Parsing command-line arguments in C?

user1251020 picture user1251020 · Mar 10, 2012 · Viewed 166.1k times · Source

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 -l -w -i or --...

  • if the option is -l it compares the files line by line.
  • if the option is -w it compares the files word by word.
  • if the options is -- it automatically assumes that the next arg is the first filename.
  • if the option is -i it compares them in a case insensitive manner.
  • defaults to comparing the files character by character.

It's not supposed to matter how many time the options are input as long as -w and -l aren't inputted at the same time and there are no more or less than 2 files.

I don't even know where to begin with parsing the command line arguments. PLEASE HELP :(

So this is the code that I came up with for everything. I haven't error checked it quite yet, but I was wondering if I'm writing things in an overcomplicated manner?

/*
 * Functions to compare files.
 */
int compare_line();
int compare_word();
int compare_char();
int case_insens();

/*
 * Program to compare the information in two files and print message saying 
 * whether or not this was successful.
 */
int main(int argc, char* argv[])
{
/*Loop counter*/
  size_t i = 0;

  /*Variables for functions*/
  int caseIns = 0;
  int line = 0;
  int word = 0;

  /*File pointers*/
  FILE *fp1, *fp2;

  /*
   * Read through command-line arguments for options.
   */
  for (i = 1; i < argc; i++) {
    printf("argv[%u] = %s\n", i, argv[i]);
    if (argv[i][0] == '-') {
       if (argv[i][1] == 'i') 
       {
           caseIns = 1;
       }
       if (argv[i][1] == 'l')
       {
           line = 1;
       }
       if (argv[i][1] == 'w')
       {
           word = 1;
       }
       if (argv[i][1] == '-')
       {
           fp1 = argv[i][2];
           fp2 = argv[i][3];
       }
       else 
       {
           printf("Invalid option.");
           return 2;
       }
    } else {
       fp1(argv[i]);
       fp2(argv[i][1]);
    }
  }

  /*
   * Check that files can be opened.
   */
  if(((fp1 = fopen(fp1, "rb")) ==  NULL) || ((fp2 = fopen(fp2, "rb")) == NULL))
  {
      perror("fopen()");
      return 3;
  }
  else{
        if (caseIns == 1)
        {
            if(line == 1 && word == 1)
            {
                printf("That is invalid.");
                return 2;
            }
            if(line == 1 && word == 0)
            {
                if(compare_line(case_insens(fp1, fp2)) == 0)
                        return 0;
            }
            if(line == 0 && word == 1)
            {
                if(compare_word(case_insens(fp1, fp2)) == 0)
                    return 0;
            }
            else
            {
                if(compare_char(case_insens(fp1,fp2)) == 0)
                    return 0;
            }
        }
        else
        {
            if(line == 1 && word == 1)
            {
                printf("That is invalid.");
                return 2;
            }
            if(line == 1 && word == 0)
            {
                if(compare_line(fp1, fp2) == 0)
                    return 0;
            }
            if(line == 0 && word == 1)
            {
                if(compare_word(fp1, fp2) == 0)
                    return 0;
            }
            else
            {
                if(compare_char(fp1, fp2) == 0)
                    return 0;
            }
        }

  }
    return 1;
    if(((fp1 = fclose(fp1)) == NULL) || (((fp2 = fclose(fp2)) == NULL)))
        {
            perror("fclose()");
            return 3;
        }
        else
        {
            fp1 = fclose(fp1);
            fp2 = fclose(fp2);
        }
}

/*
 * Function to compare two files line-by-line.
 */
int compare_line(FILE *fp1, FILE *fp2)
{
    /*Buffer variables to store the lines in the file*/
    char buff1 [LINESIZE];
    char buff2 [LINESIZE];

    /*Check that neither is the end of file*/
    while((!feof(fp1)) && (!feof(fp2)))
    {
        /*Go through files line by line*/
        fgets(buff1, LINESIZE, fp1);
        fgets(buff2, LINESIZE, fp2);
    }
    /*Compare files line by line*/
    if(strcmp(buff1, buff2) == 0)
    {
        printf("Files are equal.\n");
        return 0;
    }
    printf("Files are not equal.\n");
    return 1;
}   

/*
 * Function to compare two files word-by-word.
 */
int compare_word(FILE *fp1, FILE *fp2)
{
    /*File pointers*/
    FILE *fp1, *fp2;

    /*Arrays to store words*/
    char fp1words[LINESIZE];
    char fp2words[LINESIZE];

    if(strtok(fp1, " ") == NULL || strtok(fp2, " ") == NULL)
    {
        printf("File is empty. Cannot compare.\n");
        return 0;
    }
    else
    {
        fp1words = strtok(fp1, " ");
        fp2words = strtok(fp2, " ");

        if(fp1words == fp2words)
        {
            fputs(fp1words);
            fputs(fp2words);
            printf("Files are equal.\n");
            return 0;
        }
    }
    return 1;
}

/*
 * Function to compare two files character by character.
 */
int compare_char(FILE *fp1,FILE *fp2)
{
    /*Variables to store the characters from both files*/
    int c;
    int d;

    /*Buffer variables to store chars*/
    char buff1 [LINESIZE];
    char buff2 [LINESIZE];

    while(((c = fgetc(fp1))!= EOF) && (((d = fgetc(fp2))!=EOF)))
    {
        if(c == d)
        {
            if((fscanf(fp1, "%c", buff1)) == (fscanf(fp2, "%c", buff2)))
            {
                printf("Files have equivalent characters.\n");
                return 1;
                break;
            }
        }

    }
        return 0;
}

/*
 * Function to compare two files in a case-insensitive manner.
 */
int case_insens(FILE *fp1, FILE *fp2, size_t n)
{
    /*Pointers for files.*/
    FILE *fp1, *fp2;

    /*Variable to go through files.*/
    size_t i = 0;

    /*Arrays to store file information.*/
    char fp1store[LINESIZE];
    char fp2store[LINESIZE];

    while(!feof(fp1) && !feof(fp2))
    {
         for(i = 0; i < n; i++)
         {
                fscanf(fp1, "%s", fp1store);
                fscanf(fp2, "%s", fp2store);

                fp1store = tolower(fp1store);
                fp2store = tolower(fp2store);

                return 1;
         }
    }
    return 0;
}

Answer

Christian Hujer picture Christian Hujer · Jun 29, 2014

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.

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 = "<[email protected]>";
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.