utf8: minor simplifications

[elogind.git] / src / shared / utf8.c

diff --git a/src/shared/utf8.c b/src/shared/utf8.c
index aedf6e29ea3e8fd9e4267ab39cb37575ceb3c13c..4469a73751c3b5624d10c01a0eac59e74eb4e453 100644 (file)
--- a/src/shared/utf8.c
+++ b/src/shared/utf8.c
@@ -80,8 +80,11 @@ static bool is_unicode_control(uint32_t ch) {
 
 /* count of characters used to encode one unicode char */
 static int utf8_encoded_expected_len(const char *str) {
-        unsigned char c = (unsigned char)str[0];
+        unsigned char c;
 
+        assert(str);
+
+        c = (unsigned char) str[0];
         if (c < 0x80)
                 return 1;
         if ((c & 0xe0) == 0xc0)
@@ -94,16 +97,18 @@ static int utf8_encoded_expected_len(const char *str) {
                 return 5;
         if ((c & 0xfe) == 0xfc)
                 return 6;
+
         return 0;
 }
 
 /* decode one unicode char */
 int utf8_encoded_to_unichar(const char *str) {
-        int unichar;
-        int len;
-        int i;
+        int unichar, len, i;
+
+        assert(str);
 
         len = utf8_encoded_expected_len(str);
+
         switch (len) {
         case 1:
                 return (int)str[0];
@@ -123,12 +128,12 @@ int utf8_encoded_to_unichar(const char *str) {
                 unichar = (int)str[0] & 0x01;
                 break;
         default:
-                return -1;
+                return -EINVAL;
         }
 
         for (i = 1; i < len; i++) {
                 if (((int)str[i] & 0xc0) != 0x80)
-                        return -1;
+                        return -EINVAL;
                 unichar <<= 6;
                 unichar |= (int)str[i] & 0x3f;
         }
@@ -136,16 +141,23 @@ int utf8_encoded_to_unichar(const char *str) {
         return unichar;
 }
 
-bool utf8_is_printable(const char* str, size_t length) {
-        const uint8_t *p;
+bool utf8_is_printable_newline(const char* str, size_t length, bool newline) {
+        const char *p;
 
         assert(str);
 
-        for (p = (const uint8_t*) str; length;) {
-                int encoded_len = utf8_encoded_valid_unichar((const char *)p);
-                int val = utf8_encoded_to_unichar((const char*)p);
+        for (p = str; length;) {
+                int encoded_len, val;
+
+                encoded_len = utf8_encoded_valid_unichar(p);
+                if (encoded_len < 0 ||
+                    (size_t) encoded_len > length)
+                        return false;
 
-                if (encoded_len < 0 || val < 0 || is_unicode_control(val))
+                val = utf8_encoded_to_unichar(p);
+                if (val < 0 ||
+                    is_unicode_control(val) ||
+                    (!newline && val == '\n'))
                         return false;
 
                 length -= encoded_len;
@@ -161,8 +173,9 @@ const char *utf8_is_valid(const char *str) {
         assert(str);
 
         for (p = (const uint8_t*) str; *p; ) {
-                int len = utf8_encoded_valid_unichar((const char *)p);
+                int len;
 
+                len = utf8_encoded_valid_unichar((const char *)p);
                 if (len < 0)
                         return NULL;
 
@@ -172,6 +185,72 @@ 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 = 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;
+                }
+        }
+
+        *s = '\0';
+
+        return p;
+}
+
 char *ascii_is_valid(const char *str) {
         const char *p;
 
@@ -222,6 +301,7 @@ char *utf16_to_utf8(const void *s, size_t length) {
 
 /* expected size used to encode one unicode char */
 static int utf8_unichar_to_encoded_len(int unichar) {
+
         if (unichar < 0x80)
                 return 1;
         if (unichar < 0x800)
@@ -232,18 +312,19 @@ static int utf8_unichar_to_encoded_len(int unichar) {
                 return 4;
         if (unichar < 0x4000000)
                 return 5;
+
         return 6;
 }
 
 /* validate one encoded unicode char and return its length */
 int utf8_encoded_valid_unichar(const char *str) {
-        int len;
-        int unichar;
-        int i;
+        int len, unichar, i;
+
+        assert(str);
 
         len = utf8_encoded_expected_len(str);
         if (len == 0)
-                return -1;
+                return -EINVAL;
 
         /* ascii is valid */
         if (len == 1)
@@ -252,17 +333,17 @@ int utf8_encoded_valid_unichar(const char *str) {
         /* check if expected encoded chars are available */
         for (i = 0; i < len; i++)
                 if ((str[i] & 0x80) != 0x80)
-                        return -1;
+                        return -EINVAL;
 
         unichar = utf8_encoded_to_unichar(str);
 
         /* check if encoded length matches encoded value */
         if (utf8_unichar_to_encoded_len(unichar) != len)
-                return -1;
+                return -EINVAL;
 
         /* check if value has valid range */
         if (!is_unicode_valid(unichar))
-                return -1;
+                return -EINVAL;
 
         return len;
 }