[pull] master from apache:master

be/src/exec/arrow/parquet_row_group_reader.h

@@ -86,7 +86,6 @@ class RowGroupReader {
 private:
     int64_t _range_start_offset;
     int64_t _range_size;
-    int64_t _file_size;
     std::map<int, std::vector<ExprContext*>> _slot_conjuncts;
     std::unordered_set<int> _filter_group;
 

be/src/olap/like_column_predicate.cpp

@@ -39,72 +39,6 @@ void LikeColumnPredicate::evaluate(ColumnBlock* block, uint16_t* sel, uint16_t*
     }
 }
 
-void LikeColumnPredicate::evaluate(vectorized::IColumn& column, uint16_t* sel,
-                                   uint16_t* size) const {
-    uint16_t new_size = 0;
-
-    if (column.is_nullable()) {
-        auto* nullable_col = vectorized::check_and_get_column<vectorized::ColumnNullable>(column);
-        auto& null_map_data = nullable_col->get_null_map_column().get_data();
-        auto& nested_col = nullable_col->get_nested_column();
-        if (nested_col.is_column_dictionary()) {
-            auto* nested_col_ptr = vectorized::check_and_get_column<
-                    vectorized::ColumnDictionary<vectorized::Int32>>(nested_col);
-            auto& data_array = nested_col_ptr->get_data();
-            for (uint16_t i = 0; i < *size; i++) {
-                uint16_t idx = sel[i];
-                sel[new_size] = idx;
-                if (null_map_data[idx]) {
-                    new_size += _opposite;
-                    continue;
-                }
-
-                StringValue cell_value = nested_col_ptr->get_value(data_array[idx]);
-                doris_udf::StringVal target;
-                cell_value.to_string_val(&target);
-                new_size += _opposite ^ ((_state->function)(_fn_ctx, target, pattern).val);
-            }
-        } else {
-            for (uint16_t i = 0; i < *size; i++) {
-                uint16_t idx = sel[i];
-                sel[new_size] = idx;
-                if (null_map_data[idx]) {
-                    new_size += _opposite;
-                    continue;
-                }
-
-                StringRef cell_value = nested_col.get_data_at(idx);
-                doris_udf::StringVal target = cell_value.to_string_val();
-                new_size += _opposite ^ ((_state->function)(_fn_ctx, target, pattern).val);
-            }
-        }
-    } else {
-        if (column.is_column_dictionary()) {
-            auto* nested_col_ptr = vectorized::check_and_get_column<
-                    vectorized::ColumnDictionary<vectorized::Int32>>(column);
-            auto& data_array = nested_col_ptr->get_data();
-            for (uint16_t i = 0; i < *size; i++) {
-                uint16_t idx = sel[i];
-                sel[new_size] = idx;
-                StringValue cell_value = nested_col_ptr->get_value(data_array[idx]);
-                doris_udf::StringVal target;
-                cell_value.to_string_val(&target);
-                new_size += _opposite ^ ((_state->function)(_fn_ctx, target, pattern).val);
-            }
-        } else {
-            for (uint16_t i = 0; i < *size; i++) {
-                uint16_t idx = sel[i];
-                sel[new_size] = idx;
-                StringRef cell_value = column.get_data_at(idx);
-                doris_udf::StringVal target = cell_value.to_string_val();
-                new_size += _opposite ^ ((_state->function)(_fn_ctx, target, pattern).val);
-            }
-        }
-    }
-
-    *size = new_size;
-}
-
 void LikeColumnPredicate::evaluate_vec(const vectorized::IColumn& column, uint16_t size,
                                        bool* flags) const {
     if (column.is_nullable()) {

be/src/olap/like_column_predicate.h

@@ -33,7 +33,6 @@ class LikeColumnPredicate : public ColumnPredicate {
 
     PredicateType type() const override { return PredicateType::EQ; }
     void evaluate_vec(const vectorized::IColumn& column, uint16_t size, bool* flags) const override;
-    void evaluate(vectorized::IColumn& column, uint16_t* sel, uint16_t* size) const;
 
     void evaluate(ColumnBlock* block, uint16_t* sel, uint16_t* size) const override;
 

be/src/vec/common/hash_table/string_hash_table.h

@@ -94,9 +94,10 @@ struct StringHashTableEmpty //-V730
 public:
     bool has_zero() const { return _has_zero; }
 
