Merge remote-tracking branch 'origin/progress_bar_for_LocalServer' into progress_bar_for_LocalServer

CMakeLists.txt

@@ -169,8 +169,8 @@ 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)
 
-if (OS_LINUX AND NOT UNBUNDLED AND MAKE_STATIC_LIBRARIES AND NOT SPLIT_SHARED_LIBRARIES AND CMAKE_VERSION VERSION_GREATER "3.9.0")
+if (OS_LINUX AND (ARCH_AMD64 OR ARCH_AARCH64) AND NOT UNBUNDLED AND MAKE_STATIC_LIBRARIES AND NOT SPLIT_SHARED_LIBRARIES AND CMAKE_VERSION VERSION_GREATER "3.9.0")
-    # Only for Linux, x86_64.
+    # Only for Linux, x86_64 or aarch64.
     option(GLIBC_COMPATIBILITY "Enable compatibility with older glibc libraries." ON)
 elseif(GLIBC_COMPATIBILITY)
     message (${RECONFIGURE_MESSAGE_LEVEL} "Glibc compatibility cannot be enabled in current configuration")

base/common/DecomposedFloat.h

@@ -0,0 +1,216 @@
+#pragma once
+
+#include <cstdint>
+#include <cstddef>
+#include <cstring>
+#include <common/extended_types.h>
+
+
+/// Allows to check the internals of IEEE-754 floating point number.
+
+template <typename T> struct FloatTraits;
+
+template <>
+struct FloatTraits<float>
+{
+    using UInt = uint32_t;
+    static constexpr size_t bits = 32;
+    static constexpr size_t exponent_bits = 8;
+    static constexpr size_t mantissa_bits = bits - exponent_bits - 1;
+};
+
+template <>
+struct FloatTraits<double>
+{
+    using UInt = uint64_t;
+    static constexpr size_t bits = 64;
+    static constexpr size_t exponent_bits = 11;
+    static constexpr size_t mantissa_bits = bits - exponent_bits - 1;
+};
+
+
+/// x = sign * (2 ^ normalized_exponent) * (1 + mantissa * 2 ^ -mantissa_bits)
+/// x = sign * (2 ^ normalized_exponent + mantissa * 2 ^ (normalized_exponent - mantissa_bits))
+template <typename T>
+struct DecomposedFloat
+{
+    using Traits = FloatTraits<T>;
+
+    DecomposedFloat(T x)
+    {
+        memcpy(&x_uint, &x, sizeof(x));
+    }
+
+    typename Traits::UInt x_uint;
+
+    bool is_negative() const
+    {
+        return x_uint >> (Traits::bits - 1);
+    }
+
+    /// Returns 0 for both +0. and -0.
+    int sign() const
+    {
+        return (exponent() == 0 && mantissa() == 0)
+            ? 0
+            : (is_negative()
+                ? -1
+                : 1);
+    }
+
+    uint16_t exponent() const
+    {
+        return (x_uint >> (Traits::mantissa_bits)) & (((1ull << (Traits::exponent_bits + 1)) - 1) >> 1);
+    }
+
+    int16_t normalized_exponent() const
+    {
+        return int16_t(exponent()) - ((1ull << (Traits::exponent_bits - 1)) - 1);
+    }
+
+    uint64_t mantissa() const
+    {
+        return x_uint & ((1ull << Traits::mantissa_bits) - 1);
+    }
+
+    int64_t mantissa_with_sign() const
+    {
+        return is_negative() ? -mantissa() : mantissa();
+    }
+
+    /// NOTE Probably floating point instructions can be better.
+    bool is_integer_in_representable_range() const
+    {
+        return x_uint == 0
+            || (normalized_exponent() >= 0  /// The number is not less than one
+                /// The number is inside the range where every integer has exact representation in float
+                && normalized_exponent() <= static_cast<int16_t>(Traits::mantissa_bits)
+                /// After multiplying by 2^exp, the fractional part becomes zero, means the number is integer
+                && ((mantissa() & ((1ULL << (Traits::mantissa_bits - normalized_exponent())) - 1)) == 0));
+    }
+
+
+    /// Compare float with integer of arbitrary width (both signed and unsigned are supported). Assuming two's complement arithmetic.
+    /// Infinities are compared correctly. NaNs are treat similarly to infinities, so they can be less than all numbers.
+    /// (note that we need total order)
+    template <typename Int>
+    int compare(Int rhs)
+    {
+        if (rhs == 0)
+            return sign();
+
+        /// Different signs
+        if (is_negative() && rhs > 0)
+            return -1;
+        if (!is_negative() && rhs < 0)
+            return 1;
+
+        /// Fractional number with magnitude less than one
+        if (normalized_exponent() < 0)
+        {
+            if (!is_negative())
+                return rhs > 0 ? -1 : 1;
+            else
+                return rhs >= 0 ? -1 : 1;
+        }
+
+        /// The case of the most negative integer
+        if constexpr (is_signed_v<Int>)
+        {
+            if (rhs == std::numeric_limits<Int>::lowest())
+            {
+                assert(is_negative());
+
+                if (normalized_exponent() < static_cast<int16_t>(8 * sizeof(Int) - is_signed_v<Int>))
+                    return 1;
+                if (normalized_exponent() > static_cast<int16_t>(8 * sizeof(Int) - is_signed_v<Int>))
+                    return -1;
+
+                if (mantissa() == 0)
+                    return 0;
+                else
+                    return -1;
+            }
+        }
+
+        /// Too large number: abs(float) > abs(rhs). Also the case with infinities and NaN.
+        if (normalized_exponent() >= static_cast<int16_t>(8 * sizeof(Int) - is_signed_v<Int>))
+            return is_negative() ? -1 : 1;
+
+        using UInt = make_unsigned_t<Int>;
+        UInt uint_rhs = rhs < 0 ? -rhs : rhs;
+
+        /// Smaller octave: abs(rhs) < abs(float)
+        if (uint_rhs < (static_cast<UInt>(1) << normalized_exponent()))
+            return is_negative() ? -1 : 1;
+
+        /// Larger octave: abs(rhs) > abs(float)
+        if (normalized_exponent() + 1 < static_cast<int16_t>(8 * sizeof(Int) - is_signed_v<Int>)
+            && uint_rhs >= (static_cast<UInt>(1) << (normalized_exponent() + 1)))
+            return is_negative() ? 1 : -1;
+
+        /// The same octave
+        /// uint_rhs == 2 ^ normalized_exponent + mantissa * 2 ^ (normalized_exponent - mantissa_bits)
+
+        bool large_and_always_integer = normalized_exponent() >= static_cast<int16_t>(Traits::mantissa_bits);
+
+        typename Traits::UInt a = large_and_always_integer
+            ? mantissa() << (normalized_exponent() - Traits::mantissa_bits)
+            : mantissa() >> (Traits::mantissa_bits - normalized_exponent());
+
+        typename Traits::UInt b = uint_rhs - (static_cast<UInt>(1) << normalized_exponent());
+
+        if (a < b)
+            return is_negative() ? 1 : -1;
+        if (a > b)
+            return is_negative() ? -1 : 1;
+
+        /// Float has no fractional part means that the numbers are equal.
+        if (large_and_always_integer || (mantissa() & ((1ULL << (Traits::mantissa_bits - normalized_exponent())) - 1)) == 0)
+            return 0;
+        else
+            /// Float has fractional part means its abs value is larger.
+            return is_negative() ? -1 : 1;
+    }
+
+
+    template <typename Int>
+    bool equals(Int rhs)
+    {
+        return compare(rhs) == 0;
+    }
+
+    template <typename Int>
+    bool notEquals(Int rhs)
+    {
+        return compare(rhs) != 0;
+    }
+
+    template <typename Int>
+    bool less(Int rhs)
+    {
+        return compare(rhs) < 0;
+    }
+
+    template <typename Int>
+    bool greater(Int rhs)
+    {
+        return compare(rhs) > 0;
+    }
+
+    template <typename Int>
+    bool lessOrEquals(Int rhs)
+    {
+        return compare(rhs) <= 0;
+    }
+
+    template <typename Int>
+    bool greaterOrEquals(Int rhs)
+    {
+        return compare(rhs) >= 0;
+    }
+};
+
+
+using DecomposedFloat64 = DecomposedFloat<double>;
+using DecomposedFloat32 = DecomposedFloat<float>;

base/common/arithmeticOverflow.h

@@ -56,27 +56,33 @@ namespace common
     }
 
     template <>
-    inline bool addOverflow(__int128 x, __int128 y, __int128 & res)
+    inline bool addOverflow(Int128 x, Int128 y, Int128 & res)
     {
-        static constexpr __int128 min_int128 = minInt128();
-        static constexpr __int128 max_int128 = maxInt128();
         res = addIgnoreOverflow(x, y);
-        return (y > 0 && x > max_int128 - y) || (y < 0 && x < min_int128 - y);
+        return (y > 0 && x > std::numeric_limits<Int128>::max() - y) ||
+            (y < 0 && x < std::numeric_limits<Int128>::min() - y);
     }
 
     template <>
-    inline bool addOverflow(wInt256 x, wInt256 y, wInt256 & res)
+    inline bool addOverflow(UInt128 x, UInt128 y, UInt128 & res)
     {
         res = addIgnoreOverflow(x, y);
-        return (y > 0 && x > std::numeric_limits<wInt256>::max() - y) ||
+        return x > std::numeric_limits<UInt128>::max() - y;
-            (y < 0 && x < std::numeric_limits<wInt256>::min() - y);
     }
 
     template <>
-    inline bool addOverflow(wUInt256 x, wUInt256 y, wUInt256 & res)
+    inline bool addOverflow(Int256 x, Int256 y, Int256 & res)
     {
         res = addIgnoreOverflow(x, y);
-        return x > std::numeric_limits<wUInt256>::max() - y;
+        return (y > 0 && x > std::numeric_limits<Int256>::max() - y) ||
+            (y < 0 && x < std::numeric_limits<Int256>::min() - y);
+    }
+
+    template <>
+    inline bool addOverflow(UInt256 x, UInt256 y, UInt256 & res)
+    {
+        res = addIgnoreOverflow(x, y);
+        return x > std::numeric_limits<UInt256>::max() - y;
     }
 
     template <typename T>
@@ -104,24 +110,30 @@ namespace common
     }
 
     template <>
-    inline bool subOverflow(__int128 x, __int128 y, __int128 & res)
+    inline bool subOverflow(Int128 x, Int128 y, Int128 & res)
     {
-        static constexpr __int128 min_int128 = minInt128();
-        static constexpr __int128 max_int128 = maxInt128();
         res = subIgnoreOverflow(x, y);
-        return (y < 0 && x > max_int128 + y) || (y > 0 && x < min_int128 + y);
+        return (y < 0 && x > std::numeric_limits<Int128>::max() + y) ||
+            (y > 0 && x < std::numeric_limits<Int128>::min() + y);
     }
 
     template <>
-    inline bool subOverflow(wInt256 x, wInt256 y, wInt256 & res)
+    inline bool subOverflow(UInt128 x, UInt128 y, UInt128 & res)
     {
         res = subIgnoreOverflow(x, y);
-        return (y < 0 && x > std::numeric_limits<wInt256>::max() + y) ||
+        return x < y;
-            (y > 0 && x < std::numeric_limits<wInt256>::min() + y);
     }
 
     template <>
-    inline bool subOverflow(wUInt256 x, wUInt256 y, wUInt256 & res)
+    inline bool subOverflow(Int256 x, Int256 y, Int256 & res)
+    {
+        res = subIgnoreOverflow(x, y);
+        return (y < 0 && x > std::numeric_limits<Int256>::max() + y) ||
+            (y > 0 && x < std::numeric_limits<Int256>::min() + y);
+    }
+
+    template <>
+    inline bool subOverflow(UInt256 x, UInt256 y, UInt256 & res)
     {
         res = subIgnoreOverflow(x, y);
         return x < y;
@@ -151,36 +163,33 @@ namespace common
         return __builtin_smulll_overflow(x, y, &res);
     }
 
+    /// Overflow check is not implemented for big integers.
+
     template <>
-    inline bool mulOverflow(__int128 x, __int128 y, __int128 & res)
+    inline bool mulOverflow(Int128 x, Int128 y, Int128 & res)
     {
         res = mulIgnoreOverflow(x, y);
-        if (!x || !y)
+        return false;
-            return false;
-
-        unsigned __int128 a = (x > 0) ? x : -x;
-        unsigned __int128 b = (y > 0) ? y : -y;
-        return mulIgnoreOverflow(a, b) / b != a;
     }
 
     template <>
-    inline bool mulOverflow(wInt256 x, wInt256 y, wInt256 & res)
+    inline bool mulOverflow(Int256 x, Int256 y, Int256 & res)
     {
         res = mulIgnoreOverflow(x, y);
-        if (!x || !y)
+        return false;
-            return false;
-
-        wInt256 a = (x > 0) ? x : -x;
-        wInt256 b = (y > 0) ? y : -y;
-        return mulIgnoreOverflow(a, b) / b != a;
     }
 
     template <>
-    inline bool mulOverflow(wUInt256 x, wUInt256 y, wUInt256 & res)
+    inline bool mulOverflow(UInt128 x, UInt128 y, UInt128 & res)
     {
         res = mulIgnoreOverflow(x, y);
-        if (!x || !y)
+        return false;
-            return false;
+    }
-        return res / y != x;
+
+    template <>
+    inline bool mulOverflow(UInt256 x, UInt256 y, UInt256 & res)
+    {
+        res = mulIgnoreOverflow(x, y);
+        return false;
     }
 }

base/common/extended_types.h

@@ -5,16 +5,14 @@
 #include <common/types.h>
 #include <common/wide_integer.h>
 
-using Int128 = __int128;
 
-using wInt256 = wide::integer<256, signed>;
+using Int128 = wide::integer<128, signed>;
-using wUInt256 = wide::integer<256, unsigned>;
+using UInt128 = wide::integer<128, unsigned>;
+using Int256 = wide::integer<256, signed>;
+using UInt256 = wide::integer<256, unsigned>;
 
-static_assert(sizeof(wInt256) == 32);
+static_assert(sizeof(Int256) == 32);
-static_assert(sizeof(wUInt256) == 32);
+static_assert(sizeof(UInt256) == 32);
-
-static constexpr __int128 minInt128() { return static_cast<unsigned __int128>(1) << 127; }
-static constexpr __int128 maxInt128() { return (static_cast<unsigned __int128>(1) << 127) - 1; }
 
 /// The standard library type traits, such as std::is_arithmetic, with one exception
 /// (std::common_type), are "set in stone". Attempting to specialize them causes undefined behavior.
@@ -26,7 +24,7 @@ struct is_signed
 };
 
 template <> struct is_signed<Int128> { static constexpr bool value = true; };
-template <> struct is_signed<wInt256> { static constexpr bool value = true; };
+template <> struct is_signed<Int256> { static constexpr bool value = true; };
 
 template <typename T>
 inline constexpr bool is_signed_v = is_signed<T>::value;
@@ -37,7 +35,8 @@ struct is_unsigned
     static constexpr bool value = std::is_unsigned_v<T>;
 };
 
-template <> struct is_unsigned<wUInt256> { static constexpr bool value = true; };
+template <> struct is_unsigned<UInt128> { static constexpr bool value = true; };
+template <> struct is_unsigned<UInt256> { static constexpr bool value = true; };
 
 template <typename T>
 inline constexpr bool is_unsigned_v = is_unsigned<T>::value;
@@ -51,8 +50,9 @@ struct is_integer
 };
 
 template <> struct is_integer<Int128> { static constexpr bool value = true; };
-template <> struct is_integer<wInt256> { static constexpr bool value = true; };
+template <> struct is_integer<UInt128> { static constexpr bool value = true; };
-template <> struct is_integer<wUInt256> { static constexpr bool value = true; };
+template <> struct is_integer<Int256> { static constexpr bool value = true; };
+template <> struct is_integer<UInt256> { static constexpr bool value = true; };
 
 template <typename T>
 inline constexpr bool is_integer_v = is_integer<T>::value;
@@ -64,7 +64,11 @@ struct is_arithmetic
     static constexpr bool value = std::is_arithmetic_v<T>;
 };
 
-template <> struct is_arithmetic<__int128> { static constexpr bool value = true; };
+template <> struct is_arithmetic<Int128> { static constexpr bool value = true; };
+template <> struct is_arithmetic<UInt128> { static constexpr bool value = true; };
+template <> struct is_arithmetic<Int256> { static constexpr bool value = true; };
+template <> struct is_arithmetic<UInt256> { static constexpr bool value = true; };
+
 
 template <typename T>
 inline constexpr bool is_arithmetic_v = is_arithmetic<T>::value;
@@ -75,9 +79,10 @@ struct make_unsigned
     typedef std::make_unsigned_t<T> type;
 };
 
-template <> struct make_unsigned<Int128> { using type = unsigned __int128; };
+template <> struct make_unsigned<Int128> { using type = UInt128; };
-template <> struct make_unsigned<wInt256>  { using type = wUInt256; };
+template <> struct make_unsigned<UInt128> { using type = UInt128; };
-template <> struct make_unsigned<wUInt256> { using type = wUInt256; };
+template <> struct make_unsigned<Int256>  { using type = UInt256; };
+template <> struct make_unsigned<UInt256> { using type = UInt256; };
 
 template <typename T> using make_unsigned_t = typename make_unsigned<T>::type;
 
@@ -87,8 +92,10 @@ struct make_signed
     typedef std::make_signed_t<T> type;
 };
 
-template <> struct make_signed<wInt256>  { using type = wInt256; };
+template <> struct make_signed<Int128>  { using type = Int128; };
-template <> struct make_signed<wUInt256> { using type = wInt256; };
+template <> struct make_signed<UInt128> { using type = Int128; };
+template <> struct make_signed<Int256>  { using type = Int256; };
+template <> struct make_signed<UInt256> { using type = Int256; };
 
 template <typename T> using make_signed_t = typename make_signed<T>::type;
 
@@ -98,8 +105,10 @@ struct is_big_int
     static constexpr bool value = false;
 };
 
-template <> struct is_big_int<wInt256> { static constexpr bool value = true; };
+template <> struct is_big_int<Int128> { static constexpr bool value = true; };
-template <> struct is_big_int<wUInt256> { static constexpr bool value = true; };
+template <> struct is_big_int<UInt128> { static constexpr bool value = true; };
+template <> struct is_big_int<Int256> { static constexpr bool value = true; };
+template <> struct is_big_int<UInt256> { static constexpr bool value = true; };
 
 template <typename T>
 inline constexpr bool is_big_int_v = is_big_int<T>::value;

base/common/itoa.h

@@ -30,9 +30,8 @@
 #include <cstddef>
 #include <cstring>
 #include <type_traits>
+#include <common/extended_types.h>
 
-using int128_t = __int128;
-using uint128_t = unsigned __int128;
 
 namespace impl
 {
@@ -106,7 +105,7 @@ using UnsignedOfSize = typename SelectType
     uint16_t,
     uint32_t,
     uint64_t,
-    uint128_t
+    __uint128_t
 >::Result;
 
 /// Holds the result of dividing an unsigned N-byte variable by 10^N resulting in
@@ -313,7 +312,8 @@ namespace convert
     }
 }
 
-static inline int digits10(uint128_t x)
+template <typename T>
+static inline int digits10(T x)
 {
     if (x < 10ULL)
         return 1;
@@ -346,8 +346,11 @@ static inline int digits10(uint128_t x)
     return 12 + digits10(x / 1000000000000ULL);
 }
 
-static inline char * writeUIntText(uint128_t x, char * p)
+template <typename T>
+static inline char * writeUIntText(T x, char * p)
 {
+    static_assert(is_unsigned_v<T>);
+
     int len = digits10(x);
     auto pp = p + len;
     while (x >= 100)
@@ -370,14 +373,28 @@ static inline char * writeLeadingMinus(char * pos)
     return pos + 1;
 }
 
-static inline char * writeSIntText(int128_t x, char * pos)
+template <typename T>
+static inline char * writeSIntText(T x, char * pos)
 {
-    static constexpr int128_t min_int128 = uint128_t(1) << 127;
+    static_assert(std::is_same_v<T, Int128> || std::is_same_v<T, Int256>);
 
