Many resources are needed to download a project. Please understand that we have to compensate our server costs. Thank you in advance. Project price only 1 $
You can buy this project and download/modify it how often you want.
/**
* 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.
*/
package org.apache.solr.search;
import org.apache.lucene.util.OpenBitSet;
import org.apache.lucene.search.DocIdSet;
import org.apache.lucene.search.DocIdSetIterator;
import org.apache.lucene.search.Filter;
import org.apache.lucene.index.IndexReader;
import java.io.IOException;
/**
* SortedIntDocSet represents a sorted set of Lucene Document Ids.
*/
public class SortedIntDocSet extends DocSetBase {
protected final int[] docs;
/**
* @param docs Sorted list of ids
*/
public SortedIntDocSet(int[] docs) {
this.docs = docs;
// if (firstNonSorted(docs,0,docs.length)>=0) throw new RuntimeException("NON SORTED DOCS!!!");
}
/**
* @param docs Sorted list of ids
* @param len Number of ids in the list
*/
public SortedIntDocSet(int[] docs, int len) {
this(shrink(docs,len));
}
public int[] getDocs() { return docs; }
public int size() { return docs.length; }
public long memSize() {
return (docs.length<<2)+8;
}
public static int[] zeroInts = new int[0];
public static SortedIntDocSet zero = new SortedIntDocSet(zeroInts);
public static int[] shrink(int[] arr, int newSize) {
if (arr.length == newSize) return arr;
int[] newArr = new int[newSize];
System.arraycopy(arr, 0, newArr, 0, newSize);
return newArr;
}
/** Returns the index of the first non-sorted element or -1 if they are all sorted */
public static int firstNonSorted(int[] arr, int offset, int len) {
if (len <= 1) return -1;
int lower = arr[offset];
int end = offset + len;
for(int i=offset+1; ioffset; j--) {
if (arr[j]=doca) {
// success! we cut down the upper bound by a lot in one step!
high=probe;
} else {
// relative failure... we get to move the low pointer, but not my much
low=probe+1;
// reprobe worth it? it appears so!
probe = low + step;
if (probe=doca) {
high=probe;
} else {
low=probe+1;
}
}
}
}
// binary search the rest of the way
while (low <= high) {
int mid = (low+high) >>> 1;
int docb = b[mid];
if (docb < doca) {
low = mid+1;
}
else if (docb > doca) {
high = mid-1;
}
else {
icount++;
low = mid+1; // found it, so start at next element
break;
}
}
// Didn't find it... low is now positioned on the insertion point,
// which is higher than what we were looking for, so continue using
// the same low point.
}
return icount;
}
public int intersectionSize(DocSet other) {
if (!(other instanceof SortedIntDocSet)) {
// assume other implementations are better at random access than we are,
// true of BitDocSet and HashDocSet.
int icount = 0;
for (int i=0; i>3) >= a.length) {
return intersectionSize(a,b);
}
// if they are close in size, just do a linear walk of both.
int icount=0;
int i=0,j=0;
int doca=a[i],docb=b[j];
for(;;) {
// switch on the sign bit somehow? Hopefull JVM is smart enough to just test once.
// Since set a is less dense then set b, doca is likely to be greater than docb so
// check that case first. This resulted in a 13% speedup.
if (doca > docb) {
if (++j >= b.length) break;
docb=b[j];
} else if (doca < docb) {
if (++i >= a.length) break;
doca=a[i];
} else {
icount++;
if (++i >= a.length) break;
doca=a[i];
if (++j >= b.length) break;
docb=b[j];
}
}
return icount;
}
/** puts the intersection of a and b into the target array and returns the size */
public static int intersection(int a[], int lena, int b[], int lenb, int[] target) {
if (lena > lenb) {
int ti=lena; lena=lenb; lenb=ti;
int[] ta=a; a=b; b=ta;
}
if (lena==0) return 0;
// if b is 8 times bigger than a, use the modified binary search.
if ((lenb>>3) >= lena) {
return intersectionBinarySearch(a, lena, b, lenb, target);
}
int icount=0;
int i=0,j=0;
int doca=a[i],docb=b[j];
for(;;) {
if (doca > docb) {
if (++j >= lenb) break;
docb=b[j];
} else if (doca < docb) {
if (++i >= lena) break;
doca=a[i];
} else {
target[icount++] = doca;
if (++i >= lena) break;
doca=a[i];
if (++j >= lenb) break;
docb=b[j];
}
}
return icount;
}
/** Puts the intersection of a and b into the target array and returns the size.
* lena should be smaller than lenb */
protected static int intersectionBinarySearch(int[] a, int lena, int[] b, int lenb, int[] target) {
int step = (lenb/lena)+1;
step = step + step;
int icount = 0;
int low = 0;
int max = lenb-1;
for (int i=0; i=doca) {
// success! we cut down the upper bound by a lot in one step!
high=probe;
} else {
// relative failure... we get to move the low pointer, but not my much
low=probe+1;
// reprobe worth it? it appears so!
probe = low + step;
if (probe=doca) {
high=probe;
} else {
low=probe+1;
}
}
}
}
// binary search
while (low <= high) {
int mid = (low+high) >>> 1;
int docb = b[mid];
if (docb < doca) {
low = mid+1;
}
else if (docb > doca) {
high = mid-1;
}
else {
target[icount++] = doca;
low = mid+1; // found it, so start at next element
break;
}
}
// Didn't find it... low is now positioned on the insertion point,
// which is higher than what we were looking for, so continue using
// the same low point.
}
return icount;
}
@Override
public DocSet intersection(DocSet other) {
if (!(other instanceof SortedIntDocSet)) {
int icount = 0;
int arr[] = new int[docs.length];
for (int i=0; i=doca) {
// success! we cut down the upper bound by a lot in one step!
high=probe;
} else {
// relative failure... we get to move the low pointer, but not my much
low=probe+1;
// reprobe worth it? it appears so!
probe = low + step;
if (probe=doca) {
high=probe;
} else {
low=probe+1;
}
}
}
}
// binary search
while (low <= high) {
int mid = (low+high) >>> 1;
int docb = b[mid];
if (docb < doca) {
low = mid+1;
}
else if (docb > doca) {
high = mid-1;
}
else {
low = mid+1; // found it, so start at next element
continue outer;
}
}
// Didn't find it... low is now positioned on the insertion point,
// which is higher than what we were looking for, so continue using
// the same low point.
target[count++] = doca;
}
return count;
}
/** puts the intersection of a and not b into the target array and returns the size */
public static int andNot(int a[], int lena, int b[], int lenb, int[] target) {
if (lena==0) return 0;
if (lenb==0) {
System.arraycopy(a,0,target,0,lena);
return lena;
}
// if b is 8 times bigger than a, use the modified binary search.
if ((lenb>>3) >= lena) {
return andNotBinarySearch(a, lena, b, lenb, target);
}
int count=0;
int i=0,j=0;
int doca=a[i],docb=b[j];
for(;;) {
if (doca > docb) {
if (++j >= lenb) break;
docb=b[j];
} else if (doca < docb) {
target[count++] = doca;
if (++i >= lena) break;
doca=a[i];
} else {
if (++i >= lena) break;
doca=a[i];
if (++j >= lenb) break;
docb=b[j];
}
}
int leftover=lena - i;
if (leftover > 0) {
System.arraycopy(a,i,target,count,leftover);
count += leftover;
}
return count;
}
@Override
public DocSet andNot(DocSet other) {
if (other.size()==0) return this;
if (!(other instanceof SortedIntDocSet)) {
int count = 0;
int arr[] = new int[docs.length];
for (int i=0; i>> 1;
int docb = docs[mid];
if (docb < doc) {
low = mid+1;
}
else if (docb > doc) {
high = mid-1;
}
else {
return true;
}
}
return false;
}
public DocIterator iterator() {
return new DocIterator() {
int pos=0;
public boolean hasNext() {
return pos < docs.length;
}
public Integer next() {
return nextDoc();
}
/**
* The remove operation is not supported by this Iterator.
