Related
I am trying to make a program in C, that reads a text file and replace \r\n with \n to the same file converting the line ending from DOS to UNIX. I use fgetc and treat the file as a binary file. Thanks in advance.
#include <stdio.h>
int main()
{
FILE *fptr = fopen("textfile.txt", "rb+");
if (fptr == NULL)
{
printf("erro ficheiro \n");
return 0;
}
while((ch = fgetc(fptr)) != EOF) {
if(ch == '\r') {
fprintf(fptr,"%c", '\n');
} else {
fprintf(fptr,"%c", ch);
}
}
fclose(fptr);
}
If we assume the file uses a single byte character set, we just need to ignore all the '\r' characters when converting a text file form DOS to UNIX.
We also assume that the size of the file is less than the highest unsigned integer.
The reason we do these assumptions, is to keep the example short.
Be aware that the example below overwrites the original file, as you asked. Normally you shouldn't do this, as you can lose the contents of the original file, if an error occurs.
#include <stdio.h>
#include <stdlib.h>
#include <sys/stat.h>
// Return a negative number on failure and 0 on success.
int main()
{
const char* filename = "textfile.txt";
// Get the file size. We assume the filesize is not bigger than UINT_MAX.
struct stat info;
if (stat(filename, &info) != 0)
return -1;
size_t filesize = (size_t)info.st_size;
// Allocate memory for reading the file
char* content = (char*)malloc(filesize);
if (content == NULL)
return -2;
// Open the file for reading
FILE* fptr = fopen(filename, "rb");
if (fptr == NULL)
return -3;
// Read the file and close it - we assume the filesize is not bigger than UINT_MAX.
size_t count = fread(content, filesize, 1, fptr);
fclose(fptr);
if (count != 1)
return -4;
// Remove all '\r' characters
size_t newsize = 0;
for (long i = 0; i < filesize; ++i) {
char ch = content[i];
if (ch != '\r') {
content[newsize] = ch;
++newsize;
}
}
// Test if we found any
if (newsize != filesize) {
// Open the file for writing and truncate it.
FILE* fptr = fopen(filename, "wb");
if (fptr == NULL)
return -5;
// Write the new output to the file. Note that if an error occurs,
// then we will lose the original contents of the file.
if (newsize > 0)
count = fwrite(content, newsize, 1, fptr);
fclose(fptr);
if (newsize > 0 && count != 1)
return -6;
}
// For a console application, we don't need to free the memory allocated
// with malloc(), but normally we should free it.
// Success
return 0;
} // main()
To only remove '\r' followed by '\n' replace the loop with this loop:
// Remove all '\r' characters followed by a '\n' character
size_t newsize = 0;
for (long i = 0; i < filesize; ++i) {
char ch = content[i];
char ch2 = (i < filesize - 1) ? content[i + 1] : 0;
if (ch == '\r' && ch2 == '\n') {
ch = '\n';
++i;
}
content[newsize++] = ch;
}
I recently started at university with C programming (beginner course), and now we are doing our final examination which is about a patients' database.
I'm required to read data from a text file to a struct array (size 10000). The file contains 2 string arrays (personal identification string (10 numbers seperated by a '-') and name string), 1 int array containing photo references and 1 integer containing the amount of photo references per patient. I have tried fscanf but the program just hangs whenever i try to read, when i use fgets, it reads the whole line and stores the integers from the photo reference array into my name array (middle one). I am wondering how I should go about doing this, I've spent days trying to figure out a solution but nothing seems to work. This is what my text file looks like:
123456-1234 Name Name [1, 2, 3, 4]
234567-2345 Name2 Name2 [1, 2]
345678-3456 Name3 Name3 []
And this is my write_to_file function which writes to the file when the program exits:
void write_to_file(Patient reg[], int *pNr_of_patients){
FILE *fp;
fp=fopen("file.txt","w");
if(*pNr_of_patients>0){
int i,j;
for(i=0;i<*pNr_of_patients;i++){
fprintf(fp,"%s\t%s\t[",reg[i].pers_nr,reg[i].name);
for(j=0;j<reg[i].nr_of_ref-1;j++){
fprintf(fp,"%d, ",reg[i].photo_ref[j]);
}
if(reg[i].photo_ref[j]==0){
fprintf(fp,"]");
}else{
fprintf(fp,"%d]",reg[i].photo_ref[j]);
}
fprintf(fp,"\n");
}
fclose(fp);
}
}
This is my read_from_file function, it's missing code for reading the int array values at the end:
Edit: I added a for loop to remove the characters starting at "[" from the name string, now i just need to know how to read the array values at the end into the struct's photo reference array.
