zip_utf-8.c 7.6 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255
  1. /*
  2. zip_utf-8.c -- UTF-8 support functions for libzip
  3. Copyright (C) 2011-2012 Dieter Baron and Thomas Klausner
  4. This file is part of libzip, a library to manipulate ZIP archives.
  5. The authors can be contacted at <[email protected]>
  6. Redistribution and use in source and binary forms, with or without
  7. modification, are permitted provided that the following conditions
  8. are met:
  9. 1. Redistributions of source code must retain the above copyright
  10. notice, this list of conditions and the following disclaimer.
  11. 2. Redistributions in binary form must reproduce the above copyright
  12. notice, this list of conditions and the following disclaimer in
  13. the documentation and/or other materials provided with the
  14. distribution.
  15. 3. The names of the authors may not be used to endorse or promote
  16. products derived from this software without specific prior
  17. written permission.
  18. THIS SOFTWARE IS PROVIDED BY THE AUTHORS ``AS IS'' AND ANY EXPRESS
  19. OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
  20. WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  21. ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY
  22. DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  23. DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE
  24. GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
  25. INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER
  26. IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
  27. OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
  28. IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  29. */
  30. #include "zipint.h"
  31. #include <stdlib.h>
  32. static const zip_uint16_t _cp437_to_unicode[256] = {
  33. /* 0x00 - 0x0F */
  34. 0x2007, 0x263A, 0x263B, 0x2665, 0x2666, 0x2663, 0x2660, 0x2022,
  35. 0x25D8, 0x25CB, 0x25D9, 0x2642, 0x2640, 0x266A, 0x266B, 0x263C,
  36. /* 0x10 - 0x1F */
  37. 0x25BA, 0x25C4, 0x2195, 0x203C, 0x00B6, 0x00A7, 0x25AC, 0x21A8,
  38. 0x2191, 0x2193, 0x2192, 0x2190, 0x221F, 0x2194, 0x25B2, 0x25BC,
  39. /* 0x20 - 0x2F */
  40. 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027,
  41. 0x0028, 0x0029, 0x002A, 0x002B, 0x002C, 0x002D, 0x002E, 0x002F,
  42. /* 0x30 - 0x3F */
  43. 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037,
  44. 0x0038, 0x0039, 0x003A, 0x003B, 0x003C, 0x003D, 0x003E, 0x003F,
  45. /* 0x40 - 0x4F */
  46. 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047,
  47. 0x0048, 0x0049, 0x004A, 0x004B, 0x004C, 0x004D, 0x004E, 0x004F,
  48. /* 0x50 - 0x5F */
  49. 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057,
  50. 0x0058, 0x0059, 0x005A, 0x005B, 0x005C, 0x005D, 0x005E, 0x005F,
  51. /* 0x60 - 0x6F */
