Merge pull request #4122 from maiha/dbms-fix-misspells

dbms: Fixed misspells in comments
This commit is contained in:
alexey-milovidov 2019-01-22 23:47:57 +03:00 committed by GitHub
commit cd874be05a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
55 changed files with 71 additions and 71 deletions

View File

@ -860,7 +860,7 @@ private:
}
/// Process the query that doesn't require transfering data blocks to the server.
/// Process the query that doesn't require transferring data blocks to the server.
void processOrdinaryQuery()
{
connection->sendQuery(query, query_id, QueryProcessingStage::Complete, &context.getSettingsRef(), nullptr, true);
@ -869,7 +869,7 @@ private:
}
/// Process the query that requires transfering data blocks to the server.
/// Process the query that requires transferring data blocks to the server.
void processInsertQuery()
{
/// Send part of query without data, because data will be sent separately.
@ -1136,7 +1136,7 @@ private:
}
/// Process Log packets, exit when recieve Exception or EndOfStream
/// Process Log packets, exit when receive Exception or EndOfStream
bool receiveEndOfQuery()
{
while (true)

View File

@ -137,7 +137,7 @@ try
static KillingErrorHandler error_handler;
Poco::ErrorHandler::set(&error_handler);
/// Don't initilaize DateLUT
/// Don't initialize DateLUT
registerFunctions();
registerAggregateFunctions();

View File

@ -51,7 +51,7 @@ It is designed to retain the following properties of data:
- probability distributions of length of strings;
- probability of zero values of numbers; empty strings and arrays, NULLs;
- data compression ratio when compressed with LZ77 and entropy family of codecs;
- continuouty (magnitude of difference) of time values across table; continuouty of floating point values.
- continuity (magnitude of difference) of time values across table; continuity of floating point values.
- date component of DateTime values;
- UTF-8 validity of string values;
- string values continue to look somewhat natural.
@ -246,7 +246,7 @@ Float transformFloatMantissa(Float x, UInt64 seed)
/// Transform difference from previous number by applying pseudorandom permutation to mantissa part of it.
/// It allows to retain some continuouty property of source data.
/// It allows to retain some continuity property of source data.
template <typename Float>
class FloatModel : public IModel
{

View File

@ -22,7 +22,7 @@ std::string validateODBCConnectionString(const std::string & connection_string)
/// Connection string is a list of name, value pairs.
/// name and value are separated by '='.
/// names are case insensitive.
/// name=value pairs are sepated by ';'.
/// name=value pairs are separated by ';'.
/// ASCII whitespace characters are skipped before and after delimiters.
/// value may be optionally enclosed by {}
/// in enclosed value, } is escaped as }}.

View File

@ -13,9 +13,9 @@
<!-- How to choose between replicas during distributed query processing.
random - choose random replica from set of replicas with minimum number of errors
nearest_hostname - from set of replicas with minimum number of errors, choose replica
with minumum number of different symbols between replica's hostname and local hostname
with minimum number of different symbols between replica's hostname and local hostname
(Hamming distance).
in_order - first live replica is choosen in specified order.
in_order - first live replica is chosen in specified order.
-->
<load_balancing>random</load_balancing>
</default>

View File

@ -109,7 +109,7 @@ struct AggreagteFunctionGroupUniqArrayGenericData
};
/** Template parameter with true value should be used for columns that store their elements in memory continuously.
* For such columns groupUniqArray() can be implemented more efficently (especially for small numeric arrays).
* For such columns groupUniqArray() can be implemented more efficiently (especially for small numeric arrays).
*/
template <bool is_plain_column = false>
class AggreagteFunctionGroupUniqArrayGeneric

