#!/usr/bin/perl
use strict;
use CGI qw(:standard);
use Date::Manip qw(ParseDate ParseDateString ParseDateDelta DateCalc UnixDate);
use Date::Parse;
use HTML::Entities;
use LWP::Simple qw(get);
use XML::DOM;
 
use constant URL_EVENTS => 'http://api.meetup.com/events?key=%s&member_id=%d&format=xml';
 
print header(q(text/calendar));
 
my $parser = new XML::DOM::Parser ();
 
my $mode = param( 'cal' );
my $key  = param( 'key' );
my $user = param( 'user' );
 
if ( ! $mode || ! $key || ! $user ) {
  die
}
 
my $events_url = sprintf( URL_EVENTS, $key, $user );
#warn $events_url;
my $events_txt = get( $events_url );
#warn $events_txt;
my $events_dom = $parser->parse( $events_txt );
#warn $events_dom;
 
print qq(BEGIN:VCALENDAR\nPRODID:-//Meetup Inc//RemoteApi//EN\nVERSION:2.0\nMETHOD:PUBLISH\nCALSCALE:GREGORIAN\nX-ORIGINAL-URL:http://www.meetup.com/\nX-WR-CALNAME:mu $mode\n);
 
my $events = $events_dom->getElementsByTagName( 'item' );
for ( my $i = 0 ; $i < $events->getLength() ; $i++ ) {
  my $event = $events->item( $i );
  my $n_id    = $event->getElementsByTagName( 'id'             )->item( 0 )->getFirstChild();
  my $n_rsvp  = $event->getElementsByTagName( 'myrsvp'         )->item( 0 )->getFirstChild();
  my $n_addr0 = $event->getElementsByTagName( 'venue_name'     )->item( 0 )->getFirstChild();
  my $n_addr1 = $event->getElementsByTagName( 'venue_address1' )->item( 0 )->getFirstChild();
  my $n_addr2 = $event->getElementsByTagName( 'venue_address2' )->item( 0 )->getFirstChild();
  my $n_addr3 = $event->getElementsByTagName( 'venue_address3' )->item( 0 )->getFirstChild();
  my $n_addr4 = $event->getElementsByTagName( 'venue_city'     )->item( 0 )->getFirstChild();
  my $n_addr5 = $event->getElementsByTagName( 'venue_state'    )->item( 0 )->getFirstChild();
  my $n_addr6 = $event->getElementsByTagName( 'venue_zip'      )->item( 0 )->getFirstChild();
  my $n_desc  = $event->getElementsByTagName( 'description'    )->item( 0 )->getFirstChild();
  my $n_link  = $event->getElementsByTagName( 'event_url'      )->item( 0 )->getFirstChild();
  my $n_name  = $event->getElementsByTagName( 'name'           )->item( 0 )->getFirstChild();
  my $n_lat   = $event->getElementsByTagName( 'venue_lat'      )->item( 0 )->getFirstChild();
  my $n_lon   = $event->getElementsByTagName( 'venue_lon'      )->item( 0 )->getFirstChild();
  my $n_start_time  = $event->getElementsByTagName( 'time'           )->item( 0 )->getFirstChild();
 
  my $start_time;
  my $end_time;
 
  #my $dummy_time = "20000101T000000Z";
  my ($sec,$min,$hour,$mday,$mon,$year,$wday,$yday,$isdst) = localtime(time());
  my $dummy_time = sprintf( q(%04d%02d%02dT%02d%02d%02dZ), $year + 1900, $mon + 1, $mday, $hour, $min, $sec );
 
  if ( $n_start_time ) {
    my ($ss,$mm,$hh,$day,$month,$year,$zone);
 
    ($ss,$mm,$hh,$day,$month,$year,$zone) = strptime( $n_start_time->toString() );
    $start_time = sprintf( q(%04d%02d%02dT%02d%02d%02dZ), $year + 1900, $month + 1, $day, $hh, $mm, $ss );
 
    my $eday = $day;
    if ( $hh == 23 ) {
      $eday = $day + 1;
    }
    my $ehh = ($hh + 1) % 24;
    $end_time   = sprintf( q(%04d%02d%02dT%02d%02d%02dZ), $year + 1900, $month + 1, $eday, $ehh, $mm, $ss );
  }
  else {
    $start_time = '';
    $end_time = '';
  }
 
  if ( $mode eq $n_rsvp->toString() ) {
    my $id   = $n_id->toString();
    my $name = $n_name ? $n_name->toString() : "";
    my $desc = $n_desc ? $n_desc->toString() : "";
    my $addr = ( $n_addr0 ? $n_addr0->toString().', ' : "" )
             . ( $n_addr1 ? $n_addr1->toString().', ' : "" )
             . ( $n_addr2 ? $n_addr2->toString().', ' : "" )
             . ( $n_addr3 ? $n_addr3->toString().', ' : "" )
             . ( $n_addr4 ? $n_addr4->toString().', ' : "" )
             . ( $n_addr5 ? $n_addr5->toString().', ' : "" )
             . ( $n_addr6 ? $n_addr6->toString() : "" );
    #$desc =~ s/(.)/(ord($1) > 127) ? "" : $1/egs;
 
    $name = HTML::Entities::decode_entities( $name );
    $desc = HTML::Entities::decode_entities( $desc );
    $addr = HTML::Entities::decode_entities( $addr );
    $name =~ s/,/\\,/g;
    $desc =~ s/,/\\,/g;
    $addr =~ s/,/\\,/g;
 
