Skip to content

Improve HDF5 support #200

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
gpregger-ethz wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Improve HDF5 support #200

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ce8625d
initial support for hdf5 superblock parsing
gpregger-ethz Feb 10, 2026
9e75cde
conform with ISO C 90 (hopefully), catch errors on stream seek / read…
gpregger-ethz Mar 5, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
89 changes: 82 additions & 7 deletions src/file_hdf5.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@
Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.

*/

#if !defined(SINGLE_FORMAT) || defined(SINGLE_FORMAT_hdf5)
#ifdef HAVE_CONFIG_H
#include <config.h>
Expand All @@ -34,17 +34,17 @@
#include "types.h"
#include "filegen.h"
#include "common.h"
#ifdef DEBUG_HDF
#ifdef DEBUG_HDF5
#include "log.h"
#endif

/*@ requires valid_register_header_check(file_stat); */
static void register_header_check_hdf5(file_stat_t *file_stat);

const file_hint_t file_hint_hdf5= {
.extension="hdf",
.extension="h5",
.description="Hierarchical Data Format 5",
.max_filesize=PHOTOREC_MAX_SIZE_32,
.max_filesize=PHOTOREC_MAX_FILE_SIZE,
.recover=1,
.enable_by_default=1,
.register_header_check=&register_header_check_hdf5
Expand All @@ -54,7 +54,80 @@ struct hdf5_superblock
{
uint8_t signature[8];
uint8_t version;
};
uint8_t version_global_free_space_storage;
uint8_t version_root_group_symbol_table_entry;
uint8_t reserved;
uint8_t version_shared_header_message_format;
uint8_t offsets_size;
uint8_t lengths_size;
// if version == 0, Base Address etc start at offset 24, if version >1 at offset 28
// Offset Base Address = (bool)version*4 + 24 + 0*offsets_size
// Offset Address of Global Free-Space Heap = (bool)version*4 + 24 + 1*offset_size
// Offset End of File Address = (bool)version*4 + 24 + 2*offset_size
// Size of End of File Address = offset_size
} __attribute__ ((gcc_struct, __packed__));

/*@
@ requires \separated(file_recovery, file_recovery->handle, &errno, &Frama_C_entropy_source, &__fc_heap_status);
@ requires valid_file_check_param(file_recovery);
@ ensures valid_file_check_result(file_recovery);
@*/
static void file_check_hdf5(file_recovery_t *file_recovery)
{
FILE *handle = file_recovery->handle;
uint8_t sb_version_offset = 8;
uint8_t sb_offsets_size_offset = 0x0D;
uint8_t sb_meta_base_address_offset = 0x18;
uint8_t sb_version = 0;
uint8_t sb_offsets_size = 0;
uint8_t eof_address_offset;
uint64_t eof_address = 0;
/* Get superblock version */
if (my_fseek(handle, sb_version_offset, SEEK_SET) < 0 ||
fread(&sb_version, 1, 1, handle) != 1)
{
#ifdef DEBUG_HDF5
log_error("HDF5: Couldn't read superblock version");
#endif
return;
}
#ifdef DEBUG_HDF5
log_info("HDF5: superblock version = %u\n", sb_version);
#endif
/* Adjust sb_meta_base_address_offset if hdf5 version is >0 */
if (sb_version)
sb_meta_base_address_offset = 0x1C;
#ifdef DEBUG_HDF5
log_info("HDF5: sb_meta_base_address_offset = 0x%02X\n", sb_meta_base_address_offset);
#endif
/* Get size of offsets */
if (my_fseek(handle, sb_offsets_size_offset, SEEK_SET) < 0 ||
fread(&sb_offsets_size, 1, 1, handle) != 1)
{
#ifdef DEBUG_HDF5
log_error("HDF5: Couldn't read HDF Size of Offsets");
#endif
return;
}
#ifdef DEBUG_HDF5
log_info("HDF5: sb_offsets_size = %u\n", sb_offsets_size);
#endif
/* Get EOF Address */
eof_address_offset = sb_meta_base_address_offset + 2*sb_offsets_size;
if (my_fseek(handle, eof_address_offset, SEEK_SET) < 0 ||
fread(&eof_address, sb_offsets_size, 1, handle) != 1)
{
#ifdef DEBUG_HDF5
log_error("HDF5: Couldn't read HDF End of File Address");
#endif
return;
}
#ifdef DEBUG_HDF5
log_info("HDF5: dec eof_address = %lu\n", (long unsigned)eof_address);
log_info("HDF5: hex eof_address = 0x%02lX\n", eof_address);
#endif
file_recovery->file_size=eof_address;
}

/*@
@ requires buffer_size >= sizeof(struct hdf5_superblock);
Expand All @@ -66,11 +139,13 @@ struct hdf5_superblock
static int header_check_hdf5(const unsigned char *buffer, const unsigned int buffer_size, const unsigned int safe_header_only, const file_recovery_t *file_recovery, file_recovery_t *file_recovery_new)
{
const struct hdf5_superblock *sb=(const struct hdf5_superblock*)&buffer[0];
/*@ assert \valid_read(sb); */
if(sb->version > 2)
const uint8_t sb_version=sb->version;
if (sb_version > 1) {
return 0;
}
reset_file_recovery(file_recovery_new);
file_recovery_new->extension=file_hint_hdf5.extension;
file_recovery_new->file_check=&file_check_hdf5;
return 1;
}

Expand Down