repack: remove 'existing_packs' API from the builtin

The repack builtin defines an API for keeping track of which packs
were found in the repository at the beginning of the repack operation.
This is used to classify what state a pack was in (kept, non-kept, or
cruft), and is also used to mark which packs to delete (or keep) at the
end of a repack operation.

Now that the prerequisite refactoring is complete, this API is isolated
enough that it can be moved out to repack.[ch] and removed from the
builtin entirely.

As a result, some of its functions become static within repack.c,
cleaning up the visible API.

Signed-off-by: Taylor Blau <me@ttaylorr.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
This commit is contained in:
Taylor Blau
2025-10-15 18:28:15 -04:00
committed by Junio C Hamano
parent dab24e4bcb
commit 7d1f442588
3 changed files with 192 additions and 173 deletions

View File

@@ -3,7 +3,6 @@
#include "builtin.h" #include "builtin.h"
#include "config.h" #include "config.h"
#include "dir.h"
#include "environment.h" #include "environment.h"
#include "gettext.h" #include "gettext.h"
#include "hex.h" #include "hex.h"
@@ -108,178 +107,6 @@ static int repack_config(const char *var, const char *value,
return git_default_config(var, value, ctx, cb); return git_default_config(var, value, ctx, cb);
} }
struct existing_packs {
struct repository *repo;
struct string_list kept_packs;
struct string_list non_kept_packs;
struct string_list cruft_packs;
};
#define EXISTING_PACKS_INIT { \
.kept_packs = STRING_LIST_INIT_DUP, \
.non_kept_packs = STRING_LIST_INIT_DUP, \
.cruft_packs = STRING_LIST_INIT_DUP, \
}
static int existing_packs_has_non_kept(const struct existing_packs *existing)
{
return existing->non_kept_packs.nr || existing->cruft_packs.nr;
}
static void existing_pack_mark_for_deletion(struct string_list_item *item)
{
item->util = (void*)((uintptr_t)item->util | DELETE_PACK);
}
static void existing_pack_unmark_for_deletion(struct string_list_item *item)
{
item->util = (void*)((uintptr_t)item->util & ~DELETE_PACK);
}
static int existing_pack_is_marked_for_deletion(struct string_list_item *item)
{
return (uintptr_t)item->util & DELETE_PACK;
}
static void existing_packs_mark_retained(struct string_list_item *item)
{
item->util = (void*)((uintptr_t)item->util | RETAIN_PACK);
}
static int existing_pack_is_retained(struct string_list_item *item)
{
return (uintptr_t)item->util & RETAIN_PACK;
}
static void existing_packs_mark_for_deletion_1(const struct git_hash_algo *algop,
struct string_list *names,
struct string_list *list)
{
struct string_list_item *item;
const size_t hexsz = algop->hexsz;
for_each_string_list_item(item, list) {
char *sha1;
size_t len = strlen(item->string);
if (len < hexsz)
continue;
sha1 = item->string + len - hexsz;
if (existing_pack_is_retained(item)) {
existing_pack_unmark_for_deletion(item);
} else if (!string_list_has_string(names, sha1)) {
/*
* Mark this pack for deletion, which ensures
* that this pack won't be included in a MIDX
* (if `--write-midx` was given) and that we
* will actually delete this pack (if `-d` was
* given).
*/
existing_pack_mark_for_deletion(item);
}
}
}
static void existing_packs_retain_cruft(struct existing_packs *existing,
struct packed_git *cruft)
{
struct strbuf buf = STRBUF_INIT;
struct string_list_item *item;
strbuf_addstr(&buf, pack_basename(cruft));
strbuf_strip_suffix(&buf, ".pack");
item = string_list_lookup(&existing->cruft_packs, buf.buf);
if (!item)
BUG("could not find cruft pack '%s'", pack_basename(cruft));
existing_packs_mark_retained(item);
strbuf_release(&buf);
}
static void existing_packs_mark_for_deletion(struct existing_packs *existing,
struct string_list *names)
{
const struct git_hash_algo *algop = existing->repo->hash_algo;
existing_packs_mark_for_deletion_1(algop, names,
&existing->non_kept_packs);
existing_packs_mark_for_deletion_1(algop, names,
&existing->cruft_packs);
}
static void remove_redundant_packs_1(struct repository *repo,
struct string_list *packs,
const char *packdir)
{
struct string_list_item *item;
for_each_string_list_item(item, packs) {
if (!existing_pack_is_marked_for_deletion(item))
continue;
repack_remove_redundant_pack(repo, packdir, item->string);
}
}
static void existing_packs_remove_redundant(struct existing_packs *existing,
const char *packdir)
{
remove_redundant_packs_1(existing->repo, &existing->non_kept_packs,
packdir);
remove_redundant_packs_1(existing->repo, &existing->cruft_packs,
packdir);
}
static void existing_packs_release(struct existing_packs *existing)
{
string_list_clear(&existing->kept_packs, 0);
string_list_clear(&existing->non_kept_packs, 0);
string_list_clear(&existing->cruft_packs, 0);
}
/*
* Adds all packs hex strings (pack-$HASH) to either packs->non_kept
* or packs->kept based on whether each pack has a corresponding
* .keep file or not. Packs without a .keep file are not to be kept
* if we are going to pack everything into one file.
*/
static void existing_packs_collect(struct existing_packs *existing,
const struct string_list *extra_keep)
{
struct packfile_store *packs = existing->repo->objects->packfiles;
struct packed_git *p;
struct strbuf buf = STRBUF_INIT;
for (p = packfile_store_get_all_packs(packs); p; p = p->next) {
size_t i;
const char *base;
if (!p->pack_local)
continue;
base = pack_basename(p);
for (i = 0; i < extra_keep->nr; i++)
if (!fspathcmp(base, extra_keep->items[i].string))
break;
strbuf_reset(&buf);
strbuf_addstr(&buf, base);
strbuf_strip_suffix(&buf, ".pack");
if ((extra_keep->nr > 0 && i < extra_keep->nr) || p->pack_keep)
string_list_append(&existing->kept_packs, buf.buf);
else if (p->is_cruft)
string_list_append(&existing->cruft_packs, buf.buf);
else
string_list_append(&existing->non_kept_packs, buf.buf);
}
string_list_sort(&existing->kept_packs);
string_list_sort(&existing->non_kept_packs);
string_list_sort(&existing->cruft_packs);
strbuf_release(&buf);
}
struct write_oid_context { struct write_oid_context {
struct child_process *cmd; struct child_process *cmd;
const struct git_hash_algo *algop; const struct git_hash_algo *algop;

