123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799 |
- """
- pygments.lexers.parsers
- ~~~~~~~~~~~~~~~~~~~~~~~
- Lexers for parser generators.
- :copyright: Copyright 2006-2021 by the Pygments team, see AUTHORS.
- :license: BSD, see LICENSE for details.
- """
- import re
- from pygments.lexer import RegexLexer, DelegatingLexer, \
- include, bygroups, using
- from pygments.token import Punctuation, Other, Text, Comment, Operator, \
- Keyword, Name, String, Number, Whitespace
- from pygments.lexers.jvm import JavaLexer
- from pygments.lexers.c_cpp import CLexer, CppLexer
- from pygments.lexers.objective import ObjectiveCLexer
- from pygments.lexers.d import DLexer
- from pygments.lexers.dotnet import CSharpLexer
- from pygments.lexers.ruby import RubyLexer
- from pygments.lexers.python import PythonLexer
- from pygments.lexers.perl import PerlLexer
- __all__ = ['RagelLexer', 'RagelEmbeddedLexer', 'RagelCLexer', 'RagelDLexer',
- 'RagelCppLexer', 'RagelObjectiveCLexer', 'RagelRubyLexer',
- 'RagelJavaLexer', 'AntlrLexer', 'AntlrPythonLexer',
- 'AntlrPerlLexer', 'AntlrRubyLexer', 'AntlrCppLexer',
- 'AntlrCSharpLexer', 'AntlrObjectiveCLexer',
- 'AntlrJavaLexer', 'AntlrActionScriptLexer',
- 'TreetopLexer', 'EbnfLexer']
- class RagelLexer(RegexLexer):
- """
- A pure `Ragel <http://www.complang.org/ragel/>`_ lexer. Use this for
- fragments of Ragel. For ``.rl`` files, use RagelEmbeddedLexer instead
- (or one of the language-specific subclasses).
- .. versionadded:: 1.1
- """
- name = 'Ragel'
- aliases = ['ragel']
- filenames = []
- tokens = {
- 'whitespace': [
- (r'\s+', Whitespace)
- ],
- 'comments': [
- (r'\#.*$', Comment),
- ],
- 'keywords': [
- (r'(access|action|alphtype)\b', Keyword),
- (r'(getkey|write|machine|include)\b', Keyword),
- (r'(any|ascii|extend|alpha|digit|alnum|lower|upper)\b', Keyword),
- (r'(xdigit|cntrl|graph|print|punct|space|zlen|empty)\b', Keyword)
- ],
- 'numbers': [
- (r'0x[0-9A-Fa-f]+', Number.Hex),
- (r'[+-]?[0-9]+', Number.Integer),
- ],
- 'literals': [
- (r'"(\\\\|\\[^\\]|[^"\\])*"', String.Double),
- (r"'(\\\\|\\[^\\]|[^'\\])*'", String.Single),
- (r'\[(\\\\|\\[^\\]|[^\\\]])*\]', String), # square bracket literals
- (r'/(?!\*)(\\\\|\\[^\\]|[^/\\])*/', String.Regex), # regular expressions
- ],
- 'identifiers': [
- (r'[a-zA-Z_]\w*', Name.Variable),
- ],
- 'operators': [
- (r',', Operator), # Join
- (r'\||&|--?', Operator), # Union, Intersection and Subtraction
- (r'\.|<:|:>>?', Operator), # Concatention
- (r':', Operator), # Label
- (r'->', Operator), # Epsilon Transition
- (r'(>|\$|%|<|@|<>)(/|eof\b)', Operator), # EOF Actions
- (r'(>|\$|%|<|@|<>)(!|err\b)', Operator), # Global Error Actions
- (r'(>|\$|%|<|@|<>)(\^|lerr\b)', Operator), # Local Error Actions
- (r'(>|\$|%|<|@|<>)(~|to\b)', Operator), # To-State Actions
- (r'(>|\$|%|<|@|<>)(\*|from\b)', Operator), # From-State Actions
- (r'>|@|\$|%', Operator), # Transition Actions and Priorities
- (r'\*|\?|\+|\{[0-9]*,[0-9]*\}', Operator), # Repetition
- (r'!|\^', Operator), # Negation
- (r'\(|\)', Operator), # Grouping
- ],
- 'root': [
- include('literals'),
- include('whitespace'),
- include('comments'),
- include('keywords'),
- include('numbers'),
- include('identifiers'),
- include('operators'),
- (r'\{', Punctuation, 'host'),
- (r'=', Operator),
- (r';', Punctuation),
- ],
- 'host': [
- (r'(' + r'|'.join(( # keep host code in largest possible chunks
- r'[^{}\'"/#]+', # exclude unsafe characters
- r'[^\\]\\[{}]', # allow escaped { or }
- # strings and comments may safely contain unsafe characters
- r'"(\\\\|\\[^\\]|[^"\\])*"',
- r"'(\\\\|\\[^\\]|[^'\\])*'",
- r'//.*$\n?', # single line comment
- r'/\*(.|\n)*?\*/', # multi-line javadoc-style comment
- r'\#.*$\n?', # ruby comment
- # regular expression: There's no reason for it to start
- # with a * and this stops confusion with comments.
