private static Uri GetAnnotatedDatatypeIri(DatatypeDescription datatypeDescription)
{
if (datatypeDescription == null)
{
return(DatatypeAnnotation.String.Iri);
}
if (datatypeDescription.Id != null)
{
return(datatypeDescription.Id);
}
var annotation = DatatypeAnnotation.GetAnnotationById(datatypeDescription.Base);
if (annotation == null)
{
throw new ConversionError(
$"Could not determine the correct IRI for the datatype annotation {datatypeDescription.Base}");
}
return(annotation.Iri);
}
public static CellValue NormalizeCellValue(string rawValue, ColumnDescription column,
DatatypeDescription cellDatatype)
{
var baseDatatype = cellDatatype == null
? DatatypeAnnotation.String
: DatatypeAnnotation.GetAnnotationById(cellDatatype.Base);
if (baseDatatype == null)
{
throw new Converter.ConversionError($"Unrecognized cell base datatype ID: {cellDatatype.Base}");
}
var cellValue = new CellValue {
RawString = rawValue
};
if (rawValue == null)
{
return(cellValue);
}
var normalizedString = rawValue;
if (!RetainsLineEndings.Contains(baseDatatype))
{
normalizedString = normalizedString.Replace('\u000d', ' ').Replace('\u000a', ' ')
.Replace('\u0009', ' ');
}
if (!RetainsLeadingAndTrailingWhitespace.Contains(baseDatatype))
{
normalizedString = normalizedString.Trim();
normalizedString = Regex.Replace(normalizedString, @"\s+", " ");
}
if (normalizedString.Equals(string.Empty))
{
normalizedString = column.Default;
}
cellValue.NormalizedString = normalizedString;
// 5. if the column separator annotation is not null, the cell value is a list of values; set the list annotation on the cell to true, and create the cell value created by:
if (column.Separator != null)
{
cellValue.IsList = true;
// 5.1 if the normalized string is the same as any one of the values of the column null annotation, then the resulting value is null.
if (column.Null.Contains(normalizedString) || normalizedString == null)
{
cellValue.ValueList = null;
}
else
{
cellValue.ValueList = new List <string>();
// 5.2 split the normalized string at the character specified by the column separator annotation.
foreach (var tok in normalizedString.Split(new[] { column.Separator }, StringSplitOptions.None))
{
// 5.3 unless the datatype base is string or anyAtomicType, strip leading and trailing whitespace from these strings.
var normalizedToken = tok;
if (!RetainsLeadingAndTrailingWhitespaceInList.Contains(baseDatatype))
{
normalizedToken = normalizedToken.Trim();
}
// 5.4 applying the remaining steps to each of the strings in turn.
NormalizeCellValue(cellValue, normalizedToken, column, cellDatatype);
}
}
}
else
{
NormalizeCellValue(cellValue, normalizedString, column, cellDatatype);
}
return(cellValue);
}
