class DockerLexer(RegexLexer):
"""
Lexer for `Docker <http://docker.io>`_ configuration files.
.. versionadded:: 2.0
"""
name = 'Docker'
aliases = ['docker', 'dockerfile']
filenames = ['Dockerfile', '*.docker']
mimetypes = ['text/x-dockerfile-config']
_keywords = (r'(?:FROM|MAINTAINER|EXPOSE|WORKDIR|USER|STOPSIGNAL)')
_bash_keywords = (r'(?:RUN|CMD|ENTRYPOINT|ENV|ARG|LABEL|ADD|COPY)')
_lb = r'(?:\s*\\?\s*)' # dockerfile line break regex
flags = re.IGNORECASE | re.MULTILINE
tokens = {
'root': [
(r'#.*', Comment),
(r'(ONBUILD)(%s)' % (_lb, ), bygroups(Keyword, using(BashLexer))),
(r'(HEALTHCHECK)((%s--\w+=\w+%s)*)' % (_lb, _lb),
bygroups(Keyword, using(BashLexer))),
(r'(VOLUME|ENTRYPOINT|CMD|SHELL)(%s)(\[.*?\])' % (_lb, ),
bygroups(Keyword, using(BashLexer), using(JsonLexer))),
(r'(LABEL|ENV|ARG)((%s\w+=\w+%s)*)' % (_lb, _lb),
bygroups(Keyword, using(BashLexer))),
(r'(%s|VOLUME)\b(.*)' % (_keywords), bygroups(Keyword, String)),
(r'(%s)' % (_bash_keywords, ), Keyword),
(r'(.*\\\n)*.+', using(BashLexer)),
]
}
class TypoScriptCssDataLexer(RegexLexer):
"""
Lexer that highlights markers, constants and registers within css blocks.
.. versionadded:: 2.2
"""
name = 'TypoScriptCssData'
aliases = ['typoscriptcssdata']
tokens = {
'root': [
# marker: ###MARK###
(r'(.*)(###\w+###)(.*)', bygroups(String, Name.Constant, String)),
# constant: {$some.constant}
(r'(\{)(\$)((?:[\w\-]+\.)*)([\w\-]+)(\})',
bygroups(String.Symbol, Operator, Name.Constant, Name.Constant,
String.Symbol)), # constant
# constant: {register:somevalue}
(r'(.*)(\{)([\w\-]+)(\s*:\s*)([\w\-]+)(\})(.*)',
bygroups(String, String.Symbol, Name.Constant, Operator,
Name.Constant, String.Symbol, String)), # constant
# whitespace
(r'\s+', Text),
# comments
(r'/\*(?:(?!\*/).)*\*/', Comment),
(r'(?<!(#|\'|"))(?:#(?!(?:[a-fA-F0-9]{6}|[a-fA-F0-9]{3}))[^\n#]+|//[^\n]*)',
Comment),
# other
(r'[<>,:=.*%+|]', String),
(r'[\w"\-!/&;(){}]+', String),
]
}
class GettextLexer(RegexLexer):
"""
Lexer for Gettext catalog files.
.. versionadded:: 0.9
"""
name = 'Gettext Catalog'
aliases = ['pot', 'po']
filenames = ['*.pot', '*.po']
mimetypes = ['application/x-gettext', 'text/x-gettext', 'text/gettext']
tokens = {
'root': [
(r'^#,\s.*?$', Keyword.Type),
(r'^#:\s.*?$', Keyword.Declaration),
# (r'^#$', Comment),
(r'^(#|#\.\s|#\|\s|#~\s|#\s).*$', Comment.Single),
(r'^(")([A-Za-z-]+:)(.*")$',
bygroups(String, Name.Property, String)),
(r'^".*"$', String),
(r'^(msgid|msgid_plural|msgstr|msgctxt)(\s+)(".*")$',
bygroups(Name.Variable, Text, String)),
(r'^(msgstr\[)(\d)(\])(\s+)(".*")$',
bygroups(Name.Variable, Number.Integer, Name.Variable, Text, String)),
]
}
class ProtoBufLexer(RegexLexer):
"""
Lexer for `Protocol Buffer <http://code.google.com/p/protobuf/>`_
definition files.
.. versionadded:: 1.4
"""
name = 'Protocol Buffer'
aliases = ['protobuf', 'proto']
filenames = ['*.proto']
tokens = {
'root': [
(r'[ \t]+', Text),
(r'[,;{}\[\]()<>]', Punctuation),
(r'/(\\\n)?/(\n|(.|\n)*?[^\\]\n)', Comment.Single),
(r'/(\\\n)?\*(.|\n)*?\*(\\\n)?/', Comment.Multiline),
(words((
'import', 'option', 'optional', 'required', 'repeated', 'default',
'packed', 'ctype', 'extensions', 'to', 'max', 'rpc', 'returns',
'oneof'), prefix=r'\b', suffix=r'\b'),
Keyword),
(words((
'int32', 'int64', 'uint32', 'uint64', 'sint32', 'sint64',
'fixed32', 'fixed64', 'sfixed32', 'sfixed64',
'float', 'double', 'bool', 'string', 'bytes'), suffix=r'\b'),
Keyword.Type),
(r'(true|false)\b', Keyword.Constant),
(r'(package)(\s+)', bygroups(Keyword.Namespace, Text), 'package'),
(r'(message|extend)(\s+)',
bygroups(Keyword.Declaration, Text), 'message'),
(r'(enum|group|service)(\s+)',
bygroups(Keyword.Declaration, Text), 'type'),
(r'\".*?\"', String),
(r'\'.*?\'', String),
(r'(\d+\.\d*|\.\d+|\d+)[eE][+-]?\d+[LlUu]*', Number.Float),
(r'(\d+\.\d*|\.\d+|\d+[fF])[fF]?', Number.Float),
(r'(\-?(inf|nan))\b', Number.Float),
(r'0x[0-9a-fA-F]+[LlUu]*', Number.Hex),
(r'0[0-7]+[LlUu]*', Number.Oct),
(r'\d+[LlUu]*', Number.Integer),
(r'[+-=]', Operator),
(r'([a-zA-Z_][\w.]*)([ \t]*)(=)',
bygroups(Name.Attribute, Text, Operator)),
(r'[a-zA-Z_][\w.]*', Name),
],
'package': [
(r'[a-zA-Z_]\w*', Name.Namespace, '#pop'),
default('#pop'),
],
'message': [
(r'[a-zA-Z_]\w*', Name.Class, '#pop'),
default('#pop'),
],
'type': [
(r'[a-zA-Z_]\w*', Name, '#pop'),
default('#pop'),
],
}
class PropertiesLexer(RegexLexer):
"""
Lexer for configuration files in Java's properties format.
