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
|
//===--- PTHLexer.cpp - Lex from a token stream ---------------------------===//
//
// 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 PTHLexer interface.
//
//===----------------------------------------------------------------------===//
#include "clang/Basic/TokenKinds.h"
#include "clang/Basic/FileManager.h"
#include "clang/Basic/IdentifierTable.h"
#include "clang/Lex/PTHLexer.h"
#include "clang/Lex/Preprocessor.h"
#include "clang/Lex/PTHManager.h"
#include "clang/Lex/Token.h"
#include "clang/Lex/Preprocessor.h"
#include "llvm/Support/Compiler.h"
#include "llvm/Support/MemoryBuffer.h"
#include "llvm/ADT/StringMap.h"
#include "llvm/ADT/OwningPtr.h"
using namespace clang;
PTHLexer::PTHLexer(Preprocessor& pp, SourceLocation fileloc, const char* D,
PTHManager& PM)
: PreprocessorLexer(&pp, fileloc), TokBuf(D), CurTokenIdx(0), PTHMgr(PM),
NeedsFetching(true) {
// Make sure the EofToken is completely clean.
EofToken.startToken();
}
Token PTHLexer::GetToken() {
// Read the next token, or if we haven't advanced yet, get the last
// token read.
if (NeedsFetching) {
NeedsFetching = false;
ReadToken(LastFetched);
}
Token Tok = LastFetched;
// If we are in raw mode, zero out identifier pointers. This is
// needed for 'pragma poison'. Note that this requires that the Preprocessor
// can go back to the original source when it calls getSpelling().
if (LexingRawMode && Tok.is(tok::identifier))
Tok.setIdentifierInfo(0);
return Tok;
}
void PTHLexer::Lex(Token& Tok) {
LexNextToken:
Tok = GetToken();
if (AtLastToken()) {
Preprocessor *PPCache = PP;
if (LexEndOfFile(Tok))
return;
assert(PPCache && "Raw buffer::LexEndOfFile should return a token");
return PPCache->Lex(Tok);
}
// Don't advance to the next token yet. Check if we are at the
// start of a new line and we're processing a directive. If so, we
// consume this token twice, once as an tok::eom.
if (Tok.isAtStartOfLine() && ParsingPreprocessorDirective) {
ParsingPreprocessorDirective = false;
Tok.setKind(tok::eom);
MIOpt.ReadToken();
return;
}
// Advance to the next token.
AdvanceToken();
if (Tok.is(tok::hash)) {
if (Tok.isAtStartOfLine() && !LexingRawMode) {
PP->HandleDirective(Tok);
if (PP->isCurrentLexer(this))
goto LexNextToken;
return PP->Lex(Tok);
}
}
MIOpt.ReadToken();
if (Tok.is(tok::identifier)) {
if (LexingRawMode) return;
return PP->HandleIdentifier(Tok);
}
}
bool PTHLexer::LexEndOfFile(Token &Tok) {
if (ParsingPreprocessorDirective) {
ParsingPreprocessorDirective = false;
Tok.setKind(tok::eom);
MIOpt.ReadToken();
return true; // Have a token.
}
if (LexingRawMode) {
MIOpt.ReadToken();
return true; // Have an eof token.
}
// FIXME: Issue diagnostics similar to Lexer.
return PP->HandleEndOfFile(Tok, false);
}
void PTHLexer::setEOF(Token& Tok) {
assert(!EofToken.is(tok::eof));
Tok = EofToken;
}
void PTHLexer::DiscardToEndOfLine() {
assert(ParsingPreprocessorDirective && ParsingFilename == false &&
"Must be in a preprocessing directive!");
// Already at end-of-file?
if (AtLastToken())
return;
// Find the first token that is not the start of the *current* line.
Token T;
for (Lex(T); !AtLastToken(); Lex(T))
if (GetToken().isAtStartOfLine())
return;
}
//===----------------------------------------------------------------------===//
// Utility methods for reading from the mmap'ed PTH file.
//===----------------------------------------------------------------------===//
static inline uint8_t Read8(const char*& data) {
return (uint8_t) *(data++);
}
static inline uint32_t Read32(const char*& data) {
uint32_t V = (uint32_t) Read8(data);
V |= (((uint32_t) Read8(data)) << 8);
V |= (((uint32_t) Read8(data)) << 16);
V |= (((uint32_t) Read8(data)) << 24);
return V;
}
//===----------------------------------------------------------------------===//
// Token reconstruction from the PTH file.
