Mercurial Repositories > eric / file comparison
comparison: eric6/ThirdParty/Pygments/pygments/lexers/asm.py
eric6/ThirdParty/Pygments/pygments/lexers/asm.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.asm | |
| 4 ~~~~~~~~~~~~~~~~~~~ | |
| 5 | |
| 6 Lexers for assembly 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 RegexLexer, include, bygroups, using, words, \ | |
| 15 DelegatingLexer | |
| 16 from pygments.lexers.c_cpp import CppLexer, CLexer | |
| 17 from pygments.lexers.d import DLexer | |
| 18 from pygments.token import Text, Name, Number, String, Comment, Punctuation, \ | |
| 19 Other, Keyword, Operator | |
| 20 | |
| 21 __all__ = ['GasLexer', 'ObjdumpLexer', 'DObjdumpLexer', 'CppObjdumpLexer', | |
| 22 'CObjdumpLexer', 'HsailLexer', 'LlvmLexer', 'NasmLexer', | |
| 23 'NasmObjdumpLexer', 'TasmLexer', 'Ca65Lexer'] | |
| 24 | |
| 25 | |
| 26 class GasLexer(RegexLexer): | |
| 27 """ | |
| 28 For Gas (AT&T) assembly code. | |
| 29 """ | |
| 30 name = 'GAS' | |
| 31 aliases = ['gas', 'asm'] | |
| 32 filenames = ['*.s', '*.S'] | |
| 33 mimetypes = ['text/x-gas'] | |
| 34 | |
| 35 #: optional Comment or Whitespace | |
| 36 string = r'"(\\"|[^"])*"' | |
| 37 char = r'[\w$.@-]' | |
| 38 identifier = r'(?:[a-zA-Z$_]' + char + r'*|\.' + char + '+)' | |
| 39 number = r'(?:0[xX][a-zA-Z0-9]+|\d+)' | |
| 40 | |
| 41 tokens = { | |
| 42 'root': [ | |
| 43 include('whitespace'), | |
| 44 (identifier + ':', Name.Label), | |
| 45 (r'\.' + identifier, Name.Attribute, 'directive-args'), | |
| 46 (r'lock|rep(n?z)?|data\d+', Name.Attribute), | |
| 47 (identifier, Name.Function, 'instruction-args'), | |
| 48 (r'[\r\n]+', Text) | |
| 49 ], | |
| 50 'directive-args': [ | |
| 51 (identifier, Name.Constant), | |
| 52 (string, String), | |
| 53 ('@' + identifier, Name.Attribute), | |
| 54 (number, Number.Integer), | |
| 55 (r'[\r\n]+', Text, '#pop'), | |
| 56 (r'[;#].*?\n', Comment, '#pop'), | |
| 57 | |
| 58 include('punctuation'), | |
| 59 include('whitespace') | |
| 60 ], | |
| 61 'instruction-args': [ | |
| 62 # For objdump-disassembled code, shouldn't occur in | |
| 63 # actual assembler input | |
| 64 ('([a-z0-9]+)( )(<)('+identifier+')(>)', | |
| 65 bygroups(Number.Hex, Text, Punctuation, Name.Constant, | |
| 66 Punctuation)), | |
| 67 ('([a-z0-9]+)( )(<)('+identifier+')([-+])('+number+')(>)', | |
| 68 bygroups(Number.Hex, Text, Punctuation, Name.Constant, | |
| 69 Punctuation, Number.Integer, Punctuation)), | |
| 70 | |
| 71 # Address constants | |
| 72 (identifier, Name.Constant), | |
| 73 (number, Number.Integer), | |
| 74 # Registers | |
| 75 ('%' + identifier, Name.Variable), | |
| 76 # Numeric constants | |
| 77 ('$'+number, Number.Integer), | |
| 78 (r"$'(.|\\')'", String.Char), | |
| 79 (r'[\r\n]+', Text, '#pop'), | |
| 80 (r'[;#].*?\n', Comment, '#pop'), | |
| 81 | |
| 82 include('punctuation'), | |
| 83 include('whitespace') | |
| 84 ], | |
| 85 'whitespace': [ | |
| 86 (r'\n', Text), | |
| 87 (r'\s+', Text), | |
| 88 (r'[;#].*?\n', Comment) | |
| 89 ], | |
| 90 'punctuation': [ | |
| 91 (r'[-*,.()\[\]!:]+', Punctuation) | |
| 92 ] | |
| 93 } | |
| 94 | |
| 95 def analyse_text(text): | |
| 96 if re.match(r'^\.(text|data|section)', text, re.M): | |
| 97 return True | |
