I am getting these unexpected chars when I try to print the string inside of a file. How can I deal with this situation?
This is my code:
#include <stdlib.h>
#include <stdio.h>
char *readFile(char *filename)
{
char * buffer;
long length;
FILE * f = fopen (filename, "r");
if (f)
{
fseek (f, 0, SEEK_END);
length = ftell (f);
fseek (f, 0, SEEK_SET);
buffer = malloc (length);
if (buffer)
{
fread (buffer, 1, length, f);
}
fclose (f);
}
return buffer;
}
int main() {
char *firstS = readFile("file.txt");
printf("%s \n", firstS);
return 0;
}
You're not NUL terminating your string. Instead, do
buffer = malloc(length+1);
and then after you read in the file
buffer[length] = '\0';
When printf reads past the allocated memory for buffer, it invokes undefined behavior, printf happily reads along until it finds a '\0'. Also note you should initialize buffer to NULL:
char * buffer = NULL;
and check for that back in main before you print. If there's a problem opening the file for instance, you return an uninitialized buffer to main, and trying to read from that is another UB invoker:
char *firstS = readFile("file.txt");
if (firstS != NULL)
{
printf("%s \n", firstS);
}
else
{
// print error message to your liking
}
"Warning C6386 Buffer overrun while writing to 'buffer': the writable size is 'Param(1)*Param(2)' bytes, but '4294967295' bytes might be written."
I'm writing a code to calculate a postfix expression using a stack implemented using linked lists, and I'm reading the postfix expression from a local file in binary ( fopen(filename, "rb" ) into a buffer.
I get the above mentioned warning at this line of code:
fread(buffer, sizeof(char), fileLength, file);
But, I've used calloc to allocate exactly the amount of memory I'd need based on the length of the file like this:
fseek(file, 0, SEEK_END);
fileLength = ftell(file);
buffer = (char*)calloc(fileLength + 1, sizeof(char));
if (!buffer) {
perror("Can't allocate memory!\n");
return NULL;
}
I don't understand where it got the "'4294967295' bytes might be written". Anyone care enough to explain what might be the cause, I'm a student and I'm not that much experienced with C.
Here's the entire function block:
int CalculatePostfix(double* destination, char* fileName)
{
FILE* file = NULL;
int fileLength = 0;
char* buffer = NULL;
char* currentBuffer = NULL;
int numBytes = 0;
char operation = 0;
double number = 0;
int status = EXIT_SUCCESS;;
StackElement head = { .number = 0, .next = NULL };
file = fopen(fileName, "rb");
if (!file) {
perror("Can't open file!\n");
return -1;
}
fseek(file, 0, SEEK_END);
fileLength = ftell(file);
buffer = (char*)calloc(fileLength + 1, sizeof(char));
if (!buffer) {
perror("Can't allocate memory!\n");
return NULL;
}
rewind(file);
fread(buffer, sizeof(char), fileLength, file);
printf("|%s|\n", buffer);
fclose(file);
currentBuffer = buffer;
while (strlen(currentBuffer) > 0) {
status = sscanf(currentBuffer, " %lf %n", &number, &numBytes);
if (status == 1) {
Push(&head, number);
currentBuffer += numBytes;
}
else {
sscanf(currentBuffer, " %c %n", &operation, &numBytes);
status = PerformOperation(&head, operation);
if (status != EXIT_SUCCESS) {
free(buffer);
while (head.next != NULL) {
DeleteAfter(&head);
}
return -1;
}
currentBuffer += numBytes;
}
}
free(buffer);
return EXIT_SUCCESS;
}
ftell returns a long integer, fread takes a size_t which, depending on implementation, often is an unsigned int. So if you happen to get -1L (which is the error return code from ftell) back from ftell you will end up vid a massive large unsigned int.
So to solve this, check return value of ftell and make sure it is not -1L, then when calling fread cast to size_t
char* freadline(FILE* fp){
fseek(fp, 0, SEEK_END);
int lSize = ftell(fp);
fseek(fp, 0, SEEK_SET);
char *buffer = malloc(lSize);
fread(buffer, 1, lSize, fp);
fgets(buffer, sizeof(lSize), fp);
return buffer;
}
but it doesn't read line by line any suggestions as to how this would be read line by line
There are couple solutions here.
The first is to get the size of the entire file using fseek and ftell fseek will allow you to go to the end of file and ftell will give you the current position which can be used as a size indicator. You can then allocate enough of a buffer to read the entire file then split them up into lines.
The other solution is to use a temporary buffer of 1000 or so like you're already doing, read a character at a time using fgetc in a loop and feed it into the temporary buffer until you hit a new line indicator , then use the strlen method to get the length and allocate a buffer of that size, copy the temporary buffer then return the allocated buffer.