- r'/(?!\*)(\\\\|\\[^\\]|[^/\\])*/',
- # / is safe now that we've handled regex and javadoc comments
- r'/',
- )) + r')+', Other),
- (r'\{', Punctuation, '#push'),
- (r'\}', Punctuation, '#pop'),
- ],
- }
- class RagelEmbeddedLexer(RegexLexer):
- """
- A lexer for `Ragel`_ embedded in a host language file.
- This will only highlight Ragel statements. If you want host language
- highlighting then call the language-specific Ragel lexer.
- .. versionadded:: 1.1
- """
- name = 'Embedded Ragel'
- aliases = ['ragel-em']
- filenames = ['*.rl']
- tokens = {
- 'root': [
- (r'(' + r'|'.join(( # keep host code in largest possible chunks
- r'[^%\'"/#]+', # exclude unsafe characters
- r'%(?=[^%]|$)', # a single % sign is okay, just not 2 of them
- # strings and comments may safely contain unsafe characters
- r'"(\\\\|\\[^\\]|[^"\\])*"',
- r"'(\\\\|\\[^\\]|[^'\\])*'",
- r'/\*(.|\n)*?\*/', # multi-line javadoc-style comment
- r'//.*$\n?', # single line comment
- r'\#.*$\n?', # ruby/ragel comment
- r'/(?!\*)(\\\\|\\[^\\]|[^/\\])*/', # regular expression
- # / is safe now that we've handled regex and javadoc comments
- r'/',
- )) + r')+', Other),
- # Single Line FSM.
- # Please don't put a quoted newline in a single line FSM.
- # That's just mean. It will break this.
- (r'(%%)(?![{%])(.*)($|;)(\n?)', bygroups(Punctuation,
- using(RagelLexer),
- Punctuation, Text)),
- # Multi Line FSM.
- (r'(%%%%|%%)\{', Punctuation, 'multi-line-fsm'),
- ],
- 'multi-line-fsm': [
- (r'(' + r'|'.join(( # keep ragel code in largest possible chunks.
- r'(' + r'|'.join((
- r'[^}\'"\[/#]', # exclude unsafe characters
- r'\}(?=[^%]|$)', # } is okay as long as it's not followed by %
- r'\}%(?=[^%]|$)', # ...well, one %'s okay, just not two...
- r'[^\\]\\[{}]', # ...and } is okay if it's escaped
- # allow / if it's preceded with one of these symbols
- # (ragel EOF actions)
- r'(>|\$|%|<|@|<>)/',
- # specifically allow regex followed immediately by *
- # so it doesn't get mistaken for a comment
- r'/(?!\*)(\\\\|\\[^\\]|[^/\\])*/\*',
- # allow / as long as it's not followed by another / or by a *
- r'/(?=[^/*]|$)',
- # We want to match as many of these as we can in one block.
- # Not sure if we need the + sign here,
- # does it help performance?
