From 3c6d3052d3597100e9d531df03cb15e9988dc94d Mon Sep 17 00:00:00 2001
From: Lennart Poettering <lennart@poettering.net>
Date: Thu, 4 Dec 2014 02:27:14 +0100
Subject: [PATCH] utf8: when escaping unprintable unichars, escape the whole
 unichar, not just the first byte of it

---
 src/shared/utf8.c    | 12 ++++++------
 src/test/test-utf8.c |  7 +++++--
 2 files changed, 11 insertions(+), 8 deletions(-)

diff --git a/src/shared/utf8.c b/src/shared/utf8.c
index 0b6c38ebb..699682010 100644
--- a/src/shared/utf8.c
+++ b/src/shared/utf8.c
@@ -202,7 +202,7 @@ char *utf8_escape_invalid(const char *str) {
                         s = mempcpy(s, str, len);
                         str += len;
                 } else {
-                        s = mempcpy(s, UTF8_REPLACEMENT_CHARACTER, strlen(UTF8_REPLACEMENT_CHARACTER));
+                        s = stpcpy(s, UTF8_REPLACEMENT_CHARACTER);
                         str += 1;
                 }
         }
@@ -230,18 +230,18 @@ char *utf8_escape_non_printable(const char *str) {
                                 s = mempcpy(s, str, len);
                                 str += len;
                         } else {
-                                if ((*str < ' ') || (*str >= 127)) {
+                                while (len > 0) {
                                         *(s++) = '\\';
                                         *(s++) = 'x';
                                         *(s++) = hexchar((int) *str >> 4);
                                         *(s++) = hexchar((int) *str);
-                                } else
-                                        *(s++) = *str;
 
-                                str += 1;
+                                        str += 1;
+                                        len --;
+                                }
                         }
                 } else {
-                        s = mempcpy(s, UTF8_REPLACEMENT_CHARACTER, strlen(UTF8_REPLACEMENT_CHARACTER));
+                        s = stpcpy(s, UTF8_REPLACEMENT_CHARACTER);
                         str += 1;
                 }
         }
diff --git a/src/test/test-utf8.c b/src/test/test-utf8.c
index 6dde63cdf..3399f2ba9 100644
--- a/src/test/test-utf8.c
+++ b/src/test/test-utf8.c
@@ -47,7 +47,6 @@ static void test_utf8_encoded_valid_unichar(void) {
         assert_se(utf8_encoded_valid_unichar("a") == 1);
         assert_se(utf8_encoded_valid_unichar("\341\204") < 0);
         assert_se(utf8_encoded_valid_unichar("\341\204\341\204") < 0);
-
 }
 
 static void test_utf8_escaping(void) {
@@ -67,7 +66,7 @@ static void test_utf8_escaping(void) {
 }
 
 static void test_utf8_escaping_printable(void) {
-        _cleanup_free_ char *p1, *p2, *p3, *p4, *p5;
+        _cleanup_free_ char *p1, *p2, *p3, *p4, *p5, *p6;
 
         p1 = utf8_escape_non_printable("goo goo goo");
         puts(p1);
@@ -88,6 +87,10 @@ static void test_utf8_escaping_printable(void) {
         p5 = utf8_escape_non_printable("\001 \019\20\a");
         puts(p5);
         assert_se(utf8_is_valid(p5));
+
+        p6 = utf8_escape_non_printable("\xef\xbf\x30\x13");
+        puts(p6);
+        assert_se(utf8_is_valid(p6));
 }
 
 int main(int argc, char *argv[]) {
-- 
2.30.2