summaryrefslogtreecommitdiff
path: root/builtin/cat-file.c
blob: 27f4f235f6da176adf3e452f9f4fefd14bb453eb (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
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
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
/*
 * GIT - The information manager from hell
 *
 * Copyright (C) Linus Torvalds, 2005
 */
#include "cache.h"
#include "config.h"
#include "builtin.h"
#include "diff.h"
#include "parse-options.h"
#include "userdiff.h"
#include "streaming.h"
#include "tree-walk.h"
#include "sha1-array.h"
#include "packfile.h"
 
struct batch_options {
	int enabled;
	int follow_symlinks;
	int print_contents;
	int buffer_output;
	int all_objects;
	int cmdmode; /* may be 'w' or 'c' for --filters or --textconv */
	const char *format;
};
 
static const char *force_path;
 
static int filter_object(const char *path, unsigned mode,
			 const struct object_id *oid,
			 char **buf, unsigned long *size)
{
	enum object_type type;
 
	*buf = read_sha1_file(oid->hash, &type, size);
	if (!*buf)
		return error(_("cannot read object %s '%s'"),
			     oid_to_hex(oid), path);
	if ((type == OBJ_BLOB) && S_ISREG(mode)) {
		struct strbuf strbuf = STRBUF_INIT;
		if (convert_to_working_tree(path, *buf, *size, &strbuf)) {
			free(*buf);
			*size = strbuf.len;
			*buf = strbuf_detach(&strbuf, NULL);
		}
	}
 
	return 0;
}
 
static int cat_one_file(int opt, const char *exp_type, const char *obj_name,
			int unknown_type)
{
	struct object_id oid;
	enum object_type type;
	char *buf;
	unsigned long size;
	struct object_context obj_context;
	struct object_info oi = OBJECT_INFO_INIT;
	struct strbuf sb = STRBUF_INIT;
	unsigned flags = OBJECT_INFO_LOOKUP_REPLACE;
	const char *path = force_path;
 
	if (unknown_type)
		flags |= OBJECT_INFO_ALLOW_UNKNOWN_TYPE;
 
	if (get_oid_with_context(obj_name, GET_OID_RECORD_PATH,
				 &oid, &obj_context))
		die("Not a valid object name %s", obj_name);
 
	if (!path)
		path = obj_context.path;
	if (obj_context.mode == S_IFINVALID)
		obj_context.mode = 0100644;
 
	buf = NULL;
	switch (opt) {
	case 't':
		oi.type_name = &sb;
		if (oid_object_info_extended(&oid, &oi, flags) < 0)
			die("git cat-file: could not get object info");
		if (sb.len) {
			printf("%s\n", sb.buf);
			strbuf_release(&sb);
			return 0;
		}
		break;
 
	case 's':
		oi.sizep = &size;
		if (oid_object_info_extended(&oid, &oi, flags) < 0)
			die("git cat-file: could not get object info");
		printf("%lu\n", size);
		return 0;
 
	case 'e':
		return !has_object_file(&oid);
 
	case 'w':
		if (!path)
			die("git cat-file --filters %s: <object> must be "
			    "<sha1:path>", obj_name);
 
		if (filter_object(path, obj_context.mode,
				  &oid, &buf, &size))
			return -1;
		break;
 
	case 'c':
		if (!path)
			die("git cat-file --textconv %s: <object> must be <sha1:path>",
			    obj_name);
 
		if (textconv_object(path, obj_context.mode, &oid, 1, &buf, &size))
			break;
		/* else fallthrough */
 
	case 'p':
		type = oid_object_info(&oid, NULL);
		if (type < 0)
			die("Not a valid object name %s", obj_name);
 
		/* custom pretty-print here */
		if (type == OBJ_TREE) {
			const char *ls_args[3] = { NULL };
			ls_args[0] =  "ls-tree";
			ls_args[1] =  obj_name;
			return cmd_ls_tree(2, ls_args, NULL);
		}
 
		if (type == OBJ_BLOB)
			return stream_blob_to_fd(1, &oid, NULL, 0);
		buf = read_sha1_file(oid.hash, &type, &size);
		if (!buf)
			die("Cannot read object %s", obj_name);
 
