class GenshiTextLexer(RegexLexer):
"""
A lexer that highlights `genshi <http://genshi.edgewall.org/>`_ text
templates.
"""
name = 'Genshi Text'
aliases = ['genshitext']
mimetypes = ['application/x-genshi-text', 'text/x-genshi']
tokens = {
'root': [
(r'[^#\$\s]+', Other),
(r'^(\s*)(##.*)$', bygroups(Text, Comment)),
(r'^(\s*)(#)', bygroups(Text, Comment.Preproc), 'directive'),
include('variable'),
(r'[#\$\s]', Other),
],
'directive': [
(r'\n', Text, '#pop'),
(r'(?:def|for|if)\s+.*', using(PythonLexer), '#pop'),
(r'(choose|when|with)([^\S\n]+)(.*)',
bygroups(Keyword, Text, using(PythonLexer)), '#pop'),
(r'(choose|otherwise)\b', Keyword, '#pop'),
(r'(end\w*)([^\S\n]*)(.*)', bygroups(Keyword, Text,
Comment), '#pop'),
],
'variable': [
(r'(?<!\$)(\$\{)(.+?)(\})',
bygroups(Comment.Preproc, using(PythonLexer), Comment.Preproc)),
(r'(?<!\$)(\$)([a-zA-Z_][a-zA-Z0-9_\.]*)', Name.Variable),
]
}
class GasLexer(RegexLexer):
"""
For Gas (AT&T) assembly code.
"""
name = 'GAS'
aliases = ['gas']
filenames = ['*.s', '*.S']
mimetypes = ['text/x-gas']
#: optional Comment or Whitespace
string = r'"(\\"|[^"])*"'
char = r'[a-zA-Z$._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),
(r'/[*]', Comment, '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 GenshiMarkupLexer(RegexLexer):
"""
Base lexer for Genshi markup, used by `HtmlGenshiLexer` and
`GenshiLexer`.
"""
flags = re.DOTALL
tokens = {
'root': [
(r'[^<\$]+', Other),
(r'(<\?python)(.*?)(\?>)',
bygroups(Comment.Preproc, using(PythonLexer), Comment.Preproc)),
# yield style and script blocks as Other
(r'<\s*(script|style)\s*.*?>.*?<\s*/\1\s*>', Other),
(r'<\s*py:[a-zA-Z0-9]+', Name.Tag, 'pytag'),
(r'<\s*[a-zA-Z0-9:]+', Name.Tag, 'tag'),
include('variable'),
(r'[<\$]', Other),
],
'pytag': [
(r'\s+', Text),
(r'[a-zA-Z0-9_:-]+\s*=', Name.Attribute, 'pyattr'),
(r'/?\s*>', Name.Tag, '#pop'),
],
'pyattr': [
('(")(.*?)(")', bygroups(String, using(PythonLexer),
String), '#pop'),
("(')(.*?)(')", bygroups(String, using(PythonLexer),
String), '#pop'),
(r'[^\s>]+', String, '#pop'),
],
'tag': [
(r'\s+', Text),
(r'py:[a-zA-Z0-9_-]+\s*=', Name.Attribute, 'pyattr'),
(r'[a-zA-Z0-9_:-]+\s*=', Name.Attribute, 'attr'),
(r'/?\s*>', Name.Tag, '#pop'),
],
'attr': [('"', String, 'attr-dstring'), ("'", String, 'attr-sstring'),
(r'[^\s>]*', String, '#pop')],
'attr-dstring': [('"', String, '#pop'),
include('strings'), ("'", String)],
'attr-sstring': [("'", String, '#pop'),
include('strings'), ("'", String)],
'strings': [('[^"\'$]+', String),
include('variable')],
'variable': [
(r'(?<!\$)(\$\{)(.+?)(\})',
bygroups(Comment.Preproc, using(PythonLexer), Comment.Preproc)),
(r'(?<!\$)(\$)([a-zA-Z_][a-zA-Z0-9_\.]*)', Name.Variable),
]
}
class ObjdumpLexer(RegexLexer):
"""
For the output of 'objdump -dr'
"""
name = 'objdump'
aliases = ['objdump']
filenames = ['*.objdump']
mimetypes = ['text/x-objdump']
hex = r'[0-9A-Za-z]'
tokens = {
'root': [
# File name & format:
('(.*?)(:)( +file format )(.*?)$',
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 SmartyLexer(RegexLexer):
"""
Generic `Smarty <http://smarty.php.net/>`_ template lexer.
