internal override void Seek(TermInfo ti)
{
base.Seek(ti);
if (ti != null)
proxStream.Seek(ti.proxPointer);
proxCount = 0;
}
internal void Set(TermInfo ti)
{
docFreq = ti.docFreq;
freqPointer = ti.freqPointer;
proxPointer = ti.proxPointer;
skipOffset = ti.skipOffset;
}
internal override void Seek(TermInfo ti)
{
base.Seek(ti);
if (ti != null)
lazySkipPointer = ti.proxPointer;
lazySkipDocCount = 0;
proxCount = 0;
}
internal override void Seek(TermInfo ti, Term term)
{
base.Seek(ti, term);
if (ti != null)
lazySkipPointer = ti.proxPointer;
lazySkipProxCount = 0;
proxCount = 0;
payloadLength = 0;
needToLoadPayload = false;
}
internal override void Seek(TermInfo ti, Term term)
{
base.Seek(ti, term);
if (ti != null)
{
lazySkipPointer = ti.proxPointer;
}
lazySkipProxCount = 0;
proxCount = 0;
payloadLength = 0;
needToLoadPayload = false;
}
public override int DocFreq(Term t)
{
TermInfo ti = tis.Get(t);
if (ti != null)
{
return(ti.docFreq);
}
else
{
return(0);
}
}
internal override void Seek(TermInfo ti, Term term, IState state)
{
base.Seek(ti, term, state);
if (ti.IsEmpty == false)
{
lazySkipPointer = ti.proxPointer;
}
lazySkipProxCount = 0;
proxCount = 0;
payloadLength = 0;
needToLoadPayload = false;
}
internal void Add(Term term, TermInfo ti)
{
int length = term.text.Length;
if (termTextBuffer.Length < length)
{
termTextBuffer = new char[(int)(length * 1.25)];
}
int i = 0;
System.Collections.Generic.IEnumerator <char> chars = term.text.GetEnumerator();
while (chars.MoveNext())
{
termTextBuffer[i++] = (char)chars.Current;
}
Add(fieldInfos.FieldNumber(term.field), termTextBuffer, 0, length, ti);
}
internal virtual void Seek(TermInfo ti)
{
count = 0;
if (ti == null)
{
df = 0;
}
else
{
df = ti.docFreq;
doc = 0;
skipDoc = 0;
skipCount = 0;
numSkips = df / skipInterval;
freqPointer = ti.freqPointer;
proxPointer = ti.proxPointer;
skipPointer = freqPointer + ti.skipOffset;
freqStream.Seek(freqPointer);
haveSkipped = false;
}
}
internal virtual void Seek(TermInfo ti, Term term)
{
count = 0;
FieldInfo fi = parent.fieldInfos.FieldInfo(term.field);
currentFieldStoresPayloads = (fi != null) ? fi.storePayloads : false;
if (ti == null)
{
df = 0;
}
else
{
df = ti.docFreq;
doc = 0;
freqBasePointer = ti.freqPointer;
proxBasePointer = ti.proxPointer;
skipPointer = freqBasePointer + ti.skipOffset;
freqStream.Seek(freqBasePointer);
haveSkipped = false;
}
}
internal virtual void Seek(TermInfo ti)
{
count = 0;
if (ti == null)
{
df = 0;
}
else
{
df = ti.docFreq;
doc = 0;
skipDoc = 0;
skipCount = 0;
numSkips = df / skipInterval;
freqPointer = ti.freqPointer;
proxPointer = ti.proxPointer;
skipPointer = freqPointer + ti.skipOffset;
freqStream.Seek(freqPointer);
haveSkipped = false;
}
}
internal virtual void Seek(TermInfo ti, Term term, IState state)
{
count = 0;
FieldInfo fi = parent.core.fieldInfos.FieldInfo(term.Field);
currentFieldOmitTermFreqAndPositions = (fi != null) && fi.omitTermFreqAndPositions;
currentFieldStoresPayloads = (fi != null) && fi.storePayloads;
if (ti.IsEmpty)
{
df = 0;
}
else
{
df = ti.docFreq;
doc = 0;
freqBasePointer = ti.freqPointer;
proxBasePointer = ti.proxPointer;
skipPointer = freqBasePointer + ti.skipOffset;
freqStream.Seek(freqBasePointer, state);
haveSkipped = false;
}
}
/// <summary>Adds a new <Term, TermInfo> pair to the set.
