class GasLexer(RegexLexer):
"""
For Gas (AT&T) assembly code.
"""
name = 'GAS'
aliases = ['gas']
filenames = ['*.s', '*.S']
mimetypes = ['text/x-gas']
#: optional Comment or Whitespace
string = r'"(\\"|[^"])*"'
char = r'[a-zA-Z$._0-9@]'
identifier = r'(?:[a-zA-Z$_]' + char + '*|\.' + char + '+)'
number = r'(?:0[xX][a-zA-Z0-9]+|\d+)'
tokens = {
'root': [
include('whitespace'), (identifier + ':', Name.Label),
(r'\.' + identifier, Name.Attribute, 'directive-args'),
(r'lock|rep(n?z)?|data\d+', Name.Attribute),
(identifier, Name.Function, 'instruction-args'), (r'[\r\n]+', Text)
],
'directive-args': [(identifier, Name.Constant), (string, String),
('@' + identifier, Name.Attribute),
(number, Number.Integer),
(r'[\r\n]+', Text, '#pop'),
(r'#.*?$', Comment, '#pop'),
include('punctuation'),
include('whitespace')],
'instruction-args': [
# For objdump-disassembled code, shouldn't occur in
# actual assembler input
('([a-z0-9]+)( )(<)(' + identifier + ')(>)',
bygroups(Number.Hex, Text, Punctuation, Name.Constant,
Punctuation)),
('([a-z0-9]+)( )(<)(' + identifier + ')([-+])(' + number + ')(>)',
bygroups(Number.Hex, Text, Punctuation, Name.Constant,
Punctuation, Number.Integer, Punctuation)),
# Address constants
(identifier, Name.Constant),
(number, Number.Integer),
# Registers
('%' + identifier, Name.Variable),
# Numeric constants
('$' + number, Number.Integer),
(r'[\r\n]+', Text, '#pop'),
(r'#.*?$', Comment, '#pop'),
include('punctuation'),
include('whitespace')
],
'whitespace': [(r'\n', Text), (r'\s+', Text), (r'#.*?\n', Comment)],
'punctuation': [(r'[-*,.():]+', Punctuation)]
}
def analyse_text(text):
return re.match(r'^\.\w+', text, re.M)
class BooLexer(RegexLexer):
"""
For `Boo <http://boo.codehaus.org/>`_ source code.
"""
name = 'Boo'
aliases = ['boo']
filenames = ['*.boo']
mimetypes = ['text/x-boo']
tokens = {
'root': [
(r'\s+', Text),
(r'(#|//).*$', Comment.Single),
(r'/[*]', Comment.Multiline, 'comment'),
(r'[]{}:(),.;[]', Punctuation),
(r'\\\n', Text),
(r'\\', Text),
(r'(in|is|and|or|not)\b', Operator.Word),
(r'/(\\\\|\\/|[^/\s])/', String.Regex),
(r'@/(\\\\|\\/|[^/])*/', String.Regex),
(r'=~|!=|==|<<|>>|[-+/*%=<>&^|]', Operator),
(r'(as|abstract|callable|constructor|destructor|do|import|'
r'enum|event|final|get|interface|internal|of|override|'
r'partial|private|protected|public|return|set|static|'
r'struct|transient|virtual|yield|super|and|break|cast|'
r'continue|elif|else|ensure|except|for|given|goto|if|in|'
r'is|isa|not|or|otherwise|pass|raise|ref|try|unless|when|'
r'while|from|as)\b', Keyword),
(r'def(?=\s+\(.*?\))', Keyword),
(r'(def)(\s+)', bygroups(Keyword, Text), 'funcname'),
(r'(class)(\s+)', bygroups(Keyword, Text), 'classname'),
(r'(namespace)(\s+)', bygroups(Keyword, Text), 'namespace'),
(r'(?<!\.)(true|false|null|self|__eval__|__switch__|array|'
r'assert|checked|enumerate|filter|getter|len|lock|map|'
r'matrix|max|min|normalArrayIndexing|print|property|range|'
r'rawArrayIndexing|required|typeof|unchecked|using|'
r'yieldAll|zip)\b', Name.Builtin),
('"""(\\\\|\\"|.*?)"""', String.Double),
('"(\\\\|\\"|[^"]*?)"', String.Double),
("'(\\\\|\\'|[^']*?)'", String.Single),
('[a-zA-Z_][a-zA-Z0-9_]*', Name),
(r'(\d+\.\d*|\d*\.\d+)([fF][+-]?[0-9]+)?', Number.Float),
(r'[0-9][0-9\.]*(m|ms|d|h|s)', Number),
(r'0\d+', Number.Oct),
(r'0x[a-fA-F0-9]+', Number.Hex),
(r'\d+L', Number.Integer.Long),
(r'\d+', Number.Integer),
],
'comment': [('/[*]', Comment.Multiline, '#push'),
('[*]/', Comment.Multiline, '#pop'),
('[^/*]', Comment.Multiline), ('[*/]', Comment.Multiline)],
'funcname': [('[a-zA-Z_][a-zA-Z0-9_]*', Name.Function, '#pop')],
'classname': [('[a-zA-Z_][a-zA-Z0-9_]*', Name.Class, '#pop')],
'namespace': [('[a-zA-Z_][a-zA-Z0-9_.]*', Name.Namespace, '#pop')]
}
class ObjdumpLexer(RegexLexer):
"""
For the output of 'objdump -dr'
"""
name = 'objdump'
aliases = ['objdump']
filenames = ['*.objdump']
mimetypes = ['text/x-objdump']
hex = r'[0-9A-Za-z]'
tokens = {
'root': [
# File name & format:
('(.*?)(:)( +file format )(.*?)$',
bygroups(Name.Label, Punctuation, Text, String)),
# Section header
('(Disassembly of section )(.*?)(:)$',
bygroups(Text, Name.Label, Punctuation)),
# Function labels
# (With offset)
('(' + hex + '+)( )(<)(.*?)([-+])(0[xX][A-Za-z0-9]+)(>:)$',
bygroups(Number.Hex, Text, Punctuation, Name.Function,
Punctuation, Number.Hex, Punctuation)),
# (Without offset)
('(' + hex + '+)( )(<)(.*?)(>:)$',
bygroups(Number.Hex, Text, Punctuation, Name.Function,
Punctuation)),
# Code line with disassembled instructions
('( *)(' + hex + r'+:)(\t)((?:' + hex + hex +
' )+)( *\t)([a-zA-Z].*?)$',
bygroups(Text, Name.Label, Text, Number.Hex, Text,
using(GasLexer))),
# Code line with ascii
('( *)(' + hex + r'+:)(\t)((?:' + hex + hex + ' )+)( *)(.*?)$',
bygroups(Text, Name.Label, Text, Number.Hex, Text, String)),
# Continued code line, only raw opcodes without disassembled
# instruction
('( *)(' + hex + r'+:)(\t)((?:' + hex + hex + ' )+)$',
bygroups(Text, Name.Label, Text, Number.Hex)),
# Skipped a few bytes
('\t\.\.\.$', Text),
# Relocation line
# (With offset)
('(\t\t\t)(' + hex + '+:)( )([^\t]+)(\t)(.*?)([-+])(0x' + hex +
'+)$',
bygroups(Text, Name.Label, Text, Name.Property, Text,
Name.Constant, Punctuation, Number.Hex)),
# (Without offset)
('(\t\t\t)(' + hex + '+:)( )([^\t]+)(\t)(.*?)$',
bygroups(Text, Name.Label, Text, Name.Property, Text,
Name.Constant)),
('[^\n]+\n', Other)
]
}
class NasmLexer(RegexLexer):
"""
For Nasm (Intel) assembly code.
