llvm.org GIT mirror llvm / release_50 lib / CodeGen / MIRParser / MILexer.cpp
release_50

Tree @release_50 (Download .tar.gz)

MILexer.cpp @release_50raw · history · blame

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
//===- MILexer.cpp - Machine instructions lexer implementation ----------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file implements the lexing of machine instructions.
//
//===----------------------------------------------------------------------===//

#include "MILexer.h"
#include "llvm/ADT/None.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/ADT/StringSwitch.h"
#include "llvm/ADT/Twine.h"
#include <cctype>

using namespace llvm;

namespace {

typedef function_ref<void(StringRef::iterator Loc, const Twine &)>
    ErrorCallbackType;

/// This class provides a way to iterate and get characters from the source
/// string.
class Cursor {
  const char *Ptr;
  const char *End;

public:
  Cursor(NoneType) : Ptr(nullptr), End(nullptr) {}

  explicit Cursor(StringRef Str) {
    Ptr = Str.data();
    End = Ptr + Str.size();
  }

  bool isEOF() const { return Ptr == End; }

  char peek(int I = 0) const { return End - Ptr <= I ? 0 : Ptr[I]; }

  void advance(unsigned I = 1) { Ptr += I; }

  StringRef remaining() const { return StringRef(Ptr, End - Ptr); }

  StringRef upto(Cursor C) const {
    assert(C.Ptr >= Ptr && C.Ptr <= End);
    return StringRef(Ptr, C.Ptr - Ptr);
  }

  StringRef::iterator location() const { return Ptr; }

  operator bool() const { return Ptr != nullptr; }
};

} // end anonymous namespace

MIToken &MIToken::reset(TokenKind Kind, StringRef Range) {
  this->Kind = Kind;
  this->Range = Range;
  return *this;
}

MIToken &MIToken::setStringValue(StringRef StrVal) {
  StringValue = StrVal;
  return *this;
}

MIToken &MIToken::setOwnedStringValue(std::string StrVal) {
  StringValueStorage = std::move(StrVal);
  StringValue = StringValueStorage;
  return *this;
}

MIToken &MIToken::setIntegerValue(APSInt IntVal) {
  this->IntVal = std::move(IntVal);
  return *this;
}

/// Skip the leading whitespace characters and return the updated cursor.
static Cursor skipWhitespace(Cursor C) {
  while (isblank(C.peek()))
    C.advance();
  return C;
}

static bool isNewlineChar(char C) { return C == '\n' || C == '\r'; }

/// Skip a line comment and return the updated cursor.
static Cursor skipComment(Cursor C) {
  if (C.peek() != ';')
    return C;
  while (!isNewlineChar(C.peek()) && !C.isEOF())
    C.advance();
  return C;
}

/// Return true if the given character satisfies the following regular
/// expression: [-a-zA-Z$._0-9]
static bool isIdentifierChar(char C) {
  return isalpha(C) || isdigit(C) || C == '_' || C == '-' || C == '.' ||
         C == '$';
}

/// Unescapes the given string value.
///
/// Expects the string value to be quoted.
static std::string unescapeQuotedString(StringRef Value) {
  assert(Value.front() == '"' && Value.back() == '"');
  Cursor C = Cursor(Value.substr(1, Value.size() - 2));

  std::string Str;
  Str.reserve(C.remaining().size());
  while (!C.isEOF()) {
    char Char = C.peek();
    if (Char == '\\') {
      if (C.peek(1) == '\\') {
        // Two '\' become one
        Str += '\\';
        C.advance(2);
        continue;
      }
      if (isxdigit(C.peek(1)) && isxdigit(C.peek(2))) {
        Str += hexDigitValue(C.peek(1)) * 16 + hexDigitValue(C.peek(2));
        C.advance(3);
        continue;
      }
    }
    Str += Char;
    C.advance();
  }
  return Str;
}