| 98 elif re.match(r'^\.\w+', text, re.M): | |
| 99 return 0.1 | |
| 100 | |
| 101 | |
| 102 def _objdump_lexer_tokens(asm_lexer): | |
| 103 """ | |
| 104 Common objdump lexer tokens to wrap an ASM lexer. | |
| 105 """ | |
| 106 hex_re = r'[0-9A-Za-z]' | |
| 107 return { | |
| 108 'root': [ | |
| 109 # File name & format: | |
| 110 ('(.*?)(:)( +file format )(.*?)$', | |
| 111 bygroups(Name.Label, Punctuation, Text, String)), | |
| 112 # Section header | |
| 113 ('(Disassembly of section )(.*?)(:)$', | |
| 114 bygroups(Text, Name.Label, Punctuation)), | |
| 115 # Function labels | |
| 116 # (With offset) | |
| 117 ('('+hex_re+'+)( )(<)(.*?)([-+])(0[xX][A-Za-z0-9]+)(>:)$', | |
| 118 bygroups(Number.Hex, Text, Punctuation, Name.Function, | |
| 119 Punctuation, Number.Hex, Punctuation)), | |
| 120 # (Without offset) | |
| 121 ('('+hex_re+'+)( )(<)(.*?)(>:)$', | |
| 122 bygroups(Number.Hex, Text, Punctuation, Name.Function, | |
| 123 Punctuation)), | |
| 124 # Code line with disassembled instructions | |
| 125 ('( *)('+hex_re+r'+:)(\t)((?:'+hex_re+hex_re+' )+)( *\t)([a-zA-Z].*?)$', | |
| 126 bygroups(Text, Name.Label, Text, Number.Hex, Text, | |
| 127 using(asm_lexer))), | |
| 128 # Code line with ascii | |
| 129 ('( *)('+hex_re+r'+:)(\t)((?:'+hex_re+hex_re+' )+)( *)(.*?)$', | |
| 130 bygroups(Text, Name.Label, Text, Number.Hex, Text, String)), | |
| 131 # Continued code line, only raw opcodes without disassembled | |
| 132 # instruction | |
| 133 ('( *)('+hex_re+r'+:)(\t)((?:'+hex_re+hex_re+' )+)$', | |
| 134 bygroups(Text, Name.Label, Text, Number.Hex)), | |
| 135 # Skipped a few bytes | |
| 136 (r'\t\.\.\.$', Text), | |
| 137 # Relocation line | |
| 138 # (With offset) | |
| 139 (r'(\t\t\t)('+hex_re+r'+:)( )([^\t]+)(\t)(.*?)([-+])(0x'+hex_re+'+)$', | |
| 140 bygroups(Text, Name.Label, Text, Name.Property, Text, | |
| 141 Name.Constant, Punctuation, Number.Hex)), | |
| 142 # (Without offset) | |
| 143 (r'(\t\t\t)('+hex_re+r'+:)( )([^\t]+)(\t)(.*?)$', | |
| 144 bygroups(Text, Name.Label, Text, Name.Property, Text, | |
| 145 Name.Constant)), | |
| 146 (r'[^\n]+\n', Other) | |
| 147 ] | |
| 148 } | |
| 149 | |
| 150 | |
| 151 class ObjdumpLexer(RegexLexer): | |
| 152 """ | |
| 153 For the output of 'objdump -dr' | |
| 154 """ | |
| 155 name = 'objdump' | |
| 156 aliases = ['objdump'] | |
| 157 filenames = ['*.objdump'] | |
| 158 mimetypes = ['text/x-objdump'] | |
| 159 | |
| 160 tokens = _objdump_lexer_tokens(GasLexer) | |
| 161 | |
| 162 | |
| 163 class DObjdumpLexer(DelegatingLexer): | |
| 164 """ | |
| 165 For the output of 'objdump -Sr on compiled D files' | |
| 166 """ | |
| 167 name = 'd-objdump' | |
| 168 aliases = ['d-objdump'] | |
| 169 filenames = ['*.d-objdump'] | |
| 170 mimetypes = ['text/x-d-objdump'] | |
| 171 | |
| 172 def __init__(self, **options): | |
| 173 super(DObjdumpLexer, self).__init__(DLexer, ObjdumpLexer, **options) | |
| 174 | |
| 175 | |
| 176 class CppObjdumpLexer(DelegatingLexer): | |
| 177 """ | |
| 178 For the output of 'objdump -Sr on compiled C++ files' | |
| 179 """ | |
| 180 name = 'cpp-objdump' | |
| 181 aliases = ['cpp-objdump', 'c++-objdumb', 'cxx-objdump'] | |
| 182 filenames = ['*.cpp-objdump', '*.c++-objdump', '*.cxx-objdump'] | |
