#!/usr/bin/perl # TODO: add test for files that are needed! die("please specify the date!") if(!defined($ARGV[0])); $date = $ARGV[0]; $dump = "dewiki-" . $date . "-pages-articles.xml.bz2"; die("$dump not found!") if (! -f $dump); print "extracting Persondata from $dump\n"; system("bzip2 -dc $dump | java -jar joost.jar - addNamespaces.stx extractPersonendaten.stx pd2tab.stx > $date-extract.tab");