fixed searches in single-byte encoded documents

* while code is guaranteed to be in valid UTF-8, this cannot be
  said about the result of string building.
* The search pattern can end up with invalid Unicode bytes even when
  searching on UTF-8 buffers, e.g. if ^EQq inserts garbage.
  There are currently no checks.
* When searching on a raw buffer, it must be possible to
  search for arbitrary bytes (^EUq).
  Since teco_pattern2regexp() was always expecting clean UTF-8 input,
  this would sometimes skip over too many bytes and could even crash.
* Instead, teco_pattern2regexp() now takes the <S> target codepage
  into account.

1 files changed, 5 insertions, 11 deletions

diff --git a/src/parser.c b/src/parser.c
index 321803a..3c37f81 100644
--- a/src/parser.c
+++ b/src/parser.c
@@ -158,17 +158,11 @@ gboolean
 teco_execute_macro(const gchar *macro, gsize macro_len,
                    teco_qreg_table_t *qreg_table_locals, GError **error)
 {
-	/*
-	 * Validate UTF-8, but accept null bytes.
-	 * NOTE: there is g_utf8_validate_len() in Glib 2.60
-	 */
-	const gchar *p = macro;
-	while (!g_utf8_validate(p, macro_len - (p - macro), &p) && !*p)
-		p++;
-	if (p - macro < macro_len) {
-		g_set_error(error, TECO_ERROR, TECO_ERROR_CODEPOINT,
-		            "Invalid UTF-8 byte sequence at %" G_GSIZE_FORMAT,
-		            p - macro);
+	const teco_string_t str = {(gchar *)macro, macro_len};
+
+	if (!teco_string_validate_utf8(&str)) {
+		g_set_error_literal(error, TECO_ERROR, TECO_ERROR_CODEPOINT,
+		                    "Invalid UTF-8 byte sequence in macro");
 		return FALSE;
 	}