[systemd-devel] [PATCH v2 1/2] utf8: intruduce utf8_escape_non_printable

[WaLyong Cho]

---
 src/shared/utf8.c    | 87 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 src/shared/utf8.h    |  1 +
 src/test/test-utf8.c | 30 ++++++++++++++++++
 3 files changed, 118 insertions(+)

diff --git a/src/shared/utf8.c b/src/shared/utf8.c
index 9353559..5245604 100644
--- a/src/shared/utf8.c
+++ b/src/shared/utf8.c
@@ -210,6 +210,93 @@ char *utf8_escape_invalid(const char *str) {
         return p;
 }
 
+char *utf8_escape_non_printable(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) {
+                        if (utf8_is_printable(str, len)) {
+                                s = mempcpy(s, str, len);
+                                str += len;
+                        } else {
+                                switch (*str) {
+
+                                case '\a':
+                                        *(s++) = '\\';
+                                        *(s++) = 'a';
+                                        break;
+                                case '\b':
+                                        *(s++) = '\\';
+                                        *(s++) = 'b';
+                                        break;
+                                case '\f':
+                                        *(s++) = '\\';
+                                        *(s++) = 'f';
+                                        break;
+                                case '\n':
+                                        *(s++) = '\\';
+                                        *(s++) = 'n';
+                                        break;
+                                case '\r':
+                                        *(s++) = '\\';
+                                        *(s++) = 'r';
+                                        break;
+                                case '\t':
+                                        *(s++) = '\\';
+                                        *(s++) = 't';
+                                        break;
+                                case '\v':
+                                        *(s++) = '\\';
+                                        *(s++) = 'v';
+                                        break;
+                                case '\\':
+                                        *(s++) = '\\';
+                                        *(s++) = '\\';
+                                        break;
+                                case '"':
+                                        *(s++) = '\\';
+                                        *(s++) = '"';
+                                        break;
+                                case '\'':
+                                        *(s++) = '\\';
+                                        *(s++) = '\'';
+                                        break;
+
+                                default:
+                                        /* For special chars we prefer octal over
+                                         * hexadecimal encoding, simply because glib's
+                                         * g_strescape() does the same */
+                                        if ((*str < ' ') || (*str >= 127)) {
+                                                *(s++) = '\\';
+                                                *(s++) = octchar((unsigned char) *str >> 6);
+                                                *(s++) = octchar((unsigned char) *str >> 3);
+                                                *(s++) = octchar((unsigned char) *str);
+                                        } else
+                                                *(s++) = *str;
+                                        break;
+                                }
+                                str += 1;
+                        }
+                } 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;
 
diff --git a/src/shared/utf8.h b/src/shared/utf8.h
index c087995..1fe1a35 100644
--- a/src/shared/utf8.h
+++ b/src/shared/utf8.h
@@ -30,6 +30,7 @@
 const char *utf8_is_valid(const char *s) _pure_;
 char *ascii_is_valid(const char *s) _pure_;
 char *utf8_escape_invalid(const char *s);
+char *utf8_escape_non_printable(const char *str);
 
 bool utf8_is_printable_newline(const char* str, size_t length, bool newline) _pure_;
 _pure_ static inline bool utf8_is_printable(const char* str, size_t length) {
diff --git a/src/test/test-utf8.c b/src/test/test-utf8.c
index b7d988f..fb27fe5 100644
--- a/src/test/test-utf8.c
+++ b/src/test/test-utf8.c
@@ -66,12 +66,42 @@ static void test_utf8_escaping(void) {
         assert_se(utf8_is_valid(p3));
 }
 
+static void test_utf8_escaping_printable(void) {
+        _cleanup_free_ char *p1, *p2, *p3, *p4, *p5, *p6;
+        char c[10];
+
+        p1 = utf8_escape_non_printable("goo goo goo");
+        puts(p1);
+        assert_se(utf8_is_valid(p1));
+
+        p2 = utf8_escape_non_printable("\341\204\341\204");
+        puts(p2);
+        assert_se(utf8_is_valid(p2));
+
+        p3 = utf8_escape_non_printable("\341\204");
+        puts(p3);
+        assert_se(utf8_is_valid(p3));
+
+        p4 = utf8_escape_non_printable("ąę");
+        puts(p4);
+        assert_se(utf8_is_valid(p4));
+
+        p5 = utf8_escape_non_printable("가너도루");
+        puts(p5);
+        assert_se(utf8_is_valid(p5));
+
+        p6 = utf8_escape_non_printable("\001 \019\a");
+        puts(p6);
+        assert_se(utf8_is_valid(p6));
+}
+
 int main(int argc, char *argv[]) {
         test_utf8_is_valid();
         test_utf8_is_printable();
         test_ascii_is_valid();
         test_utf8_encoded_valid_unichar();
         test_utf8_escaping();
+        test_utf8_escaping_printable();
 
         return 0;
 }
-- 
1.9.3