Github user petermaxlee commented on a diff in the pull request:
https://github.com/apache/spark/pull/14472#discussion_r73272864
--- Diff:
sql/core/src/test/scala/org/apache/spark/sql/SQLQueryTestSuite.scala ---
@@ -0,0 +1,186 @@
+/*
+ * 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 + 2;
+ * select current_date;
+ * }}}
+ *
+ * Result files are encoded as XMLs.
+ */
+class SQLQueryTestSuite extends QueryTest with SharedSQLContext {
+
+ private val regenerateGoldenFiles: Boolean =
System.getenv("SPARK_GENERATE_GOLDEN_FILES") == "1"
+
+ private val inputFilePath = "src/test/resources/sql-tests/inputs/"
+ private val goldenFilePath = "src/test/resources/sql-tests/results/"
+
+ /** 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 toXML: String = {
+ // We are explicitly not using multi-line string due to stripMargin
removing |s,
+ // and not using XML interpolation because there is no simple way to
indent outputs nicely
+ // (scala.xml.PrettyPrinter has issue with tabs).
+ "<query>\n" +
+ s" <sql><![CDATA[$sql]]></sql>\n" +
+ s" <schema><![CDATA[$schema]]></schema>\n" +
+ s" <output><![CDATA[\n$output]]></output>\n" +
+ s"</query>"
+ }
+ }
+
+ 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")
+ cleaned.split("(?<=[^\\\\]);").map(_.trim).filterNot(q => q ==
"").toSeq
+ }
+
+ // Run the SQL queries preparing them for comparison.
+ val outputs: Seq[QueryOutput] = queries.map { sql =>
+ val df = spark.sql(sql)
+ // We might need to do some query canonicalization in the future.
+ QueryOutput(
+ sql = sql,
+ schema = df.schema.map(_.dataType.simpleString).mkString(", "),
+ output = df.showString(_numRows = 10000, truncate = 10000).trim)
--- End diff --
using showString might not be the most friendly when there is a mismatch
and the output is huge, but should work very well with smaller outputs.
---
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
