Skip to content

Commit

Permalink
Merge branch 'master' into remote_filter_for_hive
Browse files Browse the repository at this point in the history
  • Loading branch information
taiyang-li committed Mar 31, 2022
2 parents f2779ea + f055d7b commit c11f563
Show file tree
Hide file tree
Showing 73 changed files with 2,040 additions and 1,474 deletions.
10 changes: 0 additions & 10 deletions .github/workflows/master.yml
Original file line number Diff line number Diff line change
Expand Up @@ -149,7 +149,6 @@ jobs:
sudo rm -fr "$TEMP_PATH"
SplitBuildSmokeTest:
needs: [BuilderDebSplitted]
if: ${{ !contains(github.event.pull_request.labels.*.name, 'pr-documentation') && !contains(github.event.pull_request.labels.*.name, 'pr-doc-fix') }}
runs-on: [self-hosted, style-checker]
steps:
- name: Set envs
Expand Down Expand Up @@ -316,7 +315,6 @@ jobs:
sudo rm -fr "$TEMP_PATH" "$CACHES_PATH"
BuilderBinRelease:
needs: [DockerHubPush]
if: ${{ !contains(github.event.pull_request.labels.*.name, 'pr-documentation') && !contains(github.event.pull_request.labels.*.name, 'pr-doc-fix') }}
runs-on: [self-hosted, builder]
steps:
- name: Set envs
Expand Down Expand Up @@ -362,7 +360,6 @@ jobs:
sudo rm -fr "$TEMP_PATH" "$CACHES_PATH"
BuilderBinGCC:
needs: [DockerHubPush]
if: ${{ !contains(github.event.pull_request.labels.*.name, 'pr-documentation') && !contains(github.event.pull_request.labels.*.name, 'pr-doc-fix') }}
runs-on: [self-hosted, builder]
steps:
- name: Set envs
Expand Down Expand Up @@ -636,7 +633,6 @@ jobs:
##########################################################################################
BuilderDebSplitted:
needs: [DockerHubPush]
if: ${{ !contains(github.event.pull_request.labels.*.name, 'pr-documentation') && !contains(github.event.pull_request.labels.*.name, 'pr-doc-fix') }}
runs-on: [self-hosted, builder]
steps:
- name: Set envs
Expand Down Expand Up @@ -682,7 +678,6 @@ jobs:
sudo rm -fr "$TEMP_PATH" "$CACHES_PATH"
BuilderBinTidy:
needs: [DockerHubPush]
if: ${{ !contains(github.event.pull_request.labels.*.name, 'pr-documentation') && !contains(github.event.pull_request.labels.*.name, 'pr-doc-fix') }}
runs-on: [self-hosted, builder]
steps:
- name: Set envs
Expand Down Expand Up @@ -728,7 +723,6 @@ jobs:
sudo rm -fr "$TEMP_PATH" "$CACHES_PATH"
BuilderBinDarwin:
needs: [DockerHubPush]
if: ${{ !contains(github.event.pull_request.labels.*.name, 'pr-documentation') && !contains(github.event.pull_request.labels.*.name, 'pr-doc-fix') }}
runs-on: [self-hosted, builder]
steps:
- name: Set envs
Expand Down Expand Up @@ -774,7 +768,6 @@ jobs:
sudo rm -fr "$TEMP_PATH" "$CACHES_PATH"
BuilderBinAarch64:
needs: [DockerHubPush]
if: ${{ !contains(github.event.pull_request.labels.*.name, 'pr-documentation') && !contains(github.event.pull_request.labels.*.name, 'pr-doc-fix') }}
runs-on: [self-hosted, builder]
steps:
- name: Set envs
Expand Down Expand Up @@ -820,7 +813,6 @@ jobs:
sudo rm -fr "$TEMP_PATH" "$CACHES_PATH"
BuilderBinFreeBSD:
needs: [DockerHubPush]
if: ${{ !contains(github.event.pull_request.labels.*.name, 'pr-documentation') && !contains(github.event.pull_request.labels.*.name, 'pr-doc-fix') }}
runs-on: [self-hosted, builder]
steps:
- name: Set envs
Expand Down Expand Up @@ -866,7 +858,6 @@ jobs:
sudo rm -fr "$TEMP_PATH" "$CACHES_PATH"
BuilderBinDarwinAarch64:
needs: [DockerHubPush]
if: ${{ !contains(github.event.pull_request.labels.*.name, 'pr-documentation') && !contains(github.event.pull_request.labels.*.name, 'pr-doc-fix') }}
runs-on: [self-hosted, builder]
steps:
- name: Set envs
Expand Down Expand Up @@ -912,7 +903,6 @@ jobs:
sudo rm -fr "$TEMP_PATH" "$CACHES_PATH"
BuilderBinPPC64:
needs: [DockerHubPush]
if: ${{ !contains(github.event.pull_request.labels.*.name, 'pr-documentation') && !contains(github.event.pull_request.labels.*.name, 'pr-doc-fix') }}
runs-on: [self-hosted, builder]
steps:
- name: Set envs
Expand Down
2 changes: 1 addition & 1 deletion docker/test/stateful/run.sh
Original file line number Diff line number Diff line change
Expand Up @@ -115,7 +115,7 @@ function run_tests()
fi