-    if (unlikely(x == min_int128))
+    using UnsignedT = make_unsigned_t<T>;
+    static constexpr T min_int = UnsignedT(1) << (sizeof(T) * 8 - 1);
+
+    if (unlikely(x == min_int))
     {
-        memcpy(pos, "-170141183460469231731687303715884105728", 40);
+        if constexpr (std::is_same_v<T, Int128>)
-        return pos + 40;
+        {
+            const char * res = "-170141183460469231731687303715884105728";
+            memcpy(pos, res, strlen(res));
+            return pos + strlen(res);
+        }
+        else if constexpr (std::is_same_v<T, Int256>)
+        {
+            const char * res = "-57896044618658097711785492504343953926634992332820282019728792003956564819968";
+            memcpy(pos, res, strlen(res));
+            return pos + strlen(res);
+        }
     }
 
     if (x < 0)
@@ -385,7 +402,7 @@ static inline char * writeSIntText(int128_t x, char * pos)
         x = -x;
         pos = writeLeadingMinus(pos);
     }
-    return writeUIntText(static_cast<uint128_t>(x), pos);
+    return writeUIntText(UnsignedT(x), pos);
 }
 
 }
@@ -403,13 +420,25 @@ inline char * itoa(char8_t i, char * p)
 }
 
 template <>
-inline char * itoa<uint128_t>(uint128_t i, char * p)
+inline char * itoa(UInt128 i, char * p)
 {
     return impl::writeUIntText(i, p);
 }
 
 template <>
-inline char * itoa<int128_t>(int128_t i, char * p)
+inline char * itoa(Int128 i, char * p)
+{
+    return impl::writeSIntText(i, p);
+}
+
+template <>
+inline char * itoa(UInt256 i, char * p)
+{
+    return impl::writeUIntText(i, p);
+}
+
+template <>
+inline char * itoa(Int256 i, char * p)
 {
     return impl::writeSIntText(i, p);
 }

base/common/strong_typedef.h

@@ -4,7 +4,8 @@
 #include <type_traits>
 #include <utility>
 
-template <class T, class Tag>
+
+template <typename T, typename Tag>
 struct StrongTypedef
 {
 private:
@@ -38,14 +39,16 @@ public:
 
     bool operator==(const Self & rhs) const { return t == rhs.t; }
     bool operator<(const Self & rhs) const { return t < rhs.t; }
+    bool operator>(const Self & rhs) const { return t > rhs.t; }
 
     T & toUnderType() { return t; }
     const T & toUnderType() const { return t; }
 };
 
+
 namespace std
 {
-    template <class T, class Tag>
+    template <typename T, typename Tag>
     struct hash<StrongTypedef<T, Tag>>
     {
         size_t operator()(const StrongTypedef<T, Tag> & x) const

base/common/throwError.h

@@ -1,13 +1,15 @@
 #pragma once
+
 #include <stdexcept>
 
+
 /// Throw DB::Exception-like exception before its definition.
 /// DB::Exception derived from Poco::Exception derived from std::exception.
-/// DB::Exception generally cought as Poco::Exception. std::exception generally has other catch blocks and could lead to other outcomes.
+/// DB::Exception generally caught as Poco::Exception. std::exception generally has other catch blocks and could lead to other outcomes.
 /// DB::Exception is not defined yet. It'd better to throw Poco::Exception but we do not want to include any big header here, even <string>.
 /// So we throw some std::exception instead in the hope its catch block is the same as DB::Exception one.
 template <typename T>
-inline void throwError(const T & err)
+[[noreturn]] inline void throwError(const T & err)
 {
     throw std::runtime_error(err);
 }

base/common/wide_integer.h

@@ -58,9 +58,11 @@ public:
     using signed_base_type = int64_t;
 
     // ctors
-    constexpr integer() noexcept;
+    constexpr integer() noexcept = default;
+
     template <typename T>
     constexpr integer(T rhs) noexcept;
+
     template <typename T>
     constexpr integer(std::initializer_list<T> il) noexcept;
 
@@ -108,9 +110,9 @@ public:
     constexpr explicit operator bool() const noexcept;
 
     template <class T>
-    using __integral_not_wide_integer_class = typename std::enable_if<std::is_arithmetic<T>::value, T>::type;
+    using _integral_not_wide_integer_class = typename std::enable_if<std::is_arithmetic<T>::value, T>::type;
 
-    template <class T, class = __integral_not_wide_integer_class<T>>
+    template <class T, class = _integral_not_wide_integer_class<T>>
     constexpr operator T() const noexcept;
 
     constexpr operator long double() const noexcept;
@@ -119,25 +121,27 @@ public:
 
     struct _impl;
 
+    base_type items[_impl::item_count];
+
 private:
     template <size_t Bits2, typename Signed2>
     friend class integer;
 
     friend class std::numeric_limits<integer<Bits, signed>>;
     friend class std::numeric_limits<integer<Bits, unsigned>>;
-
-    base_type items[_impl::item_count];
 };
 
 template <typename T>
 static constexpr bool ArithmeticConcept() noexcept;
+
 template <class T1, class T2>
-using __only_arithmetic = typename std::enable_if<ArithmeticConcept<T1>() && ArithmeticConcept<T2>()>::type;
+using _only_arithmetic = typename std::enable_if<ArithmeticConcept<T1>() && ArithmeticConcept<T2>()>::type;
 
 template <typename T>
 static constexpr bool IntegralConcept() noexcept;
+
 template <class T, class T2>
-using __only_integer = typename std::enable_if<IntegralConcept<T>() && IntegralConcept<T2>()>::type;
+using _only_integer = typename std::enable_if<IntegralConcept<T>() && IntegralConcept<T2>()>::type;
 
 // Unary operators
 template <size_t Bits, typename Signed>
@@ -153,54 +157,55 @@ constexpr integer<Bits, Signed> operator+(const integer<Bits, Signed> & lhs) noe
 template <size_t Bits, typename Signed, size_t Bits2, typename Signed2>
 std::common_type_t<integer<Bits, Signed>, integer<Bits2, Signed2>> constexpr
 operator*(const integer<Bits, Signed> & lhs, const integer<Bits2, Signed2> & rhs);
-template <typename Arithmetic, typename Arithmetic2, class = __only_arithmetic<Arithmetic, Arithmetic2>>
+template <typename Arithmetic, typename Arithmetic2, class = _only_arithmetic<Arithmetic, Arithmetic2>>
 std::common_type_t<Arithmetic, Arithmetic2> constexpr operator*(const Arithmetic & rhs, const Arithmetic2 & lhs);
 
 template <size_t Bits, typename Signed, size_t Bits2, typename Signed2>
 std::common_type_t<integer<Bits, Signed>, integer<Bits2, Signed2>> constexpr
 operator/(const integer<Bits, Signed> & lhs, const integer<Bits2, Signed2> & rhs);
-template <typename Arithmetic, typename Arithmetic2, class = __only_arithmetic<Arithmetic, Arithmetic2>>
+template <typename Arithmetic, typename Arithmetic2, class = _only_arithmetic<Arithmetic, Arithmetic2>>
 std::common_type_t<Arithmetic, Arithmetic2> constexpr operator/(const Arithmetic & rhs, const Arithmetic2 & lhs);
 
 template <size_t Bits, typename Signed, size_t Bits2, typename Signed2>
 std::common_type_t<integer<Bits, Signed>, integer<Bits2, Signed2>> constexpr
 operator+(const integer<Bits, Signed> & lhs, const integer<Bits2, Signed2> & rhs);
-template <typename Arithmetic, typename Arithmetic2, class = __only_arithmetic<Arithmetic, Arithmetic2>>
+template <typename Arithmetic, typename Arithmetic2, class = _only_arithmetic<Arithmetic, Arithmetic2>>
 std::common_type_t<Arithmetic, Arithmetic2> constexpr operator+(const Arithmetic & rhs, const Arithmetic2 & lhs);
 
 template <size_t Bits, typename Signed, size_t Bits2, typename Signed2>
 std::common_type_t<integer<Bits, Signed>, integer<Bits2, Signed2>> constexpr
 operator-(const integer<Bits, Signed> & lhs, const integer<Bits2, Signed2> & rhs);
-template <typename Arithmetic, typename Arithmetic2, class = __only_arithmetic<Arithmetic, Arithmetic2>>
+template <typename Arithmetic, typename Arithmetic2, class = _only_arithmetic<Arithmetic, Arithmetic2>>
 std::common_type_t<Arithmetic, Arithmetic2> constexpr operator-(const Arithmetic & rhs, const Arithmetic2 & lhs);
 
 template <size_t Bits, typename Signed, size_t Bits2, typename Signed2>
 std::common_type_t<integer<Bits, Signed>, integer<Bits2, Signed2>> constexpr
 operator%(const integer<Bits, Signed> & lhs, const integer<Bits2, Signed2> & rhs);
-template <typename Integral, typename Integral2, class = __only_integer<Integral, Integral2>>
+template <typename Integral, typename Integral2, class = _only_integer<Integral, Integral2>>
 std::common_type_t<Integral, Integral2> constexpr operator%(const Integral & rhs, const Integral2 & lhs);
 
 template <size_t Bits, typename Signed, size_t Bits2, typename Signed2>
 std::common_type_t<integer<Bits, Signed>, integer<Bits2, Signed2>> constexpr
 operator&(const integer<Bits, Signed> & lhs, const integer<Bits2, Signed2> & rhs);
-template <typename Integral, typename Integral2, class = __only_integer<Integral, Integral2>>
+template <typename Integral, typename Integral2, class = _only_integer<Integral, Integral2>>
 std::common_type_t<Integral, Integral2> constexpr operator&(const Integral & rhs, const Integral2 & lhs);
 
 template <size_t Bits, typename Signed, size_t Bits2, typename Signed2>
 std::common_type_t<integer<Bits, Signed>, integer<Bits2, Signed2>> constexpr
 operator|(const integer<Bits, Signed> & lhs, const integer<Bits2, Signed2> & rhs);
-template <typename Integral, typename Integral2, class = __only_integer<Integral, Integral2>>
+template <typename Integral, typename Integral2, class = _only_integer<Integral, Integral2>>
 std::common_type_t<Integral, Integral2> constexpr operator|(const Integral & rhs, const Integral2 & lhs);
 
 template <size_t Bits, typename Signed, size_t Bits2, typename Signed2>
 std::common_type_t<integer<Bits, Signed>, integer<Bits2, Signed2>> constexpr
 operator^(const integer<Bits, Signed> & lhs, const integer<Bits2, Signed2> & rhs);
-template <typename Integral, typename Integral2, class = __only_integer<Integral, Integral2>>
+template <typename Integral, typename Integral2, class = _only_integer<Integral, Integral2>>
 std::common_type_t<Integral, Integral2> constexpr operator^(const Integral & rhs, const Integral2 & lhs);
 
 // TODO: Integral
 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>
 constexpr integer<Bits, Signed> operator>>(const integer<Bits, Signed> & lhs, int n) noexcept;
 
@@ -217,32 +222,32 @@ constexpr integer<Bits, Signed> operator>>(const integer<Bits, Signed> & lhs, In
 
 template <size_t Bits, typename Signed, size_t Bits2, typename Signed2>
 constexpr bool operator<(const integer<Bits, Signed> & lhs, const integer<Bits2, Signed2> & rhs);
-template <typename Arithmetic, typename Arithmetic2, class = __only_arithmetic<Arithmetic, Arithmetic2>>
+template <typename Arithmetic, typename Arithmetic2, class = _only_arithmetic<Arithmetic, Arithmetic2>>
 constexpr bool operator<(const Arithmetic & rhs, const Arithmetic2 & lhs);
 
 template <size_t Bits, typename Signed, size_t Bits2, typename Signed2>
 constexpr bool operator>(const integer<Bits, Signed> & lhs, const integer<Bits2, Signed2> & rhs);
-template <typename Arithmetic, typename Arithmetic2, class = __only_arithmetic<Arithmetic, Arithmetic2>>
+template <typename Arithmetic, typename Arithmetic2, class = _only_arithmetic<Arithmetic, Arithmetic2>>
 constexpr bool operator>(const Arithmetic & rhs, const Arithmetic2 & lhs);
 
 template <size_t Bits, typename Signed, size_t Bits2, typename Signed2>
 constexpr bool operator<=(const integer<Bits, Signed> & lhs, const integer<Bits2, Signed2> & rhs);
-template <typename Arithmetic, typename Arithmetic2, class = __only_arithmetic<Arithmetic, Arithmetic2>>
+template <typename Arithmetic, typename Arithmetic2, class = _only_arithmetic<Arithmetic, Arithmetic2>>
 constexpr bool operator<=(const Arithmetic & rhs, const Arithmetic2 & lhs);
 
 template <size_t Bits, typename Signed, size_t Bits2, typename Signed2>
 constexpr bool operator>=(const integer<Bits, Signed> & lhs, const integer<Bits2, Signed2> & rhs);
-template <typename Arithmetic, typename Arithmetic2, class = __only_arithmetic<Arithmetic, Arithmetic2>>
+template <typename Arithmetic, typename Arithmetic2, class = _only_arithmetic<Arithmetic, Arithmetic2>>
 constexpr bool operator>=(const Arithmetic & rhs, const Arithmetic2 & lhs);
 
 template <size_t Bits, typename Signed, size_t Bits2, typename Signed2>
 constexpr bool operator==(const integer<Bits, Signed> & lhs, const integer<Bits2, Signed2> & rhs);
-template <typename Arithmetic, typename Arithmetic2, class = __only_arithmetic<Arithmetic, Arithmetic2>>
+template <typename Arithmetic, typename Arithmetic2, class = _only_arithmetic<Arithmetic, Arithmetic2>>
 constexpr bool operator==(const Arithmetic & rhs, const Arithmetic2 & lhs);
 
 template <size_t Bits, typename Signed, size_t Bits2, typename Signed2>
 constexpr bool operator!=(const integer<Bits, Signed> & lhs, const integer<Bits2, Signed2> & rhs);
-template <typename Arithmetic, typename Arithmetic2, class = __only_arithmetic<Arithmetic, Arithmetic2>>
+template <typename Arithmetic, typename Arithmetic2, class = _only_arithmetic<Arithmetic, Arithmetic2>>
 constexpr bool operator!=(const Arithmetic & rhs, const Arithmetic2 & lhs);
 
 }

base/common/wide_integer_impl.h

@@ -5,6 +5,7 @@
 /// (See at http://www.boost.org/LICENSE_1_0.txt)
 
 #include "throwError.h"
+
 #include <cmath>
 #include <cfloat>
 #include <cassert>
@@ -81,7 +82,7 @@ public:
             res.items[T::_impl::big(0)] = std::numeric_limits<typename wide::integer<Bits, Signed>::signed_base_type>::min();
             return res;
         }
-        return 0;
+        return wide::integer<Bits, Signed>(0);
     }
 
     static constexpr wide::integer<Bits, Signed> max() noexcept
@@ -176,7 +177,7 @@ struct integer<Bits, Signed>::_impl
     constexpr static bool is_negative(const integer<B, T> & n) noexcept
     {
         if constexpr (std::is_same_v<T, signed>)
-            return static_cast<signed_base_type>(n.items[big(0)]) < 0;
+            return static_cast<signed_base_type>(n.items[integer<B, T>::_impl::big(0)]) < 0;
         else
             return false;
     }
@@ -193,40 +194,36 @@ struct integer<Bits, Signed>::_impl
     template <size_t B, class S>
     constexpr static integer<B, S> make_positive(const integer<B, S> & n) noexcept
     {
-        return is_negative(n) ? operator_unary_minus(n) : n;
+        return is_negative(n) ? integer<B, S>(operator_unary_minus(n)) : n;
     }
 
     template <typename T>
     __attribute__((no_sanitize("undefined"))) constexpr static auto to_Integral(T f) noexcept
     {
-        if constexpr (std::is_same_v<T, __int128>)
+        if constexpr (std::is_signed_v<T>)
-            return f;
-        else if constexpr (std::is_signed_v<T>)
             return static_cast<int64_t>(f);
         else
             return static_cast<uint64_t>(f);
     }
 
     template <typename Integral>
-    constexpr static void wide_integer_from_bultin(integer<Bits, Signed> & self, Integral rhs) noexcept
+    constexpr static void wide_integer_from_builtin(integer<Bits, Signed> & self, Integral rhs) noexcept
     {
-        self.items[0] = _impl::to_Integral(rhs);
+        static_assert(sizeof(Integral) <= sizeof(base_type));
-        if constexpr (std::is_same_v<Integral, __int128>)
-            self.items[1] = rhs >> base_bits;
 
-        constexpr const unsigned start = (sizeof(Integral) == 16) ? 2 : 1;
+        self.items[0] = _impl::to_Integral(rhs);
 
         if constexpr (std::is_signed_v<Integral>)
         {
             if (rhs < 0)
             {
-                for (unsigned i = start; i < item_count; ++i)
+                for (size_t i = 1; i < item_count; ++i)
                     self.items[i] = -1;
                 return;
             }
         }
 
-        for (unsigned i = start; i < item_count; ++i)
+        for (size_t i = 1; i < item_count; ++i)
             self.items[i] = 0;
     }
 
@@ -239,7 +236,8 @@ struct integer<Bits, Signed>::_impl
      * a_(n - 1) = a_n * max_int + b2, a_n <= max_int <- base case.
      */
     template <class T>
-    constexpr static void set_multiplier(integer<Bits, Signed> & self, T t) noexcept {
+    constexpr static void set_multiplier(integer<Bits, Signed> & self, T t) noexcept
+    {
         constexpr uint64_t max_int = std::numeric_limits<uint64_t>::max();
 
         /// Implementation specific behaviour on overflow (if we don't check here, stack overflow will triggered in bigint_cast).
@@ -260,7 +258,8 @@ struct integer<Bits, Signed>::_impl
         self += static_cast<uint64_t>(t - alpha * static_cast<T>(max_int)); // += b_i
     }
 
-    constexpr static void wide_integer_from_bultin(integer<Bits, Signed>& self, double rhs) noexcept {
+    constexpr static void wide_integer_from_builtin(integer<Bits, Signed>& self, double rhs) noexcept
+    {
         constexpr int64_t max_int = std::numeric_limits<int64_t>::max();
         constexpr int64_t min_int = std::numeric_limits<int64_t>::min();
 
@@ -383,13 +382,13 @@ struct integer<Bits, Signed>::_impl
             if (bit_shift)
                 lhs.items[big(items_shift)] |= std::numeric_limits<base_type>::max() << (base_bits - bit_shift);
 
-            for (unsigned i = item_count - items_shift; i < items_shift; ++i)
+            for (unsigned i = 0; i < items_shift; ++i)
-                lhs.items[little(i)] = std::numeric_limits<base_type>::max();
+                lhs.items[big(i)] = std::numeric_limits<base_type>::max();
         }
         else
         {
-            for (unsigned i = item_count - items_shift; i < items_shift; ++i)
+            for (unsigned i = 0; i < items_shift; ++i)
-                lhs.items[little(i)] = 0;
+                lhs.items[big(i)] = 0;
         }
 
         return lhs;
@@ -397,23 +396,23 @@ struct integer<Bits, Signed>::_impl
 
 private:
     template <typename T>
-    constexpr static base_type get_item(const T & x, unsigned number)
+    constexpr static base_type get_item(const T & x, unsigned idx)
     {
         if constexpr (IsWideInteger<T>::value)
         {
-            if (number < T::_impl::item_count)
+            if (idx < T::_impl::item_count)
-                return x.items[number];
+                return x.items[idx];
             return 0;
         }
         else
         {
             if constexpr (sizeof(T) <= sizeof(base_type))
             {
-                if (!number)
+                if (0 == idx)
                     return x;
             }
-            else if (number * sizeof(base_type) < sizeof(T))
+            else if (idx * sizeof(base_type) < sizeof(T))
-                return x >> (number * base_bits); // & std::numeric_limits<base_type>::max()
+                return x >> (idx * base_bits); // & std::numeric_limits<base_type>::max()
             return 0;
         }
     }
@@ -439,7 +438,7 @@ private:
 
         for (unsigned i = 1; i < item_count; ++i)
         {
-            if (underflows[i-1])
+            if (underflows[i - 1])
             {
                 base_type & res_item = res.items[little(i)];
                 if (res_item == 0)
@@ -472,7 +471,7 @@ private:
 
         for (unsigned i = 1; i < item_count; ++i)
         {
-            if (overflows[i-1])
+            if (overflows[i - 1])
             {
                 base_type & res_item = res.items[little(i)];
                 ++res_item;
@@ -532,6 +531,17 @@ private:
             res.items[little(2)] = r12 >> 64;
             return res;
         }
+        else if constexpr (Bits == 128 && sizeof(base_type) == 8)
+        {
+            using CompilerUInt128 = unsigned __int128;
+            CompilerUInt128 a = (CompilerUInt128(lhs.items[1]) << 64) + lhs.items[0];
+            CompilerUInt128 b = (CompilerUInt128(rhs.items[1]) << 64) + rhs.items[0];
+            CompilerUInt128 c = a * b;
+            integer<Bits, Signed> res;
+            res.items[0] = c;
+            res.items[1] = c >> 64;
+            return res;
+        }
         else
         {
             integer<Bits, Signed> res{};
@@ -657,7 +667,7 @@ public:
     }
 
     template <typename T>
-    constexpr static bool operator_more(const integer<Bits, Signed> & lhs, const T & rhs) noexcept
+    constexpr static bool operator_greater(const integer<Bits, Signed> & lhs, const T & rhs) noexcept
     {
         if constexpr (should_keep_size<T>())
         {
@@ -677,7 +687,7 @@ public:
         else
         {
             static_assert(IsWideInteger<T>::value);
-            return std::common_type_t<integer<Bits, Signed>, T>::_impl::operator_more(T(lhs), rhs);
+            return std::common_type_t<integer<Bits, Signed>, T>::_impl::operator_greater(T(lhs), rhs);
         }
     }
 
