Related
I am trying to solve a problem on Dynamic memory allocation by reading the input from a file by malloc(),free(),realloc(); i just need help to push the strings into an array from the file, without the commas . My test.txt file are as follows:
a,5,0
a,25,1
a,1,2
r,10,1,3
f,2
int i;
int count;
char line[256];
char *str[20];//to store the strings without commas
char ch[20];
int main (void)
{
FILE *stream;
if ( (stream = fopen ( "test.txt", "r" )) == NULL )
{ printf ("Cannot read the new file\n");
exit (1);
}
while(fgets(line, sizeof line, stream))
{
printf ("%s", line);
int length = strlen(line);
strcpy(ch,line);
for (i=0;i<length;i++)
{
if (ch[i] != ',')
{
printf ("%c", ch[i]);
}
}
}
//i++;
//FREE(x);
//FREE(y);
//FREE(z);
fclose (stream);
the str[] array should only store values like a520. (excluding the commas)
First of all DO NOT use global variables unless it is absolutely requires.
I am assuming you want str as array of pointers and str[0] stores first line, str[1] stores second line and so on.
For this:
int line_pos = 0; //stores line_number
int char_pos = 0; //stores position in str[line_pos]
while(fgets(line, sizeof(line), stream))
{
printf ("%s", line);
int length = strlen(line);
strcpy(ch,line);
str[line_pos] = calloc(length, sizeof(char)); //allocating memory
for (i=0;i<length;i++)
{
if (ch[i] != ',')
{
*(str[line_pos]+char_pos) = ch[i]; //setting value of str[line][pos]
char_pos++;
}
}
char_pos = 0;
line_pos++;
}
printf("%s", str[0]); //print first line without comma
Note that it only works for 20 lines (because you declared *str[20]) and then for 21st or later lines it leads to overflow and can cause variety of disasters. You can include:
if (line_pos >= 20)
break;
as a safety measure.
Note that slighty more memory is allocated for str(memory allocated = memory_required + number of comma). To prevent this you can set ch to text without comma:
for (i=0;i<length;i++)
{
int j = 0; //stores position in ch
if (line[i] != ',')
{
ch[j++] = line[i];
}
Then allocate memory for str[line_pos] like:
str[line_pos] = calloc(strlen(ch0, sizeof(char));
I am posed with a situation where my function does exactly what I want except handle higher amounts of input.
I initially thought to process each character one by one but was running into problems doing this. So fscanf not only does what I want it to do but it is essential in reading in only one line. I noticed, I cannot reallocate space for bigger array this way though. I have tried using format specifiers i.e. %*s to include a specific amount of buffer space before hand but this still does not work.
I have noticed also, I would have no way of knowing the size of the string I am reading in.
Here is my attempt and thoughts:
#define LINE_MAX 1000
char* getline(FILE* inputStream)
{
int capacity = LINE_MAX;
char* line = malloc(capacity * sizeof(char));
int ch;
/* if (sizeof(capacity) == sizeof(line)) { // Not a valid comparison? Too late?
capacity *= 2;
line = realloc(line, capacity * sizeof(line));
} */
if (fscanf(stream, "%[^\n]s", line) == 1) {
ch = fgetc(inputStream);
if (ch != '\n' && ch != EOF) {
fscanf(inputStream, "%*[^\n]");
fscanf(inputStream, "%*c");
}
free(line);
return line;
}
free(line);
return NULL;
}
I am new to memory allocation in general but I feel as though I had a good idea of what to do here. Turns out I was wrong.
Here is an example to read a line and store it in a Character array.
#include <stdio.h>
#include <stdlib.h>
int main(void) {
signed char *str;
int c;
int i;
int size = 10;
str = malloc(size*sizeof(char));
for(i=0;(c=getchar()) !='\n' && c != EOF;++i){
if( i == size){
size = 2*size;
str = realloc(str, size*sizeof(char));
if(str == NULL){
printf("Error Unable to Grow String! :(");
exit(-1);
}
}
str[i] = c;
}
if(i == size){
str = realloc(str, (size+1)*sizeof(char));
if(str == NULL){
printf("Error Unable to Grow String! :(");
exit(-1);
}
}
str[i] = '\0';
printf("My String : %s", str);
return 0;
}
The array is resized to twice it's original size if current array can't hold the characters read from input.
I am really new to C, and the reading files thing drives me crazy...
