[thirdparty/git.git] / bulk-checkin.c

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

static int pack_compression_level = Z_DEFAULT_COMPRESSION;

static struct bulk_checkin_state {
	unsigned plugged:1;

	char *pack_tmp_name;
	struct sha1file *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)
{
	unsigned char sha1[20];
	char packname[PATH_MAX];
	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) {
		sha1close(state->f, sha1, CSUM_FSYNC);
	} else {
		int fd = sha1close(state->f, sha1, 0);
		fixup_pack_header_footer(fd, sha1, state->pack_tmp_name,
					 state->nr_written, sha1,
					 state->offset);
		close(fd);
	}

	sprintf(packname, "%s/pack/pack-", get_object_directory());
	finish_tmp_packfile(packname, state->pack_tmp_name,
			    state->written, state->nr_written,
			    &state->pack_idx_opts, sha1);
	for (i = 0; i < state->nr_written; i++)
		free(state->written[i]);

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

	/* 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]->sha1, 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_SHA_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;

	memset(&s, 0, sizeof(s));
	git_deflate_init(&s, pack_compression_level);

	hdrlen = encode_in_pack_object_header(type, size, obuf);
	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);
			if (xread(fd, ibuf, rsize) != 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)
					git_SHA1_Update(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;
				}

				sha1write(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_SHA_CTX ctx;
	unsigned char obuf[16384];
	unsigned header_len;
	struct sha1file_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 = sprintf((char *)obuf, "%s %" PRIuMAX,
			     typename(type), (uintmax_t)size) + 1;
	git_SHA1_Init(&ctx);
	git_SHA1_Update(&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) {
			sha1file_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");
		sha1file_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");
	}
	git_SHA1_Final(result_sha1, &ctx);
	if (!idx)
		return 0;

	idx->crc32 = crc32_end(state->f);
	if (already_written(state, result_sha1)) {
		sha1file_truncate(state->f, &checkpoint);
		state->offset = checkpoint.offset;
		free(idx);
	} else {
		hashcpy(idx->sha1, 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);
}
Commit	Line	Data
568508e7 JH	1	/*
	2	* Copyright (c) 2011, Google Inc.
	3	*/
	4	#include "bulk-checkin.h"
	5	#include "csum-file.h"
	6	#include "pack.h"
	7
	8	static int pack_compression_level = Z_DEFAULT_COMPRESSION;
	9
	10	static struct bulk_checkin_state {
	11	unsigned plugged:1;
	12
	13	char *pack_tmp_name;
	14	struct sha1file *f;
	15	off_t offset;
	16	struct pack_idx_option pack_idx_opts;
	17
	18	struct pack_idx_entry **written;
	19	uint32_t alloc_written;
	20	uint32_t nr_written;
	21	} state;
	22
	23	static void finish_bulk_checkin(struct bulk_checkin_state *state)
	24	{
	25	unsigned char sha1[20];
	26	char packname[PATH_MAX];
	27	int i;
	28
	29	if (!state->f)
	30	return;
	31
	32	if (state->nr_written == 0) {
	33	close(state->f->fd);
	34	unlink(state->pack_tmp_name);
	35	goto clear_exit;
	36	} else if (state->nr_written == 1) {
	37	sha1close(state->f, sha1, CSUM_FSYNC);
	38	} else {
	39	int fd = sha1close(state->f, sha1, 0);
	40	fixup_pack_header_footer(fd, sha1, state->pack_tmp_name,
	41	state->nr_written, sha1,
	42	state->offset);
	43	close(fd);
	44	}
	45
	46	sprintf(packname, "%s/pack/pack-", get_object_directory());
	47	finish_tmp_packfile(packname, state->pack_tmp_name,
	48	state->written, state->nr_written,
	49	&state->pack_idx_opts, sha1);
	50	for (i = 0; i < state->nr_written; i++)
	51	free(state->written[i]);
	52
	53	clear_exit:
	54	free(state->written);
	55	memset(state, 0, sizeof(*state));
	56
	57	/* Make objects we just wrote available to ourselves */
	58	reprepare_packed_git();
	59	}
	60
	61	static int already_written(struct bulk_checkin_state *state, unsigned char sha1[])
	62	{
	63	int i;
	64
65	/* The object may already exist in the repository */
66	if (has_sha1_file(sha1))
67	return 1;
68
69	/* Might want to keep the list sorted */
70	for (i = 0; i < state->nr_written; i++)
71	if (!hashcmp(state->written[i]->sha1, sha1))
72	return 1;
73
74	/* This is a new object we need to keep */
75	return 0;
76	}
77
78	/*
79	* Read the contents from fd for size bytes, streaming it to the
80	* packfile in state while updating the hash in ctx. Signal a failure
81	* by returning a negative value when the resulting pack would exceed
82	* the pack size limit and this is not the first object in the pack,
83	* so that the caller can discard what we wrote from the current pack
84	* by truncating it and opening a new one. The caller will then call
85	* us again after rewinding the input fd.
86	*
87	* The already_hashed_to pointer is kept untouched by the caller to
88	* make sure we do not hash the same byte when we are called
89	* again. This way, the caller does not have to checkpoint its hash
90	* status before calling us just in case we ask it to call us again
91	* with a new pack.
92	*/
93	static int stream_to_pack(struct bulk_checkin_state *state,
94	git_SHA_CTX ctx, off_t already_hashed_to,
95	int fd, size_t size, enum object_type type,
96	const char *path, unsigned flags)
97	{
98	git_zstream s;
99	unsigned char obuf[16384];
100	unsigned hdrlen;
101	int status = Z_OK;
102	int write_object = (flags & HASH_WRITE_OBJECT);
103	off_t offset = 0;
104
105	memset(&s, 0, sizeof(s));
106	git_deflate_init(&s, pack_compression_level);
107
108	hdrlen = encode_in_pack_object_header(type, size, obuf);
109	s.next_out = obuf + hdrlen;
110	s.avail_out = sizeof(obuf) - hdrlen;
111
112	while (status != Z_STREAM_END) {
113	unsigned char ibuf[16384];
114
115	if (size && !s.avail_in) {
116	ssize_t rsize = size < sizeof(ibuf) ? size : sizeof(ibuf);
117	if (xread(fd, ibuf, rsize) != rsize)
118	die("failed to read %d bytes from '%s'",
119	(int)rsize, path);
120	offset += rsize;
121	if (*already_hashed_to < offset) {
122	size_t hsize = offset - *already_hashed_to;
123	if (rsize < hsize)
124	hsize = rsize;
125	if (hsize)
126	git_SHA1_Update(ctx, ibuf, hsize);
127	*already_hashed_to = offset;
128	}
129	s.next_in = ibuf;
130	s.avail_in = rsize;
131	size -= rsize;
132	}
133
134	status = git_deflate(&s, size ? 0 : Z_FINISH);
135
136	if (!s.avail_out \|\| status == Z_STREAM_END) {
137	if (write_object) {
138	size_t written = s.next_out - obuf;
139
140	/* would we bust the size limit? */
141	if (state->nr_written &&
142	pack_size_limit_cfg &&
143	pack_size_limit_cfg < state->offset + written) {
144	git_deflate_abort(&s);
145	return -1;
146	}
147
148	sha1write(state->f, obuf, written);
149	state->offset += written;
150	}
151	s.next_out = obuf;
152	s.avail_out = sizeof(obuf);
153	}
154
155	switch (status) {
156	case Z_OK:
157	case Z_BUF_ERROR:
158	case Z_STREAM_END:
159	continue;
160	default:
161	die("unexpected deflate failure: %d", status);
162	}
163	}
164	git_deflate_end(&s);
165	return 0;
166	}
167
168	/* Lazily create backing packfile for the state */
169	static void prepare_to_stream(struct bulk_checkin_state *state,
170	unsigned flags)
171	{
172	if (!(flags & HASH_WRITE_OBJECT) \|\| state->f)
173	return;
174
175	state->f = create_tmp_packfile(&state->pack_tmp_name);
176	reset_pack_idx_option(&state->pack_idx_opts);
177
178	/* Pretend we are going to write only one object */
179	state->offset = write_pack_header(state->f, 1);
180	if (!state->offset)
181	die_errno("unable to write pack header");
182	}
183
184	static int deflate_to_pack(struct bulk_checkin_state *state,
185	unsigned char result_sha1[],
186	int fd, size_t size,
187	enum object_type type, const char *path,
188	unsigned flags)
189	{
190	off_t seekback, already_hashed_to;
191	git_SHA_CTX ctx;
192	unsigned char obuf[16384];
193	unsigned header_len;
194	struct sha1file_checkpoint checkpoint;
195	struct pack_idx_entry *idx = NULL;
196
197	seekback = lseek(fd, 0, SEEK_CUR);
198	if (seekback == (off_t) -1)
199	return error("cannot find the current offset");
200
201	header_len = sprintf((char *)obuf, "%s %" PRIuMAX,
202	typename(type), (uintmax_t)size) + 1;
203	git_SHA1_Init(&ctx);
204	git_SHA1_Update(&ctx, obuf, header_len);
205
206	/* Note: idx is non-NULL when we are writing */
207	if ((flags & HASH_WRITE_OBJECT) != 0)
208	idx = xcalloc(1, sizeof(*idx));
209
210	already_hashed_to = 0;
211
212	while (1) {
213	prepare_to_stream(state, flags);
214	if (idx) {
215	sha1file_checkpoint(state->f, &checkpoint);
216	idx->offset = state->offset;
217	crc32_begin(state->f);
218	}
219	if (!stream_to_pack(state, &ctx, &already_hashed_to,
220	fd, size, type, path, flags))
221	break;
222	/*
223	* Writing this object to the current pack will make
224	* it too big; we need to truncate it, start a new
225	* pack, and write into it.
226	*/
227	if (!idx)
228	die("BUG: should not happen");
229	sha1file_truncate(state->f, &checkpoint);
230	state->offset = checkpoint.offset;
231	finish_bulk_checkin(state);
232	if (lseek(fd, seekback, SEEK_SET) == (off_t) -1)
233	return error("cannot seek back");
234	}
235	git_SHA1_Final(result_sha1, &ctx);
236	if (!idx)
237	return 0;
238
239	idx->crc32 = crc32_end(state->f);
240	if (already_written(state, result_sha1)) {
241	sha1file_truncate(state->f, &checkpoint);
242	state->offset = checkpoint.offset;
243	free(idx);
244	} else {
245	hashcpy(idx->sha1, result_sha1);
246	ALLOC_GROW(state->written,
247	state->nr_written + 1,
248	state->alloc_written);
249	state->written[state->nr_written++] = idx;
250	}
251	return 0;
252	}
253
254	int index_bulk_checkin(unsigned char *sha1,
255	int fd, size_t size, enum object_type type,
256	const char *path, unsigned flags)
257	{
258	int status = deflate_to_pack(&state, sha1, fd, size, type,
259	path, flags);
260	if (!state.plugged)
261	finish_bulk_checkin(&state);
262	return status;
263	}
264
265	void plug_bulk_checkin(void)
266	{
267	state.plugged = 1;
268	}
269
270	void unplug_bulk_checkin(void)
271	{
272	state.plugged = 0;
273	if (state.f)
274	finish_bulk_checkin(&state);
275	}