Merge branch 'master' of github.com:yandex/ClickHouse into normalize-bigint

This commit is contained in:
Alexey Milovidov 2021-05-09 18:54:29 +03:00
commit 9753ddc8a0
69 changed files with 7721 additions and 59 deletions

View File

@ -169,8 +169,8 @@ endif ()
option(ENABLE_TESTS "Provide unit_test_dbms target with Google.Test unit tests" ON) option(ENABLE_TESTS "Provide unit_test_dbms target with Google.Test unit tests" ON)
option(ENABLE_EXAMPLES "Build all example programs in 'examples' subdirectories" OFF) option(ENABLE_EXAMPLES "Build all example programs in 'examples' subdirectories" OFF)
if (OS_LINUX AND NOT UNBUNDLED AND MAKE_STATIC_LIBRARIES AND NOT SPLIT_SHARED_LIBRARIES AND CMAKE_VERSION VERSION_GREATER "3.9.0") if (OS_LINUX AND (ARCH_AMD64 OR ARCH_AARCH64) AND NOT UNBUNDLED AND MAKE_STATIC_LIBRARIES AND NOT SPLIT_SHARED_LIBRARIES AND CMAKE_VERSION VERSION_GREATER "3.9.0")
# Only for Linux, x86_64. # Only for Linux, x86_64 or aarch64.
option(GLIBC_COMPATIBILITY "Enable compatibility with older glibc libraries." ON) option(GLIBC_COMPATIBILITY "Enable compatibility with older glibc libraries." ON)
elseif(GLIBC_COMPATIBILITY) elseif(GLIBC_COMPATIBILITY)
message (${RECONFIGURE_MESSAGE_LEVEL} "Glibc compatibility cannot be enabled in current configuration") message (${RECONFIGURE_MESSAGE_LEVEL} "Glibc compatibility cannot be enabled in current configuration")

View File

@ -15,7 +15,7 @@ if (GLIBC_COMPATIBILITY)
add_headers_and_sources(glibc_compatibility .) add_headers_and_sources(glibc_compatibility .)
add_headers_and_sources(glibc_compatibility musl) add_headers_and_sources(glibc_compatibility musl)
if (ARCH_ARM) if (ARCH_AARCH64)
list (APPEND glibc_compatibility_sources musl/aarch64/syscall.s musl/aarch64/longjmp.s) list (APPEND glibc_compatibility_sources musl/aarch64/syscall.s musl/aarch64/longjmp.s)
set (musl_arch_include_dir musl/aarch64) set (musl_arch_include_dir musl/aarch64)
elseif (ARCH_AMD64) elseif (ARCH_AMD64)

View File

@ -35,7 +35,7 @@ RUN apt-get update \
ENV TZ=Europe/Moscow ENV TZ=Europe/Moscow
RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
RUN pip3 install urllib3 testflows==1.6.74 docker-compose docker dicttoxml kazoo tzlocal RUN pip3 install urllib3 testflows==1.6.74 docker-compose docker dicttoxml kazoo tzlocal python-dateutil numpy
ENV DOCKER_CHANNEL stable ENV DOCKER_CHANNEL stable
ENV DOCKER_VERSION 17.09.1-ce ENV DOCKER_VERSION 17.09.1-ce
@ -74,4 +74,3 @@ VOLUME /var/lib/docker
EXPOSE 2375 EXPOSE 2375
ENTRYPOINT ["dockerd-entrypoint.sh"] ENTRYPOINT ["dockerd-entrypoint.sh"]
CMD ["sh", "-c", "python3 regression.py --no-color -o classic --local --clickhouse-binary-path ${CLICKHOUSE_TESTS_SERVER_BIN_PATH} --log test.log ${TESTFLOWS_OPTS}; cat test.log | tfs report results --format json > results.json; /usr/local/bin/process_testflows_result.py || echo -e 'failure\tCannot parse results' > check_status.tsv"] CMD ["sh", "-c", "python3 regression.py --no-color -o classic --local --clickhouse-binary-path ${CLICKHOUSE_TESTS_SERVER_BIN_PATH} --log test.log ${TESTFLOWS_OPTS}; cat test.log | tfs report results --format json > results.json; /usr/local/bin/process_testflows_result.py || echo -e 'failure\tCannot parse results' > check_status.tsv"]

View File

@ -21,6 +21,7 @@ Columns:
- `bytes_allocated` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Amount of RAM allocated for the dictionary. - `bytes_allocated` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Amount of RAM allocated for the dictionary.
- `query_count` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Number of queries since the dictionary was loaded or since the last successful reboot. - `query_count` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Number of queries since the dictionary was loaded or since the last successful reboot.
- `hit_rate` ([Float64](../../sql-reference/data-types/float.md)) — For cache dictionaries, the percentage of uses for which the value was in the cache. - `hit_rate` ([Float64](../../sql-reference/data-types/float.md)) — For cache dictionaries, the percentage of uses for which the value was in the cache.
- `found_rate` ([Float64](../../sql-reference/data-types/float.md)) — The percentage of uses for which the value was found.
- `element_count` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Number of items stored in the dictionary. - `element_count` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Number of items stored in the dictionary.
- `load_factor` ([Float64](../../sql-reference/data-types/float.md)) — Percentage filled in the dictionary (for a hashed dictionary, the percentage filled in the hash table). - `load_factor` ([Float64](../../sql-reference/data-types/float.md)) — Percentage filled in the dictionary (for a hashed dictionary, the percentage filled in the hash table).
- `source` ([String](../../sql-reference/data-types/string.md)) — Text describing the [data source](../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict-sources.md) for the dictionary. - `source` ([String](../../sql-reference/data-types/string.md)) — Text describing the [data source](../../sql-reference/dictionaries/external-dictionaries/external-dicts-dict-sources.md) for the dictionary.
@ -60,4 +61,4 @@ SELECT * FROM system.dictionaries
└──────────┴──────┴────────┴─────────────┴──────┴────────┴──────────────────────────────────────┴─────────────────────┴─────────────────┴─────────────┴──────────┴───────────────┴───────────────────────┴────────────────────────────┴──────────────┴──────────────┴─────────────────────┴──────────────────────────────┘───────────────────────┴────────────────┘ └──────────┴──────┴────────┴─────────────┴──────┴────────┴──────────────────────────────────────┴─────────────────────┴─────────────────┴─────────────┴──────────┴───────────────┴───────────────────────┴────────────────────────────┴──────────────┴──────────────┴─────────────────────┴──────────────────────────────┘───────────────────────┴────────────────┘
``` ```
[Original article](https://clickhouse.tech/docs/en/operations/system_tables/dictionaries) <!--hide--> [Original article](https://clickhouse.tech/docs/en/operations/system_tables/dictionaries) <!--hide-->

View File

@ -176,8 +176,9 @@ Columns CacheDictionary<dictionary_key_type>::getColumns(
ProfileEvents::increment(ProfileEvents::DictCacheKeysExpired, expired_keys_size); ProfileEvents::increment(ProfileEvents::DictCacheKeysExpired, expired_keys_size);
ProfileEvents::increment(ProfileEvents::DictCacheKeysNotFound, not_found_keys_size); ProfileEvents::increment(ProfileEvents::DictCacheKeysNotFound, not_found_keys_size);
query_count.fetch_add(keys.size()); query_count.fetch_add(keys.size(), std::memory_order_relaxed);
hit_count.fetch_add(found_keys_size); hit_count.fetch_add(found_keys_size, std::memory_order_relaxed);
found_count.fetch_add(found_keys_size, std::memory_order_relaxed);
MutableColumns & fetched_columns_from_storage = result_of_fetch_from_storage.fetched_columns; MutableColumns & fetched_columns_from_storage = result_of_fetch_from_storage.fetched_columns;
const PaddedPODArray<KeyState> & key_index_to_state_from_storage = result_of_fetch_from_storage.key_index_to_state; const PaddedPODArray<KeyState> & key_index_to_state_from_storage = result_of_fetch_from_storage.key_index_to_state;
@ -296,8 +297,9 @@ ColumnUInt8::Ptr CacheDictionary<dictionary_key_type>::hasKeys(const Columns & k
ProfileEvents::increment(ProfileEvents::DictCacheKeysExpired, expired_keys_size); ProfileEvents::increment(ProfileEvents::DictCacheKeysExpired, expired_keys_size);
ProfileEvents::increment(ProfileEvents::DictCacheKeysNotFound, not_found_keys_size); ProfileEvents::increment(ProfileEvents::DictCacheKeysNotFound, not_found_keys_size);
query_count.fetch_add(keys.size()); query_count.fetch_add(keys.size(), std::memory_order_relaxed);
hit_count.fetch_add(found_keys_size); hit_count.fetch_add(found_keys_size, std::memory_order_relaxed);
found_count.fetch_add(found_keys_size, std::memory_order_relaxed);
size_t keys_to_update_size = expired_keys_size + not_found_keys_size; size_t keys_to_update_size = expired_keys_size + not_found_keys_size;
auto update_unit = std::make_shared<CacheDictionaryUpdateUnit<dictionary_key_type>>(key_columns, result_of_fetch_from_storage.key_index_to_state, request, keys_to_update_size); auto update_unit = std::make_shared<CacheDictionaryUpdateUnit<dictionary_key_type>>(key_columns, result_of_fetch_from_storage.key_index_to_state, request, keys_to_update_size);
@ -365,8 +367,10 @@ ColumnPtr CacheDictionary<dictionary_key_type>::getHierarchy(
{ {
if (dictionary_key_type == DictionaryKeyType::simple) if (dictionary_key_type == DictionaryKeyType::simple)
{ {
auto result = getKeysHierarchyDefaultImplementation(this, key_column, key_type); size_t keys_found;
auto result = getKeysHierarchyDefaultImplementation(this, key_column, key_type, keys_found);
query_count.fetch_add(key_column->size(), std::memory_order_relaxed); query_count.fetch_add(key_column->size(), std::memory_order_relaxed);
found_count.fetch_add(keys_found, std::memory_order_relaxed);
return result; return result;
} }
else else
@ -381,8 +385,10 @@ ColumnUInt8::Ptr CacheDictionary<dictionary_key_type>::isInHierarchy(
{ {
if (dictionary_key_type == DictionaryKeyType::simple) if (dictionary_key_type == DictionaryKeyType::simple)
{ {
auto result = getKeysIsInHierarchyDefaultImplementation(this, key_column, in_key_column, key_type); size_t keys_found;
auto result = getKeysIsInHierarchyDefaultImplementation(this, key_column, in_key_column, key_type, keys_found);
query_count.fetch_add(key_column->size(), std::memory_order_relaxed); query_count.fetch_add(key_column->size(), std::memory_order_relaxed);
found_count.fetch_add(keys_found, std::memory_order_relaxed);
return result; return result;
} }
else else
@ -668,6 +674,8 @@ void CacheDictionary<dictionary_key_type>::update(CacheDictionaryUpdateUnitPtr<d
ProfileEvents::increment(ProfileEvents::DictCacheKeysRequestedMiss, requested_keys_size - found_keys_size); ProfileEvents::increment(ProfileEvents::DictCacheKeysRequestedMiss, requested_keys_size - found_keys_size);
ProfileEvents::increment(ProfileEvents::DictCacheKeysRequestedFound, found_keys_size); ProfileEvents::increment(ProfileEvents::DictCacheKeysRequestedFound, found_keys_size);
ProfileEvents::increment(ProfileEvents::DictCacheRequests); ProfileEvents::increment(ProfileEvents::DictCacheRequests);
found_count.fetch_add(found_keys_size, std::memory_order_relaxed);
} }
else else
{ {

View File

@ -75,9 +75,20 @@ public:
size_t getQueryCount() const override { return query_count.load(std::memory_order_relaxed); } size_t getQueryCount() const override { return query_count.load(std::memory_order_relaxed); }
double getFoundRate() const override
{
size_t queries = query_count.load(std::memory_order_relaxed);
if (!queries)
return 0;
return static_cast<double>(found_count.load(std::memory_order_relaxed)) / queries;
}
double getHitRate() const override double getHitRate() const override
{ {
return static_cast<double>(hit_count.load(std::memory_order_acquire)) / query_count.load(std::memory_order_relaxed); size_t queries = query_count.load(std::memory_order_relaxed);
if (!queries)
return 0;
return static_cast<double>(hit_count.load(std::memory_order_acquire)) / queries;
} }
bool supportUpdates() const override { return false; } bool supportUpdates() const override { return false; }
@ -204,6 +215,7 @@ private:
mutable std::atomic<size_t> hit_count{0}; mutable std::atomic<size_t> hit_count{0};
mutable std::atomic<size_t> query_count{0}; mutable std::atomic<size_t> query_count{0};
mutable std::atomic<size_t> found_count{0};
}; };

View File

@ -106,6 +106,8 @@ Columns DirectDictionary<dictionary_key_type>::getColumns(
auto result_columns = request.makeAttributesResultColumns(); auto result_columns = request.makeAttributesResultColumns();
size_t keys_found = 0;
for (size_t attribute_index = 0; attribute_index < result_columns.size(); ++attribute_index) for (size_t attribute_index = 0; attribute_index < result_columns.size(); ++attribute_index)
{ {
if (!request.shouldFillResultColumnWithIndex(attribute_index)) if (!request.shouldFillResultColumnWithIndex(attribute_index))
@ -124,7 +126,10 @@ Columns DirectDictionary<dictionary_key_type>::getColumns(
const auto * it = key_to_fetched_index.find(requested_key); const auto * it = key_to_fetched_index.find(requested_key);
if (it) if (it)
{
fetched_column_from_storage->get(it->getMapped(), value_to_insert); fetched_column_from_storage->get(it->getMapped(), value_to_insert);
++keys_found;
}
else else
value_to_insert = default_value_provider.getDefaultValue(requested_key_index); value_to_insert = default_value_provider.getDefaultValue(requested_key_index);
@ -133,6 +138,7 @@ Columns DirectDictionary<dictionary_key_type>::getColumns(
} }
query_count.fetch_add(requested_keys_size, std::memory_order_relaxed); query_count.fetch_add(requested_keys_size, std::memory_order_relaxed);
found_count.fetch_add(keys_found, std::memory_order_relaxed);
return request.filterRequestedColumns(result_columns); return request.filterRequestedColumns(result_columns);
} }
@ -181,6 +187,8 @@ ColumnUInt8::Ptr DirectDictionary<dictionary_key_type>::hasKeys(
stream->readPrefix(); stream->readPrefix();
size_t keys_found = 0;
while (const auto block = stream->read()) while (const auto block = stream->read())
{ {
/// Split into keys columns and attribute columns /// Split into keys columns and attribute columns
@ -198,6 +206,8 @@ ColumnUInt8::Ptr DirectDictionary<dictionary_key_type>::hasKeys(
assert(it); assert(it);
size_t result_data_found_index = it->getMapped(); size_t result_data_found_index = it->getMapped();
/// block_keys_size cannot be used, due to duplicates.
keys_found += !result_data[result_data_found_index];
result_data[result_data_found_index] = true; result_data[result_data_found_index] = true;
block_keys_extractor.rollbackCurrentKey(); block_keys_extractor.rollbackCurrentKey();
@ -209,6 +219,7 @@ ColumnUInt8::Ptr DirectDictionary<dictionary_key_type>::hasKeys(
stream->readSuffix(); stream->readSuffix();
query_count.fetch_add(requested_keys_size, std::memory_order_relaxed); query_count.fetch_add(requested_keys_size, std::memory_order_relaxed);
found_count.fetch_add(keys_found, std::memory_order_relaxed);
return result; return result;
} }
@ -220,8 +231,10 @@ ColumnPtr DirectDictionary<dictionary_key_type>::getHierarchy(
{ {
if (dictionary_key_type == DictionaryKeyType::simple) if (dictionary_key_type == DictionaryKeyType::simple)
{ {
auto result = getKeysHierarchyDefaultImplementation(this, key_column, key_type); size_t keys_found;
auto result = getKeysHierarchyDefaultImplementation(this, key_column, key_type, keys_found);
query_count.fetch_add(key_column->size(), std::memory_order_relaxed); query_count.fetch_add(key_column->size(), std::memory_order_relaxed);
found_count.fetch_add(keys_found, std::memory_order_relaxed);
return result; return result;
} }
else else
@ -236,8 +249,10 @@ ColumnUInt8::Ptr DirectDictionary<dictionary_key_type>::isInHierarchy(
{ {
if (dictionary_key_type == DictionaryKeyType::simple) if (dictionary_key_type == DictionaryKeyType::simple)
{ {
auto result = getKeysIsInHierarchyDefaultImplementation(this, key_column, in_key_column, key_type); size_t keys_found = 0;
auto result = getKeysIsInHierarchyDefaultImplementation(this, key_column, in_key_column, key_type, keys_found);
query_count.fetch_add(key_column->size(), std::memory_order_relaxed); query_count.fetch_add(key_column->size(), std::memory_order_relaxed);
found_count.fetch_add(keys_found, std::memory_order_relaxed);
return result; return result;
} }
else else

View File

@ -42,6 +42,14 @@ public:
size_t getQueryCount() const override { return query_count.load(std::memory_order_relaxed); } size_t getQueryCount() const override { return query_count.load(std::memory_order_relaxed); }
double getFoundRate() const override
{
size_t queries = query_count.load(std::memory_order_relaxed);
if (!queries)
return 0;
return static_cast<double>(found_count.load(std::memory_order_relaxed)) / queries;
}
double getHitRate() const override { return 1.0; } double getHitRate() const override { return 1.0; }
size_t getElementCount() const override { return 0; } size_t getElementCount() const override { return 0; }
@ -101,6 +109,7 @@ private:
const DictionaryLifetime dict_lifetime; const DictionaryLifetime dict_lifetime;
mutable std::atomic<size_t> query_count{0}; mutable std::atomic<size_t> query_count{0};
mutable std::atomic<size_t> found_count{0};
}; };
extern template class DirectDictionary<DictionaryKeyType::simple>; extern template class DirectDictionary<DictionaryKeyType::simple>;

View File

@ -130,13 +130,17 @@ ColumnUInt8::Ptr FlatDictionary::hasKeys(const Columns & key_columns, const Data
auto result = ColumnUInt8::create(keys_size); auto result = ColumnUInt8::create(keys_size);
auto & out = result->getData(); auto & out = result->getData();
size_t keys_found = 0;
for (size_t key_index = 0; key_index < keys_size; ++key_index) for (size_t key_index = 0; key_index < keys_size; ++key_index)
{ {
const auto key = keys[key_index]; const auto key = keys[key_index];
out[key_index] = key < loaded_keys.size() && loaded_keys[key]; out[key_index] = key < loaded_keys.size() && loaded_keys[key];
keys_found += out[key_index];
} }
query_count.fetch_add(keys_size, std::memory_order_relaxed); query_count.fetch_add(keys_size, std::memory_order_relaxed);
found_count.fetch_add(keys_found, std::memory_order_relaxed);
return result; return result;
} }
@ -154,16 +158,20 @@ ColumnPtr FlatDictionary::getHierarchy(ColumnPtr key_column, const DataTypePtr &
auto is_key_valid_func = [&, this](auto & key) { return key < loaded_keys.size() && loaded_keys[key]; }; auto is_key_valid_func = [&, this](auto & key) { return key < loaded_keys.size() && loaded_keys[key]; };
size_t keys_found = 0;
auto get_parent_key_func = [&, this](auto & hierarchy_key) auto get_parent_key_func = [&, this](auto & hierarchy_key)
{ {
bool is_key_valid = hierarchy_key < loaded_keys.size() && loaded_keys[hierarchy_key]; bool is_key_valid = hierarchy_key < loaded_keys.size() && loaded_keys[hierarchy_key];
std::optional<UInt64> result = is_key_valid ? std::make_optional(parent_keys[hierarchy_key]) : std::nullopt; std::optional<UInt64> result = is_key_valid ? std::make_optional(parent_keys[hierarchy_key]) : std::nullopt;
keys_found += result.has_value();
return result; return result;
}; };
auto dictionary_hierarchy_array = getKeysHierarchyArray(keys, null_value, is_key_valid_func, get_parent_key_func); auto dictionary_hierarchy_array = getKeysHierarchyArray(keys, null_value, is_key_valid_func, get_parent_key_func);
query_count.fetch_add(keys.size(), std::memory_order_relaxed); query_count.fetch_add(keys.size(), std::memory_order_relaxed);
found_count.fetch_add(keys_found, std::memory_order_relaxed);
return dictionary_hierarchy_array; return dictionary_hierarchy_array;
} }
@ -187,16 +195,20 @@ ColumnUInt8::Ptr FlatDictionary::isInHierarchy(
auto is_key_valid_func = [&, this](auto & key) { return key < loaded_keys.size() && loaded_keys[key]; }; auto is_key_valid_func = [&, this](auto & key) { return key < loaded_keys.size() && loaded_keys[key]; };
size_t keys_found = 0;
auto get_parent_key_func = [&, this](auto & hierarchy_key) auto get_parent_key_func = [&, this](auto & hierarchy_key)
{ {
bool is_key_valid = hierarchy_key < loaded_keys.size() && loaded_keys[hierarchy_key]; bool is_key_valid = hierarchy_key < loaded_keys.size() && loaded_keys[hierarchy_key];
std::optional<UInt64> result = is_key_valid ? std::make_optional(parent_keys[hierarchy_key]) : std::nullopt; std::optional<UInt64> result = is_key_valid ? std::make_optional(parent_keys[hierarchy_key]) : std::nullopt;
keys_found += result.has_value();
return result; return result;
}; };
auto result = getKeysIsInHierarchyColumn(keys, keys_in, null_value, is_key_valid_func, get_parent_key_func); auto result = getKeysIsInHierarchyColumn(keys, keys_in, null_value, is_key_valid_func, get_parent_key_func);
query_count.fetch_add(keys.size(), std::memory_order_relaxed); query_count.fetch_add(keys.size(), std::memory_order_relaxed);
found_count.fetch_add(keys_found, std::memory_order_relaxed);
return result; return result;
} }
@ -223,9 +235,11 @@ ColumnPtr FlatDictionary::getDescendants(
parent_to_child[parent_key].emplace_back(static_cast<UInt64>(i)); parent_to_child[parent_key].emplace_back(static_cast<UInt64>(i));
} }
auto result = getKeysDescendantsArray(keys, parent_to_child, level); size_t keys_found;
auto result = getKeysDescendantsArray(keys, parent_to_child, level, keys_found);
query_count.fetch_add(keys.size(), std::memory_order_relaxed); query_count.fetch_add(keys.size(), std::memory_order_relaxed);
found_count.fetch_add(keys_found, std::memory_order_relaxed);
return result; return result;
} }
@ -392,17 +406,23 @@ void FlatDictionary::getItemsImpl(
const auto & container = std::get<ContainerType<AttributeType>>(attribute.container); const auto & container = std::get<ContainerType<AttributeType>>(attribute.container);
const auto rows = keys.size(); const auto rows = keys.size();
size_t keys_found = 0;
for (size_t row = 0; row < rows; ++row) for (size_t row = 0; row < rows; ++row)
{ {
const auto key = keys[row]; const auto key = keys[row];
if (key < loaded_keys.size() && loaded_keys[key]) if (key < loaded_keys.size() && loaded_keys[key])
{
set_value(row, static_cast<OutputType>(container[key])); set_value(row, static_cast<OutputType>(container[key]));
++keys_found;
}
else else
set_value(row, default_value_extractor[row]); set_value(row, default_value_extractor[row]);
} }
query_count.fetch_add(rows, std::memory_order_relaxed); query_count.fetch_add(rows, std::memory_order_relaxed);
found_count.fetch_add(keys_found, std::memory_order_relaxed);
} }
template <typename T> template <typename T>

View File

@ -47,6 +47,14 @@ public:
size_t getQueryCount() const override { return query_count.load(std::memory_order_relaxed); } size_t getQueryCount() const override { return query_count.load(std::memory_order_relaxed); }
double getFoundRate() const override
{
size_t queries = query_count.load(std::memory_order_relaxed);
if (!queries)
return 0;
return static_cast<double>(found_count.load(std::memory_order_relaxed)) / queries;
}
double getHitRate() const override { return 1.0; } double getHitRate() const override { return 1.0; }
size_t getElementCount() const override { return element_count; } size_t getElementCount() const override { return element_count; }
@ -191,6 +199,7 @@ private:
size_t element_count = 0; size_t element_count = 0;
size_t bucket_count = 0; size_t bucket_count = 0;
mutable std::atomic<size_t> query_count{0}; mutable std::atomic<size_t> query_count{0};
mutable std::atomic<size_t> found_count{0};
BlockPtr update_field_loaded_block; BlockPtr update_field_loaded_block;
}; };

View File

@ -162,6 +162,7 @@ ColumnUInt8::Ptr HashedDictionary<dictionary_key_type, sparse>::hasKeys(const Co
const auto & attribute = attributes.front(); const auto & attribute = attributes.front();
bool is_attribute_nullable = attribute.is_nullable_set.has_value(); bool is_attribute_nullable = attribute.is_nullable_set.has_value();
size_t keys_found = 0;
getAttributeContainer(0, [&](const auto & container) getAttributeContainer(0, [&](const auto & container)
{ {
@ -171,6 +172,8 @@ ColumnUInt8::Ptr HashedDictionary<dictionary_key_type, sparse>::hasKeys(const Co
