From 1910434174234ccdf5e30291453eb5ebda687b9b Mon Sep 17 00:00:00 2001
From: Alexey Milovidov <milovidov@clickhouse.com>
Date: Wed, 30 Aug 2023 20:48:26 +0200
Subject: [PATCH 01/23] Remove CurrentStatusInfo

---
 src/Common/StatusInfo.cpp              | 57 --------------------------
 src/Common/StatusInfo.h                | 39 ------------------
 src/Interpreters/ExternalLoader.cpp    | 10 -----
 src/Server/PrometheusMetricsWriter.cpp | 38 -----------------
 src/Server/PrometheusMetricsWriter.h   |  2 -
 5 files changed, 146 deletions(-)
 delete mode 100644 src/Common/StatusInfo.cpp
 delete mode 100644 src/Common/StatusInfo.h

diff --git a/src/Common/StatusInfo.cpp b/src/Common/StatusInfo.cpp
deleted file mode 100644
index 1f9ddfaf4b9..00000000000
--- a/src/Common/StatusInfo.cpp
+++ /dev/null
@@ -1,57 +0,0 @@
-#include <Common/StatusInfo.h>
-#include <Common/ExternalLoaderStatus.h>
-
-/// Available status. Add something here as you wish.
-#define APPLY_FOR_STATUS(M) \
-    M(DictionaryStatus, "Dictionary Status.", DB::getStatusEnumAllPossibleValues()) \
-
-
-namespace CurrentStatusInfo
-{
-    #define M(NAME, DOCUMENTATION, ENUM) extern const Status NAME = Status(__COUNTER__);
-        APPLY_FOR_STATUS(M)
-    #undef M
-    constexpr Status END = Status(__COUNTER__);
-
-    std::mutex locks[END] {};
-    std::unordered_map<String, Int8> values[END] {};
-
-    const char * getName(Status event)
-    {
-        static const char * strings[] =
-        {
-        #define M(NAME, DOCUMENTATION, ENUM) #NAME,
-            APPLY_FOR_STATUS(M)
-        #undef M
-        };
-
-        return strings[event];
-    }
-
-    const char * getDocumentation(Status event)
-    {
-        static const char * strings[] =
-        {
-        #define M(NAME, DOCUMENTATION, ENUM) #DOCUMENTATION,
-            APPLY_FOR_STATUS(M)
-        #undef M
-        };
-
-        return strings[event];
-    }
-
-    const std::vector<std::pair<String, Int8>> & getAllPossibleValues(Status event)
-    {
-        static const std::vector<std::pair<String, Int8>> enum_values [] =
-        {
-        #define M(NAME, DOCUMENTATION, ENUM) ENUM,
-            APPLY_FOR_STATUS(M)
-        #undef M
-        };
-        return enum_values[event];
-    }
-
-    Status end() { return END; }
-}
-
-#undef APPLY_FOR_STATUS
diff --git a/src/Common/StatusInfo.h b/src/Common/StatusInfo.h
deleted file mode 100644
index 91e6d4d3b85..00000000000
--- a/src/Common/StatusInfo.h
+++ /dev/null
@@ -1,39 +0,0 @@
-#pragma once
-
-#include <stddef.h>
-#include <cstdint>
-#include <utility>
-#include <atomic>
-#include <vector>
-#include <base/types.h>
-#include <base/strong_typedef.h>
-#include <mutex>
-#include <unordered_map>
-
-
-namespace CurrentStatusInfo
-{
-    using Status = StrongTypedef<size_t, struct StatusTag>;
-    using Key = std::string;
-
-    const char * getName(Status event);
-    const char * getDocumentation(Status event);
-    const std::vector<std::pair<String, Int8>> & getAllPossibleValues(Status event);
-
-    extern std::unordered_map<String, Int8> values[];
-    extern std::mutex locks[];
-
-    Status end();
-
-    inline void set(Status status, Key key, Int8 value)
-    {
-        std::lock_guard lock(locks[status]);
-        values[status][key] = value;
-    }
-
-    inline void unset(Status status, Key key)
-    {
-        std::lock_guard lock(locks[status]);
-        values[status].erase(key);
-    }
-}
diff --git a/src/Interpreters/ExternalLoader.cpp b/src/Interpreters/ExternalLoader.cpp
index 5dee750889c..56d480d8735 100644
--- a/src/Interpreters/ExternalLoader.cpp
+++ b/src/Interpreters/ExternalLoader.cpp
@@ -1,7 +1,6 @@
 #include "ExternalLoader.h"
 
 #include <mutex>
-#include <pcg_random.hpp>
 #include <Common/MemoryTrackerBlockerInThread.h>
 #include <Common/Config/AbstractConfigurationComparison.h>
 #include <Common/Exception.h>
@@ -9,7 +8,6 @@
 #include <Common/ThreadPool.h>
 #include <Common/randomSeed.h>
 #include <Common/setThreadName.h>
-#include <Common/StatusInfo.h>
 #include <Common/scope_guard_safe.h>
 #include <Common/logger_useful.h>
 #include <base/chrono_io.h>
@@ -18,12 +16,6 @@
 #include <unordered_set>
 
 
-namespace CurrentStatusInfo
-{
-    extern const Status DictionaryStatus;
-}
-
-
 namespace DB
 {
 namespace ErrorCodes
@@ -1145,7 +1137,6 @@ private:
         if (info && (info->loading_id == loading_id))
         {
             info->loading_id = info->state_id;
-            CurrentStatusInfo::set(CurrentStatusInfo::DictionaryStatus, name, static_cast<Int8>(info->status()));
         }
         min_id_to_finish_loading_dependencies.erase(std::this_thread::get_id());
 
@@ -1307,7 +1298,6 @@ scope_guard ExternalLoader::addConfigRepository(std::unique_ptr<IExternalLoaderC
     return [this, ptr, name]()
     {
         config_files_reader->removeConfigRepository(ptr);
-        CurrentStatusInfo::unset(CurrentStatusInfo::DictionaryStatus, name);
         reloadConfig(name);
     };
 }
diff --git a/src/Server/PrometheusMetricsWriter.cpp b/src/Server/PrometheusMetricsWriter.cpp
index 2331e455225..a7d90b9985c 100644
--- a/src/Server/PrometheusMetricsWriter.cpp
+++ b/src/Server/PrometheusMetricsWriter.cpp
@@ -1,7 +1,6 @@
 #include "PrometheusMetricsWriter.h"
 
 #include <IO/WriteHelpers.h>
-#include <Common/StatusInfo.h>
 #include <regex>    /// TODO: this library is harmful.
 #include <algorithm>
 
@@ -51,7 +50,6 @@ PrometheusMetricsWriter::PrometheusMetricsWriter(
     , send_events(config.getBool(config_name + ".events", true))
     , send_metrics(config.getBool(config_name + ".metrics", true))
     , send_asynchronous_metrics(config.getBool(config_name + ".asynchronous_metrics", true))
-    , send_status_info(config.getBool(config_name + ".status_info", true))
 {
 }
 
@@ -120,42 +118,6 @@ void PrometheusMetricsWriter::write(WriteBuffer & wb) const
             writeOutLine(wb, key, value.value);
         }
     }
-
-    if (send_status_info)
-    {
-        for (size_t i = 0, end = CurrentStatusInfo::end(); i < end; ++i)
-        {
-            std::lock_guard lock(CurrentStatusInfo::locks[static_cast<CurrentStatusInfo::Status>(i)]);
-            std::string metric_name{CurrentStatusInfo::getName(static_cast<CurrentStatusInfo::Status>(i))};
-            std::string metric_doc{CurrentStatusInfo::getDocumentation(static_cast<CurrentStatusInfo::Status>(i))};
-
-            convertHelpToSingleLine(metric_doc);
-
-            if (!replaceInvalidChars(metric_name))
-                continue;
-            std::string key{current_status_prefix + metric_name};
-
-            writeOutLine(wb, "# HELP", key, metric_doc);
-            writeOutLine(wb, "# TYPE", key, "gauge");
-
-            for (const auto & value: CurrentStatusInfo::values[i])
-            {
-                for (const auto & enum_value: CurrentStatusInfo::getAllPossibleValues(static_cast<CurrentStatusInfo::Status>(i)))
-                {
-                    DB::writeText(key, wb);
-                    DB::writeChar('{', wb);
-                    DB::writeText(key, wb);
-                    DB::writeChar('=', wb);
-                    writeDoubleQuotedString(enum_value.first, wb);
-                    DB::writeText(",name=", wb);
-                    writeDoubleQuotedString(value.first, wb);
-                    DB::writeText("} ", wb);
-                    DB::writeText(value.second == enum_value.second, wb);
-                    DB::writeChar('\n', wb);
-                }
-            }
-        }
-    }
 }
 
 }
diff --git a/src/Server/PrometheusMetricsWriter.h b/src/Server/PrometheusMetricsWriter.h
index b4f6ab57def..b05eeaf0a3a 100644
--- a/src/Server/PrometheusMetricsWriter.h
+++ b/src/Server/PrometheusMetricsWriter.h
@@ -27,12 +27,10 @@ private:
     const bool send_events;
     const bool send_metrics;
     const bool send_asynchronous_metrics;
-    const bool send_status_info;
 
     static inline constexpr auto profile_events_prefix = "ClickHouseProfileEvents_";
     static inline constexpr auto current_metrics_prefix = "ClickHouseMetrics_";
     static inline constexpr auto asynchronous_metrics_prefix = "ClickHouseAsyncMetrics_";
-    static inline constexpr auto current_status_prefix = "ClickHouseStatusInfo_";
 };
 
 }

From 9d6dc1067f172187a739e0939e23acad0e631dc1 Mon Sep 17 00:00:00 2001
From: Alexey Milovidov <milovidov@clickhouse.com>
Date: Wed, 30 Aug 2023 20:49:02 +0200
Subject: [PATCH 02/23] Remove CurrentStatusInfo

---
 ...HouseStatusInfo_DictionaryStatus.reference | 18 ---------
 ...s_ClickHouseStatusInfo_DictionaryStatus.sh | 38 -------------------
 2 files changed, 56 deletions(-)
 delete mode 100644 tests/queries/0_stateless/02390_prometheus_ClickHouseStatusInfo_DictionaryStatus.reference
 delete mode 100755 tests/queries/0_stateless/02390_prometheus_ClickHouseStatusInfo_DictionaryStatus.sh

diff --git a/tests/queries/0_stateless/02390_prometheus_ClickHouseStatusInfo_DictionaryStatus.reference b/tests/queries/0_stateless/02390_prometheus_ClickHouseStatusInfo_DictionaryStatus.reference
deleted file mode 100644
index 50c91c3fa0c..00000000000
--- a/tests/queries/0_stateless/02390_prometheus_ClickHouseStatusInfo_DictionaryStatus.reference
+++ /dev/null
@@ -1,18 +0,0 @@
-status before reload
-status after reload
-NOT_LOADED 0
-LOADED 0
-FAILED 1
-LOADING 0
-FAILED_AND_RELOADING 0
-LOADED_AND_RELOADING 0
-NOT_EXIST 0
-status after reload, table exists
-NOT_LOADED 0
-LOADED 1
-FAILED 0
-LOADING 0
-FAILED_AND_RELOADING 0
-LOADED_AND_RELOADING 0
-NOT_EXIST 0
-status after drop
diff --git a/tests/queries/0_stateless/02390_prometheus_ClickHouseStatusInfo_DictionaryStatus.sh b/tests/queries/0_stateless/02390_prometheus_ClickHouseStatusInfo_DictionaryStatus.sh
deleted file mode 100755
index 65025858e20..00000000000
--- a/tests/queries/0_stateless/02390_prometheus_ClickHouseStatusInfo_DictionaryStatus.sh
+++ /dev/null
@@ -1,38 +0,0 @@
-#!/usr/bin/env bash
-# Tags: no-ordinary-database
-
-CUR_DIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
-# shellcheck source=../shell_config.sh
-. "$CUR_DIR"/../shell_config.sh
-
-function get_dictionary_status()
-{
-    local name=$1 && shift
-    $CLICKHOUSE_CURL -sS "$CLICKHOUSE_URL_PROMETHEUS" | {
-        awk -F'[{}=," ]' -vname="$name" '/ClickHouseStatusInfo_DictionaryStatus{/ && $(NF-3) == name { print $4, $NF }'
-    }
-}
-
-$CLICKHOUSE_CLIENT -q "CREATE DICTIONARY dict (key Int, value String) PRIMARY KEY key SOURCE(CLICKHOUSE(TABLE data)) LAYOUT(HASHED()) LIFETIME(0)"
-uuid="$($CLICKHOUSE_CLIENT -q "SELECT uuid FROM system.dictionaries WHERE database = '$CLICKHOUSE_DATABASE' AND name = 'dict'")"
-
-echo 'status before reload'
-get_dictionary_status "$uuid"
-
-# source table does not exists
-# NOTE: when dictionary does not exist it produce BAD_ARGUMENTS error, so using UNKNOWN_TABLE is safe
-$CLICKHOUSE_CLIENT -n -q "SYSTEM RELOAD DICTIONARY dict -- { serverError UNKNOWN_TABLE }"
-echo 'status after reload'
-get_dictionary_status "$uuid"
-
-# create source
-$CLICKHOUSE_CLIENT -q "CREATE TABLE data (key Int, value String) Engine=Null"
-$CLICKHOUSE_CLIENT -q "SYSTEM RELOAD DICTIONARY dict"
-echo 'status after reload, table exists'
-get_dictionary_status "$uuid"
-
-# remove dictionary
-$CLICKHOUSE_CLIENT -q "DROP DICTIONARY dict"
-$CLICKHOUSE_CLIENT -q "DROP TABLE data"
-echo 'status after drop'
-get_dictionary_status "$uuid"

From bb47e2cc234baab26d018f081cb257ff1d0b9cf0 Mon Sep 17 00:00:00 2001
From: Alexey Milovidov <milovidov@clickhouse.com>
Date: Wed, 30 Aug 2023 20:56:14 +0200
Subject: [PATCH 03/23] Remove CurrentStatusInfo

