Merge branch 'master' into add-compression-sorts-optimization

.clang-tidy

@@ -22,6 +22,7 @@ Checks: [
   '-bugprone-exception-escape',
   '-bugprone-forward-declaration-namespace',
   '-bugprone-implicit-widening-of-multiplication-result',
+  '-bugprone-multi-level-implicit-pointer-conversion',
   '-bugprone-narrowing-conversions',
   '-bugprone-not-null-terminated-result',
   '-bugprone-reserved-identifier', # useful but too slow, TODO retry when https://reviews.llvm.org/rG1c282052624f9d0bd273bde0b47b30c96699c6c7 is merged
@@ -98,6 +99,7 @@ Checks: [
   '-modernize-use-nodiscard',
   '-modernize-use-trailing-return-type',
 
+  '-performance-enum-size',
   '-performance-inefficient-string-concatenation',
   '-performance-no-int-to-ptr',
   '-performance-avoid-endl',
@@ -105,6 +107,7 @@ Checks: [
 
   '-portability-simd-intrinsics',
 
+  '-readability-avoid-nested-conditional-operator',
   '-readability-avoid-unconditional-preprocessor-if',
   '-readability-braces-around-statements',
   '-readability-convert-member-functions-to-static',
@@ -118,6 +121,12 @@ Checks: [
   '-readability-magic-numbers',
   '-readability-named-parameter',
   '-readability-redundant-declaration',
+  '-readability-redundant-inline-specifier',
+  '-readability-redundant-member-init', # Useful but triggers another problem. Imagine a struct S with multiple String members. Structs are often instantiated via designated
+        # initializer S s{.s1 = [...], .s2 = [...], [...]}. In this case, compiler warning `missing-field-initializers` requires to specify all members which are not in-struct
+        # initialized (example: s1 in struct S { String s1; String s2{};}; is not in-struct initialized, therefore it must be specified at instantiation time). As explicitly
+        # specifying all members is tedious for large structs, `missing-field-initializers` makes programmers initialize as many members as possible in-struct. Clang-tidy
+        # warning `readability-redundant-member-init` does the opposite thing, both are not compatible with each other.
   '-readability-simplify-boolean-expr',
   '-readability-suspicious-call-argument',
   '-readability-uppercase-literal-suffix',
@@ -125,17 +134,6 @@ Checks: [
 
   '-zircon-*',
 
-  # These are new in clang-18, and we have to sort them out:
-  '-readability-avoid-nested-conditional-operator',
-  '-modernize-use-designated-initializers',
-  '-performance-enum-size',
-  '-readability-redundant-inline-specifier',
-  '-readability-redundant-member-init',
-  '-bugprone-crtp-constructor-accessibility',
-  '-bugprone-suspicious-stringview-data-usage',
-  '-bugprone-multi-level-implicit-pointer-conversion',
-  '-cert-err33-c',
-
   # This is a good check, but clang-tidy crashes, see https://github.com/llvm/llvm-project/issues/91872
   '-modernize-use-constraints',
   # https://github.com/abseil/abseil-cpp/issues/1667

.github/workflows/pull_request.yml

@@ -130,15 +130,21 @@ jobs:
     with:
       stage: Tests_2
       data: ${{ needs.RunConfig.outputs.data }}
+  # stage for jobs that do not prohibit merge
+  Tests_3:
+    needs: [RunConfig, Tests_1, Tests_2]
+    if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).stages_data.stages_to_do, 'Tests_3') }}
+    uses: ./.github/workflows/reusable_test_stage.yml
+    with:
+      stage: Tests_3
+      data: ${{ needs.RunConfig.outputs.data }}
 
   ################################# Reports #################################
-  # Reports should by run even if Builds_1/2 fail, so put them separatly in wf (not in Tests_1/2)
+  # Reports should by run even if Builds_1/2 fail, so put them separately in wf (not in Tests_1/2)
   Builds_1_Report:
     # run report check for failed builds to indicate the CI error
-    if: ${{ !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'ClickHouse build check') }}
-    needs:
-      - RunConfig
-      - Builds_1
+    if: ${{ !cancelled() && needs.StyleCheck.result == 'success' && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'ClickHouse build check') }}
+    needs: [RunConfig, StyleCheck, Builds_1]
     uses: ./.github/workflows/reusable_test.yml
     with:
       test_name: ClickHouse build check
@@ -146,25 +152,39 @@ jobs:
       data: ${{ needs.RunConfig.outputs.data }}
   Builds_2_Report:
     # run report check for failed builds to indicate the CI error
-    if: ${{ !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'ClickHouse special build check') }}
-    needs:
-      - RunConfig
-      - Builds_2
+    if: ${{ !cancelled() && needs.StyleCheck.result == 'success' && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'ClickHouse special build check') }}
+    needs: [RunConfig, StyleCheck, Builds_2]
     uses: ./.github/workflows/reusable_test.yml
     with:
       test_name: ClickHouse special build check
       runner_type: style-checker-aarch64
       data: ${{ needs.RunConfig.outputs.data }}
 
+  CheckReadyForMerge:
+    if: ${{ !cancelled() && needs.StyleCheck.result == 'success' }}
+    needs: [RunConfig, BuildDockers, StyleCheck, FastTest, Builds_1, Builds_2, Builds_1_Report, Builds_2_Report, Tests_1, Tests_2]
+    runs-on: [self-hosted, style-checker-aarch64]
+    steps:
+      - name: Check out repository code
+        uses: ClickHouse/checkout@v1
+        with:
+          filter: tree:0
+      - name: Check and set merge status
+        run: |
+          cd "$GITHUB_WORKSPACE/tests/ci"
+          python3 merge_pr.py --set-ci-status --wf-status ${{ contains(needs.*.result, 'failure') && 'failure' || 'success' }}
+
   ################################# Stage Final #################################
   #
   FinishCheck:
     if: ${{ !failure() && !cancelled() }}
-    needs: [RunConfig, BuildDockers, StyleCheck, FastTest, Builds_1, Builds_2, Builds_1_Report, Builds_2_Report, Tests_1, Tests_2]
+    needs: [RunConfig, BuildDockers, StyleCheck, FastTest, Builds_1, Builds_2, Builds_1_Report, Builds_2_Report, Tests_1, Tests_2, Tests_3]
     runs-on: [self-hosted, style-checker]
     steps:
       - name: Check out repository code
         uses: ClickHouse/checkout@v1
+        with:
+          filter: tree:0
       - name: Finish label
         run: |
           cd "$GITHUB_WORKSPACE/tests/ci"

CMakeLists.txt

@@ -61,9 +61,11 @@ if (ENABLE_CHECK_HEAVY_BUILDS)
     # set CPU time limit to 1000 seconds
     set (RLIMIT_CPU 1000)
 
-    # Sanitizers are too heavy
-    if (SANITIZE OR SANITIZE_COVERAGE OR WITH_COVERAGE)
-       set (RLIMIT_DATA 10000000000) # 10G
+    # Sanitizers are too heavy. Some architectures too.
+    if (SANITIZE OR SANITIZE_COVERAGE OR WITH_COVERAGE OR ARCH_RISCV64 OR ARCH_LOONGARCH64)
+        # Twice as large
+        set (RLIMIT_DATA 10000000000)
+        set (RLIMIT_AS 20000000000)
     endif()
 
     # For some files currently building RISCV64 might be too slow. TODO: Improve compilation times per file

base/base/cgroupsv2.cpp

@@ -9,11 +9,18 @@
 bool cgroupsV2Enabled()
 {
 #if defined(OS_LINUX)
-    /// This file exists iff the host has cgroups v2 enabled.
-    auto controllers_file = default_cgroups_mount / "cgroup.controllers";
-    if (!std::filesystem::exists(controllers_file))
-        return false;
-    return true;
+    try
+    {
+        /// This file exists iff the host has cgroups v2 enabled.
+        auto controllers_file = default_cgroups_mount / "cgroup.controllers";
+        if (!std::filesystem::exists(controllers_file))
+            return false;
+        return true;
+    }
+    catch (const std::filesystem::filesystem_error &) /// all "underlying OS API errors", typically: permission denied
+    {
+        return false; /// not logging the exception as most callers fall back to cgroups v1
+    }
 #else
     return false;
 #endif

contrib/libunwind

@@ -1 +1 @@
-Subproject commit 854538ce337d631b619010528adff22cd58f9dce
+Subproject commit d6a01c46327e56fd86beb8aaa31591fcd9a6b7df

docker/test/fasttest/run.sh

@@ -160,10 +160,17 @@ function clone_submodules
 
         git submodule sync
         git submodule init
-        # --jobs does not work as fast as real parallel running
-        printf '%s\0' "${SUBMODULES_TO_UPDATE[@]}" | \
-            xargs --max-procs=100 --null --no-run-if-empty --max-args=1 \
-              git submodule update --depth 1 --single-branch
+
+        # Network is unreliable
+        for _ in {1..10}
+        do
+            # --jobs does not work as fast as real parallel running
+            printf '%s\0' "${SUBMODULES_TO_UPDATE[@]}" | \
+                xargs --max-procs=100 --null --no-run-if-empty --max-args=1 \
+                  git submodule update --depth 1 --single-branch && break
+            sleep 1
+        done
+
         git submodule foreach git reset --hard
         git submodule foreach git checkout @ -f
         git submodule foreach git clean -xfd

docs/en/operations/backup.md

@@ -22,7 +22,7 @@ description: In order to effectively mitigate possible human errors, you should
   TEMPORARY TABLE table_name [AS table_name_in_backup] |
   VIEW view_name [AS view_name_in_backup]
   ALL TEMPORARY TABLES [EXCEPT ...] |
-  ALL DATABASES [EXCEPT ...] } [,...]
+  ALL [EXCEPT ...] } [,...]
   [ON CLUSTER 'cluster_name']
   TO|FROM File('<path>/<filename>') | Disk('<disk_name>', '<path>/') | S3('<S3 endpoint>/<path>', '<Access key ID>', '<Secret access key>')
   [SETTINGS base_backup = File('<path>/<filename>') | Disk(...) | S3('<S3 endpoint>/<path>', '<Access key ID>', '<Secret access key>')]

docs/en/operations/storing-data.md

@@ -7,27 +7,27 @@ title: "External Disks for Storing Data"
 