/// Term must be lexicographically greater than all previous Terms added.
/// TermInfo pointers must be positive and greater than all previous.
/// </summary>
public /*internal*/ void Add(Term term, TermInfo ti)
{
if (!isIndex && term.CompareTo(lastTerm) <= 0)
{
throw new System.IO.IOException("term out of order");
}
if (ti.freqPointer < lastTi.freqPointer)
{
throw new System.IO.IOException("freqPointer out of order");
}
if (ti.proxPointer < lastTi.proxPointer)
{
throw new System.IO.IOException("proxPointer out of order");
}
if (!isIndex && size % indexInterval == 0)
{
other.Add(lastTerm, lastTi); // add an index term
}
WriteTerm(term); // write term
output.WriteVInt(ti.docFreq); // write doc freq
output.WriteVLong(ti.freqPointer - lastTi.freqPointer); // write pointers
output.WriteVLong(ti.proxPointer - lastTi.proxPointer);
if (ti.docFreq >= skipInterval)
{
output.WriteVInt(ti.skipOffset);
}
if (isIndex)
{
output.WriteVLong(other.output.GetFilePointer() - lastIndexPointer);
lastIndexPointer = other.output.GetFilePointer(); // write pointer
}
lastTi.Set(ti);
size++;
}
/// <summary>Adds a new <fieldNumber, termBytes>, TermInfo> pair to the set.
/// Term must be lexicographically greater than all previous Terms added.
/// TermInfo pointers must be positive and greater than all previous.
/// </summary>
internal void Add(int fieldNumber, byte[] termBytes, int termBytesLength, TermInfo ti)
{
System.Diagnostics.Debug.Assert(CompareToLastTerm(fieldNumber, termBytes, termBytesLength) < 0 ||
(isIndex && termBytesLength == 0 && lastTermBytesLength == 0),
"Terms are out of order: field=" + fieldInfos.FieldName(fieldNumber) + " (number " + fieldNumber + ")" +
" lastField=" + fieldInfos.FieldName(lastFieldNumber) + " (number " + lastFieldNumber + ")" +
" text=" + System.Text.Encoding.UTF8.GetString(termBytes, 0, termBytesLength) + " lastText=" + System.Text.Encoding.UTF8.GetString(lastTermBytes, 0, lastTermBytesLength));
System.Diagnostics.Debug.Assert(ti.freqPointer >= lastTi.freqPointer, "freqPointer out of order (" + ti.freqPointer + " < " + lastTi.freqPointer + ")");
System.Diagnostics.Debug.Assert(ti.proxPointer >= lastTi.proxPointer, "proxPointer out of order (" + ti.proxPointer + " < " + lastTi.proxPointer + ")");
if (!isIndex && size % indexInterval == 0)
{
other.Add(lastFieldNumber, lastTermBytes, lastTermBytesLength, lastTi); // add an index term
}
WriteTerm(fieldNumber, termBytes, termBytesLength); // write term
output.WriteVInt(ti.docFreq); // write doc freq
output.WriteVLong(ti.freqPointer - lastTi.freqPointer); // write pointers
output.WriteVLong(ti.proxPointer - lastTi.proxPointer);
if (ti.docFreq >= skipInterval)
{
output.WriteVInt(ti.skipOffset);
}
if (isIndex)
{
output.WriteVLong(other.output.FilePointer - lastIndexPointer);
lastIndexPointer = other.output.FilePointer; // write pointer
}
lastFieldNumber = fieldNumber;
lastTi.Set(ti);
size++;
}
private void WritePostings(Posting[] postings, System.String segment)
{
IndexOutput freq = null, prox = null;
TermInfosWriter tis = null;
TermVectorsWriter termVectorWriter = null;
try
{
//open files for inverse index storage
freq = directory.CreateOutput(segment + ".frq");
prox = directory.CreateOutput(segment + ".prx");
tis = new TermInfosWriter(directory, segment, fieldInfos, termIndexInterval);
TermInfo ti = new TermInfo();
System.String currentField = null;
for (int i = 0; i < postings.Length; i++)
{
Posting posting = postings[i];
// add an entry to the dictionary with pointers to prox and freq files
ti.Set(1, freq.GetFilePointer(), prox.GetFilePointer(), - 1);
tis.Add(posting.term, ti);
// add an entry to the freq file
int postingFreq = posting.freq;
if (postingFreq == 1)
// optimize freq=1
freq.WriteVInt(1);
// set low bit of doc num.
