summaryrefslogtreecommitdiff
path: root/lib/MC/MCParser/AsmLexer.cpp
blob: 6bd89860d5121dfd1fddd40fc59523e2a3717b3f (plain)
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
//===- AsmLexer.cpp - Lexer for Assembly Files ----------------------------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This class implements the lexer for assembly files.
//
//===----------------------------------------------------------------------===//

#include "llvm/MC/MCParser/AsmLexer.h"
#include "llvm/Support/SMLoc.h"
#include "llvm/Support/MemoryBuffer.h"
#include "llvm/MC/MCAsmInfo.h"
#include <cctype>
#include <cerrno>
#include <cstdio>
#include <cstdlib>
using namespace llvm;

AsmLexer::AsmLexer(const MCAsmInfo &_MAI) : MAI(_MAI)  {
  CurBuf = NULL;
  CurPtr = NULL;
}

AsmLexer::~AsmLexer() {
}

void AsmLexer::setBuffer(const MemoryBuffer *buf, const char *ptr) {
  CurBuf = buf;

  if (ptr)
    CurPtr = ptr;
  else
    CurPtr = CurBuf->getBufferStart();

  TokStart = 0;
}

/// ReturnError - Set the error to the specified string at the specified
/// location.  This is defined to always return AsmToken::Error.
AsmToken AsmLexer::ReturnError(const char *Loc, const std::string &Msg) {
  SetError(SMLoc::getFromPointer(Loc), Msg);

  return AsmToken(AsmToken::Error, StringRef(Loc, 0));
}

int AsmLexer::getNextChar() {
  char CurChar = *CurPtr++;
  switch (CurChar) {
  default:
    return (unsigned char)CurChar;
  case 0:
    // A nul character in the stream is either the end of the current buffer or
    // a random nul in the file.  Disambiguate that here.
    if (CurPtr-1 != CurBuf->getBufferEnd())
      return 0;  // Just whitespace.

    // Otherwise, return end of file.
    --CurPtr;  // Another call to lex will return EOF again.
    return EOF;
  }
}

/// LexFloatLiteral: [0-9]*[.][0-9]*([eE][+-]?[0-9]*)?
///
/// The leading integral digit sequence and dot should have already been
/// consumed, some or all of the fractional digit sequence *can* have been
/// consumed.
AsmToken AsmLexer::LexFloatLiteral() {
  // Skip the fractional digit sequence.
  while (isdigit(*CurPtr))
    ++CurPtr;

  // Check for exponent; we intentionally accept a slighlty wider set of
  // literals here and rely on the upstream client to reject invalid ones (e.g.,
  // "1e+").
  if (*CurPtr == 'e' || *CurPtr == 'E') {
    ++CurPtr;
    if (*CurPtr == '-' || *CurPtr == '+')
      ++CurPtr;
    while (isdigit(*CurPtr))
      ++CurPtr;
  }

  return AsmToken(AsmToken::Real,
                  StringRef(TokStart, CurPtr - TokStart));
}

/// LexIdentifier: [a-zA-Z_.][a-zA-Z0-9_$.@]*
static bool IsIdentifierChar(char c) {
  return isalnum(c) || c == '_' || c == '$' || c == '.' || c == '@';
}
AsmToken AsmLexer::LexIdentifier() {
  // Check for floating point literals.
  if (CurPtr[-1] == '.' && isdigit(*CurPtr)) {
    // Disambiguate a .1243foo identifier from a floating literal.
    while (isdigit(*CurPtr))
      ++CurPtr;
    if (*CurPtr == 'e' || *CurPtr == 'E' || !IsIdentifierChar(*CurPtr))
      return LexFloatLiteral();
  }

  while (IsIdentifierChar(*CurPtr))
    ++CurPtr;

  // Handle . as a special case.
  if (CurPtr == TokStart+1 && TokStart[0] == '.')
    return AsmToken(AsmToken::Dot, StringRef(TokStart, 1));

  return AsmToken(AsmToken::Identifier, StringRef(TokStart, CurPtr - TokStart));
}

/// LexSlash: Slash: /
///           C-Style Comment: /* ... */
AsmToken AsmLexer::LexSlash() {
  switch (*CurPtr) {
  case '*': break; // C style comment.
  case '/': return ++CurPtr, LexLineComment();
  default:  return AsmToken(AsmToken::Slash, StringRef(CurPtr-1, 1));
  }

