thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-09-20 00:30:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'upstream/master' into kssenii-patch-6

Browse Source
This commit is contained in:
kssenii 2023-09-18 13:00:26 +02:00
commit 10518a9c83
752 changed files with 16275 additions and 7867 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
.clang-format
View File

@ -79,7 +79,7 @@ IndentWidth: 4
IndentWrappedFunctionNames: false
MacroBlockBegin: ''
MacroBlockEnd: ''
NamespaceIndentation: Inner
NamespaceIndentation: None
ObjCBlockIndentWidth: 4
ObjCSpaceAfterProperty: true
ObjCSpaceBeforeProtocolList: true
@ -89,6 +89,7 @@ PenaltyBreakFirstLessLess: 120
PenaltyBreakString: 1000
PenaltyExcessCharacter: 1000000
PenaltyReturnTypeOnItsOwnLine: 60
RemoveBracesLLVM: true
SpaceAfterCStyleCast: false
SpaceBeforeAssignmentOperators: true
SpaceBeforeParens: ControlStatements

45
.github/workflows/auto_release.yml vendored Normal file
View File

@ -0,0 +1,45 @@
name: AutoRelease
env:
# Force the stdout and stderr streams to be unbuffered
PYTHONUNBUFFERED: 1
concurrency:
group: auto-release
on: # yamllint disable-line rule:truthy
# schedule:
# - cron: '0 10-16 * * 1-5'
workflow_dispatch:
jobs:
CherryPick:
runs-on: [self-hosted, style-checker-aarch64]
steps:
- name: Set envs
# https://docs.github.com/en/actions/learn-github-actions/workflow-commands-for-github-actions#multiline-strings
run: |
cat >> "$GITHUB_ENV" << 'EOF'
TEMP_PATH=${{runner.temp}}/cherry_pick
ROBOT_CLICKHOUSE_SSH_KEY<<RCSK
${{secrets.ROBOT_CLICKHOUSE_SSH_KEY}}
RCSK
REPO_OWNER=ClickHouse
REPO_NAME=ClickHouse
REPO_TEAM=core
EOF
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
token: ${{secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN}}
fetch-depth: 0
- name: Auto-release
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 auto_release.py --release-after-days=3
- name: Cleanup
if: always()
run: |
docker ps --quiet | xargs --no-run-if-empty docker kill ||:
docker ps --all --quiet | xargs --no-run-if-empty docker rm -f ||:
sudo rm -fr "$TEMP_PATH"

1
.github/workflows/backport_branches.yml vendored
View File

@ -76,6 +76,7 @@ jobs:
uses: ClickHouse/checkout@v1
with:
clear-repository: true
fetch-depth: 0 # to find ancestor merge commits necessary for finding proper docker tags
- name: Download changed aarch64 images
uses: actions/download-artifact@v3
with:

1
.github/workflows/docs_check.yml vendored
View File

@ -73,6 +73,7 @@ jobs:
uses: ClickHouse/checkout@v1
with:
clear-repository: true
fetch-depth: 0 # to find ancestor merge commits necessary for finding proper docker tags
- name: Download changed aarch64 images
uses: actions/download-artifact@v3
with:

1
.github/workflows/master.yml vendored
View File

@ -60,6 +60,7 @@ jobs:
uses: ClickHouse/checkout@v1
with:
clear-repository: true
fetch-depth: 0 # to find ancestor merge commits necessary for finding proper docker tags
- name: Download changed aarch64 images
uses: actions/download-artifact@v3
with:

1
.github/workflows/nightly.yml vendored
View File

@ -53,6 +53,7 @@ jobs:
uses: ClickHouse/checkout@v1
with:
clear-repository: true
fetch-depth: 0 # to find ancestor merge commits necessary for finding proper docker tags
- name: Download changed aarch64 images
uses: actions/download-artifact@v3
with:

1
.github/workflows/pull_request.yml vendored
View File

@ -94,6 +94,7 @@ jobs:
uses: ClickHouse/checkout@v1
with:
clear-repository: true
fetch-depth: 0 # to find ancestor merge commits necessary for finding proper docker tags
- name: Download changed aarch64 images
uses: actions/download-artifact@v3
with:

1
.github/workflows/release_branches.yml vendored
View File

@ -52,6 +52,7 @@ jobs:
uses: ClickHouse/checkout@v1
with:
clear-repository: true
fetch-depth: 0 # to find ancestor merge commits necessary for finding proper docker tags
- name: Download changed aarch64 images
uses: actions/download-artifact@v3
with:

6
.gitmodules vendored
View File

@ -40,9 +40,6 @@
[submodule "contrib/boost"]
path = contrib/boost
url = https://github.com/ClickHouse/boost
[submodule "contrib/base64"]
path = contrib/base64
url = https://github.com/ClickHouse/Turbo-Base64
[submodule "contrib/arrow"]
path = contrib/arrow
url = https://github.com/ClickHouse/arrow
@ -348,3 +345,6 @@
[submodule "contrib/robin-map"]
path = contrib/robin-map
url = https://github.com/Tessil/robin-map.git
[submodule "contrib/aklomp-base64"]
path = contrib/aklomp-base64
url = https://github.com/aklomp/base64.git

2
cmake/limit_jobs.cmake
View File

@ -47,7 +47,7 @@ if (CMAKE_BUILD_TYPE_UC STREQUAL "RELWITHDEBINFO" AND ENABLE_THINLTO AND PARALLE
set (PARALLEL_LINK_JOBS 2)
endif()
message(STATUS "Building sub-tree with ${PARALLEL_COMPILE_JOBS} compile jobs and ${PARALLEL_LINK_JOBS} linker jobs (system: ${NUMBER_OF_LOGICAL_CORES} cores, ${TOTAL_PHYSICAL_MEMORY} MB DRAM, 'OFF' means the native core count).")
message(STATUS "Building sub-tree with ${PARALLEL_COMPILE_JOBS} compile jobs and ${PARALLEL_LINK_JOBS} linker jobs (system: ${NUMBER_OF_LOGICAL_CORES} cores, ${TOTAL_PHYSICAL_MEMORY} MB RAM, 'OFF' means the native core count).")
if (PARALLEL_COMPILE_JOBS LESS NUMBER_OF_LOGICAL_CORES)
set(CMAKE_JOB_POOL_COMPILE compile_job_pool${CMAKE_CURRENT_SOURCE_DIR})

2
contrib/CMakeLists.txt vendored
View File

@ -135,7 +135,7 @@ add_contrib (aws-cmake
aws-cmake
)
add_contrib (base64-cmake base64)
add_contrib (aklomp-base64-cmake aklomp-base64)
add_contrib (simdjson-cmake simdjson)
add_contrib (rapidjson-cmake rapidjson)
add_contrib (fastops-cmake fastops)

2
contrib/abseil-cpp vendored

@ -1 +1 @@
Subproject commit 215105818dfde3174fe799600bb0f3cae233d0bf
Subproject commit 5655528c41830f733160de4fb0b99073841bae9e

2
contrib/abseil-cpp-cmake/CMakeLists.txt
View File

@ -1,5 +1,5 @@
set(ABSL_ROOT_DIR "${ClickHouse_SOURCE_DIR}/contrib/abseil-cpp")
set(BUILD_TESTING OFF)
set(ABSL_PROPAGATE_CXX_STD ON)
add_subdirectory("${ABSL_ROOT_DIR}" "${ClickHouse_BINARY_DIR}/contrib/abseil-cpp")

1
contrib/aklomp-base64 vendored Submodule

@ -0,0 +1 @@
Subproject commit e77bd70bdd860c52c561568cffb251d88bba064c

1
contrib/aklomp-base64-cmake/.gitignore vendored Normal file
View File

@ -0,0 +1 @@
config.h

68
contrib/aklomp-base64-cmake/CMakeLists.txt Normal file
View File

@ -0,0 +1,68 @@
option (ENABLE_BASE64 "Enable base64" ${ENABLE_LIBRARIES})
if (NOT ENABLE_BASE64)
message(STATUS "Not using base64")
return()
endif()
SET(LIBRARY_DIR "${ClickHouse_SOURCE_DIR}/contrib/aklomp-base64")
if (ARCH_AMD64)
# These defines enable/disable SIMD codecs in base64's runtime codec dispatch.
# We don't want to limit ourselves --> enable all.
set(HAVE_SSSE3 1)
set(HAVE_SSE41 1)
set(HAVE_SSE42 1)
set(HAVE_AVX 1)
set(HAVE_AVX2 1)
set(HAVE_AVX512 1)
endif ()
if (ARCH_AARCH64)
# The choice of HAVE_NEON* depends on the target machine because base64 provides
# no runtime dispatch on ARM. NEON is only mandatory with the normal build profile.
if(NOT NO_ARMV81_OR_HIGHER)
set(HAVE_NEON64 1)
set(HAVE_NEON32 0)
endif ()
endif ()
configure_file(config.h.in ${CMAKE_CURRENT_BINARY_DIR}/config.h)
add_library(_base64
"${LIBRARY_DIR}/lib/lib.c"
"${LIBRARY_DIR}/lib/codec_choose.c"
"${LIBRARY_DIR}/lib/tables/tables.c"
"${LIBRARY_DIR}/lib/tables/table_dec_32bit.h"
"${LIBRARY_DIR}/lib/tables/table_enc_12bit.h"
"${LIBRARY_DIR}/lib/codecs.h"
"${CMAKE_CURRENT_BINARY_DIR}/config.h"
"${LIBRARY_DIR}/lib/arch/generic/codec.c"
"${LIBRARY_DIR}/lib/arch/ssse3/codec.c"
"${LIBRARY_DIR}/lib/arch/sse41/codec.c"
"${LIBRARY_DIR}/lib/arch/sse42/codec.c"
"${LIBRARY_DIR}/lib/arch/avx/codec.c"
"${LIBRARY_DIR}/lib/arch/avx2/codec.c"
"${LIBRARY_DIR}/lib/arch/avx512/codec.c"
"${LIBRARY_DIR}/lib/arch/neon32/codec.c"
"${LIBRARY_DIR}/lib/arch/neon64/codec.c"
)
if (ARCH_AMD64)
set_source_files_properties(${LIBRARY_DIR}/lib/arch/ssse3/codec.c PROPERTIES COMPILE_FLAGS "-mssse3")
set_source_files_properties(${LIBRARY_DIR}/lib/arch/sse41/codec.c PROPERTIES COMPILE_FLAGS "-msse4.1")
set_source_files_properties(${LIBRARY_DIR}/lib/arch/sse42/codec.c PROPERTIES COMPILE_FLAGS "-msse4.2")
set_source_files_properties(${LIBRARY_DIR}/lib/arch/avx/codec.c PROPERTIES COMPILE_FLAGS "-mavx")
set_source_files_properties(${LIBRARY_DIR}/lib/arch/avx2/codec.c PROPERTIES COMPILE_FLAGS "-mavx2")
set_source_files_properties(${LIBRARY_DIR}/lib/arch/avx512/codec.c PROPERTIES COMPILE_FLAGS "-mavx512vl -mavx512vbmi")
endif()
target_include_directories(_base64 SYSTEM PUBLIC ${LIBRARY_DIR}/include)
target_include_directories(_base64 PRIVATE ${CMAKE_CURRENT_SOURCE_DIR} ${CMAKE_CURRENT_BINARY_DIR})
add_library(ch_contrib::base64 ALIAS _base64)

9
contrib/aklomp-base64-cmake/config.h.in Normal file
View File

@ -0,0 +1,9 @@
#cmakedefine01 HAVE_SSSE3
#cmakedefine01 HAVE_SSE41
#cmakedefine01 HAVE_SSE42
#cmakedefine01 HAVE_AVX
#cmakedefine01 HAVE_AVX2
#cmakedefine01 HAVE_AVX512
#cmakedefine01 HAVE_NEON32
#cmakedefine01 HAVE_NEON64

1
contrib/base64 vendored

@ -1 +0,0 @@
Subproject commit 8628e258090f9eb76d90ac3c91e1ab4690e9aa11

60
contrib/base64-cmake/CMakeLists.txt
View File

@ -1,60 +0,0 @@
if(ARCH_AMD64 OR ARCH_AARCH64 OR ARCH_PPC64LE OR ARCH_S390X)
option (ENABLE_BASE64 "Enable base64" ${ENABLE_LIBRARIES})
elseif(ENABLE_BASE64)
message (${RECONFIGURE_MESSAGE_LEVEL} "base64 library is only supported on x86_64 and aarch64")
endif()
if (NOT ENABLE_BASE64)
message(STATUS "Not using base64")
return()
endif()
SET(LIBRARY_DIR "${ClickHouse_SOURCE_DIR}/contrib/base64")
add_library(_base64_scalar OBJECT "${LIBRARY_DIR}/turbob64c.c" "${LIBRARY_DIR}/turbob64d.c")
add_library(_base64_ssse3 OBJECT "${LIBRARY_DIR}/turbob64sse.c") # This file also contains code for ARM NEON
if (ARCH_AMD64)
add_library(_base64_avx OBJECT "${LIBRARY_DIR}/turbob64sse.c") # This is not a mistake. One file is compiled twice.
add_library(_base64_avx2 OBJECT "${LIBRARY_DIR}/turbob64avx2.c")
endif ()
target_compile_options(_base64_scalar PRIVATE -falign-loops)
if (ARCH_AMD64)
target_compile_options(_base64_ssse3 PRIVATE -mno-avx -mno-avx2 -mssse3 -falign-loops)
target_compile_options(_base64_avx PRIVATE -falign-loops -mavx)
target_compile_options(_base64_avx2 PRIVATE -falign-loops -mavx2)
else ()
if (ARCH_PPC64LE)
target_compile_options(_base64_ssse3 PRIVATE -D__SSSE3__ -falign-loops)
else()
target_compile_options(_base64_ssse3 PRIVATE -falign-loops)
endif()
endif ()
if (ARCH_AMD64)
add_library(_base64
$<TARGET_OBJECTS:_base64_scalar>
$<TARGET_OBJECTS:_base64_ssse3>
$<TARGET_OBJECTS:_base64_avx>
$<TARGET_OBJECTS:_base64_avx2>)
else ()
add_library(_base64
$<TARGET_OBJECTS:_base64_scalar>
$<TARGET_OBJECTS:_base64_ssse3>)
endif ()
target_include_directories(_base64 SYSTEM PUBLIC ${LIBRARY_DIR})
if (XCODE OR XCODE_VERSION)
# https://gitlab.kitware.com/cmake/cmake/issues/17457
# Some native build systems may not like targets that have only object files, so consider adding at least one real source file
# This applies to Xcode.
if (NOT EXISTS "${CMAKE_CURRENT_BINARY_DIR}/dummy.c")
file(WRITE "${CMAKE_CURRENT_BINARY_DIR}/dummy.c" "")
endif ()
target_sources(_base64 PRIVATE "${CMAKE_CURRENT_BINARY_DIR}/dummy.c")
endif ()
add_library(ch_contrib::base64 ALIAS _base64)

2
contrib/libunwind vendored

@ -1 +1 @@
Subproject commit e48aa13f67dc722511b5af33a32ba9b7748176b5
Subproject commit 30cc1d3fd3655a5cfa0ab112fe320fb9fc0a8344

2
contrib/re2 vendored

@ -1 +1 @@
Subproject commit 03da4fc0857c285e3a26782f6bc8931c4c950df4
Subproject commit a807e8a3aac2cc33c77b7071efea54fcabe38e0c

43
contrib/re2-cmake/CMakeLists.txt
View File

@ -1,14 +1,3 @@
# Copyright 2015 The RE2 Authors. All Rights Reserved.
# Use of this source code is governed by a BSD-style
# license that can be found in the LICENSE file.
# This file was edited for ClickHouse
string(FIND ${CMAKE_CURRENT_BINARY_DIR} " " _have_space)
if(_have_space GREATER 0)
message(FATAL_ERROR "Using spaces in build path [${CMAKE_CURRENT_BINARY_DIR}] highly not recommended. Library re2st will be disabled.")
endif()
set(SRC_DIR "${ClickHouse_SOURCE_DIR}/contrib/re2")
set(RE2_SOURCES
@ -35,33 +24,9 @@ set(RE2_SOURCES
${SRC_DIR}/util/rune.cc
${SRC_DIR}/util/strutil.cc
)
add_library(re2 ${RE2_SOURCES})
target_include_directories(re2 PUBLIC "${SRC_DIR}")
target_link_libraries(re2 ch_contrib::abseil_str_format)
# Building re2 which is thread-safe and re2_st which is not.
# re2 changes its state during matching of regular expression, e.g. creates temporary DFA.
# It uses RWLock to process the same regular expression object from different threads.
# In order to avoid redundant locks in some cases, we use not thread-safe version of the library (re2_st).
add_library(_re2 ${RE2_SOURCES})
target_include_directories(_re2 PUBLIC "${SRC_DIR}")
target_link_libraries(_re2 ch_contrib::abseil_str_format)
add_library(re2_st ${RE2_SOURCES})
target_compile_definitions (re2_st PRIVATE NDEBUG NO_THREADS re2=re2_st)
target_include_directories (re2_st PRIVATE .)
target_include_directories (re2_st SYSTEM PUBLIC ${CMAKE_CURRENT_BINARY_DIR})
target_include_directories (re2_st SYSTEM BEFORE PUBLIC ${SRC_DIR})
target_link_libraries (re2_st ch_contrib::abseil_str_format)
file (MAKE_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}/re2_st)
foreach (FILENAME filtered_re2.h re2.h set.h stringpiece.h)
add_custom_command (OUTPUT "${CMAKE_CURRENT_BINARY_DIR}/re2_st/${FILENAME}"
COMMAND ${CMAKE_COMMAND} -DSOURCE_FILENAME="${SRC_DIR}/re2/${FILENAME}"
-DTARGET_FILENAME="${CMAKE_CURRENT_BINARY_DIR}/re2_st/${FILENAME}"
-P "${CMAKE_CURRENT_SOURCE_DIR}/re2_transform.cmake"
COMMENT "Creating ${FILENAME} for re2_st library.")
add_custom_target (transform_${FILENAME} DEPENDS "${CMAKE_CURRENT_BINARY_DIR}/re2_st/${FILENAME}")
add_dependencies (re2_st transform_${FILENAME})
endforeach ()
# NOTE: you should not change name of library here, since it is used to generate required header (see above)
add_library(ch_contrib::re2 ALIAS re2)
add_library(ch_contrib::re2_st ALIAS re2_st)
add_library(ch_contrib::re2 ALIAS _re2)

10
contrib/re2-cmake/re2_transform.cmake
View File

@ -1,10 +0,0 @@
file (READ ${SOURCE_FILENAME} CONTENT)
string (REGEX REPLACE "using re2::RE2;" "" CONTENT "${CONTENT}")
string (REGEX REPLACE "using re2::LazyRE2;" "" CONTENT "${CONTENT}")
string (REGEX REPLACE "namespace re2 {" "namespace re2_st {" CONTENT "${CONTENT}")
string (REGEX REPLACE "re2::" "re2_st::" CONTENT "${CONTENT}")
string (REGEX REPLACE "\"re2/" "\"re2_st/" CONTENT "${CONTENT}")
string (REGEX REPLACE "(.\\*?_H)" "\\1_ST" CONTENT "${CONTENT}")
string (REGEX REPLACE "#define MUTEX_IS_PTHREAD_RWLOCK" "#undef MUTEX_IS_PTHREAD_RWLOCK" CONTENT "${CONTENT}")
string (REGEX REPLACE "typedef std::mutex MutexType;" "struct MutexType { void lock() {} void unlock() {} };" CONTENT "${CONTENT}")
file (WRITE ${TARGET_FILENAME} "${CONTENT}")

2
contrib/s2geometry vendored

@ -1 +1 @@
Subproject commit 4a7ebd5da04cb6c9ea38bbf5914a9f8f3c768564
Subproject commit 0547c38371777a1c1c8be263a6f05c3bf71bb05b

