summaryrefslogtreecommitdiff
path: root/core/src/main/java/org/elasticsearch/index/search/MatchQuery.java
blob: f3ea9447db74a57e6415090d7cea477440217509 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
/*
 * Licensed to Elasticsearch under one or more contributor
 * license agreements. See the NOTICE file distributed with
 * this work for additional information regarding copyright
 * ownership. Elasticsearch 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.elasticsearch.index.search;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.miscellaneous.DisableGraphAttribute;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.index.Term;
import org.apache.lucene.queries.ExtendedCommonTermsQuery;
import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.search.BooleanClause.Occur;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.BoostQuery;
import org.apache.lucene.search.FuzzyQuery;
import org.apache.lucene.search.MultiPhraseQuery;
import org.apache.lucene.search.MultiTermQuery;
import org.apache.lucene.search.PhraseQuery;
import org.apache.lucene.search.PrefixQuery;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.SynonymQuery;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.spans.SpanMultiTermQueryWrapper;
import org.apache.lucene.search.spans.SpanNearQuery;
import org.apache.lucene.search.spans.SpanOrQuery;
import org.apache.lucene.search.spans.SpanQuery;
import org.apache.lucene.search.spans.SpanTermQuery;
import org.apache.lucene.util.QueryBuilder;
import org.elasticsearch.ElasticsearchException;
import org.elasticsearch.common.Nullable;
import org.elasticsearch.common.io.stream.StreamInput;
import org.elasticsearch.common.io.stream.StreamOutput;
import org.elasticsearch.common.io.stream.Writeable;
import org.elasticsearch.common.lucene.all.AllTermQuery;
import org.elasticsearch.common.lucene.search.MultiPhrasePrefixQuery;
import org.elasticsearch.common.lucene.search.Queries;
import org.elasticsearch.common.unit.Fuzziness;
import org.elasticsearch.index.analysis.ShingleTokenFilterFactory;
import org.elasticsearch.index.mapper.MappedFieldType;
import org.elasticsearch.index.query.QueryShardContext;
import org.elasticsearch.index.query.support.QueryParsers;

import java.io.IOException;

public class MatchQuery {

    public enum Type implements Writeable {
        /**
         * The text is analyzed and terms are added to a boolean query.
         */
        BOOLEAN(0),
        /**
         * The text is analyzed and used as a phrase query.
         */
        PHRASE(1),
        /**
         * The text is analyzed and used in a phrase query, with the last term acting as a prefix.
         */
        PHRASE_PREFIX(2);

        private final int ordinal;

        Type(int ordinal) {
            this.ordinal = ordinal;
        }

        public static Type readFromStream(StreamInput in) throws IOException {
            int ord = in.readVInt();
            for (Type type : Type.values()) {
                if (type.ordinal == ord) {
                    return type;
                }
            }
            throw new ElasticsearchException("unknown serialized type [" + ord + "]");
        }

        @Override
        public void writeTo(StreamOutput out) throws IOException {
            out.writeVInt(this.ordinal);
        }
    }

    public enum ZeroTermsQuery implements Writeable {
        NONE(0),
        ALL(1);

        private final int ordinal;

        ZeroTermsQuery(int ordinal) {
            this.ordinal = ordinal;
        }

        public static ZeroTermsQuery readFromStream(StreamInput in) throws IOException {
            int ord = in.readVInt();
            for (ZeroTermsQuery zeroTermsQuery : ZeroTermsQuery.values()) {
                if (zeroTermsQuery.ordinal == ord) {
                    return zeroTermsQuery;
                }
            }
            throw new ElasticsearchException("unknown serialized type [" + ord + "]");
        }

        @Override
        public void writeTo(StreamOutput out) throws IOException {
            out.writeVInt(this.ordinal);
        }
    }

    /**
     * the default phrase slop
     */
    public static final int DEFAULT_PHRASE_SLOP = 0;

    /**
     * the default leniency setting
     */
    public static final boolean DEFAULT_LENIENCY = false;