		/* otherwise just spit out the data */
		break;
 
	case 0:
		if (type_from_string(exp_type) == OBJ_BLOB) {
			struct object_id blob_oid;
			if (oid_object_info(&oid, NULL) == OBJ_TAG) {
				char *buffer = read_sha1_file(oid.hash, &type, &size);
				const char *target;
				if (!skip_prefix(buffer, "object ", &target) ||
				    get_oid_hex(target, &blob_oid))
					die("%s not a valid tag", oid_to_hex(&oid));
				free(buffer);
			} else
				oidcpy(&blob_oid, &oid);
 
			if (oid_object_info(&blob_oid, NULL) == OBJ_BLOB)
				return stream_blob_to_fd(1, &blob_oid, NULL, 0);
			/*
			 * we attempted to dereference a tag to a blob
			 * and failed; there may be new dereference
			 * mechanisms this code is not aware of.
			 * fall-back to the usual case.
			 */
		}
		buf = read_object_with_reference(oid.hash, exp_type, &size, NULL);
		break;
 
	default:
		die("git cat-file: unknown option: %s", exp_type);
	}
 
	if (!buf)
		die("git cat-file %s: bad file", obj_name);
 
	write_or_die(1, buf, size);
	free(buf);
	free(obj_context.path);
	return 0;
}
 
struct expand_data {
	struct object_id oid;
	enum object_type type;
	unsigned long size;
	off_t disk_size;
	const char *rest;
	struct object_id delta_base_oid;
 
	/*
	 * If mark_query is true, we do not expand anything, but rather
	 * just mark the object_info with items we wish to query.
	 */
	int mark_query;
 
	/*
	 * Whether to split the input on whitespace before feeding it to
	 * get_sha1; this is decided during the mark_query phase based on
	 * whether we have a %(rest) token in our format.
	 */
	int split_on_whitespace;
 
	/*
	 * After a mark_query run, this object_info is set up to be
	 * passed to sha1_object_info_extended. It will point to the data
	 * elements above, so you can retrieve the response from there.
	 */
	struct object_info info;
 
	/*
	 * This flag will be true if the requested batch format and options
	 * don't require us to call sha1_object_info, which can then be
	 * optimized out.
	 */
	unsigned skip_object_info : 1;
};
 
static int is_atom(const char *atom, const char *s, int slen)
{
	int alen = strlen(atom);
	return alen == slen && !memcmp(atom, s, alen);
}
 
static void expand_atom(struct strbuf *sb, const char *atom, int len,
			void *vdata)
{
	struct expand_data *data = vdata;
 
	if (is_atom("objectname", atom, len)) {
		if (!data->mark_query)
			strbuf_addstr(sb, oid_to_hex(&data->oid));
	} else if (is_atom("objecttype", atom, len)) {
		if (data->mark_query)
			data->info.typep = &data->type;
		else
			strbuf_addstr(sb, type_name(data->type));
	} else if (is_atom("objectsize", atom, len)) {
		if (data->mark_query)
			data->info.sizep = &data->size;
		else
			strbuf_addf(sb, "%lu", data->size);
	} else if (is_atom("objectsize:disk", atom, len)) {
		if (data->mark_query)
			data->info.disk_sizep = &data->disk_size;
		else
			strbuf_addf(sb, "%"PRIuMAX, (uintmax_t)data->disk_size);
	} else if (is_atom("rest", atom, len)) {
		if (data->mark_query)
			data->split_on_whitespace = 1;
		else if (data->rest)
			strbuf_addstr(sb, data->rest);
	} else if (is_atom("deltabase", atom, len)) {
		if (data->mark_query)
			data->info.delta_base_sha1 = data->delta_base_oid.hash;
		else
			strbuf_addstr(sb,
				      oid_to_hex(&data->delta_base_oid));
	} else
		die("unknown format element: %.*s", len, atom);
}
 
static size_t expand_format(struct strbuf *sb, const char *start, void *data)
{
	const char *end;
 
	if (*start != '(')
		return 0;
	end = strchr(start + 1, ')');
	if (!end)
		die("format element '%s' does not end in ')'", start);
 
	expand_atom(sb, start + 1, end - start - 1, data);
 
