2014-09-24 14:45:10 +00:00
|
|
|
/*
|
|
|
|
!!DESCRIPTION!! print word frequencies; uses structures
|
|
|
|
!!ORIGIN!! LCC 4.1 Testsuite
|
|
|
|
!!LICENCE!! own, freely distributeable for non-profit. read CPYRIGHT.LCC
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <stdlib.h>
|
|
|
|
#include <stdio.h>
|
|
|
|
#include <string.h>
|
|
|
|
#include <ctype.h>
|
|
|
|
|
|
|
|
#define MAXWORDS 250
|
|
|
|
|
2014-11-22 17:28:05 +00:00
|
|
|
FILE *in;
|
|
|
|
#define getchar() fgetc(in)
|
|
|
|
|
2014-09-24 14:45:10 +00:00
|
|
|
struct node
|
|
|
|
{
|
2019-02-12 21:50:49 +00:00
|
|
|
int count; /* frequency count */
|
|
|
|
struct node *left; /* left subtree */
|
|
|
|
struct node *right; /* right subtree */
|
|
|
|
char *word; /* word itself */
|
2014-09-24 14:45:10 +00:00
|
|
|
} words[MAXWORDS];
|
2019-02-12 21:50:49 +00:00
|
|
|
int next; /* index of next free entry in words */
|
2014-09-24 14:45:10 +00:00
|
|
|
|
|
|
|
/*struct node *lookup();*/
|
|
|
|
|
|
|
|
int err(char *s);
|
|
|
|
int getword(char *buf);
|
|
|
|
void tprint(struct node *tree);
|
|
|
|
struct node *lookup(char *word, struct node **p);
|
|
|
|
|
|
|
|
int isletter(char c);
|
|
|
|
|
2019-02-12 21:50:49 +00:00
|
|
|
/* err - print error message s and die */
|
2014-09-24 14:45:10 +00:00
|
|
|
err(s) char *s; {
|
2019-02-12 21:50:49 +00:00
|
|
|
printf("? %s\n", s);
|
2019-11-11 15:30:09 +00:00
|
|
|
exit(EXIT_FAILURE);
|
2014-09-24 14:45:10 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/* getword - get next input word into buf, return 0 on EOF */
|
|
|
|
int getword(buf) char *buf;
|
|
|
|
{
|
2019-02-12 21:50:49 +00:00
|
|
|
char *s;
|
|
|
|
int c;
|
2014-09-24 14:45:10 +00:00
|
|
|
|
|
|
|
while (((c = getchar()) != -1) && (isletter(c) == 0))
|
2019-02-12 21:50:49 +00:00
|
|
|
;
|
2014-09-24 14:45:10 +00:00
|
|
|
for (s = buf; (c = isletter(c)); c = getchar())
|
2019-02-12 21:50:49 +00:00
|
|
|
*s++ = c;
|
|
|
|
*s = 0;
|
|
|
|
if (s > buf)
|
|
|
|
return 1;
|
|
|
|
return 0;
|
2014-09-24 14:45:10 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/* isletter - return folded version of c if it is a letter, 0 otherwise */
|
|
|
|
int isletter(char c)
|
|
|
|
{
|
2019-02-12 21:50:49 +00:00
|
|
|
if ((c >= 'A') && (c <= 'Z')) c += 'a' - 'A';
|
|
|
|
if ((c >= 'a') && (c <= 'z')) return c;
|
|
|
|
return 0;
|
2014-09-24 14:45:10 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/* lookup - lookup word in tree; install if necessary */
|
|
|
|
struct node *lookup(word, p)
|
|
|
|
char *word; struct node **p;
|
|
|
|
{
|
2019-02-12 21:50:49 +00:00
|
|
|
int cond;
|
|
|
|
/* char *malloc(); */
|
|
|
|
|
|
|
|
if (*p) {
|
|
|
|
cond = strcmp(word, (*p)->word);
|
|
|
|
if (cond < 0)
|
|
|
|
return lookup(word, &(*p)->left);
|
|
|
|
else if (cond > 0)
|
|
|
|
return lookup(word, &(*p)->right);
|
|
|
|
else
|
|
|
|
return *p;
|
|
|
|
}
|
|
|
|
if (next >= MAXWORDS)
|
|
|
|
err("out of node storage");
|
|
|
|
words[next].count = 0;
|
|
|
|
words[next].left = words[next].right = 0;
|
|
|
|
words[next].word = malloc(strlen(word) + 1);
|
|
|
|
if (words[next].word == 0)
|
|
|
|
err("out of word storage");
|
|
|
|
strcpy(words[next].word, word);
|
|
|
|
return *p = &words[next++];
|
2014-09-24 14:45:10 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/* tprint - print tree */
|
|
|
|
void tprint(tree) struct node *tree; {
|
2019-02-12 21:50:49 +00:00
|
|
|
if (tree) {
|
|
|
|
tprint(tree->left);
|
|
|
|
printf("%d:%s\n", tree->count, tree->word);
|
|
|
|
tprint(tree->right);
|
|
|
|
}
|
2014-09-24 14:45:10 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
int main(void)
|
|
|
|
{
|
2019-02-12 21:50:49 +00:00
|
|
|
struct node *root;
|
|
|
|
char word[20];
|
2014-09-24 14:45:10 +00:00
|
|
|
|
2014-11-22 17:28:05 +00:00
|
|
|
in = fopen("wf1.in","rb");
|
|
|
|
if (in == NULL) {
|
|
|
|
return EXIT_FAILURE;
|
|
|
|
}
|
|
|
|
|
2019-02-12 21:50:49 +00:00
|
|
|
root = 0;
|
|
|
|
next = 0;
|
|
|
|
while (getword(word))
|
|
|
|
lookup(word, &root)->count++;
|
|
|
|
tprint(root);
|
2014-09-24 14:45:10 +00:00
|
|
|
|
2014-11-22 17:28:05 +00:00
|
|
|
fclose(in);
|
2014-09-24 14:45:10 +00:00
|
|
|
return 0;
|
|
|
|
}
|