"""
name = 'NASM'
aliases = ['nasm']
filenames = ['*.asm', '*.ASM']
mimetypes = ['text/x-nasm']
identifier = r'[a-zA-Z$._?][a-zA-Z0-9$._?#@~]*'
hexn = r'(?:0[xX][0-9a-fA-F]+|$0[0-9a-fA-F]*|[0-9]+[0-9a-fA-F]*h)'
octn = r'[0-7]+q'
binn = r'[01]+b'
decn = r'[0-9]+'
floatn = decn + r'\.e?' + decn
string = r'"(\\"|[^"])*"|' + r"'(\\'|[^'])*'"
declkw = r'(?:res|d)[bwdqt]|times'
register = (r'[a-d][lh]|e?[a-d]x|e?[sb]p|e?[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|COMMON|CPU|GROUP|UPPERCASE|IMPORT|'
r'EXPORT|LIBRARY|MODULE')
flags = re.IGNORECASE | re.MULTILINE
tokens = {
'root': [
include('whitespace'), (r'^\s*%', Comment.Preproc, 'preproc'),
(identifier + ':', Name.Label),
(r'(%s)(\s+)(equ)' % identifier,
bygroups(Name.Constant, Keyword.Declaration,
Keyword.Declaration), 'instruction-args'),
(directives, Keyword, '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),
(floatn, Number.Float), (decn, Number.Integer),
include('punctuation'), (register, Name.Builtin),
(identifier, Name.Variable),
(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', Text), (r'[ \t]+', Text),
(r';.*', Comment.Single)],
'punctuation': [(r'[,():\[\]]+', Punctuation),
(r'[&|^<>+*/%~-]+', Operator),
(r'[$]+', Keyword.Constant), (wordop, Operator.Word),
(type, Keyword.Type)],
}
class GenericAspxLexer(RegexLexer):
"""
Lexer for ASP.NET pages.
"""
name = 'aspx-gen'
filenames = []
mimetypes = []
flags = re.DOTALL
tokens = {
'root': [
(r'(<%[@=#]?)(.*?)(%>)', bygroups(Name.Tag, Other, Name.Tag)),
(r'(<script.*?>)(.*?)(</script>)',
bygroups(using(XmlLexer), Other, using(XmlLexer))),
(r'(.+?)(?=<)', using(XmlLexer)),
(r'.+', using(XmlLexer)),
],
}
class MatlabLexer(RegexLexer):
"""
For Matlab (or GNU Octave) source code.
Contributed by Ken Schutte <*****@*****.**>.
*New in Pygments 0.10.*
"""
name = 'Matlab'
aliases = ['matlab', 'octave']
filenames = ['*.m']
mimetypes = ['text/matlab']
#
# These lists are generated automatically.
# Run the following in bash shell:
#
# for f in elfun specfun elmat; do
# echo -n "$f = "
# matlab -nojvm -r "help $f;exit;" | perl -ne \
# 'push(@c,$1) if /^ (\w+)\s+-/; END {print q{["}.join(q{","},@c).qq{"]\n};}'
# done
#
# elfun: Elementary math functions
# specfun: Special Math functions
# elmat: Elementary matrices and matrix manipulation
#
# taken from Matlab version 7.4.0.336 (R2007a)
#
elfun = ["sin","sind","sinh","asin","asind","asinh","cos","cosd","cosh",
"acos","acosd","acosh","tan","tand","tanh","atan","atand","atan2",
"atanh","sec","secd","sech","asec","asecd","asech","csc","cscd",
"csch","acsc","acscd","acsch","cot","cotd","coth","acot","acotd",
"acoth","hypot","exp","expm1","log","log1p","log10","log2","pow2",
"realpow","reallog","realsqrt","sqrt","nthroot","nextpow2","abs",
"angle","complex","conj","imag","real","unwrap","isreal","cplxpair",
"fix","floor","ceil","round","mod","rem","sign"]
specfun = ["airy","besselj","bessely","besselh","besseli","besselk","beta",
"betainc","betaln","ellipj","ellipke","erf","erfc","erfcx",
"erfinv","expint","gamma","gammainc","gammaln","psi","legendre",
"cross","dot","factor","isprime","primes","gcd","lcm","rat",
"rats","perms","nchoosek","factorial","cart2sph","cart2pol",
"pol2cart","sph2cart","hsv2rgb","rgb2hsv"]
elmat = ["zeros","ones","eye","repmat","rand","randn","linspace","logspace",
"freqspace","meshgrid","accumarray","size","length","ndims","numel",
"disp","isempty","isequal","isequalwithequalnans","cat","reshape",
"diag","blkdiag","tril","triu","fliplr","flipud","flipdim","rot90",
"find","end","sub2ind","ind2sub","bsxfun","ndgrid","permute",
"ipermute","shiftdim","circshift","squeeze","isscalar","isvector",
"ans","eps","realmax","realmin","pi","i","inf","nan","isnan",
"isinf","isfinite","j","why","compan","gallery","hadamard","hankel",
"hilb","invhilb","magic","pascal","rosser","toeplitz","vander",
"wilkinson"]
tokens = {
'root': [
# line starting with '!' is sent as a system command. not sure what
# label to use...
(r'^!.*', String.Other),
(r'%.*$', Comment),
(r'^\s*function', Keyword, 'deffunc'),
# from 'iskeyword' on version 7.11 (R2010):
(r'(break|case|catch|classdef|continue|else|elseif|end|enumerated|'
r'events|for|function|global|if|methods|otherwise|parfor|'
r'persistent|properties|return|spmd|switch|try|while)\b', Keyword),
("(" + "|".join(elfun+specfun+elmat) + r')\b', Name.Builtin),
# operators:
(r'-|==|~=|<|>|<=|>=|&&|&|~|\|\|?', Operator),
# operators requiring escape for re:
(r'\.\*|\*|\+|\.\^|\.\\|\.\/|\/|\\', Operator),
# punctuation:
(r'\[|\]|\(|\)|\{|\}|:|@|\.|,', Punctuation),
(r'=|:|;', Punctuation),
# quote can be transpose, instead of string:
# (not great, but handles common cases...)
(r'(?<=[\w\)\]])\'', Operator),
(r'(?<![\w\)\]])\'', String, 'string'),
('[a-zA-Z_][a-zA-Z0-9_]*', Name),
(r'.', Text),
],
'string': [
(r'[^\']*\'', String, '#pop')
],
'deffunc': [
(r'(\s*)(?:(.+)(\s*)(=)(\s*))?(.+)(\()(.*)(\))(\s*)',
bygroups(Text.Whitespace, Text, Text.Whitespace, Punctuation,
Text.Whitespace, Name.Function, Punctuation, Text,
Punctuation, Text.Whitespace), '#pop'),
],
}
def analyse_text(text):
if re.match('^\s*%', text, re.M): # comment
return 0.9
elif re.match('^!\w+', text, re.M): # system cmd
return 0.9
return 0.1
class MuPADLexer(RegexLexer):
"""
A `MuPAD <http://www.mupad.com>`_ lexer.
