[Refactor] Fixes some be typo part 2 (apache#4747)

be/src/common/daemon.cpp

@@ -180,12 +180,12 @@ static void init_doris_metrics(const std::vector<StorePath>& store_paths) {
     if (init_system_metrics) {
         auto st = DiskInfo::get_disk_devices(paths, &disk_devices);
         if (!st.ok()) {
-            LOG(WARNING) << "get disk devices failed, stauts=" << st.get_error_msg();
+            LOG(WARNING) << "get disk devices failed, status=" << st.get_error_msg();
             return;
         }
         st = get_inet_interfaces(&network_interfaces);
         if (!st.ok()) {
-            LOG(WARNING) << "get inet interfaces failed, stauts=" << st.get_error_msg();
+            LOG(WARNING) << "get inet interfaces failed, status=" << st.get_error_msg();
             return;
         }
     }

be/src/env/env.h

@@ -123,7 +123,7 @@ class Env {
     //
     // The function call extra cost is acceptable. Compared with returning all children
     // into a given vector, the performance of this method is 5% worse. However this
-    // approach is more flexiable and efficient in fulfilling other requirements.
+    // approach is more flexible and efficient in fulfilling other requirements.
     //
     // Returns OK if "dir" exists.
     //         NotFound if "dir" does not exist, the calling process does not have

be/src/exec/broker_writer.cpp

@@ -147,7 +147,7 @@ Status BrokerWriter::write(const uint8_t* buf, size_t buf_len, size_t* written_l
             return status;
         }
 
-        // we do not re-try simplely, because broker server may already write data
+        // we do not re-try simply, because broker server may already write data
         try {
             client->pwrite(response, request);
         } catch (apache::thrift::transport::TTransportException& e) {

be/src/exec/decompressor.cpp

@@ -131,7 +131,7 @@ Status GzipDecompressor::decompress(
             ret = inflateReset(&_z_strm);
             if (ret != Z_OK) {
                 std::stringstream ss;
-                ss << "Failed to inflateRset. return code: " << ret;
+                ss << "Failed to inflateReset. return code: " << ret;
                 return Status::InternalError(ss.str());
             }
         } else if (ret != Z_OK) {

be/src/exec/es/es_predicate.cpp

@@ -229,7 +229,7 @@ Status EsPredicate::build_disjuncts_list(const Expr* conjunct) {
     // process binary predicate
     if (TExprNodeType::BINARY_PRED == conjunct->node_type()) {
         if (conjunct->children().size() != 2) {
-            return Status::InternalError("build disjuncts failed: number of childs is not 2");
+            return Status::InternalError("build disjuncts failed: number of children is not 2");
         }
         SlotRef* slot_ref = nullptr;
         TExprOpcode::type op;
@@ -238,7 +238,7 @@ Status EsPredicate::build_disjuncts_list(const Expr* conjunct) {
         // doris on es should ignore this doris native cast transformation, we push down this `cast` to elasticsearch
         // conjunct->get_child(0)->node_type() return CAST_EXPR
         // conjunct->get_child(1)->node_type()return FLOAT_LITERAL
-        // the left child is literal and right child is SlotRef maybe not happend, but here we just process
+        // the left child is literal and right child is SlotRef maybe not happened, but here we just process
         // this situation regardless of the rewrite logic from the FE's Query Engine
         if (TExprNodeType::SLOT_REF == conjunct->get_child(0)->node_type()
             || TExprNodeType::CAST_EXPR == conjunct->get_child(0)->node_type()) {
@@ -288,7 +288,7 @@ Status EsPredicate::build_disjuncts_list(const Expr* conjunct) {
         std::string fname = conjunct->fn().name.function_name;
         if (fname == "esquery") {
             if (conjunct->children().size() != 2) {
-                return Status::InternalError("build disjuncts failed: number of childs is not 2");
+                return Status::InternalError("build disjuncts failed: number of children is not 2");
             }
             Expr* expr = conjunct->get_child(1);
             ExtLiteral literal(expr->type().type, _context->get_value(expr, NULL));
@@ -310,7 +310,7 @@ Status EsPredicate::build_disjuncts_list(const Expr* conjunct) {
             _disjuncts.push_back(predicate);
         } else if (fname == "is_null_pred" || fname == "is_not_null_pred") {
             if (conjunct->children().size() != 1) {
-                return Status::InternalError("build disjuncts failed: number of childs is not 1");
+                return Status::InternalError("build disjuncts failed: number of children is not 1");
             }
             // such as sub-query: select * from (select split_part(k, "_", 1) as new_field from table) t where t.new_field > 1;
             // conjunct->get_child(0)->node_type() == TExprNodeType::FUNCTION_CALL, at present doris on es can not support push down function
@@ -330,7 +330,7 @@ Status EsPredicate::build_disjuncts_list(const Expr* conjunct) {
             _disjuncts.push_back(predicate);
         } else if (fname == "like") {
             if (conjunct->children().size() != 2) {
-                return Status::InternalError("build disjuncts failed: number of childs is not 2");
+                return Status::InternalError("build disjuncts failed: number of children is not 2");
             }
             SlotRef* slot_ref = nullptr;
             Expr* expr = nullptr;
@@ -426,7 +426,7 @@ Status EsPredicate::build_disjuncts_list(const Expr* conjunct) {
         return Status::OK();
     }
     if (TExprNodeType::COMPOUND_PRED == conjunct->node_type()) {
-        // processe COMPOUND_AND, such as:
+        // process COMPOUND_AND, such as:
         // k = 1 or (k1 = 7 and (k2 in (6,7) or k3 = 12))
         // k1 = 7 and (k2 in (6,7) or k3 = 12) is compound pred, we should rebuild this sub tree
         if (conjunct->op() == TExprOpcode::COMPOUND_AND) {

