thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-22 15:42:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' of github.com:ClickHouse/ClickHouse into show-create-system-tables

Browse Source
This commit is contained in:
Nikita Mikhaylov 2024-05-17 12:21:50 +00:00
commit 9f33a6d9c0
1086 changed files with 11290 additions and 4805 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.clang-format
View File

@ -89,7 +89,7 @@ PenaltyBreakFirstLessLess: 120
PenaltyBreakString: 1000
PenaltyExcessCharacter: 1000000
PenaltyReturnTypeOnItsOwnLine: 60
RemoveBracesLLVM: true
RemoveBracesLLVM: false
SpaceAfterCStyleCast: false
SpaceBeforeAssignmentOperators: true
SpaceBeforeParens: ControlStatements

18
.clang-tidy
View File

@ -123,7 +123,23 @@ Checks: [
'-readability-uppercase-literal-suffix',
'-readability-use-anyofallof',
'-zircon-*'
'-zircon-*',
# These are new in clang-18, and we have to sort them out:
'-readability-avoid-nested-conditional-operator',
'-modernize-use-designated-initializers',
'-performance-enum-size',
'-readability-redundant-inline-specifier',
'-readability-redundant-member-init',
'-bugprone-crtp-constructor-accessibility',
'-bugprone-suspicious-stringview-data-usage',
'-bugprone-multi-level-implicit-pointer-conversion',
'-cert-err33-c',
# This is a good check, but clang-tidy crashes, see https://github.com/llvm/llvm-project/issues/91872
'-modernize-use-constraints',
# https://github.com/abseil/abseil-cpp/issues/1667
'-clang-analyzer-optin.core.EnumCastOutOfRange'
]
WarningsAsErrors: '*'

2
.github/PULL_REQUEST_TEMPLATE.md vendored
View File

@ -85,4 +85,4 @@ At a minimum, the following information should be added (but add more as needed)
- [ ] <!---batch_2--> 3
- [ ] <!---batch_3--> 4
<details>
</details>

6
.github/workflows/backport_branches.yml vendored
View File

@ -9,6 +9,12 @@ on: # yamllint disable-line rule:truthy
push:
branches:
- 'backport/**'
# Cancel the previous wf run in PRs.
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
jobs:
RunConfig:
runs-on: [self-hosted, style-checker-aarch64]

19
.github/workflows/cancel.yml vendored
View File

@ -1,19 +0,0 @@
name: Cancel
env:
# Force the stdout and stderr streams to be unbuffered
PYTHONUNBUFFERED: 1
on: # yamllint disable-line rule:truthy
workflow_run:
workflows: ["PullRequestCI", "ReleaseBranchCI", "DocsCheck", "BackportPR"]
types:
- requested
jobs:
cancel:
runs-on: [self-hosted, style-checker]
steps:
- uses: styfle/cancel-workflow-action@0.9.1
with:
all_but_latest: true
workflow_id: ${{ github.event.workflow.id }}

11
.github/workflows/debug.yml vendored
View File

@ -1,11 +0,0 @@
# The CI for each commit, prints envs and content of GITHUB_EVENT_PATH
name: Debug
'on':
[push, pull_request, pull_request_review, release, workflow_dispatch, workflow_call]
jobs:
DebugInfo:
runs-on: ubuntu-latest
steps:
- uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6

96
.github/workflows/merge_queue.yml vendored Normal file
View File

@ -0,0 +1,96 @@
# yamllint disable rule:comments-indentation
name: MergeQueueCI
env:
# Force the stdout and stderr streams to be unbuffered
PYTHONUNBUFFERED: 1
on: # yamllint disable-line rule:truthy
merge_group:
jobs:
RunConfig:
runs-on: [self-hosted, style-checker-aarch64]
outputs:
data: ${{ steps.runconfig.outputs.CI_DATA }}
steps:
- name: DebugInfo
uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true # to ensure correct digests
fetch-depth: 0 # to get version
filter: tree:0
- name: Python unit tests
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
echo "Testing the main ci directory"
python3 -m unittest discover -s . -p 'test_*.py'
for dir in *_lambda/; do
echo "Testing $dir"
python3 -m unittest discover -s "$dir" -p 'test_*.py'
done
- name: PrepareRunConfig
id: runconfig
run: |
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --configure --outfile ${{ runner.temp }}/ci_run_data.json
echo "::group::CI configuration"
python3 -m json.tool ${{ runner.temp }}/ci_run_data.json
echo "::endgroup::"
{
echo 'CI_DATA<<EOF'
cat ${{ runner.temp }}/ci_run_data.json
echo 'EOF'
} >> "$GITHUB_OUTPUT"
BuildDockers:
needs: [RunConfig]
if: ${{ !failure() && !cancelled() && toJson(fromJson(needs.RunConfig.outputs.data).docker_data.missing_multi) != '[]' }}
uses: ./.github/workflows/reusable_docker.yml
with:
data: ${{ needs.RunConfig.outputs.data }}
StyleCheck:
needs: [RunConfig, BuildDockers]
if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'Style check')}}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Style check
runner_type: style-checker
run_command: |
python3 style_check.py
data: ${{ needs.RunConfig.outputs.data }}
secrets:
secret_envs: |
ROBOT_CLICKHOUSE_SSH_KEY<<RCSK
${{secrets.ROBOT_CLICKHOUSE_SSH_KEY}}
RCSK
FastTest:
needs: [RunConfig, BuildDockers]
if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'Fast test') }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Fast test
runner_type: builder
data: ${{ needs.RunConfig.outputs.data }}
run_command: |
python3 fast_test_check.py
################################# Stage Final #################################
#
FinishCheck:
if: ${{ !failure() && !cancelled() }}
needs: [RunConfig, BuildDockers, StyleCheck, FastTest]
runs-on: [self-hosted, style-checker]
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
- name: Check sync status
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 sync_pr.py --status
- name: Finish label
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 finish_check.py ${{ (contains(needs.*.result, 'failure') && github.event_name == 'merge_group') && '--pipeline-failure' || '' }}

5
.github/workflows/nightly.yml vendored
View File

@ -10,14 +10,13 @@ env:
workflow_dispatch:
jobs:
Debug:
# The task for having a preserved ENV and event.json for later investigation
uses: ./.github/workflows/debug.yml
RunConfig:
runs-on: [self-hosted, style-checker-aarch64]
outputs:
data: ${{ steps.runconfig.outputs.CI_DATA }}
steps:
- name: DebugInfo
uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:

28
.github/workflows/pull_request.yml vendored
View File

@ -6,7 +6,6 @@ env:
PYTHONUNBUFFERED: 1
on: # yamllint disable-line rule:truthy
merge_group:
pull_request:
types:
- synchronize
@ -15,6 +14,11 @@ on: # yamllint disable-line rule:truthy
branches:
- master
# Cancel the previous wf run in PRs.
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
jobs:
RunConfig:
runs-on: [self-hosted, style-checker-aarch64]
@ -30,7 +34,6 @@ jobs:
fetch-depth: 0 # to get version
filter: tree:0
- name: Labels check
if: ${{ github.event_name != 'merge_group' }}
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 run_check.py
@ -58,7 +61,6 @@ jobs:
echo 'EOF'
} >> "$GITHUB_OUTPUT"
- name: Re-create GH statuses for skipped jobs if any
if: ${{ github.event_name != 'merge_group' }}
run: |
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --infile ${{ runner.temp }}/ci_run_data.json --update-gh-statuses
BuildDockers:
@ -83,7 +85,7 @@ jobs:
${{secrets.ROBOT_CLICKHOUSE_SSH_KEY}}
RCSK
FastTest:
needs: [RunConfig, BuildDockers]
needs: [RunConfig, BuildDockers, StyleCheck]
if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'Fast test') }}
uses: ./.github/workflows/reusable_test.yml
with:
@ -163,20 +165,16 @@ jobs:
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
- name: Check sync status
if: ${{ github.event_name == 'merge_group' }}
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 sync_pr.py --status
- name: Finish label
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 finish_check.py ${{ (contains(needs.*.result, 'failure') && github.event_name == 'merge_group') && '--pipeline-failure' || '' }}
- name: Auto merge if approved
if: ${{ github.event_name != 'merge_group' }}
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 merge_pr.py --check-approved
python3 finish_check.py
# FIXME: merge on approval does not work with MQ. Could be fixed by using defaul GH's automerge after some corrections in Mergeable Check status
# - name: Auto merge if approved
# if: ${{ github.event_name != 'merge_group' }}
# run: |
# cd "$GITHUB_WORKSPACE/tests/ci"
# python3 merge_pr.py --check-approved
#############################################################################################

23
.github/workflows/pull_request_approved.yml vendored
View File

@ -1,23 +0,0 @@
name: PullRequestApprovedCI
env:
# Force the stdout and stderr streams to be unbuffered
PYTHONUNBUFFERED: 1
on: # yamllint disable-line rule:truthy
pull_request_review:
types:
- submitted
jobs:
MergeOnApproval:
runs-on: [self-hosted, style-checker]
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Merge approved PR
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 merge_pr.py --check-approved

2
.gitmodules vendored
View File

@ -6,7 +6,7 @@
url = https://github.com/facebook/zstd
[submodule "contrib/lz4"]
path = contrib/lz4
url = https://github.com/ClickHouse/lz4
url = https://github.com/lz4/lz4
[submodule "contrib/librdkafka"]
path = contrib/librdkafka
url = https://github.com/ClickHouse/librdkafka

119
CMakeLists.txt
View File

@ -135,23 +135,21 @@ endif ()
include (cmake/check_flags.cmake)
include (cmake/add_warning.cmake)
if (COMPILER_CLANG)
# generate ranges for fast "addr2line" search
if (NOT CMAKE_BUILD_TYPE_UC STREQUAL "RELEASE")
# NOTE: that clang has a bug because of it does not emit .debug_aranges
# with ThinLTO, so custom ld.lld wrapper is shipped in docker images.
set(COMPILER_FLAGS "${COMPILER_FLAGS} -gdwarf-aranges")
endif ()
# See https://blog.llvm.org/posts/2021-04-05-constructor-homing-for-debug-info/
if (CMAKE_BUILD_TYPE_UC STREQUAL "DEBUG" OR CMAKE_BUILD_TYPE_UC STREQUAL "RELWITHDEBINFO")
set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Xclang -fuse-ctor-homing")
set (CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -Xclang -fuse-ctor-homing")
endif()
no_warning(enum-constexpr-conversion) # breaks Protobuf in clang-16
# generate ranges for fast "addr2line" search
if (NOT CMAKE_BUILD_TYPE_UC STREQUAL "RELEASE")
# NOTE: that clang has a bug because of it does not emit .debug_aranges
# with ThinLTO, so custom ld.lld wrapper is shipped in docker images.
set(COMPILER_FLAGS "${COMPILER_FLAGS} -gdwarf-aranges")
endif ()
# See https://blog.llvm.org/posts/2021-04-05-constructor-homing-for-debug-info/
if (CMAKE_BUILD_TYPE_UC STREQUAL "DEBUG" OR CMAKE_BUILD_TYPE_UC STREQUAL "RELWITHDEBINFO")
set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Xclang -fuse-ctor-homing")
set (CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -Xclang -fuse-ctor-homing")
endif()
no_warning(enum-constexpr-conversion) # breaks Protobuf in clang-16
option(ENABLE_TESTS "Provide unit_test_dbms target with Google.Test unit tests" ON)
option(ENABLE_EXAMPLES "Build all example programs in 'examples' subdirectories" OFF)
option(ENABLE_BENCHMARKS "Build all benchmark programs in 'benchmarks' subdirectories" OFF)
@ -284,16 +282,12 @@ endif ()
option (ENABLE_BUILD_PROFILING "Enable profiling of build time" OFF)
if (ENABLE_BUILD_PROFILING)
if (COMPILER_CLANG)
set (COMPILER_FLAGS "${COMPILER_FLAGS} -ftime-trace")
set (COMPILER_FLAGS "${COMPILER_FLAGS} -ftime-trace")
if (LINKER_NAME MATCHES "lld")
set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,--time-trace")
set (CMAKE_MODULE_LINKER_FLAGS "${CMAKE_MODULE_LINKER_FLAGS} -Wl,--time-trace")
endif ()
else ()
message (${RECONFIGURE_MESSAGE_LEVEL} "Build profiling is only available with CLang")
endif ()
if (LINKER_NAME MATCHES "lld")
set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,--time-trace")
set (CMAKE_MODULE_LINKER_FLAGS "${CMAKE_MODULE_LINKER_FLAGS} -Wl,--time-trace")
endif ()
endif ()
set (CMAKE_CXX_STANDARD 23)
@ -304,22 +298,20 @@ set (CMAKE_C_STANDARD 11)
set (CMAKE_C_EXTENSIONS ON) # required by most contribs written in C
set (CMAKE_C_STANDARD_REQUIRED ON)
if (COMPILER_CLANG)
# Enable C++14 sized global deallocation functions. It should be enabled by setting -std=c++14 but I'm not sure.
# See https://reviews.llvm.org/D112921
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsized-deallocation")
# Enable C++14 sized global deallocation functions. It should be enabled by setting -std=c++14 but I'm not sure.
# See https://reviews.llvm.org/D112921
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsized-deallocation")
# falign-functions=32 prevents from random performance regressions with the code change. Thus, providing more stable
# benchmarks.
set(COMPILER_FLAGS "${COMPILER_FLAGS} -falign-functions=32")
# falign-functions=32 prevents from random performance regressions with the code change. Thus, providing more stable
# benchmarks.
set(COMPILER_FLAGS "${COMPILER_FLAGS} -falign-functions=32")
if (ARCH_AMD64)
# align branches within a 32-Byte boundary to avoid the potential performance loss when code layout change,
# which makes benchmark results more stable.
set(BRANCHES_WITHIN_32B_BOUNDARIES "-mbranches-within-32B-boundaries")
set(COMPILER_FLAGS "${COMPILER_FLAGS} ${BRANCHES_WITHIN_32B_BOUNDARIES}")
endif()
endif ()
if (ARCH_AMD64)
# align branches within a 32-Byte boundary to avoid the potential performance loss when code layout change,
# which makes benchmark results more stable.
set(BRANCHES_WITHIN_32B_BOUNDARIES "-mbranches-within-32B-boundaries")
set(COMPILER_FLAGS "${COMPILER_FLAGS} ${BRANCHES_WITHIN_32B_BOUNDARIES}")
endif()
# Disable floating-point expression contraction in order to get consistent floating point calculation results across platforms
set (COMPILER_FLAGS "${COMPILER_FLAGS} -ffp-contract=off")
@ -348,39 +340,34 @@ set (CMAKE_ASM_FLAGS "${CMAKE_ASM_FLAGS} ${COMPILER_FLAGS} $
set (CMAKE_ASM_FLAGS_RELWITHDEBINFO "${CMAKE_ASM_FLAGS_RELWITHDEBINFO} -O3 ${DEBUG_INFO_FLAGS} ${CMAKE_ASM_FLAGS_ADD}")
set (CMAKE_ASM_FLAGS_DEBUG "${CMAKE_ASM_FLAGS_DEBUG} -O0 ${DEBUG_INFO_FLAGS} ${CMAKE_ASM_FLAGS_ADD}")
if (COMPILER_CLANG)
if (OS_DARWIN)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -stdlib=libc++")
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,-U,_inside_main")
endif()
if (OS_DARWIN)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -stdlib=libc++")
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,-U,_inside_main")
endif()
# Display absolute paths in error messages. Otherwise KDevelop fails to navigate to correct file and opens a new file instead.
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fdiagnostics-absolute-paths")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -fdiagnostics-absolute-paths")
# Display absolute paths in error messages. Otherwise KDevelop fails to navigate to correct file and opens a new file instead.
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fdiagnostics-absolute-paths")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -fdiagnostics-absolute-paths")
if (NOT ENABLE_TESTS AND NOT SANITIZE AND NOT SANITIZE_COVERAGE AND OS_LINUX)
# https://clang.llvm.org/docs/ThinLTO.html
# Applies to clang and linux only.
# Disabled when building with tests or sanitizers.
option(ENABLE_THINLTO "Clang-specific link time optimization" ON)
endif()
if (NOT ENABLE_TESTS AND NOT SANITIZE AND NOT SANITIZE_COVERAGE AND OS_LINUX)
# https://clang.llvm.org/docs/ThinLTO.html
# Applies to clang and linux only.
# Disabled when building with tests or sanitizers.
option(ENABLE_THINLTO "Clang-specific link time optimization" ON)
endif()
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fstrict-vtable-pointers")
# We cannot afford to use LTO when compiling unit tests, and it's not enough
# to only supply -fno-lto at the final linking stage. So we disable it
# completely.
if (ENABLE_THINLTO AND NOT ENABLE_TESTS AND NOT SANITIZE)
# Link time optimization
set (CMAKE_C_FLAGS_RELWITHDEBINFO "${CMAKE_C_FLAGS_RELWITHDEBINFO} -flto=thin -fwhole-program-vtables")
set (CMAKE_CXX_FLAGS_RELWITHDEBINFO "${CMAKE_CXX_FLAGS_RELWITHDEBINFO} -flto=thin -fwhole-program-vtables")
set (CMAKE_EXE_LINKER_FLAGS_RELWITHDEBINFO "${CMAKE_EXE_LINKER_FLAGS_RELWITHDEBINFO} -flto=thin -fwhole-program-vtables")
elseif (ENABLE_THINLTO)
message (${RECONFIGURE_MESSAGE_LEVEL} "Cannot enable ThinLTO")
endif ()
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fstrict-vtable-pointers")
# We cannot afford to use LTO when compiling unit tests, and it's not enough
# to only supply -fno-lto at the final linking stage. So we disable it
# completely.
if (ENABLE_THINLTO AND NOT ENABLE_TESTS AND NOT SANITIZE)
# Link time optimization
set (CMAKE_C_FLAGS_RELWITHDEBINFO "${CMAKE_C_FLAGS_RELWITHDEBINFO} -flto=thin -fwhole-program-vtables")
set (CMAKE_CXX_FLAGS_RELWITHDEBINFO "${CMAKE_CXX_FLAGS_RELWITHDEBINFO} -flto=thin -fwhole-program-vtables")
set (CMAKE_EXE_LINKER_FLAGS_RELWITHDEBINFO "${CMAKE_EXE_LINKER_FLAGS_RELWITHDEBINFO} -flto=thin -fwhole-program-vtables")
elseif (ENABLE_THINLTO)
message (${RECONFIGURE_MESSAGE_LEVEL} "ThinLTO is only available with Clang")
message (${RECONFIGURE_MESSAGE_LEVEL} "Cannot enable ThinLTO")
endif ()
# Turns on all external libs like s3, kafka, ODBC, ...

2
README.md
View File

@ -40,7 +40,6 @@ Every month we get together with the community (users, contributors, customers,
Keep an eye out for upcoming meetups and events around the world. Somewhere else you want us to be? Please feel free to reach out to tyler `<at>` clickhouse `<dot>` com. You can also peruse [ClickHouse Events](https://clickhouse.com/company/news-events) for a list of all upcoming trainings, meetups, speaking engagements, etc.
* [ClickHouse Meetup in Bengaluru](https://www.meetup.com/clickhouse-bangalore-user-group/events/300405581/) - May 4
* [ClickHouse Happy Hour @ Tom's Watch Bar - Los Angeles](https://www.meetup.com/clickhouse-los-angeles-user-group/events/300740584/) - May 22
* [ClickHouse & Confluent Meetup in Dubai](https://www.meetup.com/clickhouse-dubai-meetup-group/events/299629189/) - May 28
* [ClickHouse Meetup in Stockholm](https://www.meetup.com/clickhouse-stockholm-user-group/events/299752651/) - Jun 3
@ -49,6 +48,7 @@ Keep an eye out for upcoming meetups and events around the world. Somewhere else
* [ClickHouse Meetup in Amsterdam](https://www.meetup.com/clickhouse-netherlands-user-group/events/300781068/) - Jun 27
* [ClickHouse Meetup in Paris](https://www.meetup.com/clickhouse-france-user-group/events/300783448/) - Jul 9
* [ClickHouse Meetup @ Ramp - New York City](https://www.meetup.com/clickhouse-new-york-user-group/events/300595845/) - Jul 9
* [ClickHouse Meetup @ Klaviyo - Boston](https://www.meetup.com/clickhouse-boston-user-group/events/300907870) - Jul 11
## Recent Recordings
* **Recent Meetup Videos**: [Meetup Playlist](https://www.youtube.com/playlist?list=PL0Z2YDlm0b3iNDUzpY1S3L_iV4nARda_U) Whenever possible recordings of the ClickHouse Community Meetups are edited and presented as individual talks. Current featuring "Modern SQL in 2023", "Fast, Concurrent, and Consistent Asynchronous INSERTS in ClickHouse", and "Full-Text Indices: Design and Experiments"

8
base/base/DecomposedFloat.h
View File

@ -51,11 +51,9 @@ struct DecomposedFloat
/// Returns 0 for both +0. and -0.
int sign() const
{
return (exponent() == 0 && mantissa() == 0)
? 0
: (isNegative()
? -1
: 1);
if (exponent() == 0 && mantissa() == 0)
return 0;
return isNegative() ? -1 : 1;
}
uint16_t exponent() const

2
base/base/EnumReflection.h
View File

@ -11,7 +11,7 @@ namespace detail
template <is_enum E, class F, size_t ...I>
constexpr void static_for(F && f, std::index_sequence<I...>)
{
(std::forward<F>(f)(std::integral_constant<E, magic_enum::enum_value<E>(I)>()) , ...);
(f(std::integral_constant<E, magic_enum::enum_value<E>(I)>()) , ...);
}
}

4
base/base/JSON.cpp
View File

@ -651,7 +651,9 @@ std::string_view JSON::getRawString() const
Pos s = ptr_begin;
if (*s != '"')
throw JSONException(std::string("JSON: expected \", got ") + *s);
while (++s != ptr_end && *s != '"');
++s;
while (s != ptr_end && *s != '"')
++s;
if (s != ptr_end)
return std::string_view(ptr_begin + 1, s - ptr_begin - 1);
throw JSONException("JSON: incorrect syntax (expected end of string, found end of JSON).");

2
base/base/JSON.h
View File

@ -74,7 +74,7 @@ public:
const char * data() const { return ptr_begin; }
const char * dataEnd() const { return ptr_end; }
enum ElementType
enum ElementType : uint8_t
{
TYPE_OBJECT,
TYPE_ARRAY,

2
base/base/TypeList.h
View File

@ -27,7 +27,7 @@ namespace TypeListUtils /// In some contexts it's more handy to use functions in
constexpr Root<Args...> changeRoot(TypeList<Args...>) { return {}; }
template <typename F, typename ...Args>
constexpr void forEach(TypeList<Args...>, F && f) { (std::forward<F>(f)(TypeList<Args>{}), ...); }
constexpr void forEach(TypeList<Args...>, F && f) { (f(TypeList<Args>{}), ...); }
}
template <typename TypeListLeft, typename TypeListRight>

2
base/base/constexpr_helpers.h
View File

@ -21,7 +21,7 @@ bool func_wrapper(Func && func, Arg && arg)
template <typename T, T Begin, typename Func, T... Is>
constexpr bool static_for_impl(Func && f, std::integer_sequence<T, Is...>)
{
return (func_wrapper(std::forward<Func>(f), std::integral_constant<T, Begin + Is>{}) || ...);
return (func_wrapper(f, std::integral_constant<T, Begin + Is>{}) || ...);
}
template <auto Begin, decltype(Begin) End, typename Func>

2
base/base/find_symbols.h
View File

@ -147,7 +147,7 @@ constexpr uint16_t maybe_negate(uint16_t x)
return ~x;
}
enum class ReturnMode
enum class ReturnMode : uint8_t
{
End,
Nullptr,

3
base/base/getMemoryAmount.cpp
View File

@ -77,8 +77,7 @@ uint64_t getMemoryAmountOrZero()
{
uint64_t limit_v1;
if (limit_file_v1 >> limit_v1)
if (limit_v1 < memory_amount)
memory_amount = limit_v1;
memory_amount = std::min(memory_amount, limit_v1);
}
}

10
base/base/hex.h
View File

@ -146,7 +146,7 @@ namespace impl
TUInt res;
if constexpr (sizeof(TUInt) == 1)
{
res = static_cast<UInt8>(unhexDigit(data[0])) * 0x10 + static_cast<UInt8>(unhexDigit(data[1]));
res = unhexDigit(data[0]) * 0x10 + unhexDigit(data[1]);
}
else if constexpr (sizeof(TUInt) == 2)
{
@ -176,17 +176,19 @@ namespace impl
};
/// Helper template class to convert a value of any supported type to hexadecimal representation and back.
template <typename T, typename SFINAE = void>
template <typename T>
struct HexConversion;
template <typename TUInt>
struct HexConversion<TUInt, std::enable_if_t<std::is_integral_v<TUInt>>> : public HexConversionUInt<TUInt> {};
requires(std::is_integral_v<TUInt>)
struct HexConversion<TUInt> : public HexConversionUInt<TUInt> {};
template <size_t Bits, typename Signed>
struct HexConversion<wide::integer<Bits, Signed>> : public HexConversionUInt<wide::integer<Bits, Signed>> {};
template <typename CityHashUInt128> /// Partial specialization here allows not to include <city.h> in this header.
struct HexConversion<CityHashUInt128, std::enable_if_t<std::is_same_v<CityHashUInt128, typename CityHash_v1_0_2::uint128>>>
requires(std::is_same_v<CityHashUInt128, typename CityHash_v1_0_2::uint128>)
struct HexConversion<CityHashUInt128>
{
static const constexpr size_t num_hex_digits = 32;

30
base/base/iostream_debug_helpers.h
View File

@ -20,24 +20,26 @@ Out & dumpValue(Out &, T &&);
/// Catch-all case.
template <int priority, typename Out, typename T>
std::enable_if_t<priority == -1, Out> & dumpImpl(Out & out, T &&) // NOLINT(cppcoreguidelines-missing-std-forward)
requires(priority == -1)
Out & dumpImpl(Out & out, T &&) // NOLINT(cppcoreguidelines-missing-std-forward)
{
return out << "{...}";
}
/// An object, that could be output with operator <<.
template <int priority, typename Out, typename T>
std::enable_if_t<priority == 0, Out> & dumpImpl(Out & out, T && x, std::decay_t<decltype(std::declval<Out &>() << std::declval<T>())> * = nullptr) // NOLINT(cppcoreguidelines-missing-std-forward)
requires(priority == 0)
Out & dumpImpl(Out & out, T && x, std::decay_t<decltype(std::declval<Out &>() << std::declval<T>())> * = nullptr) // NOLINT(cppcoreguidelines-missing-std-forward)
{
return out << x;
}
/// A pointer-like object.
template <int priority, typename Out, typename T>
std::enable_if_t<priority == 1
requires(priority == 1
/// Protect from the case when operator * do effectively nothing (function pointer).
&& !std::is_same_v<std::decay_t<T>, std::decay_t<decltype(*std::declval<T>())>>
, Out> & dumpImpl(Out & out, T && x, std::decay_t<decltype(*std::declval<T>())> * = nullptr) // NOLINT(cppcoreguidelines-missing-std-forward)
&& !std::is_same_v<std::decay_t<T>, std::decay_t<decltype(*std::declval<T>())>>)
Out & dumpImpl(Out & out, T && x, std::decay_t<decltype(*std::declval<T>())> * = nullptr) // NOLINT(cppcoreguidelines-missing-std-forward)
{
if (!x)
return out << "nullptr";
@ -46,7 +48,8 @@ std::enable_if_t<priority == 1
/// Container.
template <int priority, typename Out, typename T>
std::enable_if_t<priority == 2, Out> & dumpImpl(Out & out, T && x, std::decay_t<decltype(std::begin(std::declval<T>()))> * = nullptr) // NOLINT(cppcoreguidelines-missing-std-forward)
requires(priority == 2)
Out & dumpImpl(Out & out, T && x, std::decay_t<decltype(std::begin(std::declval<T>()))> * = nullptr) // NOLINT(cppcoreguidelines-missing-std-forward)
{
bool first = true;
out << "{";
@ -63,8 +66,8 @@ std::enable_if_t<priority == 2, Out> & dumpImpl(Out & out, T && x, std::decay_t<
template <int priority, typename Out, typename T>
std::enable_if_t<priority == 3 && std::is_enum_v<std::decay_t<T>>, Out> &
dumpImpl(Out & out, T && x) // NOLINT(cppcoreguidelines-missing-std-forward)
requires(priority == 3 && std::is_enum_v<std::decay_t<T>>)
Out & dumpImpl(Out & out, T && x) // NOLINT(cppcoreguidelines-missing-std-forward)
{
return out << magic_enum::enum_name(x);
}
@ -72,8 +75,8 @@ dumpImpl(Out & out, T && x) // NOLINT(cppcoreguidelines-missing-std-forward)
/// string and const char * - output not as container or pointer.
template <int priority, typename Out, typename T>
std::enable_if_t<priority == 3 && (std::is_same_v<std::decay_t<T>, std::string> || std::is_same_v<std::decay_t<T>, const char *>), Out> &
dumpImpl(Out & out, T && x) // NOLINT(cppcoreguidelines-missing-std-forward)
requires(priority == 3 && (std::is_same_v<std::decay_t<T>, std::string> || std::is_same_v<std::decay_t<T>, const char *>))
Out & dumpImpl(Out & out, T && x) // NOLINT(cppcoreguidelines-missing-std-forward)
{
return out << std::quoted(x);
}
@ -81,8 +84,8 @@ dumpImpl(Out & out, T && x) // NOLINT(cppcoreguidelines-missing-std-forward)
/// UInt8 - output as number, not char.
template <int priority, typename Out, typename T>
std::enable_if_t<priority == 3 && std::is_same_v<std::decay_t<T>, unsigned char>, Out> &
dumpImpl(Out & out, T && x) // NOLINT(cppcoreguidelines-missing-std-forward)
requires(priority == 3 && std::is_same_v<std::decay_t<T>, unsigned char>)
Out & dumpImpl(Out & out, T && x) // NOLINT(cppcoreguidelines-missing-std-forward)
{
return out << int(x);
}
@ -108,7 +111,8 @@ Out & dumpTupleImpl(Out & out, T && x) // NOLINT(cppcoreguidelines-missing-std-f
}
template <int priority, typename Out, typename T>
std::enable_if_t<priority == 4, Out> & dumpImpl(Out & out, T && x, std::decay_t<decltype(std::get<0>(std::declval<T>()))> * = nullptr) // NOLINT(cppcoreguidelines-missing-std-forward)
requires(priority == 4)
Out & dumpImpl(Out & out, T && x, std::decay_t<decltype(std::get<0>(std::declval<T>()))> * = nullptr) // NOLINT(cppcoreguidelines-missing-std-forward)
{
return dumpTupleImpl<0>(out, x);
}

6
base/base/itoa.cpp
View File

@ -250,14 +250,16 @@ ALWAYS_INLINE inline char * uitoa<UnsignedOfSize<1>, 1>(char * p, UnsignedOfSize
//===----------------------------------------------------------===//
// itoa: handle unsigned integral operands (selected by SFINAE)
template <typename U, std::enable_if_t<!std::is_signed_v<U> && std::is_integral_v<U>> * = nullptr>
template <typename U>
requires(!std::is_signed_v<U> && std::is_integral_v<U>)
ALWAYS_INLINE inline char * itoa(U u, char * p)
{
return convert::uitoa(p, u);
}
// itoa: handle signed integral operands (selected by SFINAE)
template <typename I, size_t N = sizeof(I), std::enable_if_t<std::is_signed_v<I> && std::is_integral_v<I>> * = nullptr>
template <typename I, size_t N = sizeof(I)>
requires(std::is_signed_v<I> && std::is_integral_v<I>)
ALWAYS_INLINE inline char * itoa(I i, char * p)
{
// Need "mask" to be filled with a copy of the sign bit.

12
base/base/map.h
View File

@ -19,8 +19,8 @@ auto map(const Collection<Params...> & collection, Mapper && mapper)
using value_type = unqualified_t<decltype(mapper(*std::begin(collection)))>;
return Collection<value_type>(
boost::make_transform_iterator(std::begin(collection), std::forward<Mapper>(mapper)),
boost::make_transform_iterator(std::end(collection), std::forward<Mapper>(mapper)));
boost::make_transform_iterator(std::begin(collection), mapper),
boost::make_transform_iterator(std::end(collection), mapper));
}
/** \brief Returns collection of specified container-type,
@ -33,8 +33,8 @@ auto map(const Collection & collection, Mapper && mapper)
using value_type = unqualified_t<decltype(mapper(*std::begin(collection)))>;
return ResultCollection<value_type>(
boost::make_transform_iterator(std::begin(collection), std::forward<Mapper>(mapper)),
boost::make_transform_iterator(std::end(collection), std::forward<Mapper>(mapper)));
boost::make_transform_iterator(std::begin(collection), mapper),
boost::make_transform_iterator(std::end(collection), mapper));
}
/** \brief Returns collection of specified type,
@ -45,8 +45,8 @@ template <typename ResultCollection, typename Collection, typename Mapper>
auto map(const Collection & collection, Mapper && mapper)
{
return ResultCollection(
boost::make_transform_iterator(std::begin(collection), std::forward<Mapper>(mapper)),
boost::make_transform_iterator(std::end(collection), std::forward<Mapper>(mapper)));
boost::make_transform_iterator(std::begin(collection), mapper),
boost::make_transform_iterator(std::end(collection), mapper));
}
}

14
base/base/range.h
View File

@ -23,12 +23,10 @@ namespace internal
/// For loop adaptor which is used to iterate through a half-closed interval [begin, end).
/// The parameters `begin` and `end` can have any integral or enum types.
template <typename BeginType,
typename EndType,
typename = std::enable_if_t<
(std::is_integral_v<BeginType> || std::is_enum_v<BeginType>) &&
(std::is_integral_v<EndType> || std::is_enum_v<EndType>) &&
(!std::is_enum_v<BeginType> || !std::is_enum_v<EndType> || std::is_same_v<BeginType, EndType>), void>>
template <typename BeginType, typename EndType>
requires((std::is_integral_v<BeginType> || std::is_enum_v<BeginType>) &&
(std::is_integral_v<EndType> || std::is_enum_v<EndType>) &&
(!std::is_enum_v<BeginType> || !std::is_enum_v<EndType> || std::is_same_v<BeginType, EndType>))
inline auto range(BeginType begin, EndType end)
{
if constexpr (std::is_integral_v<BeginType> && std::is_integral_v<EndType>)
@ -50,8 +48,8 @@ inline auto range(BeginType begin, EndType end)
/// For loop adaptor which is used to iterate through a half-closed interval [0, end).
/// The parameter `end` can have any integral or enum type.
/// The same as range(0, end).
template <typename Type,
typename = std::enable_if_t<std::is_integral_v<Type> || std::is_enum_v<Type>, void>>
template <typename Type>
requires(std::is_integral_v<Type> || std::is_enum_v<Type>)
inline auto range(Type end)
{
if constexpr (std::is_integral_v<Type>)

4
base/base/sleep.cpp
View File

@ -2,6 +2,7 @@
#include <ctime>
#include <cerrno>
#include <system_error>
#if defined(OS_DARWIN)
#include <mach/mach.h>
@ -34,7 +35,8 @@ void sleepForNanoseconds(uint64_t nanoseconds)
constexpr auto clock_type = CLOCK_MONOTONIC;
struct timespec current_time;
clock_gettime(clock_type, &current_time);
if (0 != clock_gettime(clock_type, &current_time))
throw std::system_error(std::error_code(errno, std::system_category()));
constexpr uint64_t resolution = 1'000'000'000;
struct timespec finish_time = current_time;

10
base/base/wide_integer.h
View File

@ -111,7 +111,8 @@ public:
constexpr explicit operator bool() const noexcept;
template <typename T, typename = std::enable_if_t<std::is_arithmetic_v<T>, T>>
template <typename T>
requires(std::is_arithmetic_v<T>)
constexpr operator T() const noexcept;
constexpr operator long double() const noexcept;
@ -208,12 +209,14 @@ constexpr integer<Bits, Signed> operator<<(const integer<Bits, Signed> & lhs, in
template <size_t Bits, typename Signed>
constexpr integer<Bits, Signed> operator>>(const integer<Bits, Signed> & lhs, int n) noexcept;
template <size_t Bits, typename Signed, typename Int, typename = std::enable_if_t<!std::is_same_v<Int, int>>>
template <size_t Bits, typename Signed, typename Int>
requires(!std::is_same_v<Int, int>)
constexpr integer<Bits, Signed> operator<<(const integer<Bits, Signed> & lhs, Int n) noexcept
{
return lhs << int(n);
}
template <size_t Bits, typename Signed, typename Int, typename = std::enable_if_t<!std::is_same_v<Int, int>>>
template <size_t Bits, typename Signed, typename Int>
requires(!std::is_same_v<Int, int>)
constexpr integer<Bits, Signed> operator>>(const integer<Bits, Signed> & lhs, Int n) noexcept
{
return lhs >> int(n);
@ -262,4 +265,3 @@ struct hash<wide::integer<Bits, Signed>>;
// NOLINTEND(*)
#include "wide_integer_impl.h"

3
base/base/wide_integer_impl.h
View File

@ -1246,7 +1246,8 @@ constexpr integer<Bits, Signed>::operator bool() const noexcept
}
template <size_t Bits, typename Signed>
template <class T, class>
template <class T>
requires(std::is_arithmetic_v<T>)
constexpr integer<Bits, Signed>::operator T() const noexcept
{
static_assert(std::numeric_limits<T>::is_integer);

4
cmake/clang_tidy.cmake
View File

@ -5,14 +5,14 @@ if (ENABLE_CLANG_TIDY)
find_program (CLANG_TIDY_CACHE_PATH NAMES "clang-tidy-cache")
if (CLANG_TIDY_CACHE_PATH)
find_program (_CLANG_TIDY_PATH NAMES "clang-tidy-17" "clang-tidy-16" "clang-tidy")
find_program (_CLANG_TIDY_PATH NAMES "clang-tidy-18" "clang-tidy-17" "clang-tidy-16" "clang-tidy")
# Why do we use ';' here?
# It's a cmake black magic: https://cmake.org/cmake/help/latest/prop_tgt/LANG_CLANG_TIDY.html#prop_tgt:%3CLANG%3E_CLANG_TIDY
# The CLANG_TIDY_PATH is passed to CMAKE_CXX_CLANG_TIDY, which follows CXX_CLANG_TIDY syntax.
set (CLANG_TIDY_PATH "${CLANG_TIDY_CACHE_PATH};${_CLANG_TIDY_PATH}" CACHE STRING "A combined command to run clang-tidy with caching wrapper")
else ()
find_program (CLANG_TIDY_PATH NAMES "clang-tidy-17" "clang-tidy-16" "clang-tidy")
find_program (CLANG_TIDY_PATH NAMES "clang-tidy-18" "clang-tidy-17" "clang-tidy-16" "clang-tidy")
endif ()
if (CLANG_TIDY_PATH)

16
cmake/linux/default_libs.cmake
View File

@ -5,17 +5,15 @@ set (DEFAULT_LIBS "-nodefaultlibs")
# We need builtins from Clang's RT even without libcxx - for ubsan+int128.
# See https://bugs.llvm.org/show_bug.cgi?id=16404
if (COMPILER_CLANG)
execute_process (COMMAND ${CMAKE_CXX_COMPILER} --target=${CMAKE_CXX_COMPILER_TARGET} --print-libgcc-file-name --rtlib=compiler-rt OUTPUT_VARIABLE BUILTINS_LIBRARY OUTPUT_STRIP_TRAILING_WHITESPACE)
execute_process (COMMAND ${CMAKE_CXX_COMPILER} --target=${CMAKE_CXX_COMPILER_TARGET} --print-libgcc-file-name --rtlib=compiler-rt OUTPUT_VARIABLE BUILTINS_LIBRARY OUTPUT_STRIP_TRAILING_WHITESPACE)
# Apparently, in clang-19, the UBSan support library for C++ was moved out into ubsan_standalone_cxx.a, so we have to include both.
if (SANITIZE STREQUAL undefined)
string(REPLACE "builtins.a" "ubsan_standalone_cxx.a" EXTRA_BUILTINS_LIBRARY "${BUILTINS_LIBRARY}")
endif ()
# Apparently, in clang-19, the UBSan support library for C++ was moved out into ubsan_standalone_cxx.a, so we have to include both.
if (SANITIZE STREQUAL undefined)
string(REPLACE "builtins.a" "ubsan_standalone_cxx.a" EXTRA_BUILTINS_LIBRARY "${BUILTINS_LIBRARY}")
endif ()
if (NOT EXISTS "${BUILTINS_LIBRARY}")
set (BUILTINS_LIBRARY "-lgcc")
endif ()
if (NOT EXISTS "${BUILTINS_LIBRARY}")
set (BUILTINS_LIBRARY "-lgcc")
endif ()
if (OS_ANDROID)

