Merge branch 'ps/object-wo-the-repository'

The object layer has been updated to take an explicit repository
instance as a parameter in more code paths.

* ps/object-wo-the-repository:
  hash: stop depending on `the_repository` in `null_oid()`
  hash: fix "-Wsign-compare" warnings
  object-file: split out logic regarding hash algorithms
  delta-islands: stop depending on `the_repository`
  object-file-convert: stop depending on `the_repository`
  pack-bitmap-write: stop depending on `the_repository`
  pack-revindex: stop depending on `the_repository`
  pack-check: stop depending on `the_repository`
  environment: move access to "core.bigFileThreshold" into repo settings
  pack-write: stop depending on `the_repository` and `the_hash_algo`
  object: stop depending on `the_repository`
  csum-file: stop depending on `the_repository`
This commit is contained in:
Junio C Hamano
2025-04-15 13:50:14 -07:00
87 changed files with 677 additions and 613 deletions

View File

@@ -45,283 +45,6 @@
/* The maximum size for an object header. */
#define MAX_HEADER_LEN 32
static const struct object_id empty_tree_oid = {
.hash = {
0x4b, 0x82, 0x5d, 0xc6, 0x42, 0xcb, 0x6e, 0xb9, 0xa0, 0x60,
0xe5, 0x4b, 0xf8, 0xd6, 0x92, 0x88, 0xfb, 0xee, 0x49, 0x04
},
.algo = GIT_HASH_SHA1,
};
static const struct object_id empty_blob_oid = {
.hash = {
0xe6, 0x9d, 0xe2, 0x9b, 0xb2, 0xd1, 0xd6, 0x43, 0x4b, 0x8b,
0x29, 0xae, 0x77, 0x5a, 0xd8, 0xc2, 0xe4, 0x8c, 0x53, 0x91
},
.algo = GIT_HASH_SHA1,
};
static const struct object_id null_oid_sha1 = {
.hash = {0},
.algo = GIT_HASH_SHA1,
};
static const struct object_id empty_tree_oid_sha256 = {
.hash = {
0x6e, 0xf1, 0x9b, 0x41, 0x22, 0x5c, 0x53, 0x69, 0xf1, 0xc1,
0x04, 0xd4, 0x5d, 0x8d, 0x85, 0xef, 0xa9, 0xb0, 0x57, 0xb5,
0x3b, 0x14, 0xb4, 0xb9, 0xb9, 0x39, 0xdd, 0x74, 0xde, 0xcc,
0x53, 0x21
},
.algo = GIT_HASH_SHA256,
};
static const struct object_id empty_blob_oid_sha256 = {
.hash = {
0x47, 0x3a, 0x0f, 0x4c, 0x3b, 0xe8, 0xa9, 0x36, 0x81, 0xa2,
0x67, 0xe3, 0xb1, 0xe9, 0xa7, 0xdc, 0xda, 0x11, 0x85, 0x43,
0x6f, 0xe1, 0x41, 0xf7, 0x74, 0x91, 0x20, 0xa3, 0x03, 0x72,
0x18, 0x13
},
.algo = GIT_HASH_SHA256,
};
static const struct object_id null_oid_sha256 = {
.hash = {0},
.algo = GIT_HASH_SHA256,
};
static void git_hash_sha1_init(struct git_hash_ctx *ctx)
{
ctx->algop = &hash_algos[GIT_HASH_SHA1];
git_SHA1_Init(&ctx->state.sha1);
}
static void git_hash_sha1_clone(struct git_hash_ctx *dst, const struct git_hash_ctx *src)
{
dst->algop = src->algop;
git_SHA1_Clone(&dst->state.sha1, &src->state.sha1);
}
static void git_hash_sha1_update(struct git_hash_ctx *ctx, const void *data, size_t len)
{
git_SHA1_Update(&ctx->state.sha1, data, len);
}
static void git_hash_sha1_final(unsigned char *hash, struct git_hash_ctx *ctx)
{
git_SHA1_Final(hash, &ctx->state.sha1);
}
static void git_hash_sha1_final_oid(struct object_id *oid, struct git_hash_ctx *ctx)
{
git_SHA1_Final(oid->hash, &ctx->state.sha1);
memset(oid->hash + GIT_SHA1_RAWSZ, 0, GIT_MAX_RAWSZ - GIT_SHA1_RAWSZ);
oid->algo = GIT_HASH_SHA1;
}
static void git_hash_sha1_init_unsafe(struct git_hash_ctx *ctx)
{
ctx->algop = unsafe_hash_algo(&hash_algos[GIT_HASH_SHA1]);
git_SHA1_Init_unsafe(&ctx->state.sha1_unsafe);
}
static void git_hash_sha1_clone_unsafe(struct git_hash_ctx *dst, const struct git_hash_ctx *src)
{
dst->algop = src->algop;
git_SHA1_Clone_unsafe(&dst->state.sha1_unsafe, &src->state.sha1_unsafe);
}
static void git_hash_sha1_update_unsafe(struct git_hash_ctx *ctx, const void *data,
size_t len)
{
git_SHA1_Update_unsafe(&ctx->state.sha1_unsafe, data, len);
}
