fast-export: avoid stripping encoding header if we cannot reencode

When fast-export encounters a commit with an 'encoding' header, it tries
to reencode in utf-8 and then drops the encoding header.  However, if it
fails to reencode in utf-8 because e.g. one of the characters in the
commit message was invalid in the old encoding, then we need to retain
the original encoding or otherwise we lose information needed to
understand all the other (valid) characters in the original commit
message.

Signed-off-by: Elijah Newren <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: newren

builtin/fast-export.c

@@ -642,9 +642,12 @@ static void handle_commit(struct commit *commit, struct rev_info *rev,
 	printf("commit %s\nmark :%"PRIu32"\n", refname, last_idnum);
 	if (show_original_ids)
 		printf("original-oid %s\n", oid_to_hex(&commit->object.oid));
-	printf("%.*s\n%.*s\ndata %u\n%s",
+	printf("%.*s\n%.*s\n",
 	       (int)(author_end - author), author,
-	       (int)(committer_end - committer), committer,
+	       (int)(committer_end - committer), committer);
+	if (!reencoded && encoding)
+		printf("encoding %s\n", encoding);
+	printf("data %u\n%s",
 	       (unsigned)(reencoded
 			  ? strlen(reencoded) : message
 			  ? strlen(message) : 0),

t/t9350-fast-export.sh

@@ -120,6 +120,23 @@ test_expect_success 'iso-8859-7' '
 		 ! 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 "$TEST_DIRECTORY/t9350/broken-iso-8859-7-commit-message.txt" file &&
+	git fast-export wer^..wer >iso-8859-7.fi &&
+	sed "s/wer/i18n-invalid/" iso-8859-7.fi |
+		(cd new &&
+		 git fast-import &&
+		 git cat-file commit i18n-invalid >actual &&
+		 grep ^encoding actual &&
+		 # Also verify that the commit has the expected size; i.e.
+		 # that no bytes were re-encoded to a different encoding.
+		 test 252 -eq "$(git cat-file -s i18n-invalid)")
+'
+
 test_expect_success 'import/export-marks' '
 
 	git checkout -b marks master &&

t/t9350/broken-iso-8859-7-commit-message.txt

@@ -0,0 +1 @@
+Pi: �; Invalid: �