59
contrib/s2geometry-cmake/CMakeLists.txt
View File

@ -7,12 +7,6 @@ endif()
set(S2_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/s2geometry/src")
set(ABSL_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/abseil-cpp")
if(NOT EXISTS "${ABSL_SOURCE_DIR}/CMakeLists.txt")
message(FATAL_ERROR " submodule contrib/abseil-cpp is missing. To fix try run: \n git submodule update --init --recursive")
endif()
set(S2_SRCS
"${S2_SOURCE_DIR}/s2/encoded_s2cell_id_vector.cc"
"${S2_SOURCE_DIR}/s2/encoded_s2point_vector.cc"
@ -58,7 +52,9 @@ set(S2_SRCS
"${S2_SOURCE_DIR}/s2/s2edge_crossings.cc"
"${S2_SOURCE_DIR}/s2/s2edge_distances.cc"
"${S2_SOURCE_DIR}/s2/s2edge_tessellator.cc"
"${S2_SOURCE_DIR}/s2/s2error.cc"
"${S2_SOURCE_DIR}/s2/s2furthest_edge_query.cc"
"${S2_SOURCE_DIR}/s2/s2hausdorff_distance_query.cc"
"${S2_SOURCE_DIR}/s2/s2latlng.cc"
"${S2_SOURCE_DIR}/s2/s2latlng_rect.cc"
"${S2_SOURCE_DIR}/s2/s2latlng_rect_bounder.cc"
@ -93,59 +89,58 @@ set(S2_SRCS
"${S2_SOURCE_DIR}/s2/s2shape_index_buffered_region.cc"
"${S2_SOURCE_DIR}/s2/s2shape_index_measures.cc"
"${S2_SOURCE_DIR}/s2/s2shape_measures.cc"
"${S2_SOURCE_DIR}/s2/s2shape_nesting_query.cc"
"${S2_SOURCE_DIR}/s2/s2shapeutil_build_polygon_boundaries.cc"
"${S2_SOURCE_DIR}/s2/s2shapeutil_coding.cc"
"${S2_SOURCE_DIR}/s2/s2shapeutil_contains_brute_force.cc"
"${S2_SOURCE_DIR}/s2/s2shapeutil_conversion.cc"
"${S2_SOURCE_DIR}/s2/s2shapeutil_edge_iterator.cc"
"${S2_SOURCE_DIR}/s2/s2shapeutil_get_reference_point.cc"
"${S2_SOURCE_DIR}/s2/s2shapeutil_range_iterator.cc"
"${S2_SOURCE_DIR}/s2/s2shapeutil_visit_crossing_edge_pairs.cc"
"${S2_SOURCE_DIR}/s2/s2text_format.cc"
"${S2_SOURCE_DIR}/s2/s2wedge_relations.cc"
"${S2_SOURCE_DIR}/s2/s2winding_operation.cc"
"${S2_SOURCE_DIR}/s2/strings/serialize.cc"
"${S2_SOURCE_DIR}/s2/util/bits/bit-interleave.cc"
"${S2_SOURCE_DIR}/s2/util/bits/bits.cc"
"${S2_SOURCE_DIR}/s2/util/coding/coder.cc"
"${S2_SOURCE_DIR}/s2/util/coding/varint.cc"
"${S2_SOURCE_DIR}/s2/util/math/exactfloat/exactfloat.cc"
"${S2_SOURCE_DIR}/s2/util/math/mathutil.cc"
"${S2_SOURCE_DIR}/s2/util/units/length-units.cc"
)
add_library(_s2 ${S2_SRCS})
add_library(ch_contrib::s2 ALIAS _s2)
set_property(TARGET _s2 PROPERTY CXX_STANDARD 17)
if (TARGET OpenSSL::SSL)
target_link_libraries(_s2 PRIVATE OpenSSL::Crypto OpenSSL::SSL)
endif()
# Copied from contrib/s2geometry/CMakeLists
target_link_libraries(_s2 PRIVATE
absl::base
absl::btree
absl::config
absl::core_headers
absl::dynamic_annotations
absl::endian
absl::fixed_array
absl::flat_hash_map
absl::flat_hash_set
absl::hash
absl::inlined_vector
absl::int128
absl::log_severity
absl::memory
absl::span
absl::str_format
absl::strings
absl::type_traits
absl::utility
)
absl::base
absl::btree
absl::check
absl::config
absl::core_headers
absl::dynamic_annotations
absl::endian
absl::fixed_array
absl::flags
absl::flat_hash_map
absl::flat_hash_set
absl::hash
absl::inlined_vector
absl::int128
absl::log
absl::log_severity
absl::memory
absl::span
absl::status
absl::str_format
absl::strings
absl::type_traits
absl::utility
)
target_include_directories(_s2 SYSTEM BEFORE PUBLIC "${S2_SOURCE_DIR}/")
target_include_directories(_s2 SYSTEM PUBLIC "${ABSL_SOURCE_DIR}")

2
contrib/sysroot vendored

@ -1 +1 @@
Subproject commit e0d1b64da666afbfaa6f1ee0487c33f3fd2cd5cb
Subproject commit b5fcabb24d28fc33024291b2c6c1abd807c7dba8

2
contrib/usearch vendored

@ -1 +1 @@
Subproject commit f942b6f334b31716f9bdb02eb6a25fa6b222f5ba
Subproject commit 955c6f9c11adfd89c912e0d1643d160b4e9e543f

1
docker/packager/packager
View File

@ -325,7 +325,6 @@ def parse_env_variables(
if additional_pkgs:
# NOTE: This are the env for packages/build script
result.append("MAKE_APK=true")
result.append("MAKE_RPM=true")
result.append("MAKE_TGZ=true")

8
docker/test/base/setup_export_logs.sh
View File

@ -15,8 +15,8 @@ CLICKHOUSE_CI_LOGS_USER=${CLICKHOUSE_CI_LOGS_USER:-ci}
# Pre-configured destination cluster, where to export the data
CLICKHOUSE_CI_LOGS_CLUSTER=${CLICKHOUSE_CI_LOGS_CLUSTER:-system_logs_export}
EXTRA_COLUMNS=${EXTRA_COLUMNS:-"pull_request_number UInt32, commit_sha String, check_start_time DateTime, check_name LowCardinality(String), instance_type LowCardinality(String), "}
EXTRA_COLUMNS_EXPRESSION=${EXTRA_COLUMNS_EXPRESSION:-"0 AS pull_request_number, '' AS commit_sha, now() AS check_start_time, '' AS check_name, '' AS instance_type"}
EXTRA_COLUMNS=${EXTRA_COLUMNS:-"pull_request_number UInt32, commit_sha String, check_start_time DateTime, check_name LowCardinality(String), instance_type LowCardinality(String), instance_id String, "}
EXTRA_COLUMNS_EXPRESSION=${EXTRA_COLUMNS_EXPRESSION:-"0 AS pull_request_number, '' AS commit_sha, now() AS check_start_time, '' AS check_name, '' AS instance_type, '' AS instance_id"}
EXTRA_ORDER_BY_COLUMNS=${EXTRA_ORDER_BY_COLUMNS:-"check_name, "}
function __set_connection_args
@ -125,9 +125,9 @@ function setup_logs_replication
echo 'Create %_log tables'
clickhouse-client --query "SHOW TABLES FROM system LIKE '%\\_log'" | while read -r table
do
# Calculate hash of its structure:
# Calculate hash of its structure. Note: 1 is the version of extra columns - increment it if extra columns are changed:
hash=$(clickhouse-client --query "
SELECT sipHash64(groupArray((name, type)))
SELECT sipHash64(1, groupArray((name, type)))
FROM (SELECT name, type FROM system.columns
WHERE database = 'system' AND table = '$table'
ORDER BY position)

1
docker/test/fasttest/Dockerfile
View File

@ -18,6 +18,7 @@ RUN apt-get update \
python3-termcolor \
unixodbc \
pv \
jq \
zstd \
--yes --no-install-recommends

2
docker/test/fasttest/run.sh
View File

@ -120,7 +120,7 @@ function clone_submodules
contrib/libxml2
contrib/libunwind
contrib/fmtlib
contrib/base64
contrib/aklomp-base64
contrib/cctz
contrib/libcpuid
contrib/libdivide

20
docker/test/integration/mysql_java_client/Dockerfile
View File

@ -1,21 +1,15 @@
# docker build -t clickhouse/mysql-java-client .
# MySQL Java client docker container
FROM ubuntu:18.04
FROM openjdk:8-jdk-alpine
RUN apt-get update && \
apt-get install -y software-properties-common build-essential openjdk-8-jdk libmysql-java curl
RUN apk --no-cache add curl
RUN rm -rf \
/var/lib/apt/lists/* \
/var/cache/debconf \
/tmp/* \
RUN apt-get clean
ARG ver=5.1.46
RUN curl -L -o /mysql-connector-java-${ver}.jar https://repo1.maven.org/maven2/mysql/mysql-connector-java/${ver}/mysql-connector-java-${ver}.jar
ENV CLASSPATH=$CLASSPATH:/mysql-connector-java-${ver}.jar
ARG ver=8.1.0
RUN curl -L -o /mysql-connector-j-${ver}.jar https://repo1.maven.org/maven2/com/mysql/mysql-connector-j/${ver}/mysql-connector-j-${ver}.jar
ENV CLASSPATH=$CLASSPATH:/mysql-connector-j-${ver}.jar
WORKDIR /jdbc
COPY Test.java Test.java
RUN javac Test.java
COPY PreparedStatementsTest.java PreparedStatementsTest.java
RUN javac Test.java PreparedStatementsTest.java

193
docker/test/integration/mysql_java_client/PreparedStatementsTest.java Normal file
View File

@ -0,0 +1,193 @@
import com.mysql.cj.MysqlType;
import java.sql.*;
public class PreparedStatementsTest {
public static void main(String[] args) {
int i = 0;
String host = "127.0.0.1";
String port = "9004";
String user = "default";
String password = "";
String database = "default";
while (i < args.length) {
switch (args[i]) {
case "--host":
host = args[++i];
break;
case "--port":
port = args[++i];
break;
case "--user":
user = args[++i];
break;
case "--password":
password = args[++i];
break;
case "--database":
database = args[++i];
break;
default:
i++;
break;
}
}
// useServerPrepStmts uses COM_STMT_PREPARE and COM_STMT_EXECUTE
// instead of COM_QUERY which allows us to test the binary protocol
String jdbcUrl = String.format("jdbc:mysql://%s:%s/%s?useSSL=false&useServerPrepStmts=true",
host, port, database);
try {
Class.forName("com.mysql.cj.jdbc.Driver");
Connection conn = DriverManager.getConnection(jdbcUrl, user, password);
testSimpleDataTypes(conn);
testStringTypes(conn);
testLowCardinalityAndNullableTypes(conn);
testDecimalTypes(conn);
testMiscTypes(conn);
testDateTypes(conn);
testUnusualDateTime64Scales(conn);
testDateTimeTimezones(conn);
conn.close();
} catch (Exception e) {
e.printStackTrace();
System.exit(1);
}
}
private static void testSimpleDataTypes(Connection conn) throws SQLException {
System.out.println("### testSimpleDataTypes");
ResultSet rs = conn.prepareStatement("SELECT * FROM ps_simple_data_types").executeQuery();
int rowNum = 1;
while (rs.next()) {
System.out.printf("Row #%d\n", rowNum++);
System.out.printf("%s, value: %d\n", getMysqlType(rs, "i8"), rs.getInt("i8"));
System.out.printf("%s, value: %d\n", getMysqlType(rs, "i16"), rs.getInt("i16"));
System.out.printf("%s, value: %d\n", getMysqlType(rs, "i32"), rs.getInt("i32"));
System.out.printf("%s, value: %d\n", getMysqlType(rs, "i64"), rs.getLong("i64"));
System.out.printf("%s, value: %s\n", getMysqlType(rs, "i128"), rs.getString("i128"));
System.out.printf("%s, value: %s\n", getMysqlType(rs, "i256"), rs.getString("i256"));
System.out.printf("%s, value: %d\n", getMysqlType(rs, "ui8"), rs.getInt("ui8"));
System.out.printf("%s, value: %d\n", getMysqlType(rs, "ui16"), rs.getInt("ui16"));
System.out.printf("%s, value: %d\n", getMysqlType(rs, "ui32"), rs.getLong("ui32"));
System.out.printf("%s, value: %s\n", getMysqlType(rs, "ui64"), rs.getString("ui64"));
System.out.printf("%s, value: %s\n", getMysqlType(rs, "ui128"), rs.getString("ui128"));
System.out.printf("%s, value: %s\n", getMysqlType(rs, "ui256"), rs.getString("ui256"));
System.out.printf("%s, value: %f\n", getMysqlType(rs, "f32"), rs.getFloat("f32"));
System.out.printf("%s, value: %f\n", getMysqlType(rs, "f64"), rs.getFloat("f64"));
System.out.printf("%s, value: %b\n", getMysqlType(rs, "b"), rs.getBoolean("b"));
}
System.out.println();
}
private static void testStringTypes(Connection conn) throws SQLException {
System.out.println("### testStringTypes");
ResultSet rs = conn.prepareStatement("SELECT * FROM ps_string_types").executeQuery();
int rowNum = 1;
while (rs.next()) {
System.out.printf("Row #%d\n", rowNum++);
System.out.printf("%s, value: %s\n", getMysqlType(rs, "s"), rs.getString("s"));
System.out.printf("%s, value: %s\n", getMysqlType(rs, "sn"), rs.getString("sn"));
System.out.printf("%s, value: %s\n", getMysqlType(rs, "lc"), rs.getString("lc"));
System.out.printf("%s, value: %s\n", getMysqlType(rs, "nlc"), rs.getString("nlc"));
}
System.out.println();
}
private static void testLowCardinalityAndNullableTypes(Connection conn) throws SQLException {
System.out.println("### testLowCardinalityAndNullableTypes");
ResultSet rs = conn.prepareStatement("SELECT * FROM ps_low_cardinality_and_nullable_types").executeQuery();
int rowNum = 1;
while (rs.next()) {
System.out.printf("Row #%d\n", rowNum++);
System.out.printf("%s, value: %s\n", getMysqlType(rs, "ilc"), rs.getInt("ilc"));
System.out.printf("%s, value: %s\n", getMysqlType(rs, "dlc"), rs.getDate("dlc"));
// NULL int is represented as zero
System.out.printf("%s, value: %s\n", getMysqlType(rs, "ni"), rs.getInt("ni"));
}
System.out.println();
}
private static void testDecimalTypes(Connection conn) throws SQLException {
System.out.println("### testDecimalTypes");
ResultSet rs = conn.prepareStatement("SELECT * FROM ps_decimal_types").executeQuery();
int rowNum = 1;
while (rs.next()) {
System.out.printf("Row #%d\n", rowNum++);
System.out.printf("%s, value: %s\n", getMysqlType(rs, "d32"), rs.getBigDecimal("d32").toPlainString());
System.out.printf("%s, value: %s\n", getMysqlType(rs, "d64"), rs.getBigDecimal("d64").toPlainString());
System.out.printf("%s, value: %s\n", getMysqlType(rs, "d128_native"),
rs.getBigDecimal("d128_native").toPlainString());
System.out.printf("%s, value: %s\n", getMysqlType(rs, "d128_text"), rs.getString("d128_text"));
System.out.printf("%s, value: %s\n", getMysqlType(rs, "d256"), rs.getString("d256"));
}
System.out.println();
}
private static void testDateTypes(Connection conn) throws SQLException {
System.out.println("### testDateTypes");
ResultSet rs = conn.prepareStatement("SELECT * FROM ps_date_types").executeQuery();
int rowNum = 1;
while (rs.next()) {
System.out.printf("Row #%d\n", rowNum++);
System.out.printf("%s, value: %s\n", getMysqlType(rs, "d"), rs.getDate("d"));
System.out.printf("%s, value: %s\n", getMysqlType(rs, "d32"), rs.getDate("d32"));
System.out.printf("%s, value: %s\n", getMysqlType(rs, "dt"), rs.getTimestamp("dt"));
System.out.printf("%s, value: %s\n", getMysqlType(rs, "dt64_3"), rs.getTimestamp("dt64_3"));
System.out.printf("%s, value: %s\n", getMysqlType(rs, "dt64_6"), rs.getTimestamp("dt64_6"));
System.out.printf("%s, value: %s\n", getMysqlType(rs, "dt64_9"), rs.getTimestamp("dt64_9"));
}
System.out.println();
}
private static void testUnusualDateTime64Scales(Connection conn) throws SQLException {
System.out.println("### testUnusualDateTime64Scales");
ResultSet rs = conn.prepareStatement("SELECT * FROM ps_unusual_datetime64_scales").executeQuery();
int rowNum = 1;
while (rs.next()) {
System.out.printf("Row #%d\n", rowNum++);
System.out.printf("%s, value: %s\n", getMysqlType(rs, "dt64_0"), rs.getTimestamp("dt64_0"));
System.out.printf("%s, value: %s\n", getMysqlType(rs, "dt64_1"), rs.getTimestamp("dt64_1"));
System.out.printf("%s, value: %s\n", getMysqlType(rs, "dt64_2"), rs.getTimestamp("dt64_2"));
System.out.printf("%s, value: %s\n", getMysqlType(rs, "dt64_4"), rs.getTimestamp("dt64_4"));
System.out.printf("%s, value: %s\n", getMysqlType(rs, "dt64_5"), rs.getTimestamp("dt64_5"));
System.out.printf("%s, value: %s\n", getMysqlType(rs, "dt64_7"), rs.getTimestamp("dt64_7"));
System.out.printf("%s, value: %s\n", getMysqlType(rs, "dt64_8"), rs.getTimestamp("dt64_8"));
}
System.out.println();
}
private static void testDateTimeTimezones(Connection conn) throws SQLException {
System.out.println("### testDateTimeTimezones");
ResultSet rs = conn.prepareStatement("SELECT * FROM ps_datetime_timezones").executeQuery();
int rowNum = 1;
while (rs.next()) {
System.out.printf("Row #%d\n", rowNum++);
System.out.printf("%s, value: %s\n", getMysqlType(rs, "dt"), rs.getTimestamp("dt"));
System.out.printf("%s, value: %s\n", getMysqlType(rs, "dt64_3"), rs.getTimestamp("dt64_3"));
}
System.out.println();
}
private static void testMiscTypes(Connection conn) throws SQLException {
System.out.println("### testMiscTypes");
ResultSet rs = conn.prepareStatement("SELECT * FROM ps_misc_types").executeQuery();
int rowNum = 1;
while (rs.next()) {
System.out.printf("Row #%d\n", rowNum++);
System.out.printf("%s, value: %s\n", getMysqlType(rs, "a"), rs.getString("a"));
System.out.printf("%s, value: %s\n", getMysqlType(rs, "u"), rs.getString("u"));
System.out.printf("%s, value: %s\n", getMysqlType(rs, "t"), rs.getString("t"));
System.out.printf("%s, value: %s\n", getMysqlType(rs, "m"), rs.getString("m"));
}
System.out.println();
}
private static String getMysqlType(ResultSet rs, String columnLabel) throws SQLException {
ResultSetMetaData meta = rs.getMetaData();
return String.format("%s type is %s", columnLabel,
MysqlType.getByJdbcType(meta.getColumnType(rs.findColumn(columnLabel))));
}
}

3
docker/test/integration/mysql_java_client/Test.java
View File

@ -46,6 +46,7 @@ class JavaConnectorTest {
Connection conn = null;
Statement stmt = null;
try {
Class.forName("com.mysql.cj.jdbc.Driver");
conn = DriverManager.getConnection(jdbcUrl, user, password);
stmt = conn.createStatement();
stmt.executeUpdate(CREATE_TABLE_SQL);
@ -69,7 +70,7 @@ class JavaConnectorTest {
stmt.close();
conn.close();
} catch (SQLException e) {
} catch (Exception e) {
e.printStackTrace();
System.exit(1);
}

2
docker/test/integration/runner/compose/docker_compose_mysql_java_client.yml
View File

@ -3,4 +3,4 @@ services:
java1:
image: clickhouse/mysql-java-client:${DOCKER_MYSQL_JAVA_CLIENT_TAG:-latest}
# to keep container running
command: sleep infinity
command: sleep 1d

12
docker/test/performance-comparison/compare.sh
View File

@ -394,7 +394,7 @@ do
done
# for each query run, prepare array of metrics from query log
clickhouse-local --query "
clickhouse-local --multiquery --query "
create view query_runs as select * from file('analyze/query-runs.tsv', TSV,
'test text, query_index int, query_id text, version UInt8, time float');
@ -551,7 +551,7 @@ numactl --cpunodebind=all --membind=all numactl --show
# If the available memory falls below 2 * size, GNU parallel will suspend some of the running jobs.
numactl --cpunodebind=all --membind=all parallel -v --joblog analyze/parallel-log.txt --memsuspend 15G --null < analyze/commands.txt 2>> analyze/errors.log
clickhouse-local --query "
clickhouse-local --multiquery --query "
-- Join the metric names back to the metric statistics we've calculated, and make
-- a denormalized table of them -- statistics for all metrics for all queries.
-- The WITH, ARRAY JOIN and CROSS JOIN do not like each other:
@ -649,7 +649,7 @@ rm ./*.{rep,svg} test-times.tsv test-dump.tsv unstable.tsv unstable-query-ids.ts
cat analyze/errors.log >> report/errors.log ||:
cat profile-errors.log >> report/errors.log ||:
clickhouse-local --query "
clickhouse-local --multiquery --query "
create view query_display_names as select * from
file('analyze/query-display-names.tsv', TSV,
'test text, query_index int, query_display_name text')
@ -950,7 +950,7 @@ create table all_query_metrics_tsv engine File(TSV, 'report/all-query-metrics.ts
for version in {right,left}
do
rm -rf data
clickhouse-local --query "
clickhouse-local --multiquery --query "
create view query_profiles as
with 0 as left, 1 as right
select * from file('analyze/query-profiles.tsv', TSV,
@ -1120,7 +1120,7 @@ function report_metrics
rm -rf metrics ||:
mkdir metrics
clickhouse-local --query "
clickhouse-local --multiquery --query "
create view right_async_metric_log as
select * from file('right-async-metric-log.tsv', TSVWithNamesAndTypes)
;
@ -1180,7 +1180,7 @@ function upload_results
# Prepare info for the CI checks table.
rm -f ci-checks.tsv
clickhouse-local --query "
clickhouse-local --multiquery --query "
create view queries as select * from file('report/queries.tsv', TSVWithNamesAndTypes);
create table ci_checks engine File(TSVWithNamesAndTypes, 'ci-checks.tsv')

