Repository navigation
Expand file tree
/
Copy pathentry.c
More file actions
613 lines (540 loc) · 16.1 KB
/
Copy pathentry.c
File metadata and controls
613 lines (540 loc) · 16.1 KB
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
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
#define USE_THE_REPOSITORY_VARIABLE
#include "git-compat-util.h"
#include "odb.h"
#include "dir.h"
#include "environment.h"
#include "gettext.h"
#include "hex.h"
#include "name-hash.h"
#include "sparse-index.h"
#include "streaming.h"
#include "submodule.h"
#include "symlinks.h"
#include "progress.h"
#include "fsmonitor.h"
#include "entry.h"
#include "parallel-checkout.h"
static void create_directories(const char *path, int path_len,
const struct checkout *state)
{
char *buf = xmallocz(path_len);
int len = 0;
while (len < path_len) {
do {
buf[len] = path[len];
len++;
} while (len < path_len && path[len] != '/');
if (len >= path_len)
break;
buf[len] = 0;
/*
* For 'checkout-index --prefix=<dir>', <dir> is
* allowed to be a symlink to an existing directory,
* and we set 'state->base_dir_len' below, such that
* we test the path components of the prefix with the
* stat() function instead of the lstat() function.
*/
if (has_dirs_only_path(buf, len, state->base_dir_len))
continue; /* ok, it is already a directory. */
/*
* If this mkdir() would fail, it could be that there
* is already a symlink or something else exists
* there, therefore we then try to unlink it and try
* one more time to create the directory.
*/
if (mkdir(buf, 0777)) {
if (errno == EEXIST && state->force &&
!unlink_or_warn(buf) && !mkdir(buf, 0777))
continue;
die_errno("cannot create directory at '%s'", buf);
}
}
free(buf);
}
static void remove_subtree(struct strbuf *path)
{
DIR *dir = opendir(path->buf);
struct dirent *de;
int origlen = path->len;
if (!dir)
die_errno("cannot opendir '%s'", path->buf);
while ((de = readdir_skip_dot_and_dotdot(dir)) != NULL) {
struct stat st;
strbuf_addch(path, '/');
strbuf_addstr(path, de->d_name);
if (lstat(path->buf, &st))
die_errno("cannot lstat '%s'", path->buf);
if (S_ISDIR(st.st_mode))
remove_subtree(path);
else if (unlink(path->buf))
die_errno("cannot unlink '%s'", path->buf);
strbuf_setlen(path, origlen);
}
closedir(dir);
if (rmdir(path->buf))
die_errno("cannot rmdir '%s'", path->buf);
}
static int create_file(const char *path, unsigned int mode)
{
mode = (mode & 0100) ? 0777 : 0666;
return open(path, O_WRONLY | O_CREAT | O_EXCL, mode);
}
void *read_blob_entry(const struct cache_entry *ce, size_t *size)
{
enum object_type type;
unsigned long ul;
void *blob_data = odb_read_object(the_repository->objects, &ce->oid,
&type, &ul);
*size = ul;
if (blob_data) {
if (type == OBJ_BLOB)
return blob_data;
free(blob_data);
}
return NULL;
}
static int open_output_fd(char *path, const struct cache_entry *ce, int to_tempfile)
{
int symlink = (ce->ce_mode & S_IFMT) != S_IFREG;
if (to_tempfile) {
xsnprintf(path, TEMPORARY_FILENAME_LENGTH, "%s",
symlink ? ".merge_link_XXXXXX" : ".merge_file_XXXXXX");
return mkstemp(path);
} else {
return create_file(path, !symlink ? ce->ce_mode : 0666);
}
}
int fstat_checkout_output(int fd, const struct checkout *state, struct stat *st)
{
/* use fstat() only when path == ce->name */
if (fstat_is_reliable() &&
state->refresh_cache && !state->base_dir_len) {
return !fstat(fd, st);
}
return 0;
}
static int streaming_write_entry(const struct cache_entry *ce, char *path,
struct stream_filter *filter,
const struct checkout *state, int to_tempfile,
int *fstat_done, struct stat *statbuf)
{
int result = 0;
int fd;
fd = open_output_fd(path, ce, to_tempfile);
if (fd < 0)
return -1;
result |= stream_blob_to_fd(fd, &ce->oid, filter, 1);
*fstat_done = fstat_checkout_output(fd, state, statbuf);
result |= close(fd);
if (result)
unlink(path);
return result;
}
void enable_delayed_checkout(struct checkout *state)
{
if (!state->delayed_checkout) {
state->delayed_checkout = xmalloc(sizeof(*state->delayed_checkout));
state->delayed_checkout->state = CE_CAN_DELAY;
string_list_init_nodup(&state->delayed_checkout->filters);
string_list_init_nodup(&state->delayed_checkout->paths);
}
}
