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
|
//===--- PPLexerChange.cpp - Handle changing lexers in the preprocessor ---===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file implements pieces of the Preprocessor interface that manage the
// current lexer stack.
//
//===----------------------------------------------------------------------===//
#include "clang/Lex/Preprocessor.h"
#include "clang/Lex/HeaderSearch.h"
#include "clang/Lex/MacroInfo.h"
#include "clang/Lex/LexDiagnostic.h"
#include "clang/Basic/SourceManager.h"
#include "llvm/Support/MemoryBuffer.h"
using namespace clang;
PPCallbacks::~PPCallbacks() {}
//===----------------------------------------------------------------------===//
// Miscellaneous Methods.
//===----------------------------------------------------------------------===//
/// isInPrimaryFile - Return true if we're in the top-level file, not in a
/// #include. This looks through macro expansions and active _Pragma lexers.
bool Preprocessor::isInPrimaryFile() const {
if (IsFileLexer())
return IncludeMacroStack.empty();
// If there are any stacked lexers, we're in a #include.
assert(IsFileLexer(IncludeMacroStack[0]) &&
"Top level include stack isn't our primary lexer?");
for (unsigned i = 1, e = IncludeMacroStack.size(); i != e; ++i)
if (IsFileLexer(IncludeMacroStack[i]))
return false;
return true;
}
/// getCurrentLexer - Return the current file lexer being lexed from. Note
/// that this ignores any potentially active macro expansions and _Pragma
/// expansions going on at the time.
PreprocessorLexer *Preprocessor::getCurrentFileLexer() const {
if (IsFileLexer())
return CurPPLexer;
// Look for a stacked lexer.
for (unsigned i = IncludeMacroStack.size(); i != 0; --i) {
const IncludeStackInfo& ISI = IncludeMacroStack[i-1];
if (IsFileLexer(ISI))
return ISI.ThePPLexer;
}
return 0;
}
//===----------------------------------------------------------------------===//
// Methods for Entering and Callbacks for leaving various contexts
//===----------------------------------------------------------------------===//
/// EnterSourceFile - Add a source file to the top of the include stack and
/// start lexing tokens from it instead of the current buffer.
bool Preprocessor::EnterSourceFile(FileID FID, const DirectoryLookup *CurDir,
std::string &ErrorStr) {
assert(CurTokenLexer == 0 && "Cannot #include a file inside a macro!");
++NumEnteredSourceFiles;
if (MaxIncludeStackDepth < IncludeMacroStack.size())
MaxIncludeStackDepth = IncludeMacroStack.size();
if (PTH) {
if (PTHLexer *PL = PTH->CreateLexer(FID)) {
EnterSourceFileWithPTH(PL, CurDir);
return false;
}
}
// Get the MemoryBuffer for this FID, if it fails, we fail.
bool Invalid = false;
const llvm::MemoryBuffer *InputFile = getSourceManager().getBuffer(FID,
&Invalid);
if (Invalid)
return true;
EnterSourceFileWithLexer(new Lexer(FID, InputFile, *this), CurDir);
return false;
}
/// EnterSourceFileWithLexer - Add a source file to the top of the include stack
/// and start lexing tokens from it instead of the current buffer.
void Preprocessor::EnterSourceFileWithLexer(Lexer *TheLexer,
const DirectoryLookup *CurDir) {
// Add the current lexer to the include stack.
if (CurPPLexer || CurTokenLexer)
PushIncludeMacroStack();
CurLexer.reset(TheLexer);
CurPPLexer = TheLexer;
CurDirLookup = CurDir;
// Notify the client, if desired, that we are in a new source file.
if (Callbacks && !CurLexer->Is_PragmaLexer) {
SrcMgr::CharacteristicKind FileType =
SourceMgr.getFileCharacteristic(CurLexer->getFileLoc());
Callbacks->FileChanged(CurLexer->getFileLoc(),
PPCallbacks::EnterFile, FileType);
}
}
/// EnterSourceFileWithPTH - Add a source file to the top of the include stack
/// and start getting tokens from it using the PTH cache.
void Preprocessor::EnterSourceFileWithPTH(PTHLexer *PL,
const DirectoryLookup *CurDir) {
if (CurPPLexer || CurTokenLexer)
PushIncludeMacroStack();
CurDirLookup = CurDir;
CurPTHLexer.reset(PL);
CurPPLexer = CurPTHLexer.get();
// Notify the client, if desired, that we are in a new source file.
