Merge branch 'master' of github.com:ClickHouse/ClickHouse into keen-wolf-filefuncwithreadbuf

docker/server/README.md

@@ -113,10 +113,10 @@ $ docker run --rm -e CLICKHOUSE_UID=0 -e CLICKHOUSE_GID=0 --name clickhouse-serv
 
 ### How to create default database and user on starting
 
-Sometimes you may want to create user (user named `default` is used by default) and database on image starting. You can do it using environment variables `CLICKHOUSE_DB`, `CLICKHOUSE_USER` and `CLICKHOUSE_PASSWORD`:
+Sometimes you may want to create user (user named `default` is used by default) and database on image starting. You can do it using environment variables `CLICKHOUSE_DB`, `CLICKHOUSE_USER`, `CLICKHOUSE_DEFAULT_ACCESS_MANAGEMENT` and `CLICKHOUSE_PASSWORD`:
 
 ```
-$ docker run --rm -e CLICKHOUSE_DB=my_database -e CLICKHOUSE_USER=username -e CLICKHOUSE_PASSWORD=password -p 9000:9000/tcp yandex/clickhouse-server
+$ docker run --rm -e CLICKHOUSE_DB=my_database -e CLICKHOUSE_USER=username -e CLICKHOUSE_DEFAULT_ACCESS_MANAGEMENT=1 -e CLICKHOUSE_PASSWORD=password -p 9000:9000/tcp yandex/clickhouse-server
 ```
 
 ## How to extend this image

docker/server/entrypoint.sh

@@ -54,6 +54,7 @@ FORMAT_SCHEMA_PATH="$(clickhouse extract-from-config --config-file "$CLICKHOUSE_
 CLICKHOUSE_USER="${CLICKHOUSE_USER:-default}"
 CLICKHOUSE_PASSWORD="${CLICKHOUSE_PASSWORD:-}"
 CLICKHOUSE_DB="${CLICKHOUSE_DB:-}"
+CLICKHOUSE_ACCESS_MANAGEMENT="${CLICKHOUSE_DEFAULT_ACCESS_MANAGEMENT:-0}"
 
 for dir in "$DATA_DIR" \
   "$ERROR_LOG_DIR" \
@@ -97,6 +98,7 @@ if [ -n "$CLICKHOUSE_USER" ] && [ "$CLICKHOUSE_USER" != "default" ] || [ -n "$CL
           </networks>
           <password>${CLICKHOUSE_PASSWORD}</password>
           <quota>default</quota>
+          <access_management>${CLICKHOUSE_ACCESS_MANAGEMENT}</access_management>
         </${CLICKHOUSE_USER}>
       </users>
     </yandex>

docs/_description_templates/template-data-type.md

@@ -0,0 +1,29 @@
+---
+toc_priority: 
+toc_title: 
+---
+
+# data_type_name {#data_type-name}
+
+Description.
+
+**Parameters** (Optional)
+
+-   `x` — Description. [Type name](relative/path/to/type/dscr.md#type).
+-   `y` — Description. [Type name](relative/path/to/type/dscr.md#type).
+
+**Examples**
+
+```sql
+
+```
+
+## Additional Info {#additional-info} (Optional)
+
+The name of an additional section can be any, for example, **Usage**.
+
+**See Also** (Optional)
+
+-   [link](#)
+
+[Original article](https://clickhouse.tech/docs/en/data_types/<data-type-name>/) <!--hide-->

docs/en/operations/settings/settings.md

@@ -2592,6 +2592,18 @@ Possible values:
 
 Default value: `16`.
 
+## opentelemetry_start_trace_probability {#opentelemetry-start-trace-probability}
+
+Sets the probability that the ClickHouse can start a trace for executed queries (if no parent [trace context](https://www.w3.org/TR/trace-context/) is supplied).
+
+Possible values:
+
+-   0 — The trace for all executed queries is disabled (if no parent trace context is supplied).
+-   Positive floating-point number in the range [0..1]. For example, if the setting value is `0,5`, ClickHouse can start a trace on average for half of the queries.
+-   1 — The trace for all executed queries is enabled.
+
+Default value: `0`.
+
 ## optimize_on_insert {#optimize-on-insert}
 
 Enables or disables data transformation before the insertion, as if merge was done on this block (according to table engine).

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

@@ -0,0 +1,53 @@
+# system.opentelemetry_span_log {#system_tables-opentelemetry_span_log}
+
+Contains information about [trace spans](https://opentracing.io/docs/overview/spans/) for executed queries.
+
+Columns:
+
+-   `trace_id` ([UUID](../../sql-reference/data-types/uuid.md) — ID of the trace for executed query.
+
+-   `span_id` ([UInt64](../../sql-reference/data-types/int-uint.md)) — ID of the `trace span`.
+
+-   `parent_span_id` ([UInt64](../../sql-reference/data-types/int-uint.md)) — ID of the parent `trace span`.
+
+-   `operation_name` ([String](../../sql-reference/data-types/string.md)) — The name of the operation.
+
+-   `start_time_us` ([UInt64](../../sql-reference/data-types/int-uint.md)) — The start time of the `trace span` (in microseconds).
+
+-   `finish_time_us` ([UInt64](../../sql-reference/data-types/int-uint.md)) — The finish time of the `trace span` (in microseconds).
+
+-   `finish_date` ([Date](../../sql-reference/data-types/date.md)) — The finish date of the `trace span`.
+
+-   `attribute.names` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) — [Attribute](https://opentelemetry.io/docs/go/instrumentation/#attributes) names depending on the `trace span`. They are filled in according to the recommendations in the [OpenTelemetry](https://opentelemetry.io/) standard.
+
+-   `attribute.values` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) — Attribute values depending on the `trace span`. They are filled in according to the recommendations in the `OpenTelemetry` standard.
+
+**Example**
+
+Query:
+
+``` sql
+SELECT * FROM system.opentelemetry_span_log LIMIT 1 FORMAT Vertical;
+```
+
+Result:
+
+``` text
+Row 1:
+──────
+trace_id:         cdab0847-0d62-61d5-4d38-dd65b19a1914
+span_id:          701487461015578150
+parent_span_id:   2991972114672045096
+operation_name:   DB::Block DB::InterpreterSelectQuery::getSampleBlockImpl()
+start_time_us:    1612374594529090
+finish_time_us:   1612374594529108
+finish_date:      2021-02-03
+attribute.names:  []
+attribute.values: []
+```
+
+**See Also**
+
+-   [OpenTelemetry](../../operations/opentelemetry.md)
+
+[Original article](https://clickhouse.tech/docs/en/operations/system_tables/opentelemetry_span_log) <!--hide-->

