Mercurial Repositories > eric / file comparison
comparison: eric6/ThirdParty/Pygments/pygments/lexers/pascal.py
eric6/ThirdParty/Pygments/pygments/lexers/pascal.py
- changeset 6942
- 2602857055c5
- parent 6651
- e8f3b5568b21
- child 7547
- 21b0534faebc
equal
deleted
inserted
replaced
| 6941:f99d60d6b59b | 6942:2602857055c5 |
|---|---|
| 1 # -*- coding: utf-8 -*- | |
| 2 """ | |
| 3 pygments.lexers.pascal | |
| 4 ~~~~~~~~~~~~~~~~~~~~~~ | |
| 5 | |
| 6 Lexers for Pascal family languages. | |
| 7 | |
| 8 :copyright: Copyright 2006-2017 by the Pygments team, see AUTHORS. | |
| 9 :license: BSD, see LICENSE for details. | |
| 10 """ | |
| 11 | |
| 12 import re | |
| 13 | |
| 14 from pygments.lexer import Lexer, RegexLexer, include, bygroups, words, \ | |
| 15 using, this, default | |
| 16 from pygments.util import get_bool_opt, get_list_opt | |
| 17 from pygments.token import Text, Comment, Operator, Keyword, Name, String, \ | |
| 18 Number, Punctuation, Error | |
| 19 from pygments.scanner import Scanner | |
| 20 | |
| 21 # compatibility import | |
| 22 from pygments.lexers.modula2 import Modula2Lexer | |
| 23 | |
| 24 __all__ = ['DelphiLexer', 'AdaLexer'] | |
| 25 | |
| 26 | |
| 27 class DelphiLexer(Lexer): | |
| 28 """ | |
| 29 For `Delphi <http://www.borland.com/delphi/>`_ (Borland Object Pascal), | |
| 30 Turbo Pascal and Free Pascal source code. | |
| 31 | |
| 32 Additional options accepted: | |
| 33 | |
| 34 `turbopascal` | |
| 35 Highlight Turbo Pascal specific keywords (default: ``True``). | |
| 36 `delphi` | |
| 37 Highlight Borland Delphi specific keywords (default: ``True``). | |
| 38 `freepascal` | |
| 39 Highlight Free Pascal specific keywords (default: ``True``). | |
| 40 `units` | |
| 41 A list of units that should be considered builtin, supported are | |
| 42 ``System``, ``SysUtils``, ``Classes`` and ``Math``. | |
| 43 Default is to consider all of them builtin. | |
| 44 """ | |
| 45 name = 'Delphi' | |
| 46 aliases = ['delphi', 'pas', 'pascal', 'objectpascal'] | |
| 47 filenames = ['*.pas', '*.dpr'] | |
| 48 mimetypes = ['text/x-pascal'] | |
| 49 | |
| 50 TURBO_PASCAL_KEYWORDS = ( | |
| 51 'absolute', 'and', 'array', 'asm', 'begin', 'break', 'case', | |
| 52 'const', 'constructor', 'continue', 'destructor', 'div', 'do', | |
| 53 'downto', 'else', 'end', 'file', 'for', 'function', 'goto', | |
| 54 'if', 'implementation', 'in', 'inherited', 'inline', 'interface', | |
| 55 'label', 'mod', 'nil', 'not', 'object', 'of', 'on', 'operator', | |
| 56 'or', 'packed', 'procedure', 'program', 'record', 'reintroduce', | |
| 57 'repeat', 'self', 'set', 'shl', 'shr', 'string', 'then', 'to', | |
| 58 'type', 'unit', 'until', 'uses', 'var', 'while', 'with', 'xor' | |
| 59 ) | |
| 60 | |
| 61 DELPHI_KEYWORDS = ( | |
| 62 'as', 'class', 'except', 'exports', 'finalization', 'finally', | |
| 63 'initialization', 'is', 'library', 'on', 'property', 'raise', | |
| 64 'threadvar', 'try' | |
| 65 ) | |
| 66 | |
| 67 FREE_PASCAL_KEYWORDS = ( | |
| 68 'dispose', 'exit', 'false', 'new', 'true' | |
| 69 ) | |
| 70 | |
| 71 BLOCK_KEYWORDS = set(( | |
| 72 'begin', 'class', 'const', 'constructor', 'destructor', 'end', | |
| 73 'finalization', 'function', 'implementation', 'initialization', | |
| 74 'label', 'library', 'operator', 'procedure', 'program', 'property', | |
| 75 'record', 'threadvar', 'type', 'unit', 'uses', 'var' | |
| 76 )) | |
| 77 | |
| 78 FUNCTION_MODIFIERS = set(( | |
| 79 'alias', 'cdecl', 'export', 'inline', 'interrupt', 'nostackframe', | |
| 80 'pascal', 'register', 'safecall', 'softfloat', 'stdcall', | |
| 81 'varargs', 'name', 'dynamic', 'near', 'virtual', 'external', | |
| 82 'override', 'assembler' | |
| 83 )) | |
| 84 | |
| 85 # XXX: those aren't global. but currently we know no way for defining | |
| 86 # them just for the type context. | |
| 87 DIRECTIVES = set(( | |
| 88 'absolute', 'abstract', 'assembler', 'cppdecl', 'default', 'far', | |