8
cmake/sanitize.cmake
View File

@ -26,9 +26,7 @@ if (SANITIZE)
elseif (SANITIZE STREQUAL "thread")
set (TSAN_FLAGS "-fsanitize=thread")
if (COMPILER_CLANG)
set (TSAN_FLAGS "${TSAN_FLAGS} -fsanitize-ignorelist=${PROJECT_SOURCE_DIR}/tests/tsan_ignorelist.txt")
endif()
set (TSAN_FLAGS "${TSAN_FLAGS} -fsanitize-ignorelist=${PROJECT_SOURCE_DIR}/tests/tsan_ignorelist.txt")
set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${SAN_FLAGS} ${TSAN_FLAGS}")
set (CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${SAN_FLAGS} ${TSAN_FLAGS}")
@ -44,9 +42,7 @@ if (SANITIZE)
# that's why we often receive reports about UIO. The simplest way to avoid this is just set this flag here.
set(UBSAN_FLAGS "${UBSAN_FLAGS} -fno-sanitize=unsigned-integer-overflow")
endif()
if (COMPILER_CLANG)
set (UBSAN_FLAGS "${UBSAN_FLAGS} -fsanitize-ignorelist=${PROJECT_SOURCE_DIR}/tests/ubsan_ignorelist.txt")
endif()
set (UBSAN_FLAGS "${UBSAN_FLAGS} -fsanitize-ignorelist=${PROJECT_SOURCE_DIR}/tests/ubsan_ignorelist.txt")
set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${SAN_FLAGS} ${UBSAN_FLAGS}")
set (CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${SAN_FLAGS} ${UBSAN_FLAGS}")

87
cmake/tools.cmake
View File

@ -1,10 +1,6 @@
# Compiler
if (CMAKE_CXX_COMPILER_ID MATCHES "AppleClang")
set (COMPILER_CLANG 1) # Safe to treat AppleClang as a regular Clang, in general.
elseif (CMAKE_CXX_COMPILER_ID MATCHES "Clang")
set (COMPILER_CLANG 1)
else ()
if (NOT CMAKE_CXX_COMPILER_ID MATCHES "Clang")
message (FATAL_ERROR "Compiler ${CMAKE_CXX_COMPILER_ID} is not supported")
endif ()
@ -13,34 +9,30 @@ execute_process(COMMAND ${CMAKE_CXX_COMPILER} --version OUTPUT_VARIABLE COMPILER
message (STATUS "Using compiler:\n${COMPILER_SELF_IDENTIFICATION}")
# Require minimum compiler versions
set (CLANG_MINIMUM_VERSION 16)
set (CLANG_MINIMUM_VERSION 17)
set (XCODE_MINIMUM_VERSION 12.0)
set (APPLE_CLANG_MINIMUM_VERSION 12.0.0)
if (COMPILER_CLANG)
if (CMAKE_CXX_COMPILER_ID MATCHES "AppleClang")
# (Experimental!) Specify "-DALLOW_APPLECLANG=ON" when running CMake configuration step, if you want to experiment with using it.
if (NOT ALLOW_APPLECLANG AND NOT DEFINED ENV{ALLOW_APPLECLANG})
message (FATAL_ERROR "Compilation with AppleClang is unsupported. Please use vanilla Clang, e.g. from Homebrew.")
endif ()
if (CMAKE_CXX_COMPILER_ID MATCHES "AppleClang")
# (Experimental!) Specify "-DALLOW_APPLECLANG=ON" when running CMake configuration step, if you want to experiment with using it.
if (NOT ALLOW_APPLECLANG AND NOT DEFINED ENV{ALLOW_APPLECLANG})
message (FATAL_ERROR "Compilation with AppleClang is unsupported. Please use vanilla Clang, e.g. from Homebrew.")
endif ()
# For a mapping between XCode / AppleClang / vanilla Clang versions, see https://en.wikipedia.org/wiki/Xcode
if (CMAKE_CXX_COMPILER_VERSION VERSION_LESS ${APPLE_CLANG_MINIMUM_VERSION})
message (FATAL_ERROR "Compilation with AppleClang version ${CMAKE_CXX_COMPILER_VERSION} is unsupported, the minimum required version is ${APPLE_CLANG_MINIMUM_VERSION} (Xcode ${XCODE_MINIMUM_VERSION}).")
endif ()
else ()
if (CMAKE_CXX_COMPILER_VERSION VERSION_LESS ${CLANG_MINIMUM_VERSION})
message (FATAL_ERROR "Compilation with Clang version ${CMAKE_CXX_COMPILER_VERSION} is unsupported, the minimum required version is ${CLANG_MINIMUM_VERSION}.")
endif ()
# For a mapping between XCode / AppleClang / vanilla Clang versions, see https://en.wikipedia.org/wiki/Xcode
if (CMAKE_CXX_COMPILER_VERSION VERSION_LESS ${APPLE_CLANG_MINIMUM_VERSION})
message (FATAL_ERROR "Compilation with AppleClang version ${CMAKE_CXX_COMPILER_VERSION} is unsupported, the minimum required version is ${APPLE_CLANG_MINIMUM_VERSION} (Xcode ${XCODE_MINIMUM_VERSION}).")
endif ()
else ()
if (CMAKE_CXX_COMPILER_VERSION VERSION_LESS ${CLANG_MINIMUM_VERSION})
message (FATAL_ERROR "Compilation with Clang version ${CMAKE_CXX_COMPILER_VERSION} is unsupported, the minimum required version is ${CLANG_MINIMUM_VERSION}.")
endif ()
endif ()
# Linker
string (REGEX MATCHALL "[0-9]+" COMPILER_VERSION_LIST ${CMAKE_CXX_COMPILER_VERSION})
list (GET COMPILER_VERSION_LIST 0 COMPILER_VERSION_MAJOR)
# Example values: `lld-10`
# Linker
option (LINKER_NAME "Linker name or full path")
if (LINKER_NAME MATCHES "gold")
@ -48,19 +40,15 @@ if (LINKER_NAME MATCHES "gold")
endif ()
if (NOT LINKER_NAME)
if (COMPILER_CLANG)
if (OS_LINUX AND NOT ARCH_S390X)
find_program (LLD_PATH NAMES "ld.lld-${COMPILER_VERSION_MAJOR}" "ld.lld")
elseif (OS_DARWIN)
find_program (LLD_PATH NAMES "ld")
endif ()
if (OS_LINUX AND NOT ARCH_S390X)
find_program (LLD_PATH NAMES "ld.lld-${COMPILER_VERSION_MAJOR}" "ld.lld")
elseif (OS_DARWIN)
find_program (LLD_PATH NAMES "ld")
endif ()
if (LLD_PATH)
if (OS_LINUX OR OS_DARWIN)
if (COMPILER_CLANG)
# Clang driver simply allows full linker path.
set (LINKER_NAME ${LLD_PATH})
endif ()
# Clang driver simply allows full linker path.
set (LINKER_NAME ${LLD_PATH})
endif ()
endif()
endif()
@ -82,47 +70,28 @@ else ()
endif ()
# Archiver
if (COMPILER_CLANG)
find_program (LLVM_AR_PATH NAMES "llvm-ar-${COMPILER_VERSION_MAJOR}" "llvm-ar")
endif ()
find_program (LLVM_AR_PATH NAMES "llvm-ar-${COMPILER_VERSION_MAJOR}" "llvm-ar")
if (LLVM_AR_PATH)
set (CMAKE_AR "${LLVM_AR_PATH}")
endif ()
message(STATUS "Using archiver: ${CMAKE_AR}")
# Ranlib
if (COMPILER_CLANG)
find_program (LLVM_RANLIB_PATH NAMES "llvm-ranlib-${COMPILER_VERSION_MAJOR}" "llvm-ranlib")
endif ()
find_program (LLVM_RANLIB_PATH NAMES "llvm-ranlib-${COMPILER_VERSION_MAJOR}" "llvm-ranlib")
if (LLVM_RANLIB_PATH)
set (CMAKE_RANLIB "${LLVM_RANLIB_PATH}")
endif ()
message(STATUS "Using ranlib: ${CMAKE_RANLIB}")
# Install Name Tool
if (COMPILER_CLANG)
find_program (LLVM_INSTALL_NAME_TOOL_PATH NAMES "llvm-install-name-tool-${COMPILER_VERSION_MAJOR}" "llvm-install-name-tool")
endif ()
find_program (LLVM_INSTALL_NAME_TOOL_PATH NAMES "llvm-install-name-tool-${COMPILER_VERSION_MAJOR}" "llvm-install-name-tool")
if (LLVM_INSTALL_NAME_TOOL_PATH)
set (CMAKE_INSTALL_NAME_TOOL "${LLVM_INSTALL_NAME_TOOL_PATH}")
endif ()
message(STATUS "Using install-name-tool: ${CMAKE_INSTALL_NAME_TOOL}")
# Objcopy
if (COMPILER_CLANG)
find_program (OBJCOPY_PATH NAMES "llvm-objcopy-${COMPILER_VERSION_MAJOR}" "llvm-objcopy" "objcopy")
endif ()
find_program (OBJCOPY_PATH NAMES "llvm-objcopy-${COMPILER_VERSION_MAJOR}" "llvm-objcopy" "objcopy")
if (OBJCOPY_PATH)
message (STATUS "Using objcopy: ${OBJCOPY_PATH}")
else ()
@ -130,11 +99,7 @@ else ()
endif ()
# Strip
if (COMPILER_CLANG)
find_program (STRIP_PATH NAMES "llvm-strip-${COMPILER_VERSION_MAJOR}" "llvm-strip" "strip")
endif ()
find_program (STRIP_PATH NAMES "llvm-strip-${COMPILER_VERSION_MAJOR}" "llvm-strip" "strip")
if (STRIP_PATH)
message (STATUS "Using strip: ${STRIP_PATH}")
else ()

66
cmake/warnings.cmake
View File

@ -15,37 +15,35 @@ if ((NOT CMAKE_BUILD_TYPE_UC STREQUAL "DEBUG") AND (NOT SANITIZE) AND (NOT CMAKE
add_warning(frame-larger-than=65536)
endif ()
if (COMPILER_CLANG)
# Add some warnings that are not available even with -Wall -Wextra -Wpedantic.
# We want to get everything out of the compiler for code quality.
add_warning(everything)
add_warning(pedantic)
no_warning(zero-length-array)
no_warning(c++98-compat-pedantic)
no_warning(c++98-compat)
no_warning(c++20-compat) # Use constinit in C++20 without warnings
no_warning(sign-conversion)
no_warning(implicit-int-conversion)
no_warning(implicit-int-float-conversion)
no_warning(ctad-maybe-unsupported) # clang 9+, linux-only
no_warning(disabled-macro-expansion)
no_warning(documentation-unknown-command)
no_warning(double-promotion)
no_warning(exit-time-destructors)
no_warning(float-equal)
no_warning(global-constructors)
no_warning(missing-prototypes)
no_warning(missing-variable-declarations)
no_warning(padded)
no_warning(switch-enum)
no_warning(undefined-func-template)
no_warning(unused-template)
no_warning(vla)
no_warning(weak-template-vtables)
no_warning(weak-vtables)
no_warning(thread-safety-negative) # experimental flag, too many false positives
no_warning(enum-constexpr-conversion) # breaks magic-enum library in clang-16
no_warning(unsafe-buffer-usage) # too aggressive
no_warning(switch-default) # conflicts with "defaults in a switch covering all enum values"
# TODO Enable conversion, sign-conversion, double-promotion warnings.
endif ()
# Add some warnings that are not available even with -Wall -Wextra -Wpedantic.
# We want to get everything out of the compiler for code quality.
add_warning(everything)
add_warning(pedantic)
no_warning(zero-length-array)
no_warning(c++98-compat-pedantic)
no_warning(c++98-compat)
no_warning(c++20-compat) # Use constinit in C++20 without warnings
no_warning(sign-conversion)
no_warning(implicit-int-conversion)
no_warning(implicit-int-float-conversion)
no_warning(ctad-maybe-unsupported) # clang 9+, linux-only
no_warning(disabled-macro-expansion)
no_warning(documentation-unknown-command)
no_warning(double-promotion)
no_warning(exit-time-destructors)
no_warning(float-equal)
no_warning(global-constructors)
no_warning(missing-prototypes)
no_warning(missing-variable-declarations)
no_warning(padded)
no_warning(switch-enum)
no_warning(undefined-func-template)
no_warning(unused-template)
no_warning(vla)
no_warning(weak-template-vtables)
no_warning(weak-vtables)
no_warning(thread-safety-negative) # experimental flag, too many false positives
no_warning(enum-constexpr-conversion) # breaks magic-enum library in clang-16
no_warning(unsafe-buffer-usage) # too aggressive
no_warning(switch-default) # conflicts with "defaults in a switch covering all enum values"
# TODO Enable conversion, sign-conversion, double-promotion warnings.

4
contrib/abseil-cpp-cmake/CMakeLists.txt
View File

@ -52,7 +52,7 @@ function(absl_cc_library)
)
target_include_directories(${_NAME}
PUBLIC "${ABSL_COMMON_INCLUDE_DIRS}")
SYSTEM PUBLIC "${ABSL_COMMON_INCLUDE_DIRS}")
target_compile_options(${_NAME}
PRIVATE ${ABSL_CC_LIB_COPTS})
target_compile_definitions(${_NAME} PUBLIC ${ABSL_CC_LIB_DEFINES})
@ -61,7 +61,7 @@ function(absl_cc_library)
# Generating header-only library
add_library(${_NAME} INTERFACE)
target_include_directories(${_NAME}
INTERFACE "${ABSL_COMMON_INCLUDE_DIRS}")
SYSTEM INTERFACE "${ABSL_COMMON_INCLUDE_DIRS}")
target_link_libraries(${_NAME}
INTERFACE

4
contrib/capnproto-cmake/CMakeLists.txt
View File

@ -81,9 +81,7 @@ set (CAPNPC_SRCS
add_library(_capnpc ${CAPNPC_SRCS})
target_link_libraries(_capnpc PUBLIC _capnp)
if (COMPILER_CLANG)
set (CAPNP_PRIVATE_CXX_FLAGS -fno-char8_t)
endif ()
set (CAPNP_PRIVATE_CXX_FLAGS -fno-char8_t)
target_compile_options(_kj PRIVATE ${CAPNP_PRIVATE_CXX_FLAGS})
target_compile_options(_capnp PRIVATE ${CAPNP_PRIVATE_CXX_FLAGS})

2
contrib/libunwind vendored

@ -1 +1 @@
Subproject commit 40d8eadf96b127d9b22d53ce7a4fc52aaedea965
Subproject commit 854538ce337d631b619010528adff22cd58f9dce

4
contrib/libunwind-cmake/CMakeLists.txt
View File

@ -31,7 +31,9 @@ add_library(unwind ${LIBUNWIND_SOURCES})
set_target_properties(unwind PROPERTIES FOLDER "contrib/libunwind-cmake")
target_include_directories(unwind SYSTEM BEFORE PUBLIC $<BUILD_INTERFACE:${LIBUNWIND_SOURCE_DIR}/include>)
target_compile_definitions(unwind PRIVATE -D_LIBUNWIND_NO_HEAP=1 -D_DEBUG -D_LIBUNWIND_IS_NATIVE_ONLY)
target_compile_definitions(unwind PRIVATE -D_LIBUNWIND_NO_HEAP=1)
# NOTE: from this macros sizeof(unw_context_t)/sizeof(unw_cursor_t) is depends, so it should be set always
target_compile_definitions(unwind PUBLIC -D_LIBUNWIND_IS_NATIVE_ONLY)
# We should enable optimizations (otherwise it will be too slow in debug)
# and disable sanitizers (otherwise infinite loop may happen)

2
contrib/lz4 vendored

@ -1 +1 @@
Subproject commit ce45a9dbdb059511a3e9576b19db3e7f1a4f172e
Subproject commit 145f3804ca5ef5482cda0f2a4f6a2d04ba57f965

10
contrib/openssl-cmake/CMakeLists.txt
View File

@ -91,12 +91,10 @@ set(LIB_SOVERSION ${VERSION_MAJOR})
enable_language(ASM)
if(COMPILER_CLANG)
add_definitions(-Wno-unused-command-line-argument)
# Note that s390x build uses mold linker
if(NOT ARCH_S390X)
set(CMAKE_SHARED_LINKER_FLAGS "${CMAKE_SHARED_LINKER_FLAGS} -fuse-ld=lld") # only relevant for -DENABLE_OPENSSL_DYNAMIC=1
endif()
add_definitions(-Wno-unused-command-line-argument)
# Note that s390x build uses mold linker
if(NOT ARCH_S390X)
set(CMAKE_SHARED_LINKER_FLAGS "${CMAKE_SHARED_LINKER_FLAGS} -fuse-ld=lld") # only relevant for -DENABLE_OPENSSL_DYNAMIC=1
endif()
if(ARCH_AMD64)

2
contrib/sentry-native-cmake/CMakeLists.txt
View File

@ -1,4 +1,4 @@
if (NOT OS_FREEBSD AND NOT (OS_DARWIN AND COMPILER_CLANG))
if (NOT OS_FREEBSD AND NOT OS_DARWIN)
option (ENABLE_SENTRY "Enable Sentry" ${ENABLE_LIBRARIES})
else()
option (ENABLE_SENTRY "Enable Sentry" OFF)

2
contrib/yaml-cpp vendored

@ -1 +1 @@
Subproject commit 0c86adac6d117ee2b4afcedb8ade19036ca0327d
Subproject commit f91e938341273b5f9d341380ab17bcc3de5daa06

