Examples with TotalHitCountCollector org.apache.lucene.search.TotalHitCountCollector used on opensource projects

Example 16 with TotalHitCountCollector

use of org.apache.lucene.search.TotalHitCountCollector in project lucene-solr by apache.

the class SimpleNaiveBayesClassifier method getWordFreqForClass.

/**
   * 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
   */
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();
}

Example 17 with TotalHitCountCollector

use of org.apache.lucene.search.TotalHitCountCollector in project lucene-solr by apache.

the class SimpleNaiveBayesClassifier method countDocsWithClass.

/**
   * 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
   */
protected int countDocsWithClass() throws IOException {
    Terms terms = MultiFields.getTerms(this.indexReader, this.classFieldName);
    int docCount;
    if (terms == null || terms.getDocCount() == -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();
    } else {
        docCount = terms.getDocCount();
    }
    return docCount;
}

Example 18 with TotalHitCountCollector

use of org.apache.lucene.search.TotalHitCountCollector in project lucene-solr by apache.

the class FacetsCollector method doSearch.

private static TopDocs doSearch(IndexSearcher searcher, ScoreDoc after, Query q, int n, Sort sort, boolean doDocScores, boolean doMaxScore, Collector fc) throws IOException {
    int limit = searcher.getIndexReader().maxDoc();
    if (limit == 0) {
        limit = 1;
    }
    n = Math.min(n, limit);
    if (after != null && after.doc >= limit) {
        throw new IllegalArgumentException("after.doc exceeds the number of documents in the reader: after.doc=" + after.doc + " limit=" + limit);
    }
    TopDocs topDocs = null;
    if (n == 0) {
        TotalHitCountCollector totalHitCountCollector = new TotalHitCountCollector();
        searcher.search(q, MultiCollector.wrap(totalHitCountCollector, fc));
        topDocs = new TopDocs(totalHitCountCollector.getTotalHits(), new ScoreDoc[0], Float.NaN);
    } else {
        TopDocsCollector<?> hitsCollector;
        if (sort != null) {
            if (after != null && !(after instanceof FieldDoc)) {
                // remove this
                throw new IllegalArgumentException("after must be a FieldDoc; got " + after);
            }
            boolean fillFields = true;
            hitsCollector = TopFieldCollector.create(sort, n, (FieldDoc) after, fillFields, doDocScores, doMaxScore);
        } else {
            hitsCollector = TopScoreDocCollector.create(n, after);
        }
        searcher.search(q, MultiCollector.wrap(hitsCollector, fc));
        topDocs = hitsCollector.topDocs();
    }
    return topDocs;
}

Example 19 with TotalHitCountCollector

use of org.apache.lucene.search.TotalHitCountCollector in project lucene-solr by apache.

the class TestJoinUtil method testMinMaxDocs.

public void testMinMaxDocs() throws Exception {
    Directory dir = newDirectory();
    RandomIndexWriter iw = new RandomIndexWriter(random(), dir, newIndexWriterConfig(new MockAnalyzer(random(), MockTokenizer.KEYWORD, false)));
    int minChildDocsPerParent = 2;
    int maxChildDocsPerParent = 16;
    int numParents = RandomNumbers.randomIntBetween(random(), 16, 64);
    int[] childDocsPerParent = new int[numParents];
    for (int p = 0; p < numParents; p++) {
        String parentId = Integer.toString(p);
        Document parentDoc = new Document();
        parentDoc.add(new StringField("id", parentId, Field.Store.YES));
        parentDoc.add(new StringField("type", "to", Field.Store.NO));
        parentDoc.add(new SortedDocValuesField("join_field", new BytesRef(parentId)));
        iw.addDocument(parentDoc);
        int numChildren = RandomNumbers.randomIntBetween(random(), minChildDocsPerParent, maxChildDocsPerParent);
        childDocsPerParent[p] = numChildren;
        for (int c = 0; c < numChildren; c++) {
            String childId = Integer.toString(p + c);
            Document childDoc = new Document();
            childDoc.add(new StringField("id", childId, Field.Store.YES));
            childDoc.add(new StringField("type", "from", Field.Store.NO));
            childDoc.add(new SortedDocValuesField("join_field", new BytesRef(parentId)));
            iw.addDocument(childDoc);
        }
    }
    iw.close();
    IndexSearcher searcher = new IndexSearcher(DirectoryReader.open(dir));
    SortedDocValues[] values = new SortedDocValues[searcher.getIndexReader().leaves().size()];
    for (LeafReaderContext leadContext : searcher.getIndexReader().leaves()) {
        values[leadContext.ord] = DocValues.getSorted(leadContext.reader(), "join_field");
    }
    MultiDocValues.OrdinalMap ordinalMap = MultiDocValues.OrdinalMap.build(null, values, PackedInts.DEFAULT);
    Query fromQuery = new TermQuery(new Term("type", "from"));
    Query toQuery = new TermQuery(new Term("type", "to"));
    int iters = RandomNumbers.randomIntBetween(random(), 3, 9);
    for (int i = 1; i <= iters; i++) {
        final ScoreMode scoreMode = ScoreMode.values()[random().nextInt(ScoreMode.values().length)];
        int min = RandomNumbers.randomIntBetween(random(), minChildDocsPerParent, maxChildDocsPerParent - 1);
        int max = RandomNumbers.randomIntBetween(random(), min, maxChildDocsPerParent);
        if (VERBOSE) {
            System.out.println("iter=" + i);
            System.out.println("scoreMode=" + scoreMode);
            System.out.println("min=" + min);
            System.out.println("max=" + max);
        }
        Query joinQuery = JoinUtil.createJoinQuery("join_field", fromQuery, toQuery, searcher, scoreMode, ordinalMap, min, max);
        TotalHitCountCollector collector = new TotalHitCountCollector();
        searcher.search(joinQuery, collector);
        int expectedCount = 0;
        for (int numChildDocs : childDocsPerParent) {
            if (numChildDocs >= min && numChildDocs <= max) {
                expectedCount++;
            }
        }
        assertEquals(expectedCount, collector.getTotalHits());
    }
    searcher.getIndexReader().close();
    dir.close();
}

Example 20 with TotalHitCountCollector

use of org.apache.lucene.search.TotalHitCountCollector in project lucene-solr by apache.

the class CommandHandler method searchWithTimeLimiter.

/**
   * Invokes search with the specified filter and collector.  
   * If a time limit has been specified then wrap the collector in the TimeLimitingCollector
   */
private void searchWithTimeLimiter(Query query, ProcessedFilter filter, Collector collector) throws IOException {
    if (queryCommand.getTimeAllowed() > 0) {
        collector = new TimeLimitingCollector(collector, TimeLimitingCollector.getGlobalCounter(), queryCommand.getTimeAllowed());
    }
    TotalHitCountCollector hitCountCollector = new TotalHitCountCollector();
    if (includeHitCount) {
        collector = MultiCollector.wrap(collector, hitCountCollector);
    }
    if (filter.filter != null) {
        query = new BooleanQuery.Builder().add(query, Occur.MUST).add(filter.filter, Occur.FILTER).build();
    }
    if (filter.postFilter != null) {
        filter.postFilter.setLastDelegate(collector);
        collector = filter.postFilter;
    }
    try {
        searcher.search(query, collector);
    } catch (TimeLimitingCollector.TimeExceededException | ExitableDirectoryReader.ExitingReaderException x) {
        partialResults = true;
        logger.warn("Query: " + query + "; " + x.getMessage());
    }
    if (includeHitCount) {
        totalHitCount = hitCountCollector.getTotalHits();
    }
}