I want read a file including name, born place and phone number, etc. All separated by tab
The format might be like this:
Bob Jason Los Angeles 33333333
Alice Wong Washington DC 111-333-222
So I create a struct to record it.
typedef struct Person{
char name[20];
char address[30];
char phone[20];
} Person;
I tried many ways to read this file into struct but it failed.
I tired fread:
read_file = fopen("read.txt", "r");
Person temp;
fread(&temp, sizeof(Person), 100, read_file);
printf("%s %s %s \n", temp.name, temp.address, temp.phone);
But char string does not recorded into temp separated by tab, it read the whole file into temp.name and get weird output.
Then I tried fscanf and sscanf, those all not working for separating tab
fscanf(read_file, "%s %s %s", temp.name, temp.address, temp.phone);
Or
fscanf(read_file, "%s\t%s\t%s", temp.name, temp.address, temp.phone);
This separates the string by space, so I get Bob and Jason separately, while indeed, I need to get "Bob Jason" as one char string. And I did separate these format by tab when I created the text file.
Same for sscanf, I tried different ways many times...
Please help...
I suggest:
Use fgets to read the text line by line.
Use strtok to separate the contents of the line by using tab as the delimiter.
// Use an appropriate number for LINE_SIZE
#define LINE_SIZE 200
char line[LINE_SIZE];
if ( fgets(line, sizeof(line), read_file) == NULL )
{
// Deal with error.
}
Person temp;
char* token = strtok(line, "\t");
if ( token == NULL )
{
// Deal with error.
}
else
{
// Copy token at most the number of characters
// temp.name can hold. Similar logic applies to address
// and phone number.
temp.name[0] = '\0';
strncat(temp.name, token, sizeof(temp.name)-1);
}
token = strtok(NULL, "\t");
if ( token == NULL )
{
// Deal with error.
}
else
{
temp.address[0] = '\0';
strncat(temp.address, token, sizeof(temp.address)-1);
}
token = strtok(NULL, "\n");
if ( token == NULL )
{
// Deal with error.
}
else
{
temp.phone[0] = '\0';
strncat(temp.phone, token, sizeof(temp.phone)-1);
}
Update
Using a helper function, the code can be reduced in size. (Thanks #chux)
// The helper function.
void copyToken(char* destination,
char* source,
size_t maxLen;
char const* delimiter)
{
char* token = strtok(source, delimiter);
if ( token != NULL )
{
destination[0] = '\0';
strncat(destination, token, maxLen-1);
}
}
// Use an appropriate number for LINE_SIZE
#define LINE_SIZE 200
char line[LINE_SIZE];
if ( fgets(line, sizeof(line), read_file) == NULL )
{
// Deal with error.
}
Person temp;
copyToken(temp.name, line, sizeof(temp.name), "\t");
copyToken(temp.address, NULL, sizeof(temp.address), "\t");
copyToken(temp.phone, NULL, sizeof(temp.phone), "\n");
This is only for demonstration, there are better ways to initialize variables, but to illustrate your main question i.e. reading a file delimited by tabs, you can write a function something like this:
Assuming a strict field definition, and your struct definition you can get tokens using strtok().
//for a file with constant field definitions
void GetFileContents(char *file, PERSON *person)
{
char line[260];
FILE *fp;
char *buf=0;
char temp[80];
int i = -1;
fp = fopen(file, "r");
while(fgets(line, 260, fp))
{
i++;
buf = strtok(line, "\t\n");
if(buf) strcpy(person[i].name, buf);
buf = strtok(NULL, "\t\n");
if(buf) strcpy(person[i].address, buf);
buf = strtok(NULL, "\t\n");
if(buf) strcpy(person[i].phone, buf);
//Note: if you have more fields, add more strtok/strcpy sections
//Note: This method will ONLY work for consistent number of fields.
//If variable number of fields, suggest 2 dimensional string array.
}
fclose(fp);
}
Call it in main() like this:
int main(void)
{
//...
PERSON person[NUM_LINES], *pPerson; //NUM_LINES defined elsewhere
//and there are better ways
//this is just for illustration
pPerson = &person[0];//initialize pointer to person
GetFileContents(filename, pPerson); //call function to populate person.
//...
return 0;
}
First thing,
fread(&temp, sizeof(temp), 100, read_file);
will not work because the fields are not fixed width, so it will always read 20 characters for name 30 for address and so on, which is not always the correct thing to do.
You need to read one line at a time, and then parse the line, you can use any method you like to read a like, a simple one is by using fgets() like this
char line[100];
Person persons[100];
int index;
index = 0;
while (fgets(line, sizeof(line), read_file) != NULL)
{
persons[i++] = parseLineAndExtractPerson(line);
}
Now we need a function to parse the line and store the data in you Person struct instance
char *extractToken(const char *const line, char *buffer, size_t bufferLength)
{
char *pointer;
size_t length;
if ((line == NULL) || (buffer == NULL))
return NULL;
pointer = strpbrk(line, "\t");
if (pointer == NULL)
length = strlen(line);
else
length = pointer - line;
if (length >= bufferLength) /* truncate the string if it was too long */
length = bufferLength - 1;
buffer[length] = '\0';
memcpy(buffer, line, length);
return pointer + 1;
}
Person parseLineAndExtractPerson(const char *line)
{
Person person;
person.name[0] = '\0';
person.address[0] = '\0';
person.phone[0] = '\0';
line = extractToken(line, person.name, sizeof(person.name));
line = extractToken(line, person.address, sizeof(person.address));
line = extractToken(line, person.phone, sizeof(person.phone));
return person;
}
Here is a sample implementation of a loop to read at most 100 records
int main(void)
{
char line[100];
Person persons[100];
int index;
FILE *read_file;
read_file = fopen("/path/to/the/file.type", "r");
if (read_file == NULL)
return -1;
index = 0;
while ((index < 100) && (fgets(line, sizeof(line), read_file) != NULL))
{
size_t length;
/* remove the '\n' left by `fgets()'. */
length = strlen(line);
if ((length > 0) && (line[length - 1] == '\n'))
line[length - 1] = '\0';
persons[index++] = parseLineAndExtractPerson(line);
}
fclose(read_file);
while (--index >= 0)
printf("%s: %s, %s\n", persons[index].name, persons[index].address, persons[index].phone);
return 0;
}
Here is a complete program that does what I think you need
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
typedef struct Person{
char name[20];
char address[30];
char phone[20];
} Person;
char *extractToken(const char *const line, char *buffer, size_t bufferLength)
{
char *pointer;
size_t length;
if ((line == NULL) || (buffer == NULL))
return NULL;
pointer = strpbrk(line, "\t");
if (pointer == NULL)
length = strlen(line);
else
length = pointer - line;
if (length >= bufferLength) /* truncate the string if it was too long */
length = bufferLength - 1;
buffer[length] = '\0';
memcpy(buffer, line, length);
return pointer + 1;
}
Person parseLineAndExtractPerson(const char *line)
{
Person person;
person.name[0] = '\0';
person.address[0] = '\0';
person.phone[0] = '\0';
line = extractToken(line, person.name, sizeof(person.name));
line = extractToken(line, person.address, sizeof(person.address));
line = extractToken(line, person.phone, sizeof(person.phone));
return person;
}
int main(void)
{
char line[100];
Person persons[100];
int index;
FILE *read_file;
read_file = fopen("/home/iharob/data.dat", "r");
if (read_file == NULL)
return -1;
index = 0;
while (fgets(line, sizeof(line), read_file) != NULL)
{
size_t length;
length = strlen(line);
if (line[length - 1] == '\n')
line[length - 1] = '\0';
persons[index++] = parseLineAndExtractPerson(line);
}
fclose(read_file);
while (--index >= 0)
printf("%s: %s, %s\n", persons[index].name, persons[index].address, persons[index].phone);
return 0;
}
Parsing strings returned by fgets can be very annoying, especially when input is truncated. In fact, fgets leaves a lot to be desired. Did you get the correct string or was there more? Is there a newline at the end? For that matter, is the end 20 bytes away or 32768 bytes away? It would be nice if you didn't need to count that many bytes twice -- once with fgets and once with strlen, just to remove a newline that you didn't want.
Things like fscanf don't necessarily work as intended in this situation unless you have C99's "scanset" feature available, and then that will automatically add a null terminator, if you have enough room. The return value of any of the scanf family is your friend in determining whether success or failure occurred.
You can avoid the null terminator by using %NNc, where NN is the width, but if there's a \t in those NN bytes, then you need to separate it and move it to the next field, except that means bytes in the next field must be moved to the field after that one, and the 90th field will need its bytes moved to the 91st field... And hopefully you only need to do that once... Obviously that isn't actually a solution either.
Given those reasons, I feel it's easier just to read until you encounter one of the expected delimiters and let you decide the behavior of the function when the size specified is too small for a null terminator, yet large enough to fill your buffer. Anyway, here's the code. I think it's pretty straightforward:
/*
* Read a token.
*
* tok: The buffer used to store the token.
* max: The maximum number of characters to store in the buffer.
* delims: A string containing the individual delimiter bytes.
* fileptr: The file pointer to read the token from.
*
* Return value:
* - max: The buffer is full. In this case, the string _IS NOT_ null terminated.
* This may or may not be a problem: it's your choice.
* - (size_t)-1: An I/O error occurred before the last delimiter
* (just like with `fgets`, use `feof`).
* - any other value: The length of the token as `strlen` would return.
* In this case, the string _IS_ null terminated.
*/
size_t
read_token(char *restrict tok, size_t max, const char *restrict delims,
FILE *restrict fileptr)
{
int c;
size_t n;
for (n = 0; n < max && (c = getchar()) != EOF &&
strchr(delims, c) == NULL; ++n)
*tok++ = c;
if (c == EOF)
return (size_t)-1;
if (n == max)
return max;
*tok = 0;
return n;
}
Usage is pretty straightforward as well:
#include <stdio.h>
#include <stdlib.h>
typedef struct person {
char name[20];
char address[30];
char phone[20];
} Person;
int
main(void)
{
FILE *read_file;
Person temp;
size_t line_num;
size_t len;
int c;
int exit_status = EXIT_SUCCESS;
read_file = fopen("read.txt", "r");
if (read_file == NULL) {
fprintf(stderr, "Error opening read.txt\n");
return 1;
}
for (line_num = 0;; ++line_num) {
/*
* Used for detecting early EOF
* (e.g. the last line contains only a name).
*/
temp.name[0] = temp.phone[0] = 0;
len = read_token(temp.name, sizeof(temp.name), "\t",
read_file);
if (len == (size_t)-1)
break;
if (len == max) {
fprintf(stderr, "Skipping bad line %zu\n", line_num + 1);
while ((c = getchar()) != EOF && c != '\n')
; /* nothing */
continue;
}
len = read_token(temp.address, sizeof(temp.address), "\t",
read_file);
if (len == (size_t)-1)
break;
if (len == max) {
fprintf(stderr, "Skipping bad line %zu\n", line_num + 1);
while ((c = getchar()) != EOF && c != '\n')
; /* nothing */
continue;
}
len = read_token(temp.phone, sizeof(temp.phone), "\t",
read_file);
if (len == (size_t)-1)
break;
if (len == max) {
fprintf(stderr, "Skipping bad line %zu\n", line_num + 1);
while ((c = getchar()) != EOF && c != '\n')
; /* nothing */
continue;
}
// Do something with the input here. Example:
printf("Entry %zu:\n"
"\tName: %.*s\n"
"\tAddress: %.*s\n"
"\tPhone: %.*s\n\n",
line_num + 1,
(int)sizeof(temp.name), temp.name,
(int)sizeof(temp.address), temp.address,
(int)sizeof(temp.phone), temp.phone);
}
if (ferror(read_file)) {
fprintf(stderr, "error reading from file\n");
exit_status = EXIT_FAILURE;
}
else if (feof(read_file) && temp.phone[0] == 0 && temp.name[0] != 0) {
fprintf(stderr, "Unexpected end of file while reading entry %zu\n",
line_num + 1);
exit_status = EXIT_FAILURE;
}
//else feof(read_file) is still true, but we parsed a full entry/record
fclose(read_file);
return exit_status;
}
Notice how the exact same 8 lines of code appear in the read loop to handle the return value of read_token? Because of that, I think there's probably room for another function to call read_token and handle its return value, allowing main to simply call this "read_token handler", but I think the code above gives you the basic idea about how to work with read_token and how it can apply in your situation. You might change the behavior in some way, if you like, but the read_token function above would suit me rather well when working with delimited input like this (things would be a bit more complex when you add quoted fields into the mix, but not much more complex as far as I can tell). You can decide what happens with max being returned. I opted for it being considered an error, but you might think otherwise. You might even add an extra getchar when n == max and consider max being a successful return value and something like (size_t)-2 being the "token too large" error indicator instead.
I am really new to C, and the reading files thing drives me crazy...
