contencleaner - SOURCE CODE

#!/usr/bin/perl


open(RH,"<synonym-en.txt");

	while(<RH>){
		
		my $string	= $_;
		
		chomp($string);

		$string		=~ s/^\s+//;
		$strlen		= length $string;

		next if ( $strlen == 0 );
		
		if ( $string !~ /,/g ) {
			$mainword = $string; 
		} else {
			
			$string =~ s/ , /,/ig; $string =~ s/ ,/,/ig; $string =~ s/, /,/ig;
			$string	=~ s/\s+/ /;
			if ( $string !~ /\w+\./ ) {
				print "$mainword,$string\n";
			};

		}; 
		

	# print "[$strlen] $string\n";
	# sleep 1;

	}; # while(<RH>){

close RH;

#!/usr/bin/perl

# derb muss raus
# (vulgr) muss raus
# eintrg mit leerzeichen ohne klammern, dieser einzelne eintrag muss raus
# ; (...) wort; -> eintrag: raus
# taktil;Tast...;tastend : 3 punkte raus
# erstes zeichen klammer: dieser eintrag raus: (Zeit) verflieen;ablaufen;vergehen;verlaufen;vorbeigehen -> ablaufen;vergehen;verlaufen;vorbeigehen

open(RH,"<thesaurus.txt");

	while(<RH>){
		
		my $string	= $_;
		my $rstring;

		chomp;
		$strlen		= length $string;
		next if ( $strlen == 0 );

		
		if ( $string =~ /^\(/ ) {
			$rstring = &ReturnValidString($_, 1);
		} else {
			$rstring = &ReturnValidString($_, 2);
		};

		if ( length $rstring > 0 ) { # && $rstring !~ /\,{2,}/ ) {
		#	print "RETURN: $rstring\n";
			print "$rstring\n";
		};

	#	if ( $string !~ /,/g ) {
	#		$mainword = $string; 
	#	} else {
	#		
	#		$string =~ s/ , /,/ig; $string =~ s/ ,/,/ig; $string =~ s/, /,/ig;
	#		$string	=~ s/\s+/ /;
	#		if ( $string !~ /\w+\./ ) {
	#			print "$mainword,$string\n";
	#		};
	#
	#	}; 
		

	#	sleep 1;

	}; # while(<RH>){

close RH;

... [truncated, 70 more lines] ...

use Lingua::DE::Wortschatz;
use Data::Dumper;
use utf8;
use encoding 'utf8';

# /usr/lib/perl5/site_perl/5.8.7/Lingua/DE/Wortschatz.pm

my $wort = "haus";
#  my $result=Lingua::DE::Wortschatz::use_service('Sentences','voll');
my $result=Lingua::DE::Wortschatz::use_service('Thesaurus',$wort);
@lines=$result->hashrefs();
my $AdditionSynonymEntryForDatabase = "$wort,";
foreach (@lines) {
	my $syn = $_->{Synonym};
	$AdditionSynonymEntryForDatabase .= "$syn," if ( length $syn >= 4);
};

chop $AdditionSynonymEntryForDatabase;
print "NEW: '$AdditionSynonymEntryForDatabase'\n";

my $tmp	= @lines[ int(rand($#lines)) ];
my $SynReplace	= $tmp->{Synonym};

print "\n$SynReplace\n";
# opensubtitles.org: 2ge@2ge.us

#!/usr/bin/perl

# perl -MCPAN -e 'force install "XML::Amazon"'
# perl -MCPAN -e 'force install "Net::Amazon"'
# perl -MCPAN -e 'force install "Cache::File"'
# perl -MCPAN -e 'force install "XML::Simple"'
# perl -MCPAN -e 'force install "Cache::File"'

#use utf8;
#use encoding 'utf8';
# use encoding "latin-1";

use Data::Dumper;

use strict;
use Encode;
use Cache::File;
use Net::Amazon;
use Net::Amazon::Request::Artist;
use Lingua::DE::Sentence;

my @AmazonSenctences		= ();
my $MaxAmazonRecursive		= 5;
my $MaxAmazonSentences		= 20;
my $AmazonTempPath			= "/tmp/amazon";

my $RandomSen			= &AmazonGetSentences("Harry Potter");


sub AmazonGetSentences(){
	
	my $SearchQuery		= shift;
	my @RandomSentences	= ();

	my $cache = Cache::File->new( 
		cache_root        => '/tmp/mycache',
		default_expires   => '20160 min',		# 60 * 24 * 14 = 20160
	);

	my $ua = Net::Amazon->new(
		token => "1YRE8RQWEYZ6AZ1E65R2",
		locale      => 'de',					#  locale => 'us'
		cache       => $cache,
	);

	my $resp = $ua->search(
		artist => "Harry Potter",
	);

	if ( $resp->is_success() ) {

... [truncated, 115 more lines] ...

#!/usr/bin/perl
use strict;
use warnings;

# findDupeFiles:
# This script attempts to identify which files might be duplicates.
# It searches specified directories for files with a given suffix
# and reports on files that have the same MD5 digest.
# The suffix or suffixes to be searched for are specified by the first 
# command-line argument - each suffix separated from the next by a vertical bar.
# The subsequent command-line arguments specify the directories to be searched.
# If no directories are specified on the command-line, 
# it searches the current directory.
# Files whose names start with "._" are ignored.
#
# Cameron Hayne (macdev@hayne.net)  January 2006
#
#
# Examples of use:
# ----------------
# findDupeFiles '.aif|.aiff' AAA BBB CCC
# would look for duplicates among all the files with ".aif" or ".aiff" suffixes
# under the directories AAA, BBB, and CCC
#
# findDupeFiles '.aif|.aiff'
# would look for duplicates among all the files with ".aif" or ".aiff" suffixes
# under the current directory
#
# findDupeFiles '' AAA BBB CCC
# would look for duplicates among all the files (no matter what suffix)
# under the directories AAA, BBB, and CCC
#
# findDupeFiles
# would look for duplicates among all the files (no matter what suffix)
# under the current directory
# -----------------------------------------------------------------------------


use File::Find;
use File::stat;
use Digest::MD5;

my $matchSomeSuffix; # reference to a subroutine for matching suffixes
if (defined($ARGV[0]))
{
    # the list of desired suffixes is supplied in $ARGV[0]
    # separated by vertical bars - e.g. ".mp3|.aiff"
    # Note that if $ARGV[0] is '', then all files will be looked at
    
    my @suffixes = split(/\|/, $ARGV[0]);

... [truncated, 112 more lines] ...

use Lingua::EN::Inflect;


$word  = "the";
# UNCONDITIONALLY FORM THE PLURAL
print "The plural of house is ", Lingua::EN::Inflect::PL($word), "\n";


# ADD CORRECT "a" OR "an" FOR A GIVEN WORD:

print "Did you want ", Lingua::EN::Inflect::A($word), "\n";


# CONVERT NUMERALS TO WORDS (i.e. 1->"one", 101->"one hundred and one", etc.)
 # IN A SCALAR CONTEXT: GET BACK A SINGLE STRING...

# $words = NUMWORDS(1234);      # "one thousand, two hundred and thirty-four"
# $words = NUMWORDS(ORD(1234)); # "one thousand, two hundred and thirty-fourth"


 # IN A LIST CONTEXT: GET BACK A LIST OF STRINGSi, ONE FOR EACH "CHUNK"...

 #@words = NUMWORDS(1234);    # ("one thousand","two hundred and thirty-four")

use Lingua::EN::Inflect;