Contributed by Christopher Creutzig <*****@*****.**>.
*New in Pygments 0.8.*
"""
name = 'MuPAD'
aliases = ['mupad']
filenames = ['*.mu']
tokens = {
'root' : [
(r'//.*?$', Comment.Single),
(r'/\*', Comment.Multiline, 'comment'),
(r'"(?:[^"\\]|\\.)*"', String),
(r'\(|\)|\[|\]|\{|\}', Punctuation),
(r'''(?x)\b(?:
next|break|end|
axiom|end_axiom|category|end_category|domain|end_domain|inherits|
if|%if|then|elif|else|end_if|
case|of|do|otherwise|end_case|
while|end_while|
repeat|until|end_repeat|
for|from|to|downto|step|end_for|
proc|local|option|save|begin|end_proc|
delete|frame
)\b''', Keyword),
(r'''(?x)\b(?:
DOM_ARRAY|DOM_BOOL|DOM_COMPLEX|DOM_DOMAIN|DOM_EXEC|DOM_EXPR|
DOM_FAIL|DOM_FLOAT|DOM_FRAME|DOM_FUNC_ENV|DOM_HFARRAY|DOM_IDENT|
DOM_INT|DOM_INTERVAL|DOM_LIST|DOM_NIL|DOM_NULL|DOM_POLY|DOM_PROC|
DOM_PROC_ENV|DOM_RAT|DOM_SET|DOM_STRING|DOM_TABLE|DOM_VAR
)\b''', Name.Class),
(r'''(?x)\b(?:
PI|EULER|E|CATALAN|
NIL|FAIL|undefined|infinity|
TRUE|FALSE|UNKNOWN
)\b''',
Name.Constant),
(r'\b(?:dom|procname)\b', Name.Builtin.Pseudo),
(r'\.|,|:|;|=|\+|-|\*|/|\^|@|>|<|\$|\||!|\'|%|~=', Operator),
(r'''(?x)\b(?:
and|or|not|xor|
assuming|
div|mod|
union|minus|intersect|in|subset
)\b''',
Operator.Word),
(r'\b(?:I|RDN_INF|RD_NINF|RD_NAN)\b', Number),
#(r'\b(?:adt|linalg|newDomain|hold)\b', Name.Builtin),
(r'''(?x)
((?:[a-zA-Z_#][a-zA-Z_#0-9]*|`[^`]*`)
(?:::[a-zA-Z_#][a-zA-Z_#0-9]*|`[^`]*`)*)\s*([(])''',
bygroups(Name.Function, Punctuation)),
(r'''(?x)
(?:[a-zA-Z_#][a-zA-Z_#0-9]*|`[^`]*`)
(?:::[a-zA-Z_#][a-zA-Z_#0-9]*|`[^`]*`)*''', Name.Variable),
(r'[0-9]+(?:\.[0-9]*)?(?:e[0-9]+)?', Number),
(r'\.[0-9]+(?:e[0-9]+)?', Number),
(r'.', Text)
],
'comment' : [
(r'[^*/]', Comment.Multiline),
(r'/\*', Comment.Multiline, '#push'),
(r'\*/', Comment.Multiline, '#pop'),
(r'[*/]', Comment.Multiline)
]
}
class AntlrLexer(RegexLexer):
"""
Generic `ANTLR`_ Lexer.
Should not be called directly, instead
use DelegatingLexer for your target language.
*New in Pygments 1.1.*
.. _ANTLR: http://www.antlr.org/
"""
name = 'ANTLR'
aliases = ['antlr']
filenames = []
_id = r'[A-Za-z][A-Za-z_0-9]*'
_TOKEN_REF = r'[A-Z][A-Za-z_0-9]*'
_RULE_REF = r'[a-z][A-Za-z_0-9]*'
_STRING_LITERAL = r'\'(?:\\\\|\\\'|[^\']*)\''
_INT = r'[0-9]+'
tokens = {
'whitespace': [
(r'\s+', Whitespace),
],
'comments': [
(r'//.*$', Comment),
(r'/\*(.|\n)*?\*/', Comment),
],
'root': [
include('whitespace'),
include('comments'),
(r'(lexer|parser|tree)?(\s*)(grammar\b)(\s*)(' + _id + ')(;)',
bygroups(Keyword, Whitespace, Keyword, Whitespace, Name.Class,
Punctuation)),
# optionsSpec
(r'options\b', Keyword, 'options'),
# tokensSpec
(r'tokens\b', Keyword, 'tokens'),
# attrScope
(r'(scope)(\s*)(' + _id + ')(\s*)({)',
bygroups(Keyword, Whitespace, Name.Variable, Whitespace,
Punctuation), 'action'),
# exception
(r'(catch|finally)\b', Keyword, 'exception'),
# action
(r'(@' + _id + ')(\s*)(::)?(\s*)(' + _id + ')(\s*)({)',
bygroups(Name.Label, Whitespace, Punctuation, Whitespace,
Name.Label, Whitespace, Punctuation), 'action'),
# rule
(r'((?:protected|private|public|fragment)\b)?(\s*)(' + _id + ')(!)?', \
bygroups(Keyword, Whitespace, Name.Label, Punctuation),
('rule-alts', 'rule-prelims')),
],
'exception': [
(r'\n', Whitespace, '#pop'),
(r'\s', Whitespace),
include('comments'),
(r'\[', Punctuation, 'nested-arg-action'),
(r'\{', Punctuation, 'action'),
],
'rule-prelims': [
include('whitespace'),
include('comments'),
(r'returns\b', Keyword),
(r'\[', Punctuation, 'nested-arg-action'),
(r'\{', Punctuation, 'action'),
# throwsSpec
(r'(throws)(\s+)(' + _id + ')',
bygroups(Keyword, Whitespace, Name.Label)),
(r'(?:(,)(\s*)(' + _id + '))+',
bygroups(Punctuation, Whitespace, Name.Label)), # Additional throws
# optionsSpec
(r'options\b', Keyword, 'options'),
# ruleScopeSpec - scope followed by target language code or name of action
# TODO finish implementing other possibilities for scope
# L173 ANTLRv3.g from ANTLR book
(r'(scope)(\s+)({)', bygroups(Keyword, Whitespace, Punctuation),
'action'),
(r'(scope)(\s+)(' + _id + ')(\s*)(;)',
bygroups(Keyword, Whitespace, Name.Label, Whitespace, Punctuation)),
# ruleAction
(r'(@' + _id + ')(\s*)({)',
bygroups(Name.Label, Whitespace, Punctuation), 'action'),
# finished prelims, go to rule alts!
(r':', Punctuation, '#pop')
