root/ext/zip/lib/zip_utf-8.c

DEFINITIONS

1. _zip_guess_encoding
2. _zip_unicode_to_utf8_len
3. _zip_unicode_to_utf8
4. _zip_cp437_to_utf8

   1 /*
   2   zip_utf-8.c -- UTF-8 support functions for libzip
   3   Copyright (C) 2011-2012 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 <libzip@nih.at>
   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 
  36 #include "zipint.h"
  37 
  38 #include <stdlib.h>
  39 
  40 
  41 
  42 static const zip_uint16_t _cp437_to_unicode[256] = {
  43     /* 0x00 - 0x0F */
  44     0x2007, 0x263A, 0x263B, 0x2665, 0x2666, 0x2663, 0x2660, 0x2022,
  45     0x25D8, 0x25CB, 0x25D9, 0x2642, 0x2640, 0x266A, 0x266B, 0x263C,
  46 
  47     /* 0x10 - 0x1F */
  48     0x25BA, 0x25C4, 0x2195, 0x203C, 0x00B6, 0x00A7, 0x25AC, 0x21A8,
  49     0x2191, 0x2193, 0x2192, 0x2190, 0x221F, 0x2194, 0x25B2, 0x25BC,
  50 
  51     /* 0x20 - 0x2F */
  52     0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027,
  53     0x0028, 0x0029, 0x002A, 0x002B, 0x002C, 0x002D, 0x002E, 0x002F,
  54 
  55     /* 0x30 - 0x3F */
  56     0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037,
  57     0x0038, 0x0039, 0x003A, 0x003B, 0x003C, 0x003D, 0x003E, 0x003F,
  58 
  59     /* 0x40 - 0x4F */
  60     0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047,
  61     0x0048, 0x0049, 0x004A, 0x004B, 0x004C, 0x004D, 0x004E, 0x004F,
  62 
  63     /* 0x50 - 0x5F */
  64     0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057,
  65     0x0058, 0x0059, 0x005A, 0x005B, 0x005C, 0x005D, 0x005E, 0x005F,
  66 
  67     /* 0x60 - 0x6F */
  68     0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067,
  69     0x0068, 0x0069, 0x006A, 0x006B, 0x006C, 0x006D, 0x006E, 0x006F,
  70 
  71     /* 0x70 - 0x7F */
  72     0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077,
  73     0x0078, 0x0079, 0x007A, 0x007B, 0x007C, 0x007D, 0x007E, 0x2302,
  74 
  75     /* 0x80 - 0x8F */
  76     0x00C7, 0x00FC, 0x00E9, 0x00E2, 0x00E4, 0x00E0, 0x00E5, 0x00E7,
  77     0x00EA, 0x00EB, 0x00E8, 0x00EF, 0x00EE, 0x00EC, 0x00C4, 0x00C5,
  78 
  79     /* 0x90 - 0x9F */
  80     0x00C9, 0x00E6, 0x00C6, 0x00F4, 0x00F6, 0x00F2, 0x00FB, 0x00F9,
  81     0x00FF, 0x00D6, 0x00DC, 0x00A2, 0x00A3, 0x00A5, 0x20A7, 0x0192,
  82 
  83     /* 0xA0 - 0xAF */
  84     0x00E1, 0x00ED, 0x00F3, 0x00FA, 0x00F1, 0x00D1, 0x00AA, 0x00BA,
  85     0x00BF, 0x2310, 0x00AC, 0x00BD, 0x00BC, 0x00A1, 0x00AB, 0x00BB,
  86 
  87     /* 0xB0 - 0xBF */
  88     0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x2561, 0x2562, 0x2556,
  89     0x2555, 0x2563, 0x2551, 0x2557, 0x255D, 0x255C, 0x255B, 0x2510,
  90 
  91     /* 0xC0 - 0xCF */
  92     0x2514, 0x2534, 0x252C, 0x251C, 0x2500, 0x253C, 0x255E, 0x255F,
  93     0x255A, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256C, 0x2567,
  94 
  95     /* 0xD0 - 0xDF */
  96     0x2568, 0x2564, 0x2565, 0x2559, 0x2558, 0x2552, 0x2553, 0x256B,
  97     0x256A, 0x2518, 0x250C, 0x2588, 0x2584, 0x258C, 0x2590, 0x2580,
  98 
  99     /* 0xE0 - 0xEF */
 100     0x03B1, 0x00DF, 0x0393, 0x03C0, 0x03A3, 0x03C3, 0x00B5, 0x03C4,
 101     0x03A6, 0x0398, 0x03A9, 0x03B4, 0x221E, 0x03C6, 0x03B5, 0x2229,
 102 
 103     /* 0xF0 - 0xFF */
 104     0x2261, 0x00B1, 0x2265, 0x2264, 0x2320, 0x2321, 0x00F7, 0x2248,
 105     0x00B0, 0x2219, 0x00B7, 0x221A, 0x207F, 0x00B2, 0x25A0, 0x00A0
 106 };
 107 
 108 #define UTF_8_LEN_2_MASK     0xe0
 109 #define UTF_8_LEN_2_MATCH    0xc0
 110 #define UTF_8_LEN_3_MASK     0xf0
 111 #define UTF_8_LEN_3_MATCH    0xe0
 112 #define UTF_8_LEN_4_MASK     0xf8
 113 #define UTF_8_LEN_4_MATCH    0xf0
 114 #define UTF_8_CONTINUE_MASK  0xc0
 115 #define UTF_8_CONTINUE_MATCH 0x80
 116 
 117 
 118 
 119 enum zip_encoding_type
 120 _zip_guess_encoding(struct zip_string *str, enum zip_encoding_type expected_encoding)
 121 {
 122     enum zip_encoding_type enc;
 123     const zip_uint8_t *name;
 124     zip_uint32_t i, j, ulen;
 125 
 126     if (str == NULL)
 127         return ZIP_ENCODING_ASCII;
 128 
 129     name = str->raw;
 130 
 131     if (str->encoding != ZIP_ENCODING_UNKNOWN)
