From 639c29c2c4753f86e2a6916a83a182b4bb4148a8 Mon Sep 17 00:00:00 2001
From: Ryan Shpeherd <rotaryprophet@gmail.com>
Date: Mon, 14 Sep 2026 16:02:21 -0400
Subject: [PATCH] Fix scanner

---
 scanner/scanner.pl | 88 +++++++++++++++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 32 deletions(-)

diff --git a/scanner/scanner.pl b/scanner/scanner.pl
index a32ed9a..fd7a673 100755
--- a/scanner/scanner.pl
+++ b/scanner/scanner.pl
@@ -9,12 +9,20 @@ use String::ShellQuote qw/shell_quote/;
 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 $db_pass = $ENV{'DB_PASSWORD'} || 'videodetect';  
 
+my $do_scan = (defined $ENV{'DO_SCAN'}) ? $ENV{'DO_SCAN'} : 1;
+my $do_review = (defined $ENV{'DO_REVIEW'}) ? $ENV{'DO_REVIEW'} : 1;
+my $do_delete = (defined $ENV{'DO_DELETE'}) ? $ENV{'DO_DELETE'} : 1;
 
 $SIG{INT} = sub { die "Interrupted\n"; };
 
-my $dbh = DBI->connect("DBI:mysql:database=$db_name;host=$db_host", $db_user, $db_pass);
+my $dbh = DBI->connect(
+    "DBI:mysql:database=$db_name;host=$db_host;mysql_enable_utf8=1",
+    $db_user,
+    $db_pass,
+    { mysql_auto_reconnect => 1 }
+);
 
 my @video_extensions = qw(mp4 mkv avi mov flv wmv mpg mpeg webm m4v);
 my %ignored_extensions;
@@ -28,29 +36,36 @@ 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: $!";
-    print "$dir\n";
-    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);
+if($do_scan) {
+    while(my $dir = shift @dir_queue) {
+        opendir(my $dh, $dir) or die "Cannot open directory $dir: $!";
+        print "$dir\n";
+        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);
+    }
+    for my $ext (sort { $ignored_extensions{$b} <=> $ignored_extensions{$a} } keys %ignored_extensions) {
+        print "Ignored extension $ext: $ignored_extensions{$ext} times\n";
     }
-    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);
-for my $ext (sort { $ignored_extensions{$b} <=> $ignored_extensions{$a} } keys %ignored_extensions) {
-    print "Ignored extension $ext: $ignored_extensions{$ext} times\n";
+if($do_scan && $do_delete) {
+    # 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);
 }
 
-CreateReviewTasks();
+if($do_review) {
+    print "Scanning complete. Creating review tasks for completed AISCAN tasks.\n";
+    CreateReviewTasks();
+}
 
 sub process_file {
     my ($file_path) = @_;
@@ -177,25 +192,34 @@ sub get_video_info {
 }
 
 sub CreateReviewTasks {
+    # Fetch all completed AISCAN tasks and filter in Perl.
+    # This avoids MariaDB's inconsistent JSON functions in SQL WHERE clauses,
+    # which behave differently between CLI client and DBI connections.
     my $sth = $dbh->prepare("
-SELECT *
+SELECT id, video_id, results 
 FROM tasks
-WHERE task_type='AISCAN'
-AND status='COMPLETED'
-AND JSON_VALUE(results, '$.verdict')=1
-AND JSON_VALUE(results, '$.reviewed') IS NULL
-");
-    my $sth_update = $dbh->prepare("
-UPDATE tasks
-SET results = JSON_SET(results, '$.reviewed', 1)
-WHERE id = ?
+WHERE task_type='AISCAN' AND status='COMPLETED'
 ");
 
     $sth->execute();
-    while (my $row = $sth->fetchrow_hashref) {
+    while (my $row = $sth->fetchrow_hashref()) {
+        my $results = decode_json($row->{results});
+        next unless $results && ref($results) eq 'HASH';
+        next unless $results->{verdict} == 1;
+        next if exists $results->{reviewed};
+
+        print "Creating REVIEW task for video_id: $row->{video_id}\n";
         create_task($row->{video_id}, 'REVIEW');
-        $sth_update->execute($row->{id});
+
+        # Re-encode the whole JSON blob in Perl and update it.
+        # This avoids MariaDB JSON_SET path parsing issues through DBI connections.
+        $results->{reviewed} = 1;
+        my $updated = encode_json($results);
+        my $sth_update = $dbh->prepare(
+            "UPDATE tasks SET results = ? WHERE id = ?"
+        );
+        $sth_update->execute($updated, $row->{id});
+        $sth_update->finish();
     }
     $sth->finish();
-    $sth_update->finish();
 }
\ No newline at end of file