One typical use of a large binary file is to hold a sparse on-disk hash
table with a lot of holes. Help preserving the holes with lseek().
Signed-off-by: Junio C Hamano <gitster@xxxxxxxxx>
---
entry.c | 21 +++++++++++++++++++--
1 files changed, 19 insertions(+), 2 deletions(-)
diff --git a/entry.c b/entry.c
index 7733a6b..f751c60 100644
--- a/entry.c
+++ b/entry.c
@@ -123,6 +123,7 @@ static int streaming_write_entry(struct cache_entry *ce, char *path,
enum object_type type;
unsigned long sz;
int result = -1;
+ ssize_t kept = 0;
int fd = -1;
st = open_istream(ce->sha1, &type, &sz);
@@ -136,18 +137,34 @@ static int streaming_write_entry(struct cache_entry *ce, char *path,
goto close_and_exit;
for (;;) {
- char buf[10240];
- ssize_t wrote;
+ char buf[1024 * 16];
+ ssize_t wrote, holeto;
ssize_t readlen = read_istream(st, buf, sizeof(buf));
if (!readlen)
break;
+ if (sizeof(buf) == readlen) {
+ for (holeto = 0; holeto < readlen; holeto++)
+ if (buf[holeto])
+ break;
+ if (readlen == holeto) {
+ kept += holeto;
+ continue;
+ }
+ }
+ if (kept && lseek(fd, kept, SEEK_CUR) == (off_t) -1)
+ goto close_and_exit;
+ else
+ kept = 0;
wrote = write_in_full(fd, buf, readlen);
if (wrote != readlen)
goto close_and_exit;
}
+ if (kept && (lseek(fd, kept - 1, SEEK_CUR) == (off_t) -1 ||
+ write(fd, "", 1) != 1))
+ goto close_and_exit;
*fstat_done = fstat_output(fd, state, statbuf);
close_and_exit:
--
1.7.5.1.416.gac10c8
--
To unsubscribe from this list: send the line "unsubscribe git" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html