Merge branch 'master' into async_part_log

.github/workflows/backport_branches.yml

@@ -3,6 +3,9 @@ name: BackportPR
 env:
   # Force the stdout and stderr streams to be unbuffered
   PYTHONUNBUFFERED: 1
+  # Export system tables to ClickHouse Cloud
+  CLICKHOUSE_CI_LOGS_HOST: ${{ secrets.CLICKHOUSE_CI_LOGS_HOST }}
+  CLICKHOUSE_CI_LOGS_PASSWORD: ${{ secrets.CLICKHOUSE_CI_LOGS_PASSWORD }}
 
 on: # yamllint disable-line rule:truthy
   push:

.github/workflows/master.yml

@@ -3,6 +3,9 @@ name: MasterCI
 env:
   # Force the stdout and stderr streams to be unbuffered
   PYTHONUNBUFFERED: 1
+  # Export system tables to ClickHouse Cloud
+  CLICKHOUSE_CI_LOGS_HOST: ${{ secrets.CLICKHOUSE_CI_LOGS_HOST }}
+  CLICKHOUSE_CI_LOGS_PASSWORD: ${{ secrets.CLICKHOUSE_CI_LOGS_PASSWORD }}
 
 on: # yamllint disable-line rule:truthy
   push:

.github/workflows/pull_request.yml

@@ -3,6 +3,9 @@ name: PullRequestCI
 env:
   # Force the stdout and stderr streams to be unbuffered
   PYTHONUNBUFFERED: 1
+  # Export system tables to ClickHouse Cloud
+  CLICKHOUSE_CI_LOGS_HOST: ${{ secrets.CLICKHOUSE_CI_LOGS_HOST }}
+  CLICKHOUSE_CI_LOGS_PASSWORD: ${{ secrets.CLICKHOUSE_CI_LOGS_PASSWORD }}
 
 on:  # yamllint disable-line rule:truthy
   pull_request:

.github/workflows/release_branches.yml

@@ -3,6 +3,9 @@ name: ReleaseBranchCI
 env:
   # Force the stdout and stderr streams to be unbuffered
   PYTHONUNBUFFERED: 1
+  # Export system tables to ClickHouse Cloud
+  CLICKHOUSE_CI_LOGS_HOST: ${{ secrets.CLICKHOUSE_CI_LOGS_HOST }}
+  CLICKHOUSE_CI_LOGS_PASSWORD: ${{ secrets.CLICKHOUSE_CI_LOGS_PASSWORD }}
 
 on: # yamllint disable-line rule:truthy
   push:

docker/packager/packager

@@ -22,7 +22,7 @@ def check_image_exists_locally(image_name: str) -> bool:
         output = subprocess.check_output(
             f"docker images -q {image_name} 2> /dev/null", shell=True
         )
-        return output != ""
+        return output != b""
     except subprocess.CalledProcessError:
         return False
 
@@ -46,7 +46,7 @@ def build_image(image_name: str, filepath: Path) -> None:
     )
 
 
-def pre_build(repo_path: Path, env_variables: List[str]):
+def pre_build(repo_path: Path, env_variables: List[str]) -> None:
     if "WITH_PERFORMANCE=1" in env_variables:
         current_branch = subprocess.check_output(
             "git branch --show-current", shell=True, encoding="utf-8"
@@ -81,8 +81,9 @@ def run_docker_image_with_env(
     env_variables: List[str],
     ch_root: Path,
     ccache_dir: Optional[Path],
-):
+) -> None:
     output_dir.mkdir(parents=True, exist_ok=True)
+
     env_part = " -e ".join(env_variables)
     if env_part:
         env_part = " -e " + env_part
@@ -129,9 +130,10 @@ def parse_env_variables(
     version: str,
     official: bool,
     additional_pkgs: bool,
+    with_profiler: bool,
     with_coverage: bool,
     with_binaries: str,
-):
+) -> List[str]:
     DARWIN_SUFFIX = "-darwin"
     DARWIN_ARM_SUFFIX = "-darwin-aarch64"
     ARM_SUFFIX = "-aarch64"
@@ -322,6 +324,9 @@ def parse_env_variables(
         # utils are not included into clickhouse-bundle, so build everything
         build_target = "all"
 
+    if with_profiler:
+        cmake_flags.append("-DENABLE_BUILD_PROFILING=1")
+
     if with_coverage:
         cmake_flags.append("-DWITH_COVERAGE=1")
 
@@ -416,6 +421,7 @@ def parse_args() -> argparse.Namespace:
     parser.add_argument("--version")
     parser.add_argument("--official", action="store_true")
     parser.add_argument("--additional-pkgs", action="store_true")
+    parser.add_argument("--with-profiler", action="store_true")
     parser.add_argument("--with-coverage", action="store_true")
     parser.add_argument(
         "--with-binaries", choices=("programs", "tests", ""), default=""
@@ -451,7 +457,7 @@ def parse_args() -> argparse.Namespace:
     return args
 
 
-def main():
+def main() -> None:
     logging.basicConfig(level=logging.INFO, format="%(asctime)s %(message)s")
     args = parse_args()
 
@@ -479,6 +485,7 @@ def main():
         args.version,
         args.official,
         args.additional_pkgs,
+        args.with_profiler,
         args.with_coverage,
         args.with_binaries,
     )

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

@@ -6,42 +6,42 @@ sidebar_label: UUID
 
 # UUID
 
-A universally unique identifier (UUID) is a 16-byte number used to identify records. For detailed information about the UUID, see [Wikipedia](https://en.wikipedia.org/wiki/Universally_unique_identifier).
+A Universally Unique Identifier (UUID) is a 16-byte value used to identify records. For detailed information about UUIDs, see [Wikipedia](https://en.wikipedia.org/wiki/Universally_unique_identifier).
 