],
'rule-alts': [
include('whitespace'),
include('comments'),
# These might need to go in a separate 'block' state triggered by (
(r'options\b', Keyword, 'options'),
(r':', Punctuation),
# literals
(r"'(\\\\|\\'|[^'])*'", String),
(r'"(\\\\|\\"|[^"])*"', String),
(r'<<([^>]|>[^>])>>', String),
# identifiers
# Tokens start with capital letter.
(r'\$?[A-Z_][A-Za-z_0-9]*', Name.Constant),
# Rules start with small letter.
(r'\$?[a-z_][A-Za-z_0-9]*', Name.Variable),
# operators
(r'(\+|\||->|=>|=|\(|\)|\.\.|\.|\?|\*|\^|!|\#|~)', Operator),
(r',', Punctuation),
(r'\[', Punctuation, 'nested-arg-action'),
(r'\{', Punctuation, 'action'),
(r';', Punctuation, '#pop')
],
'tokens': [
include('whitespace'),
include('comments'),
(r'{', Punctuation),
(r'(' + _TOKEN_REF + r')(\s*)(=)?(\s*)(' + _STRING_LITERAL
+ ')?(\s*)(;)',
bygroups(Name.Label, Whitespace, Punctuation, Whitespace,
String, Whitespace, Punctuation)),
(r'}', Punctuation, '#pop'),
],
'options': [
include('whitespace'),
include('comments'),
(r'{', Punctuation),
(r'(' + _id + r')(\s*)(=)(\s*)(' +
'|'.join((_id, _STRING_LITERAL, _INT, '\*'))+ ')(\s*)(;)',
bygroups(Name.Variable, Whitespace, Punctuation, Whitespace,
Text, Whitespace, Punctuation)),
(r'}', Punctuation, '#pop'),
],
'action': [
(r'(' + r'|'.join(( # keep host code in largest possible chunks
r'[^\${}\'"/\\]+', # exclude unsafe characters
# strings and comments may safely contain unsafe characters
r'"(\\\\|\\"|[^"])*"', # double quote string
r"'(\\\\|\\'|[^'])*'", # single quote string
r'//.*$\n?', # single line comment
r'/\*(.|\n)*?\*/', # multi-line javadoc-style comment
# regular expression: There's no reason for it to start
# with a * and this stops confusion with comments.
r'/(?!\*)(\\\\|\\/|[^/])*/',
# backslashes are okay, as long as we are not backslashing a %
r'\\(?!%)',
# Now that we've handled regex and javadoc comments
# it's safe to let / through.
r'/',
)) + r')+', Other),
(r'(\\)(%)', bygroups(Punctuation, Other)),
(r'(\$[a-zA-Z]+)(\.?)(text|value)?',
bygroups(Name.Variable, Punctuation, Name.Property)),
(r'{', Punctuation, '#push'),
(r'}', Punctuation, '#pop'),
],
'nested-arg-action': [
(r'(' + r'|'.join(( # keep host code in largest possible chunks.
r'[^\$\[\]\'"/]+', # exclude unsafe characters
# strings and comments may safely contain unsafe characters
r'"(\\\\|\\"|[^"])*"', # double quote string
r"'(\\\\|\\'|[^'])*'", # single quote string
r'//.*$\n?', # single line comment
r'/\*(.|\n)*?\*/', # multi-line javadoc-style comment
# regular expression: There's no reason for it to start
# with a * and this stops confusion with comments.
r'/(?!\*)(\\\\|\\/|[^/])*/',
# Now that we've handled regex and javadoc comments
# it's safe to let / through.
r'/',
)) + r')+', Other),
(r'\[', Punctuation, '#push'),
(r'\]', Punctuation, '#pop'),
(r'(\$[a-zA-Z]+)(\.?)(text|value)?',
bygroups(Name.Variable, Punctuation, Name.Property)),
(r'(\\\\|\\\]|\\\[|[^\[\]])+', Other),
]
}
def analyse_text(text):
return re.search(r'^\s*grammar\s+[a-zA-Z0-9]+\s*;', text, re.M)
class RagelEmbeddedLexer(RegexLexer):
"""
A lexer for `Ragel`_ embedded in a host language file.
This will only highlight Ragel statements. If you want host language
highlighting then call the language-specific Ragel lexer.
*New in Pygments 1.1.*
"""
name = 'Embedded Ragel'
aliases = ['ragel-em']
filenames = ['*.rl']
tokens = {
'root': [
(
r'(' + r'|'.join(( # keep host code in largest possible chunks
r'[^%\'"/#]+', # exclude unsafe characters
r'%(?=[^%]|$)', # a single % sign is okay, just not 2 of them
# strings and comments may safely contain unsafe characters
r'"(\\\\|\\"|[^"])*"', # double quote string
r"'(\\\\|\\'|[^'])*'", # single quote string
r'/\*(.|\n)*?\*/', # multi-line javadoc-style comment
r'//.*$\n?', # single line comment
r'\#.*$\n?', # ruby/ragel comment
r'/(?!\*)(\\\\|\\/|[^/])*/', # regular expression
# / is safe now that we've handled regex and javadoc comments
r'/',
)) + r')+',
Other),
# Single Line FSM.
# Please don't put a quoted newline in a single line FSM.
# That's just mean. It will break this.
(r'(%%)(?![{%])(.*)($|;)(\n?)',
bygroups(Punctuation, using(RagelLexer), Punctuation, Text)),
# Multi Line FSM.
(r'(%%%%|%%){', Punctuation, 'multi-line-fsm'),
],
'multi-line-fsm': [
(
r'(' +
r'|'.join(( # keep ragel code in largest possible chunks.
r'(' + r'|'.join((
r'[^}\'"\[/#]', # exclude unsafe characters
r'}(?=[^%]|$)', # } is okay as long as it's not followed by %
r'}%(?=[^%]|$)', # ...well, one %'s okay, just not two...
r'[^\\][\\][{}]', # ...and } is okay if it's escaped
# allow / if it's preceded with one of these symbols
# (ragel EOF actions)
r'(>|\$|%|<|@|<>)/',
# specifically allow regex followed immediately by *
# so it doesn't get mistaken for a comment
r'/(?!\*)(\\\\|\\/|[^/])*/\*',
# allow / as long as it's not followed by another / or by a *
r'/(?=[^/\*]|$)',
# We want to match as many of these as we can in one block.
# Not sure if we need the + sign here,
# does it help performance?
)) + r')+',
# strings and comments may safely contain unsafe characters
r'"(\\\\|\\"|[^"])*"', # double quote string
r"'(\\\\|\\'|[^'])*'", # single quote string
r"\[(\\\\|\\\]|[^\]])*\]", # square bracket literal
r'/\*(.|\n)*?\*/', # multi-line javadoc-style comment
r'//.*$\n?', # single line comment
r'\#.*$\n?', # ruby/ragel comment
)) + r')+',
using(RagelLexer)),
(r'}%%', Punctuation, '#pop'),
]
}
def analyse_text(text):
return '@LANG: indep' in text or 0.1
class CSharpLexer(RegexLexer):
"""
For `C# <http://msdn2.microsoft.com/en-us/vcsharp/default.aspx>`_
source code.
Additional options accepted:
`unicodelevel`
Determines which Unicode characters this lexer allows for identifiers.
The possible values are:
* ``none`` -- only the ASCII letters and numbers are allowed. This
is the fastest selection.
* ``basic`` -- all Unicode characters from the specification except
category ``Lo`` are allowed.
* ``full`` -- all Unicode characters as specified in the C# specs
are allowed. Note that this means a considerable slowdown since the
``Lo`` category has more than 40,000 characters in it!
The default value is ``basic``.