 Data, processed in ClickHouse, is usually stored in the local file system — on the same machine with the ClickHouse server. That requires large-capacity disks, which can be expensive enough. To avoid that you can store the data remotely. Various storages are supported:
 1. [Amazon S3](https://aws.amazon.com/s3/) object storage.
-2. The Hadoop Distributed File System ([HDFS](https://hadoop.apache.org/docs/current/hadoop-project-dist/hadoop-hdfs/HdfsDesign.html))
-3. [Azure Blob Storage](https://azure.microsoft.com/en-us/products/storage/blobs).
+2. [Azure Blob Storage](https://azure.microsoft.com/en-us/products/storage/blobs).
+3. Unsupported: The Hadoop Distributed File System ([HDFS](https://hadoop.apache.org/docs/current/hadoop-project-dist/hadoop-hdfs/HdfsDesign.html))
 
 :::note ClickHouse also has support for external table engines, which are different from external storage option described on this page as they allow to read data stored in some general file format (like Parquet), while on this page we are describing storage configuration for ClickHouse `MergeTree` family or `Log` family tables.
 1. to work with data stored on `Amazon S3` disks, use [S3](/docs/en/engines/table-engines/integrations/s3.md) table engine.
-2. to work with data in the Hadoop Distributed File System — [HDFS](/docs/en/engines/table-engines/integrations/hdfs.md) table engine.
-3. to work with data stored in Azure Blob Storage use [AzureBlobStorage](/docs/en/engines/table-engines/integrations/azureBlobStorage.md) table engine.
+2. to work with data stored in Azure Blob Storage use [AzureBlobStorage](/docs/en/engines/table-engines/integrations/azureBlobStorage.md) table engine.
+3. Unsupported: to work with data in the Hadoop Distributed File System — [HDFS](/docs/en/engines/table-engines/integrations/hdfs.md) table engine.
 :::
 
 ## Configuring external storage {#configuring-external-storage}
 
-[MergeTree](/docs/en/engines/table-engines/mergetree-family/mergetree.md) and [Log](/docs/en/engines/table-engines/log-family/log.md) family table engines can store data to `S3`, `AzureBlobStorage`, `HDFS` using a disk with types `s3`, `azure_blob_storage`, `hdfs` accordingly.
+[MergeTree](/docs/en/engines/table-engines/mergetree-family/mergetree.md) and [Log](/docs/en/engines/table-engines/log-family/log.md) family table engines can store data to `S3`, `AzureBlobStorage`, `HDFS` (unsupported) using a disk with types `s3`, `azure_blob_storage`, `hdfs` (unsupported) accordingly.
 
 Disk configuration requires:
-1. `type` section, equal to one of `s3`, `azure_blob_storage`, `hdfs`, `local_blob_storage`, `web`.
+1. `type` section, equal to one of `s3`, `azure_blob_storage`, `hdfs` (unsupported), `local_blob_storage`, `web`.
 2. Configuration of a specific external storage type.
 
 Starting from 24.1 clickhouse version, it is possible to use a new configuration option.
 It requires to specify:
 1. `type` equal to `object_storage`
-2. `object_storage_type`, equal to one of `s3`, `azure_blob_storage` (or just `azure` from `24.3`), `hdfs`, `local_blob_storage` (or just `local` from `24.3`), `web`.
+2. `object_storage_type`, equal to one of `s3`, `azure_blob_storage` (or just `azure` from `24.3`), `hdfs` (unsupported), `local_blob_storage` (or just `local` from `24.3`), `web`.
 Optionally, `metadata_type` can be specified (it is equal to `local` by default), but it can also be set to `plain`, `web` and, starting from `24.4`, `plain_rewritable`.
 Usage of `plain` metadata type is described in [plain storage section](/docs/en/operations/storing-data.md/#storing-data-on-webserver), `web` metadata type can be used only with `web` object storage type, `local` metadata type stores metadata files locally (each metadata files contains mapping to files in object storage and some additional meta information about them).
 
@@ -328,7 +328,7 @@ Configuration:
 </s3_plain>
 ```
 
-Starting from `24.1` it is possible configure any object storage disk (`s3`, `azure`, `hdfs`, `local`) using `plain` metadata type.
+Starting from `24.1` it is possible configure any object storage disk (`s3`, `azure`, `hdfs` (unsupported), `local`) using `plain` metadata type.
 
 Configuration:
 ``` xml
@@ -428,12 +428,14 @@ Examples of working configurations can be found in integration tests directory (
 Zero-copy replication is disabled by default in ClickHouse version 22.8 and higher.  This feature is not recommended for production use.
 :::
 
-## Using HDFS storage {#hdfs-storage}
+## Using HDFS storage (Unsupported)
 
 In this sample configuration:
-- the disk is of type `hdfs`
+- the disk is of type `hdfs` (unsupported)
 - the data is hosted at `hdfs://hdfs1:9000/clickhouse/`
 
+By the way, HDFS is unsupported and therefore there might be issues when using it. Feel free to make a pull request with the fix if any issue arises.
+
 ```xml
 <clickhouse>
     <storage_configuration>
@@ -464,9 +466,11 @@ In this sample configuration:
 </clickhouse>
 ```
 
+Keep in mind that HDFS may not work in corner cases.
+
 ### Using Data Encryption {#encrypted-virtual-file-system}
 
-You can encrypt the data stored on [S3](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#table_engine-mergetree-s3), or [HDFS](#configuring-hdfs) external disks, or on a local disk. To turn on the encryption mode, in the configuration file you must define a disk with the type `encrypted` and choose a disk on which the data will be saved. An `encrypted` disk ciphers all written files on the fly, and when you read files from an `encrypted` disk it deciphers them automatically. So you can work with an `encrypted` disk like with a normal one.
+You can encrypt the data stored on [S3](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#table_engine-mergetree-s3), or [HDFS](#configuring-hdfs) (unsupported) external disks, or on a local disk. To turn on the encryption mode, in the configuration file you must define a disk with the type `encrypted` and choose a disk on which the data will be saved. An `encrypted` disk ciphers all written files on the fly, and when you read files from an `encrypted` disk it deciphers them automatically. So you can work with an `encrypted` disk like with a normal one.
 
 Example of disk configuration:
 
@@ -529,7 +533,7 @@ Example of disk configuration:
 
 It is possible to configure local cache over disks in storage configuration starting from version 22.3.
 For versions 22.3 - 22.7 cache is supported only for `s3` disk type. For versions >= 22.8 cache is supported for any disk type: S3, Azure, Local, Encrypted, etc.
-For versions >= 23.5 cache is supported only for remote disk types: S3, Azure, HDFS.
+For versions >= 23.5 cache is supported only for remote disk types: S3, Azure, HDFS (unsupported).
 Cache uses `LRU` cache policy.
 
 
@@ -971,7 +975,7 @@ Use [http_max_single_read_retries](/docs/en/operations/settings/settings.md/#htt
 
 ### Zero-copy Replication (not ready for production) {#zero-copy}
 
-Zero-copy replication is possible, but not recommended, with  `S3` and `HDFS` disks. Zero-copy replication means that if the data is stored remotely on several machines and needs to be synchronized, then only the metadata is replicated (paths to the data parts), but not the data itself.
+Zero-copy replication is possible, but not recommended, with  `S3` and `HDFS` (unsupported) disks. Zero-copy replication means that if the data is stored remotely on several machines and needs to be synchronized, then only the metadata is replicated (paths to the data parts), but not the data itself.
 
 :::note Zero-copy replication is not ready for production
 Zero-copy replication is disabled by default in ClickHouse version 22.8 and higher.  This feature is not recommended for production use.

