diff --git a/base/glibc-compatibility/musl/lgammal.c b/base/glibc-compatibility/musl/lgammal.c index 3b5d94c5051..19db11fba1a 100644 --- a/base/glibc-compatibility/musl/lgammal.c +++ b/base/glibc-compatibility/musl/lgammal.c @@ -38,7 +38,7 @@ * = log(6.3*5.3) + lgamma(5.3) * = log(6.3*5.3*4.3*3.3*2.3) + lgamma(2.3) * 2. Polynomial approximation of lgamma around its - * minimun ymin=1.461632144968362245 to maintain monotonicity. + * minimum ymin=1.461632144968362245 to maintain monotonicity. * On [ymin-0.23, ymin+0.27] (i.e., [1.23164,1.73163]), use * Let z = x-ymin; * lgamma(x) = -1.214862905358496078218 + z^2*poly(z) diff --git a/base/glibc-compatibility/musl/powl.c b/base/glibc-compatibility/musl/powl.c index 508c65c9c7c..70cc3fd02ab 100644 --- a/base/glibc-compatibility/musl/powl.c +++ b/base/glibc-compatibility/musl/powl.c @@ -202,7 +202,7 @@ long double powl(long double x, long double y) volatile long double z=0; long double w=0, W=0, Wa=0, Wb=0, ya=0, yb=0, u=0; - /* make sure no invalid exception is raised by nan comparision */ + /* make sure no invalid exception is raised by nan comparison */ if (isnan(x)) { if (!isnan(y) && y == 0.0) return 1.0; diff --git a/base/pcg-random/pcg_random.hpp b/base/pcg-random/pcg_random.hpp index f7778480c4c..abf83a60ee1 100644 --- a/base/pcg-random/pcg_random.hpp +++ b/base/pcg-random/pcg_random.hpp @@ -129,7 +129,7 @@ using namespace pcg_extras; * * default_multiplier::multiplier() * - * gives you the default multipler for 32-bit integers. We use the name + * gives you the default multiplier for 32-bit integers. We use the name * of the constant and not a generic word like value to allow these classes * to be used as mixins. */ diff --git a/docker/test/style/Dockerfile b/docker/test/style/Dockerfile index 1a4356caced..239a074969c 100644 --- a/docker/test/style/Dockerfile +++ b/docker/test/style/Dockerfile @@ -4,5 +4,8 @@ FROM ubuntu:20.04 RUN apt-get update && env DEBIAN_FRONTEND=noninteractive apt-get install --yes shellcheck libxml2-utils git python3-pip && pip3 install codespell -CMD cd /ClickHouse/utils/check-style && ./check-style -n | tee /test_output/style_output.txt && \ +CMD cd /ClickHouse/utils/check-style && \ + ./check-style -n | tee /test_output/style_output.txt && \ + ./check-typos | tee /test_output/typos_output.txt && \ + ./check-whitespaces -n | tee /test_output/whitespaces_output.txt && \ ./check-duplicate-includes.sh | tee /test_output/duplicate_output.txt diff --git a/src/AggregateFunctions/AggregateFunctionGroupArrayInsertAt.h b/src/AggregateFunctions/AggregateFunctionGroupArrayInsertAt.h index 6a5f2fbc899..a4800dd715e 100644 --- a/src/AggregateFunctions/AggregateFunctionGroupArrayInsertAt.h +++ b/src/AggregateFunctions/AggregateFunctionGroupArrayInsertAt.h @@ -107,7 +107,7 @@ public: /// TODO Do positions need to be 1-based for this function? size_t position = columns[1]->getUInt(row_num); - /// If position is larger than size to which array will be cutted - simply ignore value. + /// If position is larger than size to which array will be cut - simply ignore value. if (length_to_resize && position >= length_to_resize) return; diff --git a/src/Common/Config/ConfigProcessor.h b/src/Common/Config/ConfigProcessor.h index 5a942e73bdb..7a4102140d9 100644 --- a/src/Common/Config/ConfigProcessor.h +++ b/src/Common/Config/ConfigProcessor.h @@ -97,7 +97,7 @@ public: /// If preprocessed_dir is empty - calculate from loaded_config.path + /preprocessed_configs/ void savePreprocessedConfig(const LoadedConfig & loaded_config, std::string preprocessed_dir); - /// Set path of main config.xml. It will be cutted from all configs placed to preprocessed_configs/ + /// Set path of main config.xml. It will