/console/app/pygments/lexers/compiled.py
https://bitbucket.org/alex_muscar/myspace-competition-radar · Python · 1251 lines · 1057 code · 69 blank · 125 comment · 89 complexity · c35a71fe239c7fc3bcf58b1e9b5976ea MD5 · raw file
- # -*- coding: utf-8 -*-
- """
- pygments.lexers.compiled
- ~~~~~~~~~~~~~~~~~~~~~~~~
- Lexers for compiled languages.
- :copyright: 2006-2008 by Georg Brandl, Armin Ronacher, Christoph Hack,
- Whitney Young, Kirk McDonald, Stou Sandalski, Krzysiek Goj.
- :license: BSD, see LICENSE for more details.
- """
- import re
- try:
- set
- except NameError:
- from sets import Set as set
- from pygments.scanner import Scanner
- from pygments.lexer import Lexer, RegexLexer, include, bygroups, using, \
- this
- from pygments.util import get_bool_opt, get_list_opt
- from pygments.token import \
- Text, Comment, Operator, Keyword, Name, String, Number, Punctuation, \
- Error
- # backwards compatibility
- from pygments.lexers.functional import OcamlLexer
- __all__ = ['CLexer', 'CppLexer', 'DLexer', 'DelphiLexer', 'JavaLexer', 'ScalaLexer',
- 'DylanLexer', 'OcamlLexer', 'ObjectiveCLexer', 'FortranLexer']
- class CLexer(RegexLexer):
- """
- For C source code with preprocessor directives.
- """
- name = 'C'
- aliases = ['c']
- filenames = ['*.c', '*.h']
- mimetypes = ['text/x-chdr', 'text/x-csrc']
- #: optional Comment or Whitespace
- _ws = r'(?:\s|//.*?\n|/[*].*?[*]/)+'
- tokens = {
- 'whitespace': [
- (r'^\s*#if\s+0', Comment.Preproc, 'if0'),
- (r'^\s*#', Comment.Preproc, 'macro'),
- (r'\n', Text),
- (r'\s+', Text),
- (r'\\\n', Text), # line continuation
- (r'//(\n|(.|\n)*?[^\\]\n)', Comment),
- (r'/(\\\n)?[*](.|\n)*?[*](\\\n)?/', Comment),
- ],
- 'statements': [
- (r'L?"', String, 'string'),
- (r"L?'(\\.|\\[0-7]{1,3}|\\x[a-fA-F0-9]{1,2}|[^\\\'\n])'", String.Char),
- (r'(\d+\.\d*|\.\d+|\d+)[eE][+-]?\d+[lL]?', Number.Float),
- (r'(\d+\.\d*|\.\d+|\d+[fF])[fF]?', Number.Float),
- (r'0x[0-9a-fA-F]+[Ll]?', Number.Hex),
- (r'0[0-7]+[Ll]?', Number.Oct),
- (r'\d+[Ll]?', Number.Integer),
- (r'[~!%^&*+=|?:<>/-]', Operator),
- (r'[()\[\],.]', Punctuation),
- (r'\b(case)(.+?)(:)', bygroups(Keyword, using(this), Text)),
- (r'(auto|break|case|const|continue|default|do|else|enum|extern|'
- r'for|goto|if|register|restricted|return|sizeof|static|struct|'
- r'switch|typedef|union|volatile|virtual|while)\b', Keyword),
- (r'(int|long|float|short|double|char|unsigned|signed|void)\b',
- Keyword.Type),
- (r'(_{0,2}inline|naked|restrict|thread|typename)\b', Keyword.Reserved),
- (r'__(asm|int8|based|except|int16|stdcall|cdecl|fastcall|int32|'
- r'declspec|finally|int64|try|leave)\b', Keyword.Reserved),
- (r'(true|false|NULL)\b', Name.Builtin),
- ('[a-zA-Z_][a-zA-Z0-9_]*:(?!:)', Name.Label),
- ('[a-zA-Z_][a-zA-Z0-9_]*', Name),
- ],
- 'root': [
- include('whitespace'),
- # functions
- (r'((?:[a-zA-Z0-9_*\s])+?(?:\s|[*]))' # return arguments
- r'([a-zA-Z_][a-zA-Z0-9_]*)' # method name
- r'(\s*\([^;]*?\))' # signature
- r'(' + _ws + r')({)',
- bygroups(using(this), Name.Function, using(this), using(this),
- Punctuation),
- 'function'),
- # function declarations
- (r'((?:[a-zA-Z0-9_*\s])+?(?:\s|[*]))' # return arguments
- r'([a-zA-Z_][a-zA-Z0-9_]*)' # method name
- r'(\s*\([^;]*?\))' # signature
- r'(' + _ws + r')(;)',
- bygroups(using(this), Name.Function, using(this), using(this),
- Punctuation)),
- ('', Text, 'statement'),
- ],
- 'statement' : [
- include('whitespace'),
- include('statements'),
- ('[{}]', Punctuation),
- (';', Punctuation, '#pop'),
- ],
- 'function': [
- include('whitespace'),
- include('statements'),
- (';', Punctuation),
- ('{', Punctuation, '#push'),
- ('}', Punctuation, '#pop'),
- ],
- 'string': [
- (r'"', String, '#pop'),
- (r'\\([\\abfnrtv"\']|x[a-fA-F0-9]{2,4}|[0-7]{1,3})', String.Escape),
- (r'[^\\"\n]+', String), # all other characters
- (r'\\\n', String), # line continuation
- (r'\\', String), # stray backslash
- ],
- 'macro': [
- (r'[^/\n]+', Comment.Preproc),
- (r'/[*](.|\n)*?[*]/', Comment),
- (r'//.*?\n', Comment, '#pop'),
- (r'/', Comment.Preproc),
- (r'(?<=\\)\n', Comment.Preproc),
- (r'\n', Comment.Preproc, '#pop'),
- ],
- 'if0': [
- (r'^\s*#if.*?(?<!\\)\n', Comment, '#push'),
- (r'^\s*#el(?:se|if).*\n', Comment.Preproc, '#pop'),
- (r'^\s*#endif.*?(?<!\\)\n', Comment, '#pop'),
- (r'.*?\n', Comment),
- ]
- }
- stdlib_types = ['size_t', 'ssize_t', 'off_t', 'wchar_t', 'ptrdiff_t',
- 'sig_atomic_t', 'fpos_t', 'clock_t', 'time_t', 'va_list',
- 'jmp_buf', 'FILE', 'DIR', 'div_t', 'ldiv_t', 'mbstate_t',
- 'wctrans_t', 'wint_t', 'wctype_t']
- c99_types = ['_Bool', '_Complex', 'int8_t', 'int16_t', 'int32_t', 'int64_t',
- 'uint8_t', 'uint16_t', 'uint32_t', 'uint64_t', 'int_least8_t',
- 'int_least16_t', 'int_least32_t', 'int_least64_t',
- 'uint_least8_t', 'uint_least16_t', 'uint_least32_t',
- 'uint_least64_t', 'int_fast8_t', 'int_fast16_t', 'int_fast32_t',
- 'int_fast64_t', 'uint_fast8_t', 'uint_fast16_t', 'uint_fast32_t',
- 'uint_fast64_t', 'intptr_t', 'uintptr_t', 'intmax_t', 'uintmax_t']
- def __init__(self, **options):
- self.stdlibhighlighting = get_bool_opt(options,
- 'stdlibhighlighting', True)
- self.c99highlighting = get_bool_opt(options,
- 'c99highlighting', True)
- RegexLexer.__init__(self, **options)
- def get_tokens_unprocessed(self, text):
- for index, token, value in \
- RegexLexer.get_tokens_unprocessed(self, text):
- if token is Name:
- if self.stdlibhighlighting and value in self.stdlib_types:
- token = Keyword.Type
- elif self.c99highlighting and value in self.c99_types:
- token = Keyword.Type
- yield index, token, value
- class CppLexer(RegexLexer):
- """
- For C++ source code with preprocessor directives.
