I'm trying to implement a dynamyc array of strings (which can be any length) read from console. However it crashes on the realloc() call in the loop. The code:
void kill(char **memory, int count) {
if (memory != NULL) {
for (int i = 0; i < count; i++) {
if (memory[i] != NULL) {
free(memory[i]);
}
}
free(memory);
}
}
char **getData(int *strCount, int *allocatedCount) {
int maxStrCount = 10;
int maxStrLength = 10;
char **data = malloc(sizeof(char *) * maxStrCount);
if (data == NULL) {
return NULL;
}
for (int i = 0; i < maxStrCount; i++) {
data[i] = malloc(sizeof(char) * maxStrLength);
if (data[i] == NULL) {
kill(data, i);
return NULL;
}
}
int i = 0;
int j = 0;
for (char ch = getchar(); ch != EOF; ch = getchar()) {
if (ch == '\n') { // if end of line
data[i][j] = '\0';
i++;
j = 0;
if (i >= maxStrCount) {
// extend array
char **newData = realloc(data, sizeof(char *) * (maxStrCount * 2));
if (newData == NULL) {
kill(data, maxStrCount);
return NULL;
}
maxStrCount *= 2;
data = newData;
for (int k = i; k < maxStrCount; k++) {
data[k] = malloc(sizeof(char) * maxStrLength);
if (data[k] == NULL) {
kill(data, k);
return NULL;
}
}
}
} else { // if not end of line
data[i][j] = ch;
j++;
if (j >= maxStrLength - 1) { // extend string
maxStrLength *= 2;
char *newStr = realloc(data[i], sizeof(char) * maxStrLength); // Here it crashes
if (newStr == NULL) {
kill(data, maxStrCount);
return NULL;
}
data[i] = newStr;
}
}
}
if (j > 0) { // in case of file doesn't end with empty line
data[i][j] = '\0';
i++;
}
if (i == 0) { // in case of empty input
kill(data, maxStrCount);
return NULL;
}
*strCount = i;
*allocatedCount = maxStrCount;
return data;
}
The crash appears on the following input:
Lorem ipsum dolor sit
amet, consectetur
adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua
It happens like this: It reads "Lorem ips", then realloc is called, then reads "Lorem ipsum dolor s", then realloc is called again, all fine. Then it reads "amet, consectetur" (2-nd line) and "adipiscing elit, sed do eiusmod tempor " (3-rd line), then tries to realloc and crashes.
I watched all this trying to debug, but I still have no idea why does it crash.
You are sharing the variable maxStrLength between all strings.
You are reallocating the buffer for the 2-nd line and increasing that maxStrLength; however, when you are reading the next line, it's buffer is smaller, so you are writing into it out-of-bounds here:
data[i][j] = ch;
Related
my program works fine if i give hard code value to char *w="ls -l" but i am trying to take input form user not working help my code:: using input error occur
i don't understand the concept of fgets using fgets its gives the garbig value to execv
#include<stdio.h>
#include<sys/wait.h>
#include<stdbool.h>
void func(char **arr, char *w)
{
int i = 0, j = 0, k = 0;
char temp[100];
for (i = 0; i < 100; i++)
{
if (w[i] == '')
{
arr[k] = temp;
arr[k+1] = NULL;
break;
}
if (w[i] == ' ')
{
arr[k] = temp;
k++;
j = 0;
}
else
{
temp[j] = w[i];
j++;
}
}
}
int main()
{
char *n = "/bin/ls";
char *arr[10] = {''};
char p[100] = {''};
char *w = "ls -l";
int i = 0;
//printf("bilal-hassan-qadri $ >>");
//fgets(p, 100, stdin);
arr[2] = NULL;
bool found = false;
for (i = 0; i < sizeof(w); i++)
{
if (w[i] == ' ')
{
found=true;
func(arr,w);
break;
}
}
if (!found)
arr[0] = w;
int status;
int id = fork();
if (id == 0)
{
if (execv(n,arr) < 0)
{
printf("invalid commandn");
}
else
{
printf("ninvalid command");
}
}
else
{
wait(&status);
}
}
In the function func, You have to copy the string to elements of arr
instead of just passing the address of temp, which will vanish on leaving the function.
You can use strdup instead of copy_string if your system supports it.
You have to terminate the string in temp before copying it.
Empty string constant '' seems invalid. You shouldn't use it.
fgets stores new-line character \n if it exists. Check for it and remove if it isn't wanted.
