more test case

sql/core/src/test/scala/org/apache/spark/sql/test/DataFrameReaderWriterSuite.scala

@@ -212,7 +212,7 @@ class DataFrameReaderWriterSuite extends QueryTest with SharedSQLContext with Be
   }
 
   test("illegal format name") {
-    val e = intercept[AnalysisException] {
+    val e = intercept[ClassNotFoundException] {
       spark.read.format("illegal").load("/test")
     }
     assert(e.getMessage.contains("Failed to find data source: illegal"))
@@ -231,12 +231,10 @@ class DataFrameReaderWriterSuite extends QueryTest with SharedSQLContext with Be
   test("prevent all column partitioning") {
     withTempDir { dir =>
       val path = dir.getCanonicalPath
-      intercept[AnalysisException] {
+      val e = intercept[AnalysisException] {
         spark.range(10).write.format("parquet").mode("overwrite").partitionBy("id").save(path)
-      }
-      intercept[AnalysisException] {
-        spark.range(10).write.format("orc").mode("overwrite").partitionBy("id").save(path)
-      }
+      }.getMessage
+      assert(e.contains("Cannot use all columns for partition columns"))
     }
   }
 
@@ -318,9 +316,10 @@ class DataFrameReaderWriterSuite extends QueryTest with SharedSQLContext with Be
     val schema = df.schema
 
     // Reader, without user specified schema
-    intercept[AnalysisException] {
+    val e = intercept[IllegalArgumentException] {
       testRead(spark.read.json(), Seq.empty, schema)
-    }
+    }.getMessage
+    assert(e.contains("'path' is not specified"))
     testRead(spark.read.json(dir), data, schema)
     testRead(spark.read.json(dir, dir), data ++ data, schema)
     testRead(spark.read.json(Seq(dir, dir): _*), data ++ data, schema)
@@ -344,9 +343,10 @@ class DataFrameReaderWriterSuite extends QueryTest with SharedSQLContext with Be
     val schema = df.schema
 
     // Reader, without user specified schema
-    intercept[AnalysisException] {
+    val e = intercept[IllegalArgumentException] {
       testRead(spark.read.parquet(), Seq.empty, schema)
-    }
+    }.getMessage
+    assert(e.contains("'path' is not specified"))
     testRead(spark.read.parquet(dir), data, schema)
     testRead(spark.read.parquet(dir, dir), data ++ data, schema)
     testRead(spark.read.parquet(Seq(dir, dir): _*), data ++ data, schema)
@@ -363,23 +363,6 @@ class DataFrameReaderWriterSuite extends QueryTest with SharedSQLContext with Be
       spark.read.schema(userSchema).parquet(Seq(dir, dir): _*), expData ++ expData, userSchema)
   }
 
-  /**
-   * This only tests whether API compiles, but does not run it as orc()
-   * cannot be run without Hive classes.
-   */
-  ignore("orc - API") {
-    // Reader, with user specified schema
-    // Refer to csv-specific test suites for behavior without user specified schema
-    spark.read.schema(userSchema).orc()
-    spark.read.schema(userSchema).orc(dir)
-    spark.read.schema(userSchema).orc(dir, dir, dir)
-    spark.read.schema(userSchema).orc(Seq(dir, dir): _*)
-    Option(dir).map(spark.read.schema(userSchema).orc)
-
-    // Writer
-    spark.range(10).write.orc(dir)
-  }
-
   private def testRead(
       df: => DataFrame,
       expectedResult: Seq[String],

sql/hive/src/test/scala/org/apache/spark/sql/hive/orc/OrcSourceSuite.scala

@@ -21,7 +21,7 @@ import java.io.File
 
 import org.scalatest.BeforeAndAfterAll
 
-import org.apache.spark.sql.{AnalysisException, QueryTest, Row}
+import org.apache.spark.sql._
 import org.apache.spark.sql.hive.test.TestHiveSingleton
 import org.apache.spark.sql.sources._
 import org.apache.spark.sql.test.SQLTestUtils
@@ -197,6 +197,8 @@ abstract class OrcSuite extends QueryTest
 }
 
 class OrcSourceSuite extends OrcSuite {
+  import spark.implicits._
+
   override def beforeAll(): Unit = {
     super.beforeAll()
 
@@ -217,6 +219,49 @@ class OrcSourceSuite extends OrcSuite {
        """.stripMargin)
   }
 
+  test("orc - API") {
+    val userSchema = new StructType().add("s", StringType)
+    val data = Seq("1", "2", "3")
+    val dir = Utils.createTempDir(namePrefix = "input").getCanonicalPath
+
+    // Writer
+    spark.createDataset(data).toDF("str").write.mode(SaveMode.Overwrite).orc(dir)
+    val df = spark.read.orc(dir)
+    checkAnswer(df, spark.createDataset(data).toDF())
+    val schema = df.schema
+
+    // Reader, without user specified schema
+    intercept[IllegalArgumentException] {
+      testRead(spark.read.orc(), Seq.empty, schema)
+    }
+    testRead(spark.read.orc(dir), data, schema)
+    testRead(spark.read.orc(dir, dir), data ++ data, schema)
+    testRead(spark.read.orc(Seq(dir, dir): _*), data ++ data, schema)
+    // Test explicit calls to single arg method - SPARK-16009
+    testRead(Option(dir).map(spark.read.orc).get, data, schema)
+
+    // Reader, with user specified schema, should just apply user schema on the file data
+    testRead(spark.read.schema(userSchema).orc(), Seq.empty, userSchema)
+    spark.read.schema(userSchema).orc(dir).printSchema()
+
+    spark.read.schema(userSchema).orc(dir).explain(true)
+
+    spark.read.schema(userSchema).orc().show()
+    spark.read.schema(userSchema).orc(dir).show()
+    val expData = Seq[String](null, null, null)
+    testRead(spark.read.schema(userSchema).orc(dir), expData, userSchema)
+    testRead(spark.read.schema(userSchema).orc(dir, dir), expData ++ expData, userSchema)
+    testRead(spark.read.schema(userSchema).orc(Seq(dir, dir): _*), expData ++ expData, userSchema)
+
+  }
+  private def testRead(
+      df: => DataFrame,
+      expectedResult: Seq[String],
+      expectedSchema: StructType): Unit = {
+    checkAnswer(df, spark.createDataset(expectedResult).toDF())
+    assert(df.schema === expectedSchema)
+  }
+
   test("SPARK-12218 Converting conjunctions into ORC SearchArguments") {
     // The `LessThan` should be converted while the `StringContains` shouldn't
     val schema = new StructType(