org.apache.solr.legacy.LegacyNumericRangeQuery Maven / Gradle / Ivy
Show all versions of solr-core Show documentation
/*
* 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.legacy;
import java.io.IOException;
import java.util.LinkedList;
import java.util.Objects;
import org.apache.lucene.document.DoublePoint;
import org.apache.lucene.document.FloatPoint;
import org.apache.lucene.document.IntPoint;
import org.apache.lucene.document.LongPoint;
import org.apache.lucene.index.FilteredTermsEnum;
import org.apache.lucene.index.PointValues;
import org.apache.lucene.index.Term;
import org.apache.lucene.index.Terms;
import org.apache.lucene.index.TermsEnum;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.MultiTermQuery;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.QueryVisitor;
import org.apache.lucene.search.TermRangeQuery;
import org.apache.lucene.util.AttributeSource;
import org.apache.lucene.util.BytesRef;
import org.apache.lucene.util.NumericUtils;
/**
* A {@link Query} that matches numeric values within a
* specified range. To use this, you must first index the
* numeric values using {@link org.apache.solr.legacy.LegacyIntField}, {@link
* org.apache.solr.legacy.LegacyFloatField}, {@link org.apache.solr.legacy.LegacyLongField} or {@link org.apache.solr.legacy.LegacyDoubleField} (expert: {@link
* org.apache.solr.legacy.LegacyNumericTokenStream}). If your terms are instead textual,
* you should use {@link TermRangeQuery}.
*
* You create a new LegacyNumericRangeQuery with the static
* factory methods, eg:
*
*
* Query q = LegacyNumericRangeQuery.newFloatRange("weight", 0.03f, 0.10f, true, true);
*
*
* matches all documents whose float valued "weight" field
* ranges from 0.03 to 0.10, inclusive.
*
* The performance of LegacyNumericRangeQuery is much better
* than the corresponding {@link TermRangeQuery} because the
* number of terms that must be searched is usually far
* fewer, thanks to trie indexing, described below.
*
* You can optionally specify a precisionStep
* when creating this query. This is necessary if you've
* changed this configuration from its default (4) during
* indexing. Lower values consume more disk space but speed
* up searching. Suitable values are between 1 and
* 8. A good starting point to test is 4,
* which is the default value for all Numeric*
* classes. See below for
* details.
*
*
This query defaults to {@linkplain
* MultiTermQuery#CONSTANT_SCORE_REWRITE}.
* With precision steps of ≤4, this query can be run with
* one of the BooleanQuery rewrite methods without changing
* BooleanQuery's default max clause count.
*
*
How it works
*
* See the publication about panFMP,
* where this algorithm was described (referred to as TrieRangeQuery
):
*
*
Schindler, U, Diepenbroek, M, 2008.
* Generic XML-based Framework for Metadata Portals.
* Computers & Geosciences 34 (12), 1947-1955.
* doi:10.1016/j.cageo.2008.02.023
*
* A quote from this paper: Because Apache Lucene is a full-text
* search engine and not a conventional database, it cannot handle numerical ranges
* (e.g., field value is inside user defined bounds, even dates are numerical values).
* We have developed an extension to Apache Lucene that stores
* the numerical values in a special string-encoded format with variable precision
* (all numerical values like doubles, longs, floats, and ints are converted to
* lexicographic sortable string representations and stored with different precisions
* (for a more detailed description of how the values are stored,
* see {@link org.apache.solr.legacy.LegacyNumericUtils}). A range is then divided recursively into multiple intervals for searching:
* The center of the range is searched only with the lowest possible precision in the trie,
* while the boundaries are matched more exactly. This reduces the number of terms dramatically.
