Add OPTIMIZE CLEANUP and INSERT (*) support

- Add Cleanup flag to OptimizeQuery for OPTIMIZE TABLE ... FINAL CLEANUP
- Update explain output to append _cleanup to table name when Cleanup=true
- Add AllColumns flag to InsertQuery for INSERT INTO table (*) syntax
- Update explain output for INSERT with (*) to show Asterisk child
- Update parser to handle both new syntaxes

Author: claude

ast/ast.go

@@ -225,6 +225,7 @@ type InsertQuery struct {
 	Table       string           `json:"table,omitempty"`
 	Function    *FunctionCall    `json:"function,omitempty"` // For INSERT INTO FUNCTION syntax
 	Columns     []*Identifier    `json:"columns,omitempty"`
+	AllColumns  bool             `json:"all_columns,omitempty"` // For (*) syntax meaning all columns
 	PartitionBy Expression       `json:"partition_by,omitempty"` // For PARTITION BY clause
 	Infile      string           `json:"infile,omitempty"`       // For FROM INFILE clause
 	Compression string           `json:"compression,omitempty"`  // For COMPRESSION clause
@@ -740,6 +741,7 @@ type OptimizeQuery struct {
 	Table     string         `json:"table"`
 	Partition Expression     `json:"partition,omitempty"`
 	Final     bool           `json:"final,omitempty"`
+	Cleanup   bool           `json:"cleanup,omitempty"`
 	Dedupe    bool           `json:"dedupe,omitempty"`
 	OnCluster string         `json:"on_cluster,omitempty"`
 }

internal/explain/statements.go

@@ -24,7 +24,7 @@ func explainInsertQuery(sb *strings.Builder, n *ast.InsertQuery, indent string,
 			children++ // Database identifier (separate from table)
 		}
 	}
-	if len(n.Columns) > 0 {
+	if len(n.Columns) > 0 || n.AllColumns {
 		children++ // Column list
 	}
 	if n.Select != nil {
@@ -58,7 +58,10 @@ func explainInsertQuery(sb *strings.Builder, n *ast.InsertQuery, indent string,
 	}
 
 	// Column list
-	if len(n.Columns) > 0 {
+	if n.AllColumns {
+		fmt.Fprintf(sb, "%s ExpressionList (children 1)\n", indent)
+		fmt.Fprintf(sb, "%s  Asterisk\n", indent)
+	} else if len(n.Columns) > 0 {
 		fmt.Fprintf(sb, "%s ExpressionList (children %d)\n", indent, len(n.Columns))
 		for _, col := range n.Columns {
 			fmt.Fprintf(sb, "%s  Identifier %s\n", indent, col.Parts[len(col.Parts)-1])
@@ -1282,6 +1285,9 @@ func explainOptimizeQuery(sb *strings.Builder, n *ast.OptimizeQuery, indent stri
 	if n.Final {
 		name += "_final"
 	}
+	if n.Cleanup {
+		name += "_cleanup"
+	}
 
 	children := 1 // identifier
 	if n.Partition != nil {

parser/parser.go

@@ -1179,19 +1179,25 @@ func (p *Parser) parseInsert() *ast.InsertQuery {
 	// Parse column list
 	if p.currentIs(token.LPAREN) {
 		p.nextToken()
-		for !p.currentIs(token.RPAREN) && !p.currentIs(token.EOF) {
-			pos := p.current.Pos
-			colName := p.parseIdentifierName()
-			if colName != "" {
-				ins.Columns = append(ins.Columns, &ast.Identifier{
-					Position: pos,
-					Parts:    []string{colName},
-				})
-			}
-			if p.currentIs(token.COMMA) {
-				p.nextToken()
-			} else {
-				break
+		// Check for (*) meaning all columns
+		if p.currentIs(token.ASTERISK) {
+			ins.AllColumns = true
+			p.nextToken()
+		} else {
+			for !p.currentIs(token.RPAREN) && !p.currentIs(token.EOF) {
+				pos := p.current.Pos
+				colName := p.parseIdentifierName()
+				if colName != "" {
+					ins.Columns = append(ins.Columns, &ast.Identifier{
+						Position: pos,
+						Parts:    []string{colName},
+					})
+				}
+				if p.currentIs(token.COMMA) {
+					p.nextToken()
+				} else {
+					break
+				}
 			}
 		}
 		p.expect(token.RPAREN)
@@ -4374,6 +4380,12 @@ func (p *Parser) parseOptimize() *ast.OptimizeQuery {
 		p.nextToken()
 	}
 
+	// Handle CLEANUP
+	if p.currentIs(token.IDENT) && strings.ToUpper(p.current.Value) == "CLEANUP" {
+		opt.Cleanup = true
+		p.nextToken()
+	}
+
 	// Handle DEDUPLICATE
 	if p.currentIs(token.IDENT) && strings.ToUpper(p.current.Value) == "DEDUPLICATE" {
 		opt.Dedupe = true

parser/testdata/00577_replacing_merge_tree_vertical_merge/metadata.json

@@ -1,10 +1,5 @@
 {
   "explain_todo": {
-    "stmt12": true,
-    "stmt13": true,
-    "stmt14": true,
-    "stmt15": true,
-    "stmt16": true,
-    "stmt7": true
+    "stmt15": true
   }
 }

parser/testdata/01115_prewhere_array_join/metadata.json

@@ -1,5 +1 @@
-{
-  "explain_todo": {
-    "stmt8": true
-  }
-}
+{}

parser/testdata/01943_query_id_check/metadata.json

@@ -1,5 +1 @@
-{
-  "explain_todo": {
-    "stmt12": true
-  }
-}
+{}

parser/testdata/02490_replacing_merge_tree_is_deleted_column/metadata.json

@@ -1,41 +1,6 @@
 {
   "explain_todo": {
-    "stmt103": true,
-    "stmt104": true,
-    "stmt108": true,
-    "stmt109": true,
-    "stmt11": true,
-    "stmt14": true,
-    "stmt18": true,
-    "stmt23": true,
-    "stmt26": true,
-    "stmt30": true,
-    "stmt31": true,
-    "stmt33": true,
-    "stmt35": true,
-    "stmt37": true,
-    "stmt4": true,
-    "stmt42": true,
-    "stmt49": true,
-    "stmt50": true,
-    "stmt55": true,
-    "stmt56": true,
-    "stmt57": true,
     "stmt58": true,
-    "stmt59": true,
-    "stmt64": true,
-    "stmt65": true,
-    "stmt7": true,
-    "stmt71": true,
-    "stmt75": true,
-    "stmt77": true,
-    "stmt81": true,
-    "stmt83": true,
-    "stmt88": true,
-    "stmt89": true,
-    "stmt93": true,
-    "stmt94": true,
-    "stmt98": true,
-    "stmt99": true
+    "stmt65": true
   }
 }

parser/testdata/02861_replacing_merge_tree_with_cleanup/metadata.json

@@ -1,9 +1 @@
-{
-  "explain_todo": {
-    "stmt10": true,
-    "stmt3": true,
-    "stmt4": true,
-    "stmt6": true,
-    "stmt8": true
-  }
-}
+{}