Merge branch 'antalya-25.8' into external-contributor-workflow

Author: strtgbb

.github/workflows/master.yml

@@ -4179,7 +4179,7 @@ jobs:
     secrets: inherit
     with:
       runner_type: altinity-regression-tester
-      commit: bd9d71b4ccc80bb5b1a316b43b60f59c0c592898
+      commit: 481dd0f61ec5b22430bfc4106ac30d9abfcf70b7
       arch: x86
       build_sha: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
       timeout_minutes: 300
@@ -4191,7 +4191,7 @@ jobs:
     secrets: inherit
     with:
       runner_type: altinity-regression-tester-aarch64
-      commit: bd9d71b4ccc80bb5b1a316b43b60f59c0c592898
+      commit: 481dd0f61ec5b22430bfc4106ac30d9abfcf70b7
       arch: aarch64
       build_sha: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
       timeout_minutes: 300

.github/workflows/pull_request.yml

@@ -4045,7 +4045,7 @@ jobs:
     secrets: inherit
     with:
       runner_type: altinity-regression-tester
-      commit: bd9d71b4ccc80bb5b1a316b43b60f59c0c592898
+      commit: 481dd0f61ec5b22430bfc4106ac30d9abfcf70b7
       arch: x86
       build_sha: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
       timeout_minutes: 300
@@ -4057,7 +4057,7 @@ jobs:
     secrets: inherit
     with:
       runner_type: altinity-regression-tester-aarch64
-      commit: bd9d71b4ccc80bb5b1a316b43b60f59c0c592898
+      commit: 481dd0f61ec5b22430bfc4106ac30d9abfcf70b7
       arch: aarch64
       build_sha: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
       timeout_minutes: 300

.github/workflows/regression-reusable-suite.yml

@@ -164,7 +164,7 @@ jobs:
           --clickhouse ${{ env.clickhouse_path }}
           ${{ env.REGRESSION_ARGS }}
           ${{ env.args }} || EXITCODE=$?;
-          .github/add_link_to_logs.sh
+          .github/add_link_to_logs.sh;
           exit $EXITCODE
 
       - name: 📊 Set Commit Status

.github/workflows/regression.yml

@@ -277,7 +277,7 @@ jobs:
       build_sha: ${{ inputs.build_sha }}
       set_commit_status: true
       job_name: iceberg
-      extra_args: --only ${{ matrix.PART == 1 && '"/iceberg/iceberg engine/rest catalog/*" "/iceberg/s3 table function/*" "/iceberg/icebergS3 table function/*" "/iceberg/iceberg cache"' || '"/iceberg/iceberg engine/glue catalog/*" "/iceberg/iceberg table engine/*"' }}
+      extra_args: --only ${{ matrix.PART == 1 && '"/iceberg/iceberg engine/rest catalog/*" "/iceberg/s3 table function/*" "/iceberg/icebergS3 table function/*" "/iceberg/iceberg cache/*"' || '"/iceberg/iceberg engine/glue catalog/*" "/iceberg/iceberg table engine/*"' }}
     secrets: inherit
   LDAP:
     if: |
@@ -432,6 +432,34 @@ jobs:
       extra_args: --only ":/try*" ":/part ${{ matrix.PART }}/*"
     secrets: inherit
 
+  S3Export:
+    if: |
+      fromJson(inputs.workflow_config).custom_data.ci_regression_jobs[0] == null ||
+      contains(fromJson(inputs.workflow_config).custom_data.ci_regression_jobs, 's3')
+    strategy:
+      fail-fast: false
+      matrix:
+        PART: [part, partition]
+    uses: ./.github/workflows/regression-reusable-suite.yml
+    with:
+      ref: ${{ inputs.commit }}
+      workflow_config: ${{ inputs.workflow_config }}
+      suite_name: s3
+      suite_executable: regression.py
+      output_format: new-fails
+      flags: --with-analyzer
+      timeout_minutes: ${{ inputs.timeout_minutes }}
+      runner_arch: ${{ inputs.arch }}
+      runner_type: ${{ inputs.runner_type }}
+      storage_path: /minio
+      part: ${{ matrix.PART }}
+      build_sha: ${{ inputs.build_sha }}
+      set_commit_status: true
+      job_name: s3_export
+      regression_args: --storage minio
+      extra_args: --only ":/try*" "minio/export tests/export ${{ matrix.PART }}/*"
+    secrets: inherit
+
   TieredStorage:
     if: |
       fromJson(inputs.workflow_config).custom_data.ci_regression_jobs[0] == null ||