View File

@ -123,7 +123,7 @@ struct AggregateFunctionTopKGenericData
};
/** Template parameter with true value should be used for columns that store their elements in memory continuously.
* For such columns topK() can be implemented more efficently (especially for small numeric arrays).
* For such columns topK() can be implemented more efficiently (especially for small numeric arrays).
*/
template <bool is_plain_column = false>
class AggregateFunctionTopKGeneric : public IAggregateFunctionDataHelper<AggregateFunctionTopKGenericData, AggregateFunctionTopKGeneric<is_plain_column>>

View File

@ -12,7 +12,7 @@ namespace ErrorCodes
extern const int NOT_IMPLEMENTED;
}
/** Calculates quantile by counting number of occurences for each value in a hash map.
/** Calculates quantile by counting number of occurrences for each value in a hash map.
*
* It use O(distinct(N)) memory. Can be naturally applied for values with weight.
* In case of many identical values, it can be more efficient than QuantileExact even when weight is not used.

View File

@ -43,7 +43,7 @@ public:
virtual const char * getFamilyName() const = 0;
/** If column isn't constant, returns nullptr (or itself).
* If column is constant, transforms constant to full column (if column type allows such tranform) and return it.
* If column is constant, transforms constant to full column (if column type allows such transform) and return it.
*/
virtual Ptr convertToFullColumnIfConst() const { return getPtr(); }
@ -149,7 +149,7 @@ public:
virtual void insertDefault() = 0;
/** Removes last n elements.
* Is used to support exeption-safety of several operations.
* Is used to support exception-safety of several operations.
* For example, sometimes insertion should be reverted if we catch an exception during operation processing.
* If column has less than n elements or n == 0 - undefined behavior.
*/
@ -234,8 +234,8 @@ public:
virtual void gather(ColumnGathererStream & gatherer_stream) = 0;
/** Computes minimum and maximum element of the column.
* In addition to numeric types, the funtion is completely implemented for Date and DateTime.
* For strings and arrays function should retrurn default value.
* In addition to numeric types, the function is completely implemented for Date and DateTime.
* For strings and arrays function should return default value.
* (except for constant columns; they should return value of the constant).
* If column is empty function should return default value.
*/

View File

@ -64,7 +64,7 @@ namespace DB
* During insertion, each key is locked - to avoid parallel initialization of regions for same key.
*
* On insertion, we search for free region of at least requested size.
* If nothing was found, we evict oldest unused region; if not enogh size, we evict it neighbours; and try again.
* If nothing was found, we evict oldest unused region; if not enough size, we evict it neighbours; and try again.
*
* Metadata is allocated by usual allocator and its memory usage is not accounted.
*

View File

@ -23,7 +23,7 @@ using namespace Poco::XML;
namespace DB
{
/// For cutting prerpocessed path to this base
/// For cutting preprocessed path to this base
static std::string main_config_path;
/// Extracts from a string the first encountered number consisting of at least two digits.

View File

@ -12,7 +12,7 @@
* - in typical implementation of standard library, hash function for integers is trivial and just use lower bits;
* - traffic is non-uniformly distributed across a day;
* - we are using open-addressing linear probing hash tables that are most critical to hash function quality,
* and trivial hash function gives disasterous results.
* and trivial hash function gives disastrous results.
*/
/** Taken from MurmurHash. This is Murmur finalizer.
@ -160,7 +160,7 @@ struct TrivialHash
* NOTE Salting is far from perfect, because it commutes with first steps of calculation.
*
* NOTE As mentioned, this function is slower than intHash64.
* But occasionaly, it is faster, when written in a loop and loop is vectorized.
* But occasionally, it is faster, when written in a loop and loop is vectorized.
*/
template <DB::UInt64 salt>
inline DB::UInt32 intHash32(DB::UInt64 key)

View File

@ -165,7 +165,7 @@ void OptimizedRegularExpressionImpl<thread_safe>::analyze(
++pos;
break;
/// Quantifiers that allow a zero number of occurences.
/// Quantifiers that allow a zero number of occurrences.
case '{':
in_curly_braces = true;
[[fallthrough]];

