Source Code Cross Referenced for MoreLikeThis.java in  » Net » lucene-connector » org » apache » lucene » search » similar » Java Source Code / Java DocumentationJava Source Code and Java Documentation

Java Source Code / Java Documentation
1. 6.0 JDK Core
2. 6.0 JDK Modules
3. 6.0 JDK Modules com.sun
4. 6.0 JDK Modules com.sun.java
5. 6.0 JDK Modules sun
6. 6.0 JDK Platform
7. Ajax
8. Apache Harmony Java SE
9. Aspect oriented
10. Authentication Authorization
11. Blogger System
12. Build
13. Byte Code
14. Cache
15. Chart
16. Chat
17. Code Analyzer
18. Collaboration
19. Content Management System
20. Database Client
21. Database DBMS
22. Database JDBC Connection Pool
23. Database ORM
24. Development
25. EJB Server geronimo
26. EJB Server GlassFish
27. EJB Server JBoss 4.2.1
28. EJB Server resin 3.1.5
29. ERP CRM Financial
30. ESB
31. Forum
32. GIS
33. Graphic Library
34. Groupware
35. HTML Parser
36. IDE
37. IDE Eclipse
38. IDE Netbeans
39. Installer
40. Internationalization Localization
41. Inversion of Control
42. Issue Tracking
43. J2EE
44. JBoss
45. JMS
46. JMX
47. Library
48. Mail Clients
49. Net
50. Parser
51. PDF
52. Portal
53. Profiler
54. Project Management
55. Report
56. RSS RDF
57. Rule Engine
58. Science
59. Scripting
60. Search Engine
61. Security
62. Sevlet Container
63. Source Control
64. Swing Library
65. Template Engine
66. Test Coverage
67. Testing
68. UML
69. Web Crawler
70. Web Framework
71. Web Mail
72. Web Server
73. Web Services
74. Web Services apache cxf 2.0.1
75. Web Services AXIS2
76. Wiki Engine
77. Workflow Engines
78. XML
79. XML UI
Java
Java Tutorial
Java Open Source
Jar File Download
Java Articles
Java Products
Java by API
Photoshop Tutorials
Maya Tutorials
Flash Tutorials
3ds-Max Tutorials
Illustrator Tutorials
GIMP Tutorials
C# / C Sharp
C# / CSharp Tutorial
C# / CSharp Open Source
ASP.Net
ASP.NET Tutorial
JavaScript DHTML
JavaScript Tutorial
JavaScript Reference
HTML / CSS
HTML CSS Reference
C / ANSI-C
C Tutorial
C++
C++ Tutorial
Ruby
PHP
Python
Python Tutorial
Python Open Source
SQL Server / T-SQL
SQL Server / T-SQL Tutorial
Oracle PL / SQL
Oracle PL/SQL Tutorial
PostgreSQL
SQL / MySQL
MySQL Tutorial
VB.Net
VB.Net Tutorial
Flash / Flex / ActionScript
VBA / Excel / Access / Word
XML
XML Tutorial
Microsoft Office PowerPoint 2007 Tutorial
Microsoft Office Excel 2007 Tutorial
Microsoft Office Word 2007 Tutorial
Java Source Code / Java Documentation » Net » lucene connector » org.apache.lucene.search.similar 
Source Cross Referenced  Class Diagram Java Document (Java Doc) 


001:        /**
002:         * Copyright 2004-2005 The Apache Software Foundation.
003:         *
004:         * Licensed under the Apache License, Version 2.0 (the "License");
005:         * you may not use this file except in compliance with the License.
006:         * You may obtain a copy of the License at
007:         *
008:         *     http://www.apache.org/licenses/LICENSE-2.0
009:         *
010:         * Unless required by applicable law or agreed to in writing, software
011:         * distributed under the License is distributed on an "AS IS" BASIS,
012:         * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
013:         * See the License for the specific language governing permissions and
014:         * limitations under the License.
015:         */package org.apache.lucene.search.similar;
016:
017:        import org.apache.lucene.util.PriorityQueue;
018:        import org.apache.lucene.index.IndexReader;
019:        import org.apache.lucene.index.Term;
020:        import org.apache.lucene.index.TermFreqVector;
021:        import org.apache.lucene.search.BooleanClause;
022:        import org.apache.lucene.search.DefaultSimilarity;
023:        import org.apache.lucene.search.Similarity;
024:        import org.apache.lucene.search.TermQuery;
025:        import org.apache.lucene.search.BooleanQuery;
026:        import org.apache.lucene.search.IndexSearcher;
027:        import org.apache.lucene.search.Query;
028:        import org.apache.lucene.search.Hits;
029:        import org.apache.lucene.analysis.Analyzer;
030:        import org.apache.lucene.analysis.TokenStream;
031:        import org.apache.lucene.analysis.standard.StandardAnalyzer;
032:        import org.apache.lucene.document.Document;
033:
034:        import java.util.Set;
035:        import java.util.HashMap;
036:        import java.util.Map;
037:        import java.util.Collection;
038:        import java.util.Iterator;
039:        import java.io.IOException;
040:        import java.io.Reader;
041:        import java.io.File;
042:        import java.io.PrintStream;
043:        import java.io.StringReader;
044:        import java.io.FileReader;
045:        import java.io.InputStreamReader;
046:        import java.net.URL;
047:        import java.util.ArrayList;
048:
049:        /**
050:         * Generate "more like this" similarity queries. 