  52. 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067,
  53. 0x0068, 0x0069, 0x006A, 0x006B, 0x006C, 0x006D, 0x006E, 0x006F,
  54. /* 0x70 - 0x7F */
  55. 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077,
  56. 0x0078, 0x0079, 0x007A, 0x007B, 0x007C, 0x007D, 0x007E, 0x2302,
  57. /* 0x80 - 0x8F */
  58. 0x00C7, 0x00FC, 0x00E9, 0x00E2, 0x00E4, 0x00E0, 0x00E5, 0x00E7,
  59. 0x00EA, 0x00EB, 0x00E8, 0x00EF, 0x00EE, 0x00EC, 0x00C4, 0x00C5,
  60. /* 0x90 - 0x9F */
  61. 0x00C9, 0x00E6, 0x00C6, 0x00F4, 0x00F6, 0x00F2, 0x00FB, 0x00F9,
  62. 0x00FF, 0x00D6, 0x00DC, 0x00A2, 0x00A3, 0x00A5, 0x20A7, 0x0192,
  63. /* 0xA0 - 0xAF */
  64. 0x00E1, 0x00ED, 0x00F3, 0x00FA, 0x00F1, 0x00D1, 0x00AA, 0x00BA,
  65. 0x00BF, 0x2310, 0x00AC, 0x00BD, 0x00BC, 0x00A1, 0x00AB, 0x00BB,
  66. /* 0xB0 - 0xBF */
  67. 0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x2561, 0x2562, 0x2556,
  68. 0x2555, 0x2563, 0x2551, 0x2557, 0x255D, 0x255C, 0x255B, 0x2510,
  69. /* 0xC0 - 0xCF */
  70. 0x2514, 0x2534, 0x252C, 0x251C, 0x2500, 0x253C, 0x255E, 0x255F,
  71. 0x255A, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256C, 0x2567,
  72. /* 0xD0 - 0xDF */
  73. 0x2568, 0x2564, 0x2565, 0x2559, 0x2558, 0x2552, 0x2553, 0x256B,
  74. 0x256A, 0x2518, 0x250C, 0x2588, 0x2584, 0x258C, 0x2590, 0x2580,
  75. /* 0xE0 - 0xEF */
  76. 0x03B1, 0x00DF, 0x0393, 0x03C0, 0x03A3, 0x03C3, 0x00B5, 0x03C4,
  77. 0x03A6, 0x0398, 0x03A9, 0x03B4, 0x221E, 0x03C6, 0x03B5, 0x2229,
  78. /* 0xF0 - 0xFF */
  79. 0x2261, 0x00B1, 0x2265, 0x2264, 0x2320, 0x2321, 0x00F7, 0x2248,
  80. 0x00B0, 0x2219, 0x00B7, 0x221A, 0x207F, 0x00B2, 0x25A0, 0x00A0
  81. };
  82. #define UTF_8_LEN_2_MASK 0xe0
  83. #define UTF_8_LEN_2_MATCH 0xc0
  84. #define UTF_8_LEN_3_MASK 0xf0
  85. #define UTF_8_LEN_3_MATCH 0xe0
  86. #define UTF_8_LEN_4_MASK 0xf8
  87. #define UTF_8_LEN_4_MATCH 0xf0
  88. #define UTF_8_CONTINUE_MASK 0xc0
  89. #define UTF_8_CONTINUE_MATCH 0x80
  90. enum zip_encoding_type
  91. _zip_guess_encoding(struct zip_string *str, enum zip_encoding_type expected_encoding)
  92. {
  93. enum zip_encoding_type enc;
  94. const zip_uint8_t *name;
  95. zip_uint32_t i, j, ulen;
  96. if (str == NULL)
  97. return ZIP_ENCODING_ASCII;
  98. name = str->raw;
  99. if (str->encoding != ZIP_ENCODING_UNKNOWN)
  100. enc = str->encoding;
  101. else {
  102. enc = ZIP_ENCODING_ASCII;
  103. for (i=0; i<str->length; i++) {
  104. if ((name[i] > 31 && name[i] < 128) || name[i] == '\r' || name[i] == '\n' || name[i] == '\t')
  105. continue;
  106. enc = ZIP_ENCODING_UTF8_GUESSED;
  107. if ((name[i] & UTF_8_LEN_2_MASK) == UTF_8_LEN_2_MATCH)
  108. ulen = 1;
  109. else if ((name[i] & UTF_8_LEN_3_MASK) == UTF_8_LEN_3_MATCH)
  110. ulen = 2;
  111. else if ((name[i] & UTF_8_LEN_4_MASK) == UTF_8_LEN_4_MATCH)
  112. ulen = 3;
  113. else {
