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
| //===- EditedSource.cpp - Collection of source edits ----------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
#include "clang/Edit/EditedSource.h"
#include "clang/Basic/CharInfo.h"
#include "clang/Basic/LLVM.h"
#include "clang/Basic/SourceLocation.h"
#include "clang/Basic/SourceManager.h"
#include "clang/Edit/Commit.h"
#include "clang/Edit/EditsReceiver.h"
#include "clang/Edit/FileOffset.h"
#include "clang/Lex/Lexer.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/SmallString.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/ADT/Twine.h"
#include <algorithm>
#include <cassert>
#include <tuple>
#include <utility>
using namespace clang;
using namespace edit;
void EditsReceiver::remove(CharSourceRange range) {
replace(range, StringRef());
}
void EditedSource::deconstructMacroArgLoc(SourceLocation Loc,
SourceLocation &ExpansionLoc,
MacroArgUse &ArgUse) {
assert(SourceMgr.isMacroArgExpansion(Loc));
SourceLocation DefArgLoc =
SourceMgr.getImmediateExpansionRange(Loc).getBegin();
SourceLocation ImmediateExpansionLoc =
SourceMgr.getImmediateExpansionRange(DefArgLoc).getBegin();
ExpansionLoc = ImmediateExpansionLoc;
while (SourceMgr.isMacroBodyExpansion(ExpansionLoc))
ExpansionLoc =
SourceMgr.getImmediateExpansionRange(ExpansionLoc).getBegin();
SmallString<20> Buf;
StringRef ArgName = Lexer::getSpelling(SourceMgr.getSpellingLoc(DefArgLoc),
Buf, SourceMgr, LangOpts);
ArgUse = MacroArgUse{nullptr, SourceLocation(), SourceLocation()};
if (!ArgName.empty())
ArgUse = {&IdentTable.get(ArgName), ImmediateExpansionLoc,
SourceMgr.getSpellingLoc(DefArgLoc)};
}
void EditedSource::startingCommit() {}
void EditedSource::finishedCommit() {
for (auto &ExpArg : CurrCommitMacroArgExps) {
SourceLocation ExpLoc;
MacroArgUse ArgUse;
std::tie(ExpLoc, ArgUse) = ExpArg;
auto &ArgUses = ExpansionToArgMap[ExpLoc.getRawEncoding()];
if (llvm::find(ArgUses, ArgUse) == ArgUses.end())
ArgUses.push_back(ArgUse);
}
CurrCommitMacroArgExps.clear();
}
StringRef EditedSource::copyString(const Twine &twine) {
SmallString<128> Data;
return copyString(twine.toStringRef(Data));
}
bool EditedSource::canInsertInOffset(SourceLocation OrigLoc, FileOffset Offs) {
FileEditsTy::iterator FA = getActionForOffset(Offs);
if (FA != FileEdits.end()) {
if (FA->first != Offs)
return false; // position has been removed.
}
if (SourceMgr.isMacroArgExpansion(OrigLoc)) {
SourceLocation ExpLoc;
MacroArgUse ArgUse;
deconstructMacroArgLoc(OrigLoc, ExpLoc, ArgUse);
auto I = ExpansionToArgMap.find(ExpLoc.getRawEncoding());
if (I != ExpansionToArgMap.end() &&
find_if(I->second, [&](const MacroArgUse &U) {
return ArgUse.Identifier == U.Identifier &&
std::tie(ArgUse.ImmediateExpansionLoc, ArgUse.UseLoc) !=
std::tie(U.ImmediateExpansionLoc, U.UseLoc);
}) != I->second.end()) {
// Trying to write in a macro argument input that has already been
// written by a previous commit for another expansion of the same macro
// argument name. For example:
//
// \code
// #define MAC(x) ((x)+(x))
// MAC(a)
// \endcode
//
// A commit modified the macro argument 'a' due to the first '(x)'
// expansion inside the macro definition, and a subsequent commit tried
// to modify 'a' again for the second '(x)' expansion. The edits of the
// second commit will be rejected.