if (Callbacks) {
FileID FID = CurPPLexer->getFileID();
SourceLocation EnterLoc = SourceMgr.getLocForStartOfFile(FID);
SrcMgr::CharacteristicKind FileType =
SourceMgr.getFileCharacteristic(EnterLoc);
Callbacks->FileChanged(EnterLoc, PPCallbacks::EnterFile, FileType);
}
}
/// EnterMacro - Add a Macro to the top of the include stack and start lexing
/// tokens from it instead of the current buffer.
void Preprocessor::EnterMacro(Token &Tok, SourceLocation ILEnd,
MacroArgs *Args) {
PushIncludeMacroStack();
CurDirLookup = 0;
if (NumCachedTokenLexers == 0) {
CurTokenLexer.reset(new TokenLexer(Tok, ILEnd, Args, *this));
} else {
CurTokenLexer.reset(TokenLexerCache[--NumCachedTokenLexers]);
CurTokenLexer->Init(Tok, ILEnd, Args);
}
}
/// EnterTokenStream - Add a "macro" context to the top of the include stack,
/// which will cause the lexer to start returning the specified tokens.
///
/// If DisableMacroExpansion is true, tokens lexed from the token stream will
/// not be subject to further macro expansion. Otherwise, these tokens will
/// be re-macro-expanded when/if expansion is enabled.
///
/// If OwnsTokens is false, this method assumes that the specified stream of
/// tokens has a permanent owner somewhere, so they do not need to be copied.
/// If it is true, it assumes the array of tokens is allocated with new[] and
/// must be freed.
///
void Preprocessor::EnterTokenStream(const Token *Toks, unsigned NumToks,
bool DisableMacroExpansion,
bool OwnsTokens) {
// Save our current state.
PushIncludeMacroStack();
CurDirLookup = 0;
// Create a macro expander to expand from the specified token stream.
if (NumCachedTokenLexers == 0) {
CurTokenLexer.reset(new TokenLexer(Toks, NumToks, DisableMacroExpansion,
OwnsTokens, *this));
} else {
CurTokenLexer.reset(TokenLexerCache[--NumCachedTokenLexers]);
CurTokenLexer->Init(Toks, NumToks, DisableMacroExpansion, OwnsTokens);
}
}
/// HandleEndOfFile - This callback is invoked when the lexer hits the end of
/// the current file. This either returns the EOF token or pops a level off
/// the include stack and keeps going.
bool Preprocessor::HandleEndOfFile(Token &Result, bool isEndOfMacro) {
assert(!CurTokenLexer &&
"Ending a file when currently in a macro!");
// See if this file had a controlling macro.
if (CurPPLexer) { // Not ending a macro, ignore it.
if (const IdentifierInfo *ControllingMacro =
CurPPLexer->MIOpt.GetControllingMacroAtEndOfFile()) {
// Okay, this has a controlling macro, remember in HeaderFileInfo.
if (const FileEntry *FE =
SourceMgr.getFileEntryForID(CurPPLexer->getFileID()))
HeaderInfo.SetFileControllingMacro(FE, ControllingMacro);
}
}
// If this is a #include'd file, pop it off the include stack and continue
// lexing the #includer file.
if (!IncludeMacroStack.empty()) {
// We're done with the #included file.
RemoveTopOfLexerStack();
// Notify the client, if desired, that we are in a new source file.
if (Callbacks && !isEndOfMacro && CurPPLexer) {
SrcMgr::CharacteristicKind FileType =
SourceMgr.getFileCharacteristic(CurPPLexer->getSourceLocation());
Callbacks->FileChanged(CurPPLexer->getSourceLocation(),
PPCallbacks::ExitFile, FileType);
}
// Client should lex another token.
return false;
}
// If the file ends with a newline, form the EOF token on the newline itself,
// rather than "on the line following it", which doesn't exist. This makes
// diagnostics relating to the end of file include the last file that the user
// actually typed, which is goodness.
if (CurLexer) {
const char *EndPos = CurLexer->BufferEnd;
if (EndPos != CurLexer->BufferStart &&
(EndPos[-1] == '\n' || EndPos[-1] == '\r')) {
--EndPos;
// Handle \n\r and \r\n:
if (EndPos != CurLexer->BufferStart &&
(EndPos[-1] == '\n' || EndPos[-1] == '\r') &&
EndPos[-1] != EndPos[0])
--EndPos;
}
Result.startToken();
CurLexer->BufferPtr = EndPos;
CurLexer->FormTokenWithChars(Result, EndPos, tok::eof);
// We're done with the #included file.