*New in Pygments 0.8.*
"""
name = 'C#'
aliases = ['csharp', 'c#']
filenames = ['*.cs']
mimetypes = ['text/x-csharp'] # inferred
flags = re.MULTILINE | re.DOTALL | re.UNICODE
# for the range of allowed unicode characters in identifiers,
# see http://www.ecma-international.org/publications/files/ECMA-ST/Ecma-334.pdf
levels = {
'none':
'@?[_a-zA-Z][a-zA-Z0-9_]*',
'basic': ('@?[_' + 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 + ']*'),
'full': ('@?(?:_|[^' +
_escape(uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl')) +
'])' + '[^' + _escape(
uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl', 'Nd',
'Pc', 'Cf', 'Mn', 'Mc')) + ']*'),
}
tokens = {}
token_variants = True
for levelname, cs_ident in levels.items():
tokens[levelname] = {
'root': [
# method names
(
r'^([ \t]*(?:' + cs_ident +
r'(?:\[\])?\s+)+?)' # return type
r'(' + cs_ident + ')' # method name
r'(\s*)(\()', # signature start
bygroups(using(this), Name.Function, Text, Punctuation)),
(r'^\s*\[.*?\]', Name.Attribute),
(r'[^\S\n]+', Text),
(r'\\\n', Text), # line continuation
(r'//.*?\n', Comment.Single),
(r'/[*](.|\n)*?[*]/', Comment.Multiline),
(r'\n', Text),
(r'[~!%^&*()+=|\[\]:;,.<>/?-]', Punctuation),
(r'[{}]', Punctuation),
(r'@"(\\\\|\\"|[^"])*"', String),
(r'"(\\\\|\\"|[^"\n])*["\n]', String),
(r"'\\.'|'[^\\]'", String.Char),
(r"[0-9](\.[0-9]*)?([eE][+-][0-9]+)?"
r"[flFLdD]?|0[xX][0-9a-fA-F]+[Ll]?", Number),
(r'#[ \t]*(if|endif|else|elif|define|undef|'
r'line|error|warning|region|endregion|pragma)\b.*?\n',
Comment.Preproc),
(r'\b(extern)(\s+)(alias)\b', bygroups(Keyword, Text,
Keyword)),
(r'(abstract|as|base|break|case|catch|'
r'checked|const|continue|default|delegate|'
r'do|else|enum|event|explicit|extern|false|finally|'
r'fixed|for|foreach|goto|if|implicit|in|interface|'
r'internal|is|lock|new|null|operator|'
r'out|override|params|private|protected|public|readonly|'
r'ref|return|sealed|sizeof|stackalloc|static|'
r'switch|this|throw|true|try|typeof|'
r'unchecked|unsafe|virtual|void|while|'
r'get|set|new|partial|yield|add|remove|value)\b', Keyword),
(r'(global)(::)', bygroups(Keyword, Punctuation)),
(r'(bool|byte|char|decimal|double|float|int|long|object|sbyte|'
r'short|string|uint|ulong|ushort)\b\??', Keyword.Type),
(r'(class|struct)(\s+)', bygroups(Keyword, Text), 'class'),
(r'(namespace|using)(\s+)', bygroups(Keyword,
Text), 'namespace'),
(cs_ident, Name),
],
'class': [(cs_ident, Name.Class, '#pop')],
'namespace': [
(r'(?=\()', Text, '#pop'), # using (resource)
('(' + cs_ident + r'|\.)+', Name.Namespace, '#pop')
]
}
def __init__(self, **options):
level = get_choice_opt(options, 'unicodelevel', self.tokens.keys(),
'basic')
if level not in self._all_tokens:
# compile the regexes now
self._tokens = self.__class__.process_tokendef(level)
else:
self._tokens = self._all_tokens[level]
RegexLexer.__init__(self, **options)
class VbNetLexer(RegexLexer):
"""
For
`Visual Basic.NET <http://msdn2.microsoft.com/en-us/vbasic/default.aspx>`_
source code.
"""
name = 'VB.net'
aliases = ['vb.net', 'vbnet']
filenames = ['*.vb', '*.bas']
mimetypes = ['text/x-vbnet', 'text/x-vba'] # (?)
flags = re.MULTILINE | re.IGNORECASE
tokens = {
'root': [
(r'^\s*<.*?>', Name.Attribute),
(r'\s+', Text),
(r'\n', Text),
(r'rem\b.*?\n', Comment),
(r"'.*?\n", Comment),
(r'#If\s.*?\sThen|#ElseIf\s.*?\sThen|#End\s+If|#Const|'
r'#ExternalSource.*?\n|#End\s+ExternalSource|'
r'#Region.*?\n|#End\s+Region|#ExternalChecksum', Comment.Preproc),
(r'[\(\){}!#,.:]', Punctuation),
(r'Option\s+(Strict|Explicit|Compare)\s+'
r'(On|Off|Binary|Text)', Keyword.Declaration),
(r'(?<!\.)(AddHandler|Alias|'
r'ByRef|ByVal|Call|Case|Catch|CBool|CByte|CChar|CDate|'
r'CDec|CDbl|CInt|CLng|CObj|Continue|CSByte|CShort|'
r'CSng|CStr|CType|CUInt|CULng|CUShort|Declare|'
r'Default|Delegate|DirectCast|Do|Each|Else|ElseIf|'
r'EndIf|Erase|Error|Event|Exit|False|Finally|For|'
r'Friend|Get|Global|GoSub|GoTo|Handles|If|'
r'Implements|Inherits|Interface|'
r'Let|Lib|Loop|Me|MustInherit|'
r'MustOverride|MyBase|MyClass|Narrowing|New|Next|'
r'Not|Nothing|NotInheritable|NotOverridable|Of|On|'
r'Operator|Option|Optional|Overloads|Overridable|'
r'Overrides|ParamArray|Partial|Private|Protected|'
r'Public|RaiseEvent|ReadOnly|ReDim|RemoveHandler|Resume|'
r'Return|Select|Set|Shadows|Shared|Single|'
r'Static|Step|Stop|SyncLock|Then|'
r'Throw|To|True|Try|TryCast|Wend|'
r'Using|When|While|Widening|With|WithEvents|'
r'WriteOnly)\b', Keyword),
(r'(?<!\.)End\b', Keyword, 'end'),
(r'(?<!\.)(Dim|Const)\b', Keyword, 'dim'),
(r'(?<!\.)(Function|Sub|Property)(\s+)', bygroups(Keyword, Text),
'funcname'),
(r'(?<!\.)(Class|Structure|Enum)(\s+)', bygroups(Keyword, Text),
'classname'),
(r'(?<!\.)(Module|Namespace|Imports)(\s+)',
bygroups(Keyword, Text), 'namespace'),
(r'(?<!\.)(Boolean|Byte|Char|Date|Decimal|Double|Integer|Long|'
r'Object|SByte|Short|Single|String|Variant|UInteger|ULong|'
r'UShort)\b', Keyword.Type),
(r'(?<!\.)(AddressOf|And|AndAlso|As|GetType|In|Is|IsNot|Like|Mod|'
r'Or|OrElse|TypeOf|Xor)\b', Operator.Word),
(r'&=|[*]=|/=|\\=|\^=|\+=|-=|<<=|>>=|<<|>>|:=|'
r'<=|>=|<>|[-&*/\\^+=<>]', Operator),
('"', String, 'string'),
('[a-zA-Z_][a-zA-Z0-9_]*[%&@!#$]?', Name),
('#.*?#', Literal.Date),
(r'(\d+\.\d*|\d*\.\d+)([fF][+-]?[0-9]+)?', Number.Float),
(r'\d+([SILDFR]|US|UI|UL)?', Number.Integer),
(r'&H[0-9a-f]+([SILDFR]|US|UI|UL)?', Number.Integer),
(r'&O[0-7]+([SILDFR]|US|UI|UL)?', Number.Integer),
(r'_\n', Text), # Line continuation
],
'string': [
(r'""', String),
(r'"C?', String, '#pop'),
(r'[^"]+', String),
],
'dim': [
(r'[a-z_][a-z0-9_]*', Name.Variable, '#pop'),
(r'', Text, '#pop'), # any other syntax
],
'funcname': [
(r'[a-z_][a-z0-9_]*', Name.Function, '#pop'),
],
'classname': [
(r'[a-z_][a-z0-9_]*', Name.Class, '#pop'),
],
'namespace': [
(r'[a-z_][a-z0-9_.]*', Name.Namespace, '#pop'),
],
'end': [
(r'\s+', Text),
(r'(Function|Sub|Property|Class|Structure|Enum|Module|Namespace)\b',
Keyword, '#pop'),
(r'', Text, '#pop'),
]
}
class VerilogLexer(RegexLexer):
"""
For verilog source code with preprocessor directives.