- """
- name = 'C++'
- aliases = ['cpp', 'c++']
- filenames = ['*.cpp', '*.hpp', '*.c++', '*.h++', '*.cc', '*.hh', '*.cxx', '*.hxx']
- mimetypes = ['text/x-c++hdr', 'text/x-c++src']
- tokens = {
- 'root': [
- (r'^\s*#if\s+0', Comment.Preproc, 'if0'),
- (r'^\s*#', Comment.Preproc, 'macro'),
- (r'\n', Text),
- (r'\s+', Text),
- (r'\\\n', Text), # line continuation
- (r'/(\\\n)?/(\n|(.|\n)*?[^\\]\n)', Comment),
- (r'/(\\\n)?[*](.|\n)*?[*](\\\n)?/', Comment),
- (r'[{}]', Punctuation),
- (r'L?"', String, 'string'),
- (r"L?'(\\.|\\[0-7]{1,3}|\\x[a-fA-F0-9]{1,2}|[^\\\'\n])'", String.Char),
- (r'(\d+\.\d*|\.\d+|\d+)[eE][+-]?\d+[lL]?', Number.Float),
- (r'(\d+\.\d*|\.\d+|\d+[fF])[fF]?', Number.Float),
- (r'0x[0-9a-fA-F]+[Ll]?', Number.Hex),
- (r'0[0-7]+[Ll]?', Number.Oct),
- (r'\d+[Ll]?', Number.Integer),
- (r'[~!%^&*+=|?:<>/-]', Operator),
- (r'[()\[\],.;]', Punctuation),
- (r'(asm|auto|break|case|catch|const|const_cast|continue|'
- r'default|delete|do|dynamic_cast|else|enum|explicit|export|'
- r'extern|for|friend|goto|if|mutable|namespace|new|operator|'
- r'private|protected|public|register|reinterpret_cast|return|'
- r'restrict|sizeof|static|static_cast|struct|switch|template|'
- r'this|throw|throws|try|typedef|typeid|typename|union|using|'
- r'volatile|virtual|while)\b', Keyword),
- (r'(class)(\s+)', bygroups(Keyword, Text), 'classname'),
- (r'(bool|int|long|float|short|double|char|unsigned|signed|'
- r'void|wchar_t)\b', Keyword.Type),
- (r'(_{0,2}inline|naked|thread)\b', Keyword.Reserved),
- (r'__(asm|int8|based|except|int16|stdcall|cdecl|fastcall|int32|'
- r'declspec|finally|int64|try|leave|wchar_t|w64|virtual_inheritance|'
- r'uuidof|unaligned|super|single_inheritance|raise|noop|'
- r'multiple_inheritance|m128i|m128d|m128|m64|interface|'
- r'identifier|forceinline|event|assume)\b', Keyword.Reserved),
- (r'(true|false)\b', Keyword.Constant),
- (r'NULL\b', Name.Builtin),
- ('[a-zA-Z_][a-zA-Z0-9_]*:(?!:)', Name.Label),
- ('[a-zA-Z_][a-zA-Z0-9_]*', Name),
- ],
- 'classname': [
- (r'[a-zA-Z_][a-zA-Z0-9_]*', Name.Class, '#pop'),
- # template specification
- (r'\s*(?=>)', Text, '#pop'),
- ],
- 'string': [
- (r'"', String, '#pop'),
- (r'\\([\\abfnrtv"\']|x[a-fA-F0-9]{2,4}|[0-7]{1,3})', String.Escape),
- (r'[^\\"\n]+', String), # all other characters
- (r'\\\n', String), # line continuation
- (r'\\', String), # stray backslash
- ],
- 'macro': [
- (r'[^/\n]+', Comment.Preproc),
- (r'/[*](.|\n)*?[*]/', Comment),
- (r'//.*?\n', Comment, '#pop'),
- (r'/', Comment.Preproc),
- (r'(?<=\\)\n', Comment.Preproc),
- (r'\n', Comment.Preproc, '#pop'),
- ],
- 'if0': [
- (r'^\s*#if.*?(?<!\\)\n', Comment, '#push'),
- (r'^\s*#endif.*?(?<!\\)\n', Comment, '#pop'),
- (r'.*?\n', Comment),
- ]
- }
- class DLexer(RegexLexer):
- """
- For D source.
- """
- name = 'D'
- filenames = ['*.d', '*.di']
- aliases = ['d']
- mimetypes = ['text/x-dsrc']
- tokens = {
- 'root': [
- (r'\n', Text),
- (r'\s+', Text),
- #(r'\\\n', Text), # line continuations
- # Comments
- (r'//(.*?)\n', Comment),
- (r'/(\\\n)?[*](.|\n)*?[*](\\\n)?/', Comment),
- (r'/\+', Comment, 'nested_comment'),
- # Keywords
- (r'(abstract|alias|align|asm|assert|auto|body|break|case|cast'
- r'|catch|class|const|continue|debug|default|delegate|delete'
- r'|deprecated|do|else|enum|export|extern|finally|final'
- r'|foreach_reverse|foreach|for|function|goto|if|import|inout'
- r'|interface|invariant|in|is|lazy|mixin|module|new|nothrow|out'
- r'|override|package|pragma|private|protected|public|pure|ref|return'
- r'|scope|static|struct|super|switch|synchronized|template|this'
- r'|throw|try|typedef|typeid|typeof|union|unittest|version|volatile'
- r'|while|with|__traits)\b', Keyword
- ),
- (r'(bool|byte|cdouble|cent|cfloat|char|creal|dchar|double|float'
- r'|idouble|ifloat|int|ireal|long|real|short|ubyte|ucent|uint|ulong'
- r'|ushort|void|wchar)\b', Keyword.Type
- ),
- (r'(false|true|null)\b', Keyword.Constant),
- (r'macro\b', Keyword.Reserved),
- (r'(string|wstring|dstring)\b', Name.Builtin),
- # FloatLiteral
- # -- HexFloat
- (r'0[xX]([0-9a-fA-F_]*\.[0-9a-fA-F_]+|[0-9a-fA-F_]+)'
- r'[pP][+\-]?[0-9_]+[fFL]?[i]?', Number.Float),
- # -- DecimalFloat
- (r'[0-9_]+(\.[0-9_]+[eE][+\-]?[0-9_]+|'
- r'\.[0-9_]*|[eE][+\-]?[0-9_]+)[fFL]?[i]?', Number.Float),
- (r'\.(0|[1-9][0-9_]*)([eE][+\-]?[0-9_]+)?[fFL]?[i]?', Number.Float),
- # IntegerLiteral
- # -- Binary
- (r'0[Bb][01_]+', Number),
- # -- Octal
- (r'0[0-7_]+', Number.Oct),
- # -- Hexadecimal
- (r'0[xX][0-9a-fA-F_]+', Number.Hex),
- # -- Decimal
- (r'(0|[1-9][0-9_]*)([LUu]|Lu|LU|uL|UL)?', Number.Integer),
- # CharacterLiteral
- (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}|\\&\w+;|.)'""",
- String.Char
- ),
- # StringLiteral
- # -- WysiwygString
- (r'r"[^"]*"[cwd]?', String),
- # -- AlternateWysiwygString
- (r'`[^`]*`[cwd]?', String),
- # -- DoubleQuotedString
- (r'"(\\\\|\\"|[^"])*"[cwd]?', String),
- # -- EscapeSequence
- (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}|&\w+;)""",
- String
- ),
- # -- HexString
- (r'x"[0-9a-fA-F_\s]*"[cwd]?', String),
- # -- DelimitedString
- (r'q"\[', String, 'delimited_bracket'),
- (r'q"\(', String, 'delimited_parenthesis'),
- (r'q"<', String, 'delimited_angle'),
- (r'q"{', String, 'delimited_curly'),
- (r'q"([a-zA-Z_]\w*)\n.*?\n\1"', String),
- (r'q"(.).*?\1"', String),
- # -- TokenString
- (r'q{', String, 'token_string'),
- # Tokens
- (r'(~=|\^=|%=|\*=|==|!>=|!<=|!<>=|!<>|!<|!>|!=|>>>=|>>>|>>=|>>|>='
- r'|<>=|<>|<<=|<<|<=|\+\+|\+=|--|-=|\|\||\|=|&&|&=|\.\.\.|\.\.|/=)'
- r'|[/.&|\-+<>!()\[\]{}?,;:$=*%^~]', Punctuation
- ),
- # Identifier
- (r'[a-zA-Z_]\w*', Name),
- ],
- 'nested_comment': [
- (r'[^+/]+', Comment),
- (r'/\+', Comment, '#push'),
- (r'\+/', Comment, '#pop'),
- (r'[+/]', Comment),
- ],
- 'token_string': [
- (r'{', Punctuation, 'token_string_nest'),
- (r'}', String, '#pop'),
- include('root'),
- ],
- 'token_string_nest': [
- (r'{', Punctuation, '#push'),
- (r'}', Punctuation, '#pop'),
- include('root'),
- ],
- 'delimited_bracket': [
- (r'[^\[\]]+', String),
- (r'\[', String, 'delimited_inside_bracket'),
- (r'\]"', String, '#pop'),
- ],
- 'delimited_inside_bracket': [
- (r'[^\[\]]+', String),
- (r'\[', String, '#push'),
- (r'\]', String, '#pop'),
- ],
- 'delimited_parenthesis': [
- (r'[^\(\)]+', String),
- (r'\(', String, 'delimited_inside_parenthesis'),
- (r'\)"', String, '#pop'),
- ],
- 'delimited_inside_parenthesis': [
- (r'[^\(\)]+', String),
- (r'\(', String, '#push'),
- (r'\)', String, '#pop'),
- ],
- 'delimited_angle': [
- (r'[^<>]+', String),
- (r'<', String, 'delimited_inside_angle'),
- (r'>"', String, '#pop'),
- ],
- 'delimited_inside_angle': [
- (r'[^<>]+', String),
- (r'<', String, '#push'),
- (r'>', String, '#pop'),
- ],
- 'delimited_curly': [
- (r'[^{}]+', String),
- (r'{', String, 'delimited_inside_curly'),
- (r'}"', String, '#pop'),
- ],
- 'delimited_inside_curly': [
- (r'[^{}]+', String),
- (r'{', String, '#push'),
- (r'}', String, '#pop'),
- ],
- }
- class DelphiLexer(Lexer):
- """
- For `Delphi <http://www.borland.com/delphi/>`_ (Borland Object Pascal),
- Turbo Pascal and Free Pascal source code.
