Example usage for org.apache.lucene.search IndexSearcher getIndexReader

Introduction

In this page you can find the example usage for org.apache.lucene.search IndexSearcher getIndexReader.

Prototype

public IndexReader getIndexReader() 

Source Link

Document

Return the IndexReader this searches.

Usage

From source file:org.apache.zeppelin.search.LuceneSearch.java

License:Apache License

private List<Map<String, String>> doSearch(IndexSearcher searcher, Query query, Analyzer analyzer,
        Highlighter highlighter) {
    List<Map<String, String>> matchingParagraphs = Lists.newArrayList();
    ScoreDoc[] hits;//  w ww .  j ava 2s.c  o  m
    try {
        hits = searcher.search(query, 20).scoreDocs;
        for (int i = 0; i < hits.length; i++) {
            logger.debug("doc={} score={}", hits[i].doc, hits[i].score);

            int id = hits[i].doc;
            Document doc = searcher.doc(id);
            String path = doc.get(ID_FIELD);
            if (path != null) {
                logger.debug((i + 1) + ". " + path);
                String title = doc.get("title");
                if (title != null) {
                    logger.debug("   Title: {}", doc.get("title"));
                }

                String text = doc.get(SEARCH_FIELD_TEXT);
                String header = doc.get(SEARCH_FIELD_TITLE);
                String fragment = "";

                if (text != null) {
                    TokenStream tokenStream = TokenSources.getTokenStream(searcher.getIndexReader(), id,
                            SEARCH_FIELD_TEXT, analyzer);
                    TextFragment[] frag = highlighter.getBestTextFragments(tokenStream, text, true, 3);
                    logger.debug("    {} fragments found for query '{}'", frag.length, query);
                    for (int j = 0; j < frag.length; j++) {
                        if ((frag[j] != null) && (frag[j].getScore() > 0)) {
                            logger.debug("    Fragment: {}", frag[j].toString());
                        }
                    }
                    fragment = (frag != null && frag.length > 0) ? frag[0].toString() : "";
                }

                if (header != null) {
                    TokenStream tokenTitle = TokenSources.getTokenStream(searcher.getIndexReader(), id,
                            SEARCH_FIELD_TITLE, analyzer);
                    TextFragment[] frgTitle = highlighter.getBestTextFragments(tokenTitle, header, true, 3);
                    header = (frgTitle != null && frgTitle.length > 0) ? frgTitle[0].toString() : "";
                } else {
                    header = "";
                }
                matchingParagraphs.add(ImmutableMap.of("id", path, // <noteId>/paragraph/<paragraphId>
                        "name", title, "snippet", fragment, "text", text, "header", header));
            } else {
                logger.info("{}. No {} for this document", i + 1, ID_FIELD);
            }
        }
    } catch (IOException | InvalidTokenOffsetsException e) {
        logger.error("Exception on searching for {}", query, e);
    }
    return matchingParagraphs;
}

---

From source file:org.arastreju.sge.index.ArastrejuIndex.java

License:Apache License

public void dump() {
    ContextIndex index = provider.forContext(conversationContext.getPrimaryContext());
    org.apache.lucene.search.IndexSearcher searcher = index.getSearcher();
    IndexReader reader = searcher.getIndexReader();

    try {//from  ww w.  j ava2  s. co  m
        TopDocs top = searcher.search(new MatchAllDocsQuery(), 100);
        for (int i = 0; i < top.totalHits; i++) {
            Document doc = reader.document(top.scoreDocs[i].doc);
            LOGGER.info("---Document--- id: " + top.scoreDocs[i].doc);
            List<Fieldable> fields = doc.getFields();
            for (Fieldable f : fields) {
                LOGGER.info("\tField: name='" + f.name() + "', val='" + f.stringValue() + "'");
            }

        }
    } catch (IOException e) {
        String msg = "caught IOException while dumping index";
        LOGGER.error(msg, e);
        throw new RuntimeException(msg, e);
    }
}

---

From source file:org.carrot2.source.lucene.LuceneDocumentSource.java

License:Open Source License

/**
 * Close all opened indexes in the shared context.
 *//* w w w.  j  ava 2  s.  c o  m*/
private void closeAllIndexes() {
    synchronized (context) {
        for (IndexSearcher searcher : openIndexes.values()) {
            try {
                searcher.getIndexReader().close();
            } catch (IOException e) {
                logger.warn("Could not close search index: " + searcher, e);
            }
        }
    }
}