set +e
clickhouse-test --testname --shard --zookeeper --check-zookeeper-session --no-stateless --hung-check --print-time \
clickhouse-test -j 2 --testname --shard --zookeeper --check-zookeeper-session --no-stateless --hung-check --print-time \
--skip 00168_parallel_processing_on_replicas "${ADDITIONAL_OPTIONS[@]}" \
"$SKIP_TESTS_OPTION" 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee test_output/test_result.txt

Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,48 @@
---
toc_priority: 108
---

# groupArraySorted {#groupArraySorted}

Returns an array with the first N items in ascending order.

``` sql
groupArraySorted(N)(column)
```

**Arguments**

- `N` – The number of elements to return.

If the parameter is omitted, default value 10 is used.

**Arguments**

- `column` – The value.
- `expr` — Optional. The field or expresion to sort by. If not set values are sorted by themselves.

**Example**

Gets the first 10 numbers:

``` sql
SELECT groupArraySorted(10)(number) FROM numbers(100)
```

``` text
┌─groupArraySorted(10)(number)─┐
│ [0,1,2,3,4,5,6,7,8,9] │
└──────────────────────────────┘
```

Or the last 10:

``` sql
SELECT groupArraySorted(10)(number, -number) FROM numbers(100)
```

``` text
┌─groupArraySorted(10)(number, negate(number))─┐
│ [99,98,97,96,95,94,93,92,91,90] │
└──────────────────────────────────────────────┘
```
Original file line number Diff line number Diff line change
Expand Up @@ -35,6 +35,7 @@ ClickHouse-specific aggregate functions:
- [groupArrayInsertAt](../../../sql-reference/aggregate-functions/reference/grouparrayinsertat.md)
- [groupArrayMovingAvg](../../../sql-reference/aggregate-functions/reference/grouparraymovingavg.md)
- [groupArrayMovingSum](../../../sql-reference/aggregate-functions/reference/grouparraymovingsum.md)
- [groupArraySorted](../../../sql-reference/aggregate-functions/reference/grouparraysorted.md)
- [groupBitAnd](../../../sql-reference/aggregate-functions/reference/groupbitand.md)
- [groupBitOr](../../../sql-reference/aggregate-functions/reference/groupbitor.md)
- [groupBitXor](../../../sql-reference/aggregate-functions/reference/groupbitxor.md)
Expand Down
Empty file.
147 changes: 147 additions & 0 deletions src/AggregateFunctions/AggregateFunctionGroupArraySorted.cpp
Original file line number Diff line number Diff line change
@@ -0,0 +1,147 @@
#include <AggregateFunctions/AggregateFunctionFactory.h>
#include <AggregateFunctions/AggregateFunctionGroupArraySorted.h>
#include <AggregateFunctions/FactoryHelpers.h>
#include <AggregateFunctions/Helpers.h>
#include <DataTypes/DataTypeDate.h>
#include <DataTypes/DataTypeDateTime.h>
#include <DataTypes/DataTypeString.h>
#include <Common/FieldVisitorConvertToNumber.h>


static inline constexpr UInt64 GROUP_SORTED_ARRAY_MAX_SIZE = 0xFFFFFF;
static inline constexpr UInt64 GROUP_SORTED_ARRAY_DEFAULT_THRESHOLD = 10;


namespace DB
{
struct Settings;

namespace ErrorCodes
{
extern const int ARGUMENT_OUT_OF_BOUND;
extern const int ILLEGAL_TYPE_OF_ARGUMENT;
extern const int NUMBER_OF_ARGUMENTS_DOESNT_MATCH;
}


namespace
{
template <typename T, bool expr_sorted, typename TColumnB, bool is_plain_b>
class AggregateFunctionGroupArraySortedNumeric : public AggregateFunctionGroupArraySorted<T, false, expr_sorted, TColumnB, is_plain_b>
{
using AggregateFunctionGroupArraySorted<T, false, expr_sorted, TColumnB, is_plain_b>::AggregateFunctionGroupArraySorted;
};

template <typename T, bool expr_sorted, typename TColumnB, bool is_plain_b>
class AggregateFunctionGroupArraySortedFieldType
: public AggregateFunctionGroupArraySorted<typename T::FieldType, false, expr_sorted, TColumnB, is_plain_b>
{
using AggregateFunctionGroupArraySorted<typename T::FieldType, false, expr_sorted, TColumnB, is_plain_b>::
AggregateFunctionGroupArraySorted;
DataTypePtr getReturnType() const override { return std::make_shared<DataTypeArray>(std::make_shared<T>()); }
};