@@ -764,7 +774,6 @@ public:
         }
     }
 
-private:
     template <typename T>
     constexpr static bool is_zero(const T & x)
     {
@@ -781,46 +790,65 @@ private:
     }
 
     /// returns quotient as result and remainder in numerator.
-    template <typename T>
+    template <size_t Bits2>
-    constexpr static T divide(T & numerator, T && denominator)
+    constexpr static integer<Bits2, unsigned> divide(integer<Bits2, unsigned> & numerator, integer<Bits2, unsigned> denominator)
     {
-        if (is_zero(denominator))
+        static_assert(std::is_unsigned_v<Signed>);
-            throwError("divide by zero");
 
-        T & n = numerator;
+        if constexpr (Bits == 128 && sizeof(base_type) == 8)
-        T & d = denominator;
-        T x = 1;
-        T quotient = 0;
-
-        while (!operator_more(d, n) && operator_eq(operator_amp(shift_right(d, base_bits * item_count - 1), 1), 0))
         {
-            x = shift_left(x, 1);
+            using CompilerUInt128 = unsigned __int128;
-            d = shift_left(d, 1);
+
+            CompilerUInt128 a = (CompilerUInt128(numerator.items[1]) << 64) + numerator.items[0];
+            CompilerUInt128 b = (CompilerUInt128(denominator.items[1]) << 64) + denominator.items[0];
+            CompilerUInt128 c = a / b;
+
+            integer<Bits, Signed> res;
+            res.items[0] = c;
+            res.items[1] = c >> 64;
+
+            CompilerUInt128 remainder = a - b * c;
+            numerator.items[0] = remainder;
+            numerator.items[1] = remainder >> 64;
+
+            return res;
         }
 
-        while (!operator_eq(x, 0))
+        if (is_zero(denominator))
+            throwError("Division by zero");
+
+        integer<Bits2, unsigned> x = 1;
+        integer<Bits2, unsigned> quotient = 0;
+
+        while (!operator_greater(denominator, numerator) && is_zero(operator_amp(shift_right(denominator, Bits2 - 1), 1)))
         {
-            if (!operator_more(d, n))
+            x = shift_left(x, 1);
+            denominator = shift_left(denominator, 1);
+        }
+
+        while (!is_zero(x))
+        {
+            if (!operator_greater(denominator, numerator))
             {
-                n = operator_minus(n, d);
+                numerator = operator_minus(numerator, denominator);
                 quotient = operator_pipe(quotient, x);
             }
 
             x = shift_right(x, 1);
-            d = shift_right(d, 1);
+            denominator = shift_right(denominator, 1);
         }
 
         return quotient;
     }
 
-public:
     template <typename T>
     constexpr static auto operator_slash(const integer<Bits, Signed> & lhs, const T & rhs)
     {
         if constexpr (should_keep_size<T>())
         {
-            integer<Bits, Signed> numerator = make_positive(lhs);
+            integer<Bits, unsigned> numerator = make_positive(lhs);
-            integer<Bits, Signed> quotient = divide(numerator, make_positive(integer<Bits, Signed>(rhs)));
+            integer<Bits, unsigned> denominator = make_positive(integer<Bits, Signed>(rhs));
+            integer<Bits, unsigned> quotient = integer<Bits, unsigned>::_impl::divide(numerator, std::move(denominator));
 
             if (std::is_same_v<Signed, signed> && is_negative(rhs) != is_negative(lhs))
                 quotient = operator_unary_minus(quotient);
@@ -838,8 +866,9 @@ public:
     {
         if constexpr (should_keep_size<T>())
         {
-            integer<Bits, Signed> remainder = make_positive(lhs);
+            integer<Bits, unsigned> remainder = make_positive(lhs);
-            divide(remainder, make_positive(integer<Bits, Signed>(rhs)));
+            integer<Bits, unsigned> denominator = make_positive(integer<Bits, Signed>(rhs));
+            integer<Bits, unsigned>::_impl::divide(remainder, std::move(denominator));
 
             if (std::is_same_v<Signed, signed> && is_negative(lhs))
                 remainder = operator_unary_minus(remainder);
@@ -905,7 +934,7 @@ public:
                     ++c;
                 }
                 else
-                    throwError("invalid char from");
+                    throwError("Invalid char from");
             }
         }
         else
@@ -913,7 +942,7 @@ public:
             while (*c)
             {
                 if (*c < '0' || *c > '9')
-                    throwError("invalid char from");
+                    throwError("Invalid char from");
 
                 res = multiply(res, 10U);
                 res = plus(res, *c - '0');
@@ -930,11 +959,6 @@ public:
 
 // Members
 
-template <size_t Bits, typename Signed>
-constexpr integer<Bits, Signed>::integer() noexcept
-    : items{}
-{}
-
 template <size_t Bits, typename Signed>
 template <typename T>
 constexpr integer<Bits, Signed>::integer(T rhs) noexcept
@@ -943,7 +967,7 @@ constexpr integer<Bits, Signed>::integer(T rhs) noexcept
     if constexpr (IsWideInteger<T>::value)
         _impl::wide_integer_from_wide_integer(*this, rhs);
     else
-        _impl::wide_integer_from_bultin(*this, rhs);
+        _impl::wide_integer_from_builtin(*this, rhs);
 }
 
 template <size_t Bits, typename Signed>
@@ -956,10 +980,19 @@ constexpr integer<Bits, Signed>::integer(std::initializer_list<T> il) noexcept
         if constexpr (IsWideInteger<T>::value)
             _impl::wide_integer_from_wide_integer(*this, *il.begin());
         else
-            _impl::wide_integer_from_bultin(*this, *il.begin());
+            _impl::wide_integer_from_builtin(*this, *il.begin());
+    }
+    else if (il.size() == 0)
+    {
+        _impl::wide_integer_from_builtin(*this, 0);
     }
     else
-        _impl::wide_integer_from_bultin(*this, 0);
+    {
+        auto it = il.begin();
+        for (size_t i = 0; i < _impl::item_count; ++i)
+            if (it < il.end())
+                items[i] = *it;
+    }
 }
 
 template <size_t Bits, typename Signed>
@@ -974,7 +1007,7 @@ template <size_t Bits, typename Signed>
 template <typename T>
 constexpr integer<Bits, Signed> & integer<Bits, Signed>::operator=(T rhs) noexcept
 {
-    _impl::wide_integer_from_bultin(*this, rhs);
+    _impl::wide_integer_from_builtin(*this, rhs);
     return *this;
 }
 
@@ -1057,7 +1090,7 @@ constexpr integer<Bits, Signed> & integer<Bits, Signed>::operator>>=(int n) noex
 {
     if (static_cast<size_t>(n) >= Bits)
     {
-        if (is_negative(*this))
+        if (_impl::is_negative(*this))
             *this = -1;
         else
             *this = 0;
@@ -1107,16 +1140,17 @@ template <size_t Bits, typename Signed>
 template <class T, class>
 constexpr integer<Bits, Signed>::operator T() const noexcept
 {
-    if constexpr (std::is_same_v<T, __int128>)
+    static_assert(std::numeric_limits<T>::is_integer);
-    {
+
-        static_assert(Bits >= 128);
+    /// NOTE: memcpy will suffice, but unfortunately, this function is constexpr.
-        return (__int128(items[1]) << 64) | items[0];
+
-    }
+    using UnsignedT = std::make_unsigned_t<T>;
-    else
+
-    {
+    UnsignedT res{};
-        static_assert(std::numeric_limits<T>::is_integer);
+    for (unsigned i = 0; i < _impl::item_count && i < (sizeof(T) + sizeof(base_type) - 1) / sizeof(base_type); ++i)
-        return items[0];
+        res += UnsignedT(items[i]) << (sizeof(base_type) * 8 * i);
-    }
+
+    return res;
 }
 
 template <size_t Bits, typename Signed>
@@ -1280,7 +1314,7 @@ template <size_t Bits, typename Signed>
 constexpr integer<Bits, Signed> operator<<(const integer<Bits, Signed> & lhs, int n) noexcept
 {
     if (static_cast<size_t>(n) >= Bits)
-        return 0;
+        return integer<Bits, Signed>(0);
     if (n <= 0)
         return lhs;
     return integer<Bits, Signed>::_impl::shift_left(lhs, n);
@@ -1289,7 +1323,7 @@ template <size_t Bits, typename Signed>
 constexpr integer<Bits, Signed> operator>>(const integer<Bits, Signed> & lhs, int n) noexcept
 {
     if (static_cast<size_t>(n) >= Bits)
-        return 0;
+        return integer<Bits, Signed>(0);
     if (n <= 0)
         return lhs;
     return integer<Bits, Signed>::_impl::shift_right(lhs, n);
@@ -1309,7 +1343,7 @@ constexpr bool operator<(const Arithmetic & lhs, const Arithmetic2 & rhs)
 template <size_t Bits, typename Signed, size_t Bits2, typename Signed2>
 constexpr bool operator>(const integer<Bits, Signed> & lhs, const integer<Bits2, Signed2> & rhs)
 {
-    return std::common_type_t<integer<Bits, Signed>, integer<Bits2, Signed2>>::_impl::operator_more(lhs, rhs);
+    return std::common_type_t<integer<Bits, Signed>, integer<Bits2, Signed2>>::_impl::operator_greater(lhs, rhs);
 }
 template <typename Arithmetic, typename Arithmetic2, class>
 constexpr bool operator>(const Arithmetic & lhs, const Arithmetic2 & rhs)
@@ -1332,7 +1366,7 @@ constexpr bool operator<=(const Arithmetic & lhs, const Arithmetic2 & rhs)
 template <size_t Bits, typename Signed, size_t Bits2, typename Signed2>
 constexpr bool operator>=(const integer<Bits, Signed> & lhs, const integer<Bits2, Signed2> & rhs)
 {
-    return std::common_type_t<integer<Bits, Signed>, integer<Bits2, Signed2>>::_impl::operator_more(lhs, rhs)
+    return std::common_type_t<integer<Bits, Signed>, integer<Bits2, Signed2>>::_impl::operator_greater(lhs, rhs)
         || std::common_type_t<integer<Bits, Signed>, integer<Bits2, Signed2>>::_impl::operator_eq(lhs, rhs);
 }
 template <typename Arithmetic, typename Arithmetic2, class>

base/common/wide_integer_to_string.h

@@ -1,9 +1,12 @@
 #pragma once
 
 #include <string>
+#include <ostream>
+#include <fmt/format.h>
 
 #include "wide_integer.h"
 
+
 namespace wide
 {
 
@@ -33,3 +36,34 @@ inline std::string to_string(const integer<Bits, Signed> & n)
 }
 
 }
+
+
+template <size_t Bits, typename Signed>
+std::ostream & operator<<(std::ostream & out, const wide::integer<Bits, Signed> & value)
+{
+    return out << to_string(value);
+}
+
+
+/// See https://fmt.dev/latest/api.html#formatting-user-defined-types
+template <size_t Bits, typename Signed>
+struct fmt::formatter<wide::integer<Bits, Signed>>
+{
+    constexpr auto parse(format_parse_context & ctx)
+    {
+        auto it = ctx.begin();
+        auto end = ctx.end();
+
+        /// Only support {}.
+        if (it != end && *it != '}')
+            throw format_error("invalid format");
+
+        return it;
+    }
+
+    template <typename FormatContext>
+    auto format(const wide::integer<Bits, Signed> & value, FormatContext & ctx)
+    {
+        return format_to(ctx.out(), "{}", to_string(value));
+    }
+};

base/daemon/SentryWriter.cpp

@@ -102,7 +102,7 @@ void SentryWriter::initialize(Poco::Util::LayeredConfiguration & config)
     auto * logger = &Poco::Logger::get("SentryWriter");
     if (config.getBool("send_crash_reports.enabled", false))
     {
-        if (debug || (strlen(VERSION_OFFICIAL) > 0))
+        if (debug || (strlen(VERSION_OFFICIAL) > 0)) //-V560
         {
             enabled = true;
         }

base/glibc-compatibility/CMakeLists.txt

@@ -15,7 +15,7 @@ if (GLIBC_COMPATIBILITY)
 
     add_headers_and_sources(glibc_compatibility .)
     add_headers_and_sources(glibc_compatibility musl)
-    if (ARCH_ARM)
+    if (ARCH_AARCH64)
         list (APPEND glibc_compatibility_sources musl/aarch64/syscall.s musl/aarch64/longjmp.s)
         set (musl_arch_include_dir musl/aarch64)
     elseif (ARCH_AMD64)

base/glibc-compatibility/musl/lgamma.c

@@ -78,6 +78,9 @@
  *
  */
 
+// Disable warnings by PVS-Studio
+//-V::GA
+
 static const double
 pi  =  3.14159265358979311600e+00, /* 0x400921FB, 0x54442D18 */
 a0  =  7.72156649015328655494e-02, /* 0x3FB3C467, 0xE37DB0C8 */

base/glibc-compatibility/musl/lgammal.c

@@ -85,6 +85,9 @@
  *
  */
 
+// Disable warnings by PVS-Studio
+//-V::GA
+
 #include <stdint.h>
 #include <math.h>
 #include "libm.h"

base/glibc-compatibility/musl/libm.h

@@ -155,7 +155,7 @@ static inline long double fp_barrierl(long double x)
 static inline void fp_force_evalf(float x)
 {
 	volatile float y;
-	y = x;
+	y = x; //-V1001
 }
 #endif
 
@@ -164,7 +164,7 @@ static inline void fp_force_evalf(float x)
 static inline void fp_force_eval(double x)
 {
 	volatile double y;
-	y = x;
+	y = x; //-V1001
 }
 #endif
 
@@ -173,7 +173,7 @@ static inline void fp_force_eval(double x)
 static inline void fp_force_evall(long double x)
 {
 	volatile long double y;
-	y = x;
+	y = x; //-V1001
 }
 #endif
 

base/glibc-compatibility/musl/powf.c

@@ -3,6 +3,9 @@
  * SPDX-License-Identifier: MIT
  */
 
+// Disable warnings by PVS-Studio
+//-V::GA
+
 #include <math.h>
 #include <stdint.h>
 #include "libm.h"

base/loggers/Loggers.cpp

@@ -40,7 +40,7 @@ void Loggers::buildLoggers(Poco::Util::AbstractConfiguration & config, Poco::Log
             split->addTextLog(log, text_log_max_priority);
 
     auto current_logger = config.getString("logger", "");
-    if (config_logger == current_logger)
+    if (config_logger == current_logger) //-V1051
         return;
 
     config_logger = current_logger;

base/pcg-random/pcg_extras.hpp

@@ -447,69 +447,6 @@ inline SrcIter uneven_copy(SrcIter src_first,
                             std::integral_constant<bool, DEST_IS_SMALLER>{});
 }
 
-/* generate_to, fill in a fixed-size array of integral type using a SeedSeq
- * (actually works for any random-access iterator)
- */
-
-template <size_t size, typename SeedSeq, typename DestIter>
-inline void generate_to_impl(SeedSeq&& generator, DestIter dest,
-                             std::true_type)
-{
-    generator.generate(dest, dest+size);
-}
-
-template <size_t size, typename SeedSeq, typename DestIter>
-void generate_to_impl(SeedSeq&& generator, DestIter dest,
-                      std::false_type)
-{
-    typedef typename std::iterator_traits<DestIter>::value_type dest_t;
-    constexpr auto DEST_SIZE = sizeof(dest_t);
-    constexpr auto GEN_SIZE  = sizeof(uint32_t);
-
-    constexpr bool GEN_IS_SMALLER = GEN_SIZE < DEST_SIZE;
-    constexpr size_t FROM_ELEMS =
-        GEN_IS_SMALLER
-            ? size * ((DEST_SIZE+GEN_SIZE-1) / GEN_SIZE)
-            : (size + (GEN_SIZE / DEST_SIZE) - 1)
-                / ((GEN_SIZE / DEST_SIZE) + GEN_IS_SMALLER);
-                        //  this odd code ^^^^^^^^^^^^^^^^^ is work-around for
-                        //  a bug: http://llvm.org/bugs/show_bug.cgi?id=21287
-
-    if (FROM_ELEMS <= 1024) {
-        uint32_t buffer[FROM_ELEMS];
-        generator.generate(buffer, buffer+FROM_ELEMS);
-        uneven_copy(buffer, dest, dest+size);
-    } else {
-        uint32_t* buffer = static_cast<uint32_t*>(malloc(GEN_SIZE * FROM_ELEMS));
-        generator.generate(buffer, buffer+FROM_ELEMS);
-        uneven_copy(buffer, dest, dest+size);
-        free(static_cast<void*>(buffer));
-    }
-}
-
-template <size_t size, typename SeedSeq, typename DestIter>
-inline void generate_to(SeedSeq&& generator, DestIter dest)
-{
-    typedef typename std::iterator_traits<DestIter>::value_type dest_t;
-    constexpr bool IS_32BIT = sizeof(dest_t) == sizeof(uint32_t);
-
-    generate_to_impl<size>(std::forward<SeedSeq>(generator), dest,
-                           std::integral_constant<bool, IS_32BIT>{});
-}
-
-/* generate_one, produce a value of integral type using a SeedSeq
- * (optionally, we can have it produce more than one and pick which one
- * we want)
- */
-
-template <typename UInt, size_t i = 0UL, size_t N = i+1UL, typename SeedSeq>
-inline UInt generate_one(SeedSeq&& generator)
-{
-    UInt result[N];
-    generate_to<N>(std::forward<SeedSeq>(generator), result);
-    return result[i];
-}
-
 template <typename RngType>
 auto bounded_rand(RngType& rng, typename RngType::result_type upper_bound)
         -> typename RngType::result_type
@@ -517,7 +454,7 @@ auto bounded_rand(RngType& rng, typename RngType::result_type upper_bound)
     typedef typename RngType::result_type rtype;
     rtype threshold = (RngType::max() - RngType::min() + rtype(1) - upper_bound)
                     % upper_bound;
-    for (;;) {
+    for (;;) { //-V1044
         rtype r = rng() - RngType::min();
         if (r >= threshold)
             return r % upper_bound;

base/pcg-random/pcg_random.hpp

@@ -928,7 +928,7 @@ struct rxs_m_xs_mixin {
         constexpr bitcount_t shift = bits - xtypebits;
         constexpr bitcount_t mask = (1 << opbits) - 1;
         bitcount_t rshift =
-            opbits ? bitcount_t(internal >> (bits - opbits)) & mask : 0;
+            opbits ? bitcount_t(internal >> (bits - opbits)) & mask : 0; //-V547
         internal ^= internal >> (opbits + rshift);
         internal *= mcg_multiplier<itype>::multiplier();
         xtype result = internal >> shift;
@@ -950,7 +950,7 @@ struct rxs_m_xs_mixin {
 
         internal *= mcg_unmultiplier<itype>::unmultiplier();
 