051:         * Based on this mail:
052:         * <code><pre>
053:         * Lucene does let you access the document frequency of terms, with IndexReader.docFreq().
054:         * Term frequencies can be computed by re-tokenizing the text, which, for a single document,
055:         * is usually fast enough.  But looking up the docFreq() of every term in the document is
056:         * probably too slow.
057:         * 
058:         * You can use some heuristics to prune the set of terms, to avoid calling docFreq() too much,
059:         * or at all.  Since you're trying to maximize a tf*idf score, you're probably most interested
060:         * in terms with a high tf. Choosing a tf threshold even as low as two or three will radically
061:         * reduce the number of terms under consideration.  Another heuristic is that terms with a
062:         * high idf (i.e., a low df) tend to be longer.  So you could threshold the terms by the
063:         * number of characters, not selecting anything less than, e.g., six or seven characters.
064:         * With these sorts of heuristics you can usually find small set of, e.g., ten or fewer terms
065:         * that do a pretty good job of characterizing a document.
066:         * 
067:         * It all depends on what you're trying to do.  If you're trying to eek out that last percent
068:         * of precision and recall regardless of computational difficulty so that you can win a TREC
069:         * competition, then the techniques I mention above are useless.  But if you're trying to
070:         * provide a "more like this" button on a search results page that does a decent job and has
071:         * good performance, such techniques might be useful.
072:         * 
073:         * An efficient, effective "more-like-this" query generator would be a great contribution, if
074:         * anyone's interested.  I'd imagine that it would take a Reader or a String (the document's
075:         * text), analyzer Analyzer, and return a set of representative terms using heuristics like those
076:         * above.  The frequency and length thresholds could be parameters, etc.
077:         * 
078:         * Doug
079:         * </pre></code>
080:         *
081:         *
082:         * <p>
083:         * <h3>Initial Usage</h3>
084:         *
085:         * This class has lots of options to try to make it efficient and flexible.
086:         * See the body of {@link #main main()} below in the source for real code, or
087:         * if you want pseudo code, the simpliest possible usage is as follows. The bold
088:         * fragment is specific to this class.
089:         *
090:         * <code><pre>
091:         *
092:         * IndexReader ir = ...
093:         * IndexSearcher is = ...
094:         * <b>
095:         * MoreLikeThis mlt = new MoreLikeThis(ir);
096:         * Reader target = ... </b><em>// orig source of doc you want to find similarities to</em><b>
097:         * Query query = mlt.like( target);
098:         * </b>
099:         * Hits hits = is.search(query);
100:         * <em>// now the usual iteration thru 'hits' - the only thing to watch for is to make sure
101:         * you ignore the doc if it matches your 'target' document, as it should be similar to itself </em>
102:         *
103:         * </pre></code>
104:         *
105:         * Thus you:
106:         * <ol>
107:         * <li> do your normal, Lucene setup for searching,
108:         * <li> create a MoreLikeThis,
109:         * <li> get the text of the doc you want to find similaries to
110:         * <li> then call one of the like() calls to generate a similarity query
111:         * <li> call the searcher to find the similar docs
112:         * </ol>
113:         *
114:         * <h3>More Advanced Usage</h3>
115:         *
116:         * You may want to use {@link #setFieldNames setFieldNames(...)} so you can examine
117:         * multiple fields (e.g. body and title) for similarity.
118:         * <p>
119:         *
120:         * Depending on the size of your index and the size and makeup of your documents you
121:         * may want to call the other set methods to control how the similarity queries are
122:         * generated:
123:         * <ul>
124:         * <li> {@link #setMinTermFreq setMinTermFreq(...)}
125:         * <li> {@link #setMinDocFreq setMinDocFreq(...)}
126:         * <li> {@link #setMinWordLen setMinWordLen(...)}
127:         * <li> {@link #setMaxWordLen setMaxWordLen(...)}
128:         * <li> {@link #setMaxQueryTerms setMaxQueryTerms(...)}
129:         * <li> {@link #setMaxNumTokensParsed setMaxNumTokensParsed(...)}
130:         * <li> {@link #setStopWords setStopWord(...)} 
131:         * </ul> 
132:         *
133:         * <hr>
134:         * <pre>
135:         * Changes: Mark Harwood 29/02/04
136:         * Some bugfixing, some refactoring, some optimisation.
