summaryrefslogtreecommitdiff
path: root/src/basic/utf8.c
blob: de124abbdebadcbad7141c617ed2c69909a11b48 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
/*-*- Mode: C; c-basic-offset: 8; indent-tabs-mode: nil -*-*/

/***
  This file is part of systemd.

  Copyright 2008-2011 Kay Sievers
  Copyright 2012 Lennart Poettering

  systemd is free software; you can redistribute it and/or modify it
  under the terms of the GNU Lesser General Public License as published by
  the Free Software Foundation; either version 2.1 of the License, or
  (at your option) any later version.

  systemd is distributed in the hope that it will be useful, but
  WITHOUT ANY WARRANTY; without even the implied warranty of
  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
  Lesser General Public License for more details.

  You should have received a copy of the GNU Lesser General Public License
  along with systemd; If not, see <http://www.gnu.org/licenses/>.
***/

/* Parts of this file are based on the GLIB utf8 validation functions. The
 * original license text follows. */

/* gutf8.c - Operations on UTF-8 strings.
 *
 * Copyright (C) 1999 Tom Tromey
 * Copyright (C) 2000 Red Hat, Inc.
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Library General Public
 * License as published by the Free Software Foundation; either
 * version 2 of the License, or (at your option) any later version.
 *
 * This library is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Library General Public License for more details.
 *
 * You should have received a copy of the GNU Library General Public
 * License along with this library; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
 */

#include <errno.h>
#include <stdlib.h>
#include <inttypes.h>
#include <string.h>
#include <stdbool.h>

#include "hexdecoct.h"
#include "utf8.h"
#include "util.h"

bool unichar_is_valid(uint32_t ch) {

        if (ch >= 0x110000) /* End of unicode space */
                return false;
        if ((ch & 0xFFFFF800) == 0xD800) /* Reserved area for UTF-16 */
                return false;
        if ((ch >= 0xFDD0) && (ch <= 0xFDEF)) /* Reserved */
                return false;
        if ((ch & 0xFFFE) == 0xFFFE) /* BOM (Byte Order Mark) */
                return false;

        return true;
}

static bool unichar_is_control(uint32_t ch) {

        /*
          0 to ' '-1 is the C0 range.
          DEL=0x7F, and DEL+1 to 0x9F is C1 range.
          '\t' is in C0 range, but more or less harmless and commonly used.
        */

        return (ch < ' ' && ch != '\t' && ch != '\n') ||
                (0x7F <= ch && ch <= 0x9F);
}

/* count of characters used to encode one unicode char */
static int utf8_encoded_expected_len(const char *str) {
        unsigned char c;

        assert(str);

        c = (unsigned char) str[0];
        if (c < 0x80)
                return 1;
        if ((c & 0xe0) == 0xc0)
                return 2;
        if ((c & 0xf0) == 0xe0)
                return 3;
        if ((c & 0xf8) == 0xf0)
                return 4;
        if ((c & 0xfc) == 0xf8)
                return 5;
        if ((c & 0xfe) == 0xfc)
                return 6;

        return 0;
}

/* decode one unicode char */
int utf8_encoded_to_unichar(const char *str) {
        int unichar, len, i;

        assert(str);

        len = utf8_encoded_expected_len(str);

        switch (len) {
        case 1:
                return (int)str[0];
        case 2:
                unichar = str[0] & 0x1f;
                break;
        case 3:
                unichar = (int)str[0] & 0x0f;
                break;
        case 4:
                unichar = (int)str[0] & 0x07;
                break;
        case 5:
                unichar = (int)str[0] & 0x03;
                break;
        case 6:
                unichar = (int)str[0] & 0x01;
                break;
        default:
                return -EINVAL;
        }

        for (i = 1; i < len; i++) {
                if (((int)str[i] & 0xc0) != 0x80)
                        return -EINVAL;
                unichar <<= 6;
                unichar |= (int)str[i] & 0x3f;
        }

        return unichar;
}

bool utf8_is_printable_newline(const char* str, size_t length, bool newline) {
        const char *p;

        assert(str);

        for (p = str; length;) {
                int encoded_len, val;

                encoded_len = utf8_encoded_valid_unichar(p);
                if (encoded_len < 0 ||
                    (size_t) encoded_len > length)
                        return false;

                val = utf8_encoded_to_unichar(p);
                if (val < 0 ||
                    unichar_is_control(val) ||
                    (!newline && val == '\n'))
                        return false;

                length -= encoded_len;
                p += encoded_len;
        }

        return true;
}

const char *utf8_is_valid(const char *str) {
        const uint8_t *p;

        assert(str);

        for (p = (const uint8_t*) str; *p; ) {
                int len;

                len = utf8_encoded_valid_unichar((const char *)p);
                if (len < 0)
                        return NULL;

                p += len;
        }

        return str;
}

char *utf8_escape_invalid(const char *str) {
        char *p, *s;

        assert(str);

        p = s = malloc(strlen(str) * 4 + 1);
        if (!p)
                return NULL;

        while (*str) {
                int len;

                len = utf8_encoded_valid_unichar(str);
                if (len > 0) {
                        s = mempcpy(s, str, len);
                        str += len;
                } else {
                        s = stpcpy(s, UTF8_REPLACEMENT_CHARACTER);
                        str += 1;
                }
        }

