/// <summary>
/// Construct a TextLoader object by inferencing the dataset schema from a type.
/// </summary>
/// <param name="useHeader">Does the file contains header?</param>
/// <param name="separator">Column separator character. Default is '\t'</param>
/// <param name="allowQuotedStrings">Whether the input may include quoted values,
/// which can contain separator characters, colons,
/// and distinguish empty values from missing values. When true, consecutive separators
/// denote a missing value and an empty value is denoted by \"\".
/// When false, consecutive separators denote an empty value.</param>
/// <param name="supportSparse">Whether the input may include sparse representations e.g.
/// if one of the row contains "5 2:6 4:3" that's mean there are 5 columns all zero
/// except for 3rd and 5th columns which have values 6 and 3</param>
/// <param name="trimWhitespace">Remove trailing whitespace from lines</param>
public TextLoader CreateFrom <TInput>(bool useHeader = false,
char separator = '\t', bool allowQuotedStrings = true,
bool supportSparse = true, bool trimWhitespace = false)
{
var fields = typeof(TInput).GetFields();
Arguments.Column = new TextLoaderColumn[fields.Length];
for (int index = 0; index < fields.Length; index++)
{
var field = fields[index];
var mappingAttr = field.GetCustomAttribute <ColumnAttribute>();
if (mappingAttr == null)
{
throw Contracts.Except($"{field.Name} is missing ColumnAttribute");
}
if (Regex.Match(mappingAttr.Ordinal, @"[^(0-9,\*\-~)]+").Success)
{
throw Contracts.Except($"{mappingAttr.Ordinal} contains invalid characters. " +
$"Valid characters are 0-9, *, - and ~");
}
var name = mappingAttr.Name ?? field.Name;
Runtime.Data.TextLoader.Range[] sources;
if (!Runtime.Data.TextLoader.Column.TryParseSourceEx(mappingAttr.Ordinal, out sources))
{
throw Contracts.Except($"{mappingAttr.Ordinal} could not be parsed.");
}
Contracts.Assert(sources != null);
TextLoaderColumn tlc = new TextLoaderColumn();
tlc.Name = name;
tlc.Source = new TextLoaderRange[sources.Length];
DataKind dk;
if (!TryGetDataKind(field.FieldType.IsArray ? field.FieldType.GetElementType() : field.FieldType, out dk))
{
throw Contracts.Except($"{name} is of unsupported type.");
}
tlc.Type = dk;
for (int indexLocal = 0; indexLocal < tlc.Source.Length; indexLocal++)
{
tlc.Source[indexLocal] = new TextLoaderRange
{
AllOther = sources[indexLocal].AllOther,
AutoEnd = sources[indexLocal].AutoEnd,
ForceVector = sources[indexLocal].ForceVector,
VariableEnd = sources[indexLocal].VariableEnd,
Max = sources[indexLocal].Max,
Min = sources[indexLocal].Min
};
}
Arguments.Column[index] = tlc;
}
Arguments.HasHeader = useHeader;
Arguments.Separator = new[] { separator };
Arguments.AllowQuoting = allowQuotedStrings;
Arguments.AllowSparse = supportSparse;
Arguments.TrimWhitespace = trimWhitespace;
return(this);
}
/// <summary>
/// Construct a TextLoader object by inferencing the dataset schema from a type.
/// </summary>
/// <param name="useHeader">Does the file contains header?</param>
/// <param name="separator">Column separator character. Default is '\t'</param>
/// <param name="allowQuotedStrings">Whether the input may include quoted values,
/// which can contain separator characters, colons,
/// and distinguish empty values from missing values. When true, consecutive separators
/// denote a missing value and an empty value is denoted by \"\".
/// When false, consecutive separators denote an empty value.</param>
/// <param name="supportSparse">Whether the input may include sparse representations for example,
/// if one of the row contains "5 2:6 4:3" that's mean there are 5 columns all zero
/// except for 3rd and 5th columns which have values 6 and 3</param>
/// <param name="trimWhitespace">Remove trailing whitespace from lines</param>
public TextLoader CreateFrom <TInput>(bool useHeader = false,
char separator = '\t', bool allowQuotedStrings = true,
bool supportSparse = true, bool trimWhitespace = false)
{
var userType = typeof(TInput);
var fieldInfos = userType.GetFields(BindingFlags.Public | BindingFlags.Instance);
var propertyInfos =
userType
.GetProperties(BindingFlags.Public | BindingFlags.Instance)
.Where(x => x.CanRead && x.CanWrite && x.GetGetMethod() != null && x.GetSetMethod() != null && x.GetIndexParameters().Length == 0);
var memberInfos = (fieldInfos as IEnumerable <MemberInfo>).Concat(propertyInfos).ToArray();
Arguments.Column = new TextLoaderColumn[memberInfos.Length];
for (int index = 0; index < memberInfos.Length; index++)
{
var memberInfo = memberInfos[index];
var mappingAttr = memberInfo.GetCustomAttribute <ColumnAttribute>();
if (mappingAttr == null)
{
throw Contracts.Except($"Field or property {memberInfo.Name} is missing ColumnAttribute");
}
if (Regex.Match(mappingAttr.Ordinal, @"[^(0-9,\*\-~)]+").Success)
{
throw Contracts.Except($"{mappingAttr.Ordinal} contains invalid characters. " +
$"Valid characters are 0-9, *, - and ~");
}
var mappingNameAttr = memberInfo.GetCustomAttribute <ColumnNameAttribute>();
var name = mappingAttr.Name ?? mappingNameAttr?.Name ?? memberInfo.Name;
Runtime.Data.TextLoader.Range[] sources;
if (!Runtime.Data.TextLoader.Column.TryParseSourceEx(mappingAttr.Ordinal, out sources))
{
throw Contracts.Except($"{mappingAttr.Ordinal} could not be parsed.");
}
Contracts.Assert(sources != null);
TextLoaderColumn tlc = new TextLoaderColumn();
tlc.Name = name;
tlc.Source = new TextLoaderRange[sources.Length];
DataKind dk;
switch (memberInfo)
{
case FieldInfo field:
if (!TryGetDataKind(field.FieldType.IsArray ? field.FieldType.GetElementType() : field.FieldType, out dk))
{
throw Contracts.Except($"Field {name} is of unsupported type.");
}
break;
case PropertyInfo property:
if (!TryGetDataKind(property.PropertyType.IsArray ? property.PropertyType.GetElementType() : property.PropertyType, out dk))
{
throw Contracts.Except($"Property {name} is of unsupported type.");
}
break;
default:
Contracts.Assert(false);
throw Contracts.ExceptNotSupp("Expected a FieldInfo or a PropertyInfo");
}
tlc.Type = dk;
for (int indexLocal = 0; indexLocal < tlc.Source.Length; indexLocal++)
{
tlc.Source[indexLocal] = new TextLoaderRange
{
AllOther = sources[indexLocal].AllOther,
AutoEnd = sources[indexLocal].AutoEnd,
ForceVector = sources[indexLocal].ForceVector,
VariableEnd = sources[indexLocal].VariableEnd,
Max = sources[indexLocal].Max,
Min = sources[indexLocal].Min
};
}
Arguments.Column[index] = tlc;
}
Arguments.HasHeader = useHeader;
Arguments.Separator = new[] { separator };
Arguments.AllowQuoting = allowQuotedStrings;
Arguments.AllowSparse = supportSparse;
Arguments.TrimWhitespace = trimWhitespace;
return(this);
}
