aglinxinyuan commented on code in PR #5898: URL: https://github.com/apache/texera/pull/5898#discussion_r3456985545
########## common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceSentimentAnalysisOpDescSpec.scala: ########## @@ -0,0 +1,130 @@ +/* + * 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.huggingFace + +import org.apache.texera.amber.core.executor.OpExecWithCode +import org.apache.texera.amber.core.tuple.{AttributeType, Schema} +import org.apache.texera.amber.core.virtualidentity.{ExecutionIdentity, WorkflowIdentity} +import org.apache.texera.amber.operator.LogicalOp +import org.apache.texera.amber.operator.metadata.OperatorGroupConstants +import org.apache.texera.amber.util.JSONUtils.objectMapper +import org.scalatest.flatspec.AnyFlatSpec +import org.scalatest.matchers.should.Matchers + +import java.nio.charset.StandardCharsets +import java.util.Base64 + +class HuggingFaceSentimentAnalysisOpDescSpec extends AnyFlatSpec with Matchers { + + private val workflowId = WorkflowIdentity(1L) + private val executionId = ExecutionIdentity(1L) + + private def b64(s: String): String = + Base64.getEncoder.encodeToString(s.getBytes(StandardCharsets.UTF_8)) + + // EncodableString fields render as self.decode_python_template('<base64>') in encode mode. + private def carries(output: String, name: String): Boolean = + output.contains(name) || output.contains(b64(name)) + Review Comment: Good catch — `carries` now asserts on the base64 form only, so the raw "positive"/"neutral"/"negative" label keys can no longer mask a missing splice. ########## common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceSpamSMSDetectionOpDescSpec.scala: ########## @@ -0,0 +1,117 @@ +/* + * 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.huggingFace + +import org.apache.texera.amber.core.executor.OpExecWithCode +import org.apache.texera.amber.core.tuple.{AttributeType, Schema} +import org.apache.texera.amber.core.virtualidentity.{ExecutionIdentity, WorkflowIdentity} +import org.apache.texera.amber.operator.LogicalOp +import org.apache.texera.amber.operator.metadata.OperatorGroupConstants +import org.apache.texera.amber.util.JSONUtils.objectMapper +import org.scalatest.flatspec.AnyFlatSpec +import org.scalatest.matchers.should.Matchers + +import java.nio.charset.StandardCharsets +import java.util.Base64 + +class HuggingFaceSpamSMSDetectionOpDescSpec extends AnyFlatSpec with Matchers { + + private val workflowId = WorkflowIdentity(1L) + private val executionId = ExecutionIdentity(1L) + + private def b64(s: String): String = + Base64.getEncoder.encodeToString(s.getBytes(StandardCharsets.UTF_8)) + + private def carries(output: String, name: String): Boolean = + output.contains(name) || output.contains(b64(name)) + Review Comment: Done — `carries` is base64-only now, so "text" in "text-classification" and "score" in result["score"] can't cause a false positive. ########## common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/huggingFace/HuggingFaceTextSummarizationOpDescSpec.scala: ########## @@ -0,0 +1,121 @@ +/* + * 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.huggingFace + +import org.apache.texera.amber.core.executor.OpExecWithCode +import org.apache.texera.amber.core.tuple.{AttributeType, Schema} +import org.apache.texera.amber.core.virtualidentity.{ExecutionIdentity, WorkflowIdentity} +import org.apache.texera.amber.operator.LogicalOp +import org.apache.texera.amber.operator.metadata.OperatorGroupConstants +import org.apache.texera.amber.util.JSONUtils.objectMapper +import org.scalatest.flatspec.AnyFlatSpec +import org.scalatest.matchers.should.Matchers + +import java.nio.charset.StandardCharsets +import java.util.Base64 + +class HuggingFaceTextSummarizationOpDescSpec extends AnyFlatSpec with Matchers { + + private val workflowId = WorkflowIdentity(1L) + private val executionId = ExecutionIdentity(1L) + + private def b64(s: String): String = + Base64.getEncoder.encodeToString(s.getBytes(StandardCharsets.UTF_8)) + + private def carries(output: String, name: String): Boolean = + output.contains(name) || output.contains(b64(name)) + Review Comment: Done — `carries` asserts the base64 form only, so the `text`/`summary` local variable names no longer mask a missing splice. Applied the same tightening to the Iris spec for consistency. -- 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]