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

@@ -0,0 +1,83 @@
+---
+toc_priority: 65
+toc_title: Map(key, value)
+---
+
+# Map(key, value) {#data_type-map}
+
+`Map(key, value)` data type stores `key:value` pairs. 
+
+**Parameters** 
+-   `key` — The key part of the pair. [String](../../sql-reference/data-types/string.md) or [Integer](../../sql-reference/data-types/int-uint.md).
+-   `value` — The value part of the pair. [String](../../sql-reference/data-types/string.md), [Integer](../../sql-reference/data-types/int-uint.md) or [Array](../../sql-reference/data-types/array.md).
+
+!!! warning "Warning"
+    Currently `Map` data type is an experimental feature. To work with it you must set `allow_experimental_map_type = 1`.
+
+To get the value from an `a Map('key', 'value')` column, use `a['key']` syntax. This lookup works now with a linear complexity.
+
+**Examples**
+
+Consider the table:
+
+``` sql
+CREATE TABLE table_map (a Map(String, UInt64)) ENGINE=Memory;
+INSERT INTO table_map VALUES ({'key1':1, 'key2':10}), ({'key1':2,'key2':20}), ({'key1':3,'key2':30});
+```
+
+Select all `key2` values: 
+
+```sql
+SELECT a['key2'] FROM table_map;
+```
+Result:
+
+```text
+┌─arrayElement(a, 'key2')─┐
+│                      10 │
+│                      20 │
+│                      30 │
+└─────────────────────────┘
+```
+
+If there's no such `key` in the `Map()` column, the query returns zeros for numerical values, empty strings or empty arrays. 
+
+```sql
+INSERT INTO table_map VALUES ({'key3':100}), ({});
+SELECT a['key3'] FROM table_map;
+```
+
+Result:
+
+```text
+┌─arrayElement(a, 'key3')─┐
+│                     100 │
+│                       0 │
+└─────────────────────────┘
+┌─arrayElement(a, 'key3')─┐
+│                       0 │
+│                       0 │
+│                       0 │
+└─────────────────────────┘
+```
+
+## Convert Tuple to Map Type {#map-and-tuple}
+
+You can cast `Tuple()` as `Map()` using [CAST](../../sql-reference/functions/type-conversion-functions.md#type_conversion_function-cast) function:
+
+``` sql
+SELECT CAST(([1, 2, 3], ['Ready', 'Steady', 'Go']), 'Map(UInt8, String)') AS map;
+```
+
+``` text
+┌─map───────────────────────────┐
+│ {1:'Ready',2:'Steady',3:'Go'} │
+└───────────────────────────────┘
+```
+
+**See Also**
+
+-   [map()](../../sql-reference/functions/tuple-map-functions.md#function-map) function
+-   [CAST()](../../sql-reference/functions/type-conversion-functions.md#type_conversion_function-cast) function
+
+[Original article](https://clickhouse.tech/docs/en/data-types/map/) <!--hide-->

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

@@ -5,6 +5,68 @@ toc_title: Working with maps
 
 # Functions for maps {#functions-for-working-with-tuple-maps}
 
+## map {#function-map}
+
+Arranges `key:value` pairs into [Map(key, value)](../../sql-reference/data-types/map.md) data type.
+
+**Syntax** 
+
+``` sql
+map(key1, value1[, key2, value2, ...])
+```
+
+**Parameters** 
+
+-   `key` — The key part of the pair. [String](../../sql-reference/data-types/string.md) or [Integer](../../sql-reference/data-types/int-uint.md).
+-   `value` — The value part of the pair. [String](../../sql-reference/data-types/string.md), [Integer](../../sql-reference/data-types/int-uint.md) or [Array](../../sql-reference/data-types/array.md).
+
+**Returned value**
+
+-  Data structure as `key:value` pairs.
+
+Type: [Map(key, value)](../../sql-reference/data-types/map.md).
+
+**Examples**
+
+Query:
+
+``` sql
+SELECT map('key1', number, 'key2', number * 2) FROM numbers(3);
+```
+
+Result:
+
+``` text
+┌─map('key1', number, 'key2', multiply(number, 2))─┐
+│ {'key1':0,'key2':0}                              │
+│ {'key1':1,'key2':2}                              │
+│ {'key1':2,'key2':4}                              │
+└──────────────────────────────────────────────────┘
+```
+
+Query:
+
+``` sql
+CREATE TABLE table_map (a Map(String, UInt64)) ENGINE = MergeTree() ORDER BY a;
+INSERT INTO table_map SELECT map('key1', number, 'key2', number * 2) FROM numbers(3);
+SELECT a['key2'] FROM table_map;
+```
+
+Result:
+
+``` text
+┌─arrayElement(a, 'key2')─┐
+│                       0 │
+│                       2 │
+│                       4 │
+└─────────────────────────┘
+```
+
+**See Also** 
+
+-   [Map(key, value)](../../sql-reference/data-types/map.md) data type
+
+
 ## mapAdd {#function-mapadd}
 
 Collect all the keys and sum corresponding values.
@@ -112,4 +174,4 @@ Result:
 └──────────────────────────────┴───────────────────────────────────┘
 ```
 
-[Original article](https://clickhouse.tech/docs/en/query_language/functions/tuple-map-functions/) <!--hide-->
+[Original article](https://clickhouse.tech/docs/en/sql-reference/functions/tuple-map-functions/) <!--hide-->

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

@@ -133,10 +133,9 @@ For example:
 
 ### cutToFirstSignificantSubdomainCustom {#cuttofirstsignificantsubdomaincustom}
 
-Same as `cutToFirstSignificantSubdomain` but accept custom TLD list name, useful if:
+Returns the part of the domain that includes top-level subdomains up to the first significant subdomain. Accepts custom [TLD list](https://en.wikipedia.org/wiki/List_of_Internet_top-level_domains) name.
 
-- you need fresh TLD list,
+Can be useful if you need fresh TLD list or you have custom.
-- or you have custom.
 
 Configuration example:
 
@@ -149,21 +148,150 @@ Configuration example:
 </top_level_domains_lists>
 ```
 
-Example:
+**Syntax**
 
--   `cutToFirstSignificantSubdomain('https://news.yandex.com.tr/', 'public_suffix_list') = 'yandex.com.tr'`.
+``` sql
+cutToFirstSignificantSubdomain(URL, TLD)
+```
+
+**Parameters**
+
+-   `URL` — URL. [String](../../sql-reference/data-types/string.md).
+-   `TLD` — Custom TLD list name. [String](../../sql-reference/data-types/string.md).
+
+**Returned value**
+
+-   Part of the domain that includes top-level subdomains up to the first significant subdomain.
+
+Type: [String](../../sql-reference/data-types/string.md).
+
+**Example**
+
+Query:
+
+```sql
+SELECT cutToFirstSignificantSubdomainCustom('bar.foo.there-is-no-such-domain', 'public_suffix_list');
+```
+
+Result:
+
+```text
+┌─cutToFirstSignificantSubdomainCustom('bar.foo.there-is-no-such-domain', 'public_suffix_list')─┐
+│ foo.there-is-no-such-domain                                                                   │
+└───────────────────────────────────────────────────────────────────────────────────────────────┘
+```
+
+**See Also**
+
+-   [firstSignificantSubdomain](#firstsignificantsubdomain).
 
