Structures not taking values - c

I'm having an issue with an assignment. The task is to read a string from a txt file and compare it to an array of pointers to structures. If the string already appears then increase the count of that struct by 1, if not found, insert the string into the array with count 1. The struct is defined:
struct wordfreq {
int count;
char *word;
}
Here is the code:
#include <stdio.h>
#include <stdlib.h>
struct wordfreq {
int count;
char *word;
};
typedef struct wordfreq wordfreq;
int mystrcmp(char *str1, char *str2);
int main(int argc, char *argv[])
{
int i, j, flag, current, spot;
char *temp, *temp2;
FILE *infile, *outfile;
wordfreq *wordsptr[1000];
if (argc != 3)
{
printf("Invalid number of arguments, exiting\n");
return 1;
}
else
{
infile = fopen(argv[1], "r");
outfile = fopen(argv[2], "w");
if (infile == NULL)
{
printf("Error opening input file, exiting\n");
return 2;
}
if (outfile == NULL)
{
printf("Error opening output file, exiting\n");
return 3;
}
}
current = 0;
flag = 0;
for (i = 0; i < 1000; i++)
wordsptr[i] = NULL;
temp = (char *)calloc(20,sizeof(char));
while (fgets(temp, 20, infile) != NULL)
{
flag = 0;
for (i = 0; i < 20; i++)
if (temp[i] == '\n')
temp[i] = '\0';
printf("%s %d\n", temp, current);
wordsptr[current] = (wordfreq *)malloc(sizeof(wordfreq));
wordsptr[current]->word = (char *)malloc(20*sizeof(char));
(*wordsptr[current]).word = temp;
(*wordsptr[current]).count = 1;
current++;
}
for (i = 0; i < current; i++)
printf("%d %s\n", (*wordsptr[i]).count, (*wordsptr[i]).word);
free(temp);
for (i = 0; i < 1000; i++)
{
wordsptr[i] = NULL;
free(wordsptr[i]);
}
if (infile != NULL)
fclose(infile);
if (outfile != NULL)
fclose(outfile);
return 0;
}
int mystrcmp(char *str1, char *str2)
{
int i;
for (i = 0; str1[i] != '\0' || str2[i] != '\0';i++)
if (str1[i] != str2[i])
return 1;
return 0;
}
A couple of stipulations:
1) Have to initialize all pointers to null
2) Have to use an array of pointers to structures
run:
./assign6 words.txt freq.txt
words.txt:
apple
orange
apple
orange
banana
banana
The output I'm receiving:
1 banana
1 banana
1 banana
1 banana
1 banana
1 banana
It's supposed to output the count of the string in the txt file and the string itself to the file specified by argv[2]. Please help!

You are assigning the address of temp, which is constantly updated with new values at every iteration, hence why you get the string of the last iteration in all structures here. This is caused by the following lines:
wordsptr[current]->word = (char *)malloc(20*sizeof(char));
(*wordsptr[current]).word = temp;
(Which it is worth mentioning that this is also a memory leak because you lose the pointer to the heap memory.)
You should instead use strcpy() or a similar method to copy the characters from temp to wordsptr[current]->word.

Related

Reading a file line-by-line into an array of strings in C

I'm trying to read the following file line by line into an array of strings where each line is an element of the array:
AATGC
ATGCC
GCCGT
CGTAC
GTACG
TACGT
ACGTA
CGTAC
GTACG
TACGA
ACGAA
My code is as follows:
void **get_genome(char *filename) {
FILE *file = fopen(filename, "r");
int c;
int line_count = 0;
int line_length = 0;
for (c = getc(file); c != EOF; c = getc(file)) {
if (c == '\n') line_count++;
else line_length++;
}
line_length /= line_count;
rewind(file);
char **genome = calloc(line_length * line_count, sizeof(char));
for (int i = 0; i < line_count; i++) {
genome[i] = calloc(line_length, sizeof(char));
fscanf(file, "%s\n", genome[i]);
}
printf("%d lines of %d length\n", line_count, line_length);
for (int i = 0; i < line_count; i++)
printf("%s\n", genome[i]);
}
However, for some reason I get garbage output for the first 2 elements of the array. The following is my output:
`NP��
�NP��
GCCGT
CGTAC
GTACG
TACGT
ACGTA
CGTAC
GTACG
TACGA
ACGAA
You seem to assume that all lines have the same line length. If such is the case, you still have some problems:
the memory for the row pointers is allocated incorrectly, it should be
char **genome = calloc(line_count, sizeof(char *));
or better and less error prone:
char **genome = calloc(line_count, sizeof(*genome));
the memory for each row should be one byte longer the the null terminator.