*
* For the variant that stores long values in 8 different precisions (each reduced by 8 bits) that
* uses a lowest precision of 1 byte, the index contains only a maximum of 256 distinct values in the
* lowest precision. Overall, a range could consist of a theoretical maximum of
* 7*255*2 + 255 = 3825
distinct terms (when there is a term for every distinct value of an
* 8-byte-number in the index and the range covers almost all of them; a maximum of 255 distinct values is used
* because it would always be possible to reduce the full 256 values to one term with degraded precision).
* In practice, we have seen up to 300 terms in most cases (index with 500,000 metadata records
* and a uniform value distribution).
*
* Precision Step
* You can choose any precisionStep
when encoding values.
* Lower step values mean more precisions and so more terms in index (and index gets larger). The number
* of indexed terms per value is (those are generated by {@link org.apache.solr.legacy.LegacyNumericTokenStream}):
*
* indexedTermsPerValue = ceil(bitsPerValue / precisionStep)
*
* As the lower precision terms are shared by many values, the additional terms only
* slightly grow the term dictionary (approx. 7% for precisionStep=4
), but have a larger
* impact on the postings (the postings file will have more entries, as every document is linked to
* indexedTermsPerValue
terms instead of one). The formula to estimate the growth
* of the term dictionary in comparison to one term per value:
*
*
*
*
* On the other hand, if the precisionStep
is smaller, the maximum number of terms to match reduces,
* which optimizes query speed. The formula to calculate the maximum number of terms that will be visited while
* executing the query is:
*
*
*
*
* For longs stored using a precision step of 4, maxQueryTerms = 15*15*2 + 15 = 465
, and for a precision
* step of 2, maxQueryTerms = 31*3*2 + 3 = 189
. But the faster search speed is reduced by more seeking
* in the term enum of the index. Because of this, the ideal precisionStep
value can only
* be found out by testing. Important: You can index with a lower precision step value and test search speed
* using a multiple of the original step value.
*
* Good values for precisionStep
are depending on usage and data type:
*
* - The default for all data types is 4, which is used, when no
precisionStep
is given.
* - Ideal value in most cases for 64 bit data types (long, double) is 6 or 8.
*
- Ideal value in most cases for 32 bit data types (int, float) is 4.
*
- For low cardinality fields larger precision steps are good. If the cardinality is < 100, it is
* fair to use {@link Integer#MAX_VALUE} (see below).
*
- Steps ≥64 for long/double and ≥32 for int/float produces one token
* per value in the index and querying is as slow as a conventional {@link TermRangeQuery}. But it can be used
* to produce fields, that are solely used for sorting (in this case simply use {@link Integer#MAX_VALUE} as
*
precisionStep
). Using {@link org.apache.solr.legacy.LegacyIntField},
* {@link org.apache.solr.legacy.LegacyLongField}, {@link org.apache.solr.legacy.LegacyFloatField} or {@link org.apache.solr.legacy.LegacyDoubleField} for sorting
* is ideal, because building the field cache is much faster than with text-only numbers.
* These fields have one term per value and therefore also work with term enumeration for building distinct lists
* (e.g. facets / preselected values to search for).
* Sorting is also possible with range query optimized fields using one of the above precisionSteps
.
*
*
* Comparisons of the different types of RangeQueries on an index with about 500,000 docs showed
* that {@link TermRangeQuery} in boolean rewrite mode (with raised {@link BooleanQuery} clause count)
* took about 30-40 secs to complete, {@link TermRangeQuery} in constant score filter rewrite mode took 5 secs
* and executing this class took <100ms to complete (on an Opteron64 machine, Java 1.5, 8 bit
* precision step). This query type was developed for a geographic portal, where the performance for
* e.g. bounding boxes or exact date/time stamps is important.
*
* @deprecated Instead index with {@link IntPoint}, {@link LongPoint}, {@link FloatPoint}, {@link DoublePoint}, and
* create range queries with {@link IntPoint#newRangeQuery(String, int, int) IntPoint.newRangeQuery()},
* {@link LongPoint#newRangeQuery(String, long, long) LongPoint.newRangeQuery()},
* {@link FloatPoint#newRangeQuery(String, float, float) FloatPoint.newRangeQuery()},
* {@link DoublePoint#newRangeQuery(String, double, double) DoublePoint.newRangeQuery()} respectively.