Fixed code:
#include<stdio.h>
#include<stdlib.h>
#include<string.h>
#include<sys/wait.h>
#include<stdbool.h>
char *copy_string(const char *str) {
char *s = malloc(strlen(str) + 1);
if (s) strcpy(s, str); else {perror("malloc"); exit(1);}
return s;
}
void func(char **arr, char *w)
{
int i = 0, j = 0, k = 0;
char temp[100];
for (i = 0; i < 100; i++)
{
if (w[i] == '\0' || w[i] == '\n')
{
temp[j] = '\0';
arr[k] = copy_string(temp);
arr[k+1] = NULL;
break;
}
if (w[i] == ' ')
{
temp[j] = '\0';
arr[k] = copy_string(temp);
k++;
j = 0;
}
else
{
temp[j] = w[i];
j++;
}
}
}
int main(void)
{
char *n = "/bin/ls";
char *arr[10] = {NULL};
char p[100] = {0};
char *w = "ls -l";
int i = 0;
//printf("bilal-hassan-qadri $ >>");
fgets(p, 100, stdin);
w = p;
arr[2] = NULL;
bool found = false;
for (i = 0; w[i] != '\0'; i++)
{
if (w[i] == ' ')
{
found=true;
func(arr,w);
break;
}
}
if (!found)
arr[0] = w;
int status;
int id = fork();
if (id == 0)
{
if (execv(n,arr) < 0)
{
printf("invalid commandn");
}
else
{
printf("ninvalid command");
}
}
else
{
wait(&status);
for (i = 0; arr[i] != NULL; i++) free(arr[i]);
}
return 0;
}
My code returns a Segmentation fault and I do not know why.
It prints part of the output and gives a Segmentation fault. I cannot find the error.
It should number words & sentences & paragraphs & top words with highest frequencies in order.
Here is my code:
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "preprocessing_header.h"
#include "calculations_header.h"
int main(int argc, char* argv[])
{
if (argc != 3)
{
printf("Error: number of arguments must be 3\n");
exit(-1);
}
char* file_name;
file_name = argv[1];
int N = atoi(argv[2]);
char final_string[number_of_char_aprox];
char *string;
string = Preprocessing(file_name);
strcpy(final_string, string);
printf("%s\n", final_string);
calculations(final_string, N);
return 0;
}
/* The main function for sorting the file in the appropriate form */
char* Preprocessing(char file_name[])
{
char final_string[number_of_char_aprox];
char *string;
FILE *in = fopen(file_name,"r");
if (in == NULL) {
printf("Not found");
exit(-1);
}
Head lines_list = (Head)malloc(sizeof(struct line)); // list of the lines from the file
lines_list->next = NULL;
readFile(lines_list, in); // read the file and put each line in a node in the list
fclose(in);
remove_spaces(lines_list); // make only a single space after each word in the lines
to_lower(lines_list); // convert all charachter in each line to small letter
punctuation_marks(lines_list); // make a one single space after punctuation marks
lines_list = reverse_list(lines_list); // reverse the list
string = concat_string(lines_list);// put all line in one string
strcpy(final_string, string);
free_list(lines_list);
string = Atter_punctuation_marks(final_string); // make letters atter punctuation
strcpy(final_string, string);
string = add_point(final_string);
strcpy(final_string, string);
//string = remove_line_feed(final_string);// remove line feed in the same paragraph
//strcpy(final_string, string);
string = final(final_string);// the final form of the string
return string;
}
/* Make the needed calculations */
void calculations(char final_string[],int N)
{
int i;
int number_of_words;
int number_of_sentences;
int number_of_paragraphs;
Head_word lw[26];// array of linked list of the words
for(i = 0; i < 26; i++)
{
lw[i] = (Head_word)malloc(sizeof(struct word));