Just highlights smarty code between the preprocessor directives, other
data is left untouched by the lexer.
"""
name = 'Smarty'
aliases = ['smarty']
filenames = ['*.tpl']
mimetypes = ['application/x-smarty']
flags = re.MULTILINE | re.DOTALL
tokens = {
'root': [(r'[^{]+', Other),
(r'(\{)(\*.*?\*)(\})',
bygroups(Comment.Preproc, Comment, Comment.Preproc)),
(r'(\{php\})(.*?)(\{/php\})',
bygroups(Comment.Preproc, using(PhpLexer, startinline=True),
Comment.Preproc)),
(r'(\{)(/?[a-zA-Z_][a-zA-Z0-9_]*)(\s*)',
bygroups(Comment.Preproc, Name.Function, Text), 'smarty'),
(r'\{', Comment.Preproc, 'smarty')],
'smarty':
[(r'\s+', Text), (r'\}', Comment.Preproc, '#pop'),
(r'#[a-zA-Z_][a-zA-Z0-9_]*#', Name.Variable),
(r'\$[a-zA-Z_][a-zA-Z0-9_]*(\.[a-zA-Z0-9_]+)*', Name.Variable),
(r'[~!%^&*()+=|\[\]:;,.<>/?{}@-]', Operator),
('(true|false|null)\b', Keyword.Constant),
(r"[0-9](\.[0-9]*)?(eE[+-][0-9])?[flFLdD]?|"
r"0[xX][0-9a-fA-F]+[Ll]?", Number),
(r'"(\\\\|\\"|[^"])*"', String.Double),
(r"'(\\\\|\\'|[^'])*'", String.Single),
(r'[a-zA-Z_][a-zA-Z0-9_]*', Name.Attribute)]
}
def analyse_text(text):
rv = 0.0
if re.search('\{if\s+.*?\}.*?\{/if\}', text):
rv += 0.15
if re.search('\{include\s+file=.*?\}', text):
rv += 0.15
if re.search('\{foreach\s+.*?\}.*?\{/foreach\}', text):
rv += 0.15
if re.search('\{\$.*?\}', text):
rv += 0.01
return rv
class EvoqueLexer(RegexLexer):
"""
For files using the Evoque templating system.
*New in Pygments 1.1.*
"""
name = 'Evoque'
aliases = ['evoque']
filenames = ['*.evoque']
mimetypes = ['application/x-evoque']
flags = re.DOTALL
tokens = {
'root': [
(r'[^#$]+', Other),
(r'#\[', Comment.Multiline, 'comment'),
(r'\$\$', Other),
# svn keywords
(r'\$\w+:[^$\n]*\$', Comment.Multiline),
# directives: begin, end
(r'(\$)(begin|end)(\{(%)?)(.*?)((?(4)%)\})',
bygroups(Punctuation, Name.Builtin, Punctuation, None, String,
Punctuation, None)),
# directives: evoque, overlay
# see doc for handling first name arg: /directives/evoque/
#+ minor inconsistency: the "name" in e.g. $overlay{name=site_base}
# should be using(PythonLexer), not passed out as String
(r'(\$)(evoque|overlay)(\{(%)?)(\s*[#\w\-"\'.]+[^=,%}]+?)?'
r'(.*?)((?(4)%)\})',
bygroups(Punctuation, Name.Builtin, Punctuation, None, String,
using(PythonLexer), Punctuation, None)),
# directives: if, for, prefer, test
(r'(\$)(\w+)(\{(%)?)(.*?)((?(4)%)\})',
bygroups(Punctuation, Name.Builtin, Punctuation, None,
using(PythonLexer), Punctuation, None)),
# directive clauses (no {} expression)
(r'(\$)(else|rof|fi)', bygroups(Punctuation, Name.Builtin)),
# expressions
(r'(\$\{(%)?)(.*?)((!)(.*?))?((?(2)%)\})',
bygroups(Punctuation, None, using(PythonLexer), Name.Builtin,
None, None, Punctuation, None)),
(r'#', Other),
],
'comment': [(r'[^\]#]', Comment.Multiline),
(r'#\[', Comment.Multiline, '#push'),
(r'\]#', Comment.Multiline, '#pop'),
(r'[\]#]', Comment.Multiline)],
}
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 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]*|[0-9a-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'COMMON|CPU|GROUP|UPPERCASE|IMPORT|EXPORT|LIBRARY|MODULE')
flags = re.IGNORECASE | re.MULTILINE
tokens = {
'root': [
include('whitespace'), (r'^\s*%', Comment.Preproc, 'preproc'),
(identifier + ':', Name.Label),
(directives, Keyword, 'instruction-args'),
(r'(%s)\s+(equ)' % identifier,
bygroups(Name.Constant, 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),
(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'[$]+', Keyword.Constant), (wordop, Operator.Word),
(type, Keyword.Type)],
}
class CheetahLexer(RegexLexer):
"""
Generic `cheetah templates`_ lexer. Code that isn't Cheetah
markup is yielded as `Token.Other`. This also works for
`spitfire templates`_ which use the same syntax.