void read_from_file(Patient reg[],int *pNr_of_patients){
FILE *fp;
fp=fopen("file.txt","r");
if(fp!=NULL){
reg[*pNr_of_patients].nr_of_ref=0;
int i=0, pos;
while(fgets(reg[*pNr_of_patients].pers_nr,13,fp)!=NULL){
reg[*pNr_of_patients].pers_nr[strlen(reg[*pNr_of_patients].pers_nr)-1]='\0';
fgets(reg[*pNr_of_patients].name,31,fp);
reg[*pNr_of_patients].name[strlen(reg[*pNr_of_patients].name)-1]='\0';
for(pos=0;pos<30;pos++){
if(reg[*pNr_of_patients].name[pos]=='['){
reg[*pNr_of_patients].name[pos]='\0';
}
}
(*pNr_of_patients)++;
}
fclose(fp);
}else{
printf("File does not exist\n");
}
}
This is what my Patient struct looks like:
struct patient{
char pers_nr[12], name[30];
int photo_ref[10], nr_of_ref;
};
typedef struct patient Patient;
Calling read_from_file in main:
int main(void){
Patient patient_register[10000];
int nr_of_patients=0;
read_from_file(patient_register,&nr_of_patients);
database_management(patient_register,&nr_of_patients); //this is where I fill all the data into the array before writing to the file at the end
write_to_file(patient_register,&nr_of_patients);
return 0;
}
I think that scanning input is one of the hardest in C. That's why libraries like cs50 exists, to ease up reading input for new C users. Anyway, I constructed my solution, but I redesigned your function.
The first solution reads a single Patient from a line. It does not use sscanf the only standard call that set's errno is to strtol, which is used to convert up numbers.
The second function uses sscanf and some crazy format string construction to stay safe of buffer overflow.
It all brings down at to how the input stream is constructed and how much you trust it.
#include <stdio.h>
#include <assert.h>
#include <stddef.h>
#include <string.h>
#include <ctype.h>
#include <errno.h>
#include <stdlib.h>
#include <limits.h>
struct patient{
char pers_nr[12];
char name[30];
int photo_ref[10];
size_t nr_of_ref;
};
typedef struct patient Patient;
int patient_read_from_line_1(const char line[], Patient *p)
{
assert(line != NULL);
assert(p != NULL);
// check the first 12 characters ----------
// first 6 chars must be numbers
for (int i = 0; i < 6; ++i) {
if (!isdigit(line[i])) {
return -__LINE__;
}
}
// followed by a single '-'
if (line[6] != '-') {
return -__LINE__;
}
// followed by 4 numbers
for (int i = 7; i < 7 + 4; ++i) {
if (!isdigit(line[i])) {
return -__LINE__;
}
}
// followed by a space
if (line[7 + 4] != ' ') {
return -__LINE__;
}
// read up first field ---------------------
// cool first field checks out
memcpy(p->pers_nr, line, 11);
p->pers_nr[11] = '\0';
line += 12;
// let's omit spaces
while (line[0] == ' ') {
line++;
}
// read up second field --------------------------
// now we should read a two strings separated by a space
// so we should read up until a second space
if (!isalpha(*line)) {
return -__LINE__;
}
const char *pnt_first_space = strchr(line, ' ');
if (pnt_first_space == NULL) {
return -__LINE__;
}
const char *pnt_another_space = strchr(pnt_first_space + 1, ' ');
if (pnt_another_space == NULL) {
return -__LINE__;
}
const size_t name_to_read_length = pnt_another_space - line;
if (name_to_read_length > sizeof(p->name)) {
return -__LINE__;
}
memcpy(p->name, line, name_to_read_length);
p->name[name_to_read_length] = '\0';
// buh two fields done, now the array
line += name_to_read_length;
// let's omit the spaces
while (line[0] == ' ') {
line++;
}
// read up array -----------------------------------
// array
if (line[0] != '[') {
return -__LINE__;
}
line++;
for (size_t numscnt = 0;; ++numscnt) {
if (numscnt >= sizeof(p->photo_ref)/sizeof(*p->photo_ref)) {
return -__LINE__;
}
char *pnt;
errno = 0;
long num = strtol(line, &pnt, 10);
if (errno) {
return -__LINE__;
}
if (!(INT_MIN < num && num < INT_MAX)) {
return -__LINE__;
}
p->photo_ref[numscnt] = num;
line = pnt;
// omit spaces
while (*line == ' ') line++;
// now we should get a comma
if (line[0] != ',') {
// if don't get a comma, we need to get a ]
if (line[0] == ']') {
// cool
++line;
// but remember to save the count
p->nr_of_ref = numscnt + 1;
// cool
break;
}
return -__LINE__;
}
++line;
// omit spaces
while (*line == ' ') line++;
// start again
}
// this needs to be end of line or newline
if (line[0] != '\0' && line[0] != '\n') {
return -__LINE__;
}
// success!
return 0;
}
// ok, ok, ok, let's use sscanf
int patient_read_from_line_2(const char line[], Patient *p)
{
assert(line != NULL);
assert(p != NULL);
int ret;
int pos;
// read up first fiedl and half of the second ------------------
ret = sscanf(line, "%12s %30[^ ] %n", p->pers_nr, p->name, &pos);
if (ret != 2) {
return -__LINE__;
}
line += pos;
// read up another half of the second field -------------------
const size_t cur_name_len = strlen(p->name);
p->name[cur_name_len] = ' ';
char tmp[20];
ret = snprintf(tmp, 20, "%%%d[^ ] [%%n", (int)(sizeof(p->name) - cur_name_len - 1));
if (ret < 0) {
return -__LINE__;
}
ret = sscanf(line, tmp, &p->name[cur_name_len + 1], &pos);
if (ret != 1) {
return -__LINE__;
}
line += pos;
// read up array *sigh* -------------------------------------------
for (p->nr_of_ref = 0;; ++p->nr_of_ref) {
if (p->nr_of_ref >= sizeof(p->photo_ref)/sizeof(*p->photo_ref)) {
return -__LINE__;
}
ret = sscanf(line, " %d%1s%n", &p->photo_ref[p->nr_of_ref], tmp, &pos);
if (ret == 0) {
// hm...
if (line[0] == ']') {
// ach all ok, empty numbers list;
line++;
p->nr_of_ref++;
break;
}
return -__LINE__;
}
if (ret != 2) {
return -__LINE__;
}
line += pos;
if (tmp[0] != ',') {
if (tmp[0] == ']') {
// whoa! success
p->nr_of_ref++;
// cool
break;
}
return -__LINE__;
}
}
// so what's left? - EOF or newline
if (line[0] != '\0' && line[0] != '\n') {
return -__LINE__;
}
// success!
return 0;
}
long patient_read_from_file(FILE *fp, Patient patients[], size_t patients_len)
{
size_t patients_cnt = 0;
char line[256];
// for each line in file
while (fgets(line, sizeof(line), fp) != NULL) {
const int ret = patient_read_from_line_2(line, &patients[patients_cnt]);
if (ret < 0) {
// hanle reading error
return ret;
}
patients_cnt++;
if (patients_cnt > patients_len) {
// no more memory in patients left
return -__LINE__;
}
}
return patients_cnt;
}
void patient_fprintln(FILE *f, const Patient *p)
{
fprintf(f, "%s %s [", p->pers_nr, p->name);
for (size_t i = 0; i < p->nr_of_ref; ++i) {
fprintf(f, "%d", p->photo_ref[i]);
if (i + 1 != p->nr_of_ref) {
fprintf(f, ",");
}
}
fprintf(f, "]\n");
}
int main()
{
FILE *fp;
fp = stdin; // fopen("file.txt","r");
if (fp == NULL) {
return -__LINE__;
}
Patient patients[3];
const long patients_cnt = patient_read_from_file(fp, patients, sizeof(patients)/sizeof(*patients));
if (patients_cnt < 0) {
fprintf(stderr, "patient_read_from_file error %ld\n", patients_cnt);
return patients_cnt;
}
fclose(fp);
printf("Readed %d patients:\n", patients_cnt);
for (size_t i = 0; i < patients_cnt; ++i) {
patient_fprintln(stdout, &patients[i]);
}
return 0;
}
Live version available at onlinedbg.
This can be simplified for 100%. This has bugs for 100%. It is just to show what methods (strtol, memcpy, sscanf, isdigit, isalpha) are sometimes used by people to read from input. Also I specify length modifier to scanf (sscanf(..., "%12s") to handle overflows (hopefully). Try to always check return values from scanf and other standard functions (maybe checking snprintf return value is a little too much, but hey, let's be consistent). Be vary, that on some platforms the %n scanf modifier happens not to work. Also this can be build up to use dynamic allocation using malloc, realloc and free, both on line reading (basically it is equal to writing custom version of GNU getline), reading strings from input, reading int's array from input and dynamic allocations of patients.
This was meant as a comment but got too long, so I type it here.
read_from_file() appears overly complex. You might consider revisiting fscanf, reading the photo references as a whole string and then parsing into integers which you can assign to the photo_ref array. (While the code below might compile, I haven't verified that it works. It's just an idea of how one might proceed.)
void read_from_file (Patient reg[], int *pNr_of_patients)
{
FILE *fp;
fp = fopen ("file.txt", "r");
if (fp != NULL)
{
int n;
int i = 0; // position in photo_ref
char refs[30];
*pNr_of_patients = 0;
while (EOF !=
(n =
fscanf (fp, "%s %[^[]%[^]]]", reg[*pNr_of_patients].pers_nr,
reg[*pNr_of_patients].name, refs)))
{
// btw, reg[*pNr_of_patients].name may contain terminating blanks. right trim it. that's easy enough.
if (n > 2)
{ /* found photo refs.Now split the string into integers */
char *s = refs + 1; //skip '['
char *p;
while (*s && i<10){ // scan for the integers, 10 of them
while (*s && *s == ' ')
s++; // skip blanks
p = s; // mark start of number
while (*p && *p != ',')
p++;
if (*p == ',')
*p = 0;
reg[*pNr_of_patients].photo_ref[i++] = atoi (s); //tip: use strtol(3), verify that `i' isnt larger than size of the array
s = p + 1; // skip ','. Must Do: verify that `s' hasnt yet moved past the end of `ref'!!