 ### cutToFirstSignificantSubdomainCustomWithWWW {#cuttofirstsignificantsubdomaincustomwithwww}
 
-Same as `cutToFirstSignificantSubdomainWithWWW` but accept custom TLD list name.
+Returns the part of the domain that includes top-level subdomains up to the first significant subdomain without stripping `www`. Accepts custom TLD list name.
+
+Can be useful if you need fresh TLD list or you have custom.
+
+Configuration example:
+
+```xml
+<!-- <top_level_domains_path>/var/lib/clickhouse/top_level_domains/</top_level_domains_path> -->
+<top_level_domains_lists>
+    <!-- https://publicsuffix.org/list/public_suffix_list.dat -->
+    <public_suffix_list>public_suffix_list.dat</public_suffix_list>
+    <!-- NOTE: path is under top_level_domains_path -->
+</top_level_domains_lists>
+```
+
+**Syntax**
+
+```sql
+cutToFirstSignificantSubdomainCustomWithWWW(URL, TLD)
+```
+
+**Parameters**
+
+-   `URL` — URL. [String](../../sql-reference/data-types/string.md).
+-   `TLD` — Custom TLD list name. [String](../../sql-reference/data-types/string.md).
+
+**Returned value**
+
+-   Part of the domain that includes top-level subdomains up to the first significant subdomain without stripping `www`.
+
+Type: [String](../../sql-reference/data-types/string.md).
+
+**Example**
+
+Query:
+
+```sql
+SELECT cutToFirstSignificantSubdomainCustomWithWWW('www.foo', 'public_suffix_list');
+```
+
+Result:
+
+```text
+┌─cutToFirstSignificantSubdomainCustomWithWWW('www.foo', 'public_suffix_list')─┐
+│ www.foo                                                                      │
+└──────────────────────────────────────────────────────────────────────────────┘
+```
+
+**See Also**
+
+-   [firstSignificantSubdomain](#firstsignificantsubdomain).
 
 ### firstSignificantSubdomainCustom {#firstsignificantsubdomaincustom}
 
-Same as `firstSignificantSubdomain` but accept custom TLD list name.
+Returns the first significant subdomain. Accepts customs TLD list name.
 
-### cutToFirstSignificantSubdomainCustomWithWWW {#cuttofirstsignificantsubdomaincustomwithwww}
+Can be useful if you need fresh TLD list or you have custom.
 
-Same as `cutToFirstSignificantSubdomainWithWWW` but accept custom TLD list name.
+Configuration example:
+
+```xml
+<!-- <top_level_domains_path>/var/lib/clickhouse/top_level_domains/</top_level_domains_path> -->
+<top_level_domains_lists>
+    <!-- https://publicsuffix.org/list/public_suffix_list.dat -->
+    <public_suffix_list>public_suffix_list.dat</public_suffix_list>
+    <!-- NOTE: path is under top_level_domains_path -->
+</top_level_domains_lists>
+```
+
+**Syntax**
+
+```sql
+firstSignificantSubdomainCustom(URL, TLD)
+```
+
+**Parameters**
+
+-   `URL` — URL. [String](../../sql-reference/data-types/string.md).
+-   `TLD` — Custom TLD list name. [String](../../sql-reference/data-types/string.md).
+
+**Returned value**
+
+-   First significant subdomain.
+
+Type: [String](../../sql-reference/data-types/string.md).
+
+**Example**
+
+Query:
+
+```sql
+SELECT firstSignificantSubdomainCustom('bar.foo.there-is-no-such-domain', 'public_suffix_list');
+```
+
+Result:
+
+```text 
+┌─firstSignificantSubdomainCustom('bar.foo.there-is-no-such-domain', 'public_suffix_list')─┐
+│ foo                                                                                      │
+└──────────────────────────────────────────────────────────────────────────────────────────┘
+```
+
+**See Also**
+
+-   [firstSignificantSubdomain](#firstsignificantsubdomain).
 
 ### port(URL\[, default_port = 0\]) {#port}
 

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

@@ -14,14 +14,16 @@ ClickHouse supports the standard grammar for defining windows and window functio
 
 | Feature | Support or workaround |
 | --------| ----------|
-| ad hoc window specification (`count(*) over (partition by id order by time desc)`) | yes |
+| ad hoc window specification (`count(*) over (partition by id order by time desc)`) | supported |
-| `WINDOW` clause (`select ... from table window w as (partiton by id)`) | yes |
+| expressions involving window functions, e.g. `(count(*) over ()) / 2)` | not supported, wrap in a subquery ([feature request](https://github.com/ClickHouse/ClickHouse/issues/19857)) |
-| `ROWS` frame | yes |
+| `WINDOW` clause (`select ... from table window w as (partiton by id)`) | supported |
-| `RANGE` frame | yes, it is the default |
+| `ROWS` frame | supported |
-| `GROUPS` frame | no |
+| `RANGE` frame | supported, the default |
+| `INTERVAL` syntax for `DateTime` `RANGE OFFSET` frame | not supported, specify the number of seconds instead |
+| `GROUPS` frame | not supported |
 | Calculating aggregate functions over a frame (`sum(value) over (order by time)`) | all aggregate functions are supported |
-| `rank()`, `dense_rank()`, `row_number()` | yes |
+| `rank()`, `dense_rank()`, `row_number()` | supported |
-| `lag/lead(value, offset)` | no, replace with `any(value) over (.... rows between <offset> preceding and <offset> preceding)`, or `following` for `lead`| 
+| `lag/lead(value, offset)` | not supported, replace with `any(value) over (.... rows between <offset> preceding and <offset> preceding)`, or `following` for `lead`| 
 
 ## References
 

docs/ru/operations/settings/settings.md

@@ -2473,6 +2473,18 @@ SELECT SUM(-1), MAX(0) FROM system.one WHERE 0;
 
 Значение по умолчанию: `16`.
 
+## opentelemetry_start_trace_probability {#opentelemetry-start-trace-probability}
+
+Задает вероятность того, что ClickHouse начнет трассировку для выполненных запросов (если не указан [входящий контекст](https://www.w3.org/TR/trace-context/) трассировки).
+
+Возможные значения:
+
+-   0 — трассировка для выполненных запросов отключена (если не указан входящий контекст трассировки).
+-   Положительное число с плавающей точкой в диапазоне [0..1]. Например, при значении настройки, равной `0,5`, ClickHouse начнет трассировку в среднем для половины запросов.
+-   1 — трассировка для всех выполненных запросов включена.
+
+Значение по умолчанию: `0`.
+
 ## optimize_on_insert {#optimize-on-insert}
 
 Включает или выключает преобразование данных перед добавлением в таблицу, как будто над добавляемым блоком предварительно было произведено слияние (в соответствии с движком таблицы).

docs/ru/operations/system-tables/opentelemetry_span_log.md

@@ -0,0 +1,49 @@
+# system.opentelemetry_span_log {#system_tables-opentelemetry_span_log}
+
+Содержит информацию о [trace spans](https://opentracing.io/docs/overview/spans/) для выполненных запросов.
+
+Столбцы:
+
+-   `trace_id` ([UUID](../../sql-reference/data-types/uuid.md) — идентификатор трассировки для выполненного запроса.
+
+-   `span_id` ([UInt64](../../sql-reference/data-types/int-uint.md)) — идентификатор `trace span`.
+
+-   `parent_span_id` ([UInt64](../../sql-reference/data-types/int-uint.md)) — идентификатор родительского `trace span`.
+
+-   `operation_name` ([String](../../sql-reference/data-types/string.md)) — имя операции.
+
+-   `start_time_us` ([UInt64](../../sql-reference/data-types/int-uint.md)) — время начала `trace span` (в микросекундах).
+
+-   `finish_time_us` ([UInt64](../../sql-reference/data-types/int-uint.md)) — время окончания `trace span` (в микросекундах).
+
+-   `finish_date` ([Date](../../sql-reference/data-types/date.md)) — дата окончания `trace span`.
+
+-   `attribute.names` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) — имена [атрибутов](https://opentelemetry.io/docs/go/instrumentation/#attributes) в зависимости от `trace span`. Заполняются согласно рекомендациям в стандарте [OpenTelemetry](https://opentelemetry.io/).
+
+-   `attribute.values` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) — значения атрибутов в зависимости от `trace span`. Заполняются согласно рекомендациям в стандарте `OpenTelemetry`.
+
+**Пример**
+
+Запрос:
+
+``` sql
+SELECT * FROM system.opentelemetry_span_log LIMIT 1 FORMAT Vertical;
+```
+
+Результат:
+
+``` text
+Row 1:
+──────
+trace_id:         cdab0847-0d62-61d5-4d38-dd65b19a1914
+span_id:          701487461015578150
+parent_span_id:   2991972114672045096
+operation_name:   DB::Block DB::InterpreterSelectQuery::getSampleBlockImpl()
+start_time_us:    1612374594529090
+finish_time_us:   1612374594529108
+finish_date:      2021-02-03
+attribute.names:  []
+attribute.values: []
+```
+
+[Оригинальная статья](https://clickhouse.tech/docs/ru/operations/system_tables/opentelemetry_span_log) <!--hide-->

