Example usage for org.apache.lucene.index Term Term

Introduction

In this page you can find the example usage for org.apache.lucene.index Term Term.

Prototype

public Term(String fld, String text)

Source Link

Document

Constructs a Term with the given field and text.

Usage

From source file:SimpleNaiveBayesClassifier.java

License:Apache License

/**
 * Calculate probabilities for all classes for a given input text
 * @param inputDocument the input text as a {@code String}
 * @return a {@code List} of {@code ClassificationResult}, one for each existing class
 * @throws IOException if assigning probabilities fails
 *///from  w  ww  .j  ava2 s .  c  om
protected List<ClassificationResult<BytesRef>> assignClassNormalizedList(String inputDocument)
        throws IOException {
    List<ClassificationResult<BytesRef>> assignedClasses = new ArrayList<>();

    Terms classes = MultiFields.getTerms(leafReader, classFieldName);
    TermsEnum classesEnum = classes.iterator();
    BytesRef next;
    String[] tokenizedText = tokenize(inputDocument);
    int docsWithClassSize = countDocsWithClass();
    while ((next = classesEnum.next()) != null) {
        if (next.length > 0) {
            Term term = new Term(this.classFieldName, next);
            double clVal = calculateLogPrior(term, docsWithClassSize)
                    + calculateLogLikelihood(tokenizedText, term, docsWithClassSize);
            assignedClasses.add(new ClassificationResult<>(term.bytes(), clVal));
        }
    }

    // normalization; the values transforms to a 0-1 range
    return normClassificationResults(assignedClasses);
}

From source file:SimpleNaiveBayesClassifier.java

License:Apache License

/**
 * count the number of documents in the index having at least a value for the 'class' field
 *
 * @return the no. of documents having a value for the 'class' field
 * @throws IOException if accessing to term vectors or search fails
 *//*from   www  .  ja va  2s. co m*/
protected int countDocsWithClass() throws IOException {
    int docCount = MultiFields.getTerms(this.leafReader, this.classFieldName).getDocCount();
    if (docCount == -1) { // in case codec doesn't support getDocCount
        TotalHitCountCollector classQueryCountCollector = new TotalHitCountCollector();
        BooleanQuery.Builder q = new BooleanQuery.Builder();
        q.add(new BooleanClause(
                new WildcardQuery(new Term(classFieldName, String.valueOf(WildcardQuery.WILDCARD_STRING))),
                BooleanClause.Occur.MUST));
        if (query != null) {
            q.add(query, BooleanClause.Occur.MUST);
        }
        indexSearcher.search(q.build(), classQueryCountCollector);
        docCount = classQueryCountCollector.getTotalHits();
    }
    return docCount;
}

From source file:SimpleNaiveBayesClassifier.java

License:Apache License

/**
 * Returns the number of documents of the input class ( from the whole index or from a subset)
 * that contains the word ( in a specific field or in all the fields if no one selected)
 * @param word the token produced by the analyzer
 * @param term the term representing the class
 * @return the number of documents of the input class
 * @throws IOException if a low level I/O problem happens
 *//*w  w  w  .  j  a  v a  2s .  c o  m*/
private int getWordFreqForClass(String word, Term term) throws IOException {
    BooleanQuery.Builder booleanQuery = new BooleanQuery.Builder();
    BooleanQuery.Builder subQuery = new BooleanQuery.Builder();
    for (String textFieldName : textFieldNames) {
        subQuery.add(
                new BooleanClause(new TermQuery(new Term(textFieldName, word)), BooleanClause.Occur.SHOULD));
    }
    booleanQuery.add(new BooleanClause(subQuery.build(), BooleanClause.Occur.MUST));
    booleanQuery.add(new BooleanClause(new TermQuery(term), BooleanClause.Occur.MUST));
    if (query != null) {
        booleanQuery.add(query, BooleanClause.Occur.MUST);
    }
    TotalHitCountCollector totalHitCountCollector = new TotalHitCountCollector();
    indexSearcher.search(booleanQuery.build(), totalHitCountCollector);
    return totalHitCountCollector.getTotalHits();
}

From source file:ContentBasedAnalysis.java

License:Apache License

private static int findDocId(IndexSearcher searcher, String filename) throws Exception {
    Term t = new Term("path", filename);
    Query q = new TermQuery(t);
    TopDocs td = searcher.search(q, 2);/*from  www.j  a v  a2s.c  om*/
    if (td.totalHits < 1)
        return -1;
    else
        return td.scoreDocs[0].doc;
}

From source file:ContentBasedAnalysis.java

License:Apache License

private static int docFreq(IndexReader reader, String s) throws Exception {
    return reader.docFreq(new Term("contents", s));
}

