Merge branch 'master' into fix/zero_copy_hardlinks_instead_copy

This commit is contained in:
Konstantin Morozov 2024-10-22 09:52:38 +00:00
commit c067001415
1520 changed files with 21067 additions and 25178 deletions

View File

@ -16,3 +16,6 @@
# Applied Black formatter for Python code
e6f5a3f98b21ba99cf274a9833797889e020a2b3
# Enabling clang-tidy readability-else-no-return rule
67c1e89d90ef576e62f8b1c68269742a3c6f9b1e

View File

@ -15,7 +15,7 @@ assignees: ''
**Use case**
> A clear and concise description of what is the intended usage scenario is.
> A clear and concise description of what the intended usage scenario is.
**Describe the solution you'd like**

View File

@ -33,9 +33,6 @@ jobs:
filter: tree:0
- name: Debug Info
uses: ./.github/actions/debug
- name: Cancel previous Sync PR workflow
run: |
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --cancel-previous-run
- name: Set pending Sync status
run: |
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --set-pending-status

View File

@ -545,7 +545,7 @@ endif()
if (CMAKE_BUILD_TYPE_UC STREQUAL "RELWITHDEBINFO"
AND NOT SANITIZE AND NOT SANITIZE_COVERAGE AND NOT ENABLE_FUZZING
AND OS_LINUX AND (ARCH_AMD64 OR ARCH_AARCH64))
AND OMIT_HEAVY_DEBUG_SYMBOLS AND OS_LINUX AND (ARCH_AMD64 OR ARCH_AARCH64))
set(CHECK_LARGE_OBJECT_SIZES_DEFAULT ON)
else ()
set(CHECK_LARGE_OBJECT_SIZES_DEFAULT OFF)

View File

@ -110,8 +110,7 @@ struct DecomposedFloat
{
if (!isNegative())
return rhs > 0 ? -1 : 1;
else
return rhs >= 0 ? -1 : 1;
return rhs >= 0 ? -1 : 1;
}
/// The case of the most negative integer
@ -128,8 +127,7 @@ struct DecomposedFloat
if (mantissa() == 0)
return 0;
else
return -1;
return -1;
}
}
@ -169,9 +167,8 @@ struct DecomposedFloat
/// Float has no fractional part means that the numbers are equal.
if (large_and_always_integer || (mantissa() & ((1ULL << (Traits::mantissa_bits - normalizedExponent())) - 1)) == 0)
return 0;
else
/// Float has fractional part means its abs value is larger.
return isNegative() ? -1 : 1;
/// Float has fractional part means its abs value is larger.
return isNegative() ? -1 : 1;
}

View File

@ -205,8 +205,7 @@ JSON::ElementType JSON::getType() const
Pos after_string = skipString();
if (after_string < ptr_end && *after_string == ':')
return TYPE_NAME_VALUE_PAIR;
else
return TYPE_STRING;
return TYPE_STRING;
}
default:
throw JSONException(std::string("JSON: unexpected char ") + *ptr_begin + ", expected one of '{[tfn-0123456789\"'");
@ -474,8 +473,7 @@ JSON::Pos JSON::searchField(const char * data, size_t size) const
if (it == end())
return nullptr;
else
return it->data();
return it->data();
}
@ -487,7 +485,7 @@ bool JSON::hasEscapes() const
if (*pos == '"')
return false;
else if (*pos == '\\')
if (*pos == '\\')
return true;
throw JSONException("JSON: unexpected end of data.");
}
@ -503,7 +501,7 @@ bool JSON::hasSpecialChars() const
if (*pos == '"')
return false;
else if (pos < ptr_end)
if (pos < ptr_end)
return true;
throw JSONException("JSON: unexpected end of data.");
}
@ -682,10 +680,9 @@ double JSON::toDouble() const
if (type == TYPE_NUMBER)
return getDouble();
else if (type == TYPE_STRING)
if (type == TYPE_STRING)
return JSON(ptr_begin + 1, ptr_end, level + 1).getDouble();
else
throw JSONException("JSON: cannot convert value to double.");
throw JSONException("JSON: cannot convert value to double.");
}
Int64 JSON::toInt() const
@ -694,10 +691,9 @@ Int64 JSON::toInt() const
if (type == TYPE_NUMBER)
return getInt();
else if (type == TYPE_STRING)
if (type == TYPE_STRING)
return JSON(ptr_begin + 1, ptr_end, level + 1).getInt();
else
throw JSONException("JSON: cannot convert value to signed integer.");
throw JSONException("JSON: cannot convert value to signed integer.");
}
UInt64 JSON::toUInt() const
@ -706,10 +702,9 @@ UInt64 JSON::toUInt() const
if (type == TYPE_NUMBER)
return getUInt();
else if (type == TYPE_STRING)
if (type == TYPE_STRING)
return JSON(ptr_begin + 1, ptr_end, level + 1).getUInt();
else
throw JSONException("JSON: cannot convert value to unsigned integer.");
throw JSONException("JSON: cannot convert value to unsigned integer.");
}
std::string JSON::toString() const
@ -718,11 +713,9 @@ std::string JSON::toString() const
if (type == TYPE_STRING)
return getString();
else
{
Pos pos = skipElement();
return std::string(ptr_begin, pos - ptr_begin);
}
Pos pos = skipElement();
return std::string(ptr_begin, pos - ptr_begin);
}

View File

@ -203,9 +203,7 @@ T JSON::getWithDefault(const std::string & key, const T & default_) const
if (key_json.isType<T>())
return key_json.get<T>();
else
return default_;
}
else
return default_;
}
return default_;
}

View File

@ -151,19 +151,19 @@ inline bool memequalWide(const char * p1, const char * p2, size_t size)
return unalignedLoad<uint64_t>(p1) == unalignedLoad<uint64_t>(p2)
&& unalignedLoad<uint64_t>(p1 + size - 8) == unalignedLoad<uint64_t>(p2 + size - 8);
}
else if (size >= 4)
if (size >= 4)
{
/// Chunks of 4..7 bytes.
return unalignedLoad<uint32_t>(p1) == unalignedLoad<uint32_t>(p2)
&& unalignedLoad<uint32_t>(p1 + size - 4) == unalignedLoad<uint32_t>(p2 + size - 4);
}
else if (size >= 2)
if (size >= 2)
{
/// Chunks of 2..3 bytes.
return unalignedLoad<uint16_t>(p1) == unalignedLoad<uint16_t>(p2)
&& unalignedLoad<uint16_t>(p1 + size - 2) == unalignedLoad<uint16_t>(p2 + size - 2);
}
else if (size >= 1)
if (size >= 1)
{
/// A single byte.
return *p1 == *p2;

View File

@ -53,10 +53,9 @@ void argsToConfig(const Poco::Util::Application::ArgVec & argv,
key = arg.substr(key_start);
continue;
}
else
{
key = "";
}
key = "";
if (key_start == std::string::npos)
continue;

View File

@ -330,9 +330,8 @@ inline const char * find_first_symbols_dispatch(const char * begin, const char *
#if defined(__SSE4_2__)
if (sizeof...(symbols) >= 5)
return find_first_symbols_sse42<positive, return_mode, sizeof...(symbols), symbols...>(begin, end);
else
#endif
return find_first_symbols_sse2<positive, return_mode, symbols...>(begin, end);
return find_first_symbols_sse2<positive, return_mode, symbols...>(begin, end);
}
template <bool positive, ReturnMode return_mode>
@ -341,9 +340,8 @@ inline const char * find_first_symbols_dispatch(const std::string_view haystack,
#if defined(__SSE4_2__)
if (symbols.str.size() >= 5)
return find_first_symbols_sse42<positive, return_mode>(haystack.begin(), haystack.end(), symbols);
else
#endif
return find_first_symbols_sse2<positive, return_mode>(haystack.begin(), haystack.end(), symbols.str.data(), symbols.str.size());
return find_first_symbols_sse2<positive, return_mode>(haystack.begin(), haystack.end(), symbols.str.data(), symbols.str.size());
}
}

View File

@ -33,8 +33,7 @@ std::optional<uint64_t> getCgroupsV2MemoryLimit()
uint64_t value;
if (setting_file >> value)
return {value};
else
return {}; /// e.g. the cgroups default "max"
return {}; /// e.g. the cgroups default "max"
}
current_cgroup = current_cgroup.parent_path();
}

View File

@ -11,6 +11,9 @@ if (GLIBC_COMPATIBILITY)
if (ARCH_AARCH64)
list (APPEND glibc_compatibility_sources musl/aarch64/syscall.s musl/aarch64/longjmp.s)
set (musl_arch_include_dir musl/aarch64)
# Disable getauxval in aarch64. ARM glibc minimum requirement for the project is 2.18 and getauxval is present
# in 2.16. Having a custom one introduces issues with sanitizers
list (REMOVE_ITEM glibc_compatibility_sources musl/getauxval.c)
elseif (ARCH_AMD64)
list (APPEND glibc_compatibility_sources musl/x86_64/syscall.s musl/x86_64/longjmp.s)
set (musl_arch_include_dir musl/x86_64)
@ -18,7 +21,7 @@ if (GLIBC_COMPATIBILITY)
message (FATAL_ERROR "glibc_compatibility can only be used on x86_64 or aarch64.")
endif ()
if (SANITIZE STREQUAL thread)
if (SANITIZE STREQUAL thread AND ARCH_AMD64)
# Disable TSAN instrumentation that conflicts with re-exec due to high ASLR entropy using getauxval
# See longer comment in __auxv_init_procfs
# In the case of tsan we need to make sure getauxval is not instrumented as that would introduce tsan

View File

@ -11,6 +11,38 @@ option (ARCH_NATIVE "Add -march=native compiler flag. This makes your binaries n
if (ARCH_NATIVE)
set (COMPILER_FLAGS "${COMPILER_FLAGS} -march=native")
# Populate the ENABLE_ option flags. This is required for the build of some third-party dependencies, specifically snappy, which
# (somewhat weirdly) expects the relative SNAPPY_HAVE_ preprocessor variables to be populated, in addition to the microarchitecture
# feature flags being enabled in the compiler. This fixes the ARCH_NATIVE flag by automatically populating the ENABLE_ option flags
# according to the current CPU's capabilities, detected using clang.
if (ARCH_AMD64)
execute_process(
COMMAND sh -c "clang -E - -march=native -###"
INPUT_FILE /dev/null
OUTPUT_QUIET
ERROR_VARIABLE TEST_FEATURE_RESULT)
macro(TEST_AMD64_FEATURE TEST_FEATURE_RESULT feat flag)
if (${TEST_FEATURE_RESULT} MATCHES "\"\\+${feat}\"")
set(${flag} ON)
else ()
set(${flag} OFF)
endif ()
endmacro()
TEST_AMD64_FEATURE (${TEST_FEATURE_RESULT} ssse3 ENABLE_SSSE3)
TEST_AMD64_FEATURE (${TEST_FEATURE_RESULT} sse4.1 ENABLE_SSE41)
TEST_AMD64_FEATURE (${TEST_FEATURE_RESULT} sse4.2 ENABLE_SSE42)
TEST_AMD64_FEATURE (${TEST_FEATURE_RESULT} vpclmulqdq ENABLE_PCLMULQDQ)
TEST_AMD64_FEATURE (${TEST_FEATURE_RESULT} popcnt ENABLE_POPCNT)
TEST_AMD64_FEATURE (${TEST_FEATURE_RESULT} avx ENABLE_AVX)
TEST_AMD64_FEATURE (${TEST_FEATURE_RESULT} avx2 ENABLE_AVX2)
TEST_AMD64_FEATURE (${TEST_FEATURE_RESULT} avx512f ENABLE_AVX512)
TEST_AMD64_FEATURE (${TEST_FEATURE_RESULT} avx512vbmi ENABLE_AVX512_VBMI)
TEST_AMD64_FEATURE (${TEST_FEATURE_RESULT} bmi ENABLE_BMI)
TEST_AMD64_FEATURE (${TEST_FEATURE_RESULT} bmi2 ENABLE_BMI2)
endif ()
elseif (ARCH_AARCH64)
# ARM publishes almost every year a new revision of it's ISA [1]. Each version comes with new mandatory and optional features from
# which CPU vendors can pick and choose. This creates a lot of variability ... We provide two build "profiles", one for maximum

View File

@ -1,4 +1,21 @@
set (CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -D_LIBCPP_DEBUG=0") # More checks in debug build.
if (CMAKE_BUILD_TYPE_UC STREQUAL "DEBUG")
# Enable libcxx debug mode: https://releases.llvm.org/15.0.0/projects/libcxx/docs/DesignDocs/DebugMode.html
# The docs say the debug mode violates complexity guarantees, so do this only for Debug builds.
# set (CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -D_LIBCPP_ENABLE_DEBUG_MODE=1")
# ^^ Crashes the database upon startup, needs investigation.
# Besides that, the implementation looks like a poor man's MSAN specific to libcxx. Since CI tests MSAN
# anyways, we can keep the debug mode disabled.
# Libcxx also provides extra assertions:
# --> https://releases.llvm.org/15.0.0/projects/libcxx/docs/UsingLibcxx.html#assertions-mode
# These look orthogonal to the debug mode but the debug mode enables them implicitly:
# --> https://github.com/llvm/llvm-project/blob/release/15.x/libcxx/include/__assert#L29
# They are cheap and straightforward, so enable them in debug builds:
set (CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -D_LIBCPP_ENABLE_ASSERTIONS=1")
# TODO Once we upgrade to LLVM 18+, reconsider all of the above as they introduced "hardening modes":
# https://libcxx.llvm.org/Hardening.html
endif ()
add_subdirectory(contrib/libcxxabi-cmake)
add_subdirectory(contrib/libcxx-cmake)

View File

@ -1,6 +1,9 @@
set(ABSL_ROOT_DIR "${ClickHouse_SOURCE_DIR}/contrib/abseil-cpp")
set(ABSL_COMMON_INCLUDE_DIRS "${ABSL_ROOT_DIR}")
# To avoid errors "'X' does not refer to a value" while using `offsetof` function.
set(CMAKE_CXX_STANDARD 17)
# This is a minimized version of the function definition in CMake/AbseilHelpers.cmake
#

View File

@ -5,6 +5,9 @@ if(NOT ENABLE_PROTOBUF)
return()
endif()
# To avoid errors "'X' does not refer to a value" while using `offsetof` function.
set(CMAKE_CXX_STANDARD 17)
set(Protobuf_INCLUDE_DIR "${ClickHouse_SOURCE_DIR}/contrib/google-protobuf/src")
if(OS_FREEBSD AND SANITIZE STREQUAL "address")
# ../contrib/protobuf/src/google/protobuf/arena_impl.h:45:10: fatal error: 'sanitizer/asan_interface.h' file not found

View File

@ -6,6 +6,8 @@ if(NOT ENABLE_GRPC)
return()
endif()
set(CMAKE_CXX_STANDARD 17)
set(_gRPC_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/grpc")
set(_gRPC_BINARY_DIR "${ClickHouse_BINARY_DIR}/contrib/grpc")

View File

@ -22,7 +22,7 @@
# limitations under the License.
# We want to use C++23, but GRPC is not ready
set (CMAKE_CXX_STANDARD 20)
set (CMAKE_CXX_STANDARD 17)
set(_gRPC_ZLIB_INCLUDE_DIR "")
set(_gRPC_ZLIB_LIBRARIES ch_contrib::zlib)

2
contrib/libhdfs3 vendored

@ -1 +1 @@
Subproject commit 0d04201c45359f0d0701fb1e8297d25eff7cfecf
Subproject commit de6f1e0750aa3670a603cbfeddf5df3de1097687

2
contrib/usearch vendored

@ -1 +1 @@
Subproject commit d1d33eac94acd3b628e0b446c927ec3295ef63c7
Subproject commit 1706420acafbd83d852c512dcf343af0a4059e48

View File

@ -42,13 +42,12 @@ ENV TZ=Etc/UTC
RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
ENV DOCKER_CHANNEL stable
# Unpin the docker version after the release 24.0.3 is released
# https://github.com/moby/moby/issues/45770#issuecomment-1618255130
RUN curl -fsSL https://download.docker.com/linux/ubuntu/gpg | apt-key add - \
&& add-apt-repository "deb https://download.docker.com/linux/ubuntu $(lsb_release -c -s) ${DOCKER_CHANNEL}" \
&& apt-get update \
&& env DEBIAN_FRONTEND=noninteractive apt-get install --yes \
docker-ce='5:23.*' docker-compose-plugin='2.29.*' \
docker-ce="5:27.0.3*" \
docker-compose-plugin='2.29.*' \
&& rm -rf \
/var/lib/apt/lists/* \
/var/cache/debconf \

View File

@ -0,0 +1,5 @@
#!/bin/bash
set -e
# workaround for https://github.com/bitnami/containers/issues/73310
touch /tmp/.openldap-initialized

View File

@ -1,4 +1,4 @@
aiohttp==3.9.5
aiohttp==3.10.2
aiosignal==1.3.1
astroid==3.1.0
async-timeout==4.0.3
@ -6,12 +6,12 @@ attrs==23.2.0
black==24.4.2
boto3==1.34.131
botocore==1.34.131
certifi==2024.6.2
certifi==2024.07.04
cffi==1.16.0
charset-normalizer==3.3.2
click==8.1.7
codespell==2.2.1
cryptography==42.0.8
cryptography==43.0.1
Deprecated==1.2.14
dill==0.3.8
flake8==4.0.1
@ -19,7 +19,6 @@ frozenlist==1.4.1
idna==3.7
isort==5.13.2
jmespath==1.0.1
jwt==1.3.1
mccabe==0.6.1
multidict==6.0.5
mypy==1.8.0
@ -27,13 +26,12 @@ mypy-extensions==1.0.0
packaging==24.1
pathspec==0.9.0
pip==24.1.1
pipdeptree==2.23.0
platformdirs==4.2.2
pycodestyle==2.8.0
pycparser==2.22
pyflakes==2.4.0
PyGithub==2.3.0
PyJWT==2.8.0
PyJWT==2.9.0
pylint==3.1.0
PyNaCl==1.5.0
python-dateutil==2.9.0.post0
@ -42,7 +40,7 @@ PyYAML==6.0.1
rapidfuzz==3.9.3
requests==2.32.3
s3transfer==0.10.1
setuptools==59.6.0
setuptools==70.0.0
six==1.16.0
thefuzz==0.22.1
tomli==2.0.1
@ -52,7 +50,7 @@ types-requests==2.32.0.20240622
typing_extensions==4.12.2
unidiff==0.7.5
urllib3==2.2.2
wheel==0.37.1
wheel==0.38.1
wrapt==1.16.0
yamllint==1.26.3
yarl==1.9.4

View File

@ -196,7 +196,6 @@ When writing docs, you can use prepared templates. Copy the code of a template a
Templates:
- [Function](_description_templates/template-function.md)
- [Setting](_description_templates/template-setting.md)
- [Server Setting](_description_templates/template-server-setting.md)
- [Database or Table engine](_description_templates/template-engine.md)
- [System table](_description_templates/template-system-table.md)

View File

@ -1,27 +0,0 @@
## setting_name {#setting_name}
Description.
For the switch setting, use the typical phrase: “Enables or disables something ...”.
Possible values:
*For switcher setting:*
- 0 — Disabled.
- 1 — Enabled.
*For another setting (typical phrases):*
- Positive integer.
- 0 — Disabled or unlimited or something else.
Default value: `value`.
**Additional Info** (Optional)
The name of an additional section can be any, for example, **Usage**.
**See Also** (Optional)
- [link](#)

View File

@ -1,11 +0,0 @@
sudo apt-get install -y apt-transport-https ca-certificates dirmngr
sudo apt-key adv --keyserver hkp://keyserver.ubuntu.com:80 --recv 8919F6BD2B48D754
echo "deb https://packages.clickhouse.com/deb stable main" | sudo tee \
/etc/apt/sources.list.d/clickhouse.list
sudo apt-get update
sudo apt-get install -y clickhouse-server clickhouse-client
sudo service clickhouse-server start
clickhouse-client # or "clickhouse-client --password" if you've set up a password.

View File

@ -1,6 +0,0 @@
sudo yum install -y yum-utils
sudo yum-config-manager --add-repo https://packages.clickhouse.com/rpm/clickhouse.repo
sudo yum install -y clickhouse-server clickhouse-client
sudo /etc/init.d/clickhouse-server start
clickhouse-client # or "clickhouse-client --password" if you set up a password.

View File

@ -1,32 +0,0 @@
LATEST_VERSION=$(curl -s https://packages.clickhouse.com/tgz/stable/ | \
grep -Eo '[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+' | sort -V -r | head -n 1)
export LATEST_VERSION
case $(uname -m) in
x86_64) ARCH=amd64 ;;
aarch64) ARCH=arm64 ;;
*) echo "Unknown architecture $(uname -m)"; exit 1 ;;
esac
for PKG in clickhouse-common-static clickhouse-common-static-dbg clickhouse-server clickhouse-client
do
curl -fO "https://packages.clickhouse.com/tgz/stable/$PKG-$LATEST_VERSION-${ARCH}.tgz" \
|| curl -fO "https://packages.clickhouse.com/tgz/stable/$PKG-$LATEST_VERSION.tgz"
done
tar -xzvf "clickhouse-common-static-$LATEST_VERSION-${ARCH}.tgz" \
|| tar -xzvf "clickhouse-common-static-$LATEST_VERSION.tgz"
sudo "clickhouse-common-static-$LATEST_VERSION/install/doinst.sh"
tar -xzvf "clickhouse-common-static-dbg-$LATEST_VERSION-${ARCH}.tgz" \
|| tar -xzvf "clickhouse-common-static-dbg-$LATEST_VERSION.tgz"
sudo "clickhouse-common-static-dbg-$LATEST_VERSION/install/doinst.sh"
tar -xzvf "clickhouse-server-$LATEST_VERSION-${ARCH}.tgz" \
|| tar -xzvf "clickhouse-server-$LATEST_VERSION.tgz"
sudo "clickhouse-server-$LATEST_VERSION/install/doinst.sh" configure
sudo /etc/init.d/clickhouse-server start
tar -xzvf "clickhouse-client-$LATEST_VERSION-${ARCH}.tgz" \
|| tar -xzvf "clickhouse-client-$LATEST_VERSION.tgz"
sudo "clickhouse-client-$LATEST_VERSION/install/doinst.sh"

View File

@ -14,7 +14,12 @@ then
HAS_SSE42=$(grep sse4_2 /proc/cpuinfo)
if [ "${HAS_SSE42}" ]
then
DIR="amd64"
if ldd --version 2>&1 | grep -q musl
then
DIR="amd64musl"
else
DIR="amd64"
fi
else
DIR="amd64compat"
fi