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

@@ -0,0 +1,69 @@
+---
+toc_priority: 65
+toc_title: Map(key, value)
+---
+
+# Map(key, value) {#data_type-map}
+
+Тип данных `Map(key, value)` хранит пары `ключ:значение`. 
+
+**Параметры** 
+-   `key` — ключ. [String](../../sql-reference/data-types/string.md) или [Integer](../../sql-reference/data-types/int-uint.md).
+-   `value` — значение. [String](../../sql-reference/data-types/string.md), [Integer](../../sql-reference/data-types/int-uint.md) или [Array](../../sql-reference/data-types/array.md).
+
+!!! warning "Предупреждение"
+    Сейчас использование типа данных `Map` является экспериментальной возможностью. Чтобы использовать этот тип данных, включите настройку `allow_experimental_map_type = 1`.
+
+Чтобы получить значение из колонки `a Map('key', 'value')`, используйте синтаксис `a['key']`. В настоящее время такая подстановка работает по алгоритму с линейной сложностью.
+
+**Примеры**
+
+Рассмотрим таблицу:
+
+``` sql
+CREATE TABLE table_map (a Map(String, UInt64)) ENGINE=Memory;
+INSERT INTO table_map VALUES ({'key1':1, 'key2':10}), ({'key1':2,'key2':20}), ({'key1':3,'key2':30});
+```
+
+Выборка всех значений ключа `key2`: 
+
+```sql
+SELECT a['key2'] FROM table_map;
+```
+Результат:
+
+```text
+┌─arrayElement(a, 'key2')─┐
+│                      10 │
+│                      20 │
+│                      30 │
+└─────────────────────────┘
+```
+
+Если для какого-то ключа `key` в колонке с типом `Map()` нет значения, запрос возвращает нули для числовых колонок, пустые строки или пустые массивы. 
+
+```sql
+INSERT INTO table_map VALUES ({'key3':100}), ({});
+SELECT a['key3'] FROM table_map;
+```
+
+Результат:
+
+```text
+┌─arrayElement(a, 'key3')─┐
+│                     100 │
+│                       0 │
+└─────────────────────────┘
+┌─arrayElement(a, 'key3')─┐
+│                       0 │
+│                       0 │
+│                       0 │
+└─────────────────────────┘
+```
+
+**См. также**
+
+-   функция [map()](../../sql-reference/functions/tuple-map-functions.md#function-map)
+-   функция [CAST()](../../sql-reference/functions/type-conversion-functions.md#type_conversion_function-cast)
+
+[Original article](https://clickhouse.tech/docs/ru/data-types/map/) <!--hide-->

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

@@ -5,6 +5,66 @@ toc_title: Работа с контейнерами map
 
 # Функции для работы с контейнерами map {#functions-for-working-with-tuple-maps}
 
+## map {#function-map}
+
+Преобразовывает пары `ключ:значение` в тип данных [Map(key, value)](../../sql-reference/data-types/map.md).
+
+**Синтаксис** 
+
+``` sql
+map(key1, value1[, key2, value2, ...])
+```
+
+**Параметры** 
+
+-   `key` — ключ. [String](../../sql-reference/data-types/string.md) или [Integer](../../sql-reference/data-types/int-uint.md).
+-   `value` — значение. [String](../../sql-reference/data-types/string.md), [Integer](../../sql-reference/data-types/int-uint.md) или [Array](../../sql-reference/data-types/array.md).
+
+**Возвращаемое значение**
+
+-   Структура данных в виде пар `ключ:значение`.
+
+Тип: [Map(key, value)](../../sql-reference/data-types/map.md).
+
+**Примеры**
+
+Запрос:
+
+``` sql
+SELECT map('key1', number, 'key2', number * 2) FROM numbers(3);
+```
+
+Результат:
+
+``` text
+┌─map('key1', number, 'key2', multiply(number, 2))─┐
+│ {'key1':0,'key2':0}                              │
+│ {'key1':1,'key2':2}                              │
+│ {'key1':2,'key2':4}                              │
+└──────────────────────────────────────────────────┘
+```
+
+Запрос:
+
+``` sql
+CREATE TABLE table_map (a Map(String, UInt64)) ENGINE = MergeTree() ORDER BY a;
+INSERT INTO table_map SELECT map('key1', number, 'key2', number * 2) FROM numbers(3);
+SELECT a['key2'] FROM table_map;
+```
+
+Результат:
+
+``` text
+┌─arrayElement(a, 'key2')─┐
+│                       0 │
+│                       2 │
+│                       4 │
+└─────────────────────────┘
+```
+
+**См. также** 
+
+-   тип данных [Map(key, value)](../../sql-reference/data-types/map.md)
 ## mapAdd {#function-mapadd}
 
 Собирает все ключи и суммирует соответствующие значения.

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

@@ -115,6 +115,168 @@ SELECT topLevelDomain('svn+ssh://www.some.svn-hosting.com:80/repo/trunk')
 
 Например, `cutToFirstSignificantSubdomain('https://news.yandex.com.tr/') = 'yandex.com.tr'`.
 