else
{
freq.WriteVInt(0); // the document number
freq.WriteVInt(postingFreq); // frequency in doc
}
int lastPosition = 0; // write positions
int[] positions = posting.positions;
for (int j = 0; j < postingFreq; j++)
{
// use delta-encoding
int position = positions[j];
prox.WriteVInt(position - lastPosition);
lastPosition = position;
}
// check to see if we switched to a new field
System.String termField = posting.term.Field();
if (currentField != termField)
{
// changing field - see if there is something to save
currentField = termField;
FieldInfo fi = fieldInfos.FieldInfo(currentField);
if (fi.storeTermVector)
{
if (termVectorWriter == null)
{
termVectorWriter = new TermVectorsWriter(directory, segment, fieldInfos);
termVectorWriter.OpenDocument();
}
termVectorWriter.OpenField(currentField);
}
else if (termVectorWriter != null)
{
termVectorWriter.CloseField();
}
}
if (termVectorWriter != null && termVectorWriter.IsFieldOpen())
{
termVectorWriter.AddTerm(posting.term.Text(), postingFreq, posting.positions, posting.offsets);
}
}
if (termVectorWriter != null)
termVectorWriter.CloseDocument();
}
finally
{
// make an effort to close all streams we can but remember and re-throw
// the first exception encountered in this process
System.IO.IOException keep = null;
if (freq != null)
try
{
freq.Close();
}
catch (System.IO.IOException e)
{
if (keep == null)
keep = e;
}
if (prox != null)
try
{
prox.Close();
}
catch (System.IO.IOException e)
{
if (keep == null)
keep = e;
}
if (tis != null)
try
{
tis.Close();
}
catch (System.IO.IOException e)
{
if (keep == null)
keep = e;
}
if (termVectorWriter != null)
try
{
termVectorWriter.Close();
}
catch (System.IO.IOException e)
{
if (keep == null)
keep = e;
}
if (keep != null)
{
throw new System.IO.IOException(keep.StackTrace);
}
}
}
/// <summary>Sets the argument to the current TermInfo in the enumeration.
/// Initially invalid, valid after next() called for the first time.
/// </summary>
internal void TermInfo(TermInfo ti)
{
ti.Set(termInfo);
}
/// <summary>Sets the argument to the current TermInfo in the enumeration.
/// Initially invalid, valid after next() called for the first time.
/// </summary>
internal void TermInfo(TermInfo ti)
{
ti.Set(termInfo);
}
internal void Seek(long pointer, int p, Term t, TermInfo ti)
{
input.Seek(pointer);
position = p;
termBuffer.Set(t);
prevBuffer.Reset();
termInfo.Set(ti);
}
internal void Add(Term term, TermInfo ti)
{
UnicodeUtil.UTF16toUTF8(term.Text, 0, term.Text.Length, utf8Result);
Add(fieldInfos.FieldNumber(term.Field), utf8Result.result, utf8Result.length, ti);
}
/// <summary>Adds a new <<fieldNumber, termText>, TermInfo> pair to the set.
/// Term must be lexicographically greater than all previous Terms added.
/// TermInfo pointers must be positive and greater than all previous.
/// </summary>
internal void Add(int fieldNumber, char[] termText, int termTextStart, int termTextLength, TermInfo ti)
{
System.Diagnostics.Debug.Assert(CompareToLastTerm(fieldNumber, termText, termTextStart, termTextLength) < 0 ||
(isIndex && termTextLength == 0 && lastTermTextLength == 0),
"Terms are out of order: field=" + fieldInfos.FieldName(fieldNumber) + "(number " + fieldNumber + ")" +
" lastField=" + fieldInfos.FieldName(lastFieldNumber) + " (number " + lastFieldNumber + ")" +
" text=" + new String(termText, termTextStart, termTextLength) + " lastText=" + new String(lastTermText, 0, lastTermTextLength));
System.Diagnostics.Debug.Assert(ti.freqPointer >= lastTi.freqPointer, "freqPointer out of order (" + ti.freqPointer + " < " + lastTi.freqPointer + ")");
System.Diagnostics.Debug.Assert(ti.proxPointer >= lastTi.proxPointer, "proxPointer out of order (" + ti.proxPointer + " < " + lastTi.proxPointer + ")");
if (!isIndex && size % indexInterval == 0)
{
other.Add(lastFieldNumber, lastTermText, 0, lastTermTextLength, lastTi); // add an index term
}
WriteTerm(fieldNumber, termText, termTextStart, termTextLength); // write term
output.WriteVInt(ti.docFreq); // write doc freq
output.WriteVLong(ti.freqPointer - lastTi.freqPointer); // write pointers
output.WriteVLong(ti.proxPointer - lastTi.proxPointer);
if (ti.docFreq >= skipInterval)
{
output.WriteVInt(ti.skipOffset);
}
if (isIndex)
{
output.WriteVLong(other.output.GetFilePointer() - lastIndexPointer);
lastIndexPointer = other.output.GetFilePointer(); // write pointer
}
if (lastTermText.Length < termTextLength)
{
lastTermText = new char[(int)(termTextLength * 1.25)];
}
Array.Copy(termText, termTextStart, lastTermText, 0, termTextLength);
lastTermTextLength = termTextLength;
lastFieldNumber = fieldNumber;
lastTi.Set(ti);
size++;
}
/// <summary>Adds a new <Term, TermInfo> pair to the set.
