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 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 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: {$some.constant}
(r'(\{)(\$)((?:[\w\-]+\.)*)([\w\-]+)(\})',
bygroups(String.Symbol, Operator, Name.Constant, Name.Constant,
String.Symbol)), # constant
# constant: {register:somevalue}
(r'(.*)(\{)([\w\-]+)(\s*:\s*)([\w\-]+)(\})(.*)',
bygroups(String, String.Symbol, Name.Constant, Operator,
Name.Constant, String.Symbol, String)), # constant
# whitespace
(r'\s+', Text),
# comments
(r'/\*(?:(?!\*/).)*\*/', Comment),
(r'(?<!(#|\'|"))(?:#(?!(?:[a-fA-F0-9]{6}|[a-fA-F0-9]{3}))[^\n#]+|//[^\n]*)',
Comment),
# other
(r'[<>,:=.*%+|]', String),
(r'[\w"\-!/&;(){}]+', String),
]
}
class TypoScriptHtmlDataLexer(RegexLexer):
"""
Lexer that highlights markers, constants and registers within html tags.
.. versionadded:: 2.2
"""
name = 'TypoScriptHtmlData'
aliases = ['typoscripthtmldata']
tokens = {
'root': [
# INCLUDE_TYPOSCRIPT
(r'(INCLUDE_TYPOSCRIPT)', Name.Class),
# Language label or extension resource FILE:... or LLL:... or EXT:...
(r'(EXT|FILE|LLL):[^}\n"]*', String),
# marker: ###MARK###
(r'(.*)(###\w+###)(.*)', bygroups(String, Name.Constant, String)),
# constant: {$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 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',
'reserved', '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 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'(?s)"(\\\\|\\.|[^"\\])*"', String.Double),
(r"(?s)'(\\\\|\\.|[^'\\])*'", 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 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 DarcsPatchLexer(RegexLexer):
"""
DarcsPatchLexer is a lexer for the various versions of the darcs patch
format. Examples of this format are derived by commands such as
``darcs annotate --patch`` and ``darcs send``.
.. versionadded:: 0.10
"""
name = 'Darcs Patch'
aliases = ['dpatch']
filenames = ['*.dpatch', '*.darcspatch']
DPATCH_KEYWORDS = ('hunk', 'addfile', 'adddir', 'rmfile', 'rmdir', 'move',
'replace')
tokens = {
'root': [
(r'<', Operator),
(r'>', Operator),
(r'\{', Operator),
(r'\}', Operator),
(r'(\[)((?:TAG )?)(.*)(\n)(.*)(\*\*)(\d+)(\s?)(\])',
bygroups(Operator, Keyword, Name, Text, Name, Operator,
Literal.Date, Text, Operator)),
(r'(\[)((?:TAG )?)(.*)(\n)(.*)(\*\*)(\d+)(\s?)',
bygroups(Operator, Keyword, Name, Text, Name, Operator,
Literal.Date, Text), 'comment'),
(r'New patches:', Generic.Heading),
(r'Context:', Generic.Heading),
(r'Patch bundle hash:', Generic.Heading),
(r'(\s*)(%s)(.*\n)' % '|'.join(DPATCH_KEYWORDS),
bygroups(Text, Keyword, Text)),
(r'\+', Generic.Inserted, "insert"),
(r'-', Generic.Deleted, "delete"),
(r'.*\n', Text),
],
'comment': [
(r'[^\]].*\n', Comment),
(r'\]', Operator, "#pop"),
],
'specialText': [ # darcs add [_CODE_] special operators for clarity
(r'\n', Text, "#pop"), # line-based
(r'\[_[^_]*_]', Operator),
],
'insert': [
include('specialText'),
(r'\[', Generic.Inserted),
(r'[^\n\[]+', Generic.Inserted),
],
'delete': [
include('specialText'),
(r'\[', Generic.Deleted),
(r'[^\n\[]+', Generic.Deleted),
],
}
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 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))]
}
def gen_elixir_sigil_rules():
# all valid sigil terminators (excluding heredocs)
terminators = [
(r'\{', r'\}', 'cb'),
(r'\[', r'\]', 'sb'),
(r'\(', r'\)', 'pa'),
(r'<', r'>', 'ab'),
(r'/', r'/', '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, 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, token)
states[name + '-no-intp'] = \
gen_elixir_sigstr_rules(rterm, token, interpol=False)
return states
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 iteritems(common_sass_tokens):
tokens[group] = copy.copy(common)
tokens['value'].extend([(r'\n', Text), (r'[;{}]', Punctuation, '#pop')])
tokens['selector'].extend([(r'\n', Text), (r'[;{}]', Punctuation, '#pop')])
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 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 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 SnobolLexer(RegexLexer):
"""
Lexer for the SNOBOL4 programming language.
Recognizes the common ASCII equivalents of the original SNOBOL4 operators.
Does not require spaces around binary operators.
.. versionadded:: 1.5
"""
name = "Snobol"
aliases = ["snobol"]
filenames = ['*.snobol']
mimetypes = ['text/x-snobol']
tokens = {
# root state, start of line
# comments, continuation lines, and directives start in column 1
# as do labels
'root': [
(r'\*.*\n', Comment),
(r'[+.] ', Punctuation, 'statement'),
(r'-.*\n', Comment),
(r'END\s*\n', Name.Label, 'heredoc'),
(r'[A-Za-z$][\w$]*', Name.Label, 'statement'),
(r'\s+', Text, 'statement'),
],
# statement state, line after continuation or label
'statement': [
(r'\s*\n', Text, '#pop'),
(r'\s+', Text),
(r'(?<=[^\w.])(LT|LE|EQ|NE|GE|GT|INTEGER|IDENT|DIFFER|LGT|SIZE|'
r'REPLACE|TRIM|DUPL|REMDR|DATE|TIME|EVAL|APPLY|OPSYN|LOAD|UNLOAD|'
r'LEN|SPAN|BREAK|ANY|NOTANY|TAB|RTAB|REM|POS|RPOS|FAIL|FENCE|'
r'ABORT|ARB|ARBNO|BAL|SUCCEED|INPUT|OUTPUT|TERMINAL)(?=[^\w.])',
Name.Builtin),
(r'[A-Za-z][\w.]*', Name),
# ASCII equivalents of original operators
# | for the EBCDIC equivalent, ! likewise
# \ for EBCDIC negation
(r'\*\*|[?$.!%*/#+\-@|&\\=]', Operator),
(r'"[^"]*"', String),
(r"'[^']*'", String),
# Accept SPITBOL syntax for real numbers
# as well as Macro SNOBOL4
(r'[0-9]+(?=[^.EeDd])', Number.Integer),
(r'[0-9]+(\.[0-9]*)?([EDed][-+]?[0-9]+)?', Number.Float),
# Goto
(r':', Punctuation, 'goto'),
(r'[()<>,;]', Punctuation),
],
# Goto block
'goto': [(r'\s*\n', Text, "#pop:2"), (r'\s+', Text), (r'F|S', Keyword),
(r'(\()([A-Za-z][\w.]*)(\))',
bygroups(Punctuation, Name.Label, Punctuation))],
# everything after the END statement is basically one
# big heredoc.
'heredoc': [(r'.*\n', String.Heredoc)]
}
class RslLexer(RegexLexer):
"""
`RSL <http://en.wikipedia.org/wiki/RAISE>`_ is the formal specification
language used in RAISE (Rigorous Approach to Industrial Software Engineering)
method.
