Move to FileBasedDataSourceSuite

Author: dongjoon-hyun

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

@@ -17,6 +17,10 @@
 
 package org.apache.spark.sql
 
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.sql.internal.SQLConf
 import org.apache.spark.sql.test.SharedSQLContext
 
 class FileBasedDataSourceSuite extends QueryTest with SharedSQLContext {
@@ -92,4 +96,39 @@ class FileBasedDataSourceSuite extends QueryTest with SharedSQLContext {
       }
     }
   }
+
+  // Only ORC/Parquet support this.
+  Seq("orc", "parquet").foreach { format =>
+    testQuietly(s"Enabling/disabling ignoreMissingFiles using $format") {
+      def testIgnoreMissingFiles(): Unit = {
+        withTempDir { dir =>
+          val basePath = dir.getCanonicalPath
+          spark.range(1).toDF("a").write.format(format).save(new Path(basePath, "first").toString)
+          spark.range(1, 2).toDF("a").write.format(format)
+            .save(new Path(basePath, "second").toString)
+          val thirdPath = new Path(basePath, "third")
+          spark.range(2, 3).toDF("a").write.format(format).save(thirdPath.toString)
+          val df = spark.read.format(format).load(
+            new Path(basePath, "first").toString,
+            new Path(basePath, "second").toString,
+            new Path(basePath, "third").toString)
+
+          val fs = thirdPath.getFileSystem(spark.sparkContext.hadoopConfiguration)
+          assert(fs.delete(thirdPath, true))
+          checkAnswer(df, Seq(Row(0), Row(1)))
+        }
+      }
+
+      withSQLConf(SQLConf.IGNORE_MISSING_FILES.key -> "true") {
+        testIgnoreMissingFiles()
+      }
+
+      withSQLConf(SQLConf.IGNORE_MISSING_FILES.key -> "false") {
+        val exception = intercept[SparkException] {
+          testIgnoreMissingFiles()
+        }
+        assert(exception.getMessage().contains("does not exist"))
+      }
+    }
+  }
 }

sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/orc/OrcQuerySuite.scala

@@ -655,35 +655,4 @@ class OrcQuerySuite extends OrcQueryTest with SharedSQLContext {
       }
     }
   }
-
-  testQuietly("Enabling/disabling ignoreMissingFiles") {
-    def testIgnoreMissingFiles(): Unit = {
-      withTempDir { dir =>
-        val basePath = dir.getCanonicalPath
-        spark.range(1).toDF("a").write.orc(new Path(basePath, "first").toString)
-        spark.range(1, 2).toDF("a").write.orc(new Path(basePath, "second").toString)
-        val thirdPath = new Path(basePath, "third")
-        spark.range(2, 3).toDF("a").write.orc(thirdPath.toString)
-        val df = spark.read.orc(
-          new Path(basePath, "first").toString,
-          new Path(basePath, "second").toString,
-          new Path(basePath, "third").toString)
-
-        val fs = thirdPath.getFileSystem(spark.sparkContext.hadoopConfiguration)
-        assert(fs.delete(thirdPath, true))
-        checkAnswer(df, Seq(Row(0), Row(1)))
-      }
-    }
-
-    withSQLConf(SQLConf.IGNORE_MISSING_FILES.key -> "true") {
-      testIgnoreMissingFiles()
-    }
-
-    withSQLConf(SQLConf.IGNORE_MISSING_FILES.key -> "false") {
-      val exception = intercept[SparkException] {
-        testIgnoreMissingFiles()
-      }
-      assert(exception.getMessage().contains("does not exist"))
-    }
-  }
 }

sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetQuerySuite.scala

@@ -355,39 +355,6 @@ class ParquetQuerySuite extends QueryTest with ParquetTest with SharedSQLContext
     }
   }
 
-  testQuietly("Enabling/disabling ignoreMissingFiles") {
-    def testIgnoreMissingFiles(): Unit = {
-      withTempDir { dir =>
-        val basePath = dir.getCanonicalPath
-        spark.range(1).toDF("a").write.parquet(new Path(basePath, "first").toString)
-        spark.range(1, 2).toDF("a").write.parquet(new Path(basePath, "second").toString)
-        val thirdPath = new Path(basePath, "third")
-        spark.range(2, 3).toDF("a").write.parquet(thirdPath.toString)
-        val df = spark.read.parquet(
-          new Path(basePath, "first").toString,
-          new Path(basePath, "second").toString,
-          new Path(basePath, "third").toString)
-
-        val fs = thirdPath.getFileSystem(spark.sparkContext.hadoopConfiguration)
-        fs.delete(thirdPath, true)
-        checkAnswer(
-          df,
-          Seq(Row(0), Row(1)))
-      }
-    }
-
-    withSQLConf(SQLConf.IGNORE_MISSING_FILES.key -> "true") {
-      testIgnoreMissingFiles()
-    }
-
-    withSQLConf(SQLConf.IGNORE_MISSING_FILES.key -> "false") {
-      val exception = intercept[SparkException] {
-        testIgnoreMissingFiles()
-      }
-      assert(exception.getMessage().contains("does not exist"))
-    }
-  }
-
   /**
    * this is part of test 'Enabling/disabling ignoreCorruptFiles' but run in a loop
    * to increase the chance of failure