.. _cheetah templates: http://www.cheetahtemplate.org/
.. _spitfire templates: http://code.google.com/p/spitfire/
"""
name = 'Cheetah'
aliases = ['cheetah', 'spitfire']
filenames = ['*.tmpl', '*.spt']
mimetypes = ['application/x-cheetah', 'application/x-spitfire']
tokens = {
'root': [
(r'(##[^\n]*)$', (bygroups(Comment))),
(r'#[*](.|\n)*?[*]#', Comment),
(r'#end[^#\n]*(?:#|$)', Comment.Preproc),
(r'#slurp$', Comment.Preproc),
(r'(#[a-zA-Z]+)([^#\n]*)(#|$)',
(bygroups(Comment.Preproc, using(CheetahPythonLexer),
Comment.Preproc))),
# TODO support other Python syntax like $foo['bar']
(r'(\$)([a-zA-Z_][a-zA-Z0-9_\.]*[a-zA-Z0-9_])',
bygroups(Comment.Preproc, using(CheetahPythonLexer))),
(r'(\$\{!?)(.*?)(\})(?s)',
bygroups(Comment.Preproc, using(CheetahPythonLexer),
Comment.Preproc)),
(r'''(?sx)
(.+?) # anything, followed by:
(?:
(?=[#][#a-zA-Z]*) | # an eval comment
(?=\$[a-zA-Z_{]) | # a substitution
\Z # end of string
)
''', Other),
(r'\s+', Text),
],
}
class MyghtyLexer(RegexLexer):
"""
Generic `myghty templates`_ lexer. Code that isn't Myghty
markup is yielded as `Token.Other`.
*New in Pygments 0.6.*
.. _myghty templates: http://www.myghty.org/
"""
name = 'Myghty'
aliases = ['myghty']
filenames = ['*.myt', 'autodelegate']
mimetypes = ['application/x-myghty']
tokens = {
'root': [
(r'\s+', Text),
(r'(<%(def|method))(\s*)(.*?)(>)(.*?)(</%\2\s*>)(?s)',
bygroups(Name.Tag, None, Text, Name.Function, Name.Tag,
using(this), Name.Tag)),
(r'(<%(\w+))(.*?)(>)(.*?)(</%\2\s*>)(?s)',
bygroups(Name.Tag, None, Name.Function, Name.Tag,
using(PythonLexer), Name.Tag)),
(r'(<&[^|])(.*?)(,.*?)?(&>)',
bygroups(Name.Tag, Name.Function, using(PythonLexer), Name.Tag)),
(r'(<&\|)(.*?)(,.*?)?(&>)(?s)',
bygroups(Name.Tag, Name.Function, using(PythonLexer), Name.Tag)),
(r'</&>', Name.Tag),
(r'(<%!?)(.*?)(%>)(?s)',
bygroups(Name.Tag, using(PythonLexer), Name.Tag)),
(r'(?<=^)#[^\n]*(\n|\Z)', Comment),
(r'(?<=^)(%)([^\n]*)(\n|\Z)',
bygroups(Name.Tag, using(PythonLexer), Other)),
(r"""(?sx)
(.+?) # anything, followed by:
(?:
(?<=\n)(?=[%#]) | # an eval or comment line
(?=</?[%&]) | # a substitution or block or
# call start or end
# - don't consume
(\\\n) | # an escaped newline
\Z # end of string
)""", bygroups(Other, Operator)),
]
}
class MxmlLexer(RegexLexer):
"""
For MXML markup.
Nested AS3 in <script> tags is highlighted by the appropriate lexer.
