Coverage Report

Created: 2026-08-11 07:29

next uncovered line (L), next uncovered region (R), next uncovered branch (B)
/src/libzip/lib/zip_utf-8.c
Line
Count
Source
1
/*
2
  zip_utf-8.c -- UTF-8 support functions for libzip
3
  Copyright (C) 2011-2024 Dieter Baron and Thomas Klausner
4
5
  This file is part of libzip, a library to manipulate ZIP archives.
6
  The authors can be contacted at <info@libzip.org>
7
8
  Redistribution and use in source and binary forms, with or without
9
  modification, are permitted provided that the following conditions
10
  are met:
11
  1. Redistributions of source code must retain the above copyright
12
     notice, this list of conditions and the following disclaimer.
13
  2. Redistributions in binary form must reproduce the above copyright
14
     notice, this list of conditions and the following disclaimer in
15
     the documentation and/or other materials provided with the
16
     distribution.
17
  3. The names of the authors may not be used to endorse or promote
18
     products derived from this software without specific prior
19
     written permission.
20
21
  THIS SOFTWARE IS PROVIDED BY THE AUTHORS ``AS IS'' AND ANY EXPRESS
22
  OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
23
  WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
24
  ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY
25
  DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
26
  DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE
27
  GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
28
  INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER
29
  IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
30
  OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
31
  IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
32
*/
33
34
35
#include "zipint.h"
36
37
#include <stdlib.h>
38
39
40
static const zip_uint16_t _cp437_to_unicode[256] = {
41
    /* 0x00 - 0x0F */
42
    0x0000, 0x263A, 0x263B, 0x2665, 0x2666, 0x2663, 0x2660, 0x2022, 0x25D8, 0x25CB, 0x25D9, 0x2642, 0x2640, 0x266A, 0x266B, 0x263C,
43
44
    /* 0x10 - 0x1F */
45
    0x25BA, 0x25C4, 0x2195, 0x203C, 0x00B6, 0x00A7, 0x25AC, 0x21A8, 0x2191, 0x2193, 0x2192, 0x2190, 0x221F, 0x2194, 0x25B2, 0x25BC,
46
47
    /* 0x20 - 0x2F */
48
    0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002A, 0x002B, 0x002C, 0x002D, 0x002E, 0x002F,
49
50
    /* 0x30 - 0x3F */
51
    0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003A, 0x003B, 0x003C, 0x003D, 0x003E, 0x003F,
52
53
    /* 0x40 - 0x4F */
54
    0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004A, 0x004B, 0x004C, 0x004D, 0x004E, 0x004F,
55
56
    /* 0x50 - 0x5F */
57
    0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005A, 0x005B, 0x005C, 0x005D, 0x005E, 0x005F,
58
59
    /* 0x60 - 0x6F */
60
    0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006A, 0x006B, 0x006C, 0x006D, 0x006E, 0x006F,
61
62
    /* 0x70 - 0x7F */
63
    0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007A, 0x007B, 0x007C, 0x007D, 0x007E, 0x2302,
64
65
    /* 0x80 - 0x8F */
66
    0x00C7, 0x00FC, 0x00E9, 0x00E2, 0x00E4, 0x00E0, 0x00E5, 0x00E7, 0x00EA, 0x00EB, 0x00E8, 0x00EF, 0x00EE, 0x00EC, 0x00C4, 0x00C5,
67
68
    /* 0x90 - 0x9F */
69
    0x00C9, 0x00E6, 0x00C6, 0x00F4, 0x00F6, 0x00F2, 0x00FB, 0x00F9, 0x00FF, 0x00D6, 0x00DC, 0x00A2, 0x00A3, 0x00A5, 0x20A7, 0x0192,
70
71
    /* 0xA0 - 0xAF */
72
    0x00E1, 0x00ED, 0x00F3, 0x00FA, 0x00F1, 0x00D1, 0x00AA, 0x00BA, 0x00BF, 0x2310, 0x00AC, 0x00BD, 0x00BC, 0x00A1, 0x00AB, 0x00BB,
73
74
    /* 0xB0 - 0xBF */
75
    0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x2561, 0x2562, 0x2556, 0x2555, 0x2563, 0x2551, 0x2557, 0x255D, 0x255C, 0x255B, 0x2510,
