645 lines
30 KiB
Python
645 lines
30 KiB
Python
"""
|
|
pygments.lexers.pascal
|
|
~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
Lexers for Pascal family languages.
|
|
|
|
:copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
|
|
:license: BSD, see LICENSE for details.
|
|
"""
|
|
|
|
import re
|
|
|
|
from pygments.lexer import Lexer
|
|
from pygments.util import get_bool_opt, get_list_opt
|
|
from pygments.token import Comment, Operator, Keyword, Name, String, \
|
|
Number, Punctuation, Error, Whitespace
|
|
from pygments.scanner import Scanner
|
|
|
|
# compatibility import
|
|
from pygments.lexers.modula2 import Modula2Lexer # noqa: F401
|
|
|
|
__all__ = ['DelphiLexer', 'PortugolLexer']
|
|
|
|
|
|
class PortugolLexer(Lexer):
|
|
"""For Portugol, a Pascal dialect with keywords in Portuguese."""
|
|
name = 'Portugol'
|
|
aliases = ['portugol']
|
|
filenames = ['*.alg', '*.portugol']
|
|
mimetypes = []
|
|
url = "https://www.apoioinformatica.inf.br/produtos/visualg/linguagem"
|
|
version_added = ''
|
|
|
|
def __init__(self, **options):
|
|
Lexer.__init__(self, **options)
|
|
self.lexer = DelphiLexer(**options, portugol=True)
|
|
|
|
def get_tokens_unprocessed(self, text):
|
|
return self.lexer.get_tokens_unprocessed(text)
|
|
|
|
|
|
class DelphiLexer(Lexer):
|
|
"""
|
|
For 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', '*.dpr']
|
|
mimetypes = ['text/x-pascal']
|
|
url = 'https://www.embarcadero.com/products/delphi'
|
|
version_added = ''
|
|
|
|
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 = {
|
|
'begin', 'class', 'const', 'constructor', 'destructor', 'end',
|
|
'finalization', 'function', 'implementation', 'initialization',
|
|
'label', 'library', 'operator', 'procedure', 'program', 'property',
|
|
'record', 'threadvar', 'type', 'unit', 'uses', 'var'
|
|
}
|
|
|
|
FUNCTION_MODIFIERS = {
|
|
'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 = {
|
|
'absolute', 'abstract', 'assembler', 'cppdecl', 'default', 'far',
|
|
'far16', 'forward', 'index', 'oldfpccall', 'private', 'protected',
|
|
'published', 'public'
|
|
}
|
|
|
|
BUILTIN_TYPES = {
|
|
'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 = {
|
|
'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 = {
|
|
'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'
|
|
}
|
|
|
|
PORTUGOL_KEYWORDS = (
|
|
'aleatorio',
|
|
'algoritmo',
|
|
'arquivo',
|
|
'ate',
|
|
'caso',
|
|
'cronometro',
|
|
'debug',
|
|
'e',
|
|
'eco',
|
|
'enquanto',
|
|
'entao',
|
|
'escolha',
|
|
'escreva',
|
|
'escreval',
|
|
'faca',
|
|
'falso',
|
|
'fimalgoritmo',
|
|
'fimenquanto',
|
|
'fimescolha',
|
|
'fimfuncao',
|
|
'fimpara',
|
|
'fimprocedimento',
|
|
'fimrepita',
|
|
'fimse',
|
|
'funcao',
|
|
'inicio',
|
|
'int',
|
|
'interrompa',
|
|
'leia',
|
|
'limpatela',
|
|
'mod',
|
|
'nao',
|
|
'ou',
|
|
'outrocaso',
|
|
'para',
|
|
'passo',
|
|
'pausa',
|
|
'procedimento',
|
|
'repita',
|
|
'retorne',
|
|
'se',
|
|
'senao',
|
|
'timer',
|
|
'var',
|
|
'vetor',
|
|
'verdadeiro',
|
|
'xou',
|
|
'div',
|
|
'mod',
|
|
'abs',
|
|
'arccos',
|
|
'arcsen',
|
|
'arctan',
|
|
'cos',
|
|
'cotan',
|
|
'Exp',
|
|
'grauprad',
|
|
'int',
|
|
'log',
|
|
'logn',
|
|
'pi',
|
|
'quad',
|
|
'radpgrau',
|
|
'raizq',
|
|
'rand',
|
|
'randi',
|
|
'sen',
|
|
'Tan',
|
|
'asc',
|
|
'carac',
|
|
'caracpnum',
|
|
'compr',
|
|
'copia',
|
|
'maiusc',
|
|