I want read a file including name, born place and phone number, etc. All separated by tab
The format might be like this:
Bob Jason Los Angeles 33333333
Alice Wong Washington DC 111-333-222
So I create a struct to record it.
typedef struct Person{
char name[20];
char address[30];
char phone[20];
} Person;
I tried many ways to read this file into struct but it failed.
I tired fread:
read_file = fopen("read.txt", "r");
Person temp;
fread(&temp, sizeof(Person), 100, read_file);
printf("%s %s %s \n", temp.name, temp.address, temp.phone);
But char string does not recorded into temp separated by tab, it read the whole file into temp.name and get weird output.
Then I tried fscanf and sscanf, those all not working for separating tab
fscanf(read_file, "%s %s %s", temp.name, temp.address, temp.phone);
Or
fscanf(read_file, "%s\t%s\t%s", temp.name, temp.address, temp.phone);
This separates the string by space, so I get Bob and Jason separately, while indeed, I need to get "Bob Jason" as one char string. And I did separate these format by tab when I created the text file.
Same for sscanf, I tried different ways many times...
Please help...
I suggest:
Use fgets to read the text line by line.
Use strtok to separate the contents of the line by using tab as the delimiter.
// Use an appropriate number for LINE_SIZE
#define LINE_SIZE 200
char line[LINE_SIZE];
if ( fgets(line, sizeof(line), read_file) == NULL )
{
// Deal with error.
}
Person temp;
char* token = strtok(line, "\t");
if ( token == NULL )
{
// Deal with error.
}
else
{
// Copy token at most the number of characters
// temp.name can hold. Similar logic applies to address
// and phone number.
temp.name[0] = '\0';
strncat(temp.name, token, sizeof(temp.name)-1);
}
token = strtok(NULL, "\t");
if ( token == NULL )
{
// Deal with error.
}
else
{
temp.address[0] = '\0';
strncat(temp.address, token, sizeof(temp.address)-1);
}
token = strtok(NULL, "\n");
if ( token == NULL )
{
// Deal with error.
}
else
{
temp.phone[0] = '\0';
strncat(temp.phone, token, sizeof(temp.phone)-1);
}
Update
Using a helper function, the code can be reduced in size. (Thanks #chux)
// The helper function.
void copyToken(char* destination,
char* source,
size_t maxLen;
char const* delimiter)
{
char* token = strtok(source, delimiter);
if ( token != NULL )
{
destination[0] = '\0';
strncat(destination, token, maxLen-1);
}
}
// Use an appropriate number for LINE_SIZE
#define LINE_SIZE 200
char line[LINE_SIZE];
if ( fgets(line, sizeof(line), read_file) == NULL )
{
// Deal with error.
}
Person temp;
copyToken(temp.name, line, sizeof(temp.name), "\t");
copyToken(temp.address, NULL, sizeof(temp.address), "\t");
copyToken(temp.phone, NULL, sizeof(temp.phone), "\n");
This is only for demonstration, there are better ways to initialize variables, but to illustrate your main question i.e. reading a file delimited by tabs, you can write a function something like this:
Assuming a strict field definition, and your struct definition you can get tokens using strtok().
//for a file with constant field definitions
void GetFileContents(char *file, PERSON *person)
{
char line[260];
FILE *fp;
char *buf=0;
char temp[80];
int i = -1;
fp = fopen(file, "r");
while(fgets(line, 260, fp))
{
i++;
buf = strtok(line, "\t\n");
if(buf) strcpy(person[i].name, buf);
buf = strtok(NULL, "\t\n");
if(buf) strcpy(person[i].address, buf);
buf = strtok(NULL, "\t\n");
if(buf) strcpy(person[i].phone, buf);
//Note: if you have more fields, add more strtok/strcpy sections
//Note: This method will ONLY work for consistent number of fields.
//If variable number of fields, suggest 2 dimensional string array.
}
fclose(fp);
}
Call it in main() like this:
int main(void)
{
//...
PERSON person[NUM_LINES], *pPerson; //NUM_LINES defined elsewhere
//and there are better ways
//this is just for illustration
pPerson = &person[0];//initialize pointer to person
GetFileContents(filename, pPerson); //call function to populate person.
//...
return 0;
}
First thing,
fread(&temp, sizeof(temp), 100, read_file);
will not work because the fields are not fixed width, so it will always read 20 characters for name 30 for address and so on, which is not always the correct thing to do.
