Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

LUCENE-6464: add expert AnalyzingInfixSuggester.lookup method that accepts arbitrary BooleanQuery to filter contexts 

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1679579 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Michael McCandless 2015-05-15 14:58:55 +00:00
parent 73283d1455
commit 213cdf6793
4 changed files with 100 additions and 36 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
lucene/CHANGES.txt
View File

@ -98,6 +98,11 @@ New Features
Circle, Path (buffered line string), and Polygon.
(Karl Wright via David Smiley)
* LUCENE-6464: Add a new expert lookup method to
AnalyzingInfixSuggester to accept an arbitrary BooleanQuery to
express how contexts should be filtered. (Arcadius Ahouansou via
Mike McCandless)
Optimizations
* LUCENE-6379: IndexWriter.deleteDocuments(Query...) now detects if

105
lucene/suggest/src/java/org/apache/lucene/search/suggest/analyzing/AnalyzingInfixSuggester.java
View File

@ -24,7 +24,6 @@ import java.nio.file.Path;
import java.util.ArrayList;
import java.util.Collection;
import java.util.Collections;
import java.util.HashMap;
import java.util.HashSet;
import java.util.List;
import java.util.Map;
@ -61,6 +60,7 @@ import org.apache.lucene.index.SortedSetDocValues;
import org.apache.lucene.index.SortingMergePolicy;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.search.BooleanClause.Occur;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.Collector;
import org.apache.lucene.search.EarlyTerminatingSortingCollector;
@ -407,22 +407,13 @@ public class AnalyzingInfixSuggester extends Lookup implements Closeable {
/** Lookup, without any context. */
public List<LookupResult> lookup(CharSequence key, int num, boolean allTermsRequired, boolean doHighlight) throws IOException {
return lookup(key, (Map<BytesRef, BooleanClause.Occur>)null, num, allTermsRequired, doHighlight);
return lookup(key, (BooleanQuery)null, num, allTermsRequired, doHighlight);
}
/** Lookup, with context but without booleans. Context booleans default to SHOULD,
* so each suggestion must have at least one of the contexts. */
public List<LookupResult> lookup(CharSequence key, Set<BytesRef> contexts, int num, boolean allTermsRequired, boolean doHighlight) throws IOException {
if (contexts == null) {
return lookup(key, num, allTermsRequired, doHighlight);
}
Map<BytesRef, BooleanClause.Occur> contextInfo = new HashMap<>();
for (BytesRef context : contexts) {
contextInfo.put(context, BooleanClause.Occur.SHOULD);
}
return lookup(key, contextInfo, num, allTermsRequired, doHighlight);
return lookup(key, toQuery(contexts), num, allTermsRequired, doHighlight);
}
/** This is called if the last token isn't ended
@ -441,6 +432,66 @@ public class AnalyzingInfixSuggester extends Lookup implements Closeable {
* must match ({@code allTermsRequired}) and whether the hits
* should be highlighted ({@code doHighlight}). */
public List<LookupResult> lookup(CharSequence key, Map<BytesRef, BooleanClause.Occur> contextInfo, int num, boolean allTermsRequired, boolean doHighlight) throws IOException {
return lookup(key, toQuery(contextInfo), num, allTermsRequired, doHighlight);
}
private BooleanQuery toQuery(Map<BytesRef,BooleanClause.Occur> contextInfo) {
if (contextInfo == null || contextInfo.isEmpty()) {
return null;
}
BooleanQuery contextFilter = new BooleanQuery();
for (Map.Entry<BytesRef,BooleanClause.Occur> entry : contextInfo.entrySet()) {
addContextToQuery(contextFilter, entry.getKey(), entry.getValue());
}
return contextFilter;
}
private BooleanQuery toQuery(Set<BytesRef> contextInfo) {
if (contextInfo == null || contextInfo.isEmpty()) {
return null;
}
BooleanQuery contextFilter = new BooleanQuery();
for (BytesRef context : contextInfo) {
addContextToQuery(contextFilter, context, BooleanClause.Occur.SHOULD);
}
return contextFilter;
}
/**
* This method is handy as we do not need access to internal fields such as CONTEXTS_FIELD_NAME in order to build queries
* However, here may not be its best location.
*
* @param query an instance of @See {@link BooleanQuery}
* @param context the context
* @param clause one of {@link Occur}
*/
public void addContextToQuery(BooleanQuery query, BytesRef context, BooleanClause.Occur clause) {
// NOTE: we "should" wrap this in
// ConstantScoreQuery, or maybe send this as a
// Filter instead to search.
// TODO: if we had a BinaryTermField we could fix
// this "must be valid ut8f" limitation:
query.add(new TermQuery(new Term(CONTEXTS_FIELD_NAME, context)), clause);
}
/**
* This is an advanced method providing the capability to send down to the suggester any
* arbitrary lucene query to be used to filter the result of the suggester
*
* @param key the keyword being looked for
* @param contextQuery an arbitrary Lucene query to be used to filter the result of the suggester. {@link #addContextToQuery} could be used to build this contextQuery.
* @param num number of items to return
* @param allTermsRequired all searched terms must match or not
* @param doHighlight if true, the matching term will be highlighted in the search result
* @return the result of the suggester
* @throws IOException f the is IO exception while reading data from the index
*/
public List<LookupResult> lookup(CharSequence key, BooleanQuery contextQuery, int num, boolean allTermsRequired, boolean doHighlight) throws IOException {
if (searcherMgr == null) {
throw new IllegalStateException("suggester was not built");
@ -454,7 +505,7 @@ public class AnalyzingInfixSuggester extends Lookup implements Closeable {
}
BooleanQuery query;
Set<String> matchedTokens = new HashSet<>();
Set<String> matchedTokens;
String prefixToken = null;
try (TokenStream ts = queryAnalyzer.tokenStream("", new StringReader(key.toString()))) {
@ -496,37 +547,29 @@ public class AnalyzingInfixSuggester extends Lookup implements Closeable {
matchedTokens.add(lastToken);
lastQuery = new TermQuery(new Term(TEXT_FIELD_NAME, lastToken));
}
if (lastQuery != null) {
query.add(lastQuery, occur);
}
}
if (contextInfo != null) {
if (contextQuery != null) {
boolean allMustNot = true;
for (Map.Entry<BytesRef, BooleanClause.Occur> entry : contextInfo.entrySet()) {
if (entry.getValue() != BooleanClause.Occur.MUST_NOT) {
for (BooleanClause clause : contextQuery.clauses()) {
if (clause.getOccur() != BooleanClause.Occur.MUST_NOT) {
allMustNot = false;
break;
}
}
// do not make a subquery if all context booleans are must not
if (allMustNot == true) {
for (Map.Entry<BytesRef, BooleanClause.Occur> entry : contextInfo.entrySet()) {
query.add(new TermQuery(new Term(CONTEXTS_FIELD_NAME, entry.getKey().utf8ToString())), BooleanClause.Occur.MUST_NOT);
if (allMustNot) {
//all are MUST_NOT: add the contextQuery to the main query instead (not as sub-query)
for (BooleanClause clause : contextQuery.clauses()) {
query.add(clause);
}
} else {
BooleanQuery sub = new BooleanQuery();
query.add(sub, BooleanClause.Occur.MUST);
for (Map.Entry<BytesRef, BooleanClause.Occur> entry : contextInfo.entrySet()) {
// NOTE: we "should" wrap this in
// ConstantScoreQuery, or maybe send this as a
// Filter instead to search.
sub.add(new TermQuery(new Term(CONTEXTS_FIELD_NAME, entry.getKey())), entry.getValue());
}
//Add contextQuery as sub-query
query.add(contextQuery, BooleanClause.Occur.MUST);
}
}
}

