_sneari_sat', '_pp', '_ps', '_sp', '_ss', '_s', '_p', '_pp_sat',
+                '_ps_sat', '_sp_sat', '_ss_sat', '_s_sat', '_p_sat')), Keyword),
+
+            # Integer types
+            (r'i[1-9]\d*', Keyword)
+        ]
+    }
+
+
 class LlvmLexer(RegexLexer):
     """
     For LLVM assembly code.
@@ -209,7 +345,7 @@ class LlvmLexer(RegexLexer):
 
     #: optional Comment or Whitespace
     string = r'"[^"]*?"'
-    identifier = r'([-a-zA-Z$._][-a-zA-Z$._0-9]*|' + string + ')'
+    identifier = r'([-a-zA-Z$._][\w\-$.]*|' + string + ')'
 
     tokens = {
         'root': [
@@ -220,11 +356,11 @@ class LlvmLexer(RegexLexer):
 
             include('keyword'),
 
-            (r'%' + identifier, Name.Variable),#Name.Identifier.Local),
-            (r'@' + identifier, Name.Variable.Global),#Name.Identifier.Global),
-            (r'%\d+', Name.Variable.Anonymous),#Name.Identifier.Anonymous),
-            (r'@\d+', Name.Variable.Global),#Name.Identifier.Anonymous),
-            (r'#\d+', Name.Variable.Global),#Name.Identifier.Global),
+            (r'%' + identifier, Name.Variable),
+            (r'@' + identifier, Name.Variable.Global),
+            (r'%\d+', Name.Variable.Anonymous),
+            (r'@\d+', Name.Variable.Global),
+            (r'#\d+', Name.Variable.Global),
             (r'!' + identifier, Name.Variable),
             (r'!\d+', Name.Variable.Anonymous),
             (r'c?' + string, String),
@@ -240,75 +376,54 @@ class LlvmLexer(RegexLexer):
         ],
         'keyword': [
             # Regular keywords
-            (r'(begin|end'
-             r'|true|false'
-             r'|declare|define'
-             r'|global|constant'
-
-             r'|private|linker_private|internal|available_externally|linkonce'
-             r'|linkonce_odr|weak|weak_odr|appending|dllimport|dllexport'
-             r'|common|default|hidden|protected|extern_weak|external'
-             r'|thread_local|zeroinitializer|undef|null|to|tail|target|triple'
-             r'|datalayout|volatile|nuw|nsw|nnan|ninf|nsz|arcp|fast|exact|inbounds'
-             r'|align|addrspace|section|alias|module|asm|sideeffect|gc|dbg'
-             r'|linker_private_weak'
-             r'|attributes|blockaddress|initialexec|localdynamic|localexec'
-             r'|prefix|unnamed_addr'
-
-             r'|ccc|fastcc|coldcc|x86_stdcallcc|x86_fastcallcc|arm_apcscc'
-             r'|arm_aapcscc|arm_aapcs_vfpcc|ptx_device|ptx_kernel'
-             r'|intel_ocl_bicc|msp430_intrcc|spir_func|spir_kernel'
-             r'|x86_64_sysvcc|x86_64_win64cc|x86_thiscallcc'
-
-             r'|cc|c'
-
-             r'|signext|zeroext|inreg|sret|nounwind|noreturn|noalias|nocapture'
-             r'|byval|nest|readnone|readonly'
-             r'|inlinehint|noinline|alwaysinline|optsize|ssp|sspreq|noredzone'
-             r'|noimplicitfloat|naked'
-             r'|builtin|cold|nobuiltin|noduplicate|nonlazybind|optnone'
-             r'|returns_twice|sanitize_address|sanitize_memory|sanitize_thread'
-             r'|sspstrong|uwtable|returned'
-
-             r'|type|opaque'
-
-             r'|eq|ne|slt|sgt|sle'
-             r'|sge|ult|ugt|ule|uge'
-             r'|oeq|one|olt|ogt|ole'
-             r'|oge|ord|uno|ueq|une'
-             r'|x'
-             r'|acq_rel|acquire|alignstack|atomic|catch|cleanup|filter'
-             r'|inteldialect|max|min|monotonic|nand|personality|release'
-             r'|seq_cst|singlethread|umax|umin|unordered|xchg'
-
-             # instructions
-             r'|add|fadd|sub|fsub|mul|fmul|udiv|sdiv|fdiv|urem|srem|frem|shl'
-             r'|lshr|ashr|and|or|xor|icmp|fcmp'
-
-             r'|phi|call|trunc|zext|sext|fptrunc|fpext|uitofp|sitofp|fptoui'
-             r'|fptosi|inttoptr|ptrtoint|bitcast|select|va_arg|ret|br|switch'
-             r'|invoke|unwind|unreachable'
-             r'|indirectbr|landingpad|resume'
-
-             r'|malloc|alloca|free|load|store|getelementptr'
-
-             r'|extractelement|insertelement|shufflevector|getresult'
-             r'|extractvalue|insertvalue'
-
-             r'|atomicrmw|cmpxchg|fence'
-
-             r')\b', Keyword),
+            (words((
+                'begin', 'end', 'true', 'false', 'declare', 'define', 'global',
+                'constant', 'private', 'linker_private', 'internal',
+                'available_externally', 'linkonce', 'linkonce_odr', 'weak',
+                'weak_odr', 'appending', 'dllimport', 'dllexport', 'common',
+                'default', 'hidden', 'protected', 'extern_weak', 'external',
+                'thread_local', 'zeroinitializer', 'undef', 'null', 'to', 'tail',
+                'target', 'triple', 'datalayout', 'volatile', 'nuw', 'nsw', 'nnan',
+                'ninf', 'nsz', 'arcp', 'fast', 'exact', 'inbounds', 'align',
+                'addrspace', 'section', 'alias', 'module', 'asm', 'sideeffect',
+                'gc', 'dbg', 'linker_private_weak', 'attributes', 'blockaddress',
+                'initialexec', 'localdynamic', 'localexec', 'prefix', 'unnamed_addr',
+                'ccc', 'fastcc', 'coldcc', 'x86_stdcallcc', 'x86_fastcallcc',
+                'arm_apcscc', 'arm_aapcscc', 'arm_aapcs_vfpcc', 'ptx_device',
+                'ptx_kernel', 'intel_ocl_bicc', 'msp430_intrcc', 'spir_func',
+                'spir_kernel', 'x86_64_sysvcc', 'x86_64_win64cc', 'x86_thiscallcc',
+                'cc', 'c', 'signext', 'zeroext', 'inreg', 'sret', 'nounwind',
+                'noreturn', 'noalias', 'nocapture', 'byval', 'nest', 'readnone',
+                'readonly', 'inlinehint', 'noinline', 'alwaysinline', 'optsize', 'ssp',
+                'sspreq', 'noredzone', 'noimplicitfloat', 'naked', 'builtin', 'cold',
+                'nobuiltin', 'noduplicate', 'nonlazybind', 'optnone', 'returns_twice',
+                'sanitize_address', 'sanitize_memory', 'sanitize_thread', 'sspstrong',
+                'uwtable', 'returned', 'type', 'opaque', 'eq', 'ne', 'slt', 'sgt',
+                'sle', 'sge', 'ult', 'ugt', 'ule', 'uge', 'oeq', 'one', 'olt', 'ogt',
+                'ole', 'oge', 'ord', 'uno', 'ueq', 'une', 'x', 'acq_rel', 'acquire',
+                'alignstack', 'atomic', 'catch', 'cleanup', 'filter', 'inteldialect',
+                'max', 'min', 'monotonic', 'nand', 'personality', 'release', 'seq_cst',
+                'singlethread', 'umax', 'umin', 'unordered', 'xchg', 'add', 'fadd',
+                'sub', 'fsub', 'mul', 'fmul', 'udiv', 'sdiv', 'fdiv', 'urem', 'srem',
+                'frem', 'shl', 'lshr', 'ashr', 'and', 'or', 'xor', 'icmp', 'fcmp',
+                'phi', 'call', 'trunc', 'zext', 'sext', 'fptrunc', 'fpext', 'uitofp',
+                'sitofp', 'fptoui', 'fptosi', 'inttoptr', 'ptrtoint', 'bitcast',
+                'addrspacecast', 'select', 'va_arg', 'ret', 'br', 'switch', 'invoke',
+                'unwind', 'unreachable', 'indirectbr', 'landingpad', 'resume',
+                'malloc', 'alloca', 'free', 'load', 'store', 'getelementptr',
+                'extractelement', 'insertelement', 'shufflevector', 'getresult',
+                'extractvalue', 'insertvalue', 'atomicrmw', 'cmpxchg', 'fence'),
+                   suffix=r'\b'), Keyword),
 
