]>
Commit | Line | Data |
---|---|---|
7f110ff9 LP |
1 | /*-*- Mode: C; c-basic-offset: 8; indent-tabs-mode: nil -*-*/ |
2 | ||
3 | /*** | |
4 | This file is part of systemd. | |
5 | ||
036ae95a | 6 | Copyright 2008-2011 Kay Sievers |
7f110ff9 LP |
7 | Copyright 2012 Lennart Poettering |
8 | ||
9 | systemd is free software; you can redistribute it and/or modify it | |
5430f7f2 LP |
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 | |
7f110ff9 LP |
12 | (at your option) any later version. |
13 | ||
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 | |
5430f7f2 | 17 | Lesser General Public License for more details. |
7f110ff9 | 18 | |
5430f7f2 | 19 | You should have received a copy of the GNU Lesser General Public License |
7f110ff9 LP |
20 | along with systemd; If not, see <http://www.gnu.org/licenses/>. |
21 | ***/ | |
22 | ||
036ae95a | 23 | /* Parts of this file are based on the GLIB utf8 validation functions. The |
7f110ff9 LP |
24 | * original license text follows. */ |
25 | ||
26 | /* gutf8.c - Operations on UTF-8 strings. | |
27 | * | |
28 | * Copyright (C) 1999 Tom Tromey | |
29 | * Copyright (C) 2000 Red Hat, Inc. | |
30 | * | |
31 | * This library is free software; you can redistribute it and/or | |
23757887 | 32 | * modify it under the terms of the GNU Library General Public |
7f110ff9 LP |
33 | * License as published by the Free Software Foundation; either |
34 | * version 2 of the License, or (at your option) any later version. | |
35 | * | |
36 | * This library is distributed in the hope that it will be useful, | |
37 | * but WITHOUT ANY WARRANTY; without even the implied warranty of | |
23757887 SK |
38 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
39 | * Library General Public License for more details. | |
7f110ff9 | 40 | * |
23757887 SK |
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 | |
7f110ff9 LP |
44 | */ |
45 | ||
46 | #include <errno.h> | |
47 | #include <stdlib.h> | |
48 | #include <inttypes.h> | |
49 | #include <string.h> | |
50 | #include <stdbool.h> | |
51 | ||
52 | #include "utf8.h" | |
2e3d0692 | 53 | #include "util.h" |
7f110ff9 | 54 | |
7f110ff9 LP |
55 | static inline bool is_unicode_valid(uint32_t ch) { |
56 | ||
57 | if (ch >= 0x110000) /* End of unicode space */ | |
58 | return false; | |
59 | if ((ch & 0xFFFFF800) == 0xD800) /* Reserved area for UTF-16 */ | |
60 | return false; | |
61 | if ((ch >= 0xFDD0) && (ch <= 0xFDEF)) /* Reserved */ | |
62 | return false; | |
63 | if ((ch & 0xFFFE) == 0xFFFE) /* BOM (Byte Order Mark) */ | |
64 | return false; | |
65 | ||
66 | return true; | |
67 | } | |
68 | ||
ba961854 ZJS |
69 | static bool is_unicode_control(uint32_t ch) { |
70 | ||
71 | /* | |
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. | |
75 | */ | |
76 | ||
31f7bf19 | 77 | return (ch < ' ' && ch != '\t' && ch != '\n') || |
ba961854 ZJS |
78 | (0x7F <= ch && ch <= 0x9F); |
79 | } | |
80 | ||
7991ac34 DR |
81 | /* count of characters used to encode one unicode char */ |
