Merge branch 'master' of github.com:ClickHouse/ClickHouse into 56257_parse_crlf_with_TSV_files

.clang-tidy

@@ -123,7 +123,21 @@ Checks: [
   '-readability-uppercase-literal-suffix',
   '-readability-use-anyofallof',
 
-  '-zircon-*'
+  '-zircon-*',
+
+  # These are new in clang-18, and we have to sort them out:
+  '-readability-avoid-nested-conditional-operator',
+  '-modernize-use-designated-initializers',
+  '-performance-enum-size',
+  '-readability-redundant-inline-specifier',
+  '-readability-redundant-member-init',
+  '-bugprone-crtp-constructor-accessibility',
+  '-bugprone-suspicious-stringview-data-usage',
+  '-bugprone-multi-level-implicit-pointer-conversion',
+  '-cert-err33-c',
+
+  # This is a good check, but clang-tidy crashes, see https://github.com/llvm/llvm-project/issues/91872
+  '-modernize-use-constraints',
 ]
 
 WarningsAsErrors: '*'

.github/workflows/merge_queue.yml

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

.github/workflows/pull_request.yml

@@ -6,7 +6,6 @@ env:
   PYTHONUNBUFFERED: 1
 
 on:  # yamllint disable-line rule:truthy
-  merge_group:
   pull_request:
     types:
       - synchronize
@@ -30,7 +29,6 @@ jobs:
           fetch-depth: 0 # to get version
           filter: tree:0
       - name: Labels check
-        if: ${{ github.event_name != 'merge_group' }}
         run: |
           cd "$GITHUB_WORKSPACE/tests/ci"
           python3 run_check.py
@@ -58,7 +56,6 @@ jobs:
               echo 'EOF'
             } >> "$GITHUB_OUTPUT"
       - name: Re-create GH statuses for skipped jobs if any
-        if: ${{ github.event_name != 'merge_group' }}
         run: |
             python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --infile ${{ runner.temp }}/ci_run_data.json --update-gh-statuses
   BuildDockers:
@@ -83,7 +80,7 @@ jobs:
         ${{secrets.ROBOT_CLICKHOUSE_SSH_KEY}}
         RCSK
   FastTest:
-    needs: [RunConfig, BuildDockers]
+    needs: [RunConfig, BuildDockers, StyleCheck]
     if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'Fast test') }}
     uses: ./.github/workflows/reusable_test.yml
     with:
@@ -163,20 +160,16 @@ jobs:
     steps:
       - name: Check out repository code
         uses: ClickHouse/checkout@v1
-      - name: Check sync status
-        if: ${{ github.event_name == 'merge_group' }}
-        run: |
-          cd "$GITHUB_WORKSPACE/tests/ci"
-          python3 sync_pr.py --status
       - name: Finish label
         run: |
           cd "$GITHUB_WORKSPACE/tests/ci"
-          python3 finish_check.py ${{ (contains(needs.*.result, 'failure') && github.event_name == 'merge_group') && '--pipeline-failure' || '' }}
+          python3 finish_check.py
-      - name: Auto merge if approved
+      # FIXME: merge on approval does not work with MQ. Could be fixed by using defaul GH's automerge after some corrections in Mergeable Check status
-        if: ${{ github.event_name != 'merge_group' }}
+      # - name: Auto merge if approved
-        run: |
+      #   if: ${{ github.event_name != 'merge_group' }}
-          cd "$GITHUB_WORKSPACE/tests/ci"
+      #   run: |
-          python3 merge_pr.py --check-approved
+      #     cd "$GITHUB_WORKSPACE/tests/ci"
+      #     python3 merge_pr.py --check-approved
 
 
 #############################################################################################

.gitmodules

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

CMakeLists.txt

@@ -135,7 +135,6 @@ endif ()
 include (cmake/check_flags.cmake)
 include (cmake/add_warning.cmake)
 
-if (COMPILER_CLANG)
 # generate ranges for fast "addr2line" search
 if (NOT CMAKE_BUILD_TYPE_UC STREQUAL "RELEASE")
     # NOTE: that clang has a bug because of it does not emit .debug_aranges
@@ -150,7 +149,6 @@ if (COMPILER_CLANG)
 endif()
 
 no_warning(enum-constexpr-conversion) # breaks Protobuf in clang-16
-endif ()
 
 option(ENABLE_TESTS "Provide unit_test_dbms target with Google.Test unit tests" ON)
 option(ENABLE_EXAMPLES "Build all example programs in 'examples' subdirectories" OFF)
@@ -284,16 +282,12 @@ endif ()
 
 option (ENABLE_BUILD_PROFILING "Enable profiling of build time" OFF)
 if (ENABLE_BUILD_PROFILING)
-     if (COMPILER_CLANG)
     set (COMPILER_FLAGS "${COMPILER_FLAGS} -ftime-trace")
 
     if (LINKER_NAME MATCHES "lld")
         set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,--time-trace")
         set (CMAKE_MODULE_LINKER_FLAGS "${CMAKE_MODULE_LINKER_FLAGS} -Wl,--time-trace")
     endif ()
-     else ()
-        message (${RECONFIGURE_MESSAGE_LEVEL} "Build profiling is only available with CLang")
-     endif ()
 endif ()
 
 set (CMAKE_CXX_STANDARD 23)
@@ -304,7 +298,6 @@ set (CMAKE_C_STANDARD 11)
 set (CMAKE_C_EXTENSIONS ON) # required by most contribs written in C
 set (CMAKE_C_STANDARD_REQUIRED ON)
 
-if (COMPILER_CLANG)
 # Enable C++14 sized global deallocation functions. It should be enabled by setting -std=c++14 but I'm not sure.
 # See https://reviews.llvm.org/D112921
 set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsized-deallocation")
@@ -319,7 +312,6 @@ if (COMPILER_CLANG)
     set(BRANCHES_WITHIN_32B_BOUNDARIES "-mbranches-within-32B-boundaries")
     set(COMPILER_FLAGS "${COMPILER_FLAGS} ${BRANCHES_WITHIN_32B_BOUNDARIES}")
 endif()
-endif ()
 
 # Disable floating-point expression contraction in order to get consistent floating point calculation results across platforms
 set (COMPILER_FLAGS "${COMPILER_FLAGS} -ffp-contract=off")
@@ -348,7 +340,6 @@ set (CMAKE_ASM_FLAGS                     "${CMAKE_ASM_FLAGS} ${COMPILER_FLAGS} $
 set (CMAKE_ASM_FLAGS_RELWITHDEBINFO      "${CMAKE_ASM_FLAGS_RELWITHDEBINFO} -O3 ${DEBUG_INFO_FLAGS} ${CMAKE_ASM_FLAGS_ADD}")
 set (CMAKE_ASM_FLAGS_DEBUG               "${CMAKE_ASM_FLAGS_DEBUG} -O0 ${DEBUG_INFO_FLAGS} ${CMAKE_ASM_FLAGS_ADD}")
 