be cut from all configs placed to preprocessed_configs/ static void setConfigPath(const std::string & config_path); public: diff --git a/src/Common/Exception.h b/src/Common/Exception.h index c26f3f41ab4..a6190c7ca24 100644 --- a/src/Common/Exception.h +++ b/src/Common/Exception.h @@ -98,7 +98,7 @@ private: /// Special class of exceptions, used mostly in ParallelParsingInputFormat for -/// more convinient calculation of problem line number. +/// more convenient calculation of problem line number. class ParsingException : public Exception { public: diff --git a/src/Common/HashTable/HashTable.h b/src/Common/HashTable/HashTable.h index 2d5580bf709..15fa09490e6 100644 --- a/src/Common/HashTable/HashTable.h +++ b/src/Common/HashTable/HashTable.h @@ -1008,7 +1008,7 @@ public: * then deleting a erased_key_position will break search for it, so we need to move next_element * to erased_key_position. Now we have empty place at next_element, so we apply the identical * procedure for it. - * If an empty element is encoutered then means that there is no more next elements for which we can + * If an empty element is encountered then means that there is no more next elements for which we can * break the search so we can exit. */ diff --git a/src/Core/QueryProcessingStage.h b/src/Core/QueryProcessingStage.h index 360cf70ebdd..01e7e12ab1e 100644 --- a/src/Core/QueryProcessingStage.h +++ b/src/Core/QueryProcessingStage.h @@ -44,7 +44,7 @@ namespace QueryProcessingStage : "Unknown stage"; } - /// This methid is used for the program options, + /// This method is used for the program options, /// hence it accept under_score notation for stage: /// - complete /// - fetch_columns diff --git a/src/Core/Types.h b/src/Core/Types.h index 0d578e17517..cc8a4d7269a 100644 --- a/src/Core/Types.h +++ b/src/Core/Types.h @@ -185,7 +185,7 @@ using Decimal64 = Decimal; using Decimal128 = Decimal; using Decimal256 = Decimal; -// Distinguishable type to allow function resultion/deduction based on value type, +// Distinguishable type to allow function resolution/deduction based on value type, // but also relatively easy to convert to/from Decimal64. class DateTime64 : public Decimal64 { diff --git a/src/DataTypes/DataTypeMap.cpp b/src/DataTypes/DataTypeMap.cpp index 2047928721a..b207702d9b7 100644 --- a/src/DataTypes/DataTypeMap.cpp +++ b/src/DataTypes/DataTypeMap.cpp @@ -204,7 +204,7 @@ void DataTypeMap::serializeText(const IColumn & column, size_t row_num, WriteBuf void DataTypeMap::deserializeText(IColumn & column, ReadBuffer & istr, const FormatSettings & settings) const { - // need_safe_get_int_key is set for Interger to prevent to readIntTextUnsafe + // need_safe_get_int_key is set for Integer to prevent to readIntTextUnsafe bool need_safe_get_int_key = isInteger(key_type); deserializeTextImpl(column, istr, need_safe_get_int_key, @@ -226,7 +226,7 @@ void DataTypeMap::serializeTextJSON(const IColumn & column, size_t row_num, Writ void DataTypeMap::deserializeTextJSON(IColumn & column, ReadBuffer & istr, const FormatSettings & settings) const { - // need_safe_get_int_key is set for Interger to prevent to readIntTextUnsafe + // need_safe_get_int_key is set for Integer to prevent to readIntTextUnsafe bool need_safe_get_int_key = isInteger(key_type); deserializeTextImpl(column, istr, need_safe_get_int_key, diff --git a/src/DataTypes/IDataType.h b/src/DataTypes/IDataType.h index 060572ee997..b51722ed96d 100644 --- a/src/DataTypes/IDataType.h +++ b/src/DataTypes/IDataType.h @@ -67,7 +67,7 @@ public: * If the data type require single stream (it's true for most of data types), the stream will have empty path. * Otherwise, the path can have components like "array elements", "array