137:         *  - bugfix: retrieveTerms(int docNum) was not working for indexes without a termvector -added missing code
138:         *  - bugfix: No significant terms being created for fields with a termvector - because 
139:         *            was only counting one occurence per term/field pair in calculations(ie not including frequency info from TermVector) 
140:         *  - refactor: moved common code into isNoiseWord()
141:         *  - optimise: when no termvector support available - used maxNumTermsParsed to limit amount of tokenization
142:         * </pre>
143:         * 
144:         * @author David Spencer
145:         * @author Bruce Ritchie
146:         * @author Mark Harwood
147:         */
148:        public final class MoreLikeThis {
149:
150:            /**
151:             * Default maximum number of tokens to parse in each example doc field that is not stored with TermVector support.
152:             * @see #getMaxNumTokensParsed
153:             */
154:            public static final int DEFAULT_MAX_NUM_TOKENS_PARSED = 5000;
155:
156:            /**
157:             * Default analyzer to parse source doc with.
158:             * @see #getAnalyzer
159:             */
160:            public static final Analyzer DEFAULT_ANALYZER = new StandardAnalyzer();
161:
162:            /**
163:             * Ignore terms with less than this frequency in the source doc.
164:             * @see #getMinTermFreq
165:             * @see #setMinTermFreq	 
166:             */
167:            public static final int DEFAULT_MIN_TERM_FREQ = 2;
168:
169:            /**
170:             * Ignore words which do not occur in at least this many docs.
171:             * @see #getMinDocFreq
172:             * @see #setMinDocFreq	 
173:             */
174:            public static final int DEFAULT_MIN_DOC_FREQ = 5;
175:
176:            /**
177:             * Boost terms in query based on score.
178:             * @see #isBoost
179:             * @see #setBoost 
180:             */
181:            public static final boolean DEFAULT_BOOST = false;
182:
183:            /**
184:             * Default field names. Null is used to specify that the field names should be looked
185:             * up at runtime from the provided reader.
186:             */
187:            public static final String[] DEFAULT_FIELD_NAMES = new String[] { "contents" };
188:
189:            /**
190:             * Ignore words less than this length or if 0 then this has no effect.
191:             * @see #getMinWordLen
192:             * @see #setMinWordLen	 
193:             */
194:            public static final int DEFAULT_MIN_WORD_LENGTH = 0;
195:
196:            /**
197:             * Ignore words greater than this length or if 0 then this has no effect.
198:             * @see #getMaxWordLen
199:             * @see #setMaxWordLen	 
200:             */
201:            public static final int DEFAULT_MAX_WORD_LENGTH = 0;
202:
203:            /**
204:             * Default set of stopwords.
205:             * If null means to allow stop words.
206:             *
207:             * @see #setStopWords
208:             * @see #getStopWords
209:             */
210:            public static final Set DEFAULT_STOP_WORDS = null;
211:
212:            /**
213:             * Current set of stop words.
214:             */
215:            private Set stopWords = DEFAULT_STOP_WORDS;
216:
217:            /**
218:             * Return a Query with no more than this many terms.
219:             *
220:             * @see BooleanQuery#getMaxClauseCount
221:             * @see #getMaxQueryTerms
222:             * @see #setMaxQueryTerms	 
223:             */
224:            public static final int DEFAULT_MAX_QUERY_TERMS = 25;
225:
226:            /**
227:             * Analyzer that will be used to parse the doc.
228:             */
229:            private Analyzer analyzer = DEFAULT_ANALYZER;
230:
231:            /**
232:             * Ignore words less freqent that this.
233:             */
234:            private int minTermFreq = DEFAULT_MIN_TERM_FREQ;
235:
236:            /**
237:             * Ignore words which do not occur in at least this many docs.
238:             */
239:            private int minDocFreq = DEFAULT_MIN_DOC_FREQ;
240:
241:            /**
242:             * Should we apply a boost to the Query based on the scores?
243:             */
244:            private boolean boost = DEFAULT_BOOST;
245:
246:            /**
247:             * Field name we'll analyze.
248:             */
249:            private String[] fieldNames = DEFAULT_FIELD_NAMES;
250:
251:            /**
252:             * The maximum number of tokens to parse in each example doc field that is not stored with TermVector support
253:             */
254:            private int maxNumTokensParsed = DEFAULT_MAX_NUM_TOKENS_PARSED;
255:
256:            /**
257:             * Ignore words if less than this len.