lw[i]->next = NULL;
}
number_of_words = count_words(final_string, lw);
number_of_sentences = count_sentences(final_string);
number_of_paragraphs = count_paragraphs(final_string);
printf("\n******************************************************\n\n");
printf("\n******************************************************\n\n");
printf("number_of_words = %d\n",number_of_words);
printf("\nnumber_of_sentences = %d\n",number_of_sentences);
printf("\nnumber_of_paragraphs = %d\n",number_of_paragraphs);
printf("\n******************************************************\n\n");
printf("Top %d words with highest frequencies in order : \n\n",N);
Head_word most_repeated[N];
most_repeated_words(lw,most_repeated, N);
free_lists_words(lw);
sort(most_repeated,N); //sort the most frequently used words
print_most_repeated_words(most_repeated, N);
}
here is preprocessing_header.h
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "preprocessing_header.h"
/*read the file and put each line in a node in a linked list*/
void readFile(Head l, FILE *in)
{
position p;
while(!feof(in))
{
p = (position)malloc(sizeof(struct line));
fgets(p->string,10000,in);
p->next = l->next;
l->next = p;
}
}
/* make only a single space after each word in the lines*/
void remove_spaces(Head l)
{
int i = 0;
int j = 0;
int k;
position p = l->next;
char temp[1000];
while(p != NULL)
{
i = 0;
j = 0;
for(k = 0;k<1000;k++)
{
temp[k] = '\0';
}
while(p->string[i] != '\0')
{
if(p->string[0] == ' ')
{
while(p->string[i] == ' ')
i++;
}
while(p->string[i] != ' ' && p->string[i] != '\0')
{
temp[j] = p->string[i];
i++;
j++;
}
while(p->string[i] == ' ')
{
i++;
}
temp[j++] = ' ';
}
temp[j+1] = '\0';
strcpy(p->string,temp);
p = p->next;
}
}
void to_lower(Head l)
{
position p = l->next;
int i = 0;
while(p != NULL)
{
i = 1;
while(p->string[i] != '\0')
{
if(p->string[i]>= 65 && p->string[i]<=90)
{
p->string[i]+= 32;
}
i++;
}
p = p->next;
}
}
/*make a one single space after punctuation marks and no space before it*/
void punctuation_marks(Head l)
{
position p = l->next;
int i,j,k;
char temp[1000];
while(p != NULL)
{
i = 0;
j = 0;
for(k = 0;k<1000;k++)
{
temp[k] = '\0';
}
while(p->string[i] != '\0')
{
if(p->string[i] == '.' || p->string[i] == ',' || p->string[i] == ';' ||p->string[i] == '?' )
{
if(p->string[i-1] == ' ')
{
temp[--j] = p->string[i];
}
if(p->string[i+1] != ' ')
{
temp[j++] = p->string[i++];
temp[j++] = ' ';
}
}
temp[j++] = p->string[i++];
}
temp[j+1] = '\0';
strcpy(p->string,temp);
p = p->next;
}
}
/*reverse linked list*/
Head reverse_list(Head l)
{
Head l2 = (Head)malloc(sizeof(struct line));
l2->next = NULL;
position p = l->next;
while(p != NULL)
{
l->next = p->next;
p->next = l2->next;
l2->next = p;
p = l->next;
}
free(l);
return l2;
}
/* put all line in one string*/
char* concat_string(Head l)
{
char *temp = malloc(number_of_char_aprox*sizeof(char));
int k;
for(k = 0;k<number_of_char_aprox;k++)
{
temp[k] = '\0';
}
position p = l->next;
while(p != NULL)
{
strcat(temp,p->string);
p = p->next;
}
return temp;
}
/*remove line feed in the same paragraph*/
char* remove_line_feed(char final_string[])
{
int i;
char *temp = malloc(number_of_char_aprox*sizeof(char));
for(i = 0;i<number_of_char_aprox;i++)
{
temp[i] = '\0';
}
int j=0;
//printf("%s",final_string);
for(i = 0;i<strlen(final_string);i++)
{
if(final_string[i] == 13)
{
if(final_string[i-2]== '.')
{
temp[j++] = final_string[i++];
}
else
{
i = i+2;
}
}
temp[j++] = final_string[i];
}
return temp;
}
/*make letters atter punctuation marks capital letters*/
char* Atter_punctuation_marks(char string[])
{
char *temp = malloc(number_of_char_aprox*sizeof(char));
int k;
int i=0,j=0;
for(k = 0;k<number_of_char_aprox;k++)
{
temp[k] = '\0';
}
while(string[i] != '\0')
{
if(string[i] == '.' || string[i] == ';' ||string[i] == '?' || string[i] == '\n' )
{
if(string[i+2] >= 97 && string[i+2]<=122)
{
temp[j++] = string[i++];
temp[j++] = string[i++];
temp[j++] = string[i++]-32;
}
}
if(string[i] == 'i' && string[i-1] == ' ' && string[i+1] == ' ')
{
string[i]-= 32;
}
temp[j++] = string[i++];
}
temp[j+1] = '\0';
return temp;
}
char* to_lower_case(char string[])
{
int i = 0;
while(string[i] != '\0')
{
if(string[i]>= 65 && string[i]<=90)
{
string[i]+= 32;
}
i++;
}
return string;
}
/*make only one empty line between paragraphs and return the stirng with the final form*/
char* final(char s[])
{
int i;
int j = 0;
char *temp = malloc(number_of_char_aprox*sizeof(char));
for(i = 0;i<number_of_char_aprox;i++)
{
temp[i] = '\0';
}
j = 0;
for(i = 0;i<strlen(s);i++)
{
if(s[i]== ' ' && s[i-1] == '\n')
{
i++;
}
if(s[i] == '\n')
{
while(s[i+3] == '\n')
{
i+=3;
}
temp[j++] = '\n';
}
temp[j++] = s[i];
}
return temp;
}
void free_list(Head l)
{
position temp;
while(l->next != NULL)
{
temp = l->next;
l->next = temp->next;
free(temp);
}
free(l);
}
char* add_point(char s[])
{
int i,j=0;
char *temp = (char*)malloc(10000*sizeof(char));
for(i=0;i<strlen(s);i++)
{
if(s[i]==13 && !strchr(".,?;",s[i-1]) && !strchr(".,?;",s[i-2]) )
{
temp[j++] = '.';
i++;
}
temp[j++] = s[i];
}
return temp;
}
and here is my calculations_header.h
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "calculations_header.h"
/*count the number of words in the string and put the word in an array of linked list
which index is the first letter in each word eg (a)re in the linked list of index 0.
The word will be put in the list if it is a new word only if it is repeated the counter
of the node containing the word will increase*/
int count_words(char string[],Head_word lw[])
{
int i,j,k=0, length=0, count=0;
char word[50];
position_word p;
for(j=0;j<50;j++)
{
word[j] = '\0';
}
length= strlen(string);
for (i=0; i<length; i++)
{
if((string[i] == ' ' && string[i+1] != ' ') || string[i] == 10 || string[i] == 13)
{
if(!is_exist(word,lw[word[0]-97]))
{
//printf("%s\n",word);
p = (position_word)malloc(sizeof(struct word));
strcpy(p->string,word);
p->counter = 1;
p->next = lw[word[0]-97]->next;
lw[word[0]-97]->next = p;
}
//printf("%d",word[1]);
//printf("%s\n",word);
if((word[1]>=97 && word[1]<=123) || (word[1]>=65 && word[1]<=91))
count++;
k = 0;
for(j=0;j<50;j++)
{
word[j] = '\0';
}
}
if((string[i]>=97 && string[i]<=123) || (string[i]>=65 && string[i]<=91))
{
if(string[i] >= 65 && string[i] <= 90)
{
word[k] = string[i]+32;
}
else
{
word[k] = string[i];
}
k++;
}
}
return count;
}
/*test if the word is exist in the list*/
int is_exist(char word[], Head_word l)
{
int flag = 0;
Head_word p;
p = l->next;
while(p!=NULL)
{
if(strcmp(word,p->string) == 0)
{
p->counter++;
flag = 1;
break;
}
p = p->next;
}
return flag;
}
/*decide which N word are the most frequently used*/
void most_repeated_words(Head_word lw[],Head_word most_repeated[],int n)
{
int i,j;
int least;
position_word p;
for(i = 0 ;i<n;i++)
{
most_repeated[i] = (Head_word)malloc(sizeof(struct word));
most_repeated[i]->next = NULL;
most_repeated[i]->counter = 0;
}
for(i = 0;i<26;i++)
{
p = lw[i]->next;
while(p!= NULL)
{
for(j = 0 ; j<n;j++)
{
if(p->counter > most_repeated[j]->counter)
{
least = get_least(most_repeated,n);
strcpy(most_repeated[least]->string,p->string);
most_repeated[least]->counter = p->counter;
break;
}
}
p = p->next;
}
}
}
/*get the least repeated word in the array*/
int get_least(Head_word l[],int n)
{
int i;
int least = 10000;
int index;
for(i = 0;i<n;i++)
{
if(l[i]->counter < least)
{
least = l[i]->counter;
index = i;
}
}
return index;
}
/*count the number of sentences*/
int count_sentences(char s[])
{
int i;
int count = 0;
for(i=0;i<strlen(s);i++)
{
if(strchr(".?;,",s[i]))
{
count++;
}
}
return count;
}
/*count the number of paragraphs*/
int count_paragraphs(char s[])
{
int i;
int count = 0;
for(i=0;i<strlen(s);i++)
{
if(s[i] == '\n' && s[i+1]>=65 && s[i+1]<=90 )
{
count++;
}
}
return count+1;
}
/*print the most repeated N words and how many time it has been used*/
void print_most_repeated_words(Head_word most_repeated[],int N)
{
int i;
for(i=0;i<N;i++)
{
printf("%s\t%d\n",most_repeated[i]->string,most_repeated[i]->counter);
}
}
/*sort the N most frequently used word in ascending order */
void sort(Head_word most_repeated[],int N)
{
int i,j;
Head_word temp = (Head_word)malloc(sizeof(struct word));
for (i = 0 ; i < ( N - 1 ); i++)
{
for (j = 0 ; j < N - i - 1; j++)
{
if (most_repeated[j]->counter < most_repeated[j+1]->counter)
{
temp->counter = most_repeated[j]->counter;
strcpy(temp->string,most_repeated[j]->string);
most_repeated[j]->counter = most_repeated[j+1]->counter;
strcpy(most_repeated[j]->string,most_repeated[j+1]->string);
most_repeated[j+1]->counter = temp->counter;
strcpy(most_repeated[j+1]->string,temp->string);
}
}
}
}
void free_lists_words(Head_word l[])
{
int i;
position_word temp;
for(i = 0;i<26;i++)
{
while(l[i]->next != NULL)
{
temp = l[i]->next;
l[i]->next = temp->next;
free(temp);
}
free(l[i]);
}
}
and here is my calculations_header.h:
#ifndef CALCULATIONS_HEADER_H_INCLUDED
#define CALCULATIONS_HEADER_H_INCLUDED
/*This structure to save each word to make calculations*/
typedef struct word *ptr_word;
struct word
{
char string[50];
int counter;
ptr_word next;
};
typedef ptr_word Head_word;
typedef ptr_word position_word;
/*calculation functions prototypes*/
char* Preprocessing(char []);
void calculations(char [],int);
int count_words(char [],Head_word[]);
int is_exist(char [], Head_word);
void print(Head_word[]);
void most_repeated_words(Head_word [],Head_word[],int);
int get_least(Head_word[],int);
int count_paragraphs(char []);
int count_sentences(char []);
void print_most_repeated_words(Head_word[],int);
void sort(Head_word [],int);
void free_lists_words(Head_word []);
#endif // CALCULATIONS_HEADER_H_INCLUDED
and here is my preprocessing_header.h:
#ifndef PREPROCESSING_HEADER_H_INCLUDED
#define PREPROCESSING_HEADER_H_INCLUDED
#define number_of_char_aprox 10000
/*This structure for saving each line read from the file*/
typedef struct line *ptr;
struct line
{
char string[10000];
ptr next;
};
typedef ptr Head;
typedef ptr position;
/*preprocessing functions prototypes*/
void readFile(Head,FILE *);
void remove_spaces(Head);
void to_lower(Head);
void punctuation_marks(Head );
Head reverse_list(Head);
char* concat_string(Head);
void free_list(Head);
char* Atter_punctuation_marks(char []);
char* remove_line_feed(char []);
char* final(char []);
#endif // PREPROCESSING_HEADER_H_INCLUDED
it give me just warning on line 60 in main( string = add_point(final_string); )
i think the function calculations it make the error.
char final_string[number_of_char_aprox];
What's number_of_char_aprox? You don't even declare it as a variable. A segmentation fault happens when you are trying to access not assigned memory. As there is no value for that variable (actually there is no variable at all), it probably defaults to 0 (or NULL, or imploding universe, who knows), and when you use it to reserve memory for final_string you got your segmentation fault.
By the way, DDD is a great graphical debugger.
typedef struct {
int *info;
} row;
struct {
row* head;
int len;
int size;
} list;
int main{
list.len = 0;
list.size = 1;
list.head = malloc(list.size * sizeof(row));
//...... some other code that calls addRow (list.len) times
for (i = list.len - 1; i > 0; i--) {
free(list.head[i].info);/*****HERE**********/
}
free(list.head);
}
void addRow(int* data) {
int i;
if (list.len == list.size) {
row *temp = malloc(sizeof(row) * list.size * 2);
if (temp == NULL) {
fprintf(stderr, "Error (enter): (Line ##) Insufficient memory.\n");
return;
}
for (i = 0; i < list.len; i++) {
temp[i] = list.head[i];
}
free(list.head);
list.head = temp;
}
list.head[list.len].info = malloc(sizeof(int) * numCols);
for (i = 0; i < numCols; i++) {
list.head[list.len].info[i] = data[i];
}
list.len++;
}
This is the code that I used to addRow is were I malloc all the data. and I don't see why I'm getting a double free/ corruption error. At the area I marked HERE, I believe I am malloc-ing for all instances of info in the row struct, These line are the only ones doing malloc/free.
