#include #include #include #include #include #include #include #include #include #include #include #include #include #include "formatString.h" namespace DB { namespace ErrorCodes { extern const int ILLEGAL_TYPE_OF_ARGUMENT; extern const int NUMBER_OF_ARGUMENTS_DOESNT_MATCH; extern const int ILLEGAL_COLUMN; } using namespace GatherUtils; namespace { template class ConcatImpl : public IFunction { public: static constexpr auto name = Name::name; explicit ConcatImpl(ContextPtr context_) : context(context_) {} static FunctionPtr create(ContextPtr context) { return std::make_shared(context); } String getName() const override { return name; } bool isVariadic() const override { return true; } size_t getNumberOfArguments() const override { return 0; } bool isInjective(const ColumnsWithTypeAndName &) const override { return is_injective; } bool isSuitableForShortCircuitArgumentsExecution(const DataTypesWithConstInfo & /*arguments*/) const override { return true; } bool useDefaultImplementationForConstants() const override { return true; } DataTypePtr getReturnTypeImpl(const DataTypes & arguments) const override { if (arguments.size() < 2) throw Exception( ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH, "Number of arguments for function {} doesn't match: passed {}, should be at least 2", getName(), arguments.size()); for (const auto arg_idx : collections::range(0, arguments.size())) { const auto * arg = arguments[arg_idx].get(); if (!isStringOrFixedString(arg)) throw Exception( ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Illegal type {} of argument {} of function {}", arg->getName(), arg_idx + 1, getName()); } return std::make_shared(); } ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t input_rows_count) const override { /// Format function is not proven to be faster for two arguments. /// Actually there is overhead of 2 to 5 extra instructions for each string for checking empty strings in FormatImpl. /// Though, benchmarks are really close, for most examples we saw executeBinary is slightly faster (0-3%). /// For 3 and more arguments FormatImpl is much faster (up to 50-60%). if (arguments.size() == 2) return executeBinary(arguments, input_rows_count); else return executeFormatImpl(arguments, input_rows_count); } private: ContextWeakPtr context; ColumnPtr executeBinary(const ColumnsWithTypeAndName & arguments, size_t input_rows_count) const { const IColumn * c0 = arguments[0].column.get(); const IColumn * c1 = arguments[1].column.get(); const ColumnString * c0_string = checkAndGetColumn(c0); const ColumnString * c1_string = checkAndGetColumn(c1); const ColumnConst * c0_const_string = checkAndGetColumnConst(c0); const ColumnConst * c1_const_string = checkAndGetColumnConst(c1); auto c_res = ColumnString::create(); if (c0_string && c1_string) concat(StringSource(*c0_string), StringSource(*c1_string), StringSink(*c_res, c0->size())); else if (c0_string && c1_const_string) concat(StringSource(*c0_string), ConstSource(*c1_const_string), StringSink(*c_res, c0->size())); else if (c0_const_string && c1_string) concat(ConstSource(*c0_const_string), StringSource(*c1_string), StringSink(*c_res, c0->size())); else { /// Fallback: use generic implementation for not very important cases. return executeFormatImpl(arguments, input_rows_count); } return c_res; } ColumnPtr executeFormatImpl(const ColumnsWithTypeAndName & arguments, size_t input_rows_count) const { const size_t num_arguments = arguments.size(); assert(num_arguments >= 2); auto c_res = ColumnString::create(); std::vector data(num_arguments); std::vector offsets(num_arguments); std::vector fixed_string_sizes(num_arguments); std::vector> constant_strings(num_arguments); bool has_column_string = false; bool has_column_fixed_string = false; for (size_t i = 0; i < num_arguments; ++i) { const ColumnPtr & column = arguments[i].column; if (const ColumnString * col = checkAndGetColumn(column.get())) { has_column_string = true; data[i] = &col->getChars(); offsets[i] = &col->getOffsets(); } else if (const ColumnFixedString * fixed_col = checkAndGetColumn(column.get())) { has_column_fixed_string = true; data[i] = &fixed_col->getChars(); fixed_string_sizes[i] = fixed_col->getN(); } else if (const ColumnConst * const_col = checkAndGetColumnConstStringOrFixedString(column.get())) { constant_strings[i] = const_col->getValue(); } else throw Exception(ErrorCodes::ILLEGAL_COLUMN, "Illegal column {} of argument of function {}", column->getName(), getName()); } String pattern; pattern.reserve(2 * num_arguments); for (size_t i = 0; i < num_arguments; ++i) pattern += "{}"; FormatImpl::formatExecute( has_column_string, has_column_fixed_string, std::move(pattern), data, offsets, fixed_string_sizes, constant_strings, c_res->getChars(), c_res->getOffsets(), input_rows_count); return c_res; } }; struct NameConcat { static constexpr auto name = "concat"; }; struct NameConcatAssumeInjective { static constexpr auto name = "concatAssumeInjective"; }; using FunctionConcat = ConcatImpl; using FunctionConcatAssumeInjective = ConcatImpl; /// Also works with arrays. class ConcatOverloadResolver : public IFunctionOverloadResolver { public: static constexpr auto name = "concat"; static FunctionOverloadResolverPtr create(ContextPtr context) { return std::make_unique(context); } explicit ConcatOverloadResolver(ContextPtr context_) : context(context_) {} String getName() const override { return name; } size_t getNumberOfArguments() const override { return 0; } bool isVariadic() const override { return true; } FunctionBasePtr buildImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr & return_type) const override { if (isArray(arguments.at(0).type)) { return FunctionFactory::instance().getImpl("arrayConcat", context)->build(arguments); } else if (isMap(arguments.at(0).type)) { return FunctionFactory::instance().getImpl("mapConcat", context)->build(arguments); } else return std::make_unique( FunctionConcat::create(context), collections::map(arguments, [](const auto & elem) { return elem.type; }), return_type); } DataTypePtr getReturnTypeImpl(const DataTypes & arguments) const override { if (arguments.size() < 2) throw Exception(ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH, "Number of arguments for function {} doesn't match: passed {}, should be at least 2.", getName(), arguments.size()); /// We always return Strings from concat, even if arguments were fixed strings. return std::make_shared(); } private: ContextPtr context; }; } REGISTER_FUNCTION(Concat) { factory.registerFunction({}, FunctionFactory::CaseInsensitive); factory.registerFunction(); } }