be/src/exec/es/es_query_builder.cpp

@@ -243,9 +243,9 @@ BooleanQueryBuilder::BooleanQueryBuilder(const std::vector<ExtPredicate*>& predi
                 break;
             }
             case TExprNodeType::IS_NULL_PRED: {
-                ExtIsNullPredicate* is_null_preidicate = (ExtIsNullPredicate *)predicate;
-                ExistsQueryBuilder* exists_query = new ExistsQueryBuilder(*is_null_preidicate);
-                if (is_null_preidicate->is_not_null) {
+                ExtIsNullPredicate* is_null_predicate = (ExtIsNullPredicate *)predicate;
+                ExistsQueryBuilder* exists_query = new ExistsQueryBuilder(*is_null_predicate);
+                if (is_null_predicate->is_not_null) {
                     _should_clauses.push_back(exists_query);
                 } else {
                     BooleanQueryBuilder* bool_query = new BooleanQueryBuilder();

be/src/exec/es/es_query_builder.h

@@ -90,7 +90,7 @@ class WildCardQueryBuilder : public QueryBuilder {
     std::string _field;
 };
 
-// no predicates: all doccument match
+// no predicates: all document match
 class MatchAllQueryBuilder : public QueryBuilder {
 
 public:
@@ -109,7 +109,7 @@ class ExistsQueryBuilder : public QueryBuilder {
     std::string _field;
 };
 
-// proccess bool compound query, and play the role of a bridge for transferring predicates to es native query
+// process bool compound query, and play the role of a bridge for transferring predicates to es native query
 class BooleanQueryBuilder : public QueryBuilder {
 
 public:

be/src/exec/es/es_scan_reader.h

@@ -61,7 +61,7 @@ class ESScanReader {
     std::string _type;
     // push down filter
     std::string _query;
-    // elaticsearch shards to fetch document
+    // Elasticsearch shards to fetch document
     std::string _shards;
     // distinguish the first scroll phase and the following scroll
     bool _is_first;
@@ -81,7 +81,7 @@ class ESScanReader {
     // Each call to the scroll API returns the next batch of results until there are no more results left to return
     std::string _next_scroll_url;
 
-    // _search_url used to exeucte just only one search request to Elasticsearch
+    // _search_url used to execute just only one search request to Elasticsearch
     // _search_url would go into effect when `limit` specified:
     // select * from es_table limit 10 -> /es_table/doc/_search?terminate_after=10
     std::string _search_url;
@@ -91,7 +91,7 @@ class ESScanReader {
     std::string _cached_response;
     // keep-alive for es scroll
     std::string _scroll_keep_alive;
-    // timeout for es http connetion
+    // timeout for es http connection
     int _http_timeout_ms;
 
     bool _exactly_once;

be/src/exec/es/es_scroll_parser.cpp

@@ -86,7 +86,7 @@ static const string ERROR_COL_DATA_IS_ARRAY = "Data source returned an array for
             ss << "Expected value of type: " \
                << type_to_string(type)  \
                << "; but found type: " << json_type_to_string(col.GetType()) \
-               << "; Docuemnt slice is : " << json_value_to_string(col); \
+               << "; Document slice is : " << json_value_to_string(col); \
             return Status::RuntimeError(ss.str()); \
         } \
     } while (false)
@@ -99,7 +99,7 @@ static const string ERROR_COL_DATA_IS_ARRAY = "Data source returned an array for
             ss << "Expected value of type: " \
                << type_to_string(type)  \
                << "; but found type: " << json_type_to_string(col.GetType()) \
-               << "; Docuemnt source slice is : " << json_value_to_string(col); \
+               << "; Document source slice is : " << json_value_to_string(col); \
             return Status::RuntimeError(ss.str()); \
         } \
     } while (false)
@@ -123,7 +123,7 @@ static const string ERROR_COL_DATA_IS_ARRAY = "Data source returned an array for
             ss << "Expected value of type: " \
                << type_to_string(type)  \
                << "; but found type: " << json_type_to_string(col.GetType()) \
-               << "; Docuemnt source slice is : " << json_value_to_string(col); \
+               << "; Document source slice is : " << json_value_to_string(col); \
             return Status::RuntimeError(ss.str()); \
         } \
     } while (false)
@@ -134,7 +134,7 @@ static const string ERROR_COL_DATA_IS_ARRAY = "Data source returned an array for
         ss << "Expected value of type: " \
             << type_to_string(type)  \
             << "; but found type: " << json_type_to_string(col.GetType()) \
-            << "; Docuemnt slice is : " << json_value_to_string(col); \
+            << "; Document slice is : " << json_value_to_string(col); \
         return Status::RuntimeError(ss.str()); \
     } while (false)
 
@@ -219,7 +219,7 @@ Status ScrollParser::parse(const std::string& scroll_result, bool exactly_once)
     }
 
     if (!exactly_once && !_document_node.HasMember(FIELD_SCROLL_ID)) {
-        LOG(WARNING) << "Document has not a scroll id field scroll reponse:" << scroll_result;
+        LOG(WARNING) << "Document has not a scroll id field scroll response:" << scroll_result;
         return Status::InternalError("Document has not a scroll id field");
     }
 
@@ -454,7 +454,7 @@ Status ScrollParser::fill_tuple(const TupleDescriptor* tuple_desc,
                     // Doris On ES needs to be consistent with ES, so just divided by 1000 because the unit for from_unixtime is seconds
                     RETURN_IF_ERROR(fill_date_slot_with_timestamp(slot, col, type));
                 } else if (col.IsArray() && pure_doc_value) {
-                    // this would happend just only when `enable_docvalue_scan = true`
+                    // this would happened just only when `enable_docvalue_scan = true`
                     // ES add default format for all field after ES 6.4, if we not provided format for `date` field ES would impose
                     // a standard date-format for date field as `2020-06-16T00:00:00.000Z`
                     // At present, we just process this string format date. After some PR were merged into Doris, we would impose `epoch_mills` for
@@ -466,7 +466,7 @@ Status ScrollParser::fill_tuple(const TupleDescriptor* tuple_desc,
                     // ES would return millisecond timestamp for date field, divided by 1000 because the unit for from_unixtime is seconds
                     RETURN_IF_ERROR(fill_date_slot_with_timestamp(slot, col[0], type));
                 } else {
-                    // this would happend just only when `enable_docvalue_scan = false`, and field has string format date from _source
+                    // this would happened just only when `enable_docvalue_scan = false`, and field has string format date from _source
                     RETURN_ERROR_IF_COL_IS_ARRAY(col, type);
                     RETURN_ERROR_IF_COL_IS_NOT_STRING(col, type);
                     RETURN_IF_ERROR(fill_date_slot_with_strval(slot, col, type));

