llvm.org GIT mirror llvm / release_34 include / llvm / ADT / StringRef.h
release_34

Tree @release_34 (Download .tar.gz)

StringRef.h @release_34raw · 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
//===--- StringRef.h - Constant String Reference Wrapper --------*- C++ -*-===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//

#ifndef LLVM_ADT_STRINGREF_H
#define LLVM_ADT_STRINGREF_H

#include "llvm/Support/type_traits.h"
#include <algorithm>
#include <cassert>
#include <cstring>
#include <limits>
#include <string>
#include <utility>

namespace llvm {
  template <typename T>
  class SmallVectorImpl;
  class APInt;
  class hash_code;
  class StringRef;

  /// Helper functions for StringRef::getAsInteger.
  bool getAsUnsignedInteger(StringRef Str, unsigned Radix,
                            unsigned long long &Result);

  bool getAsSignedInteger(StringRef Str, unsigned Radix, long long &Result);

  /// StringRef - Represent a constant reference to a string, i.e. a character
  /// array and a length, which need not be null terminated.
  ///
  /// This class does not own the string data, it is expected to be used in
  /// situations where the character data resides in some other buffer, whose
  /// lifetime extends past that of the StringRef. For this reason, it is not in
  /// general safe to store a StringRef.
  class StringRef {
  public:
    typedef const char *iterator;
    typedef const char *const_iterator;
    static const size_t npos = ~size_t(0);
    typedef size_t size_type;

  private:
    /// The start of the string, in an external buffer.
    const char *Data;

    /// The length of the string.
    size_t Length;

    // Workaround PR5482: nearly all gcc 4.x miscompile StringRef and std::min()
    // Changing the arg of min to be an integer, instead of a reference to an
    // integer works around this bug.
    static size_t min(size_t a, size_t b) { return a < b ? a : b; }
    static size_t max(size_t a, size_t b) { return a > b ? a : b; }

    // Workaround memcmp issue with null pointers (undefined behavior)
    // by providing a specialized version
    static int compareMemory(const char *Lhs, const char *Rhs, size_t Length) {
      if (Length == 0) { return 0; }
      return ::memcmp(Lhs,Rhs,Length);
    }

  public:
    /// @name Constructors
    /// @{

    /// Construct an empty string ref.
    /*implicit*/ StringRef() : Data(0), Length(0) {}

    /// Construct a string ref from a cstring.
    /*implicit*/ StringRef(const char *Str)
      : Data(Str) {
        assert(Str && "StringRef cannot be built from a NULL argument");
        Length = ::strlen(Str); // invoking strlen(NULL) is undefined behavior
      }

    /// Construct a string ref from a pointer and length.
    /*implicit*/ StringRef(const char *data, size_t length)
      : Data(data), Length(length) {
        assert((data || length == 0) &&
        "StringRef cannot be built from a NULL argument with non-null length");
      }

    /// Construct a string ref from an std::string.
    /*implicit*/ StringRef(const std::string &Str)
      : Data(Str.data()), Length(Str.length()) {}

    /// @}
    /// @name Iterators
    /// @{

    iterator begin() const { return Data; }

    iterator end() const { return Data + Length; }

    /// @}
    /// @name String Operations
    /// @{

    /// data - Get a pointer to the start of the string (which may not be null
    /// terminated).
    const char *data() const { return Data; }

    /// empty - Check if the string is empty.
    bool empty() const { return Length == 0; }

    /// size - Get the string size.
    size_t size() const { return Length; }

    /// front - Get the first character in the string.
    char front() const {
      assert(!empty());
      return Data[0];
    }

    /// back - Get the last character in the string.
    char back() const {
      assert(!empty());
      return Data[Length-1];
    }

    /// equals - Check for string equality, this is more efficient than
    /// compare() when the relative ordering of inequal strings isn't needed.
    bool equals(StringRef RHS) const {
      return (Length == RHS.Length &&
              compareMemory(Data, RHS.Data, RHS.Length) == 0);
    }

    /// equals_lower - Check for string equality, ignoring case.
    bool equals_lower(StringRef RHS) const {
      return Length == RHS.Length && compare_lower(RHS) == 0;
    }

    /// compare - Compare two strings; the result is -1, 0, or 1 if this string
    /// is lexicographically less than, equal to, or greater than the \p RHS.
    int compare(StringRef RHS) const {
      // Check the prefix for a mismatch.
      if (int Res = compareMemory(Data, RHS.Data, min(Length, RHS.Length)))
        return Res < 0 ? -1 : 1;

