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(uint32_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(uint32_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) {
111 len = utf8_encoded_expected_len(str);
117 unichar = str[0] & 0x1f;
120 unichar = (int)str[0] & 0x0f;
123 unichar = (int)str[0] & 0x07;
126 unichar = (int)str[0] & 0x03;
129 unichar = (int)str[0] & 0x01;
135 for (i = 1; i < len; i++) {
136 if (((int)str[i] & 0xc0) != 0x80)
139 unichar |= (int)str[i] & 0x3f;
145 bool utf8_is_printable_newline(const char* str, size_t length, bool newline) {
150 for (p = str; length;) {
151 int encoded_len, val;
153 encoded_len = utf8_encoded_valid_unichar(p);
154 if (encoded_len < 0 ||
155 (size_t) encoded_len > length)
158 val = utf8_encoded_to_unichar(p);
160 unichar_is_control(val) ||
161 (!newline && val == '\n'))
164 length -= encoded_len;
171 const char *utf8_is_valid(const char *str) {
176 for (p = (const uint8_t*) str; *p; ) {
179 len = utf8_encoded_valid_unichar((const char *)p);
189 char *utf8_escape_invalid(const char *str) {
194 p = s = malloc(strlen(str) * 4 + 1);
201 len = utf8_encoded_valid_unichar(str);
203 s = mempcpy(s, str, len);
206 s = stpcpy(s, UTF8_REPLACEMENT_CHARACTER);
216 char *utf8_escape_non_printable(const char *str) {
221 p = s = malloc(strlen(str) * 4 + 1);
228 len = utf8_encoded_valid_unichar(str);
230 if (utf8_is_printable(str, len)) {
231 s = mempcpy(s, str, len);
237 *(s++) = hexchar((int) *str >> 4);
238 *(s++) = hexchar((int) *str);
245 s = stpcpy(s, UTF8_REPLACEMENT_CHARACTER);
255 char *ascii_is_valid(const char *str) {
260 for (p = str; *p; p++)
261 if ((unsigned char) *p >= 128)
268 * utf8_encode_unichar() - Encode single UCS-4 character as UTF-8
269 * @out_utf8: output buffer of at least 4 bytes or NULL
270 * @g: UCS-4 character to encode
272 * This encodes a single UCS-4 character as UTF-8 and writes it into @out_utf8.
273 * The length of the character is returned. It is not zero-terminated! If the
274 * output buffer is NULL, only the length is returned.
276 * Returns: The length in bytes that the UTF-8 representation does or would
279 size_t utf8_encode_unichar(char *out_utf8, uint32_t g) {
283 out_utf8[0] = g & 0x7f;
285 } else if (g < (1 << 11)) {
287 out_utf8[0] = 0xc0 | ((g >> 6) & 0x1f);
288 out_utf8[1] = 0x80 | (g & 0x3f);
291 } else if (g < (1 << 16)) {
293 out_utf8[0] = 0xe0 | ((g >> 12) & 0x0f);
294 out_utf8[1] = 0x80 | ((g >> 6) & 0x3f);
295 out_utf8[2] = 0x80 | (g & 0x3f);
298 } else if (g < (1 << 21)) {
300 out_utf8[0] = 0xf0 | ((g >> 18) & 0x07);
301 out_utf8[1] = 0x80 | ((g >> 12) & 0x3f);
302 out_utf8[2] = 0x80 | ((g >> 6) & 0x3f);
303 out_utf8[3] = 0x80 | (g & 0x3f);
311 char *utf16_to_utf8(const void *s, size_t length) {
315 r = new(char, (length * 4 + 1) / 2 + 1);
322 while (f < (const uint8_t*) s + length) {
325 /* see RFC 2781 section 2.2 */
327 w1 = f[1] << 8 | f[0];
330 if (!utf16_is_surrogate(w1)) {
331 t += utf8_encode_unichar(t, w1);
336 if (utf16_is_trailing_surrogate(w1))
338 else if (f >= (const uint8_t*) s + length)
341 w2 = f[1] << 8 | f[0];
344 if (!utf16_is_trailing_surrogate(w2)) {
349 t += utf8_encode_unichar(t, utf16_surrogate_pair_to_unichar(w1, w2));
356 /* expected size used to encode one unicode char */
357 static int utf8_unichar_to_encoded_len(int unichar) {
363 if (unichar < 0x10000)
365 if (unichar < 0x200000)
367 if (unichar < 0x4000000)
373 /* validate one encoded unicode char and return its length */
374 int utf8_encoded_valid_unichar(const char *str) {
379 len = utf8_encoded_expected_len(str);
387 /* check if expected encoded chars are available */
388 for (i = 0; i < len; i++)
389 if ((str[i] & 0x80) != 0x80)
392 unichar = utf8_encoded_to_unichar(str);
394 /* check if encoded length matches encoded value */
395 if (utf8_unichar_to_encoded_len(unichar) != len)
398 /* check if value has valid range */
399 if (!unichar_is_valid(unichar))