| 89 'far16', 'forward', 'index', 'oldfpccall', 'private', 'protected', | |
| 90 'published', 'public' | |
| 91 )) | |
| 92 | |
| 93 BUILTIN_TYPES = set(( | |
| 94 'ansichar', 'ansistring', 'bool', 'boolean', 'byte', 'bytebool', | |
| 95 'cardinal', 'char', 'comp', 'currency', 'double', 'dword', | |
| 96 'extended', 'int64', 'integer', 'iunknown', 'longbool', 'longint', | |
| 97 'longword', 'pansichar', 'pansistring', 'pbool', 'pboolean', | |
| 98 'pbyte', 'pbytearray', 'pcardinal', 'pchar', 'pcomp', 'pcurrency', | |
| 99 'pdate', 'pdatetime', 'pdouble', 'pdword', 'pextended', 'phandle', | |
| 100 'pint64', 'pinteger', 'plongint', 'plongword', 'pointer', | |
| 101 'ppointer', 'pshortint', 'pshortstring', 'psingle', 'psmallint', | |
| 102 'pstring', 'pvariant', 'pwidechar', 'pwidestring', 'pword', | |
| 103 'pwordarray', 'pwordbool', 'real', 'real48', 'shortint', | |
| 104 'shortstring', 'single', 'smallint', 'string', 'tclass', 'tdate', | |
| 105 'tdatetime', 'textfile', 'thandle', 'tobject', 'ttime', 'variant', | |
| 106 'widechar', 'widestring', 'word', 'wordbool' | |
| 107 )) | |
| 108 | |
| 109 BUILTIN_UNITS = { | |
| 110 'System': ( | |
| 111 'abs', 'acquireexceptionobject', 'addr', 'ansitoutf8', | |
| 112 'append', 'arctan', 'assert', 'assigned', 'assignfile', | |
| 113 'beginthread', 'blockread', 'blockwrite', 'break', 'chdir', | |
| 114 'chr', 'close', 'closefile', 'comptocurrency', 'comptodouble', | |
| 115 'concat', 'continue', 'copy', 'cos', 'dec', 'delete', | |
| 116 'dispose', 'doubletocomp', 'endthread', 'enummodules', | |
| 117 'enumresourcemodules', 'eof', 'eoln', 'erase', 'exceptaddr', | |
| 118 'exceptobject', 'exclude', 'exit', 'exp', 'filepos', 'filesize', | |
| 119 'fillchar', 'finalize', 'findclasshinstance', 'findhinstance', | |
| 120 'findresourcehinstance', 'flush', 'frac', 'freemem', | |
| 121 'get8087cw', 'getdir', 'getlasterror', 'getmem', | |
| 122 'getmemorymanager', 'getmodulefilename', 'getvariantmanager', | |
| 123 'halt', 'hi', 'high', 'inc', 'include', 'initialize', 'insert', | |
| 124 'int', 'ioresult', 'ismemorymanagerset', 'isvariantmanagerset', | |
| 125 'length', 'ln', 'lo', 'low', 'mkdir', 'move', 'new', 'odd', | |
| 126 'olestrtostring', 'olestrtostrvar', 'ord', 'paramcount', | |
| 127 'paramstr', 'pi', 'pos', 'pred', 'ptr', 'pucs4chars', 'random', | |
| 128 'randomize', 'read', 'readln', 'reallocmem', | |
| 129 'releaseexceptionobject', 'rename', 'reset', 'rewrite', 'rmdir', | |
| 130 'round', 'runerror', 'seek', 'seekeof', 'seekeoln', | |
| 131 'set8087cw', 'setlength', 'setlinebreakstyle', | |
| 132 'setmemorymanager', 'setstring', 'settextbuf', | |
| 133 'setvariantmanager', 'sin', 'sizeof', 'slice', 'sqr', 'sqrt', | |
| 134 'str', 'stringofchar', 'stringtoolestr', 'stringtowidechar', | |
| 135 'succ', 'swap', 'trunc', 'truncate', 'typeinfo', | |
| 136 'ucs4stringtowidestring', 'unicodetoutf8', 'uniquestring', | |
| 137 'upcase', 'utf8decode', 'utf8encode', 'utf8toansi', | |
| 138 'utf8tounicode', 'val', 'vararrayredim', 'varclear', | |
| 139 'widecharlentostring', 'widecharlentostrvar', | |
| 140 'widechartostring', 'widechartostrvar', | |
| 141 'widestringtoucs4string', 'write', 'writeln' | |
| 142 ), | |
| 143 'SysUtils': ( | |
| 144 'abort', 'addexitproc', 'addterminateproc', 'adjustlinebreaks', | |
| 145 'allocmem', 'ansicomparefilename', 'ansicomparestr', | |
| 146 'ansicomparetext', 'ansidequotedstr', 'ansiextractquotedstr', | |
| 147 'ansilastchar', 'ansilowercase', 'ansilowercasefilename', | |
| 148 'ansipos', 'ansiquotedstr', 'ansisamestr', 'ansisametext', | |
| 149 'ansistrcomp', 'ansistricomp', 'ansistrlastchar', 'ansistrlcomp', | |
| 150 'ansistrlicomp', 'ansistrlower', 'ansistrpos', 'ansistrrscan', | |
| 151 'ansistrscan', 'ansistrupper', 'ansiuppercase', | |
| 152 'ansiuppercasefilename', 'appendstr', 'assignstr', 'beep', | |
| 153 'booltostr', 'bytetocharindex', 'bytetocharlen', 'bytetype', | |