return false;
}
}
return true;
}
bool EditedSource::commitInsert(SourceLocation OrigLoc,
FileOffset Offs, StringRef text,
bool beforePreviousInsertions) {
if (!canInsertInOffset(OrigLoc, Offs))
return false;
if (text.empty())
return true;
if (SourceMgr.isMacroArgExpansion(OrigLoc)) {
MacroArgUse ArgUse;
SourceLocation ExpLoc;
deconstructMacroArgLoc(OrigLoc, ExpLoc, ArgUse);
if (ArgUse.Identifier)
CurrCommitMacroArgExps.emplace_back(ExpLoc, ArgUse);
}
FileEdit &FA = FileEdits[Offs];
if (FA.Text.empty()) {
FA.Text = copyString(text);
return true;
}
if (beforePreviousInsertions)
FA.Text = copyString(Twine(text) + FA.Text);
else
FA.Text = copyString(Twine(FA.Text) + text);
return true;
}
bool EditedSource::commitInsertFromRange(SourceLocation OrigLoc,
FileOffset Offs,
FileOffset InsertFromRangeOffs, unsigned Len,
bool beforePreviousInsertions) {
if (Len == 0)
return true;
SmallString<128> StrVec;
FileOffset BeginOffs = InsertFromRangeOffs;
FileOffset EndOffs = BeginOffs.getWithOffset(Len);
FileEditsTy::iterator I = FileEdits.upper_bound(BeginOffs);
if (I != FileEdits.begin())
--I;
for (; I != FileEdits.end(); ++I) {
FileEdit &FA = I->second;
FileOffset B = I->first;
FileOffset E = B.getWithOffset(FA.RemoveLen);
if (BeginOffs == B)
break;
if (BeginOffs < E) {
if (BeginOffs > B) {
BeginOffs = E;
++I;
}
break;
}
}
for (; I != FileEdits.end() && EndOffs > I->first; ++I) {
FileEdit &FA = I->second;
FileOffset B = I->first;
FileOffset E = B.getWithOffset(FA.RemoveLen);
if (BeginOffs < B) {
bool Invalid = false;
StringRef text = getSourceText(BeginOffs, B, Invalid);
if (Invalid)
return false;
StrVec += text;
}
StrVec += FA.Text;
BeginOffs = E;
}
if (BeginOffs < EndOffs) {
bool Invalid = false;
StringRef text = getSourceText(BeginOffs, EndOffs, Invalid);
if (Invalid)
return false;
StrVec += text;
}
return commitInsert(OrigLoc, Offs, StrVec, beforePreviousInsertions);
}
void EditedSource::commitRemove(SourceLocation OrigLoc,
FileOffset BeginOffs, unsigned Len) {
if (Len == 0)
return;
FileOffset EndOffs = BeginOffs.getWithOffset(Len);
FileEditsTy::iterator I = FileEdits.upper_bound(BeginOffs);
if (I != FileEdits.begin())
--I;
for (; I != FileEdits.end(); ++I) {
FileEdit &FA = I->second;
FileOffset B = I->first;
FileOffset E = B.getWithOffset(FA.RemoveLen);
if (BeginOffs < E)
break;
}
FileOffset TopBegin, TopEnd;
FileEdit *TopFA = nullptr;
if (I == FileEdits.end()) {
FileEditsTy::iterator
NewI = FileEdits.insert(I, std::make_pair(BeginOffs, FileEdit()));
NewI->second.RemoveLen = Len;
return;
}
FileEdit &FA = I->second;
FileOffset B = I->first;
FileOffset E = B.getWithOffset(FA.RemoveLen);
if (BeginOffs < B) {
FileEditsTy::iterator
NewI = FileEdits.insert(I, std::make_pair(BeginOffs, FileEdit()));
TopBegin = BeginOffs;
TopEnd = EndOffs;
TopFA = &NewI->second;
TopFA->RemoveLen = Len;
} else {
TopBegin = B;
TopEnd = E;
TopFA = &I->second;
if (TopEnd >= EndOffs)
return;
unsigned diff = EndOffs.getOffset() - TopEnd.getOffset();