             # Types
-            (r'void|half|float|double|x86_fp80|fp128|ppc_fp128|label|metadata',
-             Keyword.Type),
+            (words(('void', 'half', 'float', 'double', 'x86_fp80', 'fp128',
+                    'ppc_fp128', 'label', 'metadata')), Keyword.Type),
 
             # Integer types
             (r'i[1-9]\d*', Keyword)
         ]
     }
 
-
 class NasmLexer(RegexLexer):
     """
     For Nasm (Intel) assembly code.
@@ -319,7 +434,7 @@ class NasmLexer(RegexLexer):
     mimetypes = ['text/x-nasm']
 
     identifier = r'[a-z$._?][\w$.?#@~]*'
-    hexn = r'(?:0[xX][0-9a-f]+|$0[0-9a-f]*|[0-9]+[0-9a-f]*h)'
+    hexn = r'(?:0x[0-9a-f]+|$0[0-9a-f]*|[0-9]+[0-9a-f]*h)'
     octn = r'[0-7]+q'
     binn = r'[01]+b'
     decn = r'[0-9]+'
@@ -338,8 +453,8 @@ class NasmLexer(RegexLexer):
     flags = re.IGNORECASE | re.MULTILINE
     tokens = {
         'root': [
-            include('whitespace'),
             (r'^\s*%', Comment.Preproc, 'preproc'),
+            include('whitespace'),
             (identifier + ':', Name.Label),
             (r'(%s)(\s+)(equ)' % identifier,
                 bygroups(Name.Constant, Keyword.Declaration, Keyword.Declaration),
@@ -396,13 +511,93 @@ class NasmObjdumpLexer(ObjdumpLexer):
     tokens = _objdump_lexer_tokens(NasmLexer)
 