}
}
(*pNr_of_patients)++;
}
fclose (fp);
}
else
{
printf ("File does not exist\n");
}
}
There are some good answers already, but most of them try to use a single method to parse all elements of the line. I would read whole lines into a buffer first, then use sscanf() to parse the patient number and name, but use strtok() to split the array into its individual components:
void read_from_file(Patient reg[], int *pNr_of_patients) {
FILE *fp = fopen("file.txt", "r");
if (!fp) {
fprintf(stderr, "Error opening file: %s\n", strerror(errno));
*pNr_of_patients = 0;
return;
}
char line[1024];
int i = 0;
while (fgets(line, sizeof line, fp)) {
int offset = 0;
int refs = 0;
sscanf(line, "%11s %29[^[] [%n", ®[i].pers_nr, ®[i].name, &offset);
for (char *tok = strtok(line + offset, ","); tok && refs < 10; tok = strtok(NULL, ",")) {
if (*tok != ']')
reg[i].photo_ref[refs++] = atoi(tok);
}
reg[i].nr_of_ref = refs;
i++;
}
*pNr_of_patients = i;
}
Divide and Conquer
Break this down into steps. Make a function that populates 1 Patient.
The below is untested code. Consider it a starting point. The deign goal is to make a function that reads 1 line into 1 Patient.
Read in 1 entire line
// return 1: success, 0: failure EOF:end-of-file
int read_once_from_file(FILE *stream, Patient *pat_ptr) {
Patient pat = { 0 };
char buffer[100 + 30*13];
if (fgets(buffer, sizeof buffer, stream) == NULL) {
return EOF;
}
Parse the first part. Use "%n" which records the parsing offset. Use width limits on string input.
int n = 0;
if (sscanf(buffer, " %11[^\t] %29[^\t] [ %n", pat.pers_nr, pat.name) != 2) {
return 0; // improper formatted input
}
char *p = buffer + n;
Now look for ']' and photo_ref
if (*p != ']') {
for (pat.nr_of_ref=0; ; pat.nr_of_ref++) {
if (sscanf(p, "%d %n", &pat.photo_ref[i], &n) != 1) {
return 0; // improper formatted input
}
p += n;
if (*p == ']') {
pat.nr_of_ref++;
break;
}
if (*p != ',' || pat.nr_of_ref + 1 == 10) {
return 0; // improper formatted input
}
p++;
}
}
Save result
*pat_ptr = pat;
return 1;
}
Call read_once_from_file() as needed
void read_from_file(Patient reg[],int *pNr_of_patients){
*pNr_of_patients = 0;
FILE *fp = fopen("file.txt","r");
if(fp){
for (int i = 0; i<10000; i++) {
int count = read_once_from_file(fp, ®[i]);
if (count == EOF) {
break;
}
if (count != 1) {
// error
fprintf(stderr, "Input error\n");
break;
}
}
*pNr_of_patients = i;
fclose(fp);
}
}
My goal is to implement a function that calculates the number of lines in a file. And empty file is considered to have no lines. If the last line of the given file is not empty, it should be counted as a line despite not ending with a newline character.
I've come up with the following code:
int linecount(const char *filename)
{
FILE *f = fopen(filename, "r");
if(!f)
return -1;
int lines = 0;
int c = 0;
int n = 0;
while((c = fgetc(f)) != EOF){
if(c == '\n')
lines++;
n++;
}
if(n==0)
return 0; //return 0 if the file is empty
if(c!='\n' && !isspace(c))
lines++; //count the last line if it's not empty
fclose(f);
return lines;
}
However, even after playing with it for over an hour I can't figure out why its return value lines is one too large in some cases...
You were close, here how you could do it:
int linecount(const char *filename) {
FILE *f = fopen(filename, "r");
if (!f)
return -1;
int lines = 0;
int c = 0;
int n = 0;
int read_line = 0;
while ((c = fgetc(f)) != EOF) {
read_line = 1;
if (c == '\n') {
lines++;
read_line = 0;
}
n++;
}
if (n == 0)
return 0; //return 0 if the file is empty
if(read_line)
lines++;
fclose(f);
return lines;
}
The idea is that we want to know if we started reading a line AND if we met a newline, at end of this line. So, we use another variable, called read_line and we use it as a flag.
We set it to 1 (true) if we just started reading a line and we set it to 0 (false) if we just met a newline (end of the line).
Now, if we have something like:
1[newline]
2[newline]
3
we will be OK, since we need to check if read_line after we read the file. Is so, we have to increment our line counter by one.
This is also OK:
1[newline]
2[newline]
3[newline]
since we saw three newlines and the read_line is 0 after we read the file.
Same goes for this case:
1[newline]
2[newline]
3[newline]
[nothing here]
since our flag is going to be equal to 0 after reading the file, since the 3rd newline should set it to 0 and we never actually enter the 4th line in our loop, since there is nothing to read.
With your previous implementation, as stated in the comments, this line:
if(c!='\n' && !isspace(c))
would be executed with c being equal to EOF.