/// Lex a string constant using the following regular expression: \"[^\"]*\"
static Cursor lexStringConstant(Cursor C, ErrorCallbackType ErrorCallback) {
  assert(C.peek() == '"');
  for (C.advance(); C.peek() != '"'; C.advance()) {
    if (C.isEOF() || isNewlineChar(C.peek())) {
      ErrorCallback(
          C.location(),
          "end of machine instruction reached before the closing '\"'");
      return None;
    }
  }
  C.advance();
  return C;
}

static Cursor lexName(Cursor C, MIToken &Token, MIToken::TokenKind Type,
                      unsigned PrefixLength, ErrorCallbackType ErrorCallback) {
  auto Range = C;
  C.advance(PrefixLength);
  if (C.peek() == '"') {
    if (Cursor R = lexStringConstant(C, ErrorCallback)) {
      StringRef String = Range.upto(R);
      Token.reset(Type, String)
          .setOwnedStringValue(
              unescapeQuotedString(String.drop_front(PrefixLength)));
      return R;
    }
    Token.reset(MIToken::Error, Range.remaining());
    return Range;
  }
  while (isIdentifierChar(C.peek()))
    C.advance();
  Token.reset(Type, Range.upto(C))
      .setStringValue(Range.upto(C).drop_front(PrefixLength));
  return C;
}

static Cursor maybeLexIntegerOrScalarType(Cursor C, MIToken &Token) {
  if ((C.peek() != 'i' && C.peek() != 's' && C.peek() != 'p') ||
      !isdigit(C.peek(1)))
    return None;
  char Kind = C.peek();
  auto Range = C;
  C.advance(); // Skip 'i', 's', or 'p'
  while (isdigit(C.peek()))
    C.advance();

  Token.reset(Kind == 'i'
                  ? MIToken::IntegerType
                  : (Kind == 's' ? MIToken::ScalarType : MIToken::PointerType),
              Range.upto(C));
  return C;
}

static MIToken::TokenKind getIdentifierKind(StringRef Identifier) {
  return StringSwitch<MIToken::TokenKind>(Identifier)
      .Case("_", MIToken::underscore)
      .Case("implicit", MIToken::kw_implicit)
      .Case("implicit-def", MIToken::kw_implicit_define)
      .Case("def", MIToken::kw_def)
      .Case("dead", MIToken::kw_dead)
      .Case("killed", MIToken::kw_killed)
      .Case("undef", MIToken::kw_undef)
      .Case("internal", MIToken::kw_internal)
      .Case("early-clobber", MIToken::kw_early_clobber)
      .Case("debug-use", MIToken::kw_debug_use)
      .Case("tied-def", MIToken::kw_tied_def)
      .Case("frame-setup", MIToken::kw_frame_setup)
      .Case("debug-location", MIToken::kw_debug_location)
      .Case("same_value", MIToken::kw_cfi_same_value)
      .Case("offset", MIToken::kw_cfi_offset)
      .Case("def_cfa_register", MIToken::kw_cfi_def_cfa_register)
      .Case("def_cfa_offset", MIToken::kw_cfi_def_cfa_offset)
      .Case("def_cfa", MIToken::kw_cfi_def_cfa)
      .Case("blockaddress", MIToken::kw_blockaddress)
      .Case("intrinsic", MIToken::kw_intrinsic)
      .Case("target-index", MIToken::kw_target_index)
      .Case("half", MIToken::kw_half)
      .Case("float", MIToken::kw_float)
      .Case("double", MIToken::kw_double)
      .Case("x86_fp80", MIToken::kw_x86_fp80)
      .Case("fp128", MIToken::kw_fp128)
      .Case("ppc_fp128", MIToken::kw_ppc_fp128)
      .Case("target-flags", MIToken::kw_target_flags)
      .Case("volatile", MIToken::kw_volatile)
      .Case("non-temporal", MIToken::kw_non_temporal)
      .Case("dereferenceable", MIToken::kw_dereferenceable)
      .Case("invariant", MIToken::kw_invariant)
      .Case("align", MIToken::kw_align)
      .Case("stack", MIToken::kw_stack)
      .Case("got", MIToken::kw_got)
      .Case("jump-table", MIToken::kw_jump_table)
      .Case("constant-pool", MIToken::kw_constant_pool)
      .Case("call-entry", MIToken::kw_call_entry)
      .Case("liveout", MIToken::kw_liveout)
      .Case("address-taken", MIToken::kw_address_taken)
      .Case("landing-pad", MIToken::kw_landing_pad)
      .Case("liveins", MIToken::kw_liveins)
      .Case("successors", MIToken::kw_successors)
      .Case("floatpred", MIToken::kw_floatpred)
      .Case("intpred", MIToken::kw_intpred)
      .Default(MIToken::Identifier);
}