| 183 mimetypes = ['text/x-cpp-objdump'] | |
| 184 | |
| 185 def __init__(self, **options): | |
| 186 super(CppObjdumpLexer, self).__init__(CppLexer, ObjdumpLexer, **options) | |
| 187 | |
| 188 | |
| 189 class CObjdumpLexer(DelegatingLexer): | |
| 190 """ | |
| 191 For the output of 'objdump -Sr on compiled C files' | |
| 192 """ | |
| 193 name = 'c-objdump' | |
| 194 aliases = ['c-objdump'] | |
| 195 filenames = ['*.c-objdump'] | |
| 196 mimetypes = ['text/x-c-objdump'] | |
| 197 | |
| 198 def __init__(self, **options): | |
| 199 super(CObjdumpLexer, self).__init__(CLexer, ObjdumpLexer, **options) | |
| 200 | |
| 201 | |
| 202 class HsailLexer(RegexLexer): | |
| 203 """ | |
| 204 For HSAIL assembly code. | |
| 205 | |
| 206 .. versionadded:: 2.2 | |
| 207 """ | |
| 208 name = 'HSAIL' | |
| 209 aliases = ['hsail', 'hsa'] | |
| 210 filenames = ['*.hsail'] | |
| 211 mimetypes = ['text/x-hsail'] | |
| 212 | |
| 213 string = r'"[^"]*?"' | |
| 214 identifier = r'[a-zA-Z_][\w.]*' | |
| 215 # Registers | |
| 216 register_number = r'[0-9]+' | |
| 217 register = r'(\$(c|s|d|q)' + register_number + ')' | |
| 218 # Qualifiers | |
| 219 alignQual = r'(align\(\d+\))' | |
| 220 widthQual = r'(width\((\d+|all)\))' | |
| 221 allocQual = r'(alloc\(agent\))' | |
| 222 # Instruction Modifiers | |
| 223 roundingMod = (r'((_ftz)?(_up|_down|_zero|_near))') | |
| 224 datatypeMod = (r'_(' | |
| 225 # packedTypes | |
| 226 r'u8x4|s8x4|u16x2|s16x2|u8x8|s8x8|u16x4|s16x4|u32x2|s32x2|' | |
| 227 r'u8x16|s8x16|u16x8|s16x8|u32x4|s32x4|u64x2|s64x2|' | |
| 228 r'f16x2|f16x4|f16x8|f32x2|f32x4|f64x2|' | |
| 229 # baseTypes | |
| 230 r'u8|s8|u16|s16|u32|s32|u64|s64|' | |
| 231 r'b128|b8|b16|b32|b64|b1|' | |
| 232 r'f16|f32|f64|' | |
| 233 # opaqueType | |
| 234 r'roimg|woimg|rwimg|samp|sig32|sig64)') | |
| 235 | |
| 236 # Numeric Constant | |
| 237 float = r'((\d+\.)|(\d*\.\d+))[eE][+-]?\d+' | |
| 238 hexfloat = r'0[xX](([0-9a-fA-F]+\.[0-9a-fA-F]*)|([0-9a-fA-F]*\.[0-9a-fA-F]+))[pP][+-]?\d+' | |
| 239 ieeefloat = r'0((h|H)[0-9a-fA-F]{4}|(f|F)[0-9a-fA-F]{8}|(d|D)[0-9a-fA-F]{16})' | |
| 240 | |
| 241 tokens = { | |
| 242 'root': [ | |
| 243 include('whitespace'), | |
| 244 include('comments'), | |
| 245 | |
| 246 (string, String), | |
| 247 | |
| 248 (r'@' + identifier + ':?', Name.Label), | |
| 249 | |
| 250 (register, Name.Variable.Anonymous), | |
| 251 | |
| 252 include('keyword'), | |
| 253 | |
| 254 (r'&' + identifier, Name.Variable.Global), | |
| 255 (r'%' + identifier, Name.Variable), | |
| 256 | |
| 257 (hexfloat, Number.Hex), | |
| 258 (r'0[xX][a-fA-F0-9]+', Number.Hex), | |
| 259 (ieeefloat, Number.Float), | |
| 260 (float, Number.Float), | |
| 261 (r'\d+', Number.Integer), | |
| 262 | |
| 263 (r'[=<>{}\[\]()*.,:;!]|x\b', Punctuation) | |
| 264 ], | |
| 265 'whitespace': [ | |
| 266 (r'(\n|\s)+', Text), | |
| 267 ], | |
| 268 'comments': [ | |
| 269 (r'/\*.*?\*/', Comment.Multiline), | |
| 270 (r'//.*?\n', Comment.Single), | |
| 271 ], | |
| 272 'keyword': [ | |
| 273 # Types | |
| 274 (r'kernarg' + datatypeMod, Keyword.Type), | |
| 275 | |
| 276 # Regular keywords | |
| 277 (r'\$(full|base|small|large|default|zero|near)', Keyword), | |
| 278 (words(( | |
| 279 'module', 'extension', 'pragma', 'prog', 'indirect', 'signature', | |