| 154 'callterminateprocs', 'changefileext', 'charlength', | |
| 155 'chartobyteindex', 'chartobytelen', 'comparemem', 'comparestr', | |
| 156 'comparetext', 'createdir', 'createguid', 'currentyear', | |
| 157 'currtostr', 'currtostrf', 'date', 'datetimetofiledate', | |
| 158 'datetimetostr', 'datetimetostring', 'datetimetosystemtime', | |
| 159 'datetimetotimestamp', 'datetostr', 'dayofweek', 'decodedate', | |
| 160 'decodedatefully', 'decodetime', 'deletefile', 'directoryexists', | |
| 161 'diskfree', 'disksize', 'disposestr', 'encodedate', 'encodetime', | |
| 162 'exceptionerrormessage', 'excludetrailingbackslash', | |
| 163 'excludetrailingpathdelimiter', 'expandfilename', | |
| 164 'expandfilenamecase', 'expanduncfilename', 'extractfiledir', | |
| 165 'extractfiledrive', 'extractfileext', 'extractfilename', | |
| 166 'extractfilepath', 'extractrelativepath', 'extractshortpathname', | |
| 167 'fileage', 'fileclose', 'filecreate', 'filedatetodatetime', | |
| 168 'fileexists', 'filegetattr', 'filegetdate', 'fileisreadonly', | |
| 169 'fileopen', 'fileread', 'filesearch', 'fileseek', 'filesetattr', | |
| 170 'filesetdate', 'filesetreadonly', 'filewrite', 'finalizepackage', | |
| 171 'findclose', 'findcmdlineswitch', 'findfirst', 'findnext', | |
| 172 'floattocurr', 'floattodatetime', 'floattodecimal', 'floattostr', | |
| 173 'floattostrf', 'floattotext', 'floattotextfmt', 'fmtloadstr', | |
| 174 'fmtstr', 'forcedirectories', 'format', 'formatbuf', 'formatcurr', | |
| 175 'formatdatetime', 'formatfloat', 'freeandnil', 'getcurrentdir', | |
| 176 'getenvironmentvariable', 'getfileversion', 'getformatsettings', | |
| 177 'getlocaleformatsettings', 'getmodulename', 'getpackagedescription', | |
| 178 'getpackageinfo', 'gettime', 'guidtostring', 'incamonth', | |
| 179 'includetrailingbackslash', 'includetrailingpathdelimiter', | |
| 180 'incmonth', 'initializepackage', 'interlockeddecrement', | |
| 181 'interlockedexchange', 'interlockedexchangeadd', | |
| 182 'interlockedincrement', 'inttohex', 'inttostr', 'isdelimiter', | |
| 183 'isequalguid', 'isleapyear', 'ispathdelimiter', 'isvalidident', | |
| 184 'languages', 'lastdelimiter', 'loadpackage', 'loadstr', | |
| 185 'lowercase', 'msecstotimestamp', 'newstr', 'nextcharindex', 'now', | |
| 186 'outofmemoryerror', 'quotedstr', 'raiselastoserror', | |
| 187 'raiselastwin32error', 'removedir', 'renamefile', 'replacedate', | |
| 188 'replacetime', 'safeloadlibrary', 'samefilename', 'sametext', | |
| 189 'setcurrentdir', 'showexception', 'sleep', 'stralloc', 'strbufsize', | |
| 190 'strbytetype', 'strcat', 'strcharlength', 'strcomp', 'strcopy', | |
| 191 'strdispose', 'strecopy', 'strend', 'strfmt', 'stricomp', | |
| 192 'stringreplace', 'stringtoguid', 'strlcat', 'strlcomp', 'strlcopy', | |
| 193 'strlen', 'strlfmt', 'strlicomp', 'strlower', 'strmove', 'strnew', | |
| 194 'strnextchar', 'strpas', 'strpcopy', 'strplcopy', 'strpos', | |
| 195 'strrscan', 'strscan', 'strtobool', 'strtobooldef', 'strtocurr', | |
| 196 'strtocurrdef', 'strtodate', 'strtodatedef', 'strtodatetime', | |
| 197 'strtodatetimedef', 'strtofloat', 'strtofloatdef', 'strtoint', | |
| 198 'strtoint64', 'strtoint64def', 'strtointdef', 'strtotime', | |
| 199 'strtotimedef', 'strupper', 'supports', 'syserrormessage', | |
| 200 'systemtimetodatetime', 'texttofloat', 'time', 'timestamptodatetime', | |
| 201 'timestamptomsecs', 'timetostr', 'trim', 'trimleft', 'trimright', | |
| 202 'tryencodedate', 'tryencodetime', 'tryfloattocurr', 'tryfloattodatetime', | |
| 203 'trystrtobool', 'trystrtocurr', 'trystrtodate', 'trystrtodatetime', | |
| 204 'trystrtofloat', 'trystrtoint', 'trystrtoint64', 'trystrtotime', | |
| 205 'unloadpackage', 'uppercase', 'widecomparestr', 'widecomparetext', | |
| 206 'widefmtstr', 'wideformat', 'wideformatbuf', 'widelowercase', | |
| 207 'widesamestr', 'widesametext', 'wideuppercase', 'win32check', | |