	return end - start + 1;
}
 
static void batch_write(struct batch_options *opt, const void *data, int len)
{
	if (opt->buffer_output) {
		if (fwrite(data, 1, len, stdout) != len)
			die_errno("unable to write to stdout");
	} else
		write_or_die(1, data, len);
}
 
static void print_object_or_die(struct batch_options *opt, struct expand_data *data)
{
	const struct object_id *oid = &data->oid;
 
	assert(data->info.typep);
 
	if (data->type == OBJ_BLOB) {
		if (opt->buffer_output)
			fflush(stdout);
		if (opt->cmdmode) {
			char *contents;
			unsigned long size;
 
			if (!data->rest)
				die("missing path for '%s'", oid_to_hex(oid));
 
			if (opt->cmdmode == 'w') {
				if (filter_object(data->rest, 0100644, oid,
						  &contents, &size))
					die("could not convert '%s' %s",
					    oid_to_hex(oid), data->rest);
			} else if (opt->cmdmode == 'c') {
				enum object_type type;
				if (!textconv_object(data->rest, 0100644, oid,
						     1, &contents, &size))
					contents = read_sha1_file(oid->hash, &type,
								  &size);
				if (!contents)
					die("could not convert '%s' %s",
					    oid_to_hex(oid), data->rest);
			} else
				die("BUG: invalid cmdmode: %c", opt->cmdmode);
			batch_write(opt, contents, size);
			free(contents);
		} else if (stream_blob_to_fd(1, oid, NULL, 0) < 0)
			die("unable to stream %s to stdout", oid_to_hex(oid));
	}
	else {
		enum object_type type;
		unsigned long size;
		void *contents;
 
		contents = read_sha1_file(oid->hash, &type, &size);
		if (!contents)
			die("object %s disappeared", oid_to_hex(oid));
		if (type != data->type)
			die("object %s changed type!?", oid_to_hex(oid));
		if (data->info.sizep && size != data->size)
			die("object %s changed size!?", oid_to_hex(oid));
 
		batch_write(opt, contents, size);
		free(contents);
	}
}
 
static void batch_object_write(const char *obj_name, struct batch_options *opt,
			       struct expand_data *data)
{
	struct strbuf buf = STRBUF_INIT;
 
	if (!data->skip_object_info &&
	    oid_object_info_extended(&data->oid, &data->info,
				     OBJECT_INFO_LOOKUP_REPLACE) < 0) {
		printf("%s missing\n",
		       obj_name ? obj_name : oid_to_hex(&data->oid));
		fflush(stdout);
		return;
	}
 
	strbuf_expand(&buf, opt->format, expand_format, data);
	strbuf_addch(&buf, '\n');
	batch_write(opt, buf.buf, buf.len);
	strbuf_release(&buf);
 
	if (opt->print_contents) {
		print_object_or_die(opt, data);
		batch_write(opt, "\n", 1);
	}
}
 
static void batch_one_object(const char *obj_name, struct batch_options *opt,
			     struct expand_data *data)
{
	struct object_context ctx;
	int flags = opt->follow_symlinks ? GET_OID_FOLLOW_SYMLINKS : 0;
	enum follow_symlinks_result result;
 
	result = get_oid_with_context(obj_name, flags, &data->oid, &ctx);
	if (result != FOUND) {
		switch (result) {
		case MISSING_OBJECT:
			printf("%s missing\n", obj_name);
			break;
		case DANGLING_SYMLINK:
			printf("dangling %"PRIuMAX"\n%s\n",
			       (uintmax_t)strlen(obj_name), obj_name);
			break;
		case SYMLINK_LOOP:
			printf("loop %"PRIuMAX"\n%s\n",
			       (uintmax_t)strlen(obj_name), obj_name);
			break;
		case NOT_DIR:
			printf("notdir %"PRIuMAX"\n%s\n",
			       (uintmax_t)strlen(obj_name), obj_name);
			break;
		default:
			die("BUG: unknown get_sha1_with_context result %d\n",
			       result);
			break;
		}
		fflush(stdout);
		return;
	}
 
