forked from apache/spark
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request apache#14 from bzhang02/avro-example
[YSPARK-1522] Add an Avro example
- Loading branch information
Showing
11 changed files
with
48 additions
and
0 deletions.
There are no files selected for viewing
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
48 changes: 48 additions & 0 deletions
48
src/main/scala/com/yahoo/spark/starter/SparkAvroExample.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,48 @@ | ||
package com.yahoo.spark.starter | ||
|
||
import org.apache.spark.sql.{SparkSession, DataFrame} | ||
import org.apache.spark.sql.avro._ | ||
|
||
object SparkAvroExample { | ||
def main(args: Array[String]) { | ||
val spark = SparkSession | ||
.builder() | ||
.appName("Spark Avro Example") | ||
.getOrCreate() | ||
|
||
val inputDir = "avro_test/resources/" | ||
val outputDir = "avro_test/output/" | ||
|
||
// Read, query and write for normal data frame | ||
val usersDF = spark.read.format("avro").load(inputDir + "users.avro") | ||
usersDF.show() | ||
|
||
usersDF.select("name", "favorite_color").write.format("avro").save(outputDir + "namesAndFavColors.avro") | ||
|
||
val namesAndFavColorsDF = spark.read.format("avro").load(outputDir + "namesAndFavColors.avro") | ||
namesAndFavColorsDF.show() | ||
|
||
|
||
// Read, query and write for primitive types | ||
def readAndWritePrimitive(filename: String): DataFrame = { | ||
val df = spark.read.format("avro").load(inputDir + filename) | ||
df.show() | ||
df.write.format("avro").save(outputDir + filename) | ||
|
||
val df2 = spark.read.format("avro").load(outputDir + filename) | ||
df2.show() | ||
|
||
df2 | ||
} | ||
|
||
println(readAndWritePrimitive("randomBoolean.avro").head().getBoolean(0)) | ||
println(readAndWritePrimitive("randomBytes.avro").head().getAs[Array[Byte]](0)) | ||
println(readAndWritePrimitive("randomDouble.avro").head().getDouble(0)) | ||
println(readAndWritePrimitive("randomFloat.avro").head().getFloat(0)) | ||
println(readAndWritePrimitive("randomInt.avro").head().getInt(0)) | ||
println(readAndWritePrimitive("randomLong.avro").head().getLong(0)) | ||
println(readAndWritePrimitive("randomString.avro").head().getString(0)) | ||
println(readAndWritePrimitive("randomLongMap.avro").head().getAs[Map[String, Long]](0)) | ||
println(readAndWritePrimitive("randomStringArray.avro").head().getAs[Array[String]](0)) | ||
} | ||
} |