ClickHouse/src/Functions/extractTimeZoneFromFunctionArguments.cpp

84 lines
3.0 KiB
C++
Raw Normal View History

#include <Functions/extractTimeZoneFromFunctionArguments.h>
#include <Functions/FunctionHelpers.h>
#include <Core/Block.h>
#include <DataTypes/DataTypeDateTime.h>
#include <DataTypes/DataTypeDateTime64.h>
#include <Columns/ColumnString.h>
#include <Common/DateLUT.h>
namespace DB
{
namespace ErrorCodes
{
extern const int ILLEGAL_COLUMN;
extern const int ILLEGAL_TYPE_OF_ARGUMENT;
}
2023-04-12 18:36:23 +00:00
std::string extractTimeZoneNameFromColumn(const IColumn * column, const String & column_name)
{
2023-04-12 18:36:23 +00:00
const ColumnConst * time_zone_column = checkAndGetColumnConst<ColumnString>(column);
if (!time_zone_column)
throw Exception(ErrorCodes::ILLEGAL_COLUMN,
2023-04-12 18:36:23 +00:00
"Illegal column {} of time zone argument of function, must be a constant string",
column_name);
return time_zone_column->getValue<String>();
}
std::string extractTimeZoneNameFromFunctionArguments(const ColumnsWithTypeAndName & arguments, size_t time_zone_arg_num, size_t datetime_arg_num, bool allow_nonconst_timezone_arguments)
{
/// Explicit time zone may be passed in last argument.
if ((arguments.size() == time_zone_arg_num + 1)
&& (!allow_nonconst_timezone_arguments || arguments[time_zone_arg_num].column))
{
2023-04-12 18:36:23 +00:00
return extractTimeZoneNameFromColumn(arguments[time_zone_arg_num].column.get(), arguments[time_zone_arg_num].name);
}
else
{
if (arguments.size() <= datetime_arg_num)
return {};
const auto & dt_arg = arguments[datetime_arg_num].type.get();
/// If time zone is attached to an argument of type DateTime.
if (const auto * type = checkAndGetDataType<DataTypeDateTime>(dt_arg))
return type->hasExplicitTimeZone() ? type->getTimeZone().getTimeZone() : std::string();
if (const auto * type = checkAndGetDataType<DataTypeDateTime64>(dt_arg))
return type->hasExplicitTimeZone() ? type->getTimeZone().getTimeZone() : std::string();
return {};
}
}
2020-11-17 15:32:40 +00:00
const DateLUTImpl & extractTimeZoneFromFunctionArguments(const ColumnsWithTypeAndName & arguments, size_t time_zone_arg_num, size_t datetime_arg_num)
{
if (arguments.size() == time_zone_arg_num + 1)
{
2023-04-12 18:36:23 +00:00
std::string time_zone = extractTimeZoneNameFromColumn(arguments[time_zone_arg_num].column.get(), arguments[time_zone_arg_num].name);
if (time_zone.empty())
throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Provided time zone must be non-empty and be a valid time zone");
return DateLUT::instance(time_zone);
}
else
{
if (arguments.size() <= datetime_arg_num)
return DateLUT::instance();
Extended range of DateTime64 to years 1925 - 2238 The Year 1925 is a starting point because most of the timezones switched to saner (mostly 15-minutes based) offsets somewhere during 1924 or before. And that significantly simplifies implementation. 2238 is to simplify arithmetics for sanitizing LUT index access; there are less than 0x1ffff days from 1925. * Extended DateLUTImpl internal LUT to 0x1ffff items, some of which represent negative (pre-1970) time values. As a collateral benefit, Date now correctly supports dates up to 2149 (instead of 2106). * Added a new strong typedef ExtendedDayNum, which represents dates pre-1970 and post 2149. * Functions that used to return DayNum now return ExtendedDayNum. * Refactored DateLUTImpl to untie DayNum from the dual role of being a value and an index (due to negative time). Index is now a different type LUTIndex with explicit conversion functions from DatNum, time_t, and ExtendedDayNum. * Updated DateLUTImpl to properly support values close to epoch start (1970-01-01 00:00), including negative ones. * Reduced resolution of DateLUTImpl::Values::time_at_offset_change to multiple of 15-minutes to allow storing 64-bits of time_t in DateLUTImpl::Value while keeping same size. * Minor performance updates to DateLUTImpl when building month LUT by skipping non-start-of-month days. * Fixed extractTimeZoneFromFunctionArguments to work correctly with DateTime64. * New unit-tests and stateless integration tests for both DateTime and DateTime64.
