/src/libzip/lib/zip_utf-8.c

Source
/*
  zip_utf-8.c -- UTF-8 support functions for libzip
  Copyright (C) 2011-2024 Dieter Baron and Thomas Klausner

  This file is part of libzip, a library to manipulate ZIP archives.
  The authors can be contacted at <info@libzip.org>

  Redistribution and use in source and binary forms, with or without
  modification, are permitted provided that the following conditions
  are met:
  1. Redistributions of source code must retain the above copyright
     notice, this list of conditions and the following disclaimer.
  2. Redistributions in binary form must reproduce the above copyright
     notice, this list of conditions and the following disclaimer in
     the documentation and/or other materials provided with the
     distribution.
  3. The names of the authors may not be used to endorse or promote
     products derived from this software without specific prior
     written permission.

  THIS SOFTWARE IS PROVIDED BY THE AUTHORS ``AS IS'' AND ANY EXPRESS
  OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
  WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY
  DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE
  GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
  INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER
  IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
  OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
  IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/


#include "zipint.h"

#include <stdlib.h>


static const zip_uint16_t _cp437_to_unicode[256] = {
    /* 0x00 - 0x0F */
    0x0000, 0x263A, 0x263B, 0x2665, 0x2666, 0x2663, 0x2660, 0x2022, 0x25D8, 0x25CB, 0x25D9, 0x2642, 0x2640, 0x266A, 0x266B, 0x263C,

    /* 0x10 - 0x1F */
    0x25BA, 0x25C4, 0x2195, 0x203C, 0x00B6, 0x00A7, 0x25AC, 0x21A8, 0x2191, 0x2193, 0x2192, 0x2190, 0x221F, 0x2194, 0x25B2, 0x25BC,

    /* 0x20 - 0x2F */
    0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002A, 0x002B, 0x002C, 0x002D, 0x002E, 0x002F,

    /* 0x30 - 0x3F */
    0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003A, 0x003B, 0x003C, 0x003D, 0x003E, 0x003F,

    /* 0x40 - 0x4F */
    0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004A, 0x004B, 0x004C, 0x004D, 0x004E, 0x004F,

    /* 0x50 - 0x5F */
    0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005A, 0x005B, 0x005C, 0x005D, 0x005E, 0x005F,

    /* 0x60 - 0x6F */
    0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006A, 0x006B, 0x006C, 0x006D, 0x006E, 0x006F,

    /* 0x70 - 0x7F */
    0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007A, 0x007B, 0x007C, 0x007D, 0x007E, 0x2302,

    /* 0x80 - 0x8F */
    0x00C7, 0x00FC, 0x00E9, 0x00E2, 0x00E4, 0x00E0, 0x00E5, 0x00E7, 0x00EA, 0x00EB, 0x00E8, 0x00EF, 0x00EE, 0x00EC, 0x00C4, 0x00C5,

    /* 0x90 - 0x9F */
    0x00C9, 0x00E6, 0x00C6, 0x00F4, 0x00F6, 0x00F2, 0x00FB, 0x00F9, 0x00FF, 0x00D6, 0x00DC, 0x00A2, 0x00A3, 0x00A5, 0x20A7, 0x0192,

    /* 0xA0 - 0xAF */
    0x00E1, 0x00ED, 0x00F3, 0x00FA, 0x00F1, 0x00D1, 0x00AA, 0x00BA, 0x00BF, 0x2310, 0x00AC, 0x00BD, 0x00BC, 0x00A1, 0x00AB, 0x00BB,

    /* 0xB0 - 0xBF */
    0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x2561, 0x2562, 0x2556, 0x2555, 0x2563, 0x2551, 0x2557, 0x255D, 0x255C, 0x255B, 0x2510,

    /* 0xC0 - 0xCF */
    0x2514, 0x2534, 0x252C, 0x251C, 0x2500, 0x253C, 0x255E, 0x255F, 0x255A, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256C, 0x2567,

    /* 0xD0 - 0xDF */
    0x2568, 0x2564, 0x2565, 0x2559, 0x2558, 0x2552, 0x2553, 0x256B, 0x256A, 0x2518, 0x250C, 0x2588, 0x2584, 0x258C, 0x2590, 0x2580,

    /* 0xE0 - 0xEF */
    0x03B1, 0x00DF, 0x0393, 0x03C0, 0x03A3, 0x03C3, 0x00B5, 0x03C4, 0x03A6, 0x0398, 0x03A9, 0x03B4, 0x221E, 0x03C6, 0x03B5, 0x2229,