258:             */
259:            private int minWordLen = DEFAULT_MIN_WORD_LENGTH;
260:
261:            /**
262:             * Ignore words if greater than this len.
263:             */
264:            private int maxWordLen = DEFAULT_MAX_WORD_LENGTH;
265:
266:            /**
267:             * Don't return a query longer than this.
268:             */
269:            private int maxQueryTerms = DEFAULT_MAX_QUERY_TERMS;
270:
271:            /**
272:             * For idf() calculations.
273:             */
274:            private Similarity similarity = new DefaultSimilarity();
275:
276:            /**
277:             * IndexReader to use
278:             */
279:            private final IndexReader ir;
280:
281:            /**
282:             * Constructor requiring an IndexReader.
283:             */
284:            public MoreLikeThis(IndexReader ir) {
285:                this .ir = ir;
286:            }
287:
288:            /**
289:             * Returns an analyzer that will be used to parse source doc with. The default analyzer
290:             * is the {@link #DEFAULT_ANALYZER}.
291:             *
292:             * @return the analyzer that will be used to parse source doc with.
293:             * @see #DEFAULT_ANALYZER
294:             */
295:            public Analyzer getAnalyzer() {
296:                return analyzer;
297:            }
298:
299:            /**
300:             * Sets the analyzer to use. An analyzer is not required for generating a query with the
301:             * {@link #like(int)} method, all other 'like' methods require an analyzer.
302:             *
303:             * @param analyzer the analyzer to use to tokenize text.
304:             */
305:            public void setAnalyzer(Analyzer analyzer) {
306:                this .analyzer = analyzer;
307:            }
308:
309:            /**
310:             * Returns the frequency below which terms will be ignored in the source doc. The default
311:             * frequency is the {@link #DEFAULT_MIN_TERM_FREQ}.
312:             *
313:             * @return the frequency below which terms will be ignored in the source doc.
314:             */
315:            public int getMinTermFreq() {
316:                return minTermFreq;
317:            }
318:
319:            /**
320:             * Sets the frequency below which terms will be ignored in the source doc.
321:             *
322:             * @param minTermFreq the frequency below which terms will be ignored in the source doc.
323:             */
324:            public void setMinTermFreq(int minTermFreq) {
325:                this .minTermFreq = minTermFreq;
326:            }
327:
328:            /**
329:             * Returns the frequency at which words will be ignored which do not occur in at least this
330:             * many docs. The default frequency is {@link #DEFAULT_MIN_DOC_FREQ}.
331:             *
332:             * @return the frequency at which words will be ignored which do not occur in at least this
333:             * many docs.
334:             */
335:            public int getMinDocFreq() {
336:                return minDocFreq;
337:            }
338:
339:            /**
340:             * Sets the frequency at which words will be ignored which do not occur in at least this
341:             * many docs.
342:             *
343:             * @param minDocFreq the frequency at which words will be ignored which do not occur in at
344:             * least this many docs.
345:             */
346:            public void setMinDocFreq(int minDocFreq) {
347:                this .minDocFreq = minDocFreq;
348:            }
349:
350:            /**
351:             * Returns whether to boost terms in query based on "score" or not. The default is
352:             * {@link #DEFAULT_BOOST}.
353:             *
354:             * @return whether to boost terms in query based on "score" or not.
355:             * @see #setBoost
356:             */
357:            public boolean isBoost() {
358:                return boost;
359:            }
360:
361:            /**
362:             * Sets whether to boost terms in query based on "score" or not.
363:             *
364:             * @param boost true to boost terms in query based on "score", false otherwise.
365:             * @see #isBoost
366:             */
367:            public void setBoost(boolean boost) {
368:                this .boost = boost;
369:            }
370:
371:            /**
372:             * Returns the field names that will be used when generating the 'More Like This' query.
373:             * The default field names that will be used is {@link #DEFAULT_FIELD_NAMES}.
374:             *
375:             * @return the field names that will be used when generating the 'More Like This' query.
376:             */
377:            public String[] getFieldNames() {
378:                return fieldNames;
379:            }
380:
381:            /**
382:             * Sets the field names that will be used when generating the 'More Like This' query.
383:             * Set this to null for the field names to be determined at runtime from the IndexReader
384:             * provided in the constructor.
385:             *
386:             * @param fieldNames the field names that will be used when generating the 'More Like This'
387:             * query.
388:             */
389:            public void setFieldNames(String[] fieldNames) {
390:                this .fieldNames = fieldNames;
391:            }
392:
393:            /**
394:             * Returns the minimum word length below which words will be ignored. Set this to 0 for no
395:             * minimum word length. The default is {@link #DEFAULT_MIN_WORD_LENGTH}.
396:             *
397:             * @return the minimum word length below which words will be ignored.
