| Methods Summary |
|---|
| private void | closeNorms()
synchronized (norms) {
Enumeration enumerator = norms.elements();
while (enumerator.hasMoreElements()) {
Norm norm = (Norm) enumerator.nextElement();
norm.close();
}
if (singleNormStream != null) {
singleNormStream.close();
singleNormStream = null;
}
}
|
| static byte[] | createFakeNorms(int size)
byte[] ones = new byte[size];
Arrays.fill(ones, DefaultSimilarity.encodeNorm(1.0f));
return ones;
|
| protected void | doClose()
if (fieldsReader != null) {
fieldsReader.close();
}
if (tis != null) {
tis.close();
}
if (freqStream != null)
freqStream.close();
if (proxStream != null)
proxStream.close();
closeNorms();
if (termVectorsReaderOrig != null)
termVectorsReaderOrig.close();
if (cfsReader != null)
cfsReader.close();
|
| protected void | doCommit()
if (deletedDocsDirty) { // re-write deleted
si.advanceDelGen();
// We can write directly to the actual name (vs to a
// .tmp & renaming it) because the file is not live
// until segments file is written:
deletedDocs.write(directory(), si.getDelFileName());
}
if (undeleteAll && si.hasDeletions()) {
si.clearDelGen();
}
if (normsDirty) { // re-write norms
si.setNumFields(fieldInfos.size());
Enumeration values = norms.elements();
while (values.hasMoreElements()) {
Norm norm = (Norm) values.nextElement();
if (norm.dirty) {
norm.reWrite(si);
}
}
}
deletedDocsDirty = false;
normsDirty = false;
undeleteAll = false;
|
| protected void | doDelete(int docNum)
if (deletedDocs == null)
deletedDocs = new BitVector(maxDoc());
deletedDocsDirty = true;
undeleteAll = false;
deletedDocs.set(docNum);
|
| protected void | doSetNorm(int doc, java.lang.String field, byte value)
Norm norm = (Norm) norms.get(field);
if (norm == null) // not an indexed field
return;
norm.dirty = true; // mark it dirty
normsDirty = true;
norms(field)[doc] = value; // set the value
|
| protected void | doUndeleteAll()
deletedDocs = null;
deletedDocsDirty = false;
undeleteAll = true;
|
| public int | docFreq(org.apache.lucene.index.Term t)
ensureOpen();
TermInfo ti = tis.get(t);
if (ti != null)
return ti.docFreq;
else
return 0;
|
| public synchronized org.apache.lucene.document.Document | document(int n, org.apache.lucene.document.FieldSelector fieldSelector)
ensureOpen();
if (isDeleted(n))
throw new IllegalArgumentException
("attempt to access a deleted document");
return fieldsReader.doc(n, fieldSelector);
|
| private byte[] | fakeNorms()
if (ones==null) ones=createFakeNorms(maxDoc());
return ones;
|
| org.apache.lucene.index.FieldInfos | fieldInfos()Returns the field infos of this segment
return fieldInfos;
|
| java.util.Vector | files()
return new Vector(si.files());
|
| public static org.apache.lucene.index.SegmentReader | get(org.apache.lucene.index.SegmentInfo si)
return get(si.dir, si, null, false, false, BufferedIndexInput.BUFFER_SIZE);
|
| public static org.apache.lucene.index.SegmentReader | get(org.apache.lucene.index.SegmentInfo si, int readBufferSize)
return get(si.dir, si, null, false, false, readBufferSize);
|
| public static org.apache.lucene.index.SegmentReader | get(org.apache.lucene.index.SegmentInfos sis, org.apache.lucene.index.SegmentInfo si, boolean closeDir)
return get(si.dir, si, sis, closeDir, true, BufferedIndexInput.BUFFER_SIZE);
|
| public static org.apache.lucene.index.SegmentReader | get(org.apache.lucene.store.Directory dir, org.apache.lucene.index.SegmentInfo si, org.apache.lucene.index.SegmentInfos sis, boolean closeDir, boolean ownDir, int readBufferSize)
