From 6e8cdef0cf36f6e921d9e1a65c61b66196935820 Mon Sep 17 00:00:00 2001 From: Sean Zhong Date: Tue, 14 Jun 2016 09:10:27 -0700 Subject: [SPARK-15914][SQL] Add deprecated method back to SQLContext for backward source code compatibility ## What changes were proposed in this pull request? Revert partial changes in SPARK-12600, and add some deprecated method back to SQLContext for backward source code compatibility. ## How was this patch tested? Manual test. Author: Sean Zhong Closes #13637 from clockfly/SPARK-15914. --- project/MimaExcludes.scala | 9 + .../scala/org/apache/spark/sql/SQLContext.scala | 284 +++++++++++++++++++++ 2 files changed, 293 insertions(+) diff --git a/project/MimaExcludes.scala b/project/MimaExcludes.scala index 9d0d9b1be0..a6209d78e1 100644 --- a/project/MimaExcludes.scala +++ b/project/MimaExcludes.scala @@ -778,6 +778,15 @@ object MimaExcludes { ) ++ Seq( ProblemFilters.exclude[ReversedMissingMethodProblem]("org.apache.spark.mllib.linalg.Vector.asBreeze"), ProblemFilters.exclude[ReversedMissingMethodProblem]("org.apache.spark.mllib.linalg.Matrix.asBreeze") + ) ++ Seq( + // [SPARK-15914] Binary compatibility is broken since consolidation of Dataset and DataFrame + // in Spark 2.0. However, source level compatibility is still maintained. + ProblemFilters.exclude[IncompatibleResultTypeProblem]("org.apache.spark.sql.SQLContext.load"), + ProblemFilters.exclude[IncompatibleResultTypeProblem]("org.apache.spark.sql.SQLContext.jsonRDD"), + ProblemFilters.exclude[IncompatibleResultTypeProblem]("org.apache.spark.sql.SQLContext.jsonFile"), + ProblemFilters.exclude[IncompatibleResultTypeProblem]("org.apache.spark.sql.SQLContext.jdbc"), + ProblemFilters.exclude[IncompatibleResultTypeProblem]("org.apache.spark.sql.SQLContext.parquetFile"), + ProblemFilters.exclude[IncompatibleResultTypeProblem]("org.apache.spark.sql.SQLContext.applySchema") ) case v if v.startsWith("1.6") => Seq( diff --git a/sql/core/src/main/scala/org/apache/spark/sql/SQLContext.scala b/sql/core/src/main/scala/org/apache/spark/sql/SQLContext.scala index 6fcc9bb447..58b4e6c5f6 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/SQLContext.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/SQLContext.scala @@ -736,6 +736,290 @@ class SQLContext private[sql](val sparkSession: SparkSession) private[sql] def parseDataType(dataTypeString: String): DataType = { DataType.fromJson(dataTypeString) } + + //////////////////////////////////////////////////////////////////////////// + //////////////////////////////////////////////////////////////////////////// + // Deprecated methods + //////////////////////////////////////////////////////////////////////////// + //////////////////////////////////////////////////////////////////////////// + + /** + * @deprecated As of 1.3.0, replaced by `createDataFrame()`. + */ + @deprecated("Use createDataFrame instead.", "1.3.0") + def applySchema(rowRDD: RDD[Row], schema: StructType): DataFrame = { + createDataFrame(rowRDD, schema) + } + + /** + * @deprecated As of 1.3.0, replaced by `createDataFrame()`. + */ + @deprecated("Use createDataFrame instead.", "1.3.0") + def applySchema(rowRDD: JavaRDD[Row], schema: StructType): DataFrame = { + createDataFrame(rowRDD, schema) + } + + /** + * @deprecated As of 1.3.0, replaced by `createDataFrame()`. + */ + @deprecated("Use createDataFrame instead.", "1.3.0") + def applySchema(rdd: RDD[_], beanClass: Class[_]): DataFrame = { + createDataFrame(rdd, beanClass) + } + + /** + * @deprecated As of 1.3.0, replaced by `createDataFrame()`. + */ + @deprecated("Use createDataFrame instead.", "1.3.0") + def applySchema(rdd: JavaRDD[_], beanClass: Class[_]): DataFrame = { + createDataFrame(rdd, beanClass) + } + + /** + * Loads a Parquet file, returning the result as a [[DataFrame]]. This function returns an empty + * [[DataFrame]] if no paths are passed in. + * + * @group specificdata + * @deprecated As of 1.4.0, replaced by `read().parquet()`. + */ + @deprecated("Use read.parquet() instead.", "1.4.0") + @scala.annotation.varargs + def parquetFile(paths: String*): DataFrame = { + if (paths.isEmpty) { + emptyDataFrame + } else { + read.parquet(paths : _*) + } + } + + /** + * Loads a JSON file (one object per line), returning the result as a [[DataFrame]]. + * It goes through the entire dataset once to determine the schema. + * + * @group specificdata + * @deprecated As of 1.4.0, replaced by `read().json()`. + */ + @deprecated("Use read.json() instead.", "1.4.0") + def jsonFile(path: String): DataFrame = { + read.json(path) + } + + /** + * Loads a JSON file (one object per line) and applies the given schema, + * returning the result as a [[DataFrame]]. + * + * @group specificdata + * @deprecated As of 1.4.0, replaced by `read().json()`. + */ + @deprecated("Use read.json() instead.", "1.4.0") + def jsonFile(path: String, schema: StructType): DataFrame = { + read.schema(schema).json(path) + } + + /** + * @group specificdata + * @deprecated As of 1.4.0, replaced by `read().json()`. + */ + @deprecated("Use read.json() instead.", "1.4.0") + def jsonFile(path: String, samplingRatio: Double): DataFrame = { + read.option("samplingRatio", samplingRatio.toString).json(path) + } + + /** + * Loads an RDD[String] storing JSON objects (one object per record), returning the result as a + * [[DataFrame]]. + * It goes through the entire dataset once to determine the schema. + * + * @group specificdata + * @deprecated As of 1.4.0, replaced by `read().json()`. + */ + @deprecated("Use read.json() instead.", "1.4.0") + def jsonRDD(json: RDD[String]): DataFrame = read.json(json) + + /** + * Loads an RDD[String] storing JSON objects (one object per record), returning the result as a + * [[DataFrame]]. + * It goes through the entire dataset once to determine the schema. + * + * @group specificdata + * @deprecated As of 1.4.0, replaced by `read().json()`. + */ + @deprecated("Use read.json() instead.", "1.4.0") + def jsonRDD(json: JavaRDD[String]): DataFrame = read.json(json) + + /** + * Loads an RDD[String] storing JSON objects (one object per record) and applies the given schema, + * returning the result as a [[DataFrame]]. + * + * @group specificdata + * @deprecated As of 1.4.0, replaced by `read().json()`. + */ + @deprecated("Use read.json() instead.", "1.4.0") + def jsonRDD(json: RDD[String], schema: StructType): DataFrame = { + read.schema(schema).json(json) + } + + /** + * Loads an JavaRDD storing JSON objects (one object per record) and applies the given + * schema, returning the result as a [[DataFrame]]. + * + * @group specificdata + * @deprecated As of 1.4.0, replaced by `read().json()`. + */ + @deprecated("Use read.json() instead.", "1.4.0") + def jsonRDD(json: JavaRDD[String], schema: StructType): DataFrame = { + read.schema(schema).json(json) + } + + /** + * Loads an RDD[String] storing JSON objects (one object per record) inferring the + * schema, returning the result as a [[DataFrame]]. + * + * @group specificdata + * @deprecated As of 1.4.0, replaced by `read().json()`. + */ + @deprecated("Use read.json() instead.", "1.4.0") + def jsonRDD(json: RDD[String], samplingRatio: Double): DataFrame = { + read.option("samplingRatio", samplingRatio.toString).json(json) + } + + /** + * Loads a JavaRDD[String] storing JSON objects (one object per record) inferring the + * schema, returning the result as a [[DataFrame]]. + * + * @group specificdata + * @deprecated As of 1.4.0, replaced by `read().json()`. + */ + @deprecated("Use read.json() instead.", "1.4.0") + def jsonRDD(json: JavaRDD[String], samplingRatio: Double): DataFrame = { + read.option("samplingRatio", samplingRatio.toString).json(json) + } + + /** + * Returns the dataset stored at path as a DataFrame, + * using the default data source configured by spark.sql.sources.default. + * + * @group genericdata + * @deprecated As of 1.4.0, replaced by `read().load(path)`. + */ + @deprecated("Use read.load(path) instead.", "1.4.0") + def load(path: String): DataFrame = { + read.load(path) + } + + /** + * Returns the dataset stored at path as a DataFrame, using the given data source. + * + * @group genericdata + * @deprecated As of 1.4.0, replaced by `read().format(source).load(path)`. + */ + @deprecated("Use