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
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
|
/*
* 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.datasources.text
import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.{FileStatus, Path}
import org.apache.hadoop.io.{NullWritable, Text}
import org.apache.hadoop.mapreduce.{Job, RecordWriter, TaskAttemptContext}
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat
import org.apache.spark.sql.{AnalysisException, Row, SQLContext}
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.catalyst.expressions.UnsafeRow
import org.apache.spark.sql.catalyst.expressions.codegen.{BufferHolder, UnsafeRowWriter}
import org.apache.spark.sql.execution.datasources._
import org.apache.spark.sql.sources._
import org.apache.spark.sql.types.{StringType, StructType}
import org.apache.spark.util.SerializableConfiguration
/**
* A data source for reading text files.
*/
class DefaultSource extends FileFormat with DataSourceRegister {
override def shortName(): String = "text"
private def verifySchema(schema: StructType): Unit = {
if (schema.size != 1) {
throw new AnalysisException(
s"Text data source supports only a single column, and you have ${schema.size} columns.")
}
val tpe = schema(0).dataType
if (tpe != StringType) {
throw new AnalysisException(
s"Text data source supports only a string column, but you have ${tpe.simpleString}.")
}
}
override def inferSchema(
sqlContext: SQLContext,
options: Map[String, String],
files: Seq[FileStatus]): Option[StructType] = Some(new StructType().add("value", StringType))
override def prepareWrite(
sqlContext: SQLContext,
job: Job,
options: Map[String, String],
dataSchema: StructType): OutputWriterFactory = {
verifySchema(dataSchema)
val conf = job.getConfiguration
val compressionCodec = options.get("compression").map(CompressionCodecs.getCodecClassName)
compressionCodec.foreach { codec =>
CompressionCodecs.setCodecConfiguration(conf, codec)
}
new OutputWriterFactory {
override def newInstance(
path: String,
bucketId: Option[Int],
dataSchema: StructType,
context: TaskAttemptContext): OutputWriter = {
if (bucketId.isDefined) {
throw new AnalysisException("Text doesn't support bucketing")
}
new TextOutputWriter(path, dataSchema, context)
}
}
}
override def buildReader(
sqlContext: SQLContext,
dataSchema: StructType,
partitionSchema: StructType,
requiredSchema: StructType,
filters: Seq[Filter],
options: Map[String, String]): PartitionedFile => Iterator[InternalRow] = {
val conf = new Configuration(sqlContext.sessionState.hadoopConf)
val broadcastedConf =
sqlContext.sparkContext.broadcast(new SerializableConfiguration(conf))
file => {
val unsafeRow = new UnsafeRow(1)
val bufferHolder = new BufferHolder(unsafeRow)
val unsafeRowWriter = new UnsafeRowWriter(bufferHolder, 1)
new HadoopFileLinesReader(file, broadcastedConf.value.value).map { line =>
// Writes to an UnsafeRow directly
bufferHolder.reset()
unsafeRowWriter.write(0, line.getBytes, 0, line.getLength)
unsafeRow.setTotalSize(bufferHolder.totalSize())
unsafeRow
}
}
}
}
class TextOutputWriter(path: String, dataSchema: StructType, context: TaskAttemptContext)
extends OutputWriter {
private[this] val buffer = new Text()
private val recordWriter: RecordWriter[NullWritable, Text] = {
new TextOutputFormat[NullWritable, Text]() {
override def getDefaultWorkFile(context: TaskAttemptContext, extension: String): Path = {
val configuration = context.getConfiguration
val uniqueWriteJobId = configuration.get("spark.sql.sources.writeJobUUID")
val taskAttemptId = context.getTaskAttemptID
val split = taskAttemptId.getTaskID.getId
new Path(path, f"part-r-$split%05d-$uniqueWriteJobId.txt$extension")
}
}.getRecordWriter(context)
}
override def write(row: Row): Unit = throw new UnsupportedOperationException("call writeInternal")
override protected[sql] def writeInternal(row: InternalRow): Unit = {
val utf8string = row.getUTF8String(0)
buffer.set(utf8string.getBytes)
recordWriter.write(NullWritable.get(), buffer)
}
override def close(): Unit = {
recordWriter.close(context)
}
}
|
