#pragma once #include #include #include #include #include #include namespace DB { namespace ErrorCodes { extern const int CANNOT_PARSE_IPV4; extern const int CANNOT_PARSE_IPV6; extern const int ILLEGAL_COLUMN; } enum class IPStringToNumExceptionMode : uint8_t { Throw, Default, Null }; static inline bool tryParseIPv4(const char * pos, UInt32 & result_value) { return parseIPv4(pos, reinterpret_cast(&result_value)); } namespace detail { template ColumnPtr convertToIPv6(const StringColumnType & string_column, const PaddedPODArray * null_map = nullptr) { if constexpr (!std::is_same_v && !std::is_same_v) throw Exception(ErrorCodes::ILLEGAL_COLUMN, "Illegal return column type {}. Expected IPv6 or FixedString", TypeName); size_t column_size = string_column.size(); ColumnUInt8::MutablePtr col_null_map_to; ColumnUInt8::Container * vec_null_map_to = nullptr; if constexpr (exception_mode == IPStringToNumExceptionMode::Null) { col_null_map_to = ColumnUInt8::create(column_size, false); vec_null_map_to = &col_null_map_to->getData(); } auto column_create = []() -> typename ToColumn::MutablePtr { if constexpr (std::is_same_v) return ColumnFixedString::create(IPV6_BINARY_LENGTH); else return ColumnIPv6::create(); }; auto get_vector = [](auto & col_res, size_t col_size) -> typename std::conditional< std::is_same_v, decltype(ColumnFixedString::create()->getChars()), decltype(ColumnIPv6::create()->getData()) >::type { if constexpr (std::is_same_v) { auto & vec_res = col_res->getChars(); vec_res.resize(col_size * IPV6_BINARY_LENGTH); return vec_res; } else { auto & vec_res = col_res->getData(); vec_res.resize(col_size); return vec_res; } }; auto col_res = column_create(); auto & vec_res = get_vector(col_res, column_size); using Chars = typename StringColumnType::Chars; const Chars & vec_src = string_column.getChars(); size_t src_offset = 0; char src_ipv4_buf[sizeof("::ffff:") + IPV4_MAX_TEXT_LENGTH + 1] = "::ffff:"; /// ColumnFixedString contains not null terminated strings. But functions parseIPv6, parseIPv4 expect null terminated string. std::string fixed_string_buffer; if constexpr (std::is_same_v) { fixed_string_buffer.resize(string_column.getN()); } int offset_inc = 1; if constexpr (std::is_same_v) offset_inc = IPV6_BINARY_LENGTH; for (size_t out_offset = 0, i = 0; i < column_size; out_offset += offset_inc, ++i) { size_t src_next_offset = src_offset; const char * src_value = nullptr; unsigned char * res_value = reinterpret_cast(&vec_res[out_offset]); if constexpr (std::is_same_v) { src_value = reinterpret_cast(&vec_src[src_offset]); src_next_offset = string_column.getOffsets()[i]; } else if constexpr (std::is_same_v) { size_t fixed_string_size = string_column.getN(); std::memcpy(fixed_string_buffer.data(), reinterpret_cast(&vec_src[src_offset]), fixed_string_size); src_value = fixed_string_buffer.data(); src_next_offset += fixed_string_size; } if (null_map && (*null_map)[i]) { std::fill_n(&vec_res[i], IPV6_BINARY_LENGTH, 0); src_offset = src_next_offset; if constexpr (exception_mode == IPStringToNumExceptionMode::Null) (*vec_null_map_to)[i] = true; continue; } bool parse_result = false; UInt32 dummy_result = 0; /// For both cases below: In case of failure, the function parseIPv6 fills vec_res with zero bytes. /// If the source IP address is parsable as an IPv4 address, then transform it into a valid IPv6 address. /// Keeping it simple by just prefixing `::ffff:` to the IPv4 address to represent it as a valid IPv6 address. if (tryParseIPv4(src_value, dummy_result)) { std::memcpy( src_ipv4_buf + std::strlen("::ffff:"), src_value, std::min(src_next_offset - src_offset, IPV4_MAX_TEXT_LENGTH + 1)); parse_result = parseIPv6(src_ipv4_buf, res_value); } else { parse_result = parseIPv6(src_value, res_value); } if (!parse_result) { if constexpr (exception_mode == IPStringToNumExceptionMode::Throw) throw Exception("Invalid IPv6 value", ErrorCodes::CANNOT_PARSE_IPV6); else if constexpr (exception_mode == IPStringToNumExceptionMode::Default) vec_res[i] = 0; else if constexpr (exception_mode == IPStringToNumExceptionMode::Null) (*vec_null_map_to)[i] = true; } src_offset = src_next_offset; } if constexpr (exception_mode == IPStringToNumExceptionMode::Null) return ColumnNullable::create(std::move(col_res), std::move(col_null_map_to)); return col_res; } } template ColumnPtr convertToIPv6(ColumnPtr column, const PaddedPODArray * null_map = nullptr) { if (const auto * column_input_string = checkAndGetColumn(column.get())) { return detail::convertToIPv6(*column_input_string, null_map); } else if (const auto * column_input_fixed_string = checkAndGetColumn(column.get())) { return detail::convertToIPv6(*column_input_fixed_string, null_map); } else { throw Exception(ErrorCodes::ILLEGAL_COLUMN, "Illegal column type {}. Expected String or FixedString", column->getName()); } } template ColumnPtr convertToIPv4(ColumnPtr column, const PaddedPODArray * null_map = nullptr) { const ColumnString * column_string = checkAndGetColumn(column.get()); if (!column_string) { throw Exception(ErrorCodes::ILLEGAL_COLUMN, "Illegal column type {}. Expected String.", column->getName()); } size_t column_size = column_string->size(); ColumnUInt8::MutablePtr col_null_map_to; ColumnUInt8::Container * vec_null_map_to = nullptr; if constexpr (exception_mode == IPStringToNumExceptionMode::Null) { col_null_map_to = ColumnUInt8::create(column_size, false); vec_null_map_to = &col_null_map_to->getData(); } auto col_res = ToColumn::create(); auto & vec_res = col_res->getData(); vec_res.resize(column_size); const ColumnString::Chars & vec_src = column_string->getChars(); const ColumnString::Offsets & offsets_src = column_string->getOffsets(); size_t prev_offset = 0; for (size_t i = 0; i < vec_res.size(); ++i) { if (null_map && (*null_map)[i]) { vec_res[i] = 0; prev_offset = offsets_src[i]; if constexpr (exception_mode == IPStringToNumExceptionMode::Null) (*vec_null_map_to)[i] = true; continue; } bool parse_result = tryParseIPv4(reinterpret_cast(&vec_src[prev_offset]), vec_res[i]); if (!parse_result) { if constexpr (exception_mode == IPStringToNumExceptionMode::Throw) { throw Exception("Invalid IPv4 value", ErrorCodes::CANNOT_PARSE_IPV4); } else if constexpr (exception_mode == IPStringToNumExceptionMode::Default) { vec_res[i] = 0; } else if constexpr (exception_mode == IPStringToNumExceptionMode::Null) { (*vec_null_map_to)[i] = true; vec_res[i] = 0; } } prev_offset = offsets_src[i]; } if constexpr (exception_mode == IPStringToNumExceptionMode::Null) return ColumnNullable::create(std::move(col_res), std::move(col_null_map_to)); return col_res; } }