diff --stat: mark any file larger than core.bigfilethreshold binary

Too large files may lead to failure to allocate memory. If it happens
here, it could impact quite a few commands that involve
diff. Moreover, too large files are inefficient to compare anyway (and
most likely non-text), so mark them binary and skip looking at their
content.

Noticed-by: Dale R. Worley <worley@alum.mit.edu>
Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

Documentation/config.txt

@@ -499,7 +499,8 @@ core.bigFileThreshold::
 	Files larger than this size are stored deflated, without
 	attempting delta compression.  Storing large files without
 	delta compression avoids excessive memory usage, at the
-	slight expense of increased disk usage.
+	slight expense of increased disk usage. Additionally files
+	larger than this size are always treated as binary.
 +
 Default is 512 MiB on all platforms.  This should be reasonable
 for most projects as source code and other text files can still

Documentation/gitattributes.txt

@@ -440,8 +440,8 @@ Unspecified::
 
 	A path to which the `diff` attribute is unspecified
 	first gets its contents inspected, and if it looks like
-	text, it is treated as text.  Otherwise it would
+	text and is smaller than core.bigFileThreshold, it is treated
-	generate `Binary files differ`.
+	as text. Otherwise it would generate `Binary files differ`.
 
 String::
 

diff.c

@@ -2188,8 +2188,8 @@ int diff_filespec_is_binary(struct diff_filespec *one)
 			one->is_binary = one->driver->binary;
 		else {
 			if (!one->data && DIFF_FILE_VALID(one))
-				diff_populate_filespec(one, 0);
+				diff_populate_filespec(one, CHECK_BINARY);
-			if (one->data)
+			if (one->is_binary == -1 && one->data)
 				one->is_binary = buffer_is_binary(one->data,
 						one->size);
 			if (one->is_binary == -1)
@@ -2725,6 +2725,11 @@ int diff_populate_filespec(struct diff_filespec *s, unsigned int flags)
 		}
 		if (size_only)
 			return 0;
+		if ((flags & CHECK_BINARY) &&
+		    s->size > big_file_threshold && s->is_binary == -1) {
+			s->is_binary = 1;
+			return 0;
+		}
 		fd = open(s->path, O_RDONLY);
 		if (fd < 0)
 			goto err_empty;
@@ -2746,16 +2751,21 @@ int diff_populate_filespec(struct diff_filespec *s, unsigned int flags)
 	}
 	else {
 		enum object_type type;
-		if (size_only) {
+		if (size_only || (flags & CHECK_BINARY)) {
 			type = sha1_object_info(s->sha1, &s->size);
 			if (type < 0)
 				die("unable to read %s", sha1_to_hex(s->sha1));
-		} else {
+			if (size_only)
-			s->data = read_sha1_file(s->sha1, &type, &s->size);
+				return 0;
-			if (!s->data)
+			if (s->size > big_file_threshold && s->is_binary == -1) {
-				die("unable to read %s", sha1_to_hex(s->sha1));
+				s->is_binary = 1;
-			s->should_free = 1;
+				return 0;
+			}
 		}
+		s->data = read_sha1_file(s->sha1, &type, &s->size);
+		if (!s->data)
+			die("unable to read %s", sha1_to_hex(s->sha1));
+		s->should_free = 1;
 	}
 	return 0;
 }

diffcore.h

@@ -56,6 +56,7 @@ extern void fill_filespec(struct diff_filespec *, const unsigned char *,
 			  int, unsigned short);
 
 #define CHECK_SIZE_ONLY 1
+#define CHECK_BINARY    2
 extern int diff_populate_filespec(struct diff_filespec *, unsigned int);
 extern void diff_free_filespec_data(struct diff_filespec *);
 extern void diff_free_filespec_blob(struct diff_filespec *);

t/t1050-large.sh

@@ -112,6 +112,10 @@ test_expect_success 'diff --raw' '
 	git diff --raw HEAD^
 '
 
+test_expect_success 'diff --stat' '
+	git diff --stat HEAD^ HEAD
+'
+
 test_expect_success 'hash-object' '
 	git hash-object large1
 '