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 RoboconfInstancesLexer(RegexLexer):
"""
Lexer for `Roboconf <http://roboconf.net/en/roboconf.html>`_ instances files.
.. versionadded:: 2.1
"""
name = 'Roboconf Instances'
aliases = ['roboconf-instances']
filenames = ['*.instances']
flags = re.IGNORECASE | re.MULTILINE
tokens = {
'root': [
# Skip white spaces
(r'\s+', Text),
# Keywords
(words(('instance of', 'import'), suffix=r'\s*\b', prefix=r'\b'), Keyword),
(words(('name', 'count'), suffix=r's*:?', prefix=r'\b'), Name),
(r'\s*[\w.-]+\s*:', Name),
# Comments
(r'#.*\n', Comment),
# Default
(r'[^#]', Text),
(r'.*\n', Text)
]
}
class NesCLexer(CLexer):
"""
For `nesC <https://github.com/tinyos/nesc>`_ source code with preprocessor
directives.
.. versionadded:: 2.0
"""
name = 'nesC'
aliases = ['nesc']
filenames = ['*.nc']
mimetypes = ['text/x-nescsrc']
tokens = {
'statements': [
(words(('abstract', 'as', 'async', 'atomic', 'call', 'command',
'component', 'components', 'configuration', 'event',
'extends', 'generic', 'implementation', 'includes',
'interface', 'module', 'new', 'norace', 'post', 'provides',
'signal', 'task', 'uses'),
suffix=r'\b'), Keyword),
(words(('nx_struct', 'nx_union', 'nx_int8_t', 'nx_int16_t',
'nx_int32_t', 'nx_int64_t', 'nx_uint8_t', 'nx_uint16_t',
'nx_uint32_t', 'nx_uint64_t'),
suffix=r'\b'), Keyword.Type),
inherit,
],
}
class CAmkESLexer(RegexLexer):
"""
Basic lexer for the input language for the
`CAmkES <https://sel4.systems/CAmkES/>`_ component platform.
.. versionadded:: 2.1
"""
name = 'CAmkES'
aliases = ['camkes', 'idl4']
filenames = ['*.camkes', '*.idl4']
tokens = {
'root': [
# C pre-processor directive
(r'^\s*#.*\n', Comment.Preproc),
# Whitespace, comments
(r'\s+', Text),
(r'/\*(.|\n)*?\*/', Comment),
(r'//.*\n', Comment),
(r'[\[(){},.;\]]', Punctuation),
(r'[~!%^&*+=|?:<>/-]', Operator),
(words(('assembly', 'attribute', 'component', 'composition',
'configuration', 'connection', 'connector', 'consumes',
'control', 'dataport', 'Dataport', 'Dataports', 'emits',
'event', 'Event', 'Events', 'export', 'from', 'group',
'hardware', 'has', 'interface', 'Interface', 'maybe',
'procedure', 'Procedure', 'Procedures', 'provides',
'template', 'thread', 'threads', 'to', 'uses', 'with'),
suffix=r'\b'), Keyword),
(words(('bool', 'boolean', 'Buf', 'char', 'character', 'double',
'float', 'in', 'inout', 'int', 'int16_6', 'int32_t',
'int64_t', 'int8_t', 'integer', 'mutex', 'out', 'real',
'refin', 'semaphore', 'signed', 'string', 'struct',
'uint16_t', 'uint32_t', 'uint64_t', 'uint8_t', 'uintptr_t',
'unsigned', 'void'),
suffix=r'\b'), Keyword.Type),
# Recognised attributes
(r'[a-zA-Z_]\w*_(priority|domain|buffer)', Keyword.Reserved),
(words(('dma_pool', 'from_access', 'to_access'),
suffix=r'\b'), Keyword.Reserved),
# CAmkES-level include
(r'import\s+(<[^>]*>|"[^"]*");', Comment.Preproc),
# C-level include
(r'include\s+(<[^>]*>|"[^"]*");', Comment.Preproc),
# Literals
(r'0[xX][\da-fA-F]+', Number.Hex),
(r'-?[\d]+', Number),
(r'-?[\d]+\.[\d]+', Number.Float),
(r'"[^"]*"', String),
(r'[Tt]rue|[Ff]alse', Name.Builtin),
# Identifiers
(r'[a-zA-Z_]\w*', Name),
],
}
class RoboconfGraphLexer(RegexLexer):
"""
Lexer for `Roboconf <http://roboconf.net/en/roboconf.html>`_ graph files.
.. versionadded:: 2.1
"""
name = 'Roboconf Graph'
aliases = ['roboconf-graph']
filenames = ['*.graph']
flags = re.IGNORECASE | re.MULTILINE
tokens = {
'root': [
# Skip white spaces
(r'\s+', Text),
# There is one operator
(r'=', Operator),
# Keywords
(words(('facet', 'import'), suffix=r'\s*\b', prefix=r'\b'), Keyword),
(words((
'installer', 'extends', 'exports', 'imports', 'facets',
'children'), suffix=r'\s*:?', prefix=r'\b'), Name),
# Comments
(r'#.*\n', Comment),
# Default
(r'[^#]', Text),
(r'.*\n', Text)
]
}
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 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 CapDLLexer(RegexLexer):
"""
Basic lexer for
`CapDL <https://ssrg.nicta.com.au/publications/nictaabstracts/Kuz_KLW_10.abstract.pml>`_.
The source of the primary tool that reads such specifications is available
at https://github.com/seL4/capdl/tree/master/capDL-tool. Note that this
lexer only supports a subset of the grammar. For example, identifiers can
shadow type names, but these instances are currently incorrectly
highlighted as types. Supporting this would need a stateful lexer that is
considered unnecessarily complex for now.
.. versionadded:: 2.2
"""
name = 'CapDL'
aliases = ['capdl']
filenames = ['*.cdl']
tokens = {
'root': [
# C pre-processor directive
(r'^\s*#.*\n', Comment.Preproc),
# Whitespace, comments
(r'\s+', Text),
(r'/\*(.|\n)*?\*/', Comment),
(r'(//|--).*\n', Comment),
(r'[<>\[(){},:;=\]]', Punctuation),
(r'\.\.', Punctuation),
(words(('arch', 'arm11', 'caps', 'child_of', 'ia32', 'irq', 'maps',
'objects'),
suffix=r'\b'), Keyword),
(words(('aep', 'asid_pool', 'cnode', 'ep', 'frame', 'io_device',
'io_ports', 'io_pt', 'notification', 'pd', 'pt', 'tcb',
'ut', 'vcpu'),
suffix=r'\b'), Keyword.Type),
# Properties
(words(('asid', 'addr', 'badge', 'cached', 'dom', 'domainID',
'elf', 'fault_ep', 'G', 'guard', 'guard_size', 'init',
'ip', 'prio', 'sp', 'R', 'RG', 'RX', 'RW', 'RWG', 'RWX',
'W', 'WG', 'WX', 'level', 'masked', 'master_reply',
'paddr', 'ports', 'reply', 'uncached'),
suffix=r'\b'), Keyword.Reserved),
# Literals
(r'0[xX][\da-fA-F]+', Number.Hex),
(r'\d+(\.\d+)?(k|M)?', Number),
(words(('bits', ), suffix=r'\b'), Number),
(words(('cspace', 'vspace', 'reply_slot', 'caller_slot',
'ipc_buffer_slot'),
suffix=r'\b'), Number),
# Identifiers
(r'[a-zA-Z_][-@\.\w]*', Name),
],
}
class PlPgsqlLexer(PostgresBase, RegexLexer):
"""
Handle the extra syntax in Pl/pgSQL language.