SegmentReader instance;
try {
instance = (SegmentReader)IMPL.newInstance();
} catch (Exception e) {
throw new RuntimeException("cannot load SegmentReader class: " + e, e);
}
instance.init(dir, sis, closeDir, ownDir);
instance.initialize(si, readBufferSize);
return instance;
|
| public java.util.Collection | getFieldNames(org.apache.lucene.index.IndexReader$FieldOption fieldOption)
ensureOpen();
Set fieldSet = new HashSet();
for (int i = 0; i < fieldInfos.size(); i++) {
FieldInfo fi = fieldInfos.fieldInfo(i);
if (fieldOption == IndexReader.FieldOption.ALL) {
fieldSet.add(fi.name);
}
else if (!fi.isIndexed && fieldOption == IndexReader.FieldOption.UNINDEXED) {
fieldSet.add(fi.name);
}
else if (fi.storePayloads && fieldOption == IndexReader.FieldOption.STORES_PAYLOADS) {
fieldSet.add(fi.name);
}
else if (fi.isIndexed && fieldOption == IndexReader.FieldOption.INDEXED) {
fieldSet.add(fi.name);
}
else if (fi.isIndexed && fi.storeTermVector == false && fieldOption == IndexReader.FieldOption.INDEXED_NO_TERMVECTOR) {
fieldSet.add(fi.name);
}
else if (fi.storeTermVector == true &&
fi.storePositionWithTermVector == false &&
fi.storeOffsetWithTermVector == false &&
fieldOption == IndexReader.FieldOption.TERMVECTOR) {
fieldSet.add(fi.name);
}
else if (fi.isIndexed && fi.storeTermVector && fieldOption == IndexReader.FieldOption.INDEXED_WITH_TERMVECTOR) {
fieldSet.add(fi.name);
}
else if (fi.storePositionWithTermVector && fi.storeOffsetWithTermVector == false && fieldOption == IndexReader.FieldOption.TERMVECTOR_WITH_POSITION) {
fieldSet.add(fi.name);
}
else if (fi.storeOffsetWithTermVector && fi.storePositionWithTermVector == false && fieldOption == IndexReader.FieldOption.TERMVECTOR_WITH_OFFSET) {
fieldSet.add(fi.name);
}
else if ((fi.storeOffsetWithTermVector && fi.storePositionWithTermVector) &&
fieldOption == IndexReader.FieldOption.TERMVECTOR_WITH_POSITION_OFFSET) {
fieldSet.add(fi.name);
}
}
return fieldSet;
|
| protected synchronized byte[] | getNorms(java.lang.String field)
Norm norm = (Norm) norms.get(field);
if (norm == null) return null; // not indexed, or norms not stored
if (norm.bytes == null) { // value not yet read
byte[] bytes = new byte[maxDoc()];
norms(field, bytes, 0);
norm.bytes = bytes; // cache it
// it's OK to close the underlying IndexInput as we have cached the
// norms and will never read them again.
norm.close();
}
return norm.bytes;
|
| java.lang.String | getSegmentName()Return the name of the segment this reader is reading.
return segment;
|
| public org.apache.lucene.index.TermFreqVector | getTermFreqVector(int docNumber, java.lang.String field)Return a term frequency vector for the specified document and field. The
vector returned contains term numbers and frequencies for all terms in
the specified field of this document, if the field had storeTermVector
flag set. If the flag was not set, the method returns null.
// Check if this field is invalid or has no stored term vector
ensureOpen();
FieldInfo fi = fieldInfos.fieldInfo(field);
if (fi == null || !fi.storeTermVector || termVectorsReaderOrig == null)
return null;
TermVectorsReader termVectorsReader = getTermVectorsReader();
if (termVectorsReader == null)
return null;
return termVectorsReader.get(docNumber, field);
|
| public org.apache.lucene.index.TermFreqVector[] | getTermFreqVectors(int docNumber)Return an array of term frequency vectors for the specified document.
The array contains a vector for each vectorized field in the document.
Each vector vector contains term numbers and frequencies for all terms
in a given vectorized field.
If no such fields existed, the method returns null.
ensureOpen();
if (termVectorsReaderOrig == null)
return null;
TermVectorsReader termVectorsReader = getTermVectorsReader();
if (termVectorsReader == null)
return null;
return termVectorsReader.get(docNumber);
|
| private org.apache.lucene.index.TermVectorsReader | getTermVectorsReader()Create a clone from the initial TermVectorsReader and store it in the ThreadLocal.
TermVectorsReader tvReader = (TermVectorsReader)termVectorsLocal.get();
if (tvReader == null) {
tvReader = (TermVectorsReader)termVectorsReaderOrig.clone();
termVectorsLocal.set(tvReader);
}
return tvReader;
|
| public boolean | hasDeletions()
// Don't call ensureOpen() here (it could affect performance)
return deletedDocs != null;
|
| static boolean | hasDeletions(org.apache.lucene.index.SegmentInfo si)
// Don't call ensureOpen() here (it could affect performance)
return si.hasDeletions();
|
| public synchronized boolean | hasNorms(java.lang.String field)
ensureOpen();
return norms.containsKey(field);
|
| static boolean | hasSeparateNorms(org.apache.lucene.index.SegmentInfo si)
return si.hasSeparateNorms();
|
| private void | initialize(org.apache.lucene.index.SegmentInfo si, int readBufferSize)
segment = si.name;
this.si = si;
boolean success = false;
try {
// Use compound file directory for some files, if it exists
Directory cfsDir = directory();
if (si.getUseCompoundFile()) {
cfsReader = new CompoundFileReader(directory(), segment + ".cfs", readBufferSize);
cfsDir = cfsReader;
}
// No compound file exists - use the multi-file format
fieldInfos = new FieldInfos(cfsDir, segment + ".fnm");
fieldsReader = new FieldsReader(cfsDir, segment, fieldInfos, readBufferSize);
// Verify two sources of "maxDoc" agree:
if (fieldsReader.size() != si.docCount) {
throw new CorruptIndexException("doc counts differ for segment " + si.name + ": fieldsReader shows " + fieldsReader.size() + " but segmentInfo shows " + si.docCount);
}
tis = new TermInfosReader(cfsDir, segment, fieldInfos, readBufferSize);
// NOTE: the bitvector is stored using the regular directory, not cfs
if (hasDeletions(si)) {
deletedDocs = new BitVector(directory(), si.getDelFileName());
// Verify # deletes does not exceed maxDoc for this segment:
if (deletedDocs.count() > maxDoc()) {
throw new CorruptIndexException("number of deletes (" + deletedDocs.count() + ") exceeds max doc (" + maxDoc() + ") for segment " + si.name);
}
}
// 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.openInput(segment + ".frq", readBufferSize);
proxStream = cfsDir.openInput(segment + ".prx", readBufferSize);
openNorms(cfsDir, readBufferSize);
if (fieldInfos.hasVectors()) { // open term vector files only as needed
termVectorsReaderOrig = new TermVectorsReader(cfsDir, segment, fieldInfos, readBufferSize);
}
success = true;
} finally {
// With lock-less commits, it's entirely possible (and
// fine) to hit a FileNotFound exception above. In
// this case, we want to explicitly close any subset
// of things that were opened so that we don't have to
// wait for a GC to do so.