+### cutToFirstSignificantSubdomainCustom {#cuttofirstsignificantsubdomaincustom}
+
+Возвращает часть домена, включающую поддомены верхнего уровня до первого существенного поддомена. Принимает имя пользовательского [списка доменов верхнего уровня](https://ru.wikipedia.org/wiki/Список_доменов_верхнего_уровня).
+
+Полезно, если требуется актуальный список доменов верхнего уровня или если есть пользовательский.
+
+Пример конфигурации:
+
+```xml
+<!-- <top_level_domains_path>/var/lib/clickhouse/top_level_domains/</top_level_domains_path> -->
+<top_level_domains_lists>
+    <!-- https://publicsuffix.org/list/public_suffix_list.dat -->
+    <public_suffix_list>public_suffix_list.dat</public_suffix_list>
+    <!-- NOTE: path is under top_level_domains_path -->
+</top_level_domains_lists>
+```
+
+**Синтаксис**
+
+``` sql
+cutToFirstSignificantSubdomain(URL, TLD)
+```
+
+**Parameters**
+
+-   `URL` — URL. [String](../../sql-reference/data-types/string.md).
+-   `TLD` — имя пользовательского списка доменов верхнего уровня. [String](../../sql-reference/data-types/string.md).
+
+**Возвращаемое значение**
+
+-   Часть домена, включающая поддомены верхнего уровня до первого существенного поддомена.
+
+Тип: [String](../../sql-reference/data-types/string.md).
+
+**Пример**
+
+Запрос:
+
+```sql
+SELECT cutToFirstSignificantSubdomainCustom('bar.foo.there-is-no-such-domain', 'public_suffix_list');
+```
+
+Результат:
+
+```text
+┌─cutToFirstSignificantSubdomainCustom('bar.foo.there-is-no-such-domain', 'public_suffix_list')─┐
+│ foo.there-is-no-such-domain                                                                   │
+└───────────────────────────────────────────────────────────────────────────────────────────────┘
+```
+
+**Смотрите также**
+
+-   [firstSignificantSubdomain](#firstsignificantsubdomain).
+
+### cutToFirstSignificantSubdomainCustomWithWWW {#cuttofirstsignificantsubdomaincustomwithwww}
+
+Возвращает часть домена, включающую поддомены верхнего уровня до первого существенного поддомена, не опуская "www". Принимает имя пользовательского списка доменов верхнего уровня.
+
+Полезно, если требуется актуальный список доменов верхнего уровня или если есть пользовательский.
+
+Пример конфигурации:
+
+```xml
+<!-- <top_level_domains_path>/var/lib/clickhouse/top_level_domains/</top_level_domains_path> -->
+<top_level_domains_lists>
+    <!-- https://publicsuffix.org/list/public_suffix_list.dat -->
+    <public_suffix_list>public_suffix_list.dat</public_suffix_list>
+    <!-- NOTE: path is under top_level_domains_path -->
+</top_level_domains_lists>
+```
+
+**Синтаксис**
+
+```sql
+cutToFirstSignificantSubdomainCustomWithWWW(URL, TLD)
+```
+
+**Параметры**
+
+-   `URL` — URL. [String](../../sql-reference/data-types/string.md).
+-   `TLD` — имя пользовательского списка доменов верхнего уровня. [String](../../sql-reference/data-types/string.md).
+
+**Возвращаемое значение**
+
+-   Часть домена, включающая поддомены верхнего уровня до первого существенного поддомена, без удаления `www`.
+
+Тип: [String](../../sql-reference/data-types/string.md).
+
+**Пример**
+
+Запрос:
+
+```sql
+SELECT cutToFirstSignificantSubdomainCustomWithWWW('www.foo', 'public_suffix_list');
+```
+
+Результат:
+
+```text
+┌─cutToFirstSignificantSubdomainCustomWithWWW('www.foo', 'public_suffix_list')─┐
+│ www.foo                                                                      │
+└──────────────────────────────────────────────────────────────────────────────┘
+```
+
+**Смотрите также**
+
+-   [firstSignificantSubdomain](#firstsignificantsubdomain).
+
+### firstSignificantSubdomainCustom {#firstsignificantsubdomaincustom}
+
+Возвращает первый существенный поддомен. Принимает имя пользовательского списка доменов верхнего уровня.
+
+Полезно, если требуется актуальный список доменов верхнего уровня или если есть пользовательский.
+
+Пример конфигурации:
+
+```xml
+<!-- <top_level_domains_path>/var/lib/clickhouse/top_level_domains/</top_level_domains_path> -->
+<top_level_domains_lists>
+    <!-- https://publicsuffix.org/list/public_suffix_list.dat -->
+    <public_suffix_list>public_suffix_list.dat</public_suffix_list>
+    <!-- NOTE: path is under top_level_domains_path -->
+</top_level_domains_lists>
+```
+
+**Синтаксис**
+
+```sql
+firstSignificantSubdomainCustom(URL, TLD)
+```
+
+**Параметры**
+
+-   `URL` — URL. [String](../../sql-reference/data-types/string.md).
+-   `TLD` — имя пользовательского списка доменов верхнего уровня. [String](../../sql-reference/data-types/string.md).
+
+**Возвращаемое значение**
+
+-   Первый существенный поддомен.
+
+Тип: [String](../../sql-reference/data-types/string.md).
+
+**Пример**
+
+Запрос:
+
+```sql
+SELECT firstSignificantSubdomainCustom('bar.foo.there-is-no-such-domain', 'public_suffix_list');
+```
+
+Результат:
+
+```text 
+┌─firstSignificantSubdomainCustom('bar.foo.there-is-no-such-domain', 'public_suffix_list')─┐
+│ foo                                                                                      │
+└──────────────────────────────────────────────────────────────────────────────────────────┘
+```
+
+**Смотрите также**
+
+-   [firstSignificantSubdomain](#firstsignificantsubdomain).
+
 ### port(URL[, default_port = 0]) {#port}
 
 Возвращает порт или значение `default_port`, если в URL-адресе нет порта (или передан невалидный URL) 

src/Client/Connection.cpp

@@ -756,7 +756,11 @@ std::optional<UInt64> Connection::checkPacket(size_t timeout_microseconds)
 Packet Connection::receivePacket(std::function<void(Poco::Net::Socket &)> async_callback)
 {
     in->setAsyncCallback(std::move(async_callback));
-    SCOPE_EXIT(in->setAsyncCallback({}));
+    SCOPE_EXIT({
+        /// disconnect() will reset "in".
+        if (in)
+            in->setAsyncCallback({});
+    });
 
     try
     {

src/Coordination/NuKeeperStateMachine.cpp

@@ -166,6 +166,8 @@ void NuKeeperStateMachine::create_snapshot(
         }
 
     }
+
+    LOG_DEBUG(log, "Created snapshot {}", s.get_last_log_idx());
     nuraft::ptr<std::exception> except(nullptr);
     bool ret = true;
     when_done(ret, except);

src/Formats/JSONEachRowUtils.cpp

@@ -6,6 +6,7 @@ namespace DB
 namespace ErrorCodes
 {
     extern const int INCORRECT_DATA;
+    extern const int LOGICAL_ERROR;
 }
 
 std::pair<bool, size_t> fileSegmentationEngineJSONEachRowImpl(ReadBuffer & in, DB::Memory<> & memory, size_t min_chunk_size)
@@ -28,7 +29,9 @@ std::pair<bool, size_t> fileSegmentationEngineJSONEachRowImpl(ReadBuffer & in, D
         if (quotes)
         {
             pos = find_first_symbols<'\\', '"'>(pos, in.buffer().end());
-            if (pos == in.buffer().end())
+            if (pos > in.buffer().end())
+                throw Exception("Position in buffer is out of bounds. There must be a bug.", ErrorCodes::LOGICAL_ERROR);
+            else if (pos == in.buffer().end())
                 continue;
             if (*pos == '\\')
             {
@@ -45,9 +48,11 @@ std::pair<bool, size_t> fileSegmentationEngineJSONEachRowImpl(ReadBuffer & in, D
         else
         {
             pos = find_first_symbols<'{', '}', '\\', '"'>(pos, in.buffer().end());
-            if (pos == in.buffer().end())
+            if (pos > in.buffer().end())
+                throw Exception("Position in buffer is out of bounds. There must be a bug.", ErrorCodes::LOGICAL_ERROR);
+            else if (pos == in.buffer().end())
                 continue;
-            if (*pos == '{')
+            else if (*pos == '{')
             {
                 ++balance;
                 ++pos;

src/IO/BufferWithOwnMemory.h

@@ -35,10 +35,10 @@ struct Memory : boost::noncopyable, Allocator
     char * m_data = nullptr;
     size_t alignment = 0;
 