"""
flags = re.MULTILINE | re.DOTALL
name = 'MXML'
aliases = ['mxml']
filenames = ['*.mxml']
mimetimes = ['text/xml', 'application/xml']
tokens = {
'root': [
('[^<&]+', Text),
(r'&\S*?;', Name.Entity),
(r'(\<\!\[CDATA\[)(.*?)(\]\]\>)',
bygroups(String, using(ActionScript3Lexer), String)),
('<!--', Comment, 'comment'),
(r'<\?.*?\?>', Comment.Preproc),
('<![^>]*>', Comment.Preproc),
(r'<\s*[a-zA-Z0-9:._-]+', Name.Tag, 'tag'),
(r'<\s*/\s*[a-zA-Z0-9:._-]+\s*>', Name.Tag),
],
'comment': [
('[^-]+', Comment),
('-->', Comment, '#pop'),
('-', Comment),
],
'tag': [
(r'\s+', Text),
(r'[a-zA-Z0-9_.:-]+\s*=', Name.Attribute, 'attr'),
(r'/?\s*>', Name.Tag, '#pop'),
],
'attr': [
('\s+', Text),
('".*?"', String, '#pop'),
("'.*?'", String, '#pop'),
(r'[^\s>]+', String, '#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 pygments3.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'),
],
}
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 list(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),
(r'/[*](.|\n)*?[*]/', Comment),
(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',
list(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 ActionScript3Lexer(RegexLexer):
"""
For ActionScript 3 source code.
*New in Pygments 0.11.*
"""
name = 'ActionScript 3'
aliases = ['as3', 'actionscript3']
filenames = ['*.as']
mimetypes = [
'application/x-actionscript', 'text/x-actionscript',
'text/actionscript'
]
identifier = r'[$a-zA-Z_][a-zA-Z0-9_]*'
flags = re.DOTALL | re.MULTILINE
tokens = {
'root': [
(r'\s+', Text),
(r'(function\s+)(' + identifier + r')(\s*)(\()',
bygroups(Keyword.Declaration, Name.Function, Text,
Operator), 'funcparams'),
(r'(var|const)(\s+)(' + identifier + r')(\s*)(:)(\s*)(' +
identifier + r')',
bygroups(Keyword.Declaration, Text, Name, Text, Punctuation, Text,
Keyword.Type)),
(r'(import|package)(\s+)((?:' + identifier + r'|\.)+)(\s*)',
bygroups(Keyword, Text, Name.Namespace, Text)),
(r'(new)(\s+)(' + identifier + r')(\s*)(\()',
bygroups(Keyword, Text, Keyword.Type, Text, Operator)),
(r'//.*?\n', Comment.Single),
(r'/\*.*?\*/', Comment.Multiline),
(r'/(\\\\|\\/|[^\n])*/[gisx]*', String.Regex),
(r'(\.)(' + identifier + r')', bygroups(Operator, Name.Attribute)),
(r'(case|default|for|each|in|while|do|break|return|continue|if|else|'
r'throw|try|catch|with|new|typeof|arguments|instanceof|this|'
r'switch|import|include|as|is)\b', Keyword),
(r'(class|public|final|internal|native|override|private|protected|'
r'static|import|extends|implements|interface|intrinsic|return|super|'
r'dynamic|function|const|get|namespace|package|set)\b',
Keyword.Declaration),
(r'(true|false|null|NaN|Infinity|-Infinity|undefined|void)\b',
Keyword.Constant),
(r'(decodeURI|decodeURIComponent|encodeURI|escape|eval|isFinite|isNaN|'
r'isXMLName|clearInterval|fscommand|getTimer|getURL|getVersion|'
r'isFinite|parseFloat|parseInt|setInterval|trace|updateAfterEvent|'
r'unescape)\b', Name.Function),
(identifier, Name),
(r'[0-9][0-9]*\.[0-9]+([eE][0-9]+)?[fd]?', Number.Float),
(r'0x[0-9a-f]+', Number.Hex),
(r'[0-9]+', Number.Integer),
(r'"(\\\\|\\"|[^"])*"', String.Double),
(r"'(\\\\|\\'|[^'])*'", String.Single),
(r'[~\^\*!%&<>\|+=:;,/?\\{}\[\]();.-]+', Operator),
],
'funcparams': [(r'\s+', Text),
(r'(\s*)(\.\.\.)?(' + identifier + r')(\s*)(:)(\s*)(' +
identifier + r'|\*)(\s*)',
bygroups(Text, Punctuation, Name, Text, Operator, Text,
Keyword.Type, Text), 'defval'),
(r'\)', Operator, 'type')],
'type': [(r'(\s*)(:)(\s*)(' + identifier + r'|\*)',
bygroups(Text, Operator, Text, Keyword.Type), '#pop:2'),
(r'\s*', Text, '#pop:2')],
'defval': [(r'(=)(\s*)([^(),]+)(\s*)(,?)',
bygroups(Operator, Text, using(this), Text,
Operator), '#pop'), (r',?', Operator, '#pop')]
}
def analyse_text(text):
if re.match(r'\w+\s*:\s*\w', text): return 0.3
return 0.1
class PhpLexer(RegexLexer):
"""
For `PHP <http://www.php.net/>`_ source code.
For PHP embedded in HTML, use the `HtmlPhpLexer`.
Additional options accepted:
`startinline`
If given and ``True`` the lexer starts highlighting with
php code (i.e.: no starting ``<?php`` required). The default
is ``False``.
`funcnamehighlighting`
If given and ``True``, highlight builtin function names
(default: ``True``).
`disabledmodules`
If given, must be a list of module names whose function names
should not be highlighted. By default all modules are highlighted
except the special ``'unknown'`` module that includes functions
that are known to php but are undocumented.
To get a list of allowed modules have a look into the
`_phpbuiltins` module:
.. sourcecode:: pycon
>>> from pygments3.lexers._phpbuiltins import MODULES
>>> MODULES.keys()
['PHP Options/Info', 'Zip', 'dba', ...]
In fact the names of those modules match the module names from
the php documentation.
"""
name = 'PHP'
aliases = ['php', 'php3', 'php4', 'php5']
filenames = ['*.php', '*.php[345]']
mimetypes = ['text/x-php']
flags = re.IGNORECASE | re.DOTALL | re.MULTILINE
tokens = {
'root': [(r'<\?(php)?', Comment.Preproc, 'php'), (r'[^<]+', Other),
(r'<', Other)],
'php': [
(r'\?>', Comment.Preproc, '#pop'),
(r'<<<([a-zA-Z_][a-zA-Z0-9_]*)\n.*?\n\1\;?\n', String),
(r'\s+', Text),
(r'#.*?\n', Comment),
(r'//.*?\n', Comment),
(r'/\*\*/',
Comment), # put the empty comment here, it is otherwise
# seen as the start of a docstring
(r'/\*\*.*?\*/', String.Doc),
(r'/\*.*?\*/', Comment),
(r'(->|::)(\s*)([a-zA-Z_][a-zA-Z0-9_]*)',
bygroups(Operator, Text, Name.Attribute)),
(r'[~!%^&*+=|:.<>/?@-]+', Operator),
(r'[\[\]{}();,]+', Punctuation),
(r'(class)(\s+)', bygroups(Keyword, Text), 'classname'),
(r'(function)(\s+)(&?)(\s*)',
bygroups(Keyword, Text, Operator, Text), 'functionname'),
(r'(const)(\s+)([a-zA-Z_][a-zA-Z0-9_]*)',
bygroups(Keyword, Text, Name.Constant)),
(r'(and|E_PARSE|old_function|E_ERROR|or|as|E_WARNING|parent|'
r'eval|PHP_OS|break|exit|case|extends|PHP_VERSION|cfunction|'
r'FALSE|print|for|require|continue|foreach|require_once|'
r'declare|return|default|static|do|switch|die|stdClass|'
r'echo|else|TRUE|elseif|var|empty|if|xor|enddeclare|include|'
r'virtual|endfor|include_once|while|endforeach|global|__FILE__|'
r'endif|list|__LINE__|endswitch|new|__sleep|endwhile|not|'
r'array|__wakeup|E_ALL|NULL|final|php_user_filter|interface|'
r'implements|public|private|protected|abstract|clone|try|'
r'catch|throw|this)\b', Keyword),
('(true|false|null)\b', Keyword.Constant),
(r'\$\{\$+[a-zA-Z_][a-zA-Z0-9_]*\}', Name.Variable),
(r'\$+[a-zA-Z_][a-zA-Z0-9_]*', Name.Variable),
('[a-zA-Z_][a-zA-Z0-9_]*', Name.Other),
(r"[0-9](\.[0-9]*)?(eE[+-][0-9])?[flFLdD]?|"
r"0[xX][0-9a-fA-F]+[Ll]?", Number),
(r"'([^'\\]*(?:\\.[^'\\]*)*)'", String.Single),
(r'`([^`\\]*(?:\\.[^`\\]*)*)`', String.Backtick),
(r'"', String.Double, 'string'),
],
'classname': [(r'[a-zA-Z_][a-zA-Z0-9_]*', Name.Class, '#pop')],
'functionname': [(r'[a-zA-Z_][a-zA-Z0-9_]*', Name.Function, '#pop')],
'string':
[(r'"', String.Double, '#pop'), (r'[^{$"\\]+', String.Double),
(r'\\([nrt\"$]|[0-7]{1,3}|x[0-9A-Fa-f]{1,2})', String.Escape),
(r'\$[a-zA-Z_][a-zA-Z0-9_]*(\[\S+\]|->[a-zA-Z_][a-zA-Z0-9_]*)?',
String.Interpol),
(r'(\{\$\{)(.*?)(\}\})',
bygroups(String.Interpol, using(this, _startinline=True),
String.Interpol)),
(r'(\{)(\$.*?)(\})',
bygroups(String.Interpol, using(this, _startinline=True),