/// Term must be lexicographically greater than all previous Terms added.
/// TermInfo pointers must be positive and greater than all previous.
/// </summary>
/*internal*/
public void Add(Term term, TermInfo ti)
{
if (!isIndex && term.CompareTo(lastTerm) <= 0)
{
throw new System.IO.IOException("term out of order (\"" + term + "\".compareTo(\"" + lastTerm + "\") <= 0)");
}
if (ti.freqPointer < lastTi.freqPointer)
throw new System.IO.IOException("freqPointer out of order (" + ti.freqPointer + " < " + lastTi.freqPointer + ")");
if (ti.proxPointer < lastTi.proxPointer)
throw new System.IO.IOException("proxPointer out of order (" + ti.proxPointer + " < " + lastTi.proxPointer + ")");
if (!isIndex && size % indexInterval == 0)
other.Add(lastTerm, lastTi); // add an index term
WriteTerm(term); // write term
output.WriteVInt(ti.docFreq); // write doc freq
output.WriteVLong(ti.freqPointer - lastTi.freqPointer); // write pointers
output.WriteVLong(ti.proxPointer - lastTi.proxPointer);
if (ti.docFreq >= skipInterval)
{
output.WriteVInt(ti.skipOffset);
}
if (isIndex)
{
output.WriteVLong(other.output.GetFilePointer() - lastIndexPointer);
lastIndexPointer = other.output.GetFilePointer(); // write pointer
}
lastTi.Set(ti);
size++;
}
internal void Add(Term term, TermInfo ti)
{
int length = term.text.Length;
if (termTextBuffer.Length < length)
{
termTextBuffer = new char[(int) (length * 1.25)];
}
int i = 0;
System.Collections.Generic.IEnumerator<char> chars = term.text.GetEnumerator();
while (chars.MoveNext())
{
termTextBuffer[i++] = (char)chars.Current;
}
Add(fieldInfos.FieldNumber(term.field), termTextBuffer, 0, length, ti);
}
public virtual void Seek(Term term)
{
TermInfo ti = parent.tis.Get(term);
Seek(ti);
}
// FIXME: OG: remove hard-coded file names
public static void Test()
{
System.IO.FileInfo file = new System.IO.FileInfo("words.txt");
System.Console.Out.WriteLine(" reading word file containing " + file.Length + " bytes");
System.DateTime start = System.DateTime.Now;
System.Collections.ArrayList keys = System.Collections.ArrayList.Synchronized(new System.Collections.ArrayList(10));
System.IO.FileStream ws = new System.IO.FileStream(file.FullName, System.IO.FileMode.Open, System.IO.FileAccess.Read);
System.IO.StreamReader wr = new System.IO.StreamReader(new System.IO.StreamReader(ws, System.Text.Encoding.Default).BaseStream, new System.IO.StreamReader(ws, System.Text.Encoding.Default).CurrentEncoding);
for (System.String key = wr.ReadLine(); key != null; key = wr.ReadLine())
{
keys.Add(new Term("word", key));
}
wr.Close();
System.DateTime end = System.DateTime.Now;
System.Console.Out.Write(end.Ticks - start.Ticks);
System.Console.Out.WriteLine(" milliseconds to read " + keys.Count + " words");
start = System.DateTime.Now;
System.Random gen = new System.Random((System.Int32) 1251971);
long fp = (gen.Next() & 0xF) + 1;
long pp = (gen.Next() & 0xF) + 1;
int[] docFreqs = new int[keys.Count];
long[] freqPointers = new long[keys.Count];
long[] proxPointers = new long[keys.Count];
for (int i = 0; i < keys.Count; i++)
{
docFreqs[i] = (gen.Next() & 0xF) + 1;
freqPointers[i] = fp;
proxPointers[i] = pp;
fp += (gen.Next() & 0xF) + 1;
;
pp += (gen.Next() & 0xF) + 1;
;
}
end = System.DateTime.Now;
