Allocating unknown char[] in dynamically reading a file in c - c

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.

Related

Why does this loop iterating over a file buffer throw a BAD ACCESS exception?

I've been picking at this for hours and can't figure out why the loop would try to access out of bounds memory.... Any help would be super appreciated!
int CountCharacters(FILE *fp, const char* filename){
// Get file size
fseek(fp, 0L, SEEK_END);
long size = ftell(fp);
if (size == -1){ perror("Failed: "); return 0;}
rewind(fp); //seek back to file's beginning
// Allocate approrpiately sized buffer ( size + 1 for null-termination)
char *buf = malloc(sizeof (char) * (size + 1));
// Read the entire file into memory
size_t newLen = fread(buf, sizeof(char), size, fp);
if ( ferror( fp ) != 0 ) {
fputs("Error reading file", stderr);
} else {
buf[newLen++] = '\0'; /* Just to be safe. */
}
//Try to get byte count from buffer
int byte_count[256] = {0}; //initialize character counts to 0
for (int i = 0; i < size; ++i){
byte_count[(int) buf[i]]++; //BAD ACCESS ERROR HERE
}
/* Do something with byte_count here */
return (1);
}

Reading from file fails

I am reading a string from a file. After like the second or third time the function gets executed, one or more random characters become appended to the buffer string and I have no idea why that happens.
Here's the piece of code:
scorefile = fopen("highscore.dat", "rb");
if (scorefile)
{
fseek(scorefile, 0, SEEK_END);
length = ftell(scorefile);
fseek(scorefile, 0, SEEK_SET);
buffer = malloc(length);
if (buffer)
{
fread(buffer, 1, length, scorefile);
}
fclose(scorefile);
}
Am I doing something wrong here?
Let's spell it all out and go slightly more robust:
#include <stdio.h>
#include <stdlib.h>
#include <assert.h>
char *loadScoreFile(const char *filename)
{
char *buffer = NULL;
FILE *scorefile = fopen(filename, "r");
if (scorefile != NULL)
{
(void) fseek(scorefile, 0, SEEK_END);
int length = ftell(scorefile);
(void) fseek(scorefile, 0, SEEK_SET);
buffer = malloc(length + 1);
if (buffer != NULL)
{
assert(length == fread(buffer, 1, length, scorefile));
buffer[length] = '\0';
}
(void) fclose(scorefile);
}
return buffer;
}
int main()
{
for (int i = 0; i < 10; i++)
{
char *pointer = loadScoreFile("highscore.dat");
if (pointer != NULL)
{
printf("%s", pointer);
free(pointer);
}
}
return 0;
}
if you use buffer = malloc(length);, and then read length bytes into it, it will be one byte too short. Char arrays in C are zero-terminated, so they need an extra byte to but that zero. buffer = malloc(length+1); will fix this.

fread position cursor does not seem to advance as expected

I'm trying to dynamically realloc memory for a file being read one character at a time. It is not printing the buffer character by character. It looks like the fread function is not advancing 1 character at a time.
int main() {
FILE *fp;
char *newBuffer;
char *buffer = malloc(sizeof(char));
int count = 0;
/* Open file for both reading and writing */
fp = fopen("test.txt", "r");
if (!fp) {
exit(99);
}
/* Seek to the beginning of the file */
fseek(fp, SEEK_SET, 0);
/* Read into memory and display the buffer as its read */
while (1) {
newBuffer = (char*)realloc(buffer, (sizeof(char) * (++count)));
if (newBuffer) {
buffer = newBuffer;
buffer += (count - 1);
fread(buffer, sizeof(char), 1, fp);
if (feof(fp)) {
buffer = newBuffer;
break;
}
buffer = newBuffer;
printf(" %s\n", buffer);
} else {
// realloc failed
free(buffer);
exit(1);
}
}
fclose(fp);
free(newBuffer);
return(0);
}
You do not null terminate the buffer before using it as a string in printf, this is a problem.
Note that you can simplify or improve the code in various ways:
no need to fseek(fp, SEEK_SET, 0); after fopen, the FILE is already at the starting position. Note that you interverted the arguments to fseek: it should be fseek(fp, 0L, SEEK_SET); but you are lucky SEEK_SET is #defined as 0.
reading one byte from the file is much simpler with getc than fread(buffer, sizeof(char), 1, fp);. It allows for a simpler and better test for end of file. Using feof() only works in your example because you only attempt to read a single byte.
no need for the initial malloc, set buffer toNULL.reallocacceptsNULLand behaves likemallocwith such as argument,freeaccepts aNULL` argument and does nothing.
do not cast the return value of malloc, nor realloc.
sizeof(char) is 1 by definition: either use sizeof(*buffer) or elide the sizeof completely.
do not parenthesize the return expression.
the prototype for main without arguments is int main(void)
Here is a simpler version:
int main(void) {
FILE *fp;
char *newBuffer;
char *buffer = NULL;
int count = 0, c;
/* Open file for both reading */
fp = fopen("test.txt", "r");
if (!fp) {
exit(99);
}
/* Read into memory and display the buffer read */
while ((c = getc(fp)) != EOF) {
newBuffer = realloc(buffer, count + 2);
if (newBuffer) {
buffer = newBuffer;
buffer[count++] = c;
buffer[count] = '\0';
printf(" %s\n", buffer);
} else {
// realloc failed
fclose(fp);
free(buffer);
exit(1);
}
}
fclose(fp);
free(buffer);
return 0;
}
Your printf(" %s\n", buffer); expects buffer to end with a '\0' (null) character. Your code doesn't provide the required null.