String.Interpol)),
(r'(\$\{)(\S+)(\})',
bygroups(String.Interpol, Name.Variable, String.Interpol)),
(r'[${\\]+', String.Double)],
}
def __init__(self, **options):
self.funcnamehighlighting = get_bool_opt(options,
'funcnamehighlighting', True)
self.disabledmodules = get_list_opt(options, 'disabledmodules',
['unknown'])
self.startinline = get_bool_opt(options, 'startinline', False)
# private option argument for the lexer itself
if '_startinline' in options:
self.startinline = options.pop('_startinline')
# collect activated functions in a set
self._functions = set()
if self.funcnamehighlighting:
from pygments3.lexers._phpbuiltins import MODULES
for key, value in MODULES.items():
if key not in self.disabledmodules:
self._functions.update(value)
RegexLexer.__init__(self, **options)
def get_tokens_unprocessed(self, text):
stack = ['root']
if self.startinline:
stack.append('php')
for index, token, value in \
RegexLexer.get_tokens_unprocessed(self, text, stack):
if token is Name.Other:
if value in self._functions:
yield index, Name.Builtin, value
continue
yield index, token, value
def analyse_text(text):
rv = 0.0
if re.search(r'<\?(?!xml)', text):
rv += 0.3
if '?>' in text:
rv += 0.1
return rv
class MakoLexer(RegexLexer):
"""
Generic `mako templates`_ lexer. Code that isn't Mako
markup is yielded as `Token.Other`.
*New in Pygments 0.7.*
.. _mako templates: http://www.makotemplates.org/
"""
name = 'Mako'
aliases = ['mako']
filenames = ['*.mao']
mimetypes = ['application/x-mako']
tokens = {
'root': [
(r'(\s*)(%)(\s*end(?:\w+))(\n|\Z)',
bygroups(Text, Comment.Preproc, Keyword, Other)),
(r'(\s*)(%)([^\n]*)(\n|\Z)',
bygroups(Text, Comment.Preproc, using(PythonLexer), Other)),
(r'(\s*)(##[^\n]*)(\n|\Z)', bygroups(Text, Comment.Preproc,
Other)),
(r'(?s)<%doc>.*?</%doc>', Comment.Preproc),
(r'(<%)([\w\.\:]+)', bygroups(Comment.Preproc,
Name.Builtin), 'tag'),
(r'(</%)([\w\.\:]+)(>)',
bygroups(Comment.Preproc, Name.Builtin, Comment.Preproc)),
(r'<%(?=([\w\.\:]+))', Comment.Preproc, 'ondeftags'),
(r'(<%(?:!?))(.*?)(%>)(?s)',
bygroups(Comment.Preproc, using(PythonLexer), Comment.Preproc)),
(r'(\$\{)(.*?)(\})',
bygroups(Comment.Preproc, using(PythonLexer), Comment.Preproc)),
(r'''(?sx)
(.+?) # anything, followed by:
(?:
(?<=\n)(?=%|\#\#) | # an eval or comment line
(?=\#\*) | # multiline comment
(?=</?%) | # a python block
# call start or end
(?=\$\{) | # a substitution
(?<=\n)(?=\s*%) |
# - don't consume
(\\\n) | # an escaped newline
\Z # end of string
)
''', bygroups(Other, Operator)),
(r'\s+', Text),
],
'ondeftags': [
(r'<%', Comment.Preproc),
(r'(?<=<%)(include|inherit|namespace|page)', Name.Builtin),
include('tag'),
],
'tag': [
(r'((?:\w+)\s*=)\s*(".*?")', bygroups(Name.Attribute, String)),
(r'/?\s*>', Comment.Preproc, '#pop'),
(r'\s+', Text),
],
'attr': [
('".*?"', String, '#pop'),
("'.*?'", String, '#pop'),
(r'[^\s>]+', String, '#pop'),
],
}
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|Const|Continue|CSByte|CShort|'
r'CSng|CStr|CType|CUInt|CULng|CUShort|Declare|'
r'Default|Delegate|Dim|DirectCast|Do|Each|Else|ElseIf|'
r'End|EndIf|Enum|Erase|Error|Event|Exit|False|Finally|For|'
r'Friend|Function|Get|Global|GoSub|GoTo|Handles|If|'
r'Implements|Imports|Inherits|Interface|'
r'Let|Lib|Loop|Me|Module|MustInherit|'
r'MustOverride|MyBase|MyClass|Namespace|Narrowing|New|Next|'
r'Not|Nothing|NotInheritable|NotOverridable|Of|On|'
