Github user dongjoon-hyun commented on a diff in the pull request:
https://github.com/apache/spark/pull/19651#discussion_r150430468
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcUtils.scala
---
@@ -0,0 +1,138 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.sql.execution.datasources.orc
+
+import java.io.IOException
+
+import scala.collection.JavaConverters._
+import scala.collection.mutable.ArrayBuffer
+
+import org.apache.hadoop.conf.Configuration
+import org.apache.hadoop.fs.{FileStatus, Path}
+import org.apache.orc.{OrcFile, TypeDescription}
+
+import org.apache.spark.deploy.SparkHadoopUtil
+import org.apache.spark.internal.Logging
+import org.apache.spark.sql.SparkSession
+import org.apache.spark.sql.catalyst.analysis.{caseInsensitiveResolution,
caseSensitiveResolution}
+import org.apache.spark.sql.catalyst.parser.CatalystSqlParser
+import org.apache.spark.sql.types._
+
+object OrcUtils extends Logging {
+
+ // The extensions for ORC compression codecs
+ val extensionsForCompressionCodecNames = Map(
+ "NONE" -> "",
+ "SNAPPY" -> ".snappy",
+ "ZLIB" -> ".zlib",
+ "LZO" -> ".lzo")
+
+ def withNullSafe(f: Any => Any): Any => Any = {
+ input => if (input == null) null else f(input)
+ }
+
+ def listOrcFiles(pathStr: String, conf: Configuration): Seq[Path] = {
+ val origPath = new Path(pathStr)
+ val fs = origPath.getFileSystem(conf)
+ val paths = SparkHadoopUtil.get.listLeafStatuses(fs, origPath)
+ .filterNot(_.isDirectory)
+ .map(_.getPath)
+ .filterNot(_.getName.startsWith("_"))
+ .filterNot(_.getName.startsWith("."))
+ paths
+ }
+
+ private[orc] def readSchema(file: Path, conf: Configuration):
Option[TypeDescription] = {
+ try {
+ val fs = file.getFileSystem(conf)
+ val readerOptions = OrcFile.readerOptions(conf).filesystem(fs)
+ val reader = OrcFile.createReader(file, readerOptions)
+ val schema = reader.getSchema
+ if (schema.getFieldNames.size == 0) {
+ None
+ } else {
+ Some(schema)
+ }
+ } catch {
+ case _: IOException => None
--- End diff --
Yep. For here, it does.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