out[requested_key_index] = container.find(requested_key) != container.end(); out[requested_key_index] = container.find(requested_key) != container.end();
keys_found += out[requested_key_index];
if (is_attribute_nullable && !out[requested_key_index]) if (is_attribute_nullable && !out[requested_key_index])
out[requested_key_index] = attribute.is_nullable_set->find(requested_key) != nullptr; out[requested_key_index] = attribute.is_nullable_set->find(requested_key) != nullptr;
@ -179,6 +182,7 @@ ColumnUInt8::Ptr HashedDictionary<dictionary_key_type, sparse>::hasKeys(const Co
}); });
query_count.fetch_add(keys_size, std::memory_order_relaxed); query_count.fetch_add(keys_size, std::memory_order_relaxed);
found_count.fetch_add(keys_found, std::memory_order_relaxed);
return result; return result;
} }
@ -201,6 +205,8 @@ ColumnPtr HashedDictionary<dictionary_key_type, sparse>::getHierarchy(ColumnPtr
auto is_key_valid_func = [&](auto & key) { return parent_keys_map.find(key) != parent_keys_map.end(); }; auto is_key_valid_func = [&](auto & key) { return parent_keys_map.find(key) != parent_keys_map.end(); };
size_t keys_found = 0;
auto get_parent_func = [&](auto & hierarchy_key) auto get_parent_func = [&](auto & hierarchy_key)
{ {
std::optional<UInt64> result; std::optional<UInt64> result;
@ -210,12 +216,15 @@ ColumnPtr HashedDictionary<dictionary_key_type, sparse>::getHierarchy(ColumnPtr
if (it != parent_keys_map.end()) if (it != parent_keys_map.end())
result = getValueFromCell(it); result = getValueFromCell(it);
keys_found +=result.has_value();
return result; return result;
}; };
auto dictionary_hierarchy_array = getKeysHierarchyArray(keys, null_value, is_key_valid_func, get_parent_func); auto dictionary_hierarchy_array = getKeysHierarchyArray(keys, null_value, is_key_valid_func, get_parent_func);
query_count.fetch_add(keys.size(), std::memory_order_relaxed); query_count.fetch_add(keys.size(), std::memory_order_relaxed);
found_count.fetch_add(keys_found, std::memory_order_relaxed);
return dictionary_hierarchy_array; return dictionary_hierarchy_array;
} }
@ -247,6 +256,8 @@ ColumnUInt8::Ptr HashedDictionary<dictionary_key_type, sparse>::isInHierarchy(
auto is_key_valid_func = [&](auto & key) { return parent_keys_map.find(key) != parent_keys_map.end(); }; auto is_key_valid_func = [&](auto & key) { return parent_keys_map.find(key) != parent_keys_map.end(); };
size_t keys_found = 0;
auto get_parent_func = [&](auto & hierarchy_key) auto get_parent_func = [&](auto & hierarchy_key)
{ {
std::optional<UInt64> result; std::optional<UInt64> result;
@ -256,12 +267,15 @@ ColumnUInt8::Ptr HashedDictionary<dictionary_key_type, sparse>::isInHierarchy(
if (it != parent_keys_map.end()) if (it != parent_keys_map.end())
result = getValueFromCell(it); result = getValueFromCell(it);
keys_found += result.has_value();
return result; return result;
}; };
auto result = getKeysIsInHierarchyColumn(keys, keys_in, null_value, is_key_valid_func, get_parent_func); auto result = getKeysIsInHierarchyColumn(keys, keys_in, null_value, is_key_valid_func, get_parent_func);
query_count.fetch_add(keys.size(), std::memory_order_relaxed); query_count.fetch_add(keys.size(), std::memory_order_relaxed);
found_count.fetch_add(keys_found, std::memory_order_relaxed);
return result; return result;
} }
@ -290,9 +304,11 @@ ColumnPtr HashedDictionary<dictionary_key_type, sparse>::getDescendants(
for (const auto & [key, value] : parent_keys) for (const auto & [key, value] : parent_keys)
parent_to_child[value].emplace_back(key); parent_to_child[value].emplace_back(key);
auto result = getKeysDescendantsArray(keys, parent_to_child, level); size_t keys_found;
auto result = getKeysDescendantsArray(keys, parent_to_child, level, keys_found);
query_count.fetch_add(keys.size(), std::memory_order_relaxed); query_count.fetch_add(keys.size(), std::memory_order_relaxed);
found_count.fetch_add(keys_found, std::memory_order_relaxed);
return result; return result;
} }
@ -493,6 +509,8 @@ void HashedDictionary<dictionary_key_type, sparse>::getItemsImpl(
bool is_attribute_nullable = attribute.is_nullable_set.has_value(); bool is_attribute_nullable = attribute.is_nullable_set.has_value();
size_t keys_found = 0;
for (size_t key_index = 0; key_index < keys_size; ++key_index) for (size_t key_index = 0; key_index < keys_size; ++key_index)
{ {
auto key = keys_extractor.extractCurrentKey(); auto key = keys_extractor.extractCurrentKey();
@ -500,7 +518,10 @@ void HashedDictionary<dictionary_key_type, sparse>::getItemsImpl(
const auto it = attribute_container.find(key); const auto it = attribute_container.find(key);
if (it != attribute_container.end()) if (it != attribute_container.end())
{
set_value(key_index, getValueFromCell(it)); set_value(key_index, getValueFromCell(it));
++keys_found;
}
else else
{ {
if (is_attribute_nullable && attribute.is_nullable_set->find(key) != nullptr) if (is_attribute_nullable && attribute.is_nullable_set->find(key) != nullptr)
@ -513,6 +534,7 @@ void HashedDictionary<dictionary_key_type, sparse>::getItemsImpl(
} }
query_count.fetch_add(keys_size, std::memory_order_relaxed); query_count.fetch_add(keys_size, std::memory_order_relaxed);
found_count.fetch_add(keys_found, std::memory_order_relaxed);
} }
template <DictionaryKeyType dictionary_key_type, bool sparse> template <DictionaryKeyType dictionary_key_type, bool sparse>

View File

@ -59,6 +59,14 @@ public:
size_t getQueryCount() const override { return query_count.load(std::memory_order_relaxed); } size_t getQueryCount() const override { return query_count.load(std::memory_order_relaxed); }
double getFoundRate() const override
{
size_t queries = query_count.load(std::memory_order_relaxed);
if (!queries)
return 0;
return static_cast<double>(found_count.load(std::memory_order_relaxed)) / queries;
}
double getHitRate() const override { return 1.0; } double getHitRate() const override { return 1.0; }
size_t getElementCount() const override { return element_count; } size_t getElementCount() const override { return element_count; }
@ -227,6 +235,7 @@ private:
size_t element_count = 0; size_t element_count = 0;
size_t bucket_count = 0; size_t bucket_count = 0;
mutable std::atomic<size_t> query_count{0}; mutable std::atomic<size_t> query_count{0};
mutable std::atomic<size_t> found_count{0};
BlockPtr update_field_loaded_block; BlockPtr update_field_loaded_block;
Arena complex_key_arena; Arena complex_key_arena;

View File

@ -84,8 +84,14 @@ namespace
} }
} }
ColumnPtr getKeysHierarchyDefaultImplementation(const IDictionary * dictionary, ColumnPtr key_column, const DataTypePtr & key_type) ColumnPtr getKeysHierarchyDefaultImplementation(
const IDictionary * dictionary,
ColumnPtr key_column,
const DataTypePtr & key_type,
size_t & valid_keys)
{ {
valid_keys = 0;
key_column = key_column->convertToFullColumnIfConst(); key_column = key_column->convertToFullColumnIfConst();
const auto * key_column_typed = checkAndGetColumn<ColumnVector<UInt64>>(*key_column); const auto * key_column_typed = checkAndGetColumn<ColumnVector<UInt64>>(*key_column);
if (!key_column_typed) if (!key_column_typed)
@ -104,6 +110,7 @@ ColumnPtr getKeysHierarchyDefaultImplementation(const IDictionary * dictionary,
{ {
auto it = key_to_parent_key.find(key); auto it = key_to_parent_key.find(key);
std::optional<UInt64> result = (it != nullptr ? std::make_optional(it->getMapped()) : std::nullopt); std::optional<UInt64> result = (it != nullptr ? std::make_optional(it->getMapped()) : std::nullopt);
valid_keys += result.has_value();
return result; return result;
}; };
@ -117,8 +124,11 @@ ColumnUInt8::Ptr getKeysIsInHierarchyDefaultImplementation(
const IDictionary * dictionary, const IDictionary * dictionary,
ColumnPtr key_column, ColumnPtr key_column,
ColumnPtr in_key_column, ColumnPtr in_key_column,
const DataTypePtr & key_type) const DataTypePtr & key_type,
size_t & valid_keys)
{ {
valid_keys = 0;
key_column = key_column->convertToFullColumnIfConst(); key_column = key_column->convertToFullColumnIfConst();
in_key_column = in_key_column->convertToFullColumnIfConst(); in_key_column = in_key_column->convertToFullColumnIfConst();
@ -143,6 +153,7 @@ ColumnUInt8::Ptr getKeysIsInHierarchyDefaultImplementation(
{ {
auto it = key_to_parent_key.find(key); auto it = key_to_parent_key.find(key);
std::optional<UInt64> result = (it != nullptr ? std::make_optional(it->getMapped()) : std::nullopt); std::optional<UInt64> result = (it != nullptr ? std::make_optional(it->getMapped()) : std::nullopt);
valid_keys += result.has_value();
return result; return result;
}; };

View File

@ -196,6 +196,8 @@ namespace detail
* Hierarchy result is ElementsAndOffsets structure, for each element there is descendants array, * Hierarchy result is ElementsAndOffsets structure, for each element there is descendants array,
* with size offset[element_index] - (element_index > 0 ? offset[element_index - 1] : 0). * with size offset[element_index] - (element_index > 0 ? offset[element_index - 1] : 0).
* *
* @param valid_keys - number of keys that are valid in parent_to_child map
*
* Example: * Example:
* id parent_id * id parent_id
* 1 0 * 1 0
@ -218,11 +220,13 @@ namespace detail
ElementsAndOffsets<KeyType> getDescendants( ElementsAndOffsets<KeyType> getDescendants(
const PaddedPODArray<KeyType> & keys, const PaddedPODArray<KeyType> & keys,
const HashMap<KeyType, PaddedPODArray<KeyType>> & parent_to_child, const HashMap<KeyType, PaddedPODArray<KeyType>> & parent_to_child,
Strategy strategy) Strategy strategy,
size_t & valid_keys)
{ {
/// If strategy is GetAllDescendantsStrategy we try to cache and later reuse previously calculated descendants. /// If strategy is GetAllDescendantsStrategy we try to cache and later reuse previously calculated descendants.
/// If strategy is GetDescendantsAtSpecificLevelStrategy we does not use cache strategy. /// If strategy is GetDescendantsAtSpecificLevelStrategy we does not use cache strategy.
size_t keys_size = keys.size(); size_t keys_size = keys.size();
valid_keys = 0;
PaddedPODArray<KeyType> descendants; PaddedPODArray<KeyType> descendants;
descendants.reserve(keys_size); descendants.reserve(keys_size);
@ -265,6 +269,7 @@ namespace detail
descendants_offsets.emplace_back(descendants.size()); descendants_offsets.emplace_back(descendants.size());
continue; continue;
} }
++valid_keys;
next_keys_to_process_stack.emplace_back(KeyAndDepth{requested_key, 0}); next_keys_to_process_stack.emplace_back(KeyAndDepth{requested_key, 0});
@ -425,43 +430,52 @@ ColumnUInt8::Ptr getKeysIsInHierarchyColumn(
} }
/// Returns descendants array column for keys /// Returns descendants array column for keys
///
/// @param valid_keys - number of keys that are valid in parent_to_child map
template <typename KeyType> template <typename KeyType>
ColumnPtr getKeysDescendantsArray( ColumnPtr getKeysDescendantsArray(
const PaddedPODArray<KeyType> & requested_keys, const PaddedPODArray<KeyType> & requested_keys,
const HashMap<KeyType, PaddedPODArray<KeyType>> & parent_to_child, const HashMap<KeyType, PaddedPODArray<KeyType>> & parent_to_child,
size_t level) size_t level,
size_t & valid_keys)
{ {
if (level == 0) if (level == 0)
{ {
detail::GetAllDescendantsStrategy strategy { .level = level }; detail::GetAllDescendantsStrategy strategy { .level = level };
auto elements_and_offsets = detail::getDescendants(requested_keys, parent_to_child, strategy); auto elements_and_offsets = detail::getDescendants(requested_keys, parent_to_child, strategy, valid_keys);
return detail::convertElementsAndOffsetsIntoArray(std::move(elements_and_offsets)); return detail::convertElementsAndOffsetsIntoArray(std::move(elements_and_offsets));
} }
else else
{ {
detail::GetDescendantsAtSpecificLevelStrategy strategy { .level = level }; detail::GetDescendantsAtSpecificLevelStrategy strategy { .level = level };
auto elements_and_offsets = detail::getDescendants(requested_keys, parent_to_child, strategy); auto elements_and_offsets = detail::getDescendants(requested_keys, parent_to_child, strategy, valid_keys);
return detail::convertElementsAndOffsetsIntoArray(std::move(elements_and_offsets)); return detail::convertElementsAndOffsetsIntoArray(std::move(elements_and_offsets));
} }
} }
/** Default getHierarchy implementation for dictionaries that does not have structure with child to parent representation. /** Default getHierarchy implementation for dictionaries that does not have structure with child to parent representation.
* Implementation will build such structure with getColumn calls, and then getHierarchy for such structure. * Implementation will build such structure with getColumn calls, and then getHierarchy for such structure.
* Returns ColumnArray with hierarchy arrays for keys from key_column. *
* @param valid_keys - number of keys (from @key_column) for which information about parent exists.
* @return ColumnArray with hierarchy arrays for keys from key_column.
*/ */
ColumnPtr getKeysHierarchyDefaultImplementation( ColumnPtr getKeysHierarchyDefaultImplementation(
const IDictionary * dictionary, const IDictionary * dictionary,
ColumnPtr key_column, ColumnPtr key_column,
const DataTypePtr & key_type); const DataTypePtr & key_type,
size_t & valid_keys);
/** Default isInHierarchy implementation for dictionaries that does not have structure with child to parent representation. /** Default isInHierarchy implementation for dictionaries that does not have structure with child to parent representation.
* Implementation will build such structure with getColumn calls, and then getHierarchy for such structure. * Implementation will build such structure with getColumn calls, and then getHierarchy for such structure.
* Returns UInt8 column if key from in_key_column is in key hierarchy from key_column. *
* @param valid_keys - number of keys (from @key_column) for which information about parent exists.
* @return UInt8 column if key from in_key_column is in key hierarchy from key_column.
*/ */
ColumnUInt8::Ptr getKeysIsInHierarchyDefaultImplementation( ColumnUInt8::Ptr getKeysIsInHierarchyDefaultImplementation(
const IDictionary * dictionary, const IDictionary * dictionary,
ColumnPtr key_column, ColumnPtr key_column,
ColumnPtr in_key_column, ColumnPtr in_key_column,
const DataTypePtr & key_type); const DataTypePtr & key_type,
size_t & valid_keys);
} }

View File

@ -90,6 +90,8 @@ struct IDictionary : public IExternalLoadable
virtual size_t getQueryCount() const = 0; virtual size_t getQueryCount() const = 0;
virtual double getFoundRate() const = 0;
virtual double getHitRate() const = 0; virtual double getHitRate() const = 0;
virtual size_t getElementCount() const = 0; virtual size_t getElementCount() const = 0;

View File

@ -275,7 +275,9 @@ ColumnUInt8::Ptr IPAddressDictionary::hasKeys(const Columns & key_columns, const
const auto rows = first_column->size(); const auto rows = first_column->size();
auto result = ColumnUInt8::create(rows); auto result = ColumnUInt8::create(rows);
auto& out = result->getData(); auto & out = result->getData();
size_t keys_found = 0;
if (first_column->isNumeric()) if (first_column->isNumeric())
{ {
@ -285,6 +287,7 @@ ColumnUInt8::Ptr IPAddressDictionary::hasKeys(const Columns & key_columns, const
auto addrv4 = UInt32(first_column->get64(i)); auto addrv4 = UInt32(first_column->get64(i));
auto found = tryLookupIPv4(addrv4, addrv6_buf); auto found = tryLookupIPv4(addrv4, addrv6_buf);
out[i] = (found != ipNotFound()); out[i] = (found != ipNotFound());
keys_found += out[i];
} }
} }
else else
@ -297,10 +300,12 @@ ColumnUInt8::Ptr IPAddressDictionary::hasKeys(const Columns & key_columns, const
auto found = tryLookupIPv6(reinterpret_cast<const uint8_t *>(addr.data)); auto found = tryLookupIPv6(reinterpret_cast<const uint8_t *>(addr.data));
out[i] = (found != ipNotFound()); out[i] = (found != ipNotFound());
keys_found += out[i];
} }
} }
query_count.fetch_add(rows, std::memory_order_relaxed); query_count.fetch_add(rows, std::memory_order_relaxed);
found_count.fetch_add(keys_found, std::memory_order_relaxed);
return result; return result;
} }
@ -680,6 +685,8 @@ void IPAddressDictionary::getItemsImpl(
auto & vec = std::get<ContainerType<AttributeType>>(attribute.maps); auto & vec = std::get<ContainerType<AttributeType>>(attribute.maps);
size_t keys_found = 0;
if (first_column->isNumeric()) if (first_column->isNumeric())
{ {
uint8_t addrv6_buf[IPV6_BINARY_LENGTH]; uint8_t addrv6_buf[IPV6_BINARY_LENGTH];
@ -689,7 +696,10 @@ void IPAddressDictionary::getItemsImpl(
auto addrv4 = UInt32(first_column->get64(i)); auto addrv4 = UInt32(first_column->get64(i));
auto found = tryLookupIPv4(addrv4, addrv6_buf); auto found = tryLookupIPv4(addrv4, addrv6_buf);
if (found != ipNotFound()) if (found != ipNotFound())
{
set_value(i, static_cast<OutputType>(vec[*found])); set_value(i, static_cast<OutputType>(vec[*found]));
++keys_found;
}
else else
set_value(i, default_value_extractor[i]); set_value(i, default_value_extractor[i]);
} }
@ -704,13 +714,17 @@ void IPAddressDictionary::getItemsImpl(
auto found = tryLookupIPv6(reinterpret_cast<const uint8_t *>(addr.data)); auto found = tryLookupIPv6(reinterpret_cast<const uint8_t *>(addr.data));
if (found != ipNotFound()) if (found != ipNotFound())
{
set_value(i, static_cast<OutputType>(vec[*found])); set_value(i, static_cast<OutputType>(vec[*found]));
++keys_found;
}
else else
set_value(i, default_value_extractor[i]); set_value(i, default_value_extractor[i]);
} }
} }
query_count.fetch_add(rows, std::memory_order_relaxed); query_count.fetch_add(rows, std::memory_order_relaxed);
found_count.fetch_add(keys_found, std::memory_order_relaxed);
} }
template <typename T> template <typename T>

View File

@ -38,6 +38,14 @@ public:
size_t getQueryCount() const override { return query_count.load(std::memory_order_relaxed); } size_t getQueryCount() const override { return query_count.load(std::memory_order_relaxed); }
double getFoundRate() const override
{
size_t queries = query_count.load(std::memory_order_relaxed);
if (!queries)
return 0;
return static_cast<double>(found_count.load(std::memory_order_relaxed)) / queries;
}
double getHitRate() const override { return 1.0; } double getHitRate() const override { return 1.0; }
size_t getElementCount() const override { return element_count; } size_t getElementCount() const override { return element_count; }
@ -210,6 +218,7 @@ private:
size_t element_count = 0; size_t element_count = 0;
size_t bucket_count = 0; size_t bucket_count = 0;
mutable std::atomic<size_t> query_count{0}; mutable std::atomic<size_t> query_count{0};
mutable std::atomic<size_t> found_count{0};
Poco::Logger * logger; Poco::Logger * logger;
}; };

View File

@ -64,6 +64,8 @@ ColumnPtr IPolygonDictionary::getColumn(
Field row_value_to_insert; Field row_value_to_insert;
size_t polygon_index = 0; size_t polygon_index = 0;
size_t keys_found = 0;
if (unlikely(complex_attribute)) if (unlikely(complex_attribute))
{ {
for (size_t requested_key_index = 0; requested_key_index < requested_key_points.size(); ++requested_key_index) for (size_t requested_key_index = 0; requested_key_index < requested_key_points.size(); ++requested_key_index)
@ -74,6 +76,7 @@ ColumnPtr IPolygonDictionary::getColumn(
{ {
size_t attribute_values_index = polygon_index_to_attribute_value_index[polygon_index]; size_t attribute_values_index = polygon_index_to_attribute_value_index[polygon_index];
attribute_values_column->get(attribute_values_index, row_value_to_insert); attribute_values_column->get(attribute_values_index, row_value_to_insert);
++keys_found;
} }
else else
row_value_to_insert = default_value_provider.getDefaultValue(requested_key_index); row_value_to_insert = default_value_provider.getDefaultValue(requested_key_index);
@ -110,6 +113,7 @@ ColumnPtr IPolygonDictionary::getColumn(
size_t attribute_values_index = polygon_index_to_attribute_value_index[polygon_index]; size_t attribute_values_index = polygon_index_to_attribute_value_index[polygon_index];
auto data_to_insert = attribute_values_column->getDataAt(attribute_values_index); auto data_to_insert = attribute_values_column->getDataAt(attribute_values_index);
result_column_typed.insertData(data_to_insert.data, data_to_insert.size); result_column_typed.insertData(data_to_insert.data, data_to_insert.size);
++keys_found;
} }
else else
result_column_typed.insert(default_value_provider.getDefaultValue(requested_key_index)); result_column_typed.insert(default_value_provider.getDefaultValue(requested_key_index));
@ -129,6 +133,7 @@ ColumnPtr IPolygonDictionary::getColumn(
size_t attribute_values_index = polygon_index_to_attribute_value_index[polygon_index]; size_t attribute_values_index = polygon_index_to_attribute_value_index[polygon_index];
auto & item = attribute_data[attribute_values_index]; auto & item = attribute_data[attribute_values_index];
result_data.emplace_back(item); result_data.emplace_back(item);
++keys_found;
} }
else else
{ {
@ -143,6 +148,7 @@ ColumnPtr IPolygonDictionary::getColumn(
} }
query_count.fetch_add(requested_key_points.size(), std::memory_order_relaxed); query_count.fetch_add(requested_key_points.size(), std::memory_order_relaxed);
found_count.fetch_add(keys_found, std::memory_order_relaxed);
return result; return result;
} }
@ -285,16 +291,20 @@ ColumnUInt8::Ptr IPolygonDictionary::hasKeys(const Columns & key_columns, const
std::vector<IPolygonDictionary::Point> points = extractPoints(key_columns); std::vector<IPolygonDictionary::Point> points = extractPoints(key_columns);
auto result = ColumnUInt8::create(points.size()); auto result = ColumnUInt8::create(points.size());
auto& out = result->getData(); auto & out = result->getData();
size_t keys_found = 0;
for (size_t i = 0; i < points.size(); ++i) for (size_t i = 0; i < points.size(); ++i)
{ {
size_t unused_find_result = 0; size_t unused_find_result = 0;
auto & point = points[i]; auto & point = points[i];
out[i] = find(point, unused_find_result); out[i] = find(point, unused_find_result);
keys_found += out[i];
} }
query_count.fetch_add(points.size(), std::memory_order_relaxed); query_count.fetch_add(points.size(), std::memory_order_relaxed);
found_count.fetch_add(keys_found, std::memory_order_relaxed);
return result; return result;
} }

View File

@ -63,6 +63,14 @@ public:
size_t getQueryCount() const override { return query_count.load(std::memory_order_relaxed); } size_t getQueryCount() const override { return query_count.load(std::memory_order_relaxed); }
double getFoundRate() const override
{
size_t queries = query_count.load(std::memory_order_relaxed);
if (!queries)
return 0;
return static_cast<double>(found_count.load(std::memory_order_relaxed)) / queries;
}
double getHitRate() const override { return 1.0; } double getHitRate() const override { return 1.0; }
size_t getElementCount() const override { return attributes.empty() ? 0 : attributes.front()->size(); } size_t getElementCount() const override { return attributes.empty() ? 0 : attributes.front()->size(); }
@ -141,6 +149,7 @@ private:
size_t bytes_allocated = 0; size_t bytes_allocated = 0;
mutable std::atomic<size_t> query_count{0}; mutable std::atomic<size_t> query_count{0};
mutable std::atomic<size_t> found_count{0};
/** Since the original data may have been in the form of multi-polygons, an id is stored for each single polygon /** Since the original data may have been in the form of multi-polygons, an id is stored for each single polygon
* corresponding to the row in which any other attributes for this entry are located. * corresponding to the row in which any other attributes for this entry are located.

