org.apache.spark.sql.avro.functions.scala Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of databricks-connect Show documentation
Develop locally and connect IDEs, notebook servers and running applications to Databricks clusters.
The newest version!
/*
 * 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.avro

import scala.jdk.CollectionConverters._

import org.apache.spark.annotation.Experimental
import org.apache.spark.sql.Column
import org.apache.spark.sql.functions.{fnWithOptions, lit}

// scalastyle:off: object.name
object functions {
// scalastyle:on: object.name

  /**
   * Converts a binary column of avro format into its corresponding catalyst value. The specified
   * schema must match the read data, otherwise the behavior is undefined: it may fail or return
   * arbitrary result.
   *
   * @param data
   *   the binary column.
   * @param jsonFormatSchema
   *   the avro schema in JSON string format.
   *
   * @since 3.5.0
   */
  @Experimental
  def from_avro(data: Column, jsonFormatSchema: String): Column = {
    Column.fn("from_avro", data, lit(jsonFormatSchema))
  }

  /**
   * Converts a binary column of Avro format into its corresponding catalyst value. The specified
   * schema must match actual schema of the read data, otherwise the behavior is undefined: it may
   * fail or return arbitrary result. To deserialize the data with a compatible and evolved
   * schema, the expected Avro schema can be set via the option avroSchema.
   *
   * @param data
   *   the binary column.
   * @param jsonFormatSchema
   *   the avro schema in JSON string format.
   * @param options
   *   options to control how the Avro record is parsed.
   *
   * @since 3.5.0
   */
  @Experimental
  def from_avro(
      data: Column,
      jsonFormatSchema: String,
      options: java.util.Map[String, String]): Column = {
    fnWithOptions("from_avro", options.asScala.iterator, data, lit(jsonFormatSchema))
  }

  /**
   * Converts a column into binary of avro format.
   *
   * @param data
   *   the data column.
   *
   * @since 3.5.0
   */
  @Experimental
  def to_avro(data: Column): Column = {
    Column.fn("to_avro", data)
  }

  /**
   * Converts a column into binary of avro format.
   *
   * @param data
   *   the data column.
   * @param jsonFormatSchema
   *   user-specified output avro schema in JSON string format.
   *
   * @since 3.5.0
   */
  @Experimental
  def to_avro(data: Column, jsonFormatSchema: String): Column = {
    Column.fn("to_avro", data, lit(jsonFormatSchema))
  }

  // BEGIN-EDGE
  /**
   * Converts a binary column of Schema-Registry avro format into its corresponding catalyst
   * value. The schema of the given subject in Schema-Registry should not change in an
   * incompatible way, otherwise exception will be thrown at runtime when Spark consumes data with
   * new schema.
   *
   * @param data
   *   the binary column.
   * @param subject
   *   the subject in Schema-Registry that these data belong to.
   * @param schemaRegistryAddress
   *   the address(host and port) of Schema-Registry.
   */
  @Experimental
  def from_avro(data: Column, subject: String, schemaRegistryAddress: String): Column = {
    Column.fn("from_avro_schema_registry", data, lit(subject), lit(schemaRegistryAddress))
  }

  /**
   * Converts a binary column of Schema-Registry avro format into its corresponding catalyst
   * value. The schema of the given subject in Schema-Registry should not change in an
   * incompatible way, otherwise exception will be thrown at runtime when Spark consumes data with
   * new schema.
   *
   * @param data
   *   the binary column.
   * @param subject
   *   the subject in Schema-Registry that these data belong to.
   * @param schemaRegistryAddress
   *   the address(host and port) of Schema-Registry.
   * @param options
   *   options to control how the Avro record is parsed and configs for schema registry client.
   */
  @Experimental
  def from_avro(
      data: Column,
      subject: String,
      schemaRegistryAddress: String,
      options: java.util.Map[String, String]): Column = {
    fnWithOptions(
      "from_avro_schema_registry",
      options.asScala.iterator,
      data,
      lit(subject),
      lit(schemaRegistryAddress))
  }

  /**
   * Converts a column into binary of Schema-Registry avro format. The input data schema must have
   * been registered to the given subject in Schema-Registry, or the query will fail at runtime.
   *
   * @param data
   *   the data column.
   * @param subject
   *   the subject in Schema-Registry that these data belong to.
   * @param schemaRegistryAddress
   *   the address(host and port) of Schema-Registry.
   */
  @Experimental
  def to_avro(data: Column, subject: Column, schemaRegistryAddress: String): Column = {
    Column.fn("to_avro_schema_registry", data, subject, lit(schemaRegistryAddress))
  }

  /**
   * Converts a column into binary of Schema-Registry avro format. The input data schema must have
   * been registered to the given subject in Schema-Registry, or the query will fail at runtime.
   *
   * @param data
   *   the data column.
   * @param subject
   *   the subject in Schema-Registry that these data belong to.
   * @param schemaRegistryAddress
   *   the address(host and port) of Schema-Registry.
   * @param options
   *   options to control how the Avro record is parsed and configs for schema registry client.
   */
  @Experimental
  def to_avro(
      data: Column,
      subject: Column,
      schemaRegistryAddress: String,
      options: java.util.Map[String, String]): Column = {
    fnWithOptions(
      "to_avro_schema_registry",
      options.asScala.iterator,
      data,
      subject,
      lit(schemaRegistryAddress))
  }

  /**
   * Converts a column into binary of Schema-Registry avro format. The input data schema must have
   * been registered to the given subject in Schema-Registry, or the query will fail at runtime.
   *
   * @param data
   *   the data column.
   * @param subject
   *   the subject in Schema-Registry that these data belong to.
   * @param schemaRegistryAddress
   *   the address(host and port) of Schema-Registry.
   * @param jsonFormatSchema
   *   user-specified output avro schema in JSON string format.
   */
  def to_avro(
      data: Column,
      subject: Column,
      schemaRegistryAddress: String,
      jsonFormatSchema: String): Column = {
    Column.fn(
      "to_avro_schema_registry",
      data,
      subject,
      lit(schemaRegistryAddress),
      lit(jsonFormatSchema))
  }

  /**
   * Converts a column into binary of Schema-Registry avro format. The input data schema must have
   * been registered to the given subject in Schema-Registry, or the query will fail at runtime.
   *
   * @param data
   *   the data column.
   * @param subject
   *   the subject in Schema-Registry that these data belong to.
   * @param schemaRegistryAddress
   *   the address(host and port) of Schema-Registry.
   * @param options
   *   options to control how the Avro record is parsed and configs for schema registry client.
   * @param jsonFormatSchema
   *   user-specified output avro schema in JSON string format.
   */
  def to_avro(
      data: Column,
      subject: Column,
      schemaRegistryAddress: String,
      options: java.util.Map[String, String],
      jsonFormatSchema: String): Column = {
    fnWithOptions(
      "to_avro_schema_registry",
      options.asScala.iterator,
      data,
      subject,
      lit(schemaRegistryAddress),
      lit(jsonFormatSchema))
  }
  // END-EDGE
}