-        bitcount_t rshift = opbits ? (internal >> (bits - opbits)) & mask : 0;
+        bitcount_t rshift = opbits ? (internal >> (bits - opbits)) & mask : 0; //-V547
         internal = unxorshift(internal, bits, opbits + rshift);
 
         return internal;
@@ -975,7 +975,7 @@ struct rxs_m_mixin {
                                  :                    2;
         constexpr bitcount_t shift = bits - xtypebits;
         constexpr bitcount_t mask = (1 << opbits) - 1;
-        bitcount_t rshift = opbits ? (internal >> (bits - opbits)) & mask : 0;
+        bitcount_t rshift = opbits ? (internal >> (bits - opbits)) & mask : 0; //-V547
         internal ^= internal >> (opbits + rshift);
         internal *= mcg_multiplier<itype>::multiplier();
         xtype result = internal >> shift;
@@ -1366,7 +1366,7 @@ void extended<table_pow2,advance_pow2,baseclass,extvalclass,kdd>::selfinit()
     //      - any strange correlations would only be apparent if we
     //        were to backstep the generator so that the base generator
     //        was generating the same values again
-    result_type xdiff = baseclass::operator()() - baseclass::operator()();
+    result_type xdiff = baseclass::operator()() - baseclass::operator()(); //-V501
     for (size_t i = 0; i < table_size; ++i) {
         data_[i] = baseclass::operator()() ^ xdiff;
     }

cmake/find/llvm.cmake

@@ -2,7 +2,7 @@ if (APPLE OR SPLIT_SHARED_LIBRARIES OR NOT ARCH_AMD64)
     set (ENABLE_EMBEDDED_COMPILER OFF CACHE INTERNAL "")
 endif()
 
-option (ENABLE_EMBEDDED_COMPILER "Set to TRUE to enable support for 'compile_expressions' option for query execution" ${ENABLE_LIBRARIES})
+option (ENABLE_EMBEDDED_COMPILER "Enable support for 'compile_expressions' option for query execution" ON)
 # Broken in macos. TODO: update clang, re-test, enable on Apple
 if (ENABLE_EMBEDDED_COMPILER AND NOT SPLIT_SHARED_LIBRARIES AND ARCH_AMD64 AND NOT (SANITIZE STREQUAL "undefined"))
     option (USE_INTERNAL_LLVM_LIBRARY "Use bundled or system LLVM library." ${NOT_UNBUNDLED})

contrib/datasketches-cpp

@@ -1 +1 @@
-Subproject commit f915d35b2de676683493c86c585141a1e1c83334
+Subproject commit 7d73d7610db31d4e1ecde0fb3a7ee90ef371207f

docker/test/fasttest/run.sh

@@ -308,6 +308,8 @@ function run_tests
         01354_order_by_tuple_collate_const
         01355_ilike
         01411_bayesian_ab_testing
+        01798_uniq_theta_sketch
+        01799_long_uniq_theta_sketch
         collate
         collation
         _orc_
@@ -370,6 +372,10 @@ function run_tests
 
         # Depends on AWS
         01801_s3_cluster
+
+        # Depends on LLVM JIT
+        01852_jit_if
+        01865_jit_comparison_constant_result
     )
 
     (time clickhouse-test --hung-check -j 8 --order=random --use-skip-list --no-long --testname --shard --zookeeper --skip "${TESTS_TO_SKIP[@]}" -- "$FASTTEST_FOCUS" 2>&1 ||:) | ts '%Y-%m-%d %H:%M:%S' | tee "$FASTTEST_OUTPUT/test_log.txt"

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

@@ -14,11 +14,6 @@
                 <max_memory_usage>
                     <max>10G</max>
                 </max_memory_usage>
-
-                <!-- Not ready for production -->
-                <compile_expressions>
-                    <readonly />
-                </compile_expressions>
             </constraints>
         </default>
     </profiles>

docker/test/testflows/runner/Dockerfile

@@ -35,7 +35,7 @@ RUN apt-get update \
 ENV TZ=Europe/Moscow
 RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
 
-RUN pip3 install urllib3 testflows==1.6.74 docker-compose docker dicttoxml kazoo tzlocal
+RUN pip3 install urllib3 testflows==1.6.74 docker-compose docker dicttoxml kazoo tzlocal python-dateutil numpy
 
 ENV DOCKER_CHANNEL stable
 ENV DOCKER_VERSION 17.09.1-ce
@@ -74,4 +74,3 @@ VOLUME /var/lib/docker
 EXPOSE 2375
 ENTRYPOINT ["dockerd-entrypoint.sh"]
 CMD ["sh", "-c", "python3 regression.py --no-color -o classic --local --clickhouse-binary-path ${CLICKHOUSE_TESTS_SERVER_BIN_PATH} --log test.log ${TESTFLOWS_OPTS}; cat test.log | tfs report results --format json > results.json; /usr/local/bin/process_testflows_result.py || echo -e 'failure\tCannot parse results' > check_status.tsv"]
-

docs/en/commercial/cloud.md

@@ -31,10 +31,10 @@ toc_title: Cloud
 
 ## Alibaba Cloud {#alibaba-cloud}
 
-Alibaba Cloud Managed Service for ClickHouse. [China Site](https://www.aliyun.com/product/clickhouse) (will be available at the international site in May 2021). Provides the following key features:
+[Alibaba Cloud Managed Service for ClickHouse](https://www.alibabacloud.com/product/clickhouse) provides the following key features:
 
 -   Highly reliable cloud disk storage engine based on [Alibaba Cloud Apsara](https://www.alibabacloud.com/product/apsara-stack) distributed system
--   Expand capacity on-demand without manual data migration
+-   Expand capacity on demand without manual data migration
 -   Support single-node, single-replica, multi-node, and multi-replica architectures, and support hot and cold data tiering
 -   Support access allow-list, one-key recovery, multi-layer network security protection, cloud disk encryption
 -   Seamless integration with cloud log systems, databases, and data application tools

docs/en/engines/table-engines/integrations/s3.md

@@ -139,6 +139,7 @@ The following settings can be specified in configuration file for given endpoint
 
 -   `endpoint` — Specifies prefix of an endpoint. Mandatory.
 -   `access_key_id` and `secret_access_key` — Specifies credentials to use with given endpoint. Optional.
+-   `region` — Specifies S3 region name. Optional.
 -   `use_environment_credentials` — If set to `true`, S3 client will try to obtain credentials from environment variables and Amazon EC2 metadata for given endpoint. Optional, default value is `false`.
 -   `use_insecure_imds_request` — If set to `true`, S3 client will use insecure IMDS request while obtaining credentials from Amazon EC2 metadata. Optional, default value is `false`.
 -   `header` —  Adds specified HTTP header to a request to given endpoint. Optional, can be speficied multiple times.
@@ -152,6 +153,7 @@ The following settings can be specified in configuration file for given endpoint
         <endpoint>https://storage.yandexcloud.net/my-test-bucket-768/</endpoint>
         <!-- <access_key_id>ACCESS_KEY_ID</access_key_id> -->
         <!-- <secret_access_key>SECRET_ACCESS_KEY</secret_access_key> -->
+        <!-- <region>us-west-1</region> -->
         <!-- <use_environment_credentials>false</use_environment_credentials> -->
         <!-- <use_insecure_imds_request>false</use_insecure_imds_request> -->
         <!-- <header>Authorization: Bearer SOME-TOKEN</header> -->

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

@@ -739,6 +739,7 @@ Configuration markup:
             <endpoint>https://storage.yandexcloud.net/my-bucket/root-path/</endpoint>
             <access_key_id>your_access_key_id</access_key_id>
             <secret_access_key>your_secret_access_key</secret_access_key>
+            <region></region>
             <server_side_encryption_customer_key_base64>your_base64_encoded_customer_key</server_side_encryption_customer_key_base64>
             <proxy>
                 <uri>http://proxy1</uri>
@@ -764,6 +765,7 @@ Required parameters:
 -   `secret_access_key` — S3 secret access key.
 
 Optional parameters:    
+-   `region` — S3 region name.
 -   `use_environment_credentials` — Reads AWS credentials from the Environment variables AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY and AWS_SESSION_TOKEN if they exist. Default value is `false`.
 -   `use_insecure_imds_request` — If set to `true`, S3 client will use insecure IMDS request while obtaining credentials from Amazon EC2 metadata. Default value is `false`.
 -   `proxy` — Proxy configuration for S3 endpoint. Each `uri` element inside `proxy` block should contain a proxy URL. 

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

@@ -21,6 +21,7 @@ Columns:
 -   `bytes_allocated` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Amount of RAM allocated for the dictionary.
 -   `query_count` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Number of queries since the dictionary was loaded or since the last successful reboot.
 -   `hit_rate` ([Float64](../../sql-reference/data-types/float.md)) — For cache dictionaries, the percentage of uses for which the value was in the cache.
+-   `found_rate` ([Float64](../../sql-reference/data-types/float.md)) — The percentage of uses for which the value was found.
 -   `element_count` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Number of items stored in the dictionary.
 -   `load_factor` ([Float64](../../sql-reference/data-types/float.md)) — Percentage filled in the dictionary (for a hashed dictionary, the percentage filled in the hash table).
 -   `source` ([String](../../sql-reference/data-types/string.md)) — Text describing the [data source](../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict-sources.md) for the dictionary.

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

@@ -12,6 +12,9 @@ The result depends on the order of running the query, and is nondeterministic.
 
 When using multiple `quantile*` functions with different levels in a query, the internal states are not combined (that is, the query works less efficiently than it could). In this case, use the [quantiles](../../../sql-reference/aggregate-functions/reference/quantiles.md#quantiles) function.
 
+!!! note "Note"
+    Using `quantileTDigestWeighted` [is not recommended for tiny data sets](https://github.com/tdunning/t-digest/issues/167#issuecomment-828650275) and can lead to significat error. In this case, consider possibility of using [`quantileTDigest`](../../../sql-reference/aggregate-functions/reference/quantiletdigest.md) instead.
+
 **Syntax**
 
 ``` sql

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

@@ -38,3 +38,4 @@ We recommend using this function in almost all scenarios.
 -   [uniqCombined64](../../../sql-reference/aggregate-functions/reference/uniqcombined64.md#agg_function-uniqcombined64)
 -   [uniqHLL12](../../../sql-reference/aggregate-functions/reference/uniqhll12.md#agg_function-uniqhll12)
 -   [uniqExact](../../../sql-reference/aggregate-functions/reference/uniqexact.md#agg_function-uniqexact)
+-   [uniqThetaSketch](../../../sql-reference/aggregate-functions/reference/uniqthetasketch.md#agg_function-uniqthetasketch)

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

@@ -49,3 +49,4 @@ Compared to the [uniq](../../../sql-reference/aggregate-functions/reference/uniq
 -   [uniqCombined64](../../../sql-reference/aggregate-functions/reference/uniqcombined64.md#agg_function-uniqcombined64)
 -   [uniqHLL12](../../../sql-reference/aggregate-functions/reference/uniqhll12.md#agg_function-uniqhll12)
 -   [uniqExact](../../../sql-reference/aggregate-functions/reference/uniqexact.md#agg_function-uniqexact)
+-   [uniqThetaSketch](../../../sql-reference/aggregate-functions/reference/uniqthetasketch.md#agg_function-uniqthetasketch)

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

@@ -23,3 +23,4 @@ The function takes a variable number of parameters. Parameters can be `Tuple`, `
 -   [uniq](../../../sql-reference/aggregate-functions/reference/uniq.md#agg_function-uniq)
 -   [uniqCombined](../../../sql-reference/aggregate-functions/reference/uniq.md#agg_function-uniqcombined)
 -   [uniqHLL12](../../../sql-reference/aggregate-functions/reference/uniq.md#agg_function-uniqhll12)
+-   [uniqThetaSketch](../../../sql-reference/aggregate-functions/reference/uniqthetasketch.md#agg_function-uniqthetasketch)

docs/en/sql-reference/aggregate-functions/reference/uniqhll12.md

@@ -37,3 +37,4 @@ We don’t recommend using this function. In most cases, use the [uniq](../../..
 -   [uniq](../../../sql-reference/aggregate-functions/reference/uniq.md#agg_function-uniq)
 -   [uniqCombined](../../../sql-reference/aggregate-functions/reference/uniqcombined.md#agg_function-uniqcombined)
 -   [uniqExact](../../../sql-reference/aggregate-functions/reference/uniqexact.md#agg_function-uniqexact)
+-   [uniqThetaSketch](../../../sql-reference/aggregate-functions/reference/uniqthetasketch.md#agg_function-uniqthetasketch)

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

@@ -0,0 +1,39 @@
+---
+toc_priority: 195
+---
+
+# uniqThetaSketch {#agg_function-uniqthetasketch}
+
+Calculates the approximate number of different argument values, using the [Theta Sketch Framework](https://datasketches.apache.org/docs/Theta/ThetaSketchFramework.html).
+
+``` sql
+uniqThetaSketch(x[, ...])
+```
+
+**Arguments**
+
+The function takes a variable number of parameters. Parameters can be `Tuple`, `Array`, `Date`, `DateTime`, `String`, or numeric types.
+
+**Returned value**
+
+-   A [UInt64](../../../sql-reference/data-types/int-uint.md)-type number.
+
+**Implementation details**
+
+Function:
+
+-   Calculates a hash for all parameters in the aggregate, then uses it in calculations.
+
+-   Uses the [KMV](https://datasketches.apache.org/docs/Theta/InverseEstimate.html) algorithm to approximate the number of different argument values.
+
+        4096(2^12) 64-bit sketch are used. The size of the state is about 41 KB.
+
+-   The relative error is 3.125% (95% confidence), see the [relative error table](https://datasketches.apache.org/docs/Theta/ThetaErrorTable.html) for detail.
+
+**See Also**
+
+-   [uniq](../../../sql-reference/aggregate-functions/reference/uniq.md#agg_function-uniq)
+-   [uniqCombined](../../../sql-reference/aggregate-functions/reference/uniqcombined.md#agg_function-uniqcombined)
+-   [uniqCombined64](../../../sql-reference/aggregate-functions/reference/uniqcombined64.md#agg_function-uniqcombined64)
+-   [uniqHLL12](../../../sql-reference/aggregate-functions/reference/uniqhll12.md#agg_function-uniqhll12)
+-   [uniqExact](../../../sql-reference/aggregate-functions/reference/uniqexact.md#agg_function-uniqexact)

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

@@ -47,9 +47,9 @@ Union
 
 ### EXPLAIN AST {#explain-ast}
 
-Dump query AST.
+Dump query AST. Supports all types of queries, not only `SELECT`.
 
-Example:
+Examples:
 