* See {@link PointValues} for background information on Points.
*
* @since 2.9
**/
@Deprecated
public final class LegacyNumericRangeQuery extends MultiTermQuery {
private LegacyNumericRangeQuery(final String field, final int precisionStep, final LegacyNumericType dataType,
T min, T max, final boolean minInclusive, final boolean maxInclusive) {
super(field);
if (precisionStep < 1)
throw new IllegalArgumentException("precisionStep must be >=1");
this.precisionStep = precisionStep;
this.dataType = Objects.requireNonNull(dataType, "LegacyNumericType must not be null");
this.min = min;
this.max = max;
this.minInclusive = minInclusive;
this.maxInclusive = maxInclusive;
}
/**
* Factory that creates a LegacyNumericRangeQuery
, that queries a long
* range using the given precisionStep
.
* You can have half-open ranges (which are in fact </≤ or >/≥ queries)
* by setting the min or max value to null
. By setting inclusive to false, it will
* match all documents excluding the bounds, with inclusive on, the boundaries are hits, too.
*/
public static LegacyNumericRangeQuery newLongRange(final String field, final int precisionStep,
Long min, Long max, final boolean minInclusive, final boolean maxInclusive
) {
return new LegacyNumericRangeQuery<>(field, precisionStep, LegacyNumericType.LONG, min, max, minInclusive, maxInclusive);
}
/**
* Factory that creates a LegacyNumericRangeQuery
, that queries a long
* range using the default precisionStep
{@link org.apache.solr.legacy.LegacyNumericUtils#PRECISION_STEP_DEFAULT} (16).
* You can have half-open ranges (which are in fact </≤ or >/≥ queries)
* by setting the min or max value to null
. By setting inclusive to false, it will
* match all documents excluding the bounds, with inclusive on, the boundaries are hits, too.
*/
public static LegacyNumericRangeQuery newLongRange(final String field,
Long min, Long max, final boolean minInclusive, final boolean maxInclusive
) {
return new LegacyNumericRangeQuery<>(field, LegacyNumericUtils.PRECISION_STEP_DEFAULT, LegacyNumericType.LONG, min, max, minInclusive, maxInclusive);
}
/**
* Factory that creates a LegacyNumericRangeQuery
, that queries a int
* range using the given precisionStep
.
* You can have half-open ranges (which are in fact </≤ or >/≥ queries)
* by setting the min or max value to null
. By setting inclusive to false, it will
* match all documents excluding the bounds, with inclusive on, the boundaries are hits, too.
*/
public static LegacyNumericRangeQuery newIntRange(final String field, final int precisionStep,
Integer min, Integer max, final boolean minInclusive, final boolean maxInclusive
) {
return new LegacyNumericRangeQuery<>(field, precisionStep, LegacyNumericType.INT, min, max, minInclusive, maxInclusive);
}
/**
* Factory that creates a LegacyNumericRangeQuery
, that queries a int
* range using the default precisionStep
{@link org.apache.solr.legacy.LegacyNumericUtils#PRECISION_STEP_DEFAULT_32} (8).
* You can have half-open ranges (which are in fact </≤ or >/≥ queries)
* by setting the min or max value to null
. By setting inclusive to false, it will
* match all documents excluding the bounds, with inclusive on, the boundaries are hits, too.
*/
public static LegacyNumericRangeQuery newIntRange(final String field,
Integer min, Integer max, final boolean minInclusive, final boolean maxInclusive
) {
return new LegacyNumericRangeQuery<>(field, LegacyNumericUtils.PRECISION_STEP_DEFAULT_32, LegacyNumericType.INT, min, max, minInclusive, maxInclusive);
}
/**
* Factory that creates a LegacyNumericRangeQuery
, that queries a double
* range using the given precisionStep
.
