#pragma once #include #include #include #include #include #include #include #include namespace DB { /// Functions for text classification with different result types namespace ErrorCodes { extern const int ILLEGAL_TYPE_OF_ARGUMENT; extern const int ILLEGAL_COLUMN; extern const int SUPPORT_IS_DISABLED; } template class FunctionTextClassificationString : public IFunction { public: static constexpr auto name = Name::name; static FunctionPtr create(ContextPtr context) { if (!context->getSettingsRef().allow_experimental_nlp_functions) throw Exception(ErrorCodes::SUPPORT_IS_DISABLED, "Natural language processing function '{}' is experimental. Set `allow_experimental_nlp_functions` setting to enable it", name); return std::make_shared(); } String getName() const override { return name; } size_t getNumberOfArguments() const override { return 1; } bool isSuitableForShortCircuitArgumentsExecution(const DataTypesWithConstInfo & /*arguments*/) const override { return true; } bool useDefaultImplementationForConstants() const override { return true; } DataTypePtr getReturnTypeImpl(const DataTypes & arguments) const override { if (!isString(arguments[0])) throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Illegal type {} of argument of function {}. Must be String.", arguments[0]->getName(), getName()); return arguments[0]; } ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr & /*result_type*/, size_t /*input_rows_count*/) const override { const ColumnPtr & column = arguments[0].column; const ColumnString * col = checkAndGetColumn(column.get()); if (!col) throw Exception( "Illegal column " + arguments[0].column->getName() + " of argument of function " + getName(), ErrorCodes::ILLEGAL_COLUMN); auto col_res = ColumnString::create(); Impl::vector(col->getChars(), col->getOffsets(), col_res->getChars(), col_res->getOffsets()); return col_res; } }; template class FunctionTextClassificationFloat : public IFunction { public: static constexpr auto name = Name::name; static FunctionPtr create(ContextPtr context) { if (!context->getSettingsRef().allow_experimental_nlp_functions) throw Exception(ErrorCodes::SUPPORT_IS_DISABLED, "Natural language processing function '{}' is experimental. Set `allow_experimental_nlp_functions` setting to enable it", name); return std::make_shared(); } String getName() const override { return name; } size_t getNumberOfArguments() const override { return 1; } bool isSuitableForShortCircuitArgumentsExecution(const DataTypesWithConstInfo & /*arguments*/) const override { return true; } bool useDefaultImplementationForConstants() const override { return true; } DataTypePtr getReturnTypeImpl(const DataTypes & arguments) const override { if (!isString(arguments[0])) throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Illegal type {} of argument of function {}. Must be String.", arguments[0]->getName(), getName()); return std::make_shared(); } ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr & /*result_type*/, size_t /*input_rows_count*/) const override { const ColumnPtr & column = arguments[0].column; const ColumnString * col = checkAndGetColumn(column.get()); if (!col) throw Exception( "Illegal column " + arguments[0].column->getName() + " of argument of function " + getName(), ErrorCodes::ILLEGAL_COLUMN); auto col_res = ColumnVector::create(); ColumnVector::Container & vec_res = col_res->getData(); vec_res.resize(col->size()); Impl::vector(col->getChars(), col->getOffsets(), vec_res); return col_res; } }; }