sizes", etc. * - * For multidimensional arrays, path can have arbiraty length. + * For multidimensional arrays, path can have arbitrary length. * As an example, for 2-dimensional arrays of numbers we have at least three streams: * - array sizes; (sizes of top level arrays) * - array elements / array sizes; (sizes of second level (nested) arrays) diff --git a/src/Databases/DatabaseOnDisk.cpp b/src/Databases/DatabaseOnDisk.cpp index 2a8276ec6db..fb2d10a4fe7 100644 --- a/src/Databases/DatabaseOnDisk.cpp +++ b/src/Databases/DatabaseOnDisk.cpp @@ -229,7 +229,7 @@ void DatabaseOnDisk::removeDetachedPermanentlyFlag(const String & table_name, co } catch (Exception & e) { - e.addMessage("while trying to remove permanenty detached flag. Table {}.{} may still be marked as permanently detached, and will not be reattached during server restart.", backQuote(getDatabaseName()), backQuote(table_name)); + e.addMessage("while trying to remove permanently detached flag. Table {}.{} may still be marked as permanently detached, and will not be reattached during server restart.", backQuote(getDatabaseName()), backQuote(table_name)); throw; } } @@ -264,7 +264,7 @@ void DatabaseOnDisk::detachTablePermanently(const String & table_name) } catch (Exception & e) { - e.addMessage("while trying to set permanenty detached flag. Table {}.{} may be reattached during server restart.", backQuote(getDatabaseName()), backQuote(table_name)); + e.addMessage("while trying to set permanently detached flag. Table {}.{} may be reattached during server restart.", backQuote(getDatabaseName()), backQuote(table_name)); throw; } } diff --git a/src/Dictionaries/CacheDictionary.inc.h b/src/Dictionaries/CacheDictionary.inc.h index d724453f385..803b3b2566f 100644 --- a/src/Dictionaries/CacheDictionary.inc.h +++ b/src/Dictionaries/CacheDictionary.inc.h @@ -147,7 +147,7 @@ void CacheDictionary::getItemsNumberImpl( tryPushToUpdateQueueOrThrow(update_unit_ptr); waitForCurrentUpdateFinish(update_unit_ptr); - /// Add updated keys to asnwer. + /// Add updated keys to answer. const size_t attribute_index = getAttributeIndex(attribute.name); diff --git a/src/Functions/ExtractString.h b/src/Functions/ExtractString.h index c4251f8c4a6..8313f583025 100644 --- a/src/Functions/ExtractString.h +++ b/src/Functions/ExtractString.h @@ -61,7 +61,7 @@ struct ExtractStringImpl // read a ASCII word static ALWAYS_INLINE inline size_t readOneASCIIWord(PaddedPODArray & word_buf, const char *& pos, const char * end) { - // jump seperators + // jump separators while (pos < end && !isAlphaNumericASCII(*pos)) ++pos; @@ -93,7 +93,7 @@ struct ExtractStringImpl // read one UTF8 word from pos to word static ALWAYS_INLINE inline size_t readOneUTF8Word(PaddedPODArray & word_buf, const char *& pos, const char * end) { - // jump UTF8 seperator + // jump UTF8 separator while (pos < end && isUTF8Sep(*pos)) ++pos; word_buf.clear(); @@ -112,7 +112,7 @@ private: ((cont[Offset + I] = std::tolower(cont[Offset + I])), ...); } - // we use ASCII non-alphanum character as UTF8 seperator + // we use ASCII non-alphanum character as UTF8 separator static ALWAYS_INLINE inline bool isUTF8Sep(const UInt8 c) { return c < 128 && !isAlphaNumericASCII(c); } // read one UTF8 character and return it diff --git a/src/Functions/FunctionsStringHash.cpp b/src/Functions/FunctionsStringHash.cpp index d57be67ef7f..7062a47fa22 100644 --- a/src/Functions/FunctionsStringHash.cpp +++ b/src/Functions/FunctionsStringHash.cpp @@ -151,7 +151,7 @@ template ; - // we made an assumption that the size of one word cann't exceed 128, which may not true + // we made an assumption that the size of one word can't exceed 128, which may not true // if some word's size exceed 128, it