| 208 'wraptext' | |
| 209 ), | |
| 210 'Classes': ( | |
| 211 'activateclassgroup', 'allocatehwnd', 'bintohex', 'checksynchronize', | |
| 212 'collectionsequal', 'countgenerations', 'deallocatehwnd', 'equalrect', | |
| 213 'extractstrings', 'findclass', 'findglobalcomponent', 'getclass', | |
| 214 'groupdescendantswith', 'hextobin', 'identtoint', | |
| 215 'initinheritedcomponent', 'inttoident', 'invalidpoint', | |
| 216 'isuniqueglobalcomponentname', 'linestart', 'objectbinarytotext', | |
| 217 'objectresourcetotext', 'objecttexttobinary', 'objecttexttoresource', | |
| 218 'pointsequal', 'readcomponentres', 'readcomponentresex', | |
| 219 'readcomponentresfile', 'rect', 'registerclass', 'registerclassalias', | |
| 220 'registerclasses', 'registercomponents', 'registerintegerconsts', | |
| 221 'registernoicon', 'registernonactivex', 'smallpoint', 'startclassgroup', | |
| 222 'teststreamformat', 'unregisterclass', 'unregisterclasses', | |
| 223 'unregisterintegerconsts', 'unregistermoduleclasses', | |
| 224 'writecomponentresfile' | |
| 225 ), | |
| 226 'Math': ( | |
| 227 'arccos', 'arccosh', 'arccot', 'arccoth', 'arccsc', 'arccsch', 'arcsec', | |
| 228 'arcsech', 'arcsin', 'arcsinh', 'arctan2', 'arctanh', 'ceil', | |
| 229 'comparevalue', 'cosecant', 'cosh', 'cot', 'cotan', 'coth', 'csc', | |
| 230 'csch', 'cycletodeg', 'cycletograd', 'cycletorad', 'degtocycle', | |
| 231 'degtograd', 'degtorad', 'divmod', 'doubledecliningbalance', | |
| 232 'ensurerange', 'floor', 'frexp', 'futurevalue', 'getexceptionmask', | |
| 233 'getprecisionmode', 'getroundmode', 'gradtocycle', 'gradtodeg', | |
| 234 'gradtorad', 'hypot', 'inrange', 'interestpayment', 'interestrate', | |
| 235 'internalrateofreturn', 'intpower', 'isinfinite', 'isnan', 'iszero', | |
| 236 'ldexp', 'lnxp1', 'log10', 'log2', 'logn', 'max', 'maxintvalue', | |
| 237 'maxvalue', 'mean', 'meanandstddev', 'min', 'minintvalue', 'minvalue', | |
| 238 'momentskewkurtosis', 'netpresentvalue', 'norm', 'numberofperiods', | |
| 239 'payment', 'periodpayment', 'poly', 'popnstddev', 'popnvariance', | |
| 240 'power', 'presentvalue', 'radtocycle', 'radtodeg', 'radtograd', | |
| 241 'randg', 'randomrange', 'roundto', 'samevalue', 'sec', 'secant', | |
| 242 'sech', 'setexceptionmask', 'setprecisionmode', 'setroundmode', | |
| 243 'sign', 'simpleroundto', 'sincos', 'sinh', 'slndepreciation', 'stddev', | |
| 244 'sum', 'sumint', 'sumofsquares', 'sumsandsquares', 'syddepreciation', | |
| 245 'tan', 'tanh', 'totalvariance', 'variance' | |
| 246 ) | |
| 247 } | |
| 248 | |
| 249 ASM_REGISTERS = set(( | |
| 250 'ah', 'al', 'ax', 'bh', 'bl', 'bp', 'bx', 'ch', 'cl', 'cr0', | |
| 251 'cr1', 'cr2', 'cr3', 'cr4', 'cs', 'cx', 'dh', 'di', 'dl', 'dr0', | |
| 252 'dr1', 'dr2', 'dr3', 'dr4', 'dr5', 'dr6', 'dr7', 'ds', 'dx', | |
| 253 'eax', 'ebp', 'ebx', 'ecx', 'edi', 'edx', 'es', 'esi', 'esp', | |
| 254 'fs', 'gs', 'mm0', 'mm1', 'mm2', 'mm3', 'mm4', 'mm5', 'mm6', | |
| 255 'mm7', 'si', 'sp', 'ss', 'st0', 'st1', 'st2', 'st3', 'st4', 'st5', | |
| 256 'st6', 'st7', 'xmm0', 'xmm1', 'xmm2', 'xmm3', 'xmm4', 'xmm5', | |
| 257 'xmm6', 'xmm7' | |
| 258 )) | |
| 259 | |
| 260 ASM_INSTRUCTIONS = set(( | |
| 261 'aaa', 'aad', 'aam', 'aas', 'adc', 'add', 'and', 'arpl', 'bound', | |
| 262 'bsf', 'bsr', 'bswap', 'bt', 'btc', 'btr', 'bts', 'call', 'cbw', | |
| 263 'cdq', 'clc', 'cld', 'cli', 'clts', 'cmc', 'cmova', 'cmovae', | |
| 264 'cmovb', 'cmovbe', 'cmovc', 'cmovcxz', 'cmove', 'cmovg', | |
| 265 'cmovge', 'cmovl', 'cmovle', 'cmovna', 'cmovnae', 'cmovnb', | |
| 266 'cmovnbe', 'cmovnc', 'cmovne', 'cmovng', 'cmovnge', 'cmovnl', | |
| 267 'cmovnle', 'cmovno', 'cmovnp', 'cmovns', 'cmovnz', 'cmovo', | |
| 268 'cmovp', 'cmovpe', 'cmovpo', 'cmovs', 'cmovz', 'cmp', 'cmpsb', | |
| 269 'cmpsd', 'cmpsw', 'cmpxchg', 'cmpxchg486', 'cmpxchg8b', 'cpuid', | |
| 270 'cwd', 'cwde', 'daa', 'das', 'dec', 'div', 'emms', 'enter', 'hlt', | |