398:             */
399:            public int getMinWordLen() {
400:                return minWordLen;
401:            }
402:
403:            /**
404:             * Sets the minimum word length below which words will be ignored.
405:             *
406:             * @param minWordLen the minimum word length below which words will be ignored.
407:             */
408:            public void setMinWordLen(int minWordLen) {
409:                this .minWordLen = minWordLen;
410:            }
411:
412:            /**
413:             * Returns the maximum word length above which words will be ignored. Set this to 0 for no
414:             * maximum word length. The default is {@link #DEFAULT_MAX_WORD_LENGTH}.
415:             *
416:             * @return the maximum word length above which words will be ignored.
417:             */
418:            public int getMaxWordLen() {
419:                return maxWordLen;
420:            }
421:
422:            /**
423:             * Sets the maximum word length above which words will be ignored.
424:             *
425:             * @param maxWordLen the maximum word length above which words will be ignored.
426:             */
427:            public void setMaxWordLen(int maxWordLen) {
428:                this .maxWordLen = maxWordLen;
429:            }
430:
431:            /**
432:             * Set the set of stopwords.
433:             * Any word in this set is considered "uninteresting" and ignored.
434:             * Even if your Analyzer allows stopwords, you might want to tell the MoreLikeThis code to ignore them, as
435:             * for the purposes of document similarity it seems reasonable to assume that "a stop word is never interesting".
436:             * 
437:             * @param stopWords set of stopwords, if null it means to allow stop words
438:             *
439:             * @see org.apache.lucene.analysis.StopFilter#makeStopSet StopFilter.makeStopSet()
440:             * @see #getStopWords	 
441:             */
442:            public void setStopWords(Set stopWords) {
443:                this .stopWords = stopWords;
444:            }
445:
446:            /**
447:             * Get the current stop words being used.
448:             * @see #setStopWords
449:             */
450:            public Set getStopWords() {
451:                return stopWords;
452:            }
453:
454:            /**
455:             * Returns the maximum number of query terms that will be included in any generated query.
456:             * The default is {@link #DEFAULT_MAX_QUERY_TERMS}.
457:             *
458:             * @return the maximum number of query terms that will be included in any generated query.
459:             */
460:            public int getMaxQueryTerms() {
461:                return maxQueryTerms;
462:            }
463:
464:            /**
465:             * Sets the maximum number of query terms that will be included in any generated query.
466:             *
467:             * @param maxQueryTerms the maximum number of query terms that will be included in any
468:             * generated query.
469:             */
470:            public void setMaxQueryTerms(int maxQueryTerms) {
471:                this .maxQueryTerms = maxQueryTerms;
472:            }
473:
474:            /**
475:             * @return The maximum number of tokens to parse in each example doc field that is not stored with TermVector support
476:             * @see #DEFAULT_MAX_NUM_TOKENS_PARSED
477:             */
478:            public int getMaxNumTokensParsed() {
479:                return maxNumTokensParsed;
480:            }
481:
482:            /**
483:             * @param i The maximum number of tokens to parse in each example doc field that is not stored with TermVector support
484:             */
485:            public void setMaxNumTokensParsed(int i) {
486:                maxNumTokensParsed = i;
487:            }
488:
489:            /**
490:             * Return a query that will return docs like the passed lucene document ID.
491:             *
492:             * @param docNum the documentID of the lucene doc to generate the 'More Like This" query for.
493:             * @return a query that will return docs like the passed lucene document ID.
494:             */
495:            public Query like(int docNum) throws IOException {
496:                if (fieldNames == null) {
497:                    // gather list of valid fields from lucene
498:                    Collection fields = ir
499:                            .getFieldNames(IndexReader.FieldOption.INDEXED);
500:                    fieldNames = (String[]) fields.toArray(new String[fields
501:                            .size()]);
502:                }
503:
504:                return createQuery(retrieveTerms(docNum));
505:            }
506:
507:            /**
508:             * Return a query that will return docs like the passed file.
509:             *
510:             * @return a query that will return docs like the passed file.
511:             */
512:            public Query like(File f) throws IOException {
513:                if (fieldNames == null) {
514:                    // gather list of valid fields from lucene
515:                    Collection fields = ir
516:                            .getFieldNames(IndexReader.FieldOption.INDEXED);
517:                    fieldNames = (String[]) fields.toArray(new String[fields
518:                            .size()]);
519:                }
520:
521:                return like(new FileReader(f));
522:            }
523:
524:            /**
525:             * Return a query that will return docs like the passed URL.
526:             *
527:             * @return a query that will return docs like the passed URL.
528:             */
529:            public Query like(URL u) throws IOException {
530:                return like(new InputStreamReader(u.openConnection()
531:                        .getInputStream()));
532:            }
533:
534:            /**
535:             * Return a query that will return docs like the passed stream.
536:             *
537:             * @return a query that will return docs like the passed stream.
538:             */
539:            public Query like(java.io.InputStream is) throws IOException {
540:                return like(new InputStreamReader(is));
541:            }
542:
543:            /**
544:             * Return a query that will return docs like the passed Reader.
545:             *
546:             * @return a query that will return docs like the passed Reader.
547:             */
548:            public Query like(Reader r) throws IOException {
549:                return createQuery(retrieveTerms(r));
550:            }
551:
552:            /**
553:             * Create the More like query from a PriorityQueue
554:             */
555:            private Query createQuery(PriorityQueue q) {
556:                BooleanQuery query = new BooleanQuery();
557:                Object cur;
558:                int qterms = 0;
559:                float bestScore = 0;
560:
561:                while (((cur = q.pop()) != null)) {
562:                    Object[] ar = (Object[]) cur;
563:                    TermQuery tq = new TermQuery(new Term((String) ar[1],
564:                            (String) ar[0]));
565:
566:                    if (boost) {
567:                        if (qterms == 0) {
568:                            bestScore = ((Float) ar[2]).floatValue();
569:                        }
570:                        float myScore = ((Float) ar[2]).floatValue();
571:
572:                        tq.setBoost(myScore / bestScore);
573:                    }
574:
575:                    try {
576:                        query.add(tq, BooleanClause.Occur.SHOULD);
577:                    } catch (BooleanQuery.TooManyClauses ignore) {
578:                        break;
579:                    }
580:
581:                    qterms++;
582:                    if (maxQueryTerms > 0 && qterms >= maxQueryTerms) {
583:                        break;
584:                    }
585:                }
586:
587:                return query;
588:            }
589:
590:            /**
591:             * Create a PriorityQueue from a word->tf map.
592:             *
593:             * @param words a map of words keyed on the word(String) with Int objects as the values.
594:             */
595:            private PriorityQueue createQueue(Map words) throws IOException {
596:                // have collected all words in doc and their freqs
597:                int numDocs = ir.numDocs();
598:                FreqQ res = new FreqQ(words.size()); // will order words by score
599:
600:                Iterator it = words.keySet().iterator();
601:                while (it.hasNext()) { // for every word
602:                    String word = (String) it.next();
603:
604:                    int tf = ((Int) words.get(word)).x; // term freq in the source doc
605:                    if (minTermFreq > 0 && tf < minTermFreq) {
606:                        continue; // filter out words that don't occur enough times in the source
607:                    }
608:
609:                    // go through all the fields and find the largest document frequency
610:                    String topField = fieldNames[0];
611:                    int docFreq = 0;
612:                    for (int i = 0; i < fieldNames.length; i++) {
613:                        int freq = ir.docFreq(new Term(fieldNames[i], word));
614:                        topField = (freq > docFreq) ? fieldNames[i] : topField;
615:                        docFreq = (freq > docFreq) ? freq : docFreq;
616:                    }
617:
618:                    if (minDocFreq > 0 && docFreq < minDocFreq) {
619:                        continue; // filter out words that don't occur in enough docs
620:                    }
621:
622:                    if (docFreq == 0) {
623:                        continue; // index update problem?
624:                    }
625:
626:                    float idf = similarity.idf(docFreq, numDocs);
627:                    float score = tf * idf;
628:
629:                    // only really need 1st 3 entries, other ones are for troubleshooting
630:                    res.insert(new Object[] { word, // the word
631:                            topField, // the top field
632:                            new Float(score), // overall score
633:                            new Float(idf), // idf
634:                            new Integer(docFreq), // freq in all docs
635:                            new Integer(tf) });
636:                }
637:                return res;
638:            }
639:
640:            /**
641:             * Describe the parameters that control how the "more like this" query is formed.
642:             */
643:            public String describeParams() {
644:                StringBuffer sb = new StringBuffer();
645:                sb.append("\t" + "maxQueryTerms  : " + maxQueryTerms + "\n");
646:                sb.append("\t" + "minWordLen     : " + minWordLen + "\n");
647:                sb.append("\t" + "maxWordLen     : " + maxWordLen + "\n");
648:                sb.append("\t" + "fieldNames     : ");
649:                String delim = "";
650:                for (int i = 0; i < fieldNames.length; i++) {
651:                    String fieldName = fieldNames[i];
652:                    sb.append(delim).append(fieldName);
653:                    delim = ", ";
654:                }
655:                sb.append("\n");
656:                sb.append("\t" + "boost          : " + boost + "\n");
657:                sb.append("\t" + "minTermFreq    : " + minTermFreq + "\n");
658:                sb.append("\t" + "minDocFreq     : " + minDocFreq + "\n");
659:                return sb.toString();
660:            }
661:
662:            /**
663:             * Test driver.
