llvm.org GIT mirror llvm / testing lib / Support / StringRef.cpp
testing

Tree @testing (Download .tar.gz)

StringRef.cpp @testingraw · 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
//===-- StringRef.cpp - Lightweight String References ---------------------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//

#include "llvm/ADT/StringRef.h"
#include "llvm/ADT/APFloat.h"
#include "llvm/ADT/APInt.h"
#include "llvm/ADT/Hashing.h"
#include "llvm/ADT/edit_distance.h"
#include <bitset>

using namespace llvm;

// MSVC emits references to this into the translation units which reference it.
#ifndef _MSC_VER
const size_t StringRef::npos;
#endif

static char ascii_tolower(char x) {
  if (x >= 'A' && x <= 'Z')
    return x - 'A' + 'a';
  return x;
}

static char ascii_toupper(char x) {
  if (x >= 'a' && x <= 'z')
    return x - 'a' + 'A';
  return x;
}

static bool ascii_isdigit(char x) {
  return x >= '0' && x <= '9';
}

// strncasecmp() is not available on non-POSIX systems, so define an
// alternative function here.
static int ascii_strncasecmp(const char *LHS, const char *RHS, size_t Length) {
  for (size_t I = 0; I < Length; ++I) {
    unsigned char LHC = ascii_tolower(LHS[I]);
    unsigned char RHC = ascii_tolower(RHS[I]);
    if (LHC != RHC)
      return LHC < RHC ? -1 : 1;
  }
  return 0;
}

/// compare_lower - Compare strings, ignoring case.
int StringRef::compare_lower(StringRef RHS) const {
  if (int Res = ascii_strncasecmp(Data, RHS.Data, std::min(Length, RHS.Length)))
    return Res;
  if (Length == RHS.Length)
    return 0;
  return Length < RHS.Length ? -1 : 1;
}

/// Check if this string starts with the given \p Prefix, ignoring case.
bool StringRef::startswith_lower(StringRef Prefix) const {
  return Length >= Prefix.Length &&
      ascii_strncasecmp(Data, Prefix.Data, Prefix.Length) == 0;
}

/// Check if this string ends with the given \p Suffix, ignoring case.
bool StringRef::endswith_lower(StringRef Suffix) const {
  return Length >= Suffix.Length &&
      ascii_strncasecmp(end() - Suffix.Length, Suffix.Data, Suffix.Length) == 0;
}

size_t StringRef::find_lower(char C, size_t From) const {
  char L = ascii_tolower(C);
  return find_if([L](char D) { return ascii_tolower(D) == L; }, From);
}

/// compare_numeric - Compare strings, handle embedded numbers.
int StringRef::compare_numeric(StringRef RHS) const {
  for (size_t I = 0, E = std::min(Length, RHS.Length); I != E; ++I) {
    // Check for sequences of digits.
    if (ascii_isdigit(Data[I]) && ascii_isdigit(RHS.Data[I])) {
      // The longer sequence of numbers is considered larger.
      // This doesn't really handle prefixed zeros well.
      size_t J;
      for (J = I + 1; J != E + 1; ++J) {
        bool ld = J < Length && ascii_isdigit(Data[J]);
        bool rd = J < RHS.Length && ascii_isdigit(RHS.Data[J]);
        if (ld != rd)
          return rd ? -1 : 1;
        if (!rd)
          break;
      }
      // The two number sequences have the same length (J-I), just memcmp them.
      if (int Res = compareMemory(Data + I, RHS.Data + I, J - I))
        return Res < 0 ? -1 : 1;
      // Identical number sequences, continue search after the numbers.
      I = J - 1;
      continue;
    }
    if (Data[I] != RHS.Data[I])
      return (unsigned char)Data[I] < (unsigned char)RHS.Data[I] ? -1 : 1;
  }
  if (Length == RHS.Length)
    return 0;
  return Length < RHS.Length ? -1 : 1;
}

