From abff92bfdc7d4c9d2308794f0350561fe0ceb4dd Mon Sep 17 00:00:00 2001 From: Dongjoon Hyun Date: Fri, 12 Aug 2016 14:40:12 +0800 Subject: [SPARK-16975][SQL] Column-partition path starting '_' should be handled correctly ## What changes were proposed in this pull request? Currently, Spark ignores path names starting with underscore `_` and `.`. This causes read-failures for the column-partitioned file data sources whose partition column names starts from '_', e.g. `_col`. **Before** ```scala scala> spark.range(10).withColumn("_locality_code", $"id").write.partitionBy("_locality_code").save("/tmp/parquet") scala> spark.read.parquet("/tmp/parquet") org.apache.spark.sql.AnalysisException: Unable to infer schema for ParquetFormat at /tmp/parquet20. It must be specified manually; ``` **After** ```scala scala> spark.range(10).withColumn("_locality_code", $"id").write.partitionBy("_locality_code").save("/tmp/parquet") scala> spark.read.parquet("/tmp/parquet") res2: org.apache.spark.sql.DataFrame = [id: bigint, _locality_code: int] ``` ## How was this patch tested? Pass the Jenkins with a new test case. Author: Dongjoon Hyun Closes #14585 from dongjoon-hyun/SPARK-16975-PARQUET. --- sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'sql/core/src/test') diff --git a/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala index eac588fff2..4fcde58833 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala @@ -17,6 +17,7 @@ package org.apache.spark.sql +import java.io.File import java.math.MathContext import java.sql.{Date, Timestamp} @@ -2637,6 +2638,14 @@ class SQLQuerySuite extends QueryTest with SharedSQLContext { } } + test("SPARK-16975: Column-partition path starting '_' should be handled correctly") { + withTempDir { dir => + val parquetDir = new File(dir, "parquet").getCanonicalPath + spark.range(10).withColumn("_col", $"id").write.partitionBy("_col").save(parquetDir) + spark.read.parquet(parquetDir) + } + } + test("SPARK-16644: Aggregate should not put aggregate expressions to constraints") { withTable("tbl") { sql("CREATE TABLE tbl(a INT, b INT) USING parquet") -- cgit v1.2.3