- Additional options accepted:
- `turbopascal`
- Highlight Turbo Pascal specific keywords (default: ``True``).
- `delphi`
- Highlight Borland Delphi specific keywords (default: ``True``).
- `freepascal`
- Highlight Free Pascal specific keywords (default: ``True``).
- `units`
- A list of units that should be considered builtin, supported are
- ``System``, ``SysUtils``, ``Classes`` and ``Math``.
- Default is to consider all of them builtin.
- """
- name = 'Delphi'
- aliases = ['delphi', 'pas', 'pascal', 'objectpascal']
- filenames = ['*.pas']
- mimetypes = ['text/x-pascal']
- TURBO_PASCAL_KEYWORDS = [
- 'absolute', 'and', 'array', 'asm', 'begin', 'break', 'case',
- 'const', 'constructor', 'continue', 'destructor', 'div', 'do',
- 'downto', 'else', 'end', 'file', 'for', 'function', 'goto',
- 'if', 'implementation', 'in', 'inherited', 'inline', 'interface',
- 'label', 'mod', 'nil', 'not', 'object', 'of', 'on', 'operator',
- 'or', 'packed', 'procedure', 'program', 'record', 'reintroduce',
- 'repeat', 'self', 'set', 'shl', 'shr', 'string', 'then', 'to',
- 'type', 'unit', 'until', 'uses', 'var', 'while', 'with', 'xor'
- ]
- DELPHI_KEYWORDS = [
- 'as', 'class', 'except', 'exports', 'finalization', 'finally',
- 'initialization', 'is', 'library', 'on', 'property', 'raise',
- 'threadvar', 'try'
- ]
- FREE_PASCAL_KEYWORDS = [
- 'dispose', 'exit', 'false', 'new', 'true'
- ]
- BLOCK_KEYWORDS = set([
- 'begin', 'class', 'const', 'constructor', 'destructor', 'end',
- 'finalization', 'function', 'implementation', 'initialization',
- 'label', 'library', 'operator', 'procedure', 'program', 'property',
- 'record', 'threadvar', 'type', 'unit', 'uses', 'var'
- ])
- FUNCTION_MODIFIERS = set([
- 'alias', 'cdecl', 'export', 'inline', 'interrupt', 'nostackframe',
- 'pascal', 'register', 'safecall', 'softfloat', 'stdcall',
- 'varargs', 'name', 'dynamic', 'near', 'virtual', 'external',
- 'override', 'assembler'
- ])
- # XXX: those aren't global. but currently we know no way for defining
- # them just for the type context.
- DIRECTIVES = set([
- 'absolute', 'abstract', 'assembler', 'cppdecl', 'default', 'far',
- 'far16', 'forward', 'index', 'oldfpccall', 'private', 'protected',
- 'published', 'public'
- ])
- BUILTIN_TYPES = set([
- 'ansichar', 'ansistring', 'bool', 'boolean', 'byte', 'bytebool',
- 'cardinal', 'char', 'comp', 'currency', 'double', 'dword',
- 'extended', 'int64', 'integer', 'iunknown', 'longbool', 'longint',
- 'longword', 'pansichar', 'pansistring', 'pbool', 'pboolean',
- 'pbyte', 'pbytearray', 'pcardinal', 'pchar', 'pcomp', 'pcurrency',
- 'pdate', 'pdatetime', 'pdouble', 'pdword', 'pextended', 'phandle',
- 'pint64', 'pinteger', 'plongint', 'plongword', 'pointer',
- 'ppointer', 'pshortint', 'pshortstring', 'psingle', 'psmallint',
- 'pstring', 'pvariant', 'pwidechar', 'pwidestring', 'pword',
- 'pwordarray', 'pwordbool', 'real', 'real48', 'shortint',
- 'shortstring', 'single', 'smallint', 'string', 'tclass', 'tdate',
- 'tdatetime', 'textfile', 'thandle', 'tobject', 'ttime', 'variant',
- 'widechar', 'widestring', 'word', 'wordbool'
- ])
- BUILTIN_UNITS = {
- 'System': [
- 'abs', 'acquireexceptionobject', 'addr', 'ansitoutf8',
- 'append', 'arctan', 'assert', 'assigned', 'assignfile',
- 'beginthread', 'blockread', 'blockwrite', 'break', 'chdir',
- 'chr', 'close', 'closefile', 'comptocurrency', 'comptodouble',
- 'concat', 'continue', 'copy', 'cos', 'dec', 'delete',
- 'dispose', 'doubletocomp', 'endthread', 'enummodules',
- 'enumresourcemodules', 'eof', 'eoln', 'erase', 'exceptaddr',
- 'exceptobject', 'exclude', 'exit', 'exp', 'filepos', 'filesize',
- 'fillchar', 'finalize', 'findclasshinstance', 'findhinstance',
- 'findresourcehinstance', 'flush', 'frac', 'freemem',
- 'get8087cw', 'getdir', 'getlasterror', 'getmem',
- 'getmemorymanager', 'getmodulefilename', 'getvariantmanager',
- 'halt', 'hi', 'high', 'inc', 'include', 'initialize', 'insert',
- 'int', 'ioresult', 'ismemorymanagerset', 'isvariantmanagerset',
- 'length', 'ln', 'lo', 'low', 'mkdir', 'move', 'new', 'odd',
- 'olestrtostring', 'olestrtostrvar', 'ord', 'paramcount',
- 'paramstr', 'pi', 'pos', 'pred', 'ptr', 'pucs4chars', 'random',
- 'randomize', 'read', 'readln', 'reallocmem',
- 'releaseexceptionobject', 'rename', 'reset', 'rewrite', 'rmdir',
- 'round', 'runerror', 'seek', 'seekeof', 'seekeoln',
- 'set8087cw', 'setlength', 'setlinebreakstyle',
- 'setmemorymanager', 'setstring', 'settextbuf',
- 'setvariantmanager', 'sin', 'sizeof', 'slice', 'sqr', 'sqrt',
- 'str', 'stringofchar', 'stringtoolestr', 'stringtowidechar',
- 'succ', 'swap', 'trunc', 'truncate', 'typeinfo',
- 'ucs4stringtowidestring', 'unicodetoutf8', 'uniquestring',
- 'upcase', 'utf8decode', 'utf8encode', 'utf8toansi',
- 'utf8tounicode', 'val', 'vararrayredim', 'varclear',
- 'widecharlentostring', 'widecharlentostrvar',
- 'widechartostring', 'widechartostrvar',
- 'widestringtoucs4string', 'write', 'writeln'
- ],
- 'SysUtils': [
- 'abort', 'addexitproc', 'addterminateproc', 'adjustlinebreaks',
- 'allocmem', 'ansicomparefilename', 'ansicomparestr',
- 'ansicomparetext', 'ansidequotedstr', 'ansiextractquotedstr',
- 'ansilastchar', 'ansilowercase', 'ansilowercasefilename',
- 'ansipos', 'ansiquotedstr', 'ansisamestr', 'ansisametext',
- 'ansistrcomp', 'ansistricomp', 'ansistrlastchar', 'ansistrlcomp',
- 'ansistrlicomp', 'ansistrlower', 'ansistrpos', 'ansistrrscan',
- 'ansistrscan', 'ansistrupper', 'ansiuppercase',
- 'ansiuppercasefilename', 'appendstr', 'assignstr', 'beep',
- 'booltostr', 'bytetocharindex', 'bytetocharlen', 'bytetype',
- 'callterminateprocs', 'changefileext', 'charlength',
- 'chartobyteindex', 'chartobytelen', 'comparemem', 'comparestr',
