Parsing command-line arguments in C?

Question

I\'m trying to write a program that can compare two files line by line, word by word, or character by character in C. It has to be able to read in command line options

Answer 1

Docopt has a C implementation that I thought was quite nice: https://github.com/docopt/docopt.c

From a man-page standardized format describing command line options, docopt infers and creates an argument parser. This got started in python; the python version literally just parses the docstring and returns a dict. To do this in C takes a little more work, but it's clean to use and has no external dependencies.

Answer 2

To my knowledge, the three most popular ways how to parse command line arguments in C are:

• Getopt (#include <unistd.h> from the POSIX C Library), which can solve simple argument parsing tasks. If you're a bit familiar with bash, the getopt built-in of bash is based on Getopt from the GNU libc.
• Argp (#include <argp.h> from the GNU C Library), which can solve more complex tasks and takes care of stuff like, for example:
  • -?, --help for help message, including email address
  • -V, --version for version information
  • --usage for usage message
• Doing it yourself, which I don't recommend for programs that would be given to somebody else, as there is too much that could go wrong or lower quality. The popular mistake of forgetting about '--' to stop option parsing is just one example.

The GNU C Library documentation has some nice examples for Getopt and Argp.

• http://www.gnu.org/software/libc/manual/html_node/Getopt.html
• http://www.gnu.org/software/libc/manual/html_node/Argp.html

Example for using Getopt

#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>

int main(int argc, char *argv[])
{
    bool isCaseInsensitive = false;
    int opt;
    enum { CHARACTER_MODE, WORD_MODE, LINE_MODE } mode = CHARACTER_MODE;

    while ((opt = getopt(argc, argv, "ilw")) != -1) {
        switch (opt) {
        case 'i': isCaseInsensitive = true; break;
        case 'l': mode = LINE_MODE; break;
        case 'w': mode = WORD_MODE; break;
        default:
            fprintf(stderr, "Usage: %s [-ilw] [file...]\n", argv[0]);
            exit(EXIT_FAILURE);
        }
    }

    // Now optind (declared extern int by <unistd.h>) is the index of the first non-option argument.
    // If it is >= argc, there were no non-option arguments.

    // ...
}

Example for using Argp

#include <argp.h>
#include <stdbool.h>

const char *argp_program_version = "programname programversion";
const char *argp_program_bug_address = "<your@email.address>";
static char doc[] = "Your program description.";
static char args_doc[] = "[FILENAME]...";
static struct argp_option options[] = { 
    { "line", 'l', 0, 0, "Compare lines instead of characters."},
    { "word", 'w', 0, 0, "Compare words instead of characters."},
    { "nocase", 'i', 0, 0, "Compare case insensitive instead of case sensitive."},
    { 0 } 
};

struct arguments {
    enum { CHARACTER_MODE, WORD_MODE, LINE_MODE } mode;
    bool isCaseInsensitive;
};

static error_t parse_opt(int key, char *arg, struct argp_state *state) {
    struct arguments *arguments = state->input;
    switch (key) {
    case 'l': arguments->mode = LINE_MODE; break;
    case 'w': arguments->mode = WORD_MODE; break;
    case 'i': arguments->isCaseInsensitive = true; break;
    case ARGP_KEY_ARG: return 0;
    default: return ARGP_ERR_UNKNOWN;
    }   
    return 0;
}

static struct argp argp = { options, parse_opt, args_doc, doc, 0, 0, 0 };

int main(int argc, char *argv[])
{
    struct arguments arguments;

    arguments.mode = CHARACTER_MODE;
    arguments.isCaseInsensitive = false;

    argp_parse(&argp, argc, argv, 0, 0, &arguments);

    // ...
}

Example for Doing it Yourself

#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>

int main(int argc, char *argv[])
{   
    bool isCaseInsensitive = false;
    enum { CHARACTER_MODE, WORD_MODE, LINE_MODE } mode = CHARACTER_MODE;
    size_t optind;
    for (optind = 1; optind < argc && argv[optind][0] == '-'; optind++) {
        switch (argv[optind][1]) {
        case 'i': isCaseInsensitive = true; break;
        case 'l': mode = LINE_MODE; break;
        case 'w': mode = WORD_MODE; break;
        default:
            fprintf(stderr, "Usage: %s [-ilw] [file...]\n", argv[0]);
            exit(EXIT_FAILURE);
        }   
    }   

    // *argv points to the remaining non-option arguments.
    // If *argv is NULL, there were no non-option arguments.

    // ...
}   

Disclaimer: I am new to Argp, the example might contain errors.

Answer 3

I'm very surprised nobody brought up James Theiler's "opt" package.

