Support for (+) outer join syntax (apache#1145)

Author: jmhain

src/ast/mod.rs

@@ -713,6 +713,21 @@ pub enum Expr {
     /// Qualified wildcard, e.g. `alias.*` or `schema.table.*`.
     /// (Same caveats apply to `QualifiedWildcard` as to `Wildcard`.)
     QualifiedWildcard(ObjectName),
+    /// Some dialects support an older syntax for outer joins where columns are
+    /// marked with the `(+)` operator in the WHERE clause, for example:
+    ///
+    /// ```sql
+    /// SELECT t1.c1, t2.c2 FROM t1, t2 WHERE t1.c1 = t2.c2 (+)
+    /// ```
+    ///
+    /// which is equivalent to
+    ///
+    /// ```sql
+    /// SELECT t1.c1, t2.c2 FROM t1 LEFT OUTER JOIN t2 ON t1.c1 = t2.c2
+    /// ```
+    ///
+    /// See <https://docs.snowflake.com/en/sql-reference/constructs/where#joins-in-the-where-clause>.
+    OuterJoin(Box<Expr>),
 }
 
 impl fmt::Display for CastFormat {
@@ -1174,6 +1189,9 @@ impl fmt::Display for Expr {
 
                 Ok(())
             }
+            Expr::OuterJoin(expr) => {
+                write!(f, "{expr} (+)")
+            }
         }
     }
 }

src/parser/mod.rs

@@ -998,8 +998,19 @@ impl<'a> Parser<'a> {
                         if ends_with_wildcard {
                             Ok(Expr::QualifiedWildcard(ObjectName(id_parts)))
                         } else if self.consume_token(&Token::LParen) {
-                            self.prev_token();
-                            self.parse_function(ObjectName(id_parts))
+                            if dialect_of!(self is SnowflakeDialect | MsSqlDialect)
+                                && self.consume_tokens(&[Token::Plus, Token::RParen])
+                            {
+                                Ok(Expr::OuterJoin(Box::new(
+                                    match <[Ident; 1]>::try_from(id_parts) {
+                                        Ok([ident]) => Expr::Identifier(ident),
+                                        Err(parts) => Expr::CompoundIdentifier(parts),
+                                    },
+                                )))
+                            } else {
+                                self.prev_token();
+                                self.parse_function(ObjectName(id_parts))
+                            }
                         } else {
                             Ok(Expr::CompoundIdentifier(id_parts))
                         }
@@ -2860,6 +2871,21 @@ impl<'a> Parser<'a> {
         }
     }
 
+    /// If the current and subsequent tokens exactly match the `tokens`
+    /// sequence, consume them and returns true. Otherwise, no tokens are
+    /// consumed and returns false
+    #[must_use]
+    pub fn consume_tokens(&mut self, tokens: &[Token]) -> bool {
+        let index = self.index;
+        for token in tokens {
+            if !self.consume_token(token) {
+                self.index = index;
+                return false;
+            }
+        }
+        true
+    }
+
     /// Bail out if the current token is not an expected keyword, or consume it if it is
     pub fn expect_token(&mut self, expected: &Token) -> Result<(), ParserError> {
         if self.consume_token(expected) {

tests/sqlparser_snowflake.rs

@@ -1173,3 +1173,68 @@ fn parse_top() {
         "SELECT TOP 4 c1 FROM testtable",
     );
 }
+
+#[test]
+fn parse_comma_outer_join() {
+    // compound identifiers
+    let case1 =
+        snowflake().verified_only_select("SELECT t1.c1, t2.c2 FROM t1, t2 WHERE t1.c1 = t2.c2 (+)");
+    assert_eq!(
+        case1.selection,
+        Some(Expr::BinaryOp {
+            left: Box::new(Expr::CompoundIdentifier(vec![
+                Ident::new("t1"),
+                Ident::new("c1")
+            ])),
+            op: BinaryOperator::Eq,
+            right: Box::new(Expr::OuterJoin(Box::new(Expr::CompoundIdentifier(vec![
+                Ident::new("t2"),
+                Ident::new("c2")
+            ]))))
+        })
+    );
+
+    // regular identifiers
+    let case2 =
+        snowflake().verified_only_select("SELECT t1.c1, t2.c2 FROM t1, t2 WHERE c1 = c2 (+)");
+    assert_eq!(
+        case2.selection,
+        Some(Expr::BinaryOp {
+            left: Box::new(Expr::Identifier(Ident::new("c1"))),
+            op: BinaryOperator::Eq,
+            right: Box::new(Expr::OuterJoin(Box::new(Expr::Identifier(Ident::new(
+                "c2"
+            )))))
+        })
+    );
+
+    // ensure we can still parse function calls with a unary plus arg
+    let case3 =
+        snowflake().verified_only_select("SELECT t1.c1, t2.c2 FROM t1, t2 WHERE c1 = myudf(+42)");
+    assert_eq!(
+        case3.selection,
+        Some(Expr::BinaryOp {
+            left: Box::new(Expr::Identifier(Ident::new("c1"))),
+            op: BinaryOperator::Eq,
+            right: Box::new(Expr::Function(Function {
+                name: ObjectName(vec![Ident::new("myudf")]),
+                args: vec![FunctionArg::Unnamed(FunctionArgExpr::Expr(Expr::UnaryOp {
+                    op: UnaryOperator::Plus,
+                    expr: Box::new(Expr::Value(number("42")))
+                }))],
+                filter: None,
+                null_treatment: None,
+                over: None,
+                distinct: false,
+                special: false,
+                order_by: vec![]
+            }))
+        })
+    );
+
+    // permissive with whitespace
+    snowflake().verified_only_select_with_canonical(
+        "SELECT t1.c1, t2.c2 FROM t1, t2 WHERE t1.c1 = t2.c2(   +     )",
+        "SELECT t1.c1, t2.c2 FROM t1, t2 WHERE t1.c1 = t2.c2 (+)",
+    );
+}