    /* 0xF0 - 0xFF */
    0x2261, 0x00B1, 0x2265, 0x2264, 0x2320, 0x2321, 0x00F7, 0x2248, 0x00B0, 0x2219, 0x00B7, 0x221A, 0x207F, 0x00B2, 0x25A0, 0x00A0};

#define UTF_8_LEN_2_MASK 0xe0
#define UTF_8_LEN_2_MATCH 0xc0
#define UTF_8_LEN_3_MASK 0xf0
#define UTF_8_LEN_3_MATCH 0xe0
#define UTF_8_LEN_4_MASK 0xf8
#define UTF_8_LEN_4_MATCH 0xf0
#define UTF_8_CONTINUE_MASK 0xc0
#define UTF_8_CONTINUE_MATCH 0x80
#define UTF_8_CONTINUE_VALUE_MASK 0x3f

/* smallest code point that has to be encoded with a sequence of the given length, indexed by number of continuation bytes */
static const zip_uint32_t _utf8_minimum_code_point[4] = {0, 0x80, 0x800, 0x10000};


zip_encoding_type_t _zip_guess_encoding(zip_string_t *str, zip_encoding_type_t expected_encoding) {
    zip_encoding_type_t enc;
    const zip_uint8_t *name;
    zip_uint32_t i, j, ulen, codepoint;
    bool can_be_ascii = true;
    bool can_be_utf8 = true;
    bool has_control_characters = false;

    if (str == NULL) {
        return ZIP_ENCODING_ASCII;
    }

    name = str->raw;

    if (str->encoding != ZIP_ENCODING_UNKNOWN) {
        return str->encoding;
    }

    for (i = 0; i < str->length; i++) {
        if (name[i] < 128) {
            if (name[i] < 32 && name[i] != '\r' && name[i] != '\n' && name[i] != '\t') {
                has_control_characters = true;
            }
            continue;
        }

        can_be_ascii = false;
        if ((name[i] & UTF_8_LEN_2_MASK) == UTF_8_LEN_2_MATCH) {
            ulen = 1;
            codepoint = name[i] & ~UTF_8_LEN_2_MASK;
        }
        else if ((name[i] & UTF_8_LEN_3_MASK) == UTF_8_LEN_3_MATCH) {
            ulen = 2;
            codepoint = name[i] & ~UTF_8_LEN_3_MASK;
        }
        else if ((name[i] & UTF_8_LEN_4_MASK) == UTF_8_LEN_4_MATCH) {
            ulen = 3;
            codepoint = name[i] & ~UTF_8_LEN_4_MASK;
        }
        else {
            can_be_utf8 = false;
            break;
        }

        if (i + ulen >= str->length) {
            can_be_utf8 = false;
            break;
        }

        for (j = 1; j <= ulen; j++) {
            if ((name[i + j] & UTF_8_CONTINUE_MASK) != UTF_8_CONTINUE_MATCH) {
                can_be_utf8 = false;
                goto done;
            }
            codepoint = (codepoint << 6) | (name[i + j] & UTF_8_CONTINUE_VALUE_MASK);
        }

        /* reject overlong encodings, surrogate halves, and code points above U+10FFFF */
        if (codepoint < _utf8_minimum_code_point[ulen] || (codepoint >= 0xd800 && codepoint <= 0xdfff) || codepoint > 0x10ffff) {
            can_be_utf8 = false;
            goto done;
        }
        i += ulen;
    }

done:
    enc = ZIP_ENCODING_CP437;

    switch (expected_encoding) {
    case ZIP_ENCODING_UTF8_KNOWN:
    case ZIP_ENCODING_UTF8_GUESSED:
        if (can_be_utf8) {
            enc = ZIP_ENCODING_UTF8_KNOWN;
        }
        else {
            enc = ZIP_ENCODING_ERROR;
        }
        break;

    case ZIP_ENCODING_ASCII:
        if (can_be_ascii && !has_control_characters) {
            enc = ZIP_ENCODING_ASCII;
        }
        else {
            enc = ZIP_ENCODING_ERROR;
        }
        break;

    case ZIP_ENCODING_CP437:
        enc = ZIP_ENCODING_CP437;
        break;

