reads txt from file, cut them into words, and display - c

Question

#pragma warning(disable:4996)
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <ctype.h>
static WORDS heap[10000];
int heapSize;
void InitHeap()
{
heapSize = 0;
heap[0].words = NULL;
heap[0].count = -1;
}
void InsertHeap(char* string)
{
heapSize++;
strcpy(heap[heapSize].words, string);
int now = heapSize;
while (heap[now / 2].words > string)
{
heap[now] = heap[now / 2];
now /= 2;
}
strcpy(heap[now].words, string);
}
int DeleteHeap()
{
char* minElement, lastElement;
int child, now;
strcpy(minElement, heap[1].words);
strcpy(lastElement, heap[heapSize--].words);
for (now = 1; now * 2 <= heapSize; now = child)
{
child = now * 2;
if (child != heapSize && heap[child + 1].words < heap[child].words)
{
child++;
}
if (lastElement > heap[child].words)
{
strcpy(heap[now].words, heap[child].words);
}
else
{
break;
}
}
strcpy(heap[now].words, lastElement);
return now;
}
typedef struct _WORDS {
char words[64];
int count;
}WORDS;
char* MakeToken(void)
{
int i, j;
static char delim[256];
memset(delim, 0x0, 256);
for (i = 1, j = 0; i < 256; i++)
{
if (!isalpha(i)) delim[j++] = i;
}
return delim;
}
int main() {
int i = 0, cur = 0;
FILE *pFile;
char readLine[1024], *ptr;
char *token = MakeToken();
InitHeap();
pFile = fopen("C:\\Users\\Home\\Desktop\\dataset.txt", "r");
if (pFile == NULL) {
printf("File open failed.\n");
return 0;
}
while (fgets(readLine, 1024, pFile) != NULL) {
ptr = strtok(readLine, token);
while (ptr != NULL) {
InsertHeap(ptr);
ptr = strtok(NULL, token);
}
}
for (i = 0; i < heapSize; i++)
{
cur = DeleteHeap();
printf("%s %d\n", heap[cur].words, heap[cur].count);
}
return 0;
}
Error Message : Run-Time error #3
I want to make program that reads txt from file, cut them into words, and display on console. I make it, but it doesnt work. how to fix it?
I think static WORDS heap<- this part
or
delete part is error.
or its path is failure.

Answer 1

I see following errors in your code:
heap[0].words = NULL;
words is an array, not a dynamyc allocated pointer, so you cannot assign to NULL (you get a compiler error! Seems to me that the WORDS.word variable declaration is uncorrect).
strcpy(minElement, heap[1].words);
strcpy(lastElement, heap[heapSize--].words);
minElement and lastElement are not initialized and not allocated, so the strcpy function will fail.
Here is a way to correct the code, I changed the minimum possible. The following collect the words, count the number of occurences and print the result in alphabetical order:
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <ctype.h>
typedef struct _WORDS {
char words[64];
int count;
} WORDS;
static WORDS heap[10000];
int heapSize;
void InitHeap()
{
heapSize = 0;
}
void InsertHeap(char* string)
{
int num = 0;
// Search string in heap array. if found, increase count.
for(num = 0; num < heapSize; ++num)
{
if(strcmp(string, heap[num].words) == 0)
{
heap[num].count++;
return;
}
}
// If not found, add it to the array.
strcpy(heap[heapSize].words, string);
heap[heapSize].count = 1;
heapSize++;
}
char* MakeToken(void)
{
int i, j;
static char delim[256];
memset(delim, 0x0, 256);
for (i = 1, j = 0; i < 256; i++)
{
if (!isalpha(i)) delim[j++] = i;
}
return delim;
}
int compare(const void* v1, const void* v2)
{
return strcmp((const char*)v1, (const char*)v2);
}
int main()
{
int i = 0, cur = 0;
FILE *pFile;
char readLine[1024], *ptr;
char *token = MakeToken();
InitHeap();
pFile = fopen("C:\\Users\\Home\\Desktop\\dataset.txt", "r");
if(pFile == NULL)
{
printf("File open failed.\n");
return 0;
}
while (fgets(readLine, 1024, pFile) != NULL)
{
ptr = strtok(readLine, token);
while (ptr != NULL)
{
InsertHeap(ptr);
ptr = strtok(NULL, token);
}
}
// Order alphabetically the heap array.
qsort(heap, heapSize, sizeof(WORDS), compare);
for (i = 0; i < heapSize; i++)
{
printf("%s %d\n", heap[i].words, heap[i].count);
}
return 0;
}

Answer 2

I've fixed some errors in the code and it started to produce some results. Since I do not understand completely your task, I cannot progress further. The working code is as follows:
#pragma warning(disable:4996)
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <ctype.h>
typedef struct _WORDS { char words[64]; int count; }WORDS;
static WORDS app_heap[10000];
int heapSize;
void InitHeap()
{
heapSize = 0;
app_heap[0].words[0] = '\0';
app_heap[0].count = -1;
}
void InsertHeap(char* string)
{
heapSize++;
strcpy(app_heap[heapSize].words, string);
int now = heapSize;
while (app_heap[now / 2].words > string)
{
app_heap[now] = app_heap[now / 2];
now /= 2;
}
strcpy(app_heap[now].words, string);
}
int DeleteHeap()
{
char minElement[64], lastElement[64];
int child, now;
if(heapSize <= 0)
{
printf("Wrong call\n");
return 0;
}
strcpy(minElement, app_heap[1].words);
strcpy(lastElement, app_heap[heapSize--].words);
for (now = 1; now * 2 <= heapSize; now = child)
{
child = now * 2;
if (child != heapSize && app_heap[child + 1].words < app_heap[child].words)
{
child++;
}
if (lastElement > app_heap[child].words)
{
strcpy(app_heap[now].words, app_heap[child].words);
}
else
{
break;
}
}
strcpy(app_heap[now].words, lastElement);
return now;
}
char* MakeToken(void)
{
int i, j;
static char delim[256];
memset(delim, 0x0, 256);
for (i = 1, j = 0; i < 256; i++)
{
if (!isalpha(i)) delim[j++] = i;
}
return delim;
}
int main() {
int i = 0, cur = 0;
FILE *pFile;
char readLine[1024], *ptr;
char *token = MakeToken();
InitHeap();
pFile = fopen("dataset.txt", "r");
if (pFile == NULL) {
printf("File open failed.\n");
return 0;
}
while (fgets(readLine, 1024, pFile) != NULL) {
ptr = strtok(readLine, token);
while (ptr != NULL) {
InsertHeap(ptr);
ptr = strtok(NULL, token);
}
}
for (i = 0; i < heapSize; i++)
{
cur = DeleteHeap();
printf("%s %d\n", app_heap[cur].words, app_heap[cur].count);
}
return 0;
}