From 5e9d802a33ef2912a04984d431defe9809c809e1 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 1 Oct 2023 21:40:05 -0500 Subject: [PATCH 01/30] object-file-convert: stubs for converting from one object format to another Two basic functions are provided: - convert_object_file Takes an object file it's type and hash algorithm and converts it into the equivalent object file that would have been generated with hash algorithm "to". For blob objects there is no conversation to be done and it is an error to use this function on them. For commit, tree, and tag objects embedded oids are replaced by the oids of the objects they refer to with those objects and their object ids reencoded in with the hash algorithm "to". Signatures are rearranged so that they remain valid after the object has been reencoded. - repo_oid_to_algop which takes an oid that refers to an object file and returns the oid of the equivalent object file generated with the target hash algorithm. The pair of files object-file-convert.c and object-file-convert.h are introduced to hold as much of this logic as possible to keep this conversion logic cleanly separated from everything else and in the hopes that someday the code will be clean enough git can support compiling out support for sha1 and the various conversion functions. Signed-off-by: "Eric W. Biederman" Signed-off-by: Junio C Hamano --- Makefile | 1 + object-file-convert.c | 57 +++++++++++++++++++++++++++++++++++++++++++ object-file-convert.h | 24 ++++++++++++++++++ 3 files changed, 82 insertions(+) create mode 100644 object-file-convert.c create mode 100644 object-file-convert.h diff --git a/Makefile b/Makefile index 5776309365..f7e824f25c 100644 --- a/Makefile +++ b/Makefile @@ -1073,6 +1073,7 @@ LIB_OBJS += notes-cache.o LIB_OBJS += notes-merge.o LIB_OBJS += notes-utils.o LIB_OBJS += notes.o +LIB_OBJS += object-file-convert.o LIB_OBJS += object-file.o LIB_OBJS += object-name.o LIB_OBJS += object.o diff --git a/object-file-convert.c b/object-file-convert.c new file mode 100644 index 0000000000..4777aba836 --- /dev/null +++ b/object-file-convert.c @@ -0,0 +1,57 @@ +#include "git-compat-util.h" +#include "gettext.h" +#include "strbuf.h" +#include "repository.h" +#include "hash-ll.h" +#include "object.h" +#include "object-file-convert.h" + +int repo_oid_to_algop(struct repository *repo, const struct object_id *src, + const struct git_hash_algo *to, struct object_id *dest) +{ + /* + * If the source algorithm is not set, then we're using the + * default hash algorithm for that object. + */ + const struct git_hash_algo *from = + src->algo ? &hash_algos[src->algo] : repo->hash_algo; + + if (from == to) { + if (src != dest) + oidcpy(dest, src); + return 0; + } + return -1; +} + +int convert_object_file(struct strbuf *outbuf, + const struct git_hash_algo *from, + const struct git_hash_algo *to, + const void *buf, size_t len, + enum object_type type, + int gentle) +{ + int ret; + + /* Don't call this function when no conversion is necessary */ + if ((from == to) || (type == OBJ_BLOB)) + BUG("Refusing noop object file conversion"); + + switch (type) { + case OBJ_COMMIT: + case OBJ_TREE: + case OBJ_TAG: + default: + /* Not implemented yet, so fail. */ + ret = -1; + break; + } + if (!ret) + return 0; + if (gentle) { + strbuf_release(outbuf); + return ret; + } + die(_("Failed to convert object from %s to %s"), + from->name, to->name); +} diff --git a/object-file-convert.h b/object-file-convert.h new file mode 100644 index 0000000000..a4f802aa8e --- /dev/null +++ b/object-file-convert.h @@ -0,0 +1,24 @@ +#ifndef OBJECT_CONVERT_H +#define OBJECT_CONVERT_H + +struct repository; +struct object_id; +struct git_hash_algo; +struct strbuf; +#include "object.h" + +int repo_oid_to_algop(struct repository *repo, const struct object_id *src, + const struct git_hash_algo *to, struct object_id *dest); + +/* + * Convert an object file from one hash algorithm to another algorithm. + * Return -1 on failure, 0 on success. + */ +int convert_object_file(struct strbuf *outbuf, + const struct git_hash_algo *from, + const struct git_hash_algo *to, + const void *buf, size_t len, + enum object_type type, + int gentle); + +#endif /* OBJECT_CONVERT_H */ From d50cbe4a5d989c454c620cbaa0c64a06a4a2f9a2 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 1 Oct 2023 21:40:06 -0500 Subject: [PATCH 02/30] oid-array: teach oid-array to handle multiple kinds of oids While looking at how to handle input of both SHA-1 and SHA-256 oids in get_oid_with_context, I realized that the oid_array in repo_for_each_abbrev might have more than one kind of oid stored in it simultaneously. Update to oid_array_append to ensure that oids added to an oid array always have an algorithm set. Update void_hashcmp to first verify two oids use the same hash algorithm before comparing them to each other. With that oid-array should be safe to use with different kinds of oids simultaneously. Signed-off-by: "Eric W. Biederman" Signed-off-by: Junio C Hamano --- oid-array.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/oid-array.c b/oid-array.c index 8e4717746c..1f36651754 100644 --- a/oid-array.c +++ b/oid-array.c @@ -6,12 +6,20 @@ void oid_array_append(struct oid_array *array, const struct object_id *oid) { ALLOC_GROW(array->oid, array->nr + 1, array->alloc); oidcpy(&array->oid[array->nr++], oid); + if (!oid->algo) + oid_set_algo(&array->oid[array->nr - 1], the_hash_algo); array->sorted = 0; } -static int void_hashcmp(const void *a, const void *b) +static int void_hashcmp(const void *va, const void *vb) { - return oidcmp(a, b); + const struct object_id *a = va, *b = vb; + int ret; + if (a->algo == b->algo) + ret = oidcmp(a, b); + else + ret = a->algo > b->algo ? 1 : -1; + return ret; } void oid_array_sort(struct oid_array *array) From 52fca06db28a23fcea159431c1c9dafca26d609c Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 1 Oct 2023 21:40:07 -0500 Subject: [PATCH 03/30] object-names: support input of oids in any supported hash Support short oids encoded in any algorithm, while ensuring enough of the oid is specified to disambiguate between all of the oids in the repository encoded in any algorithm. By default have the code continue to only accept oids specified in the storage hash algorithm of the repository, but when something is ambiguous display all of the possible oids from any accepted oid encoding. A new flag is added GET_OID_HASH_ANY that when supplied causes the code to accept oids specified in any hash algorithm, and to return the oids that were resolved. This implements the functionality that allows both SHA-1 and SHA-256 object names, from the "Object names on the command line" section of the hash function transition document. Care is taken in get_short_oid so that when the result is ambiguous the output remains the same if GIT_OID_HASH_ANY was not supplied. If GET_OID_HASH_ANY was supplied objects of any hash algorithm that match the prefix are displayed. This required updating repo_for_each_abbrev to give it a parameter so that it knows to look at all hash algorithms. Signed-off-by: "Eric W. Biederman" Signed-off-by: Junio C Hamano --- builtin/rev-parse.c | 2 +- hash-ll.h | 1 + object-name.c | 46 ++++++++++++++++++++++++++++++++++----------- object-name.h | 3 ++- 4 files changed, 39 insertions(+), 13 deletions(-) diff --git a/builtin/rev-parse.c b/builtin/rev-parse.c index fde8861ca4..43e9676540 100644 --- a/builtin/rev-parse.c +++ b/builtin/rev-parse.c @@ -882,7 +882,7 @@ int cmd_rev_parse(int argc, const char **argv, const char *prefix) continue; } if (skip_prefix(arg, "--disambiguate=", &arg)) { - repo_for_each_abbrev(the_repository, arg, + repo_for_each_abbrev(the_repository, arg, the_hash_algo, show_abbrev, NULL); continue; } diff --git a/hash-ll.h b/hash-ll.h index 10d84cc208..2cfde63ae1 100644 --- a/hash-ll.h +++ b/hash-ll.h @@ -145,6 +145,7 @@ struct object_id { #define GET_OID_RECORD_PATH 0200 #define GET_OID_ONLY_TO_DIE 04000 #define GET_OID_REQUIRE_PATH 010000 +#define GET_OID_HASH_ANY 020000 #define GET_OID_DISAMBIGUATORS \ (GET_OID_COMMIT | GET_OID_COMMITTISH | \ diff --git a/object-name.c b/object-name.c index 0bfa29dbbf..7dd6e5e475 100644 --- a/object-name.c +++ b/object-name.c @@ -25,6 +25,7 @@ #include "midx.h" #include "commit-reach.h" #include "date.h" +#include "object-file-convert.h" static int get_oid_oneline(struct repository *r, const char *, struct object_id *, struct commit_list *); @@ -49,6 +50,7 @@ struct disambiguate_state { static void update_candidates(struct disambiguate_state *ds, const struct object_id *current) { + /* The hash algorithm of current has already been filtered */ if (ds->always_call_fn) { ds->ambiguous = ds->fn(ds->repo, current, ds->cb_data) ? 1 : 0; return; @@ -134,6 +136,8 @@ static void unique_in_midx(struct multi_pack_index *m, { uint32_t num, i, first = 0; const struct object_id *current = NULL; + int len = ds->len > ds->repo->hash_algo->hexsz ? + ds->repo->hash_algo->hexsz : ds->len; num = m->num_objects; if (!num) @@ -149,7 +153,7 @@ static void unique_in_midx(struct multi_pack_index *m, for (i = first; i < num && !ds->ambiguous; i++) { struct object_id oid; current = nth_midxed_object_oid(&oid, m, i); - if (!match_hash(ds->len, ds->bin_pfx.hash, current->hash)) + if (!match_hash(len, ds->bin_pfx.hash, current->hash)) break; update_candidates(ds, current); } @@ -159,6 +163,8 @@ static void unique_in_pack(struct packed_git *p, struct disambiguate_state *ds) { uint32_t num, i, first = 0; + int len = ds->len > ds->repo->hash_algo->hexsz ? + ds->repo->hash_algo->hexsz : ds->len; if (p->multi_pack_index) return; @@ -177,7 +183,7 @@ static void unique_in_pack(struct packed_git *p, for (i = first; i < num && !ds->ambiguous; i++) { struct object_id oid; nth_packed_object_id(&oid, p, i); - if (!match_hash(ds->len, ds->bin_pfx.hash, oid.hash)) + if (!match_hash(len, ds->bin_pfx.hash, oid.hash)) break; update_candidates(ds, &oid); } @@ -188,6 +194,10 @@ static void find_short_packed_object(struct disambiguate_state *ds) struct multi_pack_index *m; struct packed_git *p; + /* Skip, unless oids from the storage hash algorithm are wanted */ + if (ds->bin_pfx.algo && (&hash_algos[ds->bin_pfx.algo] != ds->repo->hash_algo)) + return; + for (m = get_multi_pack_index(ds->repo); m && !ds->ambiguous; m = m->next) unique_in_midx(m, ds); @@ -326,11 +336,12 @@ int set_disambiguate_hint_config(const char *var, const char *value) static int init_object_disambiguation(struct repository *r, const char *name, int len, + const struct git_hash_algo *algo, struct disambiguate_state *ds) { int i; - if (len < MINIMUM_ABBREV || len > the_hash_algo->hexsz) + if (len < MINIMUM_ABBREV || len > GIT_MAX_HEXSZ) return -1; memset(ds, 0, sizeof(*ds)); @@ -357,6 +368,7 @@ static int init_object_disambiguation(struct repository *r, ds->len = len; ds->hex_pfx[len] = '\0'; ds->repo = r; + ds->bin_pfx.algo = algo ? hash_algo_by_ptr(algo) : GIT_HASH_UNKNOWN; prepare_alt_odb(r); return 0; } @@ -491,9 +503,10 @@ static int repo_collect_ambiguous(struct repository *r UNUSED, return collect_ambiguous(oid, data); } -static int sort_ambiguous(const void *a, const void *b, void *ctx) +static int sort_ambiguous(const void *va, const void *vb, void *ctx) { struct repository *sort_ambiguous_repo = ctx; + const struct object_id *a = va, *b = vb; int a_type = oid_object_info(sort_ambiguous_repo, a, NULL); int b_type = oid_object_info(sort_ambiguous_repo, b, NULL); int a_type_sort; @@ -503,8 +516,12 @@ static int sort_ambiguous(const void *a, const void *b, void *ctx) * Sorts by hash within the same object type, just as * oid_array_for_each_unique() would do. */ - if (a_type == b_type) - return oidcmp(a, b); + if (a_type == b_type) { + if (a->algo == b->algo) + return oidcmp(a, b); + else + return a->algo > b->algo ? 1 : -1; + } /* * Between object types show tags, then commits, and finally @@ -533,8 +550,12 @@ static enum get_oid_result get_short_oid(struct repository *r, int status; struct disambiguate_state ds; int quietly = !!(flags & GET_OID_QUIETLY); + const struct git_hash_algo *algo = r->hash_algo; - if (init_object_disambiguation(r, name, len, &ds) < 0) + if (flags & GET_OID_HASH_ANY) + algo = NULL; + + if (init_object_disambiguation(r, name, len, algo, &ds) < 0) return -1; if (HAS_MULTI_BITS(flags & GET_OID_DISAMBIGUATORS)) @@ -588,7 +609,7 @@ static enum get_oid_result get_short_oid(struct repository *r, if (!ds.ambiguous) ds.fn = NULL; - repo_for_each_abbrev(r, ds.hex_pfx, collect_ambiguous, &collect); + repo_for_each_abbrev(r, ds.hex_pfx, algo, collect_ambiguous, &collect); sort_ambiguous_oid_array(r, &collect); if (oid_array_for_each(&collect, show_ambiguous_object, &out)) @@ -610,13 +631,14 @@ static enum get_oid_result get_short_oid(struct repository *r, } int repo_for_each_abbrev(struct repository *r, const char *prefix, + const struct git_hash_algo *algo, each_abbrev_fn fn, void *cb_data) { struct oid_array collect = OID_ARRAY_INIT; struct disambiguate_state ds; int ret; - if (init_object_disambiguation(r, prefix, strlen(prefix), &ds) < 0) + if (init_object_disambiguation(r, prefix, strlen(prefix), algo, &ds) < 0) return -1; ds.always_call_fn = 1; @@ -787,10 +809,12 @@ void strbuf_add_unique_abbrev(struct strbuf *sb, const struct object_id *oid, int repo_find_unique_abbrev_r(struct repository *r, char *hex, const struct object_id *oid, int len) { + const struct git_hash_algo *algo = + oid->algo ? &hash_algos[oid->algo] : r->hash_algo; struct disambiguate_state ds; struct min_abbrev_data mad; struct object_id oid_ret; - const unsigned hexsz = r->hash_algo->hexsz; + const unsigned hexsz = algo->hexsz; if (len < 0) { unsigned long count = repo_approximate_object_count(r); @@ -826,7 +850,7 @@ int repo_find_unique_abbrev_r(struct repository *r, char *hex, find_abbrev_len_packed(&mad); - if (init_object_disambiguation(r, hex, mad.cur_len, &ds) < 0) + if (init_object_disambiguation(r, hex, mad.cur_len, algo, &ds) < 0) return -1; ds.fn = repo_extend_abbrev_len; diff --git a/object-name.h b/object-name.h index 9ae5223071..064ddc97d1 100644 --- a/object-name.h +++ b/object-name.h @@ -67,7 +67,8 @@ enum get_oid_result get_oid_with_context(struct repository *repo, const char *st typedef int each_abbrev_fn(const struct object_id *oid, void *); -int repo_for_each_abbrev(struct repository *r, const char *prefix, each_abbrev_fn, void *); +int repo_for_each_abbrev(struct repository *r, const char *prefix, + const struct git_hash_algo *algo, each_abbrev_fn, void *); int set_disambiguate_hint_config(const char *var, const char *value); From 15a1ca1abe8dafa9bf3bf924b4e3c6b851717ee2 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 1 Oct 2023 21:40:08 -0500 Subject: [PATCH 04/30] repository: add a compatibility hash algorithm We currently have support for using a full stage 4 SHA-256 implementation. However, we'd like to support interoperability with SHA-1 repositories as well. The transition plan anticipates a compatibility hash algorithm configuration option that we can use to implement support for this. Let's add an element to the repository structure that indicates the compatibility hash algorithm so we can use it when we need to consider interoperability between algorithms. Add a helper function repo_set_compat_hash_algo that takes a compatibility hash algorithm and sets "repo->compat_hash_algo". If GIT_HASH_UNKNOWN is passed as the compatibility hash algorithm "repo->compat_hash_algo" is set to NULL. For now, the code results in "repo->compat_hash_algo" always being set to NULL, but that will change once a configuration option is added. Inspired-by: brian m. carlson Signed-off-by: Eric W. Biederman Signed-off-by: Junio C Hamano --- repository.c | 8 ++++++++ repository.h | 4 ++++ setup.c | 3 +++ 3 files changed, 15 insertions(+) diff --git a/repository.c b/repository.c index a7679ceeaa..80252b79e9 100644 --- a/repository.c +++ b/repository.c @@ -104,6 +104,13 @@ void repo_set_hash_algo(struct repository *repo, int hash_algo) repo->hash_algo = &hash_algos[hash_algo]; } +void repo_set_compat_hash_algo(struct repository *repo, int algo) +{ + if (hash_algo_by_ptr(repo->hash_algo) == algo) + BUG("hash_algo and compat_hash_algo match"); + repo->compat_hash_algo = algo ? &hash_algos[algo] : NULL; +} + /* * Attempt to resolve and set the provided 'gitdir' for repository 'repo'. * Return 0 upon success and a non-zero value upon failure. @@ -184,6 +191,7 @@ int repo_init(struct repository *repo, goto error; repo_set_hash_algo(repo, format.hash_algo); + repo_set_compat_hash_algo(repo, GIT_HASH_UNKNOWN); repo->repository_format_worktree_config = format.worktree_config; /* take ownership of format.partial_clone */ diff --git a/repository.h b/repository.h index 5f18486f64..bf3fc601cc 100644 --- a/repository.h +++ b/repository.h @@ -160,6 +160,9 @@ struct repository { /* Repository's current hash algorithm, as serialized on disk. */ const struct git_hash_algo *hash_algo; + /* Repository's compatibility hash algorithm. */ + const struct git_hash_algo *compat_hash_algo; + /* A unique-id for tracing purposes. */ int trace2_repo_id; @@ -199,6 +202,7 @@ void repo_set_gitdir(struct repository *repo, const char *root, const struct set_gitdir_args *extra_args); void repo_set_worktree(struct repository *repo, const char *path); void repo_set_hash_algo(struct repository *repo, int algo); +void repo_set_compat_hash_algo(struct repository *repo, int compat_algo); void initialize_the_repository(void); RESULT_MUST_BE_USED int repo_init(struct repository *r, const char *gitdir, const char *worktree); diff --git a/setup.c b/setup.c index 18927a847b..aa8bf5da52 100644 --- a/setup.c +++ b/setup.c @@ -1564,6 +1564,8 @@ const char *setup_git_directory_gently(int *nongit_ok) } if (startup_info->have_repository) { repo_set_hash_algo(the_repository, repo_fmt.hash_algo); + repo_set_compat_hash_algo(the_repository, + GIT_HASH_UNKNOWN); the_repository->repository_format_worktree_config = repo_fmt.worktree_config; /* take ownership of repo_fmt.partial_clone */ @@ -1657,6 +1659,7 @@ void check_repository_format(struct repository_format *fmt) check_repository_format_gently(get_git_dir(), fmt, NULL); startup_info->have_repository = 1; repo_set_hash_algo(the_repository, fmt->hash_algo); + repo_set_compat_hash_algo(the_repository, GIT_HASH_UNKNOWN); the_repository->repository_format_worktree_config = fmt->worktree_config; the_repository->repository_format_partial_clone = From 23b2c7e95b6f8f3045665835d2dc5028701eff18 Mon Sep 17 00:00:00 2001 From: "brian m. carlson" Date: Sun, 1 Oct 2023 21:40:09 -0500 Subject: [PATCH 05/30] loose: add a mapping between SHA-1 and SHA-256 for loose objects As part of the transition plan, we'd like to add a file in the .git directory that maps loose objects between SHA-1 and SHA-256. Let's implement the specification in the transition plan and store this data on a per-repository basis in struct repository. Signed-off-by: brian m. carlson Signed-off-by: Eric W. Biederman Signed-off-by: Junio C Hamano --- Makefile | 1 + loose.c | 246 ++++++++++++++++++++++++++++++++++++++++++ loose.h | 22 ++++ object-file-convert.c | 14 ++- object-store-ll.h | 3 + object.c | 2 + repository.c | 6 ++ 7 files changed, 293 insertions(+), 1 deletion(-) create mode 100644 loose.c create mode 100644 loose.h diff --git a/Makefile b/Makefile index f7e824f25c..3c18664def 100644 --- a/Makefile +++ b/Makefile @@ -1053,6 +1053,7 @@ LIB_OBJS += list-objects-filter.o LIB_OBJS += list-objects.o LIB_OBJS += lockfile.o LIB_OBJS += log-tree.o +LIB_OBJS += loose.o LIB_OBJS += ls-refs.o LIB_OBJS += mailinfo.o LIB_OBJS += mailmap.o diff --git a/loose.c b/loose.c new file mode 100644 index 0000000000..6ba73cc84d --- /dev/null +++ b/loose.c @@ -0,0 +1,246 @@ +#include "git-compat-util.h" +#include "hash.h" +#include "path.h" +#include "object-store.h" +#include "hex.h" +#include "wrapper.h" +#include "gettext.h" +#include "loose.h" +#include "lockfile.h" + +static const char *loose_object_header = "# loose-object-idx\n"; + +static inline int should_use_loose_object_map(struct repository *repo) +{ + return repo->compat_hash_algo && repo->gitdir; +} + +void loose_object_map_init(struct loose_object_map **map) +{ + struct loose_object_map *m; + m = xmalloc(sizeof(**map)); + m->to_compat = kh_init_oid_map(); + m->to_storage = kh_init_oid_map(); + *map = m; +} + +static int insert_oid_pair(kh_oid_map_t *map, const struct object_id *key, const struct object_id *value) +{ + khiter_t pos; + int ret; + struct object_id *stored; + + pos = kh_put_oid_map(map, *key, &ret); + + /* This item already exists in the map. */ + if (ret == 0) + return 0; + + stored = xmalloc(sizeof(*stored)); + oidcpy(stored, value); + kh_value(map, pos) = stored; + return 1; +} + +static int load_one_loose_object_map(struct repository *repo, struct object_directory *dir) +{ + struct strbuf buf = STRBUF_INIT, path = STRBUF_INIT; + FILE *fp; + + if (!dir->loose_map) + loose_object_map_init(&dir->loose_map); + + insert_oid_pair(dir->loose_map->to_compat, repo->hash_algo->empty_tree, repo->compat_hash_algo->empty_tree); + insert_oid_pair(dir->loose_map->to_storage, repo->compat_hash_algo->empty_tree, repo->hash_algo->empty_tree); + + insert_oid_pair(dir->loose_map->to_compat, repo->hash_algo->empty_blob, repo->compat_hash_algo->empty_blob); + insert_oid_pair(dir->loose_map->to_storage, repo->compat_hash_algo->empty_blob, repo->hash_algo->empty_blob); + + insert_oid_pair(dir->loose_map->to_compat, repo->hash_algo->null_oid, repo->compat_hash_algo->null_oid); + insert_oid_pair(dir->loose_map->to_storage, repo->compat_hash_algo->null_oid, repo->hash_algo->null_oid); + + strbuf_git_common_path(&path, repo, "objects/loose-object-idx"); + fp = fopen(path.buf, "rb"); + if (!fp) { + strbuf_release(&path); + return 0; + } + + errno = 0; + if (strbuf_getwholeline(&buf, fp, '\n') || strcmp(buf.buf, loose_object_header)) + goto err; + while (!strbuf_getline_lf(&buf, fp)) { + const char *p; + struct object_id oid, compat_oid; + if (parse_oid_hex_algop(buf.buf, &oid, &p, repo->hash_algo) || + *p++ != ' ' || + parse_oid_hex_algop(p, &compat_oid, &p, repo->compat_hash_algo) || + p != buf.buf + buf.len) + goto err; + insert_oid_pair(dir->loose_map->to_compat, &oid, &compat_oid); + insert_oid_pair(dir->loose_map->to_storage, &compat_oid, &oid); + } + + strbuf_release(&buf); + strbuf_release(&path); + return errno ? -1 : 0; +err: + strbuf_release(&buf); + strbuf_release(&path); + return -1; +} + +int repo_read_loose_object_map(struct repository *repo) +{ + struct object_directory *dir; + + if (!should_use_loose_object_map(repo)) + return 0; + + prepare_alt_odb(repo); + + for (dir = repo->objects->odb; dir; dir = dir->next) { + if (load_one_loose_object_map(repo, dir) < 0) { + return -1; + } + } + return 0; +} + +int repo_write_loose_object_map(struct repository *repo) +{ + kh_oid_map_t *map = repo->objects->odb->loose_map->to_compat; + struct lock_file lock; + int fd; + khiter_t iter; + struct strbuf buf = STRBUF_INIT, path = STRBUF_INIT; + + if (!should_use_loose_object_map(repo)) + return 0; + + strbuf_git_common_path(&path, repo, "objects/loose-object-idx"); + fd = hold_lock_file_for_update_timeout(&lock, path.buf, LOCK_DIE_ON_ERROR, -1); + iter = kh_begin(map); + if (write_in_full(fd, loose_object_header, strlen(loose_object_header)) < 0) + goto errout; + + for (; iter != kh_end(map); iter++) { + if (kh_exist(map, iter)) { + if (oideq(&kh_key(map, iter), the_hash_algo->empty_tree) || + oideq(&kh_key(map, iter), the_hash_algo->empty_blob)) + continue; + strbuf_addf(&buf, "%s %s\n", oid_to_hex(&kh_key(map, iter)), oid_to_hex(kh_value(map, iter))); + if (write_in_full(fd, buf.buf, buf.len) < 0) + goto errout; + strbuf_reset(&buf); + } + } + strbuf_release(&buf); + if (commit_lock_file(&lock) < 0) { + error_errno(_("could not write loose object index %s"), path.buf); + strbuf_release(&path); + return -1; + } + strbuf_release(&path); + return 0; +errout: + rollback_lock_file(&lock); + strbuf_release(&buf); + error_errno(_("failed to write loose object index %s\n"), path.buf); + strbuf_release(&path); + return -1; +} + +static int write_one_object(struct repository *repo, const struct object_id *oid, + const struct object_id *compat_oid) +{ + struct lock_file lock; + int fd; + struct stat st; + struct strbuf buf = STRBUF_INIT, path = STRBUF_INIT; + + strbuf_git_common_path(&path, repo, "objects/loose-object-idx"); + hold_lock_file_for_update_timeout(&lock, path.buf, LOCK_DIE_ON_ERROR, -1); + + fd = open(path.buf, O_WRONLY | O_CREAT | O_APPEND, 0666); + if (fd < 0) + goto errout; + if (fstat(fd, &st) < 0) + goto errout; + if (!st.st_size && write_in_full(fd, loose_object_header, strlen(loose_object_header)) < 0) + goto errout; + + strbuf_addf(&buf, "%s %s\n", oid_to_hex(oid), oid_to_hex(compat_oid)); + if (write_in_full(fd, buf.buf, buf.len) < 0) + goto errout; + if (close(fd)) + goto errout; + adjust_shared_perm(path.buf); + rollback_lock_file(&lock); + strbuf_release(&buf); + strbuf_release(&path); + return 0; +errout: + error_errno(_("failed to write loose object index %s\n"), path.buf); + close(fd); + rollback_lock_file(&lock); + strbuf_release(&buf); + strbuf_release(&path); + return -1; +} + +int repo_add_loose_object_map(struct repository *repo, const struct object_id *oid, + const struct object_id *compat_oid) +{ + int inserted = 0; + + if (!should_use_loose_object_map(repo)) + return 0; + + inserted |= insert_oid_pair(repo->objects->odb->loose_map->to_compat, oid, compat_oid); + inserted |= insert_oid_pair(repo->objects->odb->loose_map->to_storage, compat_oid, oid); + if (inserted) + return write_one_object(repo, oid, compat_oid); + return 0; +} + +int repo_loose_object_map_oid(struct repository *repo, + const struct object_id *src, + const struct git_hash_algo *to, + struct object_id *dest) +{ + struct object_directory *dir; + kh_oid_map_t *map; + khiter_t pos; + + for (dir = repo->objects->odb; dir; dir = dir->next) { + struct loose_object_map *loose_map = dir->loose_map; + if (!loose_map) + continue; + map = (to == repo->compat_hash_algo) ? + loose_map->to_compat : + loose_map->to_storage; + pos = kh_get_oid_map(map, *src); + if (pos < kh_end(map)) { + oidcpy(dest, kh_value(map, pos)); + return 0; + } + } + return -1; +} + +void loose_object_map_clear(struct loose_object_map **map) +{ + struct loose_object_map *m = *map; + struct object_id *oid; + + if (!m) + return; + + kh_foreach_value(m->to_compat, oid, free(oid)); + kh_foreach_value(m->to_storage, oid, free(oid)); + kh_destroy_oid_map(m->to_compat); + kh_destroy_oid_map(m->to_storage); + free(m); + *map = NULL; +} diff --git a/loose.h b/loose.h new file mode 100644 index 0000000000..2c2957072c --- /dev/null +++ b/loose.h @@ -0,0 +1,22 @@ +#ifndef LOOSE_H +#define LOOSE_H + +#include "khash.h" + +struct loose_object_map { + kh_oid_map_t *to_compat; + kh_oid_map_t *to_storage; +}; + +void loose_object_map_init(struct loose_object_map **map); +void loose_object_map_clear(struct loose_object_map **map); +int repo_loose_object_map_oid(struct repository *repo, + const struct object_id *src, + const struct git_hash_algo *dest_algo, + struct object_id *dest); +int repo_add_loose_object_map(struct repository *repo, const struct object_id *oid, + const struct object_id *compat_oid); +int repo_read_loose_object_map(struct repository *repo); +int repo_write_loose_object_map(struct repository *repo); + +#endif diff --git a/object-file-convert.c b/object-file-convert.c index 4777aba836..1ec945eaa1 100644 --- a/object-file-convert.c +++ b/object-file-convert.c @@ -4,6 +4,7 @@ #include "repository.h" #include "hash-ll.h" #include "object.h" +#include "loose.h" #include "object-file-convert.h" int repo_oid_to_algop(struct repository *repo, const struct object_id *src, @@ -21,7 +22,18 @@ int repo_oid_to_algop(struct repository *repo, const struct object_id *src, oidcpy(dest, src); return 0; } - return -1; + if (repo_loose_object_map_oid(repo, src, to, dest)) { + /* + * We may have loaded the object map at repo initialization but + * another process (perhaps upstream of a pipe from us) may have + * written a new object into the map. If the object is missing, + * let's reload the map to see if the object has appeared. + */ + repo_read_loose_object_map(repo); + if (repo_loose_object_map_oid(repo, src, to, dest)) + return -1; + } + return 0; } int convert_object_file(struct strbuf *outbuf, diff --git a/object-store-ll.h b/object-store-ll.h index 26a3895c82..bc76d6bec8 100644 --- a/object-store-ll.h +++ b/object-store-ll.h @@ -26,6 +26,9 @@ struct object_directory { uint32_t loose_objects_subdir_seen[8]; /* 256 bits */ struct oidtree *loose_objects_cache; + /* Map between object IDs for loose objects. */ + struct loose_object_map *loose_map; + /* * This is a temporary object store created by the tmp_objdir * facility. Disable ref updates since the objects in the store diff --git a/object.c b/object.c index 2c61e4c862..186a0a47c0 100644 --- a/object.c +++ b/object.c @@ -13,6 +13,7 @@ #include "alloc.h" #include "packfile.h" #include "commit-graph.h" +#include "loose.h" unsigned int get_max_object_index(void) { @@ -540,6 +541,7 @@ void free_object_directory(struct object_directory *odb) { free(odb->path); odb_clear_loose_cache(odb); + loose_object_map_clear(&odb->loose_map); free(odb); } diff --git a/repository.c b/repository.c index 80252b79e9..6214f61cf4 100644 --- a/repository.c +++ b/repository.c @@ -14,6 +14,7 @@ #include "read-cache-ll.h" #include "remote.h" #include "setup.h" +#include "loose.h" #include "submodule-config.h" #include "sparse-index.h" #include "trace2.h" @@ -109,6 +110,8 @@ void repo_set_compat_hash_algo(struct repository *repo, int algo) if (hash_algo_by_ptr(repo->hash_algo) == algo) BUG("hash_algo and compat_hash_algo match"); repo->compat_hash_algo = algo ? &hash_algos[algo] : NULL; + if (repo->compat_hash_algo) + repo_read_loose_object_map(repo); } /* @@ -201,6 +204,9 @@ int repo_init(struct repository *repo, if (worktree) repo_set_worktree(repo, worktree); + if (repo->compat_hash_algo) + repo_read_loose_object_map(repo); + clear_repository_format(&format); return 0; From a2d923fb0d07e2518c2d692c53f0e1d83baa1604 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 1 Oct 2023 21:40:10 -0500 Subject: [PATCH 06/30] loose: compatibilty short name support Update loose_objects_cache when udpating the loose objects map. This oidtree is used to discover which oids are possibilities when resolving short names, and it can support a mixture of sha1 and sha256 oids. With this any oid recorded objects/loose-objects-idx is usable for resolving an oid to an object. To make this maintainable a helper insert_loose_map is factored out of load_one_loose_object_map and repo_add_loose_object_map, and then modified to also update the loose_objects_cache. Signed-off-by: "Eric W. Biederman" Signed-off-by: Junio C Hamano --- loose.c | 37 +++++++++++++++++++++++++------------ 1 file changed, 25 insertions(+), 12 deletions(-) diff --git a/loose.c b/loose.c index 6ba73cc84d..f6faa6216a 100644 --- a/loose.c +++ b/loose.c @@ -7,6 +7,7 @@ #include "gettext.h" #include "loose.h" #include "lockfile.h" +#include "oidtree.h" static const char *loose_object_header = "# loose-object-idx\n"; @@ -42,6 +43,21 @@ static int insert_oid_pair(kh_oid_map_t *map, const struct object_id *key, const return 1; } +static int insert_loose_map(struct object_directory *odb, + const struct object_id *oid, + const struct object_id *compat_oid) +{ + struct loose_object_map *map = odb->loose_map; + int inserted = 0; + + inserted |= insert_oid_pair(map->to_compat, oid, compat_oid); + inserted |= insert_oid_pair(map->to_storage, compat_oid, oid); + if (inserted) + oidtree_insert(odb->loose_objects_cache, compat_oid); + + return inserted; +} + static int load_one_loose_object_map(struct repository *repo, struct object_directory *dir) { struct strbuf buf = STRBUF_INIT, path = STRBUF_INIT; @@ -49,15 +65,14 @@ static int load_one_loose_object_map(struct repository *repo, struct object_dire if (!dir->loose_map) loose_object_map_init(&dir->loose_map); + if (!dir->loose_objects_cache) { + ALLOC_ARRAY(dir->loose_objects_cache, 1); + oidtree_init(dir->loose_objects_cache); + } - insert_oid_pair(dir->loose_map->to_compat, repo->hash_algo->empty_tree, repo->compat_hash_algo->empty_tree); - insert_oid_pair(dir->loose_map->to_storage, repo->compat_hash_algo->empty_tree, repo->hash_algo->empty_tree); - - insert_oid_pair(dir->loose_map->to_compat, repo->hash_algo->empty_blob, repo->compat_hash_algo->empty_blob); - insert_oid_pair(dir->loose_map->to_storage, repo->compat_hash_algo->empty_blob, repo->hash_algo->empty_blob); - - insert_oid_pair(dir->loose_map->to_compat, repo->hash_algo->null_oid, repo->compat_hash_algo->null_oid); - insert_oid_pair(dir->loose_map->to_storage, repo->compat_hash_algo->null_oid, repo->hash_algo->null_oid); + insert_loose_map(dir, repo->hash_algo->empty_tree, repo->compat_hash_algo->empty_tree); + insert_loose_map(dir, repo->hash_algo->empty_blob, repo->compat_hash_algo->empty_blob); + insert_loose_map(dir, repo->hash_algo->null_oid, repo->compat_hash_algo->null_oid); strbuf_git_common_path(&path, repo, "objects/loose-object-idx"); fp = fopen(path.buf, "rb"); @@ -77,8 +92,7 @@ static int load_one_loose_object_map(struct repository *repo, struct object_dire parse_oid_hex_algop(p, &compat_oid, &p, repo->compat_hash_algo) || p != buf.buf + buf.len) goto err; - insert_oid_pair(dir->loose_map->to_compat, &oid, &compat_oid); - insert_oid_pair(dir->loose_map->to_storage, &compat_oid, &oid); + insert_loose_map(dir, &oid, &compat_oid); } strbuf_release(&buf); @@ -197,8 +211,7 @@ int repo_add_loose_object_map(struct repository *repo, const struct object_id *o if (!should_use_loose_object_map(repo)) return 0; - inserted |= insert_oid_pair(repo->objects->odb->loose_map->to_compat, oid, compat_oid); - inserted |= insert_oid_pair(repo->objects->odb->loose_map->to_storage, compat_oid, oid); + inserted = insert_loose_map(repo->objects->odb, oid, compat_oid); if (inserted) return write_one_object(repo, oid, compat_oid); return 0; From 63a6745a07c2202d16d580156661d42e00b9762f Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 1 Oct 2023 21:40:11 -0500 Subject: [PATCH 07/30] object-file: update the loose object map when writing loose objects To implement SHA1 compatibility on SHA256 repositories the loose object map needs to be updated whenver a loose object is written. Updating the loose object map this way allows git to support the old hash algorithm in constant time. The functions write_loose_object, and stream_loose_object are the only two functions that write to the loose object store. Update stream_loose_object to compute the compatibiilty hash, update the loose object, and then call repo_add_loose_object_map to update the loose object map. Update write_object_file_flags to convert the object into it's compatibility encoding, hash the compatibility encoding, write the object, and then update the loose object map. Update force_object_loose to lookup the hash of the compatibility encoding, write the loose object, and then update the loose object map. Update write_object_file_literally to convert the object into it's compatibility hash encoding, hash the compatibility enconding, write the object, and then update the loose object map, when the type string is a known type. For objects with an unknown type this results in a partially broken repository, as the objects are not mapped. The point of write_object_file_literally is to generate a partially broken repository for testing. For testing skipping writing the loose object map is much more useful than refusing to write the broken object at all. Except that the loose objects are updated before the loose object map I have not done any analysis to see how robust this scheme is in the event of failure. Signed-off-by: "Eric W. Biederman" Signed-off-by: Junio C Hamano --- object-file.c | 113 ++++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 95 insertions(+), 18 deletions(-) diff --git a/object-file.c b/object-file.c index 7dc0c4bfbb..4e55f475b3 100644 --- a/object-file.c +++ b/object-file.c @@ -43,6 +43,8 @@ #include "setup.h" #include "submodule.h" #include "fsck.h" +#include "loose.h" +#include "object-file-convert.h" /* The maximum size for an object header. */ #define MAX_HEADER_LEN 32 @@ -1952,9 +1954,12 @@ static int start_loose_object_common(struct strbuf *tmp_file, const char *filename, unsigned flags, git_zstream *stream, unsigned char *buf, size_t buflen, - git_hash_ctx *c, + git_hash_ctx *c, git_hash_ctx *compat_c, char *hdr, int hdrlen) { + struct repository *repo = the_repository; + const struct git_hash_algo *algo = repo->hash_algo; + const struct git_hash_algo *compat = repo->compat_hash_algo; int fd; fd = create_tmpfile(tmp_file, filename); @@ -1974,14 +1979,18 @@ static int start_loose_object_common(struct strbuf *tmp_file, git_deflate_init(stream, zlib_compression_level); stream->next_out = buf; stream->avail_out = buflen; - the_hash_algo->init_fn(c); + algo->init_fn(c); + if (compat && compat_c) + compat->init_fn(compat_c); /* Start to feed header to zlib stream */ stream->next_in = (unsigned char *)hdr; stream->avail_in = hdrlen; while (git_deflate(stream, 0) == Z_OK) ; /* nothing */ - the_hash_algo->update_fn(c, hdr, hdrlen); + algo->update_fn(c, hdr, hdrlen); + if (compat && compat_c) + compat->update_fn(compat_c, hdr, hdrlen); return fd; } @@ -1990,16 +1999,21 @@ static int start_loose_object_common(struct strbuf *tmp_file, * Common steps for the inner git_deflate() loop for writing loose * objects. Returns what git_deflate() returns. */ -static int write_loose_object_common(git_hash_ctx *c, +static int write_loose_object_common(git_hash_ctx *c, git_hash_ctx *compat_c, git_zstream *stream, const int flush, unsigned char *in0, const int fd, unsigned char *compressed, const size_t compressed_len) { + struct repository *repo = the_repository; + const struct git_hash_algo *algo = repo->hash_algo; + const struct git_hash_algo *compat = repo->compat_hash_algo; int ret; ret = git_deflate(stream, flush ? Z_FINISH : 0); - the_hash_algo->update_fn(c, in0, stream->next_in - in0); + algo->update_fn(c, in0, stream->next_in - in0); + if (compat && compat_c) + compat->update_fn(compat_c, in0, stream->next_in - in0); if (write_in_full(fd, compressed, stream->next_out - compressed) < 0) die_errno(_("unable to write loose object file")); stream->next_out = compressed; @@ -2014,15 +2028,21 @@ static int write_loose_object_common(git_hash_ctx *c, * - End the compression of zlib stream. * - Get the calculated oid to "oid". */ -static int end_loose_object_common(git_hash_ctx *c, git_zstream *stream, - struct object_id *oid) +static int end_loose_object_common(git_hash_ctx *c, git_hash_ctx *compat_c, + git_zstream *stream, struct object_id *oid, + struct object_id *compat_oid) { + struct repository *repo = the_repository; + const struct git_hash_algo *algo = repo->hash_algo; + const struct git_hash_algo *compat = repo->compat_hash_algo; int ret; ret = git_deflate_end_gently(stream); if (ret != Z_OK) return ret; - the_hash_algo->final_oid_fn(oid, c); + algo->final_oid_fn(oid, c); + if (compat && compat_c) + compat->final_oid_fn(compat_oid, compat_c); return Z_OK; } @@ -2046,7 +2066,7 @@ static int write_loose_object(const struct object_id *oid, char *hdr, fd = start_loose_object_common(&tmp_file, filename.buf, flags, &stream, compressed, sizeof(compressed), - &c, hdr, hdrlen); + &c, NULL, hdr, hdrlen); if (fd < 0) return -1; @@ -2056,14 +2076,14 @@ static int write_loose_object(const struct object_id *oid, char *hdr, do { unsigned char *in0 = stream.next_in; - ret = write_loose_object_common(&c, &stream, 1, in0, fd, + ret = write_loose_object_common(&c, NULL, &stream, 1, in0, fd, compressed, sizeof(compressed)); } while (ret == Z_OK); if (ret != Z_STREAM_END) die(_("unable to deflate new object %s (%d)"), oid_to_hex(oid), ret); - ret = end_loose_object_common(&c, &stream, ¶no_oid); + ret = end_loose_object_common(&c, NULL, &stream, ¶no_oid, NULL); if (ret != Z_OK) die(_("deflateEnd on object %s failed (%d)"), oid_to_hex(oid), ret); @@ -2108,10 +2128,12 @@ static int freshen_packed_object(const struct object_id *oid) int stream_loose_object(struct input_stream *in_stream, size_t len, struct object_id *oid) { + const struct git_hash_algo *compat = the_repository->compat_hash_algo; + struct object_id compat_oid; int fd, ret, err = 0, flush = 0; unsigned char compressed[4096]; git_zstream stream; - git_hash_ctx c; + git_hash_ctx c, compat_c; struct strbuf tmp_file = STRBUF_INIT; struct strbuf filename = STRBUF_INIT; int dirlen; @@ -2135,7 +2157,7 @@ int stream_loose_object(struct input_stream *in_stream, size_t len, */ fd = start_loose_object_common(&tmp_file, filename.buf, 0, &stream, compressed, sizeof(compressed), - &c, hdr, hdrlen); + &c, &compat_c, hdr, hdrlen); if (fd < 0) { err = -1; goto cleanup; @@ -2153,7 +2175,7 @@ int stream_loose_object(struct input_stream *in_stream, size_t len, if (in_stream->is_finished) flush = 1; } - ret = write_loose_object_common(&c, &stream, flush, in0, fd, + ret = write_loose_object_common(&c, &compat_c, &stream, flush, in0, fd, compressed, sizeof(compressed)); /* * Unlike write_loose_object(), we do not have the entire @@ -2176,7 +2198,7 @@ int stream_loose_object(struct input_stream *in_stream, size_t len, */ if (ret != Z_STREAM_END) die(_("unable to stream deflate new object (%d)"), ret); - ret = end_loose_object_common(&c, &stream, oid); + ret = end_loose_object_common(&c, &compat_c, &stream, oid, &compat_oid); if (ret != Z_OK) die(_("deflateEnd on stream object failed (%d)"), ret); close_loose_object(fd, tmp_file.buf); @@ -2203,6 +2225,8 @@ int stream_loose_object(struct input_stream *in_stream, size_t len, } err = finalize_object_file(tmp_file.buf, filename.buf); + if (!err && compat) + err = repo_add_loose_object_map(the_repository, oid, &compat_oid); cleanup: strbuf_release(&tmp_file); strbuf_release(&filename); @@ -2213,17 +2237,38 @@ int write_object_file_flags(const void *buf, unsigned long len, enum object_type type, struct object_id *oid, unsigned flags) { + struct repository *repo = the_repository; + const struct git_hash_algo *algo = repo->hash_algo; + const struct git_hash_algo *compat = repo->compat_hash_algo; + struct object_id compat_oid; char hdr[MAX_HEADER_LEN]; int hdrlen = sizeof(hdr); + /* Generate compat_oid */ + if (compat) { + if (type == OBJ_BLOB) + hash_object_file(compat, buf, len, type, &compat_oid); + else { + struct strbuf converted = STRBUF_INIT; + convert_object_file(&converted, algo, compat, + buf, len, type, 0); + hash_object_file(compat, converted.buf, converted.len, + type, &compat_oid); + strbuf_release(&converted); + } + } + /* Normally if we have it in the pack then we do not bother writing * it out into .git/objects/??/?