internal void AddDocument(Document doc)
{
indexStream.WriteLong(fieldsStream.GetFilePointer());
int storedCount = 0;
foreach (Field field in doc.Fields())
{
if (field.IsStored())
{
storedCount++;
}
}
fieldsStream.WriteVInt(storedCount);
foreach (Field field in doc.Fields())
{
if (field.IsStored())
{
fieldsStream.WriteVInt(fieldInfos.FieldNumber(field.Name()));
byte bits = 0;
if (field.IsTokenized())
{
bits |= 1;
}
fieldsStream.WriteByte(bits);
fieldsStream.WriteString(field.StringValue());
}
}
}
internal void AddDocument(Document doc)
{
indexStream.WriteLong(fieldsStream.GetFilePointer());
int storedCount = 0;
foreach (Field field in doc.Fields())
{
if (field.IsStored())
storedCount++;
}
fieldsStream.WriteVInt(storedCount);
foreach (Field field in doc.Fields())
{
if (field.IsStored())
{
fieldsStream.WriteVInt(fieldInfos.FieldNumber(field.Name()));
byte bits = 0;
if (field.IsTokenized())
bits |= 1;
fieldsStream.WriteByte(bits);
fieldsStream.WriteString(field.StringValue());
}
}
}
/// <summary>Adds Field info for a Document. </summary>
public void Add(Document doc)
{
foreach (Field field in doc.Fields())
{
Add(field.Name(), field.IsIndexed(), field.IsTermVectorStored());
}
}
// Tokenizes the fields of a document into Postings.
private void InvertDocument(Document doc)
{
foreach (Field field in doc.Fields())
{
System.String fieldName = field.Name();
int fieldNumber = fieldInfos.FieldNumber(fieldName);
int length = fieldLengths[fieldNumber]; // length of Field
int position = fieldPositions[fieldNumber]; // position in Field
if (field.IsIndexed())
{
if (!field.IsTokenized())
{
// un-tokenized Field
AddPosition(fieldName, field.StringValue(), position++);
length++;
}
else
{
System.IO.TextReader reader; // find or make Reader
if (field.ReaderValue() != null)
{
reader = field.ReaderValue();
}
else if (field.StringValue() != null)
{
reader = new System.IO.StringReader(field.StringValue());
}
else
{
throw new System.ArgumentException("Field must have either String or Reader value");
}
// Tokenize Field and add to postingTable
TokenStream stream = analyzer.TokenStream(fieldName, reader);
try
{
for (Token t = stream.Next(); t != null; t = stream.Next())
{
position += (t.GetPositionIncrement() - 1);
AddPosition(fieldName, t.TermText(), position++);
if (++length > maxFieldLength)
{
break;
}
}
}
finally
{
stream.Close();
}
}
fieldLengths[fieldNumber] = length; // save Field length
fieldPositions[fieldNumber] = position; // save Field position
fieldBoosts[fieldNumber] *= field.GetBoost();
}
}
}
/// <summary>Adds Field info for a Document. </summary>
public void Add(Document doc)
{
foreach (Field field in doc.Fields())
{
Add(field.Name(), field.IsIndexed(), field.IsTermVectorStored());
}
}
// Tokenizes the fields of a document into Postings.
private void InvertDocument(Document doc)
{
foreach(Field field in doc.Fields())
{
System.String fieldName = field.Name();
int fieldNumber = fieldInfos.FieldNumber(fieldName);
int length = fieldLengths[fieldNumber]; // length of Field
int position = fieldPositions[fieldNumber]; // position in Field
if (field.IsIndexed())
{
if (!field.IsTokenized())
{
// un-tokenized Field
AddPosition(fieldName, field.StringValue(), position++);
length++;
}
else
{
System.IO.TextReader reader; // find or make Reader
if (field.ReaderValue() != null)
reader = field.ReaderValue();
else if (field.StringValue() != null)
reader = new System.IO.StringReader(field.StringValue());
else
throw new System.ArgumentException("Field must have either String or Reader value");
// Tokenize Field and add to postingTable
TokenStream stream = analyzer.TokenStream(fieldName, reader);
try
{
for (Token t = stream.Next(); t != null; t = stream.Next())
{
position += (t.GetPositionIncrement() - 1);
AddPosition(fieldName, t.TermText(), position++);
if (++length > maxFieldLength)
break;
}
}
finally
{
stream.Close();
}
}
fieldLengths[fieldNumber] = length; // save Field length
fieldPositions[fieldNumber] = position; // save Field position
fieldBoosts[fieldNumber] *= field.GetBoost();
}
}
}
