# HG changeset patch
# User indvdum
# Date 1308687983 -14400
# Node ID d81f7add59f6a68ab9aceba0cf6e7144a0e9ed38
# Parent  37eab168f50c6d3beb4bd403b854d32ebb350c1f
 0.2.0 release

diff -r 37eab168f50c -r d81f7add59f6 email-filter.pl
--- a/email-filter.pl	Tue Jun 21 18:54:22 2011 +0400
+++ b/email-filter.pl	Wed Jun 22 00:26:23 2011 +0400
@@ -1,4 +1,10 @@
 #!/usr/bin/perl
+
+# E-mail filter tool for Aptech
+# version 0.2.0
+# Copyright 2011, David Veliev (gotoindvdum@gmail.com).
+# This program may be used under Apache License 2.0.
+
 use strict;
 
 # Глобальные переменные
@@ -6,6 +12,7 @@
 my $isRemoveDuplicates = 0;
 my $isSplitByDomens = 0;
 my $excludeDomen;
+my $outputFile;
 
 parseCommandLine();
 processFile();
@@ -28,11 +35,16 @@
 				$isRemoveDuplicates = 1;
 			} elsif ($arg eq '--split-by-domens'){
 				$isSplitByDomens = 1;
-			} elsif ($arg =~ /--exclude-domen[=]{0,1}(\w*)/){
+			} elsif ($arg =~ /--exclude-domen[=]{0,1}([\.\w]*)/){
 				$excludeDomen = $1;
-				illegalUse() if $excludeDomen ne '' && $arg !~ /--exclude-domen=\w*/;
+				illegalUse() if $excludeDomen ne '' && $arg !~ /--exclude-domen=[\.\w]*/;
 				$excludeDomen = shift(@ARGV) if $excludeDomen eq '';
 				illegalUse() if $excludeDomen eq '';
+			} elsif ($arg =~ /--output-file[=]{0,1}([\.\w]*)/){
+				$outputFile = $1;
+				illegalUse() if $outputFile ne '' && $arg !~ /--output-file=[\.\w]*/;
+				$outputFile = shift(@ARGV) if $outputFile eq '';
+				illegalUse() if $outputFile eq '';
 			} else {
 				illegalUse();
 			}
@@ -52,7 +64,7 @@
 sub about {
 	my $about = q {
 E-mail filter tool for Aptech
-version 0.1
+version 0.2.0
 
 Copyright 2011, David Veliev (gotoindvdum@gmail.com).
 
@@ -69,11 +81,12 @@
 Parse for e-mails file FILENAME with arguments KEYS and print result to standart output stream.
 
 Arguments:
-    --help                      print this help
-    --version                   print version and information about this script
-    --remove-duplicates         remove e-mail duplicates
-    --split-by-domens           split e-mails by domens
-    --exclude-domen[=]DOMEN     exclude e-mails with domen DOMEN
+    --help                          print this help
+    --version                       print version and information about this script
+    --remove-duplicates             remove e-mail duplicates
+    --split-by-domens               split e-mails by domens
+    --exclude-domen[=]DOMEN         exclude e-mails with domen DOMEN
+    --output-file[=]OUTFILENAME     redirect standart output to this file
 };
 	print $help;
 }
@@ -90,8 +103,36 @@
 	open FILE, $fileName or die "Failed to open $fileName: $!\n";
 	my @emails;
 	while(<FILE>){
-		my (@test) = $_ =~ /.*(\w@\w\.\w)*.*/;
-		print @test; 
+		push @emails, $1 while s/([\.\w]+@[\.\w]+)//;
 	}
 	close FILE;
+	if($isRemoveDuplicates){
+		my %tmp;
+		@emails = grep {! $tmp{$_}++} @emails;
+	}
+	if($excludeDomen){
+		@emails = grep {
+			$1 ne $excludeDomen if $_ =~ /[\.\w]+@([\.\w]+)/;
+		} @emails;
+	}
+	if($isSplitByDomens){
+		@emails = sort {
+			my $a_domen = $1 if $a =~ /[\.\w]+@([\.\w]+)/;
+			my $b_domen = $1 if $b =~ /[\.\w]+@([\.\w]+)/;
+			$a_domen cmp $b_domen;
+		} @emails;
+		my @tmp;
+		my %tmp;
+		while($#emails >= 0){
+			my $email = shift @emails;
+			my $domen = $1 if $email =~ /[\.\w]+@([\.\w]+)/;
+			push @tmp, '' if !$tmp{$domen}++;
+			push @tmp, $email;
+		}
+		@emails = @tmp;
+	}
+	if($outputFile){
+		open STDOUT, ">$outputFile" or die "Failed to open $outputFile: $!\n";
+	}
+	print "$_\n" for (@emails);
 }
\ No newline at end of file