82 | static int utf8_encoded_expected_len(const char *str) { | |
83 | unsigned char c = (unsigned char)str[0]; | |
ba961854 | 84 | |
7991ac34 DR |
85 | if (c < 0x80) |
86 | return 1; | |
87 | if ((c & 0xe0) == 0xc0) | |
88 | return 2; | |
89 | if ((c & 0xf0) == 0xe0) | |
90 | return 3; | |
91 | if ((c & 0xf8) == 0xf0) | |
92 | return 4; | |
93 | if ((c & 0xfc) == 0xf8) | |
94 | return 5; | |
95 | if ((c & 0xfe) == 0xfc) | |
96 | return 6; | |
97 | return 0; | |
98 | } | |
ba961854 | 99 | |
7991ac34 | 100 | /* decode one unicode char */ |
f405e86d | 101 | int utf8_encoded_to_unichar(const char *str) { |
7991ac34 DR |
102 | int unichar; |
103 | int len; | |
104 | int i; | |
ba961854 | 105 | |
7991ac34 DR |
106 | len = utf8_encoded_expected_len(str); |
107 | switch (len) { | |
108 | case 1: | |
109 | return (int)str[0]; | |
110 | case 2: | |
111 | unichar = str[0] & 0x1f; | |
112 | break; | |
113 | case 3: | |
114 | unichar = (int)str[0] & 0x0f; | |
115 | break; | |
116 | case 4: | |
117 | unichar = (int)str[0] & 0x07; | |
118 | break; | |
119 | case 5: | |
120 | unichar = (int)str[0] & 0x03; | |
121 | break; | |
122 | case 6: | |
123 | unichar = (int)str[0] & 0x01; | |
124 | break; | |
125 | default: | |
126 | return -1; | |
ba961854 ZJS |
127 | } |
128 | ||
7991ac34 DR |
129 | for (i = 1; i < len; i++) { |
130 | if (((int)str[i] & 0xc0) != 0x80) | |
131 | return -1; | |
132 | unichar <<= 6; | |
133 | unichar |= (int)str[i] & 0x3f; | |
134 | } | |
135 | ||
136 | return unichar; | |
ba961854 ZJS |
137 | } |
138 | ||
7991ac34 DR |
139 | bool utf8_is_printable(const char* str, size_t length) { |
140 | const uint8_t *p; | |
7f110ff9 LP |
141 | |
142 | assert(str); | |
143 | ||
a7176505 | 144 | for (p = (const uint8_t*) str; length;) { |
7991ac34 | 145 | int encoded_len = utf8_encoded_valid_unichar((const char *)p); |
a7176505 | 146 | int val = utf8_encoded_to_unichar((const char*)p); |
7f110ff9 | 147 | |
7991ac34 DR |
148 | if (encoded_len < 0 || val < 0 || is_unicode_control(val)) |
149 | return false; | |
7f110ff9 | 150 | |
7991ac34 | 151 | length -= encoded_len; |
a7176505 | 152 | p += encoded_len; |
7f110ff9 LP |
153 | } |
154 | ||
7991ac34 | 155 | return true; |
7f110ff9 LP |
156 | } |
157 | ||
7991ac34 DR |
158 | const char *utf8_is_valid(const char *str) { |
159 | const uint8_t *p; | |
7f110ff9 LP |
160 | |
161 | assert(str); | |
162 | ||
7991ac34 | 163 | for (p = (const uint8_t*) str; *p; ) { |
faaa5728 LP |
164 | int len; |
165 | ||
166 | len = utf8_encoded_valid_unichar((const char *)p); | |
7991ac34 DR |
167 | |
168 | if (len < 0) | |
169 | return NULL; | |
170 | ||
171 | p += len; | |
172 | } | |
7f110ff9 | 173 | |
7991ac34 | 174 | return str; |
7f110ff9 LP |
175 | } |
176 | ||
550a40ec ZJS |
177 | char *utf8_escape_invalid(const char *str) { |
178 | char *p, *s; | |
179 | ||
180 | assert(str); | |
181 | ||
182 | p = s = malloc(strlen(str) * 4 + 1); | |
183 | if (!p) | |
184 | return NULL; | |
185 | ||
186 | while (*str) { | |
187 | int len; | |
