Github user petermaxlee commented on a diff in the pull request: https://github.com/apache/spark/pull/14472#discussion_r74190929 --- Diff: sql/core/src/test/scala/org/apache/spark/sql/SQLQueryTestSuite.scala --- @@ -0,0 +1,212 @@ +/* + * 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 + +import java.io.File +import java.util.{Locale, TimeZone} + +import org.apache.spark.sql.catalyst.rules.RuleExecutor +import org.apache.spark.sql.catalyst.util.{fileToString, stringToFile} +import org.apache.spark.sql.test.SharedSQLContext + +/** + * End-to-end test cases for SQL queries. + * + * Each case is loaded from a file in "spark/sql/core/src/test/resources/sql-tests/inputs". + * Each case has a golden result file in "spark/sql/core/src/test/resources/sql-tests/results". + * + * To re-generate golden files, run: + * {{{ + * SPARK_GENERATE_GOLDEN_FILES=1 build/sbt "sql/test-only *SQLQueryTestSuite" + * }}} + * + * The format for input files is simple: + * 1. A list of SQL queries separated by semicolon. + * 2. Lines starting with -- are treated as comments and ignored. + * + * For example: + * {{{ + * -- this is a comment + * select 1, -1; + * select current_date; + * }}} + * + * The format for golden result files look roughly like: + * {{{ + * -- some header information + * + * -- !query 0 + * select 1, -1 + * -- !query 0 schema + * struct<...schema...> + * -- !query 0 output + * ... data row 1 ... + * ... data row 2 ... + * ... + * + * -- !query 1 + * ... + * }}} + */ +class SQLQueryTestSuite extends QueryTest with SharedSQLContext { + + private val regenerateGoldenFiles: Boolean = System.getenv("SPARK_GENERATE_GOLDEN_FILES") == "1" + + private val baseResourcePath = { + // If regenerateGoldenFiles is true, we must be running this in SBT and we use hard-coded + // relative path. Otherwise, we use classloader's getResource to find the location. + if (regenerateGoldenFiles) { + java.nio.file.Paths.get("src", "test", "resources", "sql-tests").toFile + } else { + val res = getClass.getClassLoader.getResource("sql-tests") + new File(res.getFile) + } + } + + private val inputFilePath = new File(baseResourcePath, "inputs").getAbsolutePath + private val goldenFilePath = new File(baseResourcePath, "results").getAbsolutePath + + /** List of test cases to ignore, in lower cases. */ + private val blackList = Set( + "blacklist.sql" // Do NOT remove this one. It is here to test the blacklist functionality. + ) + + // Create all the test cases. + listTestCases().foreach(createScalaTestCase) + + /** A test case. */ + private case class TestCase(name: String, inputFile: String, resultFile: String) + + /** A single SQL query's output. */ + private case class QueryOutput(sql: String, schema: String, output: String) { + def toString(queryIndex: Int): String = { + // We are explicitly not using multi-line string due to stripMargin removing "|" in output. + s"-- !query $queryIndex\n" + + sql + "\n" + + s"-- !query $queryIndex schema\n" + + schema + "\n" + + s"-- !query $queryIndex output\n" + + output + } + } + + private def createScalaTestCase(testCase: TestCase): Unit = { + if (blackList.contains(testCase.name.toLowerCase)) { + // Create a test case to ignore this case. + ignore(testCase.name) { /* Do nothing */ } + } else { + // Create a test case to run this case. + test(testCase.name) { runTest(testCase) } + } + } + + /** Run a test case. */ + private def runTest(testCase: TestCase): Unit = { + val input = fileToString(new File(testCase.inputFile)) + + // List of SQL queries to run + val queries: Seq[String] = { + // val cleaned = input.split("\n").filterNot(_.matches("--.*(?<=[^\\\\]);")).mkString("\n") + val cleaned = input.split("\n").filterNot(_.startsWith("--")).mkString("\n") + // note: this is not a robust way to split queries using semicolon, but works for now. + cleaned.split("(?<=[^\\\\]);").map(_.trim).filter(_ != "").toSeq --- End diff -- I copied this from HiveComparisonTest. I think it is done to avoid escaping e.g. "\;". It is really not very robust, but seems fine for now.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org