.. versionadded:: 1.5
"""
name = 'PL/pgSQL'
aliases = ['plpgsql']
mimetypes = ['text/x-plpgsql']
flags = re.IGNORECASE
tokens = {k: l[:] for (k, l) in iteritems(PostgresLexer.tokens)}
# extend the keywords list
for i, pattern in enumerate(tokens['root']):
if pattern[1] == Keyword:
tokens['root'][i] = (words(KEYWORDS + PLPGSQL_KEYWORDS,
suffix=r'\b'), Keyword)
del i
break
else:
assert 0, "SQL keywords not found"
# Add specific PL/pgSQL rules (before the SQL ones)
tokens['root'][:0] = [
(r'\%[a-z]\w*\b', Name.Builtin), # actually, a datatype
(r':=', Operator),
(r'\<\<[a-z]\w*\>\>', Name.Label),
(r'\#[a-z]\w*\b', Keyword.Pseudo), # #variable_conflict
]
class BCLexer(RegexLexer):
"""
A `BC <https://www.gnu.org/software/bc/>`_ lexer.
.. versionadded:: 2.1
"""
name = 'BC'
aliases = ['bc']
filenames = ['*.bc']
tokens = {
'root': [
(r'/\*', Comment.Multiline, 'comment'),
(r'"(?:[^"\\]|\\.)*"', String),
(r'[{}();,]', Punctuation),
(words(('if', 'else', 'while', 'for', 'break', 'continue',
'halt', 'return', 'define', 'auto', 'print', 'read',
'length', 'scale', 'sqrt', 'limits', 'quit',
'warranty'), suffix=r'\b'), Keyword),
(r'\+\+|--|\|\||&&|'
r'([-<>+*%\^/!=])=?', Operator),
# bc doesn't support exponential
(r'[0-9]+(\.[0-9]*)?', Number),
(r'\.[0-9]+', Number),
(r'.', Text)
],
'comment': [
(r'[^*/]+', Comment.Multiline),
(r'\*/', Comment.Multiline, '#pop'),
(r'[*/]', Comment.Multiline)
],
}
class SilverLexer(RegexLexer):
"""
For `Silver <https://bitbucket.org/viperproject/silver>`_ source code.
.. versionadded:: 2.2
"""
name = 'Silver'
aliases = ['silver']
filenames = ['*.sil', '*.vpr']
tokens = {
'root': [
# Whitespace and Comments
(r'\n', Whitespace),
(r'\s+', Whitespace),
(r'//[/!](.*?)\n', Comment.Doc),
(r'//(.*?)\n', Comment.Single),
(r'/\*', Comment.Multiline, 'comment'),
(words(('result', 'true', 'false', 'null', 'method', 'function',
'predicate', 'program', 'domain', 'axiom', 'var',
'returns', 'field', 'define', 'requires', 'ensures',
'invariant', 'fold', 'unfold', 'inhale', 'exhale', 'new',
'assert', 'assume', 'goto', 'while', 'if', 'elseif',
'else', 'fresh', 'constraining', 'Seq', 'Set', 'Multiset',
'union', 'intersection', 'setminus', 'subset', 'unfolding',
'in', 'old', 'forall', 'exists', 'acc', 'wildcard',
'write', 'none', 'epsilon', 'perm', 'unique', 'apply',
'package', 'folding', 'label', 'forperm'),
suffix=r'\b'), Keyword),
(words(('Int', 'Perm', 'Bool', 'Ref'),
suffix=r'\b'), Keyword.Type),
include('numbers'),
(r'[!%&*+=|?:<>/\-\[\]]', Operator),
(r'([{}():;,.])', Punctuation),
# Identifier
(r'[\w$]\w*', Name),
],
'comment': [
(r'[^*/]+', Comment.Multiline),
(r'/\*', Comment.Multiline, '#push'),
(r'\*/', Comment.Multiline, '#pop'),
(r'[*/]', Comment.Multiline),
],
'numbers': [
(r'[0-9]+', Number.Integer),
],
}
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
class MaqlLexer(RegexLexer):
"""
Lexer for `GoodData MAQL
<https://secure.gooddata.com/docs/html/advanced.metric.tutorial.html>`_
scripts.
.. versionadded:: 1.4
"""
name = 'MAQL'
aliases = ['maql']
filenames = ['*.maql']
mimetypes = ['text/x-gooddata-maql', 'application/x-gooddata-maql']
flags = re.IGNORECASE
tokens = {
'root': [
# IDENTITY
(r'IDENTIFIER\b', Name.Builtin),
# IDENTIFIER
(r'\{[^}]+\}', Name.Variable),
# NUMBER
(r'[0-9]+(?:\.[0-9]+)?(?:e[+-]?[0-9]{1,3})?', Number),
# STRING
(r'"', String, 'string-literal'),
# RELATION
(r'\<\>|\!\=', Operator),
(r'\=|\>\=|\>|\<\=|\<', Operator),
# :=
(r'\:\=', Operator),
# OBJECT
(r'\[[^]]+\]', Name.Variable.Class),
# keywords
(words(
('DIMENSION', 'DIMENSIONS', 'BOTTOM', 'METRIC', 'COUNT',
'OTHER', 'FACT', 'WITH', 'TOP', 'OR', 'ATTRIBUTE', 'CREATE',
'PARENT', 'FALSE', 'ROW', 'ROWS', 'FROM', 'ALL', 'AS', 'PF',
'COLUMN', 'COLUMNS', 'DEFINE', 'REPORT', 'LIMIT', 'TABLE',
'LIKE', 'AND', 'BY', 'BETWEEN', 'EXCEPT', 'SELECT', 'MATCH',
'WHERE', 'TRUE', 'FOR', 'IN', 'WITHOUT', 'FILTER', 'ALIAS',
'WHEN', 'NOT', 'ON', 'KEYS', 'KEY', 'FULLSET', 'PRIMARY',
'LABELS', 'LABEL', 'VISUAL', 'TITLE', 'DESCRIPTION', 'FOLDER',
'ALTER', 'DROP', 'ADD', 'DATASET', 'DATATYPE', 'INT',
'BIGINT', 'DOUBLE', 'DATE', 'VARCHAR', 'DECIMAL',
'SYNCHRONIZE', 'TYPE', 'DEFAULT', 'ORDER', 'ASC', 'DESC',
'HYPERLINK', 'INCLUDE', 'TEMPLATE', 'MODIFY'),
suffix=r'\b'), Keyword),
# FUNCNAME
(r'[a-z]\w*\b', Name.Function),
# Comments
(r'#.*', Comment.Single),
# Punctuation
(r'[,;()]', Punctuation),
# Space is not significant
(r'\s+', Text)
],
'string-literal': [(r'\\[tnrfbae"\\]', String.Escape),
(r'"', String, '#pop'), (r'[^\\"]+', String)],
}
class MathematicaLexer(RegexLexer):
"""
Lexer for `Mathematica <http://www.wolfram.com/mathematica/>`_ source code.