View File

@ -40,7 +40,7 @@ struct SpaceSavingArena
/*
* Specialized storage for StringRef with a freelist arena.
* Keys of this type that are retained on insertion must be serialised into local storage,
* Keys of this type that are retained on insertion must be serialized into local storage,
* otherwise the reference would be invalid after the processed block is released.
*/
template <>

View File

@ -41,7 +41,7 @@
* - extremely creepy code for implementation of "chroot" feature.
*
* As of 2018, there are no active maintainers of libzookeeper:
* - bugs in JIRA are fixed only occasionaly with ad-hoc patches by library users.
* - bugs in JIRA are fixed only occasionally with ad-hoc patches by library users.
*
* libzookeeper is a classical example of bad code written in C.
*

View File

@ -5,7 +5,7 @@
/// A tool for reproducing https://issues.apache.org/jira/browse/ZOOKEEPER-706
/// Original libzookeeper can't reconnect the session if the length of SET_WATCHES message
/// exceeeds jute.maxbuffer (0xfffff by default).
/// exceeds jute.maxbuffer (0xfffff by default).
/// This happens when the number of watches exceeds ~29000.
///
/// Session reconnect can be caused by forbidding packets to the current zookeeper server, e.g.

View File

@ -51,7 +51,7 @@ using MergedRowSources = PODArray<RowSourcePart>;
/** Gather single stream from multiple streams according to streams mask.
* Stream mask maps row number to index of source stream.
* Streams should conatin exactly one column.
* Streams should contain exactly one column.
*/
class ColumnGathererStream : public IProfilingBlockInputStream
{

View File

@ -85,7 +85,7 @@ Block FinishSortingBlockInputStream::readImpl()
{
Block block = children.back()->read();
/// End of input stream, but we can`t return immediatly, we need to merge already read blocks.
/// End of input stream, but we can`t return immediately, we need to merge already read blocks.
/// Check it later, when get end of stream from impl.
if (!block)
{
@ -102,7 +102,7 @@ Block FinishSortingBlockInputStream::readImpl()
if (size == 0)
continue;
/// We need to sort each block separatly before merging.
/// We need to sort each block separately before merging.
sortBlock(block, description_to_sort);
removeConstantsFromBlock(block);

View File

@ -17,7 +17,7 @@ namespace DB
/** Intended for implementation of "rollup" - aggregation (rounding) of older data
* for a table with Graphite data (Graphite is the system for time series monitoring).
*
* Table with graphite data has at least the folowing columns (accurate to the name):
* Table with graphite data has at least the following columns (accurate to the name):
* Path, Time, Value, Version
*
* Path - name of metric (sensor);

View File

@ -322,7 +322,7 @@ void registerDataTypeString(DataTypeFactory & factory)
factory.registerSimpleDataType("String", creator);
/// These synonims are added for compatibility.
/// These synonyms are added for compatibility.
factory.registerAlias("CHAR", "String", DataTypeFactory::CaseInsensitive);
factory.registerAlias("VARCHAR", "String", DataTypeFactory::CaseInsensitive);

View File

@ -20,7 +20,7 @@ void registerDataTypeNumbers(DataTypeFactory & factory)
factory.registerSimpleDataType("Float32", [] { return DataTypePtr(std::make_shared<DataTypeFloat32>()); });
factory.registerSimpleDataType("Float64", [] { return DataTypePtr(std::make_shared<DataTypeFloat64>()); });
/// These synonims are added for compatibility.
/// These synonyms are added for compatibility.
factory.registerAlias("TINYINT", "Int8", DataTypeFactory::CaseInsensitive);
factory.registerAlias("SMALLINT", "Int16", DataTypeFactory::CaseInsensitive);

View File

@ -188,7 +188,7 @@ template <typename A> struct ToInteger
// CLICKHOUSE-29. The same depth, different signs
// NOTE: This case is applied for 64-bit integers only (for backward compability), but could be used for any-bit integers
// NOTE: This case is applied for 64-bit integers only (for backward compatibility), but could be used for any-bit integers
template <typename A, typename B>
constexpr bool LeastGreatestSpecialCase =
std::is_integral_v<A> && std::is_integral_v<B>