 ```sql
 EXPLAIN AST SELECT 1;
@@ -63,6 +63,22 @@ SelectWithUnionQuery (children 1)
     Literal UInt64_1
 ```
 
+```sql
+EXPLAIN AST ALTER TABLE t1 DELETE WHERE date = today();
+```
+
+```sql
+  explain
+  AlterQuery  t1 (children 1)
+   ExpressionList (children 1)
+    AlterCommand 27 (children 1)
+     Function equals (children 1)
+      ExpressionList (children 2)
+       Identifier date
+       Function today (children 1)
+        ExpressionList
+```
+
 ### EXPLAIN SYNTAX {#explain-syntax}
 
 Returns query after syntax optimizations.

docs/ja/commercial/cloud.md

@@ -22,7 +22,7 @@ toc_title: "\u30AF\u30E9\u30A6\u30C9"
 
 ## Alibaba Cloud {#alibaba-cloud}
 
-ClickHouseのためのAlibaba Cloudの管理サービス [中国サイト](https://www.aliyun.com/product/clickhouse) (2021年5月に国際サイトで利用可能になります) 次の主な機能を提供します:
+[ClickHouseのためのAlibaba Cloudの管理サービス](https://www.alibabacloud.com/product/clickhouse) 次の主な機能を提供します:
 
 -   Alibaba Cloud Apsara分散システムをベースにした信頼性の高いクラウドディスクストレージエンジン
 -   手動でのデータ移行を必要とせずに、オン・デマンドで容量を拡張

docs/ru/engines/table-engines/integrations/s3.md

@@ -82,6 +82,7 @@ SELECT * FROM s3_engine_table LIMIT 2;
 
 Необязательные настройки:
 -   `access_key_id` и `secret_access_key` — указывают учетные данные для использования с данной точкой приема запроса.
+-   `region` — название региона S3.
 -   `use_environment_credentials` — если `true`, S3-клиент будет пытаться получить учетные данные из переменных среды и метаданных Amazon EC2 для данной точки приема запроса. Значение по умолчанию - `false`.
 -   `header` — добавляет указанный HTTP-заголовок к запросу на заданную точку приема запроса. Может быть определен несколько раз.
 -   `server_side_encryption_customer_key_base64` — устанавливает необходимые заголовки для доступа к объектам S3 с шифрованием SSE-C. 
@@ -94,6 +95,7 @@ SELECT * FROM s3_engine_table LIMIT 2;
         <endpoint>https://storage.yandexcloud.net/my-test-bucket-768/</endpoint>
         <!-- <access_key_id>ACCESS_KEY_ID</access_key_id> -->
         <!-- <secret_access_key>SECRET_ACCESS_KEY</secret_access_key> -->
+        <!-- <region>us-west-1</region> -->
         <!-- <use_environment_credentials>false</use_environment_credentials> -->
         <!-- <header>Authorization: Bearer SOME-TOKEN</header> -->
         <!-- <server_side_encryption_customer_key_base64>BASE64-ENCODED-KEY</server_side_encryption_customer_key_base64> -->

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

@@ -727,6 +727,7 @@ SETTINGS storage_policy = 'moving_from_ssd_to_hdd'
             <endpoint>https://storage.yandexcloud.net/my-bucket/root-path/</endpoint>
             <access_key_id>your_access_key_id</access_key_id>
             <secret_access_key>your_secret_access_key</secret_access_key>
+            <region></region>
             <proxy>
                 <uri>http://proxy1</uri>
                 <uri>http://proxy2</uri>
@@ -753,6 +754,7 @@ SETTINGS storage_policy = 'moving_from_ssd_to_hdd'
 
 Необязательные параметры:   
 
+-   `region` — название региона S3.
 -   `use_environment_credentials` — признак, нужно ли считывать учетные данные AWS из сетевого окружения, а также из переменных окружения `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY` и `AWS_SESSION_TOKEN`, если они есть. Значение по умолчанию: `false`.
 -   `use_insecure_imds_request` — признак, нужно ли использовать менее безопасное соединение при выполнении запроса к IMDS при получении учётных данных из метаданных Amazon EC2. Значение по умолчанию: `false`.
 -   `proxy` — конфигурация прокси-сервера для конечной точки S3. Каждый элемент `uri` внутри блока `proxy` должен содержать URL прокси-сервера. 

docs/ru/operations/tips.md

@@ -1,248 +0,0 @@
----
-toc_priority: 58
-toc_title: "Советы по эксплуатации"
----
-
-# Советы по эксплуатации {#sovety-po-ekspluatatsii}
-
-## CPU Scaling Governor {#cpu-scaling-governor}
-
-Всегда используйте `performance` scaling governor. `ondemand` scaling governor работает намного хуже при постоянно высоком спросе.
-
-``` bash
-$ echo 'performance' | sudo tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
-```
-
-## Ограничение CPU {#ogranichenie-cpu}
-
-Процессоры могут перегреваться. С помощью `dmesg` можно увидеть, если тактовая частота процессора была ограничена из-за перегрева.
-Также ограничение может устанавливаться снаружи на уровне дата-центра. С помощью `turbostat` можно за этим наблюдать под нагрузкой.
-
-## Оперативная память {#operativnaia-pamiat}
-
-Для небольших объёмов данных (до ~200 Гб в сжатом виде) лучше всего использовать столько памяти не меньше, чем объём данных.
-Для больших объёмов данных, при выполнении интерактивных (онлайн) запросов, стоит использовать разумный объём оперативной памяти (128 Гб или более) для того, чтобы горячее подмножество данных поместилось в кеше страниц.
-Даже для объёмов данных в ~50 Тб на сервер, использование 128 Гб оперативной памяти намного лучше для производительности выполнения запросов, чем 64 Гб.
-
-Не выключайте overcommit. Значение `cat /proc/sys/vm/overcommit_memory` должно быть 0 or 1. Выполните:
-
-``` bash
-$ echo 0 | sudo tee /proc/sys/vm/overcommit_memory
-```
-
-## Huge Pages {#huge-pages}
-
-Механизм прозрачных huge pages нужно отключить. Он мешает работе аллокаторов памяти, что приводит к значительной деградации производительности.
-
-``` bash
-$ echo 'madvise' | sudo tee /sys/kernel/mm/transparent_hugepage/enabled
-```
-
-С помощью `perf top` можно наблюдать за временем, проведенном в ядре операционной системы для управления памятью.
-Постоянные huge pages так же не нужно аллоцировать.
-
-## Подсистема хранения {#podsistema-khraneniia}
-
-Если ваш бюджет позволяет использовать SSD, используйте SSD.
-В противном случае используйте HDD. SATA HDDs 7200 RPM подойдут.
-
-Предпочитайте много серверов с локальными жесткими дисками вместо меньшего числа серверов с подключенными дисковыми полками.
-Но для хранения архивов с редкими запросами полки всё же подходят.
-
-## RAID {#raid}
-
-При использовании HDD можно объединить их RAID-10, RAID-5, RAID-6 или RAID-50.
-Лучше использовать программный RAID в Linux (`mdadm`). Лучше не использовать LVM.
-При создании RAID-10, нужно выбрать `far` расположение.
-Если бюджет позволяет, лучше выбрать RAID-10.
-
-На более чем 4 дисках вместо RAID-5 нужно использовать RAID-6 (предпочтительнее) или RAID-50.
-При использовании RAID-5, RAID-6 или RAID-50, нужно всегда увеличивать stripe_cache_size, так как значение по умолчанию выбрано не самым удачным образом.
-
-``` bash
-$ echo 4096 | sudo tee /sys/block/md2/md/stripe_cache_size
-```
-
-Точное число стоит вычислять из числа устройств и размер блока по формуле: `2 * num_devices * chunk_size_in_bytes / 4096`.
-
-Размер блока в 1024 Кб подходит для всех конфигураций RAID.
-Никогда не указывайте слишком маленький или слишком большой размер блока.
-
-На SSD можно использовать RAID-0.
-Вне зависимости от использования RAID, всегда используйте репликацию для безопасности данных.
-
-Включите NCQ с длинной очередью. Для HDD стоит выбрать планировщик CFQ, а для SSD — noop. Не стоит уменьшать настройку readahead.
-На HDD стоит включать кеш записи.
-
-## Файловая система {#failovaia-sistema}
-
-Ext4 самый проверенный вариант. Укажите опции монтирования `noatime,nobarrier`.
-XFS также подходит, но не так тщательно протестирована в сочетании с ClickHouse.
-Большинство других файловых систем также должны нормально работать. Файловые системы с отложенной аллокацией работают лучше.
-
-## Ядро Linux {#iadro-linux}
-
-Не используйте слишком старое ядро Linux.
-
-## Сеть {#set}
-
-При использовании IPv6, стоит увеличить размер кеша маршрутов.
-Ядра Linux до 3.2 имели массу проблем в реализации IPv6.
-
-Предпочитайте как минимум 10 Гбит сеть. 1 Гбит также будет работать, но намного хуже для починки реплик с десятками терабайт данных или для обработки распределенных запросов с большим объёмом промежуточных данных.
-
-## ZooKeeper {#zookeeper}
-
-Вероятно вы уже используете ZooKeeper для других целей. Можно использовать ту же инсталляцию ZooKeeper, если она не сильно перегружена.
-
-Лучше использовать свежую версию ZooKeeper, как минимум 3.4.9. Версия в стабильных дистрибутивах Linux может быть устаревшей.
-
-Никогда не используете написанные вручную скрипты для переноса данных между разными ZooKeeper кластерами, потому что результат будет некорректный для sequential нод. Никогда не используйте утилиту «zkcopy», по той же причине: https://github.com/ksprojects/zkcopy/issues/15
-
-Если вы хотите разделить существующий ZooKeeper кластер на два, правильный способ - увеличить количество его реплик, а затем переконфигурировать его как два независимых кластера.
-
-Не запускайте ZooKeeper на тех же серверах, что и ClickHouse. Потому что ZooKeeper очень чувствителен к задержкам, а ClickHouse может использовать все доступные системные ресурсы.
-
-С настройками по умолчанию, ZooKeeper является бомбой замедленного действия:
-
-> Сервер ZooKeeper не будет удалять файлы со старыми снепшоты и логами при использовании конфигурации по умолчанию (см. autopurge), это является ответственностью оператора.
-
-Эту бомбу нужно обезвредить.
-
-Далее описана конфигурация ZooKeeper (3.5.1), используемая в боевом окружении Яндекс.Метрики на момент 20 мая 2017 года:
-
-zoo.cfg:
-
-``` bash
-# http://hadoop.apache.org/zookeeper/docs/current/zookeeperAdmin.html
-
-# The number of milliseconds of each tick
-tickTime=2000
-# The number of ticks that the initial
-# synchronization phase can take
-initLimit=30000
-# The number of ticks that can pass between
-# sending a request and getting an acknowledgement
-syncLimit=10
-
-maxClientCnxns=2000
-
-maxSessionTimeout=60000000
-# the directory where the snapshot is stored.
-dataDir=/opt/zookeeper/{{ '{{' }} cluster['name'] {{ '{{' }} '}}' }}/data
-# Place the dataLogDir to a separate physical disc for better performance
-dataLogDir=/opt/zookeeper/{{ '{{' }} cluster['name'] {{ '{{' }} '}}' }}/logs
-
-autopurge.snapRetainCount=10
-autopurge.purgeInterval=1
-
-
-# To avoid seeks ZooKeeper allocates space in the transaction log file in
-# blocks of preAllocSize kilobytes. The default block size is 64M. One reason
-# for changing the size of the blocks is to reduce the block size if snapshots
-# are taken more often. (Also, see snapCount).
-preAllocSize=131072
-
-# Clients can submit requests faster than ZooKeeper can process them,
-# especially if there are a lot of clients. To prevent ZooKeeper from running
-# out of memory due to queued requests, ZooKeeper will throttle clients so that
-# there is no more than globalOutstandingLimit outstanding requests in the
-# system. The default limit is 1,000.ZooKeeper logs transactions to a
-# transaction log. After snapCount transactions are written to a log file a
-# snapshot is started and a new transaction log file is started. The default
-# snapCount is 10,000.
-snapCount=3000000
-
-# If this option is defined, requests will be will logged to a trace file named
-# traceFile.year.month.day.
-#traceFile=
-
-# Leader accepts client connections. Default value is "yes". The leader machine
-# coordinates updates. For higher update throughput at thes slight expense of
-# read throughput the leader can be configured to not accept clients and focus
-# on coordination.
-leaderServes=yes
-
-standaloneEnabled=false
-dynamicConfigFile=/etc/zookeeper-{{ '{{' }} cluster['name'] {{ '{{' }} '}}' }}/conf/zoo.cfg.dynamic
-```
-
-Версия Java:
-
-``` text
-Java(TM) SE Runtime Environment (build 1.8.0_25-b17)
-Java HotSpot(TM) 64-Bit Server VM (build 25.25-b02, mixed mode)
-```
-
-Параметры JVM:
-
-``` bash
-NAME=zookeeper-{{ '{{' }} cluster['name'] {{ '{{' }} '}}' }}
-ZOOCFGDIR=/etc/$NAME/conf
-
-# TODO this is really ugly
-# How to find out, which jars are needed?
-# seems, that log4j requires the log4j.properties file to be in the classpath
-CLASSPATH="$ZOOCFGDIR:/usr/build/classes:/usr/build/lib/*.jar:/usr/share/zookeeper/zookeeper-3.5.1-metrika.jar:/usr/share/zookeeper/slf4j-log4j12-1.7.5.jar:/usr/share/zookeeper/slf4j-api-1.7.5.jar:/usr/share/zookeeper/servlet-api-2.5-20081211.jar:/usr/share/zookeeper/netty-3.7.0.Final.jar:/usr/share/zookeeper/log4j-1.2.16.jar:/usr/share/zookeeper/jline-2.11.jar:/usr/share/zookeeper/jetty-util-6.1.26.jar:/usr/share/zookeeper/jetty-6.1.26.jar:/usr/share/zookeeper/javacc.jar:/usr/share/zookeeper/jackson-mapper-asl-1.9.11.jar:/usr/share/zookeeper/jackson-core-asl-1.9.11.jar:/usr/share/zookeeper/commons-cli-1.2.jar:/usr/src/java/lib/*.jar:/usr/etc/zookeeper"
-
-ZOOCFG="$ZOOCFGDIR/zoo.cfg"
-ZOO_LOG_DIR=/var/log/$NAME
-USER=zookeeper
-GROUP=zookeeper
-PIDDIR=/var/run/$NAME
-PIDFILE=$PIDDIR/$NAME.pid
-SCRIPTNAME=/etc/init.d/$NAME
-JAVA=/usr/bin/java
-ZOOMAIN="org.apache.zookeeper.server.quorum.QuorumPeerMain"
-ZOO_LOG4J_PROP="INFO,ROLLINGFILE"
-JMXLOCALONLY=false
-JAVA_OPTS="-Xms{{ '{{' }} cluster.get('xms','128M') {{ '{{' }} '}}' }} \
-    -Xmx{{ '{{' }} cluster.get('xmx','1G') {{ '{{' }} '}}' }} \
-    -Xloggc:/var/log/$NAME/zookeeper-gc.log \
-    -XX:+UseGCLogFileRotation \
-    -XX:NumberOfGCLogFiles=16 \
-    -XX:GCLogFileSize=16M \
-    -verbose:gc \
-    -XX:+PrintGCTimeStamps \
-    -XX:+PrintGCDateStamps \
-    -XX:+PrintGCDetails
-    -XX:+PrintTenuringDistribution \
-    -XX:+PrintGCApplicationStoppedTime \
-    -XX:+PrintGCApplicationConcurrentTime \
-    -XX:+PrintSafepointStatistics \
-    -XX:+UseParNewGC \
-    -XX:+UseConcMarkSweepGC \
--XX:+CMSParallelRemarkEnabled"
-```
-
-Salt init:
-
-``` text
-description "zookeeper-{{ '{{' }} cluster['name'] {{ '{{' }} '}}' }} centralized coordination service"
-
-start on runlevel [2345]
-stop on runlevel [!2345]
-
-respawn
-
-limit nofile 8192 8192
-
-pre-start script
-    [ -r "/etc/zookeeper-{{ '{{' }} cluster['name'] {{ '{{' }} '}}' }}/conf/environment" ] || exit 0
-    . /etc/zookeeper-{{ '{{' }} cluster['name'] {{ '{{' }} '}}' }}/conf/environment
-    [ -d $ZOO_LOG_DIR ] || mkdir -p $ZOO_LOG_DIR
-    chown $USER:$GROUP $ZOO_LOG_DIR
-end script
-
-script
-    . /etc/zookeeper-{{ '{{' }} cluster['name'] {{ '{{' }} '}}' }}/conf/environment
-    [ -r /etc/default/zookeeper ] && . /etc/default/zookeeper
-    if [ -z "$JMXDISABLE" ]; then
-        JAVA_OPTS="$JAVA_OPTS -Dcom.sun.management.jmxremote -Dcom.sun.management.jmxremote.local.only=$JMXLOCALONLY"
-    fi
-    exec start-stop-daemon --start -c $USER --exec $JAVA --name zookeeper-{{ '{{' }} cluster['name'] {{ '{{' }} '}}' }} \
-        -- -cp $CLASSPATH $JAVA_OPTS -Dzookeeper.log.dir=${ZOO_LOG_DIR} \
-        -Dzookeeper.root.logger=${ZOO_LOG4J_PROP} $ZOOMAIN $ZOOCFG
-end script
-```
-

docs/ru/operations/tips.md

@@ -0,0 +1 @@
+../../en/operations/tips.md

docs/ru/sql-reference/aggregate-functions/reference/quantiletdigestweighted.md

@@ -12,6 +12,9 @@ toc_priority: 208
 
 Внутренние состояния функций `quantile*` не объединяются, если они используются в одном запросе. Если вам необходимо вычислить квантили нескольких уровней, используйте функцию [quantiles](#quantiles), это повысит эффективность запроса.
 
+!!! note "Примечание"
+    Использование `quantileTDigestWeighted` [не рекомендуется для небольших наборов данных](https://github.com/tdunning/t-digest/issues/167#issuecomment-828650275) и может привести к значительной ошибке. Рассмотрите возможность использования [`quantileTDigest`](../../../sql-reference/aggregate-functions/reference/quantiletdigest.md) в таких случаях.
+
 **Синтаксис**
 
 ``` sql

docs/ru/sql-reference/statements/explain.md

@@ -47,9 +47,9 @@ Union
 
 ### EXPLAIN AST {#explain-ast}
 
-Дамп AST запроса.
+Дамп AST запроса. Поддерживает все типы запросов, не только `SELECT`.
 
-Пример:
+Примеры:
 
 ```sql
 EXPLAIN AST SELECT 1;
@@ -63,6 +63,22 @@ SelectWithUnionQuery (children 1)
     Literal UInt64_1
 ```
 
+```sql
+EXPLAIN AST ALTER TABLE t1 DELETE WHERE date = today();
+```
+
+```sql
+  explain
+  AlterQuery  t1 (children 1)
+   ExpressionList (children 1)
+    AlterCommand 27 (children 1)
+     Function equals (children 1)
+      ExpressionList (children 2)
+       Identifier date
+       Function today (children 1)
+        ExpressionList
+```
+
 ### EXPLAIN SYNTAX {#explain-syntax}
 
 Возвращает текст запроса после применения синтаксических оптимизаций.

docs/zh/commercial/cloud.md

@@ -31,7 +31,7 @@ toc_title: 云
 
 ## 阿里云 {#alibaba-cloud}
 
-阿里云的 ClickHouse 托管服务 [中国站](https://www.aliyun.com/product/clickhouse) (国际站于2021年5月初开放) 提供以下主要功能：
+[阿里云的 ClickHouse 托管服务](https://www.alibabacloud.com/zh/product/clickhouse) 提供以下主要功能：
 
 -   基于阿里飞天分布式系统的高可靠云盘存储引擎
 -   按需扩容，无需手动进行数据搬迁

programs/client/Client.cpp

@@ -1399,17 +1399,27 @@ private:
             // when `lambda()` function gets substituted into a wrong place.
             // To avoid dealing with these cases, run the check only for the
             // queries we were able to successfully execute.
-            // The final caveat is that sometimes WITH queries are not executed,
+            // Another caveat is that sometimes WITH queries are not executed,
             // if they are not referenced by the main SELECT, so they can still
             // have the aforementioned problems. Disable this check for such
             // queries, for lack of a better solution.
-            if (!have_error && queryHasWithClause(parsed_query.get()))
+            // There is also a problem that fuzzer substitutes positive Int64
+            // literals or Decimal literals, which are then parsed back as
+            // UInt64, and suddenly duplicate alias substitition starts or stops
+            // working (ASTWithAlias::formatImpl) or something like that.
+            // So we compare not even the first and second formatting of the
+            // query, but second and third.
+            // If you have to add any more workarounds to this check, just remove
+            // it altogether, it's not so useful.
+            if (!have_error && !queryHasWithClause(parsed_query.get()))
             {
-                ASTPtr parsed_formatted_query;
+                ASTPtr ast_2;
                 try
                 {
                     const auto * tmp_pos = query_to_send.c_str();
-                    parsed_formatted_query = parseQuery(tmp_pos, tmp_pos + query_to_send.size(), false /* allow_multi_statements */);
+
+                    ast_2 = parseQuery(tmp_pos, tmp_pos + query_to_send.size(),
+                        false /* allow_multi_statements */);
                 }
                 catch (Exception & e)
                 {
@@ -1419,27 +1429,30 @@ private:
                     }
                 }
 
-                if (parsed_formatted_query)
+                if (ast_2)
                 {
-                    const auto formatted_twice = parsed_formatted_query->formatForErrorMessage();
+                    const auto text_2 = ast_2->formatForErrorMessage();
-
+                    const auto * tmp_pos = text_2.c_str();
-                    if (formatted_twice != query_to_send)
+                    const auto ast_3 = parseQuery(tmp_pos, tmp_pos + text_2.size(),
+                        false /* allow_multi_statements */);
+                    const auto text_3 = ast_3->formatForErrorMessage();
+                    if (text_3 != text_2)
                     {
                         fmt::print(stderr, "The query formatting is broken.\n");
 
                         printChangedSettings();
 
-                        fmt::print(
+                        fmt::print(stderr,
-                            stderr,
                             "Got the following (different) text after formatting the fuzzed query and parsing it back:\n'{}'\n, expected:\n'{}'\n",
-                            formatted_twice,
+                            text_3, text_2);
-                            query_to_send);
                         fmt::print(stderr, "In more detail:\n");
-                        fmt::print(stderr, "AST-1:\n'{}'\n", parsed_query->dumpTree());
+                        fmt::print(stderr, "AST-1 (generated by fuzzer):\n'{}'\n", parsed_query->dumpTree());
                         fmt::print(stderr, "Text-1 (AST-1 formatted):\n'{}'\n", query_to_send);
-                        fmt::print(stderr, "AST-2 (Text-1 parsed):\n'{}'\n", parsed_formatted_query->dumpTree());
+                        fmt::print(stderr, "AST-2 (Text-1 parsed):\n'{}'\n", ast_2->dumpTree());
-                        fmt::print(stderr, "Text-2 (AST-2 formatted):\n'{}'\n", formatted_twice);
+                        fmt::print(stderr, "Text-2 (AST-2 formatted):\n'{}'\n", text_2);
-                        fmt::print(stderr, "Text-1 must be equal to Text-2, but it is not.\n");
+                        fmt::print(stderr, "AST-3 (Text-2 parsed):\n'{}'\n", ast_3->dumpTree());
+                        fmt::print(stderr, "Text-3 (AST-3 formatted):\n'{}'\n", text_3);
+                        fmt::print(stderr, "Text-3 must be equal to Text-2, but it is not.\n");
 
                         exit(1);
                     }
@@ -1456,6 +1469,11 @@ private:
                 server_exception.reset();
                 client_exception.reset();
                 have_error = false;
+
+                // We have to reinitialize connection after errors, because it
+                // might have gotten into a wrong state and we'll get false
+                // positives about "Unknown packet from server".
+                connection->forceConnected(connection_parameters.timeouts);
             }
             else if (ast_to_process->formatForErrorMessage().size() > 500)
             {

programs/client/QueryFuzzer.h

@@ -4,11 +4,14 @@
 #include <unordered_map>
 #include <vector>
 
+#include <pcg-random/pcg_random.hpp>
+
 #include <Common/randomSeed.h>
 #include <Common/Stopwatch.h>
 #include <Core/Field.h>
 #include <Parsers/IAST.h>
 
+
 namespace DB
 {
 

programs/git-import/git-import.cpp

@@ -774,7 +774,7 @@ UInt128 diffHash(const CommitDiff & file_changes)
     }
 
     UInt128 hash_of_diff;
-    hasher.get128(hash_of_diff.low, hash_of_diff.high);
+    hasher.get128(hash_of_diff.items[0], hash_of_diff.items[1]);
 
     return hash_of_diff;
 }

programs/library-bridge/SharedLibraryHandler.h

@@ -23,6 +23,8 @@ public:
 
     SharedLibraryHandler(const SharedLibraryHandler & other);
 
+    SharedLibraryHandler & operator=(const SharedLibraryHandler & other) = delete;
+
     ~SharedLibraryHandler();
 
     BlockInputStreamPtr loadAll();

programs/obfuscator/Obfuscator.cpp

@@ -365,16 +365,20 @@ static void transformFixedString(const UInt8 * src, UInt8 * dst, size_t size, UI
     }
 }
 
-static void transformUUID(const UInt128 & src, UInt128 & dst, UInt64 seed)
+static void transformUUID(const UUID & src_uuid, UUID & dst_uuid, UInt64 seed)
 {
+    const UInt128 & src = src_uuid.toUnderType();
+    UInt128 & dst = dst_uuid.toUnderType();
+
     SipHash hash;
     hash.update(seed);
-    hash.update(reinterpret_cast<const char *>(&src), sizeof(UInt128));
+    hash.update(reinterpret_cast<const char *>(&src), sizeof(UUID));
 
