Support parenthesized expression in filter (#888)

docs/ppl-lang/PPL-Example-Commands.md

@@ -50,6 +50,10 @@ _- **Limitation: new field added by eval command with a function cannot be dropp
 - `source = table | where a < 1 | fields a,b,c`
 - `source = table | where b != 'test' | fields a,b,c`
 - `source = table | where c = 'test' | fields a,b,c | head 3`
+- `source = table | where c = 'test' AND a = 1 | fields a,b,c`
+- `source = table | where c != 'test' OR a > 1 | fields a,b,c`
+- `source = table | where (b > 1 OR a > 1) AND c != 'test' | fields a,b,c`
+- `source = table | where c = 'test' NOT a > 1 | fields a,b,c` - Note: "AND" is optional
 - `source = table | where ispresent(b)`
 - `source = table | where isnull(coalesce(a, b)) | fields a,b,c | head 3`
 - `source = table | where isempty(a)`

docs/ppl-lang/ppl-where-command.md

@@ -27,15 +27,15 @@ PPL query:
 ### Additional Examples
 
 #### **Filters With Logical Conditions**
-```
-- `source = table | where c = 'test' AND a = 1 | fields a,b,c`
-- `source = table | where c != 'test' OR a > 1 | fields a,b,c | head 1`
-- `source = table | where c = 'test' NOT a > 1 | fields a,b,c`
 - `source = table | where a = 1 | fields a,b,c`
 - `source = table | where a >= 1 | fields a,b,c`
 - `source = table | where a < 1 | fields a,b,c`
 - `source = table | where b != 'test' | fields a,b,c`
 - `source = table | where c = 'test' | fields a,b,c | head 3`
+- `source = table | where c = 'test' AND a = 1 | fields a,b,c`
+- `source = table | where c != 'test' OR a > 1 | fields a,b,c`
+- `source = table | where (b > 1 OR a > 1) AND c != 'test' | fields a,b,c`
+- `source = table | where c = 'test' NOT a > 1 | fields a,b,c` - Note: "AND" is optional
 - `source = table | where ispresent(b)`
 - `source = table | where isnull(coalesce(a, b)) | fields a,b,c | head 3`
 - `source = table | where isempty(a)`
@@ -45,7 +45,6 @@ PPL query:
 - `source = table | where b not between '2024-09-10' and '2025-09-10'` - Note: This returns b >= '2024-09-10' and b <= '2025-09-10'
 - `source = table | where cidrmatch(ip, '192.169.1.0/24')`
 - `source = table | where cidrmatch(ipv6, '2003:db8::/32')`
-
 - `source = table | eval status_category =
       case(a >= 200 AND a < 300, 'Success',
       a >= 300 AND a < 400, 'Redirection',
@@ -57,10 +56,8 @@ PPL query:
       a >= 400 AND a < 500, 'Client Error',
       a >= 500, 'Server Error'
       else 'Incorrect HTTP status code'
-      ) = 'Incorrect HTTP status code'
-
+      ) = 'Incorrect HTTP status code'`
 - `source = table
       | eval factor = case(a > 15, a - 14, isnull(b), a - 7, a < 3, a + 1 else 1)
       | where case(factor = 2, 'even', factor = 4, 'even', factor = 6, 'even', factor = 8, 'even' else 'odd') = 'even'
       |  stats count() by factor`
-```