664:             * Pass in "-i INDEX" and then either "-fn FILE" or "-url URL".
665:             */
666:            public static void main(String[] a) throws Throwable {
667:                String indexName = "localhost_index";
668:                String fn = "c:/Program Files/Apache Group/Apache/htdocs/manual/vhosts/index.html.en";
669:                URL url = null;
670:                for (int i = 0; i < a.length; i++) {
671:                    if (a[i].equals("-i")) {
672:                        indexName = a[++i];
673:                    } else if (a[i].equals("-f")) {
674:                        fn = a[++i];
675:                    } else if (a[i].equals("-url")) {
676:                        url = new URL(a[++i]);
677:                    }
678:                }
679:
680:                PrintStream o = System.out;
681:                IndexReader r = IndexReader.open(indexName);
682:                o.println("Open index " + indexName + " which has "
683:                        + r.numDocs() + " docs");
684:
685:                MoreLikeThis mlt = new MoreLikeThis(r);
686:
687:                o.println("Query generation parameters:");
688:                o.println(mlt.describeParams());
689:                o.println();
690:
691:                Query query = null;
692:                if (url != null) {
693:                    o.println("Parsing URL: " + url);
694:                    query = mlt.like(url);
695:                } else if (fn != null) {
696:                    o.println("Parsing file: " + fn);
697:                    query = mlt.like(new File(fn));
698:                }
699:
700:                o.println("q: " + query);
701:                o.println();
702:                IndexSearcher searcher = new IndexSearcher(indexName);
703:
704:                Hits hits = searcher.search(query);
705:                int len = hits.length();
706:                o.println("found: " + len + " documents matching");
707:                o.println();
708:                for (int i = 0; i < Math.min(25, len); i++) {
709:                    Document d = hits.doc(i);
710:                    String summary = d.get("summary");
711:                    o.println("score  : " + hits.score(i));
712:                    o.println("url    : " + d.get("url"));
713:                    o.println("\ttitle  : " + d.get("title"));
714:                    if (summary != null)
715:                        o.println("\tsummary: " + d.get("summary"));
716:                    o.println();
717:                }
718:            }
719:
720:            /**
721:             * Find words for a more-like-this query former.
722:             *
723:             * @param docNum the id of the lucene document from which to find terms
724:             */
725:            private PriorityQueue retrieveTerms(int docNum) throws IOException {
726:                Map termFreqMap = new HashMap();
727:                for (int i = 0; i < fieldNames.length; i++) {
728:                    String fieldName = fieldNames[i];
729:                    TermFreqVector vector = ir.getTermFreqVector(docNum,
730:                            fieldName);
731:
732:                    // field does not store term vector info
733:                    if (vector == null) {
734:                        Document d = ir.document(docNum);
735:                        String text[] = d.getValues(fieldName);
736:                        if (text != null) {
737:                            for (int j = 0; j < text.length; j++) {
738:                                addTermFrequencies(new StringReader(text[j]),
739:                                        termFreqMap, fieldName);
740:                            }
741:                        }
742:                    } else {
743:                        addTermFrequencies(termFreqMap, vector);
744:                    }
745:
746:                }
747:
748:                return createQueue(termFreqMap);
749:            }
750:
751:            /**
752:             * Adds terms and frequencies found in vector into the Map termFreqMap
753:             * @param termFreqMap a Map of terms and their frequencies
754:             * @param vector List of terms and their frequencies for a doc/field
755:             */
756:            private void addTermFrequencies(Map termFreqMap,
757:                    TermFreqVector vector) {
758:                String[] terms = vector.getTerms();
759:                int freqs[] = vector.getTermFrequencies();
760:                for (int j = 0; j < terms.length; j++) {
761:                    String term = terms[j];
762:
763:                    if (isNoiseWord(term)) {
764:                        continue;
765:                    }
766:                    // increment frequency
767:                    Int cnt = (Int) termFreqMap.get(term);
768:                    if (cnt == null) {
769:                        cnt = new Int();
770:                        termFreqMap.put(term, cnt);
771:                        cnt.x = freqs[j];
772:                    } else {
773:                        cnt.x += freqs[j];
774:                    }
775:                }
776:            }
777:
778:            /**
779:             * Adds term frequencies found by tokenizing text from reader into the Map words
780:             * @param r a source of text to be tokenized
781:             * @param termFreqMap a Map of terms and their frequencies
782:             * @param fieldName Used by analyzer for any special per-field analysis
783:             */
784:            private void addTermFrequencies(Reader r, Map termFreqMap,
785:                    String fieldName) throws IOException {
786:                TokenStream ts = analyzer.tokenStream(fieldName, r);
787:                org.apache.lucene.analysis.Token token;
788:                int tokenCount = 0;
789:                while ((token = ts.next()) != null) { // for every token
790:                    String word = token.termText();
791:                    tokenCount++;
792:                    if (tokenCount > maxNumTokensParsed) {
793:                        break;
794:                    }
795:                    if (isNoiseWord(word)) {
796:                        continue;
797:                    }
798:
799:                    // increment frequency
800:                    Int cnt = (Int) termFreqMap.get(word);
801:                    if (cnt == null) {
802:                        termFreqMap.put(word, new Int());
803:                    } else {
804:                        cnt.x++;
805:                    }
806:                }
807:            }
808:
809:            /** determines if the passed term is likely to be of interest in "more like" comparisons 
810:             * 
811:             * @param term The word being considered
812:             * @return true if should be ignored, false if should be used in further analysis
813:             */
814:            private boolean isNoiseWord(String term) {
815:                int len = term.length();
816:                if (minWordLen > 0 && len < minWordLen) {
817:                    return true;
818:                }
819:                if (maxWordLen > 0 && len > maxWordLen) {
820:                    return true;
821:                }
822:                if (stopWords != null && stopWords.contains(term)) {
823:                    return true;
824:                }
825:                return false;
826:            }
827:
828:            /**
829:             * Find words for a more-like-this query former.
