diff --git a/.github/workflows/check_license.yml b/.github/workflows/check_license.yml
new file mode 100644
index 000000000000..338397dbd6cb
--- /dev/null
+++ b/.github/workflows/check_license.yml
@@ -0,0 +1,34 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+name: license header check
+on:
+  pull_request
+concurrency:
+  group: ${{ github.repository }}-${{ github.head_ref || github.sha }}-${{ github.workflow }}
+  cancel-in-progress: true
+
+jobs:
+  license-check:
+    name: License Header Check
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Check License Header
+        run: |
+          git fetch --recurse-submodules=no origin main ${{github.event.pull_request.base.sha}}
+          pip install regex
+          cd $GITHUB_WORKSPACE/
+          ./.github/workflows/util/check.sh ${{github.event.pull_request.base.sha}}
diff --git a/.github/workflows/code_style.yml b/.github/workflows/code_style.yml
index f1c9c2548324..8417264373a0 100644
--- a/.github/workflows/code_style.yml
+++ b/.github/workflows/code_style.yml
@@ -14,43 +14,56 @@
 # limitations under the License.
 
 name: Code style checks
-
 on:
-  pull_request
-
+  pull_request:
+    paths:
+      - '.github/workflows/code_style.yml'
+      - 'cpp/**'
+      - 'cpp-ch/**'
 concurrency:
   group: ${{ github.repository }}-${{ github.head_ref || github.sha }}-${{ github.workflow }}
   cancel-in-progress: true
 
 jobs:
-  formatting-check:
-    name: Formatting Check
+  CPP-format-check:
+    name: CPP Format Check
     runs-on: ubuntu-latest
     strategy:
       matrix:
         path:
-          - check: 'cpp/core'
-            exclude: ''
-          - check: 'cpp/velox'
+          - check: 'cpp'
             exclude: ''
     steps:
       - uses: actions/checkout@v4
-      - name: Run clang-format style check for C/C++ programs.
+      - name: Run clang-format style check for C/C++
         uses: jidicula/clang-format-action@v4.11.0
         with:
           clang-format-version: '15'
           check-path: ${{ matrix.path['check'] }}
           fallback-style: 'Google' # optional
 
-  license-check:
-    name: License Header Check
+  CMake-format-check:
+    name: CMake Format Check
     runs-on: ubuntu-latest
-
+    container: ubuntu:22.04
     steps:
-      - uses: actions/checkout@v3
-
-      - name: Check License Header
+      - name: Install tools
+        run: |
+          apt update -y
+          apt install git python3-pip -y
+          pip3 install --user cmake-format
+      - uses: actions/checkout@v4
+      - name: Check CMake format
         run: |
-          git fetch --recurse-submodules=no origin main ${{github.event.pull_request.base.sha}}
-          pip install regex
-          dev/check.sh ${{github.event.pull_request.base.sha}}
+          git config --global --add safe.directory $GITHUB_WORKSPACE
+          cd $GITHUB_WORKSPACE/
+          fileList=$(find ./cpp ./cpp-ch -name CMakeLists.txt -o -name *.cmake)
+          for file in $fileList; do
+              /github/home/.local/bin/cmake-format --first-comment-is-literal True --in-place $file
+          done
+          if [ -n "$(git status --porcelain)" ]; then
+             echo "Please use cmake-format to format cmake files or apply the below patch."
+             git diff -- '*CMakeLists.txt' '*.cmake'
+             exit 1
+          fi
+          echo "No CMake format issue."
diff --git a/dev/check.py b/.github/workflows/util/check.py
similarity index 100%
rename from dev/check.py
rename to .github/workflows/util/check.py
diff --git a/dev/check.sh b/.github/workflows/util/check.sh
similarity index 90%
rename from dev/check.sh
rename to .github/workflows/util/check.sh
index 9b940845f92d..d8db8bd402c3 100755
--- a/dev/check.sh
+++ b/.github/workflows/util/check.sh
@@ -15,9 +15,9 @@
 # limitations under the License.
 
 export BASE_COMMIT=$1
-dev/check.py header branch
+./.github/workflows/util/check.py header branch
 if [ $? -ne 0 ]; then
-  dev/check.py header branch --fix
+  ./.github/workflows/util/check.py header branch --fix
   echo -e "\n==== Apply using:"
   echo "patch -p1 \<<EOF"
   git --no-pager diff
diff --git a/dev/excluded_copyright_files.txt b/.github/workflows/util/excluded_copyright_files.txt
similarity index 68%
rename from dev/excluded_copyright_files.txt
rename to .github/workflows/util/excluded_copyright_files.txt
index 782f76882fde..ea5de1830ff9 100644
--- a/dev/excluded_copyright_files.txt
+++ b/.github/workflows/util/excluded_copyright_files.txt
@@ -1,2 +1,3 @@
 *cpp-ch/local-engine/Storages/ch_parquet/arrow/*
 *dev/*
+*.github/workflows/util/*
diff --git a/dev/license-header.py b/.github/workflows/util/license-header.py
similarity index 100%
rename from dev/license-header.py
rename to .github/workflows/util/license-header.py
diff --git a/dev/license.header b/.github/workflows/util/license.header
similarity index 100%
rename from dev/license.header
rename to .github/workflows/util/license.header
diff --git a/dev/util.py b/.github/workflows/util/util.py
similarity index 100%
rename from dev/util.py
rename to .github/workflows/util/util.py
diff --git a/backends-clickhouse/src/test/scala/org/apache/gluten/execution/GlutenClickHouseMergeTreeOptimizeSuite.scala b/backends-clickhouse/src/test/scala/org/apache/gluten/execution/GlutenClickHouseMergeTreeOptimizeSuite.scala
index 6f8b4d93beb6..e76d3ca55d68 100644
--- a/backends-clickhouse/src/test/scala/org/apache/gluten/execution/GlutenClickHouseMergeTreeOptimizeSuite.scala
+++ b/backends-clickhouse/src/test/scala/org/apache/gluten/execution/GlutenClickHouseMergeTreeOptimizeSuite.scala
@@ -59,6 +59,9 @@ class GlutenClickHouseMergeTreeOptimizeSuite
       .set(
         "spark.gluten.sql.columnar.backend.ch.runtime_settings.mergetree.merge_after_insert",
         "false")
+      .set(
+        "spark.gluten.sql.columnar.backend.ch.runtime_settings.input_format_parquet_max_block_size",
+        "8192")
   }
 
   override protected def createTPCHNotNullTables(): Unit = {
@@ -80,10 +83,10 @@ class GlutenClickHouseMergeTreeOptimizeSuite
 
       spark.sql("optimize lineitem_mergetree_optimize")
       val ret = spark.sql("select count(*) from lineitem_mergetree_optimize").collect()
-      assert(ret.apply(0).get(0) == 600572)
+      assertResult(600572)(ret.apply(0).get(0))
 
-      assert(
-        countFiles(new File(s"$basePath/lineitem_mergetree_optimize")) == 641
+      assertResult(462)(
+        countFiles(new File(s"$basePath/lineitem_mergetree_optimize"))
       ) // many merged parts
     }
   }
@@ -116,23 +119,23 @@ class GlutenClickHouseMergeTreeOptimizeSuite
     spark.sparkContext.setJobGroup("test", "test")
     spark.sql("optimize lineitem_mergetree_optimize_p")
     val job_ids = spark.sparkContext.statusTracker.getJobIdsForGroup("test")
-    assert(job_ids.size == 1) // will not trigger actual merge job
+    assertResult(1)(job_ids.length) // will not trigger actual merge job
     spark.sparkContext.clearJobGroup()
 
     val ret = spark.sql("select count(*) from lineitem_mergetree_optimize_p").collect()
-    assert(ret.apply(0).get(0) == 600572)
+    assertResult(600572)(ret.apply(0).get(0))
 
-    assert(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p")) == 22728)
+    assertResult(22728)(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p")))
     spark.sql("VACUUM lineitem_mergetree_optimize_p RETAIN 0 HOURS")
     if (sparkVersion.equals("3.2")) {
-      assert(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p")) == 22728)
+      assertResult(22728)(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p")))
     } else {
       // For Spark 3.3 + Delta 2.3, vacuum command will create two commit files in deltalog dir.
-      assert(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p")) == 22730)
+      assertResult(22730)(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p")))
     }
 
     val ret2 = spark.sql("select count(*) from lineitem_mergetree_optimize_p").collect()
-    assert(ret2.apply(0).get(0) == 600572)
+    assertResult(600572)(ret2.apply(0).get(0))
   }
 
   test("test mergetree optimize partitioned by one low card column") {
@@ -152,33 +155,33 @@ class GlutenClickHouseMergeTreeOptimizeSuite
     spark.sql("optimize lineitem_mergetree_optimize_p2")
     val job_ids = spark.sparkContext.statusTracker.getJobIdsForGroup("test2")
     if (sparkVersion.equals("3.2")) {
-      assert(job_ids.size == 7) // WILL trigger actual merge job
+      assertResult(7)(job_ids.length) // WILL trigger actual merge job
     } else {
-      assert(job_ids.size == 8) // WILL trigger actual merge job
+      assertResult(8)(job_ids.length) // WILL trigger actual merge job
     }
 
     spark.sparkContext.clearJobGroup()
 
     val ret = spark.sql("select count(*) from lineitem_mergetree_optimize_p2").collect()
-    assert(ret.apply(0).get(0) == 600572)
+    assertResult(600572)(ret.apply(0).get(0))
 
-    assert(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p2")) == 348)
+    assertResult(372)(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p2")))
     spark.sql("VACUUM lineitem_mergetree_optimize_p2 RETAIN 0 HOURS")
     if (sparkVersion.equals("3.2")) {
-      assert(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p2")) == 236)
+      assertResult(239)(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p2")))
     } else {
-      assert(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p2")) == 238)
+      assertResult(241)(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p2")))
     }
     spark.sql("VACUUM lineitem_mergetree_optimize_p2 RETAIN 0 HOURS")
     // the second VACUUM will remove some empty folders
     if (sparkVersion.equals("3.2")) {
-      assert(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p2")) == 220)
+      assertResult(220)(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p2")))
     } else {
-      assert(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p2")) == 226)
+      assertResult(226)(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p2")))
     }
 
     val ret2 = spark.sql("select count(*) from lineitem_mergetree_optimize_p2").collect()
-    assert(ret2.apply(0).get(0) == 600572)
+    assertResult(600572)(ret2.apply(0).get(0))
   }
 
   test("test mergetree optimize partitioned by two low card column") {
@@ -197,24 +200,24 @@ class GlutenClickHouseMergeTreeOptimizeSuite
 
       spark.sql("optimize lineitem_mergetree_optimize_p3")
       val ret = spark.sql("select count(*) from lineitem_mergetree_optimize_p3").collect()
-      assert(ret.apply(0).get(0) == 600572)
+      assertResult(600572)(ret.apply(0).get(0))
 
-      assert(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p3")) == 448)
+      assertResult(516)(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p3")))
       spark.sql("VACUUM lineitem_mergetree_optimize_p3 RETAIN 0 HOURS")
       if (sparkVersion.equals("3.2")) {
-        assert(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p3")) == 294)
+        assertResult(306)(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p3")))
       } else {
-        assert(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p3")) == 296)
+        assertResult(308)(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p3")))
       }
       spark.sql("VACUUM lineitem_mergetree_optimize_p3 RETAIN 0 HOURS")
       if (sparkVersion.equals("3.2")) {
-        assert(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p3")) == 272)
+        assertResult(276)(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p3")))
       } else {
-        assert(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p3")) == 278)
+        assertResult(282)(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p3")))
       }
 
       val ret2 = spark.sql("select count(*) from lineitem_mergetree_optimize_p3").collect()
-      assert(ret2.apply(0).get(0) == 600572)
+      assertResult(600572)(ret2.apply(0).get(0))
     }
   }
 
@@ -234,29 +237,29 @@ class GlutenClickHouseMergeTreeOptimizeSuite
 
       spark.sql("optimize lineitem_mergetree_optimize_p4")
       val ret = spark.sql("select count(*) from lineitem_mergetree_optimize_p4").collect()
-      assert(ret.apply(0).get(0) == 600572)
+      assertResult(600572)(ret.apply(0).get(0))
 
-      assert(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p4")) == 448)
+      assertResult(516)(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p4")))
       spark.sql("VACUUM lineitem_mergetree_optimize_p4 RETAIN 0 HOURS")
       if (sparkVersion.equals("3.2")) {
-        assert(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p4")) == 294)
+        assertResult(306)(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p4")))
       } else {
-        assert(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p4")) == 296)
+        assertResult(308)(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p4")))
       }
       spark.sql("VACUUM lineitem_mergetree_optimize_p4 RETAIN 0 HOURS")
       if (sparkVersion.equals("3.2")) {
-        assert(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p4")) == 272)
+        assertResult(276)(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p4")))
       } else {
-        assert(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p4")) == 278)
+        assertResult(282)(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p4")))
       }
 
       val ret2 = spark.sql("select count(*) from lineitem_mergetree_optimize_p4").collect()
-      assert(ret2.apply(0).get(0) == 600572)
+      assertResult(600572)(ret2.apply(0).get(0))
     }
   }
 
   test("test mergetree optimize with optimize.minFileSize and optimize.maxFileSize") {
-    withSQLConf("spark.databricks.delta.optimize.minFileSize" -> "83800000") {
+    withSQLConf("spark.databricks.delta.optimize.minFileSize" -> "838000") {
       // 3 from 37 parts are larger than this, so after optimize there should be 4 parts:
       // 3 original parts and 1 merged part
       spark.sql(s"""
@@ -275,20 +278,20 @@ class GlutenClickHouseMergeTreeOptimizeSuite
       spark.sql("VACUUM lineitem_mergetree_optimize_p5 RETAIN 0 HOURS")
       spark.sql("VACUUM lineitem_mergetree_optimize_p5 RETAIN 0 HOURS")
       if (sparkVersion.equals("3.2")) {
-        assert(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p5")) == 75)
+        assertResult(99)(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p5")))
       } else {
         // For Spark 3.3 + Delta 2.3, vacuum command will create two commit files in deltalog dir.
         // this case will create a checkpoint
-        assert(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p5")) == 81)
+        assertResult(105)(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p5")))
       }
 
       val ret = spark.sql("select count(*) from lineitem_mergetree_optimize_p5").collect()
-      assert(ret.apply(0).get(0) == 600572)
+      assertResult(600572)(ret.apply(0).get(0))
     }
 
     withSQLConf(
-      ("spark.databricks.delta.optimize.maxFileSize" -> "10000000"),
-      ("spark.databricks.delta.optimize.minFileSize" -> "838250")) {
+      "spark.databricks.delta.optimize.maxFileSize" -> "10000000",
+      "spark.databricks.delta.optimize.minFileSize" -> "838250") {
       // of the remaing 3 original parts, 2 are less than 838250, 1 is larger (size 838255)
       // the merged part is ~27MB, so after optimize there should be 3 parts:
       // 1 merged part from 2 original parts, 1 merged part from 34 original parts
@@ -299,14 +302,14 @@ class GlutenClickHouseMergeTreeOptimizeSuite
       spark.sql("VACUUM lineitem_mergetree_optimize_p5 RETAIN 0 HOURS")
       spark.sql("VACUUM lineitem_mergetree_optimize_p5 RETAIN 0 HOURS")
       if (sparkVersion.equals("3.2")) {
-        assert(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p5")) == 75)
+        assertResult(93)(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p5")))
       } else {
         // For Spark 3.3 + Delta 2.3, vacuum command will create two commit files in deltalog dir.
-        assert(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p5")) == 85)
+        assertResult(104)(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p5")))
       }
 
       val ret = spark.sql("select count(*) from lineitem_mergetree_optimize_p5").collect()
-      assert(ret.apply(0).get(0) == 600572)
+      assertResult(600572)(ret.apply(0).get(0))
     }
 
     // now merge all parts (testing merging from merged parts)
@@ -315,14 +318,14 @@ class GlutenClickHouseMergeTreeOptimizeSuite
     spark.sql("VACUUM lineitem_mergetree_optimize_p5 RETAIN 0 HOURS")
     spark.sql("VACUUM lineitem_mergetree_optimize_p5 RETAIN 0 HOURS")
     if (sparkVersion.equals("3.2")) {
-      assert(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p5")) == 75)
+      assertResult(77)(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p5")))
     } else {
       // For Spark 3.3 + Delta 2.3, vacuum command will create two commit files in deltalog dir.
-      assert(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p5")) == 90)
+      assertResult(93)(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p5")))
     }
 
     val ret = spark.sql("select count(*) from lineitem_mergetree_optimize_p5").collect()
-    assert(ret.apply(0).get(0) == 600572)
+    assertResult(600572)(ret.apply(0).get(0))
   }
 
   test("test mergetree optimize table with partition and bucket") {
@@ -343,24 +346,22 @@ class GlutenClickHouseMergeTreeOptimizeSuite
     spark.sql("optimize lineitem_mergetree_optimize_p6")
 
     val ret = spark.sql("select count(*) from lineitem_mergetree_optimize_p6").collect()
-    assert(ret.apply(0).get(0) == 600572)
+    assertResult(600572)(ret.apply(0).get(0))
 
-    assert(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p6")) == {
-      if (sparkVersion.equals("3.2")) 475 else 501
-    })
+    assertResult(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p6")))(
+      if (sparkVersion.equals("3.2")) 499 else 528)
     spark.sql("VACUUM lineitem_mergetree_optimize_p6 RETAIN 0 HOURS")
     spark.sql("VACUUM lineitem_mergetree_optimize_p6 RETAIN 0 HOURS")
-    assert(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p6")) == {
-      if (sparkVersion.equals("3.2")) 315 else 327
-    })
+    assertResult(countFiles(new File(s"$basePath/lineitem_mergetree_optimize_p6")))(
+      if (sparkVersion.equals("3.2")) 315 else 327)
 
     val ret2 = spark.sql("select count(*) from lineitem_mergetree_optimize_p6").collect()
-    assert(ret2.apply(0).get(0) == 600572)
+    assertResult(600572)(ret2.apply(0).get(0))
   }
 
   test("test skip index after optimize") {
     withSQLConf(
-      "spark.databricks.delta.optimize.maxFileSize" -> "100000000",
+      "spark.databricks.delta.optimize.maxFileSize" -> "2000000",
       "spark.sql.adaptive.enabled" -> "false") {
       spark.sql(s"""
                    |DROP TABLE IF EXISTS lineitem_mergetree_index;
@@ -385,12 +386,12 @@ class GlutenClickHouseMergeTreeOptimizeSuite
       val scanExec = collect(df.queryExecution.executedPlan) {
         case f: FileSourceScanExecTransformer => f
       }
-      assert(scanExec.size == 1)
-      val mergetreeScan = scanExec(0)
+      assertResult(1)(scanExec.size)
+      val mergetreeScan = scanExec.head
       val ret = df.collect()
-      assert(ret.apply(0).get(0) == 2)
+      assertResult(2)(ret.apply(0).get(0))
       val marks = mergetreeScan.metrics("selectedMarks").value
-      assert(marks == 1)
+      assertResult(1)(marks)
 
       val directory = new File(s"$basePath/lineitem_mergetree_index")
       val partDir = directory.listFiles().filter(f => f.getName.endsWith("merged")).head
@@ -403,7 +404,7 @@ class GlutenClickHouseMergeTreeOptimizeSuite
   test("test mergetree optimize with the path based table") {
     val dataPath = s"$basePath/lineitem_mergetree_optimize_path_based"
     clearDataPath(dataPath)
-    withSQLConf("spark.databricks.delta.optimize.minFileSize" -> "83800000") {
+    withSQLConf("spark.databricks.delta.optimize.minFileSize" -> "838000") {
       // 3 from 37 parts are larger than this, so after optimize there should be 4 parts:
       // 3 original parts and 1 merged part
 
@@ -422,18 +423,18 @@ class GlutenClickHouseMergeTreeOptimizeSuite
       clickhouseTable.vacuum(0.0)
       clickhouseTable.vacuum(0.0)
       if (sparkVersion.equals("3.2")) {
-        assert(countFiles(new File(dataPath)) == 75)
+        assertResult(99)(countFiles(new File(dataPath)))
       } else {
-        assert(countFiles(new File(dataPath)) == 81)
+        assertResult(105)(countFiles(new File(dataPath)))
       }
 
       val ret = spark.sql(s"select count(*) from clickhouse.`$dataPath`").collect()
-      assert(ret.apply(0).get(0) == 600572)
+      assertResult(600572)(ret.apply(0).get(0))
     }
 
     withSQLConf(
-      ("spark.databricks.delta.optimize.maxFileSize" -> "10000000"),
-      ("spark.databricks.delta.optimize.minFileSize" -> "838250")) {
+      "spark.databricks.delta.optimize.maxFileSize" -> "10000000",
+      "spark.databricks.delta.optimize.minFileSize" -> "838250") {
       // of the remaing 3 original parts, 2 are less than 838250, 1 is larger (size 838255)
       // the merged part is ~27MB, so after optimize there should be 3 parts:
       // 1 merged part from 2 original parts, 1 merged part from 34 original parts
@@ -445,13 +446,13 @@ class GlutenClickHouseMergeTreeOptimizeSuite
       clickhouseTable.vacuum(0.0)
       clickhouseTable.vacuum(0.0)
       if (sparkVersion.equals("3.2")) {
-        assert(countFiles(new File(dataPath)) == 75)
+        assertResult(93)(countFiles(new File(dataPath)))
       } else {
-        assert(countFiles(new File(dataPath)) == 85)
+        assertResult(104)(countFiles(new File(dataPath)))
       }
 
       val ret = spark.sql(s"select count(*) from clickhouse.`$dataPath`").collect()
-      assert(ret.apply(0).get(0) == 600572)
+      assertResult(600572)(ret.apply(0).get(0))
     }
 
     // now merge all parts (testing merging from merged parts)
@@ -461,19 +462,19 @@ class GlutenClickHouseMergeTreeOptimizeSuite
     clickhouseTable.vacuum(0.0)
     clickhouseTable.vacuum(0.0)
     if (sparkVersion.equals("3.2")) {
-      assert(countFiles(new File(dataPath)) == 75)
+      assertResult(77)(countFiles(new File(dataPath)))
     } else {
-      assert(countFiles(new File(dataPath)) == 90)
+      assertResult(93)(countFiles(new File(dataPath)))
     }
 
     val ret = spark.sql(s"select count(*) from clickhouse.`$dataPath`").collect()
-    assert(ret.apply(0).get(0) == 600572)
+    assertResult(600572)(ret.apply(0).get(0))
   }
 
   test("test mergetree insert with optimize basic") {
     withSQLConf(
-      ("spark.databricks.delta.optimize.minFileSize" -> "200000000"),
-      ("spark.gluten.sql.columnar.backend.ch.runtime_settings.mergetree.merge_after_insert" -> "true")
+      "spark.databricks.delta.optimize.minFileSize" -> "200000000",
+      "spark.gluten.sql.columnar.backend.ch.runtime_settings.mergetree.merge_after_insert" -> "true"
     ) {
       spark.sql(s"""
                    |DROP TABLE IF EXISTS lineitem_mergetree_insert_optimize_basic;
@@ -487,10 +488,10 @@ class GlutenClickHouseMergeTreeOptimizeSuite
                    |""".stripMargin)
 
       val ret = spark.sql("select count(*) from lineitem_mergetree_insert_optimize_basic").collect()
-      assert(ret.apply(0).get(0) == 600572)
+      assertResult(600572)(ret.apply(0).get(0))
       eventually(timeout(60.seconds), interval(3.seconds)) {
-        assert(
-          new File(s"$basePath/lineitem_mergetree_insert_optimize_basic").listFiles().length == 2
+        assertResult(2)(
+          new File(s"$basePath/lineitem_mergetree_insert_optimize_basic").listFiles().length
         )
       }
     }
diff --git a/backends-clickhouse/src/test/scala/org/apache/gluten/execution/GlutenClickHouseMergeTreePathBasedWriteSuite.scala b/backends-clickhouse/src/test/scala/org/apache/gluten/execution/GlutenClickHouseMergeTreePathBasedWriteSuite.scala
index c8c6307aba06..791239fabf48 100644
--- a/backends-clickhouse/src/test/scala/org/apache/gluten/execution/GlutenClickHouseMergeTreePathBasedWriteSuite.scala
+++ b/backends-clickhouse/src/test/scala/org/apache/gluten/execution/GlutenClickHouseMergeTreePathBasedWriteSuite.scala
@@ -60,6 +60,9 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
       .set(
         "spark.gluten.sql.columnar.backend.ch.runtime_settings.mergetree.merge_after_insert",
         "false")
+      .set(
+        "spark.gluten.sql.columnar.backend.ch.runtime_settings.input_format_parquet_max_block_size",
+        "8192")
   }
 
   override protected def createTPCHNotNullTables(): Unit = {
@@ -143,7 +146,7 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
           case f: FileSourceScanExecTransformer => f
           case w: WholeStageTransformer => w
         }
-        assert(plans.size == 4)
+        assertResult(4)(plans.size)
 
         val mergetreeScan = plans(3).asInstanceOf[FileSourceScanExecTransformer]
         assert(mergetreeScan.nodeName.startsWith("Scan mergetree"))
@@ -154,10 +157,8 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).primaryKeyOption.nonEmpty)
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).partitionColumns.isEmpty)
         val addFiles = fileIndex.matchingFiles(Nil, Nil).map(f => f.asInstanceOf[AddMergeTreeParts])
-        assert(addFiles.size == 5)
-        assert(
-          addFiles.map(_.rows).sum
-            == 600572)
+        assertResult(6)(addFiles.size)
+        assertResult(600572)(addFiles.map(_.rows).sum)
 
         // GLUTEN-5060: check the unnecessary FilterExec
         val wholeStageTransformer = plans(2).asInstanceOf[WholeStageTransformer]
@@ -174,7 +175,7 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
       .load(dataPath)
       .where("l_shipdate = date'1998-09-02'")
       .count()
-    assert(result == 183)
+    assertResult(183)(result)
   }
 
   test("test mergetree path based write with dataframe api") {
@@ -236,40 +237,35 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
           case f: FileSourceScanExecTransformer => f
           case w: WholeStageTransformer => w
         }
-        assert(plans.size == 4)
+        assertResult(4)(plans.size)
 
         val mergetreeScan = plans(3).asInstanceOf[FileSourceScanExecTransformer]
         assert(mergetreeScan.nodeName.startsWith("Scan mergetree"))
 
         val fileIndex = mergetreeScan.relation.location.asInstanceOf[TahoeFileIndex]
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).clickhouseTableConfigs.nonEmpty)
-        assert(
+        assertResult("l_shipdate,l_orderkey")(
           ClickHouseTableV2
             .getTable(fileIndex.deltaLog)
             .orderByKeyOption
             .get
-            .mkString(",")
-            .equals("l_shipdate,l_orderkey"))
-        assert(
+            .mkString(","))
+        assertResult("l_shipdate")(
           ClickHouseTableV2
             .getTable(fileIndex.deltaLog)
             .primaryKeyOption
             .get
-            .mkString(",")
-            .equals("l_shipdate"))
-        assert(
+            .mkString(","))
+        assertResult("l_returnflag,l_linestatus")(
           ClickHouseTableV2
             .getTable(fileIndex.deltaLog)
             .lowCardKeyOption
             .get
-            .mkString(",")
-            .equals("l_returnflag,l_linestatus"))
+            .mkString(","))
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).partitionColumns.isEmpty)
         val addFiles = fileIndex.matchingFiles(Nil, Nil).map(f => f.asInstanceOf[AddMergeTreeParts])
-        assert(addFiles.size == 5)
-        assert(
-          addFiles.map(_.rows).sum
-            == 600572)
+        assertResult(6)(addFiles.size)
+        assertResult(600572)(addFiles.map(_.rows).sum)
 
         // GLUTEN-5060: check the unnecessary FilterExec
         val wholeStageTransformer = plans(2).asInstanceOf[WholeStageTransformer]
@@ -286,7 +282,7 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
       .load(dataPath)
       .where("l_shipdate = date'1998-09-02'")
       .collect()
-    assert(result.length == 183)
+    assertResult(110501)(result.apply(0).get(0))
   }
 
   test("test mergetree path based insert overwrite partitioned table with small table, static") {
@@ -320,7 +316,7 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
       .format("clickhouse")
       .load(dataPath)
       .count()
-    assert(result == 2418)
+    assertResult(2418)(result)
   }
 
   test("test mergetree path based insert overwrite partitioned table with small table, dynamic") {
@@ -355,7 +351,7 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
         .format("clickhouse")
         .load(dataPath)
         .count()
-      assert(result == 600572)
+      assertResult(600572)(result)
     }
   }
 
@@ -381,11 +377,11 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
         .format("clickhouse")
         .load(dataPath)
         .where("l_returnflag = 'Z'")
-      assert(df.count() == 1)
+      assertResult(1)(df.count())
       val scanExec = collect(df.queryExecution.executedPlan) {
         case f: FileSourceScanExecTransformer => f
       }
-      assert(scanExec.size == 1)
+      assertResult(1)(scanExec.size)
 
       val mergetreeScan = scanExec.head
       assert(mergetreeScan.nodeName.startsWith("Scan mergetree"))
@@ -397,16 +393,13 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
       assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).primaryKeyOption.isEmpty)
       assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).partitionColumns.isEmpty)
       val addFiles = fileIndex.matchingFiles(Nil, Nil).map(f => f.asInstanceOf[AddMergeTreeParts])
-      assert(
-        addFiles.map(_.rows).sum
-          == 600572)
-
+      assertResult(600572)(addFiles.map(_.rows).sum)
       // 4 parts belong to the first batch
       // 2 parts belong to the second batch (1 actual updated part, 1 passively updated).
-      assert(addFiles.size == 6)
+      assertResult(6)(addFiles.size)
       val filePaths = addFiles.map(_.path).groupBy(name => name.substring(0, name.lastIndexOf("_")))
-      assert(filePaths.size == 2)
-      assert(Array(3, 3).sameElements(filePaths.values.map(paths => paths.size).toArray.sorted))
+      assertResult(2)(filePaths.size)
+      assertResult(Array(2, 4))(filePaths.values.map(paths => paths.size).toArray.sorted)
     }
 
     val clickhouseTable = ClickhouseTable.forPath(spark, dataPath)
@@ -417,33 +410,31 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
         .format("clickhouse")
         .load(dataPath)
         .where("l_returnflag = 'X'")
-      assert(df.count() == 1)
+      assertResult(1)(df.count())
       val scanExec = collect(df.queryExecution.executedPlan) {
         case f: FileSourceScanExecTransformer => f
       }
-      assert(scanExec.size == 1)
+      assertResult(1)(scanExec.size)
 
       val mergetreeScan = scanExec.head
       assert(mergetreeScan.nodeName.startsWith("Scan mergetree"))
 
       val fileIndex = mergetreeScan.relation.location.asInstanceOf[TahoeFileIndex]
       val addFiles = fileIndex.matchingFiles(Nil, Nil).map(f => f.asInstanceOf[AddMergeTreeParts])
-      assert(
-        addFiles.map(_.rows).sum
-          == 600572)
+      assertResult(600572)(addFiles.map(_.rows).sum)
 
       // 4 parts belong to the first batch
       // 2 parts belong to the second batch (1 actual updated part, 1 passively updated).
-      assert(addFiles.size == 6)
+      assertResult(6)(addFiles.size)
       val filePaths = addFiles.map(_.path).groupBy(name => name.substring(0, name.lastIndexOf("_")))
-      assert(filePaths.size == 3)
-      assert(Array(1, 2, 3).sameElements(filePaths.values.map(paths => paths.size).toArray.sorted))
+      assertResult(2)(filePaths.size)
+      assertResult(Array(2, 4))(filePaths.values.map(paths => paths.size).toArray.sorted)
     }
 
     val df = spark.read
       .format("clickhouse")
       .load(dataPath)
-    assert(df.count() == 600572)
+    assertResult(600572)(df.count())
   }
 
   test("test mergetree path based table delete") {
@@ -465,7 +456,7 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
     val df = spark.read
       .format("clickhouse")
       .load(dataPath)
-    assert(df.count() == 600571)
+    assertResult(600571)(df.count())
     val scanExec = collect(df.queryExecution.executedPlan) {
       case f: FileSourceScanExecTransformer => f
     }
@@ -474,17 +465,17 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
     val addFiles = fileIndex.matchingFiles(Nil, Nil).map(f => f.asInstanceOf[AddMergeTreeParts])
     // 4 parts belong to the first batch
     // 2 parts belong to the second batch (1 actual updated part, 1 passively updated).
-    assert(addFiles.size == 6)
+    assertResult(6)(addFiles.size)
     val filePaths = addFiles.map(_.path).groupBy(name => name.substring(0, name.lastIndexOf("_")))
-    assert(filePaths.size == 2)
-    assert(Array(3, 3).sameElements(filePaths.values.map(paths => paths.size).toArray.sorted))
+    assertResult(2)(filePaths.size)
+    assertResult(Array(2, 4))(filePaths.values.map(paths => paths.size).toArray.sorted)
 
     val clickhouseTable = ClickhouseTable.forPath(spark, dataPath)
     clickhouseTable.delete("mod(l_orderkey, 3) = 2")
     val df1 = spark.read
       .format("clickhouse")
       .load(dataPath)
-    assert(df1.count() == 400089)
+    assertResult(400089)(df1.count())
   }
 
   test("test mergetree path based table upsert") {
@@ -503,8 +494,8 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
     val df0 = spark.sql(s"""
                            | select count(*) from clickhouse.`$dataPath`
                            |""".stripMargin)
-    assert(
-      df0.collect().apply(0).get(0) == 600572
+    assertResult(600572)(
+      df0.collect().apply(0).get(0)
     )
     upsertSourceTableAndCheck(dataPath)
   }
@@ -540,8 +531,8 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
       val df1 = spark.sql(s"""
                              | select count(*) from clickhouse.`$dataPath`
                              |""".stripMargin)
-      assert(
-        df1.collect().apply(0).get(0) == 600572 + 3506
+      assertResult(600572 + 3506)(
+        df1.collect().apply(0).get(0)
       )
     }
     {
@@ -549,8 +540,8 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
         spark.sql(s"""
                      | select count(*) from clickhouse.`$dataPath` where l_returnflag = 'Z'
                      |""".stripMargin)
-      assert(
-        df2.collect().apply(0).get(0) == 3506
+      assertResult(3506)(
+        df2.collect().apply(0).get(0)
       )
     }
 
@@ -559,8 +550,8 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
         spark.sql(s"""
                      | select count(*) from clickhouse.`$dataPath` where l_orderkey > 10000000
                      |""".stripMargin)
-      assert(
-        df3.collect().apply(0).get(0) == 3506
+      assertResult(3506)(
+        df3.collect().apply(0).get(0)
       )
     }
   }
@@ -610,33 +601,31 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
         val scanExec = collect(df.queryExecution.executedPlan) {
           case f: FileSourceScanExecTransformer => f
         }
-        assert(scanExec.size == 1)
+        assertResult(1)(scanExec.size)
 
-        val mergetreeScan = scanExec(0)
+        val mergetreeScan = scanExec.head
         assert(mergetreeScan.nodeName.startsWith("Scan mergetree"))
 
         val fileIndex = mergetreeScan.relation.location.asInstanceOf[TahoeFileIndex]
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).clickhouseTableConfigs.nonEmpty)
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).bucketOption.isEmpty)
-        assert(
+        assertResult("l_shipdate,l_orderkey")(
           ClickHouseTableV2
             .getTable(fileIndex.deltaLog)
             .orderByKeyOption
             .get
-            .mkString(",")
-            .equals("l_shipdate,l_orderkey"))
-        assert(
+            .mkString(","))
+        assertResult("l_shipdate")(
           ClickHouseTableV2
             .getTable(fileIndex.deltaLog)
             .primaryKeyOption
             .get
-            .mkString(",")
-            .equals("l_shipdate"))
+            .mkString(","))
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).partitionColumns.isEmpty)
         val addFiles = fileIndex.matchingFiles(Nil, Nil).map(f => f.asInstanceOf[AddMergeTreeParts])
 
-        assert(addFiles.size == 5)
-        assert(addFiles.map(_.rows).sum == 600572)
+        assertResult(6)(addFiles.size)
+        assertResult(600572)(addFiles.map(_.rows).sum)
     }
 
     val df = spark.read
@@ -650,7 +639,7 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
                |""".stripMargin)
       .agg(sum("l_linenumber").alias("res"))
     val result = df.collect()
-    assert(result(0).getLong(0) == 34842)
+    assertResult(34842)(result(0).getLong(0))
   }
 
   test("test mergetree path based write with partition") {
@@ -707,62 +696,56 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
     runTPCHQueryBySQL(1, sqlStr, compareResult = false) {
       df =>
         val result = df.collect()
-        assert(result.size == 4)
-        assert(result(0).getString(0).equals("A"))
-        assert(result(0).getString(1).equals("F"))
-        assert(result(0).getDouble(2) == 3803858.0)
+        assertResult(4)(result.length)
+        assertResult("A")(result(0).getString(0))
+        assertResult("F")(result(0).getString(1))
+        assertResult(3803858.0)(result(0).getDouble(2))
 
-        assert(result(2).getString(0).equals("N"))
-        assert(result(2).getString(1).equals("O"))
-        assert(result(2).getDouble(2) == 7454519.0)
+        assertResult("N")(result(2).getString(0))
+        assertResult("O")(result(2).getString(1))
+        assertResult(7454519.0)(result(2).getDouble(2))
 
         val scanExec = collect(df.queryExecution.executedPlan) {
           case f: FileSourceScanExecTransformer => f
         }
-        assert(scanExec.size == 1)
+        assertResult(1)(scanExec.size)
 
-        val mergetreeScan = scanExec(0)
+        val mergetreeScan = scanExec.head
         assert(mergetreeScan.nodeName.startsWith("Scan mergetree"))
-        assert(mergetreeScan.metrics("numFiles").value == 3744)
+        assertResult(3744)(mergetreeScan.metrics("numFiles").value)
 
         val fileIndex = mergetreeScan.relation.location.asInstanceOf[TahoeFileIndex]
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).clickhouseTableConfigs.nonEmpty)
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).bucketOption.isEmpty)
-        assert(
+        assertResult("l_orderkey")(
           ClickHouseTableV2
             .getTable(fileIndex.deltaLog)
             .orderByKeyOption
             .get
-            .mkString(",")
-            .equals("l_orderkey"))
-        assert(
+            .mkString(","))
+        assertResult("l_orderkey")(
           ClickHouseTableV2
             .getTable(fileIndex.deltaLog)
             .primaryKeyOption
             .get
-            .mkString(",")
-            .equals("l_orderkey"))
-        assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).partitionColumns.size == 2)
-        assert(
+            .mkString(","))
+        assertResult(2)(ClickHouseTableV2.getTable(fileIndex.deltaLog).partitionColumns.size)
+        assertResult("l_shipdate")(
           ClickHouseTableV2
             .getTable(fileIndex.deltaLog)
-            .partitionColumns(0)
-            .equals("l_shipdate"))
-        assert(
+            .partitionColumns
+            .head)
+        assertResult("l_returnflag")(
           ClickHouseTableV2
             .getTable(fileIndex.deltaLog)
-            .partitionColumns(1)
-            .equals("l_returnflag"))
+            .partitionColumns(1))
         val addFiles = fileIndex.matchingFiles(Nil, Nil).map(f => f.asInstanceOf[AddMergeTreeParts])
 
-        assert(addFiles.size == 3835)
-        assert(addFiles.map(_.rows).sum == 602945)
-        assert(
-          addFiles.filter(_.partitionValues.get("l_shipdate").get.equals("1992-06-01")).size == 2)
-        assert(
-          addFiles.filter(_.partitionValues.get("l_shipdate").get.equals("1993-01-01")).size == 4)
-        assert(
-          addFiles.filter(_.partitionValues.get("l_shipdate").get.equals("1995-01-21")).size == 2)
+        assertResult(3835)(addFiles.size)
+        assertResult(602945)(addFiles.map(_.rows).sum)
+        assertResult(2)(addFiles.count(_.partitionValues("l_shipdate").equals("1992-06-01")))
+        assertResult(4)(addFiles.count(_.partitionValues("l_shipdate").equals("1993-01-01")))
+        assertResult(2)(addFiles.count(_.partitionValues("l_shipdate").equals("1995-01-21")))
     }
   }
 
@@ -814,61 +797,49 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
         val scanExec = collect(df.queryExecution.executedPlan) {
           case f: FileSourceScanExecTransformer => f
         }
-        assert(scanExec.size == 1)
+        assertResult(1)(scanExec.size)
 
-        val mergetreeScan = scanExec(0)
+        val mergetreeScan = scanExec.head
         assert(mergetreeScan.nodeName.startsWith("Scan mergetree"))
 
         val fileIndex = mergetreeScan.relation.location.asInstanceOf[TahoeFileIndex]
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).clickhouseTableConfigs.nonEmpty)
         val buckets = ClickHouseTableV2.getTable(fileIndex.deltaLog).bucketOption
-        assert(!buckets.isEmpty)
-        assert(buckets.get.numBuckets == 4)
-        assert(
+        assert(buckets.isDefined)
+        assertResult(4)(buckets.get.numBuckets)
+        assertResult("l_partkey,l_returnflag")(
           buckets.get.sortColumnNames
-            .mkString(",")
-            .equals("l_partkey,l_returnflag"))
-        assert(
+            .mkString(","))
+        assertResult("l_orderkey")(
           buckets.get.bucketColumnNames
-            .mkString(",")
-            .equals("l_orderkey"))
-        assert(
+            .mkString(","))
+        assertResult("l_partkey,l_returnflag")(
           ClickHouseTableV2
             .getTable(fileIndex.deltaLog)
             .orderByKeyOption
             .get
-            .mkString(",")
-            .equals("l_partkey,l_returnflag"))
-        assert(
+            .mkString(","))
+        assertResult("l_partkey")(
           ClickHouseTableV2
             .getTable(fileIndex.deltaLog)
             .primaryKeyOption
             .get
-            .mkString(",")
-            .equals("l_partkey"))
-        assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).partitionColumns.size == 1)
-        assert(
+            .mkString(","))
+        assertResult(1)(ClickHouseTableV2.getTable(fileIndex.deltaLog).partitionColumns.size)
+        assertResult("l_shipdate")(
           ClickHouseTableV2
             .getTable(fileIndex.deltaLog)
-            .partitionColumns(0)
-            .equals("l_shipdate"))
+            .partitionColumns
+            .head)
         val addFiles = fileIndex.matchingFiles(Nil, Nil).map(f => f.asInstanceOf[AddMergeTreeParts])
 
-        assert(addFiles.size == 10089)
-        assert(addFiles.map(_.rows).sum == 600572)
-        assert(
-          addFiles.filter(_.partitionValues.get("l_shipdate").get.equals("1992-06-01")).size == 4)
-        assert(
-          addFiles.filter(_.partitionValues.get("l_shipdate").get.equals("1993-01-01")).size == 4)
-        assert(
-          addFiles.filter(_.partitionValues.get("l_shipdate").get.equals("1995-01-21")).size == 4)
-        assert(
-          addFiles
-            .filter(
-              f =>
-                f.partitionValues.get("l_shipdate").get.equals("1995-01-21") && f.bucketNum.equals(
-                  "00000"))
-            .size == 1)
+        assertResult(10089)(addFiles.size)
+        assertResult(600572)(addFiles.map(_.rows).sum)
+        assertResult(4)(addFiles.count(_.partitionValues("l_shipdate").equals("1992-06-01")))
+        assertResult(4)(addFiles.count(_.partitionValues("l_shipdate").equals("1993-01-01")))
+        assertResult(4)(addFiles.count(_.partitionValues("l_shipdate").equals("1995-01-21")))
+        assertResult(1)(addFiles.count(
+          f => f.partitionValues("l_shipdate").equals("1995-01-21") && f.bucketNum.equals("00000")))
     }
     // check part pruning effect of filter on bucket column
     val df = spark.sql(s"""
@@ -883,7 +854,7 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
       .flatMap(partition => partition.asInstanceOf[GlutenMergeTreePartition].partList)
       .map(_.name)
       .distinct
-    assert(touchedParts.size == 1)
+    assertResult(1)(touchedParts.size)
 
     // test upsert on partitioned & bucketed table
     upsertSourceTableAndCheck(dataPath)
@@ -929,9 +900,9 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
         val scanExec = collect(df.queryExecution.executedPlan) {
           case f: FileSourceScanExecTransformer => f
         }
-        assert(scanExec.size == 1)
+        assertResult(1)(scanExec.size)
 
-        val mergetreeScan = scanExec(0)
+        val mergetreeScan = scanExec.head
         assert(mergetreeScan.nodeName.startsWith("Scan mergetree"))
 
         val fileIndex = mergetreeScan.relation.location.asInstanceOf[TahoeFileIndex]
@@ -941,10 +912,8 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).primaryKeyOption.isEmpty)
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).partitionColumns.isEmpty)
         val addFiles = fileIndex.matchingFiles(Nil, Nil).map(f => f.asInstanceOf[AddMergeTreeParts])
-        assert(addFiles.size == 5)
-        assert(
-          addFiles.map(_.rows).sum
-            == 600572)
+        assertResult(6)(addFiles.size)
+        assertResult(600572)(addFiles.map(_.rows).sum)
     }
   }
 
@@ -1052,9 +1021,9 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
          |
          |""".stripMargin
 
-    assert(
+    assertResult("R")(
       // total rows should remain unchanged
-      spark.sql(sqlStr2).collect().apply(0).get(0) == "R"
+      spark.sql(sqlStr2).collect().apply(0).get(0)
     )
 
     // test select *
@@ -1101,40 +1070,38 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
         val scanExec = collect(df.queryExecution.executedPlan) {
           case f: FileSourceScanExecTransformer => f
         }
-        assert(scanExec.size == 1)
+        assertResult(1)(scanExec.size)
 
-        val mergetreeScan = scanExec(0)
+        val mergetreeScan = scanExec.head
         assert(mergetreeScan.nodeName.startsWith("Scan mergetree"))
 
         val fileIndex = mergetreeScan.relation.location.asInstanceOf[TahoeFileIndex]
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).clickhouseTableConfigs.nonEmpty)
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).bucketOption.isEmpty)
-        assert(
+        assertResult("l_shipdate,l_orderkey")(
           ClickHouseTableV2
             .getTable(fileIndex.deltaLog)
             .orderByKeyOption
             .get
-            .mkString(",")
-            .equals("l_shipdate,l_orderkey"))
-        assert(
+            .mkString(","))
+        assertResult("l_shipdate")(
           ClickHouseTableV2
             .getTable(fileIndex.deltaLog)
             .primaryKeyOption
             .get
-            .mkString(",")
-            .equals("l_shipdate"))
+            .mkString(","))
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).partitionColumns.isEmpty)
         val addFiles = fileIndex.matchingFiles(Nil, Nil).map(f => f.asInstanceOf[AddMergeTreeParts])
 
-        assert(addFiles.size == 5)
-        assert(addFiles.map(_.rows).sum == 600572)
+        assertResult(6)(addFiles.size)
+        assertResult(600572)(addFiles.map(_.rows).sum)
 
         val plans = collect(df.queryExecution.executedPlan) {
           case scanExec: BasicScanExecTransformer => scanExec
         }
-        assert(plans.size == 1)
-        assert(plans(0).metrics("selectedMarksPk").value === 15)
-        assert(plans(0).metrics("totalMarksPk").value === 74)
+        assertResult(1)(plans.size)
+        assertResult(17)(plans.head.metrics("selectedMarksPk").value)
+        assertResult(74)(plans.head.metrics("totalMarksPk").value)
     }
   }
 
@@ -1161,12 +1128,12 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
     val scanExec = collect(df.queryExecution.executedPlan) {
       case f: FileSourceScanExecTransformer => f
     }
-    assert(scanExec.size == 1)
-    val mergetreeScan = scanExec(0)
+    assertResult(1)(scanExec.size)
+    val mergetreeScan = scanExec.head
 
-    assert(ret.apply(0).get(0) == 1)
+    assertResult(1)(ret.apply(0).get(0))
     val marks = mergetreeScan.metrics("selectedMarks").value
-    assert(marks == 1)
+    assertResult(1)(marks)
 
     val directory = new File(dataPath)
     // find a folder whose name is like 48b70783-b3b8-4bf8-9c52-5261aead8e3e_0_006
@@ -1197,11 +1164,11 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
     val scanExec = collect(df.queryExecution.executedPlan) {
       case f: FileSourceScanExecTransformer => f
     }
-    assert(scanExec.size == 1)
-    val mergetreeScan = scanExec(0)
-    assert(ret.apply(0).get(0) == 2)
+    assertResult(1)(scanExec.size)
+    val mergetreeScan = scanExec.head
+    assertResult(2)(ret.apply(0).get(0))
     val marks = mergetreeScan.metrics("selectedMarks").value
-    assert(marks == 2)
+    assertResult(1)(marks)
 
     val directory = new File(dataPath)
     // find a folder whose name is like 48b70783-b3b8-4bf8-9c52-5261aead8e3e_0_006
@@ -1233,11 +1200,11 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
     val scanExec = collect(df.queryExecution.executedPlan) {
       case f: FileSourceScanExecTransformer => f
     }
-    assert(scanExec.size == 1)
-    val mergetreeScan = scanExec(0)
-    assert(ret.apply(0).get(0) == 2)
+    assertResult(1)(scanExec.size)
+    val mergetreeScan = scanExec.head
+    assertResult(2)(ret.apply(0).get(0))
     val marks = mergetreeScan.metrics("selectedMarks").value
-    assert(marks == 1)
+    assertResult(1)(marks)
 
     val directory = new File(dataPath)
     // find a folder whose name is like 48b70783-b3b8-4bf8-9c52-5261aead8e3e_0_006
@@ -1277,18 +1244,16 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
           val scanExec = collect(df.queryExecution.executedPlan) {
             case f: FileSourceScanExecTransformer => f
           }
-          assert(scanExec.size == 1)
+          assertResult(1)(scanExec.size)
 
-          val mergetreeScan = scanExec(0)
+          val mergetreeScan = scanExec.head
           assert(mergetreeScan.nodeName.startsWith("Scan mergetree"))
 
           val fileIndex = mergetreeScan.relation.location.asInstanceOf[TahoeFileIndex]
           val addFiles =
             fileIndex.matchingFiles(Nil, Nil).map(f => f.asInstanceOf[AddMergeTreeParts])
-          assert(addFiles.size == 5)
-          assert(
-            addFiles.map(_.rows).sum
-              == 600572)
+          assertResult(6)(addFiles.size)
+          assertResult(600572)(addFiles.map(_.rows).sum)
       }
     }
 
@@ -1320,7 +1285,7 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
 
     val fileFilter = new WildcardFileFilter("*_0_*")
     var dataFileList = dataPathFile.list(fileFilter)
-    assert(dataFileList.size == 5)
+    assertResult(6)(dataFileList.length)
 
     // re-create the same table
     val dataPath2 = s"$basePath/lineitem_mergetree_5219_s"
@@ -1339,7 +1304,7 @@ class GlutenClickHouseMergeTreePathBasedWriteSuite
     assert(dataPathFile.isDirectory && dataPathFile.isDirectory)
 
     dataFileList = dataPathFile.list(fileFilter)
-    assert(dataFileList.size == 5)
+    assertResult(6)(dataFileList.length)
   }
 }
 // scalastyle:off line.size.limit
diff --git a/backends-clickhouse/src/test/scala/org/apache/gluten/execution/GlutenClickHouseMergeTreeWriteSuite.scala b/backends-clickhouse/src/test/scala/org/apache/gluten/execution/GlutenClickHouseMergeTreeWriteSuite.scala
index 679cea37ba67..70c6553416e2 100644
--- a/backends-clickhouse/src/test/scala/org/apache/gluten/execution/GlutenClickHouseMergeTreeWriteSuite.scala
+++ b/backends-clickhouse/src/test/scala/org/apache/gluten/execution/GlutenClickHouseMergeTreeWriteSuite.scala
@@ -57,6 +57,9 @@ class GlutenClickHouseMergeTreeWriteSuite
       .set(
         "spark.gluten.sql.columnar.backend.ch.runtime_settings.mergetree.merge_after_insert",
         "false")
+      .set(
+        "spark.gluten.sql.columnar.backend.ch.runtime_settings.input_format_parquet_max_block_size",
+        "8192")
   }
 
   override protected def createTPCHNotNullTables(): Unit = {
@@ -128,7 +131,7 @@ class GlutenClickHouseMergeTreeWriteSuite
           case f: FileSourceScanExecTransformer => f
           case w: WholeStageTransformer => w
         }
-        assert(plans.size == 4)
+        assertResult(4)(plans.size)
 
         val mergetreeScan = plans(3).asInstanceOf[FileSourceScanExecTransformer]
         assert(mergetreeScan.nodeName.startsWith("Scan mergetree"))
@@ -140,10 +143,8 @@ class GlutenClickHouseMergeTreeWriteSuite
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).primaryKeyOption.isEmpty)
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).partitionColumns.isEmpty)
         val addFiles = fileIndex.matchingFiles(Nil, Nil).map(f => f.asInstanceOf[AddMergeTreeParts])
-        assert(addFiles.size == 5)
-        assert(
-          addFiles.map(_.rows).sum
-            == 600572)
+        assertResult(6)(addFiles.size)
+        assertResult(600572)(addFiles.map(_.rows).sum)
 
         // GLUTEN-5060: check the unnecessary FilterExec
         val wholeStageTransformer = plans(2).asInstanceOf[WholeStageTransformer]
@@ -200,9 +201,9 @@ class GlutenClickHouseMergeTreeWriteSuite
          | select count(*) from lineitem_mergetree_insertoverwrite
          |
          |""".stripMargin
-    assert(
+    assertResult(300001)(
       // total rows should remain unchanged
-      spark.sql(sql2).collect().apply(0).get(0) == 300001
+      spark.sql(sql2).collect().apply(0).get(0)
     )
   }
 
@@ -251,9 +252,9 @@ class GlutenClickHouseMergeTreeWriteSuite
          | select count(*) from lineitem_mergetree_insertoverwrite2
          |
          |""".stripMargin
-    assert(
+    assertResult(2418)(
       // total rows should remain unchanged
-      spark.sql(sql2).collect().apply(0).get(0) == 2418
+      spark.sql(sql2).collect().apply(0).get(0)
     )
   }
 
@@ -303,9 +304,9 @@ class GlutenClickHouseMergeTreeWriteSuite
            | select count(*) from lineitem_mergetree_insertoverwrite3
            |
            |""".stripMargin
-      assert(
+      assertResult(600572)(
         // total rows should remain unchanged
-        spark.sql(sql2).collect().apply(0).get(0) == 600572
+        spark.sql(sql2).collect().apply(0).get(0)
       )
     }
   }
@@ -357,14 +358,14 @@ class GlutenClickHouseMergeTreeWriteSuite
 
       val df = spark.sql(sql1)
       val result = df.collect()
-      assert(
+      assertResult(1)(
         // in test data, there are only 1 row with l_orderkey = 12647
-        result.apply(0).get(0) == 1
+        result.apply(0).get(0)
       )
       val scanExec = collect(df.queryExecution.executedPlan) {
         case f: FileSourceScanExecTransformer => f
       }
-      assert(scanExec.size == 1)
+      assertResult(1)(scanExec.size)
 
       val mergetreeScan = scanExec.head
       assert(mergetreeScan.nodeName.startsWith("Scan mergetree"))
@@ -376,16 +377,14 @@ class GlutenClickHouseMergeTreeWriteSuite
       assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).primaryKeyOption.isEmpty)
       assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).partitionColumns.isEmpty)
       val addFiles = fileIndex.matchingFiles(Nil, Nil).map(f => f.asInstanceOf[AddMergeTreeParts])
-      assert(
-        addFiles.map(_.rows).sum
-          == 600572)
+      assertResult(600572)(addFiles.map(_.rows).sum)
 
       // 4 parts belong to the first batch
       // 2 parts belong to the second batch (1 actual updated part, 1 passively updated).
-      assert(addFiles.size == 6)
+      assertResult(6)(addFiles.size)
       val filePaths = addFiles.map(_.path).groupBy(name => name.substring(0, name.lastIndexOf("_")))
-      assert(filePaths.size == 2)
-      assert(Array(3, 3).sameElements(filePaths.values.map(paths => paths.size).toArray.sorted))
+      assertResult(2)(filePaths.size)
+      assertResult(Array(2, 4))(filePaths.values.map(paths => paths.size).toArray.sorted)
     }
 
     val sql2 =
@@ -393,9 +392,9 @@ class GlutenClickHouseMergeTreeWriteSuite
          | select count(*) from lineitem_mergetree_update
          |
          |""".stripMargin
-    assert(
+    assertResult(600572)(
       // total rows should remain unchanged
-      spark.sql(sql2).collect().apply(0).get(0) == 600572
+      spark.sql(sql2).collect().apply(0).get(0)
     )
   }
 
@@ -444,8 +443,8 @@ class GlutenClickHouseMergeTreeWriteSuite
                             | select count(*) from lineitem_mergetree_delete
                             |""".stripMargin)
       val result = df.collect()
-      assert(
-        result.apply(0).get(0) == 600571
+      assertResult(600571)(
+        result.apply(0).get(0)
       )
       val scanExec = collect(df.queryExecution.executedPlan) {
         case f: FileSourceScanExecTransformer => f
@@ -455,10 +454,10 @@ class GlutenClickHouseMergeTreeWriteSuite
       val addFiles = fileIndex.matchingFiles(Nil, Nil).map(f => f.asInstanceOf[AddMergeTreeParts])
       // 4 parts belong to the first batch
       // 2 parts belong to the second batch (1 actual updated part, 1 passively updated).
-      assert(addFiles.size == 6)
+      assertResult(6)(addFiles.size)
       val filePaths = addFiles.map(_.path).groupBy(name => name.substring(0, name.lastIndexOf("_")))
-      assert(filePaths.size == 2)
-      assert(Array(3, 3).sameElements(filePaths.values.map(paths => paths.size).toArray.sorted))
+      assertResult(2)(filePaths.size)
+      assertResult(Array(2, 4))(filePaths.values.map(paths => paths.size).toArray.sorted)
     }
 
     {
@@ -468,9 +467,7 @@ class GlutenClickHouseMergeTreeWriteSuite
       val df3 = spark.sql(s"""
                              | select count(*) from lineitem_mergetree_delete
                              |""".stripMargin)
-      assert(
-        df3.collect().apply(0).get(0) == 400089
-      )
+      assertResult(400089)(df3.collect().apply(0).get(0))
     }
   }
 
@@ -512,9 +509,7 @@ class GlutenClickHouseMergeTreeWriteSuite
       val df0 = spark.sql(s"""
                              | select count(*) from lineitem_mergetree_upsert
                              |""".stripMargin)
-      assert(
-        df0.collect().apply(0).get(0) == 600572
-      )
+      assertResult(600572)(df0.collect().apply(0).get(0))
     }
 
     upsertSourceTableAndCheck("lineitem_mergetree_upsert")
@@ -551,18 +546,14 @@ class GlutenClickHouseMergeTreeWriteSuite
       val df1 = spark.sql(s"""
                              | select count(*) from $tableName
                              |""".stripMargin)
-      assert(
-        df1.collect().apply(0).get(0) == 600572 + 3506
-      )
+      assertResult(600572 + 3506)(df1.collect().apply(0).get(0))
     }
     {
       val df2 =
         spark.sql(s"""
                      | select count(*) from $tableName where l_returnflag = 'Z'
                      |""".stripMargin)
-      assert(
-        df2.collect().apply(0).get(0) == 3506
-      )
+      assertResult(3506)(df2.collect().apply(0).get(0))
     }
 
     {
@@ -570,9 +561,7 @@ class GlutenClickHouseMergeTreeWriteSuite
         spark.sql(s"""
                      | select count(*) from $tableName where l_orderkey > 10000000
                      |""".stripMargin)
-      assert(
-        df3.collect().apply(0).get(0) == 3506
-      )
+      assertResult(3506)(df3.collect().apply(0).get(0))
     }
   }
 
@@ -642,33 +631,31 @@ class GlutenClickHouseMergeTreeWriteSuite
         val scanExec = collect(df.queryExecution.executedPlan) {
           case f: FileSourceScanExecTransformer => f
         }
-        assert(scanExec.size == 1)
+        assertResult(1)(scanExec.size)
 
-        val mergetreeScan = scanExec(0)
+        val mergetreeScan = scanExec.head
         assert(mergetreeScan.nodeName.startsWith("Scan mergetree"))
 
         val fileIndex = mergetreeScan.relation.location.asInstanceOf[TahoeFileIndex]
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).clickhouseTableConfigs.nonEmpty)
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).bucketOption.isEmpty)
-        assert(
+        assertResult("l_shipdate,l_orderkey")(
           ClickHouseTableV2
             .getTable(fileIndex.deltaLog)
             .orderByKeyOption
             .get
-            .mkString(",")
-            .equals("l_shipdate,l_orderkey"))
-        assert(
+            .mkString(","))
+        assertResult("l_shipdate")(
           ClickHouseTableV2
             .getTable(fileIndex.deltaLog)
             .primaryKeyOption
             .get
-            .mkString(",")
-            .equals("l_shipdate"))
+            .mkString(","))
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).partitionColumns.isEmpty)
         val addFiles = fileIndex.matchingFiles(Nil, Nil).map(f => f.asInstanceOf[AddMergeTreeParts])
 
-        assert(addFiles.size == 5)
-        assert(addFiles.map(_.rows).sum == 600572)
+        assertResult(6)(addFiles.size)
+        assertResult(600572)(addFiles.map(_.rows).sum)
     }
   }
 
@@ -800,62 +787,56 @@ class GlutenClickHouseMergeTreeWriteSuite
     runTPCHQueryBySQL(1, sqlStr, compareResult = false) {
       df =>
         val result = df.collect()
-        assert(result.size == 4)
-        assert(result(0).getString(0).equals("A"))
-        assert(result(0).getString(1).equals("F"))
-        assert(result(0).getDouble(2) == 3865234.0)
+        assertResult(4)(result.length)
+        assertResult("A")(result(0).getString(0))
+        assertResult("F")(result(0).getString(1))
+        assertResult(3865234.0)(result(0).getDouble(2))
 
-        assert(result(2).getString(0).equals("N"))
-        assert(result(2).getString(1).equals("O"))
-        assert(result(2).getDouble(2) == 7454519.0)
+        assertResult("N")(result(2).getString(0))
+        assertResult("O")(result(2).getString(1))
+        assertResult(7454519.0)(result(2).getDouble(2))
 
         val scanExec = collect(df.queryExecution.executedPlan) {
           case f: FileSourceScanExecTransformer => f
         }
-        assert(scanExec.size == 1)
+        assertResult(1)(scanExec.size)
 
-        val mergetreeScan = scanExec(0)
+        val mergetreeScan = scanExec.head
         assert(mergetreeScan.nodeName.startsWith("Scan mergetree"))
-        assert(mergetreeScan.metrics("numFiles").value == 3745)
+        assertResult(3745)(mergetreeScan.metrics("numFiles").value)
 
         val fileIndex = mergetreeScan.relation.location.asInstanceOf[TahoeFileIndex]
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).clickhouseTableConfigs.nonEmpty)
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).bucketOption.isEmpty)
-        assert(
+        assertResult("l_orderkey")(
           ClickHouseTableV2
             .getTable(fileIndex.deltaLog)
             .orderByKeyOption
             .get
-            .mkString(",")
-            .equals("l_orderkey"))
-        assert(
+            .mkString(","))
+        assertResult("l_orderkey")(
           ClickHouseTableV2
             .getTable(fileIndex.deltaLog)
             .primaryKeyOption
             .get
-            .mkString(",")
-            .equals("l_orderkey"))
-        assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).partitionColumns.size == 2)
-        assert(
+            .mkString(","))
+        assertResult(2)(ClickHouseTableV2.getTable(fileIndex.deltaLog).partitionColumns.size)
+        assertResult("l_shipdate")(
           ClickHouseTableV2
             .getTable(fileIndex.deltaLog)
-            .partitionColumns(0)
-            .equals("l_shipdate"))
-        assert(
+            .partitionColumns
+            .head)
+        assertResult("l_returnflag")(
           ClickHouseTableV2
             .getTable(fileIndex.deltaLog)
-            .partitionColumns(1)
-            .equals("l_returnflag"))
+            .partitionColumns(1))
         val addFiles = fileIndex.matchingFiles(Nil, Nil).map(f => f.asInstanceOf[AddMergeTreeParts])
 
-        assert(addFiles.size == 3836)
-        assert(addFiles.map(_.rows).sum == 605363)
-        assert(
-          addFiles.filter(_.partitionValues.get("l_shipdate").get.equals("1992-06-01")).size == 2)
-        assert(
-          addFiles.filter(_.partitionValues.get("l_shipdate").get.equals("1993-01-01")).size == 4)
-        assert(
-          addFiles.filter(_.partitionValues.get("l_shipdate").get.equals("1995-01-21")).size == 3)
+        assertResult(3836)(addFiles.size)
+        assertResult(605363)(addFiles.map(_.rows).sum)
+        assertResult(2)(addFiles.count(_.partitionValues("l_shipdate").equals("1992-06-01")))
+        assertResult(4)(addFiles.count(_.partitionValues("l_shipdate").equals("1993-01-01")))
+        assertResult(3)(addFiles.count(_.partitionValues("l_shipdate").equals("1995-01-21")))
     }
   }
 
@@ -927,49 +908,40 @@ class GlutenClickHouseMergeTreeWriteSuite
         val scanExec = collect(df.queryExecution.executedPlan) {
           case f: FileSourceScanExecTransformer => f
         }
-        assert(scanExec.size == 1)
+        assertResult(1)(scanExec.size)
 
-        val mergetreeScan = scanExec(0)
+        val mergetreeScan = scanExec.head
         assert(mergetreeScan.nodeName.startsWith("Scan mergetree"))
 
         val fileIndex = mergetreeScan.relation.location.asInstanceOf[TahoeFileIndex]
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).clickhouseTableConfigs.nonEmpty)
-        assert(!ClickHouseTableV2.getTable(fileIndex.deltaLog).bucketOption.isEmpty)
+        assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).bucketOption.isDefined)
         if (sparkVersion.equals("3.2")) {
           assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).orderByKeyOption.isEmpty)
         } else {
-          assert(
+          assertResult("l_partkey,l_returnflag")(
             ClickHouseTableV2
               .getTable(fileIndex.deltaLog)
               .orderByKeyOption
               .get
-              .mkString(",")
-              .equals("l_partkey,l_returnflag"))
+              .mkString(","))
         }
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).primaryKeyOption.isEmpty)
-        assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).partitionColumns.size == 1)
-        assert(
+        assertResult(1)(ClickHouseTableV2.getTable(fileIndex.deltaLog).partitionColumns.size)
+        assertResult("l_shipdate")(
           ClickHouseTableV2
             .getTable(fileIndex.deltaLog)
-            .partitionColumns(0)
-            .equals("l_shipdate"))
+            .partitionColumns
+            .head)
         val addFiles = fileIndex.matchingFiles(Nil, Nil).map(f => f.asInstanceOf[AddMergeTreeParts])
 
-        assert(addFiles.size == 10089)
-        assert(addFiles.map(_.rows).sum == 600572)
-        assert(
-          addFiles.filter(_.partitionValues.get("l_shipdate").get.equals("1992-06-01")).size == 4)
-        assert(
-          addFiles.filter(_.partitionValues.get("l_shipdate").get.equals("1993-01-01")).size == 4)
-        assert(
-          addFiles.filter(_.partitionValues.get("l_shipdate").get.equals("1995-01-21")).size == 4)
-        assert(
-          addFiles
-            .filter(
-              f =>
-                f.partitionValues.get("l_shipdate").get.equals("1995-01-21") && f.bucketNum.equals(
-                  "00000"))
-            .size == 1)
+        assertResult(10089)(addFiles.size)
+        assertResult(600572)(addFiles.map(_.rows).sum)
+        assertResult(4)(addFiles.count(_.partitionValues("l_shipdate").equals("1992-06-01")))
+        assertResult(4)(addFiles.count(_.partitionValues("l_shipdate").equals("1993-01-01")))
+        assertResult(4)(addFiles.count(_.partitionValues("l_shipdate").equals("1995-01-21")))
+        assertResult(1)(addFiles.count(
+          f => f.partitionValues("l_shipdate").equals("1995-01-21") && f.bucketNum.equals("00000")))
     }
     // check part pruning effect of filter on bucket column
     val df = spark.sql(s"""
@@ -984,7 +956,7 @@ class GlutenClickHouseMergeTreeWriteSuite
       .flatMap(partition => partition.asInstanceOf[GlutenMergeTreePartition].partList)
       .map(_.name)
       .distinct
-    assert(touchedParts.size == 1)
+    assertResult(1)(touchedParts.size)
 
     // test upsert on partitioned & bucketed table
     upsertSourceTableAndCheck("lineitem_mergetree_bucket")
@@ -996,9 +968,7 @@ class GlutenClickHouseMergeTreeWriteSuite
     val df0 = spark.sql(s"""
                            | select count(*) from lineitem_mergetree_bucket
                            |""".stripMargin)
-    assert(
-      df0.collect().apply(0).get(0) == 3
-    )
+    assertResult(3)(df0.collect().apply(0).get(0))
 
   }
 
@@ -1065,40 +1035,40 @@ class GlutenClickHouseMergeTreeWriteSuite
         warehouse + "/" + tableName
       }
       val deletedPath = new File(deletedPathStr)
-      assert(deletedPath.exists() == exceptedExists)
+      assertResult(exceptedExists)(deletedPath.exists())
     }
 
     // test non external table
     var tableName = "lineitem_mergetree_drop"
     var tableLocation = ""
     createAndDropTable(tableName, tableLocation)
-    checkTableExists(tableName, tableLocation, false)
+    checkTableExists(tableName, tableLocation, exceptedExists = false)
 
     // test external table
     tableName = "lineitem_mergetree_external_drop"
-    createAndDropTable(tableName, tableLocation, true)
-    checkTableExists(tableName, tableLocation, false)
+    createAndDropTable(tableName, tableLocation, isExternal = true)
+    checkTableExists(tableName, tableLocation, exceptedExists = false)
 
     // test table with the specified location
     tableName = "lineitem_mergetree_location_drop"
     tableLocation = basePath + "/" + tableName
     createAndDropTable(tableName, tableLocation)
-    checkTableExists(tableName, tableLocation, true)
+    checkTableExists(tableName, tableLocation, exceptedExists = true)
 
     tableName = "lineitem_mergetree_external_location_drop"
     tableLocation = basePath + "/" + tableName
-    createAndDropTable(tableName, tableLocation, true)
-    checkTableExists(tableName, tableLocation, true)
+    createAndDropTable(tableName, tableLocation, isExternal = true)
+    checkTableExists(tableName, tableLocation, exceptedExists = true)
 
     tableName = "lineitem_mergetree_location_purge"
     tableLocation = basePath + "/" + tableName
     createAndDropTable(tableName, tableLocation, purgeTable = true)
-    checkTableExists(tableName, tableLocation, false)
+    checkTableExists(tableName, tableLocation, exceptedExists = false)
 
     tableName = "lineitem_mergetree_external_location_purge"
     tableLocation = basePath + "/" + tableName
-    createAndDropTable(tableName, tableLocation, true, true)
-    checkTableExists(tableName, tableLocation, false)
+    createAndDropTable(tableName, tableLocation, isExternal = true, purgeTable = true)
+    checkTableExists(tableName, tableLocation, exceptedExists = false)
   }
 
   test("test mergetree CTAS simple") {
@@ -1143,9 +1113,9 @@ class GlutenClickHouseMergeTreeWriteSuite
         val scanExec = collect(df.queryExecution.executedPlan) {
           case f: FileSourceScanExecTransformer => f
         }
-        assert(scanExec.size == 1)
+        assertResult(1)(scanExec.size)
 
-        val mergetreeScan = scanExec(0)
+        val mergetreeScan = scanExec.head
         assert(mergetreeScan.nodeName.startsWith("Scan mergetree"))
 
         val fileIndex = mergetreeScan.relation.location.asInstanceOf[TahoeFileIndex]
@@ -1155,10 +1125,8 @@ class GlutenClickHouseMergeTreeWriteSuite
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).primaryKeyOption.isEmpty)
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).partitionColumns.isEmpty)
         val addFiles = fileIndex.matchingFiles(Nil, Nil).map(f => f.asInstanceOf[AddMergeTreeParts])
-        assert(addFiles.size == 5)
-        assert(
-          addFiles.map(_.rows).sum
-            == 600572)
+        assertResult(6)(addFiles.size)
+        assertResult(600572)(addFiles.map(_.rows).sum)
     }
   }
 
@@ -1289,9 +1257,9 @@ class GlutenClickHouseMergeTreeWriteSuite
          |
          |""".stripMargin
 
-    assert(
+    assertResult("R")(
       // total rows should remain unchanged
-      spark.sql(sqlStr2).collect().apply(0).get(0) == "R"
+      spark.sql(sqlStr2).collect().apply(0).get(0)
     )
 
     // test select *
@@ -1359,40 +1327,38 @@ class GlutenClickHouseMergeTreeWriteSuite
         val scanExec = collect(df.queryExecution.executedPlan) {
           case f: FileSourceScanExecTransformer => f
         }
-        assert(scanExec.size == 1)
+        assertResult(1)(scanExec.size)
 
-        val mergetreeScan = scanExec(0)
+        val mergetreeScan = scanExec.head
         assert(mergetreeScan.nodeName.startsWith("Scan mergetree"))
 
         val fileIndex = mergetreeScan.relation.location.asInstanceOf[TahoeFileIndex]
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).clickhouseTableConfigs.nonEmpty)
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).bucketOption.isEmpty)
-        assert(
+        assertResult("l_shipdate,l_orderkey")(
           ClickHouseTableV2
             .getTable(fileIndex.deltaLog)
             .orderByKeyOption
             .get
-            .mkString(",")
-            .equals("l_shipdate,l_orderkey"))
-        assert(
+            .mkString(","))
+        assertResult("l_shipdate")(
           ClickHouseTableV2
             .getTable(fileIndex.deltaLog)
             .primaryKeyOption
             .get
-            .mkString(",")
-            .equals("l_shipdate"))
+            .mkString(","))
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).partitionColumns.isEmpty)
         val addFiles = fileIndex.matchingFiles(Nil, Nil).map(f => f.asInstanceOf[AddMergeTreeParts])
 
-        assert(addFiles.size == 5)
-        assert(addFiles.map(_.rows).sum == 600572)
+        assertResult(6)(addFiles.size)
+        assertResult(600572)(addFiles.map(_.rows).sum)
 
         val plans = collect(df.queryExecution.executedPlan) {
           case scanExec: BasicScanExecTransformer => scanExec
         }
-        assert(plans.size == 1)
-        assert(plans(0).metrics("selectedMarksPk").value === 15)
-        assert(plans(0).metrics("totalMarksPk").value === 74)
+        assertResult(1)(plans.size)
+        assertResult(17)(plans.head.metrics("selectedMarksPk").value)
+        assertResult(74)(plans.head.metrics("totalMarksPk").value)
     }
   }
 
@@ -1447,21 +1413,20 @@ class GlutenClickHouseMergeTreeWriteSuite
         val scanExec = collect(df.queryExecution.executedPlan) {
           case f: FileSourceScanExecTransformer => f
         }
-        assert(scanExec.size == 1)
+        assertResult(1)(scanExec.size)
 
-        val mergetreeScan = scanExec(0)
+        val mergetreeScan = scanExec.head
         assert(mergetreeScan.nodeName.startsWith("Scan mergetree"))
 
         val fileIndex = mergetreeScan.relation.location.asInstanceOf[TahoeFileIndex]
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).clickhouseTableConfigs.nonEmpty)
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).bucketOption.isEmpty)
-        assert(
+        assertResult("l_shipdate")(
           ClickHouseTableV2
             .getTable(fileIndex.deltaLog)
             .orderByKeyOption
             .get
-            .mkString(",")
-            .equals("l_shipdate"))
+            .mkString(","))
         assert(
           ClickHouseTableV2
             .getTable(fileIndex.deltaLog)
@@ -1470,15 +1435,15 @@ class GlutenClickHouseMergeTreeWriteSuite
         assert(ClickHouseTableV2.getTable(fileIndex.deltaLog).partitionColumns.isEmpty)
         val addFiles = fileIndex.matchingFiles(Nil, Nil).map(f => f.asInstanceOf[AddMergeTreeParts])
 