	if (ctx.mode == 0) {
		printf("symlink %"PRIuMAX"\n%s\n",
		       (uintmax_t)ctx.symlink_path.len,
		       ctx.symlink_path.buf);
		fflush(stdout);
		return;
	}
 
	batch_object_write(obj_name, opt, data);
}
 
struct object_cb_data {
	struct batch_options *opt;
	struct expand_data *expand;
};
 
static int batch_object_cb(const struct object_id *oid, void *vdata)
{
	struct object_cb_data *data = vdata;
	oidcpy(&data->expand->oid, oid);
	batch_object_write(NULL, data->opt, data->expand);
	return 0;
}
 
static int batch_loose_object(const struct object_id *oid,
			      const char *path,
			      void *data)
{
	oid_array_append(data, oid);
	return 0;
}
 
static int batch_packed_object(const struct object_id *oid,
			       struct packed_git *pack,
			       uint32_t pos,
			       void *data)
{
	oid_array_append(data, oid);
	return 0;
}
 
static int batch_objects(struct batch_options *opt)
{
	struct strbuf buf = STRBUF_INIT;
	struct expand_data data;
	int save_warning;
	int retval = 0;
 
	if (!opt->format)
		opt->format = "%(objectname) %(objecttype) %(objectsize)";
 
	/*
	 * Expand once with our special mark_query flag, which will prime the
	 * object_info to be handed to sha1_object_info_extended for each
	 * object.
	 */
	memset(&data, 0, sizeof(data));
	data.mark_query = 1;
	strbuf_expand(&buf, opt->format, expand_format, &data);
	data.mark_query = 0;
	if (opt->cmdmode)
		data.split_on_whitespace = 1;
 
	if (opt->all_objects) {
		struct object_info empty = OBJECT_INFO_INIT;
		if (!memcmp(&data.info, &empty, sizeof(empty)))
			data.skip_object_info = 1;
	}
 
	/*
	 * If we are printing out the object, then always fill in the type,
	 * since we will want to decide whether or not to stream.
	 */
	if (opt->print_contents)
		data.info.typep = &data.type;
 
	if (opt->all_objects) {
		struct oid_array sa = OID_ARRAY_INIT;
		struct object_cb_data cb;
 
		for_each_loose_object(batch_loose_object, &sa, 0);
		for_each_packed_object(batch_packed_object, &sa, 0);
		if (repository_format_partial_clone)
			warning("This repository has extensions.partialClone set. Some objects may not be loaded.");
 
		cb.opt = opt;
		cb.expand = &data;
		oid_array_for_each_unique(&sa, batch_object_cb, &cb);
 
		oid_array_clear(&sa);
		return 0;
	}
 
	/*
	 * We are going to call get_sha1 on a potentially very large number of
	 * objects. In most large cases, these will be actual object sha1s. The
	 * cost to double-check that each one is not also a ref (just so we can
	 * warn) ends up dwarfing the actual cost of the object lookups
	 * themselves. We can work around it by just turning off the warning.
	 */
	save_warning = warn_on_object_refname_ambiguity;
	warn_on_object_refname_ambiguity = 0;
 
	while (strbuf_getline(&buf, stdin) != EOF) {
		if (data.split_on_whitespace) {
			/*
			 * Split at first whitespace, tying off the beginning
			 * of the string and saving the remainder (or NULL) in
			 * data.rest.
			 */
			char *p = strpbrk(buf.buf, " \t");
			if (p) {
				while (*p && strchr(" \t", *p))
					*p++ = '\0';
			}
			data.rest = p;
		}
 
		batch_one_object(buf.buf, opt, &data);
	}
 
	strbuf_release(&buf);
	warn_on_object_refname_ambiguity = save_warning;
	return retval;
}
 
static const char * const cat_file_usage[] = {
	N_("git cat-file (-t [--allow-unknown-type] | -s [--allow-unknown-type] | -e | -p | <type> | --textconv | --filters) [--path=<path>] <object>"),
	N_("git cat-file (--batch | --batch-check) [--follow-symlinks] [--textconv | --filters]"),
	NULL
};
 
static int git_cat_file_config(const char *var, const char *value, void *cb)
{
	if (userdiff_config(var, value) < 0)
		return -1;
 