There is also errors in your code as pointed out in the comments. You're discarding your allocated memory resulting in a leak. And your freadline doesn't actually read a line it just reads whatever size you're telling it to read.
the lines in the file could be of any length.
realloc() is a classic approach, but how about a simple, slow and plodding one:
Read once to find line length, seek, allocate, then read again to save the line.
#include <stdio.h>
char* freadline(FILE *fp) {
int length = 0;
long offset = ftell(fp);
if (offset == -1)
return NULL;
int scan_count = fscanf(fp, "%*[^\n]%n", &length); // Save scan length
if (scan_count == EOF)
return NULL;
if (fseek(fp, offset, SEEK_SET))
return NULL;
size_t n = length + 1u; // +1 for potential \n
char *buf = malloc(n + 1); // + 1 for \0
if (buf == NULL)
return NULL;
size_t len = fread(buf, 1, n, fp);
buf[len] = '\0';
return buf;
}
Test
#include <assert.h>
#include <stdlib.h>
int main() {
FILE *fp = fopen("tmp.txt", "w+");
assert(fp);
for (int i = 0; i < 10; i++) {
int l = i * 7;
for (int j = 0; j < l; j++) {
fputc(rand() % 26 + 'a', fp);
}
fputc('\n', fp);
}
rewind(fp);
char *s;
while ((s = freadline(fp)) != NULL) {
printf("<%s>", s);
free(s);
}
fclose(fp);
return 0;
}
Output
<
><lvqdyoq
><ykfdbxnqdquhyd
><jaeebzqmtblcabwgmscrn
><oiaftlfpcuqffaxozqegxmwgglkh
><vxtdhnzqankyprbwteazdafeqxtijjtkwea
><zqgmplohyxrutojvbzllqgjaidbtqibygdzcxkujvw
><ghwbmjjmbpksnzkgzgiluiggpkzwhaetclrcyxcsixsutjmrm
><vqlybsjnihnfqyfhyszwgpsvnhnngdnjzjypqcflnztrhcfgbkakzxam
><alsuauxxchqjxqaiddtjszgcbullyyjymytioyawpzshhfpqpsatddbcagjgobm
>
If you're ok targeting POSIX, it already has a function that does what you need: getline.
#include <stdio.h>
#include <stdlib.h>
FILE *fh = ...;
char *line = NULL;
size_t buf_size = 0;
while (1) {
ssize_t line_len = getline(&line, &buf_size, fh);
if (line_len == -1)
break;
// ...
}
free(line);
If not, getline can be implemented using using fgets and realloc in a loop. Just start with a arbitrarily-sized buffer.
I have a file that I need to read into a buffer (char *) but the problem is that the file has some "funny characters" in it inbetween the valid text.
So when I write some code like the following:
FILE *fp;
if((fp = fopen(".\\test.txt", "rt"))==NULL){
printf("Cannot open file2\n");
}
fseek(fp, 0, SEEK_END);
long int fsize = ftell(fp);
rewind(fp);
//char *buffer2 = malloc(fsize * sizeof(char));
buffer = malloc(fsize * sizeof(char));
fread(buffer, 1, fsize, fp);
buffer[fsize] = '\0';
fclose(fp);
printf("fsize = %i\n", fsize);
printf("Buffer = %s\n", buffer);
It only prints out the first part of the text file like follows:
Buffer = header
And obviously stops at the first NUL char.
Is thier any way to read the entire buffer of the file, including funny chars?
Or is this not possible in C?
The FSIZE is read correctly, just the FREAD does not read the entire buffer ;-(
Any help would be greatly appreciated ;-)
Thanks
Lynton
UPDATE: OK, I was being a little stupid.....if I write the buffer to a file it has everything in it, only if I write it out to the screen does it stop at the null so that is fine.
Don't open the file in "text" mode ("rt"), use binary mode instead ("rb").
Also, it might well be reading the data, but the printf("Buffer = %s\n", buffer) will only print up to the first NUL, so your debug is not going to do what your want. You probably want to write a little hex dumping function.
How to read all contents of file, including NUL chars between valid text?
Errors:
Allocate enough space if attempting to make a string. OP's code is 1 short. This is a dubious goal if data read may include null chracters.
Open in binary mode #Lawrence Dol
Some more error checking is useful.
