aglinxinyuan commented on code in PR #6077: URL: https://github.com/apache/texera/pull/6077#discussion_r3518165505
########## common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/SpecialPhysicalOpFactorySpec.scala: ########## @@ -0,0 +1,100 @@ +/* + * 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.texera.amber.operator + +import org.apache.texera.amber.core.storage.VFSURIFactory +import org.apache.texera.amber.core.tuple.{Attribute, AttributeType, Schema} +import org.apache.texera.amber.core.virtualidentity.{ + ExecutionIdentity, + OperatorIdentity, + PhysicalOpIdentity, + WorkflowIdentity +} +import org.apache.texera.amber.core.workflow.{GlobalPortIdentity, PortIdentity, PreferController} +import org.scalatest.flatspec.AnyFlatSpec +import org.scalatest.matchers.should.Matchers + +class SpecialPhysicalOpFactorySpec extends AnyFlatSpec with Matchers { + + private val workflowId = WorkflowIdentity(42L) + private val executionId = ExecutionIdentity(7L) + private val schema = Schema().add(new Attribute("col", AttributeType.STRING)) + + private def portUri(opName: String, layer: String, portId: Int) = { + val gpid = GlobalPortIdentity( + PhysicalOpIdentity(OperatorIdentity(opName), layer), + PortIdentity(portId), + input = false + ) + VFSURIFactory.resultURI(VFSURIFactory.createPortBaseURI(workflowId, executionId, gpid)) + } + + "SpecialPhysicalOpFactory.newSourcePhysicalOp" should + "derive a source op that wires the decoded port identity, ports, and schema" in { + val uri = portUri("srcOp", "layerA", 3) + val downstream = PhysicalOpIdentity(OperatorIdentity("down-stream"), "main") + val op = SpecialPhysicalOpFactory.newSourcePhysicalOp( + workflowId, + executionId, + uri, + downstream, + PortIdentity(5), + schema + ) + op.id.logicalOpId shouldBe OperatorIdentity("srcOp") + // layerName: "${layerName}_source_${portId.id}_${downstreamLogicalId'}_${downstreamPort.id}" Review Comment: Fixed the stray apostrophe in the comment. ########## common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/source/scan/file/FileScanUtilsSpec.scala: ########## @@ -0,0 +1,104 @@ +/* + * 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.texera.amber.operator.source.scan.file + +import org.apache.texera.amber.operator.source.scan.{FileAttributeType, FileDecodingMethod} +import org.scalatest.BeforeAndAfterAll +import org.scalatest.flatspec.AnyFlatSpec + +import java.io.{BufferedOutputStream, FileOutputStream} +import java.nio.file.{Files, Path} +import java.util.zip.{ZipEntry, ZipOutputStream} + +class FileScanUtilsSpec extends AnyFlatSpec with BeforeAndAfterAll { + + private val zips = scala.collection.mutable.ArrayBuffer.empty[Path] + + private def makeZip(entries: (String, String)*): String = { + val path = Files.createTempFile("filescanutils-", ".zip") + zips += path + val zipOut = new ZipOutputStream(new BufferedOutputStream(new FileOutputStream(path.toFile))) + try { + entries.foreach { + case (name, content) => + zipOut.putNextEntry(new ZipEntry(name)) + zipOut.write(content.getBytes("UTF-8")) + zipOut.closeEntry() + } + } finally { + zipOut.close() + } + path.toFile.toURI.toString + } + + override def afterAll(): Unit = { + zips.foreach(Files.deleteIfExists) + super.afterAll() + } + + "FileScanUtils.createTuplesFromFile" should + "extract every zip entry as a single-string tuple" in { + val tuples = FileScanUtils + .createTuplesFromFile( + fileName = makeZip("a.txt" -> "Content A", "b.txt" -> "Content B"), + displayFileName = "ignored-when-extracting", + attributeType = FileAttributeType.SINGLE_STRING, + fileEncoding = FileDecodingMethod.UTF_8, + extract = true, + outputFileName = false, + fileScanOffset = None, + fileScanLimit = None + ) + .toSeq + assert(tuples.size == 2) Review Comment: Done — now asserts the decoded contents ({"Content A", "Content B"}), not just the tuple count. ########## common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/source/scan/file/FileScanUtilsSpec.scala: ########## @@ -0,0 +1,104 @@ +/* + * 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.texera.amber.operator.source.scan.file + +import org.apache.texera.amber.operator.source.scan.{FileAttributeType, FileDecodingMethod} +import org.scalatest.BeforeAndAfterAll +import org.scalatest.flatspec.AnyFlatSpec + +import java.io.{BufferedOutputStream, FileOutputStream} +import java.nio.file.{Files, Path} +import java.util.zip.