-The example of UUID type value is represented below:
+While different UUID variants exist (see [here](https://datatracker.ietf.org/doc/html/draft-ietf-uuidrev-rfc4122bis)), ClickHouse does not validate that inserted UUIDs conform to a particular variant. UUIDs are internally treated as a sequence of 16 random bytes with [8-4-4-4-12 representation](https://en.wikipedia.org/wiki/Universally_unique_identifier#Textual_representation) at SQL level.
+
+Example UUID value:
 
 ``` text
 61f0c404-5cb3-11e7-907b-a6006ad3dba0
 ```
 
-If you do not specify the UUID column value when inserting a new record, the UUID value is filled with zero:
+The default UUID is all-zero. It is used, for example, when a new record is inserted but no value for a UUID column is specified:
 
 ``` text
 00000000-0000-0000-0000-000000000000
 ```
 
-## How to Generate
+## Generating UUIDs
 
-To generate the UUID value, ClickHouse provides the [generateUUIDv4](../../sql-reference/functions/uuid-functions.md) function.
+ClickHouse provides the [generateUUIDv4](../../sql-reference/functions/uuid-functions.md) function to generate random UUID version 4 values.
 
 ## Usage Example
 
 **Example 1**
 
-This example demonstrates creating a table with the UUID type column and inserting a value into the table.
+This example demonstrates the creation of a table with a UUID column and the insertion of a value into the table.
 
 ``` sql
 CREATE TABLE t_uuid (x UUID, y String) ENGINE=TinyLog
-```
 
-``` sql
 INSERT INTO t_uuid SELECT generateUUIDv4(), 'Example 1'
-```
 
-``` sql
 SELECT * FROM t_uuid
 ```
 
+Result:
+
 ``` text
 ┌────────────────────────────────────x─┬─y─────────┐
 │ 417ddc5d-e556-4d27-95dd-a34d84e46a50 │ Example 1 │
@@ -50,13 +50,11 @@ SELECT * FROM t_uuid
 
 **Example 2**
 
-In this example, the UUID column value is not specified when inserting a new record.
+In this example, no UUID column value is specified when the record is inserted, i.e. the default UUID value is inserted:
 
 ``` sql
 INSERT INTO t_uuid (y) VALUES ('Example 2')
-```
 
-``` sql
 SELECT * FROM t_uuid
 ```
 

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

@@ -729,6 +729,30 @@ Returns whether string `str` ends with `suffix`.
 endsWith(str, suffix)
 ```
 
+## endsWithUTF8
+
+Returns whether string `str` ends with `suffix`, the difference between `endsWithUTF8` and `endsWith` is that `endsWithUTF8` match `str` and `suffix` by UTF-8 characters.
+
+**Syntax**
+
+```sql
+endsWithUTF8(str, suffix)
+```
+
+**Example**
+
+``` sql
+SELECT endsWithUTF8('中国', '\xbd'), endsWith('中国', '\xbd')
+```
+
+Result:
+
+```result
+┌─endsWithUTF8('中国', '½')─┬─endsWith('中国', '½')─┐
+│                        0 │                    1 │
+└──────────────────────────┴──────────────────────┘
+```
+
 ## startsWith
 
