interpret-trailers: add an option to unfold values

The point of "--only-trailers" is to give a caller an output
that's easy for them to parse. Getting rid of the
non-trailer material helps, but we still may see more
complicated syntax like whitespace continuation. Let's add
an option to unfold any continuation, giving the output as a
single "key: value" line per trailer.

As a bonus, this could be used even without --only-trailers
to clean up unusual formatting in the incoming data.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

5 files changed, 56 insertions, 0 deletions

diff --git a/Documentation/git-interpret-trailers.txt b/Documentation/git-interpret-trailers.txt
index 7cc43b0e3e..be948e8028 100644
--- a/Documentation/git-interpret-trailers.txt
+++ b/Documentation/git-interpret-trailers.txt
@@ -88,6 +88,10 @@ OPTIONS
 	from the command-line or by following configured `trailer.*`
 	rules.
 
+--unfold::
+	Remove any whitespace-continuation in trailers, so that each
+	trailer appears on a line by itself with its full content.
+
 CONFIGURATION VARIABLES
 -----------------------
 
diff --git a/builtin/interpret-trailers.c b/builtin/interpret-trailers.c
index 2d90e0e480..922c3bad63 100644
--- a/builtin/interpret-trailers.c
+++ b/builtin/interpret-trailers.c
@@ -26,6 +26,7 @@ int cmd_interpret_trailers(int argc, const char **argv, const char *prefix)
 		OPT_BOOL(0, "trim-empty", &opts.trim_empty, N_("trim empty trailers")),
 		OPT_BOOL(0, "only-trailers", &opts.only_trailers, N_("output only the trailers")),
 		OPT_BOOL(0, "only-input", &opts.only_input, N_("do not apply config rules")),
+		OPT_BOOL(0, "unfold", &opts.unfold, N_("join whitespace-continued values")),
 		OPT_STRING_LIST(0, "trailer", &trailers, N_("trailer"),
 				N_("trailer(s) to add")),
 		OPT_END()
diff --git a/t/t7513-interpret-trailers.sh b/t/t7513-interpret-trailers.sh
index 94b6c52473..baf2feba98 100755
--- a/t/t7513-interpret-trailers.sh
+++ b/t/t7513-interpret-trailers.sh
@@ -1330,4 +1330,25 @@ test_expect_success 'only input' '
 	test_cmp expected actual
 '
 
+test_expect_success 'unfold' '
+	cat >expected <<-\EOF &&
+		foo: continued across several lines
+	EOF
+	# pass through tr to make leading and trailing whitespace more obvious
+	tr _ " " <<-\EOF |
+		my subject
+
+		my body
+
+		foo:_
+		__continued
+		___across
+		____several
+		_____lines
+		___
+	EOF
+	git interpret-trailers --only-trailers --only-input --unfold >actual &&
+	test_cmp expected actual
+'
+
 test_done
diff --git a/trailer.c b/trailer.c
index 847417ef89..e63f432947 100644
--- a/trailer.c
+++ b/trailer.c
@@ -886,6 +886,33 @@ static int ends_with_blank_line(const char *buf, size_t len)
 	return is_blank_line(buf + ll);
 }
 
+static void unfold_value(struct strbuf *val)
+{
+	struct strbuf out = STRBUF_INIT;
+	size_t i;
+
+	strbuf_grow(&out, val->len);
+	i = 0;
+	while (i < val->len) {
+		char c = val->buf[i++];
+		if (c == '\n') {
+			/* Collapse continuation down to a single space. */
+			while (i < val->len && isspace(val->buf[i]))
+				i++;
+			strbuf_addch(&out, ' ');
+		} else {
+			strbuf_addch(&out, c);
+		}
+	}
+
+	/* Empty lines may have left us with whitespace cruft at the edges */
+	strbuf_trim(&out);
+
+	/* output goes back to val as if we modified it in-place */
+	strbuf_swap(&out, val);
+	strbuf_release(&out);
+}
+
 static int process_input_file(FILE *outfile,
 			      const char *str,
 			      struct list_head *head,
@@ -914,6 +941,8 @@ static int process_input_file(FILE *outfile,
 		if (separator_pos >= 1) {
 			parse_trailer(&tok, &val, NULL, trailer,
 				      separator_pos);
+			if (opts->unfold)
+				unfold_value(&val);
 			add_trailer_item(head,
 					 strbuf_detach(&tok, NULL),
 					 strbuf_detach(&val, NULL));
diff --git a/trailer.h b/trailer.h
index 76c3b571bf..194f85a102 100644
--- a/trailer.h
+++ b/trailer.h
@@ -27,6 +27,7 @@ struct process_trailer_options {
 	int trim_empty;
 	int only_trailers;
 	int only_input;
+	int unfold;
 };
 
 #define PROCESS_TRAILER_OPTIONS_INIT {0}