Or you could just use fgets() and you are done. Check the example:
#include <stdio.h>
#include <string.h>
#define bufSize 1024
int main(int argc, char *argv[])
{
FILE *fp;
char buf[bufSize];
if ((fp = fopen("test.txt", "rb")) == NULL)
{ /* Open source file. */
perror("fopen source-file");
return 1;
}
int lines = 0;
while (fgets(buf, sizeof(buf), fp) != NULL)
{ /* While we don't reach the end of source. */
/* Read characters from source file to fill buffer. */
/* fgets will stop when it finds a newline. */
lines++;
}
printf("lines = %d\n", lines);
fclose(fp);
return 0;
}
Modify sample
int linecount(const char *filename)
{
FILE *f = fopen(filename, "r");
if(!f)
return -1;
int lines = 0;
int c = 0;
int flag = 1;
while((c = fgetc(f)) != EOF){
if(flag = (c == '\n'))
lines++;
}
if(!flag)
lines++; //count the last line if it's not empty
fclose(f);
return lines;
}
A simple solution can be
int linecount(const char *filename)
{
FILE *stream;
char *line = NULL;
size_t len = 0;
ssize_t read;
int numOfLines = 0;
stream = fopen(filename, "r");
if (stream == NULL)
exit(EXIT_FAILURE);
while ((read = getline(&line, &len, stream)) != -1) {
numOfLines++;
}
free(line);
fclose(stream);
return numOfLines;
}
So what I'm trying to do is to count blank lines, which means not only just containing '\n'but space and tab symbols as well. Any help is appreciated! :)
char line[300];
int emptyline = 0;
FILE *fp;
fp = fopen("test.txt", "r");
if(fp == NULL)
{
perror("Error while opening the file. \n");
system("pause");
}
else
{
while (fgets(line, sizeof line, fp))
{
int i = 0;
if (line[i] != '\n' && line[i] != '\t' && line[i] != ' ')
{
i++;
}
emptyline++;
}
printf("\n The number of empty lines is: %d\n", emptyline);
}
fclose(fp);
You should try and get your code right when posting on SO. You are incrementing both i and emptyline but the use el in your call to printf(). And then I don't know what that is supposed to be in your code where it has }ine. Please, at least make an effort.
For starters, you are incrementing emptyline for every line because it is outside of your if statement.
Second, you need to test the entire line to see if it contains any character that is not a whitespace character. Only if that is true should you increment emptyline.
int IsEmptyLine(char *line)
{
while (*line)
{
if (!isspace(*line++))
return 0;
}
return 1;
}
Before getting into the line loop increment the emptyLine counter and if an non whitespace character is encountred decrement the emptyLine counter then break the loop.
#include <stdio.h>
#include <string.h>
int getEmptyLines(const char *fileName)
{
char line[300];
int emptyLine = 0;
FILE *fp = fopen("text.txt", "r");
if (fp == NULL) {
printf("Error: Could not open specified file!\n");
return -1;
}
else {
while(fgets(line, 300, fp)) {
int i = 0;
int len = strlen(line);
emptyLine++;
for (i = 0; i < len; i++) {
if (line[i] != '\n' && line[i] != '\t' && line[i] != ' ') {
emptyLine--;
break;
}
}
}
return emptyLine;
}
}
int main(void)
{
const char fileName[] = "text.txt";
int emptyLines = getEmptyLines(fileName);
if (emptyLines >= 0) {
printf("The number of empty lines is %d", emptyLines);
}
return 0;
}
You are incrementing emptyline on every iteration, so you should wrap it in an else block.
Let's think of this problem logically, and let's use functions to make it clear what is going on.
First, we want to detect lines that only consist of whitespace. So let's create a function to do that.
bool StringIsOnlyWhitespace(const char * line) {
int i;
for (i=0; line[i] != '\0'; ++i)
if (!isspace(line[i]))
return false;
return true;
}
Now that we have a test function, let's build a loop around it.
while (fgets(line, sizeof line, fp)) {
if (StringIsOnlyWhitespace(line))
emptyline++;
}
printf("\n The number of empty lines is: %d\n", emptyline);
Note that fgets() will not return a full line (just part of it) on lines that have at least sizeof(line) characters.
I wrote this function to read a line from a file:
const char *readLine(FILE *file) {
if (file == NULL) {
printf("Error: file pointer is null.");
exit(1);
}
int maximumLineLength = 128;
char *lineBuffer = (char *)malloc(sizeof(char) * maximumLineLength);
if (lineBuffer == NULL) {
printf("Error allocating memory for line buffer.");
exit(1);
}
char ch = getc(file);
int count = 0;
while ((ch != '\n') && (ch != EOF)) {
if (count == maximumLineLength) {
maximumLineLength += 128;
lineBuffer = realloc(lineBuffer, maximumLineLength);
if (lineBuffer == NULL) {
printf("Error reallocating space for line buffer.");
exit(1);
}
}
lineBuffer[count] = ch;
count++;
ch = getc(file);
}
lineBuffer[count] = '\0';
char line[count + 1];
strncpy(line, lineBuffer, (count + 1));
free(lineBuffer);
const char *constLine = line;
return constLine;
}
The function reads the file correctly, and using printf I see that the constLine string did get read correctly as well.