integ-test/src/integration/resources/tpch/q19.ppl

@@ -37,25 +37,30 @@ where
 */
 
 source = lineitem
-| join ON p_partkey = l_partkey
-     and p_brand = 'Brand#12'
-     and p_container in ('SM CASE', 'SM BOX', 'SM PACK', 'SM PKG')
-     and l_quantity >= 1 and l_quantity <= 1 + 10
-     and p_size between 1 and 5
-     and l_shipmode in ('AIR', 'AIR REG')
-     and l_shipinstruct = 'DELIVER IN PERSON'
-     OR p_partkey = l_partkey
-     and p_brand = 'Brand#23'
-     and p_container in ('MED BAG', 'MED BOX', 'MED PKG', 'MED PACK')
-     and l_quantity >= 10 and l_quantity <= 10 + 10
-     and p_size between 1 and 10
-     and l_shipmode in ('AIR', 'AIR REG')
-     and l_shipinstruct = 'DELIVER IN PERSON'
-     OR p_partkey = l_partkey
-     and p_brand = 'Brand#34'
-     and p_container in ('LG CASE', 'LG BOX', 'LG PACK', 'LG PKG')
-     and l_quantity >= 20 and l_quantity <= 20 + 10
-     and p_size between 1 and 15
-     and l_shipmode in ('AIR', 'AIR REG')
-     and l_shipinstruct = 'DELIVER IN PERSON'
+| join ON
+     (
+         p_partkey = l_partkey
+         and p_brand = 'Brand#12'
+         and p_container in ('SM CASE', 'SM BOX', 'SM PACK', 'SM PKG')
+         and l_quantity >= 1 and l_quantity <= 1 + 10
+         and p_size between 1 and 5
+         and l_shipmode in ('AIR', 'AIR REG')
+         and l_shipinstruct = 'DELIVER IN PERSON'
+     ) OR (
+         p_partkey = l_partkey
+         and p_brand = 'Brand#23'
+         and p_container in ('MED BAG', 'MED BOX', 'MED PKG', 'MED PACK')
+         and l_quantity >= 10 and l_quantity <= 10 + 10
+         and p_size between 1 and 10
+         and l_shipmode in ('AIR', 'AIR REG')
+         and l_shipinstruct = 'DELIVER IN PERSON'
+     ) OR (
+         p_partkey = l_partkey
+         and p_brand = 'Brand#34'
+         and p_container in ('LG CASE', 'LG BOX', 'LG PACK', 'LG PKG')
+         and l_quantity >= 20 and l_quantity <= 20 + 10
+         and p_size between 1 and 15
+         and l_shipmode in ('AIR', 'AIR REG')
+         and l_shipinstruct = 'DELIVER IN PERSON'
+     )
   part

integ-test/src/integration/resources/tpch/q7.ppl

@@ -48,7 +48,7 @@ source = [
     | join ON s_nationkey = n1.n_nationkey nation as n1
     | join ON c_nationkey = n2.n_nationkey nation as n2
     | where l_shipdate between date('1995-01-01') and date('1996-12-31')
-        and n1.n_name = 'FRANCE' and n2.n_name = 'GERMANY' or n1.n_name = 'GERMANY' and n2.n_name = 'FRANCE'
+        and ((n1.n_name = 'FRANCE' and n2.n_name = 'GERMANY') or (n1.n_name = 'GERMANY' and n2.n_name = 'FRANCE'))
     | eval supp_nation = n1.n_name, cust_nation = n2.n_name, l_year = year(l_shipdate), volume = l_extendedprice * (1 - l_discount)
     | fields supp_nation, cust_nation, l_year, volume
   ] as shipping

integ-test/src/integration/scala/org/opensearch/flint/spark/ppl/FlintSparkPPLFiltersITSuite.scala

@@ -467,4 +467,96 @@ class FlintSparkPPLFiltersITSuite
     val expectedPlan = Project(Seq(UnresolvedAttribute("state")), filter)
     comparePlans(logicalPlan, expectedPlan, checkAnalysis = false)
   }
+
+  test("test parenthesis in filter") {
+    val frame = sql(s"""
+                       | source = $testTable | where country = 'Canada' or age > 60 and age < 25 | fields name, age, country
+                       | """.stripMargin)
+    assertSameRows(Seq(Row("John", 25, "Canada"), Row("Jane", 20, "Canada")), frame)
+
+    val frameWithParenthesis = sql(s"""
+                       | source = $testTable | where (country = 'Canada' or age > 60) and age < 25 | fields name, age, country
+                       | """.stripMargin)
+    assertSameRows(Seq(Row("Jane", 20, "Canada")), frameWithParenthesis)
+
+    val logicalPlan: LogicalPlan = frameWithParenthesis.queryExecution.logical
+    val table = UnresolvedRelation(Seq("spark_catalog", "default", "flint_ppl_test"))
+    val filter = Filter(
+      And(
+        Or(
+          EqualTo(UnresolvedAttribute("country"), Literal("Canada")),
+          GreaterThan(UnresolvedAttribute("age"), Literal(60))),
+        LessThan(UnresolvedAttribute("age"), Literal(25))),
+      table)
+    val expectedPlan = Project(
+      Seq(
+        UnresolvedAttribute("name"),
+        UnresolvedAttribute("age"),
+        UnresolvedAttribute("country")),
+      filter)
+    comparePlans(logicalPlan, expectedPlan, checkAnalysis = false)
+  }
+
+  test("test complex and nested parenthesis in filter") {
+    val frame1 = sql(s"""
+                        | source = $testTable | WHERE (age > 18 AND (state = 'California' OR state = 'New York'))
+                        | """.stripMargin)
+    assertSameRows(
+      Seq(
+        Row("Hello", 30, "New York", "USA", 2023, 4),
+        Row("Jake", 70, "California", "USA", 2023, 4)),
+      frame1)
+
+    val frame2 = sql(s"""
+                        | source = $testTable | WHERE ((((age > 18) AND ((((state = 'California') OR state = 'New York'))))))
+                        | """.stripMargin)
+    assertSameRows(
+      Seq(
+        Row("Hello", 30, "New York", "USA", 2023, 4),
+        Row("Jake", 70, "California", "USA", 2023, 4)),
+      frame2)
+
+    val frame3 = sql(s"""
+                        | source = $testTable | WHERE (year = 2023 AND (month BETWEEN 1 AND 6)) AND (age >= 31 OR country = 'Canada')
+                        | """.stripMargin)
+    assertSameRows(
+      Seq(
+        Row("John", 25, "Ontario", "Canada", 2023, 4),
+        Row("Jake", 70, "California", "USA", 2023, 4),
+        Row("Jane", 20, "Quebec", "Canada", 2023, 4)),
+      frame3)
+
+    val frame4 = sql(s"""
+                        | source = $testTable | WHERE ((state = 'Texas' OR state = 'California') AND (age < 30 OR (country = 'USA' AND year > 2020)))
+                        | """.stripMargin)
+    assertSameRows(Seq(Row("Jake", 70, "California", "USA", 2023, 4)), frame4)
+
+    val frame5 = sql(s"""
+                        | source = $testTable | WHERE (LIKE(LOWER(name), 'a%') OR LIKE(LOWER(name), 'j%')) AND (LENGTH(state) > 6 OR (country = 'USA' AND age > 18))
+                        | """.stripMargin)
+    assertSameRows(
+      Seq(
+        Row("John", 25, "Ontario", "Canada", 2023, 4),
+        Row("Jake", 70, "California", "USA", 2023, 4)),
+      frame5)
+
+    val frame6 = sql(s"""
+                        | source = $testTable | WHERE (age BETWEEN 25 AND 40) AND ((state IN ('California', 'New York', 'Texas') AND year = 2023) OR (country != 'USA' AND (month = 1 OR month = 12)))
+                        | """.stripMargin)
+    assertSameRows(Seq(Row("Hello", 30, "New York", "USA", 2023, 4)), frame6)
+
+    val frame7 = sql(s"""
+                        | source = $testTable | WHERE NOT (age < 18 OR (state = 'Alaska' AND year < 2020)) AND (country = 'USA' OR (country = 'Mexico' AND month BETWEEN 6 AND 8))
+                        | """.stripMargin)
+    assertSameRows(
+      Seq(
+        Row("Jake", 70, "California", "USA", 2023, 4),
+        Row("Hello", 30, "New York", "USA", 2023, 4)),
+      frame7)
+
+    val frame8 = sql(s"""
+                        | source = $testTable | WHERE (NOT (year < 2020 OR age < 18)) AND ((state = 'Texas' AND month % 2 = 0) OR (country = 'Mexico' AND (year = 2023 OR (year = 2022 AND month > 6))))
+                        | """.stripMargin)
+    assertSameRows(Seq(), frame8)
+  }
 }

ppl-spark-integration/src/main/antlr4/OpenSearchPPLParser.g4

@@ -424,6 +424,7 @@ expression
 
 logicalExpression
    : NOT logicalExpression                                      # logicalNot
+   | LT_PRTHS logicalExpression RT_PRTHS                        # parentheticLogicalExpr
    | comparisonExpression                                       # comparsion
    | left = logicalExpression (AND)? right = logicalExpression  # logicalAnd
    | left = logicalExpression OR right = logicalExpression      # logicalOr

ppl-spark-integration/src/main/java/org/opensearch/sql/ppl/parser/AstExpressionBuilder.java

@@ -157,6 +157,11 @@ public UnresolvedExpression visitBinaryArithmetic(OpenSearchPPLParser.BinaryArit
                 ctx.binaryOperator.getText(), Arrays.asList(visit(ctx.left), visit(ctx.right)));
     }
 
+    @Override
+    public UnresolvedExpression visitParentheticLogicalExpr(OpenSearchPPLParser.ParentheticLogicalExprContext ctx) {
+        return visit(ctx.logicalExpression()); // Discard parenthesis around
+    }
+
     @Override
     public UnresolvedExpression visitParentheticValueExpr(OpenSearchPPLParser.ParentheticValueExprContext ctx) {
         return visit(ctx.valueExpression()); // Discard parenthesis around