{ZipEntry, ZipOutputStream} + +class FileScanUtilsSpec extends AnyFlatSpec with BeforeAndAfterAll { + + private val zips = scala.collection.mutable.ArrayBuffer.empty[Path] + + private def makeZip(entries: (String, String)*): String = { + val path = Files.createTempFile("filescanutils-", ".zip") + zips += path + val zipOut = new ZipOutputStream(new BufferedOutputStream(new FileOutputStream(path.toFile))) + try { + entries.foreach { + case (name, content) => + zipOut.putNextEntry(new ZipEntry(name)) + zipOut.write(content.getBytes("UTF-8")) + zipOut.closeEntry() + } + } finally { + zipOut.close() + } + path.toFile.toURI.toString + } + + override def afterAll(): Unit = { + zips.foreach(Files.deleteIfExists) + super.afterAll() + } + + "FileScanUtils.createTuplesFromFile" should + "extract every zip entry as a single-string tuple" in { + val tuples = FileScanUtils + .createTuplesFromFile( + fileName = makeZip("a.txt" -> "Content A", "b.txt" -> "Content B"), + displayFileName = "ignored-when-extracting", + attributeType = FileAttributeType.SINGLE_STRING, + fileEncoding = FileDecodingMethod.UTF_8, + extract = true, + outputFileName = false, + fileScanOffset = None, + fileScanLimit = None + ) + .toSeq + assert(tuples.size == 2) + } + + it should "drop __MACOSX metadata entries when extracting" in { + val tuples = FileScanUtils + .createTuplesFromFile( + fileName = makeZip("real.txt" -> "keep me", "__MACOSX/._real.txt" -> "junk"), + displayFileName = "d", + attributeType = FileAttributeType.SINGLE_STRING, + fileEncoding = FileDecodingMethod.UTF_8, + extract = true, + outputFileName = false, + fileScanOffset = None, + fileScanLimit = None + ) + .toSeq + assert(tuples.size == 1) Review Comment: Done — now asserts the surviving entry's content is "keep me", so a mis-decode/mis-association fails the test. ########## common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/source/scan/file/FileScanUtilsSpec.scala: ########## @@ -0,0 +1,104 @@ +/* + * 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.texera.amber.operator.source.scan.file + +import org.apache.texera.amber.operator.source.scan.{FileAttributeType, FileDecodingMethod} +import org.scalatest.BeforeAndAfterAll +import org.scalatest.flatspec.AnyFlatSpec + +import java.io.{BufferedOutputStream, FileOutputStream} +import java.nio.file.{Files, Path} +import java.util.zip.{ZipEntry, ZipOutputStream} + +class FileScanUtilsSpec extends AnyFlatSpec with BeforeAndAfterAll { + + private val zips = scala.collection.mutable.ArrayBuffer.empty[Path] + + private def makeZip(entries: (String, String)*): String = { + val path = Files.createTempFile("filescanutils-", ".zip") + zips += path + val zipOut = new ZipOutputStream(new BufferedOutputStream(new FileOutputStream(path.toFile))) + try { + entries.foreach { + case (name, content) => + zipOut.putNextEntry(new ZipEntry(name)) + zipOut.write(content.getBytes("UTF-8")) + zipOut.closeEntry() + } + } finally { + zipOut.close() + } + path.toFile.toURI.toString + } + + override def afterAll(): Unit = { + zips.foreach(Files.deleteIfExists) + super.afterAll() + } + + "FileScanUtils.createTuplesFromFile" should + "extract every zip entry as a single-string tuple" in { + val tuples = FileScanUtils + .createTuplesFromFile( + fileName = makeZip("a.txt" -> "Content A", "b.txt" -> "Content B"), + displayFileName = "ignored-when-extracting", + attributeType = FileAttributeType.SINGLE_STRING, + fileEncoding = FileDecodingMethod.UTF_8, + extract = true, + outputFileName = false, + fileScanOffset = None, + fileScanLimit = None + ) + .toSeq + assert(tuples.size == 2) + } + + it should "drop __MACOSX metadata entries when extracting" in { + val tuples = FileScanUtils + .createTuplesFromFile( + fileName = makeZip("real.txt" -> "keep me", "__MACOSX/._real.txt" -> "junk"), + displayFileName = "d", + attributeType = FileAttributeType.SINGLE_STRING, + fileEncoding = FileDecodingMethod.UTF_8, + extract = true, + outputFileName = false, + fileScanOffset = None, + fileScanLimit = None + ) + .toSeq + assert(tuples.size == 1) + } + + it should "flat-map each line of an extracted entry for a per-line attribute type" in { + val tuples = FileScanUtils + .createTuplesFromFile( + fileName = makeZip("lines.txt" -> "l1\nl2\nl3"), + displayFileName = "d", + attributeType = FileAttributeType.STRING, + fileEncoding = FileDecodingMethod.UTF_8, + extract = true, + outputFileName = false, + fileScanOffset = None, + fileScanLimit = None + ) + .toSeq + assert(tuples.size == 3) Review Comment: Done — now asserts the per-line contents and order (l1, l2, l3). -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
