core: do not print invalid utf-8 in error messages

1 files changed, 26 insertions, 0 deletions

diff --git a/src/shared/utf8.c b/src/shared/utf8.c
index 6e5ba9abf4..0b524d8a90 100644
--- a/src/shared/utf8.c
+++ b/src/shared/utf8.c
@@ -174,6 +174,32 @@ const char *utf8_is_valid(const char *str) {
         return str;
 }
 
+char *utf8_escape_invalid(const char *str) {
+        char *p, *s;
+
+        assert(str);
+
+        p = s = malloc(strlen(str) * 4 + 1);
+        if (!p)
+                return NULL;
+
+        while (*str) {
+                int len;
+
+                len = utf8_encoded_valid_unichar(str);
+                if (len > 0) {
+                        s = mempcpy(s, str, len);
+                        str += len;
+                } else {
+                        s = mempcpy(s, UTF8_REPLACEMENT_CHARACTER, strlen(UTF8_REPLACEMENT_CHARACTER));
+                        str += 1;
+                }
+        }
+        *s = '\0';
+
+        return p;
+}
+
 char *ascii_is_valid(const char *str) {
         const char *p;