| 271 'ibts', 'icebp', 'idiv', 'imul', 'in', 'inc', 'insb', 'insd', | |
| 272 'insw', 'int', 'int01', 'int03', 'int1', 'int3', 'into', 'invd', | |
| 273 'invlpg', 'iret', 'iretd', 'iretw', 'ja', 'jae', 'jb', 'jbe', | |
| 274 'jc', 'jcxz', 'jcxz', 'je', 'jecxz', 'jg', 'jge', 'jl', 'jle', | |
| 275 'jmp', 'jna', 'jnae', 'jnb', 'jnbe', 'jnc', 'jne', 'jng', 'jnge', | |
| 276 'jnl', 'jnle', 'jno', 'jnp', 'jns', 'jnz', 'jo', 'jp', 'jpe', | |
| 277 'jpo', 'js', 'jz', 'lahf', 'lar', 'lcall', 'lds', 'lea', 'leave', | |
| 278 'les', 'lfs', 'lgdt', 'lgs', 'lidt', 'ljmp', 'lldt', 'lmsw', | |
| 279 'loadall', 'loadall286', 'lock', 'lodsb', 'lodsd', 'lodsw', | |
| 280 'loop', 'loope', 'loopne', 'loopnz', 'loopz', 'lsl', 'lss', 'ltr', | |
| 281 'mov', 'movd', 'movq', 'movsb', 'movsd', 'movsw', 'movsx', | |
| 282 'movzx', 'mul', 'neg', 'nop', 'not', 'or', 'out', 'outsb', 'outsd', | |
| 283 'outsw', 'pop', 'popa', 'popad', 'popaw', 'popf', 'popfd', 'popfw', | |
| 284 'push', 'pusha', 'pushad', 'pushaw', 'pushf', 'pushfd', 'pushfw', | |
| 285 'rcl', 'rcr', 'rdmsr', 'rdpmc', 'rdshr', 'rdtsc', 'rep', 'repe', | |
| 286 'repne', 'repnz', 'repz', 'ret', 'retf', 'retn', 'rol', 'ror', | |
| 287 'rsdc', 'rsldt', 'rsm', 'sahf', 'sal', 'salc', 'sar', 'sbb', | |
| 288 'scasb', 'scasd', 'scasw', 'seta', 'setae', 'setb', 'setbe', | |
| 289 'setc', 'setcxz', 'sete', 'setg', 'setge', 'setl', 'setle', | |
| 290 'setna', 'setnae', 'setnb', 'setnbe', 'setnc', 'setne', 'setng', | |
| 291 'setnge', 'setnl', 'setnle', 'setno', 'setnp', 'setns', 'setnz', | |
| 292 'seto', 'setp', 'setpe', 'setpo', 'sets', 'setz', 'sgdt', 'shl', | |
| 293 'shld', 'shr', 'shrd', 'sidt', 'sldt', 'smi', 'smint', 'smintold', | |
| 294 'smsw', 'stc', 'std', 'sti', 'stosb', 'stosd', 'stosw', 'str', | |
| 295 'sub', 'svdc', 'svldt', 'svts', 'syscall', 'sysenter', 'sysexit', | |
| 296 'sysret', 'test', 'ud1', 'ud2', 'umov', 'verr', 'verw', 'wait', | |
| 297 'wbinvd', 'wrmsr', 'wrshr', 'xadd', 'xbts', 'xchg', 'xlat', | |
| 298 'xlatb', 'xor' | |
| 299 )) | |
| 300 | |
| 301 def __init__(self, **options): | |
| 302 Lexer.__init__(self, **options) | |
| 303 self.keywords = set() | |
| 304 if get_bool_opt(options, 'turbopascal', True): | |
| 305 self.keywords.update(self.TURBO_PASCAL_KEYWORDS) | |
| 306 if get_bool_opt(options, 'delphi', True): | |
| 307 self.keywords.update(self.DELPHI_KEYWORDS) | |
| 308 if get_bool_opt(options, 'freepascal', True): | |
| 309 self.keywords.update(self.FREE_PASCAL_KEYWORDS) | |
| 310 self.builtins = set() | |
| 311 for unit in get_list_opt(options, 'units', list(self.BUILTIN_UNITS)): | |
| 312 self.builtins.update(self.BUILTIN_UNITS[unit]) | |
| 313 | |
| 314 def get_tokens_unprocessed(self, text): | |
| 315 scanner = Scanner(text, re.DOTALL | re.MULTILINE | re.IGNORECASE) | |
| 316 stack = ['initial'] | |
| 317 in_function_block = False | |
| 318 in_property_block = False | |
| 319 was_dot = False | |
| 320 next_token_is_function = False | |
| 321 next_token_is_property = False | |
| 322 collect_labels = False | |
| 323 block_labels = set() | |
| 324 brace_balance = [0, 0] | |
| 325 | |
| 326 while not scanner.eos: | |
| 327 token = Error | |
| 328 | |
| 329 if stack[-1] == 'initial': | |
| 330 if scanner.scan(r'\s+'): | |
| 331 token = Text | |
| 332 elif scanner.scan(r'\{.*?\}|\(\*.*?\*\)'): | |
| 333 if scanner.match.startswith('$'): | |
| 334 token = Comment.Preproc | |
| 335 else: | |
| 336 token = Comment.Multiline | |
| 337 elif scanner.scan(r'//.*?$'): | |
| 338 token = Comment.Single | |
| 339 elif scanner.scan(r'[-+*\/=<>:;,.@\^]'): | |
| 340 token = Operator | |
| 341 # stop label highlighting on next ";" | |
| 342 if collect_labels and scanner.match == ';': | |
| 343 collect_labels = False | |
| 344 elif scanner.scan(r'[\(\)\[\]]+'): | |
| 345 token = Punctuation | |
| 346 # abort function naming ``foo = Function(...)`` | |
| 347 next_token_is_function = False | |
