Question

我有一个包含波斯语文本的文本文件：

یک

（U + 06CC，U + 06A9）。

我希望将此文件读入字符串，然后将其存储在输出文件中。我正在使用此代码：

  const process = spawn('starter.sh', []);

  process.stdout.on('data', (data) => {
    console.log(`stdout: ${data}`);
    // prints 'Starting jarx' like expected
  });

  process.stderr.on('data', (data) => {
    console.log(`stderr: ${data}`);
  });

  process.on('close', (code) => {
    console.log(`child process exited with code ${code}`);
    // Not called unless all the spawned java processes are dead :(
  });

它不起作用。我的期望：تست

（U + 062A，U + 0633，U + 062A）。

Answer 1

试试这个：

#include <locale.h>
#include <stdio.h>
#include <wchar.h>

int main()
{
    FILE *input;
    wchar_t buf[1000];

    setlocale(LC_CTYPE,"it_IT.UTF-8");   // put your locale here

    if ((input = fopen("input.txt","r")) == NULL)
         return 1;

    while (fgetws(buf,1000,input)!=NULL) 
        wprintf(L"%s",buf);

    fclose(input);
}

Answer 2

这只是一个小错误;对于你需要的宽字符：

fprintf(out, "%lc ", c);
               -

或

fwprintf(out, L"%lc ", c);
 -            -  -

然后，它works for me。（此外，文件还有以空格分隔的字符。）

Answer 3

以下是我的Baby X项目中的utf-8例程。

您需要从UTF-8转换为Unicode代码点，然后转换为宽字符，然后您可以传递到需要宽字符的Windows（可能是）函数。为方便起见，我还添加了反向转换。

static const unsigned int offsetsFromUTF8[6] = 
{
    0x00000000UL, 0x00003080UL, 0x000E2080UL,
    0x03C82080UL, 0xFA082080UL, 0x82082080UL
};

static const unsigned char trailingBytesForUTF8[256] = {
    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
    2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5
};

int bbx_isutf8z(const char *str)
{
  int len = 0;
  int pos = 0;
  int nb;
  int i;
  int ch;

  while(str[len])
    len++;
  while(pos < len && *str)
  {
    nb = bbx_utf8_skip(str);
    if(nb < 1 || nb > 4)
      return 0;
    if(pos + nb > len)
      return 0;
    for(i=1;i<nb;i++)
      if( (str[i] & 0xC0) != 0x80 )
        return 0;
    ch = bbx_utf8_getch(str);
    if(ch < 0x80)
    {
      if(nb != 1)
        return 0;
    }
    else if(ch < 0x8000)
    {
      if(nb != 2)
        return 0;
    }
    else if(ch < 0x10000)
    {
      if(nb != 3)
        return 0;
    }
    else if(ch < 0x110000)
    {
      if(nb != 4)
        return 0;
    }
    pos += nb;
    str += nb;    
  }

  return 1;
}

int bbx_utf8_skip(const char *utf8)
{
  return trailingBytesForUTF8[(unsigned char) *utf8] + 1;
}

int bbx_utf8_getch(const char *utf8)
{
    int ch;
    int nb;

    nb = trailingBytesForUTF8[(unsigned char)*utf8];
    ch = 0;
    switch (nb) 
    {
            /* these fall through deliberately */
        case 3: ch += (unsigned char)*utf8++; ch <<= 6;
        case 2: ch += (unsigned char)*utf8++; ch <<= 6;
        case 1: ch += (unsigned char)*utf8++; ch <<= 6;
        case 0: ch += (unsigned char)*utf8++;
    }
    ch -= offsetsFromUTF8[nb];

    return ch;
}

int bbx_utf8_putch(char *out, int ch)
{
  char *dest = out;
  if (ch < 0x80) 
  {
     *dest++ = (char)ch;
  }
  else if (ch < 0x800) 
  {
    *dest++ = (ch>>6) | 0xC0;
    *dest++ = (ch & 0x3F) | 0x80;
  }
  else if (ch < 0x10000) 
  {
     *dest++ = (ch>>12) | 0xE0;
     *dest++ = ((ch>>6) & 0x3F) | 0x80;
     *dest++ = (ch & 0x3F) | 0x80;
  }
  else if (ch < 0x110000) 
  {
     *dest++ = (ch>>18) | 0xF0;
     *dest++ = ((ch>>12) & 0x3F) | 0x80;
     *dest++ = ((ch>>6) & 0x3F) | 0x80;
     *dest++ = (ch & 0x3F) | 0x80;
  }
  else
    return 0;
  return dest - out;
}

int bbx_utf8_charwidth(int ch)
{
    if (ch < 0x80)
    {
        return 1;
    }
    else if (ch < 0x800)
    {
        return 2;
    }
    else if (ch < 0x10000)
    {
        return 3;
    }
    else if (ch < 0x110000)
    {
        return 4;
    }
    else
        return 0;
}

int bbx_utf8_Nchars(const char *utf8)
{
  int answer = 0;

  while(*utf8)
  {
    utf8 += bbx_utf8_skip(utf8);
    answer++;
  }

  return answer;
}

如何在C中读取UTF-8文本文件？

3 个答案: