org.apache.lucene.index.SegmentReader#maxDoc ( )源码实例Demo

/**
 * Gets the live docs.
 *
 * @param indexReader the index reader
 * @return the live docs
 */
private static ArrayList<Integer> getLiveDocs(IndexReader indexReader) {
  ArrayList<Integer> list = new ArrayList<>();
  ListIterator<LeafReaderContext> iterator = indexReader.leaves()
      .listIterator();
  while (iterator.hasNext()) {
    LeafReaderContext lrc = iterator.next();
    SegmentReader r = (SegmentReader) lrc.reader();
    for (int docId = 0; docId < r.maxDoc(); docId++) {
      if (r.numDocs() == r.maxDoc() || r.getLiveDocs().get(docId)) {
        list.add(lrc.docBase + docId);
      }
    }
  }
  return list;
}
 

private long doCountResults(IndexSearcher searcher,
    SearchQueryRequest aRequest, MtasSpanQuery q) throws IOException
{
    ListIterator<LeafReaderContext> leafReaderContextIterator = searcher.getIndexReader()
            .leaves().listIterator();

    Map<Long, Long> annotatableDocuments = listAnnotatableDocuments(aRequest.getProject(),
        aRequest.getUser());

    final float boost = 0;
    SpanWeight spanweight = q.rewrite(searcher.getIndexReader()).createWeight(searcher, false,
            boost);

    long numResults = 0;

    while (leafReaderContextIterator.hasNext()) {
        LeafReaderContext leafReaderContext = leafReaderContextIterator.next();
        try {
            Spans spans = spanweight.getSpans(leafReaderContext, SpanWeight.Postings.POSITIONS);
            SegmentReader segmentReader = (SegmentReader) leafReaderContext.reader();
            if (spans != null) {
                while (spans.nextDoc() != Spans.NO_MORE_DOCS) {
                    if (segmentReader.numDocs() == segmentReader.maxDoc()
                            || segmentReader.getLiveDocs().get(spans.docID())) {
                        Document document = segmentReader.document(spans.docID());

                        // Retrieve user
                        String user = document.get(FIELD_USER);

                        // Retrieve source and annotation document ids
                        String rawSourceDocumentId = document.get(FIELD_SOURCE_DOCUMENT_ID);
                        String rawAnnotationDocumentId = document
                                .get(FIELD_ANNOTATION_DOCUMENT_ID);
                        if (rawSourceDocumentId == null || rawAnnotationDocumentId == null) {
                            log.trace("Indexed document lacks source/annotation document IDs"
                                    + " - source: {}, annotation: {}", rawSourceDocumentId,
                                rawAnnotationDocumentId);
                            continue;

                        }
                        long sourceDocumentId = Long.valueOf(rawSourceDocumentId);
                        long annotationDocumentId = Long.valueOf(rawAnnotationDocumentId);

                        // If the query is limited to a given document, skip any results
                        // which are not in the given document
                        Optional<SourceDocument> limitedToDocument = aRequest
                                .getLimitedToDocument();
                        if (limitedToDocument.isPresent() && !Objects
                            .equals(limitedToDocument.get().getId(), sourceDocumentId)) {
                            log.trace("Query limited to document {}, skipping results for "
                                    + "document {}", limitedToDocument.get().getId(),
                                sourceDocumentId);
                            continue;
                        }

                        if (annotatableDocuments.containsKey(sourceDocumentId)
                            && annotationDocumentId == -1) {
                            // Exclude result if the retrieved document is a sourcedocument
                            // (that is, has annotationDocument = -1) AND it has a
                            // corresponding annotation document for this user
                            log.trace("Skipping results from indexed source document {} in" 
                                + "favor of results from the corresponding annotation "
                                + "document", sourceDocumentId);
                            continue;
                        }
                        else if (annotationDocumentId != -1 && !aRequest.getUser().getUsername()
                            .equals(user)) {
                            // Exclude result if the retrieved document is an annotation
                            // document (that is, annotationDocument != -1 and its username
                            // is different from the quering user
                            log.trace("Skipping results from annotation document for user {} "
                                    + "which does not match the requested user {}", user,
                                aRequest.getUser().getUsername());
                            continue;
                        }