convert unsigned int to char alphabets

I have the following code that converts a stream data of 16-bit integer to unsigned 8-bit integer.
I am looking to convert them to alphabetical data values and see what they contain.
#include<stdio.h>
int main() {
FILE *fp,*out;
char buffer[256];
size_t i = 0;
fp=fopen("c:/Gosam/input.txt", "rb");
if(fp != NULL) {
fread(buffer, sizeof buffer,1, fp);
}
out = fopen("c:/Gosam/res.txt", "w");
if(out != NULL) {
// buffer = (char*) malloc (sizeof(char)*Size);
for( i = 0; i < sizeof(buffer); i += 2)
{
const unsigned int var = buffer[i] + 256 * buffer[i + 1];
fprintf(out, "%u\n", var);
}
fclose(out);
}
fclose(fp);
}
The following is the form of my output:
263 4294966987 4294967222 4294967032 64 4294967013 73 4294967004 90
4294967028 83 4294966975 37 4294966961 5 4294966976 82 4294966942
4294967022 4294966994 11 4294967024 29 4294966985 4294966986 4294966954 50
4294966993 4294966974 4294967019 4294967007
This are the values I want to convert to alphabetical characters and see their content.
I don't know what you expect as an answer (you didn't ask a question), but there seems to be one suspicious thing in your code:
char buffer[256];
Here char means signed char. If your code does manipulations on them (like multiplying by 256), it probably doesn't do what you expect (though I can only guess what you expect - your question doesn't mention it).
Try the following:
unsigned char buffer[256];
Also please ask a question (that is, something with a question mark), and give some examples (input, output).
Your basic mistakes were:
after opening the inputfile checking out instead of fp against NULL
fread until eof won't return the number of characters that could be read (I've used fseek and ftell for this purpose)
writing uint values instead of char values to your file
I've fixed them and commented the affected lines appropriate. I also changed the buffer to use dynamic memory allocation instead of static allocation (that's how you can allocate memory for a buffer of a size that is unknown at compile-time). Please try the following code, which will copy all ASCII characters from one file to your output file (which is probably what you meant by 'alphabetical strings'):
#include <stdio.h>
#include <stdlib.h>
int main(int argc, char* argv[]){
FILE *fp, *out;
char *buffer = NULL; /* use a pointer for dynamic memory allocation */
size_t i = 0, charCount = 0;
fp = fopen("c:/input.txt", "r"); /*read as ascii - not binary */
if(fp != NULL){ /*use 'fp' here 'out' is not initalized */
fseek(fp, 0, SEEK_END); /* go to end of the file */
charCount = ftell(fp) - 1; /* get position */
fseek(fp, 0, SEEK_SET); /* return to the beginning of the file */
buffer = (char*)malloc(sizeof(char)*charCount); /* allocate memory */
fread(buffer, sizeof(char) * charCount, 1, fp); /* reads all characters from the file */
}
out = fopen("c:/output.txt", "w");
if(out != NULL){
for(i = 0; i < charCount; i += 1){ /* loop from 0 to count of characters */
const unsigned char var = buffer[i];
fprintf(out, "%c", var);
}
fclose(out);
}
fclose(fp);
if(buffer != NULL){
free(buffer); /* deallocate memory */
}
return 0;
}

How to read the content of a file to a string in C?

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;
}

Resources