-if (COMPILER_CLANG)
 if (OS_DARWIN)
     set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -stdlib=libc++")
     set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,-U,_inside_main")
@@ -379,10 +370,6 @@ if (COMPILER_CLANG)
     message (${RECONFIGURE_MESSAGE_LEVEL} "Cannot enable ThinLTO")
 endif ()
 
-elseif (ENABLE_THINLTO)
-    message (${RECONFIGURE_MESSAGE_LEVEL} "ThinLTO is only available with Clang")
-endif ()
-
 # Turns on all external libs like s3, kafka, ODBC, ...
 option(ENABLE_LIBRARIES "Enable all external libraries by default" ON)
 

README.md

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

base/base/DecomposedFloat.h

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

base/base/EnumReflection.h

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

base/base/JSON.cpp

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

base/base/JSON.h

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

base/base/TypeList.h

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

base/base/constexpr_helpers.h

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

base/base/find_symbols.h

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

base/base/getMemoryAmount.cpp

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

base/base/hex.h

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

base/base/iostream_debug_helpers.h

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

base/base/itoa.cpp

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

base/base/map.h

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

base/base/range.h

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

base/base/sleep.cpp

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

base/base/wide_integer.h

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

base/base/wide_integer_impl.h

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

cmake/clang_tidy.cmake

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

cmake/linux/default_libs.cmake

@@ -5,7 +5,6 @@ set (DEFAULT_LIBS "-nodefaultlibs")
 
 # We need builtins from Clang's RT even without libcxx - for ubsan+int128.
 # See https://bugs.llvm.org/show_bug.cgi?id=16404
-if (COMPILER_CLANG)
 execute_process (COMMAND ${CMAKE_CXX_COMPILER} --target=${CMAKE_CXX_COMPILER_TARGET} --print-libgcc-file-name --rtlib=compiler-rt OUTPUT_VARIABLE BUILTINS_LIBRARY OUTPUT_STRIP_TRAILING_WHITESPACE)
 
 # Apparently, in clang-19, the UBSan support library for C++ was moved out into ubsan_standalone_cxx.a, so we have to include both.
@@ -16,7 +15,6 @@ if (COMPILER_CLANG)
 if (NOT EXISTS "${BUILTINS_LIBRARY}")
     set (BUILTINS_LIBRARY "-lgcc")
 endif ()
-endif ()
 
 if (OS_ANDROID)
     # pthread and rt are included in libc

cmake/sanitize.cmake

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

cmake/tools.cmake

@@ -1,10 +1,6 @@
 # Compiler
 
-if (CMAKE_CXX_COMPILER_ID MATCHES "AppleClang")
+if (NOT CMAKE_CXX_COMPILER_ID MATCHES "Clang")
-    set (COMPILER_CLANG 1) # Safe to treat AppleClang as a regular Clang, in general.
-elseif (CMAKE_CXX_COMPILER_ID MATCHES "Clang")
-    set (COMPILER_CLANG 1)
-else ()
     message (FATAL_ERROR "Compiler ${CMAKE_CXX_COMPILER_ID} is not supported")
 endif ()
 
@@ -13,11 +9,10 @@ execute_process(COMMAND ${CMAKE_CXX_COMPILER} --version OUTPUT_VARIABLE COMPILER
 message (STATUS "Using compiler:\n${COMPILER_SELF_IDENTIFICATION}")
 
 # Require minimum compiler versions
-set (CLANG_MINIMUM_VERSION 16)
+set (CLANG_MINIMUM_VERSION 17)
 set (XCODE_MINIMUM_VERSION 12.0)
 set (APPLE_CLANG_MINIMUM_VERSION 12.0.0)
 
-if (COMPILER_CLANG)
 if (CMAKE_CXX_COMPILER_ID MATCHES "AppleClang")
     # (Experimental!) Specify "-DALLOW_APPLECLANG=ON" when running CMake configuration step, if you want to experiment with using it.
     if (NOT ALLOW_APPLECLANG AND NOT DEFINED ENV{ALLOW_APPLECLANG})
@@ -33,14 +28,11 @@ if (COMPILER_CLANG)
         message (FATAL_ERROR "Compilation with Clang version ${CMAKE_CXX_COMPILER_VERSION} is unsupported, the minimum required version is ${CLANG_MINIMUM_VERSION}.")
     endif ()
 endif ()
-endif ()
-
-# Linker
 
 string (REGEX MATCHALL "[0-9]+" COMPILER_VERSION_LIST ${CMAKE_CXX_COMPILER_VERSION})
 list (GET COMPILER_VERSION_LIST 0 COMPILER_VERSION_MAJOR)
 
-# Example values: `lld-10`
+# Linker
 option (LINKER_NAME "Linker name or full path")
 
 if (LINKER_NAME MATCHES "gold")
@@ -48,22 +40,18 @@ if (LINKER_NAME MATCHES "gold")
 endif ()
 
 if (NOT LINKER_NAME)
-    if (COMPILER_CLANG)
     if (OS_LINUX AND NOT ARCH_S390X)
         find_program (LLD_PATH NAMES "ld.lld-${COMPILER_VERSION_MAJOR}" "ld.lld")
     elseif (OS_DARWIN)
         find_program (LLD_PATH NAMES "ld")
     endif ()
-    endif ()
     if (LLD_PATH)
         if (OS_LINUX OR OS_DARWIN)
-            if (COMPILER_CLANG)
             # Clang driver simply allows full linker path.
             set (LINKER_NAME ${LLD_PATH})
         endif ()
     endif()
 endif()
-endif()
 
 if (LINKER_NAME)
     find_program (LLD_PATH NAMES ${LINKER_NAME})
@@ -82,47 +70,28 @@ else ()
 endif ()
 
 # Archiver
-
-if (COMPILER_CLANG)
 find_program (LLVM_AR_PATH NAMES "llvm-ar-${COMPILER_VERSION_MAJOR}" "llvm-ar")
-endif ()
-
 if (LLVM_AR_PATH)
     set (CMAKE_AR "${LLVM_AR_PATH}")
 endif ()
-
 message(STATUS "Using archiver: ${CMAKE_AR}")
 
 # Ranlib
-
-if (COMPILER_CLANG)
 find_program (LLVM_RANLIB_PATH NAMES "llvm-ranlib-${COMPILER_VERSION_MAJOR}" "llvm-ranlib")
-endif ()
-
 if (LLVM_RANLIB_PATH)
     set (CMAKE_RANLIB "${LLVM_RANLIB_PATH}")
 endif ()
-
 message(STATUS "Using ranlib: ${CMAKE_RANLIB}")
 
 # Install Name Tool
-
-if (COMPILER_CLANG)
 find_program (LLVM_INSTALL_NAME_TOOL_PATH NAMES "llvm-install-name-tool-${COMPILER_VERSION_MAJOR}" "llvm-install-name-tool")
-endif ()
-
 if (LLVM_INSTALL_NAME_TOOL_PATH)
     set (CMAKE_INSTALL_NAME_TOOL "${LLVM_INSTALL_NAME_TOOL_PATH}")
 endif ()
-
 message(STATUS "Using install-name-tool: ${CMAKE_INSTALL_NAME_TOOL}")
 
