0

我正在将古老的IBM 代码页 437中的字符映射到 16 位 UCS2 代码。进入 UCS2 是一个相当简单的过程：

const unsigned short ibm437_to_ucs[] = { 0x0000, 0x0001, ..., 0x2320, 0x00f7 };
...
return ibm437_to_ucs[ibm_code];

但是 UCS 代码不是连续的，所以我选择不写一个可比较的数组去另一个方向。有没有比简单地循环每个字符 UCS 字符的原始数组更好的方法？

for(int i = 0; i < IBM437_MAX /* 0xff */; i++)
{
    if(ibm437_to_ucs[i] == ucs_code)
        return i;
}
return '?';
4

1 回答 1

0

以下是使用表查找和二分搜索在 C 中（以及在 C++ 中进行细微更改后）中执行此操作的方法：

#include <stdio.h>
#include <stdlib.h>

// conversion tables are based on
// http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP437.TXT

const unsigned short cp437hi_utf16[128] =
{
  0x00c7, 0x00fc, 0x00e9, 0x00e2, 0x00e4, 0x00e0, 0x00e5, 0x00e7,
  0x00ea, 0x00eb, 0x00e8, 0x00ef, 0x00ee, 0x00ec, 0x00c4, 0x00c5,
  0x00c9, 0x00e6, 0x00c6, 0x00f4, 0x00f6, 0x00f2, 0x00fb, 0x00f9,
  0x00ff, 0x00d6, 0x00dc, 0x00a2, 0x00a3, 0x00a5, 0x20a7, 0x0192,
  0x00e1, 0x00ed, 0x00f3, 0x00fa, 0x00f1, 0x00d1, 0x00aa, 0x00ba,
  0x00bf, 0x2310, 0x00ac, 0x00bd, 0x00bc, 0x00a1, 0x00ab, 0x00bb,
  0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x2561, 0x2562, 0x2556,
  0x2555, 0x2563, 0x2551, 0x2557, 0x255d, 0x255c, 0x255b, 0x2510,
  0x2514, 0x2534, 0x252c, 0x251c, 0x2500, 0x253c, 0x255e, 0x255f,
  0x255a, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256c, 0x2567,
  0x2568, 0x2564, 0x2565, 0x2559, 0x2558, 0x2552, 0x2553, 0x256b,
  0x256a, 0x2518, 0x250c, 0x2588, 0x2584, 0x258c, 0x2590, 0x2580,
  0x03b1, 0x00df, 0x0393, 0x03c0, 0x03a3, 0x03c3, 0x00b5, 0x03c4,
  0x03a6, 0x0398, 0x03a9, 0x03b4, 0x221e, 0x03c6, 0x03b5, 0x2229,
  0x2261, 0x00b1, 0x2265, 0x2264, 0x2320, 0x2321, 0x00f7, 0x2248,
  0x00b0, 0x2219, 0x00b7, 0x221a, 0x207f, 0x00b2, 0x25a0, 0x00a0
};

