aboutsummaryrefslogtreecommitdiffstats
path: root/utils/TableGen/TGLexer.cpp
blob: 4498e305b02879a550799ab4d4243bed8a07146f (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
441
442
443
444
445
446
447
448
449
//===- TGLexer.cpp - Lexer for TableGen -----------------------------------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// Implement the Lexer for TableGen.
//
//===----------------------------------------------------------------------===//

#include "TGLexer.h"
#include "llvm/Support/SourceMgr.h"
#include "llvm/Support/MemoryBuffer.h"
#include "llvm/Config/config.h"
#include <cctype>
#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <cerrno>
using namespace llvm;

TGLexer::TGLexer(SourceMgr &SM) : SrcMgr(SM) {
  CurBuffer = 0;
  CurBuf = SrcMgr.getMemoryBuffer(CurBuffer);
  CurPtr = CurBuf->getBufferStart();
  TokStart = 0;
}

SMLoc TGLexer::getLoc() const {
  return SMLoc::getFromPointer(TokStart);
}


/// ReturnError - Set the error to the specified string at the specified
/// location.  This is defined to always return tgtok::Error.
tgtok::TokKind TGLexer::ReturnError(const char *Loc, const std::string &Msg) {
  PrintError(Loc, Msg);
  return tgtok::Error;
}


void TGLexer::PrintError(const char *Loc, const std::string &Msg) const {
  SrcMgr.PrintMessage(SMLoc::getFromPointer(Loc), Msg, "error");
}

void TGLexer::PrintError(SMLoc Loc, const std::string &Msg) const {
  SrcMgr.PrintMessage(Loc, Msg, "error");
}


int TGLexer::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.
    
    // If this is the end of an included file, pop the parent file off the
    // include stack.
    SMLoc ParentIncludeLoc = SrcMgr.getParentIncludeLoc(CurBuffer);
    if (ParentIncludeLoc != SMLoc()) {
      CurBuffer = SrcMgr.FindBufferContainingLoc(ParentIncludeLoc);
      CurBuf = SrcMgr.getMemoryBuffer(CurBuffer);
      CurPtr = ParentIncludeLoc.getPointer();
      return getNextChar();
    }
    
    // Otherwise, return end of file.
    --CurPtr;  // Another call to lex will return EOF again.  
    return EOF;
  }
  case '\n':
  case '\r':
    // Handle the newline character by ignoring it and incrementing the line
    // count.  However, be careful about 'dos style' files with \n\r in them.
    // Only treat a \n\r or \r\n as a single line.
    if ((*CurPtr == '\n' || (*CurPtr == '\r')) &&
        *CurPtr != CurChar)
      ++CurPtr;  // Eat the two char newline sequence.
    return '\n';
  }  
}

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

  switch (CurChar) {
  default:
    // Handle letters: [a-zA-Z_]
    if (isalpha(CurChar) || CurChar == '_' || CurChar == '#')
      return LexIdentifier();
      
    // Unknown character, emit an error.
    return ReturnError(TokStart, "Unexpected character");
  case EOF: return tgtok::Eof;
  case ':': return tgtok::colon;
  case ';': return tgtok::semi;
  case '.': return tgtok::period;
  case ',': return tgtok::comma;
  case '<': return tgtok::less;
  case '>': return tgtok::greater;
  case ']': return tgtok::r_square;
  case '{': return tgtok::l_brace;
  case '}': return tgtok::r_brace;
  case '(': return tgtok::l_paren;
  case ')': return tgtok::r_paren;
  case '=': return tgtok::equal;
  case '?': return tgtok::question;
      
  case 0:
  case ' ':
  case '\t':
  case '\n':
  case '\r':
    // Ignore whitespace.
    return LexToken();
  case '/':
    // If this is the start of a // comment, skip until the end of the line or
    // the end of the buffer.
    if (*CurPtr == '/')
      SkipBCPLComment();
    else if (*CurPtr == '*') {
      if (SkipCComment())
        return tgtok::Error;
    } else // Otherwise, this is an error.
      return ReturnError(TokStart, "Unexpected character");
    return LexToken();
  case '-': case '+':
  case '0': case '1': case '2': case '3': case '4': case '5': case '6':
  case '7': case '8': case '9':  
    return LexNumber();
  case '"': return LexString();
  case '$': return LexVarName();
  case '[': return LexBracket();
  case '!': return LexExclaim();
  }
}

