package org.apache.lucene.index.codecs.preflex;
/**
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
import java.io.IOException;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.FieldInfos;
import org.apache.lucene.index.Term;
import org.apache.lucene.index.IndexFileNames;
import org.apache.lucene.store.Directory;
import org.apache.lucene.util.CloseableThreadLocal;
import org.apache.lucene.util.DoubleBarrelLRUCache;
/** This stores a monotonically increasing set of <Term, TermInfo> pairs in a
* Directory. Pairs are accessed either by Term or by ordinal position the
* set
* @deprecated This class has been replaced by
* FormatPostingsTermsDictReader, except for reading old segments.
* @lucene.experimental
*/
@Deprecated
public final class TermInfosReader {
private final Directory directory;
private final String segment;
private final FieldInfos fieldInfos;
private final CloseableThreadLocal<ThreadResources> threadResources = new CloseableThreadLocal<ThreadResources>();
private final SegmentTermEnum origEnum;
private final long size;
private final Term[] indexTerms;
private final TermInfo[] indexInfos;
private final long[] indexPointers;
private final int totalIndexInterval;
private final static int DEFAULT_CACHE_SIZE = 1024;
// Just adds term's ord to TermInfo
private final static class TermInfoAndOrd extends TermInfo {
final int termOrd;
public TermInfoAndOrd(TermInfo ti, int termOrd) {
super(ti);
this.termOrd = termOrd;
}
}
private static class CloneableTerm extends DoubleBarrelLRUCache.CloneableKey {
private Term term;
public CloneableTerm(Term t) {
this.term = t;
}
public boolean equals(Object other) {
return this.term.equals(other);
}
public int hashCode() {
return term.hashCode();
}
public Object clone() {
return new CloneableTerm(term);
}
}
private final DoubleBarrelLRUCache<CloneableTerm,TermInfoAndOrd> termsCache = new DoubleBarrelLRUCache<CloneableTerm,TermInfoAndOrd>(DEFAULT_CACHE_SIZE);
/**
* Per-thread resources managed by ThreadLocal
*/
private static final class ThreadResources {
SegmentTermEnum termEnum;
}
TermInfosReader(Directory dir, String seg, FieldInfos fis, int readBufferSize, int indexDivisor)
throws CorruptIndexException, IOException {
boolean success = false;
if (indexDivisor < 1 && indexDivisor != -1) {
throw new IllegalArgumentException("indexDivisor must be -1 (don't load terms index) or greater than 0: got " + indexDivisor);
}
try {
directory = dir;
segment = seg;
fieldInfos = fis;
origEnum = new SegmentTermEnum(directory.openInput(IndexFileNames.segmentFileName(segment, "", PreFlexCodec.TERMS_EXTENSION),
readBufferSize), fieldInfos, false);
size = origEnum.size;
if (indexDivisor != -1) {
// Load terms index
totalIndexInterval = origEnum.indexInterval * indexDivisor;
final SegmentTermEnum indexEnum = new SegmentTermEnum(directory.openInput(IndexFileNames.segmentFileName(segment, "", PreFlexCodec.TERMS_INDEX_EXTENSION),
readBufferSize), fieldInfos, true);
try {
int indexSize = 1+((int)indexEnum.size-1)/indexDivisor; // otherwise read index
indexTerms = new Term[indexSize];
indexInfos = new TermInfo[indexSize];
indexPointers = new long[indexSize];
for (int i=0;indexEnum.next(); i++) {
indexTerms[i] = indexEnum.term();
assert indexTerms[i] != null;
assert indexTerms[i].text() != null;
assert indexTerms[i].field() != null;
indexInfos[i] = indexEnum.termInfo();
indexPointers[i] = indexEnum.indexPointer;
for (int j = 1; j < indexDivisor; j++)
if (!indexEnum.next())
break;
}
} finally {
indexEnum.close();
}
} else {
// Do not load terms index:
totalIndexInterval = -1;
indexTerms = null;
indexInfos = null;
indexPointers = null;
}
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) {
close();
}
}
}
public int getSkipInterval() {
return origEnum.skipInterval;
}
public int getMaxSkipLevels() {
return origEnum.maxSkipLevels;
}
void close() throws IOException {
if (origEnum != null)
origEnum.close();
threadResources.close();
}
/** Returns the number of term/value pairs in the set. */
long size() {
return size;
}
private ThreadResources getThreadResources() {
ThreadResources resources = threadResources.get();
if (resources == null) {
resources = new ThreadResources();
resources.termEnum = terms();
threadResources.set(resources);
}
return resources;
}
/** Returns the offset of the greatest index entry which is less than or equal to term.*/
private int getIndexOffset(Term term) {
int lo = 0; // binary search indexTerms[]
int hi = indexTerms.length - 1;
while (hi >= lo) {
int mid = (lo + hi) >>> 1;
