Question

在纯ANSI C中计算文本文件中的行和单词的最快方法是什么？

单词以空格或句点终止。行由'\n'终止。

Answer 1

也许看看GNU wc 实用程序的源代码，因为这个实用程序完全符合您的要求。

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

typedef unsigned long count_t;  /* Counter type */

/* Current file counters: chars, words, lines */
count_t ccount;
count_t wcount;
count_t lcount;

/* Totals counters: chars, words, lines */
count_t total_ccount = 0;
count_t total_wcount = 0;
count_t total_lcount = 0;

/* Print error message and exit with error status. If PERR is not 0,
   display current errno status. */
static void
error_print (int perr, char *fmt, va_list ap)
{
  vfprintf (stderr, fmt, ap);
  if (perr)
    perror (" ");
  else
    fprintf (stderr, "\n");
  exit (1);  
}

/* Print error message and exit with error status. */
static void
errf (char *fmt, ...)
{
  va_list ap;

  va_start (ap, fmt);
  error_print (0, fmt, ap);
  va_end (ap);
}

/* Print error message followed by errno status and exit
   with error code. */
static void
perrf (char *fmt, ...)
{
  va_list ap;

  va_start (ap, fmt);
  error_print (1, fmt, ap);
  va_end (ap);
}

/* Output counters for given file */
void
report (char *file, count_t ccount, count_t wcount, count_t lcount)
{
  printf ("%6lu %6lu %6lu %s\n", lcount, wcount, ccount, file);
}

/* Return true if C is a valid word constituent */
static int
isword (unsigned char c)
{
  return isalpha (c);
}

/* Increase character and, if necessary, line counters */
#define COUNT(c)       \
      ccount++;        \
      if ((c) == '\n') \
        lcount++;

/* Get next word from the input stream. Return 0 on end
   of file or error condition. Return 1 otherwise. */
int
getword (FILE *fp)
{
  int c;
  int word = 0;

  if (feof (fp))
    return 0;

  while ((c = getc (fp)) != EOF)
    {
      if (isword (c))
        {
          wcount++;
          break;
        }
      COUNT (c);
    }

  for (; c != EOF; c = getc (fp))
    {
      COUNT (c);
      if (!isword (c))
        break;
    }

  return c != EOF;
}

/* Process file FILE. */
void
counter (char *file)
{
  FILE *fp = fopen (file, "r");

  if (!fp)
    perrf ("cannot open file `%s'", file);

  ccount = wcount = lcount = 0;
  while (getword (fp))
    ;
  fclose (fp);

  report (file, ccount, wcount, lcount);
  total_ccount += ccount;
  total_wcount += wcount;
  total_lcount += lcount;
}

int
main (int argc, char **argv)
{
  int i;

  if (argc < 2)
    errf ("usage: wc FILE [FILE...]");

  for (i = 1; i < argc; i++)
    counter (argv[i]);

  if (argc > 2)
    report ("total", total_ccount, total_wcount, total_lcount);
  return 0;
}

发现于： http://www.gnu.org/software/cflow/manual/html_node/Source-of-wc-command.html

Answer 2

阅读
迭代字符增量字符计数器
检查行的空格/行尾增加字计数器
重复第二步和第三步，直到EOF

Answer 3

这是一个明确的答案，它计算行数（对于在OP中链接的C ++版本，单词数量的扩展是微不足道的）。此版本已缓冲。另一个答案建议首先读取整个文件，这比较简单，但下面的内容更符合您的C ++示例。

#include <stdio.h>
#include <string.h>

#define BUFSIZE 1024

int main(int argc, char** argv)
{
  int newlines = 0;
  char buf[BUFSIZE];
  FILE* file;

  if (argc != 2)
    return 1;

  file = fopen(argv[1], "r");
  while (fgets(buf, BUFSIZE, file))
  {
    if (!(strlen(buf) == BUFSIZE-1 && buf[BUFSIZE-2] != '\n'))
      newlines++;
  }

  printf("Number of lines in %s: %d\n", argv[1], newlines);

  return 0;
}

可以调整BUFSIZE宏以最大限度地提高性能（因为你说你想要最快的方式）。 1024只是猜测。另一种可能是读取映射的文件内存，但我没有尝试，因为mmap不是ANSI C。

在ANSI C中计算文本文件中的行和单词的最快方法是什么？

3 个答案: