sqlparser: Improve interval parsing (#13165)

* sqlparser: Improve interval parsing

Parse only strict valid units for intervals. We should not allow any
arbitrary string value here. We already had the internal enumerable
available, but we were not using yet.

Signed-off-by: Dirkjan Bussink <d.bussink@gmail.com>

* sqlparser: Explicit parsing for date functions with intervals

In order to better be able to implement these in the evalengine, it's
easier to parse them explicitly in the parser. This ensures we have the
interval type etc. directly available instead of having to infer it
from a separate expression.

Also makes parsing these functions more strict and better match MySQL.

Signed-off-by: Dirkjan Bussink <d.bussink@gmail.com>

* sqlparser: Remove INTERVAL as general expression

INTERVAL is not a possible general expression, but only used in specific
cases. With the previous change, we already have it all handled for date
functions. The only remaining cases are for + and - where this is
handled.

Those cases are a bit special. You can have an interval on both sides of
a +, but for a - it can only be done on the right hand side.

Signed-off-by: Dirkjan Bussink <d.bussink@gmail.com>

---------

Signed-off-by: Dirkjan Bussink <d.bussink@gmail.com>

go/test/endtoend/vtgate/queries/misc/misc_test.go

@@ -174,8 +174,8 @@ func TestIntervalWithMathFunctions(t *testing.T) {
 	// Set the time zone explicitly to UTC, otherwise the output of FROM_UNIXTIME is going to be dependent
 	// on the time zone of the system.
 	mcmp.Exec("SET time_zone = '+00:00'")
-	mcmp.AssertMatches("select '2020-01-01' + interval month(DATE_SUB(FROM_UNIXTIME(1234), interval 1 month))-1 month", `[[CHAR("2020-12-01")]]`)
-	mcmp.AssertMatches("select DATE_ADD(MIN(FROM_UNIXTIME(1673444922)),interval -DAYOFWEEK(MIN(FROM_UNIXTIME(1673444922)))+1 DAY)", `[[DATETIME("2023-01-08 13:48:42")]]`)
+	mcmp.AssertMatches("select '2020-01-01' + interval month(date_sub(FROM_UNIXTIME(1234), interval 1 month))-1 month", `[[CHAR("2020-12-01")]]`)
+	mcmp.AssertMatches("select date_add(MIN(FROM_UNIXTIME(1673444922)),interval -DAYOFWEEK(MIN(FROM_UNIXTIME(1673444922)))+1 DAY)", `[[DATETIME("2023-01-08 13:48:42")]]`)
 }
 
 // TestCast tests the queries that contain the cast function.

go/vt/sqlparser/ast.go

@@ -2154,6 +2154,7 @@ type (
 	// More information available here: https://dev.mysql.com/doc/refman/8.0/en/window-functions-frames.html
 	FramePoint struct {
 		Type FramePointType
+		Unit IntervalTypes
 		Expr Expr
 	}
 
@@ -2194,6 +2195,16 @@ type (
 	FromFirstLastType int8
 )
 
+// DateAddExprType is an enum to get types of DateAddExpr.
+// This can be one of ADDDATE, DATE_ADD or a '+' operator
+// with an interval left or right.
+type DateAddExprType int8
+
+// DateSubExprType is an enum to get types of DateAddExpr.
+// This can be one of SUBDATE, DATE_SUB or a '-' operator
+// with an interval right.
+type DateSubExprType int8
+
 // *********** Expressions
 type (
 	// Expr represents an expression.
@@ -2340,12 +2351,6 @@ type (
 		Expr         Expr
 	}
 
-	// IntervalExpr represents a date-time INTERVAL expression.
-	IntervalExpr struct {
-		Expr Expr
-		Unit string
-	}
-
 	// TimestampFuncExpr represents the function and arguments for TIMESTAMP{ADD,DIFF} functions.
 	TimestampFuncExpr struct {
 		Name  string
@@ -2966,7 +2971,7 @@ type (
 	}
 
 	// RegexpInstrExpr represents REGEXP_INSTR()
-	// For more information, postVisit https://dev.mysql.com/doc/refman/8.0/en/regexp.html#function_regexp-instr
+	// For more information, see https://dev.mysql.com/doc/refman/8.0/en/regexp.html#function_regexp-instr
 	RegexpInstrExpr struct {
 		Expr         Expr
 		Pattern      Expr
@@ -2977,15 +2982,15 @@ type (
 	}
 
 	// RegexpLikeExpr represents REGEXP_LIKE()
-	// For more information, postVisit https://dev.mysql.com/doc/refman/8.0/en/regexp.html#function_regexp-like
+	// For more information, see https://dev.mysql.com/doc/refman/8.0/en/regexp.html#function_regexp-like
 	RegexpLikeExpr struct {
 		Expr      Expr
 		Pattern   Expr
 		MatchType Expr
 	}
 
 	// RegexpReplaceExpr represents REGEXP_REPLACE()
-	// For more information, postVisit https://dev.mysql.com/doc/refman/8.0/en/regexp.html#function_regexp-replace
+	// For more information, see https://dev.mysql.com/doc/refman/8.0/en/regexp.html#function_regexp-replace
 	RegexpReplaceExpr struct {
 		Expr       Expr
 		Pattern    Expr
@@ -2996,7 +3001,7 @@ type (
 	}
 
 	// RegexpSubstrExpr represents REGEXP_SUBSTR()
-	// For more information, postVisit https://dev.mysql.com/doc/refman/8.0/en/regexp.html#function_regexp-substr
+	// For more information, see https://dev.mysql.com/doc/refman/8.0/en/regexp.html#function_regexp-substr
 	RegexpSubstrExpr struct {
 		Expr       Expr
 		Pattern    Expr
@@ -3005,6 +3010,26 @@ type (
 		MatchType  Expr
 	}
 
+	// DateAddExpr represents ADDDATE(), DATE_ADD()
+	// and additions with an interval on the left and right.
+	// For more information, see https://dev.mysql.com/doc/refman/8.0/en/date-and-time-functions.html#function_date-add
+	DateAddExpr struct {
+		Type DateAddExprType
+		Date Expr
+		Unit IntervalTypes
+		Expr Expr
+	}
+
+	// DateSubExpr represents SUBDATE(), DATE_SUB()
+	// and subtractions with an interval on the right.
+	// For more information, see https://dev.mysql.com/doc/refman/8.0/en/date-and-time-functions.html#function_date-sub
+	DateSubExpr struct {
+		Type DateSubExprType
+		Date Expr
+		Unit IntervalTypes
+		Expr Expr
+	}
+
 	// ArgumentLessWindowExpr stands for the following window_functions: CUME_DIST, DENSE_RANK, PERCENT_RANK, RANK, ROW_NUMBER
 	// These functions do not take any argument.
 	ArgumentLessWindowExpr struct {
@@ -3131,7 +3156,6 @@ func (ListArg) iExpr()                             {}
 func (*BinaryExpr) iExpr()                         {}
 func (*UnaryExpr) iExpr()                          {}
 func (*IntroducerExpr) iExpr()                     {}
-func (*IntervalExpr) iExpr()                       {}
 func (*CollateExpr) iExpr()                        {}
 func (*FuncExpr) iExpr()                           {}
 func (*TimestampFuncExpr) iExpr()                  {}
@@ -3178,6 +3202,8 @@ func (*RegexpInstrExpr) iExpr()                    {}
 func (*RegexpLikeExpr) iExpr()                     {}
 func (*RegexpReplaceExpr) iExpr()                  {}
 func (*RegexpSubstrExpr) iExpr()                   {}
+func (*DateAddExpr) iExpr()                        {}
+func (*DateSubExpr) iExpr()                        {}
 func (*ArgumentLessWindowExpr) iExpr()             {}
 func (*FirstOrLastValueExpr) iExpr()               {}
 func (*NtileExpr) iExpr()                          {}
@@ -3269,6 +3295,8 @@ func (*RegexpInstrExpr) iCallable()                    {}
 func (*RegexpLikeExpr) iCallable()                     {}
 func (*RegexpReplaceExpr) iCallable()                  {}
 func (*RegexpSubstrExpr) iCallable()                   {}
+func (*DateAddExpr) iCallable()                        {}
+func (*DateSubExpr) iCallable()                        {}
 func (*ArgumentLessWindowExpr) iCallable()             {}
 func (*FirstOrLastValueExpr) iCallable()               {}
 func (*NtileExpr) iCallable()                          {}