System.Console.Out.Write(end.Ticks - start.Ticks);
System.Console.Out.WriteLine(" milliseconds to generate values");
start = System.DateTime.Now;
Directory store = FSDirectory.GetDirectory("test.store", true);
FieldInfos fis = new FieldInfos();
TermInfosWriter writer = new TermInfosWriter(store, "words", fis);
fis.Add("word", false);
for (int i = 0; i < keys.Count; i++)
{
writer.Add((Term)keys[i], new TermInfo(docFreqs[i], freqPointers[i], proxPointers[i]));
}
writer.Close();
end = System.DateTime.Now;
System.Console.Out.Write(end.Ticks - start.Ticks);
System.Console.Out.WriteLine(" milliseconds to write table");
System.Console.Out.WriteLine(" table occupies " + store.FileLength("words.tis") + " bytes");
start = System.DateTime.Now;
TermInfosReader reader = new TermInfosReader(store, "words", fis);
end = System.DateTime.Now;
System.Console.Out.Write(end.Ticks - start.Ticks);
System.Console.Out.WriteLine(" milliseconds to open table");
start = System.DateTime.Now;
SegmentTermEnum enumerator = reader.Terms();
for (int i = 0; i < keys.Count; i++)
{
enumerator.Next();
Term key = (Term)keys[i];
if (!key.Equals(enumerator.Term()))
{
throw new System.Exception("wrong term: " + enumerator.Term() + ", expected: " + key + " at " + i);
}
TermInfo ti = enumerator.TermInfo();
if (ti.docFreq != docFreqs[i])
{
throw new System.Exception("wrong value: " + System.Convert.ToString(ti.docFreq, 16) + ", expected: " + System.Convert.ToString(docFreqs[i], 16) + " at " + i);
}
if (ti.freqPointer != freqPointers[i])
{
throw new System.Exception("wrong value: " + System.Convert.ToString(ti.freqPointer, 16) + ", expected: " + System.Convert.ToString(freqPointers[i], 16) + " at " + i);
}
if (ti.proxPointer != proxPointers[i])
{
throw new System.Exception("wrong value: " + System.Convert.ToString(ti.proxPointer, 16) + ", expected: " + System.Convert.ToString(proxPointers[i], 16) + " at " + i);
}
}
end = System.DateTime.Now;
System.Console.Out.Write(end.Ticks - start.Ticks);
System.Console.Out.WriteLine(" milliseconds to iterate over " + keys.Count + " words");
start = System.DateTime.Now;
for (int i = 0; i < keys.Count; i++)
{
Term key = (Term)keys[i];
TermInfo ti = reader.Get(key);
if (ti.docFreq != docFreqs[i])
{
throw new System.Exception("wrong value: " + System.Convert.ToString(ti.docFreq, 16) + ", expected: " + System.Convert.ToString(docFreqs[i], 16) + " at " + i);
}
if (ti.freqPointer != freqPointers[i])
{
throw new System.Exception("wrong value: " + System.Convert.ToString(ti.freqPointer, 16) + ", expected: " + System.Convert.ToString(freqPointers[i], 16) + " at " + i);
}
if (ti.proxPointer != proxPointers[i])
{
throw new System.Exception("wrong value: " + System.Convert.ToString(ti.proxPointer, 16) + ", expected: " + System.Convert.ToString(proxPointers[i], 16) + " at " + i);
}
}
end = System.DateTime.Now;
System.Console.Out.Write((end.Ticks - start.Ticks) / (float)keys.Count);
System.Console.Out.WriteLine(" average milliseconds per lookup");
TermEnum e = reader.Terms(new Term("word", "azz"));
System.Console.Out.WriteLine("Word after azz is " + e.Term().text);
reader.Close();
store.Close();
}
/// <summary>Adds a new <<fieldNumber, termText>, TermInfo> pair to the set.