ci/praktika/yaml_additional_templates.py

@@ -36,7 +36,7 @@ class AltinityWorkflowTemplates:
           echo "Workflow Run Report: [View Report]($REPORT_LINK)" >> $GITHUB_STEP_SUMMARY
 """
     # Additional jobs
-    REGRESSION_HASH = "bd9d71b4ccc80bb5b1a316b43b60f59c0c592898"
+    REGRESSION_HASH = f"481dd0f61ec5b22430bfc4106ac30d9abfcf70b7"
     ALTINITY_JOBS = {
         "GrypeScan": r"""
   GrypeScanServer:

docker/server/Dockerfile.ubuntu

@@ -15,6 +15,7 @@ ARG apt_archive="http://archive.ubuntu.com"
 # We do that in advance at the begining of Dockerfile before any packages will be
 # installed to prevent picking those uid / gid by some unrelated software.
 # The same uid / gid (101) is used both for alpine and ubuntu.
+# Update gpgv to resolve CVE-2025-68973
 RUN sed -i "s|http://archive.ubuntu.com|${apt_archive}|g" /etc/apt/sources.list \
     && groupadd -r clickhouse --gid=101 \
     && useradd -r -g clickhouse --uid=101 --home-dir=/var/lib/clickhouse --shell=/bin/bash clickhouse \
@@ -25,6 +26,7 @@ RUN sed -i "s|http://archive.ubuntu.com|${apt_archive}|g" /etc/apt/sources.list
         locales \
         tzdata \
         wget \
+        gpgv \
     && busybox --install -s \
     && rm -rf /var/lib/apt/lists/* /var/cache/debconf /tmp/*
 

src/Interpreters/InterpreterShowTablesQuery.cpp

@@ -232,10 +232,10 @@ BlockIO InterpreterShowTablesQuery::execute()
     }
     auto rewritten_query = getRewrittenQuery();
     String database = getContext()->resolveDatabase(query.getFrom());
-    if (DatabaseCatalog::instance().isDatalakeCatalog(database))
+    if (query.databases || DatabaseCatalog::instance().isDatalakeCatalog(database))
     {
         auto context_copy = Context::createCopy(getContext());
-        /// HACK To always show them in explicit "SHOW TABLES" queries
+        /// HACK To always show them in explicit "SHOW TABLES" and "SHOW DATABASES" queries
         context_copy->setSetting("show_data_lake_catalogs_in_system_tables", true);
         return executeQuery(rewritten_query, context_copy, QueryFlags{ .internal = true }).second;
     }

tests/integration/test_database_glue/test.py

@@ -617,6 +617,8 @@ def test_system_tables(started_cluster):
             node.query(f"SELECT count() FROM {CATALOG_NAME}.`{namespace}.{table_name}`")
         )
 
+    assert CATALOG_NAME in node.query("SHOW DATABASES")
+    assert table_name in node.query(f"SHOW TABLES FROM {CATALOG_NAME}")
     # system.tables
     assert int(node.query(f"SELECT count() FROM system.tables WHERE database = '{CATALOG_NAME}' and table ilike '%{root_namespace}%' SETTINGS show_data_lake_catalogs_in_system_tables = true").strip()) == 4
     assert int(node.query(f"SELECT count() FROM system.tables WHERE database = '{CATALOG_NAME}' and table ilike '%{root_namespace}%'").strip()) == 4