- )) + r')+',
- # strings and comments may safely contain unsafe characters
- r'"(\\\\|\\[^\\]|[^"\\])*"',
- r"'(\\\\|\\[^\\]|[^'\\])*'",
- r"\[(\\\\|\\[^\\]|[^\]\\])*\]", # square bracket literal
- r'/\*(.|\n)*?\*/', # multi-line javadoc-style comment
- r'//.*$\n?', # single line comment
- r'\#.*$\n?', # ruby/ragel comment
- )) + r')+', using(RagelLexer)),
- (r'\}%%', Punctuation, '#pop'),
- ]
- }
- def analyse_text(text):
- return '@LANG: indep' in text
- class RagelRubyLexer(DelegatingLexer):
- """
- A lexer for `Ragel`_ in a Ruby host file.
- .. versionadded:: 1.1
- """
- name = 'Ragel in Ruby Host'
- aliases = ['ragel-ruby', 'ragel-rb']
- filenames = ['*.rl']
- def __init__(self, **options):
- super().__init__(RubyLexer, RagelEmbeddedLexer, **options)
- def analyse_text(text):
- return '@LANG: ruby' in text
- class RagelCLexer(DelegatingLexer):
- """
- A lexer for `Ragel`_ in a C host file.
- .. versionadded:: 1.1
- """
- name = 'Ragel in C Host'
- aliases = ['ragel-c']
- filenames = ['*.rl']
- def __init__(self, **options):
- super().__init__(CLexer, RagelEmbeddedLexer, **options)
- def analyse_text(text):
- return '@LANG: c' in text
- class RagelDLexer(DelegatingLexer):
- """
- A lexer for `Ragel`_ in a D host file.
- .. versionadded:: 1.1
- """
- name = 'Ragel in D Host'
- aliases = ['ragel-d']
- filenames = ['*.rl']
- def __init__(self, **options):
- super().__init__(DLexer, RagelEmbeddedLexer, **options)
- def analyse_text(text):
- return '@LANG: d' in text
- class RagelCppLexer(DelegatingLexer):
- """
- A lexer for `Ragel`_ in a CPP host file.
- .. versionadded:: 1.1
- """
- name = 'Ragel in CPP Host'
- aliases = ['ragel-cpp']
- filenames = ['*.rl']
- def __init__(self, **options):
- super().__init__(CppLexer, RagelEmbeddedLexer, **options)
- def analyse_text(text):
- return '@LANG: c++' in text
- class RagelObjectiveCLexer(DelegatingLexer):
- """
- A lexer for `Ragel`_ in an Objective C host file.
- .. versionadded:: 1.1
- """
- name = 'Ragel in Objective C Host'
- aliases = ['ragel-objc']
- filenames = ['*.rl']
- def __init__(self, **options):
- super().__init__(ObjectiveCLexer, RagelEmbeddedLexer, **options)
- def analyse_text(text):
- return '@LANG: objc' in text
- class RagelJavaLexer(DelegatingLexer):
- """
- A lexer for `Ragel`_ in a Java host file.
- .. versionadded:: 1.1
- """
- name = 'Ragel in Java Host'
- aliases = ['ragel-java']
- filenames = ['*.rl']
- def __init__(self, **options):
- super().__init__(JavaLexer, RagelEmbeddedLexer, **options)
- def analyse_text(text):
- return '@LANG: java' in text
- class AntlrLexer(RegexLexer):
- """
- Generic `ANTLR`_ Lexer.
- Should not be called directly, instead
- use DelegatingLexer for your target language.
