From 009683e36b6c057acd560688bbeb635ed5417297 Mon Sep 17 00:00:00 2001
From: York Cao <52438394+Baymine@users.noreply.github.com>
Date: Mon, 6 Jan 2025 18:38:01 +0800
Subject: [PATCH] [opt](cache) enhance cache key computation by removing
 comments and trimming SQL input (#46099)

- Currently, the SQL cache system in Doris may miss cache hits due to
semantically identical queries being treated as different because of:
  - Extra whitespace characters in the SQL query
  - SQL comments that don't affect the query execution
- For example, these queries are semantically identical but would
generate different cache keys:
  ```sql
  SELECT * FROM table;
  -- Same query with comments and extra spaces
  /* Comment */  SELECT   *   FROM   table  ;
  ```
- This PR improves the SQL cache hit rate by:
  - Trimming whitespace from SQL queries
  - Removing SQL comments before calculating the cache key MD5
- This ensures that queries that are semantically identical but differ
only in whitespace or comments will now hit the same cache entry,
improving cache efficiency and reducing unnecessary query executions
---
 .../main/java/org/apache/doris/nereids/SqlCacheContext.java    | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fe/fe-core/src/main/java/org/apache/doris/nereids/SqlCacheContext.java b/fe/fe-core/src/main/java/org/apache/doris/nereids/SqlCacheContext.java
index 45a4c1d50d5794..364c8bcab65162 100644
--- a/fe/fe-core/src/main/java/org/apache/doris/nereids/SqlCacheContext.java
+++ b/fe/fe-core/src/main/java/org/apache/doris/nereids/SqlCacheContext.java
@@ -26,6 +26,7 @@
 import org.apache.doris.mysql.FieldInfo;
 import org.apache.doris.mysql.privilege.DataMaskPolicy;
 import org.apache.doris.mysql.privilege.RowFilterPolicy;
+import org.apache.doris.nereids.parser.NereidsParser;
 import org.apache.doris.nereids.trees.expressions.Expression;
 import org.apache.doris.nereids.trees.expressions.Variable;
 import org.apache.doris.nereids.util.Utils;
@@ -349,7 +350,7 @@ public PUniqueId getOrComputeCacheKeyMd5() {
 
     /** doComputeCacheKeyMd5 */
     public synchronized PUniqueId doComputeCacheKeyMd5(Set<Variable> usedVariables) {
-        StringBuilder cacheKey = new StringBuilder(originSql);
+        StringBuilder cacheKey = new StringBuilder(NereidsParser.removeCommentAndTrimBlank(originSql.trim()));
         for (Entry<FullTableName, String> entry : usedViews.entrySet()) {
             cacheKey.append("|")
                     .append(entry.getKey())