- 'comparetext', 'createdir', 'createguid', 'currentyear',
- 'currtostr', 'currtostrf', 'date', 'datetimetofiledate',
- 'datetimetostr', 'datetimetostring', 'datetimetosystemtime',
- 'datetimetotimestamp', 'datetostr', 'dayofweek', 'decodedate',
- 'decodedatefully', 'decodetime', 'deletefile', 'directoryexists',
- 'diskfree', 'disksize', 'disposestr', 'encodedate', 'encodetime',
- 'exceptionerrormessage', 'excludetrailingbackslash',
- 'excludetrailingpathdelimiter', 'expandfilename',
- 'expandfilenamecase', 'expanduncfilename', 'extractfiledir',
- 'extractfiledrive', 'extractfileext', 'extractfilename',
- 'extractfilepath', 'extractrelativepath', 'extractshortpathname',
- 'fileage', 'fileclose', 'filecreate', 'filedatetodatetime',
- 'fileexists', 'filegetattr', 'filegetdate', 'fileisreadonly',
- 'fileopen', 'fileread', 'filesearch', 'fileseek', 'filesetattr',
- 'filesetdate', 'filesetreadonly', 'filewrite', 'finalizepackage',
- 'findclose', 'findcmdlineswitch', 'findfirst', 'findnext',
- 'floattocurr', 'floattodatetime', 'floattodecimal', 'floattostr',
- 'floattostrf', 'floattotext', 'floattotextfmt', 'fmtloadstr',
- 'fmtstr', 'forcedirectories', 'format', 'formatbuf', 'formatcurr',
- 'formatdatetime', 'formatfloat', 'freeandnil', 'getcurrentdir',
- 'getenvironmentvariable', 'getfileversion', 'getformatsettings',
- 'getlocaleformatsettings', 'getmodulename', 'getpackagedescription',
- 'getpackageinfo', 'gettime', 'guidtostring', 'incamonth',
- 'includetrailingbackslash', 'includetrailingpathdelimiter',
- 'incmonth', 'initializepackage', 'interlockeddecrement',
- 'interlockedexchange', 'interlockedexchangeadd',
- 'interlockedincrement', 'inttohex', 'inttostr', 'isdelimiter',
- 'isequalguid', 'isleapyear', 'ispathdelimiter', 'isvalidident',
- 'languages', 'lastdelimiter', 'loadpackage', 'loadstr',
- 'lowercase', 'msecstotimestamp', 'newstr', 'nextcharindex', 'now',
- 'outofmemoryerror', 'quotedstr', 'raiselastoserror',
- 'raiselastwin32error', 'removedir', 'renamefile', 'replacedate',
- 'replacetime', 'safeloadlibrary', 'samefilename', 'sametext',
- 'setcurrentdir', 'showexception', 'sleep', 'stralloc', 'strbufsize',
- 'strbytetype', 'strcat', 'strcharlength', 'strcomp', 'strcopy',
- 'strdispose', 'strecopy', 'strend', 'strfmt', 'stricomp',
- 'stringreplace', 'stringtoguid', 'strlcat', 'strlcomp', 'strlcopy',
- 'strlen', 'strlfmt', 'strlicomp', 'strlower', 'strmove', 'strnew',
- 'strnextchar', 'strpas', 'strpcopy', 'strplcopy', 'strpos',
- 'strrscan', 'strscan', 'strtobool', 'strtobooldef', 'strtocurr',
- 'strtocurrdef', 'strtodate', 'strtodatedef', 'strtodatetime',
- 'strtodatetimedef', 'strtofloat', 'strtofloatdef', 'strtoint',
- 'strtoint64', 'strtoint64def', 'strtointdef', 'strtotime',
- 'strtotimedef', 'strupper', 'supports', 'syserrormessage',
- 'systemtimetodatetime', 'texttofloat', 'time', 'timestamptodatetime',
- 'timestamptomsecs', 'timetostr', 'trim', 'trimleft', 'trimright',
- 'tryencodedate', 'tryencodetime', 'tryfloattocurr', 'tryfloattodatetime',
- 'trystrtobool', 'trystrtocurr', 'trystrtodate', 'trystrtodatetime',
- 'trystrtofloat', 'trystrtoint', 'trystrtoint64', 'trystrtotime',
- 'unloadpackage', 'uppercase', 'widecomparestr', 'widecomparetext',
- 'widefmtstr', 'wideformat', 'wideformatbuf', 'widelowercase',
- 'widesamestr', 'widesametext', 'wideuppercase', 'win32check',
- 'wraptext'
- ],
- 'Classes': [
- 'activateclassgroup', 'allocatehwnd', 'bintohex', 'checksynchronize',
- 'collectionsequal', 'countgenerations', 'deallocatehwnd', 'equalrect',
- 'extractstrings', 'findclass', 'findglobalcomponent', 'getclass',
- 'groupdescendantswith', 'hextobin', 'identtoint',
- 'initinheritedcomponent', 'inttoident', 'invalidpoint',
- 'isuniqueglobalcomponentname', 'linestart', 'objectbinarytotext',
- 'objectresourcetotext', 'objecttexttobinary', 'objecttexttoresource',
- 'pointsequal', 'readcomponentres', 'readcomponentresex',
- 'readcomponentresfile', 'rect', 'registerclass', 'registerclassalias',
- 'registerclasses', 'registercomponents', 'registerintegerconsts',
- 'registernoicon', 'registernonactivex', 'smallpoint', 'startclassgroup',
- 'teststreamformat', 'unregisterclass', 'unregisterclasses',
- 'unregisterintegerconsts', 'unregistermoduleclasses',
- 'writecomponentresfile'
- ],
- 'Math': [
- 'arccos', 'arccosh', 'arccot', 'arccoth', 'arccsc', 'arccsch', 'arcsec',
- 'arcsech', 'arcsin', 'arcsinh', 'arctan2', 'arctanh', 'ceil',
- 'comparevalue', 'cosecant', 'cosh', 'cot', 'cotan', 'coth', 'csc',
- 'csch', 'cycletodeg', 'cycletograd', 'cycletorad', 'degtocycle',
- 'degtograd', 'degtorad', 'divmod', 'doubledecliningbalance',
- 'ensurerange', 'floor', 'frexp', 'futurevalue', 'getexceptionmask',
- 'getprecisionmode', 'getroundmode', 'gradtocycle', 'gradtodeg',
- 'gradtorad', 'hypot', 'inrange', 'interestpayment', 'interestrate',
- 'internalrateofreturn', 'intpower', 'isinfinite', 'isnan', 'iszero',
- 'ldexp', 'lnxp1', 'log10', 'log2', 'logn', 'max', 'maxintvalue',
- 'maxvalue', 'mean', 'meanandstddev', 'min', 'minintvalue', 'minvalue',
- 'momentskewkurtosis', 'netpresentvalue', 'norm', 'numberofperiods',
- 'payment', 'periodpayment', 'poly', 'popnstddev', 'popnvariance',
- 'power', 'presentvalue', 'radtocycle', 'radtodeg', 'radtograd',
- 'randg', 'randomrange', 'roundto', 'samevalue', 'sec', 'secant',
- 'sech', 'setexceptionmask', 'setprecisionmode', 'setroundmode',
- 'sign', 'simpleroundto', 'sincos', 'sinh', 'slndepreciation', 'stddev',
- 'sum', 'sumint', 'sumofsquares', 'sumsandsquares', 'syddepreciation',
- 'tan', 'tanh', 'totalvariance', 'variance'
- ]
- }
- ASM_REGISTERS = set([
- 'ah', 'al', 'ax', 'bh', 'bl', 'bp', 'bx', 'ch', 'cl', 'cr0',