/// LexString - Lex "[^"]*"
tgtok::TokKind TGLexer::LexString() {
  const char *StrStart = CurPtr;
  
  CurStrVal = "";
  
  while (*CurPtr != '"') {
    // If we hit the end of the buffer, report an error.
    if (*CurPtr == 0 && CurPtr == CurBuf->getBufferEnd())
      return ReturnError(StrStart, "End of file in string literal");
    
    if (*CurPtr == '\n' || *CurPtr == '\r')
      return ReturnError(StrStart, "End of line in string literal");
    
    if (*CurPtr != '\\') {
      CurStrVal += *CurPtr++;
      continue;
    }

    ++CurPtr;
    
    switch (*CurPtr) {
    case '\\': case '\'': case '"':
      // These turn into their literal character.
      CurStrVal += *CurPtr++;
      break;
    case 't':
      CurStrVal += '\t';
      ++CurPtr;
      break;
    case 'n':
      CurStrVal += '\n';
      ++CurPtr;
      break;
        
    case '\n':
    case '\r':
      return ReturnError(CurPtr, "escaped newlines not supported in tblgen");

    // If we hit the end of the buffer, report an error.
    case '\0':
      if (CurPtr == CurBuf->getBufferEnd())
        return ReturnError(StrStart, "End of file in string literal");
      // FALL THROUGH
    default:
      return ReturnError(CurPtr, "invalid escape in string literal");
    }
  }
  
  ++CurPtr;
  return tgtok::StrVal;
}

tgtok::TokKind TGLexer::LexVarName() {
  if (!isalpha(CurPtr[0]) && CurPtr[0] != '_')
    return ReturnError(TokStart, "Invalid variable name");
  
  // Otherwise, we're ok, consume the rest of the characters.
  const char *VarNameStart = CurPtr++;
  
  while (isalpha(*CurPtr) || isdigit(*CurPtr) || *CurPtr == '_')
    ++CurPtr;

  CurStrVal.assign(VarNameStart, CurPtr);
  return tgtok::VarName;
}


tgtok::TokKind TGLexer::LexIdentifier() {
  // The first letter is [a-zA-Z_].
  const char *IdentStart = TokStart;
  
  // Match the rest of the identifier regex: [0-9a-zA-Z_]*
  while (isalpha(*CurPtr) || isdigit(*CurPtr) || *CurPtr == '_'
         || *CurPtr == '#') {
    // If this contains a '#', make sure it's value
    if (*CurPtr == '#') {
      if (strncmp(CurPtr, "#NAME#", 6) != 0) {
        return tgtok::Error;
      }
      CurPtr += 6;
    }
    else {
      ++CurPtr;
    }
  }
  
  
  // Check to see if this identifier is a keyword.
  unsigned Len = CurPtr-IdentStart;
  
  if (Len == 3 && !memcmp(IdentStart, "int", 3)) return tgtok::Int;
  if (Len == 3 && !memcmp(IdentStart, "bit", 3)) return tgtok::Bit;
  if (Len == 4 && !memcmp(IdentStart, "bits", 4)) return tgtok::Bits;
  if (Len == 6 && !memcmp(IdentStart, "string", 6)) return tgtok::String;
  if (Len == 4 && !memcmp(IdentStart, "list", 4)) return tgtok::List;
  if (Len == 4 && !memcmp(IdentStart, "code", 4)) return tgtok::Code;
  if (Len == 3 && !memcmp(IdentStart, "dag", 3)) return tgtok::Dag;
  