$zahl = "[asd]";
my $text = Lingua::EN::Inflect::NUMWORDS($zahl);

print $text;

use Lingua::DE::Num2Word;
my $text = Lingua::DE::Num2Word::num2de_cardinal( w );

print $text || "sorry, can't convert this number into german language.";

use Lingua::DE::ASCII;
  print to_ascii("Umlaute wie ,,, oder auch  usw. " .
                 "sind nicht im ASCII Format " .
                 "und werden deshalb umgeschrieben");

use Lingua::DE::Wortschatz;
use Data::Dumper;
use utf8;
use encoding 'utf8';

# /usr/lib/perl5/site_perl/5.8.7/Lingua/DE/Wortschatz.pm

my $wort = "komplett";

  #  my $result=Lingua::DE::Wortschatz::use_service('Sentences','voll');
	my $result=Lingua::DE::Wortschatz::use_service('Thesaurus',$wort);
  #  $result->dump;
    
#	print $result->dump();
#	exit;

    @lines=$result->hashrefs();
	#print Dumper @lines;
	#exit;

	my $AdditionSynonymEntryForDatabase = "$wort,";
	foreach (@lines) {
   		my $syn = $_->{Synonym};
		
	#	print "bad: $syn " if ( $syn =~ /\\x/i );

	#	foreach (split('', $syn)) {
	#	
	#		if ( ( ord($_) >= 97 && ord($_) <= 122 ) || ( ord($_) >= 65 && ord($_) <= 90 ) || ( ord($_) >= 48 && ord($_) <= 57 ) || ( $_ eq ' ' ) || ( $_ =~ s//oe/i && $_ =~ s//ue/i && $_ =~ s//ae/i && $_ =~ s//ss/)  ) {
	#			$output .= $_;
	#		}; # if ( ( ord($_

	#	}; # foreach (split('', $syn)) {

	#	next if ( $syn =~ /\\\x/i );
	#	next if ( $syn =~ //i );
	#	next if ( $syn =~ //i );
	#	next if ( $syn =~ //i );
		$AdditionSynonymEntryForDatabase .= "$syn," if ( length $syn >= 4);
		# push(@array, "$it");
	};

#	foreach $syn (@array) {
#		
#		my $len = length $syn;
#		$syn= encode("iso-8859-1", $syn);
#		print "[$len] $syn \n" if ( $syn =~ /[a-zA-Z]{3,}/i );
#		#if (  length($syn) >2 ) {
#		#	chomp($syn);
#			$AdditionSynonymEntryForDatabase .= "$syn,";

... [truncated, 21 more lines] ...

#!/usr/bin/perl

$yourdir = 'I:\syn\synonyme';
my $filecount = 0;

opendir(INDIR,$yourdir) or die "$!";
my @files = readdir INDIR;
close INDIR;

open(SYN,">syn-part2-notchecked.txt");

foreach my $inputFile (@files) {

	next if($inputFile=~/^\./);		# ignore . files
	next if($inputFile=~/\.pl/);	# perl file to ignore
	next if(-d $inputFile);			# Ignore directories
	my $string = "";

	open(RH,"<$yourdir\\$inputFile");
		while(<RH>){
			$string .= $_;
		}; # while(<RH>){
	close RH;
	
	my @content		= split("\n", $string);
	my $linecount	= 0;
	my $synonym		= "";
	my $syncount	= 0;
	my $last		= "";
	foreach my $line (@content) {
		eval {

			if ( $line =~ /\s+<\/b> <br>/i) {
				$line =~ s/<br>//ig;
				$line =~ s/<\/b>//;
				$line =~ s/^\s+//;
				$line =~ s/\s+$//;
				# print "LINE: $line\n";
				$synonym .= "$line," if ( $line ne $last || $line !~ /$last/i);
				$syncount++ if ( $line ne $last || $line !~ /$last/i);
				$last = $line;
			}; # if ( $line =~ /\s+<\/b> <br>/i) {
		
		};
		
		$linecount++;

	}; # foreach my $line (@content) {

	chop $synonym;

... [truncated, 16 more lines] ...