---
 .../testdata/configs/xml/config.xml           | 21 -------------------
 .../testdata/configs/yandex_xml/config.xml    | 21 -------------------
 programs/server/config.xml                    |  2 --
 .../test_config_xml_full/configs/config.xml   | 21 -------------------
 4 files changed, 65 deletions(-)

diff --git a/programs/diagnostics/testdata/configs/xml/config.xml b/programs/diagnostics/testdata/configs/xml/config.xml
index c08b0b2970f..50352ca800e 100644
--- a/programs/diagnostics/testdata/configs/xml/config.xml
+++ b/programs/diagnostics/testdata/configs/xml/config.xml
@@ -760,27 +760,6 @@
     </graphite>
     -->
 
-    <!-- Serve endpoint for Prometheus monitoring. -->
-    <!--
-        endpoint - mertics path (relative to root, statring with "/")
-        port - port to setup server. If not defined or 0 than http_port used
-        metrics - send data from table system.metrics
-        events - send data from table system.events
-        asynchronous_metrics - send data from table system.asynchronous_metrics
-        status_info - send data from different component from CH, ex: Dictionaries status
-    -->
-    <!--
-    <prometheus>
-        <endpoint>/metrics</endpoint>
-        <port>9363</port>
-
-        <metrics>true</metrics>
-        <events>true</events>
-        <asynchronous_metrics>true</asynchronous_metrics>
-        <status_info>true</status_info>
-    </prometheus>
-    -->
-
     <!-- Query log. Used only for queries with setting log_queries = 1. -->
     <query_log>
         <!-- What table to insert data. If table is not exist, it will be created.
diff --git a/programs/diagnostics/testdata/configs/yandex_xml/config.xml b/programs/diagnostics/testdata/configs/yandex_xml/config.xml
index c65418c6363..181f52a92f8 100644
--- a/programs/diagnostics/testdata/configs/yandex_xml/config.xml
+++ b/programs/diagnostics/testdata/configs/yandex_xml/config.xml
@@ -760,27 +760,6 @@
     </graphite>
     -->
 
-    <!-- Serve endpoint for Prometheus monitoring. -->
-    <!--
-        endpoint - mertics path (relative to root, statring with "/")
-        port - port to setup server. If not defined or 0 than http_port used
-        metrics - send data from table system.metrics
-        events - send data from table system.events
-        asynchronous_metrics - send data from table system.asynchronous_metrics
-        status_info - send data from different component from CH, ex: Dictionaries status
-    -->
-    <!--
-    <prometheus>
-        <endpoint>/metrics</endpoint>
-        <port>9363</port>
-
-        <metrics>true</metrics>
-        <events>true</events>
-        <asynchronous_metrics>true</asynchronous_metrics>
-        <status_info>true</status_info>
-    </prometheus>
-    -->
-
     <!-- Query log. Used only for queries with setting log_queries = 1. -->
     <query_log>
         <!-- What table to insert data. If table is not exist, it will be created.
diff --git a/programs/server/config.xml b/programs/server/config.xml
index 07052441a01..7f1d395faa4 100644
--- a/programs/server/config.xml
+++ b/programs/server/config.xml
@@ -971,7 +971,6 @@
         metrics - send data from table system.metrics
         events - send data from table system.events
         asynchronous_metrics - send data from table system.asynchronous_metrics
-        status_info - send data from different component from CH, ex: Dictionaries status
     -->
     <!--
     <prometheus>
@@ -981,7 +980,6 @@
         <metrics>true</metrics>
         <events>true</events>
         <asynchronous_metrics>true</asynchronous_metrics>
-        <status_info>true</status_info>
     </prometheus>
     -->
 
diff --git a/tests/integration/test_config_xml_full/configs/config.xml b/tests/integration/test_config_xml_full/configs/config.xml
index d142df18af8..ac59b3428e8 100644
--- a/tests/integration/test_config_xml_full/configs/config.xml
+++ b/tests/integration/test_config_xml_full/configs/config.xml
@@ -674,27 +674,6 @@
     </graphite>
     -->
 
-    <!-- Serve endpoint for Prometheus monitoring. -->
-    <!--
-        endpoint - mertics path (relative to root, statring with "/")
-        port - port to setup server. If not defined or 0 than http_port used
-        metrics - send data from table system.metrics
-        events - send data from table system.events
-        asynchronous_metrics - send data from table system.asynchronous_metrics
-        status_info - send data from different component from CH, ex: Dictionaries status
-    -->
-    <!--
-    <prometheus>
-        <endpoint>/metrics</endpoint>
-        <port>9363</port>
-
-        <metrics>true</metrics>
-        <events>true</events>
-        <asynchronous_metrics>true</asynchronous_metrics>
-        <status_info>true</status_info>
-    </prometheus>
-    -->
-
     <!-- Query log. Used only for queries with setting log_queries = 1. -->
     <query_log>
         <!-- What table to insert data. If table is not exist, it will be created.

From 3d5e7aefe97b4a674223144425a082d20d371a60 Mon Sep 17 00:00:00 2001
From: Alexey Milovidov <milovidov@clickhouse.com>
Date: Sun, 24 Sep 2023 21:01:55 +0200
Subject: [PATCH 04/23] Remove status_info from testdata

---
 programs/diagnostics/testdata/configs/yaml/config.yaml | 2 --
 1 file changed, 2 deletions(-)

diff --git a/programs/diagnostics/testdata/configs/yaml/config.yaml b/programs/diagnostics/testdata/configs/yaml/config.yaml
index 80d65e6b187..354065a8a9b 100644
--- a/programs/diagnostics/testdata/configs/yaml/config.yaml
+++ b/programs/diagnostics/testdata/configs/yaml/config.yaml
@@ -638,7 +638,6 @@ default_session_timeout: 60
 # metrics - send data from table system.metrics
 # events - send data from table system.events
 # asynchronous_metrics - send data from table system.asynchronous_metrics
-# status_info - send data from different component from CH, ex: Dictionaries status
 
 # prometheus:
 #     endpoint: /metrics
@@ -647,7 +646,6 @@ default_session_timeout: 60
 #     metrics: true
 #     events: true
 #     asynchronous_metrics: true
-#     status_info: true
 
 # Query log. Used only for queries with setting log_queries = 1.
 query_log:

From 51ef0ec4bc5f41078cf54539b248ba3354fac0ca Mon Sep 17 00:00:00 2001
From: Alexey Milovidov <milovidov@clickhouse.com>
Date: Sun, 24 Sep 2023 21:02:23 +0200
Subject: [PATCH 05/23] Remove status_info from example

---
 programs/server/config.yaml.example | 2 --
 1 file changed, 2 deletions(-)

diff --git a/programs/server/config.yaml.example b/programs/server/config.yaml.example
index a8f97ae5632..b472b6f4a45 100644
--- a/programs/server/config.yaml.example
+++ b/programs/server/config.yaml.example
@@ -639,7 +639,6 @@ default_session_timeout: 60
 # metrics - send data from table system.metrics
 # events - send data from table system.events
 # asynchronous_metrics - send data from table system.asynchronous_metrics
-# status_info - send data from different component from CH, ex: Dictionaries status
 
 # prometheus:
 #     endpoint: /metrics
@@ -648,7 +647,6 @@ default_session_timeout: 60
 #     metrics: true
 #     events: true
 #     asynchronous_metrics: true
-#     status_info: true
 
 # Query log. Used only for queries with setting log_queries = 1.
 query_log:

From 5e5761f6b3781edfccb2ca725dd74682feaad158 Mon Sep 17 00:00:00 2001
From: zvonand <azvonov@altinity.com>
Date: Sun, 24 Sep 2023 13:01:23 +0200
Subject: [PATCH 06/23] added docs

---
 .../functions/other-functions.md              | 29 +++++++++++++++----
 .../functions/other-functions.md              | 16 +++++++---
 2 files changed, 36 insertions(+), 9 deletions(-)

diff --git a/docs/en/sql-reference/functions/other-functions.md b/docs/en/sql-reference/functions/other-functions.md
index 566eff76584..378fc821df9 100644
--- a/docs/en/sql-reference/functions/other-functions.md
+++ b/docs/en/sql-reference/functions/other-functions.md
@@ -660,21 +660,26 @@ SELECT
 
 ## formatReadableTimeDelta
 
-Given a time interval (delta) in seconds, this function returns a time delta with year/month/day/hour/minute/second as string.
+Given a time interval (delta) in seconds, this function returns a time delta with year/month/day/hour/minute/second/millisecond/microsecond/nanosecond as string.
 
 **Syntax**
 
 ``` sql
-formatReadableTimeDelta(column[, maximum_unit])
+formatReadableTimeDelta(column[, maximum_unit, minimum_unit])
 ```
 
 **Arguments**
 
 - `column` — A column with a numeric time delta.
-- `maximum_unit` — Optional. Maximum unit to show. Acceptable values `seconds`, `minutes`, `hours`, `days`, `months`, `years`.
-
-Example:
+- `maximum_unit` — Optional. Maximum unit to show.
+  * Acceptable values: `nanoseconds`, `microseconds`, `milliseconds`, `seconds`, `minutes`, `hours`, `days`, `months`, `years`.
+  * Default value: `years`.
+- `minimum_unit` — Optional. Minimum unit to show. All smaller units are truncated.
+  * Acceptable values: `nanoseconds`, `microseconds`, `milliseconds`, `seconds`, `minutes`, `hours`, `days`, `months`, `years`.
+  * If explicitly specified value is bigger than `maximum_unit`, an exception will be thrown.
+  * Default value: `seconds` if `maximum_unit` is `seconds` or bigger, `nanoseconds` otherwise.
 
+**Example**
 ``` sql
 SELECT
     arrayJoin([100, 12345, 432546534]) AS elapsed,
@@ -703,6 +708,20 @@ SELECT
 └────────────┴─────────────────────────────────────────────────────────────────┘
 ```
 
+```sql
+SELECT
+    arrayJoin([100, 12345, 432546534.00000006]) AS elapsed,
+    formatReadableTimeDelta(elapsed, 'minutes', 'nanoseconds') AS time_delta
+```
+
+```text
+┌────────────elapsed─┬─time_delta─────────────────────────────────────┐
+│                100 │ 1 minute and 40 seconds                        │
+│              12345 │ 205 minutes and 45 seconds                     │
+│ 432546534.00000006 │ 7209108 minutes, 54 seconds and 60 nanoseconds │
+└────────────────────┴────────────────────────────────────────────────┘
+```
+
 ## parseTimeDelta
 
 Parse a sequence of numbers followed by something resembling a time unit.
diff --git a/docs/ru/sql-reference/functions/other-functions.md b/docs/ru/sql-reference/functions/other-functions.md
index 78608aaf817..835aed934d5 100644
--- a/docs/ru/sql-reference/functions/other-functions.md
+++ b/docs/ru/sql-reference/functions/other-functions.md
@@ -659,9 +659,11 @@ SELECT
 └────────────────┴───────────────────┘
 ```
 
+
 ## formatReadableTimeDelta {#formatreadabletimedelta}
 
-Принимает дельту времени в секундах. Возвращает дельту времени с (год, месяц, день, час, минута, секунда) в виде строки.
+Принимает дельту времени в секундах. Возвращает дельту времени в виде строки.
+Есть возможность указать наиболее крупную единицу измерения для вывода (год, месяц, день, час, минута, секунда, милли/микро/наносекунда).
 
 **Синтаксис**
 
@@ -671,10 +673,16 @@ formatReadableTimeDelta(column[, maximum_unit])
 
 **Аргументы**
 
--   `column` — Столбец с числовой дельтой времени.
--   `maximum_unit` — Опциональный параметр. Максимальная единица измерения для отображения. Допустимые значения: секунды, минуты, часы, дни, месяцы, годы.
+- `column` — Столбец с числовой дельтой времени.
+- `maximum_unit` — Опциональный параметр. Максимальная единица измерения для отображения.
+  * Допустимые значения: `nanoseconds`, `microseconds`, `milliseconds`, `seconds`, `minutes`, `hours`, `days`, `months`, `years`.
+  * Значение по умолчанию: `years`.
+- `minimum_unit` — Опциональный параметр. Минимальная единица измерения для отображения. Более мелкие единицы будут отброшены.
+  * Допустимые значения: `nanoseconds`, `microseconds`, `milliseconds`, `seconds`, `minutes`, `hours`, `days`, `months`, `years`.
+  * Если минимальная единица задана явно и превышает максимальную единицу, будет выкинуто исключение.
+  * Значение по умолчанию: `seconds` если максимальная единица -- секунда или более крупный интервал, в противном случае -- `nanoseconds`.
 
-Пример:
+**Пример**
 
 ``` sql
 SELECT

From 77785925269390facbf31eb82e098bafc83b0b9b Mon Sep 17 00:00:00 2001
From: zvonand <azvonov@altinity.com>
Date: Sun, 24 Sep 2023 13:04:56 +0200
Subject: [PATCH 07/23] added subseconds to formatReadableTimeDelta and add
 tests

---
 src/Functions/formatReadableTimeDelta.cpp     | 250 +++++++++++++-----
 ...at_readable_timedelta_subseconds.reference |  24 ++
 ...7_format_readable_timedelta_subseconds.sql |  30 +++
 3 files changed, 243 insertions(+), 61 deletions(-)
 create mode 100644 tests/queries/0_stateless/02887_format_readable_timedelta_subseconds.reference
 create mode 100644 tests/queries/0_stateless/02887_format_readable_timedelta_subseconds.sql

diff --git a/src/Functions/formatReadableTimeDelta.cpp b/src/Functions/formatReadableTimeDelta.cpp
index 5fd48c01e8f..96d3a6fd966 100644
--- a/src/Functions/formatReadableTimeDelta.cpp
+++ b/src/Functions/formatReadableTimeDelta.cpp
@@ -2,11 +2,11 @@
 #include <Functions/IFunction.h>
 #include <Functions/FunctionHelpers.h>
 #include <Columns/ColumnString.h>
-#include <Columns/ColumnVector.h>
 #include <Common/NaNUtils.h>
 #include <DataTypes/DataTypeString.h>
 #include <IO/WriteBufferFromVector.h>
 #include <IO/WriteHelpers.h>
+#include <IO/DoubleConverter.h>
 
 
 namespace DB
@@ -14,9 +14,10 @@ namespace DB
 
 namespace ErrorCodes
 {
-    extern const int NUMBER_OF_ARGUMENTS_DOESNT_MATCH;
-    extern const int ILLEGAL_TYPE_OF_ARGUMENT;
-    extern const int BAD_ARGUMENTS;
+extern const int CANNOT_PRINT_FLOAT_OR_DOUBLE_NUMBER;
+extern const int NUMBER_OF_ARGUMENTS_DOESNT_MATCH;
+extern const int ILLEGAL_TYPE_OF_ARGUMENT;
+extern const int BAD_ARGUMENTS;
 }
 
 namespace
@@ -52,75 +53,88 @@ public:
     {
         if (arguments.empty())
             throw Exception(ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH,
-                "Number of arguments for function {} doesn't match: passed {}, should be at least 1.",
-                getName(), arguments.size());
+                            "Number of arguments for function {} doesn't match: passed {}, should be at least 1.",
+                            getName(), arguments.size());
 