*New in Pygments 1.4.*
"""
name = 'verilog'
aliases = ['v']
filenames = ['*.v', '*.sv']
mimetypes = ['text/x-verilog']
#: optional Comment or Whitespace
_ws = r'(?:\s|//.*?\n|/[*].*?[*]/)+'
tokens = {
'root': [
(r'^\s*`define', Comment.Preproc, 'macro'),
(r'\n', Text),
(r'\s+', Text),
(r'\\\n', Text), # line continuation
(r'/(\\\n)?/(\n|(.|\n)*?[^\\]\n)', Comment.Single),
(r'/(\\\n)?[*](.|\n)*?[*](\\\n)?/', Comment.Multiline),
(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)[0-1]+', Number.Hex), # should be binary
(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'[~!%^&*+=|?:<>/-]', Operator),
(r'[()\[\],.;\']', Punctuation),
(r'`[a-zA-Z_][a-zA-Z0-9_]*', Name.Constant),
(r'^\s*(package)(\s+)', bygroups(Keyword.Namespace, Text)),
(r'^\s*(import)(\s+)', bygroups(Keyword.Namespace,
Text), 'import'),
(r'(always|always_comb|always_ff|always_latch|and|assign|automatic|'
r'begin|break|buf|bufif0|bufif1|case|casex|casez|cmos|const|'
r'continue|deassign|default|defparam|disable|do|edge|else|end|endcase|'
r'endfunction|endgenerate|endselectedModulee|endpackage|endprimitive|endspecify|'
r'endtable|endtask|enum|event|final|for|force|forever|fork|function|'
r'generate|genvar|highz0|highz1|if|initial|inout|input|'
r'integer|join|large|localparam|macroselectedModulee|medium|selectedModulee|'
r'nand|negedge|nmos|nor|not|notif0|notif1|or|output|packed|'
r'parameter|pmos|posedge|primitive|pull0|pull1|pulldown|pullup|rcmos|'
r'ref|release|repeat|return|rnmos|rpmos|rtran|rtranif0|'
r'rtranif1|scalared|signed|small|specify|specparam|strength|'
r'string|strong0|strong1|struct|table|task|'
r'tran|tranif0|tranif1|type|typedef|'
r'unsigned|var|vectored|void|wait|weak0|weak1|while|'
r'xnor|xor)\b', Keyword),
(r'(`accelerate|`autoexpand_vectornets|`celldefine|`default_nettype|'
r'`else|`elsif|`endcelldefine|`endif|`endprotect|`endprotected|'
r'`expand_vectornets|`ifdef|`ifndef|`include|`noaccelerate|`noexpand_vectornets|'
r'`noremove_gatenames|`noremove_netnames|`nounconnected_drive|'
r'`protect|`protected|`remove_gatenames|`remove_netnames|`resetall|'
r'`timescale|`unconnected_drive|`undef)\b', Comment.Preproc),
(r'(\$cits|\$citstoreal|\$citstoshortreal|\$countdrivers|\$display|\$fclose|'
r'\$fdisplay|\$finish|\$floor|\$fmonitor|\$fopen|\$fstrobe|\$fwrite|'
r'\$getpattern|\$history|\$incsave|\$input|\$itor|\$key|\$list|\$log|'
r'\$monitor|\$monitoroff|\$monitoron|\$nokey|\$nolog|\$printtimescale|'
r'\$random|\$readmemb|\$readmemh|\$realtime|\$realtobits|\$reset|\$reset_count|'
r'\$reset_value|\$restart|\$rtoi|\$save|\$scale|\$scope|\$shortrealtobits|'
r'\$showscopes|\$showvariables|\$showvars|\$sreadmemb|\$sreadmemh|'
r'\$stime|\$stop|\$strobe|\$time|\$timeformat|\$write)\b',
Name.Builtin),
(r'(class)(\s+)', bygroups(Keyword, Text), 'classname'),
(r'(byte|shortint|int|longint|interger|time|'
r'bit|logic|reg|'
r'supply0|supply1|tri|triand|trior|tri0|tri1|trireg|uwire|wire|wand|wor'
r'shortreal|real|realtime)\b', Keyword.Type),
('[a-zA-Z_][a-zA-Z0-9_]*:(?!:)', Name.Label),
('[a-zA-Z_][a-zA-Z0-9_]*', Name),
],
'classname': [
(r'[a-zA-Z_][a-zA-Z0-9_]*', Name.Class, '#pop'),
],
'string': [
(r'"', String, '#pop'),
(r'\\([\\abfnrtv"\']|x[a-fA-F0-9]{2,4}|[0-7]{1,3})',
String.Escape),
(r'[^\\"\n]+', String), # all other characters
(r'\\\n', String), # line continuation
(r'\\', String), # stray backslash
],
'macro': [
(r'[^/\n]+', Comment.Preproc),
(r'/[*](.|\n)*?[*]/', Comment.Multiline),
(r'//.*?\n', Comment.Single, '#pop'),
(r'/', Comment.Preproc),
(r'(?<=\\)\n', Comment.Preproc),
(r'\n', Comment.Preproc, '#pop'),
],
'import': [(r'[a-zA-Z0-9_:]+\*?', Name.Namespace, '#pop')]
}
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 ErlangLexer(RegexLexer):
"""
For the Erlang functional programming language.
Blame Jeremy Thurgood (http://jerith.za.net/).