 # Objcopy
-
-if (COMPILER_CLANG)
 find_program (OBJCOPY_PATH NAMES "llvm-objcopy-${COMPILER_VERSION_MAJOR}" "llvm-objcopy" "objcopy")
-endif ()
-
 if (OBJCOPY_PATH)
     message (STATUS "Using objcopy: ${OBJCOPY_PATH}")
 else ()
@@ -130,11 +99,7 @@ else ()
 endif ()
 
 # Strip
-
-if (COMPILER_CLANG)
 find_program (STRIP_PATH NAMES "llvm-strip-${COMPILER_VERSION_MAJOR}" "llvm-strip" "strip")
-endif ()
-
 if (STRIP_PATH)
     message (STATUS "Using strip: ${STRIP_PATH}")
 else ()

cmake/warnings.cmake

@@ -15,7 +15,6 @@ if ((NOT CMAKE_BUILD_TYPE_UC STREQUAL "DEBUG") AND (NOT SANITIZE) AND (NOT CMAKE
     add_warning(frame-larger-than=65536)
 endif ()
 
-if (COMPILER_CLANG)
 # Add some warnings that are not available even with -Wall -Wextra -Wpedantic.
 # We want to get everything out of the compiler for code quality.
 add_warning(everything)
@@ -48,4 +47,3 @@ if (COMPILER_CLANG)
 no_warning(unsafe-buffer-usage) # too aggressive
 no_warning(switch-default) # conflicts with "defaults in a switch covering all enum values"
 # TODO Enable conversion, sign-conversion, double-promotion warnings.
-endif ()

contrib/abseil-cpp-cmake/CMakeLists.txt

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

contrib/capnproto-cmake/CMakeLists.txt

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

contrib/lz4

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

contrib/openssl-cmake/CMakeLists.txt

@@ -91,13 +91,11 @@ set(LIB_SOVERSION ${VERSION_MAJOR})
 
 enable_language(ASM)
 
-if(COMPILER_CLANG)
 add_definitions(-Wno-unused-command-line-argument)
 # Note that s390x build uses mold linker
 if(NOT ARCH_S390X)
     set(CMAKE_SHARED_LINKER_FLAGS "${CMAKE_SHARED_LINKER_FLAGS} -fuse-ld=lld") # only relevant for -DENABLE_OPENSSL_DYNAMIC=1
 endif()
-endif()
 
 if(ARCH_AMD64)
     if(OS_DARWIN)

contrib/sentry-native-cmake/CMakeLists.txt

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

contrib/yaml-cpp

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

docker/packager/README.md

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

docker/packager/packager

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

docker/server/Dockerfile.ubuntu

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

docker/server/README.md

@@ -24,6 +24,7 @@ For more information and documentation see https://clickhouse.com/.
 ## How to use this image
 
 ### start server instance
+
 ```bash
 docker run -d --name some-clickhouse-server --ulimit nofile=262144:262144 clickhouse/clickhouse-server
 ```
@@ -66,9 +67,7 @@ docker run -d -p 18123:8123 -p19000:9000 --name some-clickhouse-server --ulimit
 echo 'SELECT version()' | curl 'http://localhost:18123/' --data-binary @-
 ```
 
-```
+`22.6.3.35`
-22.6.3.35
-```
 
 or by allowing the container to use [host ports directly](https://docs.docker.com/network/host/) using `--network=host` (also allows achieving better network performance):
 
@@ -77,16 +76,14 @@ docker run -d --network=host --name some-clickhouse-server --ulimit nofile=26214
 echo 'SELECT version()' | curl 'http://localhost:8123/' --data-binary @-
 ```
 
-```
+`22.6.3.35`
-22.6.3.35
-```
 
 ### Volumes
 
 Typically you may want to mount the following folders inside your container to achieve persistency:
 
-* `/var/lib/clickhouse/` - main folder where ClickHouse stores the data
+-	`/var/lib/clickhouse/` - main folder where ClickHouse stores the data
-* `/var/log/clickhouse-server/` - logs
+-	`/var/log/clickhouse-server/` - logs
 
 ```bash
 docker run -d \
@@ -97,9 +94,9 @@ docker run -d \
 
 You may also want to mount:
 
-* `/etc/clickhouse-server/config.d/*.xml` - files with server configuration adjustments
+-	`/etc/clickhouse-server/config.d/*.xml` - files with server configuration adjustments
-* `/etc/clickhouse-server/users.d/*.xml` - files with user settings adjustments
+-	`/etc/clickhouse-server/users.d/*.xml` - files with user settings adjustments
-* `/docker-entrypoint-initdb.d/` - folder with database initialization scripts (see below).
+-	`/docker-entrypoint-initdb.d/` - folder with database initialization scripts (see below).
 
 ### Linux capabilities
 

docker/test/base/setup_export_logs.sh

@@ -127,9 +127,6 @@ function setup_logs_replication
     echo 'Create all configured system logs'
     clickhouse-client --query "SYSTEM FLUSH LOGS"
 
-    # It's doesn't make sense to try creating tables if SYNC fails
-    echo "SYSTEM SYNC DATABASE REPLICA default" | clickhouse-client "${CONNECTION_ARGS[@]}" || return 0
-
     debug_or_sanitizer_build=$(clickhouse-client -q "WITH ((SELECT value FROM system.build_options WHERE name='BUILD_TYPE') AS build, (SELECT value FROM system.build_options WHERE name='CXX_FLAGS') as flags) SELECT build='Debug' OR flags LIKE '%fsanitize%'")
     echo "Build is debug or sanitizer: $debug_or_sanitizer_build"
 
@@ -143,7 +140,7 @@ function setup_logs_replication
             time DateTime COMMENT 'The time of test run',
             test_name String COMMENT 'The name of the test',
             coverage Array(UInt64) COMMENT 'An array of addresses of the code (a subset of addresses instrumented for coverage) that were encountered during the test run'
-        ) ENGINE = Null COMMENT 'Contains information about per-test coverage from the CI, but used only for exporting to the CI cluster'
+        ) ENGINE = MergeTree ORDER BY test_name COMMENT 'Contains information about per-test coverage from the CI, but used only for exporting to the CI cluster'
     "
 
     # For each system log table:

docker/test/fuzzer/query-fuzzer-tweaks-users.xml

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

docker/test/fuzzer/run-fuzzer.sh

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

docker/test/integration/runner/Dockerfile

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

docker/test/keeper-jepsen/run.sh

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

docker/test/server-jepsen/run.sh

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

docker/test/sqltest/run.sh

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

docker/test/stateless/Dockerfile

@@ -89,8 +89,8 @@ ENV MINIO_ROOT_USER="clickhouse"
 ENV MINIO_ROOT_PASSWORD="clickhouse"
 ENV EXPORT_S3_STORAGE_POLICIES=1
 
-RUN npm install -g azurite \
+RUN npm install -g azurite@3.30.0 \
-    && npm install -g tslib
+    && npm install -g tslib && npm install -g node
 
 COPY run.sh /
 COPY setup_minio.sh /

docker/test/stateless/stress_tests.lib

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

docker/test/util/Dockerfile

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

docs/en/development/build-cross-osx.md

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

docs/en/development/build-cross-riscv.md

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

docs/en/development/build-cross-s390x.md

@@ -5,22 +5,13 @@ title: How to Build, Run and Debug ClickHouse on Linux for s390x (zLinux)
 sidebar_label: Build on Linux for s390x (zLinux)
 ---
 
-As of writing (2023/3/10) building for s390x considered to be experimental. Not all features can be enabled, has broken features and is currently under active development. 
+At the time of writing (2024 May), support for the s390x platform is considered experimental, i.e. some features are disabled or broken on s390x.
 
+## Building ClickHouse for s390x
 
-## Building
+s390x has two OpenSSL-related build options:
-
+- By default, OpenSSL is build on s390x as a shared library. This is different from all other platforms, where OpenSSL is build as static library.
-s390x has two OpenSSL-related build options. 
+- To build OpenSSL as a static library regardless, pass `-DENABLE_OPENSSL_DYNAMIC=0` to CMake.
-- By default, the s390x build will dynamically link to OpenSSL libraries. It will build OpenSSL shared objects, so it's not necessary to install OpenSSL beforehand. (This option is recommended in all cases.)
-- Another option is to build OpenSSL in-tree. In this case two build flags need to be supplied to cmake
-```bash
--DENABLE_OPENSSL_DYNAMIC=0
-```
-
-:::note
-s390x builds are temporarily disabled in CI.
-:::
-
 
 These instructions assume that the host machine is x86_64 and has all the tooling required to build natively based on the [build instructions](../development/build.md). It also assumes that the host is Ubuntu 22.04 but the following instructions should also work on Ubuntu 20.04.
 
@@ -31,11 +22,16 @@ apt-get install binutils-s390x-linux-gnu libc6-dev-s390x-cross gcc-s390x-linux-g
 ```
 