- 'cr1', 'cr2', 'cr3', 'cr4', 'cs', 'cx', 'dh', 'di', 'dl', 'dr0',
- 'dr1', 'dr2', 'dr3', 'dr4', 'dr5', 'dr6', 'dr7', 'ds', 'dx',
- 'eax', 'ebp', 'ebx', 'ecx', 'edi', 'edx', 'es', 'esi', 'esp',
- 'fs', 'gs', 'mm0', 'mm1', 'mm2', 'mm3', 'mm4', 'mm5', 'mm6',
- 'mm7', 'si', 'sp', 'ss', 'st0', 'st1', 'st2', 'st3', 'st4', 'st5',
- 'st6', 'st7', 'xmm0', 'xmm1', 'xmm2', 'xmm3', 'xmm4', 'xmm5',
- 'xmm6', 'xmm7'
- ])
- ASM_INSTRUCTIONS = set([
- 'aaa', 'aad', 'aam', 'aas', 'adc', 'add', 'and', 'arpl', 'bound',
- 'bsf', 'bsr', 'bswap', 'bt', 'btc', 'btr', 'bts', 'call', 'cbw',
- 'cdq', 'clc', 'cld', 'cli', 'clts', 'cmc', 'cmova', 'cmovae',
- 'cmovb', 'cmovbe', 'cmovc', 'cmovcxz', 'cmove', 'cmovg',
- 'cmovge', 'cmovl', 'cmovle', 'cmovna', 'cmovnae', 'cmovnb',
- 'cmovnbe', 'cmovnc', 'cmovne', 'cmovng', 'cmovnge', 'cmovnl',
- 'cmovnle', 'cmovno', 'cmovnp', 'cmovns', 'cmovnz', 'cmovo',
- 'cmovp', 'cmovpe', 'cmovpo', 'cmovs', 'cmovz', 'cmp', 'cmpsb',
- 'cmpsd', 'cmpsw', 'cmpxchg', 'cmpxchg486', 'cmpxchg8b', 'cpuid',
- 'cwd', 'cwde', 'daa', 'das', 'dec', 'div', 'emms', 'enter', 'hlt',
- 'ibts', 'icebp', 'idiv', 'imul', 'in', 'inc', 'insb', 'insd',
- 'insw', 'int', 'int01', 'int03', 'int1', 'int3', 'into', 'invd',
- 'invlpg', 'iret', 'iretd', 'iretw', 'ja', 'jae', 'jb', 'jbe',
- 'jc', 'jcxz', 'jcxz', 'je', 'jecxz', 'jg', 'jge', 'jl', 'jle',
- 'jmp', 'jna', 'jnae', 'jnb', 'jnbe', 'jnc', 'jne', 'jng', 'jnge',
- 'jnl', 'jnle', 'jno', 'jnp', 'jns', 'jnz', 'jo', 'jp', 'jpe',
- 'jpo', 'js', 'jz', 'lahf', 'lar', 'lcall', 'lds', 'lea', 'leave',
- 'les', 'lfs', 'lgdt', 'lgs', 'lidt', 'ljmp', 'lldt', 'lmsw',
- 'loadall', 'loadall286', 'lock', 'lodsb', 'lodsd', 'lodsw',
- 'loop', 'loope', 'loopne', 'loopnz', 'loopz', 'lsl', 'lss', 'ltr',
- 'mov', 'movd', 'movq', 'movsb', 'movsd', 'movsw', 'movsx',
- 'movzx', 'mul', 'neg', 'nop', 'not', 'or', 'out', 'outsb', 'outsd',
- 'outsw', 'pop', 'popa', 'popad', 'popaw', 'popf', 'popfd', 'popfw',
- 'push', 'pusha', 'pushad', 'pushaw', 'pushf', 'pushfd', 'pushfw',
- 'rcl', 'rcr', 'rdmsr', 'rdpmc', 'rdshr', 'rdtsc', 'rep', 'repe',
- 'repne', 'repnz', 'repz', 'ret', 'retf', 'retn', 'rol', 'ror',
- 'rsdc', 'rsldt', 'rsm', 'sahf', 'sal', 'salc', 'sar', 'sbb',
- 'scasb', 'scasd', 'scasw', 'seta', 'setae', 'setb', 'setbe',
- 'setc', 'setcxz', 'sete', 'setg', 'setge', 'setl', 'setle',
- 'setna', 'setnae', 'setnb', 'setnbe', 'setnc', 'setne', 'setng',
- 'setnge', 'setnl', 'setnle', 'setno', 'setnp', 'setns', 'setnz',
- 'seto', 'setp', 'setpe', 'setpo', 'sets', 'setz', 'sgdt', 'shl',
- 'shld', 'shr', 'shrd', 'sidt', 'sldt', 'smi', 'smint', 'smintold',
- 'smsw', 'stc', 'std', 'sti', 'stosb', 'stosd', 'stosw', 'str',
- 'sub', 'svdc', 'svldt', 'svts', 'syscall', 'sysenter', 'sysexit',
- 'sysret', 'test', 'ud1', 'ud2', 'umov', 'verr', 'verw', 'wait',
- 'wbinvd', 'wrmsr', 'wrshr', 'xadd', 'xbts', 'xchg', 'xlat',
- 'xlatb', 'xor'
- ])
- def __init__(self, **options):
- Lexer.__init__(self, **options)
- self.keywords = set()
- if get_bool_opt(options, 'turbopascal', True):
- self.keywords.update(self.TURBO_PASCAL_KEYWORDS)
- if get_bool_opt(options, 'delphi', True):
- self.keywords.update(self.DELPHI_KEYWORDS)
- if get_bool_opt(options, 'freepascal', True):
- self.keywords.update(self.FREE_PASCAL_KEYWORDS)
- self.builtins = set()
- for unit in get_list_opt(options, 'units', self.BUILTIN_UNITS.keys()):
- self.builtins.update(self.BUILTIN_UNITS[unit])
- def get_tokens_unprocessed(self, text):
- scanner = Scanner(text, re.DOTALL | re.MULTILINE | re.IGNORECASE)
- stack = ['initial']
- in_function_block = False
- in_property_block = False
- was_dot = False
- next_token_is_function = False
- next_token_is_property = False
- collect_labels = False
- block_labels = set()
- brace_balance = [0, 0]
- while not scanner.eos:
- token = Error
- if stack[-1] == 'initial':
- if scanner.scan(r'\s+'):
- token = Text
- elif scanner.scan(r'\{.*?\}|\(\*.*?\*\)'):
- if scanner.match.startswith('$'):
- token = Comment.Preproc
- else:
- token = Comment.Multiline
- elif scanner.scan(r'//.*?$'):
- token = Comment.Single
- elif scanner.scan(r'[-+*\/=<>:;,.@\^]'):
- token = Operator
- # stop label highlighting on next ";"
- if collect_labels and scanner.match == ';':
- collect_labels = False
- elif scanner.scan(r'[\(\)\[\]]+'):
- token = Punctuation
- # abort function naming ``foo = Function(...)``
- next_token_is_function = False
- # if we are in a function block we count the open
- # braces because ootherwise it's impossible to
- # determine the end of the modifier context
- if in_function_block or in_property_block:
- if scanner.match == '(':
- brace_balance[0] += 1
- elif scanner.match == ')':
- brace_balance[0] -= 1
- elif scanner.match == '[':
- brace_balance[1] += 1
- elif scanner.match == ']':
- brace_balance[1] -= 1
- elif scanner.scan(r'[A-Za-z_][A-Za-z_0-9]*'):
- lowercase_name = scanner.match.lower()
- if lowercase_name == 'result':
- token = Name.Builtin.Pseudo
- elif lowercase_name in self.keywords:
- token = Keyword
- # if we are in a special block and a
- # block ending keyword occours (and the parenthesis
- # is balanced) we end the current block context
- if (in_function_block or in_property_block) and \
- lowercase_name in self.BLOCK_KEYWORDS and \
- brace_balance[0] <= 0 and \
- brace_balance[1] <= 0:
- in_function_block = False
- in_property_block = False
- brace_balance = [0, 0]
- block_labels = set()
- if lowercase_name in ('label', 'goto'):
- collect_labels = True
- elif lowercase_name == 'asm':
- stack.append('asm')
- elif lowercase_name == 'property':
- in_property_block = True
- next_token_is_property = True