static int remove_available_paths(struct string_list_item *item, void *cb_data)
{
struct string_list *available_paths = cb_data;
struct string_list_item *available;
available = string_list_lookup(available_paths, item->string);
if (available)
available->util = item->util;
return !available;
}
static int string_is_not_null(struct string_list_item *item, void *data UNUSED)
{
return !!item->string;
}
int finish_delayed_checkout(struct checkout *state, int show_progress)
{
int errs = 0;
unsigned processed_paths = 0;
off_t filtered_bytes = 0;
struct string_list_item *filter, *path;
struct progress *progress = NULL;
struct delayed_checkout *dco = state->delayed_checkout;
if (!state->delayed_checkout)
return errs;
dco->state = CE_RETRY;
if (show_progress)
progress = start_delayed_progress(the_repository,
_("Filtering content"),
dco->paths.nr);
while (dco->filters.nr > 0) {
for_each_string_list_item(filter, &dco->filters) {
struct string_list available_paths = STRING_LIST_INIT_DUP;
if (!async_query_available_blobs(filter->string, &available_paths)) {
/* Filter reported an error */
errs = 1;
filter->string = NULL;
continue;
}
if (available_paths.nr <= 0) {
/*
* Filter responded with no entries. That means
* the filter is done and we can remove the
* filter from the list (see
* "string_list_remove_empty_items" call below).
*/
filter->string = NULL;
continue;
}
/*
* In dco->paths we store a list of all delayed paths.
* The filter just send us a list of available paths.
* Remove them from the list.
*/
filter_string_list(&dco->paths, 0,
&remove_available_paths, &available_paths);
for_each_string_list_item(path, &available_paths) {
struct cache_entry* ce;
if (!path->util) {
error("external filter '%s' signaled that '%s' "
"is now available although it has not been "
"delayed earlier",
filter->string, path->string);
errs |= 1;
/*
* Do not ask the filter for available blobs,
* again, as the filter is likely buggy.
*/
filter->string = NULL;
continue;
}
ce = index_file_exists(state->istate, path->string,
strlen(path->string), 0);
if (ce) {
display_progress(progress, ++processed_paths);
errs |= checkout_entry(ce, state, NULL, path->util);
filtered_bytes += ce->ce_stat_data.sd_size;
display_throughput(progress, filtered_bytes);
} else
errs = 1;
}
string_list_clear(&available_paths, 0);
}
filter_string_list(&dco->filters, 0, string_is_not_null, NULL);
}
stop_progress(&progress);
string_list_clear(&dco->filters, 0);
/* At this point we should not have any delayed paths anymore. */
errs |= dco->paths.nr;
for_each_string_list_item(path, &dco->paths) {
error("'%s' was not filtered properly", path->string);
}
string_list_clear(&dco->paths, 0);
free(dco);
state->delayed_checkout = NULL;
return errs;
}
void update_ce_after_write(const struct checkout *state, struct cache_entry *ce,
struct stat *st)
{
if (state->refresh_cache) {
assert(state->istate);
fill_stat_cache_info(state->istate, ce, st);
ce->ce_flags |= CE_UPDATE_IN_BASE;
mark_fsmonitor_invalid(state->istate, ce);
state->istate->cache_changed |= CE_ENTRY_CHANGED;
}
}
/* Note: ca is used (and required) iff the entry refers to a regular file. */
static int write_entry(struct cache_entry *ce, char *path, struct conv_attrs *ca,
const struct checkout *state, int to_tempfile,
int *nr_checkouts)
{
unsigned int ce_mode_s_ifmt = ce->ce_mode & S_IFMT;
struct delayed_checkout *dco = state->delayed_checkout;
int fd, ret, fstat_done = 0;
char *new_blob;
struct strbuf buf = STRBUF_INIT;
size_t size;
ssize_t wrote;
size_t newsize = 0;
struct stat st;
const struct submodule *sub;
struct checkout_metadata meta;
static int scratch_nr_checkouts;
clone_checkout_metadata(&meta, &state->meta, &ce->oid);
if (ce_mode_s_ifmt == S_IFREG) {
struct stream_filter *filter = get_stream_filter_ca(ca, &ce->oid);
if (filter &&
!streaming_write_entry(ce, path, filter,
state, to_tempfile,
&fstat_done, &st))
goto finish;
}
switch (ce_mode_s_ifmt) {
case S_IFLNK:
new_blob = read_blob_entry(ce, &size);
if (!new_blob)
return error("unable to read sha1 file of %s (%s)",
ce->name, oid_to_hex(&ce->oid));
/*
* We can't make a real symlink; write out a regular file entry
* with the symlink destination as its contents.
