/*
##########
#                                                                          
# cWCount.cpp
# version 1.00 
# MDJ 1999-05-15
#
# Common Words Count:
# Counts the number of common
# words in a specified text
# file.
#
# Common words = a, an, and, as, be, but, by, for, from,
#  he, her, him, his, I, in, is, it, me, my, not, of,
#  our, out, shall, she, that, the, their, them, they,
#  to, unto, up, upon, us, was, we, were, with, you.
#
# Copyright (c) 1999 by
# M. David Johnson
# BDS Software
# P.O. Box 485
# Glenview, IL 60025-0485
# Phone: 847-998-1656
# Fax:   847-657-8359
# Email: mdjohnson@worldnet.att.net
# Web:   http://www.bds-soft.com
# All Rights Reserved
#
##########
*/

// header files
#include <iostream.h>
#include <fstream.h>
#include <string>
#include <cstring>
#include <cstdio>
#include <cstdlib>

void zeroWH();
void parseWord();

// Global Variable declarations
FILE *fp;					// file pointer
char ch;					// character holder
char word[128];				// word holder
char maxWord[128] = "a";	// maximum length word holder
unsigned long cct = 0;		// run-of-file character counter
unsigned long wct = 0;		// run-of-file word counter
unsigned long maxWordLen;	// maximum word length

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

	// Check for command line entry of filename
	if (argc != 2) {
		cout << "\n\nERROR: Filename required on command line!\n\n";
		exit(1);
	}

	// Open file for counting
	fp = fopen (argv[1], "r");
	if (fp == NULL) {
		cout << "\n\nERROR: Could not open " << argv[1] << "!\n\n";
		exit(1);
	}
	
	// Common Word Counters declarations and initialization
	unsigned long aCounter = 0;
	unsigned long anCounter = 0;
	unsigned long andCounter = 0;
	unsigned long asCounter = 0;
	unsigned long beCounter = 0;
	unsigned long butCounter = 0;
	unsigned long byCounter = 0;
	unsigned long forCounter = 0;
	unsigned long fromCounter = 0;
	unsigned long heCounter = 0;
	unsigned long herCounter = 0;
	unsigned long himCounter = 0;
	unsigned long hisCounter = 0;
	unsigned long ICounter = 0;
	unsigned long inCounter = 0;
	unsigned long isCounter = 0;
	unsigned long itCounter = 0;
	unsigned long meCounter = 0;
	unsigned long myCounter = 0;
	unsigned long notCounter = 0;
	unsigned long ofCounter = 0;
	unsigned long ourCounter = 0;
	unsigned long outCounter = 0;
	unsigned long shallCounter = 0;
	unsigned long sheCounter = 0;
	unsigned long thatCounter = 0;
	unsigned long theCounter = 0;
	unsigned long theirCounter = 0;
	unsigned long themCounter = 0;
	unsigned long theyCounter = 0;
	unsigned long toCounter = 0;
	unsigned long untoCounter = 0;
	unsigned long upCounter = 0;
	unsigned long uponCounter = 0;
	unsigned long usCounter = 0;
	unsigned long wasCounter = 0;
	unsigned long weCounter = 0;
	unsigned long wereCounter = 0;
	unsigned long withCounter = 0;
	unsigned long youCounter = 0;
	