static Cursor maybeLexIdentifier(Cursor C, MIToken &Token) {
  if (!isalpha(C.peek()) && C.peek() != '_')
    return None;
  auto Range = C;
  while (isIdentifierChar(C.peek()))
    C.advance();
  auto Identifier = Range.upto(C);
  Token.reset(getIdentifierKind(Identifier), Identifier)
      .setStringValue(Identifier);
  return C;
}

static Cursor maybeLexMachineBasicBlock(Cursor C, MIToken &Token,
                                        ErrorCallbackType ErrorCallback) {
  bool IsReference = C.remaining().startswith("%bb.");
  if (!IsReference && !C.remaining().startswith("bb."))
    return None;
  auto Range = C;
  unsigned PrefixLength = IsReference ? 4 : 3;
  C.advance(PrefixLength); // Skip '%bb.' or 'bb.'
  if (!isdigit(C.peek())) {
    Token.reset(MIToken::Error, C.remaining());
    ErrorCallback(C.location(), "expected a number after '%bb.'");
    return C;
  }
  auto NumberRange = C;
  while (isdigit(C.peek()))
    C.advance();
  StringRef Number = NumberRange.upto(C);
  unsigned StringOffset = PrefixLength + Number.size(); // Drop '%bb.<id>'
  if (C.peek() == '.') {
    C.advance(); // Skip '.'
    ++StringOffset;
    while (isIdentifierChar(C.peek()))
      C.advance();
  }
  Token.reset(IsReference ? MIToken::MachineBasicBlock
                          : MIToken::MachineBasicBlockLabel,
              Range.upto(C))
      .setIntegerValue(APSInt(Number))
      .setStringValue(Range.upto(C).drop_front(StringOffset));
  return C;
}

static Cursor maybeLexIndex(Cursor C, MIToken &Token, StringRef Rule,
                            MIToken::TokenKind Kind) {
  if (!C.remaining().startswith(Rule) || !isdigit(C.peek(Rule.size())))
    return None;
  auto Range = C;
  C.advance(Rule.size());
  auto NumberRange = C;
  while (isdigit(C.peek()))
    C.advance();
  Token.reset(Kind, Range.upto(C)).setIntegerValue(APSInt(NumberRange.upto(C)));
  return C;
}

static Cursor maybeLexIndexAndName(Cursor C, MIToken &Token, StringRef Rule,
                                   MIToken::TokenKind Kind) {
  if (!C.remaining().startswith(Rule) || !isdigit(C.peek(Rule.size())))
    return None;
  auto Range = C;
  C.advance(Rule.size());
  auto NumberRange = C;
  while (isdigit(C.peek()))
    C.advance();
  StringRef Number = NumberRange.upto(C);
  unsigned StringOffset = Rule.size() + Number.size();
  if (C.peek() == '.') {
    C.advance();
    ++StringOffset;
    while (isIdentifierChar(C.peek()))
      C.advance();
  }
  Token.reset(Kind, Range.upto(C))
      .setIntegerValue(APSInt(Number))
      .setStringValue(Range.upto(C).drop_front(StringOffset));
  return C;
}

static Cursor maybeLexJumpTableIndex(Cursor C, MIToken &Token) {
  return maybeLexIndex(C, Token, "%jump-table.", MIToken::JumpTableIndex);
}

static Cursor maybeLexStackObject(Cursor C, MIToken &Token) {
  return maybeLexIndexAndName(C, Token, "%stack.", MIToken::StackObject);
}

