# Status - Program flow seems to be correct.  Program IO seems correct.  Program connectivity seems correct.
# Issue with string evaluation. Program will not return a match if there if anything MORE than a correct match... 
# i.e. - if $SearchTerms = "blue monkies" and the only thing in the body of the email is "blue monkies" it returns
# a match.  But if the body of the email reads "maroon baboons are not blue monkies" no match is returned.
# 1/17/2012 - JLC



# MailCrawl uses 3 arguments:  -h <host> -u <username> -p <password>

# There is a hard coded path to Search_Terms.txt assigned to $InFile.  This is the file containing search terms.  
# Needs to be a standard text file with one search term per line.

# Emails matching the search criteria are saved in a raw text file Email.<Date>.txt.  Path is hard coded to $OutFile



#!/bin/perl

# import packages
use Net::POP3;
use Getopt::Long;
use strict;
use warnings;



# Declare variables
my $Sec;
my $Min;
my $Hour;
my $MDay;
my $Mon;
my $Year;
my $WDay;
my $YDay;
my $IsDst;
my $Today;
my $InFile;
my $OutFile;
my @SearchTerms;
my $Host;
my $User;
my $Pass;
my $NumMsg;
my $MsgCount;
my $SearchTerms;
my $Msg;
my $MsgList;
my $TermNum;
my $TermCount;
my $Ref;



# Get todays date to be used in output file name

($Sec,$Min,$Hour,$MDay,$Mon,$Year,$WDay,$YDay,$IsDst) =  localtime(time);
     $Year += 1900;
     $Mon++;
     $Today = "$Mon.$MDay.$Year";
     


# Set file paths

$InFile = 'H:\Tools\MailCrawl\Search_Terms.txt';
$OutFile = 'H:\Tools\MailCrawl\Email_Files\Email.'. $Today . '.txt';




# Load search terms from file into @SearchTerms array

open (SearchTerms, "<$InFile") or die "(ERROR: Unable to open Search_Terms).\n";

@SearchTerms = <SearchTerms>;



close (SearchTerms); 



# read command line options
# display usage message in case of error
GetOptions ('h|host=s' => \$Host,
            'u|user=s' => \$User,
            'p|pass=s' => \$Pass) or die("Input error. Try calling me with: -h <host> -u <username> -p <password>");

# initiate connection
# default timeout = 120 sec
my $conn = Net::POP3->new($Host) or die("ERROR: Unable to connect.\n");

# login
$NumMsg = $conn->login($User, $Pass) or die("ERROR: Unable to login.\n");



# $MsgCount used to show current message being evaluated

$MsgCount=0;


# get message numbers
# iterate over list and print each

if ($NumMsg > 0) {
    $MsgList = $conn->list();
    
    	# Loop for each email msg
    	foreach $Msg (keys(%$MsgList)) {
        
        	# Set variables to be displayed to show search status
        	$TermNum = @SearchTerms;
        	$TermCount = 0;
        	$MsgCount++;
        
           	$Ref = $conn->get($Msg);
        	
        		# Loop for each search term
        		for $SearchTerms (@SearchTerms){
        		
        			$TermCount++;
        			print "searching msg $MsgCount of $NumMsg for $SearchTerms...\n"; 
        			
        				# If match was found, write email to file
        				if (@$Ref ~~ /$SearchTerms/i) {
        					open (EmailFile, ">>$OutFile");
        					print EmailFile "@$Ref \n";
        					close (EmailFile);
        				}
        		}
    	}
} else {
    print "Mailbox is empty.\n";
}

# close connection
$conn->quit();