| 348 # if we are in a function block we count the open | |
| 349 # braces because ootherwise it's impossible to | |
| 350 # determine the end of the modifier context | |
| 351 if in_function_block or in_property_block: | |
| 352 if scanner.match == '(': | |
| 353 brace_balance[0] += 1 | |
| 354 elif scanner.match == ')': | |
| 355 brace_balance[0] -= 1 | |
| 356 elif scanner.match == '[': | |
| 357 brace_balance[1] += 1 | |
| 358 elif scanner.match == ']': | |
| 359 brace_balance[1] -= 1 | |
| 360 elif scanner.scan(r'[A-Za-z_][A-Za-z_0-9]*'): | |
| 361 lowercase_name = scanner.match.lower() | |
| 362 if lowercase_name == 'result': | |
| 363 token = Name.Builtin.Pseudo | |
| 364 elif lowercase_name in self.keywords: | |
| 365 token = Keyword | |
| 366 # if we are in a special block and a | |
| 367 # block ending keyword occours (and the parenthesis | |
| 368 # is balanced) we end the current block context | |
| 369 if (in_function_block or in_property_block) and \ | |
| 370 lowercase_name in self.BLOCK_KEYWORDS and \ | |
| 371 brace_balance[0] <= 0 and \ | |
| 372 brace_balance[1] <= 0: | |
| 373 in_function_block = False | |
| 374 in_property_block = False | |
| 375 brace_balance = [0, 0] | |
| 376 block_labels = set() | |
| 377 if lowercase_name in ('label', 'goto'): | |
| 378 collect_labels = True | |
| 379 elif lowercase_name == 'asm': | |
| 380 stack.append('asm') | |
| 381 elif lowercase_name == 'property': | |
| 382 in_property_block = True | |
| 383 next_token_is_property = True | |
| 384 elif lowercase_name in ('procedure', 'operator', | |
| 385 'function', 'constructor', | |
| 386 'destructor'): | |
| 387 in_function_block = True | |
| 388 next_token_is_function = True | |
| 389 # we are in a function block and the current name | |
| 390 # is in the set of registered modifiers. highlight | |
| 391 # it as pseudo keyword | |
| 392 elif in_function_block and \ | |
| 393 lowercase_name in self.FUNCTION_MODIFIERS: | |
| 394 token = Keyword.Pseudo | |
| 395 # if we are in a property highlight some more | |
| 396 # modifiers | |
| 397 elif in_property_block and \ | |
| 398 lowercase_name in ('read', 'write'): | |
| 399 token = Keyword.Pseudo | |
| 400 next_token_is_function = True | |
| 401 # if the last iteration set next_token_is_function | |
| 402 # to true we now want this name highlighted as | |
| 403 # function. so do that and reset the state | |
| 404 elif next_token_is_function: | |
| 405 # Look if the next token is a dot. If yes it's | |
| 406 # not a function, but a class name and the | |
| 407 # part after the dot a function name | |
| 408 if scanner.test(r'\s*\.\s*'): | |
| 409 token = Name.Class | |
| 410 # it's not a dot, our job is done | |
| 411 else: | |
| 412 token = Name.Function | |
| 413 next_token_is_function = False | |
| 414 # same for properties | |
| 415 elif next_token_is_property: | |
| 416 token = Name.Property | |
| 417 next_token_is_property = False | |
| 418 # Highlight this token as label and add it | |
| 419 # to the list of known labels | |
| 420 elif collect_labels: | |
| 421 token = Name.Label | |
| 422 block_labels.add(scanner.match.lower()) | |
| 423 # name is in list of known labels | |
| 424 elif lowercase_name in block_labels: | |
| 425 token = Name.Label | |
| 426 elif lowercase_name in self.BUILTIN_TYPES: | |
| 427 token = Keyword.Type | |
| 428 elif lowercase_name in self.DIRECTIVES: | |
| 429 token = Keyword.Pseudo | |
| 430 # builtins are just builtins if the token | |
| 431 # before isn't a dot | |
| 432 elif not was_dot and lowercase_name in self.builtins: | |
| 433 token = Name.Builtin | |
| 434 else: | |
| 435 token = Name | |
| 436 elif scanner.scan(r"'"): | |
| 437 token = String | |
| 438 stack.append('string') | |
| 439 elif scanner.scan(r'\#(\d+|\$[0-9A-Fa-f]+)'): | |
| 440 token = String.Char | |
| 441 elif scanner.scan(r'\$[0-9A-Fa-f]+'): | |
| 442 token = Number.Hex | |
| 443 elif scanner.scan(r'\d+(?![eE]|\.[^.])'): | |