assert indexTerms[mid] != null : "indexTerms = " + indexTerms.length + " mid=" + mid;
int delta = term.compareToUTF16(indexTerms[mid]);
if (delta < 0)
hi = mid - 1;
else if (delta > 0)
lo = mid + 1;
else
return mid;
}
return hi;
}
private void seekEnum(SegmentTermEnum enumerator, int indexOffset) throws IOException {
enumerator.seek(indexPointers[indexOffset],
((long) indexOffset * totalIndexInterval) - 1,
indexTerms[indexOffset], indexInfos[indexOffset]);
}
/** Returns the TermInfo for a Term in the set, or null. */
TermInfo get(Term term) throws IOException {
return get(term, false);
}
/** Returns the TermInfo for a Term in the set, or null. */
private TermInfo get(Term term, boolean mustSeekEnum) throws IOException {
if (size == 0) return null;
ensureIndexIsRead();
TermInfoAndOrd tiOrd = termsCache.get(new CloneableTerm(term));
ThreadResources resources = getThreadResources();
if (!mustSeekEnum && tiOrd != null) {
return tiOrd;
}
return seekEnum(resources.termEnum, term, tiOrd);
}
TermInfo seekEnum(SegmentTermEnum enumerator, Term term) throws IOException {
return seekEnum(enumerator, term, termsCache.get(new CloneableTerm(term)));
}
TermInfo seekEnum(SegmentTermEnum enumerator, Term term, TermInfoAndOrd tiOrd) throws IOException {
if (size == 0) {
return null;
}
// optimize sequential access: first try scanning cached enum w/o seeking
if (enumerator.term() != null // term is at or past current
&& ((enumerator.prev() != null && term.compareToUTF16(enumerator.prev())> 0)
|| term.compareToUTF16(enumerator.term()) >= 0)) {
int enumOffset = (int)(enumerator.position/totalIndexInterval)+1;
if (indexTerms.length == enumOffset // but before end of block
|| term.compareToUTF16(indexTerms[enumOffset]) < 0) {
// no need to seek
final TermInfo ti;
int numScans = enumerator.scanTo(term);
if (enumerator.term() != null && term.compareToUTF16(enumerator.term()) == 0) {
ti = enumerator.termInfo();
if (numScans > 1) {
// we only want to put this TermInfo into the cache if
// scanEnum skipped more than one dictionary entry.
// This prevents RangeQueries or WildcardQueries to
// wipe out the cache when they iterate over a large numbers
// of terms in order
if (tiOrd == null) {
termsCache.put(new CloneableTerm(term), new TermInfoAndOrd(ti, (int) enumerator.position));
} else {
assert sameTermInfo(ti, tiOrd, enumerator);
assert (int) enumerator.position == tiOrd.termOrd;
}
}
} else {
ti = null;
}
return ti;
}
}
// random-access: must seek
final int indexPos;
if (tiOrd != null) {
indexPos = tiOrd.termOrd / totalIndexInterval;
} else {
// Must do binary search:
indexPos = getIndexOffset(term);
}
seekEnum(enumerator, indexPos);
enumerator.scanTo(term);
final TermInfo ti;
if (enumerator.term() != null && term.compareToUTF16(enumerator.term()) == 0) {
ti = enumerator.termInfo();
if (tiOrd == null) {
termsCache.put(new CloneableTerm(term), new TermInfoAndOrd(ti, (int) enumerator.position));
} else {
assert sameTermInfo(ti, tiOrd, enumerator);
assert (int) enumerator.position == tiOrd.termOrd;
}
} else {
ti = null;
}
return ti;
}
// called only from asserts
private boolean sameTermInfo(TermInfo ti1, TermInfo ti2, SegmentTermEnum enumerator) {
if (ti1.docFreq != ti2.docFreq) {
return false;
}
if (ti1.freqPointer != ti2.freqPointer) {
return false;
}
if (ti1.proxPointer != ti2.proxPointer) {
return false;
}
// skipOffset is only valid when docFreq >= skipInterval:
if (ti1.docFreq >= enumerator.skipInterval &&
ti1.skipOffset != ti2.skipOffset) {
return false;
}
return true;
}
private void ensureIndexIsRead() {
if (indexTerms == null) {
throw new IllegalStateException("terms index was not loaded when this reader was created");
}
}
/** Returns the position of a Term in the set or -1. */
long getPosition(Term term) throws IOException {
if (size == 0) return -1;
ensureIndexIsRead();
int indexOffset = getIndexOffset(term);
SegmentTermEnum enumerator = getThreadResources().termEnum;
seekEnum(enumerator, indexOffset);
while(term.compareToUTF16(enumerator.term()) > 0 && enumerator.next()) {}
if (term.compareToUTF16(enumerator.term()) == 0)
return enumerator.position;
else
return -1;
}
/** Returns an enumeration of all the Terms and TermInfos in the set. */
public SegmentTermEnum terms() {
return (SegmentTermEnum)origEnum.clone();
}
/** Returns an enumeration of terms starting at or after the named term. */
public SegmentTermEnum terms(Term term) throws IOException {
get(term, true);
return (SegmentTermEnum)getThreadResources().termEnum.clone();
}
}