internal void AddDocument(Document doc)
{
indexStream.WriteLong(fieldsStream.GetFilePointer());
int storedCount = 0;
System.Collections.IEnumerator fieldIterator = doc.GetFields().GetEnumerator();
while (fieldIterator.MoveNext())
{
Fieldable field = (Fieldable)fieldIterator.Current;
if (field.IsStored())
{
storedCount++;
}
}
fieldsStream.WriteVInt(storedCount);
fieldIterator = doc.GetFields().GetEnumerator();
while (fieldIterator.MoveNext())
{
Fieldable field = (Fieldable)fieldIterator.Current;
// if the field as an instanceof FieldsReader.FieldForMerge, we're in merge mode
// and field.binaryValue() already returns the compressed value for a field
// with isCompressed()==true, so we disable compression in that case
bool disableCompression = (field is FieldsReader.FieldForMerge);
if (field.IsStored())
{
fieldsStream.WriteVInt(fieldInfos.FieldNumber(field.Name()));
byte bits = 0;
if (field.IsTokenized())
{
bits |= FieldsWriter.FIELD_IS_TOKENIZED;
}
if (field.IsBinary())
{
bits |= FieldsWriter.FIELD_IS_BINARY;
}
if (field.IsCompressed())
{
bits |= FieldsWriter.FIELD_IS_COMPRESSED;
}
fieldsStream.WriteByte(bits);
if (field.IsCompressed())
{
// compression is enabled for the current field
byte[] data = null;
if (disableCompression)
{
// optimized case for merging, the data
// is already compressed
data = field.BinaryValue();
}
else
{
// check if it is a binary field
if (field.IsBinary())
{
data = Compress(field.BinaryValue());
}
else
{
data = Compress(System.Text.Encoding.GetEncoding("UTF-8").GetBytes(field.StringValue()));
}
}
int len = data.Length;
fieldsStream.WriteVInt(len);
fieldsStream.WriteBytes(data, len);
}
else
{
// compression is disabled for the current field
if (field.IsBinary())
{
byte[] data = field.BinaryValue();
int len = data.Length;
fieldsStream.WriteVInt(len);
fieldsStream.WriteBytes(data, len);
}
else
{
fieldsStream.WriteString(field.StringValue());
}
}
}
}
}
public override void ProcessFields(Fieldable[] fields, int count)
{
fieldState.Reset(docState.doc.GetBoost());
int maxFieldLength = docState.maxFieldLength;
bool doInvert = consumer.Start(fields, count);
for (int i = 0; i < count; i++)
{
Fieldable field = fields[i];
// TODO FI: this should be "genericized" to querying
// consumer if it wants to see this particular field
// tokenized.
if (field.IsIndexed() && doInvert)
{
bool anyToken;
if (fieldState.length > 0)
{
fieldState.position += docState.analyzer.GetPositionIncrementGap(fieldInfo.name);
}
if (!field.IsTokenized())
{
// un-tokenized field
System.String stringValue = field.StringValue();
int valueLength = stringValue.Length;
perThread.singleTokenTokenStream.Reinit(stringValue, 0, valueLength);
fieldState.attributeSource = perThread.singleTokenTokenStream;
consumer.Start(field);
bool success = false;
try
{
consumer.Add();
success = true;
}
finally
{
if (!success)
{
docState.docWriter.SetAborting();
}
}
fieldState.offset += valueLength;
fieldState.length++;
fieldState.position++;
anyToken = valueLength > 0;
}
else
{
// tokenized field
TokenStream stream;
TokenStream streamValue = field.TokenStreamValue();
if (streamValue != null)
{
stream = streamValue;
}
else
{
// the field does not have a TokenStream,
// so we have to obtain one from the analyzer
System.IO.TextReader reader; // find or make Reader
System.IO.TextReader readerValue = field.ReaderValue();
if (readerValue != null)
{
reader = readerValue;
}
else
{
System.String stringValue = field.StringValue();
if (stringValue == null)
{
throw new System.ArgumentException("field must have either TokenStream, String or Reader value");
}
perThread.stringReader.Init(stringValue);
reader = perThread.stringReader;
}
// Tokenize field and add to postingTable
stream = docState.analyzer.ReusableTokenStream(fieldInfo.name, reader);
}
// reset the TokenStream to the first token
stream.Reset();
int startLength = fieldState.length;
// deprecated
bool allowMinus1Position = docState.allowMinus1Position;
try
{
int offsetEnd = fieldState.offset - 1;
bool hasMoreTokens = stream.IncrementToken();
fieldState.attributeSource = stream;
OffsetAttribute offsetAttribute = (OffsetAttribute)fieldState.attributeSource.AddAttribute(typeof(OffsetAttribute));
PositionIncrementAttribute posIncrAttribute = (PositionIncrementAttribute)fieldState.attributeSource.AddAttribute(typeof(PositionIncrementAttribute));
consumer.Start(field);
for (; ;)
{
// If we hit an exception in stream.next below
// (which is fairly common, eg if analyzer
// chokes on a given document), then it's
// non-aborting and (above) this one document
// will be marked as deleted, but still
// consume a docID
if (!hasMoreTokens)
{
break;
}
int posIncr = posIncrAttribute.GetPositionIncrement();
fieldState.position += posIncr;
if (allowMinus1Position || fieldState.position > 0)
{
fieldState.position--;
}
if (posIncr == 0)
{
fieldState.numOverlap++;
}
bool success = false;
try
{
// If we hit an exception in here, we abort
// all buffered documents since the last
// flush, on the likelihood that the
// internal state of the consumer is now
// corrupt and should not be flushed to a
// new segment:
consumer.Add();
success = true;
}
finally
{
if (!success)
{
docState.docWriter.SetAborting();
}
}
fieldState.position++;
offsetEnd = fieldState.offset + offsetAttribute.EndOffset();
if (++fieldState.length >= maxFieldLength)
{
if (docState.infoStream != null)
{
docState.infoStream.WriteLine("maxFieldLength " + maxFieldLength + " reached for field " + fieldInfo.name + ", ignoring following tokens");
}
break;
}
hasMoreTokens = stream.IncrementToken();
}
// trigger streams to perform end-of-stream operations
stream.End();
fieldState.offset += offsetAttribute.EndOffset();
anyToken = fieldState.length > startLength;
}
finally
{
stream.Close();
}
}
if (anyToken)
{
fieldState.offset += docState.analyzer.GetOffsetGap(field);
}
fieldState.boost *= field.GetBoost();
}
// LUCENE-2387: don't hang onto the field, so GC can
// reclaim
fields[i] = null;
}
consumer.Finish();
endConsumer.Finish();
}
internal void WriteField(FieldInfo fi, Fieldable field)
{
// if the field as an instanceof FieldsReader.FieldForMerge, we're in merge mode
// and field.binaryValue() already returns the compressed value for a field
// with isCompressed()==true, so we disable compression in that case
bool disableCompression = (field is FieldsReader.FieldForMerge);
fieldsStream.WriteVInt(fi.number);
byte bits = 0;
if (field.IsTokenized())
{
bits |= FieldsWriter.FIELD_IS_TOKENIZED;
}
if (field.IsBinary())
{
bits |= FieldsWriter.FIELD_IS_BINARY;
}
if (field.IsCompressed())
{
bits |= FieldsWriter.FIELD_IS_COMPRESSED;
}
fieldsStream.WriteByte(bits);
if (field.IsCompressed())
{
// compression is enabled for the current field
byte[] data = null;
if (disableCompression)
{
// optimized case for merging, the data
// is already compressed
data = field.BinaryValue();
}
else
{
// check if it is a binary field
if (field.IsBinary())
{
data = Compress(field.BinaryValue());
}
else
{
data = Compress(System.Text.Encoding.GetEncoding("UTF-8").GetBytes(field.StringValue()));
}
}
int len = data.Length;
fieldsStream.WriteVInt(len);