/// Term must be lexicographically greater than all previous Terms added.
/// TermInfo pointers must be positive and greater than all previous.
/// </summary>
internal void Add(int fieldNumber, char[] termText, int termTextStart, int termTextLength, TermInfo ti)
{
System.Diagnostics.Debug.Assert(CompareToLastTerm(fieldNumber, termText, termTextStart, termTextLength) < 0 ||
(isIndex && termTextLength == 0 && lastTermTextLength == 0),
"Terms are out of order: field=" + fieldInfos.FieldName(fieldNumber) + "(number " + fieldNumber + ")" +
" lastField=" + fieldInfos.FieldName(lastFieldNumber) + " (number " + lastFieldNumber + ")" +
" text=" + new String(termText, termTextStart, termTextLength) + " lastText=" + new String(lastTermText, 0, lastTermTextLength));
System.Diagnostics.Debug.Assert(ti.freqPointer >= lastTi.freqPointer, "freqPointer out of order (" + ti.freqPointer + " < " + lastTi.freqPointer + ")");
System.Diagnostics.Debug.Assert(ti.proxPointer >= lastTi.proxPointer, "proxPointer out of order (" + ti.proxPointer + " < " + lastTi.proxPointer + ")");
if (!isIndex && size % indexInterval == 0)
other.Add(lastFieldNumber, lastTermText, 0, lastTermTextLength, lastTi); // add an index term
WriteTerm(fieldNumber, termText, termTextStart, termTextLength); // write term
output.WriteVInt(ti.docFreq); // write doc freq
output.WriteVLong(ti.freqPointer - lastTi.freqPointer); // write pointers
output.WriteVLong(ti.proxPointer - lastTi.proxPointer);
if (ti.docFreq >= skipInterval)
{
output.WriteVInt(ti.skipOffset);
}
if (isIndex)
{
output.WriteVLong(other.output.GetFilePointer() - lastIndexPointer);
lastIndexPointer = other.output.GetFilePointer(); // write pointer
}
if (lastTermText.Length < termTextLength)
{
lastTermText = new char[(int) (termTextLength * 1.25)];
}
Array.Copy(termText, termTextStart, lastTermText, 0, termTextLength);
lastTermTextLength = termTextLength;
lastFieldNumber = fieldNumber;
lastTi.Set(ti);
size++;
}
/// <summary>Adds a new <<fieldNumber, termBytes>, TermInfo> pair to the set.
/// Term must be lexicographically greater than all previous Terms added.
/// TermInfo pointers must be positive and greater than all previous.
/// </summary>
internal void Add(int fieldNumber, byte[] termBytes, int termBytesLength, TermInfo ti)
{
System.Diagnostics.Debug.Assert(CompareToLastTerm(fieldNumber, termBytes, termBytesLength) < 0 ||
(isIndex && termBytesLength == 0 && lastTermBytesLength == 0),
"Terms are out of order: field=" + fieldInfos.FieldName(fieldNumber) + "(number " + fieldNumber + ")" +
" lastField=" + fieldInfos.FieldName(lastFieldNumber) + " (number " + lastFieldNumber + ")" +
" text=" + System.Text.Encoding.UTF8.GetString(termBytes, 0, termBytesLength) + " lastText=" + System.Text.Encoding.UTF8.GetString(lastTermBytes, 0, lastTermBytesLength));
System.Diagnostics.Debug.Assert(ti.freqPointer >= lastTi.freqPointer, "freqPointer out of order (" + ti.freqPointer + " < " + lastTi.freqPointer + ")");
System.Diagnostics.Debug.Assert(ti.proxPointer >= lastTi.proxPointer, "proxPointer out of order (" + ti.proxPointer + " < " + lastTi.proxPointer + ")");
if (!isIndex && size % indexInterval == 0)
other.Add(lastFieldNumber, lastTermBytes, lastTermBytesLength, lastTi); // add an index term
WriteTerm(fieldNumber, termBytes, termBytesLength); // write term
output.WriteVInt(ti.docFreq); // write doc freq
output.WriteVLong(ti.freqPointer - lastTi.freqPointer); // write pointers
output.WriteVLong(ti.proxPointer - lastTi.proxPointer);
if (ti.docFreq >= skipInterval)
{
output.WriteVInt(ti.skipOffset);
}
if (isIndex)
{
output.WriteVLong(other.output.GetFilePointer() - lastIndexPointer);