157
repack.c
View File

@@ -1,4 +1,5 @@
#include "git-compat-util.h" #include "git-compat-util.h"
#include "dir.h"
#include "midx.h" #include "midx.h"
#include "odb.h" #include "odb.h"
#include "packfile.h" #include "packfile.h"
@@ -62,3 +63,159 @@ void repack_remove_redundant_pack(struct repository *repo, const char *dir_name,
unlink_pack_path(buf.buf, 1); unlink_pack_path(buf.buf, 1);
strbuf_release(&buf); strbuf_release(&buf);
} }
#define DELETE_PACK 1
#define RETAIN_PACK 2
void existing_packs_collect(struct existing_packs *existing,
const struct string_list *extra_keep)
{
struct packfile_store *packs = existing->repo->objects->packfiles;
struct packed_git *p;
struct strbuf buf = STRBUF_INIT;
for (p = packfile_store_get_all_packs(packs); p; p = p->next) {
size_t i;
const char *base;
if (!p->pack_local)
continue;
base = pack_basename(p);
for (i = 0; i < extra_keep->nr; i++)
if (!fspathcmp(base, extra_keep->items[i].string))
break;
strbuf_reset(&buf);
strbuf_addstr(&buf, base);
strbuf_strip_suffix(&buf, ".pack");
if ((extra_keep->nr > 0 && i < extra_keep->nr) || p->pack_keep)
string_list_append(&existing->kept_packs, buf.buf);
else if (p->is_cruft)
string_list_append(&existing->cruft_packs, buf.buf);
else
string_list_append(&existing->non_kept_packs, buf.buf);
}
string_list_sort(&existing->kept_packs);
string_list_sort(&existing->non_kept_packs);
string_list_sort(&existing->cruft_packs);
strbuf_release(&buf);
}
int existing_packs_has_non_kept(const struct existing_packs *existing)
{
return existing->non_kept_packs.nr || existing->cruft_packs.nr;
}
static void existing_pack_mark_for_deletion(struct string_list_item *item)
{
item->util = (void*)((uintptr_t)item->util | DELETE_PACK);
}
static void existing_pack_unmark_for_deletion(struct string_list_item *item)
{
item->util = (void*)((uintptr_t)item->util & ~DELETE_PACK);
}
int existing_pack_is_marked_for_deletion(struct string_list_item *item)
{
return (uintptr_t)item->util & DELETE_PACK;
}
static void existing_packs_mark_retained(struct string_list_item *item)
{
item->util = (void*)((uintptr_t)item->util | RETAIN_PACK);
}
static int existing_pack_is_retained(struct string_list_item *item)
{
return (uintptr_t)item->util & RETAIN_PACK;
}
static void existing_packs_mark_for_deletion_1(const struct git_hash_algo *algop,
struct string_list *names,
struct string_list *list)
{
struct string_list_item *item;
const size_t hexsz = algop->hexsz;
for_each_string_list_item(item, list) {
char *sha1;
size_t len = strlen(item->string);
if (len < hexsz)
continue;
sha1 = item->string + len - hexsz;
if (existing_pack_is_retained(item)) {
existing_pack_unmark_for_deletion(item);
} else if (!string_list_has_string(names, sha1)) {
/*
* Mark this pack for deletion, which ensures
* that this pack won't be included in a MIDX
* (if `--write-midx` was given) and that we
* will actually delete this pack (if `-d` was
* given).
*/
existing_pack_mark_for_deletion(item);
}
}
}
void existing_packs_retain_cruft(struct existing_packs *existing,
struct packed_git *cruft)
{
struct strbuf buf = STRBUF_INIT;
struct string_list_item *item;