fieldsStream.WriteBytes(data, len);
}
else
{
// compression is disabled for the current field
if (field.IsBinary())
{
byte[] data = field.BinaryValue();
int len = data.Length;
fieldsStream.WriteVInt(len);
fieldsStream.WriteBytes(data, len);
}
else
{
fieldsStream.WriteString(field.StringValue());
}
}
}
internal void WriteField(FieldInfo fi, Fieldable field)
{
// if the field as an instanceof FieldsReader.FieldForMerge, we're in merge mode
// and field.binaryValue() already returns the compressed value for a field
// with isCompressed()==true, so we disable compression in that case
bool disableCompression = (field is FieldsReader.FieldForMerge);
fieldsStream.WriteVInt(fi.number);
byte bits = 0;
if (field.IsTokenized())
bits |= FieldsWriter.FIELD_IS_TOKENIZED;
if (field.IsBinary())
bits |= FieldsWriter.FIELD_IS_BINARY;
if (field.IsCompressed())
bits |= FieldsWriter.FIELD_IS_COMPRESSED;
fieldsStream.WriteByte(bits);
if (field.IsCompressed())
{
// compression is enabled for the current field
byte[] data;
int len;
int offset;
if (disableCompression)
{
// optimized case for merging, the data
// is already compressed
data = field.GetBinaryValue();
System.Diagnostics.Debug.Assert(data != null);
len = field.GetBinaryLength();
offset = field.GetBinaryOffset();
}
else
{
// check if it is a binary field
if (field.IsBinary())
{
data = CompressionTools.Compress(field.GetBinaryValue(), field.GetBinaryOffset(), field.GetBinaryLength());
}
else
{
byte[] x = System.Text.Encoding.GetEncoding("UTF-8").GetBytes(field.StringValue());
data = CompressionTools.Compress(x, 0, x.Length);
}
len = data.Length;
offset = 0;
}
fieldsStream.WriteVInt(len);
fieldsStream.WriteBytes(data, offset, len);
}
else
{
// compression is disabled for the current field
if (field.IsBinary())
{
byte[] data;
int len;
int offset;
data = field.GetBinaryValue();
len = field.GetBinaryLength();
offset = field.GetBinaryOffset();
fieldsStream.WriteVInt(len);
fieldsStream.WriteBytes(data, offset, len);
}
else
{
fieldsStream.WriteString(field.StringValue());
}
}
}
/* Invert one occurrence of one field in the document */
public void InvertField(Fieldable field, Analyzer analyzer, int maxFieldLength)
{
if (length > 0)
position += analyzer.GetPositionIncrementGap(fieldInfo.name);
if (!field.IsTokenized())
{
// un-tokenized field
System.String stringValue = field.StringValue();
int valueLength = stringValue.Length;
Token token = localToken;
token.Clear();
char[] termBuffer = token.TermBuffer();
if (termBuffer.Length < valueLength)
termBuffer = token.ResizeTermBuffer(valueLength);
DocumentsWriter.GetCharsFromString(stringValue, 0, valueLength, termBuffer, 0);
token.SetTermLength(valueLength);
token.SetStartOffset(offset);
token.SetEndOffset(offset + stringValue.Length);
AddPosition(token);
offset += stringValue.Length;
length++;
}
else
{
// tokenized field
TokenStream stream;
TokenStream streamValue = field.TokenStreamValue();
if (streamValue != null)
stream = streamValue;
else
{
// the field does not have a TokenStream,
// so we have to obtain one from the analyzer
System.IO.TextReader reader; // find or make Reader
System.IO.TextReader readerValue = field.ReaderValue();
if (readerValue != null)
reader = readerValue;
else
{
System.String stringValue = field.StringValue();
if (stringValue == null)
throw new System.ArgumentException("field must have either TokenStream, String or Reader value");
Enclosing_Instance.stringReader.Init(stringValue);
reader = Enclosing_Instance.stringReader;
}
// Tokenize field and add to postingTable