 132         enc = str->encoding;
 133     else {
 134         enc = ZIP_ENCODING_ASCII;
 135         for (i=0; i<str->length; i++) {
 136             if ((name[i] > 31 && name[i] < 128) || name[i] == '\r' || name[i] == '\n' || name[i] == '\t')
 137                 continue;
 138 
 139             enc = ZIP_ENCODING_UTF8_GUESSED;
 140             if ((name[i] & UTF_8_LEN_2_MASK) == UTF_8_LEN_2_MATCH)
 141                 ulen = 1;
 142             else if ((name[i] & UTF_8_LEN_3_MASK) == UTF_8_LEN_3_MATCH)
 143                 ulen = 2;
 144             else if ((name[i] & UTF_8_LEN_4_MASK) == UTF_8_LEN_4_MATCH)
 145                 ulen = 3;
 146             else {
 147                 enc = ZIP_ENCODING_CP437;
 148                 break;
 149             }
 150 
 151             if (i + ulen >= str->length) {
 152                 enc = ZIP_ENCODING_CP437;
 153                 break;
 154             }
 155 
 156             for (j=1; j<=ulen; j++) {
 157                 if ((name[i+j] & UTF_8_CONTINUE_MASK) != UTF_8_CONTINUE_MATCH) {
 158                     enc = ZIP_ENCODING_CP437;
 159                     goto done;
 160                 }
 161             }
 162             i += ulen;
 163         }
 164     }
 165 
 166 done:
 167     str->encoding = enc;
 168 
 169     if (expected_encoding != ZIP_ENCODING_UNKNOWN) {
 170         if (expected_encoding == ZIP_ENCODING_UTF8_KNOWN && enc == ZIP_ENCODING_UTF8_GUESSED)
 171             str->encoding = enc = ZIP_ENCODING_UTF8_KNOWN;
 172 
 173         if (expected_encoding != enc && enc != ZIP_ENCODING_ASCII)
 174             return ZIP_ENCODING_ERROR;
 175     }
 176     
 177     return enc;
 178 }
 179 
 180 
 181 
 182 static zip_uint32_t
 183 _zip_unicode_to_utf8_len(zip_uint32_t codepoint)
 184 {
 185     if (codepoint < 0x0080)
 186         return 1;
 187     if (codepoint < 0x0800)
 188         return 2;
 189     if (codepoint < 0x10000)
 190         return 3;
 191     return 4;
 192 }
 193 
 194 
 195 
 196 static zip_uint32_t
 197 _zip_unicode_to_utf8(zip_uint32_t codepoint, zip_uint8_t *buf)
 198 {
 199     if (codepoint < 0x0080) {
 200         buf[0] = codepoint & 0xff;
 201         return 1;
 202     }
 203     if (codepoint < 0x0800) {
 204         buf[0] = UTF_8_LEN_2_MATCH | ((codepoint >> 6) & 0x1f);
 205         buf[1] = UTF_8_CONTINUE_MATCH | (codepoint & 0x3f);
 206         return 2;
 207     }
 208     if (codepoint < 0x10000) {
 209         buf[0] = UTF_8_LEN_3_MATCH | ((codepoint >> 12) & 0x0f);
 210         buf[1] = UTF_8_CONTINUE_MATCH | ((codepoint >> 6) & 0x3f);
 211         buf[2] = UTF_8_CONTINUE_MATCH | (codepoint & 0x3f);
 212         return 3;
 213     }
 214     buf[0] = UTF_8_LEN_4_MATCH | ((codepoint >> 18) & 0x07);
 215     buf[1] = UTF_8_CONTINUE_MATCH | ((codepoint >> 12) & 0x3f);
 216     buf[2] = UTF_8_CONTINUE_MATCH | ((codepoint >> 6) & 0x3f);
 217     buf[3] = UTF_8_CONTINUE_MATCH | (codepoint & 0x3f);
 218     return 4;
 219 }
 220 
 221 
 222 
 223 zip_uint8_t *
 224 _zip_cp437_to_utf8(const zip_uint8_t * const _cp437buf, zip_uint32_t len,
 225                    zip_uint32_t *utf8_lenp, struct zip_error *error)
 226 {
 227     zip_uint8_t *cp437buf = (zip_uint8_t *)_cp437buf;
 228     zip_uint8_t *utf8buf;
 229     zip_uint32_t buflen, i, offset;
 230 
 231     if (len == 0) {
 232         if (utf8_lenp)
 233             *utf8_lenp = 0;
 234         return NULL;
 235     }
 236 
 237     buflen = 1;
 238     for (i=0; i<len; i++)
 239         buflen += _zip_unicode_to_utf8_len(_cp437_to_unicode[cp437buf[i]]);
 240 
 241     if ((utf8buf=(zip_uint8_t*)malloc(buflen)) == NULL) {
 242         _zip_error_set(error, ZIP_ER_MEMORY, 0);
 243         return NULL;
 244     }
 245 
 246     offset = 0;
 247     for (i=0; i<len; i++)
 248         offset += _zip_unicode_to_utf8(_cp437_to_unicode[cp437buf[i]],
 249                                        utf8buf+offset);
 250 
 251     utf8buf[buflen-1] = 0;
 252     if (utf8_lenp)
 253         *utf8_lenp = buflen-1;
 254     return utf8buf;
 255 }