我的软件得到了一些UTF8编码的字符串,我需要将其转换为ISO 8859 1。我知道UTF8域比ISO 8859更大。但是UTF8中的数据先前已经从ISO进行了上转换,所以我不应该遗漏任何内容。
我想知道是否有一种简单/直接的方法可以从UTF8转换为iso-8859-1。
我的软件得到了一些UTF8编码的字符串,我需要将其转换为ISO 8859 1。我知道UTF8域比ISO 8859更大。但是UTF8中的数据先前已经从ISO进行了上转换,所以我不应该遗漏任何内容。
我想知道是否有一种简单/直接的方法可以从UTF8转换为iso-8859-1。
以下是一个有用的函数:utf8_to_latin9()
。它将转换为ISO-8859-15
(包括欧元符号,但ISO-8859-1
没有),但也可以正确处理ISO-8859-1
->UTF-8
->ISO-8859-1
往返转换中的UTF-8
->ISO-8859-1
转换部分。
该函数忽略无效的代码点,类似于iconv的//IGNORE
标志,但不会重新组合分解的UTF-8序列;也就是说,它不会将U+006E U+0303
转换成U+00F1
。我没有重新组合,因为iconv也没有这样做。
该函数非常注意字符串的访问。它绝不会扫描超出缓冲区。输出缓冲区必须比长度多一个字节,因为它总是附加字符串结束的NUL字节。该函数返回输出中字符(字节)的数量,不包括字符串结束的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,在to_latin9()
函数中,您可以为特定代码点添加自定义音译,但只能使用单个字符替换。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
是 "ISO_8859-1"
,而 fromcode
是 "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;
}
gconv
:http://www.gnu.org/software/libc/manual/html_node/glibc-iconv-Implementation.html - J-16 SDiZiconv_close()
以释放由iconv_open()
分配的资源。只需要在printf("%s -> %s\n", input, output);
之前放置iconv_close(cd);
即可。 - silvioprogint 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;
}
strncpy(output, input, size);
如果输出缓冲区有size
个字节或更多,则输出将不会以空字符结尾。此外,最后的*out_buf = 0;
可能会写入目标数组的末尾之外。 - chqrlie