Github user aljoscha commented on a diff in the pull request:
https://github.com/apache/flink/pull/2020#discussion_r65212915
--- Diff:
flink-streaming-java/src/main/java/org/apache/flink/streaming/api/functions/source/ContinuousFileMonitoringFunction.java
---
@@ -0,0 +1,336 @@
+/*
+ * 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.streaming.api.functions.source;
+
+import org.apache.flink.annotation.Internal;
+import org.apache.flink.api.common.io.FileInputFormat;
+import org.apache.flink.api.java.tuple.Tuple2;
+import org.apache.flink.api.java.tuple.Tuple3;
+import org.apache.flink.configuration.Configuration;
+import org.apache.flink.core.fs.FileInputSplit;
+import org.apache.flink.core.fs.FileStatus;
+import org.apache.flink.core.fs.FileSystem;
+import org.apache.flink.core.fs.Path;
+import org.apache.flink.runtime.JobException;
+import org.apache.flink.streaming.api.checkpoint.Checkpointed;
+import org.apache.flink.util.Preconditions;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import java.io.IOException;
+import java.net.URI;
+import java.util.ArrayList;
+import java.util.Collections;
+import java.util.Comparator;
+import java.util.HashMap;
+import java.util.Iterator;
+import java.util.LinkedList;
+import java.util.List;
+import java.util.Map;
+
+/**
+ * This is the single (non-parallel) task which takes a {@link
FileInputFormat} and is responsible for
+ * i) monitoring a user-provided path, ii) deciding which files should be
further read and processed,
+ * iii) creating the {@link FileInputSplit FileInputSplits} corresponding
to those files, and iv) assigning
+ * them to downstream tasks for further reading and processing. Which
splits will be further processed
+ * depends on the user-provided {@link ProcessingMode} and the {@link
FilePathFilter}.
+ * The splits of the files to be read are then forwarded to the downstream
+ * {@link ContinuousFileReaderOperator} which can have parallelism greater
than one.
+ */
+@Internal
+public class ContinuousFileMonitoringFunction<OUT>
+ extends RichSourceFunction<FileInputSplit> implements
Checkpointed<Tuple3<List<Tuple2<Long, List<FileInputSplit>>>, Tuple2<Long,
List<FileInputSplit>>, Long>> {
+
+ private static final long serialVersionUID = 1L;
+
+ private static final Logger LOG =
LoggerFactory.getLogger(ContinuousFileMonitoringFunction.class);
+
+ /**
+ * The minimum interval allowed between consecutive path scans. This is
applicable if the
+ * {@code watchType} is set to {@code PROCESS_CONTINUOUSLY}.
+ */
+ public static final long MIN_MONITORING_INTERVAL = 100l;
+
+ /**
+ * Specifies when computation will be triggered.
+ */
+ public enum ProcessingMode {
--- End diff --
We should probably move this outside of this class and probably name it
`FileProcessingMode`. Just in case we want to change the actual file source
again. ð
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
