FileDocCategorySizeDatePackage
FieldsReader.javaAPI DocApache Lucene 1.95188Mon Feb 20 09:20:14 GMT 2006org.apache.lucene.index

FieldsReader

public final class FieldsReader extends Object
Class responsible for access to stored document fields. It uses <segment>.fdt and <segment>.fdx; files.
version
$Id: FieldsReader.java 329524 2005-10-30 05:38:46Z yonik $

Fields Summary
private FieldInfos
fieldInfos
private IndexInput
fieldsStream
private IndexInput
indexStream
private int
size
Constructors Summary
FieldsReader(Directory d, String segment, FieldInfos fn)

    fieldInfos = fn;

    fieldsStream = d.openInput(segment + ".fdt");
    indexStream = d.openInput(segment + ".fdx");

    size = (int)(indexStream.length() / 8);
Methods Summary
final voidclose()

    fieldsStream.close();
    indexStream.close();
final org.apache.lucene.document.Documentdoc(int n)

    indexStream.seek(n * 8L);
    long position = indexStream.readLong();
    fieldsStream.seek(position);

    Document doc = new Document();
    int numFields = fieldsStream.readVInt();
    for (int i = 0; i < numFields; i++) {
      int fieldNumber = fieldsStream.readVInt();
      FieldInfo fi = fieldInfos.fieldInfo(fieldNumber);

      byte bits = fieldsStream.readByte();
      
      boolean compressed = (bits & FieldsWriter.FIELD_IS_COMPRESSED) != 0;
      boolean tokenize = (bits & FieldsWriter.FIELD_IS_TOKENIZED) != 0;
      
      if ((bits & FieldsWriter.FIELD_IS_BINARY) != 0) {
        final byte[] b = new byte[fieldsStream.readVInt()];
        fieldsStream.readBytes(b, 0, b.length);
        if (compressed)
          doc.add(new Field(fi.name, uncompress(b), Field.Store.COMPRESS));
        else
          doc.add(new Field(fi.name, b, Field.Store.YES));
      }
      else {
        Field.Index index;
        Field.Store store = Field.Store.YES;
        
        if (fi.isIndexed && tokenize)
          index = Field.Index.TOKENIZED;
        else if (fi.isIndexed && !tokenize)
          index = Field.Index.UN_TOKENIZED;
        else
          index = Field.Index.NO;
        
        Field.TermVector termVector = null;
        if (fi.storeTermVector) {
          if (fi.storeOffsetWithTermVector) {
            if (fi.storePositionWithTermVector) {
              termVector = Field.TermVector.WITH_POSITIONS_OFFSETS;
            }
            else {
              termVector = Field.TermVector.WITH_OFFSETS;
            }
          }
          else if (fi.storePositionWithTermVector) {
            termVector = Field.TermVector.WITH_POSITIONS;
          }
          else {
            termVector = Field.TermVector.YES;
          }
        }
        else {
          termVector = Field.TermVector.NO;
        }
        
        if (compressed) {
          store = Field.Store.COMPRESS;
          final byte[] b = new byte[fieldsStream.readVInt()];
          fieldsStream.readBytes(b, 0, b.length);
          Field f = new Field(fi.name,      // field name
              new String(uncompress(b), "UTF-8"), // uncompress the value and add as string
              store,
              index,
              termVector);
          f.setOmitNorms(fi.omitNorms);
          doc.add(f);
        }
        else {
          Field f = new Field(fi.name,     // name
                fieldsStream.readString(), // read value
                store,
                index,
                termVector);
          f.setOmitNorms(fi.omitNorms);
          doc.add(f);
        }
      }
    }

    return doc;
final intsize()

    return size;
private final byte[]uncompress(byte[] input)

  
    Inflater decompressor = new Inflater();
    decompressor.setInput(input);
  
    // Create an expandable byte array to hold the decompressed data
    ByteArrayOutputStream bos = new ByteArrayOutputStream(input.length);
  
    // Decompress the data
    byte[] buf = new byte[1024];
    while (!decompressor.finished()) {
      try {
        int count = decompressor.inflate(buf);
        bos.write(buf, 0, count);
      }
      catch (DataFormatException e) {
        // this will happen if the field is not compressed
        throw new IOException ("field data are in wrong format: " + e.toString());
      }
    }
  
    decompressor.end();
    
    // Get the decompressed data
    return bos.toByteArray();