Merge branch 'en/diffstat-utf8-truncation-fix' into seenseen

The computation to shorten the filenames shown in diffstat measured
width of individual UTF-8 characters to add up, but forgot to take
into account error cases (e.g., an invalid UTF-8 sequence, or a
control character).

* en/diffstat-utf8-truncation-fix:
  diff: fix out-of-bounds reads and NULL deref in diffstat UTF-8 truncation

1 files changed, 25 insertions, 0 deletions

diff --git a/t/t4052-stat-output.sh b/t/t4052-stat-output.sh
index 7c749062e2..84c53c1a51 100755
--- a/t/t4052-stat-output.sh
+++ b/t/t4052-stat-output.sh
@@ -445,4 +445,29 @@ test_expect_success 'diffstat where line_prefix contains ANSI escape codes is co
 	test_grep "<RED>|<RESET>  ${FILENAME_TRIMMED} | 0" out
 '
 
+test_expect_success 'diffstat truncation with invalid UTF-8 does not crash' '
+	empty_blob=$(git hash-object -w --stdin </dev/null) &&
+	printf "100644 blob $empty_blob\taaa-\300-aaa\n" |
+	git mktree >tree_file &&
+	tree=$(cat tree_file) &&
+	empty_tree=$(git mktree </dev/null) &&
+	c1=$(git commit-tree -m before $empty_tree) &&
+	c2=$(git commit-tree -m after -p $c1 $tree) &&
+	git -c core.quotepath=false diff --stat --stat-name-width=5 $c1..$c2 >output &&
+	test_grep "| 0" output
+'
+
+test_expect_success FUNNYNAMES 'diffstat truncation with control chars does not crash' '
+	FNAME=$(printf "aaa-\x01-aaa") &&
+	git commit --allow-empty -m setup &&
+	>$FNAME &&
+	git add -- $FNAME &&
+	git commit -m "add file with control char name" &&
+	git -c core.quotepath=false diff --stat --stat-name-width=5 HEAD~1..HEAD >output &&
+	test_grep "| 0" output &&
+	rm -- $FNAME &&
+	git rm -- $FNAME &&
+	git commit -m "remove test file"
+'
+
 test_done