- elif lowercase_name in ('procedure', 'operator',
- 'function', 'constructor',
- 'destructor'):
- in_function_block = True
- next_token_is_function = True
- # we are in a function block and the current name
- # is in the set of registered modifiers. highlight
- # it as pseudo keyword
- elif in_function_block and \
- lowercase_name in self.FUNCTION_MODIFIERS:
- token = Keyword.Pseudo
- # if we are in a property highlight some more
- # modifiers
- elif in_property_block and \
- lowercase_name in ('read', 'write'):
- token = Keyword.Pseudo
- next_token_is_function = True
- # if the last iteration set next_token_is_function
- # to true we now want this name highlighted as
- # function. so do that and reset the state
- elif next_token_is_function:
- # Look if the next token is a dot. If yes it's
- # not a function, but a class name and the
- # part after the dot a function name
- if scanner.test(r'\s*\.\s*'):
- token = Name.Class
- # it's not a dot, our job is done
- else:
- token = Name.Function
- next_token_is_function = False
- # same for properties
- elif next_token_is_property:
- token = Name.Property
- next_token_is_property = False
- # Highlight this token as label and add it
- # to the list of known labels
- elif collect_labels:
- token = Name.Label
- block_labels.add(scanner.match.lower())
- # name is in list of known labels
- elif lowercase_name in block_labels:
- token = Name.Label
- elif lowercase_name in self.BUILTIN_TYPES:
- token = Keyword.Type
- elif lowercase_name in self.DIRECTIVES:
- token = Keyword.Pseudo
- # builtins are just builtins if the token
- # before isn't a dot
- elif not was_dot and lowercase_name in self.builtins:
- token = Name.Builtin
- else:
- token = Name
- elif scanner.scan(r"'"):
- token = String
- stack.append('string')
- elif scanner.scan(r'\#(\d+|\$[0-9A-Fa-f]+)'):
- token = String.Char
- elif scanner.scan(r'\$[0-9A-Fa-f]+'):
- token = Number.Hex
- elif scanner.scan(r'\d+(?![eE]|\.[^.])'):
- token = Number.Integer
- elif scanner.scan(r'\d+(\.\d+([eE][+-]?\d+)?|[eE][+-]?\d+)'):
- token = Number.Float
- else:
- # if the stack depth is deeper than once, pop
- if len(stack) > 1:
- stack.pop()
- scanner.get_char()
- elif stack[-1] == 'string':
- if scanner.scan(r"''"):
- token = String.Escape
- elif scanner.scan(r"'"):
- token = String
- stack.pop()
- elif scanner.scan(r"[^']*"):
- token = String
- else:
- scanner.get_char()
- stack.pop()
- elif stack[-1] == 'asm':
- if scanner.scan(r'\s+'):
- token = Text
- elif scanner.scan(r'end'):
- token = Keyword
- stack.pop()
- elif scanner.scan(r'\{.*?\}|\(\*.*?\*\)'):
- if scanner.match.startswith('$'):
- token = Comment.Preproc
- else:
- token = Comment.Multiline
- elif scanner.scan(r'//.*?$'):
- token = Comment.Single
- elif scanner.scan(r"'"):
- token = String
- stack.append('string')
- elif scanner.scan(r'@@[A-Za-z_][A-Za-z_0-9]*'):
- token = Name.Label
- elif scanner.scan(r'[A-Za-z_][A-Za-z_0-9]*'):
- lowercase_name = scanner.match.lower()
- if lowercase_name in self.ASM_INSTRUCTIONS:
- token = Keyword
- elif lowercase_name in self.ASM_REGISTERS:
- token = Name.Builtin
- else:
- token = Name
- elif scanner.scan(r'[-+*\/=<>:;,.@\^]+'):
- token = Operator
- elif scanner.scan(r'[\(\)\[\]]+'):
- token = Punctuation
- elif scanner.scan(r'\$[0-9A-Fa-f]+'):
- token = Number.Hex
- elif scanner.scan(r'\d+(?![eE]|\.[^.])'):
- token = Number.Integer
- elif scanner.scan(r'\d+(\.\d+([eE][+-]?\d+)?|[eE][+-]?\d+)'):
- token = Number.Float
- else:
- scanner.get_char()
- stack.pop()
- # save the dot!!!11
- if scanner.match.strip():
- was_dot = scanner.match == '.'
- yield scanner.start_pos, token, scanner.match or ''
- class JavaLexer(RegexLexer):
- """
- For `Java <http://www.sun.com/java/>`_ source code.
- """
- name = 'Java'
- aliases = ['java']
- filenames = ['*.java']
- mimetypes = ['text/x-java']
- flags = re.MULTILINE | re.DOTALL
- #: optional Comment or Whitespace
- _ws = r'(?:\s|//.*?\n|/[*].*?[*]/)+'
- tokens = {
- 'root': [
- # method names
- (r'^(\s*(?:[a-zA-Z_][a-zA-Z0-9_\.\[\]]*\s+)+?)' # return arguments
- r'([a-zA-Z_][a-zA-Z0-9_]*)' # method name
- r'(\s*)(\()', # signature start
- bygroups(using(this), Name.Function, Text, Operator)),
- (r'[^\S\n]+', Text),
- (r'//.*?\n', Comment),
- (r'/\*.*?\*/', Comment),
- (r'@[a-zA-Z_][a-zA-Z0-9_\.]*', Name.Decorator),
- (r'(assert|break|case|catch|continue|default|do|else|finally|for|'
- r'if|goto|instanceof|new|return|switch|this|throw|try|while)\b',
- Keyword),
- (r'(abstract|const|enum|extends|final|implements|native|private|'
- r'protected|public|static|strictfp|super|synchronized|throws|'
- r'transient|volatile)\b', Keyword.Declaration),
- (r'(boolean|byte|char|double|float|int|long|short|void)\b',
- Keyword.Type),
- (r'(package)(\s+)', bygroups(Keyword.Namespace, Text)),
- (r'(true|false|null)\b', Keyword.Constant),
- (r'(class|interface)(\s+)', bygroups(Keyword.Declaration, Text), 'class'),
- (r'(import)(\s+)', bygroups(Keyword.Namespace, Text), 'import'),
- (r'"(\\\\|\\"|[^"])*"', String),
- (r"'\\.'|'[^\\]'|'\\u[0-9a-f]{4}'", String.Char),
- (r'(\.)([a-zA-Z_][a-zA-Z0-9_]*)', bygroups(Operator, Name.Attribute)),
- (r'[a-zA-Z_][a-zA-Z0-9_]*:', Name.Label),
- (r'[a-zA-Z_\$][a-zA-Z0-9_]*', Name),
- (r'[~\^\*!%&\[\]\(\)\{\}<>\|+=:;,./?-]', Operator),
- (r'[0-9][0-9]*\.[0-9]+([eE][0-9]+)?[fd]?', Number.Float),
- (r'0x[0-9a-f]+', Number.Hex),
- (r'[0-9]+L?', Number.Integer),
- (r'\n', Text)
- ],
- 'class': [
- (r'[a-zA-Z_][a-zA-Z0-9_]*', Name.Class, '#pop')
- ],
- 'import': [
- (r'[a-zA-Z0-9_.]+\*?', Name.Namespace, '#pop')
- ],
- }
- class ScalaLexer(RegexLexer):
- """
- For `Scala <http://www.scala-lang.org>`_ source code.
