Question

Here was my original code:

#include <stdio.h>

#define IN  1   // inside a word
#define OUT 0   // outside a word

// program to print input one word per line

int main(void)
{
  int c, state;

  state = OUT;
  while ((c = getchar()) != EOF) {
    if (c == ' ' || c == '\n' || c == '\t') {
      state = OUT;
      printf("\n");
    }
    else if (state == OUT) {
      state = IN;
    }
    if (state == IN) {
      putchar(c);
    }
  }
  return 0;
}

But the problem was if there were multiple blanks (spaces) or multiple tabs next to each other a newline would be printed for both. So I used a variable (last) to keep track of where I was:

#include <stdio.h>

#define IN  1   // inside a word
#define OUT 0   // outside a word

// program to print input one word per line, corrected bug if there was
// more than one space between words to only print one \n

int main(void)
{
  int c, last, state;

  last = EOF;
  state = OUT;
  while ((c = getchar()) != EOF) {
    if (c == ' ' || c == '\n' || c == '\t') {
      if (last != c) {
        state = OUT;
        printf("\n");
      }
    }
    else if (state == OUT) {
      state = IN;
    }
    if (state == IN) {
      putchar(c);
    }
    last = c;
  }
  return 0;
}

That solved it, except now if there is [blank][tab] next to each other, a newline gets printed for both.

Could someone please help?

Answer 1

Your problem with your original code is that you will output your newline for every whitespace character. You only want to do it when transitioning from word to non-word:

Change:

if (c == ' ' || c == '\n' || c == '\t') {
    state = OUT;
    printf("\n");
}

to:

if (c == ' ' || c == '\n' || c == '\t') {
    if (state == IN) printf("\n");
    state = OUT;
}

---

In fact, what I originally thought I’d suggest would be an enumeration for the states along the lines of:

enum eState {IN, OUT};
:
enum eState state = OUT;

but, for a simple finite state machine with only two states, you can just use an boolean:

#include <stdio.h>

#define FALSE (1==0)
#define TRUE  (1==1)
// Or: enum eBoolean {FALSE = 0, TRUE = 1};

int main (void) {
    int ch;
    int inWord = FALSE;     // Or: enum eBoolean inWord = FALSE;

    // Process every character.
    while ((ch = getchar()) != EOF) {
        // Check for whitespace.
        if (ch == ' ' || ch == '\n' || ch == '\t') {
            // Check if transitioning nonwhite to white.
            if (inWord) {
                printf("\n");
            }

            // Mark white no matter what.
            inWord = FALSE;
        } else {
            // Mark non whitespace.
            inWord = TRUE;
        }

        // If not whitespace, output character.
        if (inWord) {
            putchar(ch);
        }
    }
    return 0;
}