Parsing command-line arguments?

Question

Hi 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. and if the option is -i it compares them in a case insensitive manner. Otherwise it 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 1

Instructional template for parsing command line arguments in C.

C:>programName -w -- fileOne.txt fileTwo.txt

BOOL argLine = FALSE;
BOOL argWord = FALSE;
BOOL argChar = FALSE;
char * fileName1 = NULL;
char * fileName2 = NULL;

int main(int argc, char * argv[]) {
    int i;
    printf("Argument count=%d\n",argc);
    for (i = 0; i < argc; i++) {
        printf("Argument %s\n",argv[i]);
        if (strcmp(argv[i],"-l")==0) {
            argLine = TRUE;
            printf("    argLine=TRUE\n");
        }
        else if (strcmp(argv[i],"-w")==0) {
            argWord = TRUE;
            printf("    argWord=TRUE\n");
        }
        else if (strcmp(argv[i],"-c")==0) {
            argChar = TRUE;
            printf("    argChar=TRUE\n");
        }
        else if (strcmp(argv[i],"--")==0) {
            if (i+1 <= argc) {
                fileName1 = argv[++i];
                printf("    fileName1=%s\n",fileName1);
            }
            if (i+1 <= argc) {
                fileName2 = argv[++i];
                printf("    fileName2=%s\n",fileName2);
            }
        }
    }
    return 0;
}

Answer 2

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 3

#include <stdio.h>

int main(int argc, char **argv)
{
    size_t i;
    size_t filename_i = -1;

    for (i = 0; i < argc; i++)
    {
        char const *option =  argv[i];
        if (option[0] == '-')
        {
            printf("I am a flagged option");
            switch (option[1])
            {
                case 'a':
                    /*someting*/
                    break;
                case 'b':
                    break;
                case '-':
                    /* "--" -- the next argument will be a file.*/
                    filename_i = i;
                    i = i + 1;
                    break;
                default:
                    printf("flag not recognised %s", option);
                    break;
            }
        }
        else
        {   
            printf("I am a positional argument");
        }

        /* At this point, if -- was specified, then filename_i contains the index
         into argv that contains the filename. If -- was not specified, then filename_i will be -1*/
     }
  return 0;
}

Answer 4

    /*
      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;
    }

Answer 5

I've found Gengetopt to be quite useful - you specify the options you want with a simple configuration file, and it generates a .c/.h pair that you simply include and link with your application. The generated code makes use of getopt_long, appears to handle most common sorts of command line parameters, and it can save a lot of time.

A gengetopt input file might look something like this:

version "0.1"
package "myApp"
purpose "Does something useful."

# Options
option "filename" f "Input filename" string required
option "verbose" v "Increase program verbosity" flag off
option "id" i "Data ID" int required
option "value" r "Data value" multiple(1-) int optional 

Generating the code is easy and spits out cmdline.h and cmdline.c:

$ gengetopt --input=myApp.cmdline --include-getopt

The generated code is easily integrated:

#include <stdio.h>
#include "cmdline.h"

int main(int argc, char ** argv) {
  struct gengetopt_args_info ai;
  if (cmdline_parser(argc, argv, &ai) != 0) {
    exit(1);
  }
  printf("ai.filename_arg: %s\n", ai.filename_arg);
  printf("ai.verbose_flag: %d\n", ai.verbose_flag);
  printf("ai.id_arg: %d\n", ai.id_arg);
  int i;
  for (i = 0; i < ai.value_given; ++i) {
    printf("ai.value_arg[%d]: %d\n", i, ai.value_arg[i]);
  }
}

If you need to do any extra checking (such as ensuring flags are mutually exclusive), you can do this fairly easily with the data stored in the gengetopt_args_info struct.

Answer 6

Okay that's the start of long story - made short 'bort parsing a command line in C ...