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

@@ -0,0 +1,45 @@
+---
+slug: /en/sql-reference/aggregate-functions/reference/analysis_of_variance
+sidebar_position: 6
+---
+
+# analysisOfVariance
+
+Provides a statistical test for one-way analysis of variance (ANOVA test). It is a test over several groups of normally distributed observations to find out whether all groups have the same mean or not. 
+
+**Syntax**
+
+```sql
+analysisOfVariance(val, group_no)
+```
+
+Aliases: `anova`
+
+**Parameters**
+- `val`: value. 
+- `group_no` : group number that `val` belongs to.
+
+:::note
+Groups are enumerated starting from 0 and there should be at least two groups to perform a test.
+There should be at least one group with the number of observations greater than one.
+:::
+
+**Returned value**
+
+- `(f_statistic, p_value)`. [Tuple](../../data-types/tuple.md)([Float64](../../data-types/float.md), [Float64](../../data-types/float.md)).
+
+**Example**
+
+Query:
+
+```sql
+SELECT analysisOfVariance(number, number % 2) FROM numbers(1048575);
+```
+
+Result:
+
+```response
+┌─analysisOfVariance(number, modulo(number, 2))─┐
+│ (0,1)                                         │
+└───────────────────────────────────────────────┘
+```

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

@@ -37,6 +37,7 @@ Standard aggregate functions:
 
 ClickHouse-specific aggregate functions:
 
+- [analysisOfVariance](/docs/en/sql-reference/aggregate-functions/reference/analysis_of_variance.md)
 - [any](/docs/en/sql-reference/aggregate-functions/reference/any_respect_nulls.md)
 - [anyHeavy](/docs/en/sql-reference/aggregate-functions/reference/anyheavy.md)
 - [anyLast](/docs/en/sql-reference/aggregate-functions/reference/anylast.md)

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

@@ -998,17 +998,170 @@ SELECT version()
 Returns the build ID generated by a compiler for the running ClickHouse server binary.
 If executed in the context of a distributed table, this function generates a normal column with values relevant to each shard. Otherwise it produces a constant value.
 
-## blockNumber()
+## blockNumber
 
-Returns the sequence number of the data block where the row is located.
+Returns a monotonically increasing sequence number of the [block](../../development/architecture.md#block) containing the row.
+The returned block number is updated on a best-effort basis, i.e. it may not be fully accurate.
 
-## rowNumberInBlock() {#rowNumberInBlock}
+**Syntax**
+
+```sql
+blockNumber()
+```
+
+**Returned value**
+
+- Sequence number of the data block where the row is located. [UInt64](../data-types/int-uint.md).
+
+**Example**
+
+Query:
+
+```sql
+SELECT blockNumber()
+FROM
+(
+    SELECT *
+    FROM system.numbers
+    LIMIT 10
+) SETTINGS max_block_size = 2
+```
+
+Result:
+
+```response
+┌─blockNumber()─┐
+│             7 │
+│             7 │
+└───────────────┘
+┌─blockNumber()─┐
+│             8 │
+│             8 │
+└───────────────┘
+┌─blockNumber()─┐
+│             9 │
+│             9 │
+└───────────────┘
+┌─blockNumber()─┐
+│            10 │
+│            10 │
+└───────────────┘
+┌─blockNumber()─┐
+│            11 │
+│            11 │
+└───────────────┘
+```
+
+## rowNumberInBlock {#rowNumberInBlock}
+
+Returns for each [block](../../development/architecture.md#block) processed by `rowNumberInBlock` the number of the current row.
+The returned number starts for each block at 0.
+
+**Syntax**
+
+```sql
+rowNumberInBlock()
+```
+
+**Returned value**
+
+- Ordinal number of the row in the data block starting from 0. [UInt64](../data-types/int-uint.md).
+
+**Example**
+
+Query:
+
+```sql
+SELECT rowNumberInBlock()
+FROM
+(
+    SELECT *
+    FROM system.numbers_mt
+    LIMIT 10
+) SETTINGS max_block_size = 2
+```
+
+Result:
+
+```response
+┌─rowNumberInBlock()─┐
+│                  0 │
+│                  1 │
+└────────────────────┘
+┌─rowNumberInBlock()─┐
+│                  0 │
+│                  1 │
+└────────────────────┘
+┌─rowNumberInBlock()─┐
+│                  0 │
+│                  1 │
+└────────────────────┘
+┌─rowNumberInBlock()─┐
+│                  0 │
+│                  1 │
+└────────────────────┘
+┌─rowNumberInBlock()─┐
+│                  0 │
+│                  1 │
+└────────────────────┘
+```
+
+## rowNumberInAllBlocks
+
+Returns a unique row number for each row processed by `rowNumberInAllBlocks`. The returned numbers start at 0.
+
+**Syntax**
+
+```sql
+rowNumberInAllBlocks()
+```
+
+**Returned value**
+
+- Ordinal number of the row in the data block starting from 0. [UInt64](../data-types/int-uint.md).
+
+**Example**
+
+Query:
+
+```sql
+SELECT rowNumberInAllBlocks()
+FROM
+(
+    SELECT *
+    FROM system.numbers_mt
+    LIMIT 10
+)
+SETTINGS max_block_size = 2
+```
+
+Result:
+
+```response
+┌─rowNumberInAllBlocks()─┐
+│                      0 │
+│                      1 │
+└────────────────────────┘
+┌─rowNumberInAllBlocks()─┐
+│                      4 │
+│                      5 │
+└────────────────────────┘
+┌─rowNumberInAllBlocks()─┐
+│                      2 │
+│                      3 │
+└────────────────────────┘
+┌─rowNumberInAllBlocks()─┐
+│                      6 │
+│                      7 │
+└────────────────────────┘
+┌─rowNumberInAllBlocks()─┐
+│                      8 │
+│                      9 │
+└────────────────────────┘
+```
 
-Returns the ordinal number of the row in the data block. Different data blocks are always recalculated.
 
-## rowNumberInAllBlocks()
 
-Returns the ordinal number of the row in the data block. This function only considers the affected data blocks.
 
 ## neighbor
 

programs/CMakeLists.txt

@@ -162,7 +162,7 @@ if (ARCH_AMD64 AND OS_LINUX AND NOT OS_ANDROID)
     set (HARMFUL_LIB harmful)
 endif ()
 
-target_link_libraries (clickhouse PRIVATE clickhouse_common_io string_utils ${HARMFUL_LIB})
+target_link_libraries (clickhouse PRIVATE clickhouse_common_io ${HARMFUL_LIB})
 target_include_directories (clickhouse PRIVATE ${CMAKE_CURRENT_BINARY_DIR})
 
 if (ENABLE_CLICKHOUSE_KEEPER)

programs/client/CMakeLists.txt

@@ -10,7 +10,6 @@ set (CLICKHOUSE_CLIENT_LINK
         clickhouse_common_io
         clickhouse_functions
         clickhouse_parsers
-        string_utils
 )
 
 if (TARGET ch_rust::skim)

programs/format/Format.cpp

@@ -15,7 +15,7 @@
 #include <Parsers/obfuscateQueries.h>
 #include <Parsers/parseQuery.h>
 #include <Common/ErrorCodes.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/TerminalSize.h>
 #include <Core/BaseSettingsProgramOptions.h>
 

programs/git-import/git-import.cpp

@@ -14,7 +14,7 @@
 #include <Common/TerminalSize.h>
 #include <Common/Exception.h>
 #include <Common/SipHash.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/ShellCommand.h>
 #include <Common/re2.h>
 #include <base/find_symbols.h>

programs/keeper/clickhouse-keeper.cpp

@@ -1,4 +1,4 @@
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include "config_tools.h"
 
 

programs/library-bridge/ExternalDictionaryLibraryUtils.h

@@ -1,6 +1,6 @@
 #pragma once
 
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Core/Block.h>
 #include <base/range.h>
 

programs/main.cpp

@@ -15,7 +15,7 @@
 
 #include "config_tools.h"
 
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/getHashOfLoadedBinary.h>
 #include <Common/IO.h>
 

programs/obfuscator/Obfuscator.cpp

@@ -19,7 +19,7 @@
 #include <Processors/LimitTransform.h>
 #include <Common/SipHash.h>
 #include <Common/UTF8Helpers.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/HashTable/HashMap.h>
 #include <Common/typeid_cast.h>
 #include <Common/assert_cast.h>

programs/odbc-bridge/validateODBCConnectionString.cpp

@@ -4,7 +4,7 @@
 #include <Poco/String.h>
 #include <base/find_symbols.h>
 #include <Common/Exception.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include "validateODBCConnectionString.h"
 
 

programs/server/CMakeLists.txt

@@ -13,7 +13,6 @@ set (CLICKHOUSE_SERVER_LINK
         clickhouse_parsers
         clickhouse_storages_system
         clickhouse_table_functions
-        string_utils
 
     ${LINK_RESOURCE_LIB}
 

src/Access/User.cpp

@@ -1,5 +1,5 @@
 #include <Access/User.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Core/Protocol.h>
 #include <base/insertAtEnd.h>
 

src/Access/UsersConfigAccessStorage.cpp

@@ -10,7 +10,7 @@
 #include <Dictionaries/IDictionary.h>
 #include <Common/Config/ConfigReloader.h>
 #include <Common/SSHWrapper.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/quoteString.h>
 #include <Common/transformEndianness.h>
 #include <Core/Settings.h>

src/AggregateFunctions/Combinators/AggregateFunctionCombinatorFactory.cpp

@@ -1,6 +1,6 @@
 #include "AggregateFunctionCombinatorFactory.h"
 
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 
 namespace DB
 {

src/Analyzer/Passes/AutoFinalOnQueryPass.cpp

@@ -42,7 +42,7 @@ private:
             return;
 
         const auto & storage = table_node ? table_node->getStorage() : table_function_node->getStorage();
-        bool is_final_supported = storage && storage->supportsFinal();
+        bool is_final_supported = storage && !storage->isRemote() && storage->supportsFinal();
         if (!is_final_supported)
             return;
 

src/Analyzer/QueryTreePassManager.cpp

@@ -192,7 +192,7 @@ void QueryTreePassManager::run(QueryTreeNodePtr query_tree_node)
 void QueryTreePassManager::runOnlyResolve(QueryTreeNodePtr query_tree_node)
 {
     // Run only QueryAnalysisPass and GroupingFunctionsResolvePass passes.
-    run(query_tree_node, 2);
+    run(query_tree_node, 3);
 }
 
 void QueryTreePassManager::run(QueryTreeNodePtr query_tree_node, size_t up_to_pass_index)
@@ -249,6 +249,7 @@ void addQueryTreePasses(QueryTreePassManager & manager, bool only_analyze)
 {
     manager.addPass(std::make_unique<QueryAnalysisPass>(only_analyze));
     manager.addPass(std::make_unique<GroupingFunctionsResolvePass>());
+    manager.addPass(std::make_unique<AutoFinalOnQueryPass>());
 
     manager.addPass(std::make_unique<RemoveUnusedProjectionColumnsPass>());
     manager.addPass(std::make_unique<FunctionToSubcolumnsPass>());
@@ -294,7 +295,6 @@ void addQueryTreePasses(QueryTreePassManager & manager, bool only_analyze)
 
     manager.addPass(std::make_unique<LogicalExpressionOptimizerPass>());
 
-    manager.addPass(std::make_unique<AutoFinalOnQueryPass>());
     manager.addPass(std::make_unique<CrossToInnerJoinPass>());
     manager.addPass(std::make_unique<ShardNumColumnToFunctionPass>());
 

src/Backups/BackupIO_AzureBlobStorage.cpp

@@ -36,7 +36,7 @@ BackupReaderAzureBlobStorage::BackupReaderAzureBlobStorage(
     const WriteSettings & write_settings_,
     const ContextPtr & context_)
     : BackupReaderDefault(read_settings_, write_settings_, getLogger("BackupReaderAzureBlobStorage"))
-    , data_source_description{DataSourceType::ObjectStorage, ObjectStorageType::Azure, MetadataStorageType::None, configuration_.getConnectionURLWithContainer(), false, false}
+    , data_source_description{DataSourceType::ObjectStorage, ObjectStorageType::Azure, MetadataStorageType::None, configuration_.getConnectionURL().toString(), false, false}
     , configuration(configuration_)
 {
     auto client_ptr = StorageAzureBlob::createClient(configuration, /* is_read_only */ false);
@@ -47,7 +47,7 @@ BackupReaderAzureBlobStorage::BackupReaderAzureBlobStorage(
         std::move(client_ptr),
         StorageAzureBlob::createSettings(context_),
         configuration.container,
-        configuration.getConnectionURLWithContainer());
+        configuration.getConnectionURL().toString());
 
     client = object_storage->getAzureBlobStorageClient();
     auto settings_copy = *object_storage->getSettings();
@@ -128,7 +128,7 @@ BackupWriterAzureBlobStorage::BackupWriterAzureBlobStorage(
     const ContextPtr & context_,
     bool attempt_to_create_container)
     : BackupWriterDefault(read_settings_, write_settings_, getLogger("BackupWriterAzureBlobStorage"))
-    , data_source_description{DataSourceType::ObjectStorage, ObjectStorageType::Azure, MetadataStorageType::None, configuration_.getConnectionURLWithContainer(), false, false}
+    , data_source_description{DataSourceType::ObjectStorage, ObjectStorageType::Azure, MetadataStorageType::None, configuration_.getConnectionURL().toString(), false, false}
     , configuration(configuration_)
 {
     auto client_ptr = StorageAzureBlob::createClient(configuration, /* is_read_only */ false, attempt_to_create_container);
@@ -138,7 +138,7 @@ BackupWriterAzureBlobStorage::BackupWriterAzureBlobStorage(
                                                           std::move(client_ptr),
                                                           StorageAzureBlob::createSettings(context_),
                                                           configuration_.container,
-                                                          configuration.getConnectionURLWithContainer());
+                                                          configuration_.getConnectionURL().toString());
     client = object_storage->getAzureBlobStorageClient();
     auto settings_copy = *object_storage->getSettings();
     settings_copy.use_native_copy = allow_azure_native_copy;

src/Backups/BackupImpl.cpp

@@ -4,7 +4,7 @@
 #include <Backups/BackupIO.h>
 #include <Backups/IBackupEntry.h>
 #include <Common/ProfileEvents.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <base/hex.h>
 #include <Common/logger_useful.h>
 #include <Common/quoteString.h>

src/Bridge/IBridge.cpp

@@ -6,7 +6,7 @@
 
 #include <Common/ErrorHandlers.h>
 #include <Common/SensitiveDataMasker.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/logger_useful.h>
 #include <Formats/registerFormats.h>
 #include <IO/ReadHelpers.h>

src/CMakeLists.txt

@@ -307,7 +307,6 @@ endif()
 
 target_link_libraries (clickhouse_common_io
         PRIVATE
-            string_utils
             widechar_width
             ${LINK_LIBRARIES_ONLY_ON_X86_64}
         PUBLIC
@@ -320,7 +319,6 @@ target_link_libraries (clickhouse_common_io
 
 target_link_libraries (clickhouse_compression
         PUBLIC
-            string_utils
             pcg_random
             clickhouse_parsers
         PRIVATE
@@ -410,7 +408,6 @@ dbms_target_link_libraries (
         clickhouse_parsers
         ch_contrib::lz4
         Poco::JSON
-        string_utils
     PUBLIC
         boost::system
         clickhouse_common_io
@@ -645,7 +642,6 @@ if (ENABLE_TESTS)
         dbms
         clickhouse_common_config
         clickhouse_common_zookeeper
-        string_utils
         hilite_comparator)
 
     if (TARGET ch_contrib::simdjson)

src/Client/ClientBase.cpp

@@ -18,7 +18,7 @@
 #include <Common/typeid_cast.h>
 #include <Common/TerminalSize.h>
 #include <Common/clearPasswordFromCommandLine.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/filesystemHelpers.h>
 #include <Common/NetException.h>
 #include <Columns/ColumnString.h>

src/Client/Connection.cpp

@@ -20,7 +20,7 @@
 #include <Common/NetException.h>
 #include <Common/CurrentMetrics.h>
 #include <Common/DNSResolver.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/OpenSSLHelpers.h>
 #include <Common/randomSeed.h>
 #include <Common/logger_useful.h>

src/Common/CMakeLists.txt

@@ -1,5 +1,3 @@
-add_subdirectory(StringUtils)
-
 if (ENABLE_BENCHMARKS)
     add_subdirectory(benchmarks)
 endif()

src/Common/Config/CMakeLists.txt

@@ -13,8 +13,6 @@ target_link_libraries(clickhouse_common_config
         clickhouse_common_zookeeper
         common
         Poco::XML
-    PRIVATE
-        string_utils
 )
 
 add_library(clickhouse_common_config_no_zookeeper_log ${SRCS})
@@ -23,8 +21,6 @@ target_link_libraries(clickhouse_common_config_no_zookeeper_log
         clickhouse_common_zookeeper_no_log
         common
         Poco::XML
-    PRIVATE
-        string_utils
 )
 
 if (TARGET ch_contrib::yaml_cpp)

src/Common/Config/ConfigProcessor.cpp

@@ -18,7 +18,7 @@
 #include <Poco/NumberParser.h>
 #include <Common/ZooKeeper/ZooKeeperNodeCache.h>
 #include <Common/ZooKeeper/KeeperException.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/Exception.h>
 #include <Common/XMLUtils.h>
 #include <Common/logger_useful.h>

src/Common/FrequencyHolder.h

@@ -12,7 +12,7 @@
 
 #include <Common/Arena.h>
 #include <Common/HashTable/HashMap.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <IO/ReadBufferFromFile.h>
 #include <IO/ReadBufferFromString.h>
 #include <IO/ReadHelpers.h>

src/Common/HTTPHeaderFilter.cpp

@@ -1,5 +1,5 @@
 #include <Common/HTTPHeaderFilter.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/Exception.h>
 #include <Common/re2.h>
 

