Allow mailsplit (and hence git-am) to handle mails with CRLF line-endings

It is not that uncommon to have mails with DOS line-ending, notably
Thunderbird and web mailers like Gmail (when saving what they call
"original" message).  So modify mailsplit to convert CRLF line-endings to
just LF.

Since git-rebase is built on top of git-am, add an option to mailsplit to
be used by git-am when it is acting on behalf of git-rebase, to refrain
from doing this conversion.

And add a test to make sure that rebase still works.

Signed-off-by: Brandon Casey <drafnel@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

3 files changed, 40 insertions, 3 deletions

diff --git a/builtin-mailsplit.c b/builtin-mailsplit.c
index d288fde2c..ee6ca0ebc 100644
--- a/builtin-mailsplit.c
+++ b/builtin-mailsplit.c
@@ -44,6 +44,7 @@ static int is_from_line(const char *line, int len)
 }
 
 static struct strbuf buf = STRBUF_INIT;
+static int keep_cr;
 
 /* Called with the first line (potentially partial)
  * already in buf[] -- normally that should begin with
@@ -69,6 +70,12 @@ static int split_one(FILE *mbox, const char *name, int allow_bare)
 	 * "From " and having something that looks like a date format.
 	 */
 	for (;;) {
+		if (!keep_cr && buf.len > 1 && buf.buf[buf.len-1] == '\n' &&
+			buf.buf[buf.len-2] == '\r') {
+			strbuf_setlen(&buf, buf.len-2);
+			strbuf_addch(&buf, '\n');
+		}
+
 		if (fwrite(buf.buf, 1, buf.len, output) != buf.len)
 			die_errno("cannot write output");
 
@@ -226,6 +233,8 @@ int cmd_mailsplit(int argc, const char **argv, const char *prefix)
 			nr = strtol(arg+2, NULL, 10);
 		} else if ( arg[1] == 'b' && !arg[2] ) {
 			allow_bare = 1;
+		} else if (!strcmp(arg, "--keep-cr")) {
+			keep_cr = 1;
 		} else if ( arg[1] == 'o' && arg[2] ) {
 			dir = arg+2;
 		} else if ( arg[1] == '-' && !arg[2] ) {
diff --git a/git-am.sh b/git-am.sh
index d64d99753..985226bfe 100755
--- a/git-am.sh
+++ b/git-am.sh
@@ -197,7 +197,13 @@ check_patch_format () {
 split_patches () {
 	case "$patch_format" in
 	mbox)
-		git mailsplit -d"$prec" -o"$dotest" -b -- "$@" > "$dotest/last" ||
+		case "$rebasing" in
+		'')
+			keep_cr= ;;
+		?*)
+			keep_cr=--keep-cr ;;
+		esac
+		git mailsplit -d"$prec" -o"$dotest" -b $keep_cr -- "$@" > "$dotest/last" ||
 		clean_abort
 		;;
 	stgit-series)
diff --git a/t/t3400-rebase.sh b/t/t3400-rebase.sh
index c5c29ccc4..4e6a44b62 100755
--- a/t/t3400-rebase.sh
+++ b/t/t3400-rebase.sh
@@ -3,9 +3,10 @@
 # Copyright (c) 2005 Amos Waterland
 #
 
-test_description='git rebase should not destroy author information
+test_description='git rebase assorted tests
 
-This test runs git rebase and checks that the author information is not lost.
+This test runs git rebase and checks that the author information is not lost
+among other things.
 '
 . ./test-lib.sh
 
@@ -133,4 +134,25 @@ test_expect_success 'rebase -q is quiet' '
      test ! -s output.out
 '
 
+q_to_cr () {
+	tr Q '\015'
+}
+
+test_expect_success 'Rebase a commit that sprinkles CRs in' '
+	(
+		echo "One"
+		echo "TwoQ"
+		echo "Three"
+		echo "FQur"
+		echo "Five"
+	) | q_to_cr >CR &&
+	git add CR &&
+	test_tick &&
+	git commit -a -m "A file with a line with CR" &&
+	git tag file-with-cr &&
+	git checkout HEAD^0 &&
+	git rebase --onto HEAD^^ HEAD^ &&
+	git diff --exit-code file-with-cr:CR HEAD:CR
+'
+
 test_done