-        if (arguments.size() > 2)
+        if (arguments.size() > 3)
             throw Exception(ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH,
-                "Number of arguments for function {} doesn't match: passed {}, should be at most 2.",
-                getName(), arguments.size());
+                            "Number of arguments for function {} doesn't match: passed {}, should be 1, 2 or 3.",
+                            getName(), arguments.size());
 
         const IDataType & type = *arguments[0];
 
         if (!isNativeNumber(type))
             throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Cannot format {} as time delta", type.getName());
 
-        if (arguments.size() == 2)
+        if (arguments.size() >= 2)
         {
             const auto * maximum_unit_arg = arguments[1].get();
             if (!isStringOrFixedString(maximum_unit_arg))
                 throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Illegal type {} of argument maximum_unit of function {}",
                                 maximum_unit_arg->getName(), getName());
+
+            if (arguments.size() == 3)
+            {
+                const auto * minimum_unit_arg = arguments[2].get();
+                if (!isStringOrFixedString(minimum_unit_arg))
+                    throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Illegal type {} of argument minimum_unit of function {}",
+                                    minimum_unit_arg->getName(), getName());
+            }
         }
 
         return std::make_shared<DataTypeString>();
     }
 
-    ColumnNumbers getArgumentsThatAreAlwaysConstant() const override { return {1}; }
+    ColumnNumbers getArgumentsThatAreAlwaysConstant() const override { return {1, 2}; }
 
     bool useDefaultImplementationForConstants() const override { return true; }
 
     enum Unit
     {
-        Seconds,
-        Minutes,
-        Hours,
-        Days,
-        Months,
-        Years
+        Nanoseconds = 1,
+        Microseconds = 2,
+        Milliseconds = 3,
+        Seconds = 4,
+        Minutes = 5,
+        Hours = 6,
+        Days = 7,
+        Months = 8,
+        Years = 9
     };
 
     ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t input_rows_count) const override
     {
-        std::string_view maximum_unit_str;
-        if (arguments.size() == 2)
+        std::string_view maximum_unit_str, minimum_unit_str;
+        if (arguments.size() >= 2)
         {
             const ColumnPtr & maximum_unit_column = arguments[1].column;
             const ColumnConst * maximum_unit_const_col = checkAndGetColumnConstStringOrFixedString(maximum_unit_column.get());
             if (maximum_unit_const_col)
                 maximum_unit_str = maximum_unit_const_col->getDataColumn().getDataAt(0).toView();
+
+            if (arguments.size() == 3)
+            {
+                const ColumnPtr & minimum_unit_column = arguments[2].column;
+                const ColumnConst * minimum_unit_const_col = checkAndGetColumnConstStringOrFixedString(minimum_unit_column.get());
+                if (minimum_unit_const_col)
+                    minimum_unit_str = minimum_unit_const_col->getDataColumn().getDataAt(0).toView();
+            }
         }
+        /// Default means "use all available whole units".
+        Unit max_unit = dispatchUnit(maximum_unit_str, Years, "maximum");
+        /// Set seconds as min_unit by default not to ruin old use cases
+        Unit min_unit = dispatchUnit(minimum_unit_str, Seconds, "minimum");
 
-        Unit max_unit;
-
-        /// Default means "use all available units".
-        if (maximum_unit_str.empty() || maximum_unit_str == "years")
-            max_unit = Years;
-        else if (maximum_unit_str == "months")
-            max_unit = Months;
-        else if (maximum_unit_str == "days")
-            max_unit = Days;
-        else if (maximum_unit_str == "hours")
-            max_unit = Hours;
-        else if (maximum_unit_str == "minutes")
-            max_unit = Minutes;
-        else if (maximum_unit_str == "seconds")
-            max_unit = Seconds;
-        else
-            throw Exception(ErrorCodes::BAD_ARGUMENTS,
-                "Unexpected value of maximum unit argument ({}) for function {}, the only allowed values are:"
-                " 'seconds', 'minutes', 'hours', 'days', 'months', 'years'.",
-                maximum_unit_str, getName());
+        if (min_unit > max_unit)
+        {
+            if (minimum_unit_str.empty())
+                min_unit = Nanoseconds;   /// User wants sub-second max_unit. Show him all sub-second units unless other specified.
+            else
+                throw Exception(ErrorCodes::BAD_ARGUMENTS,
+                                "Explicitly specified value of minimum unit argument ({}) for function {} "
+                                "must not be greater than maximum unit value ({}).",
+                                minimum_unit_str, getName(), maximum_unit_str);
+        }
 
         auto col_to = ColumnString::create();
 
@@ -152,14 +166,61 @@ public:
                 /// To output separators between parts: ", " and " and ".
                 bool has_output = false;
 
+                Float64 whole_part;
+                std::string fractional_str = getFractionalString(std::modf(value, &whole_part));
+
                 switch (max_unit) /// A kind of Duff Device.
                 {
-                    case Years:     processUnit(365 * 24 * 3600, " year", 5, value, buf_to, has_output); [[fallthrough]];
-                    case Months:    processUnit(static_cast<UInt64>(30.5 * 24 * 3600), " month", 6, value, buf_to, has_output); [[fallthrough]];
-                    case Days:      processUnit(24 * 3600, " day", 4, value, buf_to, has_output); [[fallthrough]];
-                    case Hours:     processUnit(3600, " hour", 5, value, buf_to, has_output); [[fallthrough]];
-                    case Minutes:   processUnit(60, " minute", 7, value, buf_to, has_output); [[fallthrough]];
-                    case Seconds:   processUnit(1, " second", 7, value, buf_to, has_output);
+                    case Years:
+                        processUnit(365 * 24 * 3600, 0, " year", 5, whole_part, fractional_str, buf_to, has_output, min_unit, min_unit == Years);
+                        if (min_unit == Years)
+                            break;
+                        [[fallthrough]];
+
+                    case Months:
+                        processUnit(static_cast<UInt64>(30.5 * 24 * 3600), 0, " month", 6, whole_part, fractional_str, buf_to, has_output, min_unit, min_unit == Months);
+                        if (min_unit == Months)
+                            break;
+                        [[fallthrough]];
+
+                    case Days:
+                        processUnit(24 * 3600, 0, " day", 4, whole_part, fractional_str, buf_to, has_output, min_unit, min_unit == Days);
+                        if (min_unit == Days)
+                            break;
+                        [[fallthrough]];
+
+                    case Hours:
+                        processUnit(3600, 0, " hour", 5, whole_part, fractional_str, buf_to, has_output, min_unit, min_unit == Hours);
+                        if (min_unit == Hours)
+                            break;
+                        [[fallthrough]];
+
+                    case Minutes:
+                        processUnit(60, 0, " minute", 7, whole_part, fractional_str, buf_to, has_output, min_unit, min_unit == Minutes);
+                        if (min_unit == Minutes)
+                            break;
+                        [[fallthrough]];
+
+                    case Seconds:
+                        processUnit(1, 0, " second", 7, whole_part, fractional_str, buf_to, has_output, min_unit, min_unit == Seconds);
+                        if (min_unit == Seconds)
+                            break;
+                        [[fallthrough]];
+
+                    case Milliseconds:
+                        processUnit(1, 3, " millisecond", 12, whole_part, fractional_str, buf_to, has_output, min_unit, min_unit == Milliseconds);
+                        if (min_unit == Milliseconds)
+                            break;
+                        [[fallthrough]];
+
+                    case Microseconds:
+                        processUnit(1, 6, " microsecond", 12, whole_part, fractional_str, buf_to, has_output, min_unit, min_unit == Microseconds);
+                        if (min_unit == Microseconds)
+                            break;
+                        [[fallthrough]];
+
+                    case Nanoseconds:
+                        processUnit(1, 9, " nanosecond", 11, whole_part, fractional_str, buf_to, has_output, min_unit, true);
                 }
             }
 
@@ -172,42 +233,68 @@ public:
     }
 
     static void processUnit(
-        UInt64 unit_size, const char * unit_name, size_t unit_name_size,
-        Float64 & value, WriteBuffer & buf_to, bool & has_output)
+        UInt64 unit_multiplier, UInt32 unit_scale, const char * unit_name, size_t unit_name_size, Float64 & whole_part,
+        String & fractional_str, WriteBuffer & buf_to, bool & has_output,  Unit min_unit, bool is_minimum_unit)
     {
-        if (unlikely(value + 1.0 == value))
+        if (unlikely(whole_part + 1.0 == whole_part))
         {
             /// The case when value is too large so exact representation for subsequent smaller units is not possible.
-            writeText(std::floor(value / unit_size), buf_to);
+            writeText(std::floor(whole_part * DecimalUtils::scaleMultiplier<Int64>(unit_scale) / unit_multiplier), buf_to);
             buf_to.write(unit_name, unit_name_size);
             writeChar('s', buf_to);
             has_output = true;
-            value = 0;
+            whole_part = 0;
             return;
         }
-
-        UInt64 num_units = static_cast<UInt64>(value / unit_size);
-
-        if (!num_units)
+        UInt64 num_units = 0;
+        if (unit_scale == 0)  /// dealing with whole number of seconds
         {
-            /// Zero units, no need to print. But if it's the last (seconds) and the only unit, print "0 seconds" nevertheless.
-            if (unit_size > 1 || has_output)
-                return;
+            num_units = static_cast<UInt64>(std::floor(whole_part / unit_multiplier));
+
+            if (!num_units)
+            {
+                /// Zero units, no need to print. But if it's the last (seconds) and the only unit, print "0 seconds" nevertheless.
+                if (unit_multiplier != 1 || has_output)
+                    return;
+            }
+
+            /// Remaining value to print on next iteration.
+            whole_part -= num_units * unit_multiplier;
+        }
+        else   /// dealing with sub-seconds, a bit more peculiar to avoid more precision issues
+        {
+            if (whole_part >= 1)  /// There were no whole units printed
+            {
+                num_units += static_cast<UInt64>(whole_part) * DecimalUtils::scaleMultiplier<Int64>(unit_scale);
+                whole_part = 0;
+            }
+
+            for (UInt32 i = 0; i < unit_scale; ++i)
+            {
+                num_units += (fractional_str[i] - '0') * DecimalUtils::scaleMultiplier<Int64>(unit_scale - i - 1);
+                fractional_str[i] = '0';
+            }
+
+            if (!num_units)
+            {
+                /// Zero units, no need to print. But if it's the last (nanoseconds) and the only unit, print "0 nanoseconds" nevertheless.
+                if (!is_minimum_unit || has_output)
+                    return;
+            }
         }
 
-        /// Remaining value to print on next iteration.
-        value -= num_units * unit_size;
-
+        /// Write number of units
         if (has_output)
         {
             /// Need delimiter between values. The last delimiter is " and ", all previous are comma.
-            if (value < 1)
+            if (is_minimum_unit || (whole_part < 1 && fractional_str.substr(0, (4 - min_unit) * 3) == std::string((4 - min_unit) * 3, '0')))
                 writeCString(" and ", buf_to);
             else
                 writeCString(", ", buf_to);
         }
 
         writeText(num_units, buf_to);
+
         buf_to.write(unit_name, unit_name_size); /// If we just leave strlen(unit_name) here, clang-11 fails to make it compile-time.
 
         /// How to pronounce: unit vs. units.
@@ -216,6 +303,47 @@ public:
 
         has_output = true;
     }
+
+private:
+    static std::string getFractionalString(const Float64 & fractional_part)
+    {
+        DB::DoubleConverter<true>::BufferType buffer;
+        double_conversion::StringBuilder builder{buffer, sizeof(buffer)};
+
+        if (!DB::DoubleConverter<false>::instance().ToFixed(fractional_part, 9, &builder))
+            throw DB::Exception(DB::ErrorCodes::CANNOT_PRINT_FLOAT_OR_DOUBLE_NUMBER, "Cannot print double number: {}", fractional_part);
+
+        return std::string(buffer, builder.position()).substr(2);   /// do not return `0.` -- we don't need it
+    }
+
+    Unit dispatchUnit(const std::string_view & unit_str, const Unit default_unit, const std::string & bound_name) const
+    {
+        if (unit_str.empty())
+            return default_unit;
+        else if (unit_str == "years")
+            return Years;
+        else if (unit_str == "months")
+            return Months;
+        else if (unit_str == "days")
+            return Days;
+        else if (unit_str == "hours")
+            return Hours;
+        else if (unit_str == "minutes")
+            return Minutes;
+        else if (unit_str == "seconds")
+            return Seconds;
+        else if (unit_str == "milliseconds")
+            return Milliseconds;
+        else if (unit_str == "microseconds")
+            return Microseconds;
+        else if (unit_str == "nanoseconds")
+            return Nanoseconds;
+        else
+            throw Exception(ErrorCodes::BAD_ARGUMENTS,
+                            "Unexpected value of {} unit argument ({}) for function {}, the only allowed values are:"
+                            " 'nanoseconds', 'microseconds', 'nanoseconds', 'seconds', 'minutes', 'hours', 'days', 'months', 'years'.",
+                            bound_name, unit_str, getName());
+    }
 };
 