View File

@ -0,0 +1,49 @@
---
sidebar_position: 1
sidebar_label: 2024
---
# 2024 Changelog
### ClickHouse release v24.3.12.75-lts (7cb5dff8019) FIXME as compared to v24.3.11.7-lts (28795d0a47e)
#### Improvement
* Backported in [#69607](https://github.com/ClickHouse/ClickHouse/issues/69607): Improved memory accounting for cgroups v2 to exclude the amount occupied by the page cache. [#65470](https://github.com/ClickHouse/ClickHouse/pull/65470) ([Nikita Taranov](https://github.com/nickitat)).
#### Bug Fix (user-visible misbehavior in an official stable release)
* Backported in [#69785](https://github.com/ClickHouse/ClickHouse/issues/69785): Fix attaching table when pg dbname contains "-" in MaterializedPostgreSQL. [#62730](https://github.com/ClickHouse/ClickHouse/pull/62730) ([takakawa](https://github.com/takakawa)).
* Backported in [#69461](https://github.com/ClickHouse/ClickHouse/issues/69461): Fix expiration in `RoleCache`. [#67748](https://github.com/ClickHouse/ClickHouse/pull/67748) ([Vitaly Baranov](https://github.com/vitlibar)).
* Backported in [#68217](https://github.com/ClickHouse/ClickHouse/issues/68217): Fixed a NULL pointer dereference, triggered by a specially crafted query, that crashed the server via hopEnd, hopStart, tumbleEnd, and tumbleStart. [#68098](https://github.com/ClickHouse/ClickHouse/pull/68098) ([Salvatore Mesoraca](https://github.com/aiven-sal)).
* Backported in [#69437](https://github.com/ClickHouse/ClickHouse/issues/69437): After unexpected restart, fail to start replication of ReplicatedMergeTree due to abnormal handling of covered-by-broken part. [#68584](https://github.com/ClickHouse/ClickHouse/pull/68584) ([baolin](https://github.com/baolinhuang)).
* Backported in [#69827](https://github.com/ClickHouse/ClickHouse/issues/69827): Make `ColumnsDescription::toString` format each column using the same `IAST::FormatState object`. This results in uniform columns metadata being written to disk and ZooKeeper. [#68733](https://github.com/ClickHouse/ClickHouse/pull/68733) ([Miсhael Stetsyuk](https://github.com/mstetsyuk)).
* Backported in [#69294](https://github.com/ClickHouse/ClickHouse/issues/69294): Fix merging of aggregated data for grouping sets. [#68744](https://github.com/ClickHouse/ClickHouse/pull/68744) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Backported in [#70470](https://github.com/ClickHouse/ClickHouse/issues/70470): Fix inf loop after `restore replica` in the replicated merge tree with zero copy. [#69293](https://github.com/ClickHouse/ClickHouse/pull/69293) ([MikhailBurdukov](https://github.com/MikhailBurdukov)).
* Backported in [#69456](https://github.com/ClickHouse/ClickHouse/issues/69456): Fix undefined behavior when all connection attempts fail getting a connection for insertions. [#69390](https://github.com/ClickHouse/ClickHouse/pull/69390) ([Pablo Marcos](https://github.com/pamarcos)).
* Backported in [#69497](https://github.com/ClickHouse/ClickHouse/issues/69497): Fixed a `LOGICAL_ERROR` with function `sqidDecode` ([#69450](https://github.com/ClickHouse/ClickHouse/issues/69450)). [#69451](https://github.com/ClickHouse/ClickHouse/pull/69451) ([Robert Schulze](https://github.com/rschu1ze)).
* Backported in [#69724](https://github.com/ClickHouse/ClickHouse/issues/69724): Keep original order of conditions during move to prewhere. Previously the order could change and it could lead to failing queries when the order is important. [#69560](https://github.com/ClickHouse/ClickHouse/pull/69560) ([Pavel Kruglov](https://github.com/Avogar)).
* Backported in [#69668](https://github.com/ClickHouse/ClickHouse/issues/69668): Fix Keeper multi-request preprocessing after ZNOAUTH error. [#69627](https://github.com/ClickHouse/ClickHouse/pull/69627) ([Antonio Andelic](https://github.com/antonio2368)).
* Backported in [#69792](https://github.com/ClickHouse/ClickHouse/issues/69792): Make getHyperrectangleForRowGroup not throw an exception when the data type in parquet file is not convertable into the requested data type. Solved the user's problem when the Parquet file had Decimal64 data type and the column data type was DateTime. [#69745](https://github.com/ClickHouse/ClickHouse/pull/69745) ([Miсhael Stetsyuk](https://github.com/mstetsyuk)).
* Backported in [#70089](https://github.com/ClickHouse/ClickHouse/issues/70089): Now SQL security will work with parameterized views correctly. [#69984](https://github.com/ClickHouse/ClickHouse/pull/69984) ([pufit](https://github.com/pufit)).
* Backported in [#70077](https://github.com/ClickHouse/ClickHouse/issues/70077): Closes [#69752](https://github.com/ClickHouse/ClickHouse/issues/69752). [#69985](https://github.com/ClickHouse/ClickHouse/pull/69985) ([pufit](https://github.com/pufit)).
* Backported in [#70162](https://github.com/ClickHouse/ClickHouse/issues/70162): Fix wrong LOGICAL_ERROR when replacing literals in ranges. [#70122](https://github.com/ClickHouse/ClickHouse/pull/70122) ([Pablo Marcos](https://github.com/pamarcos)).
* Backported in [#70232](https://github.com/ClickHouse/ClickHouse/issues/70232): Check for Nullable(Nothing) type during ALTER TABLE MODIFY COLUMN/QUERY to prevent tables with such data type. [#70123](https://github.com/ClickHouse/ClickHouse/pull/70123) ([Pavel Kruglov](https://github.com/Avogar)).
* Backported in [#70179](https://github.com/ClickHouse/ClickHouse/issues/70179): Fix data race in ColumnObject/ColumnTuple decompress method that could lead to heap use after free. [#70137](https://github.com/ClickHouse/ClickHouse/pull/70137) ([Pavel Kruglov](https://github.com/Avogar)).
* Backported in [#70241](https://github.com/ClickHouse/ClickHouse/issues/70241): Fix the password being displayed in `system.query_log` for users with bcrypt password authentication method. [#70148](https://github.com/ClickHouse/ClickHouse/pull/70148) ([Nikolay Degterinsky](https://github.com/evillique)).
* Backported in [#70397](https://github.com/ClickHouse/ClickHouse/issues/70397): Fix crash when using WITH FILL incorrectly. [#70338](https://github.com/ClickHouse/ClickHouse/pull/70338) ([Raúl Marín](https://github.com/Algunenano)).
#### NO CL CATEGORY
* Backported in [#69526](https://github.com/ClickHouse/ClickHouse/issues/69526):. [#67029](https://github.com/ClickHouse/ClickHouse/pull/67029) ([Alexander Tokmakov](https://github.com/tavplubix)).
#### NOT FOR CHANGELOG / INSIGNIFICANT
* Backported in [#69506](https://github.com/ClickHouse/ClickHouse/issues/69506): Better handling of errors from azure storage. [#62306](https://github.com/ClickHouse/ClickHouse/pull/62306) ([Anton Popov](https://github.com/CurtizJ)).
* Backported in [#69955](https://github.com/ClickHouse/ClickHouse/issues/69955): Output an operation error for ZK Multi request failed operation into log. [#68127](https://github.com/ClickHouse/ClickHouse/pull/68127) ([Aleksei Filatov](https://github.com/aalexfvk)).
* Backported in [#69485](https://github.com/ClickHouse/ClickHouse/issues/69485): Fix test_role & test_keeper_s3_snapshot integration tests. [#69013](https://github.com/ClickHouse/ClickHouse/pull/69013) ([Shankar](https://github.com/shiyer7474)).
* Backported in [#70028](https://github.com/ClickHouse/ClickHouse/issues/70028): Remove stale moving parts without zookeeper. [#69075](https://github.com/ClickHouse/ClickHouse/pull/69075) ([Kirill](https://github.com/kirillgarbar)).
* Backported in [#69421](https://github.com/ClickHouse/ClickHouse/issues/69421): Fix: Not-ready Set with parallel replicas. [#69264](https://github.com/ClickHouse/ClickHouse/pull/69264) ([Igor Nikonov](https://github.com/devcrafter)).
* Backported in [#69747](https://github.com/ClickHouse/ClickHouse/issues/69747): Add function `kill_ci_runner`. Kill runner when pre-pull failed. [#69557](https://github.com/ClickHouse/ClickHouse/pull/69557) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Backported in [#69636](https://github.com/ClickHouse/ClickHouse/issues/69636): Add more contexts to the debug action and use it broadly. [#69599](https://github.com/ClickHouse/ClickHouse/pull/69599) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* The test is flaky and the feature experimental. [#70269](https://github.com/ClickHouse/ClickHouse/pull/70269) ([Raúl Marín](https://github.com/Algunenano)).
* Fix test distributed inter server secret in 24.3. [#70325](https://github.com/ClickHouse/ClickHouse/pull/70325) ([Raúl Marín](https://github.com/Algunenano)).

View File

@ -0,0 +1,73 @@
---
sidebar_position: 1
sidebar_label: 2024
---
# 2024 Changelog
### ClickHouse release v24.8.5.115-lts (8c4cb00a384) FIXME as compared to v24.8.4.13-lts (53195bc189b)
#### Improvement
* Backported in [#70046](https://github.com/ClickHouse/ClickHouse/issues/70046): Add new column readonly_duration to the system.replicas table. Needed to be able to distinguish actual readonly replicas from sentinel ones in alerts. [#69871](https://github.com/ClickHouse/ClickHouse/pull/69871) ([Miсhael Stetsyuk](https://github.com/mstetsyuk)).
#### Bug Fix (user-visible misbehavior in an official stable release)
* Backported in [#69786](https://github.com/ClickHouse/ClickHouse/issues/69786): Fix attaching table when pg dbname contains "-" in MaterializedPostgreSQL. [#62730](https://github.com/ClickHouse/ClickHouse/pull/62730) ([takakawa](https://github.com/takakawa)).
* Backported in [#70318](https://github.com/ClickHouse/ClickHouse/issues/70318): Fixed error on generated columns in MaterializedPostgreSQL when adnum ordering is broken [#63161](https://github.com/ClickHouse/ClickHouse/issues/63161). Fixed error on id column with nextval expression as default MaterializedPostgreSQL when there are generated columns in table. Fixed error on dropping publication with symbols except [a-z1-9-]. [#67664](https://github.com/ClickHouse/ClickHouse/pull/67664) ([Kruglov Kirill](https://github.com/1on)).
* Backported in [#69467](https://github.com/ClickHouse/ClickHouse/issues/69467): Fix expiration in `RoleCache`. [#67748](https://github.com/ClickHouse/ClickHouse/pull/67748) ([Vitaly Baranov](https://github.com/vitlibar)).
* Backported in [#69735](https://github.com/ClickHouse/ClickHouse/issues/69735): Fix crash in `lag`/`lead` which is introduced in [#67091](https://github.com/ClickHouse/ClickHouse/issues/67091). [#68262](https://github.com/ClickHouse/ClickHouse/pull/68262) ([lgbo](https://github.com/lgbo-ustc)).
* Backported in [#69444](https://github.com/ClickHouse/ClickHouse/issues/69444): After unexpected restart, fail to start replication of ReplicatedMergeTree due to abnormal handling of covered-by-broken part. [#68584](https://github.com/ClickHouse/ClickHouse/pull/68584) ([baolin](https://github.com/baolinhuang)).
* Backported in [#69810](https://github.com/ClickHouse/ClickHouse/issues/69810): Make `ColumnsDescription::toString` format each column using the same `IAST::FormatState object`. This results in uniform columns metadata being written to disk and ZooKeeper. [#68733](https://github.com/ClickHouse/ClickHouse/pull/68733) ([Miсhael Stetsyuk](https://github.com/mstetsyuk)).
* Backported in [#69757](https://github.com/ClickHouse/ClickHouse/issues/69757): Fix incorrect results of Fix uniq and GROUP BY for JSON/Dynamic types. [#69203](https://github.com/ClickHouse/ClickHouse/pull/69203) ([Pavel Kruglov](https://github.com/Avogar)).
* Backported in [#70195](https://github.com/ClickHouse/ClickHouse/issues/70195): Fix insertion of incomplete type into Dynamic during deserialization. It could lead to `Parameter out of bound` errors. [#69291](https://github.com/ClickHouse/ClickHouse/pull/69291) ([Pavel Kruglov](https://github.com/Avogar)).
* Backported in [#69398](https://github.com/ClickHouse/ClickHouse/issues/69398): Mark Dynamic type as not safe primary key type to avoid issues with Fields. [#69311](https://github.com/ClickHouse/ClickHouse/pull/69311) ([Pavel Kruglov](https://github.com/Avogar)).
* Backported in [#69704](https://github.com/ClickHouse/ClickHouse/issues/69704): Improve restoring of access entities' dependencies. [#69346](https://github.com/ClickHouse/ClickHouse/pull/69346) ([Vitaly Baranov](https://github.com/vitlibar)).
* Backported in [#69459](https://github.com/ClickHouse/ClickHouse/issues/69459): Fix undefined behavior when all connection attempts fail getting a connection for insertions. [#69390](https://github.com/ClickHouse/ClickHouse/pull/69390) ([Pablo Marcos](https://github.com/pamarcos)).
* Backported in [#69503](https://github.com/ClickHouse/ClickHouse/issues/69503): Fixed a `LOGICAL_ERROR` with function `sqidDecode` ([#69450](https://github.com/ClickHouse/ClickHouse/issues/69450)). [#69451](https://github.com/ClickHouse/ClickHouse/pull/69451) ([Robert Schulze](https://github.com/rschu1ze)).
* Backported in [#69480](https://github.com/ClickHouse/ClickHouse/issues/69480): Quick fix for s3queue problem on 24.6 or create query with database replicated. [#69454](https://github.com/ClickHouse/ClickHouse/pull/69454) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Backported in [#69535](https://github.com/ClickHouse/ClickHouse/issues/69535): Fixed case when memory consumption was too high because of the squashing in `INSERT INTO ... SELECT` or `CREATE TABLE AS SELECT` queries. [#69469](https://github.com/ClickHouse/ClickHouse/pull/69469) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
* Backported in [#69696](https://github.com/ClickHouse/ClickHouse/issues/69696): Keep original order of conditions during move to prewhere. Previously the order could change and it could lead to failing queries when the order is important. [#69560](https://github.com/ClickHouse/ClickHouse/pull/69560) ([Pavel Kruglov](https://github.com/Avogar)).
* Backported in [#70439](https://github.com/ClickHouse/ClickHouse/issues/70439): Fix vrash during insertion into FixedString column in PostgreSQL engine. [#69584](https://github.com/ClickHouse/ClickHouse/pull/69584) ([Pavel Kruglov](https://github.com/Avogar)).
* Backported in [#69666](https://github.com/ClickHouse/ClickHouse/issues/69666): Fix Keeper multi-request preprocessing after ZNOAUTH error. [#69627](https://github.com/ClickHouse/ClickHouse/pull/69627) ([Antonio Andelic](https://github.com/antonio2368)).
* Backported in [#70191](https://github.com/ClickHouse/ClickHouse/issues/70191): Fix crash when executing `create view t as (with recursive 42 as ttt select ttt);`. [#69676](https://github.com/ClickHouse/ClickHouse/pull/69676) ([Han Fei](https://github.com/hanfei1991)).
* Backported in [#69798](https://github.com/ClickHouse/ClickHouse/issues/69798): Make getHyperrectangleForRowGroup not throw an exception when the data type in parquet file is not convertable into the requested data type. Solved the user's problem when the Parquet file had Decimal64 data type and the column data type was DateTime. [#69745](https://github.com/ClickHouse/ClickHouse/pull/69745) ([Miсhael Stetsyuk](https://github.com/mstetsyuk)).
* Backported in [#70410](https://github.com/ClickHouse/ClickHouse/issues/70410): Fixed `maxMapState` throwing 'Bad get' if value type is DateTime64. [#69787](https://github.com/ClickHouse/ClickHouse/pull/69787) ([Michael Kolupaev](https://github.com/al13n321)).
* Backported in [#70019](https://github.com/ClickHouse/ClickHouse/issues/70019): Fix analyzer default with old compatibility value. [#69895](https://github.com/ClickHouse/ClickHouse/pull/69895) ([Raúl Marín](https://github.com/Algunenano)).
* Backported in [#69941](https://github.com/ClickHouse/ClickHouse/issues/69941): Don't check dependencies during CREATE OR REPLACE VIEW during DROP of old table. Previously CREATE OR REPLACE query failed when there are dependent tables of the recreated view. [#69907](https://github.com/ClickHouse/ClickHouse/pull/69907) ([Pavel Kruglov](https://github.com/Avogar)).
* Backported in [#70001](https://github.com/ClickHouse/ClickHouse/issues/70001): Now SQL security will work with parameterized views correctly. [#69984](https://github.com/ClickHouse/ClickHouse/pull/69984) ([pufit](https://github.com/pufit)).
* Backported in [#70081](https://github.com/ClickHouse/ClickHouse/issues/70081): Closes [#69752](https://github.com/ClickHouse/ClickHouse/issues/69752). [#69985](https://github.com/ClickHouse/ClickHouse/pull/69985) ([pufit](https://github.com/pufit)).
* Backported in [#70068](https://github.com/ClickHouse/ClickHouse/issues/70068): Fixes `Block structure mismatch` for queries with nested views and `WHERE` condition. Fixes [#66209](https://github.com/ClickHouse/ClickHouse/issues/66209). [#70054](https://github.com/ClickHouse/ClickHouse/pull/70054) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Backported in [#70166](https://github.com/ClickHouse/ClickHouse/issues/70166): Fix wrong LOGICAL_ERROR when replacing literals in ranges. [#70122](https://github.com/ClickHouse/ClickHouse/pull/70122) ([Pablo Marcos](https://github.com/pamarcos)).
* Backported in [#70236](https://github.com/ClickHouse/ClickHouse/issues/70236): Check for Nullable(Nothing) type during ALTER TABLE MODIFY COLUMN/QUERY to prevent tables with such data type. [#70123](https://github.com/ClickHouse/ClickHouse/pull/70123) ([Pavel Kruglov](https://github.com/Avogar)).
* Backported in [#70203](https://github.com/ClickHouse/ClickHouse/issues/70203): Fix wrong result with skipping index. [#70127](https://github.com/ClickHouse/ClickHouse/pull/70127) ([Raúl Marín](https://github.com/Algunenano)).
* Backported in [#70183](https://github.com/ClickHouse/ClickHouse/issues/70183): Fix data race in ColumnObject/ColumnTuple decompress method that could lead to heap use after free. [#70137](https://github.com/ClickHouse/ClickHouse/pull/70137) ([Pavel Kruglov](https://github.com/Avogar)).
* Backported in [#70251](https://github.com/ClickHouse/ClickHouse/issues/70251): Fix possible hung in ALTER COLUMN with Dynamic type. [#70144](https://github.com/ClickHouse/ClickHouse/pull/70144) ([Pavel Kruglov](https://github.com/Avogar)).
* Backported in [#70228](https://github.com/ClickHouse/ClickHouse/issues/70228): Use correct `max_types` parameter during Dynamic type creation for JSON subcolumn. [#70147](https://github.com/ClickHouse/ClickHouse/pull/70147) ([Pavel Kruglov](https://github.com/Avogar)).
* Backported in [#70243](https://github.com/ClickHouse/ClickHouse/issues/70243): Fix the password being displayed in `system.query_log` for users with bcrypt password authentication method. [#70148](https://github.com/ClickHouse/ClickHouse/pull/70148) ([Nikolay Degterinsky](https://github.com/evillique)).
* Backported in [#70432](https://github.com/ClickHouse/ClickHouse/issues/70432): Fix possible crash in JSON column. [#70172](https://github.com/ClickHouse/ClickHouse/pull/70172) ([Pavel Kruglov](https://github.com/Avogar)).
* Backported in [#70307](https://github.com/ClickHouse/ClickHouse/issues/70307): Fix multiple issues with arrayMin and arrayMax. [#70207](https://github.com/ClickHouse/ClickHouse/pull/70207) ([Raúl Marín](https://github.com/Algunenano)).
* Backported in [#70274](https://github.com/ClickHouse/ClickHouse/issues/70274): Respect setting allow_simdjson in JSON type parser. [#70218](https://github.com/ClickHouse/ClickHouse/pull/70218) ([Pavel Kruglov](https://github.com/Avogar)).
* Backported in [#70345](https://github.com/ClickHouse/ClickHouse/issues/70345): Don't modify global settings with startup scripts. Previously, changing a setting in a startup script would change it globally. [#70310](https://github.com/ClickHouse/ClickHouse/pull/70310) ([Antonio Andelic](https://github.com/antonio2368)).
* Backported in [#70426](https://github.com/ClickHouse/ClickHouse/issues/70426): Fix ALTER of Dynamic type with reducing max_types parameter that could lead to server crash. [#70328](https://github.com/ClickHouse/ClickHouse/pull/70328) ([Pavel Kruglov](https://github.com/Avogar)).
* Backported in [#70371](https://github.com/ClickHouse/ClickHouse/issues/70371): Fix crash when using WITH FILL incorrectly. [#70338](https://github.com/ClickHouse/ClickHouse/pull/70338) ([Raúl Marín](https://github.com/Algunenano)).
#### NO CL ENTRY
* NO CL ENTRY: 'Revert "Backport [#70146](https://github.com/ClickHouse/ClickHouse/issues/70146) to 24.8: Upgrade integration-runner image"'. [#70324](https://github.com/ClickHouse/ClickHouse/pull/70324) ([Max K.](https://github.com/maxknv)).
#### NOT FOR CHANGELOG / INSIGNIFICANT
* Backported in [#69961](https://github.com/ClickHouse/ClickHouse/issues/69961): Output an operation error for ZK Multi request failed operation into log. [#68127](https://github.com/ClickHouse/ClickHouse/pull/68127) ([Aleksei Filatov](https://github.com/aalexfvk)).
* Backported in [#69491](https://github.com/ClickHouse/ClickHouse/issues/69491): Fix test_role & test_keeper_s3_snapshot integration tests. [#69013](https://github.com/ClickHouse/ClickHouse/pull/69013) ([Shankar](https://github.com/shiyer7474)).
* Backported in [#69953](https://github.com/ClickHouse/ClickHouse/issues/69953): Remove stale moving parts without zookeeper. [#69075](https://github.com/ClickHouse/ClickHouse/pull/69075) ([Kirill](https://github.com/kirillgarbar)).
* Backported in [#69353](https://github.com/ClickHouse/ClickHouse/issues/69353): Fix: Not-ready Set with parallel replicas. [#69264](https://github.com/ClickHouse/ClickHouse/pull/69264) ([Igor Nikonov](https://github.com/devcrafter)).
* Backported in [#69427](https://github.com/ClickHouse/ClickHouse/issues/69427): Fix 24.8 setting compatibility `rows_before_aggregation`. [#69394](https://github.com/ClickHouse/ClickHouse/pull/69394) ([Nikita Fomichev](https://github.com/fm4v)).
* Backported in [#69689](https://github.com/ClickHouse/ClickHouse/issues/69689): Add function `kill_ci_runner`. Kill runner when pre-pull failed. [#69557](https://github.com/ClickHouse/ClickHouse/pull/69557) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Backported in [#69639](https://github.com/ClickHouse/ClickHouse/issues/69639): Add more contexts to the debug action and use it broadly. [#69599](https://github.com/ClickHouse/ClickHouse/pull/69599) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Backported in [#69721](https://github.com/ClickHouse/ClickHouse/issues/69721): Prohibit `ALTER TABLE ... ADD INDEX ... TYPE` inverted if setting = 0. [#69684](https://github.com/ClickHouse/ClickHouse/pull/69684) ([Robert Schulze](https://github.com/rschu1ze)).
* Backported in [#69972](https://github.com/ClickHouse/ClickHouse/issues/69972): S3Queue: support having deprecated settings to not fail server startup. [#69769](https://github.com/ClickHouse/ClickHouse/pull/69769) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Backported in [#70283](https://github.com/ClickHouse/ClickHouse/issues/70283): Improve pipdeptree generator for docker images. - Update requirements.txt for the integration tests runner container - Remove some small dependencies, improve `helpers/retry_decorator.py` - Upgrade docker-compose from EOL version 1 to version 2. [#70146](https://github.com/ClickHouse/ClickHouse/pull/70146) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Backported in [#70260](https://github.com/ClickHouse/ClickHouse/issues/70260): Update test_storage_s3_queue/test.py. [#70159](https://github.com/ClickHouse/ClickHouse/pull/70159) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Backported in [#70314](https://github.com/ClickHouse/ClickHouse/issues/70314): CI: Remove await feature from release branches. [#70294](https://github.com/ClickHouse/ClickHouse/pull/70294) ([Max K.](https://github.com/maxknv)).
* Backported in [#70380](https://github.com/ClickHouse/ClickHouse/issues/70380): Fix tiny mistake, responsible for some of kafka test flaps. Example [report](https://s3.amazonaws.com/clickhouse-test-reports/0/3198aafac59c368993e7b5f49d95674cc1b1be18/integration_tests__release__[2_4].html). [#70352](https://github.com/ClickHouse/ClickHouse/pull/70352) ([filimonov](https://github.com/filimonov)).
* Backported in [#70405](https://github.com/ClickHouse/ClickHouse/issues/70405): Closes [#69634](https://github.com/ClickHouse/ClickHouse/issues/69634). [#70354](https://github.com/ClickHouse/ClickHouse/pull/70354) ([pufit](https://github.com/pufit)).

