chunk-format: create chunk format write API

In anticipation of combining the logic from the commit-graph and
multi-pack-index file formats, create a new chunk-format API. Use a
'struct chunkfile' pointer to keep track of data that has been
registered for writes. This struct is anonymous outside of
chunk-format.c to ensure no user attempts to interfere with the data.

The next change will use this API in commit-graph.c, but the general
approach is:

 1. initialize the chunkfile with init_chunkfile(f).
 2. add chunks in the intended writing order with add_chunk().
 3. write any header information to the hashfile f.
 4. write the chunkfile data using write_chunkfile().
 5. free the chunkfile struct using free_chunkfile().

Helped-by: Taylor Blau <me@ttaylorr.com>
Helped-by: Junio C Hamano <gitster@pobox.com>
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
This commit is contained in:
Derrick Stolee 2021-02-18 14:07:24 +00:00 committed by Junio C Hamano
parent eb9071912f
commit 570df42610
3 changed files with 112 additions and 0 deletions

View File

@ -854,6 +854,7 @@ LIB_OBJS += bundle.o
LIB_OBJS += cache-tree.o
LIB_OBJS += chdir-notify.o
LIB_OBJS += checkout.o
LIB_OBJS += chunk-format.o
LIB_OBJS += color.o
LIB_OBJS += column.o
LIB_OBJS += combine-diff.o

90
chunk-format.c Normal file
View File

@ -0,0 +1,90 @@
#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;
};
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;
uint64_t cur_offset = hashfile_total(cf->f);
/* 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);
int result = cf->chunks[i].write_fn(cf->f, data);
if (result)
return result;
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);
}
return 0;
}

21
chunk-format.h Normal file
View File

@ -0,0 +1,21 @@
#ifndef CHUNK_FORMAT_H
#define CHUNK_FORMAT_H
#include "git-compat-util.h"
struct hashfile;
struct chunkfile;
#define CHUNK_TOC_ENTRY_SIZE (sizeof(uint32_t) + sizeof(uint64_t))
struct chunkfile *init_chunkfile(struct hashfile *f);
void free_chunkfile(struct chunkfile *cf);
int get_num_chunks(struct chunkfile *cf);
typedef int (*chunk_write_fn)(struct hashfile *f, void *data);
void add_chunk(struct chunkfile *cf,
uint32_t id,
size_t size,
chunk_write_fn fn);
int write_chunkfile(struct chunkfile *cf, void *data);
#endif