convert: add tracing for 'working-tree-encoding' attribute

Add the GIT_TRACE_WORKING_TREE_ENCODING environment variable to enable
tracing for content that is reencoded with the 'working-tree-encoding'
attribute. This is useful to debug encoding issues.

Signed-off-by: Lars Schneider <larsxschneider@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 25 insertions, 0 deletions

diff --git a/convert.c b/convert.c
index 0e7930c154..bc35c33249 100644
--- a/convert.c
+++ b/convert.c
@@ -324,6 +324,29 @@ static int validate_encoding(const char *path, const char *enc,
 	return 0;
 }
 
+static void trace_encoding(const char *context, const char *path,
+			   const char *encoding, const char *buf, size_t len)
+{
+	static struct trace_key coe = TRACE_KEY_INIT(WORKING_TREE_ENCODING);
+	struct strbuf trace = STRBUF_INIT;
+	int i;
+
+	strbuf_addf(&trace, "%s (%s, considered %s):\n", context, path, encoding);
+	for (i = 0; i < len && buf; ++i) {
+		strbuf_addf(
+			&trace,"| \e[2m%2i:\e[0m %2x \e[2m%c\e[0m%c",
+			i,
+			(unsigned char) buf[i],
+			(buf[i] > 32 && buf[i] < 127 ? buf[i] : ' '),
+			((i+1) % 8 && (i+1) < len ? ' ' : '\n')
+		);
+	}
+	strbuf_addchars(&trace, '\n', 1);
+
+	trace_strbuf(&coe, &trace);
+	strbuf_release(&trace);
+}
+
 static const char *default_encoding = "UTF-8";
 
 static int encode_to_git(const char *path, const char *src, size_t src_len,
@@ -352,6 +375,7 @@ static int encode_to_git(const char *path, const char *src, size_t src_len,
 	if (validate_encoding(path, enc, src, src_len, die_on_error))
 		return 0;
 
+	trace_encoding("source", path, enc, src, src_len);
 	dst = reencode_string_len(src, src_len, default_encoding, enc,
 				  &dst_len);
 	if (!dst) {
@@ -369,6 +393,7 @@ static int encode_to_git(const char *path, const char *src, size_t src_len,
 			return 0;
 		}
 	}
+	trace_encoding("destination", path, default_encoding, dst, dst_len);
 
 	strbuf_attach(buf, dst, dst_len, dst_len + 1);
 	return 1;