View File

@ -42,6 +42,10 @@ brew install ccache cmake ninja libtool gettext llvm gcc binutils grep findutils
## Checkout ClickHouse Sources {#checkout-clickhouse-sources}
:::note
The ClickHouse build assumes a case-sensitive file system. Case-insensitive file systems may cause errors during the build process. If necessary, please follow [these instructions](https://brianboyko.medium.com/a-case-sensitive-src-folder-for-mac-programmers-176cc82a3830) to create a new disk image and checkout the code into it.
:::
``` bash
git clone --recursive git@github.com:ClickHouse/ClickHouse.git
# ...alternatively, you can use https://github.com/ClickHouse/ClickHouse.git as the repo URL.

View File

@ -82,7 +82,7 @@ cd ./utils/check-style
# Check duplicate includes
./check-duplicate-includes.sh
# Check c++ formatiing
# Check c++ formatting
./check-style
# Check python formatting with black

View File

@ -7,315 +7,5 @@ sidebar_position: 70
# [experimental] MaterializedMySQL
:::note
This database engine is experimental. To use it, set `allow_experimental_database_materialized_mysql` to 1 in your configuration files or by using the `SET` command:
```sql
SET allow_experimental_database_materialized_mysql=1
```
This database engine is obsolete and cannot be used.
:::
Creates a ClickHouse database with all the tables existing in MySQL, and all the data in those tables. The ClickHouse server works as MySQL replica. It reads `binlog` and performs DDL and DML queries.
## Creating a Database {#creating-a-database}
``` sql
CREATE DATABASE [IF NOT EXISTS] db_name [ON CLUSTER cluster]
ENGINE = MaterializedMySQL('host:port', ['database' | database], 'user', 'password') [SETTINGS ...]
[TABLE OVERRIDE table1 (...), TABLE OVERRIDE table2 (...)]
```
**Engine Parameters**
- `host:port` — MySQL server endpoint.
- `database` — MySQL database name.
- `user` — MySQL user.
- `password` — User password.
## Engine Settings
### max_rows_in_buffer
`max_rows_in_buffer` — Maximum number of rows that data is allowed to cache in memory (for single table and the cache data unable to query). When this number is exceeded, the data will be materialized. Default: `65 505`.
### max_bytes_in_buffer
`max_bytes_in_buffer` — Maximum number of bytes that data is allowed to cache in memory (for single table and the cache data unable to query). When this number is exceeded, the data will be materialized. Default: `1 048 576`.
### max_flush_data_time
`max_flush_data_time` — Maximum number of milliseconds that data is allowed to cache in memory (for database and the cache data unable to query). When this time is exceeded, the data will be materialized. Default: `1000`.
### max_wait_time_when_mysql_unavailable
`max_wait_time_when_mysql_unavailable` — Retry interval when MySQL is not available (milliseconds). Negative value disables retry. Default: `1000`.
### 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.
```sql
CREATE DATABASE mysql ENGINE = MaterializedMySQL('localhost:3306', 'db', 'user', '***')
SETTINGS
allows_query_when_mysql_lost=true,
max_wait_time_when_mysql_unavailable=10000;
```
## Settings on MySQL-server Side
For the correct work of `MaterializedMySQL`, there are few mandatory `MySQL`-side configuration settings that must be set:
### default_authentication_plugin
`default_authentication_plugin = mysql_native_password` since `MaterializedMySQL` can only authorize with this method.
### gtid_mode
`gtid_mode = on` since GTID based logging is a mandatory for providing correct `MaterializedMySQL` replication.
:::note
While turning on `gtid_mode` you should also specify `enforce_gtid_consistency = on`.
:::
## Virtual Columns {#virtual-columns}
When working with the `MaterializedMySQL` database engine, [ReplacingMergeTree](/docs/en/engines/table-engines/mergetree-family/replacingmergetree.md) tables are used with virtual `_sign` and `_version` columns.
### \_version
`_version` — Transaction counter. Type [UInt64](/docs/en/sql-reference/data-types/int-uint.md).
### \_sign
`_sign` — Deletion mark. Type [Int8](/docs/en/sql-reference/data-types/int-uint.md). Possible values:
- `1` — Row is not deleted,
- `-1` — Row is deleted.
## Data Types Support {#data_types-support}
| MySQL | ClickHouse |
|-------------------------|--------------------------------------------------------------|
| TINY | [Int8](/docs/en/sql-reference/data-types/int-uint.md) |
| SHORT | [Int16](/docs/en/sql-reference/data-types/int-uint.md) |
| INT24 | [Int32](/docs/en/sql-reference/data-types/int-uint.md) |
| LONG | [UInt32](/docs/en/sql-reference/data-types/int-uint.md) |
| LONGLONG | [UInt64](/docs/en/sql-reference/data-types/int-uint.md) |
| FLOAT | [Float32](/docs/en/sql-reference/data-types/float.md) |
| DOUBLE | [Float64](/docs/en/sql-reference/data-types/float.md) |
| DECIMAL, NEWDECIMAL | [Decimal](/docs/en/sql-reference/data-types/decimal.md) |
| DATE, NEWDATE | [Date](/docs/en/sql-reference/data-types/date.md) |
| DATETIME, TIMESTAMP | [DateTime](/docs/en/sql-reference/data-types/datetime.md) |
| DATETIME2, TIMESTAMP2 | [DateTime64](/docs/en/sql-reference/data-types/datetime64.md) |
| YEAR | [UInt16](/docs/en/sql-reference/data-types/int-uint.md) |
| TIME | [Int64](/docs/en/sql-reference/data-types/int-uint.md) |
| ENUM | [Enum](/docs/en/sql-reference/data-types/enum.md) |
| STRING | [String](/docs/en/sql-reference/data-types/string.md) |
| VARCHAR, VAR_STRING | [String](/docs/en/sql-reference/data-types/string.md) |
| BLOB | [String](/docs/en/sql-reference/data-types/string.md) |
| GEOMETRY | [String](/docs/en/sql-reference/data-types/string.md) |
| BINARY | [FixedString](/docs/en/sql-reference/data-types/fixedstring.md) |
| BIT | [UInt64](/docs/en/sql-reference/data-types/int-uint.md) |
| SET | [UInt64](/docs/en/sql-reference/data-types/int-uint.md) |
[Nullable](/docs/en/sql-reference/data-types/nullable.md) is supported.
The data of TIME type in MySQL is converted to microseconds in ClickHouse.
Other types are not supported. If MySQL table contains a column of such type, ClickHouse throws an exception and stops replication.
## Specifics and Recommendations {#specifics-and-recommendations}
### Compatibility Restrictions {#compatibility-restrictions}
Apart of the data types limitations there are few restrictions comparing to `MySQL` databases, that should be resolved before replication will be possible:
- Each table in `MySQL` should contain `PRIMARY KEY`.
- Replication for tables, those are containing rows with `ENUM` field values out of range (specified in `ENUM` signature) will not work.
### DDL Queries {#ddl-queries}
MySQL DDL queries are converted into the corresponding ClickHouse DDL queries ([ALTER](/docs/en/sql-reference/statements/alter/index.md), [CREATE](/docs/en/sql-reference/statements/create/index.md), [DROP](/docs/en/sql-reference/statements/drop.md), [RENAME](/docs/en/sql-reference/statements/rename.md)). If ClickHouse cannot parse some DDL query, the query is ignored.
### Data Replication {#data-replication}
`MaterializedMySQL` does not support direct `INSERT`, `DELETE` and `UPDATE` queries. However, they are supported in terms of data replication:
- MySQL `INSERT` query is converted into `INSERT` with `_sign=1`.
- MySQL `DELETE` query is converted into `INSERT` with `_sign=-1`.
- MySQL `UPDATE` query is converted into `INSERT` with `_sign=-1` and `INSERT` with `_sign=1` if the primary key has been changed, or
`INSERT` with `_sign=1` if not.
### Selecting from MaterializedMySQL Tables {#select}
`SELECT` query from `MaterializedMySQL` tables has some specifics:
- If `_version` is not specified in the `SELECT` query, the
[FINAL](/docs/en/sql-reference/statements/select/from.md/#select-from-final) modifier is used, so only rows with
`MAX(_version)` are returned for each primary key value.
- If `_sign` is not specified in the `SELECT` query, `WHERE _sign=1` is used by default. So the deleted rows are not
included into the result set.
- The result includes columns comments in case they exist in MySQL database tables.
### Index Conversion {#index-conversion}
MySQL `PRIMARY KEY` and `INDEX` clauses are converted into `ORDER BY` tuples in ClickHouse tables.
ClickHouse has only one physical order, which is determined by `ORDER BY` clause. To create a new physical order, use
[materialized views](/docs/en/sql-reference/statements/create/view.md/#materialized).
**Notes**
- Rows with `_sign=-1` are not deleted physically from the tables.
- Cascade `UPDATE/DELETE` queries are not supported by the `MaterializedMySQL` engine, as they are not visible in the
MySQL binlog.
- Replication can be easily broken.
- Manual operations on database and tables are forbidden.
- `MaterializedMySQL` is affected by the [optimize_on_insert](/docs/en/operations/settings/settings.md/#optimize-on-insert)
setting. Data is merged in the corresponding table in the `MaterializedMySQL` database when a table in the MySQL
server changes.
### Table Overrides {#table-overrides}
Table overrides can be used to customize the ClickHouse DDL queries, allowing you to make schema optimizations for your
application. This is especially useful for controlling partitioning, which is important for the overall performance of
MaterializedMySQL.
These are the schema conversion manipulations you can do with table overrides for MaterializedMySQL:
* Modify column type. Must be compatible with the original type, or replication will fail. For example,
you can modify a UInt32 column to UInt64, but you can not modify a String column to Array(String).
* Modify [column TTL](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#mergetree-column-ttl).
* Modify [column compression codec](/docs/en/sql-reference/statements/create/table.md/#codecs).
* Add [ALIAS columns](/docs/en/sql-reference/statements/create/table.md/#alias).
* Add [skipping indexes](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#table_engine-mergetree-data_skipping-indexes). Note that you need to enable `use_skip_indexes_if_final` setting to make them work (MaterializedMySQL is using `SELECT ... FINAL` by default)
* Add [projections](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#projections). Note that projection optimizations are
disabled when using `SELECT ... FINAL` (which MaterializedMySQL does by default), so their utility is limited here.
`INDEX ... TYPE hypothesis` as [described in the v21.12 blog post]](https://clickhouse.com/blog/en/2021/clickhouse-v21.12-released/)
may be more useful in this case.
* Modify [PARTITION BY](/docs/en/engines/table-engines/mergetree-family/custom-partitioning-key/)
* Modify [ORDER BY](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#mergetree-query-clauses)
* Modify [PRIMARY KEY](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#mergetree-query-clauses)
* Add [SAMPLE BY](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#mergetree-query-clauses)
* Add [table TTL](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#mergetree-query-clauses)
```sql
CREATE DATABASE db_name ENGINE = MaterializedMySQL(...)
[SETTINGS ...]
[TABLE OVERRIDE table_name (
[COLUMNS (
[col_name [datatype] [ALIAS expr] [CODEC(...)] [TTL expr], ...]
[INDEX index_name expr TYPE indextype[(...)] GRANULARITY val, ...]
[PROJECTION projection_name (SELECT <COLUMN LIST EXPR> [GROUP BY] [ORDER BY]), ...]
)]
[ORDER BY expr]
[PRIMARY KEY expr]
[PARTITION BY expr]
[SAMPLE BY expr]
[TTL expr]
), ...]
```
Example:
```sql
CREATE DATABASE db_name ENGINE = MaterializedMySQL(...)
TABLE OVERRIDE table1 (
COLUMNS (
userid UUID,
category LowCardinality(String),
timestamp DateTime CODEC(Delta, Default)
)
PARTITION BY toYear(timestamp)
),
TABLE OVERRIDE table2 (
COLUMNS (
client_ip String TTL created + INTERVAL 72 HOUR
)
SAMPLE BY ip_hash
)
```
The `COLUMNS` list is sparse; existing columns are modified as specified, extra ALIAS columns are added. It is not
possible to add ordinary or MATERIALIZED columns. Modified columns with a different type must be assignable from the
original type. There is currently no validation of this or similar issues when the `CREATE DATABASE` query executes, so
extra care needs to be taken.
You may specify overrides for tables that do not exist yet.
:::important
It is easy to break replication with table overrides if not used with care. For example:
* If an ALIAS column is added with a table override, and a column with the same name is later added to the source
MySQL table, the converted ALTER TABLE query in ClickHouse will fail and replication stops.
* It is currently possible to add overrides that reference nullable columns where not-nullable are required, such as in
`ORDER BY` or `PARTITION BY`. This will cause CREATE TABLE queries that will fail, also causing replication to stop.
:::
## Examples of Use {#examples-of-use}
Queries in MySQL:
``` sql
mysql> CREATE DATABASE db;
mysql> CREATE TABLE db.test (a INT PRIMARY KEY, b INT);
mysql> INSERT INTO db.test VALUES (1, 11), (2, 22);
mysql> DELETE FROM db.test WHERE a=1;
mysql> ALTER TABLE db.test ADD COLUMN c VARCHAR(16);
mysql> UPDATE db.test SET c='Wow!', b=222;
mysql> SELECT * FROM test;
```
```text
┌─a─┬───b─┬─c────┐
│ 2 │ 222 │ Wow! │
└───┴─────┴──────┘
```
Database in ClickHouse, exchanging data with the MySQL server:
The database and the table created:
``` sql
CREATE DATABASE mysql ENGINE = MaterializedMySQL('localhost:3306', 'db', 'user', '***');
SHOW TABLES FROM mysql;
```
``` text
┌─name─┐
│ test │
└──────┘
```
After inserting data:
``` sql
SELECT * FROM mysql.test;
```
``` text
┌─a─┬──b─┐
│ 1 │ 11 │
│ 2 │ 22 │
└───┴────┘
```
After deleting data, adding the column and updating:
``` sql
SELECT * FROM mysql.test;
```
``` text
┌─a─┬───b─┬─c────┐
│ 2 │ 222 │ Wow! │
└───┴─────┴──────┘
```

View File

@ -63,7 +63,34 @@ Currently there are 3 ways to authenticate:
- `SAS Token` - Can be used by providing an `endpoint`, `connection_string` or `storage_account_url`. It is identified by presence of '?' in the url.
- `Workload Identity` - Can be used by providing an `endpoint` or `storage_account_url`. If `use_workload_identity` parameter is set in config, ([workload identity](https://github.com/Azure/azure-sdk-for-cpp/tree/main/sdk/identity/azure-identity#authenticate-azure-hosted-applications)) is used for authentication.
### Data cache {#data-cache}
`Azure` table engine supports data caching on local disk.
See filesystem cache configuration options and usage in this [section](/docs/en/operations/storing-data.md/#using-local-cache).
Caching is made depending on the path and ETag of the storage object, so clickhouse will not read a stale cache version.
To enable caching use a setting `filesystem_cache_name = '<name>'` and `enable_filesystem_cache = 1`.
```sql
SELECT *
FROM azureBlobStorage('DefaultEndpointsProtocol=http;AccountName=devstoreaccount1;AccountKey=Eby8vdM02xNOcqFlqUwJPLlmEtlCDXJ1OUzFT50uSRZ6IFsuFq2UVErCz4I6tq/K1SZFPTOtr/KBHBeksoGMGw==;BlobEndpoint=http://azurite1:10000/devstoreaccount1/;', 'test_container', 'test_table', 'CSV')
SETTINGS filesystem_cache_name = 'cache_for_azure', enable_filesystem_cache = 1;
```
1. add the following section to clickhouse configuration file:
``` xml
<clickhouse>
<filesystem_caches>
<cache_for_azure>
<path>path to cache directory</path>
<max_size>10Gi</max_size>
</cache_for_azure>
</filesystem_caches>
</clickhouse>
```
2. reuse cache configuration (and therefore cache storage) from clickhouse `storage_configuration` section, [described here](/docs/en/operations/storing-data.md/#using-local-cache)
## See also

View File

@ -48,6 +48,10 @@ Using named collections:
CREATE TABLE deltalake ENGINE=DeltaLake(deltalake_conf, filename = 'test_table')
```
### Data cache {#data-cache}
`Iceberg` table engine and table function support data caching same as `S3`, `AzureBlobStorage`, `HDFS` storages. See [here](../../../engines/table-engines/integrations/s3.md#data-cache).
## See also
- [deltaLake table function](../../../sql-reference/table-functions/deltalake.md)

View File

@ -6,7 +6,7 @@ sidebar_label: Iceberg
# Iceberg Table Engine
This engine provides a read-only integration with existing Apache [Iceberg](https://iceberg.apache.org/) tables in Amazon S3, Azure and locally stored tables.
This engine provides a read-only integration with existing Apache [Iceberg](https://iceberg.apache.org/) tables in Amazon S3, Azure, HDFS and locally stored tables.
## Create Table
@ -19,13 +19,16 @@ CREATE TABLE iceberg_table_s3
CREATE TABLE iceberg_table_azure
ENGINE = IcebergAzure(connection_string|storage_account_url, container_name, blobpath, [account_name, account_key, format, compression])
CREATE TABLE iceberg_table_hdfs
ENGINE = IcebergHDFS(path_to_table, [,format] [,compression_method])
CREATE TABLE iceberg_table_local
ENGINE = IcebergLocal(path_to_table, [,format] [,compression_method])
```
**Engine arguments**
Description of the arguments coincides with description of arguments in engines `S3`, `AzureBlobStorage` and `File` correspondingly.
Description of the arguments coincides with description of arguments in engines `S3`, `AzureBlobStorage`, `HDFS` and `File` correspondingly.
`format` stands for the format of data files in the Iceberg table.
Engine parameters can be specified using [Named Collections](../../../operations/named-collections.md)
@ -60,6 +63,10 @@ CREATE TABLE iceberg_table ENGINE=IcebergS3(iceberg_conf, filename = 'test_table
Table engine `Iceberg` is an alias to `IcebergS3` now.
### Data cache {#data-cache}
`Iceberg` table engine and table function support data caching same as `S3`, `AzureBlobStorage`, `HDFS` storages. See [here](../../../engines/table-engines/integrations/s3.md#data-cache).
## See also
- [iceberg table function](/docs/en/sql-reference/table-functions/iceberg.md)

View File

@ -9,7 +9,7 @@ sidebar_label: MongoDB
MongoDB engine is read-only table engine which allows to read data from remote [MongoDB](https://www.mongodb.com/) collection.
Only MongoDB v3.6+ servers are supported.
[Seed list(`mongodb**+srv**`)](https://www.mongodb.com/docs/manual/reference/glossary/#std-term-seed-list) is not yet supported.
[Seed list(`mongodb+srv`)](https://www.mongodb.com/docs/manual/reference/glossary/#std-term-seed-list) is not yet supported.
:::note
If you're facing troubles, please report the issue, and try to use [the legacy implementation](../../../operations/server-configuration-parameters/settings.md#use_legacy_mongodb_integration).

View File

@ -4,12 +4,8 @@ sidebar_position: 138
sidebar_label: MySQL
---
import CloudAvailableBadge from '@theme/badges/CloudAvailableBadge';
# MySQL Table Engine
<CloudAvailableBadge />
The MySQL engine allows you to perform `SELECT` and `INSERT` queries on data that is stored on a remote MySQL server.
## Creating a Table {#creating-a-table}

View File

@ -26,6 +26,7 @@ SELECT * FROM s3_engine_table LIMIT 2;
│ two │ 2 │
└──────┴───────┘
```
## Create Table {#creating-a-table}
``` sql
@ -43,6 +44,37 @@ CREATE TABLE s3_engine_table (name String, value UInt32)
- `aws_access_key_id`, `aws_secret_access_key` - Long-term credentials for the [AWS](https://aws.amazon.com/) account user. You can use these to authenticate your requests. Parameter is optional. If credentials are not specified, they are used from the configuration file. For more information see [Using S3 for Data Storage](../mergetree-family/mergetree.md#table_engine-mergetree-s3).
- `compression` — Compression type. Supported values: `none`, `gzip/gz`, `brotli/br`, `xz/LZMA`, `zstd/zst`. Parameter is optional. By default, it will auto-detect compression by file extension.
### Data cache {#data-cache}
`S3` table engine supports data caching on local disk.
See filesystem cache configuration options and usage in this [section](/docs/en/operations/storing-data.md/#using-local-cache).
Caching is made depending on the path and ETag of the storage object, so clickhouse will not read a stale cache version.
To enable caching use a setting `filesystem_cache_name = '<name>'` and `enable_filesystem_cache = 1`.
```sql
SELECT *
FROM s3('http://minio:10000/clickhouse//test_3.csv', 'minioadmin', 'minioadminpassword', 'CSV')
SETTINGS filesystem_cache_name = 'cache_for_s3', enable_filesystem_cache = 1;
```
There are two ways to define cache in configuration file.
1. add the following section to clickhouse configuration file:
``` xml
<clickhouse>
<filesystem_caches>
<cache_for_s3>
<path>path to cache directory</path>
<max_size>10Gi</max_size>
</cache_for_s3>
</filesystem_caches>
</clickhouse>
```
2. reuse cache configuration (and therefore cache storage) from clickhouse `storage_configuration` section, [described here](/docs/en/operations/storing-data.md/#using-local-cache)
### PARTITION BY
`PARTITION BY` — Optional. In most cases you don't need a partition key, and if it is needed you generally don't need a partition key more granular than by month. Partitioning does not speed up queries (in contrast to the ORDER BY expression). You should never use too granular partitioning. Don't partition your data by client identifiers or names (instead, make client identifier or name the first column in the ORDER BY expression).

View File

@ -43,7 +43,7 @@ CREATE TABLE table
(
id Int64,
vectors Array(Float32),
INDEX index_name vectors TYPE vector_similarity(method, distance_function[, quantization, connectivity, expansion_add, expansion_search]) [GRANULARITY N]
INDEX index_name vectors TYPE vector_similarity(method, distance_function[, quantization, hnsw_max_connections_per_layer, hnsw_candidate_list_size_for_construction]) [GRANULARITY N]
)
ENGINE = MergeTree
ORDER BY id;
@ -55,11 +55,13 @@ Parameters:
line between two points in Euclidean space), or `cosineDistance` (the [cosine
distance](https://en.wikipedia.org/wiki/Cosine_similarity#Cosine_distance)- the angle between two non-zero vectors).
- `quantization`: either `f64`, `f32`, `f16`, `bf16`, or `i8` for storing the vector with reduced precision (optional, default: `bf16`)
- `m`: the number of neighbors per graph node (optional, default: 16)
- `ef_construction`: (optional, default: 128)
- `ef_search`: (optional, default: 64)
- `hnsw_max_connections_per_layer`: the number of neighbors per HNSW graph node, also known as `M` in the [HNSW
paper](https://doi.org/10.1109/TPAMI.2018.2889473) (optional, default: 16)
- `hnsw_candidate_list_size_for_construction`: the size of the dynamic candidate list when constructing the HNSW graph, also known as
`ef_construction` in the original [HNSW paper](https://doi.org/10.1109/TPAMI.2018.2889473) (optional, default: 128)
Value 0 for parameters `m`, `ef_construction`, and `ef_search` refers to the default value.
Values 0 for parameters `hnsw_max_connections_per_layer` and `hnsw_candidate_list_size_for_construction` means using the default values of
these parameters.
Example:
@ -115,6 +117,11 @@ ANN indexes are built during column insertion and merge. As a result, `INSERT` a
tables. ANNIndexes are ideally used only with immutable or rarely changed data, respectively when are far more read requests than write
requests.
:::tip
To reduce the cost of building vector similarity indexes, consider setting `materialize_skip_indexes_on_insert` which disables the
construction of skipping indexes on newly inserted parts. Search would fall back to exact search but as inserted parts are typically small
compared to the total table size, the performance impact of that would be negligible.
ANN indexes support this type of query:
``` sql
@ -124,6 +131,7 @@ FROM table
WHERE ... -- WHERE clause is optional
ORDER BY Distance(vectors, reference_vector)
LIMIT N
SETTINGS enable_analyzer = 0; -- Temporary limitation, will be lifted
```
:::tip
@ -135,6 +143,10 @@ clickhouse-client --param_vec='hello' --query="SELECT * FROM table WHERE L2Dista
```
:::
To search using a different value of HNSW parameter `hnsw_candidate_list_size_for_search` (default: 64), also known as `ef_search` in the
original [HNSW paper](https://doi.org/10.1109/TPAMI.2018.2889473), run the `SELECT` query with `SETTINGS hnsw_candidate_list_size_for_search
= <value>`.
**Restrictions**: Approximate algorithms used to determine the nearest neighbors require a limit, hence queries without `LIMIT` clause
cannot utilize ANN indexes. Also, ANN indexes are only used if the query has a `LIMIT` value smaller than setting
`max_limit_for_ann_queries` (default: 1 million rows). This is a safeguard to prevent large memory allocations by external libraries for

View File

@ -374,15 +374,15 @@ Users can create [UDF](/docs/en/sql-reference/statements/create/function.md) to
```sql
CREATE FUNCTION bfEstimateFunctions [ON CLUSTER cluster]
AS
(total_nubmer_of_all_grams, size_of_bloom_filter_in_bits) -> round((size_of_bloom_filter_in_bits / total_nubmer_of_all_grams) * log(2));
(total_number_of_all_grams, size_of_bloom_filter_in_bits) -> round((size_of_bloom_filter_in_bits / total_number_of_all_grams) * log(2));
CREATE FUNCTION bfEstimateBmSize [ON CLUSTER cluster]
AS
(total_nubmer_of_all_grams, probability_of_false_positives) -> ceil((total_nubmer_of_all_grams * log(probability_of_false_positives)) / log(1 / pow(2, log(2))));
(total_number_of_all_grams, probability_of_false_positives) -> ceil((total_number_of_all_grams * log(probability_of_false_positives)) / log(1 / pow(2, log(2))));
CREATE FUNCTION bfEstimateFalsePositive [ON CLUSTER cluster]
AS
(total_nubmer_of_all_grams, number_of_hash_functions, size_of_bloom_filter_in_bytes) -> pow(1 - exp(-number_of_hash_functions/ (size_of_bloom_filter_in_bytes / total_nubmer_of_all_grams)), number_of_hash_functions);
(total_number_of_all_grams, number_of_hash_functions, size_of_bloom_filter_in_bytes) -> pow(1 - exp(-number_of_hash_functions/ (size_of_bloom_filter_in_bytes / total_number_of_all_grams)), number_of_hash_functions);
CREATE FUNCTION bfEstimateGramNumber [ON CLUSTER cluster]
AS

View File

@ -35,7 +35,7 @@ Engine parameters:
- `root_path` - ZooKeeper path where the `table_name` will be stored.
This path should not contain the prefix defined by `<keeper_map_path_prefix>` config because the prefix will be automatically appended to the `root_path`.
Additionally, format of `auxiliary_zookeper_cluster_name:/some/path` is also supported where `auxiliary_zookeper_cluster` is a ZooKeeper cluster defined inside `<auxiliary_zookeepers>` config.
Additionally, format of `auxiliary_zookeeper_cluster_name:/some/path` is also supported where `auxiliary_zookeeper_cluster` is a ZooKeeper cluster defined inside `<auxiliary_zookeepers>` config.
By default, ZooKeeper cluster defined inside `<zookeeper>` config is used.
- `keys_limit` - number of keys allowed inside the table.
This limit is a soft limit and it can be possible that more keys will end up in the table for some edge cases.

View File

@ -877,7 +877,7 @@ INSERT INTO json_as_object (json) FORMAT JSONAsObject {"any json stucture":1}
SELECT time, json FROM json_as_object FORMAT JSONEachRow
```
```resonse
```response
{"time":"2024-09-16 12:18:10","json":{}}
{"time":"2024-09-16 12:18:13","json":{"any json stucture":"1"}}
{"time":"2024-09-16 12:18:08","json":{"foo":{"bar":{"x":"y"},"baz":"1"}}}
@ -1598,10 +1598,6 @@ the columns from input data will be mapped to the columns from the table by thei
Otherwise, the first row will be skipped.
If setting [input_format_with_types_use_header](/docs/en/operations/settings/settings-formats.md/#input_format_with_types_use_header) is set to 1,
the types from input data will be compared with the types of the corresponding columns from the table. Otherwise, the second row will be skipped.
If setting [output_format_binary_encode_types_in_binary_format](/docs/en/operations/settings/settings-formats.md/#output_format_binary_encode_types_in_binary_format) is set to 1,
the types in header will be written using [binary encoding](/docs/en/sql-reference/data-types/data-types-binary-encoding.md) instead of strings with type names in RowBinaryWithNamesAndTypes output format.
If setting [input_format_binary_encode_types_in_binary_format](/docs/en/operations/settings/settings-formats.md/#input_format_binary_encode_types_in_binary_format) is set to 1,
the types in header will be read using [binary encoding](/docs/en/sql-reference/data-types/data-types-binary-encoding.md) instead of strings with type names in RowBinaryWithNamesAndTypes input format.
:::
## RowBinaryWithDefaults {#rowbinarywithdefaults}
@ -1624,6 +1620,10 @@ For column `y` data starts with byte `00` that indicates that column has actual
## RowBinary format settings {#row-binary-format-settings}
- [format_binary_max_string_size](/docs/en/operations/settings/settings-formats.md/#format_binary_max_string_size) - The maximum allowed size for String in RowBinary format. Default value - `1GiB`.
- [output_format_binary_encode_types_in_binary_format](/docs/en/operations/settings/settings-formats.md/#output_format_binary_encode_types_in_binary_format) - Allows to write types in header using [binary encoding](/docs/en/sql-reference/data-types/data-types-binary-encoding.md) instead of strings with type names in RowBinaryWithNamesAndTypes output format. Default value - `false`.
- [input_format_binary_encode_types_in_binary_format](/docs/en/operations/settings/settings-formats.md/#input_format_binary_encode_types_in_binary_format) - Allows to read types in header using [binary encoding](/docs/en/sql-reference/data-types/data-types-binary-encoding.md) instead of strings with type names in RowBinaryWithNamesAndTypes input format. Default value - `false`.
- [output_format_binary_write_json_as_string](/docs/en/operations/settings/settings-formats.md/#output_format_binary_write_json_as_string) - Allows to write values of [JSON](/docs/en/sql-reference/data-types/newjson.md) data type as JSON [String](/docs/en/sql-reference/data-types/string.md) values in RowBinary output format. Default value - `false`.
- [input_format_binary_read_json_as_string](/docs/en/operations/settings/settings-formats.md/#input_format_binary_read_json_as_string) - Allows to read values of [JSON](/docs/en/sql-reference/data-types/newjson.md) data type as JSON [String](/docs/en/sql-reference/data-types/string.md) values in RowBinary input format. Default value - `false`.
## Values {#data-format-values}

