/js/lib/Socket.IO-node/support/expresso/deps/jscoverage/encoding.c

http://github.com/onedayitwillmake/RealtimeMultiplayerNodeJs · C · 315 lines · 259 code · 37 blank · 19 comment · 31 complexity · 7a327ada998ce4cafc9bf50ce0c0d1f2 MD5 · raw file

  1. /*
  2. encoding.c - character encoding
  3. Copyright (C) 2008 siliconforks.com
  4. This program is free software; you can redistribute it and/or modify
  5. it under the terms of the GNU General Public License as published by
  6. the Free Software Foundation; either version 2 of the License, or
  7. (at your option) any later version.
  8. This program is distributed in the hope that it will be useful,
  9. but WITHOUT ANY WARRANTY; without even the implied warranty of
  10. MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  11. GNU General Public License for more details.
  12. You should have received a copy of the GNU General Public License along
  13. with this program; if not, write to the Free Software Foundation, Inc.,
  14. 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  15. */
  16. #include <config.h>
  17. #include "encoding.h"
  18. #include <assert.h>
  19. #include <limits.h>
  20. #include <string.h>
  21. #ifdef HAVE_ICONV_H
  22. #include <iconv.h>
  23. #elif defined HAVE_WINDOWS_H
  24. #include <windows.h>
  25. #endif
  26. #include "util.h"
  27. static void skip_bom(jschar ** characters, size_t * num_characters) {
  28. jschar * c = *characters;
  29. size_t nc = *num_characters;
  30. size_t i;
  31. for (i = 0; i < nc; i++) {
  32. if (c[i] != 0xfeff) {
  33. break;
  34. }
  35. }
  36. if (i == 0) {
  37. return;
  38. }
  39. nc -= i;
  40. jschar * old = c;
  41. c = xnew(jschar, nc);
  42. memcpy(c, old + i, nc * sizeof(jschar));
  43. free(old);
  44. *characters = c;
  45. *num_characters = nc;
  46. }
  47. #ifdef HAVE_ICONV
  48. #ifdef WORDS_BIGENDIAN
  49. #define UTF_16_INTERNAL "UTF-16BE"
  50. #else
  51. #define UTF_16_INTERNAL "UTF-16LE"
  52. #endif
  53. int jscoverage_bytes_to_characters(const char * encoding, const uint8_t * bytes, size_t num_bytes, jschar ** characters, size_t * num_characters) {
  54. assert(encoding != NULL);
  55. iconv_t state = iconv_open(UTF_16_INTERNAL, encoding);
  56. if (state == (iconv_t) -1) {
  57. return JSCOVERAGE_ERROR_ENCODING_NOT_SUPPORTED;
  58. }
  59. ICONV_CONST char * input = (char *) bytes;
  60. size_t input_bytes_left = num_bytes;
  61. jschar * c = xnew(jschar, num_bytes);
  62. char * output = (char *) c;
  63. size_t output_bytes_left = sizeof(jschar) * num_bytes;
  64. size_t result = iconv(state, &input, &input_bytes_left, &output, &output_bytes_left);
  65. iconv_close(state);
  66. if (result == (size_t) -1) {
  67. free(c);
  68. return JSCOVERAGE_ERROR_INVALID_BYTE_SEQUENCE;
  69. }
  70. assert(input_bytes_left == 0);
  71. size_t nc = ((jschar *) output) - c;
  72. skip_bom(&c, &nc);
  73. *characters = c;
  74. *num_characters = nc;
