Support loose 4GB+ objects

git-zlib.c

@@ -33,7 +33,7 @@ static const char *zerr_to_string(int status)
 
 /* uLong is 32-bit on Windows, even on 64-bit systems */
 #define ULONG_MAX_VALUE maximum_unsigned_value_of_type(uLong)
-static inline uInt zlib_buf_cap(unsigned long len)
+static inline uInt zlib_buf_cap(size_t len)
 {
 	return (ZLIB_BUF_MAX < len) ? ZLIB_BUF_MAX : len;
 }

object-file.c

@@ -146,7 +146,7 @@ int stream_object_signature(struct repository *r,
  * Map and close the given loose object fd. The path argument is used for
  * error reporting.
  */
-static void *map_fd(int fd, const char *path, unsigned long *size)
+static void *map_fd(int fd, const char *path, size_t *size)
 {
 	void *map = NULL;
 	struct stat st;
@@ -167,9 +167,9 @@ static void *map_fd(int fd, const char *path, unsigned long *size)
 
 enum unpack_loose_header_result unpack_loose_header(git_zstream *stream,
 						    unsigned char *map,
-						    unsigned long mapsize,
+						    size_t mapsize,
 						    void *buffer,
-						    unsigned long bufsiz)
+						    size_t bufsiz)
 {
 	int status;
 
@@ -200,7 +200,7 @@ enum unpack_loose_header_result unpack_loose_header(git_zstream *stream,
 }
 
 void *unpack_loose_rest(git_zstream *stream,
-			void *buffer, unsigned long size,
+			void *buffer, size_t size,
 			const struct object_id *oid)
 {
 	size_t bytes = strlen(buffer) + 1, n;
@@ -749,7 +749,7 @@ static int end_loose_object_common(struct odb_source_loose *loose,
 
 int write_loose_object(struct odb_source_loose *loose,
 		       const struct object_id *oid, char *hdr,
-		       int hdrlen, const void *buf, unsigned long len,
+		       int hdrlen, const void *buf, size_t len,
 		       time_t mtime, unsigned flags)
 {
 	int fd, ret;
@@ -1613,7 +1613,7 @@ int read_loose_object(struct repository *repo,
 	int ret = -1;
 	int fd;
 	void *map = NULL;
-	unsigned long mapsize;
+	size_t mapsize;
 	git_zstream stream;
 	char hdr[MAX_HEADER_LEN];
 	size_t *size = oi->sizep;

object-file.h

@@ -139,7 +139,7 @@ void write_object_file_prepare(const struct git_hash_algo *algo,
 			       char *hdr, size_t *hdrlen);
 int write_loose_object(struct odb_source_loose *loose,
 		       const struct object_id *oid, char *hdr,
-		       int hdrlen, const void *buf, unsigned long len,
+		       int hdrlen, const void *buf, size_t len,
 		       time_t mtime, unsigned flags);
 
 /* Helper to check and "touch" a file */
@@ -180,11 +180,11 @@ enum unpack_loose_header_result {
  */
 enum unpack_loose_header_result unpack_loose_header(git_zstream *stream,
 						    unsigned char *map,
-						    unsigned long mapsize,
+						    size_t mapsize,
 						    void *buffer,
-						    unsigned long bufsiz);
+						    size_t bufsiz);
 void *unpack_loose_rest(git_zstream *stream,
-			void *buffer, unsigned long size,
+			void *buffer, size_t size,
 			const struct object_id *oid);
 
 int parse_loose_header(const char *hdr, struct object_info *oi);

odb.c

@@ -986,7 +986,7 @@ void odb_assert_oid_type(struct object_database *odb,
 }
 
 int odb_write_object_ext(struct object_database *odb,
-			 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,

odb.h

@@ -548,14 +548,14 @@ enum odb_write_object_flags {
  * Returns 0 on success, a negative error code otherwise.
  */
 int odb_write_object_ext(struct object_database *odb,
-			 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,
 			 enum odb_write_object_flags flags);
 
 static inline int odb_write_object(struct object_database *odb,
-				   const void *buf, unsigned long len,
+				   const void *buf, size_t len,
 				   enum object_type type,
 				   struct object_id *oid)
 {

odb/source-loose.c

@@ -68,7 +68,7 @@ static int read_object_info_from_path(struct odb_source_loose *loose,
 {
 	int ret;
 	int fd;
-	unsigned long mapsize;
+	size_t mapsize;
 	void *map = NULL;
 	git_zstream stream, *stream_to_end = NULL;
 	char hdr[MAX_HEADER_LEN];
@@ -248,7 +248,7 @@ static int open_loose_object(struct odb_source_loose *loose,
 
 static void *odb_source_loose_map_object(struct odb_source_loose *loose,
 					 const struct object_id *oid,
-					 unsigned long *size)
+					 size_t *size)
 {
 	const char *p;
 	int fd = open_loose_object(loose, oid, &p);
@@ -283,7 +283,7 @@ struct odb_loose_read_stream {
 		ODB_LOOSE_READ_STREAM_ERROR,
 	} z_state;
 	void *mapped;
-	unsigned long mapsize;
+	size_t mapsize;
 	char hdr[32];
 	int hdr_avail;
 	int hdr_used;
@@ -354,7 +354,7 @@ static int odb_source_loose_read_object_stream(struct odb_read_stream **out,
 	struct odb_source_loose *loose = odb_source_loose_downcast(source);
 	struct object_info oi = OBJECT_INFO_INIT;
 	struct odb_loose_read_stream *st;
-	unsigned long mapsize;
+	size_t mapsize;
 	void *mapped;
 
 	mapped = odb_source_loose_map_object(loose, oid, &mapsize);

odb/source.h

@@ -407,7 +407,7 @@ static inline int odb_source_freshen_object(struct odb_source *source,
  * object ID and the compatibility object ID, if non-NULL.
  */
 static inline int odb_source_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,

t/meson.build

@@ -427,6 +427,7 @@ integration_tests = [
   't3703-add-magic-pathspec.sh',
   't3704-add-pathspec-file.sh',
   't3705-add-sparse-checkout.sh',
+  't3706-add-4gb-file.sh',
   't3800-mktag.sh',
   't3900-i18n-commit.sh',
   't3901-i18n-patch.sh',

t/t3706-add-4gb-file.sh

@@ -0,0 +1,36 @@
+#!/bin/sh
+#
+# Copyright (c) 2026 Johannes Schindelin
+#
+
+test_description='add 4GB+ objects'
+
+. ./test-lib.sh
+
+if ! test_have_prereq EXPENSIVE,SIZE_T_IS_64BIT
+then
+	skip_all='expensive 4GB blob test; enable on 64-bit with GIT_TEST_LONG=true'
+	test_done
+fi
+
+size_4gb=4294967296
+
+test_expect_success 'set up a 4GB file' '
+	test_atexit "rm -f large" &&
+	# genrandom takes only an unsigned long...
+	test-tool genrandom 123 $(($size_4gb-1)) >large &&
+	printf 1 >>large
+'
+
+test_expect_success 'add 4GB file' '
+	git add large &&
+	git cat-file -s :large >size-staged &&
+	test $size_4gb = $(cat size-staged)
+'
+test_expect_success 'read 4GB loose object' '
+	git -P show :large >read &&
+	test_file_size read >size-read &&
+	test $size_4gb = $(cat size-read)
+'
+
+test_done