View File

@ -509,7 +509,7 @@ DESC format(JSONEachRow, $$
{"value" : "424242424242"}
$$)
```
```reponse
```response
┌─name──┬─type────────────┬─default_type─┬─default_expression─┬─comment─┬─codec_expression─┬─ttl_expression─┐
│ value │ Nullable(Int64) │ │ │ │ │ │
└───────┴─────────────────┴──────────────┴────────────────────┴─────────┴──────────────────┴────────────────┘
@ -910,9 +910,9 @@ This setting is disabled by default.
```sql
SET input_format_json_try_infer_numbers_from_strings = 1;
DESC format(CSV, '"42","42.42"');
DESC format(CSV, '42,42.42');
```
```reponse
```response
┌─name─┬─type──────────────┬─default_type─┬─default_expression─┬─comment─┬─codec_expression─┬─ttl_expression─┐
│ c1 │ Nullable(Int64) │ │ │ │ │ │
│ c2 │ Nullable(Float64) │ │ │ │ │ │

View File

@ -19,6 +19,19 @@ Features:
- Performance Optimizations: Utilizes Indexed DB for efficient caching and state management.
- Local Data Storage: All data is stored locally in the browser, ensuring no data is sent anywhere else.
### ChartDB {#chartdb}
[ChartDB](https://chartdb.io) is a free and open-source tool for visualizing and designing database schemas, including ClickHouse, with a single query. Built with React, it provides a seamless and user-friendly experience, requiring no database credentials or signup to get started.
Features:
- Schema Visualization: Instantly import and visualize your ClickHouse schema, including ER diagrams with materialized views and standard views, showing references to tables.
- AI-Powered DDL Export: Generate DDL scripts effortlessly for better schema management and documentation.
- Multi-SQL Dialect Support: Compatible with a range of SQL dialects, making it versatile for various database environments.
- No Signup or Credentials Needed: All functionality is accessible directly in the browser, keeping it frictionless and secure.
[ChartDB Source Code](https://github.com/chartdb/chartdb).
### Tabix {#tabix}
Web interface for ClickHouse in the [Tabix](https://github.com/tabixio/tabix) project.

View File

@ -31,6 +31,10 @@ The table must be enabled in the server configuration, see the `opentelemetry_sp
The tags or attributes are saved as two parallel arrays, containing the keys and values. Use [ARRAY JOIN](../sql-reference/statements/select/array-join.md) to work with them.
## Log-query-settings
ClickHouse allows you to log changes to query settings during query execution. When enabled, any modifications made to query settings will be recorded in the OpenTelemetry span log. This feature is particularly useful in production environments for tracking configuration changes that may affect query performance.
## Integration with monitoring systems
At the moment, there is no ready tool that can export the tracing data from ClickHouse to a monitoring system.

View File

@ -2,7 +2,6 @@
title: "Settings Overview"
sidebar_position: 1
slug: /en/operations/settings/
pagination_next: en/operations/settings/settings
---
# Settings Overview

View File

@ -49,7 +49,7 @@ Default value: 8192.
Maximum size of data granules in bytes.
Default value: 10Mb.
Default value: 10485760 (ca. 10 MiB).
To restrict the granule size only by number of rows, set to 0 (not recommended).

View File

@ -1,176 +0,0 @@
# The MySQL Binlog Client
The MySQL Binlog Client provides a mechanism in ClickHouse to share the binlog from a MySQL instance among multiple [MaterializedMySQL](../../engines/database-engines/materialized-mysql.md) databases. This avoids consuming unnecessary bandwidth and CPU when replicating more than one schema/database.
The implementation is resilient against crashes and disk issues. The executed GTID sets of the binlog itself and the consuming databases have persisted only after the data they describe has been safely persisted as well. The implementation also tolerates re-doing aborted operations (at-least-once delivery).
# Settings
## use_binlog_client
Forces to reuse existing MySQL binlog connection or creates new one if does not exist. The connection is defined by `user:pass@host:port`.
Default value: 0
**Example**
```sql
-- create MaterializedMySQL databases that read the events from the binlog client
CREATE DATABASE db1 ENGINE = MaterializedMySQL('host:port', 'db1', 'user', 'password') SETTINGS use_binlog_client=1
CREATE DATABASE db2 ENGINE = MaterializedMySQL('host:port', 'db2', 'user', 'password') SETTINGS use_binlog_client=1
CREATE DATABASE db3 ENGINE = MaterializedMySQL('host:port', 'db3', 'user2', 'password2') SETTINGS use_binlog_client=1
```
Databases `db1` and `db2` will use the same binlog connection, since they use the same `user:pass@host:port`. Database `db3` will use separate binlog connection.
## max_bytes_in_binlog_queue
Defines the limit of bytes in the events binlog queue. If bytes in the queue increases this limit, it will stop reading new events from MySQL until the space for new events will be freed. This introduces the memory limits. Very high value could consume all available memory. Very low value could make the databases to wait for new events.
Default value: 67108864
**Example**
```sql
CREATE DATABASE db1 ENGINE = MaterializedMySQL('host:port', 'db1', 'user', 'password') SETTINGS use_binlog_client=1, max_bytes_in_binlog_queue=33554432
CREATE DATABASE db2 ENGINE = MaterializedMySQL('host:port', 'db2', 'user', 'password') SETTINGS use_binlog_client=1
```
If database `db1` is unable to consume binlog events fast enough and the size of the events queue exceeds `33554432` bytes, reading of new events from MySQL is postponed until `db1`
consumes the events and releases some space.
NOTE: This will impact to `db2`, and it will be waiting for new events too, since they share the same connection.
## max_milliseconds_to_wait_in_binlog_queue
Defines the max milliseconds to wait when `max_bytes_in_binlog_queue` exceeded. After that it will detach the database from current binlog connection and will retry establish new one to prevent other databases to wait for this database.
Default value: 10000
**Example**
```sql
CREATE DATABASE db1 ENGINE = MaterializedMySQL('host:port', 'db1', 'user', 'password') SETTINGS use_binlog_client=1, max_bytes_in_binlog_queue=33554432, max_milliseconds_to_wait_in_binlog_queue=1000
CREATE DATABASE db2 ENGINE = MaterializedMySQL('host:port', 'db2', 'user', 'password') SETTINGS use_binlog_client=1
```
If the event queue of database `db1` is full, the binlog connection will be waiting in `1000`ms and if the database is not able to consume the events, it will be detached from the connection to create another one.
NOTE: If the database `db1` has been detached from the shared connection and created new one, after the binlog connections for `db1` and `db2` have the same positions they will be merged to one. And `db1` and `db2` will use the same connection again.
## max_bytes_in_binlog_dispatcher_buffer
Defines the max bytes in the binlog dispatcher's buffer before it is flushed to attached binlog. The events from MySQL binlog connection are buffered before sending to attached databases. It increases the events throughput from the binlog to databases.
Default value: 1048576
## max_flush_milliseconds_in_binlog_dispatcher
Defines the max milliseconds in the binlog dispatcher's buffer to wait before it is flushed to attached binlog. If there are no events received from MySQL binlog connection for a while, after some time buffered events should be sent to the attached databases.
Default value: 1000
# Design
## The Binlog Events Dispatcher
Currently each MaterializedMySQL database opens its own connection to MySQL to subscribe to binlog events. There is a need to have only one connection and _dispatch_ the binlog events to all databases that replicate from the same MySQL instance.
## Each MaterializedMySQL Database Has Its Own Event Queue
To prevent slowing down other instances there should be an _event queue_ per MaterializedMySQL database to handle the events independently of the speed of other instances. The dispatcher reads an event from the binlog, and sends it to every MaterializedMySQL database that needs it. Each database handles its events in separate threads.
## Catching up
If several databases have the same binlog position, they can use the same dispatcher. If a newly created database (or one that has been detached for some time) requests events that have been already processed, we need to create another communication _channel_ to the binlog. We do this by creating another temporary dispatcher for such databases. When the new dispatcher _catches up with_ the old one, the new/temporary dispatcher is not needed anymore and all databases getting events from this dispatcher can be moved to the old one.
## Memory Limit
There is a _memory limit_ to control event queue memory consumption per MySQL Client. If a database is not able to handle events fast enough, and the event queue is getting full, we have the following options:
1. The dispatcher is blocked until the slowest database frees up space for new events. All other databases are waiting for the slowest one. (Preferred)
2. The dispatcher is _never_ blocked, but suspends incremental sync for the slow database and continues dispatching events to remained databases.
## Performance
A lot of CPU can be saved by not processing every event in every database. The binlog contains events for all databases, it is wasteful to distribute row events to a database that it will not process it, especially if there are a lot of databases. This requires some sort of per-database binlog filtering and buffering.
Currently all events are sent to all MaterializedMySQL databases but parsing the event which consumes CPU is up to the database.
# Detailed Design
1. If a client (e.g. database) wants to read a stream of the events from MySQL binlog, it creates a connection to remote binlog by host/user/password and _executed GTID set_ params.
2. If another client wants to read the events from the binlog but for different _executed GTID set_, it is **not** possible to reuse existing connection to MySQL, then need to create another connection to the same remote binlog. (_This is how it is implemented today_).
3. When these 2 connections get the same binlog positions, they read the same events. It is logical to drop duplicate connection and move all its users out. And now one connection dispatches binlog events to several clients. Obviously only connections to the same binlog should be merged.
## Classes
1. One connection can send (or dispatch) events to several clients and might be called `BinlogEventsDispatcher`.
2. Several dispatchers grouped by _user:password@host:port_ in `BinlogClient`. Since they point to the same binlog.
3. The clients should communicate only with public API from `BinlogClient`. The result of using `BinlogClient` is an object that implements `IBinlog` to read events from. This implementation of `IBinlog` must be compatible with old implementation `MySQLFlavor` -> when replacing old implementation by new one, the behavior must not be changed.
## SQL
```sql
-- create MaterializedMySQL databases that read the events from the binlog client
CREATE DATABASE db1_client1 ENGINE = MaterializedMySQL('host:port', 'db', 'user', 'password') SETTINGS use_binlog_client=1, max_bytes_in_binlog_queue=1024;
CREATE DATABASE db2_client1 ENGINE = MaterializedMySQL('host:port', 'db', 'user', 'password') SETTINGS use_binlog_client=1;
CREATE DATABASE db3_client1 ENGINE = MaterializedMySQL('host:port', 'db2', 'user', 'password') SETTINGS use_binlog_client=1;
CREATE DATABASE db4_client2 ENGINE = MaterializedMySQL('host2:port', 'db', 'user', 'password') SETTINGS use_binlog_client=1;
CREATE DATABASE db5_client3 ENGINE = MaterializedMySQL('host:port', 'db', 'user1', 'password') SETTINGS use_binlog_client=1;
CREATE DATABASE db6_old ENGINE = MaterializedMySQL('host:port', 'db', 'user1', 'password') SETTINGS use_binlog_client=0;
```
Databases `db1_client1`, `db2_client1` and `db3_client1` share one instance of `BinlogClient` since they have the same params. `BinlogClient` will create 3 connections to MySQL server thus 3 instances of `BinlogEventsDispatcher`, but if these connections would have the same binlog position, they should be merged to one connection. Means all clients will be moved to one dispatcher and others will be closed. Databases `db4_client2` and `db5_client3` would use 2 different independent `BinlogClient` instances. Database `db6_old` will use old implementation. NOTE: By default `use_binlog_client` is disabled. Setting `max_bytes_in_binlog_queue` defines the max allowed bytes in the binlog queue. By default, it is `1073741824` bytes. If number of bytes exceeds this limit, the dispatching will be stopped until the space will be freed for new events.
## Binlog Table Structure
To see the status of the all `BinlogClient` instances there is `system.mysql_binlogs` system table. It shows the list of all created and _alive_ `IBinlog` instances with information about its `BinlogEventsDispatcher` and `BinlogClient`.
Example:
```
SELECT * FROM system.mysql_binlogs FORMAT Vertical
Row 1:
──────
binlog_client_name: root@127.0.0.1:3306
name: test_Clickhouse1
mysql_binlog_name: binlog.001154
mysql_binlog_pos: 7142294
mysql_binlog_timestamp: 1660082447
mysql_binlog_executed_gtid_set: a9d88f83-c14e-11ec-bb36-244bfedf7766:1-30523304
dispatcher_name: Applier
dispatcher_mysql_binlog_name: binlog.001154
dispatcher_mysql_binlog_pos: 7142294
dispatcher_mysql_binlog_timestamp: 1660082447
dispatcher_mysql_binlog_executed_gtid_set: a9d88f83-c14e-11ec-bb36-244bfedf7766:1-30523304
size: 0
bytes: 0
max_bytes: 0
```
### Tests
Unit tests:
```
$ ./unit_tests_dbms --gtest_filter=MySQLBinlog.*
```
Integration tests:
```
$ pytest -s -vv test_materialized_mysql_database/test.py::test_binlog_client
```
Dumps events from the file
```
$ ./utils/check-mysql-binlog/check-mysql-binlog --binlog binlog.001392
```
Dumps events from the server
```
$ ./utils/check-mysql-binlog/check-mysql-binlog --host 127.0.0.1 --port 3306 --user root --password pass --gtid a9d88f83-c14e-11ec-bb36-244bfedf7766:1-30462856
```

View File

@ -49,6 +49,18 @@ Default values are defined in [Settings.h](https://github.com/ClickHouse/ClickHo
See also the description of [max_memory_usage](#settings_max_memory_usage).
For example if you want to set `max_memory_usage_for_user` to 1000 bytes for a user named `clickhouse_read`, you can use the statement
``` sql
ALTER USER clickhouse_read SETTINGS max_memory_usage_for_user = 1000;
```
You can verify it worked by logging out of your client, logging back in, then use the `getSetting` function:
```sql
SELECT getSetting('max_memory_usage_for_user');
```
## max_rows_to_read {#max-rows-to-read}
The following restrictions can be checked on each block (instead of on each row). That is, the restrictions can be broken a little.

File diff suppressed because it is too large Load Diff

View File

@ -6,7 +6,7 @@ sidebar_label: User Settings
# Users and Roles Settings
The `users` section of the `user.xml` configuration file contains user settings.
The `users` section of the `users.xml` configuration file contains user settings.
:::note
ClickHouse also supports [SQL-driven workflow](../../guides/sre/user-management/index.md#access-control) for managing users. We recommend using it.

File diff suppressed because it is too large Load Diff

View File

@ -737,6 +737,14 @@ Number of sessions (connections) to ZooKeeper. Should be no more than one, becau
Number of watches (event subscriptions) in ZooKeeper.
### ConcurrencyControlAcquired
Total number of acquired CPU slots.
### ConcurrencyControlSoftLimit
Value of soft limit on number of CPU slots.
**See Also**
- [system.asynchronous_metrics](../../operations/system-tables/asynchronous_metrics.md#system_tables-asynchronous_metrics) — Contains periodically calculated metrics.

View File

@ -177,6 +177,26 @@ When you are ready to insert your files into ClickHouse, startup a ClickHouse se
:::
## Format Conversions
You can use `clickhouse-local` for converting data between different formats. Example:
``` bash
$ clickhouse-local --input-format JSONLines --output-format CSV --query "SELECT * FROM table" < data.json > data.csv
```
Formats are auto-detected from file extensions:
``` bash
$ clickhouse-local --query "SELECT * FROM table" < data.json > data.csv
```
As a shortcut, you can write it using the `--copy` argument:
``` bash
$ clickhouse-local --copy < data.json > data.csv
```
## Usage {#usage}
By default `clickhouse-local` has access to data of a ClickHouse server on the same host, and it does not depend on the server's configuration. It also supports loading server configuration using `--config-file` argument. For temporary data, a unique temporary data directory is created by default.

View File

@ -124,7 +124,7 @@ Converts an aggregate function for tables into an aggregate function for arrays
## -Distinct
Every unique combination of arguments will be aggregated only once. Repeating values are ignored.
Examples: `sum(DISTINCT x)`, `groupArray(DISTINCT x)`, `corrStableDistinct(DISTINCT x, y)` and so on.
Examples: `sum(DISTINCT x)` (or `sumDistinct(x)`), `groupArray(DISTINCT x)` (or `groupArrayDistinct(x)`), `corrStable(DISTINCT x, y)` (or `corrStableDistinct(x, y)`) and so on.
## -OrDefault

View File

@ -261,9 +261,10 @@ windowFunnel(window, [mode, [mode, ... ]])(timestamp, cond1, cond2, ..., condN)
- `window` — Length of the sliding window, it is the time interval between the first and the last condition. The unit of `window` depends on the `timestamp` itself and varies. Determined using the expression `timestamp of cond1 <= timestamp of cond2 <= ... <= timestamp of condN <= timestamp of cond1 + window`.
- `mode` — It is an optional argument. One or more modes can be set.
- `'strict_deduplication'` — If the same condition holds for the sequence of events, then such repeating event interrupts further processing.
- `'strict_deduplication'` — If the same condition holds for the sequence of events, then such repeating event interrupts further processing. Note: it may work unexpectedly if several conditions hold for the same event.
- `'strict_order'` — Don't allow interventions of other events. E.g. in the case of `A->B->D->C`, it stops finding `A->B->C` at the `D` and the max event level is 2.
- `'strict_increase'` — Apply conditions only to events with strictly increasing timestamps.
- `'strict_once'` — Count each event only once in the chain even if it meets the condition several times
**Returned value**
@ -490,7 +491,7 @@ Where:
## uniqUpTo(N)(x)
Calculates the number of different values of the argument up to a specified limit, `N`. If the number of different argument values is greater than `N`, this function returns `N` + 1, otherwise it calculates the exact value.
Calculates the number of different values of the argument up to a specified limit, `N`. If the number of different argument values is greater than `N`, this function returns `N` + 1, otherwise it calculates the exact value.
Recommended for use with small `N`s, up to 10. The maximum value of `N` is 100.
@ -522,7 +523,7 @@ This function behaves the same as [sumMap](../../sql-reference/aggregate-functio
- `keys`: [Array](../data-types/array.md) of keys.
- `values`: [Array](../data-types/array.md) of values.
**Returned Value**
**Returned Value**
- Returns a tuple of two arrays: keys in sorted order, and values summed for the corresponding keys.
@ -539,10 +540,10 @@ CREATE TABLE sum_map
)
ENGINE = Log
INSERT INTO sum_map VALUES
('2000-01-01', '2000-01-01 00:00:00', [1, 2, 3], [10, 10, 10]),
INSERT INTO sum_map VALUES
('2000-01-01', '2000-01-01 00:00:00', [1, 2, 3], [10, 10, 10]),
('2000-01-01', '2000-01-01 00:00:00', [3, 4, 5], [10, 10, 10]),
('2000-01-01', '2000-01-01 00:01:00', [4, 5, 6], [10, 10, 10]),
('2000-01-01', '2000-01-01 00:01:00', [4, 5, 6], [10, 10, 10]),
('2000-01-01', '2000-01-01 00:01:00', [6, 7, 8], [10, 10, 10]);
```
@ -572,7 +573,7 @@ This function behaves the same as [sumMap](../../sql-reference/aggregate-functio
- `keys`: [Array](../data-types/array.md) of keys.
- `values`: [Array](../data-types/array.md) of values.
**Returned Value**
**Returned Value**
- Returns a tuple of two arrays: keys in sorted order, and values summed for the corresponding keys.
@ -591,10 +592,10 @@ CREATE TABLE sum_map
)
ENGINE = Log
INSERT INTO sum_map VALUES
('2000-01-01', '2000-01-01 00:00:00', [1, 2, 3], [10, 10, 10]),
INSERT INTO sum_map VALUES
('2000-01-01', '2000-01-01 00:00:00', [1, 2, 3], [10, 10, 10]),
('2000-01-01', '2000-01-01 00:00:00', [3, 4, 5], [10, 10, 10]),
('2000-01-01', '2000-01-01 00:01:00', [4, 5, 6], [10, 10, 10]),
('2000-01-01', '2000-01-01 00:01:00', [4, 5, 6], [10, 10, 10]),
('2000-01-01', '2000-01-01 00:01:00', [6, 7, 8], [10, 10, 10]);
```

View File

@ -1,190 +0,0 @@
---
slug: /en/sql-reference/ansi
sidebar_position: 40
sidebar_label: ANSI Compatibility
title: "ANSI SQL Compatibility of ClickHouse SQL Dialect"
---
:::note
This article relies on Table 38, “Feature taxonomy and definition for mandatory features”, Annex F of [ISO/IEC CD 9075-2:2011](https://www.iso.org/obp/ui/#iso:std:iso-iec:9075:-2:ed-4:v1:en:sec:8).
:::
## Differences in Behaviour
The following table lists cases when query feature works in ClickHouse, but behaves not as specified in ANSI SQL.
| Feature ID | Feature Name | Difference |
|------------|-----------------------------|-----------------------------------------------------------------------------------------------------------|
| E011 | Numeric data types | Numeric literal with period is interpreted as approximate (`Float64`) instead of exact (`Decimal`) |
| E051-05 | Select items can be renamed | Item renames have a wider visibility scope than just the SELECT result |
| E141-01 | NOT NULL constraints | `NOT NULL` is implied for table columns by default |
| E011-04 | Arithmetic operators | ClickHouse overflows instead of checked arithmetic and changes the result data type based on custom rules |
## Feature Status
| Feature ID | Feature Name | Status | Comment |
|------------|--------------------------------------------------------------------------------------------------------------------------|----------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| **E011** | **Numeric data types** | <span class="text-warning">Partial</span> | |
| E011-01 | INTEGER and SMALLINT data types | <span class="text-success">Yes</span> | |
| E011-02 | REAL, DOUBLE PRECISION and FLOAT data types data types | <span class="text-success">Yes</span> | |
| E011-03 | DECIMAL and NUMERIC data types | <span class="text-success">Yes</span> | |
| E011-04 | Arithmetic operators | <span class="text-success">Yes</span> | |
| E011-05 | Numeric comparison | <span class="text-success">Yes</span> | |
| E011-06 | Implicit casting among the numeric data types | <span class="text-danger">No</span> | ANSI SQL allows arbitrary implicit cast between numeric types, while ClickHouse relies on functions having multiple overloads instead of implicit cast |
| **E021** | **Character string types** | <span class="text-warning">Partial</span> | |
| E021-01 | CHARACTER data type | <span class="text-success">Yes</span> | |
| E021-02 | CHARACTER VARYING data type | <span class="text-success">Yes</span> | |
| E021-03 | Character literals | <span class="text-success">Yes</span> | |
| E021-04 | CHARACTER_LENGTH function | <span class="text-warning">Partial</span> | No `USING` clause |
| E021-05 | OCTET_LENGTH function | <span class="text-danger">No</span> | `LENGTH` behaves similarly |
| E021-06 | SUBSTRING | <span class="text-warning">Partial</span> | No support for `SIMILAR` and `ESCAPE` clauses, no `SUBSTRING_REGEX` variant |
| E021-07 | Character concatenation | <span class="text-warning">Partial</span> | No `COLLATE` clause |
| E021-08 | UPPER and LOWER functions | <span class="text-success">Yes</span> | |
| E021-09 | TRIM function | <span class="text-success">Yes</span> | |
| E021-10 | Implicit casting among the fixed-length and variable-length character string types | <span class="text-warning">Partial</span> | ANSI SQL allows arbitrary implicit cast between string types, while ClickHouse relies on functions having multiple overloads instead of implicit cast |
| E021-11 | POSITION function | <span class="text-warning">Partial</span> | No support for `IN` and `USING` clauses, no `POSITION_REGEX` variant |
| E021-12 | Character comparison | <span class="text-success">Yes</span> | |
| **E031** | **Identifiers** | <span class="text-warning">Partial</span>| |
| E031-01 | Delimited identifiers | <span class="text-warning">Partial</span> | Unicode literal support is limited |
| E031-02 | Lower case identifiers | <span class="text-success">Yes</span> | |
| E031-03 | Trailing underscore | <span class="text-success">Yes</span> | |
| **E051** | **Basic query specification** | <span class="text-warning">Partial</span>| |
| E051-01 | SELECT DISTINCT | <span class="text-success">Yes</span> | |
| E051-02 | GROUP BY clause | <span class="text-success">Yes</span> | |
| E051-04 | GROUP BY can contain columns not in `<select list>` | <span class="text-success">Yes</span> | |
| E051-05 | Select items can be renamed | <span class="text-success">Yes</span> | |
| E051-06 | HAVING clause | <span class="text-success">Yes</span> | |
| E051-07 | Qualified \* in select list | <span class="text-success">Yes</span> | |
| E051-08 | Correlation name in the FROM clause | <span class="text-success">Yes</span> | |
| E051-09 | Rename columns in the FROM clause | <span class="text-danger">No</span> | |
| **E061** | **Basic predicates and search conditions** | <span class="text-warning">Partial</span> | |
| E061-01 | Comparison predicate | <span class="text-success">Yes</span> | |
| E061-02 | BETWEEN predicate | <span class="text-warning">Partial</span> | No `SYMMETRIC` and `ASYMMETRIC` clause |
| E061-03 | IN predicate with list of values | <span class="text-success">Yes</span> | |
| E061-04 | LIKE predicate | <span class="text-success">Yes</span> | |
| E061-05 | LIKE predicate: ESCAPE clause | <span class="text-danger">No</span> | |
| E061-06 | NULL predicate | <span class="text-success">Yes</span> | |
| E061-07 | Quantified comparison predicate | <span class="text-danger">No</span> | |
| E061-08 | EXISTS predicate | <span class="text-danger">No</span> | |
| E061-09 | Subqueries in comparison predicate | <span class="text-success">Yes</span> | |
| E061-11 | Subqueries in IN predicate | <span class="text-success">Yes</span> | |
| E061-12 | Subqueries in quantified comparison predicate | <span class="text-danger">No</span> | |
| E061-13 | Correlated subqueries | <span class="text-danger">No</span> | |
| E061-14 | Search condition | <span class="text-success">Yes</span> | |
| **E071** | **Basic query expressions** | <span class="text-warning">Partial</span> | |
| E071-01 | UNION DISTINCT table operator | <span class="text-success">Yes</span> | |
| E071-02 | UNION ALL table operator | <span class="text-success">Yes</span> | |
| E071-03 | EXCEPT DISTINCT table operator | <span class="text-danger">No</span> | |
| E071-05 | Columns combined via table operators need not have exactly the same data type | <span class="text-success">Yes</span> | |
| E071-06 | Table operators in subqueries | <span class="text-success">Yes</span> | |
| **E081** | **Basic privileges** | <span class="text-success">Yes</span> |
| E081-01 | SELECT privilege at the table level | <span class="text-success">Yes</span> |
| E081-02 | DELETE privilege | |
| E081-03 | INSERT privilege at the table level | <span class="text-success">Yes</span> |
| E081-04 | UPDATE privilege at the table level | <span class="text-success">Yes</span> |
| E081-05 | UPDATE privilege at the column level | |
| E081-06 | REFERENCES privilege at the table level | | |
| E081-07 | REFERENCES privilege at the column level | | |
| E081-08 | WITH GRANT OPTION | <span class="text-success">Yes</span> | |
| E081-09 | USAGE privilege | | |
| E081-10 | EXECUTE privilege | | |
| **E091** | **Set functions** |<span class="text-success">Yes</span> |
| E091-01 | AVG | <span class="text-success">Yes</span> | |
| E091-02 | COUNT | <span class="text-success">Yes</span> | |
| E091-03 | MAX | <span class="text-success">Yes</span> | |
| E091-04 | MIN | <span class="text-success">Yes</span> | |
| E091-05 | SUM | <span class="text-success">Yes</span> | |
| E091-06 | ALL quantifier | <span class="text-success">Yes</span> | |
| E091-07 | DISTINCT quantifier | <span class="text-success">Yes</span> | Not all aggregate functions supported |
| **E101** | **Basic data manipulation** | <span class="text-warning">Partial</span> | |
| E101-01 | INSERT statement | <span class="text-success">Yes</span> | Note: primary key in ClickHouse does not imply the `UNIQUE` constraint |
| E101-03 | Searched UPDATE statement | <span class="text-warning">Partial</span> | Theres an `ALTER UPDATE` statement for batch data modification |
| E101-04 | Searched DELETE statement | <span class="text-warning">Partial</span> | Theres an `ALTER DELETE` statement for batch data removal |
| **E111** | **Single row SELECT statement** | <span class="text-danger">No</span> | |
| **E121** | **Basic cursor support** | <span class="text-danger">No</span> | |
| E121-01 | DECLARE CURSOR | <span class="text-danger">No</span> | |
| E121-02 | ORDER BY columns need not be in select list | <span class="text-success">Yes</span> | |
| E121-03 | Value expressions in ORDER BY clause | <span class="text-success">Yes</span> | |
| E121-04 | OPEN statement | <span class="text-danger">No</span> | |
| E121-06 | Positioned UPDATE statement | <span class="text-danger">No</span> | |
| E121-07 | Positioned DELETE statement | <span class="text-danger">No</span> | |
| E121-08 | CLOSE statement | <span class="text-danger">No</span> | |
| E121-10 | FETCH statement: implicit NEXT | <span class="text-danger">No</span> | |
| E121-17 | WITH HOLD cursors | <span class="text-danger">No</span> | |
| **E131** | **Null value support (nulls in lieu of values)** | <span class="text-success">Yes</span> | Some restrictions apply |
| **E141** | **Basic integrity constraints** | <span class="text-warning">Partial</span> | |
| E141-01 | NOT NULL constraints | <span class="text-success">Yes</span> | Note: `NOT NULL` is implied for table columns by default |
| E141-02 | UNIQUE constraint of NOT NULL columns | <span class="text-danger">No</span> | |
| E141-03 | PRIMARY KEY constraints | <span class="text-warning">Partial</span> | |
| E141-04 | Basic FOREIGN KEY constraint with the NO ACTION default for both referential delete action and referential update action | <span class="text-danger">No</span> | |
| E141-06 | CHECK constraint | <span class="text-success">Yes</span> | |
| E141-07 | Column defaults | <span class="text-success">Yes</span> | |
| E141-08 | NOT NULL inferred on PRIMARY KEY | <span class="text-success">Yes</span> | |
| E141-10 | Names in a foreign key can be specified in any order | <span class="text-danger">No</span> | |
| **E151** | **Transaction support** | <span class="text-danger">No</span> | |
| E151-01 | COMMIT statement | <span class="text-danger">No</span> | |
| E151-02 | ROLLBACK statement | <span class="text-danger">No</span> | |
| **E152** | **Basic SET TRANSACTION statement** | <span class="text-danger">No</span> | |
| E152-01 | SET TRANSACTION statement: ISOLATION LEVEL SERIALIZABLE clause | <span class="text-danger">No</span> | |
| E152-02 | SET TRANSACTION statement: READ ONLY and READ WRITE clauses | <span class="text-danger">No</span> | |
| **E153** | **Updatable queries with subqueries** | <span class="text-success">Yes</span> | |
| **E161** | **SQL comments using leading double minus** | <span class="text-success">Yes</span> | |
| **E171** | **SQLSTATE support** | <span class="text-danger">No</span> | |
| **E182** | **Host language binding** | <span class="text-danger">No</span> | |
| **F031** | **Basic schema manipulation** | <span class="text-warning">Partial</span>| |
| F031-01 | CREATE TABLE statement to create persistent base tables | <span class="text-warning">Partial</span> | No `SYSTEM VERSIONING`, `ON COMMIT`, `GLOBAL`, `LOCAL`, `PRESERVE`, `DELETE`, `REF IS`, `WITH OPTIONS`, `UNDER`, `LIKE`, `PERIOD FOR` clauses and no support for user resolved data types |
| F031-02 | CREATE VIEW statement | <span class="text-warning">Partial</span> | No `RECURSIVE`, `CHECK`, `UNDER`, `WITH OPTIONS` clauses and no support for user resolved data types |
| F031-03 | GRANT statement | <span class="text-success">Yes</span> | |
| F031-04 | ALTER TABLE statement: ADD COLUMN clause | <span class="text-success">Yes</span> | No support for `GENERATED` clause and system time period |
| F031-13 | DROP TABLE statement: RESTRICT clause | <span class="text-danger">No</span> | |
| F031-16 | DROP VIEW statement: RESTRICT clause | <span class="text-danger">No</span> | |
| F031-19 | REVOKE statement: RESTRICT clause | <span class="text-danger">No</span> | |
| **F041** | **Basic joined table** | <span class="text-warning">Partial</span> | |
| F041-01 | Inner join (but not necessarily the INNER keyword) | <span class="text-success">Yes</span> | |
| F041-02 | INNER keyword | <span class="text-success">Yes</span> | |
| F041-03 | LEFT OUTER JOIN | <span class="text-success">Yes</span> | |
| F041-04 | RIGHT OUTER JOIN | <span class="text-success">Yes</span> | |
| F041-05 | Outer joins can be nested | <span class="text-success">Yes</span> | |
| F041-07 | The inner table in a left or right outer join can also be used in an inner join | <span class="text-success">Yes</span> | |
| F041-08 | All comparison operators are supported (rather than just =) | <span class="text-danger">No</span> | |
| **F051** | **Basic date and time** | <span class="text-warning">Partial</span> | |
| F051-01 | DATE data type (including support of DATE literal) | <span class="text-success">Yes</span> | |
| F051-02 | TIME data type (including support of TIME literal) with fractional seconds precision of at least 0 | <span class="text-danger">No</span> | |
| F051-03 | TIMESTAMP data type (including support of TIMESTAMP literal) with fractional seconds precision of at least 0 and 6 | <span class="text-success">Yes</span> | |
| F051-04 | Comparison predicate on DATE, TIME, and TIMESTAMP data types | <span class="text-success">Yes</span> | |
| F051-05 | Explicit CAST between datetime types and character string types | <span class="text-success">Yes</span> | |
| F051-06 | CURRENT_DATE | <span class="text-danger">No</span> | `today()` is similar |
| F051-07 | LOCALTIME | <span class="text-danger">No</span> | `now()` is similar |
| F051-08 | LOCALTIMESTAMP | <span class="text-danger">No</span> | |
| **F081** | **UNION and EXCEPT in views** | <span class="text-warning">Partial</span> | |
| **F131** | **Grouped operations** | <span class="text-warning">Partial</span> | |
| F131-01 | WHERE, GROUP BY, and HAVING clauses supported in queries with grouped views | <span class="text-success">Yes</span> | |
| F131-02 | Multiple tables supported in queries with grouped views | <span class="text-success">Yes</span> | |
| F131-03 | Set functions supported in queries with grouped views | <span class="text-success">Yes</span> | |
| F131-04 | Subqueries with GROUP BY and HAVING clauses and grouped views | <span class="text-success">Yes</span> | |
| F131-05 | Single row SELECT with GROUP BY and HAVING clauses and grouped views | <span class="text-danger">No</span> | |
| **F181** | **Multiple module support** | <span class="text-danger">No</span> | |
| **F201** | **CAST function** | <span class="text-success">Yes</span> | |
| **F221** | **Explicit defaults** | <span class="text-danger">No</span> | |
| **F261** | **CASE expression** | <span class="text-success">Yes</span> | |
| F261-01 | Simple CASE | <span class="text-success">Yes</span> | |
| F261-02 | Searched CASE | <span class="text-success">Yes</span> | |
| F261-03 | NULLIF | <span class="text-success">Yes</span> | |
| F261-04 | COALESCE | <span class="text-success">Yes</span> | |
| **F311** | **Schema definition statement** | <span class="text-warning">Partial</span> | |
| F311-01 | CREATE SCHEMA | <span class="text-warning">Partial</span> | See CREATE DATABASE |
| F311-02 | CREATE TABLE for persistent base tables | <span class="text-success">Yes</span> | |
| F311-03 | CREATE VIEW | <span class="text-success">Yes</span> | |
| F311-04 | CREATE VIEW: WITH CHECK OPTION | <span class="text-danger">No</span> | |
| F311-05 | GRANT statement | <span class="text-success">Yes</span> | |
| **F471** | **Scalar subquery values** | <span class="text-success">Yes</span> | |
| **F481** | **Expanded NULL predicate** | <span class="text-success">Yes</span> | |
| **F812** | **Basic flagging** | <span class="text-danger">No</span> | |
| **S011** | **Distinct data types** | | |
| **T321** | **Basic SQL-invoked routines** | <span class="text-danger">No</span> | |
| T321-01 | User-defined functions with no overloading | <span class="text-danger">No</span> | |
| T321-02 | User-defined stored procedures with no overloading | <span class="text-danger">No</span> | |
| T321-03 | Function invocation | <span class="text-danger">No</span> | |
| T321-04 | CALL statement | <span class="text-danger">No</span> | |
| T321-05 | RETURN statement | <span class="text-danger">No</span> | |
| **T631** | **IN predicate with one list element** | <span class="text-success">Yes</span> | |

View File

@ -86,7 +86,7 @@ The table below describes how different interval kinds of `Interval` data type a