8
docker/packager/README.md
View File

@ -3,10 +3,10 @@ compilers and build settings. Correctly configured Docker daemon is single depen
Usage:
Build deb package with `clang-17` in `debug` mode:
Build deb package with `clang-18` in `debug` mode:
```
$ mkdir deb/test_output
$ ./packager --output-dir deb/test_output/ --package-type deb --compiler=clang-17 --debug-build
$ ./packager --output-dir deb/test_output/ --package-type deb --compiler=clang-18 --debug-build
$ ls -l deb/test_output
-rw-r--r-- 1 root root 3730 clickhouse-client_22.2.2+debug_all.deb
-rw-r--r-- 1 root root 84221888 clickhouse-common-static_22.2.2+debug_amd64.deb
@ -17,11 +17,11 @@ $ ls -l deb/test_output
```
Build ClickHouse binary with `clang-17` and `address` sanitizer in `relwithdebuginfo`
Build ClickHouse binary with `clang-18` and `address` sanitizer in `relwithdebuginfo`
mode:
```
$ mkdir $HOME/some_clickhouse
$ ./packager --output-dir=$HOME/some_clickhouse --package-type binary --compiler=clang-17 --sanitizer=address
$ ./packager --output-dir=$HOME/some_clickhouse --package-type binary --compiler=clang-18 --sanitizer=address
$ ls -l $HOME/some_clickhouse
-rwxr-xr-x 1 root root 787061952 clickhouse
lrwxrwxrwx 1 root root 10 clickhouse-benchmark -> clickhouse

24
docker/packager/packager
View File

@ -403,19 +403,19 @@ def parse_args() -> argparse.Namespace:
parser.add_argument(
"--compiler",
choices=(
"clang-17",
"clang-17-darwin",
"clang-17-darwin-aarch64",
"clang-17-aarch64",
"clang-17-aarch64-v80compat",
"clang-17-ppc64le",
"clang-17-riscv64",
"clang-17-s390x",
"clang-17-amd64-compat",
"clang-17-amd64-musl",
"clang-17-freebsd",
"clang-18",
"clang-18-darwin",
"clang-18-darwin-aarch64",
"clang-18-aarch64",
"clang-18-aarch64-v80compat",
"clang-18-ppc64le",
"clang-18-riscv64",
"clang-18-s390x",
"clang-18-amd64-compat",
"clang-18-amd64-musl",
"clang-18-freebsd",
),
default="clang-17",
default="clang-18",
help="a compiler to use",
)
parser.add_argument(

18
docker/server/Dockerfile.ubuntu
View File

@ -1,11 +1,14 @@
FROM ubuntu:20.04
# see https://github.com/moby/moby/issues/4032#issuecomment-192327844
# It could be removed after we move on a version 23:04+
ARG DEBIAN_FRONTEND=noninteractive
# ARG for quick switch to a given ubuntu mirror
ARG apt_archive="http://archive.ubuntu.com"
# We shouldn't use `apt upgrade` to not change the upstream image. It's updated biweekly
# user/group precreated explicitly with fixed uid/gid on purpose.
# It is especially important for rootless containers: in that case entrypoint
# can't do chown and owners of mounted volumes should be configured externally.
@ -16,13 +19,11 @@ RUN sed -i "s|http://archive.ubuntu.com|${apt_archive}|g" /etc/apt/sources.list
&& groupadd -r clickhouse --gid=101 \
&& useradd -r -g clickhouse --uid=101 --home-dir=/var/lib/clickhouse --shell=/bin/bash clickhouse \
&& apt-get update \
&& apt-get upgrade -yq \
&& apt-get install --yes --no-install-recommends \
ca-certificates \
locales \
tzdata \
wget \
&& apt-get clean \
&& rm -rf /var/lib/apt/lists/* /var/cache/debconf /tmp/*
ARG REPO_CHANNEL="stable"
@ -30,6 +31,9 @@ ARG REPOSITORY="deb [signed-by=/usr/share/keyrings/clickhouse-keyring.gpg] https
ARG VERSION="24.4.1.2088"
ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"
#docker-official-library:off
# The part between `docker-official-library` tags is related to our builds
# set non-empty deb_location_url url to create a docker image
# from debs created by CI build, for example:
# docker build . --network host --build-arg version="21.4.1.6282" --build-arg deb_location_url="https://..." -t ...
@ -80,19 +84,22 @@ RUN if [ -n "${single_binary_location_url}" ]; then \
&& rm -rf /tmp/* ; \
fi
# The rest is the same in the official docker and in our build system
#docker-official-library:on
# A fallback to installation from ClickHouse repository
RUN if ! clickhouse local -q "SELECT ''" > /dev/null 2>&1; then \
apt-get update \
&& apt-get install --yes --no-install-recommends \
apt-transport-https \
ca-certificates \
dirmngr \
gnupg2 \
&& mkdir -p /etc/apt/sources.list.d \
&& GNUPGHOME=$(mktemp -d) \
&& GNUPGHOME="$GNUPGHOME" gpg --no-default-keyring \
&& GNUPGHOME="$GNUPGHOME" gpg --batch --no-default-keyring \
--keyring /usr/share/keyrings/clickhouse-keyring.gpg \
--keyserver hkp://keyserver.ubuntu.com:80 --recv-keys 8919F6BD2B48D754 \
--keyserver hkp://keyserver.ubuntu.com:80 \
--recv-keys 3a9ea1193a97b548be1457d48919f6bd2b48d754 \
&& rm -rf "$GNUPGHOME" \
&& chmod +r /usr/share/keyrings/clickhouse-keyring.gpg \
&& echo "${REPOSITORY}" > /etc/apt/sources.list.d/clickhouse.list \
@ -127,7 +134,6 @@ RUN mkdir /docker-entrypoint-initdb.d
COPY docker_related_config.xml /etc/clickhouse-server/config.d/
COPY entrypoint.sh /entrypoint.sh
RUN chmod +x /entrypoint.sh
EXPOSE 9000 8123 9009
VOLUME /var/lib/clickhouse

39
docker/server/README.md
View File

@ -4,33 +4,34 @@
ClickHouse is an open-source column-oriented DBMS (columnar database management system) for online analytical processing (OLAP) that allows users to generate analytical reports using SQL queries in real-time.
ClickHouse works 100-1000x faster than traditional database management systems, and processes hundreds of millions to over a billion rows and tens of gigabytes of data per server per second. With a widespread user base around the globe, the technology has received praise for its reliability, ease of use, and fault tolerance.
ClickHouse works 100-1000x faster than traditional database management systems, and processes hundreds of millions to over a billion rows and tens of gigabytes of data per server per second. With a widespread user base around the globe, the technology has received praise for its reliability, ease of use, and fault tolerance.
For more information and documentation see https://clickhouse.com/.
## Versions
- The `latest` tag points to the latest release of the latest stable branch.
- Branch tags like `22.2` point to the latest release of the corresponding branch.
- Full version tags like `22.2.3.5` point to the corresponding release.
- The tag `head` is built from the latest commit to the default branch.
- Each tag has optional `-alpine` suffix to reflect that it's built on top of `alpine`.
- The `latest` tag points to the latest release of the latest stable branch.
- Branch tags like `22.2` point to the latest release of the corresponding branch.
- Full version tags like `22.2.3.5` point to the corresponding release.
- The tag `head` is built from the latest commit to the default branch.
- Each tag has optional `-alpine` suffix to reflect that it's built on top of `alpine`.
### Compatibility
- The amd64 image requires support for [SSE3 instructions](https://en.wikipedia.org/wiki/SSE3). Virtually all x86 CPUs after 2005 support SSE3.
- The arm64 image requires support for the [ARMv8.2-A architecture](https://en.wikipedia.org/wiki/AArch64#ARMv8.2-A) and additionally the Load-Acquire RCpc register. The register is optional in version ARMv8.2-A and mandatory in [ARMv8.3-A](https://en.wikipedia.org/wiki/AArch64#ARMv8.3-A). Supported in Graviton >=2, Azure and GCP instances. Examples for unsupported devices are Raspberry Pi 4 (ARMv8.0-A) and Jetson AGX Xavier/Orin (ARMv8.2-A).
- The amd64 image requires support for [SSE3 instructions](https://en.wikipedia.org/wiki/SSE3). Virtually all x86 CPUs after 2005 support SSE3.
- The arm64 image requires support for the [ARMv8.2-A architecture](https://en.wikipedia.org/wiki/AArch64#ARMv8.2-A) and additionally the Load-Acquire RCpc register. The register is optional in version ARMv8.2-A and mandatory in [ARMv8.3-A](https://en.wikipedia.org/wiki/AArch64#ARMv8.3-A). Supported in Graviton >=2, Azure and GCP instances. Examples for unsupported devices are Raspberry Pi 4 (ARMv8.0-A) and Jetson AGX Xavier/Orin (ARMv8.2-A).
## How to use this image
### start server instance
```bash
docker run -d --name some-clickhouse-server --ulimit nofile=262144:262144 clickhouse/clickhouse-server
```
By default, ClickHouse will be accessible only via the Docker network. See the [networking section below](#networking).
By default, starting above server instance will be run as the `default` user without password.
By default, starting above server instance will be run as the `default` user without password.
### connect to it from a native client
@ -66,9 +67,7 @@ docker run -d -p 18123:8123 -p19000:9000 --name some-clickhouse-server --ulimit
echo 'SELECT version()' | curl 'http://localhost:18123/' --data-binary @-
```
```
22.6.3.35
```
`22.6.3.35`
or by allowing the container to use [host ports directly](https://docs.docker.com/network/host/) using `--network=host` (also allows achieving better network performance):
@ -77,16 +76,14 @@ docker run -d --network=host --name some-clickhouse-server --ulimit nofile=26214
echo 'SELECT version()' | curl 'http://localhost:8123/' --data-binary @-
```
```
22.6.3.35
```
`22.6.3.35`
### Volumes
Typically you may want to mount the following folders inside your container to achieve persistency:
* `/var/lib/clickhouse/` - main folder where ClickHouse stores the data
* `/var/log/clickhouse-server/` - logs
- `/var/lib/clickhouse/` - main folder where ClickHouse stores the data
- `/var/log/clickhouse-server/` - logs
```bash
docker run -d \
@ -97,9 +94,9 @@ docker run -d \
You may also want to mount:
* `/etc/clickhouse-server/config.d/*.xml` - files with server configuration adjustments
* `/etc/clickhouse-server/users.d/*.xml` - files with user settings adjustments
* `/docker-entrypoint-initdb.d/` - folder with database initialization scripts (see below).
- `/etc/clickhouse-server/config.d/*.xml` - files with server configuration adjustments
- `/etc/clickhouse-server/users.d/*.xml` - files with user settings adjustments
- `/docker-entrypoint-initdb.d/` - folder with database initialization scripts (see below).
### Linux capabilities
@ -150,7 +147,7 @@ docker run --rm -e CLICKHOUSE_DB=my_database -e CLICKHOUSE_USER=username -e CLIC
## How to extend this image
To perform additional initialization in an image derived from this one, add one or more `*.sql`, `*.sql.gz`, or `*.sh` scripts under `/docker-entrypoint-initdb.d`. After the entrypoint calls `initdb`, it will run any `*.sql` files, run any executable `*.sh` scripts, and source any non-executable `*.sh` scripts found in that directory to do further initialization before starting the service.
To perform additional initialization in an image derived from this one, add one or more `*.sql`, `*.sql.gz`, or `*.sh` scripts under `/docker-entrypoint-initdb.d`. After the entrypoint calls `initdb`, it will run any `*.sql` files, run any executable `*.sh` scripts, and source any non-executable `*.sh` scripts found in that directory to do further initialization before starting the service.
Also, you can provide environment variables `CLICKHOUSE_USER` & `CLICKHOUSE_PASSWORD` that will be used for clickhouse-client during initialization.
For example, to add an additional user and database, add the following to `/docker-entrypoint-initdb.d/init-db.sh`:

2
docker/test/base/setup_export_logs.sh
View File

@ -140,7 +140,7 @@ function setup_logs_replication
time DateTime COMMENT 'The time of test run',
test_name String COMMENT 'The name of the test',
coverage Array(UInt64) COMMENT 'An array of addresses of the code (a subset of addresses instrumented for coverage) that were encountered during the test run'
) ENGINE = Null COMMENT 'Contains information about per-test coverage from the CI, but used only for exporting to the CI cluster'
) ENGINE = MergeTree ORDER BY test_name COMMENT 'Contains information about per-test coverage from the CI, but used only for exporting to the CI cluster'
"
# For each system log table:

5
docker/test/fuzzer/query-fuzzer-tweaks-users.xml
View File

@ -31,6 +31,11 @@
<allow_experimental_analyzer>
<readonly/>
</allow_experimental_analyzer>
<!-- This feature is broken, deprecated and will be removed. We don't want more reports about it -->
<allow_experimental_object_type>
<readonly/>
</allow_experimental_object_type>
</constraints>
</default>
</profiles>

2
docker/test/fuzzer/run-fuzzer.sh
View File

@ -17,7 +17,7 @@ stage=${stage:-}
script_dir="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
echo "$script_dir"
repo_dir=ch
BINARY_TO_DOWNLOAD=${BINARY_TO_DOWNLOAD:="clang-17_debug_none_unsplitted_disable_False_binary"}
BINARY_TO_DOWNLOAD=${BINARY_TO_DOWNLOAD:="clang-18_debug_none_unsplitted_disable_False_binary"}
BINARY_URL_TO_DOWNLOAD=${BINARY_URL_TO_DOWNLOAD:="https://clickhouse-builds.s3.amazonaws.com/$PR_TO_TEST/$SHA_TO_TEST/clickhouse_build_check/$BINARY_TO_DOWNLOAD/clickhouse"}
function git_clone_with_retry

3
docker/test/integration/runner/Dockerfile
View File

@ -101,7 +101,8 @@ RUN python3 -m pip install --no-cache-dir \
retry==0.9.2 \
bs4==0.0.2 \
lxml==5.1.0 \
urllib3==2.0.7
urllib3==2.0.7 \
jwcrypto==1.5.6
# bs4, lxml are for cloud tests, do not delete
# Hudi supports only spark 3.3.*, not 3.4

2
docker/test/keeper-jepsen/run.sh
View File

@ -2,7 +2,7 @@
set -euo pipefail
CLICKHOUSE_PACKAGE=${CLICKHOUSE_PACKAGE:="https://clickhouse-builds.s3.amazonaws.com/$PR_TO_TEST/$SHA_TO_TEST/clickhouse_build_check/clang-17_relwithdebuginfo_none_unsplitted_disable_False_binary/clickhouse"}
CLICKHOUSE_PACKAGE=${CLICKHOUSE_PACKAGE:="https://clickhouse-builds.s3.amazonaws.com/$PR_TO_TEST/$SHA_TO_TEST/clickhouse_build_check/clang-18_relwithdebuginfo_none_unsplitted_disable_False_binary/clickhouse"}
CLICKHOUSE_REPO_PATH=${CLICKHOUSE_REPO_PATH:=""}

2
docker/test/server-jepsen/run.sh
View File

@ -2,7 +2,7 @@
set -euo pipefail
CLICKHOUSE_PACKAGE=${CLICKHOUSE_PACKAGE:="https://clickhouse-builds.s3.amazonaws.com/$PR_TO_TEST/$SHA_TO_TEST/clickhouse_build_check/clang-17_relwithdebuginfo_none_unsplitted_disable_False_binary/clickhouse"}
CLICKHOUSE_PACKAGE=${CLICKHOUSE_PACKAGE:="https://clickhouse-builds.s3.amazonaws.com/$PR_TO_TEST/$SHA_TO_TEST/clickhouse_build_check/clang-18_relwithdebuginfo_none_unsplitted_disable_False_binary/clickhouse"}
CLICKHOUSE_REPO_PATH=${CLICKHOUSE_REPO_PATH:=""}

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

@ -6,7 +6,7 @@ set -e
set -u
set -o pipefail
BINARY_TO_DOWNLOAD=${BINARY_TO_DOWNLOAD:="clang-17_debug_none_unsplitted_disable_False_binary"}
BINARY_TO_DOWNLOAD=${BINARY_TO_DOWNLOAD:="clang-18_debug_none_unsplitted_disable_False_binary"}
BINARY_URL_TO_DOWNLOAD=${BINARY_URL_TO_DOWNLOAD:="https://clickhouse-builds.s3.amazonaws.com/$PR_TO_TEST/$SHA_TO_TEST/clickhouse_build_check/$BINARY_TO_DOWNLOAD/clickhouse"}
function wget_with_retry

2
docker/test/stateless/setup_minio.sh
View File

@ -83,7 +83,7 @@ setup_minio() {
./mc alias set clickminio http://localhost:11111 clickhouse clickhouse
./mc admin user add clickminio test testtest
./mc admin policy set clickminio readwrite user=test
./mc mb clickminio/test
./mc mb --ignore-existing clickminio/test
if [ "$test_type" = "stateless" ]; then
./mc policy set public clickminio/test
fi

30
docker/test/stateless/stress_tests.lib
View File

@ -120,13 +120,41 @@ EOL
local max_users_mem
max_users_mem=$((total_mem*30/100)) # 30%
# Similar to docker/test/fuzzer/query-fuzzer-tweaks-users.xml
echo "Setting max_memory_usage_for_user=$max_users_mem and max_memory_usage for queries to 10G"
cat > /etc/clickhouse-server/users.d/max_memory_usage_for_user.xml <<EOL
cat > /etc/clickhouse-server/users.d/stress_test_tweaks-users.xml <<EOL
<clickhouse>
<profiles>
<default>
<max_execution_time>60</max_execution_time>
<max_memory_usage>10G</max_memory_usage>
<max_memory_usage_for_user>${max_users_mem}</max_memory_usage_for_user>
<table_function_remote_max_addresses>200</table_function_remote_max_addresses>
<constraints>
<max_execution_time>
<max>60</max>
</max_execution_time>
<max_memory_usage>
<max>10G</max>
</max_memory_usage>
<table_function_remote_max_addresses>
<max>200</max>
</table_function_remote_max_addresses>
<!-- Don't waste cycles testing the old interpreter. Spend time in the new analyzer instead -->
<allow_experimental_analyzer>
<readonly/>
</allow_experimental_analyzer>
<!-- This feature is broken, deprecated and will be removed. We don't want more reports about it -->
<allow_experimental_object_type>
<readonly/>
</allow_experimental_object_type>
</constraints>
</default>
</profiles>
</clickhouse>

2
docker/test/util/Dockerfile
View File

@ -5,7 +5,7 @@ FROM ubuntu:22.04
ARG apt_archive="http://archive.ubuntu.com"
RUN sed -i "s|http://archive.ubuntu.com|$apt_archive|g" /etc/apt/sources.list
ENV DEBIAN_FRONTEND=noninteractive LLVM_VERSION=17
ENV DEBIAN_FRONTEND=noninteractive LLVM_VERSION=18
RUN apt-get update \
&& apt-get install \