static void git_hash_sha1_final_unsafe(unsigned char *hash, struct git_hash_ctx *ctx)
{
git_SHA1_Final_unsafe(hash, &ctx->state.sha1_unsafe);
}
static void git_hash_sha1_final_oid_unsafe(struct object_id *oid, struct git_hash_ctx *ctx)
{
git_SHA1_Final_unsafe(oid->hash, &ctx->state.sha1_unsafe);
memset(oid->hash + GIT_SHA1_RAWSZ, 0, GIT_MAX_RAWSZ - GIT_SHA1_RAWSZ);
oid->algo = GIT_HASH_SHA1;
}
static void git_hash_sha256_init(struct git_hash_ctx *ctx)
{
ctx->algop = unsafe_hash_algo(&hash_algos[GIT_HASH_SHA256]);
git_SHA256_Init(&ctx->state.sha256);
}
static void git_hash_sha256_clone(struct git_hash_ctx *dst, const struct git_hash_ctx *src)
{
dst->algop = src->algop;
git_SHA256_Clone(&dst->state.sha256, &src->state.sha256);
}
static void git_hash_sha256_update(struct git_hash_ctx *ctx, const void *data, size_t len)
{
git_SHA256_Update(&ctx->state.sha256, data, len);
}
static void git_hash_sha256_final(unsigned char *hash, struct git_hash_ctx *ctx)
{
git_SHA256_Final(hash, &ctx->state.sha256);
}
static void git_hash_sha256_final_oid(struct object_id *oid, struct git_hash_ctx *ctx)
{
git_SHA256_Final(oid->hash, &ctx->state.sha256);
/*
* This currently does nothing, so the compiler should optimize it out,
* but keep it in case we extend the hash size again.
*/
memset(oid->hash + GIT_SHA256_RAWSZ, 0, GIT_MAX_RAWSZ - GIT_SHA256_RAWSZ);
oid->algo = GIT_HASH_SHA256;
}
static void git_hash_unknown_init(struct git_hash_ctx *ctx UNUSED)
{
BUG("trying to init unknown hash");
}
static void git_hash_unknown_clone(struct git_hash_ctx *dst UNUSED,
const struct git_hash_ctx *src UNUSED)
{
BUG("trying to clone unknown hash");
}
static void git_hash_unknown_update(struct git_hash_ctx *ctx UNUSED,
const void *data UNUSED,
size_t len UNUSED)
{
BUG("trying to update unknown hash");
}
static void git_hash_unknown_final(unsigned char *hash UNUSED,
struct git_hash_ctx *ctx UNUSED)
{
BUG("trying to finalize unknown hash");
}
static void git_hash_unknown_final_oid(struct object_id *oid UNUSED,
struct git_hash_ctx *ctx UNUSED)
{
BUG("trying to finalize unknown hash");
}
static const struct git_hash_algo sha1_unsafe_algo = {
.name = "sha1",
.format_id = GIT_SHA1_FORMAT_ID,
.rawsz = GIT_SHA1_RAWSZ,
.hexsz = GIT_SHA1_HEXSZ,
.blksz = GIT_SHA1_BLKSZ,
.init_fn = git_hash_sha1_init_unsafe,
.clone_fn = git_hash_sha1_clone_unsafe,
.update_fn = git_hash_sha1_update_unsafe,
.final_fn = git_hash_sha1_final_unsafe,
.final_oid_fn = git_hash_sha1_final_oid_unsafe,
.empty_tree = &empty_tree_oid,
.empty_blob = &empty_blob_oid,
.null_oid = &null_oid_sha1,
};
const struct git_hash_algo hash_algos[GIT_HASH_NALGOS] = {
{
.name = NULL,
.format_id = 0x00000000,
.rawsz = 0,
.hexsz = 0,
.blksz = 0,
.init_fn = git_hash_unknown_init,
.clone_fn = git_hash_unknown_clone,
.update_fn = git_hash_unknown_update,
.final_fn = git_hash_unknown_final,
.final_oid_fn = git_hash_unknown_final_oid,
.empty_tree = NULL,
.empty_blob = NULL,
.null_oid = NULL,
},
{
.name = "sha1",
.format_id = GIT_SHA1_FORMAT_ID,
.rawsz = GIT_SHA1_RAWSZ,
.hexsz = GIT_SHA1_HEXSZ,
.blksz = GIT_SHA1_BLKSZ,
.init_fn = git_hash_sha1_init,
.clone_fn = git_hash_sha1_clone,
.update_fn = git_hash_sha1_update,
.final_fn = git_hash_sha1_final,
.final_oid_fn = git_hash_sha1_final_oid,
.unsafe = &sha1_unsafe_algo,
.empty_tree = &empty_tree_oid,
.empty_blob = &empty_blob_oid,
.null_oid = &null_oid_sha1,
},
{
.name = "sha256",
.format_id = GIT_SHA256_FORMAT_ID,
.rawsz = GIT_SHA256_RAWSZ,
.hexsz = GIT_SHA256_HEXSZ,
.blksz = GIT_SHA256_BLKSZ,
.init_fn = git_hash_sha256_init,
.clone_fn = git_hash_sha256_clone,
