[GitHub] [iceberg] JingsongLi commented on a change in pull request #1182: Integrate Iceberg catalog to Flink catalog

[GitBox <gi...@apache.org>]

JingsongLi commented on a change in pull request #1182:
URL: https://github.com/apache/iceberg/pull/1182#discussion_r453395113



##########
File path: flink/src/main/java/org/apache/iceberg/flink/FlinkCatalog.java
##########
@@ -0,0 +1,508 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *   http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied.  See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.apache.iceberg.flink;
+
+import java.io.Closeable;
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.Collections;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+import java.util.Set;
+import java.util.stream.Collectors;
+import org.apache.flink.table.api.TableSchema;
+import org.apache.flink.table.catalog.AbstractCatalog;
+import org.apache.flink.table.catalog.CatalogBaseTable;
+import org.apache.flink.table.catalog.CatalogDatabase;
+import org.apache.flink.table.catalog.CatalogDatabaseImpl;
+import org.apache.flink.table.catalog.CatalogFunction;
+import org.apache.flink.table.catalog.CatalogPartition;
+import org.apache.flink.table.catalog.CatalogPartitionSpec;
+import org.apache.flink.table.catalog.CatalogTableImpl;
+import org.apache.flink.table.catalog.ObjectPath;
+import org.apache.flink.table.catalog.exceptions.CatalogException;
+import org.apache.flink.table.catalog.exceptions.DatabaseAlreadyExistException;
+import org.apache.flink.table.catalog.exceptions.DatabaseNotEmptyException;
+import org.apache.flink.table.catalog.exceptions.DatabaseNotExistException;
+import org.apache.flink.table.catalog.exceptions.FunctionNotExistException;
+import org.apache.flink.table.catalog.exceptions.TableAlreadyExistException;
+import org.apache.flink.table.catalog.exceptions.TableNotExistException;
+import org.apache.flink.table.catalog.stats.CatalogColumnStatistics;
+import org.apache.flink.table.catalog.stats.CatalogTableStatistics;
+import org.apache.flink.table.expressions.Expression;
+import org.apache.flink.util.StringUtils;
+import org.apache.iceberg.CachingCatalog;
+import org.apache.iceberg.Table;
+import org.apache.iceberg.catalog.Catalog;
+import org.apache.iceberg.catalog.Namespace;
+import org.apache.iceberg.catalog.SupportsNamespaces;
+import org.apache.iceberg.catalog.TableIdentifier;
+import org.apache.iceberg.exceptions.AlreadyExistsException;
+import org.apache.iceberg.exceptions.NamespaceNotEmptyException;
+import org.apache.iceberg.exceptions.NoSuchNamespaceException;
+import org.apache.iceberg.relocated.com.google.common.collect.Maps;
+import org.apache.iceberg.relocated.com.google.common.collect.Sets;
+
+/**
+ * A Flink Catalog implementation that wraps an Iceberg {@link Catalog}.
+ * <p>
+ * The mapping between Flink database and Iceberg namespace:
+ * Supplying a base namespace for a given catalog, so if you have a catalog that supports a 2-level namespace, you
+ * would supply the first level in the catalog configuration and the second level would be exposed as Flink databases.
+ * <p>
+ * The Iceberg table manages its partitions by itself. The partition of the Iceberg table is independent of the
+ * partition of Flink.
+ */
+public class FlinkCatalog extends AbstractCatalog {
+
+  private final Catalog originalCatalog;
+  private final Catalog icebergCatalog;
+  private final String[] baseNamespace;
+  private final SupportsNamespaces asNamespaceCatalog;
+
+  public FlinkCatalog(
+      String catalogName,
+      String defaultDatabase,
+      String[] baseNamespace,
+      Catalog icebergCatalog,
+      boolean cacheEnabled) {
+    super(catalogName, defaultDatabase);
+    this.originalCatalog = icebergCatalog;
+    this.icebergCatalog = cacheEnabled ? CachingCatalog.wrap(icebergCatalog) : icebergCatalog;
+    this.baseNamespace = baseNamespace;
+    if (icebergCatalog instanceof SupportsNamespaces) {
+      asNamespaceCatalog = (SupportsNamespaces) icebergCatalog;
+    } else {
+      asNamespaceCatalog = null;
+    }
+  }
+
+  @Override
+  public void open() throws CatalogException {
+  }
+
+  @Override
+  public void close() throws CatalogException {
+    if (originalCatalog instanceof Closeable) {
+      try {
+        ((Closeable) originalCatalog).close();
+      } catch (IOException e) {
+        throw new CatalogException(e);
+      }
+    }
+  }
+
+  private Namespace toNamespace(String database) {
+    String[] namespace = new String[baseNamespace.length + 1];
+    System.arraycopy(baseNamespace, 0, namespace, 0, baseNamespace.length);
+    namespace[baseNamespace.length] = database;
+    return Namespace.of(namespace);
+  }
+
+  private TableIdentifier toIdentifier(ObjectPath path) {
+    return TableIdentifier.of(toNamespace(path.getDatabaseName()), path.getObjectName());
+  }
+
+  @Override
+  public List<String> listDatabases() throws CatalogException {
+    if (asNamespaceCatalog == null) {
+      return Collections.singletonList(getDefaultDatabase());
+    }
+
+    return listAllNamespaces(Namespace.empty()).stream()
+        .map(n -> n.level(n.levels().length - 1))
+        .collect(Collectors.toList());
+  }
+
+  private List<Namespace> listAllNamespaces(Namespace namespace) {
+    if (asNamespaceCatalog == null) {
+      throw new RuntimeException("The asNamespaceCatalog should not be null.");
+    }
+
+    String[] levels = namespace.levels();
+    if (levels.length == baseNamespace.length + 1) {
+      return Collections.singletonList(namespace);
+    }
+    if (levels.length < baseNamespace.length + 1) {
+      for (int i = 0; i < levels.length; i++) {
+        if (!baseNamespace[i].equals(levels[i])) {
+          return Collections.emptyList();
+        }
+      }
+      List<Namespace> ret = new ArrayList<>();
+      asNamespaceCatalog.listNamespaces(namespace).forEach(n -> ret.addAll(listAllNamespaces(n)));

Review comment:
       You are right, `asNamespaceCatalog.listNamespaces(Namespace.of(baseNamespace))` is enough.




----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org



---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@iceberg.apache.org
For additional commands, e-mail: issues-help@iceberg.apache.org