* Copyright (C) 2000 Red Hat, Inc.
*
* This library is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
+ * modify it under the terms of the GNU Library General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * Lesser General Public License for more details.
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * Library General Public License for more details.
*
- * You should have received a copy of the GNU Lesser General Public
- * License along with this library; if not, write to the
- * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * You should have received a copy of the GNU Library General Public
+ * License along with this library; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include <errno.h>
#include <stdbool.h>
#include "utf8.h"
+#include "util.h"
#define FILTER_CHAR '_'
'\t' is in C0 range, but more or less harmless and commonly used.
*/
- return (ch < ' ' && ch != '\t') ||
+ return (ch < ' ' && ch != '\t' && ch != '\n') ||
(0x7F <= ch && ch <= 0x9F);
}
-char* utf8_is_printable_n(const char* str, size_t length) {
+bool utf8_is_printable(const char* str, size_t length) {
uint32_t val = 0;
uint32_t min = 0;
const uint8_t *p;
min = (1 << 16);
val = (uint32_t) (*p & 0x07);
} else
- goto error;
+ return false;
p++;
length--;
if (!length || !is_continuation_char(*p))
- goto error;
+ return false;
merge_continuation_char(&val, *p);
TWO_REMAINING:
p++;
length--;
if (!is_continuation_char(*p))
- goto error;
+ return false;
merge_continuation_char(&val, *p);
ONE_REMAINING:
p++;
length--;
if (!is_continuation_char(*p))
- goto error;
+ return false;
merge_continuation_char(&val, *p);
if (val < min)
- goto error;
+ return false;
}
if (is_unicode_control(val))
- goto error;
+ return false;
}
- return (char*) str;
-
-error:
- return NULL;
+ return true;
}
static char* utf8_validate(const char *str, char *output) {
}
char *ascii_filter(const char *str) {
- char *r, *s, *d;
+ const char *s;
+ char *r, *d;
size_t l;
assert(str);
if (!r)
return NULL;
- for (s = r, d = r; *s; s++)
+ for (s = str, d = r; *s; s++)
if ((unsigned char) *s < 128)
*(d++) = *s;
return r;
}
+
+char *utf16_to_utf8(const void *s, size_t length) {
+ char *r;
+ const uint8_t *f;
+ uint8_t *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));
+ }
+ }
+
+ *t = 0;
+
+ return r;
+}
+
+/* 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];
+
+ if (c < 0x80)
+ return 1;
+ if ((c & 0xe0) == 0xc0)
+ return 2;
+ if ((c & 0xf0) == 0xe0)
+ return 3;
+ if ((c & 0xf8) == 0xf0)
+ return 4;
+ if ((c & 0xfc) == 0xf8)
+ return 5;
+ if ((c & 0xfe) == 0xfc)
+ return 6;
+ return 0;
+}
+
+/* decode one unicode char */
+static int utf8_encoded_to_unichar(const char *str) {
+ int unichar;
+ int len;
+ int i;
+
+ len = utf8_encoded_expected_len(str);
+ switch (len) {
+ case 1:
+ return (int)str[0];
+ case 2:
+ unichar = str[0] & 0x1f;
+ break;
+ case 3:
+ unichar = (int)str[0] & 0x0f;
+ break;
+ case 4:
+ unichar = (int)str[0] & 0x07;
+ break;
+ case 5:
+ unichar = (int)str[0] & 0x03;
+ break;
+ case 6:
+ unichar = (int)str[0] & 0x01;
+ break;
+ default:
+ return -1;
+ }
+
+ for (i = 1; i < len; i++) {
+ if (((int)str[i] & 0xc0) != 0x80)
+ return -1;
+ unichar <<= 6;
+ unichar |= (int)str[i] & 0x3f;
+ }
+
+ return unichar;
+}
+
+/* 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)
+ return 2;
+ if (unichar < 0x10000)
+ return 3;
+ if (unichar < 0x200000)
+ 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;
+
+ len = utf8_encoded_expected_len(str);
+ if (len == 0)
+ return -1;
+
+ /* ascii is valid */
+ if (len == 1)
+ return 1;
+
+ /* check if expected encoded chars are available */
+ for (i = 0; i < len; i++)
+ if ((str[i] & 0x80) != 0x80)
+ return -1;
+
+ unichar = utf8_encoded_to_unichar(str);
+
+ /* check if encoded length matches encoded value */
+ if (utf8_unichar_to_encoded_len(unichar) != len)
+ return -1;
+
+ /* check if value has valid range */
+ if (!is_unicode_valid(unichar))
+ return -1;
+
+ return len;
+}
+
+int is_utf8_encoding_whitelisted(char c, const char *white) {
+ if ((c >= '0' && c <= '9') ||
+ (c >= 'A' && c <= 'Z') ||
+ (c >= 'a' && c <= 'z') ||
+ strchr("#+-.:=@_", c) != NULL ||
+ (white != NULL && strchr(white, c) != NULL))
+ return 1;
+ return 0;
+}
+
+int udev_encode_string(const char *str, char *str_enc, size_t len) {
+ size_t i, j;
+
+ if (str == NULL || str_enc == NULL)
+ return -1;
+
+ for (i = 0, j = 0; str[i] != '\0'; i++) {
+ int seqlen;
+
+ seqlen = utf8_encoded_valid_unichar(&str[i]);
+ if (seqlen > 1) {
+ if (len-j < (size_t)seqlen)
+ goto err;
+ memcpy(&str_enc[j], &str[i], seqlen);
+ j += seqlen;
+ i += (seqlen-1);
+ } else if (str[i] == '\\' || !is_utf8_encoding_whitelisted(str[i], NULL)) {
+ if (len-j < 4)
+ goto err;
+ sprintf(&str_enc[j], "\\x%02x", (unsigned char) str[i]);
+ j += 4;
+ } else {
+ if (len-j < 1)
+ goto err;
+ str_enc[j] = str[i];
+ j++;
+ }
+ }
+ if (len-j < 1)
+ goto err;
+ str_enc[j] = '\0';
+ return 0;
+err:
+ return -1;
+}