\n is the fscanf() format string matches any sequence of whitespace characters. It is redundant as %s skips those anyway.
it is safer to count items separated by white space to avoid miscounting the items if the file contains any blank characters.
you do not close file.
you do not return the genome at the end of the function
you do not check for errors.
Here is a modified version:
void **get_genome(const char *filename) {
FILE *file = fopen(filename, "r");
if (file == NULL)
return NULL;
int line_count = 1;
int item_count = 0;
int item_length = -1;
int length = 0;
int c;
while ((c = getc(file)) != EOF) {
if (isspace(c)) {
if (length == 0)
continue; // ignore subsequent whitespace
item_count++;
if (item_length < 0) {
item_length = length;
} else
if (item_length != length) {
printf("inconsistent item length on line %d\", line_count);
fclose(file);
return NULL;
}
length = 0;
} else {
length++;
}
}
if (length) {
printf("line %d truncated\n", line_count);
fclose(file);
return NULL;
}
rewind(file);
char **genome = calloc(item_count, sizeof(*genome));
if (genome == NULL) {
printf("out of memory\n");
fclose(file);
return NULL;
}
for (int i = 0; i < item_count; i++) {
genome[i] = calloc(item_length + 1, sizeof(*genome[i]));
if (genome[i] == NULL) {
while (i > 0) {
free(genome[i]);
}
free(genome);
printf("out of memory\n");
fclose(file);
return NULL;
}
fscanf(file, "%s", genome[i]);
}
fclose(file);
printf("%d items of %d length on %d lines\n",
item_count, item_length, line_count);
for (int i = 0; i < item_count; i++)
printf("%s\n", genome[i]);
return genome;
}
char **genome = calloc(line_length * line_count, sizeof(char));
must be
char **genome = calloc(line_count, sizeof(char*));
or more 'secure'
char **genome = calloc(line_count, sizeof(*genome));
in case you change the type of genome
else the allocated block if not enough long if you are in 64b because line_count is 5 rather than 8, so you write out of it with an undefined behavior
You also need to return genome at the end of the function
It was also possible to not count the number of lines and to use realloc to increment your array when reading the file
As I see the lines have the same length. Your function should inform the caller how many lines have been read. There is no need of reading the file twice. There is no need of calloc (which is more expensive function). Always check the result of the memory allocation functions.
Here is a bit different version of the function:
char **get_genome(char *filename, size_t *line_count) {
FILE *file = fopen(filename, "r");
int c;
size_t line_length = 0;
char **genome = NULL, **tmp;
*line_count = 0;
if(file)
{
while(1)
{
c = getc(file);
if( c == EOF || c == '\n') break;
line_length++;
}
rewind(file);
while(1)
{
char *line = malloc(line_length + 1);
if(line)
{
if(!fgets(line, line_length + 1, file))
{
free(line);
break;
}
line[line_length] = 0;
tmp = realloc(genome, (*line_count + 1) * sizeof(*genome));
if(tmp)
{
genome = tmp;
genome[*line_count] = line;
*line_count += 1;
}
else
{
// do some memory free magic
}
}
}
fclose(file);
}
return genome;
}

How to find words with capital letters in a char using c?

I'm trying to find all the words with capital letters in a string, but am unable to process my data structure. i seem to be able to print out fileContent, indicating that it is loading in successfully, but my second function is not working on the file.