{38} file. */ - write_object_file_prepare(the_hash_algo, buf, len, type, oid, hdr, - &hdrlen); + write_object_file_prepare(algo, buf, len, type, oid, hdr, &hdrlen); if (freshen_packed_object(oid) || freshen_loose_object(oid)) return 0; - return write_loose_object(oid, hdr, hdrlen, buf, len, 0, flags); + if (write_loose_object(oid, hdr, hdrlen, buf, len, 0, flags)) + return -1; + if (compat) + return repo_add_loose_object_map(repo, oid, &compat_oid); + return 0; } int write_object_file_literally(const void *buf, unsigned long len, @@ -2231,7 +2276,27 @@ int write_object_file_literally(const void *buf, unsigned long len, unsigned flags) { char *header; + struct repository *repo = the_repository; + const struct git_hash_algo *algo = repo->hash_algo; + const struct git_hash_algo *compat = repo->compat_hash_algo; + struct object_id compat_oid; int hdrlen, status = 0; + int compat_type = -1; + + if (compat) { + compat_type = type_from_string_gently(type, -1, 1); + if (compat_type == OBJ_BLOB) + hash_object_file(compat, buf, len, compat_type, + &compat_oid); + else if (compat_type != -1) { + struct strbuf converted = STRBUF_INIT; + convert_object_file(&converted, algo, compat, + buf, len, compat_type, 0); + hash_object_file(compat, converted.buf, converted.len, + compat_type, &compat_oid); + strbuf_release(&converted); + } + } /* type string, SP, %lu of the length plus NUL must fit this */ hdrlen = strlen(type) + MAX_HEADER_LEN; @@ -2244,6 +2309,8 @@ int write_object_file_literally(const void *buf, unsigned long len, if (freshen_packed_object(oid) || freshen_loose_object(oid)) goto cleanup; status = write_loose_object(oid, header, hdrlen, buf, len, 0, 0); + if (compat_type != -1) + return repo_add_loose_object_map(repo, oid, &compat_oid); cleanup: free(header); @@ -2252,9 +2319,12 @@ int write_object_file_literally(const void *buf, unsigned long len, int force_object_loose(const struct object_id *oid, time_t mtime) { + struct repository *repo = the_repository; + const struct git_hash_algo *compat = repo->compat_hash_algo; void *buf; unsigned long len; struct object_info oi = OBJECT_INFO_INIT; + struct object_id compat_oid; enum object_type type; char hdr[MAX_HEADER_LEN]; int hdrlen; @@ -2267,8 +2337,15 @@ int force_object_loose(const struct object_id *oid, time_t mtime) oi.contentp = &buf; if (oid_object_info_extended(the_repository, oid, &oi, 0)) return error(_("cannot read object for %s"), oid_to_hex(oid)); + if (compat) { + if (repo_oid_to_algop(repo, oid, compat, &compat_oid)) + return error(_("cannot map object %s to %s"), + oid_to_hex(oid), compat->name); + } hdrlen = format_object_header(hdr, sizeof(hdr), type, len); ret = write_loose_object(oid, hdr, hdrlen, buf, len, mtime, 0); + if (!ret && compat) + ret = repo_add_loose_object_map(the_repository, oid, &compat_oid); free(buf); return ret; From c2538492df8259885abc18acdadacc22b1e77e5a Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 1 Oct 2023 21:40:12 -0500 Subject: [PATCH 08/30] object-file: add a compat_oid_in parameter to write_object_file_flags To create the proper signatures for commit objects both versions of the commit object need to be generated and signed. After that it is a waste to throw away the work of generating the compatibility hash so update write_object_file_flags to take a compatibility hash input parameter that it can use to skip the work of generating the compatability hash. Update the places that don't generate the compatability hash to pass NULL so it is easy to tell write_object_file_flags should not attempt to use their compatability hash. Signed-off-by: "Eric W. Biederman" Signed-off-by: Junio C Hamano --- cache-tree.c | 2 +- object-file.c | 6 ++++-- object-store-ll.h | 4 ++-- 3 files changed, 7 insertions(+), 5 deletions(-) diff --git a/cache-tree.c b/cache-tree.c index 641427ed41..ddc7d3d869 100644 --- a/cache-tree.c +++ b/cache-tree.c @@ -448,7 +448,7 @@ static int update_one(struct cache_tree *it, hash_object_file(the_hash_algo, buffer.buf, buffer.len, OBJ_TREE, &it->oid); } else if (write_object_file_flags(buffer.buf, buffer.len, OBJ_TREE, - &it->oid, flags & WRITE_TREE_SILENT + &it->oid, NULL, flags & WRITE_TREE_SILENT ? HASH_SILENT : 0)) { strbuf_release(&buffer); return -1; diff --git a/object-file.c b/object-file.c index 4e55f475b3..820810a5f4 100644 --- a/object-file.c +++ b/object-file.c @@ -2235,7 +2235,7 @@ int stream_loose_object(struct input_stream *in_stream, size_t len, int write_object_file_flags(const void *buf, unsigned long len, enum object_type type, struct object_id *oid, - unsigned flags) + struct object_id *compat_oid_in, unsigned flags) { struct repository *repo = the_repository; const struct git_hash_algo *algo = repo->hash_algo; @@ -2246,7 +2246,9 @@ int write_object_file_flags(const void *buf, unsigned long len, /* Generate compat_oid */ if (compat) { - if (type == OBJ_BLOB) + if (compat_oid_in) + oidcpy(&compat_oid, compat_oid_in); + else if (type == OBJ_BLOB) hash_object_file(compat, buf, len, type, &compat_oid); else { struct strbuf converted = STRBUF_INIT; diff --git a/object-store-ll.h b/object-store-ll.h index bc76d6bec8..c5f2bb2fc2 100644 --- a/object-store-ll.h +++ b/object-store-ll.h @@ -255,11 +255,11 @@ void hash_object_file(const struct git_hash_algo *algo, const void *buf, int write_object_file_flags(const void *buf, unsigned long len, enum object_type type, struct object_id *oid, - unsigned flags); + struct object_id *comapt_oid_in, unsigned flags); static inline int write_object_file(const void *buf, unsigned long len, enum object_type type, struct object_id *oid) { - return write_object_file_flags(buf, len, type, oid, 0); + return write_object_file_flags(buf, len, type, oid, NULL, 0); } int write_object_file_literally(const void *buf, unsigned long len, From 6206089cbd0b1cb30a017ec904567f040ab4cea0 Mon Sep 17 00:00:00 2001 From: "brian m. carlson" Date: Sun, 1 Oct 2023 21:40:13 -0500 Subject: [PATCH 09/30] commit: write commits for both hashes When we write a commit, we include data that is specific to the hash algorithm, such as parents and the root tree. In order to write both a SHA-1 commit and a SHA-256 version, we need to convert between them. However, a straightforward conversion isn't necessarily what we want. When we sign a commit, we sign its data, so if we create a commit for SHA-256 and then write a SHA-1 version, we'll still have only signed the SHA-256 data. While this is valid, it would be better to sign both forms of data so people using SHA-1 can verify the signatures as well. Consequently, we don't want to use the standard mapping that occurs when we write an object. Instead, let's move most of the writing of the commit into a separate function which is agnostic of the hash algorithm and which simply writes into a buffer and specify both versions of the object ourselves. We can then call this function twice: once with the SHA-256 contents, and if SHA-1 is enabled, once with the SHA-1 contents. If we're signing the commit, we then sign both versions and append both signatures to both buffers. To produce a consistent hash, we always append the signatures in the order in which Git implemented them: first SHA-1, then SHA-256. In order to make this signing code work, we split the commit signing code into two functions, one which signs the buffer, and one which appends the signature. Signed-off-by: brian m. carlson Signed-off-by: Eric W. Biederman Signed-off-by: Junio C Hamano --- commit.c | 199 ++++++++++++++++++++++++++++++++++++++++--------------- 1 file changed, 145 insertions(+), 54 deletions(-) diff --git a/commit.c b/commit.c index b3223478bc..6765f3a82b 100644 --- a/commit.c +++ b/commit.c @@ -28,6 +28,7 @@ #include "shallow.h" #include "tree.h" #include "hook.h" +#include "object-file-convert.h" static struct commit_extra_header *read_commit_extra_header_lines(const char *buf, size_t len, const char **); @@ -1100,12 +1101,11 @@ static const char *gpg_sig_headers[] = { "gpgsig-sha256", }; -int sign_with_header(struct strbuf *buf, const char *keyid) +static int add_commit_signature(struct strbuf *buf, struct strbuf *sig, const struct git_hash_algo *algo) { - struct strbuf sig = STRBUF_INIT; int inspos, copypos; const char *eoh; - const char *gpg_sig_header = gpg_sig_headers[hash_algo_by_ptr(the_hash_algo)]; + const char *gpg_sig_header = gpg_sig_headers[hash_algo_by_ptr(algo)]; int gpg_sig_header_len = strlen(gpg_sig_header); /* find the end of the header */ @@ -1115,15 +1115,8 @@ int sign_with_header(struct strbuf *buf, const char *keyid) else inspos = eoh - buf->buf + 1; - if (!keyid || !*keyid) - keyid = get_signing_key(); - if (sign_buffer(buf, &sig, keyid)) { - strbuf_release(&sig); - return -1; - } - - for (copypos = 0; sig.buf[copypos]; ) { - const char *bol = sig.buf + copypos; + for (copypos = 0; sig->buf[copypos]; ) { + const char *bol = sig->buf + copypos; const char *eol = strchrnul(bol, '\n'); int len = (eol - bol) + !!*eol; @@ -1136,11 +1129,17 @@ int sign_with_header(struct strbuf *buf, const char *keyid) inspos += len; copypos += len; } - strbuf_release(&sig); return 0; } - +static int sign_commit_to_strbuf(struct strbuf *sig, struct strbuf *buf, const char *keyid) +{ + if (!keyid || !*keyid) + keyid = get_signing_key(); + if (sign_buffer(buf, sig, keyid)) + return -1; + return 0; +} int parse_signed_commit(const struct commit *commit, struct strbuf *payload, struct strbuf *signature, @@ -1599,6 +1598,49 @@ N_("Warning: commit message did not conform to UTF-8.\n" "You may want to amend it after fixing the message, or set the config\n" "variable i18n.commitEncoding to the encoding your project uses.\n"); +static void write_commit_tree(struct strbuf *buffer, const char *msg, size_t msg_len, + const struct object_id *tree, + const struct object_id *parents, size_t parents_len, + const char *author, const char *committer, + struct commit_extra_header *extra) +{ + int encoding_is_utf8; + size_t i; + + /* Not having i18n.commitencoding is the same as having utf-8 */ + encoding_is_utf8 = is_encoding_utf8(git_commit_encoding); + + strbuf_grow(buffer, 8192); /* should avoid reallocs for the headers */ + strbuf_addf(buffer, "tree %s\n", oid_to_hex(tree)); + + /* + * NOTE! This ordering means that the same exact tree merged with a + * different order of parents will be a _different_ changeset even + * if everything else stays the same. + */ + for (i = 0; i < parents_len; i++) + strbuf_addf(buffer, "parent %s\n", oid_to_hex(&parents[i])); + + /* Person/date information */ + if (!author) + author = git_author_info(IDENT_STRICT); + strbuf_addf(buffer, "author %s\n", author); + if (!committer) + committer = git_committer_info(IDENT_STRICT); + strbuf_addf(buffer, "committer %s\n", committer); + if (!encoding_is_utf8) + strbuf_addf(buffer, "encoding %s\n", git_commit_encoding); + + while (extra) { + add_extra_header(buffer, extra); + extra = extra->next; + } + strbuf_addch(buffer, '\n'); + + /* And add the comment */ + strbuf_add(buffer, msg, msg_len); +} + int commit_tree_extended(const char *msg, size_t msg_len, const struct object_id *tree, struct commit_list *parents, struct object_id *ret, @@ -1606,63 +1648,112 @@ int commit_tree_extended(const char *msg, size_t msg_len, const char *sign_commit, struct commit_extra_header *extra) { - int result; + struct repository *r = the_repository; + int result = 0; int encoding_is_utf8; - struct strbuf buffer; + struct strbuf buffer = STRBUF_INIT, compat_buffer = STRBUF_INIT; + struct strbuf sig = STRBUF_INIT, compat_sig = STRBUF_INIT; + struct object_id *parent_buf = NULL, *compat_oid = NULL; + struct object_id compat_oid_buf; + size_t i, nparents; + + /* Not having i18n.commitencoding is the same as having utf-8 */ + encoding_is_utf8 = is_encoding_utf8(git_commit_encoding); assert_oid_type(tree, OBJ_TREE); if (memchr(msg, '\0', msg_len)) return error("a NUL byte in commit log message not allowed."); - /* Not having i18n.commitencoding is the same as having utf-8 */ - encoding_is_utf8 = is_encoding_utf8(git_commit_encoding); - - strbuf_init(&buffer, 8192); /* should avoid reallocs for the headers */ - strbuf_addf(&buffer, "tree %s\n", oid_to_hex(tree)); - - /* - * NOTE! This ordering means that the same exact tree merged with a - * different order of parents will be a _different_ changeset even - * if everything else stays the same. - */ + nparents = commit_list_count(parents); + CALLOC_ARRAY(parent_buf, nparents); + i = 0; while (parents) { struct commit *parent = pop_commit(&parents); - strbuf_addf(&buffer, "parent %s\n", - oid_to_hex(&parent->object.oid)); + oidcpy(&parent_buf[i++], &parent->object.oid); } - /* Person/date information */ - if (!author) - author = git_author_info(IDENT_STRICT); - strbuf_addf(&buffer, "author %s\n", author); - if (!committer) - committer = git_committer_info(IDENT_STRICT); - strbuf_addf(&buffer, "committer %s\n", committer); - if (!encoding_is_utf8) - strbuf_addf(&buffer, "encoding %s\n", git_commit_encoding); - - while (extra) { - add_extra_header(&buffer, extra); - extra = extra->next; - } - strbuf_addch(&buffer, '\n'); - - /* And add the comment */ - strbuf_add(&buffer, msg, msg_len); - - /* And check the encoding */ - if (encoding_is_utf8 && !verify_utf8(&buffer)) - fprintf(stderr, _(commit_utf8_warn)); - - if (sign_commit && sign_with_header(&buffer, sign_commit)) { + write_commit_tree(&buffer, msg, msg_len, tree, parent_buf, nparents, author, committer, extra); + if (sign_commit && sign_commit_to_strbuf(&sig, &buffer, sign_commit)) { result = -1; goto out; } + if (r->compat_hash_algo) { + struct object_id mapped_tree; + struct object_id *mapped_parents; - result = write_object_file(buffer.buf, buffer.len, OBJ_COMMIT, ret); + CALLOC_ARRAY(mapped_parents, nparents); + + if (repo_oid_to_algop(r, tree, r->compat_hash_algo, &mapped_tree)) { + result = -1; + free(mapped_parents); + goto out; + } + for (i = 0; i < nparents; i++) + if (repo_oid_to_algop(r, &parent_buf[i], r->compat_hash_algo, &mapped_parents[i])) { + result = -1; + free(mapped_parents); + goto out; + } + write_commit_tree(&compat_buffer, msg, msg_len, &mapped_tree, + mapped_parents, nparents, author, committer, extra); + free(mapped_parents); + + if (sign_commit && sign_commit_to_strbuf(&compat_sig, &compat_buffer, sign_commit)) { + result = -1; + goto out; + } + } + + if (sign_commit) { + struct sig_pairs { + struct strbuf *sig; + const struct git_hash_algo *algo; + } bufs [2] = { + { &compat_sig, r->compat_hash_algo }, + { &sig, r->hash_algo }, + }; + int i; + + /* + * We write algorithms in the order they were implemented in + * Git to produce a stable hash when multiple algorithms are + * used. + */ + if (r->compat_hash_algo && hash_algo_by_ptr(bufs[0].algo) > hash_algo_by_ptr(bufs[1].algo)) + SWAP(bufs[0], bufs[1]); + + /* + * We traverse each algorithm in order, and apply the signature + * to each buffer. + */ + for (i = 0; i < ARRAY_SIZE(bufs); i++) { + if (!bufs[i].algo) + continue; + add_commit_signature(&buffer, bufs[i].sig, bufs[i].algo); + if (r->compat_hash_algo) + add_commit_signature(&compat_buffer, bufs[i].sig, bufs[i].algo); + } + } + + /* And check the encoding. */ + if (encoding_is_utf8 && (!verify_utf8(&buffer) || !verify_utf8(&compat_buffer))) + fprintf(stderr, _(commit_utf8_warn)); + + if (r->compat_hash_algo) { + hash_object_file(r->compat_hash_algo, compat_buffer.buf, compat_buffer.len, + OBJ_COMMIT, &compat_oid_buf); + compat_oid = &compat_oid_buf; + } + + result = write_object_file_flags(buffer.buf, buffer.len, OBJ_COMMIT, + ret, compat_oid, 0); out: + free(parent_buf); strbuf_release(&buffer); + strbuf_release(&compat_buffer); + strbuf_release(&sig); + strbuf_release(&compat_sig); return result; } From a3e8ae5473942c0d2621c5936685b6d98e63f006 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 1 Oct 2023 21:40:14 -0500 Subject: [PATCH 10/30] commit: convert mergetag before computing the signature of a commit It so happens that commit mergetag lines embed a tag object. So to compute the compatible signature of a commit object that has mergetag lines the compatible embedded tag must be computed first. Implement this by duplicating and converting the commit extra headers into the compatible version of the commit extra headers, that need to be passed to commit_tree_extended. To handle merge tags only the compatible extra headers need to be computed. Signed-off-by: Eric W. Biederman Signed-off-by: Junio C Hamano --- commit.c | 42 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 41 insertions(+), 1 deletion(-) diff --git a/commit.c b/commit.c index 6765f3a82b..913e015966 100644 --- a/commit.c +++ b/commit.c @@ -1355,6 +1355,39 @@ void append_merge_tag_headers(struct commit_list *parents, } } +static int convert_commit_extra_headers(struct commit_extra_header *orig, + struct commit_extra_header **result) +{ + const struct git_hash_algo *compat = the_repository->compat_hash_algo; + const struct git_hash_algo *algo = the_repository->hash_algo; + struct commit_extra_header *extra = NULL, **tail = &extra; + struct strbuf out = STRBUF_INIT; + while (orig) { + struct commit_extra_header *new; + CALLOC_ARRAY(new, 1); + if (!strcmp(orig->key, "mergetag")) { + if (convert_object_file(&out, algo, compat, + orig->value, orig->len, + OBJ_TAG, 1)) { + free(new); + free_commit_extra_headers(extra); + return -1; + } + new->key = xstrdup("mergetag"); + new->value = strbuf_detach(&out, &new->len); + } else { + new->key = xstrdup(orig->key); + new->len = orig->len; + new->value = xmemdupz(orig->value, orig->len); + } + *tail = new; + tail = &new->next; + orig = orig->next; + } + *result = extra; + return 0; +} + static void add_extra_header(struct strbuf *buffer, struct commit_extra_header *extra) { @@ -1679,6 +1712,7 @@ int commit_tree_extended(const char *msg, size_t msg_len, goto out; } if (r->compat_hash_algo) { + struct commit_extra_header *compat_extra = NULL; struct object_id mapped_tree; struct object_id *mapped_parents; @@ -1695,8 +1729,14 @@ int commit_tree_extended(const char *msg, size_t msg_len, free(mapped_parents); goto out; } + if (convert_commit_extra_headers(extra, &compat_extra)) { + result = -1; + free(mapped_parents); + goto out; + } write_commit_tree(&compat_buffer, msg, msg_len, &mapped_tree, - mapped_parents, nparents, author, committer, extra); + mapped_parents, nparents, author, committer, compat_extra); + free_commit_extra_headers(compat_extra); free(mapped_parents); if (sign_commit && sign_commit_to_strbuf(&compat_sig, &compat_buffer, sign_commit)) { From 6bcc5fa20d960c86a58248e66481c1c57155cca6 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 1 Oct 2023 21:40:15 -0500 Subject: [PATCH 11/30] commit: export add_header_signature to support handling signatures on tags Rename add_commit_signature as add_header_signature, and expose it so that it can be used for converting tags from one object format to another. Inspired-by: brian m. carlson Signed-off-by: "Eric W. Biederman" Signed-off-by: Junio C Hamano --- commit.c | 6 +++--- commit.h | 1 + 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/commit.c b/commit.c index 913e015966..2b61a4d0aa 100644 --- a/commit.c +++ b/commit.c @@ -1101,7 +1101,7 @@ static const char *gpg_sig_headers[] = { "gpgsig-sha256", }; -static int add_commit_signature(struct strbuf *buf, struct strbuf *sig, const struct git_hash_algo *algo) +int add_header_signature(struct strbuf *buf, struct strbuf *sig, const struct git_hash_algo *algo) { int inspos, copypos; const char *eoh; @@ -1770,9 +1770,9 @@ int commit_tree_extended(const char *msg, size_t msg_len, for (i = 0; i < ARRAY_SIZE(bufs); i++) { if (!bufs[i].algo) continue; - add_commit_signature(&buffer, bufs[i].sig, bufs[i].algo); + add_header_signature(&buffer, bufs[i].sig, bufs[i].algo); if (r->compat_hash_algo) - add_commit_signature(&compat_buffer, bufs[i].sig, bufs[i].algo); + add_header_signature(&compat_buffer, bufs[i].sig, bufs[i].algo); } } diff --git a/commit.h b/commit.h index 28928833c5..03edcec012 100644 --- a/commit.h +++ b/commit.h @@ -370,5 +370,6 @@ int parse_buffer_signed_by_header(const char *buffer, struct strbuf *payload, struct strbuf *signature, const struct git_hash_algo *algop); +int add_header_signature(struct strbuf *buf, struct strbuf *sig, const struct git_hash_algo *algo); #endif /* COMMIT_H */ From 867386d0c8aa0ea9edb683585b69b20f96c4f776 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 1 Oct 2023 21:40:16 -0500 Subject: [PATCH 12/30] tag: sign both hashes When we write a tag the object oid is specific to the hash algorithm. This matters when a tag is signed. The hash transition plan calls for signatures on both the sha1 form and the sha256 form of the object, and for both of those signatures to live in the tag object. To generate tag object with multiple signatures, first compute the unsigned form of the tag, and then if the tag is being signed compute the unsigned form of the tag with the compatibilityr hash. Then compute compute the signatures of both buffers. Once the signatures are computed add them to both buffers. This allows computing the compatibility hash in do_sign, saving write_object_file the expense of recomputing the compatibility tag just to compute it's hash. Signed-off-by: Eric W. Biederman Signed-off-by: Junio C Hamano --- builtin/tag.c | 45 +++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 41 insertions(+), 4 deletions(-) diff --git a/builtin/tag.c b/builtin/tag.c index 3918eacbb5..8c4bc28952 100644 --- a/builtin/tag.c +++ b/builtin/tag.c @@ -28,6 +28,7 @@ #include "ref-filter.h" #include "date.h" #include "write-or-die.h" +#include "object-file-convert.h" static const char * const git_tag_usage[] = { N_("git tag [-a | -s | -u ] [-f] [-m | -F ] [-e]\n" @@ -174,9 +175,43 @@ static int verify_tag(const char *name, const char *ref UNUSED, return 0; } -static int do_sign(struct strbuf *buffer) +static int do_sign(struct strbuf *buffer, struct object_id **compat_oid, + struct object_id *compat_oid_buf) { - return sign_buffer(buffer, buffer, get_signing_key()); + const struct git_hash_algo *compat = the_repository->compat_hash_algo; + struct strbuf sig = STRBUF_INIT, compat_sig = STRBUF_INIT; + struct strbuf compat_buf = STRBUF_INIT; + const char *keyid = get_signing_key(); + int ret = -1; + + if (sign_buffer(buffer, &sig, keyid)) + return -1; + + if (compat) { + const struct git_hash_algo *algo = the_repository->hash_algo; + + if (convert_object_file(&compat_buf, algo, compat, + buffer->buf, buffer->len, OBJ_TAG, 1)) + goto out; + if (sign_buffer(&compat_buf, &compat_sig, keyid)) + goto out; + add_header_signature(&compat_buf, &sig, algo); + strbuf_addbuf(&compat_buf, &compat_sig); + hash_object_file(compat, compat_buf.buf, compat_buf.len, + OBJ_TAG, compat_oid_buf); + *compat_oid = compat_oid_buf; + } + + if (compat_sig.len) + add_header_signature(buffer, &compat_sig, compat); + + strbuf_addbuf(buffer, &sig); + ret = 0; +out: + strbuf_release(&sig); + strbuf_release(&compat_sig); + strbuf_release(&compat_buf); + return ret; } static const char tag_template[] = @@ -249,9 +284,11 @@ static void write_tag_body(int fd, const struct object_id *oid) static int build_tag_object(struct strbuf *buf, int sign, struct object_id *result) { - if (sign && do_sign(buf) < 0) + struct object_id *compat_oid = NULL, compat_oid_buf; + if (sign && do_sign(buf, &compat_oid, &compat_oid_buf) < 0) return error(_("unable to sign the tag")); - if (write_object_file(buf->buf, buf->len, OBJ_TAG, result) < 0) + if (write_object_file_flags(buf->buf, buf->len, OBJ_TAG, result, + compat_oid, 0) < 0) return error(_("unable to write tag file")); return 0; } From 095261a18d91cf47e8e8ef3b55f5e88e52ffc85f Mon Sep 17 00:00:00 2001 From: "brian m. carlson" Date: Sun, 1 Oct 2023 21:40:17 -0500 Subject: [PATCH 13/30] cache: add a function to read an OID of a specific algorithm Currently, we always read a object ID of the current algorithm with oidread. However, once we start converting objects, we'll need to consider what happens when we want to read an object ID of a specific algorithm, such as the compatibility algorithm. To make this easier, let's define oidread_algop, which specifies which algorithm we should use for our object ID, and define oidread in terms of it. Signed-off-by: brian m. carlson Signed-off-by: "Eric W. Biederman" Signed-off-by: Junio C Hamano --- hash.