*/
if (!has_symlinks || to_tempfile)
goto write_file_entry;
ret = symlink(new_blob, path);
free(new_blob);
if (ret)
return error_errno("unable to create symlink %s", path);
break;
case S_IFREG:
/*
* We do not send the blob in case of a retry, so do not
* bother reading it at all.
*/
if (dco && dco->state == CE_RETRY) {
new_blob = NULL;
size = 0;
} else {
new_blob = read_blob_entry(ce, &size);
if (!new_blob)
return error("unable to read sha1 file of %s (%s)",
ce->name, oid_to_hex(&ce->oid));
}
/*
* Convert from git internal format to working tree format
*/
if (dco && dco->state != CE_NO_DELAY) {
ret = async_convert_to_working_tree_ca(ca, ce->name,
new_blob, size,
&buf, &meta, dco);
if (ret) {
struct string_list_item *item =
string_list_lookup(&dco->paths, ce->name);
if (item) {
item->util = nr_checkouts ? nr_checkouts
: &scratch_nr_checkouts;
free(new_blob);
goto delayed;
}
}
} else {
ret = convert_to_working_tree_ca(ca, ce->name, new_blob,
size, &buf, &meta);
}
if (ret) {
free(new_blob);
new_blob = strbuf_detach(&buf, &newsize);
size = newsize;
}
/*
* No "else" here as errors from convert are OK at this
* point. If the error would have been fatal (e.g.
* filter is required), then we would have died already.
*/
write_file_entry:
fd = open_output_fd(path, ce, to_tempfile);
if (fd < 0) {
free(new_blob);
return error_errno("unable to create file %s", path);
}
wrote = write_in_full(fd, new_blob, size);
if (!to_tempfile)
fstat_done = fstat_checkout_output(fd, state, &st);
close(fd);
free(new_blob);
if (wrote < 0)
return error("unable to write file %s", path);
break;
case S_IFGITLINK:
if (to_tempfile)
return error("cannot create temporary submodule %s", ce->name);
if (mkdir(path, 0777) < 0)
return error("cannot create submodule directory %s", path);
sub = submodule_from_ce(ce);
if (sub)
return submodule_move_head(ce->name, state->super_prefix,
NULL, oid_to_hex(&ce->oid),
state->force ? SUBMODULE_MOVE_HEAD_FORCE : 0);
break;
default:
return error("unknown file mode for %s in index", ce->name);
}
finish:
if (state->refresh_cache) {
if (!fstat_done && lstat(ce->name, &st) < 0)
return error_errno("unable to stat just-written file %s",
ce->name);
update_ce_after_write(state, ce , &st);
}
if (nr_checkouts)
(*nr_checkouts)++;
delayed:
return 0;
}
/*
* This is like 'lstat()', except it refuses to follow symlinks
* in the path, after skipping "skiplen".
*/
static int check_path(const char *path, int len, struct stat *st, int skiplen)
{
const char *slash = path + len;
while (path < slash && *slash != '/')
slash--;
if (!has_dirs_only_path(path, slash - path, skiplen)) {
errno = ENOENT;
return -1;
}
return lstat(path, st);
}
static void mark_colliding_entries(const struct checkout *state,
struct cache_entry *ce, struct stat *st)
{
int trust_ino = check_stat;
#if defined(GIT_WINDOWS_NATIVE) || defined(__CYGWIN__)
trust_ino = 0;
#endif
ce->ce_flags |= CE_MATCHED;
/* TODO: audit for interaction with sparse-index. */
ensure_full_index(state->istate);
for (size_t i = 0; i < state->istate->cache_nr; i++) {
struct cache_entry *dup = state->istate->cache[i];
if (dup == ce) {
/*
* Parallel checkout doesn't create the files in index
* order. So the other side of the collision may appear
* after the given cache_entry in the array.