You need to read one line at a time, and then parse the line, you can use any method you like to read a like, a simple one is by using fgets() like this
char line[100];
Person persons[100];
int index;
index = 0;
while (fgets(line, sizeof(line), read_file) != NULL)
{
persons[i++] = parseLineAndExtractPerson(line);
}
Now we need a function to parse the line and store the data in you Person struct instance
char *extractToken(const char *const line, char *buffer, size_t bufferLength)
{
char *pointer;
size_t length;
if ((line == NULL) || (buffer == NULL))
return NULL;
pointer = strpbrk(line, "\t");
if (pointer == NULL)
length = strlen(line);
else
length = pointer - line;
if (length >= bufferLength) /* truncate the string if it was too long */
length = bufferLength - 1;
buffer[length] = '\0';
memcpy(buffer, line, length);
return pointer + 1;
}
Person parseLineAndExtractPerson(const char *line)
{
Person person;
person.name[0] = '\0';
person.address[0] = '\0';
person.phone[0] = '\0';
line = extractToken(line, person.name, sizeof(person.name));
line = extractToken(line, person.address, sizeof(person.address));
line = extractToken(line, person.phone, sizeof(person.phone));
return person;
}
Here is a sample implementation of a loop to read at most 100 records
int main(void)
{
char line[100];
Person persons[100];
int index;
FILE *read_file;
read_file = fopen("/path/to/the/file.type", "r");
if (read_file == NULL)
return -1;
index = 0;
while ((index < 100) && (fgets(line, sizeof(line), read_file) != NULL))
{
size_t length;
/* remove the '\n' left by `fgets()'. */
length = strlen(line);
if ((length > 0) && (line[length - 1] == '\n'))
line[length - 1] = '\0';
persons[index++] = parseLineAndExtractPerson(line);
}
fclose(read_file);
while (--index >= 0)
printf("%s: %s, %s\n", persons[index].name, persons[index].address, persons[index].phone);
return 0;
}
Here is a complete program that does what I think you need
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
typedef struct Person{
char name[20];
char address[30];
char phone[20];
} Person;
char *extractToken(const char *const line, char *buffer, size_t bufferLength)
{
char *pointer;
size_t length;
if ((line == NULL) || (buffer == NULL))
return NULL;
pointer = strpbrk(line, "\t");
if (pointer == NULL)
length = strlen(line);
else
length = pointer - line;
if (length >= bufferLength) /* truncate the string if it was too long */
length = bufferLength - 1;
buffer[length] = '\0';
memcpy(buffer, line, length);
return pointer + 1;
}
Person parseLineAndExtractPerson(const char *line)
{
Person person;
person.name[0] = '\0';
person.address[0] = '\0';
person.phone[0] = '\0';
line = extractToken(line, person.name, sizeof(person.name));
line = extractToken(line, person.address, sizeof(person.address));
line = extractToken(line, person.phone, sizeof(person.phone));
return person;
}
int main(void)
{
char line[100];
Person persons[100];
int index;
FILE *read_file;
read_file = fopen("/home/iharob/data.dat", "r");
if (read_file == NULL)
return -1;
index = 0;
while (fgets(line, sizeof(line), read_file) != NULL)
{
size_t length;
length = strlen(line);
if (line[length - 1] == '\n')
line[length - 1] = '\0';
persons[index++] = parseLineAndExtractPerson(line);
}
fclose(read_file);
while (--index >= 0)
printf("%s: %s, %s\n", persons[index].name, persons[index].address, persons[index].phone);
return 0;
}
Parsing strings returned by fgets can be very annoying, especially when input is truncated. In fact, fgets leaves a lot to be desired. Did you get the correct string or was there more? Is there a newline at the end? For that matter, is the end 20 bytes away or 32768 bytes away? It would be nice if you didn't need to count that many bytes twice -- once with fgets and once with strlen, just to remove a newline that you didn't want.
Things like fscanf don't necessarily work as intended in this situation unless you have C99's "scanset" feature available, and then that will automatically add a null terminator, if you have enough room. The return value of any of the scanf family is your friend in determining whether success or failure occurred.
You can avoid the null terminator by using %NNc, where NN is the width, but if there's a \t in those NN bytes, then you need to separate it and move it to the next field, except that means bytes in the next field must be moved to the field after that one, and the 90th field will need its bytes moved to the 91st field... And hopefully you only need to do that once... Obviously that isn't actually a solution either.