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/hash.h b/hash.h index 615ae0691d..e064807c17 100644 --- a/hash.h +++ b/hash.h @@ -73,10 +73,15 @@ static inline void oidclr(struct object_id *oid) oid->algo = hash_algo_by_ptr(the_hash_algo); } +static inline void oidread_algop(struct object_id *oid, const unsigned char *hash, const struct git_hash_algo *algop) +{ + memcpy(oid->hash, hash, algop->rawsz); + oid->algo = hash_algo_by_ptr(algop); +} + static inline void oidread(struct object_id *oid, const unsigned char *hash) { - memcpy(oid->hash, hash, the_hash_algo->rawsz); - oid->algo = hash_algo_by_ptr(the_hash_algo); + oidread_algop(oid, hash, the_hash_algo); } static inline int is_empty_blob_sha1(const unsigned char *sha1) From 45b3b1214154975ac03c818838e3d12571f57d1e Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 1 Oct 2023 21:40:18 -0500 Subject: [PATCH 14/30] object: factor out parse_mode out of fast-import and tree-walk into in object.h builtin/fast-import.c and tree-walk.c have almost identical version of get_mode. The two functions started out the same but have diverged slightly. The version in fast-import changed mode to a uint16_t to save memory. The version in tree-walk started erroring if no mode was present. As far as I can tell both of these changes are valid for both of the callers, so add the both changes and place the common parsing helper in object.h Rename the helper from get_mode to parse_mode so it does not conflict with another helper named get_mode in diff-no-index.c This will be used shortly in a new helper decode_tree_entry_raw which is used to compute cmpatibility objects as part of the sha256 transition. Signed-off-by: "Eric W. Biederman" Signed-off-by: Junio C Hamano --- builtin/fast-import.c | 18 ++---------------- object.h | 18 ++++++++++++++++++ tree-walk.c | 22 +++------------------- 3 files changed, 23 insertions(+), 35 deletions(-) diff --git a/builtin/fast-import.c b/builtin/fast-import.c index 4dbb10aff3..2c645fcfbe 100644 --- a/builtin/fast-import.c +++ b/builtin/fast-import.c @@ -1235,20 +1235,6 @@ static void *gfi_unpack_entry( return unpack_entry(the_repository, p, oe->idx.offset, &type, sizep); } -static const char *get_mode(const char *str, uint16_t *modep) -{ - unsigned char c; - uint16_t mode = 0; - - while ((c = *str++) != ' ') { - if (c < '0' || c > '7') - return NULL; - mode = (mode << 3) + (c - '0'); - } - *modep = mode; - return str; -} - static void load_tree(struct tree_entry *root) { struct object_id *oid = &root->versions[1].oid; @@ -1286,7 +1272,7 @@ static void load_tree(struct tree_entry *root) t->entries[t->entry_count++] = e; e->tree = NULL; - c = get_mode(c, &e->versions[1].mode); + c = parse_mode(c, &e->versions[1].mode); if (!c) die("Corrupt mode in %s", oid_to_hex(oid)); e->versions[0].mode = e->versions[1].mode; @@ -2275,7 +2261,7 @@ static void file_change_m(const char *p, struct branch *b) struct object_id oid; uint16_t mode, inline_data = 0; - p = get_mode(p, &mode); + p = parse_mode(p, &mode); if (!p) die("Corrupt mode: %s", command_buf.buf); switch (mode) { diff --git a/object.h b/object.h index 114d45954d..70c8d4ae63 100644 --- a/object.h +++ b/object.h @@ -190,6 +190,24 @@ void *create_object(struct repository *r, const struct object_id *oid, void *obj void *object_as_type(struct object *obj, enum object_type type, int quiet); + +static inline const char *parse_mode(const char *str, uint16_t *modep) +{ + unsigned char c; + unsigned int mode = 0; + + if (*str == ' ') + return NULL; + + while ((c = *str++) != ' ') { + if (c < '0' || c > '7') + return NULL; + mode = (mode << 3) + (c - '0'); + } + *modep = mode; + return str; +} + /* * Returns the object, having parsed it to find out what it is. * diff --git a/tree-walk.c b/tree-walk.c index 29ead71be1..3af50a01c2 100644 --- a/tree-walk.c +++ b/tree-walk.c @@ -10,27 +10,11 @@ #include "pathspec.h" #include "json-writer.h" -static const char *get_mode(const char *str, unsigned int *modep) -{ - unsigned char c; - unsigned int mode = 0; - - if (*str == ' ') - return NULL; - - while ((c = *str++) != ' ') { - if (c < '0' || c > '7') - return NULL; - mode = (mode << 3) + (c - '0'); - } - *modep = mode; - return str; -} - static int decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size, struct strbuf *err) { const char *path; - unsigned int mode, len; + unsigned int len; + uint16_t mode; const unsigned hashsz = the_hash_algo->rawsz; if (size < hashsz + 3 || buf[size - (hashsz + 1)]) { @@ -38,7 +22,7 @@ static int decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned l return -1; } - path = get_mode(buf, &mode); + path = parse_mode(buf, &mode); if (!path) { strbuf_addstr(err, _("malformed mode in tree entry")); return -1; From 33a14e81ae0673f8b3f7cf85168c7c573fa2fb58 Mon Sep 17 00:00:00 2001 From: "brian m. carlson" Date: Sun, 1 Oct 2023 21:40:19 -0500 Subject: [PATCH 15/30] object-file-convert: add a function to convert trees between algorithms In the future, we're going to want to provide SHA-256 repositories that have compatibility support for SHA-1 as well. In order to do so, we'll need to be able to convert tree objects from SHA-256 to SHA-1 by writing a tree with each SHA-256 object ID mapped to a SHA-1 object ID. We implement a function, convert_tree_object, that takes an existing tree buffer and writes it to a new strbuf, converting between algorithms. Let's make this function generic, because while we only need it to convert from the main algorithm to the compatibility algorithm now, we may need to do the other way around in the future, such as for transport. We avoid reusing the code in decode_tree_entry because that code normalizes data, and we don't want that here. We want to produce a complete round trip of data, so if, for example, the old entry had a wrongly zero-padded mode, we'd want to preserve that when converting to ensure a stable hash value. Signed-off-by: brian m. carlson Signed-off-by: Eric W. Biederman Signed-off-by: Junio C Hamano --- object-file-convert.c | 51 ++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 50 insertions(+), 1 deletion(-) diff --git a/object-file-convert.c b/object-file-convert.c index 1ec945eaa1..70b80fb61e 100644 --- a/object-file-convert.c +++ b/object-file-convert.c @@ -1,8 +1,10 @@ #include "git-compat-util.h" #include "gettext.h" #include "strbuf.h" +#include "hex.h" #include "repository.h" #include "hash-ll.h" +#include "hash.h" #include "object.h" #include "loose.h" #include "object-file-convert.h" @@ -36,6 +38,51 @@ int repo_oid_to_algop(struct repository *repo, const struct object_id *src, return 0; } +static int decode_tree_entry_raw(struct object_id *oid, const char **path, + size_t *len, const struct git_hash_algo *algo, + const char *buf, unsigned long size) +{ + uint16_t mode; + const unsigned hashsz = algo->rawsz; + + if (size < hashsz + 3 || buf[size - (hashsz + 1)]) { + return -1; + } + + *path = parse_mode(buf, &mode); + if (!*path || !**path) + return -1; + *len = strlen(*path) + 1; + + oidread_algop(oid, (const unsigned char *)*path + *len, algo); + return 0; +} + +static int convert_tree_object(struct strbuf *out, + const struct git_hash_algo *from, + const struct git_hash_algo *to, + const char *buffer, size_t size) +{ + const char *p = buffer, *end = buffer + size; + + while (p < end) { + struct object_id entry_oid, mapped_oid; + const char *path = NULL; + size_t pathlen; + + if (decode_tree_entry_raw(&entry_oid, &path, &pathlen, from, p, + end - p)) + return error(_("failed to decode tree entry")); + if (repo_oid_to_algop(the_repository, &entry_oid, to, &mapped_oid)) + return error(_("failed to map tree entry for %s"), oid_to_hex(&entry_oid)); + strbuf_add(out, p, path - p); + strbuf_add(out, path, pathlen); + strbuf_add(out, mapped_oid.hash, to->rawsz); + p = path + pathlen + from->rawsz; + } + return 0; +} + int convert_object_file(struct strbuf *outbuf, const struct git_hash_algo *from, const struct git_hash_algo *to, @@ -50,8 +97,10 @@ int convert_object_file(struct strbuf *outbuf, BUG("Refusing noop object file conversion"); switch (type) { - case OBJ_COMMIT: case OBJ_TREE: + ret = convert_tree_object(outbuf, from, to, buf, len); + break; + case OBJ_COMMIT: case OBJ_TAG: default: /* Not implemented yet, so fail. */ From c8762c30df5b5c0a2a91e14e77cfc94b459d089b Mon Sep 17 00:00:00 2001 From: "brian m. carlson" Date: Sun, 1 Oct 2023 21:40:20 -0500 Subject: [PATCH 16/30] object-file-convert: convert tag objects when writing When writing a tag object in a repository with both SHA-1 and SHA-256, we'll need to convert our commit objects so that we can write the hash values for both into the repository. To do so, let's add a function to convert tag objects. Note that signatures for tag objects in the current algorithm trail the message, and those for the alternate algorithm are in headers. Therefore, we parse the tag object for both a trailing signature and a header and then, when writing the other format, swap the two around. Signed-off-by: brian m. carlson Signed-off-by: Eric W. Biederman Signed-off-by: Junio C Hamano --- object-file-convert.c | 52 ++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 51 insertions(+), 1 deletion(-) diff --git a/object-file-convert.c b/object-file-convert.c index 70b80fb61e..089b68442d 100644 --- a/object-file-convert.c +++ b/object-file-convert.c @@ -7,6 +7,8 @@ #include "hash.h" #include "object.h" #include "loose.h" +#include "commit.h" +#include "gpg-interface.h" #include "object-file-convert.h" int repo_oid_to_algop(struct repository *repo, const struct object_id *src, @@ -83,6 +85,52 @@ static int convert_tree_object(struct strbuf *out, return 0; } +static int convert_tag_object(struct strbuf *out, + const struct git_hash_algo *from, + const struct git_hash_algo *to, + const char *buffer, size_t size) +{ + struct strbuf payload = STRBUF_INIT, temp = STRBUF_INIT, oursig = STRBUF_INIT, othersig = STRBUF_INIT; + size_t payload_size; + struct object_id oid, mapped_oid; + const char *p; + + /* Add some slop for longer signature header in the new algorithm. */ + strbuf_grow(out, size + 7); + + /* Is there a signature for our algorithm? */ + payload_size = parse_signed_buffer(buffer, size); + strbuf_add(&payload, buffer, payload_size); + if (payload_size != size) { + /* Yes, there is. */ + strbuf_add(&oursig, buffer + payload_size, size - payload_size); + } + /* Now, is there a signature for the other algorithm? */ + if (parse_buffer_signed_by_header(payload.buf, payload.len, &temp, &othersig, to)) { + /* Yes, there is. */ + strbuf_swap(&payload, &temp); + strbuf_release(&temp); + } + + /* + * Our payload is now in payload and we may have up to two signatrures + * in oursig and othersig. + */ + if (strncmp(payload.buf, "object ", 7) || payload.buf[from->hexsz + 7] != '\n') + return error("bogus tag object"); + if (parse_oid_hex_algop(payload.buf + 7, &oid, &p, from) < 0) + return error("bad tag object ID"); + if (repo_oid_to_algop(the_repository, &oid, to, &mapped_oid)) + return error("unable to map tree %s in tag object", + oid_to_hex(&oid)); + strbuf_addf(out, "object %s", oid_to_hex(&mapped_oid)); + strbuf_add(out, p, payload.len - (p - payload.buf)); + strbuf_addbuf(out, &othersig); + if (oursig.len) + add_header_signature(out, &oursig, from); + return 0; +} + int convert_object_file(struct strbuf *outbuf, const struct git_hash_algo *from, const struct git_hash_algo *to, @@ -100,8 +148,10 @@ int convert_object_file(struct strbuf *outbuf, case OBJ_TREE: ret = convert_tree_object(outbuf, from, to, buf, len); break; - case OBJ_COMMIT: case OBJ_TAG: + ret = convert_tag_object(outbuf, from, to, buf, len); + break; + case OBJ_COMMIT: default: /* Not implemented yet, so fail. */ ret = -1; From ac45d995f3329e5a7e85bf103bd94b48107b3803 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 1 Oct 2023 21:40:21 -0500 Subject: [PATCH 17/30] object-file-convert: don't leak when converting tag objects Upon close examination I discovered that while brian's code to convert tag objects was functionally correct, it leaked memory. Rearrange the code so that all error checking happens before any memory is allocated. Add code to release the temporary strbufs the code uses. The code pretty much assumes the tag object ends with a newline, so add an explict test to verify that is the case. Signed-off-by: Eric W. Biederman Signed-off-by: Junio C Hamano --- object-file-convert.c | 59 +++++++++++++++++++++++-------------------- 1 file changed, 32 insertions(+), 27 deletions(-) diff --git a/object-file-convert.c b/object-file-convert.c index 089b68442d..79e8e211ff 100644 --- a/object-file-convert.c +++ b/object-file-convert.c @@ -90,44 +90,49 @@ static int convert_tag_object(struct strbuf *out, const struct git_hash_algo *to, const char *buffer, size_t size) { - struct strbuf payload = STRBUF_INIT, temp = STRBUF_INIT, oursig = STRBUF_INIT, othersig = STRBUF_INIT; + struct strbuf payload = STRBUF_INIT, oursig = STRBUF_INIT, othersig = STRBUF_INIT; + const int entry_len = from->hexsz + 7; size_t payload_size; struct object_id oid, mapped_oid; const char *p; - /* Add some slop for longer signature header in the new algorithm. */ - strbuf_grow(out, size + 7); - - /* Is there a signature for our algorithm? */ - payload_size = parse_signed_buffer(buffer, size); - strbuf_add(&payload, buffer, payload_size); - if (payload_size != size) { - /* Yes, there is. */ - strbuf_add(&oursig, buffer + payload_size, size - payload_size); - } - /* Now, is there a signature for the other algorithm? */ - if (parse_buffer_signed_by_header(payload.buf, payload.len, &temp, &othersig, to)) { - /* Yes, there is. */ - strbuf_swap(&payload, &temp); - strbuf_release(&temp); - } - - /* - * Our payload is now in payload and we may have up to two signatrures - * in oursig and othersig. - */ - if (strncmp(payload.buf, "object ", 7) || payload.buf[from->hexsz + 7] != '\n') + /* Consume the object line */ + if ((entry_len >= size) || + memcmp(buffer, "object ", 7) || buffer[entry_len] != '\n') return error("bogus tag object"); - if (parse_oid_hex_algop(payload.buf + 7, &oid, &p, from) < 0) + if (parse_oid_hex_algop(buffer + 7, &oid, &p, from) < 0) return error("bad tag object ID"); if (repo_oid_to_algop(the_repository, &oid, to, &mapped_oid)) return error("unable to map tree %s in tag object", oid_to_hex(&oid)); - strbuf_addf(out, "object %s", oid_to_hex(&mapped_oid)); - strbuf_add(out, p, payload.len - (p - payload.buf)); - strbuf_addbuf(out, &othersig); + size -= ((p + 1) - buffer); + buffer = p + 1; + + /* Is there a signature for our algorithm? */ + payload_size = parse_signed_buffer(buffer, size); + if (payload_size != size) { + /* Yes, there is. */ + strbuf_add(&oursig, buffer + payload_size, size - payload_size); + } + + /* Now, is there a signature for the other algorithm? */ + parse_buffer_signed_by_header(buffer, payload_size, &payload, &othersig, to); + /* + * Our payload is now in payload and we may have up to two signatrures + * in oursig and othersig. + */ + + /* Add some slop for longer signature header in the new algorithm. */ + strbuf_grow(out, (7 + to->hexsz + 1) + size + 7); + strbuf_addf(out, "object %s\n", oid_to_hex(&mapped_oid)); + strbuf_addbuf(out, &payload); if (oursig.len) add_header_signature(out, &oursig, from); + strbuf_addbuf(out, &othersig); + + strbuf_release(&payload); + strbuf_release(&othersig); + strbuf_release(&oursig); return 0; } From 318b023e4a3f5e4f2ecf202aa87db7e5df2c4442 Mon Sep 17 00:00:00 2001 From: "brian m. carlson" Date: Sun, 1 Oct 2023 21:40:22 -0500 Subject: [PATCH 18/30] object-file-convert: convert commit objects when writing When writing a commit object in a repository with both SHA-1 and SHA-256, we'll need to convert our commit objects so that we can write the hash values for both into the repository. To do so, let's add a function to convert commit objects. Read the commit object and map the tree value and any of the parent values, and copy the rest of the commit through unmodified. Note that we don't need to modify the signature headers, because they are the same under both algorithms. Signed-off-by: brian m. carlson Signed-off-by: Eric W. Biederman Signed-off-by: Junio C Hamano --- object-file-convert.c | 46 ++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 45 insertions(+), 1 deletion(-) diff --git a/object-file-convert.c b/object-file-convert.c index 79e8e211ff..0da081104e 100644 --- a/object-file-convert.c +++ b/object-file-convert.c @@ -136,6 +136,48 @@ static int convert_tag_object(struct strbuf *out, return 0; } +static int convert_commit_object(struct strbuf *out, + const struct git_hash_algo *from, + const struct git_hash_algo *to, + const char *buffer, size_t size) +{ + const char *tail = buffer; + const char *bufptr = buffer; + const int tree_entry_len = from->hexsz + 5; + const int parent_entry_len = from->hexsz + 7; + struct object_id oid, mapped_oid; + const char *p; + + tail += size; + if (tail <= bufptr + tree_entry_len + 1 || memcmp(bufptr, "tree ", 5) || + bufptr[tree_entry_len] != '\n') + return error("bogus commit object"); + if (parse_oid_hex_algop(bufptr + 5, &oid, &p, from) < 0) + return error("bad tree pointer"); + + if (repo_oid_to_algop(the_repository, &oid, to, &mapped_oid)) + return error("unable to map tree %s in commit object", + oid_to_hex(&oid)); + strbuf_addf(out, "tree %s\n", oid_to_hex(&mapped_oid)); + bufptr = p + 1; + + while (bufptr + parent_entry_len < tail && !memcmp(bufptr, "parent ", 7)) { + if (tail <= bufptr + parent_entry_len + 1 || + parse_oid_hex_algop(bufptr + 7, &oid, &p, from) || + *p != '\n') + return error("bad parents in commit"); + + if (repo_oid_to_algop(the_repository, &oid, to, &mapped_oid)) + return error("unable to map parent %s in commit object", + oid_to_hex(&oid)); + + strbuf_addf(out, "parent %s\n", oid_to_hex(&mapped_oid)); + bufptr = p + 1; + } + strbuf_add(out, bufptr, tail - bufptr); + return 0; +} + int convert_object_file(struct strbuf *outbuf, const struct git_hash_algo *from, const struct git_hash_algo *to, @@ -150,13 +192,15 @@ int convert_object_file(struct strbuf *outbuf, BUG("Refusing noop object file conversion"); switch (type) { + case OBJ_COMMIT: + ret = convert_commit_object(outbuf, from, to, buf, len); + break; case OBJ_TREE: ret = convert_tree_object(outbuf, from, to, buf, len); break; case OBJ_TAG: ret = convert_tag_object(outbuf, from, to, buf, len); break; - case OBJ_COMMIT: default: /* Not implemented yet, so fail. */ ret = -1; From 08a45903cb32304946c11dfb2239db448777aed7 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 1 Oct 2023 21:40:23 -0500 Subject: [PATCH 19/30] object-file-convert: convert commits that embed signed tags As mentioned in the hash function transition plan commit mergetag lines need to be handled. The commit mergetag lines embed an entire tag object in a commit object. Keep the implementation sane if not fast by unembedding the tag object, converting the tag object, and embedding the new tag object, in the new commit object. In the long run I don't expect any other approach is maintainable, as tag objects may be extended in ways that require additional translation. To keep the implementation of convert_commit_object maintainable I have modified convert_commit_object to process the lines in any order, and to fail on unknown lines. We can't know ahead of time if a new line might embed something that needs translation or not so it is better to fail and require the code to be updated instead of silently mistranslating objects. Signed-off-by: Eric W. Biederman Signed-off-by: Junio C Hamano --- object-file-convert.c | 104 +++++++++++++++++++++++++++++++++--------- 1 file changed, 82 insertions(+), 22 deletions(-) diff --git a/object-file-convert.c b/object-file-convert.c index 0da081104e..4f6189095b 100644 --- a/object-file-convert.c +++ b/object-file-convert.c @@ -146,35 +146,95 @@ static int convert_commit_object(struct strbuf *out, const int tree_entry_len = from->hexsz + 5; const int parent_entry_len = from->hexsz + 7; struct object_id oid, mapped_oid; - const char *p; + const char *p, *eol; tail += size; - if (tail <= bufptr + tree_entry_len + 1 || memcmp(bufptr, "tree ", 5) || - bufptr[tree_entry_len] != '\n') - return error("bogus commit object"); - if (parse_oid_hex_algop(bufptr + 5, &oid, &p, from) < 0) - return error("bad tree pointer"); - if (repo_oid_to_algop(the_repository, &oid, to, &mapped_oid)) - return error("unable to map tree %s in commit object", - oid_to_hex(&oid)); - strbuf_addf(out, "tree %s\n", oid_to_hex(&mapped_oid)); - bufptr = p + 1; + while ((bufptr < tail) && (*bufptr != '\n')) { + eol = memchr(bufptr, '\n', tail - bufptr); + if (!eol) + return error(_("bad %s in commit"), "line"); - while (bufptr + parent_entry_len < tail && !memcmp(bufptr, "parent ", 7)) { - if (tail <= bufptr + parent_entry_len + 1 || - parse_oid_hex_algop(bufptr + 7, &oid, &p, from) || - *p != '\n') - return error("bad parents in commit"); + if (((bufptr + 5) < eol) && !memcmp(bufptr, "tree ", 5)) + { + if (((bufptr + tree_entry_len) != eol) || + parse_oid_hex_algop(bufptr + 5, &oid, &p, from) || + (p != eol)) + return error(_("bad %s in commit"), "tree"); - if (repo_oid_to_algop(the_repository, &oid, to, &mapped_oid)) - return error("unable to map parent %s in commit object", - oid_to_hex(&oid)); + if (repo_oid_to_algop(the_repository, &oid, to, &mapped_oid)) + return error(_("unable to map %s %s in commit object"), + "tree", oid_to_hex(&oid)); + strbuf_addf(out, "tree %s\n", oid_to_hex(&mapped_oid)); + } + else if (((bufptr + 7) < eol) && !memcmp(bufptr, "parent ", 7)) + { + if (((bufptr + parent_entry_len) != eol) || + parse_oid_hex_algop(bufptr + 7, &oid, &p, from) || + (p != eol)) + return error(_("bad %s in commit"), "parent"); - strbuf_addf(out, "parent %s\n", oid_to_hex(&mapped_oid)); - bufptr = p + 1; + if (repo_oid_to_algop(the_repository, &oid, to, &mapped_oid)) + return error(_("unable to map %s %s in commit object"), + "parent", oid_to_hex(&oid)); + + strbuf_addf(out, "parent %s\n", oid_to_hex(&mapped_oid)); + } + else if (((bufptr + 9) < eol) && !memcmp(bufptr, "mergetag ", 9)) + { + struct strbuf tag = STRBUF_INIT, new_tag = STRBUF_INIT; + + /* Recover the tag object from the mergetag */ + strbuf_add(&tag, bufptr + 9, (eol - (bufptr + 9)) + 1); + + bufptr = eol + 1; + while ((bufptr < tail) && (*bufptr == ' ')) { + eol = memchr(bufptr, '\n', tail - bufptr); + if (!eol) { + strbuf_release(&tag); + return error(_("bad %s in commit"), "mergetag continuation"); + } + strbuf_add(&tag, bufptr + 1, (eol - (bufptr + 1)) + 1); + bufptr = eol + 1; + } + + /* Compute the new tag object */ + if (convert_tag_object(&new_tag, from, to, tag.buf, tag.len)) { + strbuf_release(&tag); + strbuf_release(&new_tag); + return -1; + } + + /* Write the new mergetag */ + strbuf_addstr(out, "mergetag"); + strbuf_add_lines(out, " ", new_tag.buf, new_tag.len); + strbuf_release(&tag); + strbuf_release(&new_tag); + } + else if (((bufptr + 7) < tail) && !memcmp(bufptr, "author ", 7)) + strbuf_add(out, bufptr, (eol - bufptr) + 1); + else if (((bufptr + 10) < tail) && !memcmp(bufptr, "committer ", 10)) + strbuf_add(out, bufptr, (eol - bufptr) + 1); + else if (((bufptr + 9) < tail) && !memcmp(bufptr, "encoding ", 9)) + strbuf_add(out, bufptr, (eol - bufptr) + 1); + else if (((bufptr + 6) < tail) && !memcmp(bufptr, "gpgsig", 6)) + strbuf_add(out, bufptr, (eol - bufptr) + 1); + else { + /* Unknown line fail it might embed an