#!/usr/bin/perl

use Encode;

$string;
open(RH,"<synonyme1.html");
	while(<RH>){
		$string .= $_;
	}; # while(<RH>){
close RH;


@content = split(/\#\#\#/, $string);

open(SYN,">syn-part1-notchecked.txt");
for ( @content) {
	
	my @words = split(',', $_);
	my $synonyme = "";

	my $count = 0;
	foreach my $txt ( @words ) {
		chomp($txt);
		if ( $txt !~ /<.*?>/ ) {
			my $txt		= Encode::decode( 'iso-8859-1', $txt );
			# print "WORDS: $ustring\n";
			$txt =~ s/\s+//;
			#print "TXT: '$txt' \n";
			
			if ( $txt !~ /\s/ ) {
				$count++;
				$synonyme .= "$txt," if ( length $txt > 0 );
			}; # if ( $txt !~ /\s/ ) {
		
		}; # if ( $txt !~ /<.*?>/ ) {

	}; # foreach my $txt ( @words ) {

	chop($synonyme);
	# print "[$count] SYNONYM: $synonyme \n" if ( $count > 3);
	print SYN "$synonyme\n" if ( $count > 3);
	#select(undef,undef,undef, 0.25);
};

#!/usr/bin/perl

use IO::Handle;

$yourdir = 'I:\syn\synonyme1';
my $filecount = 0;

opendir(INDIR,$yourdir) or die "$!";
my @files = readdir INDIR;
close INDIR;

open(SYN,">syn-part3-notchecked.txt");
SYN->autoflush(1);

foreach my $inputFile (@files) {

	next if($inputFile=~/^\./);		# ignore . files
	next if($inputFile=~/\.pl/);	# perl file to ignore
	next if(-d $inputFile);			# Ignore directories
	my $string = "";

	open(RH,"<$yourdir\\$inputFile");
		while(<RH>){
			$string .= $_;
		}; # while(<RH>){
	close RH;
	
	my @content		= split("\n", $string);
	my $linecount	= 0;
	my $synonym		= "";
	my $syncount	= 0;
	my $last		= "";
	foreach my $line (@content) {
		eval {

			if ( $line =~ /\s+<\/b> <br>/i) {
				$line =~ s/<br>//ig;
				$line =~ s/<\/b>//;
				$line =~ s/^\s+//;
				$line =~ s/\s+$//;
				# print "LINE: $line\n";
				$synonym .= "$line," if ( $line ne $last || $line !~ /$last/i);
				$syncount++ if ( $line ne $last || $line !~ /$last/i);
				$last = $line;
			}; # if ( $line =~ /\s+<\/b> <br>/i) {
		
		};
		
		$linecount++;


... [truncated, 19 more lines] ...

#!/usr/bin/perl 

#########################################
##### Author:		Sebastian Enger / B.Sc
##### CopyRight:	Sebastian Enger / B.Sc
##### LastModified	7.01.2007
##### Function:		Dublicated Content Filter fr Google
##### Todo:			
########################################

# todo:
# statische synonym textdatei nehmen und diese dann abarbeiten, wenn kein treffer gefunden wurde dann benutze das langsame my $result	= Lingua::DE::Wortschatz::use_service('T', $_);
# StringManipulation ist mir noch zu krass, der text wird extrem unleserlich bis jetzt noch
###	amazon content grabbing + adding

# string::approx benutzen 
# TheCerial: my $ApproxMatchingQuantifier   = "40%";
# TheCerial: $matched						= amatch($FileName, $ApproxMatchingQuantifier, $TemporarySearchQuery);

# my $sentences			= get_sentences($text);				# returns an array ref
# my $FullContentArray	= &Main( $sentences	);
# $WordCount				= $#FullContent;

# synonyme in format bringen
# synonyme vergleichen mit textdate und zu modifizierendem text
# wenn syn. nicht in text datei vorhanden dann benutze webservice
# ergebnisse vom webservice dann auch in unsere syn. datei hinzufgen


# perl -MCPAN -e 'install "Text::German"'
# perl -MCPAN -e 'install "Text::English"'
# perl -MCPAN -e 'install "Lingua::EN:Inflect"'
# perl -MCPAN -e 'install "Lingua::DE::Wortschatz"'
# perl -MCPAN -e 'install "Lingua::DE::Num2Word"'
# perl -MCPAN -e 'install "Lingua::DE::ASCII"'
# perl -MCPAN -e 'install "Lingua::DE::Sentence"'
# perl -MCPAN -e 'install "Lingua::DE::TypoGenerator"'
# perl -MCPAN -e 'install "String::Approx"'
# perl -MCPAN -e 'install "Text::Levenshtein"'


# reniceing to 20 !
# system ("renice 20 $$");


use strict;
use Text::German;
# use Text::English;
use Lingua::DE::ASCII;
# use Lingua::EN::Inflect;

... [truncated, 467 more lines] ...

#!/usr/bin/perl 

#########################################
##### Author:		Sebastian Enger / B.Sc
##### CopyRight:	Sebastian Enger / B.Sc
##### LastModified	7.01.2007
##### Function:		Dublicated Content Filter fr Google
##### Todo:			
########################################

# todo:
# statische synonym textdatei nehmen und diese dann abarbeiten, wenn kein treffer gefunden wurde dann benutze das langsame my $result	= Lingua::DE::Wortschatz::use_service('T', $_);
# StringManipulation ist mir noch zu krass, der text wird extrem unleserlich bis jetzt noch
###	amazon content grabbing + adding

# string::approx benutzen 
# TheCerial: my $ApproxMatchingQuantifier   = "40%";
# TheCerial: $matched						= amatch($FileName, $ApproxMatchingQuantifier, $TemporarySearchQuery);

# my $sentences			= get_sentences($text);				# returns an array ref
# my $FullContentArray	= &Main( $sentences	);
# $WordCount			= $#FullContent;

# synonyme in format bringen
# synonyme vergleichen mit textdate und zu modifizierendem text
# wenn syn. nicht in text datei vorhanden dann benutze webservice
# ergebnisse vom webservice dann auch in unsere syn. datei hinzufgen


# perl -MCPAN -e 'install "Text::German"'
# perl -MCPAN -e 'install "Text::English"'
# perl -MCPAN -e 'install "Lingua::EN:Inflect"'
# perl -MCPAN -e 'install "Lingua::DE::Wortschatz"'
# perl -MCPAN -e 'install "Lingua::DE::Num2Word"'
# perl -MCPAN -e 'install "Lingua::DE::ASCII"'
# perl -MCPAN -e 'install "Lingua::DE::Sentence"'
# perl -MCPAN -e 'install "Lingua::DE::TypoGenerator"'
# perl -MCPAN -e 'install "String::Approx"'
# perl -MCPAN -e 'install "Text::Levenshtein"'


# reniceing to 20 !
system("renice 20 $$");
system("clear");

use strict;
# use Text::German;
# use Text::English;
# use Lingua::DE::ASCII;
use Lingua::EN::Inflect;

... [truncated, 657 more lines] ...

#!/usr/bin/perl 

#########################################
##### Author:		Sebastian Enger / B.Sc
##### CopyRight:	Sebastian Enger / B.Sc
##### LastModified	7.01.2007
##### Function:		Dublicated Content Filter fr Google
##### Todo:			
########################################

# todo:
# statische synonym textdatei nehmen und diese dann abarbeiten, wenn kein treffer gefunden wurde dann benutze das langsame my $result	= Lingua::DE::Wortschatz::use_service('T', $_);
# StringManipulation ist mir noch zu krass, der text wird extrem unleserlich bis jetzt noch
###	amazon content grabbing + adding

# my $sentences			= get_sentences($text);				# returns an array ref
# my $FullContentArray	= &Main( $sentences	);
# $WordCount			= $#FullContent;

# synonyme in format bringen
# synonyme vergleichen mit textdate und zu modifizierendem text
# wenn syn. nicht in text datei vorhanden dann benutze webservice
# ergebnisse vom webservice dann auch in unsere syn. datei hinzufgen


# perl -MCPAN -e 'install "Text::German"'
# perl -MCPAN -e 'install "Text::English"'
# perl -MCPAN -e 'install "Lingua::EN:Inflect"'
# perl -MCPAN -e 'install "Lingua::DE::Wortschatz"'
# perl -MCPAN -e 'install "Lingua::DE::Num2Word"'
# perl -MCPAN -e 'install "Lingua::DE::ASCII"'
# perl -MCPAN -e 'install "Lingua::DE::Sentence"'
# perl -MCPAN -e 'install "Lingua::DE::TypoGenerator"'
# perl -MCPAN -e 'install "String::Approx"'
# perl -MCPAN -e 'install "Text::Levenshtein"'


# reniceing to 20 !
system("renice 20 $$");
system("clear");

use strict;
use Data::Dumper;
use Text::German;
use Text::English;
use Lingua::DE::ASCII;
use Lingua::EN::Inflect;
use Lingua::DE::Sentence;
use Lingua::DE::Num2Word;
use Lingua::DE::Wortschatz;

... [truncated, 710 more lines] ...

#!/usr/bin/perl 

#########################################
##### Author:		Sebastian Enger / B.Sc
##### CopyRight:	Sebastian Enger / B.Sc
##### LastModified	7.01.2007
##### Function:		Dublicated Content Filter fr Google
##### Todo:			
########################################

# todo:
# statische synonym textdatei nehmen und diese dann abarbeiten, wenn kein treffer gefunden wurde dann benutze das langsame my $result	= Lingua::DE::Wortschatz::use_service('T', $_);
# StringManipulation ist mir noch zu krass, der text wird extrem unleserlich bis jetzt noch
###	amazon content grabbing + adding

# my $sentences			= get_sentences($text);				# returns an array ref
# my $FullContentArray	= &Main( $sentences	);
# $WordCount			= $#FullContent;

# synonyme in format bringen
# synonyme vergleichen mit textdate und zu modifizierendem text
# wenn syn. nicht in text datei vorhanden dann benutze webservice
# ergebnisse vom webservice dann auch in unsere syn. datei hinzufgen


# perl -MCPAN -e 'install "Text::German"'
# perl -MCPAN -e 'install "Text::English"'
# perl -MCPAN -e 'install "Lingua::EN:Inflect"'
# perl -MCPAN -e 'install "Lingua::DE::Wortschatz"'
# perl -MCPAN -e 'install "Lingua::DE::Num2Word"'
# perl -MCPAN -e 'install "Lingua::DE::ASCII"'
# perl -MCPAN -e 'install "Lingua::DE::Sentence"'
# perl -MCPAN -e 'install "Lingua::DE::TypoGenerator"'
# perl -MCPAN -e 'install "String::Approx"'
# perl -MCPAN -e 'install "Text::Levenshtein"'


# reniceing to 20 !
system("renice 20 $$");
system("clear");

use strict;
use Data::Dumper;
use Text::German;
use Text::English;
use Lingua::DE::ASCII;
use Lingua::EN::Inflect;
use Lingua::DE::Sentence;
use Lingua::DE::Num2Word;
use Lingua::DE::Wortschatz;

... [truncated, 719 more lines] ...