src/Common/ProfileEvents.cpp

@@ -360,6 +360,7 @@ The server successfully detected this situation and will download merged part fr
     M(QueryProfilerSignalOverruns, "Number of times we drop processing of a query profiler signal due to overrun plus the number of signals that OS has not delivered due to overrun.") \
     M(QueryProfilerConcurrencyOverruns, "Number of times we drop processing of a query profiler signal due to too many concurrent query profilers in other threads, which may indicate overload.") \
     M(QueryProfilerRuns, "Number of times QueryProfiler had been run.") \
+    M(QueryProfilerErrors, "Invalid memory accesses during asynchronous stack unwinding.") \
     \
     M(CreatedLogEntryForMerge, "Successfully created log entry to merge parts in ReplicatedMergeTree.") \
     M(NotCreatedLogEntryForMerge, "Log entry to merge parts in ReplicatedMergeTree is not created due to concurrent log update by another replica.") \

src/Common/ProxyConfigurationResolverProvider.cpp

@@ -4,7 +4,7 @@
 #include <Common/Exception.h>
 #include <Common/ProxyListConfigurationResolver.h>
 #include <Common/RemoteProxyConfigurationResolver.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/logger_useful.h>
 
 namespace DB

src/Common/ProxyListConfigurationResolver.cpp

@@ -1,6 +1,6 @@
 #include <Common/ProxyListConfigurationResolver.h>
 
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/logger_useful.h>
 #include <Poco/URI.h>
 

src/Common/QueryProfiler.cpp

@@ -12,7 +12,6 @@
 #include <Common/logger_useful.h>
 #include <Common/thread_local_rng.h>
 
-#include <random>
 
 namespace CurrentMetrics
 {
@@ -25,6 +24,7 @@ namespace ProfileEvents
     extern const Event QueryProfilerSignalOverruns;
     extern const Event QueryProfilerConcurrencyOverruns;
     extern const Event QueryProfilerRuns;
+    extern const Event QueryProfilerErrors;
 }
 
 namespace DB
@@ -84,11 +84,29 @@ namespace
 #endif
 
         const auto signal_context = *reinterpret_cast<ucontext_t *>(context);
-        const StackTrace stack_trace(signal_context);
+        std::optional<StackTrace> stack_trace;
+
+#if defined(SANITIZER)
+        constexpr bool sanitizer = true;
+#else
+        constexpr bool sanitizer = false;
+#endif
+
+        asynchronous_stack_unwinding = true;
+        if (sanitizer || 0 == sigsetjmp(asynchronous_stack_unwinding_signal_jump_buffer, 1))
+        {
+            stack_trace.emplace(signal_context);
+        }
+        else
+        {
+            ProfileEvents::incrementNoTrace(ProfileEvents::QueryProfilerErrors);
+        }
+        asynchronous_stack_unwinding = false;
+
+        if (stack_trace)
+            TraceSender::send(trace_type, *stack_trace, {});
 
-        TraceSender::send(trace_type, stack_trace, {});
         ProfileEvents::incrementNoTrace(ProfileEvents::QueryProfilerRuns);
-
         errno = saved_errno;
     }
 

src/Common/RemoteHostFilter.cpp

@@ -1,7 +1,7 @@
 #include <Poco/URI.h>
 #include <Poco/Util/AbstractConfiguration.h>
 #include <Common/RemoteHostFilter.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/Exception.h>
 #include <Common/re2.h>
 #include <IO/WriteHelpers.h>

src/Common/Scheduler/Nodes/DynamicResourceManager.cpp

@@ -5,7 +5,7 @@
 #include <Common/Scheduler/ISchedulerQueue.h>
 
 #include <Common/Exception.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 
 #include <map>
 #include <tuple>

src/Common/SensitiveDataMasker.cpp

@@ -10,7 +10,7 @@
 #include <Common/re2.h>
 
 #include <Common/Exception.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/ProfileEvents.h>
 
 #ifndef NDEBUG

src/Common/StackTrace.cpp

@@ -560,3 +560,7 @@ void StackTrace::dropCache()
     std::lock_guard lock{stacktrace_cache_mutex};
     cacheInstance().clear();
 }
+
+
+thread_local bool asynchronous_stack_unwinding = false;
+thread_local sigjmp_buf asynchronous_stack_unwinding_signal_jump_buffer;

src/Common/StackTrace.h

@@ -8,6 +8,7 @@
 #include <optional>
 #include <functional>
 #include <csignal>
+#include <csetjmp>
 
 #ifdef OS_DARWIN
 // ucontext is not available without _XOPEN_SOURCE
@@ -87,3 +88,8 @@ protected:
 };
 
 std::string signalToErrorMessage(int sig, const siginfo_t & info, const ucontext_t & context);
+
+/// Special handling for errors during asynchronous stack unwinding,
+/// Which is used in Query Profiler
+extern thread_local bool asynchronous_stack_unwinding;
+extern thread_local sigjmp_buf asynchronous_stack_unwinding_signal_jump_buffer;

src/Common/StringSearcher.h

@@ -2,7 +2,7 @@
 
 #include <base/getPageSize.h>
 #include <Common/Exception.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/UTF8Helpers.h>
 #include <Core/Defines.h>
 #include <Poco/Unicode.h>

src/Common/StringUtils.cpp

@@ -0,0 +1,87 @@
+#include <Common/StringUtils.h>
+
+#include <Common/TargetSpecific.h>
+
+#if USE_MULTITARGET_CODE
+#include <immintrin.h>
+#endif
+
+
+namespace impl
+{
+
+bool startsWith(const std::string & s, const char * prefix, size_t prefix_size)
+{
+    return s.size() >= prefix_size && 0 == memcmp(s.data(), prefix, prefix_size);
+}
+
+bool endsWith(const std::string & s, const char * suffix, size_t suffix_size)
+{
+    return s.size() >= suffix_size && 0 == memcmp(s.data() + s.size() - suffix_size, suffix, suffix_size);
+}
+
+}
+
+DECLARE_DEFAULT_CODE(
+bool isAllASCII(const UInt8 * data, size_t size)
+{
+    UInt8 mask = 0;
+    for (size_t i = 0; i < size; ++i)
+        mask |= data[i];
+
+    return !(mask & 0x80);
+})
+
+DECLARE_SSE42_SPECIFIC_CODE(
+/// Copy from https://github.com/lemire/fastvalidate-utf-8/blob/master/include/simdasciicheck.h
+bool isAllASCII(const UInt8 * data, size_t size)
+{
+    __m128i masks = _mm_setzero_si128();
+
+    size_t i = 0;
+    for (; i + 16 <= size; i += 16)
+    {
+        __m128i bytes = _mm_loadu_si128(reinterpret_cast<const __m128i *>(data + i));
+        masks = _mm_or_si128(masks, bytes);
+    }
+    int mask = _mm_movemask_epi8(masks);
+
+    UInt8 tail_mask = 0;
+    for (; i < size; i++)
+        tail_mask |= data[i];
+
+    mask |= (tail_mask & 0x80);
+    return !mask;
+})
+
+DECLARE_AVX2_SPECIFIC_CODE(
+bool isAllASCII(const UInt8 * data, size_t size)
+{
+    __m256i masks = _mm256_setzero_si256();
+
+    size_t i = 0;
+    for (; i + 32 <= size; i += 32)
+    {
+        __m256i bytes = _mm256_loadu_si256(reinterpret_cast<const __m256i *>(data + i));
+        masks = _mm256_or_si256(masks, bytes);
+    }
+    int mask = _mm256_movemask_epi8(masks);
+
+    UInt8 tail_mask = 0;
+    for (; i < size; i++)
+        tail_mask |= data[i];
+
+    mask |= (tail_mask & 0x80);
+    return !mask;
+})
+
+bool isAllASCII(const UInt8 * data, size_t size)
+{
+#if USE_MULTITARGET_CODE
+    if (isArchSupported(DB::TargetArch::AVX2))
+        return TargetSpecific::AVX2::isAllASCII(data, size);
+    if (isArchSupported(DB::TargetArch::SSE42))
+        return TargetSpecific::SSE42::isAllASCII(data, size);
+#endif
+    return TargetSpecific::Default::isAllASCII(data, size);
+}

src/Common/StringUtils.h

@@ -7,8 +7,10 @@
 #include <cstdint>
 #include <type_traits>
 
+#include <base/types.h>
 
-namespace detail
+
+namespace impl
 {
     bool startsWith(const std::string & s, const char * prefix, size_t prefix_size);
     bool endsWith(const std::string & s, const char * suffix, size_t suffix_size);
@@ -17,12 +19,12 @@ namespace detail
 
 inline bool startsWith(const std::string & s, const std::string & prefix)
 {
-    return detail::startsWith(s, prefix.data(), prefix.size());
+    return impl::startsWith(s, prefix.data(), prefix.size());
 }
 
 inline bool endsWith(const std::string & s, const std::string & suffix)
 {
-    return detail::endsWith(s, suffix.data(), suffix.size());
+    return impl::endsWith(s, suffix.data(), suffix.size());
 }
 