    case ZIP_ENCODING_UNKNOWN:
        if (can_be_ascii && !has_control_characters) {
            /* only bytes from 0x20-0x7F */
            enc = ZIP_ENCODING_ASCII;
        }
        else if (can_be_ascii && has_control_characters) {
            /* only bytes from 0x00-0x7F */
            enc = ZIP_ENCODING_CP437;
        }
        else if (can_be_utf8) {
            /* contains bytes from 0x80-0xFF and is valid UTF-8 */
            enc = ZIP_ENCODING_UTF8_GUESSED;
        }
        else {
            /* fallback */
            enc = ZIP_ENCODING_CP437;
        }
        break;
    case ZIP_ENCODING_ERROR:
        /* invalid, shouldn't happen */
        enc = ZIP_ENCODING_ERROR;
        break;
    }

    str->encoding = enc;
    return enc;
}


static zip_uint32_t _zip_unicode_to_utf8_len(zip_uint32_t codepoint) {
    if (codepoint < 0x0080) {
        return 1;
    }
    if (codepoint < 0x0800) {
        return 2;
    }
    if (codepoint < 0x10000) {
        return 3;
    }
    return 4;
}


static zip_uint32_t _zip_unicode_to_utf8(zip_uint32_t codepoint, zip_uint8_t *buf) {
    if (codepoint < 0x0080) {
        buf[0] = codepoint & 0xff;
        return 1;
    }
    if (codepoint < 0x0800) {
        buf[0] = (zip_uint8_t)(UTF_8_LEN_2_MATCH | ((codepoint >> 6) & 0x1f));
        buf[1] = (zip_uint8_t)(UTF_8_CONTINUE_MATCH | (codepoint & 0x3f));
        return 2;
    }
    if (codepoint < 0x10000) {
        buf[0] = (zip_uint8_t)(UTF_8_LEN_3_MATCH | ((codepoint >> 12) & 0x0f));
        buf[1] = (zip_uint8_t)(UTF_8_CONTINUE_MATCH | ((codepoint >> 6) & 0x3f));
        buf[2] = (zip_uint8_t)(UTF_8_CONTINUE_MATCH | (codepoint & 0x3f));
        return 3;
    }
    buf[0] = (zip_uint8_t)(UTF_8_LEN_4_MATCH | ((codepoint >> 18) & 0x07));
    buf[1] = (zip_uint8_t)(UTF_8_CONTINUE_MATCH | ((codepoint >> 12) & 0x3f));
    buf[2] = (zip_uint8_t)(UTF_8_CONTINUE_MATCH | ((codepoint >> 6) & 0x3f));
    buf[3] = (zip_uint8_t)(UTF_8_CONTINUE_MATCH | (codepoint & 0x3f));
    return 4;
}


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) {
    zip_uint8_t *cp437buf = (zip_uint8_t *)_cp437buf;
    zip_uint8_t *utf8buf;
    zip_uint32_t buflen, i, offset;

    if (len == 0) {
        if (utf8_lenp) {
            *utf8_lenp = 0;
        }
        return NULL;
    }

    buflen = 1;
    for (i = 0; i < len; i++) {
        buflen += _zip_unicode_to_utf8_len(_cp437_to_unicode[cp437buf[i]]);
    }

    if ((utf8buf = (zip_uint8_t *)malloc(buflen)) == NULL) {
        zip_error_set(error, ZIP_ER_MEMORY, 0);
        return NULL;
    }

    offset = 0;
    for (i = 0; i < len; i++) {
        offset += _zip_unicode_to_utf8(_cp437_to_unicode[cp437buf[i]], utf8buf + offset);
    }

    utf8buf[buflen - 1] = 0;
    if (utf8_lenp) {
        *utf8_lenp = buflen - 1;
    }
    return utf8buf;
}