      // Otherwise the prefixes match, so we only need to check the lengths.
      if (Length == RHS.Length)
        return 0;
      return Length < RHS.Length ? -1 : 1;
    }

    /// compare_lower - Compare two strings, ignoring case.
    int compare_lower(StringRef RHS) const;

    /// compare_numeric - Compare two strings, treating sequences of digits as
    /// numbers.
    int compare_numeric(StringRef RHS) const;

    /// \brief Determine the edit distance between this string and another
    /// string.
    ///
    /// \param Other the string to compare this string against.
    ///
    /// \param AllowReplacements whether to allow character
    /// replacements (change one character into another) as a single
    /// operation, rather than as two operations (an insertion and a
    /// removal).
    ///
    /// \param MaxEditDistance If non-zero, the maximum edit distance that
    /// this routine is allowed to compute. If the edit distance will exceed
    /// that maximum, returns \c MaxEditDistance+1.
    ///
    /// \returns the minimum number of character insertions, removals,
    /// or (if \p AllowReplacements is \c true) replacements needed to
    /// transform one of the given strings into the other. If zero,
    /// the strings are identical.
    unsigned edit_distance(StringRef Other, bool AllowReplacements = true,
                           unsigned MaxEditDistance = 0) const;

    /// str - Get the contents as an std::string.
    std::string str() const {
      if (Data == 0) return std::string();
      return std::string(Data, Length);
    }

    /// @}
    /// @name Operator Overloads
    /// @{

    char operator[](size_t Index) const {
      assert(Index < Length && "Invalid index!");
      return Data[Index];
    }

    /// @}
    /// @name Type Conversions
    /// @{

    operator std::string() const {
      return str();
    }

    /// @}
    /// @name String Predicates
    /// @{

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

    /// Check if this string starts with the given \p Prefix, ignoring case.
    bool startswith_lower(StringRef Prefix) const;

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

    /// Check if this string ends with the given \p Suffix, ignoring case.
    bool endswith_lower(StringRef Suffix) const;

    /// @}
    /// @name String Searching
    /// @{

    /// Search for the first character \p C in the string.
    ///
    /// \returns The index of the first occurrence of \p C, or npos if not
    /// found.
    size_t find(char C, size_t From = 0) const {
      for (size_t i = min(From, Length), e = Length; i != e; ++i)
        if (Data[i] == C)
          return i;
      return npos;
    }

    /// Search for the first string \p Str in the string.
    ///
    /// \returns The index of the first occurrence of \p Str, or npos if not
    /// found.
    size_t find(StringRef Str, size_t From = 0) const;

    /// Search for the last character \p C in the string.
    ///
    /// \returns The index of the last occurrence of \p C, or npos if not
    /// found.
    size_t rfind(char C, size_t From = npos) const {
      From = min(From, Length);
      size_t i = From;
      while (i != 0) {
        --i;
        if (Data[i] == C)
          return i;
      }
      return npos;
    }

    /// Search for the last string \p Str in the string.
    ///
    /// \returns The index of the last occurrence of \p Str, or npos if not
    /// found.
    size_t rfind(StringRef Str) const;

    /// Find the first character in the string that is \p C, or npos if not
    /// found. Same as find.
    size_t find_first_of(char C, size_t From = 0) const {
      return find(C, From);
    }

    /// Find the first character in the string that is in \p Chars, or npos if
    /// not found.
    ///
    /// Complexity: O(size() + Chars.size())
    size_t find_first_of(StringRef Chars, size_t From = 0) const;

    /// Find the first character in the string that is not \p C or npos if not
    /// found.
    size_t find_first_not_of(char C, size_t From = 0) const;

    /// Find the first character in the string that is not in the string
    /// \p Chars, or npos if not found.
    ///
    /// Complexity: O(size() + Chars.size())
    size_t find_first_not_of(StringRef Chars, size_t From = 0) const;

    /// Find the last character in the string that is \p C, or npos if not
    /// found.
    size_t find_last_of(char C, size_t From = npos) const {
      return rfind(C, From);
    }

    /// Find the last character in the string that is in \p C, or npos if not
    /// found.
    ///
    /// Complexity: O(size() + Chars.size())
    size_t find_last_of(StringRef Chars, size_t From = npos) const;

    /// Find the last character in the string that is not \p C, or npos if not
    /// found.
    size_t find_last_not_of(char C, size_t From = npos) const;

    /// Find the last character in the string that is not in \p Chars, or
    /// npos if not found.
    ///
    /// Complexity: O(size() + Chars.size())
    size_t find_last_not_of(StringRef Chars, size_t From = npos) const;

