fast-export: do automatic reencoding of commit messages only if requested

Automatic re-encoding of commit messages (and dropping of the encoding
header) hurts attempts to do reversible history rewrites (e.g. sha1sum
<-> sha256sum transitions, some subtree rewrites), and seems
inconsistent with the general principle followed elsewhere in
fast-export of requiring explicit user requests to modify the output
(e.g. --signed-tags=strip, --tag-of-filtered-object=rewrite).  Add a
--reencode flag that the user can use to specify, and like other
fast-export flags, default it to 'abort'.

Signed-off-by: Elijah Newren <newren@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 35 insertions, 3 deletions

diff --git a/t/t9350-fast-export.sh b/t/t9350-fast-export.sh
index e2ab8eddc0..b4004e05c2 100755
--- a/t/t9350-fast-export.sh
+++ b/t/t9350-fast-export.sh
@@ -94,14 +94,14 @@ test_expect_success 'fast-export --show-original-ids | git fast-import' '
 	test $MUSS = $(git rev-parse --verify refs/tags/muss)
 '
 
-test_expect_success 'iso-8859-7' '
+test_expect_success 'reencoding iso-8859-7' '
 
 	test_when_finished "git reset --hard HEAD~1" &&
 	test_config i18n.commitencoding iso-8859-7 &&
 	test_tick &&
 	echo rosten >file &&
 	git commit -s -F "$TEST_DIRECTORY/t9350/simple-iso-8859-7-commit-message.txt" file &&
-	git fast-export wer^..wer >iso-8859-7.fi &&
+	git fast-export --reencode=yes wer^..wer >iso-8859-7.fi &&
 	sed "s/wer/i18n/" iso-8859-7.fi |
 		(cd new &&
 		 git fast-import &&
@@ -118,13 +118,45 @@ test_expect_success 'iso-8859-7' '
 		 ! grep ^encoding actual)
 '
 
+test_expect_success 'aborting on iso-8859-7' '
+
+	test_when_finished "git reset --hard HEAD~1" &&
+	test_config i18n.commitencoding iso-8859-7 &&
+	echo rosten >file &&
+	git commit -s -F "$TEST_DIRECTORY/t9350/simple-iso-8859-7-commit-message.txt" file &&
+	test_must_fail git fast-export --reencode=abort wer^..wer >iso-8859-7.fi
+'
+
+test_expect_success 'preserving iso-8859-7' '
+
+	test_when_finished "git reset --hard HEAD~1" &&
+	test_config i18n.commitencoding iso-8859-7 &&
+	echo rosten >file &&
+	git commit -s -F "$TEST_DIRECTORY/t9350/simple-iso-8859-7-commit-message.txt" file &&
+	git fast-export --reencode=no wer^..wer >iso-8859-7.fi &&
+	sed "s/wer/i18n-no-recoding/" iso-8859-7.fi |
+		(cd new &&
+		 git fast-import &&
+		 # The commit object, if not re-encoded, is 240 bytes.
+		 # Removing the "encoding iso-8859-7\n" header would drops 20
+		 # bytes.  Re-encoding the Pi character from \xF0 (\360) in
+		 # iso-8859-7 to \xCF\x80 (\317\200) in UTF-8 adds a byte.
+		 # Check for the expected size...
+		 test 240 -eq "$(git cat-file -s i18n-no-recoding)" &&
+		 # ...as well as the expected byte.
+		 git cat-file commit i18n-no-recoding >actual &&
+		 grep $(printf "\360") actual &&
+		 # Also make sure the commit has the "encoding" header
+		 grep ^encoding actual)
+'
+
 test_expect_success 'encoding preserved if reencoding fails' '
 
 	test_when_finished "git reset --hard HEAD~1" &&
 	test_config i18n.commitencoding iso-8859-7 &&
 	echo rosten >file &&
 	git commit -s -F "$TEST_DIRECTORY/t9350/broken-iso-8859-7-commit-message.txt" file &&
-	git fast-export wer^..wer >iso-8859-7.fi &&
+	git fast-export --reencode=yes wer^..wer >iso-8859-7.fi &&
 	sed "s/wer/i18n-invalid/" iso-8859-7.fi |
 		(cd new &&
 		 git fast-import &&