### Aggregate function parameter binary encoding
The table below describes how parameters of `AggragateFunction` and `SimpleAggregateFunction` are encoded.
The table below describes how parameters of `AggregateFunction` and `SimpleAggregateFunction` are encoded.
The encoding of a parameter consists of 1 byte indicating the type of the parameter and the value itself.
| Parameter type | Binary encoding |
@ -106,7 +106,7 @@ The encoding of a parameter consists of 1 byte indicating the type of the parame
| `String` | `0x0C<var_uint_size><data>` |
| `Array` | `0x0D<var_uint_size><value_encoding_1>...<value_encoding_N>` |
| `Tuple` | `0x0E<var_uint_size><value_encoding_1>...<value_encoding_N>` |
| `Map` | `0x0F<var_uint_size><key_encoding_1><value_encoding_1>...<key_endoding_N><value_encoding_N>` |
| `Map` | `0x0F<var_uint_size><key_encoding_1><value_encoding_1>...<key_encoding_N><value_encoding_N>` |
| `IPv4` | `0x10<uint32_little_endian_value>` |
| `IPv6` | `0x11<uint128_little_endian_value>` |
| `UUID` | `0x12<uuid_value>` |

View File

@ -297,99 +297,257 @@ $$)
└───────────────┴────────────────┴───────────────┴──────┴───────┴────────────┴─────────┘
```
## Comparing values of Dynamic type
## Using Dynamic type in functions
Values of `Dynamic` types are compared similar to values of `Variant` type:
Most of the functions support arguments with type `Dynamic`. In this case the function is executed separately on each internal data type stored inside `Dynamic` column.
When the result type of the function depends on the arguments types, the result of such function executed with `Dynamic` arguments will be `Dynamic`. When the result type of the function doesn't depend on the arguments types - the result will be `Nullable(T)` where `T` the usual result type of this function.
Examples:
```sql
CREATE TABLE test (d Dynamic) ENGINE=Memory;
INSERT INTO test VALUES (NULL), (1::Int8), (2::Int16), (3::Int32), (4::Int64);
```
```sql
SELECT d, dynamicType(d) FROM test;
```
```text
┌─d────┬─dynamicType(d)─┐
│ ᴺᵁᴸᴸ │ None │
│ 1 │ Int8 │
│ 2 │ Int16 │
│ 3 │ Int32 │
│ 4 │ Int64 │
└──────┴────────────────┘
```
```sql
SELECT d, d + 1 AS res, toTypeName(res), dynamicType(res) FROM test;
```
```text
┌─d────┬─res──┬─toTypeName(res)─┬─dynamicType(res)─┐
│ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ Dynamic │ None │
│ 1 │ 2 │ Dynamic │ Int16 │
│ 2 │ 3 │ Dynamic │ Int32 │
│ 3 │ 4 │ Dynamic │ Int64 │
│ 4 │ 5 │ Dynamic │ Int64 │
└──────┴──────┴─────────────────┴──────────────────┘
```
```sql
SELECT d, d + d AS res, toTypeName(res), dynamicType(res) FROM test;
```
```text
┌─d────┬─res──┬─toTypeName(res)─┬─dynamicType(res)─┐
│ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ Dynamic │ None │
│ 1 │ 2 │ Dynamic │ Int16 │
│ 2 │ 4 │ Dynamic │ Int32 │
│ 3 │ 6 │ Dynamic │ Int64 │
│ 4 │ 8 │ Dynamic │ Int64 │
└──────┴──────┴─────────────────┴──────────────────┘
```
```sql
SELECT d, d < 3 AS res, toTypeName(res) FROM test;
```
```text
┌─d────┬──res─┬─toTypeName(res)─┐
│ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ Nullable(UInt8) │
│ 1 │ 1 │ Nullable(UInt8) │
│ 2 │ 1 │ Nullable(UInt8) │
│ 3 │ 0 │ Nullable(UInt8) │
│ 4 │ 0 │ Nullable(UInt8) │
└──────┴──────┴─────────────────┘
```
```sql
SELECT d, exp2(d) AS res, toTypeName(res) FROM test;
```
```sql
┌─d────┬──res─┬─toTypeName(res)───┐
│ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ Nullable(Float64) │
│ 1 │ 2 │ Nullable(Float64) │
│ 2 │ 4 │ Nullable(Float64) │
│ 3 │ 8 │ Nullable(Float64) │
│ 4 │ 16 │ Nullable(Float64) │
└──────┴──────┴───────────────────┘
```
```sql
TRUNCATE TABLE test;
INSERT INTO test VALUES (NULL), ('str_1'), ('str_2');
SELECT d, dynamicType(d) FROM test;
```
```text
┌─d─────┬─dynamicType(d)─┐
│ ᴺᵁᴸᴸ │ None │
│ str_1 │ String │
│ str_2 │ String │
└───────┴────────────────┘
```
```sql
SELECT d, upper(d) AS res, toTypeName(res) FROM test;
```
```text
┌─d─────┬─res───┬─toTypeName(res)──┐
│ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ Nullable(String) │
│ str_1 │ STR_1 │ Nullable(String) │
│ str_2 │ STR_2 │ Nullable(String) │
└───────┴───────┴──────────────────┘
```
```sql
SELECT d, extract(d, '([0-3])') AS res, toTypeName(res) FROM test;
```
```text
┌─d─────┬─res──┬─toTypeName(res)──┐
│ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ Nullable(String) │
│ str_1 │ 1 │ Nullable(String) │
│ str_2 │ 2 │ Nullable(String) │
└───────┴──────┴──────────────────┘
```
```sql
TRUNCATE TABLE test;
INSERT INTO test VALUES (NULL), ([1, 2]), ([3, 4]);
SELECT d, dynamicType(d) FROM test;
```
```text
┌─d─────┬─dynamicType(d)─┐
│ ᴺᵁᴸᴸ │ None │
│ [1,2] │ Array(Int64) │
│ [3,4] │ Array(Int64) │
└───────┴────────────────┘
```
```sql
SELECT d, d[1] AS res, toTypeName(res), dynamicType(res) FROM test;
```
```text
┌─d─────┬─res──┬─toTypeName(res)─┬─dynamicType(res)─┐
│ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ Dynamic │ None │
│ [1,2] │ 1 │ Dynamic │ Int64 │
│ [3,4] │ 3 │ Dynamic │ Int64 │
└───────┴──────┴─────────────────┴──────────────────┘
```
If function cannot be executed on some type inside `Dynamic` column, the exception will be thrown:
```sql
INSERT INTO test VALUES (42), (43), ('str_1');
SELECT d, dynamicType(d) FROM test;
```
```text
┌─d─────┬─dynamicType(d)─┐
│ 42 │ Int64 │
│ 43 │ Int64 │
│ str_1 │ String │
└───────┴────────────────┘
┌─d─────┬─dynamicType(d)─┐
│ ᴺᵁᴸᴸ │ None │
│ [1,2] │ Array(Int64) │
│ [3,4] │ Array(Int64) │
└───────┴────────────────┘
```
```sql
SELECT d, d + 1 AS res, toTypeName(res), dynamicType(d) FROM test;
```
```text
Received exception:
Code: 43. DB::Exception: Illegal types Array(Int64) and UInt8 of arguments of function plus: while executing 'FUNCTION plus(__table1.d : 3, 1_UInt8 :: 1) -> plus(__table1.d, 1_UInt8) Dynamic : 0'. (ILLEGAL_TYPE_OF_ARGUMENT)
```
We can filter out unneeded types:
```sql
SELECT d, d + 1 AS res, toTypeName(res), dynamicType(res) FROM test WHERE dynamicType(d) NOT IN ('String', 'Array(Int64)', 'None')
```
```text
┌─d──┬─res─┬─toTypeName(res)─┬─dynamicType(res)─┐
│ 42 │ 43 │ Dynamic │ Int64 │
│ 43 │ 44 │ Dynamic │ Int64 │
└────┴─────┴─────────────────┴──────────────────┘
```
Or extract required type as subcolumn:
```sql
SELECT d, d.Int64 + 1 AS res, toTypeName(res) FROM test;
```
```text
┌─d─────┬──res─┬─toTypeName(res)─┐
│ 42 │ 43 │ Nullable(Int64) │
│ 43 │ 44 │ Nullable(Int64) │
│ str_1 │ ᴺᵁᴸᴸ │ Nullable(Int64) │
└───────┴──────┴─────────────────┘
┌─d─────┬──res─┬─toTypeName(res)─┐
│ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ Nullable(Int64) │
│ [1,2] │ ᴺᵁᴸᴸ │ Nullable(Int64) │
│ [3,4] │ ᴺᵁᴸᴸ │ Nullable(Int64) │
└───────┴──────┴─────────────────┘
```
## Using Dynamic type in ORDER BY and GROUP BY
During `ORDER BY` and `GROUP BY` values of `Dynamic` types are compared similar to values of `Variant` type:
The result of operator `<` for values `d1` with underlying type `T1` and `d2` with underlying type `T2` of a type `Dynamic` is defined as follows:
- If `T1 = T2 = T`, the result will be `d1.T < d2.T` (underlying values will be compared).
- If `T1 != T2`, the result will be `T1 < T2` (type names will be compared).
Examples:
```sql
CREATE TABLE test (d1 Dynamic, d2 Dynamic) ENGINE=Memory;
INSERT INTO test VALUES (42, 42), (42, 43), (42, 'abc'), (42, [1, 2, 3]), (42, []), (42, NULL);
CREATE TABLE test (d Dynamic) ENGINE=Memory;
INSERT INTO test VALUES (42), (43), ('abc'), ('abd'), ([1, 2, 3]), ([]), (NULL);
```
```sql
SELECT d2, dynamicType(d2) as d2_type from test order by d2;
SELECT d, dynamicType(d) FROM test;
```
```text
┌─d2──────┬─d2_type──────┐
│ [] │ Array(Int64) │
│ [1,2,3] │ Array(Int64) │
│ 42 │ Int64 │
│ 43 │ Int64 │
│ abc │ String │
│ ᴺᵁᴸᴸ │ None │
└─────────┴──────────────┘
┌─d───────┬─dynamicType(d)─┐
│ 42 │ Int64 │
│ 43 │ Int64 │
│ abc │ String │
│ abd │ String │
│ [1,2,3] │ Array(Int64) │
│ [] │ Array(Int64) │
│ ᴺᵁᴸᴸ │ None │
└─────────┴────────────────┘
```
```sql
SELECT d1, dynamicType(d1) as d1_type, d2, dynamicType(d2) as d2_type, d1 = d2, d1 < d2, d1 > d2 from test;
```
```text
┌─d1─┬─d1_type─┬─d2──────┬─d2_type──────┬─equals(d1, d2)─┬─less(d1, d2)─┬─greater(d1, d2)─┐
│ 42 │ Int64 │ 42 │ Int64 │ 1 │ 0 │ 0 │
│ 42 │ Int64 │ 43 │ Int64 │ 0 │ 1 │ 0 │
│ 42 │ Int64 │ abc │ String │ 0 │ 1 │ 0 │
│ 42 │ Int64 │ [1,2,3] │ Array(Int64) │ 0 │ 0 │ 1 │
│ 42 │ Int64 │ [] │ Array(Int64) │ 0 │ 0 │ 1 │
│ 42 │ Int64 │ ᴺᵁᴸᴸ │ None │ 0 │ 1 │ 0 │
└────┴─────────┴─────────┴──────────────┴────────────────┴──────────────┴─────────────────┘
```
If you need to find the row with specific `Dynamic` value, you can do one of the following:
- Cast value to the `Dynamic` type:
```sql
SELECT * FROM test WHERE d2 == [1,2,3]::Array(UInt32)::Dynamic;
```
```text
┌─d1─┬─d2──────┐
│ 42 │ [1,2,3] │
└────┴─────────┘
```
- Compare `Dynamic` subcolumn with required type:
```sql
SELECT * FROM test WHERE d2.`Array(Int65)` == [1,2,3] -- or using variantElement(d2, 'Array(UInt32)')
```
```text
┌─d1─┬─d2──────┐
│ 42 │ [1,2,3] │
└────┴─────────┘
```
Sometimes it can be useful to make additional check on dynamic type as subcolumns with complex types like `Array/Map/Tuple` cannot be inside `Nullable` and will have default values instead of `NULL` on rows with different types:
```sql
SELECT d2, d2.`Array(Int64)`, dynamicType(d2) FROM test WHERE d2.`Array(Int64)` == [];
```
```text
┌─d2───┬─d2.Array(UInt32)─┬─dynamicType(d2)─┐
│ 42 │ [] │ Int64 │
│ 43 │ [] │ Int64 │
│ abc │ [] │ String │
│ [] │ [] │ Array(Int32) │
│ ᴺᵁᴸᴸ │ [] │ None │
└──────┴──────────────────┴─────────────────┘
SELECT d, dynamicType(d) FROM test ORDER BY d;
```
```sql
SELECT d2, d2.`Array(Int64)`, dynamicType(d2) FROM test WHERE dynamicType(d2) == 'Array(Int64)' AND d2.`Array(Int64)` == [];
```
```text
┌─d2─┬─d2.Array(UInt32)─┬─dynamicType(d2)─┐
│ [] │ [] │ Array(Int64) │
└────┴──────────────────┴─────────────────┘
┌─d───────┬─dynamicType(d)─┐
│ [] │ Array(Int64) │
│ [1,2,3] │ Array(Int64) │
│ 42 │ Int64 │
│ 43 │ Int64 │
│ abc │ String │
│ abd │ String │
│ ᴺᵁᴸᴸ │ None │
└─────────┴────────────────┘
```
**Note:** values of dynamic types with different numeric types are considered as different values and not compared between each other, their type names are compared instead.
@ -411,6 +569,21 @@ SELECT d, dynamicType(d) FROM test ORDER by d;
└─────┴────────────────┘
```
```sql
SELECT d, dynamicType(d) FROM test GROUP by d;
```
```text
┌─d───┬─dynamicType(d)─┐
│ 1 │ Int64 │
│ 100 │ UInt32 │
│ 1 │ UInt32 │
│ 100 │ Int64 │
└─────┴────────────────┘
```
**Note**: the described comparison rule is not applied during execution of comparison functions like `<`/`>`/`=` and others because of [special work](#using-dynamic-type-in-functions) of functions with `Dynamic` type
## Reaching the limit in number of different data types stored inside Dynamic
`Dynamic` data type can store only limited number of different data types as separate subcolumns. By default, this limit is 32, but you can change it in type declaration using syntax `Dynamic(max_types=N)` where N is between 0 and 254 (due to implementation details, it's impossible to have more than 254 different data types that can be stored as separate subcolumns inside Dynamic).

View File

@ -1972,7 +1972,7 @@ Result:
## toISOYear
Converts a date, or date with time, to a UInt16 number containing the ISO Year number.
Converts a date, or date with time, to the ISO year as a UInt16 number.
**Syntax**
@ -1982,11 +1982,11 @@ toISOYear(value)
**Arguments**
- `value` — The value with date or date with time.
- `value` — The value with date or date with time. [Date](../data-types/date.md), [Date32](../data-types/date32.md), [DateTime](../data-types/datetime.md) or [DateTime64](../data-types/datetime64.md)
**Returned value**
- `value` converted to the current ISO year number. [UInt16](../data-types/int-uint.md).
- The input value converted to a ISO year number. [UInt16](../data-types/int-uint.md).
**Example**
@ -1995,7 +1995,7 @@ Query:
```sql
SELECT
toISOYear(toDate('2024/10/02')) as year1,
toISOYear(toDateTime('2024/10/02 01:30:00')) as year2
toISOYear(toDateTime('2024-10-02 01:30:00')) as year2
```
Result:
@ -2010,6 +2010,38 @@ Result:
Converts a date, or date with time, to a UInt8 number containing the ISO Week number.
**Syntax**
```sql
toISOWeek(value)
```
**Arguments**
- `value` — The value with date or date with time.
**Returned value**
- `value` converted to the current ISO week number. [UInt8](../data-types/int-uint.md).
**Example**
Query:
```sql
SELECT
toISOWeek(toDate('2024/10/02')) AS week1,
toISOWeek(toDateTime('2024/10/02 01:30:00')) AS week2
```
Response:
```response
┌─week1─┬─week2─┐
│ 40 │ 40 │
└───────┴───────┘
```
## toWeek
This function returns the week number for date or datetime. The two-argument form of `toWeek()` enables you to specify whether the week starts on Sunday or Monday and whether the return value should be in the range from 0 to 53 or from 1 to 53. If the mode argument is omitted, the default mode is 0.
@ -2901,7 +2933,42 @@ The same as today() - 1.
## timeSlot
Rounds the time to the half hour.
Round the time to the start of a half-an-hour length interval.
**Syntax**
```sql
timeSlot(time[, time_zone])
```
**Arguments**
- `time` — Time to round to the start of a half-an-hour length interval. [DateTime](../data-types/datetime.md)/[Date32](../data-types/date32.md)/[DateTime64](../data-types/datetime64.md).
- `time_zone` — A String type const value or an expression representing the time zone. [String](../data-types/string.md).
:::note
Though this function can take values of the extended types `Date32` and `DateTime64` as an argument, passing it a time outside the normal range (year 1970 to 2149 for `Date` / 2106 for `DateTime`) will produce wrong results.
:::
**Return type**
- Returns the time rounded to the start of a half-an-hour length interval. [DateTime](../data-types/datetime.md).
**Example**
Query:
```sql
SELECT timeSlot(toDateTime('2000-01-02 03:04:05', 'UTC'));
```
Result:
```response
┌─timeSlot(toDateTime('2000-01-02 03:04:05', 'UTC'))─┐
│ 2000-01-02 03:00:00 │
└────────────────────────────────────────────────────┘
```
## toYYYYMM

View File

@ -244,24 +244,42 @@ SELECT IPv6CIDRToRange(toIPv6('2001:0db8:0000:85a3:0000:0000:ac1f:8001'), 32);
└────────────────────────────────────────────────────────────────────────┘
```
## toIPv4(string)
## toIPv4
An alias to `IPv4StringToNum()` that takes a string form of IPv4 address and returns value of [IPv4](../data-types/ipv4.md) type, which is binary equal to value returned by `IPv4StringToNum()`.
Like [`IPv4StringToNum`](##IPv4NumToString(num)) but takes a string form of IPv4 address and returns value of [IPv4](../data-types/ipv4.md) type.
**Syntax**
```sql
toIPv4(string)
```
**Arguments**
- `string` — IPv4 address. [String](../data-types/string.md).
**Returned value**
- `string` converted to the IPv4 address. [IPv4](../data-types/ipv4.md).
**Examples**
Query:
``` sql
WITH
'171.225.130.45' as IPv4_string
SELECT
toTypeName(IPv4StringToNum(IPv4_string)),
toTypeName(toIPv4(IPv4_string))
SELECT toIPv4('171.225.130.45');
```
Result:
``` text
┌─toTypeName(IPv4StringToNum(IPv4_string))─┬─toTypeName(toIPv4(IPv4_string))─┐
│ UInt32 │ IPv4 │
└──────────────────────────────────────────┴─────────────────────────────────┘
┌─toIPv4('171.225.130.45')─┐
171.225.130.45
└──────────────────────────┘
```
Query:
``` sql
WITH
'171.225.130.45' as IPv4_string
@ -270,91 +288,124 @@ SELECT
hex(toIPv4(IPv4_string))
```
Result:
``` text
┌─hex(IPv4StringToNum(IPv4_string))─┬─hex(toIPv4(IPv4_string))─┐
│ ABE1822D │ ABE1822D │
└───────────────────────────────────┴──────────────────────────┘
```
## toIPv4OrDefault(string)
## toIPv4OrDefault
Same as `toIPv4`, but if the IPv4 address has an invalid format, it returns `0.0.0.0` (0 IPv4).
Same as `toIPv4`, but if the IPv4 address has an invalid format, it returns `0.0.0.0` (0 IPv4), or the provided IPv4 default.
**Syntax**
```sql
toIPv4OrDefault(value)
toIPv4OrDefault(string[, default])
```
**Arguments**
- `value` — The value with IPv4 address.
- `value` — IP address. [String](../data-types/string.md).
- `default` (optional) — The value to return if `string` has an invalid format. [IPv4](../data-types/ipv4.md).
**Returned value**
- `value` converted to the current IPv4 address. [String](../data-types/string.md).
- `string` converted to the current IPv4 address. [String](../data-types/string.md).
**Example**
Query:
```sql
WITH
'::ffff:127.0.0.1' AS valid_IPv6_string,
'fe80:2030:31:24' AS invalid_IPv6_string
SELECT
toIPv4OrDefault('192.168.0.1') AS s1,
toIPv4OrDefault('192.168.0') AS s2
toIPv4OrDefault(valid_IPv6_string) AS valid,
toIPv4OrDefault(invalid_IPv6_string) AS default,
toIPv4OrDefault(invalid_IPv6_string, toIPv4('1.1.1.1')) AS provided_default;
```
Result:
```response
┌─s1──────────┬─s2──────┐
192.168.0.1 │ 0.0.0.0
└─────────────┴─────────┘
┌─valid───┬─default─┬─provided_default─┐
0.0.0.0 │ 0.0.0.0 │ 1.1.1.1
└─────────┴─────────┴──────────────────┘
```
## toIPv4OrNull(string)
## toIPv4OrNull
Same as `toIPv4`, but if the IPv4 address has an invalid format, it returns null.
Same as [`toIPv4`](#toipv4), but if the IPv4 address has an invalid format, it returns null.
**Syntax**
```sql
toIPv4OrNull(value)
toIPv4OrNull(string)
```
**Arguments**
- `value` — The value with IPv4 address.
- `string` — IP address. [String](../data-types/string.md).
**Returned value**
- `value` converted to the current IPv4 address. [String](../data-types/string.md).
- `string` converted to the current IPv4 address, or null if `string` is an invalid address. [String](../data-types/string.md).
**Example**
Query:
```sql
SELECT
toIPv4OrNull('192.168.0.1') AS s1,
toIPv4OrNull('192.168.0') AS s2
``` sql
WITH 'fe80:2030:31:24' AS invalid_IPv6_string
SELECT toIPv4OrNull(invalid_IPv6_string);
```
Result:
```response
┌─s1──────────┬─s2───┐
│ 192.168.0.1 │ ᴺᵁᴸᴸ │
└───────────────────┘
``` text
┌─toIPv4OrNull(invalid_IPv6_string)─┐
│ ᴺᵁᴸᴸ
└───────────────────────────────────┘
```
## toIPv6OrDefault(string)
## toIPv4OrZero
Same as `toIPv6`, but if the IPv6 address has an invalid format, it returns `::` (0 IPv6).
Same as [`toIPv4`](#toipv4), but if the IPv4 address has an invalid format, it returns `0.0.0.0`.
## toIPv6OrNull(string)
**Syntax**
Same as `toIPv6`, but if the IPv6 address has an invalid format, it returns null.
```sql
toIPv4OrZero(string)
```
**Arguments**
- `string` — IP address. [String](../data-types/string.md).
**Returned value**
- `string` converted to the current IPv4 address, or `0.0.0.0` if `string` is an invalid address. [String](../data-types/string.md).
**Example**
Query:
``` sql
WITH 'Not an IP address' AS invalid_IPv6_string
SELECT toIPv4OrZero(invalid_IPv6_string);
```
Result:
``` text
┌─toIPv4OrZero(invalid_IPv6_string)─┐
│ 0.0.0.0 │
└───────────────────────────────────┘
```
## toIPv6
@ -371,7 +422,7 @@ toIPv6(string)
**Argument**
- `string` — IP address. [String](../data-types/string.md)
- `string` — IP address. [String](../data-types/string.md).
**Returned value**
@ -410,6 +461,117 @@ Result:
└─────────────────────┘
```
## toIPv6OrDefault
Same as [`toIPv6`](#toipv6), but if the IPv6 address has an invalid format, it returns `::` (0 IPv6) or the provided IPv6 default.
**Syntax**
```sql
toIPv6OrDefault(string[, default])
```
**Argument**
- `string` — IP address. [String](../data-types/string.md).
- `default` (optional) — The value to return if `string` has an invalid format. [IPv6](../data-types/ipv6.md).
**Returned value**
- IPv6 address [IPv6](../data-types/ipv6.md), otherwise `::` or the provided optional default if `string` has an invalid format.
**Example**
Query:
``` sql
WITH
'127.0.0.1' AS valid_IPv4_string,
'127.0.0.1.6' AS invalid_IPv4_string
SELECT
toIPv6OrDefault(valid_IPv4_string) AS valid,
toIPv6OrDefault(invalid_IPv4_string) AS default,
toIPv6OrDefault(invalid_IPv4_string, toIPv6('1.1.1.1')) AS provided_default
```
Result:
``` text
┌─valid────────────┬─default─┬─provided_default─┐
│ ::ffff:127.0.0.1 │ :: │ ::ffff:1.1.1.1 │
└──────────────────┴─────────┴──────────────────┘
```
## toIPv6OrNull
Same as [`toIPv6`](#toipv6), but if the IPv6 address has an invalid format, it returns null.
**Syntax**
```sql
toIPv6OrNull(string)
```
**Argument**
- `string` — IP address. [String](../data-types/string.md).
**Returned value**
- IP address. [IPv6](../data-types/ipv6.md), or null if `string` is not a valid format.
**Example**
Query:
``` sql
WITH '127.0.0.1.6' AS invalid_IPv4_string
SELECT toIPv6OrNull(invalid_IPv4_string);
```
Result:
``` text
┌─toIPv6OrNull(invalid_IPv4_string)─┐
│ ᴺᵁᴸᴸ │
└───────────────────────────────────┘
```
## toIPv6OrZero
Same as [`toIPv6`](#toipv6), but if the IPv6 address has an invalid format, it returns `::`.
**Syntax**
```sql
toIPv6OrZero(string)
```
**Argument**
- `string` — IP address. [String](../data-types/string.md).
**Returned value**
- IP address. [IPv6](../data-types/ipv6.md), or `::` if `string` is not a valid format.
**Example**
Query:
``` sql
WITH '127.0.0.1.6' AS invalid_IPv4_string
SELECT toIPv6OrZero(invalid_IPv4_string);
```
Result:
``` text
┌─toIPv6OrZero(invalid_IPv4_string)─┐
│ :: │
└───────────────────────────────────┘
```
## IPv6StringToNumOrDefault(s)
Same as `toIPv6`, but if the IPv6 address has an invalid format, it returns 0.

View File

@ -202,7 +202,7 @@ Result:
Returns the type name of the passed argument.
If `NULL` is passed, then the function returns type `Nullable(Nothing)`, which corresponds to ClickHouse's internal `NULL` representation.
If `NULL` is passed, the function returns type `Nullable(Nothing)`, which corresponds to ClickHouse's internal `NULL` representation.
**Syntax**
@ -212,11 +212,11 @@ toTypeName(value)
**Arguments**
- `value`The value with any arbitrary.
- `value`A value of arbitrary type.
**Returned value**
- `value` converted to the current data type name. [String](../data-types/string.md).
- The data type name of the input value. [String](../data-types/string.md).
**Example**
@ -410,13 +410,37 @@ Code: 44. DB::Exception: Received from localhost:9000. DB::Exception: Illegal ty
## ignore
Accepts any arguments, including `NULL` and does nothing. Always returns 0.
The argument is internally still evaluated. Useful e.g. for benchmarks.
Accepts arbitrary arguments and unconditionally returns `0`.
The argument is still evaluated internally, making it useful for eg. benchmarking.
**Syntax**
```sql
ignore(x)
ignore([arg1[, arg2[, ...]])
```
**Arguments**
- Accepts arbitrarily many arguments of arbitrary type, including `NULL`.
**Returned value**
- Returns `0`.
**Example**
Query:
```sql
SELECT ignore(0, 'ClickHouse', NULL);
```
Result:
```response
┌─ignore(0, 'ClickHouse', NULL)─┐
│ 0 │
└───────────────────────────────┘
```
## sleep
@ -524,13 +548,9 @@ Useful in table engine parameters of `CREATE TABLE` queries where you need to sp
currentDatabase()
```
**Arguments**
None.
**Returned value**
- `value` returns the current database name. [String](../data-types/string.md).
- Returns the current database name. [String](../data-types/string.md).
**Example**
@ -579,6 +599,42 @@ Result:
└───────────────┘
```
## currentSchemas
Returns a single-element array with the name of the current database schema.
**Syntax**
```sql
currentSchemas(bool)
```
Alias: `current_schemas`.
**Arguments**
- `bool`: A boolean value. [Bool](../data-types/boolean.md).
:::note
The boolean argument is ignored. It only exists for the sake of compatibility with the [implementation](https://www.postgresql.org/docs/7.3/functions-misc.html) of this function in PostgreSQL.
:::
**Returned values**
- Returns a single-element array with the name of the current database
**Example**
```sql
SELECT currentSchemas(true);
```
Result:
```response
['default']
```
## isConstant
Returns whether the argument is a constant expression.
@ -1821,7 +1877,7 @@ toColumnTypeName(value)
**Example**
Difference between `toTypeName ' and ' toColumnTypeName`:
Difference between `toTypeName` and `toColumnTypeName`:
```sql
SELECT toTypeName(CAST('2018-01-01 01:02:03' AS DateTime))
@ -3897,13 +3953,15 @@ Retrieves the connection ID of the client that submitted the current query and r
connectionId()
```
Alias: `connection_id`.
**Parameters**
None.
**Returned value**
Returns an integer of type UInt64.
The current connection ID. [UInt64](../data-types/int-uint.md).
**Implementation details**
@ -3921,40 +3979,6 @@ SELECT connectionId();
0
```
## connection_id
An alias of `connectionId`. Retrieves the connection ID of the client that submitted the current query and returns it as a UInt64 integer.
**Syntax**
```sql
connection_id()
```
**Parameters**
None.
**Returned value**
Returns an integer of type UInt64.
**Implementation details**
This function is most useful in debugging scenarios or for internal purposes within the MySQL handler. It was created for compatibility with [MySQL's `CONNECTION_ID` function](https://dev.mysql.com/doc/refman/8.0/en/information-functions.html#function_connection-id) It is not typically used in production queries.
**Example**
Query:
```sql
SELECT connection_id();
```
```response
0
```
## getClientHTTPHeader
Get the value of an HTTP header.
@ -4366,3 +4390,37 @@ Result:
1. │ ['{ArraySizes}','{ArrayElements, TupleElement(keys), Regular}','{ArrayElements, TupleElement(values), Regular}'] │
└──────────────────────────────────────────────────────────────────────────────────────────────────────────────────┘
```
## globalVariable
Takes constant string argument and returns the value of global variable with that name. It is intended for compatibility with MySQL.
**Syntax**
```sql
globalVariable(name)
```
**Arguments**
- `name` — Global variable name. [String](../data-types/string.md).
**Returned value**
- Returns the value of variable `name`.
**Example**
Query:
```sql
SELECT globalVariable('max_allowed_packet');
```
Result:
```response
┌─globalVariable('max_allowed_packet')─┐
│ 67108864 │
└──────────────────────────────────────┘
```

View File

@ -24,7 +24,7 @@ Returns a random UInt32 number with uniform distribution.
Uses a linear congruential generator with an initial state obtained from the system, which means that while it appears random, it's not truly random and can be predictable if the initial state is known. For scenarios where true randomness is crucial, consider using alternative methods like system-level calls or integrating with external libraries.
### Syntax
**Syntax**
```sql
rand()
@ -32,15 +32,15 @@ rand()
Alias: `rand32`
### Arguments
**Arguments**
None.
### Returned value
**Returned value**
Returns a number of type UInt32.
### Example
**Example**
```sql
SELECT rand();
@ -54,23 +54,23 @@ SELECT rand();
Returns a random UInt64 integer (UInt64) number
### Syntax
**Syntax**
```sql
rand64()
```
### Arguments
**Arguments**
None.
### Returned value
**Arguments**
Returns a number UInt64 number with uniform distribution.
Uses a linear congruential generator with an initial state obtained from the system, which means that while it appears random, it's not truly random and can be predictable if the initial state is known. For scenarios where true randomness is crucial, consider using alternative methods like system-level calls or integrating with external libraries.
### Example
**Example**
```sql
SELECT rand64();
@ -84,21 +84,21 @@ SELECT rand64();
Returns a random Float64 number.
### Syntax
**Syntax**
```sql
randCanonical()
```
### Arguments
**Arguments**
None.
### Returned value
**Arguments**
Returns a Float64 value between 0 (inclusive) and 1 (exclusive).
### Example
**Example**
```sql
SELECT randCanonical();
@ -112,25 +112,25 @@ SELECT randCanonical();
Generates a single constant column filled with a random value. Unlike `rand`, this function ensures the same random value appears in every row of the generated column, making it useful for scenarios requiring a consistent random seed across rows in a single query.
### Syntax
**Syntax**
```sql
randConstant([x]);
```
### Arguments
**Arguments**
- **[x] (Optional):** An optional expression that influences the generated random value. Even if provided, the resulting value will still be constant within the same query execution. Different queries using the same expression will likely generate different constant values.
### Returned value
**Arguments**
Returns a column of type UInt32 containing the same random value in each row.
### Implementation details
**Implementation details**
The actual output will be different for each query execution, even with the same optional expression. The optional parameter may not significantly change the generated value compared to using `randConstant` alone.
### Examples
**Example**
```sql
SELECT randConstant() AS random_value;
@ -156,22 +156,22 @@ SELECT randConstant(10) AS random_value;
Returns a random Float64 drawn uniformly from interval [`min`, `max`].
### Syntax
**Syntax**
```sql
randUniform(min, max)
```
### Arguments
**Arguments**
- `min` - `Float64` - left boundary of the range,
- `max` - `Float64` - right boundary of the range.
### Returned value
**Arguments**
A random number of type [Float64](../data-types/float.md).
### Example
**Example**
```sql
SELECT randUniform(5.5, 10) FROM numbers(5)

View File

@ -1096,7 +1096,7 @@ convertCharset(s, from, to)
## base58Encode
Encodes a String using [Base58](https://datatracker.ietf.org/doc/html/draft-msporny-base58) in the "Bitcoin" alphabet.
Encodes a string using [Base58](https://datatracker.ietf.org/doc/html/draft-msporny-base58) in the "Bitcoin" alphabet.
**Syntax**
@ -1110,7 +1110,7 @@ base58Encode(plaintext)
**Returned value**
- A string containing the encoded value of the argument. [String](../data-types/string.md).
- A string containing the encoded value of the argument. [String](../data-types/string.md) or [FixedString](../data-types/fixedstring.md).
**Example**
@ -1128,7 +1128,7 @@ Result:
## base58Decode
Accepts a String and decodes it using [Base58](https://datatracker.ietf.org/doc/html/draft-msporny-base58) 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**
@ -1138,7 +1138,7 @@ base58Decode(encoded)
**Arguments**
- `encoded` — [String](../data-types/string.md) column or constant. If the string is not a valid Base58-encoded value, an exception is thrown.
- `encoded` — [String](../data-types/string.md) or [FixedString](../data-types/fixedstring.md). If the string is not a valid Base58-encoded value, an exception is thrown.
**Returned value**
@ -1170,7 +1170,7 @@ tryBase58Decode(encoded)
**Parameters**
- `encoded`: [String](../data-types/string.md) column or constant. If the string is not a valid Base58-encoded value, returns an empty string in case of error.
- `encoded`: [String](../data-types/string.md) or [FixedString](../data-types/fixedstring.md). If the string is not a valid Base58-encoded value, returns an empty string in case of error.
**Returned value**

View File

@ -755,7 +755,7 @@ Result:
## match {#match}
Returns whether string `haystack` matches the regular expression `pattern` in [re2 regular syntax](https://github.com/google/re2/wiki/Syntax).
Returns whether string `haystack` matches the regular expression `pattern` in [re2 regular expression syntax](https://github.com/google/re2/wiki/Syntax).
Matching is based on UTF-8, e.g. `.` matches the Unicode code point `¥` which is represented in UTF-8 using two bytes. The regular
expression must not contain null bytes. If the haystack or the pattern are not valid UTF-8, then the behavior is undefined.
@ -852,9 +852,10 @@ multiFuzzyMatchAllIndices(haystack, distance, \[pattern<sub>1</sub>, pattern<sub
## extract
Extracts a fragment of a string using a regular expression. If `haystack` does not match the `pattern` regex, an empty string is returned.
Returns the first match of a regular expression in a string.
If `haystack` does not match the `pattern` regex, an empty string is returned.
For regex without subpatterns, the function uses the fragment that matches the entire regex. Otherwise, it uses the fragment that matches the first subpattern.
If the regular expression has capturing groups, the function matches the input string against the first capturing group.
**Syntax**
@ -862,13 +863,36 @@ For regex without subpatterns, the function uses the fragment that matches the e
extract(haystack, pattern)
```
*Arguments**
- `haystack` — Input string. [String](../data-types/string.md).
- `pattern` — Regular expression with [re2 regular expression syntax](https://github.com/google/re2/wiki/Syntax).
**Returned value**
- The first match of the regular expression in the haystack string. [String](../data-types/string.md).
**Example**
Query:
```sql
SELECT extract('number: 1, number: 2, number: 3', '\\d+') AS result;
```
Result:
```response
┌─result─┐
│ 1 │
└────────┘
```
## extractAll
Extracts all fragments of a string using a regular expression. If `haystack` does not match the `pattern` regex, an empty string is returned.
Returns an array of all matches of a regular expression in a string. If `haystack` does not match the `pattern` regex, an empty string is returned.
Returns an array of strings consisting of all matches of the regex.
The behavior with respect to subpatterns is the same as in function `extract`.
The behavior with respect to sub-patterns is the same as in function [`extract`](#extract).
**Syntax**
@ -876,6 +900,31 @@ The behavior with respect to subpatterns is the same as in function `extract`.
extractAll(haystack, pattern)
```
*Arguments**
- `haystack` — Input string. [String](../data-types/string.md).
- `pattern` — Regular expression with [re2 regular expression syntax](https://github.com/google/re2/wiki/Syntax).
**Returned value**
- Array of matches of the regular expression in the haystack string. [Array](../data-types/array.md)([String](../data-types/string.md)).
**Example**
Query:
```sql
SELECT extractAll('number: 1, number: 2, number: 3', '\\d+') AS result;
```
Result:
```response
┌─result────────┐
│ ['1','2','3'] │
└───────────────┘
```
## extractAllGroupsHorizontal
Matches all groups of the `haystack` string using the `pattern` regular expression. Returns an array of arrays, where the first array includes all fragments matching the first group, the second array - matching the second group, etc.
@ -891,7 +940,7 @@ extractAllGroupsHorizontal(haystack, pattern)
**Arguments**
- `haystack` — Input string. [String](../data-types/string.md).
- `pattern` — Regular expression with [re2 syntax](https://github.com/google/re2/wiki/Syntax). Must contain groups, each group enclosed in parentheses. If `pattern` contains no groups, an exception is thrown. [String](../data-types/string.md).
- `pattern` — Regular expression with [re2 regular expression syntax](https://github.com/google/re2/wiki/Syntax). Must contain groups, each group enclosed in parentheses. If `pattern` contains no groups, an exception is thrown. [String](../data-types/string.md).
**Returned value**
@ -915,6 +964,39 @@ Result:
└──────────────────────────────────────────────────────────────────────────────────────────┘
```
## extractGroups
Match all groups of given input string with a given regular expression, returns an array of arrays of matches.
**Syntax**
``` sql
extractGroups(haystack, pattern)
```
**Arguments**
- `haystack` — Input string. [String](../data-types/string.md).
- `pattern` — Regular expression with [re2 regular expression syntax](https://github.com/google/re2/wiki/Syntax). Must contain groups, each group enclosed in parentheses. If `pattern` contains no groups, an exception is thrown. [String](../data-types/string.md).
**Returned value**
- Array of arrays of matches. [Array](../data-types/array.md).
**Example**
``` sql
SELECT extractGroups('hello abc=111 world', '("[^"]+"|\\w+)=("[^"]+"|\\w+)') AS result;
```
Result:
``` text
┌─result────────┐
│ ['abc','111'] │
└───────────────┘
```
## extractAllGroupsVertical
Matches all groups of the `haystack` string using the `pattern` regular expression. Returns an array of arrays, where each array includes matching fragments from every group. Fragments are grouped in order of appearance in the `haystack`.
@ -928,7 +1010,7 @@ extractAllGroupsVertical(haystack, pattern)
**Arguments**
- `haystack` — Input string. [String](../data-types/string.md).
- `pattern` — Regular expression with [re2 syntax](https://github.com/google/re2/wiki/Syntax). Must contain groups, each group enclosed in parentheses. If `pattern` contains no groups, an exception is thrown. [String](../data-types/string.md).
- `pattern` — Regular expression with [re2 regular expression syntax](https://github.com/google/re2/wiki/Syntax). Must contain groups, each group enclosed in parentheses. If `pattern` contains no groups, an exception is thrown. [String](../data-types/string.md).
**Returned value**
@ -1484,7 +1566,7 @@ countMatches(haystack, pattern)
**Arguments**
- `haystack` — The string to search in. [String](../../sql-reference/syntax.md#syntax-string-literal).
- `pattern` — The regular expression with [re2 syntax](https://github.com/google/re2/wiki/Syntax). [String](../data-types/string.md).
- `pattern` — The regular expression with [re2 regular expression syntax](https://github.com/google/re2/wiki/Syntax). [String](../data-types/string.md).
**Returned value**
@ -1529,7 +1611,7 @@ countMatchesCaseInsensitive(haystack, pattern)
**Arguments**
- `haystack` — The string to search in. [String](../../sql-reference/syntax.md#syntax-string-literal).
- `pattern` — The regular expression with [re2 syntax](https://github.com/google/re2/wiki/Syntax). [String](../data-types/string.md).
- `pattern` — The regular expression with [re2 regular expression syntax](https://github.com/google/re2/wiki/Syntax). [String](../data-types/string.md).
**Returned value**