-    void set_has_zero() {
+    void set_has_zero(const typename Cell::key_type& key) {
         _has_zero = true;
         new (zero_value()) Cell();
+        zero_value()->value.first = key;
     }
 
     void set_has_zero(const Cell& other) {
@@ -118,9 +119,11 @@ struct StringHashTableEmpty //-V730
     using ConstLookupResult = const Cell*;
 
     template <typename KeyHolder>
-    void ALWAYS_INLINE emplace(KeyHolder&&, LookupResult& it, bool& inserted, size_t = 0) {
+    void ALWAYS_INLINE emplace(KeyHolder&& key_holder, LookupResult& it, bool& inserted,
+                               size_t = 0) {
         if (!has_zero()) {
-            set_has_zero();
+            const auto& key = key_holder_get_key(key_holder);
+            set_has_zero(key);
             inserted = true;
         } else
             inserted = false;
@@ -292,28 +295,28 @@ class StringHashTable : private boost::noncopyable {
                 break;
             }
             case 1: {
-                iterator1.template operator++();
+                ++iterator1;
                 if (iterator1 == container->m1.end()) {
                     need_switch_to_next = true;
                 }
                 break;
             }
             case 2: {
-                iterator2.template operator++();
+                ++iterator2;
                 if (iterator2 == container->m2.end()) {
                     need_switch_to_next = true;
                 }
                 break;
             }
             case 3: {
-                iterator3.template operator++();
+                ++iterator3;
                 if (iterator3 == container->m3.end()) {
                     need_switch_to_next = true;
                 }
                 break;
             }
             case 4: {
-                iterator4.template operator++();
+                ++iterator4;
                 break;
             }
             }
@@ -467,7 +470,7 @@ class StringHashTable : private boost::noncopyable {
         const size_t sz = x.size;
         if (sz == 0) {
             key_holder_discard_key(key_holder);
-            return func(self.m0, VoidKey {}, 0);
+            return func(self.m0, std::forward<KeyHolder>(key_holder), 0);
         }
 
         if (x.data[sz - 1] == 0) {

docs/.vuepress/sidebar/en/docs.js

@@ -248,6 +248,7 @@ module.exports = [
           "spark-sink"
         ],
       },
+      "cloudcanal",
       {
         title: "UDF",
         directoryPath: "udf/",

docs/.vuepress/sidebar/zh-CN/docs.js

@@ -248,6 +248,7 @@ module.exports = [
           "spark-sink"
         ],
       },
+      "cloudcanal",
       {
         title: "自定义函数",
         directoryPath: "udf/",
@@ -790,7 +791,7 @@ module.exports = [
               "SHOW-STREAM-LOAD",
               "SHOW-SYNC-JOB",
               "SHOW-TABLE-ID",
-              "SHOW-TABLES",			  
+              "SHOW-TABLES",
               "SHOW-TABLE-STATUS",
               "SHOW-TABLET",
               "SHOW-TRANSACTION",

docs/en/docs/ecosystem/cloudcanal.md

@@ -0,0 +1,35 @@
+---
+{
+    "title": "CloudCanal Data Import",
+    "language": "zh-CN"
+}
+---
+
+<!--
+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.
+-->
+
+# CloudCanal Data Import
+
+## Introduction
+
+CloudCanal Community Edition is a free data migration and synchronization platform published by [ClouGence Company](https://www.clougence.com) that integrates structure migration, full data migration/check/correction, and incremental real-time synchronization. Product contains complete
+Its productization capabilities help enterprises break data silos, complete data integration and interoperability, and make better use of data.
+![image.png](../../../.vuepress/public/images/cloudcanal/cloudcanal-1.jpg)
+
+> There is no English version of this document, please switch to the Chinese version.

docs/zh-CN/docs/ecosystem/cloudcanal.md

@@ -1,3 +1,29 @@
+---
+{
+    "title": "CloudCanal 数据导入",
+    "language": "zh-CN"
+}
+---
+
+<!--
+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.
+-->
+
 # CloudCanal 数据导入
 
 ## 介绍