read.format(source).load(path) instead.", "1.4.0") + def load(path: String, source: String): DataFrame = { + read.format(source).load(path) + } + + /** + * (Java-specific) Returns the dataset specified by the given data source and + * a set of options as a DataFrame. + * + * @group genericdata + * @deprecated As of 1.4.0, replaced by `read().format(source).options(options).load()`. + */ + @deprecated("Use read.format(source).options(options).load() instead.", "1.4.0") + def load(source: String, options: java.util.Map[String, String]): DataFrame = { + read.options(options).format(source).load() + } + + /** + * (Scala-specific) Returns the dataset specified by the given data source and + * a set of options as a DataFrame. + * + * @group genericdata + * @deprecated As of 1.4.0, replaced by `read().format(source).options(options).load()`. + */ + @deprecated("Use read.format(source).options(options).load() instead.", "1.4.0") + def load(source: String, options: Map[String, String]): DataFrame = { + read.options(options).format(source).load() + } + + /** + * (Java-specific) Returns the dataset specified by the given data source and + * a set of options as a DataFrame, using the given schema as the schema of the DataFrame. + * + * @group genericdata + * @deprecated As of 1.4.0, replaced by + * `read().format(source).schema(schema).options(options).load()`. + */ + @deprecated("Use read.format(source).schema(schema).options(options).load() instead.", "1.4.0") + def load( + source: String, + schema: StructType, + options: java.util.Map[String, String]): DataFrame = { + read.format(source).schema(schema).options(options).load() + } + + /** + * (Scala-specific) Returns the dataset specified by the given data source and + * a set of options as a DataFrame, using the given schema as the schema of the DataFrame. + * + * @group genericdata + * @deprecated As of 1.4.0, replaced by + * `read().format(source).schema(schema).options(options).load()`. + */ + @deprecated("Use read.format(source).schema(schema).options(options).load() instead.", "1.4.0") + def load(source: String, schema: StructType, options: Map[String, String]): DataFrame = { + read.format(source).schema(schema).options(options).load() + } + + /** + * Construct a [[DataFrame]] representing the database table accessible via JDBC URL + * url named table. + * + * @group specificdata + * @deprecated As of 1.4.0, replaced by `read().jdbc()`. + */ + @deprecated("Use read.jdbc() instead.", "1.4.0") + def jdbc(url: String, table: String): DataFrame = { + read.jdbc(url, table, new Properties) + } + + /** + * Construct a [[DataFrame]] representing the database table accessible via JDBC URL + * url named table. Partitions of the table will be retrieved in parallel based on the parameters + * passed to this function. + * + * @param columnName the name of a column of integral type that will be used for partitioning. + * @param lowerBound the minimum value of `columnName` used to decide partition stride + * @param upperBound the maximum value of `columnName` used to decide partition stride + * @param numPartitions the number of partitions. the range `minValue`-`maxValue` will be split + * evenly into this many partitions + * @group specificdata + * @deprecated As of 1.4.0, replaced by `read().jdbc()`. + */ + @deprecated("Use read.jdbc() instead.", "1.4.0") + def jdbc( + url: String, + table: String, + columnName: String, + lowerBound: Long, + upperBound: Long, + numPartitions: Int): DataFrame = { + read.jdbc(url, table, columnName, lowerBound, upperBound, numPartitions, new Properties) + } + + /** + * Construct a [[DataFrame]] representing the database table accessible via JDBC URL + * url named table. The theParts parameter gives a list expressions + * suitable for inclusion in WHERE clauses; each one defines one partition + * of the [[DataFrame]]. + * + * @group specificdata + * @deprecated As of 1.4.0, replaced by `read().jdbc()`. + */ + @deprecated("Use read.jdbc() instead.", "1.4.0") + def jdbc(url: String, table: String, theParts: Array[String]): DataFrame = { + read.jdbc(url, table, theParts, new Properties) + } } /** -- cgit v1.2.3