lucene-java-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Evert Wagenaar <evert.wagen...@gmail.com>
Subject Re: How to get the terms matching a WildCardQuery in Lucene 6.2?
Date Tue, 25 Oct 2016 20:07:32 GMT
Thanks Allison. I will try it.

Let you know if it works.

Evert Wagenaar

Op dinsdag 25 oktober 2016 heeft Allison, Timothy B. <tallison@mitre.org>
het volgende geschreven:

> A WildcardTerm subclasses a MultitermQuery.  If you are using the
> QueryParser, you need to set the rewrite method on the parser.
>
> Try this…and beware of hitting the max BooleanQuery clause limit…and/or
> reset that
>
>
>
> BooleanQuery.setMaxClauseCount(numberBigEnoughForYourNeeds);
>
>
>
> import java.util.HashSet;
> import java.util.Set;
>
> import org.apache.lucene.analysis.Analyzer;
> import org.apache.lucene.analysis.standard.StandardAnalyzer;
> import org.apache.lucene.document.Document;
> import org.apache.lucene.document.Field;
> import org.apache.lucene.document.TextField;
> import org.apache.lucene.index.DirectoryReader;
> import org.apache.lucene.index.IndexReader;
> import org.apache.lucene.index.IndexWriter;
> import org.apache.lucene.index.IndexWriterConfig;
> import org.apache.lucene.index.Term;
> import org.apache.lucene.queryparser.classic.QueryParser;
> import org.apache.lucene.search.IndexSearcher;
> import org.apache.lucene.search.MultiTermQuery;
> import org.apache.lucene.search.Query;
> import org.apache.lucene.search.Weight;
> import org.apache.lucene.store.Directory;
> import org.apache.lucene.store.RAMDirectory;
>
> public class RewriteTest {
>
>
>
>
>     /** Simple command-line based search demo. */
>     public static void main(String[] args) throws Exception {
>         Analyzer analyzer = new StandardAnalyzer();
>         String field = "contents";
>         Directory directory = new RAMDirectory();
>         IndexWriterConfig config = new IndexWriterConfig(analyzer);
>         IndexWriter indexWriter = new IndexWriter(directory, config);
>         for (int i = 0; i < 100; i++) {
>             Document d = new Document();
>             d.add(new TextField(field, "aard00"+i, Field.Store.YES));
>             indexWriter.addDocument(d);
>         }
>         indexWriter.flush();
>         indexWriter.close();
>
>         String queryString = "aard????";
>
>         IndexReader reader = DirectoryReader.open(directory);
>         IndexSearcher searcher = new IndexSearcher(reader);
>
>
>         QueryParser parser = new QueryParser(field, analyzer);
>         parser.setMultiTermRewriteMethod(MultiTermQuery.CONSTANT_SCORE_
> BOOLEAN_REWRITE);
>         Query q = parser.parse(queryString);
>         q = q.rewrite(reader);
>         Set<Term> terms = new HashSet<>();
>         Weight weight = q.createWeight(searcher, false);
>         weight.extractTerms(terms);
>         for (Term t : terms) {
>             System.out.println(t);
>         }
>         reader.close();
>     }
>
> }
>
>
> From: Evert Wagenaar [mailto:evert.wagenaar@gmail.com <javascript:;>]
> Sent: Tuesday, October 25, 2016 1:42 PM
> To: java-user@lucene.apache.org <javascript:;>
> Subject: Re: How to get the terms matching a WildCardQuery in Lucene 6.2?
>
> Hi Allison,
>
> Unfortunately I can't compile the code (see below). Can you tell me what's
> wrong?
> I tried both MultiTermQuery.SCORING_BOOLEAN_REWRITE and
> CONSTANT_SCORE_BOOLEAN_REWRITE
>
> What I don't understand actually is the relation between my Query (which
> is a wildcard Query and not a MultiTermQuery.
>
> Can you explain?
>
> Thanks,
>
> Evert Wagenaar
>
>
> [Inline image 1]
>
> Full code of Searcher:
>
>
> package tk.evertwagenaar.lucene;
>
>
>
> import java.io.BufferedReader;
>
> import java.io.IOException;
>
> import java.io.InputStreamReader;
>
> import java.nio.charset.StandardCharsets;