static Cursor maybeLexFixedStackObject(Cursor C, MIToken &Token) {
  return maybeLexIndex(C, Token, "%fixed-stack.", MIToken::FixedStackObject);
}

static Cursor maybeLexConstantPoolItem(Cursor C, MIToken &Token) {
  return maybeLexIndex(C, Token, "%const.", MIToken::ConstantPoolItem);
}

static Cursor maybeLexSubRegisterIndex(Cursor C, MIToken &Token,
                                       ErrorCallbackType ErrorCallback) {
  const StringRef Rule = "%subreg.";
  if (!C.remaining().startswith(Rule))
    return None;
  return lexName(C, Token, MIToken::SubRegisterIndex, Rule.size(),
                 ErrorCallback);
}

static Cursor maybeLexIRBlock(Cursor C, MIToken &Token,
                              ErrorCallbackType ErrorCallback) {
  const StringRef Rule = "%ir-block.";
  if (!C.remaining().startswith(Rule))
    return None;
  if (isdigit(C.peek(Rule.size())))
    return maybeLexIndex(C, Token, Rule, MIToken::IRBlock);
  return lexName(C, Token, MIToken::NamedIRBlock, Rule.size(), ErrorCallback);
}

static Cursor maybeLexIRValue(Cursor C, MIToken &Token,
                              ErrorCallbackType ErrorCallback) {
  const StringRef Rule = "%ir.";
  if (!C.remaining().startswith(Rule))
    return None;
  if (isdigit(C.peek(Rule.size())))
    return maybeLexIndex(C, Token, Rule, MIToken::IRValue);
  return lexName(C, Token, MIToken::NamedIRValue, Rule.size(), ErrorCallback);
}

static Cursor maybeLexStringConstant(Cursor C, MIToken &Token,
                                     ErrorCallbackType ErrorCallback) {
  if (C.peek() != '"')
    return None;
  return lexName(C, Token, MIToken::StringConstant, /*PrefixLength=*/0,
                 ErrorCallback);
}

static Cursor lexVirtualRegister(Cursor C, MIToken &Token) {
  auto Range = C;
  C.advance(); // Skip '%'
  auto NumberRange = C;
  while (isdigit(C.peek()))
    C.advance();
  Token.reset(MIToken::VirtualRegister, Range.upto(C))
      .setIntegerValue(APSInt(NumberRange.upto(C)));
  return C;
}

/// Returns true for a character allowed in a register name.
static bool isRegisterChar(char C) {
  return isIdentifierChar(C) && C != '.';
}

static Cursor maybeLexRegister(Cursor C, MIToken &Token) {
  if (C.peek() != '%')
    return None;
  if (isdigit(C.peek(1)))
    return lexVirtualRegister(C, Token);
  auto Range = C;
  C.advance(); // Skip '%'
  while (isRegisterChar(C.peek()))
    C.advance();
  Token.reset(MIToken::NamedRegister, Range.upto(C))
      .setStringValue(Range.upto(C).drop_front(1)); // Drop the '%'
  return C;
}

static Cursor maybeLexGlobalValue(Cursor C, MIToken &Token,
                                  ErrorCallbackType ErrorCallback) {
  if (C.peek() != '@')
    return None;
  if (!isdigit(C.peek(1)))
    return lexName(C, Token, MIToken::NamedGlobalValue, /*PrefixLength=*/1,
                   ErrorCallback);
  auto Range = C;
  C.advance(1); // Skip the '@'
  auto NumberRange = C;
  while (isdigit(C.peek()))
    C.advance();
  Token.reset(MIToken::GlobalValue, Range.upto(C))
      .setIntegerValue(APSInt(NumberRange.upto(C)));
  return C;
}

static Cursor maybeLexExternalSymbol(Cursor C, MIToken &Token,
                                     ErrorCallbackType ErrorCallback) {
  if (C.peek() != '$')
    return None;
  return lexName(C, Token, MIToken::ExternalSymbol, /*PrefixLength=*/1,
                 ErrorCallback);
}

