summaryrefslogtreecommitdiff
path: root/clang/lib/Basic/IdentifierTable.cpp
blob: 43899f0979b570cc3f9de01b3ef01753bd1f1a8a (about) (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
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
//===--- IdentifierTable.cpp - Hash table for identifier lookup -----------===//
//
//                     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 IdentifierInfo, IdentifierVisitor, and
// IdentifierTable interfaces.
//
//===----------------------------------------------------------------------===//

#include "clang/Basic/IdentifierTable.h"
#include "clang/Basic/LangOptions.h"
#include "llvm/ADT/FoldingSet.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/SmallString.h"
#include "llvm/ADT/StringSwitch.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Support/ErrorHandling.h"
#include <cstdio>

using namespace clang;

//===----------------------------------------------------------------------===//
// IdentifierInfo Implementation
//===----------------------------------------------------------------------===//

IdentifierInfo::IdentifierInfo() {
  TokenID = tok::identifier;
  ObjCOrBuiltinID = 0;
  HasMacro = false;
  IsExtension = false;
  IsCXX11CompatKeyword = false;
  IsPoisoned = false;
  IsCPPOperatorKeyword = false;
  NeedsHandleIdentifier = false;
  IsFromAST = false;
  ChangedAfterLoad = false;
  RevertedTokenID = false;
  OutOfDate = false;
  IsModulesImport = false;
  FETokenInfo = 0;
  Entry = 0;
}

//===----------------------------------------------------------------------===//
// IdentifierTable Implementation
//===----------------------------------------------------------------------===//

IdentifierIterator::~IdentifierIterator() { }

IdentifierInfoLookup::~IdentifierInfoLookup() {}

namespace {
  /// \brief A simple identifier lookup iterator that represents an
  /// empty sequence of identifiers.
  class EmptyLookupIterator : public IdentifierIterator
  {
  public:
    virtual StringRef Next() { return StringRef(); }
  };
}

IdentifierIterator *IdentifierInfoLookup::getIdentifiers() const {
  return new EmptyLookupIterator();
}

ExternalIdentifierLookup::~ExternalIdentifierLookup() {}

IdentifierTable::IdentifierTable(const LangOptions &LangOpts,
                                 IdentifierInfoLookup* externalLookup)
  : HashTable(8192), // Start with space for 8K identifiers.
    ExternalLookup(externalLookup) {

  // Populate the identifier table with info about keywords for the current
  // language.
  AddKeywords(LangOpts);
      

  // Add the '_experimental_modules_import' contextual keyword.
  get("__experimental_modules_import").setModulesImport(true);
}

//===----------------------------------------------------------------------===//
// Language Keyword Implementation
//===----------------------------------------------------------------------===//

// Constants for TokenKinds.def
namespace {
  enum {
    KEYC99 = 0x1,
    KEYCXX = 0x2,
    KEYCXX0X = 0x4,
    KEYGNU = 0x8,
    KEYMS = 0x10,
    BOOLSUPPORT = 0x20,
    KEYALTIVEC = 0x40,
    KEYNOCXX = 0x80,
    KEYBORLAND = 0x100,
    KEYOPENCL = 0x200,
    KEYC11 = 0x400,
    KEYARC = 0x800,
    KEYALL = 0x0fff
  };
}