.. versionadded:: 2.0
"""
name = 'RSL'
aliases = ['rsl']
filenames = ['*.rsl']
mimetypes = ['text/rsl']
flags = re.MULTILINE | re.DOTALL
tokens = {
'root': [
(words(
('Bool', 'Char', 'Int', 'Nat', 'Real', 'Text', 'Unit', 'abs',
'all', 'always', 'any', 'as', 'axiom', 'card', 'case',
'channel', 'chaos', 'class', 'devt_relation', 'dom', 'elems',
'else', 'elif', 'end', 'exists', 'extend', 'false', 'for',
'hd', 'hide', 'if', 'in', 'is', 'inds', 'initialise', 'int',
'inter', 'isin', 'len', 'let', 'local', 'ltl_assertion',
'object', 'of', 'out', 'post', 'pre', 'read', 'real', 'rng',
'scheme', 'skip', 'stop', 'swap', 'then', 'theory',
'test_case', 'tl', 'transition_system', 'true', 'type',
'union', 'until', 'use', 'value', 'variable', 'while', 'with',
'write', '~isin', '-inflist', '-infset', '-list', '-set'),
prefix=r'\b',
suffix=r'\b'), Keyword),
(r'(variable|value)\b', Keyword.Declaration),
(r'--.*?\n', Comment),
(r'<:.*?:>', Comment),
(r'\{!.*?!\}', Comment),
(r'/\*.*?\*/', Comment),
(r'^[ \t]*([\w]+)[ \t]*:[^:]', Name.Function),
(r'(^[ \t]*)([\w]+)([ \t]*\([\w\s,]*\)[ \t]*)(is|as)',
bygroups(Text, Name.Function, Text, Keyword)),
(r'\b[A-Z]\w*\b', Keyword.Type),
(r'(true|false)\b', Keyword.Constant),
(r'".*"', String),
(r'\'.\'', String.Char),
(r'(><|->|-m->|/\\|<=|<<=|<\.|\|\||\|\^\||-~->|-~m->|\\/|>=|>>|'
r'\.>|\+\+|-\\|<->|=>|:-|~=|\*\*|<<|>>=|\+>|!!|\|=\||#)',
Operator),
(r'[0-9]+\.[0-9]+([eE][0-9]+)?[fd]?', Number.Float),
(r'0x[0-9a-f]+', Number.Hex),
(r'[0-9]+', Number.Integer),
(r'.', Text),
],
}
def analyse_text(text):
"""
Check for the most common text in the beginning of a RSL file.
"""
if re.search(r'scheme\s*.*?=\s*class\s*type', text, re.I) is not None:
return 1.0
def _objdump_lexer_tokens(asm_lexer):
"""
Common objdump lexer tokens to wrap an ASM lexer.
"""
hex_re = r'[0-9A-Za-z]'
return {
'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_re + '+)( )(<)(.*?)([-+])(0[xX][A-Za-z0-9]+)(>:)$',
bygroups(Number.Hex, Text, Punctuation, Name.Function,
Punctuation, Number.Hex, Punctuation)),
# (Without offset)
('(' + hex_re + '+)( )(<)(.*?)(>:)$',
bygroups(Number.Hex, Text, Punctuation, Name.Function,
Punctuation)),
# Code line with disassembled instructions
('( *)(' + hex_re + r'+:)(\t)((?:' + hex_re + hex_re +
' )+)( *\t)([a-zA-Z].*?)$',
bygroups(Text, Name.Label, Text, Number.Hex, Text,
using(asm_lexer))),
# Code line with ascii
('( *)(' + hex_re + r'+:)(\t)((?:' + hex_re + hex_re +
' )+)( *)(.*?)$',
bygroups(Text, Name.Label, Text, Number.Hex, Text, String)),
# Continued code line, only raw opcodes without disassembled
# instruction
('( *)(' + hex_re + r'+:)(\t)((?:' + hex_re + hex_re + ' )+)$',
bygroups(Text, Name.Label, Text, Number.Hex)),
# Skipped a few bytes
(r'\t\.\.\.$', Text),
# Relocation line
# (With offset)
(r'(\t\t\t)(' + hex_re + r'+:)( )([^\t]+)(\t)(.*?)([-+])(0x' +
hex_re + '+)$',
bygroups(Text, Name.Label, Text, Name.Property, Text,
Name.Constant, Punctuation, Number.Hex)),
# (Without offset)
(r'(\t\t\t)(' + hex_re + r'+:)( )([^\t]+)(\t)(.*?)$',
bygroups(Text, Name.Label, Text, Name.Property, Text,
Name.Constant)),
(r'[^\n]+\n', Other)
]
}
def _make_call_state(compound,
_label=_label,
_label_compound=_label_compound):
state = []
if compound:
state.append((r'(?=\))', Text, '#pop'))
state.append((r'(:?)(%s)' % (_label_compound if compound else _label),
bygroups(Punctuation, Name.Label), '#pop'))
return state
class XorgLexer(RegexLexer):
"""Lexer for xorg.conf file."""