* You can have half-open ranges (which are in fact </≤ or >/≥ queries)
* by setting the min or max value to null
.
* {@link Double#NaN} will never match a half-open range, to hit {@code NaN} use a query
* with {@code min == max == Double.NaN}. By setting inclusive to false, it will
* match all documents excluding the bounds, with inclusive on, the boundaries are hits, too.
*/
public static LegacyNumericRangeQuery newDoubleRange(final String field, final int precisionStep,
Double min, Double max, final boolean minInclusive, final boolean maxInclusive
) {
return new LegacyNumericRangeQuery<>(field, precisionStep, LegacyNumericType.DOUBLE, min, max, minInclusive, maxInclusive);
}
/**
* Factory that creates a LegacyNumericRangeQuery
, that queries a double
* range using the default precisionStep
{@link org.apache.solr.legacy.LegacyNumericUtils#PRECISION_STEP_DEFAULT} (16).
* You can have half-open ranges (which are in fact </≤ or >/≥ queries)
* by setting the min or max value to null
.
* {@link Double#NaN} will never match a half-open range, to hit {@code NaN} use a query
* with {@code min == max == Double.NaN}. By setting inclusive to false, it will
* match all documents excluding the bounds, with inclusive on, the boundaries are hits, too.
*/
public static LegacyNumericRangeQuery newDoubleRange(final String field,
Double min, Double max, final boolean minInclusive, final boolean maxInclusive
) {
return new LegacyNumericRangeQuery<>(field, LegacyNumericUtils.PRECISION_STEP_DEFAULT, LegacyNumericType.DOUBLE, min, max, minInclusive, maxInclusive);
}
/**
* Factory that creates a LegacyNumericRangeQuery
, that queries a float
* range using the given precisionStep
.
* You can have half-open ranges (which are in fact </≤ or >/≥ queries)
* by setting the min or max value to null
.
* {@link Float#NaN} will never match a half-open range, to hit {@code NaN} use a query
* with {@code min == max == Float.NaN}. By setting inclusive to false, it will
* match all documents excluding the bounds, with inclusive on, the boundaries are hits, too.
*/
public static LegacyNumericRangeQuery newFloatRange(final String field, final int precisionStep,
Float min, Float max, final boolean minInclusive, final boolean maxInclusive
) {
return new LegacyNumericRangeQuery<>(field, precisionStep, LegacyNumericType.FLOAT, min, max, minInclusive, maxInclusive);
}
/**
* Factory that creates a LegacyNumericRangeQuery
, that queries a float
* range using the default precisionStep
{@link org.apache.solr.legacy.LegacyNumericUtils#PRECISION_STEP_DEFAULT_32} (8).
* You can have half-open ranges (which are in fact </≤ or >/≥ queries)
* by setting the min or max value to null
.
* {@link Float#NaN} will never match a half-open range, to hit {@code NaN} use a query
* with {@code min == max == Float.NaN}. By setting inclusive to false, it will
* match all documents excluding the bounds, with inclusive on, the boundaries are hits, too.
