EBCDIC 到 ASCII 转换背后的基本原理是什么？

Question

我想了解这种转换究竟是如何发生的。

http://www8.cs.umu.se/~isak/Snippets/a2e.c

/*
**  ASCII <=> EBCDIC conversion functions
*/

static unsigned char a2e[256] = {
          0,  1,  2,  3, 55, 45, 46, 47, 22,  5, 37, 11, 12, 13, 14, 15,
         16, 17, 18, 19, 60, 61, 50, 38, 24, 25, 63, 39, 28, 29, 30, 31,
         64, 79,127,123, 91,108, 80,125, 77, 93, 92, 78,107, 96, 75, 97,
        240,241,242,243,244,245,246,247,248,249,122, 94, 76,126,110,111,
        124,193,194,195,196,197,198,199,200,201,209,210,211,212,213,214,
        215,216,217,226,227,228,229,230,231,232,233, 74,224, 90, 95,109,
        121,129,130,131,132,133,134,135,136,137,145,146,147,148,149,150,
        151,152,153,162,163,164,165,166,167,168,169,192,106,208,161,  7,
         32, 33, 34, 35, 36, 21,  6, 23, 40, 41, 42, 43, 44,  9, 10, 27,
         48, 49, 26, 51, 52, 53, 54,  8, 56, 57, 58, 59,  4, 20, 62,225,
         65, 66, 67, 68, 69, 70, 71, 72, 73, 81, 82, 83, 84, 85, 86, 87,
         88, 89, 98, 99,100,101,102,103,104,105,112,113,114,115,116,117,
        118,119,120,128,138,139,140,141,142,143,144,154,155,156,157,158,
        159,160,170,171,172,173,174,175,176,177,178,179,180,181,182,183,
        184,185,186,187,188,189,190,191,202,203,204,205,206,207,218,219,
        220,221,222,223,234,235,236,237,238,239,250,251,252,253,254,255
};

static unsigned char e2a[256] = {
          0,  1,  2,  3,156,  9,134,127,151,141,142, 11, 12, 13, 14, 15,
         16, 17, 18, 19,157,133,  8,135, 24, 25,146,143, 28, 29, 30, 31,
        128,129,130,131,132, 10, 23, 27,136,137,138,139,140,  5,  6,  7,
        144,145, 22,147,148,149,150,  4,152,153,154,155, 20, 21,158, 26,
         32,160,161,162,163,164,165,166,167,168, 91, 46, 60, 40, 43, 33,
         38,169,170,171,172,173,174,175,176,177, 93, 36, 42, 41, 59, 94,
         45, 47,178,179,180,181,182,183,184,185,124, 44, 37, 95, 62, 63,
        186,187,188,189,190,191,192,193,194, 96, 58, 35, 64, 39, 61, 34,
        195, 97, 98, 99,100,101,102,103,104,105,196,197,198,199,200,201,
        202,106,107,108,109,110,111,112,113,114,203,204,205,206,207,208,
        209,126,115,116,117,118,119,120,121,122,210,211,212,213,214,215,
        216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,
        123, 65, 66, 67, 68, 69, 70, 71, 72, 73,232,233,234,235,236,237,
        125, 74, 75, 76, 77, 78, 79, 80, 81, 82,238,239,240,241,242,243,
         92,159, 83, 84, 85, 86, 87, 88, 89, 90,244,245,246,247,248,249,
         48, 49, 50, 51, 52, 53, 54, 55, 56, 57,250,251,252,253,254,255
};

char ASCIItoEBCDIC(const unsigned char c)
{
        return a2e[c];
}

char EBCDICtoASCII(const unsigned char c)
{
        return e2a[c];
}

以示例文本 char sample[6] = "hello"; 为例，h 如何从 ascii 转换为 ebcdic，反之亦然？

编辑：我真的不需要转换字符串。我只想知道这些表是如何构建的。

Answer 1

I just want to know how these tables were constructed.