- .. versionadded:: 1.1
- .. _ANTLR: http://www.antlr.org/
- """
- name = 'ANTLR'
- aliases = ['antlr']
- filenames = []
- _id = r'[A-Za-z]\w*'
- _TOKEN_REF = r'[A-Z]\w*'
- _RULE_REF = r'[a-z]\w*'
- _STRING_LITERAL = r'\'(?:\\\\|\\\'|[^\']*)\''
- _INT = r'[0-9]+'
- tokens = {
- 'whitespace': [
- (r'\s+', Whitespace),
- ],
- 'comments': [
- (r'//.*$', Comment),
- (r'/\*(.|\n)*?\*/', Comment),
- ],
- 'root': [
- include('whitespace'),
- include('comments'),
- (r'(lexer|parser|tree)?(\s*)(grammar\b)(\s*)(' + _id + ')(;)',
- bygroups(Keyword, Whitespace, Keyword, Whitespace, Name.Class,
- Punctuation)),
- # optionsSpec
- (r'options\b', Keyword, 'options'),
- # tokensSpec
- (r'tokens\b', Keyword, 'tokens'),
- # attrScope
- (r'(scope)(\s*)(' + _id + r')(\s*)(\{)',
- bygroups(Keyword, Whitespace, Name.Variable, Whitespace,
- Punctuation), 'action'),
- # exception
- (r'(catch|finally)\b', Keyword, 'exception'),
- # action
- (r'(@' + _id + r')(\s*)(::)?(\s*)(' + _id + r')(\s*)(\{)',
- bygroups(Name.Label, Whitespace, Punctuation, Whitespace,
- Name.Label, Whitespace, Punctuation), 'action'),
- # rule
- (r'((?:protected|private|public|fragment)\b)?(\s*)(' + _id + ')(!)?',
- bygroups(Keyword, Whitespace, Name.Label, Punctuation),
- ('rule-alts', 'rule-prelims')),
- ],
- 'exception': [
- (r'\n', Whitespace, '#pop'),
- (r'\s', Whitespace),
- include('comments'),
- (r'\[', Punctuation, 'nested-arg-action'),
- (r'\{', Punctuation, 'action'),
- ],
- 'rule-prelims': [
- include('whitespace'),
- include('comments'),
- (r'returns\b', Keyword),
- (r'\[', Punctuation, 'nested-arg-action'),
- (r'\{', Punctuation, 'action'),
- # throwsSpec
- (r'(throws)(\s+)(' + _id + ')',
- bygroups(Keyword, Whitespace, Name.Label)),
- (r'(,)(\s*)(' + _id + ')',
- bygroups(Punctuation, Whitespace, Name.Label)), # Additional throws
- # optionsSpec
- (r'options\b', Keyword, 'options'),
- # ruleScopeSpec - scope followed by target language code or name of action
- # TODO finish implementing other possibilities for scope
- # L173 ANTLRv3.g from ANTLR book
- (r'(scope)(\s+)(\{)', bygroups(Keyword, Whitespace, Punctuation),
- 'action'),
- (r'(scope)(\s+)(' + _id + r')(\s*)(;)',
- bygroups(Keyword, Whitespace, Name.Label, Whitespace, Punctuation)),
- # ruleAction
- (r'(@' + _id + r')(\s*)(\{)',
- bygroups(Name.Label, Whitespace, Punctuation), 'action'),
- # finished prelims, go to rule alts!
- (r':', Punctuation, '#pop')
- ],
- 'rule-alts': [
- include('whitespace'),
- include('comments'),
- # These might need to go in a separate 'block' state triggered by (
- (r'options\b', Keyword, 'options'),
- (r':', Punctuation),
- # literals
- (r'"(\\\\|\\[^\\]|[^"\\])*"', String.Double),
- (r"'(\\\\|\\[^\\]|[^'\\])*'", String.Single),
- (r'<<([^>]|>[^>])>>', String),
- # identifiers
- # Tokens start with capital letter.
- (r'\$?[A-Z_]\w*', Name.Constant),
- # Rules start with small letter.
