convert: add round trip check based on 'core.checkRoundtripEncoding'

UTF supports lossless conversion round tripping and conversions between
UTF and other encodings are mostly round trip safe as Unicode aims to be
a superset of all other character encodings. However, certain encodings
(e.g. SHIFT-JIS) are known to have round trip issues [1].

Add 'core.checkRoundtripEncoding', which contains a comma separated
list of encodings, to define for what encodings Git should check the
conversion round trip if they are used in the 'working-tree-encoding'
attribute.

Set SHIFT-JIS as default value for 'core.checkRoundtripEncoding'.

[1] https://support.microsoft.com/en-us/help/170559/prb-conversion-problem-between-shift-jis-and-unicode

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

1 files changed, 77 insertions, 0 deletions

diff --git a/convert.c b/convert.c
index bc35c33..1ae6301 100644
--- a/convert.c
+++ b/convert.c
@@ -347,6 +347,42 @@ static void trace_encoding(const char *context, const char *path,
 	strbuf_release(&trace);
 }
 
+static int check_roundtrip(const char *enc_name)
+{
+	/*
+	 * check_roundtrip_encoding contains a string of comma and/or
+	 * space separated encodings (eg. "UTF-16, ASCII, CP1125").
+	 * Search for the given encoding in that string.
+	 */
+	const char *found = strcasestr(check_roundtrip_encoding, enc_name);
+	const char *next;
+	int len;
+	if (!found)
+		return 0;
+	next = found + strlen(enc_name);
+	len = strlen(check_roundtrip_encoding);
+	return (found && (
+			/*
+			 * check that the found encoding is at the
+			 * beginning of check_roundtrip_encoding or
+			 * that it is prefixed with a space or comma
+			 */
+			found == check_roundtrip_encoding || (
+				(isspace(found[-1]) || found[-1] == ',')
+			)
+		) && (
+			/*
+			 * check that the found encoding is at the
+			 * end of check_roundtrip_encoding or
+			 * that it is suffixed with a space or comma
+			 */
+			next == check_roundtrip_encoding + len || (
+				next < check_roundtrip_encoding + len &&
+				(isspace(next[0]) || next[0] == ',')
+			)
+		));
+}
+
 static const char *default_encoding = "UTF-8";
 
 static int encode_to_git(const char *path, const char *src, size_t src_len,
@@ -395,6 +431,47 @@ static int encode_to_git(const char *path, const char *src, size_t src_len,
 	}
 	trace_encoding("destination", path, default_encoding, dst, dst_len);
 
+	/*
+	 * UTF supports lossless conversion round tripping [1] and conversions
+	 * between UTF and other encodings are mostly round trip safe as
+	 * Unicode aims to be a superset of all other character encodings.
+	 * However, certain encodings (e.g. SHIFT-JIS) are known to have round
+	 * trip issues [2]. Check the round trip conversion for all encodings
+	 * listed in core.checkRoundtripEncoding.
+	 *
+	 * The round trip check is only performed if content is written to Git.
+	 * This ensures that no information is lost during conversion to/from
+	 * the internal UTF-8 representation.
+	 *
+	 * Please note, the code below is not tested because I was not able to
+	 * generate a faulty round trip without an iconv error. Iconv errors
+	 * are already caught above.
+	 *
+	 * [1] http://unicode.org/faq/utf_bom.html#gen2
+	 * [2] https://support.microsoft.com/en-us/help/170559/prb-conversion-problem-between-shift-jis-and-unicode
+	 */
+	if (die_on_error && check_roundtrip(enc)) {
+		char *re_src;
+		int re_src_len;
+
+		re_src = reencode_string_len(dst, dst_len,
+					     enc, default_encoding,
+					     &re_src_len);
+
+		trace_printf("Checking roundtrip encoding for %s...\n", enc);
+		trace_encoding("reencoded source", path, enc,
+			       re_src, re_src_len);
+
+		if (!re_src || src_len != re_src_len ||
+		    memcmp(src, re_src, src_len)) {
+			const char* msg = _("encoding '%s' from %s to %s and "
+					    "back is not the same");
+			die(msg, path, enc, default_encoding);
+		}
+
+		free(re_src);
+	}
+
 	strbuf_attach(buf, dst, dst_len, dst_len + 1);
 	return 1;
 }