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
char* loadFile(char* fileName)
{
FILE *inputFile;
inputFile = fopen(fileName, "r");
//finds the end of the file
fseek(inputFile, 0, SEEK_END);
//stores the size of the file
int size = ftell(inputFile);
//Sets the scan to the start of the file
fseek(inputFile, 0, SEEK_SET);
char *documentStore = (char*)malloc(size);
int i = 0, c;
while((c = fgetc(inputFile)) != EOF)
{
documentStore[i] = c;
i++;
}
return documentStore;
}
void countImportantWords(char* fileContent, char** importantWords, int* frequencyWords)
{
int uniqueWordCount = 0;
int lengthWordStore = 10;
int i = 0;
int recording = 0;
char wordBuffer[50];
int wordBufferCount = 0;
int isWordPresent = 0;
while(fileContent[i] != EOF)
{
//To allocate more memory incase the structure is full
if(uniqueWordCount == lengthWordStore)
{
lengthWordStore += 10;
char** newWordStore = realloc(importantWords, lengthWordStore * sizeof(char*));
int* newFrequencyStore = realloc(frequencyWords, sizeof(int));
importantWords = newWordStore;
frequencyWords = newFrequencyStore;
}
printf("%s", wordBuffer);
//Conditions to fill if its a word
if(fileContent[i] >= 'A' && fileContent[i] <= 'Z' && recording == 0)
{
wordBuffer[0] = fileContent[i];
recording = 1;
}else if(fileContent[i] >= 'a' && fileContent[i] <= 'z' && recording == 1)
{
//each if is to check if the end of word is reached. Any character that is non alphabetical is considered end of word
wordBufferCount += 1;
wordBuffer[wordBufferCount] = fileContent[i];
} else if (fileContent[i] >= 'A' && fileContent[i] <= 'Z' && recording == 1)
{
wordBufferCount += 1;
wordBuffer[wordBufferCount] = fileContent[i];
} else {
//Adding a terminating character so that it strcpy only copies until that point
wordBuffer[wordBufferCount + 1] = '\0';
recording = 0;
//check to see if that word is in the array already, and if it is, it will just increment the frequency
for(int j = 0; j < uniqueWordCount; j++){
if(strcmp(wordBuffer, importantWords[j]) == 0)
{
frequencyWords[j] += 1;
isWordPresent = 1;
}
}
//if its not present, it should assign it to the structure
if(isWordPresent == 0)
{
char* wordStore = (char*)malloc(wordBufferCount * sizeof(char));
strcpy(wordStore, wordBuffer);
uniqueWordCount += 1;
importantWords[uniqueWordCount] = wordStore;
frequencyWords[uniqueWordCount] = 1;
}
}
i++;
}
}
int main() {
char fileName[50];
char *fileContent;
char **importantWords = (char**)malloc(10*sizeof(char**));
int *frequencyWords = (int*)malloc(10*sizeof(int));
printf("Please input the full file path: ");
scanf("%s", fileName);
fileContent = loadFile(fileName);
countImportantWords(fileContent, importantWords, frequencyWords);
int i = 0;
while(importantWords[i] != '\0')
{
printf("%s %d", importantWords[i], frequencyWords[i]);
i++;
}
return 0;
}
I've put in the full file so you can see how the structure was created incase that it is the issue, but ideally what would happen is that the final loop would print out all the words that are important and they're frequency. Currently i'm getting exit code 11, which i'm not sure what it means, but may be worth mentioning. I'd really appreciate any help :)
You can simplify the process dramatically but utilising functions and learning to manage your memory. I wrote a short example which does not take punctuation into account. It just assumes every word is separated by a space, which you can customise to your discretion.
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>
char* readfile(char* filename){
char* data = NULL;
FILE* file = fopen(filename, "r");
if(file == NULL){
return NULL;
}
fseek(file, 0, SEEK_END);
long size = ftell(file)+1;
fseek(file, 0, SEEK_SET);
data = (char*)malloc(size);
if(data == NULL){
return NULL;
}
fgets(data, (int)size, file);
return data;
}
typedef struct uppercase_t{
char** word;
int count;
}uppercase;
void copy(uppercase* u,char* token){
size_t length = strlen(token);
u->word[u->count] = (char*)malloc(length+1);
if(u->word[u->count] == NULL){
return;
}
strcpy(u->word[u->count], token);
++u->count;
}
void createuppercasedata(uppercase* u, char* data){
const char delimeter[] = " ";
char* token = strtok(data, delimeter);
if(token == NULL){
return;
}
u->word = (char**)malloc(u->count+1);
if(u->word == NULL){
return;
}
if(isupper(token[0])){
copy(u,token);
}
while(token != NULL){
token = strtok(0, delimeter);
if(token != NULL)
if(isupper(token[0])) {
char** reallocated = (char**)realloc(u->word, u->count+1);
if(reallocated == NULL){
return;
}
u->word = reallocated;
copy(u, token);
}
}
}
void destroyuppercasedata(uppercase* u){
for(int index = 0; index < u->count; ++index){
free(u->word[index]);
}
free(u->word);
}
int main(){
char filename[] = "textfile";
char* data = readfile(filename);
if(data == NULL){
return -1;
}
uppercase u = {0};
createuppercasedata(&u, data);
printf("found %i uppercase words\n",u.count);
for(int index = 0; index < u.count; ++index){
printf("%s\n", u.word[index]);
}
destroyuppercasedata(&u);
free(data);
}
The code will allocate a new pointer for each uppercase and memory for the word to be copied too. It will free all the memory it allocated in the structure with destroyuppercasedata and it will free the initial data that was read from file. Error checking and memory management in C is really important. So utilise those properly.
This was the test file I used.
textfile
How many Uppercase words can Be Found In this text File the answer should be Seven
And this was the output to the terminal:
How
Uppercase
Be
Found
In
File
Seven

How to parse and arrange lines of a csv file based on matching word in C?

I have csv file with below format :
name,birthmonth,country,hobby
jack,jan,england,soccer
roben,july,germany,soccer
emma,dec,china,tennis
yannick,sep,france,music
alex,nov,england,cricket
thomas,apr,germany,tennis
mike,oct,netherlands,cycling
michelle,feb,france,poetry
yui,mar,japan,coding
feng,jun,china,reading
I want to parse this file using C, and put all the lines with same country name in a consecutive manner i.e shown below:
name,birthmonth,country,hobby
jack,jan,england,soccer
alex,nov,england,cricket
roben,july,germany,soccer
thomas,apr,germany,tennis
emma,dec,china,tennis
feng,jun,china,reading
yannick,sep,france,music
michelle,feb,france,poetry
mike,oct,netherlands,cycling
yui,mar,japan,coding
So far, I have tried this code below, however not able to match things properly and proceed further:
#include<stdio.h>
#include<stdlib.h>
#include<ctype.h>
#include<fcntl.h>
#include<string.h>
int main (int argc, char **argv) {
//int line;
char line[200];
char *inputFile = argv[1];
FILE *input_csv_file;
char a,b,c,d,e;
input_csv_file = fopen(inputFile, "rt");
if(input_csv_file ==0) {
printf("Can not open input file \n");
}
else {
//while((line = fgetc(input_csv_file)) != EOF) {
while(fgets(line, sizeof line, input_csv_file) != NULL) {
printf ("line = %s\n", line);
if(sscanf(line, "%s,%s,%s,%s,%s", a,b,c,d,e)) {
//if(sscanf(line, "%[^,], %[^,], %[^,], %[^,], %[^,]", a,b,c,d,e)) {
printf("d=%s\n",d);
}
}
}
return 0;
}
I am a newbie in C/C++. Any help would be much appreciated
Thanks.
I could write the code to get the required output. Below is the code:
#include<stdio.h>
#include<stdlib.h>
#include<ctype.h>
#include<fcntl.h>
#include<string.h>
int main(int argc, char ** argv)
{
struct filedata {
char nation[8];
char content[50];
};
char line[100];
char *inputFile = argv[1];
FILE *input_csv_file;
int iter = 0, c;
char * tok;
int count = 0;
char ch;
char country[] = "country";
char header_line[50];
input_csv_file = fopen(inputFile, "rt");
//count line numbers of the input csv
for(ch = getc(input_csv_file); ch!= EOF; ch=getc(input_csv_file))
if(ch == '\n')
count = count + 1;
fclose(input_csv_file);
count = count -1;
struct filedata * record[count];
input_csv_file = fopen(inputFile, "rt");
if(input_csv_file == 0)
{
printf("Can not open input file\n");
} else
{
while(fgets(line, sizeof line, input_csv_file) != NULL)
{
//printf("-- line = %s\n", line);
int s_line = sizeof line;
char dup_line[s_line];
strcpy(dup_line, line);
int h = 0;
int s_token;
tok = strtok(line, ",");
while(tok != NULL)
{
h++;
if(h == 3)
{
s_token = sizeof tok;
break;
}
tok = strtok(NULL, ",");
}
// skipping the line having column headers
if(compare_col(tok, country) == 0) {
strcpy(header_line, dup_line);
continue;
}
iter++;
c = iter - 1;
record[c] = (struct filedata*)malloc(sizeof(struct filedata));
strcpy(record[c]->nation, tok);
strcpy(record[c]->content, dup_line);
} //while
struct filedata * temp;
FILE * fptr;
fptr = fopen("nation_csv.txt", "w");
if(fptr == NULL)
{
printf("Error in opening the file to write\n");
exit(1);
}
// sorting the arr of struct nation wise
for(iter=1; iter < count; iter++)
for(c =0 ; c < count -1; c++) {
if(strcmp(record[c]->nation, record[c+1]->nation) > 0) {
temp = record[c];
record[c] = record[c+1];
record[c+1] = temp;
}
}
for(iter=0; iter < count; ++iter)
{
if(iter == 0) {
fprintf(fptr, "%s", header_line);
continue;
}
fprintf(fptr, "%s", record[iter]->content);
}
fclose(fptr);
}
fclose(input_csv_file);
}
int compare_col(char a[], char b[] )
{
int c = 0;
while(a[c] == b[c]) {
if(a[c] == '\0' || b[c] == '\0')
break;
c++;
}
if(a[c] == '\0' && b[c] == '\0')
return 0;
else
return -1;
}
Thanks for all your inputs. Any further inputs to make it better are much appreciated.
Thanks

fscanf specific digits from a file

So I got this file and i want to scanf() only the digits inside the first {} than the digits inside the second {} and so on.
I've managed to call just the digits from the file, but I don't know how to separate them into groups
this is the file:
{5, 2, 3}, {1,5}, { }, { }, {3}, { }, { }
Below is the code I use so far
void main()
{
int rc=0,num,size;
FILE* f = fopen("graph-file.txt","rt");
if (f == NULL)
{
printf("Failed to open the file\n");
}
size = fscanf(f,"%d",&num);
fseek(f,1,SEEK_CUR);
while(rc != EOF)
{
if( rc == 1)
{
printf("%d\n",num);
}
fseek(f,1,SEEK_CUR);
rc = fscanf(f,"%d",&num);
}
}
Your code as it is has some issues, for example the mode string is wrong "rt"? You only need to specify "b" for binary and that only affects the end of line character which can be a problem if the file is read/written on different platforms.
To achieve what you want there is no simple way, as #JonathanLeffler suggests in this comment you could use a json library json-c1 is a very easy to use one.