template <template <typename, bool, typename, bool> class AggregateFunctionTemplate, typename TColumnA, bool expr_sorted, typename TColumnB, bool is_plain_b, typename... TArgs>
AggregateFunctionPtr
createAggregateFunctionGroupArraySortedTypedFinal(TArgs && ... args)
{
return AggregateFunctionPtr(new AggregateFunctionTemplate<TColumnA, expr_sorted, TColumnB, is_plain_b>(std::forward<TArgs>(args)...));
}

template <bool expr_sorted = false, typename TColumnB = UInt64, bool is_plain_b = false>
AggregateFunctionPtr
createAggregateFunctionGroupArraySortedTyped(const DataTypes & argument_types, const Array & params, UInt64 threshold)
{
#define DISPATCH(A, C, B) \
if (which.idx == TypeIndex::A) \
return createAggregateFunctionGroupArraySortedTypedFinal<C, B, expr_sorted, TColumnB, is_plain_b>(threshold, argument_types, params);
#define DISPATCH_NUMERIC(A) DISPATCH(A, AggregateFunctionGroupArraySortedNumeric, A)
WhichDataType which(argument_types[0]);
FOR_NUMERIC_TYPES(DISPATCH_NUMERIC)
DISPATCH(Enum8, AggregateFunctionGroupArraySortedNumeric, Int8)
DISPATCH(Enum16, AggregateFunctionGroupArraySortedNumeric, Int16)
DISPATCH(Date, AggregateFunctionGroupArraySortedFieldType, DataTypeDate)
DISPATCH(DateTime, AggregateFunctionGroupArraySortedFieldType, DataTypeDateTime)
#undef DISPATCH
#undef DISPATCH_NUMERIC

if (argument_types[0]->isValueUnambiguouslyRepresentedInContiguousMemoryRegion())
{
return AggregateFunctionPtr(new AggregateFunctionGroupArraySorted<StringRef, true, expr_sorted, TColumnB, is_plain_b>(
threshold, argument_types, params));
}
else
{
return AggregateFunctionPtr(new AggregateFunctionGroupArraySorted<StringRef, false, expr_sorted, TColumnB, is_plain_b>(
threshold, argument_types, params));
}
}


AggregateFunctionPtr createAggregateFunctionGroupArraySorted(
const std::string & name, const DataTypes & argument_types, const Array & params, const Settings *)
{
UInt64 threshold = GROUP_SORTED_ARRAY_DEFAULT_THRESHOLD;

if (params.size() == 1)
{
UInt64 k = applyVisitor(FieldVisitorConvertToNumber<UInt64>(), params[0]);

if (k > GROUP_SORTED_ARRAY_MAX_SIZE)
throw Exception(
"Too large parameter(s) for aggregate function " + name + ". Maximum: " + toString(GROUP_SORTED_ARRAY_MAX_SIZE),
ErrorCodes::ARGUMENT_OUT_OF_BOUND);

if (k == 0)
throw Exception("Parameter 0 is illegal for aggregate function " + name, ErrorCodes::ARGUMENT_OUT_OF_BOUND);

threshold = k;
}
else if (!params.empty())
{
throw Exception("Aggregate function " + name + " only supports 1 parameter.", ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH);
}

if (argument_types.size() == 2)
{
if (isNumber(argument_types[1]))
{
#define DISPATCH2(A, B) \
if (which.idx == TypeIndex::A) \
return createAggregateFunctionGroupArraySortedTyped<true, B>(argument_types, params, threshold);
#define DISPATCH(A) DISPATCH2(A, A)
WhichDataType which(argument_types[1]);
FOR_NUMERIC_TYPES(DISPATCH)
DISPATCH2(Enum8, Int8)
DISPATCH2(Enum16, Int16)
#undef DISPATCH
#undef DISPATCH2
throw Exception("Invalid parameter type.", ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
}
else if (argument_types[1]->isValueUnambiguouslyRepresentedInContiguousMemoryRegion())
{
return createAggregateFunctionGroupArraySortedTyped<true, StringRef, true>(argument_types, params, threshold);
}
else
{
return createAggregateFunctionGroupArraySortedTyped<true, StringRef, false>(argument_types, params, threshold);
}
}
else if (argument_types.size() == 1)
{
return createAggregateFunctionGroupArraySortedTyped<>(argument_types, params, threshold);
}
else
{
throw Exception(
"Aggregate function " + name + " requires one or two parameters.", ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH);
}
}
}

void registerAggregateFunctionGroupArraySorted(AggregateFunctionFactory & factory)
{
AggregateFunctionProperties properties = {.returns_default_when_only_null = false, .is_order_dependent = true};
factory.registerFunction("groupArraySorted", {createAggregateFunctionGroupArraySorted, properties});
}
}
Loading

0 comments on commit c11f563

Please sign in to comment.