6
docs/en/development/build-cross-osx.md
View File

@ -13,14 +13,14 @@ The cross-build for macOS is based on the [Build instructions](../development/bu
The following sections provide a walk-through for building ClickHouse for `x86_64` macOS. If you’re targeting ARM architecture, simply substitute all occurrences of `x86_64` with `aarch64`. For example, replace `x86_64-apple-darwin` with `aarch64-apple-darwin` throughout the steps.
## Install Clang-17
## Install clang-18
Follow the instructions from https://apt.llvm.org/ for your Ubuntu or Debian setup.
For example the commands for Bionic are like:
``` bash
sudo echo "deb [trusted=yes] http://apt.llvm.org/bionic/ llvm-toolchain-bionic-17 main" >> /etc/apt/sources.list
sudo apt-get install clang-17
sudo apt-get install clang-18
```
## Install Cross-Compilation Toolset {#install-cross-compilation-toolset}
@ -59,7 +59,7 @@ curl -L 'https://github.com/phracker/MacOSX-SDKs/releases/download/11.3/MacOSX11
cd ClickHouse
mkdir build-darwin
cd build-darwin
CC=clang-17 CXX=clang++-17 cmake -DCMAKE_AR:FILEPATH=${CCTOOLS}/bin/x86_64-apple-darwin-ar -DCMAKE_INSTALL_NAME_TOOL=${CCTOOLS}/bin/x86_64-apple-darwin-install_name_tool -DCMAKE_RANLIB:FILEPATH=${CCTOOLS}/bin/x86_64-apple-darwin-ranlib -DLINKER_NAME=${CCTOOLS}/bin/x86_64-apple-darwin-ld -DCMAKE_TOOLCHAIN_FILE=cmake/darwin/toolchain-x86_64.cmake ..
CC=clang-18 CXX=clang++-18 cmake -DCMAKE_AR:FILEPATH=${CCTOOLS}/bin/x86_64-apple-darwin-ar -DCMAKE_INSTALL_NAME_TOOL=${CCTOOLS}/bin/x86_64-apple-darwin-install_name_tool -DCMAKE_RANLIB:FILEPATH=${CCTOOLS}/bin/x86_64-apple-darwin-ranlib -DLINKER_NAME=${CCTOOLS}/bin/x86_64-apple-darwin-ld -DCMAKE_TOOLCHAIN_FILE=cmake/darwin/toolchain-x86_64.cmake ..
ninja
```

2
docs/en/development/build-cross-riscv.md
View File

@ -23,7 +23,7 @@ sudo bash -c "$(wget -O - https://apt.llvm.org/llvm.sh)"
``` bash
cd ClickHouse
mkdir build-riscv64
CC=clang-17 CXX=clang++-17 cmake . -Bbuild-riscv64 -G Ninja -DCMAKE_TOOLCHAIN_FILE=cmake/linux/toolchain-riscv64.cmake -DGLIBC_COMPATIBILITY=OFF -DENABLE_LDAP=OFF -DOPENSSL_NO_ASM=ON -DENABLE_JEMALLOC=ON -DENABLE_PARQUET=OFF -DENABLE_GRPC=OFF -DENABLE_HDFS=OFF -DENABLE_MYSQL=OFF
CC=clang-18 CXX=clang++-18 cmake . -Bbuild-riscv64 -G Ninja -DCMAKE_TOOLCHAIN_FILE=cmake/linux/toolchain-riscv64.cmake -DGLIBC_COMPATIBILITY=OFF -DENABLE_LDAP=OFF -DOPENSSL_NO_ASM=ON -DENABLE_JEMALLOC=ON -DENABLE_PARQUET=OFF -DENABLE_GRPC=OFF -DENABLE_HDFS=OFF -DENABLE_MYSQL=OFF
ninja -C build-riscv64
```

2
docs/en/development/build.md
View File

@ -109,7 +109,7 @@ The build requires the following components:
- Git (used to checkout the sources, not needed for the build)
- CMake 3.20 or newer
- Compiler: clang-17 or newer
- Compiler: clang-18 or newer
- Linker: lld-17 or newer
- Ninja
- Yasm

4
docs/en/development/continuous-integration.md
View File

@ -153,7 +153,7 @@ Builds ClickHouse in various configurations for use in further steps. You have t
### Report Details
- **Compiler**: `clang-17`, optionally with the name of a target platform
- **Compiler**: `clang-18`, optionally with the name of a target platform
- **Build type**: `Debug` or `RelWithDebInfo` (cmake).
- **Sanitizer**: `none` (without sanitizers), `address` (ASan), `memory` (MSan), `undefined` (UBSan), or `thread` (TSan).
- **Status**: `success` or `fail`
@ -177,7 +177,7 @@ Performs static analysis and code style checks using `clang-tidy`. The report is
There is a convenience `packager` script that runs the clang-tidy build in docker
```sh
mkdir build_tidy
./docker/packager/packager --output-dir=./build_tidy --package-type=binary --compiler=clang-17 --debug-build --clang-tidy
./docker/packager/packager --output-dir=./build_tidy --package-type=binary --compiler=clang-18 --debug-build --clang-tidy
```

2
docs/en/development/developer-instruction.md
View File

@ -121,7 +121,7 @@ While inside the `build` directory, configure your build by running CMake. Befor
export CC=clang CXX=clang++
cmake ..
If you installed clang using the automatic installation script above, also specify the version of clang installed in the first command, e.g. `export CC=clang-17 CXX=clang++-17`. The clang version will be in the script output.
If you installed clang using the automatic installation script above, also specify the version of clang installed in the first command, e.g. `export CC=clang-18 CXX=clang++-18`. The clang version will be in the script output.
The `CC` variable specifies the compiler for C (short for C Compiler), and `CXX` variable instructs which C++ compiler is to be used for building.

3
docs/en/engines/database-engines/materialized-mysql.md
View File

@ -51,6 +51,9 @@ ENGINE = MaterializedMySQL('host:port', ['database' | database], 'user', 'passwo
### allows_query_when_mysql_lost
`allows_query_when_mysql_lost` — Allows to query a materialized table when MySQL is lost. Default: `0` (`false`).
### allow_startup_database_without_connection_to_mysql
`allow_startup_database_without_connection_to_mysql` — Allow to create and attach database without available connection to MySQL. Default: `0` (`false`).
### materialized_mysql_tables_list
`materialized_mysql_tables_list` — a comma-separated list of mysql database tables, which will be replicated by MaterializedMySQL database engine. Default value: empty list — means whole tables will be replicated.

10
docs/en/engines/table-engines/mergetree-family/replication.md
View File

@ -10,7 +10,7 @@ sidebar_label: Data Replication
In ClickHouse Cloud replication is managed for you. Please create your tables without adding arguments. For example, in the text below you would replace:
```sql
ENGINE = ReplicatedReplacingMergeTree(
ENGINE = ReplicatedMergeTree(
'/clickhouse/tables/{shard}/table_name',
'{replica}',
ver
@ -20,7 +20,7 @@ ENGINE = ReplicatedReplacingMergeTree(
with:
```sql
ENGINE = ReplicatedReplacingMergeTree
ENGINE = ReplicatedMergeTree
```
:::
@ -140,11 +140,11 @@ The system monitors data synchronicity on replicas and is able to recover after
:::note
In ClickHouse Cloud replication is managed for you. Please create your tables without adding arguments. For example, in the text below you would replace:
```
ENGINE = ReplicatedReplacingMergeTree('/clickhouse/tables/{shard}/table_name', '{replica}', ver)
ENGINE = ReplicatedMergeTree('/clickhouse/tables/{shard}/table_name', '{replica}', ver)
```
with:
```
ENGINE = ReplicatedReplacingMergeTree
ENGINE = ReplicatedMergeTree
```
:::
@ -177,7 +177,7 @@ CREATE TABLE table_name
CounterID UInt32,
UserID UInt32,
ver UInt16
) ENGINE = ReplicatedReplacingMergeTree('/clickhouse/tables/{shard}/table_name', '{replica}', ver)
) ENGINE = ReplicatedMergeTree('/clickhouse/tables/{shard}/table_name', '{replica}', ver)
PARTITION BY toYYYYMM(EventDate)
ORDER BY (CounterID, EventDate, intHash32(UserID))
SAMPLE BY intHash32(UserID);

49
docs/en/interfaces/formats.md
View File

@ -75,7 +75,7 @@ The supported formats are:
| [ArrowStream](#data-format-arrow-stream) | ✔ | ✔ |
| [ORC](#data-format-orc) | ✔ | ✔ |
| [One](#data-format-one) | ✔ | ✗ |
| [Npy](#data-format-npy) | ✔ | ✗ |
| [Npy](#data-format-npy) | ✔ | ✔ |
| [RowBinary](#rowbinary) | ✔ | ✔ |
| [RowBinaryWithNames](#rowbinarywithnamesandtypes) | ✔ | ✔ |
| [RowBinaryWithNamesAndTypes](#rowbinarywithnamesandtypes) | ✔ | ✔ |
@ -207,7 +207,7 @@ SELECT * FROM nestedt FORMAT TSV
Differs from `TabSeparated` format in that the rows are written without escaping.
When parsing with this format, tabs or linefeeds are not allowed in each field.
This format is also available under the name `TSVRaw`.
This format is also available under the names `TSVRaw`, `Raw`.
## TabSeparatedWithNames {#tabseparatedwithnames}
@ -242,14 +242,14 @@ This format is also available under the name `TSVWithNamesAndTypes`.
Differs from `TabSeparatedWithNames` format in that the rows are written without escaping.
When parsing with this format, tabs or linefeeds are not allowed in each field.
This format is also available under the name `TSVRawWithNames`.
This format is also available under the names `TSVRawWithNames`, `RawWithNames`.
## TabSeparatedRawWithNamesAndTypes {#tabseparatedrawwithnamesandtypes}
Differs from `TabSeparatedWithNamesAndTypes` format in that the rows are written without escaping.
When parsing with this format, tabs or linefeeds are not allowed in each field.
This format is also available under the name `TSVRawWithNamesAndNames`.
This format is also available under the names `TSVRawWithNamesAndNames`, `RawWithNamesAndNames`.
## Template {#format-template}
@ -2466,23 +2466,22 @@ Result:
## Npy {#data-format-npy}
This function is designed to load a NumPy array from a .npy file into ClickHouse. The NumPy file format is a binary format used for efficiently storing arrays of numerical data. During import, ClickHouse treats top level dimension as an array of rows with single column. Supported Npy data types and their corresponding type in ClickHouse:
| Npy type | ClickHouse type |
|:--------:|:---------------:|
| b1 | UInt8 |
| i1 | Int8 |
| i2 | Int16 |
| i4 | Int32 |
| i8 | Int64 |
| u1 | UInt8 |
| u2 | UInt16 |
| u4 | UInt32 |
| u8 | UInt64 |
| f2 | Float32 |
| f4 | Float32 |
| f8 | Float64 |
| S | String |
| U | String |
This function is designed to load a NumPy array from a .npy file into ClickHouse. The NumPy file format is a binary format used for efficiently storing arrays of numerical data. During import, ClickHouse treats top level dimension as an array of rows with single column. Supported Npy data types and their corresponding type in ClickHouse:
| Npy data type (`INSERT`) | ClickHouse data type | Npy data type (`SELECT`) |
|--------------------------|-----------------------------------------------------------------|--------------------------|
| `i1` | [Int8](/docs/en/sql-reference/data-types/int-uint.md) | `i1` |
| `i2` | [Int16](/docs/en/sql-reference/data-types/int-uint.md) | `i2` |
| `i4` | [Int32](/docs/en/sql-reference/data-types/int-uint.md) | `i4` |
| `i8` | [Int64](/docs/en/sql-reference/data-types/int-uint.md) | `i8` |
| `u1`, `b1` | [UInt8](/docs/en/sql-reference/data-types/int-uint.md) | `u1` |
| `u2` | [UInt16](/docs/en/sql-reference/data-types/int-uint.md) | `u2` |
| `u4` | [UInt32](/docs/en/sql-reference/data-types/int-uint.md) | `u4` |
| `u8` | [UInt64](/docs/en/sql-reference/data-types/int-uint.md) | `u8` |
| `f2`, `f4` | [Float32](/docs/en/sql-reference/data-types/float.md) | `f4` |
| `f8` | [Float64](/docs/en/sql-reference/data-types/float.md) | `f8` |
| `S`, `U` | [String](/docs/en/sql-reference/data-types/string.md) | `S` |
| | [FixedString](/docs/en/sql-reference/data-types/fixedstring.md) | `S` |
**Example of saving an array in .npy format using Python**
@ -2509,6 +2508,14 @@ Result:
└───────────────┘
```
**Selecting Data**
You can select data from a ClickHouse table and save them into some file in the Npy format by the following command:
```bash
$ clickhouse-client --query="SELECT {column} FROM {some_table} FORMAT Npy" > {filename.npy}
```
## LineAsString {#lineasstring}
In this format, every line of input data is interpreted as a single string value. This format can only be parsed for table with a single field of type [String](/docs/en/sql-reference/data-types/string.md). The remaining columns must be set to [DEFAULT](/docs/en/sql-reference/statements/create/table.md/#default) or [MATERIALIZED](/docs/en/sql-reference/statements/create/table.md/#materialized), or omitted.

12
docs/en/interfaces/third-party/gui.md vendored
View File

@ -210,6 +210,18 @@ Features:
- Pre-built metrics dashboards.
- Multiple users/projects via YAML config.
### clickhouse-monitoring {#clickhouse-monitoring}
[clickhouse-monitoring](https://github.com/duyet/clickhouse-monitoring) is a simple Next.js dashboard that relies on `system.*` tables to help monitor and provide an overview of your ClickHouse cluster.
Features:
- Query monitor: current queries, query history, query resources (memory, parts read, file_open, ...), most expensive queries, most used tables or columns, etc.
- Cluster monitor: total memory/CPU usage, distributed queue, global settings, mergetree settings, metrics, etc.
- Tables and parts information: size, row count, compression, part size, etc., at the column level detail.
- Useful tools: Zookeeper data exploration, query EXPLAIN, kill queries, etc.
- Visualization metric charts: queries and resource usage, number of merges/mutation, merge performance, query performance, etc.
## Commercial {#commercial}
### DataGrip {#datagrip}

55
docs/en/operations/configuration-files.md
View File

@ -67,6 +67,8 @@ generates merged configuration file:
</clickhouse>
```
### Using from_env and from_zk
To specify that a value of an element should be replaced by the value of an environment variable, you can use attribute `from_env`.
Example with `$MAX_QUERY_SIZE = 150000`:
@ -93,6 +95,59 @@ which is equal to
</clickhouse>
```
The same is possible using `from_zk`:
``` xml
<clickhouse>
<postgresql_port from_zk="/zk_configs/postgresql_port"/>
</clickhouse>
```
```
# clickhouse-keeper-client
/ :) touch /zk_configs
/ :) create /zk_configs/postgresql_port "9005"
/ :) get /zk_configs/postgresql_port
9005
```
which is equal to
``` xml
<clickhouse>
<postgresql_port>9005</postgresql_port>
</clickhouse>
```
#### Default values for from_env and from_zk attributes
It's possible to set the default value and substitute it only if the environment variable or zookeeper node is set using `replace="1"`.
With previous example, but `MAX_QUERY_SIZE` is unset:
``` xml
<clickhouse>
<profiles>
<default>
<max_query_size from_env="MAX_QUERY_SIZE" replace="1">150000</max_query_size>
</default>
</profiles>
</clickhouse>
```
will take the default value
``` xml
<clickhouse>
<profiles>
<default>
<max_query_size>150000</max_query_size>
</default>
</profiles>
</clickhouse>
```
## Substituting Configuration {#substitution}
The config can define substitutions. There are two types of substitutions:

2
docs/en/operations/storing-data.md
View File

@ -371,6 +371,8 @@ is equal to
</s3_plain_rewritable>
```
Starting from `24.5` it is possible configure any object storage disk (`s3`, `azure`, `local`) using `plain_rewritable` metadata type.
### Using Azure Blob Storage {#azure-blob-storage}
`MergeTree` family table engines can store data to [Azure Blob Storage](https://azure.microsoft.com/en-us/services/storage/blobs/) using a disk with type `azure_blob_storage`.

2
docs/en/operations/system-tables/part_log.md
View File

@ -14,7 +14,7 @@ The `system.part_log` table contains the following columns:
- `event_type` ([Enum8](../../sql-reference/data-types/enum.md)) — Type of the event that occurred with the data part. Can have one of the following values:
- `NewPart` — Inserting of a new data part.
- `MergeParts` — Merging of data parts.
- `DownloadParts` — Downloading a data part.
- `DownloadPart` — Downloading a data part.
- `RemovePart` — Removing or detaching a data part using [DETACH PARTITION](../../sql-reference/statements/alter/partition.md#alter_detach-partition).
- `MutatePart` — Mutating of a data part.
- `MovePart` — Moving the data part from the one disk to another one.

29
docs/en/operations/system-tables/server_settings.md
View File

@ -32,20 +32,21 @@ WHERE name LIKE '%thread_pool%'
```
``` text
┌─name────────────────────────────────────────┬─value─┬─default─┬─changed─┬─description─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┬─type───┬─changeable_without_restart─┬─is_obsolete─┐
│ max_thread_pool_size │ 10000 │ 10000 │ 0 │ The maximum number of threads that could be allocated from the OS and used for query execution and background operations. │ UInt64 │ No │ 0 │
│ max_thread_pool_free_size │ 1000 │ 1000 │ 0 │ The maximum number of threads that will always stay in a global thread pool once allocated and remain idle in case of insufficient number of tasks. │ UInt64 │ No │ 0 │
│ thread_pool_queue_size │ 10000 │ 10000 │ 0 │ The maximum number of tasks that will be placed in a queue and wait for execution. │ UInt64 │ No │ 0 │
│ max_io_thread_pool_size │ 100 │ 100 │ 0 │ The maximum number of threads that would be used for IO operations │ UInt64 │ No │ 0 │
│ max_io_thread_pool_free_size │ 0 │ 0 │ 0 │ Max free size for IO thread pool. │ UInt64 │ No │ 0 │
│ io_thread_pool_queue_size │ 10000 │ 10000 │ 0 │ Queue size for IO thread pool. │ UInt64 │ No │ 0 │
│ max_active_parts_loading_thread_pool_size │ 64 │ 64 │ 0 │ The number of threads to load active set of data parts (Active ones) at startup. │ UInt64 │ No │ 0 │
│ max_outdated_parts_loading_thread_pool_size │ 32 │ 32 │ 0 │ The number of threads to load inactive set of data parts (Outdated ones) at startup. │ UInt64 │ No │ 0 │
│ max_parts_cleaning_thread_pool_size │ 128 │ 128 │ 0 │ The number of threads for concurrent removal of inactive data parts. │ UInt64 │ No │ 0 │
│ max_backups_io_thread_pool_size │ 1000 │ 1000 │ 0 │ The maximum number of threads that would be used for IO operations for BACKUP queries │ UInt64 │ No │ 0 │
│ max_backups_io_thread_pool_free_size │ 0 │ 0 │ 0 │ Max free size for backups IO thread pool. │ UInt64 │ No │ 0 │
│ backups_io_thread_pool_queue_size │ 0 │ 0 │ 0 │ Queue size for backups IO thread pool. │ UInt64 │ No │ 0 │
└─────────────────────────────────────────────┴───────┴─────────┴─────────┴─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┴────────┴────────────────────────────┴─────────────┘
┌─name──────────────────────────────────────────┬─value─┬─default─┬─changed─┬─description─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┬─type───┬─changeable_without_restart─┬─is_obsolete─┐
│ max_thread_pool_size │ 10000 │ 10000 │ 0 │ The maximum number of threads that could be allocated from the OS and used for query execution and background operations. │ UInt64 │ No │ 0 │
│ max_thread_pool_free_size │ 1000 │ 1000 │ 0 │ The maximum number of threads that will always stay in a global thread pool once allocated and remain idle in case of insufficient number of tasks. │ UInt64 │ No │ 0 │
│ thread_pool_queue_size │ 10000 │ 10000 │ 0 │ The maximum number of tasks that will be placed in a queue and wait for execution. │ UInt64 │ No │ 0 │
│ max_io_thread_pool_size │ 100 │ 100 │ 0 │ The maximum number of threads that would be used for IO operations │ UInt64 │ No │ 0 │
│ max_io_thread_pool_free_size │ 0 │ 0 │ 0 │ Max free size for IO thread pool. │ UInt64 │ No │ 0 │
│ io_thread_pool_queue_size │ 10000 │ 10000 │ 0 │ Queue size for IO thread pool. │ UInt64 │ No │ 0 │
│ max_active_parts_loading_thread_pool_size │ 64 │ 64 │ 0 │ The number of threads to load active set of data parts (Active ones) at startup. │ UInt64 │ No │ 0 │
│ max_outdated_parts_loading_thread_pool_size │ 32 │ 32 │ 0 │ The number of threads to load inactive set of data parts (Outdated ones) at startup. │ UInt64 │ No │ 0 │
│ max_unexpected_parts_loading_thread_pool_size │ 32 │ 32 │ 0 │ The number of threads to load inactive set of data parts (Unexpected ones) at startup. │ UInt64 │ No │ 0 │
│ max_parts_cleaning_thread_pool_size │ 128 │ 128 │ 0 │ The number of threads for concurrent removal of inactive data parts. │ UInt64 │ No │ 0 │
│ max_backups_io_thread_pool_size │ 1000 │ 1000 │ 0 │ The maximum number of threads that would be used for IO operations for BACKUP queries │ UInt64 │ No │ 0 │
│ max_backups_io_thread_pool_free_size │ 0 │ 0 │ 0 │ Max free size for backups IO thread pool. │ UInt64 │ No │ 0 │
│ backups_io_thread_pool_queue_size │ 0 │ 0 │ 0 │ Queue size for backups IO thread pool. │ UInt64 │ No │ 0 │
└───────────────────────────────────────────────┴───────┴─────────┴─────────┴─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┴────────┴────────────────────────────┴─────────────┘
```

1
docs/en/sql-reference/data-types/map.md
View File

@ -7,6 +7,7 @@ sidebar_label: Map(K, V)
# Map(K, V)
`Map(K, V)` data type stores `key:value` pairs.
The Map datatype is implemented as `Array(Tuple(key T1, value T2))`, which means that the order of keys in each map does not change, i.e., this data type maintains insertion order.
**Parameters**

31
docs/en/sql-reference/functions/conditional-functions.md
View File

@ -234,3 +234,34 @@ SELECT least(toDateTime32(now() + toIntervalDay(1)), toDateTime64(now(), 3))
:::note
The type returned is a DateTime64 as the DataTime32 must be promoted to 64 bit for the comparison.
:::
## clamp
Constrain the return value between A and B.
**Syntax**
``` sql
clamp(value, min, max)
```
**Arguments**
- `value` – Input value.
- `min` – Limit the lower bound.
- `max` – Limit the upper bound.
**Returned values**
If the value is less than the minimum value, return the minimum value; if it is greater than the maximum value, return the maximum value; otherwise, return the current value.
Examples:
```sql
SELECT clamp(1, 2, 3) result, toTypeName(result) type;
```
```response
┌─result─┬─type────┐
│ 2 │ Float64 │
└────────┴─────────┘
```

476
docs/en/sql-reference/functions/date-time-functions.md
View File

@ -2558,13 +2558,27 @@ Like function `YYYYMMDDhhmmssToDate()` but produces a [DateTime64](../../sql-ref
Accepts an additional, optional `precision` parameter after the `timezone` parameter.
## addYears, addQuarters, addMonths, addWeeks, addDays, addHours, addMinutes, addSeconds, addMilliseconds, addMicroseconds, addNanoseconds
## addYears
These functions add units of the interval specified by the function name to a date, a date with time or a string-encoded date / date with time. A date or date with time is returned.
Adds a specified number of years to a date, a date with time or a string-encoded date / date with time.
Example:
**Syntax**
``` sql
```sql
addYears(date, num)
```
**Parameters**
- `date`: Date / date with time to add specified number of years to. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md), [String](../data-types/string.md).
- `num`: Number of years to add. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date` plus `num` years. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Example**
```sql
WITH
toDate('2024-01-01') AS date,
toDateTime('2024-01-01 00:00:00') AS date_time,
@ -2575,12 +2589,456 @@ SELECT
addYears(date_time_string, 1) AS add_years_with_date_time_string
```
``` text
```response
┌─add_years_with_date─┬─add_years_with_date_time─┬─add_years_with_date_time_string─┐
│ 2025-01-01 │ 2025-01-01 00:00:00 │ 2025-01-01 00:00:00.000 │
└─────────────────────┴──────────────────────────┴─────────────────────────────────┘
```
## addQuarters
Adds a specified number of quarters to a date, a date with time or a string-encoded date / date with time.
**Syntax**
```sql
addQuarters(date, num)
```
**Parameters**
- `date`: Date / date with time to add specified number of quarters to. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md), [String](../data-types/string.md).
- `num`: Number of quarters to add. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date` plus `num` quarters. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Example**
```sql
WITH
toDate('2024-01-01') AS date,
toDateTime('2024-01-01 00:00:00') AS date_time,
'2024-01-01 00:00:00' AS date_time_string
SELECT
addQuarters(date, 1) AS add_quarters_with_date,
addQuarters(date_time, 1) AS add_quarters_with_date_time,
addQuarters(date_time_string, 1) AS add_quarters_with_date_time_string
```
```response
┌─add_quarters_with_date─┬─add_quarters_with_date_time─┬─add_quarters_with_date_time_string─┐
│ 2024-04-01 │ 2024-04-01 00:00:00 │ 2024-04-01 00:00:00.000 │
└────────────────────────┴─────────────────────────────┴────────────────────────────────────┘
```
## addMonths
Adds a specified number of months to a date, a date with time or a string-encoded date / date with time.
**Syntax**
```sql
addMonths(date, num)
```
**Parameters**
- `date`: Date / date with time to add specified number of months to. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md), [String](../data-types/string.md).
- `num`: Number of months to add. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date` plus `num` months. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Example**
```sql
WITH
toDate('2024-01-01') AS date,
toDateTime('2024-01-01 00:00:00') AS date_time,
'2024-01-01 00:00:00' AS date_time_string
SELECT
addMonths(date, 6) AS add_months_with_date,
addMonths(date_time, 6) AS add_months_with_date_time,
addMonths(date_time_string, 6) AS add_months_with_date_time_string
```
```response
┌─add_months_with_date─┬─add_months_with_date_time─┬─add_months_with_date_time_string─┐
│ 2024-07-01 │ 2024-07-01 00:00:00 │ 2024-07-01 00:00:00.000 │
└──────────────────────┴───────────────────────────┴──────────────────────────────────┘
```
## addWeeks
Adds a specified number of weeks to a date, a date with time or a string-encoded date / date with time.
**Syntax**
```sql
addWeeks(date, num)
```
**Parameters**
- `date`: Date / date with time to add specified number of weeks to. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md), [String](../data-types/string.md).
- `num`: Number of weeks to add. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date` plus `num` weeks. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Example**
```sql
WITH
toDate('2024-01-01') AS date,
toDateTime('2024-01-01 00:00:00') AS date_time,
'2024-01-01 00:00:00' AS date_time_string
SELECT
addWeeks(date, 5) AS add_weeks_with_date,
addWeeks(date_time, 5) AS add_weeks_with_date_time,
addWeeks(date_time_string, 5) AS add_weeks_with_date_time_string
```
```response
┌─add_weeks_with_date─┬─add_weeks_with_date_time─┬─add_weeks_with_date_time_string─┐
│ 2024-02-05 │ 2024-02-05 00:00:00 │ 2024-02-05 00:00:00.000 │
└─────────────────────┴──────────────────────────┴─────────────────────────────────┘
```
## addDays
Adds a specified number of days to a date, a date with time or a string-encoded date / date with time.
**Syntax**
```sql
addDays(date, num)
```
**Parameters**
- `date`: Date / date with time to add specified number of days to. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md), [String](../data-types/string.md).
- `num`: Number of days to add. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date` plus `num` days. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Example**
```sql
WITH
toDate('2024-01-01') AS date,
toDateTime('2024-01-01 00:00:00') AS date_time,
'2024-01-01 00:00:00' AS date_time_string
SELECT
addDays(date, 5) AS add_days_with_date,
addDays(date_time, 5) AS add_days_with_date_time,
addDays(date_time_string, 5) AS add_days_with_date_time_string
```
```response
┌─add_days_with_date─┬─add_days_with_date_time─┬─add_days_with_date_time_string─┐
│ 2024-01-06 │ 2024-01-06 00:00:00 │ 2024-01-06 00:00:00.000 │
└────────────────────┴─────────────────────────┴────────────────────────────────┘
```
## addHours
Adds a specified number of days to a date, a date with time or a string-encoded date / date with time.
**Syntax**
```sql
addHours(date, num)
```
**Parameters**
- `date`: Date / date with time to add specified number of hours to. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md), [String](../data-types/string.md).
- `num`: Number of hours to add. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date` plus `num` hours. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Example**
```sql
WITH
toDate('2024-01-01') AS date,
toDateTime('2024-01-01 00:00:00') AS date_time,
'2024-01-01 00:00:00' AS date_time_string
SELECT
addHours(date, 12) AS add_hours_with_date,
addHours(date_time, 12) AS add_hours_with_date_time,
addHours(date_time_string, 12) AS add_hours_with_date_time_string
```
```response
┌─add_hours_with_date─┬─add_hours_with_date_time─┬─add_hours_with_date_time_string─┐
│ 2024-01-01 12:00:00 │ 2024-01-01 12:00:00 │ 2024-01-01 12:00:00.000 │
└─────────────────────┴──────────────────────────┴─────────────────────────────────┘
```
## addMinutes
Adds a specified number of minutes to a date, a date with time or a string-encoded date / date with time.
**Syntax**
```sql
addMinutes(date, num)
```
**Parameters**
- `date`: Date / date with time to add specified number of minutes to. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md), [String](../data-types/string.md).
- `num`: Number of minutes to add. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date` plus `num` minutes. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Example**
```sql
WITH
toDate('2024-01-01') AS date,
toDateTime('2024-01-01 00:00:00') AS date_time,
'2024-01-01 00:00:00' AS date_time_string
SELECT
addMinutes(date, 20) AS add_minutes_with_date,
addMinutes(date_time, 20) AS add_minutes_with_date_time,
addMinutes(date_time_string, 20) AS add_minutes_with_date_time_string
```
```response
┌─add_minutes_with_date─┬─add_minutes_with_date_time─┬─add_minutes_with_date_time_string─┐
│ 2024-01-01 00:20:00 │ 2024-01-01 00:20:00 │ 2024-01-01 00:20:00.000 │
└───────────────────────┴────────────────────────────┴───────────────────────────────────┘
```
## addSeconds
Adds a specified number of seconds to a date, a date with time or a string-encoded date / date with time.
**Syntax**
```sql
addSeconds(date, num)
```
**Parameters**
- `date`: Date / date with time to add specified number of seconds to. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md), [String](../data-types/string.md).
- `num`: Number of seconds to add. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date` plus `num` seconds. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Example**
```sql
WITH
toDate('2024-01-01') AS date,
toDateTime('2024-01-01 00:00:00') AS date_time,
'2024-01-01 00:00:00' AS date_time_string
SELECT
addSeconds(date, 30) AS add_seconds_with_date,
addSeconds(date_time, 30) AS add_seconds_with_date_time,
addSeconds(date_time_string, 30) AS add_seconds_with_date_time_string
```
```response
┌─add_seconds_with_date─┬─add_seconds_with_date_time─┬─add_seconds_with_date_time_string─┐
│ 2024-01-01 00:00:30 │ 2024-01-01 00:00:30 │ 2024-01-01 00:00:30.000 │
└───────────────────────┴────────────────────────────┴───────────────────────────────────┘
```
## addMilliseconds
Adds a specified number of milliseconds to a date with time or a string-encoded date with time.
**Syntax**
```sql
addMilliseconds(date_time, num)
```
**Parameters**
- `date_time`: Date with time to add specified number of milliseconds to. [DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md), [String](../data-types/string.md).
- `num`: Number of milliseconds to add. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date_time` plus `num` milliseconds. [DateTime64](../data-types/datetime64.md).
**Example**
```sql
WITH
toDateTime('2024-01-01 00:00:00') AS date_time,
'2024-01-01 00:00:00' AS date_time_string
SELECT
addMilliseconds(date_time, 1000) AS add_milliseconds_with_date_time,
addMilliseconds(date_time_string, 1000) AS add_milliseconds_with_date_time_string
```
```response
┌─add_milliseconds_with_date_time─┬─add_milliseconds_with_date_time_string─┐
│ 2024-01-01 00:00:01.000 │ 2024-01-01 00:00:01.000 │
└─────────────────────────────────┴────────────────────────────────────────┘
```
## addMicroseconds
Adds a specified number of microseconds to a date with time or a string-encoded date with time.
**Syntax**
```sql
addMicroseconds(date_time, num)
```
**Parameters**
- `date_time`: Date with time to add specified number of microseconds to. [DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md), [String](../data-types/string.md).
- `num`: Number of microseconds to add. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date_time` plus `num` microseconds. [DateTime64](../data-types/datetime64.md).
**Example**
```sql
WITH
toDateTime('2024-01-01 00:00:00') AS date_time,
'2024-01-01 00:00:00' AS date_time_string
SELECT
addMicroseconds(date_time, 1000000) AS add_microseconds_with_date_time,
addMicroseconds(date_time_string, 1000000) AS add_microseconds_with_date_time_string
```
```response
┌─add_microseconds_with_date_time─┬─add_microseconds_with_date_time_string─┐
│ 2024-01-01 00:00:01.000000 │ 2024-01-01 00:00:01.000000 │
└─────────────────────────────────┴────────────────────────────────────────┘
```
## addNanoseconds
Adds a specified number of microseconds to a date with time or a string-encoded date with time.
**Syntax**
```sql
addNanoseconds(date_time, num)
```
**Parameters**
- `date_time`: Date with time to add specified number of nanoseconds to. [DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md), [String](../data-types/string.md).
- `num`: Number of nanoseconds to add. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date_time` plus `num` nanoseconds. [DateTime64](../data-types/datetime64.md).
**Example**
```sql
WITH
toDateTime('2024-01-01 00:00:00') AS date_time,
'2024-01-01 00:00:00' AS date_time_string
SELECT
addNanoseconds(date_time, 1000) AS add_nanoseconds_with_date_time,
addNanoseconds(date_time_string, 1000) AS add_nanoseconds_with_date_time_string
```
```response
┌─add_nanoseconds_with_date_time─┬─add_nanoseconds_with_date_time_string─┐
│ 2024-01-01 00:00:00.000001000 │ 2024-01-01 00:00:00.000001000 │
└────────────────────────────────┴───────────────────────────────────────┘
```
## addInterval
Adds an interval to another interval or tuple of intervals.
**Syntax**
```sql
addInterval(interval_1, interval_2)
```
**Parameters**
- `interval_1`: First interval or tuple of intervals. [interval](../data-types/special-data-types/interval.md), [tuple](../data-types/tuple.md)([interval](../data-types/special-data-types/interval.md)).
- `interval_2`: Second interval to be added. [interval](../data-types/special-data-types/interval.md).
**Returned value**
- Returns a tuple of intervals. [tuple](../data-types/tuple.md)([interval](../data-types/special-data-types/interval.md)).
:::note
Intervals of the same type will be combined into a single interval. For instance if `toIntervalDay(1)` and `toIntervalDay(2)` are passed then the result will be `(3)` rather than `(1,1)`.
:::
**Example**
Query:
```sql
SELECT addInterval(INTERVAL 1 DAY, INTERVAL 1 MONTH);
SELECT addInterval((INTERVAL 1 DAY, INTERVAL 1 YEAR), INTERVAL 1 MONTH);
SELECT addInterval(INTERVAL 2 DAY, INTERVAL 1 DAY);
```
Result:
```response
┌─addInterval(toIntervalDay(1), toIntervalMonth(1))─┐
│ (1,1) │
└───────────────────────────────────────────────────┘
┌─addInterval((toIntervalDay(1), toIntervalYear(1)), toIntervalMonth(1))─┐
│ (1,1,1) │
└────────────────────────────────────────────────────────────────────────┘
┌─addInterval(toIntervalDay(2), toIntervalDay(1))─┐
│ (3) │
└─────────────────────────────────────────────────┘
```
## addTupleOfIntervals
Consecutively adds a tuple of intervals to a Date or a DateTime.
**Syntax**
```sql
addTupleOfIntervals(interval_1, interval_2)
```
**Parameters**
- `date`: First interval or interval of tuples. [date](../data-types/date.md)/[date32](../data-types/date32.md)/[datetime](../data-types/datetime.md)/[datetime64](../data-types/datetime64.md).
- `intervals`: Tuple of intervals to add to `date`. [tuple](../data-types/tuple.md)([interval](../data-types/special-data-types/interval.md)).
**Returned value**
- Returns `date` with added `intervals`. [date](../data-types/date.md)/[date32](../data-types/date32.md)/[datetime](../data-types/datetime.md)/[datetime64](../data-types/datetime64.md).
**Example**
Query:
```sql
WITH toDate('2018-01-01') AS date
SELECT addTupleOfIntervals(date, (INTERVAL 1 DAY, INTERVAL 1 MONTH, INTERVAL 1 YEAR))
```
Result:
```response
┌─addTupleOfIntervals(date, (toIntervalDay(1), toIntervalMonth(1), toIntervalYear(1)))─┐
│ 2019-02-02 │
└──────────────────────────────────────────────────────────────────────────────────────┘
```
## subtractYears
Subtracts a specified number of years from a date, a date with time or a string-encoded date / date with time.
@ -2893,7 +3351,7 @@ subtractMilliseconds(date_time, num)
- `num`: Number of milliseconds to subtract. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date_time` minus `num` milliseconds. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
- Returns `date_time` minus `num` milliseconds. [DateTime64](../data-types/datetime64.md).
**Example**
@ -2928,7 +3386,7 @@ subtractMicroseconds(date_time, num)
- `num`: Number of microseconds to subtract. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date_time` minus `num` microseconds. [DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
- Returns `date_time` minus `num` microseconds. [DateTime64](../data-types/datetime64.md).
**Example**
@ -2963,7 +3421,7 @@ subtractNanoseconds(date_time, num)
- `num`: Number of nanoseconds to subtract. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date_time` minus `num` nanoseconds. [DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
- Returns `date_time` minus `num` nanoseconds. [DateTime64](../data-types/datetime64.md).
**Example**
@ -3001,7 +3459,7 @@ subtractInterval(interval_1, interval_2)
- Returns a tuple of intervals. [tuple](../data-types/tuple.md)([interval](../data-types/special-data-types/interval.md)).
:::note
If the types of the first interval (or the interval in the tuple) and the second interval are the same they will be merged into one interval.
Intervals of the same type will be combined into a single interval. For instance if `toIntervalDay(2)` and `toIntervalDay(1)` are passed then the result will be `(1)` rather than `(2,1)`
:::
**Example**

71
docs/en/sql-reference/functions/functions-for-nulls.md
View File

@ -12,6 +12,8 @@ Returns whether the argument is [NULL](../../sql-reference/syntax.md#null).
See also operator [`IS NULL`](../operators/index.md#is_null).
**Syntax**
``` sql
isNull(x)
```
@ -52,6 +54,45 @@ Result:
└───┘
```
## isNullable
Returns `1` if a column is [Nullable](../data-types/nullable.md) (i.e allows `NULL` values), `0` otherwise.
**Syntax**
``` sql
isNullable(x)
```
**Arguments**
- `x` — column.
**Returned value**
- `1` if `x` allows `NULL` values. [UInt8](../data-types/int-uint.md).
- `0` if `x` does not allow `NULL` values. [UInt8](../data-types/int-uint.md).
**Example**
Query:
``` sql
CREATE TABLE tab (ordinary_col UInt32, nullable_col Nullable(UInt32)) ENGINE = Log;
INSERT INTO tab (ordinary_col, nullable_col) VALUES (1,1), (2, 2), (3,3);
SELECT isNullable(ordinary_col), isNullable(nullable_col) FROM tab;
```
Result:
``` text
┌───isNullable(ordinary_col)──┬───isNullable(nullable_col)──┐
1. │ 0 │ 1 │
2. │ 0 │ 1 │
3. │ 0 │ 1 │
└─────────────────────────────┴─────────────────────────────┘
```
## isNotNull
Returns whether the argument is not [NULL](../../sql-reference/syntax.md#null-literal).
@ -96,6 +137,36 @@ Result:
└───┘
```
## isNotDistinctFrom
Performs null-safe comparison. Used to compare JOIN keys which contain NULL values in the JOIN ON section.
This function will consider two `NULL` values as identical and will return `true`, which is distinct from the usual
equals behavior where comparing two `NULL` values would return `NULL`.
:::note
This function is an internal function used by the implementation of JOIN ON. Please do not use it manually in queries.
:::
**Syntax**
``` sql
isNotDistinctFrom(x, y)
```
**Arguments**
- `x` — first JOIN key.
- `y` — second JOIN key.
**Returned value**
- `true` when `x` and `y` are both `NULL`.
- `false` otherwise.
**Example**
For a complete example see: [NULL values in JOIN keys](../../sql-reference/statements/select/join#null-values-in-join-keys).
## isZeroOrNull
Returns whether the argument is 0 (zero) or [NULL](../../sql-reference/syntax.md#null-literal).

28
docs/en/sql-reference/functions/other-functions.md
View File

@ -3301,3 +3301,31 @@ The setting is not enabled by default for security reasons, because some headers
HTTP headers are case sensitive for this function.
If the function is used in the context of a distributed query, it returns non-empty result only on the initiator node.
## showCertificate
Shows information about the current server's Secure Sockets Layer (SSL) certificate if it has been configured. See [Configuring SSL-TLS](https://clickhouse.com/docs/en/guides/sre/configuring-ssl) for more information on how to configure ClickHouse to use OpenSSL certificates to validate connections.
**Syntax**
```sql
showCertificate()
```
**Returned value**
- Map of key-value pairs relating to the configured SSL certificate. [Map](../../sql-reference/data-types/map.md)([String](../../sql-reference/data-types/string.md), [String](../../sql-reference/data-types/string.md)).
**Example**
Query:
```sql
SELECT showCertificate() FORMAT LineAsString;
```
Result:
```response
{'version':'1','serial_number':'2D9071D64530052D48308473922C7ADAFA85D6C5','signature_algo':'sha256WithRSAEncryption','issuer':'/CN=marsnet.local CA','not_before':'May 7 17:01:21 2024 GMT','not_after':'May 7 17:01:21 2025 GMT','subject':'/CN=chnode1','pkey_algo':'rsaEncryption'}
```

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

@ -1058,7 +1058,7 @@ convertCharset(s, from, to)
## base58Encode
Encodes a String using [Base58](https://tools.ietf.org/id/draft-msporny-base58-01.html) in the "Bitcoin" alphabet.
Encodes a String using [Base58](https://datatracker.ietf.org/doc/html/draft-msporny-base58) in the "Bitcoin" alphabet.
**Syntax**
@ -1092,7 +1092,7 @@ Result:
## base58Decode
Accepts a String and decodes it using [Base58](https://tools.ietf.org/id/draft-msporny-base58-01.html) encoding scheme using "Bitcoin" alphabet.
Accepts a String and decodes it using [Base58](https://datatracker.ietf.org/doc/html/draft-msporny-base58) encoding scheme using "Bitcoin" alphabet.
**Syntax**

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

@ -152,7 +152,7 @@ Configuration example:
**Syntax**
``` sql
cutToFirstSignificantSubdomain(URL, TLD)
cutToFirstSignificantSubdomainCustom(URL, TLD)
```
**Arguments**

10
docs/en/sql-reference/statements/select/join.md
View File

@ -151,6 +151,14 @@ Result:
Query with `INNER` type of a join and conditions with `OR` and `AND`:
:::note
By default, non-equal conditions are supported as long as they use columns from the same table.
For example, `t1.a = t2.key AND t1.b > 0 AND t2.b > t2.c`, because `t1.b > 0` uses columns only from `t1` and `t2.b > t2.c` uses columns only from `t2`.
However, you can try experimental support for conditions like `t1.a = t2.key AND t1.b > t2.key`, check out section below for more details.
:::
``` sql
SELECT a, b, val FROM t1 INNER JOIN t2 ON t1.a = t2.key OR t1.b = t2.key AND t2.val > 3;
```
@ -165,7 +173,7 @@ Result:
└───┴────┴─────┘
```
## [experimental] Join with inequality conditions
## [experimental] Join with inequality conditions for columns from different tables
:::note
This feature is experimental. To use it, set `allow_experimental_join_condition` to 1 in your configuration files or by using the `SET` command:

