Question

我正在尝试将字符串“aÜ”从 UTF-8 转换为 CP1251 通过C ++库iconv.h使用TRANSLIT，结果我得到字符串“a?”，期待“aU”。

当我在这台计算机上使用php脚本<?php echo iconv("UTF-8", "Windows-1251//TRANSLIT", "Ü");>时，我会得到“aU”字符串。

以下是代码：

#include <cstdlib>
#include <iconv.h>
#include <locale.h>
#include <stdio.h>
#include <string.h>
#include <errno.h>
using namespace std;

int IConvert(char *buf,char *outbuf, size_t len, const char *from, const char *to)
{
    iconv_t iconv_cd;
    if ((iconv_cd = iconv_open(to, from)) == (iconv_t) -1) {
        printf("Cannot open iconv from %s to %s\n", from, to);
        return 0;
    }

    char *inbuf = buf;
    size_t inlen = len;
    size_t outlen = len;
    size_t res = 0;

    while (inlen > 0 && outlen > 0) {
        res = iconv(iconv_cd, &inbuf, &inlen, &outbuf, &outlen);
        if (res == 0)
            break;

        if (res == (size_t) (-1)) {
            if (errno != EILSEQ && errno != EINVAL) {
                iconv_close(iconv_cd);
                *outbuf = '\0';
                printf("Erorr %s (%s)\n", strerror(errno), from);

                return 0;
            } else if (inbuf < outbuf) {
                iconv_close(iconv_cd);
                *outbuf = '\0';
                printf("Erorr %s (inbuf < outbuf)\n", strerror(errno));

                return 0;
            }
        }
        if (inlen > 0 && outlen > 0) {
            *outbuf++ = *inbuf++;
            inlen--;
            outlen--;
        }
    }
    iconv_close(iconv_cd);
    *outbuf = '\0';
    return 1;
}
int main(int argc, char** argv) {
        char* line = "\u00C0a\u00DC";
        char* from = (char*) malloc(strlen(from)+1);
        char* to = (char*) malloc(strlen(from)+1);
        strcpy(from, line);
        printf("%s\n", from);
        IConvert(from, to, strlen(from)+1, "UTF-8", "CP1251//TRANSLIT");
        printf("%s\n", to);
    return 0;
}

知道问题可能是什么？

Answer 1

解决方案是

setlocale(LC_ALL, "");

在您的计划开始时。是的，语言环境会影响音译。在德国语言环境中，将被音译到UE而不是U.

使用iconv translit从UTF-8转换为CP1251

1 个答案: