csum-file: introduce sha1file_checkpoint

It is useful to be able to rewind a check-summed file to a certain
previous state after writing data into it using sha1write() API. The
fast-import command does this after streaming a blob data to the packfile
being generated and then noticing that the same blob has already been
written, and it does this with a private code truncate_pack() that is
commented as "Yes, this is a layering violation".

Introduce two API functions, sha1file_checkpoint(), that allows the caller
to save a state of a sha1file, and then later revert it to the saved state.
Use it to reimplement truncate_pack().

Signed-off-by: Junio C Hamano <[email protected]>

Author: gitster

csum-file.c

@@ -158,6 +158,26 @@ struct sha1file *sha1fd_throughput(int fd, const char *name, struct progress *tp
 	return f;
 }
 
+void sha1file_checkpoint(struct sha1file *f, struct sha1file_checkpoint *checkpoint)
+{
+	sha1flush(f);
+	checkpoint->offset = f->total;
+	checkpoint->ctx = f->ctx;
+}
+
+int sha1file_truncate(struct sha1file *f, struct sha1file_checkpoint *checkpoint)
+{
+	off_t offset = checkpoint->offset;
+
+	if (ftruncate(f->fd, offset) ||
+	    lseek(f->fd, offset, SEEK_SET) != offset)
+		return -1;
+	f->total = offset;
+	f->ctx = checkpoint->ctx;
+	f->offset = 0; /* sha1flush() was called in checkpoint */
+	return 0;
+}
+
 void crc32_begin(struct sha1file *f)
 {
 	f->crc32 = crc32(0, NULL, 0);

csum-file.h

@@ -17,6 +17,15 @@ struct sha1file {
 	unsigned char buffer[8192];
 };
 
+/* Checkpoint */
+struct sha1file_checkpoint {
+	off_t offset;
+	git_SHA_CTX ctx;
+};
+
+extern void sha1file_checkpoint(struct sha1file *, struct sha1file_checkpoint *);
+extern int sha1file_truncate(struct sha1file *, struct sha1file_checkpoint *);
+
 /* sha1close flags */
 #define CSUM_CLOSE	1
 #define CSUM_FSYNC	2

fast-import.c

@@ -1143,17 +1143,11 @@ static int store_object(
 	return 0;
 }
 
-static void truncate_pack(off_t to, git_SHA_CTX *ctx)
+static void truncate_pack(struct sha1file_checkpoint *checkpoint)
 {
-	if (ftruncate(pack_data->pack_fd, to)
-	 || lseek(pack_data->pack_fd, to, SEEK_SET) != to)
+	if (sha1file_truncate(pack_file, checkpoint))
 		die_errno("cannot truncate pack to skip duplicate");
-	pack_size = to;
-
-	/* yes this is a layering violation */
-	pack_file->total = to;
-	pack_file->offset = 0;
-	pack_file->ctx = *ctx;
+	pack_size = checkpoint->offset;
 }
 
 static void stream_blob(uintmax_t len, unsigned char *sha1out, uintmax_t mark)
@@ -1166,20 +1160,17 @@ static void stream_blob(uintmax_t len, unsigned char *sha1out, uintmax_t mark)
 	unsigned long hdrlen;
 	off_t offset;
 	git_SHA_CTX c;
-	git_SHA_CTX pack_file_ctx;
 	git_zstream s;
+	struct sha1file_checkpoint checkpoint;
 	int status = Z_OK;
 
 	/* Determine if we should auto-checkpoint. */
 	if ((max_packsize && (pack_size + 60 + len) > max_packsize)
 		|| (pack_size + 60 + len) < pack_size)
 		cycle_packfile();
 
-	offset = pack_size;
-
-	/* preserve the pack_file SHA1 ctx in case we have to truncate later */
-	sha1flush(pack_file);
-	pack_file_ctx = pack_file->ctx;
+	sha1file_checkpoint(pack_file, &checkpoint);
+	offset = checkpoint.offset;
 
 	hdrlen = snprintf((char *)out_buf, out_sz, "blob %" PRIuMAX, len) + 1;
 	if (out_sz <= hdrlen)
@@ -1245,14 +1236,14 @@ static void stream_blob(uintmax_t len, unsigned char *sha1out, uintmax_t mark)
 
 	if (e->idx.offset) {
 		duplicate_count_by_type[OBJ_BLOB]++;
-		truncate_pack(offset, &pack_file_ctx);
+		truncate_pack(&checkpoint);
 
 	} else if (find_sha1_pack(sha1, packed_git)) {
 		e->type = OBJ_BLOB;
 		e->pack_id = MAX_PACK_ID;
 		e->idx.offset = 1; /* just not zero! */
 		duplicate_count_by_type[OBJ_BLOB]++;
-		truncate_pack(offset, &pack_file_ctx);
+		truncate_pack(&checkpoint);
 
 	} else {
 		e->depth = 0;