However, if I use the function e.g. like this:
while (!feof(myFile)) {
const char *line = readLine(myFile);
printf("%s\n", line);
}
printf outputs gibberish. Why?
If your task is not to invent the line-by-line reading function, but just to read the file line-by-line, you may use a typical code snippet involving the getline() function (see the manual page here):
#define _GNU_SOURCE
#include <stdio.h>
#include <stdlib.h>
int main(void)
{
FILE * fp;
char * line = NULL;
size_t len = 0;
ssize_t read;
fp = fopen("/etc/motd", "r");
if (fp == NULL)
exit(EXIT_FAILURE);
while ((read = getline(&line, &len, fp)) != -1) {
printf("Retrieved line of length %zu:\n", read);
printf("%s", line);
}
fclose(fp);
if (line)
free(line);
exit(EXIT_SUCCESS);
}
FILE* filePointer;
int bufferLength = 255;
char buffer[bufferLength]; /* not ISO 90 compatible */
filePointer = fopen("file.txt", "r");
while(fgets(buffer, bufferLength, filePointer)) {
printf("%s\n", buffer);
}
fclose(filePointer);
In your readLine function, you return a pointer to the line array (Strictly speaking, a pointer to its first character, but the difference is irrelevant here). Since it's an automatic variable (i.e., it's “on the stack”), the memory is reclaimed when the function returns. You see gibberish because printf has put its own stuff on the stack.
You need to return a dynamically allocated buffer from the function. You already have one, it's lineBuffer; all you have to do is truncate it to the desired length.
lineBuffer[count] = '\0';
realloc(lineBuffer, count + 1);
return lineBuffer;
}
ADDED (response to follow-up question in comment): readLine returns a pointer to the characters that make up the line. This pointer is what you need to work with the contents of the line. It's also what you must pass to free when you've finished using the memory taken by these characters. Here's how you might use the readLine function:
char *line = readLine(file);
printf("LOG: read a line: %s\n", line);
if (strchr(line, 'a')) { puts("The line contains an a"); }
/* etc. */
free(line);
/* After this point, the memory allocated for the line has been reclaimed.
You can't use the value of `line` again (though you can assign a new value
to the `line` variable if you want). */
//open and get the file handle
FILE* fh;
fopen_s(&fh, filename, "r");
//check if file exists
if (fh == NULL){
printf("file does not exists %s", filename);
return 0;
}
//read line by line
const size_t line_size = 300;
char* line = malloc(line_size);
while (fgets(line, line_size, fh) != NULL) {
printf(line);
}
free(line); // dont forget to free heap memory
A complete, fgets() solution:
#include <stdio.h>
#include <string.h>
#define MAX_LEN 256
int main(void)
{
FILE* fp;
fp = fopen("file.txt", "r");
if (fp == NULL) {
perror("Failed: ");
return 1;
}
char buffer[MAX_LEN];
while (fgets(buffer, MAX_LEN, fp))
{
// Remove trailing newline
buffer[strcspn(buffer, "\n")] = 0;
printf("%s\n", buffer);
}
fclose(fp);
return 0;
}
Output:
First line of file
Second line of file
Third (and also last) line of file
Remember, if you want to read from Standard Input (rather than a file as in this case), then all you have to do is pass stdin as the third parameter of fgets() method, like this:
while(fgets(buffer, MAX_LEN, stdin))
Appendix
Removing trailing newline character from fgets() input
how to detect a file is opened or not in c
readLine() returns pointer to local variable, which causes undefined behaviour.
To get around you can:
Create variable in caller function and pass its address to readLine()
Allocate memory for line using malloc() - in this case line will be persistent
Use global variable, although it is generally a bad practice
Use fgets() to read a line from a file handle.
Some things wrong with the example:
you forgot to add \n to your printfs. Also error messages should go to stderr i.e. fprintf(stderr, ....
(not a biggy but) consider using fgetc() rather than getc(). getc() is a macro, fgetc() is a proper function
getc() returns an int so ch should be declared as an int. This is important since the comparison with EOF will be handled correctly. Some 8 bit character sets use 0xFF as a valid character (ISO-LATIN-1 would be an example) and EOF which is -1, will be 0xFF if assigned to a char.
There is a potential buffer overflow at the line
lineBuffer[count] = '\0';
If the line is exactly 128 characters long, count is 128 at the point that gets executed.
As others have pointed out, line is a locally declared array. You can't return a pointer to it.
strncpy(count + 1) will copy at most count + 1 characters but will terminate if it hits '\0' Because you set lineBuffer[count] to '\0' you know it will never get to count + 1. However, if it did, it would not put a terminating '\0' on, so you need to do it. You often see something like the following:
char buffer [BUFFER_SIZE];
strncpy(buffer, sourceString, BUFFER_SIZE - 1);
buffer[BUFFER_SIZE - 1] = '\0';
if you malloc() a line to return (in place of your local char array), your return type should be char* - drop the const.