        *s = '\0';

        return p;
}

char *utf8_escape_non_printable(const char *str) {
        char *p, *s;

        assert(str);

        p = s = malloc(strlen(str) * 4 + 1);
        if (!p)
                return NULL;

        while (*str) {
                int len;

                len = utf8_encoded_valid_unichar(str);
                if (len > 0) {
                        if (utf8_is_printable(str, len)) {
                                s = mempcpy(s, str, len);
                                str += len;
                        } else {
                                while (len > 0) {
                                        *(s++) = '\\';
                                        *(s++) = 'x';
                                        *(s++) = hexchar((int) *str >> 4);
                                        *(s++) = hexchar((int) *str);

                                        str += 1;
                                        len --;
                                }
                        }
                } else {
                        s = stpcpy(s, UTF8_REPLACEMENT_CHARACTER);
                        str += 1;
                }
        }

        *s = '\0';

        return p;
}

char *ascii_is_valid(const char *str) {
        const char *p;

        assert(str);

        for (p = str; *p; p++)
                if ((unsigned char) *p >= 128)
                        return NULL;

        return (char*) str;
}

/**
 * utf8_encode_unichar() - Encode single UCS-4 character as UTF-8
 * @out_utf8: output buffer of at least 4 bytes or NULL
 * @g: UCS-4 character to encode
 *
 * This encodes a single UCS-4 character as UTF-8 and writes it into @out_utf8.
 * The length of the character is returned. It is not zero-terminated! If the
 * output buffer is NULL, only the length is returned.
 *
 * Returns: The length in bytes that the UTF-8 representation does or would
 *          occupy.
 */
size_t utf8_encode_unichar(char *out_utf8, uint32_t g) {

        if (g < (1 << 7)) {
                if (out_utf8)
                        out_utf8[0] = g & 0x7f;
                return 1;
        } else if (g < (1 << 11)) {
                if (out_utf8) {
                        out_utf8[0] = 0xc0 | ((g >> 6) & 0x1f);
                        out_utf8[1] = 0x80 | (g & 0x3f);
                }
                return 2;
        } else if (g < (1 << 16)) {
                if (out_utf8) {
                        out_utf8[0] = 0xe0 | ((g >> 12) & 0x0f);
                        out_utf8[1] = 0x80 | ((g >> 6) & 0x3f);
                        out_utf8[2] = 0x80 | (g & 0x3f);
                }
                return 3;
        } else if (g < (1 << 21)) {
                if (out_utf8) {
                        out_utf8[0] = 0xf0 | ((g >> 18) & 0x07);
                        out_utf8[1] = 0x80 | ((g >> 12) & 0x3f);
                        out_utf8[2] = 0x80 | ((g >> 6) & 0x3f);
                        out_utf8[3] = 0x80 | (g & 0x3f);
                }
                return 4;
        }

        return 0;
}

char *utf16_to_utf8(const void *s, size_t length) {
        const uint8_t *f;
        char *r, *t;

        r = new(char, (length * 4 + 1) / 2 + 1);
        if (!r)
                return NULL;

        f = s;
        t = r;

        while (f < (const uint8_t*) s + length) {
                uint16_t w1, w2;

                /* see RFC 2781 section 2.2 */

                w1 = f[1] << 8 | f[0];
                f += 2;

                if (!utf16_is_surrogate(w1)) {
                        t += utf8_encode_unichar(t, w1);

                        continue;
                }

                if (utf16_is_trailing_surrogate(w1))
                        continue;
                else if (f >= (const uint8_t*) s + length)
                        break;

                w2 = f[1] << 8 | f[0];
                f += 2;

                if (!utf16_is_trailing_surrogate(w2)) {
                        f -= 2;
                        continue;
                }

                t += utf8_encode_unichar(t, utf16_surrogate_pair_to_unichar(w1, w2));
        }

        *t = 0;
        return r;
}

/* expected size used to encode one unicode char */
static int utf8_unichar_to_encoded_len(int unichar) {

        if (unichar < 0x80)
                return 1;
        if (unichar < 0x800)
                return 2;
        if (unichar < 0x10000)
                return 3;
        if (unichar < 0x200000)
                return 4;
        if (unichar < 0x4000000)
                return 5;

        return 6;
}

/* validate one encoded unicode char and return its length */
int utf8_encoded_valid_unichar(const char *str) {
        int len, unichar, i;

        assert(str);

        len = utf8_encoded_expected_len(str);
        if (len == 0)
                return -EINVAL;

        /* ascii is valid */
        if (len == 1)
                return 1;

        /* check if expected encoded chars are available */
        for (i = 0; i < len; i++)
                if ((str[i] & 0x80) != 0x80)
                        return -EINVAL;

        unichar = utf8_encoded_to_unichar(str);

        /* check if encoded length matches encoded value */
        if (utf8_unichar_to_encoded_len(unichar) != len)
                return -EINVAL;

        /* check if value has valid range */
        if (!unichar_is_valid(unichar))
                return -EINVAL;

        return len;
}