mirror of
https://github.com/ClickHouse/ClickHouse.git
synced 2024-11-24 00:22:29 +00:00
merged with master
This commit is contained in:
Nikolai Kochetov
commit
7e45661a38
@ -1,7 +1,7 @@
|
||||
# This strings autochanged from release_lib.sh:
|
||||
set(VERSION_DESCRIBE v1.1.54378-testing)
|
||||
set(VERSION_REVISION 54378)
|
||||
set(VERSION_GITHASH 5b19d89133a5ff7c72e40cc8c0226cb00466ba10)
|
||||
set(VERSION_DESCRIBE v1.1.54379-testing)
|
||||
set(VERSION_REVISION 54379)
|
||||
set(VERSION_GITHASH c087449023ab2b582987af162a5cb989ba77db67)
|
||||
# end of autochange
|
||||
|
||||
set (VERSION_MAJOR 1)
|
||||
|
||||
@ -69,4 +69,14 @@ String Macros::expand(const String & s, size_t level) const
|
||||
return expand(res, level + 1);
|
||||
}
|
||||
|
||||
Names Macros::expand(const Names & source_names, size_t level) const
|
||||
{
|
||||
Names result_names;
|
||||
result_names.reserve(source_names.size());
|
||||
|
||||
for (const String & name : source_names)
|
||||
result_names.push_back(expand(name, level));
|
||||
|
||||
return result_names;
|
||||
}
|
||||
}
|
||||
|
||||
@ -1,9 +1,11 @@
|
||||
#pragma once
|
||||
|
||||
#include <Core/Types.h>
|
||||
#include <Core/Names.h>
|
||||
#include <map>
|
||||
|
||||
|
||||
|
||||
namespace Poco
|
||||
{
|
||||
namespace Util
|
||||
@ -28,6 +30,10 @@ public:
|
||||
* level - the level of recursion.
|
||||
*/
|
||||
String expand(const String & s, size_t level = 0) const;
|
||||
|
||||
/** Apply expand for the list.
|
||||
*/
|
||||
Names expand(const Names & source_names, size_t level = 0) const;
|
||||
|
||||
using MacroMap = std::map<String, String>;
|
||||
const MacroMap getMacroMap() const { return macros; }
|
||||
|
||||
@ -3,9 +3,6 @@
|
||||
#include <Core/Types.h>
|
||||
#include <Common/BitHelpers.h>
|
||||
|
||||
#if __SSE2__
|
||||
#include <emmintrin.h>
|
||||
#endif
|
||||
|
||||
namespace DB
|
||||
{
|
||||
@ -52,29 +49,9 @@ inline size_t seqLength(const UInt8 first_octet)
|
||||
inline size_t countCodePoints(const UInt8 * data, size_t size)
|
||||
{
|
||||
size_t res = 0;
|
||||
const auto end = data + size;
|
||||
|
||||
#if __SSE2__
|
||||
const auto bytes_sse = sizeof(__m128i);
|
||||
const auto src_end_sse = (data + size) - (size % bytes_sse);
|
||||
|
||||
const auto align_sse = _mm_set1_epi8(0x40);
|
||||
const auto upper_bound = _mm_set1_epi8(0xBF);
|
||||
|
||||
for (; data < src_end_sse; data += bytes_sse)
|
||||
{
|
||||
const auto chars = _mm_loadu_si128(reinterpret_cast<const __m128i *>(data));
|
||||
|
||||
///Align to zero for the solve two case
|
||||
const auto align_res = _mm_adds_epu8(chars, align_sse);
|
||||
const auto less_than_and_equals = _mm_cmpeq_epi8(_mm_min_epu8(align_res, upper_bound), align_res);
|
||||
|
||||
res += __builtin_popcount(_mm_movemask_epi8(less_than_and_equals));
|
||||
}
|
||||
|
||||
#endif
|
||||
|
||||
for (; data < end; ++data) /// Skip UTF-8 continuation bytes.
|
||||
/// TODO SIMD implementation looks quite simple.
|
||||
for (auto end = data + size; data < end; ++data) /// Skip UTF-8 continuation bytes.
