reftable/block: create public interface for reading blocks

While users of the reftable library wouldn't generally require access to
individual blocks in a reftable table, there are valid usecases where
one may require low-level access to them. One such upcoming usecase in
the Git codebase is to implement consistency checks for the reftable
library where we want to verify each block individually.

Create a public interface for reading blocks. The interface isn't yet
complete and lacks e.g. a way to read individual records from a block.
Such missing functionality will be backfilled in subsequent commits.

Note that this change also requires us to expose `reftable_buf`, which
is used by the `reftable_block_first_key()` function.

Signed-off-by: Patrick Steinhardt <ps@pks.im>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
maint
Patrick Steinhardt 2025-04-07 15:16:21 +02:00 committed by Junio C Hamano
parent ce76cec964
commit 655e18d6b4
4 changed files with 78 additions and 54 deletions

View File

@ -18,13 +18,6 @@

#define REFTABLE_UNUSED __attribute__((__unused__))

struct reftable_buf {
size_t alloc;
size_t len;
char *buf;
};
#define REFTABLE_BUF_INIT { 0 }

/*
* Initialize the buffer such that it is ready for use. This is equivalent to
* using REFTABLE_BUF_INIT for stack-allocated variables.

View File

@ -11,6 +11,7 @@

#include "basics.h"
#include "record.h"
#include "reftable-block.h"
#include "reftable-blocksource.h"

/*
@ -62,53 +63,6 @@ int block_writer_finish(struct block_writer *w);
/* clears out internally allocated block_writer members. */
void block_writer_release(struct block_writer *bw);

/*
* A block part of a reftable. Contains records as well as some metadata
* describing them.
*/
struct reftable_block {
/* offset of the block header; nonzero for the first block in a
* reftable. */
uint32_t header_off;

/* the memory block */
struct reftable_block_data block_data;
uint32_t hash_size;

/* Uncompressed data for log entries. */
struct z_stream_s *zstream;
unsigned char *uncompressed_data;
size_t uncompressed_cap;

/*
* Restart point data. Restart points are located after the block's
* record data.
*/
uint16_t restart_count;
uint32_t restart_off;

/* size of the data in the file. For log blocks, this is the compressed
* size. */
uint32_t full_block_size;
uint8_t block_type;
};

/*
* Initialize a reftable block from the given block source.
*/
int reftable_block_init(struct reftable_block *b,
struct reftable_block_source *source,
uint32_t offset, uint32_t header_size,
uint32_t table_block_size, uint32_t hash_size);

void reftable_block_release(struct reftable_block *b);

/* Returns the block type (eg. 'r' for refs) */
uint8_t reftable_block_type(const struct reftable_block *b);

/* Decodes the first key in the block */
int reftable_block_first_key(const struct reftable_block *b, struct reftable_buf *key);

/* Iterate over entries in a block */
struct block_iter {
/* offset within the block of the next entry to read. */

View File

@ -11,6 +11,14 @@

#include <stddef.h>

/* A buffer that contains arbitrary byte slices. */
struct reftable_buf {
size_t alloc;
size_t len;
char *buf;
};
#define REFTABLE_BUF_INIT { 0 }

/*
* Hash functions understood by the reftable library. Note that the values are
* arbitrary and somewhat random such that we can easily detect cases where the

69
reftable/reftable-block.h Normal file
View File

@ -0,0 +1,69 @@
/*
* Copyright 2020 Google LLC
*
* Use of this source code is governed by a BSD-style
* license that can be found in the LICENSE file or at
* https://developers.google.com/open-source/licenses/bsd
*/

#ifndef REFTABLE_BLOCK_H
#define REFTABLE_BLOCK_H

#include <stdint.h>

#include "reftable-basics.h"
#include "reftable-blocksource.h"

struct z_stream_s;

/*
* A block part of a reftable. Contains records as well as some metadata
* describing them.
*/
struct reftable_block {
/*
* Offset of the block header; nonzero for the first block in a
* reftable.
*/
uint32_t header_off;

/* The memory block. */
struct reftable_block_data block_data;
uint32_t hash_size;

/* Uncompressed data for log entries. */
struct z_stream_s *zstream;
unsigned char *uncompressed_data;
size_t uncompressed_cap;

/*
* Restart point data. Restart points are located after the block's
* record data.
*/
uint16_t restart_count;
uint32_t restart_off;

/*
* Size of the data in the file. For log blocks, this is the compressed
* size.
*/
uint32_t full_block_size;
uint8_t block_type;
};

/* Initialize a reftable block from the given block source. */
int reftable_block_init(struct reftable_block *b,
struct reftable_block_source *source,
uint32_t offset, uint32_t header_size,
uint32_t table_block_size, uint32_t hash_size);

/* Release resources allocated by the block. */
void reftable_block_release(struct reftable_block *b);

/* Returns the block type (eg. 'r' for refs). */
uint8_t reftable_block_type(const struct reftable_block *b);

/* Decodes the first key in the block. */
int reftable_block_first_key(const struct reftable_block *b, struct reftable_buf *key);

#endif /* REFTABLE_BLOCK_H */