- (r'\$?[a-z_]\w*', Name.Variable),
- # operators
- (r'(\+|\||->|=>|=|\(|\)|\.\.|\.|\?|\*|\^|!|\#|~)', Operator),
- (r',', Punctuation),
- (r'\[', Punctuation, 'nested-arg-action'),
- (r'\{', Punctuation, 'action'),
- (r';', Punctuation, '#pop')
- ],
- 'tokens': [
- include('whitespace'),
- include('comments'),
- (r'\{', Punctuation),
- (r'(' + _TOKEN_REF + r')(\s*)(=)?(\s*)(' + _STRING_LITERAL
- + r')?(\s*)(;)',
- bygroups(Name.Label, Whitespace, Punctuation, Whitespace,
- String, Whitespace, Punctuation)),
- (r'\}', Punctuation, '#pop'),
- ],
- 'options': [
- include('whitespace'),
- include('comments'),
- (r'\{', Punctuation),
- (r'(' + _id + r')(\s*)(=)(\s*)(' +
- '|'.join((_id, _STRING_LITERAL, _INT, r'\*')) + r')(\s*)(;)',
- bygroups(Name.Variable, Whitespace, Punctuation, Whitespace,
- Text, Whitespace, Punctuation)),
- (r'\}', Punctuation, '#pop'),
- ],
- 'action': [
- (r'(' + r'|'.join(( # keep host code in largest possible chunks
- r'[^${}\'"/\\]+', # exclude unsafe characters
- # strings and comments may safely contain unsafe characters
- r'"(\\\\|\\[^\\]|[^"\\])*"',
- r"'(\\\\|\\[^\\]|[^'\\])*'",
- r'//.*$\n?', # single line comment
- r'/\*(.|\n)*?\*/', # multi-line javadoc-style comment
- # regular expression: There's no reason for it to start
- # with a * and this stops confusion with comments.
- r'/(?!\*)(\\\\|\\[^\\]|[^/\\])*/',
- # backslashes are okay, as long as we are not backslashing a %
- r'\\(?!%)',
- # Now that we've handled regex and javadoc comments
- # it's safe to let / through.
- r'/',
- )) + r')+', Other),
- (r'(\\)(%)', bygroups(Punctuation, Other)),
- (r'(\$[a-zA-Z]+)(\.?)(text|value)?',
- bygroups(Name.Variable, Punctuation, Name.Property)),
- (r'\{', Punctuation, '#push'),
- (r'\}', Punctuation, '#pop'),
- ],
- 'nested-arg-action': [
- (r'(' + r'|'.join(( # keep host code in largest possible chunks.
- r'[^$\[\]\'"/]+', # exclude unsafe characters
- # strings and comments may safely contain unsafe characters
- r'"(\\\\|\\[^\\]|[^"\\])*"',
- r"'(\\\\|\\[^\\]|[^'\\])*'",
- r'//.*$\n?', # single line comment
- r'/\*(.|\n)*?\*/', # multi-line javadoc-style comment
- # regular expression: There's no reason for it to start
- # with a * and this stops confusion with comments.
- r'/(?!\*)(\\\\|\\[^\\]|[^/\\])*/',
- # Now that we've handled regex and javadoc comments
- # it's safe to let / through.
- r'/',
- )) + r')+', Other),
- (r'\[', Punctuation, '#push'),
- (r'\]', Punctuation, '#pop'),
- (r'(\$[a-zA-Z]+)(\.?)(text|value)?',
- bygroups(Name.Variable, Punctuation, Name.Property)),
- (r'(\\\\|\\\]|\\\[|[^\[\]])+', Other),
- ]
- }
- def analyse_text(text):
- return re.search(r'^\s*grammar\s+[a-zA-Z0-9]+\s*;', text, re.M)
- # http://www.antlr.org/wiki/display/ANTLR3/Code+Generation+Targets
- class AntlrCppLexer(DelegatingLexer):
- """
- `ANTLR`_ with CPP Target
- .. versionadded:: 1.1
- """
- name = 'ANTLR With CPP Target'
- aliases = ['antlr-cpp']
- filenames = ['*.G', '*.g']
- def __init__(self, **options):
- super().__init__(CppLexer, AntlrLexer, **options)
- def analyse_text(text):
- return AntlrLexer.analyse_text(text) and \
- re.search(r'^\s*language\s*=\s*C\s*;', text, re.M)
- class AntlrObjectiveCLexer(DelegatingLexer):
- """
- `ANTLR`_ with Objective-C Target
- .. versionadded:: 1.1
- """
- name = 'ANTLR With ObjectiveC Target'
- aliases = ['antlr-objc']
- filenames = ['*.G', '*.g']
- def __init__(self, **options):
- super().__init__(ObjectiveCLexer, AntlrLexer, **options)
- def analyse_text(text):
- return AntlrLexer.analyse_text(text) and \
- re.search(r'^\s*language\s*=\s*ObjC\s*;', text)
- class AntlrCSharpLexer(DelegatingLexer):
- """
- `ANTLR`_ with C# Target
- .. versionadded:: 1.1
- """
- name = 'ANTLR With C# Target'
- aliases = ['antlr-csharp', 'antlr-c#']
- filenames = ['*.G', '*.g']
- def __init__(self, **options):
- super().__init__(CSharpLexer, AntlrLexer, **options)
- def analyse_text(text):
- return AntlrLexer.analyse_text(text) and \
- re.search(r'^\s*language\s*=\s*CSharp2\s*;', text, re.M)
- class AntlrPythonLexer(DelegatingLexer):
- """
- `ANTLR`_ with Python Target
- .. versionadded:: 1.1
- """
- name = 'ANTLR With Python Target'
- aliases = ['antlr-python']
- filenames = ['*.G', '*.g']
- def __init__(self, **options):
- super().__init__(PythonLexer, AntlrLexer, **options)
- def analyse_text(text):
- return AntlrLexer.analyse_text(text) and \
- re.search(r'^\s*language\s*=\s*Python\s*;', text, re.M)
- class AntlrJavaLexer(DelegatingLexer):
- """
- `ANTLR`_ with Java Target
- .. versionadded:: 1.
- """
- name = 'ANTLR With Java Target'
- aliases = ['antlr-java']
- filenames = ['*.G', '*.g']
- def __init__(self, **options):
- super().__init__(JavaLexer, AntlrLexer, **options)
- def analyse_text(text):
- # Antlr language is Java by default
- return AntlrLexer.analyse_text(text) and 0.9
- class AntlrRubyLexer(DelegatingLexer):
- """
- `ANTLR`_ with Ruby Target
- .. versionadded:: 1.1
- """
- name = 'ANTLR With Ruby Target'
- aliases = ['antlr-ruby', 'antlr-rb']
- filenames = ['*.G', '*.g']
- def __init__(self, **options):
- super().__init__(RubyLexer, AntlrLexer, **options)
- def analyse_text(text):
- return AntlrLexer.analyse_text(text) and \
- re.search(r'^\s*language\s*=\s*Ruby\s*;', text, re.M)
- class AntlrPerlLexer(DelegatingLexer):
- """
- `ANTLR`_ with Perl Target
- .. versionadded:: 1.1
- """
- name = 'ANTLR With Perl Target'
- aliases = ['antlr-perl']
- filenames = ['*.G', '*.g']
- def __init__(self, **options):
- super().__init__(PerlLexer, AntlrLexer, **options)
- def analyse_text(text):
- return AntlrLexer.analyse_text(text) and \
- re.search(r'^\s*language\s*=\s*Perl5\s*;', text, re.M)
- class AntlrActionScriptLexer(DelegatingLexer):
- """
- `ANTLR`_ with ActionScript Target
- .. versionadded:: 1.1
- """
- name = 'ANTLR With ActionScript Target'
- aliases = ['antlr-actionscript', 'antlr-as']
- filenames = ['*.G', '*.g']
- def __init__(self, **options):
- from pygments.lexers.actionscript import ActionScriptLexer
- super().__init__(ActionScriptLexer, AntlrLexer, **options)
- def analyse_text(text):
- return AntlrLexer.analyse_text(text) and \
- re.search(r'^\s*language\s*=\s*ActionScript\s*;', text, re.M)
- class TreetopBaseLexer(RegexLexer):
- """
- A base lexer for `Treetop <http://treetop.rubyforge.org/>`_ grammars.
- Not for direct use; use TreetopLexer instead.