Note: trailing whitespace counts as part of the value as per spec
.. versionadded:: 1.4
"""
name = 'Properties'
aliases = ['properties', 'jproperties']
filenames = ['*.properties']
mimetypes = ['text/x-java-properties']
tokens = {
'root': [
(r'^(\w+)([ \t])(\w+\s*)$', bygroups(Name.Attribute, Text,
String)),
(r'^\w+(\\[ \t]\w*)*$', Name.Attribute),
(r'(^ *)([#!].*)', bygroups(Text, Comment)),
# More controversial comments
(r'(^ *)((?:;|//).*)', bygroups(Text, Comment)),
(r'(.*?)([ \t]*)([=:])([ \t]*)(.*(?:(?<=\\)\n.*)*)',
bygroups(Name.Attribute, Text, Operator, Text, String)),
(r'\s', Text),
],
}
class ApacheConfLexer(RegexLexer):
"""
Lexer for configuration files following the Apache config file
format.
.. versionadded:: 0.6
"""
name = 'ApacheConf'
aliases = ['apacheconf', 'aconf', 'apache']
filenames = ['.htaccess', 'apache.conf', 'apache2.conf']
mimetypes = ['text/x-apacheconf']
flags = re.MULTILINE | re.IGNORECASE
tokens = {
'root': [
(r'\s+', Text),
(r'#(.*\\\n)+.*$|(#.*?)$', Comment),
(r'(<[^\s>/][^\s>]*)(?:(\s+)(.*))?(>)',
bygroups(Name.Tag, Text, String, Name.Tag)),
(r'(</[^\s>]+)(>)', bygroups(Name.Tag, Name.Tag)),
(r'[a-z]\w*', Name.Builtin, 'value'),
(r'\.+', Text),
],
'value': [(r'\\\n', Text), (r'$', Text, '#pop'), (r'\\', Text),
(r'[^\S\n]+', Text),
(r'\d+\.\d+\.\d+\.\d+(?:/\d+)?', Number), (r'\d+', Number),
(r'/([*a-z0-9][*\w./-]+)', String.Other),
(r'(on|off|none|any|all|double|email|dns|min|minimal|'
r'os|productonly|full|emerg|alert|crit|error|warn|'
r'notice|info|debug|registry|script|inetd|standalone|'
r'user|group)\b', Keyword),
(r'"([^"\\]*(?:\\(.|\n)[^"\\]*)*)"', String.Double),
(r'[^\s"\\]+', Text)],
}
class BBCodeLexer(RegexLexer):
"""
A lexer that highlights BBCode(-like) syntax.
.. versionadded:: 0.6
"""
name = 'BBCode'
aliases = ['bbcode']
mimetypes = ['text/x-bbcode']
tokens = {
'root': [
(r'[^[]+', Text),
# tag/end tag begin
(r'\[/?\w+', Keyword, 'tag'),
# stray bracket
(r'\[', Text),
],
'tag': [
(r'\s+', Text),
# attribute with value
(r'(\w+)(=)("?[^\s"\]]+"?)',
bygroups(Name.Attribute, Operator, String)),
# tag argument (a la [color=green])
(r'(=)("?[^\s"\]]+"?)', bygroups(Operator, String)),
# tag end
(r'\]', Keyword, '#pop'),
],
}
class DuelLexer(RegexLexer):
"""
Lexer for Duel Views Engine (formerly JBST) markup with JavaScript code blocks.
See http://duelengine.org/.
See http://jsonml.org/jbst/.
.. versionadded:: 1.4
"""
name = 'Duel'
aliases = ['duel', 'jbst', 'jsonml+bst']
filenames = ['*.duel', '*.jbst']
mimetypes = ['text/x-duel', 'text/x-jbst']
flags = re.DOTALL
tokens = {
'root': [
(r'(<%[@=#!:]?)(.*?)(%>)',
bygroups(Name.Tag, using(JavascriptLexer), Name.Tag)),
(r'(<%\$)(.*?)(:)(.*?)(%>)',
bygroups(Name.Tag, Name.Function, Punctuation, String, Name.Tag)),
(r'(<%--)(.*?)(--%>)',
bygroups(Name.Tag, Comment.Multiline, Name.Tag)),
(r'(<script.*?>)(.*?)(</script>)',
bygroups(using(HtmlLexer), using(JavascriptLexer),
using(HtmlLexer))),
(r'(.+?)(?=<)', using(HtmlLexer)),
(r'.+', using(HtmlLexer)),
],
}
class TypoScriptHtmlDataLexer(RegexLexer):
"""
Lexer that highlights markers, constants and registers within html tags.
.. versionadded:: 2.2
"""
name = 'TypoScriptHtmlData'
aliases = ['typoscripthtmldata']
tokens = {
'root': [
# INCLUDE_TYPOSCRIPT
(r'(INCLUDE_TYPOSCRIPT)', Name.Class),
# Language label or extension resource FILE:... or LLL:... or EXT:...
(r'(EXT|FILE|LLL):[^}\n"]*', String),
# marker: ###MARK###
(r'(.*)(###\w+###)(.*)', bygroups(String, Name.Constant, String)),
# constant: {$some.constant}
(r'(\{)(\$)((?:[\w\-]+\.)*)([\w\-]+)(\})',
bygroups(String.Symbol, Operator, Name.Constant, Name.Constant,
String.Symbol)), # constant
# constant: {register:somevalue}
(r'(.*)(\{)([\w\-]+)(\s*:\s*)([\w\-]+)(\})(.*)',
bygroups(String, String.Symbol, Name.Constant, Operator,
Name.Constant, String.Symbol, String)), # constant
# whitespace
(r'\s+', Text),
# other
(r'[<>,:=.*%+|]', String),
(r'[\w"\-!/&;(){}#]+', String),
]
}
class UsdLexer(RegexLexer):
"""
A lexer that parses Pixar's Universal Scene Description file format.
