Hive Tables

from os.path import abspath

from pyspark.sql import SparkSession
from pyspark.sql import Row

# warehouse_location points to the default location for managed databases and tables
warehouse_location = abspath('spark-warehouse')

spark = SparkSession \
    .builder \
    .appName("Python Spark SQL Hive integration example") \
    .config("spark.sql.warehouse.dir", warehouse_location) \
    .enableHiveSupport() \
    .getOrCreate()

# spark is an existing SparkSession
spark.sql("CREATE TABLE IF NOT EXISTS src (key INT, value STRING) USING hive")
spark.sql("LOAD DATA LOCAL INPATH 'examples/src/main/resources/kv1.txt' INTO TABLE src")

# Queries are expressed in HiveQL
spark.sql("SELECT * FROM src").show()
# +---+-------+
# |key|  value|
# +---+-------+
# |238|val_238|
# | 86| val_86|
# |311|val_311|
# ...

# Aggregation queries are also supported.
spark.sql("SELECT COUNT(*) FROM src").show()
# +--------+
# |count(1)|
# +--------+
# |    500 |
# +--------+

# The results of SQL queries are themselves DataFrames and support all normal functions.
sqlDF = spark.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.
stringsDS = sqlDF.rdd.map(lambda row: "Key: %d, Value: %s" % (row.key, row.value))
for record in stringsDS.collect():
    print(record)
# 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.
Record = Row("key", "value")
recordsDF = spark.createDataFrame([Record(i, "val_" + str(i)) for i in range(1, 101)])
recordsDF.createOrReplaceTempView("records")

# Queries can then join DataFrame data with data stored in Hive.
spark.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|
# ...

import java.io.File

import org.apache.spark.sql.{Row, SaveMode, 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) USING hive")
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|
// ...

// Create a Hive managed Parquet table, with HQL syntax instead of the Spark SQL native syntax
// `USING hive`
sql("CREATE TABLE hive_records(key int, value string) STORED AS PARQUET")
// Save DataFrame to the Hive managed table
val df = spark.table("src")
df.write.mode(SaveMode.Overwrite).saveAsTable("hive_records")
// After insertion, the Hive managed table has data now
sql("SELECT * FROM hive_records").show()
// +---+-------+
// |key|  value|
// +---+-------+
// |238|val_238|
// | 86| val_86|
// |311|val_311|
// ...

// Prepare a Parquet data directory
val dataDir = "/tmp/parquet_data"
spark.range(10).write.parquet(dataDir)
// Create a Hive external Parquet table
sql(s"CREATE EXTERNAL TABLE hive_bigints(id bigint) STORED AS PARQUET LOCATION '$dataDir'")
// The Hive external table should already have data
sql("SELECT * FROM hive_bigints").show()
// +---+
// | id|
// +---+
// |  0|
// |  1|
// |  2|
// ... Order may vary, as spark processes the partitions in parallel.

// Turn on flag for Hive Dynamic Partitioning
spark.sqlContext.setConf("hive.exec.dynamic.partition", "true")
spark.sqlContext.setConf("hive.exec.dynamic.partition.mode", "nonstrict")
// Create a Hive partitioned table using DataFrame API
df.write.partitionBy("key").format("hive").saveAsTable("hive_part_tbl")
// Partitioned column `key` will be moved to the end of the schema.
sql("SELECT * FROM hive_part_tbl").show()
// +-------+---+
// |  value|key|
// +-------+---+
// |val_238|238|
// | val_86| 86|
// |val_311|311|
// ...

spark.stop()

import java.io.File;
import java.io.Serializable;
import java.util.ArrayList;
import java.util.List;

import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SparkSession;

public static class Record implements Serializable {
  private int key;
  private String value;

  public int getKey() {
    return key;
  }

  public void setKey(int key) {
    this.key = key;
  }

  public String getValue() {
    return value;
  }

  public void setValue(String value) {
    this.value = value;
  }
}

// warehouseLocation points to the default location for managed databases and tables
String warehouseLocation = new File("spark-warehouse").getAbsolutePath();
SparkSession spark = SparkSession
  .builder()
  .appName("Java Spark Hive Example")
  .config("spark.sql.warehouse.dir", warehouseLocation)
  .enableHiveSupport()
  .getOrCreate();

spark.sql("CREATE TABLE IF NOT EXISTS src (key INT, value STRING) USING hive");
spark.sql("LOAD DATA LOCAL INPATH 'examples/src/main/resources/kv1.txt' INTO TABLE src");

// Queries are expressed in HiveQL
spark.sql("SELECT * FROM src").show();
// +---+-------+
// |key|  value|
// +---+-------+
// |238|val_238|
// | 86| val_86|
// |311|val_311|
// ...

// Aggregation queries are also supported.
spark.sql("SELECT COUNT(*) FROM src").show();
// +--------+
// |count(1)|
// +--------+
// |    500 |
// +--------+

// The results of SQL queries are themselves DataFrames and support all normal functions.
Dataset<Row> sqlDF = spark.sql("SELECT key, value FROM src WHERE key < 10 ORDER BY key");

// The items in DataFrames are of type Row, which lets you to access each column by ordinal.
Dataset<String> stringsDS = sqlDF.map(
    (MapFunction<Row, String>) row -> "Key: " + row.get(0) + ", Value: " + row.get(1),
    Encoders.STRING());
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.
List<Record> records = new ArrayList<>();
for (int key = 1; key < 100; key++) {
  Record record = new Record();
  record.setKey(key);
  record.setValue("val_" + key);
  records.add(record);
}
Dataset<Row> recordsDF = spark.createDataFrame(records, Record.class);
recordsDF.createOrReplaceTempView("records");

// Queries can then join DataFrames data with data stored in Hive.
spark.sql("SELECT * FROM records r JOIN src s ON r.key = s.key").show();
// +---+------+---+------+
// |key| value|key| value|
// +---+------+---+------+
// |  2| val_2|  2| val_2|
// |  2| val_2|  2| val_2|
// |  4| val_4|  4| val_4|
// ...

# enableHiveSupport defaults to TRUE
sparkR.session(enableHiveSupport = TRUE)
sql("CREATE TABLE IF NOT EXISTS src (key INT, value STRING) USING hive")
sql("LOAD DATA LOCAL INPATH 'examples/src/main/resources/kv1.txt' INTO TABLE src")

# Queries can be expressed in HiveQL.
results <- collect(sql("FROM src SELECT key, value"))