*/
if (parallel_checkout_status() == PC_RUNNING)
continue;
else
break;
}
if (dup->ce_flags & (CE_MATCHED | CE_VALID | CE_SKIP_WORKTREE))
continue;
if ((trust_ino && !match_stat_data(&dup->ce_stat_data, st)) ||
paths_collide(ce->name, dup->name)) {
dup->ce_flags |= CE_MATCHED;
break;
}
}
}
int checkout_entry_ca(struct cache_entry *ce, struct conv_attrs *ca,
const struct checkout *state, char *topath,
int *nr_checkouts)
{
static struct strbuf path = STRBUF_INIT;
struct stat st;
struct conv_attrs ca_buf;
if (ce->ce_flags & CE_WT_REMOVE) {
if (topath)
/*
* No content and thus no path to create, so we have
* no pathname to return.
*/
BUG("Can't remove entry to a path");
unlink_entry(ce, state->super_prefix);
return 0;
}
if (topath) {
if (S_ISREG(ce->ce_mode) && !ca) {
convert_attrs(state->istate, &ca_buf, ce->name);
ca = &ca_buf;
}
return write_entry(ce, topath, ca, state, 1, nr_checkouts);
}
strbuf_reset(&path);
strbuf_add(&path, state->base_dir, state->base_dir_len);
strbuf_add(&path, ce->name, ce_namelen(ce));
if (!check_path(path.buf, path.len, &st, state->base_dir_len)) {
const struct submodule *sub;
unsigned changed = ie_match_stat(state->istate, ce, &st,
CE_MATCH_IGNORE_VALID | CE_MATCH_IGNORE_SKIP_WORKTREE);
/*
* Needs to be checked before !changed returns early,
* as the possibly empty directory was not changed
*/
sub = submodule_from_ce(ce);
if (sub) {
int err;
if (!is_submodule_populated_gently(ce->name, &err)) {
struct stat sb;
if (lstat(ce->name, &sb))
die(_("could not stat file '%s'"), ce->name);
if (!(st.st_mode & S_IFDIR))
unlink_or_warn(ce->name);
return submodule_move_head(ce->name, state->super_prefix,
NULL, oid_to_hex(&ce->oid), 0);
} else
return submodule_move_head(ce->name, state->super_prefix,
"HEAD", oid_to_hex(&ce->oid),
state->force ? SUBMODULE_MOVE_HEAD_FORCE : 0);
}
if (!changed)
return 0;
if (!state->force) {
if (!state->quiet)
fprintf(stderr,
"%s already exists, no checkout\n",
path.buf);
return -1;
}
if (state->clone)
mark_colliding_entries(state, ce, &st);
/*
* We unlink the old file, to get the new one with the
* right permissions (including umask, which is nasty
* to emulate by hand - much easier to let the system
* just do the right thing)
*/
if (S_ISDIR(st.st_mode)) {
/* If it is a gitlink, leave it alone! */
if (S_ISGITLINK(ce->ce_mode))
return 0;
/*
* We must avoid replacing submodules' leading
* directories with symbolic links, lest recursive
* clones can write into arbitrary locations.
*
* Technically, this logic is not limited
* to recursive clones, or for that matter to
* submodules' paths colliding with symbolic links'
* paths. Yet it strikes a balance in favor of
* simplicity, and if paths are colliding, we might
* just as well keep the directories during a clone.
*/
if (state->clone && S_ISLNK(ce->ce_mode))
return 0;
remove_subtree(&path);
} else if (unlink(path.buf))
return error_errno("unable to unlink old '%s'", path.buf);
} else if (state->not_new)
return 0;
create_directories(path.buf, path.len, state);
if (S_ISREG(ce->ce_mode) && !ca) {
convert_attrs(state->istate, &ca_buf, ce->name);
ca = &ca_buf;
}
if (!enqueue_checkout(ce, ca, nr_checkouts))
return 0;
return write_entry(ce, path.buf, ca, state, 0, nr_checkouts);
}
void unlink_entry(const struct cache_entry *ce, const char *super_prefix)
{
const struct submodule *sub = submodule_from_ce(ce);
if (sub) {
/* state.force is set at the caller. */
submodule_move_head(ce->name, super_prefix, "HEAD", NULL,
SUBMODULE_MOVE_HEAD_FORCE);
}
if (check_leading_path(ce->name, ce_namelen(ce), 1) >= 0)
return;
if (remove_or_warn(ce->ce_mode, ce->name))
return;
schedule_dir_for_removal(ce->name, ce_namelen(ce));
}
int remove_or_warn(unsigned int mode, const char *file)
{
return S_ISGITLINK(mode) ? rmdir_or_warn(file) : unlink_or_warn(file);
}