| 280 'decl', 'kernel', 'function', 'enablebreakexceptions', | |
| 281 'enabledetectexceptions', 'maxdynamicgroupsize', 'maxflatgridsize', | |
| 282 'maxflatworkgroupsize', 'requireddim', 'requiredgridsize', | |
| 283 'requiredworkgroupsize', 'requirenopartialworkgroups'), | |
| 284 suffix=r'\b'), Keyword), | |
| 285 | |
| 286 # instructions | |
| 287 (roundingMod, Keyword), | |
| 288 (datatypeMod, Keyword), | |
| 289 (r'_(' + alignQual + '|' + widthQual + ')', Keyword), | |
| 290 (r'_kernarg', Keyword), | |
| 291 (r'(nop|imagefence)\b', Keyword), | |
| 292 (words(( | |
| 293 'cleardetectexcept', 'clock', 'cuid', 'debugtrap', 'dim', | |
| 294 'getdetectexcept', 'groupbaseptr', 'kernargbaseptr', 'laneid', | |
| 295 'maxcuid', 'maxwaveid', 'packetid', 'setdetectexcept', 'waveid', | |
| 296 'workitemflatabsid', 'workitemflatid', 'nullptr', 'abs', 'bitrev', | |
| 297 'currentworkgroupsize', 'currentworkitemflatid', 'fract', 'ncos', | |
| 298 'neg', 'nexp2', 'nlog2', 'nrcp', 'nrsqrt', 'nsin', 'nsqrt', | |
| 299 'gridgroups', 'gridsize', 'not', 'sqrt', 'workgroupid', | |
| 300 'workgroupsize', 'workitemabsid', 'workitemid', 'ceil', 'floor', | |
| 301 'rint', 'trunc', 'add', 'bitmask', 'borrow', 'carry', 'copysign', | |
| 302 'div', 'rem', 'sub', 'shl', 'shr', 'and', 'or', 'xor', 'unpackhi', | |
| 303 'unpacklo', 'max', 'min', 'fma', 'mad', 'bitextract', 'bitselect', | |
| 304 'shuffle', 'cmov', 'bitalign', 'bytealign', 'lerp', 'nfma', 'mul', | |
| 305 'mulhi', 'mul24hi', 'mul24', 'mad24', 'mad24hi', 'bitinsert', | |
| 306 'combine', 'expand', 'lda', 'mov', 'pack', 'unpack', 'packcvt', | |
| 307 'unpackcvt', 'sad', 'sementp', 'ftos', 'stof', 'cmp', 'ld', 'st', | |
| 308 '_eq', '_ne', '_lt', '_le', '_gt', '_ge', '_equ', '_neu', '_ltu', | |
| 309 '_leu', '_gtu', '_geu', '_num', '_nan', '_seq', '_sne', '_slt', | |
| 310 '_sle', '_sgt', '_sge', '_snum', '_snan', '_sequ', '_sneu', '_sltu', | |
| 311 '_sleu', '_sgtu', '_sgeu', 'atomic', '_ld', '_st', '_cas', '_add', | |
| 312 '_and', '_exch', '_max', '_min', '_or', '_sub', '_wrapdec', | |
| 313 '_wrapinc', '_xor', 'ret', 'cvt', '_readonly', '_kernarg', '_global', | |
| 314 'br', 'cbr', 'sbr', '_scacq', '_screl', '_scar', '_rlx', '_wave', | |
| 315 '_wg', '_agent', '_system', 'ldimage', 'stimage', '_v2', '_v3', '_v4', | |
| 316 '_1d', '_2d', '_3d', '_1da', '_2da', '_1db', '_2ddepth', '_2dadepth', | |
| 317 '_width', '_height', '_depth', '_array', '_channelorder', | |
| 318 '_channeltype', 'querysampler', '_coord', '_filter', '_addressing', | |
| 319 'barrier', 'wavebarrier', 'initfbar', 'joinfbar', 'waitfbar', | |
| 320 'arrivefbar', 'leavefbar', 'releasefbar', 'ldf', 'activelaneid', | |
| 321 'activelanecount', 'activelanemask', 'activelanepermute', 'call', | |
| 322 'scall', 'icall', 'alloca', 'packetcompletionsig', | |
| 323 'addqueuewriteindex', 'casqueuewriteindex', 'ldqueuereadindex', | |
| 324 'stqueuereadindex', 'readonly', 'global', 'private', 'group', | |
| 325 'spill', 'arg', '_upi', '_downi', '_zeroi', '_neari', '_upi_sat', | |
| 326 '_downi_sat', '_zeroi_sat', '_neari_sat', '_supi', '_sdowni', | |
| 327 '_szeroi', '_sneari', '_supi_sat', '_sdowni_sat', '_szeroi_sat', | |
| 328 '_sneari_sat', '_pp', '_ps', '_sp', '_ss', '_s', '_p', '_pp_sat', | |
| 329 '_ps_sat', '_sp_sat', '_ss_sat', '_s_sat', '_p_sat')), Keyword), | |
| 330 | |
| 331 # Integer types | |
| 332 (r'i[1-9]\d*', Keyword) | |
| 333 ] | |
| 334 } | |
| 335 | |
| 336 | |
| 337 class LlvmLexer(RegexLexer): | |
| 338 """ | |
| 339 For LLVM assembly code. | |
| 340 """ | |
| 341 name = 'LLVM' | |
| 342 aliases = ['llvm'] | |
| 343 filenames = ['*.ll'] | |
| 344 mimetypes = ['text/x-llvm'] | |
| 345 | |
| 346 #: optional Comment or Whitespace | |
| 347 string = r'"[^"]*?"' | |
| 348 identifier = r'([-a-zA-Z$._][\w\-$.]*|' + string + ')' | |
| 349 | |
| 350 tokens = { | |
| 351 'root': [ | |
| 352 include('whitespace'), | |
| 353 | |
| 354 # Before keywords, because keywords are valid label names :(... | |
| 355 (identifier + r'\s*:', Name.Label), | |
| 356 | |
| 357 include('keyword'), | |
| 358 | |
| 359 (r'%' + identifier, Name.Variable), | |
| 360 (r'@' + identifier, Name.Variable.Global), | |
| 361 (r'%\d+', Name.Variable.Anonymous), | |
| 362 (r'@\d+', Name.Variable.Global), | |
| 363 (r'#\d+', Name.Variable.Global), | |
| 364 (r'!' + identifier, Name.Variable), | |
| 365 (r'!\d+', Name.Variable.Anonymous), | |
| 366 (r'c?' + string, String), | |
| 367 | |
| 368 (r'0[xX][a-fA-F0-9]+', Number), | |
| 369 (r'-?\d+(?:[.]\d+)?(?:[eE][-+]?\d+(?:[.]\d+)?)?', Number), | |
| 370 | |
| 371 (r'[=<>{}\[\]()*.,!]|x\b', Punctuation) | |
| 372 ], | |
| 373 'whitespace': [ | |
| 374 (r'(\n|\s)+', Text), | |
| 375 (r';.*?\n', Comment) | |
| 376 ], | |
| 377 'keyword': [ | |
| 378 # Regular keywords | |
| 379 (words(( | |
| 380 'begin', 'end', 'true', 'false', 'declare', 'define', 'global', | |
| 381 'constant', 'private', 'linker_private', 'internal', | |
| 382 'available_externally', 'linkonce', 'linkonce_odr', 'weak', | |
| 383 'weak_odr', 'appending', 'dllimport', 'dllexport', 'common', | |
| 384 'default', 'hidden', 'protected', 'extern_weak', 'external', | |
| 385 'thread_local', 'zeroinitializer', 'undef', 'null', 'to', 'tail', | |
| 386 'target', 'triple', 'datalayout', 'volatile', 'nuw', 'nsw', 'nnan', | |
| 387 'ninf', 'nsz', 'arcp', 'fast', 'exact', 'inbounds', 'align', | |
| 388 'addrspace', 'section', 'alias', 'module', 'asm', 'sideeffect', | |
| 389 'gc', 'dbg', 'linker_private_weak', 'attributes', 'blockaddress', | |
| 390 'initialexec', 'localdynamic', 'localexec', 'prefix', 'unnamed_addr', | |
| 391 'ccc', 'fastcc', 'coldcc', 'x86_stdcallcc', 'x86_fastcallcc', | |
| 392 'arm_apcscc', 'arm_aapcscc', 'arm_aapcs_vfpcc', 'ptx_device', | |
| 393 'ptx_kernel', 'intel_ocl_bicc', 'msp430_intrcc', 'spir_func', | |
| 394 'spir_kernel', 'x86_64_sysvcc', 'x86_64_win64cc', 'x86_thiscallcc', | |
| 395 'cc', 'c', 'signext', 'zeroext', 'inreg', 'sret', 'nounwind', | |
| 396 'noreturn', 'noalias', 'nocapture', 'byval', 'nest', 'readnone', | |
| 397 'readonly', 'inlinehint', 'noinline', 'alwaysinline', 'optsize', 'ssp', | |
| 398 'sspreq', 'noredzone', 'noimplicitfloat', 'naked', 'builtin', 'cold', | |
| 399 'nobuiltin', 'noduplicate', 'nonlazybind', 'optnone', 'returns_twice', | |
| 400 'sanitize_address', 'sanitize_memory', 'sanitize_thread', 'sspstrong', | |
| 401 'uwtable', 'returned', 'type', 'opaque', 'eq', 'ne', 'slt', 'sgt', | |
| 402 'sle', 'sge', 'ult', 'ugt', 'ule', 'uge', 'oeq', 'one', 'olt', 'ogt', | |
| 403 'ole', 'oge', 'ord', 'uno', 'ueq', 'une', 'x', 'acq_rel', 'acquire', | |
| 404 'alignstack', 'atomic', 'catch', 'cleanup', 'filter', 'inteldialect', | |
| 405 'max', 'min', 'monotonic', 'nand', 'personality', 'release', 'seq_cst', | |
| 406 'singlethread', 'umax', 'umin', 'unordered', 'xchg', 'add', 'fadd', | |
| 407 'sub', 'fsub', 'mul', 'fmul', 'udiv', 'sdiv', 'fdiv', 'urem', 'srem', | |
| 408 'frem', 'shl', 'lshr', 'ashr', 'and', 'or', 'xor', 'icmp', 'fcmp', | |
| 409 'phi', 'call', 'trunc', 'zext', 'sext', 'fptrunc', 'fpext', 'uitofp', | |
| 410 'sitofp', 'fptoui', 'fptosi', 'inttoptr', 'ptrtoint', 'bitcast', | |
| 411 'addrspacecast', 'select', 'va_arg', 'ret', 'br', 'switch', 'invoke', | |
| 412 'unwind', 'unreachable', 'indirectbr', 'landingpad', 'resume', | |
| 413 'malloc', 'alloca', 'free', 'load', 'store', 'getelementptr', | |
| 414 'extractelement', 'insertelement', 'shufflevector', 'getresult', | |
| 415 'extractvalue', 'insertvalue', 'atomicrmw', 'cmpxchg', 'fence', | |
| 416 'allocsize', 'amdgpu_cs', 'amdgpu_gs', 'amdgpu_kernel', 'amdgpu_ps', | |
| 417 'amdgpu_vs', 'any', 'anyregcc', 'argmemonly', 'avr_intrcc', | |
| 418 'avr_signalcc', 'caller', 'catchpad', 'catchret', 'catchswitch', | |
| 419 'cleanuppad', 'cleanupret', 'comdat', 'convergent', 'cxx_fast_tlscc', | |
| 420 'deplibs', 'dereferenceable', 'dereferenceable_or_null', 'distinct', | |
| 421 'exactmatch', 'externally_initialized', 'from', 'ghccc', 'hhvm_ccc', | |
| 422 'hhvmcc', 'ifunc', 'inaccessiblemem_or_argmemonly', 'inaccessiblememonly', | |
| 423 'inalloca', 'jumptable', 'largest', 'local_unnamed_addr', 'minsize', | |
| 424 'musttail', 'noduplicates', 'none', 'nonnull', 'norecurse', 'notail', | |
| 425 'preserve_allcc', 'preserve_mostcc', 'prologue', 'safestack', 'samesize', | |
| 426 'source_filename', 'swiftcc', 'swifterror', 'swiftself', 'webkit_jscc', | |
| 427 'within', 'writeonly', 'x86_intrcc', 'x86_vectorcallcc'), | |
| 428 suffix=r'\b'), Keyword), | |
| 429 | |
| 430 # Types | |
| 431 (words(('void', 'half', 'float', 'double', 'x86_fp80', 'fp128', | |
| 432 'ppc_fp128', 'label', 'metadata', 'token')), Keyword.Type), | |
| 433 | |
| 434 # Integer types | |
| 435 (r'i[1-9]\d*', Keyword) | |
| 436 ] | |
| 437 } | |
| 438 | |
| 439 | |
| 440 class NasmLexer(RegexLexer): | |
| 441 """ | |
| 442 For Nasm (Intel) assembly code. | |
| 443 """ | |
| 444 name = 'NASM' | |
| 445 aliases = ['nasm'] | |
| 446 filenames = ['*.asm', '*.ASM'] | |
| 447 mimetypes = ['text/x-nasm'] | |
| 448 | |
| 449 identifier = r'[a-z$._?][\w$.?#@~]*' | |
| 450 hexn = r'(?:0x[0-9a-f]+|$0[0-9a-f]*|[0-9]+[0-9a-f]*h)' | |
| 451 octn = r'[0-7]+q' | |
| 452 binn = r'[01]+b' | |
| 453 decn = r'[0-9]+' | |
| 454 floatn = decn + r'\.e?' + decn | |
| 455 string = r'"(\\"|[^"\n])*"|' + r"'(\\'|[^'\n])*'|" + r"`(\\`|[^`\n])*`" | |
| 456 declkw = r'(?:res|d)[bwdqt]|times' | |
| 457 register = (r'r[0-9][0-5]?[bwd]|' | |
| 458 r'[a-d][lh]|[er]?[a-d]x|[er]?[sb]p|[er]?[sd]i|[c-gs]s|st[0-7]|' | |
| 459 r'mm[0-7]|cr[0-4]|dr[0-367]|tr[3-7]') | |
| 460 wordop = r'seg|wrt|strict' | |
| 461 type = r'byte|[dq]?word' | |
