Extract german noun inflections from Wiktionary (quick and dirty)

gistfile1.pl

#!perl -w
use strict;
use warnings;
use encoding 'utf-8';
use MediaWiki::DumpFile::Pages;
use YAML::XS;

my $pages = MediaWiki::DumpFile::Pages
  ->new('dewiktionary-20120416-pages-meta-current.xml');
  
while(defined(my $page = $pages->next)) {
  my $rev = $page->revision;
  my $re = qr/
    \{\{Deutsch\s+Substantiv\s+Übersicht\s+
    (\|.*?\s+)*
    \|Nominativ\s+Singular\s*=\s*(?<NS>.*?)\s+
    \|Nominativ\s+Plural\s*=\s*(?<NP>.*?)\s+
    \|Genitiv\s+Singular\s*=\s*(?<GS>.*?)\s+
    \|Genitiv\s+Plural\s*=\s*(?<GP>.*?)\s+
    \|Dativ\s+Singular\s*=\s*(?<DS>.*?)\s+
    \|Dativ\s+Plural\s*=\s*(?<DP>.*?)\s+
    \|Akkusativ\s+Singular\s*=\s*(?<AS>.*?)\s+
    \|Akkusativ\s+Plural\s*=\s*(?<AP>.*?)\s+
    \}\}/x;

  if ($rev->text =~ $re) {
    print Dump \%+;
  } elsif (index ($rev->text, 'Deutsch Substantiv Übersicht') >= 0) {
#    die $rev->text;
  }
}