Add support for dialects (Redshift) that expect the TOP keyword in a SELECT statement to appear before the ALL/DISTINCT option

Author: yoavcloud

src/ast/query.rs

@@ -327,12 +327,20 @@ impl fmt::Display for Select {
             write!(f, " {value_table_mode}")?;
         }
 
+        if let Some(ref top) = self.top {
+            if top.is_before_distinct {
+                write!(f, " {top}")?;
+            }
+        }
         if let Some(ref distinct) = self.distinct {
             write!(f, " {distinct}")?;
         }
         if let Some(ref top) = self.top {
-            write!(f, " {top}")?;
+            if !top.is_before_distinct {
+                write!(f, " {top}")?;
+            }
         }
+
         write!(f, " {}", display_comma_separated(&self.projection))?;
 
         if let Some(ref into) = self.into {
@@ -1996,6 +2004,9 @@ pub struct Top {
     /// MSSQL only.
     pub percent: bool,
     pub quantity: Option<TopQuantity>,
+    // Whether this option was parsed before `ALL`/`DISTINCT`
+    // See `Dialect::expects_top_before_distinct`
+    pub is_before_distinct: bool,
 }
 
 #[derive(Debug, Clone, PartialEq, PartialOrd, Eq, Ord, Hash)]

src/dialect/mod.rs

@@ -590,6 +590,12 @@ pub trait Dialect: Debug + Any {
     fn supports_try_convert(&self) -> bool {
         false
     }
+
+    /// Returns true if this dialect expects the the `TOP` option
+    /// before the `ALL`/`DISTINCT` options
+    fn expects_top_before_distinct(&self) -> bool {
+        false
+    }
 }
 
 /// This represents the operators for which precedence must be defined

src/dialect/redshift.rs

@@ -68,4 +68,10 @@ impl Dialect for RedshiftSqlDialect {
     fn supports_connect_by(&self) -> bool {
         true
     }
+
+    /// Redshift expects the `TOP` option before the `ALL/DISTINCT` option:
+    /// <https://docs.aws.amazon.com/redshift/latest/dg/r_SELECT_list.html#r_SELECT_list-parameters>
+    fn expects_top_before_distinct(&self) -> bool {
+        true
+    }
 }

src/keywords.rs

@@ -254,6 +254,7 @@ define_keywords!(
     DISCARD,
     DISCONNECT,
     DISTINCT,
+    DISTINCTROW,
     DISTRIBUTE,
     DIV,
     DO,

src/parser/mod.rs

@@ -3534,7 +3534,9 @@ impl<'a> Parser<'a> {
     pub fn parse_all_or_distinct(&mut self) -> Result<Option<Distinct>, ParserError> {
         let loc = self.peek_token().location;
         let all = self.parse_keyword(Keyword::ALL);
-        let distinct = self.parse_keyword(Keyword::DISTINCT);
+        let distinct = self
+            .parse_one_of_keywords(&[Keyword::DISTINCT, Keyword::DISTINCTROW])
+            .is_some();
         if !distinct {
             return Ok(None);
         }
@@ -9174,12 +9176,14 @@ impl<'a> Parser<'a> {
                 None
             };
 
-        let distinct = self.parse_all_or_distinct()?;
-
-        let top = if self.parse_keyword(Keyword::TOP) {
-            Some(self.parse_top()?)
+        let (distinct, top) = if self.dialect.expects_top_before_distinct() {
+            let top = self.maybe_parse_top(true)?;
+            let distinct = self.parse_all_or_distinct()?;
+            (distinct, top)
         } else {
-            None
+            let distinct = self.parse_all_or_distinct()?;
+            let top = self.maybe_parse_top(false)?;
+            (distinct, top)
         };
 
         let projection = self.parse_projection()?;
@@ -11491,7 +11495,14 @@ impl<'a> Parser<'a> {
 
     /// Parse a TOP clause, MSSQL equivalent of LIMIT,
     /// that follows after `SELECT [DISTINCT]`.
-    pub fn parse_top(&mut self) -> Result<Top, ParserError> {
+    pub fn maybe_parse_top(
+        &mut self,
+        is_before_distinct: bool,
+    ) -> Result<Option<Top>, ParserError> {
+        if !self.parse_keyword(Keyword::TOP) {
+            return Ok(None);
+        }
+
         let quantity = if self.consume_token(&Token::LParen) {
             let quantity = self.parse_expr()?;
             self.expect_token(&Token::RParen)?;
@@ -11509,11 +11520,12 @@ impl<'a> Parser<'a> {
 
         let with_ties = self.parse_keywords(&[Keyword::WITH, Keyword::TIES]);
 
-        Ok(Top {
+        Ok(Some(Top {
             with_ties,
             percent,
             quantity,
-        })
+            is_before_distinct,
+        }))
     }
 
     /// Parse a LIMIT clause

tests/sqlparser_mysql.rs

@@ -2796,3 +2796,11 @@ fn test_group_concat() {
     mysql_and_generic()
         .verified_expr("GROUP_CONCAT(DISTINCT test_score ORDER BY test_score DESC SEPARATOR ' ')");
 }
+
+#[test]
+fn parse_select_distinctrow() {
+    mysql().one_statement_parses_to(
+        "SELECT DISTINCTROW a FROM tbl", 
+        "SELECT DISTINCT a FROM tbl"
+    );
+}

tests/sqlparser_redshift.rs

@@ -196,3 +196,12 @@ fn test_create_view_with_no_schema_binding() {
     redshift_and_generic()
         .verified_stmt("CREATE VIEW myevent AS SELECT eventname FROM event WITH NO SCHEMA BINDING");
 }
+
+#[test]
+fn test_select_top() {
+    redshift().one_statement_parses_to("SELECT ALL * FROM tbl", "SELECT * FROM tbl");
+    redshift().verified_stmt("SELECT TOP 3 * FROM tbl");
+    redshift().one_statement_parses_to("SELECT TOP 3 ALL * FROM tbl", "SELECT TOP 3 * FROM tbl");
+    redshift().verified_stmt("SELECT TOP 3 DISTINCT * FROM tbl");
+    redshift().verified_stmt("SELECT TOP 3 DISTINCT a, b, c FROM tbl");
+}