    /// @}
    /// @name Helpful Algorithms
    /// @{

    /// Return the number of occurrences of \p C in the string.
    size_t count(char C) const {
      size_t Count = 0;
      for (size_t i = 0, e = Length; i != e; ++i)
        if (Data[i] == C)
          ++Count;
      return Count;
    }

    /// Return the number of non-overlapped occurrences of \p Str in
    /// the string.
    size_t count(StringRef Str) const;

    /// Parse the current string as an integer of the specified radix.  If
    /// \p Radix is specified as zero, this does radix autosensing using
    /// extended C rules: 0 is octal, 0x is hex, 0b is binary.
    ///
    /// If the string is invalid or if only a subset of the string is valid,
    /// this returns true to signify the error.  The string is considered
    /// erroneous if empty or if it overflows T.
    template <typename T>
    typename enable_if_c<std::numeric_limits<T>::is_signed, bool>::type
    getAsInteger(unsigned Radix, T &Result) const {
      long long LLVal;
      if (getAsSignedInteger(*this, Radix, LLVal) ||
            static_cast<T>(LLVal) != LLVal)
        return true;
      Result = LLVal;
      return false;
    }

    template <typename T>
    typename enable_if_c<!std::numeric_limits<T>::is_signed, bool>::type
    getAsInteger(unsigned Radix, T &Result) const {
      unsigned long long ULLVal;
      if (getAsUnsignedInteger(*this, Radix, ULLVal) ||
            static_cast<T>(ULLVal) != ULLVal)
        return true;
      Result = ULLVal;
      return false;
    }

    /// Parse the current string as an integer of the specified \p Radix, or of
    /// an autosensed radix if the \p Radix given is 0.  The current value in
    /// \p Result is discarded, and the storage is changed to be wide enough to
    /// store the parsed integer.
    ///
    /// \returns true if the string does not solely consist of a valid
    /// non-empty number in the appropriate base.
    ///
    /// APInt::fromString is superficially similar but assumes the
    /// string is well-formed in the given radix.
    bool getAsInteger(unsigned Radix, APInt &Result) const;

    /// @}
    /// @name String Operations
    /// @{

    // Convert the given ASCII string to lowercase.
    std::string lower() const;

    /// Convert the given ASCII string to uppercase.
    std::string upper() const;

    /// @}
    /// @name Substring Operations
    /// @{

    /// Return a reference to the substring from [Start, Start + N).
    ///
    /// \param Start The index of the starting character in the substring; if
    /// the index is npos or greater than the length of the string then the
    /// empty substring will be returned.
    ///
    /// \param N The number of characters to included in the substring. If N
    /// exceeds the number of characters remaining in the string, the string
    /// suffix (starting with \p Start) will be returned.
    StringRef substr(size_t Start, size_t N = npos) const {
      Start = min(Start, Length);
      return StringRef(Data + Start, min(N, Length - Start));
    }

    /// Return a StringRef equal to 'this' but with the first \p N elements
    /// dropped.
    StringRef drop_front(size_t N = 1) const {
      assert(size() >= N && "Dropping more elements than exist");
      return substr(N);
    }

    /// Return a StringRef equal to 'this' but with the last \p N elements
    /// dropped.
    StringRef drop_back(size_t N = 1) const {
      assert(size() >= N && "Dropping more elements than exist");
      return substr(0, size()-N);
    }

    /// Return a reference to the substring from [Start, End).
    ///
    /// \param Start The index of the starting character in the substring; if
    /// the index is npos or greater than the length of the string then the
    /// empty substring will be returned.
    ///
    /// \param End The index following the last character to include in the
    /// substring. If this is npos, or less than \p Start, or exceeds the
    /// number of characters remaining in the string, the string suffix
    /// (starting with \p Start) will be returned.
    StringRef slice(size_t Start, size_t End) const {
      Start = min(Start, Length);
      End = min(max(Start, End), Length);
      return StringRef(Data + Start, End - Start);
    }

    /// Split into two substrings around the first occurrence of a separator
    /// character.
    ///
    /// If \p Separator is in the string, then the result is a pair (LHS, RHS)
    /// such that (*this == LHS + Separator + RHS) is true and RHS is
    /// maximal. If \p Separator is not in the string, then the result is a
    /// pair (LHS, RHS) where (*this == LHS) and (RHS == "").
    ///
    /// \param Separator The character to split on.
    /// \returns The split substrings.
    std::pair<StringRef, StringRef> split(char Separator) const {
      size_t Idx = find(Separator);
      if (Idx == npos)
        return std::make_pair(*this, StringRef());
      return std::make_pair(slice(0, Idx), slice(Idx+1, npos));
    }

