From bce7d88fae089863bac162b872014ab74194e1ca Mon Sep 17 00:00:00 2001
From: tanishq-chugh <tanishqchugh@cloudera.com>
Date: Sat, 18 Apr 2026 18:08:16 +0530
Subject: [PATCH 1/2] HIVE-29551: Avoid quadratic runtime in
 ColumnStatsSemanticAnalyzer#getColumnTypes

---
 .../ql/parse/ColumnStatsSemanticAnalyzer.java | 32 +++++++++++--------
 1 file changed, 19 insertions(+), 13 deletions(-)

diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsSemanticAnalyzer.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsSemanticAnalyzer.java
index 023934d9eb24..0a2cd9750fcb 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsSemanticAnalyzer.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsSemanticAnalyzer.java
@@ -24,6 +24,7 @@
 import com.google.common.base.Preconditions;
 import java.util.ArrayList;
 import java.util.Collections;
+import java.util.HashMap;
 import java.util.List;
 import java.util.Map;
 import java.util.Objects;
@@ -205,23 +206,28 @@ private static String getColTypeOf(Table tbl, String partKey) {
   protected static List<String> getColumnTypes(Table tbl, List<String> colNames) {
     List<String> colTypes = new ArrayList<>();
     List<FieldSchema> cols = tbl.getCols();
-    List<String> copyColNames = new ArrayList<>(colNames);
-
-    for (String colName : copyColNames) {
-      for (FieldSchema col : cols) {
-        if (colName.equalsIgnoreCase(col.getName())) {
-          String type = col.getType();
-          TypeInfo typeInfo = TypeInfoUtils.getTypeInfoFromTypeString(type);
-          if (typeInfo.getCategory() != ObjectInspector.Category.PRIMITIVE) {
-            logTypeWarning(colName, type);
-            colNames.remove(colName);
-          } else {
-            colTypes.add(type);
-          }
+    Map<String, String> colTypeMap = new HashMap<>();
+
+    for (FieldSchema col : cols) {
+      colTypeMap.put(col.getName().toLowerCase(), col.getType());
+    }
+
+    List<String> nonPrimColNames = new ArrayList<>();
+    for (String colName : colNames) {
+      String type = colTypeMap.get(colName.toLowerCase());
+      if (type != null) {
+        TypeInfo typeInfo = TypeInfoUtils.getTypeInfoFromTypeString(type);
+        if (typeInfo.getCategory() != ObjectInspector.Category.PRIMITIVE) {
+          logTypeWarning(colName, type);
+        } else {
+          nonPrimColNames.add(colName);
+          colTypes.add(type);
         }
       }
     }
 
+    colNames.clear();
+    colNames.addAll(nonPrimColNames);
     return colTypes;
   }
 

From 4a6804d75a2d0bf084dd87b1315f657be7ce3d2a Mon Sep 17 00:00:00 2001
From: tanishq-chugh <tanishqchugh@cloudera.com>
Date: Sun, 19 Apr 2026 13:03:02 +0530
Subject: [PATCH 2/2] Update the wrong column name used

---
 .../hadoop/hive/ql/parse/ColumnStatsSemanticAnalyzer.java   | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsSemanticAnalyzer.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsSemanticAnalyzer.java
index 0a2cd9750fcb..93f63751cc8b 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsSemanticAnalyzer.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsSemanticAnalyzer.java
@@ -212,7 +212,7 @@ protected static List<String> getColumnTypes(Table tbl, List<String> colNames) {
       colTypeMap.put(col.getName().toLowerCase(), col.getType());
     }
 
-    List<String> nonPrimColNames = new ArrayList<>();
+    List<String> primColNames = new ArrayList<>();
     for (String colName : colNames) {
       String type = colTypeMap.get(colName.toLowerCase());
       if (type != null) {
@@ -220,14 +220,14 @@ protected static List<String> getColumnTypes(Table tbl, List<String> colNames) {
         if (typeInfo.getCategory() != ObjectInspector.Category.PRIMITIVE) {
           logTypeWarning(colName, type);
         } else {
-          nonPrimColNames.add(colName);
+          primColNames.add(colName);
           colTypes.add(type);
         }
       }
     }
 
     colNames.clear();
-    colNames.addAll(nonPrimColNames);
+    colNames.addAll(primColNames);
     return colTypes;
   }