would be cut up to several word static constexpr size_t max_string_size = 1u << 15; static constexpr size_t simultaneously_codepoints_num = StrOp::buffer_size; @@ -203,7 +203,7 @@ struct SimhashImpl return res_bit.to_ullong(); } - // Simhash word shingle calculate funtion: String -> UInt64 + // Simhash word shingle calculate function: String -> UInt64 // this function extracting n word shingle from input string, and maintain a 64-dimensions vector as well // for each word shingle, calculate a 64 bit hash value, and update the vector according the hash value // finally return a 64 bit value(UInt64), i'th bit is 1 means vector[i] > 0, otherwise, vector[i] < 0 @@ -211,8 +211,8 @@ struct SimhashImpl // word shingle hash value calculate: // 1. at the first, extracts N word shingles and calculate N hash values, store into an array, use this N hash values // to calculate the first word shingle hash value - // 2. next, we extrac one word each time, and calculate a new hash value of the new word,then use the latest N hash - // values to caculate the next word shingle hash value + // 2. next, we extract one word each time, and calculate a new hash value of the new word,then use the latest N hash + // values to calculate the next word shingle hash value static ALWAYS_INLINE inline UInt64 wordShinglesCalculateHashValue( const char * data, size_t size, @@ -254,12 +254,12 @@ struct SimhashImpl // for example, N = 5, array |a0|a1|a2|a3|a4|, now , a0 is the oldest location, // so we need to store new word hash into location of a0, then ,this array become // |a5|a1|a2|a3|a4|, next time, a1 become the oldest location, we need to store new - // word hash value into locaion of a1, then array become |a5|a6|a2|a3|a4| + // word hash value into location of a1, then array become |a5|a6|a2|a3|a4| nword_hashes[offset] = Hash::hashSum(word_buf.data(), word_buf.size()); offset = (offset + 1) % N; // according to the word hash storation way, in order to not lose the word shingle's // sequence information, when calculation word shingle hash value, we need provide the offset - // inforation, which is the offset of the first word's hash value of the word shingle + // information, which is the offset of the first word's hash value of the word shingle hash_value = hash_functor(nword_hashes, N, offset); std::bitset<64> bits(hash_value); for (size_t i = 0; i < 64; ++i) diff --git a/src/Functions/FunctionsStringSearch.h b/src/Functions/FunctionsStringSearch.h index 9e7d608aec6..75579b28fd3 100644 --- a/src/Functions/FunctionsStringSearch.h +++ b/src/Functions/FunctionsStringSearch.h @@ -29,7 +29,7 @@ namespace DB * multiMatchAnyIndex(haystack, [pattern_1, pattern_2, ..., pattern_n]) -- search by re2 regular expressions pattern_i; Returns index of any match or zero if none; * multiMatchAllIndices(haystack, [pattern_1, pattern_2, ..., pattern_n]) -- search by re2 regular expressions pattern_i; Returns an array of matched indices in any order; * - * countSubstrings(haystack, needle) -- count number of occurences of needle in haystack. + * countSubstrings(haystack, needle) -- count number of occurrences of needle in haystack. * countSubstringsCaseInsensitive(haystack, needle) * * Applies regexp re2 and pulls: diff --git a/src/Functions/abtesting.cpp b/src/Functions/abtesting.cpp index 1af929c8fb9..7bed2f4a2b9 100644 --- a/src/Functions/abtesting.cpp +++ b/src/Functions/abtesting.cpp @@ -236,7 +236,7 @@ public: if (const ColumnConst * col_higher_is_better = checkAndGetColumnConst(arguments[1].column.get())) higher_is_better = col_higher_is_better->getBool(0); else - throw Exception("Second argument for function " + getName() + " must be Constatnt boolean", ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT); + throw Exception("Second argument for function " + getName() + " must be Constant boolean", ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT); if (const ColumnConst * col_const_arr = checkAndGetColumnConst(arguments[2].column.get())) { diff --git a/src/Functions/array/arrayElement.cpp b/src/Functions/array/arrayElement.cpp index 310b6b5b450..88166f04e0e 100644 --- a/src/Functions/array/arrayElement.cpp +++ b/src/Functions/array/arrayElement.cpp @@ -86,7 +86,7 @@ private: ColumnPtr executeTuple(const ColumnsWithTypeAndName & arguments, size_t input_rows_count) const; /** For a map the function finds the matched value for a key. - * Currently implemented just as linear seach in array. + * Currently implemented just as linear search in array. * However, optimizations are possible. */ ColumnPtr executeMap(const ColumnsWithTypeAndName & arguments, const DataTypePtr & result_type, size_t input_rows_count) const; diff --git a/src/IO/WriteBufferFromVector.h b/src/IO/WriteBufferFromVector.h index ad0f8bd17a8..2a9810f3461 100644 --- a/src/IO/WriteBufferFromVector.h +++ b/src/IO/WriteBufferFromVector.h @@ -15,7 +15,7 @@ namespace ErrorCodes /** Writes data to existing std::vector or similar type. When not enough space, it doubles vector size. * - * In destructor, vector is cutted to the size of written data. + * In destructor, vector is cut to the size of written data. * You can call 'finalize' to resize earlier. * * The vector should live until this object is destroyed or until the 'finish' method is called. diff --git a/src/Interpreters/InterpreterInsertQuery.cpp b/src/Interpreters/InterpreterInsertQuery.cpp index 9ac936b5489..2a193dc7249 100644 --- a/src/Interpreters/InterpreterInsertQuery.cpp +++ b/src/Interpreters/InterpreterInsertQuery.cpp @@ -268,7 +268,7 @@ BlockIO InterpreterInsertQuery::execute() const auto & selects = select_query.list_of_selects->children; const auto & union_modes = select_query.list_of_modes; - /// ASTSelectWithUnionQuery is not normalized now, so it may pass some querys which can be Trivial select querys + /// ASTSelectWithUnionQuery is not normalized now, so it may pass some queries which can be Trivial select queries is_trivial_insert_select = std::all_of( union_modes.begin(), diff --git a/src/Interpreters/InterpreterOptimizeQuery.cpp b/src/Interpreters/InterpreterOptimizeQuery.cpp index c382b86afd6..cda8471c32e 100644 --- a/src/Interpreters/InterpreterOptimizeQuery.cpp +++ b/src/Interpreters/InterpreterOptimizeQuery.cpp @@ -57,7 +57,7 @@ BlockIO InterpreterOptimizeQuery::execute() { // Deduplication is performed only for adjacent rows in a block, // and all rows in block are in the sorting key order within a single partition, - // hence deduplication always implicitly takes sorting keys and parition keys in account. + // hence deduplication always implicitly takes sorting keys and partition keys in account. // So we just explicitly state that limitation in order to avoid confusion. if (std::find(column_names.begin(), column_names.end(), required_col) == column_names.end()) throw Exception(ErrorCodes::THERE_IS_NO_COLUMN, diff --git a/src/Interpreters/TreeRewriter.cpp b/src/Interpreters/TreeRewriter.cpp index 9816d1a3940..fc3ad79f217 100644 --- a/src/Interpreters/TreeRewriter.cpp +++ b/src/Interpreters/TreeRewriter.cpp @@ -132,7 +132,7 @@ struct CustomizeAggregateFunctionsSuffixData } }; -// Used to rewrite aggregate functions with -OrNull suffix in some cases, such as sumIfOrNull, we shoule rewrite to sumOrNullIf +// Used to rewrite aggregate functions with -OrNull suffix in some cases, such as sumIfOrNull, we should rewrite to sumOrNullIf struct CustomizeAggregateFunctionsMoveSuffixData { using