    /// Split into two substrings around the first occurrence of a separator
    /// string.
    ///
    /// If \p Separator is in the string, then the result is a pair (LHS, RHS)
    /// such that (*this == LHS + Separator + RHS) is true and RHS is
    /// maximal. If \p Separator is not in the string, then the result is a
    /// pair (LHS, RHS) where (*this == LHS) and (RHS == "").
    ///
    /// \param Separator - The string to split on.
    /// \return - The split substrings.
    std::pair<StringRef, StringRef> split(StringRef Separator) const {
      size_t Idx = find(Separator);
      if (Idx == npos)
        return std::make_pair(*this, StringRef());
      return std::make_pair(slice(0, Idx), slice(Idx + Separator.size(), npos));
    }

    /// Split into substrings around the occurrences of a separator string.
    ///
    /// Each substring is stored in \p A. If \p MaxSplit is >= 0, at most
    /// \p MaxSplit splits are done and consequently <= \p MaxSplit
    /// elements are added to A.
    /// If \p KeepEmpty is false, empty strings are not added to \p A. They
    /// still count when considering \p MaxSplit
    /// An useful invariant is that
    /// Separator.join(A) == *this if MaxSplit == -1 and KeepEmpty == true
    ///
    /// \param A - Where to put the substrings.
    /// \param Separator - The string to split on.
    /// \param MaxSplit - The maximum number of times the string is split.
    /// \param KeepEmpty - True if empty substring should be added.
    void split(SmallVectorImpl<StringRef> &A,
               StringRef Separator, int MaxSplit = -1,
               bool KeepEmpty = true) const;

    /// Split into two substrings around the last occurrence of a separator
    /// character.
    ///
    /// If \p Separator is in the string, then the result is a pair (LHS, RHS)
    /// such that (*this == LHS + Separator + RHS) is true and RHS is
    /// minimal. If \p Separator is not in the string, then the result is a
    /// pair (LHS, RHS) where (*this == LHS) and (RHS == "").
    ///
    /// \param Separator - The character to split on.
    /// \return - The split substrings.
    std::pair<StringRef, StringRef> rsplit(char Separator) const {
      size_t Idx = rfind(Separator);
      if (Idx == npos)
        return std::make_pair(*this, StringRef());
      return std::make_pair(slice(0, Idx), slice(Idx+1, npos));
    }

    /// Return string with consecutive characters in \p Chars starting from
    /// the left removed.
    StringRef ltrim(StringRef Chars = " \t\n\v\f\r") const {
      return drop_front(std::min(Length, find_first_not_of(Chars)));
    }

    /// Return string with consecutive characters in \p Chars starting from
    /// the right removed.
    StringRef rtrim(StringRef Chars = " \t\n\v\f\r") const {
      return drop_back(Length - std::min(Length, find_last_not_of(Chars) + 1));
    }

    /// Return string with consecutive characters in \p Chars starting from
    /// the left and right removed.
    StringRef trim(StringRef Chars = " \t\n\v\f\r") const {
      return ltrim(Chars).rtrim(Chars);
    }

    /// @}
  };

  /// @name StringRef Comparison Operators
  /// @{

  inline bool operator==(StringRef LHS, StringRef RHS) {
    return LHS.equals(RHS);
  }

  inline bool operator!=(StringRef LHS, StringRef RHS) {
    return !(LHS == RHS);
  }

  inline bool operator<(StringRef LHS, StringRef RHS) {
    return LHS.compare(RHS) == -1;
  }

  inline bool operator<=(StringRef LHS, StringRef RHS) {
    return LHS.compare(RHS) != 1;
  }

  inline bool operator>(StringRef LHS, StringRef RHS) {
    return LHS.compare(RHS) == 1;
  }

  inline bool operator>=(StringRef LHS, StringRef RHS) {
    return LHS.compare(RHS) != -1;
  }

  inline std::string &operator+=(std::string &buffer, StringRef string) {
    return buffer.append(string.data(), string.size());
  }

  /// @}

  /// \brief Compute a hash_code for a StringRef.
  hash_code hash_value(StringRef S);

  // StringRefs can be treated like a POD type.
  template <typename T> struct isPodLike;
  template <> struct isPodLike<StringRef> { static const bool value = true; };

  /// Construct a string ref from a boolean.
  inline StringRef toStringRef(bool B) {
    return StringRef(B ? "true" : "false");
  }
}

#endif