7
lucene/suggest/src/java/org/apache/lucene/search/suggest/analyzing/BlendedInfixSuggester.java
View File

@ -35,6 +35,7 @@ import org.apache.lucene.index.MultiDocValues;
import org.apache.lucene.index.Terms;
import org.apache.lucene.index.TermsEnum;
import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.FieldDoc;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.TopFieldDocs;
@ -156,6 +157,12 @@ public class BlendedInfixSuggester extends AnalyzingInfixSuggester {
return super.lookup(key, contextInfo, num * numFactor, allTermsRequired, doHighlight);
}
@Override
public List<Lookup.LookupResult> lookup(CharSequence key, BooleanQuery contextQuery, int num, boolean allTermsRequired, boolean doHighlight) throws IOException {
// here we multiply the number of searched element by the defined factor
return super.lookup(key, contextQuery, num * numFactor, allTermsRequired, doHighlight);
}
@Override
protected FieldType getTextFieldType() {
FieldType ft = new FieldType(TextField.TYPE_NOT_STORED);

11
lucene/suggest/src/test/org/apache/lucene/search/suggest/analyzing/AnalyzingInfixSuggesterTest.java
View File

@ -38,6 +38,7 @@ import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.suggest.Input;
import org.apache.lucene.search.suggest.InputArrayIterator;
import org.apache.lucene.search.suggest.Lookup.LookupResult;
@ -949,7 +950,7 @@ public class AnalyzingInfixSuggesterTest extends LuceneTestCase {
return result;
}
// LUCENE-5528
// LUCENE-5528 and LUCENE-6464
public void testBasicContext() throws Exception {
Input keys[] = new Input[] {
new Input("lend me your ear", 8, new BytesRef("foobar"), asSet("foo", "bar")),
@ -1175,6 +1176,14 @@ public class AnalyzingInfixSuggesterTest extends LuceneTestCase {
assertTrue(result.contexts.contains(new BytesRef("foo")));
assertTrue(result.contexts.contains(new BytesRef("baz")));
//LUCENE-6464 Using the advanced context filtering by query.
//Note that this is just a sanity test as all the above tests run through the filter by query method
BooleanQuery query = new BooleanQuery();
suggester.addContextToQuery(query, new BytesRef("foo"), BooleanClause.Occur.MUST);
suggester.addContextToQuery(query, new BytesRef("bar"), BooleanClause.Occur.MUST_NOT);
results = suggester.lookup(TestUtil.stringToCharSequence("ear", random()), query, 10, true, true);
assertEquals(1, results.size());
suggester.close();
a.close();
}