*/
public void remove() {
throw new UnsupportedOperationException("The remove operation is not supported by this Iterator.");
}
public int nextDoc() {
return docs[pos++];
}
public float score() {
return 0.0f;
}
};
}
@Override
public OpenBitSet getBits() {
int maxDoc = size() > 0 ? docs[size()-1] : 0;
OpenBitSet bs = new OpenBitSet(maxDoc+1);
for (int doc : docs) {
bs.fastSet(doc);
}
return bs;
}
public static int findIndex(int[] arr, int value, int low, int high) {
// binary search
while (low <= high) {
int mid = (low+high) >>> 1;
int found = arr[mid];
if (found < value) {
low = mid+1;
}
else if (found > value) {
high = mid-1;
}
else {
return mid;
}
}
return low;
}
@Override
public Filter getTopFilter() {
return new Filter() {
int lastEndIdx = 0;
@Override
public DocIdSet getDocIdSet(IndexReader reader) throws IOException {
int offset = 0;
SolrIndexReader r = (SolrIndexReader)reader;
while (r.getParent() != null) {
offset += r.getBase();
r = r.getParent();
}
final int base = offset;
final int maxDoc = reader.maxDoc();
final int max = base + maxDoc; // one past the max doc in this segment.
int sidx = Math.max(0,lastEndIdx);
if (sidx > 0 && docs[sidx-1] >= base) {
// oops, the lastEndIdx isn't correct... we must have been used
// in a multi-threaded context, or the indexreaders are being
// used out-of-order. start at 0.
sidx = 0;
}
if (sidx < docs.length && docs[sidx] < base) {
// if docs[sidx] is < base, we need to seek to find the real start.
sidx = findIndex(docs, base, sidx, docs.length-1);
}
final int startIdx = sidx;
// Largest possible end index is limited to the start index
// plus the number of docs contained in the segment. Subtract 1 since
// the end index is inclusive.
int eidx = Math.min(docs.length, startIdx + maxDoc) - 1;
// find the real end
eidx = findIndex(docs, max, startIdx, eidx) - 1;
final int endIdx = eidx;
lastEndIdx = endIdx;
return new DocIdSet() {
public DocIdSetIterator iterator() throws IOException {
return new DocIdSetIterator() {
int idx = startIdx;
int adjustedDoc = -1;
public int doc() {
return adjustedDoc;
}
@Override
public int docID() {
return adjustedDoc;
}
@Override
public int nextDoc() throws IOException {
return adjustedDoc = (idx > endIdx) ? NO_MORE_DOCS : (docs[idx++] - base);
}
@Override
public int advance(int target) throws IOException {
if (idx > endIdx || target==NO_MORE_DOCS) return adjustedDoc=NO_MORE_DOCS;
target += base;
// probe next
int rawDoc = docs[idx++];
if (rawDoc >= target) return adjustedDoc=rawDoc-base;
int high = endIdx;
// TODO: probe more before resorting to binary search?
// binary search
while (idx <= high) {
int mid = (idx+high) >>> 1;
rawDoc = docs[mid];
if (rawDoc < target) {
idx = mid+1;
}
else if (rawDoc > target) {
high = mid-1;
}
else {
idx=mid+1;
return adjustedDoc=rawDoc - base;
}
}
// low is on the insertion point...
if (idx <= endIdx) {
return adjustedDoc = docs[idx++] - base;
} else {
return adjustedDoc=NO_MORE_DOCS;
}
}
};
}
@Override
public boolean isCacheable() {
return true;
}
};
}
};
}
}