const unsigned long utf16_cp437hi[128] =
{
  0xff00a0, 0xad00a1, 0x9b00a2, 0x9c00a3,
  0x9d00a5, 0xa600aa, 0xae00ab, 0xaa00ac,
  0xf800b0, 0xf100b1, 0xfd00b2, 0xe600b5,
  0xfa00b7, 0xa700ba, 0xaf00bb, 0xac00bc,
  0xab00bd, 0xa800bf, 0x8e00c4, 0x8f00c5,
  0x9200c6, 0x8000c7, 0x9000c9, 0xa500d1,
  0x9900d6, 0x9a00dc, 0xe100df, 0x8500e0,
  0xa000e1, 0x8300e2, 0x8400e4, 0x8600e5,
  0x9100e6, 0x8700e7, 0x8a00e8, 0x8200e9,
  0x8800ea, 0x8900eb, 0x8d00ec, 0xa100ed,
  0x8c00ee, 0x8b00ef, 0xa400f1, 0x9500f2,
  0xa200f3, 0x9300f4, 0x9400f6, 0xf600f7,
  0x9700f9, 0xa300fa, 0x9600fb, 0x8100fc,
  0x9800ff, 0x9f0192, 0xe20393, 0xe90398,
  0xe403a3, 0xe803a6, 0xea03a9, 0xe003b1,
  0xeb03b4, 0xee03b5, 0xe303c0, 0xe503c3,
  0xe703c4, 0xed03c6, 0xfc207f, 0x9e20a7,
  0xf92219, 0xfb221a, 0xec221e, 0xef2229,
  0xf72248, 0xf02261, 0xf32264, 0xf22265,
  0xa92310, 0xf42320, 0xf52321, 0xc42500,
  0xb32502, 0xda250c, 0xbf2510, 0xc02514,
  0xd92518, 0xc3251c, 0xb42524, 0xc2252c,
  0xc12534, 0xc5253c, 0xcd2550, 0xba2551,
  0xd52552, 0xd62553, 0xc92554, 0xb82555,
  0xb72556, 0xbb2557, 0xd42558, 0xd32559,
  0xc8255a, 0xbe255b, 0xbd255c, 0xbc255d,
  0xc6255e, 0xc7255f, 0xcc2560, 0xb52561,
  0xb62562, 0xb92563, 0xd12564, 0xd22565,
  0xcb2566, 0xcf2567, 0xd02568, 0xca2569,
  0xd8256a, 0xd7256b, 0xce256c, 0xdf2580,
  0xdc2584, 0xdb2588, 0xdd258c, 0xde2590,
  0xb02591, 0xb12592, 0xb22593, 0xfe25a0
};

unsigned short Cp437toUtf16(unsigned char c)
{
  if (c < 0x80)
    return c;
  return cp437hi_utf16[c - 0x80];
}

static int CompareUtf16toCp437(const void* pv1, const void* pv2)
{
  const unsigned long *pl1 = pv1, *pl2 = pv2;
  unsigned long v1 = *pl1 & 0xFFFF, v2 = *pl2 & 0xFFFF;

  if (v1 > v2)
    return +1;

  if (v1 < v2)
    return -1;

  return 0;
}

int Utf16toCp437(unsigned long cp)
{
  unsigned long* p;

  if (cp < 0x80)
    return cp;

  if (cp > 0xFFFF)
    return -1;

  p = bsearch(&cp,
              utf16_cp437hi,
              sizeof(utf16_cp437hi) / sizeof(utf16_cp437hi[0]),
              sizeof(utf16_cp437hi[0]),
              &CompareUtf16toCp437);

  if (p == NULL)
    return -1;

  return *p >> 16;
}

int main(void)
{
  unsigned c;

  for (c = 0; c <= 0xFF; c++)
  {
    unsigned long cp = Cp437toUtf16(c);
    int c2 = Utf16toCp437(cp);

    printf("0x%02X -> 0x%04lX -> 0x%02X\n", c, cp, c2);