/**
* Helper function to parse the command line
* @param argc Argument Counter
* @param argv Argument Vector
* @param prog Program Instance Reference to fill with options
*/
bool parseCommandLine(int argc, char* argv[], DuplicateFileHardLinker* prog) {
  bool pathAdded = false;

  // iterate over all arguments...
  for ( int i = 1; i<argc; i++ ) {

    // is argv a command line option ?
    if ( argv[i][0] == '-' || argv[i][0] == '/' ) {

// ~~~~~~ Optionally Cut that part vvvvvvvvvvvvv for sake of simplicity ~~~~~~~
      // check for longer options
            if ( stricmp( &argv[i][1], "NoFileName"  ) == 0
              ||  strcmp( &argv[i][1], "q1"          ) == 0 ) {

        boNoFileNameLog = true;
      } else if ( strcmp( &argv[i][1], "HowAreYou?"    ) == 0 ) {
          logInfo( "SECRET FOUND: Well - wow I'm glad ya ask me.");
      } else {

// ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
// Now here comes the main thing:
//
        // check for one char options
        while ( char option = *++argv[i] ) {

          switch ( option ) {
          case '?':
            // Show program usage

            logInfo(L"Options:");
            logInfo(L"  /q\t>Quite mode");
            logInfo(L"  /v\t>Verbose mode");
            logInfo(L"  /d\t>Debug mode");
            return false;

            // Log options
          case 'q':
            setLogLevel(LOG_ERROR);
            break;

          case 'v':
            setLogLevel(LOG_VERBOSE);
            break;

          case 'd':
            setLogLevel(LOG_DEBUG);
            break;

          default:
            logError(L"'%s' is an illegal command line option!"
                      "  Use /? to see valid options!", option);
            return false;
          } // switch one-char-option
        } //while one-char-options
      }  //else one vs longer options
    } // if isArgAnOption

// 
// ^^^^^^^^^^^^^^^^^^^^^^^^^^^  So that's it! ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
// What follows now is are some usefull extras...
//
    else {


      // the command line options seems to be a path...
      WCHAR tmpPath[MAX_PATH_LENGTH];
      mbstowcs(tmpPath, argv[i], sizeof(tmpPath));

      // check if the path is existing!
      //...

      prog->addPath(tmpPath); //Comment or remove to get a working example
      pathAdded = true;
    }
  }

  // check for parameters
  if ( !pathAdded ) {
    logError("You need to specify at least one folder to process!\n"
             "Use /? to see valid options!");
    return false;
  }

  return true;
}



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

  try {
    // parse the command line
    if ( !parseCommandLine(argc, argv, prog) ) {
      return 1; 
    }

// I know that sample is just to show how the nicely parse commandline Arguments
// So Please excuse more nice useful C-glatter that follows now...
  }
  catch ( LPCWSTR err ) {
    DWORD dwError = GetLastError();
    if ( wcslen(err) > 0 ) {
      if ( dwError != 0 ) {
        logError(dwError, err);
      }
      else {
        logError(err);
      }
    }
    return 2;
  }
}

#define LOG_ERROR               1
#define LOG_INFO                0
#define LOG_VERBOSE             -1
#define LOG_DEBUG               -2

/** Logging Level for the console output */
int logLevel = LOG_INFO;

void logError(LPCWSTR message, ...) {
  va_list argp;
  fwprintf(stderr, L"ERROR: ");
  va_start(argp, message);
  vfwprintf(stderr, message, argp);
  va_end(argp);
  fwprintf(stderr, L"\n");
}


void logInfo(LPCWSTR message, ...) {
  if ( logLevel <= LOG_INFO ) {
    va_list argp;
    va_start(argp, message);
    vwprintf(message, argp);
    va_end(argp);
    wprintf(L"\n");
  }
}

Note that this version will also support combining arguments: So instead of writing /h /s -> /hs will also work.

Sorry for being the n-th person posting here - however I wasn't really satisfied with all the stand-alone-versions I saw here. Well the lib ones are quit nice. So I would prefere libUCW option parser, Arg or Getopt over a home-made ones.

Note you may change:

*++argv[i] -> (++argv*)[0] longer less cryptic but still cryptic.

Okay let's break it down: 1. argv[i]-> access i-th element in the argv-char pointer field

2. ++*... -> will forward the argv-pointer by one char

3. ... [0]-> will follow the pointer read the char

4. ++(...) -> bracket are there so we'll increase the pointer and not the char value itself.

So nice that In C## the pointers 'died' - long live the pointers !!!