static bool isValidHexFloatingPointPrefix(char C) {
  return C == 'H' || C == 'K' || C == 'L' || C == 'M';
}

static Cursor lexFloatingPointLiteral(Cursor Range, Cursor C, MIToken &Token) {
  C.advance();
  // Skip over [0-9]*([eE][-+]?[0-9]+)?
  while (isdigit(C.peek()))
    C.advance();
  if ((C.peek() == 'e' || C.peek() == 'E') &&
      (isdigit(C.peek(1)) ||
       ((C.peek(1) == '-' || C.peek(1) == '+') && isdigit(C.peek(2))))) {
    C.advance(2);
    while (isdigit(C.peek()))
      C.advance();
  }
  Token.reset(MIToken::FloatingPointLiteral, Range.upto(C));
  return C;
}

static Cursor maybeLexHexadecimalLiteral(Cursor C, MIToken &Token) {
  if (C.peek() != '0' || (C.peek(1) != 'x' && C.peek(1) != 'X'))
    return None;
  Cursor Range = C;
  C.advance(2);
  unsigned PrefLen = 2;
  if (isValidHexFloatingPointPrefix(C.peek())) {
    C.advance();
    PrefLen++;
  }
  while (isxdigit(C.peek()))
    C.advance();
  StringRef StrVal = Range.upto(C);
  if (StrVal.size() <= PrefLen)
    return None;
  if (PrefLen == 2)
    Token.reset(MIToken::HexLiteral, Range.upto(C));
  else // It must be 3, which means that there was a floating-point prefix.
    Token.reset(MIToken::FloatingPointLiteral, Range.upto(C));
  return C;
}

static Cursor maybeLexNumericalLiteral(Cursor C, MIToken &Token) {
  if (!isdigit(C.peek()) && (C.peek() != '-' || !isdigit(C.peek(1))))
    return None;
  auto Range = C;
  C.advance();
  while (isdigit(C.peek()))
    C.advance();
  if (C.peek() == '.')
    return lexFloatingPointLiteral(Range, C, Token);
  StringRef StrVal = Range.upto(C);
  Token.reset(MIToken::IntegerLiteral, StrVal).setIntegerValue(APSInt(StrVal));
  return C;
}

static MIToken::TokenKind getMetadataKeywordKind(StringRef Identifier) {
  return StringSwitch<MIToken::TokenKind>(Identifier)
      .Case("!tbaa", MIToken::md_tbaa)
      .Case("!alias.scope", MIToken::md_alias_scope)
      .Case("!noalias", MIToken::md_noalias)
      .Case("!range", MIToken::md_range)
      .Default(MIToken::Error);
}

static Cursor maybeLexExlaim(Cursor C, MIToken &Token,
                             ErrorCallbackType ErrorCallback) {
  if (C.peek() != '!')
    return None;
  auto Range = C;
  C.advance(1);
  if (isdigit(C.peek()) || !isIdentifierChar(C.peek())) {
    Token.reset(MIToken::exclaim, Range.upto(C));
    return C;
  }
  while (isIdentifierChar(C.peek()))
    C.advance();
  StringRef StrVal = Range.upto(C);
  Token.reset(getMetadataKeywordKind(StrVal), StrVal);
  if (Token.isError())
    ErrorCallback(Token.location(),
                  "use of unknown metadata keyword '" + StrVal + "'");
  return C;
}

static MIToken::TokenKind symbolToken(char C) {
  switch (C) {
  case ',':
    return MIToken::comma;
  case '.':
    return MIToken::dot;
  case '=':
    return MIToken::equal;
  case ':':
    return MIToken::colon;
  case '(':
    return MIToken::lparen;
  case ')':
    return MIToken::rparen;
  case '{':
    return MIToken::lbrace;
  case '}':
    return MIToken::rbrace;
  case '+':
    return MIToken::plus;
  case '-':
    return MIToken::minus;
  case '<':
    return MIToken::less;
  case '>':
    return MIToken::greater;
  default:
    return MIToken::Error;
  }
}

