自己写的一个统计大容量文本里面单词的函数

#include

 

#define VALIDATE_IS_STRING(f) do{ \
 while ((c = getc(f)) != EOF) {    \
  if (validate_character_is_space(c)) { \
            if (word) {   \
                wcount++; \
            } \
            word = 0; \
        } else if((c >= 65 && c <= 90) || (c >= 97 && c <= 122)) { \
            word = 1; \
        } \
    } \
}while(0)

 

#define PRINTI(x)   printf("The words number  is: %d\n", x)

 

static FILE * open_file_by_filename(char *filename) {
 FILE *fp= NULL;

 if ((fp = fopen(filename, "r")) == NULL) {
  printf("Can not open file, please check your filename!\n");
  return (NULL);
 }

 return (fp);
}

 

static unsigned int validate_character_is_space(int ch) {
 return (unsigned int)(ch - 9) < 5u || ch == ' ';
}

 

static int get_string_number_in_file(FILE *filename) {
 int i = 0, iterate = 1;
 register int c;
 register int word = 0;
 long int wcount = 0;

 VALIDATE_IS_STRING(filename);

 return (wcount);
}

 

int main(int argc, char **argv) {
 FILE *fd;
 int count;

 if (argc < 2|| argc >=3) {
  printf("Invalid argument,please set right argument !\n");
  return (-1);
 }

 if ((fd = open_file_by_filename(argv[1])) == NULL)
  return (-1);
 count = get_string_number_in_file(fd);
 PRINTI(count);
 fclose(fd);

 return (0);
}

 

做过一个简单的测试，在对10M大小的文本进行单词数统计时，用时不到0.1秒。。。