 }
diff --git a/tests/queries/0_stateless/02887_format_readable_timedelta_subseconds.reference b/tests/queries/0_stateless/02887_format_readable_timedelta_subseconds.reference
new file mode 100644
index 00000000000..389479eb529
--- /dev/null
+++ b/tests/queries/0_stateless/02887_format_readable_timedelta_subseconds.reference
@@ -0,0 +1,24 @@
+1 second
+1 minute
+2 minutes and 3 seconds
+24 seconds
+35 seconds
+1 minute and 6 seconds
+1 minute and 7 seconds
+48 seconds
+1 minute and 39 seconds
+1 hour
+1120 milliseconds
+60200 milliseconds
+123330 milliseconds
+24450 milliseconds
+35570 milliseconds
+66640 milliseconds
+67797 milliseconds, 979 microseconds and 790 nanoseconds
+48888 milliseconds and 888 microseconds
+99960 milliseconds
+3600000 milliseconds
+0 seconds
+1 hour and 1 second
+0 nanoseconds
+1000 milliseconds and 500 microseconds
diff --git a/tests/queries/0_stateless/02887_format_readable_timedelta_subseconds.sql b/tests/queries/0_stateless/02887_format_readable_timedelta_subseconds.sql
new file mode 100644
index 00000000000..0a8a76d54fd
--- /dev/null
+++ b/tests/queries/0_stateless/02887_format_readable_timedelta_subseconds.sql
@@ -0,0 +1,30 @@
+-- max_unit bigger than second, min_unit omitted (and considered 'seconds')
+WITH
+    'hours' AS maximum_unit,
+    arrayJoin([1.12, 60.2, 123.33, 24.45, 35.57, 66.64, 67.79, 48.88, 99.96, 3600]) AS elapsed
+SELECT
+    formatReadableTimeDelta(elapsed, maximum_unit) AS time_delta;
+
+-- max_unit smaller than second, min_unit omitted (and considered 'nanoseconds')
+WITH
+    'milliseconds' AS maximum_unit,
+    arrayJoin([1.12, 60.2, 123.33, 24.45, 35.57, 66.64, 67.79797979, 48.888888, 99.96, 3600]) AS elapsed
+SELECT
+    formatReadableTimeDelta(elapsed, maximum_unit) AS time_delta;
+
+-- Check exception is thrown
+SELECT formatReadableTimeDelta(1.1, 'seconds', 'hours'); -- { serverError BAD_ARGUMENTS }
+
+-- Check empty units are omitted unless they are the only one
+WITH
+    'hours' AS maximum_unit,
+    'microseconds' as minimum_unit,
+    arrayJoin([0, 3601.000000003]) AS elapsed
+SELECT
+    formatReadableTimeDelta(elapsed, maximum_unit, minimum_unit);
+
+WITH
+    'milliseconds' AS maximum_unit,
+    arrayJoin([0, 1.0005]) AS elapsed
+SELECT
+    formatReadableTimeDelta(elapsed, maximum_unit);

From b8695525ad1c54f03ba29b74ea05f9a2c15f3e50 Mon Sep 17 00:00:00 2001
From: Alexey Milovidov <milovidov@clickhouse.com>
Date: Sun, 24 Sep 2023 19:17:33 +0200
Subject: [PATCH 08/23] Add a test for compatibility

---
 .../0_stateless/02887_tuple_element_distributed.reference   | 6 ++++++
 .../queries/0_stateless/02887_tuple_element_distributed.sql | 1 +
 2 files changed, 7 insertions(+)
 create mode 100644 tests/queries/0_stateless/02887_tuple_element_distributed.reference
 create mode 100644 tests/queries/0_stateless/02887_tuple_element_distributed.sql

diff --git a/tests/queries/0_stateless/02887_tuple_element_distributed.reference b/tests/queries/0_stateless/02887_tuple_element_distributed.reference
new file mode 100644
index 00000000000..a9e2f17562a
--- /dev/null
+++ b/tests/queries/0_stateless/02887_tuple_element_distributed.reference
@@ -0,0 +1,6 @@
+1
+1
+1
+1
+1
+1
diff --git a/tests/queries/0_stateless/02887_tuple_element_distributed.sql b/tests/queries/0_stateless/02887_tuple_element_distributed.sql
new file mode 100644
index 00000000000..b9c5c856d00
--- /dev/null
+++ b/tests/queries/0_stateless/02887_tuple_element_distributed.sql
@@ -0,0 +1 @@
+SELECT equals(tupleElement(tuple('a', 10) AS x, 1), 'a') FROM remote('127.0.0.{1,2,3}', numbers(2));

From bb0375d97015a030193db8ffec13dd4df6edc1d0 Mon Sep 17 00:00:00 2001
From: Nikolay Degterinsky <evillique@gmail.com>
Date: Fri, 22 Sep 2023 20:20:21 +0000
Subject: [PATCH 09/23] Fix data race in SYSTEM STOP LISTEN

---
 programs/server/Server.cpp | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/programs/server/Server.cpp b/programs/server/Server.cpp
index a968acb549f..78f3f749d9a 100644
--- a/programs/server/Server.cpp
+++ b/programs/server/Server.cpp
@@ -1516,11 +1516,13 @@ try
 
     global_context->setStopServersCallback([&](const ServerType & server_type)
     {
+        std::lock_guard lock(servers_lock);
         stopServers(servers, server_type);
     });
 
     global_context->setStartServersCallback([&](const ServerType & server_type)
     {
+        std::lock_guard lock(servers_lock);
         createServers(
             config(),
             listen_hosts,

From 4fb12f8703d68400cd7d1ea71f18e645ea889c49 Mon Sep 17 00:00:00 2001
From: avogar <avogar@clickhouse.com>
Date: Mon, 18 Sep 2023 19:35:08 +0000
Subject: [PATCH 10/23] Add retries to rests
 test_async_query_sending/test_async_connect

---
 .../integration/test_hedged_requests/test.py  | 37 +++++++++++++------
 1 file changed, 26 insertions(+), 11 deletions(-)

diff --git a/tests/integration/test_hedged_requests/test.py b/tests/integration/test_hedged_requests/test.py
index 6f5d5706da4..d3f22625f76 100644
--- a/tests/integration/test_hedged_requests/test.py
+++ b/tests/integration/test_hedged_requests/test.py
@@ -133,7 +133,7 @@ def check_if_query_sending_was_suspended():
         "SELECT value FROM system.events WHERE event='SuspendSendingQueryToShard'"
     )
 
-    assert int(result) >= 1
+    return len(result) != 0 and int(result) >= 1
 
 
 def check_if_query_sending_was_not_suspended():
@@ -380,11 +380,19 @@ def test_async_connect(started_cluster):
     # Restart server to reset connection pool state
     NODES["node"].restart_clickhouse()
 
-    NODES["node"].query(
-        "SELECT hostName(), id FROM distributed_connect ORDER BY id LIMIT 1 SETTINGS prefer_localhost_replica = 0, connect_timeout_with_failover_ms=5000, async_query_sending_for_remote=1, max_threads=1, max_distributed_connections=1"
-    )
-    check_changing_replica_events(2)
-    check_if_query_sending_was_suspended()
+    attempt = 0
+    while attempt < 1000:
+        NODES["node"].query(
+            "SELECT hostName(), id FROM distributed_connect ORDER BY id LIMIT 1 SETTINGS prefer_localhost_replica = 0, connect_timeout_with_failover_ms=5000, async_query_sending_for_remote=1, max_threads=1, max_distributed_connections=1"
+        )
+
+        check_changing_replica_events(2)
+        if check_if_query_sending_was_suspended():
+            break
+
+        attempt += 1
+
+    assert attempt < 1000
 
     NODES["node"].query("DROP TABLE distributed_connect")
 
@@ -418,10 +426,17 @@ def test_async_query_sending(started_cluster):
     )
     check_if_query_sending_was_not_suspended()
 
-    NODES["node"].query(
-        "SELECT hostName(), id FROM distributed_query_sending ORDER BY id LIMIT 1 SETTINGS"
-        " prefer_localhost_replica = 0, async_query_sending_for_remote=1, max_threads = 1, max_distributed_connections=1"
-    )
-    check_if_query_sending_was_suspended()
+    attempt = 0
+    while attempt < 1000:
+        NODES["node"].query(
+            "SELECT hostName(), id FROM distributed_query_sending ORDER BY id LIMIT 1 SETTINGS"
+            " prefer_localhost_replica = 0, async_query_sending_for_remote=1, max_threads = 1, max_distributed_connections=1"
+        )
 
+        if check_if_query_sending_was_suspended():
+            break
+
+        attempt += 1
+
+    assert attempt < 1000
     NODES["node"].query("DROP TABLE distributed_query_sending")

From 92de61ca5bfe68aa7e758ee70cf6a0d94c8fb7f1 Mon Sep 17 00:00:00 2001
From: Kruglov Pavel <48961922+Avogar@users.noreply.github.com>
Date: Tue, 19 Sep 2023 13:32:49 +0200
Subject: [PATCH 11/23] Use less attempts

---
 tests/integration/test_hedged_requests/test.py | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/tests/integration/test_hedged_requests/test.py b/tests/integration/test_hedged_requests/test.py
index d3f22625f76..02ecf3c1367 100644
--- a/tests/integration/test_hedged_requests/test.py
+++ b/tests/integration/test_hedged_requests/test.py
@@ -381,7 +381,7 @@ def test_async_connect(started_cluster):
     NODES["node"].restart_clickhouse()
 
     attempt = 0
-    while attempt < 1000:
+    while attempt < 100:
         NODES["node"].query(
             "SELECT hostName(), id FROM distributed_connect ORDER BY id LIMIT 1 SETTINGS prefer_localhost_replica = 0, connect_timeout_with_failover_ms=5000, async_query_sending_for_remote=1, max_threads=1, max_distributed_connections=1"
         )
@@ -392,7 +392,7 @@ def test_async_connect(started_cluster):
 
         attempt += 1
 
-    assert attempt < 1000
+    assert attempt < 100
 
     NODES["node"].query("DROP TABLE distributed_connect")
 
@@ -427,7 +427,7 @@ def test_async_query_sending(started_cluster):
     check_if_query_sending_was_not_suspended()
 
     attempt = 0
-    while attempt < 1000:
+    while attempt < 100:
         NODES["node"].query(
             "SELECT hostName(), id FROM distributed_query_sending ORDER BY id LIMIT 1 SETTINGS"
             " prefer_localhost_replica = 0, async_query_sending_for_remote=1, max_threads = 1, max_distributed_connections=1"
@@ -438,5 +438,5 @@ def test_async_query_sending(started_cluster):
 
         attempt += 1
 
-    assert attempt < 1000
+    assert attempt < 100
     NODES["node"].query("DROP TABLE distributed_query_sending")

From ac384677cce8a59265d9a05cf968b355b769fc38 Mon Sep 17 00:00:00 2001
From: kssenii <sumarokovakseniia@mail.ru>
Date: Mon, 25 Sep 2023 13:10:25 +0200
Subject: [PATCH 12/23] Delete a test

---
 tests/queries/0_stateless/02344_describe_cache.reference | 1 -
 tests/queries/0_stateless/02344_describe_cache.sql       | 4 ----
 2 files changed, 5 deletions(-)
 delete mode 100644 tests/queries/0_stateless/02344_describe_cache.reference
 delete mode 100644 tests/queries/0_stateless/02344_describe_cache.sql

diff --git a/tests/queries/0_stateless/02344_describe_cache.reference b/tests/queries/0_stateless/02344_describe_cache.reference
deleted file mode 100644
index 5db1aa3e7f5..00000000000
--- a/tests/queries/0_stateless/02344_describe_cache.reference
+++ /dev/null
@@ -1 +0,0 @@
-134217728	10000000	33554432	4194304	1	0	0	0	/var/lib/clickhouse/filesystem_caches/s3_cache/	2	0
diff --git a/tests/queries/0_stateless/02344_describe_cache.sql b/tests/queries/0_stateless/02344_describe_cache.sql
deleted file mode 100644
index 9c5c5c10952..00000000000
--- a/tests/queries/0_stateless/02344_describe_cache.sql
+++ /dev/null
@@ -1,4 +0,0 @@
--- Tags: no-fasttest, no-parallel
-
-SYSTEM DROP FILESYSTEM CACHE 's3_cache';
-DESCRIBE FILESYSTEM CACHE 's3_cache';

From d2b787429dafd7b66a3fb21eab94e5cf8d524397 Mon Sep 17 00:00:00 2001
From: Azat Khuzhin <a3at.mail@gmail.com>
Date: Mon, 25 Sep 2023 14:23:46 +0200
Subject: [PATCH 13/23] Remove 02151_hash_table_sizes_stats_distributed (fixes
 broken CI) (#54969)

* Fix 02151_hash_table_sizes_stats_distributed (fixes broken CI)

Fixes: #54961
Signed-off-by: Azat Khuzhin <a.khuzhin@semrush.com>

* Remove 02151_hash_table_sizes_stats_distributed

Signed-off-by: Azat Khuzhin <a.khuzhin@semrush.com>

---------

Signed-off-by: Azat Khuzhin <a.khuzhin@semrush.com>
---
 ...sh_table_sizes_stats_distributed.reference | 33 -------
 ...2151_hash_table_sizes_stats_distributed.sh | 95 -------------------
 2 files changed, 128 deletions(-)
 delete mode 100644 tests/queries/0_stateless/02151_hash_table_sizes_stats_distributed.reference
 delete mode 100755 tests/queries/0_stateless/02151_hash_table_sizes_stats_distributed.sh

