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
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
|
/*
* 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
import org.apache.hadoop.fs.Path
import org.apache.spark.internal.Logging
import org.apache.spark.internal.io.FileCommitProtocol
import org.apache.spark.sql.{DataFrame, SparkSession}
import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.execution.datasources.{FileFormat, FileFormatWriter}
object FileStreamSink {
// The name of the subdirectory that is used to store metadata about which files are valid.
val metadataDir = "_spark_metadata"
}
/**
* A sink that writes out results to parquet files. Each batch is written out to a unique
* directory. After all of the files in a batch have been successfully written, the list of
* file paths is appended to the log atomically. In the case of partial failures, some duplicate
* data may be present in the target directory, but only one copy of each file will be present
* in the log.
*/
class FileStreamSink(
sparkSession: SparkSession,
path: String,
fileFormat: FileFormat,
partitionColumnNames: Seq[String],
options: Map[String, String]) extends Sink with Logging {
private val basePath = new Path(path)
private val logPath = new Path(basePath, FileStreamSink.metadataDir)
private val fileLog =
new FileStreamSinkLog(FileStreamSinkLog.VERSION, sparkSession, logPath.toUri.toString)
private val hadoopConf = sparkSession.sessionState.newHadoopConf()
override def addBatch(batchId: Long, data: DataFrame): Unit = {
if (batchId <= fileLog.getLatest().map(_._1).getOrElse(-1L)) {
logInfo(s"Skipping already committed batch $batchId")
} else {
val committer = FileCommitProtocol.instantiate(
className = sparkSession.sessionState.conf.streamingFileCommitProtocolClass,
jobId = batchId.toString,
outputPath = path,
isAppend = false)
committer match {
case manifestCommitter: ManifestFileCommitProtocol =>
manifestCommitter.setupManifestOptions(fileLog, batchId)
case _ => // Do nothing
}
// Get the actual partition columns as attributes after matching them by name with
// the given columns names.
val partitionColumns: Seq[Attribute] = partitionColumnNames.map { col =>
val nameEquality = data.sparkSession.sessionState.conf.resolver
data.logicalPlan.output.find(f => nameEquality(f.name, col)).getOrElse {
throw new RuntimeException(s"Partition column $col not found in schema ${data.schema}")
}
}
FileFormatWriter.write(
sparkSession = sparkSession,
plan = data.logicalPlan,
fileFormat = fileFormat,
committer = committer,
outputSpec = FileFormatWriter.OutputSpec(path, Map.empty),
hadoopConf = hadoopConf,
partitionColumns = partitionColumns,
bucketSpec = None,
refreshFunction = _ => (),
options = options)
}
}
override def toString: String = s"FileSink[$path]"
}
|
