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
51 #include "alloc-util.h"
52 #include "hexdecoct.h"
56 bool unichar_is_valid(char32_t ch) {
58 if (ch >= 0x110000) /* End of unicode space */
60 if ((ch & 0xFFFFF800) == 0xD800) /* Reserved area for UTF-16 */
62 if ((ch >= 0xFDD0) && (ch <= 0xFDEF)) /* Reserved */
64 if ((ch & 0xFFFE) == 0xFFFE) /* BOM (Byte Order Mark) */
70 static bool unichar_is_control(char32_t ch) {
73 0 to ' '-1 is the C0 range.
74 DEL=0x7F, and DEL+1 to 0x9F is C1 range.
75 '\t' is in C0 range, but more or less harmless and commonly used.
78 return (ch < ' ' && ch != '\t' && ch != '\n') ||
79 (0x7F <= ch && ch <= 0x9F);
82 /* count of characters used to encode one unicode char */
83 static int utf8_encoded_expected_len(const char *str) {
88 c = (unsigned char) str[0];
91 if ((c & 0xe0) == 0xc0)
93 if ((c & 0xf0) == 0xe0)
95 if ((c & 0xf8) == 0xf0)
97 if ((c & 0xfc) == 0xf8)
99 if ((c & 0xfe) == 0xfc)
105 /* decode one unicode char */
106 int utf8_encoded_to_unichar(const char *str, char32_t *ret_unichar) {
112 len = utf8_encoded_expected_len(str);
116 *ret_unichar = (char32_t)str[0];
119 unichar = str[0] & 0x1f;
122 unichar = (char32_t)str[0] & 0x0f;
125 unichar = (char32_t)str[0] & 0x07;
128 unichar = (char32_t)str[0] & 0x03;
131 unichar = (char32_t)str[0] & 0x01;
137 for (i = 1; i < len; i++) {
138 if (((char32_t)str[i] & 0xc0) != 0x80)
141 unichar |= (char32_t)str[i] & 0x3f;
144 *ret_unichar = unichar;
149 bool utf8_is_printable_newline(const char* str, size_t length, bool newline) {
154 for (p = str; length;) {
158 encoded_len = utf8_encoded_valid_unichar(p);
159 if (encoded_len < 0 ||
160 (size_t) encoded_len > length)
163 r = utf8_encoded_to_unichar(p, &val);
165 unichar_is_control(val) ||
166 (!newline && val == '\n'))
169 length -= encoded_len;
176 const char *utf8_is_valid(const char *str) {
181 for (p = (const uint8_t*) str; *p; ) {
184 len = utf8_encoded_valid_unichar((const char *)p);
194 char *utf8_escape_invalid(const char *str) {
199 p = s = malloc(strlen(str) * 4 + 1);
206 len = utf8_encoded_valid_unichar(str);
208 s = mempcpy(s, str, len);
211 s = stpcpy(s, UTF8_REPLACEMENT_CHARACTER);
221 char *utf8_escape_non_printable(const char *str) {
226 p = s = malloc(strlen(str) * 4 + 1);
233 len = utf8_encoded_valid_unichar(str);
235 if (utf8_is_printable(str, len)) {
236 s = mempcpy(s, str, len);
242 *(s++) = hexchar((int) *str >> 4);
243 *(s++) = hexchar((int) *str);
250 s = stpcpy(s, UTF8_REPLACEMENT_CHARACTER);
260 char *ascii_is_valid(const char *str) {
265 for (p = str; *p; p++)
266 if ((unsigned char) *p >= 128)
273 * utf8_encode_unichar() - Encode single UCS-4 character as UTF-8
274 * @out_utf8: output buffer of at least 4 bytes or NULL
275 * @g: UCS-4 character to encode
277 * This encodes a single UCS-4 character as UTF-8 and writes it into @out_utf8.
278 * The length of the character is returned. It is not zero-terminated! If the
279 * output buffer is NULL, only the length is returned.
281 * Returns: The length in bytes that the UTF-8 representation does or would
284 size_t utf8_encode_unichar(char *out_utf8, char32_t g) {
288 out_utf8[0] = g & 0x7f;
290 } else if (g < (1 << 11)) {
292 out_utf8[0] = 0xc0 | ((g >> 6) & 0x1f);
293 out_utf8[1] = 0x80 | (g & 0x3f);
296 } else if (g < (1 << 16)) {
298 out_utf8[0] = 0xe0 | ((g >> 12) & 0x0f);
299 out_utf8[1] = 0x80 | ((g >> 6) & 0x3f);
300 out_utf8[2] = 0x80 | (g & 0x3f);
303 } else if (g < (1 << 21)) {
305 out_utf8[0] = 0xf0 | ((g >> 18) & 0x07);
306 out_utf8[1] = 0x80 | ((g >> 12) & 0x3f);
307 out_utf8[2] = 0x80 | ((g >> 6) & 0x3f);
308 out_utf8[3] = 0x80 | (g & 0x3f);
316 char *utf16_to_utf8(const void *s, size_t length) {
320 r = new(char, (length * 4 + 1) / 2 + 1);
327 while (f < (const uint8_t*) s + length) {
330 /* see RFC 2781 section 2.2 */
332 w1 = f[1] << 8 | f[0];
335 if (!utf16_is_surrogate(w1)) {
336 t += utf8_encode_unichar(t, w1);
341 if (utf16_is_trailing_surrogate(w1))
343 else if (f >= (const uint8_t*) s + length)
346 w2 = f[1] << 8 | f[0];
349 if (!utf16_is_trailing_surrogate(w2)) {
354 t += utf8_encode_unichar(t, utf16_surrogate_pair_to_unichar(w1, w2));
361 /* expected size used to encode one unicode char */
362 static int utf8_unichar_to_encoded_len(char32_t unichar) {
368 if (unichar < 0x10000)
370 if (unichar < 0x200000)
372 if (unichar < 0x4000000)
378 /* validate one encoded unicode char and return its length */
379 int utf8_encoded_valid_unichar(const char *str) {
385 len = utf8_encoded_expected_len(str);
393 /* check if expected encoded chars are available */
394 for (i = 0; i < len; i++)
395 if ((str[i] & 0x80) != 0x80)
398 r = utf8_encoded_to_unichar(str, &unichar);
402 /* check if encoded length matches encoded value */
403 if (utf8_unichar_to_encoded_len(unichar) != len)
406 /* check if value has valid range */
407 if (!unichar_is_valid(unichar))