.. versionadded:: 2.0
"""
name = 'Mathematica'
aliases = ['mathematica', 'mma', 'nb']
filenames = ['*.nb', '*.cdf', '*.nbp', '*.ma']
mimetypes = ['application/mathematica',
'application/vnd.wolfram.mathematica',
'application/vnd.wolfram.mathematica.package',
'application/vnd.wolfram.cdf']
# http://reference.wolfram.com/mathematica/guide/Syntax.html
operators = (
";;", "=", "=.", "!=" "==", ":=", "->", ":>", "/.", "+", "-", "*", "/",
"^", "&&", "||", "!", "<>", "|", "/;", "?", "@", "//", "/@", "@@",
"@@@", "~~", "===", "&", "<", ">", "<=", ">=",
)
punctuation = (",", ";", "(", ")", "[", "]", "{", "}")
def _multi_escape(entries):
return '(%s)' % ('|'.join(re.escape(entry) for entry in entries))
tokens = {
'root': [
(r'(?s)\(\*.*?\*\)', Comment),
(r'([a-zA-Z]+[A-Za-z0-9]*`)', Name.Namespace),
(r'([A-Za-z0-9]*_+[A-Za-z0-9]*)', Name.Variable),
(r'#\d*', Name.Variable),
(r'([a-zA-Z]+[a-zA-Z0-9]*)', Name),
(r'-?\d+\.\d*', Number.Float),
(r'-?\d*\.\d+', Number.Float),
(r'-?\d+', Number.Integer),
(words(operators), Operator),
(words(punctuation), Punctuation),
(r'".*?"', String),
(r'\s+', Text.Whitespace),
],
}
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 BSTLexer(RegexLexer):
"""
A lexer for BibTeX bibliography styles.
.. versionadded:: 2.2
"""
name = 'BST'
aliases = ['bst', 'bst-pybtex']
filenames = ['*.bst']
flags = re.IGNORECASE | re.MULTILINE
tokens = {
'root': [
include('whitespace'),
(words(['read', 'sort']), Keyword),
(words(['execute', 'integers', 'iterate', 'reverse',
'strings']), Keyword, ('group')),
(words(['function', 'macro']), Keyword, ('group', 'group')),
(words(['entry']), Keyword, ('group', 'group', 'group')),
],
'group': [
include('whitespace'),
(r'\{', Punctuation, ('#pop', 'group-end', 'body')),
],
'group-end': [
include('whitespace'),
(r'\}', Punctuation, '#pop'),
],
'body': [
include('whitespace'),
(r"\'[^#\"\{\}\s]+", Name.Function),
(r'[^#\"\{\}\s]+\$', Name.Builtin),
(r'[^#\"\{\}\s]+', Name.Variable),
(r'"[^\"]*"', String),
(r'#-?\d+', Number),
(r'\{', Punctuation, ('group-end', 'body')),
default('#pop'),
],
'whitespace': [
(r'\s+', Text),
('%.*?$', Comment.SingleLine),
],
}
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 BoogieLexer(RegexLexer):
"""
For `Boogie <https://boogie.codeplex.com/>`_ source code.
.. versionadded:: 2.1
"""
name = 'Boogie'
aliases = ['boogie']
filenames = ['*.bpl']
tokens = {
'root': [
# Whitespace and Comments
(r'\n', Whitespace),
(r'\s+', Whitespace),
(r'//[/!](.*?)\n', Comment.Doc),
(r'//(.*?)\n', Comment.Single),
(r'/\*', Comment.Multiline, 'comment'),
(words(('axiom', 'break', 'call', 'ensures', 'else', 'exists',
'function', 'forall', 'if', 'invariant', 'modifies',
'procedure', 'requires', 'then', 'var', 'while'),
suffix=r'\b'), Keyword),
(words(('const', ), suffix=r'\b'), Keyword.Reserved),
(words(('bool', 'int', 'ref'), suffix=r'\b'), Keyword.Type),
include('numbers'),
(r"(>=|<=|:=|!=|==>|&&|\|\||[+/\-=>*<\[\]])", Operator),
(r"([{}():;,.])", Punctuation),
# Identifier
(r'[a-zA-Z_]\w*', Name),
],
'comment': [
(r'[^*/]+', Comment.Multiline),
(r'/\*', Comment.Multiline, '#push'),
(r'\*/', Comment.Multiline, '#pop'),
(r'[*/]', Comment.Multiline),
],
'numbers': [
(r'[0-9]+', Number.Integer),
],
}
class EiffelLexer(RegexLexer):
"""
For `Eiffel <http://www.eiffel.com>`_ source code.
.. versionadded:: 2.0
"""
name = 'Eiffel'
aliases = ['eiffel']
filenames = ['*.e']
mimetypes = ['text/x-eiffel']
tokens = {
'root': [
(r'[^\S\n]+', Text),
(r'--.*?\n', Comment.Single),
(r'[^\S\n]+', Text),
# Please note that keyword and operator are case insensitive.
(r'(?i)(true|false|void|current|result|precursor)\b',
Keyword.Constant),
(r'(?i)(and(\s+then)?|not|xor|implies|or(\s+else)?)\b',
Operator.Word),
(words(
('across', 'agent', 'alias', 'all', 'as', 'assign', 'attached',
'attribute', 'check', 'class', 'convert', 'create', 'debug',
'deferred', 'detachable', 'do', 'else', 'elseif', 'end',
'ensure', 'expanded', 'export', 'external', 'feature', 'from',
'frozen', 'if', 'inherit', 'inspect', 'invariant', 'like',
'local', 'loop', 'none', 'note', 'obsolete', 'old', 'once',
'only', 'redefine', 'rename', 'require', 'rescue', 'retry',
'select', 'separate', 'then', 'undefine', 'until', 'variant',
'when'),
prefix=r'(?i)\b',
suffix=r'\b'), Keyword.Reserved),
(r'"\[(([^\]%]|\n)|%(.|\n)|\][^"])*?\]"', String),
(r'"([^"%\n]|%.)*?"', String),
include('numbers'),
(r"'([^'%]|%'|%%)'", String.Char),
(r"(//|\\\\|>=|<=|:=|/=|~|/~|[\\?!#%&@|+/\-=>*$<^\[\]])",
Operator),
(r"([{}():;,.])", Punctuation),
(r'([a-z]\w*)|([A-Z][A-Z0-9_]*[a-z]\w*)', Name),
(r'([A-Z][A-Z0-9_]*)', Name.Class),
(r'\n+', Text),
],
'numbers': [
(r'0[xX][a-fA-F0-9]+', Number.Hex),
(r'0[bB][01]+', Number.Bin),
(r'0[cC][0-7]+', Number.Oct),
(r'([0-9]+\.[0-9]*)|([0-9]*\.[0-9]+)', Number.Float),
(r'[0-9]+', Number.Integer),
],
}
class NitLexer(RegexLexer):
"""
For `nit <http://nitlanguage.org>`_ source.