If you want to do it yourself, try this code that I did just write
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <ctype.h>
int
append_number(int size, int **arrays, int value)
{
void *pointer;
pointer = realloc(arrays[0], (++size + 1) * sizeof(**arrays));
if (pointer == NULL)
return 0;
arrays[0] = pointer;
arrays[0][size] = value;
return 1;
}
int
get_value(const char *input)
{
if (input == NULL)
return -1;
while ((*input != '\0') && (isspace((unsigned char) *input) != 0))
input++;
if (*input == '\0')
return -1;
return atoi(input);
}
int *
extract_arrays(char *array)
{
int value;
int *list;
list = malloc(sizeof(*list));
if (list == NULL)
return NULL;
list[0] = 0;
while (array != NULL)
{
char *delimiter;
delimiter = strchr(array, ',');
if (delimiter != NULL)
*delimiter = '\0';
value = get_value(array);
if (value > 0)
list[0] += append_number(list[0], &list, value);
if (delimiter != NULL)
array = delimiter + 1;
else
array = NULL;
}
return list;
}
void
print_array(int *list)
{
fprintf(stdout, "[");
for (int j = 1 ; j < list[0] ; ++j)
fprintf(stdout, "%d ", list[j]);
if (list[0] > 0)
fprintf(stdout, "%d", list[list[0]]);
fprintf(stdout, "]\n");
}
int **
parse_line(char *line, size_t *count)
{
char *open;
char *close;
char *next;
int **arrays; // Depends on the maximum size of an inner array
*count = 0;
arrays = NULL;
next = line;
while ((next != NULL) && ((open = strchr(next, '{')) != NULL))
{
close = strchr(open, '}');
if (close != NULL)
{
void *pointer;
char *values;
*close = '\0';
next = strchr(close + 1, ',');
values = open + 1;
pointer = realloc(arrays, (*count + 1) * sizeof(*arrays));
if (pointer == NULL)
goto error;
arrays = pointer;
arrays[(*count)++] = extract_arrays(values);
}
else
next = open + 1;
}
return arrays;
error:
for (size_t i = 0 ; i < *count ; ++i)
free(arrays[i]);
free(arrays);
*count = 0;
return NULL;
}
int main(void)
{
char line[100];
size_t count;
int **arrays;
FILE *file;
file = fopen("graph-file.txt", "r");
if (file == NULL)
return -1; // Failure openning the file
while (fgets(line, sizeof(line), file) != NULL)
{
arrays = parse_line(line, &count);
for (size_t i = 0 ; i < count ; ++i)
{
print_array(arrays[i]);
// DO something with it ...
free(arrays[i]);
}
free(arrays);
}
fclose(file);
return 0;
}
Of course, there are a lot of possible optimizations (specially the realloc() parts), but I leave that to you.
Above, the int ** pointer returned by parse_line() contains count arrays where the first element is the length of each array.
1I know that on most linux distributions it can be installed with the package manager, and I have been using it a lot recently for some web development related projects.
Arrays are probably what you're going to need to accomplish this task. Arrays allow you to have various amounts of digits that you can store what you read into. That's how you can separate the groupings. The next part will be how to change which part of the array you're looking at, which this link should also help with.
C Arrays Tutorial.
If the numbers that you're trying to read will only be single digit numbers, then you could ditch the fseek and fscanf functions and use getc instead. Just check each read for anything that's not a number '0'-'9'.
C getc
Those websites I linked also have a lot of other good tutorials on them for learning C\C++.
Good luck.
Edit: less condescending.

C Program Segmentation Fault main()

I am novice to C programming and I have written a code to a requirement specification but I am consistently getting Segmentation Fault and unable to proceed ahead.
If the file name is 'code.c' and it runs with an error of not passing the argument (filename). But if the filename is passed, we land in Segmentation Fault.
Any help/suggestions will be appreciated.
#include <stdio.h>
#include <stdlib.h>
#include <math.h>
#include <string.h>
struct _data
{
char *firstName;
char *lastName;
long number;
};
// SCAN FILE
int SCAN(FILE *(*stream))
{
*stream = fopen("inputFile.data", "r");
int ch = 0, lines = 0;
while (!feof(*stream))
{
ch = fgetc(*stream);
if (ch == '\n')
{
lines++;
}
}
return lines;
}
// LOAD FILE
struct _data *LOAD(FILE *stream, int size)
{
int i;
size_t chrCount;
char *text, *number, *firstName, *lastName;
struct _data *BlackBox;
if ((BlackBox = (struct _data*)calloc(size, sizeof(struct _data))) == NULL)
{
printf("ERROR - Could not allocate memory.\n");
exit(0);
}
rewind(stream);
for (i = 0; i < size; i++)
{
getline(&text, &chrCount, stream);
firstName = strtok(text, " ");
lastName = strtok(text, " ");
number = strtok(NULL, "\n");
// Allocate memory for name part of struct.