 If you wish to cross compile rust code install the rust cross compile target for s390x:
+
 ```bash
 rustup target add s390x-unknown-linux-gnu
 ```
 
+The s390x build uses the mold linker, download it from https://github.com/rui314/mold/releases/download/v2.0.0/mold-2.0.0-x86_64-linux.tar.gz
+and place it into your `$PATH`.
+
 To build for s390x:
+
 ```bash
 cmake -DCMAKE_TOOLCHAIN_FILE=cmake/linux/toolchain-s390x.cmake ..
 ninja

docs/en/development/build.md

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

docs/en/development/continuous-integration.md

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

docs/en/development/developer-instruction.md

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

docs/en/engines/database-engines/materialized-mysql.md

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

docs/en/engines/table-engines/integrations/rabbitmq.md

@@ -73,6 +73,7 @@ Optional parameters:
 - `rabbitmq_queue_consume` - Use user-defined queues and do not make any RabbitMQ setup: declaring exchanges, queues, bindings. Default: `false`.
 - `rabbitmq_username` - RabbitMQ username.
 - `rabbitmq_password` - RabbitMQ password.
+- `reject_unhandled_messages` - Reject messages (send RabbitMQ negative acknowledgement) in case of errors. This setting is automatically enabled if there is a `x-dead-letter-exchange` defined in `rabbitmq_queue_settings_list`.
 - `rabbitmq_commit_on_select` - Commit messages when select query is made. Default: `false`.
 - `rabbitmq_max_rows_per_message` — The maximum number of rows written in one RabbitMQ message for row-based formats. Default : `1`.
 - `rabbitmq_empty_queue_backoff_start` — A start backoff point to reschedule read if the rabbitmq queue is empty.

docs/en/engines/table-engines/mergetree-family/annindexes.md

@@ -22,9 +22,8 @@ ORDER BY Distance(vectors, Point)
 LIMIT N
 ```
 
-`vectors` contains N-dimensional values of type [Array](../../../sql-reference/data-types/array.md) or
+`vectors` contains N-dimensional values of type [Array(Float32)](../../../sql-reference/data-types/array.md), for example embeddings.
-[Tuple](../../../sql-reference/data-types/tuple.md), for example embeddings. Function `Distance` computes the distance between two vectors.
+Function `Distance` computes the distance between two vectors. Often, the Euclidean (L2) distance is chosen as distance function but [other
-Often, the Euclidean (L2) distance is chosen as distance function but [other
 distance functions](/docs/en/sql-reference/functions/distance-functions.md) are also possible. `Point` is the reference point, e.g. `(0.17,
 0.33, ...)`, and `N` limits the number of search results.
 
@@ -47,7 +46,7 @@ of the search space (using clustering, search trees, etc.) which allows to compu
 
 # Creating and Using ANN Indexes {#creating_using_ann_indexes}
 
-Syntax to create an ANN index over an [Array](../../../sql-reference/data-types/array.md) column:
+Syntax to create an ANN index over an [Array(Float32)](../../../sql-reference/data-types/array.md) column:
 
 ```sql
 CREATE TABLE table_with_ann_index
@@ -60,19 +59,6 @@ ENGINE = MergeTree
 ORDER BY id;
 ```
 
-Syntax to create an ANN index over a [Tuple](../../../sql-reference/data-types/tuple.md) column:
-
-```sql
-CREATE TABLE table_with_ann_index
-(
-  `id` Int64,
-  `vectors` Tuple(Float32[, Float32[, ...]]),
-  INDEX [ann_index_name] vectors TYPE [ann_index_type]([ann_index_parameters]) [GRANULARITY [N]]
-)
-ENGINE = MergeTree
-ORDER BY id;
-```
-
 ANN indexes are built during column insertion and merge. As a result, `INSERT` and `OPTIMIZE` statements will be slower than for ordinary
 tables. ANNIndexes are ideally used only with immutable or rarely changed data, respectively when are far more read requests than write
 requests.
@@ -164,7 +150,7 @@ linear surfaces (lines in 2D, planes in 3D etc.).
   </iframe>
 </div>
 
-Syntax to create an Annoy index over an [Array](../../../sql-reference/data-types/array.md) column:
+Syntax to create an Annoy index over an [Array(Float32)](../../../sql-reference/data-types/array.md) column:
 
 ```sql
 CREATE TABLE table_with_annoy_index
@@ -177,19 +163,6 @@ ENGINE = MergeTree
 ORDER BY id;
 ```
 
-Syntax to create an ANN index over a [Tuple](../../../sql-reference/data-types/tuple.md) column:
-
-```sql
-CREATE TABLE table_with_annoy_index
-(
-  id Int64,
-  vectors Tuple(Float32[, Float32[, ...]]),
-  INDEX [ann_index_name] vectors TYPE annoy([Distance[, NumTrees]]) [GRANULARITY N]
-)
-ENGINE = MergeTree
-ORDER BY id;
-```
-
 Annoy currently supports two distance functions:
 - `L2Distance`, also called Euclidean distance, is the length of a line segment between two points in Euclidean space
   ([Wikipedia](https://en.wikipedia.org/wiki/Euclidean_distance)).
@@ -203,10 +176,9 @@ Parameter `NumTrees` is the number of trees which the algorithm creates (default
 more accurate search results but slower index creation / query times (approximately linearly) as well as larger index sizes.
 
