view release on metacpan or  search on metacpan

bin/micro-dict  view on Meta::CPAN

#!/bin/bash
IFS=$'\n';

#REMOVETHESE="gov|search|cid|aaa|bbb|ccc|ddd|eee|fff|ggg|hhh|iii|jjj|kkk|lll|mmm|nnn|ooo|ppp|qqq|rrr|sss|ttt|eee|fff|ggg|hhh|iii|jjj|kkk|lll|mmm|nnn|ooo|ppp|qqq|rrr|sss|ttt|uuu|vvv|www|xxx|yyy|zzz|org|wiki|png|jpg|thumb|pdf|ref|idx|php|html|json|abc|...
#  egrep -v "($REMOVETHESE)" |

                                    #+ options to sort. Changed from




stop=$(perl -MAI::MicroStructure::WordBlacklist -E  "my \$s=AI::MicroStructure::WordBlacklist::getStopWords('de'); my @s = keys %\$s; print join('|',@s);")

bin/micro-dict~  view on Meta::CPAN

#!/bin/bash
IFS=$'\n';

#REMOVETHESE="gov|search|cid|aaa|bbb|ccc|ddd|eee|fff|ggg|hhh|iii|jjj|kkk|lll|mmm|nnn|ooo|ppp|qqq|rrr|sss|ttt|eee|fff|ggg|hhh|iii|jjj|kkk|lll|mmm|nnn|ooo|ppp|qqq|rrr|sss|ttt|uuu|vvv|www|xxx|yyy|zzz|org|wiki|png|jpg|thumb|pdf|ref|idx|php|html|json|abc|...
#  egrep -v "($REMOVETHESE)" |

                                    #+ options to sort. Changed from




stop=$(perl -MAI::MicroStructure::WordBlacklist -E  "my \$s=AI::MicroStructure::WordBlacklist::getStopWords('de'); my @s = keys %\$s; print join('|',@s);")

bin/micro-wiki  view on Meta::CPAN

      $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)$/}@all_links;
      my @book = grep{/books.google/i}@all_links;
         foreach(@tags){
            if($_->[1] && $_->[1]!~/\W/){
              $doc->{tags}->{$_->[1]}->{$_->[0]} = $doc->{tags}->{$_->[1]}->{$_->[0]} ? $doc->{tags}->{$_->[1]}->{$_->[0]} +1:1;
            }
         }

          $doc->{image}=[map{$_="http:$_"; }grep{/[1-9][0-9][0-9]px/}$e->img];
          $doc->{cat}=[grep{/^.*.(Kategory|Category)+?/}@all_links];
          $doc->{cat}=[sort grep{!/(category|wikipedia|article|page|List.*.of)/i}map{$a=$_; $a =~ s/^.*.://g; $_=$a;}@{$doc->{cat}}];