stream = analyzer.ReusableTokenStream(fieldInfo.name, reader);
}
// reset the TokenStream to the first token
stream.Reset();
try
{
offsetEnd = offset - 1;
for (; ; )
{
Token token = stream.Next(localToken);
if (token == null)
break;
position += (token.GetPositionIncrement() - 1);
AddPosition(token);
if (++length >= maxFieldLength)
{
if (Enclosing_Instance.Enclosing_Instance.infoStream != null)
Enclosing_Instance.Enclosing_Instance.infoStream.WriteLine("maxFieldLength " + maxFieldLength + " reached for field " + fieldInfo.name + ", ignoring following tokens");
break;
}
}
offset = offsetEnd + 1;
}
finally
{
stream.Close();
}
}
boost *= field.GetBoost();
}
internal override void processFields(Fieldable[] fields,
int count)
{
fieldState.reset(docState.doc.GetBoost());
int maxFieldLength = docState.maxFieldLength;
bool doInvert = consumer.start(fields, count);
for (int i = 0; i < count; i++)
{
Fieldable field = fields[i];
// TODO FI: this should be "genericized" to querying
// consumer if it wants to see this particular field
// tokenized.
if (field.IsIndexed() && doInvert)
{
if (fieldState.length > 0)
{
fieldState.position += docState.analyzer.GetPositionIncrementGap(fieldInfo.name);
}
if (!field.IsTokenized())
{ // un-tokenized field
string stringValue = field.StringValue();
int valueLength = stringValue.Length;
Token token = perThread.localToken.Reinit(stringValue, fieldState.offset, fieldState.offset + valueLength);
bool success = false;
try
{
consumer.add(token);
success = true;
}
finally
{
if (!success)
{
docState.docWriter.SetAborting();
}
}
fieldState.offset += valueLength;
fieldState.length++;
fieldState.position++;
}
else
{ // tokenized field
TokenStream stream;
TokenStream streamValue = field.TokenStreamValue();
if (streamValue != null)
{
stream = streamValue;
}
else
{
// the field does not have a TokenStream,
// so we have to obtain one from the analyzer
System.IO.TextReader reader; // find or make Reader
System.IO.TextReader readerValue = field.ReaderValue();
if (readerValue != null)
{
reader = readerValue;
}
else
{
string stringValue = field.StringValue();
if (stringValue == null)
{
throw new System.ArgumentException("field must have either TokenStream, string or Reader value");
}
perThread.stringReader.Init(stringValue);
reader = perThread.stringReader;
}
// Tokenize field and add to postingTable
stream = docState.analyzer.ReusableTokenStream(fieldInfo.name, reader);
}
// reset the TokenStream to the first token
stream.Reset();
try
{
int offsetEnd = fieldState.offset - 1;
Token localToken = perThread.localToken;
for (; ;)
{
// If we hit an exception in stream.next below
// (which is fairly common, eg if analyzer
// chokes on a given document), then it's
// non-aborting and (above) this one document
// will be marked as deleted, but still
// consume a docID
Token token = stream.Next(localToken);
if (token == null)
{
break;
}
fieldState.position += (token.GetPositionIncrement() - 1);
bool success = false;
try
{
// If we hit an exception in here, we abort
// all buffered documents since the last
// flush, on the likelihood that the
// internal state of the consumer is now
// corrupt and should not be flushed to a
// new segment:
consumer.add(token);
success = true;
}
finally
{
if (!success)
{
docState.docWriter.SetAborting();
}
}
fieldState.position++;
offsetEnd = fieldState.offset + token.EndOffset();
if (++fieldState.length >= maxFieldLength)
{
if (docState.infoStream != null)
{
docState.infoStream.WriteLine("maxFieldLength " + maxFieldLength + " reached for field " + fieldInfo.name + ", ignoring following tokens");
