Load/fill a struct with char** array as a struct member, c - c

In the last two days i have asked a question to load struct, but i have a problem to access my struct out side my loop(a loop to load my struct). i have edited my question/and code this way:
myfile.txt
Biology,chemistry,maths,music
Mechanics,IT,Geology,music,Astronomy
football,vollyball,baseball
main.c
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#define path "myfile.txt"
typedef struct student_info
{
char **cources_as_list;
} std_info;
std_info *myinfo; //a global var that will conatain student info
int line_count = 0, cource_count = 0;
char** load_file()
{
char *line = NULL;
size_t len = 0;
FILE *fp;
int indexq=0;
fp = fopen(path, "r");
if (fp == NULL)
{
perror("FILE OPEN ERROR[IN load_file]: ");
exit(1);
}
char **mydata = malloc (sizeof (char *) * 4);//aup to four elements
while (getline(&line, &len, fp) != -1)
{
strtok(line, "\n");
mydata[indexq]= strdup(line);
indexq++;
}
line_count = indexq;
return mydata;
}
char **return_cource_list(char *cources_string) {
char *token;
char **cource_list = malloc(sizeof(char *) * 10);
int index = 0;
//course_string is delimited by ",": (eg. Biology,chemistry,maths,music). parse this and add to my char ** variable.
token = strtok(cources_string, ",");
while (token != NULL)
{
cource_list[index] = strdup(token);
token = strtok(NULL, ",");
index++;
}
cource_count = index;
return cource_list;
}
int main()
{
int i, j;
char** mydata = load_file(); //returns lines as a list/char ** array from file
for (i = 0; i < line_count; i++) //line_count is the number of elements/lines in "mydata"
{
printf("line_data: %s\n",mydata[i]);//i can see all my lines!
char **std_cource_list = return_cource_list(mydata[i]);
for (j = 0; j < cource_count; j++)
{
printf("\tcourse[%d]: %s\n",j,std_cource_list[j]);//i have all my courses as a list from each line
}
//can i load my struct like this? or any option to load my struct?
myinfo[i].cources_as_list = std_cource_list;
}
// i want to see my structure elements here, (nested for loop required).
}
Am getting seg_fault error while loading my char array to my struct.
(i.e: this line: myinfo[i].cources_as_list = std_cource_list;)

You need to allocate the memory for your struct.
std_info *myinfo = malloc(sizeof(std_info));
Also don't make it global, since there is really no need for global variables in this task.

Try
std_info * myinfo = malloc(line_count * sizeof *myinfo);
This allocates memory to hold line_count objects of std_info, with myinfo pointing to the 1st.