View File

@ -5230,15 +5230,52 @@ Result:
Also see the `toUnixTimestamp` function.
## toFixedString(s, N)
## toFixedString
Converts a [String](../data-types/string.md) type argument to a [FixedString(N)](../data-types/fixedstring.md) type (a string of fixed length N).
If the string has fewer bytes than N, it is padded with null bytes to the right. If the string has more bytes than N, an exception is thrown.
## toStringCutToZero(s)
**Syntax**
```sql
toFixedString(s, N)
```
**Arguments**
- `s` — A String to convert to a fixed string. [String](../data-types/string.md).
- `N` — Length N. [UInt8](../data-types/int-uint.md)
**Returned value**
- An N length fixed string of `s`. [FixedString](../data-types/fixedstring.md).
**Example**
Query:
``` sql
SELECT toFixedString('foo', 8) AS s;
```
Result:
```response
┌─s─────────────┐
│ foo\0\0\0\0\0 │
└───────────────┘
```
## toStringCutToZero
Accepts a String or FixedString argument. Returns the String with the content truncated at the first zero byte found.
**Syntax**
```sql
toStringCutToZero(s)
```
**Example**
Query:

View File

@ -41,7 +41,7 @@ ORDER BY ts, event_type;
│ 2020-01-02 00:00:00 │ imp │ 2 │
└─────────────────────┴────────────┴─────────────────┘
-- Let's add the new measurment `cost`
-- Let's add the new measurement `cost`
-- and the new dimension `browser`.
ALTER TABLE events

View File

@ -46,7 +46,7 @@ The `CHECK TABLE` query supports the following table engines:
- [StripeLog](../../engines/table-engines/log-family/stripelog.md)
- [MergeTree family](../../engines/table-engines/mergetree-family/mergetree.md)
Performed over the tables with another table engines causes an `NOT_IMPLEMETED` exception.
Performed over the tables with another table engines causes an `NOT_IMPLEMENTED` exception.
Engines from the `*Log` family do not provide automatic data recovery on failure. Use the `CHECK TABLE` query to track data loss in a timely manner.