TopEnd = EndOffs;
TopFA->RemoveLen += diff;
if (B == BeginOffs)
TopFA->Text = StringRef();
++I;
}
while (I != FileEdits.end()) {
FileEdit &FA = I->second;
FileOffset B = I->first;
FileOffset E = B.getWithOffset(FA.RemoveLen);
if (B >= TopEnd)
break;
if (E <= TopEnd) {
FileEdits.erase(I++);
continue;
}
if (B < TopEnd) {
unsigned diff = E.getOffset() - TopEnd.getOffset();
TopEnd = E;
TopFA->RemoveLen += diff;
FileEdits.erase(I);
}
break;
}
}
bool EditedSource::commit(const Commit &commit) {
if (!commit.isCommitable())
return false;
struct CommitRAII {
EditedSource &Editor;
CommitRAII(EditedSource &Editor) : Editor(Editor) {
Editor.startingCommit();
}
~CommitRAII() {
Editor.finishedCommit();
}
} CommitRAII(*this);
for (edit::Commit::edit_iterator
I = commit.edit_begin(), E = commit.edit_end(); I != E; ++I) {
const edit::Commit::Edit &edit = *I;
switch (edit.Kind) {
case edit::Commit::Act_Insert:
commitInsert(edit.OrigLoc, edit.Offset, edit.Text, edit.BeforePrev);
break;
case edit::Commit::Act_InsertFromRange:
commitInsertFromRange(edit.OrigLoc, edit.Offset,
edit.InsertFromRangeOffs, edit.Length,
edit.BeforePrev);
break;
case edit::Commit::Act_Remove:
commitRemove(edit.OrigLoc, edit.Offset, edit.Length);
break;
}
}
return true;
}
// Returns true if it is ok to make the two given characters adjacent.
static bool canBeJoined(char left, char right, const LangOptions &LangOpts) {
// FIXME: Should use TokenConcatenation to make sure we don't allow stuff like
// making two '<' adjacent.
return !(Lexer::isIdentifierBodyChar(left, LangOpts) &&
Lexer::isIdentifierBodyChar(right, LangOpts));
}
/// Returns true if it is ok to eliminate the trailing whitespace between
/// the given characters.
static bool canRemoveWhitespace(char left, char beforeWSpace, char right,
const LangOptions &LangOpts) {
if (!canBeJoined(left, right, LangOpts))
return false;
if (isWhitespace(left) || isWhitespace(right))
return true;
if (canBeJoined(beforeWSpace, right, LangOpts))
return false; // the whitespace was intentional, keep it.
return true;
}
/// Check the range that we are going to remove and:
/// -Remove any trailing whitespace if possible.
/// -Insert a space if removing the range is going to mess up the source tokens.
static void adjustRemoval(const SourceManager &SM, const LangOptions &LangOpts,
SourceLocation Loc, FileOffset offs,
unsigned &len, StringRef &text) {
assert(len && text.empty());
SourceLocation BeginTokLoc = Lexer::GetBeginningOfToken(Loc, SM, LangOpts);
if (BeginTokLoc != Loc)
return; // the range is not at the beginning of a token, keep the range.
bool Invalid = false;
StringRef buffer = SM.getBufferData(offs.getFID(), &Invalid);
if (Invalid)
return;
unsigned begin = offs.getOffset();
unsigned end = begin + len;
// Do not try to extend the removal if we're at the end of the buffer already.
if (end == buffer.size())
return;
assert(begin < buffer.size() && end < buffer.size() && "Invalid range!");
// FIXME: Remove newline.
if (begin == 0) {
if (buffer[end] == ' ')
++len;
return;
}
if (buffer[end] == ' ') {
assert((end + 1 != buffer.size() || buffer.data()[end + 1] == 0) &&
"buffer not zero-terminated!");
if (canRemoveWhitespace(/*left=*/buffer[begin-1],
/*beforeWSpace=*/buffer[end-1],
/*right=*/buffer.data()[end + 1], // zero-terminated
LangOpts))
++len;
return;
}
if (!canBeJoined(buffer[begin-1], buffer[end], LangOpts))
text = " ";
}
static void applyRewrite(EditsReceiver &receiver,
StringRef text, FileOffset offs, unsigned len,
const SourceManager &SM, const LangOptions &LangOpts,
bool shouldAdjustRemovals) {
assert(offs.getFID().isValid());
SourceLocation Loc = SM.getLocForStartOfFile(offs.getFID());
Loc = Loc.getLocWithOffset(offs.getOffset());
assert(Loc.isFileID());
if (text.empty() && shouldAdjustRemovals)
adjustRemoval(SM, LangOpts, Loc, offs, len, text);
CharSourceRange range = CharSourceRange::getCharRange(Loc,
Loc.getLocWithOffset(len));
if (text.empty()) {
assert(len);
receiver.remove(range);
return;
}
if (len)
receiver.replace(range, text);
else
receiver.insert(Loc, text);
}
void EditedSource::applyRewrites(EditsReceiver &receiver,
bool shouldAdjustRemovals) {
SmallString<128> StrVec;
FileOffset CurOffs, CurEnd;
unsigned CurLen;
if (FileEdits.empty())
return;
FileEditsTy::iterator I = FileEdits.begin();
CurOffs = I->first;
StrVec = I->second.Text;
CurLen = I->second.RemoveLen;
CurEnd = CurOffs.getWithOffset(CurLen);
++I;
for (FileEditsTy::iterator E = FileEdits.end(); I != E; ++I) {
FileOffset offs = I->first;
FileEdit act = I->second;
assert(offs >= CurEnd);
if (offs == CurEnd) {
StrVec += act.Text;
CurLen += act.RemoveLen;
CurEnd.getWithOffset(act.RemoveLen);
continue;
}
applyRewrite(receiver, StrVec, CurOffs, CurLen, SourceMgr, LangOpts,
shouldAdjustRemovals);
CurOffs = offs;
StrVec = act.Text;
CurLen = act.RemoveLen;
CurEnd = CurOffs.getWithOffset(CurLen);
}
applyRewrite(receiver, StrVec, CurOffs, CurLen, SourceMgr, LangOpts,
shouldAdjustRemovals);
}
void EditedSource::clearRewrites() {
FileEdits.clear();
StrAlloc.Reset();
}
StringRef EditedSource::getSourceText(FileOffset BeginOffs, FileOffset EndOffs,
bool &Invalid) {
assert(BeginOffs.getFID() == EndOffs.getFID());
assert(BeginOffs <= EndOffs);
SourceLocation BLoc = SourceMgr.getLocForStartOfFile(BeginOffs.getFID());
BLoc = BLoc.getLocWithOffset(BeginOffs.getOffset());
assert(BLoc.isFileID());
SourceLocation
ELoc = BLoc.getLocWithOffset(EndOffs.getOffset() - BeginOffs.getOffset());
return Lexer::getSourceText(CharSourceRange::getCharRange(BLoc, ELoc),
SourceMgr, LangOpts, &Invalid);
}
EditedSource::FileEditsTy::iterator
EditedSource::getActionForOffset(FileOffset Offs) {
FileEditsTy::iterator I = FileEdits.upper_bound(Offs);
if (I == FileEdits.begin())
return FileEdits.end();
--I;
FileEdit &FA = I->second;
FileOffset B = I->first;
FileOffset E = B.getWithOffset(FA.RemoveLen);
if (Offs >= B && Offs < E)
return I;
return FileEdits.end();
}
|