You never allocate space for myinfo and I would suggest making it a local variable. There is almost no need for global variables except in very specific cases.
Also, you are using malloc() almost only for fixed size allocations which would be easier to manage and more efficient if you do statically in the sense that you can use arrays for that.
This might be what you're interested in
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <stddef.h>
struct student_info
{
char **courses;
size_t size;
};
char **
load_file(const char *const path)
{
char *line;
FILE *file;
char **data;
size_t row;
size_t length;
size_t count;
file = fopen(path, "r");
if (file == NULL)
{
perror("FILE OPEN ERROR[IN load_file]: ");
return NULL; // Notify the caller that there was a problem
// but do not necessarily quit as you might
// retry with another path.
}
count = 0;
for (int chr = fgetc(file) ; chr != EOF ; chr = fgetc(file))
count += (chr == '\n') ? 1 : 0;
rewind(file);
data = malloc((count + 1) * sizeof(*data));
if (data == NULL)
{
// Perhaps notify the error
fclose(file);
return NULL;
}
data[count] = NULL; // Use as end of array delimiter
row = 0;
line = NULL;
length = 0;
while ((length = getline(&line, &length, file)) != -1)
{
// The last character is always `\n' so remove it
data[row] = malloc(length);
if (data == NULL)
{
fclose(file);
for (size_t i = row ; i >= 0 ; --i)
{
free(data[i]);
free(data);
return NULL;
}
}
data[row][length - 1] = '\0';
memcpy(data[row], line, length - 1);
++row;
}
fclose(file);
// You need to `free' this, read the documentation
free(line);
return data;
}
char **
extract_courses_as_list(const char *const input)
{
char **courses;
size_t index;
const char *tail;
const char *head;
size_t count;
head = input;
count = 0;
/* Count the number of fields to allocate memory */
while (head != NULL)
{
tail = strchr(head, ',');
if (tail != NULL)
head = tail + 1;
else
head = NULL;
count += 1;
}
index = 0;
/* Allocate memory for the list, and the sentinel */
courses = malloc((count + 1) * sizeof(*courses));
head = input;
while (head != NULL)
{
ptrdiff_t length;
/* find the next `,' in the input string */
tail = strchr(head, ',');
if (tail == NULL) /* if it's not there, it's the last one */
tail = strchr(head, '\0');
/* compute the number of characters of the field */
length = (ptrdiff_t) (tail - head);
/* allocate space to copy the string */
courses[index] = malloc(length + 1);
if (courses == NULL) /* always be safe and check */
{
for (size_t i = index ; i >= 0 ; --i)
free(courses[index]);
free(courses);
return NULL;
}
/* always remember to `null' terminate */
courses[index][length] = '\0';
/* finally, copy the string */
memcpy(courses[index], head, length);
/* check whehter it was the last field and
* update the pointer to the next one accordingly
*/
if ((tail != NULL) && (*tail != '\0'))
head = tail + 1;
else
head = NULL;
/* Don't forget the fields counter */
index++;
}
courses[count] = NULL;
return courses;
}
void
concatenate_lists(struct student_info *info, char **source)
{
char **temporary;
size_t length;
length = info->size;
for (size_t i = 0 ; source[i] != NULL ; ++i)
length++;
temporary = realloc(info->courses, length * sizeof(*temporary));
if (temporary == NULL)
return;
for (size_t i = 0 ; source[i] != NULL ; ++i)
temporary[i + info->size] = strdup(source[i]);
info->courses = temporary;
info->size = length;
}
void
free_list(char **lines)
{
if (lines == NULL)
return;
for (size_t i = 0 ; lines[i] != '\0' ; ++i)
free(lines[i]);
free(lines);
}
int
main()
{
struct student_info info;
char **lines;
lines = load_file("data.tx");
if (lines == NULL)
return -1;
info.courses = NULL;
info.size = 0;
for (size_t i = 0 ; lines[i] != NULL ; ++i)
{
char **courses;
courses = extract_courses_as_list(lines[i]);
if (courses == NULL)
continue;
concatenate_lists(&info, courses);
free_list(courses);
}
for (size_t i = 0 ; i < info.size ; ++i)
{
fprintf(stderr, "%s\n", info.courses[i]);
free(info.courses[i]);
}
free(info.courses);
free_list(lines);
return 0;
}
You will notice that I never used strdup(), the reason being that the length of the string that we want to copy is always known.

Related

How to get whole structure from function?