.. versionadded:: 2.6
"""
name = "USD"
aliases = ["usd", "usda"]
filenames = ["*.usd", "*.usda"]
tokens = {
"root": [
(r"(custom){_WHITESPACE}(uniform)(\s+){}(\s+){}(\s*)(=)".format(
_TYPE, _BASE_ATTRIBUTE, _WHITESPACE=_WHITESPACE),
bygroups(Keyword.Token, Whitespace, Keyword.Token, Whitespace,
Keyword.Type, Whitespace, Name.Attribute, Text,
Name.Keyword.Tokens, Whitespace, Operator)),
(r"(custom){_WHITESPACE}{}(\s+){}(\s*)(=)".format(
_TYPE, _BASE_ATTRIBUTE, _WHITESPACE=_WHITESPACE),
bygroups(Keyword.Token, Whitespace, Keyword.Type, Whitespace,
Name.Attribute, Text, Name.Keyword.Tokens, Whitespace,
Operator)),
(r"(uniform){_WHITESPACE}{}(\s+){}(\s*)(=)".format(
_TYPE, _BASE_ATTRIBUTE, _WHITESPACE=_WHITESPACE),
bygroups(Keyword.Token, Whitespace, Keyword.Type, Whitespace,
Name.Attribute, Text, Name.Keyword.Tokens, Whitespace,
Operator)),
(r"{}{_WHITESPACE}{}(\s*)(=)".format(
_TYPE, _BASE_ATTRIBUTE, _WHITESPACE=_WHITESPACE),
bygroups(Keyword.Type, Whitespace, Name.Attribute, Text,
Name.Keyword.Tokens, Whitespace, Operator)),
] + _keywords(KEYWORDS, Keyword.Tokens) +
_keywords(SPECIAL_NAMES, Name.Builtins) +
_keywords(COMMON_ATTRIBUTES, Name.Attribute) +
[(r"\b\w+:[\w:]+\b", Name.Attribute)] +
_keywords(OPERATORS, Operator) + # more attributes
[(type_ + r"\[\]", Keyword.Type)
for type_ in TYPES] + _keywords(TYPES, Keyword.Type) + [
(r"[(){}\[\]]", Punctuation),
("#.*?$", Comment.Single),
(",", Punctuation),
(";", Punctuation
), # ";"s are allowed to combine separate metadata lines
("=", Operator),
(r"[-]*([0-9]*[.])?[0-9]+(?:e[+-]*\d+)?", Number),
(r"'''(?:.|\n)*?'''", String),
(r'"""(?:.|\n)*?"""', String),
(r"'.*?'", String),
(r'".*?"', String),
(r"<(\.\./)*([\w/]+|[\w/]+\.\w+[\w:]*)>", Name.Namespace),
(r"@.*?@", String.Interpol),
(r'\(.*"[.\\n]*".*\)', String.Doc),
(r"\A#usda .+$", Comment.Hashbang),
(r"\s+", Whitespace),
(r"\w+", Text),
(r"[_:.]+", Punctuation),
],
}
class AlloyLexer(RegexLexer):
"""
For `Alloy <http://alloy.mit.edu>`_ source code.
.. versionadded:: 2.0
"""
name = 'Alloy'
aliases = ['alloy']
filenames = ['*.als']
mimetypes = ['text/x-alloy']
flags = re.MULTILINE | re.DOTALL
iden_rex = r'[a-zA-Z_][\w\']*'
text_tuple = (r'[^\S\n]+', Text)
tokens = {
'sig': [
(r'(extends)\b', Keyword, '#pop'),
(iden_rex, Name),
text_tuple,
(r',', Punctuation),
(r'\{', Operator, '#pop'),
],
'module': [
text_tuple,
(iden_rex, Name, '#pop'),
],
'fun': [
text_tuple,
(r'\{', Operator, '#pop'),
(iden_rex, Name, '#pop'),
],
'root': [
(r'--.*?$', Comment.Single),
(r'//.*?$', Comment.Single),
(r'/\*.*?\*/', Comment.Multiline),
text_tuple,
(r'(module|open)(\s+)', bygroups(Keyword.Namespace, Text),
'module'),
(r'(sig|enum)(\s+)', bygroups(Keyword.Declaration, Text), 'sig'),
(r'(iden|univ|none)\b', Keyword.Constant),
(r'(int|Int)\b', Keyword.Type),
(r'(this|abstract|extends|set|seq|one|lone|let)\b', Keyword),
(r'(all|some|no|sum|disj|when|else)\b', Keyword),
(r'(run|check|for|but|exactly|expect|as)\b', Keyword),
(r'(and|or|implies|iff|in)\b', Operator.Word),
(r'(fun|pred|fact|assert)(\s+)', bygroups(Keyword, Text), 'fun'),
(r'!|#|&&|\+\+|<<|>>|>=|<=>|<=|\.|->', Operator),
(r'[-+/*%=<>&!^|~{}\[\]().]', Operator),
(iden_rex, Name),
(r'[:,]', Punctuation),
(r'[0-9]+', Number.Integer),
(r'"(\\\\|\\"|[^"])*"', String),
(r'\n', Text),
]
}
class CppLexer(CFamilyLexer):
"""
For C++ source code with preprocessor directives.