     /// Saving version and variant from an old UUID
     hash.get128(reinterpret_cast<char *>(&dst));
-    dst.high = (dst.high & 0x1fffffffffffffffull) | (src.high & 0xe000000000000000ull);
+
-    dst.low = (dst.low & 0xffffffffffff0fffull) | (src.low & 0x000000000000f000ull);
+    dst.items[1] = (dst.items[1] & 0x1fffffffffffffffull) | (src.items[1] & 0xe000000000000000ull);
+    dst.items[0] = (dst.items[0] & 0xffffffffffff0fffull) | (src.items[0] & 0x000000000000f000ull);
 }
 
 class FixedStringModel : public IModel
@@ -426,10 +430,10 @@ public:
 
     ColumnPtr generate(const IColumn & column) override
     {
-        const ColumnUInt128 & src_column = assert_cast<const ColumnUInt128 &>(column);
+        const ColumnUUID & src_column = assert_cast<const ColumnUUID &>(column);
         const auto & src_data = src_column.getData();
 
-        auto res_column = ColumnUInt128::create();
+        auto res_column = ColumnUUID::create();
         auto & res_data = res_column->getData();
 
         res_data.resize(src_data.size());

programs/odbc-bridge/ColumnInfoHandler.cpp

@@ -109,7 +109,7 @@ void ODBCColumnsInfoHandler::handleRequest(HTTPServerRequest & request, HTTPServ
                 validateODBCConnectionString(connection_string),
                 getContext()->getSettingsRef().odbc_bridge_connection_pool_size);
 
-        nanodbc::catalog catalog(*connection);
+        nanodbc::catalog catalog(connection->get());
         std::string catalog_name;
 
         /// In XDBC tables it is allowed to pass either database_name or schema_name in table definion, but not both of them.

programs/odbc-bridge/IdentifierQuoteHandler.cpp

@@ -46,7 +46,7 @@ void IdentifierQuoteHandler::handleRequest(HTTPServerRequest & request, HTTPServ
                 validateODBCConnectionString(connection_string),
                 getContext()->getSettingsRef().odbc_bridge_connection_pool_size);
 
-        auto identifier = getIdentifierQuote(*connection);
+        auto identifier = getIdentifierQuote(connection->get());
 
         WriteBufferFromHTTPServerResponse out(response, request.getMethod() == Poco::Net::HTTPRequest::HTTP_HEAD, keep_alive_timeout);
         try

programs/odbc-bridge/MainHandler.cpp

@@ -18,13 +18,10 @@
 #include <Processors/Formats/InputStreamFromInputFormat.h>
 #include <common/logger_useful.h>
 #include <Server/HTTP/HTMLForm.h>
-#include "ODBCConnectionFactory.h"
 
 #include <mutex>
 #include <memory>
 
-#include <nanodbc/nanodbc.h>
-
 
 namespace DB
 {
@@ -133,12 +130,12 @@ void ODBCHandler::handleRequest(HTTPServerRequest & request, HTTPServerResponse
 
             auto quoting_style = IdentifierQuotingStyle::None;
 #if USE_ODBC
-            quoting_style = getQuotingStyle(*connection);
+            quoting_style = getQuotingStyle(connection->get());
 #endif
             auto & read_buf = request.getStream();
             auto input_format = FormatFactory::instance().getInput(format, read_buf, *sample_block, getContext(), max_block_size);
             auto input_stream = std::make_shared<InputStreamFromInputFormat>(input_format);
-            ODBCBlockOutputStream output_stream(*connection, db_name, table_name, *sample_block, getContext(), quoting_style);
+            ODBCBlockOutputStream output_stream(std::move(connection), db_name, table_name, *sample_block, getContext(), quoting_style);
             copyData(*input_stream, output_stream);
             writeStringBinary("Ok.", out);
         }
@@ -148,7 +145,7 @@ void ODBCHandler::handleRequest(HTTPServerRequest & request, HTTPServerResponse
             LOG_TRACE(log, "Query: {}", query);
 
             BlockOutputStreamPtr writer = FormatFactory::instance().getOutputStreamParallelIfPossible(format, out, *sample_block, getContext());
-            ODBCBlockInputStream inp(*connection, query, *sample_block, max_block_size);
+            ODBCBlockInputStream inp(std::move(connection), query, *sample_block, max_block_size);
             copyData(inp, *writer);
         }
     }

programs/odbc-bridge/ODBCBlockInputStream.cpp

@@ -21,14 +21,13 @@ namespace ErrorCodes
 
 
 ODBCBlockInputStream::ODBCBlockInputStream(
-    nanodbc::connection & connection_, const std::string & query_str, const Block & sample_block, const UInt64 max_block_size_)
+    nanodbc::ConnectionHolderPtr connection, const std::string & query_str, const Block & sample_block, const UInt64 max_block_size_)
     : log(&Poco::Logger::get("ODBCBlockInputStream"))
     , max_block_size{max_block_size_}
-    , connection(connection_)
     , query(query_str)
 {
     description.init(sample_block);
-    result = execute(connection, NANODBC_TEXT(query));
+    result = execute(connection->get(), NANODBC_TEXT(query));
 }
 
 

programs/odbc-bridge/ODBCBlockInputStream.h

@@ -4,7 +4,7 @@
 #include <Core/Block.h>
 #include <DataStreams/IBlockInputStream.h>
 #include <Core/ExternalResultDescription.h>
-#include <nanodbc/nanodbc.h>
+#include "ODBCConnectionFactory.h"
 
 
 namespace DB
@@ -13,7 +13,7 @@ namespace DB
 class ODBCBlockInputStream final : public IBlockInputStream
 {
 public:
-    ODBCBlockInputStream(nanodbc::connection & connection_, const std::string & query_str, const Block & sample_block, const UInt64 max_block_size_);
+    ODBCBlockInputStream(nanodbc::ConnectionHolderPtr connection, const std::string & query_str, const Block & sample_block, const UInt64 max_block_size_);
 
     String getName() const override { return "ODBC"; }
 
@@ -36,7 +36,6 @@ private:
     const UInt64 max_block_size;
     ExternalResultDescription description;
 
-    nanodbc::connection & connection;
     nanodbc::result result;
     String query;
     bool finished = false;

programs/odbc-bridge/ODBCBlockOutputStream.cpp

@@ -1,5 +1,6 @@
 #include "ODBCBlockOutputStream.h"
 
+#include <Common/hex.h>
 #include <common/logger_useful.h>
 #include <Core/Field.h>
 #include <common/LocalDate.h>
@@ -37,17 +38,16 @@ namespace
         query.IAST::format(settings);
         return buf.str();
     }
-
 }
 
-ODBCBlockOutputStream::ODBCBlockOutputStream(nanodbc::connection & connection_,
+ODBCBlockOutputStream::ODBCBlockOutputStream(nanodbc::ConnectionHolderPtr connection_,
                                              const std::string & remote_database_name_,
                                              const std::string & remote_table_name_,
                                              const Block & sample_block_,
                                              ContextPtr local_context_,
                                              IdentifierQuotingStyle quoting_)
     : log(&Poco::Logger::get("ODBCBlockOutputStream"))
-    , connection(connection_)
+    , connection(std::move(connection_))
     , db_name(remote_database_name_)
     , table_name(remote_table_name_)
     , sample_block(sample_block_)
@@ -69,7 +69,7 @@ void ODBCBlockOutputStream::write(const Block & block)
     writer->write(block);
 
     std::string query = getInsertQuery(db_name, table_name, block.getColumnsWithTypeAndName(), quoting) + values_buf.str();
-    execute(connection, query);
+    execute(connection->get(), query);
 }
 
 }

programs/odbc-bridge/ODBCBlockOutputStream.h

@@ -5,7 +5,7 @@
 #include <Core/ExternalResultDescription.h>
 #include <Parsers/IdentifierQuotingStyle.h>
 #include <Interpreters/Context_fwd.h>
-#include <nanodbc/nanodbc.h>
+#include "ODBCConnectionFactory.h"
 
 
 namespace DB
@@ -16,7 +16,7 @@ class ODBCBlockOutputStream : public IBlockOutputStream
 
 public:
     ODBCBlockOutputStream(
-            nanodbc::connection & connection_,
+            nanodbc::ConnectionHolderPtr connection_,
             const std::string & remote_database_name_,
             const std::string & remote_table_name_,
             const Block & sample_block_,
@@ -29,7 +29,7 @@ public:
 private:
     Poco::Logger * log;
 
-    nanodbc::connection & connection;
+    nanodbc::ConnectionHolderPtr connection;
     std::string db_name;
     std::string table_name;
     Block sample_block;

programs/odbc-bridge/ODBCConnectionFactory.h

@@ -6,53 +6,51 @@
 #include <common/BorrowedObjectPool.h>
 #include <unordered_map>
 
+namespace DB
+{
+namespace ErrorCodes
+{
+    extern const int NO_FREE_CONNECTION;
+}
+}
 
 namespace nanodbc
 {
 
-static constexpr inline auto ODBC_CONNECT_TIMEOUT = 100;
+using ConnectionPtr = std::unique_ptr<nanodbc::connection>;
-
-using ConnectionPtr = std::shared_ptr<nanodbc::connection>;
 using Pool = BorrowedObjectPool<ConnectionPtr>;
 using PoolPtr = std::shared_ptr<Pool>;
 
 class ConnectionHolder
 {
-
 public:
-    ConnectionHolder(const std::string & connection_string_, PoolPtr pool_) : connection_string(connection_string_), pool(pool_) {}
+    ConnectionHolder(PoolPtr pool_, ConnectionPtr connection_) : pool(pool_), connection(std::move(connection_)) {}
 
-    ~ConnectionHolder()
+    ConnectionHolder(const ConnectionHolder & other) = delete;
+
+    ~ConnectionHolder() { pool->returnObject(std::move(connection)); }
+
+    nanodbc::connection & get() const
     {
-        if (connection)
+        assert(connection != nullptr);
-            pool->returnObject(std::move(connection));
-    }
-
-    nanodbc::connection & operator*()
-    {
-        if (!connection)
-        {
-            pool->borrowObject(connection, [&]()
-            {
-                return std::make_shared<nanodbc::connection>(connection_string, ODBC_CONNECT_TIMEOUT);
-            });
-        }
-
         return *connection;
     }
 
 private:
-    std::string connection_string;
     PoolPtr pool;
     ConnectionPtr connection;
 };
 
+using ConnectionHolderPtr = std::unique_ptr<ConnectionHolder>;
 }
 
 
 namespace DB
 {
 
+static constexpr inline auto ODBC_CONNECT_TIMEOUT = 100;
+static constexpr inline auto ODBC_POOL_WAIT_TIMEOUT = 10000;
+
 class ODBCConnectionFactory final : private boost::noncopyable
 {
 public:
@@ -62,14 +60,32 @@ public:
         return ret;
     }
 
-    nanodbc::ConnectionHolder get(const std::string & connection_string, size_t pool_size)
+    nanodbc::ConnectionHolderPtr get(const std::string & connection_string, size_t pool_size)
     {
         std::lock_guard lock(mutex);
 
         if (!factory.count(connection_string))
             factory.emplace(std::make_pair(connection_string, std::make_shared<nanodbc::Pool>(pool_size)));
 
-        return nanodbc::ConnectionHolder(connection_string, factory[connection_string]);
+        auto & pool = factory[connection_string];
+
+        nanodbc::ConnectionPtr connection;
+        auto connection_available = pool->tryBorrowObject(connection, []() { return nullptr; }, ODBC_POOL_WAIT_TIMEOUT);
+
+        if (!connection_available)
+            throw Exception("Unable to fetch connection within the timeout", ErrorCodes::NO_FREE_CONNECTION);
+
+        try
+        {
+            if (!connection || !connection->connected())
+                connection = std::make_unique<nanodbc::connection>(connection_string, ODBC_CONNECT_TIMEOUT);
+        }
+        catch (...)
+        {
+            pool->returnObject(std::move(connection));
+        }
+
+        return std::make_unique<nanodbc::ConnectionHolder>(factory[connection_string], std::move(connection));
     }
 
 private:

programs/odbc-bridge/SchemaAllowedHandler.cpp

@@ -53,7 +53,7 @@ void SchemaAllowedHandler::handleRequest(HTTPServerRequest & request, HTTPServer
                 validateODBCConnectionString(connection_string),
                 getContext()->getSettingsRef().odbc_bridge_connection_pool_size);
 
-        bool result = isSchemaAllowed(*connection);
+        bool result = isSchemaAllowed(connection->get());
 
         WriteBufferFromHTTPServerResponse out(response, request.getMethod() == Poco::Net::HTTPRequest::HTTP_HEAD, keep_alive_timeout);
         try

programs/odbc-bridge/getIdentifierQuote.cpp

@@ -3,7 +3,6 @@
 #if USE_ODBC
 
 #include <common/logger_useful.h>
-#include <nanodbc/nanodbc.h>
 #include <sql.h>
 #include <sqlext.h>
 

programs/server/Server.cpp

@@ -13,6 +13,7 @@
 #include <Poco/Net/HTTPServer.h>
 #include <Poco/Net/NetException.h>
 #include <Poco/Util/HelpFormatter.h>
+#include <Poco/Environment.h>
 #include <ext/scope_guard.h>
 #include <common/defines.h>
 #include <common/logger_useful.h>
@@ -385,6 +386,11 @@ void Server::initialize(Poco::Util::Application & self)
 {
     BaseDaemon::initialize(self);
     logger().information("starting up");
+
+    LOG_INFO(&logger(), "OS Name = {}, OS Version = {}, OS Architecture = {}",
+        Poco::Environment::osName(),
+        Poco::Environment::osVersion(),
+        Poco::Environment::osArchitecture());
 }
 
 std::string Server::getDefaultCorePath() const
@@ -879,7 +885,8 @@ int Server::main(const std::vector<std::string> & /*args*/)
         global_context->setMMappedFileCache(mmap_cache_size);
 
 #if USE_EMBEDDED_COMPILER
-    size_t compiled_expression_cache_size = config().getUInt64("compiled_expression_cache_size", 500);
+    constexpr size_t compiled_expression_cache_size_default = 1024 * 1024 * 1024;
+    size_t compiled_expression_cache_size = config().getUInt64("compiled_expression_cache_size", compiled_expression_cache_size_default);
     CompiledExpressionCacheFactory::instance().init(compiled_expression_cache_size);
 #endif
 

programs/server/config.xml

@@ -329,6 +329,8 @@
       -->
     <mmap_cache_size>1000</mmap_cache_size>
 
+    <!-- Cache size for compiled expressions.-->
+    <compiled_expression_cache_size>1073741824</compiled_expression_cache_size>
 
     <!-- Path to data directory, with trailing slash. -->
     <path>/var/lib/clickhouse/</path>
@@ -518,6 +520,33 @@
     <!-- Reallocate memory for machine code ("text") using huge pages. Highly experimental. -->
     <remap_executable>false</remap_executable>
 
+    <![CDATA[
+         Uncomment below in order to use JDBC table engine and function.
+
+         To install and run JDBC bridge in background:
+         * [Debian/Ubuntu]
+           export MVN_URL=https://repo1.maven.org/maven2/ru/yandex/clickhouse/clickhouse-jdbc-bridge
+           export PKG_VER=$(curl -sL $MVN_URL/maven-metadata.xml | grep '<release>' | sed -e 's|.*>\(.*\)<.*|\1|')
+           wget https://github.com/ClickHouse/clickhouse-jdbc-bridge/releases/download/v$PKG_VER/clickhouse-jdbc-bridge_$PKG_VER-1_all.deb
+           apt install --no-install-recommends -f ./clickhouse-jdbc-bridge_$PKG_VER-1_all.deb
+           clickhouse-jdbc-bridge &
+
+         * [CentOS/RHEL]
+           export MVN_URL=https://repo1.maven.org/maven2/ru/yandex/clickhouse/clickhouse-jdbc-bridge
+           export PKG_VER=$(curl -sL $MVN_URL/maven-metadata.xml | grep '<release>' | sed -e 's|.*>\(.*\)<.*|\1|')
+           wget https://github.com/ClickHouse/clickhouse-jdbc-bridge/releases/download/v$PKG_VER/clickhouse-jdbc-bridge-$PKG_VER-1.noarch.rpm
+           yum localinstall -y clickhouse-jdbc-bridge-$PKG_VER-1.noarch.rpm
+           clickhouse-jdbc-bridge &
+
+         Please refer to https://github.com/ClickHouse/clickhouse-jdbc-bridge#usage for more information.
+    ]]>
+    <!--
+    <jdbc_bridge>
+        <host>127.0.0.1</host>
+        <port>9019</port>
+    </jdbc_bridge>
+    -->
+  
     <!-- Configuration of clusters that could be used in Distributed tables.
          https://clickhouse.tech/docs/en/operations/table_engines/distributed/
       -->

src/Access/DiskAccessStorage.cpp

@@ -355,8 +355,9 @@ String DiskAccessStorage::getStorageParamsJSON() const
     std::lock_guard lock{mutex};
     Poco::JSON::Object json;
     json.set("path", directory_path);
-    if (readonly)
+    bool readonly_loaded = readonly;
-        json.set("readonly", readonly.load());
+    if (readonly_loaded)
+        json.set("readonly", Poco::Dynamic::Var{true});
     std::ostringstream oss;         // STYLE_CHECK_ALLOW_STD_STRING_STREAM
     oss.exceptions(std::ios::failbit);
     Poco::JSON::Stringifier::stringify(json, oss);

src/Access/ExternalAuthenticators.cpp

@@ -77,7 +77,7 @@ auto parseLDAPServer(const Poco::Util::AbstractConfiguration & config, const Str
         if (enable_tls_lc_str == "starttls")
             params.enable_tls = LDAPClient::Params::TLSEnable::YES_STARTTLS;
         else if (config.getBool(ldap_server_config + ".enable_tls"))
-            params.enable_tls = LDAPClient::Params::TLSEnable::YES;
+            params.enable_tls = LDAPClient::Params::TLSEnable::YES; //-V1048
         else
             params.enable_tls = LDAPClient::Params::TLSEnable::NO;
     }
@@ -96,7 +96,7 @@ auto parseLDAPServer(const Poco::Util::AbstractConfiguration & config, const Str
         else if (tls_minimum_protocol_version_lc_str == "tls1.1")
             params.tls_minimum_protocol_version = LDAPClient::Params::TLSProtocolVersion::TLS1_1;
         else if (tls_minimum_protocol_version_lc_str == "tls1.2")
-            params.tls_minimum_protocol_version = LDAPClient::Params::TLSProtocolVersion::TLS1_2;
+            params.tls_minimum_protocol_version = LDAPClient::Params::TLSProtocolVersion::TLS1_2; //-V1048
         else
             throw Exception("Bad value for 'tls_minimum_protocol_version' entry, allowed values are: 'ssl2', 'ssl3', 'tls1.0', 'tls1.1', 'tls1.2'", ErrorCodes::BAD_ARGUMENTS);
     }
@@ -113,7 +113,7 @@ auto parseLDAPServer(const Poco::Util::AbstractConfiguration & config, const Str
         else if (tls_require_cert_lc_str == "try")
             params.tls_require_cert = LDAPClient::Params::TLSRequireCert::TRY;
         else if (tls_require_cert_lc_str == "demand")
-            params.tls_require_cert = LDAPClient::Params::TLSRequireCert::DEMAND;
+            params.tls_require_cert = LDAPClient::Params::TLSRequireCert::DEMAND; //-V1048
         else
             throw Exception("Bad value for 'tls_require_cert' entry, allowed values are: 'never', 'allow', 'try', 'demand'", ErrorCodes::BAD_ARGUMENTS);
     }

src/Access/GrantedRoles.cpp

@@ -136,7 +136,7 @@ GrantedRoles::Elements GrantedRoles::getElements() const
     boost::range::set_difference(roles, roles_with_admin_option, std::back_inserter(element.ids));
     if (!element.empty())
     {
-        element.admin_option = false;
+        element.admin_option = false; //-V1048
         elements.emplace_back(std::move(element));
     }
 

src/Access/IAccessStorage.h

@@ -1,7 +1,7 @@
 #pragma once
 
 #include <Access/IAccessEntity.h>
-#include <common/types.h>
+#include <Core/Types.h>
 #include <Core/UUID.h>
 #include <ext/scope_guard.h>
 #include <functional>

src/Access/Quota.h

@@ -45,7 +45,7 @@ struct Quota : public IAccessEntity
 
     struct ResourceTypeInfo
     {
-        const char * const raw_name;
+        const char * const raw_name = "";
         const String name;    /// Lowercased with underscores, e.g. "result_rows".
         const String keyword; /// Uppercased with spaces, e.g. "RESULT ROWS".
         const bool output_as_float = false;

src/Access/RolesOrUsersSet.h

@@ -1,6 +1,7 @@
 #pragma once
 
 #include <Core/UUID.h>
+#include <Core/Types.h>
 #include <boost/container/flat_set.hpp>
 #include <memory>
 #include <optional>

src/Access/RowPolicy.h

@@ -2,6 +2,7 @@
 
 #include <Access/IAccessEntity.h>
 #include <Access/RolesOrUsersSet.h>
+#include <Core/Types.h>
 #include <array>
 