Here is my several hours... Reading whole file line by line.
char * readline(FILE *fp, char *buffer)
{
int ch;
int i = 0;
size_t buff_len = 0;
buffer = malloc(buff_len + 1);
if (!buffer) return NULL; // Out of memory
while ((ch = fgetc(fp)) != '\n' && ch != EOF)
{
buff_len++;
void *tmp = realloc(buffer, buff_len + 1);
if (tmp == NULL)
{
free(buffer);
return NULL; // Out of memory
}
buffer = tmp;
buffer[i] = (char) ch;
i++;
}
buffer[i] = '\0';
// Detect end
if (ch == EOF && (i == 0 || ferror(fp)))
{
free(buffer);
return NULL;
}
return buffer;
}
void lineByline(FILE * file){
char *s;
while ((s = readline(file, 0)) != NULL)
{
puts(s);
free(s);
printf("\n");
}
}
int main()
{
char *fileName = "input-1.txt";
FILE* file = fopen(fileName, "r");
lineByline(file);
return 0;
}
const char *readLine(FILE *file, char* line) {
if (file == NULL) {
printf("Error: file pointer is null.");
exit(1);
}
int maximumLineLength = 128;
char *lineBuffer = (char *)malloc(sizeof(char) * maximumLineLength);
if (lineBuffer == NULL) {
printf("Error allocating memory for line buffer.");
exit(1);
}
char ch = getc(file);
int count = 0;
while ((ch != '\n') && (ch != EOF)) {
if (count == maximumLineLength) {
maximumLineLength += 128;
lineBuffer = realloc(lineBuffer, maximumLineLength);
if (lineBuffer == NULL) {
printf("Error reallocating space for line buffer.");
exit(1);
}
}
lineBuffer[count] = ch;
count++;
ch = getc(file);
}
lineBuffer[count] = '\0';
char line[count + 1];
strncpy(line, lineBuffer, (count + 1));
free(lineBuffer);
return line;
}
char linebuffer[256];
while (!feof(myFile)) {
const char *line = readLine(myFile, linebuffer);
printf("%s\n", line);
}
note that the 'line' variable is declared in calling function and then passed, so your readLine function fills predefined buffer and just returns it. This is the way most of C libraries work.
There are other ways, which I'm aware of:
defining the char line[] as static
(static char line[MAX_LINE_LENGTH]
-> it will hold it's value AFTER returning from the function). -> bad,
the function is not reentrant, and
race condition can occur -> if you
call it twice from two threads, it
will overwrite it's results
malloc()ing the char line[], and
freeing it in calling functions ->
too many expensive mallocs, and,
delegating the responsibility to free the buffer to another function (the most elegant solution is to call malloc and free on any buffers in same function)
btw, 'explicit' casting from char* to const char* is redundant.
btw2, there is no need to malloc() the lineBuffer, just define it char lineBuffer[128], so you don't need to free it
btw3 do not use 'dynamic sized stack arrays' (defining the array as char arrayName[some_nonconstant_variable]), if you don't exactly know what are you doing, it works only in C99.
void readLine(FILE* file, char* line, int limit)
{
int i;
int read;
read = fread(line, sizeof(char), limit, file);
line[read] = '\0';
for(i = 0; i <= read;i++)
{
if('\0' == line[i] || '\n' == line[i] || '\r' == line[i])
{
line[i] = '\0';
break;
}
}
if(i != read)
{
fseek(file, i - read + 1, SEEK_CUR);
}
}
what about this one?
Implement method to read, and get content from a file (input1.txt)
#include <stdio.h>
#include <stdlib.h>
void testGetFile() {
// open file
FILE *fp = fopen("input1.txt", "r");
size_t len = 255;
// need malloc memory for line, if not, segmentation fault error will occurred.
char *line = malloc(sizeof(char) * len);
// check if file exist (and you can open it) or not
if (fp == NULL) {
printf("can open file input1.txt!");
return;
}
while(fgets(line, len, fp) != NULL) {
printf("%s\n", line);
}
free(line);
}
Hope this help. Happy coding!
You should use the ANSI functions for reading a line, eg. fgets. After calling you need free() in calling context, eg:
...
const char *entirecontent=readLine(myFile);
puts(entirecontent);
free(entirecontent);
...
const char *readLine(FILE *file)
{
char *lineBuffer=calloc(1,1), line[128];
if ( !file || !lineBuffer )
{
fprintf(stderr,"an ErrorNo 1: ...");
exit(1);
}
for(; fgets(line,sizeof line,file) ; strcat(lineBuffer,line) )
{
if( strchr(line,'\n') ) *strchr(line,'\n')=0;
lineBuffer=realloc(lineBuffer,strlen(lineBuffer)+strlen(line)+1);
if( !lineBuffer )
{
fprintf(stderr,"an ErrorNo 2: ...");
exit(2);
}
}
return lineBuffer;
}
My implement from scratch:
FILE *pFile = fopen(your_file_path, "r");
int nbytes = 1024;
char *line = (char *) malloc(nbytes);
char *buf = (char *) malloc(nbytes);
size_t bytes_read;
int linesize = 0;
while (fgets(buf, nbytes, pFile) != NULL) {
bytes_read = strlen(buf);
// if line length larger than size of line buffer
if (linesize + bytes_read > nbytes) {
char *tmp = line;
nbytes += nbytes / 2;
line = (char *) malloc(nbytes);
memcpy(line, tmp, linesize);
free(tmp);
}
memcpy(line + linesize, buf, bytes_read);
linesize += bytes_read;
if (feof(pFile) || buf[bytes_read-1] == '\n') {
handle_line(line);
linesize = 0;
memset(line, '\0', nbytes);
}
}
free(buf);
free(line);
Provide a portable and generic getdelim function, test passed via msvc, clang, gcc.
