Spark SQL常见4种数据源详解

scala> val df = spark.read.load("hdfs://hadoop001:9000/namesAndAges.parquet")
df: org.apache.spark.sql.DataFrame = [age: bigint, name: string]
scala> df.select("name").write.save("names.parquet")

scala> val peopleDF = spark.read.format("json").load("hdfs://hadoop001:9000/people.json")
peopleDF: org.apache.spark.sql.DataFrame = [age: bigint, name: string]
scala> peopleDF.write.format("parquet").save("hdfs://hadoop001:9000/namesAndAges.parquet")
scala>

val sqlDF = spark.sql("SELECT * FROM parquet.`hdfs://hadoop001:9000/namesAndAges.parquet`")
sqlDF.show()

// Encoders for most common types are automatically provided by importing spark.implicits._
import spark.implicits._
val peopleDF = spark.read.json("examples/src/main/resources/people.json")
// DataFrames can be saved as Parquet files, maintaining the schema information
peopleDF.write.parquet("hdfs://hadoop001:9000/people.parquet")
// Read in the parquet file created above
// Parquet files are self-describing so the schema is preserved
// The result of loading a Parquet file is also a DataFrame
val parquetFileDF = spark.read.parquet("hdfs://hadoop001:9000/people.parquet")
// Parquet files can also be used to create a temporary view and then used in SQL statements
parquetFileDF.createOrReplaceTempView("parquetFile")
val namesDF = spark.sql("SELECT name FROM parquetFile WHERE age BETWEEN 13 AND 19")
namesDF.map(attributes => "Name: " + attributes(0)).show()
// +------------+
// | value|
// +------------+
// |Name: Justin|
// +------------+

path
└── to
└── table
├── gender=male
│ ├── ...
│ │
│ ├── country=US
│ │ └── data.parquet
│ ├── country=CN
│ │ └── data.parquet
│ └── ...
└── gender=female
├── ...
│
├── country=US
│ └── data.parquet
├── country=CN
│ └── data.parquet
└── ...

root
|-- name: string (nullable = true)
|-- age: long (nullable = true)
|-- gender: string (nullable = true)
|-- country: string (nullable = true)

spark.sql.sources.partitionColumnTypeInference.enabled

// sqlContext from the previous example is used in this example.
// This is used to implicitly convert an RDD to a DataFrame.
import spark.implicits._
// Create a simple DataFrame, stored into a partition directory
val df1 = sc.makeRDD(1 to 5).map(i => (i, i * 2)).toDF("single", "double")
df1.write.parquet("hdfs://hadoop001:9000/data/test_table/key=1")
// Create another DataFrame in a new partition directory,
// adding a new column and dropping an existing column
val df2 = sc.makeRDD(6 to 10).map(i => (i, i * 3)).toDF("single", "triple")
df2.write.parquet("hdfs://hadoop001:9000/data/test_table/key=2")
// Read the partitioned table
val df3 = spark.read.option("mergeSchema", "true").parquet("hdfs://hadoop001:9000/data/test_table")
df3.printSchema()
// The final schema consists of all 3 columns in the Parquet files together
// with the partitioning column appeared in the partition directory paths.
// root
// |-- single: int (nullable = true)
// |-- double: int (nullable = true)
// |-- triple: int (nullable = true)
// |-- key : int (nullable = true)