This is my code:
#include <stdio.h>
typedef struct
{
char name[100];
char number[100];
} contact_t;
void empty_array(char *line)
{
for (int j = 0; line[j] != '\0'; j++)
{
line[j] = '\0';
}
}
void read_text(contact_t *contact)
{
int c, cnt = 0;
int i = 0;
char line[100];
do
{
c = getchar();
if ( (c == '\n') || (c == EOF))
{
if( cnt % 2 == 0)
{
for(int j = 0; line[j] != '\0'; j++)
contact -> name[j] = line[j];
}
else
{
for(int j = 0; line[j] != '\0'; j++)
contact -> number[j] = line[j];
}
empty_array(line);
i = 0;
cnt++;
}
line [i] = c;
i++;
} while (c != EOF);
}
int main()
{
contact_t contact = {"x", "0"};
int *j_ptr;
read_text(&contact);
printf("%s", contact.name);
printf("%s", contact.number);
return 0;
}
I am reading a text file(6 lines, name and number, name and number...) from standard input. Then I assign every second line(starting from the first) from that text file to structure contact.name and the rest are I assign to contact.number. So I have several 3 contact structures. I managed to pass to main only the last one, because I don't know how to get acces to int cnt and again make a for cycle.
This is what last prints give me:
John Green
254454556
UPDATE:
I am sorry for not being clear enough as I was writing this question in a hurry. This code is a part of school project and we are not allowed to work with dynamically allocated memory or use fscanf, fopen, qsort, lsearch, bsearch and hsearch etc. Basically, I would just like to use pointers to index of array line and then in main function use a for cycle again to pass all structures from the function read_text to main function of the program.
A few issues ...
main only provides space for one contact entry
read_text needs to use a dynamic array (vs. overwriting the same entry)
read_text needs to return the list pointer and the count to the caller (e.g. main)
The method used in read_text is a bit convoluted.
Style fixes:
contact -> name --> contact->name
list [i] --> list[i]
Here is the refactored code. It is annotated:
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
typedef struct {
char name[100];
char number[100];
} contact_t;
int
read_text(contact_t **listp)
{
char buf[1000];
contact_t *list = NULL;
char *cp = NULL;
int cnt = 0;
// loop on input until EOF
while (fgets(buf,sizeof(buf),stdin) != NULL) {
// increase size of list
++cnt;
list = realloc(list,sizeof(*list) * cnt);
// handle error
if (list == NULL) {
perror("realloc/increase");
exit(1);
}
// point to current record
contact_t *contact = &list[cnt - 1];
// get first name
contact->name[0] = 0;
cp = strtok(buf," \n");
if (cp == NULL)
break;
strcat(contact->name,cp);
// add separater
strcat(contact->name," ");
// get last name
cp = strtok(NULL," \n");
if (cp == NULL)
break;
strcat(contact->name,cp);
// get number
cp = strtok(NULL," \n");
if (cp == NULL)
break;
strcpy(contact->number,cp);
}
// trim to actual amount stored (if error)
if ((cp == NULL) && (cnt > 0)) {
--cnt;
list = realloc(list,sizeof(*list) * cnt);
if (list == NULL) {
perror("realloc/trim");
exit(1);
}
}
// give caller the list pointer
*listp = list;
return cnt;
}
int
main(void)
{
int cnt;
contact_t *list;
cnt = read_text(&list);
// print all entries read in
for (int idx = 0; idx < cnt; ++idx) {
contact_t *contact = &list[idx];
printf("'%s' '%s'\n",contact->name,contact->number);
}
return 0;
}
Here is the test input I used:
John Green 254454556
Fred Smith 8765309
Bob Jones 99728967341
Mary Gallagher 4329268757
Here is the program output:
'John Green' '254454556'
'Fred Smith' '8765309'
'Bob Jones' '99728967341'
'Mary Gallagher' '4329268757'
UPDATE:
I am sorry, I should have clarified that I cannot use dynamically allocated memory. Malloc, calloc or also fsangf is not available –
gregalz
Okay, no malloc et. al. Ironically, I was going to use a predefined fixed size array. But, decided to use a dynamic array instead ;-)
Not sure what fsangf is. So, I'll assume that's fscanf. If you're heavily restricted, maybe you should edit your question and post what you can and can not use.
Here's the code that uses just a fixed array:
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
typedef struct {
char name[100];
char number[100];
} contact_t;
#define NLIST 1000
contact_t list[NLIST];
int
read_text(contact_t *list,int max)
{
char buf[1000];
char *cp = NULL;
int cnt = 0;
// loop on input until EOF
while (fgets(buf,sizeof(buf),stdin) != NULL) {
// don't overflow the max size
if (cnt >= max)
break;
// point to current record and increase list count
contact_t *contact = &list[cnt++];
// get first name
contact->name[0] = 0;
cp = strtok(buf," \n");
if (cp == NULL)
break;
strcat(contact->name,cp);
// add separater
strcat(contact->name," ");
// get last name
cp = strtok(NULL," \n");
if (cp == NULL)
break;
strcat(contact->name,cp);
// get number
cp = strtok(NULL," \n");
if (cp == NULL)
break;
strcpy(contact->number,cp);
}
// trim to actual amount stored (if error)
if ((cp == NULL) && (cnt > 0))
--cnt;
return cnt;
}
int
main(void)
{
int cnt;
cnt = read_text(list,NLIST);
// print all entries read in
for (int idx = 0; idx < cnt; ++idx) {
contact_t *contact = &list[idx];
printf("'%s' '%s'\n",contact->name,contact->number);
}
return 0;
}