	return git_default_config(var, value, cb);
}
 
static int batch_option_callback(const struct option *opt,
				 const char *arg,
				 int unset)
{
	struct batch_options *bo = opt->value;
 
	if (bo->enabled) {
		return 1;
	}
 
	bo->enabled = 1;
	bo->print_contents = !strcmp(opt->long_name, "batch");
	bo->format = arg;
 
	return 0;
}
 
int cmd_cat_file(int argc, const char **argv, const char *prefix)
{
	int opt = 0;
	const char *exp_type = NULL, *obj_name = NULL;
	struct batch_options batch = {0};
	int unknown_type = 0;
 
	const struct option options[] = {
		OPT_GROUP(N_("<type> can be one of: blob, tree, commit, tag")),
		OPT_CMDMODE('t', NULL, &opt, N_("show object type"), 't'),
		OPT_CMDMODE('s', NULL, &opt, N_("show object size"), 's'),
		OPT_CMDMODE('e', NULL, &opt,
			    N_("exit with zero when there's no error"), 'e'),
		OPT_CMDMODE('p', NULL, &opt, N_("pretty-print object's content"), 'p'),
		OPT_CMDMODE(0, "textconv", &opt,
			    N_("for blob objects, run textconv on object's content"), 'c'),
		OPT_CMDMODE(0, "filters", &opt,
			    N_("for blob objects, run filters on object's content"), 'w'),
		OPT_STRING(0, "path", &force_path, N_("blob"),
			   N_("use a specific path for --textconv/--filters")),
		OPT_BOOL(0, "allow-unknown-type", &unknown_type,
			  N_("allow -s and -t to work with broken/corrupt objects")),
		OPT_BOOL(0, "buffer", &batch.buffer_output, N_("buffer --batch output")),
		{ OPTION_CALLBACK, 0, "batch", &batch, "format",
			N_("show info and content of objects fed from the standard input"),
			PARSE_OPT_OPTARG, batch_option_callback },
		{ OPTION_CALLBACK, 0, "batch-check", &batch, "format",
			N_("show info about objects fed from the standard input"),
			PARSE_OPT_OPTARG, batch_option_callback },
		OPT_BOOL(0, "follow-symlinks", &batch.follow_symlinks,
			 N_("follow in-tree symlinks (used with --batch or --batch-check)")),
		OPT_BOOL(0, "batch-all-objects", &batch.all_objects,
			 N_("show all objects with --batch or --batch-check")),
		OPT_END()
	};
 
	git_config(git_cat_file_config, NULL);
 
	batch.buffer_output = -1;
	argc = parse_options(argc, argv, prefix, options, cat_file_usage, 0);
 
	if (opt) {
		if (batch.enabled && (opt == 'c' || opt == 'w'))
			batch.cmdmode = opt;
		else if (argc == 1)
			obj_name = argv[0];
		else
			usage_with_options(cat_file_usage, options);
	}
	if (!opt && !batch.enabled) {
		if (argc == 2) {
			exp_type = argv[0];
			obj_name = argv[1];
		} else
			usage_with_options(cat_file_usage, options);
	}
	if (batch.enabled) {
		if (batch.cmdmode != opt || argc)
			usage_with_options(cat_file_usage, options);
		if (batch.cmdmode && batch.all_objects)
			die("--batch-all-objects cannot be combined with "
			    "--textconv nor with --filters");
	}
 
	if ((batch.follow_symlinks || batch.all_objects) && !batch.enabled) {
		usage_with_options(cat_file_usage, options);
	}
 
	if (force_path && opt != 'c' && opt != 'w') {
		error("--path=<path> needs --textconv or --filters");
		usage_with_options(cat_file_usage, options);
	}
 
	if (force_path && batch.enabled) {
		error("--path=<path> incompatible with --batch");
		usage_with_options(cat_file_usage, options);
	}
 
	if (batch.buffer_output < 0)
		batch.buffer_output = batch.all_objects;
 
	if (batch.enabled)
		return batch_objects(&batch);
 
	if (unknown_type && opt != 't' && opt != 's')
		die("git cat-file --allow-unknown-type: use with -s or -t");
	return cat_one_file(opt, exp_type, obj_name, unknown_type);
}