Question

我正在尝试打印出一串UTF-16字符。我暂时发布了这个问题，给出的建议是使用iconv转换为UTF-32并将其打印为wchar_t字符串。

我做了一些研究，并成功编写了以下代码：

// *c is the pointer to the characters (UTF-16) i'm trying to print
// sz is the size in bytes of the input i'm trying to print

iconv_t icv;
char in_buf[sz];
char* in;
size_t in_sz;
char out_buf[sz * 2];
char* out;
size_t out_sz;

icv = iconv_open("UTF-32", "UTF-16");

memcpy(in_buf, c, sz);

in = in_buf;
in_sz = sz;
out = out_buf;
out_sz = sz * 2;

size_t ret = iconv(icv, &in, &in_sz, &out, &out_sz);
printf("ret = %d\n", ret);
printf("*** %ls ***\n", ((wchar_t*) out_buf));

iconv调用总是返回0，所以我猜转换应该没问题？

但是，印刷似乎很受欢迎。有时，转换后的wchar_t字符串打印正常。其他时候，它似乎在打印wchar_t时遇到问题，并且完全终止printf函数调用，这样甚至不会打印尾随的“***”。

我也尝试过使用

wprintf(((wchar_t*) "*** %ls ***\n"), out_buf));

但没有任何印刷品。

我在这里错过了什么吗？

参考：How to Print UTF-16 Characters in C?

更新

在评论中纳入了一些建议。

更新代码：

// *c is the pointer to the characters (UTF-16) i'm trying to print
// sz is the size in bytes of the input i'm trying to print

iconv_t icv;
char in_buf[sz];
char* in;
size_t in_sz;
wchar_t out_buf[sz / 2];
char* out;
size_t out_sz;

icv = iconv_open("UTF-32", "UTF-16");

memcpy(in_buf, c, sz);

in = in_buf;
in_sz = sz;
out = (char*) out_buf;
out_sz = sz * 2;

size_t ret = iconv(icv, &in, &in_sz, &out, &out_sz);
printf("ret = %d\n", ret);
printf("*** %ls ***\n", out_buf);
wprintf(L"*** %ls ***\n", out_buf);

仍然是相同的结果，并非所有的UTF-16字符串都被打印出来（printf和wprintf）。

我还能错过什么？

不过，我正在使用Linux，并且已经验证wchar_t是4个字节。

Answer 1

这是一个简短的程序，它将UTF-16转换为宽字符数组，然后将其打印出来。

#include <endian.h>
#include <errno.h>
#include <iconv.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <wchar.h>

#define FROMCODE "UTF-16"

#if (BYTE_ORDER == LITTLE_ENDIAN)
#define TOCODE "UTF-32LE"
#elif (BYTE_ORDER == BIG_ENDIAN)
#define TOCODE "UTF-32BE"
#else
#error Unsupported byte order
#endif

int main(void)
{
    void *tmp;
    char *outbuf;
    const char *inbuf;
    long converted = 0;
    wchar_t *out = NULL;
    int status = EXIT_SUCCESS, n;
    size_t inbytesleft, outbytesleft, size;
    const char in[] = {
        0xff, 0xfe,
        'H', 0x0,
        'e', 0x0,
        'l', 0x0,
        'l', 0x0,
        'o', 0x0,
        ',', 0x0,
        ' ', 0x0,
        'W', 0x0,
        'o', 0x0,
        'r', 0x0,
        'l', 0x0,
        'd', 0x0,
        '!', 0x0
    };
    iconv_t cd = iconv_open(TOCODE, FROMCODE);
    if ((iconv_t)-1 == cd) {
        if (EINVAL == errno) {
            fprintf(stderr, "iconv: cannot convert from %s to %s\n",
                    FROMCODE, TOCODE);
        } else {
            fprintf(stderr, "iconv: %s\n", strerror(errno));
        }
        goto error;
    }
    size = sizeof(in) * sizeof(wchar_t);
    inbuf = in;
    inbytesleft = sizeof(in);
    while (1) {
        tmp = realloc(out, size + sizeof(wchar_t));
        if (!tmp) {
            fprintf(stderr, "realloc: %s\n", strerror(errno));
            goto error;
        }
        out = tmp;
        outbuf = (char *)out + converted;
        outbytesleft = size - converted;
        n = iconv(cd, (char **)&inbuf, &inbytesleft, &outbuf, &outbytesleft);
        if (-1 == n) {
            if (EINVAL == errno) {
                /* junk at the end of the buffer, ignore it */
                break;
            } else if (E2BIG != errno) {
                /* unrecoverable error */
                fprintf(stderr, "iconv: %s\n", strerror(errno));
                goto error;
            }
            /* increase the size of the output buffer */
            converted = size - outbytesleft;
            size <<= 1;
        } else {
            /* done */
            break;
        }
    }
    converted = (size - outbytesleft) / sizeof(wchar_t);
    out[converted] = L'\0';
    fprintf(stdout, "%ls\n", out);
    /* flush the iconv buffer */
    iconv(cd, NULL, NULL, &outbuf, &outbytesleft);
exit:
    if (out) {
        free(out);
    }
    if (cd) {
        iconv_close(cd);
    }
    exit(status);
error:
    status = EXIT_FAILURE;
    goto exit;
}

由于UTF-16是一种可变长度编码，因此您猜测输出缓冲区需要多大。正确的程序应该处理输出缓冲区不足以容纳转换数据的情况。

您还应该注意iconv没有NULL - 为您终止输出缓冲区。

Iconv是面向流的处理器，因此如果要将其重新用于另一次转换，则需要刷新iconv_t（示例代码在接近结束时执行此操作）。如果你想进行流处理，你将处理EINVAL错误，将输入缓冲区中剩余的任何字节复制到新输入缓冲区的开头，然后再次调用iconv。

如何将UTF-16转换为UTF-32并在C中打印生成的wchar_t？

1 个答案: