[fix](typo) fix spelling typos in BE and cloud comments and messages

be/src/common/config.cpp

@@ -1378,7 +1378,7 @@ DEFINE_mInt64(auto_inc_fetch_thread_num, "3");
 // default max to 2048 connections
 DEFINE_mInt64(lookup_connection_cache_capacity, "2048");
 
-// level of compression when using LZ4_HC, whose defalut value is LZ4HC_CLEVEL_DEFAULT
+// level of compression when using LZ4_HC, whose default value is LZ4HC_CLEVEL_DEFAULT
 DEFINE_mInt64(LZ4_HC_compression_level, "9");
 
 DEFINE_mBool(enable_merge_on_write_correctness_check, "true");

be/src/common/config.h

@@ -489,7 +489,7 @@ DECLARE_Bool(enable_parquet_cache_compressed_pages);
 // whether to disable pk page cache feature in storage
 DECLARE_Bool(disable_pk_storage_page_cache);
 
-// Cache for mow primary key storage page size, it's seperated from
+// Cache for mow primary key storage page size, it's separated from
 // storage_page_cache_limit
 DECLARE_String(pk_storage_page_cache_limit);
 // data page size for primary key index
@@ -1435,7 +1435,7 @@ DECLARE_mInt64(auto_inc_fetch_thread_num);
 // Max connection cache num for point lookup queries
 DECLARE_mInt64(lookup_connection_cache_capacity);
 
-// level of compression when using LZ4_HC, whose defalut value is LZ4HC_CLEVEL_DEFAULT
+// level of compression when using LZ4_HC, whose default value is LZ4HC_CLEVEL_DEFAULT
 DECLARE_mInt64(LZ4_HC_compression_level);
 // Max json key length in bytes when parsing json into variant subcolumns/jsonb.
 DECLARE_mInt32(variant_max_json_key_length);

be/src/core/column/column.h

@@ -181,7 +181,7 @@ class IColumn : public COW<IColumn> {
                                "Method erase is not supported for " + get_name());
     }
 
-    /// cut or expand inplace. `this` would be moved, only the return value is avaliable.
+    /// cut or expand inplace. `this` would be moved, only the return value is available.
     virtual Ptr shrink(size_t length) const final {
         // NOLINTBEGIN(performance-move-const-arg)
         MutablePtr res = std::move(*this).mutate();

be/src/core/value/vdatetime_value.h

@@ -599,7 +599,7 @@ class VecDateTimeValue { // Now this type is a temp solution with little changes
     void unix_timestamp(int64_t* timestamp, const cctz::time_zone& ctz) const;
 
     //construct datetime_value from timestamp and timezone
-    //timestamp is an internal timestamp value representing seconds since '1970-01-01 00:00:00' UTC. negative avaliable.
+    //timestamp is an internal timestamp value representing seconds since '1970-01-01 00:00:00' UTC. negative available.
     //we don't do any check in it because it's hot path. any usage want ensure the time legality should check itself.
     bool from_unixtime(int64_t, const std::string& timezone);
     void from_unixtime(int64_t, const cctz::time_zone& ctz);
@@ -1102,7 +1102,7 @@ class DateV2Value {
     void unix_timestamp(std::pair<int64_t, int64_t>* timestamp, const cctz::time_zone& ctz) const;
 
     //construct datetime_value from timestamp and timezone
-    //timestamp is an internal timestamp value representing seconds since '1970-01-01 00:00:00' UTC. negative avaliable.
+    //timestamp is an internal timestamp value representing seconds since '1970-01-01 00:00:00' UTC. negative available.
     //we don't do any check in it because it's hot path. any usage want ensure the time legality should check itself.
     bool from_unixtime(int64_t, const std::string& timezone);
     void from_unixtime(int64_t, const cctz::time_zone& ctz);

be/src/exec/pipeline/pipeline_fragment_context.cpp

@@ -2675,7 +2675,7 @@ PipelineFragmentContext::collect_realtime_profile() const {
     std::vector<std::shared_ptr<TRuntimeProfileTree>> res;
 