diff --git a/tests/queries/0_stateless/02151_hash_table_sizes_stats_distributed.reference b/tests/queries/0_stateless/02151_hash_table_sizes_stats_distributed.reference
deleted file mode 100644
index 0d10114f4ff..00000000000
--- a/tests/queries/0_stateless/02151_hash_table_sizes_stats_distributed.reference
+++ /dev/null
@@ -1,33 +0,0 @@
-1
-1
---
-1
-1
---
-1
-1
---
-1
-1
---
-1
-1
-1
-1
---
-1
-1
---
-1
-1
-1
-1
---
-1
-1
---
-1
-1
-1
-1
---
diff --git a/tests/queries/0_stateless/02151_hash_table_sizes_stats_distributed.sh b/tests/queries/0_stateless/02151_hash_table_sizes_stats_distributed.sh
deleted file mode 100755
index 77b9b2942c5..00000000000
--- a/tests/queries/0_stateless/02151_hash_table_sizes_stats_distributed.sh
+++ /dev/null
@@ -1,95 +0,0 @@
-#!/usr/bin/env bash
-# Tags: long, distributed, no-tsan, no-debug
-
-# These tests don't use `current_database = currentDatabase()` condition, because database name isn't propagated during remote queries.
-
-# shellcheck disable=SC2154
-
-CURDIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
-# shellcheck source=../shell_config.sh
-. "$CURDIR"/../shell_config.sh
-
-
-# tests rely on that all the rows are unique and max_threads divides table_size
-table_size=1000005
-max_threads=5
-
-
-prepare_table() {
-  table_name="t_hash_table_sizes_stats_$RANDOM$RANDOM"
-  $CLICKHOUSE_CLIENT -q "DROP TABLE IF EXISTS $table_name;"
-  if [ -z "$1" ]; then
-    $CLICKHOUSE_CLIENT -q "CREATE TABLE $table_name(number UInt64) Engine=MergeTree() ORDER BY tuple() SETTINGS index_granularity = 8192, index_granularity_bytes = '10Mi';"
-  else
-    $CLICKHOUSE_CLIENT -q "CREATE TABLE $table_name(number UInt64) Engine=MergeTree() ORDER BY $1 SETTINGS index_granularity = 8192, index_granularity_bytes = '10Mi';"
-  fi
-  $CLICKHOUSE_CLIENT -q "SYSTEM STOP MERGES $table_name;"
-  for ((i = 1; i <= max_threads; i++)); do
-    cnt=$((table_size / max_threads))
-    from=$(((i - 1) * cnt))
-    $CLICKHOUSE_CLIENT -q "INSERT INTO $table_name SELECT * FROM numbers($from, $cnt);"
-  done
-  $CLICKHOUSE_CLIENT -q "DROP TABLE IF EXISTS ${table_name}_d;"
-  $CLICKHOUSE_CLIENT -q "CREATE TABLE ${table_name}_d AS $table_name ENGINE = Distributed(test_cluster_two_shards, currentDatabase(), $table_name);"
-  table_name="${table_name}_d"
-}
-
-prepare_table_with_sorting_key() {
-  prepare_table "$1"
-}
-
-run_query() {
-  query_id="${CLICKHOUSE_DATABASE}_hash_table_sizes_stats_$RANDOM$RANDOM"
-  $CLICKHOUSE_CLIENT --query_id="$query_id" --multiquery -q "
-    SET max_block_size = $((table_size / 10));
-    SET merge_tree_min_rows_for_concurrent_read = 1;
-    SET max_untracked_memory = 0;
-    SET prefer_localhost_replica = 1;
-    $query"
-}
-
-check_preallocated_elements() {
-  $CLICKHOUSE_CLIENT -q "SYSTEM FLUSH LOGS"
-  # rows may be distributed in any way including "everything goes to the one particular thread"
-  min=$1
-  if [ -z "$2" ]; then
-    max=$1
-  else
-    max=$2
-  fi
-  $CLICKHOUSE_CLIENT --param_query_id="$query_id" -q "
-    SELECT COUNT(*)
-      FROM system.query_log
-     WHERE event_date >= yesterday() AND (query_id = {query_id:String} OR initial_query_id = {query_id:String})
-           AND ProfileEvents['AggregationPreallocatedElementsInHashTables'] BETWEEN $min AND $max
-  GROUP BY query_id"
-}
-
-check_convertion_to_two_level() {
-  $CLICKHOUSE_CLIENT -q "SYSTEM FLUSH LOGS"
-  # rows may be distributed in any way including "everything goes to the one particular thread"
-  $CLICKHOUSE_CLIENT --param_query_id="$query_id" -q "
-    SELECT SUM(ProfileEvents['AggregationHashTablesInitializedAsTwoLevel']) BETWEEN 1 AND $max_threads
-      FROM system.query_log
-     WHERE event_date >= yesterday() AND (query_id = {query_id:String} OR initial_query_id = {query_id:String})
-  GROUP BY query_id"
-}
-
-print_border() {
-  echo "--"
-}
-
-
-# shellcheck source=./02151_hash_table_sizes_stats.testcases
-source "$CURDIR"/02151_hash_table_sizes_stats.testcases
-
-
-test_one_thread_simple_group_by
-test_one_thread_simple_group_by_with_limit
-test_one_thread_simple_group_by_with_join_and_subquery
-test_several_threads_simple_group_by_with_limit_single_level_ht
-test_several_threads_simple_group_by_with_limit_two_level_ht
-test_several_threads_simple_group_by_with_limit_and_rollup_single_level_ht
-test_several_threads_simple_group_by_with_limit_and_rollup_two_level_ht
-test_several_threads_simple_group_by_with_limit_and_cube_single_level_ht
-test_several_threads_simple_group_by_with_limit_and_cube_two_level_ht

From 5a6d37d8e793299bf15c7cad2c366575ac5670d3 Mon Sep 17 00:00:00 2001
From: Alex Cheng <chengxin1985@gmail.com>
Date: Fri, 22 Sep 2023 19:55:44 +0800
Subject: [PATCH 14/23] fix exception message in Pipe::addTransform

---
 src/QueryPipeline/Pipe.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/QueryPipeline/Pipe.cpp b/src/QueryPipeline/Pipe.cpp
index 293d152ea65..ff842478712 100644
--- a/src/QueryPipeline/Pipe.cpp
+++ b/src/QueryPipeline/Pipe.cpp
@@ -556,7 +556,7 @@ void Pipe::addTransform(ProcessorPtr transform, InputPort * totals, InputPort *
         throw Exception(ErrorCodes::LOGICAL_ERROR, "Cannot add transform consuming totals to Pipe because Pipe does not have totals");
 
     if (extremes && !extremes_port)
-        throw Exception(ErrorCodes::LOGICAL_ERROR, "Cannot add transform consuming extremes to Pipe because it already has extremes");
+        throw Exception(ErrorCodes::LOGICAL_ERROR, "Cannot add transform consuming extremes to Pipe because Pipe does not have extremes");
 
     if (totals)
     {

From b7a3873265ae7afa68b379920c9d60cb2fbf7d82 Mon Sep 17 00:00:00 2001
From: flynn <fenglv15@mails.ucas.ac.cn>
Date: Fri, 22 Sep 2023 17:43:52 +0000
Subject: [PATCH 15/23] Add function hammingDistance

---
 src/Functions/FunctionsStringSimilarity.h     |  42 +++++--
 src/Functions/stringHammingDistance.cpp       | 106 ++++++++++++++++++
 .../02884_string_hamming_distance.reference   |  10 ++
 .../02884_string_hamming_distance.sql         |  17 +++
 4 files changed, 166 insertions(+), 9 deletions(-)
 create mode 100644 src/Functions/stringHammingDistance.cpp
 create mode 100644 tests/queries/0_stateless/02884_string_hamming_distance.reference
 create mode 100644 tests/queries/0_stateless/02884_string_hamming_distance.sql

diff --git a/src/Functions/FunctionsStringSimilarity.h b/src/Functions/FunctionsStringSimilarity.h
index a360442ea75..e148730054d 100644
--- a/src/Functions/FunctionsStringSimilarity.h
+++ b/src/Functions/FunctionsStringSimilarity.h
@@ -27,6 +27,9 @@ namespace ErrorCodes
     extern const int TOO_LARGE_STRING_SIZE;
 }
 
+template <typename T>
+concept has_max_string_size = requires { T::max_string_size; };
+
 template <typename Impl, typename Name>
 class FunctionsStringSimilarity : public IFunction
 {
@@ -68,10 +71,17 @@ public:
         {
             ResultType res{};
             const String & needle = col_needle_const->getValue<String>();
-            if (needle.size() > Impl::max_string_size)
+            if constexpr (has_max_string_size<Impl>)
             {
-                throw Exception(ErrorCodes::TOO_LARGE_STRING_SIZE, "String size of needle is too big for function {}. "
-                    "Should be at most {}", getName(), Impl::max_string_size);
+                if (needle.size() > Impl::max_string_size)
+                {
+                    throw Exception(
+                        ErrorCodes::TOO_LARGE_STRING_SIZE,
+                        "String size of needle is too big for function {}. "
+                        "Should be at most {}",
+                        getName(),
+                        Impl::max_string_size);
+                }
             }
             Impl::constantConstant(col_haystack_const->getValue<String>(), needle, res);
             return result_type->createColumnConst(col_haystack_const->size(), toField(res));
@@ -88,10 +98,17 @@ public:
         if (col_haystack_vector && col_needle_const)
         {
             const String & needle = col_needle_const->getValue<String>();
-            if (needle.size() > Impl::max_string_size)
+            if constexpr (has_max_string_size<Impl>)
             {
-                throw Exception(ErrorCodes::TOO_LARGE_STRING_SIZE, "String size of needle is too big for function {}. "
-                    "Should be at most {}", getName(), Impl::max_string_size);
+                if (needle.size() > Impl::max_string_size)
+                {
+                    throw Exception(
+                        ErrorCodes::TOO_LARGE_STRING_SIZE,
+                        "String size of needle is too big for function {}. "
+                        "Should be at most {}",
+                        getName(),
+                        Impl::max_string_size);
+                }
             }
             Impl::vectorConstant(col_haystack_vector->getChars(), col_haystack_vector->getOffsets(), needle, vec_res);
         }
@@ -107,10 +124,17 @@ public:
         else if (col_haystack_const && col_needle_vector)
         {
             const String & haystack = col_haystack_const->getValue<String>();
-            if (haystack.size() > Impl::max_string_size)
+            if constexpr (has_max_string_size<Impl>)
             {
-                throw Exception(ErrorCodes::TOO_LARGE_STRING_SIZE, "String size of haystack is too big for function {}. "
-                    "Should be at most {}", getName(), Impl::max_string_size);
+                if (haystack.size() > Impl::max_string_size)
+                {
+                    throw Exception(
+                        ErrorCodes::TOO_LARGE_STRING_SIZE,
+                        "String size of haystack is too big for function {}. "
+                        "Should be at most {}",
+                        getName(),
+                        Impl::max_string_size);
+                }
             }
             Impl::constantVector(haystack, col_needle_vector->getChars(), col_needle_vector->getOffsets(), vec_res);
         }
diff --git a/src/Functions/stringHammingDistance.cpp b/src/Functions/stringHammingDistance.cpp
new file mode 100644
index 00000000000..fd22ca96ba3
--- /dev/null
+++ b/src/Functions/stringHammingDistance.cpp
@@ -0,0 +1,106 @@
+#include <Columns/ColumnString.h>
+#include <Columns/ColumnsNumber.h>
+#include <DataTypes/DataTypeString.h>
+#include <DataTypes/DataTypesNumber.h>
+#include <Functions/FunctionFactory.h>
+#include <Functions/FunctionsStringSimilarity.h>
+
+#ifdef __SSE4_2__
+#    include <nmmintrin.h>
+#endif
+
+namespace DB
+{
+struct StringHammingDistanceImpl
+{
+    using ResultType = UInt64;
+
+    static void constantConstant(const std::string & haystack, const std::string & needle, UInt64 & res)
+    {
+        res = process(haystack.data(), haystack.size(), needle.data(), needle.size());
+    }
+
+    static void vectorVector(
+        const ColumnString::Chars & haystack_data,
+        const ColumnString::Offsets & haystack_offsets,
+        const ColumnString::Chars & needle_data,
+        const ColumnString::Offsets & needle_offsets,
+        PaddedPODArray<UInt64> & res)
+    {
+        size_t size = res.size();
+        const char * haystack = reinterpret_cast<const char *>(haystack_data.data());
+        const char * needle = reinterpret_cast<const char *>(needle_data.data());
+        for (size_t i = 0; i < size; ++i)
+        {
+            res[i] = process(
+                haystack + haystack_offsets[i - 1],
+                haystack_offsets[i] - haystack_offsets[i - 1] - 1,
+                needle + needle_offsets[i - 1],
+                needle_offsets[i] - needle_offsets[i - 1] - 1);
+        }
+    }
+
+    static void constantVector(
+        const std::string & haystack,
+        const ColumnString::Chars & needle_data,
+        const ColumnString::Offsets & needle_offsets,
+        PaddedPODArray<UInt64> & res)
+    {
+        const char * haystack_data = haystack.data();
+        size_t haystack_size = haystack.size();
+        const char * needle = reinterpret_cast<const char *>(needle_data.data());
+        size_t size = res.size();
+        for (size_t i = 0; i < size; ++i)
+        {
+            res[i] = process(haystack_data, haystack_size, needle + needle_offsets[i - 1], needle_offsets[i] - needle_offsets[i - 1] - 1);
+        }
+    }
+
+    static void vectorConstant(
+        const ColumnString::Chars & data, const ColumnString::Offsets & offsets, const std::string & needle, PaddedPODArray<UInt64> & res)
+    {
+        constantVector(needle, data, offsets, res);
+    }
+
+private:
+    static UInt64 inline process(const char * haystack, size_t haystack_size, const char * needle, size_t needle_size)
+    {
+        UInt64 res = 0;
+        const char * haystack_end = haystack + haystack_size;
+        const char * needle_end = needle + needle_size;
+
+#ifdef __SSE4_2__
+        static constexpr auto mode = _SIDD_UBYTE_OPS | _SIDD_CMP_EQUAL_EACH | _SIDD_NEGATIVE_POLARITY;
+
+        const char * haystack_end16 = haystack + haystack_size / 16 * 16;
+        const char * needle_end16 = needle + needle_size / 16 * 16;
+
+        for (; haystack < haystack_end16 && needle < needle_end16; haystack += 16, needle += 16)
+        {
+            __m128i s1 = _mm_loadu_si128(reinterpret_cast<const __m128i *>(haystack));
+            __m128i s2 = _mm_loadu_si128(reinterpret_cast<const __m128i *>(needle));
+            auto result_mask = _mm_cmpestrm(s1, 16, s2, 16, mode);
+            const __m128i mask_hi = _mm_unpackhi_epi64(result_mask, result_mask);
+            res += _mm_popcnt_u64(_mm_cvtsi128_si64(result_mask)) + _mm_popcnt_u64(_mm_cvtsi128_si64(mask_hi));
+        }
+#endif
+        for (; haystack != haystack_end && needle != needle_end; ++haystack, ++needle)
+            res += *haystack != *needle;
+
+        res = res + (haystack_end - haystack) + (needle_end - needle);
+        return res;
+    }
+};
+
+struct NameStringHammingDistance
+{
+    static constexpr auto name = "hammingDistance";
+};
+
+using FunctionStringHammingDistance = FunctionsStringSimilarity<StringHammingDistanceImpl, NameStringHammingDistance>;
+
+REGISTER_FUNCTION(StringHammingDistance)
+{
+    factory.registerFunction<FunctionStringHammingDistance>();
+}
+}
diff --git a/tests/queries/0_stateless/02884_string_hamming_distance.reference b/tests/queries/0_stateless/02884_string_hamming_distance.reference
new file mode 100644
index 00000000000..656cd356016
--- /dev/null
+++ b/tests/queries/0_stateless/02884_string_hamming_distance.reference
@@ -0,0 +1,10 @@
+0
+1
+7
+7
+3
+6
+3
+6
+6
+3
diff --git a/tests/queries/0_stateless/02884_string_hamming_distance.sql b/tests/queries/0_stateless/02884_string_hamming_distance.sql
new file mode 100644
index 00000000000..3f026d6f8d0
--- /dev/null
+++ b/tests/queries/0_stateless/02884_string_hamming_distance.sql
@@ -0,0 +1,17 @@
+select hammingDistance('abcd', 'abcd');
+drop table if exists t;
+create table t
+(
+	s1 String,
+	s2 String
+) engine = MergeTree order by s1;
+
+insert into t values ('abcdefg', 'abcdef') ('abcdefg', 'bcdefg') ('abcdefg', '');
+
+select hammingDistance(s1, s2) from t;
+
+select hammingDistance('abc', s2) from t;
+
+select hammingDistance(s2, 'def') from t;
+
+drop table t;