"""
name = 'C++'
aliases = ['cpp', 'c++']
filenames = [
'*.cpp', '*.hpp', '*.c++', '*.h++', '*.cc', '*.hh', '*.cxx', '*.hxx',
'*.C', '*.H', '*.cp', '*.CPP'
]
mimetypes = ['text/x-c++hdr', 'text/x-c++src']
priority = 0.1
tokens = {
'statements': [
(words(
('catch', 'const_cast', 'delete', 'dynamic_cast', 'explicit',
'export', 'friend', 'mutable', 'namespace', 'new', 'operator',
'private', 'protected', 'public', 'reinterpret_cast',
'restrict', 'static_cast', 'template', 'this', 'throw',
'throws', 'try', 'typeid', 'typename', 'using', 'virtual',
'constexpr', 'nullptr', 'decltype', 'thread_local', 'alignas',
'alignof', 'static_assert', 'noexcept', 'override', 'final'),
suffix=r'\b'), Keyword),
(r'char(16_t|32_t)\b', Keyword.Type),
(r'(class)(\s+)', bygroups(Keyword, Text), 'classname'),
# C++11 raw strings
(r'(R)(")([^\\()\s]{,16})(\()((?:.|\n)*?)(\)\3)(")',
bygroups(String.Affix, String, String.Delimiter, String.Delimiter,
String, String.Delimiter, String)),
# C++11 UTF-8/16/32 strings
(r'(u8|u|U)(")', bygroups(String.Affix, String), 'string'),
inherit,
],
'root': [
inherit,
# C++ Microsoft-isms
(words(('virtual_inheritance', 'uuidof', 'super',
'single_inheritance', 'multiple_inheritance', 'interface',
'event'),
prefix=r'__',
suffix=r'\b'), Keyword.Reserved),
# Offload C++ extensions, http://offload.codeplay.com/
(r'__(offload|blockingoffload|outer)\b', Keyword.Pseudo),
],
'classname': [
(r'[a-zA-Z_]\w*', Name.Class, '#pop'),
# template specification
(r'\s*(?=>)', Text, '#pop'),
],
}
def analyse_text(text):
if re.search('#include <[a-z_]+>', text):
return 0.2
if re.search('using namespace ', text):
return 0.4
class BaseMakefileLexer(RegexLexer):
"""
Lexer for simple Makefiles (no preprocessing).
.. versionadded:: 0.10
"""
name = 'Base Makefile'
aliases = ['basemake']
filenames = []
mimetypes = []
tokens = {
'root': [
# recipes (need to allow spaces because of expandtabs)
(r'^(?:[\t ]+.*\n|\n)+', using(BashLexer)),
# special variables
(r'\$[<@$+%?|*]', Keyword),
(r'\s+', Text),
(r'#.*?\n', Comment),
(r'(export)(\s+)(?=[\w${}\t -]+\n)', bygroups(Keyword,
Text), 'export'),
(r'export\s+', Keyword),
# assignment
(r'([\w${}().-]+)(\s*)([!?:+]?=)([ \t]*)((?:.*\\\n)+|.*\n)',
bygroups(Name.Variable, Text, Operator, Text, using(BashLexer))),
# strings
(r'"(\\\\|\\[^\\]|[^"\\])*"', String.Double),
(r"'(\\\\|\\[^\\]|[^'\\])*'", String.Single),
# targets
(r'([^\n:]+)(:+)([ \t]*)', bygroups(Name.Function, Operator,
Text), 'block-header'),
# expansions
(r'\$\(', Keyword, 'expansion'),
],
'expansion': [
(r'[^\w$().-]+', Text),
(r'[\w.-]+', Name.Variable),
(r'\$', Keyword),
(r'\(', Keyword, '#push'),
(r'\)', Keyword, '#pop'),
],
'export': [
(r'[\w${}-]+', Name.Variable),
(r'\n', Text, '#pop'),
(r'\s+', Text),
],
'block-header': [
(r'[,|]', Punctuation),
(r'#.*?\n', Comment, '#pop'),
(r'\\\n', Text), # line continuation
(r'\$\(', Keyword, 'expansion'),
(r'[a-zA-Z_]+', Name),
(r'\n', Text, '#pop'),
(r'.', Text),
],
}
class NewspeakLexer(RegexLexer):
"""
For `Newspeak <http://newspeaklanguage.org/>` syntax.
.. versionadded:: 1.1
"""
name = 'Newspeak'
filenames = ['*.ns2']
aliases = ['newspeak', ]
mimetypes = ['text/x-newspeak']
tokens = {
'root': [
(r'\b(Newsqueak2)\b', Keyword.Declaration),
(r"'[^']*'", String),
(r'\b(class)(\s+)(\w+)(\s*)',
bygroups(Keyword.Declaration, Text, Name.Class, Text)),
(r'\b(mixin|self|super|private|public|protected|nil|true|false)\b',
Keyword),
(r'(\w+\:)(\s*)([a-zA-Z_]\w+)',
bygroups(Name.Function, Text, Name.Variable)),
(r'(\w+)(\s*)(=)',
bygroups(Name.Attribute, Text, Operator)),
(r'<\w+>', Comment.Special),
include('expressionstat'),
include('whitespace')
],
'expressionstat': [
(r'(\d+\.\d*|\.\d+|\d+[fF])[fF]?', Number.Float),
(r'\d+', Number.Integer),
(r':\w+', Name.Variable),
(r'(\w+)(::)', bygroups(Name.Variable, Operator)),
(r'\w+:', Name.Function),
(r'\w+', Name.Variable),
(r'\(|\)', Punctuation),
(r'\[|\]', Punctuation),
(r'\{|\}', Punctuation),
(r'(\^|\+|\/|~|\*|<|>|=|@|%|\||&|\?|!|,|-|:)', Operator),
(r'\.|;', Punctuation),
include('whitespace'),
include('literals'),
],
'literals': [
(r'\$.', String),
(r"'[^']*'", String),
(r"#'[^']*'", String.Symbol),
(r"#\w+:?", String.Symbol),
(r"#(\+|\/|~|\*|<|>|=|@|%|\||&|\?|!|,|-)+", String.Symbol)
],
'whitespace': [
(r'\s+', Text),
(r'"[^"]*"', Comment)
],
}
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),
(r'"""(\\\\|\\"|.*?)"""', String.Double),
(r'"(\\\\|\\"|[^"]*?)"', String.Double),
(r"'(\\\\|\\'|[^']*?)'", String.Single),
(r'[a-zA-Z_]\w*', Name),
(r'(\d+\.\d*|\d*\.\d+)([fF][+-]?[0-9]+)?', Number.Float),
(r'[0-9][0-9.]*(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': [(r'[a-zA-Z_]\w*', Name.Function, '#pop')],
'classname': [(r'[a-zA-Z_]\w*', Name.Class, '#pop')],
'namespace': [(r'[a-zA-Z_][\w.]*', Name.Namespace, '#pop')]
}
class PacmanConfLexer(RegexLexer):
"""
Lexer for `pacman.conf
<https://www.archlinux.org/pacman/pacman.conf.5.html>`_.
Actually, IniLexer works almost fine for this format,
but it yield error token. It is because pacman.conf has
a form without assignment like:
UseSyslog
Color
TotalDownload
CheckSpace
VerbosePkgLists
These are flags to switch on.
.. versionadded:: 2.1
"""
name = 'PacmanConf'
aliases = ['pacmanconf']
filenames = ['pacman.conf']
mimetypes = []
tokens = {
'root': [
# comment
(r'#.*$', Comment.Single),
# section header
(r'^\s*\[.*?\]\s*$', Keyword),
# variable definitions
# (Leading space is allowed...)
(r'(\w+)(\s*)(=)', bygroups(Name.Attribute, Text, Operator)),
# flags to on
(r'^(\s*)(\w+)(\s*)$', bygroups(Text, Name.Attribute, Text)),
# built-in special values
(
words(
(
'$repo', # repository
'$arch', # architecture
'%o', # outfile
'%u', # url
),
suffix=r'\b'),
Name.Variable),
# fallback
(r'.', Text),
],
}
class ScdocLexer(RegexLexer):
"""
`scdoc` is a simple man page generator for POSIX systems written in C99.
https://git.sr.ht/~sircmpwn/scdoc
.. versionadded:: 2.5
"""
name = 'scdoc'
aliases = ['scdoc', 'scd']
filenames = ['*.scd', '*.scdoc']
flags = re.MULTILINE
tokens = {
'root': [
# comment
(r'^(;.+\n)', bygroups(Comment)),
# heading with pound prefix
(r'^(#)([^#].+\n)', bygroups(Generic.Heading, Text)),
(r'^(#{2})(.+\n)', bygroups(Generic.Subheading, Text)),
# bulleted lists
(r'^(\s*)([*-])(\s)(.+\n)',
bygroups(Text, Keyword, Text, using(this, state='inline'))),
# numbered lists
(r'^(\s*)(\.+\.)( .+\n)',
bygroups(Text, Keyword, using(this, state='inline'))),
# quote
(r'^(\s*>\s)(.+\n)', bygroups(Keyword, Generic.Emph)),
# text block
(r'^(```\n)([\w\W]*?)(^```$)', bygroups(String, Text, String)),
include('inline'),
],
'inline': [
# escape
(r'\\.', Text),
# underlines
(r'(\s)(_[^_]+_)(\W|\n)', bygroups(Text, Generic.Emph, Text)),
# bold
(r'(\s)(\*[^*]+\*)(\W|\n)', bygroups(Text, Generic.Strong, Text)),
# inline code
(r'`[^`]+`', String.Backtick),
# general text, must come last!
(r'[^\\\s]+', Text),
(r'.', Text),
],
}
def analyse_text(text):
"""This is very similar to markdown, save for the escape characters
needed for * and _."""
result = 0
if '\\*' in text:
result += 0.01
if '\\_' in text:
result += 0.01
return result
class PostgresLexer(PostgresBase, RegexLexer):
"""
Lexer for the PostgreSQL dialect of SQL.
.. versionadded:: 1.5
"""
name = 'PostgreSQL SQL dialect'
aliases = ['postgresql', 'postgres']
mimetypes = ['text/x-postgresql']
flags = re.IGNORECASE
tokens = {
'root': [
(r'\s+', Text),
(r'--.*\n?', Comment.Single),
(r'/\*', Comment.Multiline, 'multiline-comments'),
(r'(' + '|'.join(
s.replace(" ", r"\s+")
for s in DATATYPES + PSEUDO_TYPES) + r')\b', Name.Builtin),
(words(KEYWORDS, suffix=r'\b'), Keyword),
(r'[+*/<>=~!@#%^&|`?-]+', Operator),
(r'::', Operator), # cast
(r'\$\d+', Name.Variable),
(r'([0-9]*\.[0-9]*|[0-9]+)(e[+-]?[0-9]+)?', Number.Float),
(r'[0-9]+', Number.Integer),
(r"((?:E|U&)?)(')", bygroups(String.Affix,
String.Single), 'string'),
# quoted identifier
(r'((?:U&)?)(")', bygroups(String.Affix,
String.Name), 'quoted-ident'),
(r'(?s)(\$)([^$]*)(\$)(.*?)(\$)(\2)(\$)', language_callback),
(r'[a-z_]\w*', Name),
# psql variable in SQL
(r""":(['"]?)[a-z]\w*\b\1""", Name.Variable),
(r'[;:()\[\]{},.]', Punctuation),
],
'multiline-comments':
[(r'/\*', Comment.Multiline, 'multiline-comments'),
(r'\*/', Comment.Multiline, '#pop'), (r'[^/*]+', Comment.Multiline),
(r'[/*]', Comment.Multiline)],
'string': [
(r"[^']+", String.Single),
(r"''", String.Single),
(r"'", String.Single, '#pop'),
],
'quoted-ident': [
(r'[^"]+', String.Name),
(r'""', String.Name),
(r'"', String.Name, '#pop'),
],
}
class PonyLexer(RegexLexer):
"""
For Pony source code.