    /**
     * the default zero terms query
     */
    public static final ZeroTermsQuery DEFAULT_ZERO_TERMS_QUERY = ZeroTermsQuery.NONE;

    protected final QueryShardContext context;

    protected String analyzer;

    protected BooleanClause.Occur occur = BooleanClause.Occur.SHOULD;

    protected boolean enablePositionIncrements = true;

    protected int phraseSlop = DEFAULT_PHRASE_SLOP;

    protected Fuzziness fuzziness = null;

    protected int fuzzyPrefixLength = FuzzyQuery.defaultPrefixLength;

    protected int maxExpansions = FuzzyQuery.defaultMaxExpansions;

    protected boolean transpositions = FuzzyQuery.defaultTranspositions;

    protected MultiTermQuery.RewriteMethod fuzzyRewriteMethod;

    protected boolean lenient = DEFAULT_LENIENCY;

    protected ZeroTermsQuery zeroTermsQuery = DEFAULT_ZERO_TERMS_QUERY;

    protected Float commonTermsCutoff = null;

    public MatchQuery(QueryShardContext context) {
        this.context = context;
    }

    public void setAnalyzer(String analyzer) {
        this.analyzer = analyzer;
    }

    public void setOccur(BooleanClause.Occur occur) {
        this.occur = occur;
    }

    public void setCommonTermsCutoff(Float cutoff) {
        this.commonTermsCutoff = cutoff;
    }

    public void setEnablePositionIncrements(boolean enablePositionIncrements) {
        this.enablePositionIncrements = enablePositionIncrements;
    }

    public void setPhraseSlop(int phraseSlop) {
        this.phraseSlop = phraseSlop;
    }

    public void setFuzziness(Fuzziness fuzziness) {
        this.fuzziness = fuzziness;
    }

    public void setFuzzyPrefixLength(int fuzzyPrefixLength) {
        this.fuzzyPrefixLength = fuzzyPrefixLength;
    }

    public void setMaxExpansions(int maxExpansions) {
        this.maxExpansions = maxExpansions;
    }

    public void setTranspositions(boolean transpositions) {
        this.transpositions = transpositions;
    }

    public void setFuzzyRewriteMethod(MultiTermQuery.RewriteMethod fuzzyRewriteMethod) {
        this.fuzzyRewriteMethod = fuzzyRewriteMethod;
    }

    public void setLenient(boolean lenient) {
        this.lenient = lenient;
    }

    public void setZeroTermsQuery(ZeroTermsQuery zeroTermsQuery) {
        this.zeroTermsQuery = zeroTermsQuery;
    }

    protected Analyzer getAnalyzer(MappedFieldType fieldType) {
        if (this.analyzer == null) {
            if (fieldType != null) {
                return context.getSearchAnalyzer(fieldType);
            }
            return context.getMapperService().searchAnalyzer();
        } else {
            Analyzer analyzer = context.getMapperService().getIndexAnalyzers().get(this.analyzer);
            if (analyzer == null) {
                throw new IllegalArgumentException("No analyzer found for [" + this.analyzer + "]");
            }
            return analyzer;
        }
    }

    public Query parse(Type type, String fieldName, Object value) throws IOException {
        final String field;
        MappedFieldType fieldType = context.fieldMapper(fieldName);
        if (fieldType != null) {
            field = fieldType.name();
        } else {
            field = fieldName;
        }

        /*
         * If the user forced an analyzer we really don't care if they are
         * searching a type that wants term queries to be used with query string
         * because the QueryBuilder will take care of it. If they haven't forced
         * an analyzer then types like NumberFieldType that want terms with
         * query string will blow up because their analyzer isn't capable of
         * passing through QueryBuilder.
         */
        boolean noForcedAnalyzer = this.analyzer == null;
        if (fieldType != null && fieldType.tokenized() == false && noForcedAnalyzer) {
            return blendTermQuery(new Term(fieldName, value.toString()), fieldType);
        }

        Analyzer analyzer = getAnalyzer(fieldType);
        assert analyzer != null;
        MatchQueryBuilder builder = new MatchQueryBuilder(analyzer, fieldType);
        builder.setEnablePositionIncrements(this.enablePositionIncrements);

        Query query = null;
        switch (type) {
            case BOOLEAN:
                if (commonTermsCutoff == null) {
                    query = builder.createBooleanQuery(field, value.toString(), occur);
                } else {
                    query = builder.createCommonTermsQuery(field, value.toString(), occur, occur, commonTermsCutoff, fieldType);
                }
                break;
            case PHRASE:
                query = builder.createPhraseQuery(field, value.toString(), phraseSlop);
                break;
            case PHRASE_PREFIX:
                query = builder.createPhrasePrefixQuery(field, value.toString(), phraseSlop, maxExpansions);
                break;
            default:
                throw new IllegalStateException("No type found for [" + type + "]");
        }