    if (c != c2)
    {
      puts("Failure!");
      return EXIT_FAILURE;
    }
  }

  puts("Success!");
  return EXIT_SUCCESS;
}

输出（ideone）：

0x00 -> 0x0000 -> 0x00
0x01 -> 0x0001 -> 0x01
0x02 -> 0x0002 -> 0x02
0x03 -> 0x0003 -> 0x03
0x04 -> 0x0004 -> 0x04
0x05 -> 0x0005 -> 0x05
0x06 -> 0x0006 -> 0x06
0x07 -> 0x0007 -> 0x07
0x08 -> 0x0008 -> 0x08
0x09 -> 0x0009 -> 0x09
0x0A -> 0x000A -> 0x0A
0x0B -> 0x000B -> 0x0B
0x0C -> 0x000C -> 0x0C
0x0D -> 0x000D -> 0x0D
0x0E -> 0x000E -> 0x0E
0x0F -> 0x000F -> 0x0F
0x10 -> 0x0010 -> 0x10
0x11 -> 0x0011 -> 0x11
0x12 -> 0x0012 -> 0x12
0x13 -> 0x0013 -> 0x13
0x14 -> 0x0014 -> 0x14
0x15 -> 0x0015 -> 0x15
0x16 -> 0x0016 -> 0x16
0x17 -> 0x0017 -> 0x17
0x18 -> 0x0018 -> 0x18
0x19 -> 0x0019 -> 0x19
0x1A -> 0x001A -> 0x1A
0x1B -> 0x001B -> 0x1B
0x1C -> 0x001C -> 0x1C
0x1D -> 0x001D -> 0x1D
0x1E -> 0x001E -> 0x1E
0x1F -> 0x001F -> 0x1F
0x20 -> 0x0020 -> 0x20
0x21 -> 0x0021 -> 0x21
0x22 -> 0x0022 -> 0x22
0x23 -> 0x0023 -> 0x23
0x24 -> 0x0024 -> 0x24
0x25 -> 0x0025 -> 0x25
0x26 -> 0x0026 -> 0x26
0x27 -> 0x0027 -> 0x27
0x28 -> 0x0028 -> 0x28
0x29 -> 0x0029 -> 0x29
0x2A -> 0x002A -> 0x2A
0x2B -> 0x002B -> 0x2B
0x2C -> 0x002C -> 0x2C
0x2D -> 0x002D -> 0x2D
0x2E -> 0x002E -> 0x2E
0x2F -> 0x002F -> 0x2F
0x30 -> 0x0030 -> 0x30
0x31 -> 0x0031 -> 0x31
0x32 -> 0x0032 -> 0x32
0x33 -> 0x0033 -> 0x33
0x34 -> 0x0034 -> 0x34
0x35 -> 0x0035 -> 0x35
0x36 -> 0x0036 -> 0x36
0x37 -> 0x0037 -> 0x37
0x38 -> 0x0038 -> 0x38
0x39 -> 0x0039 -> 0x39
0x3A -> 0x003A -> 0x3A
0x3B -> 0x003B -> 0x3B
0x3C -> 0x003C -> 0x3C
0x3D -> 0x003D -> 0x3D
0x3E -> 0x003E -> 0x3E
0x3F -> 0x003F -> 0x3F
0x40 -> 0x0040 -> 0x40
0x41 -> 0x0041 -> 0x41
0x42 -> 0x0042 -> 0x42
0x43 -> 0x0043 -> 0x43
0x44 -> 0x0044 -> 0x44
0x45 -> 0x0045 -> 0x45
0x46 -> 0x0046 -> 0x46
0x47 -> 0x0047 -> 0x47
0x48 -> 0x0048 -> 0x48
0x49 -> 0x0049 -> 0x49
0x4A -> 0x004A -> 0x4A
0x4B -> 0x004B -> 0x4B
0x4C -> 0x004C -> 0x4C
0x4D -> 0x004D -> 0x4D
0x4E -> 0x004E -> 0x4E
0x4F -> 0x004F -> 0x4F
0x50 -> 0x0050 -> 0x50
0x51 -> 0x0051 -> 0x51