  75. return 0;
  76. }
  77. #elif HAVE_MULTIBYTETOWIDECHAR
  78. /* http://msdn.microsoft.com/en-us/library/ms776446(VS.85).aspx */
  79. static struct CodePage {
  80. UINT value;
  81. LPCSTR string;
  82. } code_pages[] = {
  83. {37, "IBM037"}, /* IBM EBCDIC US-Canada */
  84. {437, "IBM437"}, /* OEM United States */
  85. {500, "IBM500"}, /* IBM EBCDIC International */
  86. {708, "ASMO-708"}, /* Arabic (ASMO 708) */
  87. {720, "DOS-720"}, /* Arabic (Transparent ASMO); Arabic (DOS) */
  88. {737, "ibm737"}, /* OEM Greek (formerly 437G); Greek (DOS) */
  89. {775, "ibm775"}, /* OEM Baltic; Baltic (DOS) */
  90. {850, "ibm850"}, /* OEM Multilingual Latin 1; Western European (DOS) */
  91. {852, "ibm852"}, /* OEM Latin 2; Central European (DOS) */
  92. {855, "IBM855"}, /* OEM Cyrillic (primarily Russian) */
  93. {857, "ibm857"}, /* OEM Turkish; Turkish (DOS) */
  94. {858, "IBM00858"}, /* OEM Multilingual Latin 1 + Euro symbol */
  95. {860, "IBM860"}, /* OEM Portuguese; Portuguese (DOS) */
  96. {861, "ibm861"}, /* OEM Icelandic; Icelandic (DOS) */
  97. {862, "DOS-862"}, /* OEM Hebrew; Hebrew (DOS) */
  98. {863, "IBM863"}, /* OEM French Canadian; French Canadian (DOS) */
  99. {864, "IBM864"}, /* OEM Arabic; Arabic (864) */
  100. {865, "IBM865"}, /* OEM Nordic; Nordic (DOS) */
  101. {866, "cp866"}, /* OEM Russian; Cyrillic (DOS) */
  102. {869, "ibm869"}, /* OEM Modern Greek; Greek, Modern (DOS) */
  103. {870, "IBM870"}, /* IBM EBCDIC Multilingual/ROECE (Latin 2); IBM EBCDIC Multilingual Latin 2 */
  104. {874, "windows-874"}, /* ANSI/OEM Thai (same as 28605, ISO 8859-15); Thai (Windows) */
  105. {875, "cp875"}, /* IBM EBCDIC Greek Modern */
  106. {932, "shift_jis"}, /* ANSI/OEM Japanese; Japanese (Shift-JIS) */
  107. {936, "gb2312"}, /* ANSI/OEM Simplified Chinese (PRC, Singapore); Chinese Simplified (GB2312) */
  108. {949, "ks_c_5601-1987"}, /* ANSI/OEM Korean (Unified Hangul Code) */
  109. {950, "big5"}, /* ANSI/OEM Traditional Chinese (Taiwan; Hong Kong SAR, PRC); Chinese Traditional (Big5) */
  110. {1026, "IBM1026"}, /* IBM EBCDIC Turkish (Latin 5) */
  111. {1047, "IBM01047"}, /* IBM EBCDIC Latin 1/Open System */
  112. {1140, "IBM01140"}, /* IBM EBCDIC US-Canada (037 + Euro symbol); IBM EBCDIC (US-Canada-Euro) */
  113. {1141, "IBM01141"}, /* IBM EBCDIC Germany (20273 + Euro symbol); IBM EBCDIC (Germany-Euro) */
  114. {1142, "IBM01142"}, /* IBM EBCDIC Denmark-Norway (20277 + Euro symbol); IBM EBCDIC (Denmark-Norway-Euro) */
  115. {1143, "IBM01143"}, /* IBM EBCDIC Finland-Sweden (20278 + Euro symbol); IBM EBCDIC (Finland-Sweden-Euro) */
  116. {1144, "IBM01144"}, /* IBM EBCDIC Italy (20280 + Euro symbol); IBM EBCDIC (Italy-Euro) */
  117. {1145, "IBM01145"}, /* IBM EBCDIC Latin America-Spain (20284 + Euro symbol); IBM EBCDIC (Spain-Euro) */
  118. {1146, "IBM01146"}, /* IBM EBCDIC United Kingdom (20285 + Euro symbol); IBM EBCDIC (UK-Euro) */
