📄 utf8fix.c
字号:
{"象", 0.078045},
{"重", 0.126537},
{"去", 0.330934},
{"再", 0.117460},
{"光", 0.084711},
{"百", 0.072738},
{"却", 0.105046},
{"呢", 0.056342},
{"界", 0.083728},
{"变", 0.064229},
{"回", 0.156121},
{"车", 0.089804},
{"党", 0.054791},
{"难", 0.092669},
{"地", 0.430809},
{"吃", 0.072425},
{"办", 0.061534},
{"电", 0.125012},
{"都", 0.252867},
{"产", 0.103862},
{"非", 0.068245},
{"言", 0.064196},
{"间", 0.131700},
{"把", 0.158959},
{"也", 0.412956},
{"候", 0.061082},
{"城", 0.060972},
{"何", 0.088065},
{"新", 0.131476},
{"保", 0.061942},
{"满", 0.057693},
{"关", 0.112545},
{"样", 0.169738},
{"比", 0.097747},
{"面", 0.188836},
{"青", 0.067301},
{"入", 0.103631},
{"题", 0.074605},
{"反", 0.087462},
{"少", 0.112757},
{"院", 0.064434},
{"父", 0.060794},
{"意", 0.161359},
{"进", 0.161229},
{"人", 1.081233},
{"开", 0.211932},
{"目", 0.094628},
{"别", 0.100654},
{"觉", 0.075649},
{"好", 0.253067},
{"成", 0.232004},
{"军", 0.104464},
{"定", 0.141283},
{"又", 0.202277},
{"场", 0.098824},
{"社", 0.071268},
{"接", 0.076121},
{"学", 0.313110},
{"士", 0.059531},
{"天", 0.262760},
{"程", 0.058312},
{"特", 0.075691},
{"每", 0.067385},
{"区", 0.059983},
{"强", 0.060747},
{"通", 0.095327},
{"制", 0.081732},
{"必", 0.060990},
{"平", 0.116858},
{"已", 0.183761},
{"总", 0.099417},
{"用", 0.208392},
{"口", 0.119434},
{"黄", 0.055445},
{"望", 0.075475},
{"权", 0.064165},
{"日", 0.238170},
{"带", 0.065223},
{"看", 0.216015},
{"长", 0.176671},
{"师", 0.098604},
{"于", 0.237050},
{"可", 0.310500},
{"门", 0.123004},
{"先", 0.103316},
{"认", 0.073529},
{"这", 0.748073},
{"从", 0.181841},
{"功", 0.069931},
{"下", 0.366675},
{"由", 0.106073},
{"领", 0.063793},
{"脸", 0.055222},
{"期", 0.089414},
{"本", 0.197245},
{"己", 0.148374},
{"有", 0.846428},
{"法", 0.158459},
{"处", 0.099988},
{"身", 0.167521},
{"边", 0.077498},
{"派", 0.057761},
{"司", 0.084963},
{"论", 0.072820},
{"后", 0.297066},
{"度", 0.074446},
{"许", 0.075854},
{"立", 0.093914},
{"与", 0.165147},
{"信", 0.114573},
{"笑", 0.096279},
{"真", 0.116060},
{"京", 0.082472},
{"动", 0.178348},
{"女", 0.141049},
{"表", 0.090741},
{"加", 0.109685},
{"语", 0.057889},
{"相", 0.122566},
{"完", 0.060534},
{"告", 0.058129},
{"量", 0.059348},
{"件", 0.090981},
{"息", 0.056893},
{"外", 0.167708},
{"计", 0.085688},
{"合", 0.087272},
{"连", 0.067046},
{"眼", 0.101187},
{"空", 0.058894},
{"理", 0.154598},
{"者", 0.145362},
{"经", 0.189995},
{"多", 0.270297},
{"头", 0.189444},
{"给", 0.136868},
{"力", 0.138951},
{"统", 0.074402},
{"高", 0.162739},
{"很", 0.134687},
{"政", 0.120122},
{"常", 0.089189},
{"张", 0.093070},
{"个", 0.594848},
{"路", 0.089668},
{"走", 0.125810},
{"如", 0.201591},
{"子", 0.441396},
{"而", 0.260181},
{"做", 0.086397},
{"和", 0.440206},
{"并", 0.111459},
{"海", 0.119826},
{"队", 0.066006},
{"着", 0.335011},
{"就", 0.389616},
{"二", 0.155393},
{"风", 0.076789},
{"部", 0.143537},
{"同", 0.187525},
{"其", 0.152385},
{"发", 0.232956},
{"红", 0.063231},
{"才", 0.099303},
{"马", 0.093403},
{"快", 0.064661},
{"起", 0.235155},
{"出", 0.425756},
{"服", 0.075191},
{"放", 0.087173},
{"品", 0.059628},
{"英", 0.057878},
{"决", 0.062792},
{"九", 0.096854},
{"气", 0.114705},
{"科", 0.072145},
{"七", 0.061058},
{"应", 0.089767}
};
static const short lookup[] =
{
0, -1, -1, 1, -1, -1, 2, -1,
-1, 3, -1, 4, -1, 5, -1, 6,
7, -1, 8, -1, 9, 10, -1, 11,
-1, 12, 13, -1, 14, -1, 15, 16,
-1, 17, -1, 18, -1, -1, 19, -1,
-1, 20, -1, 21, -1, -1, 22, -1,
-1, 23, 24, 25, -1, 26, -1, 27,
28, -1, 29, -1, 30, 31, -1, 32,
-1, 33, 34, -1, 35, -1, 36, 37,
-1, 38, -1, 39, 40, -1, -482, -1,
43, -359, -2, 44, 45, 46, 47, -1,
48, -1, 49, 50, -1, 51, -1, -1,
52, -1, -1, -1, 53, 54, -1, 55,
-1, 56, 57, -1, 58, 59, 60, 61,
-1, 62, 63, 64, 65, -1, 66, 67,
68, 69, -1, 70, -1, 71, 72, -1,
73, -1, 74, 75, -1, 76, 77, 78,
79, -1, 80, -1, 81, 82, -1, 83,
-1, 84, 85, -1, 86, -1, 87, 88,
-1, 89, 90, 91, -1, -1, 92, -1,
93, 94, -1, 95, -1, 96, 97, -1,
98, -1, 99, 100, -1, 101, -1, 102,
103, -1, 104, -1, -605, 107, -1, 108,
-1, 109, 110, -1, 111, -1, 112, 113,
-1, 114, -1, 115, 116, -1, 117, -1,
118, 119, -1, 120, -295, -2, -1, -1,
121, -1, 122, 123, -1, -1, 124, 125,
126, -1, 127, -1, 128, 129, -1, 130,
-1, 131, 132, -1, 133, -1, 134, 135,
-1, 136, -1, 137, 138, -1, 139, -1,
140, 141, -1, -1, 142, 143, -1, -1,
144, -1, 145, 146, -1, 147, -1, 148,
149, -1, 150, -1, 151, 152, -1, -1,
-1, -1, 153, -1, 154, -1, 155, 156,
-1, 157, -1, 158, 159, -1, 160, -1,
161, -1, -1, 162, -1, 163, 164, -1,
165, -1, 166, -1, -1, 167, -1, 168,
-1, -1, 169, -1, -727, 172, -1, 173,
-1, 174, 175, -1, 176, -1, 177, 178,
-1, 179, -1, 180, 181, -1, 182, -1,
183, 184, -1, 185, -1, 186, -230, -2,
187, -1, 188, -1, -1, 189, -1, 190,
191, -1, 192, -1, 193, 194, -1, 195,
-1, 196, 197, -1, 198, -1, 199, 200,
-1, 201, -1, 202, 203, -1, 204, -1,
205, 206, -1, 207, -1, 208, 209, -1,
210, -1, 211, -1, -1, 212, -1, 213,
-1, -1, 214, -1, 215, 216, -1, -1,
217, 218, 219, -1, 220, -1, 221, 222,
-1, 223, -1, 224, 225, -1, 226, 227,
228, 229, -1, 230, -1, 231, -1, -1,
232, -1, -822, 235, -1, 236, -1, 237,
238, -1, 239, -1, 240, -167, -2, 241,
-1, 242, -1, -1, 243, -1, 244, 245,
-1, 246, 247, 248, 249, -1, 250, -1,
251, 252, -1, 253, 254, 255, -1, -1,
256, -1, 257, 258, -1, 259, -1, 260,
261, -1, 262, -1, 263, 264, -1, 265,
-1, 266, 267, -1, 268, -1, 269, 270,
-1, 271, -1, 272, 273, -1, 274, -1,
275, 276, -1, 277, -1, 278, -1, -1,
279, -1, 280, -1, -1, 281, -1, 282,
-1, -1, 283, -1, 284, -1, -1, 285,
-1, 286, -1, -1, 287, -1, 288, -1,
-1, 289, -1, 290, 291, -1, 292, -1,
293, -1, -1, 294, -1, 295, 296, -1,
297, -1, 298, -1, -1, 299, -1, 300,