 
+class TasmLexer(RegexLexer):
+    """
+    For Tasm (Turbo Assembler) assembly code.
+    """
+    name = 'TASM'
+    aliases = ['tasm']
+    filenames = ['*.asm', '*.ASM', '*.tasm']
+    mimetypes = ['text/x-tasm']
+
+    identifier = r'[@a-z$._?][\w$.?#@~]*'
+    hexn = r'(?:0x[0-9a-f]+|$0[0-9a-f]*|[0-9]+[0-9a-f]*h)'
+    octn = r'[0-7]+q'
+    binn = r'[01]+b'
+    decn = r'[0-9]+'
+    floatn = decn + r'\.e?' + decn
+    string = r'"(\\"|[^"\n])*"|' + r"'(\\'|[^'\n])*'|" + r"`(\\`|[^`\n])*`"
+    declkw = r'(?:res|d)[bwdqt]|times'
+    register = (r'r[0-9][0-5]?[bwd]|'
+                r'[a-d][lh]|[er]?[a-d]x|[er]?[sb]p|[er]?[sd]i|[c-gs]s|st[0-7]|'
+                r'mm[0-7]|cr[0-4]|dr[0-367]|tr[3-7]')
+    wordop = r'seg|wrt|strict'
+    type = r'byte|[dq]?word'
+    directives = (r'BITS|USE16|USE32|SECTION|SEGMENT|ABSOLUTE|EXTERN|GLOBAL|'
+                  r'ORG|ALIGN|STRUC|ENDSTRUC|ENDS|COMMON|CPU|GROUP|UPPERCASE|INCLUDE|'
+                  r'EXPORT|LIBRARY|MODULE|PROC|ENDP|USES|ARG|DATASEG|UDATASEG|END|IDEAL|'
+                  r'P386|MODEL|ASSUME|CODESEG|SIZE')
+    # T[A-Z][a-z] is more of a convention. Lexer should filter out STRUC definitions
+    # and then 'add' them to datatype somehow.
+    datatype = (r'db|dd|dw|T[A-Z][a-z]+')
+
+    flags = re.IGNORECASE | re.MULTILINE
+    tokens = {
+        'root': [
+            (r'^\s*%', Comment.Preproc, 'preproc'),
+            include('whitespace'),
+            (identifier + ':', Name.Label),
+            (directives, Keyword, 'instruction-args'),
+            (r'(%s)(\s+)(%s)' % (identifier, datatype),
+                bygroups(Name.Constant, Keyword.Declaration, Keyword.Declaration),
+                'instruction-args'),
+            (declkw, Keyword.Declaration, 'instruction-args'),
+            (identifier, Name.Function, 'instruction-args'),
+            (r'[\r\n]+', Text)
+        ],
+        'instruction-args': [
+            (string, String),
+            (hexn, Number.Hex),
+            (octn, Number.Oct),
+            (binn, Number.Bin),
+            (floatn, Number.Float),
+            (decn, Number.Integer),
+            include('punctuation'),
+            (register, Name.Builtin),
+            (identifier, Name.Variable),
+            # Do not match newline when it's preceeded by a backslash
+            (r'(\\\s*)(;.*)([\r\n])', bygroups(Text, Comment.Single, Text)),
+            (r'[\r\n]+', Text, '#pop'),
+            include('whitespace')
+        ],
+        'preproc': [
+            (r'[^;\n]+', Comment.Preproc),
+            (r';.*?\n', Comment.Single, '#pop'),
+            (r'\n', Comment.Preproc, '#pop'),
+        ],
+        'whitespace': [
+            (r'[\n\r]', Text),
+            (r'\\[\n\r]', Text),
+            (r'[ \t]+', Text),
+            (r';.*', Comment.Single)
+        ],
+        'punctuation': [
+            (r'[,():\[\]]+', Punctuation),
+            (r'[&|^<>+*=/%~-]+', Operator),
+            (r'[$]+', Keyword.Constant),
+            (wordop, Operator.Word),
+            (type, Keyword.Type)
+        ],
+    }
+
+
 class Ca65Lexer(RegexLexer):
     """
     For ca65 assembler sources.
 
     .. versionadded:: 1.6
     """
-    name = 'ca65'
+    name = 'ca65 assembler'
     aliases = ['ca65']
     filenames = ['*.s']
 
@@ -424,7 +619,7 @@ class Ca65Lexer(RegexLexer):
             (r'\$[0-9a-f]+|[0-9a-f]+h\b', Number.Hex),
             (r'\d+', Number.Integer),
             (r'%[01]+', Number.Bin),
-            (r'[#,.:()=]', Punctuation),
+            (r'[#,.:()=\[\]]', Punctuation),
             (r'[a-z_.@$][\w.@$]*', Name),
         ]
     }