import java.io.File
import org.apache.spark.sql.Row
import org.apache.spark.sql.SparkSession
case class Record(key: Int, value: String)
// warehouseLocation points to the default location for managed databases and tables
val warehouseLocation = new File("spark-warehouse").getAbsolutePath
val spark = SparkSession
.builder()
.appName("Spark Hive Example")
.config("spark.sql.warehouse.dir", warehouseLocation)
.enableHiveSupport()
.getOrCreate()
import spark.implicits._
import spark.sql
sql("CREATE TABLE IF NOT EXISTS src (key INT, value STRING)")
sql("LOAD DATA LOCAL INPATH 'examples/src/main/resources/kv1.txt' INTO TABLE src")
// Queries are expressed in HiveQL
sql("SELECT * FROM src").show()
// +---+-------+
// |key| value|
// +---+-------+
// |238|val_238|
// | 86| val_86|
// |311|val_311|
// ...
// Aggregation queries are also supported.
sql("SELECT COUNT(*) FROM src").show()
// +--------+
// |count(1)|
// +--------+
// | 500 |
// +--------+
// The results of SQL queries are themselves DataFrames and support all normal functions.
val sqlDF = sql("SELECT key, value FROM src WHERE key < 10 ORDER BY key")
// The items in DataFrames are of type Row, which allows you to access each column by ordinal.
val stringsDS = sqlDF.map {
case Row(key: Int, value: String) => s"Key: $key, Value: $value"
}
stringsDS.show()
// +--------------------+
// | value|
// +--------------------+
// |Key: 0, Value: val_0|
// |Key: 0, Value: val_0|
// |Key: 0, Value: val_0|
// ...
// You can also use DataFrames to create temporary views within a SparkSession.
val recordsDF = spark.createDataFrame((1 to 100).map(i => Record(i, s"val_$i")))
recordsDF.createOrReplaceTempView("records")
// Queries can then join DataFrame data with data stored in Hive.
sql("SELECT * FROM records r JOIN src s ON r.key = s.key").show()
// +---+------+---+------+
// |key| value|key| value|
// +---+------+---+------+
// | 2| val_2| 2| val_2|
// | 4| val_4| 4| val_4|
// | 5| val_5| 5| val_5|
// ...

spark.sql.warehouse.dir=

$ bin/spark-shell --master spark://hadoop001:7077 --jars mysql-connector-java-5.1.27-bin.jar

{"name":"Michael"}
{"name":"Andy", "age":30}
{"name":"Justin", "age":19}
// Primitive types (Int, String, etc) and Product types (case classes) encoders are
// supported by importing this when creating a Dataset.
import spark.implicits._
// A JSON dataset is pointed to by path.
// The path can be either a single text file or a directory storing text files
val path = "examples/src/main/resources/people.json"
val peopleDF = spark.read.json(path)
// The inferred schema can be visualized using the printSchema() method
peopleDF.printSchema()
// root
// |-- age: long (nullable = true)
// |-- name: string (nullable = true)
// Creates a temporary view using the DataFrame
peopleDF.createOrReplaceTempView("people")
// SQL statements can be run by using the sql methods provided by spark
val teenagerNamesDF = spark.sql("SELECT name FROM people WHERE age BETWEEN 13 AND 19")
teenagerNamesDF.show()
// +------+
// | name|
// +------+
// |Justin|
// +------+
// Alternatively, a DataFrame can be created for a JSON dataset represented by
// a Dataset[String] storing one JSON object per string
val otherPeopleDataset = spark.createDataset(
"""{"name":"Yin","address":{"city":"Columbus","state":"Ohio"}}""" :: Nil)
val otherPeople = spark.read.json(otherPeopleDataset)
otherPeople.show()
// +---------------+----+
// | address|name|
// +---------------+----+
// |[Columbus,Ohio]| Yin|
// +---------------+----+

$ bin/spark-shell --master spark://hadoop001:7077 --jars mysql-connector-java-5.1.27-bin.jar
// Note: JDBC loading and saving can be achieved via either the load/save or jdbc methods
// Loading data from a JDBC source
val jdbcDF = spark.read.format("jdbc").option("url", "jdbc:mysql://hadoop001:3306/rdd").option("dbtable", " rddtable").option("user", "root").option("password", "hive").load()
val connectionProperties = new Properties()
connectionProperties.put("user", "root")
connectionProperties.put("password", "hive")
val jdbcDF2 = spark.read
.jdbc("jdbc:mysql://hadoop001:3306/rdd", "rddtable", connectionProperties)
// Saving data to a JDBC source
jdbcDF.write
.format("jdbc")
.option("url", "jdbc:mysql://hadoop001:3306/rdd")
.option("dbtable", "rddtable2")
.option("user", "root")
.option("password", "hive")
.save()
jdbcDF2.write
.jdbc("jdbc:mysql://hadoop001:3306/mysql", "db", connectionProperties)
// Specifying create table column data types on write
jdbcDF.write
.option("createTableColumnTypes", "name CHAR(64), comments VARCHAR(1024)")
.jdbc("jdbc:mysql://hadoop001:3306/mysql", "db", connectionProperties)