  119. {1147, "IBM01147"}, /* IBM EBCDIC France (20297 + Euro symbol); IBM EBCDIC (France-Euro) */
  120. {1148, "IBM01148"}, /* IBM EBCDIC International (500 + Euro symbol); IBM EBCDIC (International-Euro) */
  121. {1149, "IBM01149"}, /* IBM EBCDIC Icelandic (20871 + Euro symbol); IBM EBCDIC (Icelandic-Euro) */
  122. {1200, "utf-16"}, /* Unicode UTF-16, little endian byte order (BMP of ISO 10646); available only to managed applications */
  123. {1201, "unicodeFFFE"}, /* Unicode UTF-16, big endian byte order; available only to managed applications */
  124. {1250, "windows-1250"}, /* ANSI Central European; Central European (Windows) */
  125. {1251, "windows-1251"}, /* ANSI Cyrillic; Cyrillic (Windows) */
  126. {1252, "windows-1252"}, /* ANSI Latin 1; Western European (Windows) */
  127. {1253, "windows-1253"}, /* ANSI Greek; Greek (Windows) */
  128. {1254, "windows-1254"}, /* ANSI Turkish; Turkish (Windows) */
  129. {1255, "windows-1255"}, /* ANSI Hebrew; Hebrew (Windows) */
  130. {1256, "windows-1256"}, /* ANSI Arabic; Arabic (Windows) */
  131. {1257, "windows-1257"}, /* ANSI Baltic; Baltic (Windows) */
  132. {1258, "windows-1258"}, /* ANSI/OEM Vietnamese; Vietnamese (Windows) */
  133. {1361, "Johab"}, /* Korean (Johab) */
  134. {10000, "macintosh"}, /* MAC Roman; Western European (Mac) */
  135. {10001, "x-mac-japanese"}, /* Japanese (Mac) */
  136. {10002, "x-mac-chinesetrad"}, /* MAC Traditional Chinese (Big5); Chinese Traditional (Mac) */
  137. {10003, "x-mac-korean"}, /* Korean (Mac) */
  138. {10004, "x-mac-arabic"}, /* Arabic (Mac) */
  139. {10005, "x-mac-hebrew"}, /* Hebrew (Mac) */
  140. {10006, "x-mac-greek"}, /* Greek (Mac) */
  141. {10007, "x-mac-cyrillic"}, /* Cyrillic (Mac) */
  142. {10008, "x-mac-chinesesimp"}, /* MAC Simplified Chinese (GB 2312); Chinese Simplified (Mac) */
  143. {10010, "x-mac-romanian"}, /* Romanian (Mac) */
  144. {10017, "x-mac-ukrainian"}, /* Ukrainian (Mac) */
  145. {10021, "x-mac-thai"}, /* Thai (Mac) */
  146. {10029, "x-mac-ce"}, /* MAC Latin 2; Central European (Mac) */
  147. {10079, "x-mac-icelandic"}, /* Icelandic (Mac) */
  148. {10081, "x-mac-turkish"}, /* Turkish (Mac) */
  149. {10082, "x-mac-croatian"}, /* Croatian (Mac) */
  150. {12000, "utf-32"}, /* Unicode UTF-32, little endian byte order; available only to managed applications */
  151. {12001, "utf-32BE"}, /* Unicode UTF-32, big endian byte order; available only to managed applications */
  152. {20000, "x-Chinese_CNS"}, /* CNS Taiwan; Chinese Traditional (CNS) */
  153. {20001, "x-cp20001"}, /* TCA Taiwan */
  154. {20002, "x_Chinese-Eten"}, /* Eten Taiwan; Chinese Traditional (Eten) */
  155. {20003, "x-cp20003"}, /* IBM5550 Taiwan */
  156. {20004, "x-cp20004"}, /* TeleText Taiwan */
  157. {20005, "x-cp20005"}, /* Wang Taiwan */
  158. {20105, "x-IA5"}, /* IA5 (IRV International Alphabet No. 5, 7-bit); Western European (IA5) */
  159. {20106, "x-IA5-German"}, /* IA5 German (7-bit) */
