X-Git-Url: http://www.chiark.greenend.org.uk/ucgi/~ianmdlvl/git?a=blobdiff_plain;f=src%2Fshared%2Futf8.c;h=03a0abe44b7df0bd05d676476cf38db5412ba800;hb=60e1651a31c9c0ed1caef1a63f5e3a87156b0b1e;hp=9353559b76d1dc9b4212045565c57e229e7d0b16;hpb=7e8185ef942de5acecfa4cda03d7d7711ddda992;p=elogind.git

diff --git a/src/shared/utf8.c b/src/shared/utf8.c
index 9353559b7..03a0abe44 100644
--- a/src/shared/utf8.c
+++ b/src/shared/utf8.c
@@ -142,18 +142,20 @@ int utf8_encoded_to_unichar(const char *str) {
 }
 
 bool utf8_is_printable_newline(const char* str, size_t length, bool newline) {
-        const uint8_t *p;
+        const char *p;
 
         assert(str);
 
-        for (p = (const uint8_t*) str; length;) {
+        for (p = str; length;) {
                 int encoded_len, val;
 
-                encoded_len = utf8_encoded_valid_unichar((const char *) p);
-                val = utf8_encoded_to_unichar((const char*) p);
-
+                encoded_len = utf8_encoded_valid_unichar(p);
                 if (encoded_len < 0 ||
-                    val < 0 ||
+                    (size_t) encoded_len > length)
+                        return false;
+
+                val = utf8_encoded_to_unichar(p);
+                if (val < 0 ||
                     is_unicode_control(val) ||
                     (!newline && val == '\n'))
                         return false;
@@ -200,7 +202,46 @@ 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;
+                }
+        }
+
+        *s = '\0';
+
+        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 {
+                                while (len > 0) {
+                                        *(s++) = '\\';
+                                        *(s++) = 'x';
+                                        *(s++) = hexchar((int) *str >> 4);
+                                        *(s++) = hexchar((int) *str);
+
+                                        str += 1;
+                                        len --;
+                                }
+                        }
+                } else {
+                        s = stpcpy(s, UTF8_REPLACEMENT_CHARACTER);
                         str += 1;
                 }
         }
@@ -222,39 +263,36 @@ char *ascii_is_valid(const char *str) {
         return (char*) str;
 }
 
+int utf8_encode_unichar(uint16_t c, char *p) {
+        uint8_t *t = (uint8_t*) p;
+
+        if (c < 0x80) {
+                t[0] = (uint8_t) c;
+                return 1;
+        } else if (c < 0x800) {
+                t[0] = (uint8_t) (0xc0 | (c >> 6));
+                t[1] = (uint8_t) (0x80 | (c & 0x3f));
+                return 2;
+        } else {
+                t[0] = (uint8_t) (0xe0 | (c >> 12));
+                t[1] = (uint8_t) (0x80 | ((c >> 6) & 0x3f));
+                t[2] = (uint8_t) (0x80 | (c & 0x3f));
+                return 3;
+        }
+}
+
 char *utf16_to_utf8(const void *s, size_t length) {
-        char *r;
         const uint8_t *f;
-        uint8_t *t;
+        char *r, *t;
 
         r = new(char, (length*3+1)/2 + 1);
         if (!r)
                 return NULL;
 
-        t = (uint8_t*) r;
-
-        for (f = s; f < (const uint8_t*) s + length; f += 2) {
-                uint16_t c;
-
-                c = (f[1] << 8) | f[0];
-
-                if (c == 0) {
-                        *t = 0;
-                        return r;
-                } else if (c < 0x80) {
-                        *(t++) = (uint8_t) c;
-                } else if (c < 0x800) {
-                        *(t++) = (uint8_t) (0xc0 | (c >> 6));
-                        *(t++) = (uint8_t) (0x80 | (c & 0x3f));
-                } else {
-                        *(t++) = (uint8_t) (0xe0 | (c >> 12));
-                        *(t++) = (uint8_t) (0x80 | ((c >> 6) & 0x3f));
-                        *(t++) = (uint8_t) (0x80 | (c & 0x3f));
-                }
-        }
+        for (f = s, t = r; f < (const uint8_t*) s + length; f += 2)
+                t += utf8_encode_unichar((f[1] << 8) | f[0], t);
 
         *t = 0;
-
         return r;
 }