oid */ + return -1; + } + /* Consume any trailing continuation lines */ + bufptr = eol + 1; + while ((bufptr < tail) && (*bufptr == ' ')) { + eol = memchr(bufptr, '\n', tail - bufptr); + if (!eol) + return error(_("bad %s in commit"), "continuation"); + strbuf_add(out, bufptr, (eol - bufptr) + 1); + bufptr = eol + 1; + } } - strbuf_add(out, bufptr, tail - bufptr); + if (bufptr < tail) + strbuf_add(out, bufptr, tail - bufptr); return 0; } From 2328ebaa4ef7a921c7021db9e83e122dbe2ac7ad Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 1 Oct 2023 21:40:24 -0500 Subject: [PATCH 20/30] object-file: update object_info_extended to reencode objects oid_object_info_extended is updated to detect an oid encoding that does not match the current repository, use repo_oid_to_algop to find the correspoding oid in the current repository and to return the data for the oid. Signed-off-by: "Eric W. Biederman" Signed-off-by: Junio C Hamano --- object-file.c | 91 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 91 insertions(+) diff --git a/object-file.c b/object-file.c index 820810a5f4..b2d43d0098 100644 --- a/object-file.c +++ b/object-file.c @@ -1662,10 +1662,101 @@ static int do_oid_object_info_extended(struct repository *r, return 0; } +static int oid_object_info_convert(struct repository *r, + const struct object_id *input_oid, + struct object_info *input_oi, unsigned flags) +{ + const struct git_hash_algo *input_algo = &hash_algos[input_oid->algo]; + int do_die = flags & OBJECT_INFO_DIE_IF_CORRUPT; + struct strbuf type_name = STRBUF_INIT; + struct object_id oid, delta_base_oid; + struct object_info new_oi, *oi; + unsigned long size; + void *content; + int ret; + + if (repo_oid_to_algop(r, input_oid, the_hash_algo, &oid)) { + if (do_die) + die(_("missing mapping of %s to %s"), + oid_to_hex(input_oid), the_hash_algo->name); + return -1; + } + + /* Is new_oi needed? */ + oi = input_oi; + if (input_oi && (input_oi->delta_base_oid || input_oi->sizep || + input_oi->contentp)) { + new_oi = *input_oi; + /* Does delta_base_oid need to be converted? */ + if (input_oi->delta_base_oid) + new_oi.delta_base_oid = &delta_base_oid; + /* Will the attributes differ when converted? */ + if (input_oi->sizep || input_oi->contentp) { + new_oi.contentp = &content; + new_oi.sizep = &size; + new_oi.type_name = &type_name; + } + oi = &new_oi; + } + + ret = oid_object_info_extended(r, &oid, oi, flags); + if (ret) + return -1; + if (oi == input_oi) + return ret; + + if (new_oi.contentp) { + struct strbuf outbuf = STRBUF_INIT; + enum object_type type; + + type = type_from_string_gently(type_name.buf, type_name.len, + !do_die); + if (type == -1) + return -1; + if (type != OBJ_BLOB) { + ret = convert_object_file(&outbuf, + the_hash_algo, input_algo, + content, size, type, !do_die); + if (ret == -1) + return -1; + free(content); + size = outbuf.len; + content = strbuf_detach(&outbuf, NULL); + } + if (input_oi->sizep) + *input_oi->sizep = size; + if (input_oi->contentp) + *input_oi->contentp = content; + else + free(content); + if (input_oi->type_name) + *input_oi->type_name = type_name; + else + strbuf_release(&type_name); + } + if (new_oi.delta_base_oid == &delta_base_oid) { + if (repo_oid_to_algop(r, &delta_base_oid, input_algo, + input_oi->delta_base_oid)) { + if (do_die) + die(_("missing mapping of %s to %s"), + oid_to_hex(&delta_base_oid), + input_algo->name); + return -1; + } + } + input_oi->whence = new_oi.whence; + input_oi->u = new_oi.u; + return ret; +} + int oid_object_info_extended(struct repository *r, const struct object_id *oid, struct object_info *oi, unsigned flags) { int ret; + + if (oid->algo && (hash_algo_by_ptr(r->hash_algo) != oid->algo)) + return oid_object_info_convert(r, oid, oi, flags); + obj_read_lock(); ret = do_oid_object_info_extended(r, oid, oi, flags); obj_read_unlock(); From 9ae702faf151802f481e68db8d5cb5b536b31c2a Mon Sep 17 00:00:00 2001 From: "brian m. carlson" Date: Sun, 1 Oct 2023 21:40:25 -0500 Subject: [PATCH 21/30] repository: implement extensions.compatObjectFormat Add a configuration option to enable updating and reading from compatibility hash maps when git accesses the reposotiry. Call the helper function repo_set_compat_hash_algo with the value that compatObjectFormat is set to. Signed-off-by: "Eric W. Biederman" Signed-off-by: Junio C Hamano --- Documentation/config/extensions.txt | 12 ++++++++++++ repository.c | 2 +- setup.c | 23 +++++++++++++++++++++-- setup.h | 1 + 4 files changed, 35 insertions(+), 3 deletions(-) diff --git a/Documentation/config/extensions.txt b/Documentation/config/extensions.txt index bccaec7a96..9f72e6d9f4 100644 --- a/Documentation/config/extensions.txt +++ b/Documentation/config/extensions.txt @@ -7,6 +7,18 @@ Note that this setting should only be set by linkgit:git-init[1] or linkgit:git-clone[1]. Trying to change it after initialization will not work and will produce hard-to-diagnose issues. +extensions.compatObjectFormat:: + + Specify a compatitbility hash algorithm to use. The acceptable values + are `sha1` and `sha256`. The value specified must be different from the + value of extensions.objectFormat. This allows client level + interoperability between git repositories whose objectFormat matches + this compatObjectFormat. In particular when fully implemented the + pushes and pulls from a repository in whose objectFormat matches + compatObjectFormat. As well as being able to use oids encoded in + compatObjectFormat in addition to oids encoded with objectFormat to + locally specify objects. + extensions.worktreeConfig:: If enabled, then worktrees will load config settings from the `$GIT_DIR/config.worktree` file in addition to the diff --git a/repository.c b/repository.c index 6214f61cf4..9d91536b61 100644 --- a/repository.c +++ b/repository.c @@ -194,7 +194,7 @@ int repo_init(struct repository *repo, goto error; repo_set_hash_algo(repo, format.hash_algo); - repo_set_compat_hash_algo(repo, GIT_HASH_UNKNOWN); + repo_set_compat_hash_algo(repo, format.compat_hash_algo); repo->repository_format_worktree_config = format.worktree_config; /* take ownership of format.partial_clone */ diff --git a/setup.c b/setup.c index aa8bf5da52..85259a259b 100644 --- a/setup.c +++ b/setup.c @@ -590,6 +590,25 @@ static enum extension_result handle_extension(const char *var, "extensions.objectformat", value); data->hash_algo = format; return EXTENSION_OK; + } else if (!strcmp(ext, "compatobjectformat")) { + struct string_list_item *item; + int format; + + if (!value) + return config_error_nonbool(var); + format = hash_algo_by_name(value); + if (format == GIT_HASH_UNKNOWN) + return error(_("invalid value for '%s': '%s'"), + "extensions.compatobjectformat", value); + /* For now only support compatObjectFormat being specified once. */ + for_each_string_list_item(item, &data->v1_only_extensions) { + if (!strcmp(item->string, "compatobjectformat")) + return error(_("'%s' already specified as '%s'"), + "extensions.compatobjectformat", + hash_algos[data->compat_hash_algo].name); + } + data->compat_hash_algo = format; + return EXTENSION_OK; } return EXTENSION_UNKNOWN; } @@ -1565,7 +1584,7 @@ const char *setup_git_directory_gently(int *nongit_ok) if (startup_info->have_repository) { repo_set_hash_algo(the_repository, repo_fmt.hash_algo); repo_set_compat_hash_algo(the_repository, - GIT_HASH_UNKNOWN); + repo_fmt.compat_hash_algo); the_repository->repository_format_worktree_config = repo_fmt.worktree_config; /* take ownership of repo_fmt.partial_clone */ @@ -1659,7 +1678,7 @@ void check_repository_format(struct repository_format *fmt) check_repository_format_gently(get_git_dir(), fmt, NULL); startup_info->have_repository = 1; repo_set_hash_algo(the_repository, fmt->hash_algo); - repo_set_compat_hash_algo(the_repository, GIT_HASH_UNKNOWN); + repo_set_compat_hash_algo(the_repository, fmt->compat_hash_algo); the_repository->repository_format_worktree_config = fmt->worktree_config; the_repository->repository_format_partial_clone = diff --git a/setup.h b/setup.h index 58fd2605dd..5d678ceb8c 100644 --- a/setup.h +++ b/setup.h @@ -86,6 +86,7 @@ struct repository_format { int worktree_config; int is_bare; int hash_algo; + int compat_hash_algo; int sparse_index; char *work_tree; struct string_list unknown_extensions; From d7446c89b8ed57f1fa0a5b2ea5e4b7e5fcb7d9cd Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 1 Oct 2023 21:40:26 -0500 Subject: [PATCH 22/30] rev-parse: add an --output-object-format parameter The new --output-object-format parameter returns the oid in the specified format. This is a generally useful plumbing facility. It is useful for writing test cases and for directly querying the translation maps. Signed-off-by: "Eric W. Biederman" Signed-off-by: Junio C Hamano --- Documentation/git-rev-parse.txt | 12 ++++++++++++ builtin/rev-parse.c | 23 +++++++++++++++++++++++ 2 files changed, 35 insertions(+) diff --git a/Documentation/git-rev-parse.txt b/Documentation/git-rev-parse.txt index f26a7591e3..f0f9021f2a 100644 --- a/Documentation/git-rev-parse.txt +++ b/Documentation/git-rev-parse.txt @@ -159,6 +159,18 @@ for another option. unfortunately named tag "master"), and show them as full refnames (e.g. "refs/heads/master"). +--output-object-format=(sha1|sha256|storage):: + + Allow oids to be input from any object format that the current + repository supports. + + Specifying "sha1" translates if necessary and returns a sha1 oid. + + Specifying "sha256" translates if necessary and returns a sha256 oid. + + Specifying "storage" translates if necessary and returns an oid in + encoded in the storage hash algorithm. + Options for Objects ~~~~~~~~~~~~~~~~~~~ diff --git a/builtin/rev-parse.c b/builtin/rev-parse.c index 43e9676540..0ef3e658cc 100644 --- a/builtin/rev-parse.c +++ b/builtin/rev-parse.c @@ -25,6 +25,7 @@ #include "submodule.h" #include "commit-reach.h" #include "shallow.h" +#include "object-file-convert.h" #define DO_REVS 1 #define DO_NOREV 2 @@ -675,6 +676,8 @@ static void print_path(const char *path, const char *prefix, enum format_type fo int cmd_rev_parse(int argc, const char **argv, const char *prefix) { int i, as_is = 0, verify = 0, quiet = 0, revs_count = 0, type = 0; + const struct git_hash_algo *output_algo = NULL; + const struct git_hash_algo *compat = NULL; int did_repo_setup = 0; int has_dashdash = 0; int output_prefix = 0; @@ -746,6 +749,7 @@ int cmd_rev_parse(int argc, const char **argv, const char *prefix) prepare_repo_settings(the_repository); the_repository->settings.command_requires_full_index = 0; + compat = the_repository->compat_hash_algo; } if (!strcmp(arg, "--")) { @@ -833,6 +837,22 @@ int cmd_rev_parse(int argc, const char **argv, const char *prefix) flags |= GET_OID_QUIETLY; continue; } + if (opt_with_value(arg, "--output-object-format", &arg)) { + if (!arg) + die(_("no object format specified")); + if (!strcmp(arg, the_hash_algo->name) || + !strcmp(arg, "storage")) { + flags |= GET_OID_HASH_ANY; + output_algo = the_hash_algo; + continue; + } + else if (compat && !strcmp(arg, compat->name)) { + flags |= GET_OID_HASH_ANY; + output_algo = compat; + continue; + } + else die(_("unsupported object format: %s"), arg); + } if (opt_with_value(arg, "--short", &arg)) { filter &= ~(DO_FLAGS|DO_NOREV); verify = 1; @@ -1083,6 +1103,9 @@ int cmd_rev_parse(int argc, const char **argv, const char *prefix) } if (!get_oid_with_context(the_repository, name, flags, &oid, &unused)) { + if (output_algo) + repo_oid_to_algop(the_repository, &oid, + output_algo, &oid); if (verify) revs_count++; else From d6222a2d05c93b22d5ef19b7361f7b1ef2964eb4 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 1 Oct 2023 21:40:27 -0500 Subject: [PATCH 23/30] builtin/cat-file: let the oid determine the output algorithm Use GET_OID_HASH_ANY when calling get_oid_with_context. This implements the semi-obvious behaviour that specifying a sha1 oid shows the output for a sha1 encoded object, and specifying a sha256 oid shows the output for a sha256 encoded object. This is useful for testing the the conversion of an object to an equivalent object encoded with a different hash function. Signed-off-by: "Eric W. Biederman" Signed-off-by: Junio C Hamano --- builtin/cat-file.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/builtin/cat-file.c b/builtin/cat-file.c index 694c8538df..e615d1f8e0 100644 --- a/builtin/cat-file.c +++ b/builtin/cat-file.c @@ -107,7 +107,10 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name, struct object_info oi = OBJECT_INFO_INIT; struct strbuf sb = STRBUF_INIT; unsigned flags = OBJECT_INFO_LOOKUP_REPLACE; - unsigned get_oid_flags = GET_OID_RECORD_PATH | GET_OID_ONLY_TO_DIE; + unsigned get_oid_flags = + GET_OID_RECORD_PATH | + GET_OID_ONLY_TO_DIE | + GET_OID_HASH_ANY; const char *path = force_path; const int opt_cw = (opt == 'c' || opt == 'w'); if (!path && opt_cw) @@ -223,7 +226,8 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name, &size); const char *target; if (!skip_prefix(buffer, "object ", &target) || - get_oid_hex(target, &blob_oid)) + get_oid_hex_algop(target, &blob_oid, + &hash_algos[oid.algo])) die("%s not a valid tag", oid_to_hex(&oid)); free(buffer); } else @@ -512,7 +516,9 @@ static void batch_one_object(const char *obj_name, struct expand_data *data) { struct object_context ctx; - int flags = opt->follow_symlinks ? GET_OID_FOLLOW_SYMLINKS : 0; + int flags = + GET_OID_HASH_ANY | + (opt->follow_symlinks ? GET_OID_FOLLOW_SYMLINKS : 0); enum get_oid_result result; result = get_oid_with_context(the_repository, obj_name, From efed687edcaa272601e0f4e192db368972daa7ac Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 1 Oct 2023 21:40:28 -0500 Subject: [PATCH 24/30] tree-walk: init_tree_desc take an oid to get the hash algorithm To make it possible for git ls-tree to display the tree encoded in the hash algorithm of the oid specified to git ls-tree, update init_tree_desc to take as a parameter the oid of the tree object. Update all callers of init_tree_desc and init_tree_desc_gently to pass the oid of the tree object. Use the oid of the tree object to discover the hash algorithm of the oid and store that hash algorithm in struct tree_desc. Use the hash algorithm in decode_tree_entry and update_tree_entry_internal to handle reading a tree object encoded in a hash algorithm that differs from the repositories hash algorithm. Signed-off-by: "Eric W. Biederman" Signed-off-by: Junio C Hamano --- archive.c | 3 ++- builtin/am.c | 6 +++--- builtin/checkout.c | 8 +++++--- builtin/clone.c | 2 +- builtin/commit.c | 2 +- builtin/grep.c | 8 ++++---- builtin/merge.c | 3 ++- builtin/pack-objects.c | 6 ++++-- builtin/read-tree.c | 2 +- builtin/stash.c | 5 +++-- cache-tree.c | 2 +- delta-islands.c | 2 +- diff-lib.c | 2 +- fsck.c | 6 ++++-- http-push.c | 2 +- list-objects.c | 2 +- match-trees.c | 4 ++-- merge-ort.c | 11 ++++++----- merge-recursive.c | 2 +- merge.c | 3 ++- pack-bitmap-write.c | 2 +- packfile.c | 3 ++- reflog.c | 2 +- revision.c | 4 ++-- tree-walk.c | 36 +++++++++++++++++++++--------------- tree-walk.h | 7 +++++-- tree.c | 2 +- walker.c | 2 +- 28 files changed, 80 insertions(+), 59 deletions(-) diff --git a/archive.c b/archive.c index ca11db185b..b10269aee7 100644 --- a/archive.c +++ b/archive.c @@ -339,7 +339,8 @@ int write_archive_entries(struct archiver_args *args, opts.src_index = args->repo->index; opts.dst_index = args->repo->index; opts.fn = oneway_merge; - init_tree_desc(&t, args->tree->buffer, args->tree->size); + init_tree_desc(&t, &args->tree->object.oid, + args->tree->buffer, args->tree->size); if (unpack_trees(1, &t, &opts)) return -1; git_attr_set_direction(GIT_ATTR_INDEX); diff --git a/builtin/am.c b/builtin/am.c index 8bde034fae..4dfd714b91 100644 --- a/builtin/am.c +++ b/builtin/am.c @@ -1991,8 +1991,8 @@ static int fast_forward_to(struct tree *head, struct tree *remote, int reset) opts.reset = reset ? UNPACK_RESET_PROTECT_UNTRACKED : 0; opts.preserve_ignored = 0; /* FIXME: !overwrite_ignore */ opts.fn = twoway_merge; - init_tree_desc(&t[0], head->buffer, head->size); - init_tree_desc(&t[1], remote->buffer, remote->size); + init_tree_desc(&t[0], &head->object.oid, head->buffer, head->size); + init_tree_desc(&t[1], &remote->object.oid, remote->buffer, remote->size); if (unpack_trees(2, t, &opts)) { rollback_lock_file(&lock_file); @@ -2026,7 +2026,7 @@ static int merge_tree(struct tree *tree) opts.dst_index = &the_index; opts.merge = 1; opts.fn = oneway_merge; - init_tree_desc(&t[0], tree->buffer, tree->size); + init_tree_desc(&t[0], &tree->object.oid, tree->buffer, tree->size); if (unpack_trees(1, t, &opts)) { rollback_lock_file(&lock_file); diff --git a/builtin/checkout.c b/builtin/checkout.c index f53612f468..03eff73fd0 100644 --- a/builtin/checkout.c +++ b/builtin/checkout.c @@ -701,7 +701,7 @@ static int reset_tree(struct tree *tree, const struct checkout_opts *o, info->commit ? &info->commit->object.oid : null_oid(), NULL); parse_tree(tree); - init_tree_desc(&tree_desc, tree->buffer, tree->size); + init_tree_desc(&tree_desc, &tree->object.oid, tree->buffer, tree->size); switch (unpack_trees(1, &tree_desc, &opts)) { case -2: *writeout_error = 1; @@ -815,10 +815,12 @@ static int merge_working_tree(const struct checkout_opts *opts, die(_("unable to parse commit %s"), oid_to_hex(old_commit_oid)); - init_tree_desc(&trees[0], tree->buffer, tree->size); + init_tree_desc(&trees[0], &tree->object.oid, + tree->buffer, tree->size); parse_tree(new_tree); tree = new_tree; - init_tree_desc(&trees[1], tree->buffer, tree->size); + init_tree_desc(&trees[1], &tree->object.oid, + tree->buffer, tree->size); ret = unpack_trees(2, trees, &topts); clear_unpack_trees_porcelain(&topts); diff --git a/builtin/clone.c b/builtin/clone.c index c6357af949..79ceefb939 100644 --- a/builtin/clone.c +++ b/builtin/clone.c @@ -737,7 +737,7 @@ static int checkout(int submodule_progress, int filter_submodules) if (!tree) die(_("unable to parse commit %s"), oid_to_hex(&oid)); parse_tree(tree); - init_tree_desc(&t, tree->buffer, tree->size); + init_tree_desc(&t, &tree->object.oid, tree->buffer, tree->size); if (unpack_trees(1, &t, &opts) < 0) die(_("unable to checkout working tree")); diff --git a/builtin/commit.c b/builtin/commit.c index 7da5f92448..537319932b 100644 --- a/builtin/commit.c +++ b/builtin/commit.c @@ -340,7 +340,7 @@ static void create_base_index(const struct commit *current_head) if (!tree) die(_("failed to unpack HEAD tree object")); parse_tree(tree); - init_tree_desc(&t, tree->buffer, tree->size); + init_tree_desc(&t, &tree->object.oid, tree->buffer, tree->size); if (unpack_trees(1, &t, &opts)) exit(128); /* We've already reported the error, finish dying */ } diff --git a/builtin/grep.c b/builtin/grep.c index 50e712a184..0c2b8a376f 100644 --- a/builtin/grep.c +++ b/builtin/grep.c @@ -530,7 +530,7 @@ static int grep_submodule(struct grep_opt *opt, strbuf_addstr(&base, filename); strbuf_addch(&base, '/'); - init_tree_desc(&tree, data, size); + init_tree_desc(&tree, oid, data, size); hit = grep_tree(&subopt, pathspec, &tree, &base, base.len, object_type == OBJ_COMMIT); strbuf_release(&base); @@ -574,7 +574,7 @@ static int grep_cache(struct grep_opt *opt, data = repo_read_object_file(the_repository, &ce->oid, &type, &size); - init_tree_desc(&tree, data, size); + init_tree_desc(&tree, &ce->oid, data, size); hit |= grep_tree(opt, pathspec, &tree, &name, 0, 0); strbuf_setlen(&name, name_base_len); @@ -670,7 +670,7 @@ static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec, oid_to_hex(&entry.oid)); strbuf_addch(base, '/'); - init_tree_desc(&sub, data, size); + init_tree_desc(&sub, &entry.oid, data, size); hit |= grep_tree(opt, pathspec, &sub, base, tn_len, check_attr); free(data); @@ -714,7 +714,7 @@ static int grep_object(struct grep_opt *opt, const struct pathspec *pathspec, strbuf_add(&base, name, len); strbuf_addch(&base, ':'); } - init_tree_desc(&tree, data, size); + init_tree_desc(&tree, &obj->oid, data, size); hit = grep_tree(opt, pathspec, &tree, &base, base.len, obj->type == OBJ_COMMIT); strbuf_release(&base); diff --git a/builtin/merge.c b/builtin/merge.c index de68910177..718165d459 100644 --- a/builtin/merge.c +++ b/builtin/merge.c @@ -704,7 +704,8 @@ static int read_tree_trivial(struct object_id *common, struct object_id *head, cache_tree_free(&the_index.cache_tree); for (i = 0; i < nr_trees; i++) { parse_tree(trees[i]); - init_tree_desc(t+i, trees[i]->buffer, trees[i]->size); + init_tree_desc(t+i, &trees[i]->object.oid, + trees[i]->buffer, trees[i]->size); } if (unpack_trees(nr_trees, t, &opts)) return -1; diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c index d2a162d528..d349020026 100644 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@ -1756,7 +1756,8 @@ static void add_pbase_object(struct tree_desc *tree, tree = pbase_tree_get(&entry.oid); if (!tree) return; - init_tree_desc(&sub, tree->tree_data, tree->tree_size); + init_tree_desc(&sub, &tree->oid, + tree->tree_data, tree->tree_size); add_pbase_object(&sub, down, downlen, fullname); pbase_tree_put(tree); @@ -1816,7 +1817,8 @@ static void add_preferred_base_object(const char *name) } else { struct tree_desc tree; - init_tree_desc(&tree, it->pcache.tree_data, it->pcache.tree_size); + init_tree_desc(&tree, &it->pcache.oid, + it->pcache.tree_data, it->pcache.tree_size); add_pbase_object(&tree, name, cmplen, name); } } diff --git a/builtin/read-tree.c b/builtin/read-tree.c index 1fec702a04..24d6d156d3 100644 --- a/builtin/read-tree.c +++ b/builtin/read-tree.c @@ -264,7 +264,7 @@ int cmd_read_tree(int argc, const char **argv, const char *cmd_prefix) for (i = 0; i < nr_trees; i++) { struct tree *tree = trees[i]; parse_tree(tree); - init_tree_desc(t+i, tree->buffer, tree->size); + init_tree_desc(t+i, &tree->object.oid, tree->buffer, tree->size); } if (unpack_trees(nr_trees, t, &opts)) return 128; diff --git a/builtin/stash.c b/builtin/stash.c index fe64cde9ce..9ee52af4d2 100644 --- a/builtin/stash.c +++ b/builtin/stash.c @@ -285,7 +285,7 @@ static int reset_tree(struct object_id *i_tree, int update, int reset) if (parse_tree(tree)) return -1; - init_tree_desc(t, tree->buffer, tree->size); + init_tree_desc(t, &tree->object.oid, tree->buffer, tree->size); opts.head_idx = 1; opts.src_index = &the_index; @@ -871,7 +871,8 @@ static void diff_include_untracked(const struct stash_info *info, struct diff_op tree[i] = parse_tree_indirect(oid[i]); if (parse_tree(tree[i]) < 0) die(_("failed to parse tree")); - init_tree_desc(&tree_desc[i], tree[i]->buffer, tree[i]->size); + init_tree_desc(&tree_desc[i], &tree[i]->object.oid, + tree[i]->buffer, tree[i]->size); } unpack_tree_opt.head_idx = -1; diff --git a/cache-tree.c b/cache-tree.c index ddc7d3d869..334973a01c 100644 --- a/cache-tree.c +++ b/cache-tree.c @@ -770,7 +770,7 @@ static void prime_cache_tree_rec(struct repository *r, oidcpy(&it->oid, &tree->object.oid); - init_tree_desc(&desc, tree->buffer, tree->size); + init_tree_desc(&desc, &tree->object.oid, tree->buffer, tree->size); cnt = 0; while (tree_entry(&desc, &entry)) { if (!S_ISDIR(entry.mode)) diff --git a/delta-islands.c b/delta-islands.c index 5de5759f3f..1ff3506b10 100644 --- a/delta-islands.c +++ b/delta-islands.c @@ -289,7 +289,7 @@ void resolve_tree_islands(struct repository *r, if (!tree || parse_tree(tree) < 0) die(_("bad tree object %s"), oid_to_hex(&ent->idx.oid)); - init_tree_desc(&desc, tree->buffer, tree->size); + init_tree_desc(&desc, &tree->object.oid, tree->buffer, tree->size); while (tree_entry(&desc, &entry)) { struct object *obj; diff --git a/diff-lib.c b/diff-lib.c index 6b0c6a7180..add323f562 100644 --- a/diff-lib.c +++ b/diff-lib.c @@ -558,7 +558,7 @@ static int diff_cache(struct rev_info *revs, opts.pathspec = &revs->diffopt.pathspec; opts.pathspec->recursive = 1; - init_tree_desc(&t, tree->buffer, tree->size); + init_tree_desc(&t, &tree->object.oid, tree->buffer, tree->size); return unpack_trees(1, &t, &opts); } diff --git a/fsck.c b/fsck.c index 2b1e348005..6b492a48da 100644 --- a/fsck.c +++ b/fsck.c @@ -313,7 +313,8 @@ static int fsck_walk_tree(struct tree *tree, void *data, struct fsck_options *op return -1; name = fsck_get_object_name(options, &tree->object.oid); - if (init_tree_desc_gently(&desc, tree->buffer, tree->size, 0)) + if (init_tree_desc_gently(&desc, &tree->object.oid, + tree->buffer, tree->size, 0)) return -1; while (tree_entry_gently(&desc, &entry)) { struct object *obj; @@ -583,7 +584,8 @@ static int fsck_tree(const struct object_id *tree_oid, const char *o_name; struct name_stack df_dup_candidates = { NULL }; - if (init_tree_desc_gently(&desc, buffer, size, TREE_DESC_RAW_MODES)) { + if (init_tree_desc_gently(&desc, tree_oid, buffer, size, + TREE_DESC_RAW_MODES)) { retval += report(options, tree_oid, OBJ_TREE, FSCK_MSG_BAD_TREE, "cannot be parsed as a tree"); diff --git a/http-push.c b/http-push.c index a704f490fd..81c35b5e96 100644 --- a/http-push.c +++ b/http-push.c @@ -1308,7 +1308,7 @@ static struct object_list **process_tree(struct tree *tree, obj->flags |= SEEN; p = add_one_object(obj, p); - init_tree_desc(&desc, tree->buffer, tree->size); + init_tree_desc(&desc, &tree->object.oid, tree->buffer, tree->size); while (tree_entry(&desc, &entry)) switch (object_type(entry.mode)) { diff --git a/list-objects.c b/list-objects.c index e60a6cd5b4..312335c8a7 100644 --- a/list-objects.c +++ b/list-objects.c @@ -97,7 +97,7 @@ static void process_tree_contents(struct traversal_context *ctx, enum interesting match = ctx->revs->diffopt.pathspec.nr == 0 ? all_entries_interesting : entry_not_interesting; - init_tree_desc(&desc, tree->buffer, tree->size); + init_tree_desc(&desc, &tree->object.oid, tree->buffer, tree->size); while (tree_entry(&desc, &entry)) { if (match != all_entries_interesting) { diff --git a/match-trees.c b/match-trees.c index 0885ac681c..3412b6a140 100644 --- a/match-trees.c +++ b/match-trees.c @@ -63,7 +63,7 @@ static void *fill_tree_desc_strict(struct tree_desc *desc, die("unable to read tree (%s)", oid_to_hex(hash)); if (type != OBJ_TREE) die("%s is not a tree", oid_to_hex(hash)); - init_tree_desc(desc, buffer, size); + init_tree_desc(desc, hash, buffer, size); return buffer; } @@ -194,7 +194,7 @@ static int splice_tree(const struct object_id *oid1, const char *prefix, buf = repo_read_object_file(the_repository, oid1, &type, &sz); if (!buf) die("cannot read tree %s", oid_to_hex(oid1)); - init_tree_desc(&desc, buf, sz); + init_tree_desc(&desc, oid1, buf, sz); rewrite_here = NULL; while (desc.size) { diff --git a/merge-ort.c b/merge-ort.c index 8631c99700..3a5729c91e 100644 --- a/merge-ort.c +++ b/merge-ort.c @@ -1679,9 +1679,10 @@ static int collect_merge_info(struct merge_options *opt, parse_tree(merge_base); parse_tree(side1); parse_tree(side2); - init_tree_desc(t + 0, merge_base->buffer, merge_base->size); - init_tree_desc(t + 1, side1->buffer, side1->size); - init_tree_desc(t + 2, side2->buffer, side2->size); + init_tree_desc(t + 0, &merge_base->object.oid, + merge_base->buffer, merge_base->size); + init_tree_desc(t + 1, &side1->object.oid, side1->buffer, side1->size); + init_tree_desc(t + 2, &side2->object.oid, side2->buffer, side2->size); trace2_region_enter("merge", "traverse_trees", opt->repo); ret = traverse_trees(NULL, 3, t, &info); @@ -4400,9 +4401,9 @@ static int checkout(struct merge_options *opt, unpack_opts.fn = twoway_merge; unpack_opts.preserve_ignored = 0; /* FIXME: !opts->overwrite_ignore */ parse_tree(prev); - init_tree_desc(&trees[0], prev->buffer, prev->size); + init_tree_desc(&trees[0], &prev->object.oid, prev->buffer, prev->size); parse_tree(next); - init_tree_desc(&trees[1], next->buffer, next->size); + init_tree_desc(&trees[1], &next->object.oid, next->buffer, next->size); ret = unpack_trees(2, trees, &unpack_opts); clear_unpack_trees_porcelain(&unpack_opts); diff --git a/merge-recursive.c b/merge-recursive.c index 6a4081bb0f..93df9eecdd 100644 --- a/merge-recursive.c +++ b/merge-recursive.c @@ -411,7 +411,7 @@ static inline int merge_detect_rename(struct merge_options *opt) static void init_tree_desc_from_tree(struct tree_desc *desc, struct tree *tree) { parse_tree(tree); - init_tree_desc(desc, tree->buffer, tree->size); + init_tree_desc(desc, &tree->object.oid, tree->buffer, tree->size); } static int unpack_trees_start(struct merge_options *opt, diff --git a/merge.c b/merge.c index b60925459c..86179c3410 100644 --- a/merge.c +++ b/merge.c @@ -81,7 +81,8 @@ int checkout_fast_forward(struct repository *r, } for (i = 0; i < nr_trees; i++) { parse_tree(trees[i]); - init_tree_desc(t+i, trees[i]->buffer, trees[i]->size); + init_tree_desc(t+i, &trees[i]->object.oid, + trees[i]->buffer, trees[i]->size); } memset(&opts, 0, sizeof(opts)); diff --git a/pack-bitmap-write.c b/pack-bitmap-write.c index f6757c3cbf..9211e08f01 100644 --- a/pack-bitmap-write.c +++ b/pack-bitmap-write.c @@ -366,7 +366,7 @@ static int fill_bitmap_tree(struct bitmap *bitmap, if (parse_tree(tree) < 0) die("unable to load tree object %s", oid_to_hex(&tree->object.oid)); - init_tree_desc(&desc, tree->buffer, tree->size); + init_tree_desc(&desc, &tree->object.oid, tree->buffer, tree->size); while (tree_entry(&desc, &entry)) { switch (object_type(entry.mode)) { diff --git a/packfile.c b/packfile.c index 9cc0a2e37a..1fae0fcdd9 100644 --- a/packfile.c +++ b/packfile.c @@ -2250,7 +2250,8 @@ static int add_promisor_object(const struct object_id *oid, struct tree *tree = (struct tree *)obj; struct tree_desc desc; struct name_entry entry; - if (init_tree_desc_gently(&desc, tree->buffer, tree->size, 0)) + if (init_tree_desc_gently(&desc, &tree->object.oid, + tree->buffer, tree->size, 0)) /* * Error messages are given when packs are * verified, so do not print any here. diff --git a/reflog.c b/reflog.c index 9ad50e7d93..c6992a1926 100644 --- a/reflog.c +++ b/reflog.c @@ -40,7 +40,7 @@ static int tree_is_complete(const struct object_id *oid) tree->buffer = data; tree->size = size; } - init_tree_desc(&desc, tree->buffer, tree->size); + init_tree_desc(&desc, &tree->object.oid, tree->buffer, tree->size); complete = 1; while (tree_entry(&desc, &entry)) { if (!repo_has_object_file(the_repository, &entry.oid) || diff --git a/revision.c b/revision.c index 2f4c53ea20..a60dfc23a2 100644 --- a/revision.c +++ b/revision.c @@ -82,7 +82,7 @@ static void mark_tree_contents_uninteresting(struct repository *r, if (parse_tree_gently(tree, 1) < 0) return; - init_tree_desc(&desc, tree->buffer, tree->size); + init_tree_desc(&desc, &tree->object.oid, tree->buffer, tree->size); while (tree_entry(&desc, &entry)) { switch (object_type(entry.mode)) { case OBJ_TREE: @@ -189,7 +189,7 @@ static void add_children_by_path(struct repository *r, if (parse_tree_gently(tree, 1) < 0) return; - init_tree_desc(&desc, tree->buffer, tree->size); + init_tree_desc(&desc, &tree->object.oid, tree->buffer, tree->size); while (tree_entry(&desc, &entry)) { switch (object_type(entry.mode)) { case OBJ_TREE: diff --git a/tree-walk.c b/tree-walk.c index 3af50a01c2..0b44ec7c75 100644 --- a/tree-walk.c +++ b/tree-walk.c @@ -15,7 +15,7 @@ static int decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned l const char *path; unsigned int len; uint16_t mode; - const unsigned hashsz = the_hash_algo->rawsz; + const unsigned hashsz = desc->algo->rawsz; if (size < hashsz + 3 || buf[size - (hashsz + 1)]) { strbuf_addstr(err, _("too-short tree object")); @@ -37,15 +37,19 @@ static int decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned l desc->entry.path = path; desc->entry.mode = (desc->flags & TREE_DESC_RAW_MODES) ? mode : canon_mode(mode); desc->entry.pathlen = len - 1; - oidread(&desc->entry.oid, (const unsigned char *)path + len); + oidread_algop(&desc->entry.oid, (const unsigned char *)path + len, + desc->algo); return 0; } -static int init_tree_desc_internal(struct tree_desc *desc, const void *buffer, - unsigned long size, struct strbuf *err, +static int init_tree_desc_internal(struct tree_desc *desc, + const struct object_id *oid, + const void *buffer, unsigned long size, + struct strbuf *err, enum tree_desc_flags flags) { + desc->algo = (oid && oid->algo) ? &hash_algos[oid->algo] : the_hash_algo; desc->buffer = buffer; desc->size = size; desc->flags = flags; @@ -54,19 +58,21 @@ static int init_tree_desc_internal(struct tree_desc *desc, const void *buffer, return 0; } -void init_tree_desc(struct tree_desc *desc, const void *buffer, unsigned long size) +void init_tree_desc(struct tree_desc *desc, const struct object_id *tree_oid, + const void *buffer, unsigned long size) { struct strbuf err = STRBUF_INIT; - if (init_tree_desc_internal(desc, buffer, size, &err, 0)) + if (init_tree_desc_internal(desc, tree_oid, buffer, size, &err, 0)) die("%s", err.buf); strbuf_release(&err); } -int init_tree_desc_gently(struct tree_desc *desc, const void *buffer, unsigned long size, +int init_tree_desc_gently(struct tree_desc *desc, const struct object_id *oid, + const void *buffer, unsigned long size, enum tree_desc_flags flags) { struct strbuf err = STRBUF_INIT; - int result = init_tree_desc_internal(desc, buffer, size, &err, flags); + int result = init_tree_desc_internal(desc, oid, buffer, size, &err, flags); if (result) error("%s", err.buf); strbuf_release(&err); @@ -85,7 +91,7 @@ void *fill_tree_descriptor(struct repository *r, if (!buf) die("unable to read tree %s", oid_to_hex(oid)); } - init_tree_desc(desc, buf, size); + init_tree_desc(desc, oid, buf, size); return buf; } @@ -102,7 +108,7 @@ static void entry_extract(struct tree_desc *t, struct name_entry *a) static int update_tree_entry_internal(struct tree_desc *desc, struct strbuf *err) { const void *buf = desc->buffer; - const unsigned char *end = (const unsigned char *)desc->entry.path + desc->entry.pathlen + 1 + the_hash_algo->rawsz; + const unsigned char *end = (const unsigned char *)desc->entry.path + desc->entry.pathlen + 1 + desc->algo->rawsz; unsigned long size = desc->size; unsigned long len = end - (const unsigned char *)buf; @@ -611,7 +617,7 @@ int get_tree_entry(struct repository *r, retval = -1; } else { struct tree_desc t; - init_tree_desc(&t, tree, size); + init_tree_desc(&t, tree_oid, tree, size); retval = find_tree_entry(r, &t, name, oid, mode); } free(tree); @@ -654,7 +660,7 @@ enum get_oid_result get_tree_entry_follow_symlinks(struct repository *r, struct tree_desc t; int follows_remaining = GET_TREE_ENTRY_FOLLOW_SYMLINKS_MAX_LINKS; - init_tree_desc(&t, NULL, 0UL); + init_tree_desc(&t, NULL, NULL, 0UL); strbuf_addstr(&namebuf, name); oidcpy(¤t_tree_oid, tree_oid); @@ -690,7 +696,7 @@ enum get_oid_result get_tree_entry_follow_symlinks(struct repository *r, goto done; /* descend */ - init_tree_desc(&t, tree, size); + init_tree_desc(&t, ¤t_tree_oid, tree, size); } /* Handle symlinks to e.g. a//b by removing leading slashes */ @@ -724,7 +730,7 @@ enum get_oid_result get_tree_entry_follow_symlinks(struct repository *r, free(parent->tree); parents_nr--; parent = &parents[parents_nr - 1]; - init_tree_desc(&t, parent->tree, parent->size); + init_tree_desc(&t, &parent->oid, parent->tree, parent->size); strbuf_remove(&namebuf, 0, remainder ? 3 : 2); continue; } @@ -804,7 +810,7 @@ enum get_oid_result get_tree_entry_follow_symlinks(struct repository *r, contents_start = contents; parent = &parents[parents_nr - 1]; - init_tree_desc(&t, parent->tree, parent->size); + init_tree_desc(&t, &parent->oid, parent->tree, parent->size); strbuf_splice(&namebuf, 0, len, contents_start, link_len); if (remainder) diff --git a/tree-walk.h b/tree-walk.h index 74cdceb3fe..cf54d01019 100644 --- a/tree-walk.h +++ b/tree-walk.h @@ -26,6 +26,7 @@ struct name_entry { * A semi-opaque data structure used to maintain the current state of the walk. */ struct tree_desc { + const struct git_hash_algo *algo; /* * pointer into the memory representation of the tree. It always * points at the current entry being visited. @@ -85,9 +86,11 @@ int update_tree_entry_gently(struct tree_desc *); * size parameters are assumed to be the same as the buffer and size * members of `struct tree`. */ -void init_tree_desc(struct tree_desc *desc, const void *buf, unsigned long size); +void init_tree_desc(struct tree_desc *desc, const struct object_id *tree_oid, + const void *buf, unsigned long size); -int init_tree_desc_gently(struct tree_desc *desc, const void *buf, unsigned long size, +int init_tree_desc_gently(struct tree_desc *desc, const struct object_id *oid, + const void *buf, unsigned long size, enum tree_desc_flags flags); /* diff --git a/tree.c b/tree.c index c745462f96..44bcf728f1 100644 --- a/tree.c +++ b/tree.c @@ -27,7 +27,7 @@ int read_tree_at(struct repository *r, if (parse_tree(tree)) return -1; - init_tree_desc(&desc, tree->buffer, tree->size); + init_tree_desc(&desc, &tree->object.oid, tree->buffer, tree->size); while (tree_entry(&desc, &entry)) { if (retval != all_entries_interesting) { diff --git a/walker.c b/walker.c index 65002a7220..c0fd632d92 100644 --- a/walker.c +++ b/walker.c @@ -45,7 +45,7 @@ static int process_tree(struct walker *walker, struct tree *tree) if (parse_tree(tree)) return -1; - init_tree_desc(&desc, tree->buffer, tree->size); + init_tree_desc(&desc, &tree->object.oid, tree->buffer, tree->size); while (tree_entry(&desc, &entry)) { struct object *obj = NULL; From 8d691757b8fcbe9b7898a5d1dcb37b198a8c60e1 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 1 Oct 2023 21:40:29 -0500 Subject: [PATCH 25/30] object-file: handle compat objects in check_object_signature Update check_object_signature to find the hash algorithm the exising signature uses, and to use the same hash algorithm when recomputing it to check the signature is valid. This will be useful when teaching git ls-tree to display objects encoded with the compat hash algorithm. Signed-off-by: "Eric W. Biederman" Signed-off-by: Junio C Hamano --- object-file.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/object-file.c b/object-file.c index b2d43d0098..5fa4b14bae 100644 --- a/object-file.c +++ b/object-file.c @@ -1094,9 +1094,11 @@ int check_object_signature(struct repository *r, const struct object_id *oid, void *buf, unsigned long size, enum object_type type) { + const struct git_hash_algo *algo = + oid->algo ? &hash_algos[oid->algo] : r->hash_algo; struct object_id real_oid; - hash_object_file(r->hash_algo, buf, size, type, &real_oid); + hash_object_file(algo, buf, size, type, &real_oid); return !oideq(oid, &real_oid) ? -1 : 0; } From c68be1fd31328472d994857e66c376dfc4562964 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 1 Oct 2023 21:40:30 -0500 Subject: [PATCH 26/30] builtin/ls-tree: let the oid determine the output algorithm Update cmd_ls_tree to call get_oid_with_context and pass GET_OID_HASH_ANY instead of calling the simpler repo_get_oid. This implments in ls-tree the behavior that asking to display a sha1 hash displays the corrresponding sha1 encoded object and asking to display a sha256 hash displayes the corresponding sha256 encoded object. This is useful for testing the conversion of an object to an equivlanet object encoded with a different hash function. Signed-off-by: "Eric W. Biederman" Signed-off-by: Junio C Hamano --- builtin/ls-tree.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/builtin/ls-tree.c b/builtin/ls-tree.c index f558db5f3b..71281ab705 100644 --- a/builtin/ls-tree.c +++ b/builtin/ls-tree.c @@ -376,6 +376,7 @@ int cmd_ls_tree(int argc, const char **argv, const char *prefix) OPT_END() }; struct ls_tree_cmdmode_to_fmt *m2f = ls_tree_cmdmode_format; + struct object_context obj_context; int ret; git_config(git_default_config, NULL); @@ -407,7 +408,9 @@ int cmd_ls_tree(int argc, const char **argv, const char *prefix) ls_tree_usage, ls_tree_options); if (argc < 1) usage_with_options(ls_tree_usage, ls_tree_options); - if (repo_get_oid(the_repository, argv[0], &oid)) + if (get_oid_with_context(the_repository, argv[0], + GET_OID_HASH_ANY, &oid, + &obj_context)) die("Not a valid object name %s", argv[0]); /* From 48b16ab231bc20ad86dc94bcf64647a83d374a2b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 1 Oct 2023 21:40:31 -0500 Subject: [PATCH 27/30] test-lib: compute the compatibility hash so tests may use it Inspired-by: brian m. carlson Signed-off-by: "Eric W. Biederman" Signed-off-by: Junio C Hamano --- t/test-lib-functions.sh | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/t/test-lib-functions.sh b/t/test-lib-functions.sh index 2f8868caa1..92b462e2e7 100644 --- a/t/test-lib-functions.sh +++ b/t/test-lib-functions.sh @@ -1599,7 +1599,16 @@ test_set_hash () { # Detect the hash algorithm in use. test_detect_hash () { - test_hash_algo="${GIT_TEST_DEFAULT_HASH:-sha1}" + case "$GIT_TEST_DEFAULT_HASH" in + "sha256") + test_hash_algo=sha256 + test_compat_hash_algo=sha1 + ;; + *) + test_hash_algo=sha1 + test_compat_hash_algo=sha256 + ;; + esac } # Load common hash metadata and common placeholder object IDs for use with @@ -1651,6 +1660,12 @@ test_oid () { local algo="${test_hash_algo}" && case "$1" in + --hash=storage) + algo="$test_hash_algo" && + shift;; + --hash=compat) + algo="$test_compat_hash_algo" && + shift;; --hash=*) algo="${1#--hash=}" && shift;; From baab175c1d2f51bb02a1af5afd1fe2daffed0f75 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 1 Oct 2023 21:40:32 -0500 Subject: [PATCH 28/30] t1006: rename sha1 to oid Before I extend this test, changing the naming of the relevant hash from sha1 to oid. Calling the hash sha1 is incorrect today as it can be either sha1 or sha256 depending on the value of GIT_DEFAULT_HASH_FUNCTION when the test is called. I plan to test sha1 and sha256 simultaneously in the same repository. Having a name like sha1 will be even more confusing. Signed-off-by: "Eric W. Biederman" Signed-off-by: Junio C Hamano --- t/t1006-cat-file.sh | 220 ++++++++++++++++++++++---------------------- 1 file changed, 110 insertions(+), 110 deletions(-) diff --git a/t/t1006-cat-file.sh b/t/t1006-cat-file.sh index d73a0be1b9..9b018b5389 100755 --- a/t/t1006-cat-file.sh +++ b/t/t1006-cat-file.sh @@ -112,65 +112,65 @@ strlen () { run_tests () { type=$1 - sha1=$2 + oid=$2 size=$3 content=$4 pretty_content=$5 - batch_output="$sha1 $type $size + batch_output="$oid $type $size $content" test_expect_success "$type exists" ' - git cat-file -e $sha1 + git cat-file -e $oid ' test_expect_success "Type of $type is correct" ' echo $type >expect && - git cat-file -t $sha1 >actual && + git cat-file -t $oid >actual && test_cmp expect actual ' test_expect_success "Size of $type is correct" ' echo $size >expect && - git cat-file -s $sha1 >actual && + git cat-file -s $oid >actual && test_cmp expect actual ' test_expect_success "Type of $type is correct using --allow-unknown-type" ' echo $type >expect && - git cat-file -t --allow-unknown-type $sha1 >actual && + git cat-file -t --allow-unknown-type $oid >actual && test_cmp expect actual ' test_expect_success "Size of $type is correct using --allow-unknown-type" ' echo $size >expect && - git cat-file -s --allow-unknown-type $sha1 >actual && + git cat-file -s --allow-unknown-type $oid >actual && test_cmp expect actual ' test -z "$content" || test_expect_success "Content of $type is correct" ' echo_without_newline "$content" >expect && - git cat-file $type $sha1 >actual && + git cat-file $type $oid >actual && test_cmp expect actual ' test_expect_success "Pretty content of $type is correct" ' echo_without_newline "$pretty_content" >expect && - git cat-file -p $sha1 >actual && + git cat-file -p $oid >actual && test_cmp expect actual ' test -z "$content" || test_expect_success "--batch output of $type is correct" ' echo "$batch_output" >expect && - echo $sha1 | git cat-file --batch >actual && + echo $oid | git cat-file --batch >actual && test_cmp expect actual ' test_expect_success "--batch-check output of $type is correct" ' - echo "$sha1 $type $size" >expect && - echo_without_newline $sha1 | git cat-file --batch-check >actual && + echo "$oid $type $size" >expect && + echo_without_newline $oid | git cat-file --batch-check >actual && test_cmp expect actual ' @@ -179,33 +179,33 @@ $content" test -z "$content" || test_expect_success "--batch-command $opt output of $type content is correct" ' echo "$batch_output" >expect && - test_write_lines "contents $sha1" | git cat-file --batch-command $opt >actual && + test_write_lines "contents $oid" | git cat-file --batch-command $opt >actual && test_cmp expect actual ' test_expect_success "--batch-command $opt output of $type info is correct" ' - echo "$sha1 $type $size" >expect && - test_write_lines "info $sha1" | + echo "$oid $type $size" >expect && + test_write_lines "info $oid" | git cat-file --batch-command $opt >actual && test_cmp expect actual ' done test_expect_success "custom --batch-check format" ' - echo "$type $sha1" >expect && - echo $sha1 | git cat-file --batch-check="%(objecttype) %(objectname)" >actual && + echo "$type $oid" >expect && + echo $oid | git cat-file --batch-check="%(objecttype) %(objectname)" >actual && test_cmp expect actual ' test_expect_success "custom --batch-command format" ' - echo "$type $sha1" >expect && - echo "info $sha1" | git cat-file --batch-command="%(objecttype) %(objectname)" >actual && + echo "$type $oid" >expect && + echo "info $oid" | git cat-file --batch-command="%(objecttype) %(objectname)" >actual && test_cmp expect actual ' test_expect_success '--batch-check with %(rest)' ' echo "$type this is some extra content" >expect && - echo "$sha1 this is some extra