6
docker/test/stateless/Dockerfile
View File

@ -40,6 +40,7 @@ RUN apt-get update -y \
cargo \
zstd \
file \
jq \
pv \
zip \
p7zip-full \
@ -87,5 +88,10 @@ RUN npm install -g azurite \
COPY run.sh /
COPY setup_minio.sh /
COPY setup_hdfs_minicluster.sh /
COPY attach_gdb.lib /
COPY utils.lib /
# We store stress_tests.lib in stateless image to avoid duplication of this file in stress and upgrade tests
COPY stress_tests.lib /
CMD ["/bin/bash", "/run.sh"]

2
tests/ci/attach_gdb.lib → docker/test/stateless/attach_gdb.lib
View File

@ -1,6 +1,6 @@
#!/bin/bash
source /usr/share/clickhouse-test/ci/utils.lib
source /utils.lib
function attach_gdb_to_clickhouse()
{

4
docker/test/stateless/run.sh
View File

@ -22,10 +22,10 @@ dpkg -i package_folder/clickhouse-client_*.deb
ln -s /usr/share/clickhouse-test/clickhouse-test /usr/bin/clickhouse-test
# shellcheck disable=SC1091
source /usr/share/clickhouse-test/ci/attach_gdb.lib || true # FIXME: to not break old builds, clean on 2023-09-01
source /attach_gdb.lib
# shellcheck disable=SC1091
source /usr/share/clickhouse-test/ci/utils.lib || true # FIXME: to not break old builds, clean on 2023-09-01
source /utils.lib
# install test configs
/usr/share/clickhouse-test/config/install.sh

0
tests/ci/stress_tests.lib → docker/test/stateless/stress_tests.lib
View File

0
tests/ci/utils.lib → docker/test/stateless/utils.lib
View File

4
docker/test/stress/run.sh
View File

@ -16,8 +16,8 @@ ln -s /usr/share/clickhouse-test/clickhouse-test /usr/bin/clickhouse-test
# Stress tests and upgrade check uses similar code that was placed
# in a separate bash library. See tests/ci/stress_tests.lib
source /usr/share/clickhouse-test/ci/attach_gdb.lib
source /usr/share/clickhouse-test/ci/stress_tests.lib
source /attach_gdb.lib
source /stress_tests.lib
install_packages package_folder

16
docker/test/upgrade/run.sh
View File

@ -16,8 +16,8 @@ ln -s /usr/share/clickhouse-test/ci/get_previous_release_tag.py /usr/bin/get_pre
# Stress tests and upgrade check uses similar code that was placed
# in a separate bash library. See tests/ci/stress_tests.lib
source /usr/share/clickhouse-test/ci/attach_gdb.lib
source /usr/share/clickhouse-test/ci/stress_tests.lib
source /attach_gdb.lib
source /stress_tests.lib
azurite-blob --blobHost 0.0.0.0 --blobPort 10000 --debug /azurite_log &
./setup_minio.sh stateless # to have a proper environment
@ -60,6 +60,12 @@ install_packages previous_release_package_folder
# available for dump via clickhouse-local
configure
# async_replication setting doesn't exist on some older versions
sudo cat /etc/clickhouse-server/config.d/keeper_port.xml \
| sed "/<async_replication>1<\/async_replication>/d" \
> /etc/clickhouse-server/config.d/keeper_port.xml.tmp
sudo mv /etc/clickhouse-server/config.d/keeper_port.xml.tmp /etc/clickhouse-server/config.d/keeper_port.xml
# it contains some new settings, but we can safely remove it
rm /etc/clickhouse-server/config.d/merge_tree.xml
rm /etc/clickhouse-server/config.d/enable_wait_for_shutdown_replicated_tables.xml
@ -82,6 +88,12 @@ sudo cat /etc/clickhouse-server/config.d/keeper_port.xml \
> /etc/clickhouse-server/config.d/keeper_port.xml.tmp
sudo mv /etc/clickhouse-server/config.d/keeper_port.xml.tmp /etc/clickhouse-server/config.d/keeper_port.xml
# async_replication setting doesn't exist on some older versions
sudo cat /etc/clickhouse-server/config.d/keeper_port.xml \
| sed "/<async_replication>1<\/async_replication>/d" \
> /etc/clickhouse-server/config.d/keeper_port.xml.tmp
sudo mv /etc/clickhouse-server/config.d/keeper_port.xml.tmp /etc/clickhouse-server/config.d/keeper_port.xml
# But we still need default disk because some tables loaded only into it
sudo cat /etc/clickhouse-server/config.d/s3_storage_policy_by_default.xml \
| sed "s|<main><disk>s3</disk></main>|<main><disk>s3</disk></main><default><disk>default</disk></default>|" \

2
docs/en/engines/database-engines/replicated.md
View File

@ -37,6 +37,8 @@ When creating a new replica of the database, this replica creates tables by itse
[`ALTER TABLE FREEZE|ATTACH|FETCH|DROP|DROP DETACHED|DETACH PARTITION|PART`](../../sql-reference/statements/alter/partition.md) queries are allowed but not replicated. The database engine will only add/fetch/remove the partition/part to the current replica. However, if the table itself uses a Replicated table engine, then the data will be replicated after using `ATTACH`.
In case you need only configure a cluster without maintaining table replication, refer to [Cluster Discovery](../../operations/cluster-discovery.md) feature.
## Usage Example {#usage-example}
Creating a cluster with three hosts:

9
docs/en/engines/table-engines/mergetree-family/annindexes.md
View File

@ -252,7 +252,7 @@ CREATE TABLE table_with_usearch_index
(
id Int64,
vectors Array(Float32),
INDEX [ann_index_name] vectors TYPE usearch([Distance]) [GRANULARITY N]
INDEX [ann_index_name] vectors TYPE usearch([Distance[, ScalarKind]]) [GRANULARITY N]
)
ENGINE = MergeTree
ORDER BY id;
@ -265,7 +265,7 @@ CREATE TABLE table_with_usearch_index
(
id Int64,
vectors Tuple(Float32[, Float32[, ...]]),
INDEX [ann_index_name] vectors TYPE usearch([Distance]) [GRANULARITY N]
INDEX [ann_index_name] vectors TYPE usearch([Distance[, ScalarKind]]) [GRANULARITY N]
)
ENGINE = MergeTree
ORDER BY id;
@ -277,5 +277,8 @@ USearch currently supports two distance functions:
- `cosineDistance`, also called cosine similarity, is the cosine of the angle between two (non-zero) vectors
([Wikipedia](https://en.wikipedia.org/wiki/Cosine_similarity)).
USearch allows storing the vectors in reduced precision formats. Supported scalar kinds are `f64`, `f32`, `f16` or `i8`. If no scalar kind
was specified during index creation, `f16` is used as default.
For normalized data, `L2Distance` is usually a better choice, otherwise `cosineDistance` is recommended to compensate for scale. If no
distance function was specified during index creation, `L2Distance` is used as default.
distance function was specified during index creation, `L2Distance` is used as default.

4
docs/en/engines/table-engines/mergetree-family/mergetree.md
View File

@ -1139,6 +1139,8 @@ Optional parameters:
- `s3_max_put_burst` — Max number of requests that can be issued simultaneously before hitting request per second limit. By default (`0` value) equals to `s3_max_put_rps`.
- `s3_max_get_rps` — Maximum GET requests per second rate before throttling. Default value is `0` (unlimited).
- `s3_max_get_burst` — Max number of requests that can be issued simultaneously before hitting request per second limit. By default (`0` value) equals to `s3_max_get_rps`.
- `read_resource` — Resource name to be used for [scheduling](/docs/en/operations/workload-scheduling.md) of read requests to this disk. Default value is empty string (IO scheduling is not enabled for this disk).
- `write_resource` — Resource name to be used for [scheduling](/docs/en/operations/workload-scheduling.md) of write requests to this disk. Default value is empty string (IO scheduling is not enabled for this disk).
### Configuring the cache
@ -1248,6 +1250,8 @@ Limit parameters (mainly for internal usage):
Other parameters:
* `metadata_path` - Path on local FS to store metadata files for Blob Storage. Default value is `/var/lib/clickhouse/disks/<disk_name>/`.
* `skip_access_check` - If true, disk access checks will not be performed on disk start-up. Default value is `false`.
* `read_resource` — Resource name to be used for [scheduling](/docs/en/operations/workload-scheduling.md) of read requests to this disk. Default value is empty string (IO scheduling is not enabled for this disk).
* `write_resource` — Resource name to be used for [scheduling](/docs/en/operations/workload-scheduling.md) of write requests to this disk. Default value is empty string (IO scheduling is not enabled for this disk).
Examples of working configurations can be found in integration tests directory (see e.g. [test_merge_tree_azure_blob_storage](https://github.com/ClickHouse/ClickHouse/blob/master/tests/integration/test_merge_tree_azure_blob_storage/configs/config.d/storage_conf.xml) or [test_azure_blob_storage_zero_copy_replication](https://github.com/ClickHouse/ClickHouse/blob/master/tests/integration/test_azure_blob_storage_zero_copy_replication/configs/config.d/storage_conf.xml)).

6
docs/en/interfaces/cli.md
View File

@ -30,7 +30,7 @@ It may lack support for new features.
## Usage {#cli_usage}
The client can be used in interactive and non-interactive (batch) mode.
The client can be used in interactive and non-interactive (batch) mode.
### Gather your connection details
<ConnectionDetails />
@ -177,8 +177,8 @@ You can pass parameters to `clickhouse-client` (all parameters have a default va
- `--user, -u` – The username. Default value: default.
- `--password` – The password. Default value: empty string.
- `--ask-password` - Prompt the user to enter a password.
- `--query, -q` – The query to process when using non-interactive mode. Cannot be used simultaneously with `--queries-file`.
- `--queries-file` – file path with queries to execute. Cannot be used simultaneously with `--query`.
- `--query, -q` – The query to process when using non-interactive mode. `--query` can be specified multiple times, e.g. `--query "SELECT 1" --query "SELECT 2"`. Cannot be used simultaneously with `--queries-file`.
- `--queries-file` – file path with queries to execute. `--queries-file` can be specified multiple times, e.g. `--query queries1.sql --query queries2.sql`. Cannot be used simultaneously with `--query`.
- `--multiquery, -n` – If specified, multiple queries separated by semicolons can be listed after the `--query` option. For convenience, it is also possible to omit `--query` and pass the queries directly after `--multiquery`.
- `--multiline, -m` – If specified, allow multiline queries (do not send the query on Enter).
- `--database, -d` – Select the current default database. Default value: the current database from the server settings (‘default’ by default).

41
docs/en/interfaces/http.md
View File

@ -18,6 +18,8 @@ $ curl 'http://localhost:8123/'
Ok.
```
Also see: [HTTP response codes caveats](#http_response_codes_caveats).
Sometimes, `curl` command is not available on user operating systems. On Ubuntu or Debian, run `sudo apt install curl`. Please refer this [documentation](https://curl.se/download.html) to install it before running the examples.
Web UI can be accessed here: `http://localhost:8123/play`.
@ -56,7 +58,7 @@ Connection: Close
Content-Type: text/tab-separated-values; charset=UTF-8
X-ClickHouse-Server-Display-Name: clickhouse.ru-central1.internal
X-ClickHouse-Query-Id: 5abe861c-239c-467f-b955-8a201abb8b7f
X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","peak_memory_usage":"0"}
X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334,"peak_memory_usage":"0"}
1
```
@ -286,9 +288,9 @@ Similarly, you can use ClickHouse sessions in the HTTP protocol. To do this, you
You can receive information about the progress of a query in `X-ClickHouse-Progress` response headers. To do this, enable [send_progress_in_http_headers](../operations/settings/settings.md#settings-send_progress_in_http_headers). Example of the header sequence:
``` text
X-ClickHouse-Progress: {"read_rows":"2752512","read_bytes":"240570816","total_rows_to_read":"8880128","peak_memory_usage":"4371480"}
X-ClickHouse-Progress: {"read_rows":"5439488","read_bytes":"482285394","total_rows_to_read":"8880128","peak_memory_usage":"13621616"}
X-ClickHouse-Progress: {"read_rows":"8783786","read_bytes":"819092887","total_rows_to_read":"8880128","peak_memory_usage":"23155600"}
X-ClickHouse-Progress: {"read_rows":"2752512","read_bytes":"240570816","total_rows_to_read":"8880128","elapsed_ns":"662334","peak_memory_usage":"4371480"}
X-ClickHouse-Progress: {"read_rows":"5439488","read_bytes":"482285394","total_rows_to_read":"8880128","elapsed_ns":"992334","peak_memory_usage":"13621616"}
X-ClickHouse-Progress: {"read_rows":"8783786","read_bytes":"819092887","total_rows_to_read":"8880128","elapsed_ns":"1232334","peak_memory_usage":"23155600"}
```
Possible header fields:
@ -323,6 +325,27 @@ $ curl -sS 'http://localhost:8123/?max_result_bytes=4000000&buffer_size=3000000&
Use buffering to avoid situations where a query processing error occurred after the response code and HTTP headers were sent to the client. In this situation, an error message is written at the end of the response body, and on the client-side, the error can only be detected at the parsing stage.
## HTTP response codes caveats {#http_response_codes_caveats}
Because of limitation of HTTP protocol, HTTP 200 response code does not guarantee that a query was successful.
Here is an example:
```
curl -v -Ss "http://localhost:8123/?max_block_size=1&query=select+sleepEachRow(0.001),throwIf(number=2)from+numbers(5)"
* Trying 127.0.0.1:8123...
...
< HTTP/1.1 200 OK
...
Code: 395. DB::Exception: Value passed to 'throwIf' function is non-zero: while executing 'FUNCTION throwIf(equals(number, 2) :: 1) -> throwIf(equals(number, 2))
```
The reason for this behavior is the nature of the HTTP protocol. The HTTP header is sent first with an HTTP code of 200, followed by the HTTP body, and then the error is injected into the body as plain text.
This behavior is independent of the format used, whether it's `Native`, `TSV`, or `JSON`; the error message will always be in the middle of the response stream.
You can mitigate this problem by enabling `wait_end_of_query=1` ([Response Buffering](#response-buffering)). In this case, the sending of the HTTP header is delayed until the entire query is resolved.
However, this does not completely solve the problem because the result must still fit within the `http_response_buffer_size`, and other settings like `send_progress_in_http_headers` can interfere with the delay of the header.
The only way to catch all errors is to analyze the HTTP body before parsing it using the required format.
### Queries with Parameters {#cli-queries-with-parameters}
You can create a query with parameters and pass values for them from the corresponding HTTP request parameters. For more information, see [Queries with Parameters for CLI](../interfaces/cli.md#cli-queries-with-parameters).
@ -416,7 +439,7 @@ $ curl -v 'http://localhost:8123/predefined_query'
< X-ClickHouse-Format: Template
< X-ClickHouse-Timezone: Asia/Shanghai
< Keep-Alive: timeout=3
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","peak_memory_usage":"0"}
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334","peak_memory_usage":"0"}
<
# HELP "Query" "Number of executing queries"
# TYPE "Query" counter
@ -581,7 +604,7 @@ $ curl -vv -H 'XXX:xxx' 'http://localhost:8123/hi'
< Content-Type: text/html; charset=UTF-8
< Transfer-Encoding: chunked
< Keep-Alive: timeout=3
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","peak_memory_usage":"0"}
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334","peak_memory_usage":"0"}
<
* Connection #0 to host localhost left intact
Say Hi!%
@ -621,7 +644,7 @@ $ curl -v -H 'XXX:xxx' 'http://localhost:8123/get_config_static_handler'
< Content-Type: text/plain; charset=UTF-8
< Transfer-Encoding: chunked
< Keep-Alive: timeout=3
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","peak_memory_usage":"0"}
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334","peak_memory_usage":"0"}
<
* Connection #0 to host localhost left intact
<html ng-app="SMI2"><head><base href="http://ui.tabix.io/"></head><body><div ui-view="" class="content-ui"></div><script src="http://loader.tabix.io/master.js"></script></body></html>%
@ -673,7 +696,7 @@ $ curl -vv -H 'XXX:xxx' 'http://localhost:8123/get_absolute_path_static_handler'
< Content-Type: text/html; charset=UTF-8
< Transfer-Encoding: chunked
< Keep-Alive: timeout=3
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","peak_memory_usage":"0"}
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334","peak_memory_usage":"0"}
<
<html><body>Absolute Path File</body></html>
* Connection #0 to host localhost left intact
@ -692,7 +715,7 @@ $ curl -vv -H 'XXX:xxx' 'http://localhost:8123/get_relative_path_static_handler'
< Content-Type: text/html; charset=UTF-8
< Transfer-Encoding: chunked
< Keep-Alive: timeout=3
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","peak_memory_usage":"0"}
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334","peak_memory_usage":"0"}
<
<html><body>Relative Path File</body></html>
* Connection #0 to host localhost left intact

171
docs/en/operations/cluster-discovery.md Normal file
View File

@ -0,0 +1,171 @@
---
slug: /en/operations/cluster-discovery
sidebar_label: Cluster Discovery
---
# Cluster Discovery
## Overview
ClickHouse's Cluster Discovery feature simplifies cluster configuration by allowing nodes to automatically discover and register themselves without the need for explicit definition in the configuration files. This is especially beneficial in cases where the manual definition of each node becomes cumbersome.
:::note
Cluster Discovery is an experimental feature and can be changed or removed in future versions.
To enable it include the `allow_experimental_cluster_discovery` setting in your configuration file:
```xml
<clickhouse>
<!-- ... -->
<allow_experimental_cluster_discovery>1</allow_experimental_cluster_discovery>
<!-- ... -->
</clickhouse>
```
:::
## Remote Servers Configuration
### Traditional Manual Configuration
Traditionally, in ClickHouse, each shard and replica in the cluster needed to be manually specified in the configuration:
```xml
<remote_servers>
<cluster_name>
<shard>
<replica>
<host>node1</host>
<port>9000</port>
</replica>
<replica>
<host>node2</host>
<port>9000</port>
</replica>
</shard>
<shard>
<replica>
<host>node3</host>
<port>9000</port>
</replica>
<replica>
<host>node4</host>
<port>9000</port>
</replica>
</shard>
</cluster_name>
</remote_servers>
```
### Using Cluster Discovery
With Cluster Discovery, rather than defining each node explicitly, you simply specify a path in ZooKeeper. All nodes that register under this path in ZooKeeper will be automatically discovered and added to the cluster.
```xml
<remote_servers>
<cluster_name>
<discovery>
<path>/clickhouse/discovery/cluster_name</path>
</discovery>
</cluster_name>
</remote_servers>
```
If you want to specify a shard number for a particular node, you can include the `<shard>` tag within the `<discovery>` section:
for `node1` and `node2`:
```xml
<discovery>
<path>/clickhouse/discovery/cluster_name</path>
<shard>1</shard>
</discovery>
```
for `node3` and `node4`:
```xml
<discovery>
<path>/clickhouse/discovery/cluster_name</path>
<shard>2</shard>
</discovery>
```
### Observer mode
Nodes configured in observer mode will not register themselves as replicas.
They will solely observe and discover other active replicas in the cluster without actively participating.
To enable observer mode, include the `<observer/>` tag within the `<discovery>` section:
```xml
<discovery>
<path>/clickhouse/discovery/cluster_name</path>
<observer/>
</discovery>
```
## Use-Cases and Limitations
As nodes are added or removed from the specified ZooKeeper path, they are automatically discovered or removed from the cluster without the need for configuration changes or server restarts.
However, changes affect only cluster configuration, not the data or existing databases and tables.
Consider the following example with a cluster of 3 nodes:
```xml
<remote_servers>
<default>
<discovery>
<path>/clickhouse/discovery/default_cluster</path>
</discovery>
</default>
</remote_servers>
```
```
SELECT * EXCEPT (default_database, errors_count, slowdowns_count, estimated_recovery_time, database_shard_name, database_replica_name)
FROM system.clusters WHERE cluster = 'default';
┌─cluster─┬─shard_num─┬─shard_weight─┬─replica_num─┬─host_name────┬─host_address─┬─port─┬─is_local─┬─user─┬─is_active─┐
│ default │ 1 │ 1 │ 1 │ 92d3c04025e8 │ 172.26.0.5 │ 9000 │ 0 │ │ ᴺᵁᴸᴸ │
│ default │ 1 │ 1 │ 2 │ a6a68731c21b │ 172.26.0.4 │ 9000 │ 1 │ │ ᴺᵁᴸᴸ │
│ default │ 1 │ 1 │ 3 │ 8e62b9cb17a1 │ 172.26.0.2 │ 9000 │ 0 │ │ ᴺᵁᴸᴸ │
└─────────┴───────────┴──────────────┴─────────────┴──────────────┴──────────────┴──────┴──────────┴──────┴───────────┘
```
```sql
CREATE TABLE event_table ON CLUSTER default (event_time DateTime, value String)
ENGINE = ReplicatedMergeTree('/clickhouse/tables/event_table', '{replica}')
ORDER BY event_time PARTITION BY toYYYYMM(event_time);
INSERT INTO event_table ...
```
Then, we add a new node to the cluster, starting a new node with the same entry in the `remote_servers` section in a configuration file:
```
┌─cluster─┬─shard_num─┬─shard_weight─┬─replica_num─┬─host_name────┬─host_address─┬─port─┬─is_local─┬─user─┬─is_active─┐
│ default │ 1 │ 1 │ 1 │ 92d3c04025e8 │ 172.26.0.5 │ 9000 │ 0 │ │ ᴺᵁᴸᴸ │
│ default │ 1 │ 1 │ 2 │ a6a68731c21b │ 172.26.0.4 │ 9000 │ 1 │ │ ᴺᵁᴸᴸ │
│ default │ 1 │ 1 │ 3 │ 8e62b9cb17a1 │ 172.26.0.2 │ 9000 │ 0 │ │ ᴺᵁᴸᴸ │
│ default │ 1 │ 1 │ 4 │ b0df3669b81f │ 172.26.0.6 │ 9000 │ 0 │ │ ᴺᵁᴸᴸ │
└─────────┴───────────┴──────────────┴─────────────┴──────────────┴──────────────┴──────┴──────────┴──────┴───────────┘
```
The fourth node is participating in the cluster, but table `event_table` still exists only on the first three nodes:
```sql
SELECT hostname(), database, table FROM clusterAllReplicas(default, system.tables) WHERE table = 'event_table' FORMAT PrettyCompactMonoBlock
┌─hostname()───┬─database─┬─table───────┐
│ a6a68731c21b │ default │ event_table │
│ 92d3c04025e8 │ default │ event_table │
│ 8e62b9cb17a1 │ default │ event_table │
└──────────────┴──────────┴─────────────┘
```
If you need to have tables replicated on all the nodes, you may use the [Replicated](../engines/database-engines/replicated.md) database engine in alternative to cluster discovery.

2
docs/en/operations/optimizing-performance/sampling-query-profiler.md
View File

@ -11,6 +11,8 @@ ClickHouse runs sampling profiler that allows analyzing query execution. Using p
Query profiler is automatically enabled in ClickHouse Cloud and you can run a sample query as follows
:::note If you are running the following query in ClickHouse Cloud, make sure to change `FROM system.trace_log` to `FROM clusterAllReplicas(default, system.trace_log)` to select from all nodes of the cluster :::
``` sql
SELECT
count(),

12
docs/en/operations/server-configuration-parameters/settings.md
View File

@ -88,7 +88,7 @@ Default: 2
## background_merges_mutations_scheduling_policy
The policy on how to perform a scheduling for background merges and mutations. Possible values are: `round_robin` and `shortest_task_first`.
The policy on how to perform a scheduling for background merges and mutations. Possible values are: `round_robin` and `shortest_task_first`.
## background_merges_mutations_scheduling_policy
@ -583,7 +583,7 @@ Both the cache for `local_disk`, and temporary data will be stored in `/tiny_loc
Type: String
Default:
Default:
## thread_pool_queue_size
@ -640,7 +640,7 @@ When `/disk1` is full, temporary data will be stored on `/disk2`.
```
Type: String
Default:
Default:
## uncompressed_cache_policy
@ -1948,7 +1948,7 @@ If the table does not exist, ClickHouse will create it. If the structure of the
<flush_interval_milliseconds>7500</flush_interval_milliseconds>
<max_size_rows>1048576</max_size_rows>
<reserved_size_rows>8192</reserved_size_rows>
<buffer_size_rows_flush_threshold>524288</buffer_size_rows_flush_threshold>
<buffer_size_rows_flush_threshold>524288</buffer_size_rows_flush_threshold>
<flush_on_crash>false</flush_on_crash>
</query_thread_log>
```
@ -2236,6 +2236,8 @@ For the value of the `incl` attribute, see the section “[Configuration files](
**See Also**
- [skip_unavailable_shards](../../operations/settings/settings.md#settings-skip_unavailable_shards)
- [Cluster Discovery](../../operations/cluster-discovery.md)
- [Replicated database engine](../../engines/database-engines/replicated.md)
## timezone {#server_configuration_parameters-timezone}
@ -2404,7 +2406,7 @@ This section contains the following parameters:
* nearest_hostname - selects a ZooKeeper node with a hostname that is most similar to the server’s hostname.
* first_or_random - selects the first ZooKeeper node, if it's not available then randomly selects one of remaining ZooKeeper nodes.
* round_robin - selects the first ZooKeeper node, if reconnection happens selects the next.
**Example configuration**
``` xml

2
docs/en/operations/settings/merge-tree-settings.md
View File

@ -71,7 +71,7 @@ Possible values:
- Any positive integer.
Default value: 150.
Default value: 1000.
ClickHouse artificially executes `INSERT` longer (adds ‘sleep’) so that the background merge process can merge parts faster than they are added.

49
docs/en/operations/settings/settings.md
View File

@ -4644,6 +4644,14 @@ SELECT toFloat64('1.7091'), toFloat64('1.5008753E7') SETTINGS precise_float_pars
└─────────────────────┴──────────────────────────┘
```
## partial_result_update_duration_ms
Interval (in milliseconds) for sending updates with partial data about the result table to the client (in interactive mode) during query execution. Setting to 0 disables partial results. Only supported for single-threaded GROUP BY without key, ORDER BY, LIMIT and OFFSET.
## max_rows_in_partial_result
Maximum rows to show in the partial result after every real-time update while the query runs (use partial result limit + OFFSET as a value in case of OFFSET in the query).
## validate_tcp_client_information {#validate-tcp-client-information}
Determines whether validation of client information enabled when query packet is received from a client using a TCP connection.
@ -4659,3 +4667,44 @@ The default value is `false`.
``` xml
<validate_tcp_client_information>true</validate_tcp_client_information>
```
## ignore_access_denied_multidirectory_globs {#ignore_access_denied_multidirectory_globs}
Allows to ignore 'permission denied' errors when using multi-directory `{}` globs for [File](../../sql-reference/table-functions/file.md#globs_in_path) and [HDFS](../../sql-reference/table-functions/hdfs.md) storages.
This setting is only applicable to multi directory `{}` globs.
Possible values: `0`, `1`.
Default value: `0`.
### Example
Having the following structure in `user_files`:
```
my_directory/
├── data1
│ ├── f1.csv
├── data2
│ ├── f2.csv
└── test_root
```
where `data1`, `data2` directories are accessible, but one has no rights to read `test_root` directories.
For a query like `SELECT *, _path, _file FROM file('my_directory/{data1/f1,data2/f2}.csv', CSV)` an exception will be thrown:
`Code: 1001. DB::Exception: std::__1::__fs::filesystem::filesystem_error: filesystem error: in directory_iterator::directory_iterator(...): Permission denied`.
It happens because a multi-directory glob requires a recursive search in _all_ available directories under `my_directory`.
If this setting is on, all inaccessible directories will be silently skipped, even if they are explicitly specified inside `{}`.
```sql
SELECT _path, _file FROM file('my_directory/{data1/f1,data2/f2}.csv', CSV) SETTINGS ignore_access_denied_multidirectory_globs = 0;
Code: 1001. DB::Exception: std::__1::__fs::filesystem::filesystem_error: filesystem error: in directory_iterator::directory_iterator(...): Permission denied
```
```sql
SELECT _path, _file FROM file('my_directory/{data1/f1,data2/f2}.csv', CSV) SETTINGS ignore_access_denied_multidirectory_globs = 1;
┌─_path───────────────────┬─_file───────┐
│ <full path to file> │ <file name> │
└─────────────────────────┴─────────────┘
```

13
docs/en/operations/system-tables/information_schema.md
View File

@ -3,12 +3,13 @@ slug: /en/operations/system-tables/information_schema
---
# INFORMATION_SCHEMA
`INFORMATION_SCHEMA` (`information_schema`) is a system database that contains views. Using these views, you can get information about the metadata of database objects. These views read data from the columns of the [system.columns](../../operations/system-tables/columns.md), [system.databases](../../operations/system-tables/databases.md) and [system.tables](../../operations/system-tables/tables.md) system tables.
The structure and composition of system tables may change in different versions of the product, but the support of the `information_schema` makes it possible to change the structure of system tables without changing the method of access to metadata. Metadata requests do not depend on the DBMS used.
`INFORMATION_SCHEMA` (or: `information_schema`) is a system database which provides a (somewhat) standardized, [DBMS-agnostic view](https://en.wikipedia.org/wiki/Information_schema) on metadata of database objects. The views in `INFORMATION_SCHEMA` are generally inferior to normal system tables but tools can use them to obtain basic information in a cross-DBMS manner. The structure and content of views in `INFORMATION_SCHEMA` is supposed to evolves in a backwards-compatible way, i.e. only new functionality is added but existing functionality is not changed or removed. In terms of internal implementation, views in `INFORMATION_SCHEMA` usually map to to normal system tables like [system.columns](../../operations/system-tables/columns.md), [system.databases](../../operations/system-tables/databases.md) and [system.tables](../../operations/system-tables/tables.md).
``` sql
SHOW TABLES FROM INFORMATION_SCHEMA;
-- or:
SHOW TABLES FROM information_schema;
```
``` text
@ -17,6 +18,10 @@ SHOW TABLES FROM INFORMATION_SCHEMA;
│ SCHEMATA │
│ TABLES │
│ VIEWS │
│ columns │
│ schemata │
│ tables │
│ views │
└──────────┘
```
@ -27,6 +32,8 @@ SHOW TABLES FROM INFORMATION_SCHEMA;
- [TABLES](#tables)
- [VIEWS](#views)
Case-insensitive equivalent views, e.g. `INFORMATION_SCHEMA.columns` are provided for reasons of compatibility with other databases.
## COLUMNS {#columns}
Contains columns read from the [system.columns](../../operations/system-tables/columns.md) system table and columns that are not supported in ClickHouse or do not make sense (always `NULL`), but must be by the standard.

17
docs/en/operations/system-tables/licenses.md
View File

@ -1,7 +1,7 @@
---
slug: /en/operations/system-tables/licenses
---
# licenses
# licenses
Contains licenses of third-party libraries that are located in the [contrib](https://github.com/ClickHouse/ClickHouse/tree/master/contrib) directory of ClickHouse sources.
@ -20,21 +20,10 @@ SELECT library_name, license_type, license_path FROM system.licenses LIMIT 15
``` text
┌─library_name───────┬─license_type─┬─license_path────────────────────────┐
│ FastMemcpy │ MIT │ /contrib/FastMemcpy/LICENSE │
│ arrow │ Apache │ /contrib/arrow/LICENSE.txt │
│ avro │ Apache │ /contrib/avro/LICENSE.txt │
│ aws-c-common │ Apache │ /contrib/aws-c-common/LICENSE │
│ aws-c-event-stream │ Apache │ /contrib/aws-c-event-stream/LICENSE │
│ aws-checksums │ Apache │ /contrib/aws-checksums/LICENSE │
│ aws │ Apache │ /contrib/aws/LICENSE.txt │
│ base64 │ BSD 2-clause │ /contrib/base64/LICENSE │
│ boost │ Boost │ /contrib/boost/LICENSE_1_0.txt │
│ base64 │ BSD 2-clause │ /contrib/aklomp-base64/LICENSE │
│ brotli │ MIT │ /contrib/brotli/LICENSE │
│ capnproto │ MIT │ /contrib/capnproto/LICENSE │
│ cassandra │ Apache │ /contrib/cassandra/LICENSE.txt │
│ cctz │ Apache │ /contrib/cctz/LICENSE.txt │
│ cityhash102 │ MIT │ /contrib/cityhash102/COPYING │
│ cppkafka │ BSD 2-clause │ /contrib/cppkafka/LICENSE │
│ [...] │ [...] │ [...] │
└────────────────────┴──────────────┴─────────────────────────────────────┘
```

3
docs/en/operations/system-tables/query_log.md
View File

@ -101,7 +101,8 @@ Columns:
- `ProfileEvents` ([Map(String, UInt64)](../../sql-reference/data-types/map.md)) — ProfileEvents that measure different metrics. The description of them could be found in the table [system.events](../../operations/system-tables/events.md#system_tables-events)
- `Settings` ([Map(String, String)](../../sql-reference/data-types/map.md)) — Settings that were changed when the client ran the query. To enable logging changes to settings, set the `log_query_settings` parameter to 1.
- `log_comment` ([String](../../sql-reference/data-types/string.md)) — Log comment. It can be set to arbitrary string no longer than [max_query_size](../../operations/settings/settings.md#settings-max_query_size). An empty string if it is not defined.
- `thread_ids` ([Array(UInt64)](../../sql-reference/data-types/array.md)) — Thread ids that are participating in query execution.
- `thread_ids` ([Array(UInt64)](../../sql-reference/data-types/array.md)) — Thread ids that are participating in query execution. These threads may not have run simultaneously.
- `peak_threads_usage` ([UInt64)](../../sql-reference/data-types/int-uint.md)) — Maximum count of simultaneous threads executing the query.
- `used_aggregate_functions` ([Array(String)](../../sql-reference/data-types/array.md)) — Canonical names of `aggregate functions`, which were used during query execution.
- `used_aggregate_function_combinators` ([Array(String)](../../sql-reference/data-types/array.md)) — Canonical names of `aggregate functions combinators`, which were used during query execution.
- `used_database_engines` ([Array(String)](../../sql-reference/data-types/array.md)) — Canonical names of `database engines`, which were used during query execution.

64
docs/en/operations/system-tables/scheduler.md Normal file
View File

@ -0,0 +1,64 @@
---
slug: /en/operations/system-tables/scheduler
---
# scheduler
Contains information and status for [scheduling nodes](/docs/en/operations/workload-scheduling.md/#hierarchy) residing on the local server.
This table can be used for monitoring. The table contains a row for every scheduling node.
Example:
``` sql
SELECT *
FROM system.scheduler
WHERE resource = 'network_read' AND path = '/prio/fair/prod'
FORMAT Vertical
```
``` text
Row 1:
──────
resource: network_read
path: /prio/fair/prod
type: fifo
weight: 5
priority: 0
is_active: 0
active_children: 0
dequeued_requests: 67
dequeued_cost: 4692272
busy_periods: 63
vruntime: 938454.1999999989
system_vruntime: ᴺᵁᴸᴸ
queue_length: 0
queue_cost: 0
budget: -60524
is_satisfied: ᴺᵁᴸᴸ
inflight_requests: ᴺᵁᴸᴸ
inflight_cost: ᴺᵁᴸᴸ
max_requests: ᴺᵁᴸᴸ
max_cost: ᴺᵁᴸᴸ
```
Columns:
- `resource` (`String`) - Resource name
- `path` (`String`) - Path to a scheduling node within this resource scheduling hierarchy
- `type` (`String`) - Type of a scheduling node.
- `weight` (`Float64`) - Weight of a node, used by a parent node of `fair`` type.
- `priority` (`Int64`) - Priority of a node, used by a parent node of 'priority' type (Lower value means higher priority).
- `is_active` (`UInt8`) - Whether this node is currently active - has resource requests to be dequeued and constraints satisfied.
- `active_children` (`UInt64`) - The number of children in active state.
- `dequeued_requests` (`UInt64`) - The total number of resource requests dequeued from this node.
- `dequeued_cost` (`UInt64`) - The sum of costs (e.g. size in bytes) of all requests dequeued from this node.
- `busy_periods` (`UInt64`) - The total number of deactivations of this node.
- `vruntime` (`Nullable(Float64)`) - For children of `fair` nodes only. Virtual runtime of a node used by SFQ algorithm to select the next child to process in a max-min fair manner.
- `system_vruntime` (`Nullable(Float64)`) - For `fair` nodes only. Virtual runtime showing `vruntime` of the last processed resource request. Used during child activation as the new value of `vruntime`.
- `queue_length` (`Nullable(UInt64)`) - For `fifo` nodes only. Current number of resource requests residing in the queue.
- `queue_cost` (`Nullable(UInt64)`) - For `fifo` nodes only. Sum of costs (e.g. size in bytes) of all requests residing in the queue.
- `budget` (`Nullable(Int64)`) - For `fifo` nodes only. The number of available "cost units" for new resource requests. Can appear in case of discrepancy of estimated and real costs of resource requests (e.g. after read/write failure)
- `is_satisfied` (`Nullable(UInt8)`) - For constraint nodes only (e.g. `inflight_limit`). Equals `1` if all the constraint of this node are satisfied.
- `inflight_requests` (`Nullable(Int64)`) - For `inflight_limit` nodes only. The number of resource requests dequeued from this node, that are currently in consumption state.
- `inflight_cost` (`Nullable(Int64)`) - For `inflight_limit` nodes only. The sum of costs (e.g. bytes) of all resource requests dequeued from this node, that are currently in consumption state.
- `max_requests` (`Nullable(Int64)`) - For `inflight_limit` nodes only. Upper limit for `inflight_requests` leading to constraint violation.
- `max_cost` (`Nullable(Int64)`) - For `inflight_limit` nodes only. Upper limit for `inflight_cost` leading to constraint violation.

11
docs/en/operations/utilities/clickhouse-keeper-client.md
View File

@ -16,6 +16,8 @@ A client application to interact with clickhouse-keeper by its native protocol.
- `--session-timeout=TIMEOUT` — Set session timeout in seconds. Default value: 10s.
- `--operation-timeout=TIMEOUT` — Set operation timeout in seconds. Default value: 10s.
- `--history-file=FILE_PATH` — Set path of history file. Default value: `~/.keeper-client-history`.
- `--log-level=LEVEL` — Set log level. Default value: `information`.
- `--no-confirmation` — If set, will not require a confirmation on several commands. Default value `false` for interactive and `true` for query
- `--help` — Shows the help message.
## Example {#clickhouse-keeper-client-example}
@ -43,12 +45,13 @@ keeper foo bar
## Commands {#clickhouse-keeper-client-commands}
- `ls [path]` -- Lists the nodes for the given path (default: cwd)
- `cd [path]` -- Change the working path (default `.`)
- `set <path> <value> [version]` -- Updates the node's value. Only update if version matches (default: -1)
- `cd [path]` -- Changes the working path (default `.`)
- `exists <path>` -- Returns `1` if node exists, `0` otherwise
- `set <path> <value> [version]` -- Updates the node's value. Only updates if version matches (default: -1)
- `create <path> <value> [mode]` -- Creates new node with the set value
- `touch <path>` -- Creates new node with an empty string as value. Doesn't throw an exception if the node already exists
- `get <path>` -- Returns the node's value
- `remove <path>` -- Remove the node
- `rm <path> [version]` -- Removes the node only if version matches (default: -1)
- `rmr <path>` -- Recursively deletes path. Confirmation required
- `flwc <command>` -- Executes four-letter-word command
- `help` -- Prints this message
@ -56,3 +59,5 @@ keeper foo bar
- `find_super_nodes <threshold> [path]` -- Finds nodes with number of children larger than some threshold for the given path (default `.`)
- `delete_stale_backups` -- Deletes ClickHouse nodes used for backups that are now inactive
- `find_big_family [path] [n]` -- Returns the top n nodes with the biggest family in the subtree (default path = `.` and n = 10)
- `sync <path>` -- Synchronizes node between processes and leader
- `reconfig <add|remove|set> "<arg>" [version]` -- Reconfigure Keeper cluster. See https://clickhouse.com/docs/en/guides/sre/keeper/clickhouse-keeper#reconfiguration

4
docs/en/operations/utilities/clickhouse-local.md
View File

@ -202,8 +202,8 @@ Arguments:
- `-S`, `--structure` — table structure for input data.
- `--input-format` — input format, `TSV` by default.
- `-f`, `--file` — path to data, `stdin` by default.
- `-q`, `--query` — queries to execute with `;` as delimiter. Cannot be used simultaneously with `--queries-file`.
- `--queries-file` - file path with queries to execute. Cannot be used simultaneously with `--query`.
- `-q`, `--query` — queries to execute with `;` as delimiter. `--query` can be specified multiple times, e.g. `--query "SELECT 1" --query "SELECT 2"`. Cannot be used simultaneously with `--queries-file`.
- `--queries-file` - file path with queries to execute. `--queries-file` can be specified multiple times, e.g. `--query queries1.sql --query queries2.sql`. Cannot be used simultaneously with `--query`.
- `--multiquery, -n` – If specified, multiple queries separated by semicolons can be listed after the `--query` option. For convenience, it is also possible to omit `--query` and pass the queries directly after `--multiquery`.
- `-N`, `--table` — table name where to put output data, `table` by default.
- `--format`, `--output-format` — output format, `TSV` by default.

153
docs/en/operations/workload-scheduling.md Normal file
View File

@ -0,0 +1,153 @@
---
slug: /en/operations/workload-scheduling
sidebar_position: 69
sidebar_label: "Workload scheduling"
title: "Workload scheduling"
---
When ClickHouse execute multiple queries simultaneously, they may be using shared resources (e.g. disks). Scheduling constraints and policies can be applied to regulate how resources are utilized and shared between different workloads. For every resource a scheduling hierarchy can be configured. Hierarchy root represents a resource, while leafs are queues, holding requests that exceed resource capacity.
:::note
Currently only remote disk IO can be scheduled using described method. For CPU scheduling see settings about thread pools and [`concurrent_threads_soft_limit_num`](server-configuration-parameters/settings.md#concurrent_threads_soft_limit_num). For flexible memory limits see [Memory overcommit](settings/memory-overcommit.md)
:::
## Disk configuration {#disk-config}
To enable IO scheduling for a specific disk, you have to specify `read_resource` and/or `write_resource` in storage configuration. It says ClickHouse what resource should be used for every read and write requests with given disk. Read and write resource can refer to the same resource name, which is useful for local SSDs or HDDs. Multiple different disks also can refer to the same resource, which is useful for remote disks: if you want to be able to allow fair division of network bandwidth between e.g. "production" and "development" workloads.
Example:
```xml
<clickhouse>
<storage_configuration>
...
<disks>
<s3>
<type>s3</type>
<endpoint>https://clickhouse-public-datasets.s3.amazonaws.com/my-bucket/root-path/</endpoint>
<access_key_id>your_access_key_id</access_key_id>
<secret_access_key>your_secret_access_key</secret_access_key>
<read_resource>network_read</read_resource>
<write_resource>network_write</write_resource>
</s3>
</disks>
<policies>
<s3_main>
<volumes>
<main>
<disk>s3</disk>
</main>
</volumes>
</s3_main>
</policies>
</storage_configuration>
</clickhouse>
```
## Workload markup {#workload_markup}
Queries can be marked with setting `workload` to distinguish different workloads. If `workload` is not set, than value "default" is used. Note that you are able to specify the other value using settings profiles. Setting constraints can be used to make `workload` constant if you want all queries from the user to be marked with fixed value of `workload` setting.
Let's consider an example of a system with two different workloads: "production" and "development".
```sql
SELECT count() FROM my_table WHERE value = 42 SETTINGS workload = 'production'
SELECT count() FROM my_table WHERE value = 13 SETTINGS workload = 'development'
```
## Resource scheduling hierarchy {#hierarchy}
From the standpoint of scheduling subsystem a resource represents a hierarchy of scheduling nodes.
```mermaid
graph TD
subgraph network_read
nr_root(("/"))
-->|100 concurrent requests| nr_fair("fair")
-->|75% bandwidth| nr_prod["prod"]
nr_fair
-->|25% bandwidth| nr_dev["dev"]
end
subgraph network_write
nw_root(("/"))
-->|100 concurrent requests| nw_fair("fair")
-->|75% bandwidth| nw_prod["prod"]
nw_fair
-->|25% bandwidth| nw_dev["dev"]
end
```
**Possible node types:**
* `inflight_limit` (constraint) - blocks if either number of concurrent in-flight requests exceeds `max_requests`, or their total cost exceeds `max_cost`; must have a single child.
* `fair` (policy) - selects the next request to serve from one of its children nodes according to max-min fairness; children nodes can specify `weight` (default is 1).
* `priority` (policy) - selects the next request to serve from one of its children nodes according to static priorities (lower value means higher priority); children nodes can specify `priority` (default is 0).
* `fifo` (queue) - leaf of the hierarchy capable of holding requests that exceed resource capacity.
The following example shows how to define IO scheduling hierarchies shown in the picture:
```xml
<clickhouse>
<resources>
<network_read>
<node path="/">
<type>inflight_limit</type>
<max_requests>100</max_requests>
</node>
<node path="/fair">
<type>fair</type>
</node>
<node path="/fair/prod">
<type>fifo</type>
<weight>3</weight>
</node>
<node path="/fair/dev">
<type>fifo</type>
</node>
</network_read>
<network_write>
<node path="/">
<type>inflight_limit</type>
<max_requests>100</max_requests>
</node>
<node path="/fair">
<type>fair</type>
</node>
<node path="/fair/prod">
<type>fifo</type>
<weight>3</weight>
</node>
<node path="/fair/dev">
<type>fifo</type>
</node>
</network_write>
</resources>
</clickhouse>
```
## Workload classifiers {#workload_classifiers}
Workload classifiers are used to define mapping from `workload` specified by a query into leaf-queues that should be used for specific resources. At the moment, workload classification is simple: only static mapping is available.
Example:
```xml
<clickhouse>
<workload_classifiers>
<production>
<network_read>/fair/prod</network_read>
<network_write>/fair/prod</network_write>
</production>
<development>
<network_read>/fair/dev</network_read>
<network_write>/fair/dev</network_write>
</development>
<default>
<network_read>/fair/dev</network_read>
<network_write>/fair/dev</network_write>
</default>
</workload_classifiers>
</clickhouse>
```
## See also
- [system.scheduler](/docs/en/operations/system-tables/scheduler.md)

2
docs/en/sql-reference/aggregate-functions/reference/grouparray.md
View File

@ -12,7 +12,7 @@ Values can be added to the array in any (indeterminate) order.
The second version (with the `max_size` parameter) limits the size of the resulting array to `max_size` elements. For example, `groupArray(1)(x)` is equivalent to `[any (x)]`.
In some cases, you can still rely on the order of execution. This applies to cases when `SELECT` comes from a subquery that uses `ORDER BY`.
In some cases, you can still rely on the order of execution. This applies to cases when `SELECT` comes from a subquery that uses `ORDER BY` if the subquery result is small enough.
**Example**

2
docs/en/sql-reference/aggregate-functions/reference/grouparraylast.md
View File

@ -10,7 +10,7 @@ Syntax: `groupArrayLast(max_size)(x)`
Creates an array of last argument values.
For example, `groupArrayLast(1)(x)` is equivalent to `[anyLast (x)]`.
In some cases, you can still rely on the order of execution. This applies to cases when `SELECT` comes from a subquery that uses `ORDER BY`.
In some cases, you can still rely on the order of execution. This applies to cases when `SELECT` comes from a subquery that uses `ORDER BY` if the subquery result is small enough.
**Example**

6
docs/en/sql-reference/aggregate-functions/reference/stddevpop.md
View File

@ -7,6 +7,10 @@ sidebar_position: 30
The result is equal to the square root of [varPop](../../../sql-reference/aggregate-functions/reference/varpop.md).
:::note
Alias:
- `STD`
- `STDDEV_POP`
:::note
This function uses a numerically unstable algorithm. If you need [numerical stability](https://en.wikipedia.org/wiki/Numerical_stability) in calculations, use the `stddevPopStable` function. It works slower but provides a lower computational error.
:::

4
docs/en/sql-reference/aggregate-functions/reference/stddevsamp.md
View File

@ -7,6 +7,8 @@ sidebar_position: 31
The result is equal to the square root of [varSamp](../../../sql-reference/aggregate-functions/reference/varsamp.md).
:::note
Alias: `STDDEV_SAMP`.
:::note
This function uses a numerically unstable algorithm. If you need [numerical stability](https://en.wikipedia.org/wiki/Numerical_stability) in calculations, use the `stddevSampStable` function. It works slower but provides a lower computational error.
:::

4
docs/en/sql-reference/aggregate-functions/reference/varpop.md
View File

@ -9,6 +9,8 @@ Calculates the amount `Σ((x - x̅)^2) / n`, where `n` is the sample size and `x
In other words, dispersion for a set of values. Returns `Float64`.
:::note
Alias: `VAR_POP`.
:::note
This function uses a numerically unstable algorithm. If you need [numerical stability](https://en.wikipedia.org/wiki/Numerical_stability) in calculations, use the `varPopStable` function. It works slower but provides a lower computational error.
:::

4
docs/en/sql-reference/aggregate-functions/reference/varsamp.md
View File

@ -11,6 +11,8 @@ It represents an unbiased estimate of the variance of a random variable if passe
Returns `Float64`. When `n <= 1`, returns `+∞`.
:::note
Alias: `VAR_SAMP`.
:::note
This function uses a numerically unstable algorithm. If you need [numerical stability](https://en.wikipedia.org/wiki/Numerical_stability) in calculations, use the `varSampStable` function. It works slower but provides a lower computational error.
:::

6
docs/en/sql-reference/dictionaries/index.md
View File

@ -2361,6 +2361,12 @@ Result:
└────────────────────────────────────────┴───────────────────────────────────────────────────────────────────────────────────────┘
```
#### Matching Modes
Pattern matching behavior can be modified with certain dictionary settings:
- `regexp_dict_flag_case_insensitive`: Use case-insensitive matching (defaults to `false`). Can be overridden in individual expressions with `(?i)` and `(?-i)`.
- `regexp_dict_flag_dotall`: Allow '.' to match newline characters (defaults to `false`).
### Use Regular Expression Tree Dictionary in ClickHouse Cloud
Above used `YAMLRegExpTree` source works in ClickHouse Open Source but not in ClickHouse Cloud. To use regexp tree dictionaries in ClickHouse could, first create a regexp tree dictionary from a YAML file locally in ClickHouse Open Source, then dump this dictionary into a CSV file using the `dictionary` table function and the [INTO OUTFILE](../statements/select/into-outfile.md) clause.

280
docs/en/sql-reference/functions/date-time-functions.md
View File

@ -237,6 +237,11 @@ type_samoa: DateTime('US/Samoa')
int32samoa: 1546300800
```
**See Also**
- [formatDateTime](#date_time_functions-formatDateTime) - supports non-constant timezone.
- [toString](type-conversion-functions.md#tostring) - supports non-constant timezone.
## timeZoneOf
Returns the timezone name of [DateTime](../../sql-reference/data-types/datetime.md) or [DateTime64](../../sql-reference/data-types/datetime64.md) data types.
@ -720,6 +725,42 @@ SELECT toDate('2016-12-27') AS date, toYearWeek(date) AS yearWeek0, toYearWeek(d
└────────────┴───────────┴───────────┴───────────┴───────────────┘
```
## toDaysSinceYearZero
Returns for a given date, the number of days passed since [1 January 0000](https://en.wikipedia.org/wiki/Year_zero) in the [proleptic Gregorian calendar defined by ISO 8601](https://en.wikipedia.org/wiki/Gregorian_calendar#Proleptic_Gregorian_calendar). The calculation is the same as in MySQL's [`TO_DAYS()`](https://dev.mysql.com/doc/refman/8.0/en/date-and-time-functions.html#function_to-days) function.
**Syntax**
``` sql
toDaysSinceYearZero(date)
```
Aliases: `TO_DAYS`
**Arguments**
- `date` — The date to calculate the number of days passed since year zero from. [Date](../../sql-reference/data-types/date.md) or [Date32](../../sql-reference/data-types/date32.md).
**Returned value**
The number of days passed since date 0000-01-01.
Type: [UInt32](../../sql-reference/data-types/int-uint.md).
**Example**
``` sql
SELECT toDaysSinceYearZero(toDate('2023-09-08'));
```
Result:
``` text
┌─toDaysSinceYearZero(toDate('2023-09-08')))─┐
│ 713569 │
└────────────────────────────────────────────┘
```
## age
Returns the `unit` component of the difference between `startdate` and `enddate`. The difference is calculated using a precision of 1 microsecond.
@ -942,6 +983,8 @@ Result:
Adds the time interval or date interval to the provided date or date with time.
If the addition results in a value outside the bounds of the data type, the result is undefined.
**Syntax**
``` sql
@ -965,13 +1008,13 @@ Aliases: `dateAdd`, `DATE_ADD`.
- `year`
- `value` — Value of interval to add. [Int](../../sql-reference/data-types/int-uint.md).
- `date` — The date or date with time to which `value` is added. [Date](../../sql-reference/data-types/date.md) or [DateTime](../../sql-reference/data-types/datetime.md).
- `date` — The date or date with time to which `value` is added. [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) or [DateTime64](../../sql-reference/data-types/datetime64.md).
**Returned value**
Date or date with time obtained by adding `value`, expressed in `unit`, to `date`.
Type: [Date](../../sql-reference/data-types/date.md) or [DateTime](../../sql-reference/data-types/datetime.md).
Type: [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) or [DateTime64](../../sql-reference/data-types/datetime64.md).
**Example**
@ -987,10 +1030,16 @@ Result:
└───────────────────────────────────────────────┘
```
**See Also**
- [addDate](#addDate)
## date\_sub
Subtracts the time interval or date interval from the provided date or date with time.
If the subtraction results in a value outside the bounds of the data type, the result is undefined.
**Syntax**
``` sql
@ -1015,13 +1064,13 @@ Aliases: `dateSub`, `DATE_SUB`.
- `year`
- `value` — Value of interval to subtract. [Int](../../sql-reference/data-types/int-uint.md).
- `date` — The date or date with time from which `value` is subtracted. [Date](../../sql-reference/data-types/date.md) or [DateTime](../../sql-reference/data-types/datetime.md).
- `date` — The date or date with time from which `value` is subtracted. [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) or [DateTime64](../../sql-reference/data-types/datetime64.md).
**Returned value**
Date or date with time obtained by subtracting `value`, expressed in `unit`, from `date`.
Type: [Date](../../sql-reference/data-types/date.md) or [DateTime](../../sql-reference/data-types/datetime.md).
Type: [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) or [DateTime64](../../sql-reference/data-types/datetime64.md).
**Example**
@ -1037,10 +1086,15 @@ Result:
└────────────────────────────────────────────────┘
```
**See Also**
- [subDate](#subDate)
## timestamp\_add
Adds the specified time value with the provided date or date time value.
If the addition results in a value outside the bounds of the data type, the result is undefined.
**Syntax**
``` sql
@ -1051,7 +1105,7 @@ Aliases: `timeStampAdd`, `TIMESTAMP_ADD`.
**Arguments**
- `date` — Date or date with time. [Date](../../sql-reference/data-types/date.md) or [DateTime](../../sql-reference/data-types/datetime.md).
- `date` — Date or date with time. [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) or [DateTime64](../../sql-reference/data-types/datetime64.md).
- `value` — Value of interval to add. [Int](../../sql-reference/data-types/int-uint.md).
- `unit` — The type of interval to add. [String](../../sql-reference/data-types/string.md).
Possible values:
@ -1069,7 +1123,7 @@ Aliases: `timeStampAdd`, `TIMESTAMP_ADD`.
Date or date with time with the specified `value` expressed in `unit` added to `date`.
Type: [Date](../../sql-reference/data-types/date.md) or [DateTime](../../sql-reference/data-types/datetime.md).
Type: [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) or [DateTime64](../../sql-reference/data-types/datetime64.md).
**Example**
@ -1089,6 +1143,8 @@ Result:
Subtracts the time interval from the provided date or date with time.
If the subtraction results in a value outside the bounds of the data type, the result is undefined.
**Syntax**
``` sql
@ -1112,13 +1168,13 @@ Aliases: `timeStampSub`, `TIMESTAMP_SUB`.
- `year`
- `value` — Value of interval to subtract. [Int](../../sql-reference/data-types/int-uint.md).
- `date` — Date or date with time. [Date](../../sql-reference/data-types/date.md) or [DateTime](../../sql-reference/data-types/datetime.md).
- `date` — Date or date with time. [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) or [DateTime64](../../sql-reference/data-types/datetime64.md).
**Returned value**
Date or date with time obtained by subtracting `value`, expressed in `unit`, from `date`.
Type: [Date](../../sql-reference/data-types/date.md) or [DateTime](../../sql-reference/data-types/datetime.md).
Type: [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) or [DateTime64](../../sql-reference/data-types/datetime64.md).
**Example**
@ -1134,6 +1190,90 @@ Result:
└──────────────────────────────────────────────────────────────┘
```
## addDate
Adds the time interval or date interval to the provided date or date with time.
If the addition results in a value outside the bounds of the data type, the result is undefined.
**Syntax**
``` sql
addDate(date, interval)
```
**Arguments**
- `date` — The date or date with time to which `interval` is added. [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) or [DateTime64](../../sql-reference/data-types/datetime64.md).
- `interval` — Interval to add. [Interval](../../sql-reference/data-types/special-data-types/interval.md).
**Returned value**
Date or date with time obtained by adding `interval` to `date`.
Type: [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) or [DateTime64](../../sql-reference/data-types/datetime64.md).
**Example**
```sql
SELECT addDate(toDate('2018-01-01'), INTERVAL 3 YEAR);
```
Result:
```text
┌─addDate(toDate('2018-01-01'), toIntervalYear(3))─┐
│ 2021-01-01 │
└──────────────────────────────────────────────────┘
```
Alias: `ADDDATE`
**See Also**
- [date_add](#date_add)
## subDate
Subtracts the time interval or date interval from the provided date or date with time.
If the subtraction results in a value outside the bounds of the data type, the result is undefined.
**Syntax**
``` sql
subDate(date, interval)
```
**Arguments**
- `date` — The date or date with time from which `interval` is subtracted. [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) or [DateTime64](../../sql-reference/data-types/datetime64.md).
- `interval` — Interval to subtract. [Interval](../../sql-reference/data-types/special-data-types/interval.md).
**Returned value**
Date or date with time obtained by subtracting `interval` from `date`.
Type: [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) or [DateTime64](../../sql-reference/data-types/datetime64.md).
**Example**
```sql
SELECT subDate(toDate('2018-01-01'), INTERVAL 3 YEAR);
```
Result:
```text
┌─subDate(toDate('2018-01-01'), toIntervalYear(3))─┐
│ 2015-01-01 │
└──────────────────────────────────────────────────┘
```
Alias: `SUBDATE`
**See Also**
- [date_sub](#date_sub)
## now
Returns the current date and time at the moment of query analysis. The function is a constant expression.
@ -1285,6 +1425,8 @@ Rounds the time to the half hour.
Converts a date or date with time to a UInt32 number containing the year and month number (YYYY \* 100 + MM). Accepts a second optional timezone argument. If provided, the timezone must be a string constant.
This functions is the opposite of function `YYYYMMDDToDate()`.
**Example**
``` sql
@ -1307,8 +1449,7 @@ Converts a date or date with time to a UInt32 number containing the year and mon
**Example**
```sql
SELECT
toYYYYMMDD(now(), 'US/Eastern')
SELECT toYYYYMMDD(now(), 'US/Eastern')
```
Result:
@ -1326,8 +1467,7 @@ Converts a date or date with time to a UInt64 number containing the year and mon
**Example**
```sql
SELECT
toYYYYMMDDhhmmss(now(), 'US/Eastern')
SELECT toYYYYMMDDhhmmss(now(), 'US/Eastern')
```
Result:
@ -1338,6 +1478,93 @@ Result:
└───────────────────────────────────────┘
```
## YYYYMMDDToDate
Converts a number containing the year, month and day number to a [Date](../../sql-reference/data-types/date.md).
This functions is the opposite of function `toYYYYMMDD()`.
The output is undefined if the input does not encode a valid Date value.
**Syntax**
```sql
YYYYMMDDToDate(yyyymmdd);
```
**Arguments**
- `yyyymmdd` - A number representing the year, month and day. [Integer](../../sql-reference/data-types/int-uint.md), [Float](../../sql-reference/data-types/float.md) or [Decimal](../../sql-reference/data-types/decimal.md).
**Returned value**
- a date created from the arguments.
Type: [Date](../../sql-reference/data-types/date.md).
**Example**
```sql
SELECT YYYYMMDDToDate(20230911);
```
Result:
```response
┌─toYYYYMMDD(20230911)─┐
│ 2023-09-11 │
└──────────────────────┘
```
## YYYYMMDDToDate32
Like function `YYYYMMDDToDate()` but produces a [Date32](../../sql-reference/data-types/date32.md).
## YYYYMMDDhhmmssToDateTime
Converts a number containing the year, month, day, hours, minute and second number to a [DateTime](../../sql-reference/data-types/datetime.md).
The output is undefined if the input does not encode a valid DateTime value.
This functions is the opposite of function `toYYYYMMDDhhmmss()`.
**Syntax**
```sql
YYYYMMDDhhmmssToDateTime(yyyymmddhhmmss[, timezone]);
```
**Arguments**
- `yyyymmddhhmmss` - A number representing the year, month and day. [Integer](../../sql-reference/data-types/int-uint.md), [Float](../../sql-reference/data-types/float.md) or [Decimal](../../sql-reference/data-types/decimal.md).
- `timezone` - [Timezone](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-timezone) for the returned value (optional).
**Returned value**
- a date with time created from the arguments.
Type: [DateTime](../../sql-reference/data-types/datetime.md).
**Example**
```sql
SELECT YYYYMMDDToDateTime(20230911131415);
```
Result:
```response
┌──────YYYYMMDDhhmmssToDateTime(20230911131415)─┐
│ 2023-09-11 13:14:15 │
└───────────────────────────────────────────────┘
```
## YYYYMMDDhhmmssToDateTime64
Like function `YYYYMMDDhhmmssToDate()` but produces a [DateTime64](../../sql-reference/data-types/datetime64.md).
Accepts an additional, optional `precision` parameter after the `timezone` parameter.
## addYears, addMonths, addWeeks, addDays, addHours, addMinutes, addSeconds, addQuarters
Function adds a Date/DateTime interval to a Date/DateTime and then return the Date/DateTime. For example:
@ -1494,6 +1721,33 @@ Result:
└─────────────────────────────────────────────────────────────────────┘
```
Additionally, the `formatDateTime` function can take a third String argument containing the name of the time zone. Example: `Asia/Istanbul`. In this case, the time is formatted according to the specified time zone.
**Example**
```sql
SELECT
now() AS ts,
time_zone,
formatDateTime(ts, '%T', time_zone) AS str_tz_time
FROM system.time_zones
WHERE time_zone LIKE 'Europe%'
LIMIT 10
┌──────────────────ts─┬─time_zone─────────┬─str_tz_time─┐
│ 2023-09-08 19:13:40 │ Europe/Amsterdam │ 21:13:40 │
│ 2023-09-08 19:13:40 │ Europe/Andorra │ 21:13:40 │
│ 2023-09-08 19:13:40 │ Europe/Astrakhan │ 23:13:40 │
│ 2023-09-08 19:13:40 │ Europe/Athens │ 22:13:40 │
│ 2023-09-08 19:13:40 │ Europe/Belfast │ 20:13:40 │
│ 2023-09-08 19:13:40 │ Europe/Belgrade │ 21:13:40 │
│ 2023-09-08 19:13:40 │ Europe/Berlin │ 21:13:40 │
│ 2023-09-08 19:13:40 │ Europe/Bratislava │ 21:13:40 │
│ 2023-09-08 19:13:40 │ Europe/Brussels │ 21:13:40 │
│ 2023-09-08 19:13:40 │ Europe/Bucharest │ 22:13:40 │
└─────────────────────┴───────────────────┴─────────────┘
```
**See Also**
- [formatDateTimeInJodaSyntax](##formatDateTimeInJodaSyntax)
@ -1603,7 +1857,7 @@ monthName(date)
**Arguments**
- `date` — Date or date with time. [Date](../../sql-reference/data-types/date.md) or [DateTime](../../sql-reference/data-types/datetime.md).
- `date` — Date or date with time. [Date](../../sql-reference/data-types/date.md), [DateTime](../../sql-reference/data-types/datetime.md) or [DateTime64](../../sql-reference/data-types/datetime64.md).
**Returned value**

2
docs/en/sql-reference/functions/nlp-functions.md
View File

@ -204,7 +204,7 @@ Other possible results:
Query:
```sql
SELECT detectLanguageMixed('Je pense que je ne parviendrai jamais à parler français comme un natif. Where there’s a will, there’s a way.');
SELECT detectLanguage('Je pense que je ne parviendrai jamais à parler français comme un natif. Where there’s a will, there’s a way.');
```
Result:

8
docs/en/sql-reference/functions/splitting-merging-functions.md
View File

@ -33,6 +33,13 @@ Returns an array of selected substrings. Empty substrings may be selected when:
Type: [Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md)).
:::note
The behavior of parameter `max_substrings` changed starting with ClickHouse v22.11. In versions older than that, `max_substrings` > 0 meant that `max_substring`-many splits were performed and that the remainder of the string was returned as the final element of the list.
For example,
- in v22.10: `SELECT splitByChar('=', 'a=b=c=d', 2); -- ['a','b','c=d']`
- in v22.11: `SELECT splitByChar('=', 'a=b=c=d', 2); -- ['a','b']`
:::
**Example**
``` sql
@ -63,7 +70,6 @@ splitByString(separator, s[, max_substrings]))
- `s` — The string to split. [String](../../sql-reference/data-types/string.md).
- `max_substrings` — An optional `Int64` defaulting to 0. When `max_substrings` > 0, the returned substrings will be no more than `max_substrings`, otherwise the function will return as many substrings as possible.
**Returned value(s)**
Returns an array of selected substrings. Empty substrings may be selected when:

23
docs/en/sql-reference/functions/type-conversion-functions.md
View File

@ -892,16 +892,29 @@ Query:
``` sql
SELECT
now() AS now_local,
toString(now(), 'Asia/Yekaterinburg') AS now_yekat;
now() AS ts,
time_zone,
toString(ts, time_zone) AS str_tz_datetime
FROM system.time_zones
WHERE time_zone LIKE 'Europe%'
LIMIT 10
```
Result:
```response
┌───────────now_local─┬─now_yekat───────────┐
│ 2016-06-15 00:11:21 │ 2016-06-15 02:11:21 │
└─────────────────────┴─────────────────────┘
┌──────────────────ts─┬─time_zone─────────┬─str_tz_datetime─────┐
│ 2023-09-08 19:14:59 │ Europe/Amsterdam │ 2023-09-08 21:14:59 │
│ 2023-09-08 19:14:59 │ Europe/Andorra │ 2023-09-08 21:14:59 │
│ 2023-09-08 19:14:59 │ Europe/Astrakhan │ 2023-09-08 23:14:59 │
│ 2023-09-08 19:14:59 │ Europe/Athens │ 2023-09-08 22:14:59 │
│ 2023-09-08 19:14:59 │ Europe/Belfast │ 2023-09-08 20:14:59 │
│ 2023-09-08 19:14:59 │ Europe/Belgrade │ 2023-09-08 21:14:59 │
│ 2023-09-08 19:14:59 │ Europe/Berlin │ 2023-09-08 21:14:59 │
│ 2023-09-08 19:14:59 │ Europe/Bratislava │ 2023-09-08 21:14:59 │
│ 2023-09-08 19:14:59 │ Europe/Brussels │ 2023-09-08 21:14:59 │
│ 2023-09-08 19:14:59 │ Europe/Bucharest │ 2023-09-08 22:14:59 │
└─────────────────────┴───────────────────┴─────────────────────┘
```
Also see the `toUnixTimestamp` function.

8
docs/en/sql-reference/statements/create/table.md
View File

@ -391,19 +391,19 @@ DEFLATE_QPL is not available in ClickHouse Cloud.
### Specialized Codecs
These codecs are designed to make compression more effective by using specific features of data. Some of these codecs do not compress data themself. Instead, they prepare the data for a common purpose codec, which compresses it better than without this preparation.
These codecs are designed to make compression more effective by exploiting specific features of the data. Some of these codecs do not compress data themself, they instead preprocess the data such that a second compression stage using a general-purpose codec can achieve a higher data compression rate.
#### Delta
`Delta(delta_bytes)` — Compression approach in which raw values are replaced by the difference of two neighboring values, except for the first value that stays unchanged. Up to `delta_bytes` are used for storing delta values, so `delta_bytes` is the maximum size of raw values. Possible `delta_bytes` values: 1, 2, 4, 8. The default value for `delta_bytes` is `sizeof(type)` if equal to 1, 2, 4, or 8. In all other cases, it’s 1. Delta is a data preparation codec, i.e. cannot be used stand-alone.
`Delta(delta_bytes)` — Compression approach in which raw values are replaced by the difference of two neighboring values, except for the first value that stays unchanged. Up to `delta_bytes` are used for storing delta values, so `delta_bytes` is the maximum size of raw values. Possible `delta_bytes` values: 1, 2, 4, 8. The default value for `delta_bytes` is `sizeof(type)` if equal to 1, 2, 4, or 8. In all other cases, it’s 1. Delta is a data preparation codec, i.e. it cannot be used stand-alone.
#### DoubleDelta
`DoubleDelta(bytes_size)` — Calculates delta of deltas and writes it in compact binary form. Possible `bytes_size` values: 1, 2, 4, 8, the default value is `sizeof(type)` if equal to 1, 2, 4, or 8. In all other cases, it’s 1. Optimal compression rates are achieved for monotonic sequences with a constant stride, such as time series data. Can be used with any fixed-width type. Implements the algorithm used in Gorilla TSDB, extending it to support 64-bit types. Uses 1 extra bit for 32-bit deltas: 5-bit prefixes instead of 4-bit prefixes. For additional information, see Compressing Time Stamps in [Gorilla: A Fast, Scalable, In-Memory Time Series Database](http://www.vldb.org/pvldb/vol8/p1816-teller.pdf). DoubleDelta is a data preparation codec, i.e. cannot be used stand-alone.
`DoubleDelta(bytes_size)` — Calculates delta of deltas and writes it in compact binary form. Possible `bytes_size` values: 1, 2, 4, 8, the default value is `sizeof(type)` if equal to 1, 2, 4, or 8. In all other cases, it’s 1. Optimal compression rates are achieved for monotonic sequences with a constant stride, such as time series data. Can be used with any fixed-width type. Implements the algorithm used in Gorilla TSDB, extending it to support 64-bit types. Uses 1 extra bit for 32-bit deltas: 5-bit prefixes instead of 4-bit prefixes. For additional information, see Compressing Time Stamps in [Gorilla: A Fast, Scalable, In-Memory Time Series Database](http://www.vldb.org/pvldb/vol8/p1816-teller.pdf). DoubleDelta is a data preparation codec, i.e. it cannot be used stand-alone.
#### GCD
`GCD()` - - Calculates the greatest common denominator (GCD) of the values in the column, then divides each value by the GCD. Can be used with integer, decimal and date/time columns. A viable use case are timestamps or monetary values with high precision. GCD is a data preparation codec, i.e. cannot be used stand-alone.
`GCD()` - - Calculates the greatest common denominator (GCD) of the values in the column, then divides each value by the GCD. Can be used with integer, decimal and date/time columns. The codec is well suited for columns with values that change (increase or decrease) in multiples of the GCD, e.g. 24, 28, 16, 24, 8, 24 (GCD = 4). GCD is a data preparation codec, i.e. it cannot be used stand-alone.
#### Gorilla

2
docs/en/sql-reference/statements/create/user.md
View File

@ -90,7 +90,7 @@ In ClickHouse Cloud, by default, passwords must meet the following complexity re
CREATE USER name3 IDENTIFIED WITH sha256_password BY 'my_password'
```
The `name3` user can now login using `my_password`, but the password is stored as the hashed value above. THe following SQL file was created in `/var/lib/clickhouse/access` and gets executed at server startup:
The `name3` user can now login using `my_password`, but the password is stored as the hashed value above. The following SQL file was created in `/var/lib/clickhouse/access` and gets executed at server startup:
```bash
/var/lib/clickhouse/access $ cat 3843f510-6ebd-a52d-72ac-e021686d8a93.sql

15
docs/en/sql-reference/statements/show.md
View File

@ -208,7 +208,7 @@ The optional keyword `FULL` causes the output to include the collation, comment
The statement produces a result table with the following structure:
- field - The name of the column (String)
- type - The column data type (String)
- null - If the column data type is Nullable (UInt8)
- null - `YES` if the column data type is Nullable, `NO` otherwise (String)
- key - `PRI` if the column is part of the primary key, `SOR` if the column is part of the sorting key, empty otherwise (String)
- default - Default expression of the column if it is of type `ALIAS`, `DEFAULT`, or `MATERIALIZED`, otherwise `NULL`. (Nullable(String))
- extra - Additional information, currently unused (String)
@ -638,3 +638,16 @@ Outputs the content of the [system.table_engines](../../operations/system-tables
**See Also**
- [system.table_engines](../../operations/system-tables/table_engines.md) table
## SHOW FUNCTIONS
``` sql
SHOW FUNCTIONS [LIKE | ILIKE '<pattern>']
```
Outputs the content of the [system.functions](../../operations/system-tables/functions.md) table.
If either `LIKE` or `ILIKE` clause is specified, the query returns a list of system functions whose names match the provided `<pattern>`.
**See Also**
- [system.functions](../../operations/system-tables/functions.md) table

6
docs/en/sql-reference/table-functions/file.md
View File

@ -135,13 +135,13 @@ Getting data from table in table.csv, located in archive1.zip or/and archive2.zi
SELECT * FROM file('user_files/archives/archive{1..2}.zip :: table.csv');
```
## Globs in Path
## Globs in Path {#globs_in_path}
Multiple path components can have globs. For being processed file must exist and match to the whole path pattern (not only suffix or prefix).
- `*` — Substitutes any number of any characters except `/` including empty string.
- `?` — Substitutes any single character.
- `{some_string,another_string,yet_another_one}` — Substitutes any of strings `'some_string', 'another_string', 'yet_another_one'`, including `/`.
- `{some_string,another_string,yet_another_one}` — Substitutes any of strings `'some_string', 'another_string', 'yet_another_one'`. In case at least one of strings contains `/`, `'permission denied'` errors may be ignored using [ignore_access_denied_multidirectory_globs](/docs/en/operations/settings/settings.md#ignore_access_denied_multidirectory_globs) setting for file & HDFS.
- `{N..M}` — Substitutes any number in range from N to M including both borders.
- `**` - Fetches all files inside the folder recursively.
@ -210,7 +210,7 @@ SELECT count(*) FROM file('big_dir/**/file002', 'CSV', 'name String, value UInt3
- [engine_file_allow_create_multiple_files](/docs/en/operations/settings/settings.md#engine_file_allow_create_multiple_files) - allows to create a new file on each insert if format has suffix. Disabled by default.
- [engine_file_skip_empty_files](/docs/en/operations/settings/settings.md#engine_file_skip_empty_files) - allows to skip empty files while reading. Disabled by default.
- [storage_file_read_method](/docs/en/operations/settings/settings.md#engine-file-emptyif-not-exists) - method of reading data from storage file, one of: read, pread, mmap (only for clickhouse-local). Default value: `pread` for clickhouse-server, `mmap` for clickhouse-local.
- [ignore_access_denied_multidirectory_globs](/docs/en/operations/settings/settings.md#ignore_access_denied_multidirectory_globs) - allows to ignore permission denied errors for multi-directory globs.
**See Also**

5
docs/en/sql-reference/table-functions/hdfs.md
View File

@ -39,13 +39,13 @@ LIMIT 2
└─────────┴─────────┴─────────┘
```
**Globs in path**
## Globs in path {#globs_in_path}
Multiple path components can have globs. For being processed file should exists and matches to the whole path pattern (not only suffix or prefix).
- `*` — Substitutes any number of any characters except `/` including empty string.
- `?` — Substitutes any single character.
- `{some_string,another_string,yet_another_one}` — Substitutes any of strings `'some_string', 'another_string', 'yet_another_one'`.
- `{some_string,another_string,yet_another_one}` — Substitutes any of strings `'some_string', 'another_string', 'yet_another_one'`. In case at least one of strings contains `/`, `'permission denied'` errors may be ignored using [ignore_access_denied_multidirectory_globs](/docs/en/operations/settings/settings.md#ignore_access_denied_multidirectory_globs) setting.
- `{N..M}` — Substitutes any number in range from N to M including both borders.
Constructions with `{}` are similar to the [remote table function](../../sql-reference/table-functions/remote.md)).
@ -102,6 +102,7 @@ FROM hdfs('hdfs://hdfs1:9000/big_dir/file{0..9}{0..9}{0..9}', 'CSV', 'name Strin
- [hdfs_truncate_on_insert](/docs/en/operations/settings/settings.md#hdfs-truncate-on-insert) - allows to truncate file before insert into it. Disabled by default.
- [hdfs_create_multiple_files](/docs/en/operations/settings/settings.md#hdfs_allow_create_multiple_files) - allows to create a new file on each insert if format has suffix. Disabled by default.
- [hdfs_skip_empty_files](/docs/en/operations/settings/settings.md#hdfs_skip_empty_files) - allows to skip empty files while reading. Disabled by default.
- [ignore_access_denied_multidirectory_globs](/docs/en/operations/settings/settings.md#ignore_access_denied_multidirectory_globs) - allows to ignore permission denied errors for multi-directory globs.
**See Also**

2
docs/ru/interfaces/cli.md
View File

@ -128,7 +128,7 @@ $ clickhouse-client --param_tbl="numbers" --param_db="system" --param_col="numbe
- `--port` — порт для подключения, по умолчанию — 9000. Обратите внимание: для HTTP-интерфейса и нативного интерфейса используются разные порты.
- `--user, -u` — имя пользователя, по умолчанию — ‘default’.
- `--password` — пароль, по умолчанию — пустая строка.
- `--query, -q` — запрос для выполнения, при использовании в неинтерактивном режиме.
- `--query, -q` — запрос для выполнения, при использовании в неинтерактивном режиме. Допускается указание `--query` несколько раз (`--query "SELECT 1;" --query "SELECT 2;"...`).
- `--queries-file` - путь к файлу с запросами для выполнения. Необходимо указать только одну из опций: `query` или `queries-file`.
- `--database, -d` — выбрать текущую БД. Без указания значение берется из настроек сервера (по умолчанию — БД ‘default’).
- `--multiline, -m` — если указано — разрешить многострочные запросы, не отправлять запрос по нажатию Enter.

16
docs/ru/interfaces/http.md
View File

@ -50,7 +50,7 @@ Connection: Close
Content-Type: text/tab-separated-values; charset=UTF-8
X-ClickHouse-Server-Display-Name: clickhouse.ru-central1.internal
X-ClickHouse-Query-Id: 5abe861c-239c-467f-b955-8a201abb8b7f
X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","peak_memory_usage":"0"}
X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334","peak_memory_usage":"0"}
1
```
@ -267,9 +267,9 @@ $ echo 'SELECT number FROM system.numbers LIMIT 10' | curl 'http://localhost:812
Прогресс выполнения запроса можно отслеживать с помощью заголовков ответа `X-ClickHouse-Progress`. Для этого включите [send_progress_in_http_headers](../operations/settings/settings.md#settings-send_progress_in_http_headers). Пример последовательности заголовков:
``` text
X-ClickHouse-Progress: {"read_rows":"2752512","read_bytes":"240570816","total_rows_to_read":"8880128","peak_memory_usage":"4371480"}
X-ClickHouse-Progress: {"read_rows":"5439488","read_bytes":"482285394","total_rows_to_read":"8880128","peak_memory_usage":"13621616"}
X-ClickHouse-Progress: {"read_rows":"8783786","read_bytes":"819092887","total_rows_to_read":"8880128","peak_memory_usage":"23155600"}
X-ClickHouse-Progress: {"read_rows":"2752512","read_bytes":"240570816","total_rows_to_read":"8880128","elapsed_ns":"662334","peak_memory_usage":"4371480"}
X-ClickHouse-Progress: {"read_rows":"5439488","read_bytes":"482285394","total_rows_to_read":"8880128","elapsed_ns":"992334","peak_memory_usage":"13621616"}
X-ClickHouse-Progress: {"read_rows":"8783786","read_bytes":"819092887","total_rows_to_read":"8880128","elapsed_ns":"1232334","peak_memory_usage":"23155600"}
```
Возможные поля заголовка:
@ -530,7 +530,7 @@ $ curl -vv -H 'XXX:xxx' 'http://localhost:8123/hi'
< Content-Type: text/html; charset=UTF-8
< Transfer-Encoding: chunked
< Keep-Alive: timeout=3
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","peak_memory_usage":"0"}
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334","peak_memory_usage":"0"}
<
* Connection #0 to host localhost left intact
Say Hi!%
@ -570,7 +570,7 @@ $ curl -v -H 'XXX:xxx' 'http://localhost:8123/get_config_static_handler'
< Content-Type: text/plain; charset=UTF-8
< Transfer-Encoding: chunked
< Keep-Alive: timeout=3
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","peak_memory_usage":"0"}
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334","peak_memory_usage":"0"}
<
* Connection #0 to host localhost left intact
<html ng-app="SMI2"><head><base href="http://ui.tabix.io/"></head><body><div ui-view="" class="content-ui"></div><script src="http://loader.tabix.io/master.js"></script></body></html>%
@ -622,7 +622,7 @@ $ curl -vv -H 'XXX:xxx' 'http://localhost:8123/get_absolute_path_static_handler'
< Content-Type: text/html; charset=UTF-8
< Transfer-Encoding: chunked
< Keep-Alive: timeout=3
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","peak_memory_usage":"0"}
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334","peak_memory_usage":"0"}
<
<html><body>Absolute Path File</body></html>
* Connection #0 to host localhost left intact
@ -641,7 +641,7 @@ $ curl -vv -H 'XXX:xxx' 'http://localhost:8123/get_relative_path_static_handler'
< Content-Type: text/html; charset=UTF-8
< Transfer-Encoding: chunked
< Keep-Alive: timeout=3
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","peak_memory_usage":"0"}
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334","peak_memory_usage":"0"}
<
<html><body>Relative Path File</body></html>
* Connection #0 to host localhost left intact