-        assert(addFiles.size == 5)
-        assert(addFiles.map(_.rows).sum == 600572)
+        assertResult(6)(addFiles.size)
+        assertResult(600572)(addFiles.map(_.rows).sum)
 
         val plans = collect(df.queryExecution.executedPlan) {
           case scanExec: BasicScanExecTransformer => scanExec
         }
-        assert(plans.size == 1)
-        assert(plans(0).metrics("selectedMarksPk").value === 15)
-        assert(plans(0).metrics("totalMarksPk").value === 74)
+        assertResult(1)(plans.size)
+        assertResult(17)(plans.head.metrics("selectedMarksPk").value)
+        assertResult(74)(plans.head.metrics("totalMarksPk").value)
     }
   }
 
@@ -1527,21 +1492,21 @@ class GlutenClickHouseMergeTreeWriteSuite
     runSql(sqlStr)(
       df => {
         val result = df.collect()
-        assert(result.size == 1)
-        assert(result(0).getLong(0) == 10)
+        assertResult(1)(result.length)
+        assertResult(10)(result(0).getLong(0))
 
         val scanExec = collect(df.queryExecution.executedPlan) {
           case f: FileSourceScanExecTransformer => f
         }
-        assert(scanExec.size == 1)
+        assertResult(1)(scanExec.size)
 
-        val mergetreeScan = scanExec(0)
+        val mergetreeScan = scanExec.head
         assert(mergetreeScan.nodeName.startsWith("Scan mergetree"))
 
         val fileIndex = mergetreeScan.relation.location.asInstanceOf[TahoeFileIndex]
         val addFiles = fileIndex.matchingFiles(Nil, Nil).map(f => f.asInstanceOf[AddMergeTreeParts])
-        assert(addFiles.size == 1)
-        assert(addFiles(0).rows == 10)
+        assertResult(1)(addFiles.size)
+        assertResult(10)(addFiles.head.rows)
       })
   }
 
@@ -1585,16 +1550,16 @@ class GlutenClickHouseMergeTreeWriteSuite
       val scanExec = collect(df.queryExecution.executedPlan) {
         case f: FileSourceScanExecTransformer => f
       }
-      assert(scanExec.size == 1)
+      assertResult(1)(scanExec.size)
 
-      val mergetreeScan = scanExec(0)
+      val mergetreeScan = scanExec.head
       assert(mergetreeScan.nodeName.startsWith("Scan mergetree"))
 
       val fileIndex = mergetreeScan.relation.location.asInstanceOf[TahoeFileIndex]
       val addFiles = fileIndex.matchingFiles(Nil, Nil).map(f => f.asInstanceOf[AddMergeTreeParts])
-      assert(
-        (addFiles.map(_.marks).sum - addFiles.size) == mergetreeScan.metrics("totalMarksPk").value)
-      assert(mergetreeScan.metrics("selectedMarksPk").value == exceptedCnt)
+      assertResult(mergetreeScan.metrics("totalMarksPk").value)(
+        addFiles.map(_.marks).sum - addFiles.size)
+      assertResult(exceptedCnt)(mergetreeScan.metrics("selectedMarksPk").value)
     }
 
     val sqlStr1 =
@@ -1609,8 +1574,8 @@ class GlutenClickHouseMergeTreeWriteSuite
     runSql(sqlStr1)(
       df => {
         val result = df.collect()
-        assert(result.size == 1)
-        assert(result(0).getDouble(0).toString.substring(0, 6).equals("2.6480"))
+        assertResult(1)(result.length)
+        assertResult("2.6480")(result(0).getDouble(0).toString.substring(0, 6))
 
         checkSelectedMarksCnt(df, 34)
       })
@@ -1627,10 +1592,10 @@ class GlutenClickHouseMergeTreeWriteSuite
     runSql(sqlStr2)(
       df => {
         val result = df.collect()
-        assert(result.size == 1)
-        assert(result(0).getDouble(0).toString.substring(0, 6).equals("5.3379"))
+        assertResult(1)(result.length)
+        assertResult("5.3379")(result(0).getDouble(0).toString.substring(0, 6))
 
-        checkSelectedMarksCnt(df, 24)
+        checkSelectedMarksCnt(df, 29)
       })
   }
 
@@ -1666,18 +1631,16 @@ class GlutenClickHouseMergeTreeWriteSuite
           val scanExec = collect(df.queryExecution.executedPlan) {
             case f: FileSourceScanExecTransformer => f
           }
-          assert(scanExec.size == 1)
+          assertResult(1)(scanExec.size)
 
-          val mergetreeScan = scanExec(0)
+          val mergetreeScan = scanExec.head
           assert(mergetreeScan.nodeName.startsWith("Scan mergetree"))
 
           val fileIndex = mergetreeScan.relation.location.asInstanceOf[TahoeFileIndex]
           val addFiles =
             fileIndex.matchingFiles(Nil, Nil).map(f => f.asInstanceOf[AddMergeTreeParts])
-          assert(addFiles.size == 5)
-          assert(
-            addFiles.map(_.rows).sum
-              == 600572)
+          assertResult(6)(addFiles.size)
+          assertResult(600572)(addFiles.map(_.rows).sum)
       }
     }
 
@@ -1715,7 +1678,7 @@ class GlutenClickHouseMergeTreeWriteSuite
 
     val fileFilter = new WildcardFileFilter("*_0_*")
     var dataFileList = dataPath.list(fileFilter)
-    assert(dataFileList.size == 5)
+    assertResult(6)(dataFileList.length)
 
     // test with the normal table
     spark.sql(s"""
@@ -1796,7 +1759,7 @@ class GlutenClickHouseMergeTreeWriteSuite
     assert(dataPath.isDirectory && dataPath.isDirectory)
 
     dataFileList = dataPath.list(fileFilter)
-    assert(dataFileList.size == 5)
+    assertResult(6)(dataFileList.length)
 
     // re-create the same table
     for (i <- 0 until 10) {
@@ -1818,7 +1781,7 @@ class GlutenClickHouseMergeTreeWriteSuite
     assert(dataPath.isDirectory && dataPath.isDirectory)
 
     dataFileList = dataPath.list(fileFilter)
-    assert(dataFileList.size == 5)
+    assertResult(6)(dataFileList.length)
   }
 
   test("test mergetree with primary keys filter pruning by driver") {
@@ -1872,22 +1835,22 @@ class GlutenClickHouseMergeTreeWriteSuite
     Seq(("true", 2), ("false", 3)).foreach(
       conf => {
         withSQLConf(
-          ("spark.gluten.sql.columnar.backend.ch.runtime_settings.enabled_driver_filter_mergetree_index" -> conf._1)) {
+          "spark.gluten.sql.columnar.backend.ch.runtime_settings.enabled_driver_filter_mergetree_index" -> conf._1) {
           runTPCHQueryBySQL(6, sqlStr) {
             df =>
               val scanExec = collect(df.queryExecution.executedPlan) {
                 case f: FileSourceScanExecTransformer => f
               }
-              assert(scanExec.size == 1)
+              assertResult(1)(scanExec.size)
 
-              val mergetreeScan = scanExec(0)
+              val mergetreeScan = scanExec.head
               assert(mergetreeScan.nodeName.startsWith("Scan mergetree"))
 
               val plans = collect(df.queryExecution.executedPlan) {
                 case scanExec: BasicScanExecTransformer => scanExec
               }
-              assert(plans.size == 1)
-              assert(plans(0).getSplitInfos.size == conf._2)
+              assertResult(1)(plans.size)
+              assertResult(conf._2)(plans.head.getSplitInfos.size)
           }
         }
       })
@@ -1990,14 +1953,14 @@ class GlutenClickHouseMergeTreeWriteSuite
     Seq(("true", 2), ("false", 2)).foreach(
       conf => {
         withSQLConf(
-          ("spark.gluten.sql.columnar.backend.ch.runtime_settings.enabled_driver_filter_mergetree_index" -> conf._1)) {
+          "spark.gluten.sql.columnar.backend.ch.runtime_settings.enabled_driver_filter_mergetree_index" -> conf._1) {
           runTPCHQueryBySQL(12, sqlStr) {
             df =>
               val scanExec = collect(df.queryExecution.executedPlan) {
                 case f: BasicScanExecTransformer => f
               }
-              assert(scanExec.size == 2)
-              assert(scanExec(1).getSplitInfos.size == conf._2)
+              assertResult(2)(scanExec.size)
+              assertResult(conf._2)(scanExec(1).getSplitInfos.size)
           }
         }
       })
diff --git a/backends-clickhouse/src/test/scala/org/apache/gluten/execution/GlutenClickHouseTableAfterRestart.scala b/backends-clickhouse/src/test/scala/org/apache/gluten/execution/GlutenClickHouseTableAfterRestart.scala
index ab11c1e0c201..f9e831cb4aa7 100644
--- a/backends-clickhouse/src/test/scala/org/apache/gluten/execution/GlutenClickHouseTableAfterRestart.scala
+++ b/backends-clickhouse/src/test/scala/org/apache/gluten/execution/GlutenClickHouseTableAfterRestart.scala
@@ -61,6 +61,9 @@ class GlutenClickHouseTableAfterRestart
       .set(
         "spark.gluten.sql.columnar.backend.ch.runtime_settings.mergetree.merge_after_insert",
         "false")
+      .set(
+        "spark.gluten.sql.columnar.backend.ch.runtime_settings.input_format_parquet_max_block_size",
+        "8192")
   }
 
   override protected def createTPCHNotNullTables(): Unit = {
@@ -180,9 +183,9 @@ class GlutenClickHouseTableAfterRestart
       // for this run, missing count should not increase
       runTPCHQueryBySQL(1, sqlStr)(_ => {})
       val stats1 = ClickhouseSnapshot.deltaScanCache.stats()
-      assert(stats1.missCount() - oldMissingCount1 == 0)
+      assertResult(oldMissingCount1)(stats1.missCount())
       val stats2 = ClickhouseSnapshot.addFileToAddMTPCache.stats()
-      assert(stats2.missCount() - oldMissingCount2 == 0)
+      assertResult(oldMissingCount2)(stats2.missCount())
     }
 
     val oldMissingCount1 = ClickhouseSnapshot.deltaScanCache.stats().missCount()
@@ -194,10 +197,9 @@ class GlutenClickHouseTableAfterRestart
 
     // after restart, additionally check stats of delta scan cache
     val stats1 = ClickhouseSnapshot.deltaScanCache.stats()
-    assert(stats1.missCount() - oldMissingCount1 == 1)
+    assertResult(oldMissingCount1 + 1)(stats1.missCount())
     val stats2 = ClickhouseSnapshot.addFileToAddMTPCache.stats()
-    assert(stats2.missCount() - oldMissingCount2 == 5)
-
+    assertResult(oldMissingCount2 + 6)(stats2.missCount())
   }
 
   test("test optimize after restart") {
@@ -222,7 +224,8 @@ class GlutenClickHouseTableAfterRestart
     restartSpark()
 
     spark.sql("optimize table_restart_optimize")
-    assert(spark.sql("select count(*) from table_restart_optimize").collect().apply(0).get(0) == 4)
+    assertResult(4)(
+      spark.sql("select count(*) from table_restart_optimize").collect().apply(0).get(0))
   }
 
   test("test vacuum after restart") {
@@ -250,7 +253,8 @@ class GlutenClickHouseTableAfterRestart
 
     spark.sql("vacuum table_restart_vacuum")
 
-    assert(spark.sql("select count(*) from table_restart_vacuum").collect().apply(0).get(0) == 4)
+    assertResult(4)(
+      spark.sql("select count(*) from table_restart_vacuum").collect().apply(0).get(0))
   }
 
   test("test update after restart") {
@@ -276,7 +280,8 @@ class GlutenClickHouseTableAfterRestart
 
     spark.sql("update table_restart_update set name = 'tom' where id = 1")
 
-    assert(spark.sql("select count(*) from table_restart_update").collect().apply(0).get(0) == 4)
+    assertResult(4)(
+      spark.sql("select count(*) from table_restart_update").collect().apply(0).get(0))
   }
 
   test("test delete after restart") {
@@ -302,7 +307,8 @@ class GlutenClickHouseTableAfterRestart
 
     spark.sql("delete from table_restart_delete where where id = 1")
 
-    assert(spark.sql("select count(*) from table_restart_delete").collect().apply(0).get(0) == 2)
+    assertResult(2)(
+      spark.sql("select count(*) from table_restart_delete").collect().apply(0).get(0))
   }
 
   test("test drop after restart") {
diff --git a/backends-velox/src/test/scala/org/apache/gluten/execution/TestOperator.scala b/backends-velox/src/test/scala/org/apache/gluten/execution/TestOperator.scala
index 3cf485aac06b..a892b6f313a4 100644
--- a/backends-velox/src/test/scala/org/apache/gluten/execution/TestOperator.scala
+++ b/backends-velox/src/test/scala/org/apache/gluten/execution/TestOperator.scala
@@ -157,6 +157,71 @@ class TestOperator extends VeloxWholeStageTransformerSuite with AdaptiveSparkPla
     checkLengthAndPlan(df, 60141)
   }
 
+  test("not in") {
+    // integral type
+    val df = runQueryAndCompare(
+      "select l_orderkey from lineitem " +
+        "where l_partkey not in (1552, 674, 1062)") {
+      checkGlutenOperatorMatch[FileSourceScanExecTransformer]
+    }
+    checkLengthAndPlan(df, 60053)
+
+    val df2 = runQueryAndCompare(
+      "select l_orderkey from lineitem " +
+        "where l_partkey not in (1552, 674) and l_partkey not in (1062)") {
+      checkGlutenOperatorMatch[FileSourceScanExecTransformer]
+    }
+    checkLengthAndPlan(df2, 60053)
+
+    val df3 = runQueryAndCompare(
+      "select l_orderkey from lineitem " +
+        "where l_partkey not in (1552, 674) and l_partkey != 1062") {
+      checkGlutenOperatorMatch[FileSourceScanExecTransformer]
+    }
+    checkLengthAndPlan(df3, 60053)
+
+    // string type
+    val df4 =
+      runQueryAndCompare("select o_orderstatus from orders where o_orderstatus not in ('O', 'F')") {
+        checkGlutenOperatorMatch[FileSourceScanExecTransformer]
+      }
+    checkLengthAndPlan(df4, 363)
+
+    // bool type
+    withTable("t") {
+      sql("create table t (id int, b boolean) using parquet")
+      sql("insert into t values (1, true), (2, false), (3, null)")
+      runQueryAndCompare("select * from t where b not in (true)") {
+        checkGlutenOperatorMatch[FileSourceScanExecTransformer]
+      }
+
+      runQueryAndCompare("select * from t where b not in (true, false)") {
+        checkGlutenOperatorMatch[FileSourceScanExecTransformer]
+      }
+    }
+
+    // mix not-in with range
+    runQueryAndCompare(
+      "select l_orderkey from lineitem " +
+        "where l_partkey not in (1552, 674) and l_partkey >= 1552") {
+      checkGlutenOperatorMatch[FileSourceScanExecTransformer]
+    }
+
+    // mix not-in with in
+    runQueryAndCompare(
+      "select l_orderkey from lineitem " +
+        "where l_partkey not in (1552, 674) and l_partkey in (1552)") {
+      checkGlutenOperatorMatch[FileSourceScanExecTransformer]
+    }
+
+    // not-in with or relation
+    runQueryAndCompare(
+      "select l_orderkey from lineitem " +
+        "where l_partkey not in (1552, 674) or l_partkey in (1552)") {
+      checkGlutenOperatorMatch[FileSourceScanExecTransformer]
+    }
+  }
+
   test("coalesce") {
     var df = runQueryAndCompare(
       "select l_orderkey, coalesce(l_comment, 'default_val') " +
diff --git a/cpp-ch/CMakeLists.txt b/cpp-ch/CMakeLists.txt
index 0c41f494d2a1..1ef19b3b5651 100644
--- a/cpp-ch/CMakeLists.txt
+++ b/cpp-ch/CMakeLists.txt
@@ -16,7 +16,9 @@ cmake_minimum_required(VERSION 3.20)
 
 file(READ ${CMAKE_CURRENT_SOURCE_DIR}/clickhouse.version CH_VERSION)
 
-set(CH_SOURCE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/ClickHouse CACHE STRING "ClickHouse source dir")
+set(CH_SOURCE_DIR
+    ${CMAKE_CURRENT_SOURCE_DIR}/ClickHouse
+    CACHE STRING "ClickHouse source dir")
 string(REGEX REPLACE ".*CH_ORG=([^\n]+).*" "\\1" CH_ORG "${CH_VERSION}")
 string(REGEX REPLACE ".*CH_BRANCH=([^\n]+).*" "\\1" CH_BRANCH "${CH_VERSION}")
 string(REGEX REPLACE ".*CH_COMMIT=([^\n]+).*" "\\1" CH_COMMIT "${CH_VERSION}")
@@ -27,93 +29,93 @@ message("CH_COMMIT=${CH_COMMIT}")
 
 project(libch LANGUAGES C CXX ASM)
 file(GLOB clickhouse_files "${CH_SOURCE_DIR}/*")
-if ("${CH_SOURCE_DIR}" STREQUAL "${CMAKE_SOURCE_DIR}/ClickHouse")
-    if (NOT clickhouse_files)
-        execute_process(COMMAND git clone -b ${CH_BRANCH} --depth 3 https://github.com/${CH_ORG}/ClickHouse.git ${CH_SOURCE_DIR} COMMAND_ERROR_IS_FATAL ANY)
-        execute_process(COMMAND git reset --hard ${CH_COMMIT} WORKING_DIRECTORY ${CH_SOURCE_DIR} COMMAND_ERROR_IS_FATAL ANY)
-        execute_process(COMMAND git submodule update --init --force --depth 1 WORKING_DIRECTORY ${CH_SOURCE_DIR} COMMAND_ERROR_IS_FATAL ANY)
-    else()
-        execute_process(COMMAND git fetch origin ${CH_BRANCH} --depth 3 WORKING_DIRECTORY ${CH_SOURCE_DIR} COMMAND_ERROR_IS_FATAL ANY)
-        execute_process(COMMAND git checkout ${CH_BRANCH} WORKING_DIRECTORY ${CH_SOURCE_DIR} COMMAND_ERROR_IS_FATAL ANY)
-        execute_process(COMMAND git reset --hard ${CH_COMMIT} WORKING_DIRECTORY ${CH_SOURCE_DIR} COMMAND_ERROR_IS_FATAL ANY)
-        execute_process(COMMAND git submodule update --init --recursive --force --depth 1 WORKING_DIRECTORY ${CH_SOURCE_DIR} COMMAND_ERROR_IS_FATAL ANY)
-    endif()
+if("${CH_SOURCE_DIR}" STREQUAL "${CMAKE_SOURCE_DIR}/ClickHouse")
+  if(NOT clickhouse_files)
+    execute_process(
+      COMMAND
+        git clone -b ${CH_BRANCH} --depth 3
+        https://github.com/${CH_ORG}/ClickHouse.git ${CH_SOURCE_DIR}
+        COMMAND_ERROR_IS_FATAL ANY)
+    execute_process(
+      COMMAND git reset --hard ${CH_COMMIT}
+      WORKING_DIRECTORY ${CH_SOURCE_DIR} COMMAND_ERROR_IS_FATAL ANY)
+    execute_process(
+      COMMAND git submodule update --init --force --depth 1
+      WORKING_DIRECTORY ${CH_SOURCE_DIR} COMMAND_ERROR_IS_FATAL ANY)
+  else()
+    execute_process(
+      COMMAND git fetch origin ${CH_BRANCH} --depth 3
+      WORKING_DIRECTORY ${CH_SOURCE_DIR} COMMAND_ERROR_IS_FATAL ANY)
+    execute_process(
+      COMMAND git checkout ${CH_BRANCH}
+      WORKING_DIRECTORY ${CH_SOURCE_DIR} COMMAND_ERROR_IS_FATAL ANY)
+    execute_process(
+      COMMAND git reset --hard ${CH_COMMIT}
+      WORKING_DIRECTORY ${CH_SOURCE_DIR} COMMAND_ERROR_IS_FATAL ANY)
+    execute_process(
+      COMMAND git submodule update --init --recursive --force --depth 1
+      WORKING_DIRECTORY ${CH_SOURCE_DIR} COMMAND_ERROR_IS_FATAL ANY)
+  endif()
 else()
-    if (NOT clickhouse_files)
-        # Checking out *all* submodules takes > 5 min. Therefore, the smoke build ("FastTest") in CI initializes only the set of
-        # submodules minimally needed for a build and we cannot assume here that all submodules are populated.
-        message(ERROR "clickhouse ${CH_SOURCE_DIR} is missing or empty. to fix try run:")
-        message(STATUS "    git clone --recursive --depth 1 https://github.com/Kyligence/ClickHouse.git ${CMAKE_SOURCE_DIR}")
-    endif()
+  if(NOT clickhouse_files)
+    # Checking out *all* submodules takes > 5 min. Therefore, the smoke build
+    # ("FastTest") in CI initializes only the set of submodules minimally needed
+    # for a build and we cannot assume here that all submodules are populated.
+    message(ERROR
+            "clickhouse ${CH_SOURCE_DIR} is missing or empty. to fix try run:")
+    message(
+      STATUS
+        "    git clone --recursive --depth 1 https://github.com/Kyligence/ClickHouse.git ${CMAKE_SOURCE_DIR}"
+    )
+  endif()
 endif()
 
-if (EXISTS "${CH_SOURCE_DIR}/utils/extern-local-engine")
-    execute_process(COMMAND rm -rf ${CH_SOURCE_DIR}/utils/extern-local-engine)
-endif ()
-execute_process(COMMAND ln -s ${CMAKE_CURRENT_SOURCE_DIR}/local-engine ${CH_SOURCE_DIR}/utils/extern-local-engine COMMAND_ERROR_IS_FATAL ANY)
+if(EXISTS "${CH_SOURCE_DIR}/utils/extern-local-engine")
+  execute_process(COMMAND rm -rf ${CH_SOURCE_DIR}/utils/extern-local-engine)
+endif()
+execute_process(
+  COMMAND ln -s ${CMAKE_CURRENT_SOURCE_DIR}/local-engine
+          ${CH_SOURCE_DIR}/utils/extern-local-engine COMMAND_ERROR_IS_FATAL ANY)
 
-# execute_process(COMMAND find ${CMAKE_CURRENT_SOURCE_DIR}/local-engine -regex '.*\.\(c\|cpp\|h\)' -exec clang-format-15 --verbose -i --style=file -i {} \;)
+# execute_process(COMMAND find ${CMAKE_CURRENT_SOURCE_DIR}/local-engine -regex
+# '.*\.\(c\|cpp\|h\)' -exec clang-format-15 --verbose -i --style=file -i {} \;)
 
 set(CH_BINARY_DIR "${CMAKE_CURRENT_SOURCE_DIR}/build")
 option(ENABLE_CPP_TEST "Build CPP Unit test" OFF)
 
-if (ENABLE_CPP_TEST)
-add_custom_command(
-        USES_TERMINAL
-        COMMAND
-        bash -c
-        \"cmake -DCMAKE_C_COMPILER=${CMAKE_C_COMPILER}
-        -DCMAKE_CXX_COMPILER=${CMAKE_CXX_COMPILER}
-        -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE}
-        -DENABLE_PROTOBUF=ON
-        -DENABLE_TESTS=ON
-        -DENABLE_JEMALLOC=ON
-        -DENABLE_MULTITARGET_CODE=ON
-        -DENABLE_EXTERN_LOCAL_ENGINE=ON
-        -DCOMPILER_FLAGS='-fvisibility=hidden -fvisibility-inlines-hidden'
-        -S ${CH_SOURCE_DIR} -G Ninja -B ${CH_BINARY_DIR} &&
-        cmake --build ${CH_BINARY_DIR} --target ch unit_tests_local_engine\"
-        OUTPUT _build_ch)
+if(ENABLE_CPP_TEST)
+  add_custom_command(
+    USES_TERMINAL
+    COMMAND
+      bash -c \"cmake -DCMAKE_C_COMPILER=${CMAKE_C_COMPILER}
+      -DCMAKE_CXX_COMPILER=${CMAKE_CXX_COMPILER}
+      -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE} -DENABLE_PROTOBUF=ON
+      -DENABLE_TESTS=ON -DENABLE_JEMALLOC=ON -DENABLE_MULTITARGET_CODE=ON
+      -DENABLE_EXTERN_LOCAL_ENGINE=ON -DCOMPILER_FLAGS='-fvisibility=hidden
+      -fvisibility-inlines-hidden' -S ${CH_SOURCE_DIR} -G Ninja -B
+      ${CH_BINARY_DIR} && cmake --build ${CH_BINARY_DIR} --target ch
+      unit_tests_local_engine\"
+    OUTPUT _build_ch)
 else()
-add_custom_command(
-        USES_TERMINAL
-        COMMAND
-        bash -c
-        \"cmake -DCMAKE_C_COMPILER=${CMAKE_C_COMPILER}
-        -DCMAKE_CXX_COMPILER=${CMAKE_CXX_COMPILER}
-        -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE}
-        -DENABLE_PROTOBUF=ON
-        -DENABLE_TESTS=OFF
-        -DENABLE_JEMALLOC=ON
-        -DENABLE_MULTITARGET_CODE=ON
-        -DENABLE_EXTERN_LOCAL_ENGINE=ON
-        -DENABLE_ODBC=OFF
-        -DENABLE_CAPNP=OFF
-        -DENABLE_ROCKSDB=OFF
-        -DENABLE_GRPC=OFF
-        -DENABLE_RUST=OFF
-        -DENABLE_H3=OFF
-        -DENABLE_AMQPCPP=OFF
-        -DENABLE_CASSANDRA=OFF
-        -DENABLE_KAFKA=OFF
-        -DENABLE_NATS=OFF
-        -DENABLE_LIBPQXX=OFF
-        -DENABLE_NURAFT=OFF
-        -DENABLE_DATASKETCHES=OFF
-        -DENABLE_SQLITE=OFF
-        -DENABLE_S2_GEOMETRY=OFF
-        -DENABLE_ANNOY=OFF
-        -DENABLE_ULID=OFF
-        -DENABLE_MYSQL=OFF
-        -DENABLE_BCRYPT=OFF
-        -DENABLE_LDAP=OFF
-        -DENABLE_MSGPACK=OFF
-        -DUSE_REPLXX=OFF
-        -DENABLE_CLICKHOUSE_ALL=OFF
-        -DCOMPILER_FLAGS='-fvisibility=hidden -fvisibility-inlines-hidden'
-        -S ${CH_SOURCE_DIR} -G Ninja -B ${CH_BINARY_DIR} &&
-        cmake --build ${CH_BINARY_DIR} --target libch\"
-        OUTPUT _build_ch)
+  add_custom_command(
+    USES_TERMINAL
+    COMMAND
+      bash -c \"cmake -DCMAKE_C_COMPILER=${CMAKE_C_COMPILER}
+      -DCMAKE_CXX_COMPILER=${CMAKE_CXX_COMPILER}
+      -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE} -DENABLE_PROTOBUF=ON
+      -DENABLE_TESTS=OFF -DENABLE_JEMALLOC=ON -DENABLE_MULTITARGET_CODE=ON
+      -DENABLE_EXTERN_LOCAL_ENGINE=ON -DENABLE_ODBC=OFF -DENABLE_CAPNP=OFF
+      -DENABLE_ROCKSDB=OFF -DENABLE_GRPC=OFF -DENABLE_RUST=OFF -DENABLE_H3=OFF
+      -DENABLE_AMQPCPP=OFF -DENABLE_CASSANDRA=OFF -DENABLE_KAFKA=OFF
+      -DENABLE_NATS=OFF -DENABLE_LIBPQXX=OFF -DENABLE_NURAFT=OFF
+      -DENABLE_DATASKETCHES=OFF -DENABLE_SQLITE=OFF -DENABLE_S2_GEOMETRY=OFF
+      -DENABLE_ANNOY=OFF -DENABLE_ULID=OFF -DENABLE_MYSQL=OFF
+      -DENABLE_BCRYPT=OFF -DENABLE_LDAP=OFF -DENABLE_MSGPACK=OFF
+      -DUSE_REPLXX=OFF -DENABLE_CLICKHOUSE_ALL=OFF
+      -DCOMPILER_FLAGS='-fvisibility=hidden -fvisibility-inlines-hidden' -S
+      ${CH_SOURCE_DIR} -G Ninja -B ${CH_BINARY_DIR} && cmake --build
+      ${CH_BINARY_DIR} --target libch\"
+    OUTPUT _build_ch)
 endif()
 
 add_custom_target(build_ch ALL DEPENDS _build_ch)
diff --git a/cpp-ch/local-engine/CMakeLists.txt b/cpp-ch/local-engine/CMakeLists.txt
index 8c96c5f98f71..93ee4b8218af 100644
--- a/cpp-ch/local-engine/CMakeLists.txt
+++ b/cpp-ch/local-engine/CMakeLists.txt
@@ -13,22 +13,24 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
-if (ENABLE_MULTITARGET_CODE)
-    add_definitions(-DENABLE_MULTITARGET_CODE=1)
+if(ENABLE_MULTITARGET_CODE)
+  add_definitions(-DENABLE_MULTITARGET_CODE=1)
 else()
-    add_definitions(-DENABLE_MULTITARGET_CODE=0)
+  add_definitions(-DENABLE_MULTITARGET_CODE=0)
 endif()
 
-set (CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -w -ffunction-sections -fdata-sections")
-set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -w -ffunction-sections -fdata-sections")
-set (CMAKE_SHARED_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,--no-export-dynamic -Wl,--gc-sections")
+set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -w -ffunction-sections -fdata-sections")
+set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -w -ffunction-sections -fdata-sections")
+set(CMAKE_SHARED_LINKER_FLAGS
+    "${CMAKE_EXE_LINKER_FLAGS} -Wl,--no-export-dynamic -Wl,--gc-sections")
 
-if (COMPILER_CLANG AND CMAKE_CXX_COMPILER_VERSION VERSION_LESS 16)
-    set (CMAKE_SHARED_LINKER_FLAGS "${CMAKE_SHARED_LINKER_FLAGS} --ld-path=${LLD_WRAPPER}")
+if(COMPILER_CLANG AND CMAKE_CXX_COMPILER_VERSION VERSION_LESS 16)
+  set(CMAKE_SHARED_LINKER_FLAGS
+      "${CMAKE_SHARED_LINKER_FLAGS} --ld-path=${LLD_WRAPPER}")
 else()
-    set (CMAKE_SHARED_LINKER_FLAGS "${CMAKE_SHARED_LINKER_FLAGS} --ld-path=${LLD_PATH}")
-endif ()
+  set(CMAKE_SHARED_LINKER_FLAGS
+      "${CMAKE_SHARED_LINKER_FLAGS} --ld-path=${LLD_PATH}")
+endif()
 
 set(THRIFT_INCLUDE_DIR "${ClickHouse_SOURCE_DIR}/contrib/thrift/lib/cpp/src")
 
@@ -37,7 +39,7 @@ include(FindJava)
 include(UseJava)
 include(FindJNI)
 
-#set(JNI_NATIVE_SOURCES local_engine_jni.cpp)
+# set(JNI_NATIVE_SOURCES local_engine_jni.cpp)
 set(LOCALENGINE_SHARED_LIB _gluten_ch)
 
 add_subdirectory(proto)
@@ -61,116 +63,124 @@ add_headers_and_sources(disks Disks)
 add_headers_and_sources(disks Disks/ObjectStorages)
 
 include_directories(
-        ${JNI_INCLUDE_DIRS}
-        ${CMAKE_CURRENT_BINARY_DIR}/proto
-        ${THRIFT_INCLUDE_DIR}
-        ${CMAKE_BINARY_DIR}/contrib/thrift-cmake
-        ${CMAKE_BINARY_DIR}/contrib/llvm-project/llvm/include
-        ${CMAKE_CURRENT_SOURCE_DIR}
-        ${ClickHouse_SOURCE_DIR}/src
-        ${ClickHouse_SOURCE_DIR}/base
-        ${ClickHouse_SOURCE_DIR}/contrib/orc/c++/include
-        ${ClickHouse_SOURCE_DIR}/contrib/arrow-cmake/cpp/src/orc/c++/include
-        ${CMAKE_BINARY_DIR}/contrib/orc/c++/include
-        ${ClickHouse_SOURCE_DIR}/contrib/azure/sdk/storage/azure-storage-blobs/inc
-        ${ClickHouse_SOURCE_DIR}/contrib/azure/sdk/core/azure-core/inc
-        ${ClickHouse_SOURCE_DIR}/contrib/azure/sdk/storage/azure-storage-common/inc
-        ${ClickHouse_SOURCE_DIR}/contrib/llvm-project/llvm/include
-        ${ClickHouse_SOURCE_DIR}/contrib/llvm-project/utils/bazel/llvm-project-overlay/llvm/include
+  ${JNI_INCLUDE_DIRS}
+  ${CMAKE_CURRENT_BINARY_DIR}/proto
+  ${THRIFT_INCLUDE_DIR}
+  ${CMAKE_BINARY_DIR}/contrib/thrift-cmake
+  ${CMAKE_BINARY_DIR}/contrib/llvm-project/llvm/include
+  ${CMAKE_CURRENT_SOURCE_DIR}
+  ${ClickHouse_SOURCE_DIR}/src
+  ${ClickHouse_SOURCE_DIR}/base
+  ${ClickHouse_SOURCE_DIR}/contrib/orc/c++/include
+  ${ClickHouse_SOURCE_DIR}/contrib/arrow-cmake/cpp/src/orc/c++/include
+  ${CMAKE_BINARY_DIR}/contrib/orc/c++/include
+  ${ClickHouse_SOURCE_DIR}/contrib/azure/sdk/storage/azure-storage-blobs/inc
+  ${ClickHouse_SOURCE_DIR}/contrib/azure/sdk/core/azure-core/inc
+  ${ClickHouse_SOURCE_DIR}/contrib/azure/sdk/storage/azure-storage-common/inc
+  ${ClickHouse_SOURCE_DIR}/contrib/llvm-project/llvm/include
+  ${ClickHouse_SOURCE_DIR}/contrib/llvm-project/utils/bazel/llvm-project-overlay/llvm/include
 )
 
 add_subdirectory(Storages/Parquet)
 add_subdirectory(Storages/SubstraitSource)
 add_subdirectory(Functions)
 
-add_library(gluten_clickhouse_backend_libs
-        ${builder_sources}
-        ${join_sources}
-        ${parser_sources}
-        ${rewriter_sources}
-        ${storages_sources}
-        ${common_sources}
-        ${external_sources}
-        ${shuffle_sources}
-        ${operator_sources}
-        ${aggregate_functions_sources}
-        ${jni_sources}
-        ${disks_sources}
-)
-
-target_link_libraries(gluten_clickhouse_backend_libs PUBLIC
-        substrait_source
-        clickhouse_aggregate_functions
-        clickhouse_functions
-        gluten_spark_functions
-        ch_contrib::xxHash
-)
+add_library(
+  gluten_clickhouse_backend_libs
+  ${builder_sources}
+  ${join_sources}
+  ${parser_sources}
+  ${rewriter_sources}
+  ${storages_sources}
+  ${common_sources}
+  ${external_sources}
+  ${shuffle_sources}
+  ${operator_sources}
+  ${aggregate_functions_sources}
+  ${jni_sources}
+  ${disks_sources})
+
+target_link_libraries(
+  gluten_clickhouse_backend_libs
+  PUBLIC substrait_source clickhouse_aggregate_functions clickhouse_functions
+         gluten_spark_functions ch_contrib::xxHash)
 
 # Add udf sources files in sub directories to functions_sources
-option(ENABLE_LOCAL_UDFS "Build UDFs in 'local-engine/Parser/*_udf' subdirectories" ON)
-if (ENABLE_LOCAL_UDFS)
-    file(GLOB children CONFIGURE_DEPENDS RELATIVE ${CMAKE_CURRENT_SOURCE_DIR} Parser/*_udf)
-    foreach(child ${children})
-        add_headers_and_sources(local_udfs ${child})
-    endforeach()
-endif ()
-
-file(GLOB children CONFIGURE_DEPENDS RELATIVE ${CMAKE_CURRENT_SOURCE_DIR} Parser/*_function_parser)
+option(ENABLE_LOCAL_UDFS
+       "Build UDFs in 'local-engine/Parser/*_udf' subdirectories" ON)
+if(ENABLE_LOCAL_UDFS)
+  file(
+    GLOB children CONFIGURE_DEPENDS
+    RELATIVE ${CMAKE_CURRENT_SOURCE_DIR}
+    Parser/*_udf)
+  foreach(child ${children})
+    add_headers_and_sources(local_udfs ${child})
+  endforeach()
+endif()
+
+file(
+  GLOB children CONFIGURE_DEPENDS
+  RELATIVE ${CMAKE_CURRENT_SOURCE_DIR}
+  Parser/*_function_parser)
 foreach(child ${children})
-    add_headers_and_sources(function_parsers ${child})
+  add_headers_and_sources(function_parsers ${child})
 endforeach()
 