*/
public static LegacyNumericRangeQuery newFloatRange(final String field,
Float min, Float max, final boolean minInclusive, final boolean maxInclusive
) {
return new LegacyNumericRangeQuery<>(field, LegacyNumericUtils.PRECISION_STEP_DEFAULT_32, LegacyNumericType.FLOAT, min, max, minInclusive, maxInclusive);
}
@Override @SuppressWarnings("unchecked")
protected TermsEnum getTermsEnum(final Terms terms, AttributeSource atts) throws IOException {
// very strange: java.lang.Number itself is not Comparable, but all subclasses used here are
if (min != null && max != null && ((Comparable) min).compareTo(max) > 0) {
return TermsEnum.EMPTY;
}
return new NumericRangeTermsEnum(terms.iterator());
}
/** Returns true
if the lower endpoint is inclusive */
public boolean includesMin() { return minInclusive; }
/** Returns true
if the upper endpoint is inclusive */
public boolean includesMax() { return maxInclusive; }
/** Returns the lower value of this range query */
public T getMin() { return min; }
/** Returns the upper value of this range query */
public T getMax() { return max; }
/** Returns the precision step. */
public int getPrecisionStep() { return precisionStep; }
@Override
public String toString(final String field) {
final StringBuilder sb = new StringBuilder();
if (!getField().equals(field)) sb.append(getField()).append(':');
return sb.append(minInclusive ? '[' : '{')
.append((min == null) ? "*" : min.toString())
.append(" TO ")
.append((max == null) ? "*" : max.toString())
.append(maxInclusive ? ']' : '}')
.toString();
}
@Override
@SuppressWarnings({"unchecked","rawtypes"})
public final boolean equals(final Object o) {
if (o==this) return true;
if (!super.equals(o))
return false;
if (o instanceof LegacyNumericRangeQuery) {
final LegacyNumericRangeQuery q=(LegacyNumericRangeQuery)o;
return (
(q.min == null ? min == null : q.min.equals(min)) &&
(q.max == null ? max == null : q.max.equals(max)) &&
minInclusive == q.minInclusive &&
maxInclusive == q.maxInclusive &&
precisionStep == q.precisionStep
);
}
return false;
}
@Override
public final int hashCode() {
int hash = super.hashCode();
hash = 31 * hash + precisionStep;
hash = 31 * hash + Objects.hashCode(min);
hash = 31 * hash + Objects.hashCode(max);
hash = 31 * hash + Objects.hashCode(minInclusive);
hash = 31 * hash + Objects.hashCode(maxInclusive);
return hash;
}
// members (package private, to be also fast accessible by NumericRangeTermEnum)
final int precisionStep;
final LegacyNumericType dataType;
final T min, max;
final boolean minInclusive,maxInclusive;
// used to handle float/double infinity correcty
static final long LONG_NEGATIVE_INFINITY =
NumericUtils.doubleToSortableLong(Double.NEGATIVE_INFINITY);
static final long LONG_POSITIVE_INFINITY =
NumericUtils.doubleToSortableLong(Double.POSITIVE_INFINITY);
static final int INT_NEGATIVE_INFINITY =
NumericUtils.floatToSortableInt(Float.NEGATIVE_INFINITY);
static final int INT_POSITIVE_INFINITY =
NumericUtils.floatToSortableInt(Float.POSITIVE_INFINITY);
/**
* Subclass of FilteredTermsEnum for enumerating all terms that match the
* sub-ranges for trie range queries, using flex API.
*
* WARNING: This term enumeration is not guaranteed to be always ordered by
* {@link Term#compareTo}.
* The ordering depends on how {@link org.apache.solr.legacy.LegacyNumericUtils#splitLongRange} and
* {@link org.apache.solr.legacy.LegacyNumericUtils#splitIntRange} generates the sub-ranges. For
* {@link MultiTermQuery} ordering is not relevant.