| 444 token = Number.Integer | |
| 445 elif scanner.scan(r'\d+(\.\d+([eE][+-]?\d+)?|[eE][+-]?\d+)'): | |
| 446 token = Number.Float | |
| 447 else: | |
| 448 # if the stack depth is deeper than once, pop | |
| 449 if len(stack) > 1: | |
| 450 stack.pop() | |
| 451 scanner.get_char() | |
| 452 | |
| 453 elif stack[-1] == 'string': | |
| 454 if scanner.scan(r"''"): | |
| 455 token = String.Escape | |
| 456 elif scanner.scan(r"'"): | |
| 457 token = String | |
| 458 stack.pop() | |
| 459 elif scanner.scan(r"[^']*"): | |
| 460 token = String | |
| 461 else: | |
| 462 scanner.get_char() | |
| 463 stack.pop() | |
| 464 | |
| 465 elif stack[-1] == 'asm': | |
| 466 if scanner.scan(r'\s+'): | |
| 467 token = Text | |
| 468 elif scanner.scan(r'end'): | |
| 469 token = Keyword | |
| 470 stack.pop() | |
| 471 elif scanner.scan(r'\{.*?\}|\(\*.*?\*\)'): | |
| 472 if scanner.match.startswith('$'): | |
| 473 token = Comment.Preproc | |
| 474 else: | |
| 475 token = Comment.Multiline | |
| 476 elif scanner.scan(r'//.*?$'): | |
| 477 token = Comment.Single | |
| 478 elif scanner.scan(r"'"): | |
| 479 token = String | |
| 480 stack.append('string') | |
| 481 elif scanner.scan(r'@@[A-Za-z_][A-Za-z_0-9]*'): | |
| 482 token = Name.Label | |
| 483 elif scanner.scan(r'[A-Za-z_][A-Za-z_0-9]*'): | |
| 484 lowercase_name = scanner.match.lower() | |
| 485 if lowercase_name in self.ASM_INSTRUCTIONS: | |
| 486 token = Keyword | |
| 487 elif lowercase_name in self.ASM_REGISTERS: | |
| 488 token = Name.Builtin | |
| 489 else: | |
| 490 token = Name | |
| 491 elif scanner.scan(r'[-+*\/=<>:;,.@\^]+'): | |
| 492 token = Operator | |
| 493 elif scanner.scan(r'[\(\)\[\]]+'): | |
| 494 token = Punctuation | |
| 495 elif scanner.scan(r'\$[0-9A-Fa-f]+'): | |
| 496 token = Number.Hex | |
| 497 elif scanner.scan(r'\d+(?![eE]|\.[^.])'): | |
| 498 token = Number.Integer | |
| 499 elif scanner.scan(r'\d+(\.\d+([eE][+-]?\d+)?|[eE][+-]?\d+)'): | |
| 500 token = Number.Float | |
| 501 else: | |
| 502 scanner.get_char() | |
| 503 stack.pop() | |
| 504 | |
| 505 # save the dot!!!11 | |
| 506 if scanner.match.strip(): | |
| 507 was_dot = scanner.match == '.' | |
| 508 yield scanner.start_pos, token, scanner.match or '' | |
| 509 | |
| 510 | |
| 511 class AdaLexer(RegexLexer): | |
| 512 """ | |
| 513 For Ada source code. | |
| 514 | |
| 515 .. versionadded:: 1.3 | |
| 516 """ | |
| 517 | |
| 518 name = 'Ada' | |
| 519 aliases = ['ada', 'ada95', 'ada2005'] | |
| 520 filenames = ['*.adb', '*.ads', '*.ada'] | |
| 521 mimetypes = ['text/x-ada'] | |
| 522 | |
| 523 flags = re.MULTILINE | re.IGNORECASE | |
| 524 | |
| 525 tokens = { | |
| 526 'root': [ | |
| 527 (r'[^\S\n]+', Text), | |
| 528 (r'--.*?\n', Comment.Single), | |
| 529 (r'[^\S\n]+', Text), | |
| 530 (r'function|procedure|entry', Keyword.Declaration, 'subprogram'), | |
| 531 (r'(subtype|type)(\s+)(\w+)', | |
| 532 bygroups(Keyword.Declaration, Text, Keyword.Type), 'type_def'), | |
| 533 (r'task|protected', Keyword.Declaration), | |
| 534 (r'(subtype)(\s+)', bygroups(Keyword.Declaration, Text)), | |
| 535 (r'(end)(\s+)', bygroups(Keyword.Reserved, Text), 'end'), | |
| 536 (r'(pragma)(\s+)(\w+)', bygroups(Keyword.Reserved, Text, | |
| 537 Comment.Preproc)), | |
| 538 (r'(true|false|null)\b', Keyword.Constant), | |
| 539 (words(( | |
| 540 'Address', 'Byte', 'Boolean', 'Character', 'Controlled', 'Count', | |
| 541 'Cursor', 'Duration', 'File_Mode', 'File_Type', 'Float', 'Generator', | |
| 542 'Integer', 'Long_Float', 'Long_Integer', 'Long_Long_Float', | |
| 543 'Long_Long_Integer', 'Natural', 'Positive', 'Reference_Type', | |
| 544 'Short_Float', 'Short_Integer', 'Short_Short_Float', | |
| 545 'Short_Short_Integer', 'String', 'Wide_Character', 'Wide_String'), | |
| 546 suffix=r'\b'), | |
| 547 Keyword.Type), | |
| 548 (r'(and(\s+then)?|in|mod|not|or(\s+else)|rem)\b', Operator.Word), | |
| 549 (r'generic|private', Keyword.Declaration), | |