// Compute the edit distance between the two given strings.
unsigned StringRef::edit_distance(llvm::StringRef Other,
                                  bool AllowReplacements,
                                  unsigned MaxEditDistance) const {
  return llvm::ComputeEditDistance(
      makeArrayRef(data(), size()),
      makeArrayRef(Other.data(), Other.size()),
      AllowReplacements, MaxEditDistance);
}

//===----------------------------------------------------------------------===//
// String Operations
//===----------------------------------------------------------------------===//

std::string StringRef::lower() const {
  std::string Result(size(), char());
  for (size_type i = 0, e = size(); i != e; ++i) {
    Result[i] = ascii_tolower(Data[i]);
  }
  return Result;
}

std::string StringRef::upper() const {
  std::string Result(size(), char());
  for (size_type i = 0, e = size(); i != e; ++i) {
    Result[i] = ascii_toupper(Data[i]);
  }
  return Result;
}

//===----------------------------------------------------------------------===//
// String Searching
//===----------------------------------------------------------------------===//


/// find - Search for the first string \arg Str in the string.
///
/// \return - The index of the first occurrence of \arg Str, or npos if not
/// found.
size_t StringRef::find(StringRef Str, size_t From) const {
  if (From > Length)
    return npos;

  const char *Start = Data + From;
  size_t Size = Length - From;

  const char *Needle = Str.data();
  size_t N = Str.size();
  if (N == 0)
    return From;
  if (Size < N)
    return npos;
  if (N == 1) {
    const char *Ptr = (const char *)::memchr(Start, Needle[0], Size);
    return Ptr == nullptr ? npos : Ptr - Data;
  }

  const char *Stop = Start + (Size - N + 1);

  // For short haystacks or unsupported needles fall back to the naive algorithm
  if (Size < 16 || N > 255) {
    do {
      if (std::memcmp(Start, Needle, N) == 0)
        return Start - Data;
      ++Start;
    } while (Start < Stop);
    return npos;
  }

  // Build the bad char heuristic table, with uint8_t to reduce cache thrashing.
  uint8_t BadCharSkip[256];
  std::memset(BadCharSkip, N, 256);
  for (unsigned i = 0; i != N-1; ++i)
    BadCharSkip[(uint8_t)Str[i]] = N-1-i;

  do {
    uint8_t Last = Start[N - 1];
    if (LLVM_UNLIKELY(Last == (uint8_t)Needle[N - 1]))
      if (std::memcmp(Start, Needle, N - 1) == 0)
        return Start - Data;

    // Otherwise skip the appropriate number of bytes.
    Start += BadCharSkip[Last];
  } while (Start < Stop);

  return npos;
}

size_t StringRef::find_lower(StringRef Str, size_t From) const {
  StringRef This = substr(From);
  while (This.size() >= Str.size()) {
    if (This.startswith_lower(Str))
      return From;
    This = This.drop_front();
    ++From;
  }
  return npos;
}

size_t StringRef::rfind_lower(char C, size_t From) const {
  From = std::min(From, Length);
  size_t i = From;
  while (i != 0) {
    --i;
    if (ascii_tolower(Data[i]) == ascii_tolower(C))
      return i;
  }
  return npos;
}

/// rfind - Search for the last string \arg Str in the string.
///
/// \return - The index of the last occurrence of \arg Str, or npos if not
/// found.
size_t StringRef::rfind(StringRef Str) const {
  size_t N = Str.size();
  if (N > Length)
    return npos;
  for (size_t i = Length - N + 1, e = 0; i != e;) {
    --i;
    if (substr(i, N).equals(Str))
      return i;
  }
  return npos;
}

size_t StringRef::rfind_lower(StringRef Str) const {
  size_t N = Str.size();
  if (N > Length)
    return npos;
  for (size_t i = Length - N + 1, e = 0; i != e;) {
    --i;
    if (substr(i, N).equals_lower(Str))
      return i;
  }
  return npos;
}

/// find_first_of - Find the first character in the string that is in \arg
/// Chars, or npos if not found.
///
/// Note: O(size() + Chars.size())
StringRef::size_type StringRef::find_first_of(StringRef Chars,
                                              size_t From) const {
  std::bitset<1 << CHAR_BIT> CharBits;
  for (size_type i = 0; i != Chars.size(); ++i)
    CharBits.set((unsigned char)Chars[i]);

  for (size_type i = std::min(From, Length), e = Length; i != e; ++i)
    if (CharBits.test((unsigned char)Data[i]))
      return i;
  return npos;
}

/// find_first_not_of - Find the first character in the string that is not
/// \arg C or npos if not found.
StringRef::size_type StringRef::find_first_not_of(char C, size_t From) const {
  for (size_type i = std::min(From, Length), e = Length; i != e; ++i)
    if (Data[i] != C)
      return i;
  return npos;
}

/// find_first_not_of - Find the first character in the string that is not
/// in the string \arg Chars, or npos if not found.
///
/// Note: O(size() + Chars.size())
StringRef::size_type StringRef::find_first_not_of(StringRef Chars,
                                                  size_t From) const {
  std::bitset<1 << CHAR_BIT> CharBits;
  for (size_type i = 0; i != Chars.size(); ++i)
    CharBits.set((unsigned char)Chars[i]);

  for (size_type i = std::min(From, Length), e = Length; i != e; ++i)
    if (!CharBits.test((unsigned char)Data[i]))
      return i;
  return npos;
}

/// find_last_of - Find the last character in the string that is in \arg C,
/// or npos if not found.
///
/// Note: O(size() + Chars.size())
StringRef::size_type StringRef::find_last_of(StringRef Chars,
                                             size_t From) const {
  std::bitset<1 << CHAR_BIT> CharBits;
  for (size_type i = 0; i != Chars.size(); ++i)
    CharBits.set((unsigned char)Chars[i]);

  for (size_type i = std::min(From, Length) - 1, e = -1; i != e; --i)
    if (CharBits.test((unsigned char)Data[i]))
      return i;
  return npos;
}

/// find_last_not_of - Find the last character in the string that is not
/// \arg C, or npos if not found.
StringRef::size_type StringRef::find_last_not_of(char C, size_t From) const {
  for (size_type i = std::min(From, Length) - 1, e = -1; i != e; --i)
    if (Data[i] != C)
      return i;
  return npos;
}

/// find_last_not_of - Find the last character in the string that is not in
/// \arg Chars, or npos if not found.
///
/// Note: O(size() + Chars.size())
StringRef::size_type StringRef::find_last_not_of(StringRef Chars,
                                                 size_t From) const {
  std::bitset<1 << CHAR_BIT> CharBits;
  for (size_type i = 0, e = Chars.size(); i != e; ++i)
    CharBits.set((unsigned char)Chars[i]);

  for (size_type i = std::min(From, Length) - 1, e = -1; i != e; --i)
    if (!CharBits.test((unsigned char)Data[i]))
      return i;
  return npos;
}

void StringRef::split(SmallVectorImpl<StringRef> &A,
                      StringRef Separator, int MaxSplit,
                      bool KeepEmpty) const {
  StringRef S = *this;

  // Count down from MaxSplit. When MaxSplit is -1, this will just split
  // "forever". This doesn't support splitting more than 2^31 times
  // intentionally; if we ever want that we can make MaxSplit a 64-bit integer
  // but that seems unlikely to be useful.
  while (MaxSplit-- != 0) {
    size_t Idx = S.find(Separator);
    if (Idx == npos)
      break;

    // Push this split.
    if (KeepEmpty || Idx > 0)
      A.push_back(S.slice(0, Idx));

    // Jump forward.
    S = S.slice(Idx + Separator.size(), npos);
  }

  // Push the tail.
  if (KeepEmpty || !S.empty())
    A.push_back(S);
}

void StringRef::split(SmallVectorImpl<StringRef> &A, char Separator,
                      int MaxSplit, bool KeepEmpty) const {
  StringRef S = *this;

  // Count down from MaxSplit. When MaxSplit is -1, this will just split
  // "forever". This doesn't support splitting more than 2^31 times
  // intentionally; if we ever want that we can make MaxSplit a 64-bit integer
  // but that seems unlikely to be useful.
  while (MaxSplit-- != 0) {
    size_t Idx = S.find(Separator);
    if (Idx == npos)
      break;

    // Push this split.
    if (KeepEmpty || Idx > 0)
      A.push_back(S.slice(0, Idx));

    // Jump forward.
    S = S.slice(Idx + 1, npos);
  }

  // Push the tail.
  if (KeepEmpty || !S.empty())
    A.push_back(S);
}

//===----------------------------------------------------------------------===//
// Helpful Algorithms
//===----------------------------------------------------------------------===//

/// count - Return the number of non-overlapped occurrences of \arg Str in
/// the string.
size_t StringRef::count(StringRef Str) const {
  size_t Count = 0;
  size_t N = Str.size();
  if (N > Length)
    return 0;
  for (size_t i = 0, e = Length - N + 1; i != e; ++i)
    if (substr(i, N).equals(Str))
      ++Count;
  return Count;
}

static unsigned GetAutoSenseRadix(StringRef &Str) {
  if (Str.empty())
    return 10;

  if (Str.startswith("0x") || Str.startswith("0X")) {
    Str = Str.substr(2);
    return 16;
  }
  
  if (Str.startswith("0b") || Str.startswith("0B")) {
    Str = Str.substr(2);
    return 2;
  }

  if (Str.startswith("0o")) {
    Str = Str.substr(2);
    return 8;
  }

  if (Str[0] == '0' && Str.size() > 1 && ascii_isdigit(Str[1])) {
    Str = Str.substr(1);
    return 8;
  }

  return 10;
}

bool llvm::consumeUnsignedInteger(StringRef &Str, unsigned Radix,
                                  unsigned long long &Result) {
  // Autosense radix if not specified.
  if (Radix == 0)
    Radix = GetAutoSenseRadix(Str);

  // Empty strings (after the radix autosense) are invalid.
  if (Str.empty()) return true;

  // Parse all the bytes of the string given this radix.  Watch for overflow.
  StringRef Str2 = Str;
  Result = 0;
  while (!Str2.empty()) {
    unsigned CharVal;
    if (Str2[0] >= '0' && Str2[0] <= '9')
      CharVal = Str2[0] - '0';
    else if (Str2[0] >= 'a' && Str2[0] <= 'z')
      CharVal = Str2[0] - 'a' + 10;
    else if (Str2[0] >= 'A' && Str2[0] <= 'Z')
      CharVal = Str2[0] - 'A' + 10;
    else
      break;

    // If the parsed value is larger than the integer radix, we cannot
    // consume any more characters.
    if (CharVal >= Radix)
      break;

    // Add in this character.
    unsigned long long PrevResult = Result;
    Result = Result * Radix + CharVal;

    // Check for overflow by shifting back and seeing if bits were lost.
    if (Result / Radix < PrevResult)
      return true;

    Str2 = Str2.substr(1);
  }

  // We consider the operation a failure if no characters were consumed
  // successfully.
  if (Str.size() == Str2.size())
    return true;

  Str = Str2;
  return false;
}

bool llvm::consumeSignedInteger(StringRef &Str, unsigned Radix,
                                long long &Result) {
  unsigned long long ULLVal;

  // Handle positive strings first.
  if (Str.empty() || Str.front() != '-') {
    if (consumeUnsignedInteger(Str, Radix, ULLVal) ||
        // Check for value so large it overflows a signed value.
        (long long)ULLVal < 0)
      return true;
    Result = ULLVal;
    return false;
  }

