CODEWITHSUNDEEP
javalucene
Yogesh
Yogesh

Reputation: 4784

PhraseQuery Not working Lucene 4.5.0

I tried to work with PhraseQuery but could not get hits from search. I am using Lucene 4.5.0.

My Indexing code

private IndexWriter writer;

public LuceneIndexSF(final String indexDir) throws IOException {
    Analyzer analyzer = new KeywordAnalyzer();
    IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_45,
            analyzer);
    Directory directory = FSDirectory.open(new File(indexDir));
    writer = new IndexWriter(directory, config);
}
private Document getDocument(File f, String line, int lineNum)
            throws IOException {
        Document doc = new Document();
        Field field = null;
        if (line != null && line.split(DELIMITER).length >= 5) {
            String[] lineValues = line.split(DELIMITER);
            field = new Field("name", line.split("\t")[1],
                    TextField.TYPE_STORED);
            doc.add(field);
            if (lineValues[2] != null && !lineValues[2].trim().isEmpty()) {
                field = new Field("ref", lineValues[2], TextField.TYPE_STORED);
                doc.add(field);
            }
            field = new Field("type", lineValues[3], TextField.TYPE_STORED);
            doc.add(field);
            field = new LongField("code", Long.parseLong(lineValues[4]),
                    LongField.TYPE_STORED);
            doc.add(field);
            if (lineValues.length == 7 && lineValues[5] != null
                    && !lineValues[5].trim().isEmpty()) {
                field = new Field("alias1", lineValues[5],
                        TextField.TYPE_STORED);
                doc.add(field);
            }
            if (lineValues.length == 7 && lineValues[6] != null
                    && !lineValues[6].trim().isEmpty()) {
                field = new Field("alias2", lineValues[6],
                        TextField.TYPE_STORED);
                doc.add(field);
            }
        }
        field = new IntField("linenum", lineNum, IntField.TYPE_STORED);
        doc.add(field);
        return doc;
    }
.... and other code where i add document in writer using writer.addDocument(doc);

My Searching Code

private static void search(String indexDir, String quer) throws IOException,
        ParseException {
    IndexReader inxRead = DirectoryReader.open(FSDirectory.open(new File(
            indexDir)));
    IndexSearcher is = new IndexSearcher(inxRead);
    String[] termArr = quer.split(" ");
    PhraseQuery phraseQuery= new PhraseQuery();
    for(int inx = 0; inx < termArr.length; inx++){
        phraseQuery.add(new Term("name", termArr[inx]));
    }
    phraseQuery.setSlop(4);
    long start = System.currentTimeMillis();
    TopDocs hits = is.search(phraseQuery, 1000);
    long end = System.currentTimeMillis();
    System.err.println("Parser> Found " + hits.totalHits
            + " document(s) (in " + (end - start)
            + " milliseconds) that matched query '" + multiQuery + "':");
    for (ScoreDoc scoreDoc : hits.scoreDocs) {
        Document doc = is.doc(scoreDoc.doc);
        System.out.println("Parser> " + scoreDoc.score + " :: "
                + doc.get("type") + " - " + doc.get("code") + " - "
                + doc.get("name") + ", " + doc.get("linenum"));
    }
    inxRead.close();
}

Please tell me if i am doing any thing wrong.

Edit

also tried with Standard Analyzer still not results

Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_45);

Solution

According to Arun's answer PhraseQuery to work properly requires Analyzer which Tokenize each word in Document's Field for my case i used LowerCaseFilter with making all queries lower case so that it can work without case sensitivity. And used EdgeNGramTokenFilter which for auto completion purposes.

public LuceneIndexSF(final String indexDir) throws IOException {
Analyzer analyzer = new Analyzer() {
        @Override
        protected TokenStreamComponents createComponents(String fieldName,
                java.io.Reader reader) {
            Tokenizer source = new StandardTokenizer(Version.LUCENE_45,
                    reader);
            TokenStream result = new StandardFilter(Version.LUCENE_45,
                    source);
            result = new LowerCaseFilter(Version.LUCENE_45, result);
            result = new EdgeNGramTokenFilter(Version.LUCENE_45, result, 1,
                    20);
            return new TokenStreamComponents(source, result);
        }
    };
IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_45,
        analyzer);
Directory directory = FSDirectory.open(new File(indexDir));
writer = new IndexWriter(directory, config);
}

My final search method

private static void search(String indexDir, String quer) throws IOException,
    ParseException {
IndexReader inxRead = DirectoryReader.open(FSDirectory.open(new File(
        indexDir)));
IndexSearcher is = new IndexSearcher(inxRead);
String[] termArr = quer.split(" ");
PhraseQuery query1 = new PhraseQuery();
PhraseQuery query2 = new PhraseQuery();
PhraseQuery query3 = new PhraseQuery();
for (int inx = 0; inx < termArr.length; inx++) {
    query1.add(new Term(SchoolFinderConstant.ENTITY_NAME,termArr[inx]),inx);
    query2.add(new Term(SchoolFinderConstant.ENTITY_ALIAS1,termArr[inx]),inx);
    query3.add(new Term(SchoolFinderConstant.ENTITY_ALIAS2,termArr[inx]),inx);
}
BooleanQuery mainQuery = new BooleanQuery();
mainQuery.add(query1, Occur.SHOULD);
mainQuery.add(query2, Occur.SHOULD);
mainQuery.add(query3, Occur.SHOULD);
long start = System.currentTimeMillis();
TopDocs hits = is.search(mainQuery, 1000);
long end = System.currentTimeMillis();
System.err.println("Parser> Found " + hits.totalHits
        + " document(s) (in " + (end - start)
        + " milliseconds) that matched query '" + multiQuery + "':");
for (ScoreDoc scoreDoc : hits.scoreDocs) {
    Document doc = is.doc(scoreDoc.doc);
    System.out.println("Parser> " + scoreDoc.score + " :: "
            + doc.get("type") + " - " + doc.get("code") + " - "
            + doc.get("name") + ", " + doc.get("linenum"));
}
inxRead.close();
}

Upvotes: 0

Views: 720

Answers (1)

Arun
Arun

Reputation: 1787

I played with your code with KeywordAnalyzer, obviously it did not work as the KeywordAnalyzer "Tokenizes" the entire stream as a single token. This is useful for data like zip codes, ids, and some product names. http://lucene.apache.org/core/4_5_0/analyzers-common/org/apache/lucene/analysis/core/KeywordAnalyzer.html , for this to work you need to specify entire token without any change.

Then i used WhitespaceAnalyzer it worked and able to find matches for your PhraseQuery. No change to rest of the code. Let me know if this worked for you.

The reason search worked with MultiFieldQueryParser is you are forced to use the analyzer at the time of query which matches to your index. So in short , you need to make sure your index analyzer and query time analyzers are similar.

Upvotes: 1

Related Questions