contencleaner - examples - SOURCE CODE

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] ...