From 5a72de34ed26792d1a6a22ab2cb0287d99f40936 Mon Sep 17 00:00:00 2001
From: flynn <fenglv15@mails.ucas.ac.cn>
Date: Fri, 22 Sep 2023 17:48:17 +0000
Subject: [PATCH 16/23] add doc

---
 .../functions/string-search-functions.md      | 26 ++++++++++++++++++-
 1 file changed, 25 insertions(+), 1 deletion(-)

diff --git a/docs/en/sql-reference/functions/string-search-functions.md b/docs/en/sql-reference/functions/string-search-functions.md
index c10a1036677..cb4963c1091 100644
--- a/docs/en/sql-reference/functions/string-search-functions.md
+++ b/docs/en/sql-reference/functions/string-search-functions.md
@@ -680,4 +680,28 @@ Like [hasSubsequence](#hasSubsequence) but assumes `haystack` and `needle` are U
 
 ## hasSubsequenceCaseInsensitiveUTF8
 
-Like [hasSubsequenceUTF8](#hasSubsequenceUTF8) but searches case-insensitively.
\ No newline at end of file
+Like [hasSubsequenceUTF8](#hasSubsequenceUTF8) but searches case-insensitively.
+
+## hammingDistance
+
+Calculates the hamming distance between two strings.
+
+**Syntax**
+
+```sql
+hammingDistance(haystack, needle)
+```
+
+**Examples**
+
+``` sql
+SELECT hammingDistance('abc', 'ab') ;
+```
+
+Result:
+
+``` text
+┌─hammingDistance('abc', 'ab')─┐
+│                            1 │
+└──────────────────────────────┘
+```

From cbbabc4e1fa8715133a6f527c63da6c333879901 Mon Sep 17 00:00:00 2001
From: flynn <fenglv15@mails.ucas.ac.cn>
Date: Sat, 23 Sep 2023 04:11:20 +0000
Subject: [PATCH 17/23] fix

---
 .../functions/string-search-functions.md           | 14 +++++++-------
 ...HammingDistance.cpp => byteHammingDistance.cpp} | 11 ++++++-----
 2 files changed, 13 insertions(+), 12 deletions(-)
 rename src/Functions/{stringHammingDistance.cpp => byteHammingDistance.cpp} (90%)

diff --git a/docs/en/sql-reference/functions/string-search-functions.md b/docs/en/sql-reference/functions/string-search-functions.md
index cb4963c1091..c7e2bfa1cad 100644
--- a/docs/en/sql-reference/functions/string-search-functions.md
+++ b/docs/en/sql-reference/functions/string-search-functions.md
@@ -682,26 +682,26 @@ Like [hasSubsequence](#hasSubsequence) but assumes `haystack` and `needle` are U
 
 Like [hasSubsequenceUTF8](#hasSubsequenceUTF8) but searches case-insensitively.
 
-## hammingDistance
+## byteHammingDistance
 
-Calculates the hamming distance between two strings.
+Calculates the hamming distance between two byte strings.
 
 **Syntax**
 
 ```sql
-hammingDistance(haystack, needle)
+byteHammingDistance(haystack, needle)
 ```
 
 **Examples**
 
 ``` sql
-SELECT hammingDistance('abc', 'ab') ;
+SELECT byteHammingDistance('abc', 'ab') ;
 ```
 
 Result:
 
 ``` text
-┌─hammingDistance('abc', 'ab')─┐
-│                            1 │
-└──────────────────────────────┘
+┌─byteHammingDistance('abc', 'ab')─┐
+│                                1 │
+└──────────────────────────────────┘
 ```
diff --git a/src/Functions/stringHammingDistance.cpp b/src/Functions/byteHammingDistance.cpp
similarity index 90%
rename from src/Functions/stringHammingDistance.cpp
rename to src/Functions/byteHammingDistance.cpp
index fd22ca96ba3..80df4163c1c 100644
--- a/src/Functions/stringHammingDistance.cpp
+++ b/src/Functions/byteHammingDistance.cpp
@@ -11,7 +11,7 @@
 
 namespace DB
 {
-struct StringHammingDistanceImpl
+struct ByteHammingDistanceImpl
 {
     using ResultType = UInt64;
 
@@ -92,15 +92,16 @@ private:
     }
 };
 
-struct NameStringHammingDistance
+struct NameByteHammingDistance
 {
-    static constexpr auto name = "hammingDistance";
+    static constexpr auto name = "byteHammingDistance";
 };
 
-using FunctionStringHammingDistance = FunctionsStringSimilarity<StringHammingDistanceImpl, NameStringHammingDistance>;
+using FunctionByteHammingDistance = FunctionsStringSimilarity<ByteHammingDistanceImpl, NameByteHammingDistance>;
 
 REGISTER_FUNCTION(StringHammingDistance)
 {
-    factory.registerFunction<FunctionStringHammingDistance>();
+    factory.registerFunction<FunctionByteHammingDistance>(
+        FunctionDocumentation{.description = R"(Calculates the hamming distance between two bytes strings.)"});
 }
 }

From 53da7243ea362c8f3cfe211a49827d9606805709 Mon Sep 17 00:00:00 2001
From: flynn <fenglv15@mails.ucas.ac.cn>
Date: Sat, 23 Sep 2023 04:14:21 +0000
Subject: [PATCH 18/23] fix spell check

---
 utils/check-style/aspell-ignore/en/aspell-dict.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/utils/check-style/aspell-ignore/en/aspell-dict.txt b/utils/check-style/aspell-ignore/en/aspell-dict.txt
index e5a031dabe3..ef3ad7d793c 100644
--- a/utils/check-style/aspell-ignore/en/aspell-dict.txt
+++ b/utils/check-style/aspell-ignore/en/aspell-dict.txt
@@ -1178,6 +1178,7 @@ builtins
 byteSize
 bytebase
 bytesToCutForIPv
+byteHammingDistance
 cLoki
 caConfig
 cacheSessions

From c1f4d911b8de9b7b025f0d97198bfde816fea74d Mon Sep 17 00:00:00 2001
From: flynn <fenglv15@mails.ucas.ac.cn>
Date: Sat, 23 Sep 2023 04:52:31 +0000
Subject: [PATCH 19/23] update test

---
 ...ce.reference => 02884_byte_hamming_distance.reference} | 0
 ...mming_distance.sql => 02884_byte_hamming_distance.sql} | 8 ++++----
 2 files changed, 4 insertions(+), 4 deletions(-)
 rename tests/queries/0_stateless/{02884_string_hamming_distance.reference => 02884_byte_hamming_distance.reference} (100%)
 rename tests/queries/0_stateless/{02884_string_hamming_distance.sql => 02884_byte_hamming_distance.sql} (52%)

diff --git a/tests/queries/0_stateless/02884_string_hamming_distance.reference b/tests/queries/0_stateless/02884_byte_hamming_distance.reference
similarity index 100%
rename from tests/queries/0_stateless/02884_string_hamming_distance.reference
rename to tests/queries/0_stateless/02884_byte_hamming_distance.reference
diff --git a/tests/queries/0_stateless/02884_string_hamming_distance.sql b/tests/queries/0_stateless/02884_byte_hamming_distance.sql
similarity index 52%
rename from tests/queries/0_stateless/02884_string_hamming_distance.sql
rename to tests/queries/0_stateless/02884_byte_hamming_distance.sql
index 3f026d6f8d0..62d4348449c 100644
--- a/tests/queries/0_stateless/02884_string_hamming_distance.sql
+++ b/tests/queries/0_stateless/02884_byte_hamming_distance.sql
@@ -1,4 +1,4 @@
-select hammingDistance('abcd', 'abcd');
+select byteHammingDistance('abcd', 'abcd');
 drop table if exists t;
 create table t
 (
@@ -8,10 +8,10 @@ create table t
 
 insert into t values ('abcdefg', 'abcdef') ('abcdefg', 'bcdefg') ('abcdefg', '');
 
-select hammingDistance(s1, s2) from t;
+select byteHammingDistance(s1, s2) from t;
 
-select hammingDistance('abc', s2) from t;
+select byteHammingDistance('abc', s2) from t;
 
-select hammingDistance(s2, 'def') from t;
+select byteHammingDistance(s2, 'def') from t;
 
 drop table t;

From 03b088a5710b6e458f2460bb067da8c43a5ca0b4 Mon Sep 17 00:00:00 2001
From: flynn <fenglv15@mails.ucas.ac.cn>
Date: Sat, 23 Sep 2023 17:17:35 +0000
Subject: [PATCH 20/23] add more functions

---
 .../functions/string-search-functions.md      |  53 +++++
 src/Functions/FunctionsStringDistance.cpp     | 218 ++++++++++++++++++
 src/Functions/byteHammingDistance.cpp         | 107 ---------
 .../02884_byte_hamming_distance.reference     |  10 -
 .../02884_string_distance_function.reference  |  37 +++
 ...sql => 02884_string_distance_function.sql} |  15 +-
 .../aspell-ignore/en/aspell-dict.txt          |   3 +
 7 files changed, 322 insertions(+), 121 deletions(-)
 create mode 100644 src/Functions/FunctionsStringDistance.cpp
 delete mode 100644 src/Functions/byteHammingDistance.cpp
 delete mode 100644 tests/queries/0_stateless/02884_byte_hamming_distance.reference
 create mode 100644 tests/queries/0_stateless/02884_string_distance_function.reference
 rename tests/queries/0_stateless/{02884_byte_hamming_distance.sql => 02884_string_distance_function.sql} (50%)