  // C Style comment.
  ++CurPtr;  // skip the star.
  while (1) {
    int CurChar = getNextChar();
    switch (CurChar) {
    case EOF:
      return ReturnError(TokStart, "unterminated comment");
    case '*':
      // End of the comment?
      if (CurPtr[0] != '/') break;

      ++CurPtr;   // End the */.
      return LexToken();
    }
  }
}

/// LexLineComment: Comment: #[^\n]*
///                        : //[^\n]*
AsmToken AsmLexer::LexLineComment() {
  // FIXME: This is broken if we happen to a comment at the end of a file, which
  // was .included, and which doesn't end with a newline.
  int CurChar = getNextChar();
  while (CurChar != '\n' && CurChar != '\n' && CurChar != EOF)
    CurChar = getNextChar();

  if (CurChar == EOF)
    return AsmToken(AsmToken::Eof, StringRef(CurPtr, 0));
  return AsmToken(AsmToken::EndOfStatement, StringRef(CurPtr, 0));
}

static void SkipIgnoredIntegerSuffix(const char *&CurPtr) {
  if (CurPtr[0] == 'L' && CurPtr[1] == 'L')
    CurPtr += 2;
  if (CurPtr[0] == 'U' && CurPtr[1] == 'L' && CurPtr[2] == 'L')
    CurPtr += 3;
}

/// LexDigit: First character is [0-9].
///   Local Label: [0-9][:]
///   Forward/Backward Label: [0-9][fb]
///   Binary integer: 0b[01]+
///   Octal integer: 0[0-7]+
///   Hex integer: 0x[0-9a-fA-F]+
///   Decimal integer: [1-9][0-9]*
AsmToken AsmLexer::LexDigit() {
  // Decimal integer: [1-9][0-9]*
  if (CurPtr[-1] != '0' || CurPtr[0] == '.') {
    while (isdigit(*CurPtr))
      ++CurPtr;

    // Check for floating point literals.
    if (*CurPtr == '.' || *CurPtr == 'e') {
      ++CurPtr;
      return LexFloatLiteral();
    }

    StringRef Result(TokStart, CurPtr - TokStart);

    long long Value;
    if (Result.getAsInteger(10, Value)) {
      // Allow positive values that are too large to fit into a signed 64-bit
      // integer, but that do fit in an unsigned one, we just convert them over.
      unsigned long long UValue;
      if (Result.getAsInteger(10, UValue))
        return ReturnError(TokStart, "invalid decimal number");
      Value = (long long)UValue;
    }

    // The darwin/x86 (and x86-64) assembler accepts and ignores ULL and LL
    // suffixes on integer literals.
    SkipIgnoredIntegerSuffix(CurPtr);

    return AsmToken(AsmToken::Integer, Result, Value);
  }

  if (*CurPtr == 'b') {
    ++CurPtr;
    // See if we actually have "0b" as part of something like "jmp 0b\n"
    if (!isdigit(CurPtr[0])) {
      --CurPtr;
      StringRef Result(TokStart, CurPtr - TokStart);
      return AsmToken(AsmToken::Integer, Result, 0);
    }
    const char *NumStart = CurPtr;
    while (CurPtr[0] == '0' || CurPtr[0] == '1')
      ++CurPtr;

    // Requires at least one binary digit.
    if (CurPtr == NumStart)
      return ReturnError(TokStart, "Invalid binary number");

    StringRef Result(TokStart, CurPtr - TokStart);

    long long Value;
    if (Result.substr(2).getAsInteger(2, Value))
      return ReturnError(TokStart, "Invalid binary number");

    // The darwin/x86 (and x86-64) assembler accepts and ignores ULL and LL
    // suffixes on integer literals.
    SkipIgnoredIntegerSuffix(CurPtr);

    return AsmToken(AsmToken::Integer, Result, Value);
  }

  if (*CurPtr == 'x') {
    ++CurPtr;
    const char *NumStart = CurPtr;
    while (isxdigit(CurPtr[0]))
      ++CurPtr;