  // Get the positive part of the value.
  StringRef Str2 = Str.drop_front(1);
  if (consumeUnsignedInteger(Str2, Radix, ULLVal) ||
      // Reject values so large they'd overflow as negative signed, but allow
      // "-0".  This negates the unsigned so that the negative isn't undefined
      // on signed overflow.
      (long long)-ULLVal > 0)
    return true;

  Str = Str2;
  Result = -ULLVal;
  return false;
}

/// GetAsUnsignedInteger - Workhorse method that converts a integer character
/// sequence of radix up to 36 to an unsigned long long value.
bool llvm::getAsUnsignedInteger(StringRef Str, unsigned Radix,
                                unsigned long long &Result) {
  if (consumeUnsignedInteger(Str, Radix, Result))
    return true;

  // For getAsUnsignedInteger, we require the whole string to be consumed or
  // else we consider it a failure.
  return !Str.empty();
}

bool llvm::getAsSignedInteger(StringRef Str, unsigned Radix,
                              long long &Result) {
  if (consumeSignedInteger(Str, Radix, Result))
    return true;

  // For getAsSignedInteger, we require the whole string to be consumed or else
  // we consider it a failure.
  return !Str.empty();
}

bool StringRef::getAsInteger(unsigned Radix, APInt &Result) const {
  StringRef Str = *this;

  // Autosense radix if not specified.
  if (Radix == 0)
    Radix = GetAutoSenseRadix(Str);

  assert(Radix > 1 && Radix <= 36);

  // Empty strings (after the radix autosense) are invalid.
  if (Str.empty()) return true;

  // Skip leading zeroes.  This can be a significant improvement if
  // it means we don't need > 64 bits.
  while (!Str.empty() && Str.front() == '0')
    Str = Str.substr(1);

  // If it was nothing but zeroes....
  if (Str.empty()) {
    Result = APInt(64, 0);
    return false;
  }

  // (Over-)estimate the required number of bits.
  unsigned Log2Radix = 0;
  while ((1U << Log2Radix) < Radix) Log2Radix++;
  bool IsPowerOf2Radix = ((1U << Log2Radix) == Radix);

  unsigned BitWidth = Log2Radix * Str.size();
  if (BitWidth < Result.getBitWidth())
    BitWidth = Result.getBitWidth(); // don't shrink the result
  else if (BitWidth > Result.getBitWidth())
    Result = Result.zext(BitWidth);

  APInt RadixAP, CharAP; // unused unless !IsPowerOf2Radix
  if (!IsPowerOf2Radix) {
    // These must have the same bit-width as Result.
    RadixAP = APInt(BitWidth, Radix);
    CharAP = APInt(BitWidth, 0);
  }

  // Parse all the bytes of the string given this radix.
  Result = 0;
  while (!Str.empty()) {
    unsigned CharVal;
    if (Str[0] >= '0' && Str[0] <= '9')
      CharVal = Str[0]-'0';
    else if (Str[0] >= 'a' && Str[0] <= 'z')
      CharVal = Str[0]-'a'+10;
    else if (Str[0] >= 'A' && Str[0] <= 'Z')
      CharVal = Str[0]-'A'+10;
    else
      return true;

    // If the parsed value is larger than the integer radix, the string is
    // invalid.
    if (CharVal >= Radix)
      return true;

    // Add in this character.
    if (IsPowerOf2Radix) {
      Result <<= Log2Radix;
      Result |= CharVal;
    } else {
      Result *= RadixAP;
      CharAP = CharVal;
      Result += CharAP;
    }

    Str = Str.substr(1);
  }

  return false;
}

bool StringRef::getAsDouble(double &Result, bool AllowInexact) const {
  APFloat F(0.0);
  APFloat::opStatus Status =
      F.convertFromString(*this, APFloat::rmNearestTiesToEven);
  if (Status != APFloat::opOK) {
    if (!AllowInexact || Status != APFloat::opInexact)
      return true;
  }

  Result = F.convertToDouble();
  return false;
}

// Implementation of StringRef hashing.
hash_code llvm::hash_value(StringRef S) {
  return hash_combine_range(S.begin(), S.end());
}