// FILE *fp = fopen(".\\test.txt", "rt");
FILE *fp = fopen(".\\test.txt", "rb");
if (fp==NULL) {
printf("Cannot open file2\n");
exit(-1);
}
if (fseek(fp, 0, SEEK_END)) {
printf("fseek() trouble\n");
exit(-1);
}
long fsize = ftell(fp);
if (fsize == -1 || fsize >= SIZE_MAX) {
printf("fell() trouble\n");
exit(-1);
}
// Add 1 if trying to make a string.
size_t sz = (size_t) fsize;
if (making_a_string) sz++;
rewind(fp);
char *buffer = malloc(sizeof *buffer * sz);
if (buffer == NULL && sz > 0) { // Tolerate a file size of 0
printf("malloc() trouble\n");
exit(-1);
}
size_t in = fread(buffer, 1, fsize, fp);
fclose(fp);
if (in != fsize) {
printf("fread() trouble\n");
exit(-1);
}
if (making_a_string) {
buffer[fsize] = '\0';
}
To print the entire data, use, fwrite(). In order to print a character array, a trailing null chracter is not needed as in a string, but the length of the character array is used.
printf("fsize = %ld\n", fsize); // Note: %ld
printf("Buffer = <", );
fwrite(buffer, 1, fsize, stdout);
printf(">\n");
What is the simplest way (least error-prone, least lines of code, however you want to interpret it) to open a file in C and read its contents into a string (char*, char[], whatever)?
I tend to just load the entire buffer as a raw memory chunk into memory and do the parsing on my own. That way I have best control over what the standard lib does on multiple platforms.
This is a stub I use for this. you may also want to check the error-codes for fseek, ftell and fread. (omitted for clarity).
char * buffer = 0;
long length;
FILE * f = fopen (filename, "rb");
if (f)
{
fseek (f, 0, SEEK_END);
length = ftell (f);
fseek (f, 0, SEEK_SET);
buffer = malloc (length);
if (buffer)
{
fread (buffer, 1, length, f);
}
fclose (f);
}
if (buffer)
{
// start to process your data / extract strings here...
}
Another, unfortunately highly OS-dependent, solution is memory mapping the file. The benefits generally include performance of the read, and reduced memory use as the applications view and operating systems file cache can actually share the physical memory.
POSIX code would look like this:
int fd = open("filename", O_RDONLY);
int len = lseek(fd, 0, SEEK_END);
void *data = mmap(0, len, PROT_READ, MAP_PRIVATE, fd, 0);
Windows on the other hand is little more tricky, and unfortunately I don't have a compiler in front of me to test, but the functionality is provided by CreateFileMapping() and MapViewOfFile().
If "read its contents into a string" means that the file does not contain characters with code 0, you can also use getdelim() function, that either accepts a block of memory and reallocates it if necessary, or just allocates the entire buffer for you, and reads the file into it until it encounters a specified delimiter or end of file. Just pass '\0' as the delimiter to read the entire file.
This function is available in the GNU C Library, http://www.gnu.org/software/libc/manual/html_mono/libc.html#index-getdelim-994
The sample code might look as simple as
char* buffer = NULL;
size_t len;
ssize_t bytes_read = getdelim( &buffer, &len, '\0', fp);
if ( bytes_read != -1) {
/* Success, now the entire file is in the buffer */
If you are reading special files like stdin or a pipe, you are not going to be able to use fstat to get the file size beforehand. Also, if you are reading a binary file fgets is going to lose the string size information because of embedded '\0' characters. Best way to read a file then is to use read and realloc:
#include <stdio.h>
#include <unistd.h>
#include <errno.h>
#include <string.h>
int main () {
char buf[4096];
ssize_t n;
char *str = NULL;
size_t len = 0;
while (n = read(STDIN_FILENO, buf, sizeof buf)) {
if (n < 0) {
if (errno == EAGAIN)
continue;
perror("read");
break;
}
str = realloc(str, len + n + 1);
memcpy(str + len, buf, n);
len += n;
str[len] = '\0';
}
printf("%.*s\n", len, str);
return 0;
}
Note: This is a modification of the accepted answer above.
Here's a way to do it, complete with error checking.
I've added a size checker to quit when file was bigger than 1 GiB. I did this because the program puts the whole file into a string which may use too much ram and crash a computer. However, if you don't care about that you could just remove it from the code.
#include <stdio.h>
#include <stdlib.h>
#define FILE_OK 0
#define FILE_NOT_EXIST 1
#define FILE_TOO_LARGE 2
#define FILE_READ_ERROR 3
char * c_read_file(const char * f_name, int * err, size_t * f_size) {
char * buffer;
size_t length;
FILE * f = fopen(f_name, "rb");
size_t read_length;
if (f) {
fseek(f, 0, SEEK_END);
length = ftell(f);
fseek(f, 0, SEEK_SET);
// 1 GiB; best not to load a whole large file in one string
if (length > 1073741824) {
*err = FILE_TOO_LARGE;
return NULL;
}
buffer = (char *)malloc(length + 1);
if (length) {
read_length = fread(buffer, 1, length, f);
if (length != read_length) {
free(buffer);
*err = FILE_READ_ERROR;
return NULL;
}
}
fclose(f);
*err = FILE_OK;
buffer[length] = '\0';
*f_size = length;
}
else {
*err = FILE_NOT_EXIST;
return NULL;
}
return buffer;
}
And to check for errors:
int err;
size_t f_size;
char * f_data;
f_data = c_read_file("test.txt", &err, &f_size);
if (err) {
// process error
}
else {
// process data
free(f_data);
}
What is the simplest way (least error-prone, least lines of code, however you want to interpret it) to open a file in C and read its contents into a string ...?