if (!success) {
doClose();
}
}
|
| public synchronized boolean | isDeleted(int n)
return (deletedDocs != null && deletedDocs.get(n));
|
| public int | maxDoc()
// Don't call ensureOpen() here (it could affect performance)
return si.docCount;
|
| public synchronized byte[] | norms(java.lang.String field)
ensureOpen();
byte[] bytes = getNorms(field);
if (bytes==null) bytes=fakeNorms();
return bytes;
|
| public synchronized void | norms(java.lang.String field, byte[] bytes, int offset)Read norms into a pre-allocated array.
ensureOpen();
Norm norm = (Norm) norms.get(field);
if (norm == null) {
System.arraycopy(fakeNorms(), 0, bytes, offset, maxDoc());
return;
}
if (norm.bytes != null) { // can copy from cache
System.arraycopy(norm.bytes, 0, bytes, offset, maxDoc());
return;
}
// Read from disk. norm.in may be shared across multiple norms and
// should only be used in a synchronized context.
norm.in.seek(norm.normSeek);
norm.in.readBytes(bytes, offset, maxDoc());
|
| public int | numDocs()
// Don't call ensureOpen() here (it could affect performance)
int n = maxDoc();
if (deletedDocs != null)
n -= deletedDocs.count();
return n;
|
| private void | openNorms(org.apache.lucene.store.Directory cfsDir, int readBufferSize)
long nextNormSeek = SegmentMerger.NORMS_HEADER.length; //skip header (header unused for now)
int maxDoc = maxDoc();
for (int i = 0; i < fieldInfos.size(); i++) {
FieldInfo fi = fieldInfos.fieldInfo(i);
if (fi.isIndexed && !fi.omitNorms) {
Directory d = directory();
String fileName = si.getNormFileName(fi.number);
if (!si.hasSeparateNorms(fi.number)) {
d = cfsDir;
}
// singleNormFile means multiple norms share this file
boolean singleNormFile = fileName.endsWith("." + IndexFileNames.NORMS_EXTENSION);
IndexInput normInput = null;
long normSeek;
if (singleNormFile) {
normSeek = nextNormSeek;
if (singleNormStream==null) {
singleNormStream = d.openInput(fileName, readBufferSize);
}
// All norms in the .nrm file can share a single IndexInput since
// they are only used in a synchronized context.
// If this were to change in the future, a clone could be done here.
normInput = singleNormStream;
} else {
normSeek = 0;
normInput = d.openInput(fileName);
}
norms.put(fi.name, new Norm(normInput, fi.number, normSeek));
nextNormSeek += maxDoc; // increment also if some norms are separate
}
}
|
| void | rollbackCommit()
super.rollbackCommit();
deletedDocsDirty = rollbackDeletedDocsDirty;
normsDirty = rollbackNormsDirty;
undeleteAll = rollbackUndeleteAll;
Enumeration values = norms.elements();
while (values.hasMoreElements()) {
Norm norm = (Norm) values.nextElement();
norm.dirty = norm.rollbackDirty;
}
|
| void | setSegmentInfo(org.apache.lucene.index.SegmentInfo info)
si = info;
|
| void | startCommit()
super.startCommit();
rollbackDeletedDocsDirty = deletedDocsDirty;
rollbackNormsDirty = normsDirty;
rollbackUndeleteAll = undeleteAll;
Enumeration values = norms.elements();
while (values.hasMoreElements()) {
Norm norm = (Norm) values.nextElement();
norm.rollbackDirty = norm.dirty;
}
|
| public org.apache.lucene.index.TermDocs | termDocs()
ensureOpen();
return new SegmentTermDocs(this);
|
| public org.apache.lucene.index.TermPositions | termPositions()
ensureOpen();
return new SegmentTermPositions(this);
|
| public org.apache.lucene.index.TermEnum | terms()
ensureOpen();
return tis.terms();
|
| public org.apache.lucene.index.TermEnum | terms(org.apache.lucene.index.Term t)
ensureOpen();
return tis.terms(t);
|
| static boolean | usesCompoundFile(org.apache.lucene.index.SegmentInfo si)
return si.getUseCompoundFile();
|
