如何在C中读/写UTF8文本文件？

Question

我试图从文本文件中读取UTF8文本,然后将其中一些文本打印到另一个文件.我正在使用Linux和gcc编译器.这是我正在使用的代码:

#include <stdio.h>
#include <stdlib.h>

int main(){
    FILE *fin;
    FILE *fout;
    int character;
    fin=fopen("in.txt", "r");
    fout=fopen("out.txt","w");
    while((character=fgetc(fin))!=EOF){
        putchar(character); // It displays the right character (UTF8) in the terminal
        fprintf(fout,"%c ",character); // It displays weird characters in the file
    }
    fclose(fin);
    fclose(fout);
    printf("\nFile has been created...\n");
    return 0;
}

它现在适用于英文字符.

Answer 1

代替

fprintf(fout,"%c ",character);

使用

fprintf(fout,"%c",character);

第二个fprintf()不包含空格,之后%c导致out.txt显示奇怪的字符.原因是fgetc()检索单个字节(与ASCII字符相同),而不是 UTF-8字符.由于UTF-8也兼容ASCII,它会将英文字符写入文件.

putchar(character)顺序输出字节,每个字节之间没有额外的空格,因此原始的UTF-8序列保持不变.要看看我在说什么,试试吧

while((character=fgetc(fin))!=EOF){
    putchar(character);
    printf(" "); // This mimics what you are doing when you write to out.txt
    fprintf(fout,"%c ",character);
}

如果要将UTF-8字符与它们之间的空格写入out.txt,则需要处理UTF-8字符的可变长度编码.

#include <stdio.h>
#include <stdlib.h>

/* The first byte of a UTF-8 character
 * indicates how many bytes are in
 * the character, so only check that
 */
int numberOfBytesInChar(unsigned char val) {
    if (val < 128) {
        return 1;
    } else if (val < 224) {
        return 2;
    } else if (val < 240) {
        return 3;
    } else {
        return 4;
    }
}

int main(){
    FILE *fin;
    FILE *fout;
    int character;
    fin = fopen("in.txt", "r");
    fout = fopen("out.txt","w");
    while( (character = fgetc(fin)) != EOF) {
        for (int i = 0; i < numberOfBytesInChar((unsigned char)character) - 1; i++) {
            putchar(character);
            fprintf(fout, "%c", character);
            character = fgetc(fin);
        }
        putchar(character);
        printf(" ");
        fprintf(fout, "%c ", character);
    }
    fclose(fin);
    fclose(fout);
    printf("\nFile has been created...\n");
    return 0;
}

Answer 2

这段代码对我有用：

/* fgetwc example */
#include <stdio.h>
#include <wchar.h>
#include <stdlib.h>
#include <locale.h>
int main ()
{
  setlocale(LC_ALL, "en_US.UTF-8");
  FILE * fin;
  FILE * fout;
  wint_t wc;
  fin=fopen ("in.txt","r");
  fout=fopen("out.txt","w");
  while((wc=fgetwc(fin))!=WEOF){
        // work with: "wc"
  }
  fclose(fin);
  fclose(fout);
  printf("File has been created...\n");
  return 0;
}