2020-04-17 13:26:44 +00:00
const auto & dt_arg = arguments[datetime_arg_num].type.get();
/// If time zone is attached to an argument of type DateTime.
Extended range of DateTime64 to years 1925 - 2238 The Year 1925 is a starting point because most of the timezones switched to saner (mostly 15-minutes based) offsets somewhere during 1924 or before. And that significantly simplifies implementation. 2238 is to simplify arithmetics for sanitizing LUT index access; there are less than 0x1ffff days from 1925. * Extended DateLUTImpl internal LUT to 0x1ffff items, some of which represent negative (pre-1970) time values. As a collateral benefit, Date now correctly supports dates up to 2149 (instead of 2106). * Added a new strong typedef ExtendedDayNum, which represents dates pre-1970 and post 2149. * Functions that used to return DayNum now return ExtendedDayNum. * Refactored DateLUTImpl to untie DayNum from the dual role of being a value and an index (due to negative time). Index is now a different type LUTIndex with explicit conversion functions from DatNum, time_t, and ExtendedDayNum. * Updated DateLUTImpl to properly support values close to epoch start (1970-01-01 00:00), including negative ones. * Reduced resolution of DateLUTImpl::Values::time_at_offset_change to multiple of 15-minutes to allow storing 64-bits of time_t in DateLUTImpl::Value while keeping same size. * Minor performance updates to DateLUTImpl when building month LUT by skipping non-start-of-month days. * Fixed extractTimeZoneFromFunctionArguments to work correctly with DateTime64. * New unit-tests and stateless integration tests for both DateTime and DateTime64.
2020-04-17 13:26:44 +00:00
if (const auto * type = checkAndGetDataType<DataTypeDateTime>(dt_arg))
2020-03-10 07:06:51 +00:00
return type->getTimeZone();
Extended range of DateTime64 to years 1925 - 2238 The Year 1925 is a starting point because most of the timezones switched to saner (mostly 15-minutes based) offsets somewhere during 1924 or before. And that significantly simplifies implementation. 2238 is to simplify arithmetics for sanitizing LUT index access; there are less than 0x1ffff days from 1925. * Extended DateLUTImpl internal LUT to 0x1ffff items, some of which represent negative (pre-1970) time values. As a collateral benefit, Date now correctly supports dates up to 2149 (instead of 2106). * Added a new strong typedef ExtendedDayNum, which represents dates pre-1970 and post 2149. * Functions that used to return DayNum now return ExtendedDayNum. * Refactored DateLUTImpl to untie DayNum from the dual role of being a value and an index (due to negative time). Index is now a different type LUTIndex with explicit conversion functions from DatNum, time_t, and ExtendedDayNum. * Updated DateLUTImpl to properly support values close to epoch start (1970-01-01 00:00), including negative ones. * Reduced resolution of DateLUTImpl::Values::time_at_offset_change to multiple of 15-minutes to allow storing 64-bits of time_t in DateLUTImpl::Value while keeping same size. * Minor performance updates to DateLUTImpl when building month LUT by skipping non-start-of-month days. * Fixed extractTimeZoneFromFunctionArguments to work correctly with DateTime64. * New unit-tests and stateless integration tests for both DateTime and DateTime64.
2020-04-17 13:26:44 +00:00
if (const auto * type = checkAndGetDataType<DataTypeDateTime64>(dt_arg))
return type->getTimeZone();
return DateLUT::instance();
}
}
}