|
||||
res += (*data <= 0x7F || *data >= 0xC0);
|
||||
|
||||
return res;
|
||||
|
||||
@ -359,6 +359,8 @@ void InterpreterSelectQuery::executeImpl(Pipeline & pipeline, const BlockInputSt
|
||||
if (!dry_run)
|
||||
from_stage = storage->getQueryProcessingStage(context);
|
||||
|
||||
query_analyzer->makeSetsForIndex();
|
||||
|
||||
auto optimize_prewhere = [&](auto & merge_tree)
|
||||
{
|
||||
SelectQueryInfo query_info;
|
||||
@ -374,8 +376,6 @@ void InterpreterSelectQuery::executeImpl(Pipeline & pipeline, const BlockInputSt
|
||||
optimize_prewhere(*merge_tree);
|
||||
else if (const StorageReplicatedMergeTree * merge_tree = dynamic_cast<const StorageReplicatedMergeTree *>(storage.get()))
|
||||
optimize_prewhere(*merge_tree);
|
||||
|
||||
query_analyzer->makeSetsForIndex();
|
||||
}
|
||||
|
||||
AnalysisResult expressions = analyzeExpressions(from_stage);
|
||||
|
||||
@ -1106,7 +1106,10 @@ String KeyCondition::RPNElement::toString() const
|
||||
ss << "(";
|
||||
print_wrapped_column(ss);
|
||||
ss << (function == FUNCTION_IN_SET ? " in " : " notIn ");
|
||||
ss << set_index->size() << "-element set";
|
||||
if (!set_index)
|
||||
ss << "unknown size set";
|
||||
else
|
||||
ss << set_index->size() << "-element set";
|
||||
ss << ")";
|
||||
return ss.str();
|
||||
}
|
||||
|
||||
@ -6,6 +6,7 @@
|
||||
#include <boost/algorithm/string/replace.hpp>
|
||||
#include <boost/algorithm/string/split.hpp>
|
||||
#include <boost/algorithm/string/trim.hpp>
|
||||
#include <Common/Macros.h>
|
||||
#include <Common/Exception.h>
|
||||
#include <Common/setThreadName.h>
|
||||
#include <Common/typeid_cast.h>
|
||||
@ -225,7 +226,11 @@ StorageKafka::StorageKafka(
|
||||
const String & format_name_, const String & schema_name_, size_t num_consumers_)
|
||||
: IStorage{columns_},
|
||||
table_name(table_name_), database_name(database_name_), context(context_),
|
||||
topics(topics_), brokers(brokers_), group(group_), format_name(format_name_), schema_name(schema_name_),
|
||||
topics(context.getMacros()->expand(topics_)),
|
||||
brokers(context.getMacros()->expand(brokers_)),
|
||||
group(context.getMacros()->expand(group_)),
|
||||
format_name(context.getMacros()->expand(format_name_)),
|
||||
schema_name(context.getMacros()->expand(schema_name_)),
|
||||
num_consumers(num_consumers_), log(&Logger::get("StorageKafka (" + table_name_ + ")")),
|
||||
semaphore(0, num_consumers_), mutex(), consumers(), event_update()
|
||||
{
|
||||
|
||||
@ -1,38 +0,0 @@
|
||||
<test>
|
||||
<name>functions_length</name>
|
||||
<type>once</type>
|
||||
|
||||
<stop_conditions>
|
||||
<all_of>
|
||||
<total_time_ms>10000</total_time_ms>
|
||||
</all_of>
|
||||
<any_of>
|
||||
<average_speed_not_changing_for_ms>5000</average_speed_not_changing_for_ms>
|
||||
<total_time_ms>20000</total_time_ms>
|
||||
</any_of>
|
||||
</stop_conditions>
|
||||
|
||||
<main_metric>
|
||||
<avg_rows_per_second/>
|
||||
</main_metric>
|
||||
|
||||
<substitutions>
|
||||
<substitution>
|
||||
<name>string</name>
|
||||
<values>
|
||||
<value>materialize('')</value>
|
||||
<value>materialize('Hello, world')</value>
|
||||
<value>toString(number)</value>
|
||||
<value>reinterpretAsString(number)</value>
|
||||
<value>materialize('中文测试字符串')</value>
|
||||
<value>materialize('https://github.com/yandex/ClickHouse/pull/1882')</value>
|
||||
<value>materialize('https://zh.wikipedia.org/wiki/%E4%B8%AD%E6%97%A5%E9%9F%93%E7%B5%B1%E4%B8%80%E8%A1%A8%E6%84%8F%E6%96%87%E5%AD%97%E6%93%B4%E5%B1%95%E5%8D%80F')</value>
|
||||
<value>concat('中文测试字符串 ', toString(number), ' Привет, мир!')</value>
|
||||
<value>concat(concat('中文测试字符串 ', toString(number), ' Привет, мир!') AS x, x, x, x, x, x, x, x, x, x)</value>
|
||||
<value>convertCharset(concat(reinterpretAsString(rand64(1)), reinterpretAsString(rand64(2)), reinterpretAsString(rand64(3)), reinterpretAsString(rand64(4)), reinterpretAsString(rand64(5)), reinterpretAsString(rand64(6)), reinterpretAsString(rand64(7)), reinterpretAsString(rand64(8)), reinterpretAsString(rand64(9)), reinterpretAsString(rand64(10))), 'UTF-16', 'UTF-8')</value>
|
||||
</values>
|
||||
</substitution>
|
||||
</substitutions>
|
||||
|
||||
<query>SELECT count() FROM system.numbers WHERE NOT ignore(lengthUTF8({string}))</query>
|
||||
</test>
|
||||
1
dbms/tests/queries/0_stateless/00624_length_utf8.sql
Normal file
1
dbms/tests/queries/0_stateless/00624_length_utf8.sql
Normal file
@ -0,0 +1 @@
|
||||
SELECT 'привет пр' AS x, lengthUTF8(x) AS y;
|
||||
4
debian/changelog
vendored
4
debian/changelog
vendored
@ -1,5 +1,5 @@
|
||||
clickhouse (1.1.54378) unstable; urgency=low
|
||||
clickhouse (1.1.54379) unstable; urgency=low
|
||||
|
||||
* Modified source code
|
||||
|
||||
-- <robot-metrika-test@yandex-team.ru> Fri, 13 Apr 2018 15:44:34 +0300
|
||||
-- <robot-metrika-test@yandex-team.ru> Fri, 20 Apr 2018 22:15:52 +0300
|
||||
|
||||
Loading…
Reference in New Issue
Block a user