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
53 #define FILTER_CHAR '_'
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 inline bool is_continuation_char(uint8_t ch) {
70 if ((ch & 0xc0) != 0x80) /* 10xxxxxx */
75 static inline void merge_continuation_char(uint32_t *u_ch, uint8_t ch) {
80 static bool is_unicode_control(uint32_t ch) {
83 0 to ' '-1 is the C0 range.
84 DEL=0x7F, and DEL+1 to 0x9F is C1 range.
85 '\t' is in C0 range, but more or less harmless and commonly used.
88 return (ch < ' ' && ch != '\t') ||
89 (0x7F <= ch && ch <= 0x9F);
92 char* utf8_is_printable_n(const char* str, size_t length) {
99 for (p = (const uint8_t*) str; length; p++, length--) {
103 if ((*p & 0xe0) == 0xc0) { /* 110xxxxx two-char seq. */
105 val = (uint32_t) (*p & 0x1e);
107 } else if ((*p & 0xf0) == 0xe0) { /* 1110xxxx three-char seq.*/
109 val = (uint32_t) (*p & 0x0f);
111 } else if ((*p & 0xf8) == 0xf0) { /* 11110xxx four-char seq */
113 val = (uint32_t) (*p & 0x07);
119 if (!length || !is_continuation_char(*p))
121 merge_continuation_char(&val, *p);
126 if (!is_continuation_char(*p))
128 merge_continuation_char(&val, *p);
133 if (!is_continuation_char(*p))
135 merge_continuation_char(&val, *p);
141 if (is_unicode_control(val))
151 static char* utf8_validate(const char *str, char *output) {
154 const uint8_t *p, *last;
160 o = (uint8_t*) output;
161 for (p = (const uint8_t*) str; *p; p++) {
168 if ((*p & 0xe0) == 0xc0) { /* 110xxxxx two-char seq. */
171 val = (uint32_t) (*p & 0x1e);
173 } else if ((*p & 0xf0) == 0xe0) { /* 1110xxxx three-char seq.*/
176 val = (uint32_t) (*p & 0x0f);
178 } else if ((*p & 0xf8) == 0xf0) { /* 11110xxx four-char seq */
181 val = (uint32_t) (*p & 0x07);
186 if (!is_continuation_char(*p))
188 merge_continuation_char(&val, *p);
192 if (!is_continuation_char(*p))
194 merge_continuation_char(&val, *p);
198 if (!is_continuation_char(*p))
200 merge_continuation_char(&val, *p);
205 if (!is_unicode_valid(val))
209 memcpy(o, last, (size_t) size);
218 p = last; /* We retry at the next character */
238 char* utf8_is_valid (const char *str) {
239 return utf8_validate(str, NULL);
242 char* utf8_filter (const char *str) {
247 new_str = malloc(strlen(str) + 1);
251 return utf8_validate(str, new_str);
254 char *ascii_is_valid(const char *str) {
259 for (p = str; *p; p++)
260 if ((unsigned char) *p >= 128)
266 char *ascii_filter(const char *str) {
278 for (s = str, d = r; *s; s++)
279 if ((unsigned char) *s < 128)