[PATCH v4 1/5] setup: add an escape hatch for "no more default hash algorithm" change

[Junio C Hamano <gitster@pobox.com>]

Partially revert c8aed5e8 (repository: stop setting SHA1 as the
default object hash, 2024-05-07), to keep end-user systems still
broken when we have gap in our test coverage but yet give them an
escape hatch to set the GIT_DEFAULT_HASH environment variable to
"sha1" in order to revert to the previous behaviour.  This variable
has been in use for using SHA-256 hash by default, and it should be
a better fit than inventing a new and test-only knob.

Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 environment.h |  1 +
 repository.c  | 40 ++++++++++++++++++++++++++++++++++++++++
 setup.c       |  2 --
 3 files changed, 41 insertions(+), 2 deletions(-)

diff --git a/environment.h b/environment.h
index 05fd94d7be..deaa29408f 100644
--- a/environment.h
+++ b/environment.h
@@ -56,6 +56,7 @@ const char *getenv_safe(struct strvec *argv, const char *name);
 #define GIT_OPTIONAL_LOCKS_ENVIRONMENT "GIT_OPTIONAL_LOCKS"
 #define GIT_TEXT_DOMAIN_DIR_ENVIRONMENT "GIT_TEXTDOMAINDIR"
 #define GIT_ATTR_SOURCE_ENVIRONMENT "GIT_ATTR_SOURCE"
+#define GIT_DEFAULT_HASH_ENVIRONMENT "GIT_DEFAULT_HASH"
 
 /*
  * Environment variable used in handshaking the wire protocol.
diff --git a/repository.c b/repository.c
index 15c10015b0..f912ee9a7c 100644
--- a/repository.c
+++ b/repository.c
@@ -1,5 +1,6 @@
 #include "git-compat-util.h"
 #include "abspath.h"
+#include "environment.h"
 #include "repository.h"
 #include "object-store-ll.h"
 #include "config.h"
@@ -19,6 +20,27 @@
 static struct repository the_repo;
 struct repository *the_repository = &the_repo;
 
+static void set_default_hash_algo(struct repository *repo)
+{
+	const char *hash_name;
+	int algo;
+
+	hash_name = getenv(GIT_DEFAULT_HASH_ENVIRONMENT);
+	if (!hash_name)
+		return;
+	algo = hash_algo_by_name(hash_name);
+
+	/*
+	 * NEEDSWORK: after all, falling back to SHA-1 by assigning
+	 * GIT_HASH_SHA1 to algo here, instead of returning, may give
+	 * us better behaviour.
+	 */
+	if (algo == GIT_HASH_UNKNOWN)
+		return;
+
+	repo_set_hash_algo(repo, algo);
+}
+
 void initialize_repository(struct repository *repo)
 {
 	repo->objects = raw_object_store_new();
@@ -26,6 +48,24 @@ void initialize_repository(struct repository *repo)
 	repo->parsed_objects = parsed_object_pool_new();
 	ALLOC_ARRAY(repo->index, 1);
 	index_state_init(repo->index, repo);
+
+	/*
+	 * When a command runs inside a repository, it learns what
+	 * hash algorithm is in use from the repository, but some
+	 * commands are designed to work outside a repository, yet
+	 * they want to access the_hash_algo, if only for the length
+	 * of the hashed value to see if their input looks like a
+	 * plausible hash value.
+	 *
+	 * We are in the process of identifying the codepaths and
+	 * giving them an appropriate default individually; any
+	 * unconverted codepath that tries to access the_hash_algo
+	 * will thus fail.  The end-users however have an escape hatch
+	 * to set GIT_DEFAULT_HASH environment variable to "sha1" get
+	 * back the old behaviour of defaulting to SHA-1.
+	 */
+	if (repo == the_repository)
+		set_default_hash_algo(repo);
 }
 
 static void expand_base_dir(char **out, const char *in,
diff --git a/setup.c b/setup.c
index 7c996659bd..d084703465 100644
--- a/setup.c
+++ b/setup.c
@@ -1840,8 +1840,6 @@ int daemonize(void)
 #define TEST_FILEMODE 1
 #endif
 
-#define GIT_DEFAULT_HASH_ENVIRONMENT "GIT_DEFAULT_HASH"
-
 static void copy_templates_1(struct strbuf *path, struct strbuf *template_path,
 			     DIR *dir)
 {
-- 
2.45.0-145-g3e4a232f6e