# name: test/sql/copy/parquet/parquet2strings.test
# description: Issue #2261: TPC-H Q6 fails on Parquet input
# group: [parquet]

# Here's how we generate this
# from pyspark.sql import SparkSession
# from pyspark.sql.types import *
# from pyspark.sql.functions import *

# spark = SparkSession.builder.master("local").config("spark.hadoop.parquet.writer.version", "v2").getOrCreate()
# sc = spark.sparkContext
# ref = spark.range(42, 10000, 2).toDF("id").orderBy(rand())
# ref2 = ref.selectExpr("*", "repeat('XYZ', id%5) || cast(id as string) id_string")

# ref2.show(10)
# ref2.write.parquet("p2strings.parquet")
# ref2.write.csv("p2strings.csv")

# for now
mode skip

require parquet


query I
SELECT id_string FROM 'data/parquet-testing/p2strings.parquet' limit 10;
----