“#include” a text file in a C program as a char[]

Question

Is there a way to include an entire text file as a string in a C program at compile-time?

something like:

• file.txt:

  This is
  a little
  text file
  

• main.c:

  #include <stdio.h>
  int main(void) {
     #blackmagicinclude("file.txt", content)
     /*
     equiv: char[] content = "This is\na little\ntext file";
     */
     printf("%s", content);
  }
  

obtaining a little program that prints on stdout "This is a little text file"

At the moment I used an hackish python script, but it's butt-ugly and limited to only one variable name, can you tell me another way to do it?

Answer 1

I reimplemented xxd in python3, fixing all of xxd's annoyances:

• Const correctness
• string length datatype: int → size_t
• Null termination (in case you might want that)
• C string compatible: Drop unsigned on the array.
• Smaller, readable output, as you would have written it: Printable ascii is output as-is; other bytes are hex-encoded.

Here is the script, filtered by itself, so you can see what it does:

pyxxd.c

#include <stddef.h>

extern const char pyxxd[];
extern const size_t pyxxd_len;

const char pyxxd[] =
"#!/usr/bin/env python3\n"
"\n"
"import sys\n"
"import re\n"
"\n"
"def is_printable_ascii(byte):\n"
"    return byte >= ord(' ') and byte <= ord('~')\n"
"\n"
"def needs_escaping(byte):\n"
"    return byte == ord('\\\"') or byte == ord('\\\\')\n"
"\n"
"def stringify_nibble(nibble):\n"
"    if nibble < 10:\n"
"        return chr(nibble + ord('0'))\n"
"    return chr(nibble - 10 + ord('a'))\n"
"\n"
"def write_byte(of, byte):\n"
"    if is_printable_ascii(byte):\n"
"        if needs_escaping(byte):\n"
"            of.write('\\\\')\n"
"        of.write(chr(byte))\n"
"    elif byte == ord('\\n'):\n"
"        of.write('\\\\n\"\\n\"')\n"
"    else:\n"
"        of.write('\\\\x')\n"
"        of.write(stringify_nibble(byte >> 4))\n"
"        of.write(stringify_nibble(byte & 0xf))\n"
"\n"
"def mk_valid_identifier(s):\n"
"    s = re.sub('^[^_a-z]', '_', s)\n"
"    s = re.sub('[^_a-z0-9]', '_', s)\n"
"    return s\n"
"\n"
"def main():\n"
"    # `xxd -i` compatibility\n"
"    if len(sys.argv) != 4 or sys.argv[1] != \"-i\":\n"
"        print(\"Usage: xxd -i infile outfile\")\n"
"        exit(2)\n"
"\n"
"    with open(sys.argv[2], \"rb\") as infile:\n"
"        with open(sys.argv[3], \"w\") as outfile:\n"
"\n"
"            identifier = mk_valid_identifier(sys.argv[2]);\n"
"            outfile.write('#include <stddef.h>\\n\\n');\n"
"            outfile.write('extern const char {}[];\\n'.format(identifier));\n"
"            outfile.write('extern const size_t {}_len;\\n\\n'.format(identifier));\n"
"            outfile.write('const char {}[] =\\n\"'.format(identifier));\n"
"\n"
"            while True:\n"
"                byte = infile.read(1)\n"
"                if byte == b\"\":\n"
"                    break\n"
"                write_byte(outfile, ord(byte))\n"
"\n"
"            outfile.write('\";\\n\\n');\n"
"            outfile.write('const size_t {}_len = sizeof({}) - 1;\\n'.format(identifier, identifier));\n"
"\n"
"if __name__ == '__main__':\n"
"    main()\n"
"";

const size_t pyxxd_len = sizeof(pyxxd) - 1;

Usage (this extracts the script):

#include <stdio.h>

extern const char pyxxd[];
extern const size_t pyxxd_len;

int main()
{
    fwrite(pyxxd, 1, pyxxd_len, stdout);
}

Answer 2

You need my xtr utility but you can do it with a bash script. This is a script I call bin2inc. The first parameter is the name of the resulting char[] variable. The second parameter is the name of the file. The output is C include file with the file content encoded (in lowercase hex) as the variable name given. The char array is zero terminated, and the length of the data is stored in $variableName_length

#!/bin/bash

fileSize ()

{

    [ -e "$1" ]  && {

        set -- `ls -l "$1"`;

        echo $5;

    }

}

echo unsigned char $1'[] = {'
./xtr -fhex -p 0x -s ', ' < "$2";
echo '0x00'
echo '};';
echo '';
echo unsigned long int ${1}_length = $(fileSize "$2")';'

YOU CAN GET XTR HERE xtr (character eXTRapolator) is GPLV3

Answer 3

You can do this using objcopy:

objcopy --input binary --output elf64-x86-64 myfile.txt myfile.o

Now you have an object file you can link into your executable which contains symbols for the beginning, end, and size of the content from myfile.txt.