  if (Len == 5 && !memcmp(IdentStart, "class", 5)) return tgtok::Class;
  if (Len == 3 && !memcmp(IdentStart, "def", 3)) return tgtok::Def;
  if (Len == 4 && !memcmp(IdentStart, "defm", 4)) return tgtok::Defm;
  if (Len == 10 && !memcmp(IdentStart, "multiclass", 10))
    return tgtok::MultiClass;
  if (Len == 5 && !memcmp(IdentStart, "field", 5)) return tgtok::Field;
  if (Len == 3 && !memcmp(IdentStart, "let", 3)) return tgtok::Let;
  if (Len == 2 && !memcmp(IdentStart, "in", 2)) return tgtok::In;
  
  if (Len == 7 && !memcmp(IdentStart, "include", 7)) {
    if (LexInclude()) return tgtok::Error;
    return Lex();
  }
    
  CurStrVal.assign(IdentStart, CurPtr);
  return tgtok::Id;
}

/// LexInclude - We just read the "include" token.  Get the string token that
/// comes next and enter the include.
bool TGLexer::LexInclude() {
  // The token after the include must be a string.
  tgtok::TokKind Tok = LexToken();
  if (Tok == tgtok::Error) return true;
  if (Tok != tgtok::StrVal) {
    PrintError(getLoc(), "Expected filename after include");
    return true;
  }

  // Get the string.
  std::string Filename = CurStrVal;

  
  CurBuffer = SrcMgr.AddIncludeFile(Filename, SMLoc::getFromPointer(CurPtr));
  if (CurBuffer == -1) {
    PrintError(getLoc(), "Could not find include file '" + Filename + "'");
    return true;
  }
  
  // Save the line number and lex buffer of the includer.
  CurBuf = SrcMgr.getMemoryBuffer(CurBuffer);
  CurPtr = CurBuf->getBufferStart();
  return false;
}

void TGLexer::SkipBCPLComment() {
  ++CurPtr;  // skip the second slash.
  while (1) {
    switch (*CurPtr) {
    case '\n':
    case '\r':
      return;  // Newline is end of comment.
    case 0:
      // If this is the end of the buffer, end the comment.
      if (CurPtr == CurBuf->getBufferEnd())
        return;
      break;
    }
    // Otherwise, skip the character.
    ++CurPtr;
  }
}

/// SkipCComment - This skips C-style /**/ comments.  The only difference from C
/// is that we allow nesting.
bool TGLexer::SkipCComment() {
  ++CurPtr;  // skip the star.
  unsigned CommentDepth = 1;
  
  while (1) {
    int CurChar = getNextChar();
    switch (CurChar) {
    case EOF:
      PrintError(TokStart, "Unterminated comment!");
      return true;
    case '*':
      // End of the comment?
      if (CurPtr[0] != '/') break;
      
      ++CurPtr;   // End the */.
      if (--CommentDepth == 0)
        return false;
      break;
    case '/':
      // Start of a nested comment?
      if (CurPtr[0] != '*') break;
      ++CurPtr;
      ++CommentDepth;
      break;
    }
  }
}

/// LexNumber - Lex:
///    [-+]?[0-9]+
///    0x[0-9a-fA-F]+
///    0b[01]+
tgtok::TokKind TGLexer::LexNumber() {
  if (CurPtr[-1] == '0') {
    if (CurPtr[0] == 'x') {
      ++CurPtr;
      const char *NumStart = CurPtr;
      while (isxdigit(CurPtr[0]))
        ++CurPtr;
      
