diff options
Diffstat (limited to 'bin/keyword-import.pl')
| -rwxr-xr-x | bin/keyword-import.pl | 252 |
1 files changed, 252 insertions, 0 deletions
diff --git a/bin/keyword-import.pl b/bin/keyword-import.pl new file mode 100755 index 0000000..1a377bb --- /dev/null +++ b/bin/keyword-import.pl @@ -0,0 +1,252 @@ +#!/usr/bin/perl + +use lib "/bucky/lib"; +use Bucky; + +$dbh = DBI->connect ($dsn); + +# get keyword + threads +my $target = $ARGV[0]; +my @dirs; +my %threads, %comments, %files; +our %keywords = get_keywords(); +my $keyword; + +if ($target > 0) + { + push @dirs, $target if (-e $target && -d $target); + } +else + { + $keyword = $ARGV[0]; + print "Importing keyword $keyword\n"; + @dirs = dir_list("$keyword/"); + chdir("$keyword/"); + } + +# read in all data... +foreach my $dir (@dirs) + { + next if ($dir eq "keyword"); + my @files = dir_list("$dir/"); + my $t, $c, $f; + + print "Reading in thread $dir ...\n"; + foreach my $filename (@files) + { + next if ($filename !~ /(thread|comment|file)/); + my ($type, $id) = split /\./, $filename, 2; + my $file = read_file("$dir/$filename"); + + if ($type eq "thread") + { + $t = flat2thread($file); + $threads{$t->{id}} = $t; + print "t.$t->{id} "; + } + elsif ($type eq "comment") + { + $c = flat2comment($file); + $comments{$c->{id}} = $c; + print "c.$c->{id} "; + } + elsif ($type eq "file") + { + $f = flat2file($file); + if (-e "$dir/data/$f->{filename}") + { + $files{$f->{id}} = $f; + print "f.$f->{id} "; + } + else + { + print "No data for $f->{filename} !\n" + } + } + } + print "$t->{title}"; + print "\n"; + } + +print "\n"; + +# now that data is all in a structure, +# parse through threads, comments, files IN ORDER +# get "real" thread ids to update "thread" when you next encounter it... +# as comments are created, keep track of "real ids".. update "parent_id != -1" where appropriate +# as files are created, update parent_id and move files + +# if keyword does not exist, create it. +#my $realk = get_keyword($keyword); +#if ($realk == -1) +# { +# my $file = read_file("keyword"); +# my $k = flat2thread($file); +# instantiate_keyword($k); +# } + +my %realthread = (-1 => -1); +my %realcomment = (-1 => -1); +my %realfile = (-1 => -1); + +foreach my $tid (sort { $a <=> $b } keys %threads) + { + my $t = $threads{$tid}; + my $fakeid = instantiate_thread($t); + print "thread $t->{id} => $fakeid\n"; + $realthread{$t->{id}} = $fakeid; + $ttot++; + } + +foreach my $cid (sort { $a <=> $b } keys %comments) + { + my $c = $comments{$cid}; + my $fakeid = instantiate_comment($c, $realthread{$c->{thread}}, $realcomment{$c->{parent_id}}); + print "comment $c->{id} => $fakeid\n"; + print " .. new thread: $c->{thread} -> $realthread{$c->{thread}}\n"; + print " .. new parent: $c->{parent_id} -> $realcomment{$c->{parent_id}}\n" + if ($c->{parent_id} != -1); + $realcomment{$c->{id}} = $fakeid; + $ctot++; + } + +foreach my $fid (sort { $a <=> $b } keys %files) + { + my $f = $files{$fid}; + my $realt = $realthread{$f->{parent_id}}; + my $fakeid = instantiate_file($f, $realt); + mkdir ("$data_path/$realt/") unless (-e "$data_path/$realt/"); + mkdir ("$data_path/$realt/.thumb/") unless (-e "$data_path/$realt/.thumb/"); + system("/bin/chmod 777 $data_path/$realt/.thumb"); + system ("/bin/cp \"$f->{parent_id}/data/$f->{filename}\" $data_path/$realt/"); + print "file $f->{id} => $fakeid\n"; + + print " .. new thread: $f->{parent_id} -> $realthread{$f->{parent_id}}\n"; + $realfile{$f->{id}} = $fakeid; + $ftot++; + $sizetot += $f->{size}; + } + +print "Import successful!\nTotal: $ttot.t $ctot.c $ftot.f ($sizetot b.)\n"; + +$dbh->disconnect(); + +########################### + +sub instantiate_keyword + { + my ($k) = @_; + my %nk = + ( + keyword => $k->{keyword}, + threads => " ", + owner => $k->{username}, + public => $k->{public}, + agglutinate => $k->{agglutinate}, + color => $k->{color} + ); + add_keyword(\%nk); + } + +sub instantiate_thread + { + my ($t) = @_; + my %nt = + ( + title => $t->{title}, + username => $t->{username}, + keyword => (exists ($keywords{$t->{keyword}}) ? $t->{keyword} : ""), + createdate => $t->{createdate}, + lastmodified => $t->{lastmodified}, + size => $t->{size}, + private => $t->{private}, + allowed => $t->{allowed}, + flagged => $t->{flagged}, + color => $t->{color}, + display => $t->{display} + ); + my $thread_id = add_thread_by_hash(\%nt); + die if ($thread_id == -1); + return $thread_id; + } + +sub instantiate_comment + { + my ($c, $newt, $newp) = @_; + my $comment_id = add_comment($newt, $newp, $c->{username}, $c->{comment}, $c->{date}); + return $comment_id; + } + +sub instantiate_file + { + my ($f, $newt) = @_; + my $file_id = add_file($newt, $f->{username}, $f->{filename}, $f->{size}, $f->{date}); + return $file_id; + } + +########################### + +sub dir_list + { + my ($d) = @_; + opendir (DIR, $d) or die "couldn't list: $d, $!"; + @files = grep (!/^\./, sort readdir (DIR)); + closedir DIR; + return @files; + } + +sub flat2hash + { + my ($file) = @_; + my %hash; + foreach my $line (@$file) + { + $line =~ s/\r//; + chomp $line; + last if (!$line); + last if ($line eq "\n"); + my ($k, $v) = split /:/, $line, 2; + $hash{$k} = $v; + } + return \%hash; + } + +sub flat2comment + { + my ($file) = @_; + my $comment_hash = flat2hash($file); + my $reading = 0; + foreach my $line (@$file) + { + $line =~ s/\r//; + if (!$line && !$reading) + { $reading = 1; next; } + next unless ($reading); + $comment_hash->{comment} .= $line; + } + return $comment_hash; + } + +sub flat2file + { + my ($file) = @_; + return flat2hash($file); + } + +sub flat2thread + { + my ($file) = @_; + return flat2hash($file); + } + +sub read_file + { + my ($file) = @_; + my @out; + + open F, $file or die "problem with $file $!"; + @out=<F>; + close F; + return \@out; + } + |