TypeToVisit = ASTFunction; diff --git a/src/Parsers/New/AST/JoinExpr.cpp b/src/Parsers/New/AST/JoinExpr.cpp index a5effedc242..acbeae86897 100644 --- a/src/Parsers/New/AST/JoinExpr.cpp +++ b/src/Parsers/New/AST/JoinExpr.cpp @@ -57,7 +57,7 @@ JoinExpr::JoinExpr(JoinExpr::ExprType type, JoinExpr::JoinOpType op, JoinExpr::J ASTPtr JoinExpr::convertToOld() const { - /** The sole convertable chain of Join's may look like: + /** The sole convertible chain of Join's may look like: * * … FROM table1 JOIN table2 ON SMTH JOIN table3 ON SMTH JOIN … * diff --git a/src/Parsers/New/AST/README.md b/src/Parsers/New/AST/README.md index 51e587f296c..4216a8dcfdc 100644 --- a/src/Parsers/New/AST/README.md +++ b/src/Parsers/New/AST/README.md @@ -13,7 +13,7 @@ Basic principles in code **predetermined order** and with **predetermined type**: some elements may be `nullptr` to preserve positions of other elements. - The order may be defined as a position in vector from the start, the last element, and some pattern of variable number of elements in between. It's convenient to define `enum ChildIndex : Uint8 {…}` with index numbers for each class. -- If there is more than one variable pack of elements or the order can't be determenistic, then wrap elements into the lists and store the +- If there is more than one variable pack of elements or the order can't be deterministic, then wrap elements into the lists and store the multi-level structure (see `ColumnExpr::ExprType::FUNCTION` for example). - Don't do multi-level structure just for nothing or to mimic the parse tree: the less is depth the better. - The whole grammar separates expressions for databases, tables and columns. That way we already assess the semantics on the parser level. diff --git a/src/Parsers/ParserOptimizeQuery.cpp b/src/Parsers/ParserOptimizeQuery.cpp index 629b88adb88..441cec1465e 100644 --- a/src/Parsers/ParserOptimizeQuery.cpp +++ b/src/Parsers/ParserOptimizeQuery.cpp @@ -14,7 +14,7 @@ bool ParserOptimizeQueryColumnsSpecification::parseImpl(Pos & pos, ASTPtr & node { // Do not allow APPLY and REPLACE transformers. // Since we use Columns Transformers only to get list of columns, - // ad we can't actuall modify content of the columns for deduplication. + // we can't actually modify content of the columns for deduplication. const auto allowed_transformers = ParserColumnsTransformers::ColumnTransformers{ParserColumnsTransformers::ColumnTransformer::EXCEPT}; return ParserColumnsMatcher(allowed_transformers).parse(pos, node, expected) diff --git a/src/Server/grpc_protos/clickhouse_grpc.proto b/src/Server/grpc_protos/clickhouse_grpc.proto index c80a8bf1d40..2f25973297c 100644 --- a/src/Server/grpc_protos/clickhouse_grpc.proto +++ b/src/Server/grpc_protos/clickhouse_grpc.proto @@ -21,19 +21,19 @@ message NameAndType { string type = 2; } -// Desribes an external table - a table which will exists only while a query is executing. +// Describes an external table - a table which will exists only while a query is executing. message ExternalTable { // Name of the table. If omitted, "_data" is used. string name = 1; - + // Columns of the table. Types are required, names can be omitted. If the names are omitted, "_1", "_2", ... is used. repeated NameAndType columns = 2; // Data to insert to the external table. // If a method with streaming input (i.e. ExecuteQueryWithStreamInput() or ExecuteQueryWithStreamIO()) is used, - // then data for insertion to the same external table can be splitted between multiple QueryInfos. + // then data for insertion to the same external table can be split between multiple QueryInfos. string data = 3; - + // Format of the data to insert to the external table. string format = 4; @@ -57,7 +57,7 @@ message QueryInfo { // Delimiter for input_data, inserted between input_data from adjacent QueryInfos. string input_data_delimiter = 6; - + // Default output format. If not specified, 'TabSeparated' is used. string output_format = 7; @@ -71,7 +71,7 @@ message QueryInfo { string session_id = 12; bool session_check = 13; uint32 session_timeout = 14; - + // Set `cancel` to true to stop executing the query. bool cancel = 15; diff --git a/src/Storages/MergeTree/MergeTreeRangeReader.cpp b/src/Storages/MergeTree/MergeTreeRangeReader.cpp index e22c6bb3d0c..c13146bd35c 100644 --- a/src/Storages/MergeTree/MergeTreeRangeReader.cpp +++ b/src/Storages/MergeTree/MergeTreeRangeReader.cpp @@ -637,7 +637,7 @@ MergeTreeRangeReader::ReadResult MergeTreeRangeReader::read(size_t max_rows, Mar if (!columns.empty()) { - /// If some columns absent in part, then evaulate default values + /// If some columns absent in part, then evaluate default values if (should_evaluate_missing_defaults) { auto block = prev_reader->sample_block.cloneWithColumns(read_result.columns); @@ -681,7 +681,7 @@ MergeTreeRangeReader::ReadResult MergeTreeRangeReader::read(size_t max_rows, Mar merge_tree_reader->fillMissingColumns(read_result.columns, should_evaluate_missing_defaults, read_result.num_rows); - /// If some columns absent in part, then evaulate default values + /// If some columns absent in part, then evaluate default values if (should_evaluate_missing_defaults) merge_tree_reader->evaluateMissingDefaults({}, read_result.columns); diff --git a/src/Storages/MergeTree/RPNBuilder.h b/src/Storages/MergeTree/RPNBuilder.h index ed25252642b..292a120d28a 100644 --- a/src/Storages/MergeTree/RPNBuilder.h +++ b/src/Storages/MergeTree/RPNBuilder.h @@ -31,7 +31,7 @@ public: */ block_with_constants = KeyCondition::getBlockWithConstants(query_info.query, query_info.syntax_analyzer_result, context); - /// Trasform WHERE section to Reverse Polish notation + /// Transform WHERE section to Reverse Polish notation const ASTSelectQuery & select = typeid_cast(*query_info.query); if (select.where()) { diff --git a/src/Storages/MergeTree/tests/gtest_ReplicatedMergeTreeLogEntry.cpp b/src/Storages/MergeTree/tests/gtest_ReplicatedMergeTreeLogEntry.cpp index 98e70bd6147..03f36d866bb 100644 --- a/src/Storages/MergeTree/tests/gtest_ReplicatedMergeTreeLogEntry.cpp +++ b/src/Storages/MergeTree/tests/gtest_ReplicatedMergeTreeLogEntry.cpp @@ -213,7 +213,7 @@ TEST_P(ReplicatedMergeTreeLogEntryDataTest, transcode) // Enabling this warning would ruin test brievity without adding anything else in return, // since most of the fields have default constructors or be will be zero-initialized as by standard, -// so values are predicatable and stable accross runs. +// so values are predicatable and stable across runs. #pragma GCC diagnostic push #pragma GCC diagnostic ignored "-Wmissing-field-initializers" @@ -301,7 +301,7 @@ INSTANTIATE_TEST_SUITE_P(Merge, ReplicatedMergeTreeLogEntryDataTest, // This is just an example of how to set all fields. Can't be used as is since depending on type, // only some fields are serialized/deserialized, and even if everything works perfectly, -// some fileds in deserialized object would be unset (hence differ from expected). +// some fields in deserialized object would be unset (hence differ from expected). // INSTANTIATE_TEST_SUITE_P(Full, ReplicatedMergeTreeLogEntryDataTest, // ::testing::ValuesIn(std::initializer_list{ // { diff --git a/src/Storages/RocksDB/EmbeddedRocksDBBlockInputStream.cpp b/src/Storages/RocksDB/EmbeddedRocksDBBlockInputStream.cpp index 49b91aa7477..35c41cabd8b 100644 --- a/src/Storages/RocksDB/EmbeddedRocksDBBlockInputStream.cpp +++ b/src/Storages/RocksDB/EmbeddedRocksDBBlockInputStream.cpp @@ -56,7 +56,7 @@ Block EmbeddedRocksDBBlockInputStream::readImpl() finished = !iterator->Valid(); if (!iterator->status().ok()) { - throw Exception("Engine " + getName() + " got error while seeking key value datas: " + iterator->status().ToString(), + throw Exception("Engine " + getName() + " got error while seeking key value data: " + iterator->status().ToString(), ErrorCodes::ROCKSDB_ERROR); } return sample_block.cloneWithColumns(std::move(columns)); diff --git a/src/Storages/StorageInMemoryMetadata.h b/src/Storages/StorageInMemoryMetadata.h index 3656edf71f4..4c5edf31efe 100644 --- a/src/Storages/StorageInMemoryMetadata.h +++ b/src/Storages/StorageInMemoryMetadata.h @@ -61,13 +61,13 @@ struct StorageInMemoryMetadata /// Sets constraints void setConstraints(ConstraintsDescription constraints_); - /// Set partition key for storage (methods bellow, are just wrappers for this struct). + /// Set partition key for storage (methods below, are just wrappers for this struct). void setPartitionKey(const KeyDescription & partition_key_); - /// Set sorting key for storage (methods bellow, are just wrappers for this struct). + /// Set sorting key for storage (methods below, are just wrappers for this struct). void setSortingKey(const KeyDescription & sorting_key_); - /// Set primary key for storage (methods bellow, are just wrappers for this struct). + /// Set primary key for storage (methods below, are just wrappers for this struct). void setPrimaryKey(const KeyDescription & primary_key_); - /// Set sampling key for storage (methods bellow, are just wrappers for this struct). + /// Set sampling key for storage (methods below, are just wrappers for this struct). void setSamplingKey(const KeyDescription & sampling_key_); /// Set common table TTLs diff --git a/utils/check-style/check-typos b/utils/check-style/check-typos index 14deb039059..b5858968841 100755 --- a/utils/check-style/check-typos +++ b/utils/check-style/check-typos @@ -3,12 +3,11 @@ # Check for typos in code. ROOT_PATH=$(git rev-parse --show-toplevel) -CURDIR=$(dirname "${BASH_SOURCE[0]}") codespell \ - --skip '*generated*,*gperf*,*.bin,*.mrk*,*.idx,checksums.txt,*.dat,*.pyc,*.kate-swp' \ - --ignore-words "${CURDIR}/codespell-ignore-words.list" \ - --exclude-file "${CURDIR}/codespell-ignore-lines.list" \ + --skip '*generated*,*gperf*,*.bin,*.mrk*,*.idx,checksums.txt,*.dat,*.pyc,*.kate-swp,*obfuscateQueries.cpp' \ + --ignore-words "${ROOT_PATH}/utils/check-style/codespell-ignore-words.list" \ + --exclude-file "${ROOT_PATH}/utils/check-style/codespell-ignore-lines.list" \ --quiet-level 2 \ "$ROOT_PATH"/{src,base,programs,utils} \ $@ | grep -P '.' \ diff --git a/utils/check-style/check-whitespaces b/utils/check-style/check-whitespaces new file mode 100755 index 00000000000..1aa3fd8cf6d --- /dev/null +++ b/utils/check-style/check-whitespaces @@ -0,0 +1,9 @@ +#!/usr/bin/env bash + +ROOT_PATH=$(git rev-parse --show-toplevel) +EXCLUDE_DIRS='build/|integration/|widechar_width/|glibc-compatibility/|memcpy/|consistent-hashing/|Parsers/New' + +# Double whitespaces +find $ROOT_PATH/{src,base,programs,utils} -name '*.h' -or -name '*.cpp' 2>/dev/null | + grep -vP $EXCLUDE_DIRS | + while read i; do $ROOT_PATH/utils/check-style/double-whitespaces.pl < $i || echo -e "^ File $i contains double whitespaces\n"; done \ No newline at end of file diff --git a/utils/check-style/codespell-ignore-words.list b/utils/check-style/codespell-ignore-words.list index 4433e9917e3..200b55d112d 100644 --- a/utils/check-style/codespell-ignore-words.list +++ b/utils/check-style/codespell-ignore-words.list @@ -5,3 +5,8 @@ parsering nd ect pullrequest +pullrequests +thenn +ths +offsett +numer