git@vger.kernel.org list mirror (unofficial, one of many)
 help / color / Atom feed
70b14fdf414355cb5a48f35c975027b45cd59ea7 blob 7423 bytes (raw)

  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
 
/*
 * Copyright (c) 2011, Google Inc.
 */
#include "cache.h"
#include "bulk-checkin.h"
#include "csum-file.h"
#include "pack.h"
#include "strbuf.h"
#include "packfile.h"

static struct bulk_checkin_state {
	unsigned plugged:1;

	char *pack_tmp_name;
	struct hashfile *f;
	off_t offset;
	struct pack_idx_option pack_idx_opts;

	struct pack_idx_entry **written;
	uint32_t alloc_written;
	uint32_t nr_written;
} state;

static void finish_bulk_checkin(struct bulk_checkin_state *state)
{
	struct object_id oid;
	struct strbuf packname = STRBUF_INIT;
	int i;

	if (!state->f)
		return;

	if (state->nr_written == 0) {
		close(state->f->fd);
		unlink(state->pack_tmp_name);
		goto clear_exit;
	} else if (state->nr_written == 1) {
		finalize_hashfile(state->f, oid.hash, CSUM_HASH_IN_STREAM | CSUM_FSYNC | CSUM_CLOSE);
	} else {
		int fd = finalize_hashfile(state->f, oid.hash, 0);
		fixup_pack_header_footer(fd, oid.hash, state->pack_tmp_name,
					 state->nr_written, oid.hash,
					 state->offset);
		close(fd);
	}

	strbuf_addf(&packname, "%s/pack/pack-", get_object_directory());
	finish_tmp_packfile(&packname, state->pack_tmp_name,
			    state->written, state->nr_written,
			    &state->pack_idx_opts, oid.hash);
	for (i = 0; i < state->nr_written; i++)
		free(state->written[i]);

clear_exit:
	free(state->written);
	memset(state, 0, sizeof(*state));

	strbuf_release(&packname);
	/* Make objects we just wrote available to ourselves */
	reprepare_packed_git();
}

static int already_written(struct bulk_checkin_state *state, unsigned char sha1[])
{
	int i;

	/* The object may already exist in the repository */
	if (has_sha1_file(sha1))
		return 1;

	/* Might want to keep the list sorted */
	for (i = 0; i < state->nr_written; i++)
		if (!hashcmp(state->written[i]->oid.hash, sha1))
			return 1;

	/* This is a new object we need to keep */
	return 0;
}

/*
 * Read the contents from fd for size bytes, streaming it to the
 * packfile in state while updating the hash in ctx. Signal a failure
 * by returning a negative value when the resulting pack would exceed
 * the pack size limit and this is not the first object in the pack,
 * so that the caller can discard what we wrote from the current pack
 * by truncating it and opening a new one. The caller will then call
 * us again after rewinding the input fd.
 *
 * The already_hashed_to pointer is kept untouched by the caller to
 * make sure we do not hash the same byte when we are called
 * again. This way, the caller does not have to checkpoint its hash
 * status before calling us just in case we ask it to call us again
 * with a new pack.
 */
static int stream_to_pack(struct bulk_checkin_state *state,
			  git_hash_ctx *ctx, off_t *already_hashed_to,
			  int fd, size_t size, enum object_type type,
			  const char *path, unsigned flags)
{
	git_zstream s;
	unsigned char obuf[16384];
	unsigned hdrlen;
	int status = Z_OK;
	int write_object = (flags & HASH_WRITE_OBJECT);
	off_t offset = 0;

	git_deflate_init(&s, pack_compression_level);

	hdrlen = encode_in_pack_object_header(obuf, sizeof(obuf), type, size);
	s.next_out = obuf + hdrlen;
	s.avail_out = sizeof(obuf) - hdrlen;

	while (status != Z_STREAM_END) {
		unsigned char ibuf[16384];

		if (size && !s.avail_in) {
			ssize_t rsize = size < sizeof(ibuf) ? size : sizeof(ibuf);
			ssize_t read_result = read_in_full(fd, ibuf, rsize);
			if (read_result < 0)
				die_errno("failed to read from '%s'", path);
			if (read_result != rsize)
				die("failed to read %d bytes from '%s'",
				    (int)rsize, path);
			offset += rsize;
			if (*already_hashed_to < offset) {
				size_t hsize = offset - *already_hashed_to;
				if (rsize < hsize)
					hsize = rsize;
				if (hsize)
					the_hash_algo->update_fn(ctx, ibuf, hsize);
				*already_hashed_to = offset;
			}
			s.next_in = ibuf;
			s.avail_in = rsize;
			size -= rsize;
		}

		status = git_deflate(&s, size ? 0 : Z_FINISH);

		if (!s.avail_out || status == Z_STREAM_END) {
			if (write_object) {
				size_t written = s.next_out - obuf;