content" | + echo "$oid this is some extra content" | git cat-file --batch-check="%(objecttype) %(rest)" >actual && test_cmp expect actual ' @@ -216,7 +216,7 @@ $content" echo "$size" && echo "$content" } >expect && - echo $sha1 | git cat-file --batch="%(objectsize)" >actual && + echo $oid | git cat-file --batch="%(objectsize)" >actual && test_cmp expect actual ' @@ -226,25 +226,25 @@ $content" echo "$type" && echo "$content" } >expect && - echo $sha1 | git cat-file --batch="%(objecttype)" >actual && + echo $oid | git cat-file --batch="%(objecttype)" >actual && test_cmp expect actual ' } hello_content="Hello World" hello_size=$(strlen "$hello_content") -hello_sha1=$(echo_without_newline "$hello_content" | git hash-object --stdin) +hello_oid=$(echo_without_newline "$hello_content" | git hash-object --stdin) test_expect_success "setup" ' echo_without_newline "$hello_content" > hello && git update-index --add hello ' -run_tests 'blob' $hello_sha1 $hello_size "$hello_content" "$hello_content" +run_tests 'blob' $hello_oid $hello_size "$hello_content" "$hello_content" test_expect_success '--batch-command --buffer with flush for blob info' ' - echo "$hello_sha1 blob $hello_size" >expect && - test_write_lines "info $hello_sha1" "flush" | + echo "$hello_oid blob $hello_size" >expect && + test_write_lines "info $hello_oid" "flush" | GIT_TEST_CAT_FILE_NO_FLUSH_ON_EXIT=1 \ git cat-file --batch-command --buffer >actual && test_cmp expect actual @@ -252,38 +252,38 @@ test_expect_success '--batch-command --buffer with flush for blob info' ' test_expect_success '--batch-command --buffer without flush for blob info' ' touch output && - test_write_lines "info $hello_sha1" | + test_write_lines "info $hello_oid" | GIT_TEST_CAT_FILE_NO_FLUSH_ON_EXIT=1 \ git cat-file --batch-command --buffer >>output && test_must_be_empty output ' test_expect_success '--batch-check without %(rest) considers whole line' ' - echo "$hello_sha1 blob $hello_size" >expect && - git update-index --add --cacheinfo 100644 $hello_sha1 "white space" && + echo "$hello_oid blob $hello_size" >expect && + git update-index --add --cacheinfo 100644 $hello_oid "white space" && test_when_finished "git update-index --remove \"white space\"" && echo ":white space" | git cat-file --batch-check >actual && test_cmp expect actual ' -tree_sha1=$(git write-tree) +tree_oid=$(git write-tree) tree_size=$(($(test_oid rawsz) + 13)) -tree_pretty_content="100644 blob $hello_sha1 hello${LF}" +tree_pretty_content="100644 blob $hello_oid hello${LF}" -run_tests 'tree' $tree_sha1 $tree_size "" "$tree_pretty_content" +run_tests 'tree' $tree_oid $tree_size "" "$tree_pretty_content" commit_message="Initial commit" -commit_sha1=$(echo_without_newline "$commit_message" | git commit-tree $tree_sha1) +commit_oid=$(echo_without_newline "$commit_message" | git commit-tree $tree_oid) commit_size=$(($(test_oid hexsz) + 137)) -commit_content="tree $tree_sha1 +commit_content="tree $tree_oid author $GIT_AUTHOR_NAME <$GIT_AUTHOR_EMAIL> $GIT_AUTHOR_DATE committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE $commit_message" -run_tests 'commit' $commit_sha1 $commit_size "$commit_content" "$commit_content" +run_tests 'commit' $commit_oid $commit_size "$commit_content" "$commit_content" -tag_header_without_timestamp="object $hello_sha1 +tag_header_without_timestamp="object $hello_oid type blob tag hellotag tagger $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL>" @@ -292,14 +292,14 @@ tag_content="$tag_header_without_timestamp 0 +0000 $tag_description" -tag_sha1=$(echo_without_newline "$tag_content" | git hash-object -t tag --stdin -w) +tag_oid=$(echo_without_newline "$tag_content" | git hash-object -t tag --stdin -w) tag_size=$(strlen "$tag_content") -run_tests 'tag' $tag_sha1 $tag_size "$tag_content" "$tag_content" +run_tests 'tag' $tag_oid $tag_size "$tag_content" "$tag_content" test_expect_success "Reach a blob from a tag pointing to it" ' echo_without_newline "$hello_content" >expect && - git cat-file blob $tag_sha1 >actual && + git cat-file blob $tag_oid >actual && test_cmp expect actual ' @@ -308,31 +308,31 @@ do for opt in t s e p do test_expect_success "Passing -$opt with --$batch fails" ' - test_must_fail git cat-file --$batch -$opt $hello_sha1 + test_must_fail git cat-file --$batch -$opt $hello_oid ' test_expect_success "Passing --$batch with -$opt fails" ' - test_must_fail git cat-file -$opt --$batch $hello_sha1 + test_must_fail git cat-file -$opt --$batch $hello_oid ' done test_expect_success "Passing with --$batch fails" ' - test_must_fail git cat-file --$batch blob $hello_sha1 + test_must_fail git cat-file --$batch blob $hello_oid ' test_expect_success "Passing --$batch with fails" ' - test_must_fail git cat-file blob --$batch $hello_sha1 + test_must_fail git cat-file blob --$batch $hello_oid ' - test_expect_success "Passing sha1 with --$batch fails" ' - test_must_fail git cat-file --$batch $hello_sha1 + test_expect_success "Passing oid with --$batch fails" ' + test_must_fail git cat-file --$batch $hello_oid ' done for opt in t s e p do test_expect_success "Passing -$opt with --follow-symlinks fails" ' - test_must_fail git cat-file --follow-symlinks -$opt $hello_sha1 + test_must_fail git cat-file --follow-symlinks -$opt $hello_oid ' done @@ -360,12 +360,12 @@ test_expect_success "--batch-check for a non-existent hash" ' test_expect_success "--batch for an existent and a non-existent hash" ' cat >expect <<-EOF && - $tag_sha1 tag $tag_size + $tag_oid tag $tag_size $tag_content 0000000000000000000000000000000000000000 missing EOF - printf "$tag_sha1\n0000000000000000000000000000000000000000" >in && + printf "$tag_oid\n0000000000000000000000000000000000000000" >in && git cat-file --batch actual && test_cmp expect actual ' @@ -386,74 +386,74 @@ test_expect_success 'empty --batch-check notices missing object' ' test_cmp expect actual ' -batch_input="$hello_sha1 -$commit_sha1 -$tag_sha1 +batch_input="$hello_oid +$commit_oid +$tag_oid deadbeef " printf "%s\0" \ - "$hello_sha1 blob $hello_size" \ + "$hello_oid blob $hello_size" \ "$hello_content" \ - "$commit_sha1 commit $commit_size" \ + "$commit_oid commit $commit_size" \ "$commit_content" \ - "$tag_sha1 tag $tag_size" \ + "$tag_oid tag $tag_size" \ "$tag_content" \ "deadbeef missing" \ " missing" >batch_output -test_expect_success '--batch with multiple sha1s gives correct format' ' +test_expect_success '--batch with multiple oids gives correct format' ' tr "\0" "\n" expect && echo_without_newline "$batch_input" >in && git cat-file --batch actual && test_cmp expect actual ' -test_expect_success '--batch, -z with multiple sha1s gives correct format' ' +test_expect_success '--batch, -z with multiple oids gives correct format' ' echo_without_newline_nul "$batch_input" >in && tr "\0" "\n" expect && git cat-file --batch -z actual && test_cmp expect actual ' -test_expect_success '--batch, -Z with multiple sha1s gives correct format' ' +test_expect_success '--batch, -Z with multiple oids gives correct format' ' echo_without_newline_nul "$batch_input" >in && git cat-file --batch -Z actual && test_cmp batch_output actual ' -batch_check_input="$hello_sha1 -$tree_sha1 -$commit_sha1 -$tag_sha1 +batch_check_input="$hello_oid +$tree_oid +$commit_oid +$tag_oid deadbeef " printf "%s\0" \ - "$hello_sha1 blob $hello_size" \ - "$tree_sha1 tree $tree_size" \ - "$commit_sha1 commit $commit_size" \ - "$tag_sha1 tag $tag_size" \ + "$hello_oid blob $hello_size" \ + "$tree_oid tree $tree_size" \ + "$commit_oid commit $commit_size" \ + "$tag_oid tag $tag_size" \ "deadbeef missing" \ " missing" >batch_check_output -test_expect_success "--batch-check with multiple sha1s gives correct format" ' +test_expect_success "--batch-check with multiple oids gives correct format" ' tr "\0" "\n" expect && echo_without_newline "$batch_check_input" >in && git cat-file --batch-check actual && test_cmp expect actual ' -test_expect_success "--batch-check, -z with multiple sha1s gives correct format" ' +test_expect_success "--batch-check, -z with multiple oids gives correct format" ' tr "\0" "\n" expect && echo_without_newline_nul "$batch_check_input" >in && git cat-file --batch-check -z actual && test_cmp expect actual ' -test_expect_success "--batch-check, -Z with multiple sha1s gives correct format" ' +test_expect_success "--batch-check, -Z with multiple oids gives correct format" ' echo_without_newline_nul "$batch_check_input" >in && git cat-file --batch-check -Z actual && test_cmp batch_check_output actual @@ -480,18 +480,18 @@ test_expect_success FUNNYNAMES '--batch-check, -Z with newline in input' ' test_cmp expect actual ' -batch_command_multiple_info="info $hello_sha1 -info $tree_sha1 -info $commit_sha1 -info $tag_sha1 +batch_command_multiple_info="info $hello_oid +info $tree_oid +info $commit_oid +info $tag_oid info deadbeef" test_expect_success '--batch-command with multiple info calls gives correct format' ' cat >expect <<-EOF && - $hello_sha1 blob $hello_size - $tree_sha1 tree $tree_size - $commit_sha1 commit $commit_size - $tag_sha1 tag $tag_size + $hello_oid blob $hello_size + $tree_oid tree $tree_size + $commit_oid commit $commit_size + $tag_oid tag $tag_size deadbeef missing EOF @@ -512,19 +512,19 @@ test_expect_success '--batch-command with multiple info calls gives correct form test_cmp expect_nul actual ' -batch_command_multiple_contents="contents $hello_sha1 -contents $commit_sha1 -contents $tag_sha1 +batch_command_multiple_contents="contents $hello_oid +contents $commit_oid +contents $tag_oid contents deadbeef flush" test_expect_success '--batch-command with multiple command calls gives correct format' ' printf "%s\0" \ - "$hello_sha1 blob $hello_size" \ + "$hello_oid blob $hello_size" \ "$hello_content" \ - "$commit_sha1 commit $commit_size" \ + "$commit_oid commit $commit_size" \ "$commit_content" \ - "$tag_sha1 tag $tag_size" \ + "$tag_oid tag $tag_size" \ "$tag_content" \ "deadbeef missing" >expect_nul && tr "\0" "\n" expect && @@ -569,7 +569,7 @@ test_expect_success 'confirm that neither loose blob is a delta' ' # we will check only that one of the two objects is a delta # against the other, but not the order. We can do so by just # asking for the base of both, and checking whether either -# sha1 appears in the output. +# oid appears in the output. test_expect_success '%(deltabase) reports packed delta bases' ' git repack -ad && git cat-file --batch-check="%(deltabase)" actual && @@ -583,12 +583,12 @@ test_expect_success 'setup bogus data' ' bogus_short_type="bogus" && bogus_short_content="bogus" && bogus_short_size=$(strlen "$bogus_short_content") && - bogus_short_sha1=$(echo_without_newline "$bogus_short_content" | git hash-object -t $bogus_short_type --literally -w --stdin) && + bogus_short_oid=$(echo_without_newline "$bogus_short_content" | git hash-object -t $bogus_short_type --literally -w --stdin) && bogus_long_type="abcdefghijklmnopqrstuvwxyz1234679" && bogus_long_content="bogus" && bogus_long_size=$(strlen "$bogus_long_content") && - bogus_long_sha1=$(echo_without_newline "$bogus_long_content" | git hash-object -t $bogus_long_type --literally -w --stdin) + bogus_long_oid=$(echo_without_newline "$bogus_long_content" | git hash-object -t $bogus_long_type --literally -w --stdin) ' for arg1 in '' --allow-unknown-type @@ -608,9 +608,9 @@ do if test "$arg1" = "--allow-unknown-type" then - git cat-file $arg1 $arg2 $bogus_short_sha1 + git cat-file $arg1 $arg2 $bogus_short_oid else - test_must_fail git cat-file $arg1 $arg2 $bogus_short_sha1 >out 2>actual && + test_must_fail git cat-file $arg1 $arg2 $bogus_short_oid >out 2>actual && test_must_be_empty out && test_cmp expect actual fi @@ -620,21 +620,21 @@ do if test "$arg2" = "-p" then cat >expect <<-EOF - error: header for $bogus_long_sha1 too long, exceeds 32 bytes - fatal: Not a valid object name $bogus_long_sha1 + error: header for $bogus_long_oid too long, exceeds 32 bytes + fatal: Not a valid object name $bogus_long_oid EOF else cat >expect <<-EOF - error: header for $bogus_long_sha1 too long, exceeds 32 bytes + error: header for $bogus_long_oid too long, exceeds 32 bytes fatal: git cat-file: could not get object info EOF fi && if test "$arg1" = "--allow-unknown-type" then - git cat-file $arg1 $arg2 $bogus_short_sha1 + git cat-file $arg1 $arg2 $bogus_short_oid else - test_must_fail git cat-file $arg1 $arg2 $bogus_long_sha1 >out 2>actual && + test_must_fail git cat-file $arg1 $arg2 $bogus_long_oid >out 2>actual && test_must_be_empty out && test_cmp expect actual fi @@ -668,28 +668,28 @@ do done test_expect_success '-e is OK with a broken object without --allow-unknown-type' ' - git cat-file -e $bogus_short_sha1 + git cat-file -e $bogus_short_oid ' test_expect_success '-e can not be combined with --allow-unknown-type' ' - test_expect_code 128 git cat-file -e --allow-unknown-type $bogus_short_sha1 + test_expect_code 128 git cat-file -e --allow-unknown-type $bogus_short_oid ' test_expect_success '-p cannot print a broken object even with --allow-unknown-type' ' - test_must_fail git cat-file -p $bogus_short_sha1 && - test_expect_code 128 git cat-file -p --allow-unknown-type $bogus_short_sha1 + test_must_fail git cat-file -p $bogus_short_oid && + test_expect_code 128 git cat-file -p --allow-unknown-type $bogus_short_oid ' test_expect_success ' does not work with objects of broken types' ' cat >err.expect <<-\EOF && fatal: invalid object type "bogus" EOF - test_must_fail git cat-file $bogus_short_type $bogus_short_sha1 2>err.actual && + test_must_fail git cat-file $bogus_short_type $bogus_short_oid 2>err.actual && test_cmp err.expect err.actual ' test_expect_success 'broken types combined with --batch and --batch-check' ' - echo $bogus_short_sha1 >bogus-oid && + echo $bogus_short_oid >bogus-oid && cat >err.expect <<-\EOF && fatal: invalid object type @@ -711,52 +711,52 @@ test_expect_success 'the --allow-unknown-type option does not consider replaceme cat >expect <<-EOF && $bogus_short_type EOF - git cat-file -t --allow-unknown-type $bogus_short_sha1 >actual && + git cat-file -t --allow-unknown-type $bogus_short_oid >actual && test_cmp expect actual && # Create it manually, as "git replace" will die on bogus # types. head=$(git rev-parse --verify HEAD) && - test_when_finished "test-tool ref-store main delete-refs 0 msg refs/replace/$bogus_short_sha1" && - test-tool ref-store main update-ref msg "refs/replace/$bogus_short_sha1" $head $ZERO_OID REF_SKIP_OID_VERIFICATION && + test_when_finished "test-tool ref-store main delete-refs 0 msg refs/replace/$bogus_short_oid" && + test-tool ref-store main update-ref msg "refs/replace/$bogus_short_oid" $head $ZERO_OID REF_SKIP_OID_VERIFICATION && cat >expect <<-EOF && commit EOF - git cat-file -t --allow-unknown-type $bogus_short_sha1 >actual && + git cat-file -t --allow-unknown-type $bogus_short_oid >actual && test_cmp expect actual ' test_expect_success "Type of broken object is correct" ' echo $bogus_short_type >expect && - git cat-file -t --allow-unknown-type $bogus_short_sha1 >actual && + git cat-file -t --allow-unknown-type $bogus_short_oid >actual && test_cmp expect actual ' test_expect_success "Size of broken object is correct" ' echo $bogus_short_size >expect && - git cat-file -s --allow-unknown-type $bogus_short_sha1 >actual && + git cat-file -s --allow-unknown-type $bogus_short_oid >actual && test_cmp expect actual ' test_expect_success 'clean up broken object' ' - rm .git/objects/$(test_oid_to_path $bogus_short_sha1) + rm .git/objects/$(test_oid_to_path $bogus_short_oid) ' test_expect_success "Type of broken object is correct when type is large" ' echo $bogus_long_type >expect && - git cat-file -t --allow-unknown-type $bogus_long_sha1 >actual && + git cat-file -t --allow-unknown-type $bogus_long_oid >actual && test_cmp expect actual ' test_expect_success "Size of large broken object is correct when type is large" ' echo $bogus_long_size >expect && - git cat-file -s --allow-unknown-type $bogus_long_sha1 >actual && + git cat-file -s --allow-unknown-type $bogus_long_oid >actual && test_cmp expect actual ' test_expect_success 'clean up broken object' ' - rm .git/objects/$(test_oid_to_path $bogus_long_sha1) + rm .git/objects/$(test_oid_to_path $bogus_long_oid) ' test_expect_success 'cat-file -t and -s on corrupt loose object' ' @@ -853,7 +853,7 @@ test_expect_success 'prep for symlink tests' ' test_ln_s_add loop2 loop1 && git add morx dir/subdir/ind2 dir/ind1 && git commit -am "test" && - echo $hello_sha1 blob $hello_size >found + echo $hello_oid blob $hello_size >found ' test_expect_success 'git cat-file --batch-check --follow-symlinks works for non-links' ' @@ -941,7 +941,7 @@ test_expect_success 'git cat-file --batch-check --follow-symlinks works for dir/ echo HEAD:dirlink/morx >>expect && echo HEAD:dirlink/morx | git cat-file --batch-check --follow-symlinks >actual && test_cmp expect actual && - echo $hello_sha1 blob $hello_size >expect && + echo $hello_oid blob $hello_size >expect && echo HEAD:dirlink/ind1 | git cat-file --batch-check --follow-symlinks >actual && test_cmp expect actual ' From 3afa8d86accb01686a24c7859bee31370472ef56 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 1 Oct 2023 21:40:33 -0500 Subject: [PATCH 29/30] t1006: test oid compatibility with cat-file Update the existing tests that are oid based to test that cat-file works correctly with the normal oid and the compat_oid. Signed-off-by: "Eric W. Biederman" Signed-off-by: Junio C Hamano --- t/t1006-cat-file.sh | 307 ++++++++++++++++++++++++++------------------ 1 file changed, 182 insertions(+), 125 deletions(-) diff --git a/t/t1006-cat-file.sh b/t/t1006-cat-file.sh index 9b018b5389..23d3d37283 100755 --- a/t/t1006-cat-file.sh +++ b/t/t1006-cat-file.sh @@ -236,27 +236,38 @@ hello_size=$(strlen "$hello_content") hello_oid=$(echo_without_newline "$hello_content" | git hash-object --stdin) test_expect_success "setup" ' + git config core.repositoryformatversion 1 && + git config extensions.objectformat $test_hash_algo && + git config extensions.compatobjectformat $test_compat_hash_algo && echo_without_newline "$hello_content" > hello && git update-index --add hello ' -run_tests 'blob' $hello_oid $hello_size "$hello_content" "$hello_content" +run_blob_tests () { + oid=$1 -test_expect_success '--batch-command --buffer with flush for blob info' ' - echo "$hello_oid blob $hello_size" >expect && - test_write_lines "info $hello_oid" "flush" | + run_tests 'blob' $oid $hello_size "$hello_content" "$hello_content" + + test_expect_success '--batch-command --buffer with flush for blob info' ' + echo "$oid blob $hello_size" >expect && + test_write_lines "info $oid" "flush" | GIT_TEST_CAT_FILE_NO_FLUSH_ON_EXIT=1 \ git cat-file --batch-command --buffer >actual && test_cmp expect actual -' + ' -test_expect_success '--batch-command --buffer without flush for blob info' ' + test_expect_success '--batch-command --buffer without flush for blob info' ' touch output && - test_write_lines "info $hello_oid" | + test_write_lines "info $oid" | GIT_TEST_CAT_FILE_NO_FLUSH_ON_EXIT=1 \ git cat-file --batch-command --buffer >>output && test_must_be_empty output -' + ' +} + +hello_compat_oid=$(git rev-parse --output-object-format=$test_compat_hash_algo $hello_oid) +run_blob_tests $hello_oid +run_blob_tests $hello_compat_oid test_expect_success '--batch-check without %(rest) considers whole line' ' echo "$hello_oid blob $hello_size" >expect && @@ -267,35 +278,58 @@ test_expect_success '--batch-check without %(rest) considers whole line' ' ' tree_oid=$(git write-tree) +tree_compat_oid=$(git rev-parse --output-object-format=$test_compat_hash_algo $tree_oid) tree_size=$(($(test_oid rawsz) + 13)) +tree_compat_size=$(($(test_oid --hash=compat rawsz) + 13)) tree_pretty_content="100644 blob $hello_oid hello${LF}" +tree_compat_pretty_content="100644 blob $hello_compat_oid hello${LF}" run_tests 'tree' $tree_oid $tree_size "" "$tree_pretty_content" +run_tests 'tree' $tree_compat_oid $tree_compat_size "" "$tree_compat_pretty_content" commit_message="Initial commit" commit_oid=$(echo_without_newline "$commit_message" | git commit-tree $tree_oid) +commit_compat_oid=$(git rev-parse --output-object-format=$test_compat_hash_algo $commit_oid) commit_size=$(($(test_oid hexsz) + 137)) +commit_compat_size=$(($(test_oid --hash=compat hexsz) + 137)) commit_content="tree $tree_oid author $GIT_AUTHOR_NAME <$GIT_AUTHOR_EMAIL> $GIT_AUTHOR_DATE committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE $commit_message" -run_tests 'commit' $commit_oid $commit_size "$commit_content" "$commit_content" +commit_compat_content="tree $tree_compat_oid +author $GIT_AUTHOR_NAME <$GIT_AUTHOR_EMAIL> $GIT_AUTHOR_DATE +committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE -tag_header_without_timestamp="object $hello_oid -type blob +$commit_message" + +run_tests 'commit' $commit_oid $commit_size "$commit_content" "$commit_content" +run_tests 'commit' $commit_compat_oid $commit_compat_size "$commit_compat_content" "$commit_compat_content" + +tag_header_without_oid="type blob tag hellotag tagger $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL>" +tag_header_without_timestamp="object $hello_oid +$tag_header_without_oid" +tag_compat_header_without_timestamp="object $hello_compat_oid +$tag_header_without_oid" tag_description="This is a tag" tag_content="$tag_header_without_timestamp 0 +0000 +$tag_description" +tag_compat_content="$tag_compat_header_without_timestamp 0 +0000 + $tag_description" tag_oid=$(echo_without_newline "$tag_content" | git hash-object -t tag --stdin -w) tag_size=$(strlen "$tag_content") +tag_compat_oid=$(git rev-parse --output-object-format=$test_compat_hash_algo $tag_oid) +tag_compat_size=$(strlen "$tag_compat_content") + run_tests 'tag' $tag_oid $tag_size "$tag_content" "$tag_content" +run_tests 'tag' $tag_compat_oid $tag_compat_size "$tag_compat_content" "$tag_compat_content" test_expect_success "Reach a blob from a tag pointing to it" ' echo_without_newline "$hello_content" >expect && @@ -303,37 +337,43 @@ test_expect_success "Reach a blob from a tag pointing to it" ' test_cmp expect actual ' -for batch in batch batch-check batch-command +for oid in $hello_oid $hello_compat_oid do - for opt in t s e p + for batch in batch batch-check batch-command do + for opt in t s e p + do test_expect_success "Passing -$opt with --$batch fails" ' - test_must_fail git cat-file --$batch -$opt $hello_oid + test_must_fail git cat-file --$batch -$opt $oid ' test_expect_success "Passing --$batch with -$opt fails" ' - test_must_fail git cat-file -$opt --$batch $hello_oid + test_must_fail git cat-file -$opt --$batch $oid + ' + done + + test_expect_success "Passing with --$batch fails" ' + test_must_fail