You can find opt at http://public.lanl.gov/jt/Software/

and a flattering post with some examples of how it is so much simpler than other approaches is here:

http://www.decompile.com/not_invented_here/opt/

Answer 4

Use getopt(), or perhaps getopt_long().

int iflag = 0;
enum { WORD_MODE, LINE_MODE } op_mode = WORD_MODE;  // Default set
int opt;

while ((opt = getopt(argc, argv, "ilw") != -1)
{
    switch (opt)
    {
    case 'i':
        iflag = 1;
        break;
    case 'l':
        op_mode = LINE_MODE;
        break;
    case 'w':
        op_mode = WORD_MODE;
        break;
    default:
        fprintf(stderr, "Usage: %s [-ilw] [file ...]\n", argv[0]);
        exit(EXIT_FAILURE);
    }
}

/* Process file names or stdin */
if (optind >= argc)
    process(stdin, "(standard input)", op_mode);
else
{
    int i;
    for (i = optind; i < argc; i++)
    {
        FILE *fp = fopen(argv[i], "r");
        if (fp == 0)
            fprintf(stderr, "%s: failed to open %s (%d %s)\n",
                    argv[0], argv[i], errno, strerror(errno));
        else
        {
            process(fp, argv[i], op_mode);
            fclose(fp);
        }
    }
 }

Note that you need to determine which headers to include (I make it 4 that are required), and the way I wrote the op_mode type means you have a problem in the function process() - you can't access the enumeration down there. It's best to move the enumeration outside the function; you might even make op_mode a file-scope variable without external linkage (a fancy way of saying static) to avoid passing it to the function. This code does not handle - as a synonym for standard input, another exercise for the reader. Note that getopt() automatically takes care of -- to mark the end of options for you.

I've not run any version of the typing above past a compiler; there could be mistakes in it.

---

For extra credit, write a (library) function:

int filter(int argc, char **argv, int idx, int (*function)(FILE *fp, const char *fn));

which encapsulates the logic for processing file name options after the getopt() loop. It should handle - as standard input. Note that using this would indicate that op_mode should be a static file scope variable. The filter() function takes argc, argv, optind and a pointer to the processing function. It should return 0 (EXIT_SUCCESS) if it was able to open all the files and all invocations of the function reported 0, otherwise 1 (or EXIT_FAILURE). Having such a function simplifies writing Unix-style 'filter' programs that read files specified on the command line or standard input.

Answer 5

Tooting my own horn if I may, I'd also like to suggest taking a look at an option parsing library that I've written: dropt.

• It's a C library (with a C++ wrapper if desired).
• It's lightweight.
• It's extensible (custom argument types can be easily added and have equal footing with built-in argument types).
• It should be very portable (it's written in standard C) with no dependencies (other than the C standard library).
• It has a very unrestrictive license (zlib/libpng).

One feature that it offers that many others don't is the ability to override earlier options. For example, if you have a shell alias:

alias bar="foo --flag1 --flag2 --flag3"

and you want to use bar but with--flag1 disabled, it allows you to do:

bar --flag1=0

Answer 6

    /*
      Here's a rough one not relying on any libraries.
      Example:
      -wi | -iw //word case insensitive
      -li | -il //line case insensitive
      -- file  //specify the first filename (you could just get the files
      as positional arguments in the else statement instead)
      PS: don't mind the #define's, they're just pasting code :D
    */
    #ifndef OPT_H
    #define OPT_H

    //specify option requires argument
    #define require \
      optarg = opt_pointer + 1; \
      if (*optarg == '\0') \
      { \
        if (++optind == argc) \
          goto opt_err_arg; \
        else \
          optarg = argv[optind]; \
      } \
      opt_pointer = opt_null_terminator;

    //start processing argv
    #define opt \
    int   optind                 = 1; \
    char *opt_pointer            = argv[1]; \
    char *optarg                 = NULL; \
    char  opt_null_terminator[2] = {'\0','\0'}; \
    if (0) \
    { \
      opt_err_arg: \
        fprintf(stderr,"option %c requires argument.\n",*opt_pointer); \
        return 1; \
      opt_err_opt: \
        fprintf(stderr,"option %c is invalid.\n",*opt_pointer); \
        return 1; \
    } \
    for (; optind < argc; opt_pointer = argv[++optind]) \
      if (*opt_pointer++ == '-') \
      { \
        for (;;++opt_pointer) \
          switch (*opt_pointer) \
          {

    //stop processing argv
    #define done \
          default: \
            if (*opt_pointer != '\0') \
              goto opt_err_opt; \
            else \
              goto opt_next; \
            break; \
          } \
        opt_next:; \
      }
    #endif //opt.h

    #include <stdio.h>
    #include "opt.h"
    int
    main (int argc, char **argv)
    {
      #define by_character 0
      #define by_word      1
      #define by_line      2
      int cmp = by_character;
      int case_insensitive = 0;
      opt
      case 'h':
        puts ("HELP!");
        break;
      case 'v':
        puts ("fileCMP Version 1.0");
        break;
      case 'i':
        case_insensitive = 1;
        break;
      case 'w':
        cmp = by_word;
        break;
      case 'l':
        cmp = by_line;
        break;
      case '-':required
        printf("first filename: %s\n", optarg);
        break;
      done
      else printf ("Positional Argument %s\n", argv[optind]);
      return 0;
    }