/// AddKeyword - This method is used to associate a token ID with specific
/// identifiers because they are language keywords.  This causes the lexer to
/// automatically map matching identifiers to specialized token codes.
///
/// The C90/C99/CPP/CPP0x flags are set to 3 if the token is a keyword in a
/// future language standard, set to 2 if the token should be enabled in the
/// specified language, set to 1 if it is an extension in the specified
/// language, and set to 0 if disabled in the specified language.
static void AddKeyword(StringRef Keyword,
                       tok::TokenKind TokenCode, unsigned Flags,
                       const LangOptions &LangOpts, IdentifierTable &Table) {
  unsigned AddResult = 0;
  if (Flags == KEYALL) AddResult = 2;
  else if (LangOpts.CPlusPlus && (Flags & KEYCXX)) AddResult = 2;
  else if (LangOpts.CPlusPlus0x && (Flags & KEYCXX0X)) AddResult = 2;
  else if (LangOpts.C99 && (Flags & KEYC99)) AddResult = 2;
  else if (LangOpts.GNUKeywords && (Flags & KEYGNU)) AddResult = 1;
  else if (LangOpts.MicrosoftExt && (Flags & KEYMS)) AddResult = 1;
  else if (LangOpts.Borland && (Flags & KEYBORLAND)) AddResult = 1;
  else if (LangOpts.Bool && (Flags & BOOLSUPPORT)) AddResult = 2;
  else if (LangOpts.AltiVec && (Flags & KEYALTIVEC)) AddResult = 2;
  else if (LangOpts.OpenCL && (Flags & KEYOPENCL)) AddResult = 2;
  else if (!LangOpts.CPlusPlus && (Flags & KEYNOCXX)) AddResult = 2;
  else if (LangOpts.C11 && (Flags & KEYC11)) AddResult = 2;
  // We treat bridge casts as objective-C keywords so we can warn on them
  // in non-arc mode.
  else if (LangOpts.ObjC2 && (Flags & KEYARC)) AddResult = 2;
  else if (LangOpts.CPlusPlus && (Flags & KEYCXX0X)) AddResult = 3;

  // Don't add this keyword if disabled in this language.
  if (AddResult == 0) return;

  IdentifierInfo &Info =
      Table.get(Keyword, AddResult == 3 ? tok::identifier : TokenCode);
  Info.setIsExtensionToken(AddResult == 1);
  Info.setIsCXX11CompatKeyword(AddResult == 3);
}

/// AddCXXOperatorKeyword - Register a C++ operator keyword alternative
/// representations.
static void AddCXXOperatorKeyword(StringRef Keyword,
                                  tok::TokenKind TokenCode,
                                  IdentifierTable &Table) {
  IdentifierInfo &Info = Table.get(Keyword, TokenCode);
  Info.setIsCPlusPlusOperatorKeyword();
}

/// AddObjCKeyword - Register an Objective-C @keyword like "class" "selector" or
/// "property".
static void AddObjCKeyword(StringRef Name,
                           tok::ObjCKeywordKind ObjCID,
                           IdentifierTable &Table) {
  Table.get(Name).setObjCKeywordID(ObjCID);
}

/// AddKeywords - Add all keywords to the symbol table.
///
void IdentifierTable::AddKeywords(const LangOptions &LangOpts) {
  // Add keywords and tokens for the current language.
#define KEYWORD(NAME, FLAGS) \
  AddKeyword(StringRef(#NAME), tok::kw_ ## NAME,  \
             FLAGS, LangOpts, *this);
#define ALIAS(NAME, TOK, FLAGS) \
  AddKeyword(StringRef(NAME), tok::kw_ ## TOK,  \
             FLAGS, LangOpts, *this);
#define CXX_KEYWORD_OPERATOR(NAME, ALIAS) \
  if (LangOpts.CXXOperatorNames)          \
    AddCXXOperatorKeyword(StringRef(#NAME), tok::ALIAS, *this);
#define OBJC1_AT_KEYWORD(NAME) \
  if (LangOpts.ObjC1)          \
    AddObjCKeyword(StringRef(#NAME), tok::objc_##NAME, *this);
#define OBJC2_AT_KEYWORD(NAME) \
  if (LangOpts.ObjC2)          \
    AddObjCKeyword(StringRef(#NAME), tok::objc_##NAME, *this);
#define TESTING_KEYWORD(NAME, FLAGS)
#include "clang/Basic/TokenKinds.def"

  if (LangOpts.ParseUnknownAnytype)
    AddKeyword("__unknown_anytype", tok::kw___unknown_anytype, KEYALL,
               LangOpts, *this);
}

tok::PPKeywordKind IdentifierInfo::getPPKeywordID() const {
  // We use a perfect hash function here involving the length of the keyword,
  // the first and third character.  For preprocessor ID's there are no
  // collisions (if there were, the switch below would complain about duplicate
  // case values).  Note that this depends on 'if' being null terminated.