76
77
    /* 0xC0 - 0xCF */
78
    0x2514, 0x2534, 0x252C, 0x251C, 0x2500, 0x253C, 0x255E, 0x255F, 0x255A, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256C, 0x2567,
79
80
    /* 0xD0 - 0xDF */
81
    0x2568, 0x2564, 0x2565, 0x2559, 0x2558, 0x2552, 0x2553, 0x256B, 0x256A, 0x2518, 0x250C, 0x2588, 0x2584, 0x258C, 0x2590, 0x2580,
82
83
    /* 0xE0 - 0xEF */
84
    0x03B1, 0x00DF, 0x0393, 0x03C0, 0x03A3, 0x03C3, 0x00B5, 0x03C4, 0x03A6, 0x0398, 0x03A9, 0x03B4, 0x221E, 0x03C6, 0x03B5, 0x2229,
85
86
    /* 0xF0 - 0xFF */
87
    0x2261, 0x00B1, 0x2265, 0x2264, 0x2320, 0x2321, 0x00F7, 0x2248, 0x00B0, 0x2219, 0x00B7, 0x221A, 0x207F, 0x00B2, 0x25A0, 0x00A0};
88
89
514
#define UTF_8_LEN_2_MASK 0xe0
90
2.62k
#define UTF_8_LEN_2_MATCH 0xc0
91
390
#define UTF_8_LEN_3_MASK 0xf0
92
1.22k
#define UTF_8_LEN_3_MATCH 0xe0
93
298
#define UTF_8_LEN_4_MASK 0xf8
94
298
#define UTF_8_LEN_4_MATCH 0xf0
95
560
#define UTF_8_CONTINUE_MASK 0xc0
96
4.34k
#define UTF_8_CONTINUE_MATCH 0x80
97
98
99
59.7k
zip_encoding_type_t _zip_guess_encoding(zip_string_t *str, zip_encoding_type_t expected_encoding) {
100
59.7k
    zip_encoding_type_t enc;
101
59.7k
    const zip_uint8_t *name;
102
59.7k
    zip_uint32_t i, j, ulen;
103
59.7k
    bool can_be_ascii = true;
104
59.7k
    bool can_be_utf8 = true;
105
59.7k
    bool has_control_characters = false;
106
107
59.7k
    if (str == NULL) {
108
0
        return ZIP_ENCODING_ASCII;
109
0
    }
110
111
59.7k
    name = str->raw;
112
113
59.7k
    if (str->encoding != ZIP_ENCODING_UNKNOWN) {
114
0
        return str->encoding;
115
0
    }
116
117
1.29M
    for (i = 0; i < str->length; i++) {
118
1.23M
        if (name[i] < 128) {
119
1.23M
            if (name[i] < 32 && name[i] != '\r' && name[i] != '\n' && name[i] != '\t') {
120
4.11k
                has_control_characters = true;
121
4.11k
            }
122
1.23M
            continue;
123
1.23M
        }
124
125
514
        can_be_ascii = false;
126
514
        if ((name[i] & UTF_8_LEN_2_MASK) == UTF_8_LEN_2_MATCH) {
127
124
            ulen = 1;
128
124
        }
129
390
        else if ((name[i] & UTF_8_LEN_3_MASK) == UTF_8_LEN_3_MATCH) {
130
92
            ulen = 2;
131
92
        }
132
298
        else if ((name[i] & UTF_8_LEN_4_MASK) == UTF_8_LEN_4_MATCH) {
133
113
            ulen = 3;
134
113
        }
135
185
        else {
136
185
            can_be_utf8 = false;
137
185
            break;
138
185
        }
139
140
329
        if (i + ulen >= str->length) {
141
24
            can_be_utf8 = false;
142
24
            break;
143
24
        }
144
145
807
        for (j = 1; j <= ulen; j++) {
146
560
            if ((name[i + j] & UTF_8_CONTINUE_MASK) != UTF_8_CONTINUE_MATCH) {
147
58
                can_be_utf8 = false;
148
58
                goto done;
149
58
            }
150
560
        }
151
247
        i += ulen;
152
247
    }
153
154
59.7k
done:
155
59.7k
    enc = ZIP_ENCODING_CP437;
156
157
59.7k
    switch (expected_encoding) {
158
26.1k
    case ZIP_ENCODING_UTF8_KNOWN:
159
26.1k
    case ZIP_ENCODING_UTF8_GUESSED:
160
26.1k
        if (can_be_utf8) {
161
25.9k
            enc = ZIP_ENCODING_UTF8_KNOWN;
162
25.9k
        }
163
123
        else {
164
123
            enc = ZIP_ENCODING_ERROR;
165
123
        }
166
26.1k
        break;
167
168
0
    case ZIP_ENCODING_ASCII:
169
0
        if (can_be_ascii && !has_control_characters) {
170
0
            enc = ZIP_ENCODING_ASCII;
171
0
        }
172
0
        else {
173
0
            enc = ZIP_ENCODING_ERROR;
174
0
        }
175
0
        break;
176
177
0
    case ZIP_ENCODING_CP437:
178
0
        enc = ZIP_ENCODING_CP437;