Given those reasons, I feel it's easier just to read until you encounter one of the expected delimiters and let you decide the behavior of the function when the size specified is too small for a null terminator, yet large enough to fill your buffer. Anyway, here's the code. I think it's pretty straightforward:
/*
* Read a token.
*
* tok: The buffer used to store the token.
* max: The maximum number of characters to store in the buffer.
* delims: A string containing the individual delimiter bytes.
* fileptr: The file pointer to read the token from.
*
* Return value:
* - max: The buffer is full. In this case, the string _IS NOT_ null terminated.
* This may or may not be a problem: it's your choice.
* - (size_t)-1: An I/O error occurred before the last delimiter
* (just like with `fgets`, use `feof`).
* - any other value: The length of the token as `strlen` would return.
* In this case, the string _IS_ null terminated.
*/
size_t
read_token(char *restrict tok, size_t max, const char *restrict delims,
FILE *restrict fileptr)
{
int c;
size_t n;
for (n = 0; n < max && (c = getchar()) != EOF &&
strchr(delims, c) == NULL; ++n)
*tok++ = c;
if (c == EOF)
return (size_t)-1;
if (n == max)
return max;
*tok = 0;
return n;
}
Usage is pretty straightforward as well:
#include <stdio.h>
#include <stdlib.h>
typedef struct person {
char name[20];
char address[30];
char phone[20];
} Person;
int
main(void)
{
FILE *read_file;
Person temp;
size_t line_num;
size_t len;
int c;
int exit_status = EXIT_SUCCESS;
read_file = fopen("read.txt", "r");
if (read_file == NULL) {
fprintf(stderr, "Error opening read.txt\n");
return 1;
}
for (line_num = 0;; ++line_num) {
/*
* Used for detecting early EOF
* (e.g. the last line contains only a name).
*/
temp.name[0] = temp.phone[0] = 0;
len = read_token(temp.name, sizeof(temp.name), "\t",
read_file);
if (len == (size_t)-1)
break;
if (len == max) {
fprintf(stderr, "Skipping bad line %zu\n", line_num + 1);
while ((c = getchar()) != EOF && c != '\n')
; /* nothing */
continue;
}
len = read_token(temp.address, sizeof(temp.address), "\t",
read_file);
if (len == (size_t)-1)
break;
if (len == max) {
fprintf(stderr, "Skipping bad line %zu\n", line_num + 1);
while ((c = getchar()) != EOF && c != '\n')
; /* nothing */
continue;
}
len = read_token(temp.phone, sizeof(temp.phone), "\t",
read_file);
if (len == (size_t)-1)
break;
if (len == max) {
fprintf(stderr, "Skipping bad line %zu\n", line_num + 1);
while ((c = getchar()) != EOF && c != '\n')
; /* nothing */
continue;
}
// Do something with the input here. Example:
printf("Entry %zu:\n"
"\tName: %.*s\n"
"\tAddress: %.*s\n"
"\tPhone: %.*s\n\n",
line_num + 1,
(int)sizeof(temp.name), temp.name,
(int)sizeof(temp.address), temp.address,
(int)sizeof(temp.phone), temp.phone);
}
if (ferror(read_file)) {
fprintf(stderr, "error reading from file\n");
exit_status = EXIT_FAILURE;
}
else if (feof(read_file) && temp.phone[0] == 0 && temp.name[0] != 0) {
fprintf(stderr, "Unexpected end of file while reading entry %zu\n",
line_num + 1);
exit_status = EXIT_FAILURE;
}
//else feof(read_file) is still true, but we parsed a full entry/record
fclose(read_file);
return exit_status;
}
Notice how the exact same 8 lines of code appear in the read loop to handle the return value of read_token? Because of that, I think there's probably room for another function to call read_token and handle its return value, allowing main to simply call this "read_token handler", but I think the code above gives you the basic idea about how to work with read_token and how it can apply in your situation. You might change the behavior in some way, if you like, but the read_token function above would suit me rather well when working with delimited input like this (things would be a bit more complex when you add quoted fields into the mix, but not much more complex as far as I can tell). You can decide what happens with max being returned. I opted for it being considered an error, but you might think otherwise. You might even add an extra getchar when n == max and consider max being a successful return value and something like (size_t)-2 being the "token too large" error indicator instead.
i have a certain txt file(for instance - dic.txt) in which words appear in this order:
hello - ola - hiya \n
chips - fries - frenchfries \n
I need to read the contents of the file into an array of string arrays:
for instance:
array[0] : [hello,ola,hiya]
array[1] : [chips,fries,frenchfries]
I was thinking of using strtok in order to split each line in the file into a string (after copying the entire file into a string and calculating the number of lines),but i could not figure how to split each line ("hello - ola - hiya \n") into the words,and storing each array into the array (an array of strings within an array).