lastIndexPointer = other.output.GetFilePointer(); // write pointer
}
lastFieldNumber = fieldNumber;
lastTi.Set(ti);
size++;
}
internal void Add(Term term, TermInfo ti)
{
UnicodeUtil.UTF16toUTF8(term.text, 0, term.text.Length, utf8Result);
Add(fieldInfos.FieldNumber(term.field), utf8Result.result, utf8Result.length, ti);
}
private void WritePostings(Posting[] postings, System.String segment)
{
IndexOutput freq = null, prox = null;
TermInfosWriter tis = null;
TermVectorsWriter termVectorWriter = null;
try
{
//open files for inverse index storage
freq = directory.CreateOutput(segment + ".frq");
prox = directory.CreateOutput(segment + ".prx");
tis = new TermInfosWriter(directory, segment, fieldInfos, termIndexInterval);
TermInfo ti = new TermInfo();
System.String currentField = null;
for (int i = 0; i < postings.Length; i++)
{
Posting posting = postings[i];
// add an entry to the dictionary with pointers to prox and freq files
ti.Set(1, freq.GetFilePointer(), prox.GetFilePointer(), -1);
tis.Add(posting.term, ti);
// add an entry to the freq file
int postingFreq = posting.freq;
if (postingFreq == 1)
{
// optimize freq=1
freq.WriteVInt(1);
}
// set low bit of doc num.
else
{
freq.WriteVInt(0); // the document number
freq.WriteVInt(postingFreq); // frequency in doc
}
int lastPosition = 0; // write positions
int[] positions = posting.positions;
for (int j = 0; j < postingFreq; j++)
{
// use delta-encoding
int position = positions[j];
prox.WriteVInt(position - lastPosition);
lastPosition = position;
}
// check to see if we switched to a new field
System.String termField = posting.term.Field();
if (currentField != termField)
{
// changing field - see if there is something to save
currentField = termField;
FieldInfo fi = fieldInfos.FieldInfo(currentField);
if (fi.storeTermVector)
{
if (termVectorWriter == null)
{
termVectorWriter = new TermVectorsWriter(directory, segment, fieldInfos);
termVectorWriter.OpenDocument();
}
termVectorWriter.OpenField(currentField);
}
else if (termVectorWriter != null)
{
termVectorWriter.CloseField();
}
}
if (termVectorWriter != null && termVectorWriter.IsFieldOpen())
{
termVectorWriter.AddTerm(posting.term.Text(), postingFreq, posting.positions, posting.offsets);
}
}
if (termVectorWriter != null)
{
termVectorWriter.CloseDocument();
}
}
finally
{
// make an effort to close all streams we can but remember and re-throw
// the first exception encountered in this process
System.IO.IOException keep = null;
if (freq != null)
{
try
{
freq.Close();
}
catch (System.IO.IOException e)
{
if (keep == null)
{
keep = e;
}
}
}
if (prox != null)
{
try
{
prox.Close();
}
catch (System.IO.IOException e)
{
if (keep == null)
{
keep = e;
}
}
}
if (tis != null)
{
try
{
tis.Close();
}
catch (System.IO.IOException e)
{
if (keep == null)
{
keep = e;
}
}
}
if (termVectorWriter != null)
{
try
{
termVectorWriter.Close();
}
catch (System.IO.IOException e)
{
if (keep == null)
{
keep = e;
}
}
}
if (keep != null)
{
throw new System.IO.IOException(keep.StackTrace);
}
}
}
internal virtual void Seek(TermInfo ti, Term term)
{
count = 0;
FieldInfo fi = parent.fieldInfos.FieldInfo(term.field);
currentFieldOmitTf = (fi != null) ? fi.omitTf : false;
currentFieldStoresPayloads = (fi != null) ? fi.storePayloads : false;
if (ti == null)
{
df = 0;
}
else
{
df = ti.docFreq;
doc = 0;
freqBasePointer = ti.freqPointer;
proxBasePointer = ti.proxPointer;
skipPointer = freqBasePointer + ti.skipOffset;
freqStream.Seek(freqBasePointer);
haveSkipped = false;
}
}
public virtual void Seek(Term term)
{
TermInfo ti = parent.core.GetTermsReader().Get(term);
Seek(ti, term);
}