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
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
|
/*
* 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.hive.execution
import java.util
import scala.collection.JavaConverters._
import org.apache.hadoop.hive.conf.HiveConf
import org.apache.hadoop.hive.conf.HiveConf.ConfVars
import org.apache.hadoop.hive.ql.{Context, ErrorMsg}
import org.apache.hadoop.mapred.{FileOutputFormat, JobConf}
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.catalyst.expressions.Attribute
import org.apache.spark.sql.execution.{SparkPlan, UnaryExecNode}
import org.apache.spark.sql.hive._
import org.apache.spark.sql.hive.HiveShim.{ShimFileSinkDesc => FileSinkDesc}
import org.apache.spark.SparkException
import org.apache.spark.util.SerializableJobConf
private[hive]
case class InsertIntoHiveTable(
table: MetastoreRelation,
partition: Map[String, Option[String]],
child: SparkPlan,
overwrite: Boolean,
ifNotExists: Boolean) extends UnaryExecNode {
@transient private val sessionState = sqlContext.sessionState.asInstanceOf[HiveSessionState]
@transient private val client = sessionState.metadataHive
@transient private val hiveconf = sessionState.hiveconf
@transient private lazy val hiveContext = new Context(hiveconf)
def output: Seq[Attribute] = Seq.empty
private def saveAsHiveFile(
rdd: RDD[InternalRow],
valueClass: Class[_],
fileSinkConf: FileSinkDesc,
conf: SerializableJobConf,
writerContainer: SparkHiveWriterContainer): Unit = {
assert(valueClass != null, "Output value class not set")
conf.value.setOutputValueClass(valueClass)
val outputFileFormatClassName = fileSinkConf.getTableInfo.getOutputFileFormatClassName
assert(outputFileFormatClassName != null, "Output format class not set")
conf.value.set("mapred.output.format.class", outputFileFormatClassName)
FileOutputFormat.setOutputPath(
conf.value,
SparkHiveWriterContainer.createPathFromString(fileSinkConf.getDirName, conf.value))
log.debug("Saving as hadoop file of type " + valueClass.getSimpleName)
writerContainer.driverSideSetup()
sqlContext.sparkContext.runJob(rdd, writerContainer.writeToFile _)
writerContainer.commitJob()
}
/**
* Inserts all the rows in the table into Hive. Row objects are properly serialized with the
* `org.apache.hadoop.hive.serde2.SerDe` and the
* `org.apache.hadoop.mapred.OutputFormat` provided by the table definition.
*
* Note: this is run once and then kept to avoid double insertions.
*/
protected[sql] lazy val sideEffectResult: Seq[InternalRow] = {
// Have to pass the TableDesc object to RDD.mapPartitions and then instantiate new serializer
// instances within the closure, since Serializer is not serializable while TableDesc is.
val tableDesc = table.tableDesc
val tableLocation = table.hiveQlTable.getDataLocation
val tmpLocation = hiveContext.getExternalTmpPath(tableLocation)
val fileSinkConf = new FileSinkDesc(tmpLocation.toString, tableDesc, false)
val isCompressed = hiveconf.getBoolean(
ConfVars.COMPRESSRESULT.varname, ConfVars.COMPRESSRESULT.defaultBoolVal)
if (isCompressed) {
// Please note that isCompressed, "mapred.output.compress", "mapred.output.compression.codec",
// and "mapred.output.compression.type" have no impact on ORC because it uses table properties
// to store compression information.
hiveconf.set("mapred.output.compress", "true")
fileSinkConf.setCompressed(true)
fileSinkConf.setCompressCodec(hiveconf.get("mapred.output.compression.codec"))
fileSinkConf.setCompressType(hiveconf.get("mapred.output.compression.type"))
}
val numDynamicPartitions = partition.values.count(_.isEmpty)
val numStaticPartitions = partition.values.count(_.nonEmpty)
val partitionSpec = partition.map {
case (key, Some(value)) => key -> value
case (key, None) => key -> ""
}
// All partition column names in the format of "<column name 1>/<column name 2>/..."
