[GitHub] [incubator-seatunnel] EricJoy2048 commented on a diff in pull request #2399: [Feature][Connector-V2] Add base source connector code for connector-file-base

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

EricJoy2048 commented on code in PR #2399:
URL: https://github.com/apache/incubator-seatunnel/pull/2399#discussion_r945155962


##########
seatunnel-connectors-v2/connector-file/connector-file-base/src/main/java/org/apache/seatunnel/connectors/seatunnel/file/source/reader/AbstractReadStrategy.java:
##########
@@ -0,0 +1,86 @@
+/*
+ * 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.seatunnel.connectors.seatunnel.file.source.reader;
+
+import org.apache.seatunnel.connectors.seatunnel.file.config.HadoopConf;
+import org.apache.seatunnel.connectors.seatunnel.file.exception.FilePluginException;
+
+import lombok.extern.slf4j.Slf4j;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.CommonConfigurationKeys;
+import org.apache.hadoop.fs.FileStatus;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.List;
+
+@Slf4j
+public abstract class AbstractReadStrategy implements ReadStrategy {
+    HadoopConf hadoopConf;
+
+    @Override
+    public void init(HadoopConf conf) {
+        this.hadoopConf = conf;
+    }
+
+    @Override
+    public Configuration getConfiguration(HadoopConf hadoopConf) {

Review Comment:
   I guess the `S3 File Source` and `OSS File Source` will extend this class too. Does the `Configuration` can use for read `S3 File` and `OSS File`?



##########
seatunnel-connectors-v2/connector-file/connector-file-base/src/main/java/org/apache/seatunnel/connectors/seatunnel/file/source/BaseFileSourceReader.java:
##########
@@ -0,0 +1,92 @@
+/*
+ * 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.seatunnel.connectors.seatunnel.file.source;
+
+import org.apache.seatunnel.api.source.Collector;
+import org.apache.seatunnel.api.source.SourceReader;
+import org.apache.seatunnel.api.table.type.SeaTunnelRow;
+import org.apache.seatunnel.connectors.seatunnel.file.config.HadoopConf;
+import org.apache.seatunnel.connectors.seatunnel.file.source.reader.ReadStrategy;
+import org.apache.seatunnel.connectors.seatunnel.file.source.split.FileSourceSplit;
+
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Set;
+
+public class BaseFileSourceReader implements SourceReader<SeaTunnelRow, FileSourceSplit> {
+    private static final long THREAD_WAIT_TIME = 500L;
+    private final ReadStrategy readStrategy;
+    private final HadoopConf hadoopConf;
+    private final SourceReader.Context context;
+    private final Set<FileSourceSplit> sourceSplits;
+
+    public BaseFileSourceReader(ReadStrategy readStrategy, HadoopConf hadoopConf, SourceReader.Context context) {
+        this.readStrategy = readStrategy;
+        this.hadoopConf = hadoopConf;
+        this.context = context;
+        this.sourceSplits = new HashSet<>();
+    }
+
+    @Override
+    public void open() throws Exception {
+        readStrategy.init(hadoopConf);
+    }
+
+    @Override
+    public void close() throws IOException {
+
+    }
+
+    @Override
+    public void pollNext(Collector<SeaTunnelRow> output) throws Exception {
+        if (sourceSplits.isEmpty()) {
+            Thread.sleep(THREAD_WAIT_TIME);
+            return;
+        }
+        sourceSplits.forEach(source -> {
+            try {
+                readStrategy.read(source.splitId(), output);
+            } catch (Exception e) {
+                throw new RuntimeException("File source read error", e);
+            }
+        });
+        context.signalNoMoreElement();

Review Comment:
   We should consider that the `File Source Connector` should also support streaming jobs? In the feature, we plan to support read local file in streaming model which is like `Flume`. Of course, you can improve it in the future PR.



-- 
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.

To unsubscribe, e-mail: commits-unsubscribe@seatunnel.apache.org

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