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
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
|
/*
* 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.json
import java.io.CharArrayWriter
import com.fasterxml.jackson.core.JsonFactory
import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.{FileStatus, Path}
import org.apache.hadoop.io.{LongWritable, NullWritable, Text}
import org.apache.hadoop.mapred.{JobConf, TextInputFormat}
import org.apache.hadoop.mapreduce.{Job, RecordWriter, TaskAttemptContext}
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat
import org.apache.spark.internal.Logging
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.{AnalysisException, Row, SparkSession}
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.catalyst.expressions.JoinedRow
import org.apache.spark.sql.catalyst.expressions.codegen.GenerateUnsafeProjection
import org.apache.spark.sql.execution.datasources._
import org.apache.spark.sql.sources._
import org.apache.spark.sql.types.StructType
import org.apache.spark.util.SerializableConfiguration
class DefaultSource extends FileFormat with DataSourceRegister {
override def shortName(): String = "json"
override def inferSchema(
sparkSession: SparkSession,
options: Map[String, String],
files: Seq[FileStatus]): Option[StructType] = {
if (files.isEmpty) {
None
} else {
val parsedOptions: JSONOptions = new JSONOptions(options)
val columnNameOfCorruptRecord =
parsedOptions.columnNameOfCorruptRecord
.getOrElse(sparkSession.sessionState.conf.columnNameOfCorruptRecord)
val jsonFiles = files.filterNot { status =>
val name = status.getPath.getName
name.startsWith("_") || name.startsWith(".")
}.toArray
val jsonSchema = InferSchema.infer(
createBaseRdd(sparkSession, jsonFiles),
columnNameOfCorruptRecord,
parsedOptions)
checkConstraints(jsonSchema)
Some(jsonSchema)
}
}
override def prepareWrite(
sparkSession: SparkSession,
job: Job,
options: Map[String, String],
dataSchema: StructType): OutputWriterFactory = {
val conf = job.getConfiguration
val parsedOptions: JSONOptions = new JSONOptions(options)
parsedOptions.compressionCodec.foreach { codec =>
CompressionCodecs.setCodecConfiguration(conf, codec)
}
new OutputWriterFactory {
override def newInstance(
path: String,
bucketId: Option[Int],
dataSchema: StructType,
context: TaskAttemptContext): OutputWriter = {
new JsonOutputWriter(path, bucketId, dataSchema, context)
}
}
}
override def buildReader(
sparkSession: SparkSession,
dataSchema: StructType,
partitionSchema: StructType,
requiredSchema: StructType,
filters: Seq[Filter],
options: Map[String, String],
hadoopConf: Configuration): PartitionedFile => Iterator[InternalRow] = {
val broadcastedHadoopConf =
sparkSession.sparkContext.broadcast(new SerializableConfiguration(hadoopConf))
val parsedOptions: JSONOptions = new JSONOptions(options)
val columnNameOfCorruptRecord = parsedOptions.columnNameOfCorruptRecord
.getOrElse(sparkSession.sessionState.conf.columnNameOfCorruptRecord)
val fullSchema = requiredSchema.toAttributes ++ partitionSchema.toAttributes
val joinedRow = new JoinedRow()
(file: PartitionedFile) => {
val lines = new HadoopFileLinesReader(file, broadcastedHadoopConf.value.value).map(_.toString)
val rows = JacksonParser.parseJson(
lines,
requiredSchema,
columnNameOfCorruptRecord,
parsedOptions)
val appendPartitionColumns = GenerateUnsafeProjection.generate(fullSchema, fullSchema)
rows.map { row =>
appendPartitionColumns(joinedRow(row, file.partitionValues))
}
}
}
private def createBaseRdd(
sparkSession: SparkSession,
inputPaths: Seq[FileStatus]): RDD[String] = {
val job = Job.getInstance(sparkSession.sessionState.hadoopConf)
val conf = job.getConfiguration
val paths = inputPaths.map(_.getPath)
if (paths.nonEmpty) {
FileInputFormat.setInputPaths(job, paths: _*)
}
sparkSession.sparkContext.hadoopRDD(
conf.asInstanceOf[JobConf],
classOf[TextInputFormat],
classOf[LongWritable],
classOf[Text]).map(_._2.toString) // get the text line
}
/** Constraints to be imposed on schema to be stored. */
private def checkConstraints(schema: StructType): Unit = {
if (schema.fieldNames.length != schema.fieldNames.distinct.length) {
val duplicateColumns = schema.fieldNames.groupBy(identity).collect {
case (x, ys) if ys.length > 1 => "\"" + x + "\""
}.mkString(", ")
throw new AnalysisException(s"Duplicate column(s) : $duplicateColumns found, " +
s"cannot save to JSON format")
}
}
override def toString: String = "JSON"
override def hashCode(): Int = getClass.hashCode()
override def equals(other: Any): Boolean = other.isInstanceOf[DefaultSource]
}
private[json] class JsonOutputWriter(
path: String,
bucketId: Option[Int],
dataSchema: StructType,
context: TaskAttemptContext)
extends OutputWriter with Logging {
private[this] val writer = new CharArrayWriter()
// create the Generator without separator inserted between 2 records
private[this] val gen = new JsonFactory().createGenerator(writer).setRootValueSeparator(null)
private[this] val result = new Text()
private val recordWriter: RecordWriter[NullWritable, Text] = {
new TextOutputFormat[NullWritable, Text]() {
override def getDefaultWorkFile(context: TaskAttemptContext, extension: String): Path = {
val configuration = context.getConfiguration
val uniqueWriteJobId = configuration.get("spark.sql.sources.writeJobUUID")
val taskAttemptId = context.getTaskAttemptID
val split = taskAttemptId.getTaskID.getId
val bucketString = bucketId.map(BucketingUtils.bucketIdToString).getOrElse("")
new Path(path, f"part-r-$split%05d-$uniqueWriteJobId$bucketString.json$extension")
}
}.getRecordWriter(context)
}
override def write(row: Row): Unit = throw new UnsupportedOperationException("call writeInternal")
override protected[sql] def writeInternal(row: InternalRow): Unit = {
JacksonGenerator(dataSchema, gen)(row)
gen.flush()
result.set(writer.toString)
writer.reset()
recordWriter.write(NullWritable.get(), result)
}
override def close(): Unit = {
gen.close()
recordWriter.close(context)
}
}
|