git cat-file --$batch blob $oid + ' + + test_expect_success "Passing --$batch with fails" ' + test_must_fail git cat-file blob --$batch $oid + ' + + test_expect_success "Passing oid with --$batch fails" ' + test_must_fail git cat-file --$batch $oid ' done - - test_expect_success "Passing with --$batch fails" ' - test_must_fail git cat-file --$batch blob $hello_oid - ' - - test_expect_success "Passing --$batch with fails" ' - test_must_fail git cat-file blob --$batch $hello_oid - ' - - test_expect_success "Passing oid with --$batch fails" ' - test_must_fail git cat-file --$batch $hello_oid - ' done -for opt in t s e p +for oid in $hello_oid $hello_compat_oid do - test_expect_success "Passing -$opt with --follow-symlinks fails" ' - test_must_fail git cat-file --follow-symlinks -$opt $hello_oid + for opt in t s e p + do + test_expect_success "Passing -$opt with --follow-symlinks fails" ' + test_must_fail git cat-file --follow-symlinks -$opt $oid ' + done done test_expect_success "--batch-check for a non-existent named object" ' @@ -386,78 +426,160 @@ test_expect_success 'empty --batch-check notices missing object' ' test_cmp expect actual ' -batch_input="$hello_oid -$commit_oid -$tag_oid +batch_tests () { + boid=$1 + loid=$2 + lsize=$3 + coid=$4 + csize=$5 + ccontent=$6 + toid=$7 + tsize=$8 + tcontent=$9 + + batch_input="$boid +$coid +$toid deadbeef " -printf "%s\0" \ - "$hello_oid blob $hello_size" \ + printf "%s\0" \ + "$boid blob $hello_size" \ "$hello_content" \ - "$commit_oid commit $commit_size" \ - "$commit_content" \ - "$tag_oid tag $tag_size" \ - "$tag_content" \ + "$coid commit $csize" \ + "$ccontent" \ + "$toid tag $tsize" \ + "$tcontent" \ "deadbeef missing" \ " missing" >batch_output -test_expect_success '--batch with multiple oids gives correct format' ' + test_expect_success '--batch with multiple oids gives correct format' ' tr "\0" "\n" expect && echo_without_newline "$batch_input" >in && git cat-file --batch actual && test_cmp expect actual -' + ' -test_expect_success '--batch, -z with multiple oids gives correct format' ' + test_expect_success '--batch, -z with multiple oids gives correct format' ' echo_without_newline_nul "$batch_input" >in && tr "\0" "\n" expect && git cat-file --batch -z actual && test_cmp expect actual -' + ' -test_expect_success '--batch, -Z with multiple oids gives correct format' ' + test_expect_success '--batch, -Z with multiple oids gives correct format' ' echo_without_newline_nul "$batch_input" >in && git cat-file --batch -Z actual && test_cmp batch_output actual -' + ' -batch_check_input="$hello_oid -$tree_oid -$commit_oid -$tag_oid +batch_check_input="$boid +$loid +$coid +$toid deadbeef " -printf "%s\0" \ - "$hello_oid blob $hello_size" \ - "$tree_oid tree $tree_size" \ - "$commit_oid commit $commit_size" \ - "$tag_oid tag $tag_size" \ + printf "%s\0" \ + "$boid blob $hello_size" \ + "$loid tree $lsize" \ + "$coid commit $csize" \ + "$toid tag $tsize" \ "deadbeef missing" \ " missing" >batch_check_output -test_expect_success "--batch-check with multiple oids gives correct format" ' + test_expect_success "--batch-check with multiple oids gives correct format" ' tr "\0" "\n" expect && echo_without_newline "$batch_check_input" >in && git cat-file --batch-check actual && test_cmp expect actual -' + ' -test_expect_success "--batch-check, -z with multiple oids gives correct format" ' + test_expect_success "--batch-check, -z with multiple oids gives correct format" ' tr "\0" "\n" expect && echo_without_newline_nul "$batch_check_input" >in && git cat-file --batch-check -z actual && test_cmp expect actual -' + ' -test_expect_success "--batch-check, -Z with multiple oids gives correct format" ' + test_expect_success "--batch-check, -Z with multiple oids gives correct format" ' echo_without_newline_nul "$batch_check_input" >in && git cat-file --batch-check -Z actual && test_cmp batch_check_output actual -' + ' + +batch_command_multiple_info="info $boid +info $loid +info $coid +info $toid +info deadbeef" + + test_expect_success '--batch-command with multiple info calls gives correct format' ' + cat >expect <<-EOF && + $boid blob $hello_size + $loid tree $lsize + $coid commit $csize + $toid tag $tsize + deadbeef missing + EOF + + echo "$batch_command_multiple_info" >in && + git cat-file --batch-command --buffer actual && + + test_cmp expect actual && + + echo "$batch_command_multiple_info" | tr "\n" "\0" >in && + git cat-file --batch-command --buffer -z actual && + + test_cmp expect actual && + + echo "$batch_command_multiple_info" | tr "\n" "\0" >in && + tr "\n" "\0" expect_nul && + git cat-file --batch-command --buffer -Z actual && + + test_cmp expect_nul actual + ' + +batch_command_multiple_contents="contents $boid +contents $coid +contents $toid +contents deadbeef +flush" + + test_expect_success '--batch-command with multiple command calls gives correct format' ' + printf "%s\0" \ + "$boid blob $hello_size" \ + "$hello_content" \ + "$coid commit $csize" \ + "$ccontent" \ + "$toid tag $tsize" \ + "$tcontent" \ + "deadbeef missing" >expect_nul && + tr "\0" "\n" expect && + + echo "$batch_command_multiple_contents" >in && + git cat-file --batch-command --buffer actual && + + test_cmp expect actual && + + echo "$batch_command_multiple_contents" | tr "\n" "\0" >in && + git cat-file --batch-command --buffer -z actual && + + test_cmp expect actual && + + echo "$batch_command_multiple_contents" | tr "\n" "\0" >in && + git cat-file --batch-command --buffer -Z actual && + + test_cmp expect_nul actual + ' + +} + +batch_tests $hello_oid $tree_oid $tree_size $commit_oid $commit_size "$commit_content" $tag_oid $tag_size "$tag_content" +batch_tests $hello_compat_oid $tree_compat_oid $tree_compat_size $commit_compat_oid $commit_compat_size "$commit_compat_content" $tag_compat_oid $tag_compat_size "$tag_compat_content" + test_expect_success FUNNYNAMES 'setup with newline in input' ' touch -- "newline${LF}embedded" && @@ -480,71 +602,6 @@ test_expect_success FUNNYNAMES '--batch-check, -Z with newline in input' ' test_cmp expect actual ' -batch_command_multiple_info="info $hello_oid -info $tree_oid -info $commit_oid -info $tag_oid -info deadbeef" - -test_expect_success '--batch-command with multiple info calls gives correct format' ' - cat >expect <<-EOF && - $hello_oid blob $hello_size - $tree_oid tree $tree_size - $commit_oid commit $commit_size - $tag_oid tag $tag_size - deadbeef missing - EOF - - echo "$batch_command_multiple_info" >in && - git cat-file --batch-command --buffer actual && - - test_cmp expect actual && - - echo "$batch_command_multiple_info" | tr "\n" "\0" >in && - git cat-file --batch-command --buffer -z actual && - - test_cmp expect actual && - - echo "$batch_command_multiple_info" | tr "\n" "\0" >in && - tr "\n" "\0" expect_nul && - git cat-file --batch-command --buffer -Z actual && - - test_cmp expect_nul actual -' - -batch_command_multiple_contents="contents $hello_oid -contents $commit_oid -contents $tag_oid -contents deadbeef -flush" - -test_expect_success '--batch-command with multiple command calls gives correct format' ' - printf "%s\0" \ - "$hello_oid blob $hello_size" \ - "$hello_content" \ - "$commit_oid commit $commit_size" \ - "$commit_content" \ - "$tag_oid tag $tag_size" \ - "$tag_content" \ - "deadbeef missing" >expect_nul && - tr "\0" "\n" expect && - - echo "$batch_command_multiple_contents" >in && - git cat-file --batch-command --buffer actual && - - test_cmp expect actual && - - echo "$batch_command_multiple_contents" | tr "\n" "\0" >in && - git cat-file --batch-command --buffer -z actual && - - test_cmp expect actual && - - echo "$batch_command_multiple_contents" | tr "\n" "\0" >in && - git cat-file --batch-command --buffer -Z actual && - - test_cmp expect_nul actual -' - test_expect_success 'setup blobs which are likely to delta' ' test-tool genrandom foo 10240 >foo && { cat foo && echo plus; } >foo-plus && From 7673ecd2dcdcf0aae01cccdb5c25f9b96160a8c0 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 1 Oct 2023 21:40:34 -0500 Subject: [PATCH 30/30] t1016-compatObjectFormat: add tests to verify the conversion between objects For now my strategy is simple. Create two identical repositories one in each format. Use fixed timestamps. Verify the dynamically computed compatibility objects from one repository match the objects stored in the other repository. A general limitation of this strategy is that the git when generating signed tags and commits with compatObjectFormat enabled will generate a signature for both formats. To overcome this limitation I have added "test-tool delete-gpgsig" that when fed an signed commit or tag with two signatures deletes one of the signatures. With that in place I can have "git commit" and "git tag" generate signed objects, have my tool delete one, and feed the new object into "git hash-object" to create the kinds of commits and tags git without compatObjectFormat enabled will generate. Signed-off-by: "Eric W. Biederman" Signed-off-by: Junio C Hamano --- Makefile | 1 + t/helper/test-delete-gpgsig.c | 62 ++++++++ t/helper/test-tool.c | 1 + t/helper/test-tool.h | 1 + t/t1016-compatObjectFormat.sh | 281 ++++++++++++++++++++++++++++++++++ t/t1016/gpg | 2 + 6 files changed, 348 insertions(+) create mode 100644 t/helper/test-delete-gpgsig.c create mode 100755 t/t1016-compatObjectFormat.sh create mode 100755 t/t1016/gpg diff --git a/Makefile b/Makefile index 3c18664def..3e4444fb9a 100644 --- a/Makefile +++ b/Makefile @@ -790,6 +790,7 @@ TEST_BUILTINS_OBJS += test-crontab.o TEST_BUILTINS_OBJS += test-csprng.o TEST_BUILTINS_OBJS += test-ctype.o TEST_BUILTINS_OBJS += test-date.o +TEST_BUILTINS_OBJS += test-delete-gpgsig.o TEST_BUILTINS_OBJS += test-delta.o TEST_BUILTINS_OBJS += test-dir-iterator.o TEST_BUILTINS_OBJS += test-drop-caches.o diff --git a/t/helper/test-delete-gpgsig.c b/t/helper/test-delete-gpgsig.c new file mode 100644 index 0000000000..e36831af03 --- /dev/null +++ b/t/helper/test-delete-gpgsig.c @@ -0,0 +1,62 @@ +#include "test-tool.h" +#include "gpg-interface.h" +#include "strbuf.h" + + +int cmd__delete_gpgsig(int argc, const char **argv) +{ + struct strbuf buf = STRBUF_INIT; + const char *pattern = "gpgsig"; + const char *bufptr, *tail, *eol; + int deleting = 0; + size_t plen; + + if (argc >= 2) { + pattern = argv[1]; + argv++; + argc--; + } + + plen = strlen(pattern); + strbuf_read(&buf, 0, 0); + + if (!strcmp(pattern, "trailer")) { + size_t payload_size = parse_signed_buffer(buf.buf, buf.len); + fwrite(buf.buf, 1, payload_size, stdout); + fflush(stdout); + return 0; + } + + bufptr = buf.buf; + tail = bufptr + buf.len; + + while (bufptr < tail) { + /* Find the end of the line */ + eol = memchr(bufptr, '\n', tail - bufptr); + if (!eol) + eol = tail; + + /* Drop continuation lines */ + if (deleting && (bufptr < eol) && (bufptr[0] == ' ')) { + bufptr = eol + 1; + continue; + } + deleting = 0; + + /* Does the line match the prefix? */ + if (((bufptr + plen) < eol) && + !memcmp(bufptr, pattern, plen) && + (bufptr[plen] == ' ')) { + deleting = 1; + bufptr = eol + 1; + continue; + } + + /* Print all other lines */ + fwrite(bufptr, 1, (eol - bufptr) + 1, stdout); + bufptr = eol + 1; + } + fflush(stdout); + + return 0; +} diff --git a/t/helper/test-tool.c b/t/helper/test-tool.c index abe8a785eb..8b6c84f202 100644 --- a/t/helper/test-tool.c +++ b/t/helper/test-tool.c @@ -21,6 +21,7 @@ static struct test_cmd cmds[] = { { "csprng", cmd__csprng }, { "ctype", cmd__ctype }, { "date", cmd__date }, + { "delete-gpgsig", cmd__delete_gpgsig }, { "delta", cmd__delta }, { "dir-iterator", cmd__dir_iterator }, { "drop-caches", cmd__drop_caches }, diff --git a/t/helper/test-tool.h b/t/helper/test-tool.h index ea2672436c..76baaece35 100644 --- a/t/helper/test-tool.h +++ b/t/helper/test-tool.h @@ -15,6 +15,7 @@ int cmd__csprng(int argc, const char **argv); int cmd__ctype(int argc, const char **argv); int cmd__date(int argc, const char **argv); int cmd__delta(int argc, const char **argv); +int cmd__delete_gpgsig(int argc, const char **argv); int cmd__dir_iterator(int argc, const char **argv); int cmd__drop_caches(int argc, const char **argv); int cmd__dump_cache_tree(int argc, const char **argv); diff --git a/t/t1016-compatObjectFormat.sh b/t/t1016-compatObjectFormat.sh new file mode 100755 index 0000000000..8132cd37b8 --- /dev/null +++ b/t/t1016-compatObjectFormat.sh @@ -0,0 +1,281 @@ +#!/bin/sh +# +# Copyright (c) 2023 Eric Biederman +# + +test_description='Test how well compatObjectFormat works' + +TEST_PASSES_SANITIZE_LEAK=true +. ./test-lib.sh +. "$TEST_DIRECTORY"/lib-gpg.sh + +# All of the follow variables must be defined in the environment: +# GIT_AUTHOR_NAME +# GIT_AUTHOR_EMAIL +# GIT_AUTHOR_DATE +# GIT_COMMITTER_NAME +# GIT_COMMITTER_EMAIL +# GIT_COMMITTER_DATE +# +# The test relies on these variables being set so that the two +# different commits in two different repositories encoded with two +# different hash functions result in the same content in the commits. +# This means that when the commit is translated between hash functions +# the commit is identical to the commit in the other repository. + +compat_hash () { + case "$1" in + "sha1") + echo "sha256" + ;; + "sha256") + echo "sha1" + ;; + esac +} + +hello_oid () { + case "$1" in + "sha1") + echo "$hello_sha1_oid" + ;; + "sha256") + echo "$hello_sha256_oid" + ;; + esac +} + +tree_oid () { + case "$1" in + "sha1") + echo "$tree_sha1_oid" + ;; + "sha256") + echo "$tree_sha256_oid" + ;; + esac +} + +commit_oid () { + case "$1" in + "sha1") + echo "$commit_sha1_oid" + ;; + "sha256") + echo "$commit_sha256_oid" + ;; + esac +} + +commit2_oid () { + case "$1" in + "sha1") + echo "$commit2_sha1_oid" + ;; + "sha256") + echo "$commit2_sha256_oid" + ;; + esac +} + +del_sigcommit () { + local delete=$1 + + if test "$delete" = "sha256" ; then + local pattern="gpgsig-sha256" + else + local pattern="gpgsig" + fi + test-tool delete-gpgsig "$pattern" +} + + +del_sigtag () { + local storage=$1 + local delete=$2 + + if test "$storage" = "$delete" ; then + local pattern="trailer" + elif test "$storage" = "sha256" ; then + local pattern="gpgsig" + else + local pattern="gpgsig-sha256" + fi + test-tool delete-gpgsig "$pattern" +} + +base=$(pwd) +for hash in sha1 sha256 +do + cd "$base" + mkdir -p repo-$hash + cd repo-$hash + + test_expect_success "setup $hash repository" ' + git init --object-format=$hash && + git config core.repositoryformatversion 1 && + git config extensions.objectformat $hash && + git config extensions.compatobjectformat $(compat_hash $hash) && + git config gpg.program $TEST_DIRECTORY/t1016/gpg && + echo "Hellow World!" > hello && + eval hello_${hash}_oid=$(git hash-object hello) && + git update-index --add hello && + git commit -m "Initial commit" && + eval commit_${hash}_oid=$(git rev-parse HEAD) && + eval tree_${hash}_oid=$(git rev-parse HEAD^{tree}) + ' + test_expect_success "create a $hash tagged blob" ' + git tag --no-sign -m "This is a tag" hellotag $(hello_oid $hash) && + eval hellotag_${hash}_oid=$(git rev-parse hellotag) + ' + test_expect_success "create a $hash tagged tree" ' + git tag --no-sign -m "This is a tag" treetag $(tree_oid $hash) && + eval treetag_${hash}_oid=$(git rev-parse treetag) + ' + test_expect_success "create a $hash tagged commit" ' + git tag --no-sign -m "This is a tag" committag $(commit_oid $hash) && + eval committag_${hash}_oid=$(git rev-parse committag) + ' + test_expect_success GPG2 "create a $hash signed commit" ' + git commit --gpg-sign --allow-empty -m "This is a signed commit" && + eval signedcommit_${hash}_oid=$(git rev-parse HEAD) + ' + test_expect_success GPG2 "create a $hash signed tag" ' + git tag -s -m "This is a signed tag" signedtag HEAD && + eval signedtag_${hash}_oid=$(git rev-parse signedtag) + ' + test_expect_success "create a $hash branch" ' + git checkout -b branch $(commit_oid $hash) && + echo "More more more give me more!" > more && + eval more_${hash}_oid=$(git hash-object more) && + echo "Another and another and another" > another && + eval another_${hash}_oid=$(git hash-object another) && + git update-index --add more another && + git commit -m "Add more files!" && + eval commit2_${hash}_oid=$(git rev-parse HEAD) && + eval tree2_${hash}_oid=$(git rev-parse HEAD^{tree}) + ' + test_expect_success GPG2 "create another $hash signed tag" ' + git tag -s -m "This is another signed tag" signedtag2 $(commit2_oid $hash) && + eval signedtag2_${hash}_oid=$(git rev-parse signedtag2) + ' + test_expect_success GPG2 "merge the $hash branches together" ' + git merge -S -m "merge some signed tags together" signedtag signedtag2 && + eval signedcommit2_${hash}_oid=$(git rev-parse HEAD) + ' + test_expect_success GPG2 "create additional $hash signed commits" ' + git commit --gpg-sign --allow-empty -m "This is an additional signed commit" && + git cat-file commit HEAD | del_sigcommit sha256 > "../${hash}_signedcommit3" && + git cat-file commit HEAD | del_sigcommit sha1 > "../${hash}_signedcommit4" && + eval signedcommit3_${hash}_oid=$(git hash-object -t commit -w ../${hash}_signedcommit3) && + eval signedcommit4_${hash}_oid=$(git hash-object -t commit -w ../${hash}_signedcommit4) + ' + test_expect_success GPG2 "create additional $hash signed tags" ' + git tag -s -m "This is an additional signed tag" signedtag34 HEAD && + git cat-file tag signedtag34 | del_sigtag "${hash}" sha256 > ../${hash}_signedtag3 && + git cat-file tag signedtag34 | del_sigtag "${hash}" sha1 > ../${hash}_signedtag4 && + eval signedtag3_${hash}_oid=$(git hash-object -t tag -w ../${hash}_signedtag3) && + eval signedtag4_${hash}_oid=$(git hash-object -t tag -w ../${hash}_signedtag4) + ' +done +cd "$base" + +compare_oids () { + test "$#" = 5 && { local PREREQ=$1; shift; } || PREREQ= + local type="$1" + local name="$2" + local sha1_oid="$3" + local sha256_oid="$4" + + echo ${sha1_oid} > ${name}_sha1_expected + echo ${sha256_oid} > ${name}_sha256_expected + echo ${type} > ${name}_type_expected + + git --git-dir=repo-sha1/.git rev-parse --output-object-format=sha256 ${sha1_oid} > ${name}_sha1_sha256_found + git --git-dir=repo-sha256/.git rev-parse --output-object-format=sha1 ${sha256_oid} > ${name}_sha256_sha1_found + local sha1_sha256_oid=$(cat ${name}_sha1_sha256_found) + local sha256_sha1_oid=$(cat ${name}_sha256_sha1_found) + + test_expect_success $PREREQ "Verify ${type} ${name}'s sha1 oid" ' + git --git-dir=repo-sha256/.git rev-parse --output-object-format=sha1 ${sha256_oid} > ${name}_sha1 && + test_cmp ${name}_sha1 ${name}_sha1_expected +' + + test_expect_success $PREREQ "Verify ${type} ${name}'s sha256 oid" ' + git --git-dir=repo-sha1/.git rev-parse --output-object-format=sha256 ${sha1_oid} > ${name}_sha256 && + test_cmp ${name}_sha256 ${name}_sha256_expected +' + + test_expect_success $PREREQ "Verify ${name}'s sha1 type" ' + git --git-dir=repo-sha1/.git cat-file -t ${sha1_oid} > ${name}_type1 && + git --git-dir=repo-sha256/.git cat-file -t ${sha256_sha1_oid} > ${name}_type2 && + test_cmp ${name}_type1 ${name}_type2 && + test_cmp ${name}_type1 ${name}_type_expected +' + + test_expect_success $PREREQ "Verify ${name}'s sha256 type" ' + git --git-dir=repo-sha256/.git cat-file -t ${sha256_oid} > ${name}_type3 && + git --git-dir=repo-sha1/.git cat-file -t ${sha1_sha256_oid} > ${name}_type4 && + test_cmp ${name}_type3 ${name}_type4 && + test_cmp ${name}_type3 ${name}_type_expected +' + + test_expect_success $PREREQ "Verify ${name}'s sha1 size" ' + git --git-dir=repo-sha1/.git cat-file -s ${sha1_oid} > ${name}_size1 && + git --git-dir=repo-sha256/.git cat-file -s ${sha256_sha1_oid} > ${name}_size2 && + test_cmp ${name}_size1 ${name}_size2 +' + + test_expect_success $PREREQ "Verify ${name}'s sha256 size" ' + git --git-dir=repo-sha256/.git cat-file -s ${sha256_oid} > ${name}_size3 && + git --git-dir=repo-sha1/.git cat-file -s ${sha1_sha256_oid} > ${name}_size4 && + test_cmp ${name}_size3 ${name}_size4 +' + + test_expect_success $PREREQ "Verify ${name}'s sha1 pretty content" ' + git --git-dir=repo-sha1/.git cat-file -p ${sha1_oid} > ${name}_content1 && + git --git-dir=repo-sha256/.git cat-file -p ${sha256_sha1_oid} > ${name}_content2 && + test_cmp ${name}_content1 ${name}_content2 +' + + test_expect_success $PREREQ "Verify ${name}'s sha256 pretty content" ' + git --git-dir=repo-sha256/.git cat-file -p ${sha256_oid} > ${name}_content3 && + git --git-dir=repo-sha1/.git cat-file -p ${sha1_sha256_oid} > ${name}_content4 && + test_cmp ${name}_content3 ${name}_content4 +' + + test_expect_success $PREREQ "Verify ${name}'s sha1 content" ' + git --git-dir=repo-sha1/.git cat-file ${type} ${sha1_oid} > ${name}_content5 && + git --git-dir=repo-sha256/.git cat-file ${type} ${sha256_sha1_oid} > ${name}_content6 && + test_cmp ${name}_content5 ${name}_content6 +' + + test_expect_success $PREREQ "Verify ${name}'s sha256 content" ' + git --git-dir=repo-sha256/.git cat-file ${type} ${sha256_oid} > ${name}_content7 && + git --git-dir=repo-sha1/.git cat-file ${type} ${sha1_sha256_oid} > ${name}_content8 && + test_cmp ${name}_content7 ${name}_content8 +' + +} + +compare_oids 'blob' hello "$hello_sha1_oid" "$hello_sha256_oid" +compare_oids 'tree' tree "$tree_sha1_oid" "$tree_sha256_oid" +compare_oids 'commit' commit "$commit_sha1_oid" "$commit_sha256_oid" +compare_oids GPG2 'commit' signedcommit "$signedcommit_sha1_oid" "$signedcommit_sha256_oid" +compare_oids 'tag' hellotag "$hellotag_sha1_oid" "$hellotag_sha256_oid" +compare_oids 'tag' treetag "$treetag_sha1_oid" "$treetag_sha256_oid" +compare_oids 'tag' committag "$committag_sha1_oid" "$committag_sha256_oid" +compare_oids GPG2 'tag' signedtag "$signedtag_sha1_oid" "$signedtag_sha256_oid" + +compare_oids 'blob' more "$more_sha1_oid" "$more_sha256_oid" +compare_oids 'blob' another "$another_sha1_oid" "$another_sha256_oid" +compare_oids 'tree' tree2 "$tree2_sha1_oid" "$tree2_sha256_oid" +compare_oids 'commit' commit2 "$commit2_sha1_oid" "$commit2_sha256_oid" +compare_oids GPG2 'tag' signedtag2 "$signedtag2_sha1_oid" "$signedtag2_sha256_oid" +compare_oids GPG2 'commit' signedcommit2 "$signedcommit2_sha1_oid" "$signedcommit2_sha256_oid" +compare_oids GPG2 'commit' signedcommit3 "$signedcommit3_sha1_oid" "$signedcommit3_sha256_oid" +compare_oids GPG2 'commit' signedcommit4 "$signedcommit4_sha1_oid" "$signedcommit4_sha256_oid" +compare_oids GPG2 'tag' signedtag3 "$signedtag3_sha1_oid" "$signedtag3_sha256_oid" +compare_oids GPG2 'tag' signedtag4 "$signedtag4_sha1_oid" "$signedtag4_sha256_oid" + +test_done diff --git a/t/t1016/gpg b/t/t1016/gpg new file mode 100755 index 0000000000..2601cb18a5 --- /dev/null +++ b/t/t1016/gpg @@ -0,0 +1,2 @@ +#!/bin/sh +exec gpg --faked-system-time "20230918T154812" "$@"