有没有办法从UTF8转换为iso-8859-1?

问题描述 投票:8回答:2

我的软件在UTF8中得到的字符串比转换到ISO 8859要好。我知道UTF8域大于iso 8859.但UTF8中的数据以前是从ISO上转换过来的,所以我不应该错过任何东西。

我想知道是否有一种简单/直接的方式从UTF8转换为iso-8859-1。

谢谢

c linux utf-8 character-encoding embedded
2个回答
12
投票

这是一个你可能会觉得有用的功能:utf8_to_latin9()。它转换为ISO-8859-15(包括欧元,ISO-8859-1没有),但也适用于UTF-8-> ISO-8859-1转换部分的ISO-8859-1-> UTF-8-> ISO-8859-1往返。

该函数忽略了类似于iconv的//IGNORE标志的无效代码点,但不重新组合分解的UTF-8序列;也就是说,它不会将U+006E U+0303变成U+00F1。我不打算重新组合,因为iconv也没有。

该函数对字符串访问非常谨慎。它永远不会超出缓冲区。输出缓冲区必须比长度长一个字节,因为它总是附加字符串结尾的NUL字节。该函数返回输出中的字符数(字节),不包括字符串结尾的NUL字节。

/* UTF-8 to ISO-8859-1/ISO-8859-15 mapper.
 * Return 0..255 for valid ISO-8859-15 code points, 256 otherwise.
*/
static inline unsigned int to_latin9(const unsigned int code)
{
    /* Code points 0 to U+00FF are the same in both. */
    if (code < 256U)
        return code;
    switch (code) {
    case 0x0152U: return 188U; /* U+0152 = 0xBC: OE ligature */
    case 0x0153U: return 189U; /* U+0153 = 0xBD: oe ligature */
    case 0x0160U: return 166U; /* U+0160 = 0xA6: S with caron */
    case 0x0161U: return 168U; /* U+0161 = 0xA8: s with caron */
    case 0x0178U: return 190U; /* U+0178 = 0xBE: Y with diaresis */
    case 0x017DU: return 180U; /* U+017D = 0xB4: Z with caron */
    case 0x017EU: return 184U; /* U+017E = 0xB8: z with caron */
    case 0x20ACU: return 164U; /* U+20AC = 0xA4: Euro */
    default:      return 256U;
    }
}

/* Convert an UTF-8 string to ISO-8859-15.
 * All invalid sequences are ignored.
 * Note: output == input is allowed,
 * but   input < output < input + length
 * is not.
 * Output has to have room for (length+1) chars, including the trailing NUL byte.
*/
size_t utf8_to_latin9(char *const output, const char *const input, const size_t length)
{
    unsigned char             *out = (unsigned char *)output;
    const unsigned char       *in  = (const unsigned char *)input;
    const unsigned char *const end = (const unsigned char *)input + length;
    unsigned int               c;

    while (in < end)
        if (*in < 128)
            *(out++) = *(in++); /* Valid codepoint */
        else
        if (*in < 192)
            in++;               /* 10000000 .. 10111111 are invalid */
        else
        if (*in < 224) {        /* 110xxxxx 10xxxxxx */
            if (in + 1 >= end)
                break;
            if ((in[1] & 192U) == 128U) {
                c = to_latin9( (((unsigned int)(in[0] & 0x1FU)) << 6U)
                             |  ((unsigned int)(in[1] & 0x3FU)) );
                if (c < 256)
                    *(out++) = c;
            }
            in += 2;

        } else
        if (*in < 240) {        /* 1110xxxx 10xxxxxx 10xxxxxx */
            if (in + 2 >= end)
                break;
            if ((in[1] & 192U) == 128U &&
                (in[2] & 192U) == 128U) {
                c = to_latin9( (((unsigned int)(in[0] & 0x0FU)) << 12U)
                             | (((unsigned int)(in[1] & 0x3FU)) << 6U)
                             |  ((unsigned int)(in[2] & 0x3FU)) );
                if (c < 256)
                    *(out++) = c;
            }
            in += 3;