 

src/AggregateFunctions/AggregateFunctionAvg.h

@@ -7,7 +7,7 @@
 #include <DataTypes/DataTypesDecimal.h>
 #include <DataTypes/DataTypesNumber.h>
 #include <AggregateFunctions/IAggregateFunction.h>
-#include "Core/DecimalFunctions.h"
+#include <Core/DecimalFunctions.h>
 
 
 namespace DB

src/AggregateFunctions/AggregateFunctionAvgWeighted.h

@@ -5,18 +5,18 @@
 
 namespace DB
 {
-template <class T>
+template <typename T>
 using AvgWeightedFieldType = std::conditional_t<IsDecimalNumber<T>,
     std::conditional_t<std::is_same_v<T, Decimal256>, Decimal256, Decimal128>,
     std::conditional_t<DecimalOrExtendedInt<T>,
         Float64, // no way to do UInt128 * UInt128, better cast to Float64
         NearestFieldType<T>>>;
 
-template <class T, class U>
+template <typename T, typename U>
 using MaxFieldType = std::conditional_t<(sizeof(AvgWeightedFieldType<T>) > sizeof(AvgWeightedFieldType<U>)),
     AvgWeightedFieldType<T>, AvgWeightedFieldType<U>>;
 
-template <class Value, class Weight>
+template <typename Value, typename Weight>
 class AggregateFunctionAvgWeighted final :
     public AggregateFunctionAvgBase<
         MaxFieldType<Value, Weight>, AvgWeightedFieldType<Weight>, AggregateFunctionAvgWeighted<Value, Weight>>

src/AggregateFunctions/AggregateFunctionBoundingRatio.h

@@ -2,7 +2,6 @@
 
 #include <DataTypes/DataTypesNumber.h>
 #include <Columns/ColumnsNumber.h>
-#include <Common/FieldVisitors.h>
 #include <IO/ReadHelpers.h>
 #include <IO/WriteHelpers.h>
 #include <AggregateFunctions/Helpers.h>
@@ -20,7 +19,7 @@ namespace ErrorCodes
 
 /** Tracks the leftmost and rightmost (x, y) data points.
   */
-struct AggregateFunctionBoundingRatioData
+struct AggregateFunctionBoundingRatioData //-V730
 {
     struct Point
     {

src/AggregateFunctions/AggregateFunctionDistinct.h

@@ -10,7 +10,6 @@
 #include <Common/HashTable/HashMap.h>
 #include <Common/SipHash.h>
 
-#include <Common/FieldVisitors.h>
 
 namespace DB
 {

src/AggregateFunctions/AggregateFunctionGroupArray.h

@@ -296,12 +296,7 @@ public:
         if (size)
         {
             typename ColumnVector<T>::Container & data_to = assert_cast<ColumnVector<T> &>(arr_to.getData()).getData();
-            if constexpr (is_big_int_v<T>)
+            data_to.insert(this->data(place).value.begin(), this->data(place).value.end());
-                // is data_to empty? we should probably use std::vector::insert then
-                for (auto it = this->data(place).value.begin(); it != this->data(place).value.end(); it++)
-                    data_to.push_back(*it);
-            else
-                data_to.insert(this->data(place).value.begin(), this->data(place).value.end());
         }
     }
 

src/AggregateFunctions/AggregateFunctionGroupArrayMoving.cpp

@@ -21,6 +21,7 @@ namespace ErrorCodes
 namespace
 {
 
+/// TODO Proper support for Decimal256.
 template <typename T, typename LimitNumberOfElements>
 struct MovingSum
 {

src/AggregateFunctions/AggregateFunctionGroupArrayMoving.h

@@ -38,7 +38,7 @@ struct MovingData
     using Array = PODArray<T, 32, Allocator>;
 
     Array value;    /// Prefix sums.
-    T sum = 0;
+    T sum{};
 
     void NO_SANITIZE_UNDEFINED add(T val, Arena * arena)
     {
@@ -69,9 +69,9 @@ struct MovingAvgData : public MovingData<T>
     T NO_SANITIZE_UNDEFINED get(size_t idx, UInt64 window_size) const
     {
         if (idx < window_size)
-            return this->value[idx] / window_size;
+            return this->value[idx] / T(window_size);
         else
-            return (this->value[idx] - this->value[idx - window_size]) / window_size;
+            return (this->value[idx] - this->value[idx - window_size]) / T(window_size);
     }
 };
 

src/AggregateFunctions/AggregateFunctionHistogram.h

@@ -220,7 +220,7 @@ private:
     }
 
 public:
-    AggregateFunctionHistogramData()
+    AggregateFunctionHistogramData() //-V730
         : size(0)
         , lower_bound(std::numeric_limits<Mean>::max())
         , upper_bound(std::numeric_limits<Mean>::lowest())

src/AggregateFunctions/AggregateFunctionMannWhitney.h

@@ -6,7 +6,6 @@
 #include <Columns/ColumnVector.h>
 #include <Columns/ColumnTuple.h>
 #include <Common/assert_cast.h>
-#include <Common/FieldVisitors.h>
 #include <Common/PODArray_fwd.h>
 #include <common/types.h>
 #include <DataTypes/DataTypesDecimal.h>
@@ -21,7 +20,7 @@
 
 #include <Common/ArenaAllocator.h>
 
-#include <iostream>
+
 namespace DB
 {
 

src/AggregateFunctions/AggregateFunctionMinMaxAny.h

@@ -181,7 +181,7 @@ public:
 /** For strings. Short strings are stored in the object itself, and long strings are allocated separately.
   * NOTE It could also be suitable for arrays of numbers.
   */
-struct SingleValueDataString
+struct SingleValueDataString //-V730
 {
 private:
     using Self = SingleValueDataString;

src/AggregateFunctions/AggregateFunctionQuantile.cpp

@@ -100,13 +100,14 @@ AggregateFunctionPtr createAggregateFunctionQuantile(const std::string & name, c
         if (which.idx == TypeIndex::Decimal32) return std::make_shared<Function<Decimal32, false>>(argument_types, params);
         if (which.idx == TypeIndex::Decimal64) return std::make_shared<Function<Decimal64, false>>(argument_types, params);
         if (which.idx == TypeIndex::Decimal128) return std::make_shared<Function<Decimal128, false>>(argument_types, params);
+        if (which.idx == TypeIndex::Decimal256) return std::make_shared<Function<Decimal256, false>>(argument_types, params);
         if (which.idx == TypeIndex::DateTime64) return std::make_shared<Function<DateTime64, false>>(argument_types, params);
-        //if (which.idx == TypeIndex::Decimal256) return std::make_shared<Function<Decimal256, false>>(argument_types, params);
     }
 
     if constexpr (supportBigInt<Function>())
     {
         if (which.idx == TypeIndex::Int128) return std::make_shared<Function<Int128, true>>(argument_types, params);
+        if (which.idx == TypeIndex::UInt128) return std::make_shared<Function<Int128, true>>(argument_types, params);
         if (which.idx == TypeIndex::Int256) return std::make_shared<Function<Int256, true>>(argument_types, params);
         if (which.idx == TypeIndex::UInt256) return std::make_shared<Function<UInt256, true>>(argument_types, params);
     }

src/AggregateFunctions/AggregateFunctionStatistics.cpp

@@ -36,7 +36,7 @@ AggregateFunctionPtr createAggregateFunctionStatisticsBinary(const std::string &
     assertNoParameters(name, parameters);
     assertBinary(name, argument_types);
 
-    AggregateFunctionPtr res(createWithTwoNumericTypes<FunctionTemplate>(*argument_types[0], *argument_types[1], argument_types));
+    AggregateFunctionPtr res(createWithTwoBasicNumericTypes<FunctionTemplate>(*argument_types[0], *argument_types[1], argument_types));
     if (!res)
         throw Exception("Illegal types " + argument_types[0]->getName() + " and " + argument_types[1]->getName()
             + " of arguments for aggregate function " + name, ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);

src/AggregateFunctions/AggregateFunctionStatistics.h

@@ -13,7 +13,7 @@
 namespace DB
 {
 
-namespace
+namespace detail
 {
 
 /// This function returns true if both values are large and comparable.
@@ -72,7 +72,7 @@ public:
         Float64 factor = static_cast<Float64>(count * source.count) / total_count;
         Float64 delta = mean - source.mean;
 
-        if (areComparable(count, source.count))
+        if (detail::areComparable(count, source.count))
             mean = (source.count * source.mean + count * mean) / total_count;
         else
             mean = source.mean + delta * (static_cast<Float64>(count) / total_count);
@@ -302,7 +302,7 @@ public:
         Float64 left_delta = left_mean - source.left_mean;
         Float64 right_delta = right_mean - source.right_mean;
 
-        if (areComparable(count, source.count))
+        if (detail::areComparable(count, source.count))
         {
             left_mean = (source.count * source.left_mean + count * left_mean) / total_count;
             right_mean = (source.count * source.right_mean + count * right_mean) / total_count;

src/AggregateFunctions/AggregateFunctionStatisticsSimple.cpp

@@ -41,7 +41,7 @@ AggregateFunctionPtr createAggregateFunctionStatisticsBinary(const std::string &
     assertNoParameters(name, parameters);
     assertBinary(name, argument_types);
 
-    AggregateFunctionPtr res(createWithTwoNumericTypes<FunctionTemplate>(*argument_types[0], *argument_types[1], argument_types));
+    AggregateFunctionPtr res(createWithTwoBasicNumericTypes<FunctionTemplate>(*argument_types[0], *argument_types[1], argument_types));
     if (!res)
         throw Exception("Illegal types " + argument_types[0]->getName() + " and " + argument_types[1]->getName()
             + " of arguments for aggregate function " + name, ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);

src/AggregateFunctions/AggregateFunctionStatisticsSimple.h

@@ -131,11 +131,10 @@ public:
                 static_cast<ResultType>(static_cast<const ColVecT2 &>(*columns[1]).getData()[row_num]));
         else
         {
-            if constexpr (std::is_same_v<T1, Decimal256>)
+            if constexpr (IsDecimalNumber<T1>)
             {
                 this->data(place).add(static_cast<ResultType>(
-                    static_cast<const ColVecT1 &>(*columns[0]).getData()[row_num].value
+                    static_cast<const ColVecT1 &>(*columns[0]).getData()[row_num].value));
-                ));
             }
             else
                 this->data(place).add(

src/AggregateFunctions/AggregateFunctionTopK.cpp

@@ -2,9 +2,10 @@
 #include <AggregateFunctions/AggregateFunctionTopK.h>
 #include <AggregateFunctions/Helpers.h>
 #include <AggregateFunctions/FactoryHelpers.h>
+#include <Common/FieldVisitors.h>
 #include <DataTypes/DataTypeDate.h>
 #include <DataTypes/DataTypeDateTime.h>
-#include "registerAggregateFunctions.h"
+
 
 #define TOP_K_MAX_SIZE 0xFFFFFF
 

src/AggregateFunctions/AggregateFunctionTopK.h

@@ -10,7 +10,6 @@
 #include <Columns/ColumnArray.h>
 
 #include <Common/SpaceSaving.h>
-#include <Common/FieldVisitors.h>
 #include <Common/assert_cast.h>
 
 #include <AggregateFunctions/IAggregateFunction.h>

src/AggregateFunctions/AggregateFunctionUniq.cpp

@@ -132,6 +132,12 @@ void registerAggregateFunctionsUniq(AggregateFunctionFactory & factory)
 
     factory.registerFunction("uniqExact",
         {createAggregateFunctionUniq<true, AggregateFunctionUniqExactData, AggregateFunctionUniqExactData<String>>, properties});
+
+#if USE_DATASKETCHES
+    factory.registerFunction("uniqThetaSketch",
+        {createAggregateFunctionUniq<AggregateFunctionUniqThetaSketchData, AggregateFunctionUniqThetaSketchData>, properties});
+#endif
+
 }
 
 }

src/AggregateFunctions/AggregateFunctionUniq.h

@@ -22,6 +22,7 @@
 
 #include <AggregateFunctions/UniquesHashSet.h>
 #include <AggregateFunctions/IAggregateFunction.h>
+#include <AggregateFunctions/ThetaSketchData.h>
 #include <AggregateFunctions/UniqVariadicHash.h>
 
 
@@ -69,7 +70,7 @@ struct AggregateFunctionUniqHLL12Data<String>
 };
 
 template <>
-struct AggregateFunctionUniqHLL12Data<UInt128>
+struct AggregateFunctionUniqHLL12Data<UUID>
 {
     using Set = HyperLogLogWithSmallSetOptimization<UInt64, 16, 12>;
     Set set;
@@ -124,6 +125,19 @@ struct AggregateFunctionUniqExactData<String>
 };
 
 
+/// uniqThetaSketch
+#if USE_DATASKETCHES
+
+struct AggregateFunctionUniqThetaSketchData
+{
+    using Set = ThetaSketchData<UInt64>;
+    Set set;
+
+    static String getName() { return "uniqThetaSketch"; }
+};
+
+#endif
+
 namespace detail
 {
 
@@ -133,16 +147,14 @@ template <typename T> struct AggregateFunctionUniqTraits
 {
     static UInt64 hash(T x)
     {
-        if constexpr (std::is_same_v<T, UInt128>)
+        if constexpr (std::is_same_v<T, Float32> || std::is_same_v<T, Float64>)
-        {
-            return sipHash64(x);
-        }
-        else if constexpr (std::is_same_v<T, Float32> || std::is_same_v<T, Float64>)
         {
             return ext::bit_cast<UInt64>(x);
         }
         else if constexpr (sizeof(T) <= sizeof(UInt64))
+        {
             return x;
+        }
         else
             return DefaultHash64<T>(x);
     }
@@ -184,11 +196,17 @@ struct OneAdder
                 UInt128 key;
                 SipHash hash;
                 hash.update(value.data, value.size);
-                hash.get128(key.low, key.high);
+                hash.get128(key);
 
                 data.set.insert(key);
             }
         }
+#if USE_DATASKETCHES
+        else if constexpr (std::is_same_v<Data, AggregateFunctionUniqThetaSketchData>)
+        {
+            data.set.insertOriginal(column.getDataAt(row_num));
+        }
+#endif
     }
 };
 

src/AggregateFunctions/AggregateFunctionUniqCombined.cpp

@@ -3,11 +3,13 @@
 #include <AggregateFunctions/AggregateFunctionFactory.h>
 #include <AggregateFunctions/Helpers.h>
 
+#include <Common/FieldVisitors.h>
+
 #include <DataTypes/DataTypeDate.h>
 #include <DataTypes/DataTypeDateTime.h>
 
 #include <functional>
-#include "registerAggregateFunctions.h"
+
 
 namespace DB
 {

src/AggregateFunctions/AggregateFunctionUniqCombined.h

@@ -1,7 +1,6 @@
 #pragma once
 
 #include <Common/CombinedCardinalityEstimator.h>
-#include <Common/FieldVisitors.h>
 #include <Common/SipHash.h>
 #include <Common/typeid_cast.h>
 #include <Common/assert_cast.h>

src/AggregateFunctions/AggregateFunctionUniqUpTo.cpp

@@ -1,11 +1,11 @@
 #include <AggregateFunctions/AggregateFunctionFactory.h>
 #include <AggregateFunctions/Helpers.h>
 #include <AggregateFunctions/AggregateFunctionUniqUpTo.h>
+#include <Common/FieldVisitors.h>
 #include <DataTypes/DataTypeDate.h>
 #include <DataTypes/DataTypeDateTime.h>
 #include <DataTypes/DataTypeString.h>
 #include <DataTypes/DataTypeFixedString.h>
-#include "registerAggregateFunctions.h"
 
 
 namespace DB

src/AggregateFunctions/AggregateFunctionUniqUpTo.h

@@ -1,6 +1,7 @@
 #pragma once
 
-#include <Common/FieldVisitors.h>
+#include <common/unaligned.h>
+
 #include <Common/typeid_cast.h>
 #include <Common/assert_cast.h>
 
@@ -35,7 +36,7 @@ namespace DB
   */
 
 template <typename T>
-struct __attribute__((__packed__)) AggregateFunctionUniqUpToData
+struct AggregateFunctionUniqUpToData
 {
 /** If count == threshold + 1 - this means that it is "overflowed" (values greater than threshold).
   * In this case (for example, after calling the merge function), the `data` array does not necessarily contain the initialized values
@@ -43,7 +44,17 @@ struct __attribute__((__packed__)) AggregateFunctionUniqUpToData
   *   then set count to `threshold + 1`, and values from another state are not copied.
   */
     UInt8 count = 0;
-    T data[0];
+    char data_ptr[0];
+
+    T load(size_t i) const
+    {
+        return unalignedLoad<T>(data_ptr + i * sizeof(T));
+    }
+
+    void store(size_t i, const T & x)
+    {
+        unalignedStore<T>(data_ptr + i * sizeof(T), x);
+    }
 
     size_t size() const
     {
@@ -60,12 +71,12 @@ struct __attribute__((__packed__)) AggregateFunctionUniqUpToData
 
         /// Linear search for the matching element.
         for (size_t i = 0; i < count; ++i)
-            if (data[i] == x)
+            if (load(i) == x)
                 return;
 
         /// Did not find the matching element. If there is room for one more element, insert it.
         if (count < threshold)
-            data[count] = x;
+            store(count, x);
 
         /// After increasing count, the state may be overflowed.
         ++count;
@@ -84,7 +95,7 @@ struct __attribute__((__packed__)) AggregateFunctionUniqUpToData
         }
 
         for (size_t i = 0; i < rhs.count; ++i)
-            insert(rhs.data[i], threshold);
+            insert(rhs.load(i), threshold);
     }
 
     void write(WriteBuffer & wb, UInt8 threshold) const
@@ -93,7 +104,7 @@ struct __attribute__((__packed__)) AggregateFunctionUniqUpToData
 
         /// Write values only if the state is not overflowed. Otherwise, they are not needed, and only the fact that the state is overflowed is important.
         if (count <= threshold)
-            wb.write(reinterpret_cast<const char *>(data), count * sizeof(data[0]));
+            wb.write(data_ptr, count * sizeof(T));
     }
 
     void read(ReadBuffer & rb, UInt8 threshold)
@@ -101,7 +112,7 @@ struct __attribute__((__packed__)) AggregateFunctionUniqUpToData
         readBinary(count, rb);
 
         if (count <= threshold)
-            rb.read(reinterpret_cast<char *>(data), count * sizeof(data[0]));
+            rb.read(data_ptr, count * sizeof(T));
     }
 
     /// ALWAYS_INLINE is required to have better code layout for uniqUpTo function

src/AggregateFunctions/Helpers.h

@@ -15,12 +15,12 @@
     M(Float32) \
     M(Float64)
 
-// No UInt128 here because of the name conflict
 #define FOR_NUMERIC_TYPES(M) \
     M(UInt8) \
     M(UInt16) \
     M(UInt32) \
     M(UInt64) \
+    M(UInt128) \
     M(UInt256) \
     M(Int8) \
     M(Int16) \
@@ -109,6 +109,8 @@ static IAggregateFunction * createWithUnsignedIntegerType(const IDataType & argu
     if (which.idx == TypeIndex::UInt16) return new AggregateFunctionTemplate<UInt16, Data<UInt16>>(std::forward<TArgs>(args)...);
     if (which.idx == TypeIndex::UInt32) return new AggregateFunctionTemplate<UInt32, Data<UInt32>>(std::forward<TArgs>(args)...);
     if (which.idx == TypeIndex::UInt64) return new AggregateFunctionTemplate<UInt64, Data<UInt64>>(std::forward<TArgs>(args)...);
+    if (which.idx == TypeIndex::UInt128) return new AggregateFunctionTemplate<UInt128, Data<UInt128>>(std::forward<TArgs>(args)...);
+    if (which.idx == TypeIndex::UInt256) return new AggregateFunctionTemplate<UInt256, Data<UInt256>>(std::forward<TArgs>(args)...);
     return nullptr;
 }
 
