static void hash_object(object_t* object, uint32_t* hash) {
switch (object->type) {
case type_nil: *hash = hash_nil(*hash); return;
case type_bool: *hash = hash_bool(*hash, object->b); return;
case type_double: *hash = hash_double(*hash, object->d); return;
case type_int: *hash = hash_i64(*hash, object->i); return;
case type_uint: *hash = hash_u64(*hash, object->u); return;
case type_str:
*hash = hash_str(*hash, object->str, object->l);
return;
// unused types in this benchmark
#if 0
case type_float:
write_float(hash, node_float(node));
return;
case type_bin:
*hash = hash_str(*hash, node_data(node), node_data_len(node));
return;
case type_ext:
*hash = hash_u8(*hash, node_exttype(node));
*hash = hash_str(*hash, node_data(node), node_data_len(node));
return;
#endif
case type_array: {
uint32_t count = object->l;
for (uint32_t i = 0; i < count; ++i)
hash_object(object->children + i, hash);
*hash = hash_u32(*hash, count);
return;
}
case type_map: {
uint32_t count = object->l;
for (uint32_t i = 0; i < count; ++i) {
// we expect keys to be short strings
object_t* key = object->children + (i * 2);
*hash = hash_str(*hash, key->str, key->l);
hash_object(object->children + (i * 2) + 1, hash);
}
*hash = hash_u32(*hash, count);
return;
}
default:
break;
}
abort();
}
/* Adds w to remset rs. Returns true if rs overflowed when inserting w. */
bool rs_add_elem( remset_t *rs, word w )
{
word mask, *tbl, *b, *pooltop, *poollim, tblsize, h;
bool overflowed = FALSE;
remset_data_t *data = DATA(rs);
pooltop = data->curr_pool->top;
poollim = data->curr_pool->lim;
tbl = data->tbl_bot;
tblsize = data->tbl_lim - tbl;
mask = tblsize-1;
h = hash_object( w, mask );
b = (word*)tbl[ h ];
while (b != 0 && *b != w)
b = (word*)*(b+1);
if (b == 0) {
if (pooltop == poollim) {
handle_overflow( rs, 0, pooltop );
pooltop = data->curr_pool->top;
poollim = data->curr_pool->lim;
overflowed = TRUE;
}
*pooltop = w;
*(pooltop+1) = tbl[h];
tbl[h] = (word)pooltop;
pooltop += 2;
data->curr_pool->top = pooltop;
data->curr_pool->lim = poollim;
data->stats.recorded += 1;
rs->live += 1;
}
return overflowed;
}
bool rs_add_elem_new( remset_t *rs, word w )
{
word mask, *tbl, *b, *pooltop, *poollim, tblsize, h;
bool overflowed = FALSE;
remset_data_t *data = DATA(rs);
assert2(! rs_isremembered( rs, w ));
pooltop = data->curr_pool->top;
poollim = data->curr_pool->lim;
tbl = data->tbl_bot;
tblsize = data->tbl_lim - tbl;
mask = tblsize-1;
h = hash_object( w, mask );
if (pooltop == poollim) {
handle_overflow( rs, 0, pooltop );
pooltop = data->curr_pool->top;
poollim = data->curr_pool->lim;
overflowed = TRUE;
}
*pooltop = w;
*(pooltop+1) = tbl[h];
tbl[h] = (word)pooltop;
pooltop += 2;
data->curr_pool->top = pooltop;
data->curr_pool->lim = poollim;
data->stats.recorded += 1;
rs->live += 1;
return overflowed;
}
bool run_test(uint32_t* hash_out) {
char* data = benchmark_in_situ_copy(insitu_data, insitu_size);
if (!data)
return false;
hash_object(root_object, hash_out);
benchmark_in_situ_free(data);
return true;
}
static void hash_stdin_paths(const char *type, int write_objects)
{
struct strbuf buf = STRBUF_INIT, nbuf = STRBUF_INIT;
while (strbuf_getline(&buf, stdin, '\n') != EOF) {
if (buf.buf[0] == '"') {
strbuf_reset(&nbuf);
if (unquote_c_style(&nbuf, buf.buf, NULL))
die("line is badly quoted");
strbuf_swap(&buf, &nbuf);
}
hash_object(buf.buf, type, write_objects, buf.buf);
}
strbuf_release(&buf);
strbuf_release(&nbuf);
}
static void hash_stdin_paths(const char *type, int no_filters, unsigned flags,
int literally)
{
struct strbuf buf = STRBUF_INIT, nbuf = STRBUF_INIT;
while (strbuf_getline_lf(&buf, stdin) != EOF) {
if (buf.buf[0] == '"') {
strbuf_reset(&nbuf);
if (unquote_c_style(&nbuf, buf.buf, NULL))
die("line is badly quoted");
strbuf_swap(&buf, &nbuf);
}
hash_object(buf.buf, type, no_filters ? NULL : buf.buf, flags,
literally);
}
strbuf_release(&buf);
strbuf_release(&nbuf);
}
bool rs_isremembered( remset_t *rs, word w )
{
word mask, *tbl, *b, tblsize, h;
remset_data_t *data = DATA(rs);
assert( WORDS_PER_POOL_ENTRY == 2 );
/* Search hash table */
tbl = data->tbl_bot;
tblsize = data->tbl_lim - tbl;
mask = tblsize-1;
h = hash_object( w, mask );