				/* would we bust the size limit? */
				if (state->nr_written &&
				    pack_size_limit_cfg &&
				    pack_size_limit_cfg < state->offset + written) {
					git_deflate_abort(&s);
					return -1;
				}

				hashwrite(state->f, obuf, written);
				state->offset += written;
			}
			s.next_out = obuf;
			s.avail_out = sizeof(obuf);
		}

		switch (status) {
		case Z_OK:
		case Z_BUF_ERROR:
		case Z_STREAM_END:
			continue;
		default:
			die("unexpected deflate failure: %d", status);
		}
	}
	git_deflate_end(&s);
	return 0;
}

/* Lazily create backing packfile for the state */
static void prepare_to_stream(struct bulk_checkin_state *state,
			      unsigned flags)
{
	if (!(flags & HASH_WRITE_OBJECT) || state->f)
		return;

	state->f = create_tmp_packfile(&state->pack_tmp_name);
	reset_pack_idx_option(&state->pack_idx_opts);

	/* Pretend we are going to write only one object */
	state->offset = write_pack_header(state->f, 1);
	if (!state->offset)
		die_errno("unable to write pack header");
}

static int deflate_to_pack(struct bulk_checkin_state *state,
			   unsigned char result_sha1[],
			   int fd, size_t size,
			   enum object_type type, const char *path,
			   unsigned flags)
{
	off_t seekback, already_hashed_to;
	git_hash_ctx ctx;
	unsigned char obuf[16384];
	unsigned header_len;
	struct hashfile_checkpoint checkpoint;
	struct pack_idx_entry *idx = NULL;

	seekback = lseek(fd, 0, SEEK_CUR);
	if (seekback == (off_t) -1)
		return error("cannot find the current offset");

	header_len = xsnprintf((char *)obuf, sizeof(obuf), "%s %" PRIuMAX,
			       type_name(type), (uintmax_t)size) + 1;
	the_hash_algo->init_fn(&ctx);
	the_hash_algo->update_fn(&ctx, obuf, header_len);

	/* Note: idx is non-NULL when we are writing */
	if ((flags & HASH_WRITE_OBJECT) != 0)
		idx = xcalloc(1, sizeof(*idx));

	already_hashed_to = 0;

	while (1) {
		prepare_to_stream(state, flags);
		if (idx) {
			hashfile_checkpoint(state->f, &checkpoint);
			idx->offset = state->offset;
			crc32_begin(state->f);
		}
		if (!stream_to_pack(state, &ctx, &already_hashed_to,
				    fd, size, type, path, flags))
			break;
		/*
		 * Writing this object to the current pack will make
		 * it too big; we need to truncate it, start a new
		 * pack, and write into it.
		 */
		if (!idx)
			die("BUG: should not happen");
		hashfile_truncate(state->f, &checkpoint);
		state->offset = checkpoint.offset;
		finish_bulk_checkin(state);
		if (lseek(fd, seekback, SEEK_SET) == (off_t) -1)
			return error("cannot seek back");
	}
	the_hash_algo->final_fn(result_sha1, &ctx);
	if (!idx)
		return 0;

	idx->crc32 = crc32_end(state->f);
	if (already_written(state, result_sha1)) {
		hashfile_truncate(state->f, &checkpoint);
		state->offset = checkpoint.offset;
		free(idx);
	} else {
		hashcpy(idx->oid.hash, result_sha1);
		ALLOC_GROW(state->written,
			   state->nr_written + 1,
			   state->alloc_written);
		state->written[state->nr_written++] = idx;
	}
	return 0;
}

int index_bulk_checkin(unsigned char *sha1,
		       int fd, size_t size, enum object_type type,
		       const char *path, unsigned flags)
{
	int status = deflate_to_pack(&state, sha1, fd, size, type,
				     path, flags);
	if (!state.plugged)
		finish_bulk_checkin(&state);
	return status;
}

void plug_bulk_checkin(void)
{
	state.plugged = 1;
}

void unplug_bulk_checkin(void)
{
	state.plugged = 0;
	if (state.f)
		finish_bulk_checkin(&state);
}
debug log:

solving 70b14fdf41 ...
found 70b14fdf41 in https://80x24.org/mirrors/git.git

git@vger.kernel.org list mirror (unofficial, one of many)

Archives are clonable:
	git clone --mirror https://public-inbox.org/git
	git clone --mirror http://ou63pmih66umazou.onion/git
	git clone --mirror http://czquwvybam4bgbro.onion/git
	git clone --mirror http://hjrcffqmbrq6wope.onion/git

Newsgroups are available over NNTP:
	nntp://news.public-inbox.org/inbox.comp.version-control.git
	nntp://ou63pmih66umazou.onion/inbox.comp.version-control.git
	nntp://czquwvybam4bgbro.onion/inbox.comp.version-control.git
	nntp://hjrcffqmbrq6wope.onion/inbox.comp.version-control.git
	nntp://news.gmane.org/gmane.comp.version-control.git

 note: .onion URLs require Tor: https://www.torproject.org/

AGPL code for this site: git clone https://public-inbox.org/ public-inbox