#!/usr/bin/perl 

#########################################
##### Author:		Sebastian Enger / B.Sc
##### CopyRight:	Sebastian Enger / B.Sc
##### LastModified	7.01.2007
##### Function:		Dublicated Content Filter fr Google
##### Todo:			
########################################

# todo:
# statische synonym textdatei nehmen und diese dann abarbeiten, wenn kein treffer gefunden wurde dann benutze das langsame my $result	= Lingua::DE::Wortschatz::use_service('T', $_);
# StringManipulation ist mir noch zu krass, der text wird extrem unleserlich bis jetzt noch
###	amazon content grabbing + adding

# my $sentences			= get_sentences($text);				# returns an array ref
# my $FullContentArray	= &Main( $sentences	);
# $WordCount			= $#FullContent;

# synonyme in format bringen
# synonyme vergleichen mit textdate und zu modifizierendem text
# wenn syn. nicht in text datei vorhanden dann benutze webservice
# ergebnisse vom webservice dann auch in unsere syn. datei hinzufgen


# perl -MCPAN -e 'install "Text::German"'
# perl -MCPAN -e 'install "Text::English"'
# perl -MCPAN -e 'install "Lingua::EN:Inflect"'
# perl -MCPAN -e 'install "Lingua::DE::Wortschatz"'
# perl -MCPAN -e 'install "Lingua::DE::Num2Word"'
# perl -MCPAN -e 'install "Lingua::DE::ASCII"'
# perl -MCPAN -e 'install "Lingua::DE::Sentence"'
# perl -MCPAN -e 'install "Lingua::DE::TypoGenerator"'
# perl -MCPAN -e 'install "String::Approx"'
# perl -MCPAN -e 'install "Text::Levenshtein"'
# perl -MCPAN -e 'install "Text::LevenshteinXS"'
# /usr/lib/perl5/site_perl/5.8.7/Lingua/DE/Wortschatz.pm

# reniceing to 20 !
# system("renice 20 $$");
# system("clear");

use strict;
use Data::Dumper;
use Text::German;
use Text::English;
use Lingua::DE::ASCII;
use Text::LevenshteinXS qw(distance);
use Lingua::EN::Inflect;
use Lingua::DE::Sentence;

... [truncated, 944 more lines] ...

#!/usr/bin/perl 

#########################################
##### Author:		Sebastian Enger / B.Sc
##### CopyRight:	Sebastian Enger / B.Sc
##### LastModified	7.01.2007
##### Function:		Dublicated Content Filter fr Google
##### Todo:			
########################################

# todo: wenn ein result von wortschatz kommt, dann erst prfen, ob der eintrag nicht schon vorhanden ist, erst dann hinzufgen !
###	amazon content grabbing + adding

# my $sentences			= get_sentences($text);				# returns an array ref
# my $FullContentArray	= &Main( $sentences	);
# $WordCount			= $#FullContent;

# perl -MCPAN -e 'install "Text::German"'
# perl -MCPAN -e 'install "Text::English"'
# perl -MCPAN -e 'install "Lingua::EN:Inflect"'
# perl -MCPAN -e 'install "Lingua::DE::Wortschatz"'
# perl -MCPAN -e 'install "Lingua::DE::Num2Word"'
# perl -MCPAN -e 'install "Lingua::DE::ASCII"'
# perl -MCPAN -e 'install "Lingua::DE::Sentence"'
# perl -MCPAN -e 'install "Lingua::DE::TypoGenerator"'
# perl -MCPAN -e 'install "String::Approx"'
# perl -MCPAN -e 'install "Text::Levenshtein"'
# perl -MCPAN -e 'install "Text::LevenshteinXS"'
# /usr/lib/perl5/site_perl/5.8.7/Lingua/DE/Wortschatz.pm

# reniceing to 20 !
# system("renice 20 $$");
# system("clear");

use strict;
use Data::Dumper;
use Text::German;
use Text::English;
use Lingua::DE::ASCII;
use Text::LevenshteinXS qw(distance);
use Lingua::EN::Inflect;
use Lingua::DE::Sentence;
use Lingua::DE::Num2Word;
use Lingua::DE::Wortschatz;
use Lingua::DE::TypoGenerator;		# generate typing errors from given keyword


# random initilisation
srand();


... [truncated, 945 more lines] ...