if ((BlackBox[i].firstName = (char*)calloc(strlen(firstName), sizeof(char))) == NULL)
{
printf("ERROR - Could not allocate memory.\n");
exit(0);
}
if ((BlackBox[i].lastName = (char*)calloc(strlen(lastName), sizeof(char))) == NULL)
{
printf("ERROR - Could not allocate memory.\n");
exit(0);
}
strcpy(BlackBox[i].firstName, firstName);
strcpy(BlackBox[i].lastName, lastName);
BlackBox[i].number = atol(number);
}
fclose(stream);
return BlackBox;
}
void SEARCH(struct _data *BlackBox, char *name, int size, int inputs)
{
int i;
int found = 0;
char *search = " ";
char *firstName;
char *lastName;
if (inputs == 2)
{
firstName = strtok(name, search);
lastName = strtok(NULL, search);
}
printf("*******************************************\n");
if (inputs == 2)
{
for (i = 0; i < size; i++)
{
if (!strcasecmp(firstName, BlackBox[i].firstName) && !strcasecmp(firstName, BlackBox[i].firstName))
{
printf("The name was found at the %d entry.\n", i);
found = 1;
break;
}
}
}
else
{
for (i = 0; i < size; i++)
{
if (!strcasecmp(firstName, BlackBox[i].firstName) || !strcasecmp(firstName, BlackBox[i].firstName))
{
printf("The name was found at the %d entry.\n", i);
found = 1;
break;
}
}
}
if (found == 0)
{
printf("The name was NOT found.\n");
}
printf("*******************************************\n");
}
// FREE MEMORY
void FREE(struct _data *BlackBox, int size)
{
int i;
for (i = 0; i < size; i++)
{
free(BlackBox[i].firstName);
free(BlackBox[i].lastName);
}
free(BlackBox);
BlackBox = NULL;
}
// MAIN
int main(int argv, char **argc)
{
int size;
FILE *stream;
struct _data *BlackBox;
// argv == 1 WORKS, Below message is printed.
if (argv == 1)
{
printf("*******************************************\n");
printf("* You must include a name to search for. *\n");
printf("*******************************************\n");
}
// argv == 2 DOES NOT WORK, Segmentation Fault.
if (argv == 2)
{
size = SCAN (&stream);
BlackBox = LOAD(stream, size);
SEARCH(BlackBox, argc[1], size, 1);
}
if (argv == 3)
{
size = SCAN(&stream);
BlackBox = LOAD(stream, size);
SEARCH(BlackBox, argc[2], size, 2);
}
return 0;
}
You have a problem in this code:
firstName = strtok(text, " ");
lastName = strtok(text, " ");
number = strtok(NULL, "\n");
...
BlackBox[i].number = atol(number);
The second strtok() call should pass NULL as its first argument. As it is, the third strtok() call is certain to return NULL because the first call modifies text in such a way that the second consumes the whole thing (when tokenizing again from the beginning, as it erroneously does). You do not test for that, however, and as a result, atol() attempts to dereference a null pointer.
Update:
Additionally, as #chqrlie and later #JamesWilkins observed, you do not allocate sufficient space for BlackBox[i].firstName and BlackBox[i].lastName, as you need room for the string terminators as well. This is an entirely separate problem that could also produce a segfault. I like #chqrlie's suggestion to switch to strdup(), but it would be sufficient to just increase each allocation by one unit.
Update 2:
Furthermore, you have an issue with this line:
getline(&text, &chrCount, stream);
You do not initialize variable text before the first call, so it contains a junk value. The function allocates a buffer only when its first argument points to a NULL pointer; otherwise it writes the line to the buffer pointed to by the pointer obtained by dereferencing the first argument. Writing to a random location in memory certainly produces undefined behavior, which in practice often manifests as a segfault.
Moreover, unless you can rely on no line of the file being longer than the first, you also need to free the text pointer at the end of each loop iteration AND reset its value to NULL, so that getline() allocates a fresh buffer on the next iteration. If you do not free it on each iteration, then you need instead to free it after the end of the loop; else you will leak memory.