diff --git a/docs/en/sql-reference/functions/string-search-functions.md b/docs/en/sql-reference/functions/string-search-functions.md
index c7e2bfa1cad..e75c4fa8252 100644
--- a/docs/en/sql-reference/functions/string-search-functions.md
+++ b/docs/en/sql-reference/functions/string-search-functions.md
@@ -705,3 +705,56 @@ Result:
 │                                1 │
 └──────────────────────────────────┘
 ```
+
+- Alias: mismatches
+
+## byteJaccardIndex
+
+Calculates the jaccard similarity index between two byte strings.
+
+**Syntax**
+
+```sql
+byteJaccardIndex(haystack, needle)
+```
+
+**Examples**
+
+``` sql
+SELECT byteJaccardIndex('clickhouse', 'mouse');
+```
+
+Result:
+
+``` text
+┌─byteJaccardIndex('clickhouse', 'mouse')─┐
+│                                     0.4 │
+└─────────────────────────────────────────┘
+```
+
+## byteEditDistance
+
+Calcultes the edit distance between two byte strings.
+
+**Syntax**
+
+```sql
+byteEidtDistance(haystack, needle)
+```
+
+**Examples**
+
+``` sql
+SELECT byteEditDistance('clickhouse', 'mouse');
+```
+
+Result:
+
+``` text
+┌─byteEditDistance('clickhouse', 'mouse')─┐
+│                                       6 │
+└─────────────────────────────────────────┘
+```
+
+- Alias: byteLevenshteinDistance
+
diff --git a/src/Functions/FunctionsStringDistance.cpp b/src/Functions/FunctionsStringDistance.cpp
new file mode 100644
index 00000000000..73ff379aae0
--- /dev/null
+++ b/src/Functions/FunctionsStringDistance.cpp
@@ -0,0 +1,218 @@
+#include <Columns/ColumnString.h>
+#include <Columns/ColumnsNumber.h>
+#include <DataTypes/DataTypeString.h>
+#include <DataTypes/DataTypesNumber.h>
+#include <Functions/FunctionFactory.h>
+#include <Functions/FunctionsStringSimilarity.h>
+#include <Common/PODArray.h>
+
+#ifdef __SSE4_2__
+#    include <nmmintrin.h>
+#endif
+
+namespace DB
+{
+namespace ErrorCodes
+{
+extern const int TOO_LARGE_STRING_SIZE;
+}
+
+template <typename Op>
+struct FunctionDistanceImpl
+{
+    using ResultType = typename Op::ResultType;
+
+    static void constantConstant(const std::string & haystack, const std::string & needle, ResultType & res)
+    {
+        res = Op::process(haystack.data(), haystack.size(), needle.data(), needle.size());
+    }
+
+    static void vectorVector(
+        const ColumnString::Chars & haystack_data,
+        const ColumnString::Offsets & haystack_offsets,
+        const ColumnString::Chars & needle_data,
+        const ColumnString::Offsets & needle_offsets,
+        PaddedPODArray<ResultType> & res)
+    {
+        size_t size = res.size();
+        const char * haystack = reinterpret_cast<const char *>(haystack_data.data());
+        const char * needle = reinterpret_cast<const char *>(needle_data.data());
+        for (size_t i = 0; i < size; ++i)
+        {
+            res[i] = Op::process(
+                haystack + haystack_offsets[i - 1],
+                haystack_offsets[i] - haystack_offsets[i - 1] - 1,
+                needle + needle_offsets[i - 1],
+                needle_offsets[i] - needle_offsets[i - 1] - 1);
+        }
+    }
+
+    static void constantVector(
+        const std::string & haystack,
+        const ColumnString::Chars & needle_data,
+        const ColumnString::Offsets & needle_offsets,
+        PaddedPODArray<ResultType> & res)
+    {
+        const char * haystack_data = haystack.data();
+        size_t haystack_size = haystack.size();
+        const char * needle = reinterpret_cast<const char *>(needle_data.data());
+        size_t size = res.size();
+        for (size_t i = 0; i < size; ++i)
+        {
+            res[i]
+                = Op::process(haystack_data, haystack_size, needle + needle_offsets[i - 1], needle_offsets[i] - needle_offsets[i - 1] - 1);
+        }
+    }
+
+    static void vectorConstant(
+        const ColumnString::Chars & data,
+        const ColumnString::Offsets & offsets,
+        const std::string & needle,
+        PaddedPODArray<ResultType> & res)
+    {
+        constantVector(needle, data, offsets, res);
+    }
+
+};
+
+struct ByteHammingDistanceImpl
+{
+    using ResultType = UInt64;
+    static ResultType inline process(
+        const char * __restrict haystack, size_t haystack_size, const char * __restrict needle, size_t needle_size)
+    {
+        UInt64 res = 0;
+        const char * haystack_end = haystack + haystack_size;
+        const char * needle_end = needle + needle_size;
+
+#ifdef __SSE4_2__
+        static constexpr auto mode = _SIDD_UBYTE_OPS | _SIDD_CMP_EQUAL_EACH | _SIDD_NEGATIVE_POLARITY;
+
+        const char * haystack_end16 = haystack + haystack_size / 16 * 16;
+        const char * needle_end16 = needle + needle_size / 16 * 16;
+
+        for (; haystack < haystack_end16 && needle < needle_end16; haystack += 16, needle += 16)
+        {
+            __m128i s1 = _mm_loadu_si128(reinterpret_cast<const __m128i *>(haystack));
+            __m128i s2 = _mm_loadu_si128(reinterpret_cast<const __m128i *>(needle));
+            auto result_mask = _mm_cmpestrm(s1, 16, s2, 16, mode);
+            const __m128i mask_hi = _mm_unpackhi_epi64(result_mask, result_mask);
+            res += _mm_popcnt_u64(_mm_cvtsi128_si64(result_mask)) + _mm_popcnt_u64(_mm_cvtsi128_si64(mask_hi));
+        }
+#endif
+        for (; haystack != haystack_end && needle != needle_end; ++haystack, ++needle)
+            res += *haystack != *needle;
+
+        res = res + (haystack_end - haystack) + (needle_end - needle);
+        return res;
+    }
+};
+
+struct ByteJaccardIndexImpl
+{
+    using ResultType = Float64;
+    static ResultType inline process(
+        const char * __restrict haystack, size_t haystack_size, const char * __restrict needle, size_t needle_size)
+    {
+        if (haystack_size == 0 || needle_size == 0)
+            return 0;
+
+        std::unordered_set<char> haystack_set(haystack, haystack + haystack_size);
+        std::unordered_set<char> needle_set(needle, needle + needle_size);
+
+        size_t intersect = 0;
+        for (auto elem : haystack_set)
+        {
+            intersect += needle_set.contains(elem);
+        }
+        return static_cast<Float64>(intersect) / (haystack_set.size() + needle_set.size() - intersect);
+    }
+};
+
+struct ByteEditDistanceImpl
+{
+    using ResultType = UInt64;
+    static constexpr size_t max_string_size = 1u << 16;
+
+    static ResultType inline process(
+        const char * __restrict haystack, size_t haystack_size, const char * __restrict needle, size_t needle_size)
+    {
+        if (haystack_size == 0 || needle_size == 0)
+            return haystack_size + needle_size;
+
+        /// Safety threshold against DoS, since we use two array to calculate the distance.
+        if (haystack_size > max_string_size || needle_size > max_string_size)
+            throw Exception(
+                ErrorCodes::TOO_LARGE_STRING_SIZE,
+                "The string size is too big for function byteEditDistance. "
+                "Should be at most {}",
+                max_string_size);
+
+        PaddedPODArray<ResultType> distances0(haystack_size + 1, 0);
+        PaddedPODArray<ResultType> distances1(haystack_size + 1, 0);
+
+        ResultType substitution = 0;
+        ResultType insertion = 0;
+        ResultType deletion = 0;
+
+        for (size_t i = 0; i <= haystack_size; ++i)
+            distances0[i] = i;
+
+        for (size_t pos_needle = 0; pos_needle < needle_size; ++pos_needle)
+        {
+            distances1[0] = pos_needle + 1;
+
+            for (size_t pos_haystack = 0; pos_haystack < haystack_size; pos_haystack++)
+            {
+                deletion = distances0[pos_haystack + 1] + 1;
+                insertion = distances1[pos_haystack] + 1;
+                substitution = distances0[pos_haystack];
+
+                if (*(needle + pos_needle) != *(haystack + pos_haystack))
+                    substitution += 1;
+
+                distances1[pos_haystack + 1] = std::min(deletion, std::min(substitution, insertion));
+            }
+            distances0.swap(distances1);
+        }
+
+        return distances0[haystack_size];
+    }
+};
+
+struct NameByteHammingDistance
+{
+    static constexpr auto name = "byteHammingDistance";
+};
+
+struct NameByteJaccardIndex
+{
+    static constexpr auto name = "byteJaccardIndex";
+};
+
+struct NameByteEditDistance
+{
+    static constexpr auto name = "byteEditDistance";
+};
+
+using FunctionByteHammingDistance
+    = FunctionsStringSimilarity<FunctionDistanceImpl<ByteHammingDistanceImpl>, NameByteHammingDistance>;
+
+using FunctionByteJaccardIndex = FunctionsStringSimilarity<FunctionDistanceImpl<ByteJaccardIndexImpl>, NameByteJaccardIndex>;
+
+using FunctionByteEditDistance = FunctionsStringSimilarity<FunctionDistanceImpl<ByteEditDistanceImpl>, NameByteEditDistance>;
+
+REGISTER_FUNCTION(StringHammingDistance)
+{
+    factory.registerFunction<FunctionByteHammingDistance>(
+        FunctionDocumentation{.description = R"(Calculates the hamming distance between two bytes strings.)"});
+    factory.registerAlias("mismatches", NameByteHammingDistance::name);
+
+    factory.registerFunction<FunctionByteJaccardIndex>(
+        FunctionDocumentation{.description = R"(Calculates the jaccard similarity index between two bytes strings.)"});
+
+    factory.registerFunction<FunctionByteEditDistance>(
+        FunctionDocumentation{.description = R"(Calculates the edit distance between two bytes strings.)"});
+    factory.registerAlias("byteLevenshteinDistance", NameByteEditDistance::name);
+}
+}
diff --git a/src/Functions/byteHammingDistance.cpp b/src/Functions/byteHammingDistance.cpp
deleted file mode 100644
index 80df4163c1c..00000000000
--- a/src/Functions/byteHammingDistance.cpp
+++ /dev/null
@@ -1,107 +0,0 @@
-#include <Columns/ColumnString.h>
-#include <Columns/ColumnsNumber.h>
-#include <DataTypes/DataTypeString.h>
-#include <DataTypes/DataTypesNumber.h>
-#include <Functions/FunctionFactory.h>
-#include <Functions/FunctionsStringSimilarity.h>
-
-#ifdef __SSE4_2__
-#    include <nmmintrin.h>
-#endif
-
-namespace DB
-{
-struct ByteHammingDistanceImpl
-{
-    using ResultType = UInt64;
-
-    static void constantConstant(const std::string & haystack, const std::string & needle, UInt64 & res)
-    {
-        res = process(haystack.data(), haystack.size(), needle.data(), needle.size());
-    }
-
-    static void vectorVector(
-        const ColumnString::Chars & haystack_data,
-        const ColumnString::Offsets & haystack_offsets,
-        const ColumnString::Chars & needle_data,
-        const ColumnString::Offsets & needle_offsets,
-        PaddedPODArray<UInt64> & res)
-    {
-        size_t size = res.size();
-        const char * haystack = reinterpret_cast<const char *>(haystack_data.data());
-        const char * needle = reinterpret_cast<const char *>(needle_data.data());
-        for (size_t i = 0; i < size; ++i)
-        {
-            res[i] = process(
-                haystack + haystack_offsets[i - 1],
-                haystack_offsets[i] - haystack_offsets[i - 1] - 1,
-                needle + needle_offsets[i - 1],
-                needle_offsets[i] - needle_offsets[i - 1] - 1);
-        }
-    }
-
-    static void constantVector(
-        const std::string & haystack,
-        const ColumnString::Chars & needle_data,
-        const ColumnString::Offsets & needle_offsets,
-        PaddedPODArray<UInt64> & res)
-    {
-        const char * haystack_data = haystack.data();
-        size_t haystack_size = haystack.size();
-        const char * needle = reinterpret_cast<const char *>(needle_data.data());
-        size_t size = res.size();
-        for (size_t i = 0; i < size; ++i)
-        {
-            res[i] = process(haystack_data, haystack_size, needle + needle_offsets[i - 1], needle_offsets[i] - needle_offsets[i - 1] - 1);
-        }
-    }
-
-    static void vectorConstant(
-        const ColumnString::Chars & data, const ColumnString::Offsets & offsets, const std::string & needle, PaddedPODArray<UInt64> & res)
-    {
-        constantVector(needle, data, offsets, res);
-    }
-
-private:
-    static UInt64 inline process(const char * haystack, size_t haystack_size, const char * needle, size_t needle_size)
-    {
-        UInt64 res = 0;
-        const char * haystack_end = haystack + haystack_size;
-        const char * needle_end = needle + needle_size;
-
-#ifdef __SSE4_2__
-        static constexpr auto mode = _SIDD_UBYTE_OPS | _SIDD_CMP_EQUAL_EACH | _SIDD_NEGATIVE_POLARITY;
-
-        const char * haystack_end16 = haystack + haystack_size / 16 * 16;
-        const char * needle_end16 = needle + needle_size / 16 * 16;
-
-        for (; haystack < haystack_end16 && needle < needle_end16; haystack += 16, needle += 16)
-        {
-            __m128i s1 = _mm_loadu_si128(reinterpret_cast<const __m128i *>(haystack));
-            __m128i s2 = _mm_loadu_si128(reinterpret_cast<const __m128i *>(needle));
-            auto result_mask = _mm_cmpestrm(s1, 16, s2, 16, mode);
-            const __m128i mask_hi = _mm_unpackhi_epi64(result_mask, result_mask);
-            res += _mm_popcnt_u64(_mm_cvtsi128_si64(result_mask)) + _mm_popcnt_u64(_mm_cvtsi128_si64(mask_hi));
-        }
-#endif
-        for (; haystack != haystack_end && needle != needle_end; ++haystack, ++needle)
-            res += *haystack != *needle;
-
-        res = res + (haystack_end - haystack) + (needle_end - needle);
-        return res;