*/
private final class NumericRangeTermsEnum extends FilteredTermsEnum {
private BytesRef currentLowerBound, currentUpperBound;
private final LinkedList rangeBounds = new LinkedList<>();
NumericRangeTermsEnum(final TermsEnum tenum) {
super(tenum);
switch (dataType) {
case LONG:
case DOUBLE: {
// lower
long minBound;
if (dataType == LegacyNumericType.LONG) {
minBound = (min == null) ? Long.MIN_VALUE : min.longValue();
} else {
assert dataType == LegacyNumericType.DOUBLE;
minBound = (min == null) ? LONG_NEGATIVE_INFINITY
: NumericUtils.doubleToSortableLong(min.doubleValue());
}
if (!minInclusive && min != null) {
if (minBound == Long.MAX_VALUE) break;
minBound++;
}
// upper
long maxBound;
if (dataType == LegacyNumericType.LONG) {
maxBound = (max == null) ? Long.MAX_VALUE : max.longValue();
} else {
assert dataType == LegacyNumericType.DOUBLE;
maxBound = (max == null) ? LONG_POSITIVE_INFINITY
: NumericUtils.doubleToSortableLong(max.doubleValue());
}
if (!maxInclusive && max != null) {
if (maxBound == Long.MIN_VALUE) break;
maxBound--;
}
LegacyNumericUtils.splitLongRange(new LegacyNumericUtils.LongRangeBuilder() {
@Override
public final void addRange(BytesRef minPrefixCoded, BytesRef maxPrefixCoded) {
rangeBounds.add(minPrefixCoded);
rangeBounds.add(maxPrefixCoded);
}
}, precisionStep, minBound, maxBound);
break;
}
case INT:
case FLOAT: {
// lower
int minBound;
if (dataType == LegacyNumericType.INT) {
minBound = (min == null) ? Integer.MIN_VALUE : min.intValue();
} else {
assert dataType == LegacyNumericType.FLOAT;
minBound = (min == null) ? INT_NEGATIVE_INFINITY
: NumericUtils.floatToSortableInt(min.floatValue());
}
if (!minInclusive && min != null) {
if (minBound == Integer.MAX_VALUE) break;
minBound++;
}
// upper
int maxBound;
if (dataType == LegacyNumericType.INT) {
maxBound = (max == null) ? Integer.MAX_VALUE : max.intValue();
} else {
assert dataType == LegacyNumericType.FLOAT;
maxBound = (max == null) ? INT_POSITIVE_INFINITY
: NumericUtils.floatToSortableInt(max.floatValue());
}
if (!maxInclusive && max != null) {
if (maxBound == Integer.MIN_VALUE) break;
maxBound--;
}
LegacyNumericUtils.splitIntRange(new LegacyNumericUtils.IntRangeBuilder() {
@Override
public final void addRange(BytesRef minPrefixCoded, BytesRef maxPrefixCoded) {
rangeBounds.add(minPrefixCoded);
rangeBounds.add(maxPrefixCoded);
}
}, precisionStep, minBound, maxBound);
break;
}
default:
// should never happen
throw new IllegalArgumentException("Invalid LegacyNumericType");
}
}
private void nextRange() {
assert rangeBounds.size() % 2 == 0;
currentLowerBound = rangeBounds.removeFirst();
assert currentUpperBound == null || currentUpperBound.compareTo(currentLowerBound) <= 0 :
"The current upper bound must be <= the new lower bound";
currentUpperBound = rangeBounds.removeFirst();
}
@Override
protected final BytesRef nextSeekTerm(BytesRef term) {
while (rangeBounds.size() >= 2) {
nextRange();
// if the new upper bound is before the term parameter, the sub-range is never a hit
if (term != null && term.compareTo(currentUpperBound) > 0)
continue;
// never seek backwards, so use current term if lower bound is smaller
return (term != null && term.compareTo(currentLowerBound) > 0) ?
term : currentLowerBound;
}
// no more sub-range enums available
assert rangeBounds.isEmpty();
currentLowerBound = currentUpperBound = null;
return null;
}
@Override
protected final AcceptStatus accept(BytesRef term) {
while (currentUpperBound == null || term.compareTo(currentUpperBound) > 0) {
if (rangeBounds.isEmpty())
return AcceptStatus.END;
// peek next sub-range, only seek if the current term is smaller than next lower bound
if (term.compareTo(rangeBounds.getFirst()) < 0)
return AcceptStatus.NO_AND_SEEK;
// step forward to next range without seeking, as next lower range bound is less or equal current term
nextRange();
}
return AcceptStatus.YES;
}
}
@Override
public void visit(QueryVisitor visitor) {
visitor.visitLeaf(this);
}
}