I was considering using malloc in order to allocate memory for each line of words,and storing the pointer to the string's array into the array,but i will be glad to receive any suggestions.
The straightforward way to read lines from a file and then split them into tokens is to read lines with fgets and then use strtok to split each line into tokens:
int main(int argc, char *argv[])
{
// Check for arguments and file pointer omitted
FILE *f = fopen(argv[1], "r");
for (;;) {
char line[80];
char *token;
if (fgets(line, 80, f) == NULL) break;
token = strtok(line, " -\n");
while (token) {
// Do something with token, for example:
printf("'%s' ", token);
token = strtok(NULL, " -\n");
}
}
fclose(f);
return 0;
}
This approach is fine as long as all the lines in your file are shorter than 80 characters. It works for variable numbers of tokens per line.
You have mentioned the issue of handling memory for the lines. The example above assumes that the memory handling is done by the data structure for each word. (It's not part of the example, which just prints the tokens.)
You can malloc memory for each line, which is more flexible than a rigid character limit per line, but you'll end up with a lot of allocations. The benefit is that your words don't need extra memory, they can just be pointers into the lines, but you'll have to take care of properly allocating memory for the lines - and freeing it afterwards.
If you read the whole text file to a contiguous chunk of memory, you're basically done with memory storage, as long as you keep that chunk "alive" as long as your words live:
char *slurp(const char *filename, int *psize)
{
char *buffer;
int size;
FILE *f;
f = fopen(filename, "r");
if (f == NULL) return NULL;
fseek(f, 0, SEEK_END);
size = ftell(f);
fseek(f, 0, SEEK_SET);
buffer = malloc(size + 1);
if (buffer) {
if (fread(buffer, 1, size, f) < size) {
free(buffer);
} else {
buffer[size] = '\0';
if (psize) *psize = size;
}
}
fclose(f);
return buffer;
}
With that chunk of memory, you can first look for lines by looking for the next newline, and then use strtok as above:
int main(int argc, char *argv[])
{
char *buffer; // contiguous memory chunk
char *next; // pointer to next line or NULL for last line
buffer = slurp(argv[1], NULL);
if (buffer == NULL) return 0;
next = buffer;
while (next) {
char *token;
char *p = next;
// Find beginning of the next line,
// i.e. the char after the next newline
next = strchr(p, '\n');
if (next) {
*next = '\0'; // Null-terminate line
next = next + 1; // Advance past newline
}
token = strtok(p, " -\n");
while (token) {
// Do something with token, for example:
printf("'%s' ", token);
token = strtok(NULL, " -\n");
}
}
free(buffer); // ... and invalidate your words
return 0;
}
If you use fscan, you always copy the found tokens to a temporary buffer and when you store them away in your dictionary structure, you have to copy them again with strcpy. That's a lot of copying. Here, you read and allocate once and then work with pointers into the chunk. strtok null-terminates the tokens, so your chunk is a chain of C strings.
Reading the wholem file into memory is usually not a good solution, but in this case, where the file basically is the data, it makes sense.
(Note: All this discussion about memory does not affect the memory needed for your dictionary structure, the nodes in trees and lined lists or whatever. It is just about storing the strings proper.)
using fgets:
int eol(int c, FILE *stream) //given a char and the file, check if eol included
{
if (c == '\n')
return 1;
if (c == '\r') {
if ((c = getc(stream)) != '\n')
ungetc(c, stream);
return 1;
}
return 0;
}
int charsNumInLine(FILE *stream)
{
int position = ftell(stream);
int c, num_of_chars=0;
while ((c = getc(stream)) != EOF && !eol(c, stream))
num_of_chars++;
fseek(stream,position,SEEK_SET); //get file pointer to where it was before this function call
return num_of_chars;
}
void main()
{
//...
char *buffer;
int size;
while()
{
size=charsNumInLine(stream);
buffer = (char*)malloc( size*sizeof(char) );
fgets(buffer,sizeof(buffer),stream);
if (feof(stream) || ferror(stream) )
break;
// use strtok to separate words...
}
//...
}
another way is to use fscanf(file,"%s",buff)to read words and then use the above function eol to see when we get to a newline.