Memory leak caused by realloc in valgrind C

I have a my_string object made that contains a char pointer, a size, and a capacity. I am trying to read words from a dictionary text file into the my_string object and print them to the screen. The default capacity is 7, so when I read a word that is longer than 7 characters, I need to reallocate some space at the end of the string. I haven't been able to implement this functionality correctly yet. It seems to work correctly, but when I run it in valgrind, there is apparently a memory leak somewhere in my code. Not sure where this is coming from, because I free the entire string after the program runs. If someone could help me with this you'd be a lifesaver. Here is my driver code, and my my_string.c file:
main.c
#include <stdio.h>
#include <stdlib.h>
#include "my_string.h"
int main(int argc, char* argv[]) {
MY_STRING hMy_String = NULL;
FILE* fp;
hMy_String = my_string_init_default();
fp = fopen("dictionary.txt", "r");
int len;
while(my_string_extraction(hMy_String, fp)) {
len = my_string_get_size(hMy_String);
if(len == 8){
my_string_insertion(hMy_String, stdout);
printf("\n");
if(fgetc(fp) == ' '){
printf("Found a space after the string\n");
}
}
}
my_string_destroy(&hMy_String);
fclose(fp);
return 0;
}
my_string.c
#include <stdio.h>
#include <stdlib.h>
#include "my_string.h"
struct my_string {
int size;
int capacity;
char* data;
};
typedef struct my_string My_String;
MY_STRING my_string_init_default(void){
//default capacity of string is 7
//initializes pointer to My_String, set to NULL for good practice
My_String* pMy_String = NULL;
//allocates memory for default string
pMy_String = (My_String*)malloc(sizeof(My_String));
if(pMy_String != NULL) {
pMy_String->size = 0;
pMy_String->capacity = 7;
pMy_String->data = (char*)malloc(sizeof(char) * pMy_String->capacity);
if(pMy_String->data == NULL) {
free(pMy_String);
pMy_String = NULL;
}
}
//returns copy of address to default string
return pMy_String;
}
MY_STRING my_string_init_c_string(char* c_string) {
int i = 0;
//initializes a pointer to a My_String
My_String* theString = NULL;
//loops through string, for every character, i increases 1
while((*c_string) != '\0'){
c_string++;
i++;
}
//resets c_strings value from before the loop
c_string = c_string - i;
i++; //i needs to be 1 greater than the length of the string
//allocation
theString = malloc(sizeof(My_String) + i);
//if there was an error, return NULL
if(theString == NULL)
return NULL;
else {
//sets the values of the object to the given values
(*theString).size = (i - 1);
(*theString).capacity = i;
(*theString).data = c_string;
}
//returns address of the initialized string
return theString;
}
int my_string_get_capacity(MY_STRING hMy_string){
return sizeof(hMy_string);
}
int my_string_get_size(MY_STRING hMy_string) {
char* str = (char*) hMy_string;
int size = 0;
while(str[size] != '\0')
size++;
return size;
}
int my_string_compare(MY_STRING hLeft_string, MY_STRING hRight_string) {
// sets the strings to pointers to the My_String data type
My_String* Left = hLeft_string;
My_String* Right = hRight_string;
//variables for lexicographical value of each string
int left_lex = 0;
int right_lex = 0;
//loops through left string, adds up left_lex value
while((*Left->data) != '\0') {
left_lex += (*Left->data);
(*Left).data++;
}
//loops through right string, adds up right_lex value
while((*Right->data) != '\0') {
right_lex += (*Right->data);
(*Right).data++;
}
//does the comparison and returns the corrosponding value
if(left_lex < right_lex){
return -1;
}else if (left_lex == right_lex) {
return 0;
}else {
return 1;
}
}
Status my_string_extraction(MY_STRING hMy_string, FILE* fp) {
My_String* pMy_string = hMy_string;
int start = 0, end = 0;
char ch;
int strLength, capacity, i;
while(!feof(fp)){
ch = fgetc(fp);
if(ch == ' ' || ch == '\t' || ch == '\n' ||ch == '\r') {
continue;
}
else {
start = ftell(fp) - 1;
end = start + 1;
break;
}
}
if(end == 0){
return FAILURE;
}
while(!feof(fp)) {
ch = fgetc(fp);
end++;
if(ch == ' ' || ch == '\t' || ch == '\n' ||ch == '\r'){
break;
}
}
strLength = end - start - 1;
(*pMy_string).size = strLength;
if(strLength == 0){
return FAILURE;
}
capacity = my_string_get_capacity(hMy_string);
if(strLength >= capacity){
hMy_string = realloc(hMy_string, strLength + 1);
}
fseek(fp, start, SEEK_SET);
char* str = (char*)hMy_string;
for(i = 0; i < strLength; i++) {
str[i] = fgetc(fp);
}
str[i] = '\0';
return SUCCESS;
}
Status my_string_insertion(MY_STRING hMy_string, FILE* fp) {
char* str = (char*)hMy_string;
if(fprintf(fp, "%s", str))
return SUCCESS;
else
return FAILURE;
}
void my_string_destroy(MY_STRING* phMy_string){
free(*phMy_string);
*phMy_string = NULL;
}