 Returns whether string `str` starts with `prefix`.
@@ -745,6 +769,25 @@ startsWith(str, prefix)
 SELECT startsWith('Spider-Man', 'Spi');
 ```
 
+## startsWithUTF8
+
+Returns whether string `str` starts with `prefix`, the difference between `startsWithUTF8` and `startsWith` is that `startsWithUTF8` match `str` and `suffix` by UTF-8 characters.
+
+
+**Example**
+
+``` sql
+SELECT startsWithUTF8('中国', '\xe4'), startsWith('中国', '\xe4')
+```
+
+Result:
+
+```result
+┌─startsWithUTF8('中国', '⥩─┬─startsWith('中国', '⥩─┐
+│                          0 │                      1 │
+└────────────────────────────┴────────────────────────┘
+```
+
 ## trim
 
 Removes the specified characters from the start or end of a string. If not specified otherwise, the function removes whitespace (ASCII-character 32).

src/Disks/IO/ReadBufferFromAzureBlobStorage.cpp

@@ -102,6 +102,19 @@ bool ReadBufferFromAzureBlobStorage::nextImpl()
     size_t bytes_read = 0;
 
     size_t sleep_time_with_backoff_milliseconds = 100;
+
+    auto handle_exception = [&, this](const auto & e, size_t i)
+    {
+        LOG_INFO(log, "Exception caught during Azure Read for file {} at attempt {}/{}: {}", path, i + 1, max_single_read_retries, e.Message);
+        if (i + 1 == max_single_read_retries)
+            throw;
+
+        sleepForMilliseconds(sleep_time_with_backoff_milliseconds);
+        sleep_time_with_backoff_milliseconds *= 2;
+        initialized = false;
+        initialize();
+    };
+
     for (size_t i = 0; i < max_single_read_retries; ++i)
     {
         try
@@ -111,16 +124,13 @@ bool ReadBufferFromAzureBlobStorage::nextImpl()
                 read_settings.remote_throttler->add(bytes_read, ProfileEvents::RemoteReadThrottlerBytes, ProfileEvents::RemoteReadThrottlerSleepMicroseconds);
             break;
         }
+        catch (const Azure::Core::Http::TransportException & e)
+        {
+            handle_exception(e, i);
+        }
         catch (const Azure::Storage::StorageException & e)
         {
-            LOG_INFO(log, "Exception caught during Azure Read for file {} at attempt {}: {}", path, i, e.Message);
-            if (i + 1 == max_single_read_retries)
-                throw;
-
-            sleepForMilliseconds(sleep_time_with_backoff_milliseconds);
-            sleep_time_with_backoff_milliseconds *= 2;
-            initialized = false;
-            initialize();
+            handle_exception(e, i);
         }
     }
 
@@ -211,6 +221,17 @@ void ReadBufferFromAzureBlobStorage::initialize()
         blob_client = std::make_unique<Azure::Storage::Blobs::BlobClient>(blob_container_client->GetBlobClient(path));
 
     size_t sleep_time_with_backoff_milliseconds = 100;
+
+    auto handle_exception = [&, this](const auto & e, size_t i)
+    {
+        LOG_INFO(log, "Exception caught during Azure Download for file {} at offset {} at attempt {}/{}: {}", path, offset, i + 1, max_single_download_retries, e.Message);
+        if (i + 1 == max_single_download_retries)
+            throw;
+
+        sleepForMilliseconds(sleep_time_with_backoff_milliseconds);
+        sleep_time_with_backoff_milliseconds *= 2;
+    };
+
     for (size_t i = 0; i < max_single_download_retries; ++i)
     {
         try
@@ -219,14 +240,13 @@ void ReadBufferFromAzureBlobStorage::initialize()
             data_stream = std::move(download_response.Value.BodyStream);
             break;
         }
+        catch (const Azure::Core::Http::TransportException & e)
+        {
+            handle_exception(e, i);
+        }
         catch (const Azure::Core::RequestFailedException & e)
         {
-            LOG_INFO(log, "Exception caught during Azure Download for file {} at offset {} at attempt {} : {}", path, offset, i + 1, e.Message);
-            if (i + 1 == max_single_download_retries)
-                throw;
-
-            sleepForMilliseconds(sleep_time_with_backoff_milliseconds);
-            sleep_time_with_backoff_milliseconds *= 2;
+            handle_exception(e,i);
         }
     }
 

src/Functions/FunctionBinaryArithmetic.h

@@ -1173,21 +1173,8 @@ class FunctionBinaryArithmetic : public IFunction
 
         const auto * left_array_col = typeid_cast<const ColumnArray *>(arguments[0].column.get());
         const auto * right_array_col = typeid_cast<const ColumnArray *>(arguments[1].column.get());
-        const auto & left_offsets = left_array_col->getOffsets();
-        const auto & right_offsets = right_array_col->getOffsets();
-
-        chassert(left_offsets.size() == right_offsets.size() && "Unexpected difference in number of offsets");
-        /// Unpacking non-const arrays and checking sizes of them.
-        for (auto offset_index = 0U; offset_index < left_offsets.size(); ++offset_index)
-        {
-            if (left_offsets[offset_index] != right_offsets[offset_index])
-            {
-                throw Exception(ErrorCodes::SIZES_OF_ARRAYS_DONT_MATCH,
-                "Cannot apply operation for arrays of different sizes. Size of the first argument: {}, size of the second argument: {}",
-                *left_array_col->getOffsets().data(),
-                *right_array_col ->getOffsets().data());
-            }
-        }
+        if (!left_array_col->hasEqualOffsets(*right_array_col))
+            throw Exception(ErrorCodes::SIZES_OF_ARRAYS_DONT_MATCH, "Two arguments for function {} must have equal sizes", getName());
 
         const auto & left_array_type = typeid_cast<const DataTypeArray *>(arguments[0].type.get())->getNestedType();
         new_arguments[0] = {left_array_col->getDataPtr(), left_array_type, arguments[0].name};
@@ -1198,6 +1185,7 @@ class FunctionBinaryArithmetic : public IFunction
         result_array_type = typeid_cast<const DataTypeArray *>(result_type.get())->getNestedType();
 
         size_t rows_count = 0;
+        const auto & left_offsets = left_array_col->getOffsets();
         if (!left_offsets.empty())
             rows_count = left_offsets.back();
         auto res = executeImpl(new_arguments, result_array_type, rows_count);