- .. versionadded:: 1.6
- """
- tokens = {
- 'root': [
- include('space'),
- (r'require[ \t]+[^\n\r]+[\n\r]', Other),
- (r'module\b', Keyword.Namespace, 'module'),
- (r'grammar\b', Keyword, 'grammar'),
- ],
- 'module': [
- include('space'),
- include('end'),
- (r'module\b', Keyword, '#push'),
- (r'grammar\b', Keyword, 'grammar'),
- (r'[A-Z]\w*(?:::[A-Z]\w*)*', Name.Namespace),
- ],
- 'grammar': [
- include('space'),
- include('end'),
- (r'rule\b', Keyword, 'rule'),
- (r'include\b', Keyword, 'include'),
- (r'[A-Z]\w*', Name),
- ],
- 'include': [
- include('space'),
- (r'[A-Z]\w*(?:::[A-Z]\w*)*', Name.Class, '#pop'),
- ],
- 'rule': [
- include('space'),
- include('end'),
- (r'"(\\\\|\\[^\\]|[^"\\])*"', String.Double),
- (r"'(\\\\|\\[^\\]|[^'\\])*'", String.Single),
- (r'([A-Za-z_]\w*)(:)', bygroups(Name.Label, Punctuation)),
- (r'[A-Za-z_]\w*', Name),
- (r'[()]', Punctuation),
- (r'[?+*/&!~]', Operator),
- (r'\[(?:\\.|\[:\^?[a-z]+:\]|[^\\\]])+\]', String.Regex),
- (r'([0-9]*)(\.\.)([0-9]*)',
- bygroups(Number.Integer, Operator, Number.Integer)),
- (r'(<)([^>]+)(>)', bygroups(Punctuation, Name.Class, Punctuation)),
- (r'\{', Punctuation, 'inline_module'),
- (r'\.', String.Regex),
- ],
- 'inline_module': [
- (r'\{', Other, 'ruby'),
- (r'\}', Punctuation, '#pop'),
- (r'[^{}]+', Other),
- ],
- 'ruby': [
- (r'\{', Other, '#push'),
- (r'\}', Other, '#pop'),
- (r'[^{}]+', Other),
- ],
- 'space': [
- (r'[ \t\n\r]+', Whitespace),
- (r'#[^\n]*', Comment.Single),
- ],
- 'end': [
- (r'end\b', Keyword, '#pop'),
- ],
- }
- class TreetopLexer(DelegatingLexer):
- """
- A lexer for `Treetop <http://treetop.rubyforge.org/>`_ grammars.
- .. versionadded:: 1.6
- """
- name = 'Treetop'
- aliases = ['treetop']
- filenames = ['*.treetop', '*.tt']
- def __init__(self, **options):
- super().__init__(RubyLexer, TreetopBaseLexer, **options)
- class EbnfLexer(RegexLexer):
- """
- Lexer for `ISO/IEC 14977 EBNF
- <http://en.wikipedia.org/wiki/Extended_Backus%E2%80%93Naur_Form>`_
- grammars.
- .. versionadded:: 2.0
- """
- name = 'EBNF'
- aliases = ['ebnf']
- filenames = ['*.ebnf']
- mimetypes = ['text/x-ebnf']
- tokens = {
- 'root': [
- include('whitespace'),
- include('comment_start'),
- include('identifier'),
- (r'=', Operator, 'production'),
- ],
- 'production': [
- include('whitespace'),
- include('comment_start'),
- include('identifier'),
- (r'"[^"]*"', String.Double),
- (r"'[^']*'", String.Single),
- (r'(\?[^?]*\?)', Name.Entity),
- (r'[\[\]{}(),|]', Punctuation),
- (r'-', Operator),
- (r';', Punctuation, '#pop'),
- (r'\.', Punctuation, '#pop'),
- ],
- 'whitespace': [
- (r'\s+', Text),
- ],
- 'comment_start': [
- (r'\(\*', Comment.Multiline, 'comment'),
- ],
- 'comment': [
- (r'[^*)]', Comment.Multiline),
- include('comment_start'),
- (r'\*\)', Comment.Multiline, '#pop'),
- (r'[*)]', Comment.Multiline),
- ],
- 'identifier': [
- (r'([a-zA-Z][\w \-]*)', Keyword),
- ],
- }
|