      // Requires at least one hex digit.
      if (CurPtr == NumStart)
        return ReturnError(TokStart, "Invalid hexadecimal number");

      errno = 0;
      CurIntVal = strtoll(NumStart, 0, 16);
      if (errno == EINVAL)
        return ReturnError(TokStart, "Invalid hexadecimal number");
      if (errno == ERANGE) {
        errno = 0;
        CurIntVal = (int64_t)strtoull(NumStart, 0, 16);
        if (errno == EINVAL)
          return ReturnError(TokStart, "Invalid hexadecimal number");
        if (errno == ERANGE)
          return ReturnError(TokStart, "Hexadecimal number out of range");
      }
      return tgtok::IntVal;
    } else if (CurPtr[0] == 'b') {
      ++CurPtr;
      const char *NumStart = CurPtr;
      while (CurPtr[0] == '0' || CurPtr[0] == '1')
        ++CurPtr;

      // Requires at least one binary digit.
      if (CurPtr == NumStart)
        return ReturnError(CurPtr-2, "Invalid binary number");
      CurIntVal = strtoll(NumStart, 0, 2);
      return tgtok::IntVal;
    }
  }

  // Check for a sign without a digit.
  if (!isdigit(CurPtr[0])) {
    if (CurPtr[-1] == '-')
      return tgtok::minus;
    else if (CurPtr[-1] == '+')
      return tgtok::plus;
  }
  
  while (isdigit(CurPtr[0]))
    ++CurPtr;
  CurIntVal = strtoll(TokStart, 0, 10);
  return tgtok::IntVal;
}

/// LexBracket - We just read '['.  If this is a code block, return it,
/// otherwise return the bracket.  Match: '[' and '[{ ( [^}]+ | }[^]] )* }]'
tgtok::TokKind TGLexer::LexBracket() {
  if (CurPtr[0] != '{')
    return tgtok::l_square;
  ++CurPtr;
  const char *CodeStart = CurPtr;
  while (1) {
    int Char = getNextChar();
    if (Char == EOF) break;
    
    if (Char != '}') continue;
    
    Char = getNextChar();
    if (Char == EOF) break;
    if (Char == ']') {
      CurStrVal.assign(CodeStart, CurPtr-2);
      return tgtok::CodeFragment;
    }
  }
  
  return ReturnError(CodeStart-2, "Unterminated Code Block");
}

/// LexExclaim - Lex '!' and '![a-zA-Z]+'.
tgtok::TokKind TGLexer::LexExclaim() {
  if (!isalpha(*CurPtr))
    return ReturnError(CurPtr-1, "Invalid \"!operator\"");
  
  const char *Start = CurPtr++;
  while (isalpha(*CurPtr))
    ++CurPtr;
  
  // Check to see which operator this is.
  unsigned Len = CurPtr-Start;
  
  if (Len == 3  && !memcmp(Start, "con", 3)) return tgtok::XConcat;
  if (Len == 3  && !memcmp(Start, "sra", 3)) return tgtok::XSRA;
  if (Len == 3  && !memcmp(Start, "srl", 3)) return tgtok::XSRL;
  if (Len == 3  && !memcmp(Start, "shl", 3)) return tgtok::XSHL;
  if (Len == 9  && !memcmp(Start, "strconcat", 9))   return tgtok::XStrConcat;
  if (Len == 10 && !memcmp(Start, "nameconcat", 10)) return tgtok::XNameConcat;
  if (Len == 5 && !memcmp(Start, "subst", 5)) return tgtok::XSubst;
  if (Len == 7 && !memcmp(Start, "foreach", 7)) return tgtok::XForEach;
  if (Len == 4 && !memcmp(Start, "cast", 4)) return tgtok::XCast;
  if (Len == 3 && !memcmp(Start, "car", 3)) return tgtok::XCar;
  if (Len == 3 && !memcmp(Start, "cdr", 3)) return tgtok::XCdr;
  if (Len == 4 && !memcmp(Start, "null", 4)) return tgtok::XNull;
  if (Len == 2 && !memcmp(Start, "if", 2)) return tgtok::XIf;

  return ReturnError(Start-1, "Unknown operator");
}