Coverage Report

Created: 2026-08-25 06:40

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	1.05k	#define UTF_8_LEN_2_MASK 0xe0
90	3.36k	#define UTF_8_LEN_2_MATCH 0xc0
91	863	#define UTF_8_LEN_3_MASK 0xf0
92	2.01k	#define UTF_8_LEN_3_MATCH 0xe0
93	880	#define UTF_8_LEN_4_MASK 0xf8
94	535	#define UTF_8_LEN_4_MATCH 0xf0
95	1.44k	#define UTF_8_CONTINUE_MASK 0xc0
96	6.56k	#define UTF_8_CONTINUE_MATCH 0x80
97	1.35k	#define UTF_8_CONTINUE_VALUE_MASK 0x3f
98
99		/* smallest code point that has to be encoded with a sequence of the given length, indexed by number of continuation bytes */
100		static const zip_uint32_t _utf8_minimum_code_point[4] = {0, 0x80, 0x800, 0x10000};
101
102
103	71.1k	zip_encoding_type_t _zip_guess_encoding(zip_string_t *str, zip_encoding_type_t expected_encoding) {
104	71.1k	zip_encoding_type_t enc;
105	71.1k	const zip_uint8_t *name;
106	71.1k	zip_uint32_t i, j, ulen, codepoint;
107	71.1k	bool can_be_ascii = true;
108	71.1k	bool can_be_utf8 = true;
109	71.1k	bool has_control_characters = false;
110
111	71.1k	if (str == NULL) {
112	0	return ZIP_ENCODING_ASCII;
113	0	}
114
115	71.1k	name = str->raw;
116
117	71.1k	if (str->encoding != ZIP_ENCODING_UNKNOWN) {
118	0	return str->encoding;
119	0	}
120
121	1.65M	for (i = 0; i < str->length; i++) {
122	1.58M	if (name[i] < 128) {
123	1.58M	if (name[i] < 32 && name[i] != '\r' && name[i] != '\n' && name[i] != '\t') {
124	8.45k	has_control_characters = true;
125	8.45k	}
126	1.58M	continue;
127	1.58M	}
128
129	878	can_be_ascii = false;
130	878	if ((name[i] & UTF_8_LEN_2_MASK) == UTF_8_LEN_2_MATCH) {
131	179	ulen = 1;
132	179	codepoint = name[i] & ~UTF_8_LEN_2_MASK;
133	179	}
134	699	else if ((name[i] & UTF_8_LEN_3_MASK) == UTF_8_LEN_3_MATCH) {
135	164	ulen = 2;
136	164	codepoint = name[i] & ~UTF_8_LEN_3_MASK;
137	164	}
138	535	else if ((name[i] & UTF_8_LEN_4_MASK) == UTF_8_LEN_4_MATCH) {
139	345	ulen = 3;
140	345	codepoint = name[i] & ~UTF_8_LEN_4_MASK;
141	345	}
142	190	else {
143	190	can_be_utf8 = false;
144	190	break;
145	190	}
146
147	688	if (i + ulen >= str->length) {
148	20	can_be_utf8 = false;
149	20	break;
150	20	}
151
152	2.02k	for (j = 1; j <= ulen; j++) {
153	1.44k	if ((name[i + j] & UTF_8_CONTINUE_MASK) != UTF_8_CONTINUE_MATCH) {
154	86	can_be_utf8 = false;
155	86	goto done;
156	86	}
157	1.35k	codepoint = (codepoint << 6) \| (name[i + j] & UTF_8_CONTINUE_VALUE_MASK);
158	1.35k	}
159
160		/* reject overlong encodings, surrogate halves, and code points above U+10FFFF */
161	582	if (codepoint < _utf8_minimum_code_point[ulen] \|\| (codepoint >= 0xd800 && codepoint <= 0xdfff) \|\| codepoint > 0x10ffff) {
162	36	can_be_utf8 = false;
163	36	goto done;
164	36	}
165	546	i += ulen;
166	546	}
167
168	71.1k	done:
169	71.1k	enc = ZIP_ENCODING_CP437;
170
171	71.1k	switch (expected_encoding) {
172	30.0k	case ZIP_ENCODING_UTF8_KNOWN:
173	30.0k	case ZIP_ENCODING_UTF8_GUESSED:
174	30.0k	if (can_be_utf8) {
175	29.8k	enc = ZIP_ENCODING_UTF8_KNOWN;
176	29.8k	}
177	192	else {
178	192	enc = ZIP_ENCODING_ERROR;
179	192	}
180	30.0k	break;
181
182	0	case ZIP_ENCODING_ASCII:
183	0	if (can_be_ascii && !has_control_characters) {
184	0	enc = ZIP_ENCODING_ASCII;
185	0	}
186	0	else {