        } else
        if (*in < 248) {        /* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */
            if (in + 3 >= end)
                break;
            if ((in[1] & 192U) == 128U &&
                (in[2] & 192U) == 128U &&
                (in[3] & 192U) == 128U) {
                c = to_latin9( (((unsigned int)(in[0] & 0x07U)) << 18U)
                             | (((unsigned int)(in[1] & 0x3FU)) << 12U)
                             | (((unsigned int)(in[2] & 0x3FU)) << 6U)
                             |  ((unsigned int)(in[3] & 0x3FU)) );
                if (c < 256)
                    *(out++) = c;
            }
            in += 4;

        } else
        if (*in < 252) {        /* 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx */
            if (in + 4 >= end)
                break;
            if ((in[1] & 192U) == 128U &&
                (in[2] & 192U) == 128U &&
                (in[3] & 192U) == 128U &&
                (in[4] & 192U) == 128U) {
                c = to_latin9( (((unsigned int)(in[0] & 0x03U)) << 24U)
                             | (((unsigned int)(in[1] & 0x3FU)) << 18U)
                             | (((unsigned int)(in[2] & 0x3FU)) << 12U)
                             | (((unsigned int)(in[3] & 0x3FU)) << 6U)
                             |  ((unsigned int)(in[4] & 0x3FU)) );
                if (c < 256)
                    *(out++) = c;
            }
            in += 5;

        } else
        if (*in < 254) {        /* 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx */
            if (in + 5 >= end)
                break;
            if ((in[1] & 192U) == 128U &&
                (in[2] & 192U) == 128U &&
                (in[3] & 192U) == 128U &&
                (in[4] & 192U) == 128U &&
                (in[5] & 192U) == 128U) {
                c = to_latin9( (((unsigned int)(in[0] & 0x01U)) << 30U)
                             | (((unsigned int)(in[1] & 0x3FU)) << 24U)
                             | (((unsigned int)(in[2] & 0x3FU)) << 18U)
                             | (((unsigned int)(in[3] & 0x3FU)) << 12U)
                             | (((unsigned int)(in[4] & 0x3FU)) << 6U)
                             |  ((unsigned int)(in[5] & 0x3FU)) );
                if (c < 256)
                    *(out++) = c;
            }
            in += 6;

        } else
            in++;               /* 11111110 and 11111111 are invalid */

    /* Terminate the output string. */
    *out = '\0';

    return (size_t)(out - (unsigned char *)output);
}

请注意,您可以在to_latin9()函数中为特定代码点添加自定义音译,但您只能使用单字符替换。

正如当前编写的那样,该函数可以安全地进行就地转换:输入和输出指针可以是相同的。输出字符串永远不会长于输入字符串。如果您的输入字符串有额外字节的空间(例如,它有NUL终止字符串),您可以安全地使用上述函数将其从UTF-8转换为ISO-8859-1 / 15。我故意用这种方式写它,因为它应该在嵌入式环境中省去一些努力,尽管这种方法有点受限。定制和扩展。

编辑:

我包括一对转换函数in an edit to this answer,用于拉丁文-1 / 9到/从UTF-8转换(ISO-8859-1或-15到/从UTF-8);主要区别在于这些函数返回动态分配的副本,并保持原始字符串不变。


13
投票

iconv - 执行字符集转换

size_t iconv(iconv_t cd, char **inbuf, size_t *inbytesleft, char **outbuf, size_t *outbytesleft);

iconv_t iconv_open(const char *tocode, const char *fromcode);

tocode"ISO_8859-1"fromcode"UTF-8"

工作范例:

#include <iconv.h>
#include <stdio.h>

int main (void) {
    iconv_t cd = iconv_open("ISO_8859-1", "UTF-8");
    if (cd == (iconv_t) -1) {
        perror("iconv_open failed!");
        return 1;
    }

    char input[] = "Test äöü";
    char *in_buf = &input[0];
    size_t in_left = sizeof(input) - 1;

    char output[32];
    char *out_buf = &output[0];
    size_t out_left = sizeof(output) - 1;

    do {
        if (iconv(cd, &in_buf, &in_left, &out_buf, &out_left) == (size_t) -1) {
            perror("iconv failed!");
            return 1;
        }
    } while (in_left > 0 && out_left > 0);
    *out_buf = 0;

    iconv_close(cd);

    printf("%s -> %s\n", input, output);
    return 0;
}
© www.soinside.com 2019 - 2024. All rights reserved.