.. versionadded:: 2.0
"""
name = 'Nit'
aliases = ['nit']
filenames = ['*.nit']
tokens = {
'root': [
(r'#.*?$', Comment.Single),
(words(('package', 'module', 'import', 'class', 'abstract',
'interface', 'universal', 'enum', 'end', 'fun', 'type',
'init', 'redef', 'isa', 'do', 'readable', 'writable',
'var', 'intern', 'extern', 'public', 'protected',
'private', 'intrude', 'if', 'then', 'else', 'while',
'loop', 'for', 'in', 'and', 'or', 'not', 'implies',
'return', 'continue', 'break', 'abort', 'assert', 'new',
'is', 'once', 'super', 'self', 'true', 'false', 'nullable',
'null', 'as', 'isset', 'label', '__debug__'),
suffix=r'(?=[\r\n\t( ])'), Keyword),
(r'[A-Z]\w*', Name.Class),
(r'"""(([^\'\\]|\\.)|\\r|\\n)*((\{\{?)?(""?\{\{?)*""""*)',
String), # Simple long string
(r'\'\'\'(((\\.|[^\'\\])|\\r|\\n)|\'((\\.|[^\'\\])|\\r|\\n)|'
r'\'\'((\\.|[^\'\\])|\\r|\\n))*\'\'\'',
String), # Simple long string alt
(r'"""(([^\'\\]|\\.)|\\r|\\n)*((""?)?(\{\{?""?)*\{\{\{\{*)',
String), # Start long string
(r'\}\}\}(((\\.|[^\'\\])|\\r|\\n))*(""?)?(\{\{?""?)*\{\{\{\{*',
String), # Mid long string
(r'\}\}\}(((\\.|[^\'\\])|\\r|\\n))*(\{\{?)?(""?\{\{?)*""""*',
String), # End long string
(r'"(\\.|([^"}{\\]))*"', String), # Simple String
(r'"(\\.|([^"}{\\]))*\{', String), # Start string
(r'\}(\\.|([^"}{\\]))*\{', String), # Mid String
(r'\}(\\.|([^"}{\\]))*"', String), # End String
(r'(\'[^\'\\]\')|(\'\\.\')', String.Char),
(r'[0-9]+', Number.Integer),
(r'[0-9]*.[0-9]+', Number.Float),
(r'0(x|X)[0-9A-Fa-f]+', Number.Hex),
(r'[a-z]\w*', Name),
(r'_\w+', Name.Variable.Instance),
(r'==|!=|<==>|>=|>>|>|<=|<<|<|\+|-|=|/|\*|%|\+=|-=|!|@', Operator),
(r'\(|\)|\[|\]|,|\.\.\.|\.\.|\.|::|:', Punctuation),
(r'`\{[^`]*`\}', Text), # Extern blocks won't be Lexed by Nit
(r'[\r\n\t ]+', Text),
],
}
class OpenEdgeLexer(RegexLexer):
"""
Lexer for `OpenEdge ABL (formerly Progress)
<http://web.progress.com/en/openedge/abl.html>`_ source code.
.. versionadded:: 1.5
"""
name = 'OpenEdge ABL'
aliases = ['openedge', 'abl', 'progress']
filenames = ['*.p', '*.cls']
mimetypes = ['text/x-openedge', 'application/x-openedge']
types = (
r'(?i)(^|(?<=[^\w\-]))(CHARACTER|CHAR|CHARA|CHARAC|CHARACT|CHARACTE|'
r'COM-HANDLE|DATE|DATETIME|DATETIME-TZ|'
r'DECIMAL|DEC|DECI|DECIM|DECIMA|HANDLE|'
r'INT64|INTEGER|INT|INTE|INTEG|INTEGE|'
r'LOGICAL|LONGCHAR|MEMPTR|RAW|RECID|ROWID)\s*($|(?=[^\w\-]))')
keywords = words(OPENEDGEKEYWORDS,
prefix=r'(?i)(^|(?<=[^\w\-]))',
suffix=r'\s*($|(?=[^\w\-]))')
tokens = {
'root': [
(r'/\*', Comment.Multiline, 'comment'),
(r'\{', Comment.Preproc, 'preprocessor'),
(r'\s*&.*', Comment.Preproc),
(r'0[xX][0-9a-fA-F]+[LlUu]*', Number.Hex),
(r'(?i)(DEFINE|DEF|DEFI|DEFIN)\b', Keyword.Declaration),
(types, Keyword.Type),
(keywords, Name.Builtin),
(r'"(\\\\|\\"|[^"])*"', String.Double),
(r"'(\\\\|\\'|[^'])*'", String.Single),
(r'[0-9][0-9]*\.[0-9]+([eE][0-9]+)?[fd]?', Number.Float),
(r'[0-9]+', Number.Integer),
(r'\s+', Text),
(r'[+*/=-]', Operator),
(r'[.:()]', Punctuation),
(r'.', Name.Variable), # Lazy catch-all
],
'comment': [(r'[^*/]', Comment.Multiline),
(r'/\*', Comment.Multiline, '#push'),
(r'\*/', Comment.Multiline, '#pop'),
(r'[*/]', Comment.Multiline)],
'preprocessor': [
(r'[^{}]', Comment.Preproc),
(r'\{', Comment.Preproc, '#push'),
(r'\}', Comment.Preproc, '#pop'),
],
}
class MozPreprocHashLexer(RegexLexer):
"""
Lexer for Mozilla Preprocessor files (with '#' as the marker).
Other data is left untouched.
.. versionadded:: 2.0
"""
name = 'mozhashpreproc'
aliases = [name]
filenames = []
mimetypes = []
tokens = {
'root': [
(r'^#', Comment.Preproc, ('expr', 'exprstart')),
(r'.+', Other),
],
'exprstart': [
(r'(literal)(.*)', bygroups(Comment.Preproc, Text), '#pop:2'),
(words(('define', 'undef', 'if', 'ifdef', 'ifndef', 'else', 'elif',
'elifdef', 'elifndef', 'endif', 'expand', 'filter',
'unfilter', 'include', 'includesubst', 'error')),
Comment.Preproc, '#pop'),
],
'expr': [
(words(('!', '!=', '==', '&&', '||')), Operator),
(r'(defined)(\()', bygroups(Keyword, Punctuation)),
(r'\)', Punctuation),
(r'[0-9]+', Number.Decimal),
(r'__\w+?__', Name.Variable),
(r'@\w+?@', Name.Class),
(r'\w+', Name),
(r'\n', Text, '#pop'),
(r'\s+', Text),
(r'\S', Punctuation),
],
}
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,
],
'classname': [
(r'[a-zA-Z_]\w*', Name.Class, '#pop'),
# template specification
(r'\s*(?=>)', Text, '#pop'),
],
}
class MqlLexer(CppLexer):
"""
For `MQL4 <http://docs.mql4.com/>`_ and
`MQL5 <http://www.mql5.com/en/docs>`_ source code.
