From 5130528a5c7d73552be06aec4ac0f072df9d745d Mon Sep 17 00:00:00 2001
From: AKIRA <33112463+Kikyou1997@users.noreply.github.com>
Date: Thu, 17 Aug 2023 16:09:18 +0800
Subject: [PATCH] [fix](stats) Add logic for data size calculation (#23103)

---
 .../java/org/apache/doris/statistics/BaseAnalysisTask.java   | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/fe/fe-core/src/main/java/org/apache/doris/statistics/BaseAnalysisTask.java b/fe/fe-core/src/main/java/org/apache/doris/statistics/BaseAnalysisTask.java
index 7ff30db5de8998..5b5fcdd9c7de2f 100644
--- a/fe/fe-core/src/main/java/org/apache/doris/statistics/BaseAnalysisTask.java
+++ b/fe/fe-core/src/main/java/org/apache/doris/statistics/BaseAnalysisTask.java
@@ -206,7 +206,10 @@ public long getJobId() {
 
     // TODO : time cost is intolerable when column is string type, return 0 directly for now.
     protected String getDataSizeFunction(Column column) {
-        return "0";
+        if (column.getType().isStringType()) {
+            return "SUM(LENGTH(`${colName}`))";
+        }
+        return "COUNT(1) * " + column.getType().getSlotSize();
     }
 
     protected String getSampleExpression() {