summaryrefslogtreecommitdiff
path: root/src/libudev/utf8.c
diff options
context:
space:
mode:
authorDave Reisner <dreisner@archlinux.org>2014-01-09 12:20:25 -0500
committerAnthony G. Basile <blueness@gentoo.org>2014-01-09 12:21:20 -0500
commit7ed87c74dfb81761cbcefc10cd4f79394a1d36a3 (patch)
treed42454fd7146d18041770ace67e7d623bdc77830 /src/libudev/utf8.c
parent0a6fb50746ab00d650145cf17fc1a15f109bc386 (diff)
move utf8 functions from libudev-private.h to utf8.h
There's now some more obvious overlap amongst the two utf8 validation functions, but no more than there already was previously. This also adds some menial tests for anyone who wants to do more merging of these two in the future. Adopted for eudev: Anthony G. Basile <blueness@gentoo.org> Signed-off-by: Anthony G. Basile <blueness@gentoo.org>
Diffstat (limited to 'src/libudev/utf8.c')
-rw-r--r--src/libudev/utf8.c233
1 files changed, 233 insertions, 0 deletions
diff --git a/src/libudev/utf8.c b/src/libudev/utf8.c
new file mode 100644
index 0000000000..c9e84b804c
--- /dev/null
+++ b/src/libudev/utf8.c
@@ -0,0 +1,233 @@
+/***
+ This file is part of udev, forked from systemd.
+
+ Copyright 2008-2011 Kay Sievers
+ Copyright 2012 Lennart Poettering
+
+ systemd is free software; you can redistribute it and/or modify it
+ under the terms of the GNU Lesser General Public License as published by
+ the Free Software Foundation; either version 2.1 of the License, or
+ (at your option) any later version.
+
+ systemd 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.
+
+ You should have received a copy of the GNU Lesser General Public License
+ along with systemd; If not, see <http://www.gnu.org/licenses/>.
+***/
+
+/* Parts of this file are based on the GLIB utf8 validation functions. The
+ * original license text follows. */
+
+/* gutf8.c - Operations on UTF-8 strings.
+ *
+ * Copyright (C) 1999 Tom Tromey
+ * 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 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
+ * Library General Public License for more details.
+ *
+ * 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 <stdlib.h>
+#include <inttypes.h>
+#include <string.h>
+#include <stdbool.h>
+
+#include "utf8.h"
+#include "util.h"
+
+static inline bool is_unicode_valid(uint32_t ch) {
+
+ if (ch >= 0x110000) /* End of unicode space */
+ return false;
+ if ((ch & 0xFFFFF800) == 0xD800) /* Reserved area for UTF-16 */
+ return false;
+ if ((ch >= 0xFDD0) && (ch <= 0xFDEF)) /* Reserved */
+ return false;
+ if ((ch & 0xFFFE) == 0xFFFE) /* BOM (Byte Order Mark) */
+ return false;
+
+ return true;
+}
+/* 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 */
+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;
+}
+
+const char *utf8_is_valid(const char *str) {
+ const uint8_t *p;
+
+ assert(str);
+
+ for (p = (const uint8_t*) str; *p; ) {
+ int len;
+
+ len = utf8_encoded_valid_unichar((const char *)p);
+
+ if (len < 0)
+ return NULL;
+
+ p += len;
+ }
+
+ return str;
+}
+/* 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;
+}