#define HASH(LEN, FIRST, THIRD) \
  (LEN << 5) + (((FIRST-'a') + (THIRD-'a')) & 31)
#define CASE(LEN, FIRST, THIRD, NAME) \
  case HASH(LEN, FIRST, THIRD): \
    return memcmp(Name, #NAME, LEN) ? tok::pp_not_keyword : tok::pp_ ## NAME

  unsigned Len = getLength();
  if (Len < 2) return tok::pp_not_keyword;
  const char *Name = getNameStart();
  switch (HASH(Len, Name[0], Name[2])) {
  default: return tok::pp_not_keyword;
  CASE( 2, 'i', '\0', if);
  CASE( 4, 'e', 'i', elif);
  CASE( 4, 'e', 's', else);
  CASE( 4, 'l', 'n', line);
  CASE( 4, 's', 'c', sccs);
  CASE( 5, 'e', 'd', endif);
  CASE( 5, 'e', 'r', error);
  CASE( 5, 'i', 'e', ident);
  CASE( 5, 'i', 'd', ifdef);
  CASE( 5, 'u', 'd', undef);

  CASE( 6, 'a', 's', assert);
  CASE( 6, 'd', 'f', define);
  CASE( 6, 'i', 'n', ifndef);
  CASE( 6, 'i', 'p', import);
  CASE( 6, 'p', 'a', pragma);
      
  CASE( 7, 'd', 'f', defined);
  CASE( 7, 'i', 'c', include);
  CASE( 7, 'w', 'r', warning);

  CASE( 8, 'u', 'a', unassert);
  CASE(12, 'i', 'c', include_next);

  CASE(14, '_', 'p', __public_macro);
      
  CASE(15, '_', 'p', __private_macro);

  CASE(16, '_', 'i', __include_macros);
#undef CASE
#undef HASH
  }
}

//===----------------------------------------------------------------------===//
// Stats Implementation
//===----------------------------------------------------------------------===//

/// PrintStats - Print statistics about how well the identifier table is doing
/// at hashing identifiers.
void IdentifierTable::PrintStats() const {
  unsigned NumBuckets = HashTable.getNumBuckets();
  unsigned NumIdentifiers = HashTable.getNumItems();
  unsigned NumEmptyBuckets = NumBuckets-NumIdentifiers;
  unsigned AverageIdentifierSize = 0;
  unsigned MaxIdentifierLength = 0;

  // TODO: Figure out maximum times an identifier had to probe for -stats.
  for (llvm::StringMap<IdentifierInfo*, llvm::BumpPtrAllocator>::const_iterator
       I = HashTable.begin(), E = HashTable.end(); I != E; ++I) {
    unsigned IdLen = I->getKeyLength();
    AverageIdentifierSize += IdLen;
    if (MaxIdentifierLength < IdLen)
      MaxIdentifierLength = IdLen;
  }

  fprintf(stderr, "\n*** Identifier Table Stats:\n");
  fprintf(stderr, "# Identifiers:   %d\n", NumIdentifiers);
  fprintf(stderr, "# Empty Buckets: %d\n", NumEmptyBuckets);
  fprintf(stderr, "Hash density (#identifiers per bucket): %f\n",
          NumIdentifiers/(double)NumBuckets);
  fprintf(stderr, "Ave identifier length: %f\n",
          (AverageIdentifierSize/(double)NumIdentifiers));
  fprintf(stderr, "Max identifier length: %d\n", MaxIdentifierLength);

  // Compute statistics about the memory allocated for identifiers.
  HashTable.getAllocator().PrintStats();
}

//===----------------------------------------------------------------------===//
// SelectorTable Implementation
//===----------------------------------------------------------------------===//

unsigned llvm::DenseMapInfo<clang::Selector>::getHashValue(clang::Selector S) {
  return DenseMapInfo<void*>::getHashValue(S.getAsOpaquePtr());
}

namespace clang {
/// MultiKeywordSelector - One of these variable length records is kept for each
/// selector containing more than one keyword. We use a folding set
/// to unique aggregate names (keyword selectors in ObjC parlance). Access to
/// this class is provided strictly through Selector.
class MultiKeywordSelector
  : public DeclarationNameExtra, public llvm::FoldingSetNode {
  MultiKeywordSelector(unsigned nKeys) {
    ExtraKindOrNumArgs = NUM_EXTRA_KINDS + nKeys;
  }
public:
  // Constructor for keyword selectors.
  MultiKeywordSelector(unsigned nKeys, IdentifierInfo **IIV) {
    assert((nKeys > 1) && "not a multi-keyword selector");
    ExtraKindOrNumArgs = NUM_EXTRA_KINDS + nKeys;

