bool CSVRowInputStream::read(MutableColumns & columns, RowReadExtension & ext)
{
if (istr.eof())
return false;
updateDiagnosticInfo();
String tmp;
for (size_t input_position = 0; input_position < column_indexes_for_input_fields.size(); ++input_position)
{
const auto & column_index = column_indexes_for_input_fields[input_position];
if (column_index)
{
skipWhitespacesAndTabs(istr);
data_types[*column_index]->deserializeAsTextCSV(*columns[*column_index], istr, format_settings);
skipWhitespacesAndTabs(istr);
}
else
{
readCSVString(tmp, istr, format_settings.csv);
}
skipDelimiter(istr, format_settings.csv.delimiter, input_position + 1 == column_indexes_for_input_fields.size());
}
fillUnreadColumnsWithDefaults(columns, ext);
return true;
}
void CSVRowInputStream::readPrefix()
{
/// In this format, we assume, that if first string field contain BOM as value, it will be written in quotes,
/// so BOM at beginning of stream cannot be confused with BOM in first string value, and it is safe to skip it.
skipBOMIfExists(istr);
if (with_names)
{
if (format_settings.with_names_use_header)
{
String column_name;
do
{
skipWhitespacesAndTabs(istr);
readCSVString(column_name, istr, format_settings.csv);
skipWhitespacesAndTabs(istr);
addInputColumn(column_name);
}
while (checkChar(format_settings.csv.delimiter, istr));
skipDelimiter(istr, format_settings.csv.delimiter, true);
}
else
{
setupAllColumnsByTableSchema();
skipRow(istr, format_settings.csv, column_indexes_for_input_fields.size());
}
}
else
{
setupAllColumnsByTableSchema();
}
}
void DataTypeEnum<Type>::deserializeTextCSV(IColumn & column, ReadBuffer & istr, const char delimiter) const
{
std::string name;
readCSVString(name, istr, delimiter);
static_cast<ColumnType &>(column).getData().push_back(getValue(StringRef(name)));
}
/** gcc-7 generates wrong code with optimization level greater than 1.
* See tests: dbms/src/IO/tests/write_int.cpp
* and dbms/tests/queries/0_stateless/00898_parsing_bad_diagnostic_message.sh
* This is compiler bug. The bug does not present in gcc-8 and clang-8.
* Nevertheless, we don't need high optimization of this function.
*/
bool OPTIMIZE(1) CSVRowInputStream::parseRowAndPrintDiagnosticInfo(MutableColumns & columns,
WriteBuffer & out, size_t max_length_of_column_name, size_t max_length_of_data_type_name)
{
const char delimiter = format_settings.csv.delimiter;
for (size_t input_position = 0; input_position < column_indexes_for_input_fields.size(); ++input_position)
{
if (input_position == 0 && istr.eof())
{
out << "<End of stream>\n";
return false;
}
if (column_indexes_for_input_fields[input_position].has_value())
{
const auto & column_index = *column_indexes_for_input_fields[input_position];
const auto & current_column_type = data_types[column_index];
out << "Column " << input_position << ", " << std::string((input_position < 10 ? 2 : input_position < 100 ? 1 : 0), ' ')
<< "name: " << header.safeGetByPosition(column_index).name << ", " << std::string(max_length_of_column_name - header.safeGetByPosition(column_index).name.size(), ' ')
<< "type: " << current_column_type->getName() << ", " << std::string(max_length_of_data_type_name - current_column_type->getName().size(), ' ');
BufferBase::Position prev_position = istr.position();
BufferBase::Position curr_position = istr.position();
std::exception_ptr exception;
try
{
skipWhitespacesAndTabs(istr);
prev_position = istr.position();
current_column_type->deserializeAsTextCSV(*columns[column_index], istr, format_settings);
curr_position = istr.position();
skipWhitespacesAndTabs(istr);
}
catch (...)
{
exception = std::current_exception();
}
if (curr_position < prev_position)
throw Exception("Logical error: parsing is non-deterministic.", ErrorCodes::LOGICAL_ERROR);
if (isNumber(current_column_type) || isDateOrDateTime(current_column_type))
{
/// An empty string instead of a value.
if (curr_position == prev_position)
{
out << "ERROR: text ";
verbosePrintString(prev_position, std::min(prev_position + 10, istr.buffer().end()), out);
out << " is not like " << current_column_type->getName() << "\n";
return false;
}
}
out << "parsed text: ";
verbosePrintString(prev_position, curr_position, out);
if (exception)
{
if (current_column_type->getName() == "DateTime")
out << "ERROR: DateTime must be in YYYY-MM-DD hh:mm:ss or NNNNNNNNNN (unix timestamp, exactly 10 digits) format.\n";
else if (current_column_type->getName() == "Date")
out << "ERROR: Date must be in YYYY-MM-DD format.\n";
else
out << "ERROR\n";
return false;
}
out << "\n";
if (current_column_type->haveMaximumSizeOfValue())
{
if (*curr_position != '\n' && *curr_position != '\r' && *curr_position != delimiter)
{
out << "ERROR: garbage after " << current_column_type->getName() << ": ";
verbosePrintString(curr_position, std::min(curr_position + 10, istr.buffer().end()), out);
out << "\n";
if (current_column_type->getName() == "DateTime")
out << "ERROR: DateTime must be in YYYY-MM-DD hh:mm:ss or NNNNNNNNNN (unix timestamp, exactly 10 digits) format.\n";
else if (current_column_type->getName() == "Date")
out << "ERROR: Date must be in YYYY-MM-DD format.\n";
return false;
}
}
}
else
{
static const String skipped_column_str = "<SKIPPED COLUMN>";
out << "Column " << input_position << ", " << std::string((input_position < 10 ? 2 : input_position < 100 ? 1 : 0), ' ')
<< "name: " << skipped_column_str << ", " << std::string(max_length_of_column_name - skipped_column_str.length(), ' ')
<< "type: " << skipped_column_str << ", " << std::string(max_length_of_data_type_name - skipped_column_str.length(), ' ');
String tmp;
readCSVString(tmp, istr, format_settings.csv);
}
/// Delimiters
if (input_position + 1 == column_indexes_for_input_fields.size())
{
if (istr.eof())
return false;
/// we support the extra delimiter at the end of the line
if (*istr.position() == delimiter)
{
++istr.position();
if (istr.eof())
break;
}
if (!istr.eof() && *istr.position() != '\n' && *istr.position() != '\r')
{
out << "ERROR: There is no line feed. ";
verbosePrintString(istr.position(), istr.position() + 1, out);
out << " found instead.\n"
" It's like your file has more columns than expected.\n"
"And if your file have right number of columns, maybe it have unquoted string value with comma.\n";
return false;
}
skipEndOfLine(istr);
}
else
{
try
{
assertChar(delimiter, istr);
}
catch (const DB::Exception &)
{
if (*istr.position() == '\n' || *istr.position() == '\r')
{
out << "ERROR: Line feed found where delimiter (" << delimiter << ") is expected."
" It's like your file has less columns than expected.\n"
"And if your file have right number of columns, maybe it have unescaped quotes in values.\n";
}
else
{
out << "ERROR: There is no delimiter (" << delimiter << "). ";
verbosePrintString(istr.position(), istr.position() + 1, out);
out << " found instead.\n";
}
return false;
}
}
}
return true;
}