 :::note
-Indexes over columns of type `Array` will generally work faster than indexes on `Tuple` columns. All arrays must have same length. To avoid
+All arrays must have same length. To avoid errors, you can use a
-errors, you can use a [CONSTRAINT](/docs/en/sql-reference/statements/create/table.md#constraints), for example, `CONSTRAINT
+[CONSTRAINT](/docs/en/sql-reference/statements/create/table.md#constraints), for example, `CONSTRAINT constraint_name_1 CHECK
-constraint_name_1 CHECK length(vectors) = 256`. Also, empty `Arrays` and unspecified `Array` values in INSERT statements (i.e. default
+length(vectors) = 256`. Also, empty `Arrays` and unspecified `Array` values in INSERT statements (i.e. default values) are not supported.
-values) are not supported.
 :::
 
 The creation of Annoy indexes (whenever a new part is build, e.g. at the end of a merge) is a relatively slow process. You can increase
@@ -264,19 +236,6 @@ ENGINE = MergeTree
 ORDER BY id;
 ```
 
-Syntax to create an ANN index over a [Tuple](../../../sql-reference/data-types/tuple.md) column:
-
-```sql
-CREATE TABLE table_with_usearch_index
-(
-  id Int64,
-  vectors Tuple(Float32[, Float32[, ...]]),
-  INDEX [ann_index_name] vectors TYPE usearch([Distance[, ScalarKind]]) [GRANULARITY N]
-)
-ENGINE = MergeTree
-ORDER BY id;
-```
-
 USearch currently supports two distance functions:
 - `L2Distance`, also called Euclidean distance, is the length of a line segment between two points in Euclidean space
   ([Wikipedia](https://en.wikipedia.org/wiki/Euclidean_distance)).

docs/en/engines/table-engines/mergetree-family/invertedindexes.md

@@ -2,7 +2,7 @@
 slug: /en/engines/table-engines/mergetree-family/invertedindexes
 sidebar_label:  Full-text Indexes
 description: Quickly find search terms in text.
-keywords: [full-text search, text search, inverted, index, indices]
+keywords: [full-text search, text search, index, indices]
 ---
 
 # Full-text Search using Full-text Indexes [experimental]
@@ -53,6 +53,10 @@ ENGINE = MergeTree
 ORDER BY key
 ```
 
+:::note
+In earlier versions of ClickHouse, the corresponding index type name was `inverted`.
+:::
+
 where `N` specifies the tokenizer:
 
 - `full_text(0)` (or shorter: `full_text()`) set the tokenizer to "tokens", i.e. split strings along spaces,

docs/en/engines/table-engines/mergetree-family/mergetree.md

@@ -494,7 +494,7 @@ Syntax: `tokenbf_v1(size_of_bloom_filter_in_bytes, number_of_hash_functions, ran
 #### Special-purpose
 
 - Experimental indexes to support approximate nearest neighbor (ANN) search. See [here](annindexes.md) for details.
-- An experimental inverted index to support full-text search. See [here](invertedindexes.md) for details.
+- An experimental full-text index to support full-text search. See [here](invertedindexes.md) for details.
 
 ### Functions Support {#functions-support}
 
@@ -502,8 +502,8 @@ Conditions in the `WHERE` clause contains calls of the functions that operate wi
 
 Indexes of type `set` can be utilized by all functions. The other index types are supported as follows:
 
-| Function (operator) / Index                                                                                | primary key | minmax | ngrambf_v1 | tokenbf_v1 | bloom_filter | inverted |
+| Function (operator) / Index                                                                                | primary key | minmax | ngrambf_v1 | tokenbf_v1 | bloom_filter | full_text |
-|------------------------------------------------------------------------------------------------------------|-------------|--------|------------|------------|--------------|----------|
+|------------------------------------------------------------------------------------------------------------|-------------|--------|------------|------------|--------------|-----------|
 | [equals (=, ==)](/docs/en/sql-reference/functions/comparison-functions.md/#equals)                         | ✔           | ✔      | ✔          | ✔          | ✔            | ✔         |
 | [notEquals(!=, <>)](/docs/en/sql-reference/functions/comparison-functions.md/#notequals)             | ✔           | ✔      | ✔          | ✔          | ✔            | ✔         |
 | [like](/docs/en/sql-reference/functions/string-search-functions.md/#like)                                  | ✔           | ✔      | ✔          | ✔          | ✗            | ✔         |

docs/en/engines/table-engines/mergetree-family/replication.md

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

docs/en/interfaces/formats.md

@@ -91,6 +91,7 @@ The supported formats are:
 | [MySQLDump](#mysqldump)                                                                   | ✔    | ✗     |
 | [DWARF](#dwarf)                                                                           | ✔    | ✗     |
 | [Markdown](#markdown)                                                                     | ✗    | ✔     |
+| [Form](#form)                                                                             | ✔    | ✗     |
 
 
 You can control some format processing parameters with the ClickHouse settings. For more information read the [Settings](/docs/en/operations/settings/settings-formats.md) section.
@@ -207,7 +208,7 @@ SELECT * FROM nestedt FORMAT TSV
 Differs from `TabSeparated` format in that the rows are written without escaping.
 When parsing with this format, tabs or linefeeds are not allowed in each field.
 
-This format is also available under the name `TSVRaw`.
+This format is also available under the names `TSVRaw`, `Raw`.
 
 ## TabSeparatedWithNames {#tabseparatedwithnames}
 
@@ -242,14 +243,14 @@ This format is also available under the name `TSVWithNamesAndTypes`.
 Differs from `TabSeparatedWithNames` format in that the rows are written without escaping.
 When parsing with this format, tabs or linefeeds are not allowed in each field.
 
-This format is also available under the name `TSVRawWithNames`.
+This format is also available under the names `TSVRawWithNames`, `RawWithNames`.
 
 ## TabSeparatedRawWithNamesAndTypes {#tabseparatedrawwithnamesandtypes}
 
 Differs from `TabSeparatedWithNamesAndTypes` format in that the rows are written without escaping.
 When parsing with this format, tabs or linefeeds are not allowed in each field.
 
-This format is also available under the name `TSVRawWithNamesAndNames`.
+This format is also available under the names `TSVRawWithNamesAndNames`, `RawWithNamesAndNames`.
 
