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 bool unichar_is_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 unichar_is_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 unichar_is_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)
267 * utf8_encode_unichar() - Encode single UCS-4 character as UTF-8
268 * @out_utf8: output buffer of at least 4 bytes or NULL
269 * @g: UCS-4 character to encode
271 * This encodes a single UCS-4 character as UTF-8 and writes it into @out_utf8.
272 * The length of the character is returned. It is not zero-terminated! If the
273 * output buffer is NULL, only the length is returned.
275 * Returns: The length in bytes that the UTF-8 representation does or would
278 size_t utf8_encode_unichar(char *out_utf8, uint32_t g) {
282 out_utf8[0] = g & 0x7f;
284 } else if (g < (1 << 11)) {
286 out_utf8[0] = 0xc0 | ((g >> 6) & 0x1f);
287 out_utf8[1] = 0x80 | (g & 0x3f);
290 } else if (g < (1 << 16)) {
292 out_utf8[0] = 0xe0 | ((g >> 12) & 0x0f);
293 out_utf8[1] = 0x80 | ((g >> 6) & 0x3f);
294 out_utf8[2] = 0x80 | (g & 0x3f);
297 } else if (g < (1 << 21)) {
299 out_utf8[0] = 0xf0 | ((g >> 18) & 0x07);
300 out_utf8[1] = 0x80 | ((g >> 12) & 0x3f);
301 out_utf8[2] = 0x80 | ((g >> 6) & 0x3f);
302 out_utf8[3] = 0x80 | (g & 0x3f);
310 char *utf16_to_utf8(const void *s, size_t length) {
314 r = new(char, (length * 4 + 1) / 2 + 1);
321 while (f < (const uint8_t*) s + length) {
324 /* see RFC 2781 section 2.2 */
326 w1 = f[1] << 8 | f[0];
329 if (!utf16_is_surrogate(w1)) {
330 t += utf8_encode_unichar(t, w1);
335 if (utf16_is_trailing_surrogate(w1))
337 else if (f >= (const uint8_t*) s + length)
340 w2 = f[1] << 8 | f[0];
343 if (!utf16_is_trailing_surrogate(w2)) {
348 t += utf8_encode_unichar(t, utf16_surrogate_pair_to_unichar(w1, w2));
355 /* expected size used to encode one unicode char */
356 static int utf8_unichar_to_encoded_len(int unichar) {
362 if (unichar < 0x10000)
364 if (unichar < 0x200000)
366 if (unichar < 0x4000000)
372 /* validate one encoded unicode char and return its length */
373 int utf8_encoded_valid_unichar(const char *str) {
378 len = utf8_encoded_expected_len(str);
386 /* check if expected encoded chars are available */
387 for (i = 0; i < len; i++)
388 if ((str[i] & 0x80) != 0x80)
391 unichar = utf8_encoded_to_unichar(str);
393 /* check if encoded length matches encoded value */
394 if (utf8_unichar_to_encoded_len(unichar) != len)
397 /* check if value has valid range */
398 if (!unichar_is_valid(unichar))