42
docs/ru/operations/settings/settings.md
View File

@ -4209,3 +4209,45 @@ SELECT toFloat64('1.7091'), toFloat64('1.5008753E7') SETTINGS precise_float_pars
│ 1.7091 │ 15008753 │
└─────────────────────┴──────────────────────────┘
```
## ignore_access_denied_multidirectory_globs {#ignore_access_denied_multidirectory_globs}
Позволяет игнорировать ошибку 'permission denied', возникающую при использовании шаблона `{}`, содержащего `/` внутри себя.
Работает для [File](../../sql-reference/table-functions/file.md#globs_in_path) и [HDFS](../../sql-reference/table-functions/hdfs.md).
Работает _только_ для указанных выше шаблонов `{}`.
Возможные значения: `0`, `1`.
Значение по умолчанию: `0`.
### Пример
Пусть в `user_files` имеется следующая структура:
```
my_directory/
├── data1
│ ├── f1.csv
├── data2
│ ├── f2.csv
└── test_root
```
Пусть также директории `data1`, `data2` могут быть прочитаны, но прав на чтение `test_root` нет.
На запрос `SELECT *, _path, _file FROM file('my_directory/{data1/f1,data2/f2}.csv', CSV)` будет выброшено исключение:
`Code: 1001. DB::Exception: std::__1::__fs::filesystem::filesystem_error: filesystem error: in directory_iterator::directory_iterator(...): Permission denied`.
Это происходит, так как для обработки такого шаблона необходимо выполнить рекурсивный поиск по _всем_ директориям, находящимся внутри `my_directory`.
Если данная настройка имеет значение 1, то недоступные директории будут тихо пропущены, даже если они явно указаны внутри `{}`.
```sql
SELECT _path, _file FROM file('my_directory/{data1/f1,data2/f2}.csv', CSV) SETTINGS ignore_access_denied_multidirectory_globs = 0;
Code: 1001. DB::Exception: std::__1::__fs::filesystem::filesystem_error: filesystem error: in directory_iterator::directory_iterator(...): Permission denied
```
```sql
SELECT _path, _file FROM file('my_directory/{data1/f1,data2/f2}.csv', CSV) SETTINGS ignore_access_denied_multidirectory_globs = 1;
┌─_path───────────────────┬─_file───────┐
│ <full path to file> │ <file name> │
└─────────────────────────┴─────────────┘
```

15
docs/ru/operations/system-tables/licenses.md
View File

@ -20,21 +20,10 @@ SELECT library_name, license_type, license_path FROM system.licenses LIMIT 15
``` text
┌─library_name───────┬─license_type─┬─license_path────────────────────────┐
│ FastMemcpy │ MIT │ /contrib/FastMemcpy/LICENSE │
│ arrow │ Apache │ /contrib/arrow/LICENSE.txt │
│ avro │ Apache │ /contrib/avro/LICENSE.txt │
│ aws-c-common │ Apache │ /contrib/aws-c-common/LICENSE │
│ aws-c-event-stream │ Apache │ /contrib/aws-c-event-stream/LICENSE │
│ aws-checksums │ Apache │ /contrib/aws-checksums/LICENSE │
│ aws │ Apache │ /contrib/aws/LICENSE.txt │
│ base64 │ BSD 2-clause │ /contrib/base64/LICENSE │
│ boost │ Boost │ /contrib/boost/LICENSE_1_0.txt │
│ base64 │ BSD 2-clause │ /contrib/aklomp-base64/LICENSE │
│ brotli │ MIT │ /contrib/brotli/LICENSE │
│ capnproto │ MIT │ /contrib/capnproto/LICENSE │
│ cassandra │ Apache │ /contrib/cassandra/LICENSE.txt │
│ cctz │ Apache │ /contrib/cctz/LICENSE.txt │
│ cityhash102 │ MIT │ /contrib/cityhash102/COPYING │
│ cppkafka │ BSD 2-clause │ /contrib/cppkafka/LICENSE │
│ [...] │ [...] │ [...] │
└────────────────────┴──────────────┴─────────────────────────────────────┘
```

3
docs/ru/operations/system-tables/query_log.md
View File

@ -99,7 +99,8 @@ ClickHouse не удаляет данные из таблица автомати
- `ProfileEvents` ([Map(String, UInt64)](../../sql-reference/data-types/array.md)) — счетчики для изменения различных метрик. Описание метрик можно получить из таблицы [system.events](#system_tables-events)(#system_tables-events
- `Settings` ([Map(String, String)](../../sql-reference/data-types/array.md)) — имена настроек, которые меняются, когда клиент выполняет запрос. Чтобы разрешить логирование изменений настроек, установите параметр `log_query_settings` равным 1.
- `log_comment` ([String](../../sql-reference/data-types/string.md)) — комментарий к записи в логе. Представляет собой произвольную строку, длина которой должна быть не больше, чем [max_query_size](../../operations/settings/settings.md#settings-max_query_size). Если нет комментария, то пустая строка.
- `thread_ids` ([Array(UInt64)](../../sql-reference/data-types/array.md)) — идентификаторы потоков, участвующих в обработке запросов.
- `thread_ids` ([Array(UInt64)](../../sql-reference/data-types/array.md)) — идентификаторы потоков, участвующих в обработке запросов, эти потоки не обязательно выполняются одновременно.
- `peak_threads_usage` ([UInt64)](../../sql-reference/data-types/int-uint.md)) — максимальное количество одновременно работавших потоков, участвоваших в обработке запроса.
- `used_aggregate_functions` ([Array(String)](../../sql-reference/data-types/array.md)) — канонические имена `агрегатных функций`, использованных при выполнении запроса.
- `used_aggregate_function_combinators` ([Array(String)](../../sql-reference/data-types/array.md)) — канонические имена `комбинаторов агрегатных функций`, использованных при выполнении запроса.
- `used_database_engines` ([Array(String)](../../sql-reference/data-types/array.md)) — канонические имена `движков баз данных`, использованных при выполнении запроса.

3
docs/ru/sql-reference/table-functions/file.md
View File

@ -79,7 +79,7 @@ SELECT * FROM file('test.csv', 'CSV', 'column1 UInt32, column2 UInt32, column3 U
- `*` — заменяет любое количество любых символов кроме `/`, включая отсутствие символов.
- `?` — заменяет ровно один любой символ.
- `{some_string,another_string,yet_another_one}` — заменяет любую из строк `'some_string', 'another_string', 'yet_another_one'`, причём строка может содержать `/`.
- `{some_string,another_string,yet_another_one}` — заменяет любую из строк `'some_string', 'another_string', 'yet_another_one'`. В случае, если в какой-либо из строк содержится `/`, то ошибки доступа (permission denied) к существующим, но недоступным директориям/файлам могут быть проигнорированы при помощи настройки [ignore_access_denied_multidirectory_globs](/docs/ru/operations/settings/settings.md#ignore_access_denied_multidirectory_globs).
- `{N..M}` — заменяет любое число в интервале от `N` до `M` включительно (может содержать ведущие нули).
Конструкция с `{}` аналогична табличной функции [remote](remote.md).
@ -124,6 +124,7 @@ SELECT count(*) FROM file('big_dir/file{0..9}{0..9}{0..9}', 'CSV', 'name String,
- `_path` — путь к файлу.
- `_file` — имя файла.
**Смотрите также**
- [Виртуальные столбцы](index.md#table_engines-virtual_columns)

6
docs/ru/sql-reference/table-functions/hdfs.md
View File

@ -39,11 +39,11 @@ LIMIT 2
└─────────┴─────────┴─────────┘
```
**Шаблоны в пути**
## Шаблоны поиска в компонентах пути {#globs-in-path}
- `*` — Заменяет любое количество любых символов кроме `/`, включая отсутствие символов.
- `?` — Заменяет ровно один любой символ.
- `{some_string,another_string,yet_another_one}` — Заменяет любую из строк `'some_string', 'another_string', 'yet_another_one'`.
- `{some_string,another_string,yet_another_one}` — Заменяет любую из строк `'some_string', 'another_string', 'yet_another_one'`. В случае, если в какой-либо из строк содержится `/`, то ошибки доступа (permission denied) к существующим, но недоступным директориям/файлам могут быть проигнорированы при помощи настройки [ignore_access_denied_multidirectory_globs](/docs/ru/operations/settings/settings.md#ignore_access_denied_multidirectory_globs).
- `{N..M}` — Заменяет любое число в интервале от `N` до `M` включительно (может содержать ведущие нули).
Конструкция с `{}` аналогична табличной функции [remote](remote.md).
@ -62,3 +62,5 @@ LIMIT 2
**Смотрите также**
- [Виртуальные столбцы](index.md#table_engines-virtual_columns)
- Параметр [ignore_access_denied_multidirectory_globs](/docs/ru/operations/settings/settings.md#ignore_access_denied_multidirectory_globs)

2
docs/zh/interfaces/cli.md
View File

@ -116,7 +116,7 @@ $ clickhouse-client --param_tuple_in_tuple="(10, ('dt', 10))" -q "SELECT * FROM
- `--port` – 连接的端口，默认值：9000。注意HTTP接口以及TCP原生接口使用的是不同端口。
- `--user, -u` – 用户名。 默认值：`default`。
- `--password` – 密码。 默认值：空字符串。
- `--query, -q` – 使用非交互模式查询。
- `--query, -q` – 使用非交互模式查询。 允许多次指定 `--query`（`--query "SELECT 1;" --query "SELECT 2;"...`）。
- `--database, -d` – 默认当前操作的数据库. 默认值：服务端默认的配置（默认是`default`）。
- `--multiline, -m` – 如果指定，允许多行语句查询（Enter仅代表换行，不代表查询语句完结）。
- `--multiquery, -n` – 如果指定, 允许处理用`;`号分隔的多个查询，只在非交互模式下生效。

18
docs/zh/interfaces/http.md
View File

@ -53,7 +53,7 @@ Connection: Close
Content-Type: text/tab-separated-values; charset=UTF-8
X-ClickHouse-Server-Display-Name: clickhouse.ru-central1.internal
X-ClickHouse-Query-Id: 5abe861c-239c-467f-b955-8a201abb8b7f
X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","peak_memory_usage":"0"}
X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334","peak_memory_usage":"0"}
1
```
@ -262,9 +262,9 @@ $ echo 'SELECT number FROM system.numbers LIMIT 10' | curl 'http://localhost:812
您可以在`X-ClickHouse-Progress`响应头中收到查询进度的信息。为此，启用[Http Header携带进度](../operations/settings/settings.md#settings-send_progress_in_http_headers)。示例：
``` text
X-ClickHouse-Progress: {"read_rows":"2752512","read_bytes":"240570816","total_rows_to_read":"8880128","peak_memory_usage":"4371480"}
X-ClickHouse-Progress: {"read_rows":"5439488","read_bytes":"482285394","total_rows_to_read":"8880128","peak_memory_usage":"13621616"}
X-ClickHouse-Progress: {"read_rows":"8783786","read_bytes":"819092887","total_rows_to_read":"8880128","peak_memory_usage":"23155600"}
X-ClickHouse-Progress: {"read_rows":"2752512","read_bytes":"240570816","total_rows_to_read":"8880128","elapsed_ns":"662334","peak_memory_usage":"4371480"}
X-ClickHouse-Progress: {"read_rows":"5439488","read_bytes":"482285394","total_rows_to_read":"8880128","elapsed_ns":"992334","peak_memory_usage":"13621616"}
X-ClickHouse-Progress: {"read_rows":"8783786","read_bytes":"819092887","total_rows_to_read":"8880128","elapsed_ns":"1232334","peak_memory_usage":"23155600"}
```
显示字段信息:
@ -363,7 +363,7 @@ $ curl -v 'http://localhost:8123/predefined_query'
< X-ClickHouse-Format: Template
< X-ClickHouse-Timezone: Asia/Shanghai
< Keep-Alive: timeout=3
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","peak_memory_usage":"0"}
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334","peak_memory_usage":"0"}
<
# HELP "Query" "Number of executing queries"
# TYPE "Query" counter
@ -521,7 +521,7 @@ $ curl -vv -H 'XXX:xxx' 'http://localhost:8123/hi'
< Content-Type: text/html; charset=UTF-8
< Transfer-Encoding: chunked
< Keep-Alive: timeout=3
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","peak_memory_usage":"0"}
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334","peak_memory_usage":"0"}
<
* Connection #0 to host localhost left intact
Say Hi!%
@ -561,7 +561,7 @@ $ curl -v -H 'XXX:xxx' 'http://localhost:8123/get_config_static_handler'
< Content-Type: text/plain; charset=UTF-8
< Transfer-Encoding: chunked
< Keep-Alive: timeout=3
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","peak_memory_usage":"0"}
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334","peak_memory_usage":"0"}
<
* Connection #0 to host localhost left intact
<html ng-app="SMI2"><head><base href="http://ui.tabix.io/"></head><body><div ui-view="" class="content-ui"></div><script src="http://loader.tabix.io/master.js"></script></body></html>%
@ -613,7 +613,7 @@ $ curl -vv -H 'XXX:xxx' 'http://localhost:8123/get_absolute_path_static_handler'
< Content-Type: text/html; charset=UTF-8
< Transfer-Encoding: chunked
< Keep-Alive: timeout=3
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","peak_memory_usage":"0"}
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334","peak_memory_usage":"0"}
<
<html><body>Absolute Path File</body></html>
* Connection #0 to host localhost left intact
@ -632,7 +632,7 @@ $ curl -vv -H 'XXX:xxx' 'http://localhost:8123/get_relative_path_static_handler'
< Content-Type: text/html; charset=UTF-8
< Transfer-Encoding: chunked
< Keep-Alive: timeout=3
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","peak_memory_usage":"0"}
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334","peak_memory_usage":"0"}
<
<html><body>Relative Path File</body></html>
* Connection #0 to host localhost left intact

16
docs/zh/operations/system-tables/licenses.md
View File

@ -20,21 +20,9 @@ SELECT library_name, license_type, license_path FROM system.licenses LIMIT 15
``` text
┌─library_name───────┬─license_type─┬─license_path────────────────────────┐
│ FastMemcpy │ MIT │ /contrib/FastMemcpy/LICENSE │
│ arrow │ Apache │ /contrib/arrow/LICENSE.txt │
│ avro │ Apache │ /contrib/avro/LICENSE.txt │
│ aws-c-common │ Apache │ /contrib/aws-c-common/LICENSE │
│ aws-c-event-stream │ Apache │ /contrib/aws-c-event-stream/LICENSE │
│ aws-checksums │ Apache │ /contrib/aws-checksums/LICENSE │
│ aws │ Apache │ /contrib/aws/LICENSE.txt │
│ base64 │ BSD 2-clause │ /contrib/base64/LICENSE │
│ boost │ Boost │ /contrib/boost/LICENSE_1_0.txt │
│ base64 │ BSD 2-clause │ /contrib/aklomp-base64/LICENSE │
│ brotli │ MIT │ /contrib/brotli/LICENSE │
│ capnproto │ MIT │ /contrib/capnproto/LICENSE │
│ cassandra │ Apache │ /contrib/cassandra/LICENSE.txt │
│ cctz │ Apache │ /contrib/cctz/LICENSE.txt │
│ cityhash102 │ MIT │ /contrib/cityhash102/COPYING │
│ cppkafka │ BSD 2-clause │ /contrib/cppkafka/LICENSE │
│ [...] │ [...] │ [...] │
└────────────────────┴──────────────┴─────────────────────────────────────┘
```

4
docs/zh/sql-reference/aggregate-functions/reference/stddevsamp.md
View File

@ -5,8 +5,8 @@ sidebar_position: 31
# stddevSamp {#stddevsamp}
结果等于 [varSamp] (../../../sql-reference/aggregate-functions/reference/varsamp.md)的平方根。
结果等于 [varSamp](../../../sql-reference/aggregate-functions/reference/varsamp.md) 的平方根。
:::note
该函数使用数值不稳定的算法。 如果你需要 [数值稳定性](https://en.wikipedia.org/wiki/Numerical_stability) 在计算中，使用 `stddevSampStable` 函数。 它的工作速度较慢，但提供较低的计算错误。
:::
:::

4
packages/clickhouse-keeper.yaml
View File

@ -32,10 +32,10 @@ contents:
dst: /usr/bin/clickhouse-keeper
- src: clickhouse-keeper.service
dst: /lib/systemd/system/clickhouse-keeper.service
- src: clickhouse
- src: clickhouse-keeper
dst: /usr/bin/clickhouse-keeper-client
type: symlink
- src: clickhouse
- src: clickhouse-keeper
dst: /usr/bin/clickhouse-keeper-converter
type: symlink
# docs

6
programs/client/Client.cpp
View File

@ -1189,7 +1189,7 @@ void Client::processOptions(const OptionsDescription & options_description,
void Client::processConfig()
{
if (config().has("query") && config().has("queries-file"))
if (!queries.empty() && config().has("queries-file"))
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Options '--query' and '--queries-file' cannot be specified at the same time");
/// Batch mode is enabled if one of the following is true:
@ -1200,9 +1200,9 @@ void Client::processConfig()
/// - --queries-file command line option is present.
/// The value of the option is used as file with query (or of multiple queries) to execute.
delayed_interactive = config().has("interactive") && (config().has("query") || config().has("queries-file"));
delayed_interactive = config().has("interactive") && (!queries.empty() || config().has("queries-file"));
if (stdin_is_a_tty
&& (delayed_interactive || (!config().has("query") && queries_files.empty())))
&& (delayed_interactive || (queries.empty() && queries_files.empty())))
{
is_interactive = true;
}

7
programs/extract-from-config/ExtractFromConfig.cpp
View File

@ -18,7 +18,14 @@
#include <Common/Exception.h>
#include <Common/parseGlobs.h>
#ifdef __clang__
# pragma clang diagnostic push
# pragma clang diagnostic ignored "-Wzero-as-null-pointer-constant"
#endif
#include <re2/re2.h>
#ifdef __clang__
# pragma clang diagnostic pop
#endif
static void setupLogging(const std::string & log_level)
{

10
programs/git-import/git-import.cpp
View File

@ -9,8 +9,6 @@
#include <thread>
#include <filesystem>
#include <re2/re2.h>
#include <boost/program_options.hpp>
#include <Common/TerminalSize.h>
@ -26,6 +24,14 @@
#include <IO/WriteBufferFromFile.h>
#include <IO/WriteBufferFromFileDescriptor.h>
#ifdef __clang__
# pragma clang diagnostic push
# pragma clang diagnostic ignored "-Wzero-as-null-pointer-constant"
#endif
#include <re2/re2.h>
#ifdef __clang__
# pragma clang diagnostic pop
#endif
static constexpr auto documentation = R"(
A tool to extract information from Git repository for analytics.

143
programs/keeper-client/Commands.cpp
View File

@ -9,11 +9,11 @@ namespace DB
bool LSCommand::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const
{
String arg;
if (!parseKeeperPath(pos, expected, arg))
String path;
if (!parseKeeperPath(pos, expected, path))
return true;
node->args.push_back(std::move(arg));
node->args.push_back(std::move(path));
return true;
}
@ -42,11 +42,11 @@ void LSCommand::execute(const ASTKeeperQuery * query, KeeperClient * client) con
bool CDCommand::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const
{
String arg;
if (!parseKeeperPath(pos, expected, arg))
String path;
if (!parseKeeperPath(pos, expected, path))
return true;
node->args.push_back(std::move(arg));
node->args.push_back(std::move(path));
return true;
}
@ -64,11 +64,12 @@ void CDCommand::execute(const ASTKeeperQuery * query, KeeperClient * client) con
bool SetCommand::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const
{
String arg;
if (!parseKeeperPath(pos, expected, arg))
String path;
if (!parseKeeperPath(pos, expected, path))
return false;
node->args.push_back(std::move(arg));
node->args.push_back(std::move(path));
String arg;
if (!parseKeeperArg(pos, expected, arg))
return false;
node->args.push_back(std::move(arg));
@ -93,11 +94,12 @@ void SetCommand::execute(const ASTKeeperQuery * query, KeeperClient * client) co
bool CreateCommand::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const
{
String arg;
if (!parseKeeperPath(pos, expected, arg))
String path;
if (!parseKeeperPath(pos, expected, path))
return false;
node->args.push_back(std::move(arg));
node->args.push_back(std::move(path));
String arg;
if (!parseKeeperArg(pos, expected, arg))
return false;
node->args.push_back(std::move(arg));
@ -143,10 +145,10 @@ void TouchCommand::execute(const ASTKeeperQuery * query, KeeperClient * client)
bool GetCommand::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const
{
String arg;
if (!parseKeeperPath(pos, expected, arg))
String path;
if (!parseKeeperPath(pos, expected, path))
return false;
node->args.push_back(std::move(arg));
node->args.push_back(std::move(path));
return true;
}
@ -156,13 +158,28 @@ void GetCommand::execute(const ASTKeeperQuery * query, KeeperClient * client) co
std::cout << client->zookeeper->get(client->getAbsolutePath(query->args[0].safeGet<String>())) << "\n";
}
bool ExistsCommand::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, DB::Expected & expected) const
{
String path;
if (!parseKeeperPath(pos, expected, path))
return false;
node->args.push_back(std::move(path));
return true;
}
void ExistsCommand::execute(const DB::ASTKeeperQuery * query, DB::KeeperClient * client) const
{
std::cout << client->zookeeper->exists(client->getAbsolutePath(query->args[0].safeGet<String>())) << "\n";
}
bool GetStatCommand::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const
{
String arg;
if (!parseKeeperPath(pos, expected, arg))
String path;
if (!parseKeeperPath(pos, expected, path))
return true;
node->args.push_back(std::move(arg));
node->args.push_back(std::move(path));
return true;
}
@ -325,25 +342,33 @@ void FindBigFamily::execute(const ASTKeeperQuery * query, KeeperClient * client)
bool RMCommand::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const
{
String arg;
if (!parseKeeperPath(pos, expected, arg))
String path;
if (!parseKeeperPath(pos, expected, path))
return false;
node->args.push_back(std::move(arg));
node->args.push_back(std::move(path));
ASTPtr version;
if (ParserNumber{}.parse(pos, version, expected))
node->args.push_back(version->as<ASTLiteral &>().value);
return true;
}
void RMCommand::execute(const ASTKeeperQuery * query, KeeperClient * client) const
{
client->zookeeper->remove(client->getAbsolutePath(query->args[0].safeGet<String>()));
Int32 version{-1};
if (query->args.size() == 2)
version = static_cast<Int32>(query->args[1].get<Int32>());
client->zookeeper->remove(client->getAbsolutePath(query->args[0].safeGet<String>()), version);
}
bool RMRCommand::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const
{
String arg;
if (!parseKeeperPath(pos, expected, arg))
String path;
if (!parseKeeperPath(pos, expected, path))
return false;
node->args.push_back(std::move(arg));
node->args.push_back(std::move(path));
return true;
}
@ -351,8 +376,72 @@ bool RMRCommand::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & nod
void RMRCommand::execute(const ASTKeeperQuery * query, KeeperClient * client) const
{
String path = client->getAbsolutePath(query->args[0].safeGet<String>());
client->askConfirmation("You are going to recursively delete path " + path,
[client, path]{ client->zookeeper->removeRecursive(path); });
client->askConfirmation(
"You are going to recursively delete path " + path, [client, path] { client->zookeeper->removeRecursive(path); });
}
bool ReconfigCommand::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, DB::Expected & expected) const
{
ReconfigCommand::Operation operation;
if (ParserKeyword{"ADD"}.ignore(pos, expected))
operation = ReconfigCommand::Operation::ADD;
else if (ParserKeyword{"REMOVE"}.ignore(pos, expected))
operation = ReconfigCommand::Operation::REMOVE;
else if (ParserKeyword{"SET"}.ignore(pos, expected))
operation = ReconfigCommand::Operation::SET;
else
return false;
node->args.push_back(operation);
ParserToken{TokenType::Whitespace}.ignore(pos);
String arg;
if (!parseKeeperArg(pos, expected, arg))
return false;
node->args.push_back(std::move(arg));
return true;
}
void ReconfigCommand::execute(const DB::ASTKeeperQuery * query, DB::KeeperClient * client) const
{
String joining;
String leaving;
String new_members;
auto operation = query->args[0].get<ReconfigCommand::Operation>();
switch (operation)
{
case static_cast<UInt8>(ReconfigCommand::Operation::ADD):
joining = query->args[1].safeGet<DB::String>();
break;
case static_cast<UInt8>(ReconfigCommand::Operation::REMOVE):
leaving = query->args[1].safeGet<DB::String>();
break;
case static_cast<UInt8>(ReconfigCommand::Operation::SET):
new_members = query->args[1].safeGet<DB::String>();
break;
default:
UNREACHABLE();
}
auto response = client->zookeeper->reconfig(joining, leaving, new_members);
std::cout << response.value << '\n';
}
bool SyncCommand::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, DB::Expected & expected) const
{
String path;
if (!parseKeeperPath(pos, expected, path))
return false;
node->args.push_back(std::move(path));
return true;
}
void SyncCommand::execute(const DB::ASTKeeperQuery * query, DB::KeeperClient * client) const
{
std::cout << client->zookeeper->sync(client->getAbsolutePath(query->args[0].safeGet<String>())) << "\n";
}
bool HelpCommand::parse(IParser::Pos & /* pos */, std::shared_ptr<ASTKeeperQuery> & /* node */, Expected & /* expected */) const

47
programs/keeper-client/Commands.h
View File

@ -51,7 +51,7 @@ class CDCommand : public IKeeperClientCommand
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
String getHelpMessage() const override { return "{} [path] -- Change the working path (default `.`)"; }
String getHelpMessage() const override { return "{} [path] -- Changes the working path (default `.`)"; }
};
class SetCommand : public IKeeperClientCommand
@ -64,7 +64,7 @@ class SetCommand : public IKeeperClientCommand
String getHelpMessage() const override
{
return "{} <path> <value> [version] -- Updates the node's value. Only update if version matches (default: -1)";
return "{} <path> <value> [version] -- Updates the node's value. Only updates if version matches (default: -1)";
}
};
@ -101,6 +101,17 @@ class GetCommand : public IKeeperClientCommand
String getHelpMessage() const override { return "{} <path> -- Returns the node's value"; }
};
class ExistsCommand : public IKeeperClientCommand
{
String getName() const override { return "exists"; }
bool parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const override;
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
String getHelpMessage() const override { return "{} <path> -- Returns `1` if node exists, `0` otherwise"; }
};
class GetStatCommand : public IKeeperClientCommand
{
String getName() const override { return "get_stat"; }
@ -154,7 +165,6 @@ class FindBigFamily : public IKeeperClientCommand
}
};
class RMCommand : public IKeeperClientCommand
{
String getName() const override { return "rm"; }
@ -163,7 +173,7 @@ class RMCommand : public IKeeperClientCommand
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
String getHelpMessage() const override { return "{} <path> -- Remove the node"; }
String getHelpMessage() const override { return "{} <path> [version] -- Removes the node only if version matches (default: -1)"; }
};
class RMRCommand : public IKeeperClientCommand
@ -177,6 +187,35 @@ class RMRCommand : public IKeeperClientCommand
String getHelpMessage() const override { return "{} <path> -- Recursively deletes path. Confirmation required"; }
};
class ReconfigCommand : public IKeeperClientCommand
{
enum class Operation : UInt8
{
ADD = 0,
REMOVE = 1,
SET = 2,
};
String getName() const override { return "reconfig"; }
bool parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const override;
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
String getHelpMessage() const override { return "{} <add|remove|set> \"<arg>\" [version] -- Reconfigure Keeper cluster. See https://clickhouse.com/docs/en/guides/sre/keeper/clickhouse-keeper#reconfiguration"; }
};
class SyncCommand: public IKeeperClientCommand
{
String getName() const override { return "sync"; }
bool parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const override;
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
String getHelpMessage() const override { return "{} <path> -- Synchronizes node between processes and leader"; }
};
class HelpCommand : public IKeeperClientCommand
{
String getName() const override { return "help"; }

98
programs/keeper-client/KeeperClient.cpp
View File

@ -84,8 +84,11 @@ std::vector<String> KeeperClient::getCompletions(const String & prefix) const
void KeeperClient::askConfirmation(const String & prompt, std::function<void()> && callback)
{
if (!ask_confirmation)
return callback();
std::cout << prompt << " Continue?\n";
need_confirmation = true;
waiting_confirmation = true;
confirmation_callback = callback;
}
@ -170,6 +173,14 @@ void KeeperClient::defineOptions(Poco::Util::OptionSet & options)
Poco::Util::Option("log-level", "", "set log level")
.argument("<level>")
.binding("log-level"));
options.addOption(
Poco::Util::Option("no-confirmation", "", "if set, will not require a confirmation on several commands. default false for interactive and true for query")
.binding("no-confirmation"));
options.addOption(
Poco::Util::Option("tests-mode", "", "run keeper-client in a special mode for tests. all commands output are separated by special symbols. default false")
.binding("tests-mode"));
}
void KeeperClient::initialize(Poco::Util::Application & /* self */)
@ -184,12 +195,15 @@ void KeeperClient::initialize(Poco::Util::Application & /* self */)
std::make_shared<CreateCommand>(),
std::make_shared<TouchCommand>(),
std::make_shared<GetCommand>(),
std::make_shared<ExistsCommand>(),
std::make_shared<GetStatCommand>(),
std::make_shared<FindSuperNodes>(),
std::make_shared<DeleteStaleBackups>(),
std::make_shared<FindBigFamily>(),
std::make_shared<RMCommand>(),
std::make_shared<RMRCommand>(),
std::make_shared<ReconfigCommand>(),
std::make_shared<SyncCommand>(),
std::make_shared<HelpCommand>(),
std::make_shared<FourLetterWordCommand>(),
});
@ -229,18 +243,6 @@ void KeeperClient::initialize(Poco::Util::Application & /* self */)
EventNotifier::init();
}
void KeeperClient::executeQuery(const String & query)
{
std::vector<String> queries;
boost::algorithm::split(queries, query, boost::is_any_of(";"));
for (const auto & query_text : queries)
{
if (!query_text.empty())
processQueryText(query_text);
}
}
bool KeeperClient::processQueryText(const String & text)
{
if (exit_strings.find(text) != exit_strings.end())
@ -248,29 +250,44 @@ bool KeeperClient::processQueryText(const String & text)
try
{
if (need_confirmation)
if (waiting_confirmation)
{
need_confirmation = false;
waiting_confirmation = false;
if (text.size() == 1 && (text == "y" || text == "Y"))
confirmation_callback();
return true;
}
KeeperParser parser;
String message;
const char * begin = text.data();
ASTPtr res = tryParseQuery(parser, begin, begin + text.size(), message, true, "", false, 0, 0, false);
const char * end = begin + text.size();
if (!res)
while (begin < end)
{
std::cerr << message << "\n";
return true;
String message;
ASTPtr res = tryParseQuery(
parser,
begin,
end,
/* out_error_message = */ message,
/* hilite = */ true,
/* description = */ "",
/* allow_multi_statements = */ true,
/* max_query_size = */ 0,
/* max_parser_depth = */ 0,
/* skip_insignificant = */ false);
if (!res)
{
std::cerr << message << "\n";
return true;
}
auto * query = res->as<ASTKeeperQuery>();
auto command = KeeperClient::commands.find(query->command);
command->second->execute(query, this);
}
auto * query = res->as<ASTKeeperQuery>();
auto command = KeeperClient::commands.find(query->command);
command->second->execute(query, this);
}
catch (Coordination::Exception & err)
{
@ -279,7 +296,7 @@ bool KeeperClient::processQueryText(const String & text)
return true;
}
void KeeperClient::runInteractive()
void KeeperClient::runInteractiveReplxx()
{
LineReader::Patterns query_extenders = {"\\"};
@ -299,7 +316,7 @@ void KeeperClient::runInteractive()
while (true)
{
String prompt;
if (need_confirmation)
if (waiting_confirmation)
prompt = "[y/n] ";
else
prompt = cwd.string() + " :) ";
@ -313,6 +330,26 @@ void KeeperClient::runInteractive()
}
}
void KeeperClient::runInteractiveInputStream()
{
for (String input; std::getline(std::cin, input);)
{
if (!processQueryText(input))
break;
std::cout << "\a\a\a\a" << std::endl;
std::cerr << std::flush;
}
}
void KeeperClient::runInteractive()
{
if (config().hasOption("tests-mode"))
runInteractiveInputStream();
else
runInteractiveReplxx();
}
int KeeperClient::main(const std::vector<String> & /* args */)
{
if (config().hasOption("help"))
@ -362,8 +399,13 @@ int KeeperClient::main(const std::vector<String> & /* args */)
zk_args.operation_timeout_ms = config().getInt("operation-timeout", 10) * 1000;
zookeeper = std::make_unique<zkutil::ZooKeeper>(zk_args);
if (config().has("no-confirmation") || config().has("query"))
ask_confirmation = false;
if (config().has("query"))
executeQuery(config().getString("query"));
{
processQueryText(config().getString("query"));
}
else
runInteractive();

7
programs/keeper-client/KeeperClient.h
View File

@ -49,8 +49,10 @@ public:
protected:
void runInteractive();
void runInteractiveReplxx();
void runInteractiveInputStream();
bool processQueryText(const String & text);
void executeQuery(const String & query);
void loadCommands(std::vector<Command> && new_commands);
@ -61,7 +63,8 @@ protected:
zkutil::ZooKeeperArgs zk_args;
bool need_confirmation = false;
bool ask_confirmation = true;
bool waiting_confirmation = false;
std::vector<String> registered_commands_and_four_letter_words;
};

33
programs/keeper-client/Parser.cpp
View File

@ -7,43 +7,32 @@ namespace DB
bool parseKeeperArg(IParser::Pos & pos, Expected & expected, String & result)
{
expected.add(pos, getTokenName(TokenType::BareWord));
if (pos->type == TokenType::BareWord)
if (pos->type == TokenType::QuotedIdentifier || pos->type == TokenType::StringLiteral)
{
result = String(pos->begin, pos->end);
++pos;
ParserToken{TokenType::Whitespace}.ignore(pos);
return true;
if (!parseIdentifierOrStringLiteral(pos, expected, result))
return false;
}
bool status = parseIdentifierOrStringLiteral(pos, expected, result);
ParserToken{TokenType::Whitespace}.ignore(pos);
return status;
}
bool parseKeeperPath(IParser::Pos & pos, Expected & expected, String & path)
{
expected.add(pos, "path");
if (pos->type == TokenType::QuotedIdentifier || pos->type == TokenType::StringLiteral)
return parseIdentifierOrStringLiteral(pos, expected, path);
String result;
while (pos->type != TokenType::Whitespace && pos->type != TokenType::EndOfStream)
while (pos->type != TokenType::Whitespace && pos->type != TokenType::EndOfStream && pos->type != TokenType::Semicolon)
{
result.append(pos->begin, pos->end);
++pos;
}
ParserToken{TokenType::Whitespace}.ignore(pos);
if (result.empty())
return false;
path = result;
return true;
}
bool parseKeeperPath(IParser::Pos & pos, Expected & expected, String & path)
{
expected.add(pos, "path");
return parseKeeperArg(pos, expected, path);
}
bool KeeperParser::parseImpl(Pos & pos, ASTPtr & node, Expected & expected)
{
auto query = std::make_shared<ASTKeeperQuery>();

23
programs/local/LocalServer.cpp
View File

@ -319,7 +319,7 @@ static bool checkIfStdinIsRegularFile()
std::string LocalServer::getInitialCreateTableQuery()
{
if (!config().has("table-structure") && !config().has("table-file") && !config().has("table-data-format") && (!checkIfStdinIsRegularFile() || !config().has("query")))
if (!config().has("table-structure") && !config().has("table-file") && !config().has("table-data-format") && (!checkIfStdinIsRegularFile() || queries.empty()))
return {};
auto table_name = backQuoteIfNeed(config().getString("table-name", "table"));
@ -461,7 +461,7 @@ try
if (first_time)
{
if (queries_files.empty() && !config().has("query"))
if (queries_files.empty() && queries.empty())
{
std::cerr << "\033[31m" << "ClickHouse compiled in fuzzing mode." << "\033[0m" << std::endl;
std::cerr << "\033[31m" << "You have to provide a query with --query or --queries-file option." << "\033[0m" << std::endl;
@ -473,7 +473,7 @@ try
#else
is_interactive = stdin_is_a_tty
&& (config().hasOption("interactive")
|| (!config().has("query") && !config().has("table-structure") && queries_files.empty() && !config().has("table-file")));
|| (queries.empty() && !config().has("table-structure") && queries_files.empty() && !config().has("table-file")));
#endif
if (!is_interactive)
{
@ -569,20 +569,17 @@ void LocalServer::updateLoggerLevel(const String & logs_level)
void LocalServer::processConfig()
{
if (config().has("query") && config().has("queries-file"))
if (!queries.empty() && config().has("queries-file"))
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Options '--query' and '--queries-file' cannot be specified at the same time");
delayed_interactive = config().has("interactive") && (config().has("query") || config().has("queries-file"));
if (is_interactive && !delayed_interactive)
{
if (config().has("multiquery"))
is_multiquery = true;
}
else
if (config().has("multiquery"))
is_multiquery = true;
delayed_interactive = config().has("interactive") && (!queries.empty() || config().has("queries-file"));
if (!is_interactive || delayed_interactive)
{
echo_queries = config().hasOption("echo") || config().hasOption("verbose");
ignore_error = config().getBool("ignore-error", false);
is_multiquery = true;
}
print_stack_trace = config().getBool("stacktrace", false);
@ -881,6 +878,8 @@ void LocalServer::processOptions(const OptionsDescription &, const CommandLineOp
config().setBool("no-system-tables", true);
if (options.count("only-system-tables"))
config().setBool("only-system-tables", true);
if (options.count("database"))
config().setString("default_database", options["database"].as<std::string>());
if (options.count("input-format"))
config().setString("table-data-format", options["input-format"].as<std::string>());

2
programs/server/Server.cpp
View File

@ -1393,7 +1393,7 @@ try
const auto interserver_listen_hosts = getInterserverListenHosts(config());
const auto listen_try = getListenTry(config());
if (config().has("keeper_server"))
if (config().has("keeper_server.server_id"))
{
#if USE_NURAFT
//// If we don't have configured connection probably someone trying to use clickhouse-server instead

10
programs/static-files-disk-uploader/static-files-disk-uploader.cpp
View File

@ -10,9 +10,17 @@
#include <Disks/IO/createReadBufferFromFileBase.h>
#include <boost/program_options.hpp>
#include <re2/re2.h>
#include <filesystem>
#ifdef __clang__
# pragma clang diagnostic push
# pragma clang diagnostic ignored "-Wzero-as-null-pointer-constant"
#endif
#include <re2/re2.h>
#ifdef __clang__
# pragma clang diagnostic pop
#endif
namespace fs = std::filesystem;
#define EXTRACT_PATH_PATTERN ".*\\/store/(.*)"

9
src/Access/AccessControl.cpp
View File

@ -26,10 +26,17 @@
#include <IO/Operators.h>
#include <Poco/AccessExpireCache.h>
#include <boost/algorithm/string/join.hpp>
#include <re2/re2.h>
#include <filesystem>
#include <mutex>
#ifdef __clang__
# pragma clang diagnostic push
# pragma clang diagnostic ignored "-Wzero-as-null-pointer-constant"
#endif
#include <re2/re2.h>
#ifdef __clang__
# pragma clang diagnostic pop
#endif
namespace DB
{

Some files were not shown because too many files have changed in this diff Show More