Scan an article dump file for double redirects that exist in the most recent article revision

  #!/usr/bin/perl
  
  #progress information goes to STDERR, a list of double redirects found
  #goes to STDOUT
  
  binmode(STDOUT, ":utf8");
  binmode(STDERR, ":utf8");
  
  use strict;
  use warnings;
  use MediaWiki::DumpFile::Compat;
  
  my $file = shift(@ARGV);
  my $pmwd = Parse::MediaWikiDump->new;
  my $pages;
  my $page;
  my %redirs;
  my $artcount = 0;
  my $file_size;
  my $start = time;
  
  if (defined($file)) {
        $file_size = (stat($file))[7];
        $pages = $pmwd->pages($file);
  } else {
        print STDERR "No file specified, using standard input\n";
        $pages = $pmwd->pages(\*STDIN);
  }
  
  #the case of the first letter of titles is ignored - force this option
  #because the other values of the case setting are unknown
  die 'this program only supports the first-letter case setting' unless
        $pages->case eq 'first-letter';
  
  print STDERR "Analyzing articles:\n";
  
  while(defined($page = $pages->next)) {
    update_ui() if ++$artcount % 500 == 0;
  
    #main namespace only
    next unless $page->namespace eq '';
    next unless defined($page->redirect);
  
    my $title = case_fixer($page->title);
    #create a list of redirects indexed by their original name
    $redirs{$title} = case_fixer($page->redirect);
  }
  
  my $redir_count = scalar(keys(%redirs));
  print STDERR "done; searching $redir_count redirects:\n";
  
  my $count = 0;
  
  #if a redirect location is also a key to the index we have a double redirect
  foreach my $key (keys(%redirs)) {
    my $redirect = $redirs{$key};
  
    if (defined($redirs{$redirect})) {
      print "$key\n";
      $count++;
    }
  }
  
  print STDERR "discovered $count double redirects\n";
  
  #removes any case sensativity from the very first letter of the title
  #but not from the optional namespace name
  sub case_fixer {
    my $title = shift;
  
    #check for namespace
    if ($title =~ /^(.+?):(.+)/) {
      $title = $1 . ':' . ucfirst($2);
    } else {
      $title = ucfirst($title);
    }
  
    return $title;
  }
  
  sub pretty_bytes {
    my $bytes = shift;
    my $pretty = int($bytes) . ' bytes';
  
    if (($bytes = $bytes / 1024) > 1) {
      $pretty = int($bytes) . ' kilobytes';
    }
  
    if (($bytes = $bytes / 1024) > 1) {
      $pretty = sprintf("%0.2f", $bytes) . ' megabytes';
    }
  
    if (($bytes = $bytes / 1024) > 1) {
      $pretty = sprintf("%0.4f", $bytes) . ' gigabytes';
    }
  
    return $pretty;
  }
  
  sub pretty_number {
    my $number = reverse(shift);
    $number =~ s/(...)/$1,/g;
    $number = reverse($number);
    $number =~ s/^,//;
  
    return $number;
  }
  
  sub update_ui {
    my $seconds = time - $start;
    my $bytes = $pages->current_byte;
  
    print STDERR "  ", pretty_number($artcount),  " articles; "; 
    print STDERR pretty_bytes($bytes), " processed; ";
  
    if (defined($file_size)) {
      my $percent = int($bytes / $file_size * 100);
  
      print STDERR "$percent% completed\n"; 
    } else {
      my $bytes_per_second = int($bytes / $seconds);
      print STDERR pretty_bytes($bytes_per_second), " per second\n";
    }
  }

Version 0.4

This class was updated to support version 0.4 dump files from a MediaWiki instance but it does not currently support any of the new information available in those files.