git@vger.kernel.org list mirror (unofficial, one of many)
 help / color / mirror / code / Atom feed
blob 1c3dca62e2057bbdb8339e13e10f962befd26857 4189 bytes (raw)
name: chunk-format.c 	 # note: path name is non-authoritative(*)

  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
 
#include "cache.h"
#include "chunk-format.h"
#include "csum-file.h"

/*
 * When writing a chunk-based file format, collect the chunks in
 * an array of chunk_info structs. The size stores the _expected_
 * amount of data that will be written by write_fn.
 */
struct chunk_info {
	uint32_t id;
	uint64_t size;
	chunk_write_fn write_fn;

	const void *start;
};

struct chunkfile {
	struct hashfile *f;

	struct chunk_info *chunks;
	size_t chunks_nr;
	size_t chunks_alloc;
};

struct chunkfile *init_chunkfile(struct hashfile *f)
{
	struct chunkfile *cf = xcalloc(1, sizeof(*cf));
	cf->f = f;
	return cf;
}

void free_chunkfile(struct chunkfile *cf)
{
	if (!cf)
		return;
	free(cf->chunks);
	free(cf);
}

int get_num_chunks(struct chunkfile *cf)
{
	return cf->chunks_nr;
}

void add_chunk(struct chunkfile *cf,
	       uint32_t id,
	       size_t size,
	       chunk_write_fn fn)
{
	ALLOC_GROW(cf->chunks, cf->chunks_nr + 1, cf->chunks_alloc);

	cf->chunks[cf->chunks_nr].id = id;
	cf->chunks[cf->chunks_nr].write_fn = fn;
	cf->chunks[cf->chunks_nr].size = size;
	cf->chunks_nr++;
}

int write_chunkfile(struct chunkfile *cf, void *data)
{
	int i, result = 0;
	uint64_t cur_offset = hashfile_total(cf->f);

	trace2_region_enter("chunkfile", "write", the_repository);

	/* Add the table of contents to the current offset */
	cur_offset += (cf->chunks_nr + 1) * CHUNK_TOC_ENTRY_SIZE;

	for (i = 0; i < cf->chunks_nr; i++) {
		hashwrite_be32(cf->f, cf->chunks[i].id);
		hashwrite_be64(cf->f, cur_offset);

		cur_offset += cf->chunks[i].size;
	}

	/* Trailing entry marks the end of the chunks */
	hashwrite_be32(cf->f, 0);
	hashwrite_be64(cf->f, cur_offset);

	for (i = 0; i < cf->chunks_nr; i++) {
		off_t start_offset = hashfile_total(cf->f);
		result = cf->chunks[i].write_fn(cf->f, data);

		if (result)
			goto cleanup;

		if (hashfile_total(cf->f) - start_offset != cf->chunks[i].size)
			BUG("expected to write %"PRId64" bytes to chunk %"PRIx32", but wrote %"PRId64" instead",
			    cf->chunks[i].size, cf->chunks[i].id,
			    hashfile_total(cf->f) - start_offset);
	}

cleanup:
	trace2_region_leave("chunkfile", "write", the_repository);
	return result;
}

int read_table_of_contents(struct chunkfile *cf,
			   const unsigned char *mfile,
			   size_t mfile_size,
			   uint64_t toc_offset,
			   int toc_length)
{
	int i;
	uint32_t chunk_id;
	const unsigned char *table_of_contents = mfile + toc_offset;

	ALLOC_GROW(cf->chunks, toc_length, cf->chunks_alloc);

	while (toc_length--) {
		uint64_t chunk_offset, next_chunk_offset;

		chunk_id = get_be32(table_of_contents);
		chunk_offset = get_be64(table_of_contents + 4);

		if (!chunk_id) {
			error(_("terminating chunk id appears earlier than expected"));
			return 1;
		}

		table_of_contents += CHUNK_TOC_ENTRY_SIZE;
		next_chunk_offset = get_be64(table_of_contents + 4);

		if (next_chunk_offset < chunk_offset ||
		    next_chunk_offset > mfile_size - the_hash_algo->rawsz) {
			error(_("improper chunk offset(s) %"PRIx64" and %"PRIx64""),
			      chunk_offset, next_chunk_offset);
			return -1;
		}

		for (i = 0; i < cf->chunks_nr; i++) {
			if (cf->chunks[i].id == chunk_id) {
				error(_("duplicate chunk ID %"PRIx32" found"),
					chunk_id);
				return -1;
			}
		}

		cf->chunks[cf->chunks_nr].id = chunk_id;
		cf->chunks[cf->chunks_nr].start = mfile + chunk_offset;
		cf->chunks[cf->chunks_nr].size = next_chunk_offset - chunk_offset;
		cf->chunks_nr++;
	}

	chunk_id = get_be32(table_of_contents);
	if (chunk_id) {
		error(_("final chunk has non-zero id %"PRIx32""), chunk_id);
		return -1;
	}

	return 0;
}

static int pair_chunk_fn(const unsigned char *chunk_start,
			 size_t chunk_size,
			 void *data)
{
	const unsigned char **p = data;
	*p = chunk_start;
	return 0;
}

int pair_chunk(struct chunkfile *cf,
	       uint32_t chunk_id,
	       const unsigned char **p)
{
	return read_chunk(cf, chunk_id, pair_chunk_fn, p);
}

int read_chunk(struct chunkfile *cf,
	       uint32_t chunk_id,
	       chunk_read_fn fn,
	       void *data)
{
	int i;

	for (i = 0; i < cf->chunks_nr; i++) {
		if (cf->chunks[i].id == chunk_id)
			return fn(cf->chunks[i].start, cf->chunks[i].size, data);
	}

	return CHUNK_NOT_FOUND;
}

debug log:

solving 1c3dca62e205 ...
found 1c3dca62e205 in https://80x24.org/mirrors/git.git

(*) Git path names are given by the tree(s) the blob belongs to.
    Blobs themselves have no identifier aside from the hash of its contents.^

Code repositories for project(s) associated with this public inbox

	https://80x24.org/mirrors/git.git

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).