I just want to get into the habit free-ing properly when terminating the program.
FULL PROGRAM:
#include<stdio.h>
#include<stdlib.h>
#include<ctype.h>
typedef struct {
int *info;
} row;
struct {
row* head;
int len;
int size;
} list;
static int sortCol, numCols;
int qSortCompare(const void*, const void*);
void printList();
int processInput();
void nullify(char*, int);
int main(int n, char **args) {
sortCol = 1;
numCols = 0;
if (n > 1 && args[1][0] == '-' && args[1][1] == 'c') {
sortCol = atoi(args[2]);
}
list.len = 0;
list.size = 1;
list.head = malloc(list.size * sizeof(row));
processInput();
if (sortCol < 1 || sortCol > numCols) {
fprintf(stderr, "Error (enter): (Line ##) Invalid column to sort.\n");
return 1;
}
printList();
qsort(list.head, list.len, sizeof(row), &qSortCompare);
printf("\n");
printList();
int i;
printf("add1:%p\nadd2:%p\n", list.head[0].info, list.head[1].info);
for (i = 0; i < list.len; i++) {
free(list.head[i].info);
}
free(list.head);
return 0;
}
void nullify(char* str, int n) {
int i;
for (i = 0; i < n; i++)
str[i] = '\0';
}
int parseInt(char *str, int index) {
int num = -1;
sscanf(str + index, "%d", &num);
return num;
}
void addRow(int* data) {
int i;
if (list.len == list.size) {
row *temp = malloc(sizeof(row) * list.size * 2);
if (temp == NULL) {
fprintf(stderr, "Error (enter): (Line ##) Insufficient memory.\n");
return;
}
for (i = 0; i < list.len; i++) {
temp[i] = list.head[i];
}
free(list.head);
list.head = temp;
}
list.head[list.len].info = malloc(sizeof(int) * numCols);
if (list.head[list.len].info == NULL) {
fprintf(stderr, "Error (enter): (Line ##) Insufficient memory.\n");
return;
}
for (i = 0; i < numCols; i++) {
list.head[list.len].info[i] = data[i];
}
list.len++;
}
int processInput() {
int i, maxChars = 200, totalN = 0;
int *nums, curNumIndex = 0, onNum, curNum;
numCols = maxChars / 2;
nums = (int*) (malloc(sizeof(int) * numCols));
char str[maxChars], ch;
for (i = 0; i < numCols; i++) {
nums[i] = -1;
}
while (!feof(stdin)) {
nullify(str, maxChars);
fgets(str, maxChars, stdin);
onNum = isdigit(str[0]);
curNumIndex = 0;
for (i = 0; i < maxChars; i++) {
ch = str[i];
if ((!isspace(ch)) && (!isdigit(ch)) && (ch != '\0')) {
fprintf(stderr, "Error 1: (Line ##) Invalid char in input.\n");
//return 0;
}
if (isspace(ch) && onNum) {
curNum = parseInt(str, curNumIndex);
curNumIndex = i;
nums[totalN % numCols] = curNum;
totalN++;
if (totalN % numCols == 0)
addRow(nums);
} else {
onNum = isdigit(str[i]);
}
if (ch == '\n' || ch == '\0')
break;
}
if (numCols > totalN) {
if (totalN > 0) {
numCols = totalN;
addRow(nums);
} else {
fprintf(stderr,
"Error (enter): (Line ##) Invalid first line of input.\n");
}
}
if (ch != '\n' && ch != '\0') {
fprintf(stderr,
"Error (enter): (Line ##) A row from input too long.\n");
//return 0;
}
}
return 1;
}
int qSortCompare(const void *c1, const void *c2) {
row *t1, *t2;
t1 = (row*)c1;
t2 = (row*)c2;
return t1->info[sortCol - 1] - t2->info[sortCol - 1];
}
void printList() {
int i, j;
for (i = 0; i < list.len; i++) {
for (j = 0; j < numCols; j++) {
printf("%10d ", list.head[i].info[j]);
}
printf("\n");
}
}
Program needs a EOF terminated input of integer numbers. Specifically with the same number of integers before the newline.
UPDATE: I used gdb to analysis the free part i it only fails on the second iteration, using for(i = 0; i < list.len; i++) and for(i = list.len - 1; i > 0 ; i--)
Another thing is that I don't see the update to list.size (it should be updated when resizing head)
"I just want to get into the habit free-ing properly when terminating the program."