    // Fill in the trailing keyword array.
    IdentifierInfo **KeyInfo = reinterpret_cast<IdentifierInfo **>(this+1);
    for (unsigned i = 0; i != nKeys; ++i)
      KeyInfo[i] = IIV[i];
  }

  // getName - Derive the full selector name and return it.
  std::string getName() const;

  unsigned getNumArgs() const { return ExtraKindOrNumArgs - NUM_EXTRA_KINDS; }

  typedef IdentifierInfo *const *keyword_iterator;
  keyword_iterator keyword_begin() const {
    return reinterpret_cast<keyword_iterator>(this+1);
  }
  keyword_iterator keyword_end() const {
    return keyword_begin()+getNumArgs();
  }
  IdentifierInfo *getIdentifierInfoForSlot(unsigned i) const {
    assert(i < getNumArgs() && "getIdentifierInfoForSlot(): illegal index");
    return keyword_begin()[i];
  }
  static void Profile(llvm::FoldingSetNodeID &ID,
                      keyword_iterator ArgTys, unsigned NumArgs) {
    ID.AddInteger(NumArgs);
    for (unsigned i = 0; i != NumArgs; ++i)
      ID.AddPointer(ArgTys[i]);
  }
  void Profile(llvm::FoldingSetNodeID &ID) {
    Profile(ID, keyword_begin(), getNumArgs());
  }
};
} // end namespace clang.

unsigned Selector::getNumArgs() const {
  unsigned IIF = getIdentifierInfoFlag();
  if (IIF == ZeroArg)
    return 0;
  if (IIF == OneArg)
    return 1;
  // We point to a MultiKeywordSelector (pointer doesn't contain any flags).
  MultiKeywordSelector *SI = reinterpret_cast<MultiKeywordSelector *>(InfoPtr);
  return SI->getNumArgs();
}

IdentifierInfo *Selector::getIdentifierInfoForSlot(unsigned argIndex) const {
  if (getIdentifierInfoFlag()) {
    assert(argIndex == 0 && "illegal keyword index");
    return getAsIdentifierInfo();
  }
  // We point to a MultiKeywordSelector (pointer doesn't contain any flags).
  MultiKeywordSelector *SI = reinterpret_cast<MultiKeywordSelector *>(InfoPtr);
  return SI->getIdentifierInfoForSlot(argIndex);
}

StringRef Selector::getNameForSlot(unsigned int argIndex) const {
  IdentifierInfo *II = getIdentifierInfoForSlot(argIndex);
  return II? II->getName() : StringRef();
}

std::string MultiKeywordSelector::getName() const {
  SmallString<256> Str;
  llvm::raw_svector_ostream OS(Str);
  for (keyword_iterator I = keyword_begin(), E = keyword_end(); I != E; ++I) {
    if (*I)
      OS << (*I)->getName();
    OS << ':';
  }

  return OS.str();
}

std::string Selector::getAsString() const {
  if (InfoPtr == 0)
    return "<null selector>";

  if (InfoPtr & ArgFlags) {
    IdentifierInfo *II = getAsIdentifierInfo();

    // If the number of arguments is 0 then II is guaranteed to not be null.
    if (getNumArgs() == 0)
      return II->getName();

    if (!II)
      return ":";

    return II->getName().str() + ":";
  }

  // We have a multiple keyword selector (no embedded flags).
  return reinterpret_cast<MultiKeywordSelector *>(InfoPtr)->getName();
}

/// Interpreting the given string using the normal CamelCase
/// conventions, determine whether the given string starts with the
/// given "word", which is assumed to end in a lowercase letter.
static bool startsWithWord(StringRef name, StringRef word) {
  if (name.size() < word.size()) return false;
  return ((name.size() == word.size() ||
           !islower(name[word.size()]))
          && name.startswith(word));
}

ObjCMethodFamily Selector::getMethodFamilyImpl(Selector sel) {
  IdentifierInfo *first = sel.getIdentifierInfoForSlot(0);
  if (!first) return OMF_None;

