为什么我的解析器提取的每个包含后都会得到'ÿ'字符？- C

Question

我有这个功能:

/*This func runs *.c1 file, and replace every include file with its content
It will save those changes to *.c2 file*/
void includes_extractor(FILE *c1_fp, char *c1_file_name ,int c1_file_str_len )
{
    int i=0;
    FILE *c2_fp , *header_fp;
    char ch, *c2_file_name,header_name[80]; /* we can assume line length 80 chars MAX*/
    char inc_name[]="include"; 
    char inc_chk[INCLUDE_LEN+1]; /*INCLUDE_LEN is defined | +1 for null*/

    /* making the c2 file name */

    c2_file_name=(char *) malloc ((c1_file_str_len)*sizeof(char));
    if (c2_file_name == NULL)
    {
     printf("Out of memory !\n");
     exit(0);
    } 

    strcpy(c2_file_name , c1_file_name); 
    c2_file_name[c1_file_str_len-1] = '\0'; 
    c2_file_name[c1_file_str_len-2] = '2';

/*Open source & destination files + ERR check */

    if( !(c1_fp = fopen (c1_file_name,"r") ) )
    {
     fprintf(stderr,"\ncannot open *.c1 file !\n");
     exit(0);
    }

    if( !(c2_fp = fopen (c2_file_name,"w+") ) )
    {
     fprintf(stderr,"\ncannot open *.c2 file !\n");
     exit(0);
    }

/*next code lines are copy char by char from c1 to c2,
  but if meet header file, copy its content */

    ch=fgetc(c1_fp);
    while (!feof(c1_fp))
    {
        i=0;    /*zero i */ 
        if (ch == '#') /*potential #include case*/
        {
             fgets(inc_chk, INCLUDE_LEN+1, c1_fp); /*8 places for "include" + null*/
         if(strcmp(inc_chk,inc_name)==0) /*case #include*/
         {
          ch=fgetc(c1_fp);
          while(ch==' ') /* stop when head with a '<' or '"' */
          {
           ch=fgetc(c1_fp);
          } /*while(2)*/

          ch=fgetc(c1_fp); /*start read header file name*/

          while((ch!='"') && (ch!='>')) /*until we get the end of header name*/
          {
           header_name[i] = ch;
           i++;
           ch=fgetc(c1_fp);
          }/*while(3)*/
          header_name[i]='\0';  /*close the header_name array*/


          if( !(header_fp = fopen (header_name,"r") ) ) /*open *.h for read + ERR chk*/
          {
               fprintf(stderr,"cannot open header file !\n");
           exit(0);
              }

          while (!feof(header_fp)) /*copy header file content to *.c2 file*/
          {
           ch=fgetc(header_fp);
           fputc(ch,c2_fp);
          }/*while(4)*/
          fclose(header_fp);
         }
                }/*frst if*/
        else
        {
         fputc(ch,c2_fp);
        }
     ch=fgetc(c1_fp);
    }/*while(1)*/ 

fclose(c1_fp);
fclose(c2_fp);
free (c2_file_name);    
}

此函数读取单个*.c1文件并将其副本保存到*.c2文件,但提取*.c1文件中的所有包含文件,并将其内容扩展为*.c2.

在提取的每个包含文件之后,我得到'ÿ'符号.

包含可以包含1行或1000行,但'ÿ'符号将在每个提取的包含后出现一次.

找不到原因......

Answer 1

"ÿ"对应于代码点0xFF.到达文件末尾时fgetc返回EOF,通常定义为-1.将-1存储在一个字符中,你将以0xFF结束.你必须在通话fgetc和fpuc.之间检查EOF .

int ch;
...
/*copy header file content to *.c2 file*/
for (ch=fgetc(header_fp); ch > -1; ch=fgetc(header_fp)) {
   fputc(ch,c2_fp);
}

您可以使用fgets获取一个字符块,而不是一次只获取一个字符.

#ifndef BUFSIZE
#  define BUFSIZE 1024
#endif
char buf[BUFSIZE], *read;
...
/*copy header file content to *.c2 file*/
while ((read = fgets(buf, BUFSIZE, header_fp))) {
    fputs(buf, c2_fp);
}