View File

@ -442,7 +442,7 @@ DEFLATE_QPL is not available in ClickHouse Cloud.
### Specialized Codecs
These codecs are designed to make compression more effective by exploiting specific features of the data. Some of these codecs do not compress data themself, they instead preprocess the data such that a second compression stage using a general-purpose codec can achieve a higher data compression rate.
These codecs are designed to make compression more effective by exploiting specific features of the data. Some of these codecs do not compress data themselves, they instead preprocess the data such that a second compression stage using a general-purpose codec can achieve a higher data compression rate.
#### Delta

View File

@ -194,7 +194,7 @@ REFRESH EVERY 1 MONTH OFFSET 5 DAY 2 HOUR -- on 6th day of every month, at 2:00
REFRESH EVERY 2 WEEK OFFSET 5 DAY 15 HOUR 10 MINUTE -- every other Saturday, at 3:10 pm
REFRESH EVERY 30 MINUTE -- at 00:00, 00:30, 01:00, 01:30, etc
REFRESH AFTER 30 MINUTE -- 30 minutes after the previous refresh completes, no alignment with time of day
-- REFRESH AFTER 1 HOUR OFFSET 1 MINUTE -- syntax errror, OFFSET is not allowed with AFTER
-- REFRESH AFTER 1 HOUR OFFSET 1 MINUTE -- syntax error, OFFSET is not allowed with AFTER
REFRESH EVERY 1 WEEK 2 DAYS -- every 9 days, not on any particular day of the week or month;
-- specifically, when day number (since 1969-12-29) is divisible by 9
REFRESH EVERY 5 MONTHS -- every 5 months, different months each year (as 12 is not divisible by 5);

View File

@ -121,6 +121,14 @@ However, you can delete old data using `ALTER TABLE ... DROP PARTITION`.
To insert a default value instead of `NULL` into a column with not nullable data type, enable [insert_null_as_default](../../operations/settings/settings.md#insert_null_as_default) setting.
`INSERT` also supports CTE(common table expression). For example, the following two statements are equivalent:
``` sql
INSERT INTO x WITH y AS (SELECT * FROM numbers(10)) SELECT * FROM y;
WITH y AS (SELECT * FROM numbers(10)) INSERT INTO x SELECT * FROM y;
```
## Inserting Data from a File
**Syntax**

View File

@ -29,7 +29,7 @@ The condition could be any expression based on your requirements.
Here is a simple example that intersects the numbers 1 to 10 with the numbers 3 to 8:
```sql
SELECT number FROM numbers(1,10) INTERSECT SELECT number FROM numbers(3,6);
SELECT number FROM numbers(1,10) INTERSECT SELECT number FROM numbers(3,8);
```
Result:

View File

@ -351,11 +351,15 @@ Shows privileges for a user.
**Syntax**
``` sql
SHOW GRANTS [FOR user1 [, user2 ...]]
SHOW GRANTS [FOR user1 [, user2 ...]] [WITH IMPLICIT] [FINAL]
```
If user is not specified, the query returns privileges for the current user.
The `WITH IMPLICIT` modifier allows to show the implicit grants (e.g., `GRANT SELECT ON system.one`)
The `FINAL` modifier merges all grants from the user and its granted roles (with inheritance)
## SHOW CREATE USER
Shows parameters that were used at a [user creation](../../sql-reference/statements/create/user.md).

View File

@ -18,9 +18,9 @@ generateRandom(['name TypeName[, name TypeName]...', [, 'random_seed'[, 'max_str
- `name` — Name of corresponding column.
- `TypeName` — Type of corresponding column.
- `max_array_length` — Maximum elements for all generated arrays or maps. Defaults to `10`.
- `max_string_length` — Maximum string length for all generated strings. Defaults to `10`.
- `random_seed` — Specify random seed manually to produce stable results. If NULL — seed is randomly generated.
- `max_string_length` — Maximum string length for all generated strings. Defaults to `10`.
- `max_array_length` — Maximum elements for all generated arrays or maps. Defaults to `10`.
**Returned Value**

View File

@ -6,7 +6,7 @@ sidebar_label: iceberg
# iceberg Table Function
Provides a read-only table-like interface to Apache [Iceberg](https://iceberg.apache.org/) tables in Amazon S3, Azure or locally stored.
Provides a read-only table-like interface to Apache [Iceberg](https://iceberg.apache.org/) tables in Amazon S3, Azure, HDFS or locally stored.
## Syntax
@ -17,13 +17,16 @@ icebergS3(named_collection[, option=value [,..]])
icebergAzure(connection_string|storage_account_url, container_name, blobpath, [,account_name], [,account_key] [,format] [,compression_method])
icebergAzure(named_collection[, option=value [,..]])
icebergHDFS(path_to_table, [,format] [,compression_method])
icebergHDFS(named_collection[, option=value [,..]])
icebergLocal(path_to_table, [,format] [,compression_method])
icebergLocal(named_collection[, option=value [,..]])
```
## Arguments
Description of the arguments coincides with description of arguments in table functions `s3`, `azureBlobStorage` and `file` correspondingly.
Description of the arguments coincides with description of arguments in table functions `s3`, `azureBlobStorage`, `HDFS` and `file` correspondingly.
`format` stands for the format of data files in the Iceberg table.
**Returned value**
@ -36,7 +39,7 @@ SELECT * FROM icebergS3('http://test.s3.amazonaws.com/clickhouse-bucket/test_tab
```
:::important
ClickHouse currently supports reading v1 and v2 of the Iceberg format via the `icebergS3`, `icebergAzure` and `icebergLocal` table functions and `IcebergS3`, `icebergAzure` ans `icebergLocal` table engines.
ClickHouse currently supports reading v1 and v2 of the Iceberg format via the `icebergS3`, `icebergAzure`, `icebergHDFS` and `icebergLocal` table functions and `IcebergS3`, `icebergAzure`, `IcebergHDFS` and `IcebergLocal` table engines.
:::
## Defining a named collection

View File

@ -1,2 +0,0 @@
# Just an empty yaml file. Keep it alone.
{}

View File

@ -7,190 +7,3 @@ sidebar_label: "[experimental] MaterializedMySQL"
# [экспериментальный] MaterializedMySQL {#materialized-mysql}
**Это экспериментальный движок, который не следует использовать в продакшене.**
Создает базу данных ClickHouse со всеми таблицами, существующими в MySQL, и всеми данными в этих таблицах.
Сервер ClickHouse работает как реплика MySQL. Он читает файл binlog и выполняет DDL and DML-запросы.
## Создание базы данных {#creating-a-database}
``` sql
CREATE DATABASE [IF NOT EXISTS] db_name [ON CLUSTER cluster]
ENGINE = MaterializedMySQL('host:port', ['database' | database], 'user', 'password') [SETTINGS ...]
```
**Параметры движка**
- `host:port` — адрес сервера MySQL.
- `database` — имя базы данных на удалённом сервере.
- `user` — пользователь MySQL.
- `password` — пароль пользователя.
**Настройки движка**
- `max_rows_in_buffer` — максимальное количество строк, содержимое которых может кешироваться в памяти (для одной таблицы и данных кеша, которые невозможно запросить). При превышении количества строк, данные будут материализованы. Значение по умолчанию: `65 505`.
- `max_bytes_in_buffer` — максимальное количество байтов, которое разрешено кешировать в памяти (для одной таблицы и данных кеша, которые невозможно запросить). При превышении количества строк, данные будут материализованы. Значение по умолчанию: `1 048 576`.
- `max_rows_in_buffers` — максимальное количество строк, содержимое которых может кешироваться в памяти (для базы данных и данных кеша, которые невозможно запросить). При превышении количества строк, данные будут материализованы. Значение по умолчанию: `65 505`.
- `max_bytes_in_buffers` — максимальное количество байтов, которое разрешено кешировать данным в памяти (для базы данных и данных кеша, которые невозможно запросить). При превышении количества строк, данные будут материализованы. Значение по умолчанию: `1 048 576`.
- `max_flush_data_time` — максимальное время в миллисекундах, в течение которого разрешено кешировать данные в памяти (для базы данных и данных кеша, которые невозможно запросить). При превышении количества указанного периода, данные будут материализованы. Значение по умолчанию: `1000`.
- `max_wait_time_when_mysql_unavailable` — интервал между повторными попытками, если MySQL недоступен. Указывается в миллисекундах. Отрицательное значение отключает повторные попытки. Значение по умолчанию: `1000`.
- `allows_query_when_mysql_lost` — признак, разрешен ли запрос к материализованной таблице при потере соединения с MySQL. Значение по умолчанию: `0` (`false`).
```sql
CREATE DATABASE mysql ENGINE = MaterializedMySQL('localhost:3306', 'db', 'user', '***')
SETTINGS
allows_query_when_mysql_lost=true,
max_wait_time_when_mysql_unavailable=10000;
```
**Настройки на стороне MySQL-сервера**
Для правильной работы `MaterializedMySQL` следует обязательно указать на сервере MySQL следующие параметры конфигурации:
- `default_authentication_plugin = mysql_native_password``MaterializedMySQL` может авторизоваться только с помощью этого метода.
- `gtid_mode = on` — ведение журнала на основе GTID является обязательным для обеспечения правильной репликации.
:::note Внимание
При включении `gtid_mode` вы также должны указать `enforce_gtid_consistency = on`.
:::
## Виртуальные столбцы {#virtual-columns}
При работе с движком баз данных `MaterializedMySQL` используются таблицы семейства [ReplacingMergeTree](../../engines/table-engines/mergetree-family/replacingmergetree.md) с виртуальными столбцами `_sign` и `_version`.
- `_version` — счетчик транзакций. Тип [UInt64](../../sql-reference/data-types/int-uint.md).
- `_sign` — метка удаления. Тип [Int8](../../sql-reference/data-types/int-uint.md). Возможные значения:
- `1` — строка не удалена,
- `-1` — строка удалена.
## Поддержка типов данных {#data_types-support}
| MySQL | ClickHouse |
|-------------------------|--------------------------------------------------------------|
| TINY | [Int8](../../sql-reference/data-types/int-uint.md) |
| SHORT | [Int16](../../sql-reference/data-types/int-uint.md) |
| INT24 | [Int32](../../sql-reference/data-types/int-uint.md) |
| LONG | [UInt32](../../sql-reference/data-types/int-uint.md) |
| LONGLONG | [UInt64](../../sql-reference/data-types/int-uint.md) |
| FLOAT | [Float32](../../sql-reference/data-types/float.md) |
| DOUBLE | [Float64](../../sql-reference/data-types/float.md) |
| DECIMAL, NEWDECIMAL | [Decimal](../../sql-reference/data-types/decimal.md) |
| DATE, NEWDATE | [Date](../../sql-reference/data-types/date.md) |
| DATETIME, TIMESTAMP | [DateTime](../../sql-reference/data-types/datetime.md) |
| DATETIME2, TIMESTAMP2 | [DateTime64](../../sql-reference/data-types/datetime64.md) |
| ENUM | [Enum](../../sql-reference/data-types/enum.md) |
| STRING | [String](../../sql-reference/data-types/string.md) |
| VARCHAR, VAR_STRING | [String](../../sql-reference/data-types/string.md) |
| BLOB | [String](../../sql-reference/data-types/string.md) |
| BINARY | [FixedString](../../sql-reference/data-types/fixedstring.md) |
Тип [Nullable](../../sql-reference/data-types/nullable.md) поддерживается.
Другие типы не поддерживаются. Если таблица MySQL содержит столбец другого типа, ClickHouse выдаст исключение "Неподдерживаемый тип данных" ("Unhandled data type") и остановит репликацию.
## Особенности и рекомендации {#specifics-and-recommendations}
### Ограничения совместимости {#compatibility-restrictions}
Кроме ограничений на типы данных, существует несколько ограничений по сравнению с базами данных MySQL, которые следует решить до того, как станет возможной репликация:
- Каждая таблица в MySQL должна содержать `PRIMARY KEY`.
- Репликация для таблиц, содержащих строки со значениями полей `ENUM` вне диапазона значений (определяется размерностью `ENUM`), не будет работать.
### DDL-запросы {#ddl-queries}
DDL-запросы в MySQL конвертируются в соответствующие DDL-запросы в ClickHouse ([ALTER](../../sql-reference/statements/alter/index.md), [CREATE](../../sql-reference/statements/create/index.md), [DROP](../../sql-reference/statements/drop.md), [RENAME](../../sql-reference/statements/rename.md)). Если ClickHouse не может конвертировать какой-либо DDL-запрос, он его игнорирует.
### Репликация данных {#data-replication}
Данные являются неизменяемыми со стороны пользователя ClickHouse, но автоматически обновляются путём репликации следующих запросов из MySQL:
- Запрос `INSERT` конвертируется в ClickHouse в `INSERT` с `_sign=1`.
- Запрос `DELETE` конвертируется в ClickHouse в `INSERT` с `_sign=-1`.
- Запрос `UPDATE` конвертируется в ClickHouse в `INSERT` с `_sign=-1` и `INSERT` с `_sign=1`.
### Выборка из таблиц движка MaterializedMySQL {#select}
Запрос `SELECT` из таблиц движка `MaterializedMySQL` имеет некоторую специфику:
- Если в запросе `SELECT` напрямую не указан столбец `_version`, то используется модификатор [FINAL](../../sql-reference/statements/select/from.md#select-from-final). Таким образом, выбираются только строки с `MAX(_version)`.
- Если в запросе `SELECT` напрямую не указан столбец `_sign`, то по умолчанию используется `WHERE _sign=1`. Таким образом, удаленные строки не включаются в результирующий набор.
- Результат включает комментарии к столбцам, если они существуют в таблицах базы данных MySQL.
### Конвертация индексов {#index-conversion}
Секции `PRIMARY KEY` и `INDEX` в MySQL конвертируются в кортежи `ORDER BY` в таблицах ClickHouse.
В таблицах ClickHouse данные физически хранятся в том порядке, который определяется секцией `ORDER BY`. Чтобы физически перегруппировать данные, используйте [материализованные представления](../../sql-reference/statements/create/view.md#materialized).
**Примечание**
- Строки с `_sign=-1` физически не удаляются из таблиц.
- Каскадные запросы `UPDATE/DELETE` не поддерживаются движком `MaterializedMySQL`.
- Репликация может быть легко нарушена.
- Прямые операции изменения данных в таблицах и базах данных `MaterializedMySQL` запрещены.
- На работу `MaterializedMySQL` влияет настройка [optimize_on_insert](../../operations/settings/settings.md#optimize-on-insert). Когда таблица на MySQL сервере меняется, происходит слияние данных в соответсвующей таблице в базе данных `MaterializedMySQL`.
## Примеры использования {#examples-of-use}
Запросы в MySQL:
``` sql
mysql> CREATE DATABASE db;
mysql> CREATE TABLE db.test (a INT PRIMARY KEY, b INT);
mysql> INSERT INTO db.test VALUES (1, 11), (2, 22);
mysql> DELETE FROM db.test WHERE a=1;
mysql> ALTER TABLE db.test ADD COLUMN c VARCHAR(16);
mysql> UPDATE db.test SET c='Wow!', b=222;
mysql> SELECT * FROM test;
```
```text
+---+------+------+
| a | b | c |
+---+------+------+
| 2 | 222 | Wow! |
+---+------+------+
```
База данных в ClickHouse, обмен данными с сервером MySQL:
База данных и созданная таблица:
``` sql
CREATE DATABASE mysql ENGINE = MaterializedMySQL('localhost:3306', 'db', 'user', '***');
SHOW TABLES FROM mysql;
```
``` text
┌─name─┐
│ test │
└──────┘
```
После вставки данных:
``` sql
SELECT * FROM mysql.test;
```
``` text
┌─a─┬──b─┐
│ 1 │ 11 │
│ 2 │ 22 │
└───┴────┘
```
После удаления данных, добавления столбца и обновления:
``` sql
SELECT * FROM mysql.test;
```
``` text
┌─a─┬───b─┬─c────┐
│ 2 │ 222 │ Wow! │
└───┴─────┴──────┘
```

View File

@ -9,6 +9,19 @@ sidebar_label: "Визуальные интерфейсы от сторонни
## С открытым исходным кодом {#s-otkrytym-iskhodnym-kodom}
### ChartDB {#chartdb}
[ChartDB](https://chartdb.io) — бесплатный и открытый инструмент для визуализации и проектирования схем баз данных, включая ClickHouse, с помощью одного запроса. Разработан на базе React, обеспечивает удобный и простой интерфейс, не требует ввода учетных данных или регистрации.
Основные возможности:
- Визуализация схем: мгновенно импортируйте и визуализируйте схему ClickHouse, включая ER-диаграммы с материализованными представлениями и стандартными представлениями, показывающими ссылки на таблицы;
- Экспорт DDL с поддержкой ИИ: легко генерируйте DDL-скрипты для лучшего управления и документирования схем;
- Поддержка различных SQL-диалектов: совместим с широким спектром SQL-диалектов, что делает его универсальным для разных сред баз данных;
- Без регистрации и учетных данных: весь функционал доступен прямо в браузере, обеспечивая бесшовное и безопасное использование.
[Исходный код ChartDB](https://github.com/chartdb/chartdb).
### Tabix {#tabix}
Веб-интерфейс для ClickHouse в проекте [Tabix](https://github.com/tabixio/tabix).

View File

@ -33,7 +33,7 @@ sidebar_label: "Отличительные возможности ClickHouse"
## Поддержка SQL {#sql-support}
ClickHouse поддерживает [декларативный язык запросов на основе SQL](../sql-reference/index.md) и во [многих случаях](../sql-reference/ansi.mdx) совпадающий с SQL-стандартом.
ClickHouse поддерживает декларативный язык запросов SQL.
Поддерживаются [GROUP BY](../sql-reference/statements/select/group-by.md), [ORDER BY](../sql-reference/statements/select/order-by.md), подзапросы в секциях [FROM](../sql-reference/statements/select/from.md), [IN](../sql-reference/operators/in.md), [JOIN](../sql-reference/statements/select/join.md), [функции window](../sql-reference/window-functions/index.mdx), а также скалярные подзапросы.

View File

@ -6,7 +6,7 @@ sidebar_label: "Настройки пользователей"
# Настройки пользователей {#nastroiki-polzovatelei}
Раздел `users` конфигурационного файла `user.xml` содержит настройки для пользователей.
Раздел `users` конфигурационного файла `users.xml` содержит настройки для пользователей.
:::note Информация
Для управления пользователями рекомендуется использовать [SQL-ориентированный воркфлоу](../access-rights.md#access-control), который также поддерживается в ClickHouse.
@ -30,7 +30,7 @@ sidebar_label: "Настройки пользователей"
<profile>profile_name</profile>
<quota>default</quota>
<default_database>default<default_database>
<default_database>default</default_database>
<databases>
<database_name>
<table_name>

View File

@ -93,7 +93,7 @@ WITH anySimpleState(number) AS c SELECT toTypeName(c), c FROM numbers(1);
## -Distinct {#agg-functions-combinator-distinct}
При наличии комбинатора Distinct, каждое уникальное значение аргументов, будет учитано в агрегатной функции только один раз.
Примеры: `sum(DISTINCT x)`, `groupArray(DISTINCT x)`, `corrStableDistinct(DISTINCT x, y)` и т.п.
Примеры: `sum(DISTINCT x)` (или `sumDistinct(x)`), `groupArray(DISTINCT x)` (или `groupArrayDistinct(x)`), `corrStable(DISTINCT x, y)` (или `corrStableDistinct(x, y)`) и т.п.
## -OrDefault {#agg-functions-combinator-ordefault}

View File

@ -1,10 +0,0 @@
---
slug: /ru/sql-reference/ansi
sidebar_position: 40
sidebar_label: ANSI Compatibility
title: "ANSI Compatibility"
---
import Content from '@site/docs/en/sql-reference/ansi.md';
<Content />

View File

@ -464,7 +464,7 @@ GRANT INSERT(x,y) ON db.table TO john
- `FILE`. Уровень: `GLOBAL`
- `URL`. Уровень: `GLOBAL`
- `REMOTE`. Уровень: `GLOBAL`
- `YSQL`. Уровень: `GLOBAL`
- `MYSQL`. Уровень: `GLOBAL`
- `ODBC`. Уровень: `GLOBAL`
- `JDBC`. Уровень: `GLOBAL`
- `HDFS`. Уровень: `GLOBAL`

View File

@ -29,7 +29,7 @@ FROM table2
Запрос:
``` sql
SELECT number FROM numbers(1,10) INTERSECT SELECT number FROM numbers(3,6);
SELECT number FROM numbers(1,10) INTERSECT SELECT number FROM numbers(3,8);
```
Результат:

View File

@ -234,11 +234,14 @@ SHOW DICTIONARIES FROM db LIKE '%reg%' LIMIT 2
### Синтаксис {#show-grants-syntax}
``` sql
SHOW GRANTS [FOR user]
SHOW GRANTS [FOR user1 [, user2 ...]] [WITH IMPLICIT] [FINAL]
```
Если пользователь не задан, запрос возвращает привилегии текущего пользователя.
`WITH IMPLICIT` добавляет неявные привилегии (например `GRANT SELECT ON system.one`).
`FINAL` объединяет все текущие привилегии с привилегиями всех ролей пользователя (с наследованием).
## SHOW CREATE USER {#show-create-user-statement}

View File

@ -18,9 +18,9 @@ generateRandom('name TypeName[, name TypeName]...', [, 'random_seed'[, 'max_stri
- `name` — название соответствующего столбца.
- `TypeName` — тип соответствующего столбца.
- `max_array_length` — максимальная длина массива для всех сгенерированных массивов. По умолчанию `10`.
- `max_string_length` — максимальная длина строки для всех генерируемых строк. По умолчанию `10`.
- `random_seed` — укажите состояние генератора случайных чисел вручную, чтобы получить стабильные результаты. Если значение равно `NULL` - генератор инициализируется случайным состоянием.
- `max_string_length` — максимальная длина строки для всех генерируемых строк. По умолчанию `10`.
- `max_array_length` — максимальная длина массива для всех сгенерированных массивов. По умолчанию `10`.
**Возвращаемое значение**

View File

@ -5,6 +5,19 @@ slug: /zh/interfaces/third-party/gui
## 开源 {#kai-yuan}
### ChartDB {#chartdb}
ClickHouse 的数据库模式可视化工具 [ChartDB](https://chartdb.io)。
主要功能:
- 一键导入并可视化 ClickHouse 模式,包括带有物化视图和标准视图的 ER 图表,并显示表之间的引用关系。
- 支持 AI 驱动的 DDL 导出功能,便于数据库模式管理和文档生成。
- 支持多种 SQL 方言,适用于各种数据库环境。
- 直接在浏览器中使用,无需数据库凭证或注册,使用简单且安全。
[ChartDB 源代码](https://github.com/chartdb/chartdb).
### Tabix {#tabix}
ClickHouse Web 界面 [Tabix](https://github.com/tabixio/tabix).

View File

@ -37,7 +37,7 @@ ClickHouse会使用服务器上一切可用的资源从而以最自然的方
## 支持SQL {#zhi-chi-sql}
ClickHouse支持一种[基于SQL的声明式查询语言](../sql-reference/index.md),它在许多情况下与[ANSI SQL标准](../sql-reference/ansi.md)相同
ClickHouse支持一种基于SQL的声明式查询语言。
支持的查询[GROUP BY](../sql-reference/statements/select/group-by.md), [ORDER BY](../sql-reference/statements/select/order-by.md), [FROM](../sql-reference/statements/select/from.md), [JOIN](../sql-reference/statements/select/join.md), [IN](../sql-reference/operators/in.md)以及非相关子查询。

View File

@ -8,7 +8,7 @@ sidebar_label: "\u7528\u6237\u8BBE\u7F6E"
# 用户设置 {#user-settings}
`user.xml` 中的 `users` 配置段包含了用户配置
`users.xml` 中的 `users` 配置段包含了用户配置
:::note
ClickHouse还支持 [SQL驱动的工作流](/docs/en/operations/access-rights#access-control) 用于管理用户。 我们建议使用它。

View File

@ -1,191 +0,0 @@
---
slug: /zh/sql-reference/ansi
sidebar_position: 40
sidebar_label: "ANSI\u517C\u5BB9\u6027"
---
# ClickHouse SQL方言 与ANSI SQL的兼容性{#ansi-sql-compatibility-of-clickhouse-sql-dialect}
:::note
本文参考Annex G所著的[ISO/IEC CD 9075-2:2011](https://www.iso.org/obp/ui/#iso:std:iso-iec:9075:-2:ed-4:v1:en:sec:8)标准.
:::
## 行为差异 {#differences-in-behaviour}
下表列出了ClickHouse能够使用但与ANSI SQL规定有差异的查询特性。
| 功能ID | 功能名称 | 差异 |
| ------- | --------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| E011 | 数值型数据类型 | 带小数点的数字被视为近似值 (`Float64`)而不是精确值 (`Decimal`) |
| E051-05 | SELECT 的列可以重命名 | 字段重命名的作用范围不限于进行重命名的SELECT子查询参考[表达式别名](https://clickhouse.com/docs/zh/sql-reference/syntax/#notes-on-usage) |
| E141-01 | NOT NULL非空约束 | ClickHouse表中每一列默认为`NOT NULL` |
| E011-04 | 算术运算符 | ClickHouse在运算时会进行溢出而不是四舍五入。此外会根据自定义规则修改结果数据类型参考[溢出检查](https://clickhouse.com/docs/zh/sql-reference/data-types/decimal/#yi-chu-jian-cha) |
## 功能状态 {#feature-status}
| 功能ID | 功能名称 | 状态 | 注释 |
| -------- | ---------------------------------------------------------------------------------------- | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **E011** | **数值型数据类型** | **部分**{.text-warning} | |
| E011-01 | INTEGER 整型和SMALLINT (小整型)数据类型 | 是 {.text-success} | |
| E011-02 | REAL 实数、DOUBLE PRECISION 双精度浮点数和FLOAT单精度浮点数数据类型数据类型 | 是 {.text-success} | |
| E011-03 | DECIMAL 精确数字和NUMERIC (精确数字)数据类型 | 是 {.text-success} | |
| E011-04 | 算术运算符 | 是 {.text-success} | |
| E011-05 | 数值比较 | 是 {.text-success} | |
| E011-06 | 数值数据类型之间的隐式转换 | 否 {.text-danger} | ANSI SQL允许在数值类型之间进行任意隐式转换而ClickHouse针对不同数据类型有对应的比较函数和类型转换函数 |
| **E021** | **字符串类型** | **部分**{.text-warning} | |
| E021-01 | CHARACTER (字符串)数据类型 | 是 {.text-success} | |
| E021-02 | CHARACTER VARYING (可变字符串)数据类型 | 是 {.text-success} | |
| E021-03 | 字符字面量 | 是 {.text-success} | |
| E021-04 | CHARACTER_LENGTH 函数 | 部分 {.text-warning} | 不支持 `using` 从句 |
| E021-05 | OCTET_LENGTH 函数 | 否 {.text-danger} | 使用 `LENGTH` 函数代替 |
| E021-06 | SUBSTRING | 部分 {.text-warning} | 不支持 `SIMILAR``ESCAPE` 从句,没有`SUBSTRING_REGEX` 函数 |
| E021-07 | 字符串拼接 | 部分 {.text-warning} | 不支持 `COLLATE` 从句 |
| E021-08 | 大小写转换 | 是 {.text-success} | |
| E021-09 | 裁剪字符串 | 是 {.text-success} | |
| E021-10 | 固定长度和可变长度字符串类型之间的隐式转换 | 部分 {.text-warning} | ANSI SQL允许在数据类型之间进行任意隐式转换而ClickHouse针对不同数据类型有对应的比较函数和类型转换函数 |
| E021-11 | POSITION 函数 | 部分 {.text-warning} | 不支持 `IN``USING` 从句,不支持`POSITION_REGEX`函数 |
| E021-12 | 字符串比较 | 是 {.text-success} | |
| **E031** | **标识符** | **部分**{.text-warning} | |
| E031-01 | 分隔标识符 | 部分 {.text-warning} | Unicode文字支持有限 |
| E031-02 | 小写标识符 | 是 {.text-success} | |
| E031-03 | 标识符最后加下划线 | 是 {.text-success} | |
| **E051** | **基本查询规范** | **部分**{.text-warning} | |
| E051-01 | SELECT DISTINCT | 是 {.text-success} | |
| E051-02 | GROUP BY 从句 | 是 {.text-success} | |
| E051-04 | GROUP BY 从句中的列可以包含不在 `<select list>`中出现的列 | 是 {.text-success} | |
| E051-05 | SELECT 的列可以重命名 | 是 {.text-success} | |
| E051-06 | HAVING 从句 | 是 {.text-success} | |
| E051-07 | SELECT 选择的列中允许出现\* | 是 {.text-success} | |
| E051-08 | FROM 从句中的关联名称 | 是 {.text-success} | |
| E051-09 | 重命名 FROM 从句中的列 | 否 {.text-danger} | |
| **E061** | **基本谓词和搜索条件** | **部分**{.text-warning} | |
| E061-01 | 比较谓词 | 是 {.text-success} | |
| E061-02 | BETWEEN 谓词 | 部分 {.text-warning} | 不支持 `SYMMETRIC``ASYMMETRIC` 从句 |
| E061-03 | IN 谓词后可接值列表 | 是 {.text-success} | |
| E061-04 | LIKE 谓词 | 是 {.text-success} | |
| E061-05 | LIKE 谓词后接 ESCAPE 从句 | 否 {.text-danger} | |
| E061-06 | NULL 谓词 | 是 {.text-success} | |
| E061-07 | 量化比较谓词ALL、SOME、ANY | 否 {.text-danger} | |
| E061-08 | EXISTS 谓词 | 否 {.text-danger} | |
| E061-09 | 比较谓词中的子查询 | 是 {.text-success} | |
| E061-11 | IN 谓词中的子查询 | 是 {.text-success} | |
| E061-12 | 量化比较谓词BETWEEN、IN、LIKE中的子查询 | 否 {.text-danger} | |
| E061-13 | 相关子查询 | 否 {.text-danger} | |
| E061-14 | 搜索条件 | 是 {.text-success} | |
| **E071** | **基本查询表达式** | **部分**{.text-warning} | |
| E071-01 | UNION DISTINCT 表运算符 | 是 {.text-success} | |
| E071-02 | UNION ALL 表运算符 | 是 {.text-success} | |
| E071-03 | EXCEPT DISTINCT 表运算符 | 否 {.text-danger} | |
| E071-05 | 通过表运算符组合的列不必具有完全相同的数据类型 | 是 {.text-success} | |
| E071-06 | 子查询中的表运算符 | 是 {.text-success} | |
| **E081** | **基本权限** | **是**{.text-success} | |
| E081-01 | 表级别的SELECT查询权限 | 是 {.text-success} | |
| E081-02 | DELETE删除权限 | 是 {.text-success} | |
| E081-03 | 表级别的INSERT插入权限 | 是 {.text-success} | |
| E081-04 | 表级别的UPDATE更新权限 | 是 {.text-success} | |
| E081-05 | 列级别的UPDATE更新权限 | 是 {.text-success} | |
| E081-06 | 表级别的REFERENCES引用权限 | 是 {.text-success} | |
| E081-07 | 列级别的REFERENCES引用权限 | 是 {.text-success} | |
| E081-08 | WITH GRANT OPTION | 是 {.text-success} | |
| E081-09 | USAGE使用权限 | 是 {.text-success} | |
| E081-10 | EXECUTE执行权限 | 是 {.text-success} | |
| **E091** | **集合函数** | **是**{.text-success} | |
| E091-01 | AVG | 是 {.text-success} | |
| E091-02 | COUNT | 是 {.text-success} | |
| E091-03 | MAX | 是 {.text-success} | |
| E091-04 | MIN | 是 {.text-success} | |
| E091-05 | SUM | 是 {.text-success} | |
| E091-06 | ALL修饰词 | 否。 {.text-danger} | |
| E091-07 | DISTINCT修饰词 | 是 {.text-success} | 并非所有聚合函数都支持该修饰词 |
| **E101** | **基本数据操作** | **部分**{.text-warning} | |
| E101-01 | INSERT插入语句 | 是 {.text-success} | 注ClickHouse中的主键并不隐含`UNIQUE` 约束 |
| E101-03 | 可指定范围的UPDATE更新语句 | 部分 {.text-warning} | `ALTER UPDATE` 语句用来批量更新数据 |
| E101-04 | 可指定范围的DELETE删除语句 | 部分 {.text-warning} | `ALTER DELETE` 语句用来批量删除数据 |
| **E111** | **返回一行的SELECT语句** | **否**{.text-danger} | |
| **E121** | **基本游标支持** | **否**{.text-danger} | |
| E121-01 | DECLARE CURSOR | 否 {.text-danger} | |
| E121-02 | ORDER BY 涉及的列不需要出现在SELECT的列中 | 是 {.text-success} | |
| E121-03 | ORDER BY 从句中的表达式 | 是 {.text-success} | |
| E121-04 | OPEN 语句 | 否 {.text-danger} | |
| E121-06 | 受游标位置控制的 UPDATE 语句 | 否 {.text-danger} | |
| E121-07 | 受游标位置控制的 DELETE 语句 | 否 {.text-danger} | |
| E121-08 | CLOSE 语句 | 否 {.text-danger} | |
| E121-10 | FETCH 语句中包含隐式NEXT | 否 {.text-danger} | |
| E121-17 | WITH HOLD 游标 | 否 {.text-danger} | |
| **E131** | **空值支持** | **是**{.text-success} | 有部分限制 |
| **E141** | **基本完整性约束** | **部分**{.text-warning} | |
| E141-01 | NOT NULL非空约束 | 是 {.text-success} | 注: 默认情况下ClickHouse表中的列隐含`NOT NULL`约束 |
| E141-02 | NOT NULL非空列的UNIQUE唯一约束 | 否 {.text-danger} | |
| E141-03 | 主键约束 | 部分 {.text-warning} | |
| E141-04 | 对于引用删除和引用更新操作基本的FOREIGN KEY外键约束默认不进行任何操作NO ACTION | 否 {.text-danger} | |
| E141-06 | CHECK检查约束 | 是 {.text-success} | |
| E141-07 | 列默认值 | 是 {.text-success} | |
| E141-08 | 在主键上推断非空 | 是 {.text-success} | |
| E141-10 | 可以按任何顺序指定外键中的名称 | 否 {.text-danger} | |
| **E151** | **事务支持** | **否**{.text-danger} | |
| E151-01 | COMMIT提交语句 | 否 {.text-danger} | |
| E151-02 | ROLLBACK回滚语句 | 否 {.text-danger} | |
| **E152** | **基本的SET TRANSACTION设置事务隔离级别语句** | **否**{.text-danger} | |
| E152-01 | SET TRANSACTION语句ISOLATION LEVEL SERIALIZABLE隔离级别为串行化从句 | 否 {.text-danger} | |
| E152-02 | SET TRANSACTION语句READ ONLY只读和READ WRITE读写从句 | 否 {.text-danger} | |
| **E153** | **具有子查询的可更新查询** | **是**{.text-success} | |
| **E161** | **使用“--”符号作为SQL注释** | **是**{.text-success} | |
| **E171** | **SQLSTATE支持** | **否**{.text-danger} | |
| **E182** | **主机语言绑定** | **否**{.text-danger} | |
| **F031** | **基本架构操作** | **部分**{.text-warning} | |
| F031-01 | 使用 CREATE TABLE 语句创建持久表 | 部分 {.text-warning} | 不支持 `SYSTEM VERSIONING`, `ON COMMIT`, `GLOBAL`, `LOCAL`, `PRESERVE`, `DELETE`, `REF IS`, `WITH OPTIONS`, `UNDER`, `LIKE`, `PERIOD FOR` 从句,不支持用户解析的数据类型 |
| F031-02 | CREATE VIEW创建视图语句 | 部分 {.text-warning} | 不支持 `RECURSIVE`, `CHECK`, `UNDER`, `WITH OPTIONS` 从句,不支持用户解析的数据类型 |
| F031-03 | GRANT授权语句 | 是 {.text-success} | |
| F031-04 | ALTER TABLE语句ADD COLUMN从句 | 是 {.text-success} | 不支持 `GENERATED` 从句和以系统时间做参数 |
| F031-13 | DROP TABLE语句RESTRICT从句 | 否 {.text-danger} | |
| F031-16 | DROP VIEW语句RESTRICT子句 | 否 {.text-danger} | |
| F031-19 | REVOKE语句RESTRICT子句 | 否 {.text-danger} | |
| **F041** | **基本连接关系** | **部分**{.text-warning} | |
| F041-01 | Inner join但不一定是INNER关键字) | 是 {.text-success} | |
| F041-02 | INNER 关键字 | 是 {.text-success} | |
| F041-03 | LEFT OUTER JOIN | 是 {.text-success} | |
| F041-04 | RIGHT OUTER JOIN | 是 {.text-success} | |
| F041-05 | 外连接可嵌套 | 是 {.text-success} | |
| F041-07 | 左外部连接或右外连接中的内部表也可用于内部联接 | 是 {.text-success} | |
| F041-08 | 支持所有比较运算符(而不仅仅是=) | 否 {.text-danger} | |
| **F051** | **基本日期和时间** | **部分**{.text-warning} | |
| F051-01 | DATE日期数据类型并支持用于表达日期的字面量) | 是 {.text-success} | |
| F051-02 | TIME时间数据类型并支持用于表达时间的字面量小数秒精度至少为0 | 否 {.text-danger} | |
| F051-03 | 时间戳数据类型并支持用于表达时间戳的字面量小数秒精度至少为0和6 | 是 {.text-danger} | |
| F051-04 | 日期、时间和时间戳数据类型的比较谓词 | 是 {.text-success} | |
| F051-05 | DateTime 类型和字符串形式表达的时间之间的显式转换 | 是 {.text-success} | |
| F051-06 | CURRENT_DATE | 否 {.text-danger} | 使用`today()`替代 |
| F051-07 | LOCALTIME | 否 {.text-danger} | 使用`now()`替代 |
| F051-08 | LOCALTIMESTAMP | 否 {.text-danger} | |
| **F081** | **视图的UNION和EXCEPT操作** | **部分**{.text-warning} | |
| **F131** | **分组操作** | **部分**{.text-warning} | |
| F131-01 | 在具有分组视图的查询中支持 WHERE、GROUP BY 和 HAVING 子句 | 是 {.text-success} | |
| F131-02 | 在分组视图中支持多张表 | 是 {.text-success} | |
| F131-03 | 分组视图的查询中支持集合函数 | 是 {.text-success} | |
| F131-04 | 带有 `GROUP BY``HAVING` 从句,以及分组视图的子查询 | 是 {.text-success} | |
| F131-05 | 带有 `GROUP BY``HAVING` 从句以及分组视图的仅返回1条记录的SELECT查询 | 否 {.text-danger} | |
| **F181** | **多模块支持** | **否**{.text-danger} | |
| **F201** | **CAST 函数** | **是**{.text-success} | |
| **F221** | **显式默认值** | **否**{.text-danger} | |
| **F261** | **CASE 表达式** | **是**{.text-success} | |
| F261-01 | 简单 CASE 表达式 | 是 {.text-success} | |
| F261-02 | 搜索型 CASE 表达式 | 是 {.text-success} | |
| F261-03 | NULLIF | 是 {.text-success} | |
| F261-04 | COALESCE | 是 {.text-success} | |
| **F311** | **架构定义语句** | **部分**{.text-warning} | |
| F311-01 | CREATE SCHEMA | 部分 {.text-warning} | 见`CREATE DATABASE` |
| F311-02 | 用于创建持久表的 CREATE TABLE | 是 {.text-success} | |
| F311-03 | CREATE VIEW | 是 {.text-success} | |
| F311-04 | CREATE VIEW: WITH CHECK OPTION | 否 {.text-danger} | |
| F311-05 | GRANT 语句 | 是 {.text-success} | |
| **F471** | **标量子查询** | **是**{.text-success} | |
| **F481** | **扩展 NULL 谓词** | **是**{.text-success} | |
| **F812** | **基本标志位** | **否**{.text-danger} |
| **S011** | **用于不重复数据的数据类型** | **否**{.text-danger} |
| **T321** | **基本的SQL调用例程** | **否**{.text-danger} | |
| T321-01 | 没有重载的用户定义函数 | 否{.text-danger} | |
| T321-02 | 没有重载的用户定义存储过程 | 否{.text-danger} | |
| T321-03 | 功能调用 | 否 {.text-danger} | |
| T321-04 | CALL 语句 | 否 {.text-danger} | |
| T321-05 | RETURN 语句 | 否 {.text-danger} | |
| **T631** | **IN 谓词后接一个列表** | **是**{.text-success} | |

View File

@ -110,7 +110,7 @@ SHOW DICTIONARIES FROM db LIKE '%reg%' LIMIT 2
### 语法 {#show-grants-syntax}
``` sql
SHOW GRANTS [FOR user]
SHOW GRANTS [FOR user1 [, user2 ...]] [WITH IMPLICIT] [FINAL]
```
如果未指定用户,输出当前用户的权限

View File

@ -18,9 +18,9 @@ generateRandom('name TypeName[, name TypeName]...', [, 'random_seed'[, 'max_stri
- `name` — 对应列的名称。
- `TypeName` — 对应列的类型。
- `max_array_length` — 生成数组的最大长度。 默认为10。
- `max_string_length` — 生成字符串的最大长度。 默认为10。
- `random_seed` — 手动指定随机种子以产生稳定的结果。 如果为NULL-种子是随机生成的。
- `max_string_length` — 生成字符串的最大长度。 默认为10。
- `max_array_length` — 生成数组的最大长度。 默认为10。
**返回值**

View File

@ -155,7 +155,7 @@ function _clickhouse_quote()
function _clickhouse_get_options()
{
# By default --help will not print all settings, this is done only under --verbose
"$@" --help --verbose 2>&1 | awk -F '[ ,=<>.]' '{ for (i=1; i <= NF; ++i) { if (substr($i, 1, 1) == "-" && length($i) > 1) print $i; } }' | sort -u
"$@" --help --verbose 2>&1 | LANG=c awk -F '[ ,=<>.]' '{ for (i=1; i <= NF; ++i) { if (substr($i, 1, 1) == "-" && length($i) > 1) print $i; } }' | sort -u
}
function _complete_for_clickhouse_generic_bin_impl()

View File

@ -445,15 +445,13 @@ private:
shutdown = true;
throw;
}
else
{
std::cerr << getCurrentExceptionMessage(print_stacktrace,
true /*check embedded stack trace*/) << std::endl;
size_t info_index = round_robin ? 0 : connection_index;
++comparison_info_per_interval[info_index]->errors;
++comparison_info_total[info_index]->errors;
}
std::cerr << getCurrentExceptionMessage(print_stacktrace,
true /*check embedded stack trace*/) << std::endl;
size_t info_index = round_robin ? 0 : connection_index;
++comparison_info_per_interval[info_index]->errors;
++comparison_info_total[info_index]->errors;
}
// Count failed queries toward executed, so that we'd reach
// max_iterations even if every run fails.

View File

@ -480,27 +480,23 @@ void Client::connect()
}
catch (const Exception & e)
{
/// This problem can't be fixed with reconnection so it is not attempted
if (e.code() == DB::ErrorCodes::AUTHENTICATION_FAILED)
{
/// This problem can't be fixed with reconnection so it is not attempted
throw;
}
else
{
if (attempted_address_index == hosts_and_ports.size() - 1)
throw;
if (is_interactive)
{
std::cerr << "Connection attempt to database at "
<< connection_parameters.host << ":" << connection_parameters.port
<< " resulted in failure"
<< std::endl
<< getExceptionMessage(e, false)
<< std::endl
<< "Attempting connection to the next provided address"
<< std::endl;
}
if (attempted_address_index == hosts_and_ports.size() - 1)
throw;
if (is_interactive)
{
std::cerr << "Connection attempt to database at "
<< connection_parameters.host << ":" << connection_parameters.port
<< " resulted in failure"
<< std::endl
<< getExceptionMessage(e, false)
<< std::endl
<< "Attempting connection to the next provided address"
<< std::endl;
}
}
}
@ -516,6 +512,7 @@ void Client::connect()
{
std::cout << "Connected to " << server_name << " server version " << server_version << "." << std::endl << std::endl;
#ifndef CLICKHOUSE_CLOUD
auto client_version_tuple = std::make_tuple(VERSION_MAJOR, VERSION_MINOR, VERSION_PATCH);
auto server_version_tuple = std::make_tuple(server_version_major, server_version_minor, server_version_patch);
@ -531,6 +528,7 @@ void Client::connect()
<< "It may indicate that the server is out of date and can be upgraded." << std::endl
<< std::endl;
}
#endif
}
if (!client_context->getSettingsRef()[Setting::use_client_time_zone])

View File

@ -38,18 +38,10 @@ public:
String path_to = disk_to.getRelativeFromRoot(getValueFromCommandLineOptionsThrow<String>(options, "path-to"));
bool recursive = options.count("recursive");
if (!disk_from.getDisk()->exists(path_from))
{
throw Exception(
ErrorCodes::BAD_ARGUMENTS,
"cannot stat '{}' on disk '{}': No such file or directory",
path_from,
disk_from.getDisk()->getName());
}
else if (disk_from.getDisk()->isFile(path_from))
if (disk_from.getDisk()->existsFile(path_from))
{
auto target_location = getTargetLocation(path_from, disk_to, path_to);
if (!disk_to.getDisk()->exists(target_location) || disk_to.getDisk()->isFile(target_location))
if (!disk_to.getDisk()->existsDirectory(target_location))
{
disk_from.getDisk()->copyFile(
path_from,
@ -65,7 +57,7 @@ public:
ErrorCodes::BAD_ARGUMENTS, "cannot overwrite directory {} with non-directory {}", target_location, path_from);
}
}
else if (disk_from.getDisk()->isDirectory(path_from))
else if (disk_from.getDisk()->existsDirectory(path_from))
{
if (!recursive)
{
@ -73,11 +65,11 @@ public:
}
auto target_location = getTargetLocation(path_from, disk_to, path_to);
if (disk_to.getDisk()->isFile(target_location))
if (disk_to.getDisk()->existsFile(target_location))
{
throw Exception(ErrorCodes::BAD_ARGUMENTS, "cannot overwrite non-directory {} with directory {}", path_to, target_location);
}
else if (!disk_to.getDisk()->exists(target_location))
if (!disk_to.getDisk()->existsDirectory(target_location))
{
disk_to.getDisk()->createDirectory(target_location);
}
@ -89,6 +81,14 @@ public:
/* write_settings= */ {},
/* cancellation_hook= */ {});
}
else
{
throw Exception(
ErrorCodes::BAD_ARGUMENTS,
"cannot stat '{}' on disk '{}': No such file or directory",
path_from,
disk_from.getDisk()->getName());
}
}
};

View File

@ -72,13 +72,9 @@ private:
auto path = [&]() -> String
{
if (relative_path.ends_with("/"))
{
return relative_path + file_name;
}
else
{
return relative_path + "/" + file_name;
}
return relative_path + "/" + file_name;
}();
if (disk.isDirectory(path))
{

View File

@ -30,21 +30,21 @@ public:
String path_from = disk.getRelativeFromRoot(getValueFromCommandLineOptionsThrow<String>(options, "path-from"));
String path_to = disk.getRelativeFromRoot(getValueFromCommandLineOptionsThrow<String>(options, "path-to"));
if (disk.getDisk()->isFile(path_from))
if (disk.getDisk()->existsFile(path_from))
{
disk.getDisk()->moveFile(path_from, path_to);
}
else if (disk.getDisk()->isDirectory(path_from))
else if (disk.getDisk()->existsDirectory(path_from))
{
auto target_location = getTargetLocation(path_from, disk, path_to);
if (!disk.getDisk()->exists(target_location))
if (!disk.getDisk()->existsDirectory(target_location))
{
disk.getDisk()->createDirectory(target_location);
disk.getDisk()->moveDirectory(path_from, target_location);
}
else
{
if (disk.getDisk()->isFile(target_location))
if (disk.getDisk()->existsFile(target_location))
{
throw Exception(
ErrorCodes::BAD_ARGUMENTS, "cannot overwrite non-directory '{}' with directory '{}'", target_location, path_from);
@ -53,13 +53,11 @@ public:
{
throw Exception(ErrorCodes::BAD_ARGUMENTS, "cannot move '{}' to '{}': Directory not empty", path_from, target_location);
}
else
{
disk.getDisk()->moveDirectory(path_from, target_location);
}
disk.getDisk()->moveDirectory(path_from, target_location);
}
}
else if (!disk.getDisk()->exists(path_from))
else
{
throw Exception(
ErrorCodes::BAD_ARGUMENTS,

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