'minusc',
|
|
'numpcarac',
|
|
'pos',
|
|
)
|
|
|
|
PORTUGOL_BUILTIN_TYPES = {
|
|
'inteiro', 'real', 'caractere', 'logico'
|
|
}
|
|
|
|
def __init__(self, **options):
|
|
Lexer.__init__(self, **options)
|
|
self.keywords = set()
|
|
self.builtins = set()
|
|
if get_bool_opt(options, 'portugol', False):
|
|
self.keywords.update(self.PORTUGOL_KEYWORDS)
|
|
self.builtins.update(self.PORTUGOL_BUILTIN_TYPES)
|
|
self.is_portugol = True
|
|
else:
|
|
self.is_portugol = False
|
|
|
|
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)
|
|
for unit in get_list_opt(options, 'units', list(self.BUILTIN_UNITS)):
|
|
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 = Whitespace
|
|
elif not self.is_portugol and scanner.scan(r'\{.*?\}|\(\*.*?\*\)'):
|
|
if scanner.match.startswith('$'):
|
|
token = Comment.Preproc
|
|
else:
|
|
token = Comment.Multiline
|
|
elif scanner.scan(r'//.*?$'):
|
|
token = Comment.Single
|
|
elif self.is_portugol and scanner.scan(r'(<\-)|(>=)|(<=)|%|<|>|-|\+|\*|\=|(<>)|\/|\.|:|,'):
|
|
token = Operator
|
|
elif not self.is_portugol and 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 occurs (and the parenthesis
|
|
# is balanced) we end the current block context
|
|
if self.is_portugol:
|
|
if lowercase_name in ('funcao', 'procedimento'):
|
|
in_function_block = True
|
|
next_token_is_function = True
|
|
else:
|
|
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 not self.is_portugol and in_function_block and \
|
|
lowercase_name in self.FUNCTION_MODIFIERS:
|
|
token = Keyword.Pseudo
|
|
# if we are in a property highlight some more
|
|
# modifiers
|
|
elif not self.is_portugol and 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 not self.is_portugol and 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
|
|
|
|
if self.is_portugol:
|
|
block_labels.add(scanner.match.lower())
|
|
|
|
# same for properties
|
|
elif not self.is_portugol and 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 not self.is_portugol and 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 self.is_portugol and lowercase_name in self.PORTUGOL_BUILTIN_TYPES:
|
|
token = Keyword.Type
|
|
elif not self.is_portugol and lowercase_name in self.BUILTIN_TYPES:
|
|
token = Keyword.Type
|
|
elif not self.is_portugol and lowercase_name in self.DIRECTIVES:
|
|
token = Keyword.Pseudo
|
|
# builtins are just builtins if the token
|
|
# before isn't a dot
|
|
elif not self.is_portugol and not was_dot and lowercase_name in self.builtins:
|
|
token = Name.Builtin
|
|
else:
|
|
token = Name
|
|
elif self.is_portugol and scanner.scan(r"\""):
|
|
token = String
|
|
stack.append('string')
|
|
elif not self.is_portugol and scanner.scan(r"'"):
|
|
token = String
|
|
stack.append('string')
|
|
elif not self.is_portugol and scanner.scan(r'\#(\d+|\$[0-9A-Fa-f]+)'):
|
|
token = String.Char
|
|
elif not self.is_portugol and 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 self.is_portugol:
|
|
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()
|
|
else:
|
|
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 not self.is_portugol and stack[-1] == 'asm':
|
|
if scanner.scan(r'\s+'):
|
|
token = Whitespace
|
|
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 not self.is_portugol and scanner.match.strip():
|
|
was_dot = scanner.match == '.'
|
|
|
|
yield scanner.start_pos, token, scanner.match or ''
|