Last active
August 30, 2019 11:33
-
-
Save prodeezy/001cf155ff0675be7d307e9f842e1dac to your computer and use it in GitHub Desktop.
Test Struct based Filter on Iceberg
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
bash-3.2$ cat people.json | |
{"name":"Michael"} | |
{"name":"Andy", "age":30, "friends": {"Josh": 10, "Biswa": 25}, "location": { "lat": 101.123, "lon": 50.324 } } | |
{"name":"Justin", "age":19, "friends": {"Kannan": 75, "Sanjay": 100}, "location": { "lat": 175.926, "lon": 20.524 } } | |
spark-shell | |
import org.apache.spark.sql.types._ ; | |
import org.apache.iceberg.hadoop.HadoopTables; | |
import org.apache.iceberg.Schema; | |
import org.apache.iceberg.spark.SparkSchemaUtil | |
val schema = new StructType().add("age", IntegerType).add("name", StringType).add("friends", MapType(StringType, IntegerType)).add("location", new StructType().add("lat", DoubleType).add("lon", DoubleType)) | |
val json = spark.read.schema(schema).json("people.json") | |
json.write.format("iceberg").mode("append").save("iceberg-people-struct") | |
val tables = new HadoopTables() | |
val iceSchema = SparkSchemaUtil.convert(schema) | |
val iceTable = tables.create(iceSchema, "iceberg-people-complex") | |
iceTable.schema | |
val iceTable = tables.create(iceSchema, "iceberg-people-struct") | |
val iceDf = spark.read.format("iceberg").load("iceberg-people-struct") | |
iceDf.createOrReplaceTempView("iceberg_people_struct") | |
spark.sql("select location.lat from iceberg_people_struct where location.lat = 101.123 ").show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment