[fix](nereids)OrToIn and SimplifyRange rules dead loop (apache#41689)

intro by apache#41222

[bug]
OrToIn Rule set state flag in Or expression to avoid repeatedly process
the same expression. But SimplifyRange Rule may remove this flag, and
hence OrToIn and SimplifyRange Rules go into dead loop.

[fix]
if the input expression and output expression of SimplifyRange Rule are
the same, SimplifyRange will return input expression to keep expression
state.

fe/fe-core/src/main/java/org/apache/doris/nereids/rules/expression/ExpressionOptimization.java

@@ -48,7 +48,6 @@ public class ExpressionOptimization extends ExpressionRewrite {
                     SimplifyDecimalV3Comparison.INSTANCE,
                     SimplifyRange.INSTANCE,
                     OrToIn.INSTANCE,
-                    SimplifyRange.INSTANCE,
                     DateFunctionRewrite.INSTANCE,
                     ArrayContainToArrayOverlap.INSTANCE,
                     CaseWhenToIf.INSTANCE,

fe/fe-core/src/main/java/org/apache/doris/nereids/rules/expression/rules/SimplifyRange.java

@@ -494,6 +494,9 @@ public Expression toExpression() {
             for (int i = 1; i < sourceValues.size(); i++) {
                 result = mergeExprOp.apply(result, sourceValues.get(i).toExpression());
             }
+            if (result.equals(expr)) {
+                return expr;
+            }
             return result;
         }
     }

fe/fe-core/src/test/java/org/apache/doris/nereids/rules/rewrite/OrToInTest.java

@@ -205,4 +205,12 @@ void test16() {
         Assertions.assertEquals("(a = 1)",
                 rewritten.toSql());
     }
+
+    @Test
+    void test17() {
+        String expr = "(a=1 and b=2) or (a in (2, 3) and ((a=2 and c=3) or (a=3 and d=4)))";
+        Expression expression = PARSER.parseExpression(expr);
+        Expression rewritten = OrToIn.INSTANCE.rewriteTree(expression, context);
+        System.out.println(rewritten);
+    }
 }

regression-test/data/nereids_hint_tpcds_p0/shape/query13.out

@@ -7,7 +7,7 @@ PhysicalResultSink
 --------PhysicalProject
 ----------hashJoin[INNER_JOIN broadcast] hashCondition=((store.s_store_sk = store_sales.ss_store_sk)) otherCondition=() build RFs:RF4 s_store_sk->[ss_store_sk]
 ------------PhysicalProject
---------------hashJoin[INNER_JOIN shuffle] hashCondition=((customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk)) otherCondition=((((((household_demographics.hd_dep_count = 1) AND cd_marital_status IN ('D', 'W')) AND cd_education_status IN ('2 yr Degree', 'Primary')) AND ((cd_marital_status IN ('D', 'W') AND cd_education_status IN ('2 yr Degree', 'Primary')) AND ((((customer_demographics.cd_marital_status = 'D') AND (customer_demographics.cd_education_status = 'Primary')) AND ((store_sales.ss_sales_price >= 50.00) AND (store_sales.ss_sales_price <= 100.00))) OR (((customer_demographics.cd_marital_status = 'W') AND (customer_demographics.cd_education_status = '2 yr Degree')) AND ((store_sales.ss_sales_price >= 150.00) AND (store_sales.ss_sales_price <= 200.00)))))) OR ((((customer_demographics.cd_marital_status = 'M') AND (customer_demographics.cd_education_status = 'College')) AND ((store_sales.ss_sales_price >= 100.00) AND (store_sales.ss_sales_price <= 150.00))) AND (household_demographics.hd_dep_count = 3)))) build RFs:RF3 ss_cdemo_sk->[cd_demo_sk]
+--------------hashJoin[INNER_JOIN shuffle] hashCondition=((customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk)) otherCondition=((((((household_demographics.hd_dep_count = 1) AND cd_marital_status IN ('D', 'W')) AND cd_education_status IN ('2 yr Degree', 'Primary')) AND ((((customer_demographics.cd_marital_status = 'D') AND (customer_demographics.cd_education_status = 'Primary')) AND ((store_sales.ss_sales_price >= 50.00) AND (store_sales.ss_sales_price <= 100.00))) OR (((customer_demographics.cd_marital_status = 'W') AND (customer_demographics.cd_education_status = '2 yr Degree')) AND ((store_sales.ss_sales_price >= 150.00) AND (store_sales.ss_sales_price <= 200.00))))) OR ((((customer_demographics.cd_marital_status = 'M') AND (customer_demographics.cd_education_status = 'College')) AND ((store_sales.ss_sales_price >= 100.00) AND (store_sales.ss_sales_price <= 150.00))) AND (household_demographics.hd_dep_count = 3)))) build RFs:RF3 ss_cdemo_sk->[cd_demo_sk]
 ----------------PhysicalProject
 ------------------filter(((((customer_demographics.cd_marital_status = 'M') AND (customer_demographics.cd_education_status = 'College')) OR ((customer_demographics.cd_marital_status = 'D') AND (customer_demographics.cd_education_status = 'Primary'))) OR ((customer_demographics.cd_marital_status = 'W') AND (customer_demographics.cd_education_status = '2 yr Degree'))) and cd_education_status IN ('2 yr Degree', 'College', 'Primary') and cd_marital_status IN ('D', 'M', 'W'))
 --------------------PhysicalOlapScan[customer_demographics] apply RFs: RF3

regression-test/data/nereids_tpcds_shape_sf1000_p0/bs_downgrade_shape/query13.out

@@ -14,7 +14,7 @@ PhysicalResultSink
 ----------------PhysicalProject
 ------------------hashJoin[INNER_JOIN broadcast] hashCondition=((store_sales.ss_sold_date_sk = date_dim.d_date_sk)) otherCondition=() build RFs:RF2 d_date_sk->[ss_sold_date_sk]
 --------------------PhysicalProject
-----------------------hashJoin[INNER_JOIN broadcast] hashCondition=((store_sales.ss_hdemo_sk = household_demographics.hd_demo_sk)) otherCondition=((((((household_demographics.hd_dep_count = 1) AND cd_marital_status IN ('D', 'W')) AND cd_education_status IN ('2 yr Degree', 'Primary')) AND ((cd_marital_status IN ('D', 'W') AND cd_education_status IN ('2 yr Degree', 'Primary')) AND ((((customer_demographics.cd_marital_status = 'D') AND (customer_demographics.cd_education_status = 'Primary')) AND ((store_sales.ss_sales_price >= 50.00) AND (store_sales.ss_sales_price <= 100.00))) OR (((customer_demographics.cd_marital_status = 'W') AND (customer_demographics.cd_education_status = '2 yr Degree')) AND ((store_sales.ss_sales_price >= 150.00) AND (store_sales.ss_sales_price <= 200.00)))))) OR ((((customer_demographics.cd_marital_status = 'M') AND (customer_demographics.cd_education_status = 'College')) AND ((store_sales.ss_sales_price >= 100.00) AND (store_sales.ss_sales_price <= 150.00))) AND (household_demographics.hd_dep_count = 3)))) build RFs:RF1 hd_demo_sk->[ss_hdemo_sk]
+----------------------hashJoin[INNER_JOIN broadcast] hashCondition=((store_sales.ss_hdemo_sk = household_demographics.hd_demo_sk)) otherCondition=((((((household_demographics.hd_dep_count = 1) AND cd_marital_status IN ('D', 'W')) AND cd_education_status IN ('2 yr Degree', 'Primary')) AND ((((customer_demographics.cd_marital_status = 'D') AND (customer_demographics.cd_education_status = 'Primary')) AND ((store_sales.ss_sales_price >= 50.00) AND (store_sales.ss_sales_price <= 100.00))) OR (((customer_demographics.cd_marital_status = 'W') AND (customer_demographics.cd_education_status = '2 yr Degree')) AND ((store_sales.ss_sales_price >= 150.00) AND (store_sales.ss_sales_price <= 200.00))))) OR ((((customer_demographics.cd_marital_status = 'M') AND (customer_demographics.cd_education_status = 'College')) AND ((store_sales.ss_sales_price >= 100.00) AND (store_sales.ss_sales_price <= 150.00))) AND (household_demographics.hd_dep_count = 3)))) build RFs:RF1 hd_demo_sk->[ss_hdemo_sk]
 ------------------------PhysicalProject
 --------------------------hashJoin[INNER_JOIN broadcast] hashCondition=((customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk)) otherCondition=() build RFs:RF0 cd_demo_sk->[ss_cdemo_sk]
 ----------------------------PhysicalProject

