public /*internal*/ FieldsReader(Directory d, System.String segment, FieldInfos fn)
{
fieldInfos = fn;
fieldsStream = d.OpenFile(segment + ".fdt");
indexStream = d.OpenFile(segment + ".fdx");
size = (int) (indexStream.Length() / 8);
}
private void Initialize(Directory directory, System.String segment, FieldInfos fis, bool isi)
{
fieldInfos = fis;
isIndex = isi;
output = directory.CreateFile(segment + (isIndex?".tii":".tis"));
output.WriteInt(FORMAT); // write format
output.WriteLong(0); // leave space for size
output.WriteInt(indexInterval); // write indexInterval
output.WriteInt(skipInterval); // write skipInterval
}
public /*internal*/ TermInfosReader(Directory dir, System.String seg, FieldInfos fis)
{
directory = dir;
segment = seg;
fieldInfos = fis;
origEnum = new SegmentTermEnum(directory.OpenFile(segment + ".tis"), fieldInfos, false);
size = origEnum.size;
ReadIndex();
}
/*internal*/ public void AddDocument(System.String segment, Document doc)
{
// write Field names
fieldInfos = new FieldInfos();
fieldInfos.Add(doc);
fieldInfos.Write(directory, segment + ".fnm");
// write Field values
FieldsWriter fieldsWriter = new FieldsWriter(directory, segment, fieldInfos);
try
{
fieldsWriter.AddDocument(doc);
}
finally
{
fieldsWriter.Close();
}
// invert doc into postingTable
postingTable.Clear(); // clear postingTable
fieldLengths = new int[fieldInfos.Size()]; // init fieldLengths
fieldPositions = new int[fieldInfos.Size()]; // init fieldPositions
fieldBoosts = new float[fieldInfos.Size()]; // init fieldBoosts
float boost = doc.GetBoost();
for (int i = 0; i < fieldBoosts.Length; i++)
{
fieldBoosts[i] = boost;
}
InvertDocument(doc);
// sort postingTable into an array
Posting[] postings = SortPostingTable();
/*
for (int i = 0; i < postings.length; i++) {
Posting posting = postings[i];
System.out.print(posting.term);
System.out.print(" freq=" + posting.freq);
System.out.print(" pos=");
System.out.print(posting.positions[0]);
for (int j = 1; j < posting.freq; j++)
System.out.print("," + posting.positions[j]);
System.out.println("");
}
*/
// write postings
WritePostings(postings, segment);
// write norms of indexed fields
WriteNorms(doc, segment);
}
/// <summary>Create term vectors writer for the specified segment in specified
/// directory. A new TermVectorsWriter should be created for each
/// segment. The parameter <code>maxFields</code> indicates how many total
/// fields are found in this document. Not all of these fields may require
/// termvectors to be stored, so the number of calls to
/// <code>openField</code> is less or equal to this number.
/// </summary>
public TermVectorsWriter(Directory directory, System.String segment, FieldInfos fieldInfos)
{
// Open files for TermVector storage
tvx = directory.CreateFile(segment + TVX_EXTENSION);
tvx.WriteInt(FORMAT_VERSION);
tvd = directory.CreateFile(segment + TVD_EXTENSION);
tvd.WriteInt(FORMAT_VERSION);
tvf = directory.CreateFile(segment + TVF_EXTENSION);
tvf.WriteInt(FORMAT_VERSION);
this.fieldInfos = fieldInfos;
fields = System.Collections.ArrayList.Synchronized(new System.Collections.ArrayList(fieldInfos.Size()));
terms = System.Collections.ArrayList.Synchronized(new System.Collections.ArrayList(10));
}
public /*internal*/ TermVectorsReader(Directory d, System.String segment, FieldInfos fieldInfos)
{
if (d.FileExists(segment + TermVectorsWriter.TVX_EXTENSION))
{
tvx = d.OpenFile(segment + TermVectorsWriter.TVX_EXTENSION);
CheckValidFormat(tvx);
tvd = d.OpenFile(segment + TermVectorsWriter.TVD_EXTENSION);
CheckValidFormat(tvd);
tvf = d.OpenFile(segment + TermVectorsWriter.TVF_EXTENSION);
CheckValidFormat(tvf);
size = (int) tvx.Length() / 8;
}
this.fieldInfos = fieldInfos;
}
internal SegmentTermEnum(InputStream i, FieldInfos fis, bool isi)
{
input = i;
fieldInfos = fis;
isIndex = isi;
int firstInt = input.ReadInt();
if (firstInt >= 0)
{
// original-format file, without explicit format version number
format = 0;
size = firstInt;
// back-compatible settings
indexInterval = 128;
skipInterval = System.Int32.MaxValue; // switch off skipTo optimization
}
else
{
// we have a format version number
format = firstInt;
// check that it is a format we can understand
if (format < TermInfosWriter.FORMAT)
throw new System.IO.IOException("Unknown format version:" + format);
size = input.ReadLong(); // read the size
if (format == - 1)
{
if (!isIndex)
{
indexInterval = input.ReadInt();
formatM1SkipInterval = input.ReadInt();
}
// switch off skipTo optimization for file format prior to 1.4rc2 in order to avoid a bug in
// skipTo implementation of these versions
skipInterval = System.Int32.MaxValue;
}
else
{
indexInterval = input.ReadInt();
skipInterval = input.ReadInt();
}
}
}
private void Initialize(SegmentInfo si)
{
segment = si.name;
// Use compound file directory for some files, if it exists
Directory cfsDir = Directory();
if (Directory().FileExists(segment + ".cfs"))
{
cfsReader = new CompoundFileReader(Directory(), segment + ".cfs");
cfsDir = cfsReader;
}
// No compound file exists - use the multi-file format
fieldInfos = new FieldInfos(cfsDir, segment + ".fnm");
fieldsReader = new FieldsReader(cfsDir, segment, fieldInfos);
tis = new TermInfosReader(cfsDir, segment, fieldInfos);
// NOTE: the bitvector is stored using the regular directory, not cfs
if (HasDeletions(si))
deletedDocs = new BitVector(Directory(), segment + ".del");
// make sure that all index files have been read or are kept open
// so that if an index update removes them we'll still have them
freqStream = cfsDir.OpenFile(segment + ".frq");
proxStream = cfsDir.OpenFile(segment + ".prx");
OpenNorms(cfsDir);
if (fieldInfos.HasVectors())
{
// open term vector files only as needed
termVectorsReader = new TermVectorsReader(cfsDir, segment, fieldInfos);
}
}
private TermInfosWriter(Directory directory, System.String segment, FieldInfos fis, bool isIndex)
{
Initialize(directory, segment, fis, isIndex);
}
public /*internal*/ TermInfosWriter(Directory directory, System.String segment, FieldInfos fis)
{
Initialize(directory, segment, fis, false);
other = new TermInfosWriter(directory, segment, fis, true);
other.other = this;
}
/// <summary> </summary>
/// <returns> The number of documents in all of the readers
/// </returns>
/// <throws> IOException </throws>
private int MergeFields()
{
fieldInfos = new FieldInfos(); // merge Field names
int docCount = 0;
for (int i = 0; i < readers.Count; i++)
{
Monodoc.Lucene.Net.Index.IndexReader reader = (Monodoc.Lucene.Net.Index.IndexReader) readers[i];
fieldInfos.AddIndexed(reader.GetIndexedFieldNames(true), true);
fieldInfos.AddIndexed(reader.GetIndexedFieldNames(false), false);
fieldInfos.Add(reader.GetFieldNames(false), false);
}
fieldInfos.Write(directory, segment + ".fnm");
FieldsWriter fieldsWriter = new FieldsWriter(directory, segment, fieldInfos);
try
{
for (int i = 0; i < readers.Count; i++)
{
Monodoc.Lucene.Net.Index.IndexReader reader = (Monodoc.Lucene.Net.Index.IndexReader) readers[i];
int maxDoc = reader.MaxDoc();
for (int j = 0; j < maxDoc; j++)
if (!reader.IsDeleted(j))
{
// skip deleted docs
fieldsWriter.AddDocument(reader.Document(j));
docCount++;
}
}
}
finally
{
fieldsWriter.Close();
}
return docCount;
}
internal FieldsWriter(Directory d, System.String segment, FieldInfos fn)
{
fieldInfos = fn;
fieldsStream = d.CreateFile(segment + ".fdt");
indexStream = d.CreateFile(segment + ".fdx");
}