*New in Pygments 0.9.*
"""
name = 'Erlang'
aliases = ['erlang']
filenames = ['*.erl', '*.hrl']
mimetypes = ['text/x-erlang']
keywords = [
'after',
'begin',
'case',
'catch',
'cond',
'end',
'fun',
'if',
'let',
'of',
'query',
'receive',
'try',
'when',
]
builtins = [ # See erlang(3) man page
'abs', 'append_element', 'apply', 'atom_to_list', 'binary_to_list',
'bitstring_to_list', 'binary_to_term', 'bit_size', 'bump_reductions',
'byte_size', 'cancel_timer', 'check_process_code',
'delete_selectedModulee', 'demonitor', 'disconnect_node', 'display',
'element', 'erase', 'exit', 'float', 'float_to_list', 'fun_info',
'fun_to_list', 'function_exported', 'garbage_collect', 'get',
'get_keys', 'group_leader', 'hash', 'hd', 'integer_to_list',
'iolist_to_binary', 'iolist_size', 'is_atom', 'is_binary',
'is_bitstring', 'is_boolean', 'is_builtin', 'is_float', 'is_function',
'is_integer', 'is_list', 'is_number', 'is_pid', 'is_port',
'is_process_alive', 'is_record', 'is_reference', 'is_tuple', 'length',
'link', 'list_to_atom', 'list_to_binary', 'list_to_bitstring',
'list_to_existing_atom', 'list_to_float', 'list_to_integer',
'list_to_pid', 'list_to_tuple', 'load_selectedModulee',
'localtime_to_universaltime', 'make_tuple', 'md5', 'md5_final',
'md5_update', 'memory', 'selectedModulee_loaded', 'monitor',
'monitor_node', 'node', 'nodes', 'open_port', 'phash', 'phash2',
'pid_to_list', 'port_close', 'port_command', 'port_connect',
'port_control', 'port_call', 'port_info', 'port_to_list',
'process_display', 'process_flag', 'process_info',
'purge_selectedModulee', 'put', 'read_timer', 'ref_to_list',
'register', 'resume_process', 'round', 'send', 'send_after',
'send_nosuspend', 'set_cookie', 'setelement', 'size', 'spawn',
'spawn_link', 'spawn_monitor', 'spawn_opt', 'split_binary',
'start_timer', 'statistics', 'suspend_process', 'system_flag',
'system_info', 'system_monitor', 'system_profile', 'term_to_binary',
'tl', 'trace', 'trace_delivered', 'trace_info', 'trace_pattern',
'trunc', 'tuple_size', 'tuple_to_list', 'universaltime_to_localtime',
'unlink', 'unregister', 'whereis'
]
operators = r'(\+|-|\*|/|<|>|=|==|/=|=:=|=/=|=<|>=|\+\+|--|<-|!)'
word_operators = [
'and', 'andalso', 'band', 'bnot', 'bor', 'bsl', 'bsr', 'bxor', 'div',
'not', 'or', 'orelse', 'rem', 'xor'
]
atom_re = r"(?:[a-z][a-zA-Z0-9_]*|'[^\n']*[^\\]')"
variable_re = r'(?:[A-Z_][a-zA-Z0-9_]*)'
escape_re = r'(?:\\(?:[bdefnrstv\'"\\/]|[0-7][0-7]?[0-7]?|\^[a-zA-Z]))'
macro_re = r'(?:' + variable_re + r'|' + atom_re + r')'
base_re = r'(?:[2-9]|[12][0-9]|3[0-6])'
tokens = {
'root': [
(r'\s+', Text),
(r'%.*\n', Comment),
('(' + '|'.join(keywords) + r')\b', Keyword),
('(' + '|'.join(builtins) + r')\b', Name.Builtin),
('(' + '|'.join(word_operators) + r')\b', Operator.Word),
(r'^-', Punctuation, 'directive'),
(operators, Operator),
(r'"', String, 'string'),
(r'<<', Name.Label),
(r'>>', Name.Label),
(r'(' + atom_re + ')(:)', bygroups(Name.Namespace, Punctuation)),
(r'^(' + atom_re + r')(\s*)(\()',
bygroups(Name.Function, Text, Punctuation)),
(r'[+-]?' + base_re + r'#[0-9a-zA-Z]+', Number.Integer),
(r'[+-]?\d+', Number.Integer),
(r'[+-]?\d+.\d+', Number.Float),
(r'[]\[:_@\".{}()|;,]', Punctuation),
(variable_re, Name.Variable),
(atom_re, Name),
(r'\?' + macro_re, Name.Constant),
(r'\$(?:' + escape_re + r'|\\[ %]|[^\\])', String.Char),
(r'#' + atom_re + r'(:?\.' + atom_re + r')?', Name.Label),
],
'string': [
(escape_re, String.Escape),
(r'"', String, '#pop'),
(r'~[0-9.*]*[~#+bBcdefginpPswWxX]', String.Interpol),
(r'[^"\\~]+', String),
(r'~', String),
],
'directive': [
(r'(define)(\s*)(\()(' + macro_re + r')',
bygroups(Name.Entity, Text, Punctuation, Name.Constant), '#pop'),
(r'(record)(\s*)(\()(' + macro_re + r')',
bygroups(Name.Entity, Text, Punctuation, Name.Label), '#pop'),
(atom_re, Name.Entity, '#pop'),
],
}
class HaskellLexer(RegexLexer):
"""
A Haskell lexer based on the lexemes defined in the Haskell 98 Report.
*New in Pygments 0.8.*
"""
name = 'Haskell'
aliases = ['haskell', 'hs']
filenames = ['*.hs']
mimetypes = ['text/x-haskell']
reserved = [
'case', 'class', 'data', 'default', 'deriving', 'do', 'else', 'if',
'in', 'infix[lr]?', 'instance', 'let', 'newtype', 'of', 'then', 'type',
'where', '_'
]
ascii = [
'NUL', 'SOH', '[SE]TX', 'EOT', 'ENQ', 'ACK', 'BEL', 'BS', 'HT', 'LF',
'VT', 'FF', 'CR', 'S[OI]', 'DLE', 'DC[1-4]', 'NAK', 'SYN', 'ETB',
'CAN', 'EM', 'SUB', 'ESC', '[FGRU]S', 'SP', 'DEL'
]
tokens = {
'root': [
# Whitespace:
(r'\s+', Text),
#(r'--\s*|.*$', Comment.Doc),
(r'--(?![!#$%&*+./<=>?@\^|_~]).*?$', Comment.Single),
(r'{-', Comment.Multiline, 'comment'),
# Lexemes:
# Identifiers
(r'\bimport\b', Keyword.Reserved, 'import'),
(r'\bselectedModulee\b', Keyword.Reserved, 'selectedModulee'),
(r'\berror\b', Name.Exception),
(r'\b(%s)(?!\')\b' % '|'.join(reserved), Keyword.Reserved),
(r'^[_a-z][\w\']*', Name.Function),
(r'[_a-z][\w\']*', Name),
(r'[A-Z][\w\']*', Keyword.Type),
# Operators
(r'\\(?![:!#$%&*+.\\/<=>?@^|~-]+)', 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),
