@@ -5,6 +5,7 @@
#include "hash.h"
#include "hex.h"
#include "parse-options.h"
+#include "setup.h"
static void flush_current_id(int patchlen, struct object_id *id, struct object_id *result)
{
@@ -237,6 +238,18 @@ int cmd_patch_id(int argc, const char **argv, const char *prefix)
argc = parse_options(argc, argv, prefix, builtin_patch_id_options,
patch_id_usage, 0);
+ /*
+ * We rely on `the_hash_algo` to compute patch IDs. This is dubious as
+ * it means that the hash algorithm now depends on the object hash of
+ * the repository, even though git-patch-id(1) clearly defines that
+ * patch IDs always use SHA1.
+ *
+ * TODO: This hack should be removed in favor of converting the code
+ * that computes patch IDs to always use SHA1.
+ */
+ if (!startup_info->have_repository)
+ repo_set_hash_algo(the_repository, GIT_HASH_SHA1);
+
generate_id_list(opts ? opts > 1 : config.stable,
opts ? opts == 3 : config.verbatim);
return 0;
@@ -310,4 +310,38 @@ test_expect_success 'patch-id handles diffs with one line of before/after' '
test_config patchid.stable true &&
calc_patch_id diffu1stable <diffu1
'
+
+test_expect_failure 'patch-id computes same ID with different object hashes' '
+ test_when_finished "rm -rf repo-sha1 repo-sha256" &&
+
+ cat >diff <<-\EOF &&
+ diff --git a/bar b/bar
+ index bdaf90f..31051f6 100644
+ --- a/bar
+ +++ b/bar
+ @@ -2 +2,2 @@
+ b
+ +c
+ EOF
+
+ git init --object-format=sha1 repo-sha1 &&
+ git -C repo-sha1 patch-id <diff >patch-id-sha1 &&
+ git init --object-format=sha256 repo-sha256 &&
+ git -C repo-sha256 patch-id <diff >patch-id-sha256 &&
+ test_cmp patch-id-sha1 patch-id-sha256
+'
+
+test_expect_success 'patch-id without repository' '
+ cat >diff <<-\EOF &&
+ diff --git a/bar b/bar
+ index bdaf90f..31051f6 100644
+ --- a/bar
+ +++ b/bar
+ @@ -2 +2,2 @@
+ b
+ +c
+ EOF
+ nongit git patch-id <diff
+'
+
test_done
In c8aed5e8da (repository: stop setting SHA1 as the default object hash, 2024-05-07), we have adapted `initialize_repository()` to no longer set up a default hash function. As this function is also used to set up `the_repository`, the consequence is that `the_hash_algo` will now by default be a `NULL` pointer unless the hash algorithm was configured properly. This is done as a mechanism to detect cases where we may be using the wrong hash function by accident. This change now causes git-patch-id(1) to segfault when it's run outside of a repository. As this command can read diffs from stdin, it does not necessarily need a repository, but then relies on `the_hash_algo` to compute the patch ID itself. It is somewhat dubious that git-patch-id(1) relies on `the_hash_algo` in the first place. Quoting its manpage: A "patch ID" is nothing but a sum of SHA-1 of the file diffs associated with a patch, with line numbers ignored. As such, it’s "reasonably stable", but at the same time also reasonably unique, i.e., two patches that have the same "patch ID" are almost guaranteed to be the same thing. We explicitly document patch IDs to be using SHA-1. Furthermore, patch IDs are supposed to be stable for most of the part. But even with the same input, the patch IDs will now be different depending on the repo's configured object hash. Work around the issue by setting up SHA-1 when there was no startup repository for now. This is arguably not the correct fix, but for now we rather want to focus on getting the segfault fixed. Signed-off-by: Patrick Steinhardt <ps@pks.im> --- builtin/patch-id.c | 13 +++++++++++++ t/t4204-patch-id.sh | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 47 insertions(+)