Try this (though I'm using Visual Studio on Windows). I added code to check for a missing '\n' on the last line, and also allowed for a variable number of search terms. I also increased the memory allocation for strings by 1 to account for the null terminating character. I noticed you are using getline(const char*..., which I think is GNU (Linux?), so I change that to fgets() just so I could compile and test it in VS (so you can change it back if you like). I put in various null checks as well, to be safer.
#include <iostream>
using namespace std;
struct _data
{
char *firstName;
char *lastName;
long number;
};
// SCAN FILE
int SCAN(FILE *(*stream))
{
*stream = fopen("inputFile.data", "r");
if (*stream == NULL)
{
perror("Error opening file");
return 0;
}
char ch = 0, lines = 0, linesize = 0;
while ((ch = fgetc(*stream)) != EOF)
{
if (ch == '\n')
{
lines++;
linesize = 0;
}
else linesize++;
}
if (linesize > 0)
lines++; // (last line doesn't have '\n')
return lines;
}
// LOAD FILE
struct _data *LOAD(FILE *stream, int lineCount)
{
int i;
size_t chrCount = 256;
char text[256], *result, *number, *firstName, *lastName;
struct _data *BlackBox;
if ((BlackBox = (struct _data*)calloc(lineCount, sizeof(struct _data))) == NULL)
{
printf("ERROR - Could not allocate memory.\n");
exit(0);
}
else memset(BlackBox, 0, sizeof(struct _data) * lineCount); // (make sure all data members are null to begin)
rewind(stream);
for (i = 0; i < lineCount; i++)
{
result = fgets(text, chrCount, stream);
if (result == NULL)
break; // (EOF)
firstName = strtok(text, " ");
lastName = strtok(NULL, " ");
number = strtok(NULL, "\n");
// Allocate memory for name part of struct.
if ((BlackBox[i].firstName = (char*)calloc(strlen(firstName) + 1, sizeof(char))) == NULL)
{
printf("ERROR - Could not allocate memory.\n");
exit(0);
}
if ((BlackBox[i].lastName = (char*)calloc(strlen(lastName) + 1, sizeof(char))) == NULL)
{
printf("ERROR - Could not allocate memory.\n");
exit(0);
}
strcpy(BlackBox[i].firstName, firstName);
strcpy(BlackBox[i].lastName, lastName);
BlackBox[i].number = atol(number);
}
fclose(stream);
return BlackBox;
}
void SEARCH(struct _data *BlackBox, char **names, int lineCount, int inputs)
{
int i, l;
int found = 0;
printf("*******************************************\n");
for (i = 0; i < inputs; ++i)
{
for (l = 0; l < lineCount; ++l)
{
if (BlackBox[l].firstName != NULL && !_stricmp(names[i], BlackBox[l].firstName)
|| BlackBox[l].lastName != NULL && !_stricmp(names[i], BlackBox[l].lastName))
{
printf("The name was found on line %d.\n", 1 + l);
found = 1;
break;
}
}
if (found) break;
}
if (!found)
printf("The name was NOT found.\n");
printf("*******************************************\n");
}
// FREE MEMORY
void FREE(struct _data *BlackBox, int lineCount)
{
int i;
for (i = 0; i < lineCount; i++)
{
if (BlackBox[i].firstName != NULL)
free(BlackBox[i].firstName);
if (BlackBox[i].lastName != NULL)
free(BlackBox[i].lastName);
}
free(BlackBox);
}
// MAIN
int main(int argc, char **argv)
{
int lineCount;
FILE *stream;
struct _data *BlackBox;
// argc == 1 WORKS, Below message is printed.
if (argc == 1)
{
printf("*******************************************\n");
printf("* You must include a name to search for. *\n");
printf("*******************************************\n");
}
// argc == 2 DOES NOT WORK, Segmentation Fault.
if (argc > 1)
{
lineCount = SCAN(&stream);
if (lineCount > 0)
{
BlackBox = LOAD(stream, lineCount);
SEARCH(BlackBox, argv + 1, lineCount, argc - 1);
FREE(BlackBox, lineCount);
}
}
return 0;
}
Tested it on the command line, and it works.
The problem is the argv and argc. argc is supposed to be an int (think argument count), while argv is meant to be char**. You have them mixed up in your main.

Resources