strbuf_addstr(&buf, pack_basename(cruft));
strbuf_strip_suffix(&buf, ".pack");
item = string_list_lookup(&existing->cruft_packs, buf.buf);
if (!item)
BUG("could not find cruft pack '%s'", pack_basename(cruft));
existing_packs_mark_retained(item);
strbuf_release(&buf);
}
void existing_packs_mark_for_deletion(struct existing_packs *existing,
struct string_list *names)
{
const struct git_hash_algo *algop = existing->repo->hash_algo;
existing_packs_mark_for_deletion_1(algop, names,
&existing->non_kept_packs);
existing_packs_mark_for_deletion_1(algop, names,
&existing->cruft_packs);
}
static void remove_redundant_packs_1(struct repository *repo,
struct string_list *packs,
const char *packdir)
{
struct string_list_item *item;
for_each_string_list_item(item, packs) {
if (!existing_pack_is_marked_for_deletion(item))
continue;
repack_remove_redundant_pack(repo, packdir, item->string);
}
}
void existing_packs_remove_redundant(struct existing_packs *existing,
const char *packdir)
{
remove_redundant_packs_1(existing->repo, &existing->non_kept_packs,
packdir);
remove_redundant_packs_1(existing->repo, &existing->cruft_packs,
packdir);
}
void existing_packs_release(struct existing_packs *existing)
{
string_list_clear(&existing->kept_packs, 0);
string_list_clear(&existing->non_kept_packs, 0);
string_list_clear(&existing->cruft_packs, 0);
}

View File

@@ -2,6 +2,7 @@
#define REPACK_H #define REPACK_H
#include "list-objects-filter-options.h" #include "list-objects-filter-options.h"
#include "string-list.h"
struct pack_objects_args { struct pack_objects_args {
char *window; char *window;
@@ -31,4 +32,38 @@ void pack_objects_args_release(struct pack_objects_args *args);
void repack_remove_redundant_pack(struct repository *repo, const char *dir_name, void repack_remove_redundant_pack(struct repository *repo, const char *dir_name,
const char *base_name); const char *base_name);
struct repository;
struct packed_git;
struct existing_packs {
struct repository *repo;
struct string_list kept_packs;
struct string_list non_kept_packs;
struct string_list cruft_packs;
};
#define EXISTING_PACKS_INIT { \
.kept_packs = STRING_LIST_INIT_DUP, \
.non_kept_packs = STRING_LIST_INIT_DUP, \
.cruft_packs = STRING_LIST_INIT_DUP, \
}
/*
* Adds all packs hex strings (pack-$HASH) to either packs->non_kept
* or packs->kept based on whether each pack has a corresponding
* .keep file or not. Packs without a .keep file are not to be kept
* if we are going to pack everything into one file.
*/
void existing_packs_collect(struct existing_packs *existing,
const struct string_list *extra_keep);
int existing_packs_has_non_kept(const struct existing_packs *existing);
int existing_pack_is_marked_for_deletion(struct string_list_item *item);
void existing_packs_retain_cruft(struct existing_packs *existing,
struct packed_git *cruft);
void existing_packs_mark_for_deletion(struct existing_packs *existing,
struct string_list *names);
void existing_packs_remove_redundant(struct existing_packs *existing,
const char *packdir);
void existing_packs_release(struct existing_packs *existing);
#endif /* REPACK_H */ #endif /* REPACK_H */