830:             * The result is a priority queue of arrays with one entry for <b>every word</b> in the document.
831:             * Each array has 6 elements.
832:             * The elements are:
833:             * <ol>
834:             * <li> The word (String)
835:             * <li> The top field that this word comes from (String)
836:             * <li> The score for this word (Float)
837:             * <li> The IDF value (Float)
838:             * <li> The frequency of this word in the index (Integer)
839:             * <li> The frequency of this word in the source document (Integer)	 	 
840:             * </ol>
841:             * This is a somewhat "advanced" routine, and in general only the 1st entry in the array is of interest.
842:             * This method is exposed so that you can identify the "interesting words" in a document.
843:             * For an easier method to call see {@link #retrieveInterestingTerms retrieveInterestingTerms()}.
844:             *
845:             * @param r the reader that has the content of the document
846:             * @return the most intresting words in the document ordered by score, with the highest scoring, or best entry, first
847:             *
848:             * @see #retrieveInterestingTerms
849:             */
850:            public PriorityQueue retrieveTerms(Reader r) throws IOException {
851:                Map words = new HashMap();
852:                for (int i = 0; i < fieldNames.length; i++) {
853:                    String fieldName = fieldNames[i];
854:                    addTermFrequencies(r, words, fieldName);
855:                }
856:                return createQueue(words);
857:            }
858:
859:            /**
860:             * Convenience routine to make it easy to return the most interesting words in a document.
861:             * More advanced users will call {@link #retrieveTerms(java.io.Reader) retrieveTerms()} directly.
862:             * @param r the source document
863:             * @return the most interesting words in the document
864:             *
865:             * @see #retrieveTerms(java.io.Reader)
866:             * @see #setMaxQueryTerms
867:             */
868:            public String[] retrieveInterestingTerms(Reader r)
869:                    throws IOException {
870:                ArrayList al = new ArrayList(maxQueryTerms);
871:                PriorityQueue pq = retrieveTerms(r);
872:                Object cur;
873:                int lim = maxQueryTerms; // have to be careful, retrieveTerms returns all words but that's probably not useful to our caller...
874:                // we just want to return the top words
875:                while (((cur = pq.pop()) != null) && lim-- > 0) {
876:                    Object[] ar = (Object[]) cur;
877:                    al.add(ar[0]); // the 1st entry is the interesting word
878:                }
879:                String[] res = new String[al.size()];
880:                return (String[]) al.toArray(res);
881:            }
882:
883:            /**
884:             * PriorityQueue that orders words by score.
885:             */
886:            private static class FreqQ extends PriorityQueue {
887:                FreqQ(int s) {
888:                    initialize(s);
889:                }
890:
891:                protected boolean lessThan(Object a, Object b) {
892:                    Object[] aa = (Object[]) a;
893:                    Object[] bb = (Object[]) b;
894:                    Float fa = (Float) aa[2];
895:                    Float fb = (Float) bb[2];
896:                    return fa.floatValue() > fb.floatValue();
897:                }
898:            }
899:
900:            /**
901:             * Use for frequencies and to avoid renewing Integers.
902:             */
903:            private static class Int {
904:                int x;
905:
906:                Int() {
907:                    x = 1;
908:                }
909:            }
910:
911:        }
www.java2java.com | Contact Us
Copyright 2009 - 12 Demo Source and Support. All rights reserved.
All other trademarks are property of their respective owners.