    // Requires at least one hex digit.
    if (CurPtr == NumStart)
      return ReturnError(CurPtr-2, "Invalid hexadecimal number");

    unsigned long long Result;
    if (StringRef(TokStart, CurPtr - TokStart).getAsInteger(0, Result))
      return ReturnError(TokStart, "Invalid hexadecimal number");

    // The darwin/x86 (and x86-64) assembler accepts and ignores ULL and LL
    // suffixes on integer literals.
    SkipIgnoredIntegerSuffix(CurPtr);

    return AsmToken(AsmToken::Integer, StringRef(TokStart, CurPtr - TokStart),
                    (int64_t)Result);
  }

  // Must be an octal number, it starts with 0.
  while (*CurPtr >= '0' && *CurPtr <= '7')
    ++CurPtr;

  StringRef Result(TokStart, CurPtr - TokStart);
  long long Value;
  if (Result.getAsInteger(8, Value))
    return ReturnError(TokStart, "Invalid octal number");

  // The darwin/x86 (and x86-64) assembler accepts and ignores ULL and LL
  // suffixes on integer literals.
  SkipIgnoredIntegerSuffix(CurPtr);

  return AsmToken(AsmToken::Integer, Result, Value);
}

/// LexSingleQuote: Integer: 'b'
AsmToken AsmLexer::LexSingleQuote() {
  int CurChar = getNextChar();

  if (CurChar == '\\')
    CurChar = getNextChar();

  if (CurChar == EOF)
    return ReturnError(TokStart, "unterminated single quote");

  CurChar = getNextChar();

  if (CurChar != '\'')
    return ReturnError(TokStart, "single quote way too long");

  // The idea here being that 'c' is basically just an integral
  // constant.
  StringRef Res = StringRef(TokStart,CurPtr - TokStart);
  long long Value;

  if (Res.startswith("\'\\")) {
    char theChar = Res[2];
    switch (theChar) {
      default: Value = theChar; break;
      case '\'': Value = '\''; break;
      case 't': Value = '\t'; break;
      case 'n': Value = '\n'; break;
      case 'b': Value = '\b'; break;
    }
  } else
    Value = TokStart[1];

  return AsmToken(AsmToken::Integer, Res, Value);
}


/// LexQuote: String: "..."
AsmToken AsmLexer::LexQuote() {
  int CurChar = getNextChar();
  // TODO: does gas allow multiline string constants?
  while (CurChar != '"') {
    if (CurChar == '\\') {
      // Allow \", etc.
      CurChar = getNextChar();
    }

    if (CurChar == EOF)
      return ReturnError(TokStart, "unterminated string constant");

    CurChar = getNextChar();
  }

  return AsmToken(AsmToken::String, StringRef(TokStart, CurPtr - TokStart));
}

StringRef AsmLexer::LexUntilEndOfStatement() {
  TokStart = CurPtr;

  while (!isAtStartOfComment(*CurPtr) &&    // Start of line comment.
         !isAtStatementSeparator(CurPtr) && // End of statement marker.
         *CurPtr != '\n' &&
         *CurPtr != '\r' &&
         (*CurPtr != 0 || CurPtr != CurBuf->getBufferEnd())) {
    ++CurPtr;
  }
  return StringRef(TokStart, CurPtr-TokStart);
}

bool AsmLexer::isAtStartOfComment(char Char) {
  // FIXME: This won't work for multi-character comment indicators like "//".
  return Char == *MAI.getCommentString();
}

bool AsmLexer::isAtStatementSeparator(const char *Ptr) {
  return strncmp(Ptr, MAI.getSeparatorString(),
                 strlen(MAI.getSeparatorString())) == 0;
}

AsmToken AsmLexer::LexToken() {
  TokStart = CurPtr;
  // This always consumes at least one character.
  int CurChar = getNextChar();

  if (isAtStartOfComment(CurChar))
    return LexLineComment();
  if (isAtStatementSeparator(TokStart)) {
    CurPtr += strlen(MAI.getSeparatorString()) - 1;
    return AsmToken(AsmToken::EndOfStatement,
                    StringRef(TokStart, strlen(MAI.getSeparatorString())));
  }

  switch (CurChar) {
  default:
    // Handle identifier: [a-zA-Z_.][a-zA-Z0-9_$.@]*
    if (isalpha(CurChar) || CurChar == '_' || CurChar == '.')
      return LexIdentifier();

