C language: split lines by tabs (strtok() and fgets() usage)

Subject: show how to split lines by tabs using strtok() and fgets() function calls in C-language (C99).

Usage: compile source C-code (for example, with M$ Visual Studio or with GCC)

and run it with one option: the name of file (like <the name of program> <the name of file>).

//------- the start of the C code -------

/********************************************************************* * Author: Stepan A. Baranov (rosmir@gmail.com) * web-site: www.rosmir.org *********************************************************************/ #include <stdio.h> #include <stdlib.h> #include <string.h> #include <limits.h> #if defined(_MSC_VER) // M$ Visual Studio #pragma warning (disable: 4996) #define LINE_MAX 0x4000 #endif int main (int argc, const char *argv[]) { int i = 1, j =1, size; char line[LINE_MAX], *tl, seps[] = "\t"; FILE *fp; if (argc != 2) return EXIT_FAILURE; fp = fopen (argv[1], "rb"); if (fp == NULL) return EXIT_FAILURE; fseek (fp, 0, SEEK_SET); while (fgets (line, LINE_MAX, fp) != NULL) { size = strlen (line); if (line[size-1] == 10) { line[size-1] = '\0'; if (line[size-2] == 13) line[size-2] = '\0'; } printf ("line %i (%i): %s\n", i++, (int) strlen (line), line); for (tl = strtok (line, seps); tl; tl = strtok (NULL, seps)) { printf ("(%i:%s) ", j++, tl); } printf ("\n"); j = 1; } return EXIT_SUCCESS; }

//------- the end of the C code -------

NOTE! the end-of-line (EOL) characters on various platforms:

Platform - Characters - ASCII Codes

Macintosh - \r - 13

Unix - \n - 10

Windows - \r\n - 13 10

DOS - \n\r - 10 13

NOTE! fgets() doesn't work correctly with Macintosh or DOS newline characters (see: link)

NOTE! fgets() keeps all new line symbols: the newline, if any, is retained.