From 245c0b00539de5806038106ec4de889ee6ee233a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Tom=C3=A1s=20Cohen=20Arazi?= <tomascohen@theke.io>
Date: Thu, 21 May 2026 23:44:46 -0300
Subject: [PATCH] Bug 42669: Fix es_indexer_daemon.pl silent job failure and
 NoNodes recovery

When update_index() throws, the daemon now:
- On NoNodes: aborts the batch, recreates the indexer object to reset
  the dead-node connection pool, and resets jobs to 'new' for retry.
- On other errors: marks jobs as 'failed' instead of 'finished'.

This prevents silent data loss where records disappear from search
results because their indexing jobs were incorrectly marked as done.

Signed-off-by: Martin Renvoize <martin.renvoize@openfifth.co.uk>
Signed-off-by: Lisette Scheer <lisette@bywatersolutions.com>
Signed-off-by: Lucas Gass <lucas@bywatersolutions.com>
(cherry picked from commit 3183061da95420fab5d2775e2b7019c9d29b642c)
Signed-off-by: Baptiste Wojtkowski <baptiste.wojtkowski@biblibre.com>
---
 misc/workers/es_indexer_daemon.pl | 41 ++++++++++++++++++++++++++++---
 1 file changed, 37 insertions(+), 4 deletions(-)

diff --git a/misc/workers/es_indexer_daemon.pl b/misc/workers/es_indexer_daemon.pl
index 374e639fd6..9b7fa109de 100755
--- a/misc/workers/es_indexer_daemon.pl
+++ b/misc/workers/es_indexer_daemon.pl
@@ -211,6 +211,8 @@ $conn->disconnect;
 sub commit {
     my (@jobs) = @_;
 
+    return unless @jobs;
+
     my @bib_records;
     my @auth_records;
 
@@ -241,32 +243,63 @@ sub commit {
         }
     }
 
+    my $index_ok = 1;
+    my $no_nodes = 0;
+
     if (@auth_records) {
         my $auth_chunks = natatime $at_a_time, @auth_records;
-        while ( ( my @auth_chunk = $auth_chunks->() ) ) {
+        while ( !$no_nodes && ( my @auth_chunk = $auth_chunks->() ) ) {
             try {
                 $auth_indexer->update_index( \@auth_chunk );
             } catch {
                 $logger->warn( sprintf "Update of elastic index failed with: %s", $_ );
+                if ( "$_" =~ /NoNodes/ ) {
+                    $no_nodes = 1;
+                    $auth_indexer =
+                        Koha::SearchEngine::Indexer->new( { index => $Koha::SearchEngine::AUTHORITIES_INDEX } );
+                } else {
+                    $index_ok = 0;
+                }
             };
         }
     }
-    if (@bib_records) {
+    if ( !$no_nodes && @bib_records ) {
         my $biblio_chunks = natatime $at_a_time, @bib_records;
-        while ( ( my @bib_chunk = $biblio_chunks->() ) ) {
+        while ( !$no_nodes && ( my @bib_chunk = $biblio_chunks->() ) ) {
             try {
                 $biblio_indexer->update_index( \@bib_chunk );
             } catch {
                 $logger->warn( sprintf "Update of elastic index failed with: %s", $_ );
+                if ( "$_" =~ /NoNodes/ ) {
+                    $no_nodes = 1;
+                    $biblio_indexer =
+                        Koha::SearchEngine::Indexer->new( { index => $Koha::SearchEngine::BIBLIOS_INDEX } );
+                } else {
+                    $index_ok = 0;
+                }
             };
         }
     }
 
+    if ($no_nodes) {
+
+        # ES is unreachable — reset jobs to 'new' so they are retried after reconnection
+        $logger->warn("Elasticsearch unavailable (NoNodes), resetting jobs for retry");
+        $jobs->update(
+            {
+                progress   => 0,
+                status     => 'new',
+                started_on => undef,
+            }
+        );
+        return;
+    }
+
     # Finish
     $jobs->update(
         {
             progress => 1,
-            status   => 'finished',
+            status   => $index_ok ? 'finished' : 'failed',
             ended_on => \'NOW()',
         }
     );