View File

@ -11,7 +11,7 @@
#include <Common/config.h>
/** More efficient implementations of mathematical functions are possible when using a separate library.
* Disabled due to licence compatibility limitations.
* Disabled due to license compatibility limitations.
* To enable: download http://www.agner.org/optimize/vectorclass.zip and unpack to contrib/vectorclass
* Then rebuild with -DENABLE_VECTORCLASS=1
*/

View File

@ -10,7 +10,7 @@
#include <Common/config.h>
/** More efficient implementations of mathematical functions are possible when using a separate library.
* Disabled due to licence compatibility limitations.
* Disabled due to license compatibility limitations.
* To enable: download http://www.agner.org/optimize/vectorclass.zip and unpack to contrib/vectorclass
* Then rebuild with -DENABLE_VECTORCLASS=1
*/

View File

@ -24,7 +24,7 @@ namespace ErrorCodes
*
* Non-cryptographic generators:
*
* rand - linear congruental generator 0 .. 2^32 - 1.
* rand - linear congruential generator 0 .. 2^32 - 1.
* rand64 - combines several rand values to get values from the range 0 .. 2^64 - 1.
*
* randConstant - service function, produces a constant column with a random value.

View File

@ -39,7 +39,7 @@ namespace DB
* replaceRegexpOne(haystack, pattern, replacement) - replaces the pattern with the specified regexp, only the first occurrence.
* replaceRegexpAll(haystack, pattern, replacement) - replaces the pattern with the specified type, all occurrences.
*
* multiPosition(haystack, [pattern_1, pattern_2, ..., pattern_n]) -- find first occurences (positions) of all the const patterns inside haystack
* multiPosition(haystack, [pattern_1, pattern_2, ..., pattern_n]) -- find first occurrences (positions) of all the const patterns inside haystack
* multiPositionUTF8(haystack, [pattern_1, pattern_2, ..., pattern_n])
* multiPositionCaseInsensitive(haystack, [pattern_1, pattern_2, ..., pattern_n])
* multiPositionCaseInsensitiveUTF8(haystack, [pattern_1, pattern_2, ..., pattern_n])

View File

@ -23,7 +23,7 @@ namespace DB
* queryStringAndFragment
*
* Functions, removing parts from URL.
* If URL has nothing like, then it is retured unchanged.
* If URL has nothing like, then it is returned unchanged.
*
* cutWWW
* cutFragment

View File

@ -163,7 +163,7 @@ public:
* Function could be injective with some arguments fixed to some constant values.
* Examples:
* plus(const, x);
* multiply(const, x) where x is an integer and constant is not divisable by two;
* multiply(const, x) where x is an integer and constant is not divisible by two;
* concat(x, 'const');
* concat(x, 'const', y) where const contain at least one non-numeric character;
* concat with FixedString

View File

@ -36,7 +36,7 @@ namespace ErrorCodes
*
* It is implemented in two steps.
* At first step, it creates a pattern of zeros, literal characters, whitespaces, etc.
* and quickly fills resulting charater array (string column) with this pattern.
* and quickly fills resulting character array (string column) with this pattern.
* At second step, it walks across the resulting character array and modifies/replaces specific charaters,
* by calling some functions by pointers and shifting cursor by specified amount.
*

View File

@ -17,7 +17,7 @@ struct MinusImpl
return static_cast<Result>(a) - b;
}
/// Apply operation and check overflow. It's used for Deciamal operations. @returns true if overflowed, false othervise.
/// Apply operation and check overflow. It's used for Deciamal operations. @returns true if overflowed, false otherwise.
template <typename Result = ResultType>
static inline bool apply(A a, B b, Result & c)
{