.. versionadded:: 2.0
"""
name = 'MQL'
aliases = ['mql', 'mq4', 'mq5', 'mql4', 'mql5']
filenames = ['*.mq4', '*.mq5', '*.mqh']
mimetypes = ['text/x-mql']
tokens = {
'statements': [
(words(_mql_builtins.keywords, suffix=r'\b'), Keyword),
(words(_mql_builtins.c_types, suffix=r'\b'), Keyword.Type),
(words(_mql_builtins.types, suffix=r'\b'), Name.Function),
(words(_mql_builtins.constants, suffix=r'\b'), Name.Constant),
(words(_mql_builtins.colors, prefix='(clr)?',
suffix=r'\b'), Name.Constant),
inherit,
],
}
class AmbientTalkLexer(RegexLexer):
"""
Lexer for `AmbientTalk <https://code.google.com/p/ambienttalk>`_ source code.
.. versionadded:: 2.0
"""
name = 'AmbientTalk'
filenames = ['*.at']
aliases = ['at', 'ambienttalk', 'ambienttalk/2']
mimetypes = ['text/x-ambienttalk']
flags = re.MULTILINE | re.DOTALL
builtin = words(('if:', 'then:', 'else:', 'when:', 'whenever:',
'discovered:', 'disconnected:', 'reconnected:',
'takenOffline:', 'becomes:', 'export:', 'as:', 'object:',
'actor:', 'mirror:', 'taggedAs:', 'mirroredBy:', 'is:'))
tokens = {
'root': [
(r'\s+', Text),
(r'//.*?\n', Comment.Single),
(r'/\*.*?\*/', Comment.Multiline),
(r'(def|deftype|import|alias|exclude)\b', Keyword),
(builtin, Name.Builtin),
(r'(true|false|nil)\b', Keyword.Constant),
(r'(~|lobby|jlobby|/)\.', Keyword.Constant, 'namespace'),
(r'"(\\\\|\\"|[^"])*"', String),
(r'\|', Punctuation, 'arglist'),
(r'<:|[*^!%&<>+=,./?-]|:=', Operator),
(r"`[a-zA-Z_]\w*", String.Symbol),
(r"[a-zA-Z_]\w*:", Name.Function),
(r"[{}()\[\];`]", Punctuation),
(r'(self|super)\b', Name.Variable.Instance),
(r"[a-zA-Z_]\w*", Name.Variable),
(r"@[a-zA-Z_]\w*", Name.Class),
(r"@\[", Name.Class, 'annotations'),
include('numbers'),
],
'numbers': [(r'(\d+\.\d*|\d*\.\d+)([eE][+-]?[0-9]+)?', Number.Float),
(r'\d+', Number.Integer)],
'namespace': [(r'[a-zA-Z_]\w*\.', Name.Namespace),
(r'[a-zA-Z_]\w*:', Name.Function, '#pop'),
(r'[a-zA-Z_]\w*(?!\.)', Name.Function, '#pop')],
'annotations': [(r"(.*?)\]", Name.Class, '#pop')],
'arglist': [
(r'\|', Punctuation, '#pop'),
(r'\s*(,)\s*', Punctuation),
(r'[a-zA-Z_]\w*', Name.Variable),
],
}
class PikeLexer(CppLexer):
"""
For `Pike <http://pike.lysator.liu.se/>`_ source code.
.. versionadded:: 2.0
"""
name = 'Pike'
aliases = ['pike']
filenames = ['*.pike', '*.pmod']
mimetypes = ['text/x-pike']
tokens = {
'statements': [
(words(('catch', 'new', 'private', 'protected', 'public', 'gauge',
'throw', 'throws', 'class', 'interface', 'implement',
'abstract', 'extends', 'from', 'this', 'super', 'constant',
'final', 'static', 'import', 'use', 'extern', 'inline',
'proto', 'break', 'continue', 'if', 'else', 'for', 'while',
'do', 'switch', 'case', 'as', 'in', 'version', 'return',
'true', 'false', 'null', '__VERSION__', '__MAJOR__',
'__MINOR__', '__BUILD__', '__REAL_VERSION__',
'__REAL_MAJOR__', '__REAL_MINOR__', '__REAL_BUILD__',
'__DATE__', '__TIME__', '__FILE__', '__DIR__', '__LINE__',
'__AUTO_BIGNUM__', '__NT__', '__PIKE__', '__amigaos__',
'_Pragma', 'static_assert', 'defined', 'sscanf'),
suffix=r'\b'), Keyword),
(r'(bool|int|long|float|short|double|char|string|object|void|mapping|'
r'array|multiset|program|function|lambda|mixed|'
r'[a-z_][a-z0-9_]*_t)\b', Keyword.Type),
(r'(class)(\s+)', bygroups(Keyword, Text), 'classname'),
(r'[~!%^&*+=|?:<>/@-]', Operator),
inherit,
],
'classname': [
(r'[a-zA-Z_]\w*', Name.Class, '#pop'),
# template specification
(r'\s*(?=>)', Text, '#pop'),
],
}
class NuSMVLexer(RegexLexer):
"""
Lexer for the NuSMV language.
.. versionadded:: 2.2
"""
name = 'NuSMV'
aliases = ['nusmv']
filenames = ['*.smv']
mimetypes = []
tokens = {
'root': [
# Comments
(r'(?s)\/\-\-.*?\-\-/', Comment),
(r'--.*\n', Comment),
# Reserved
(words(('MODULE', 'DEFINE', 'MDEFINE', 'CONSTANTS', 'VAR', 'IVAR',
'FROZENVAR', 'INIT', 'TRANS', 'INVAR', 'SPEC', 'CTLSPEC',
'LTLSPEC', 'PSLSPEC', 'COMPUTE', 'NAME', 'INVARSPEC',
'FAIRNESS', 'JUSTICE', 'COMPASSION', 'ISA', 'ASSIGN',
'CONSTRAINT', 'SIMPWFF', 'CTLWFF', 'LTLWFF', 'PSLWFF',
'COMPWFF', 'IN', 'MIN', 'MAX', 'MIRROR', 'PRED',
'PREDICATES'), suffix=r'(?![\w$#-])'),
Keyword.Declaration),
(r'process(?![\w$#-])', Keyword),
(words(('array', 'of', 'boolean', 'integer', 'real', 'word'),
suffix=r'(?![\w$#-])'), Keyword.Type),
(words(('case', 'esac'), suffix=r'(?![\w$#-])'), Keyword),
(words(('word1', 'bool', 'signed', 'unsigned', 'extend', 'resize',
'sizeof', 'uwconst', 'swconst', 'init', 'self', 'count',
'abs', 'max', 'min'), suffix=r'(?![\w$#-])'),
Name.Builtin),
(words(('EX', 'AX', 'EF', 'AF', 'EG', 'AG', 'E', 'F', 'O', 'G',
'H', 'X', 'Y', 'Z', 'A', 'U', 'S', 'V', 'T', 'BU', 'EBF',
'ABF', 'EBG', 'ABG', 'next', 'mod', 'union', 'in', 'xor',
'xnor'), suffix=r'(?![\w$#-])'),
Operator.Word),
(words(('TRUE', 'FALSE'), suffix=r'(?![\w$#-])'), Keyword.Constant),
# Names
(r'[a-zA-Z_][\w$#-]*', Name.Variable),
# Operators
(r':=', Operator),
(r'[-&|+*/<>!=]', Operator),
# Literals
(r'\-?\d+\b', Number.Integer),
(r'0[su][bB]\d*_[01_]+', Number.Bin),
(r'0[su][oO]\d*_[0-7_]+', Number.Oct),
(r'0[su][dD]\d*_[\d_]+', Number.Dec),
(r'0[su][hH]\d*_[\da-fA-F_]+', Number.Hex),
# Whitespace, punctuation and the rest
(r'\s+', Text.Whitespace),
(r'[()\[\]{};?:.,]', Punctuation),
],
}
class AmplLexer(RegexLexer):
"""
For `AMPL <http://ampl.com/>`_ source code.
