At the risk of getting slapped for poor code quality, I'm listing a C utility, is_binary, built around the original buffer_is_binary() routine in the Git source. Please see internal comments for how to build and run. Easily modifyable:
/***********************************************************
* is_binary.c
*
* Usage: is_binary <pathname>
* Returns a 1 if a binary; return a 0 if non-binary
*
* Thanks to Git and Stackoverflow developers for helping with these routines:
* - the buffer_is_binary() routine from the xdiff-interface.c module
* in git source code.
* - the read-a-filename-from-stdin route
* - the read-a-file-into-memory (fill_buffer()) routine
*
* To build:
* % gcc is_binary.c -o is_binary
*
* To build debuggable (to push a few messages to stdout):
* % gcc -DDEBUG=1 ./is_binary.c -o is_binary
*
* BUGS:
* Doesn't work with piped input, like
* % cat foo.tar | is_binary
* Claims that zero input is binary. Actually,
* what should it be?
*
* Revision 1.4
*
* Tue Sep 12 09:01:33 EDT 2017
***********************************************************/
#include <string.h>
#include <stdio.h>
#include <stdlib.h>
#define MAX_PATH_LENGTH 200
#define FIRST_FEW_BYTES 8000
/* global, unfortunately */
char *source_blob_buffer;
/* From: https://stackoverflow.com/questions/14002954/c-programming-how-to-read-the-whole-file-contents-into-a-buffer */
/* From: https://stackoverflow.com/questions/1563882/reading-a-file-name-from-piped-command */
/* From: https://stackoverflow.com/questions/6119956/how-to-determine-if-git-handles-a-file-as-binary-or-as-text
*/
/* The key routine in this function is from libc: void *memchr(const void *s, int c, size_t n); */
/* Checks for any occurrence of a zero byte (NUL character) in the first 8000 bytes (or the entire length if shorter). */
int buffer_is_binary(const char *ptr, unsigned long size)
{
if (FIRST_FEW_BYTES < size)
size = FIRST_FEW_BYTES;
/* printf("buff = %s.\n", ptr); */
return !!memchr(ptr, 0, size);
}
int fill_buffer(FILE * file_object_pointer) {
fseek(file_object_pointer, 0, SEEK_END);
long fsize = ftell(file_object_pointer);
fseek(file_object_pointer, 0, SEEK_SET); //same as rewind(f);
source_blob_buffer = malloc(fsize + 1);
fread(source_blob_buffer, fsize, 1, file_object_pointer);
fclose(file_object_pointer);
source_blob_buffer[fsize] = 0;
return (fsize + 1);
}
int main(int argc, char *argv[]) {
char pathname[MAX_PATH_LENGTH];
FILE *file_object_pointer;
if (argc == 1) {
file_object_pointer = stdin;
} else {
strcpy(pathname,argv[1]);
#ifdef DEBUG
printf("pathname=%s.\n", pathname);
#endif
file_object_pointer = fopen (pathname, "rb");
if (file_object_pointer == NULL) {
printf ("I'm sorry, Dave, I can't do that--");
printf ("open the file '%s', that is.\n", pathname);
exit(3);
}
}
if (!file_object_pointer) {
printf("Not a file nor a pipe--sorry.\n");
exit (4);
}
int fsize = fill_buffer(file_object_pointer);
int result = buffer_is_binary(source_blob_buffer, fsize - 2);
#ifdef DEBUG
if (result == 1) {
printf ("%s %d\n", pathname, fsize - 1);
}
else {
printf ("File '%s' is NON-BINARY; size is %d bytes.\n", pathname, fsize - 1);
}
#endif
exit(result);
/* easy check -- 'echo $?' after running */
}