  StringRef name = first->getName();
  if (sel.isUnarySelector()) {
    if (name == "autorelease") return OMF_autorelease;
    if (name == "dealloc") return OMF_dealloc;
    if (name == "finalize") return OMF_finalize;
    if (name == "release") return OMF_release;
    if (name == "retain") return OMF_retain;
    if (name == "retainCount") return OMF_retainCount;
    if (name == "self") return OMF_self;
  }
 
  if (name == "performSelector") return OMF_performSelector;

  // The other method families may begin with a prefix of underscores.
  while (!name.empty() && name.front() == '_')
    name = name.substr(1);

  if (name.empty()) return OMF_None;
  switch (name.front()) {
  case 'a':
    if (startsWithWord(name, "alloc")) return OMF_alloc;
    break;
  case 'c':
    if (startsWithWord(name, "copy")) return OMF_copy;
    break;
  case 'i':
    if (startsWithWord(name, "init")) return OMF_init;
    break;
  case 'm':
    if (startsWithWord(name, "mutableCopy")) return OMF_mutableCopy;
    break;
  case 'n':
    if (startsWithWord(name, "new")) return OMF_new;
    break;
  default:
    break;
  }

  return OMF_None;
}

namespace {
  struct SelectorTableImpl {
    llvm::FoldingSet<MultiKeywordSelector> Table;
    llvm::BumpPtrAllocator Allocator;
  };
} // end anonymous namespace.

static SelectorTableImpl &getSelectorTableImpl(void *P) {
  return *static_cast<SelectorTableImpl*>(P);
}

/*static*/ Selector
SelectorTable::constructSetterName(IdentifierTable &Idents,
                                   SelectorTable &SelTable,
                                   const IdentifierInfo *Name) {
  SmallString<100> SelectorName;
  SelectorName = "set";
  SelectorName += Name->getName();
  SelectorName[3] = toupper(SelectorName[3]);
  IdentifierInfo *SetterName = &Idents.get(SelectorName);
  return SelTable.getUnarySelector(SetterName);
}

size_t SelectorTable::getTotalMemory() const {
  SelectorTableImpl &SelTabImpl = getSelectorTableImpl(Impl);
  return SelTabImpl.Allocator.getTotalMemory();
}

Selector SelectorTable::getSelector(unsigned nKeys, IdentifierInfo **IIV) {
  if (nKeys < 2)
    return Selector(IIV[0], nKeys);

  SelectorTableImpl &SelTabImpl = getSelectorTableImpl(Impl);

  // Unique selector, to guarantee there is one per name.
  llvm::FoldingSetNodeID ID;
  MultiKeywordSelector::Profile(ID, IIV, nKeys);

  void *InsertPos = 0;
  if (MultiKeywordSelector *SI =
        SelTabImpl.Table.FindNodeOrInsertPos(ID, InsertPos))
    return Selector(SI);

  // MultiKeywordSelector objects are not allocated with new because they have a
  // variable size array (for parameter types) at the end of them.
  unsigned Size = sizeof(MultiKeywordSelector) + nKeys*sizeof(IdentifierInfo *);
  MultiKeywordSelector *SI =
    (MultiKeywordSelector*)SelTabImpl.Allocator.Allocate(Size,
                                         llvm::alignOf<MultiKeywordSelector>());
  new (SI) MultiKeywordSelector(nKeys, IIV);
  SelTabImpl.Table.InsertNode(SI, InsertPos);
  return Selector(SI);
}

SelectorTable::SelectorTable() {
  Impl = new SelectorTableImpl();
}

SelectorTable::~SelectorTable() {
  delete &getSelectorTableImpl(Impl);
}

const char *clang::getOperatorSpelling(OverloadedOperatorKind Operator) {
  switch (Operator) {
  case OO_None:
  case NUM_OVERLOADED_OPERATORS:
    return 0;

#define OVERLOADED_OPERATOR(Name,Spelling,Token,Unary,Binary,MemberOnly) \
  case OO_##Name: return Spelling;
#include "clang/Basic/OperatorKinds.def"
  }

  llvm_unreachable("Invalid OverloadedOperatorKind!");
}