.. versionadded:: 2.2
"""
name = 'Ampl'
aliases = ['ampl']
filenames = ['*.run']
tokens = {
'root': [
(r'\n', Text),
(r'\s+', Text.Whitespace),
(r'#.*?\n', Comment.Single),
(r'/[*](.|\n)*?[*]/', Comment.Multiline),
(words(
('call', 'cd', 'close', 'commands', 'data', 'delete',
'display', 'drop', 'end', 'environ', 'exit', 'expand',
'include', 'load', 'model', 'objective', 'option', 'problem',
'purge', 'quit', 'redeclare', 'reload', 'remove', 'reset',
'restore', 'shell', 'show', 'solexpand', 'solution', 'solve',
'update', 'unload', 'xref', 'coeff', 'coef', 'cover', 'obj',
'interval', 'default', 'from', 'to', 'to_come', 'net_in',
'net_out', 'dimen', 'dimension', 'check', 'complements',
'write', 'function', 'pipe', 'format', 'if', 'then', 'else',
'in', 'while', 'repeat', 'for'),
suffix=r'\b'), Keyword.Reserved),
(r'(integer|binary|symbolic|ordered|circular|reversed|INOUT|IN|OUT|LOCAL)',
Keyword.Type),
(r'\".*?\"', String.Double),
(r'\'.*?\'', String.Single),
(r'[()\[\]{},;:]+', Punctuation),
(r'\b(\w+)(\.)(astatus|init0|init|lb0|lb1|lb2|lb|lrc|'
r'lslack|rc|relax|slack|sstatus|status|ub0|ub1|ub2|'
r'ub|urc|uslack|val)',
bygroups(Name.Variable, Punctuation, Keyword.Reserved)),
(r'(set|param|var|arc|minimize|maximize|subject to|s\.t\.|subj to|'
r'node|table|suffix|read table|write table)(\s+)(\w+)',
bygroups(Keyword.Declaration, Text, Name.Variable)),
(r'(param)(\s*)(:)(\s*)(\w+)(\s*)(:)(\s*)((\w|\s)+)',
bygroups(Keyword.Declaration, Text, Punctuation, Text,
Name.Variable, Text, Punctuation, Text, Name.Variable)),
(r'(let|fix|unfix)(\s*)((?:\{.*\})?)(\s*)(\w+)',
bygroups(Keyword.Declaration, Text, using(this), Text,
Name.Variable)),
(words(('abs', 'acos', 'acosh', 'alias', 'asin', 'asinh', 'atan',
'atan2', 'atanh', 'ceil', 'ctime', 'cos', 'exp', 'floor',
'log', 'log10', 'max', 'min', 'precision', 'round', 'sin',
'sinh', 'sqrt', 'tan', 'tanh', 'time', 'trunc', 'Beta',
'Cauchy', 'Exponential', 'Gamma', 'Irand224', 'Normal',
'Normal01', 'Poisson', 'Uniform', 'Uniform01', 'num',
'num0', 'ichar', 'char', 'length', 'substr', 'sprintf',
'match', 'sub', 'gsub', 'print', 'printf', 'next', 'nextw',
'prev', 'prevw', 'first', 'last', 'ord', 'ord0', 'card',
'arity', 'indexarity'),
prefix=r'\b',
suffix=r'\b'), Name.Builtin),
(r'(\+|\-|\*|/|\*\*|=|<=|>=|==|\||\^|<|>|\!|\.\.|:=|\&|\!=|<<|>>)',
Operator),
(words(('or', 'exists', 'forall', 'and', 'in', 'not', 'within',
'union', 'diff', 'difference', 'symdiff', 'inter',
'intersect', 'intersection', 'cross', 'setof', 'by',
'less', 'sum', 'prod', 'product', 'div', 'mod'),
suffix=r'\b'), Keyword.Reserved
), # Operator.Name but not enough emphasized with that
(r'(\d+\.(?!\.)\d*|\.(?!.)\d+)([eE][+-]?\d+)?', Number.Float),
(r'\d+([eE][+-]?\d+)?', Number.Integer),
(r'[+-]?Infinity', Number.Integer),
(r'(\w+|(\.(?!\.)))', Text)
]
}
class PerlLexer(RegexLexer):
"""
For `Perl <http://www.perl.org>`_ source code.
"""
name = 'Perl'
aliases = ['perl', 'pl']
filenames = ['*.pl', '*.pm', '*.t']
mimetypes = ['text/x-perl', 'application/x-perl']