  114. enc = ZIP_ENCODING_CP437;
  115. break;
  116. }
  117. if (i + ulen >= str->length) {
  118. enc = ZIP_ENCODING_CP437;
  119. break;
  120. }
  121. for (j=1; j<=ulen; j++) {
  122. if ((name[i+j] & UTF_8_CONTINUE_MASK) != UTF_8_CONTINUE_MATCH) {
  123. enc = ZIP_ENCODING_CP437;
  124. goto done;
  125. }
  126. }
  127. i += ulen;
  128. }
  129. }
  130. done:
  131. str->encoding = enc;
  132. if (expected_encoding != ZIP_ENCODING_UNKNOWN) {
  133. if (expected_encoding == ZIP_ENCODING_UTF8_KNOWN && enc == ZIP_ENCODING_UTF8_GUESSED)
  134. str->encoding = enc = ZIP_ENCODING_UTF8_KNOWN;
  135. if (expected_encoding != enc && enc != ZIP_ENCODING_ASCII)
  136. return ZIP_ENCODING_ERROR;
  137. }
  138. return enc;
  139. }
  140. static zip_uint32_t
  141. _zip_unicode_to_utf8_len(zip_uint32_t codepoint)
  142. {
  143. if (codepoint < 0x0080)
  144. return 1;
  145. if (codepoint < 0x0800)
  146. return 2;
  147. if (codepoint < 0x10000)
  148. return 3;
  149. return 4;
  150. }
  151. static zip_uint32_t
  152. _zip_unicode_to_utf8(zip_uint32_t codepoint, zip_uint8_t *buf)
  153. {
  154. if (codepoint < 0x0080) {
  155. buf[0] = codepoint & 0xff;
  156. return 1;
  157. }
  158. if (codepoint < 0x0800) {
  159. buf[0] = UTF_8_LEN_2_MATCH | ((codepoint >> 6) & 0x1f);
  160. buf[1] = UTF_8_CONTINUE_MATCH | (codepoint & 0x3f);
  161. return 2;
  162. }
  163. if (codepoint < 0x10000) {
  164. buf[0] = UTF_8_LEN_3_MATCH | ((codepoint >> 12) & 0x0f);
  165. buf[1] = UTF_8_CONTINUE_MATCH | ((codepoint >> 6) & 0x3f);
  166. buf[2] = UTF_8_CONTINUE_MATCH | (codepoint & 0x3f);
  167. return 3;
  168. }
  169. buf[0] = UTF_8_LEN_4_MATCH | ((codepoint >> 18) & 0x07);
  170. buf[1] = UTF_8_CONTINUE_MATCH | ((codepoint >> 12) & 0x3f);
  171. buf[2] = UTF_8_CONTINUE_MATCH | ((codepoint >> 6) & 0x3f);
  172. buf[3] = UTF_8_CONTINUE_MATCH | (codepoint & 0x3f);
  173. return 4;
  174. }
  175. zip_uint8_t *
  176. _zip_cp437_to_utf8(const zip_uint8_t * const _cp437buf, zip_uint32_t len,
  177. zip_uint32_t *utf8_lenp, struct zip_error *error)
  178. {
  179. zip_uint8_t *cp437buf = (zip_uint8_t *)_cp437buf;
  180. zip_uint8_t *utf8buf;
  181. zip_uint32_t buflen, i, offset;
  182. if (len == 0) {
  183. if (utf8_lenp)
  184. *utf8_lenp = 0;
  185. return NULL;
  186. }
  187. buflen = 1;
  188. for (i=0; i<len; i++)
  189. buflen += _zip_unicode_to_utf8_len(_cp437_to_unicode[cp437buf[i]]);
  190. if ((utf8buf=(zip_uint8_t*)malloc(buflen)) == NULL) {
  191. _zip_error_set(error, ZIP_ER_MEMORY, 0);
  192. return NULL;
  193. }
  194. offset = 0;
  195. for (i=0; i<len; i++)
  196. offset += _zip_unicode_to_utf8(_cp437_to_unicode[cp437buf[i]],
  197. utf8buf+offset);
  198. utf8buf[buflen-1] = 0;
  199. if (utf8_lenp)
  200. *utf8_lenp = buflen-1;
  201. return utf8buf;
  202. }