- """
- name = 'Scala'
- aliases = ['scala']
- filenames = ['*.scala']
- mimetypes = ['text/x-scala']
- flags = re.MULTILINE | re.DOTALL
- #: optional Comment or Whitespace
- _ws = r'(?:\s|//.*?\n|/[*].*?[*]/)+'
- tokens = {
- 'root': [
- # method names
- (r'(class|interface|trait|object)(\s+)', bygroups(Keyword, Text), 'class'),
- (r'^(\s*def)'
- r'([a-zA-Z_][a-zA-Z0-9_]*)' # method name
- r'(\s*)(\()', # signature start
- bygroups(using(this), Name.Function, Text, Operator)),
- (r"'([a-zA-Z_][a-zA-Z0-9_]*)", Text.Symbol),
- (r'[^\S\n]+', Text),
- (r'//.*?\n', Comment),
- (r'/\*.*?\*/', Comment),
- (r'@[a-zA-Z_][a-zA-Z0-9_\.]*', Name.Decorator),
- (r'(abstract|case|catch|do|else|extends|final|finally|for|forSome'
- r'|if|implicit|lazy|match|new|null|override|private|protected'
- r'|requires|return|sealed|super|this|throw|try|type|while|with'
- r'|yield|let|def|var|println|=>|<-|_)\b', Keyword),
- (r'(boolean|byte|char|double|float|int|long|short|void)\b',
- Keyword.Type),
- (r'(String|Int|Array|HashMap)\b', Keyword.Type),
- (r'(true|false|null)\b', Keyword.Constant),
- (r'(import)(\s+)', bygroups(Keyword, Text), 'import'),
- (r'"(\\\\|\\"|[^"])*"', String),
- (r"'\\.'|'[^\\]'|'\\u[0-9a-f]{4}'", String.Char),
- (r'(\.)([a-zA-Z_][a-zA-Z0-9_]*)', bygroups(Operator, Name.Attribute)),
- (r'[a-zA-Z_\$][a-zA-Z0-9_]*', Name),
- (r'[~\^\*!%&\[\]\(\)\{\}<>\|+=:;,./?-]', Operator),
- (r'[0-9][0-9]*\.[0-9]+([eE][0-9]+)?[fd]?', Number.Float),
- (r'0x[0-9a-f]+', Number.Hex),
- (r'[0-9]+L?', Number.Integer),
- (r'\n', Text)
- ],
- 'class': [
- (r'[a-zA-Z_][a-zA-Z0-9_]*', Name.Class, '#pop'),
- (r'([a-zA-Z_][a-zA-Z0-9_]*)(\s*)(\()',
- bygroups(Name.Class, Text, Operator), '#pop'),
- ],
- 'import': [
- (r'[a-zA-Z0-9_.]+\*?', Name.Namespace, '#pop')
- ],
- }
- class DylanLexer(RegexLexer):
- """
- For the `Dylan <http://www.opendylan.org/>`_ language.
- *New in Pygments 0.7.*
- """
- name = 'Dylan'
- aliases = ['dylan']
- filenames = ['*.dylan']
- mimetypes = ['text/x-dylan']
- flags = re.DOTALL
- tokens = {
- 'root': [
- (r'\b(subclass|abstract|block|c(on(crete|stant)|lass)|domain'
- r'|ex(c(eption|lude)|port)|f(unction(|al))|generic|handler'
- r'|i(n(herited|line|stance|terface)|mport)|library|m(acro|ethod)'
- r'|open|primary|sealed|si(deways|ngleton)|slot'
- r'|v(ariable|irtual))\b', Name.Builtin),
- (r'<\w+>', Keyword.Type),
- (r'#?"(?:\\.|[^"])+?"', String.Double),
- (r'//.*?\n', Comment),
- (r'/\*[\w\W]*?\*/', Comment.Multiline),
- (r'\'.*?\'', String.Single),
- (r'=>|\b(a(bove|fterwards)|b(e(gin|low)|y)|c(ase|leanup|reate)'
- r'|define|else(|if)|end|f(inally|or|rom)|i[fn]|l(et|ocal)|otherwise'
- r'|rename|s(elect|ignal)|t(hen|o)|u(n(less|til)|se)|wh(en|ile))\b',
- Keyword),
- (r'([ \t])([!\$%&\*\/:<=>\?~_^a-zA-Z0-9.+\-]*:)',
- bygroups(Text, Name.Variable)),
- (r'([ \t]*)(\S+[^:])([ \t]*)(\()([ \t]*)',
- bygroups(Text, Name.Function, Text, Punctuation, Text)),
- (r'-?[0-9.]+', Number),
- (r'[(),;]', Punctuation),
- (r'\$[a-zA-Z0-9-]+', Name.Constant),
- (r'[!$%&*/:<>=?~^.+\[\]{}-]+', Operator),
- (r'\s+', Text),
- (r'#[a-zA-Z0-9-]+', Keyword),
- (r'[a-zA-Z0-9-]+', Name.Variable),
- ],
- }
- class ObjectiveCLexer(RegexLexer):
- """
- For Objective-C source code with preprocessor directives.
- """
- name = 'Objective-C'
- aliases = ['objective-c', 'objectivec', 'obj-c', 'objc']
- #XXX: objc has .h files too :-/
- filenames = ['*.m']
- mimetypes = ['text/x-objective-c']
- #: optional Comment or Whitespace
- _ws = r'(?:\s|//.*?\n|/[*].*?[*]/)+'
- tokens = {
- 'whitespace': [
- (r'^(\s*)(#if\s+0)', bygroups(Text, Comment.Preproc), 'if0'),
- (r'^(\s*)(#)', bygroups(Text, Comment.Preproc), 'macro'),
- (r'\n', Text),
- (r'\s+', Text),
- (r'\\\n', Text), # line continuation
- (r'//(\n|(.|\n)*?[^\\]\n)', Comment),
- (r'/(\\\n)?[*](.|\n)*?[*](\\\n)?/', Comment),
- ],
- 'statements': [
- (r'(L|@)?"', String, 'string'),
- (r"(L|@)?'(\\.|\\[0-7]{1,3}|\\x[a-fA-F0-9]{1,2}|[^\\\'\n])'", String.Char),
- (r'(\d+\.\d*|\.\d+|\d+)[eE][+-]?\d+[lL]?', Number.Float),
- (r'(\d+\.\d*|\.\d+|\d+[fF])[fF]?', Number.Float),
- (r'0x[0-9a-fA-F]+[Ll]?', Number.Hex),
- (r'0[0-7]+[Ll]?', Number.Oct),
- (r'\d+[Ll]?', Number.Integer),
- (r'[~!%^&*+=|?:<>/-]', Operator),
- (r'[()\[\],.]', Punctuation),
- (r'(auto|break|case|const|continue|default|do|else|enum|extern|'
- r'for|goto|if|register|restricted|return|sizeof|static|struct|'
- r'switch|typedef|union|volatile|virtual|while|in|@selector|'
- r'@private|@protected|@public|@encode|'
- r'@synchronized|@try|@throw|@catch|@finally|@end|@property|'
- r'@synthesize|@dynamic)\b', Keyword),
- (r'(int|long|float|short|double|char|unsigned|signed|void|'
- r'id|BOOL|IBOutlet|IBAction|SEL)\b', Keyword.Type),
- (r'(_{0,2}inline|naked|restrict|thread|typename)\b', Keyword.Reserved),
- (r'__(asm|int8|based|except|int16|stdcall|cdecl|fastcall|int32|'
- r'declspec|finally|int64|try|leave)\b', Keyword.Reserved),
- (r'(TRUE|FALSE|nil|NULL)\b', Name.Builtin),
- ('[a-zA-Z_][a-zA-Z0-9_]*:(?!:)', Name.Label),
- ('[a-zA-Z_][a-zA-Z0-9_]*', Name),
- ],
- 'root': [
- include('whitespace'),
- # functions
- (r'((?:[a-zA-Z0-9_*\s])+?(?:\s|[*]))' # return arguments
- r'([a-zA-Z_][a-zA-Z0-9_]*)' # method name
- r'(\s*\([^;]*?\))' # signature
- r'(' + _ws + r')({)',
- bygroups(using(this), Name.Function, using(this), Text, Punctuation),
- 'function'),
- # function declarations
- (r'((?:[a-zA-Z0-9_*\s])+?(?:\s|[*]))' # return arguments
- r'([a-zA-Z_][a-zA-Z0-9_]*)' # method name
- r'(\s*\([^;]*?\))' # signature
- r'(' + _ws + r')(;)',
- bygroups(using(this), Name.Function, using(this), Text, Punctuation)),
- (r'(@interface|@implementation)(\s+)', bygroups(Keyword, Text), 'classname'),
- (r'(@class|@protocol)(\s+)', bygroups(Keyword, Text), 'forward_classname'),
- (r'(\s*)(@end)(\s*)', bygroups(Text, Keyword, Text)),
- ('', Text, 'statement'),
- ],
- 'classname' : [
- # interface definition that inherits
- ('([a-zA-Z_][a-zA-Z0-9_]*)(\s*:\s*)([a-zA-Z_][a-zA-Z0-9_]*)?',
- bygroups(Name.Class, Text, Name.Class), '#pop'),
- # interface definition for a category
- ('([a-zA-Z_][a-zA-Z0-9_]*)(\s*)(\([a-zA-Z_][a-zA-Z0-9_]*\))',
- bygroups(Name.Class, Text, Name.Label), '#pop'),
- # simple interface / implementation
- ('([a-zA-Z_][a-zA-Z0-9_]*)', Name.Class, '#pop')
- ],
- 'forward_classname' : [
- ('([a-zA-Z_][a-zA-Z0-9_]*)(\s*,\s*)',
- bygroups(Name.Class, Text), 'forward_classname'),
- ('([a-zA-Z_][a-zA-Z0-9_]*)(\s*;?)',
- bygroups(Name.Class, Text), '#pop')
- ],
- 'statement' : [
- include('whitespace'),
- include('statements'),
- ('[{}]', Punctuation),
- (';', Punctuation, '#pop'),
- ],
- 'function': [
- include('whitespace'),
- include('statements'),
- (';', Punctuation),
- ('{', Punctuation, '#push'),
- ('}', Punctuation, '#pop'),
- ],
- 'string': [
- (r'"', String, '#pop'),
- (r'\\([\\abfnrtv"\']|x[a-fA-F0-9]{2,4}|[0-7]{1,3})', String.Escape),
- (r'[^\\"\n]+', String), # all other characters
- (r'\\\n', String), # line continuation
- (r'\\', String), # stray backslash
- ],
- 'macro': [
- (r'[^/\n]+', Comment.Preproc),
- (r'/[*](.|\n)*?[*]/', Comment),
- (r'//.*?\n', Comment, '#pop'),
- (r'/', Comment.Preproc),
- (r'(?<=\\)\n', Comment.Preproc),
- (r'\n', Comment.Preproc, '#pop'),
- ],
- 'if0': [
- (r'^\s*#if.*?(?<!\\)\n', Comment, '#push'),
- (r'^\s*#endif.*?(?<!\\)\n', Comment, '#pop'),
- (r'.*?\n', Comment),
- ]
- }
- class FortranLexer(RegexLexer):
- '''
- Lexer for FORTRAN 90 code.