r'Operator|Option|Optional|Overloads|Overridable|'
r'Overrides|ParamArray|Partial|Private|Property|Protected|'
r'Public|RaiseEvent|ReadOnly|ReDim|RemoveHandler|Resume|'
r'Return|Select|Set|Shadows|Shared|Single|'
r'Static|Step|Stop|Structure|Sub|SyncLock|Then|'
r'Throw|To|True|Try|TryCast|Wend|'
r'Using|When|While|Widening|With|WithEvents|'
r'WriteOnly)\b', Keyword),
(r'(?<!\.)(Function|Sub|Property)(\s+)', bygroups(Keyword, Text),
'funcname'),
(r'(?<!\.)(Class|Structure|Enum)(\s+)', bygroups(Keyword, Text),
'classname'),
(r'(?<!\.)(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_]*[%&@!#$]?', Name),
('#.*?#', Literal.Date),
(r'(\d+\.\d*|\d*\.\d+)([fF][+-]?[0-9]+)?', Number.Float),
(r'\d+([SILDFR]|US|UI|UL)?', Number.Integer),
(r'&H[0-9a-f]+([SILDFR]|US|UI|UL)?', Number.Integer),
(r'&O[0-7]+([SILDFR]|US|UI|UL)?', Number.Integer),
(r'_\n', Text), # Line continuation
],
'string': [
(r'""', String),
(r'"C?', String, '#pop'),
(r'[^"]+', String),
],
'funcname': [(r'[a-z_][a-z0-9_]*', Name.Function, '#pop')],
'classname': [(r'[a-z_][a-z0-9_]*', Name.Class, '#pop')],
'namespace': [(r'[a-z_][a-z0-9_.]*', Name.Namespace, '#pop')],
}
class HaskellLexer(RegexLexer):
"""
A Haskell lexer based on the lexemes defined in the Haskell 98 Report.
*New in Pygments 0.8.*
"""
name = 'Haskell'
aliases = ['haskell', 'hs']
filenames = ['*.hs']
mimetypes = ['text/x-haskell']
reserved = ['case','class','data','default','deriving','do','else',
'if','in','infix[lr]?','instance',
'let','newtype','of','then','type','where','_']
ascii = ['NUL','SOH','[SE]TX','EOT','ENQ','ACK',
'BEL','BS','HT','LF','VT','FF','CR','S[OI]','DLE',
'DC[1-4]','NAK','SYN','ETB','CAN',
'EM','SUB','ESC','[FGRU]S','SP','DEL']
tokens = {
'root': [
# Whitespace:
(r'\s+', Text),
#(r'--\s*|.*$', Comment.Doc),
(r'--.*$', Comment.Single),
(r'{-', Comment.Multiline, 'comment'),
# Lexemes:
# Identifiers
(r'\bimport\b', Keyword.Reserved, 'import'),
(r'\bmodule\b', Keyword.Reserved, 'module'),
(r'\berror\b', Name.Exception),
(r'\b(%s)(?!\')\b' % '|'.join(reserved), Keyword.Reserved),
(r'^[_a-z][\w\']*', Name.Function),
(r'[_a-z][\w\']*', Name),
(r'[A-Z][\w\']*', Keyword.Type),
# Operators
(r'\\(?![:!#$%&*+.\\/<=>?@^|~-]+)', 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),
# 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'),
],
'module': [
(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'[_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'\n\s+\\', String.Escape, '#pop'),
],
}
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 7.4.0.336 (R2007a):
(r'(break|case|catch|classdef|continue|else|elseif|end|for|function|'
r'global|if|otherwise|parfor|persistent|return|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\)\]]+)(\')', bygroups(Text, Operator)),
(r'\'', 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 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_module',
'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_module', 'localtime_to_universaltime', 'make_tuple', 'md5',
'md5_final', 'md5_update', 'memory', 'module_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_module',
'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 DjangoLexer(RegexLexer):
"""
Generic `django <http://www.djangoproject.com/documentation/templates/>`_
and `jinja <http://wsgiarea.pocoo.org/jinja/>`_ template lexer.