.update_fn = git_hash_sha256_update,
.final_fn = git_hash_sha256_final,
.final_oid_fn = git_hash_sha256_final_oid,
.empty_tree = &empty_tree_oid_sha256,
.empty_blob = &empty_blob_oid_sha256,
.null_oid = &null_oid_sha256,
}
};
const struct object_id *null_oid(void)
{
return the_hash_algo->null_oid;
}
const char *empty_tree_oid_hex(const struct git_hash_algo *algop)
{
static char buf[GIT_MAX_HEXSZ + 1];
return oid_to_hex_r(buf, algop->empty_tree);
}
int hash_algo_by_name(const char *name)
{
int i;
if (!name)
return GIT_HASH_UNKNOWN;
for (i = 1; i < GIT_HASH_NALGOS; i++)
if (!strcmp(name, hash_algos[i].name))
return i;
return GIT_HASH_UNKNOWN;
}
int hash_algo_by_id(uint32_t format_id)
{
int i;
for (i = 1; i < GIT_HASH_NALGOS; i++)
if (format_id == hash_algos[i].format_id)
return i;
return GIT_HASH_UNKNOWN;
}
int hash_algo_by_length(int len)
{
int i;
for (i = 1; i < GIT_HASH_NALGOS; i++)
if (len == hash_algos[i].rawsz)
return i;
return GIT_HASH_UNKNOWN;
}
const struct git_hash_algo *unsafe_hash_algo(const struct git_hash_algo *algop)
{
/* If we have a faster "unsafe" implementation, use that. */
if (algop->unsafe)
return algop->unsafe;
/* Otherwise use the default one. */
return algop;
}
/*
* This is meant to hold a *small* number of objects that you would
* want repo_read_object_file() to be able to return, but yet you do not want
@@ -1793,7 +1516,7 @@ static int oid_object_info_convert(struct repository *r,
if (type == -1)
return -1;
if (type != OBJ_BLOB) {
ret = convert_object_file(&outbuf,
ret = convert_object_file(the_repository, &outbuf,
the_hash_algo, input_algo,
content, size, type, !do_die);
free(content);
@@ -2510,7 +2233,7 @@ int write_object_file_flags(const void *buf, unsigned long len,
hash_object_file(compat, buf, len, type, &compat_oid);
else {
struct strbuf converted = STRBUF_INIT;
convert_object_file(&converted, algo, compat,
convert_object_file(the_repository, &converted, algo, compat,
buf, len, type, 0);
hash_object_file(compat, converted.buf, converted.len,
type, &compat_oid);
@@ -2550,7 +2273,8 @@ int write_object_file_literally(const void *buf, unsigned long len,
&compat_oid);
else if (compat_type != -1) {
struct strbuf converted = STRBUF_INIT;
convert_object_file(&converted, algo, compat,
convert_object_file(the_repository,
&converted, algo, compat,
buf, len, compat_type, 0);
hash_object_file(compat, converted.buf, converted.len,
compat_type, &compat_oid);
@@ -2681,7 +2405,7 @@ static int index_mem(struct index_state *istate,
opts.strict = 1;
opts.error_func = hash_format_check_report;
if (fsck_buffer(null_oid(), type, buf, size, &opts))
if (fsck_buffer(null_oid(the_hash_algo), type, buf, size, &opts))
die(_("refusing to create malformed object"));
fsck_finish(&opts);
}
@@ -2803,7 +2527,8 @@ int index_fd(struct index_state *istate, struct object_id *oid,
ret = index_stream_convert_blob(istate, oid, fd, path, flags);
else if (!S_ISREG(st->st_mode))
ret = index_pipe(istate, oid, fd, type, path, flags);
else if (st->st_size <= big_file_threshold || type != OBJ_BLOB ||
else if (st->st_size <= repo_settings_get_big_file_threshold(the_repository) ||
type != OBJ_BLOB ||
(path && would_convert_to_git(istate, path)))
ret = index_core(istate, oid, fd, xsize_t(st->st_size),
type, path, flags);
@@ -3134,7 +2859,8 @@ int read_loose_object(const char *path,
goto out_inflate;
}
if (*oi->typep == OBJ_BLOB && *size > big_file_threshold) {
if (*oi->typep == OBJ_BLOB &&
*size > repo_settings_get_big_file_threshold(the_repository)) {
if (check_stream_oid(&stream, hdr, *size, path, expected_oid) < 0)
goto out_inflate;
} else {