-    }
-};
-
-struct NameByteHammingDistance
-{
-    static constexpr auto name = "byteHammingDistance";
-};
-
-using FunctionByteHammingDistance = FunctionsStringSimilarity<ByteHammingDistanceImpl, NameByteHammingDistance>;
-
-REGISTER_FUNCTION(StringHammingDistance)
-{
-    factory.registerFunction<FunctionByteHammingDistance>(
-        FunctionDocumentation{.description = R"(Calculates the hamming distance between two bytes strings.)"});
-}
-}
diff --git a/tests/queries/0_stateless/02884_byte_hamming_distance.reference b/tests/queries/0_stateless/02884_byte_hamming_distance.reference
deleted file mode 100644
index 656cd356016..00000000000
--- a/tests/queries/0_stateless/02884_byte_hamming_distance.reference
+++ /dev/null
@@ -1,10 +0,0 @@
-0
-1
-7
-7
-3
-6
-3
-6
-6
-3
diff --git a/tests/queries/0_stateless/02884_string_distance_function.reference b/tests/queries/0_stateless/02884_string_distance_function.reference
new file mode 100644
index 00000000000..d50ffa0a48e
--- /dev/null
+++ b/tests/queries/0_stateless/02884_string_distance_function.reference
@@ -0,0 +1,37 @@
+0
+1
+7
+7
+10
+3
+6
+3
+10
+6
+6
+3
+10
+1
+7
+7
+10
+3
+6
+3
+10
+6
+6
+3
+10
+0.8571428571428571
+0.8571428571428571
+0
+0.4
+1
+1
+7
+6
+1
+1
+7
+6
diff --git a/tests/queries/0_stateless/02884_byte_hamming_distance.sql b/tests/queries/0_stateless/02884_string_distance_function.sql
similarity index 50%
rename from tests/queries/0_stateless/02884_byte_hamming_distance.sql
rename to tests/queries/0_stateless/02884_string_distance_function.sql
index 62d4348449c..bab22f24bf2 100644
--- a/tests/queries/0_stateless/02884_byte_hamming_distance.sql
+++ b/tests/queries/0_stateless/02884_string_distance_function.sql
@@ -6,12 +6,19 @@ create table t
 	s2 String
 ) engine = MergeTree order by s1;
 
-insert into t values ('abcdefg', 'abcdef') ('abcdefg', 'bcdefg') ('abcdefg', '');
-
+insert into t values ('abcdefg', 'abcdef') ('abcdefg', 'bcdefg') ('abcdefg', '') ('mouse', 'clickhouse');
 select byteHammingDistance(s1, s2) from t;
-
 select byteHammingDistance('abc', s2) from t;
-
 select byteHammingDistance(s2, 'def') from t;
 
+select mismatches(s1, s2) from t;
+select mismatches('abc', s2) from t;
+select mismatches(s2, 'def') from t;
+
+select byteJaccardIndex(s1, s2) from t;
+select byteEditDistance(s1, s2) from t;
+select byteLevenshteinDistance(s1, s2) from t;
+
+SELECT byteEditDistance(randomString(power(2, 17)), 'abc'); -- { serverError 131 }
+
 drop table t;
diff --git a/utils/check-style/aspell-ignore/en/aspell-dict.txt b/utils/check-style/aspell-ignore/en/aspell-dict.txt
index ef3ad7d793c..560b9130e10 100644
--- a/utils/check-style/aspell-ignore/en/aspell-dict.txt
+++ b/utils/check-style/aspell-ignore/en/aspell-dict.txt
@@ -1178,7 +1178,10 @@ builtins
 byteSize
 bytebase
 bytesToCutForIPv
+byteEditDistance
 byteHammingDistance
+byteJaccardIndex
+byteLevenshteinDistance
 cLoki
 caConfig
 cacheSessions

From 9b40ca9d5fe7a8ab2d47f10ea4d66c55ec24e35b Mon Sep 17 00:00:00 2001
From: flynn <fenglv15@mails.ucas.ac.cn>
Date: Sat, 23 Sep 2023 17:50:02 +0000
Subject: [PATCH 21/23] fix spell

---
 docs/en/sql-reference/functions/string-search-functions.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/en/sql-reference/functions/string-search-functions.md b/docs/en/sql-reference/functions/string-search-functions.md
index e75c4fa8252..8a2e257ed34 100644
--- a/docs/en/sql-reference/functions/string-search-functions.md
+++ b/docs/en/sql-reference/functions/string-search-functions.md
@@ -734,7 +734,7 @@ Result:
 
 ## byteEditDistance
 
-Calcultes the edit distance between two byte strings.
+Calculates the edit distance between two byte strings.
 
 **Syntax**
 

From 601f904275834f6750638142083c4d9e531a4348 Mon Sep 17 00:00:00 2001
From: avogar <avogar@clickhouse.com>
Date: Wed, 20 Sep 2023 16:00:28 +0000
Subject: [PATCH 22/23] Move obsolete format settings to separate section

---
 src/Core/Settings.cpp                    |  2 +-
 src/Core/Settings.h                      | 26 ++++++++++++++++--------
 src/Storages/FileLog/FileLogSettings.h   |  2 +-
 src/Storages/Hive/HiveSettings.h         |  2 +-
 src/Storages/Kafka/KafkaSettings.h       |  2 +-
 src/Storages/NATS/NATSSettings.h         |  2 +-
 src/Storages/RabbitMQ/RabbitMQSettings.h |  2 +-
 src/Storages/S3Queue/S3QueueSettings.h   |  2 +-
 src/Storages/SetSettings.h               |  2 +-
 9 files changed, 25 insertions(+), 17 deletions(-)

diff --git a/src/Core/Settings.cpp b/src/Core/Settings.cpp
index ed0868eaa4d..33db7660abd 100644
--- a/src/Core/Settings.cpp
+++ b/src/Core/Settings.cpp
@@ -158,6 +158,6 @@ void Settings::applyCompatibilitySetting(const String & compatibility_value)
     }
 }
 
-IMPLEMENT_SETTINGS_TRAITS(FormatFactorySettingsTraits, FORMAT_FACTORY_SETTINGS)
+IMPLEMENT_SETTINGS_TRAITS(FormatFactorySettingsTraits, LIST_OF_ALL_FORMAT_SETTINGS)
 
 }
diff --git a/src/Core/Settings.h b/src/Core/Settings.h
index f2b55fbcd0b..8338e5c7d59 100644
--- a/src/Core/Settings.h
+++ b/src/Core/Settings.h
@@ -806,7 +806,7 @@ class IColumn;
     M(Bool, create_index_ignore_unique, false, "Ignore UNIQUE keyword in CREATE UNIQUE INDEX. Made for SQL compatibility tests.", 0)                                                                                                  \
 
 // End of COMMON_SETTINGS
-    // Please add settings related to formats into the FORMAT_FACTORY_SETTINGS and move obsolete settings to OBSOLETE_SETTINGS.
+    // Please add settings related to formats into the FORMAT_FACTORY_SETTINGS, move obsolete settings to OBSOLETE_SETTINGS and obsolete format settings to OBSOLETE_FORMAT_SETTINGS.
 
 #define MAKE_OBSOLETE(M, TYPE, NAME, DEFAULT) \
     M(TYPE, NAME, DEFAULT, "Obsolete setting, does nothing.", BaseSettingsHelpers::Flags::OBSOLETE)
@@ -859,9 +859,6 @@ class IColumn;
     MAKE_OBSOLETE(M, Seconds, drain_timeout, 3) \
     MAKE_OBSOLETE(M, UInt64, backup_threads, 16) \
     MAKE_OBSOLETE(M, UInt64, restore_threads, 16) \
-    MAKE_OBSOLETE(M, Bool, input_format_arrow_import_nested, false) \
-    MAKE_OBSOLETE(M, Bool, input_format_parquet_import_nested, false) \
-    MAKE_OBSOLETE(M, Bool, input_format_orc_import_nested, false) \
     MAKE_OBSOLETE(M, Bool, optimize_duplicate_order_by_and_distinct, false) \
 
     /** The section above is for obsolete settings. Do not add anything there. */
@@ -1068,10 +1065,17 @@ class IColumn;
 // End of FORMAT_FACTORY_SETTINGS
 // Please add settings non-related to formats into the COMMON_SETTINGS above.
 
-#define LIST_OF_SETTINGS(M, ALIAS)    \
-    COMMON_SETTINGS(M, ALIAS)         \
-    OBSOLETE_SETTINGS(M, ALIAS)       \
-    FORMAT_FACTORY_SETTINGS(M, ALIAS)
+#define OBSOLETE_FORMAT_SETTINGS(M, ALIAS) \
+    /** Obsolete format settings that do nothing but left for compatibility reasons. Remove each one after half a year of obsolescence. */ \
+    MAKE_OBSOLETE(M, Bool, input_format_arrow_import_nested, false) \
+    MAKE_OBSOLETE(M, Bool, input_format_parquet_import_nested, false) \
+    MAKE_OBSOLETE(M, Bool, input_format_orc_import_nested, false) \
+
+#define LIST_OF_SETTINGS(M, ALIAS)     \
+    COMMON_SETTINGS(M, ALIAS)          \
+    OBSOLETE_SETTINGS(M, ALIAS)        \
+    FORMAT_FACTORY_SETTINGS(M, ALIAS)  \
+    OBSOLETE_FORMAT_SETTINGS(M, ALIAS) \
 
 DECLARE_SETTINGS_TRAITS_ALLOW_CUSTOM_SETTINGS(SettingsTraits, LIST_OF_SETTINGS)
 
@@ -1110,10 +1114,14 @@ private:
     std::unordered_set<std::string_view> settings_changed_by_compatibility_setting;
 };
 
+#define LIST_OF_ALL_FORMAT_SETTINGS(M, ALIAS) \
+    FORMAT_FACTORY_SETTINGS(M, ALIAS)         \
+    OBSOLETE_FORMAT_SETTINGS(M, ALIAS)        \
+
 /*
  * User-specified file format settings for File and URL engines.
  */
-DECLARE_SETTINGS_TRAITS(FormatFactorySettingsTraits, FORMAT_FACTORY_SETTINGS)
+DECLARE_SETTINGS_TRAITS(FormatFactorySettingsTraits, LIST_OF_ALL_FORMAT_SETTINGS)
 
 struct FormatFactorySettings : public BaseSettings<FormatFactorySettingsTraits>
 {
diff --git a/src/Storages/FileLog/FileLogSettings.h b/src/Storages/FileLog/FileLogSettings.h
index 00c774dba08..4f3157424db 100644
--- a/src/Storages/FileLog/FileLogSettings.h
+++ b/src/Storages/FileLog/FileLogSettings.h
@@ -21,7 +21,7 @@ class ASTStorage;
 
 #define LIST_OF_FILELOG_SETTINGS(M, ALIAS) \
     FILELOG_RELATED_SETTINGS(M, ALIAS) \
-    FORMAT_FACTORY_SETTINGS(M, ALIAS)
+    LIST_OF_ALL_FORMAT_SETTINGS(M, ALIAS)
 
 DECLARE_SETTINGS_TRAITS(FileLogSettingsTraits, LIST_OF_FILELOG_SETTINGS)
 
diff --git a/src/Storages/Hive/HiveSettings.h b/src/Storages/Hive/HiveSettings.h
index aaaa3306cf7..cbef19b3fa7 100644
--- a/src/Storages/Hive/HiveSettings.h
+++ b/src/Storages/Hive/HiveSettings.h
@@ -20,7 +20,7 @@ class ASTStorage;
 
 #define LIST_OF_HIVE_SETTINGS(M, ALIAS) \
     HIVE_RELATED_SETTINGS(M, ALIAS) \
-    FORMAT_FACTORY_SETTINGS(M, ALIAS)
+    LIST_OF_ALL_FORMAT_SETTINGS(M, ALIAS)
 
 DECLARE_SETTINGS_TRAITS(HiveSettingsTraits, LIST_OF_HIVE_SETTINGS)
 
diff --git a/src/Storages/Kafka/KafkaSettings.h b/src/Storages/Kafka/KafkaSettings.h
index 03c415b80e1..cfe9f16c019 100644
--- a/src/Storages/Kafka/KafkaSettings.h
+++ b/src/Storages/Kafka/KafkaSettings.h
@@ -39,7 +39,7 @@ class ASTStorage;
 
 #define LIST_OF_KAFKA_SETTINGS(M, ALIAS) \
     KAFKA_RELATED_SETTINGS(M, ALIAS) \
-    FORMAT_FACTORY_SETTINGS(M, ALIAS)
+    LIST_OF_ALL_FORMAT_SETTINGS(M, ALIAS)
 
 DECLARE_SETTINGS_TRAITS(KafkaSettingsTraits, LIST_OF_KAFKA_SETTINGS)
 
diff --git a/src/Storages/NATS/NATSSettings.h b/src/Storages/NATS/NATSSettings.h
index e82f351dd42..2482f811e50 100644
--- a/src/Storages/NATS/NATSSettings.h
+++ b/src/Storages/NATS/NATSSettings.h
@@ -30,7 +30,7 @@ class ASTStorage;
 
 #define LIST_OF_NATS_SETTINGS(M, ALIAS) \
     NATS_RELATED_SETTINGS(M, ALIAS) \
-    FORMAT_FACTORY_SETTINGS(M, ALIAS)
+    LIST_OF_ALL_FORMAT_SETTINGS(M, ALIAS)
 
 DECLARE_SETTINGS_TRAITS(NATSSettingsTraits, LIST_OF_NATS_SETTINGS)
 
diff --git a/src/Storages/RabbitMQ/RabbitMQSettings.h b/src/Storages/RabbitMQ/RabbitMQSettings.h
index 58d80c6ec9d..78cc8bf4df1 100644
--- a/src/Storages/RabbitMQ/RabbitMQSettings.h
+++ b/src/Storages/RabbitMQ/RabbitMQSettings.h
@@ -38,7 +38,7 @@ namespace DB
 
 #define LIST_OF_RABBITMQ_SETTINGS(M, ALIAS) \
     RABBITMQ_RELATED_SETTINGS(M, ALIAS) \
-    FORMAT_FACTORY_SETTINGS(M, ALIAS)
+    LIST_OF_ALL_FORMAT_SETTINGS(M, ALIAS)
 
 DECLARE_SETTINGS_TRAITS(RabbitMQSettingsTraits, LIST_OF_RABBITMQ_SETTINGS)
 
diff --git a/src/Storages/S3Queue/S3QueueSettings.h b/src/Storages/S3Queue/S3QueueSettings.h
index 75defc4a57f..328980f46d8 100644
--- a/src/Storages/S3Queue/S3QueueSettings.h
+++ b/src/Storages/S3Queue/S3QueueSettings.h
@@ -33,7 +33,7 @@ class ASTStorage;
 
 #define LIST_OF_S3QUEUE_SETTINGS(M, ALIAS) \
     S3QUEUE_RELATED_SETTINGS(M, ALIAS) \
-    FORMAT_FACTORY_SETTINGS(M, ALIAS)
+    LIST_OF_ALL_FORMAT_SETTINGS(M, ALIAS)
 
 DECLARE_SETTINGS_TRAITS(S3QueueSettingsTraits, LIST_OF_S3QUEUE_SETTINGS)
 
diff --git a/src/Storages/SetSettings.h b/src/Storages/SetSettings.h
index cc1cc642f91..98c1f3d97f5 100644
--- a/src/Storages/SetSettings.h
+++ b/src/Storages/SetSettings.h
@@ -15,7 +15,7 @@ class ASTStorage;
 
 #define LIST_OF_SET_SETTINGS(M, ALIAS) \
     SET_RELATED_SETTINGS(M, ALIAS) \
-    FORMAT_FACTORY_SETTINGS(M, ALIAS)
+    LIST_OF_ALL_FORMAT_SETTINGS(M, ALIAS)
 
 DECLARE_SETTINGS_TRAITS(setSettingsTraits, LIST_OF_SET_SETTINGS)
 

From 5b4033e829d5e5d56b9e70e40d41617513cbb064 Mon Sep 17 00:00:00 2001
From: Tyler Hannan <tyler@clickhouse.com>
Date: Mon, 25 Sep 2023 17:11:20 +0200
Subject: [PATCH 23/23] Update README.md

Updating README
---
 README.md | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index 6d253342a15..6736f5c67f3 100644
--- a/README.md
+++ b/README.md
@@ -22,9 +22,11 @@ curl https://clickhouse.com/ | sh
 
 ## Upcoming Events
 
-* [**v23.8 Community Call**](https://clickhouse.com/company/events/v23-8-community-release-call?utm_source=github&utm_medium=social&utm_campaign=release-webinar-2023-08) - Aug 31 - 23.8 is rapidly approaching. Original creator, co-founder, and CTO of ClickHouse Alexey Milovidov will walk us through the highlights of the release.
-* [**ClickHouse & AI - A Meetup in San Francisco**](https://www.meetup.com/clickhouse-silicon-valley-meetup-group/events/294472987) - Aug 8
-* [**ClickHouse Meetup in Paris**](https://www.meetup.com/clickhouse-france-user-group/events/294283460) - Sep 12
+* [**v23.9 Community Call**]([https://clickhouse.com/company/events/v23-8-community-release-call](https://clickhouse.com/company/events/v23-9-community-release-call)?utm_source=github&utm_medium=social&utm_campaign=release-webinar-2023-08) - Sep 28 - 23.9 is rapidly approaching. Original creator, co-founder, and CTO of ClickHouse Alexey Milovidov will walk us through the highlights of the release.
+* [**ClickHouse Meetup in Amsterdam**](https://www.meetup.com/clickhouse-netherlands-user-group/events/296334590/)) - Oct 31
+* [**ClickHouse Meetup in Beijing**](https://www.meetup.com/clickhouse-beijing-user-group/events/296334856/) - Nov 4
+* [**ClickHouse Meetup in San Francisco**](https://www.meetup.com/clickhouse-silicon-valley-meetup-group/events/296334923/) - Nov 14
+* [**ClickHouse Meetup in Singapore**](https://www.meetup.com/clickhouse-singapore-meetup-group/events/296334976/) - Nov 15
 
 Also, keep an eye out for upcoming meetups around the world. Somewhere else you want us to be? Please feel free to reach out to tyler <at> clickhouse <dot> com.