The correct way to handle things like this is to free a non-NULL pointer and then set the pointer to NULL.
For example:
int* x = malloc (sizeof (int));
if (x != NULL) {
free (x);
x = NULL;
}
/* Misc. Code ... */
/* Now for whatever reason, you want to free x again */
/* This branch is never triggered, because you were smart enough to set x to NULL
* when you freed it the first time...
*/
if (x != NULL) {
free (x);
x = NULL;
}
filenamelists is a struct with two file pointers. merge mergesorts these two fileptrs. I'm getting a segfault on the while(fscanf(filenamelist[0].file1, "%d", &chd) != EOF). I think its because I'm not implementing pthread correctly. Ive been trying to debug forever so any help would be appreciated. tempf is a file ptr to the mergesorted arrays. It is rewinded in the merge function itself.
for(i=0; i<size; i++)
{
if(argc==1)
{
char* tedious2 = (char*) malloc((strlen(argv[i+1]+7))*sizeof(char));
strcpy(tedious2,argv[i+1]);
filenamelist[i].file1 = fopen(strcat(tedious2,".sorted"),"r");
filenamelist[i].file2 = NULL;
filenamelist[i].alone = 1;
free(tedious2);
break;
}
else if(size-1 ==i && size%2 != 0)
{
char* tedious1 = (char*) malloc((strlen(argv[i+1]+7))*sizeof(char));
strcpy(tedious1,argv[i+1]);
filenamelist[i].file1 = fopen(strcat(tedious1,".sorted"),"r");
filenamelist[i].file2 = NULL;
filenamelist[i].alone = 1;
free(tedious1);
}
else
{
char* tedious3 = (char*) malloc((strlen(argv[i+1]+7))*sizeof(char));
strcpy(tedious3,argv[i+1]);
char* tedious4 = (char*) malloc((strlen(argv[i+2]+7))*sizeof(char));
strcpy(tedious4,argv[i+2]);
filenamelist[i].file1 = fopen(strcat(tedious3,".sorted"),"r");
filenamelist[i].file2 = fopen(strcat(tedious4,".sorted"),"r");
filenamelist[i].alone = 0;
free(tedious3);
free(tedious4);
}
}
// pthread_t* threadid2;
// threadid2 = (pthread_t*) malloc(sizeof(pthread_t)*(2*argc));
while(size>=0)
{
i = 0;
pthread_t* threadid2;
threadid2 = (pthread_t*) malloc(sizeof(pthread_t)*size);
for ( ; i<size;i++ )
{
pthread_create(&threadid2[i], NULL, merge, &filenamelist[i]);
}
i = 0;
for ( ; i<size; i++)
{
pthread_join(threadid2[i], tempf);
if (i%2 == 0)
{
filenamelist[i/2].file1 = tempf;
}
else
{
filenamelist[i/2].file2 = tempf;
}
}
zit=0;
truth = 0;
while(zit<z)
{
if(inputFiles[zit] == tempf)
truth = 1;
zit++;
}
if(truth != 1)
{
inputFiles[z] = tempf;
z++;
}
if(size==1)
size = 0;
else if (size % 2 == 0)
size = size/2;
else
size = (size/2)+1;
free(threadid2);
}
int chd = 0;
// if(0!=feof(tempf))
// rewind(tempf);
//rewind(filenamelist[0]->file1);
int finish = 0;
//printf("file 1:%p",tempf);
while(fscanf(filenamelist[0].file1, "%d", &chd) != EOF)
finish++;
rewind(filenamelist[0].file1);
int* finarr = (int*) malloc(finish*sizeof(int));
int xx =0;
for(;fscanf(filenamelist[0].file1, "%d", &chd) != EOF; xx++)
finarr[xx] = chd;
tempf is declared at start of func as FILE* tempf;
char* tedious2 = (char*) malloc((strlen(argv[i+1]+7))*sizeof(char));
Make that:
char *tedious2 = malloc( strlen(argv[i+1]) + strlen(".sorted") + 1 );
How can i strip the HTML from document between and including the <...> tags in a HTML document using C? My current program uses curl to get the contents of the webpage and puts it into a text file, it then reads from the text file and removes the <>, but i am unsure of how to remove everything between those tags.