235
docs/en/sql-reference/statements/select/with.md
View File

@ -5,21 +5,21 @@ sidebar_label: WITH
# WITH Clause
ClickHouse supports Common Table Expressions ([CTE](https://en.wikipedia.org/wiki/Hierarchical_and_recursive_queries_in_SQL)) and substitutes the code defined in the `WITH` clause in all places of use for the rest of `SELECT` query. Named subqueries can be included to the current and child query context in places where table objects are allowed. Recursion is prevented by hiding the current level CTEs from the WITH expression.
ClickHouse supports Common Table Expressions ([CTE](https://en.wikipedia.org/wiki/Hierarchical_and_recursive_queries_in_SQL)) and substitutes the code defined in the `WITH` clause in all places of use for the rest of `SELECT` query. Named subqueries can be included to the current and child query context in places where table objects are allowed. Recursion is prevented by hiding the current level CTEs from the WITH expression.
Please note that CTEs do not guarantee the same results in all places they are called because the query will be re-executed for each use case.
An example of such behavior is below
``` sql
with cte_numbers as
with cte_numbers as
(
select
num
from generateRandom('num UInt64', NULL)
select
num
from generateRandom('num UInt64', NULL)
limit 1000000
)
select
count()
count()
from cte_numbers
where num in (select num from cte_numbers)
```
@ -87,3 +87,226 @@ LIMIT 10;
WITH test1 AS (SELECT i + 1, j + 1 FROM test1)
SELECT * FROM test1;
```
## Recursive Queries
The optional RECURSIVE modifier allows for a WITH query to refer to its own output. Example:
**Example:** Sum integers from 1 through 100
```sql
WITH RECURSIVE test_table AS (
SELECT 1 AS number
UNION ALL
SELECT number + 1 FROM test_table WHERE number < 100
)
SELECT sum(number) FROM test_table;
```
``` text
┌─sum(number)─┐
│ 5050 │
└─────────────┘
```
The general form of a recursive `WITH` query is always a non-recursive term, then `UNION ALL`, then a recursive term, where only the recursive term can contain a reference to the query's own output. Recursive CTE query is executed as follows:
1. Evaluate the non-recursive term. Place result of non-recursive term query in a temporary working table.
2. As long as the working table is not empty, repeat these steps:
1. Evaluate the recursive term, substituting the current contents of the working table for the recursive self-reference. Place result of recursive term query in a temporary intermediate table.
2. Replace the contents of the working table with the contents of the intermediate table, then empty the intermediate table.
Recursive queries are typically used to work with hierarchical or tree-structured data. For example, we can write a query that performs tree traversal:
**Example:** Tree traversal
First let's create tree table:
```sql
DROP TABLE IF EXISTS tree;
CREATE TABLE tree
(
id UInt64,
parent_id Nullable(UInt64),
data String
) ENGINE = MergeTree ORDER BY id;
INSERT INTO tree VALUES (0, NULL, 'ROOT'), (1, 0, 'Child_1'), (2, 0, 'Child_2'), (3, 1, 'Child_1_1');
```
We can traverse those tree with such query:
**Example:** Tree traversal
```sql
WITH RECURSIVE search_tree AS (
SELECT id, parent_id, data
FROM tree t
WHERE t.id = 0
UNION ALL
SELECT t.id, t.parent_id, t.data
FROM tree t, search_tree st
WHERE t.parent_id = st.id
)
SELECT * FROM search_tree;
```
```text
┌─id─┬─parent_id─┬─data──────┐
│ 0 │ ᴺᵁᴸᴸ │ ROOT │
│ 1 │ 0 │ Child_1 │
│ 2 │ 0 │ Child_2 │
│ 3 │ 1 │ Child_1_1 │
└────┴───────────┴───────────┘
```
### Search order
To create a depth-first order, we compute for each result row an array of rows that we have already visited:
**Example:** Tree traversal depth-first order
```sql
WITH RECURSIVE search_tree AS (
SELECT id, parent_id, data, [t.id] AS path
FROM tree t
WHERE t.id = 0
UNION ALL
SELECT t.id, t.parent_id, t.data, arrayConcat(path, [t.id])
FROM tree t, search_tree st
WHERE t.parent_id = st.id
)
SELECT * FROM search_tree ORDER BY path;
```
```text
┌─id─┬─parent_id─┬─data──────┬─path────┐
│ 0 │ ᴺᵁᴸᴸ │ ROOT │ [0] │
│ 1 │ 0 │ Child_1 │ [0,1] │
│ 3 │ 1 │ Child_1_1 │ [0,1,3] │
│ 2 │ 0 │ Child_2 │ [0,2] │
└────┴───────────┴───────────┴─────────┘
```
To create a breadth-first order, standard approach is to add column that tracks the depth of the search:
**Example:** Tree traversal breadth-first order
```sql
WITH RECURSIVE search_tree AS (
SELECT id, parent_id, data, [t.id] AS path, toUInt64(0) AS depth
FROM tree t
WHERE t.id = 0
UNION ALL
SELECT t.id, t.parent_id, t.data, arrayConcat(path, [t.id]), depth + 1
FROM tree t, search_tree st
WHERE t.parent_id = st.id
)
SELECT * FROM search_tree ORDER BY depth;
```
```text
┌─id─┬─link─┬─data──────┬─path────┬─depth─┐
│ 0 │ ᴺᵁᴸᴸ │ ROOT │ [0] │ 0 │
│ 1 │ 0 │ Child_1 │ [0,1] │ 1 │
│ 2 │ 0 │ Child_2 │ [0,2] │ 1 │
│ 3 │ 1 │ Child_1_1 │ [0,1,3] │ 2 │
└────┴──────┴───────────┴─────────┴───────┘
```
### Cycle detection
First let's create graph table:
```sql
DROP TABLE IF EXISTS graph;
CREATE TABLE graph
(
from UInt64,
to UInt64,
label String
) ENGINE = MergeTree ORDER BY (from, to);
INSERT INTO graph VALUES (1, 2, '1 -> 2'), (1, 3, '1 -> 3'), (2, 3, '2 -> 3'), (1, 4, '1 -> 4'), (4, 5, '4 -> 5');
```
We can traverse that graph with such query:
**Example:** Graph traversal without cycle detection
```sql
WITH RECURSIVE search_graph AS (
SELECT from, to, label FROM graph g
UNION ALL
SELECT g.from, g.to, g.label
FROM graph g, search_graph sg
WHERE g.from = sg.to
)
SELECT DISTINCT * FROM search_graph ORDER BY from;
```
```text
┌─from─┬─to─┬─label──┐
│ 1 │ 4 │ 1 -> 4 │
│ 1 │ 2 │ 1 -> 2 │
│ 1 │ 3 │ 1 -> 3 │
│ 2 │ 3 │ 2 -> 3 │
│ 4 │ 5 │ 4 -> 5 │
└──────┴────┴────────┘
```
But if we add cycle in that graph, previous query will fail with `Maximum recursive CTE evaluation depth` error:
```sql
INSERT INTO graph VALUES (5, 1, '5 -> 1');
WITH RECURSIVE search_graph AS (
SELECT from, to, label FROM graph g
UNION ALL
SELECT g.from, g.to, g.label
FROM graph g, search_graph sg
WHERE g.from = sg.to
)
SELECT DISTINCT * FROM search_graph ORDER BY from;
```
```text
Code: 306. DB::Exception: Received from localhost:9000. DB::Exception: Maximum recursive CTE evaluation depth (1000) exceeded, during evaluation of search_graph AS (SELECT from, to, label FROM graph AS g UNION ALL SELECT g.from, g.to, g.label FROM graph AS g, search_graph AS sg WHERE g.from = sg.to). Consider raising max_recursive_cte_evaluation_depth setting.: While executing RecursiveCTESource. (TOO_DEEP_RECURSION)
```
The standard method for handling cycles is to compute an array of the already visited nodes:
**Example:** Graph traversal with cycle detection
```sql
WITH RECURSIVE search_graph AS (
SELECT from, to, label, false AS is_cycle, [tuple(g.from, g.to)] AS path FROM graph g
UNION ALL
SELECT g.from, g.to, g.label, has(path, tuple(g.from, g.to)), arrayConcat(sg.path, [tuple(g.from, g.to)])
FROM graph g, search_graph sg
WHERE g.from = sg.to AND NOT is_cycle
)
SELECT * FROM search_graph WHERE is_cycle ORDER BY from;
```
```text
┌─from─┬─to─┬─label──┬─is_cycle─┬─path──────────────────────┐
│ 1 │ 4 │ 1 -> 4 │ true │ [(1,4),(4,5),(5,1),(1,4)] │
│ 4 │ 5 │ 4 -> 5 │ true │ [(4,5),(5,1),(1,4),(4,5)] │
│ 5 │ 1 │ 5 -> 1 │ true │ [(5,1),(1,4),(4,5),(5,1)] │
└──────┴────┴────────┴──────────┴───────────────────────────┘
```
### Infinite queries
It is also possible to use infinite recursive CTE queries if `LIMIT` is used in outer query:
**Example:** Infinite recursive CTE query
```sql
WITH RECURSIVE test_table AS (
SELECT 1 AS number
UNION ALL
SELECT number + 1 FROM test_table
)
SELECT sum(number) FROM (SELECT number FROM test_table LIMIT 100);
```
```text
┌─sum(number)─┐
│ 5050 │
└─────────────┘
```

19
docs/en/sql-reference/table-functions/s3.md
View File

@ -248,6 +248,25 @@ FROM s3(
LIMIT 5;
```
## Working with archives
Suppose that we have several archive files with following URIs on S3:
- 'https://s3-us-west-1.amazonaws.com/umbrella-static/top-1m-2018-01-10.csv.zip'
- 'https://s3-us-west-1.amazonaws.com/umbrella-static/top-1m-2018-01-11.csv.zip'
- 'https://s3-us-west-1.amazonaws.com/umbrella-static/top-1m-2018-01-12.csv.zip'
Extracting data from these archives is possible using ::. Globs can be used both in the url part as well as in the part after :: (responsible for the name of a file inside the archive).
``` sql
SELECT *
FROM s3(
'https://s3-us-west-1.amazonaws.com/umbrella-static/top-1m-2018-01-1{0..2}.csv.zip :: *.csv'
);
```
## Virtual Columns {#virtual-columns}
- `_path` — Path to the file. Type: `LowCardinalty(String)`.

2
docs/ru/operations/utilities/backupview.md
View File

@ -1,5 +1,5 @@
---
slug: /en/operations/utilities/backupview
slug: /ru/operations/utilities/backupview
title: clickhouse_backupview
---

311
docs/ru/sql-reference/functions/null-functions.md Normal file
View File

@ -0,0 +1,311 @@
---
slug: /ru/sql-reference/functions/null-functions
sidebar_position: 63
sidebar_label: "Функции для работы с Nullable-аргументами"
---
# Функции для работы с Nullable-аргументами {#funktsii-dlia-raboty-s-nullable-argumentami}
## isNull {#isnull}
Проверяет является ли аргумент [NULL](../../sql-reference/syntax.md#null-literal).
``` sql
isNull(x)
```
Синоним: `ISNULL`.
**Аргументы**
- `x` — значение с не составным типом данных.
**Возвращаемое значение**
- `1`, если `x` — `NULL`.
- `0`, если `x` — не `NULL`.
**Пример**
Входная таблица
``` text
┌─x─┬────y─┐
│ 1 │ ᴺᵁᴸᴸ │
│ 2 │ 3 │
└───┴──────┘
```
Запрос
``` sql
SELECT x FROM t_null WHERE isNull(y);
```
``` text
┌─x─┐
│ 1 │
└───┘
```
## isNotNull {#isnotnull}
Проверяет не является ли аргумент [NULL](../../sql-reference/syntax.md#null-literal).
``` sql
isNotNull(x)
```
**Аргументы**
- `x` — значение с не составным типом данных.
**Возвращаемое значение**
- `0`, если `x` — `NULL`.
- `1`, если `x` — не `NULL`.
**Пример**
Входная таблица
``` text
┌─x─┬────y─┐
│ 1 │ ᴺᵁᴸᴸ │
│ 2 │ 3 │
└───┴──────┘
```
Запрос
``` sql
SELECT x FROM t_null WHERE isNotNull(y);
```
``` text
┌─x─┐
│ 2 │
└───┘
```
## coalesce {#coalesce}
Последовательно слева-направо проверяет являются ли переданные аргументы `NULL` и возвращает первый не `NULL`.
``` sql
coalesce(x,...)
```
**Аргументы**
- Произвольное количество параметров не составного типа. Все параметры должны быть совместимы по типу данных.
**Возвращаемые значения**
- Первый не `NULL` аргумент.
- `NULL`, если все аргументы — `NULL`.
**Пример**
Рассмотрим адресную книгу, в которой может быть указано несколько способов связи с клиентом.
``` text
┌─name─────┬─mail─┬─phone─────┬──icq─┐
│ client 1 │ ᴺᵁᴸᴸ │ 123-45-67 │ 123 │
│ client 2 │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │
└──────────┴──────┴───────────┴──────┘
```
Поля `mail` и `phone` имеют тип String, а поле `icq` — `UInt32`, его необходимо будет преобразовать в `String`.
Получим из адресной книги первый доступный способ связаться с клиентом:
``` sql
SELECT coalesce(mail, phone, CAST(icq,'Nullable(String)')) FROM aBook;
```
``` text
┌─name─────┬─coalesce(mail, phone, CAST(icq, 'Nullable(String)'))─┐
│ client 1 │ 123-45-67 │
│ client 2 │ ᴺᵁᴸᴸ │
└──────────┴──────────────────────────────────────────────────────┘
```
## ifNull {#ifnull}
Возвращает альтернативное значение, если основной аргумент — `NULL`.
``` sql
ifNull(x,alt)
```
**Аргументы**
- `x` — значение для проверки на `NULL`,
- `alt` — значение, которое функция вернёт, если `x` — `NULL`.
**Возвращаемые значения**
- Значение `x`, если `x` — не `NULL`.
- Значение `alt`, если `x` — `NULL`.
**Пример**
``` sql
SELECT ifNull('a', 'b');
```
``` text
┌─ifNull('a', 'b')─┐
│ a │
└──────────────────┘
```
``` sql
SELECT ifNull(NULL, 'b');
```
``` text
┌─ifNull(NULL, 'b')─┐
│ b │
└───────────────────┘
```
## nullIf {#nullif}
Возвращает `NULL`, если аргументы равны.
``` sql
nullIf(x, y)
```
**Аргументы**
`x`, `y` — значения для сравнивания. Они должны быть совместимых типов, иначе ClickHouse сгенерирует исключение.
**Возвращаемые значения**
- `NULL`, если аргументы равны.
- Значение `x`, если аргументы не равны.
**Пример**
``` sql
SELECT nullIf(1, 1);
```
``` text
┌─nullIf(1, 1)─┐
│ ᴺᵁᴸᴸ │
└──────────────┘
```
``` sql
SELECT nullIf(1, 2);
```
``` text
┌─nullIf(1, 2)─┐
│ 1 │
└──────────────┘
```
## assumeNotNull {#assumenotnull}
Приводит значение типа [Nullable](../../sql-reference/functions/functions-for-nulls.md) к не `Nullable`, если значение не `NULL`.
``` sql
assumeNotNull(x)
```
**Аргументы**
- `x` — исходное значение.
**Возвращаемые значения**
- Исходное значение с не `Nullable` типом, если оно — не `NULL`.
- Неспецифицированный результат, зависящий от реализации, если исходное значение — `NULL`.
**Пример**
Рассмотрим таблицу `t_null`.
``` sql
SHOW CREATE TABLE t_null;
```
``` text
┌─statement─────────────────────────────────────────────────────────────────┐
│ CREATE TABLE default.t_null ( x Int8, y Nullable(Int8)) ENGINE = TinyLog │
└───────────────────────────────────────────────────────────────────────────┘
```
``` text
┌─x─┬────y─┐
│ 1 │ ᴺᵁᴸᴸ │
│ 2 │ 3 │
└───┴──────┘
```
Применим функцию `assumeNotNull` к столбцу `y`.
``` sql
SELECT assumeNotNull(y) FROM t_null;
```
``` text
┌─assumeNotNull(y)─┐
│ 0 │
│ 3 │
└──────────────────┘
```
``` sql
SELECT toTypeName(assumeNotNull(y)) FROM t_null;
```
``` text
┌─toTypeName(assumeNotNull(y))─┐
│ Int8 │
│ Int8 │
└──────────────────────────────┘
```
## toNullable {#tonullable}
Преобразует тип аргумента к `Nullable`.
``` sql
toNullable(x)
```
**Аргументы**
- `x` — значение произвольного не составного типа.
**Возвращаемое значение**
- Входное значение с типом не `Nullable`.
**Пример**
``` sql
SELECT toTypeName(10);
```
``` text
┌─toTypeName(10)─┐
│ UInt8 │
└────────────────┘
```
``` sql
SELECT toTypeName(toNullable(10));
```
``` text
┌─toTypeName(toNullable(10))─┐
│ Nullable(UInt8) │
└────────────────────────────┘
```

2
docs/ru/sql-reference/functions/string-functions.md
View File

@ -493,7 +493,7 @@ SELECT concat(key1, key2), sum(value) FROM key_val GROUP BY (key1, key2);
## base58Encode(plaintext), base58Decode(encoded_text) {#base58}
Принимает на вход строку или колонку строк и кодирует/раскодирует их с помощью схемы кодирования [Base58](https://tools.ietf.org/id/draft-msporny-base58-01.html) с использованием стандартного алфавита Bitcoin.
Принимает на вход строку или колонку строк и кодирует/раскодирует их с помощью схемы кодирования [Base58](https://datatracker.ietf.org/doc/html/draft-msporny-base58) с использованием стандартного алфавита Bitcoin.
**Синтаксис**

254
docs/zh/sql-reference/functions/null-functions.md Normal file
View File

@ -0,0 +1,254 @@
---
slug: /zh/sql-reference/functions/null-functions
---
# Nullable处理函数 {#nullablechu-li-han-shu}
## isNull {#isnull}
检查参数是否为[NULL](../../sql-reference/syntax.md#null-literal)。
isNull(x)
**参数**
- `x` — 一个非复合数据类型的值。
**返回值**
- `1` 如果`x`为`NULL`。
- `0` 如果`x`不为`NULL`。
**示例**
存在以下内容的表
```response
┌─x─┬────y─┐
│ 1 │ ᴺᵁᴸᴸ │
│ 2 │ 3 │
└───┴──────┘
```
对其进行查询
```sql
SELECT x FROM t_null WHERE isNull(y)
```
```response
┌─x─┐
│ 1 │
└───┘
```
## isNotNull {#isnotnull}
检查参数是否不为 [NULL](../../sql-reference/syntax.md#null-literal).
isNotNull(x)
**参数:**
- `x` — 一个非复合数据类型的值。
**返回值**
- `0` 如果`x`为`NULL`。
- `1` 如果`x`不为`NULL`。
**示例**
存在以下内容的表
```response
┌─x─┬────y─┐
│ 1 │ ᴺᵁᴸᴸ │
│ 2 │ 3 │
└───┴──────┘
```
对其进行查询
```sql
SELECT x FROM t_null WHERE isNotNull(y)
```
```response
┌─x─┐
│ 2 │
└───┘
```
## 合并 {#coalesce}
检查从左到右是否传递了«NULL»参数并返回第一个非`'NULL`参数。
coalesce(x,...)
**参数:**
- 任何数量的非复合类型的参数。所有参数必须与数据类型兼容。
**返回值**
- 第一个非’NULL\`参数。
- `NULL`，如果所有参数都是’NULL\`。
**示例**
考虑可以指定多种联系客户的方式的联系人列表。
```response
┌─name─────┬─mail─┬─phone─────┬──icq─┐
│ client 1 │ ᴺᵁᴸᴸ │ 123-45-67 │ 123 │
│ client 2 │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │
└──────────┴──────┴───────────┴──────┘
```
`mail`和`phone`字段是String类型，但`icq`字段是`UInt32`，所以它需要转换为`String`。
从联系人列表中获取客户的第一个可用联系方式：
```sql
SELECT coalesce(mail, phone, CAST(icq,'Nullable(String)')) FROM aBook
```
```response
┌─name─────┬─coalesce(mail, phone, CAST(icq, 'Nullable(String)'))─┐
│ client 1 │ 123-45-67 │
│ client 2 │ ᴺᵁᴸᴸ │
└──────────┴──────────────────────────────────────────────────────┘
```
## ifNull {#ifnull}
如果第一个参数为«NULL»，则返回第二个参数的值。
ifNull(x,alt)
**参数:**
- `x` — 要检查«NULL»的值。
- `alt` — 如果`x`为’NULL\`，函数返回的值。
**返回值**
- 价值 `x`，如果 `x` 不是 `NULL`.
- 价值 `alt`，如果 `x` 是 `NULL`.
**示例**
SELECT ifNull('a', 'b')
┌─ifNull('a', 'b')─┐
│ a │
└──────────────────┘
SELECT ifNull(NULL, 'b')
┌─ifNull(NULL, 'b')─┐
│ b │
└───────────────────┘
## nullIf {#nullif}
如果参数相等，则返回`NULL`。
nullIf(x, y)
**参数:**
`x`, `y` — 用于比较的值。 它们必须是类型兼容的，否则将抛出异常。
**返回值**
- 如果参数相等，则为`NULL`。
- 如果参数不相等，则为`x`值。
**示例**
SELECT nullIf(1, 1)
┌─nullIf(1, 1)─┐
│ ᴺᵁᴸᴸ │
└──────────────┘
SELECT nullIf(1, 2)
┌─nullIf(1, 2)─┐
│ 1 │
└──────────────┘
## assumeNotNull {#assumenotnull}
将[可为空](../../sql-reference/functions/functions-for-nulls.md)类型的值转换为非`Nullable`类型的值。
assumeNotNull(x)
**参数：**
- `x` — 原始值。
**返回值**
- 如果`x`不为`NULL`，返回非`Nullable`类型的原始值。
- 如果`x`为`NULL`，则返回任意值。
**示例**
存在如下`t_null`表。
SHOW CREATE TABLE t_null
┌─statement─────────────────────────────────────────────────────────────────┐
│ CREATE TABLE default.t_null ( x Int8, y Nullable(Int8)) ENGINE = TinyLog │
└───────────────────────────────────────────────────────────────────────────┘
┌─x─┬────y─┐
│ 1 │ ᴺᵁᴸᴸ │
│ 2 │ 3 │
└───┴──────┘
将列`y`作为`assumeNotNull`函数的参数。
SELECT assumeNotNull(y) FROM t_null
┌─assumeNotNull(y)─┐
│ 0 │
│ 3 │
└──────────────────┘
SELECT toTypeName(assumeNotNull(y)) FROM t_null
┌─toTypeName(assumeNotNull(y))─┐
│ Int8 │
│ Int8 │
└──────────────────────────────┘
## 可调整 {#tonullable}
将参数的类型转换为`Nullable`。
toNullable(x)
**参数：**
- `x` — 任何非复合类型的值。
**返回值**
- 输入的值，但其类型为`Nullable`。
**示例**
SELECT toTypeName(10)
┌─toTypeName(10)─┐
│ UInt8 │
└────────────────┘
SELECT toTypeName(toNullable(10))
┌─toTypeName(toNullable(10))─┐
│ Nullable(UInt8) │
└────────────────────────────┘

4
programs/git-import/git-import.cpp
View File

@ -233,7 +233,7 @@ struct Commit
};
enum class FileChangeType
enum class FileChangeType : uint8_t
{
Add,
Delete,
@ -291,7 +291,7 @@ struct FileChange
};
enum class LineType
enum class LineType : uint8_t
{
Empty,
Comment,

10
programs/install/Install.cpp
View File

@ -323,7 +323,7 @@ int mainEntryClickHouseInstall(int argc, char ** argv)
{
fmt::print("Symlink {} already exists but it points to {}. Will replace the old symlink to {}.\n",
main_bin_path.string(), points_to.string(), binary_self_canonical_path.string());
fs::remove(main_bin_path);
(void)fs::remove(main_bin_path);
}
}
}
@ -489,7 +489,7 @@ int mainEntryClickHouseInstall(int argc, char ** argv)
{
fmt::print("Symlink {} already exists but it points to {}. Will replace the old symlink to {}.\n",
symlink_path.string(), points_to.string(), main_bin_path.string());
fs::remove(symlink_path);
(void)fs::remove(symlink_path);
}
}
}
@ -1006,7 +1006,7 @@ namespace
else
{
fmt::print("{} file exists but damaged, ignoring.\n", pid_file.string());
fs::remove(pid_file);
(void)fs::remove(pid_file);
}
}
else
@ -1014,7 +1014,7 @@ namespace
/// Create a directory for pid file.
/// It's created by "install" but we also support cases when ClickHouse is already installed different way.
fs::path pid_path = pid_file;
pid_path.remove_filename();
pid_path = pid_path.remove_filename();
fs::create_directories(pid_path);
/// All users are allowed to read pid file (for clickhouse status command).
fs::permissions(pid_path, fs::perms::owner_all | fs::perms::group_read | fs::perms::others_read, fs::perm_options::replace);
@ -1098,7 +1098,7 @@ namespace
else
{
fmt::print("{} file exists but damaged, ignoring.\n", pid_file.string());
fs::remove(pid_file);
(void)fs::remove(pid_file);
}
}
catch (const Exception & e)

64
programs/keeper-client/Commands.cpp
View File

@ -8,6 +8,11 @@
namespace DB
{
namespace ErrorCodes
{
extern const int KEEPER_EXCEPTION;
}
bool LSCommand::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const
{
String path;
@ -216,6 +221,8 @@ bool FindSuperNodes::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> &
node->args.push_back(threshold->as<ASTLiteral &>().value);
ParserToken{TokenType::Whitespace}.ignore(pos);
String path;
if (!parseKeeperPath(pos, expected, path))
path = ".";
@ -230,19 +237,23 @@ void FindSuperNodes::execute(const ASTKeeperQuery * query, KeeperClient * client
auto path = client->getAbsolutePath(query->args[1].safeGet<String>());
Coordination::Stat stat;
client->zookeeper->get(path, &stat);
if (!client->zookeeper->exists(path, &stat))
return; /// It is ok if node was deleted meanwhile
if (stat.numChildren >= static_cast<Int32>(threshold))
{
std::cout << static_cast<String>(path) << "\t" << stat.numChildren << "\n";
return;
}
auto children = client->zookeeper->getChildren(path);
Strings children;
auto status = client->zookeeper->tryGetChildren(path, children);
if (status == Coordination::Error::ZNONODE)
return; /// It is ok if node was deleted meanwhile
else if (status != Coordination::Error::ZOK)
throw DB::Exception(DB::ErrorCodes::KEEPER_EXCEPTION, "Error {} while getting children of {}", status, path.string());
std::sort(children.begin(), children.end());
auto next_query = *query;
for (const auto & child : children)
{
auto next_query = *query;
next_query.args[1] = DB::Field(path / child);
execute(&next_query, client);
}
@ -310,31 +321,34 @@ bool FindBigFamily::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> &
return true;
}
/// DFS the subtree and return the number of nodes in the subtree
static Int64 traverse(const fs::path & path, KeeperClient * client, std::vector<std::tuple<Int64, String>> & result)
{
Int64 nodes_in_subtree = 1;
Strings children;
auto status = client->zookeeper->tryGetChildren(path, children);
if (status == Coordination::Error::ZNONODE)
return 0;
else if (status != Coordination::Error::ZOK)
throw DB::Exception(DB::ErrorCodes::KEEPER_EXCEPTION, "Error {} while getting children of {}", status, path.string());
for (auto & child : children)
nodes_in_subtree += traverse(path / child, client, result);
result.emplace_back(nodes_in_subtree, path.string());
return nodes_in_subtree;
}
void FindBigFamily::execute(const ASTKeeperQuery * query, KeeperClient * client) const
{
auto path = client->getAbsolutePath(query->args[0].safeGet<String>());
auto n = query->args[1].safeGet<UInt64>();
std::vector<std::tuple<Int32, String>> result;
std::vector<std::tuple<Int64, String>> result;
std::queue<fs::path> queue;
queue.push(path);
while (!queue.empty())
{
auto next_path = queue.front();
queue.pop();
auto children = client->zookeeper->getChildren(next_path);
for (auto & child : children)
child = next_path / child;
auto response = client->zookeeper->get(children);
for (size_t i = 0; i < response.size(); ++i)
{
result.emplace_back(response[i].stat.numChildren, children[i]);
queue.push(children[i]);
}
}
traverse(path, client, result);
std::sort(result.begin(), result.end(), std::greater());
for (UInt64 i = 0; i < std::min(result.size(), static_cast<size_t>(n)); ++i)

5
programs/keeper-client/KeeperClient.cpp
View File

@ -86,7 +86,10 @@ std::vector<String> KeeperClient::getCompletions(const String & prefix) const
void KeeperClient::askConfirmation(const String & prompt, std::function<void()> && callback)
{
if (!ask_confirmation)
return callback();
{
callback();
return;
}
std::cout << prompt << " Continue?\n";
waiting_confirmation = true;

5
programs/keeper/Keeper.cpp
View File

@ -249,11 +249,6 @@ struct KeeperHTTPContext : public IHTTPContext
return context->getConfigRef().getUInt64("keeper_server.http_max_field_value_size", 128 * 1024);
}
uint64_t getMaxChunkSize() const override
{
return context->getConfigRef().getUInt64("keeper_server.http_max_chunk_size", 100_GiB);
}
Poco::Timespan getReceiveTimeout() const override
{
return {context->getConfigRef().getInt64("keeper_server.http_receive_timeout", DBMS_DEFAULT_RECEIVE_TIMEOUT_SEC), 0};

1
programs/library-bridge/LibraryBridgeHandlers.cpp
View File

@ -284,7 +284,6 @@ void ExternalDictionaryLibraryBridgeRequestHandler::handleRequest(HTTPServerRequ
else if (method == "extDict_loadIds")
{
LOG_DEBUG(log, "Getting diciontary ids for dictionary with id: {}", dictionary_id);
String ids_string;
std::vector<uint64_t> ids = parseIdsFromBinary(request.getStream());
auto library_handler = ExternalDictionaryLibraryHandlerFactory::instance().get(dictionary_id);

4
programs/library-bridge/SharedLibrary.cpp
View File

@ -14,7 +14,7 @@ namespace ErrorCodes
SharedLibrary::SharedLibrary(std::string_view path, int flags)
{
handle = dlopen(path.data(), flags);
handle = dlopen(path.data(), flags); // NOLINT
if (!handle)
throw Exception(ErrorCodes::CANNOT_DLOPEN, "Cannot dlopen: ({})", dlerror()); // NOLINT(concurrency-mt-unsafe) // MT-Safe on Linux, see man dlerror
@ -34,7 +34,7 @@ void * SharedLibrary::getImpl(std::string_view name, bool no_throw)
{
dlerror(); // NOLINT(concurrency-mt-unsafe) // MT-Safe on Linux, see man dlerror
auto * res = dlsym(handle, name.data());
auto * res = dlsym(handle, name.data()); // NOLINT
if (char * error = dlerror()) // NOLINT(concurrency-mt-unsafe) // MT-Safe on Linux, see man dlerror
{

8
programs/local/LocalServer.cpp
View File

@ -160,6 +160,14 @@ void LocalServer::initialize(Poco::Util::Application & self)
getOutdatedPartsLoadingThreadPool().setMaxTurboThreads(active_parts_loading_threads);
const size_t unexpected_parts_loading_threads = config().getUInt("max_unexpected_parts_loading_thread_pool_size", 32);
getUnexpectedPartsLoadingThreadPool().initialize(
unexpected_parts_loading_threads,
0, // We don't need any threads one all the parts will be loaded
unexpected_parts_loading_threads);
getUnexpectedPartsLoadingThreadPool().setMaxTurboThreads(active_parts_loading_threads);
const size_t cleanup_threads = config().getUInt("max_parts_cleaning_thread_pool_size", 128);
getPartsCleaningThreadPool().initialize(
cleanup_threads,

2
programs/main.cpp
View File

@ -119,7 +119,7 @@ std::pair<std::string_view, std::string_view> clickhouse_short_names[] =
};
enum class InstructionFail
enum class InstructionFail : uint8_t
{
NONE = 0,
SSE3 = 1,

7
programs/obfuscator/Obfuscator.cpp
View File

@ -674,8 +674,7 @@ private:
if (pos + length > end)
length = end - pos;
if (length > sizeof(CodePoint))
length = sizeof(CodePoint);
length = std::min(length, sizeof(CodePoint));
CodePoint res = 0;
memcpy(&res, pos, length);
@ -883,9 +882,7 @@ public:
throw Exception(ErrorCodes::LOGICAL_ERROR, "Logical error in markov model");
size_t offset_from_begin_of_string = pos - data;
size_t determinator_sliding_window_size = params.determinator_sliding_window_size;
if (determinator_sliding_window_size > determinator_size)
determinator_sliding_window_size = determinator_size;
size_t determinator_sliding_window_size = std::min(params.determinator_sliding_window_size, determinator_size);
size_t determinator_sliding_window_overflow = offset_from_begin_of_string + determinator_sliding_window_size > determinator_size
? offset_from_begin_of_string + determinator_sliding_window_size - determinator_size : 0;

3
programs/odbc-bridge/ODBCSource.cpp
View File

@ -119,8 +119,7 @@ void ODBCSource::insertValue(
time_t time = 0;
const DataTypeDateTime & datetime_type = assert_cast<const DataTypeDateTime &>(*data_type);
readDateTimeText(time, in, datetime_type.getTimeZone());
if (time < 0)
time = 0;
time = std::max<time_t>(time, 0);
column.insert(static_cast<UInt32>(time));
break;
}

2
programs/odbc-bridge/getIdentifierQuote.cpp
View File

@ -37,7 +37,7 @@ std::string getIdentifierQuote(nanodbc::ConnectionHolderPtr connection_holder)
IdentifierQuotingStyle getQuotingStyle(nanodbc::ConnectionHolderPtr connection)
{
auto identifier_quote = getIdentifierQuote(connection);
if (identifier_quote.length() == 0)
if (identifier_quote.empty())
return IdentifierQuotingStyle::None;
else if (identifier_quote[0] == '`')
return IdentifierQuotingStyle::Backticks;

10
programs/server/Server.cpp
View File

@ -885,6 +885,16 @@ try
server_settings.max_active_parts_loading_thread_pool_size
);
getUnexpectedPartsLoadingThreadPool().initialize(
server_settings.max_unexpected_parts_loading_thread_pool_size,
0, // We don't need any threads once all the parts will be loaded
server_settings.max_unexpected_parts_loading_thread_pool_size);
/// It could grow if we need to synchronously wait until all the data parts will be loaded.
getUnexpectedPartsLoadingThreadPool().setMaxTurboThreads(
server_settings.max_active_parts_loading_thread_pool_size
);
getPartsCleaningThreadPool().initialize(
server_settings.max_parts_cleaning_thread_pool_size,
0, // We don't need any threads one all the parts will be deleted

50
programs/server/dashboard.html
View File

@ -538,9 +538,57 @@ let params = default_params;
/// Palette generation for charts
function generatePalette(numColors) {
// oklch() does not work in firefox<=125 inside <canvas> element so we convert it back to rgb for now.
// Based on https://github.com/color-js/color.js/blob/main/src/spaces/oklch.js
const multiplyMatrices = (A, B) => {
return [
A[0]*B[0] + A[1]*B[1] + A[2]*B[2],
A[3]*B[0] + A[4]*B[1] + A[5]*B[2],
A[6]*B[0] + A[7]*B[1] + A[8]*B[2]
];
}
const oklch2oklab = ([l, c, h]) => [
l,
isNaN(h) ? 0 : c * Math.cos(h * Math.PI / 180),
isNaN(h) ? 0 : c * Math.sin(h * Math.PI / 180)
]
const srgbLinear2rgb = rgb => rgb.map(c =>
Math.abs(c) > 0.0031308 ?
(c < 0 ? -1 : 1) * (1.055 * (Math.abs(c) ** (1 / 2.4)) - 0.055) :
12.92 * c
)
const oklab2xyz = lab => {
const LMSg = multiplyMatrices([
1, 0.3963377773761749, 0.2158037573099136,
1, -0.1055613458156586, -0.0638541728258133,
1, -0.0894841775298119, -1.2914855480194092,
], lab)
const LMS = LMSg.map(val => val ** 3)
return multiplyMatrices([
1.2268798758459243, -0.5578149944602171, 0.2813910456659647,
-0.0405757452148008, 1.1122868032803170, -0.0717110580655164,
-0.0763729366746601, -0.4214933324022432, 1.5869240198367816
], LMS)
}
const xyz2rgbLinear = xyz => {
return multiplyMatrices([
3.2409699419045226, -1.537383177570094, -0.4986107602930034,
-0.9692436362808796, 1.8759675015077202, 0.04155505740717559,
0.05563007969699366, -0.20397695888897652, 1.0569715142428786
], xyz)
}
const oklch2rgb = lch => srgbLinear2rgb(xyz2rgbLinear(oklab2xyz(oklch2oklab(lch))))
palette = [];
for (let i = 0; i < numColors; i++) {
palette.push(`oklch(${theme != 'dark' ? 0.75 : 0.5}, 0.15, ${360 * i / numColors})`);
//palette.push(`oklch(${theme != 'dark' ? 0.75 : 0.5}, 0.15, ${360 * i / numColors})`);
let rgb = oklch2rgb([theme != 'dark' ? 0.75 : 0.5, 0.15, 360 * i / numColors]);
palette.push(`rgb(${rgb[0] * 255}, ${rgb[1] * 255}, ${rgb[2] * 255})`);
}
return palette;
}

2
programs/static-files-disk-uploader/static-files-disk-uploader.cpp
View File

@ -111,13 +111,11 @@ void processTableFiles(const fs::path & data_path, fs::path dst_path, bool test_
std::shared_ptr<WriteBuffer> directory_meta;
if (test_mode)
{
auto files_root = dst_path / prefix;
directory_meta = std::make_shared<WriteBufferFromHTTP>(HTTPConnectionGroupType::HTTP, Poco::URI(dst_path / directory_prefix / ".index"), Poco::Net::HTTPRequest::HTTP_PUT);
}
else
{
dst_path = fs::canonical(dst_path);
auto files_root = dst_path / prefix;
fs::create_directories(dst_path / directory_prefix);
directory_meta = std::make_shared<WriteBufferFromFile>(dst_path / directory_prefix / ".index");
}

2
src/Access/AccessBackup.cpp
View File

@ -93,8 +93,6 @@ namespace
break;
}
size_t id_endpos = line.find('\t');
String id_as_string = line.substr(0, id_endpos);
UUID id = parse<UUID>(line);
line.clear();

2
src/Access/AccessBackup.h
View File

@ -8,7 +8,7 @@
namespace DB
{
class AccessControl;
enum class AccessEntityType;
enum class AccessEntityType : uint8_t;
struct IAccessEntity;
using AccessEntityPtr = std::shared_ptr<const IAccessEntity>;
class AccessRightsElements;

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