HyukjinKwon commented on a change in pull request #28308: URL: https://github.com/apache/spark/pull/28308#discussion_r433711518
########## File path: sql/core/src/test/scala/org/apache/spark/sql/expressions/ExpressionInfoSuite.scala ########## @@ -0,0 +1,156 @@ +/* + * 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.expressions + +import scala.collection.parallel.immutable.ParVector + +import org.apache.spark.SparkFunSuite +import org.apache.spark.sql.catalyst.FunctionIdentifier +import org.apache.spark.sql.catalyst.expressions.ExpressionInfo +import org.apache.spark.sql.execution.HiveResult.hiveResultString +import org.apache.spark.sql.internal.SQLConf +import org.apache.spark.sql.test.SharedSparkSession + +class ExpressionInfoSuite extends SparkFunSuite with SharedSparkSession { + + test("Replace _FUNC_ in ExpressionInfo") { + val info = spark.sessionState.catalog.lookupFunctionInfo(FunctionIdentifier("upper")) + assert(info.getName === "upper") + assert(info.getClassName === "org.apache.spark.sql.catalyst.expressions.Upper") + assert(info.getUsage === "upper(str) - Returns `str` with all characters changed to uppercase.") + assert(info.getExamples.contains("> SELECT upper('SparkSql');")) + assert(info.getSince === "1.0.1") + assert(info.getNote === "") + assert(info.getExtended.contains("> SELECT upper('SparkSql');")) + } + + test("group info in ExpressionInfo") { + val info = spark.sessionState.catalog.lookupFunctionInfo(FunctionIdentifier("sum")) + assert(info.getGroup === "agg_funcs") + + Seq("agg_funcs", "array_funcs", "datetime_funcs", "json_funcs", "map_funcs", "window_funcs") + .foreach { groupName => + val info = new ExpressionInfo( + "testClass", null, "testName", null, "", "", "", groupName, "", "") + assert(info.getGroup === groupName) + } + + val errMsg = intercept[IllegalArgumentException] { + val invalidGroupName = "invalid_group_funcs" + new ExpressionInfo("testClass", null, "testName", null, "", "", "", invalidGroupName, "", "") + }.getMessage + assert(errMsg.contains("'group' is malformed in the expression [testName].")) + } + + test("error handling in ExpressionInfo") { + val errMsg1 = intercept[IllegalArgumentException] { + val invalidNote = " invalid note" + new ExpressionInfo("testClass", null, "testName", null, "", "", invalidNote, "", "", "") + }.getMessage + assert(errMsg1.contains("'note' is malformed in the expression [testName].")) + + val errMsg2 = intercept[IllegalArgumentException] { + val invalidSince = "-3.0.0" + new ExpressionInfo("testClass", null, "testName", null, "", "", "", "", invalidSince, "") + }.getMessage + assert(errMsg2.contains("'since' is malformed in the expression [testName].")) + + val errMsg3 = intercept[IllegalArgumentException] { + val invalidDeprecated = " invalid deprecated" + new ExpressionInfo("testClass", null, "testName", null, "", "", "", "", "", invalidDeprecated) + }.getMessage + assert(errMsg3.contains("'deprecated' is malformed in the expression [testName].")) + } + + test("using _FUNC_ instead of function names in examples") { + val exampleRe = "(>.*;)".r + val setStmtRe = "(?i)^(>\\s+set\\s+).+".r + val ignoreSet = Set( + // Examples for CaseWhen show simpler syntax: + // `CASE WHEN ... THEN ... WHEN ... THEN ... END` + "org.apache.spark.sql.catalyst.expressions.CaseWhen", + // _FUNC_ is replaced by `locate` but `locate(... IN ...)` is not supported + "org.apache.spark.sql.catalyst.expressions.StringLocate", + // _FUNC_ is replaced by `%` which causes a parsing error on `SELECT %(2, 1.8)` + "org.apache.spark.sql.catalyst.expressions.Remainder", + // Examples demonstrate alternative names, see SPARK-20749 + "org.apache.spark.sql.catalyst.expressions.Length") + spark.sessionState.functionRegistry.listFunction().foreach { funcId => + val info = spark.sessionState.catalog.lookupFunctionInfo(funcId) + val className = info.getClassName + withClue(s"Expression class '$className'") { + val exprExamples = info.getOriginalExamples + if (!exprExamples.isEmpty && !ignoreSet.contains(className)) { + assert(exampleRe.findAllIn(exprExamples).toIterable + .filter(setStmtRe.findFirstIn(_).isEmpty) // Ignore SET commands + .forall(_.contains("_FUNC_"))) + } + } + } + } + + test("check outputs of expression examples") { Review comment: @advancedxy, that was fixed SPARK-31725. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