179
0
        break;
180
181
33.6k
    case ZIP_ENCODING_UNKNOWN:
182
33.6k
        if (can_be_ascii && !has_control_characters) {
183
            /* only bytes from 0x20-0x7F */
184
33.4k
            enc = ZIP_ENCODING_ASCII;
185
33.4k
        }
186
196
        else if (can_be_ascii && has_control_characters) {
187
            /* only bytes from 0x00-0x7F */
188
42
            enc = ZIP_ENCODING_CP437;
189
42
        }
190
154
        else if (can_be_utf8) {
191
            /* contains bytes from 0x80-0xFF and is valid UTF-8 */
192
10
            enc = ZIP_ENCODING_UTF8_GUESSED;
193
10
        }
194
144
        else {
195
            /* fallback */
196
144
            enc = ZIP_ENCODING_CP437;
197
144
        }
198
33.6k
        break;
199
0
    case ZIP_ENCODING_ERROR:
200
        /* invalid, shouldn't happen */
201
0
        enc = ZIP_ENCODING_ERROR;
202
0
        break;
203
59.7k
    }
204
205
59.7k
    str->encoding = enc;
206
59.7k
    return enc;
207
59.7k
}
208
209
210
4.71k
static zip_uint32_t _zip_unicode_to_utf8_len(zip_uint32_t codepoint) {
211
4.71k
    if (codepoint < 0x0080) {
212
1.76k
        return 1;
213
1.76k
    }
214
2.95k
    if (codepoint < 0x0800) {
215
2.11k
        return 2;
216
2.11k
    }
217
837
    if (codepoint < 0x10000) {
218
837
        return 3;
219
837
    }
220
0
    return 4;
221
837
}
222
223
224
4.71k
static zip_uint32_t _zip_unicode_to_utf8(zip_uint32_t codepoint, zip_uint8_t *buf) {
225
4.71k
    if (codepoint < 0x0080) {
226
1.76k
        buf[0] = codepoint & 0xff;
227
1.76k
        return 1;
228
1.76k
    }
229
2.95k
    if (codepoint < 0x0800) {
230
2.11k
        buf[0] = (zip_uint8_t)(UTF_8_LEN_2_MATCH | ((codepoint >> 6) & 0x1f));
231
2.11k
        buf[1] = (zip_uint8_t)(UTF_8_CONTINUE_MATCH | (codepoint & 0x3f));
232
2.11k
        return 2;
233
2.11k
    }
234
837
    if (codepoint < 0x10000) {
235
837
        buf[0] = (zip_uint8_t)(UTF_8_LEN_3_MATCH | ((codepoint >> 12) & 0x0f));
236
837
        buf[1] = (zip_uint8_t)(UTF_8_CONTINUE_MATCH | ((codepoint >> 6) & 0x3f));
237
837
        buf[2] = (zip_uint8_t)(UTF_8_CONTINUE_MATCH | (codepoint & 0x3f));
238
837
        return 3;
239
837
    }
240
0
    buf[0] = (zip_uint8_t)(UTF_8_LEN_4_MATCH | ((codepoint >> 18) & 0x07));
241
0
    buf[1] = (zip_uint8_t)(UTF_8_CONTINUE_MATCH | ((codepoint >> 12) & 0x3f));
242
0
    buf[2] = (zip_uint8_t)(UTF_8_CONTINUE_MATCH | ((codepoint >> 6) & 0x3f));
243
0
    buf[3] = (zip_uint8_t)(UTF_8_CONTINUE_MATCH | (codepoint & 0x3f));
244
0
    return 4;
245
837
}
246
247
248
186
zip_uint8_t *_zip_cp437_to_utf8(const zip_uint8_t *const _cp437buf, zip_uint32_t len, zip_uint32_t *utf8_lenp, zip_error_t *error) {
249
186
    zip_uint8_t *cp437buf = (zip_uint8_t *)_cp437buf;
250
186
    zip_uint8_t *utf8buf;
251
186
    zip_uint32_t buflen, i, offset;
252
253
186
    if (len == 0) {
254
0
        if (utf8_lenp) {
255
0
            *utf8_lenp = 0;
256
0
        }
257
0
        return NULL;
258
0
    }
259
260
186
    buflen = 1;
261
4.90k
    for (i = 0; i < len; i++) {
262
4.71k
        buflen += _zip_unicode_to_utf8_len(_cp437_to_unicode[cp437buf[i]]);
263
4.71k
    }
264
265
186
    if ((utf8buf = (zip_uint8_t *)malloc(buflen)) == NULL) {
266
0
        zip_error_set(error, ZIP_ER_MEMORY, 0);
267
0
        return NULL;
268
0
    }
269
270
186
    offset = 0;
271
4.90k
    for (i = 0; i < len; i++) {
272
4.71k
        offset += _zip_unicode_to_utf8(_cp437_to_unicode[cp437buf[i]], utf8buf + offset);
273
4.71k
    }
274
275
186
    utf8buf[buflen - 1] = 0;
276
186
    if (utf8_lenp) {
277
186
        *utf8_lenp = buflen - 1;
278
186
    }
279
186
    return utf8buf;
280
186
}