Merge pull request #3533 from PhilipOakley/hashliteral_t

Begin `unsigned long`->`size_t` conversion to support large files on Windows

Author: dscho

object-file.c

@@ -509,9 +509,9 @@ int odb_source_loose_read_object_info(struct odb_source *source,
 }
 
 static void hash_object_body(const struct git_hash_algo *algo, struct git_hash_ctx *c,
-			     const void *buf, unsigned long len,
+			     const void *buf, size_t len,
 			     struct object_id *oid,
-			     char *hdr, int *hdrlen)
+			     char *hdr, size_t *hdrlen)
 {
 	algo->init_fn(c);
 	git_hash_update(c, hdr, *hdrlen);
@@ -520,16 +520,16 @@ static void hash_object_body(const struct git_hash_algo *algo, struct git_hash_c
 }
 
 static void write_object_file_prepare(const struct git_hash_algo *algo,
-				      const void *buf, unsigned long len,
+				      const void *buf, size_t len,
 				      enum object_type type, struct object_id *oid,
-				      char *hdr, int *hdrlen)
+				      char *hdr, size_t *hdrlen)
 {
 	struct git_hash_ctx c;
 
 	/* Generate the header */
 	*hdrlen = format_object_header(hdr, *hdrlen, type, len);
 
-	/* Sha1.. */
+	/* Hash (function pointers) computation */
 	hash_object_body(algo, &c, buf, len, oid, hdr, hdrlen);
 }
 
@@ -665,11 +665,11 @@ int finalize_object_file_flags(struct repository *repo,
 }
 
 void hash_object_file(const struct git_hash_algo *algo, const void *buf,
-		      unsigned long len, enum object_type type,
+		      size_t len, enum object_type type,
 		      struct object_id *oid)
 {
 	char hdr[MAX_HEADER_LEN];
-	int hdrlen = sizeof(hdr);
+	size_t hdrlen = sizeof(hdr);
 
 	write_object_file_prepare(algo, buf, len, type, oid, hdr, &hdrlen);
 }
@@ -1110,15 +1110,15 @@ int odb_source_loose_write_stream(struct odb_source *source,
 }
 
 int odb_source_loose_write_object(struct odb_source *source,
-				  const void *buf, unsigned long len,
+				  const void *buf, size_t len,
 				  enum object_type type, struct object_id *oid,
 				  struct object_id *compat_oid_in, unsigned flags)
 {
 	const struct git_hash_algo *algo = source->odb->repo->hash_algo;
 	const struct git_hash_algo *compat = source->odb->repo->compat_hash_algo;
 	struct object_id compat_oid;
 	char hdr[MAX_HEADER_LEN];
-	int hdrlen = sizeof(hdr);
+	size_t hdrlen = sizeof(hdr);
 
 	/* Generate compat_oid */
 	if (compat) {

object-file.h

@@ -177,7 +177,7 @@ int finalize_object_file_flags(struct repository *repo,
 			       enum finalize_object_file_flags flags);
 
 void hash_object_file(const struct git_hash_algo *algo, const void *buf,
-		      unsigned long len, enum object_type type,
+		      size_t len, enum object_type type,
 		      struct object_id *oid);
 
 /* Helper to check and "touch" a file */

sha1dc_git.c

@@ -27,10 +27,9 @@ void git_SHA1DCFinal(unsigned char hash[20], SHA1_CTX *ctx)
 /*
  * Same as SHA1DCUpdate, but adjust types to match git's usual interface.
  */
-void git_SHA1DCUpdate(SHA1_CTX *ctx, const void *vdata, unsigned long len)
+void git_SHA1DCUpdate(SHA1_CTX *ctx, const void *vdata, size_t len)
 {
 	const char *data = vdata;
-	/* We expect an unsigned long, but sha1dc only takes an int */
 	while (len > INT_MAX) {
 		SHA1DCUpdate(ctx, data, INT_MAX);
 		data += INT_MAX;

sha1dc_git.h

@@ -15,7 +15,7 @@ void git_SHA1DCInit(SHA1_CTX *);
 #endif
 
 void git_SHA1DCFinal(unsigned char [20], SHA1_CTX *);
-void git_SHA1DCUpdate(SHA1_CTX *ctx, const void *data, unsigned long len);
+void git_SHA1DCUpdate(SHA1_CTX *ctx, const void *data, size_t len);
 
 #define platform_SHA_IS_SHA1DC /* used by "test-tool sha1-is-sha1dc" */
 

t/t1007-hash-object.sh

@@ -49,6 +49,9 @@ test_expect_success 'setup' '
 
 	example sha1:ddd3f836d3e3fbb7ae289aa9ae83536f76956399
 	example sha256:b44fe1fe65589848253737db859bd490453510719d7424daab03daf0767b85ae
+
+	large5GB sha1:0be2be10a4c8764f32c4bf372a98edc731a4b204
+	large5GB sha256:dc18ca621300c8d3cfa505a275641ebab00de189859e022a975056882d313e64
 	EOF
 '
 
@@ -258,4 +261,40 @@ test_expect_success '--stdin outside of repository (uses default hash)' '
 	test_cmp expect actual
 '
 
+test_expect_success EXPENSIVE,SIZE_T_IS_64BIT,!LONG_IS_64BIT \
+		'files over 4GB hash literally' '
+	test-tool genzeros $((5*1024*1024*1024)) >big &&
+	test_oid large5GB >expect &&
+	git hash-object --stdin --literally <big >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success EXPENSIVE,SIZE_T_IS_64BIT,!LONG_IS_64BIT \
+		'files over 4GB hash correctly via --stdin' '
+	{ test -f big || test-tool genzeros $((5*1024*1024*1024)) >big; } &&
+	test_oid large5GB >expect &&
+	git hash-object --stdin <big >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success EXPENSIVE,SIZE_T_IS_64BIT,!LONG_IS_64BIT \
+		'files over 4GB hash correctly' '
+	{ test -f big || test-tool genzeros $((5*1024*1024*1024)) >big; } &&
+	test_oid large5GB >expect &&
+	git hash-object -- big >actual &&
+	test_cmp expect actual
+'
+
+# This clean filter does nothing, other than excercising the interface.
+# We ensure that cleaning doesn't mangle large files on 64-bit Windows.
+test_expect_success EXPENSIVE,SIZE_T_IS_64BIT,!LONG_IS_64BIT \
+		'hash filtered files over 4GB correctly' '
+	{ test -f big || test-tool genzeros $((5*1024*1024*1024)) >big; } &&
+	test_oid large5GB >expect &&
+	test_config filter.null-filter.clean "cat" &&
+	echo "big filter=null-filter" >.gitattributes &&
+	git hash-object -- big >actual &&
+	test_cmp expect actual
+'
+
 test_done