- *New in Pygments 0.10.*
- '''
- name = 'Fortran'
- aliases = ['fortran']
- filenames = ['*.f', '*.f90']
- mimetypes = ['text/x-fortran']
- flags = re.IGNORECASE
- # Data Types: INTEGER, REAL, COMPLEX, LOGICAL, CHARACTER and DOUBLE PRECISION
- # Operators: **, *, +, -, /, <, >, <=, >=, ==, /=
- # Logical (?): NOT, AND, OR, EQV, NEQV
- # Builtins:
- # http://gcc.gnu.org/onlinedocs/gcc-3.4.6/g77/Table-of-Intrinsic-Functions.html
- tokens = {
- 'root': [
- (r'!.*\n', Comment),
- include('strings'),
- include('core'),
- (r'[a-z][a-z0-9_]*', Name.Variable),
- include('nums'),
- (r'[\s]+', Text),
- ],
- 'core': [
- # Statements
- (r'\b(ACCEPT|ALLOCATABLE|ALLOCATE|ARRAY|ASSIGN|BACKSPACE|BLOCK DATA|'
- r'BYTE|CALL|CASE|CLOSE|COMMON|CONTAINS|CONTINUE|CYCLE|DATA|'
- r'DEALLOCATE|DECODE|DIMENSION|DO|ENCODE|END FILE|ENDIF|END|ENTRY|'
- r'EQUIVALENCE|EXIT|EXTERNAL|EXTRINSIC|FORALL|FORMAT|FUNCTION|GOTO|'
- r'IF|IMPLICIT|INCLUDE|INQUIRE|INTENT|INTERFACE|INTRINSIC|MODULE|'
- r'NAMELIST|NULLIFY|NONE|OPEN|OPTIONAL|OPTIONS|PARAMETER|PAUSE|'
- r'POINTER|PRINT|PRIVATE|PROGRAM|PUBLIC|PURE|READ|RECURSIVE|RETURN|'
- r'REWIND|SAVE|SELECT|SEQUENCE|STOP|SUBROUTINE|TARGET|TYPE|USE|'
- r'VOLATILE|WHERE|WRITE|WHILE|THEN|ELSE|ENDIF)\s*\b',
- Keyword),
- # Data Types
- (r'\b(CHARACTER|COMPLEX|DOUBLE PRECISION|DOUBLE COMPLEX|INTEGER|'
- r'LOGICAL|REAL)\s*\b',
- Keyword.Type),
- # Operators
- (r'(\*\*|\*|\+|-|\/|<|>|<=|>=|==|\/=|=)', Operator),
- (r'(::)', Keyword.Declaration),
- (r'[(),:&%]', Punctuation),
- # Intrinsics
- (r'\b(Abort|Abs|Access|AChar|ACos|AdjustL|AdjustR|AImag|AInt|Alarm|'
- r'All|Allocated|ALog|AMax|AMin|AMod|And|ANInt|Any|'
- r'ASin|Associated|ATan|BesJ|BesJN|BesY|BesYN|'
- r'Bit_Size|BTest|CAbs|CCos|Ceiling|CExp|Char|ChDir|ChMod|CLog|'
- r'Cmplx|Complex|Conjg|Cos|CosH|Count|CPU_Time|CShift|CSin|CSqRt|'
- r'CTime|DAbs|DACos|DASin|DATan|Date_and_Time|DbesJ|'
- r'DbesJ|DbesJN|DbesY|DbesY|DbesYN|Dble|DCos|DCosH|DDiM|DErF|DErFC|'
- r'DExp|Digits|DiM|DInt|DLog|DLog|DMax|DMin|DMod|DNInt|Dot_Product|'
- r'DProd|DSign|DSinH|DSin|DSqRt|DTanH|DTan|DTime|EOShift|Epsilon|'
- r'ErF|ErFC|ETime|Exit|Exp|Exponent|FDate|FGet|FGetC|Float|'
- r'Floor|Flush|FNum|FPutC|FPut|Fraction|FSeek|FStat|FTell|'
- r'GError|GetArg|GetCWD|GetEnv|GetGId|GetLog|GetPId|GetUId|'
- r'GMTime|HostNm|Huge|IAbs|IAChar|IAnd|IArgC|IBClr|IBits|'
- r'IBSet|IChar|IDate|IDiM|IDInt|IDNInt|IEOr|IErrNo|IFix|Imag|'
- r'ImagPart|Index|Int|IOr|IRand|IsaTty|IShft|IShftC|ISign|'
- r'ITime|Kill|Kind|LBound|Len|Len_Trim|LGe|LGt|Link|LLe|LLt|LnBlnk|'
- r'Loc|Log|Log|Logical|Long|LShift|LStat|LTime|MatMul|Max|'
- r'MaxExponent|MaxLoc|MaxVal|MClock|Merge|Min|MinExponent|MinLoc|'
- r'MinVal|Mod|Modulo|MvBits|Nearest|NInt|Not|Or|Pack|PError|'
- r'Precision|Present|Product|Radix|Rand|Random_Number|Random_Seed|'
- r'Range|Real|RealPart|Rename|Repeat|Reshape|RRSpacing|RShift|Scale|'
- r'Scan|Second|Selected_Int_Kind|Selected_Real_Kind|Set_Exponent|'
- r'Shape|Short|Sign|Signal|SinH|Sin|Sleep|Sngl|Spacing|Spread|SqRt|'
- r'SRand|Stat|Sum|SymLnk|System|System_Clock|Tan|TanH|Time|'
- r'Tiny|Transfer|Transpose|Trim|TtyNam|UBound|UMask|Unlink|Unpack|'
- r'Verify|XOr|ZAbs|ZCos|ZExp|ZLog|ZSin|ZSqRt)\s*\b',
- Name.Builtin),
- # Booleans
- (r'\.(true|false)\.', Name.Builtin),
- # Comparing Operators
- (r'\.(eq|ne|lt|le|gt|ge|not|and|or|eqv|neqv)\.', Operator.Word),
- ],
- 'strings': [
- (r'"(\\\\|\\[0-7]+|\\.|[^"])*"', String.Double),
- (r"'(\\\\|\\[0-7]+|\\.|[^'])*'", String.Single),
- ],
- 'nums': [
- (r'\d+(?![.Ee])', Number.Integer),
- (r'[+-]?\d*\.\d+([eE][-+]?\d+)?', Number.Float),
- (r'[+-]?\d+\.\d*([eE][-+]?\d+)?', Number.Float),
- ],
- }