Merge branch 'jk/big-and-future-archive-tar'

"git archive" learned to handle files that are larger than 8GB and
commits far in the future than expressible by the traditional US-TAR
format.

* jk/big-and-future-archive-tar:
  archive-tar: drop return value
  archive-tar: write extended headers for far-future mtime
  archive-tar: write extended headers for file sizes >= 8GB
  t5000: test tar files that overflow ustar headers
  t9300: factor out portable "head -c" replacement

t/t5000-tar-tree.sh

@@ -319,4 +319,78 @@ test_expect_success 'catch non-matching pathspec' '
 	test_must_fail git archive -v HEAD -- "*.abc" >/dev/null
 '
 
+# Pull the size and date of each entry in a tarfile using the system tar.
+#
+# We'll pull out only the year from the date; that avoids any question of
+# timezones impacting the result (as long as we keep our test times away from a
+# year boundary; our reference times are all in August).
+#
+# The output of tar_info is expected to be "<size> <year>", both in decimal. It
+# ignores the return value of tar. We have to do this, because some of our test
+# input is only partial (the real data is 64GB in some cases).
+tar_info () {
+	"$TAR" tvf "$1" |
+	awk '{
+		split($4, date, "-")
+		print $3 " " date[1]
+	}'
+}
+
+# See if our system tar can handle a tar file with huge sizes and dates far in
+# the future, and that we can actually parse its output.
+#
+# The reference file was generated by GNU tar, and the magic time and size are
+# both octal 01000000000001, which overflows normal ustar fields.
+test_lazy_prereq TAR_HUGE '
+	echo "68719476737 4147" >expect &&
+	tar_info "$TEST_DIRECTORY"/t5000/huge-and-future.tar >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'set up repository with huge blob' '
+	obj_d=19 &&
+	obj_f=f9c8273ec45a8938e6999cb59b3ff66739902a &&
+	obj=${obj_d}${obj_f} &&
+	mkdir -p .git/objects/$obj_d &&
+	cp "$TEST_DIRECTORY"/t5000/$obj .git/objects/$obj_d/$obj_f &&
+	rm -f .git/index &&
+	git update-index --add --cacheinfo 100644,$obj,huge &&
+	git commit -m huge
+'
+
+# We expect git to die with SIGPIPE here (otherwise we
+# would generate the whole 64GB).
+test_expect_success 'generate tar with huge size' '
+	{
+		git archive HEAD
+		echo $? >exit-code
+	} | test_copy_bytes 4096 >huge.tar &&
+	echo 141 >expect &&
+	test_cmp expect exit-code
+'
+
+test_expect_success TAR_HUGE 'system tar can read our huge size' '
+	echo 68719476737 >expect &&
+	tar_info huge.tar | cut -d" " -f1 >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'set up repository with far-future commit' '
+	rm -f .git/index &&
+	echo content >file &&
+	git add file &&
+	GIT_COMMITTER_DATE="@68719476737 +0000" \
+		git commit -m "tempori parendum"
+'
+
+test_expect_success 'generate tar with future mtime' '
+	git archive HEAD >future.tar
+'
+
+test_expect_success TAR_HUGE 'system tar can read our future mtime' '
+	echo 4147 >expect &&
+	tar_info future.tar | cut -d" " -f2 >actual &&
+	test_cmp expect actual
+'
+
 test_done

t/t9300-fast-import.sh

@@ -7,23 +7,6 @@ test_description='test git fast-import utility'
 . ./test-lib.sh
 . "$TEST_DIRECTORY"/diff-lib.sh ;# test-lib chdir's into trash
 
-# Print $1 bytes from stdin to stdout.
-#
-# This could be written as "head -c $1", but IRIX "head" does not
-# support the -c option.
-head_c () {
-	perl -e '
-		my $len = $ARGV[1];
-		while ($len > 0) {
-			my $s;
-			my $nread = sysread(STDIN, $s, $len);
-			die "cannot read: $!" unless defined($nread);
-			print $s;
-			$len -= $nread;
-		}
-	' - "$1"
-}
-
 verify_packs () {
 	for p in .git/objects/pack/*.pack
 	do
@@ -2481,7 +2464,7 @@ test_expect_success PIPE 'R: copy using cat-file' '
 
 		read blob_id type size <&3 &&
 		echo "$blob_id $type $size" >response &&
-		head_c $size >blob <&3 &&
+		test_copy_bytes $size >blob <&3 &&
 		read newline <&3 &&
 
 		cat <<-EOF &&
@@ -2524,7 +2507,7 @@ test_expect_success PIPE 'R: print blob mid-commit' '
 		EOF
 
 		read blob_id type size <&3 &&
-		head_c $size >actual <&3 &&
+		test_copy_bytes $size >actual <&3 &&
 		read newline <&3 &&
 
 		echo
@@ -2559,7 +2542,7 @@ test_expect_success PIPE 'R: print staged blob within commit' '
 		echo "cat-blob $to_get" &&
 
 		read blob_id type size <&3 &&
-		head_c $size >actual <&3 &&
+		test_copy_bytes $size >actual <&3 &&
 		read newline <&3 &&
 
 		echo deleteall

t/test-lib-functions.sh

@@ -961,3 +961,17 @@ test_env () {
 		done
 	)
 }
+
+# Read up to "$1" bytes (or to EOF) from stdin and write them to stdout.
+test_copy_bytes () {
+	perl -e '
+		my $len = $ARGV[1];
+		while ($len > 0) {
+			my $s;
+			my $nread = sysread(STDIN, $s, $len);
+			die "cannot read: $!" unless defined($nread);
+			print $s;
+			$len -= $nread;
+		}
+	' - "$1"
+}