.. versionadded:: 2.4
"""
name = 'Pony'
aliases = ['pony']
filenames = ['*.pony']
_caps = r'(iso|trn|ref|val|box|tag)'
tokens = {
'root':
[(r'\n', Text), (r'[^\S\n]+', Text), (r'//.*\n', Comment.Single),
(r'/\*', Comment.Multiline, 'nested_comment'),
(r'"""(?:.|\n)*?"""', String.Doc), (r'"', String, 'string'),
(r'\'.*\'', String.Char), (r'=>|[]{}:().~;,|&!^?[]', Punctuation),
(words(('addressof', 'and', 'as', 'consume', 'digestof', 'is', 'isnt',
'not', 'or'),
suffix=r'\b'), Operator.Word),
(r'!=|==|<<|>>|[-+/*%=<>]', Operator),
(words(('box', 'break', 'compile_error', 'compile_intrinsic',
'continue', 'do', 'else', 'elseif', 'embed', 'end', 'error',
'for', 'if', 'ifdef', 'in', 'iso', 'lambda', 'let', 'match',
'object', 'recover', 'ref', 'repeat', 'return', 'tag', 'then',
'this', 'trn', 'try', 'until', 'use', 'var', 'val', 'where',
'while', 'with', '#any', '#read', '#send', '#share'),
suffix=r'\b'), Keyword),
(r'(actor|class|struct|primitive|interface|trait|type)((?:\s)+)',
bygroups(Keyword, Text), 'typename'),
(r'(new|fun|be)((?:\s)+)', bygroups(Keyword, Text), 'methodname'),
(words(
('I8', 'U8', 'I16', 'U16', 'I32', 'U32', 'I64', 'U64', 'I128',
'U128', 'ILong', 'ULong', 'ISize', 'USize', 'F32', 'F64', 'Bool',
'Pointer', 'None', 'Any', 'Array', 'String', 'Iterator'),
suffix=r'\b'), Name.Builtin.Type), (r'_?[A-Z]\w*', Name.Type),
(r'(\d+\.\d*|\.\d+|\d+)[eE][+-]?\d+', Number.Float),
(r'0x[0-9a-fA-F]+', Number.Hex), (r'\d+', Number.Integer),
(r'(true|false)\b', Name.Builtin), (r'_\d*', Name),
(r'_?[a-z][\w\'_]*', Name)],
'typename': [(_caps + r'?((?:\s)*)(_?[A-Z]\w*)',
bygroups(Keyword, Text, Name.Class), '#pop')],
'methodname': [(_caps + r'?((?:\s)*)(_?[a-z]\w*)',
bygroups(Keyword, Text, Name.Function), '#pop')],
'nested_comment': [(r'[^*/]+', Comment.Multiline),
(r'/\*', Comment.Multiline, '#push'),
(r'\*/', Comment.Multiline, '#pop'),
(r'[*/]', Comment.Multiline)],
'string': [(r'"', String, '#pop'), (r'\\"', String),
(r'[^\\"]+', String)]
}
class PkgConfigLexer(RegexLexer):
"""
Lexer for `pkg-config
<http://www.freedesktop.org/wiki/Software/pkg-config/>`_
(see also `manual page <http://linux.die.net/man/1/pkg-config>`_).
.. versionadded:: 2.1
"""
name = 'PkgConfig'
aliases = ['pkgconfig']
filenames = ['*.pc']
mimetypes = []
tokens = {
'root': [
(r'#.*$', Comment.Single),
# variable definitions
(r'^(\w+)(=)', bygroups(Name.Attribute, Operator)),
# keyword lines
(r'^([\w.]+)(:)', bygroups(Name.Tag, Punctuation), 'spvalue'),
# variable references
include('interp'),
# fallback
(r'[^${}#=:\n.]+', Text),
(r'.', Text),
],
'interp': [
# you can escape literal "$" as "$$"
(r'\$\$', Text),
# variable references
(r'\$\{', String.Interpol, 'curly'),
],
'curly': [
(r'\}', String.Interpol, '#pop'),
(r'\w+', Name.Attribute),
],
'spvalue': [
include('interp'),
(r'#.*$', Comment.Single, '#pop'),
(r'\n', Text, '#pop'),
# fallback
(r'[^${}#\n]+', Text),
(r'.', Text),
],
}
def gen_elixir_sigil_rules():
# all valid sigil terminators (excluding heredocs)
terminators = [
(r'\{', r'\}', '}', 'cb'),
(r'\[', r'\]', r'\]', 'sb'),
(r'\(', r'\)', ')', 'pa'),
('<', '>', '>', 'ab'),
('/', '/', '/', 'slas'),
(r'\|', r'\|', '|', 'pipe'),
('"', '"', '"', 'quot'),
("'", "'", "'", 'apos'),
]
# heredocs have slightly different rules
triquotes = [(r'"""', 'triquot'), (r"'''", 'triapos')]
token = String.Other
states = {'sigils': []}
for term, name in triquotes:
states['sigils'] += [
(r'(~[a-z])(%s)' % (term, ), bygroups(token, String.Heredoc),
(name + '-end', name + '-intp')),
(r'(~[A-Z])(%s)' % (term, ), bygroups(token, String.Heredoc),
(name + '-end', name + '-no-intp')),
]
states[name + '-end'] = [
(r'[a-zA-Z]+', token, '#pop'),
default('#pop'),
]
states[name + '-intp'] = [
(r'^\s*' + term, String.Heredoc, '#pop'),
include('heredoc_interpol'),
]
states[name + '-no-intp'] = [
(r'^\s*' + term, String.Heredoc, '#pop'),
include('heredoc_no_interpol'),
]
for lterm, rterm, rterm_class, name in terminators:
states['sigils'] += [
(r'~[a-z]' + lterm, token, name + '-intp'),
(r'~[A-Z]' + lterm, token, name + '-no-intp'),
]
states[name + '-intp'] = \
gen_elixir_sigstr_rules(rterm, rterm_class, token)
states[name + '-no-intp'] = \
gen_elixir_sigstr_rules(rterm, rterm_class, token, interpol=False)
return states
class DebianControlLexer(RegexLexer):
"""
Lexer for Debian ``control`` files and ``apt-cache show <pkg>`` outputs.