flags = re.DOTALL | re.MULTILINE
# TODO: give this to a perl guy who knows how to parse perl...
tokens = {
'balanced-regex': [
(r'/(\\\\|\\[^\\]|[^\\/])*/[egimosx]*', String.Regex, '#pop'),
(r'!(\\\\|\\[^\\]|[^\\!])*![egimosx]*', String.Regex, '#pop'),
(r'\\(\\\\|[^\\])*\\[egimosx]*', String.Regex, '#pop'),
(r'\{(\\\\|\\[^\\]|[^\\}])*\}[egimosx]*', String.Regex, '#pop'),
(r'<(\\\\|\\[^\\]|[^\\>])*>[egimosx]*', String.Regex, '#pop'),
(r'\[(\\\\|\\[^\\]|[^\\\]])*\][egimosx]*', String.Regex, '#pop'),
(r'\((\\\\|\\[^\\]|[^\\)])*\)[egimosx]*', String.Regex, '#pop'),
(r'@(\\\\|\\[^\\]|[^\\@])*@[egimosx]*', String.Regex, '#pop'),
(r'%(\\\\|\\[^\\]|[^\\%])*%[egimosx]*', String.Regex, '#pop'),
(r'\$(\\\\|\\[^\\]|[^\\$])*\$[egimosx]*', String.Regex, '#pop'),
],
'root': [
(r'\A\#!.+?$', Comment.Hashbang),
(r'\#.*?$', Comment.Single),
(r'^=[a-zA-Z0-9]+\s+.*?\n=cut', Comment.Multiline),
(words(('case', 'continue', 'do', 'else', 'elsif', 'for',
'foreach', 'if', 'last', 'my', 'next', 'our', 'redo',
'reset', 'then', 'unless', 'until', 'while', 'print',
'new', 'BEGIN', 'CHECK', 'INIT', 'END', 'return'),
suffix=r'\b'), Keyword),
(r'(format)(\s+)(\w+)(\s*)(=)(\s*\n)',
bygroups(Keyword, Text, Name, Text, Punctuation, Text), 'format'),
(r'(eq|lt|gt|le|ge|ne|not|and|or|cmp)\b', Operator.Word),
# common delimiters
(r's/(\\\\|\\[^\\]|[^\\/])*/(\\\\|\\[^\\]|[^\\/])*/[egimosx]*',
String.Regex),
(r's!(\\\\|\\!|[^!])*!(\\\\|\\!|[^!])*![egimosx]*', String.Regex),
(r's\\(\\\\|[^\\])*\\(\\\\|[^\\])*\\[egimosx]*', String.Regex),
(r's@(\\\\|\\[^\\]|[^\\@])*@(\\\\|\\[^\\]|[^\\@])*@[egimosx]*',
String.Regex),
(r's%(\\\\|\\[^\\]|[^\\%])*%(\\\\|\\[^\\]|[^\\%])*%[egimosx]*',
String.Regex),
# balanced delimiters
(r's\{(\\\\|\\[^\\]|[^\\}])*\}\s*', String.Regex, 'balanced-regex'
),
(r's<(\\\\|\\[^\\]|[^\\>])*>\s*', String.Regex, 'balanced-regex'),
(r's\[(\\\\|\\[^\\]|[^\\\]])*\]\s*', String.Regex,
'balanced-regex'),
(r's\((\\\\|\\[^\\]|[^\\)])*\)\s*', String.Regex,
'balanced-regex'),
(r'm?/(\\\\|\\[^\\]|[^\\/\n])*/[gcimosx]*', String.Regex),
(r'm(?=[/!\\{<\[(@%$])', String.Regex, 'balanced-regex'),
(r'((?<==~)|(?<=\())\s*/(\\\\|\\[^\\]|[^\\/])*/[gcimosx]*',
String.Regex),
(r'\s+', Text),
(words(
('abs', 'accept', 'alarm', 'atan2', 'bind', 'binmode', 'bless',
'caller', 'chdir', 'chmod', 'chomp', 'chop', 'chown', 'chr',
'chroot', 'close', 'closedir', 'connect', 'continue', 'cos',
'crypt', 'dbmclose', 'dbmopen', 'defined', 'delete', 'die',
'dump', 'each', 'endgrent', 'endhostent', 'endnetent',
'endprotoent', 'endpwent', 'endservent', 'eof', 'eval',
'exec', 'exists', 'exit', 'exp', 'fcntl', 'fileno', 'flock',
'fork', 'format', 'formline', 'getc', 'getgrent', 'getgrgid',
'getgrnam', 'gethostbyaddr', 'gethostbyname', 'gethostent',
'getlogin', 'getnetbyaddr', 'getnetbyname', 'getnetent',
'getpeername', 'getpgrp', 'getppid', 'getpriority',
'getprotobyname', 'getprotobynumber', 'getprotoent',
'getpwent', 'getpwnam', 'getpwuid', 'getservbyname',
'getservbyport', 'getservent', 'getsockname', 'getsockopt',
'glob', 'gmtime', 'goto', 'grep', 'hex', 'import', 'index',
'int', 'ioctl', 'join', 'keys', 'kill', 'last', 'lc',
'lcfirst', 'length', 'link', 'listen', 'local', 'localtime',
'log', 'lstat', 'map', 'mkdir', 'msgctl', 'msgget', 'msgrcv',
'msgsnd', 'my', 'next', 'oct', 'open', 'opendir', 'ord',
'our', 'pack', 'pipe', 'pop', 'pos', 'printf', 'prototype',
'push', 'quotemeta', 'rand', 'read', 'readdir', 'readline',
'readlink', 'readpipe', 'recv', 'redo', 'ref', 'rename',
'reverse', 'rewinddir', 'rindex', 'rmdir', 'scalar', 'seek',
'seekdir', 'select', 'semctl', 'semget', 'semop', 'send',
'setgrent', 'sethostent', 'setnetent', 'setpgrp',
'setpriority', 'setprotoent', 'setpwent', 'setservent',
'setsockopt', 'shift', 'shmctl', 'shmget', 'shmread',
'shmwrite', 'shutdown', 'sin', 'sleep', 'socket',
'socketpair', 'sort', 'splice', 'split', 'sprintf', 'sqrt',
'srand', 'stat', 'study', 'substr', 'symlink', 'syscall',
'sysopen', 'sysread', 'sysseek', 'system', 'syswrite', 'tell',
'telldir', 'tie', 'tied', 'time', 'times', 'tr', 'truncate',
'uc', 'ucfirst', 'umask', 'undef', 'unlink', 'unpack',
'unshift', 'untie', 'utime', 'values', 'vec', 'wait',
'waitpid', 'wantarray', 'warn', 'write'),
suffix=r'\b'), Name.Builtin),
(r'((__(DATA|DIE|WARN)__)|(STD(IN|OUT|ERR)))\b',
Name.Builtin.Pseudo),
(r'(<<)([\'"]?)([a-zA-Z_]\w*)(\2;?\n.*?\n)(\3)(\n)',
bygroups(String, String, String.Delimiter, String,
String.Delimiter, Text)),
(r'__END__', Comment.Preproc, 'end-part'),
(r'\$\^[ADEFHILMOPSTWX]', Name.Variable.Global),
(r"\$[\\\"\[\]'&`+*.,;=%~?@$!<>(^|/-](?!\w)",
Name.Variable.Global),
(r'[$@%#]+', Name.Variable, 'varname'),
(r'0_?[0-7]+(_[0-7]+)*', Number.Oct),
(r'0x[0-9A-Fa-f]+(_[0-9A-Fa-f]+)*', Number.Hex),
(r'0b[01]+(_[01]+)*', Number.Bin),
(r'(?i)(\d*(_\d*)*\.\d+(_\d*)*|\d+(_\d*)*\.\d+(_\d*)*)(e[+-]?\d+)?',
Number.Float),
(r'(?i)\d+(_\d*)*e[+-]?\d+(_\d*)*', Number.Float),
(r'\d+(_\d+)*', Number.Integer),
(r"'(\\\\|\\[^\\]|[^'\\])*'", String),
(r'"(\\\\|\\[^\\]|[^"\\])*"', String),
(r'`(\\\\|\\[^\\]|[^`\\])*`', String.Backtick),
(r'<([^\s>]+)>', String.Regex),
(r'(q|qq|qw|qr|qx)\{', String.Other, 'cb-string'),
(r'(q|qq|qw|qr|qx)\(', String.Other, 'rb-string'),
(r'(q|qq|qw|qr|qx)\[', String.Other, 'sb-string'),
(r'(q|qq|qw|qr|qx)\<', String.Other, 'lt-string'),
(r'(q|qq|qw|qr|qx)([\W_])(.|\n)*?\2', String.Other),
(r'(package)(\s+)([a-zA-Z_]\w*(?:::[a-zA-Z_]\w*)*)',
bygroups(Keyword, Text, Name.Namespace)),
(r'(use|require|no)(\s+)([a-zA-Z_]\w*(?:::[a-zA-Z_]\w*)*)',
bygroups(Keyword, Text, Name.Namespace)),
(r'(sub)(\s+)', bygroups(Keyword, Text), 'funcname'),
(words(('no', 'package', 'require', 'use'),
suffix=r'\b'), Keyword),
(r'(\[\]|\*\*|::|<<|>>|>=|<=>|<=|={3}|!=|=~|'