>
> import java.nio.file.Files;
>
> import java.nio.file.Paths;
>
> import java.util.Date;
>
> import java.util.HashSet;
>
> import java.util.Set;
>
>
>
> import org.apache.lucene.analysis.Analyzer;
>
> import org.apache.lucene.analysis.standard.StandardAnalyzer;
>
> import org.apache.lucene.document.Document;
>
> import org.apache.lucene.index.DirectoryReader;
>
> import org.apache.lucene.index.IndexReader;
>
> import org.apache.lucene.index.Term;
>
> import org.apache.lucene.queryparser.classic.QueryParser;
>
> import org.apache.lucene.search.IndexSearcher;
>
> import org.apache.lucene.search.MultiTermQuery;
>
> import org.apache.lucene.search.Query;
>
> import org.apache.lucene.search.ScoreDoc;
>
> import org.apache.lucene.search.TopDocs;
>
> import org.apache.lucene.search.Weight;
>
> import org.apache.lucene.store.FSDirectory;
>
>
>
> /** Simple command-line based search demo. */
>
> public class SearchFiles {
>
>
>
>        private static IndexReader reader;
>
>        private static Query q;
>
>
>
>        private SearchFiles() {
>
>        }
>
>
>
>        /** Simple command-line based search demo. */
>
>        public static void main(String[] args) throws Exception {
>
>               String usage = "Usage:\tjava org.apache.lucene.demo.SearchFiles
> [-index dir] [-field f] [-repeat n] [-queries file] [-query string] [-raw]
> [-paging hitsPerPage]\n\nSee http://lucene.apache.org/core/4_1_0/demo/
> for details.";
>
>               if (args.length > 0 && ("-h".equals(args[0]) ||
> "-help".equals(args[0]))) {
>
>                      System.out.println(usage);
>
>                      System.exit(0);
>
>               }
>
>
>
>               String index = "index";
>
>               String field = "contents";
>
>               String queries = null;
>
>               int repeat = 0;
>
>               boolean raw = false;
>
>               String queryString = "aard????";
>
>               int hitsPerPage = 10;
>
>
>
>               reader = DirectoryReader.open(FSDirectory.open(Paths.get(
> index)));
>
>               IndexSearcher searcher = new IndexSearcher(reader);
>
>               Analyzer analyzer = new StandardAnalyzer();
>
>
>
>               BufferedReader in = null;
>
>
>
>               QueryParser parser = new QueryParser(field, analyzer);
>
>               while (true) {
>
>                      if (queries == null && queryString == null) { //
> prompt the user
>
>                             System.out.println("Enter query: ");
>
>                      }
>
>
>
>                      Query q = parser.parse(queryString);
>
>                      System.out.println("Searching for: " +
> q.toString(field));
>
>
>
>                      if (repeat > 0) { // repeat & time as benchmark
>
>                             Date start = new Date();
>
>                             for (int i = 0; i < repeat; i++) {
>
>                                    searcher.search(q, 100);
>
>                             }
>
>                             Date end = new Date();
>
>                             System.out.println("Time: " + (end.getTime() -
> start.getTime()) + "ms");
>
>                             doPagingSearch(in, searcher, q, hitsPerPage,
> raw, queries == null && queryString == null);
>
>
>
>
>
>                      MultiTermQuery.CONSTANT_SCORE_BOOLEAN_REWRITE
>
>
>
>                             q = q.rewrite(reader);
>
>                             Set<Term> terms = new HashSet<>();
>
>                             Weight weight = q.createWeight(searcher,
> false);
>
>                             terms = weight.extractTerms(terms);
>
>
>
>                             System.out.println("Match: " + terms);
>
>                             reader.close();
>
>
>
>                      }
