Edit a HTML file

Dev Shed Forums Sponsor:

December 9th, 2012, 07:10 AM

Deadman19

Registered User

Join Date: Dec 2012

Posts: 1

Time spent in forums: 8 m 7 sec
Reputation Power: 0

Edit a HTML file

Hey, guys. I need a little help here. I have to edit a HTML text file in C and my first task is to put every tag and the text between them on a new line. So far I managed to do that everytime I find an ">", but I can't do the same thing for the "<" character. Here is the source:

Quote:

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

void strins (char *d, char *s)
{
char *aux=strdup(d);
strcpy(d,s);
strcat(d,aux);
}
void verif1(char *a, char b[10])
{
char *poz;
poz=strchr(a,'>');
while (poz!=NULL)
{
if(a[poz-a+1]!='\n' && a[poz-a+1]!='\0')
{
strins(a+(poz-a+1),b);
a=(char *)realloc(a,strlen(a)*sizeof(char));
}
poz=strchr(poz+1,'>');
}
}
void verif2(char *a, char b[10])
{
char *poz;
poz=strchr(a,'<');
while (poz!=NULL)
{
if((poz-a)!=0 && a[poz-a-1]!='\n')
{
strins(a+(poz-a-1),b);
a=(char *)realloc(a,strlen(a)*sizeof(char));
}
poz=strchr(poz+1,'<');
}
}
int main()
{
freopen("date.in","r",stdin);
char *a, b[10];
int i=0;
b[i]='\n';
b[i+1]='\0';
a=(char *)malloc(40*sizeof(char));
while (!feof(stdin))
{
a[i]=getc(stdin);
i++;
}
a[i]='\0';
verif1(a,b);
verif2(a,b);
printf("%s \n",a);
return 0;
}

The verif1 function is for the ">" character and verif2 is for "<". Can anybody tell me what might be the problem?

December 9th, 2012, 12:20 PM

salem

Contributed User

Join Date: Jun 2005

Posts: 3,905

Folding Points: 153 Folding Title: Novice Folder

Time spent in forums: 2 Months 3 Weeks 4 Days 1 h 2 m 3 sec
Reputation Power: 1774

Allow me to indent your code...

Code:

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

void strins(char *d, char *s)
{
  char *aux = strdup(d);
  strcpy(d, s);
  strcat(d, aux);
}

void verif1(char *a, char b[10])
{
  char *poz;
  poz = strchr(a, '>');
  while (poz != NULL) {
    if (a[poz - a + 1] != '\n' && a[poz - a + 1] != '\0') {
      strins(a + (poz - a + 1), b);
      a = (char *) realloc(a, strlen(a) * sizeof(char));
    }
    poz = strchr(poz + 1, '>');
  }
}

void verif2(char *a, char b[10])
{
  char *poz;
  poz = strchr(a, '<');
  while (poz != NULL) {
    if ((poz - a) != 0 && a[poz - a - 1] != '\n') {
      strins(a + (poz - a - 1), b);
      a = (char *) realloc(a, strlen(a) * sizeof(char));
    }
    poz = strchr(poz + 1, '<');
  }
}

int main()
{
  freopen("date.in", "r", stdin);
  char *a, b[10];
  int i = 0;
  b[i] = '\n';
  b[i + 1] = '\0';
  a = (char *) malloc(40 * sizeof(char));
  while (!feof(stdin)) {
    a[i] = getc(stdin);
    i++;
  }
  a[i] = '\0';
  verif1(a, b);
  verif2(a, b);
  printf("%s \n", a);
  return 0;
}

Here are some problems.
1. strins leaks the memory allocated to aux
2. your realloc calls are shrinking memory, not growing memory. strlen() tells you the length of the string excluding the \0. You need to count the \0 AND allow for the insertion of one more character.

General comments.
1. Better variable names than a, b, s would go a long way to improving readability.
2. Expressions like a[poz - a + 1] can be reduced to poz[1]
3. Don't cast the return result of realloc/malloc. All it is doing in your case is masking the fact that you've failed to include stdlib.h.
4. The initial allocation of 40 chars is inadequate for any meaningful HTML document.
5. Your use of feof() is wrong - see here
6. The b variable in main could be reduced to char *b = "\n";

__________________
If you dance barefoot on the broken glass of undefined behaviour, you've got to expect the occasional cut.
If at first you don't succeed, try writing your phone number on the exam paper

Developer Shed Advertisers and Affiliates