View File

@ -17,7 +17,7 @@ struct MultiplyImpl
return static_cast<Result>(a) * b;
}
/// Apply operation and check overflow. It's used for Deciamal operations. @returns true if overflowed, false othervise.
/// Apply operation and check overflow. It's used for Deciamal operations. @returns true if overflowed, false otherwise.
template <typename Result = ResultType>
static inline bool apply(A a, B b, Result & c)
{

View File

@ -18,7 +18,7 @@ struct PlusImpl
return static_cast<Result>(a) + b;
}
/// Apply operation and check overflow. It's used for Deciamal operations. @returns true if overflowed, false othervise.
/// Apply operation and check overflow. It's used for Deciamal operations. @returns true if overflowed, false otherwise.
template <typename Result = ResultType>
static inline bool apply(A a, B b, Result & c)
{

View File

@ -991,7 +991,7 @@ void skipToUnescapedNextLineOrEOF(ReadBuffer & buf)
if (buf.eof())
return;
/// Skip escaped character. We do not consider escape sequences with more than one charater after backslash (\x01).
/// Skip escaped character. We do not consider escape sequences with more than one character after backslash (\x01).
/// It's ok for the purpose of this function, because we are interested only in \n and \\.
++buf.position();
continue;

View File

@ -581,7 +581,7 @@ inline ReturnType readDateTimeTextImpl(time_t & datetime, ReadBuffer & buf, cons
{
/** Read 10 characters, that could represent unix timestamp.
* Only unix timestamp of 5-10 characters is supported.
* Then look at 5th charater. If it is a number - treat whole as unix timestamp.
* Then look at 5th character. If it is a number - treat whole as unix timestamp.
* If it is not a number - then parse datetime in YYYY-MM-DD hh:mm:ss format.
*/

View File

@ -124,7 +124,7 @@ struct ContextShared
ConfigurationPtr config; /// Global configuration settings.
Databases databases; /// List of databases and tables in them.
mutable std::shared_ptr<EmbeddedDictionaries> embedded_dictionaries; /// Metrica's dictionaeis. Have lazy initialization.
mutable std::shared_ptr<EmbeddedDictionaries> embedded_dictionaries; /// Metrica's dictionaries. Have lazy initialization.
mutable std::shared_ptr<ExternalDictionaries> external_dictionaries;
mutable std::shared_ptr<ExternalModels> external_models;
String default_profile_name; /// Default profile name used for default values.

View File

@ -276,7 +276,7 @@ bool DDLWorker::initAndCheckTask(const String & entry_name, String & out_reason)
catch (...)
{
/// What should we do if we even cannot parse host name and therefore cannot properly submit execution status?
/// We can try to create fail node using FQDN if it equal to host name in cluster config attempt will be sucessfull.
/// We can try to create fail node using FQDN if it equal to host name in cluster config attempt will be successful.
/// Otherwise, that node will be ignored by DDLQueryStatusInputSream.
tryLogCurrentException(log, "Cannot parse DDL task " + entry_name + ", will try to send error status");
@ -1153,7 +1153,7 @@ private:
Strings current_active_hosts; /// Hosts that were in active state at the last check
size_t num_hosts_finished = 0;
/// Save the first detected error and throw it at the end of excecution
/// Save the first detected error and throw it at the end of execution
std::unique_ptr<Exception> first_exception;
Int64 timeout_seconds = 120;

View File

@ -77,7 +77,7 @@ BlockIO InterpreterRenameQuery::execute()
std::set<UniqueTableName> unique_tables_from;
/// Don't allow to drop tables (that we are renaming); do't allow to create tables in places where tables will be renamed.
/// Don't allow to drop tables (that we are renaming); don't allow to create tables in places where tables will be renamed.
std::map<UniqueTableName, std::unique_ptr<DDLGuard>> table_guards;
for (const auto & elem : rename.elements)

