VideoDetect/scanner/scanner.pl

#!/usr/bin/perl
use strict;
use warnings;
use DBI;
use Digest::SHA qw(sha256_hex);
use JSON;

my $db_host = $ENV{'DB_HOST'} || 'mariadb';
my $db_name = $ENV{'DB_NAME'} || 'videodetect';
my $db_user = $ENV{'DB_USER'} || 'videodetect';
my $db_pass = $ENV{'DB_PASSWORD'} || 'videodetect123';  

my $dbh = DBI->connect("DBI:mysql:database=$db_name;host=$db_host", $db_user, $db_pass);

my @video_extensions = qw(mp4 mkv avi mov flv wmv mpg mpeg webm);
my @dir_queue = ('/data');


# Get NOW() from the database
my $sth = $dbh->prepare("SELECT NOW() AS now");
$sth->execute();
my $row = $sth->fetchrow_hashref();
my $now = $row->{now};
$sth->finish();

while(my $dir = shift @dir_queue) {
    opendir(my $dh, $dir) or die "Cannot open directory $dir: $!";
    while (my $file = readdir($dh)) {
        next if ($file eq '.' || $file eq '..');
        my $full_path = "$dir/$file";
        if (-d $full_path) {
            unshift @dir_queue, $full_path;
        } elsif (-f $full_path) {
            process_file($full_path);
        }
    }
    closedir($dh);
}

# Any entry where last_scan_time < $now is considered deleted or moved, so we can mark them as such
my $sth_delete = $dbh->prepare("DELETE FROM videos WHERE last_scan_time < ? OR last_scan_time IS NULL");
$sth_delete->execute($now);

sub process_file {
    my ($file_path) = @_;
    # Determine if the file is a video based on mime info or extension. For simplicity, let's check the extension.
    if (my ($ext)=$file_path =~ /^.+\.(\S+?)$/) {
        unless (grep { lc($ext) eq $_ } @video_extensions) {
            return;  # Not a video file
        }
    }

    my $sth = $dbh->prepare("SELECT id,file_size FROM videos WHERE file_path=?");
    $sth->execute($file_path);
    if(my $row = $sth->fetchrow_hashref()) {
        my $file_size = -s $file_path;
        if ($file_size != $row->{file_size}) {
            warn "File size mismatch for $file_path. Updating record.";
            my $update_sth = $dbh->prepare("UPDATE videos SET file_size=?, last_scan_time=NOW() WHERE id=?");
            $update_sth->execute($file_size, $row->{id});
            $update_sth->finish();
            create_review_task($row->{id});
        }
        return;  # Already exists and size matches
    }

    my $info = get_video_info($file_path);
    unless ($info) {
        warn "Failed to get video info for $file_path. Skipping.";
        return;
    }
    $sth = $dbh->prepare("INSERT INTO videos (file_path, file_size, file_hash, resolution_w, resolution_h, codec, duration, last_scan_time) VALUES (?, ?, ?, ?, ?, ?, ?, NOW())");
    $sth->execute(
        $file_path,
        -s $file_path,
        $info->{file_hash},
        $info->{resolution_w},
        $info->{resolution_h},
        $info->{codec},
        $info->{duration}
    );
    $sth->finish();

    my $video_id = $dbh->last_insert_id(undef, undef, 'videos', undef);
    create_review_task($video_id);
}

sub create_review_task {
    my ($video_id) = @_;
    $dbh->do("DELETE FROM tasks WHERE video_id=$video_id AND task_type='REVIEW'");
    my $sth = $dbh->prepare("INSERT INTO tasks (video_id, task_type, status) VALUES (?, 'REVIEW', 'PENDING')");
    $sth->execute($video_id);
    $sth->finish();
}

sub get_video_info {
    my ($file_path) = @_;

    # --- Compute SHA-256 hash of the file ---
    return undef unless -f $file_path && -r $file_path;
    open(my $fh, '<:raw', $file_path) or do { warn "Cannot open $file_path: $!"; return undef; };
    my $hash = sha256_hex($fh);
    close($fh);

    # --- Run ffprobe to extract metadata ---
    my $probe_cmd = qq{ffprobe -v quiet -print_format json -show_format -show_streams '$file_path'};
    my $output = `$probe_cmd`;
    return undef unless defined $output && length($output);

    my $json = JSON->new->utf8->canonical(1);
    my $data = $json->decode($output);

    # --- Extract codec from video stream (prefer first video stream found) ---
    my $codec = undef;
    if (exists $data->{streams} && ref($data->{streams}) eq 'ARRAY') {
        for my $stream (@{$data->{streams}}) {
            if ($stream->{codec_type} eq 'video') {
                $codec = $stream->{codec_name};
                last;
            }
        }
    }

    # --- Extract resolution and duration from format/streams ---
    my ($resolution_w, $resolution_h, $duration);

    # Duration from format first, then stream
    if (exists $data->{format} && exists $data->{format}{duration}) {
        $duration = $data->{format}{duration} + 0;   # force numeric
    } elsif (exists $data->{streams}[0] && exists $data->{streams}[0]{duration}) {
        $duration = $data->{streams}[0]{duration} + 0;
    }

    # Resolution from video stream first, then format side data
    if (exists $data->{streams} && ref($data->{streams}) eq 'ARRAY') {
        for my $stream (@{$data->{streams}}) {
            next unless $stream->{codec_type} eq 'video';
            if ($stream->{width} && $stream->{height}) {
                $resolution_w = $stream->{width};
                $resolution_h = $stream->{height};
                last;
            }
        }
    }

    return {
        file_hash      => $hash,
        resolution_w   => $resolution_w // 0,
        resolution_h   => $resolution_h // 0,
        codec          => $codec // 'unknown',
        duration       => $duration,
    };
}