.. versionadded:: 0.9
"""
name = 'Debian Control file'
aliases = ['control', 'debcontrol']
filenames = ['control']
tokens = {
'root': [
(r'^(Description)', Keyword, 'description'),
(r'^(Maintainer)(:\s*)', bygroups(Keyword, Text), 'maintainer'),
(r'^((Build-)?Depends)', Keyword, 'depends'),
(r'^((?:Python-)?Version)(:\s*)(\S+)$',
bygroups(Keyword, Text, Number)),
(r'^((?:Installed-)?Size)(:\s*)(\S+)$',
bygroups(Keyword, Text, Number)),
(r'^(MD5Sum|SHA1|SHA256)(:\s*)(\S+)$',
bygroups(Keyword, Text, Number)),
(r'^([a-zA-Z\-0-9\.]*?)(:\s*)(.*?)$',
bygroups(Keyword, Whitespace, String)),
],
'maintainer': [
(r'<[^>]+>', Generic.Strong),
(r'<[^>]+>$', Generic.Strong, '#pop'),
(r',\n?', Text),
(r'.', Text),
],
'description': [
(r'(.*)(Homepage)(: )(\S+)',
bygroups(Text, String, Name, Name.Class)),
(r':.*\n', Generic.Strong),
(r' .*\n', Text),
default('#pop'),
],
'depends': [
(r':\s*', Text),
(r'(\$)(\{)(\w+\s*:\s*\w+)', bygroups(Operator, Text, Name.Entity)),
(r'\(', Text, 'depend_vers'),
(r',', Text),
(r'\|', Operator),
(r'[\s]+', Text),
(r'[})]\s*$', Text, '#pop'),
(r'\}', Text),
(r'[^,]$', Name.Function, '#pop'),
(r'([+.a-zA-Z0-9-])(\s*)', bygroups(Name.Function, Text)),
(r'\[.*?\]', Name.Entity),
],
'depend_vers': [
(r'\),', Text, '#pop'),
(r'\)[^,]', Text, '#pop:2'),
(r'([><=]+)(\s*)([^)]+)', bygroups(Operator, Text, Number))
]
}
class Cfengine3Lexer(RegexLexer):
"""
Lexer for `CFEngine3 <http://cfengine.org>`_ policy files.
.. versionadded:: 1.5
"""
name = 'CFEngine3'
aliases = ['cfengine3', 'cf3']
filenames = ['*.cf']
mimetypes = []
tokens = {
'root': [
(r'#.*?\n', Comment),
(r'(body)(\s+)(\S+)(\s+)(control)',
bygroups(Keyword, Text, Keyword, Text, Keyword)),
(r'(body|bundle)(\s+)(\S+)(\s+)(\w+)(\()',
bygroups(Keyword, Text, Keyword, Text, Name.Function,
Punctuation), 'arglist'),
(r'(body|bundle)(\s+)(\S+)(\s+)(\w+)',
bygroups(Keyword, Text, Keyword, Text, Name.Function)),
(r'(")([^"]+)(")(\s+)(string|slist|int|real)(\s*)(=>)(\s*)',
bygroups(Punctuation, Name.Variable, Punctuation, Text,
Keyword.Type, Text, Operator, Text)),
(r'(\S+)(\s*)(=>)(\s*)',
bygroups(Keyword.Reserved, Text, Operator, Text)),
(r'"', String, 'string'),
(r'(\w+)(\()', bygroups(Name.Function, Punctuation)),
(r'([\w.!&|()]+)(::)', bygroups(Name.Class, Punctuation)),
(r'(\w+)(:)', bygroups(Keyword.Declaration, Punctuation)),
(r'@[{(][^)}]+[})]', Name.Variable),
(r'[(){},;]', Punctuation),
(r'=>', Operator),
(r'->', Operator),
(r'\d+\.\d+', Number.Float),
(r'\d+', Number.Integer),
(r'\w+', Name.Function),
(r'\s+', Text),
],
'string': [
(r'\$[{(]', String.Interpol, 'interpol'),
(r'\\.', String.Escape),
(r'"', String, '#pop'),
(r'\n', String),
(r'.', String),
],
'interpol': [
(r'\$[{(]', String.Interpol, '#push'),
(r'[})]', String.Interpol, '#pop'),
(r'[^${()}]+', String.Interpol),
],
'arglist': [
(r'\)', Punctuation, '#pop'),
(r',', Punctuation),
(r'\w+', Name.Variable),
(r'\s+', Text),
],
}
def _make_redirect_state(compound,
_core_token_compound=_core_token_compound,
_nl=_nl, _punct=_punct, _stoken=_stoken,
_string=_string, _space=_space,
_variable=_variable, _ws=_ws):
stoken_compound = (r'(?:[%s]+|(?:%s|%s|%s)+)' %
(_punct, _string, _variable, _core_token_compound))
return [
(r'((?:(?<=[%s%s])\d)?)(>>?&|<&)([%s%s]*)(\d)' %
(_nl, _ws, _nl, _ws),
bygroups(Number.Integer, Punctuation, Text, Number.Integer)),
(r'((?:(?<=[%s%s])(?<!\^[%s])\d)?)(>>?|<)(%s?%s)' %
(_nl, _ws, _nl, _space, stoken_compound if compound else _stoken),
bygroups(Number.Integer, Punctuation, using(this, state='text')))
]
class ScssLexer(RegexLexer):
"""
For SCSS stylesheets.
"""
name = 'SCSS'
aliases = ['scss']
filenames = ['*.scss']
mimetypes = ['text/x-scss']
flags = re.IGNORECASE | re.DOTALL
tokens = {
'root': [
(r'\s+', Text),
(r'//.*?\n', Comment.Single),
(r'/\*.*?\*/', Comment.Multiline),
(r'@import', Keyword, 'value'),
(r'@for', Keyword, 'for'),
(r'@(debug|warn|if|while)', Keyword, 'value'),
(r'(@mixin)( [\w-]+)', bygroups(Keyword, Name.Function), 'value'),
(r'(@include)( [\w-]+)', bygroups(Keyword, Name.Decorator), 'value'),
(r'@extend', Keyword, 'selector'),
(r'(@media)(\s+)', bygroups(Keyword, Text), 'value'),
(r'@[\w-]+', Keyword, 'selector'),
(r'(\$[\w-]*\w)([ \t]*:)', bygroups(Name.Variable, Operator), 'value'),
# TODO: broken, and prone to infinite loops.
# (r'(?=[^;{}][;}])', Name.Attribute, 'attr'),
# (r'(?=[^;{}:]+:[^a-z])', Name.Attribute, 'attr'),
default('selector'),
],
'attr': [
(r'[^\s:="\[]+', Name.Attribute),
(r'#\{', String.Interpol, 'interpolation'),
(r'[ \t]*:', Operator, 'value'),
default('#pop'),
],
'inline-comment': [
(r"(\\#|#(?=[^{])|\*(?=[^/])|[^#*])+", Comment.Multiline),
(r'#\{', String.Interpol, 'interpolation'),
(r"\*/", Comment, '#pop'),
],
}
for group, common in common_sass_tokens.items():
tokens[group] = copy.copy(common)
tokens['value'].extend([(r'\n', Text), (r'[;{}]', Punctuation, '#pop')])
tokens['selector'].extend([(r'\n', Text), (r'[;{}]', Punctuation, '#pop')])
class ECLexer(CLexer):
"""
For eC source code with preprocessor directives.
.. versionadded:: 1.5
"""
name = 'eC'
aliases = ['ec']
filenames = ['*.ec', '*.eh']
mimetypes = ['text/x-echdr', 'text/x-ecsrc']
tokens = {
'statements': [
(words((
'virtual', 'class', 'private', 'public', 'property', 'import',
'delete', 'new', 'new0', 'renew', 'renew0', 'define', 'get',
'set', 'remote', 'dllexport', 'dllimport', 'stdcall', 'subclass',
'__on_register_module', 'namespace', 'using', 'typed_object',
'any_object', 'incref', 'register', 'watch', 'stopwatching', 'firewatchers',
'watchable', 'class_designer', 'class_fixed', 'class_no_expansion', 'isset',
'class_default_property', 'property_category', 'class_data',
'class_property', 'thisclass', 'dbtable', 'dbindex',
'database_open', 'dbfield'), suffix=r'\b'), Keyword),
(words(('uint', 'uint16', 'uint32', 'uint64', 'bool', 'byte',
'unichar', 'int64'), suffix=r'\b'),
Keyword.Type),
(r'(class)(\s+)', bygroups(Keyword, Text), 'classname'),
(r'(null|value|this)\b', Name.Builtin),
inherit,
]
}
class IniLexer(RegexLexer):
"""
Lexer for configuration files in INI style.
"""
name = 'INI'
aliases = ['ini', 'cfg', 'dosini']
filenames = ['*.ini', '*.cfg', '*.inf']
mimetypes = ['text/x-ini', 'text/inf']
tokens = {
'root': [
(r'\s+', Text),
(r'[;#].*', Comment.Single),
(r'\[.*?\]$', Keyword),
(r'(.*?)([ \t]*)(=)([ \t]*)([^\t\n]*)',
bygroups(Name.Attribute, Text, Operator, Text, String)),
# standalone option, supported by some INI parsers
(r'(.+?)$', Name.Attribute),
],
}
def analyse_text(text):
npos = text.find('\n')
if npos < 3:
return False
return text[0] == '[' and text[npos - 1] == ']'
class VGLLexer(RegexLexer):
"""
For `SampleManager VGL <http://www.thermoscientific.com/samplemanager>`_
source code.
.. versionadded:: 1.6
"""
name = 'VGL'
aliases = ['vgl']
filenames = ['*.rpf']
flags = re.MULTILINE | re.DOTALL | re.IGNORECASE
tokens = {
'root': [
(r'\{[^}]*\}', Comment.Multiline),
(r'declare', Keyword.Constant),
(r'(if|then|else|endif|while|do|endwhile|and|or|prompt|object'
r'|create|on|line|with|global|routine|value|endroutine|constant'
r'|global|set|join|library|compile_option|file|exists|create|copy'
r'|delete|enable|windows|name|notprotected)(?! *[=<>.,()])',
Keyword),
(r'(true|false|null|empty|error|locked)', Keyword.Constant),
(r'[~^*#!%&\[\]()<>|+=:;,./?-]', Operator),
(r'"[^"]*"', String),
(r'(\.)([a-z_$][\w$]*)', bygroups(Operator, Name.Attribute)),
(r'[0-9][0-9]*(\.[0-9]+(e[+\-]?[0-9]+)?)?', Number),
(r'[a-z_$][\w$]*', Name),
(r'[\r\n]+', Text),
(r'\s+', Text)
]
}
class CharmciLexer(CppLexer):
"""
For `Charm++ <https://charm.cs.illinois.edu>`_ interface files (.ci).
.. versionadded:: 2.4
"""
name = 'Charmci'
aliases = ['charmci']
filenames = ['*.ci']
mimetypes = []
tokens = {
'statements': [
(r'(module)(\s+)', bygroups(Keyword, Text), 'classname'),
(words(('mainmodule', 'mainchare', 'chare', 'array', 'group',
'nodegroup', 'message', 'conditional')), Keyword),
(words(('entry', 'aggregate', 'threaded', 'sync', 'exclusive',
'nokeep', 'notrace', 'immediate', 'expedited', 'inline',
'local', 'python', 'accel', 'readwrite', 'writeonly',
'accelblock', 'memcritical', 'packed', 'varsize',
'initproc', 'initnode', 'initcall', 'stacksize',
'createhere', 'createhome', 'reductiontarget', 'iget',
'nocopy', 'mutable', 'migratable', 'readonly')), Keyword),
inherit,
],
}
class DylanLidLexer(RegexLexer):
"""
For Dylan LID (Library Interchange Definition) files.
.. versionadded:: 1.6
"""
name = 'DylanLID'
aliases = ['dylan-lid', 'lid']
filenames = ['*.lid', '*.hdp']
mimetypes = ['text/x-dylan-lid']
flags = re.IGNORECASE
tokens = {
'root': [
# Whitespace
(r'\s+', Text),
# single line comment
(r'//.*?\n', Comment.Single),
# lid header
(r'(.*?)(:)([ \t]*)(.*(?:\n[ \t].+)*)',
bygroups(Name.Attribute, Operator, Text, String)),
]
}