-    Memory() {}
+    Memory() = default;
 
     /// If alignment != 0, then allocate memory aligned to specified value.
-    Memory(size_t size_, size_t alignment_ = 0) : m_capacity(size_), m_size(m_capacity), alignment(alignment_)
+    explicit Memory(size_t size_, size_t alignment_ = 0) : m_capacity(size_), m_size(m_capacity), alignment(alignment_)
     {
         alloc();
     }
@@ -140,7 +140,7 @@ protected:
     Memory<> memory;
 public:
     /// If non-nullptr 'existing_memory' is passed, then buffer will not create its own memory and will use existing_memory without ownership.
-    BufferWithOwnMemory(size_t size = DBMS_DEFAULT_BUFFER_SIZE, char * existing_memory = nullptr, size_t alignment = 0)
+    explicit BufferWithOwnMemory(size_t size = DBMS_DEFAULT_BUFFER_SIZE, char * existing_memory = nullptr, size_t alignment = 0)
         : Base(nullptr, 0), memory(existing_memory ? 0 : size, alignment)
     {
         Base::set(existing_memory ? existing_memory : memory.data(), size);

src/Parsers/ExpressionElementParsers.cpp

@@ -266,7 +266,7 @@ bool ParserFunction::parseImpl(Pos & pos, ASTPtr & node, Expected & expected)
     ParserIdentifier id_parser;
     ParserKeyword distinct("DISTINCT");
     ParserKeyword all("ALL");
-    ParserExpressionList contents(false);
+    ParserExpressionList contents(false, is_table_function);
     ParserSelectWithUnionQuery select;
     ParserKeyword over("OVER");
 
@@ -278,6 +278,12 @@ bool ParserFunction::parseImpl(Pos & pos, ASTPtr & node, Expected & expected)
     ASTPtr expr_list_args;
     ASTPtr expr_list_params;
 
+    if (is_table_function)
+    {
+        if (ParserTableFunctionView().parse(pos, node, expected))
+            return true;
+    }
+
     if (!id_parser.parse(pos, identifier, expected))
         return false;
 
@@ -312,36 +318,6 @@ bool ParserFunction::parseImpl(Pos & pos, ASTPtr & node, Expected & expected)
         }
     }
 
-    if (!has_distinct && !has_all)
-    {
-        auto old_pos = pos;
-        auto maybe_an_subquery = pos->type == TokenType::OpeningRoundBracket;
-
-        if (select.parse(pos, query, expected))
-        {
-            auto & select_ast = query->as<ASTSelectWithUnionQuery &>();
-            if (select_ast.list_of_selects->children.size() == 1 && maybe_an_subquery)
-            {
-                // It's an subquery. Bail out.
-                pos = old_pos;
-            }
-            else
-            {
-                if (pos->type != TokenType::ClosingRoundBracket)
-                    return false;
-                ++pos;
-                auto function_node = std::make_shared<ASTFunction>();
-                tryGetIdentifierNameInto(identifier, function_node->name);
-                auto expr_list_with_single_query = std::make_shared<ASTExpressionList>();
-                expr_list_with_single_query->children.push_back(query);
-                function_node->arguments = expr_list_with_single_query;
-                function_node->children.push_back(function_node->arguments);
-                node = function_node;
-                return true;
-            }
-        }
-    }
-
     const char * contents_begin = pos->begin;
     if (!contents.parse(pos, expr_list_args, expected))
         return false;
@@ -477,6 +453,49 @@ bool ParserFunction::parseImpl(Pos & pos, ASTPtr & node, Expected & expected)
     return true;
 }
 
+bool ParserTableFunctionView::parseImpl(Pos & pos, ASTPtr & node, Expected & expected)
+{
+    ParserIdentifier id_parser;
+    ParserKeyword view("VIEW");
+    ParserSelectWithUnionQuery select;
+
+    ASTPtr identifier;
+    ASTPtr query;
+
+    if (!view.ignore(pos, expected))
+        return false;
+
+    if (pos->type != TokenType::OpeningRoundBracket)
+        return false;
+
+    ++pos;
+
+    bool maybe_an_subquery = pos->type == TokenType::OpeningRoundBracket;
+
+    if (!select.parse(pos, query, expected))
+        return false;
+
+    auto & select_ast = query->as<ASTSelectWithUnionQuery &>();
+    if (select_ast.list_of_selects->children.size() == 1 && maybe_an_subquery)
+    {
+        // It's an subquery. Bail out.
+        return false;
+    }
+
+    if (pos->type != TokenType::ClosingRoundBracket)
+        return false;
+    ++pos;
+    auto function_node = std::make_shared<ASTFunction>();
+    tryGetIdentifierNameInto(identifier, function_node->name);
+    auto expr_list_with_single_query = std::make_shared<ASTExpressionList>();
+    expr_list_with_single_query->children.push_back(query);
+    function_node->name = "view";
+    function_node->arguments = expr_list_with_single_query;
+    function_node->children.push_back(function_node->arguments);
+    node = function_node;
+    return true;
+}
+
 bool ParserWindowReference::parseImpl(Pos & pos, ASTPtr & node, Expected & expected)
 {
     ASTFunction * function = dynamic_cast<ASTFunction *>(node.get());

src/Parsers/ExpressionElementParsers.h

@@ -149,11 +149,25 @@ protected:
 class ParserFunction : public IParserBase
 {
 public:
-    ParserFunction(bool allow_function_parameters_ = true) : allow_function_parameters(allow_function_parameters_) {}
+    ParserFunction(bool allow_function_parameters_ = true, bool is_table_function_ = false)
+        : allow_function_parameters(allow_function_parameters_), is_table_function(is_table_function_)
+    {
+    }
+
 protected:
     const char * getName() const override { return "function"; }
     bool parseImpl(Pos & pos, ASTPtr & node, Expected & expected) override;
     bool allow_function_parameters;
+    bool is_table_function;
+};
+
+// A special function parser for view table function.
+// It parses an SELECT query as its argument and doesn't support getColumnName().
+class ParserTableFunctionView : public IParserBase
+{
+protected:
+    const char * getName() const override { return "function"; }
+    bool parseImpl(Pos & pos, ASTPtr & node, Expected & expected) override;
 };
 
 // Window reference (the thing that goes after OVER) for window function.

src/Parsers/ExpressionListParsers.cpp

@@ -468,6 +468,14 @@ bool ParserLambdaExpression::parseImpl(Pos & pos, ASTPtr & node, Expected & expe
 }
 
 
+bool ParserTableFunctionExpression::parseImpl(Pos & pos, ASTPtr & node, Expected & expected)
+{
+    if (ParserTableFunctionView().parse(pos, node, expected))
+        return true;
+    return elem_parser.parse(pos, node, expected);
+}
+
+
 bool ParserPrefixUnaryOperatorExpression::parseImpl(Pos & pos, ASTPtr & node, Expected & expected)
 {
     /// try to find any of the valid operators
@@ -570,8 +578,9 @@ bool ParserTupleElementExpression::parseImpl(Pos & pos, ASTPtr & node, Expected
 }
 