 ## Template {#format-template}
 
@@ -2844,3 +2845,31 @@ FORMAT Markdown
 ```
 
 Markdown table will be generated automatically and can be used on markdown-enabled platforms, like Github. This format is used only for output.
+
+## Form {#form}
+
+The Form format can be used to read or write a single record in the application/x-www-form-urlencoded format in which data is formatted `key1=value1&key2=value2`
+
+Examples:
+
+Given a file `data.tmp` placed in the `user_files` path with some URL encoded data:
+
+```text
+t_page=116&c.e=ls7xfkpm&c.tti.m=raf&rt.start=navigation&rt.bmr=390%2C11%2C10
+```
+
+```sql
+SELECT * FROM file(data.tmp, Form) FORMAT vertical;
+```
+
+Result:
+
+```text
+Row 1:
+──────
+t_page:   116
+c.e:      ls7xfkpm
+c.tti.m:  raf
+rt.start: navigation
+rt.bmr:   390,11,10
+```

docs/en/interfaces/third-party/gui.md

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

docs/en/operations/settings/settings.md

@@ -1925,7 +1925,9 @@ Default value: `16`.
 
 ### wait_for_async_insert {#wait-for-async-insert}
 
-Enables or disables waiting for processing of asynchronous insertion. If enabled, server will return `OK` only after the data is inserted. Otherwise, it will return `OK` even if the data wasn't inserted.
+Enables or disables waiting for processing of asynchronous insertion. If enabled, server will return `OK` only after the data is inserted. Otherwise, it will return `OK` as soon it has received the data, but it might still fail to parse or insert it later (You can check in system.asynchronous_insert_log)
+
+If you want to use asynchronous inserts, we need to also enable [`async_insert`](#async-insert).
 
 Possible values:
 

docs/en/operations/storing-data.md

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

docs/en/operations/system-tables/part_log.md

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

docs/en/sql-reference/aggregate-functions/reference/any.md

@@ -7,15 +7,50 @@ sidebar_position: 6
 
 Selects the first encountered value of a column.
 
-By default, it ignores NULL values and returns the first NOT NULL value found in the column. As [`first_value`](../../../sql-reference/aggregate-functions/reference/first_value.md) if supports `RESPECT NULLS`, in which case it will select the first value passed, independently on whether it's NULL or not.
+**Syntax**
 
+```sql
+any(column)
+```
+
+Aliases: `any_value`, [`first_value`](../reference/first_value.md).
+
+**Parameters**
+- `column`: The column name. 
+
+**Returned value**
+
+By default, it ignores NULL values and returns the first NOT NULL value found in the column. Like [`first_value`](../../../sql-reference/aggregate-functions/reference/first_value.md) it supports `RESPECT NULLS`, in which case it will select the first value passed, independently on whether it's NULL or not.
+
+:::note
 The return type of the function is the same as the input, except for LowCardinality which is discarded. This means that given no rows as input it will return the default value of that type (0 for integers, or Null for a Nullable() column). You might use the `-OrNull` [combinator](../../../sql-reference/aggregate-functions/combinators.md) ) to modify this behaviour.
+:::
 
+:::warning
 The query can be executed in any order and even in a different order each time, so the result of this function is indeterminate.
-To get a determinate result, you can use the ‘min’ or ‘max’ function instead of ‘any’.
+To get a determinate result, you can use the [`min`](../reference/min.md) or [`max`](../reference/max.md) function instead of `any`.
+:::
 
-In some cases, you can rely on the order of execution. This applies to cases when SELECT comes from a subquery that uses ORDER BY.
+**Implementation details**
+
+In some cases, you can rely on the order of execution. This applies to cases when `SELECT` comes from a subquery that uses `ORDER BY`.
 
 When a `SELECT` query has the `GROUP BY` clause or at least one aggregate function, ClickHouse (in contrast to MySQL) requires that all expressions in the `SELECT`, `HAVING`, and `ORDER BY` clauses be calculated from keys or from aggregate functions. In other words, each column selected from the table must be used either in keys or inside aggregate functions. To get behavior like in MySQL, you can put the other columns in the `any` aggregate function.
 
-- Alias: `any_value`, `first_value`.
+**Example**
+
+Query:
+
+```sql
+CREATE TABLE any_nulls (city Nullable(String)) ENGINE=Log;
+
+INSERT INTO any_nulls (city) VALUES (NULL), ('Amsterdam'), ('New York'), ('Tokyo'), ('Valencia'), (NULL);
+
+SELECT any(city) FROM any_nulls;
+```
+
+```response
+┌─any(city)─┐
+│ Amsterdam │
+└───────────┘
+```

docs/en/sql-reference/aggregate-functions/reference/any_respect_nulls.md

@@ -0,0 +1,44 @@
+---
+slug: /en/sql-reference/aggregate-functions/reference/any_respect_nulls
+sidebar_position: 103
+---
+
+# any_respect_nulls
+
+Selects the first encountered value of a column, irregardless of whether it is a `NULL` value or not.
+
+Alias: `any_value_respect_nulls`, `first_value_repect_nulls`.
+
+**Syntax**
+
+```sql
+any_respect_nulls(column)
+```
+
+**Parameters**
+- `column`: The column name. 
+
+**Returned value**
+
+- The last value encountered, irregardless of whether it is a `NULL` value or not.
+
+**Example**
+
+Query:
+
+```sql
+CREATE TABLE any_nulls (city Nullable(String)) ENGINE=Log;
+
+INSERT INTO any_nulls (city) VALUES (NULL), ('Amsterdam'), ('New York'), ('Tokyo'), ('Valencia'), (NULL);
+
+SELECT any(city), any_respect_nulls(city) FROM any_nulls;
+```
+
+```response
+┌─any(city)─┬─any_respect_nulls(city)─┐
+│ Amsterdam │ ᴺᵁᴸᴸ                    │
+└───────────┴─────────────────────────┘
+```
+
+**See Also**
+- [any](../reference/any.md)

docs/en/sql-reference/aggregate-functions/reference/anylast.md

@@ -5,5 +5,35 @@ sidebar_position: 104
 
 # anyLast
 
-Selects the last value encountered.
+Selects the last value encountered. The result is just as indeterminate as for the [any](../../../sql-reference/aggregate-functions/reference/any.md) function.
-The result is just as indeterminate as for the [any](../../../sql-reference/aggregate-functions/reference/any.md) function.
+
+**Syntax**
+
+```sql
+anyLast(column)
+```
+
+**Parameters**
+- `column`: The column name. 
+
+**Returned value**
+
+- The last value encountered.
+
+**Example**
+
+Query:
+
+```sql
+CREATE TABLE any_last_nulls (city Nullable(String)) ENGINE=Log;
+
+INSERT INTO any_last_nulls (city) VALUES ('Amsterdam'),(NULL),('New York'),('Tokyo'),('Valencia'),(NULL);
+
+SELECT anyLast(city) FROM any_last_nulls;
+```
+
+```response
+┌─anyLast(city)─┐
+│ Valencia      │
+└───────────────┘
+```

docs/en/sql-reference/aggregate-functions/reference/anylast_respect_nulls.md

@@ -0,0 +1,39 @@
+---
+slug: /en/sql-reference/aggregate-functions/reference/anylast_respect_nulls
+sidebar_position: 104
+---
+
+# anyLast_respect_nulls
+
+Selects the last value encountered, irregardless of whether it is `NULL` or not.
+
+**Syntax**
+
+```sql
+anyLast_respect_nulls(column)
+```
+
+**Parameters**
+- `column`: The column name. 
+
+**Returned value**
+
+- The last value encountered, irregardless of whether it is `NULL` or not.
+
+**Example**
+
+Query:
+
+```sql
+CREATE TABLE any_last_nulls (city Nullable(String)) ENGINE=Log;
+
+INSERT INTO any_last_nulls (city) VALUES ('Amsterdam'),(NULL),('New York'),('Tokyo'),('Valencia'),(NULL);
+
+SELECT anyLast(city), anyLast_respect_nulls(city) FROM any_last_nulls;
+```
+
+```response
+┌─anyLast(city)─┬─anyLast_respect_nulls(city)─┐
+│ Valencia      │ ᴺᵁᴸᴸ                        │
+└───────────────┴─────────────────────────────┘
+```

docs/en/sql-reference/aggregate-functions/reference/index.md

@@ -37,8 +37,10 @@ Standard aggregate functions:
 
 ClickHouse-specific aggregate functions:
 
+- [any](/docs/en/sql-reference/aggregate-functions/reference/any_respect_nulls.md)
 - [anyHeavy](/docs/en/sql-reference/aggregate-functions/reference/anyheavy.md)
 - [anyLast](/docs/en/sql-reference/aggregate-functions/reference/anylast.md)
+- [anyLast](/docs/en/sql-reference/aggregate-functions/reference/anylast_respect_nulls.md)
 - [boundingRatio](/docs/en/sql-reference/aggregate-functions/reference/boundrat.md)
 - [first_value](/docs/en/sql-reference/aggregate-functions/reference/first_value.md)
 - [last_value](/docs/en/sql-reference/aggregate-functions/reference/last_value.md)
@@ -97,6 +99,7 @@ ClickHouse-specific aggregate functions:
 - [quantileBFloat16Weighted](/docs/en/sql-reference/aggregate-functions/reference/quantilebfloat16.md#quantilebfloat16weighted)
 - [quantileDD](/docs/en/sql-reference/aggregate-functions/reference/quantileddsketch.md#quantileddsketch)
 - [simpleLinearRegression](/docs/en/sql-reference/aggregate-functions/reference/simplelinearregression.md)
+- [singleValueOrNull](/docs/en/sql-reference/aggregate-functions/reference/singlevalueornull.md)
 - [stochasticLinearRegression](/docs/en/sql-reference/aggregate-functions/reference/stochasticlinearregression.md)
 - [stochasticLogisticRegression](/docs/en/sql-reference/aggregate-functions/reference/stochasticlogisticregression.md)
 - [categoricalInformationValue](/docs/en/sql-reference/aggregate-functions/reference/categoricalinformationvalue.md)

docs/en/sql-reference/aggregate-functions/reference/singlevalueornull.md

@@ -0,0 +1,57 @@
+---
+slug: /en/sql-reference/aggregate-functions/reference/singlevalueornull
+sidebar_position: 220
+---
+
+# singleValueOrNull
+
+The aggregate function `singleValueOrNull` is used to implement subquery operators, such as `x = ALL (SELECT ...)`. It checks if there is only one unique non-NULL value in the data.
+If there is only one unique value, it returns it. If there are zero or at least two distinct values, it returns NULL.
+
+**Syntax**
+
+``` sql
+singleValueOrNull(x)
+```
+
+**Parameters**
+
+- `x` — Column of any [data type](../../data-types/index.md).
+
+**Returned values**
+
+- The unique value, if there is only one unique non-NULL value in `x`.
+- `NULL`, if there are zero or at least two distinct values.
+
+**Examples**
+
+Query:
+
+``` sql
+CREATE TABLE test (x UInt8 NULL) ENGINE=Log;
+INSERT INTO test (x) VALUES (NULL), (NULL), (5), (NULL), (NULL);
+SELECT singleValueOrNull(x) FROM test;
+```
+
+Result:
+
+```response
+┌─singleValueOrNull(x)─┐
+│                    5 │
+└──────────────────────┘
+```
+
+Query:
+
+```sql
+INSERT INTO test (x) VALUES (10);
+SELECT singleValueOrNull(x) FROM test;
+```
+
+Result:
+
+```response
+┌─singleValueOrNull(x)─┐
+│                 ᴺᵁᴸᴸ │
+└──────────────────────┘
+```

docs/en/sql-reference/data-types/map.md

@@ -7,10 +7,11 @@ sidebar_label: Map(K, V)
 # Map(K, V)
 
 `Map(K, V)` data type stores `key:value` pairs.
+The Map datatype is implemented as `Array(Tuple(key T1, value T2))`, which means that the order of keys in each map does not change, i.e., this data type maintains insertion order.
 
 **Parameters**
 
-- `key` — The key part of the pair. [String](../../sql-reference/data-types/string.md), [Integer](../../sql-reference/data-types/int-uint.md), [LowCardinality](../../sql-reference/data-types/lowcardinality.md), [FixedString](../../sql-reference/data-types/fixedstring.md), [UUID](../../sql-reference/data-types/uuid.md), [Date](../../sql-reference/data-types/date.md), [DateTime](../../sql-reference/data-types/datetime.md), [Date32](../../sql-reference/data-types/date32.md), [Enum](../../sql-reference/data-types/enum.md).
+- `key` — The key part of the pair. Arbitrary type, except [Nullable](../../sql-reference/data-types/nullable.md) and [LowCardinality](../../sql-reference/data-types/lowcardinality.md) nested with [Nullable](../../sql-reference/data-types/nullable.md) types.
 - `value` — The value part of the pair. Arbitrary type, including [Map](../../sql-reference/data-types/map.md) and [Array](../../sql-reference/data-types/array.md).
 
 To get the value from an `a Map('key', 'value')` column, use `a['key']` syntax. This lookup works now with a linear complexity.

docs/en/sql-reference/functions/conditional-functions.md

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

docs/en/sql-reference/functions/functions-for-nulls.md

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

docs/en/sql-reference/functions/math-functions.md

@@ -792,6 +792,39 @@ Result:
 │       -1 │
 └──────────┘
 ```
+## sigmoid
+
+Returns the [sigmoid function](https://en.wikipedia.org/wiki/Sigmoid_function).
+
+**Syntax**
+
+```sql
+sigmoid(x)
+```
+
+**Parameters**
+
+- `x` — input value. Values from the interval: `-∞ < x < +∞`. [(U)Int*](../../sql-reference/data-types/int-uint.md), [Float*](../../sql-reference/data-types/float.md) or [Decimal*](../../sql-reference/data-types/decimal.md).
+
+**Returned value**
+
+- Corresponding value along the sigmoid curve between 0 and 1. [Float64](../../sql-reference/data-types/float.md).
+
+**Example**
+
+Query:
+
+``` sql
+SELECT round(sigmoid(x), 5) FROM (SELECT arrayJoin([-1, 0, 1]) AS x);
+```
+
+Result:
+
+```result
+0.26894
+0.5
+0.73106
+```
 