View File

@ -586,7 +586,7 @@ void InterpreterSelectQuery::executeImpl(Pipeline & pipeline, const BlockInputSt
executePreLimit(pipeline);
}
// If there is no global subqueries, we can run subqueries only when recieve them on server.
// If there is no global subqueries, we can run subqueries only when receive them on server.
if (!query_analyzer->hasGlobalSubqueries() && !expressions.subqueries_for_sets.empty())
executeSubqueriesInSetsAndJoins(pipeline, expressions.subqueries_for_sets);
}

View File

@ -53,7 +53,7 @@ ExecutionStatus getOverallExecutionStatusOfCommands()
return ExecutionStatus(0);
}
/// Consequently tries to execute all commands and genreates final exception message for failed commands
/// Consequently tries to execute all commands and generates final exception message for failed commands
template <typename Callable, typename ... Callables>
ExecutionStatus getOverallExecutionStatusOfCommands(Callable && command, Callables && ... commands)
{

View File

@ -278,7 +278,7 @@ struct Settings
M(SettingBool, log_profile_events, true, "Log query performance statistics into the query_log and query_thread_log.") \
M(SettingBool, log_query_settings, true, "Log query settings into the query_log.") \
M(SettingBool, log_query_threads, true, "Log query threads into system.query_thread_log table. This setting have effect only when 'log_queries' is true.") \
M(SettingLogsLevel, send_logs_level, "none", "Send server text logs with specified minumum level to client. Valid values: 'trace', 'debug', 'information', 'warning', 'error', 'none'") \
M(SettingLogsLevel, send_logs_level, "none", "Send server text logs with specified minimum level to client. Valid values: 'trace', 'debug', 'information', 'warning', 'error', 'none'") \
M(SettingBool, enable_optimize_predicate_expression, 0, "If it is set to true, optimize predicates to subqueries.") \
\
M(SettingUInt64, low_cardinality_max_dictionary_size, 8192, "Maximum size (in rows) of shared global dictionary for LowCardinality type.") \

View File

@ -766,7 +766,7 @@ SyntaxAnalyzerResultPtr SyntaxAnalyzer::analyze(
/// Executing scalar subqueries - replacing them with constant values.
executeScalarSubqueries(query, context, subquery_depth);
/// Optimize if with constant condition after constants was substituted instead of sclalar subqueries.
/// Optimize if with constant condition after constants was substituted instead of scalar subqueries.
OptimizeIfWithConstantConditionVisitor(result.aliases).visit(query);
if (select_query)

View File

@ -115,7 +115,7 @@ std::vector<ASTPtr *> TranslateQualifiedNamesMatcher::visit(ASTTableJoin & join,
std::vector<ASTPtr *> TranslateQualifiedNamesMatcher::visit(ASTSelectQuery & select, const ASTPtr & , Data &)
{
/// If the WHERE clause or HAVING consists of a single quailified column, the reference must be translated not only in children,
/// If the WHERE clause or HAVING consists of a single qualified column, the reference must be translated not only in children,
/// but also in where_expression and having_expression.
std::vector<ASTPtr *> out;
if (select.prewhere_expression)

View File

@ -330,7 +330,7 @@ static std::tuple<ASTPtr, BlockIO> executeQueryImpl(
{
if (auto counting_stream = dynamic_cast<const CountingBlockOutputStream *>(stream_out))
{
/// NOTE: Redundancy. The same values coulld be extracted from process_list_elem->progress_out.query_settings = process_list_elem->progress_in
/// NOTE: Redundancy. The same values could be extracted from process_list_elem->progress_out.query_settings = process_list_elem->progress_in
elem.result_rows = counting_stream->getProgress().rows;
elem.result_bytes = counting_stream->getProgress().bytes;
}

View File

@ -15,7 +15,7 @@ namespace DB
* or
* (subquery)
*
* Optionally with alias (correllation name):
* Optionally with alias (correlation name):
* [AS] alias
*
* Table may contain FINAL and SAMPLE modifiers:

View File

@ -132,7 +132,7 @@ Token Lexer::nextTokenImpl()
++pos;
}
/// exponentation (base 10 or base 2)
/// exponentiation (base 10 or base 2)
if (pos + 1 < end && (hex ? (*pos == 'p' || *pos == 'P') : (*pos == 'e' || *pos == 'E')))
{
++pos;
@ -195,7 +195,7 @@ Token Lexer::nextTokenImpl()
while (pos < end && isNumericASCII(*pos))
++pos;
/// exponentation
/// exponentiation
if (pos + 1 < end && (*pos == 'e' || *pos == 'E'))
{
++pos;

View File

@ -49,7 +49,7 @@ ASTPtr parseQuery(
/** Split queries separated by ; on to list of single queries
* Returns pointer to the end of last sucessfuly parsed query (first), and true if all queries are sucessfuly parsed (second)
* Returns pointer to the end of last successfully parsed query (first), and true if all queries are successfully parsed (second)
* NOTE: INSERT's data should be placed in single line.
*/
std::pair<const char *, bool> splitMultipartQuery(const std::string & queries, std::vector<std::string> & queries_list);

View File

@ -155,7 +155,7 @@ public:
return;
// An error was thrown during the stream or it did not finish successfully
// The read offsets weren't comitted, so consumer must rejoin the group from the original starting point
// The read offsets weren't committed, so consumer must rejoin the group from the original starting point
if (!finalized)
{
LOG_TRACE(storage.log, "KafkaBlockInputStream did not finish successfully, unsubscribing from assignments and rejoining");

View File

@ -6,7 +6,7 @@
namespace DB
{
/// Select all parts within partition (having at least two parts) with minumum total size.
/// Select all parts within partition (having at least two parts) with minimum total size.
class AllMergeSelector : public IMergeSelector
{
public:

View File

@ -339,7 +339,7 @@ private:
/** Is node the key column
* or expression in which column of key is wrapped by chain of functions,
* that can be monotomic on certain ranges?
* that can be monotonic on certain ranges?
* If these conditions are true, then returns number of column in key, type of resulting expression
* and fills chain of possibly-monotonic functions.
*/

View File

@ -84,7 +84,7 @@ MergeTreeBlockSizePredictor::MergeTreeBlockSizePredictor(
: data_part(data_part_)
{
number_of_rows_in_part = data_part->rows_count;
/// Initialize with sample block untill update won't called.
/// Initialize with sample block until update won't called.
initialize(sample_block, columns);
}
@ -173,7 +173,7 @@ void MergeTreeBlockSizePredictor::update(const Block & block, double decay)
block_size_rows = new_rows;
/// Make recursive updates for each read row: v_{i+1} = (1 - decay) v_{i} + decay v_{target}
/// Use sum of gemetric sequence formula to update multiple rows: v{n} = (1 - decay)^n v_{0} + (1 - (1 - decay)^n) v_{target}
/// Use sum of geometric sequence formula to update multiple rows: v{n} = (1 - decay)^n v_{0} + (1 - (1 - decay)^n) v_{target}
/// NOTE: DEFAULT and MATERIALIZED columns without data has inaccurate estimation of v_{target}
double alpha = std::pow(1. - decay, diff_rows);

View File

@ -714,7 +714,7 @@ MergeTreeData::MutableDataPartPtr MergeTreeDataMergerMutator::mergePartsToTempor
if (disk_reservation && sum_input_rows_upper_bound)
{
/// The same progress from merge_entry could be used for both algorithms (it should be more accurate)
/// But now we are using inaccurate row-based estimation in Horizontal case for backward compability
/// But now we are using inaccurate row-based estimation in Horizontal case for backward compatibility
Float64 progress = (merge_alg == MergeAlgorithm::Horizontal)
? std::min(1., 1. * rows_written / sum_input_rows_upper_bound)
: std::min(1., merge_entry->progress.load(std::memory_order_relaxed));