>
>               }
>
>        }
>
>
>
>        /**
>
>        * Search the Query against the Index
>
>        */
>
>        public static void doPagingSearch(BufferedReader in, IndexSearcher
> searcher, Query query, int hitsPerPage,
>
>                      boolean raw, boolean interactive) throws IOException {
>
>
>
>               // Collect enough docs to show 5 pages
>
>               TopDocs results = searcher.search(query, 5 * hitsPerPage);
>
>               ScoreDoc[] hits = results.scoreDocs;
>
>
>
>               int numTotalHits = results.totalHits;
>
>               System.out.println(numTotalHits + " total matching
> documents");
>
>
>
>               int start = 0;
>
>               int end = Math.min(numTotalHits, hitsPerPage);
>
>
>
>               hits = searcher.search(query, numTotalHits).scoreDocs;
>
>               end = Math.min(hits.length, start + hitsPerPage);
>
>
>
>               for (int i = start; i < end; i++) {
>
>                      Document doc = searcher.doc(hits[i].doc);
>
>                      String path = doc.get("path");
>
>                      System.out.println((i + 1) + ". " + path);
>
>                      query.rewrite(reader);
>
>               }
>
>        }
>
> }
> Evert  Wagenaar
>
> On Tue, Oct 25, 2016 at 1:58 AM, Evert Wagenaar <evert.wagenaar@gmail.com
> <javascript:;><mailto:evert.wagenaar@gmail.com <javascript:;>>>
wrote:
> Thanks Allison. I will try it.
>
>
> Op maandag 24 oktober 2016 heeft Allison, Timothy B. <tallison@mitre.org
> <javascript:;><mailto:tallison@mitre.org <javascript:;>>> het volgende
> geschreven:
> Make sure to setRewriteMethod on the MultiTermQuery to:
>  MultiTermQuery.SCORING_BOOLEAN_REWRITE or CONSTANT_SCORE_BOOLEAN_REWRITE
>
> Then something like this should work:
>
>         q = q.rewrite(reader);
>
>         Set<Term> terms = new HashSet<>();
>         Weight weight = q.createWeight(searcher, false);
>
>         weight.extractTerms(terms);
>
>
>
> -----Original Message-----
> From: Evert Wagenaar [mailto:evert.wagenaar@gmail.com <javascript:;>]
> Sent: Monday, October 24, 2016 12:41 PM
> To: java-user@lucene.apache.org <javascript:;>
> Subject: How to get the terms matching a WildCardQuery in Lucene 6.2?
>
> I already asked this on StackOverflow. Unfortunately without any answer
> for over a week now.
>
> Therefore again to the real experts:
>
>
> I downloaded a list of 350.000 English words in a .txt file and Indexed it
> using the latest Lucene (6.2). I want to apply wildcard queries like
> aard???? and then retreive a list of matches.
>
> I've done this before in an older version of Lucene. Here it was pretty
> simple. I just had to do a Query.rewrite() and this retuned what I needed.
> Unfortunately in 6.2 this doesn't work anymore. There is a
> Query.rewrite(Indexreader reader) which should return a HashMap of Terms.
> In my case there's only one matching Term (aardvark). The Searcher returns
> one hit, containing the Document path to the wordlist. The HashMap is
> however empty.
>
> When I change the Query to find more then one single match (like aa*) the
> HashMap remains empty.
>
> I tried the MatchExtractor too. Unfortunately without result.
>
> The Objective of this is to demonstrate the power of Lucene to easily find
> words of a particular length, given one or more characters. I'm pretty sure
> I can do this using regular expressions in Java but then it's outside my
> objective.
>
> Can anyone tell me why this isn't working? I use the StandardAnalyzer.
> Should I use a different Application?
>
> Any help is greatly appreciated.
>
> Thanks.
>
>
>
> --
> Sent from Gmail IPad
>
>
> --
> Sent from Gmail IPad
>
>

-- 
Sent from Gmail IPad

Mime
  • Unnamed multipart/alternative (inline, None, 0 bytes)
View raw message