 
@@ -30,12 +32,12 @@ inline bool endsWith(const std::string & s, const std::string & suffix)
 /// string that is known at compile time.
 inline bool startsWith(const std::string & s, const char * prefix)
 {
-    return detail::startsWith(s, prefix, strlen(prefix));
+    return impl::startsWith(s, prefix, strlen(prefix));
 }
 
 inline bool endsWith(const std::string & s, const char * suffix)
 {
-    return detail::endsWith(s, suffix, strlen(suffix));
+    return impl::endsWith(s, suffix, strlen(suffix));
 }
 
 /// Given an integer, return the adequate suffix for
@@ -315,6 +317,9 @@ inline void trim(std::string & str, char c = ' ')
     trimLeft(str, c);
 }
 
+/// If all characters in the string are ASCII, return true
+bool isAllASCII(const UInt8 * data, size_t size);
+
 constexpr bool containsGlobs(const std::string & str)
 {
     return str.find_first_of("*?{") != std::string::npos;

src/Common/StringUtils/CMakeLists.txt

@@ -1,8 +0,0 @@
-# These files are located in separate library, because they are used by separate products
-#  in places when no dependency on whole "dbms" library is possible.
-
-include("${ClickHouse_SOURCE_DIR}/cmake/dbms_glob_sources.cmake")
-
-add_headers_and_sources(clickhouse_common_stringutils .)
-
-add_library(string_utils ${clickhouse_common_stringutils_headers} ${clickhouse_common_stringutils_sources})

src/Common/StringUtils/StringUtils.cpp

@@ -1,17 +0,0 @@
-#include "StringUtils.h"
-
-
-namespace detail
-{
-
-bool startsWith(const std::string & s, const char * prefix, size_t prefix_size)
-{
-    return s.size() >= prefix_size && 0 == memcmp(s.data(), prefix, prefix_size);
-}
-
-bool endsWith(const std::string & s, const char * suffix, size_t suffix_size)
-{
-    return s.size() >= suffix_size && 0 == memcmp(s.data() + s.size() - suffix_size, suffix, suffix_size);
-}
-
-}

src/Common/TLDListsHolder.cpp

@@ -1,5 +1,5 @@
 #include <Common/TLDListsHolder.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/logger_useful.h>
 #include <IO/ReadBufferFromFile.h>
 #include <IO/ReadHelpers.h>

src/Common/UTF8Helpers.cpp

@@ -1,14 +1,9 @@
-#include <Common/StringUtils/StringUtils.h>
-#include <Common/TargetSpecific.h>
 #include <Common/UTF8Helpers.h>
+#include <Common/StringUtils.h>
 
 #include <widechar_width.h>
 #include <bit>
 
-#if USE_MULTITARGET_CODE
-#include <immintrin.h>
-#endif
-
 namespace DB
 {
 namespace UTF8
@@ -208,7 +203,6 @@ size_t computeWidthImpl(const UInt8 * data, size_t size, size_t prefix, size_t l
 
 }
 
-
 size_t computeWidth(const UInt8 * data, size_t size, size_t prefix) noexcept
 {
     return computeWidthImpl<Width>(data, size, prefix, 0);
@@ -219,71 +213,5 @@ size_t computeBytesBeforeWidth(const UInt8 * data, size_t size, size_t prefix, s
     return computeWidthImpl<BytesBeforeLimit>(data, size, prefix, limit);
 }
 
-
-DECLARE_DEFAULT_CODE(
-bool isAllASCII(const UInt8 * data, size_t size)
-{
-    UInt8 mask = 0;
-    for (size_t i = 0; i < size; ++i)
-        mask |= data[i];
-
-    return !(mask & 0x80);
-})
-
-DECLARE_SSE42_SPECIFIC_CODE(
-/// Copy from https://github.com/lemire/fastvalidate-utf-8/blob/master/include/simdasciicheck.h
-bool isAllASCII(const UInt8 * data, size_t size)
-{
-    __m128i masks = _mm_setzero_si128();
-
-    size_t i = 0;
-    for (; i + 16 <= size; i += 16)
-    {
-        __m128i bytes = _mm_loadu_si128(reinterpret_cast<const __m128i *>(data + i));
-        masks = _mm_or_si128(masks, bytes);
-    }
-    int mask = _mm_movemask_epi8(masks);
-
-    UInt8 tail_mask = 0;
-    for (; i < size; i++)
-        tail_mask |= data[i];
-
-    mask |= (tail_mask & 0x80);
-    return !mask;
-})
-
-DECLARE_AVX2_SPECIFIC_CODE(
-bool isAllASCII(const UInt8 * data, size_t size)
-{
-    __m256i masks = _mm256_setzero_si256();
-
-    size_t i = 0;
-    for (; i + 32 <= size; i += 32)
-    {
-        __m256i bytes = _mm256_loadu_si256(reinterpret_cast<const __m256i *>(data + i));
-        masks = _mm256_or_si256(masks, bytes);
-    }
-    int mask = _mm256_movemask_epi8(masks);
-
-    UInt8 tail_mask = 0;
-    for (; i < size; i++)
-        tail_mask |= data[i];
-
-    mask |= (tail_mask & 0x80);
-    return !mask;
-})
-
-bool isAllASCII(const UInt8* data, size_t size)
-{
-#if USE_MULTITARGET_CODE
-    if (isArchSupported(TargetArch::AVX2))
-        return TargetSpecific::AVX2::isAllASCII(data, size);
-    if (isArchSupported(TargetArch::SSE42))
-        return TargetSpecific::SSE42::isAllASCII(data, size);
-#endif
-    return TargetSpecific::Default::isAllASCII(data, size);
-}
-
-
 }
 }

src/Common/UTF8Helpers.h

@@ -136,10 +136,6 @@ size_t computeWidth(const UInt8 * data, size_t size, size_t prefix = 0) noexcept
   */
 size_t computeBytesBeforeWidth(const UInt8 * data, size_t size, size_t prefix, size_t limit) noexcept;
 
-
-/// If all the characters in the string are ASCII, return true.
-bool isAllASCII(const UInt8* data, size_t size);
-
 }
 
 }

src/Common/Volnitsky.h

@@ -7,7 +7,7 @@
 #include <base/types.h>
 #include <Poco/Unicode.h>
 #include <Common/StringSearcher.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/UTF8Helpers.h>
 #include <base/unaligned.h>
 

src/Common/ZooKeeper/CMakeLists.txt

@@ -12,8 +12,6 @@ target_link_libraries (clickhouse_common_zookeeper
         clickhouse_common_io
         clickhouse_compression
         common
-    PRIVATE
-        string_utils
 )
 
 # for examples -- no logging (to avoid extra dependencies)
@@ -23,8 +21,6 @@ target_link_libraries (clickhouse_common_zookeeper_no_log
         clickhouse_common_io
         clickhouse_compression
         common
-    PRIVATE
-        string_utils
 )
 if (ENABLE_EXAMPLES)
     add_subdirectory(examples)

src/Common/ZooKeeper/TestKeeper.cpp

@@ -1,7 +1,7 @@
 #include "Common/ZooKeeper/IKeeper.h"
 #include <Common/ZooKeeper/TestKeeper.h>
 #include <Common/setThreadName.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <base/types.h>
 #include <functional>
 

src/Common/ZooKeeper/ZooKeeper.cpp

@@ -19,7 +19,7 @@
 #include <Core/ServerUUID.h>
 #include "Common/ZooKeeper/IKeeper.h"
 #include <Common/DNSResolver.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/Exception.h>
 
 #include <Poco/Net/NetException.h>

src/Common/ZooKeeper/ZooKeeperArgs.cpp

@@ -4,7 +4,7 @@
 #include <base/getFQDNOrHostName.h>
 #include <Poco/Util/AbstractConfiguration.h>
 #include <Common/isLocalAddress.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Poco/String.h>
 
 namespace DB

src/Common/ZooKeeper/examples/CMakeLists.txt

@@ -7,7 +7,6 @@ clickhouse_add_executable(zkutil_test_commands_new_lib zkutil_test_commands_new_
 target_link_libraries(zkutil_test_commands_new_lib PRIVATE
     clickhouse_common_zookeeper_no_log
     clickhouse_compression
-    string_utils
     dbms)
 
 clickhouse_add_executable(zkutil_test_async zkutil_test_async.cpp)

src/Common/ZooKeeper/examples/zkutil_test_commands_new_lib.cpp

@@ -1,7 +1,7 @@
 #include <Poco/ConsoleChannel.h>
 #include <Poco/Logger.h>
 #include <Poco/Event.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/ZooKeeper/ZooKeeperImpl.h>
 #include <Common/typeid_cast.h>
 #include <iostream>

src/Common/escapeForFileName.cpp

@@ -1,5 +1,5 @@
 #include <base/hex.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/escapeForFileName.h>
 
 namespace DB

src/Common/examples/CMakeLists.txt

@@ -87,3 +87,6 @@ if (ENABLE_SSL)
     clickhouse_add_executable (encrypt_decrypt encrypt_decrypt.cpp)
     target_link_libraries (encrypt_decrypt PRIVATE dbms)
 endif()
+
+clickhouse_add_executable (check_pointer_valid check_pointer_valid.cpp)
+target_link_libraries (check_pointer_valid PRIVATE clickhouse_common_io)

