Merge branch 'master' of github.com:ClickHouse/ClickHouse

Author: Blargian

ci/jobs/scripts/check_style/aspell-ignore/en/aspell-dict.txt

@@ -152,6 +152,7 @@ CapContains
 CapUnion
 CapnProto
 CapnProtoEnumComparingMode
+CardSecondary
 CatBoost
 CellAreaM
 CellAreaRads

ci/praktika/info.py

@@ -113,6 +113,10 @@ def is_merge_queue_event(self):
     def is_push_event(self):
         return self.env.EVENT_TYPE == "push"
 
+    @property
+    def is_dispatch_event(self):
+        return self.env.EVENT_TYPE == "dispatch"
+
     @property
     def instance_lifecycle(self):
         return self.env.INSTANCE_LIFE_CYCLE

ci/praktika/job.py

@@ -92,7 +92,7 @@ def parametrize(
                 == len(timeout)
                 == len(provides)
                 == len(requires)
-            ), f"Parametrization lists must be of the same size [{len(parameter)}, {len(runs_on)}, {len(timeout)}, {len(provides)}, {len(requires)}]"
+            ), f"Parametrization lists for job [{self.name}] must be of the same size [{len(parameter)}, {len(runs_on)}, {len(timeout)}, {len(provides)}, {len(requires)}]"
 
             res = []
             for parameter_, runs_on_, timeout_, provides_, requires_ in zip(

ci/praktika/runner.py

@@ -36,7 +36,7 @@ def generate_local_run_environment(workflow, job, pr=None, sha=None):
             BRANCH="branch_name",
             SHA=sha or Shell.get_output("git rev-parse HEAD"),
             PR_NUMBER=pr or -1,
-            EVENT_TYPE="",
+            EVENT_TYPE=workflow.event,
             JOB_OUTPUT_STREAM="",
             EVENT_FILE_PATH="",
             CHANGE_URL="",

ci/praktika/validator.py

@@ -56,7 +56,7 @@ def validate(cls):
             for job in workflow.jobs:
                 cls.evaluate_check(
                     isinstance(job, Job.Config),
-                    f"Invalid job type [{job}]",
+                    f"Invalid job type [{job}]: type [{type(job)}]",
                     workflow.name,
                 )
 
@@ -158,7 +158,7 @@ def validate(cls):
                         artifact.is_s3_artifact()
                     ), f"All artifacts must be of S3 type if enable_cache|enable_html=True, artifact [{artifact.name}], type [{artifact.type}], workflow [{workflow.name}]"
 
-            if workflow.dockers:
+            if workflow.dockers and not workflow.disable_dockers_build:
                 assert (
                     Settings.DOCKERHUB_USERNAME
                 ), f"Settings.DOCKERHUB_USERNAME must be provided if workflow has dockers, workflow [{workflow.name}]"

ci/praktika/workflow.py

@@ -107,3 +107,4 @@ class InputConfig:
             description: str
             is_required: bool
             default_value: str
+            options: Optional[List] = None

ci/praktika/yaml_generator.py

@@ -112,6 +112,14 @@ class Templates:
         default: {DEFAULT_VALUE}\
 """
 
+        TEMPLATE_OPTIONS_INPUT = """
+      {NAME}:
+        description: {DESCRIPTION}
+        type: choice
+        options: {OPTIONS}
+        default: {DEFAULT_VALUE}\
+"""
+
         TEMPLATE_SECRET_CONFIG = """\
       {SECRET_NAME}:
         required: true
@@ -378,12 +386,22 @@ def generate(self):
         # for dispatch workflows only
         dispatch_inputs = ""
         for input_item in self.workflow_config.dispatch_inputs:
-            dispatch_inputs += YamlGenerator.Templates.TEMPLATE_INPUT.format(
-                NAME=input_item.name,
-                DESCRIPTION=input_item.description,
-                IS_REQUIRED="true" if input_item.is_required else "false",
-                DEFAULT_VALUE=input_item.default_value or "''",
-            )
+            if not input_item.options:
+                dispatch_inputs += YamlGenerator.Templates.TEMPLATE_INPUT.format(
+                    NAME=input_item.name,
+                    DESCRIPTION=input_item.description,
+                    IS_REQUIRED="true" if input_item.is_required else "false",
+                    DEFAULT_VALUE=input_item.default_value or "''",
+                )
+            else:
+                dispatch_inputs += (
+                    YamlGenerator.Templates.TEMPLATE_OPTIONS_INPUT.format(
+                        NAME=input_item.name,
+                        DESCRIPTION=input_item.description,
+                        OPTIONS=input_item.options,
+                        DEFAULT_VALUE=input_item.default_value or "''",
+                    )
+                )
 
         if self.workflow_config.event in (
             Workflow.Event.PULL_REQUEST,

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

@@ -8,6 +8,19 @@ slug: /sql-reference/data-types/newjson
 title: 'JSON Data Type'
 ---
 
+import {CardSecondary} from '@clickhouse/click-ui/bundled';
+
+<CardSecondary
+  badgeState="success"
+  badgeText=""
+  description="Check out our JSON best practice guide for examples, advanced features and considerations for using the JSON type."
+  icon="book"
+  infoText="Read more"
+  infoUrl="/docs/best-practices/use-json-where-appropriate"
+  title="Looking for a guide?"
+/>
+<br/>
+
 The `JSON` type stores JavaScript Object Notation (JSON) documents in a single column.
 
