commit e650a842f69a783ed41a073df81eac7e8490b003
from: Omar Polo <op@omarpolo.com>
via: Thomas Adam <thomas@xteddy.org>
date: Wed Aug 06 12:48:03 2025 UTC

improve binary blob detection

just like the change just done in diff.git, consider a blob binary
if it has any control character (except for the tabs)

joint work with jtt@, ok stsp@

commit - c1e3a5dcf911a2de8acb7b561ae0431563f5c456
commit + e650a842f69a783ed41a073df81eac7e8490b003
blob - eab399777a9e609d5c47a051ccb6670648eb8fb3
blob + 3587c86ce3d30a31f0f14059600eb50a93afc294
--- lib/object.c
+++ lib/object.c
@@ -22,6 +22,7 @@
 #include <sys/uio.h>
 #include <sys/mman.h>
 
+#include <ctype.h>
 #include <errno.h>
 #include <fcntl.h>
 #include <stdio.h>
@@ -373,7 +374,7 @@ const struct got_error *
 got_object_blob_is_binary(int *binary, struct got_blob_object *blob)
 {
 	const struct got_error *err;
-	size_t hdrlen, len;
+	size_t hdrlen, len, i;
 
 	*binary = 0;
 	hdrlen = got_object_blob_get_hdrlen(blob);
@@ -385,7 +386,13 @@ got_object_blob_is_binary(int *binary, struct got_blob
 	if (err)
 		return err;
 
-	*binary = memchr(blob->read_buf, '\0', len) != NULL;
+	for (i = 0; i < len; ++i) {
+		if (iscntrl((unsigned char)blob->read_buf[i]) &&
+		    !isspace((unsigned char)blob->read_buf[i])) {
+			*binary = 1;
+			break;
+		}
+	}
 
 	if (fseeko(blob->f, hdrlen, SEEK_SET) == -1)
 		return got_error_from_errno("fseeko");