  160. {20107, "x-IA5-Swedish"}, /* IA5 Swedish (7-bit) */
  161. {20108, "x-IA5-Norwegian"}, /* IA5 Norwegian (7-bit) */
  162. {20127, "us-ascii"}, /* US-ASCII (7-bit) */
  163. {20261, "x-cp20261"}, /* T.61 */
  164. {20269, "x-cp20269"}, /* ISO 6937 Non-Spacing Accent */
  165. {20273, "IBM273"}, /* IBM EBCDIC Germany */
  166. {20277, "IBM277"}, /* IBM EBCDIC Denmark-Norway */
  167. {20278, "IBM278"}, /* IBM EBCDIC Finland-Sweden */
  168. {20280, "IBM280"}, /* IBM EBCDIC Italy */
  169. {20284, "IBM284"}, /* IBM EBCDIC Latin America-Spain */
  170. {20285, "IBM285"}, /* IBM EBCDIC United Kingdom */
  171. {20290, "IBM290"}, /* IBM EBCDIC Japanese Katakana Extended */
  172. {20297, "IBM297"}, /* IBM EBCDIC France */
  173. {20420, "IBM420"}, /* IBM EBCDIC Arabic */
  174. {20423, "IBM423"}, /* IBM EBCDIC Greek */
  175. {20424, "IBM424"}, /* IBM EBCDIC Hebrew */
  176. {20833, "x-EBCDIC-KoreanExtended"}, /* IBM EBCDIC Korean Extended */
  177. {20838, "IBM-Thai"}, /* IBM EBCDIC Thai */
  178. {20866, "koi8-r"}, /* Russian (KOI8-R); Cyrillic (KOI8-R) */
  179. {20871, "IBM871"}, /* IBM EBCDIC Icelandic */
  180. {20880, "IBM880"}, /* IBM EBCDIC Cyrillic Russian */
  181. {20905, "IBM905"}, /* IBM EBCDIC Turkish */
  182. {20924, "IBM00924"}, /* IBM EBCDIC Latin 1/Open System (1047 + Euro symbol) */
  183. {20932, "EUC-JP"}, /* Japanese (JIS 0208-1990 and 0121-1990) */
  184. {20936, "x-cp20936"}, /* Simplified Chinese (GB2312); Chinese Simplified (GB2312-80) */
  185. {20949, "x-cp20949"}, /* Korean Wansung */
  186. {21025, "cp1025"}, /* IBM EBCDIC Cyrillic Serbian-Bulgarian */
  187. {21866, "koi8-u"}, /* Ukrainian (KOI8-U); Cyrillic (KOI8-U) */
  188. {28591, "iso-8859-1"}, /* ISO 8859-1 Latin 1; Western European (ISO) */
  189. {28592, "iso-8859-2"}, /* ISO 8859-2 Central European; Central European (ISO) */
  190. {28593, "iso-8859-3"}, /* ISO 8859-3 Latin 3 */
  191. {28594, "iso-8859-4"}, /* ISO 8859-4 Baltic */
  192. {28595, "iso-8859-5"}, /* ISO 8859-5 Cyrillic */
  193. {28596, "iso-8859-6"}, /* ISO 8859-6 Arabic */
  194. {28597, "iso-8859-7"}, /* ISO 8859-7 Greek */
  195. {28598, "iso-8859-8"}, /* ISO 8859-8 Hebrew; Hebrew (ISO-Visual) */
  196. {28599, "iso-8859-9"}, /* ISO 8859-9 Turkish */
  197. {28603, "iso-8859-13"}, /* ISO 8859-13 Estonian */
  198. {28605, "iso-8859-15"}, /* ISO 8859-15 Latin 9 */
  199. {29001, "x-Europa"}, /* Europa 3 */
  200. {38598, "iso-8859-8-i"}, /* ISO 8859-8 Hebrew; Hebrew (ISO-Logical) */
  201. {50220, "iso-2022-jp"}, /* ISO 2022 Japanese with no halfwidth Katakana; Japanese (JIS) */
  202. {50221, "csISO2022JP"}, /* ISO 2022 Japanese with halfwidth Katakana; Japanese (JIS-Allow 1 byte Kana) */
  203. {50222, "iso-2022-jp"}, /* ISO 2022 Japanese JIS X 0201-1989; Japanese (JIS-Allow 1 byte Kana - SO/SI) */
  204. {50225, "iso-2022-kr"}, /* ISO 2022 Korean */
  205. {50227, "x-cp50227"}, /* ISO 2022 Simplified Chinese; Chinese Simplified (ISO 2022) */