-1, -1, 301, -1, 302, -1, -1, 303,
-1, 304, -1, -1, 305, -1, -952, -94,
-2, 308, -1, 309, -1, -1, -1, -1,
310, -1, -1, 311, -1, 312, -1, -1,
313, -1, 314, -1, -1, 315, -1, 316,
-1, -1, 317, -1, 318, -1, -1, 319,
-1, 320, -1, -1, 321, -1, 322, -1,
-1, 323, -1, 324, -1, -1, 325, 326,
327, -1, -1, 328, -1, 329, 330, -1,
331, -1, 332, -1, -1, 333, -1, 334,
-1, -1, -1, -1, 335, 336, -1, 337,
-1, 338, -1, -1, 339, -1, 340, -1,
-1, -1, -1, 341, -1, -1, 342, -1,
343, -1, -1, -1, -1, 344, -1, -1,
-1, -1, 345, -1, -1, 346, -1, 347,
-1, -1, 348, -1, 349, -1, -1, 350,
-1, 351, 352, -1, -1, -1, -1, -1,
-1, -1, -1, 353, -1, -1, 354, -1,
355, -1, -1, -1, -1, 356, -1, -1,
357, -1, 358, -1, -1, -1, -1, 359,
-1, -1, -1, -1, 360, 361, -1, -1,
-1, 362, -1, -1, -1, -1, 363, -1,
-1, 364, -1, 365, -1, -1, 366, -1,
367, -1, -1, 368, -1, -1, -1, -1,
-1, -1, 369, -1, -1, 370, -1, 371,
-1, -1, 372, -1, -1, -1, -1, -1,
-1, 373, -1, -1, -1, -1, -1, -1,
-1, 374, -1, 375, -1, -1, 376, -1,
377, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, 378,
-1, -1, 379, -1, 380, -1, -1, -1,
-1, 381, -1, -1, -1, -1, -1, -1,
-1, -1, -1, 382, -1, -1, -1, -1,
-1, -1, -1, -1, -1, 383, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, 384, -1, -1,
-1, -1, -1, -1, 385, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1,
-1, 386, -1, -1, -1, -1, -1, -1,
387, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, 388, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, 389, -1, -1, -1, -1,
390, -1, -1, -1, -1, -1, -1, -1,
391, -1, 392, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1,
-1, 393, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, 394, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, 395, -1, -1, -1, -1,
396, -1, 397, -1, -1, -1, -1, -1,
-1, -1, -1, -1, 398, -1, -1, -1,
-1, -1, -1, -1, -1, -1, 399
};
if (len <= MAX_WORD_LENGTH && len >= MIN_WORD_LENGTH)
{
register int key = gbHash (str, len);
if (key <= MAX_HASH_VALUE && key >= 0)
{
register int index = lookup[key];
if (index >= 0)
{
register const char *s = wordlist[index].name;
if (*str == *s && !_ogg_strncmp (str + 1, s + 1, len - 1))
return &wordlist[index];
}
else if (index < -TOTAL_KEYWORDS)
{
register int offset = - 1 - TOTAL_KEYWORDS - index;
register const struct charHz *wordptr = &wordlist[TOTAL_KEYWORDS + lookup[offset]];
register const struct charHz *wordendptr = wordptr + -lookup[offset + 1];
while (wordptr < wordendptr)
{
register const char *s = wordptr->name;
if (*str == *s && !_ogg_strncmp (str + 1, s + 1, len - 1))
return wordptr;
wordptr++;
}
}
}
}
return 0;
}
/* ANSI-C code produced by gperf version 2.7.1 (19981006 egcs) */
/* Command-line: gperf -L ANSI-C -I -t -H b5Hash -N inBig5 -C -E -o -n -c -D b5percent.txt */