| 550 (r'package', Keyword.Declaration, 'package'), | |
| 551 (r'array\b', Keyword.Reserved, 'array_def'), | |
| 552 (r'(with|use)(\s+)', bygroups(Keyword.Namespace, Text), 'import'), | |
| 553 (r'(\w+)(\s*)(:)(\s*)(constant)', | |
| 554 bygroups(Name.Constant, Text, Punctuation, Text, | |
| 555 Keyword.Reserved)), | |
| 556 (r'<<\w+>>', Name.Label), | |
| 557 (r'(\w+)(\s*)(:)(\s*)(declare|begin|loop|for|while)', | |
| 558 bygroups(Name.Label, Text, Punctuation, Text, Keyword.Reserved)), | |
| 559 (words(( | |
| 560 'abort', 'abs', 'abstract', 'accept', 'access', 'aliased', 'all', | |
| 561 'array', 'at', 'begin', 'body', 'case', 'constant', 'declare', | |
| 562 'delay', 'delta', 'digits', 'do', 'else', 'elsif', 'end', 'entry', | |
| 563 'exception', 'exit', 'interface', 'for', 'goto', 'if', 'is', 'limited', | |
| 564 'loop', 'new', 'null', 'of', 'or', 'others', 'out', 'overriding', | |
| 565 'pragma', 'protected', 'raise', 'range', 'record', 'renames', 'requeue', | |
| 566 'return', 'reverse', 'select', 'separate', 'subtype', 'synchronized', | |
| 567 'task', 'tagged', 'terminate', 'then', 'type', 'until', 'when', | |
| 568 'while', 'xor'), prefix=r'\b', suffix=r'\b'), | |
| 569 Keyword.Reserved), | |
| 570 (r'"[^"]*"', String), | |
| 571 include('attribute'), | |
| 572 include('numbers'), | |
| 573 (r"'[^']'", String.Character), | |
| 574 (r'(\w+)(\s*|[(,])', bygroups(Name, using(this))), | |
| 575 (r"(<>|=>|:=|[()|:;,.'])", Punctuation), | |
| 576 (r'[*<>+=/&-]', Operator), | |
| 577 (r'\n+', Text), | |
| 578 ], | |
| 579 'numbers': [ | |
| 580 (r'[0-9_]+#[0-9a-f]+#', Number.Hex), | |
| 581 (r'[0-9_]+\.[0-9_]*', Number.Float), | |
| 582 (r'[0-9_]+', Number.Integer), | |
| 583 ], | |
| 584 'attribute': [ | |
| 585 (r"(')(\w+)", bygroups(Punctuation, Name.Attribute)), | |
| 586 ], | |
| 587 'subprogram': [ | |
| 588 (r'\(', Punctuation, ('#pop', 'formal_part')), | |
| 589 (r';', Punctuation, '#pop'), | |
| 590 (r'is\b', Keyword.Reserved, '#pop'), | |
| 591 (r'"[^"]+"|\w+', Name.Function), | |
| 592 include('root'), | |
| 593 ], | |
| 594 'end': [ | |
| 595 ('(if|case|record|loop|select)', Keyword.Reserved), | |
| 596 (r'"[^"]+"|[\w.]+', Name.Function), | |
| 597 (r'\s+', Text), | |
| 598 (';', Punctuation, '#pop'), | |
| 599 ], | |
| 600 'type_def': [ | |
| 601 (r';', Punctuation, '#pop'), | |
| 602 (r'\(', Punctuation, 'formal_part'), | |
| 603 (r'with|and|use', Keyword.Reserved), | |
| 604 (r'array\b', Keyword.Reserved, ('#pop', 'array_def')), | |
| 605 (r'record\b', Keyword.Reserved, ('record_def')), | |
| 606 (r'(null record)(;)', bygroups(Keyword.Reserved, Punctuation), '#pop'), | |
| 607 include('root'), | |
| 608 ], | |
| 609 'array_def': [ | |
| 610 (r';', Punctuation, '#pop'), | |
| 611 (r'(\w+)(\s+)(range)', bygroups(Keyword.Type, Text, Keyword.Reserved)), | |
| 612 include('root'), | |
| 613 ], | |
| 614 'record_def': [ | |
| 615 (r'end record', Keyword.Reserved, '#pop'), | |
| 616 include('root'), | |
| 617 ], | |
| 618 'import': [ | |
| 619 (r'[\w.]+', Name.Namespace, '#pop'), | |
| 620 default('#pop'), | |
| 621 ], | |
| 622 'formal_part': [ | |
| 623 (r'\)', Punctuation, '#pop'), | |
| 624 (r'\w+', Name.Variable), | |
| 625 (r',|:[^=]', Punctuation), | |
| 626 (r'(in|not|null|out|access)\b', Keyword.Reserved), | |
| 627 include('root'), | |
| 628 ], | |
| 629 'package': [ | |
| 630 ('body', Keyword.Declaration), | |
| 631 (r'is\s+new|renames', Keyword.Reserved), | |
| 632 ('is', Keyword.Reserved, '#pop'), | |
| 633 (';', Punctuation, '#pop'), | |
| 634 (r'\(', Punctuation, 'package_instantiation'), | |
| 635 (r'([\w.]+)', Name.Class), | |
| 636 include('root'), | |
| 637 ], | |
| 638 'package_instantiation': [ | |
| 639 (r'("[^"]+"|\w+)(\s+)(=>)', bygroups(Name.Variable, Text, Punctuation)), | |
| 640 (r'[\w.\'"]', Text), | |
| 641 (r'\)', Punctuation, '#pop'), | |
| 642 include('root'), | |
| 643 ], | |
| 644 } |