From source file:SearcherTest.java

/**
 * ?/*from  ww  w  .  j  a v a2s .c o m*/
 * ???TermQuery
 * TermQuery??QueryTermQuery???????
 * ??????TermQuery??
 * Lucene??????????/
 * ??????????
 *
 * @throws Exception
 */
@Test
public void testTermQuery() throws Exception {
    String searchField = "contents";
    String q = "xxxxxxxxx$";
    Term t = new Term(searchField, q);
    Query query = new TermQuery(t);
    TopDocs hits = is.search(query, 10);
    System.out.println("? '" + q + "'" + hits.totalHits + "");
    for (ScoreDoc scoreDoc : hits.scoreDocs) {
        Document doc = is.doc(scoreDoc.doc);
        System.out.println(doc.get("fullPath"));
    }
}

From source file:SearcherTest.java

/**
 * ???BooleanQuery/*from   ww  w  . j av a  2  s  . co  m*/
 * BooleanQuery???Query
 * ?Query???Query
 * ?BooleanQuery??
 * BooleanQuery?????API??
 * ?BooleanQuery????API?
 *
 * @throws Exception
 */
@Test
public void testBooleanQuery() throws Exception {
    String searchField = "contents";
    String q1 = "xxxxxxxxx";
    String q2 = "oooooooooooooooo";
    Query query1 = new TermQuery(new Term(searchField, q1));
    Query query2 = new TermQuery(new Term(searchField, q2));
    BooleanQuery.Builder builder = new BooleanQuery.Builder();
    //  1MUSTMUST???
    //  2MUSTMUST_NOT??MUST_NOT??
    // 3SHOULDMUST_NOT?MUSTMUST_NOT
    // 4SHOULDMUSTMUST??,SHOULD???
    // 5SHOULDSHOULD???
    // 6MUST_NOTMUST_NOT?
    builder.add(query1, BooleanClause.Occur.MUST);
    builder.add(query2, BooleanClause.Occur.MUST);
    BooleanQuery booleanQuery = builder.build();
    TopDocs hits = is.search(booleanQuery, 10);
    System.out.println("? " + q1 + "And" + q2 + "" + hits.totalHits + "");
    for (ScoreDoc scoreDoc : hits.scoreDocs) {
        Document doc = is.doc(scoreDoc.doc);
        System.out.println(doc.get("fullPath"));
    }
}

From source file:SearcherTest.java

/**
 * PrefixQuery  PrefixQuery?xxx%//from w  w w.j ava 2 s. c  o  m
 *
 * @throws Exception
 */
@Test
public void testPrefixQuery() throws Exception {
    String searchField = "contents";
    String q = "1license";
    Term t = new Term(searchField, q);
    Query query = new PrefixQuery(t);
    TopDocs hits = is.search(query, 10);
    System.out.println("? '" + q + "'" + hits.totalHits + "");

    for (ScoreDoc scoreDoc : hits.scoreDocs) {
        Document doc = is.doc(scoreDoc.doc);
        System.out.println(doc.get("fullPath"));
    }
}

From source file:SearcherTest.java

/**
 * PhraseQuery?big car?/*www  .j a v  a2s .  com*/
 * ?document?"big car"
 * document???????big black car?
 * ????slop
 * slopslop???
 *
 * @throws Exception
 */
@Test
public void testPhraseQuery() throws Exception {
    String searchField = "contents";
    String q1 = "xxxx";
    String q2 = "bbb";
    Term t1 = new Term(searchField, q1);
    Term t2 = new Term(searchField, q2);
    PhraseQuery.Builder builder = new PhraseQuery.Builder();
    builder.add(t1);
    builder.add(t2);
    builder.setSlop(0);
    PhraseQuery query = builder.build();
    TopDocs hits = is.search(query, 10);
    System.out.println("? '" + q1 + q2 + "" + "" + hits.totalHits
            + "");

    for (ScoreDoc scoreDoc : hits.scoreDocs) {
        Document doc = is.doc(scoreDoc.doc);
        System.out.println(doc.get("fullPath"));
    }
}

From source file:SearcherTest.java

/**
 * ??FuzzyQuery/*from  ww  w.  ja v  a  2  s  .co m*/
 * FuzzyQuery????
 *
 * @throws Exception
 */
@Test
public void testFuzzyQuery() throws Exception {
    String searchField = "contents";
    String q = "ljlxx";
    Term t = new Term(searchField, q);
    Query query = new FuzzyQuery(t);
    TopDocs hits = is.search(query, 10);
    System.out.println("? '" + q + "'" + hits.totalHits + "");

    for (ScoreDoc scoreDoc : hits.scoreDocs) {
        Document doc = is.doc(scoreDoc.doc);
        System.out.println(doc.get("fullPath"));
    }
}