| 462 directives = (r'BITS|USE16|USE32|SECTION|SEGMENT|ABSOLUTE|EXTERN|GLOBAL|' | |
| 463 r'ORG|ALIGN|STRUC|ENDSTRUC|COMMON|CPU|GROUP|UPPERCASE|IMPORT|' | |
| 464 r'EXPORT|LIBRARY|MODULE') | |
| 465 | |
| 466 flags = re.IGNORECASE | re.MULTILINE | |
| 467 tokens = { | |
| 468 'root': [ | |
| 469 (r'^\s*%', Comment.Preproc, 'preproc'), | |
| 470 include('whitespace'), | |
| 471 (identifier + ':', Name.Label), | |
| 472 (r'(%s)(\s+)(equ)' % identifier, | |
| 473 bygroups(Name.Constant, Keyword.Declaration, Keyword.Declaration), | |
| 474 'instruction-args'), | |
| 475 (directives, Keyword, 'instruction-args'), | |
| 476 (declkw, Keyword.Declaration, 'instruction-args'), | |
| 477 (identifier, Name.Function, 'instruction-args'), | |
| 478 (r'[\r\n]+', Text) | |
| 479 ], | |
| 480 'instruction-args': [ | |
| 481 (string, String), | |
| 482 (hexn, Number.Hex), | |
| 483 (octn, Number.Oct), | |
| 484 (binn, Number.Bin), | |
| 485 (floatn, Number.Float), | |
| 486 (decn, Number.Integer), | |
| 487 include('punctuation'), | |
| 488 (register, Name.Builtin), | |
| 489 (identifier, Name.Variable), | |
| 490 (r'[\r\n]+', Text, '#pop'), | |
| 491 include('whitespace') | |
| 492 ], | |
| 493 'preproc': [ | |
| 494 (r'[^;\n]+', Comment.Preproc), | |
| 495 (r';.*?\n', Comment.Single, '#pop'), | |
| 496 (r'\n', Comment.Preproc, '#pop'), | |
| 497 ], | |
| 498 'whitespace': [ | |
| 499 (r'\n', Text), | |
| 500 (r'[ \t]+', Text), | |
| 501 (r';.*', Comment.Single) | |
| 502 ], | |
| 503 'punctuation': [ | |
| 504 (r'[,():\[\]]+', Punctuation), | |
| 505 (r'[&|^<>+*/%~-]+', Operator), | |
| 506 (r'[$]+', Keyword.Constant), | |
| 507 (wordop, Operator.Word), | |
| 508 (type, Keyword.Type) | |
| 509 ], | |
| 510 } | |
| 511 | |
| 512 | |
| 513 class NasmObjdumpLexer(ObjdumpLexer): | |
| 514 """ | |
| 515 For the output of 'objdump -d -M intel'. | |
| 516 | |
| 517 .. versionadded:: 2.0 | |
| 518 """ | |
| 519 name = 'objdump-nasm' | |
| 520 aliases = ['objdump-nasm'] | |
| 521 filenames = ['*.objdump-intel'] | |
| 522 mimetypes = ['text/x-nasm-objdump'] | |
| 523 | |
| 524 tokens = _objdump_lexer_tokens(NasmLexer) | |
| 525 | |
| 526 | |
| 527 class TasmLexer(RegexLexer): | |
| 528 """ | |
| 529 For Tasm (Turbo Assembler) assembly code. | |
| 530 """ | |
| 531 name = 'TASM' | |
| 532 aliases = ['tasm'] | |
| 533 filenames = ['*.asm', '*.ASM', '*.tasm'] | |
| 534 mimetypes = ['text/x-tasm'] | |
| 535 | |
| 536 identifier = r'[@a-z$._?][\w$.?#@~]*' | |
| 537 hexn = r'(?:0x[0-9a-f]+|$0[0-9a-f]*|[0-9]+[0-9a-f]*h)' | |
| 538 octn = r'[0-7]+q' | |
| 539 binn = r'[01]+b' | |
| 540 decn = r'[0-9]+' | |
| 541 floatn = decn + r'\.e?' + decn | |
| 542 string = r'"(\\"|[^"\n])*"|' + r"'(\\'|[^'\n])*'|" + r"`(\\`|[^`\n])*`" | |
| 543 declkw = r'(?:res|d)[bwdqt]|times' | |
| 544 register = (r'r[0-9][0-5]?[bwd]|' | |
| 545 r'[a-d][lh]|[er]?[a-d]x|[er]?[sb]p|[er]?[sd]i|[c-gs]s|st[0-7]|' | |
| 546 r'mm[0-7]|cr[0-4]|dr[0-367]|tr[3-7]') | |
| 547 wordop = r'seg|wrt|strict' | |
| 548 type = r'byte|[dq]?word' | |
| 549 directives = (r'BITS|USE16|USE32|SECTION|SEGMENT|ABSOLUTE|EXTERN|GLOBAL|' | |
| 550 r'ORG|ALIGN|STRUC|ENDSTRUC|ENDS|COMMON|CPU|GROUP|UPPERCASE|INCLUDE|' | |
| 551 r'EXPORT|LIBRARY|MODULE|PROC|ENDP|USES|ARG|DATASEG|UDATASEG|END|IDEAL|' | |