 
-ParserExpressionWithOptionalAlias::ParserExpressionWithOptionalAlias(bool allow_alias_without_as_keyword)
+ParserExpressionWithOptionalAlias::ParserExpressionWithOptionalAlias(bool allow_alias_without_as_keyword, bool is_table_function)
-    : impl(std::make_unique<ParserWithOptionalAlias>(std::make_unique<ParserExpression>(),
+    : impl(std::make_unique<ParserWithOptionalAlias>(
+        is_table_function ? ParserPtr(std::make_unique<ParserTableFunctionExpression>()) : ParserPtr(std::make_unique<ParserExpression>()),
         allow_alias_without_as_keyword))
 {
 }
@@ -580,7 +589,7 @@ ParserExpressionWithOptionalAlias::ParserExpressionWithOptionalAlias(bool allow_
 bool ParserExpressionList::parseImpl(Pos & pos, ASTPtr & node, Expected & expected)
 {
     return ParserList(
-        std::make_unique<ParserExpressionWithOptionalAlias>(allow_alias_without_as_keyword),
+        std::make_unique<ParserExpressionWithOptionalAlias>(allow_alias_without_as_keyword, is_table_function),
         std::make_unique<ParserToken>(TokenType::Comma))
         .parse(pos, node, expected);
 }

src/Parsers/ExpressionListParsers.h

@@ -436,13 +436,26 @@ protected:
 };
 
 
+// It's used to parse expressions in table function.
+class ParserTableFunctionExpression : public IParserBase
+{
+private:
+    ParserLambdaExpression elem_parser;
+
+protected:
+    const char * getName() const override { return "table function expression"; }
+
+    bool parseImpl(Pos & pos, ASTPtr & node, Expected & expected) override;
+};
+
+
 using ParserExpression = ParserLambdaExpression;
 
 
 class ParserExpressionWithOptionalAlias : public IParserBase
 {
 public:
-    ParserExpressionWithOptionalAlias(bool allow_alias_without_as_keyword);
+    explicit ParserExpressionWithOptionalAlias(bool allow_alias_without_as_keyword, bool is_table_function = false);
 protected:
     ParserPtr impl;
 
@@ -459,11 +472,12 @@ protected:
 class ParserExpressionList : public IParserBase
 {
 public:
-    ParserExpressionList(bool allow_alias_without_as_keyword_)
+    explicit ParserExpressionList(bool allow_alias_without_as_keyword_, bool is_table_function_ = false)
-        : allow_alias_without_as_keyword(allow_alias_without_as_keyword_) {}
+        : allow_alias_without_as_keyword(allow_alias_without_as_keyword_), is_table_function(is_table_function_) {}
 
 protected:
     bool allow_alias_without_as_keyword;
+    bool is_table_function; // This expression list is used by a table function
 
     const char * getName() const override { return "list of expressions"; }
     bool parseImpl(Pos & pos, ASTPtr & node, Expected & expected) override;
@@ -473,7 +487,7 @@ protected:
 class ParserNotEmptyExpressionList : public IParserBase
 {
 public:
-    ParserNotEmptyExpressionList(bool allow_alias_without_as_keyword)
+    explicit ParserNotEmptyExpressionList(bool allow_alias_without_as_keyword)
         : nested_parser(allow_alias_without_as_keyword) {}
 private:
     ParserExpressionList nested_parser;

src/Parsers/ParserTablesInSelectQuery.cpp

@@ -22,7 +22,7 @@ bool ParserTableExpression::parseImpl(Pos & pos, ASTPtr & node, Expected & expec
     auto res = std::make_shared<ASTTableExpression>();
 
     if (!ParserWithOptionalAlias(std::make_unique<ParserSubquery>(), true).parse(pos, res->subquery, expected)
-        && !ParserWithOptionalAlias(std::make_unique<ParserFunction>(), true).parse(pos, res->table_function, expected)
+        && !ParserWithOptionalAlias(std::make_unique<ParserFunction>(true, true), true).parse(pos, res->table_function, expected)
         && !ParserWithOptionalAlias(std::make_unique<ParserCompoundIdentifier>(false, true), true).parse(pos, res->database_and_table_name, expected))
         return false;
 

src/Processors/Formats/Impl/CSVRowInputFormat.cpp

@@ -15,6 +15,7 @@ namespace ErrorCodes
 {
     extern const int BAD_ARGUMENTS;
     extern const int INCORRECT_DATA;
+    extern const int LOGICAL_ERROR;
 }
 
 
@@ -436,9 +437,11 @@ static std::pair<bool, size_t> fileSegmentationEngineCSVImpl(ReadBuffer & in, DB
         if (quotes)
         {
             pos = find_first_symbols<'"'>(pos, in.buffer().end());
-            if (pos == in.buffer().end())
+            if (pos > in.buffer().end())
+                throw Exception("Position in buffer is out of bounds. There must be a bug.", ErrorCodes::LOGICAL_ERROR);
+            else if (pos == in.buffer().end())
                 continue;
-            if (*pos == '"')
+            else if (*pos == '"')
             {
                 ++pos;
                 if (loadAtPosition(in, memory, pos) && *pos == '"')
@@ -450,9 +453,11 @@ static std::pair<bool, size_t> fileSegmentationEngineCSVImpl(ReadBuffer & in, DB
         else
         {
             pos = find_first_symbols<'"', '\r', '\n'>(pos, in.buffer().end());
-            if (pos == in.buffer().end())
+            if (pos > in.buffer().end())
+                throw Exception("Position in buffer is out of bounds. There must be a bug.", ErrorCodes::LOGICAL_ERROR);
+            else if (pos == in.buffer().end())
                 continue;
-            if (*pos == '"')
+            else if (*pos == '"')
             {
                 quotes = true;
                 ++pos;

src/Processors/Formats/Impl/RegexpRowInputFormat.cpp

@@ -11,6 +11,7 @@ namespace ErrorCodes
 {
     extern const int INCORRECT_DATA;
     extern const int BAD_ARGUMENTS;
+    extern const int LOGICAL_ERROR;
 }
 
 RegexpRowInputFormat::RegexpRowInputFormat(
@@ -182,7 +183,9 @@ static std::pair<bool, size_t> fileSegmentationEngineRegexpImpl(ReadBuffer & in,
     while (loadAtPosition(in, memory, pos) && need_more_data)
     {
         pos = find_first_symbols<'\n', '\r'>(pos, in.buffer().end());
-        if (pos == in.buffer().end())
+        if (pos > in.buffer().end())
+                throw Exception("Position in buffer is out of bounds. There must be a bug.", ErrorCodes::LOGICAL_ERROR);
+        else if (pos == in.buffer().end())
             continue;
 
         // Support DOS-style newline ("\r\n")

src/Processors/Formats/Impl/TabSeparatedRowInputFormat.cpp

@@ -15,6 +15,7 @@ namespace DB
 namespace ErrorCodes
 {
     extern const int INCORRECT_DATA;
+    extern const int LOGICAL_ERROR;
 }
 
 
@@ -433,10 +434,11 @@ static std::pair<bool, size_t> fileSegmentationEngineTabSeparatedImpl(ReadBuffer
     {
         pos = find_first_symbols<'\\', '\r', '\n'>(pos, in.buffer().end());
 
-        if (pos == in.buffer().end())
+        if (pos > in.buffer().end())
+                throw Exception("Position in buffer is out of bounds. There must be a bug.", ErrorCodes::LOGICAL_ERROR);
+        else if (pos == in.buffer().end())
             continue;
-
+        else if (*pos == '\\')
-        if (*pos == '\\')
         {
             ++pos;
             if (loadAtPosition(in, memory, pos))

tests/config/config.d/test_keeper_port.xml

@@ -6,6 +6,8 @@
         <coordination_settings>
             <operation_timeout_ms>10000</operation_timeout_ms>
             <session_timeout_ms>30000</session_timeout_ms>
+            <snapshot_distance>0</snapshot_distance>
+            <reserved_log_items>0</reserved_log_items>
         </coordination_settings>
 