	// Do parsing and counting
	for (;;) {
		zeroWH();			// clear the word holder
		parseWord();		// parse out a word
		if ((strcmp(word, "a")) == 0) {
			aCounter++;
		}
		if ((strcmp(word, "an")) == 0) {
			anCounter++;
		}
		if ((strcmp(word, "and")) == 0) {
			andCounter++;
		}
		if ((strcmp(word, "as")) == 0) {
			asCounter++;
		}
		if ((strcmp(word, "be")) == 0) {
			beCounter++;
		}
		if ((strcmp(word, "but")) == 0) {
			butCounter++;
		}
		if ((strcmp(word, "by")) == 0) {
			byCounter++;
		}
		if ((strcmp(word, "for")) == 0) {
			forCounter++;
		}
		if ((strcmp(word, "from")) == 0) {
			fromCounter++;
		}
		if ((strcmp(word, "he")) == 0) {
			heCounter++;
		}
		if ((strcmp(word, "her")) == 0) {
			herCounter++;
		}
		if ((strcmp(word, "him")) == 0) {
			himCounter++;
		}
		if ((strcmp(word, "his")) == 0) {
			hisCounter++;
		}
		if ((strcmp(word, "i")) == 0) {
			ICounter++;
		}
		if ((strcmp(word, "in")) == 0) {
			inCounter++;
		}
		if ((strcmp(word, "is")) == 0) {
			isCounter++;
		}
		if ((strcmp(word, "it")) == 0) {
			itCounter++;
		}
		if ((strcmp(word, "me")) == 0) {
			meCounter++;
		}
		if ((strcmp(word, "my")) == 0) {
			myCounter++;
		}
		if ((strcmp(word, "not")) == 0) {
			notCounter++;
		}
		if ((strcmp(word, "of")) == 0) {
			ofCounter++;
		}
		if ((strcmp(word, "our")) == 0) {
			ourCounter++;
		}
		if ((strcmp(word, "out")) == 0) {
			outCounter++;
		}
		if ((strcmp(word, "shall")) == 0) {
			shallCounter++;
		}
		if ((strcmp(word, "she")) == 0) {
			sheCounter++;
		}
		if ((strcmp(word, "that")) == 0) {
			thatCounter++;
		}
		if ((strcmp(word, "the")) == 0) {
			theCounter++;
		}
		if ((strcmp(word, "their")) == 0) {
			theirCounter++;
		}
		if ((strcmp(word, "them")) == 0) {
			themCounter++;
		}
		if ((strcmp(word, "they")) == 0) {
			theyCounter++;
		}
		if ((strcmp(word, "to")) == 0) {
			toCounter++;
		}
		if ((strcmp(word, "unto")) == 0) {
			untoCounter++;
		}
		if ((strcmp(word, "up")) == 0) {
			upCounter++;
		}
		if ((strcmp(word, "upon")) == 0) {
			uponCounter++;
		}
		if ((strcmp(word, "us")) == 0) {
			usCounter++;
		}
		if ((strcmp(word, "was")) == 0) {
			wasCounter++;
		}
		if ((strcmp(word, "we")) == 0) {
			weCounter++;
		}
		if ((strcmp(word, "were")) == 0) {
			wereCounter++;
		}
		if ((strcmp(word, "with")) == 0) {
			withCounter++;
		}
		if ((strcmp(word, "you")) == 0) {
			youCounter++;
		}
		if (feof(fp) != 0) {
			break;				// exit if EOF
		}
	}

	// Close the file and open the report file
	fclose(fp);
	FILE *fpR;
	char *rFilename = "cWReport.txt";
	fpR = fopen(rFilename, "w");
	if (fpR == NULL) {
		cout << "\n\nError: Could not open " << rFilename << "\n\n";
		exit(1);
	}
	