-# Notice: soures files under Parser/*_udf subdirectories must be built into target ${LOCALENGINE_SHARED_LIB} directly
-#         to make sure all function parsers are registered successly.
-add_library(${LOCALENGINE_SHARED_LIB} SHARED
-        local_engine_jni.cpp
-        ${local_udfs_sources}
-        ${function_parsers_sources}
-        $<TARGET_OBJECTS:clickhouse_malloc>) # why add clickhouse_malloc? check clickhouse PR-8046
+# Notice: soures files under Parser/*_udf subdirectories must be built into
+# target ${LOCALENGINE_SHARED_LIB} directly to make sure all function parsers
+# are registered successly.
+add_library(
+  ${LOCALENGINE_SHARED_LIB} SHARED
+  local_engine_jni.cpp ${local_udfs_sources} ${function_parsers_sources}
+  $<TARGET_OBJECTS:clickhouse_malloc>) # why add clickhouse_malloc? check
+                                       # clickhouse PR-8046
 
 target_compile_options(${LOCALENGINE_SHARED_LIB} PUBLIC -fPIC
-        -Wno-shorten-64-to-32)
-
-target_link_libraries(${LOCALENGINE_SHARED_LIB}
-PUBLIC
-        clickhouse_new_delete
-        clickhouse_common_config
-        clickhouse_common_io
-        clickhouse_parsers
-        clickhouse_storages_system
-        loggers
-        gluten_clickhouse_backend_libs
-        ch_contrib::protobuf
-PRIVATE
-        substrait
-)
+                                                        -Wno-shorten-64-to-32)
+
+target_link_libraries(
+  ${LOCALENGINE_SHARED_LIB}
+  PUBLIC clickhouse_new_delete
+         clickhouse_common_config
+         clickhouse_common_io
+         clickhouse_parsers
+         clickhouse_storages_system
+         loggers
+         gluten_clickhouse_backend_libs
+         ch_contrib::protobuf
+  PRIVATE substrait)
 
 target_link_libraries(${LOCALENGINE_SHARED_LIB} PUBLIC ch_parquet)
 
-if (ENABLE_JEMALLOC)
-    target_link_options(${LOCALENGINE_SHARED_LIB} PRIVATE
-        -Wl,--version-script=${CMAKE_CURRENT_SOURCE_DIR}/libch.map -Wl,-Bsymbolic-functions)
+if(ENABLE_JEMALLOC)
+  target_link_options(
+    ${LOCALENGINE_SHARED_LIB} PRIVATE
+    -Wl,--version-script=${CMAKE_CURRENT_SOURCE_DIR}/libch.map
+    -Wl,-Bsymbolic-functions)
 else()
-    target_link_options(${LOCALENGINE_SHARED_LIB} PRIVATE
-        -Wl,--version-script=${CMAKE_CURRENT_SOURCE_DIR}/libch-hide-jemalloc.map)
+  target_link_options(
+    ${LOCALENGINE_SHARED_LIB} PRIVATE
+    -Wl,--version-script=${CMAKE_CURRENT_SOURCE_DIR}/libch-hide-jemalloc.map)
 endif()
 
-if ("${CMAKE_BUILD_TYPE}" MATCHES "Debug")
-    set(LOCALENGINE_SHARED_LIB_NAME "libchd.so")
-else ()
-    set(LOCALENGINE_SHARED_LIB_NAME "libch.so")
-endif ()
+if("${CMAKE_BUILD_TYPE}" MATCHES "Debug")
+  set(LOCALENGINE_SHARED_LIB_NAME "libchd.so")
+else()
+  set(LOCALENGINE_SHARED_LIB_NAME "libch.so")
+endif()
 
 add_custom_command(
-        OUTPUT ${LOCALENGINE_SHARED_LIB_NAME}
-        COMMAND ${CMAKE_COMMAND} -E rename $<TARGET_FILE:${LOCALENGINE_SHARED_LIB}> ${LOCALENGINE_SHARED_LIB_NAME}
-        COMMENT "Renaming $<TARGET_FILE:${LOCALENGINE_SHARED_LIB}> to ${LOCALENGINE_SHARED_LIB_NAME}"
-        DEPENDS ${LOCALENGINE_SHARED_LIB})
+  OUTPUT ${LOCALENGINE_SHARED_LIB_NAME}
+  COMMAND ${CMAKE_COMMAND} -E rename $<TARGET_FILE:${LOCALENGINE_SHARED_LIB}>
+          ${LOCALENGINE_SHARED_LIB_NAME}
+  COMMENT
+    "Renaming $<TARGET_FILE:${LOCALENGINE_SHARED_LIB}> to ${LOCALENGINE_SHARED_LIB_NAME}"
+  DEPENDS ${LOCALENGINE_SHARED_LIB})
 
 add_custom_target(libch ALL DEPENDS ${LOCALENGINE_SHARED_LIB_NAME})
 
 add_subdirectory(tests)
 
-if (ENABLE_EXAMPLES)
-    add_subdirectory(examples)
-endif()
\ No newline at end of file
+if(ENABLE_EXAMPLES)
+  add_subdirectory(examples)
+endif()
diff --git a/cpp-ch/local-engine/Functions/CMakeLists.txt b/cpp-ch/local-engine/Functions/CMakeLists.txt
index 5968c86094f7..74697315597b 100644
--- a/cpp-ch/local-engine/Functions/CMakeLists.txt
+++ b/cpp-ch/local-engine/Functions/CMakeLists.txt
@@ -16,51 +16,52 @@
 add_headers_and_sources(gluten_spark_functions .)
 
 add_library(gluten_spark_functions_obj OBJECT ${gluten_spark_functions_sources})
-list (APPEND PRIVATE_LIBS
-        boost::headers_only
-        pcg_random
-        Poco::Foundation
-        Poco::Util
-        Poco::Net
-        Poco::JSON
-        ch_contrib::cctz
-        ch_contrib::fmt
-        ch_contrib::pdqsort
-        ch_contrib::miniselect
-        ch_contrib::magic_enum
-        ch_contrib::double_conversion
-        ch_contrib::dragonbox_to_chars
-        ch_contrib::re2
-        ch_contrib::abseil_swiss_tables
-        ch_contrib::sparsehash
-        ch_contrib::metrohash
-        ch_contrib::murmurhash
-        ch_contrib::wyhash
-        ch_contrib::cityhash
-        ch_contrib::farmhash
-        ch_contrib::xxHash
-        OpenSSL::SSL
-)
+list(
+  APPEND
+  PRIVATE_LIBS
+  boost::headers_only
+  pcg_random
+  Poco::Foundation
+  Poco::Util
+  Poco::Net
+  Poco::JSON
+  ch_contrib::cctz
+  ch_contrib::fmt
+  ch_contrib::pdqsort
+  ch_contrib::miniselect
+  ch_contrib::magic_enum
+  ch_contrib::double_conversion
+  ch_contrib::dragonbox_to_chars
+  ch_contrib::re2
+  ch_contrib::abseil_swiss_tables
+  ch_contrib::sparsehash
+  ch_contrib::metrohash
+  ch_contrib::murmurhash
+  ch_contrib::wyhash
+  ch_contrib::cityhash
+  ch_contrib::farmhash
+  ch_contrib::xxHash
+  OpenSSL::SSL)
 
-if (TARGET ch_contrib::vectorscan)
-    list (APPEND PRIVATE_LIBS ch_contrib::vectorscan)
+if(TARGET ch_contrib::vectorscan)
+  list(APPEND PRIVATE_LIBS ch_contrib::vectorscan)
 endif()
 
-if (TARGET ch_contrib::rapidjson)
-    list (APPEND PRIVATE_LIBS ch_contrib::rapidjson)
+if(TARGET ch_contrib::rapidjson)
+  list(APPEND PRIVATE_LIBS ch_contrib::rapidjson)
 endif()
 
-if (TARGET ch_contrib::simdjson)
-    list (APPEND PRIVATE_LIBS ch_contrib::simdjson)
+if(TARGET ch_contrib::simdjson)
+  list(APPEND PRIVATE_LIBS ch_contrib::simdjson)
 endif()
 
-if (TARGET ch_rust::blake3)
-    list (APPEND PRIVATE_LIBS ch_rust::blake3)
+if(TARGET ch_rust::blake3)
+  list(APPEND PRIVATE_LIBS ch_rust::blake3)
 endif()
 
-list (APPEND OBJECT_LIBS $<TARGET_OBJECTS:gluten_spark_functions_obj>)
+list(APPEND OBJECT_LIBS $<TARGET_OBJECTS:gluten_spark_functions_obj>)
 
 target_link_libraries(gluten_spark_functions_obj PRIVATE ${PRIVATE_LIBS})
 
 add_library(gluten_spark_functions INTERFACE)
-target_link_libraries(gluten_spark_functions INTERFACE ${OBJECT_LIBS})
\ No newline at end of file
+target_link_libraries(gluten_spark_functions INTERFACE ${OBJECT_LIBS})
diff --git a/cpp-ch/local-engine/Storages/Parquet/CMakeLists.txt b/cpp-ch/local-engine/Storages/Parquet/CMakeLists.txt
index f3d9e14f4b9c..bfe538710804 100644
--- a/cpp-ch/local-engine/Storages/Parquet/CMakeLists.txt
+++ b/cpp-ch/local-engine/Storages/Parquet/CMakeLists.txt
@@ -18,13 +18,10 @@ set(ARROW_INCLUDE_DIR "${ClickHouse_SOURCE_DIR}/contrib/arrow/cpp/src")
 add_headers_and_sources(Parquet .)
 add_library(ch_parquet ${Parquet_sources})
 
-target_link_libraries(ch_parquet PUBLIC
-    boost::headers_only
-    clickhouse_common_io
-)
+target_link_libraries(ch_parquet PUBLIC boost::headers_only
+                                        clickhouse_common_io)
 
-target_include_directories(ch_parquet SYSTEM BEFORE PUBLIC 
-    ${ARROW_INCLUDE_DIR}
-    ${CMAKE_BINARY_DIR}/contrib/arrow-cmake/cpp/src
-    ${ClickHouse_SOURCE_DIR}/contrib/arrow-cmake/cpp/src
-)
+target_include_directories(
+  ch_parquet SYSTEM BEFORE
+  PUBLIC ${ARROW_INCLUDE_DIR} ${CMAKE_BINARY_DIR}/contrib/arrow-cmake/cpp/src
+         ${ClickHouse_SOURCE_DIR}/contrib/arrow-cmake/cpp/src)
diff --git a/cpp-ch/local-engine/Storages/SubstraitSource/CMakeLists.txt b/cpp-ch/local-engine/Storages/SubstraitSource/CMakeLists.txt
index 4e43c924f6fe..228f54255cb4 100644
--- a/cpp-ch/local-engine/Storages/SubstraitSource/CMakeLists.txt
+++ b/cpp-ch/local-engine/Storages/SubstraitSource/CMakeLists.txt
@@ -15,30 +15,24 @@
 
 set(ARROW_INCLUDE_DIR "${ClickHouse_SOURCE_DIR}/contrib/arrow/cpp/src")
 
-
 macro(add_headers_and_sources_including_cc prefix common_path)
-    add_glob(${prefix}_headers ${CMAKE_CURRENT_SOURCE_DIR} ${common_path}/*.h)
-    add_glob(${prefix}_sources ${common_path}/*.cpp ${common_path}/*.c ${common_path}/*.cc ${common_path}/*.h)
+  add_glob(${prefix}_headers ${CMAKE_CURRENT_SOURCE_DIR} ${common_path}/*.h)
+  add_glob(${prefix}_sources ${common_path}/*.cpp ${common_path}/*.c
+           ${common_path}/*.cc ${common_path}/*.h)
 endmacro()
 
 add_headers_and_sources(substrait_source .)
 add_headers_and_sources_including_cc(ch_parquet arrow)
 add_library(substrait_source ${substrait_source_sources})
-target_compile_options(substrait_source PRIVATE
-    -Wno-suggest-destructor-override
-    -Wno-inconsistent-missing-destructor-override
-)
+target_compile_options(
+  substrait_source PRIVATE -Wno-suggest-destructor-override
+                           -Wno-inconsistent-missing-destructor-override)
 
-target_link_libraries(substrait_source PUBLIC
-    boost::headers_only
-    ch_contrib::protobuf
-    clickhouse_common_io
-    ch_contrib::hdfs
-    substrait
-)
+target_link_libraries(
+  substrait_source PUBLIC boost::headers_only ch_contrib::protobuf
+                          clickhouse_common_io ch_contrib::hdfs substrait)
 
-target_include_directories(substrait_source SYSTEM BEFORE PUBLIC
-    ${ARROW_INCLUDE_DIR}
-    ${CMAKE_BINARY_DIR}/contrib/arrow-cmake/cpp/src
-    ${ClickHouse_SOURCE_DIR}/contrib/arrow-cmake/cpp/src
-)
\ No newline at end of file
+target_include_directories(
+  substrait_source SYSTEM BEFORE
+  PUBLIC ${ARROW_INCLUDE_DIR} ${CMAKE_BINARY_DIR}/contrib/arrow-cmake/cpp/src
+         ${ClickHouse_SOURCE_DIR}/contrib/arrow-cmake/cpp/src)
diff --git a/cpp-ch/local-engine/examples/CMakeLists.txt b/cpp-ch/local-engine/examples/CMakeLists.txt
index bbeeb98d2445..03cd3bfe3f19 100644
--- a/cpp-ch/local-engine/examples/CMakeLists.txt
+++ b/cpp-ch/local-engine/examples/CMakeLists.txt
@@ -13,5 +13,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-clickhouse_add_executable (signal_demo signal_demo.cpp)
-target_link_libraries(signal_demo PRIVATE gluten_clickhouse_backend_libs loggers)
\ No newline at end of file
+clickhouse_add_executable(signal_demo signal_demo.cpp)
+target_link_libraries(signal_demo PRIVATE gluten_clickhouse_backend_libs
+                                          loggers)
diff --git a/cpp-ch/local-engine/proto/CMakeLists.txt b/cpp-ch/local-engine/proto/CMakeLists.txt
index 31583ff659ed..ffb34504af52 100644
--- a/cpp-ch/local-engine/proto/CMakeLists.txt
+++ b/cpp-ch/local-engine/proto/CMakeLists.txt
@@ -12,37 +12,34 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-file(GLOB protobuf_files
-        substrait/*.proto
-        substrait/extensions/*.proto
-        )
+file(GLOB protobuf_files substrait/*.proto substrait/extensions/*.proto)
 
-FOREACH(FIL ${protobuf_files})
-    file(RELATIVE_PATH FIL_RELATIVE ${ClickHouse_SOURCE_DIR}/utils/extern-local-engine/proto/ ${FIL})
-    string(REGEX REPLACE "\\.proto" "" FILE_NAME ${FIL_RELATIVE})
-    LIST(APPEND SUBSTRAIT_SRCS "${CMAKE_CURRENT_BINARY_DIR}/${FILE_NAME}.pb.cc")
-    LIST(APPEND SUBSTRAIT_HEADERS "${CMAKE_CURRENT_BINARY_DIR}/${FILE_NAME}.pb.h")
-ENDFOREACH()
+foreach(FIL ${protobuf_files})
+  file(RELATIVE_PATH FIL_RELATIVE
+       ${ClickHouse_SOURCE_DIR}/utils/extern-local-engine/proto/ ${FIL})
+  string(REGEX REPLACE "\\.proto" "" FILE_NAME ${FIL_RELATIVE})
+  list(APPEND SUBSTRAIT_SRCS "${CMAKE_CURRENT_BINARY_DIR}/${FILE_NAME}.pb.cc")
+  list(APPEND SUBSTRAIT_HEADERS "${CMAKE_CURRENT_BINARY_DIR}/${FILE_NAME}.pb.h")
+endforeach()
 
 # Generate Substrait headers
 add_custom_command(
-        OUTPUT ${SUBSTRAIT_SRCS} ${SUBSTRAIT_HEADERS}
-        COMMAND
-        $<TARGET_FILE:protoc> --cpp_out ${CMAKE_CURRENT_BINARY_DIR}
-        --proto_path ${CMAKE_CURRENT_SOURCE_DIR}
-        --proto_path ${ClickHouse_SOURCE_DIR}/contrib/google-protobuf/src
-        ${protobuf_files}
-        DEPENDS ${protobuf_files}
-        COMMENT "Running cpp protocol buffer compiler"
-        VERBATIM)
-add_custom_target(generate_substrait ALL DEPENDS ${SUBSTRAIT_SRCS} ${SUBSTRAIT_HEADERS})
+  OUTPUT ${SUBSTRAIT_SRCS} ${SUBSTRAIT_HEADERS}
+  COMMAND
+    $<TARGET_FILE:protoc> --cpp_out ${CMAKE_CURRENT_BINARY_DIR} --proto_path
+    ${CMAKE_CURRENT_SOURCE_DIR} --proto_path
+    ${ClickHouse_SOURCE_DIR}/contrib/google-protobuf/src ${protobuf_files}
+  DEPENDS ${protobuf_files}
+  COMMENT "Running cpp protocol buffer compiler"
+  VERBATIM)
+add_custom_target(generate_substrait ALL DEPENDS ${SUBSTRAIT_SRCS}
+                                                 ${SUBSTRAIT_HEADERS})
 set_source_files_properties(${SUBSTRAIT_SRCS} PROPERTIES GENERATED TRUE)
 
 add_library(substrait ${SUBSTRAIT_SRCS})
 add_dependencies(substrait generate_substrait)
-target_compile_options(substrait PUBLIC -fPIC
-        -Wno-reserved-identifier
-        -Wno-deprecated)
-target_include_directories(substrait SYSTEM BEFORE PRIVATE ${CMAKE_CURRENT_BINARY_DIR})
+target_compile_options(substrait PUBLIC -fPIC -Wno-reserved-identifier
+                                        -Wno-deprecated)
+target_include_directories(substrait SYSTEM BEFORE
+                           PRIVATE ${CMAKE_CURRENT_BINARY_DIR})
 target_link_libraries(substrait ch_contrib::protobuf)
-
diff --git a/cpp-ch/local-engine/tests/CMakeLists.txt b/cpp-ch/local-engine/tests/CMakeLists.txt
index 9781a332e89c..be02bf6234d2 100644
--- a/cpp-ch/local-engine/tests/CMakeLists.txt
+++ b/cpp-ch/local-engine/tests/CMakeLists.txt
@@ -12,76 +12,92 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-configure_file(${CMAKE_CURRENT_SOURCE_DIR}/testConfig.h.in ${CMAKE_CURRENT_SOURCE_DIR}/testConfig.h)
+configure_file(${CMAKE_CURRENT_SOURCE_DIR}/testConfig.h.in
+               ${CMAKE_CURRENT_SOURCE_DIR}/testConfig.h)
 
-if (ENABLE_TESTS)
-    macro(add_gtest_sources prefix common_path)
-        add_glob(${prefix}_sources ${common_path}/gtest*.cpp)
-    endmacro()
+if(ENABLE_TESTS)
+  macro(add_gtest_sources prefix common_path)
+    add_glob(${prefix}_sources ${common_path}/gtest*.cpp)
+  endmacro()
 
-    set(USE_INTERNAL_GTEST_LIBRARY 0)
-    set(BENCHMARK_ENABLE_TESTING OFF)
+  set(USE_INTERNAL_GTEST_LIBRARY 0)
+  set(BENCHMARK_ENABLE_TESTING OFF)
 
-    enable_testing()
-    include(CTest)
+  enable_testing()
+  include(CTest)
 
-    include_directories(${GTEST_INCLUDE_DIRS})
+  include_directories(${GTEST_INCLUDE_DIRS})
 
-    set(TEST_DATA_DIR "${ClickHouse_SOURCE_DIR}/utils/extern-local-engine/tests")
-    set(HAVE_POSIX_REGEX 1)
-    set(LOCAL_ENGINE_DIR "${ClickHouse_SOURCE_DIR}/utils/extern-local-engine")
+  set(TEST_DATA_DIR "${ClickHouse_SOURCE_DIR}/utils/extern-local-engine/tests")
+  set(HAVE_POSIX_REGEX 1)
+  set(LOCAL_ENGINE_DIR "${ClickHouse_SOURCE_DIR}/utils/extern-local-engine")
 
-    add_gtest_sources(local_engine_gtest .)
-    if (ENABLE_LOCAL_UDFS)
-        file(GLOB children CONFIGURE_DEPENDS RELATIVE ${CMAKE_CURRENT_SOURCE_DIR} ../Parser/*_udf/tests)
-        foreach(child ${children})
-            add_gtest_sources(local_engine_gtest ${child})
-        endforeach()
-
-        file(GLOB children CONFIGURE_DEPENDS RELATIVE ${CMAKE_CURRENT_SOURCE_DIR} ../Parser/*_udf)
-        foreach(child ${children})
-            add_headers_and_sources(local_engine_udf ${child})
-        endforeach()
-    endif ()
+  add_gtest_sources(local_engine_gtest .)
+  if(ENABLE_LOCAL_UDFS)
+    file(
+      GLOB children CONFIGURE_DEPENDS
+      RELATIVE ${CMAKE_CURRENT_SOURCE_DIR}
+      ../Parser/*_udf/tests)
+    foreach(child ${children})
+      add_gtest_sources(local_engine_gtest ${child})
+    endforeach()
 
-    file(GLOB children CONFIGURE_DEPENDS RELATIVE ${CMAKE_CURRENT_SOURCE_DIR} ../Parser/*_function_parser)
+    file(
+      GLOB children CONFIGURE_DEPENDS
+      RELATIVE ${CMAKE_CURRENT_SOURCE_DIR}
+      ../Parser/*_udf)
     foreach(child ${children})
-        add_headers_and_sources(local_engine_function_parser ${child})
+      add_headers_and_sources(local_engine_udf ${child})
     endforeach()
+  endif()
 
+  file(
+    GLOB children CONFIGURE_DEPENDS
+    RELATIVE ${CMAKE_CURRENT_SOURCE_DIR}
+    ../Parser/*_function_parser)
+  foreach(child ${children})
+    add_headers_and_sources(local_engine_function_parser ${child})
+  endforeach()
 
-    message("local engine gtest sources: ${local_engine_gtest_sources}")
-    message("local engine udf sources: ${local_engine_udf_sources}")
-    message("local engine function parser sources: ${local_engine_function_parser_sources}")
+  message("local engine gtest sources: ${local_engine_gtest_sources}")
+  message("local engine udf sources: ${local_engine_udf_sources}")
+  message(
+    "local engine function parser sources: ${local_engine_function_parser_sources}"
+  )
 
-    add_executable(unit_tests_local_engine
-        gluten_test_util.cpp
-        ${local_engine_gtest_sources}
-        ${local_engine_udf_sources}
-        ${local_engine_function_parser_sources})
-    target_include_directories(unit_tests_local_engine PRIVATE
-        ${ClickHouse_SOURCE_DIR}/utils/extern-local_engine
-        ${CMAKE_CURRENT_SOURCE_DIR}
-    )
-    # no-unreachable-code for GTEST_SKIP
-    target_compile_options(unit_tests_local_engine PRIVATE -Wno-unreachable-code)
-    target_link_libraries(unit_tests_local_engine PRIVATE gluten_clickhouse_backend_libs clickhouse_parsers loggers ch_contrib::gmock_all ch_contrib::gtest)
-    target_link_libraries(unit_tests_local_engine PRIVATE ch_parquet)
+  add_executable(
+    unit_tests_local_engine
+    gluten_test_util.cpp ${local_engine_gtest_sources}
+    ${local_engine_udf_sources} ${local_engine_function_parser_sources})
+  target_include_directories(
+    unit_tests_local_engine
+    PRIVATE ${ClickHouse_SOURCE_DIR}/utils/extern-local_engine
+            ${CMAKE_CURRENT_SOURCE_DIR})
+  # no-unreachable-code for GTEST_SKIP
+  target_compile_options(unit_tests_local_engine PRIVATE -Wno-unreachable-code)
+  target_link_libraries(
+    unit_tests_local_engine
+    PRIVATE gluten_clickhouse_backend_libs clickhouse_parsers loggers
+            ch_contrib::gmock_all ch_contrib::gtest)
+  target_link_libraries(unit_tests_local_engine PRIVATE ch_parquet)
 endif()
 
-if (ENABLE_BENCHMARKS)
-    include_directories(benchmark_local_engine SYSTEM PUBLIC
-        ${ClickHouse_SOURCE_DIR}/utils/extern-local_engine
-    )
-    add_executable(benchmark_local_engine
-        gluten_test_util.cpp
-        benchmark_local_engine.cpp
-        benchmark_parquet_read.cpp
-        benchmark_spark_row.cpp
-        benchmark_unix_timestamp_function.cpp
-        benchmark_spark_floor_function.cpp
-        benchmark_cast_float_function.cpp
-        benchmark_to_datetime_function.cpp
-        benchmark_spark_divide_function.cpp)
-    target_link_libraries(benchmark_local_engine PRIVATE gluten_clickhouse_backend_libs ch_contrib::gbenchmark_all loggers ch_parquet)
+if(ENABLE_BENCHMARKS)
+  include_directories(benchmark_local_engine SYSTEM PUBLIC
+                      ${ClickHouse_SOURCE_DIR}/utils/extern-local_engine)
+  add_executable(
+    benchmark_local_engine
+    gluten_test_util.cpp
+    benchmark_local_engine.cpp
+    benchmark_parquet_read.cpp
+    benchmark_spark_row.cpp
+    benchmark_unix_timestamp_function.cpp
+    benchmark_spark_floor_function.cpp
+    benchmark_cast_float_function.cpp
+    benchmark_to_datetime_function.cpp
+    benchmark_spark_divide_function.cpp)
+  target_link_libraries(
+    benchmark_local_engine
+    PRIVATE gluten_clickhouse_backend_libs ch_contrib::gbenchmark_all loggers
+            ch_parquet)
 endif()
diff --git a/cpp/CMake/BuildGTest.cmake b/cpp/CMake/BuildGTest.cmake
index fff99455c419..d85578c0593c 100644
--- a/cpp/CMake/BuildGTest.cmake
+++ b/cpp/CMake/BuildGTest.cmake
@@ -6,15 +6,14 @@ set(GLUTEN_GTEST_BUILD_SHA256_CHECKSUM
     ad7fdba11ea011c1d925b3289cf4af2c66a352e18d4c7264392fead75e919363)
 set(GLUTEN_GTEST_SOURCE_URL
     "https://github.com/google/googletest/archive/refs/tags/v${GLUTEN_GTEST_VERSION}.tar.gz"
-    )
+)
 
 resolve_dependency_url(GTEST)
 
 message(STATUS "Building gtest from source")
 FetchContent_Declare(
-    gtest
-    URL ${GLUTEN_GTEST_SOURCE_URL}
-    URL_HASH "${GLUTEN_GTEST_BUILD_SHA256_CHECKSUM}"
-)
+  gtest
+  URL ${GLUTEN_GTEST_SOURCE_URL}
+  URL_HASH "${GLUTEN_GTEST_BUILD_SHA256_CHECKSUM}")
 
 FetchContent_MakeAvailable(gtest)
diff --git a/cpp/CMake/BuildGflags.cmake b/cpp/CMake/BuildGflags.cmake
index 4cb201115835..8e66bd6b9839 100644
--- a/cpp/CMake/BuildGflags.cmake
+++ b/cpp/CMake/BuildGflags.cmake
@@ -17,10 +17,10 @@
 include_guard(GLOBAL)
 
 set(GLUTEN_GFLAGS_BUILD_SHA256_CHECKSUM
-  34af2f15cf7367513b352bdcd2493ab14ce43692d2dcd9dfc499492966c64dcf)
+    34af2f15cf7367513b352bdcd2493ab14ce43692d2dcd9dfc499492966c64dcf)
 string(CONCAT GLUTEN_GFLAGS_SOURCE_URL
-  "https://github.com/gflags/gflags/archive/refs/tags/"
-  "v${GLUTEN_GFLAGS_VERSION}.tar.gz")
+              "https://github.com/gflags/gflags/archive/refs/tags/"
+              "v${GLUTEN_GFLAGS_VERSION}.tar.gz")
 
 resolve_dependency_url(GFLAGS)
 
diff --git a/cpp/CMake/BuildGlog.cmake b/cpp/CMake/BuildGlog.cmake
index cf405225c313..3f0f78a16531 100644
--- a/cpp/CMake/BuildGlog.cmake
+++ b/cpp/CMake/BuildGlog.cmake
@@ -14,10 +14,10 @@
 include_guard(GLOBAL)
 
 set(GLUTEN_GLOG_BUILD_SHA256_CHECKSUM
-  8a83bf982f37bb70825df71a9709fa90ea9f4447fb3c099e1d720a439d88bad6)
+    8a83bf982f37bb70825df71a9709fa90ea9f4447fb3c099e1d720a439d88bad6)
 set(GLUTEN_GLOG_SOURCE_URL
-  "https://github.com/google/glog/archive/refs/tags/v${GLUTEN_GLOG_VERSION}.tar.gz"
-  )
+    "https://github.com/google/glog/archive/refs/tags/v${GLUTEN_GLOG_VERSION}.tar.gz"
+)
 
 resolve_dependency_url(GLOG)
 
@@ -27,7 +27,7 @@ FetchContent_Declare(
   URL ${GLUTEN_GLOG_SOURCE_URL}
   URL_HASH SHA256=${GLUTEN_GLOG_BUILD_SHA256_CHECKSUM}
   PATCH_COMMAND git apply ${CMAKE_CURRENT_LIST_DIR}/glog/glog-no-export.patch
-  && git apply ${CMAKE_CURRENT_LIST_DIR}/glog/glog-config.patch)
+                && git apply ${CMAKE_CURRENT_LIST_DIR}/glog/glog-config.patch)
 
 set(BUILD_SHARED_LIBS OFF)
 set(WITH_UNWIND OFF)
@@ -48,6 +48,6 @@ endif()
 # These headers are missing from the include dir but adding the src dir causes
 # issues with folly so we just copy it to the include dir
 file(COPY ${glog_SOURCE_DIR}/src/glog/platform.h
-  DESTINATION ${glog_BINARY_DIR}/glog)
+     DESTINATION ${glog_BINARY_DIR}/glog)
 file(COPY ${glog_SOURCE_DIR}/src/glog/log_severity.h
-  DESTINATION ${glog_BINARY_DIR}/glog)
+     DESTINATION ${glog_BINARY_DIR}/glog)
diff --git a/cpp/CMake/BuildGoogleBenchmark.cmake b/cpp/CMake/BuildGoogleBenchmark.cmake
index 8efbb58eab74..a71d73432f62 100644
--- a/cpp/CMake/BuildGoogleBenchmark.cmake
+++ b/cpp/CMake/BuildGoogleBenchmark.cmake
@@ -21,8 +21,10 @@ include(FetchContent)
 set(GLUTEN_GBENCHMARK_BUILD_VERSION "v1.6.0")
 set(GLUTEN_GBENCHMARK_SOURCE_URL
     "https://github.com/google/benchmark/archive/refs/tags/${GLUTEN_GBENCHMARK_BUILD_VERSION}.tar.gz"
-    "https://github.com/ursa-labs/thirdparty/releases/download/latest/gbenchmark-${GLUTEN_GBENCHMARK_BUILD_VERSION}.tar.gz")
-set(GLUTEN_GBENCHMARK_BUILD_SHA256_CHECKSUM "1f71c72ce08d2c1310011ea6436b31e39ccab8c2db94186d26657d41747c85d6")
+    "https://github.com/ursa-labs/thirdparty/releases/download/latest/gbenchmark-${GLUTEN_GBENCHMARK_BUILD_VERSION}.tar.gz"
+)
+set(GLUTEN_GBENCHMARK_BUILD_SHA256_CHECKSUM
+    "1f71c72ce08d2c1310011ea6436b31e39ccab8c2db94186d26657d41747c85d6")
 
 resolve_dependency_url(GBENCHMARK)
 
@@ -30,12 +32,11 @@ set(GBENCHMARK_CMAKE_ARGS "-fPIC -w")
 
 message(STATUS "Building google benchmark from source")
 FetchContent_Declare(
-    gbenchmark
-    URL ${GLUTEN_GBENCHMARK_SOURCE_URL}
-    URL_HASH "${GLUTEN_GBENCHMARK_BUILD_SHA256_CHECKSUM}"
-)
+  gbenchmark
+  URL ${GLUTEN_GBENCHMARK_SOURCE_URL}
+  URL_HASH "${GLUTEN_GBENCHMARK_BUILD_SHA256_CHECKSUM}")
 
-if (NOT gbenchmark_POPULATED)
+if(NOT gbenchmark_POPULATED)
   # We don't want to build tests.
   set(BENCHMARK_ENABLE_TESTING
       OFF
diff --git a/cpp/CMake/BuildMemkind.cmake b/cpp/CMake/BuildMemkind.cmake
index 039db0cc0d81..2f2248de6fc4 100644
--- a/cpp/CMake/BuildMemkind.cmake
+++ b/cpp/CMake/BuildMemkind.cmake
@@ -26,48 +26,50 @@ endif()
 macro(build_hwloc)
   message(STATUS "Building hwloc from source")
   set(HWLOC_BUILD_VERSION "2.8.0")
-  set(HWLOC_BUILD_SHA256_CHECKSUM "311d44e99bbf6d269c2cbc569d073978d88352bc31d51e31457d4df94783172d")
+  set(HWLOC_BUILD_SHA256_CHECKSUM
+      "311d44e99bbf6d269c2cbc569d073978d88352bc31d51e31457d4df94783172d")
   set(HWLOC_SOURCE_URL
-          "https://github.com/open-mpi/hwloc/archive/refs/tags/hwloc-${HWLOC_BUILD_VERSION}.tar.gz")
+      "https://github.com/open-mpi/hwloc/archive/refs/tags/hwloc-${HWLOC_BUILD_VERSION}.tar.gz"
+  )
   set(HWLOC_LIB_NAME "hwloc")
   set(HWLOC_PREFIX "${CMAKE_CURRENT_BINARY_DIR}/hwloc_ep-install")
   set(HWLOC_SOURCE_DIR "${HWLOC_PREFIX}/src/hwloc_ep")
   set(HWLOC_INCLUDE_DIR "${HWLOC_SOURCE_DIR}/include")
   set(HWLOC_LIB_DIR "${HWLOC_SOURCE_DIR}/hwloc/.libs")
-  set(HWLOC_STATIC_LIB_NAME "${CMAKE_STATIC_LIBRARY_PREFIX}${HWLOC_LIB_NAME}${CMAKE_STATIC_LIBRARY_SUFFIX}")
+  set(HWLOC_STATIC_LIB_NAME
+      "${CMAKE_STATIC_LIBRARY_PREFIX}${HWLOC_LIB_NAME}${CMAKE_STATIC_LIBRARY_SUFFIX}"
+  )
   set(HWLOC_STATIC_LIB_TARGETS
-          "${HWLOC_SOURCE_DIR}/src/.libs/${HWLOC_STATIC_LIB_NAME}")
+      "${HWLOC_SOURCE_DIR}/src/.libs/${HWLOC_STATIC_LIB_NAME}")
   set(HWLOC_CONFIGURE_ARGS
-          "--prefix=${HWLOC_PREFIX}"
-          "--with-pic"
-          "--enable-static"
-          "--disable-shared"
-          "--enable-plugins")
-  ExternalProject_Add(hwloc_ep
-          PREFIX ${HWLOC_PREFIX}
-          URL ${HWLOC_SOURCE_URL}
-          URL_HASH "SHA256=${HWLOC_BUILD_SHA256_CHECKSUM}"
-          SOURCE_DIR ${HWLOC_SOURCE_DIR}
-          CONFIGURE_COMMAND ./configure ${HWLOC_CONFIGURE_ARGS}
-          BUILD_COMMAND ${MAKE}
-          BUILD_BYPRODUCTS ${HWLOC_STATIC_LIB_TARGETS}
-          BUILD_IN_SOURCE 1)
+      "--prefix=${HWLOC_PREFIX}" "--with-pic" "--enable-static"
+      "--disable-shared" "--enable-plugins")
+  ExternalProject_Add(
+    hwloc_ep
+    PREFIX ${HWLOC_PREFIX}
+    URL ${HWLOC_SOURCE_URL}
+    URL_HASH "SHA256=${HWLOC_BUILD_SHA256_CHECKSUM}"
+    SOURCE_DIR ${HWLOC_SOURCE_DIR}
+    CONFIGURE_COMMAND ./configure ${HWLOC_CONFIGURE_ARGS}
+    BUILD_COMMAND ${MAKE}
+    BUILD_BYPRODUCTS ${HWLOC_STATIC_LIB_TARGETS}
+    BUILD_IN_SOURCE 1)
 
-  ExternalProject_Add_Step(hwloc_ep pre-configure
-          COMMAND ./autogen.sh
-          DEPENDEES download
-          DEPENDERS configure
-          WORKING_DIRECTORY ${HWLOC_SOURCE_DIR})
+  ExternalProject_Add_Step(
+    hwloc_ep pre-configure
+    COMMAND ./autogen.sh
+    DEPENDEES download
+    DEPENDERS configure
+    WORKING_DIRECTORY ${HWLOC_SOURCE_DIR})
 