}
break;
}
}
fieldState.offset = offsetEnd + 1;
}
finally
{
stream.Close();
}
}
fieldState.boost *= field.GetBoost();
}
}
consumer.finish();
endConsumer.finish();
}
internal void WriteField(FieldInfo fi, Fieldable field)
{
// if the field as an instanceof FieldsReader.FieldForMerge, we're in merge mode
// and field.binaryValue() already returns the compressed value for a field
// with isCompressed()==true, so we disable compression in that case
bool disableCompression = (field is FieldsReader.FieldForMerge);
fieldsStream.WriteVInt(fi.number);
byte bits = 0;
if (field.IsTokenized())
{
bits |= FieldsWriter.FIELD_IS_TOKENIZED;
}
if (field.IsBinary())
{
bits |= FieldsWriter.FIELD_IS_BINARY;
}
if (field.IsCompressed())
{
bits |= FieldsWriter.FIELD_IS_COMPRESSED;
}
fieldsStream.WriteByte(bits);
if (field.IsCompressed())
{
// compression is enabled for the current field
byte[] data;
int len;
int offset;
if (disableCompression)
{
// optimized case for merging, the data
// is already compressed
data = field.GetBinaryValue();
System.Diagnostics.Debug.Assert(data != null);
len = field.GetBinaryLength();
offset = field.GetBinaryOffset();
}
else
{
// check if it is a binary field
if (field.IsBinary())
{
data = Compress(field.GetBinaryValue(), field.GetBinaryOffset(), field.GetBinaryLength());
}
else
{
byte[] x = System.Text.Encoding.UTF8.GetBytes(field.StringValue());
data = Compress(x, 0, x.Length);
}
len = data.Length;
offset = 0;
}
fieldsStream.WriteVInt(len);
fieldsStream.WriteBytes(data, offset, len);
}
else
{
// compression is disabled for the current field
if (field.IsBinary())
{
int length = field.GetBinaryLength();
fieldsStream.WriteVInt(length);
fieldsStream.WriteBytes(field.BinaryValue(), field.GetBinaryOffset(), length);
}
else
{
fieldsStream.WriteString(field.StringValue());
}
}
}
// Tokenizes the fields of a document into Postings.
private void InvertDocument(Document doc)
{
System.Collections.IEnumerator fieldIterator = doc.GetFields().GetEnumerator();
while (fieldIterator.MoveNext())
{
Fieldable field = (Fieldable)fieldIterator.Current;
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 (length > 0)
{
position += analyzer.GetPositionIncrementGap(fieldName);
}
int offset = fieldOffsets[fieldNumber]; // offset field
if (field.IsIndexed())
{
if (!field.IsTokenized())
{
// un-tokenized field
System.String stringValue = field.StringValue();
if (field.IsStoreOffsetWithTermVector())
{
AddPosition(fieldName, stringValue, position++, new TermVectorOffsetInfo(offset, offset + stringValue.Length));
}
else
{
AddPosition(fieldName, stringValue, position++, null);
}
offset += stringValue.Length;
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
{
Token lastToken = null;
for (Token t = stream.Next(); t != null; t = stream.Next())
{
position += (t.GetPositionIncrement() - 1);
if (field.IsStoreOffsetWithTermVector())
{
AddPosition(fieldName, t.TermText(), position++, new TermVectorOffsetInfo(offset + t.StartOffset(), offset + t.EndOffset()));
}
else
{
AddPosition(fieldName, t.TermText(), position++, null);
}
lastToken = t;
if (++length >= maxFieldLength)
{
if (infoStream != null)
{
infoStream.WriteLine("maxFieldLength " + maxFieldLength + " reached, ignoring following tokens");
}
break;
}
}
if (lastToken != null)
{
offset += lastToken.EndOffset() + 1;
}
}
finally
{
stream.Close();
}
}
fieldLengths[fieldNumber] = length; // save field length
fieldPositions[fieldNumber] = position; // save field position
fieldBoosts[fieldNumber] *= field.GetBoost();
fieldOffsets[fieldNumber] = offset;
}
}
}