187	0	enc = ZIP_ENCODING_ERROR;
188	0	}
189	0	break;
190
191	0	case ZIP_ENCODING_CP437:
192	0	enc = ZIP_ENCODING_CP437;
193	0	break;
194
195	41.0k	case ZIP_ENCODING_UNKNOWN:
196	41.0k	if (can_be_ascii && !has_control_characters) {
197		/* only bytes from 0x20-0x7F */
198	40.8k	enc = ZIP_ENCODING_ASCII;
199	40.8k	}
200	199	else if (can_be_ascii && has_control_characters) {
201		/* only bytes from 0x00-0x7F */
202	47	enc = ZIP_ENCODING_CP437;
203	47	}
204	152	else if (can_be_utf8) {
205		/* contains bytes from 0x80-0xFF and is valid UTF-8 */
206	12	enc = ZIP_ENCODING_UTF8_GUESSED;
207	12	}
208	140	else {
209		/* fallback */
210	140	enc = ZIP_ENCODING_CP437;
211	140	}
212	41.0k	break;
213	0	case ZIP_ENCODING_ERROR:
214		/* invalid, shouldn't happen */
215	0	enc = ZIP_ENCODING_ERROR;
216	0	break;
217	71.1k	}
218
219	71.1k	str->encoding = enc;
220	71.1k	return enc;
221	71.1k	}
222
223
224	5.95k	static zip_uint32_t _zip_unicode_to_utf8_len(zip_uint32_t codepoint) {
225	5.95k	if (codepoint < 0x0080) {
226	2.14k	return 1;
227	2.14k	}
228	3.80k	if (codepoint < 0x0800) {
229	2.48k	return 2;
230	2.48k	}
231	1.31k	if (codepoint < 0x10000) {
232	1.31k	return 3;
233	1.31k	}
234	0	return 4;
235	1.31k	}
236
237
238	5.95k	static zip_uint32_t _zip_unicode_to_utf8(zip_uint32_t codepoint, zip_uint8_t *buf) {
239	5.95k	if (codepoint < 0x0080) {
240	2.14k	buf[0] = codepoint & 0xff;
241	2.14k	return 1;
242	2.14k	}
243	3.80k	if (codepoint < 0x0800) {
244	2.48k	buf[0] = (zip_uint8_t)(UTF_8_LEN_2_MATCH \| ((codepoint >> 6) & 0x1f));
245	2.48k	buf[1] = (zip_uint8_t)(UTF_8_CONTINUE_MATCH \| (codepoint & 0x3f));
246	2.48k	return 2;
247	2.48k	}
248	1.31k	if (codepoint < 0x10000) {
249	1.31k	buf[0] = (zip_uint8_t)(UTF_8_LEN_3_MATCH \| ((codepoint >> 12) & 0x0f));
250	1.31k	buf[1] = (zip_uint8_t)(UTF_8_CONTINUE_MATCH \| ((codepoint >> 6) & 0x3f));
251	1.31k	buf[2] = (zip_uint8_t)(UTF_8_CONTINUE_MATCH \| (codepoint & 0x3f));
252	1.31k	return 3;
253	1.31k	}
254	0	buf[0] = (zip_uint8_t)(UTF_8_LEN_4_MATCH \| ((codepoint >> 18) & 0x07));
255	0	buf[1] = (zip_uint8_t)(UTF_8_CONTINUE_MATCH \| ((codepoint >> 12) & 0x3f));
256	0	buf[2] = (zip_uint8_t)(UTF_8_CONTINUE_MATCH \| ((codepoint >> 6) & 0x3f));
257	0	buf[3] = (zip_uint8_t)(UTF_8_CONTINUE_MATCH \| (codepoint & 0x3f));
258	0	return 4;
259	1.31k	}
260
261
262	187	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) {
263	187	zip_uint8_t cp437buf = (zip_uint8_t )_cp437buf;
264	187	zip_uint8_t *utf8buf;
265	187	zip_uint32_t buflen, i, offset;
266
267	187	if (len == 0) {
268	0	if (utf8_lenp) {
269	0	*utf8_lenp = 0;
270	0	}
271	0	return NULL;
272	0	}
273
274	187	buflen = 1;
275	6.13k	for (i = 0; i < len; i++) {
276	5.95k	buflen += _zip_unicode_to_utf8_len(_cp437_to_unicode[cp437buf[i]]);
277	5.95k	}
278
279	187	if ((utf8buf = (zip_uint8_t *)malloc(buflen)) == NULL) {
280	0	zip_error_set(error, ZIP_ER_MEMORY, 0);
281	0	return NULL;
282	0	}
283
284	187	offset = 0;
285	6.13k	for (i = 0; i < len; i++) {
286	5.95k	offset += _zip_unicode_to_utf8(_cp437_to_unicode[cp437buf[i]], utf8buf + offset);
287	5.95k	}
288
289	187	utf8buf[buflen - 1] = 0;
290	187	if (utf8_lenp) {
291	187	*utf8_lenp = buflen - 1;
292	187	}
293	187	return utf8buf;
294	187	}