Read text from phone book list and add to a structure

I am attempting to read from file "pb_List.txt" that contains:
John:789-654-3210
Bill:852-123-4567
Amy:963-321-0000
I need to add the name and number contents to a phone book structure "pb"
struct phonebook{
char name[value_size];
char phone[value_size];
}
struct phonebook pb[book_size];
UPDATE:
void addFile(){
File *pb_List;
pb_List = fopen("pb_List.txt", "r");
char name[value_size];
char phone[value_size];
fscanf(pb_List, "%s %s", name, phone);
strcpy(pb[size].name, name);
strcpy(pb[size].phone, phone);
size++
}
I was able to add the first line, but my function obviously doesn't iterate to the next line. How would my while loop look for this?
So I ended up wanting to continue writing an almost full program to your problem. Thus, I updated this answer with a full example of how to use my original answer in a program. Below the code of my original answer is the actual code of a working program.
For your code, I don't think the "phonebook"'s name and phone should be an array but should be a pointer to arrays of chars. That is because if you have a large program even if you give a size that is always bigger than the necessary size or working with a version of "c" that allows dynamic array allocation at runtime, you can run into the problem of running out of stack memory.
Nonetheless, this code below is an example and is for parsing just one line. In a real usage case, you would have to modify the code properly to use it in a loop. For the routines, you just look for the ":" location. If you found that then look for the null char(end of string) location. I did place comments in the code, thus, I am not going to explain much here.
Also, you should give consideration to letting pb be dynamic with calloc() and realloc(). Also, calloc() and realloc() do not always work. You can also, use malloc() but you have to inject the null char by yourself.
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
struct phonebook{
char * name;
char * phone;
};
int main(void) {
char * line = "John:789-654-3210";
char c;
// search for the :
struct phonebook pb[1];
int dotloc = -1;
int endloc = 0;
int recordIndex = 0;
// Find the dot first
// and then end line.
// This could be done in one loop
// But split into two
for ( int i = 0; ; i++) {
if( line[i] == ':' ) {
dotloc = i;
break;
}
if( line[i] == '\0' ) break;
}
// If found : then that is valid
if ( dotloc > -1 ){
for( int i = dotloc + 1; ; i++){
if( line[i] == '\0' ){
endloc = i;
break;
}
}
// Positioning
// If : is at pos, there is 5 char in the string
// add + for null char.
// If : is at 0 there isn't a char but when calloc still need one for the null char. Empty string.
pb[recordIndex].name = (char*) calloc(dotloc + 1, sizeof(char));
// If : is at 5 and end is at 10, there is only 4 char in between but add keep five because of end char.
pb[recordIndex].phone = (char*) calloc(endloc - dotloc, sizeof(char));
// Memory allocation fail.
// Do something else.
if( pb[recordIndex].name == NULL ) return 1;
if( pb[recordIndex].phone == NULL ) return 1;
// copy from line[0] to dotloc location as how many chars.
// if dotloc is 0, nothing will be copy.
// null char is already appended by calloc.
memcpy(pb[recordIndex].name, line, dotloc * sizeof(char));
// copy from the location of where dotloc is plus 1
// how many char is base on where endloc is - dotloc
// -1
// If endloc at 1 and dot loc is at 0(next to), nothing to be copy.
memcpy(pb[recordIndex].phone, &line[dotloc + 1], (endloc - dotloc - 1));
recordIndex++;
}
printf("%s\n", pb[0].name);
printf("%s", pb[0].phone);