It just highlights django/jinja code between the preprocessor directives,
other data is left untouched by the lexer.
"""
name = 'Django/Jinja'
aliases = ['django', 'jinja']
mimetypes = ['application/x-django-templating', 'application/x-jinja']
flags = re.M | re.S
tokens = {
'root': [
(r'[^{]+', Other),
(r'\{\{', Comment.Preproc, 'var'),
# jinja/django comments
(r'\{[*#].*?[*#]\}', Comment),
# django comments
(r'(\{%)(-?\s*)(comment)(\s*-?)(%\})(.*?)'
r'(\{%)(-?\s*)(endcomment)(\s*-?)(%\})',
bygroups(Comment.Preproc, Text, Keyword, Text, Comment.Preproc,
Comment, Comment.Preproc, Text, Keyword, Text,
Comment.Preproc)),
# raw jinja blocks
(r'(\{%)(-?\s*)(raw)(\s*-?)(%\})(.*?)'
r'(\{%)(-?\s*)(endraw)(\s*-?)(%\})',
bygroups(Comment.Preproc, Text, Keyword, Text, Comment.Preproc,
Text, Comment.Preproc, Text, Keyword, Text,
Comment.Preproc)),
# filter blocks
(r'(\{%)(-?\s*)(filter)(\s+)([a-zA-Z_][a-zA-Z0-9_]*)',
bygroups(Comment.Preproc, Text, Keyword, Text,
Name.Function), 'block'),
(r'(\{%)(-?\s*)([a-zA-Z_][a-zA-Z0-9_]*)',
bygroups(Comment.Preproc, Text, Keyword), 'block'),
(r'\{', Other)
],
'varnames': [
(r'(\|)(\s*)([a-zA-Z_][a-zA-Z0-9_]*)',
bygroups(Operator, Text, Name.Function)),
(r'(is)(\s+)(not)?(\s+)?([a-zA-Z_][a-zA-Z0-9_]*)',
bygroups(Keyword, Text, Keyword, Text, Name.Function)),
(r'(_|true|false|none|True|False|None)\b', Keyword.Pseudo),
(r'(in|as|reversed|recursive|not|and|or|is|if|else|import|'
r'with(?:(?:out)?\s*context)?)\b', Keyword),
(r'(loop|block|super|forloop)\b', Name.Builtin),
(r'[a-zA-Z][a-zA-Z0-9_]*', Name.Variable),
(r'\.[a-zA-Z0-9_]+', Name.Variable),
(r':?"(\\\\|\\"|[^"])*"', String.Double),
(r":?'(\\\\|\\'|[^'])*'", String.Single),
(r'([{}()\[\]+\-*/,:]|[><=]=?)', Operator),
(r"[0-9](\.[0-9]*)?(eE[+-][0-9])?[flFLdD]?|"
r"0[xX][0-9a-fA-F]+[Ll]?", Number),
],
'var': [(r'\s+', Text),
(r'(-?)(\}\})', bygroups(Text, Comment.Preproc), '#pop'),
include('varnames')],
'block': [(r'\s+', Text),
(r'(-?)(%\})', bygroups(Text, Comment.Preproc), '#pop'),
include('varnames'), (r'.', Punctuation)]
}
def analyse_text(text):
rv = 0.0
if re.search(r'\{%\s*(block|extends)', text) is not None:
rv += 0.4
if re.search(r'\{%\s*if\s*.*?%\}', text) is not None:
rv += 0.1
if re.search(r'\{\{.*?\}\}', text) is not None:
rv += 0.1
return rv
