1 /*-*- Mode: C; c-basic-offset: 8; indent-tabs-mode: nil -*-*/
4 This file is part of systemd.
6 Copyright 2008-2011 Kay Sievers
7 Copyright 2012 Lennart Poettering
9 systemd is free software; you can redistribute it and/or modify it
10 under the terms of the GNU Lesser General Public License as published by
11 the Free Software Foundation; either version 2.1 of the License, or
12 (at your option) any later version.
14 systemd is distributed in the hope that it will be useful, but
15 WITHOUT ANY WARRANTY; without even the implied warranty of
16 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
17 Lesser General Public License for more details.
19 You should have received a copy of the GNU Lesser General Public License
20 along with systemd; If not, see <http://www.gnu.org/licenses/>.
23 /* Parts of this file are based on the GLIB utf8 validation functions. The
24 * original license text follows. */
26 /* gutf8.c - Operations on UTF-8 strings.
28 * Copyright (C) 1999 Tom Tromey
29 * Copyright (C) 2000 Red Hat, Inc.
31 * This library is free software; you can redistribute it and/or
32 * modify it under the terms of the GNU Library General Public
33 * License as published by the Free Software Foundation; either
34 * version 2 of the License, or (at your option) any later version.
36 * This library is distributed in the hope that it will be useful,
37 * but WITHOUT ANY WARRANTY; without even the implied warranty of
38 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
39 * Library General Public License for more details.
41 * You should have received a copy of the GNU Library General Public
42 * License along with this library; if not, write to the Free Software
43 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
55 static inline bool is_unicode_valid(uint32_t ch) {
57 if (ch >= 0x110000) /* End of unicode space */
59 if ((ch & 0xFFFFF800) == 0xD800) /* Reserved area for UTF-16 */
61 if ((ch >= 0xFDD0) && (ch <= 0xFDEF)) /* Reserved */
63 if ((ch & 0xFFFE) == 0xFFFE) /* BOM (Byte Order Mark) */
69 static bool is_unicode_control(uint32_t ch) {
72 0 to ' '-1 is the C0 range.
73 DEL=0x7F, and DEL+1 to 0x9F is C1 range.
74 '\t' is in C0 range, but more or less harmless and commonly used.
77 return (ch < ' ' && ch != '\t' && ch != '\n') ||
78 (0x7F <= ch && ch <= 0x9F);
81 /* count of characters used to encode one unicode char */
82 static int utf8_encoded_expected_len(const char *str) {
87 c = (unsigned char) str[0];
90 if ((c & 0xe0) == 0xc0)
92 if ((c & 0xf0) == 0xe0)
94 if ((c & 0xf8) == 0xf0)
96 if ((c & 0xfc) == 0xf8)
98 if ((c & 0xfe) == 0xfc)
104 /* decode one unicode char */
105 int utf8_encoded_to_unichar(const char *str) {
110 len = utf8_encoded_expected_len(str);
116 unichar = str[0] & 0x1f;
119 unichar = (int)str[0] & 0x0f;
122 unichar = (int)str[0] & 0x07;
125 unichar = (int)str[0] & 0x03;
128 unichar = (int)str[0] & 0x01;
134 for (i = 1; i < len; i++) {
135 if (((int)str[i] & 0xc0) != 0x80)
138 unichar |= (int)str[i] & 0x3f;
144 bool utf8_is_printable_newline(const char* str, size_t length, bool newline) {
149 for (p = str; length;) {
150 int encoded_len, val;
152 encoded_len = utf8_encoded_valid_unichar(p);
153 if (encoded_len < 0 ||
154 (size_t) encoded_len > length)
157 val = utf8_encoded_to_unichar(p);
159 is_unicode_control(val) ||
160 (!newline && val == '\n'))
163 length -= encoded_len;
170 const char *utf8_is_valid(const char *str) {
175 for (p = (const uint8_t*) str; *p; ) {
178 len = utf8_encoded_valid_unichar((const char *)p);
188 char *utf8_escape_invalid(const char *str) {
193 p = s = malloc(strlen(str) * 4 + 1);
200 len = utf8_encoded_valid_unichar(str);
202 s = mempcpy(s, str, len);
205 s = stpcpy(s, UTF8_REPLACEMENT_CHARACTER);
215 char *utf8_escape_non_printable(const char *str) {
220 p = s = malloc(strlen(str) * 4 + 1);
227 len = utf8_encoded_valid_unichar(str);
229 if (utf8_is_printable(str, len)) {
230 s = mempcpy(s, str, len);
236 *(s++) = hexchar((int) *str >> 4);
237 *(s++) = hexchar((int) *str);
244 s = stpcpy(s, UTF8_REPLACEMENT_CHARACTER);
254 char *ascii_is_valid(const char *str) {
259 for (p = str; *p; p++)
260 if ((unsigned char) *p >= 128)
266 char *utf16_to_utf8(const void *s, size_t length) {
271 r = new(char, (length*3+1)/2 + 1);
277 for (f = s; f < (const uint8_t*) s + length; f += 2) {
280 c = (f[1] << 8) | f[0];
285 } else if (c < 0x80) {
286 *(t++) = (uint8_t) c;
287 } else if (c < 0x800) {
288 *(t++) = (uint8_t) (0xc0 | (c >> 6));
289 *(t++) = (uint8_t) (0x80 | (c & 0x3f));
291 *(t++) = (uint8_t) (0xe0 | (c >> 12));
292 *(t++) = (uint8_t) (0x80 | ((c >> 6) & 0x3f));
293 *(t++) = (uint8_t) (0x80 | (c & 0x3f));
302 /* expected size used to encode one unicode char */
303 static int utf8_unichar_to_encoded_len(int unichar) {
309 if (unichar < 0x10000)
311 if (unichar < 0x200000)
313 if (unichar < 0x4000000)
319 /* validate one encoded unicode char and return its length */
320 int utf8_encoded_valid_unichar(const char *str) {
325 len = utf8_encoded_expected_len(str);
333 /* check if expected encoded chars are available */
334 for (i = 0; i < len; i++)
335 if ((str[i] & 0x80) != 0x80)
338 unichar = utf8_encoded_to_unichar(str);
340 /* check if encoded length matches encoded value */
341 if (utf8_unichar_to_encoded_len(unichar) != len)
344 /* check if value has valid range */
345 if (!is_unicode_valid(unichar))