    // Unknown character, emit an error.
    return ReturnError(TokStart, "invalid character in input");
  case EOF: return AsmToken(AsmToken::Eof, StringRef(TokStart, 0));
  case 0:
  case ' ':
  case '\t':
    // Ignore whitespace.
    return LexToken();
  case '\n': // FALL THROUGH.
  case '\r':
    return AsmToken(AsmToken::EndOfStatement, StringRef(TokStart, 1));
  case ':': return AsmToken(AsmToken::Colon, StringRef(TokStart, 1));
  case '+': return AsmToken(AsmToken::Plus, StringRef(TokStart, 1));
  case '-': return AsmToken(AsmToken::Minus, StringRef(TokStart, 1));
  case '~': return AsmToken(AsmToken::Tilde, StringRef(TokStart, 1));
  case '(': return AsmToken(AsmToken::LParen, StringRef(TokStart, 1));
  case ')': return AsmToken(AsmToken::RParen, StringRef(TokStart, 1));
  case '[': return AsmToken(AsmToken::LBrac, StringRef(TokStart, 1));
  case ']': return AsmToken(AsmToken::RBrac, StringRef(TokStart, 1));
  case '{': return AsmToken(AsmToken::LCurly, StringRef(TokStart, 1));
  case '}': return AsmToken(AsmToken::RCurly, StringRef(TokStart, 1));
  case '*': return AsmToken(AsmToken::Star, StringRef(TokStart, 1));
  case ',': return AsmToken(AsmToken::Comma, StringRef(TokStart, 1));
  case '$': return AsmToken(AsmToken::Dollar, StringRef(TokStart, 1));
  case '@': return AsmToken(AsmToken::At, StringRef(TokStart, 1));
  case '=':
    if (*CurPtr == '=')
      return ++CurPtr, AsmToken(AsmToken::EqualEqual, StringRef(TokStart, 2));
    return AsmToken(AsmToken::Equal, StringRef(TokStart, 1));
  case '|':
    if (*CurPtr == '|')
      return ++CurPtr, AsmToken(AsmToken::PipePipe, StringRef(TokStart, 2));
    return AsmToken(AsmToken::Pipe, StringRef(TokStart, 1));
  case '^': return AsmToken(AsmToken::Caret, StringRef(TokStart, 1));
  case '&':
    if (*CurPtr == '&')
      return ++CurPtr, AsmToken(AsmToken::AmpAmp, StringRef(TokStart, 2));
    return AsmToken(AsmToken::Amp, StringRef(TokStart, 1));
  case '!':
    if (*CurPtr == '=')
      return ++CurPtr, AsmToken(AsmToken::ExclaimEqual, StringRef(TokStart, 2));
    return AsmToken(AsmToken::Exclaim, StringRef(TokStart, 1));
  case '%': return AsmToken(AsmToken::Percent, StringRef(TokStart, 1));
  case '/': return LexSlash();
  case '#': return AsmToken(AsmToken::Hash, StringRef(TokStart, 1));
  case '\'': return LexSingleQuote();
  case '"': return LexQuote();
  case '0': case '1': case '2': case '3': case '4':
  case '5': case '6': case '7': case '8': case '9':
    return LexDigit();
  case '<':
    switch (*CurPtr) {
    case '<': return ++CurPtr, AsmToken(AsmToken::LessLess,
                                        StringRef(TokStart, 2));
    case '=': return ++CurPtr, AsmToken(AsmToken::LessEqual,
                                        StringRef(TokStart, 2));
    case '>': return ++CurPtr, AsmToken(AsmToken::LessGreater,
                                        StringRef(TokStart, 2));
    default: return AsmToken(AsmToken::Less, StringRef(TokStart, 1));
    }
  case '>':
    switch (*CurPtr) {
    case '>': return ++CurPtr, AsmToken(AsmToken::GreaterGreater,
                                        StringRef(TokStart, 2));
    case '=': return ++CurPtr, AsmToken(AsmToken::GreaterEqual,
                                        StringRef(TokStart, 2));
    default: return AsmToken(AsmToken::Greater, StringRef(TokStart, 1));
    }

  // TODO: Quoted identifiers (objc methods etc)
  // local labels: [0-9][:]
  // Forward/backward labels: [0-9][fb]
  // Integers, fp constants, character constants.
  }
}