 ## degrees
 

docs/en/sql-reference/functions/string-functions.md

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

docs/en/sql-reference/functions/tuple-map-functions.md

@@ -16,7 +16,7 @@ map(key1, value1[, key2, value2, ...])
 
 **Arguments**
 
-- `key` — The key part of the pair. [String](../../sql-reference/data-types/string.md), [Integer](../../sql-reference/data-types/int-uint.md), [LowCardinality](../../sql-reference/data-types/lowcardinality.md), [FixedString](../../sql-reference/data-types/fixedstring.md), [UUID](../../sql-reference/data-types/uuid.md), [Date](../../sql-reference/data-types/date.md), [DateTime](../../sql-reference/data-types/datetime.md), [Date32](../../sql-reference/data-types/date32.md), [Enum](../../sql-reference/data-types/enum.md).
+- `key` — The key part of the pair. Arbitrary type, except [Nullable](../../sql-reference/data-types/nullable.md) and [LowCardinality](../../sql-reference/data-types/lowcardinality.md) nested with [Nullable](../../sql-reference/data-types/nullable.md).
 - `value` — The value part of the pair. Arbitrary type, including [Map](../../sql-reference/data-types/map.md) and [Array](../../sql-reference/data-types/array.md).
 
 **Returned value**

docs/en/sql-reference/statements/select/join.md

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

docs/en/sql-reference/statements/select/with.md

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

docs/en/sql-reference/statements/truncate.md

@@ -25,7 +25,7 @@ If the `alter_sync` is set to `2` and some replicas are not active for more than
 
 ## TRUNCATE ALL TABLES
 ``` sql
-TRUNCATE ALL TABLES [IF EXISTS] db [ON CLUSTER cluster]
+TRUNCATE ALL TABLES FROM [IF EXISTS] db [ON CLUSTER cluster]
 ```
 
 Removes all data from all tables in a database.

docs/ru/sql-reference/functions/null-functions.md

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

docs/ru/sql-reference/functions/string-functions.md

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

docs/zh/sql-reference/functions/null-functions.md

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

programs/git-import/git-import.cpp

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

programs/install/Install.cpp

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

programs/keeper-client/KeeperClient.cpp

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

programs/library-bridge/LibraryBridgeHandlers.cpp

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

programs/library-bridge/SharedLibrary.cpp

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

programs/main.cpp

@@ -119,7 +119,7 @@ std::pair<std::string_view, std::string_view> clickhouse_short_names[] =
 };
 
 
-enum class InstructionFail
+enum class InstructionFail : uint8_t
 {
     NONE = 0,
     SSE3 = 1,
@@ -491,9 +491,13 @@ int main(int argc_, char ** argv_)
     ///     clickhouse -q 'select 1' # use local
     ///     clickhouse # spawn local
     ///     clickhouse local # spawn local
+    ///     clickhouse "select ..." # spawn local
     ///
-    if (main_func == printHelp && !argv.empty() && (argv.size() == 1 || argv[1][0] == '-'))
+    if (main_func == printHelp && !argv.empty() && (argv.size() == 1 || argv[1][0] == '-'
+        || std::string_view(argv[1]).contains(' ')))
+    {
         main_func = mainEntryClickHouseLocal;
+    }
 
     int exit_code = main_func(static_cast<int>(argv.size()), argv.data());
 

programs/obfuscator/Obfuscator.cpp

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

programs/odbc-bridge/ODBCSource.cpp

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

programs/odbc-bridge/getIdentifierQuote.cpp

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

programs/server/dashboard.html

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

programs/static-files-disk-uploader/static-files-disk-uploader.cpp

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

src/Access/AccessBackup.cpp

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

src/Access/AccessBackup.h

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

src/Access/AccessRights.cpp

@@ -241,11 +241,12 @@ namespace
 
     enum Level
     {
-        GLOBAL_LEVEL,
+        GLOBAL_LEVEL = 0,
-        DATABASE_LEVEL,
+        DATABASE_LEVEL = 1,
         GLOBAL_WITH_PARAMETER = DATABASE_LEVEL,
-        TABLE_LEVEL,
+        TABLE_LEVEL = 2,
-        COLUMN_LEVEL,
+        COLUMN_LEVEL = 3,
+        MAX = COLUMN_LEVEL,
     };
 
     AccessFlags getAllGrantableFlags(Level level)
@@ -520,7 +521,7 @@ public:
 
 private:
     AccessFlags getAllGrantableFlags() const { return ::DB::getAllGrantableFlags(level); }
-    AccessFlags getChildAllGrantableFlags() const { return ::DB::getAllGrantableFlags(static_cast<Level>(level + 1)); }
+    AccessFlags getChildAllGrantableFlags() const { return ::DB::getAllGrantableFlags(static_cast<Level>(level == Level::MAX ? level : (level + 1))); }
 
     Node * tryGetChild(std::string_view name) const
     {

src/Access/AuthenticationData.cpp

@@ -118,13 +118,16 @@ void AuthenticationData::setPassword(const String & password_)
     switch (type)
     {
         case AuthenticationType::PLAINTEXT_PASSWORD:
-            return setPasswordHashBinary(Util::stringToDigest(password_));
+            setPasswordHashBinary(Util::stringToDigest(password_));
+            return;
 
         case AuthenticationType::SHA256_PASSWORD:
-            return setPasswordHashBinary(Util::encodeSHA256(password_));
+            setPasswordHashBinary(Util::encodeSHA256(password_));
+            return;
 
         case AuthenticationType::DOUBLE_SHA1_PASSWORD:
-            return setPasswordHashBinary(Util::encodeDoubleSHA1(password_));
+            setPasswordHashBinary(Util::encodeDoubleSHA1(password_));
+            return;
 
         case AuthenticationType::BCRYPT_PASSWORD:
         case AuthenticationType::NO_PASSWORD:
@@ -146,7 +149,7 @@ void AuthenticationData::setPasswordBcrypt(const String & password_, int workfac
     if (type != AuthenticationType::BCRYPT_PASSWORD)
         throw Exception(ErrorCodes::LOGICAL_ERROR, "Cannot specify bcrypt password for authentication type {}", toString(type));
 
-    return setPasswordHashBinary(Util::encodeBcrypt(password_, workfactor_));
+    setPasswordHashBinary(Util::encodeBcrypt(password_, workfactor_));
 }
 
 String AuthenticationData::getPassword() const

src/Access/Common/AccessEntityType.h

@@ -7,7 +7,7 @@ namespace DB
 {
 
 /// Represents the type of an access entity (see the IAccessEntity class).
-enum class AccessEntityType
+enum class AccessEntityType : uint8_t
 {
     USER,
     ROLE,

src/Access/Common/AccessFlags.cpp

@@ -115,15 +115,15 @@ namespace
         {
             UNKNOWN = -2,
             GROUP = -1,
-            GLOBAL,
+            GLOBAL = 0,
-            DATABASE,
+            DATABASE = 1,
-            TABLE,
+            TABLE = 2,
             VIEW = TABLE,
-            COLUMN,
+            COLUMN = 3,
-            DICTIONARY,
+            DICTIONARY = 4,
-            NAMED_COLLECTION,
+            NAMED_COLLECTION = 5,
-            USER_NAME,
+            USER_NAME = 6,
-            TABLE_ENGINE,
+            TABLE_ENGINE = 7,
         };
 
         struct Node;