     // we do not have mutex to protect pipeline_id_to_profile
-    // so we need to make sure this funciton is invoked after fragment context
+    // so we need to make sure this function is invoked after fragment context
     // has already been prepared.
     if (!_prepared) {
         std::string msg =
@@ -2703,7 +2703,7 @@ PipelineFragmentContext::collect_realtime_profile() const {
 std::shared_ptr<TRuntimeProfileTree>
 PipelineFragmentContext::collect_realtime_load_channel_profile() const {
     // we do not have mutex to protect pipeline_id_to_profile
-    // so we need to make sure this funciton is invoked after fragment context
+    // so we need to make sure this function is invoked after fragment context
     // has already been prepared.
     if (!_prepared) {
         std::string msg =

be/src/exec/sink/writer/async_result_writer.cpp

@@ -180,7 +180,7 @@ void AsyncResultWriter::process_block(RuntimeState* state, RuntimeProfile* opera
 
     bool need_finish = false;
     {
-        // If the last block is sent successfuly, then call finish to clear the buffer or commit
+        // If the last block is sent successfully, then call finish to clear the buffer or commit
         // transactions.
         // Using lock to make sure the writer status is not modified
         // There is a unique ptr err_msg in Status, if it is modified, the unique ptr

be/src/exec/sink/writer/vtablet_writer.cpp

@@ -1562,7 +1562,7 @@ void VTabletWriter::_send_batch_process() {
         }
 
         // for auto partition tables, there's a situation: we haven't open any node channel but decide to cancel the task.
-        // then the judge in front will never be true because opened_nodes won't increase. so we have to specially check wether we called close.
+        // then the judge in front will never be true because opened_nodes won't increase. so we have to specially check whether we called close.
         // we must RECHECK opened_nodes below, after got closed signal, because it may changed. Think of this:
         //      checked opened_nodes = 0 ---> new block arrived ---> task finished, close() was called ---> we got _try_close here
         // if we don't check again, we may lose the last package.

be/src/exprs/aggregate/aggregate_function_rpc.h

@@ -326,7 +326,7 @@ struct AggregateRpcUdafData {
             break;
         }
         default:
-            LOG(ERROR) << "failed to get result cause unkown return type";
+            LOG(ERROR) << "failed to get result cause unknown return type";
             to.insert_default();
         }
         return Status::OK();

be/src/exprs/function/function_bitmap.cpp

@@ -167,7 +167,7 @@ struct ToBitmapWithCheck {
                     continue;
                 } else {
                     const char* raw_str = reinterpret_cast<const char*>(&data[offsets[i - 1]]);
-                    // The string lenght is less than 2G, so that cast the str size to int, not use size_t
+                    // The string length is less than 2G, so that cast the str size to int, not use size_t
                     int str_size = cast_set<int>(offsets[i] - offsets[i - 1]);
                     StringParser::ParseResult parse_result = StringParser::PARSE_SUCCESS;
                     uint64_t int_value = StringParser::string_to_unsigned_int<uint64_t>(
@@ -329,7 +329,7 @@ struct BitmapFromArray {
             auto prev_offset = offset_column_data[i - 1];
             for (auto j = prev_offset; j < curr_offset; ++j) {
                 auto data = nested_column_data[j];
-                // invaild value
+                // invalid value
                 if (UNLIKELY(data < 0) || UNLIKELY(nested_null_map[j])) {
                     res.emplace_back();
                     null_map[i] = 1;

be/src/exprs/function/function_convert_tz.cpp

@@ -139,7 +139,7 @@ class FunctionConvertTZ : public IFunction {
                 context->get_function_state(FunctionContext::FRAGMENT_LOCAL));
         if (!convert_tz_state) {
             return Status::RuntimeError(
-                    "funciton context for function '{}' must have ConvertTzState;", get_name());
+                    "function context for function '{}' must have ConvertTzState;", get_name());
         }
 
         auto result_null_map_column = ColumnUInt8::create(input_rows_count, 0);

be/src/exprs/function/function_datetime_string_to_string.h

@@ -162,7 +162,7 @@ class FunctionDateTimeStringToString : public IFunction {
         auto* format_state = reinterpret_cast<FormatState*>(
                 context->get_function_state(FunctionContext::FRAGMENT_LOCAL));
         if (!format_state) {
-            return Status::RuntimeError("funciton context for function '{}' must have FormatState;",
+            return Status::RuntimeError("function context for function '{}' must have FormatState;",
                                         get_name());
         }
 

be/src/exprs/function/function_dict_get.cpp

@@ -33,7 +33,7 @@ namespace doris {
 struct DictGetState {
     std::shared_ptr<const IDictionary> dict;
     ///TODO:
-    // 1. we do not need to check dict every time(shoud only check in open)
+    // 1. we do not need to check dict every time(should only check in open)
     // 2. for some dict, will init some struct each time, we should cache it
 };
 
@@ -85,7 +85,7 @@ class FunctionDictGet : public IFunction {
         auto* dict_state = reinterpret_cast<DictGetState*>(
                 context->get_function_state(FunctionContext::FRAGMENT_LOCAL));
         if (!dict_state) {
-            return Status::RuntimeError("funciton context for function '{}' must have dict_state;",
+            return Status::RuntimeError("function context for function '{}' must have dict_state;",
                                         get_name());
         }
 

be/src/exprs/function/function_dict_get_many.cpp

@@ -38,7 +38,7 @@ namespace doris {
 struct DictGetState {
     std::shared_ptr<const IDictionary> dict;
     ///TODO:
-    // 1. we do not need to check dict every time(shoud only check in open)
+    // 1. we do not need to check dict every time(should only check in open)
     // 2. for some dict, will init some struct each time, we should cache it
 };
 
@@ -90,7 +90,7 @@ class FunctionDictGetMany : public IFunction {
         auto* dict_state = reinterpret_cast<DictGetState*>(
                 context->get_function_state(FunctionContext::FRAGMENT_LOCAL));
         if (!dict_state) {
-            return Status::RuntimeError("funciton context for function '{}' must have dict_state;",
+            return Status::RuntimeError("function context for function '{}' must have dict_state;",
                                         get_name());
         }
 

be/src/exprs/function/function_string_concat.h

@@ -114,7 +114,7 @@ class FunctionStringConcat : public IFunction {
         auto* concat_state = reinterpret_cast<ConcatState*>(
                 context->get_function_state(FunctionContext::FRAGMENT_LOCAL));
         if (!concat_state) {
-            return Status::RuntimeError("funciton context for function '{}' must have ConcatState;",
+            return Status::RuntimeError("function context for function '{}' must have ConcatState;",
                                         get_name());
         }
         if (concat_state->use_state) {

be/src/exprs/function/in.h

@@ -198,7 +198,7 @@ class FunctionIn : public IFunction {
         auto* in_state = reinterpret_cast<InState*>(
                 context->get_function_state(FunctionContext::FRAGMENT_LOCAL));
         if (!in_state) {
-            return Status::RuntimeError("funciton context for function '{}' must have Set;",
+            return Status::RuntimeError("function context for function '{}' must have Set;",
                                         get_name());
         }
         auto res = ColumnUInt8::create();

be/src/format/orc/vorc_reader.cpp

@@ -1041,7 +1041,7 @@ bool OrcReader::_check_expr_can_push_down(const VExprSPtr& expr) {
             if (fn_name == "is_null_pred" || fn_name == "is_not_null_pred") {
                 return _check_slot_can_push_down(expr);
             }
-            VLOG_CRITICAL << "Unsupported function [funciton=" << fn_name << "]";
+            VLOG_CRITICAL << "Unsupported function [function=" << fn_name << "]";
         }
         return false;
     default:

be/src/io/fs/s3_file_reader.cpp

@@ -56,7 +56,7 @@ bvar::LatencyRecorder s3_bytes_per_read("s3_file_reader", "bytes_per_read"); //
 bvar::PerSecond<bvar::Adder<uint64_t>> s3_read_througthput("s3_file_reader", "s3_read_throughput",
                                                            &s3_bytes_read_total);
 // Although we can get QPS from s3_bytes_per_read, but s3_bytes_per_read only
-// record successfull request, and s3_get_request_qps will record all request.
+// record successful request, and s3_get_request_qps will record all request.
 bvar::PerSecond<bvar::Adder<uint64_t>> s3_get_request_qps("s3_file_reader", "s3_get_request",
                                                           &s3_file_reader_read_counter);
 bvar::LatencyRecorder s3_file_reader_latency("s3_file_reader", "s3_latency");

be/src/runtime/fragment_mgr.cpp

@@ -632,7 +632,7 @@ Status FragmentMgr::exec_plan_fragment(const TPipelineFragmentParams& params,
     VLOG_ROW << "Query: " << print_id(params.query_id) << " exec_plan_fragment params is "
              << apache::thrift::ThriftDebugString(params).c_str();
     // sometimes TPipelineFragmentParams debug string is too long and glog
-    // will truncate the log line, so print query options seperately for debuggin purpose
+    // will truncate the log line, so print query options separately for debuggin purpose
     VLOG_ROW << "Query: " << print_id(params.query_id) << "query options is "
              << apache::thrift::ThriftDebugString(params.query_options).c_str();
 

be/src/runtime/memory/mem_tracker_limiter.h

@@ -301,7 +301,7 @@ inline Status MemTrackerLimiter::check_limit(int64_t bytes) {
     }
 
     // If reserve not enabled, then should check limit here to kill the query when limit exceed.
-    // For insert into select or pure load job, its memtable is accounted in a seperate memtracker limiter,
+    // For insert into select or pure load job, its memtable is accounted in a separate memtracker limiter,
     // and its reserve is set to true. So that it will not reach this logic.
     // Only query and load job has exec_mem_limit and the _limit > 0, other memtracker limiter's _limit is -1 so
     // it will not take effect.

be/src/runtime/memory/thread_mem_tracker_mgr.h

@@ -352,7 +352,7 @@ inline doris::Status ThreadMemTrackerMgr::try_reserve(int64_t size, TryReserveCh
     if (process_limit_checker) {
         if (!doris::GlobalMemoryArbitrator::try_reserve_process_memory(size)) {
             auto err_msg = fmt::format(
-                    "reserve memory failed, size: {}, because proccess memory exceeded, {}",
+                    "reserve memory failed, size: {}, because process memory exceeded, {}",
                     PrettyPrinter::print_bytes(size),
                     GlobalMemoryArbitrator::process_mem_log_str());
             _limiter_tracker->release(size);         // rollback

be/src/service/point_query_executor.cpp

@@ -497,7 +497,7 @@ Status PointQueryExecutor::_lookup_row_key() {
         _row_read_ctxs[i]._row_location = location;
         // acquire and wrap this rowset
         (*rowset_ptr)->acquire();
-        VLOG_DEBUG << "aquire rowset " << (*rowset_ptr)->rowset_id();
+        VLOG_DEBUG << "acquire rowset " << (*rowset_ptr)->rowset_id();
         _row_read_ctxs[i]._rowset_ptr = std::unique_ptr<RowsetSharedPtr, decltype(&release_rowset)>(
                 rowset_ptr.release(), &release_rowset);
         _row_hits++;

be/src/storage/cache/page_cache.h

@@ -206,7 +206,7 @@ class StoragePageCache {
     int32_t _index_cache_percentage = 0;
     std::unique_ptr<DataPageCache> _data_page_cache;
     std::unique_ptr<IndexPageCache> _index_page_cache;
-    // Cache data for primary key index data page, seperated from data
+    // Cache data for primary key index data page, separated from data
     // page cache to make it for flexible. we need this cache When construct
     // delete bitmap in unique key with mow
     std::unique_ptr<PKIndexPageCache> _pk_index_page_cache;

be/src/storage/compaction/compaction.cpp

@@ -527,7 +527,7 @@ Status CompactionMixin::build_basic_info(bool is_ordered_compaction) {
                    [](const RowsetSharedPtr& rowset) { return rowset->rowset_meta(); });
     _cur_tablet_schema = _tablet->tablet_schema_with_merged_max_schema_version(rowset_metas);
 
-    // if enable_vertical_compact_variant_subcolumns is true, we need to compact the variant subcolumns in seperate column groups
+    // if enable_vertical_compact_variant_subcolumns is true, we need to compact the variant subcolumns in separate column groups
     // so get_extended_compaction_schema will extended the schema for variant columns
     // for ordered compaction, we don't need to extend the schema for variant columns
     if (_enable_vertical_compact_variant_subcolumns && !is_ordered_compaction) {
@@ -1685,7 +1685,7 @@ Status CloudCompactionMixin::build_basic_info() {
         _cur_tablet_schema = _tablet->tablet_schema_with_merged_max_schema_version(rowset_metas);
     }
 
-    // if enable_vertical_compact_variant_subcolumns is true, we need to compact the variant subcolumns in seperate column groups
+    // if enable_vertical_compact_variant_subcolumns is true, we need to compact the variant subcolumns in separate column groups
     // so get_extended_compaction_schema will extended the schema for variant columns
     if (_enable_vertical_compact_variant_subcolumns) {
         RETURN_IF_ERROR(variant_util::VariantCompactionUtil::get_extended_compaction_schema(

be/src/storage/index/zone_map/zone_map_index.h

@@ -198,7 +198,7 @@ class ZoneMapIndexReader : public MetadataAdder<ZoneMapIndexReader> {
 
 private:
     DorisCallOnce<Status> _load_once;
-    // TODO: yyq, we shoud remove file_reader from here.
+    // TODO: yyq, we should remove file_reader from here.
     io::FileReaderSPtr _file_reader;
     std::unique_ptr<IndexedColumnMetaPB> _page_zone_maps_meta;
     std::vector<ZoneMapPB> _page_zone_maps;

be/src/storage/partial_update_info.cpp

@@ -640,7 +640,7 @@ static void fill_non_primary_key_cell_for_column_store(
             } else if (tablet_column.is_auto_increment()) {
                 // In flexible partial update, the skip bitmap indicates whether a cell
                 // is specified in the original load, so the generated auto-increment value is filled
-                // in current block in place if needed rather than using a seperate column to
+                // in current block in place if needed rather than using a separate column to
                 // store the generated auto-increment value in fixed partial update
                 new_col->insert_from(cur_col, block_pos);
             } else {
@@ -747,7 +747,7 @@ static void fill_non_primary_key_cell_for_row_store(
             } else if (tablet_column.is_auto_increment()) {
                 // In flexible partial update, the skip bitmap indicates whether a cell
                 // is specified in the original load, so the generated auto-increment value is filled
-                // in current block in place if needed rather than using a seperate column to
+                // in current block in place if needed rather than using a separate column to
                 // store the generated auto-increment value in fixed partial update
                 new_col->insert_from(cur_col, block_pos);
             } else {

be/src/storage/segment/segment.cpp

@@ -280,7 +280,7 @@ Status Segment::_open(OlapReaderStatistics* stats) {
     _num_rows = footer_pb_shared->num_rows();
 
     // An estimated memory usage of a segment
-    // Footer is seperated to StoragePageCache so we don't need to add it to _meta_mem_usage
+    // Footer is separated to StoragePageCache so we don't need to add it to _meta_mem_usage
     // _meta_mem_usage += footer_pb_shared->ByteSizeLong();
     if (_pk_index_meta != nullptr) {
         _meta_mem_usage += _pk_index_meta->ByteSizeLong();

be/src/storage/segment/segment_iterator.cpp

@@ -2732,11 +2732,11 @@ Status SegmentIterator::_read_columns_by_rowids(std::vector<ColumnId>& read_colu
     }
 
     for (auto cid : read_column_ids) {
-        auto& colunm = (*mutable_columns)[cid];
-        if (_no_need_read_key_data(cid, colunm, select_size)) {
+        auto& column = (*mutable_columns)[cid];
+        if (_no_need_read_key_data(cid, column, select_size)) {
             continue;
         }
-        if (_prune_column(cid, colunm, select_size)) {
+        if (_prune_column(cid, column, select_size)) {
             continue;
         }
 

be/src/storage/segment/vertical_segment_writer.h

@@ -90,7 +90,7 @@ class VerticalSegmentWriter {
 
     // Add one block to batch, memory is owned by the caller.
     // The batched blocks will be flushed in write_batch.
-    // Once write_batch is called, no more blocks shoud be added.
+    // Once write_batch is called, no more blocks should be added.
     Status batch_block(const Block* block, size_t row_pos, size_t num_rows);
     Status write_batch();
 

be/src/storage/storage_engine.cpp

@@ -1411,7 +1411,7 @@ void StorageEngine::add_unused_delete_bitmap_key_ranges(int64_t tablet_id,
     _unused_delete_bitmap.push_back(std::make_tuple(tablet_id, rowsets, key_ranges));
 }
 
-// TODO(zc): refactor this funciton
+// TODO(zc): refactor this function
 Status StorageEngine::create_tablet(const TCreateTabletReq& request, RuntimeProfile* profile) {
     // Get all available stores, use ref_root_path if the caller specified
     std::vector<DataDir*> stores;