'0' in ASCII 的代码值为 48。
EBCDIC 中的 '0' 的代码值为 240。

所以我们需要将 48 映射到 240 以及将 240 映射到 48 的表。

以 ASCII 代码值 48 转换 '0'。a2e[48] returns 240，字符的 EBCDIC 代码'0'。

static unsigned char a2e[256] = {
    ...
    ...
    ...
    240,241,242,243,244,245,246,247,248,249,122, 94, 76,126,110,111,
    ...

现在使用字符 '0' 的 EBCDIC 代码 240。 e2a[240] which returns 48, 字符'0'.

的ASCII码

static unsigned char e2a[256] = {
     ...
     13 more rows
     ...
     48, 49, 50, 51, 52, 53, 54, 55, 56, 57,250,251,252,253,254,255
};

对所有其他常见字符执行此操作。为其余部分定义映射。回想一下，ASCII 只定义了 128 个字符，而 EBCDIC 定义了 256 个字符。

杂项

EBCDIC 布局与某些 punch cards.

有一定关系

在两个字符集中，字符 0、1、... 9 是连续的 - 这是 C 中编码的要求。

两组中，大小写字母相差1位，所以可以编码如下（还是用C的好tolower()）

int from_upper_to_lower(int code) {
  return code - 'A' + 'a`;
}

Answer 2

可以使用 tables 在汇编程序中编写从一种字符集转换为另一种字符集的函数。

在 C 中，您可以将此字符串从 ASCII 转换为 EBCDIC

char sample[6] = "hello";

以下方式

char * AsciiToEbcdic( char *s )
{
    for ( char *p = s; *p; ++p ) *p = a2e[( unsigned char )*p];

    return s;
}

前提是 table 可以在函数中访问。

这是一个演示程序。

#include <stdio.h>

char * AsciiToEbcdic( char *s )
{
    static unsigned char a2e[256] = 
    {
          0,  1,  2,  3, 55, 45, 46, 47, 22,  5, 37, 11, 12, 13, 14, 15,
         16, 17, 18, 19, 60, 61, 50, 38, 24, 25, 63, 39, 28, 29, 30, 31,
         64, 79,127,123, 91,108, 80,125, 77, 93, 92, 78,107, 96, 75, 97,
        240,241,242,243,244,245,246,247,248,249,122, 94, 76,126,110,111,
        124,193,194,195,196,197,198,199,200,201,209,210,211,212,213,214,
        215,216,217,226,227,228,229,230,231,232,233, 74,224, 90, 95,109,
        121,129,130,131,132,133,134,135,136,137,145,146,147,148,149,150,
        151,152,153,162,163,164,165,166,167,168,169,192,106,208,161,  7,
         32, 33, 34, 35, 36, 21,  6, 23, 40, 41, 42, 43, 44,  9, 10, 27,
         48, 49, 26, 51, 52, 53, 54,  8, 56, 57, 58, 59,  4, 20, 62,225,
         65, 66, 67, 68, 69, 70, 71, 72, 73, 81, 82, 83, 84, 85, 86, 87,
         88, 89, 98, 99,100,101,102,103,104,105,112,113,114,115,116,117,
        118,119,120,128,138,139,140,141,142,143,144,154,155,156,157,158,
        159,160,170,171,172,173,174,175,176,177,178,179,180,181,182,183,
        184,185,186,187,188,189,190,191,202,203,204,205,206,207,218,219,
        220,221,222,223,234,235,236,237,238,239,250,251,252,253,254,255
    };

    for ( char *p = s; *p; ++p ) *p = a2e[( unsigned char )*p];

    return s;
} 

int main( void ) 
{
    char s[] = "@@@@@";

    printf( "\"%s\"\n", s );
    printf( "\"%s\"\n", AsciiToEbcdic( s ) );

    return 0;
}

它的输出是

"@@@@@"
"|||||"

EBCDIC 到 ASCII 转换背后的基本原理是什么？

What's the rationale behind this EBCDIC to ASCII conversion?

c

char

ascii

ebcdic