b = (word*)tbl[ h ];
while (b != 0 && *b != w)
b = (word*)*(b+1);
return b != 0;
}
void rs_del_elem( remset_t *rs, word w )
{
word mask, *tbl, *b, *pooltop, *poollim, tblsize, h;
bool overflowed = FALSE;
remset_data_t *data = DATA(rs);
pooltop = data->curr_pool->top;
poollim = data->curr_pool->lim;
tbl = data->tbl_bot;
tblsize = data->tbl_lim - tbl;
mask = tblsize-1;
h = hash_object( w, mask );
b = (word*)tbl[ h ];
while (b != 0 && *b != w) {
b = (word*)*(b+1);
}
if (b != 0) {
*b = (word)(word*)0;
rs->live -= 1;
}
}
int cmd_hash_object(int argc, const char **argv, const char *prefix)
{
static const char * const hash_object_usage[] = {
N_("git hash-object [-t <type>] [-w] [--path=<file> | --no-filters] [--stdin] [--] <file>..."),
N_("git hash-object --stdin-paths"),
NULL
};
const char *type = blob_type;
int hashstdin = 0;
int stdin_paths = 0;
int no_filters = 0;
int literally = 0;
int nongit = 0;
unsigned flags = HASH_FORMAT_CHECK;
const char *vpath = NULL;
const struct option hash_object_options[] = {
OPT_STRING('t', NULL, &type, N_("type"), N_("object type")),
OPT_BIT('w', NULL, &flags, N_("write the object into the object database"),
HASH_WRITE_OBJECT),
OPT_COUNTUP( 0 , "stdin", &hashstdin, N_("read the object from stdin")),
OPT_BOOL( 0 , "stdin-paths", &stdin_paths, N_("read file names from stdin")),
OPT_BOOL( 0 , "no-filters", &no_filters, N_("store file as is without filters")),
OPT_BOOL( 0, "literally", &literally, N_("just hash any random garbage to create corrupt objects for debugging Git")),
OPT_STRING( 0 , "path", &vpath, N_("file"), N_("process file as it were from this path")),
OPT_END()
};
int i;
const char *errstr = NULL;
argc = parse_options(argc, argv, NULL, hash_object_options,
hash_object_usage, 0);
if (flags & HASH_WRITE_OBJECT)
prefix = setup_git_directory();
else
prefix = setup_git_directory_gently(&nongit);
if (vpath && prefix)
vpath = xstrdup(prefix_filename(prefix, vpath));
git_config(git_default_config, NULL);
if (stdin_paths) {
if (hashstdin)
errstr = "Can't use --stdin-paths with --stdin";
else if (argc)
errstr = "Can't specify files with --stdin-paths";
else if (vpath)
errstr = "Can't use --stdin-paths with --path";
}
else {
if (hashstdin > 1)
errstr = "Multiple --stdin arguments are not supported";
if (vpath && no_filters)
errstr = "Can't use --path with --no-filters";
}
if (errstr) {
error("%s", errstr);
usage_with_options(hash_object_usage, hash_object_options);
}
if (hashstdin)
hash_fd(0, type, vpath, flags, literally);
for (i = 0 ; i < argc; i++) {
const char *arg = argv[i];
char *to_free = NULL;
if (prefix)
arg = to_free = prefix_filename(prefix, arg);
hash_object(arg, type, no_filters ? NULL : vpath ? vpath : arg,
flags, literally);
free(to_free);
}
if (stdin_paths)
hash_stdin_paths(type, no_filters, flags, literally);
return 0;
}
int main(int argc, const char **argv)
{
int i;
const char *prefix = NULL;
int prefix_length = -1;
const char *errstr = NULL;
type = blob_type;
git_extract_argv0_path(argv[0]);
git_config(git_default_config, NULL);
argc = parse_options(argc, argv, hash_object_options, hash_object_usage, 0);
if (write_object) {
prefix = setup_git_directory();
prefix_length = prefix ? strlen(prefix) : 0;
if (vpath && prefix)
vpath = prefix_filename(prefix, prefix_length, vpath);
}
if (stdin_paths) {
if (hashstdin)
errstr = "Can't use --stdin-paths with --stdin";
else if (argc)
errstr = "Can't specify files with --stdin-paths";
else if (vpath)
errstr = "Can't use --stdin-paths with --path";
else if (no_filters)
errstr = "Can't use --stdin-paths with --no-filters";
}
else {
if (hashstdin > 1)
errstr = "Multiple --stdin arguments are not supported";
if (vpath && no_filters)
errstr = "Can't use --path with --no-filters";
}
if (errstr) {
error("%s", errstr);
usage_with_options(hash_object_usage, hash_object_options);
}
if (hashstdin)
hash_fd(0, type, write_object, vpath);
for (i = 0 ; i < argc; i++) {
const char *arg = argv[i];
if (0 <= prefix_length)
arg = prefix_filename(prefix, prefix_length, arg);
hash_object(arg, type, write_object,
no_filters ? NULL : vpath ? vpath : arg);
}
if (stdin_paths)
hash_stdin_paths(type, write_object);
return 0;
}