src/Common/examples/check_pointer_valid.cpp

@@ -0,0 +1,53 @@
+#include <csetjmp>
+#include <csignal>
+#include <cstring>
+#include <iostream>
+
+
+/// This example demonstrates how is it possible to check if a pointer to memory is readable using a signal handler.
+
+thread_local bool checking_pointer = false;
+thread_local jmp_buf signal_jump_buffer;
+
+
+void signalHandler(int sig, siginfo_t *, void *)
+{
+    if (checking_pointer && sig == SIGSEGV)
+        siglongjmp(signal_jump_buffer, 1);
+}
+
+bool isPointerValid(const void * ptr)
+{
+    checking_pointer = true;
+    if (0 == sigsetjmp(signal_jump_buffer, 1))
+    {
+        char res;
+        memcpy(&res, ptr, 1);
+        __asm__ __volatile__("" :: "r"(res) : "memory");
+        checking_pointer = false;
+        return true;
+    }
+    else
+    {
+        checking_pointer = false;
+        return false;
+    }
+}
+
+int main(int, char **)
+{
+    struct sigaction sa;
+    memset(&sa, 0, sizeof(sa));
+    sa.sa_sigaction = signalHandler;
+    sa.sa_flags = SA_SIGINFO;
+
+    if (sigemptyset(&sa.sa_mask)
+        || sigaddset(&sa.sa_mask, SIGSEGV)
+        || sigaction(SIGSEGV, &sa, nullptr))
+        return 1;
+
+    std::cerr << isPointerValid(reinterpret_cast<const void *>(0x123456789)) << "\n";
+    std::cerr << isPointerValid(&sa) << "\n";
+
+    return 0;
+}

src/Common/format.h

@@ -3,7 +3,7 @@
 #include <base/types.h>
 #include <Common/Exception.h>
 #include <Common/PODArray.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 
 namespace DB
 {

src/Common/formatIPv6.cpp

@@ -1,6 +1,6 @@
 #include <Common/formatIPv6.h>
 #include <base/hex.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 
 #include <base/range.h>
 #include <array>

src/Common/formatIPv6.h

@@ -7,7 +7,7 @@
 #include <base/hex.h>
 #include <base/types.h>
 #include <base/unaligned.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 
 constexpr size_t IPV4_BINARY_LENGTH = 4;
 constexpr size_t IPV6_BINARY_LENGTH = 16;

src/Common/getMappedArea.cpp

@@ -3,7 +3,7 @@
 
 #if defined(OS_LINUX)
 
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <base/hex.h>
 #include <IO/ReadBufferFromFile.h>
 #include <IO/ReadHelpers.h>

src/Common/getMultipleKeysFromConfig.cpp

@@ -1,7 +1,7 @@
 #include <Common/getMultipleKeysFromConfig.h>
 
 #include <Poco/Util/AbstractConfiguration.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 
 namespace DB
 {

src/Coordination/FourLetterCommand.cpp

@@ -8,7 +8,7 @@
 #include <Poco/Path.h>
 #include <Common/getCurrentProcessFDCount.h>
 #include <Common/getMaxFileDescriptorCount.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/config_version.h>
 #include "Coordination/KeeperFeatureFlags.h"
 #include <Coordination/Keeper4LWInfo.h>

src/Coordination/KeeperStorage.cpp

@@ -11,7 +11,7 @@
 #include <Common/ZooKeeper/ZooKeeperCommon.h>
 #include <Common/SipHash.h>
 #include <Common/ZooKeeper/ZooKeeperConstants.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/ZooKeeper/IKeeper.h>
 #include <base/hex.h>
 #include <base/scope_guard.h>

src/Core/SettingsQuirks.cpp

@@ -92,7 +92,7 @@ void applySettingsQuirks(Settings & settings, LoggerPtr log)
 
 void doSettingsSanityCheckClamp(Settings & current_settings, LoggerPtr log)
 {
-    auto getCurrentValue = [&current_settings](const std::string_view name) -> Field
+    auto get_current_value = [&current_settings](const std::string_view name) -> Field
     {
         Field current_value;
         bool has_current_value = current_settings.tryGet(name, current_value);
@@ -100,7 +100,7 @@ void doSettingsSanityCheckClamp(Settings & current_settings, LoggerPtr log)
         return current_value;
     };
 
-    UInt64 max_threads = getCurrentValue("max_threads").get<UInt64>();
+    UInt64 max_threads = get_current_value("max_threads").get<UInt64>();
     UInt64 max_threads_max_value = 256 * getNumberOfPhysicalCPUCores();
     if (max_threads > max_threads_max_value)
     {
@@ -109,7 +109,7 @@ void doSettingsSanityCheckClamp(Settings & current_settings, LoggerPtr log)
         current_settings.set("max_threads", max_threads_max_value);
     }
 
-    constexpr UInt64 max_sane_block_rows_size = 4294967296; // 2^32
+    static constexpr UInt64 max_sane_block_rows_size = 4294967296; // 2^32
     std::unordered_set<String> block_rows_settings{
         "max_block_size",
         "max_insert_block_size",
@@ -120,13 +120,21 @@ void doSettingsSanityCheckClamp(Settings & current_settings, LoggerPtr log)
         "input_format_parquet_max_block_size"};
     for (auto const & setting : block_rows_settings)
     {
-        auto block_size = getCurrentValue(setting).get<UInt64>();
-        if (block_size > max_sane_block_rows_size)
+        if (auto block_size = get_current_value(setting).get<UInt64>();
+            block_size > max_sane_block_rows_size)
         {
             if (log)
                 LOG_WARNING(log, "Sanity check: '{}' value is too high ({}). Reduced to {}", setting, block_size, max_sane_block_rows_size);
             current_settings.set(setting, max_sane_block_rows_size);
         }
     }
+
+    if (auto max_block_size = get_current_value("max_block_size").get<UInt64>(); max_block_size == 0)
+    {
+        if (log)
+            LOG_WARNING(log, "Sanity check: 'max_block_size' cannot be 0. Set to default value {}", DEFAULT_BLOCK_SIZE);
+        current_settings.set("max_block_size", DEFAULT_BLOCK_SIZE);
+    }
 }
+
 }

src/Daemon/BaseDaemon.cpp

@@ -144,6 +144,9 @@ static std::atomic_flag fatal_error_printed;
   */
 static void signalHandler(int sig, siginfo_t * info, void * context)
 {
+    if (asynchronous_stack_unwinding && sig == SIGSEGV)
+        siglongjmp(asynchronous_stack_unwinding_signal_jump_buffer, 1);
+
     DENY_ALLOCATIONS_IN_SCOPE;
     auto saved_errno = errno;   /// We must restore previous value of errno in signal handler.
 
@@ -185,6 +188,7 @@ static void signalHandler(int sig, siginfo_t * info, void * context)
     errno = saved_errno;
 }
 
+
 static bool getenvBool(const char * name)
 {
     bool res = false;

src/DataTypes/DataTypeFactory.cpp

@@ -7,7 +7,7 @@
 #include <Parsers/ASTLiteral.h>
 #include <Common/typeid_cast.h>
 #include <Poco/String.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <IO/WriteHelpers.h>
 #include <Core/Defines.h>
 #include <Common/CurrentThread.h>

src/DataTypes/DataTypeMap.cpp

@@ -1,5 +1,5 @@
 #include <base/map.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Columns/ColumnMap.h>
 #include <Core/Field.h>
 #include <DataTypes/DataTypeMap.h>

src/DataTypes/DataTypeTuple.cpp

@@ -1,6 +1,6 @@
 #include <base/map.h>
 #include <base/range.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Columns/ColumnTuple.h>
 #include <Columns/ColumnConst.h>
 #include <Core/Field.h>

src/DataTypes/NestedUtils.cpp

@@ -3,7 +3,7 @@
 
 #include <Common/typeid_cast.h>
 #include <Common/assert_cast.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include "Columns/IColumn.h"
 
 #include <DataTypes/DataTypeArray.h>

src/DataTypes/Serializations/SerializationMap.cpp

@@ -2,7 +2,7 @@
 #include <DataTypes/Serializations/SerializationNullable.h>
 #include <DataTypes/DataTypeMap.h>
 
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Columns/ColumnMap.h>
 #include <Core/Field.h>
 #include <Formats/FormatSettings.h>

src/Databases/DatabaseOrdinary.cpp

@@ -76,6 +76,20 @@ static void setReplicatedEngine(ASTCreateQuery * create_query, ContextPtr contex
     String replica_path = server_settings.default_replica_path;
     String replica_name = server_settings.default_replica_name;
 