#include <curl/curl.h>
#include <stdio.h>
#include <stdlib.h>
#include <fcntl.h>
#include <unistd.h>
#define WEBPAGE_URL "http://homepages.paradise.net.nz/adrianfu/index.html"
#define DESTINATION_FILE "/home/user/data.txt"
size_t write_data( void *ptr, size_t size, size_t nmeb, void *stream)
{
return fwrite(ptr,size,nmeb,stream);
}
int main()
{
int in_tag = 0;
char * buffer;
char c;
long lSize;
size_t result;
FILE * file = fopen(DESTINATION_FILE,"w+");
if (file==NULL) {
fputs ("File error",stderr);
exit (1);
}
CURL *handle = curl_easy_init();
curl_easy_setopt(handle,CURLOPT_URL,WEBPAGE_URL); /*Using the http protocol*/
curl_easy_setopt(handle,CURLOPT_WRITEFUNCTION, write_data);
curl_easy_setopt(handle,CURLOPT_WRITEDATA, file);
curl_easy_perform(handle);
curl_easy_cleanup(handle);
int i, nRead, fd;
int source;
char buf[1024];
if((fd = open("data.txt", O_RDONLY)) == -1)
{
printf("Cannot open the file");
}
else
{
nRead = read(fd, buf, 1024);
printf("Original String ");
for(i=0; i<nRead; i++)
{
printf("%c", buf[i]);
}
printf("\nReplaced String ");
for(i=0; i<nRead; i++)
{
if(buf[i]=='<' || buf[i]=='>'){
buf[i]=' ';
}
printf("%c", buf[i]);
}
}
close(source);
return 0;
}
Placing just the code that removes the contents between the '<' and '>' tags (assuming that you deal with proper html, meaning that you don't have one tag nested in the declaration of the other like <html < body> >). I am just changing a small portion of your code. I will also remove the tags from the buf variable, instead of replacing the undesired characters with intervals, because I think this will be more useful to you (correct me if I am wrong).
int idx = 0;
int opened = 0; // false
for(i=0; i<nRead; i++)
{
if(buf[i]=='<') {
opened = 1; // true
} else if (buf[i] == '>') {
opened = 0; // false
} else if (!opened) {
buf[idx++] = buf[i];
}
}
buf[idx] = '\0';
printf("%s\n", buf);
This would also handle scripts and style tags
int stripHTMLTags(char *sToClean,size_t size)
{
int i=0,j=0,k=0;
int flag = 0; // 0: searching for < or & (& as in &bspn; etc), 1: searching for >, 2: searching for ; after &, 3: searching for </script>,</style>, -->
char tempbuf[1024*1024] = "";
char searchbuf[1024] = "";
while(i<size)
{
if(flag == 0)
{
if(sToClean[i] == '<')
{
flag = 1;
tempbuf[0] = '\0';
k=0; // track for <script>,<style>, <!-- --> etc
}
else if(sToClean[i] == '&')
{
flag = 2;
}
else
{
sToClean[j] = sToClean[i];
j++;
}
}
else if(flag == 1)
{
tempbuf[k] = sToClean[i];
k++;
tempbuf[k] = '\0';
//printf("DEBUG: %s\n",tempbuf);
if((0 == strcmp(tempbuf,"script")))
{
flag = 3;
strcpy(searchbuf,"</script>");
//printf("DEBUG: Detected %s\n",tempbuf);
tempbuf[0] = '\0';
k = 0;
}
else if((0 == strcmp(tempbuf,"style")))
{
flag = 3;
strcpy(searchbuf,"</style>");
//printf("DEBUG: Detected %s\n",tempbuf);
tempbuf[0] = '\0';
k = 0;
}
else if((0 == strcmp(tempbuf,"!--")))
{
flag = 3;
strcpy(searchbuf,"-->");
//printf("DEBUG: Detected %s\n",tempbuf);
tempbuf[0] = '\0';
k = 0;
}
if(sToClean[i] == '>')
{
sToClean[j] = ' ';
j++;
flag = 0;
}
}
else if(flag == 2)
{
if(sToClean[i] == ';')
{
sToClean[j] = ' ';
j++;
flag = 0;
}
}
else if(flag == 3)
{
tempbuf[k] = sToClean[i];
k++;
tempbuf[k] = '\0';
//printf("DEBUG: %s\n",tempbuf);
//printf("DEBUG: Searching for %s\n",searchbuf);
if(0 == strcmp(&tempbuf[0] + k - strlen(searchbuf),searchbuf))
{
flag = 0;
//printf("DEBUG: Detected END OF %s\n",searchbuf);
searchbuf[0] = '\0';
tempbuf[0] = '\0';
k = 0;
}
}
i++;
}
sToClean[j] = '\0';
return j;
}