[GitHub] [flink] bowenli86 commented on a change in pull request #11990: [FLINK-17387][hive] Implement LookupableTableSource for Hive connector

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

bowenli86 commented on a change in pull request #11990:
URL: https://github.com/apache/flink/pull/11990#discussion_r422294096



##########
File path: flink-connectors/flink-connector-hive/src/main/java/org/apache/flink/connectors/hive/read/HiveTableLookupFunction.java
##########
@@ -0,0 +1,142 @@
+/*
+ * 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.flink.connectors.hive.read;
+
+import org.apache.flink.api.common.typeinfo.TypeInformation;
+import org.apache.flink.connectors.hive.FlinkHiveException;
+import org.apache.flink.table.data.GenericRowData;
+import org.apache.flink.table.data.RowData;
+import org.apache.flink.table.functions.FunctionContext;
+import org.apache.flink.table.functions.TableFunction;
+import org.apache.flink.table.runtime.typeutils.RowDataTypeInfo;
+import org.apache.flink.table.types.DataType;
+import org.apache.flink.table.types.logical.LogicalType;
+import org.apache.flink.util.Preconditions;
+
+import java.io.IOException;
+import java.time.Duration;
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+import java.util.stream.Collectors;
+import java.util.stream.IntStream;
+
+/**
+ * Lookup table function for Hive tables.
+ */
+public class HiveTableLookupFunction extends TableFunction<RowData> {
+
+	private static final long serialVersionUID = 1L;
+
+	private final HiveTableInputFormat inputFormat;
+	// indices of lookup columns in the record returned by input format
+	private final int[] lookupCols;
+	private transient Map<RowData, List<RowData>> cache;
+	// timestamp when cache expires
+	private transient long cacheExpire;
+	private final Duration cacheTTL = Duration.ofHours(1);
+
+	public HiveTableLookupFunction(HiveTableInputFormat inputFormat, String[] lookupKeys) {
+		lookupCols = new int[lookupKeys.length];
+		String[] allFields = inputFormat.getFieldNames();
+		Map<String, Integer> nameToIndex = IntStream.range(0, allFields.length).boxed().collect(
+				Collectors.toMap(i -> allFields[i], i -> i));
+		List<Integer> selectedIndices = Arrays.stream(inputFormat.getSelectedFields()).boxed().collect(Collectors.toList());
+		for (int i = 0; i < lookupKeys.length; i++) {
+			Integer index = nameToIndex.get(lookupKeys[i]);
+			Preconditions.checkArgument(index != null, "Lookup keys %s not found in table schema", Arrays.toString(lookupKeys));
+			index = selectedIndices.indexOf(index);
+			Preconditions.checkArgument(index >= 0, "Lookup keys %s not selected", Arrays.toString(lookupKeys));
+			lookupCols[i] = index;
+		}
+		this.inputFormat = inputFormat;
+	}
+
+	@Override
+	public TypeInformation<RowData> getResultType() {
+		String[] allNames = inputFormat.getFieldNames();
+		DataType[] allTypes = inputFormat.getFieldTypes();
+		int[] selected = inputFormat.getSelectedFields();
+		return new RowDataTypeInfo(
+				Arrays.stream(selected).mapToObj(i -> allTypes[i].getLogicalType()).toArray(LogicalType[]::new),
+				Arrays.stream(selected).mapToObj(i -> allNames[i]).toArray(String[]::new));
+	}
+
+	@Override
+	public void open(FunctionContext context) throws Exception {
+		super.open(context);
+		cache = new HashMap<>();
+		cacheExpire = -1;
+	}
+
+	public void eval(Object... values) {
+		Preconditions.checkArgument(values.length == lookupCols.length, "Number of values and lookup keys mismatch");
+		reloadCache();
+		RowData probeKey = GenericRowData.of(values);
+		List<RowData> matchedRows = cache.get(probeKey);
+		if (matchedRows != null) {
+			for (RowData matchedRow : matchedRows) {
+				collect(matchedRow);
+			}
+		}
+	}
+
+	private void reloadCache() {

Review comment:
       does it mean it caches all rows of a hive file?




----------------------------------------------------------------
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