diff mbox series

[v2,3/5] fast-export: avoid stripping encoding header if we cannot reencode

Message ID 20190430182523.3339-4-newren@gmail.com (mailing list archive)
State New, archived
Headers show
Series Fix and extend encoding handling in fast export/import | expand

Commit Message

Elijah Newren April 30, 2019, 6:25 p.m. UTC
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 <newren@gmail.com>
---
 builtin/fast-export.c  |  7 +++++--
 t/t9350-fast-export.sh | 14 ++++++++++++++
 2 files changed, 19 insertions(+), 2 deletions(-)
diff mbox series

Patch

diff --git a/builtin/fast-export.c b/builtin/fast-export.c
index 9e283482ef..7734a9f5a5 100644
--- a/builtin/fast-export.c
+++ b/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),
diff --git a/t/t9350-fast-export.sh b/t/t9350-fast-export.sh
index f55759651a..67dd7ac7f4 100755
--- a/t/t9350-fast-export.sh
+++ b/t/t9350-fast-export.sh
@@ -109,6 +109,20 @@  test_expect_success 'iso-8859-7' '
 		 grep $(printf "\317\200") 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 -m "$(printf "Pi: \360; Invalid: \377")" 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)
+'
+
 test_expect_success 'import/export-marks' '
 
 	git checkout -b marks master &&