0x52 -> 0x0052 -> 0x52
0x53 -> 0x0053 -> 0x53
0x54 -> 0x0054 -> 0x54
0x55 -> 0x0055 -> 0x55
0x56 -> 0x0056 -> 0x56
0x57 -> 0x0057 -> 0x57
0x58 -> 0x0058 -> 0x58
0x59 -> 0x0059 -> 0x59
0x5A -> 0x005A -> 0x5A
0x5B -> 0x005B -> 0x5B
0x5C -> 0x005C -> 0x5C
0x5D -> 0x005D -> 0x5D
0x5E -> 0x005E -> 0x5E
0x5F -> 0x005F -> 0x5F
0x60 -> 0x0060 -> 0x60
0x61 -> 0x0061 -> 0x61
0x62 -> 0x0062 -> 0x62
0x63 -> 0x0063 -> 0x63
0x64 -> 0x0064 -> 0x64
0x65 -> 0x0065 -> 0x65
0x66 -> 0x0066 -> 0x66
0x67 -> 0x0067 -> 0x67
0x68 -> 0x0068 -> 0x68
0x69 -> 0x0069 -> 0x69
0x6A -> 0x006A -> 0x6A
0x6B -> 0x006B -> 0x6B
0x6C -> 0x006C -> 0x6C
0x6D -> 0x006D -> 0x6D
0x6E -> 0x006E -> 0x6E
0x6F -> 0x006F -> 0x6F
0x70 -> 0x0070 -> 0x70
0x71 -> 0x0071 -> 0x71
0x72 -> 0x0072 -> 0x72
0x73 -> 0x0073 -> 0x73
0x74 -> 0x0074 -> 0x74
0x75 -> 0x0075 -> 0x75
0x76 -> 0x0076 -> 0x76
0x77 -> 0x0077 -> 0x77
0x78 -> 0x0078 -> 0x78
0x79 -> 0x0079 -> 0x79
0x7A -> 0x007A -> 0x7A
0x7B -> 0x007B -> 0x7B
0x7C -> 0x007C -> 0x7C
0x7D -> 0x007D -> 0x7D
0x7E -> 0x007E -> 0x7E
0x7F -> 0x007F -> 0x7F
0x80 -> 0x00C7 -> 0x80
0x81 -> 0x00FC -> 0x81
0x82 -> 0x00E9 -> 0x82
0x83 -> 0x00E2 -> 0x83
0x84 -> 0x00E4 -> 0x84
0x85 -> 0x00E0 -> 0x85
0x86 -> 0x00E5 -> 0x86
0x87 -> 0x00E7 -> 0x87
0x88 -> 0x00EA -> 0x88
0x89 -> 0x00EB -> 0x89
0x8A -> 0x00E8 -> 0x8A
0x8B -> 0x00EF -> 0x8B
0x8C -> 0x00EE -> 0x8C
0x8D -> 0x00EC -> 0x8D
0x8E -> 0x00C4 -> 0x8E
0x8F -> 0x00C5 -> 0x8F
0x90 -> 0x00C9 -> 0x90
0x91 -> 0x00E6 -> 0x91
0x92 -> 0x00C6 -> 0x92
0x93 -> 0x00F4 -> 0x93
0x94 -> 0x00F6 -> 0x94
0x95 -> 0x00F2 -> 0x95
0x96 -> 0x00FB -> 0x96
0x97 -> 0x00F9 -> 0x97
0x98 -> 0x00FF -> 0x98
0x99 -> 0x00D6 -> 0x99
0x9A -> 0x00DC -> 0x9A
0x9B -> 0x00A2 -> 0x9B
0x9C -> 0x00A3 -> 0x9C
0x9D -> 0x00A5 -> 0x9D
0x9E -> 0x20A7 -> 0x9E
0x9F -> 0x0192 -> 0x9F
0xA0 -> 0x00E1 -> 0xA0
0xA1 -> 0x00ED -> 0xA1
0xA2 -> 0x00F3 -> 0xA2
0xA3 -> 0x00FA -> 0xA3
0xA4 -> 0x00F1 -> 0xA4
0xA5 -> 0x00D1 -> 0xA5
0xA6 -> 0x00AA -> 0xA6
0xA7 -> 0x00BA -> 0xA7
0xA8 -> 0x00BF -> 0xA8
0xA9 -> 0x2310 -> 0xA9
0xAA -> 0x00AC -> 0xAA