name = 'Xorg'
aliases = ['xorg.conf']
filenames = ['xorg.conf']
mimetypes = []
tokens = {
'root': [
(r'\s+', Text),
(r'#.*$', Comment),
(r'((?:Sub)?Section)(\s+)("\w+")',
bygroups(String.Escape, Text, String.Escape)),
(r'(End(|Sub)Section)', String.Escape),
(r'(\w+)(\s+)([^\n#]+)', bygroups(Name.Builtin, Text,
Name.Constant)),
],
}
def _make_redirect_state(compound,
_core_token_compound=_core_token_compound,
_nl=_nl,
_punct=_punct,
_stoken=_stoken,
_string=_string,
_space=_space,
_variable=_variable,
_ws=_ws):
stoken_compound = (r'(?:[%s]+|(?:%s|%s|%s)+)' %
(_punct, _string, _variable, _core_token_compound))
return [
(r'((?:(?<=[%s%s])\d)?)(>>?&|<&)([%s%s]*)(\d)' %
(_nl, _ws, _nl, _ws),
bygroups(Number.Integer, Punctuation, Text, Number.Integer)),
(r'((?:(?<=[%s%s])(?<!\^[%s])\d)?)(>>?|<)(%s?%s)' %
(_nl, _ws, _nl, _space, stoken_compound if compound else _stoken),
bygroups(Number.Integer, Punctuation, using(this, state='text')))
]
def gen_elixir_string_rules(name, symbol, token):
states = {}
states['string_' + name] = [
(r'[^#%s\\]+' % (symbol,), token),
include('escapes'),
(r'\\.', token),
(r'(%s)' % (symbol,), bygroups(token), "#pop"),
include('interpol')
]
return states
class ScdocLexer(RegexLexer):
"""
`scdoc` is a simple man page generator for POSIX systems written in C99.
https://git.sr.ht/~sircmpwn/scdoc
.. versionadded:: 2.5
"""
name = 'scdoc'
aliases = ['scdoc', 'scd']
filenames = ['*.scd', '*.scdoc']
flags = re.MULTILINE
tokens = {
'root': [
# comment
(r'^(;.+\n)', bygroups(Comment)),
# heading with pound prefix
(r'^(#)([^#].+\n)', bygroups(Generic.Heading, Text)),
(r'^(#{2})(.+\n)', bygroups(Generic.Subheading, Text)),
# bulleted lists
(r'^(\s*)([*-])(\s)(.+\n)',
bygroups(Text, Keyword, Text, using(this, state='inline'))),
# numbered lists
(r'^(\s*)(\.+\.)( .+\n)',
bygroups(Text, Keyword, using(this, state='inline'))),
# quote
(r'^(\s*>\s)(.+\n)', bygroups(Keyword, Generic.Emph)),
# text block
(r'^(```\n)([\w\W]*?)(^```$)', 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),
],
}
class ResourceLexer(RegexLexer):
"""Lexer for `ICU Resource bundles
<http://userguide.icu-project.org/locale/resources>`_.