/*
* An implementation conform IEEE Std 1003.1-2017:
* https://pubs.opengroup.org/onlinepubs/9699919799/functions/getdelim.html
*
* <nio.h>:
* https://github.com/junjiemars/c/blob/c425bd0e49df35a2649327664d3f6cd610791996/src/posix/nio.h
* <nio.c>:
* https://github.com/junjiemars/c/blob/c425bd0e49df35a2649327664d3f6cd610791996/src/posix/nio.c
*
*/
#include <errno.h>
#include <stdlib.h>
#include <stdio.h>
#include <limits.h>
/*
* LINE_MAX dependents on OS' implementations so check it first.
* https://github.com/junjiemars/c/blob/c425bd0e49df35a2649327664d3f6cd610791996/src/posix/nlim_auto_check
*/
#define NM_LINE_MAX 4096 /* Linux */
#if (MSVC)
typedef SSIZE_T ssize_t;
# if !defined(SSIZE_MAX)
# define SSIZE_MAX ((ssize_t)((size_t)((ssize_t)-1) >> 1))
# endif
#endif
ssize_t getdelim(char **restrict lineptr, size_t *restrict n, int delimiter,
FILE *restrict stream);
#if defined(getline)
# undef getline
#endif
#define getline(lp, n, f) getdelim((lp), (n), 0x0a, (f))
ssize_t
getdelim(char **restrict lineptr, size_t *restrict n, int delimiter,
FILE *restrict stream)
{
int c;
char *p, *p1;
ssize_t len;
if (NULL == lineptr || NULL == n || NULL == stream
|| (UCHAR_MAX < delimiter || delimiter < 0))
{
errno = EINVAL;
return EOF;
}
if (feof(stream) || ferror(stream))
{
return EOF;
}
if (0 == *lineptr)
{
if (0 == *n)
{
*n = NM_LINE_MAX;
}
*lineptr = malloc(*n);
if (0 == *lineptr)
{
return EOF;
}
}
p = *lineptr;
len = 0;
while (EOF != (c = fgetc(stream)))
{
if (SSIZE_MAX == (ssize_t) len)
{
errno = EOVERFLOW;
return EOF;
}
if ((size_t) len == (*n - 1))
{
*n <<= 1;
p1 = realloc(*lineptr, *n);
if (0 == p1)
{
return EOF;
}
*lineptr = p1;
p = p1 + len;
}
*p++ = (char) c;
len++;
if (c == delimiter)
{
break;
}
}
if (ferror(stream))
{
return EOF;
}
*p = 0;
return len;
}
int
main(void)
{
FILE *fp;
char *line = NULL;
size_t len = 0;
ssize_t read;
fp = fopen("/some-file", "r");
if (fp == NULL)
exit(1);
while ((read = getline(&line, &len, fp)) != -1) {
printf("Retrieved line of length %zu :\n", read);
printf("%s", line);
}
if (ferror(fp)) {
/* handle error */
}
free(line);
fclose(fp);
return 0;
}
You make the mistake of returning a pointer to an automatic variable.
The variable line is allocated in the stack and only lives as long as the function lives.
You are not allowed to return a pointer to it, because as soon as it returns the memory will be given elsewhere.
const char* func x(){
char line[100];
return (const char*) line; //illegal
}
To avoid this, you either return a pointer to memory which resides on the heap eg. lineBuffer
and it should be the user's responsibility to call free() when he is done with it.
Alternatively you can ask the user to pass you as an argument a memory address on which to write the line contents at.
I want a code from ground 0 so i did this to read the content of dictionary's word line by line.
char temp_str[20]; // you can change the buffer size according to your requirements And A single line's length in a File.
Note I've initialized the buffer With Null character each time I read line.This function can be Automated But Since I need A proof of Concept and want to design a programme Byte By Byte
#include<stdio.h>
int main()
{
int i;
char temp_ch;
FILE *fp=fopen("data.txt","r");
while(temp_ch!=EOF)
{
i=0;
char temp_str[20]={'\0','\0','\0','\0','\0','\0','\0','\0','\0','\0','\0','\0','\0','\0','\0','\0','\0','\0','\0'};
while(temp_ch!='\n')
{
temp_ch=fgetc(fp);
temp_str[i]=temp_ch;
i++;
}
if(temp_ch=='\n')
{
temp_ch=fgetc(fp);
temp_str[i]=temp_ch;
}
printf("%s",temp_str);
}
return 0;
}