r'!~|&&?|\|\||\.{1,3})', Operator),
(r'[-+/*%=<>&^|!\\~]=?', Operator),
(r'[()\[\]:;,<>/?{}]', Punctuation), # yes, there's no shortage
# of punctuation in Perl!
(r'(?=\w)', Name, 'name'),
],
'format': [
(r'\.\n', String.Interpol, '#pop'),
(r'[^\n]*\n', String.Interpol),
],
'varname': [
(r'\s+', Text),
(r'\{', Punctuation, '#pop'), # hash syntax?
(r'\)|,', Punctuation, '#pop'), # argument specifier
(r'\w+::', Name.Namespace),
(r'[\w:]+', Name.Variable, '#pop'),
],
'name': [
(r'[a-zA-Z_]\w*(::[a-zA-Z_]\w*)*(::)?(?=\s*->)', Name.Namespace,
'#pop'),
(r'[a-zA-Z_]\w*(::[a-zA-Z_]\w*)*::', Name.Namespace, '#pop'),
(r'[\w:]+', Name, '#pop'),
(r'[A-Z_]+(?=\W)', Name.Constant, '#pop'),
(r'(?=\W)', Text, '#pop'),
],
'funcname': [
(r'[a-zA-Z_]\w*[!?]?', Name.Function),
(r'\s+', Text),
# argument declaration
(r'(\([$@%]*\))(\s*)', bygroups(Punctuation, Text)),
(r';', Punctuation, '#pop'),
(r'.*?\{', Punctuation, '#pop'),
],
'cb-string': [(r'\\[{}\\]', String.Other), (r'\\', String.Other),
(r'\{', String.Other, 'cb-string'),
(r'\}', String.Other, '#pop'),
(r'[^{}\\]+', String.Other)],
'rb-string': [(r'\\[()\\]', String.Other), (r'\\', String.Other),
(r'\(', String.Other, 'rb-string'),
(r'\)', String.Other, '#pop'),
(r'[^()]+', String.Other)],
'sb-string': [(r'\\[\[\]\\]', String.Other), (r'\\', String.Other),
(r'\[', String.Other, 'sb-string'),
(r'\]', String.Other, '#pop'),
(r'[^\[\]]+', String.Other)],
'lt-string': [(r'\\[<>\\]', String.Other), (r'\\', String.Other),
(r'\<', String.Other, 'lt-string'),
(r'\>', String.Other, '#pop'),
(r'[^<>]+', String.Other)],
'end-part': [(r'.+', Comment.Preproc, '#pop')]
}
def analyse_text(text):
if shebang_matches(text, r'perl'):
return True
if re.search(r'(?:my|our)\s+[$@%(]', text):
return 0.9
class GoLexer(RegexLexer):
"""
For `Go <http://golang.org>`_ source.
.. versionadded:: 1.2
"""
name = 'Go'
filenames = ['*.go']
aliases = ['go']
mimetypes = ['text/x-gosrc']
flags = re.MULTILINE | re.UNICODE
tokens = {
'root': [
(r'\n', Text),
(r'\s+', Text),
(r'\\\n', Text), # line continuations
(r'//(.*?)\n', Comment.Single),
(r'/(\\\n)?[*](.|\n)*?[*](\\\n)?/', Comment.Multiline),
(r'(import|package)\b', Keyword.Namespace),
(r'(var|func|struct|map|chan|type|interface|const)\b',
Keyword.Declaration),
(words(('break', 'default', 'select', 'case', 'defer', 'go',
'else', 'goto', 'switch', 'fallthrough', 'if', 'range',
'continue', 'for', 'return'),
suffix=r'\b'), Keyword),
(r'(true|false|iota|nil)\b', Keyword.Constant),
# It seems the builtin types aren't actually keywords, but
# can be used as functions. So we need two declarations.
(words(('uint', 'uint8', 'uint16', 'uint32', 'uint64', 'int',
'int8', 'int16', 'int32', 'int64', 'float', 'float32',
'float64', 'complex64', 'complex128', 'byte', 'rune',
'string', 'bool', 'error', 'uintptr', 'print', 'println',
'panic', 'recover', 'close', 'complex', 'real', 'imag',
'len', 'cap', 'append', 'copy', 'delete', 'new', 'make'),
suffix=r'\b(\()'), bygroups(Name.Builtin, Punctuation)),
(words(('uint', 'uint8', 'uint16', 'uint32', 'uint64', 'int',
'int8', 'int16', 'int32', 'int64', 'float', 'float32',
'float64', 'complex64', 'complex128', 'byte', 'rune',
'string', 'bool', 'error', 'uintptr'),
suffix=r'\b'), Keyword.Type),
# imaginary_lit
(r'\d+i', Number),
(r'\d+\.\d*([Ee][-+]\d+)?i', Number),
(r'\.\d+([Ee][-+]\d+)?i', Number),
(r'\d+[Ee][-+]\d+i', Number),
# float_lit
(r'\d+(\.\d+[eE][+\-]?\d+|'
r'\.\d*|[eE][+\-]?\d+)', Number.Float),
(r'\.\d+([eE][+\-]?\d+)?', Number.Float),
# int_lit
# -- octal_lit
(r'0[0-7]+', Number.Oct),
# -- hex_lit
(r'0[xX][0-9a-fA-F]+', Number.Hex),
# -- decimal_lit
(r'(0|[1-9][0-9]*)', Number.Integer),
# char_lit
(r"""'(\\['"\\abfnrtv]|\\x[0-9a-fA-F]{2}|\\[0-7]{1,3}"""
r"""|\\u[0-9a-fA-F]{4}|\\U[0-9a-fA-F]{8}|[^\\])'""", String.Char),
# StringLiteral
# -- raw_string_lit
(r'`[^`]*`', String),
# -- interpreted_string_lit
(r'"(\\\\|\\"|[^"])*"', String),
# Tokens
(r'(<<=|>>=|<<|>>|<=|>=|&\^=|&\^|\+=|-=|\*=|/=|%=|&=|\|=|&&|\|\|'
r'|<-|\+\+|--|==|!=|:=|\.\.\.|[+\-*/%&])', Operator),
(r'[|^<>=!()\[\]{}.,;:]', Punctuation),
# identifier
(r'[^\W\d]\w*', Name.Other),
]
}
