convert: check for detectable errors in UTF encodings

Check that new content is valid with respect to the user defined
'working-tree-encoding' attribute.

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

1 files changed, 61 insertions, 0 deletions

diff --git a/convert.c b/convert.c
index 21d5cb60da..0e7930c154 100644
--- a/convert.c
+++ b/convert.c
@@ -266,6 +266,64 @@ static int will_convert_lf_to_crlf(size_t len, struct text_stat *stats,
 
 }
 
+static int validate_encoding(const char *path, const char *enc,
+		      const char *data, size_t len, int die_on_error)
+{
+	/* We only check for UTF here as UTF?? can be an alias for UTF-?? */
+	if (istarts_with(enc, "UTF")) {
+		/*
+		 * Check for detectable errors in UTF encodings
+		 */
+		if (has_prohibited_utf_bom(enc, data, len)) {
+			const char *error_msg = _(
+				"BOM is prohibited in '%s' if encoded as %s");
+			/*
+			 * This advice is shown for UTF-??BE and UTF-??LE encodings.
+			 * We cut off the last two characters of the encoding name
+			 * to generate the encoding name suitable for BOMs.
+			 */
+			const char *advise_msg = _(
+				"The file '%s' contains a byte order "
+				"mark (BOM). Please use UTF-%s as "
+				"working-tree-encoding.");
+			const char *stripped = NULL;
+			char *upper = xstrdup_toupper(enc);
+			upper[strlen(upper)-2] = '\0';
+			if (!skip_prefix(upper, "UTF-", &stripped))
+				skip_prefix(stripped, "UTF", &stripped);
+			advise(advise_msg, path, stripped);
+			free(upper);
+			if (die_on_error)
+				die(error_msg, path, enc);
+			else {
+				return error(error_msg, path, enc);
+			}
+
+		} else if (is_missing_required_utf_bom(enc, data, len)) {
+			const char *error_msg = _(
+				"BOM is required in '%s' if encoded as %s");
+			const char *advise_msg = _(
+				"The file '%s' is missing a byte order "
+				"mark (BOM). Please use UTF-%sBE or UTF-%sLE "
+				"(depending on the byte order) as "
+				"working-tree-encoding.");
+			const char *stripped = NULL;
+			char *upper = xstrdup_toupper(enc);
+			if (!skip_prefix(upper, "UTF-", &stripped))
+				skip_prefix(stripped, "UTF", &stripped);
+			advise(advise_msg, path, stripped, stripped);
+			free(upper);
+			if (die_on_error)
+				die(error_msg, path, enc);
+			else {
+				return error(error_msg, path, enc);
+			}
+		}
+
+	}
+	return 0;
+}
+
 static const char *default_encoding = "UTF-8";
 
 static int encode_to_git(const char *path, const char *src, size_t src_len,
@@ -291,6 +349,9 @@ static int encode_to_git(const char *path, const char *src, size_t src_len,
 	if (!buf && !src)
 		return 1;
 
+	if (validate_encoding(path, enc, src, src_len, die_on_error))
+		return 0;
+
 	dst = reencode_string_len(src, src_len, default_encoding, enc,
 				  &dst_len);
 	if (!dst) {