be/src/exec/es/es_scroll_query.cpp

@@ -68,7 +68,7 @@ std::string ESScrollQueryBuilder::build(const std::map<std::string, std::string>
     rapidjson::Document es_query_dsl;
     rapidjson::Document::AllocatorType &allocator = es_query_dsl.GetAllocator();
     es_query_dsl.SetObject();
-    // generate the filter caluse
+    // generate the filter clause
     rapidjson::Document scratch_document;
     rapidjson::Value query_node(rapidjson::kObjectType);
     query_node.SetObject();
@@ -128,7 +128,7 @@ std::string ESScrollQueryBuilder::build(const std::map<std::string, std::string>
     rapidjson::Value field("_doc", allocator);
     sort_node.PushBack(field, allocator);
     es_query_dsl.AddMember("sort", sort_node, allocator);
-    // number of docuements returned
+    // number of documents returned
     es_query_dsl.AddMember("size", size, allocator);
     rapidjson::StringBuffer buffer;
     rapidjson::Writer<rapidjson::StringBuffer> writer(buffer);

be/src/exec/es/es_scroll_query.h

@@ -33,7 +33,7 @@ class ESScrollQueryBuilder {
     static std::string build_next_scroll_body(const std::string& scroll_id, const std::string& scroll);
     static std::string build_clear_scroll_body(const std::string& scroll_id);
     // @note: predicates should processed before pass it to this method, 
-    // tie breaker for predicate wheather can push down es can reference the push-down filters
+    // tie breaker for predicate whether can push down es can reference the push-down filters
     static std::string build(const std::map<std::string, std::string>& properties,
                 const std::vector<std::string>& fields, std::vector<EsPredicate*>& predicates, const std::map<std::string, std::string>& docvalue_context,
                 bool* doc_value_mode);

be/src/exec/es_http_scan_node.cpp

@@ -385,7 +385,7 @@ Status EsHttpScanNode::scanner_scan(
             if (_runtime_state->is_cancelled()) {
                 return Status::Cancelled("Cancelled");
             }
-            // Queue size Must be samller than _max_buffered_batches
+            // Queue size Must be smaller than _max_buffered_batches
             _batch_queue.push_back(row_batch);
 
             // Notify reader to 
@@ -430,7 +430,7 @@ void EsHttpScanNode::scanner_worker(int start_idx, int length, std::promise<Stat
     const TEsScanRange& es_scan_range = 
         _scan_ranges[start_idx].scan_range.es_scan_range;
 
-    // Collect the informations from scan range to perperties
+    // Collect the information from scan range to properties
     std::map<std::string, std::string> properties(_properties);
     properties[ESScanReader::KEY_INDEX] = es_scan_range.index;
     if (es_scan_range.__isset.type) {

be/src/exec/es_http_scan_node.h

@@ -73,7 +73,7 @@ class EsHttpScanNode : public ScanNode {
     // Collect all scanners 's status
     Status collect_scanners_status();
 
-    // One scanner worker, This scanner will hanle 'length' ranges start from start_idx
+    // One scanner worker, This scanner will handle 'length' ranges start from start_idx
     void scanner_worker(int start_idx, int length, std::promise<Status>& p_status);
 
     // Scan one range

be/src/exec/es_scan_node.cpp

@@ -400,7 +400,7 @@ bool EsScanNode::get_disjuncts(ExprContext* context, Expr* conjunct,
                                vector<TExtPredicate>& disjuncts) {
     if (TExprNodeType::BINARY_PRED == conjunct->node_type()) {
         if (conjunct->children().size() != 2) {
-            VLOG(1) << "get disjuncts fail: number of childs is not 2";
+            VLOG(1) << "get disjuncts fail: number of children is not 2";
             return false;
         }
         SlotRef* slotRef;

be/src/exec/except_node.cpp

@@ -49,7 +49,7 @@ Status ExceptNode::open(RuntimeState* state) {
     bool eos = false;
 
     for (int i = 1; i < _children.size(); ++i) {
-        // rebuid hash table, for first time will rebuild with the no duplicated _hash_tbl,
+        // rebuild hash table, for first time will rebuild with the no duplicated _hash_tbl,
         if (i > 1) {
             SCOPED_TIMER(_build_timer);
             std::unique_ptr<HashTable> temp_tbl(

be/src/exec/except_node.h

@@ -25,7 +25,7 @@ class MemPool;
 class RowBatch;
 class TupleRow;
 
-// Node that calulate the except results of its children by either materializing their
+// Node that calculate the except results of its children by either materializing their
 // evaluated expressions into row batches or passing through (forwarding) the
 // batches if the input tuple layout is identical to the output tuple layout
 // and expressions don't need to be evaluated. The except node pulls from its

be/src/exec/hash_join_node_ir.cpp

@@ -27,7 +27,7 @@ namespace doris {
 // This lets us distinguish between the join conjuncts vs. non-join conjuncts
 // for codegen.
 // Note: don't declare this static.  LLVM will pick the fastcc calling convention and
-// we will not be able to replace the funcitons with codegen'd versions.
+// we will not be able to replace the functions with codegen'd versions.
 // TODO: explicitly set the calling convention?
 // TODO: investigate using fastcc for all codegen internal functions?
 bool IR_NO_INLINE eval_other_join_conjuncts(ExprContext* const* ctxs, int num_ctxs, TupleRow* row) {

be/src/exec/hash_table.h

@@ -113,7 +113,7 @@ class HashTable {
         insert_impl(row);
     }
 
-    // Insert row into the hash table. if the row is alread exist will not insert
+    // Insert row into the hash table. if the row is already exist will not insert
     void IR_ALWAYS_INLINE insert_unique(TupleRow* row) {
         if (find(row, false) == end()) {
             insert(row);
@@ -379,7 +379,7 @@ class HashTable {
     const int _num_build_tuples;
     // outer join || has null equal join should be true
     const bool _stores_nulls;
-    // true: the null-safe equal '<=>' is true. The row with null shoud be judged.
+    // true: the null-safe equal '<=>' is true. The row with null should be judged.
     // false: the equal '=' is false. The row with null should be filtered.
     const std::vector<bool> _finds_nulls;
 

be/src/exec/intersect_node.h

@@ -25,12 +25,12 @@ class MemPool;
 class RowBatch;
 class TupleRow;
 
-// Node that calulate the intersect results of its children by either materializing their
+// Node that calculate the intersect results of its children by either materializing their
 // evaluated expressions into row batches or passing through (forwarding) the
 // batches if the input tuple layout is identical to the output tuple layout
 // and expressions don't need to be evaluated. The children should be ordered
 // such that all passthrough children come before the children that need
-// materialization. The interscet node pulls from its children sequentially, i.e.
+// materialization. The intersect node pulls from its children sequentially, i.e.
 // it exhausts one child completely before moving on to the next one.
 class IntersectNode : public SetOperationNode {
 public:

be/src/exec/json_scanner.cpp

@@ -445,9 +445,9 @@ void JsonReader::_set_tuple_value(rapidjson::Value& objectValue, Tuple* tuple, c
  * handle input a simple json.
  * A json is a simple json only when user not specifying the json path.
  * For example:
- *  case 1. [{"colunm1":"value1", "colunm2":10}, {"colunm1":"
-", "colunm2":30}]
- *  case 2. {"colunm1":"value1", "colunm2":10}
+ *  case 1. [{"column1":"value1", "column2":10}, {"column1":"
+", "column2":30}]
+ *  case 2. {"column1":"value1", "column2":10}
  */
 Status JsonReader::_handle_simple_json(Tuple* tuple, const std::vector<SlotDescriptor*>& slot_descs, MemPool* tuple_pool, bool* eof) {
     do {
@@ -570,9 +570,9 @@ Status JsonReader::_handle_nested_complex_json(Tuple* tuple, const std::vector<S
 /**
  * flat array for json. _json_doc should be an array
  * For example:
- *  [{"colunm1":"value1", "colunm2":10}, {"colunm1":"value2", "colunm2":30}]
+ *  [{"column1":"value1", "column2":10}, {"column1":"value2", "column2":30}]
  * Result:
- *      colunm1    colunm2
+ *      column1    column2
  *      ------------------
  *      value1     10
  *      value2     30