[
https://issues.apache.org/jira/browse/FLINK-2168?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15837091#comment-15837091
]
ASF GitHub Bot commented on FLINK-2168:
---------------------------------------
Github user wuchong commented on a diff in the pull request:
https://github.com/apache/flink/pull/3149#discussion_r97701834
--- Diff:
flink-connectors/flink-hbase/src/main/java/org/apache/flink/addons/hbase/HBaseTableSourceInputFormat.java
---
@@ -0,0 +1,160 @@
+/*
+ * 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.addons.hbase;
+
+import org.apache.flink.api.common.io.InputFormat;
+import org.apache.flink.api.common.typeinfo.TypeInformation;
+import org.apache.flink.api.java.typeutils.ResultTypeQueryable;
+import org.apache.flink.api.java.typeutils.RowTypeInfo;
+import org.apache.flink.configuration.Configuration;
+import org.apache.flink.types.Row;
+import org.apache.hadoop.hbase.HBaseConfiguration;
+import org.apache.hadoop.hbase.TableName;
+import org.apache.hadoop.hbase.TableNotFoundException;
+import org.apache.hadoop.hbase.client.HTable;
+import org.apache.hadoop.hbase.client.Connection;
+import org.apache.hadoop.hbase.client.ConnectionFactory;
+import org.apache.hadoop.hbase.client.Result;
+import org.apache.hadoop.hbase.client.Scan;
+import org.apache.hadoop.hbase.util.Bytes;
+import org.apache.hadoop.hbase.util.Pair;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.Map;
+
+/**
+ * {@link InputFormat} subclass that wraps the access for HTables. Returns
the result as {@link Row}
+ */
+public class HBaseTableSourceInputFormat extends TableInputFormat<Row>
implements ResultTypeQueryable<Row> {
+
+ private static final long serialVersionUID = 1L;
+
+ private static final Logger LOG =
LoggerFactory.getLogger(HBaseTableSourceInputFormat.class);
+ private String tableName;
+ private transient Connection conn;
+ private transient org.apache.hadoop.conf.Configuration conf;
+ private HBaseTableSchema schema;
+
+ public HBaseTableSourceInputFormat(org.apache.hadoop.conf.Configuration
conf, String tableName, HBaseTableSchema schema) {
+ this.tableName = tableName;
+ this.conf = conf;
+ this.schema = schema;
+ }
+
+ @Override
+ public void configure(Configuration parameters) {
+ LOG.info("Initializing HBaseConfiguration");
+ connectToTable();
+ if(table != null) {
+ scan = getScanner();
+ }
+ }
+
+ @Override
+ protected Scan getScanner() {
+ // TODO : Pass 'rowkey'. For this we need FilterableTableSource
+ Scan scan = new Scan();
+ Map<String, List<Pair>> familyMap = schema.getFamilyMap();
+ for(String family : familyMap.keySet()) {
+ // select only the fields in the 'selectedFields'
+ List<Pair> colDetails = familyMap.get(family);
+ for(Pair<String, TypeInformation<?>> pair : colDetails)
{
+ scan.addColumn(Bytes.toBytes(family),
Bytes.toBytes(pair.getFirst()));
+ }
+ }
+ return scan;
+ }
+
+ @Override
+ public String getTableName() {
+ return tableName;
+ }
+
+ @Override
+ protected Row mapResultToTuple(Result res) {
+ List<Object> values = new ArrayList<Object>();
+ int i = 0;
+ Map<String, List<Pair>> familyMap = schema.getFamilyMap();
+ Row[] rows = new Row[familyMap.size()];
+ for(String family : familyMap.keySet()) {
+ List<Pair> colDetails = familyMap.get(family);
+ for(Pair<String, TypeInformation<?>> pair : colDetails)
{
+ byte[] value =
res.getValue(Bytes.toBytes(family), Bytes.toBytes(pair.getFirst()));
+ if(value != null) {
+ values.add(schema.deserialize(value,
pair.getSecond()));
+ } else {
+
values.add(schema.deserializeNull(pair.getSecond()));
--- End diff --
Do we really need this method to indicate `null` using the special default
value? Why not set null `values.add(null)` directly ?
`Row` supports nullable field, but Tuple doesn't.
> Add HBaseTableSource
> --------------------
>
> Key: FLINK-2168
> URL: https://issues.apache.org/jira/browse/FLINK-2168
> Project: Flink
> Issue Type: New Feature
> Components: Table API & SQL
> Affects Versions: 0.9
> Reporter: Fabian Hueske
> Assignee: ramkrishna.s.vasudevan
> Priority: Minor
> Labels: starter
>
> Add a {{HBaseTableSource}} to read data from a HBase table. The
> {{HBaseTableSource}} should implement the {{ProjectableTableSource}}
> (FLINK-3848) and {{FilterableTableSource}} (FLINK-3849) interfaces.
> The implementation can be based on Flink's {{TableInputFormat}}.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