@@ -119,11 +121,11 @@ static IAggregateFunction * createWithNumericBasedType(const IDataType & argumen
     if (f)
         return f;
 
-    /// expects that DataTypeDate based on UInt16, DataTypeDateTime based on UInt32 and UUID based on UInt128
+    /// expects that DataTypeDate based on UInt16, DataTypeDateTime based on UInt32
     WhichDataType which(argument_type);
     if (which.idx == TypeIndex::Date) return new AggregateFunctionTemplate<UInt16>(std::forward<TArgs>(args)...);
     if (which.idx == TypeIndex::DateTime) return new AggregateFunctionTemplate<UInt32>(std::forward<TArgs>(args)...);
-    if (which.idx == TypeIndex::UUID) return new AggregateFunctionTemplate<UInt128>(std::forward<TArgs>(args)...);
+    if (which.idx == TypeIndex::UUID) return new AggregateFunctionTemplate<UUID>(std::forward<TArgs>(args)...);
     return nullptr;
 }
 
@@ -184,6 +186,29 @@ static IAggregateFunction * createWithTwoNumericTypes(const IDataType & first_ty
     return nullptr;
 }
 
+template <typename FirstType, template <typename, typename> class AggregateFunctionTemplate, typename... TArgs>
+static IAggregateFunction * createWithTwoBasicNumericTypesSecond(const IDataType & second_type, TArgs && ... args)
+{
+    WhichDataType which(second_type);
+#define DISPATCH(TYPE) \
+    if (which.idx == TypeIndex::TYPE) return new AggregateFunctionTemplate<FirstType, TYPE>(std::forward<TArgs>(args)...);
+    FOR_BASIC_NUMERIC_TYPES(DISPATCH)
+#undef DISPATCH
+    return nullptr;
+}
+
+template <template <typename, typename> class AggregateFunctionTemplate, typename... TArgs>
+static IAggregateFunction * createWithTwoBasicNumericTypes(const IDataType & first_type, const IDataType & second_type, TArgs && ... args)
+{
+    WhichDataType which(first_type);
+#define DISPATCH(TYPE) \
+    if (which.idx == TypeIndex::TYPE) \
+        return createWithTwoBasicNumericTypesSecond<TYPE, AggregateFunctionTemplate>(second_type, std::forward<TArgs>(args)...);
+    FOR_BASIC_NUMERIC_TYPES(DISPATCH)
+#undef DISPATCH
+    return nullptr;
+}
+
 template <typename FirstType, template <typename, typename> class AggregateFunctionTemplate, typename... TArgs>
 static IAggregateFunction * createWithTwoNumericOrDateTypesSecond(const IDataType & second_type, TArgs && ... args)
 {
@@ -195,7 +220,7 @@ static IAggregateFunction * createWithTwoNumericOrDateTypesSecond(const IDataTyp
     if (which.idx == TypeIndex::Enum8) return new AggregateFunctionTemplate<FirstType, Int8>(std::forward<TArgs>(args)...);
     if (which.idx == TypeIndex::Enum16) return new AggregateFunctionTemplate<FirstType, Int16>(std::forward<TArgs>(args)...);
 
-    /// expects that DataTypeDate based on UInt16, DataTypeDateTime based on UInt32 and UUID based on UInt128
+    /// expects that DataTypeDate based on UInt16, DataTypeDateTime based on UInt32
     if (which.idx == TypeIndex::Date) return new AggregateFunctionTemplate<FirstType, UInt16>(std::forward<TArgs>(args)...);
     if (which.idx == TypeIndex::DateTime) return new AggregateFunctionTemplate<FirstType, UInt32>(std::forward<TArgs>(args)...);
 
@@ -216,7 +241,7 @@ static IAggregateFunction * createWithTwoNumericOrDateTypes(const IDataType & fi
     if (which.idx == TypeIndex::Enum16)
         return createWithTwoNumericOrDateTypesSecond<Int16, AggregateFunctionTemplate>(second_type, std::forward<TArgs>(args)...);
 
-    /// expects that DataTypeDate based on UInt16, DataTypeDateTime based on UInt32 and UUID based on UInt128
+    /// expects that DataTypeDate based on UInt16, DataTypeDateTime based on UInt32
     if (which.idx == TypeIndex::Date)
         return createWithTwoNumericOrDateTypesSecond<UInt16, AggregateFunctionTemplate>(second_type, std::forward<TArgs>(args)...);
     if (which.idx == TypeIndex::DateTime)

src/AggregateFunctions/QuantileExact.h

@@ -263,7 +263,7 @@ struct QuantileExactLow : public QuantileExactBase<Value, QuantileExactLow<Value
         {
             // sort inputs in ascending order
             std::sort(array.begin(), array.end());
-            size_t n = level < 1 ? level * array.size() : (array.size() - 1);
+
             // if level is 0.5 then compute the "low" median of the sorted array
             // by the method of rounding.
             if (level == 0.5)
@@ -278,10 +278,14 @@ struct QuantileExactLow : public QuantileExactBase<Value, QuantileExactLow<Value
                     return array[static_cast<size_t>((floor(s / 2)) - 1)];
                 }
             }
-            // else quantile is the nth index of the sorted array obtained by multiplying
+            else
-            // level and size of array. Example if level = 0.1 and size of array is 10,
+            {
-            // then return array[1].
+                // else quantile is the nth index of the sorted array obtained by multiplying
-            return array[n];
+                // level and size of array. Example if level = 0.1 and size of array is 10,
+                // then return array[1].
+                size_t n = level < 1 ? level * array.size() : (array.size() - 1);
+                return array[n];
+            }
         }
         return std::numeric_limits<Value>::quiet_NaN();
     }
@@ -295,7 +299,7 @@ struct QuantileExactLow : public QuantileExactBase<Value, QuantileExactLow<Value
             for (size_t i = 0; i < size; ++i)
             {
                 auto level = levels[indices[i]];
-                size_t n = level < 1 ? level * array.size() : (array.size() - 1);
+
                 // if level is 0.5 then compute the "low" median of the sorted array
                 // by the method of rounding.
                 if (level == 0.5)
@@ -310,9 +314,13 @@ struct QuantileExactLow : public QuantileExactBase<Value, QuantileExactLow<Value
                         result[indices[i]] = array[static_cast<size_t>(floor((s / 2) - 1))];
                     }
                 }
-                // else quantile is the nth index of the sorted array obtained by multiplying
+                else
-                // level and size of array. Example if level = 0.1 and size of array is 10.
+                {
-                result[indices[i]] = array[n];
+                    // else quantile is the nth index of the sorted array obtained by multiplying
+                    // level and size of array. Example if level = 0.1 and size of array is 10.
+                    size_t n = level < 1 ? level * array.size() : (array.size() - 1);
+                    result[indices[i]] = array[n];
+                }
             }
         }
         else
@@ -337,7 +345,7 @@ struct QuantileExactHigh : public QuantileExactBase<Value, QuantileExactHigh<Val
         {
             // sort inputs in ascending order
             std::sort(array.begin(), array.end());
-            size_t n = level < 1 ? level * array.size() : (array.size() - 1);
+
             // if level is 0.5 then compute the "high" median of the sorted array
             // by the method of rounding.
             if (level == 0.5)
@@ -345,9 +353,13 @@ struct QuantileExactHigh : public QuantileExactBase<Value, QuantileExactHigh<Val
                 auto s = array.size();
                 return array[static_cast<size_t>(floor(s / 2))];
             }
-            // else quantile is the nth index of the sorted array obtained by multiplying
+            else
-            // level and size of array. Example if level = 0.1 and size of array is 10.
+            {
-            return array[n];
+                // else quantile is the nth index of the sorted array obtained by multiplying
+                // level and size of array. Example if level = 0.1 and size of array is 10.
+                size_t n = level < 1 ? level * array.size() : (array.size() - 1);
+                return array[n];
+            }
         }
         return std::numeric_limits<Value>::quiet_NaN();
     }
@@ -361,7 +373,7 @@ struct QuantileExactHigh : public QuantileExactBase<Value, QuantileExactHigh<Val
             for (size_t i = 0; i < size; ++i)
             {
                 auto level = levels[indices[i]];
-                size_t n = level < 1 ? level * array.size() : (array.size() - 1);
+
                 // if level is 0.5 then compute the "high" median of the sorted array
                 // by the method of rounding.
                 if (level == 0.5)
@@ -369,9 +381,13 @@ struct QuantileExactHigh : public QuantileExactBase<Value, QuantileExactHigh<Val
                     auto s = array.size();
                     result[indices[i]] = array[static_cast<size_t>(floor(s / 2))];
                 }
-                // else quantile is the nth index of the sorted array obtained by multiplying
+                else
-                // level and size of array. Example if level = 0.1 and size of array is 10.
+                {
-                result[indices[i]] = array[n];
+                    // else quantile is the nth index of the sorted array obtained by multiplying
+                    // level and size of array. Example if level = 0.1 and size of array is 10.
+                    size_t n = level < 1 ? level * array.size() : (array.size() - 1);
+                    result[indices[i]] = array[n];
+                }
             }
         }
         else

src/AggregateFunctions/QuantileReservoirSampler.h

@@ -54,7 +54,7 @@ struct QuantileReservoirSampler
     /// Get the value of the `level` quantile. The level must be between 0 and 1.
     Value get(Float64 level)
     {
-        return data.quantileInterpolated(level);
+        return Value(data.quantileInterpolated(level));
     }
 
     /// Get the `size` values of `levels` quantiles. Write `size` results starting with `result` address.
@@ -62,7 +62,7 @@ struct QuantileReservoirSampler
     void getMany(const Float64 * levels, const size_t * indices, size_t size, Value * result)
     {
         for (size_t i = 0; i < size; ++i)
-            result[indices[i]] = data.quantileInterpolated(levels[indices[i]]);
+            result[indices[i]] = Value(data.quantileInterpolated(levels[indices[i]]));
     }
 
     /// The same, but in the case of an empty state, NaN is returned.

src/AggregateFunctions/ReservoirSampler.h

@@ -131,12 +131,20 @@ public:
         size_t left_index = static_cast<size_t>(index);
         size_t right_index = left_index + 1;
         if (right_index == samples.size())
-            return static_cast<double>(samples[left_index]);
+        {
+            if constexpr (DB::IsDecimalNumber<T>)
+                return static_cast<double>(samples[left_index].value);
+            else
+                return static_cast<double>(samples[left_index]);
+        }
 
         double left_coef = right_index - index;
         double right_coef = index - left_index;
 
-        return static_cast<double>(samples[left_index]) * left_coef + static_cast<double>(samples[right_index]) * right_coef;
+        if constexpr (DB::IsDecimalNumber<T>)
+            return static_cast<double>(samples[left_index].value) * left_coef + static_cast<double>(samples[right_index].value) * right_coef;
+        else
+            return static_cast<double>(samples[left_index]) * left_coef + static_cast<double>(samples[right_index]) * right_coef;
     }
 
     void merge(const ReservoirSampler<T, OnEmpty> & b)

src/AggregateFunctions/ThetaSketchData.h

@@ -0,0 +1,119 @@
+#pragma once
+
+#if !defined(ARCADIA_BUILD)
+#    include <Common/config.h>
+#endif
+
+#if USE_DATASKETCHES
+
+#include <boost/noncopyable.hpp>
+#include <memory>
+#include <theta_sketch.hpp> // Y_IGNORE
+#include <theta_union.hpp> // Y_IGNORE
+
+
+namespace DB
+{
+
+
+template <typename Key>
+class ThetaSketchData : private boost::noncopyable
+{
+private:
+    std::unique_ptr<datasketches::update_theta_sketch> sk_update;
+    std::unique_ptr<datasketches::theta_union> sk_union;
+
+    inline datasketches::update_theta_sketch * getSkUpdate()
+    {
+        if (!sk_update)
+            sk_update = std::make_unique<datasketches::update_theta_sketch>(datasketches::update_theta_sketch::builder().build());
+        return sk_update.get();
+    }
+
+    inline datasketches::theta_union * getSkUnion()
+    {
+        if (!sk_union)
+            sk_union = std::make_unique<datasketches::theta_union>(datasketches::theta_union::builder().build());
+        return sk_union.get();
+    }
+
+public:
+    using value_type = Key;
+
+    ThetaSketchData() = default;
+    ~ThetaSketchData() = default;
+
+    /// Insert original value without hash, as `datasketches::update_theta_sketch.update` will do the hash internal.
+    void insertOriginal(const StringRef & value)
+    {
+        getSkUpdate()->update(value.data, value.size);
+    }
+
+    /// Note that `datasketches::update_theta_sketch.update` will do the hash again.
+    void insert(Key value)
+    {
+        getSkUpdate()->update(value);
+    }
+
+    UInt64 size() const
+    {
+        if (sk_union)
+            return static_cast<UInt64>(sk_union->get_result().get_estimate());
+        else if (sk_update)
+            return static_cast<UInt64>(sk_update->get_estimate());
+        else
+            return 0;
+    }
+
+    void merge(const ThetaSketchData & rhs)
+    {
+        datasketches::theta_union * u = getSkUnion();
+
+        if (sk_update)
+        {
+            u->update(*sk_update);
+            sk_update.reset(nullptr);
+        }
+
+        if (rhs.sk_update)
+            u->update(*rhs.sk_update);
+        else if (rhs.sk_union)
+            u->update(rhs.sk_union->get_result());
+    }
+
+    /// You can only call for an empty object.
+    void read(DB::ReadBuffer & in)
+    {
+        datasketches::compact_theta_sketch::vector_bytes bytes;
+        readVectorBinary(bytes, in);
+        if (!bytes.empty())
+        {
+            auto sk = datasketches::compact_theta_sketch::deserialize(bytes.data(), bytes.size());
+            getSkUnion()->update(sk);
+        }
+    }
+
+    void write(DB::WriteBuffer & out) const
+    {
+        if (sk_update)
+        {
+            auto bytes = sk_update->compact().serialize();
+            writeVectorBinary(bytes, out);
+        }
+        else if (sk_union)
+        {
+            auto bytes = sk_union->get_result().serialize();
+            writeVectorBinary(bytes, out);
+        }
+        else
+        {
+            datasketches::compact_theta_sketch::vector_bytes bytes;
+            writeVectorBinary(bytes, out);
+        }
+    }
+};
+
+
+}
+
+#endif

src/AggregateFunctions/UniqVariadicHash.h

@@ -3,7 +3,6 @@
 #include <city.h>
 #include <Core/Defines.h>
 #include <Common/SipHash.h>
-#include <Common/UInt128.h>
 #include <Common/assert_cast.h>
 #include <Columns/ColumnTuple.h>
 
@@ -107,7 +106,7 @@ struct UniqVariadicHash<true, false>
         }
 
         UInt128 key;
-        hash.get128(key.low, key.high);
+        hash.get128(key);
         return key;
     }
 };
@@ -131,7 +130,7 @@ struct UniqVariadicHash<true, true>
         }
 
         UInt128 key;
-        hash.get128(key.low, key.high);
+        hash.get128(key);
         return key;
     }
 };

src/CMakeLists.txt

@@ -184,6 +184,7 @@ add_object_library(clickhouse_disks Disks)
 add_object_library(clickhouse_interpreters Interpreters)
 add_object_library(clickhouse_interpreters_mysql Interpreters/MySQL)
 add_object_library(clickhouse_interpreters_clusterproxy Interpreters/ClusterProxy)
+add_object_library(clickhouse_interpreters_jit Interpreters/JIT)
 add_object_library(clickhouse_columns Columns)
 add_object_library(clickhouse_storages Storages)
 add_object_library(clickhouse_storages_distributed Storages/Distributed)

src/Columns/ColumnDecimal.h

@@ -85,8 +85,8 @@ private:
     {}
 
 public:
-    const char * getFamilyName() const override { return TypeName<T>::get(); }
+    const char * getFamilyName() const override { return TypeName<T>; }
-    TypeIndex getDataType() const override { return TypeId<T>::value; }
+    TypeIndex getDataType() const override { return TypeId<T>; }
 
     bool isNumeric() const override { return false; }
     bool canBeInsideNullable() const override { return true; }

src/Columns/ColumnUnique.h

@@ -665,7 +665,7 @@ UInt128 ColumnUnique<ColumnType>::IncrementalHash::getHash(const ColumnType & co
             column.updateHashWithValue(i, sip_hash);
 
         std::lock_guard lock(mutex);
-        sip_hash.get128(hash.low, hash.high);
+        sip_hash.get128(hash);
         cur_hash = hash;
         num_added_rows.store(column_size);
     }

src/Columns/ColumnVector.cpp

@@ -33,6 +33,7 @@ namespace ErrorCodes
     extern const int PARAMETER_OUT_OF_BOUND;
     extern const int SIZES_OF_COLUMNS_DOESNT_MATCH;
     extern const int LOGICAL_ERROR;
+    extern const int NOT_IMPLEMENTED;
 }
 
 template <typename T>
@@ -154,7 +155,7 @@ void ColumnVector<T>::getPermutation(bool reverse, size_t limit, int nan_directi
     else
     {
         /// A case for radix sort
-        if constexpr (is_arithmetic_v<T> && !std::is_same_v<T, UInt128>)
+        if constexpr (is_arithmetic_v<T> && !is_big_int_v<T>)
         {
             /// Thresholds on size. Lower threshold is arbitrary. Upper threshold is chosen by the type for histogram counters.
             if (s >= 256 && s <= std::numeric_limits<UInt32>::max())
@@ -292,28 +293,37 @@ MutableColumnPtr ColumnVector<T>::cloneResized(size_t size) const
         memcpy(new_col.data.data(), data.data(), count * sizeof(data[0]));
 
         if (size > count)
-            memset(static_cast<void *>(&new_col.data[count]), static_cast<int>(ValueType()), (size - count) * sizeof(ValueType));
+            memset(static_cast<void *>(&new_col.data[count]), 0, (size - count) * sizeof(ValueType));
     }
 
     return res;
 }
 
 template <typename T>
-UInt64 ColumnVector<T>::get64(size_t n) const
+UInt64 ColumnVector<T>::get64(size_t n [[maybe_unused]]) const
 {
-    return ext::bit_cast<UInt64>(data[n]);
+    if constexpr (is_arithmetic_v<T>)
+        return ext::bit_cast<UInt64>(data[n]);
+    else
+        throw Exception(ErrorCodes::NOT_IMPLEMENTED, "Cannot get the value of {} as UInt64", TypeName<T>);
 }
 
 template <typename T>
-inline Float64 ColumnVector<T>::getFloat64(size_t n) const
+inline Float64 ColumnVector<T>::getFloat64(size_t n [[maybe_unused]]) const
 {
-    return static_cast<Float64>(data[n]);
+    if constexpr (is_arithmetic_v<T>)
+        return static_cast<Float64>(data[n]);
+    else
+        throw Exception(ErrorCodes::NOT_IMPLEMENTED, "Cannot get the value of {} as Float64", TypeName<T>);
 }
 
 template <typename T>
-Float32 ColumnVector<T>::getFloat32(size_t n) const
+Float32 ColumnVector<T>::getFloat32(size_t n [[maybe_unused]]) const
 {
-    return static_cast<Float32>(data[n]);
+    if constexpr (is_arithmetic_v<T>)
+        return static_cast<Float32>(data[n]);
+    else
+        throw Exception(ErrorCodes::NOT_IMPLEMENTED, "Cannot get the value of {} as Float32", TypeName<T>);
 }
 
 template <typename T>
@@ -482,8 +492,6 @@ void ColumnVector<T>::gather(ColumnGathererStream & gatherer)
 template <typename T>
 void ColumnVector<T>::getExtremes(Field & min, Field & max) const
 {
-    using FastRefT = std::conditional_t<is_big_int_v<T>, const T &, const T>;
-
     size_t size = data.size();
 
     if (size == 0)
@@ -504,7 +512,7 @@ void ColumnVector<T>::getExtremes(Field & min, Field & max) const
     T cur_min = NaNOrZero<T>();
     T cur_max = NaNOrZero<T>();
 
-    for (FastRefT x : data)
+    for (const T & x : data)
     {
         if (isNaN(x))
             continue;
@@ -569,5 +577,6 @@ template class ColumnVector<Int128>;
 template class ColumnVector<Int256>;
 template class ColumnVector<Float32>;
 template class ColumnVector<Float64>;
+template class ColumnVector<UUID>;
 
 }