         <raft_configuration>

tests/integration/test_testkeeper_back_to_back/test.py

@@ -29,8 +29,8 @@ def get_fake_zk():
         def reset_last_zxid_listener(state):
             print("Fake zk callback called for state", state)
             global _fake_zk_instance
-            # reset last_zxid -- fake server doesn't support it
+            if state != KazooState.CONNECTED:
-            _fake_zk_instance.last_zxid = 0
+                _fake_zk_instance._reset()
 
         _fake_zk_instance.add_listener(reset_last_zxid_listener)
         _fake_zk_instance.start()

tests/queries/0_stateless/01715_table_function_view_fix.sql

@@ -0,0 +1 @@
+SELECT view(SELECT 1); -- { clientError 62 }

tests/queries/1_stateful/00158_cache_dictionary_has.reference

@@ -1,6 +1,6 @@
+100
 6410
-6410
+100
-25323
 25323
-1774655
+100
 1774655

tests/queries/1_stateful/00158_cache_dictionary_has.sql

@@ -6,15 +6,15 @@ CREATE DICTIONARY db_dict.cache_hits
 PRIMARY KEY WatchID
 SOURCE(CLICKHOUSE(HOST 'localhost' PORT tcpPort() USER 'default' TABLE 'hits' PASSWORD '' DB 'test'))
 LIFETIME(MIN 300 MAX 600)
-LAYOUT(CACHE(SIZE_IN_CELLS 100000 QUERY_WAIT_TIMEOUT_MILLISECONDS 600000));
+LAYOUT(CACHE(SIZE_IN_CELLS 100 QUERY_WAIT_TIMEOUT_MILLISECONDS 600000));
 
-SELECT sum(flag) FROM (SELECT dictHas('db_dict.cache_hits', toUInt64(WatchID)) as flag FROM test.hits PREWHERE WatchID % 1400 == 0);
+SELECT sum(flag) FROM (SELECT dictHas('db_dict.cache_hits', toUInt64(WatchID)) as flag FROM test.hits PREWHERE WatchID % 1400 == 0 LIMIT 100);
 SELECT count() from test.hits PREWHERE WatchID % 1400 == 0;
 
-SELECT sum(flag) FROM (SELECT dictHas('db_dict.cache_hits', toUInt64(WatchID)) as flag FROM test.hits PREWHERE WatchID % 350 == 0);
+SELECT sum(flag) FROM (SELECT dictHas('db_dict.cache_hits', toUInt64(WatchID)) as flag FROM test.hits PREWHERE WatchID % 350 == 0 LIMIT 100);
 SELECT count() from test.hits PREWHERE WatchID % 350 == 0;
 
-SELECT sum(flag) FROM (SELECT dictHas('db_dict.cache_hits', toUInt64(WatchID)) as flag FROM test.hits PREWHERE WatchID % 5 == 0);
+SELECT sum(flag) FROM (SELECT dictHas('db_dict.cache_hits', toUInt64(WatchID)) as flag FROM test.hits PREWHERE WatchID % 5 == 0 LIMIT 100);
 SELECT count() from test.hits PREWHERE WatchID % 5 == 0;
 
 DROP DICTIONARY IF EXISTS db_dict.cache_hits;

tests/queries/skip_list.json

@@ -10,7 +10,6 @@
         "00152_insert_different_granularity",
         "00151_replace_partition_with_different_granularity",
         "00157_cache_dictionary",
-        "00992_system_parts_race_condition_zookeeper", /// TODO remove me (alesapin)
         "01193_metadata_loading",
         "01473_event_time_microseconds",
         "01526_max_untracked_memory", /// requires TraceCollector, does not available under sanitizers
@@ -26,7 +25,6 @@
         "memory_profiler",
         "odbc_roundtrip",
         "01103_check_cpu_instructions_at_startup",
-        "00992_system_parts_race_condition_zookeeper", /// TODO remove me (alesapin)
         "01473_event_time_microseconds",
         "01526_max_untracked_memory", /// requires TraceCollector, does not available under sanitizers
         "01193_metadata_loading"
@@ -37,7 +35,6 @@
         "memory_profiler",
         "01103_check_cpu_instructions_at_startup",
         "00900_orc_load",
-        "00992_system_parts_race_condition_zookeeper", /// TODO remove me (alesapin)
         "01473_event_time_microseconds",
         "01526_max_untracked_memory", /// requires TraceCollector, does not available under sanitizers
         "01193_metadata_loading"
@@ -49,7 +46,6 @@
         "01103_check_cpu_instructions_at_startup",
         "01086_odbc_roundtrip", /// can't pass because odbc libraries are not instrumented
         "00877_memory_limit_for_new_delete", /// memory limits don't work correctly under msan because it replaces malloc/free
-        "00992_system_parts_race_condition_zookeeper", /// TODO remove me (alesapin)
         "01473_event_time_microseconds",
         "01526_max_untracked_memory", /// requires TraceCollector, does not available under sanitizers
         "01193_metadata_loading"
@@ -61,7 +57,6 @@
         "00980_alter_settings_race",
         "00834_kill_mutation_replicated_zookeeper",
         "00834_kill_mutation",
-        "00992_system_parts_race_condition_zookeeper", /// TODO remove me (alesapin)
         "01200_mutations_memory_consumption",
         "01103_check_cpu_instructions_at_startup",
         "01037_polygon_dicts_",
@@ -87,7 +82,6 @@
         "00505_secure",
         "00505_shard_secure",
         "odbc_roundtrip",
-        "00992_system_parts_race_condition_zookeeper", /// TODO remove me (alesapin)
         "01103_check_cpu_instructions_at_startup",
         "01114_mysql_database_engine_segfault",
         "00834_cancel_http_readonly_queries_on_client_close",
@@ -101,19 +95,16 @@
         "01455_time_zones"
     ],
     "release-build": [
-        "00992_system_parts_race_condition_zookeeper" /// TODO remove me (alesapin)
     ],
     "database-ordinary": [
         "00604_show_create_database",
         "00609_mv_index_in_in",
         "00510_materizlized_view_and_deduplication_zookeeper",
-        "00738_lock_for_inner_table",
+        "00738_lock_for_inner_table"
-        "00992_system_parts_race_condition_zookeeper" /// TODO remove me (alesapin)
     ],
     "polymorphic-parts": [
         "01508_partition_pruning_long", /// bug, shoud be fixed
-        "01482_move_to_prewhere_and_cast", /// bug, shoud be fixed
+        "01482_move_to_prewhere_and_cast" /// bug, shoud be fixed
-        "00992_system_parts_race_condition_zookeeper" /// TODO remove me (alesapin)
     ],
     "antlr": [
         "00186_very_long_arrays",
@@ -153,7 +144,6 @@
         "00982_array_enumerate_uniq_ranked",
         "00984_materialized_view_to_columns",
         "00988_constraints_replication_zookeeper",
-        "00992_system_parts_race_condition_zookeeper", /// TODO remove me (alesapin)
         "00995_order_by_with_fill",
         "01001_enums_in_in_section",
         "01011_group_uniq_array_memsan",