        if (query == null) {
            return zeroTermsQuery();
        } else {
            return query;
        }
    }

    protected final Query termQuery(MappedFieldType fieldType, Object value, boolean lenient) {
        try {
            return fieldType.termQuery(value, context);
        } catch (RuntimeException e) {
            if (lenient) {
                return null;
            }
            throw e;
        }
    }

    protected Query zeroTermsQuery() {
        if (zeroTermsQuery == DEFAULT_ZERO_TERMS_QUERY) {
            return Queries.newMatchNoDocsQuery("Matching no documents because no terms present.");
        }
        return Queries.newMatchAllQuery();
    }

    private class MatchQueryBuilder extends QueryBuilder {

        private final MappedFieldType mapper;

        /**
         * Creates a new QueryBuilder using the given analyzer.
         */
        MatchQueryBuilder(Analyzer analyzer, @Nullable MappedFieldType mapper) {
            super(analyzer);
            this.mapper = mapper;
        }

        @Override
        protected Query newTermQuery(Term term) {
            return blendTermQuery(term, mapper);
        }

        @Override
        protected Query newSynonymQuery(Term[] terms) {
            return blendTermsQuery(terms, mapper);
        }

        /**
         * Checks if graph analysis should be enabled for the field depending
         * on the provided {@link Analyzer}
         */
        protected Query createFieldQuery(Analyzer analyzer, BooleanClause.Occur operator, String field,
                                         String queryText, boolean quoted, int phraseSlop) {
            assert operator == BooleanClause.Occur.SHOULD || operator == BooleanClause.Occur.MUST;

            // Use the analyzer to get all the tokens, and then build an appropriate
            // query based on the analysis chain.
            try (TokenStream source = analyzer.tokenStream(field, queryText)) {
                if (source.hasAttribute(DisableGraphAttribute.class)) {
                    /**
                     * A {@link TokenFilter} in this {@link TokenStream} disabled the graph analysis to avoid
                     * paths explosion. See {@link ShingleTokenFilterFactory} for details.
                     */
                    setEnableGraphQueries(false);
                }
                Query query = super.createFieldQuery(source, operator, field, quoted, phraseSlop);
                setEnableGraphQueries(true);
                return query;
            } catch (IOException e) {
                throw new RuntimeException("Error analyzing query text", e);
            }
        }

        public Query createPhrasePrefixQuery(String field, String queryText, int phraseSlop, int maxExpansions) {
            final Query query = createFieldQuery(getAnalyzer(), Occur.MUST, field, queryText, true, phraseSlop);
            return toMultiPhrasePrefix(query, phraseSlop, maxExpansions);
        }

        private Query toMultiPhrasePrefix(final Query query, int phraseSlop, int maxExpansions) {
            float boost = 1;
            Query innerQuery = query;
            while (innerQuery instanceof BoostQuery) {
                BoostQuery bq = (BoostQuery) innerQuery;
                boost *= bq.getBoost();
                innerQuery = bq.getQuery();
            }
            if (query instanceof SpanQuery) {
                return toSpanQueryPrefix((SpanQuery) query, boost);
            }
            final MultiPhrasePrefixQuery prefixQuery = new MultiPhrasePrefixQuery();
            prefixQuery.setMaxExpansions(maxExpansions);
            prefixQuery.setSlop(phraseSlop);
            if (innerQuery instanceof PhraseQuery) {
                PhraseQuery pq = (PhraseQuery) innerQuery;
                Term[] terms = pq.getTerms();
                int[] positions = pq.getPositions();
                for (int i = 0; i < terms.length; i++) {
                    prefixQuery.add(new Term[]{terms[i]}, positions[i]);
                }
                return boost == 1 ? prefixQuery : new BoostQuery(prefixQuery, boost);
            } else if (innerQuery instanceof MultiPhraseQuery) {
                MultiPhraseQuery pq = (MultiPhraseQuery) innerQuery;
                Term[][] terms = pq.getTermArrays();
                int[] positions = pq.getPositions();
                for (int i = 0; i < terms.length; i++) {
                    prefixQuery.add(terms[i], positions[i]);
                }
                return boost == 1 ? prefixQuery : new BoostQuery(prefixQuery, boost);
            } else if (innerQuery instanceof TermQuery) {
                prefixQuery.add(((TermQuery) innerQuery).getTerm());
                return boost == 1 ? prefixQuery : new BoostQuery(prefixQuery, boost);
            } else if (innerQuery instanceof AllTermQuery) {
                prefixQuery.add(((AllTermQuery) innerQuery).getTerm());
                return boost == 1 ? prefixQuery : new BoostQuery(prefixQuery, boost);
            }
            return query;
        }

        private Query toSpanQueryPrefix(SpanQuery query, float boost) {
            if (query instanceof SpanTermQuery) {
                SpanMultiTermQueryWrapper<PrefixQuery> ret =
                    new SpanMultiTermQueryWrapper<>(new PrefixQuery(((SpanTermQuery) query).getTerm()));
                return boost == 1 ? ret : new BoostQuery(ret, boost);
            } else if (query instanceof SpanNearQuery) {
                SpanNearQuery spanNearQuery = (SpanNearQuery) query;
                SpanQuery[] clauses = spanNearQuery.getClauses();
                if (clauses[clauses.length-1] instanceof SpanTermQuery) {
                    clauses[clauses.length-1] = new SpanMultiTermQueryWrapper<>(
                        new PrefixQuery(((SpanTermQuery) clauses[clauses.length-1]).getTerm())
                    );
                }
                SpanNearQuery newQuery = new SpanNearQuery(clauses, spanNearQuery.getSlop(), spanNearQuery.isInOrder());
                return boost == 1 ? newQuery : new BoostQuery(newQuery, boost);
            } else if (query instanceof SpanOrQuery) {
                SpanOrQuery orQuery = (SpanOrQuery) query;
                SpanQuery[] clauses = new SpanQuery[orQuery.getClauses().length];
                for (int i = 0; i < clauses.length; i++) {
                    clauses[i] = (SpanQuery) toSpanQueryPrefix(orQuery.getClauses()[i], 1);
                }
                return boost == 1 ? new SpanOrQuery(clauses) : new BoostQuery(new SpanOrQuery(clauses), boost);
            } else {
                return query;
            }
        }

        public Query createCommonTermsQuery(String field, String queryText, Occur highFreqOccur, Occur lowFreqOccur, float
            maxTermFrequency, MappedFieldType fieldType) {
            Query booleanQuery = createBooleanQuery(field, queryText, lowFreqOccur);
            if (booleanQuery != null && booleanQuery instanceof BooleanQuery) {
                BooleanQuery bq = (BooleanQuery) booleanQuery;
                return boolToExtendedCommonTermsQuery(bq, highFreqOccur, lowFreqOccur, maxTermFrequency, fieldType);
            }
            return booleanQuery;
        }

        private Query boolToExtendedCommonTermsQuery(BooleanQuery bq, Occur highFreqOccur, Occur lowFreqOccur, float
            maxTermFrequency, MappedFieldType fieldType) {
            ExtendedCommonTermsQuery query = new ExtendedCommonTermsQuery(highFreqOccur, lowFreqOccur, maxTermFrequency,
                bq.isCoordDisabled(), fieldType);
            for (BooleanClause clause : bq.clauses()) {
                if (!(clause.getQuery() instanceof TermQuery)) {
                    return bq;
                }
                query.add(((TermQuery) clause.getQuery()).getTerm());
            }
            return query;
        }
    }

    protected Query blendTermsQuery(Term[] terms, MappedFieldType fieldType) {
        return new SynonymQuery(terms);
    }

    protected Query blendTermQuery(Term term, MappedFieldType fieldType) {
        if (fuzziness != null) {
            if (fieldType != null) {
                try {
                    Query query = fieldType.fuzzyQuery(term.text(), fuzziness, fuzzyPrefixLength, maxExpansions, transpositions);
                    if (query instanceof FuzzyQuery) {
                        QueryParsers.setRewriteMethod((FuzzyQuery) query, fuzzyRewriteMethod);
                    }
                    return query;
                } catch (RuntimeException e) {
                    if (lenient) {
                        return new TermQuery(term);
                    } else {
                        throw e;
                    }
                }
            }
            int edits = fuzziness.asDistance(term.text());
            FuzzyQuery query = new FuzzyQuery(term, edits, fuzzyPrefixLength, maxExpansions, transpositions);
            QueryParsers.setRewriteMethod(query, fuzzyRewriteMethod);
            return query;
        }
        if (fieldType != null) {
            Query query = termQuery(fieldType, term.bytes(), lenient);
            if (query != null) {
                return query;
            }
        }
        return new TermQuery(term);
    }

}