+    /// Check that replica path doesn't exist
+    Macros::MacroExpansionInfo info;
+    StorageID table_id = StorageID(create_query->getDatabase(), create_query->getTable(), create_query->uuid);
+    info.table_id = table_id;
+    info.expand_special_macros_only = false;
+
+    String zookeeper_path = context->getMacros()->expand(replica_path, info);
+    if (context->getZooKeeper()->exists(zookeeper_path))
+        throw Exception(
+            ErrorCodes::LOGICAL_ERROR,
+            "Found existing ZooKeeper path {} while trying to convert table {} to replicated. Table will not be converted.",
+            zookeeper_path, backQuote(table_id.getFullTableName())
+        );
+
     auto args = std::make_shared<ASTExpressionList>();
     args->children.push_back(std::make_shared<ASTLiteral>(replica_path));
     args->children.push_back(std::make_shared<ASTLiteral>(replica_name));

src/Databases/DatabaseReplicated.cpp

@@ -944,6 +944,13 @@ void DatabaseReplicated::recoverLostReplica(const ZooKeeperPtr & current_zookeep
         query_context->setSetting("allow_hyperscan", 1);
         query_context->setSetting("allow_simdjson", 1);
         query_context->setSetting("allow_deprecated_syntax_for_merge_tree", 1);
+        query_context->setSetting("allow_suspicious_primary_key", 1);
+        query_context->setSetting("allow_suspicious_ttl_expressions", 1);
+        query_context->setSetting("allow_suspicious_variant_types", 1);
+        query_context->setSetting("enable_deflate_qpl_codec", 1);
+        query_context->setSetting("enable_zstd_qat_codec", 1);
+        query_context->setSetting("allow_create_index_without_type", 1);
+        query_context->setSetting("allow_experimental_s3queue", 1);
 
         auto txn = std::make_shared<ZooKeeperMetadataTransaction>(current_zookeeper, zookeeper_path, false, "");
         query_context->initZooKeeperMetadataTransaction(txn);

src/Dictionaries/CMakeLists.txt

@@ -39,7 +39,6 @@ target_link_libraries(clickhouse_dictionaries
         Poco::Data
         Poco::MongoDB
         Poco::Redis
-        string_utils
 )
 
 target_link_libraries(clickhouse_dictionaries PUBLIC ch_contrib::abseil_swiss_tables)

src/Dictionaries/DictionaryStructure.cpp

@@ -7,7 +7,7 @@
 #include <IO/WriteHelpers.h>
 #include <IO/Operators.h>
 
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 
 #include <Formats/FormatSettings.h>
 #include <Columns/IColumn.h>

src/Dictionaries/FileDictionarySource.cpp

@@ -1,6 +1,6 @@
 #include "FileDictionarySource.h"
 #include <Common/logger_useful.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/filesystemHelpers.h>
 #include <IO/ReadBufferFromFile.h>
 #include <Interpreters/Context.h>

src/Disks/DiskType.cpp

@@ -32,8 +32,16 @@ bool DataSourceDescription::operator==(const DataSourceDescription & other) cons
 
 bool DataSourceDescription::sameKind(const DataSourceDescription & other) const
 {
-    return std::tie(type, object_storage_type, description)
-        == std::tie(other.type, other.object_storage_type, other.description);
+    std::string_view our_description = description;
+    if (our_description.ends_with('/') && our_description.length() > 1)
+        our_description = our_description.substr(0, our_description.length() - 1);
+
+    std::string_view other_description = other.description;
+    if (other_description.ends_with('/') && other_description.length() > 1)
+        other_description = other_description.substr(0, other_description.length() - 1);
+
+    return std::tie(type, object_storage_type, our_description)
+        == std::tie(other.type, other.object_storage_type, other_description);
 }
 
 std::string DataSourceDescription::toString() const

src/Disks/IVolume.cpp

@@ -1,6 +1,6 @@
 #include "IVolume.h"
 
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/quoteString.h>
 
 #include <memory>

src/Disks/ObjectStorages/AzureBlobStorage/AzureObjectStorage.h

@@ -173,7 +173,9 @@ private:
     MultiVersion<Azure::Storage::Blobs::BlobContainerClient> client;
     MultiVersion<AzureObjectStorageSettings> settings;
     const String object_namespace; /// container + prefix
-    const String description; /// url + container
+
+    /// We use source url without container and prefix as description, because in Azure there are no limitations for operations between different containers.
+    const String description;
 
     LoggerPtr log;
 };

src/Disks/ObjectStorages/ObjectStorageFactory.cpp

@@ -306,14 +306,13 @@ void registerAzureObjectStorage(ObjectStorageFactory & factory)
         bool /* skip_access_check */) -> ObjectStoragePtr
     {
         AzureBlobStorageEndpoint endpoint = processAzureBlobStorageEndpoint(config, config_prefix);
-        std::string endpoint_string = endpoint.getEndpoint();
 
         return createObjectStorage<AzureObjectStorage>(
             ObjectStorageType::Azure, config, config_prefix, name,
             getAzureBlobContainerClient(config, config_prefix),
             getAzureBlobStorageSettings(config, config_prefix, context),
             endpoint.prefix.empty() ? endpoint.container_name : endpoint.container_name + "/" + endpoint.prefix,
-            endpoint.prefix.empty() ? endpoint_string : endpoint_string.substr(0, endpoint_string.length() - endpoint.prefix.length()));
+            endpoint.getEndpointWithoutContainer());
     };
     factory.registerObjectStorageType("azure_blob_storage", creator);
     factory.registerObjectStorageType("azure", creator);

src/Disks/ObjectStorages/S3/S3ObjectStorage.cpp

@@ -20,7 +20,7 @@
 #include <Disks/ObjectStorages/S3/diskSettings.h>
 
 #include <Common/ProfileEvents.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/logger_useful.h>
 #include <Common/MultiVersion.h>
 #include <Common/Macros.h>

src/Disks/ObjectStorages/S3/diskSettings.cpp

@@ -4,7 +4,7 @@
 
 #if USE_AWS_S3
 
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/logger_useful.h>
 #include <Common/Throttler.h>
 #include <Common/ProxyConfigurationResolverProvider.h>

src/Disks/VolumeJBOD.cpp

@@ -1,6 +1,6 @@
 #include "VolumeJBOD.h"
 
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/formatReadable.h>
 #include <Common/quoteString.h>
 #include <Common/logger_useful.h>

src/Formats/CapnProtoSchema.cpp

@@ -9,7 +9,7 @@
 #include <DataTypes/DataTypesNumber.h>
 #include <DataTypes/DataTypeString.h>
 #include <DataTypes/IDataType.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <boost/algorithm/string/join.hpp>
 #include <capnp/schema.h>
 #include <capnp/schema-parser.h>

src/Formats/StructureToCapnProtoSchema.cpp

@@ -7,7 +7,7 @@
 #include <DataTypes/DataTypeMap.h>
 #include <DataTypes/DataTypeTuple.h>
 #include <DataTypes/DataTypeEnum.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/randomSeed.h>
 #include <pcg_random.hpp>
 

src/Formats/StructureToProtobufSchema.cpp

@@ -7,7 +7,7 @@
 #include <DataTypes/DataTypeMap.h>
 #include <DataTypes/DataTypeTuple.h>
 #include <DataTypes/DataTypeEnum.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 
 namespace DB
 {

src/Functions/ExtractString.h

@@ -1,6 +1,6 @@
 #pragma once
 #include <Common/PODArray.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/UTF8Helpers.h>
 
 #include <algorithm>

src/Functions/FunctionTokens.h

@@ -14,7 +14,7 @@
 #include <Interpreters/Context.h>
 #include <IO/WriteHelpers.h>
 #include <Interpreters/castColumn.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Common/assert_cast.h>
 #include <Common/typeid_cast.h>
 

src/Functions/FunctionsProgrammingClassification.cpp

@@ -2,7 +2,7 @@
 
 #if USE_NLP
 
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Functions/FunctionFactory.h>
 #include <Functions/FunctionsTextClassification.h>
 

src/Functions/FunctionsTonalityClassification.cpp

@@ -2,7 +2,7 @@
 
 #if USE_NLP
 
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 #include <Functions/FunctionFactory.h>
 #include <Functions/FunctionsTextClassification.h>
 

src/Functions/JSONPath/Parsers/ParserJSONPathMemberAccess.cpp

@@ -5,7 +5,7 @@
 #include <Parsers/ASTIdentifier_fwd.h>
 #include <Parsers/ExpressionElementParsers.h>
 #include <Parsers/Lexer.h>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 
 namespace DB
 {

src/Functions/LowerUpperUTF8Impl.h

@@ -3,6 +3,7 @@
 #include <Functions/LowerUpperImpl.h>
 #include <base/defines.h>
 #include <Poco/UTF8Encoding.h>
+#include <Common/StringUtils.h>
 #include <Common/UTF8Helpers.h>
 
 #ifdef __SSE2__
@@ -94,7 +95,7 @@ struct LowerUpperUTF8Impl
         if (data.empty())
             return;
 
-        bool all_ascii = UTF8::isAllASCII(data.data(), data.size());
+        bool all_ascii = isAllASCII(data.data(), data.size());
         if (all_ascii)
         {
             LowerUpperImpl<not_case_lower_bound, not_case_upper_bound>::vector(data, offsets, res_data, res_offsets);

src/Functions/URL/domain.h

@@ -3,7 +3,7 @@
 #include "protocol.h"
 #include <base/find_symbols.h>
 #include <cstring>
-#include <Common/StringUtils/StringUtils.h>
+#include <Common/StringUtils.h>
 
 namespace DB
 {