//===----------------------------------------------------------------------===//
void PTHLexer::ReadToken(Token& T) {
// Clear the token.
// FIXME: Setting the flags directly should obviate this step.
T.startToken();
// Read the type of the token.
T.setKind((tok::TokenKind) Read8(TokBuf));
// Set flags. This is gross, since we are really setting multiple flags.
T.setFlag((Token::TokenFlags) Read8(TokBuf));
// Set the IdentifierInfo* (if any).
T.setIdentifierInfo(PTHMgr.ReadIdentifierInfo(TokBuf));
// Set the SourceLocation. Since all tokens are constructed using a
// raw lexer, they will all be offseted from the same FileID.
T.setLocation(SourceLocation::getFileLoc(FileID, Read32(TokBuf)));
// Finally, read and set the length of the token.
T.setLength(Read32(TokBuf));
}
//===----------------------------------------------------------------------===//
// Internal Data Structures for PTH file lookup and resolving identifiers.
//===----------------------------------------------------------------------===//
/// PTHFileLookup - This internal data structure is used by the PTHManager
/// to map from FileEntry objects managed by FileManager to offsets within
/// the PTH file.
namespace {
class VISIBILITY_HIDDEN PTHFileLookup {
public:
class Val {
uint32_t v;
public:
Val() : v(~0) {}
Val(uint32_t x) : v(x) {}
operator uint32_t() const {
assert(v != ~((uint32_t)0) && "PTHFileLookup entry initialized.");
return v;
}
Val& operator=(uint32_t x) { v = x; return *this; }
bool isValid() const { return v != ~((uint32_t)0); }
};
private:
llvm::StringMap<Val> FileMap;
public:
PTHFileLookup() {};
Val Lookup(const FileEntry* FE) {
const char* s = FE->getName();
unsigned size = strlen(s);
return FileMap.GetOrCreateValue(s, s+size).getValue();
}
void ReadTable(const char* D) {
uint32_t N = Read32(D); // Read the length of the table.
for ( ; N > 0; --N) { // The rest of the data is the table itself.
uint32_t len = Read32(D);
const char* s = D;
D += len;
FileMap.GetOrCreateValue(s, s+len).getValue() = Read32(D);
}
}
};
} // end anonymous namespace
//===----------------------------------------------------------------------===//
// PTHManager methods.
//===----------------------------------------------------------------------===//
PTHManager::PTHManager(const llvm::MemoryBuffer* buf, void* fileLookup,
const char* idDataTable, void* perIDCache,
Preprocessor& pp)
: Buf(buf), PerIDCache(perIDCache), FileLookup(fileLookup),
IdDataTable(idDataTable), ITable(pp.getIdentifierTable()), PP(pp) {}
PTHManager::~PTHManager() {
delete Buf;
delete (PTHFileLookup*) FileLookup;
free(PerIDCache);
}
PTHManager* PTHManager::Create(const std::string& file, Preprocessor& PP) {
// Memory map the PTH file.
llvm::OwningPtr<llvm::MemoryBuffer>
File(llvm::MemoryBuffer::getFile(file.c_str()));
if (!File)
return 0;
// Get the buffer ranges and check if there are at least three 32-bit
// words at the end of the file.
const char* BufBeg = File->getBufferStart();
const char* BufEnd = File->getBufferEnd();
if(!(BufEnd > BufBeg + sizeof(uint32_t)*3)) {
assert(false && "Invalid PTH file.");
return 0; // FIXME: Proper error diagnostic?
}
// Compute the address of the index table at the end of the PTH file.
// This table contains the offset of the file lookup table, the
// persistent ID -> identifer data table.
const char* EndTable = BufEnd - sizeof(uint32_t)*3;
// Construct the file lookup table. This will be used for mapping from
// FileEntry*'s to cached tokens.
const char* FileTableOffset = EndTable + sizeof(uint32_t)*2;
const char* FileTable = BufBeg + Read32(FileTableOffset);
if (!(FileTable > BufBeg && FileTable < BufEnd)) {
assert(false && "Invalid PTH file.");
return 0; // FIXME: Proper error diagnostic?
}
|