CurLexer.reset();
} else {
assert(CurPTHLexer && "Got EOF but no current lexer set!");
CurPTHLexer->getEOF(Result);
CurPTHLexer.reset();
}
CurPPLexer = 0;
// This is the end of the top-level file. If the diag::pp_macro_not_used
// diagnostic is enabled, look for macros that have not been used.
if (getDiagnostics().getDiagnosticLevel(diag::pp_macro_not_used) !=
Diagnostic::Ignored) {
for (macro_iterator I = macro_begin(false), E = macro_end(false);
I != E; ++I)
if (!I->second->isUsed())
Diag(I->second->getDefinitionLoc(), diag::pp_macro_not_used);
}
return true;
}
/// HandleEndOfTokenLexer - This callback is invoked when the current TokenLexer
/// hits the end of its token stream.
bool Preprocessor::HandleEndOfTokenLexer(Token &Result) {
assert(CurTokenLexer && !CurPPLexer &&
"Ending a macro when currently in a #include file!");
// Delete or cache the now-dead macro expander.
if (NumCachedTokenLexers == TokenLexerCacheSize)
CurTokenLexer.reset();
else
TokenLexerCache[NumCachedTokenLexers++] = CurTokenLexer.take();
// Handle this like a #include file being popped off the stack.
return HandleEndOfFile(Result, true);
}
/// RemoveTopOfLexerStack - Pop the current lexer/macro exp off the top of the
/// lexer stack. This should only be used in situations where the current
/// state of the top-of-stack lexer is unknown.
void Preprocessor::RemoveTopOfLexerStack() {
assert(!IncludeMacroStack.empty() && "Ran out of stack entries to load");
if (CurTokenLexer) {
// Delete or cache the now-dead macro expander.
if (NumCachedTokenLexers == TokenLexerCacheSize)
CurTokenLexer.reset();
else
TokenLexerCache[NumCachedTokenLexers++] = CurTokenLexer.take();
}
PopIncludeMacroStack();
}
/// HandleMicrosoftCommentPaste - When the macro expander pastes together a
/// comment (/##/) in microsoft mode, this method handles updating the current
/// state, returning the token on the next source line.
void Preprocessor::HandleMicrosoftCommentPaste(Token &Tok) {
assert(CurTokenLexer && !CurPPLexer &&
"Pasted comment can only be formed from macro");
// We handle this by scanning for the closest real lexer, switching it to
// raw mode and preprocessor mode. This will cause it to return \n as an
// explicit EOM token.
PreprocessorLexer *FoundLexer = 0;
bool LexerWasInPPMode = false;
for (unsigned i = 0, e = IncludeMacroStack.size(); i != e; ++i) {
IncludeStackInfo &ISI = *(IncludeMacroStack.end()-i-1);
if (ISI.ThePPLexer == 0) continue; // Scan for a real lexer.
// Once we find a real lexer, mark it as raw mode (disabling macro
// expansions) and preprocessor mode (return EOM). We know that the lexer
// was *not* in raw mode before, because the macro that the comment came
// from was expanded. However, it could have already been in preprocessor
// mode (#if COMMENT) in which case we have to return it to that mode and
// return EOM.
FoundLexer = ISI.ThePPLexer;
FoundLexer->LexingRawMode = true;
LexerWasInPPMode = FoundLexer->ParsingPreprocessorDirective;
FoundLexer->ParsingPreprocessorDirective = true;
break;
}
// Okay, we either found and switched over the lexer, or we didn't find a
// lexer. In either case, finish off the macro the comment came from, getting
// the next token.
if (!HandleEndOfTokenLexer(Tok)) Lex(Tok);
// Discarding comments as long as we don't have EOF or EOM. This 'comments
// out' the rest of the line, including any tokens that came from other macros
// that were active, as in:
// #define submacro a COMMENT b
// submacro c
// which should lex to 'a' only: 'b' and 'c' should be removed.
while (Tok.isNot(tok::eom) && Tok.isNot(tok::eof))
Lex(Tok);
// If we got an eom token, then we successfully found the end of the line.
if (Tok.is(tok::eom)) {
assert(FoundLexer && "Can't get end of line without an active lexer");
// Restore the lexer back to normal mode instead of raw mode.
FoundLexer->LexingRawMode = false;
// If the lexer was already in preprocessor mode, just return the EOM token
// to finish the preprocessor line.
if (LexerWasInPPMode) return;
// Otherwise, switch out of PP mode and return the next lexed token.
FoundLexer->ParsingPreprocessorDirective = false;
return Lex(Tok);
}
// If we got an EOF token, then we reached the end of the token stream but
// didn't find an explicit \n. This can only happen if there was no lexer
// active (an active lexer would return EOM at EOF if there was no \n in
// preprocessor directive mode), so just return EOF as our token.
assert(!FoundLexer && "Lexer should return EOM before EOF in PP mode");
}
|