   # The include directory must exist before it is referenced by a target.
   file(MAKE_DIRECTORY "${HWLOC_INCLUDE_DIR}")
 
   add_library(hwloc::hwloc STATIC IMPORTED)
-  set_target_properties(hwloc::hwloc
-          PROPERTIES IMPORTED_LOCATION
-          "${HWLOC_LIB_DIR}/${HWLOC_STATIC_LIB_NAME}"
-          INTERFACE_INCLUDE_DIRECTORIES
-          "${HWLOC_INCLUDE_DIR}")
+  set_target_properties(
+    hwloc::hwloc
+    PROPERTIES IMPORTED_LOCATION "${HWLOC_LIB_DIR}/${HWLOC_STATIC_LIB_NAME}"
+               INTERFACE_INCLUDE_DIRECTORIES "${HWLOC_INCLUDE_DIR}")
 
   add_dependencies(hwloc::hwloc hwloc_ep)
 endmacro()
@@ -75,36 +77,43 @@ endmacro()
 macro(build_memkind)
   message(STATUS "Building Memkind from source")
   set(MEMKIND_BUILD_VERSION "v1.14.0")
-  set(MEMKIND_BUILD_SHA256_CHECKSUM "ab366b20b5a87ea655483631fc762ba6eb59eb6c3a08652e643f1ee3f06a6a12")
+  set(MEMKIND_BUILD_SHA256_CHECKSUM
+      "ab366b20b5a87ea655483631fc762ba6eb59eb6c3a08652e643f1ee3f06a6a12")
   set(MEMKIND_SOURCE_URL
-          "https://github.com/memkind/memkind/archive/refs/tags/${MEMKIND_BUILD_VERSION}.tar.gz")
+      "https://github.com/memkind/memkind/archive/refs/tags/${MEMKIND_BUILD_VERSION}.tar.gz"
+  )
   set(MEMKIND_LIB_NAME "memkind")
   set(MEMKIND_PREFIX "${CMAKE_CURRENT_BINARY_DIR}/memkind_ep-install")
   set(MEMKIND_SOURCE_DIR "${MEMKIND_PREFIX}/src/memkind_ep")
   set(MEMKIND_INCLUDE_DIR "${MEMKIND_SOURCE_DIR}/include")
   set(MEMKIND_LIB_DIR "${MEMKIND_SOURCE_DIR}/.libs")
-  set(MEMKIND_STATIC_LIB_NAME "${CMAKE_STATIC_LIBRARY_PREFIX}${MEMKIND_LIB_NAME}${CMAKE_STATIC_LIBRARY_SUFFIX}")
+  set(MEMKIND_STATIC_LIB_NAME
+      "${CMAKE_STATIC_LIBRARY_PREFIX}${MEMKIND_LIB_NAME}${CMAKE_STATIC_LIBRARY_SUFFIX}"
+  )
   set(MEMKIND_STATIC_LIB_TARGETS
-          "${MEMKIND_SOURCE_DIR}/src/.libs/${MEMKIND_STATIC_LIB_NAME}")
-  set(MEMKIND_CONFIGURE_ARGS
-          "--prefix=${MEMKIND_PREFIX}"
-          "--with-pic"
-          "--enable-static")
-  ExternalProject_Add(memkind_ep
-          PREFIX ${MEMKIND_PREFIX}
-          URL ${MEMKIND_SOURCE_URL}
-          URL_HASH "SHA256=${MEMKIND_BUILD_SHA256_CHECKSUM}"
-          SOURCE_DIR ${MEMKIND_SOURCE_DIR}
-          CONFIGURE_COMMAND ${CMAKE_COMMAND} -E env LDFLAGS=-L${HWLOC_LIB_DIR} env CFLAGS=-I${HWLOC_INCLUDE_DIR} env CXXFLAGS=-I${HWLOC_INCLUDE_DIR} ./configure ${MEMKIND_CONFIGURE_ARGS}
-          BUILD_COMMAND ${MAKE}
-          BUILD_BYPRODUCTS ${MEMKIND_STATIC_LIB_TARGETS}
-          BUILD_IN_SOURCE 1)
+      "${MEMKIND_SOURCE_DIR}/src/.libs/${MEMKIND_STATIC_LIB_NAME}")
+  set(MEMKIND_CONFIGURE_ARGS "--prefix=${MEMKIND_PREFIX}" "--with-pic"
+                             "--enable-static")
+  ExternalProject_Add(
+    memkind_ep
+    PREFIX ${MEMKIND_PREFIX}
+    URL ${MEMKIND_SOURCE_URL}
+    URL_HASH "SHA256=${MEMKIND_BUILD_SHA256_CHECKSUM}"
+    SOURCE_DIR ${MEMKIND_SOURCE_DIR}
+    CONFIGURE_COMMAND
+      ${CMAKE_COMMAND} -E env LDFLAGS=-L${HWLOC_LIB_DIR} env
+      CFLAGS=-I${HWLOC_INCLUDE_DIR} env CXXFLAGS=-I${HWLOC_INCLUDE_DIR}
+      ./configure ${MEMKIND_CONFIGURE_ARGS}
+    BUILD_COMMAND ${MAKE}
+    BUILD_BYPRODUCTS ${MEMKIND_STATIC_LIB_TARGETS}
+    BUILD_IN_SOURCE 1)
 
-  ExternalProject_Add_Step(memkind_ep pre-configure
-          COMMAND ./autogen.sh
-          DEPENDEES download
-          DEPENDERS configure
-          WORKING_DIRECTORY ${MEMKIND_SOURCE_DIR})
+  ExternalProject_Add_Step(
+    memkind_ep pre-configure
+    COMMAND ./autogen.sh
+    DEPENDEES download
+    DEPENDERS configure
+    WORKING_DIRECTORY ${MEMKIND_SOURCE_DIR})
 
   add_dependencies(memkind_ep hwloc::hwloc)
 
@@ -112,12 +121,12 @@ macro(build_memkind)
   file(MAKE_DIRECTORY "${MEMKIND_INCLUDE_DIR}")
 
   add_library(memkind::memkind STATIC IMPORTED)
-  set_target_properties(memkind::memkind
-          PROPERTIES IMPORTED_LOCATION
-          "${MEMKIND_LIB_DIR}/${MEMKIND_STATIC_LIB_NAME}"
-          INTERFACE_INCLUDE_DIRECTORIES
-          "${MEMKIND_INCLUDE_DIR}")
-  target_link_libraries(memkind::memkind INTERFACE hwloc::hwloc dl numa pthread daxctl)
+  set_target_properties(
+    memkind::memkind
+    PROPERTIES IMPORTED_LOCATION "${MEMKIND_LIB_DIR}/${MEMKIND_STATIC_LIB_NAME}"
+               INTERFACE_INCLUDE_DIRECTORIES "${MEMKIND_INCLUDE_DIR}")
+  target_link_libraries(memkind::memkind INTERFACE hwloc::hwloc dl numa pthread
+                                                   daxctl)
 
   add_dependencies(memkind::memkind memkind_ep)
 endmacro()
diff --git a/cpp/CMake/BuildQATZstd.cmake b/cpp/CMake/BuildQATZstd.cmake
index f6c152db1460..f79e9ea58fcc 100644
--- a/cpp/CMake/BuildQATZstd.cmake
+++ b/cpp/CMake/BuildQATZstd.cmake
@@ -28,61 +28,72 @@ macro(build_qatzstd)
   include(FindZstd)
 
   message(STATUS "Building QAT-ZSTD from source")
-  set(QATZSTD_SOURCE_URL
-      "https://github.com/marin-ma/QAT-ZSTD-Plugin.git")
+  set(QATZSTD_SOURCE_URL "https://github.com/marin-ma/QAT-ZSTD-Plugin.git")
   set(QATZSTD_SOURCE_BRANCH "fix-duplicate-symbol")
   set(QATZSTD_LIB_NAME "qatseqprod")
 
-  set(QATZSTD_PREFIX
-      "${CMAKE_CURRENT_BINARY_DIR}/qatzstd_ep-install")
+  set(QATZSTD_PREFIX "${CMAKE_CURRENT_BINARY_DIR}/qatzstd_ep-install")
   set(QATZSTD_SOURCE_DIR "${QATZSTD_PREFIX}/src/qatzstd_ep")
   set(QATZSTD_INCLUDE_DIR "${QATZSTD_SOURCE_DIR}/src")
-  set(QATZSTD_STATIC_LIB_NAME "${CMAKE_STATIC_LIBRARY_PREFIX}${QATZSTD_LIB_NAME}${CMAKE_STATIC_LIBRARY_SUFFIX}")
-  set(QATZSTD_STATIC_LIB_TARGETS "${QATZSTD_SOURCE_DIR}/src/${QATZSTD_STATIC_LIB_NAME}")
+  set(QATZSTD_STATIC_LIB_NAME
+      "${CMAKE_STATIC_LIBRARY_PREFIX}${QATZSTD_LIB_NAME}${CMAKE_STATIC_LIBRARY_SUFFIX}"
+  )
+  set(QATZSTD_STATIC_LIB_TARGETS
+      "${QATZSTD_SOURCE_DIR}/src/${QATZSTD_STATIC_LIB_NAME}")
   set(QATZSTD_MAKE_ARGS "ENABLE_USDM_DRV=1" "ZSTDLIB=${ZSTD_INCLUDE_DIR}")
 
-  ExternalProject_Add(qatzstd_ep
-      PREFIX ${QATZSTD_PREFIX}
-      GIT_REPOSITORY ${QATZSTD_SOURCE_URL}
-      GIT_TAG ${QATZSTD_SOURCE_BRANCH}
-      SOURCE_DIR ${QATZSTD_SOURCE_DIR}
-      CONFIGURE_COMMAND ""
-      BUILD_COMMAND ${MAKE} ${QATZSTD_MAKE_ARGS}
-      INSTALL_COMMAND ""
-      BUILD_BYPRODUCTS ${QATZSTD_STATIC_LIB_TARGETS}
-      BUILD_IN_SOURCE 1)
+  ExternalProject_Add(
+    qatzstd_ep
+    PREFIX ${QATZSTD_PREFIX}
+    GIT_REPOSITORY ${QATZSTD_SOURCE_URL}
+    GIT_TAG ${QATZSTD_SOURCE_BRANCH}
+    SOURCE_DIR ${QATZSTD_SOURCE_DIR}
+    CONFIGURE_COMMAND ""
+    BUILD_COMMAND ${MAKE} ${QATZSTD_MAKE_ARGS}
+    INSTALL_COMMAND ""
+    BUILD_BYPRODUCTS ${QATZSTD_STATIC_LIB_TARGETS}
+    BUILD_IN_SOURCE 1)
 
   add_library(qatzstd::qatzstd STATIC IMPORTED)
 
   # The include directory must exist before it is referenced by a target.
   file(MAKE_DIRECTORY "${QATZSTD_INCLUDE_DIR}")
 
-  set(QATZSTD_INCLUDE_DIRS
-      "${QATZSTD_INCLUDE_DIR}"
-      "${ZSTD_INCLUDE_DIR}")
+  set(QATZSTD_INCLUDE_DIRS "${QATZSTD_INCLUDE_DIR}" "${ZSTD_INCLUDE_DIR}")
 
   set(QATZSTD_LINK_LIBRARIES
-      "${ZSTD_LIBRARY}"
-      "${QAT_LIBRARY}"
-      "${USDM_DRV_LIBRARY}"
-      "${ADF_LIBRARY}"
+      "${ZSTD_LIBRARY}" "${QAT_LIBRARY}" "${USDM_DRV_LIBRARY}" "${ADF_LIBRARY}"
       "${OSAL_LIBRARY}")
 
-  set_target_properties(qatzstd::qatzstd
-      PROPERTIES IMPORTED_LOCATION
-      "${QATZSTD_STATIC_LIB_TARGETS}"
-      INTERFACE_INCLUDE_DIRECTORIES
-      "${QATZSTD_INCLUDE_DIRS}"
-      INTERFACE_LINK_LIBRARIES
-      "${QATZSTD_LINK_LIBRARIES}")
+  set_target_properties(
+    qatzstd::qatzstd
+    PROPERTIES IMPORTED_LOCATION "${QATZSTD_STATIC_LIB_TARGETS}"
+               INTERFACE_INCLUDE_DIRECTORIES "${QATZSTD_INCLUDE_DIRS}"
+               INTERFACE_LINK_LIBRARIES "${QATZSTD_LINK_LIBRARIES}")
 
   add_dependencies(qatzstd::qatzstd qatzstd_ep)
 endmacro()
 
-find_library(QAT_LIBRARY REQUIRED NAMES qat PATHS "$ENV{ICP_ROOT}/build" NO_DEFAULT_PATH)
-find_library(USDM_DRV_LIBRARY REQUIRED NAMES usdm_drv PATHS "$ENV{ICP_ROOT}/build" NO_DEFAULT_PATH)
-find_library(ADF_LIBRARY REQUIRED NAMES adf PATHS "$ENV{ICP_ROOT}/build" NO_DEFAULT_PATH)
-find_library(OSAL_LIBRARY REQUIRED NAMES osal PATHS "$ENV{ICP_ROOT}/build" NO_DEFAULT_PATH)
+find_library(
+  QAT_LIBRARY REQUIRED
+  NAMES qat
+  PATHS "$ENV{ICP_ROOT}/build"
+  NO_DEFAULT_PATH)
+find_library(
+  USDM_DRV_LIBRARY REQUIRED
+  NAMES usdm_drv
+  PATHS "$ENV{ICP_ROOT}/build"
+  NO_DEFAULT_PATH)
+find_library(
+  ADF_LIBRARY REQUIRED
+  NAMES adf
+  PATHS "$ENV{ICP_ROOT}/build"
+  NO_DEFAULT_PATH)
+find_library(
+  OSAL_LIBRARY REQUIRED
+  NAMES osal
+  PATHS "$ENV{ICP_ROOT}/build"
+  NO_DEFAULT_PATH)
 
 message(STATUS "Found qat: ${QAT_LIBRARY}")
 message(STATUS "Found usdm_drv: ${USDM_DRV_LIBRARY}")
@@ -90,4 +101,3 @@ message(STATUS "Found adf: ${ADF_LIBRARY}")
 message(STATUS "Found osal: ${OSAL_LIBRARY}")
 
 build_qatzstd()
-
diff --git a/cpp/CMake/BuildQATzip.cmake b/cpp/CMake/BuildQATzip.cmake
index 376f1645509a..c68ef25ada2e 100644
--- a/cpp/CMake/BuildQATzip.cmake
+++ b/cpp/CMake/BuildQATzip.cmake
@@ -26,38 +26,42 @@ endif()
 macro(build_qatzip)
   message(STATUS "Building QATzip from source")
   set(QATZIP_BUILD_VERSION "v1.1.1")
-  set(QATZIP_BUILD_SHA256_CHECKSUM "679f5522deb35e7ffa36f227ae49d07ef2d69a83e56bfda849303829b274e79b")
+  set(QATZIP_BUILD_SHA256_CHECKSUM
+      "679f5522deb35e7ffa36f227ae49d07ef2d69a83e56bfda849303829b274e79b")
   set(QATZIP_SOURCE_URL
-      "https://github.com/intel/QATzip/archive/refs/tags/${QATZIP_BUILD_VERSION}.tar.gz")
+      "https://github.com/intel/QATzip/archive/refs/tags/${QATZIP_BUILD_VERSION}.tar.gz"
+  )
   set(QATZIP_LIB_NAME "qatzip")
 
-  set(QATZIP_PREFIX
-      "${CMAKE_CURRENT_BINARY_DIR}/qatzip_ep-install")
+  set(QATZIP_PREFIX "${CMAKE_CURRENT_BINARY_DIR}/qatzip_ep-install")
   set(QATZIP_SOURCE_DIR "${QATZIP_PREFIX}/src/qatzip_ep")
   set(QATZIP_INCLUDE_DIR "${QATZIP_SOURCE_DIR}/include")
-  set(QATZIP_STATIC_LIB_NAME "${CMAKE_STATIC_LIBRARY_PREFIX}${QATZIP_LIB_NAME}${CMAKE_STATIC_LIBRARY_SUFFIX}")
+  set(QATZIP_STATIC_LIB_NAME
+      "${CMAKE_STATIC_LIBRARY_PREFIX}${QATZIP_LIB_NAME}${CMAKE_STATIC_LIBRARY_SUFFIX}"
+  )
   set(QATZIP_STATIC_LIB_TARGETS
       "${QATZIP_SOURCE_DIR}/src/.libs/${QATZIP_STATIC_LIB_NAME}")
-  set(QATZIP_CONFIGURE_ARGS
-      "--prefix=${QATZIP_PREFIX}"
-      "--with-pic"
-      "--with-ICP_ROOT=$ENV{ICP_ROOT}")
+  set(QATZIP_CONFIGURE_ARGS "--prefix=${QATZIP_PREFIX}" "--with-pic"
+                            "--with-ICP_ROOT=$ENV{ICP_ROOT}")
 
-  ExternalProject_Add(qatzip_ep
-      PREFIX ${QATZIP_PREFIX}
-      URL ${QATZIP_SOURCE_URL}
-      URL_HASH "SHA256=${QATZIP_BUILD_SHA256_CHECKSUM}"
-      SOURCE_DIR ${QATZIP_SOURCE_DIR}
-      CONFIGURE_COMMAND ${CMAKE_COMMAND} -E env QZ_ROOT=${QATZIP_SOURCE_DIR} ./configure ${QATZIP_CONFIGURE_ARGS}
-      BUILD_COMMAND ${MAKE} all
-      BUILD_BYPRODUCTS ${QATZIP_STATIC_LIB_TARGETS}
-      BUILD_IN_SOURCE 1)
+  ExternalProject_Add(
+    qatzip_ep
+    PREFIX ${QATZIP_PREFIX}
+    URL ${QATZIP_SOURCE_URL}
+    URL_HASH "SHA256=${QATZIP_BUILD_SHA256_CHECKSUM}"
+    SOURCE_DIR ${QATZIP_SOURCE_DIR}
+    CONFIGURE_COMMAND ${CMAKE_COMMAND} -E env QZ_ROOT=${QATZIP_SOURCE_DIR}
+                      ./configure ${QATZIP_CONFIGURE_ARGS}
+    BUILD_COMMAND ${MAKE} all
+    BUILD_BYPRODUCTS ${QATZIP_STATIC_LIB_TARGETS}
+    BUILD_IN_SOURCE 1)
 
-  ExternalProject_Add_Step(qatzip_ep pre-configure
-      COMMAND ./autogen.sh
-      DEPENDEES download
-      DEPENDERS configure
-      WORKING_DIRECTORY ${QATZIP_SOURCE_DIR})
+  ExternalProject_Add_Step(
+    qatzip_ep pre-configure
+    COMMAND ./autogen.sh
+    DEPENDEES download
+    DEPENDERS configure
+    WORKING_DIRECTORY ${QATZIP_SOURCE_DIR})
 
   # The include directory must exist before it is referenced by a target.
   file(MAKE_DIRECTORY "${QATZIP_INCLUDE_DIR}")
@@ -73,13 +77,11 @@ macro(build_qatzip)
       Threads::Threads)
 
   add_library(qatzip::qatzip STATIC IMPORTED)
-  set_target_properties(qatzip::qatzip
-      PROPERTIES IMPORTED_LOCATION
-      "${QATZIP_STATIC_LIB_TARGETS}"
-      INTERFACE_INCLUDE_DIRECTORIES
-      "${QATZIP_INCLUDE_DIR}"
-      INTERFACE_LINK_LIBRARIES
-      "${QATZIP_LINK_LIBRARIES}")
+  set_target_properties(
+    qatzip::qatzip
+    PROPERTIES IMPORTED_LOCATION "${QATZIP_STATIC_LIB_TARGETS}"
+               INTERFACE_INCLUDE_DIRECTORIES "${QATZIP_INCLUDE_DIR}"
+               INTERFACE_LINK_LIBRARIES "${QATZIP_LINK_LIBRARIES}")
 
   add_dependencies(qatzip::qatzip qatzip_ep)
 endmacro()
@@ -90,10 +92,26 @@ find_package(Threads REQUIRED)
 find_library(ZLIB_LIBRARY REQUIRED NAMES z)
 find_library(LZ4_LIBRARY REQUIRED NAMES lz4)
 find_library(UDEV_LIBRARY REQUIRED NAMES udev)
-find_library(USDM_DRV_LIBRARY REQUIRED NAMES usdm_drv PATHS "$ENV{ICP_ROOT}/build" NO_DEFAULT_PATH)
-find_library(QAT_LIBRARY REQUIRED NAMES qat PATHS "$ENV{ICP_ROOT}/build" NO_DEFAULT_PATH)
-find_library(OSAL_LIBRARY REQUIRED NAMES osal PATHS "$ENV{ICP_ROOT}/build" NO_DEFAULT_PATH)
-find_library(ADF_LIBRARY REQUIRED NAMES adf PATHS "$ENV{ICP_ROOT}/build" NO_DEFAULT_PATH)
+find_library(
+  USDM_DRV_LIBRARY REQUIRED
+  NAMES usdm_drv
+  PATHS "$ENV{ICP_ROOT}/build"
+  NO_DEFAULT_PATH)
+find_library(
+  QAT_LIBRARY REQUIRED
+  NAMES qat
+  PATHS "$ENV{ICP_ROOT}/build"
+  NO_DEFAULT_PATH)
+find_library(
+  OSAL_LIBRARY REQUIRED
+  NAMES osal
+  PATHS "$ENV{ICP_ROOT}/build"
+  NO_DEFAULT_PATH)
+find_library(
+  ADF_LIBRARY REQUIRED
+  NAMES adf
+  PATHS "$ENV{ICP_ROOT}/build"
+  NO_DEFAULT_PATH)
 
 message(STATUS "Found zlib: ${ZLIB_LIBRARY}")
 message(STATUS "Found lz4: ${LZ4_LIBRARY}")
@@ -102,4 +120,3 @@ message(STATUS "Found usdm_drv: ${USDM_DRV_LIBRARY}")
 message(STATUS "Found qat: ${QAT_LIBRARY}")
 
 build_qatzip()
-
diff --git a/cpp/CMake/BuildQpl.cmake b/cpp/CMake/BuildQpl.cmake
index dbfd16645342..7715bb8e767f 100644
--- a/cpp/CMake/BuildQpl.cmake
+++ b/cpp/CMake/BuildQpl.cmake
@@ -18,46 +18,43 @@
 include(ExternalProject)
 
 macro(build_qpl)
-    message(STATUS "Building QPL from source")
-    set(QPL_BUILD_VERSION "v1.1.0")
-    set(QPL_BUILD_SHA256_CHECKSUM "00306000035621dfbc21007481395c46ba9723fc8add8ca5142847b94dc564c5")
-    set(QPL_SOURCE_URL
-            "https://github.com/intel/qpl/archive/refs/tags/v1.1.0.tar.gz")
-    set(QPL_LIB_NAME "qpl")
-
-    set(QPL_PREFIX
-            "${CMAKE_CURRENT_BINARY_DIR}/qpl_ep-install")
-    set(QPL_SOURCE_DIR "${QPL_PREFIX}/src/qpl_ep")
-    set(QPL_INCLUDE_DIR "${QPL_PREFIX}/include")
-    set(QPL_LIB_DIR "${QPL_PREFIX}/lib")
-    set(QPL_STATIC_LIB_NAME "${CMAKE_STATIC_LIBRARY_PREFIX}${QPL_LIB_NAME}${CMAKE_STATIC_LIBRARY_SUFFIX}${QPL_STATIC_LIB_MAJOR_VERSION}")
-    set(QPL_STATIC_LIB_TARGETS
-            "${QPL_LIB_DIR}/${QPL_STATIC_LIB_NAME}"
-            )
-    ExternalProject_Add(qpl_ep
-            PREFIX ${QPL_PREFIX}
-            URL ${QPL_SOURCE_URL}
-            URL_HASH "SHA256=${QPL_BUILD_SHA256_CHECKSUM}"
-            SOURCE_DIR ${QPL_SOURCE_DIR}
-            CMAKE_ARGS
-            -DCMAKE_INSTALL_PREFIX=${QPL_PREFIX}
-            -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE}
-            -DQPL_BUILD_TESTS=OFF
-            -DLOG_HW_INIT=ON
-            BUILD_BYPRODUCTS ${QPL_STATIC_LIB_TARGETS})
-
-    # The include directory must exist before it is referenced by a target.
-    file(MAKE_DIRECTORY "${QPL_INCLUDE_DIR}")
-
-    add_library(qpl::qpl STATIC IMPORTED)
-    set_target_properties(qpl::qpl
-            PROPERTIES IMPORTED_LOCATION
-            "${QPL_LIB_DIR}/${QPL_STATIC_LIB_NAME}"
-            INTERFACE_INCLUDE_DIRECTORIES
-            "${QPL_INCLUDE_DIR}")
-
-    add_dependencies(qpl::qpl qpl_ep)
+  message(STATUS "Building QPL from source")
+  set(QPL_BUILD_VERSION "v1.1.0")
+  set(QPL_BUILD_SHA256_CHECKSUM
+      "00306000035621dfbc21007481395c46ba9723fc8add8ca5142847b94dc564c5")
+  set(QPL_SOURCE_URL
+      "https://github.com/intel/qpl/archive/refs/tags/v1.1.0.tar.gz")
+  set(QPL_LIB_NAME "qpl")
+
+  set(QPL_PREFIX "${CMAKE_CURRENT_BINARY_DIR}/qpl_ep-install")
+  set(QPL_SOURCE_DIR "${QPL_PREFIX}/src/qpl_ep")
+  set(QPL_INCLUDE_DIR "${QPL_PREFIX}/include")
+  set(QPL_LIB_DIR "${QPL_PREFIX}/lib")
+  set(QPL_STATIC_LIB_NAME
+      "${CMAKE_STATIC_LIBRARY_PREFIX}${QPL_LIB_NAME}${CMAKE_STATIC_LIBRARY_SUFFIX}${QPL_STATIC_LIB_MAJOR_VERSION}"
+  )
+  set(QPL_STATIC_LIB_TARGETS "${QPL_LIB_DIR}/${QPL_STATIC_LIB_NAME}")
+  ExternalProject_Add(
+    qpl_ep
+    PREFIX ${QPL_PREFIX}
+    URL ${QPL_SOURCE_URL}
+    URL_HASH "SHA256=${QPL_BUILD_SHA256_CHECKSUM}"
+    SOURCE_DIR ${QPL_SOURCE_DIR}
+    CMAKE_ARGS -DCMAKE_INSTALL_PREFIX=${QPL_PREFIX}
+               -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE} -DQPL_BUILD_TESTS=OFF
+               -DLOG_HW_INIT=ON
+    BUILD_BYPRODUCTS ${QPL_STATIC_LIB_TARGETS})
+
+  # The include directory must exist before it is referenced by a target.
+  file(MAKE_DIRECTORY "${QPL_INCLUDE_DIR}")
+
+  add_library(qpl::qpl STATIC IMPORTED)
+  set_target_properties(
+    qpl::qpl
+    PROPERTIES IMPORTED_LOCATION "${QPL_LIB_DIR}/${QPL_STATIC_LIB_NAME}"
+               INTERFACE_INCLUDE_DIRECTORIES "${QPL_INCLUDE_DIR}")
+
+  add_dependencies(qpl::qpl qpl_ep)
 endmacro()
 
 build_qpl()
-
diff --git a/cpp/CMake/ConfigArrow.cmake b/cpp/CMake/ConfigArrow.cmake
index 1ae4ece1b8ef..8f036be53411 100644
--- a/cpp/CMake/ConfigArrow.cmake
+++ b/cpp/CMake/ConfigArrow.cmake
@@ -15,7 +15,7 @@
 # specific language governing permissions and limitations
 # under the License.
 
-if (${CMAKE_SYSTEM_NAME} STREQUAL "Darwin")
+if(${CMAKE_SYSTEM_NAME} STREQUAL "Darwin")
   set(ARROW_SHARED_LIBRARY_SUFFIX ".1500.dylib")
   set(ARROW_SHARED_LIBRARY_PARENT_SUFFIX ".1500.1.0.dylib")
 else()
@@ -30,22 +30,28 @@ set(ARROW_SUBSTRAIT_LIB_NAME "arrow_substrait")
 
 function(FIND_ARROW_LIB LIB_NAME)
   if(NOT TARGET Arrow::${LIB_NAME})
-    set(ARROW_LIB_FULL_NAME ${CMAKE_SHARED_LIBRARY_PREFIX}${LIB_NAME}${ARROW_SHARED_LIBRARY_SUFFIX})
+    set(ARROW_LIB_FULL_NAME
+        ${CMAKE_SHARED_LIBRARY_PREFIX}${LIB_NAME}${ARROW_SHARED_LIBRARY_SUFFIX})
     add_library(Arrow::${LIB_NAME} SHARED IMPORTED)
-    find_library(ARROW_LIB_${LIB_NAME}
-        NAMES ${ARROW_LIB_FULL_NAME}
-        PATHS ${ARROW_LIB_DIR} ${ARROW_LIB64_DIR}
-        NO_DEFAULT_PATH)
+    find_library(
+      ARROW_LIB_${LIB_NAME}
+      NAMES ${ARROW_LIB_FULL_NAME}
+      PATHS ${ARROW_LIB_DIR} ${ARROW_LIB64_DIR}
+      NO_DEFAULT_PATH)
     if(NOT ARROW_LIB_${LIB_NAME})
       message(FATAL_ERROR "Arrow library Not Found: ${ARROW_LIB_FULL_NAME}")
     else()
       message(STATUS "Found Arrow library: ${ARROW_LIB_${LIB_NAME}}")
-      set_target_properties(Arrow::${LIB_NAME}
+      set_target_properties(
+        Arrow::${LIB_NAME}
         PROPERTIES IMPORTED_LOCATION "${ARROW_LIB_${LIB_NAME}}"
-        INTERFACE_INCLUDE_DIRECTORIES
-        "${ARROW_HOME}/install/include")
+                   INTERFACE_INCLUDE_DIRECTORIES
+                   "${ARROW_HOME}/install/include")
     endif()
-    file(COPY ${ARROW_LIB_${LIB_NAME}} DESTINATION ${root_directory}/releases/ FOLLOW_SYMLINK_CHAIN)
+    file(
+      COPY ${ARROW_LIB_${LIB_NAME}}
+      DESTINATION ${root_directory}/releases/
+      FOLLOW_SYMLINK_CHAIN)
   endif()
 endfunction()
 
diff --git a/cpp/CMake/FindThrift.cmake b/cpp/CMake/FindThrift.cmake
index 07028971d9fc..273500a6ae36 100644
--- a/cpp/CMake/FindThrift.cmake
+++ b/cpp/CMake/FindThrift.cmake
@@ -12,27 +12,26 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-# - Find Thrift (a cross platform RPC lib/tool)
+# * Find Thrift (a cross platform RPC lib/tool)
 #
 # Variables used by this module, they can change the default behaviour and need
 # to be set before calling find_package:
 #
-#  Thrift_ROOT - When set, this path is inspected instead of standard library
-#                locations as the root of the Thrift installation.
-#                The environment variable THRIFT_HOME overrides this variable.
+# Thrift_ROOT - When set, this path is inspected instead of standard library
+# locations as the root of the Thrift installation. The environment variable
+# THRIFT_HOME overrides this variable.
 #
-# This module defines
-#  Thrift_FOUND, whether Thrift is found or not
-#  Thrift_COMPILER_FOUND, whether Thrift compiler is found or not
+# This module defines Thrift_FOUND, whether Thrift is found or not
+# Thrift_COMPILER_FOUND, whether Thrift compiler is found or not
 #
-#  thrift::thrift, a library target to use Thrift
-#  thrift::compiler, a executable target to use Thrift compiler
+# thrift::thrift, a library target to use Thrift thrift::compiler, a executable
+# target to use Thrift compiler
 
 function(EXTRACT_THRIFT_VERSION)
   if(THRIFT_INCLUDE_DIR)
     file(READ "${THRIFT_INCLUDE_DIR}/thrift/config.h" THRIFT_CONFIG_H_CONTENT)
-    string(REGEX MATCH "#define PACKAGE_VERSION \"[0-9.]+\"" THRIFT_VERSION_DEFINITION
-                 "${THRIFT_CONFIG_H_CONTENT}")
+    string(REGEX MATCH "#define PACKAGE_VERSION \"[0-9.]+\""
+                 THRIFT_VERSION_DEFINITION "${THRIFT_CONFIG_H_CONTENT}")
     string(REGEX MATCH "[0-9.]+" Thrift_VERSION "${THRIFT_VERSION_DEFINITION}")
     set(Thrift_VERSION
         "${Thrift_VERSION}"
@@ -66,14 +65,16 @@ set(THRIFT_LIB_NAME_BASE "thrift${THRIFT_MSVC_LIB_SUFFIX}")
 if(ARROW_THRIFT_USE_SHARED)
   set(THRIFT_LIB_NAMES thrift)
   if(CMAKE_IMPORT_LIBRARY_SUFFIX)
-    list(APPEND
-         THRIFT_LIB_NAMES
-         "${CMAKE_IMPORT_LIBRARY_PREFIX}${THRIFT_LIB_NAME_BASE}${CMAKE_IMPORT_LIBRARY_SUFFIX}"
+    list(
+      APPEND
+      THRIFT_LIB_NAMES
+      "${CMAKE_IMPORT_LIBRARY_PREFIX}${THRIFT_LIB_NAME_BASE}${CMAKE_IMPORT_LIBRARY_SUFFIX}"
     )
   endif()
-  list(APPEND
-       THRIFT_LIB_NAMES
-       "${CMAKE_SHARED_LIBRARY_PREFIX}${THRIFT_LIB_NAME_BASE}${CMAKE_SHARED_LIBRARY_SUFFIX}"
+  list(
+    APPEND
+    THRIFT_LIB_NAMES
+    "${CMAKE_SHARED_LIBRARY_PREFIX}${THRIFT_LIB_NAME_BASE}${CMAKE_SHARED_LIBRARY_SUFFIX}"
   )
 else()
   set(THRIFT_LIB_NAMES
@@ -82,20 +83,24 @@ else()
 endif()
 
 if(Thrift_ROOT)
-  find_library(THRIFT_LIB
-               NAMES ${THRIFT_LIB_NAMES}
-               PATHS ${Thrift_ROOT}
-               PATH_SUFFIXES "lib/${CMAKE_LIBRARY_ARCHITECTURE}" "lib")
-  find_path(THRIFT_INCLUDE_DIR thrift/Thrift.h
-            PATHS ${Thrift_ROOT}
-            PATH_SUFFIXES "include")
-  find_program(THRIFT_COMPILER thrift
-               PATHS ${Thrift_ROOT}
-               PATH_SUFFIXES "bin")
+  find_library(
+    THRIFT_LIB
+    NAMES ${THRIFT_LIB_NAMES}
+    PATHS ${Thrift_ROOT}
+    PATH_SUFFIXES "lib/${CMAKE_LIBRARY_ARCHITECTURE}" "lib")
+  find_path(
+    THRIFT_INCLUDE_DIR thrift/Thrift.h
+    PATHS ${Thrift_ROOT}
+    PATH_SUFFIXES "include")
+  find_program(
+    THRIFT_COMPILER thrift
+    PATHS ${Thrift_ROOT}
+    PATH_SUFFIXES "bin")
   extract_thrift_version()
 else()
-  # THRIFT-4760: The pkgconfig files are currently only installed when using autotools.
-  # Starting with 0.13, they are also installed for the CMake-based installations of Thrift.
+  # THRIFT-4760: The pkgconfig files are currently only installed when using
+  # autotools. Starting with 0.13, they are also installed for the CMake-based
+  # installations of Thrift.
   find_package(PkgConfig QUIET)
   pkg_check_modules(THRIFT_PC thrift)
   if(THRIFT_PC_FOUND)
@@ -103,19 +108,22 @@ else()
 
     list(APPEND THRIFT_PC_LIBRARY_DIRS "${THRIFT_PC_LIBDIR}")
 
-    find_library(THRIFT_LIB
-                 NAMES ${THRIFT_LIB_NAMES}
-                 PATHS ${THRIFT_PC_LIBRARY_DIRS}
-                 NO_DEFAULT_PATH)
-    find_program(THRIFT_COMPILER thrift
-                 HINTS ${THRIFT_PC_PREFIX}
-                 NO_DEFAULT_PATH
-                 PATH_SUFFIXES "bin")
+    find_library(
+      THRIFT_LIB
+      NAMES ${THRIFT_LIB_NAMES}
+      PATHS ${THRIFT_PC_LIBRARY_DIRS}
+      NO_DEFAULT_PATH)
+    find_program(
+      THRIFT_COMPILER thrift
+      HINTS ${THRIFT_PC_PREFIX}
+      NO_DEFAULT_PATH
+      PATH_SUFFIXES "bin")
     set(Thrift_VERSION ${THRIFT_PC_VERSION})
   else()
-    find_library(THRIFT_LIB
-                 NAMES ${THRIFT_LIB_NAMES}
-                 PATH_SUFFIXES "lib/${CMAKE_LIBRARY_ARCHITECTURE}" "lib")
+    find_library(
+      THRIFT_LIB
+      NAMES ${THRIFT_LIB_NAMES}
+      PATH_SUFFIXES "lib/${CMAKE_LIBRARY_ARCHITECTURE}" "lib")
     find_path(THRIFT_INCLUDE_DIR thrift/Thrift.h PATH_SUFFIXES "include")
     find_program(THRIFT_COMPILER thrift PATH_SUFFIXES "bin")
     extract_thrift_version()
@@ -140,14 +148,15 @@ if(Thrift_FOUND)
   else()
     add_library(thrift::thrift STATIC IMPORTED)
   endif()
-  set_target_properties(thrift::thrift
-                        PROPERTIES IMPORTED_LOCATION "${THRIFT_LIB}"
-                                   INTERFACE_INCLUDE_DIRECTORIES "${THRIFT_INCLUDE_DIR}")
+  set_target_properties(
+    thrift::thrift
+    PROPERTIES IMPORTED_LOCATION "${THRIFT_LIB}" INTERFACE_INCLUDE_DIRECTORIES
+                                                 "${THRIFT_INCLUDE_DIR}")
   if(WIN32 AND NOT MSVC_TOOLCHAIN)
-    # We don't need this for Visual C++ because Thrift uses
-    # "#pragma comment(lib, "Ws2_32.lib")" in
-    # thrift/windows/config.h for Visual C++.
-    set_target_properties(thrift::thrift PROPERTIES INTERFACE_LINK_LIBRARIES "ws2_32")
+    # We don't need this for Visual C++ because Thrift uses "#pragma
+    # comment(lib, "Ws2_32.lib")" in thrift/windows/config.h for Visual C++.
+    set_target_properties(thrift::thrift PROPERTIES INTERFACE_LINK_LIBRARIES
+                                                    "ws2_32")
   endif()
 
   if(Thrift_COMPILER_FOUND)
diff --git a/cpp/CMake/FindZstd.cmake b/cpp/CMake/FindZstd.cmake
index a7efd5adfd3f..62e8b874d735 100644
--- a/cpp/CMake/FindZstd.cmake
+++ b/cpp/CMake/FindZstd.cmake
@@ -15,43 +15,44 @@
 # specific language governing permissions and limitations
 # under the License.
 
