aboutsummaryrefslogtreecommitdiff
path: root/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/MetadataLog.scala
blob: 9e2604c9c069f0888ce32da2596fdc00ed8fa6ba (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
/*
* 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.spark.sql.execution.streaming

/**
 * A general MetadataLog that supports the following features:
 *
 *  - Allow the user to store a metadata object for each batch.
 *  - Allow the user to query the latest batch id.
 *  - Allow the user to query the metadata object of a specified batch id.
 *  - Allow the user to query metadata objects in a range of batch ids.
 *  - Allow the user to remove obsolete metadata
 */
trait MetadataLog[T] {

  /**
   * Store the metadata for the specified batchId and return `true` if successful. If the batchId's
   * metadata has already been stored, this method will return `false`.
   */
  def add(batchId: Long, metadata: T): Boolean

  /**
   * Return the metadata for the specified batchId if it's stored. Otherwise, return None.
   */
  def get(batchId: Long): Option[T]

  /**
   * Return metadata for batches between startId (inclusive) and endId (inclusive). If `startId` is
   * `None`, just return all batches before endId (inclusive).
   */
  def get(startId: Option[Long], endId: Option[Long]): Array[(Long, T)]

  /**
   * Return the latest batch Id and its metadata if exist.
   */
  def getLatest(): Option[(Long, T)]

  /**
   * Removes all the log entry earlier than thresholdBatchId (exclusive).
   * This operation should be idempotent.
   */
  def purge(thresholdBatchId: Long): Unit
}