# Character/String Literals
(r"'", String.Char, 'character'),
(r'"', String, 'string'),
# Special
(r'\[\]', Keyword.Type),
(r'\(\)', Name.Builtin),
(r'[][(),;`{}]', Punctuation),
],
'import': [
# Import statements
(r'\s+', Text),
(r'"', String, 'string'),
# after "funclist" state
(r'\)', Punctuation, '#pop'),
(r'qualified\b', Keyword),
# import X as Y
(r'([A-Z][a-zA-Z0-9_.]*)(\s+)(as)(\s+)([A-Z][a-zA-Z0-9_.]*)',
bygroups(Name.Namespace, Text, Keyword, Text, Name), '#pop'),
# import X hiding (functions)
(r'([A-Z][a-zA-Z0-9_.]*)(\s+)(hiding)(\s+)(\()',
bygroups(Name.Namespace, Text, Keyword, Text,
Punctuation), 'funclist'),
# import X (functions)
(r'([A-Z][a-zA-Z0-9_.]*)(\s+)(\()',
bygroups(Name.Namespace, Text, Punctuation), 'funclist'),
# import X
(r'[a-zA-Z0-9_.]+', Name.Namespace, '#pop'),
],
'selectedModulee': [
(r'\s+', Text),
(r'([A-Z][a-zA-Z0-9_.]*)(\s+)(\()',
bygroups(Name.Namespace, Text, Punctuation), 'funclist'),
(r'[A-Z][a-zA-Z0-9_.]*', Name.Namespace, '#pop'),
],
'funclist': [
(r'\s+', Text),
(r'[A-Z][a-zA-Z0-9_]*', Keyword.Type),
(r'(_[\w\']+|[a-z][\w\']*)', Name.Function),
(r'--.*$', Comment.Single),
(r'{-', Comment.Multiline, 'comment'),
(r',', Punctuation),
(r'[:!#$%&*+.\\/<=>?@^|~-]+', Operator),
# (HACK, but it makes sense to push two instances, believe me)
(r'\(', Punctuation, ('funclist', 'funclist')),
(r'\)', Punctuation, '#pop:2'),
],
'comment': [
# Multiline Comments
(r'[^-{}]+', Comment.Multiline),
(r'{-', Comment.Multiline, '#push'),
(r'-}', Comment.Multiline, '#pop'),
(r'[-{}]', Comment.Multiline),
],
'character': [
# Allows multi-chars, incorrectly.
(r"[^\\']", String.Char),
(r"\\", String.Escape, 'escape'),
("'", String.Char, '#pop'),
],
'string': [
(r'[^\\"]+', String),
(r"\\", String.Escape, 'escape'),
('"', String, '#pop'),
],
'escape': [
(r'[abfnrtv"\'&\\]', String.Escape, '#pop'),
(r'\^[][A-Z@\^_]', String.Escape, '#pop'),
('|'.join(ascii), String.Escape, '#pop'),
(r'o[0-7]+', String.Escape, '#pop'),
(r'x[\da-fA-F]+', String.Escape, '#pop'),
(r'\d+', String.Escape, '#pop'),
(r'\s+\\', String.Escape, '#pop'),
],
}
class CommonLispLexer(RegexLexer):
"""
A Common Lisp lexer.
*New in Pygments 0.9.*
"""
name = 'Common Lisp'
aliases = ['common-lisp', 'cl']
filenames = ['*.cl', '*.lisp', '*.el'] # use for Elisp too
mimetypes = ['text/x-common-lisp']
flags = re.IGNORECASE | re.MULTILINE
### couple of useful regexes
# characters that are not macro-characters and can be used to begin a symbol
nonmacro = r'\\.|[a-zA-Z0-9!$%&*+-/<=>?@\[\]^_{}~]'
constituent = nonmacro + '|[#.:]'
terminated = r'(?=[ "()\'\n,;`])' # whitespace or terminating macro characters
### symbol token, reverse-engineered from hyperspec
# Take a deep breath...
symbol = r'(\|[^|]+\||(?:%s)(?:%s)*)' % (nonmacro, constituent)
def __init__(self, **options):
from plushcms.syntaxhighlight.pygments.lexers._clbuiltins import BUILTIN_FUNCTIONS, \
SPECIAL_FORMS, MACROS, LAMBDA_LIST_KEYWORDS, DECLARATIONS, \
BUILTIN_TYPES, BUILTIN_CLASSES
self.builtin_function = BUILTIN_FUNCTIONS
self.special_forms = SPECIAL_FORMS
self.macros = MACROS
self.lambda_list_keywords = LAMBDA_LIST_KEYWORDS
self.declarations = DECLARATIONS
self.builtin_types = BUILTIN_TYPES
self.builtin_classes = BUILTIN_CLASSES
RegexLexer.__init__(self, **options)
def get_tokens_unprocessed(self, text):
stack = ['root']
for index, token, value in RegexLexer.get_tokens_unprocessed(
self, text, stack):
if token is Name.Variable:
if value in self.builtin_function:
yield index, Name.Builtin, value
continue
if value in self.special_forms:
yield index, Keyword, value
continue
if value in self.macros:
yield index, Name.Builtin, value
continue
if value in self.lambda_list_keywords:
yield index, Keyword, value
continue
if value in self.declarations:
yield index, Keyword, value
continue
if value in self.builtin_types:
yield index, Keyword.Type, value
continue
if value in self.builtin_classes:
yield index, Name.Class, value
continue
yield index, token, value
tokens = {
'root' : [
('', Text, 'body'),
],
'multiline-comment' : [
(r'#\|', Comment.Multiline, '#push'), # (cf. Hyperspec 2.4.8.19)
(r'\|#', Comment.Multiline, '#pop'),
(r'[^|#]+', Comment.Multiline),
(r'[|#]', Comment.Multiline),
],
'commented-form' : [
(r'\(', Comment.Preproc, '#push'),
(r'\)', Comment.Preproc, '#pop'),
(r'[^()]+', Comment.Preproc),
],
'body' : [
# whitespace
(r'\s+', Text),
# single-line comment
(r';.*$', Comment.Single),
# multi-line comment
(r'#\|', Comment.Multiline, 'multiline-comment'),
# encoding comment (?)
(r'#\d*Y.*$', Comment.Special),
# strings and characters
(r'"(\\.|[^"\\])*"', String),
# quoting
(r":" + symbol, String.Symbol),
(r"'" + symbol, String.Symbol),
(r"'", Operator),
(r"`", Operator),
# decimal numbers
(r'[-+]?\d+\.?' + terminated, Number.Integer),
(r'[-+]?\d+/\d+' + terminated, Number),
(r'[-+]?(\d*\.\d+([defls][-+]?\d+)?|\d+(\.\d*)?[defls][-+]?\d+)' \
+ terminated, Number.Float),
# sharpsign strings and characters
(r"#\\." + terminated, String.Char),
(r"#\\" + symbol, String.Char),
# vector
(r'#\(', Operator, 'body'),
# bitstring
(r'#\d*\*[01]*', Literal.Other),
# uninterned symbol
(r'#:' + symbol, String.Symbol),
# read-time and load-time evaluation
(r'#[.,]', Operator),
# function shorthand
(r'#\'', Name.Function),
# binary rational
(r'#[bB][+-]?[01]+(/[01]+)?', Number),
# octal rational
(r'#[oO][+-]?[0-7]+(/[0-7]+)?', Number.Oct),
# hex rational
(r'#[xX][+-]?[0-9a-fA-F]+(/[0-9a-fA-F]+)?', Number.Hex),
# radix rational
(r'#\d+[rR][+-]?[0-9a-zA-Z]+(/[0-9a-zA-Z]+)?', Number),
# complex
(r'(#[cC])(\()', bygroups(Number, Punctuation), 'body'),
# array
(r'(#\d+[aA])(\()', bygroups(Literal.Other, Punctuation), 'body'),
# structure
(r'(#[sS])(\()', bygroups(Literal.Other, Punctuation), 'body'),
# path
(r'#[pP]?"(\\.|[^"])*"', Literal.Other),
# reference
(r'#\d+=', Operator),
(r'#\d+#', Operator),
# read-time comment
(r'#+nil' + terminated + '\s*\(', Comment.Preproc, 'commented-form'),
# read-time conditional
(r'#[+-]', Operator),
# special operators that should have been parsed already
(r'(,@|,|\.)', Operator),
# special constants
(r'(t|nil)' + terminated, Name.Constant),
# functions and variables
(r'\*' + symbol + '\*', Name.Variable.Global),
(symbol, Name.Variable),
# parentheses
(r'\(', Punctuation, 'body'),
(r'\)', Punctuation, '#pop'),
],
}