188 | ||
189 | len = utf8_encoded_valid_unichar(str); | |
190 | if (len > 0) { | |
191 | s = mempcpy(s, str, len); | |
192 | str += len; | |
193 | } else { | |
194 | s = mempcpy(s, UTF8_REPLACEMENT_CHARACTER, strlen(UTF8_REPLACEMENT_CHARACTER)); | |
195 | str += 1; | |
196 | } | |
197 | } | |
198 | *s = '\0'; | |
199 | ||
200 | return p; | |
201 | } | |
202 | ||
7f110ff9 LP |
203 | char *ascii_is_valid(const char *str) { |
204 | const char *p; | |
205 | ||
206 | assert(str); | |
207 | ||
208 | for (p = str; *p; p++) | |
209 | if ((unsigned char) *p >= 128) | |
210 | return NULL; | |
211 | ||
212 | return (char*) str; | |
213 | } | |
214 | ||
2e3d0692 LP |
215 | char *utf16_to_utf8(const void *s, size_t length) { |
216 | char *r; | |
217 | const uint8_t *f; | |
218 | uint8_t *t; | |
219 | ||
220 | r = new(char, (length*3+1)/2 + 1); | |
221 | if (!r) | |
222 | return NULL; | |
223 | ||
224 | t = (uint8_t*) r; | |
225 | ||
226 | for (f = s; f < (const uint8_t*) s + length; f += 2) { | |
227 | uint16_t c; | |
228 | ||
229 | c = (f[1] << 8) | f[0]; | |
230 | ||
231 | if (c == 0) { | |
232 | *t = 0; | |
233 | return r; | |
234 | } else if (c < 0x80) { | |
235 | *(t++) = (uint8_t) c; | |
236 | } else if (c < 0x800) { | |
237 | *(t++) = (uint8_t) (0xc0 | (c >> 6)); | |
238 | *(t++) = (uint8_t) (0x80 | (c & 0x3f)); | |
239 | } else { | |
240 | *(t++) = (uint8_t) (0xe0 | (c >> 12)); | |
241 | *(t++) = (uint8_t) (0x80 | ((c >> 6) & 0x3f)); | |
242 | *(t++) = (uint8_t) (0x80 | (c & 0x3f)); | |
243 | } | |
244 | } | |
245 | ||
246 | *t = 0; | |
2e3d0692 | 247 | |
7b4d7cc0 | 248 | return r; |
2e3d0692 | 249 | } |
02a36bc9 | 250 | |
02a36bc9 DR |
251 | /* expected size used to encode one unicode char */ |
252 | static int utf8_unichar_to_encoded_len(int unichar) { | |
253 | if (unichar < 0x80) | |
254 | return 1; | |
255 | if (unichar < 0x800) | |
256 | return 2; | |
257 | if (unichar < 0x10000) | |
258 | return 3; | |
259 | if (unichar < 0x200000) | |
260 | return 4; | |
261 | if (unichar < 0x4000000) | |
262 | return 5; | |
263 | return 6; | |
264 | } | |
265 | ||
266 | /* validate one encoded unicode char and return its length */ | |
267 | int utf8_encoded_valid_unichar(const char *str) { | |
268 | int len; | |
269 | int unichar; | |
270 | int i; | |
271 | ||
272 | len = utf8_encoded_expected_len(str); | |
273 | if (len == 0) | |
274 | return -1; | |
275 | ||
276 | /* ascii is valid */ | |
277 | if (len == 1) | |
278 | return 1; | |
279 | ||
280 | /* check if expected encoded chars are available */ | |
281 | for (i = 0; i < len; i++) | |
282 | if ((str[i] & 0x80) != 0x80) | |
283 | return -1; | |
284 | ||
285 | unichar = utf8_encoded_to_unichar(str); | |
286 | ||
287 | /* check if encoded length matches encoded value */ | |
288 | if (utf8_unichar_to_encoded_len(unichar) != len) | |
289 | return -1; | |
290 | ||
291 | /* check if value has valid range */ | |
292 | if (!is_unicode_valid(unichar)) | |
293 | return -1; | |
294 | ||
295 | return len; | |
296 | } |