[SPARK-32840][SQL] nvalid interval value can happen to be just adhesi…

…ve with the unit
apache · Sep 10, 2020 · d3dc77c · d3dc77c
1 parent 0c7616b
commit d3dc77c
Show file tree

Hide file tree

Showing 4 changed files with 88 additions and 3 deletions.
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala
@@ -2107,7 +2107,16 @@ class AstBuilder(conf: SQLConf) extends SqlBaseBaseVisitor[AnyRef] with Logging
         val kvs = units.indices.map { i =>
           val u = units(i).getText
           val v = if (values(i).STRING() != null) {
-            string(values(i).STRING())
+            val value = string(values(i).STRING())
+            // SPARK-32840: For invalid cases, e.g. INTERVAL '1 day 2' hour,
+            // INTERVAL 'interval 1' day, we need to check ahead before they are concatenated with
+            // units and become valid ones, e.g. '1 day 2 hour'.
+            // Ideally, we only ensure the value parts don't contain any units here.
+            if (value.exists(Character.isLetter)) {
+              throw new ParseException("Can only use numbers in the interval value part for" +
+                s" multiple unit value pairs interval form, but got invalid value: $value", ctx)
+            }
+            value
           } else {
             values(i).getText
           }

diff --git a/sql/core/src/test/resources/sql-tests/inputs/interval.sql b/sql/core/src/test/resources/sql-tests/inputs/interval.sql
@@ -180,3 +180,7 @@ SELECT
   to_json(from_json('{"a":"1 days"}', 'a interval')),
   to_json(map('a', interval 25 month 100 day 130 minute)),
   from_json(to_json(map('a', interval 25 month 100 day 130 minute)), 'a interval');
+
+select interval '1 day 2' day;
+select interval 'interval 1' day;
+select interval '-\t 1' day;
diff --git a/sql/core/src/test/resources/sql-tests/results/ansi/interval.sql.out b/sql/core/src/test/resources/sql-tests/results/ansi/interval.sql.out
@@ -1,5 +1,5 @@
 -- Automatically generated by SQLQueryTestSuite
--- Number of queries: 93
+-- Number of queries: 96
 
 
 -- !query
@@ -956,3 +956,39 @@ SELECT
 struct<from_json({"a":"1 days"}):struct<a:interval>,to_json(from_json({"a":"1 days"})):string,to_json(map(a, INTERVAL '2 years 1 months 100 days 2 hours 10 minutes')):string,from_json(to_json(map(a, INTERVAL '2 years 1 months 100 days 2 hours 10 minutes'))):struct<a:interval>>
 -- !query output
 {"a":1 days}	{"a":"1 days"}	{"a":"2 years 1 months 100 days 2 hours 10 minutes"}	{"a":2 years 1 months 100 days 2 hours 10 minutes}
+
+
+-- !query
+select interval '1 day 2' day
+-- !query schema
+struct<>
+-- !query output
+org.apache.spark.sql.catalyst.parser.ParseException
+
+Can only use numbers in the interval value part for multiple unit value pairs interval form, but got invalid value: 1 day 2(line 1, pos 16)
+
+== SQL ==
+select interval '1 day 2' day
+----------------^^^
+
+
+-- !query
+select interval 'interval 1' day
+-- !query schema
+struct<>
+-- !query output
+org.apache.spark.sql.catalyst.parser.ParseException
+
+Can only use numbers in the interval value part for multiple unit value pairs interval form, but got invalid value: interval 1(line 1, pos 16)
+
+== SQL ==
+select interval 'interval 1' day
+----------------^^^
+
+
+-- !query
+select interval '-\t 1' day
+-- !query schema
+struct<INTERVAL '-1 days':interval>
+-- !query output
+-1 days
diff --git a/sql/core/src/test/resources/sql-tests/results/interval.sql.out b/sql/core/src/test/resources/sql-tests/results/interval.sql.out
@@ -1,5 +1,5 @@
 -- Automatically generated by SQLQueryTestSuite
--- Number of queries: 93
+-- Number of queries: 96
 
 
 -- !query
@@ -928,3 +928,39 @@ SELECT
 struct<from_json({"a":"1 days"}):struct<a:interval>,to_json(from_json({"a":"1 days"})):string,to_json(map(a, INTERVAL '2 years 1 months 100 days 2 hours 10 minutes')):string,from_json(to_json(map(a, INTERVAL '2 years 1 months 100 days 2 hours 10 minutes'))):struct<a:interval>>
 -- !query output
 {"a":1 days}	{"a":"1 days"}	{"a":"2 years 1 months 100 days 2 hours 10 minutes"}	{"a":2 years 1 months 100 days 2 hours 10 minutes}
+
+
+-- !query
+select interval '1 day 2' day
+-- !query schema
+struct<>
+-- !query output
+org.apache.spark.sql.catalyst.parser.ParseException
+
+Can only use numbers in the interval value part for multiple unit value pairs interval form, but got invalid value: 1 day 2(line 1, pos 16)
+
+== SQL ==
+select interval '1 day 2' day
+----------------^^^
+
+
+-- !query
+select interval 'interval 1' day
+-- !query schema
+struct<>
+-- !query output
+org.apache.spark.sql.catalyst.parser.ParseException
+
+Can only use numbers in the interval value part for multiple unit value pairs interval form, but got invalid value: interval 1(line 1, pos 16)
+
+== SQL ==
+select interval 'interval 1' day
+----------------^^^
+
+
+-- !query
+select interval '-\t 1' day
+-- !query schema
+struct<INTERVAL '-1 days':interval>
+-- !query output
+-1 days