1 /*-*- Mode: C; c-basic-offset: 8; indent-tabs-mode: nil -*-*/
4 This file is part of systemd.
6 Copyright 2012 Lennart Poettering
8 systemd is free software; you can redistribute it and/or modify it
9 under the terms of the GNU Lesser General Public License as published by
10 the Free Software Foundation; either version 2.1 of the License, or
11 (at your option) any later version.
13 systemd is distributed in the hope that it will be useful, but
14 WITHOUT ANY WARRANTY; without even the implied warranty of
15 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
16 Lesser General Public License for more details.
18 You should have received a copy of the GNU Lesser General Public License
19 along with systemd; If not, see <http://www.gnu.org/licenses/>.
22 /* This file is based on the GLIB utf8 validation functions. The
23 * original license text follows. */
25 /* gutf8.c - Operations on UTF-8 strings.
27 * Copyright (C) 1999 Tom Tromey
28 * Copyright (C) 2000 Red Hat, Inc.
30 * This library is free software; you can redistribute it and/or
31 * modify it under the terms of the GNU Library General Public
32 * License as published by the Free Software Foundation; either
33 * version 2 of the License, or (at your option) any later version.
35 * This library is distributed in the hope that it will be useful,
36 * but WITHOUT ANY WARRANTY; without even the implied warranty of
37 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
38 * Library General Public License for more details.
40 * You should have received a copy of the GNU Library General Public
41 * License along with this library; if not, write to the Free Software
42 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
54 #define FILTER_CHAR '_'
56 static inline bool is_unicode_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 inline bool is_continuation_char(uint8_t ch) {
71 if ((ch & 0xc0) != 0x80) /* 10xxxxxx */
76 static inline void merge_continuation_char(uint32_t *u_ch, uint8_t ch) {
81 static bool is_unicode_control(uint32_t ch) {
84 0 to ' '-1 is the C0 range.
85 DEL=0x7F, and DEL+1 to 0x9F is C1 range.
86 '\t' is in C0 range, but more or less harmless and commonly used.
89 return (ch < ' ' && ch != '\t' && ch != '\n') ||
90 (0x7F <= ch && ch <= 0x9F);
93 bool utf8_is_printable(const char* str, size_t length) {
100 for (p = (const uint8_t*) str; length; p++, length--) {
104 if ((*p & 0xe0) == 0xc0) { /* 110xxxxx two-char seq. */
106 val = (uint32_t) (*p & 0x1e);
108 } else if ((*p & 0xf0) == 0xe0) { /* 1110xxxx three-char seq.*/
110 val = (uint32_t) (*p & 0x0f);
112 } else if ((*p & 0xf8) == 0xf0) { /* 11110xxx four-char seq */
114 val = (uint32_t) (*p & 0x07);
120 if (!length || !is_continuation_char(*p))
122 merge_continuation_char(&val, *p);
127 if (!is_continuation_char(*p))
129 merge_continuation_char(&val, *p);
134 if (!is_continuation_char(*p))
136 merge_continuation_char(&val, *p);
142 if (is_unicode_control(val))
149 static char* utf8_validate(const char *str, char *output) {
152 const uint8_t *p, *last;
158 o = (uint8_t*) output;
159 for (p = (const uint8_t*) str; *p; p++) {
166 if ((*p & 0xe0) == 0xc0) { /* 110xxxxx two-char seq. */
169 val = (uint32_t) (*p & 0x1e);
171 } else if ((*p & 0xf0) == 0xe0) { /* 1110xxxx three-char seq.*/
174 val = (uint32_t) (*p & 0x0f);
176 } else if ((*p & 0xf8) == 0xf0) { /* 11110xxx four-char seq */
179 val = (uint32_t) (*p & 0x07);
184 if (!is_continuation_char(*p))
186 merge_continuation_char(&val, *p);
190 if (!is_continuation_char(*p))
192 merge_continuation_char(&val, *p);
196 if (!is_continuation_char(*p))
198 merge_continuation_char(&val, *p);
203 if (!is_unicode_valid(val))
207 memcpy(o, last, (size_t) size);
216 p = last; /* We retry at the next character */
236 char* utf8_is_valid (const char *str) {
237 return utf8_validate(str, NULL);
240 char* utf8_filter (const char *str) {
245 new_str = malloc(strlen(str) + 1);
249 return utf8_validate(str, new_str);
252 char *ascii_is_valid(const char *str) {
257 for (p = str; *p; p++)
258 if ((unsigned char) *p >= 128)
264 char *ascii_filter(const char *str) {
276 for (s = str, d = r; *s; s++)
277 if ((unsigned char) *s < 128)
285 char *utf16_to_utf8(const void *s, size_t length) {
290 r = new(char, (length*3+1)/2 + 1);
296 for (f = s; f < (const uint8_t*) s + length; f += 2) {
299 c = (f[1] << 8) | f[0];
304 } else if (c < 0x80) {
305 *(t++) = (uint8_t) c;
306 } else if (c < 0x800) {
307 *(t++) = (uint8_t) (0xc0 | (c >> 6));
308 *(t++) = (uint8_t) (0x80 | (c & 0x3f));
310 *(t++) = (uint8_t) (0xe0 | (c >> 12));
311 *(t++) = (uint8_t) (0x80 | ((c >> 6) & 0x3f));
312 *(t++) = (uint8_t) (0x80 | (c & 0x3f));