 If you want to use the `JSON` type, and for the examples on this page, please use:

docs/en/sql-reference/functions/ip-address-functions.md

@@ -248,21 +248,22 @@ SELECT IPv6CIDRToRange(toIPv6('2001:0db8:0000:85a3:0000:0000:ac1f:8001'), 32);
 
 ## toIPv4 {#toipv4}
 
-Like [`IPv4StringToNum`](#IPv4StringToNum) but takes a string form of IPv4 address and returns value of [IPv4](../data-types/ipv4.md) type.
+Converts a string or a UInt32 form of IPv4 address to [IPv4](../data-types/ipv4.md) type.
+Similar to [`IPv4StringToNum`](#IPv4StringToNum) and [IPv4NumToString](#IPv4NumToString) functions but it supports both string and unsigned integer data types as input arguments.
 
 **Syntax**
 
 ```sql
-toIPv4(string)
+toIPv4(x)
 ```
 
 **Arguments**
 
-- `string` — IPv4 address. [String](../data-types/string.md).
+- `x` — IPv4 address. [`String`](../data-types/string.md), [`UInt8/16/32`](../data-types/int-uint.md).
 
 **Returned value**
 
-- `string` converted to the IPv4 address. [IPv4](../data-types/ipv4.md).
+- IPv4 address. [IPv4](../data-types/ipv4.md).
 
 **Examples**
 
@@ -298,6 +299,21 @@ Result:
 └───────────────────────────────────┴──────────────────────────┘
 ```
 
+
+Query:
+
+```sql
+SELECT toIPv4(2130706433);
+```
+
+Result:
+
+```text
+┌─toIPv4(2130706433)─┐
+│ 127.0.0.1          │
+└────────────────────┘
+```
+
 ## toIPv4OrDefault {#toipv4ordefault}
 
 Same as `toIPv4`, but if the IPv4 address has an invalid format, it returns `0.0.0.0` (0 IPv4), or the provided IPv4 default.
@@ -412,7 +428,7 @@ Result:
 ## toIPv6 {#toipv6}
 
 Converts a string or a UInt128 form of IPv6 address to [IPv6](../data-types/ipv6.md) type. For strings, if the IPv6 address has an invalid format, returns an empty value.
-Similar to [IPv6StringToNum](#ipv6stringtonum) function, which converts IPv6 address to binary format.
+Similar to [IPv6StringToNum](#ipv6stringtonum) and [IPv6NumToString](#ipv6numtostringx) functions, which convert IPv6 address to and from binary format (i.e. `FixedString(16)`).
 
 If the input string contains a valid IPv4 address, then the IPv6 equivalent of the IPv4 address is returned.
 
@@ -425,7 +441,7 @@ toIPv6(UInt128)
 
 **Argument**
 
-- `string` or `UInt128` — IP address. [String](../data-types/string.md).
+- `x` — IP address. [`String`](../data-types/string.md) or [`UInt128`](../data-types/int-uint.md).
 
 **Returned value**
 

docs/en/sql-reference/functions/splitting-merging-functions.md

@@ -6,6 +6,8 @@ slug: /sql-reference/functions/splitting-merging-functions
 title: 'Functions for Splitting Strings'
 ---
 
+import DeprecatedBadge from '@theme/badges/DeprecatedBadge';
+
 # Functions for Splitting Strings
 
 ## splitByChar {#splitbychar}
@@ -347,9 +349,14 @@ Result:
 
 ## ngrams {#ngrams}
 
+<DeprecatedBadge/>
+
+
 Splits a UTF-8 string into n-grams of `ngramsize` symbols.
+This function is deprecated. Prefer to use [tokens](#tokens) with the `ngram` tokenizer.
+The function might be removed at some point in future.
 
-**Syntax** 
+**Syntax**
 
 ```sql
 ngrams(string, ngramsize)
@@ -380,18 +387,23 @@ Result:
 
 ## tokens {#tokens}
 
-Splits a string into tokens using non-alphanumeric ASCII characters as separators.
+Splits a string into tokens using the given tokenizer.
+The default tokenizer uses non-alphanumeric ASCII characters as separators.
 
 **Arguments**
 
-- `input_string` — Any set of bytes represented as the [String](../data-types/string.md) data type object.
+- `value` — The input string. [String](../data-types/string.md) or [FixedString](../data-types/fixedstring.md).
+- `tokenizer` — The tokenizer to use. Valid arguments are `default`, `ngram`, and `noop`. Optional, if not set explicitly, defaults to `default`. [const String](../data-types/string.md)
+- `ngrams` — Only relevant if argument `tokenizer` is `ngram`: An optional parameter which defines the length of the ngrams. If not set explicitly, defaults to `3`. [UInt8](../data-types/int-uint.md).
 
 **Returned value**
 
 - The resulting array of tokens from input string. [Array](../data-types/array.md).
 
 **Example**
 
+Using the default settings:
+
 ```sql
 SELECT tokens('test1,;\\ test2,;\\ test3,;\\   test4') AS tokens;
 ```
@@ -403,3 +415,17 @@ Result:
 │ ['test1','test2','test3','test4'] │
 └───────────────────────────────────┘
 ```
+
+Using the ngram tokenizer with ngram length 3:
+
+```sql
+SELECT tokens('abc def', 'ngram', 3) AS tokens;
+```
+
+Result:
+
+```text
+┌─tokens──────────────────────────┐
+│ ['abc','bc ','c d',' de','def'] │
+└─────────────────────────────────┘
+```