.. versionadded:: 2.0
"""
name = 'ResourceBundle'
aliases = ['resource', 'resourcebundle']
filenames = []
_types = (':table', ':array', ':string', ':bin', ':import', ':intvector',
':int', ':alias')
flags = re.MULTILINE | re.IGNORECASE
tokens = {
'root': [
(r'//.*?$', Comment),
(r'"', String, 'string'),
(r'-?\d+', Number.Integer),
(r'[,{}]', Operator),
(r'([^\s{:]+)(\s*)(%s?)' % '|'.join(_types),
bygroups(Name, Text, Keyword)),
(r'\s+', Text),
(words(_types), Keyword),
],
'string':
[(r'(\\x[0-9a-f]{2}|\\u[0-9a-f]{4}|\\U00[0-9a-f]{6}|'
r'\\[0-7]{1,3}|\\c.|\\[abtnvfre\'"?\\]|\\\{|[^"{\\])+', String),
(r'\{', String.Escape, 'msgname'), (r'"', String, '#pop')],
'msgname':
[(r'([^{},]+)(\s*)', bygroups(Name,
String.Escape), ('#pop', 'message'))],
'message':
[(r'\{', String.Escape, 'msgname'), (r'\}', String.Escape, '#pop'),
(r'(,)(\s*)([a-z]+)(\s*\})',
bygroups(Operator, String.Escape, Keyword, String.Escape), '#pop'),
(r'(,)(\s*)([a-z]+)(\s*)(,)(\s*)(offset)(\s*)(:)(\s*)(-?\d+)(\s*)',
bygroups(Operator, String.Escape, Keyword, String.Escape, Operator,
String.Escape, Operator.Word, String.Escape, Operator,
String.Escape, Number.Integer, String.Escape), 'choice'),
(r'(,)(\s*)([a-z]+)(\s*)(,)(\s*)',
bygroups(Operator, String.Escape, Keyword, String.Escape, Operator,
String.Escape), 'choice'), (r'\s+', String.Escape)],
'choice': [(r'(=|<|>|<=|>=|!=)(-?\d+)(\s*\{)',
bygroups(Operator, Number.Integer,
String.Escape), 'message'),
(r'([a-z]+)(\s*\{)', bygroups(Keyword.Type,
String.Escape), 'str'),
(r'\}', String.Escape, ('#pop', '#pop')),
(r'\s+', String.Escape)],
'str': [(r'\}', String.Escape, '#pop'),
(r'\{', String.Escape, 'msgname'), (r'[^{}]+', String)]
}
def analyse_text(text):
if text.startswith('root:table'):
return 1.0
class HspecLexer(HaskellLexer):
"""
A Haskell lexer with support for Hspec constructs.
.. versionadded:: 2.4.0
"""
name = 'Hspec'
aliases = ['hspec']
filenames = []
mimetypes = []
tokens = {
'root': [
(r'(it\s*)("[^"]*")', bygroups(Text, String.Doc)),
(r'(describe\s*)("[^"]*")', bygroups(Text, String.Doc)),
(r'(context\s*)("[^"]*")', bygroups(Text, String.Doc)),
inherit,
],
}
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 GroffLexer(RegexLexer):
"""
Lexer for the (g)roff typesetting language, supporting groff
extensions. Mainly useful for highlighting manpage sources.
.. versionadded:: 0.6
"""
name = 'Groff'
aliases = ['groff', 'nroff', 'man']
filenames = ['*.[1234567]', '*.man']
mimetypes = ['application/x-troff', 'text/troff']
tokens = {
'root': [
(r'(\.)(\w+)', bygroups(Text, Keyword), 'request'),
(r'\.', Punctuation, 'request'),
# Regular characters, slurp till we find a backslash or newline
(r'[^\\\n]+', Text, 'textline'),
default('textline'),
],
'textline': [
include('escapes'),
(r'[^\\\n]+', Text),
(r'\n', Text, '#pop'),
],
'escapes': [
# groff has many ways to write escapes.
(r'\\"[^\n]*', Comment),
(r'\\[fn]\w', String.Escape),
(r'\\\(.{2}', String.Escape),
(r'\\.\[.*\]', String.Escape),
(r'\\.', String.Escape),
(r'\\\n', Text, 'request'),
],
'request': [
(r'\n', Text, '#pop'),
include('escapes'),
(r'"[^\n"]+"', String.Double),
(r'\d+', Number),
(r'\S+', String),
(r'\s+', Text),
],
}
def analyse_text(text):
if text[:1] != '.':
return False
if text[:3] == '.\\"':
return True
if text[:4] == '.TH ':
return True
if text[1:3].isalnum() and text[3].isspace():
return 0.9