AI-MicroStructure

 view release on metacpan or  search on metacpan

bin/micro-relation-test  view on Meta::CPAN

             compress_threshold => 100_000,
             compress_ratio => 0.9,
             compress_methods => [ \&IO::Compress::Gzip::gzip,
                                   \&IO::Uncompress::Gunzip::gunzip ],
             max_failures => 3,
             failure_timeout => 2,
             ketama_points => 150,
             nowait => 1,
             hash_namespace => 1,
             serialize_methods => [ \&Storable::freeze, \&Storable::thaw ],
             utf8 => ($^V ge v5.8.1 ? 1 : 0),
             max_size => 512 * 1024,
         });





sub  decruft  {
  my($file)  =  @_;
  my($cruftSet)  =  q{%§&|#[^+*(]),'";};

bin/micro-sense  view on Meta::CPAN

#print Dumper [split("sense",`wn $line  -coorn`)];
push @{$data->{'search'}},grep{/[a-z|A-Z]/}split("\n|,",lc `micro-wnet $line words`) unless(!$words);
#push @{$data->{'coordinate'}},map{$_=trim($_); @_=grep(/[A-Z]|[0-9]|[a-z]/,map{$_=trim($_)}split("\n|=>",$_))}split(/Sense/,`wn $line -coorn`) unless(!$words);
#shift @{$data->{'coordinate'}} &&  shift @{$data->{'search'}} for(0..1);
#@{$data->{'search'}};
END{

 $data = {"rows"=>$data,"senses"=>[sort keys %{$data->{'senses'}}]};


   my $utf8_encoded_json_text = encode_json($data);

  if($debug == 1) {
    print Dumper $data,$wn;
  }


  print $utf8_encoded_json_text;

}

bin/micro-wiki  view on Meta::CPAN

#!/usr/bin/perl -w
use utf8;
use File::Basename;
use Data::Printer;
use Data::Dumper;
use Parallel::Iterator qw( iterate );
use Env qw/PWD/;
use JSON::XS;
use HTML::Strip;
use AI::MicroStructure::Util;
use WWW::Wikipedia;
use LWP::UserAgent;
use HTML::SimpleLinkExtor;
use URI::Escape qw( uri_unescape );
our $e = HTML::SimpleLinkExtor->new;

binmode STDOUT, ':utf8';
binmode STDERR, ':utf8';


my $state  = AI::MicroStructure::Util::config();

my @CWD    = $state->{cwd};
our $config = $state->{cfg};


die("require a argument") unless($ARGV[0]);

bin/micro-wiki  view on Meta::CPAN

}

sub URLEncode {
my $theURL = $_[0];
$theURL =~ s/([\W])/"%" . uc(sprintf("%2.2x",ord($1)))/eg;
return $theURL;
}

sub smartdecode {
use URI::Escape qw( uri_unescape );
use utf8;
my $x = my $y = uri_unescape($_[0]);
return $x if utf8::decode($x);
return $y;
}

sub imgTranslate {

my ($idx,$url) = @_;

print $idx;
print $url;
if($url){

bin/micro-wiki  view on Meta::CPAN

      my $wiki = WWW::Wikipedia->new();
      my $hs = HTML::Strip->new();

      my $result = $wiki->search(ucfirst $url);
      if (defined($result) && $result->text() ) {

      my $clean_text = $hs->parse($result->text() );
      $hs->eof;

      require HTML::SimpleLinkExtor;
      no warnings 'utf8';
      my $e = HTML::SimpleLinkExtor->new();
      $e->parse($response->decoded_content);


      my @all_links = $e->links;
      my @tags= map{$_=lc($_); $_=~s/\)|\/wiki\///g; $_=~s/ /_/g; $_=[split("_\\(",$_)] }grep {/([(].+?[)]|$url)/}@all_links ;# $result->related();
      my @audio = grep{/^(\/\/|upload|http).*.(mp3|wave|ogg|OGG|WAVE|MP3)$/}@all_links;
      my @pdf = grep{/^(\/\/|upload|http).*.(pdf|PDF)$/}@all_links;
      my @book = grep{/books.google/i}@all_links;
         foreach(@tags){

bin/remote.pl  view on Meta::CPAN

    "\x{012b}"     => 'i',
    "\x{014d}"     => 'o',
    "\x{016b}"     => 'u',
    "\xe2\x99\x80" => 'female',
    "\xe2\x99\x82" => 'male',
    "\x{2640}"     => 'female',
    "\x{2642}"     => 'male',
);
my $utf_re = qr/(@{[join( '|', sort keys %utf2asc )]})/;

sub tr_utf8_basic {
    my $str = shift;
    $str =~ s/$utf_re/$utf2asc{$1}/go;
    return $str;
}

1;

package main;

use Data::Printer;

bin/remote.pl  view on Meta::CPAN

__PACKAGE__->init();

our %Remote = (
    source => {
        female => 'http://en.wikipedia.org/wiki/Knowledge_of_female_porn_stars',
        male   => 'http://en.wikipedia.org/wiki/Knowledge_of_male_porn_stars'
    },
    extract => sub {
        return
            map { AI::MicroStructure::RemoteKnowledge::tr_accent($_) }
            map { AI::MicroStructure::RemoteKnowledge::tr_utf8_basic($_) }
            grep { ! /^Knowledge_|_Groups$/ }
            map { s/[-\s']/_/g; s/[."]//g; $_ }
            $_[0]
            =~ m{^<li>(?:<[^>]*>)?(.*?)(?:(?: ?[-,(<]| aka | see ).*)?</li>}mig
    },
    ,
);

1;
package main;

lib/AI/MicroStructure.pm  view on Meta::CPAN

use File::Spec;
use File::Glob;
use Data::Dumper;
use Data::Printer;
use AI::MicroStructure::Util;
use Carp qw(croak);
our $absstructdir = "";
our $structdir = "";
our $VERSION = '0.20';
our $Structure = 'any'; # default structure
our $CODESET = 'utf8';
our $LANG = '';
our %MICRO;
our %MODS;
our %ALIEN;
our $str = "[A-Z]";
our $special = "any";
our $search;
our $data={};
our $item="";
our @items;

lib/AI/MicroStructure/RemoteList.pm  view on Meta::CPAN

    "\x{012b}"     => 'i',
    "\x{014d}"     => 'o',
    "\x{016b}"     => 'u',
    "\xe2\x99\x80" => 'female',
    "\xe2\x99\x82" => 'male',
    "\x{2640}"     => 'female',
    "\x{2642}"     => 'male',
);
my $utf_re = qr/(@{[join( '|', sort keys %utf2asc )]})/;

sub tr_utf8_basic {
    my $str = shift;
    $str =~ s/$utf_re/$utf2asc{$1}/go;
    return $str;
}

1;

__END__

=head1 NAME

lib/AI/MicroStructure/RemoteList.pm  view on Meta::CPAN

=item tr_nonword( $str )

Return a copy of C<$str> with all non-word characters turned into
underscores (C<_>).

=item tr_accent( $str )

Return a copy of C<$str> will all iso-8859-1 accented characters turned
into basic ASCII characters.

=item tr_utf8_basic( $str )

Return a copy of C<$str> with some of the utf-8 accented characters turned
into basic ASCII characters. This is very crude, but I didn't to bother
and depend on the proper module to do that.

=back

=head1 AUTHOR

'santex'  << <santex@cpan.org> >>.