Merge branch 'jk/read-commit-buffer-data-after-free'

"git log --grep=<pattern>" used to look for the pattern in literal
bytes of the commit log message and ignored the log-output encoding.

* jk/read-commit-buffer-data-after-free:
  log: re-encode commit messages before grepping

1 files changed, 58 insertions, 0 deletions

diff --git a/t/t4210-log-i18n.sh b/t/t4210-log-i18n.sh
new file mode 100755
index 0000000000..52a74729ba
--- /dev/null
+++ b/t/t4210-log-i18n.sh
@@ -0,0 +1,58 @@
+#!/bin/sh
+
+test_description='test log with i18n features'
+. ./test-lib.sh
+
+# two forms of é
+utf8_e=$(printf '\303\251')
+latin1_e=$(printf '\351')
+
+test_expect_success 'create commits in different encodings' '
+	test_tick &&
+	cat >msg <<-EOF &&
+	utf8
+
+	t${utf8_e}st
+	EOF
+	git add msg &&
+	git -c i18n.commitencoding=utf8 commit -F msg &&
+	cat >msg <<-EOF &&
+	latin1
+
+	t${latin1_e}st
+	EOF
+	git add msg &&
+	git -c i18n.commitencoding=ISO-8859-1 commit -F msg
+'
+
+test_expect_success 'log --grep searches in log output encoding (utf8)' '
+	cat >expect <<-\EOF &&
+	latin1
+	utf8
+	EOF
+	git log --encoding=utf8 --format=%s --grep=$utf8_e >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'log --grep searches in log output encoding (latin1)' '
+	cat >expect <<-\EOF &&
+	latin1
+	utf8
+	EOF
+	git log --encoding=ISO-8859-1 --format=%s --grep=$latin1_e >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'log --grep does not find non-reencoded values (utf8)' '
+	>expect &&
+	git log --encoding=utf8 --format=%s --grep=$latin1_e >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'log --grep does not find non-reencoded values (latin1)' '
+	>expect &&
+	git log --encoding=ISO-8859-1 --format=%s --grep=$utf8_e >actual &&
+	test_cmp expect actual
+'
+
+test_done