	// Output the report to the report file
	fprintf(fpR, "    a = %u \n", aCounter);
	fprintf(fpR, "   an = %u \n", anCounter);
	fprintf(fpR, "  and = %u \n", andCounter);
	fprintf(fpR, "   as = %u \n", asCounter);
	fprintf(fpR, "   be = %u \n", beCounter);
	fprintf(fpR, "  but = %u \n", butCounter);
	fprintf(fpR, "   by = %u \n", byCounter);
	fprintf(fpR, "  for = %u \n", forCounter);
	fprintf(fpR, " from = %u \n", fromCounter);
	fprintf(fpR, "   he = %u \n", heCounter);
	fprintf(fpR, "  her = %u \n", herCounter);
	fprintf(fpR, "  him = %u \n", himCounter);
	fprintf(fpR, "  his = %u \n", hisCounter);
	fprintf(fpR, "    I = %u \n", ICounter);
	fprintf(fpR, "   in = %u \n", inCounter);
	fprintf(fpR, "   is = %u \n", isCounter);
	fprintf(fpR, "   it = %u \n", itCounter);
	fprintf(fpR, "   me = %u \n", meCounter);
	fprintf(fpR, "   my = %u \n", myCounter);
	fprintf(fpR, "  not = %u \n", notCounter);
	fprintf(fpR, "   of = %u \n", ofCounter);
	fprintf(fpR, "  our = %u \n", ourCounter);
	fprintf(fpR, "  out = %u \n", outCounter);
	fprintf(fpR, "shall = %u \n", shallCounter);
	fprintf(fpR, "  she = %u \n", sheCounter);
	fprintf(fpR, " that = %u \n", thatCounter);
	fprintf(fpR, "  the = %u \n", theCounter);
	fprintf(fpR, "their = %u \n", theirCounter);
	fprintf(fpR, " them = %u \n", themCounter);
	fprintf(fpR, " they = %u \n", theyCounter);
	fprintf(fpR, "   to = %u \n", toCounter);
	fprintf(fpR, " unto = %u \n", untoCounter);
	fprintf(fpR, "   up = %u \n", upCounter);
	fprintf(fpR, " upon = %u \n", uponCounter);
	fprintf(fpR, "   us = %u \n", usCounter);
	fprintf(fpR, "  was = %u \n", wasCounter);
	fprintf(fpR, "   we = %u \n", weCounter);
	fprintf(fpR, " were = %u \n", wereCounter);
	fprintf(fpR, " with = %u \n", withCounter);
	fprintf(fpR, "  you = %u \n\n", youCounter);
	fprintf(fpR, "    total words = %u \n\n", wct - 1);
	fprintf(fpR, "max word length = %u \n\n", maxWordLen);
	fprintf(fpR, "max word        = %s\n", maxWord);

	// Close the report file and indicate completion
	fclose(fpR);
	cout << "\nReport Complete\n\n";

	return(0);
}

/*
##########
#
# zeroWH
# MDJ 1999-05-15
#
# Zero the global word holder
# and the global character count
#
##########
*/

void zeroWH() {
	for (int i = 0; i < 128; i++) {
		word[i] = 0;
	}
	cct = 0;
}

/*
##########
#
# parseWord
# MDJ 1999-05-15
#
# Parse a word from the document
#
# Characters:
#	ASCII 39     = '
#	ASCII 45     = -
#   ASCII 48-57  = 0-9
#   ASCII 65-90  = A-Z
#	ASCII 97-122 = a-z
#
# All other ASCII values
#	= whitespace
#
##########
*/

void parseWord() {
	for (;;) {
		ch = fgetc(fp);			// get a character
		if (feof(fp) != 0) {
			break;				// exit if EOF
		}
		
		// Skip leading whitespace
		if ((cct == 0)                   &&
			(ch != 39)                   &&
			(ch != 45)                   &&
			(!((ch > 47) && (ch < 58)))  &&
			(!((ch > 64) && (ch < 91)))  &&
			(!((ch > 96) && (ch < 123)))) {
				continue;
		}
		
		// Add characters to word holder
		if ((ch == 39)                ||
			(ch == 45)                ||
			((ch > 47) && (ch < 58))  ||
			((ch > 64) && (ch < 91))  ||
			((ch > 96) && (ch < 123))) {
				if ((ch > 64) && (ch < 91)) {
					ch += 32;	// convert to lower case
				}
				word[cct] = ch;
				cct++;
				continue;
		}
		
		// End-of-word at whitespace
		if ((cct) > maxWordLen) {
			maxWordLen = cct;			// new max word length
			strcpy(maxWord, word);		// new max word
		}
		wct++;							// increment word counter
		if ((wct % 10000) == 0) {
			cout << wct << "\n";		// progress counter
		}
		break;
	}
}

/*
##########
#
# end of cWCount.cpp
#
##########
*/