View File

@ -16,7 +16,7 @@ public:
/** Minimum ratio of size of one part to all parts in set of parts to merge (for usual cases).
* For example, if all parts have equal size, it means, that at least 'base' number of parts should be merged.
* If parts has non-uniform sizes, then minumum number of parts to merge is effectively increased.
* If parts has non-uniform sizes, then minimum number of parts to merge is effectively increased.
* This behaviour balances merge-tree workload.
* It called 'base', because merge-tree depth could be estimated as logarithm with that base.
*

View File

@ -131,7 +131,7 @@ public:
if (storage.table_fd_init_offset < 0)
throw Exception("File descriptor isn't seekable, inside " + storage.getName(), ErrorCodes::CANNOT_SEEK_THROUGH_FILE);
/// ReadBuffer's seek() doesn't make sence, since cache is empty
/// ReadBuffer's seek() doesn't make sense, since cache is empty
if (lseek(storage.table_fd, storage.table_fd_init_offset, SEEK_SET) < 0)
throwFromErrno("Cannot seek file descriptor, inside " + storage.getName(), ErrorCodes::CANNOT_SEEK_THROUGH_FILE);
}

View File

@ -1592,7 +1592,7 @@ bool StorageReplicatedMergeTree::executeReplaceRange(const LogEntry & entry)
MergeTreePartInfo new_part_info;
String checksum_hex;
/// Part which will be comitted
/// Part which will be committed
MergeTreeData::MutableDataPartPtr res_part;
/// We could find a covering part
@ -1624,7 +1624,7 @@ bool StorageReplicatedMergeTree::executeReplaceRange(const LogEntry & entry)
data.format_version));
}
/// What parts we should add? Or we have already added all required parts (we an replica-intializer)
/// What parts we should add? Or we have already added all required parts (we an replica-initializer)
{
auto data_parts_lock = data.lockParts();
@ -3427,7 +3427,7 @@ bool StorageReplicatedMergeTree::getFakePartCoveringAllPartsInPartition(const St
--right;
/// Artificial high level is choosen, to make this part "covering" all parts inside.
/// Artificial high level is chosen, to make this part "covering" all parts inside.
part_info = MergeTreePartInfo(partition_id, left, right, MergeTreePartInfo::MAX_LEVEL, mutation_version);
return true;
}
@ -3692,7 +3692,7 @@ std::optional<EphemeralLockInZooKeeper>
StorageReplicatedMergeTree::allocateBlockNumber(
const String & partition_id, zkutil::ZooKeeperPtr & zookeeper, const String & zookeeper_block_id_path)
{
/// Lets check for duplicates in advance, to avoid superflous block numbers allocation
/// Lets check for duplicates in advance, to avoid superfluous block numbers allocation
Coordination::Requests deduplication_check_ops;
if (!zookeeper_block_id_path.empty())
{
@ -4742,7 +4742,7 @@ void StorageReplicatedMergeTree::replacePartitionFrom(const StoragePtr & source_
for (size_t i = 0; i < src_all_parts.size(); ++i)
{
/// We also make some kind of deduplication to avoid duplicated parts in case of ATTACH PARTITION
/// Assume that merges in the partiton are quite rare
/// Assume that merges in the partition are quite rare
/// Save deduplication block ids with special prefix replace_partition
auto & src_part = src_all_parts[i];

View File

@ -33,5 +33,5 @@ SELECT roundToExp2(number) AS k, length(groupArray(1)([hex(number)] AS i)), leng
DROP TABLE test.numbers_mt;
-- Check binary compability:
-- Check binary compatibility:
-- clickhouse-client -h old -q "SELECT arrayReduce('groupArrayState', [['1'], ['22'], ['333']]) FORMAT RowBinary" | clickhouse-local -s --input-format RowBinary --structure "d AggregateFunction(groupArray2, Array(String))" -q "SELECT groupArray2Merge(d) FROM table"