// Sometimes you need to free memory properly.
// depend on which system you target or your use case.
free(pb[0].name);
free(pb[0].phone);
return 0;
}
I won't give much explanation into what each function in the program does, as the key point already mentioned above and that can take hours to write. This program below to demonstrate how to utilize my original answer.
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
struct phoneRecord{
char * name;
char * phone;
};
struct phoneBook{
struct phoneRecord * record;
int length;
int size;
};
struct phoneBook newBook(){
// change init_size to 1 for debugging
int init_size = 30;
static size_t recordSize = sizeof(struct phoneRecord);
struct phoneBook output;
output.record = (struct phoneRecord*) malloc( init_size * recordSize);
output.length = 0;
output.size = init_size;
return output;
}
void freeBook( struct phoneBook * pb){
for ( int i = 0; i < pb->length; i++ ){
free(pb->record[i].name);
free(pb->record[i].phone);
}
free(pb->record);
pb->record = NULL;
pb->length = 0;
pb->size = 0;
}
// 0 for success
// 1 for error
int increaseBookSize(struct phoneBook * pb){
if ( pb == NULL ) return 1;
static size_t recordSize = sizeof(struct phoneRecord);
const int newSize = pb->size * 2;
if ( newSize == 0 ) return 1;
struct phoneRecord * tempPointer = (struct phoneRecord*) realloc(pb->record, newSize * recordSize);
if ( tempPointer != NULL ) {
pb->record = tempPointer;
pb->size = newSize;
return 0;
}
return 1;
}
// Return - 1 for error.
// Return 0 for no record found or no dot.
// Return 1 for record found.
int getRecord( const char * line, struct phoneRecord * pr){
// Null check
if ( pr == NULL ) return -1;
int dotloc = -1;
int endloc = 0;
for ( int i = 0; ; i++) {
if( line[i] == ':' ) {
dotloc = i;
break;
}
if( line[i] == '\0' ) break;
}
if ( dotloc > -1 ){
for( int i = dotloc + 1; ; i++){
if( line[i] == '\0' ){
endloc = i;
break;
}
}
pr->name = (char*) calloc(dotloc + 1, sizeof(char));
pr->phone = (char*) calloc(endloc - dotloc, sizeof(char));
if( pr->name == NULL ) return -1;
if( pr->phone == NULL ) return -1;
memcpy(pr->name, line, dotloc * sizeof(char));
memcpy(pr->phone, &line[dotloc + 1], (endloc - dotloc - 1));
return 1;
}
return 0;
}
int main(void) {
struct phoneBook pb = newBook();
const char * fileName = "test.txt";
char * line = NULL;
FILE *fp;
size_t len = 0;
int recordReturnCode;
fp = fopen(fileName, "r");
if (fp == NULL){
printf("Couldn't open file %s.\n", fileName);
return 1;
}
while (getline(&line, &len, fp) != -1) {
if ( pb.length >= pb.size ) {
if ( increaseBookSize(&pb) != 0 ) {
printf("Something is wrong with getting more memory for the book. However, still print out what already got.\n");
break;
}
}
recordReturnCode = getRecord(line, &pb.record[pb.length]);
if ( recordReturnCode == 1 ) pb.length++;
if ( recordReturnCode == -1 ){
printf("Something is wrong with getting the record. Clean up and exit.\n");
freeBook(&pb);
free(line);
return 1;
}
}
free(line);
printf("Print phonebook size for debuging. Size: %d\n", pb.size);
printf("Read file '%s' and found %d records. Printing each record.\n\n", fileName, pb.length);
for ( int i = 0; i < pb.length; i++ ){
printf("Record: %d | Name: %s | Phone: %s", i, pb.record[i].name, pb.record[i].phone);
}
freeBook(&pb);
printf("\n\nChecking book after free. Length: %d, Size: %d", pb.length, pb.size);
if ( pb.record == NULL ) printf("\nPhonebook free properly, record is NULL.");
return 0;
}
test.txt content:
John:789-654-3210
Bill:852-123-4567
This is not a valid record
Amy:963-321-0000
AfterEmpty:123-456-789
:###-###-####
noNumber:
Kevin:123-123-1234