  206. {51932, "euc-jp"}, /* EUC Japanese */
  207. {51936, "EUC-CN"}, /* EUC Simplified Chinese; Chinese Simplified (EUC) */
  208. {51949, "euc-kr"}, /* EUC Korean */
  209. {52936, "hz-gb-2312"}, /* HZ-GB2312 Simplified Chinese; Chinese Simplified (HZ) */
  210. {54936, "GB18030"}, /* Windows XP and later: GB18030 Simplified Chinese (4 byte); Chinese Simplified (GB18030) */
  211. {57002, "x-iscii-de"}, /* ISCII Devanagari */
  212. {57003, "x-iscii-be"}, /* ISCII Bengali */
  213. {57004, "x-iscii-ta"}, /* ISCII Tamil */
  214. {57005, "x-iscii-te"}, /* ISCII Telugu */
  215. {57006, "x-iscii-as"}, /* ISCII Assamese */
  216. {57007, "x-iscii-or"}, /* ISCII Oriya */
  217. {57008, "x-iscii-ka"}, /* ISCII Kannada */
  218. {57009, "x-iscii-ma"}, /* ISCII Malayalam */
  219. {57010, "x-iscii-gu"}, /* ISCII Gujarati */
  220. {57011, "x-iscii-pa"}, /* ISCII Punjabi */
  221. {65000, "utf-7"}, /* Unicode (UTF-7) */
  222. {65001, "utf-8"}, /* Unicode (UTF-8) */
  223. };
  224. int find_code_page(const char * encoding, UINT * code_page) {
  225. for (size_t i = 0; i < sizeof(code_pages) / sizeof(code_pages[0]); i++) {
  226. if (strcasecmp(encoding, code_pages[i].string) == 0) {
  227. *code_page = code_pages[i].value;
  228. return 0;
  229. }
  230. }
  231. return -1;
  232. }
  233. int jscoverage_bytes_to_characters(const char * encoding, const uint8_t * bytes, size_t num_bytes, jschar ** characters, size_t * num_characters) {
  234. assert(encoding != NULL);
  235. if (num_bytes == 0) {
  236. *characters = xnew(jschar, 0);
  237. *num_characters = 0;
  238. return 0;
  239. }
  240. UINT code_page;
  241. if (find_code_page(encoding, &code_page) != 0) {
  242. return JSCOVERAGE_ERROR_ENCODING_NOT_SUPPORTED;
  243. }
  244. if (num_bytes > INT_MAX) {
  245. fatal("overflow");
  246. }
  247. *characters = xnew(jschar, num_bytes);
  248. int result = MultiByteToWideChar(code_page, MB_ERR_INVALID_CHARS, bytes, num_bytes, *characters, num_bytes);
  249. if (result == 0) {
  250. free(*characters);
  251. return JSCOVERAGE_ERROR_INVALID_BYTE_SEQUENCE;
  252. }
  253. *num_characters = result;
  254. skip_bom(characters, num_characters);
  255. return 0;
  256. }
  257. #else
  258. int jscoverage_bytes_to_characters(const char * encoding, const uint8_t * bytes, size_t num_bytes, jschar ** characters, size_t * num_characters) {
  259. assert(encoding != NULL);
  260. if (strcasecmp(encoding, "us-ascii") != 0 && strcasecmp(encoding, "iso-8859-1") != 0 && strcasecmp(encoding, "utf-8") != 0) {
  261. return JSCOVERAGE_ERROR_ENCODING_NOT_SUPPORTED;
  262. }
  263. jschar * c = xnew(jschar, num_bytes);
  264. for (size_t i = 0; i < num_bytes; i++) {
  265. if (bytes[i] > 127) {
  266. free(c);
  267. return JSCOVERAGE_ERROR_ENCODING_NOT_SUPPORTED;
  268. }
  269. c[i] = bytes[i];
  270. }
  271. *characters = c;
  272. *num_characters = num_bytes;
  273. return 0;
  274. }
  275. #endif