#!/usr/bin/perl
#
# Update the database of episodes with airdate info extracted from the
# Doctor Who wikipedia page being piped into us.
#
my $topdir="/huge/vids";
my $whodir="$topdir/DoctorWho";
my $dbdir="$whodir/.data";
my $dbfile="$dbdir/allinfo.txt";
my %db;

# Get PATH set to include this script's directory and other useful bits

my $newpath=`dirname $0`;
chomp($newpath);
$newpath=`$newpath/echo-path`;
chomp($newpath);
$ENV{'PATH'}=$newpath;

# Read in the existing database (if any) to start with known data
# so this update won't discard any information.

my $fh;
my $r;
if (open($fh, '<', $dbfile)) {
   while (<$fh>) {
      chomp;
      if (/^\[(.+)\]$/) {
         my $basename = $1;
         $r = {};
         $db{$basename} = $r;
      } elsif (/^([A-Za-z0-9_]+)=(.+)$/) {
         if (defined($r)) {
            my $key = $1;
            my $val = $2;
            $r->{$key} = $val;
         }
      }
   }
   close($fh);
   undef($fh);
   undef($r);
}

my $in_row=0;
my $in_col=0;
my @cols;
my $col_data='';

my %months;
$months{'january'}=1;
$months{'february'}=2;
$months{'march'}=3;
$months{'april'}=4;
$months{'may'}=5;
$months{'june'}=6;
$months{'july'}=7;
$months{'august'}=8;
$months{'september'}=9;
$months{'october'}=10;
$months{'november'}=11;
$months{'december'}=12;
$months{'jan'}=1;
$months{'feb'}=2;
$months{'mar'}=3;
$months{'apr'}=4;
$months{'jun'}=6;
$months{'jul'}=7;
$months{'aug'}=8;
$months{'sep'}=9;
$months{'oct'}=10;
$months{'nov'}=11;
$months{'dec'}=12;

sub process_cols {
   my $ar = shift;
   if (($ar->[0]=~/title=/) && ($ar->[5]=~/\d+\s+[A-Za-z]+\s+\d+/)) {
      my @titles = split(/\<br\b/, $ar->[0]);
      my @dates = split(/\<br\b/, $ar->[5]);
      if (scalar(@titles) == scalar(@dates)) {
         while (scalar(@titles) > 0) {
            my $t = shift(@titles);
            my $d = shift(@dates);
            if ($t=~/title=\"([^\"]+)\"/) {
               $t = $1;
               $t=~s/\(Doctor Who\)//g;
               $t=~s/Doctor Who\://g;
               $t=~s/^\s+//;
               $t=~s/\s+$//;
               $t=~s/\&[a-zA-Z0-9_]+\;//g;
               $t=~s/([\w']+)/\u\L$1/g;
               $t=~s/[^A-Za-z_0-9]//g;
               $t=~s/DoctorWhoEpisode$//;
               if ($d=~/(\d+\s+[A-Za-z]+\s+\d+)/) {
                  $d = $1;
                  @dmy=split(' ',$d);
                  my $m=$dmy[1];
                  $m=~tr/A-Z/a-z/;
                  $m=$months{$m};
                  $d=sprintf("%04d-%02d-%02d",$dmy[2],$m,$dmy[0]);
                  my $r = $db{$t};
                  if (! defined($r)) {
                     $r = {};
                     $db{$t} = $r;
                  }
                  if (! exists($r->{'airdate'})) {
                     $r->{'airdate'} = $d;
                  }
               }
            }
         }
      }
   }
}

while (<>) {
   if (/^\<tr\b/) {
      $in_row = 1;
   }
   if ($in_row) {
      if (/^\<td\b/) {
         $in_col = 1;
         $col_data='';
      }
      if ($in_col) {
         $col_data .= $_;
      }
      if (/\<\/td\b/) {
         $in_col=0;
         if ($col_data ne '') {
            push(@cols, $col_data);
         }
      }
   }
   if (/\<\/tr\b/) {
      $in_row = 0;
      if (scalar(@cols) >= 6) {
         &process_cols(\@cols);
         undef @cols;
      }
   }
}

# Save new db (keeping backup)

sub compare_airdate {
   my $ada = $db{$a}->{'airdate'};
   my $adb = $db{$b}->{'airdate'};
   if (! defined($ada)) {
      $ada='';
   }
   if (! defined($adb)) {
      $adb='';
   }
   my $rval = $ada cmp $adb;
   if ($rval == 0) {
      $rval = $a cmp $b;
   }
   return $rval;
}

my $dbtemp="$dbfile.$$";
my $dbh;
if (open($dbh, '>', $dbtemp)) {
   foreach $bn (sort compare_airdate keys %db) {
      $r = $db{$bn};
      print $dbh "\n[$bn]\n";
      my $key;
      my $val;
      foreach $key (sort(keys(%{$r}))) {
         $val = $r->{$key};
         print $dbh "$key=$val\n";
      }
   }
   close($dbh);
   unlink("$dbfile.bak");
   link($dbfile,"$dbfile.bak");
   unlink($dbfile);
   link($dbtemp,$dbfile);
   unlink($dbtemp);
}