regression-test/data/nereids_tpcds_shape_sf1000_p0/shape/query13.out

@@ -14,7 +14,7 @@ PhysicalResultSink
 ----------------PhysicalProject
 ------------------hashJoin[INNER_JOIN broadcast] hashCondition=((store_sales.ss_sold_date_sk = date_dim.d_date_sk)) otherCondition=() build RFs:RF2 d_date_sk->[ss_sold_date_sk]
 --------------------PhysicalProject
-----------------------hashJoin[INNER_JOIN broadcast] hashCondition=((store_sales.ss_hdemo_sk = household_demographics.hd_demo_sk)) otherCondition=((((((household_demographics.hd_dep_count = 1) AND cd_marital_status IN ('D', 'W')) AND cd_education_status IN ('2 yr Degree', 'Primary')) AND ((cd_marital_status IN ('D', 'W') AND cd_education_status IN ('2 yr Degree', 'Primary')) AND ((((customer_demographics.cd_marital_status = 'D') AND (customer_demographics.cd_education_status = 'Primary')) AND ((store_sales.ss_sales_price >= 50.00) AND (store_sales.ss_sales_price <= 100.00))) OR (((customer_demographics.cd_marital_status = 'W') AND (customer_demographics.cd_education_status = '2 yr Degree')) AND ((store_sales.ss_sales_price >= 150.00) AND (store_sales.ss_sales_price <= 200.00)))))) OR ((((customer_demographics.cd_marital_status = 'M') AND (customer_demographics.cd_education_status = 'College')) AND ((store_sales.ss_sales_price >= 100.00) AND (store_sales.ss_sales_price <= 150.00))) AND (household_demographics.hd_dep_count = 3)))) build RFs:RF1 hd_demo_sk->[ss_hdemo_sk]
+----------------------hashJoin[INNER_JOIN broadcast] hashCondition=((store_sales.ss_hdemo_sk = household_demographics.hd_demo_sk)) otherCondition=((((((household_demographics.hd_dep_count = 1) AND cd_marital_status IN ('D', 'W')) AND cd_education_status IN ('2 yr Degree', 'Primary')) AND ((((customer_demographics.cd_marital_status = 'D') AND (customer_demographics.cd_education_status = 'Primary')) AND ((store_sales.ss_sales_price >= 50.00) AND (store_sales.ss_sales_price <= 100.00))) OR (((customer_demographics.cd_marital_status = 'W') AND (customer_demographics.cd_education_status = '2 yr Degree')) AND ((store_sales.ss_sales_price >= 150.00) AND (store_sales.ss_sales_price <= 200.00))))) OR ((((customer_demographics.cd_marital_status = 'M') AND (customer_demographics.cd_education_status = 'College')) AND ((store_sales.ss_sales_price >= 100.00) AND (store_sales.ss_sales_price <= 150.00))) AND (household_demographics.hd_dep_count = 3)))) build RFs:RF1 hd_demo_sk->[ss_hdemo_sk]
 ------------------------PhysicalProject
 --------------------------hashJoin[INNER_JOIN broadcast] hashCondition=((customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk)) otherCondition=() build RFs:RF0 cd_demo_sk->[ss_cdemo_sk]
 ----------------------------PhysicalProject

regression-test/data/nereids_tpcds_shape_sf100_p0/noStatsRfPrune/query13.out

@@ -9,7 +9,7 @@ PhysicalResultSink
 ------------PhysicalProject
 --------------hashJoin[INNER_JOIN broadcast] hashCondition=((store_sales.ss_addr_sk = customer_address.ca_address_sk)) otherCondition=((((ca_state IN ('KS', 'MI', 'SD') AND ((store_sales.ss_net_profit >= 100.00) AND (store_sales.ss_net_profit <= 200.00))) OR (ca_state IN ('CO', 'MO', 'ND') AND ((store_sales.ss_net_profit >= 150.00) AND (store_sales.ss_net_profit <= 300.00)))) OR (ca_state IN ('NH', 'OH', 'TX') AND ((store_sales.ss_net_profit >= 50.00) AND (store_sales.ss_net_profit <= 250.00))))) build RFs:RF3 ca_address_sk->[ss_addr_sk]
 ----------------PhysicalProject
-------------------hashJoin[INNER_JOIN broadcast] hashCondition=((store_sales.ss_hdemo_sk = household_demographics.hd_demo_sk)) otherCondition=((((((household_demographics.hd_dep_count = 1) AND cd_marital_status IN ('M', 'S')) AND cd_education_status IN ('4 yr Degree', 'College')) AND ((cd_marital_status IN ('M', 'S') AND cd_education_status IN ('4 yr Degree', 'College')) AND ((((customer_demographics.cd_marital_status = 'S') AND (customer_demographics.cd_education_status = 'College')) AND ((store_sales.ss_sales_price >= 50.00) AND (store_sales.ss_sales_price <= 100.00))) OR (((customer_demographics.cd_marital_status = 'M') AND (customer_demographics.cd_education_status = '4 yr Degree')) AND ((store_sales.ss_sales_price >= 150.00) AND (store_sales.ss_sales_price <= 200.00)))))) OR ((((customer_demographics.cd_marital_status = 'D') AND (customer_demographics.cd_education_status = 'Unknown')) AND ((store_sales.ss_sales_price >= 100.00) AND (store_sales.ss_sales_price <= 150.00))) AND (household_demographics.hd_dep_count = 3)))) build RFs:RF2 hd_demo_sk->[ss_hdemo_sk]
+------------------hashJoin[INNER_JOIN broadcast] hashCondition=((store_sales.ss_hdemo_sk = household_demographics.hd_demo_sk)) otherCondition=((((((household_demographics.hd_dep_count = 1) AND cd_marital_status IN ('M', 'S')) AND cd_education_status IN ('4 yr Degree', 'College')) AND ((((customer_demographics.cd_marital_status = 'S') AND (customer_demographics.cd_education_status = 'College')) AND ((store_sales.ss_sales_price >= 50.00) AND (store_sales.ss_sales_price <= 100.00))) OR (((customer_demographics.cd_marital_status = 'M') AND (customer_demographics.cd_education_status = '4 yr Degree')) AND ((store_sales.ss_sales_price >= 150.00) AND (store_sales.ss_sales_price <= 200.00))))) OR ((((customer_demographics.cd_marital_status = 'D') AND (customer_demographics.cd_education_status = 'Unknown')) AND ((store_sales.ss_sales_price >= 100.00) AND (store_sales.ss_sales_price <= 150.00))) AND (household_demographics.hd_dep_count = 3)))) build RFs:RF2 hd_demo_sk->[ss_hdemo_sk]
 --------------------PhysicalProject
 ----------------------hashJoin[INNER_JOIN broadcast] hashCondition=((customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk)) otherCondition=() build RFs:RF1 cd_demo_sk->[ss_cdemo_sk]
 ------------------------PhysicalProject

regression-test/data/nereids_tpcds_shape_sf100_p0/no_stats_shape/query13.out

@@ -9,7 +9,7 @@ PhysicalResultSink
 ------------PhysicalProject
 --------------hashJoin[INNER_JOIN broadcast] hashCondition=((store_sales.ss_addr_sk = customer_address.ca_address_sk)) otherCondition=((((ca_state IN ('KS', 'MI', 'SD') AND ((store_sales.ss_net_profit >= 100.00) AND (store_sales.ss_net_profit <= 200.00))) OR (ca_state IN ('CO', 'MO', 'ND') AND ((store_sales.ss_net_profit >= 150.00) AND (store_sales.ss_net_profit <= 300.00)))) OR (ca_state IN ('NH', 'OH', 'TX') AND ((store_sales.ss_net_profit >= 50.00) AND (store_sales.ss_net_profit <= 250.00))))) build RFs:RF3 ca_address_sk->[ss_addr_sk]
 ----------------PhysicalProject
-------------------hashJoin[INNER_JOIN broadcast] hashCondition=((store_sales.ss_hdemo_sk = household_demographics.hd_demo_sk)) otherCondition=((((((household_demographics.hd_dep_count = 1) AND cd_marital_status IN ('M', 'S')) AND cd_education_status IN ('4 yr Degree', 'College')) AND ((cd_marital_status IN ('M', 'S') AND cd_education_status IN ('4 yr Degree', 'College')) AND ((((customer_demographics.cd_marital_status = 'S') AND (customer_demographics.cd_education_status = 'College')) AND ((store_sales.ss_sales_price >= 50.00) AND (store_sales.ss_sales_price <= 100.00))) OR (((customer_demographics.cd_marital_status = 'M') AND (customer_demographics.cd_education_status = '4 yr Degree')) AND ((store_sales.ss_sales_price >= 150.00) AND (store_sales.ss_sales_price <= 200.00)))))) OR ((((customer_demographics.cd_marital_status = 'D') AND (customer_demographics.cd_education_status = 'Unknown')) AND ((store_sales.ss_sales_price >= 100.00) AND (store_sales.ss_sales_price <= 150.00))) AND (household_demographics.hd_dep_count = 3)))) build RFs:RF2 hd_demo_sk->[ss_hdemo_sk]
+------------------hashJoin[INNER_JOIN broadcast] hashCondition=((store_sales.ss_hdemo_sk = household_demographics.hd_demo_sk)) otherCondition=((((((household_demographics.hd_dep_count = 1) AND cd_marital_status IN ('M', 'S')) AND cd_education_status IN ('4 yr Degree', 'College')) AND ((((customer_demographics.cd_marital_status = 'S') AND (customer_demographics.cd_education_status = 'College')) AND ((store_sales.ss_sales_price >= 50.00) AND (store_sales.ss_sales_price <= 100.00))) OR (((customer_demographics.cd_marital_status = 'M') AND (customer_demographics.cd_education_status = '4 yr Degree')) AND ((store_sales.ss_sales_price >= 150.00) AND (store_sales.ss_sales_price <= 200.00))))) OR ((((customer_demographics.cd_marital_status = 'D') AND (customer_demographics.cd_education_status = 'Unknown')) AND ((store_sales.ss_sales_price >= 100.00) AND (store_sales.ss_sales_price <= 150.00))) AND (household_demographics.hd_dep_count = 3)))) build RFs:RF2 hd_demo_sk->[ss_hdemo_sk]
 --------------------PhysicalProject
 ----------------------hashJoin[INNER_JOIN broadcast] hashCondition=((customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk)) otherCondition=() build RFs:RF1 cd_demo_sk->[ss_cdemo_sk]
 ------------------------PhysicalProject

regression-test/data/nereids_tpcds_shape_sf100_p0/rf_prune/query13.out

@@ -7,7 +7,7 @@ PhysicalResultSink
 --------PhysicalProject
 ----------hashJoin[INNER_JOIN broadcast] hashCondition=((store.s_store_sk = store_sales.ss_store_sk)) otherCondition=()
 ------------PhysicalProject
---------------hashJoin[INNER_JOIN broadcast] hashCondition=((customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk)) otherCondition=((((((household_demographics.hd_dep_count = 1) AND cd_marital_status IN ('M', 'S')) AND cd_education_status IN ('4 yr Degree', 'College')) AND ((cd_marital_status IN ('M', 'S') AND cd_education_status IN ('4 yr Degree', 'College')) AND ((((customer_demographics.cd_marital_status = 'S') AND (customer_demographics.cd_education_status = 'College')) AND ((store_sales.ss_sales_price >= 50.00) AND (store_sales.ss_sales_price <= 100.00))) OR (((customer_demographics.cd_marital_status = 'M') AND (customer_demographics.cd_education_status = '4 yr Degree')) AND ((store_sales.ss_sales_price >= 150.00) AND (store_sales.ss_sales_price <= 200.00)))))) OR ((((customer_demographics.cd_marital_status = 'D') AND (customer_demographics.cd_education_status = 'Unknown')) AND ((store_sales.ss_sales_price >= 100.00) AND (store_sales.ss_sales_price <= 150.00))) AND (household_demographics.hd_dep_count = 3)))) build RFs:RF3 ss_cdemo_sk->[cd_demo_sk]
+--------------hashJoin[INNER_JOIN broadcast] hashCondition=((customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk)) otherCondition=((((((household_demographics.hd_dep_count = 1) AND cd_marital_status IN ('M', 'S')) AND cd_education_status IN ('4 yr Degree', 'College')) AND ((((customer_demographics.cd_marital_status = 'S') AND (customer_demographics.cd_education_status = 'College')) AND ((store_sales.ss_sales_price >= 50.00) AND (store_sales.ss_sales_price <= 100.00))) OR (((customer_demographics.cd_marital_status = 'M') AND (customer_demographics.cd_education_status = '4 yr Degree')) AND ((store_sales.ss_sales_price >= 150.00) AND (store_sales.ss_sales_price <= 200.00))))) OR ((((customer_demographics.cd_marital_status = 'D') AND (customer_demographics.cd_education_status = 'Unknown')) AND ((store_sales.ss_sales_price >= 100.00) AND (store_sales.ss_sales_price <= 150.00))) AND (household_demographics.hd_dep_count = 3)))) build RFs:RF3 ss_cdemo_sk->[cd_demo_sk]
 ----------------PhysicalProject
 ------------------filter(((((customer_demographics.cd_marital_status = 'D') AND (customer_demographics.cd_education_status = 'Unknown')) OR ((customer_demographics.cd_marital_status = 'S') AND (customer_demographics.cd_education_status = 'College'))) OR ((customer_demographics.cd_marital_status = 'M') AND (customer_demographics.cd_education_status = '4 yr Degree'))) and cd_education_status IN ('4 yr Degree', 'College', 'Unknown') and cd_marital_status IN ('D', 'M', 'S'))
 --------------------PhysicalOlapScan[customer_demographics] apply RFs: RF3