0xAB -> 0x00BD -> 0xAB
0xAC -> 0x00BC -> 0xAC
0xAD -> 0x00A1 -> 0xAD
0xAE -> 0x00AB -> 0xAE
0xAF -> 0x00BB -> 0xAF
0xB0 -> 0x2591 -> 0xB0
0xB1 -> 0x2592 -> 0xB1
0xB2 -> 0x2593 -> 0xB2
0xB3 -> 0x2502 -> 0xB3
0xB4 -> 0x2524 -> 0xB4
0xB5 -> 0x2561 -> 0xB5
0xB6 -> 0x2562 -> 0xB6
0xB7 -> 0x2556 -> 0xB7
0xB8 -> 0x2555 -> 0xB8
0xB9 -> 0x2563 -> 0xB9
0xBA -> 0x2551 -> 0xBA
0xBB -> 0x2557 -> 0xBB
0xBC -> 0x255D -> 0xBC
0xBD -> 0x255C -> 0xBD
0xBE -> 0x255B -> 0xBE
0xBF -> 0x2510 -> 0xBF
0xC0 -> 0x2514 -> 0xC0
0xC1 -> 0x2534 -> 0xC1
0xC2 -> 0x252C -> 0xC2
0xC3 -> 0x251C -> 0xC3
0xC4 -> 0x2500 -> 0xC4
0xC5 -> 0x253C -> 0xC5
0xC6 -> 0x255E -> 0xC6
0xC7 -> 0x255F -> 0xC7
0xC8 -> 0x255A -> 0xC8
0xC9 -> 0x2554 -> 0xC9
0xCA -> 0x2569 -> 0xCA
0xCB -> 0x2566 -> 0xCB
0xCC -> 0x2560 -> 0xCC
0xCD -> 0x2550 -> 0xCD
0xCE -> 0x256C -> 0xCE
0xCF -> 0x2567 -> 0xCF
0xD0 -> 0x2568 -> 0xD0
0xD1 -> 0x2564 -> 0xD1
0xD2 -> 0x2565 -> 0xD2
0xD3 -> 0x2559 -> 0xD3
0xD4 -> 0x2558 -> 0xD4
0xD5 -> 0x2552 -> 0xD5
0xD6 -> 0x2553 -> 0xD6
0xD7 -> 0x256B -> 0xD7
0xD8 -> 0x256A -> 0xD8
0xD9 -> 0x2518 -> 0xD9
0xDA -> 0x250C -> 0xDA
0xDB -> 0x2588 -> 0xDB
0xDC -> 0x2584 -> 0xDC
0xDD -> 0x258C -> 0xDD
0xDE -> 0x2590 -> 0xDE
0xDF -> 0x2580 -> 0xDF
0xE0 -> 0x03B1 -> 0xE0
0xE1 -> 0x00DF -> 0xE1
0xE2 -> 0x0393 -> 0xE2
0xE3 -> 0x03C0 -> 0xE3
0xE4 -> 0x03A3 -> 0xE4
0xE5 -> 0x03C3 -> 0xE5
0xE6 -> 0x00B5 -> 0xE6
0xE7 -> 0x03C4 -> 0xE7
0xE8 -> 0x03A6 -> 0xE8
0xE9 -> 0x0398 -> 0xE9
0xEA -> 0x03A9 -> 0xEA
0xEB -> 0x03B4 -> 0xEB
0xEC -> 0x221E -> 0xEC
0xED -> 0x03C6 -> 0xED
0xEE -> 0x03B5 -> 0xEE
0xEF -> 0x2229 -> 0xEF
0xF0 -> 0x2261 -> 0xF0
0xF1 -> 0x00B1 -> 0xF1
0xF2 -> 0x2265 -> 0xF2
0xF3 -> 0x2264 -> 0xF3
0xF4 -> 0x2320 -> 0xF4
0xF5 -> 0x2321 -> 0xF5
0xF6 -> 0x00F7 -> 0xF6
0xF7 -> 0x2248 -> 0xF7
0xF8 -> 0x00B0 -> 0xF8
0xF9 -> 0x2219 -> 0xF9
0xFA -> 0x00B7 -> 0xFA
0xFB -> 0x221A -> 0xFB
0xFC -> 0x207F -> 0xFC
0xFD -> 0x00B2 -> 0xFD
0xFE -> 0x25A0 -> 0xFE
0xFF -> 0x00A0 -> 0xFF
Success!

更新bsearch()：您也可以在不调用回调函数的情况下实现内联二进制搜索。如果它很重要，它会加快速度。

于 2013-04-16T06:52:54.897 回答