-# ZSTD_HOME environmental variable is used to check for Zstd headers and static library
+# ZSTD_HOME environmental variable is used to check for Zstd headers and static
+# library
 
-# ZSTD_INCLUDE_DIR: directory containing headers
-# ZSTD_LIBRARY: path to libzstd.so
-# ZSTD_FOUND: whether zstd has been found
+# ZSTD_INCLUDE_DIR: directory containing headers ZSTD_LIBRARY: path to
+# libzstd.so ZSTD_FOUND: whether zstd has been found
 
-if (NOT "$ENV{ZSTD_HOME}" STREQUAL "")
+if(NOT "$ENV{ZSTD_HOME}" STREQUAL "")
   file(TO_CMAKE_PATH "$ENV{ZSTD_HOME}" _zstd_path)
   message(STATUS "ZSTD_HOME: ${_zstd_path}")
 else()
   set(_zstd_path "/usr/local")
 endif()
 
-find_path(ZSTD_INCLUDE_DIR zstd.h HINTS
-    ${_zstd_path}
-    PATH_SUFFIXES "include")
+find_path(
+  ZSTD_INCLUDE_DIR zstd.h
+  HINTS ${_zstd_path}
+  PATH_SUFFIXES "include")
 
-find_library (ZSTD_LIBRARY NAMES zstd HINTS
-    ${_zstd_path}
-    PATH_SUFFIXES "lib")
+find_library(
+  ZSTD_LIBRARY
+  NAMES zstd
+  HINTS ${_zstd_path}
+  PATH_SUFFIXES "lib")
 
-if (ZSTD_INCLUDE_DIR AND ZSTD_LIBRARY)
+if(ZSTD_INCLUDE_DIR AND ZSTD_LIBRARY)
   set(ZSTD_FOUND TRUE)
   set(ZSTD_HEADER_NAME zstd.h)
   set(ZSTD_HEADER ${ZSTD_INCLUDE_DIR}/${ZSTD_HEADER_NAME})
-else ()
+else()
   set(ZSTD_FOUND FALSE)
-endif ()
+endif()
 
-if (ZSTD_FOUND)
+if(ZSTD_FOUND)
   message(STATUS "Found the zstd header: ${ZSTD_HEADER}")
   message(STATUS "Found the zstd static library: ${ZSTD_LIBRARY}")
-else ()
-  message(FATAL_ERROR ZSTD_ERR_MSG "Could not find zstd. Looked in ${_zstd_path}.")
-endif ()
-
-mark_as_advanced(
-    ZSTD_INCLUDE_DIR
-    ZSTD_LIBRARY)
+else()
+  message(FATAL_ERROR ZSTD_ERR_MSG
+                      "Could not find zstd. Looked in ${_zstd_path}.")
+endif()
 
+mark_as_advanced(ZSTD_INCLUDE_DIR ZSTD_LIBRARY)
diff --git a/cpp/CMake/Findglog.cmake b/cpp/CMake/Findglog.cmake
index b165fd80f3d7..6d9dbdacf1b1 100644
--- a/cpp/CMake/Findglog.cmake
+++ b/cpp/CMake/Findglog.cmake
@@ -22,23 +22,17 @@ if(NOT BUILD_GLOG)
   include(FindPackageHandleStandardArgs)
   include(SelectLibraryConfigurations)
 
-  find_library(GLOG_LIBRARY_RELEASE glog
-    PATHS ${GLOG_LIBRARYDIR})
-  find_library(GLOG_LIBRARY_DEBUG glogd
-    PATHS ${GLOG_LIBRARYDIR})
+  find_library(GLOG_LIBRARY_RELEASE glog PATHS ${GLOG_LIBRARYDIR})
+  find_library(GLOG_LIBRARY_DEBUG glogd PATHS ${GLOG_LIBRARYDIR})
 
-  find_path(GLOG_INCLUDE_DIR glog/logging.h
-    PATHS ${GLOG_INCLUDEDIR})
+  find_path(GLOG_INCLUDE_DIR glog/logging.h PATHS ${GLOG_INCLUDEDIR})
 
   select_library_configurations(GLOG)
 
-  find_package_handle_standard_args(glog DEFAULT_MSG
-    GLOG_LIBRARY
-    GLOG_INCLUDE_DIR)
+  find_package_handle_standard_args(glog DEFAULT_MSG GLOG_LIBRARY
+                                    GLOG_INCLUDE_DIR)
 
-  mark_as_advanced(
-    GLOG_LIBRARY
-    GLOG_INCLUDE_DIR)
+  mark_as_advanced(GLOG_LIBRARY GLOG_INCLUDE_DIR)
 endif()
 
 if(NOT glog_FOUND)
@@ -56,26 +50,40 @@ endif()
 
 # glog::glog may already exist. Use google::glog to avoid conflicts.
 add_library(google::glog ${libglog_type} IMPORTED)
-set_target_properties(google::glog PROPERTIES INTERFACE_INCLUDE_DIRECTORIES "${GLOG_INCLUDE_DIR}")
-set_target_properties(google::glog PROPERTIES IMPORTED_LINK_INTERFACE_LANGUAGES "C" IMPORTED_LOCATION "${GLOG_LIBRARY}")
+set_target_properties(google::glog PROPERTIES INTERFACE_INCLUDE_DIRECTORIES
+                                              "${GLOG_INCLUDE_DIR}")
+set_target_properties(
+  google::glog PROPERTIES IMPORTED_LINK_INTERFACE_LANGUAGES "C"
+                          IMPORTED_LOCATION "${GLOG_LIBRARY}")
 
 set(GLUTEN_GFLAGS_VERSION 2.2.2)
-find_package(gflags ${GLUTEN_GFLAGS_VERSION} CONFIG COMPONENTS ${libgflags_component})
+find_package(gflags ${GLUTEN_GFLAGS_VERSION} CONFIG
+             COMPONENTS ${libgflags_component})
 
 if(NOT gflags_FOUND AND glog_FOUND)
-  message(FATAL_ERROR "Glog found but Gflags not found. Set BUILD_GLOG=ON and reload cmake.")
+  message(
+    FATAL_ERROR
+      "Glog found but Gflags not found. Set BUILD_GLOG=ON and reload cmake.")
 endif()
 
 if(gflags_FOUND)
-  if(NOT TARGET gflags::gflags_${libgflags_component} AND NOT TARGET gflags_${libgflags_component})
-    message(FATAL_ERROR "Found Gflags but missing component gflags_${libgflags_component}")
+  if(NOT TARGET gflags::gflags_${libgflags_component}
+     AND NOT TARGET gflags_${libgflags_component})
+    message(
+      FATAL_ERROR
+        "Found Gflags but missing component gflags_${libgflags_component}")
   endif()
   if(TARGET gflags::gflags_${libgflags_component})
-    set_target_properties(google::glog PROPERTIES IMPORTED_LINK_INTERFACE_LIBRARIES gflags::gflags_${libgflags_component})
+    set_target_properties(
+      google::glog PROPERTIES IMPORTED_LINK_INTERFACE_LIBRARIES
+                              gflags::gflags_${libgflags_component})
   else()
-    set_target_properties(google::glog PROPERTIES IMPORTED_LINK_INTERFACE_LIBRARIES gflags_${libgflags_component})
+    set_target_properties(
+      google::glog PROPERTIES IMPORTED_LINK_INTERFACE_LIBRARIES
+                              gflags_${libgflags_component})
   endif()
 else()
   include(BuildGflags)
-  set_target_properties(google::glog PROPERTIES IMPORTED_LINK_INTERFACE_LIBRARIES gflags_static)
+  set_target_properties(
+    google::glog PROPERTIES IMPORTED_LINK_INTERFACE_LIBRARIES gflags_static)
 endif()
diff --git a/cpp/CMake/Findjemalloc_pic.cmake b/cpp/CMake/Findjemalloc_pic.cmake
index 9511dcd33663..fae9f0d7ad80 100644
--- a/cpp/CMake/Findjemalloc_pic.cmake
+++ b/cpp/CMake/Findjemalloc_pic.cmake
@@ -20,7 +20,7 @@ macro(find_jemalloc)
   # Find the existing Protobuf
   set(CMAKE_FIND_LIBRARY_SUFFIXES ".a")
   find_package(jemalloc_pic)
-  if ("${Jemalloc_LIBRARY}" STREQUAL "Jemalloc_LIBRARY-NOTFOUND")
+  if("${Jemalloc_LIBRARY}" STREQUAL "Jemalloc_LIBRARY-NOTFOUND")
     message(FATAL_ERROR "Jemalloc Library Not Found")
   endif()
   set(PROTOC_BIN ${Jemalloc_PROTOC_EXECUTABLE})
@@ -35,22 +35,18 @@ macro(build_jemalloc)
   else()
     set(JEMALLOC_BUILD_VERSION "5.2.1")
     set(JEMALLOC_SOURCE_URL
-            "https://github.com/jemalloc/jemalloc/releases/download/${JEMALLOC_BUILD_VERSION}/jemalloc-${JEMALLOC_BUILD_VERSION}.tar.bz2"
-            "https://github.com/ursa-labs/thirdparty/releases/download/latest/jemalloc-${JEMALLOC_BUILD_VERSION}.tar.bz2"
-            )
+        "https://github.com/jemalloc/jemalloc/releases/download/${JEMALLOC_BUILD_VERSION}/jemalloc-${JEMALLOC_BUILD_VERSION}.tar.bz2"
+        "https://github.com/ursa-labs/thirdparty/releases/download/latest/jemalloc-${JEMALLOC_BUILD_VERSION}.tar.bz2"
+    )
   endif()
 
   set(JEMALLOC_PREFIX "${CMAKE_CURRENT_BINARY_DIR}/jemalloc_ep-install")
   set(JEMALLOC_LIB_DIR "${JEMALLOC_PREFIX}/lib")
   set(JEMALLOC_INCLUDE_DIR "${JEMALLOC_PREFIX}/include")
-  set(
-    JEMALLOC_STATIC_LIB
-    "${JEMALLOC_LIB_DIR}/${CMAKE_STATIC_LIBRARY_PREFIX}jemalloc_pic${CMAKE_STATIC_LIBRARY_SUFFIX}"
-    )
-  set(
-    JEMALLOC_INCLUDE
-    "${JEMALLOC_PREFIX}/include"
-    )
+  set(JEMALLOC_STATIC_LIB
+      "${JEMALLOC_LIB_DIR}/${CMAKE_STATIC_LIBRARY_PREFIX}jemalloc_pic${CMAKE_STATIC_LIBRARY_SUFFIX}"
+  )
+  set(JEMALLOC_INCLUDE "${JEMALLOC_PREFIX}/include")
   set(JEMALLOC_CONFIGURE_ARGS
       "AR=${CMAKE_AR}"
       "CC=${CMAKE_C_COMPILER}"
@@ -66,14 +62,15 @@ macro(build_jemalloc)
       "CFLAGS=-fPIC"
       "CXXFLAGS=-fPIC")
   set(JEMALLOC_BUILD_COMMAND ${MAKE} ${MAKE_BUILD_ARGS})
-  ExternalProject_Add(jemalloc_ep
-                      URL ${JEMALLOC_SOURCE_URL}
-                      PATCH_COMMAND touch doc/jemalloc.3 doc/jemalloc.html
-                      CONFIGURE_COMMAND "./configure" ${JEMALLOC_CONFIGURE_ARGS}
-                      BUILD_COMMAND ${JEMALLOC_BUILD_COMMAND}
-                      BUILD_IN_SOURCE 1
-                      BUILD_BYPRODUCTS "${JEMALLOC_STATIC_LIB}"
-                      INSTALL_COMMAND make install)
+  ExternalProject_Add(
+    jemalloc_ep
+    URL ${JEMALLOC_SOURCE_URL}
+    PATCH_COMMAND touch doc/jemalloc.3 doc/jemalloc.html
+    CONFIGURE_COMMAND "./configure" ${JEMALLOC_CONFIGURE_ARGS}
+    BUILD_COMMAND ${JEMALLOC_BUILD_COMMAND}
+    BUILD_IN_SOURCE 1
+    BUILD_BYPRODUCTS "${JEMALLOC_STATIC_LIB}"
+    INSTALL_COMMAND make install)
 
   file(MAKE_DIRECTORY "${JEMALLOC_INCLUDE_DIR}")
   add_library(jemalloc::libjemalloc STATIC IMPORTED)
@@ -81,7 +78,6 @@ macro(build_jemalloc)
     jemalloc::libjemalloc
     PROPERTIES INTERFACE_LINK_LIBRARIES Threads::Threads
                IMPORTED_LOCATION "${JEMALLOC_STATIC_LIB}"
-               INTERFACE_INCLUDE_DIRECTORIES
-               "${JEMALLOC_INCLUDE_DIR}")
+               INTERFACE_INCLUDE_DIRECTORIES "${JEMALLOC_INCLUDE_DIR}")
   add_dependencies(jemalloc::libjemalloc protobuf_ep)
 endmacro()
diff --git a/cpp/CMakeLists.txt b/cpp/CMakeLists.txt
index d6e3eeb133f7..3ee336dd6a14 100644
--- a/cpp/CMakeLists.txt
+++ b/cpp/CMakeLists.txt
@@ -19,13 +19,13 @@ message(STATUS "Building using CMake version: ${CMAKE_VERSION}")
 set(CMAKE_CXX_STANDARD 17)
 set(CMAKE_CXX_STANDARD_REQUIRED ON)
 
-# The set(CACHE) command does not remove any normal variable of the same name from the current scope
-# https://cmake.org/cmake/help/latest/policy/CMP0126.html
+# The set(CACHE) command does not remove any normal variable of the same name
+# from the current scope https://cmake.org/cmake/help/latest/policy/CMP0126.html
 if(POLICY CMP0126)
   cmake_policy(SET CMP0126 NEW)
 endif()
 
-if (CMAKE_VERSION VERSION_GREATER_EQUAL "3.24.0")
+if(CMAKE_VERSION VERSION_GREATER_EQUAL "3.24.0")
   cmake_policy(SET CMP0135 NEW)
 endif()
 
@@ -36,7 +36,9 @@ if(NOT DEFINED CMAKE_BUILD_TYPE)
 endif()
 
 set(CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/CMake" ${CMAKE_MODULE_PATH})
-set(CMAKE_EXPORT_COMPILE_COMMANDS ON CACHE INTERNAL "")
+set(CMAKE_EXPORT_COMPILE_COMMANDS
+    ON
+    CACHE INTERNAL "")
 
 project(gluten)
 
@@ -60,12 +62,12 @@ option(ENABLE_ABFS "Enable ABFS" OFF)
 set(root_directory ${PROJECT_BINARY_DIR})
 get_filename_component(GLUTEN_HOME ${CMAKE_SOURCE_DIR} DIRECTORY)
 
-if (NOT DEFINED VELOX_HOME)
+if(NOT DEFINED VELOX_HOME)
   set(VELOX_HOME ${GLUTEN_HOME}/ep/build-velox/build/velox_ep)
   message(STATUS "Set VELOX_HOME to ${VELOX_HOME}")
 endif()
 
-if (${CMAKE_BUILD_TYPE} STREQUAL "Debug")
+if(${CMAKE_BUILD_TYPE} STREQUAL "Debug")
   set(ARROW_HOME ${VELOX_HOME}/_build/debug/third_party/arrow_ep)
 else()
   set(ARROW_HOME ${VELOX_HOME}/_build/release/third_party/arrow_ep)
@@ -77,10 +79,10 @@ include(ResolveDependency)
 # Compiler flags
 #
 
-if (${CMAKE_BUILD_TYPE} STREQUAL "Debug")
+if(${CMAKE_BUILD_TYPE} STREQUAL "Debug")
   set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -ggdb -O0")
   message(STATUS "CMAKE_CXX_FLAGS_DEBUG=${CMAKE_CXX_FLAGS_DEBUG}")
-else ()
+else()
   add_definitions(-DNDEBUG)
   message(STATUS "Add definition NDEBUG")
 endif()
@@ -97,22 +99,20 @@ set(KNOWN_WARNINGS
        -Wno-ignored-qualifiers")
 
 if("${CMAKE_CXX_COMPILER_ID}" STREQUAL "GNU")
-  set(KNOWN_WARNINGS
-      "-Wno-error=unused-but-set-variable \
+  set(KNOWN_WARNINGS "-Wno-error=unused-but-set-variable \
       ${KNOWN_WARNINGS}")
   if(CMAKE_CXX_COMPILER_VERSION VERSION_LESS 11)
-    set(KNOWN_WARNINGS
-        "-Wno-error=maybe-uninitialized \
+    set(KNOWN_WARNINGS "-Wno-error=maybe-uninitialized \
       ${KNOWN_WARNINGS}")
   endif()
-elseif ("${CMAKE_CXX_COMPILER_ID}" STREQUAL "Clang")
+elseif("${CMAKE_CXX_COMPILER_ID}" STREQUAL "Clang")
   # Experimental
   set(KNOWN_WARNINGS
       "-Wno-implicit-int-float-conversion \
       -Wno-nullability-completeness \
       -Wno-mismatched-tags \
       ${KNOWN_WARNINGS}")
-elseif ("${CMAKE_CXX_COMPILER_ID}" STREQUAL "AppleClang")
+elseif("${CMAKE_CXX_COMPILER_ID}" STREQUAL "AppleClang")
   # Experimental
   set(KNOWN_WARNINGS
       "-Wno-implicit-int-float-conversion \
@@ -126,15 +126,16 @@ else()
 endif()
 
 # see https://issues.apache.org/jira/browse/ARROW-4665
-if (${CMAKE_SYSTEM_NAME} MATCHES "Darwin")
+if(${CMAKE_SYSTEM_NAME} MATCHES "Darwin")
   set(KNOWN_WARNINGS
       "-Wno-macro-redefined \
       -Wno-nullability-completeness \
       -Wno-pessimizing-move \
       -Wno-mismatched-tags \
       ${KNOWN_WARNINGS}")
-  # Specific definition for an issue with boost/stacktrace when building on macOS.
-  # See https://github.com/boostorg/stacktrace/issues/88 and comments therein.
+  # Specific definition for an issue with boost/stacktrace when building on
+  # macOS. See https://github.com/boostorg/stacktrace/issues/88 and comments
+  # therein.
   add_compile_definitions(_GNU_SOURCE)
 endif()
 
@@ -166,17 +167,11 @@ endif()
 function(ADD_TEST_CASE TEST_NAME)
   set(options)
   set(one_value_args)
-  set(multi_value_args
-      SOURCES
-      EXTRA_LINK_LIBS
-      EXTRA_INCLUDES
-      EXTRA_DEPENDENCIES)
-
-  cmake_parse_arguments(ARG
-      "${options}"
-      "${one_value_args}"
-      "${multi_value_args}"
-      ${ARGN})
+  set(multi_value_args SOURCES EXTRA_LINK_LIBS EXTRA_INCLUDES
+                       EXTRA_DEPENDENCIES)
+
+  cmake_parse_arguments(ARG "${options}" "${one_value_args}"
+                        "${multi_value_args}" ${ARGN})
 
   if(ARG_SOURCES)
     set(SOURCES ${ARG_SOURCES})
@@ -185,7 +180,8 @@ function(ADD_TEST_CASE TEST_NAME)
   endif()
 
   add_executable(${TEST_NAME} ${SOURCES})
-  target_link_libraries(${TEST_NAME} gluten google::glog GTest::gtest GTest::gtest_main Threads::Threads)
+  target_link_libraries(${TEST_NAME} gluten google::glog GTest::gtest
+                        GTest::gtest_main Threads::Threads)
   target_include_directories(${TEST_NAME} PRIVATE ${CMAKE_SOURCE_DIR}/core)
 
   if(ARG_EXTRA_LINK_LIBS)
diff --git a/cpp/core/CMakeLists.txt b/cpp/core/CMakeLists.txt
index dc9ce3435c38..3a4d6e9e8792 100644
--- a/cpp/core/CMakeLists.txt
+++ b/cpp/core/CMakeLists.txt
@@ -23,25 +23,27 @@ include(GNUInstallDirs)
 include(CheckCXXCompilerFlag)
 
 # Only set arch=native for non-AppleClang compilers.
-if (NOT CMAKE_CXX_COMPILER_ID MATCHES "AppleClang")
+if(NOT CMAKE_CXX_COMPILER_ID MATCHES "AppleClang")
   set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=native")
 endif()
 
 set(BOOST_MIN_VERSION "1.42.0")
 find_package(Boost REQUIRED)
-INCLUDE_DIRECTORIES(${Boost_INCLUDE_DIRS})
+include_directories(${Boost_INCLUDE_DIRS})
 set(source_root_directory ${CMAKE_CURRENT_SOURCE_DIR})
 
-if (CMAKE_VERSION VERSION_GREATER_EQUAL "3.24.0")
+if(CMAKE_VERSION VERSION_GREATER_EQUAL "3.24.0")
   cmake_policy(SET CMP0135 NEW)
 endif()
 
 set(CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/CMake" ${CMAKE_MODULE_PATH})
 
-set(SUBSTRAIT_PROTO_SRC_DIR ${GLUTEN_HOME}/gluten-core/src/main/resources/substrait/proto)
+set(SUBSTRAIT_PROTO_SRC_DIR
+    ${GLUTEN_HOME}/gluten-core/src/main/resources/substrait/proto)
 message(STATUS "Set Substrait Proto Directory in ${SUBSTRAIT_PROTO_SRC_DIR}")
 
-set(GLUTEN_PROTO_SRC_DIR ${GLUTEN_HOME}/gluten-core/src/main/resources/org/apache/gluten/proto)
+set(GLUTEN_PROTO_SRC_DIR
+    ${GLUTEN_HOME}/gluten-core/src/main/resources/org/apache/gluten/proto)
 message(STATUS "Set Gluten Proto Directory in ${GLUTEN_PROTO_SRC_DIR}")
 
 find_program(CCACHE_FOUND ccache)
@@ -58,31 +60,25 @@ macro(build_protobuf)
     set(PROTOBUF_SOURCE_URL "$ENV{GLUTEN_PROTOBUF_URL}")
   else()
     set(PROTOBUF_BUILD_VERSION "21.4")
-    set (PROTOBUF_SOURCE_URL
-            "https://github.com/protocolbuffers/protobuf/releases/download/v${PROTOBUF_BUILD_VERSION}/protobuf-all-${PROTOBUF_BUILD_VERSION}.tar.gz")
+    set(PROTOBUF_SOURCE_URL
+        "https://github.com/protocolbuffers/protobuf/releases/download/v${PROTOBUF_BUILD_VERSION}/protobuf-all-${PROTOBUF_BUILD_VERSION}.tar.gz"
+    )
   endif()
-  set(PROTOBUF_BUILD_SHA256_CHECKSUM "6c5e1b0788afba4569aeebb2cfe205cb154aa01deacaba0cd26442f3b761a836")
+  set(PROTOBUF_BUILD_SHA256_CHECKSUM
+      "6c5e1b0788afba4569aeebb2cfe205cb154aa01deacaba0cd26442f3b761a836")
 
   set(PROTOBUF_PREFIX "${CMAKE_CURRENT_BINARY_DIR}/protobuf_ep-install")
   set(PROTOBUF_INCLUDE_DIR "${PROTOBUF_PREFIX}/include")
-  set(
-    PROTOBUF_STATIC_LIB
-    "${PROTOBUF_PREFIX}/lib/${CMAKE_STATIC_LIBRARY_PREFIX}protobuf${CMAKE_STATIC_LIBRARY_SUFFIX}"
-    )
-  set(
-    PROTOC_STATIC_LIB
-    "${PROTOBUF_PREFIX}/lib/${CMAKE_STATIC_LIBRARY_PREFIX}protoc${CMAKE_STATIC_LIBRARY_SUFFIX}"
-    )
-  set(
-    PROTOC_BIN
-    "${PROTOBUF_PREFIX}/bin/protoc"
-    )
-  set(
-    PROTOBUF_INCLUDE
-    "${PROTOBUF_PREFIX}/include"
-    CACHE PATH
-    "Protobuf include path"
-    )
+  set(PROTOBUF_STATIC_LIB
+      "${PROTOBUF_PREFIX}/lib/${CMAKE_STATIC_LIBRARY_PREFIX}protobuf${CMAKE_STATIC_LIBRARY_SUFFIX}"
+  )
+  set(PROTOC_STATIC_LIB
+      "${PROTOBUF_PREFIX}/lib/${CMAKE_STATIC_LIBRARY_PREFIX}protoc${CMAKE_STATIC_LIBRARY_SUFFIX}"
+  )
+  set(PROTOC_BIN "${PROTOBUF_PREFIX}/bin/protoc")
+  set(PROTOBUF_INCLUDE
+      "${PROTOBUF_PREFIX}/include"
+      CACHE PATH "Protobuf include path")
   set(PROTOBUF_COMPILER "${PROTOBUF_PREFIX}/bin/protoc")
   set(PROTOBUF_CONFIGURE_ARGS
       "AR=${CMAKE_AR}"
@@ -94,22 +90,23 @@ macro(build_protobuf)
       "CFLAGS=-fPIC"
       "CXXFLAGS=-fPIC")
   set(PROTOBUF_BUILD_COMMAND ${MAKE} ${MAKE_BUILD_ARGS})
-  ExternalProject_Add(protobuf_ep
-                      PREFIX protobuf_ep
-                      CONFIGURE_COMMAND ./autogen.sh COMMAND "./configure" ${PROTOBUF_CONFIGURE_ARGS}
-                      BUILD_BYPRODUCTS "${PROTOBUF_STATIC_LIB}" "${PROTOBUF_COMPILER}"
-                      BUILD_COMMAND ${PROTOBUF_BUILD_COMMAND}
-                      BUILD_IN_SOURCE 1
-                      URL ${PROTOBUF_SOURCE_URL}
-                      URL_HASH "SHA256=${PROTOBUF_BUILD_SHA256_CHECKSUM}"
-  )
+  ExternalProject_Add(
+    protobuf_ep
+    PREFIX protobuf_ep
+    CONFIGURE_COMMAND ./autogen.sh
+    COMMAND "./configure" ${PROTOBUF_CONFIGURE_ARGS}
+    BUILD_BYPRODUCTS "${PROTOBUF_STATIC_LIB}" "${PROTOBUF_COMPILER}"
+    BUILD_COMMAND ${PROTOBUF_BUILD_COMMAND}
+    BUILD_IN_SOURCE 1
+    URL ${PROTOBUF_SOURCE_URL}
+    URL_HASH "SHA256=${PROTOBUF_BUILD_SHA256_CHECKSUM}")
 
   file(MAKE_DIRECTORY "${PROTOBUF_INCLUDE_DIR}")
   add_library(protobuf::libprotobuf STATIC IMPORTED)
   set_target_properties(
     protobuf::libprotobuf
-    PROPERTIES IMPORTED_LOCATION "${PROTOBUF_STATIC_LIB}" INTERFACE_INCLUDE_DIRECTORIES
-               "${PROTOBUF_INCLUDE_DIR}")
+    PROPERTIES IMPORTED_LOCATION "${PROTOBUF_STATIC_LIB}"
+               INTERFACE_INCLUDE_DIRECTORIES "${PROTOBUF_INCLUDE_DIR}")
   add_dependencies(protobuf::libprotobuf protobuf_ep)
 endmacro()
 
@@ -117,17 +114,19 @@ macro(find_protobuf)
   # Find the existing Protobuf
   set(CMAKE_FIND_LIBRARY_SUFFIXES ".a")
   find_package(Protobuf)
-  if ("${Protobuf_LIBRARY}" STREQUAL "Protobuf_LIBRARY-NOTFOUND")
+  if("${Protobuf_LIBRARY}" STREQUAL "Protobuf_LIBRARY-NOTFOUND")
     message(FATAL_ERROR "Protobuf Library Not Found")
   endif()
   set(PROTOC_BIN ${Protobuf_PROTOC_EXECUTABLE})
-  set(PROTOBUF_INCLUDE "${Protobuf_INCLUDE_DIRS}" CACHE PATH "Protobuf include path")
+  set(PROTOBUF_INCLUDE
+      "${Protobuf_INCLUDE_DIRS}"
+      CACHE PATH "Protobuf include path")
 endmacro()
 
 if(USE_AVX512)
   # Only enable additional instruction sets if they are supported
   message(STATUS "System processor: ${CMAKE_SYSTEM_PROCESSOR}")
-  if (CMAKE_SYSTEM_PROCESSOR MATCHES "(x86)|(X86)|(amd64)|(AMD64)")
+  if(CMAKE_SYSTEM_PROCESSOR MATCHES "(x86)|(X86)|(amd64)|(AMD64)")
     set(AVX512_FLAG "-march=skylake-avx512")
     check_cxx_compiler_flag(${AVX512_FLAG} CXX_SUPPORTS_AVX512)
     if(NOT CXX_SUPPORTS_AVX512)
@@ -135,7 +134,7 @@ if(USE_AVX512)
     endif()
     set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${AVX512_FLAG}")
     add_definitions(-DCOLUMNAR_PLUGIN_USE_AVX512)
-  endif ()
+  endif()
 endif()
 
 # Set up Proto
@@ -144,83 +143,90 @@ file(MAKE_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}/proto)
 
 # List Substrait Proto compiled files
 file(GLOB SUBSTRAIT_PROTO_FILES ${SUBSTRAIT_PROTO_SRC_DIR}/substrait/*.proto
-        ${SUBSTRAIT_PROTO_SRC_DIR}/substrait/extensions/*.proto)
-FOREACH(PROTO ${SUBSTRAIT_PROTO_FILES})
+     ${SUBSTRAIT_PROTO_SRC_DIR}/substrait/extensions/*.proto)
+foreach(PROTO ${SUBSTRAIT_PROTO_FILES})
   file(RELATIVE_PATH REL_PROTO ${SUBSTRAIT_PROTO_SRC_DIR} ${PROTO})
   string(REGEX REPLACE "\\.proto" "" PROTO_NAME ${REL_PROTO})
-  LIST(APPEND SUBSTRAIT_PROTO_SRCS "${PROTO_OUTPUT_DIR}/${PROTO_NAME}.pb.cc")
-  LIST(APPEND SUBSTRAIT_PROTO_HDRS "${PROTO_OUTPUT_DIR}/${PROTO_NAME}.pb.h")
-ENDFOREACH()
-set(SUBSTRAIT_PROTO_OUTPUT_FILES ${SUBSTRAIT_PROTO_HDRS} ${SUBSTRAIT_PROTO_SRCS})
-set_source_files_properties(${SUBSTRAIT_PROTO_OUTPUT_FILES} PROPERTIES GENERATED TRUE)
-get_filename_component(SUBSTRAIT_PROTO_DIR ${SUBSTRAIT_PROTO_SRC_DIR}/ DIRECTORY)
+  list(APPEND SUBSTRAIT_PROTO_SRCS "${PROTO_OUTPUT_DIR}/${PROTO_NAME}.pb.cc")
+  list(APPEND SUBSTRAIT_PROTO_HDRS "${PROTO_OUTPUT_DIR}/${PROTO_NAME}.pb.h")
+endforeach()
+set(SUBSTRAIT_PROTO_OUTPUT_FILES ${SUBSTRAIT_PROTO_HDRS}
+                                 ${SUBSTRAIT_PROTO_SRCS})
+set_source_files_properties(${SUBSTRAIT_PROTO_OUTPUT_FILES} PROPERTIES GENERATED
+                                                                       TRUE)
+get_filename_component(SUBSTRAIT_PROTO_DIR ${SUBSTRAIT_PROTO_SRC_DIR}/
+                       DIRECTORY)
 
 # List Gluten Proto compiled files
 file(GLOB GLUTEN_PROTO_FILES ${GLUTEN_PROTO_SRC_DIR}/*.proto)
-FOREACH(PROTO ${GLUTEN_PROTO_FILES})
+foreach(PROTO ${GLUTEN_PROTO_FILES})
   file(RELATIVE_PATH REL_PROTO ${GLUTEN_PROTO_SRC_DIR} ${PROTO})
   string(REGEX REPLACE "\\.proto" "" PROTO_NAME ${REL_PROTO})
-  LIST(APPEND GLUTEN_PROTO_SRCS "${PROTO_OUTPUT_DIR}/${PROTO_NAME}.pb.cc")
-  LIST(APPEND GLUTEN_PROTO_HDRS "${PROTO_OUTPUT_DIR}/${PROTO_NAME}.pb.h")
-ENDFOREACH()
+  list(APPEND GLUTEN_PROTO_SRCS "${PROTO_OUTPUT_DIR}/${PROTO_NAME}.pb.cc")
+  list(APPEND GLUTEN_PROTO_HDRS "${PROTO_OUTPUT_DIR}/${PROTO_NAME}.pb.h")
+endforeach()
 set(GLUTEN_PROTO_OUTPUT_FILES ${GLUTEN_PROTO_HDRS} ${GLUTEN_PROTO_SRCS})
-set_source_files_properties(${GLUTEN_PROTO_OUTPUT_FILES} PROPERTIES GENERATED TRUE)
+set_source_files_properties(${GLUTEN_PROTO_OUTPUT_FILES} PROPERTIES GENERATED
+                                                                    TRUE)
 get_filename_component(GLUTEN_PROTO_DIR ${GLUTEN_PROTO_SRC_DIR}/ DIRECTORY)
 
-set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wno-deprecated-declarations -Wno-attributes")
+set(CMAKE_CXX_FLAGS
+    "${CMAKE_CXX_FLAGS} -Wno-deprecated-declarations -Wno-attributes")
 
 message("Core module final CMAKE_CXX_FLAGS=${CMAKE_CXX_FLAGS}")
 
 set(SPARK_COLUMNAR_PLUGIN_SRCS
-        ${SUBSTRAIT_PROTO_SRCS}
-        ${GLUTEN_PROTO_SRCS}
-        compute/Runtime.cc
-        compute/ProtobufUtils.cc
-        compute/ResultIterator.cc
-        config/GlutenConfig.cc
-        jni/JniWrapper.cc
-        memory/AllocationListener.cc
-        memory/MemoryAllocator.cc
-        memory/ArrowMemoryPool.cc
-        memory/ColumnarBatch.cc
-        operators/writer/ArrowWriter.cc
-        shuffle/FallbackRangePartitioner.cc
-        shuffle/HashPartitioner.cc
-        shuffle/LocalPartitionWriter.cc
-        shuffle/Options.cc
-        shuffle/Partitioner.cc
-        shuffle/Partitioning.cc
-        shuffle/Payload.cc
-        shuffle/rss/RssPartitionWriter.cc
-        shuffle/RoundRobinPartitioner.cc
-        shuffle/ShuffleMemoryPool.cc
-        shuffle/ShuffleReader.cc
-        shuffle/SinglePartitioner.cc
-        shuffle/Spill.cc
-        shuffle/Utils.cc
-        utils/Compression.cc
-        utils/StringUtil.cc
-        utils/ObjectStore.cc
-        jni/JniError.cc
-        jni/JniCommon.cc)
+    ${SUBSTRAIT_PROTO_SRCS}
+    ${GLUTEN_PROTO_SRCS}
+    compute/Runtime.cc
+    compute/ProtobufUtils.cc
+    compute/ResultIterator.cc
+    config/GlutenConfig.cc
+    jni/JniWrapper.cc
+    memory/AllocationListener.cc
+    memory/MemoryAllocator.cc
+    memory/ArrowMemoryPool.cc
+    memory/ColumnarBatch.cc
+    operators/writer/ArrowWriter.cc
+    shuffle/FallbackRangePartitioner.cc
+    shuffle/HashPartitioner.cc
+    shuffle/LocalPartitionWriter.cc
+    shuffle/Options.cc
+    shuffle/Partitioner.cc
+    shuffle/Partitioning.cc
+    shuffle/Payload.cc
+    shuffle/rss/RssPartitionWriter.cc
+    shuffle/RoundRobinPartitioner.cc
+    shuffle/ShuffleMemoryPool.cc
+    shuffle/ShuffleReader.cc
+    shuffle/SinglePartitioner.cc
+    shuffle/Spill.cc
+    shuffle/Utils.cc
+    utils/Compression.cc
+    utils/StringUtil.cc
+    utils/ObjectStore.cc
+    jni/JniError.cc
+    jni/JniCommon.cc)
 
 file(MAKE_DIRECTORY ${root_directory}/releases)
 add_library(gluten SHARED ${SPARK_COLUMNAR_PLUGIN_SRCS})
 add_dependencies(gluten jni_proto)
 
 if(ENABLE_GLUTEN_VCPKG)
-  # Hide symbols of some static dependencies. Otherwise, if such dependencies are already
-  # statically linked to libvelox.so, a runtime error will be reported: xxx is being linked
-  # both statically and dynamically.
-  target_link_options(gluten PRIVATE -Wl,--version-script=${CMAKE_CURRENT_SOURCE_DIR}/symbols.map)
+  # Hide symbols of some static dependencies. Otherwise, if such dependencies
+  # are already statically linked to libvelox.so, a runtime error will be
+  # reported: xxx is being linked both statically and dynamically.
+  target_link_options(
+    gluten PRIVATE -Wl,--version-script=${CMAKE_CURRENT_SOURCE_DIR}/symbols.map)
 endif()
 
 if(CMAKE_CXX_COMPILER_VERSION VERSION_LESS 9.0)
-  execute_process(COMMAND ${CMAKE_C_COMPILER} -print-file-name=libstdc++fs.a
+  execute_process(
+    COMMAND ${CMAKE_C_COMPILER} -print-file-name=libstdc++fs.a
     RESULT_VARIABLE LIBSTDCXXFS_STATIC_RESULT
     OUTPUT_VARIABLE LIBSTDCXXFS_STATIC_PATH
     OUTPUT_STRIP_TRAILING_WHITESPACE)
-  if (LIBSTDCXXFS_STATIC_RESULT EQUAL 0 AND EXISTS "${LIBSTDCXXFS_STATIC_PATH}")
+  if(LIBSTDCXXFS_STATIC_RESULT EQUAL 0 AND EXISTS "${LIBSTDCXXFS_STATIC_PATH}")
     message(STATUS "libstdc++fs.a found at: ${LIBSTDCXXFS_STATIC_PATH}")
     target_link_libraries(gluten PRIVATE ${LIBSTDCXXFS_STATIC_PATH})
   else()
@@ -243,57 +249,55 @@ if(ENABLE_QAT)
   include(BuildQATzip)
   include(BuildQATZstd)
   target_sources(gluten PRIVATE utils/qat/QatCodec.cc)
-  target_include_directories(gluten PUBLIC ${QATZIP_INCLUDE_DIR} ${QATZSTD_INCLUDE_DIR})
+  target_include_directories(gluten PUBLIC ${QATZIP_INCLUDE_DIR}
+                                           ${QATZSTD_INCLUDE_DIR})
   target_link_libraries(gluten PUBLIC qatzip::qatzip qatzstd::qatzstd)
 endif()
 
 if(ENABLE_IAA)
   include(BuildQpl)
   target_include_directories(gluten PUBLIC ${QPL_INCLUDE_DIR})
-  target_sources(gluten PRIVATE utils/qpl/qpl_job_pool.cc utils/qpl/qpl_codec.cc)
+  target_sources(gluten PRIVATE utils/qpl/qpl_job_pool.cc
+                                utils/qpl/qpl_codec.cc)
   target_link_libraries(gluten PUBLIC qpl::qpl)
 endif()
 
 if(BUILD_PROTOBUF)
   build_protobuf()
   message(STATUS "Building ProtoBuf from Source: ${BUILD_PROTOBUF}")
-  target_link_libraries(gluten
-                        LINK_PRIVATE protobuf::libprotobuf)
+  target_link_libraries(gluten LINK_PRIVATE protobuf::libprotobuf)
 else()
   find_protobuf()
   message(STATUS "Use existing ProtoBuf libraries: ${PROTOBUF_LIBRARY}")
-  target_link_libraries(gluten
-                        LINK_PUBLIC ${PROTOBUF_LIBRARY})
+  target_link_libraries(gluten LINK_PUBLIC ${PROTOBUF_LIBRARY})
 endif()
 
-add_custom_command(OUTPUT ${SUBSTRAIT_PROTO_OUTPUT_FILES}
-        COMMAND ${PROTOC_BIN}
-        --proto_path
-        ${SUBSTRAIT_PROTO_SRC_DIR}/
-        --cpp_out
-        ${PROTO_OUTPUT_DIR}
-        ${SUBSTRAIT_PROTO_FILES}
-        DEPENDS  ${SUBSTRAIT_PROTO_DIR}
-        COMMENT "Running Substrait PROTO compiler"
-        VERBATIM)
-
-add_custom_command(OUTPUT ${GLUTEN_PROTO_OUTPUT_FILES}
-        COMMAND ${PROTOC_BIN}
-        --proto_path
-        ${GLUTEN_PROTO_SRC_DIR}/
-        --cpp_out
-        ${PROTO_OUTPUT_DIR}
-        ${GLUTEN_PROTO_FILES}
-        DEPENDS  ${GLUTEN_PROTO_DIR}
-        COMMENT "Running Gluten PROTO compiler"
-        VERBATIM)
-
-add_custom_target(jni_proto ALL DEPENDS ${SUBSTRAIT_PROTO_OUTPUT_FILES} ${GLUTEN_PROTO_OUTPUT_FILES})
+add_custom_command(
+  OUTPUT ${SUBSTRAIT_PROTO_OUTPUT_FILES}
+  COMMAND ${PROTOC_BIN} --proto_path ${SUBSTRAIT_PROTO_SRC_DIR}/ --cpp_out
+          ${PROTO_OUTPUT_DIR} ${SUBSTRAIT_PROTO_FILES}
+  DEPENDS ${SUBSTRAIT_PROTO_DIR}
+  COMMENT "Running Substrait PROTO compiler"
+  VERBATIM)
+
+add_custom_command(
+  OUTPUT ${GLUTEN_PROTO_OUTPUT_FILES}
+  COMMAND ${PROTOC_BIN} --proto_path ${GLUTEN_PROTO_SRC_DIR}/ --cpp_out
+          ${PROTO_OUTPUT_DIR} ${GLUTEN_PROTO_FILES}
+  DEPENDS ${GLUTEN_PROTO_DIR}
+  COMMENT "Running Gluten PROTO compiler"
+  VERBATIM)
+
+add_custom_target(jni_proto ALL DEPENDS ${SUBSTRAIT_PROTO_OUTPUT_FILES}
+                                        ${GLUTEN_PROTO_OUTPUT_FILES})
 add_dependencies(jni_proto protobuf::libprotobuf)
 
-target_include_directories(gluten PUBLIC ${CMAKE_SYSTEM_INCLUDE_PATH} ${JNI_INCLUDE_DIRS} ${CMAKE_CURRENT_SOURCE_DIR} ${PROTO_OUTPUT_DIR} ${PROTOBUF_INCLUDE})
-set_target_properties(gluten PROPERTIES
-        LIBRARY_OUTPUT_DIRECTORY ${root_directory}/releases)
+target_include_directories(
+  gluten
+  PUBLIC ${CMAKE_SYSTEM_INCLUDE_PATH} ${JNI_INCLUDE_DIRS}
+         ${CMAKE_CURRENT_SOURCE_DIR} ${PROTO_OUTPUT_DIR} ${PROTOBUF_INCLUDE})
+set_target_properties(gluten PROPERTIES LIBRARY_OUTPUT_DIRECTORY
+                                        ${root_directory}/releases)
 
 include(Findjemalloc_pic)
 # Build Jemalloc
@@ -313,23 +317,26 @@ if(BUILD_BENCHMARKS)
   add_subdirectory(benchmarks)
 endif()
 
-
 if(DEFINED ENV{HADOOP_HOME})
   set(LIBHDFS3_DESTINATION $ENV{HADOOP_HOME}/lib/native)
 else()
   set(LIBHDFS3_DESTINATION ${CMAKE_INSTALL_LIBDIR})
 endif()
 
-target_link_libraries(gluten
-    PUBLIC Arrow::arrow Arrow::parquet)
+target_link_libraries(gluten PUBLIC Arrow::arrow Arrow::parquet)
 target_link_libraries(gluten PRIVATE google::glog)
 
-install(TARGETS gluten
-        DESTINATION ${CMAKE_INSTALL_LIBDIR})
+install(TARGETS gluten DESTINATION ${CMAKE_INSTALL_LIBDIR})
 install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/resources/libhdfs.so
         DESTINATION ${LIBHDFS3_DESTINATION})
 
-add_custom_command(TARGET gluten POST_BUILD COMMAND ld $<TARGET_FILE:gluten> || true
-        COMMENT "Checking ld result of libgluten.so")
-add_custom_command(TARGET gluten POST_BUILD COMMAND ldd $<TARGET_FILE:gluten> || true
-        COMMENT "Checking ldd result of libgluten.so")
+add_custom_command(
+  TARGET gluten
+  POST_BUILD
+  COMMAND ld $<TARGET_FILE:gluten> || true
+  COMMENT "Checking ld result of libgluten.so")
+add_custom_command(
+  TARGET gluten
+  POST_BUILD
+  COMMAND ldd $<TARGET_FILE:gluten> || true
+  COMMENT "Checking ldd result of libgluten.so")
diff --git a/cpp/core/benchmarks/CMakeLists.txt b/cpp/core/benchmarks/CMakeLists.txt
index 6d39501477df..4b4c7656639c 100644
--- a/cpp/core/benchmarks/CMakeLists.txt
+++ b/cpp/core/benchmarks/CMakeLists.txt
@@ -31,7 +31,8 @@
 
 macro(package_add_gbenchmark TESTNAME)
   add_executable(${TESTNAME} ${ARGN})
-  target_link_libraries(${TESTNAME} benchmark::benchmark gluten google::glog ${CMAKE_THREAD_LIBS_INIT})
+  target_link_libraries(${TESTNAME} benchmark::benchmark gluten google::glog
+                        ${CMAKE_THREAD_LIBS_INIT})
   target_include_directories(${TESTNAME} PUBLIC ${source_root_directory})
   set_target_properties(${TESTNAME} PROPERTIES FOLDER tests)
 endmacro()
diff --git a/cpp/velox/CMakeLists.txt b/cpp/velox/CMakeLists.txt
index 34cc9001cf38..6d66ea506a7e 100644
--- a/cpp/velox/CMakeLists.txt
+++ b/cpp/velox/CMakeLists.txt
@@ -23,39 +23,54 @@ include(GNUInstallDirs)
 include(CheckCXXCompilerFlag)
 include(FindPackageHandleStandardArgs)
 
-set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wno-deprecated-declarations -Wno-attributes")
-if (NOT ${CMAKE_SYSTEM_NAME} STREQUAL "Darwin")
+set(CMAKE_CXX_FLAGS
+    "${CMAKE_CXX_FLAGS} -Wno-deprecated-declarations -Wno-attributes")
+if(NOT ${CMAKE_SYSTEM_NAME} STREQUAL "Darwin")
   set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wno-class-memaccess")
 endif()
 
-set(SYSTEM_LIB_PATH "/usr/lib" CACHE PATH "System Lib dir")
-set(SYSTEM_LIB64_PATH "/usr/lib64" CACHE PATH "System Lib64 dir")
-set(SYSTEM_LOCAL_LIB_PATH "/usr/local/lib" CACHE PATH "System Local Lib dir")
-set(SYSTEM_LOCAL_LIB64_PATH "/usr/local/lib64" CACHE PATH "System Local Lib64 dir")
-if (CMAKE_SYSTEM_PROCESSOR MATCHES "(x86)|(X86)|(amd64)|(AMD64)")
-  set(SYSTEM_LIB_MULTIARCH_PATH "/usr/lib/x86_64-linux-gnu" CACHE PATH "System Lib MultiArch dir")
+set(SYSTEM_LIB_PATH
+    "/usr/lib"
+    CACHE PATH "System Lib dir")
+set(SYSTEM_LIB64_PATH
+    "/usr/lib64"
+    CACHE PATH "System Lib64 dir")
+set(SYSTEM_LOCAL_LIB_PATH
+    "/usr/local/lib"
+    CACHE PATH "System Local Lib dir")
+set(SYSTEM_LOCAL_LIB64_PATH
+    "/usr/local/lib64"
+    CACHE PATH "System Local Lib64 dir")
+if(CMAKE_SYSTEM_PROCESSOR MATCHES "(x86)|(X86)|(amd64)|(AMD64)")
+  set(SYSTEM_LIB_MULTIARCH_PATH
+      "/usr/lib/x86_64-linux-gnu"
+      CACHE PATH "System Lib MultiArch dir")
 elseif(CMAKE_SYSTEM_PROCESSOR STREQUAL aarch64)
-  set(SYSTEM_LIB_MULTIARCH_PATH "/usr/lib/aarch64-linux-gnu" CACHE PATH "System Lib MultiArch dir")
+  set(SYSTEM_LIB_MULTIARCH_PATH
+      "/usr/lib/aarch64-linux-gnu"
+      CACHE PATH "System Lib MultiArch dir")
 elseif(CMAKE_SYSTEM_PROCESSOR STREQUAL arm64)
-  set(SYSTEM_LIB_MULTIARCH_PATH "/usr/lib" CACHE PATH "System Lib MultiArch dir")
+  set(SYSTEM_LIB_MULTIARCH_PATH
+      "/usr/lib"
+      CACHE PATH "System Lib MultiArch dir")
 else()
   message(FATAL_ERROR "Unsupported processor type: ${CMAKE_SYSTEM_PROCESSOR}")
 endif()
 
-if (NOT DEFINED VELOX_HOME)
+if(NOT DEFINED VELOX_HOME)
   set(VELOX_HOME ${GLUTEN_HOME}/ep/build-velox/build/velox_ep)
   message(STATUS "Set VELOX_HOME to ${VELOX_HOME}")
 endif()
 
 # Keep same compile option with Velox.
 execute_process(
-    COMMAND
+  COMMAND
     bash -c
     "( source ${VELOX_HOME}/scripts/setup-helper-functions.sh && echo -n $(get_cxx_flags $ENV{CPU_TARGET}))"
-    OUTPUT_VARIABLE SCRIPT_CXX_FLAGS
-    RESULT_VARIABLE COMMAND_STATUS)
+  OUTPUT_VARIABLE SCRIPT_CXX_FLAGS
+  RESULT_VARIABLE COMMAND_STATUS)
 if(COMMAND_STATUS EQUAL "1")
-    message(FATAL_ERROR "Unable to determine compiler flags!")
+  message(FATAL_ERROR "Unable to determine compiler flags!")
 endif()
 set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${SCRIPT_CXX_FLAGS}")
 
@@ -63,10 +78,14 @@ message("Velox module final CMAKE_CXX_FLAGS=${CMAKE_CXX_FLAGS}")
 
 # User can specify VELOX_BUILD_PATH, if Velox are built elsewhere.
 if(NOT DEFINED VELOX_BUILD_PATH)
-  if (${CMAKE_BUILD_TYPE} STREQUAL "Debug")
-    set(VELOX_BUILD_PATH "${VELOX_HOME}/_build/debug" CACHE PATH "Velox build directory.")
+  if(${CMAKE_BUILD_TYPE} STREQUAL "Debug")
+    set(VELOX_BUILD_PATH
+        "${VELOX_HOME}/_build/debug"
+        CACHE PATH "Velox build directory.")
   else()
-    set(VELOX_BUILD_PATH "${VELOX_HOME}/_build/release" CACHE PATH "Velox build directory.")
+    set(VELOX_BUILD_PATH
+        "${VELOX_HOME}/_build/release"
+        CACHE PATH "Velox build directory.")
   endif()
 endif()
 
@@ -78,25 +97,28 @@ function(ADD_VELOX_DEPENDENCY VELOX_DEP_LIB_NAME VELOX_DEP_LIB_PATH)
   endif()
   set(VELOX_DEP_LIB facebook::velox::${VELOX_DEP_LIB_NAME})
   add_library(${VELOX_DEP_LIB} STATIC IMPORTED)
-  set_target_properties(${VELOX_DEP_LIB} PROPERTIES
-      IMPORTED_LOCATION ${VELOX_DEP_LIB_PATH})
+  set_target_properties(${VELOX_DEP_LIB} PROPERTIES IMPORTED_LOCATION
+                                                    ${VELOX_DEP_LIB_PATH})
   target_link_libraries(velox PUBLIC ${VELOX_DEP_LIB})
 endfunction()
 
 macro(ADD_VELOX_OBJECTS)
   add_library(velox_objects OBJECT IMPORTED GLOBAL)
-  set_property(TARGET velox_objects PROPERTY IMPORTED_OBJECTS
-          "${VELOX_COMPONENTS_PATH}/connectors/hive/CMakeFiles/velox_hive_connector.dir/FileHandle.cpp.o"
-          "${VELOX_COMPONENTS_PATH}/connectors/hive/CMakeFiles/velox_hive_connector.dir/HiveConfig.cpp.o"
-          "${VELOX_COMPONENTS_PATH}/connectors/hive/CMakeFiles/velox_hive_connector.dir/HiveConnector.cpp.o"
-          "${VELOX_COMPONENTS_PATH}/connectors/hive/CMakeFiles/velox_hive_connector.dir/HiveDataSink.cpp.o"
-          "${VELOX_COMPONENTS_PATH}/connectors/hive/CMakeFiles/velox_hive_connector.dir/HiveDataSource.cpp.o"
-          "${VELOX_COMPONENTS_PATH}/connectors/hive/CMakeFiles/velox_hive_connector.dir/HivePartitionUtil.cpp.o"
-          "${VELOX_COMPONENTS_PATH}/connectors/hive/CMakeFiles/velox_hive_connector.dir/PartitionIdGenerator.cpp.o"
-          "${VELOX_COMPONENTS_PATH}/connectors/hive/CMakeFiles/velox_hive_connector.dir/SplitReader.cpp.o"
-          "${VELOX_COMPONENTS_PATH}/connectors/hive/CMakeFiles/velox_hive_connector.dir/TableHandle.cpp.o"
-          "${VELOX_COMPONENTS_PATH}/connectors/hive/CMakeFiles/velox_hive_connector.dir/HiveConnectorUtil.cpp.o"
-          )
+  set_property(
+    TARGET velox_objects
+    PROPERTY
+      IMPORTED_OBJECTS
+      "${VELOX_COMPONENTS_PATH}/connectors/hive/CMakeFiles/velox_hive_connector.dir/FileHandle.cpp.o"
+      "${VELOX_COMPONENTS_PATH}/connectors/hive/CMakeFiles/velox_hive_connector.dir/HiveConfig.cpp.o"
+      "${VELOX_COMPONENTS_PATH}/connectors/hive/CMakeFiles/velox_hive_connector.dir/HiveConnector.cpp.o"
+      "${VELOX_COMPONENTS_PATH}/connectors/hive/CMakeFiles/velox_hive_connector.dir/HiveDataSink.cpp.o"
+      "${VELOX_COMPONENTS_PATH}/connectors/hive/CMakeFiles/velox_hive_connector.dir/HiveDataSource.cpp.o"
+      "${VELOX_COMPONENTS_PATH}/connectors/hive/CMakeFiles/velox_hive_connector.dir/HivePartitionUtil.cpp.o"
+      "${VELOX_COMPONENTS_PATH}/connectors/hive/CMakeFiles/velox_hive_connector.dir/PartitionIdGenerator.cpp.o"
+      "${VELOX_COMPONENTS_PATH}/connectors/hive/CMakeFiles/velox_hive_connector.dir/SplitReader.cpp.o"
+      "${VELOX_COMPONENTS_PATH}/connectors/hive/CMakeFiles/velox_hive_connector.dir/TableHandle.cpp.o"
+      "${VELOX_COMPONENTS_PATH}/connectors/hive/CMakeFiles/velox_hive_connector.dir/HiveConnectorUtil.cpp.o"
+  )
   target_link_libraries(velox PUBLIC velox_objects)
 endmacro()
 
@@ -112,125 +134,302 @@ endmacro()
 
 macro(ADD_VELOX_DEPENDENCIES)
   add_velox_objects()
-  add_velox_dependency(expression::sigparser "${VELOX_COMPONENTS_PATH}/expression/signature_parser/libvelox_signature_parser.a")
-  add_velox_dependency(functions::sparksql::lib "${VELOX_COMPONENTS_PATH}/functions/sparksql/libvelox_functions_spark.a")
-  add_velox_dependency(functions::sparksql::agg "${VELOX_COMPONENTS_PATH}/functions/sparksql/aggregates/libvelox_functions_spark_aggregates.a")
-  add_velox_dependency(functions::window::sparksql "${VELOX_COMPONENTS_PATH}/functions/sparksql/window/libvelox_functions_spark_window.a")
-  add_velox_dependency(functions::prestosql::agg "${VELOX_COMPONENTS_PATH}/functions/prestosql/aggregates/libvelox_aggregates.a")
-  add_velox_dependency(functions::lib::agg "${VELOX_COMPONENTS_PATH}/functions/lib/aggregates/libvelox_functions_aggregates.a")
-  add_velox_dependency(functions::prestosql::window "${VELOX_COMPONENTS_PATH}/functions/prestosql/window/libvelox_window.a")
-  add_velox_dependency(functions::lib::window "${VELOX_COMPONENTS_PATH}/functions/lib/window/libvelox_functions_window.a")
-  add_velox_dependency(velox::buffer "${VELOX_COMPONENTS_PATH}/buffer/libvelox_buffer.a")
-
-  add_velox_dependency(functions::isnull "${VELOX_COMPONENTS_PATH}/functions/lib/libvelox_is_null_functions.a")
-  add_velox_dependency(functions::prestosql "${VELOX_COMPONENTS_PATH}/functions/prestosql/registration/libvelox_functions_prestosql.a")
-  add_velox_dependency(functions::prestosql::impl "${VELOX_COMPONENTS_PATH}/functions/prestosql/libvelox_functions_prestosql_impl.a")
-  add_velox_dependency(functions::json "${VELOX_COMPONENTS_PATH}/functions/prestosql/json/libvelox_functions_json.a")
-  add_velox_dependency(functions::hyperloglog "${VELOX_COMPONENTS_PATH}/common/hyperloglog/libvelox_common_hyperloglog.a")
-  add_velox_dependency(functions::lib "${VELOX_COMPONENTS_PATH}/functions/lib/libvelox_functions_lib.a")
-  add_velox_dependency(functions::lib::date_time_formatter "${VELOX_COMPONENTS_PATH}/functions/lib/libvelox_functions_lib_date_time_formatter.a")
+  add_velox_dependency(
+    expression::sigparser
+    "${VELOX_COMPONENTS_PATH}/expression/signature_parser/libvelox_signature_parser.a"
+  )
+  add_velox_dependency(
+    functions::sparksql::lib
+    "${VELOX_COMPONENTS_PATH}/functions/sparksql/libvelox_functions_spark.a")
+  add_velox_dependency(
+    functions::sparksql::agg
+    "${VELOX_COMPONENTS_PATH}/functions/sparksql/aggregates/libvelox_functions_spark_aggregates.a"
+  )
+  add_velox_dependency(
+    functions::window::sparksql
+    "${VELOX_COMPONENTS_PATH}/functions/sparksql/window/libvelox_functions_spark_window.a"
+  )
+  add_velox_dependency(
+    functions::prestosql::agg
+    "${VELOX_COMPONENTS_PATH}/functions/prestosql/aggregates/libvelox_aggregates.a"
+  )
+  add_velox_dependency(
+    functions::lib::agg
+    "${VELOX_COMPONENTS_PATH}/functions/lib/aggregates/libvelox_functions_aggregates.a"
+  )
+  add_velox_dependency(
+    functions::prestosql::window
+    "${VELOX_COMPONENTS_PATH}/functions/prestosql/window/libvelox_window.a")
+  add_velox_dependency(
+    functions::lib::window
+    "${VELOX_COMPONENTS_PATH}/functions/lib/window/libvelox_functions_window.a")
+  add_velox_dependency(velox::buffer
+                       "${VELOX_COMPONENTS_PATH}/buffer/libvelox_buffer.a")
+
+  add_velox_dependency(
+    functions::isnull
+    "${VELOX_COMPONENTS_PATH}/functions/lib/libvelox_is_null_functions.a")
+  add_velox_dependency(
+    functions::prestosql
+    "${VELOX_COMPONENTS_PATH}/functions/prestosql/registration/libvelox_functions_prestosql.a"
+  )
+  add_velox_dependency(
+    functions::prestosql::impl
+    "${VELOX_COMPONENTS_PATH}/functions/prestosql/libvelox_functions_prestosql_impl.a"
+  )
+  add_velox_dependency(
+    functions::json
+    "${VELOX_COMPONENTS_PATH}/functions/prestosql/json/libvelox_functions_json.a"
+  )
+  add_velox_dependency(
+    functions::hyperloglog
+    "${VELOX_COMPONENTS_PATH}/common/hyperloglog/libvelox_common_hyperloglog.a")
+  add_velox_dependency(
+    functions::lib
+    "${VELOX_COMPONENTS_PATH}/functions/lib/libvelox_functions_lib.a")
+  add_velox_dependency(
+    functions::lib::date_time_formatter
+    "${VELOX_COMPONENTS_PATH}/functions/lib/libvelox_functions_lib_date_time_formatter.a"
+  )
   if(BUILD_TESTS)
-    add_velox_dependency(exec::test "${VELOX_COMPONENTS_PATH}/exec/tests/utils/libvelox_exec_test_lib.a")
-    add_velox_dependency(temp::path "${VELOX_COMPONENTS_PATH}/exec/tests/utils/libvelox_temp_path.a")
-    add_velox_dependency(dwio::common::test::utils "${VELOX_COMPONENTS_PATH}/dwio/common/tests/utils/libvelox_dwio_common_test_utils.a")
+    add_velox_dependency(
+      exec::test
+      "${VELOX_COMPONENTS_PATH}/exec/tests/utils/libvelox_exec_test_lib.a")
+    add_velox_dependency(
+      temp::path
+      "${VELOX_COMPONENTS_PATH}/exec/tests/utils/libvelox_temp_path.a")
+    add_velox_dependency(
+      dwio::common::test::utils
+      "${VELOX_COMPONENTS_PATH}/dwio/common/tests/utils/libvelox_dwio_common_test_utils.a"
+    )
   endif()
   add_velox_dependency(exec "${VELOX_COMPONENTS_PATH}/exec/libvelox_exec.a")
 
   if(BUILD_TESTS)
-    add_velox_dependency(parse::parser "${VELOX_COMPONENTS_PATH}/parse/libvelox_parse_parser.a")
-    add_velox_dependency(duckdb::parser "${VELOX_COMPONENTS_PATH}/duckdb/conversion/libvelox_duckdb_parser.a")
-    add_velox_dependency(parse::expression "${VELOX_COMPONENTS_PATH}/parse/libvelox_parse_expression.a")
-    add_velox_dependency(parse::utils "${VELOX_COMPONENTS_PATH}/parse/libvelox_parse_utils.a")
-    add_velox_dependency(function::registry "${VELOX_COMPONENTS_PATH}/functions/libvelox_function_registry.a")
+    add_velox_dependency(
+      parse::parser "${VELOX_COMPONENTS_PATH}/parse/libvelox_parse_parser.a")
+    add_velox_dependency(
+      duckdb::parser
+      "${VELOX_COMPONENTS_PATH}/duckdb/conversion/libvelox_duckdb_parser.a")
+    add_velox_dependency(
+      parse::expression
+      "${VELOX_COMPONENTS_PATH}/parse/libvelox_parse_expression.a")
+    add_velox_dependency(
+      parse::utils "${VELOX_COMPONENTS_PATH}/parse/libvelox_parse_utils.a")
+    add_velox_dependency(
+      function::registry
+      "${VELOX_COMPONENTS_PATH}/functions/libvelox_function_registry.a")
   endif()
-  add_velox_dependency(vector::arrow::bridge "${VELOX_COMPONENTS_PATH}/vector/arrow/libvelox_arrow_bridge.a")
+  add_velox_dependency(
+    vector::arrow::bridge
+    "${VELOX_COMPONENTS_PATH}/vector/arrow/libvelox_arrow_bridge.a")
   add_velox_dependency(row "${VELOX_COMPONENTS_PATH}/row/libvelox_row_fast.a")
-  add_velox_dependency(connector "${VELOX_COMPONENTS_PATH}/connectors/libvelox_connector.a")
-  add_velox_dependency(connector::hive_parition "${VELOX_COMPONENTS_PATH}/connectors/hive/libvelox_hive_partition_function.a")
-  add_velox_dependency(connector::hive::iceberg::IcebergSplitReader "${VELOX_COMPONENTS_PATH}/connectors/hive/iceberg/libvelox_hive_iceberg_splitreader.a")
+  add_velox_dependency(
+    connector "${VELOX_COMPONENTS_PATH}/connectors/libvelox_connector.a")
+  add_velox_dependency(
+    connector::hive_parition
+    "${VELOX_COMPONENTS_PATH}/connectors/hive/libvelox_hive_partition_function.a"
+  )
+  add_velox_dependency(
+    connector::hive::iceberg::IcebergSplitReader
+    "${VELOX_COMPONENTS_PATH}/connectors/hive/iceberg/libvelox_hive_iceberg_splitreader.a"
+  )
   if(ENABLE_HDFS)
-    add_velox_dependency(connector::hive::hdfs "${VELOX_COMPONENTS_PATH}/connectors/hive/storage_adapters/hdfs/libvelox_hdfs.a")
+    add_velox_dependency(
+      connector::hive::hdfs
+      "${VELOX_COMPONENTS_PATH}/connectors/hive/storage_adapters/hdfs/libvelox_hdfs.a"
+    )
   endif()
   if(ENABLE_GCS)
-    add_velox_dependency(connector::hive::gcs "${VELOX_COMPONENTS_PATH}/connectors/hive/storage_adapters/gcs/libvelox_gcs.a")
+    add_velox_dependency(
+      connector::hive::gcs
+      "${VELOX_COMPONENTS_PATH}/connectors/hive/storage_adapters/gcs/libvelox_gcs.a"
+    )
   endif()
   if(ENABLE_S3)
-    add_velox_dependency(connector::hive::s3fs "${VELOX_COMPONENTS_PATH}/connectors/hive/storage_adapters/s3fs/libvelox_s3fs.a")
+    add_velox_dependency(
+      connector::hive::s3fs
+      "${VELOX_COMPONENTS_PATH}/connectors/hive/storage_adapters/s3fs/libvelox_s3fs.a"
+    )
   endif()
   if(ENABLE_ABFS)
-  add_velox_dependency(connector::hive::abfs "${VELOX_COMPONENTS_PATH}/connectors/hive/storage_adapters/abfs/libvelox_abfs.a")
+    add_velox_dependency(
+      connector::hive::abfs
+      "${VELOX_COMPONENTS_PATH}/connectors/hive/storage_adapters/abfs/libvelox_abfs.a"
+    )
   endif()
-  add_velox_dependency(dwio::dwrf::writer "${VELOX_COMPONENTS_PATH}/dwio/dwrf/writer/libvelox_dwio_dwrf_writer.a")
-  add_velox_dependency(dwio::dwrf::reader "${VELOX_COMPONENTS_PATH}/dwio/dwrf/reader/libvelox_dwio_dwrf_reader.a")
-  add_velox_dependency(dwio::dwrf::utils "${VELOX_COMPONENTS_PATH}/dwio/dwrf/utils/libvelox_dwio_dwrf_utils.a")
-  add_velox_dependency(dwio::dwrf::common "${VELOX_COMPONENTS_PATH}/dwio/dwrf/common/libvelox_dwio_dwrf_common.a")
-  add_velox_dependency(parquet "${VELOX_COMPONENTS_PATH}/dwio/parquet/libvelox_dwio_parquet_reader.a")
-  add_velox_dependency(parquet::reader::native "${VELOX_COMPONENTS_PATH}/dwio/parquet/reader/libvelox_dwio_native_parquet_reader.a")
+  add_velox_dependency(
+    dwio::dwrf::writer
+    "${VELOX_COMPONENTS_PATH}/dwio/dwrf/writer/libvelox_dwio_dwrf_writer.a")
+  add_velox_dependency(
+    dwio::dwrf::reader
+    "${VELOX_COMPONENTS_PATH}/dwio/dwrf/reader/libvelox_dwio_dwrf_reader.a")
+  add_velox_dependency(
+    dwio::dwrf::utils
+    "${VELOX_COMPONENTS_PATH}/dwio/dwrf/utils/libvelox_dwio_dwrf_utils.a")
+  add_velox_dependency(
+    dwio::dwrf::common
+    "${VELOX_COMPONENTS_PATH}/dwio/dwrf/common/libvelox_dwio_dwrf_common.a")
+  add_velox_dependency(
+    parquet
+    "${VELOX_COMPONENTS_PATH}/dwio/parquet/libvelox_dwio_parquet_reader.a")
+  add_velox_dependency(
+    parquet::reader::native
+    "${VELOX_COMPONENTS_PATH}/dwio/parquet/reader/libvelox_dwio_native_parquet_reader.a"
+  )
   if(BUILD_TESTS)
-    add_velox_dependency(dwio::common::utils "${VELOX_COMPONENTS_PATH}/dwio/common/tests/utils/libvelox_dwio_common_test_utils.a")
-    add_velox_dependency(dwio::dwrf::test_utils "${VELOX_COMPONENTS_PATH}/dwio/dwrf/test/utils/libvelox_dwrf_test_utils.a")
-    add_velox_dependency(parquet::reader::duckdb_conversion "${VELOX_COMPONENTS_PATH}/duckdb/conversion/libvelox_duckdb_conversion.a")
+    add_velox_dependency(
+      dwio::common::utils
+      "${VELOX_COMPONENTS_PATH}/dwio/common/tests/utils/libvelox_dwio_common_test_utils.a"
+    )
+    add_velox_dependency(
+      dwio::dwrf::test_utils
+      "${VELOX_COMPONENTS_PATH}/dwio/dwrf/test/utils/libvelox_dwrf_test_utils.a"
+    )
+    add_velox_dependency(
+      parquet::reader::duckdb_conversion
+      "${VELOX_COMPONENTS_PATH}/duckdb/conversion/libvelox_duckdb_conversion.a")
 
     add_duckdb()
 
-    add_velox_dependency(tpch::gen "${VELOX_COMPONENTS_PATH}/tpch/gen/libvelox_tpch_gen.a")
-    add_velox_dependency(dbgen "${VELOX_COMPONENTS_PATH}/tpch/gen/dbgen/libvelox_dbgen.a")
+    add_velox_dependency(
+      tpch::gen "${VELOX_COMPONENTS_PATH}/tpch/gen/libvelox_tpch_gen.a")
+    add_velox_dependency(
+      dbgen "${VELOX_COMPONENTS_PATH}/tpch/gen/dbgen/libvelox_dbgen.a")
   endif()
 
-  add_velox_dependency(parquet::reader::thrift "${VELOX_COMPONENTS_PATH}/dwio/parquet/thrift/libvelox_dwio_parquet_thrift.a")
-
-  add_velox_dependency(velox::arrow::parquet::writer "${VELOX_COMPONENTS_PATH}/dwio/parquet/writer/libvelox_dwio_arrow_parquet_writer.a")
-  add_velox_dependency(dwio::arrow::parquet::writer "${VELOX_COMPONENTS_PATH}/dwio/parquet/writer/arrow/libvelox_dwio_arrow_parquet_writer_lib.a")
-  add_velox_dependency(dwio::arrow::parquet::writer::util "${VELOX_COMPONENTS_PATH}/dwio/parquet/writer/arrow/util/libvelox_dwio_arrow_parquet_writer_util_lib.a")
-  add_velox_dependency(dwio::arrow::parquet::writer::thrift::lib "${VELOX_COMPONENTS_PATH}/dwio/parquet/writer/arrow/generated/libvelox_dwio_arrow_parquet_writer_thrift_lib.a")
-  add_velox_dependency(dwio::common::compression "${VELOX_COMPONENTS_PATH}/dwio/common/compression/libvelox_dwio_common_compression.a")
-  add_velox_dependency(dwio::common "${VELOX_COMPONENTS_PATH}/dwio/common/libvelox_dwio_common.a")
-  add_velox_dependency(functions::prestosql::types "${VELOX_COMPONENTS_PATH}/functions/prestosql/types/libvelox_presto_types.a")
-  add_velox_dependency(functions::spark::specialforms "${VELOX_COMPONENTS_PATH}/functions/sparksql/specialforms/libvelox_functions_spark_specialforms.a")
-  add_velox_dependency(expression "${VELOX_COMPONENTS_PATH}/expression/libvelox_expression.a")
+  add_velox_dependency(
+    parquet::reader::thrift
+    "${VELOX_COMPONENTS_PATH}/dwio/parquet/thrift/libvelox_dwio_parquet_thrift.a"
+  )
+
+  add_velox_dependency(
+    velox::arrow::parquet::writer
+    "${VELOX_COMPONENTS_PATH}/dwio/parquet/writer/libvelox_dwio_arrow_parquet_writer.a"
+  )
+  add_velox_dependency(
+    dwio::arrow::parquet::writer
+    "${VELOX_COMPONENTS_PATH}/dwio/parquet/writer/arrow/libvelox_dwio_arrow_parquet_writer_lib.a"
+  )
+  add_velox_dependency(
+    dwio::arrow::parquet::writer::util
+    "${VELOX_COMPONENTS_PATH}/dwio/parquet/writer/arrow/util/libvelox_dwio_arrow_parquet_writer_util_lib.a"
+  )
+  add_velox_dependency(
+    dwio::arrow::parquet::writer::thrift::lib
+    "${VELOX_COMPONENTS_PATH}/dwio/parquet/writer/arrow/generated/libvelox_dwio_arrow_parquet_writer_thrift_lib.a"
+  )
+  add_velox_dependency(
+    dwio::common::compression
+    "${VELOX_COMPONENTS_PATH}/dwio/common/compression/libvelox_dwio_common_compression.a"
+  )
+  add_velox_dependency(
+    dwio::common "${VELOX_COMPONENTS_PATH}/dwio/common/libvelox_dwio_common.a")
+  add_velox_dependency(
+    functions::prestosql::types
+    "${VELOX_COMPONENTS_PATH}/functions/prestosql/types/libvelox_presto_types.a"
+  )
+  add_velox_dependency(
+    functions::spark::specialforms
+    "${VELOX_COMPONENTS_PATH}/functions/sparksql/specialforms/libvelox_functions_spark_specialforms.a"
+  )
+  add_velox_dependency(
+    expression "${VELOX_COMPONENTS_PATH}/expression/libvelox_expression.a")
   add_velox_dependency(core "${VELOX_COMPONENTS_PATH}/core/libvelox_core.a")
 
-  add_velox_dependency(type::fbhive "${VELOX_COMPONENTS_PATH}/type/fbhive/libvelox_type_fbhive.a")
+  add_velox_dependency(
+    type::fbhive "${VELOX_COMPONENTS_PATH}/type/fbhive/libvelox_type_fbhive.a")
   add_velox_dependency(type "${VELOX_COMPONENTS_PATH}/type/libvelox_type.a")
-  add_velox_dependency(vector::serializes "${VELOX_COMPONENTS_PATH}/serializers/libvelox_presto_serializer.a")
-  add_velox_dependency(functions::lib::util "${VELOX_COMPONENTS_PATH}/functions/lib/libvelox_functions_util.a")
-  add_velox_dependency(vector "${VELOX_COMPONENTS_PATH}/vector/libvelox_vector.a")
-  add_velox_dependency(expression::function "${VELOX_COMPONENTS_PATH}/expression/libvelox_expression_functions.a")
-  add_velox_dependency(expression::type_calculation "${VELOX_COMPONENTS_PATH}/expression/type_calculation/libvelox_type_calculation.a")
-
-  add_velox_dependency(common::caching "${VELOX_COMPONENTS_PATH}/common/caching/libvelox_caching.a")
-  add_velox_dependency(common::base "${VELOX_COMPONENTS_PATH}/common/base/libvelox_common_base.a")
-  add_velox_dependency(common::memory "${VELOX_COMPONENTS_PATH}/common/memory/libvelox_memory.a")
-  add_velox_dependency(common::serialization "${VELOX_COMPONENTS_PATH}/common/serialization/libvelox_serialization.a")
-  add_velox_dependency(common::base::exception "${VELOX_COMPONENTS_PATH}/common/base/libvelox_exception.a")
-
-  add_velox_dependency(type::tz "${VELOX_COMPONENTS_PATH}/type/tz/libvelox_type_tz.a")
-  add_velox_dependency(dwio::dwrf::proto "${VELOX_COMPONENTS_PATH}/dwio/dwrf/proto/libvelox_dwio_dwrf_proto.a")
-  add_velox_dependency(dwio::catalog::fbhive "${VELOX_COMPONENTS_PATH}/dwio/catalog/fbhive/libvelox_dwio_catalog_fbhive.a")
-  add_velox_dependency(dwio::common::exception "${VELOX_COMPONENTS_PATH}/dwio/common/exception/libvelox_dwio_common_exception.a")
-  add_velox_dependency(dwio::common::encryption "${VELOX_COMPONENTS_PATH}/dwio/common/encryption/libvelox_dwio_common_encryption.a")
-
-  add_velox_dependency(core::config "${VELOX_COMPONENTS_PATH}/core/libvelox_config.a")
-  add_velox_dependency(common::encode "${VELOX_COMPONENTS_PATH}/common/encode/libvelox_encode.a")
-  add_velox_dependency(common::time "${VELOX_COMPONENTS_PATH}/common/time/libvelox_time.a")
+  add_velox_dependency(
+    vector::serializes
+    "${VELOX_COMPONENTS_PATH}/serializers/libvelox_presto_serializer.a")
+  add_velox_dependency(
+    functions::lib::util
+    "${VELOX_COMPONENTS_PATH}/functions/lib/libvelox_functions_util.a")
+  add_velox_dependency(vector
+                       "${VELOX_COMPONENTS_PATH}/vector/libvelox_vector.a")
+  add_velox_dependency(
+    expression::function
+    "${VELOX_COMPONENTS_PATH}/expression/libvelox_expression_functions.a")
+  add_velox_dependency(
+    expression::type_calculation
+    "${VELOX_COMPONENTS_PATH}/expression/type_calculation/libvelox_type_calculation.a"
+  )
+
+  add_velox_dependency(
+    common::caching
+    "${VELOX_COMPONENTS_PATH}/common/caching/libvelox_caching.a")
+  add_velox_dependency(
+    common::base "${VELOX_COMPONENTS_PATH}/common/base/libvelox_common_base.a")
+  add_velox_dependency(
+    common::memory "${VELOX_COMPONENTS_PATH}/common/memory/libvelox_memory.a")
+  add_velox_dependency(
+    common::serialization
+    "${VELOX_COMPONENTS_PATH}/common/serialization/libvelox_serialization.a")
+  add_velox_dependency(
+    common::base::exception
+    "${VELOX_COMPONENTS_PATH}/common/base/libvelox_exception.a")
+
+  add_velox_dependency(type::tz
+                       "${VELOX_COMPONENTS_PATH}/type/tz/libvelox_type_tz.a")
+  add_velox_dependency(
+    dwio::dwrf::proto
+    "${VELOX_COMPONENTS_PATH}/dwio/dwrf/proto/libvelox_dwio_dwrf_proto.a")
+  add_velox_dependency(
+    dwio::catalog::fbhive
+    "${VELOX_COMPONENTS_PATH}/dwio/catalog/fbhive/libvelox_dwio_catalog_fbhive.a"
+  )
+  add_velox_dependency(
+    dwio::common::exception
+    "${VELOX_COMPONENTS_PATH}/dwio/common/exception/libvelox_dwio_common_exception.a"
+  )
+  add_velox_dependency(
+    dwio::common::encryption
+    "${VELOX_COMPONENTS_PATH}/dwio/common/encryption/libvelox_dwio_common_encryption.a"
+  )
+
+  add_velox_dependency(core::config
+                       "${VELOX_COMPONENTS_PATH}/core/libvelox_config.a")
+  add_velox_dependency(
+    common::encode "${VELOX_COMPONENTS_PATH}/common/encode/libvelox_encode.a")
+  add_velox_dependency(common::time
+                       "${VELOX_COMPONENTS_PATH}/common/time/libvelox_time.a")
   if(BUILD_TESTS)
-    add_velox_dependency(common::file::test "${VELOX_COMPONENTS_PATH}/common/file/tests/libvelox_file_test_utils.a")
+    add_velox_dependency(
+      common::file::test
+      "${VELOX_COMPONENTS_PATH}/common/file/tests/libvelox_file_test_utils.a")
   endif()
-  add_velox_dependency(common::file "${VELOX_COMPONENTS_PATH}/common/file/libvelox_file.a")
-  add_velox_dependency(common::process "${VELOX_COMPONENTS_PATH}/common/process/libvelox_process.a")
-
-  add_velox_dependency(common::test_util "${VELOX_COMPONENTS_PATH}/common/testutil/libvelox_test_util.a")
-
-  add_velox_dependency(external::md5 "${VELOX_COMPONENTS_PATH}/external/md5/libmd5.a")
-  add_velox_dependency(external::date "${VELOX_COMPONENTS_PATH}/external/date/libvelox_external_date.a")
-  add_velox_dependency(velox::parquet::writer "${VELOX_COMPONENTS_PATH}/dwio/parquet/libvelox_dwio_parquet_writer.a")
+  add_velox_dependency(common::file
+                       "${VELOX_COMPONENTS_PATH}/common/file/libvelox_file.a")
+  add_velox_dependency(
+    common::process
+    "${VELOX_COMPONENTS_PATH}/common/process/libvelox_process.a")
+
+  add_velox_dependency(
+    common::test_util
+    "${VELOX_COMPONENTS_PATH}/common/testutil/libvelox_test_util.a")
+
+  add_velox_dependency(external::md5
+                       "${VELOX_COMPONENTS_PATH}/external/md5/libmd5.a")
+  add_velox_dependency(
+    external::date
+    "${VELOX_COMPONENTS_PATH}/external/date/libvelox_external_date.a")
+  add_velox_dependency(
+    velox::parquet::writer
+    "${VELOX_COMPONENTS_PATH}/dwio/parquet/libvelox_dwio_parquet_writer.a")
 
   if(BUILD_TESTS)
-    add_velox_dependency(vector::test::util "${VELOX_COMPONENTS_PATH}/vector/tests/utils/libvelox_vector_test_lib.a")
+    add_velox_dependency(
+      vector::test::util
+      "${VELOX_COMPONENTS_PATH}/vector/tests/utils/libvelox_vector_test_lib.a")
   endif()
-  add_velox_dependency(common::compression "${VELOX_COMPONENTS_PATH}/common/compression/libvelox_common_compression.a")
-  add_velox_dependency(common::io "${VELOX_COMPONENTS_PATH}/common/io/libvelox_common_io.a")
-  add_velox_dependency(velox::status "${VELOX_COMPONENTS_PATH}/common/base/libvelox_status.a")
+  add_velox_dependency(
+    common::compression
+    "${VELOX_COMPONENTS_PATH}/common/compression/libvelox_common_compression.a")
+  add_velox_dependency(
+    common::io "${VELOX_COMPONENTS_PATH}/common/io/libvelox_common_io.a")
+  add_velox_dependency(velox::status
+                       "${VELOX_COMPONENTS_PATH}/common/base/libvelox_status.a")
 endmacro()
 
 macro(find_libhdfs3)
@@ -241,18 +440,16 @@ macro(find_libhdfs3)
     find_path(libhdfs3_INCLUDE_DIR hdfs/hdfs.h)
     set(CMAKE_FIND_LIBRARY_SUFFIXES ".so")
     find_library(libhdfs3_LIBRARY NAMES hdfs3)
-    find_package_handle_standard_args(libhdfs3 DEFAULT_MSG
-      libhdfs3_INCLUDE_DIR
-      libhdfs3_LIBRARY
-    )
+    find_package_handle_standard_args(libhdfs3 DEFAULT_MSG libhdfs3_INCLUDE_DIR
+                                      libhdfs3_LIBRARY)
     add_library(HDFS::hdfs3 SHARED IMPORTED)
-      set_target_properties(HDFS::hdfs3 PROPERTIES
-      INTERFACE_INCLUDE_DIRECTORIES "${libhdfs3_INCLUDE_DIR}"
-      IMPORTED_LOCATION "${libhdfs3_LIBRARY}"
-    )
+    set_target_properties(
+      HDFS::hdfs3
+      PROPERTIES INTERFACE_INCLUDE_DIRECTORIES "${libhdfs3_INCLUDE_DIR}"
+                 IMPORTED_LOCATION "${libhdfs3_LIBRARY}")
   endif()
 
-  if (NOT libhdfs3_FOUND)
+  if(NOT libhdfs3_FOUND)
     message(FATAL_ERROR "LIBHDFS3 Library Not Found")
   endif()
 endmacro()
@@ -262,30 +459,35 @@ macro(find_re2)
   if(re2_FOUND AND TARGET re2::re2)
     set(RE2_LIBRARY re2::re2)
   else()
-    find_library(RE2_LIBRARY NAMES re2 PATHS ${SYSTEM_LIB_PATH} ${SYSTEM_LIB64_PATH} ${SYSTEM_LIB_MULTIARCH_PATH} ${SYSTEM_LOCAL_LIB_PATH} ${SYSTEM_LOCAL_LIB64_PATH} NO_DEFAULT_PATH)
+    find_library(
+      RE2_LIBRARY
+      NAMES re2
+      PATHS ${SYSTEM_LIB_PATH} ${SYSTEM_LIB64_PATH} ${SYSTEM_LIB_MULTIARCH_PATH}
+            ${SYSTEM_LOCAL_LIB_PATH} ${SYSTEM_LOCAL_LIB64_PATH}
+      NO_DEFAULT_PATH)
   endif()
 
-  if (NOT RE2_LIBRARY)
-     message(FATAL_ERROR "RE2 Library Not Found")
+  if(NOT RE2_LIBRARY)
+    message(FATAL_ERROR "RE2 Library Not Found")
   else()
     message(STATUS "RE2 Library Can Be Found in ${RE2_LIBRARY}")
   endif()
 endmacro()
 
 macro(find_awssdk)
-  set (CMAKE_FIND_LIBRARY_SUFFIXES ".a")
+  set(CMAKE_FIND_LIBRARY_SUFFIXES ".a")
   find_package(AWSSDK REQUIRED COMPONENTS s3;identity-management)
 endmacro()
 
 macro(find_gcssdk)
-  set (CMAKE_FIND_LIBRARY_SUFFIXES ".so")
+  set(CMAKE_FIND_LIBRARY_SUFFIXES ".so")
   find_package(google_cloud_cpp_storage REQUIRED)
 endmacro()
 
 macro(find_azure)
   find_package(CURL REQUIRED)
   find_package(LibXml2 REQUIRED)
-  set (CMAKE_FIND_LIBRARY_SUFFIXES ".a")
+  set(CMAKE_FIND_LIBRARY_SUFFIXES ".a")
   find_package(azure-storage-blobs-cpp CONFIG REQUIRED)
   find_package(azure-storage-files-datalake-cpp CONFIG REQUIRED)
 endmacro()
@@ -327,12 +529,11 @@ set(VELOX_SRCS
     utils/VeloxArrowUtils.cc
     utils/ConfigExtractor.cc
     utils/Common.cc
-    utils/VeloxBatchAppender.cc
-    )
+    utils/VeloxBatchAppender.cc)
 
-if (ENABLE_HDFS)
+if(ENABLE_HDFS)
   list(APPEND VELOX_SRCS utils/HdfsUtils.cc)
-endif ()
+endif()
 
 if(ENABLE_S3)
   find_package(ZLIB)
@@ -346,30 +547,30 @@ add_library(velox SHARED ${VELOX_SRCS})
 
 if(ENABLE_GLUTEN_VCPKG)
   # Hide symbols of static dependencies
-  target_link_options(velox PRIVATE -Wl,--version-script=${CMAKE_CURRENT_SOURCE_DIR}/symbols.map)
+  target_link_options(
+    velox PRIVATE -Wl,--version-script=${CMAKE_CURRENT_SOURCE_DIR}/symbols.map)
 endif()
 
-target_include_directories(velox PUBLIC
-    ${CMAKE_SYSTEM_INCLUDE_PATH}
-    ${JNI_INCLUDE_DIRS}
-    ${CMAKE_CURRENT_SOURCE_DIR}
-    ${VELOX_HOME}/
-    ${VELOX_BUILD_PATH}/
-    ${VELOX_BUILD_PATH}/_deps/xsimd-src/include/
-    ${VELOX_HOME}/third_party/xsimd/include/)
-
-set_target_properties(velox PROPERTIES
-    LIBRARY_OUTPUT_DIRECTORY ${root_directory}/releases
-    )
-
-## If folly is not installed in system lib paths, please add
-## `-DCMAKE_PREFIX_PATH="${folly lib path}" to cmake arguments.
-## It is also applicable to other dependencies.
+target_include_directories(
+  velox
+  PUBLIC ${CMAKE_SYSTEM_INCLUDE_PATH}
+         ${JNI_INCLUDE_DIRS}
+         ${CMAKE_CURRENT_SOURCE_DIR}
+         ${VELOX_HOME}/
+         ${VELOX_BUILD_PATH}/
+         ${VELOX_BUILD_PATH}/_deps/xsimd-src/include/
+         ${VELOX_HOME}/third_party/xsimd/include/)
+
+set_target_properties(velox PROPERTIES LIBRARY_OUTPUT_DIRECTORY
+                                       ${root_directory}/releases)
+
+# If folly is not installed in system lib paths, please add
+# `-DCMAKE_PREFIX_PATH="${folly lib path}" to cmake arguments. It is also
+# applicable to other dependencies.
 find_package(Folly REQUIRED CONFIG)
 
-target_include_directories(velox PUBLIC
-        ${GTEST_INCLUDE_DIRS}
-        ${PROTOBUF_INCLUDE})
+target_include_directories(velox PUBLIC ${GTEST_INCLUDE_DIRS}
+                                        ${PROTOBUF_INCLUDE})
 
 target_link_libraries(velox PUBLIC gluten)
 add_velox_dependencies()
@@ -383,11 +584,13 @@ target_link_libraries(velox PUBLIC Folly::folly)
 find_re2()
 target_link_libraries(velox PUBLIC ${RE2_LIBRARY})
 
-# since https://github.com/facebookincubator/velox/commit/47970417ac92135e862c0fde350d4d60fa2f1423
+# since
+# https://github.com/facebookincubator/velox/commit/47970417ac92135e862c0fde350d4d60fa2f1423
 if(Stemmer_FOUND)
   target_link_libraries(velox PUBLIC stemmer::stemmer)
 else()
-  add_velox_dependency(velox "${VELOX_BUILD_PATH}/_deps/libstemmer/src/libstemmer/libstemmer.a")
+  add_velox_dependency(
+    velox "${VELOX_BUILD_PATH}/_deps/libstemmer/src/libstemmer/libstemmer.a")
 endif()
 
 set(CMAKE_FIND_LIBRARY_SUFFIXES_BCK ${CMAKE_FIND_LIBRARY_SUFFIXES})
@@ -396,7 +599,8 @@ find_package(simdjson CONFIG)
 if(simdjson_FOUND AND TARGET simdjson::simdjson)
   target_link_libraries(velox PUBLIC simdjson::simdjson)
 else()
-  add_velox_dependency(external::simdjson "${VELOX_BUILD_PATH}/_deps/simdjson-build/libsimdjson.a")
+  add_velox_dependency(external::simdjson
+                       "${VELOX_BUILD_PATH}/_deps/simdjson-build/libsimdjson.a")
 endif()
 set(CMAKE_FIND_LIBRARY_SUFFIXES ${CMAKE_FIND_LIBRARY_SUFFIXES_BCK})
 
@@ -411,7 +615,8 @@ endif()
 if(Thrift_FOUND)
   target_link_libraries(velox PUBLIC thrift::thrift)
 else()
-  add_velox_dependency(thrift "${ARROW_HOME}/src/arrow_ep-build/thrift_ep-install/lib/libthrift.a")
+  add_velox_dependency(
+    thrift "${ARROW_HOME}/src/arrow_ep-build/thrift_ep-install/lib/libthrift.a")
 endif()
 
 if(BUILD_TESTS)
@@ -451,7 +656,13 @@ if(ENABLE_ABFS)
   target_link_libraries(velox PUBLIC Azure::azure-storage-files-datalake)
 endif()
 
-add_custom_command(TARGET velox POST_BUILD COMMAND ld $<TARGET_FILE:velox> || true
-        COMMENT "Checking ld result of libvelox.so")
-add_custom_command(TARGET velox POST_BUILD COMMAND ldd $<TARGET_FILE:velox> || true
-        COMMENT "Checking ldd result of libvelox.so")
+add_custom_command(
+  TARGET velox
+  POST_BUILD
+  COMMAND ld $<TARGET_FILE:velox> || true
+  COMMENT "Checking ld result of libvelox.so")
+add_custom_command(
+  TARGET velox
+  POST_BUILD
+  COMMAND ldd $<TARGET_FILE:velox> || true
+  COMMENT "Checking ldd result of libvelox.so")
diff --git a/cpp/velox/benchmarks/CMakeLists.txt b/cpp/velox/benchmarks/CMakeLists.txt
index 74f21c29bc1d..903ec0d65825 100644
--- a/cpp/velox/benchmarks/CMakeLists.txt
+++ b/cpp/velox/benchmarks/CMakeLists.txt
@@ -15,10 +15,15 @@
 
 find_arrow_lib(${PARQUET_LIB_NAME})
 
-set(VELOX_BENCHMARK_COMMON_SRCS common/FileReaderIterator.cc common/BenchmarkUtils.cc)
+set(VELOX_BENCHMARK_COMMON_SRCS common/FileReaderIterator.cc
+                                common/BenchmarkUtils.cc)
 add_library(velox_benchmark_common STATIC ${VELOX_BENCHMARK_COMMON_SRCS})
-target_include_directories(velox_benchmark_common PUBLIC ${CMAKE_SOURCE_DIR}/velox ${CMAKE_SOURCE_DIR}/core)
-target_link_libraries(velox_benchmark_common PUBLIC Arrow::parquet velox benchmark::benchmark google::glog)
+target_include_directories(
+  velox_benchmark_common PUBLIC ${CMAKE_SOURCE_DIR}/velox
+                                ${CMAKE_SOURCE_DIR}/core)
+target_link_libraries(
+  velox_benchmark_common PUBLIC Arrow::parquet velox benchmark::benchmark
+                                google::glog)
 
 function(add_velox_benchmark BM_EXEC BM_FILE)
   add_executable(${BM_EXEC} ${BM_FILE})
diff --git a/cpp/velox/substrait/SubstraitToVeloxPlan.cc b/cpp/velox/substrait/SubstraitToVeloxPlan.cc
index 4e875d4790e5..8b8a9262403c 100644
--- a/cpp/velox/substrait/SubstraitToVeloxPlan.cc
+++ b/cpp/velox/substrait/SubstraitToVeloxPlan.cc
@@ -20,6 +20,7 @@
 #include "VariantToVectorConverter.h"
 #include "velox/connectors/hive/HiveDataSink.h"
 #include "velox/exec/TableWriter.h"
+#include "velox/type/Filter.h"
 #include "velox/type/Type.h"
 
 #include "utils/ConfigExtractor.h"
@@ -1465,10 +1466,12 @@ connector::hive::SubfieldFilters SubstraitToVeloxPlanConverter::createSubfieldFi
       auto expr = scalarFunction.arguments()[0].value();
       if (expr.has_scalar_function()) {
         // Set its child to filter info with reverse enabled.
-        setFilterInfo(scalarFunction.arguments()[0].value().scalar_function(), inputTypeList, columnToFilterInfo, true);
+        setFilterInfo(expr.scalar_function(), inputTypeList, columnToFilterInfo, true);
+      } else if (expr.has_singular_or_list()) {
+        auto singularOrList = expr.singular_or_list();
+        setFilterInfo(singularOrList, columnToFilterInfo, true);
       } else {
-        // TODO: support push down of Not In.
-        VELOX_NYI("Scalar function expected.");
+        VELOX_NYI("Only support push down Not with scalar function or In.");
       }
     } else if (filterName == sOr) {
       VELOX_CHECK(scalarFunction.arguments().size() == 2);
@@ -1593,24 +1596,26 @@ bool SubstraitToVeloxPlanConverter::canPushdownNot(
     std::vector<RangeRecorder>& rangeRecorders) {
   VELOX_CHECK(scalarFunction.arguments().size() == 1, "Only one arg is expected for Not.");
   const auto& notArg = scalarFunction.arguments()[0];
-  if (!notArg.value().has_scalar_function()) {
-    // Not for a Boolean Literal or Or List is not supported curretly.
-    // It can be pushed down with an AlwaysTrue or AlwaysFalse Range.
-    return false;
-  }
-
-  auto argFunction =
-      SubstraitParser::findFunctionSpec(functionMap_, notArg.value().scalar_function().function_reference());
-  auto functionName = SubstraitParser::getNameBeforeDelimiter(argFunction);
+  if (notArg.value().has_singular_or_list()) {
+    auto singularOrList = notArg.value().singular_or_list();
+    if (!canPushdownSingularOrList(singularOrList)) {
+      return false;
+    }
+    uint32_t colIdx = getColumnIndexFromSingularOrList(singularOrList);
+    return rangeRecorders.at(colIdx).setInRange();
+  } else if (notArg.value().has_scalar_function()) {
+    auto argFunction =
+        SubstraitParser::findFunctionSpec(functionMap_, notArg.value().scalar_function().function_reference());
+    auto functionName = SubstraitParser::getNameBeforeDelimiter(argFunction);
 
-  static const std::unordered_set<std::string> supportedNotFunctions = {sGte, sGt, sLte, sLt, sEqual};
+    static const std::unordered_set<std::string> supportedNotFunctions = {sGte, sGt, sLte, sLt, sEqual};
 
-  uint32_t fieldIdx;
-  bool isFieldOrWithLiteral = fieldOrWithLiteral(notArg.value().scalar_function().arguments(), fieldIdx);
+    uint32_t fieldIdx;
+    bool isFieldOrWithLiteral = fieldOrWithLiteral(notArg.value().scalar_function().arguments(), fieldIdx);
 
-  if (supportedNotFunctions.find(functionName) != supportedNotFunctions.end() && isFieldOrWithLiteral &&
-      rangeRecorders.at(fieldIdx).setCertainRangeForFunction(functionName, true /*reverse*/)) {
-    return true;
+    return (
+        supportedNotFunctions.find(functionName) != supportedNotFunctions.end() && isFieldOrWithLiteral &&
+        rangeRecorders.at(fieldIdx).setCertainRangeForFunction(functionName, true /*reverse*/));
   }
   return false;
 }
@@ -1966,6 +1971,7 @@ template <TypeKind KIND>
 void SubstraitToVeloxPlanConverter::setInFilter(
     const std::vector<variant>& variants,
     bool nullAllowed,
+    bool negated,
     const std::string& inputName,
     connector::hive::SubfieldFilters& filters) {}
 
@@ -1973,6 +1979,7 @@ template <>
 void SubstraitToVeloxPlanConverter::setInFilter<TypeKind::BIGINT>(
     const std::vector<variant>& variants,
     bool nullAllowed,
+    bool negated,
     const std::string& inputName,
     connector::hive::SubfieldFilters& filters) {
   std::vector<int64_t> values;
@@ -1981,13 +1988,18 @@ void SubstraitToVeloxPlanConverter::setInFilter<TypeKind::BIGINT>(
     int64_t value = variant.value<int64_t>();
     values.emplace_back(value);
   }
-  filters[common::Subfield(inputName)] = common::createBigintValues(values, nullAllowed);
+  if (negated) {
+    filters[common::Subfield(inputName)] = common::createNegatedBigintValues(values, nullAllowed);
+  } else {
+    filters[common::Subfield(inputName)] = common::createBigintValues(values, nullAllowed);
+  }
 }
 
 template <>
 void SubstraitToVeloxPlanConverter::setInFilter<TypeKind::INTEGER>(
     const std::vector<variant>& variants,
     bool nullAllowed,
+    bool negated,
     const std::string& inputName,
     connector::hive::SubfieldFilters& filters) {
   // Use bigint values for int type.
@@ -1998,13 +2010,18 @@ void SubstraitToVeloxPlanConverter::setInFilter<TypeKind::INTEGER>(
     int64_t value = variant.value<int32_t>();
     values.emplace_back(value);
   }
-  filters[common::Subfield(inputName)] = common::createBigintValues(values, nullAllowed);
+  if (negated) {
+    filters[common::Subfield(inputName)] = common::createNegatedBigintValues(values, nullAllowed);
+  } else {
+    filters[common::Subfield(inputName)] = common::createBigintValues(values, nullAllowed);
+  }
 }
 
 template <>
 void SubstraitToVeloxPlanConverter::setInFilter<TypeKind::SMALLINT>(
     const std::vector<variant>& variants,
     bool nullAllowed,
+    bool negated,
     const std::string& inputName,
     connector::hive::SubfieldFilters& filters) {
   // Use bigint values for small int type.
@@ -2015,13 +2032,18 @@ void SubstraitToVeloxPlanConverter::setInFilter<TypeKind::SMALLINT>(
     int64_t value = variant.value<int16_t>();
     values.emplace_back(value);
   }
-  filters[common::Subfield(inputName)] = common::createBigintValues(values, nullAllowed);
+  if (negated) {
+    filters[common::Subfield(inputName)] = common::createNegatedBigintValues(values, nullAllowed);
+  } else {
+    filters[common::Subfield(inputName)] = common::createBigintValues(values, nullAllowed);
+  }
 }
 
 template <>
 void SubstraitToVeloxPlanConverter::setInFilter<TypeKind::TINYINT>(
     const std::vector<variant>& variants,
     bool nullAllowed,
+    bool negated,
     const std::string& inputName,
     connector::hive::SubfieldFilters& filters) {
   // Use bigint values for tiny int type.
@@ -2032,13 +2054,18 @@ void SubstraitToVeloxPlanConverter::setInFilter<TypeKind::TINYINT>(
     int64_t value = variant.value<int8_t>();
     values.emplace_back(value);
   }
-  filters[common::Subfield(inputName)] = common::createBigintValues(values, nullAllowed);
+  if (negated) {
+    filters[common::Subfield(inputName)] = common::createNegatedBigintValues(values, nullAllowed);
+  } else {
+    filters[common::Subfield(inputName)] = common::createBigintValues(values, nullAllowed);
+  }
 }
 
 template <>
 void SubstraitToVeloxPlanConverter::setInFilter<TypeKind::VARCHAR>(
     const std::vector<variant>& variants,
     bool nullAllowed,
+    bool negated,
     const std::string& inputName,
     connector::hive::SubfieldFilters& filters) {
   std::vector<std::string> values;
@@ -2047,7 +2074,11 @@ void SubstraitToVeloxPlanConverter::setInFilter<TypeKind::VARCHAR>(
     std::string value = variant.value<std::string>();
     values.emplace_back(value);
   }
-  filters[common::Subfield(inputName)] = std::make_unique<common::BytesValues>(values, nullAllowed);
+  if (negated) {
+    filters[common::Subfield(inputName)] = std::make_unique<common::NegatedBytesValues>(values, nullAllowed);
+  } else {
+    filters[common::Subfield(inputName)] = std::make_unique<common::BytesValues>(values, nullAllowed);
+  }
 }
 
 template <TypeKind KIND, typename FilterType>
@@ -2102,6 +2133,17 @@ void SubstraitToVeloxPlanConverter::constructSubfieldFilters(
     if (filterInfo.notValue_) {
       filters[common::Subfield(inputName)] =
           std::make_unique<common::BoolValue>(!filterInfo.notValue_.value().value<bool>(), nullAllowed);
+    } else if (filterInfo.notValues_.size() > 0) {
+      std::set<bool> notValues;
+      for (auto v : filterInfo.notValues_) {
+        notValues.emplace(v.value<bool>());
+      }
+      if (notValues.size() == 1) {
+        filters[common::Subfield(inputName)] = std::make_unique<common::BoolValue>(!(*notValues.begin()), nullAllowed);
+      } else {
+        // if there are more than one distinct value in NOT IN list, the filter should be AlwaysFalse
+        filters[common::Subfield(inputName)] = std::make_unique<common::AlwaysFalse>();
+      }
     } else if (rangeSize == 0) {
       // IsNull/IsNotNull.
       if (!nullAllowed) {
@@ -2140,11 +2182,22 @@ void SubstraitToVeloxPlanConverter::constructSubfieldFilters(
     if (filterInfo.values_.size() > 0) {
       // To filter out null is a default behaviour of Spark IN expression.
       nullAllowed = false;
-      setInFilter<KIND>(filterInfo.values_, nullAllowed, inputName, filters);
+      setInFilter<KIND>(filterInfo.values_, nullAllowed, false, inputName, filters);
       // Currently, In cannot coexist with other filter conditions
       // due to multirange is in 'OR' relation but 'AND' is needed.
       VELOX_CHECK(rangeSize == 0, "LowerBounds or upperBounds conditons cannot be supported after IN filter.");
       VELOX_CHECK(!filterInfo.notValue_.has_value(), "Not equal cannot be supported after IN filter.");
+      VELOX_CHECK(filterInfo.notValues_.size() == 0, "Not in cannot be supported after IN filter.");
+      return;
+    }
+
+    // Handle not in filter.
+    if (filterInfo.notValues_.size() > 0) {
+      setInFilter<KIND>(filterInfo.notValues_, filterInfo.nullAllowed_, true, inputName, filters);
+      // Currently, NOT In cannot coexist with other filter conditions
+      // due to multirange is in 'OR' relation but 'AND' is needed.
+      VELOX_CHECK(rangeSize == 0, "LowerBounds or upperBounds conditons cannot be supported after NOT IN filter.");
+      VELOX_CHECK(!filterInfo.notValue_.has_value(), "Not equal cannot be supported after NOT IN filter.");
       return;
     }
 
@@ -2429,7 +2482,8 @@ uint32_t SubstraitToVeloxPlanConverter::getColumnIndexFromSingularOrList(
 
 void SubstraitToVeloxPlanConverter::setFilterInfo(
     const ::substrait::Expression_SingularOrList& singularOrList,
-    std::vector<FilterInfo>& columnToFilterInfo) {
+    std::vector<FilterInfo>& columnToFilterInfo,
+    bool reverse) {
   VELOX_CHECK(singularOrList.options_size() > 0, "At least one option is expected.");
   // Get the column index.
   uint32_t colIdx = getColumnIndexFromSingularOrList(singularOrList);
@@ -2443,7 +2497,11 @@ void SubstraitToVeloxPlanConverter::setFilterInfo(
     variants.emplace_back(exprConverter_->toVeloxExpr(option.literal())->value());
   }
   // Set the value list to filter info.
-  columnToFilterInfo[colIdx].setValues(variants);
+  if (!reverse) {
+    columnToFilterInfo[colIdx].setValues(variants);
+  } else {
+    columnToFilterInfo[colIdx].setNotValues(variants);
+  }
 }
 
 } // namespace gluten
diff --git a/cpp/velox/substrait/SubstraitToVeloxPlan.h b/cpp/velox/substrait/SubstraitToVeloxPlan.h
index 3a0e677afeaa..1535b1f85f51 100644
--- a/cpp/velox/substrait/SubstraitToVeloxPlan.h
+++ b/cpp/velox/substrait/SubstraitToVeloxPlan.h
@@ -377,6 +377,16 @@ class SubstraitToVeloxPlanConverter {
       }
     }
 
+    // Set a list of values to be used in the push down of 'not in' expression.
+    void setNotValues(const std::vector<variant>& notValues) {
+      for (const auto& value : notValues) {
+        notValues_.emplace_back(value);
+      }
+      if (!initialized_) {
+        initialized_ = true;
+      }
+    }
+
     // Whether this filter map is initialized.
     bool initialized_ = false;
 
@@ -402,6 +412,9 @@ class SubstraitToVeloxPlanConverter {
 
     // The list of values used in 'in' expression.
     std::vector<variant> values_;
+
+    // The list of values should not be equal to.
+    std::vector<variant> notValues_;
   };
 
   /// Returns unique ID to use for plan node. Produces sequential numbers
@@ -464,9 +477,11 @@ class SubstraitToVeloxPlanConverter {
       bool reverse = false);
 
   /// Extract SingularOrList and set it to the filter info map.
+  /// If reverse is true, the opposite filter info will be set.
   void setFilterInfo(
       const ::substrait::Expression_SingularOrList& singularOrList,
-      std::vector<FilterInfo>& columnToFilterInfo);
+      std::vector<FilterInfo>& columnToFilterInfo,
+      bool reverse = false);
 
   /// Extract SingularOrList and returns the field index.
   static uint32_t getColumnIndexFromSingularOrList(const ::substrait::Expression_SingularOrList&);
@@ -484,13 +499,15 @@ class SubstraitToVeloxPlanConverter {
   template <TypeKind KIND, typename FilterType>
   void createNotEqualFilter(variant notVariant, bool nullAllowed, std::vector<std::unique_ptr<FilterType>>& colFilters);
 
-  /// Create a values range to handle in filter.
-  /// variants: the list of values extracted from the in expression.
+  /// Create a values range to handle (not) in filter.
+  /// variants: the list of values extracted from the (not) in expression.
+  //  negated: false for IN filter, true for NOT IN filter.
   /// inputName: the column input name.
   template <TypeKind KIND>
   void setInFilter(
       const std::vector<variant>& variants,
       bool nullAllowed,
+      bool negated,
       const std::string& inputName,
       connector::hive::SubfieldFilters& filters);
 
diff --git a/cpp/velox/tests/CMakeLists.txt b/cpp/velox/tests/CMakeLists.txt
index 29beb69da220..f3d65f127f67 100644
--- a/cpp/velox/tests/CMakeLists.txt
+++ b/cpp/velox/tests/CMakeLists.txt
@@ -16,14 +16,9 @@
 function(add_velox_test TEST_EXEC)
   set(options)
   set(one_value_args)
-  set(multi_value_args
-      SOURCES
-      )
-  cmake_parse_arguments(ARG
-      "${options}"
-      "${one_value_args}"
-      "${multi_value_args}"
-      ${ARGN})
+  set(multi_value_args SOURCES)
+  cmake_parse_arguments(ARG "${options}" "${one_value_args}"
+                        "${multi_value_args}" ${ARGN})
 
   if(ARG_SOURCES)
     set(SOURCES ${ARG_SOURCES})
@@ -31,34 +26,34 @@ function(add_velox_test TEST_EXEC)
     message(FATAL_ERROR "No sources specified for test ${TEST_NAME}")
   endif()
   add_executable(${TEST_EXEC} ${SOURCES} ${VELOX_TEST_COMMON_SRCS})
-  target_include_directories(${TEST_EXEC} PRIVATE ${CMAKE_SOURCE_DIR}/velox ${CMAKE_SOURCE_DIR}/src ${VELOX_BUILD_PATH}/_deps/duckdb-src/src/include)
-  target_link_libraries(${TEST_EXEC} velox_benchmark_common GTest::gtest GTest::gtest_main)
+  target_include_directories(
+    ${TEST_EXEC} PRIVATE ${CMAKE_SOURCE_DIR}/velox ${CMAKE_SOURCE_DIR}/src
+                         ${VELOX_BUILD_PATH}/_deps/duckdb-src/src/include)
+  target_link_libraries(${TEST_EXEC} velox_benchmark_common GTest::gtest
+                        GTest::gtest_main)
   gtest_discover_tests(${TEST_EXEC} DISCOVERY_MODE PRE_TEST)
 endfunction()
 
 set(VELOX_TEST_COMMON_SRCS JsonToProtoConverter.cc FilePathGenerator.cc)
 
 add_velox_test(velox_shuffle_writer_test SOURCES VeloxShuffleWriterTest.cc)
-# TODO: ORC is not well supported.
-# add_velox_test(orc_test SOURCES OrcTest.cc)
+# TODO: ORC is not well supported. add_velox_test(orc_test SOURCES OrcTest.cc)
 add_velox_test(
-    velox_operators_test
-    SOURCES
-    VeloxColumnarToRowTest.cc
-    VeloxRowToColumnarTest.cc
-    VeloxColumnarBatchSerializerTest.cc
-    VeloxColumnarBatchTest.cc)
+  velox_operators_test SOURCES VeloxColumnarToRowTest.cc
+  VeloxRowToColumnarTest.cc VeloxColumnarBatchSerializerTest.cc
+  VeloxColumnarBatchTest.cc)
 add_velox_test(
-    velox_plan_conversion_test
-    SOURCES
-    Substrait2VeloxPlanConversionTest.cc
-    Substrait2VeloxPlanValidatorTest.cc
-    Substrait2VeloxValuesNodeConversionTest.cc
-    SubstraitExtensionCollectorTest.cc
-    VeloxSubstraitRoundTripTest.cc
-    VeloxSubstraitSignatureTest.cc
-    VeloxToSubstraitTypeTest.cc)
-add_velox_test(spark_functions_test SOURCES SparkFunctionTest.cc FunctionTest.cc)
+  velox_plan_conversion_test
+  SOURCES
+  Substrait2VeloxPlanConversionTest.cc
+  Substrait2VeloxPlanValidatorTest.cc
+  Substrait2VeloxValuesNodeConversionTest.cc
+  SubstraitExtensionCollectorTest.cc
+  VeloxSubstraitRoundTripTest.cc
+  VeloxSubstraitSignatureTest.cc
+  VeloxToSubstraitTypeTest.cc)
+add_velox_test(spark_functions_test SOURCES SparkFunctionTest.cc
+               FunctionTest.cc)
 add_velox_test(execution_ctx_test SOURCES RuntimeTest.cc)
 add_velox_test(velox_memory_test SOURCES MemoryManagerTest.cc)
 add_velox_test(buffer_outputstream_test SOURCES BufferOutputStreamTest.cc)
diff --git a/docs/developers/CppCodingStyle.md b/docs/developers/CppCodingStyle.md
index 9dca4cf69fbc..42101882a9e5 100644
--- a/docs/developers/CppCodingStyle.md
+++ b/docs/developers/CppCodingStyle.md
@@ -28,11 +28,20 @@ Gluten CPP coding, there are a few Philosophical rules as the following.
 ## Code Formatting
 
 Many aspects of C++ coding style will be covered by clang-format, such as spacing,
-line width, indentation and ordering (for includes, using directives and etc). 
+line width, indentation and ordering (for includes, using directives and etc).
 
 * Always ensure your code is compatible with clang-format-15 for Velox backend.
 * `dev/formatcppcode.sh` is provided for formatting Velox CPP code.
 
+To format cmake files like CMakeLists.txt & *.cmake, `cmake-format` is required to
+be installed. Here is an example.
+
+```
+apt install python3-pip -y
+pip3 install --user cmake-format
+cmake-format --first-comment-is-literal True --in-place cpp/velox/CMakeLists.txt
+```
+
 ## Naming Conventions
 
 * Use **PascalCase** for types (class, struct, enum, type alias, type