View File

@ -195,17 +195,20 @@ ColumnUInt8::Ptr RangeHashedDictionary::hasKeys(const Columns & key_columns, con
ColumnUInt8::Ptr result; ColumnUInt8::Ptr result;
size_t keys_found = 0;
auto type_call = [&](const auto & dictionary_attribute_type) auto type_call = [&](const auto & dictionary_attribute_type)
{ {
using Type = std::decay_t<decltype(dictionary_attribute_type)>; using Type = std::decay_t<decltype(dictionary_attribute_type)>;
using AttributeType = typename Type::AttributeType; using AttributeType = typename Type::AttributeType;
using ValueType = DictionaryValueType<AttributeType>; using ValueType = DictionaryValueType<AttributeType>;
result = hasKeysImpl<ValueType>(attribute, ids, dates); result = hasKeysImpl<ValueType>(attribute, ids, dates, keys_found);
}; };
callOnDictionaryAttributeType(attribute.type, type_call); callOnDictionaryAttributeType(attribute.type, type_call);
query_count.fetch_add(ids.size(), std::memory_order_relaxed); query_count.fetch_add(ids.size(), std::memory_order_relaxed);
found_count.fetch_add(keys_found, std::memory_order_relaxed);
return result; return result;
} }
@ -214,13 +217,16 @@ template <typename AttributeType>
ColumnUInt8::Ptr RangeHashedDictionary::hasKeysImpl( ColumnUInt8::Ptr RangeHashedDictionary::hasKeysImpl(
const Attribute & attribute, const Attribute & attribute,
const PaddedPODArray<UInt64> & ids, const PaddedPODArray<UInt64> & ids,
const PaddedPODArray<RangeStorageType> & dates) const const PaddedPODArray<RangeStorageType> & dates,
size_t & keys_found) const
{ {
auto result = ColumnUInt8::create(ids.size()); auto result = ColumnUInt8::create(ids.size());
auto& out = result->getData(); auto& out = result->getData();
const auto & attr = *std::get<Ptr<AttributeType>>(attribute.maps); const auto & attr = *std::get<Ptr<AttributeType>>(attribute.maps);
keys_found = 0;
for (const auto row : ext::range(0, ids.size())) for (const auto row : ext::range(0, ids.size()))
{ {
const auto it = attr.find(ids[row]); const auto it = attr.find(ids[row]);
@ -237,10 +243,8 @@ ColumnUInt8::Ptr RangeHashedDictionary::hasKeysImpl(
return v.range.contains(date); return v.range.contains(date);
}); });
if (val_it != std::end(ranges_and_values)) out[row] = val_it != std::end(ranges_and_values);
out[row] = true; keys_found += out[row];
else
out[row] = false;
} }
else else
out[row] = false; out[row] = false;
@ -396,6 +400,8 @@ void RangeHashedDictionary::getItemsImpl(
const auto & attr = *std::get<Ptr<AttributeType>>(attribute.maps); const auto & attr = *std::get<Ptr<AttributeType>>(attribute.maps);
size_t keys_found = 0;
for (const auto row : ext::range(0, ids.size())) for (const auto row : ext::range(0, ids.size()))
{ {
const auto it = attr.find(ids[row]); const auto it = attr.find(ids[row]);
@ -413,7 +419,8 @@ void RangeHashedDictionary::getItemsImpl(
if (val_it != std::end(ranges_and_values)) if (val_it != std::end(ranges_and_values))
{ {
auto& value = val_it->value; ++keys_found;
auto & value = val_it->value;
if (value) if (value)
set_value(row, static_cast<OutputType>(*value), false); // NOLINT set_value(row, static_cast<OutputType>(*value), false); // NOLINT
@ -432,6 +439,7 @@ void RangeHashedDictionary::getItemsImpl(
} }
query_count.fetch_add(ids.size(), std::memory_order_relaxed); query_count.fetch_add(ids.size(), std::memory_order_relaxed);
found_count.fetch_add(keys_found, std::memory_order_relaxed);
} }

View File

@ -32,6 +32,14 @@ public:
size_t getQueryCount() const override { return query_count.load(std::memory_order_relaxed); } size_t getQueryCount() const override { return query_count.load(std::memory_order_relaxed); }
double getFoundRate() const override
{
size_t queries = query_count.load(std::memory_order_relaxed);
if (!queries)
return 0;
return static_cast<double>(found_count.load(std::memory_order_relaxed)) / queries;
}
double getHitRate() const override { return 1.0; } double getHitRate() const override { return 1.0; }
size_t getElementCount() const override { return element_count; } size_t getElementCount() const override { return element_count; }
@ -171,7 +179,8 @@ private:
ColumnUInt8::Ptr hasKeysImpl( ColumnUInt8::Ptr hasKeysImpl(
const Attribute & attribute, const Attribute & attribute,
const PaddedPODArray<UInt64> & ids, const PaddedPODArray<UInt64> & ids,
const PaddedPODArray<RangeStorageType> & dates) const; const PaddedPODArray<RangeStorageType> & dates,
size_t & keys_found) const;
template <typename T> template <typename T>
static void setAttributeValueImpl(Attribute & attribute, const UInt64 id, const Range & range, const Field & value); static void setAttributeValueImpl(Attribute & attribute, const UInt64 id, const Range & range, const Field & value);
@ -209,6 +218,7 @@ private:
size_t element_count = 0; size_t element_count = 0;
size_t bucket_count = 0; size_t bucket_count = 0;
mutable std::atomic<size_t> query_count{0}; mutable std::atomic<size_t> query_count{0};
mutable std::atomic<size_t> found_count{0};
}; };
} }

View File

@ -154,10 +154,12 @@ TEST(HierarchyDictionariesUtils, getDescendants)
PaddedPODArray<UInt64> keys = {0, 1, 2, 3, 4}; PaddedPODArray<UInt64> keys = {0, 1, 2, 3, 4};
{ {
size_t keys_found;
auto result = DB::detail::getDescendants( auto result = DB::detail::getDescendants(
keys, keys,
parent_to_child, parent_to_child,
DB::detail::GetAllDescendantsStrategy()); DB::detail::GetAllDescendantsStrategy(),
keys_found);
const auto & actual_elements = result.elements; const auto & actual_elements = result.elements;
const auto & actual_offsets = result.offsets; const auto & actual_offsets = result.offsets;
@ -167,12 +169,15 @@ TEST(HierarchyDictionariesUtils, getDescendants)
ASSERT_EQ(actual_elements, expected_elements); ASSERT_EQ(actual_elements, expected_elements);
ASSERT_EQ(actual_offsets, expected_offsets); ASSERT_EQ(actual_offsets, expected_offsets);
ASSERT_EQ(keys_found, 3);
} }
{ {
size_t keys_found;
auto result = DB::detail::getDescendants( auto result = DB::detail::getDescendants(
keys, keys,
parent_to_child, parent_to_child,
DB::detail::GetDescendantsAtSpecificLevelStrategy{1}); DB::detail::GetDescendantsAtSpecificLevelStrategy{1},
keys_found);
const auto & actual_elements = result.elements; const auto & actual_elements = result.elements;
const auto & actual_offsets = result.offsets; const auto & actual_offsets = result.offsets;
@ -182,6 +187,7 @@ TEST(HierarchyDictionariesUtils, getDescendants)
ASSERT_EQ(actual_elements, expected_elements); ASSERT_EQ(actual_elements, expected_elements);
ASSERT_EQ(actual_offsets, expected_offsets); ASSERT_EQ(actual_offsets, expected_offsets);
ASSERT_EQ(keys_found, 3);
} }
} }
{ {
@ -192,10 +198,12 @@ TEST(HierarchyDictionariesUtils, getDescendants)
PaddedPODArray<UInt64> keys = {1, 2, 3}; PaddedPODArray<UInt64> keys = {1, 2, 3};
{ {
size_t keys_found;
auto result = DB::detail::getDescendants( auto result = DB::detail::getDescendants(
keys, keys,
parent_to_child, parent_to_child,
DB::detail::GetAllDescendantsStrategy()); DB::detail::GetAllDescendantsStrategy(),
keys_found);
const auto & actual_elements = result.elements; const auto & actual_elements = result.elements;
const auto & actual_offsets = result.offsets; const auto & actual_offsets = result.offsets;
@ -205,12 +213,15 @@ TEST(HierarchyDictionariesUtils, getDescendants)
ASSERT_EQ(actual_elements, expected_elements); ASSERT_EQ(actual_elements, expected_elements);
ASSERT_EQ(actual_offsets, expected_offsets); ASSERT_EQ(actual_offsets, expected_offsets);
ASSERT_EQ(keys_found, 2);
} }
{ {
size_t keys_found;
auto result = DB::detail::getDescendants( auto result = DB::detail::getDescendants(
keys, keys,
parent_to_child, parent_to_child,
DB::detail::GetDescendantsAtSpecificLevelStrategy{1}); DB::detail::GetDescendantsAtSpecificLevelStrategy{1},
keys_found);
const auto & actual_elements = result.elements; const auto & actual_elements = result.elements;
const auto & actual_offsets = result.offsets; const auto & actual_offsets = result.offsets;
@ -220,6 +231,7 @@ TEST(HierarchyDictionariesUtils, getDescendants)
ASSERT_EQ(actual_elements, expected_elements); ASSERT_EQ(actual_elements, expected_elements);
ASSERT_EQ(actual_offsets, expected_offsets); ASSERT_EQ(actual_offsets, expected_offsets);
ASSERT_EQ(keys_found, 2);
} }
} }
} }

View File

@ -13,6 +13,7 @@ namespace ErrorCodes
{ {
extern const int ILLEGAL_TYPE_OF_ARGUMENT; extern const int ILLEGAL_TYPE_OF_ARGUMENT;
extern const int ILLEGAL_COLUMN; extern const int ILLEGAL_COLUMN;
extern const int DECIMAL_OVERFLOW;
} }
/** arrayDifference() - returns an array with the difference between all pairs of neighboring elements. /** arrayDifference() - returns an array with the difference between all pairs of neighboring elements.
@ -63,7 +64,23 @@ struct ArrayDifferenceImpl
else else
{ {
Element curr = src[pos]; Element curr = src[pos];
dst[pos] = curr - prev;
if constexpr (IsDecimalNumber<Element>)
{
using ResultNativeType = typename Result::NativeType;
ResultNativeType result_value;
bool overflow = common::subOverflow(static_cast<ResultNativeType>(curr.value), static_cast<ResultNativeType>(prev), result_value);
if (overflow)
throw Exception(ErrorCodes::DECIMAL_OVERFLOW, "Decimal math overflow");
dst[pos] = Result(result_value);
}
else
{
dst[pos] = curr - prev;
}
prev = curr; prev = curr;
} }
} }

View File

@ -858,9 +858,9 @@ void Aggregator::writeToTemporaryFile(AggregatedDataVariants & data_variants, co
ProfileEvents::increment(ProfileEvents::ExternalAggregationUncompressedBytes, uncompressed_bytes); ProfileEvents::increment(ProfileEvents::ExternalAggregationUncompressedBytes, uncompressed_bytes);
LOG_DEBUG(log, LOG_DEBUG(log,
"Written part in {} sec., {} rows, {} uncompressed, {} compressed," "Written part in {:.3f} sec., {} rows, {} uncompressed, {} compressed,"
" {} uncompressed bytes per row, {} compressed bytes per row, compression rate: {}" " {:.3f} uncompressed bytes per row, {:.3f} compressed bytes per row, compression rate: {:.3f}"
" ({} rows/sec., {}/sec. uncompressed, {}/sec. compressed)", " ({:.3f} rows/sec., {}/sec. uncompressed, {}/sec. compressed)",
elapsed_seconds, elapsed_seconds,
rows, rows,
ReadableSize(uncompressed_bytes), ReadableSize(uncompressed_bytes),
@ -1493,7 +1493,7 @@ BlocksList Aggregator::convertToBlocks(AggregatedDataVariants & data_variants, b
double elapsed_seconds = watch.elapsedSeconds(); double elapsed_seconds = watch.elapsedSeconds();
LOG_DEBUG(log, LOG_DEBUG(log,
"Converted aggregated data to blocks. {} rows, {} in {} sec. ({} rows/sec., {}/sec.)", "Converted aggregated data to blocks. {} rows, {} in {} sec. ({:.3f} rows/sec., {}/sec.)",
rows, ReadableSize(bytes), rows, ReadableSize(bytes),
elapsed_seconds, rows / elapsed_seconds, elapsed_seconds, rows / elapsed_seconds,
ReadableSize(bytes / elapsed_seconds)); ReadableSize(bytes / elapsed_seconds));
@ -2097,7 +2097,7 @@ Block Aggregator::mergeBlocks(BlocksList & blocks, bool final)
size_t rows = block.rows(); size_t rows = block.rows();
size_t bytes = block.bytes(); size_t bytes = block.bytes();
double elapsed_seconds = watch.elapsedSeconds(); double elapsed_seconds = watch.elapsedSeconds();
LOG_DEBUG(log, "Merged partially aggregated blocks. {} rows, {}. in {} sec. ({} rows/sec., {}/sec.)", LOG_DEBUG(log, "Merged partially aggregated blocks. {} rows, {}. in {} sec. ({:.3f} rows/sec., {}/sec.)",
rows, ReadableSize(bytes), rows, ReadableSize(bytes),
elapsed_seconds, rows / elapsed_seconds, elapsed_seconds, rows / elapsed_seconds,
ReadableSize(bytes / elapsed_seconds)); ReadableSize(bytes / elapsed_seconds));

View File

@ -541,7 +541,7 @@ void AggregatingTransform::initGenerate()
double elapsed_seconds = watch.elapsedSeconds(); double elapsed_seconds = watch.elapsedSeconds();
size_t rows = variants.sizeWithoutOverflowRow(); size_t rows = variants.sizeWithoutOverflowRow();
LOG_DEBUG(log, "Aggregated. {} to {} rows (from {}) in {} sec. ({} rows/sec., {}/sec.)", LOG_DEBUG(log, "Aggregated. {} to {} rows (from {}) in {} sec. ({:.3f} rows/sec., {}/sec.)",
src_rows, rows, ReadableSize(src_bytes), src_rows, rows, ReadableSize(src_bytes),
elapsed_seconds, src_rows / elapsed_seconds, elapsed_seconds, src_rows / elapsed_seconds,
ReadableSize(src_bytes / elapsed_seconds)); ReadableSize(src_bytes / elapsed_seconds));

View File

@ -37,6 +37,7 @@ NamesAndTypesList StorageSystemDictionaries::getNamesAndTypes()
{"bytes_allocated", std::make_shared<DataTypeUInt64>()}, {"bytes_allocated", std::make_shared<DataTypeUInt64>()},
{"query_count", std::make_shared<DataTypeUInt64>()}, {"query_count", std::make_shared<DataTypeUInt64>()},
{"hit_rate", std::make_shared<DataTypeFloat64>()}, {"hit_rate", std::make_shared<DataTypeFloat64>()},
{"found_rate", std::make_shared<DataTypeFloat64>()},
{"element_count", std::make_shared<DataTypeUInt64>()}, {"element_count", std::make_shared<DataTypeUInt64>()},
{"load_factor", std::make_shared<DataTypeFloat64>()}, {"load_factor", std::make_shared<DataTypeFloat64>()},
{"source", std::make_shared<DataTypeString>()}, {"source", std::make_shared<DataTypeString>()},
@ -113,6 +114,7 @@ void StorageSystemDictionaries::fillData(MutableColumns & res_columns, ContextPt
res_columns[i++]->insert(dict_ptr->getBytesAllocated()); res_columns[i++]->insert(dict_ptr->getBytesAllocated());
res_columns[i++]->insert(dict_ptr->getQueryCount()); res_columns[i++]->insert(dict_ptr->getQueryCount());
res_columns[i++]->insert(dict_ptr->getHitRate()); res_columns[i++]->insert(dict_ptr->getHitRate());
res_columns[i++]->insert(dict_ptr->getFoundRate());
res_columns[i++]->insert(dict_ptr->getElementCount()); res_columns[i++]->insert(dict_ptr->getElementCount());
res_columns[i++]->insert(dict_ptr->getLoadFactor()); res_columns[i++]->insert(dict_ptr->getLoadFactor());
res_columns[i++]->insert(dict_ptr->getSource()->toString()); res_columns[i++]->insert(dict_ptr->getSource()->toString());
@ -125,7 +127,7 @@ void StorageSystemDictionaries::fillData(MutableColumns & res_columns, ContextPt
} }
else else
{ {
for (size_t j = 0; j != 8; ++j) // Number of empty fields if dict_ptr is null for (size_t j = 0; j != 9; ++j) // Number of empty fields if dict_ptr is null
res_columns[i++]->insertDefault(); res_columns[i++]->insertDefault();
} }

View File

@ -0,0 +1 @@
SELECT arrayDifference([toDecimal32(100.0000991821289, 0), -2147483647]) AS x; --{serverError 407}

View File

@ -0,0 +1,33 @@
simple_key_flat_dictionary_01862 1
simple_key_flat_dictionary_01862 1
simple_key_flat_dictionary_01862 0.67
simple_key_direct_dictionary_01862 0
simple_key_direct_dictionary_01862 0
simple_key_direct_dictionary_01862 1
simple_key_direct_dictionary_01862 0.5
simple_key_hashed_dictionary_01862 0
simple_key_hashed_dictionary_01862 1
simple_key_hashed_dictionary_01862 0.5
simple_key_sparse_hashed_dictionary_01862 0
simple_key_sparse_hashed_dictionary_01862 1
simple_key_sparse_hashed_dictionary_01862 0.5
simple_key_cache_dictionary_01862 0
simple_key_cache_dictionary_01862 1
simple_key_cache_dictionary_01862 0.5
complex_key_hashed_dictionary_01862 0
complex_key_hashed_dictionary_01862 1
complex_key_hashed_dictionary_01862 0.5
complex_key_direct_dictionary_01862 0
complex_key_direct_dictionary_01862 1
complex_key_direct_dictionary_01862 0.5
complex_key_cache_dictionary_01862 0
complex_key_cache_dictionary_01862 1
complex_key_cache_dictionary_01862 0.5
simple_key_range_hashed_dictionary_01862 0
simple_key_range_hashed_dictionary_01862 1
simple_key_range_hashed_dictionary_01862 0.5
ip_trie_dictionary_01862 0
ip_trie_dictionary_01862 1
ip_trie_dictionary_01862 0.5
polygon_dictionary_01862 0
polygon_dictionary_01862 0.8

View File

@ -0,0 +1,309 @@
--
-- Simple key
--
DROP TABLE IF EXISTS simple_key_source_table_01862;
CREATE TABLE simple_key_source_table_01862
(
id UInt64,
value String
) ENGINE = Memory();
INSERT INTO simple_key_source_table_01862 VALUES (1, 'First');
INSERT INTO simple_key_source_table_01862 VALUES (1, 'First');
-- simple flat
DROP DICTIONARY IF EXISTS simple_key_flat_dictionary_01862;
CREATE DICTIONARY simple_key_flat_dictionary_01862
(
id UInt64,
value String
)
PRIMARY KEY id
SOURCE(CLICKHOUSE(HOST 'localhost' PORT tcpPort() TABLE 'simple_key_source_table_01862'))
LAYOUT(FLAT())
LIFETIME(MIN 0 MAX 1000);
SELECT * FROM simple_key_flat_dictionary_01862 FORMAT Null;
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'simple_key_flat_dictionary_01862';
SELECT * FROM simple_key_flat_dictionary_01862 WHERE id = 0 FORMAT Null;
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'simple_key_flat_dictionary_01862';
SELECT dictGet('simple_key_flat_dictionary_01862', 'value', toUInt64(2)) FORMAT Null;
SELECT name, round(found_rate, 2) FROM system.dictionaries WHERE database = currentDatabase() AND name = 'simple_key_flat_dictionary_01862';
DROP DICTIONARY simple_key_flat_dictionary_01862;
-- simple direct
DROP DICTIONARY IF EXISTS simple_key_direct_dictionary_01862;
CREATE DICTIONARY simple_key_direct_dictionary_01862
(
id UInt64,
value String
)
PRIMARY KEY id
SOURCE(CLICKHOUSE(HOST 'localhost' PORT tcpPort() TABLE 'simple_key_source_table_01862'))
LAYOUT(DIRECT());
-- check that found_rate is 0, not nan
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'simple_key_direct_dictionary_01862';
SELECT * FROM simple_key_direct_dictionary_01862 FORMAT Null;
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'simple_key_direct_dictionary_01862';
SELECT dictGet('simple_key_direct_dictionary_01862', 'value', toUInt64(1)) FORMAT Null;
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'simple_key_direct_dictionary_01862';
SELECT dictGet('simple_key_direct_dictionary_01862', 'value', toUInt64(2)) FORMAT Null;
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'simple_key_direct_dictionary_01862';
DROP DICTIONARY simple_key_direct_dictionary_01862;
-- simple hashed
DROP DICTIONARY IF EXISTS simple_key_hashed_dictionary_01862;
CREATE DICTIONARY simple_key_hashed_dictionary_01862
(
id UInt64,
value String
)
PRIMARY KEY id
SOURCE(CLICKHOUSE(HOST 'localhost' PORT tcpPort() TABLE 'simple_key_source_table_01862'))
LAYOUT(HASHED())
LIFETIME(MIN 0 MAX 1000);
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'simple_key_hashed_dictionary_01862';
SELECT dictGet('simple_key_hashed_dictionary_01862', 'value', toUInt64(1)) FORMAT Null;
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'simple_key_hashed_dictionary_01862';
SELECT dictGet('simple_key_hashed_dictionary_01862', 'value', toUInt64(2)) FORMAT Null;
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'simple_key_hashed_dictionary_01862';
DROP DICTIONARY simple_key_hashed_dictionary_01862;
-- simple sparse_hashed
DROP DICTIONARY IF EXISTS simple_key_sparse_hashed_dictionary_01862;
CREATE DICTIONARY simple_key_sparse_hashed_dictionary_01862
(
id UInt64,
value String
)
PRIMARY KEY id
SOURCE(CLICKHOUSE(HOST 'localhost' PORT tcpPort() TABLE 'simple_key_source_table_01862'))
LAYOUT(SPARSE_HASHED())
LIFETIME(MIN 0 MAX 1000);
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'simple_key_sparse_hashed_dictionary_01862';
SELECT dictGet('simple_key_sparse_hashed_dictionary_01862', 'value', toUInt64(1)) FORMAT Null;
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'simple_key_sparse_hashed_dictionary_01862';
SELECT dictGet('simple_key_sparse_hashed_dictionary_01862', 'value', toUInt64(2)) FORMAT Null;
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'simple_key_sparse_hashed_dictionary_01862';
DROP DICTIONARY simple_key_sparse_hashed_dictionary_01862;
-- simple cache
DROP DICTIONARY IF EXISTS simple_key_cache_dictionary_01862;
CREATE DICTIONARY simple_key_cache_dictionary_01862
(
id UInt64,
value String
)
PRIMARY KEY id
SOURCE(CLICKHOUSE(HOST 'localhost' PORT tcpPort() TABLE 'simple_key_source_table_01862'))
LAYOUT(CACHE(SIZE_IN_CELLS 100000))
LIFETIME(MIN 0 MAX 1000);
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'simple_key_cache_dictionary_01862';
SELECT toUInt64(1) as key, dictGet('simple_key_cache_dictionary_01862', 'value', key) FORMAT Null;
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'simple_key_cache_dictionary_01862';
SELECT toUInt64(2) as key, dictGet('simple_key_cache_dictionary_01862', 'value', key) FORMAT Null;
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'simple_key_cache_dictionary_01862';
DROP DICTIONARY simple_key_cache_dictionary_01862;
DROP TABLE simple_key_source_table_01862;
--
-- Complex key
--
DROP TABLE IF EXISTS complex_key_source_table_01862;
CREATE TABLE complex_key_source_table_01862
(
id UInt64,
id_key String,
value String
) ENGINE = Memory();
INSERT INTO complex_key_source_table_01862 VALUES (1, 'FirstKey', 'First');
INSERT INTO complex_key_source_table_01862 VALUES (1, 'FirstKey', 'First');
-- complex hashed
DROP DICTIONARY IF EXISTS complex_key_hashed_dictionary_01862;
CREATE DICTIONARY complex_key_hashed_dictionary_01862
(
id UInt64,
id_key String,
value String
)
PRIMARY KEY id, id_key
SOURCE(CLICKHOUSE(HOST 'localhost' PORT tcpPort() TABLE 'complex_key_source_table_01862'))
LAYOUT(COMPLEX_KEY_HASHED())
LIFETIME(MIN 0 MAX 1000);
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'complex_key_hashed_dictionary_01862';
SELECT dictGet('complex_key_hashed_dictionary_01862', 'value', (toUInt64(1), 'FirstKey')) FORMAT Null;
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'complex_key_hashed_dictionary_01862';
SELECT dictGet('complex_key_hashed_dictionary_01862', 'value', (toUInt64(2), 'FirstKey')) FORMAT Null;
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'complex_key_hashed_dictionary_01862';
DROP DICTIONARY complex_key_hashed_dictionary_01862;
-- complex direct
DROP DICTIONARY IF EXISTS complex_key_direct_dictionary_01862;
CREATE DICTIONARY complex_key_direct_dictionary_01862
(
id UInt64,
id_key String,
value String
)
PRIMARY KEY id, id_key
SOURCE(CLICKHOUSE(HOST 'localhost' PORT tcpPort() TABLE 'complex_key_source_table_01862'))
LAYOUT(COMPLEX_KEY_DIRECT());
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'complex_key_direct_dictionary_01862';
SELECT dictGet('complex_key_direct_dictionary_01862', 'value', (toUInt64(1), 'FirstKey')) FORMAT Null;
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'complex_key_direct_dictionary_01862';
SELECT dictGet('complex_key_direct_dictionary_01862', 'value', (toUInt64(2), 'FirstKey')) FORMAT Null;
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'complex_key_direct_dictionary_01862';
DROP DICTIONARY complex_key_direct_dictionary_01862;
-- complex cache
DROP DICTIONARY IF EXISTS complex_key_cache_dictionary_01862;
CREATE DICTIONARY complex_key_cache_dictionary_01862
(
id UInt64,
id_key String,
value String
)
PRIMARY KEY id, id_key
SOURCE(CLICKHOUSE(HOST 'localhost' PORT tcpPort() TABLE 'complex_key_source_table_01862'))
LAYOUT(COMPLEX_KEY_CACHE(SIZE_IN_CELLS 100000))
LIFETIME(MIN 0 MAX 1000);
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'complex_key_cache_dictionary_01862';
SELECT dictGet('complex_key_cache_dictionary_01862', 'value', (toUInt64(1), 'FirstKey')) FORMAT Null;
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'complex_key_cache_dictionary_01862';
SELECT dictGet('complex_key_cache_dictionary_01862', 'value', (toUInt64(2), 'FirstKey')) FORMAT Null;
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'complex_key_cache_dictionary_01862';
DROP DICTIONARY complex_key_cache_dictionary_01862;
DROP TABLE complex_key_source_table_01862;
--
-- Range
--
DROP TABLE IF EXISTS range_key_source_table_01862;
CREATE TABLE range_key_source_table_01862
(
id UInt64,
value String,
first Date,
last Date
) ENGINE = Memory();
INSERT INTO range_key_source_table_01862 VALUES (1, 'First', today(), today());
INSERT INTO range_key_source_table_01862 VALUES (1, 'First', today(), today());
-- simple range_hashed
DROP DICTIONARY IF EXISTS simple_key_range_hashed_dictionary_01862;
CREATE DICTIONARY simple_key_range_hashed_dictionary_01862
(
id UInt64,
value String,
first Date,
last Date
)
PRIMARY KEY id
SOURCE(CLICKHOUSE(HOST 'localhost' PORT tcpPort() TABLE 'range_key_source_table_01862'))
LAYOUT(RANGE_HASHED())
RANGE(MIN first MAX last)
LIFETIME(MIN 0 MAX 1000);
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'simple_key_range_hashed_dictionary_01862';
SELECT dictGet('simple_key_range_hashed_dictionary_01862', 'value', toUInt64(1), today()) FORMAT Null;
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'simple_key_range_hashed_dictionary_01862';
SELECT dictGet('simple_key_range_hashed_dictionary_01862', 'value', toUInt64(2), today()) FORMAT Null;
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'simple_key_range_hashed_dictionary_01862';
DROP DICTIONARY simple_key_range_hashed_dictionary_01862;
DROP TABLE range_key_source_table_01862;
--
-- IP Trie
--
DROP TABLE IF EXISTS ip_trie_source_table_01862;
CREATE TABLE ip_trie_source_table_01862
(
prefix String,
value String
) ENGINE = Memory();
INSERT INTO ip_trie_source_table_01862 VALUES ('127.0.0.0/8', 'First');
INSERT INTO ip_trie_source_table_01862 VALUES ('127.0.0.0/8', 'First');
-- ip_trie
DROP DICTIONARY IF EXISTS ip_trie_dictionary_01862;
CREATE DICTIONARY ip_trie_dictionary_01862
(
prefix String,
value String
)
PRIMARY KEY prefix
SOURCE(CLICKHOUSE(HOST 'localhost' PORT tcpPort() TABLE 'ip_trie_source_table_01862'))
LAYOUT(IP_TRIE())
LIFETIME(MIN 0 MAX 1000);
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'ip_trie_dictionary_01862';
SELECT dictGet('ip_trie_dictionary_01862', 'value', tuple(toIPv4('127.0.0.1'))) FORMAT Null;
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'ip_trie_dictionary_01862';
SELECT dictGet('ip_trie_dictionary_01862', 'value', tuple(toIPv4('1.1.1.1'))) FORMAT Null;
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'ip_trie_dictionary_01862';
DROP DICTIONARY ip_trie_dictionary_01862;
DROP TABLE ip_trie_source_table_01862;
-- Polygon
DROP TABLE IF EXISTS polygons_01862;
CREATE TABLE polygons_01862 (
key Array(Array(Array(Tuple(Float64, Float64)))),
name String
) ENGINE = Memory;
INSERT INTO polygons_01862 VALUES ([[[(3, 1), (0, 1), (0, -1), (3, -1)]]], 'Click East');
INSERT INTO polygons_01862 VALUES ([[[(-1, 1), (1, 1), (1, 3), (-1, 3)]]], 'Click North');
INSERT INTO polygons_01862 VALUES ([[[(-3, 1), (-3, -1), (0, -1), (0, 1)]]], 'Click South');
INSERT INTO polygons_01862 VALUES ([[[(-1, -1), (1, -1), (1, -3), (-1, -3)]]], 'Click West');
DROP TABLE IF EXISTS points_01862;
CREATE TABLE points_01862 (x Float64, y Float64) ENGINE = Memory;
INSERT INTO points_01862 VALUES ( 0.1, 0.0);
INSERT INTO points_01862 VALUES (-0.1, 0.0);
INSERT INTO points_01862 VALUES ( 0.0, 1.1);
INSERT INTO points_01862 VALUES ( 0.0, -1.1);
INSERT INTO points_01862 VALUES ( 3.0, 3.0);
DROP DICTIONARY IF EXISTS polygon_dictionary_01862;
CREATE DICTIONARY polygon_dictionary_01862
(
key Array(Array(Array(Tuple(Float64, Float64)))),
name String
)
PRIMARY KEY key
SOURCE(CLICKHOUSE(HOST 'localhost' PORT tcpPort() USER 'default' TABLE 'polygons_01862'))
LIFETIME(0)
LAYOUT(POLYGON());
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'polygon_dictionary_01862';
SELECT tuple(x, y) as key, dictGet('polygon_dictionary_01862', 'name', key) FROM points_01862 FORMAT Null;
SELECT name, found_rate FROM system.dictionaries WHERE database = currentDatabase() AND name = 'polygon_dictionary_01862';
DROP TABLE polygons_01862;
DROP TABLE points_01862;

View File

@ -0,0 +1,46 @@
from multiprocessing.dummy import Pool
from testflows.core import *
def join(tasks, test=None):
"""Join all parallel tests.
"""
exc = None
if test is None:
test = current()
for task in tasks:
try:
task.get()
except Exception as e:
exc = e
if exc:
raise exc
def start(pool, tasks, scenario, kwargs=None, test=None):
"""Start parallel test.
"""
if test is None:
test = current()
if kwargs is None:
kwargs = {}
task = pool.apply_async(scenario, [], kwargs)
tasks.append(task)
return task
def run_scenario(pool, tasks, scenario, kwargs=None):
"""Run scenario in parallel if parallel flag is set
in the context.
"""
if kwargs is None:
kwargs = {}
if current().context.parallel:
start(pool, tasks, scenario, kwargs)
else:
scenario(**kwargs)

View File

@ -0,0 +1,6 @@
<yandex>
<timezone>Europe/Moscow</timezone>
<listen_host replace="replace">0.0.0.0</listen_host>
<path>/var/lib/clickhouse/</path>
<tmp_path>/var/lib/clickhouse/tmp/</tmp_path>
</yandex>

View File

@ -0,0 +1,17 @@
<yandex>
<shutdown_wait_unfinished>3</shutdown_wait_unfinished>
<logger>
<level>trace</level>
<log>/var/log/clickhouse-server/log.log</log>
<errorlog>/var/log/clickhouse-server/log.err.log</errorlog>
<size>1000M</size>
<count>10</count>
<stderr>/var/log/clickhouse-server/stderr.log</stderr>
<stdout>/var/log/clickhouse-server/stdout.log</stdout>
</logger>
<part_log>
<database>system</database>
<table>part_log</table>
<flush_interval_milliseconds>500</flush_interval_milliseconds>
</part_log>
</yandex>

View File

@ -0,0 +1,5 @@
<?xml version="1.0"?>
<yandex>
<https_port>8443</https_port>
<tcp_port_secure>9440</tcp_port_secure>
</yandex>

View File

@ -0,0 +1,107 @@
<?xml version="1.0"?>
<yandex>
<remote_servers>
<replicated_cluster>
<shard>
<internal_replication>true</internal_replication>
<replica>
<host>clickhouse1</host>
<port>9000</port>
</replica>
<replica>
<host>clickhouse2</host>
<port>9000</port>
</replica>
<replica>
<host>clickhouse3</host>
<port>9000</port>
</replica>
</shard>
</replicated_cluster>
<!--
<replicated_cluster_readonly>
<shard>
<internal_replication>true</internal_replication>
<replica>
<host>clickhouse1</host>
<port>9000</port>
<user>readonly</user>
</replica>
<replica>
<host>clickhouse2</host>
<port>9000</port>
<user>readonly</user>
</replica>
<replica>
<host>clickhouse3</host>
<port>9000</port>
<user>readonly</user>
</replica>
</shard>
</replicated_cluster_readonly>
-->
<replicated_cluster_secure>
<shard>
<internal_replication>true</internal_replication>
<replica>
<host>clickhouse1</host>
<port>9440</port>
<secure>1</secure>
</replica>
<replica>
<host>clickhouse2</host>
<port>9440</port>
<secure>1</secure>
</replica>
<replica>
<host>clickhouse3</host>
<port>9440</port>
<secure>1</secure>
</replica>
</shard>
</replicated_cluster_secure>
<sharded_cluster>
<shard>
<replica>
<host>clickhouse1</host>
<port>9000</port>
</replica>
</shard>
<shard>
<replica>
<host>clickhouse2</host>
<port>9000</port>
</replica>
</shard>
<shard>
<replica>
<host>clickhouse3</host>
<port>9000</port>
</replica>
</shard>
</sharded_cluster>
<sharded_cluster_secure>
<shard>
<replica>
<host>clickhouse1</host>
<port>9440</port>
<secure>1</secure>
</replica>
</shard>
<shard>
<replica>
<host>clickhouse2</host>
<port>9440</port>
<secure>1</secure>
</replica>
</shard>
<shard>
<replica>
<host>clickhouse3</host>
<port>9440</port>
<secure>1</secure>
</replica>
</shard>
</sharded_cluster_secure>
</remote_servers>
</yandex>

View File

@ -0,0 +1,17 @@
<yandex>
<openSSL>
<server>
<certificateFile>/etc/clickhouse-server/ssl/server.crt</certificateFile>
<privateKeyFile>/etc/clickhouse-server/ssl/server.key</privateKeyFile>
<verificationMode>none</verificationMode>
<cacheSessions>true</cacheSessions>
</server>
<client>
<cacheSessions>true</cacheSessions>
<verificationMode>none</verificationMode>
<invalidCertificateHandler>
<name>AcceptCertificateHandler</name>
</invalidCertificateHandler>
</client>
</openSSL>
</yandex>

View File

@ -0,0 +1,20 @@
<yandex>
<storage_configuration>
<disks>
<default>
<keep_free_space_bytes>1024</keep_free_space_bytes>
</default>
</disks>
<policies>
<default>
<volumes>
<default>
<disk>default</disk>
</default>
</volumes>
</default>
</policies>
</storage_configuration>
</yandex>

View File

@ -0,0 +1,10 @@
<?xml version="1.0"?>
<yandex>
<zookeeper>
<node index="1">
<host>zookeeper</host>
<port>2181</port>
</node>
<session_timeout_ms>15000</session_timeout_ms>
</zookeeper>
</yandex>

View File

@ -0,0 +1,436 @@
<?xml version="1.0"?>
<!--
NOTE: User and query level settings are set up in "users.xml" file.
-->
<yandex>
<logger>
<!-- Possible levels: https://github.com/pocoproject/poco/blob/develop/Foundation/include/Poco/Logger.h#L105 -->
<level>trace</level>
<log>/var/log/clickhouse-server/clickhouse-server.log</log>
<errorlog>/var/log/clickhouse-server/clickhouse-server.err.log</errorlog>
<size>1000M</size>
<count>10</count>
<!-- <console>1</console> --> <!-- Default behavior is autodetection (log to console if not daemon mode and is tty) -->
</logger>
<!--display_name>production</display_name--> <!-- It is the name that will be shown in the client -->
<http_port>8123</http_port>
<tcp_port>9000</tcp_port>
<!-- For HTTPS and SSL over native protocol. -->
<!--
<https_port>8443</https_port>
<tcp_port_secure>9440</tcp_port_secure>
-->
<!-- Used with https_port and tcp_port_secure. Full ssl options list: https://github.com/ClickHouse-Extras/poco/blob/master/NetSSL_OpenSSL/include/Poco/Net/SSLManager.h#L71 -->
<openSSL>
<server> <!-- Used for https server AND secure tcp port -->
<!-- openssl req -subj "/CN=localhost" -new -newkey rsa:2048 -days 365 -nodes -x509 -keyout /etc/clickhouse-server/server.key -out /etc/clickhouse-server/server.crt -->
<certificateFile>/etc/clickhouse-server/server.crt</certificateFile>
<privateKeyFile>/etc/clickhouse-server/server.key</privateKeyFile>
<!-- openssl dhparam -out /etc/clickhouse-server/dhparam.pem 4096 -->
<dhParamsFile>/etc/clickhouse-server/dhparam.pem</dhParamsFile>
<verificationMode>none</verificationMode>
<loadDefaultCAFile>true</loadDefaultCAFile>
<cacheSessions>true</cacheSessions>
<disableProtocols>sslv2,sslv3</disableProtocols>
<preferServerCiphers>true</preferServerCiphers>
</server>
<client> <!-- Used for connecting to https dictionary source -->
<loadDefaultCAFile>true</loadDefaultCAFile>
<cacheSessions>true</cacheSessions>
<disableProtocols>sslv2,sslv3</disableProtocols>
<preferServerCiphers>true</preferServerCiphers>
<!-- Use for self-signed: <verificationMode>none</verificationMode> -->
<invalidCertificateHandler>
<!-- Use for self-signed: <name>AcceptCertificateHandler</name> -->
<name>RejectCertificateHandler</name>
</invalidCertificateHandler>
</client>
</openSSL>
<!-- Default root page on http[s] server. For example load UI from https://tabix.io/ when opening http://localhost:8123 -->
<!--
<http_server_default_response><![CDATA[<html ng-app="SMI2"><head><base href="http://ui.tabix.io/"></head><body><div ui-view="" class="content-ui"></div><script src="http://loader.tabix.io/master.js"></script></body></html>]]></http_server_default_response>
-->
<!-- Port for communication between replicas. Used for data exchange. -->
<interserver_http_port>9009</interserver_http_port>
<!-- Hostname that is used by other replicas to request this server.
If not specified, than it is determined analoguous to 'hostname -f' command.
This setting could be used to switch replication to another network interface.
-->
<!--
<interserver_http_host>example.yandex.ru</interserver_http_host>
-->
<!-- Listen specified host. use :: (wildcard IPv6 address), if you want to accept connections both with IPv4 and IPv6 from everywhere. -->
<!-- <listen_host>::</listen_host> -->
<!-- Same for hosts with disabled ipv6: -->
<!-- <listen_host>0.0.0.0</listen_host> -->
<!-- Default values - try listen localhost on ipv4 and ipv6: -->
<!--
<listen_host>::1</listen_host>
<listen_host>127.0.0.1</listen_host>
-->
<!-- Don't exit if ipv6 or ipv4 unavailable, but listen_host with this protocol specified -->
<!-- <listen_try>0</listen_try> -->
<!-- Allow listen on same address:port -->
<!-- <listen_reuse_port>0</listen_reuse_port> -->
<!-- <listen_backlog>64</listen_backlog> -->
<max_connections>4096</max_connections>
<keep_alive_timeout>3</keep_alive_timeout>
<!-- Maximum number of concurrent queries. -->
<max_concurrent_queries>100</max_concurrent_queries>
<!-- Set limit on number of open files (default: maximum). This setting makes sense on Mac OS X because getrlimit() fails to retrieve
correct maximum value. -->
<!-- <max_open_files>262144</max_open_files> -->
<!-- Size of cache of uncompressed blocks of data, used in tables of MergeTree family.
In bytes. Cache is single for server. Memory is allocated only on demand.
Cache is used when 'use_uncompressed_cache' user setting turned on (off by default).
Uncompressed cache is advantageous only for very short queries and in rare cases.
-->
<uncompressed_cache_size>8589934592</uncompressed_cache_size>
<!-- Approximate size of mark cache, used in tables of MergeTree family.
In bytes. Cache is single for server. Memory is allocated only on demand.
You should not lower this value.
-->
<mark_cache_size>5368709120</mark_cache_size>
<!-- Path to data directory, with trailing slash. -->
<path>/var/lib/clickhouse/</path>
<!-- Path to temporary data for processing hard queries. -->
<tmp_path>/var/lib/clickhouse/tmp/</tmp_path>
<!-- Directory with user provided files that are accessible by 'file' table function. -->
<user_files_path>/var/lib/clickhouse/user_files/</user_files_path>
<!-- Path to folder where users and roles created by SQL commands are stored. -->
<access_control_path>/var/lib/clickhouse/access/</access_control_path>
<!-- Path to configuration file with users, access rights, profiles of settings, quotas. -->
<users_config>users.xml</users_config>
<!-- Default profile of settings. -->
<default_profile>default</default_profile>
<!-- System profile of settings. This settings are used by internal processes (Buffer storage, Distibuted DDL worker and so on). -->
<!-- <system_profile>default</system_profile> -->
<!-- Default database. -->
<default_database>default</default_database>
<!-- Server time zone could be set here.
Time zone is used when converting between String and DateTime types,
when printing DateTime in text formats and parsing DateTime from text,
it is used in date and time related functions, if specific time zone was not passed as an argument.
Time zone is specified as identifier from IANA time zone database, like UTC or Africa/Abidjan.
If not specified, system time zone at server startup is used.
Please note, that server could display time zone alias instead of specified name.
Example: W-SU is an alias for Europe/Moscow and Zulu is an alias for UTC.
-->
<!-- <timezone>Europe/Moscow</timezone> -->
<!-- You can specify umask here (see "man umask"). Server will apply it on startup.
Number is always parsed as octal. Default umask is 027 (other users cannot read logs, data files, etc; group can only read).
-->
<!-- <umask>022</umask> -->
<!-- Perform mlockall after startup to lower first queries latency
and to prevent clickhouse executable from being paged out under high IO load.
Enabling this option is recommended but will lead to increased startup time for up to a few seconds.
-->
<mlock_executable>false</mlock_executable>
<!-- Configuration of clusters that could be used in Distributed tables.
https://clickhouse.yandex/docs/en/table_engines/distributed/
-->
<remote_servers incl="remote" >
<!-- Test only shard config for testing distributed storage -->
<test_shard_localhost>
<shard>
<replica>
<host>localhost</host>
<port>9000</port>
</replica>
</shard>
</test_shard_localhost>
<test_cluster_two_shards_localhost>
<shard>
<replica>
<host>localhost</host>
<port>9000</port>
</replica>
</shard>
<shard>
<replica>
<host>localhost</host>
<port>9000</port>
</replica>
</shard>
</test_cluster_two_shards_localhost>
<test_shard_localhost_secure>
<shard>
<replica>
<host>localhost</host>
<port>9440</port>
<secure>1</secure>
</replica>
</shard>
</test_shard_localhost_secure>
<test_unavailable_shard>
<shard>
<replica>
<host>localhost</host>
<port>9000</port>
</replica>
</shard>
<shard>
<replica>
<host>localhost</host>
<port>1</port>
</replica>
</shard>
</test_unavailable_shard>
</remote_servers>
<!-- If element has 'incl' attribute, then for it's value will be used corresponding substitution from another file.
By default, path to file with substitutions is /etc/metrika.xml. It could be changed in config in 'include_from' element.
Values for substitutions are specified in /yandex/name_of_substitution elements in that file.
-->
<!-- ZooKeeper is used to store metadata about replicas, when using Replicated tables.
Optional. If you don't use replicated tables, you could omit that.
See https://clickhouse.yandex/docs/en/table_engines/replication/
-->
<zookeeper incl="zookeeper" optional="true" />
<!-- Substitutions for parameters of replicated tables.
Optional. If you don't use replicated tables, you could omit that.
See https://clickhouse.yandex/docs/en/table_engines/replication/#creating-replicated-tables
-->
<macros incl="macros" optional="true" />
<!-- Reloading interval for embedded dictionaries, in seconds. Default: 3600. -->
<builtin_dictionaries_reload_interval>3600</builtin_dictionaries_reload_interval>
<!-- Maximum session timeout, in seconds. Default: 3600. -->
<max_session_timeout>3600</max_session_timeout>
<!-- Default session timeout, in seconds. Default: 60. -->
<default_session_timeout>60</default_session_timeout>
<!-- Sending data to Graphite for monitoring. Several sections can be defined. -->
<!--
interval - send every X second
root_path - prefix for keys
hostname_in_path - append hostname to root_path (default = true)
metrics - send data from table system.metrics
events - send data from table system.events
asynchronous_metrics - send data from table system.asynchronous_metrics
-->
<!--
<graphite>
<host>localhost</host>
<port>42000</port>
<timeout>0.1</timeout>
<interval>60</interval>
<root_path>one_min</root_path>
<hostname_in_path>true</hostname_in_path>
<metrics>true</metrics>
<events>true</events>
<asynchronous_metrics>true</asynchronous_metrics>
</graphite>
<graphite>
<host>localhost</host>
<port>42000</port>
<timeout>0.1</timeout>
<interval>1</interval>
<root_path>one_sec</root_path>
<metrics>true</metrics>
<events>true</events>
<asynchronous_metrics>false</asynchronous_metrics>
</graphite>
-->
<!-- Query log. Used only for queries with setting log_queries = 1. -->
<query_log>
<!-- What table to insert data. If table is not exist, it will be created.
When query log structure is changed after system update,
then old table will be renamed and new table will be created automatically.
-->
<database>system</database>
<table>query_log</table>
<!--
PARTITION BY expr https://clickhouse.yandex/docs/en/table_engines/custom_partitioning_key/
Example:
event_date
toMonday(event_date)
toYYYYMM(event_date)
toStartOfHour(event_time)
-->
<partition_by>toYYYYMM(event_date)</partition_by>
<!-- Interval of flushing data. -->
<flush_interval_milliseconds>7500</flush_interval_milliseconds>
</query_log>
<!-- Trace log. Stores stack traces collected by query profilers.
See query_profiler_real_time_period_ns and query_profiler_cpu_time_period_ns settings. -->
<trace_log>
<database>system</database>
<table>trace_log</table>
<partition_by>toYYYYMM(event_date)</partition_by>
<flush_interval_milliseconds>7500</flush_interval_milliseconds>
</trace_log>
<!-- Query thread log. Has information about all threads participated in query execution.
Used only for queries with setting log_query_threads = 1. -->
<query_thread_log>
<database>system</database>
<table>query_thread_log</table>
<partition_by>toYYYYMM(event_date)</partition_by>
<flush_interval_milliseconds>7500</flush_interval_milliseconds>
</query_thread_log>
<!-- Uncomment if use part log.
Part log contains information about all actions with parts in MergeTree tables (creation, deletion, merges, downloads).
<part_log>
<database>system</database>
<table>part_log</table>
<flush_interval_milliseconds>7500</flush_interval_milliseconds>
</part_log>
-->
<!-- Uncomment to write text log into table.
Text log contains all information from usual server log but stores it in structured and efficient way.
<text_log>
<database>system</database>
<table>text_log</table>
<flush_interval_milliseconds>7500</flush_interval_milliseconds>
</text_log>
-->
<!-- Parameters for embedded dictionaries, used in Yandex.Metrica.
See https://clickhouse.yandex/docs/en/dicts/internal_dicts/
-->
<!-- Path to file with region hierarchy. -->
<!-- <path_to_regions_hierarchy_file>/opt/geo/regions_hierarchy.txt</path_to_regions_hierarchy_file> -->
<!-- Path to directory with files containing names of regions -->
<!-- <path_to_regions_names_files>/opt/geo/</path_to_regions_names_files> -->
<!-- Configuration of external dictionaries. See:
https://clickhouse.yandex/docs/en/dicts/external_dicts/
-->
<dictionaries_config>*_dictionary.xml</dictionaries_config>
<!-- Uncomment if you want data to be compressed 30-100% better.
Don't do that if you just started using ClickHouse.
-->
<compression incl="compression">
<!--
<!- - Set of variants. Checked in order. Last matching case wins. If nothing matches, lz4 will be used. - ->
<case>
<!- - Conditions. All must be satisfied. Some conditions may be omitted. - ->
<min_part_size>10000000000</min_part_size> <!- - Min part size in bytes. - ->
<min_part_size_ratio>0.01</min_part_size_ratio> <!- - Min size of part relative to whole table size. - ->
<!- - What compression method to use. - ->
<method>zstd</method>
</case>
-->
</compression>
<!-- Allow to execute distributed DDL queries (CREATE, DROP, ALTER, RENAME) on cluster.
Works only if ZooKeeper is enabled. Comment it if such functionality isn't required. -->
<distributed_ddl>
<!-- Path in ZooKeeper to queue with DDL queries -->
<path>/clickhouse/task_queue/ddl</path>
<!-- Settings from this profile will be used to execute DDL queries -->
<!-- <profile>default</profile> -->
</distributed_ddl>
<!-- Settings to fine tune MergeTree tables. See documentation in source code, in MergeTreeSettings.h -->
<!--
<merge_tree>
<max_suspicious_broken_parts>5</max_suspicious_broken_parts>
</merge_tree>
-->
<!-- Protection from accidental DROP.
If size of a MergeTree table is greater than max_table_size_to_drop (in bytes) than table could not be dropped with any DROP query.
If you want do delete one table and don't want to restart clickhouse-server, you could create special file <clickhouse-path>/flags/force_drop_table and make DROP once.
By default max_table_size_to_drop is 50GB; max_table_size_to_drop=0 allows to DROP any tables.
The same for max_partition_size_to_drop.
Uncomment to disable protection.
-->
<!-- <max_table_size_to_drop>0</max_table_size_to_drop> -->
<!-- <max_partition_size_to_drop>0</max_partition_size_to_drop> -->
<!-- Example of parameters for GraphiteMergeTree table engine -->
<graphite_rollup_example>
<pattern>
<regexp>click_cost</regexp>
<function>any</function>
<retention>
<age>0</age>
<precision>3600</precision>
</retention>
<retention>
<age>86400</age>
<precision>60</precision>
</retention>
</pattern>
<default>
<function>max</function>
<retention>
<age>0</age>
<precision>60</precision>
</retention>
<retention>
<age>3600</age>
<precision>300</precision>
</retention>
<retention>
<age>86400</age>
<precision>3600</precision>
</retention>
</default>
</graphite_rollup_example>
<!-- Directory in <clickhouse-path> containing schema files for various input formats.
The directory will be created if it doesn't exist.
-->
<format_schema_path>/var/lib/clickhouse/format_schemas/</format_schema_path>
<!-- Uncomment to disable ClickHouse internal DNS caching. -->
<!-- <disable_internal_dns_cache>1</disable_internal_dns_cache> -->
</yandex>

View File

@ -0,0 +1,8 @@
-----BEGIN DH PARAMETERS-----
MIIBCAKCAQEAua92DDli13gJ+//ZXyGaggjIuidqB0crXfhUlsrBk9BV1hH3i7fR
XGP9rUdk2ubnB3k2ejBStL5oBrkHm9SzUFSQHqfDjLZjKoUpOEmuDc4cHvX1XTR5
Pr1vf5cd0yEncJWG5W4zyUB8k++SUdL2qaeslSs+f491HBLDYn/h8zCgRbBvxhxb
9qeho1xcbnWeqkN6Kc9bgGozA16P9NLuuLttNnOblkH+lMBf42BSne/TWt3AlGZf
slKmmZcySUhF8aKfJnLKbkBCFqOtFRh8zBA9a7g+BT/lSANATCDPaAk1YVih2EKb
dpc3briTDbRsiqg2JKMI7+VdULY9bh3EawIBAg==
-----END DH PARAMETERS-----

View File

@ -0,0 +1,19 @@
-----BEGIN CERTIFICATE-----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-----END CERTIFICATE-----

View File

@ -0,0 +1,28 @@
-----BEGIN PRIVATE KEY-----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-----END PRIVATE KEY-----

View File

@ -0,0 +1,133 @@
<?xml version="1.0"?>
<yandex>
<!-- Profiles of settings. -->
<profiles>
<!-- Default settings. -->
<default>
<!-- Maximum memory usage for processing single query, in bytes. -->
<max_memory_usage>10000000000</max_memory_usage>
<!-- Use cache of uncompressed blocks of data. Meaningful only for processing many of very short queries. -->
<use_uncompressed_cache>0</use_uncompressed_cache>
<!-- How to choose between replicas during distributed query processing.
random - choose random replica from set of replicas with minimum number of errors
nearest_hostname - from set of replicas with minimum number of errors, choose replica
with minimum number of different symbols between replica's hostname and local hostname
(Hamming distance).
in_order - first live replica is chosen in specified order.
first_or_random - if first replica one has higher number of errors, pick a random one from replicas with minimum number of errors.
-->
<load_balancing>random</load_balancing>
</default>
<!-- Profile that allows only read queries. -->
<readonly>
<readonly>1</readonly>
</readonly>
</profiles>
<!-- Users and ACL. -->
<users>
<!-- If user name was not specified, 'default' user is used. -->
<default>
<!-- Password could be specified in plaintext or in SHA256 (in hex format).
If you want to specify password in plaintext (not recommended), place it in 'password' element.
Example: <password>qwerty</password>.
Password could be empty.
If you want to specify SHA256, place it in 'password_sha256_hex' element.
Example: <password_sha256_hex>65e84be33532fb784c48129675f9eff3a682b27168c0ea744b2cf58ee02337c5</password_sha256_hex>
Restrictions of SHA256: impossibility to connect to ClickHouse using MySQL JS client (as of July 2019).
If you want to specify double SHA1, place it in 'password_double_sha1_hex' element.
Example: <password_double_sha1_hex>e395796d6546b1b65db9d665cd43f0e858dd4303</password_double_sha1_hex>
How to generate decent password:
Execute: PASSWORD=$(base64 < /dev/urandom | head -c8); echo "$PASSWORD"; echo -n "$PASSWORD" | sha256sum | tr -d '-'
In first line will be password and in second - corresponding SHA256.
How to generate double SHA1:
Execute: PASSWORD=$(base64 < /dev/urandom | head -c8); echo "$PASSWORD"; echo -n "$PASSWORD" | openssl dgst -sha1 -binary | openssl dgst -sha1
In first line will be password and in second - corresponding double SHA1.
-->
<password></password>
<!-- List of networks with open access.
To open access from everywhere, specify:
<ip>::/0</ip>
To open access only from localhost, specify:
<ip>::1</ip>
<ip>127.0.0.1</ip>
Each element of list has one of the following forms:
<ip> IP-address or network mask. Examples: 213.180.204.3 or 10.0.0.1/8 or 10.0.0.1/255.255.255.0
2a02:6b8::3 or 2a02:6b8::3/64 or 2a02:6b8::3/ffff:ffff:ffff:ffff::.
<host> Hostname. Example: server01.yandex.ru.
To check access, DNS query is performed, and all received addresses compared to peer address.
<host_regexp> Regular expression for host names. Example, ^server\d\d-\d\d-\d\.yandex\.ru$
To check access, DNS PTR query is performed for peer address and then regexp is applied.
Then, for result of PTR query, another DNS query is performed and all received addresses compared to peer address.
Strongly recommended that regexp is ends with $
All results of DNS requests are cached till server restart.
-->
<networks incl="networks" replace="replace">
<ip>::/0</ip>
</networks>
<!-- Settings profile for user. -->
<profile>default</profile>
<!-- Quota for user. -->
<quota>default</quota>
<!-- Allow access management -->
<access_management>1</access_management>
<!-- Example of row level security policy. -->
<!-- <databases>
<test>
<filtered_table1>
<filter>a = 1</filter>
</filtered_table1>
<filtered_table2>
<filter>a + b &lt; 1 or c - d &gt; 5</filter>
</filtered_table2>
</test>
</databases> -->
</default>
<!-- Example of user with readonly access. -->
<!-- <readonly>
<password></password>
<networks incl="networks" replace="replace">
<ip>::1</ip>
<ip>127.0.0.1</ip>
</networks>
<profile>readonly</profile>
<quota>default</quota>
</readonly> -->
</users>
<!-- Quotas. -->
<quotas>
<!-- Name of quota. -->
<default>
<!-- Limits for time interval. You could specify many intervals with different limits. -->
<interval>
<!-- Length of interval. -->
<duration>3600</duration>
<!-- No limits. Just calculate resource usage for time interval. -->
<queries>0</queries>
<errors>0</errors>
<result_rows>0</result_rows>
<read_rows>0</read_rows>
<execution_time>0</execution_time>
</interval>
</default>
</quotas>
</yandex>

View File

@ -0,0 +1,8 @@
<?xml version="1.0"?>
<yandex>
<macros>
<replica>clickhouse1</replica>
<shard>01</shard>
<shard2>01</shard2>
</macros>
</yandex>

View File

@ -0,0 +1,8 @@
<?xml version="1.0"?>
<yandex>
<macros>
<replica>clickhouse2</replica>
<shard>01</shard>
<shard2>02</shard2>
</macros>
</yandex>

View File

@ -0,0 +1,8 @@
<?xml version="1.0"?>
<yandex>
<macros>
<replica>clickhouse3</replica>
<shard>01</shard>
<shard2>03</shard2>
</macros>
</yandex>

View File

@ -0,0 +1,28 @@
version: '2.3'
services:
clickhouse:
image: yandex/clickhouse-integration-test
expose:
- "9000"
- "9009"
- "8123"
volumes:
- "${CLICKHOUSE_TESTS_DIR}/configs/clickhouse/config.d:/etc/clickhouse-server/config.d"
- "${CLICKHOUSE_TESTS_DIR}/configs/clickhouse/users.d/:/etc/clickhouse-server/users.d"
- "${CLICKHOUSE_TESTS_DIR}/configs/clickhouse/ssl:/etc/clickhouse-server/ssl"
- "${CLICKHOUSE_TESTS_DIR}/configs/clickhouse/config.xml:/etc/clickhouse-server/config.xml"
- "${CLICKHOUSE_TESTS_DIR}/configs/clickhouse/users.xml:/etc/clickhouse-server/users.xml"
- "${CLICKHOUSE_TESTS_SERVER_BIN_PATH:-/usr/bin/clickhouse}:/usr/bin/clickhouse"
- "${CLICKHOUSE_TESTS_ODBC_BRIDGE_BIN_PATH:-/usr/bin/clickhouse-odbc-bridge}:/usr/bin/clickhouse-odbc-bridge"
entrypoint: bash -c "clickhouse server --config-file=/etc/clickhouse-server/config.xml --log-file=/var/log/clickhouse-server/clickhouse-server.log --errorlog-file=/var/log/clickhouse-server/clickhouse-server.err.log"
healthcheck:
test: clickhouse client --query='select 1'
interval: 3s
timeout: 2s
retries: 40
start_period: 2s
cap_add:
- SYS_PTRACE
security_opt:
- label:disable

View File

@ -0,0 +1,61 @@
version: '2.3'
services:
zookeeper:
extends:
file: zookeeper-service.yml
service: zookeeper
clickhouse1:
extends:
file: clickhouse-service.yml
service: clickhouse
hostname: clickhouse1
volumes:
- "${CLICKHOUSE_TESTS_DIR}/_instances/clickhouse1/database/:/var/lib/clickhouse/"
- "${CLICKHOUSE_TESTS_DIR}/_instances/clickhouse1/logs/:/var/log/clickhouse-server/"
- "${CLICKHOUSE_TESTS_DIR}/configs/clickhouse1/config.d:/etc/clickhouse-server/config.d"
- "${CLICKHOUSE_TESTS_DIR}/configs/clickhouse1/users.d:/etc/clickhouse-server/users.d"
depends_on:
zookeeper:
condition: service_healthy
clickhouse2:
extends:
file: clickhouse-service.yml
service: clickhouse
hostname: clickhouse2
volumes:
- "${CLICKHOUSE_TESTS_DIR}/_instances/clickhouse2/database/:/var/lib/clickhouse/"
- "${CLICKHOUSE_TESTS_DIR}/_instances/clickhouse2/logs/:/var/log/clickhouse-server/"
- "${CLICKHOUSE_TESTS_DIR}/configs/clickhouse2/config.d:/etc/clickhouse-server/config.d"
- "${CLICKHOUSE_TESTS_DIR}/configs/clickhouse2/users.d:/etc/clickhouse-server/users.d"
depends_on:
zookeeper:
condition: service_healthy
clickhouse3:
extends:
file: clickhouse-service.yml
service: clickhouse
hostname: clickhouse3
volumes:
- "${CLICKHOUSE_TESTS_DIR}/_instances/clickhouse3/database/:/var/lib/clickhouse/"
- "${CLICKHOUSE_TESTS_DIR}/_instances/clickhouse3/logs/:/var/log/clickhouse-server/"
- "${CLICKHOUSE_TESTS_DIR}/configs/clickhouse3/config.d:/etc/clickhouse-server/config.d"
- "${CLICKHOUSE_TESTS_DIR}/configs/clickhouse3/users.d:/etc/clickhouse-server/users.d"
depends_on:
zookeeper:
condition: service_healthy
all_services_ready:
image: hello-world
depends_on:
clickhouse1:
condition: service_healthy
clickhouse2:
condition: service_healthy
clickhouse3:
condition: service_healthy
zookeeper:
condition: service_healthy

View File

@ -0,0 +1,18 @@
version: '2.3'
services:
zookeeper:
image: zookeeper:3.4.12
expose:
- "2181"
environment:
ZOO_TICK_TIME: 500
ZOO_MY_ID: 1
healthcheck:
test: echo stat | nc localhost 2181
interval: 3s
timeout: 2s
retries: 5
start_period: 2s
security_opt:
- label:disable

View File

@ -0,0 +1,79 @@
#!/usr/bin/env python3
import sys
from testflows.core import *
append_path(sys.path, "..")
from helpers.cluster import Cluster
from helpers.argparser import argparser
from datetime64_extended_range.requirements import *
from datetime64_extended_range.common import *
# cross-outs
# https://github.com/ClickHouse/ClickHouse/issues/16581#issuecomment-804360350: 128 and 256-bit types are not supported for now
# https://github.com/ClickHouse/ClickHouse/issues/17079#issuecomment-783396589 : leap seconds unsupported
# https://github.com/ClickHouse/ClickHouse/issues/22824 : dateDiff not working woth dt64
# https://github.com/ClickHouse/ClickHouse/issues/22852 : formatDateTime wrong value
# https://github.com/ClickHouse/ClickHouse/issues/22854 : timeSlot(), toMonday() wrong when out of normal
# https://github.com/ClickHouse/ClickHouse/issues/16260 : timeSlots(), dateDiff() not working with DT64
# https://github.com/ClickHouse/ClickHouse/issues/22927#issuecomment-816574952 : toRelative...Num() wrong when out of normal range
# https://github.com/ClickHouse/ClickHouse/issues/22928 : toStartOf...() wrong when out of normal range
# https://github.com/ClickHouse/ClickHouse/issues/22929 : toUnixTimestamp() exception when out of normal
# https://github.com/ClickHouse/ClickHouse/issues/22930 : toWeek()
# https://github.com/ClickHouse/ClickHouse/issues/22948 : toYearWeek()
# https://github.com/ClickHouse/ClickHouse/issues/22959 : toUnixTimestamp64*() wrong fractal seconds treatment
# For `reference times` test it is unclear how to evaluate correctness - majority of test cases are correct, and ONLY
# Juba and Monrovia timezones are damaged - probably, due to wrong DST shifts lookup tables
xfails = {
"type conversion/to int 8 16 32 64 128 256/:": [(Fail, "https://github.com/ClickHouse/ClickHouse/issues/16581#issuecomment-804360350")],
"type conversion/to uint 8 16 32 64 256/:": [(Fail, "https://github.com/ClickHouse/ClickHouse/issues/16581#issuecomment-804360350")],
"non existent time/leap seconds/:": [(Fail, "https://github.com/ClickHouse/ClickHouse/issues/17079#issuecomment-783396589")],
"date time funcs/date diff/:": [(Fail, "https://github.com/ClickHouse/ClickHouse/issues/22824")],
"date time funcs/format date time/:": [(Fail, "https://github.com/ClickHouse/ClickHouse/issues/22852")],
"date time funcs/time slot/:": [(Fail, "https://github.com/ClickHouse/ClickHouse/issues/22854")],
"date time funcs/to monday/:": [(Fail, "https://github.com/ClickHouse/ClickHouse/issues/22854")],
"date time funcs/time slots/:": [(Fail, "https://github.com/ClickHouse/ClickHouse/issues/16260")],
"date time funcs/to relative :/:": [(Fail, "https://github.com/ClickHouse/ClickHouse/issues/22927#issuecomment-816574952")],
"date time funcs/to start of :/:": [(Fail, "https://github.com/ClickHouse/ClickHouse/issues/22928")],
"date time funcs/to unix timestamp/:": [(Fail, "https://github.com/ClickHouse/ClickHouse/issues/22929")],
"date time funcs/to week/:": [(Fail, "https://github.com/ClickHouse/ClickHouse/issues/22930")],
"date time funcs/to year week/:": [(Fail, "https://github.com/ClickHouse/ClickHouse/issues/22948")],
"type conversion/to unix timestamp64 */:": [(Fail, "https://github.com/ClickHouse/ClickHouse/issues/22959")],
"type conversion/from unix timestamp64 */:": [(Fail, "https://github.com/ClickHouse/ClickHouse/issues/22959")],
"type conversion/to int 8 16 32 64 128 256/:": [(Fail, "https://github.com/ClickHouse/ClickHouse/issues/16581#issuecomment-804360350")],
"reference times/:": [(Fail, "check procedure unclear")],
}
@TestModule
@Name("datetime64 extended range")
@ArgumentParser(argparser)
@Specifications(
QA_SRS010_ClickHouse_DateTime64_Extended_Range
)
@Requirements(
RQ_SRS_010_DateTime64_ExtendedRange("1.0"),
)
@XFails(xfails)
def regression(self, local, clickhouse_binary_path, parallel=False, stress=False):
"""ClickHouse DateTime64 Extended Range regression module.
"""
nodes = {
"clickhouse": ("clickhouse1", "clickhouse2", "clickhouse3"),
}
with Cluster(local, clickhouse_binary_path, nodes=nodes) as cluster:
self.context.cluster = cluster
self.context.parallel = parallel
self.context.stress = stress
Scenario(run=load("datetime64_extended_range.tests.generic", "generic"), flags=TE)
Scenario(run=load("datetime64_extended_range.tests.non_existent_time", "feature"), flags=TE)
Scenario(run=load("datetime64_extended_range.tests.reference_times", "reference_times"), flags=TE)
Scenario(run=load("datetime64_extended_range.tests.date_time_functions", "date_time_funcs"), flags=TE)
Scenario(run=load("datetime64_extended_range.tests.type_conversion", "type_conversion"), flags=TE)
if main():
regression()

View File

@ -0,0 +1 @@
from .requirements import *

View File

@ -0,0 +1,805 @@
# QA-SRS010 ClickHouse DateTime64 Extended Range
# Software Requirements Specification
## Table of Contents
* 1 [Revision History](#revision-history)
* 2 [Introduction](#introduction)
* 3 [Terminology](#terminology)
* 3.1 [SRS](#srs)
* 3.2 [Normal Date Range](#normal-date-range)
* 3.3 [Extended Date Range](#extended-date-range)
* 4 [Requirements](#requirements)
* 4.1 [Generic](#generic)
* 4.1.0.1 [RQ.SRS-010.DateTime64.ExtendedRange](#rqsrs-010datetime64extendedrange)
* 4.1.0.2 [RQ.SRS-010.DateTime64.ExtendedRange.NormalRange.Start](#rqsrs-010datetime64extendedrangenormalrangestart)
* 4.1.0.3 [RQ.SRS-010.DateTime64.ExtendedRange.NormalRange.Start.BeforeEpochForTimeZone](#rqsrs-010datetime64extendedrangenormalrangestartbeforeepochfortimezone)
* 4.1.0.4 [RQ.SRS-010.DateTime64.ExtendedRange.NormalRange.End](#rqsrs-010datetime64extendedrangenormalrangeend)
* 4.1.0.5 [RQ.SRS-010.DateTime64.ExtendedRange.NormalRange.End.AfterEpochForTimeZone](#rqsrs-010datetime64extendedrangenormalrangeendafterepochfortimezone)
* 4.1.0.6 [RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions](#rqsrs-010datetime64extendedrangetypeconversionfunctions)
* 4.1.0.7 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions](#rqsrs-010datetime64extendedrangedatesandtimesfunctions)
* 4.1.0.8 [RQ.SRS-010.DateTime64.ExtendedRange.TimeZones](#rqsrs-010datetime64extendedrangetimezones)
* 4.1.0.9 [RQ.SRS-010.DateTime64.ExtendedRange.NonExistentTime](#rqsrs-010datetime64extendedrangenonexistenttime)
* 4.1.0.10 [RQ.SRS-010.DateTime64.ExtendedRange.Comparison](#rqsrs-010datetime64extendedrangecomparison)
* 4.1.0.11 [RQ.SRS-010.DateTime64.ExtendedRange.SpecificTimestamps](#rqsrs-010datetime64extendedrangespecifictimestamps)
* 4.2 [Specific](#specific)
* 4.2.0.1 [RQ.SRS-010.DateTime64.ExtendedRange.Start](#rqsrs-010datetime64extendedrangestart)
* 4.2.0.2 [RQ.SRS-010.DateTime64.ExtendedRange.End](#rqsrs-010datetime64extendedrangeend)
* 4.2.0.3 [Non-Existent Time](#non-existent-time)
* 4.2.0.3.1 [RQ.SRS-010.DateTime64.ExtendedRange.NonExistentTime.InvalidDate](#rqsrs-010datetime64extendedrangenonexistenttimeinvaliddate)
* 4.2.0.3.2 [RQ.SRS-010.DateTime64.ExtendedRange.NonExistentTime.InvalidTime](#rqsrs-010datetime64extendedrangenonexistenttimeinvalidtime)
* 4.2.0.3.3 [RQ.SRS-010.DateTime64.ExtendedRange.NonExistentTime.TimeZoneSwitch](#rqsrs-010datetime64extendedrangenonexistenttimetimezoneswitch)
* 4.2.0.3.4 [RQ.SRS-010.DateTime64.ExtendedRange.NonExistentTime.DaylightSavingTime](#rqsrs-010datetime64extendedrangenonexistenttimedaylightsavingtime)
* 4.2.0.3.5 [RQ.SRS-010.DateTime64.ExtendedRange.NonExistentTime.DaylightSavingTime.Disappeared](#rqsrs-010datetime64extendedrangenonexistenttimedaylightsavingtimedisappeared)
* 4.2.0.3.6 [RQ.SRS-010.DateTime64.ExtendedRange.NonExistentTime.LeapSeconds](#rqsrs-010datetime64extendedrangenonexistenttimeleapseconds)
* 4.2.0.4 [Dates And Times Functions](#dates-and-times-functions)
* 4.2.0.4.1 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toTimeZone](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstotimezone)
* 4.2.0.4.2 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toYear](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstoyear)
* 4.2.0.4.3 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toQuarter](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstoquarter)
* 4.2.0.4.4 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toMonth](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstomonth)
* 4.2.0.4.5 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toDayOfYear](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstodayofyear)
* 4.2.0.4.6 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toDayOfMonth](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstodayofmonth)
* 4.2.0.4.7 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toDayOfWeek](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstodayofweek)
* 4.2.0.4.8 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toHour](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstohour)
* 4.2.0.4.9 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toMinute](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstominute)
* 4.2.0.4.10 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toSecond](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstosecond)
* 4.2.0.4.11 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toUnixTimestamp](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstounixtimestamp)
* 4.2.0.4.12 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toStartOfYear](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstostartofyear)
* 4.2.0.4.13 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toStartOfISOYear](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstostartofisoyear)
* 4.2.0.4.14 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toStartOfQuarter](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstostartofquarter)
* 4.2.0.4.15 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toStartOfMonth](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstostartofmonth)
* 4.2.0.4.16 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toMonday](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstomonday)
* 4.2.0.4.17 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toStartOfWeek](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstostartofweek)
* 4.2.0.4.18 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toStartOfDay](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstostartofday)
* 4.2.0.4.19 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toStartOfHour](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstostartofhour)
* 4.2.0.4.20 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toStartOfMinute](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstostartofminute)
* 4.2.0.4.21 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toStartOfSecond](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstostartofsecond)
* 4.2.0.4.22 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toStartOfFiveMinute](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstostartoffiveminute)
* 4.2.0.4.23 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toStartOfTenMinutes](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstostartoftenminutes)
* 4.2.0.4.24 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toStartOfFifteenMinutes](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstostartoffifteenminutes)
* 4.2.0.4.25 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toStartOfInterval](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstostartofinterval)
* 4.2.0.4.26 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toTime](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstotime)
* 4.2.0.4.27 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toRelativeYearNum](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstorelativeyearnum)
* 4.2.0.4.28 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toRelativeQuarterNum](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstorelativequarternum)
* 4.2.0.4.29 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toRelativeMonthNum](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstorelativemonthnum)
* 4.2.0.4.30 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toRelativeWeekNum](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstorelativeweeknum)
* 4.2.0.4.31 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toRelativeDayNum](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstorelativedaynum)
* 4.2.0.4.32 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toRelativeHourNum](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstorelativehournum)
* 4.2.0.4.33 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toRelativeMinuteNum](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstorelativeminutenum)
* 4.2.0.4.34 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toRelativeSecondNum](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstorelativesecondnum)
* 4.2.0.4.35 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toISOYear](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstoisoyear)
* 4.2.0.4.36 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toISOWeek](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstoisoweek)
* 4.2.0.4.37 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toWeek](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstoweek)
* 4.2.0.4.38 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toYearWeek](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstoyearweek)
* 4.2.0.4.39 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.now](#rqsrs-010datetime64extendedrangedatesandtimesfunctionsnow)
* 4.2.0.4.40 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.today](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstoday)
* 4.2.0.4.41 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.yesterday](#rqsrs-010datetime64extendedrangedatesandtimesfunctionsyesterday)
* 4.2.0.4.42 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.timeSlot](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstimeslot)
* 4.2.0.4.43 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toYYYYMM](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstoyyyymm)
* 4.2.0.4.44 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toYYYYMMDD](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstoyyyymmdd)
* 4.2.0.4.45 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toYYYYMMDDhhmmss](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstoyyyymmddhhmmss)
* 4.2.0.4.46 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.addYears](#rqsrs-010datetime64extendedrangedatesandtimesfunctionsaddyears)
* 4.2.0.4.47 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.addMonths](#rqsrs-010datetime64extendedrangedatesandtimesfunctionsaddmonths)
* 4.2.0.4.48 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.addWeeks](#rqsrs-010datetime64extendedrangedatesandtimesfunctionsaddweeks)
* 4.2.0.4.49 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.addDays](#rqsrs-010datetime64extendedrangedatesandtimesfunctionsadddays)
* 4.2.0.4.50 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.addHours](#rqsrs-010datetime64extendedrangedatesandtimesfunctionsaddhours)
* 4.2.0.4.51 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.addMinutes](#rqsrs-010datetime64extendedrangedatesandtimesfunctionsaddminutes)
* 4.2.0.4.52 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.addSeconds](#rqsrs-010datetime64extendedrangedatesandtimesfunctionsaddseconds)
* 4.2.0.4.53 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.addQuarters](#rqsrs-010datetime64extendedrangedatesandtimesfunctionsaddquarters)
* 4.2.0.4.54 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.subtractYears](#rqsrs-010datetime64extendedrangedatesandtimesfunctionssubtractyears)
* 4.2.0.4.55 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.subtractMonths](#rqsrs-010datetime64extendedrangedatesandtimesfunctionssubtractmonths)
* 4.2.0.4.56 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.subtractWeeks](#rqsrs-010datetime64extendedrangedatesandtimesfunctionssubtractweeks)
* 4.2.0.4.57 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.subtractDays](#rqsrs-010datetime64extendedrangedatesandtimesfunctionssubtractdays)
* 4.2.0.4.58 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.subtractHours](#rqsrs-010datetime64extendedrangedatesandtimesfunctionssubtracthours)
* 4.2.0.4.59 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.subtractMinutes](#rqsrs-010datetime64extendedrangedatesandtimesfunctionssubtractminutes)
* 4.2.0.4.60 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.subtractSeconds](#rqsrs-010datetime64extendedrangedatesandtimesfunctionssubtractseconds)
* 4.2.0.4.61 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.subtractQuarters](#rqsrs-010datetime64extendedrangedatesandtimesfunctionssubtractquarters)
* 4.2.0.4.62 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.dateDiff](#rqsrs-010datetime64extendedrangedatesandtimesfunctionsdatediff)
* 4.2.0.4.63 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.timeSlots](#rqsrs-010datetime64extendedrangedatesandtimesfunctionstimeslots)
* 4.2.0.4.64 [RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.formatDateTime](#rqsrs-010datetime64extendedrangedatesandtimesfunctionsformatdatetime)
* 4.2.1 [Type Conversion Functions](#type-conversion-functions)
* 4.2.1.4.1 [RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.toInt(8|16|32|64|128|256)](#rqsrs-010datetime64extendedrangetypeconversionfunctionstoint8163264128256)
* 4.2.1.4.2 [RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.toUInt(8|16|32|64|256)](#rqsrs-010datetime64extendedrangetypeconversionfunctionstouint8163264256)
* 4.2.1.4.3 [RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.toFloat(32|64)](#rqsrs-010datetime64extendedrangetypeconversionfunctionstofloat3264)
* 4.2.1.4.4 [RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.toDate](#rqsrs-010datetime64extendedrangetypeconversionfunctionstodate)
* 4.2.1.4.5 [RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.toDateTime](#rqsrs-010datetime64extendedrangetypeconversionfunctionstodatetime)
* 4.2.1.4.6 [RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.toDateTime64](#rqsrs-010datetime64extendedrangetypeconversionfunctionstodatetime64)
* 4.2.1.4.7 [RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.toDateTime64.FromString.MissingTime](#rqsrs-010datetime64extendedrangetypeconversionfunctionstodatetime64fromstringmissingtime)
* 4.2.1.4.8 [RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.toDecimal(32|64|128|256)](#rqsrs-010datetime64extendedrangetypeconversionfunctionstodecimal3264128256)
* 4.2.1.4.9 [RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.toString](#rqsrs-010datetime64extendedrangetypeconversionfunctionstostring)
* 4.2.1.4.10 [RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.CAST(x,T)](#rqsrs-010datetime64extendedrangetypeconversionfunctionscastxt)
* 4.2.1.4.11 [RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.toUnixTimestamp64Milli](#rqsrs-010datetime64extendedrangetypeconversionfunctionstounixtimestamp64milli)
* 4.2.1.4.12 [RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.toUnixTimestamp64Micro](#rqsrs-010datetime64extendedrangetypeconversionfunctionstounixtimestamp64micro)
* 4.2.1.4.13 [RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.toUnixTimestamp64Nano](#rqsrs-010datetime64extendedrangetypeconversionfunctionstounixtimestamp64nano)
* 4.2.1.4.14 [RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.fromUnixTimestamp64Milli](#rqsrs-010datetime64extendedrangetypeconversionfunctionsfromunixtimestamp64milli)
* 4.2.1.4.15 [RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.fromUnixTimestamp64Micro](#rqsrs-010datetime64extendedrangetypeconversionfunctionsfromunixtimestamp64micro)
* 4.2.1.4.16 [RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.fromUnixTimestamp64Nano](#rqsrs-010datetime64extendedrangetypeconversionfunctionsfromunixtimestamp64nano)
* 5 [References](#references)
## Revision History
This document is stored in an electronic form using [Git] source control management software
hosted in a [GitHub Repository].
All the updates are tracked using the [Revision History].
## Introduction
This document will cover requirements to support extended range for the [DateTime64] data type
that is outside the normal **1970** (1970-01-02 00:00:00 UTC) to **2105** (2105-12-31 23:59:59.99999 UTC) date range.
## Terminology
### SRS
Software Requirements Specification
### Normal Date Range
**1970** `1970-01-02T00:00:00.000000` to **2105** `2105-12-31T23:59:59.99999`
### Extended Date Range
**1925** `1925-01-01T00:00:00.000000` to **2238** `2238-12-31 23:59:59.99999`
## Requirements
### Generic
##### RQ.SRS-010.DateTime64.ExtendedRange
version: 1.0
[ClickHouse] SHALL support extended range for the [DateTime64] data type that includes dates from the year **1925** to **2238**.
##### RQ.SRS-010.DateTime64.ExtendedRange.NormalRange.Start
version: 1.0
[ClickHouse] SHALL support proper time handling around the normal date range that starts at `1970-01-01 00:00:00.000`
expressed using the [ISO 8601 format].
##### RQ.SRS-010.DateTime64.ExtendedRange.NormalRange.Start.BeforeEpochForTimeZone
version: 1.0
[ClickHouse] SHALL support proper time handling around the start of the [normal date range]
when this time for the time zone is before the start of the [normal date range].
##### RQ.SRS-010.DateTime64.ExtendedRange.NormalRange.End
version: 1.0
[ClickHouse] SHALL support proper time handling around the normal date range that ends at `2105-12-31T23:59:59.99999`
expressed using the [ISO 8601 format].
##### RQ.SRS-010.DateTime64.ExtendedRange.NormalRange.End.AfterEpochForTimeZone
version: 1.0
[ClickHouse] SHALL support proper time handling around the end of the [normal date range]
when this time for the time zone is after the end of the [normal date range].
##### RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions
version: 1.0
[ClickHouse] SHALL support proper conversion to and from [DateTime64] data type from other data types.
##### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions
version: 1.0
[ClickHouse] SHALL support correct operation of the [Dates and Times Functions] with the [DateTime64] data type
when it stores dates within the [normal date range] and the [extended date range].
##### RQ.SRS-010.DateTime64.ExtendedRange.TimeZones
version: 1.0
[ClickHouse] SHALL support correct operation with the [DateTime64] extended range data type
when combined with a supported time zone.
##### RQ.SRS-010.DateTime64.ExtendedRange.NonExistentTime
version: 1.0
[ClickHouse] SHALL support proper handling of non-existent times when using [DateTime64] extended range data type.
##### RQ.SRS-010.DateTime64.ExtendedRange.Comparison
version: 1.0
[ClickHouse] SHALL support proper handling of time comparison when using [DateTime64] extended range data type.
For example, `SELECT toDateTime64('2019-05-05 20:20:12.050', 3) < now()`.
##### RQ.SRS-010.DateTime64.ExtendedRange.SpecificTimestamps
version: 1.0
[ClickHouse] SHALL properly work with the following timestamps in all supported timezones:
```
[9961200,73476000,325666800,354675600,370400400,386125200,388566010,401850000,417574811,496803600,528253200,624423614,636516015,671011200,717555600,752047218,859683600,922582800,1018173600,1035705600,1143334800,1162105223,1174784400,1194156000,1206838823,1224982823,1236495624,1319936400,1319936424,1425798025,1459040400,1509872400,2090451627,2140668000]
```
### Specific
##### RQ.SRS-010.DateTime64.ExtendedRange.Start
version: 1.0
[ClickHouse] SHALL support extended range for the [DateTime64] data type that starts at `1925-01-01T00:00:00.000000`
expressed using the [ISO 8601 format].
##### RQ.SRS-010.DateTime64.ExtendedRange.End
version: 1.0
[ClickHouse] SHALL support extended range for the [DateTime64] data type that ends at `2238-12-31T23:59:59.999999`
expressed using the [ISO 8601 format].
##### Non-Existent Time
###### RQ.SRS-010.DateTime64.ExtendedRange.NonExistentTime.InvalidDate
version: 1.0
[ClickHouse] SHALL support proper handling of invalid dates when using [DateTime64] extended range data type,
such as:
* `YYYY-04-31, YYYY-06-31, YYYY-09-31, YYYY-11-31`
* `1990-02-30 00:00:02`
###### RQ.SRS-010.DateTime64.ExtendedRange.NonExistentTime.InvalidTime
version: 1.0
[ClickHouse] SHALL support proper handling of invalid time for a timezone
when using [DateTime64] extended range data type, for example,
* `2002-04-07 02:30:00` never happened at all in the US/Eastern timezone ([Stuart Bishop: pytz library](http://pytz.sourceforge.net/#problems-with-localtime))
###### RQ.SRS-010.DateTime64.ExtendedRange.NonExistentTime.TimeZoneSwitch
version: 1.0
[ClickHouse] SHALL support proper handling of invalid time when using [DateTime64] extended range data type
when the invalid time is caused when *countries switch timezone definitions with no
daylight savings time switch* [Stuart Bishop: pytz library](http://pytz.sourceforge.net/#problems-with-localtime).
>
> For example, in 1915 Warsaw switched from Warsaw time to Central European time with
> no daylight savings transition. So at the stroke of midnight on August 5th 1915 the clocks
> were wound back 24 minutes creating an ambiguous time period that cannot be specified without
> referring to the timezone abbreviation or the actual UTC offset. In this case midnight happened twice,
> neither time during a daylight saving time period. pytz handles this transition by treating the ambiguous
> period before the switch as daylight savings time, and the ambiguous period after as standard time.
>
> [Stuart Bishop: pytz library](http://pytz.sourceforge.net/#problems-with-localtime)
###### RQ.SRS-010.DateTime64.ExtendedRange.NonExistentTime.DaylightSavingTime
version: 1.0
[ClickHouse] SHALL support proper handling of invalid time when using [DateTime64] extended range data type
when for a given timezone time switches from standard to daylight saving.
> For example, in the US/Eastern timezone on the last Sunday morning in October, the following sequence happens:
>
> 01:00 EDT occurs
> 1 hour later, instead of 2:00am the clock is turned back 1 hour and 01:00 happens again (this time 01:00 EST)
> In fact, every instant between 01:00 and 02:00 occurs twice.
> [Stuart Bishop: pytz library](http://pytz.sourceforge.net/#problems-with-localtime)
###### RQ.SRS-010.DateTime64.ExtendedRange.NonExistentTime.DaylightSavingTime.Disappeared
version: 1.0
[ClickHouse] SHALL support proper handling of invalid time when using [DateTime64] extended range data type
for a given timezone when transition from the standard to daylight saving time causes an hour to disappear.
Expected behavior: if DateTime64 initialized by a skipped time value, it is being treated as DST and resulting value will be an hour earlier, e.g. `SELECT toDateTime64('2020-03-08 02:34:00', 0, 'America/Denver')` returns `2020-03-08 01:34:00`.
###### RQ.SRS-010.DateTime64.ExtendedRange.NonExistentTime.LeapSeconds
version: 1.0
[ClickHouse] SHALL support proper handling of leap seconds adjustments when using [DateTime64] extended range data type.
##### Dates And Times Functions
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toTimeZone
version: 1.0
[ClickHouse] SHALL support correct operation of the [toTimeZone](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#totimezone)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toYear
version: 1.0
[ClickHouse] SHALL support correct operation of the [toYear](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#toyear)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toQuarter
version: 1.0
[ClickHouse] SHALL support correct operation of the [toQuarter](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#toquarter)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toMonth
version: 1.0
[ClickHouse] SHALL support correct operation of the [toMonth](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#tomonth)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toDayOfYear
version: 1.0
[ClickHouse] SHALL support correct operation of the [toDayOfYear](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#todayofyear)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toDayOfMonth
version: 1.0
[ClickHouse] SHALL support correct operation of the [toDayOfMonth](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#todayofmonth)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toDayOfWeek
version: 1.0
[ClickHouse] SHALL support correct operation of the [toDayOfWeek](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#todayofweek)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toHour
version: 1.0
[ClickHouse] SHALL support correct operation of the [toHour](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#tohour)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toMinute
version: 1.0
[ClickHouse] SHALL support correct operation of the [toMinute](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#tominute)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toSecond
version: 1.0
[ClickHouse] SHALL support correct operation of the [toSecond](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#tosecond)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toUnixTimestamp
version: 1.0
[ClickHouse] SHALL support correct operation of the [toUnitTimestamp](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#to-unix-timestamp)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
Timestamp value expected to be negative when DateTime64 value is prior to `1970-01-01` and positine otherwise.
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toStartOfYear
version: 1.0
[ClickHouse] SHALL support correct operation of the [toStartOfYear](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#tostartofyear)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toStartOfISOYear
version: 1.0
[ClickHouse] SHALL support correct operation of the [toStartOfISOYear](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#tostartofisoyear)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toStartOfQuarter
version: 1.0
[ClickHouse] SHALL support correct operation of the [toStartOfQuarter](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#tostartofquarter)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toStartOfMonth
version: 1.0
[ClickHouse] SHALL support correct operation of the [toStartOfMonth](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#tostartofmonth)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toMonday
version: 1.0
[ClickHouse] SHALL support correct operation of the [toMonday](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#tomonday)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toStartOfWeek
version: 1.0
[ClickHouse] SHALL support correct operation of the [toStartOfWeek](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#tostartofweektmode)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toStartOfDay
version: 1.0
[ClickHouse] SHALL support correct operation of the [toStartOfDay](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#tostartofday)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toStartOfHour
version: 1.0
[ClickHouse] SHALL support correct operation of the [toStartOfHour](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#tostartofhour)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toStartOfMinute
version: 1.0
[ClickHouse] SHALL support correct operation of the [toStartOfMinute](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#tostartofminute)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toStartOfSecond
version: 1.0
[ClickHouse] SHALL support correct operation of the [toStartOfSecond](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#tostartofsecond)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toStartOfFiveMinute
version: 1.0
[ClickHouse] SHALL support correct operation of the [toStartOfFiveMinute](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#tostartoffiveminute)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toStartOfTenMinutes
version: 1.0
[ClickHouse] SHALL support correct operation of the [toStartOfTenMinutes](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#tostartoftenminutes)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toStartOfFifteenMinutes
version: 1.0
[ClickHouse] SHALL support correct operation of the [toStartOfFifteenMinutes](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#tostartoffifteenminutes)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toStartOfInterval
version: 1.0
[ClickHouse] SHALL support correct operation of the [toStartOfInterval](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#tostartofintervaltime-or-data-interval-x-unit-time-zone)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
More detailed description can be found [here](https://github.com/ClickHouse/ClickHouse/issues/1201).
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toTime
version: 1.0
[ClickHouse] SHALL support correct operation of the [toTime](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#totime)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toRelativeYearNum
version: 1.0
[ClickHouse] SHALL support correct operation of the [toRelativeYearNum](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#torelativeyearnum)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toRelativeQuarterNum
version: 1.0
[ClickHouse] SHALL support correct operation of the [toRelativeQuarterNum](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#torelativequarternum)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toRelativeMonthNum
version: 1.0
[ClickHouse] SHALL support correct operation of the [toRelativeMonthNum](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#torelativemonthnum)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toRelativeWeekNum
version: 1.0
[ClickHouse] SHALL support correct operation of the [toRelativeWeekNum](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#torelativeweeknum)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toRelativeDayNum
version: 1.0
[ClickHouse] SHALL support correct operation of the [toRelativeDayNum](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#torelativedaynum)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toRelativeHourNum
version: 1.0
[ClickHouse] SHALL support correct operation of the [toRelativeHourNum](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#torelativehournum)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toRelativeMinuteNum
version: 1.0
[ClickHouse] SHALL support correct operation of the [toRelativeMinuteNum](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#torelativeminutenum)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toRelativeSecondNum
version: 1.0
[ClickHouse] SHALL support correct operation of the [toRelativeSecondNum](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#torelativesecondnum)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toISOYear
version: 1.0
[ClickHouse] SHALL support correct operation of the [toISOYear](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#toisoyear)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toISOWeek
version: 1.0
[ClickHouse] SHALL support correct operation of the [toISOWeek](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#toisoweek)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toWeek
version: 1.0
[ClickHouse] SHALL support correct operation of the [toWeek](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#toweekdatemode)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toYearWeek
version: 1.0
[ClickHouse] SHALL support correct operation of the [toYearWeek](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#toyearweekdatemode)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.now
version: 1.0
[ClickHouse] SHALL support conversion of output from the [now](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#now)
function to the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.today
version: 1.0
[ClickHouse] SHALL support conversion of output from the [today](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#today)
function to the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.yesterday
version: 1.0
[ClickHouse] SHALL support conversion of output from the [yesterday](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#yesterday)
function to the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.timeSlot
version: 1.0
[ClickHouse] SHALL support conversion of output from the [timeSlot](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#timeslot)
function to the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toYYYYMM
version: 1.0
[ClickHouse] SHALL support correct operation of the [toYYYYMM](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#toyyyymm)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toYYYYMMDD
version: 1.0
[ClickHouse] SHALL support correct operation of the [toYYYYMMDD](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#toyyyymmdd)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.toYYYYMMDDhhmmss
version: 1.0
[ClickHouse] SHALL support correct operation of the [toYYYYMMDDhhmmss](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#toyyyymmddhhmmss)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.addYears
version: 1.0
[ClickHouse] SHALL support correct operation of the [addYears](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#addyears-addmonths-addweeks-adddays-addhours-addminutes-addseconds-addquarters)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.addMonths
version: 1.0
[ClickHouse] SHALL support correct operation of the [addMonths](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#addyears-addmonths-addweeks-adddays-addhours-addminutes-addseconds-addquarters)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.addWeeks
version: 1.0
[ClickHouse] SHALL support correct operation of the [addWeeks](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#addyears-addmonths-addweeks-adddays-addhours-addminutes-addseconds-addquarters)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.addDays
version: 1.0
[ClickHouse] SHALL support correct operation of the [addDays](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#addyears-addmonths-addweeks-adddays-addhours-addminutes-addseconds-addquarters)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.addHours
version: 1.0
[ClickHouse] SHALL support correct operation of the [addHours](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#addyears-addmonths-addweeks-adddays-addhours-addminutes-addseconds-addquarters)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.addMinutes
version: 1.0
[ClickHouse] SHALL support correct operation of the [addMinutes](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#addyears-addmonths-addweeks-adddays-addhours-addminutes-addseconds-addquarters)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.addSeconds
version: 1.0
[ClickHouse] SHALL support correct operation of the [addSeconds](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#addyears-addmonths-addweeks-adddays-addhours-addminutes-addseconds-addquarters)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.addQuarters
version: 1.0
[ClickHouse] SHALL support correct operation of the [addQuarters](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#addyears-addmonths-addweeks-adddays-addhours-addminutes-addseconds-addquarters)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.subtractYears
version: 1.0
[ClickHouse] SHALL support correct operation of the [subtractYears](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#subtractyears-subtractmonths-subtractweeks-subtractdays-subtracthours-subtractminutes-subtractseconds-subtractquarters)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.subtractMonths
version: 1.0
[ClickHouse] SHALL support correct operation of the [subtractMonths](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#subtractyears-subtractmonths-subtractweeks-subtractdays-subtracthours-subtractminutes-subtractseconds-subtractquarters)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.subtractWeeks
version: 1.0
[ClickHouse] SHALL support correct operation of the [subtractWeeks](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#subtractyears-subtractmonths-subtractweeks-subtractdays-subtracthours-subtractminutes-subtractseconds-subtractquarters)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.subtractDays
version: 1.0
[ClickHouse] SHALL support correct operation of the [subtractDays](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#subtractyears-subtractmonths-subtractweeks-subtractdays-subtracthours-subtractminutes-subtractseconds-subtractquarters)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.subtractHours
version: 1.0
[ClickHouse] SHALL support correct operation of the [subtractHours](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#subtractyears-subtractmonths-subtractweeks-subtractdays-subtracthours-subtractminutes-subtractseconds-subtractquarters)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.subtractMinutes
version: 1.0
[ClickHouse] SHALL support correct operation of the [subtractMinutes](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#subtractyears-subtractmonths-subtractweeks-subtractdays-subtracthours-subtractminutes-subtractseconds-subtractquarters)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.subtractSeconds
version: 1.0
[ClickHouse] SHALL support correct operation of the [subtractSeconds](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#subtractyears-subtractmonths-subtractweeks-subtractdays-subtracthours-subtractminutes-subtractseconds-subtractquarters)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.subtractQuarters
version: 1.0
[ClickHouse] SHALL support correct operation of the [subtractQuarters](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#subtractyears-subtractmonths-subtractweeks-subtractdays-subtracthours-subtractminutes-subtractseconds-subtractquarters)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.dateDiff
version: 1.0
[ClickHouse] SHALL support correct operation of the [dateDiff](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#datediff)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.timeSlots
version: 1.0
[ClickHouse] SHALL support correct operation of the [timeSlots](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#timeslotsstarttime-duration-size)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.DatesAndTimesFunctions.formatDateTime
version: 1.0
[ClickHouse] SHALL support correct operation of the [formatDateTime](https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/#formatdatetime)
function used with the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
#### Type Conversion Functions
###### RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.toInt(8|16|32|64|128|256)
version: 1.0
[ClickHouse] SHALL support correct conversion of the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range]
to integer types using [toInt(8|16|32|64|128|256)](https://clickhouse.tech/docs/en/sql-reference/functions/type-conversion-functions/#toint8163264128256) functions.
###### RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.toUInt(8|16|32|64|256)
version: 1.0
[ClickHouse] SHALL support correct conversion of the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range]
to unsigned integer types using [toUInt(8|16|32|64|256)](https://clickhouse.tech/docs/en/sql-reference/functions/type-conversion-functions/#touint8163264256) functions.
###### RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.toFloat(32|64)
version: 1.0
[ClickHouse] SHALL support correct conversion of the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range]
to float types using [toFloat(32|64)](https://clickhouse.tech/docs/en/sql-reference/functions/type-conversion-functions/#tofloat3264) functions.
###### RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.toDate
version: 1.0
[ClickHouse] SHALL support correct conversion of the [DateTime64] data type when it stores dates within the [normal date range]
to the [Date](https://clickhouse.tech/docs/en/sql-reference/data-types/date/) type using the [toDate](https://clickhouse.tech/docs/en/sql-reference/functions/type-conversion-functions/#todate) function.
This function is ONLY supposed to work in NORMAL RANGE.
###### RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.toDateTime
version: 1.0
[ClickHouse] SHALL support correct conversion of the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range]
to the [DateTime](https://clickhouse.tech/docs/en/sql-reference/data-types/datetime/) type using the [toDateTime](https://clickhouse.tech/docs/en/sql-reference/functions/type-conversion-functions/#todatetime) function.
This function is ONLY supposed to work in NORMAL RANGE.
###### RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.toDateTime64
version: 1.0
[ClickHouse] SHALL support correct conversion from the data types supported by the [toDateTime64](https://clickhouse.tech/docs/en/sql-reference/data-types/datetime64/) function
to the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range].
###### RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.toDateTime64.FromString.MissingTime
version: 1.0
[ClickHouse] SHALL support correct conversion from the [String](https://clickhouse.tech/docs/en/sql-reference/data-types/string/)
data type to the [DateTime64](https://clickhouse.tech/docs/en/sql-reference/data-types/datetime64/) data type
when value of the string is missing the `hh:mm-ss.sss` part.
For example, `toDateTime64('2020-01-01', 3)`.
###### RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.toDecimal(32|64|128|256)
version: 1.0
[ClickHouse] SHALL support correct conversion of the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range]
to [Decimal](https://clickhouse.tech/docs/en/sql-reference/data-types/decimal/) types using [toDecimal(32|64|128|256)](https://clickhouse.tech/docs/en/sql-reference/functions/type-conversion-functions/#todecimal3264128256) functions.
###### RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.toString
version: 1.0
[ClickHouse] SHALL support correct conversion of the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range]
to the [String](https://clickhouse.tech/docs/en/sql-reference/data-types/string/) type using the [toString](https://clickhouse.tech/docs/en/sql-reference/functions/type-conversion-functions/#tostring) function.
###### RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.CAST(x,T)
version: 1.0
[ClickHouse] SHALL support correct conversion of the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range]
to one of the supported data type using the [CAST(x,T)](https://clickhouse.tech/docs/en/sql-reference/functions/type-conversion-functions/#type_conversion_function-cast) function.
###### RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.toUnixTimestamp64Milli
version: 1.0
[ClickHouse] SHALL support correct conversion of the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range]
to the [Int64](https://clickhouse.tech/docs/en/sql-reference/data-types/int-uint/) type using the [toUnixTimestamp64Milli](https://clickhouse.tech/docs/en/sql-reference/functions/type-conversion-functions/#tounixtimestamp64milli) function.
###### RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.toUnixTimestamp64Micro
version: 1.0
[ClickHouse] SHALL support correct conversion of the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range]
to the [Int64](https://clickhouse.tech/docs/en/sql-reference/data-types/int-uint/) type using the [toUnixTimestamp64Micro](https://clickhouse.tech/docs/en/sql-reference/functions/type-conversion-functions/#tounixtimestamp64micro) function.
###### RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.toUnixTimestamp64Nano
version: 1.0
[ClickHouse] SHALL support correct conversion of the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range]
to the [Int64](https://clickhouse.tech/docs/en/sql-reference/data-types/int-uint/) type using the [toUnixTimestamp64Nano](https://clickhouse.tech/docs/en/sql-reference/functions/type-conversion-functions/#tounixtimestamp64nano) function.
###### RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.fromUnixTimestamp64Milli
version: 1.0
[ClickHouse] SHALL support correct conversion from the [Int64](https://clickhouse.tech/docs/en/sql-reference/data-types/int-uint/) type
to the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range]
using the [fromUnixTimestamp64Milli](https://clickhouse.tech/docs/en/sql-reference/functions/type-conversion-functions/#fromunixtimestamp64milli) function.
###### RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.fromUnixTimestamp64Micro
version: 1.0
[ClickHouse] SHALL support correct conversion from the [Int64](https://clickhouse.tech/docs/en/sql-reference/data-types/int-uint/) type
to the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range]
using the [fromUnixTimestamp64Micro](https://clickhouse.tech/docs/en/sql-reference/functions/type-conversion-functions/#fromunixtimestamp64micro) function.
###### RQ.SRS-010.DateTime64.ExtendedRange.TypeConversionFunctions.fromUnixTimestamp64Nano
version: 1.0
[ClickHouse] SHALL support correct conversion from the [Int64](https://clickhouse.tech/docs/en/sql-reference/data-types/int-uint/) type
to the [DateTime64] data type when it stores dates within the [normal date range] and the [extended date range]
using the [fromUnixTimestamp64Nano](https://clickhouse.tech/docs/en/sql-reference/functions/type-conversion-functions/#fromunixtimestamp64nano) function.
## References
* **DateTime64**: https://clickhouse.tech/docs/en/sql-reference/data-types/datetime64/
* **ISO 8601 format**: https://en.wikipedia.org/wiki/ISO_8601
* **ClickHouse:** https://clickhouse.tech
* **GitHub Repository:** https://github.com/ClickHouse/ClickHouse/blob/master/tests/testflows/datetime64_extended_range/requirements/requirements.md
* **Revision History:** https://github.com/ClickHouse/ClickHouse/commits/master/tests/testflows/datetime64_extended_range/requirements/requirements.md
* **Git:** https://git-scm.com/
[SRS]: #srs
[normal date range]: #normal-date-range
[extended date range]: #extended-date-range
[Dates and Times Functions]: https://clickhouse.tech/docs/en/sql-reference/functions/date-time-functions/
[DateTime64]: https://clickhouse.tech/docs/en/sql-reference/data-types/datetime64/
[ISO 8601 format]: https://en.wikipedia.org/wiki/ISO_8601
[ClickHouse]: https://clickhouse.tech
[GitHub Repository]: https://github.com/ClickHouse/ClickHouse/blob/master/tests/testflows/datetime64_extended_range/requirements/requirements.md
[Revision History]: https://github.com/ClickHouse/ClickHouse/commits/master/tests/testflows/datetime64_extended_range/requirements/requirements.md
[Git]: https://git-scm.com/
[GitHub]: https://github.com

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,179 @@
import pytz
import datetime
from testflows.core import *
from testflows.asserts import error
from contextlib import contextmanager
from datetime64_extended_range.common import *
def in_normal_range(dt: datetime.datetime):
"""Check if DateTime is in normal range
"""
return dt <= datetime.datetime(2105, 12, 31, 23, 59, 59, 999999) and dt >= datetime.datetime(1970, 1, 1, 0, 0, 0)
def years_range(stress=False, padding=(0, 0)):
"""Returns a set of year values used for testing.
"""
return range(1925+padding[0], 2283-padding[1]) if stress else (1927, 2000, 2281)
def timezones_range(stress=False):
"""Returns a set of timezone values used for testing.
"""
if stress:
return pytz.all_timezones
else:
return ['UTC', 'Asia/Novosibirsk', 'America/Denver']
@contextmanager
def create_table(timezone, node):
try:
node.query(f"CREATE TABLE dt(timestamp DateTime64(3, {timezone})) Engine = TinyLog")
yield
finally:
node.query("DROP TABLE dt")
@TestOutline
def insert_check_datetime(self, datetime, expected, precision=0, timezone="UTC"):
"""Check how a particular datetime value works with different
functions that accept DateTime64 data type.
:param datetime: datetime string
:param expected: expected result
:param precision: time precision, default: 0
:param timezone: timezone, default: UTC
"""
with create_table(timezone, self.context.node):
with When("I use toDateTime64"):
r = self.context.node.query(f"SELECT toDateTime64('{datetime}', {precision}, '{timezone}')")
with Then(f"I expect {expected}"):
assert r.output == expected, error()
def datetime_generator(year, microseconds=False):
"""Helper generator
"""
date = datetime.datetime(year, 1, 1, 0, 0, 0)
if microseconds:
date = datetime.datetime(year, 1, 1, 0, 0, 0, 123000)
while not (date.month == 12 and date.day == 31):
yield date
date = date + datetime.timedelta(days=1, hours=1, minutes=1, seconds=1)
def select_dates_in_year(year, stress=False, microseconds=False):
"""Returns various datetimes in a year that are to be checked
"""
if not stress:
dates = [datetime.datetime(year, 1, 1, 0, 0, 0), datetime.datetime(year, 12, 31, 23, 59, 59)]
if microseconds:
dates = [datetime.datetime(year, 1, 1, 0, 0, 0, 123000), datetime.datetime(year, 12, 31, 23, 59, 59, 123000)]
if year % 4 == 0 and (year % 100 != 0 or year % 400 == 0):
dates.append(datetime.datetime(year, 2, 29, 11, 11, 11, 123000))
return dates
else:
return datetime_generator(year)
@TestOutline
def select_check_datetime(self, datetime, expected, precision=0, timezone="UTC"):
"""Check how a particular datetime value works with different
functions that accept DateTime64 data type.
:param datetime: datetime string
:param expected: expected result
:param precision: time precision, default: 0
:param timezone: timezone, default: UTC
"""
with When("I use toDateTime64"):
r = self.context.node.query(f"SELECT toDateTime64('{datetime}', {precision}, '{timezone}')")
with Then(f"I expect {expected}"):
assert r.output == expected, error()
@TestStep(When)
def exec_query(self, request, expected=None, exitcode=None):
"""Execute a query and check expected result.
:param request: query string
:param expected: result string
:param exitcode: exitcode
"""
r = self.context.node.query(request)
if expected is not None:
with Then(f"output should match the expected", description=f"{expected}"):
assert r.output == expected, error()
elif exitcode is not None:
with Then(f"output exitcode should match expected", description=f"{exitcode}"):
assert r.exitcode == exitcode, error()
@TestStep
def walk_datetime_in_incrementing_steps(self, date, hrs_range=(0, 24), step=1, timezone="UTC", precision=0):
"""Sweep time starting from some start date. The time is incremented
in steps specified by the `step` parameter
(default: 1 min).
:param hrs_range: range in hours
:param step: step in minutes
"""
stress = self.context.stress
tasks = []
pool = Pool(4)
secs = f"00{'.' * (precision > 0)}{'0' * precision}"
try:
with When(f"I loop through datetime range {hrs_range} starting from {date} in {step}min increments"):
for hrs in range(*hrs_range) if stress else (hrs_range[0], hrs_range[1]-1):
for mins in range(0, 60, step) if stress else (0, 59):
datetime = f"{date} {str(hrs).zfill(2)}:{str(mins).zfill(2)}:{secs}"
expected = datetime
with When(f"time is {datetime}"):
run_scenario(pool, tasks, Test(name=f"{hrs}:{mins}:{secs}", test=select_check_datetime),
kwargs=dict(datetime=datetime, precision=precision, timezone=timezone,
expected=expected))
finally:
join(tasks)
@TestStep
def walk_datetime_in_decrementing_steps(self, date, hrs_range=(23, 0), step=1, timezone="UTC", precision=0):
"""Sweep time starting from some start date. The time is decremented
in steps specified by the `step` parameter
(default: 1 min).
:param date: string
:param hrs_range: range in hours
:param step: step in minutes
:param timezone: String
"""
stress = self.context.stress
tasks = []
pool = Pool(4)
secs = f"00{'.' * (precision > 0)}{'0' * precision}"
try:
with When(f"I loop through datetime range {hrs_range} starting from {date} in {step}min decrements"):
for hrs in range(*hrs_range, -1) if stress else (hrs_range[1], hrs_range[0]):
for mins in range(59, 0, -step) if stress else (59, 0):
datetime = f"{date} {str(hrs).zfill(2)}:{str(mins).zfill(2)}:{secs}"
expected = datetime
with When(f"time is {datetime}"):
run_scenario(pool, tasks, Test(name=f"{hrs}:{mins}:{secs}", test=select_check_datetime),
kwargs=dict(datetime=datetime, precision=precision, timezone=timezone,
expected=expected))
finally:
join(tasks)

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,151 @@
from testflows.core import *
from datetime64_extended_range.requirements.requirements import *
from datetime64_extended_range.common import *
from datetime64_extended_range.tests.common import *
import pytz
import datetime
import itertools
@TestScenario
@Requirements(
RQ_SRS_010_DateTime64_ExtendedRange_NormalRange_Start("1.0"),
)
def normal_range_start(self):
"""Check DateTime64 can accept a dates around the start of the normal range that begins at 1970-01-01 00:00:00.000.
"""
with When("I do incrementing time sweep", description="check different time points in the first 24 hours at given date"):
walk_datetime_in_incrementing_steps(date="1970-01-01", precision=3, hrs_range=(0, 24))
@TestScenario
@Requirements(
RQ_SRS_010_DateTime64_ExtendedRange_NormalRange_End("1.0")
)
def normal_range_end(self):
"""Check DateTime64 can accept a dates around the end of the normal range that ends at 2105-12-31 23:59:59.99999.
"""
with When("I do decrementing time sweep",
description="check different time points in the last 24 hours at given date"):
walk_datetime_in_decrementing_steps(date="2105-12-31", precision=3, hrs_range=(23, 0))
@TestScenario
@Requirements(
RQ_SRS_010_DateTime64_ExtendedRange_Start("1.0")
)
def extended_range_start(self):
"""Check DateTime64 supports dates around the beginning of the extended range that begins at 1698-01-01 00:00:00.000000.
"""
with When("I do incrementing time sweep",
description="check different time points in the first 24 hours at given date"):
walk_datetime_in_incrementing_steps(date="1925-01-01", precision=5, hrs_range=(0, 24))
@TestScenario
@Requirements(
RQ_SRS_010_DateTime64_ExtendedRange_End("1.0")
)
def extended_range_end(self, precision=3):
"""Check DateTime64 supports dates around the beginning of the extended range that ends at 2377-12-31T23:59:59.999999.
"""
with When("I do decrementing time sweep",
description="check different time points in the last 24 hours at given date"):
walk_datetime_in_decrementing_steps(date="2238-12-31", precision=5, hrs_range=(23, 0))
@TestScenario
@Requirements(
RQ_SRS_010_DateTime64_ExtendedRange_NormalRange_Start_BeforeEpochForTimeZone("1.0")
)
def timezone_local_below_normal_range(self):
"""Check how UTC normal range time value treated
when current timezone time value is out of normal range.
"""
with When("I do incrementing time sweep",
description="check different time points when UTC datetime fits normal range but below it for local datetime"):
walk_datetime_in_incrementing_steps(date="1969-12-31", hrs_range=(17, 24), timezone='America/Phoenix')
@TestScenario
@Requirements(
RQ_SRS_010_DateTime64_ExtendedRange_NormalRange_End_AfterEpochForTimeZone("1.0")
)
def timezone_local_above_normal_range(self):
"""Check how UTC normal range time value treated
when current timezone time value is out of normal range.
"""
with When("I do decrementing time sweep",
description="check different time points when UTC datetime fits normal range but above it for local datetime"):
walk_datetime_in_decrementing_steps(date="2106-01-01", hrs_range=(6, 0), timezone='Asia/Novosibirsk')
@TestScenario
@Requirements(
RQ_SRS_010_DateTime64_ExtendedRange_Comparison("1.0")
)
def comparison_check(self):
"""Check how comparison works with DateTime64 extended range.
"""
stress = self.context.stress
comparators = (">", "<", "==", "<=", ">=", "!=")
timezones = timezones_range(stress=stress)
datetimes = []
for year in years_range(stress=stress):
datetimes += list(select_dates_in_year(year=year, stress=stress))
for dt_1, dt_2 in itertools.product(datetimes, datetimes):
for tz1, tz2 in itertools.product(timezones, timezones):
dt1_str = dt_1.strftime("%Y-%m-%d %H:%M:%S")
dt2_str = dt_2.strftime("%Y-%m-%d %H:%M:%S")
dt1 = pytz.timezone(tz1).localize(dt_1)
dt2 = pytz.timezone(tz2).localize(dt_2)
with When(f"{dt1_str} {tz1}, {dt2_str} {tz2}"):
for c in comparators:
expr = f"dt1 {c} dt2"
expected = str(int(eval(expr)))
with Then(f"I check {dt1_str} {c} {dt2_str}"):
query = f"SELECT toDateTime64('{dt1_str}', 0, '{tz1}') {c} toDateTime64('{dt2_str}', 0, '{tz2}')"
exec_query(request=query, expected=expected)
@TestScenario
@Requirements(
RQ_SRS_010_DateTime64_ExtendedRange_TimeZones("1.0")
)
def timezones_support(self):
"""Check how timezones work with DateTime64 extended range.
"""
stress = self.context.stress
timezones = timezones_range(stress=stress)
for year in years_range(stress):
with Given("I select datetimes in a year"):
datetimes = select_dates_in_year(year=year, stress=stress)
for dt in datetimes:
for tz in timezones:
with Step(f"{dt} {tz}"):
with By("computing expected output using python"):
dt_str = dt.strftime("%Y-%m-%d %H:%M:%S")
with And("forming a toTimeZone ClickHouse query"):
query = f"SELECT toDateTime64('{dt_str}', 0, '{tz}')"
with Then(f"I execute query", flags=TE):
exec_query(request=query, expected=f"{dt_str}")
@TestFeature
def generic(self, node="clickhouse1"):
"""Check the basic operations with DateTime64
"""
self.context.node = self.context.cluster.node(node)
for scenario in loads(current_module(), Scenario, Suite):
Scenario(run=scenario, flags=TE)

View File

@ -0,0 +1,164 @@
from testflows.core import *
import datetime
from datetime64_extended_range.requirements.requirements import *
from datetime64_extended_range.tests.common import *
@TestScenario
@Requirements(
RQ_SRS_010_DateTime64_ExtendedRange_NonExistentTime_InvalidDate("1.0")
)
def invalid_date(self):
"""Check how non-existent date is treated.
For example, check 31st day in month that only has 30 days.
"""
date_range = [1930, 1980, 2230]
if self.context.stress:
date_range = range(1925, 2238)
with When("I check 31st day of a 30-day month"):
for year in date_range:
for month in (4, 6, 9, 11):
datetime = f"{year}-{str(month).zfill(2)}-31 12:23:34"
expected = f"{year}-{str(month + 1).zfill(2)}-01 12:23:34"
with Then(f"{datetime}", description=f"expected {expected}", flags=TE):
select_check_datetime(datetime=datetime, expected=expected)
@TestOutline(Suite)
@Requirements(
RQ_SRS_010_DateTime64_ExtendedRange_NonExistentTime_InvalidTime("1.0")
)
@Examples(
"datetime expected timezone", [
('2002-04-07 02:30:00', '2002-04-07 01:30:00', 'America/New_York'),
('2020-03-29 02:30:00', '2020-03-29 01:30:00', 'Europe/Zurich'),
('2017-03-26 02:30:00', '2017-03-26 01:30:00', 'Europe/Berlin')
])
def invalid_time(self, datetime, expected, timezone='UTC'):
"""proper handling of invalid time for a timezone
when using DateTime64 extended range data type, for example,
2:30am on 7th April 2002 never happened at all in the US/Eastern timezone,
"""
with When(f"I check non-existent datetime {datetime}"):
select_check_datetime(datetime=datetime, expected=expected, timezone=timezone)
@TestOutline(Scenario)
@Requirements(
RQ_SRS_010_DateTime64_ExtendedRange_NonExistentTime_DaylightSavingTime("1.0"),
RQ_SRS_010_DateTime64_ExtendedRange_NonExistentTime_DaylightSavingTime_Disappeared("1.0")
)
@Examples(
"tz time_dates", [
('America/Denver', {'02:30:00': ('2018-03-11', '2020-03-08', '1980-04-27', '1942-02-09')}),
('Europe/Zurich', {'02:30:00': ('2016-03-27', '2020-03-29', '1981-03-29'), '01:30:00': ('1942-05-04', )})
])
def dst_disappeared(self, tz, time_dates):
"""Proper handling of switching DST, when an hour is being skipped.
Testing in 2 steps: first, try to make a DateTime64 with skipped time value.
Second, adding interval so that result is in the skipped time.
"""
for time, dates in time_dates.items():
for date in dates:
with Given(f"forming a datetime"):
dt_str = f"{date} {time}"
dt = datetime.datetime.strptime(dt_str, "%Y-%m-%d %H:%M:%S")
with Step("Assignment test"):
with When("computing expected result"):
dt -= datetime.timedelta(hours=1)
expected = dt.strftime("%Y-%m-%d %H:%M:%S")
with Then(f"I check skipped hour"):
select_check_datetime(datetime=dt_str, expected=expected, timezone=tz)
with Step("Addition test"):
with When("computing expected result"):
dt += datetime.timedelta(hours=2)
expected = dt.strftime("%Y-%m-%d %H:%M:%S")
with Then(f"I check skipped hour"):
query = f"SELECT addHours(toDateTime64('{dt_str}', 0, '{tz}'), 1)"
exec_query(request=query, expected=f"{expected}")
@TestOutline(Scenario)
@Requirements(
RQ_SRS_010_DateTime64_ExtendedRange_NonExistentTime_LeapSeconds("1.0")
)
@Examples(
"datet years", [
("06-30 23:59:55", [1972, 1981, 1982, 1983, 1985, 1992, 1993, 1994, 1997, 2012, 2015]),
("12-31 23:59:55", [1972, 1973, 1974, 1975, 1976, 1977, 1978, 1979, 1987, 1989, 1990, 1995, 1998, 2005, 2008, 2016])
])
def leap_seconds(self, datet, years):
"""Test proper handling of leap seconds. Read more: https://de.wikipedia.org/wiki/Schaltsekunde
Being checked by selecting a timestamp prior to leap second and adding seconds so that the result is after it.
"""
for year in years:
with When(f"{datet}, {year}"):
with By("forming an expected result using python"):
dt_str = f"{year}-{datet}"
dt = datetime.datetime.strptime(dt_str, '%Y-%m-%d %H:%M:%S')
dt += datetime.timedelta(seconds=9)
expected = dt.strftime("%Y-%m-%d %H:%M:%S")
with And(f"forming a query"):
query = f"SELECT addSeconds(toDateTime64('{dt_str}', 0, 'UTC'), 10)"
with Then("executing query"):
exec_query(request=query, expected=f"{expected}")
@TestScenario
@Requirements(
RQ_SRS_010_DateTime64_ExtendedRange_NonExistentTime_DaylightSavingTime("1.0"),
RQ_SRS_010_DateTime64_ExtendedRange_NonExistentTime_TimeZoneSwitch("1.0")
)
def dst_time_zone_switch(self):
"""Check how ClickHouse supports handling of invalid time when using DateTime64 extended range data type
when the invalid time is caused when countries switch timezone definitions with no daylight savings time switch.
"""
stress = self.context.stress
timezones = timezones_range(stress)
utc = pytz.timezone("UTC")
for timezone in timezones:
if timezone == 'UTC':
continue
with Step(f"{timezone}"):
tz = pytz.timezone(timezone)
transition_times = tz._utc_transition_times
transition_info = tz._transition_info
for i in range(len(transition_times)-1, 0, -1):
if (transition_times[i] > datetime.datetime.now()) or (transition_times[i].year < 1925) or (transition_times[i].year > 2238):
continue
with Step(f"{transition_times[i]}"):
with By("localize python datetime"):
dt = transition_times[i]
dt0 = dt - datetime.timedelta(hours=4)
dt0 = utc.localize(dt0).astimezone(tz).replace(tzinfo=None)
with And("compute expected result using Pytz"):
seconds_shift = transition_info[i][0] - transition_info[i-1][0]
dt1 = dt0 + datetime.timedelta(hours=8) + seconds_shift
dt0_str = dt0.strftime("%Y-%m-%d %H:%M:%S")
dt1_str = dt1.strftime("%Y-%m-%d %H:%M:%S")
with And("forming a ClickHouse query"):
query = f"SELECT addHours(toDateTime64('{dt0_str}', 0, '{timezone}'), 8)"
with Then("executing the query"):
exec_query(request=query, expected=f"{dt1_str}")
@TestFeature
@Name("non existent time")
@Requirements(
RQ_SRS_010_DateTime64_ExtendedRange_NonExistentTime("1.0")
)
def feature(self, node="clickhouse1"):
"""Check how ClickHouse treats non-existent time in DateTime64 data type.
"""
self.context.node = self.context.cluster.node(node)
for scenario in loads(current_module(), Scenario, Suite):
Scenario(run=scenario, flags=TE)

View File

@ -0,0 +1,38 @@
import pytz
from datetime import datetime
from testflows.core import *
from datetime64_extended_range.common import *
from datetime64_extended_range.tests.common import select_check_datetime
from datetime64_extended_range.requirements.requirements import *
from datetime64_extended_range.tests.common import *
@TestSuite
@Requirements(
RQ_SRS_010_DateTime64_ExtendedRange_SpecificTimestamps("1.0")
)
def reference_times(self, node="clickhouse1"):
"""Check how ClickHouse converts a set of particular timestamps
to DateTime64 for all timezones and compare the result to pytz.
"""
self.context.node = self.context.cluster.node(node)
timestamps = [9961200, 73476000, 325666800, 354675600, 370400400, 386125200, 388566010, 401850000, 417574811,
496803600, 528253200, 624423614, 636516015, 671011200, 717555600, 752047218, 859683600, 922582800,
1018173600, 1035705600, 1143334800, 1162105223, 1174784400, 1194156000, 1206838823, 1224982823,
1236495624, 1319936400, 1319936424, 1425798025, 1459040400, 1509872400, 2090451627, 2140668000]
query = ""
for tz in pytz.all_timezones:
timezone = pytz.timezone(tz)
query += f"select '{tz}', arrayJoin(arrayFilter(x -> x.2 <> x.3, arrayMap(x -> tuple(x.1, x.2, toString(toDateTime64(x.1, 0, '{tz}'))), ["
need_comma = 0
for timestamp in timestamps:
for reference_timestamp in [timestamp - 1, timestamp, timestamp + 1]:
query += f"{',' if need_comma else ''}tuple({reference_timestamp},'{datetime.datetime.fromtimestamp(reference_timestamp, timezone).strftime('%Y-%m-%d %H:%M:%S')}')"
need_comma = 1
query += "] ) ) );"
exec_query(request=query, expected="")

View File

@ -0,0 +1,479 @@
import time
import pytz
import decimal
import itertools
import numpy as np
from dateutil.tz import tzlocal
from datetime import datetime, timedelta
import dateutil.relativedelta as rd
from testflows.core import *
from datetime64_extended_range.requirements.requirements import *
from datetime64_extended_range.common import *
from datetime64_extended_range.tests.common import *
@TestOutline(Scenario)
@Examples("cast", [
(False, Requirements(RQ_SRS_010_DateTime64_ExtendedRange_TypeConversionFunctions_toInt_8_16_32_64_128_256_("1.0"))),
(True, Requirements(RQ_SRS_010_DateTime64_ExtendedRange_TypeConversionFunctions_CAST_x_T_("1.0")))
])
def to_int_8_16_32_64_128_256(self, cast):
"""Check the toInt(8|16|32|64|128|256) functions with DateTime64 extended range
"""
stress = self.context.stress
timezones = timezones_range(stress)
for year in years_range(stress):
with Given("I select datetimes in a year"):
datetimes = select_dates_in_year(year=year, stress=stress)
for d in datetimes:
for tz in timezones:
dt = pytz.timezone(tz).localize(d)
for int_type in (8, 16, 32, 64, 128, 256):
with When(f"{dt} {tz}, int{int_type}"):
with By("converting datetime to string"):
dt_str = dt.strftime("%Y-%m-%d %H:%M:%S")
with And("computing the expected result using python"):
py_res = int(time.mktime(dt.timetuple()))
expected = f"{py_res}"
if not (int_type == 128 or int_type == 256):
"""ALL dates fit into int128 and int256, so no need to check"""
np_res = exec(f"np.int{int_type}({py_res})")
else:
np_res = py_res
if np_res == py_res:
with Given(f"{py_res} fits int{int_type}"):
with When(f"making a query string for ClickHouse if py_res fits int{int_type}"):
if cast:
query = f"SELECT cast(toDateTime64('{dt_str}', 0, '{tz}'), 'Int{int_type}')"
else:
query = f"SELECT toInt{int_type}(toDateTime64('{dt_str}', 0, '{tz}'))"
with Then(f"I execute toInt{int_type}() query"):
exec_query(request=query, expected=f"{expected}")
@TestOutline(Scenario)
@Examples("cast", [
(False, Requirements(RQ_SRS_010_DateTime64_ExtendedRange_TypeConversionFunctions_toUInt_8_16_32_64_256_("1.0"))),
(True, Requirements(RQ_SRS_010_DateTime64_ExtendedRange_TypeConversionFunctions_CAST_x_T_("1.0")))
])
def to_uint_8_16_32_64_256(self, cast):
"""Check the toUInt(8|16|32|64|256) functions with DateTime64 extended range
"""
stress = self.context.stress
timezones = timezones_range(stress)
for year in years_range(stress):
with Given("I select datetimes in a year"):
datetimes = select_dates_in_year(year=year, stress=stress)
for d in datetimes:
for tz in timezones:
dt = pytz.timezone(tz).localize(d)
for int_type in (8, 16, 32, 64, 256):
with Step(f"{dt} {tz}, int{int_type}"):
with By("converting datetime to string"):
dt_str = dt.strftime("%Y-%m-%d %H:%M:%S")
with And("computing the expected result using python"):
py_res = int(time.mktime(dt.timetuple()))
expected = f"{py_res}"
if int_type != 256:
"""ALL dates fit into uint256, so no need to check"""
np_res = exec(f"np.uint{int_type}({py_res})")
else:
np_res = py_res
if np_res == py_res:
with Given(f"{py_res} fits int{int_type}"):
with When(f"making a query string for ClickHouse if py_res fits int{int_type}"):
if cast:
query = f"SELECT cast(toDateTime64('{dt_str}', 0, '{tz}'), 'UInt{int_type}')"
else:
query = f"SELECT toUInt{int_type}(toDateTime64('{dt_str}', 0, '{tz}'))"
with Then(f"I execute toInt{int_type}() query"):
exec_query(request=query, expected=f"{expected}")
@TestOutline(Scenario)
@Examples("cast", [
(False, Requirements(RQ_SRS_010_DateTime64_ExtendedRange_TypeConversionFunctions_toFloat_32_64_("1.0"))),
(True, Requirements(RQ_SRS_010_DateTime64_ExtendedRange_TypeConversionFunctions_CAST_x_T_("1.0")))
])
def to_float_32_64(self, cast):
"""Check the toFloat(32|64) functions with DateTime64 extended range
"""
stress = self.context.stress
timezones = timezones_range(stress)
for year in years_range(stress):
with Given("I select datetimes in a year"):
datetimes = select_dates_in_year(year=year, stress=stress)
for d in datetimes:
for tz in timezones:
dt = pytz.timezone(tz).localize(d)
for float_type in (32, 64):
with Step(f"{dt} {tz}, int{float_type}"):
with By("converting datetime to string"):
dt_str = dt.strftime("%Y-%m-%d %H:%M:%S")
with And("computing the expected result using python"):
py_res = int(time.mktime(dt.timetuple()))
expected = f"{py_res}"
np_res = exec(f"np.float{float_type}({py_res})")
if np_res == py_res:
with When(f"making a query string for ClickHouse"):
if cast:
query = f"SELECT cast(toDateTime64('{dt_str}', 0, '{tz}'), 'Float{float_type}')"
else:
query = f"SELECT toFloat{float_type}(toDateTime64('{dt_str}', 0, '{tz}'))"
with Then(f"I execute toFloat{float_type}() query"):
exec_query(request=query, expected=f"{expected}")
@TestScenario
@Requirements(
RQ_SRS_010_DateTime64_ExtendedRange_TypeConversionFunctions_toDateTime64_FromString_MissingTime("1.0")
)
def to_datetime64_from_string_missing_time(self):
"""Check the toDateTime64() with DateTime64 extended range conversion when string is missing the time part.
"""
stress = self.context.stress
timezones = timezones_range(stress)
for year in years_range(stress):
with Given("I select datetimes in a year"):
datetimes = select_dates_in_year(year=year, stress=stress)
for dt in datetimes:
for tz in timezones:
with Step(f"{dt} {tz}"):
with By("converting datetime to string"):
dt_str = dt.strftime("%Y-%m-%d")
with And("figure out expected result in python"):
expected = f"{dt.strftime('%Y-%m-%d')} 00:00:00"
with When(f"making a query string for ClickHouse"):
query = f"SELECT toDateTime64('{dt_str}', 0, '{tz}')"
with Then(f"I execute toDateTime64() query"):
exec_query(request=query, expected=f"{expected}")
@TestScenario
@Requirements(
RQ_SRS_010_DateTime64_ExtendedRange_TypeConversionFunctions_toDateTime64("1.0")
)
def to_datetime64(self):
"""Check the toDateTime64() conversion with DateTime64. This is supposed to work in normal range ONLY.
"""
stress = self.context.stress
timezones = timezones_range(stress)
for year in years_range(stress):
with Given("I select datetimes in a year"):
datetimes = select_dates_in_year(year=year, stress=stress)
for dt in datetimes:
for tz in timezones:
with By("converting datetime to string"):
dt_str = dt.strftime("%Y-%m-%d %H:%M:%S")
with And(f"making a query string for ClickHouse"):
query = f"SELECT toDateTime64('{dt_str}', 0, '{tz}')"
with When("figure out expected result in python"):
expected = f"{dt.strftime('%Y-%m-%d %H:%M:%S')}"
with Then(f"I execute toDateTime64() query"):
exec_query(request=query, expected=f"{expected}")
@TestOutline(Scenario)
@Examples("cast", [
(False, Requirements(RQ_SRS_010_DateTime64_ExtendedRange_TypeConversionFunctions_toDate("1.0"))),
(True, Requirements(RQ_SRS_010_DateTime64_ExtendedRange_TypeConversionFunctions_CAST_x_T_("1.0")))
])
def to_date(self, cast):
"""Check the toDate() conversion with DateTime64. This is supposed to work in normal range ONLY.
"""
stress = self.context.stress
timezones = timezones_range(stress)
for year in years_range(stress):
with Given("I select datetimes in a year"):
datetimes = select_dates_in_year(year=year, stress=stress)
for dt in datetimes:
for tz in timezones:
with Step(f"{dt} {tz}"):
expected = None # by default - not checked, checking the exitcode
with By("converting datetime to string"):
dt_str = dt.strftime("%Y-%m-%d %H:%M:%S")
if in_normal_range(dt):
with And("DateTime64 fits normal range, change its value"):
expected = f"{dt.strftime('%Y-%m-%d')}" # being checked in case DateTime64 fits normal range
with Given(f"I make a query string for ClickHouse"):
if cast:
query = f"SELECT CAST(toDateTime64('{dt_str}', 0, '{tz}'), 'Date')"
else:
query = f"SELECT toDate(toDateTime64('{dt_str}', 0, '{tz}'))"
with Then(f"I execute toDate() query and check return/exitcode"):
exec_query(request=query, expected=expected, exitcode=0)
@TestOutline(Scenario)
@Examples("cast", [
(False, Requirements(RQ_SRS_010_DateTime64_ExtendedRange_TypeConversionFunctions_toDateTime("1.0"))),
(True, Requirements(RQ_SRS_010_DateTime64_ExtendedRange_TypeConversionFunctions_CAST_x_T_("1.0")))
])
def to_datetime(self, cast):
"""Check the toDateTime() conversion with DateTime64. This is supposed to work in normal range ONLY.
"""
stress = self.context.stress
timezones = timezones_range(stress)
for year in years_range(stress):
with Given("I select datetimes in a year"):
datetimes = select_dates_in_year(year=year, stress=stress)
for dt in datetimes:
for tz in timezones:
with By("converting datetime to string"):
dt_str = dt.strftime("%Y-%m-%d %H:%M:%S")
with And(f"making a query string for ClickHouse"):
if cast:
query = f"SELECT CAST(toDateTime64('{dt_str}', 0, '{tz}'), 'DateTime')"
with When("figure out expected result in python"):
dt_local = pytz.timezone(tz).localize(dt)
dt_transformed = dt_local.astimezone(tzlocal())
expected = f"{dt_transformed.strftime('%Y-%m-%d %H:%M:%S')}"
else:
query = f"SELECT toDateTime(toDateTime64('{dt_str}', 0, '{tz}'))"
with When("figure out expected result in python"):
expected = f"{dt.strftime('%Y-%m-%d %H:%M:%S')}"
if not in_normal_range(dt):
with When(f"I execute toDateTime() query out of normal range"):
exec_query(request=query, exitcode=0)
else:
with When(f"I execute toDateTime() query"):
exec_query(request=query, expected=f"{expected}")
@TestOutline(Scenario)
@Examples("cast", [
(False, Requirements(RQ_SRS_010_DateTime64_ExtendedRange_TypeConversionFunctions_toString("1.0"))),
(True, Requirements(RQ_SRS_010_DateTime64_ExtendedRange_TypeConversionFunctions_CAST_x_T_("1.0")))
])
def to_string(self, cast):
"""Check the toString() with DateTime64 extended range.
"""
stress = self.context.stress
timezones = timezones_range(stress)
for year in years_range(stress):
with Given("I select datetimes in a year"):
datetimes = select_dates_in_year(year=year, stress=stress)
for dt in datetimes:
for tz in timezones:
with Step(f"{dt} {tz}"):
with By("converting datetime to string"):
dt_str = dt.strftime("%Y-%m-%d %H:%M:%S")
with When(f"making a query string for ClickHouse"):
if cast:
query = f"SELECT cast(toDateTime64('{dt_str}', 0, '{tz}'), 'String')"
else:
query = f"SELECT toString(toDateTime64('{dt_str}', 0, '{tz}'))"
with Then(f"I execute toDateTime64() query"):
exec_query(request=query, expected=f"{dt_str}")
def valid_decimal_range(bit_depth, S):
"""A helper to find valid range for Decimal(32|64|128|256) with given scale (S)"""
return {32: -1 * 10 ** (9 - S), 64: -1 * 10 ** (18 - S), 128: -1 * 10 ** (38 - S), 256: -1 * 10 ** (76 - S)}[
bit_depth]
@TestOutline(Scenario)
@Examples("cast", [
(False, Requirements(RQ_SRS_010_DateTime64_ExtendedRange_TypeConversionFunctions_toDecimal_32_64_128_256_("1.0"))),
(True, Requirements(RQ_SRS_010_DateTime64_ExtendedRange_TypeConversionFunctions_CAST_x_T_("1.0")))
])
def to_decimal_32_64_128_256(self, cast):
"""Check the toDecimal(32|64|128|256) functions with DateTime64 extended range.
Decimal32(S) - ( -1 * 10^(9 - S), 1 * 10^(9 - S) )
Decimal64(S) - ( -1 * 10^(18 - S), 1 * 10^(18 - S) )
Decimal128(S) - ( -1 * 10^(38 - S), 1 * 10^(38 - S) )
Decimal256(S) - ( -1 * 10^(76 - S), 1 * 10^(76 - S) )
"""
stress = self.context.stress
timezones = timezones_range(stress)
scales = {32: 9, 64: 18, 128: 38, 256: 76}
for year in years_range(stress):
with Given("I select datetimes in a year"):
datetimes = select_dates_in_year(year=year, stress=stress)
for d in datetimes:
for tz in timezones:
dt = pytz.timezone(tz).localize(d)
for decimal_type in (32, 64, 128, 256):
for scale in range(scales[decimal_type]):
with When(f"{dt} {tz}, Decimal{decimal_type}({scale})"):
valid_range = valid_decimal_range(bit_depth=decimal_type, S=scale)
with By("computing the expected result using python"):
expected = decimal.Decimal(time.mktime(dt.timetuple()))
if -valid_range < expected < valid_range:
with And("converting datetime to string"):
dt_str = dt.strftime("%Y-%m-%d %H:%M:%S")
with When(f"making a query string for ClickHouse"):
if cast:
query = f"SELECT cast(toDateTime64('{dt_str}', 0, '{tz}'), 'Decimal({decimal_type}, {scale})')"
else:
query = f"SELECT toDecimal{decimal_type}(toDateTime64('{dt_str}', 0, '{tz}'))"
with Then(f"I execute toDecimal{decimal_type}() query"):
exec_query(request=query, expected=f"{expected}")
@TestOutline
def to_unix_timestamp64_milli_micro_nano(self, scale):
"""Check the toUnixTimestamp64[Milli/Micro/Nano] functions with DateTime64 extended range.
:param scale: 3 for milli, 6 for micro, 9 for nano; int
"""
stress = self.context.stress
timezones = timezones_range(stress)
func = {3: 'Milli', 6: 'Micro', 9: 'Nano'}
for year in years_range(stress):
with Given("I select datetimes in a year"):
datetimes = select_dates_in_year(year=year, stress=stress, microseconds=True)
for d in datetimes:
for tz in timezones:
dt = pytz.timezone(tz).localize(d)
with When(f"{dt} {tz}"):
with By("converting datetime to string"):
dt_str = dt.strftime("%Y-%m-%d %H:%M:%S.%f")
with And("converting DateTime to UTC"):
dt = dt.astimezone(pytz.timezone('UTC'))
with And("computing the expected result using python"):
expected = int(dt.timestamp() * (10**scale))
if expected >= 0:
expected += dt.microsecond * 10 ** (scale - 6)
else:
expected -= dt.microsecond * 10 ** (scale - 6)
with When(f"making a query string for ClickHouse"):
query = f"SELECT toUnixTimestamp64{func[scale]}(toDateTime64('{dt_str}', {scale}, '{tz}'))"
with Then(f"I execute toUnixTimestamp64{func[scale]}() query"):
exec_query(request=query, expected=f"{expected}")
@TestScenario
@Requirements(
RQ_SRS_010_DateTime64_ExtendedRange_TypeConversionFunctions_toUnixTimestamp64Milli("1.0")
)
def to_unix_timestamp64_milli(self):
"""Check the toUnixTimestamp64Milli functions with DateTime64 extended range.
"""
to_unix_timestamp64_milli_micro_nano(scale=3)
@TestScenario
@Requirements(
RQ_SRS_010_DateTime64_ExtendedRange_TypeConversionFunctions_toUnixTimestamp64Micro("1.0")
)
def to_unix_timestamp64_micro(self):
"""Check the toUnixTimestamp64Micro functions with DateTime64 extended range.
"""
to_unix_timestamp64_milli_micro_nano(scale=6)
@TestScenario
@Requirements(
RQ_SRS_010_DateTime64_ExtendedRange_TypeConversionFunctions_toUnixTimestamp64Nano("1.0")
)
def to_unix_timestamp64_nano(self):
"""Check the toUnixTimestamp64Nano functions with DateTime64 extended range.
"""
to_unix_timestamp64_milli_micro_nano(scale=9)
@TestOutline
def from_unix_timestamp64_milli_micro_nano(self, scale):
"""Check the fromUnixTimestamp64[Milli/Micro/Nano] functions with DateTime64 extended range.
:param scale: 3 for milli, 6 for micro, 9 for nano; int
"""
stress = self.context.stress
timezones = timezones_range(stress)
func = {3: 'Milli', 6: 'Micro', 9: 'Nano'}
for year in years_range(stress):
with Given("I select datetimes in a year"):
datetimes = select_dates_in_year(year=year, stress=stress, microseconds=True)
for d in datetimes:
for tz in timezones:
dt = pytz.timezone(tz).localize(d)
with When(f"{dt} {tz}"):
with By("converting datetime to string"):
d_str = d.strftime("%Y-%m-%d %H:%M:%S.%f")
d_str += "0" * (scale-3)
with And("converting DateTime64 to UTC"):
dt = dt.astimezone(pytz.timezone('UTC'))
with And("computing the expected result using python"):
ts = int(dt.timestamp() * (10**scale))
if ts >= 0:
ts += dt.microsecond * 10 ** (scale - 6)
else:
ts -= dt.microsecond * 10 ** (scale - 6)
with And(f"making a query string for ClickHouse"):
query = f"SELECT fromUnixTimestamp64{func[scale]}(CAST({ts}, 'Int64'), '{tz}')"
with Then(f"I execute fromUnixTimestamp64{func[scale]}() query"):
exec_query(request=query, expected=f"{d_str}")
@TestScenario
@Requirements(
RQ_SRS_010_DateTime64_ExtendedRange_TypeConversionFunctions_fromUnixTimestamp64Milli("1.0")
)
def from_unix_timestamp64_milli(self):
"""Check the fromUnixTimestamp64Milli functions with DateTime64 extended range.
"""
from_unix_timestamp64_milli_micro_nano(scale=3)
@TestScenario
@Requirements(
RQ_SRS_010_DateTime64_ExtendedRange_TypeConversionFunctions_fromUnixTimestamp64Micro("1.0")
)
def from_unix_timestamp64_micro(self):
"""Check the fromUnixTimestamp64Micro functions with DateTime64 extended range.
"""
from_unix_timestamp64_milli_micro_nano(scale=6)
@TestScenario
@Requirements(
RQ_SRS_010_DateTime64_ExtendedRange_TypeConversionFunctions_fromUnixTimestamp64Nano("1.0")
)
def from_unix_timestamp64_nano(self):
"""Check the fromUnixTimestamp64Nano functions with DateTime64 extended range.
"""
from_unix_timestamp64_milli_micro_nano(scale=9)
@TestFeature
@Requirements(
RQ_SRS_010_DateTime64_ExtendedRange_TypeConversionFunctions("1.0")
)
def type_conversion(self, node="clickhouse1"):
"""Check the type conversion operations with DateTime64. Cast can be set as Requirement thereby as the module
tests exactly what CAST does.
"""
self.context.node = self.context.cluster.node(node)
for scenario in loads(current_module(), Scenario):
Scenario(run=scenario, flags=TE)

View File

@ -278,7 +278,7 @@ class Cluster(object):
if not os.path.exists(docker_compose_file_path): if not os.path.exists(docker_compose_file_path):
raise TypeError("docker compose file '{docker_compose_file_path}' does not exist") raise TypeError("docker compose file '{docker_compose_file_path}' does not exist")
self.docker_compose += f" --no-ansi --project-directory \"{docker_compose_project_dir}\" --file \"{docker_compose_file_path}\"" self.docker_compose += f" --project-directory \"{docker_compose_project_dir}\" --file \"{docker_compose_file_path}\""
self.lock = threading.Lock() self.lock = threading.Lock()
def shell(self, node, timeout=300): def shell(self, node, timeout=300):

View File

@ -19,7 +19,8 @@ def regression(self, local, clickhouse_binary_path, stress=None, parallel=None):
# Feature(test=load("rbac.regression", "regression"))(**args) # Feature(test=load("rbac.regression", "regression"))(**args)
# Feature(test=load("aes_encryption.regression", "regression"))(**args) # Feature(test=load("aes_encryption.regression", "regression"))(**args)
Feature(test=load("map_type.regression", "regression"))(**args) Feature(test=load("map_type.regression", "regression"))(**args)
# Feature(test=load("window_functions.regression", "regression"))(**args) Feature(test=load("window_functions.regression", "regression"))(**args)
# Feature(test=load("datetime64_extended_range.regression", "regression"))(**args)
# Feature(test=load("kerberos.regression", "regression"))(**args) # Feature(test=load("kerberos.regression", "regression"))(**args)
if main(): if main():

View File

@ -202,7 +202,13 @@ All the updates are tracked using the [Revision History].
## Introduction ## Introduction
This software requirements specification covers requirements for `Map(key, value)` data type in [ClickHouse]. This software requirements specification covers requirements for supporting window functions in [ClickHouse].
Similar functionality exists in [MySQL] and [PostreSQL]. [PostreSQL] defines a window function as follows:
> A window function performs a calculation across a set of table rows that are somehow related to the current row.
> This is comparable to the type of calculation that can be done with an aggregate function.
> But unlike regular aggregate functions, use of a window function does not cause rows to
> become grouped into a single output row — the rows retain their separate identities.
## Requirements ## Requirements
@ -2290,3 +2296,5 @@ version: 1.0
[Revision History]: https://github.com/ClickHouse/ClickHouse/commits/master/tests/testflows/window_functions/requirements/requirements.md [Revision History]: https://github.com/ClickHouse/ClickHouse/commits/master/tests/testflows/window_functions/requirements/requirements.md
[Git]: https://git-scm.com/ [Git]: https://git-scm.com/
[GitHub]: https://github.com [GitHub]: https://github.com
[PostreSQL]: https://www.postgresql.org/docs/9.2/tutorial-window.html
[MySQL]: https://dev.mysql.com/doc/refman/8.0/en/window-functions.html

View File

@ -1,6 +1,6 @@
# These requirements were auto generated # These requirements were auto generated
# from software requirements specification (SRS) # from software requirements specification (SRS)
# document by TestFlows v1.6.210312.1172513. # document by TestFlows v1.6.210505.1133630.
# Do not edit by hand but re-generate instead # Do not edit by hand but re-generate instead
# using 'tfs requirements generate' command. # using 'tfs requirements generate' command.
from testflows.core import Specification from testflows.core import Specification
@ -3796,7 +3796,13 @@ All the updates are tracked using the [Revision History].
## Introduction ## Introduction
This software requirements specification covers requirements for `Map(key, value)` data type in [ClickHouse]. This software requirements specification covers requirements for supporting window functions in [ClickHouse].
Similar functionality exists in [MySQL] and [PostreSQL]. [PostreSQL] defines a window function as follows:
> A window function performs a calculation across a set of table rows that are somehow related to the current row.
> This is comparable to the type of calculation that can be done with an aggregate function.
> But unlike regular aggregate functions, use of a window function does not cause rows to
> become grouped into a single output row the rows retain their separate identities.
## Requirements ## Requirements
@ -5884,4 +5890,6 @@ version: 1.0
[Revision History]: https://github.com/ClickHouse/ClickHouse/commits/master/tests/testflows/window_functions/requirements/requirements.md [Revision History]: https://github.com/ClickHouse/ClickHouse/commits/master/tests/testflows/window_functions/requirements/requirements.md
[Git]: https://git-scm.com/ [Git]: https://git-scm.com/
[GitHub]: https://github.com [GitHub]: https://github.com
[PostreSQL]: https://www.postgresql.org/docs/9.2/tutorial-window.html
[MySQL]: https://dev.mysql.com/doc/refman/8.0/en/window-functions.html
''') ''')

View File

@ -100,7 +100,7 @@ def t1_table(self, name="t1", distributed=False):
create_table(name=name + "_source", statement=sql, on_cluster="sharded_cluster") create_table(name=name + "_source", statement=sql, on_cluster="sharded_cluster")
with And("a distributed table"): with And("a distributed table"):
sql = "CREATE TABLE {name} AS " + name + '_source' + " ENGINE = Distributed(sharded_cluster, default, " + f"{name + '_source'}, rand())" sql = "CREATE TABLE {name} AS " + name + '_source' + " ENGINE = Distributed(sharded_cluster, default, " + f"{name + '_source'}, f1 % toUInt8(getMacro('shard')))"
table = create_table(name=name, statement=sql) table = create_table(name=name, statement=sql)
with And("populating table with data"): with And("populating table with data"):
@ -155,7 +155,7 @@ def datetimes_table(self, name="datetimes", distributed=False):
create_table(name=name + "_source", statement=sql, on_cluster="sharded_cluster") create_table(name=name + "_source", statement=sql, on_cluster="sharded_cluster")
with And("a distributed table"): with And("a distributed table"):
sql = "CREATE TABLE {name} AS " + name + '_source' + " ENGINE = Distributed(sharded_cluster, default, " + f"{name + '_source'}, rand())" sql = "CREATE TABLE {name} AS " + name + '_source' + " ENGINE = Distributed(sharded_cluster, default, " + f"{name + '_source'}, id % toUInt8(getMacro('shard')))"
table = create_table(name=name, statement=sql) table = create_table(name=name, statement=sql)
with And("populating table with data"): with And("populating table with data"):
@ -213,7 +213,7 @@ def numerics_table(self, name="numerics", distributed=False):
create_table(name=name + "_source", statement=sql, on_cluster="sharded_cluster") create_table(name=name + "_source", statement=sql, on_cluster="sharded_cluster")
with And("a distributed table"): with And("a distributed table"):
sql = "CREATE TABLE {name} AS " + name + '_source' + " ENGINE = Distributed(sharded_cluster, default, " + f"{name + '_source'}, rand())" sql = "CREATE TABLE {name} AS " + name + '_source' + " ENGINE = Distributed(sharded_cluster, default, " + f"{name + '_source'}, id % toUInt8(getMacro('shard')))"
table = create_table(name=name, statement=sql) table = create_table(name=name, statement=sql)
with And("populating table with data"): with And("populating table with data"):
@ -282,7 +282,7 @@ def tenk1_table(self, name="tenk1", distributed=False):
create_table(name=name + '_source', statement=sql, on_cluster="sharded_cluster") create_table(name=name + '_source', statement=sql, on_cluster="sharded_cluster")
with And("a distributed table"): with And("a distributed table"):
sql = "CREATE TABLE {name} AS " + name + '_source' + " ENGINE = Distributed(sharded_cluster, default, " + f"{name + '_source'}, rand())" sql = "CREATE TABLE {name} AS " + name + '_source' + " ENGINE = Distributed(sharded_cluster, default, " + f"{name + '_source'}, unique1 % toUInt8(getMacro('shard')))"
table = create_table(name=name, statement=sql) table = create_table(name=name, statement=sql)
with And("populating table with data"): with And("populating table with data"):
@ -353,7 +353,7 @@ def empsalary_table(self, name="empsalary", distributed=False):
create_table(name=name + "_source", statement=sql, on_cluster="sharded_cluster") create_table(name=name + "_source", statement=sql, on_cluster="sharded_cluster")
with And("a distributed table"): with And("a distributed table"):
sql = "CREATE TABLE {name} AS " + name + '_source' + " ENGINE = Distributed(sharded_cluster, default, " + f"{name + '_source'}, rand())" sql = "CREATE TABLE {name} AS " + name + '_source' + " ENGINE = Distributed(sharded_cluster, default, " + f"{name + '_source'}, empno % toUInt8(getMacro('shard')))"
table = create_table(name=name, statement=sql) table = create_table(name=name, statement=sql)
with And("populating distributed table with data"): with And("populating distributed table with data"):