static Cursor maybeLexSymbol(Cursor C, MIToken &Token) {
  MIToken::TokenKind Kind;
  unsigned Length = 1;
  if (C.peek() == ':' && C.peek(1) == ':') {
    Kind = MIToken::coloncolon;
    Length = 2;
  } else
    Kind = symbolToken(C.peek());
  if (Kind == MIToken::Error)
    return None;
  auto Range = C;
  C.advance(Length);
  Token.reset(Kind, Range.upto(C));
  return C;
}

static Cursor maybeLexNewline(Cursor C, MIToken &Token) {
  if (!isNewlineChar(C.peek()))
    return None;
  auto Range = C;
  C.advance();
  Token.reset(MIToken::Newline, Range.upto(C));
  return C;
}

static Cursor maybeLexEscapedIRValue(Cursor C, MIToken &Token,
                                     ErrorCallbackType ErrorCallback) {
  if (C.peek() != '`')
    return None;
  auto Range = C;
  C.advance();
  auto StrRange = C;
  while (C.peek() != '`') {
    if (C.isEOF() || isNewlineChar(C.peek())) {
      ErrorCallback(
          C.location(),
          "end of machine instruction reached before the closing '`'");
      Token.reset(MIToken::Error, Range.remaining());
      return C;
    }
    C.advance();
  }
  StringRef Value = StrRange.upto(C);
  C.advance();
  Token.reset(MIToken::QuotedIRValue, Range.upto(C)).setStringValue(Value);
  return C;
}

StringRef llvm::lexMIToken(StringRef Source, MIToken &Token,
                           ErrorCallbackType ErrorCallback) {
  auto C = skipComment(skipWhitespace(Cursor(Source)));
  if (C.isEOF()) {
    Token.reset(MIToken::Eof, C.remaining());
    return C.remaining();
  }

  if (Cursor R = maybeLexIntegerOrScalarType(C, Token))
    return R.remaining();
  if (Cursor R = maybeLexMachineBasicBlock(C, Token, ErrorCallback))
    return R.remaining();
  if (Cursor R = maybeLexIdentifier(C, Token))
    return R.remaining();
  if (Cursor R = maybeLexJumpTableIndex(C, Token))
    return R.remaining();
  if (Cursor R = maybeLexStackObject(C, Token))
    return R.remaining();
  if (Cursor R = maybeLexFixedStackObject(C, Token))
    return R.remaining();
  if (Cursor R = maybeLexConstantPoolItem(C, Token))
    return R.remaining();
  if (Cursor R = maybeLexSubRegisterIndex(C, Token, ErrorCallback))
    return R.remaining();
  if (Cursor R = maybeLexIRBlock(C, Token, ErrorCallback))
    return R.remaining();
  if (Cursor R = maybeLexIRValue(C, Token, ErrorCallback))
    return R.remaining();
  if (Cursor R = maybeLexRegister(C, Token))
    return R.remaining();
  if (Cursor R = maybeLexGlobalValue(C, Token, ErrorCallback))
    return R.remaining();
  if (Cursor R = maybeLexExternalSymbol(C, Token, ErrorCallback))
    return R.remaining();
  if (Cursor R = maybeLexHexadecimalLiteral(C, Token))
    return R.remaining();
  if (Cursor R = maybeLexNumericalLiteral(C, Token))
    return R.remaining();
  if (Cursor R = maybeLexExlaim(C, Token, ErrorCallback))
    return R.remaining();
  if (Cursor R = maybeLexSymbol(C, Token))
    return R.remaining();
  if (Cursor R = maybeLexNewline(C, Token))
    return R.remaining();
  if (Cursor R = maybeLexEscapedIRValue(C, Token, ErrorCallback))
    return R.remaining();
  if (Cursor R = maybeLexStringConstant(C, Token, ErrorCallback))
    return R.remaining();

  Token.reset(MIToken::Error, C.remaining());
  ErrorCallback(C.location(),
                Twine("unexpected character '") + Twine(C.peek()) + "'");
  return C.remaining();
}