Printing top 10 recurring words in a file

Edited question:
Hi guys, my goal is to print the top 10 occurring words in a file, I have managed to get everything to work from reading the file to counting word occurrences and printing it, but when I implement my qsort I get a segfault. I looked over my pointers and they look okay to me, I would appreciate any feedback.
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <ctype.h>
#define MAX 51
struct words
{
char *ch;
int index;
struct words *pNext;
};
struct words* createWordCounter(char *ch)
{
struct words *pCounter = NULL;
pCounter = (struct words*)malloc(sizeof(char));
pCounter->ch = (char*)malloc(strlen(ch)+1);
strcpy(pCounter->ch, ch);
pCounter->index = 1;
pCounter->pNext = NULL;
return pCounter;
}
struct words *pStart = NULL;
char* removePunc(struct words* ch)
{
char *src = ch, *dst = ch;
while (*src)
{
if (ispunct((unsigned char)*src))
{
src++;
}
else if (isupper((unsigned char)*src))
{
*dst++ = tolower((unsigned char)*src);
src++;
}
else if (src == dst)
{
src++;
dst++;
}
else
{
*dst++ = *src++;
}
}
*dst = 0;
}
void addWord(char *word)
{
struct words *pCounter = NULL;
struct words *pLast = NULL;
if(pStart == NULL)
{
pStart = createWordCounter(word);
return;
}
pCounter = pStart;
while(pCounter != NULL)
{
if(strcmp(word, pCounter->ch) == 0)
{
++pCounter->index;
return;
}
pLast = pCounter;
pCounter = pCounter->pNext;
}
pLast->pNext = createWordCounter(word);
}
void printWord(struct words *pCounter)
{
printf("\n%-30s %5d\n", pCounter->ch, pCounter->index);
}
//sort
int compare (const void * a, const void * b){
struct words *A1 = (struct words *)a;
struct words *B1 = (struct words *)b;
return B1->index - A1->index;
/*
if ((A1->count - B1->count) > 0)
return -1;
else if ((A1->count - B2->count) < 0)
return 1;
else
return 0;
*/
}
int main(int argc, char * argv[])
{
struct words *pCounter = NULL;
char temp[MAX];
FILE *fpt;
if(argc == 2)
{
printf("File name is: %s\n",argv[1]);
fpt = fopen(argv[1], "r");
//fail test
if(fpt == NULL)
{
printf("cannot open file, exiting program...\n");
exit(0);
}
//get the data out of the file and insert in struct
int wordCounter = 0;
int i = 0;
int lines = 0;
while((fscanf(fpt, "%s ", &temp)) == 1)
{
removePunc(temp);
addWord(temp);
if(temp == ' ')
i++;
if(temp == '\n')
lines++;
wordCounter++;
}
/*
pCounter = pStart;
while(pCounter != NULL)
{
printWord(pCounter);
pCounter = pCounter->pNext;
}
*/
//sort
qsort(pCounter, wordCounter, sizeof(struct words), compare);
for(int j = 0; i < 10; i++)
{
printWord(pCounter);
}
}
fclose(fpt);
return 0;
}
First temp is already a pointer, so do not include '&' before it in fscanf. Second, don't skimp on buffer size (e.g. #define MAX 1024). Third, protect your array bounds with the field-width modifier and don't put trailing whitespace in your format-string.
Putting it altogether (presuming you use 1024 as MAX, you can use
fscanf(fpt, "1023%s", temp))
Well done on checking the return of fscanf during your read.
Adding to the things that have already been mentioned.
In createWordCounter(...)
pCounter = (struct words*)malloc(sizeof(char));
you are allocating memory for a char. Even though the pointer to a struct is the pointer to its first member, the first element of words is a pointer to a char. It is better to be careful and write
struct words *pCounter = malloc(sizeof *pCounter);
Also, be mindful of operator precedence.
In addWord(...) you have
++pCounter->index;
What that does is increment the pointer pCounter before accessing index. If you are trying to increment index, it should be
++(pCounter->index);
or
pCounter->index++;
I recommend striping your program down to its bare essentials and test each part one at a time systematically to narrow down the cause of your errors.
I think the main problem is the size of temp array when you try to using fscanf.
while((fscanf(fpt, "%s ", temp)) == 1)
When the length of one line is bigger than MAX, segmentation fault occur.
You can change your code like this
#define SCANF_LEN2(x) #x
#define SCANF_LEN(x) SCANF_LEN2(x)
//...
//your original code
//...
while((fscanf(fpt, "%"SCANF_LEN(MAX)"s ", temp)) == 1)
By the way, you should check
(1) compile warning about type
char* removePunc(struct words* ch)
should be char* removePunc(char *ch)
if(temp == ' ') should be if(temp[0] == ' ')
if(temp == '\n') should be if(temp[0] == '\n')
(2) malloc size
pCounter = (struct words*)malloc(sizeof(char)); should be pCounter = (struct words*)malloc(sizeof(struct words));
(3) remember free after using malloc

