[GitHub] [spark] turboFei commented on a change in pull request #31040: [SPARK-33100][SQL] Ignore a semicolon inside a bracketed comment in spark-sql

[GitBox <gi...@apache.org>]

turboFei commented on a change in pull request #31040:
URL: https://github.com/apache/spark/pull/31040#discussion_r551847397



##########
File path: sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/CliSuite.scala
##########
@@ -296,4 +296,67 @@ class CliSuite extends SparkFunSuite with BeforeAndAfterAll with Logging {
       "set spark.sql.warehouse.dir;" -> tmpDir.getAbsolutePath)
     tmpDir.delete()
   }
+
+  test("SPARK-26321 Should not split semicolon within quoted string literals") {
+    runCliWithin(3.minute)(
+      """select 'Test1', "^;^";""" -> "Test1\t^;^",
+      """select 'Test2', "\";";""" -> "Test2\t\";",
+      """select 'Test3', "\';";""" -> "Test3\t';",
+      "select concat('Test4', ';');" -> "Test4;"
+    )
+  }
+
+  test("SPARK-30049 Should not complain for quotes in commented lines") {
+    runCliWithin(1.minute)(
+      """SELECT concat('test', 'comment') -- someone's comment here
+        |;""".stripMargin -> "testcomment"
+    )
+  }
+
+  test("SPARK-31102 spark-sql fails to parse when contains comment") {
+    runCliWithin(1.minute)(
+      """SELECT concat('test', 'comment'),
+        |    -- someone's comment here
+        | 2;""".stripMargin -> "testcomment"
+    )
+  }
+
+  test("SPARK-30049 Should not complain for quotes in commented with multi-lines") {
+    runCliWithin(1.minute)(
+      """SELECT concat('test', 'comment') -- someone's comment here \
+        | comment continues here with single ' quote \
+        | extra ' \
+        |;""".stripMargin -> "testcomment"
+    )
+  }
+
+  test("SPARK-31595 Should allow unescaped quote mark in quoted string") {
+    runCliWithin(1.minute)(
+      "SELECT '\"legal string a';select 1 + 234;".stripMargin -> "235"
+    )
+    runCliWithin(1.minute)(
+      "SELECT \"legal 'string b\";select 22222 + 1;".stripMargin -> "22223"
+    )
+  }
+
+  test("SPARK-33100: Ignore a semicolon inside a bracketed comment in spark-sql") {
+    runCliWithin(4.minute)(
+      "/* SELECT 'test';*/ SELECT 'test';" -> "test",
+      ";;/* SELECT 'test';*/ SELECT 'test';" -> "test",
+      "/* SELECT 'test';*/;; SELECT 'test';" -> "test",
+      "SELECT 'test'; -- SELECT 'test';" -> "",
+      "SELECT 'test'; /* SELECT 'test';*/;" -> "",
+      "/*$meta chars{^\\;}*/ SELECT 'test';" -> "test",
+      "/*\nmulti-line\n*/ SELECT 'test';" -> "test",
+      "/*/* multi-level bracketed*/ SELECT 'test';" -> "test"
+    )
+  }
+
+  test("SPARK-33100: test sql statements with hint in bracketed comment") {
+    runCliWithin(2.minute)(
+      "CREATE TEMPORARY VIEW t AS SELECT * FROM VALUES(1, 2) AS t(k, v);" -> "",
+      "EXPLAIN EXTENDED SELECT /*+ broadcast(t) */ * from t;"
+        -> "ResolvedHint (strategy=broadcast)"

Review comment:
       because spark-2.4 does not support mergeJoin hint, so I modify this ut




----------------------------------------------------------------
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:
users@infra.apache.org



---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org