val partitionColumns = fileSinkConf.getTableInfo.getProperties.getProperty("partition_columns")
val partitionColumnNames = Option(partitionColumns).map(_.split("/")).orNull
// Validate partition spec if there exist any dynamic partitions
if (numDynamicPartitions > 0) {
// Report error if dynamic partitioning is not enabled
if (!hiveconf.getBoolVar(HiveConf.ConfVars.DYNAMICPARTITIONING)) {
throw new SparkException(ErrorMsg.DYNAMIC_PARTITION_DISABLED.getMsg)
}
// Report error if dynamic partition strict mode is on but no static partition is found
if (numStaticPartitions == 0 && hiveconf.getVar(
HiveConf.ConfVars.DYNAMICPARTITIONINGMODE).equalsIgnoreCase("strict")) {
throw new SparkException(ErrorMsg.DYNAMIC_PARTITION_STRICT_MODE.getMsg)
}
// Report error if any static partition appears after a dynamic partition
val isDynamic = partitionColumnNames.map(partitionSpec(_).isEmpty)
if (isDynamic.init.zip(isDynamic.tail).contains((true, false))) {
throw new SparkException(ErrorMsg.PARTITION_DYN_STA_ORDER.getMsg)
}
}
val jobConf = new JobConf(hiveconf)
val jobConfSer = new SerializableJobConf(jobConf)
// When speculation is on and output committer class name contains "Direct", we should warn
// users that they may loss data if they are using a direct output committer.
val speculationEnabled = sqlContext.sparkContext.conf.getBoolean("spark.speculation", false)
val outputCommitterClass = jobConf.get("mapred.output.committer.class", "")
if (speculationEnabled && outputCommitterClass.contains("Direct")) {
val warningMessage =
s"$outputCommitterClass may be an output committer that writes data directly to " +
"the final location. Because speculation is enabled, this output committer may " +
"cause data loss (see the case in SPARK-10063). If possible, please use a output " +
"committer that does not have this behavior (e.g. FileOutputCommitter)."
logWarning(warningMessage)
}
val writerContainer = if (numDynamicPartitions > 0) {
val dynamicPartColNames = partitionColumnNames.takeRight(numDynamicPartitions)
new SparkHiveDynamicPartitionWriterContainer(
jobConf,
fileSinkConf,
dynamicPartColNames,
child.output,
table)
} else {
new SparkHiveWriterContainer(
jobConf,
fileSinkConf,
child.output,
table)
}
@transient val outputClass = writerContainer.newSerializer(table.tableDesc).getSerializedClass
saveAsHiveFile(child.execute(), outputClass, fileSinkConf, jobConfSer, writerContainer)
val outputPath = FileOutputFormat.getOutputPath(jobConf)
// Have to construct the format of dbname.tablename.
val qualifiedTableName = s"${table.databaseName}.${table.tableName}"
// TODO: Correctly set holdDDLTime.
// In most of the time, we should have holdDDLTime = false.
// holdDDLTime will be true when TOK_HOLD_DDLTIME presents in the query as a hint.
val holdDDLTime = false
if (partition.nonEmpty) {
// loadPartition call orders directories created on the iteration order of the this map
val orderedPartitionSpec = new util.LinkedHashMap[String, String]()
table.hiveQlTable.getPartCols.asScala.foreach { entry =>
orderedPartitionSpec.put(entry.getName, partitionSpec.getOrElse(entry.getName, ""))
}
// inheritTableSpecs is set to true. It should be set to false for a IMPORT query
// which is currently considered as a Hive native command.
val inheritTableSpecs = true
// TODO: Correctly set isSkewedStoreAsSubdir.
val isSkewedStoreAsSubdir = false
if (numDynamicPartitions > 0) {
client.synchronized {
client.loadDynamicPartitions(
outputPath.toString,
qualifiedTableName,
orderedPartitionSpec,
overwrite,
numDynamicPartitions,
holdDDLTime,
isSkewedStoreAsSubdir)
}
} else {
// scalastyle:off
// ifNotExists is only valid with static partition, refer to
// https://cwiki.apache.org/confluence/display/Hive/LanguageManual+DML#LanguageManualDML-InsertingdataintoHiveTablesfromqueries
// scalastyle:on
val oldPart =
client.getPartitionOption(
client.getTable(table.databaseName, table.tableName),
partitionSpec)
if (oldPart.isEmpty || !ifNotExists) {
client.loadPartition(
outputPath.toString,
qualifiedTableName,
orderedPartitionSpec,
overwrite,
holdDDLTime,
inheritTableSpecs,
isSkewedStoreAsSubdir)
}
}
} else {
client.loadTable(
outputPath.toString, // TODO: URI
qualifiedTableName,
overwrite,
holdDDLTime)
}
// Invalidate the cache.
sqlContext.cacheManager.invalidateCache(table)
// It would be nice to just return the childRdd unchanged so insert operations could be chained,
// however for now we return an empty list to simplify compatibility checks with hive, which
// does not return anything for insert operations.
// TODO: implement hive compatibility as rules.
Seq.empty[InternalRow]
}
override def executeCollect(): Array[InternalRow] = sideEffectResult.toArray
protected override def doExecute(): RDD[InternalRow] = {
sqlContext.sparkContext.parallelize(sideEffectResult.asInstanceOf[Seq[InternalRow]], 1)
}
}
|
