From 502df284fbb6e8857fa83675810abe4489b57b39 Mon Sep 17 00:00:00 2001
From: Anton Ivashkin <ianton@live.com>
Date: Thu, 19 Mar 2026 12:04:43 +0100
Subject: [PATCH] Fix remote initiator host name

---
 src/Storages/IStorageCluster.cpp              |  4 +-
 .../test_s3_cluster/configs/cluster.xml       | 52 +++++++++++++
 tests/integration/test_s3_cluster/test.py     | 74 +++++++++++++++++++
 3 files changed, 129 insertions(+), 1 deletion(-)

diff --git a/src/Storages/IStorageCluster.cpp b/src/Storages/IStorageCluster.cpp
index b7d72ce08ce8..3f09a0a595bf 100644
--- a/src/Storages/IStorageCluster.cpp
+++ b/src/Storages/IStorageCluster.cpp
@@ -34,6 +34,7 @@
 #include <Analyzer/JoinNode.h>
 #include <Analyzer/InDepthQueryTreeVisitor.h>
 #include <Analyzer/Utils.h>
+#include <Poco/URI.h>
 
 #include <algorithm>
 #include <memory>
@@ -405,7 +406,8 @@ IStorageCluster::RemoteCallVariables IStorageCluster::convertToRemote(
     /// After getClusterImpl each shard must have exactly 1 replica
     if (shard_addresses.size() != 1)
         throw Exception(ErrorCodes::LOGICAL_ERROR, "Size of shard {} in cluster {} is not equal 1", shard_num, cluster_name_from_settings);
-    auto host_name = shard_addresses[0].toString();
+    std::string host_name;
+    Poco::URI::decode(shard_addresses[0].toString(), host_name);
 
     LOG_INFO(log, "Choose remote initiator '{}'", host_name);
 
diff --git a/tests/integration/test_s3_cluster/configs/cluster.xml b/tests/integration/test_s3_cluster/configs/cluster.xml
index 84e6afd12f71..0452a383a709 100644
--- a/tests/integration/test_s3_cluster/configs/cluster.xml
+++ b/tests/integration/test_s3_cluster/configs/cluster.xml
@@ -20,6 +20,20 @@
         </shard>
     </cluster_simple>
 
+    <!-- Cluster without s0_0_0-->
+    <cluster_remote>
+        <shard>
+            <replica>
+                <host>s0_0_1</host>
+                <port>9000</port>
+            </replica>
+            <replica>
+                <host>s0_1_0</host>
+                <port>9000</port>
+            </replica>
+        </shard>
+    </cluster_remote>
+
     <!-- A part of the cluster above, represents only one shard-->
     <first_shard>
         <shard>
@@ -49,6 +63,44 @@
         </shard>
     </cluster_non_existent_port>
 
+    <cluster_with_dots>
+        <shard>
+            <replica>
+                <host>c2.s0_0_0</host>
+                <port>9000</port>
+            </replica>
+            <replica>
+                <host>c2.s0_0_1</host>
+                <port>9000</port>
+            </replica>
+        </shard>
+    </cluster_with_dots>
+
+    <cluster_all>
+        <shard>
+            <replica>
+                <host>s0_0_0</host>
+                <port>9000</port>
+            </replica>
+            <replica>
+                <host>s0_0_1</host>
+                <port>9000</port>
+            </replica>
+            <replica>
+                <host>s0_1_0</host>
+                <port>9000</port>
+            </replica>
+            <replica>
+                <host>c2.s0_0_0</host>
+                <port>9000</port>
+            </replica>
+            <replica>
+                <host>c2.s0_0_1</host>
+                <port>9000</port>
+            </replica>
+        </shard>
+    </cluster_all>
+
     </remote_servers>
     <macros>
         <default_cluster_macro>cluster_simple</default_cluster_macro>
diff --git a/tests/integration/test_s3_cluster/test.py b/tests/integration/test_s3_cluster/test.py
index a1397da6eea6..77626af827ee 100644
--- a/tests/integration/test_s3_cluster/test.py
+++ b/tests/integration/test_s3_cluster/test.py
@@ -114,6 +114,22 @@ def started_cluster():
             with_zookeeper=True,
             stay_alive=True,
         )
+        cluster.add_instance(
+            "c2.s0_0_0",
+            main_configs=["configs/cluster.xml", "configs/named_collections.xml"],
+            user_configs=["configs/users.xml"],
+            macros={"replica": "replica1", "shard": "shard1"},
+            with_zookeeper=True,
+            stay_alive=True,
+        )
+        cluster.add_instance(
+            "c2.s0_0_1",
+            main_configs=["configs/cluster.xml", "configs/named_collections.xml"],
+            user_configs=["configs/users.xml"],
+            macros={"replica": "replica2", "shard": "shard1"},
+            with_zookeeper=True,
+            stay_alive=True,
+        )
 
         logging.info("Starting cluster...")
         cluster.start()
@@ -1197,3 +1213,61 @@ def test_joins(started_cluster):
     )
     res = list(map(str.split, result8.splitlines()))
     assert len(res) == 25
+
+
+def test_object_storage_remote_initiator(started_cluster):
+    node = started_cluster.instances["s0_0_0"]
+
+    query_id = uuid.uuid4().hex
+    result = node.query(
+        f"""
+        SELECT * from s3Cluster(
+            'cluster_remote',
+            'http://minio1:9001/root/data/{{clickhouse,database}}/*', 'minio', '{minio_secret_key}', 'CSV',
+            'name String, value UInt32, polygon Array(Array(Tuple(Float64, Float64)))') ORDER BY (name, value, polygon)
+        SETTINGS object_storage_remote_initiator=1
+        """,
+        query_id = query_id,
+    )
+
+    assert result is not None
+
+    node.query("SYSTEM FLUSH LOGS ON CLUSTER 'cluster_all'")
+    queries = node.query(
+        f"""
+        SELECT count()
+            FROM clusterAllReplicas('cluster_all', system.query_log)
+            WHERE type='QueryFinish' AND initial_query_id='{query_id}'
+            FORMAT TSV
+        """
+    ).splitlines()
+
+    # initial node + describe table + remote initiator + 2 subqueries on replicas
+    assert queries == ["5"]
+
+    query_id = uuid.uuid4().hex
+    result = node.query(
+        f"""
+        SELECT * from s3Cluster(
+            'cluster_with_dots',
+            'http://minio1:9001/root/data/{{clickhouse,database}}/*', 'minio', '{minio_secret_key}', 'CSV',
+            'name String, value UInt32, polygon Array(Array(Tuple(Float64, Float64)))') ORDER BY (name, value, polygon)
+        SETTINGS object_storage_remote_initiator=1
+        """,
+        query_id = query_id,
+    )
+
+    assert result is not None
+
+    node.query("SYSTEM FLUSH LOGS ON CLUSTER 'cluster_all'")
+    queries = node.query(
+        f"""
+        SELECT count()
+            FROM clusterAllReplicas('cluster_all', system.query_log)
+            WHERE type='QueryFinish' AND initial_query_id='{query_id}'
+            FORMAT TSV
+        """
+    ).splitlines()
+
+    # initial node + describe table + remote initiator + 2 subqueries on replicas
+    assert queries == ["5"]