I'm trying to read text from a file and store it into a string so that I can then encrypt and decrypt it using openssl. How can I do this?
You could use dynamic memory. My "skeleton" code for reading any type of file is this:
// Assumes: the file # file name is a text file; ASCII or UTF-8 (no BOM)
void readwholefile(char *filename)
{
FILE *fp;
char *buffer = NULL;
size_t i, len;
fp = fopen(filename, "rb");
fseek(fp, 0, SEEK_END);
len = ftell(fp);
rewind(fp);
buffer = malloc(len + 1);
if (NULL == buffer)
{
// Handle malloc failure & exit
exit(-1);
}
fread(buffer, 1, len, fp);
fclose(fp);
buffer[len] = '\0';
// buffer now contains the content of your file; do what you want with it
free(buffer);
buffer = NULL;
}
If you are using a POSIX system, you can use getline:
char *line = nullptr;
size_t line_size = 0
ssize_t len = getline(&line, &line_size, fp);
This will read until a newline and malloc enough space for the resulting line. You can use getdelim to read up to some delimiter other than a newline.
While reading a file into char *, where should the null be added and why? Option1 or option2, both seem to compile.
char* load_file(char const* path)
{
char* buffer = 0;
long length;
FILE * f = fopen (path, "rb");
if (f)
{
fseek (f, 0, SEEK_END);
length = ftell (f);
fseek (f, 0, SEEK_SET);
buffer = (char*)malloc ((length+1)*sizeof(char));
if (buffer)
{
fread (buffer, sizeof(char), length, f);
}
fclose (f);
}
buffer[length] = '\0'; //option1
buffer[length+1] = '\0'; //Option2
return buffer;
}
With your malloc call you allocate an "array" of length + 1 characters, with indexes from 0 to length (inclusive). Therefore the correct option can only be "option1".
I wrote some code to read first pos bytes from a binary file and write it into another file. Turned out I got segmentation fault when I ran it. Here is the code:
void outputUntillPos(const char * inFileName, const char * outFileName, int pos) {
FILE * inFile = fopen(inFileName, "r");
FILE * outFile = fopen(outFileName, "aw");
char buf[1024];
int read = 0;
int remain = pos;
do {
if(remain <= 1024) {
read = fread(buf, 1, pos, inFile);
} else {
read = fread(buf, 1, 1024, inFile);
}
remain -= read;
fwrite(buf, 1, read, outFile);
memset(buf, 0, 1024);
} while(remain > 0);
}
Did I get out-of-range operation here?
EDIT: Thanks to all the help, here is the edited code.
void outputUntillPos(const char * inFileName, const char * outFileName, int pos) {
FILE * inFile = fopen(inFileName, "r");
FILE * outFile = fopen(outFileName, "aw");
char buf[1024];
int read = 0;
int remain = pos;
if((inFile != NULL) && (outFile != NULL)) {
do {
if(remain <= 1024) {
read = fread(buf, 1, remain, inFile);
} else {
read = fread(buf, 1, 1024, inFile);
}
remain -= read;
fwrite(buf, 1, read, outFile);
memset(buf, 0, 1024);
} while(remain > 0 && read > 0);
}
fclose(inFile);
fclose(outFile);
}
When remain becomes <= 1024 and the if portion of the block is entered, you're reading in pos bytes, which if it's greater that 1024 will write past the end of the buffer. That's what causes the segfault.
You want to use remain here instead:
if(remain <= 1024) {
read = fread(buf, 1, remain, inFile);
} else {
read = fread(buf, 1, 1024, inFile);
}
Also, be sure to check the return value of fopen, and to fclose(inFile) and fclose(outFile) before you return.
When the remaining amount of bytes to read (in variable remain) becomes less that 1024, you for some reason attempt to read pos bytes. Why pos??? You are supposed to read remain bytes on the last iteration, not pos bytes.
If pos is greater than 1024 and the input file still has extra data, then of course you will overrun the buffer on that last iteration.
I'm looking for a cross platform (Windows + Linux) solution to reading the contents of an entire file into a char *.
This is what I've got now:
FILE *stream;
char *contents;
fileSize = 0;
//Open the stream
stream = fopen(argv[1], "r");
//Steak to the end of the file to determine the file size
fseek(stream, 0L, SEEK_END);
fileSize = ftell(stream);
fseek(stream, 0L, SEEK_SET);
//Allocate enough memory (should I add 1 for the \0?)
contents = (char *)malloc(fileSize);
//Read the file
fscanf(stream, "%s", contents);
//Print it again for debugging
printf("Read %s\n", contents);
Unfortunately this will only print the first line in the file so I assume that fscanf stops at the first newline character. However I would like to read the entire file including, and preserving, the new line characters. I'd prefer not to use a while loop and realloc to manually construct the entire string, I mean there has to be a simpler way?
Something like this, may be?
FILE *stream;
char *contents;
fileSize = 0;
//Open the stream. Note "b" to avoid DOS/UNIX new line conversion.
stream = fopen(argv[1], "rb");
//Seek to the end of the file to determine the file size
fseek(stream, 0L, SEEK_END);
fileSize = ftell(stream);
fseek(stream, 0L, SEEK_SET);
//Allocate enough memory (add 1 for the \0, since fread won't add it)
contents = malloc(fileSize+1);
//Read the file
size_t size=fread(contents,1,fileSize,stream);
contents[size]=0; // Add terminating zero.
//Print it again for debugging
printf("Read %s\n", contents);
//Close the file
fclose(stream);
free(contents);
The function fread will read from the stream and not terminate on end-of-line characters.
From the man page, you have:
size_t fread(void *restrict ptr, size_t size, size_t nitems, FILE *restrict stream);
which reads in nitems of size size.
fread reads all the files as-is:
if (fread(contents, 1, fileSize, stream) != fileSize) {
/* error occurred */
}
I've got this:
ssize_t filetomem(const char *filename, uint8_t **result)
{
ssize_t size = 0;
FILE *f = fopen(filename, "r");
if (f == NULL)
{
*result = NULL;
return -1;
}
fseek(f, 0, SEEK_END);
size = ftell(f);
fseek(f, 0, SEEK_SET);
*result = malloc(size);
if (size != fread(*result, sizeof(**result), size, f))
{
free(*result);
return -2;
}
fclose(f);
return size;
}
Meaning of return value:
Positive or 0: successfully read the file
minus one: couldn't open file (possibly no such file)
minus two: fread() failed
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;
}