Sadly, even after years, answers are error prone and many lack proper string formation and error checking.
#include <stdio.h>
#include <stdlib.h>
// Read the file into allocated memory.
// Return NULL on error.
char* readfile(FILE *f) {
// f invalid? fseek() fail?
if (f == NULL || fseek(f, 0, SEEK_END)) {
return NULL;
}
long length = ftell(f);
rewind(f);
// Did ftell() fail? Is the length too long?
if (length == -1 || (unsigned long) length >= SIZE_MAX) {
return NULL;
}
// Convert from long to size_t
size_t ulength = (size_t) length;
char *buffer = malloc(ulength + 1);
// Allocation failed? Read incomplete?
if (buffer == NULL || fread(buffer, 1, ulength, f) != ulength) {
free(buffer);
return NULL;
}
buffer[ulength] = '\0'; // Now buffer points to a string
return buffer;
}
Note that if the text file contains null characters, the allocated data will contain all the file data, yet the string will appear to be short. Better code would also return the length information so the caller can handle that.
char* readfile(FILE *f, size_t *ulength_ptr) {
...
if (ulength_ptr) *ulength_ptr == *ulength;
...
}
If the file is text, and you want to get the text line by line, the easiest way is to use fgets().
char buffer[100];
FILE *fp = fopen("filename", "r"); // do not use "rb"
while (fgets(buffer, sizeof(buffer), fp)) {
... do something
}
fclose(fp);
If you're using glib, then you can use g_file_get_contents;
gchar *contents;
GError *err = NULL;
g_file_get_contents ("foo.txt", &contents, NULL, &err);
g_assert ((contents == NULL && err != NULL) || (contents != NULL && err == NULL));
if (err != NULL)
{
// Report error to user, and free error
g_assert (contents == NULL);
fprintf (stderr, "Unable to read file: %s\n", err->message);
g_error_free (err);
}
else
{
// Use file contents
g_assert (contents != NULL);
}
}
Just modified from the accepted answer above.
#include <stdio.h>
#include <stdlib.h>
#include <assert.h>
char *readFile(char *filename) {
FILE *f = fopen(filename, "rt");
assert(f);
fseek(f, 0, SEEK_END);
long length = ftell(f);
fseek(f, 0, SEEK_SET);
char *buffer = (char *) malloc(length + 1);
buffer[length] = '\0';
fread(buffer, 1, length, f);
fclose(f);
return buffer;
}
int main() {
char *content = readFile("../hello.txt");
printf("%s", content);
}
// Assumes the file exists and will seg. fault otherwise.
const GLchar *load_shader_source(char *filename) {
FILE *file = fopen(filename, "r"); // open
fseek(file, 0L, SEEK_END); // find the end
size_t size = ftell(file); // get the size in bytes
GLchar *shaderSource = calloc(1, size); // allocate enough bytes
rewind(file); // go back to file beginning
fread(shaderSource, size, sizeof(char), file); // read each char into ourblock
fclose(file); // close the stream
return shaderSource;
}
This is a pretty crude solution because nothing is checked against null.
I will add my own version, based on the answers here, just for reference. My code takes into consideration sizeof(char) and adds a few comments to it.
// Open the file in read mode.
FILE *file = fopen(file_name, "r");
// Check if there was an error.
if (file == NULL) {
fprintf(stderr, "Error: Can't open file '%s'.", file_name);
exit(EXIT_FAILURE);
}
// Get the file length
fseek(file, 0, SEEK_END);
long length = ftell(file);
fseek(file, 0, SEEK_SET);
// Create the string for the file contents.
char *buffer = malloc(sizeof(char) * (length + 1));
buffer[length] = '\0';
// Set the contents of the string.
fread(buffer, sizeof(char), length, file);
// Close the file.
fclose(file);
// Do something with the data.
// ...
// Free the allocated string space.
free(buffer);
easy and neat(assuming contents in the file are less than 10000):
void read_whole_file(char fileName[1000], char buffer[10000])
{
FILE * file = fopen(fileName, "r");
if(file == NULL)
{
puts("File not found");
exit(1);
}
char c;
int idx=0;
while (fscanf(file , "%c" ,&c) == 1)
{
buffer[idx] = c;
idx++;
}
buffer[idx] = 0;
}