    $desc =~ s#
#\\n#gs;
    $desc .= "\\n\\n\\nGoing?\\n\\n";
    foreach my $response ( qw( yes no maybe ) ) {
      $desc .= uc($response).qq(: http://api.meetup.com/rsvp?event_id=$id&key=$key&rsvp=$response\\n);
    }
 
    my $geo = $n_lat && $n_lon ? "GEO:" . $n_lat->toString() . ";" . $n_lon->toString() . "\n" : undef;
 
    #print sprintf( qq(BEGIN:VEVENT\nSUMMARY:%s\nDESCRIPTION:%s\nLAST-MODIFIED:%s\nUID:%s\nCLASS:%s\nCREATED:%s\nDTSTAMP:%s\nDTSTART:%s\nDTEND:%s\nLOCATION:%s\n\nURL:%s\nEND:VEVENT\n),
    print sprintf( qq(BEGIN:VEVENT\nSUMMARY:%s\nDESCRIPTION:%s\nLAST-MODIFIED:%s\nUID:%s\nCLASS:%s\nCREATED:%s\nDTSTAMP:%s\nDTSTART:%s\nDTEND:%s\n%sLOCATION:%s\nURL:%s\nEND:VEVENT\n),
      $name,
      $desc,
      $start_time,
      "event_$id\@meetup.com",
      "PUBLIC",
      $dummy_time,
      $dummy_time,
      $start_time,
      $end_time,
      $geo,
      $addr,
      $n_link ? $n_link->toString() : "",
    );
  }
}
 
print qq(END:VCALENDAR\n);

	public static void itemItemRecommendations(String path, String file) {
		File f = new File(path, file);
	    try {
			DataModel model = new FileDataModel(f);
			model.refresh(null);
		    ItemSimilarity itemSimilarity = new LogLikelihoodSimilarity(model);
		    ItemBasedRecommender itemRecommender = new GenericItemBasedRecommender(model, itemSimilarity);
		    for ( Item i : model.getItems() )
			    for ( RecommendedItem j : itemRecommender.mostSimilarItems(i.getID(), 50) )
			    	if ( j.getValue() >= 0.7 )
			    		System.out.println(i.getID() + "\t" + j.getItem().getID() + "\t" + String.format("%.3f", j.getValue()));
		} catch (FileNotFoundException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		} catch (TasteException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
	}

./bin/hadoop jar contrib/streaming/*-streaming.jar -input /home/aday/classC.dat -output /home/aday/classC_dns.dat -mapper 'perl -ne '\''print `host $_`'\''' -numReduceTasks 0

library(Matrix);
 
#F = strsplit(as.character(mm[1,2]),', ')[[1]]
#G = matrix( as.numeric(unlist(strsplit(F[c(-1,-length(F))],':'))), nrow=2 )
#tt = new('dsparseVector', x=G[2,], i=as.integer(G[1,]), length=max(as.integer(G[1,])))
 
minus = function(v1,v2) {
  i = sort(union(v1@i,v2@i));
  s = length(i);
 
  x = vector(mode='numeric',length=s);
  for ( k in 1:s ) {
    z = i[k];
    if ( z < length(v1) ) {
      x[k] = as.numeric(v1[z]);
    }
    if ( z < length(v2) ) {
      x[k] = x[k] - as.numeric(v2[z]);
    }
  }
  new("dsparseVector", x=x, i=i, length=max(v1@i,v2@i))
}

#!/usr/bin/perl
use strict;
use DBI;
 
######configuration
my $PREFIX = 'wp_h5otpn_';
my $DB = '';
my $HOST = '';
my $USER = '';
my $PASS = '';
######
my $dbh = DBI->connect(qq(dbi:mysql:database=$DB;host=$HOST), $USER, $PASS) or die $!;
 
my $term_sth   = $dbh->prepare(qq(SELECT * FROM (SELECT name, count(name) AS c FROM ${PREFIX}terms GROUP BY name) AS d WHERE d.c > 1));
my $name_sth   = $dbh->prepare(qq(SELECT term_id FROM ${PREFIX}terms WHERE name = ?));
my $update_sth = $dbh->prepare(qq(UPDATE ${PREFIX}term_relationships SET term_taxonomy_id = (SELECT term_taxonomy_id FROM ${PREFIX}term_taxonomy WHERE term_id = ?) WHERE term_taxonomy_id = (SELECT term_taxonomy_id FROM ${PREFIX}term_taxonomy WHERE term_id = ?)));
my $delete1_sth = $dbh->prepare(qq(DELETE FROM ${PREFIX}term_taxonomy WHERE term_id = ?));
my $delete2_sth = $dbh->prepare(qq(DELETE FROM ${PREFIX}terms WHERE term_id = ?));
$term_sth->execute();
 
while ( my ( $name, $count ) = $term_sth->fetchrow_array() ) {
  $name_sth->execute( $name );
  my $new = undef;
  while ( my ( $term_id ) = $name_sth->fetchrow_array() ) {
    if ( ! $new ) {
      $new = $term_id;
      next;
    }
    warn "$name\t$term_id\t->\t$new";
    $update_sth->execute( $new, $term_id );
    $delete1_sth->execute( $term_id );
    $delete2_sth->execute( $term_id );
  }
}
 
__DATA__
SELECT t.term_id, t.name, r.*, s.* FROM wp_h5otpn_terms AS t, wp_h5otpn_term_taxonomy AS r, wp_h5otpn_term_relationships AS s WHERE s.term_taxonomy_id = r.term_taxonomy_id AND r.term_id = t.term_id AND r.taxonomy = 'post_tag' AND t.name = 'whatever';