/****************************************************
400 Most frequently used BIG5 chars in GB code space.
The percentage is taken over all BIG5 code space.
****************************************************/
/* maximum key range = 986, duplicates = 4 */
#ifdef __GNUC__
__inline
#endif
static unsigned int
b5Hash (register const char *str, register unsigned int len)
{
static const unsigned short asso_values[] =
{
986, 986, 986, 986, 986, 986, 986, 986, 986, 986,
986, 986, 986, 986, 986, 986, 986, 986, 986, 986,
986, 986, 986, 986, 986, 986, 986, 986, 986, 986,
986, 986, 986, 986, 986, 986, 986, 986, 986, 986,
986, 986, 986, 986, 986, 986, 986, 986, 986, 986,
986, 986, 986, 986, 986, 986, 986, 986, 986, 986,
986, 986, 986, 986, 986, 986, 986, 986, 986, 986,
986, 986, 986, 986, 986, 986, 986, 986, 986, 986,
986, 986, 986, 986, 986, 986, 986, 986, 986, 986,
986, 986, 986, 986, 986, 986, 986, 986, 986, 986,
986, 986, 986, 986, 986, 986, 986, 986, 986, 986,
986, 986, 986, 986, 986, 986, 986, 986, 986, 986,
986, 986, 986, 986, 986, 986, 986, 986, 986, 986,
986, 986, 986, 986, 986, 986, 986, 986, 986, 986,
986, 986, 986, 986, 986, 986, 986, 986, 986, 986,
986, 986, 986, 986, 986, 986, 986, 986, 986, 986,
986, 81, 0, 166, 0, 55, 35, 5, 396, 21,
116, 80, 265, 19, 986, 311, 28, 25, 345, 105,
215, 95, 10, 415, 30, 468, 40, 110, 330, 80,
155, 480, 180, 333, 21, 498, 188, 190, 89, 453,
200, 228, 380, 13, 436, 475, 11, 278, 273, 430,
280, 340, 120, 236, 183, 296, 488, 500, 456, 356,
246, 120, 64, 491, 78, 285, 163, 461, 418, 288,
4, 510, 326, 438, 383, 478, 76, 135, 330, 260,
495, 45, 33, 1, 73, 501, 380, 433, 348, 505,
425, 363, 23, 206, 195, 986
};
return asso_values[(unsigned char)str[len - 1]] + asso_values[(unsigned char)str[0]];
}
#ifdef __GNUC__
__inline
#endif
static const struct charHz *
inBig5 (register const char *str, register unsigned int len)
{
enum
{
TOTAL_KEYWORDS = 400,
MIN_WORD_LENGTH = 2,
MAX_WORD_LENGTH = 2,
MIN_HASH_VALUE = 0,
MAX_HASH_VALUE = 985
};
static const struct charHz wordlist[] =
{
{"い", 0.769287},
{"ぇ", 0.306841},
{"Г", 0.019016},
{"
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -