spark-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From NathanHowell <...@git.apache.org>
Subject [GitHub] spark pull request #16386: [SPARK-18352][SQL] Support parsing multiline json...
Date Sat, 11 Feb 2017 00:48:46 GMT
Github user NathanHowell commented on a diff in the pull request:

    https://github.com/apache/spark/pull/16386#discussion_r100652445
  
    --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonDataSource.scala
---
    @@ -0,0 +1,213 @@
    +/*
    + * 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.InputStream
    +
    +import scala.reflect.ClassTag
    +
    +import com.fasterxml.jackson.core.{JsonFactory, JsonParser}
    +import com.google.common.io.ByteStreams
    +import org.apache.hadoop.conf.Configuration
    +import org.apache.hadoop.fs.{FileStatus, Path}
    +import org.apache.hadoop.io.{LongWritable, Text}
    +import org.apache.hadoop.mapreduce.Job
    +import org.apache.hadoop.mapreduce.lib.input.{FileInputFormat, TextInputFormat}
    +
    +import org.apache.spark.TaskContext
    +import org.apache.spark.input.{PortableDataStream, StreamInputFormat}
    +import org.apache.spark.rdd.{BinaryFileRDD, RDD}
    +import org.apache.spark.sql.{AnalysisException, SparkSession}
    +import org.apache.spark.sql.catalyst.InternalRow
    +import org.apache.spark.sql.catalyst.json.{CreateJacksonParser, JacksonParser, JSONOptions}
    +import org.apache.spark.sql.execution.datasources.{CodecStreams, HadoopFileLinesReader,
PartitionedFile}
    +import org.apache.spark.sql.types.StructType
    +import org.apache.spark.unsafe.types.UTF8String
    +import org.apache.spark.util.Utils
    +
    +/**
    + * Common functions for parsing JSON files
    + * @tparam T A datatype containing the unparsed JSON, such as [[Text]] or [[String]]
    + */
    +abstract class JsonDataSource[T] extends Serializable {
    +  def isSplitable: Boolean
    +
    +  /**
    +   * Parse a [[PartitionedFile]] into 0 or more [[InternalRow]] instances
    +   */
    +  def readFile(
    +    conf: Configuration,
    +    file: PartitionedFile,
    +    parser: JacksonParser): Iterator[InternalRow]
    +
    +  /**
    +   * Create an [[RDD]] that handles the preliminary parsing of [[T]] records
    +   */
    +  protected def createBaseRdd(
    +    sparkSession: SparkSession,
    +    inputPaths: Seq[FileStatus]): RDD[T]
    +
    +  /**
    +   * A generic wrapper to invoke the correct [[JsonFactory]] method to allocate a [[JsonParser]]
    +   * for an instance of [[T]]
    +   */
    +  def createParser(jsonFactory: JsonFactory, value: T): JsonParser
    +
    +  final def infer(
    +      sparkSession: SparkSession,
    +      inputPaths: Seq[FileStatus],
    +      parsedOptions: JSONOptions): Option[StructType] = {
    +    if (inputPaths.nonEmpty) {
    +      val jsonSchema = JsonInferSchema.infer(
    +        createBaseRdd(sparkSession, inputPaths),
    +        parsedOptions,
    +        createParser)
    +      checkConstraints(jsonSchema)
    +      Some(jsonSchema)
    +    } else {
    +      None
    +    }
    +  }
    +
    +  /** Constraints to be imposed on schema to be stored. */
    +  private def checkConstraints(schema: StructType): Unit = {
    --- End diff --
    
    IIRC this was a check added because some of the backends (maybe parquet?) were writing
corrupt files... if this is checked globally now it should be fine to remove


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org


Mime
View raw message