                        while (spans.nextStartPosition() != Spans.NO_MORE_POSITIONS) {
                            numResults++;
                        }
                    }
                }
            }
        }
        catch (Exception e) {
            log.error("Unable to process query results", e);
            numResults = -1;
        }
    }
    return numResults;
}
 

private static void doQuery(IndexReader indexReader, String field, MtasSpanQuery q,
        List<String> prefixes)
    throws IOException
{
    ListIterator<LeafReaderContext> iterator = indexReader.leaves().listIterator();
    IndexSearcher searcher = new IndexSearcher(indexReader);
    final float boost = 0;
    SpanWeight spanweight = q.rewrite(indexReader).createWeight(searcher, false, boost);

    while (iterator.hasNext()) {
        System.out.println("#### new iteration ####");
        LeafReaderContext lrc = iterator.next();
        Spans spans = spanweight.getSpans(lrc, SpanWeight.Postings.POSITIONS);
        SegmentReader segmentReader = (SegmentReader) lrc.reader();
        Terms terms = segmentReader.terms(field);
        CodecInfo mtasCodecInfo = CodecInfo.getCodecInfoFromTerms(terms);
        if (spans != null) {
            while (spans.nextDoc() != Spans.NO_MORE_DOCS) {
                if (segmentReader.numDocs() == segmentReader.maxDoc()
                        || segmentReader.getLiveDocs().get(spans.docID())) {
                    String idValue = segmentReader.document(spans.docID()).getField(FIELD_ID)
                            .stringValue();
                    System.out.println("********  New doc " + spans.docID() + "-" + idValue);
                    while (spans.nextStartPosition() != Spans.NO_MORE_POSITIONS) {
                        System.out.println("------");
                        List<MtasTokenString> tokens = mtasCodecInfo
                                .getPrefixFilteredObjectsByPositions(field, spans.docID(),
                                        prefixes, spans.startPosition(),
                                        (spans.endPosition() - 1));
                        for (MtasTokenString token : tokens) {
                            System.out.print("docId: " + (lrc.docBase + spans.docID()) + ", ");
                            System.out.print(" position: " + token.getPositionStart()
                                    + (!Objects.equals(token.getPositionEnd(),
                                            token.getPositionStart())
                                                    ? "-" + token.getPositionEnd()
                                                    : ""));
                            System.out.print(" offset: " + token.getOffsetStart() + "-"
                                    + token.getOffsetEnd());
                            System.out.print(" mtasId: " + token.getId());
                            System.out.println(" " + token.getPrefix()
                                    + (token.getPostfix() != null ? ":" + token.getPostfix()
                                            : "")
                                    + ", ");
                        }
                        System.out.println("------");
                        List<MtasTreeHit<String>> hits = mtasCodecInfo
                                .getPositionedTermsByPrefixesAndPositionRange(field,
                                        spans.docID(), prefixes, spans.startPosition(),
                                        (spans.endPosition() - 1));
                        for (MtasTreeHit<String> hit : hits) {
                            System.out.print("docId: " + (lrc.docBase + spans.docID()) + ", ");
                            System.out.print("position: " + hit.startPosition
                                    + (hit.endPosition != hit.startPosition
                                            ? "-" + hit.endPosition
                                            : ""));
                            System.out.println(" " + CodecUtil.termPrefix(hit.data)
                                    + (CodecUtil.termValue(hit.data) != null
                                            ? ":" + CodecUtil.termValue(hit.data)
                                            : "")
                                    + ", ");
                        }
                    }
                    // if (prefixes != null && !prefixes.isEmpty()) {
                    // }
                }
            }
        }
    }
}