| 552 r'P386|MODEL|ASSUME|CODESEG|SIZE') | |
| 553 # T[A-Z][a-z] is more of a convention. Lexer should filter out STRUC definitions | |
| 554 # and then 'add' them to datatype somehow. | |
| 555 datatype = (r'db|dd|dw|T[A-Z][a-z]+') | |
| 556 | |
| 557 flags = re.IGNORECASE | re.MULTILINE | |
| 558 tokens = { | |
| 559 'root': [ | |
| 560 (r'^\s*%', Comment.Preproc, 'preproc'), | |
| 561 include('whitespace'), | |
| 562 (identifier + ':', Name.Label), | |
| 563 (directives, Keyword, 'instruction-args'), | |
| 564 (r'(%s)(\s+)(%s)' % (identifier, datatype), | |
| 565 bygroups(Name.Constant, Keyword.Declaration, Keyword.Declaration), | |
| 566 'instruction-args'), | |
| 567 (declkw, Keyword.Declaration, 'instruction-args'), | |
| 568 (identifier, Name.Function, 'instruction-args'), | |
| 569 (r'[\r\n]+', Text) | |
| 570 ], | |
| 571 'instruction-args': [ | |
| 572 (string, String), | |
| 573 (hexn, Number.Hex), | |
| 574 (octn, Number.Oct), | |
| 575 (binn, Number.Bin), | |
| 576 (floatn, Number.Float), | |
| 577 (decn, Number.Integer), | |
| 578 include('punctuation'), | |
| 579 (register, Name.Builtin), | |
| 580 (identifier, Name.Variable), | |
| 581 # Do not match newline when it's preceeded by a backslash | |
| 582 (r'(\\\s*)(;.*)([\r\n])', bygroups(Text, Comment.Single, Text)), | |
| 583 (r'[\r\n]+', Text, '#pop'), | |
| 584 include('whitespace') | |
| 585 ], | |
| 586 'preproc': [ | |
| 587 (r'[^;\n]+', Comment.Preproc), | |
| 588 (r';.*?\n', Comment.Single, '#pop'), | |
| 589 (r'\n', Comment.Preproc, '#pop'), | |
| 590 ], | |
| 591 'whitespace': [ | |
| 592 (r'[\n\r]', Text), | |
| 593 (r'\\[\n\r]', Text), | |
| 594 (r'[ \t]+', Text), | |
| 595 (r';.*', Comment.Single) | |
| 596 ], | |
| 597 'punctuation': [ | |
| 598 (r'[,():\[\]]+', Punctuation), | |
| 599 (r'[&|^<>+*=/%~-]+', Operator), | |
| 600 (r'[$]+', Keyword.Constant), | |
| 601 (wordop, Operator.Word), | |
| 602 (type, Keyword.Type) | |
| 603 ], | |
| 604 } | |
| 605 | |
| 606 | |
| 607 class Ca65Lexer(RegexLexer): | |
| 608 """ | |
| 609 For ca65 assembler sources. | |
| 610 | |
| 611 .. versionadded:: 1.6 | |
| 612 """ | |
| 613 name = 'ca65 assembler' | |
| 614 aliases = ['ca65'] | |
| 615 filenames = ['*.s'] | |
| 616 | |
| 617 flags = re.IGNORECASE | |
| 618 | |
| 619 tokens = { | |
| 620 'root': [ | |
| 621 (r';.*', Comment.Single), | |
| 622 (r'\s+', Text), | |
| 623 (r'[a-z_.@$][\w.@$]*:', Name.Label), | |
| 624 (r'((ld|st)[axy]|(in|de)[cxy]|asl|lsr|ro[lr]|adc|sbc|cmp|cp[xy]' | |
| 625 r'|cl[cvdi]|se[cdi]|jmp|jsr|bne|beq|bpl|bmi|bvc|bvs|bcc|bcs' | |
| 626 r'|p[lh][ap]|rt[is]|brk|nop|ta[xy]|t[xy]a|txs|tsx|and|ora|eor' | |
| 627 r'|bit)\b', Keyword), | |
| 628 (r'\.\w+', Keyword.Pseudo), | |
| 629 (r'[-+~*/^&|!<>=]', Operator), | |
| 630 (r'"[^"\n]*.', String), | |
| 631 (r"'[^'\n]*.", String.Char), | |
| 632 (r'\$[0-9a-f]+|[0-9a-f]+h\b', Number.Hex), | |
| 633 (r'\d+', Number.Integer), | |
| 634 (r'%[01]+', Number.Bin), | |
| 635 (r'[#,.:()=\[\]]', Punctuation), | |
| 636 (r'[a-z_.@$][\w.@$]*', Name), | |
| 637 ] | |
| 638 } | |
| 639 | |
| 640 def analyse_text(self, text): | |
| 641 # comments in GAS start with "#" | |
| 642 if re.match(r'^\s*;', text, re.MULTILINE): | |
| 643 return 0.9 |
