13

我的软件在 UTF8 中获取了一些字符串,而不是我需要转换为 ISO 8859 1。我知道 UTF8 域大于 ISO 8859。但是 UTF8 中的数据之前已经从 ISO 上转换,所以我不应该错过任何东西。

我想知道是否有一种简单/直接的方法可以将 UTF8 转换为 iso-8859-1。

4

3 回答 3

15

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"

工作示例:

#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;
}
于 2012-06-22T12:49:00.190 回答
15

这是一个您可能会觉得有用的功能:utf8_to_latin9(). 它转换为ISO-8859-15(包括 EURO,它ISO-8859-1没有),但也适用于-> ->往返的UTF-8->ISO-8859-1转换部分。ISO-8859-1UTF-8ISO-8859-1

该函数会忽略类似于//IGNOREiconv 的标志的无效代码点,但不会重构已分解的 UTF-8 序列;也就是说,它不会U+006E U+0303变成U+00F1. 我不打扰重新组合,因为 iconv 也没有。

该函数对字符串访问非常小心。它永远不会扫描超出缓冲区。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(字节)数,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,您可以为to_latin9()函数中的特定代码点添加自定义音译,但仅限于一个字符替换。

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相同。输出字符串永远不会比输入字符串长。如果您的输入字符串有空间容纳额外的字节(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。我故意这样写,因为它应该在嵌入式环境中为您节省一些精力,尽管这种方法有点有限。定制和扩展。

编辑:

我在对此答案的编辑中包含了一对转换函数,用于拉丁 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一个动态分配的副本,并保持原始字符串不变。

于 2012-06-23T22:31:24.940 回答
0

以下示例也使用了 iconv 库。即使您有一个包含混合 UTF-8 和 ISO-8859-1 字符的文件(或输入流),它也可以工作(例如,如果您有一个 UTF-8 文件并在使用 ISO 的环境中编辑它,则可能发生这种情况-8859-1)。

int Utf8ToLatin1(char* input, char* output, size_t size)
{
    size_t in_left = size;
    size_t out_left = size;

    char *in_buf    = input;
    char *out_buf   = output;

    iconv_t cd = iconv_open("ISO_8859-1", "UTF-8");
    if (cd == (iconv_t)-1) {
        (void) fprintf(stderr, "iconv_open() failed, msg encoding will be kept!");
        strncpy(output, input, size);
        return -1;
    }

    do {
        if (iconv(cd, &in_buf, &in_left, &out_buf, &out_left) == (size_t) -1) {
            if (errno == EILSEQ) {
                /* Input conversion stopped due to an input byte that
                 * does not belong to the input codeset.
                 */
                printf("Input conversion stopped due to an input byte that does not belong to the input codeset.\n");
                *out_buf= *in_buf;
                out_buf++   ;out_left--;
                in_buf++    ;in_left--;

            } else if (errno == E2BIG) {
                /* Input conversion stopped due to lack of space in
                 * the output buffer.
                 */
                printf("Input conversion stopped due to lack of space in the output buffer.\n");
                perror("iconv failed!, propably the encoding is already Latin, msg encoding will be kept!\n");
                strncpy(output, input, size);
                return -1;
            } else if (errno == EINVAL) {
                /* Input conversion stopped due to an incomplete
                 * character or shift sequence at the end of the
                 * input buffer.
                 */
                printf("Input conversion stopped due to an incomplete character or shift sequence at the end of the input buffer.\n");
                *out_buf= *in_buf;
                out_buf++   ;out_left--;
                in_buf++    ;in_left--;
            }

        }
    } while (in_left > 0 && out_left > 0);
    *out_buf = 0;

    iconv_close(cd);

    printf("*********************************************************\n");
    printf("ISO-8859-1:\n %s\n", input, output);
    return 0;

}
于 2020-07-22T17:17:49.347 回答