Parsing and data overwriting issues in C using custom strtok

I'm reading in a .csv file, which I then need to parse into tokens. I tried using strtok(), but that unfortunately cannot return null fields (which my data is fulll of). So I went with a home-made version of strtok that I found, strtok_single, which returns the correct values that I need.
The data is input into my array correctly; but there is something wrong because before the initilization loops finish, the data gets overwritten. I've tried print statements and analyzing the problem but I just can't figure out what's wrong. Any insight at all would be helpful.
Here is the homemade strtok function I'm using:
char* strtok_single(char* str, char const* delims) {
static char* src = NULL;
char* p, *ret = 0;
if (str != NULL)
src = str;
if (src == NULL)
return NULL;
if ((p = strpbrk(src, delims)) != NULL) {
*p = 0;
ret = src;
src = ++p;
}
return ret;
}
Here is my code:
int main() {
int numLines = 0;
int ch, i, j;
char tmp[1024];
char* field;
char line[1024];
FILE* fp = fopen("filename.csv", "r");
// count number of lines in file
while ((ch = fgetc(fp)) != EOF) {
if (ch == '\n')
numLines++;
}
fclose(fp);
// Allocate memory for each line in file
char*** activity = malloc(numLines * sizeof(char**));
for (i = 0; i < numLines; i++) {
activity[i] = malloc(42 * sizeof(char*));
for (j = 0; j < 42; j++) {
activity[i][j] = malloc(100 * sizeof(char));
}
}
// read activity file and initilize activity matrix
FILE* stream = fopen("filename.csv", "r");
i = 0;
while (fgets(line, 1024, stream)) {
j = 0;
int newlineLoc = strcspn(line, "\n");
line[newlineLoc] = ',';
strcpy(tmp, line);
field = strtok_single(tmp, ",");
while (field != NULL) {
for (j = 0; j < 42; j++) {
activity[i][j] = field;
field = strtok_single(NULL, ",");
// when I print activity[i][j] here, the values are correct
}
// when I print activity[i][j] here, the values are correct for the
// first iteration
// and then get overwritten by partial data from the next line
}
i++;
} // close while
fclose(stream);
// by the time I get to here my matrix is full of garbage
// some more code that prints the array and frees memory
} // close main
activity[i][j] = field;
When the loops finish, each activity[i][j] points to somewhere in tmp, which is overwritten in each loop. Instead, since you pre-allocate space in each activity[i][j], you should just copy the contents of the string to that:
strcpy(activity[i][j], field);
Being careful of buffer overflow (i.e. if field is more than 99 characters).
Also, the sizeof(char) is superfluous since it's always 1 by definition.
Your line "activity[i][j] = field;" is backwards - you want the pointer assigned to the malloc'd memory.

Resources