---

From source file:org.cee.store.lucene.LuceneArticleStore.java

License:Apache License

private Query createRelatedArticlesQuery(List<EntityKey> sites, ArticleKey reference, IndexSearcher searcher,
        String language) throws IOException {
    Query articleQuery = createArticleQuery(reference);
    TopDocs topDocs = searcher.search(articleQuery, 1);
    if (topDocs.totalHits == 0) {
        return new BooleanQuery(true);
    }//from  ww w  .  j  av  a 2s  .  c o  m
    MoreLikeThis mlt = new MoreLikeThis(searcher.getIndexReader());
    mlt.setFieldNames(LuceneConstants.ARTICLE_RELATED_SEARCH_FIELDS);
    mlt.setMaxQueryTerms(20);
    mlt.setBoost(true);
    mlt.setMinTermFreq(0);
    mlt.setMinDocFreq(0);
    Query relatedQuery = boostRelatedQuery(mlt.like(topDocs.scoreDocs[0].doc));

    BooleanQuery query = new BooleanQuery();
    query.add(new BooleanClause(relatedQuery, Occur.MUST));
    query.add(new BooleanClause(createQueryArticlesOfSites(sites), Occur.MUST));
    return query;
}

---

From source file:org.codelibs.elasticsearch.common.lucene.Lucene.java

License:Apache License

/**
 * Check whether there is one or more documents matching the provided query.
 *///from  www .j a  va2  s  . co m
public static boolean exists(IndexSearcher searcher, Query query) throws IOException {
    final Weight weight = searcher.createNormalizedWeight(query, false);
    // the scorer API should be more efficient at stopping after the first
    // match than the bulk scorer API
    for (LeafReaderContext context : searcher.getIndexReader().leaves()) {
        final Scorer scorer = weight.scorer(context);
        if (scorer == null) {
            continue;
        }
        final Bits liveDocs = context.reader().getLiveDocs();
        final DocIdSetIterator iterator = scorer.iterator();
        for (int doc = iterator.nextDoc(); doc != DocIdSetIterator.NO_MORE_DOCS; doc = iterator.nextDoc()) {
            if (liveDocs == null || liveDocs.get(doc)) {
                return true;
            }
        }
    }
    return false;
}

---

From source file:org.codelibs.elasticsearch.search.suggest.Suggester.java

License:Apache License

public Suggest.Suggestion<? extends Suggest.Suggestion.Entry<? extends Suggest.Suggestion.Entry.Option>> execute(
        String name, T suggestion, IndexSearcher searcher, CharsRefBuilder spare) throws IOException {
    // #3469 We want to ignore empty shards

    if (searcher.getIndexReader().numDocs() == 0) {
        return null;
    }//from   ww w  .j  a  v a2s .  c o m
    return innerExecute(name, suggestion, searcher, spare);
}

---

From source file:org.codelibs.elasticsearch.search.suggest.term.TermSuggester.java

License:Apache License

@Override
public TermSuggestion innerExecute(String name, TermSuggestionContext suggestion, IndexSearcher searcher,
        CharsRefBuilder spare) throws IOException {
    DirectSpellChecker directSpellChecker = suggestion.getDirectSpellCheckerSettings()
            .createDirectSpellChecker();
    final IndexReader indexReader = searcher.getIndexReader();
    TermSuggestion response = new TermSuggestion(name, suggestion.getSize(),
            suggestion.getDirectSpellCheckerSettings().sort());
    List<Token> tokens = queryTerms(suggestion, spare);
    for (Token token : tokens) {
        // TODO: Extend DirectSpellChecker in 4.1, to get the raw suggested words as BytesRef
        SuggestWord[] suggestedWords = directSpellChecker.suggestSimilar(token.term, suggestion.getShardSize(),
                indexReader, suggestion.getDirectSpellCheckerSettings().suggestMode());
        Text key = new Text(new BytesArray(token.term.bytes()));
        TermSuggestion.Entry resultEntry = new TermSuggestion.Entry(key, token.startOffset,
                token.endOffset - token.startOffset);
        for (SuggestWord suggestWord : suggestedWords) {
            Text word = new Text(suggestWord.string);
            resultEntry.addOption(new TermSuggestion.Entry.Option(word, suggestWord.freq, suggestWord.score));
        }//  w w  w  . j a va 2 s . c  om
        response.addTerm(resultEntry);
    }
    return response;
}

---

From source file:org.codesearch.indexer.server.tasks.ClearTask.java

License:Open Source License

/**
 * executes the task deletes all index files and resets the
 * lastIndexingRevision of all repositories
 *
 * @throws TaskExecutionException//from   ww  w.  j  av a2s .c  o m
 */
@Override
public void execute() throws TaskExecutionException {
    if (repositories == null || repositories.isEmpty()) { // Clear the whole index
        LOG.info("Clearing the whole index");
        boolean deleteSuccess = true;
        if (indexLocation.listFiles() != null) {
            for (File f : indexLocation.listFiles()) {
                if (!f.delete()) {
                    LOG.error("Could not delete file: " + f.getName());
                    deleteSuccess = false;
                }
            }
        }
        if (deleteSuccess) {
            LOG.debug("Successfully cleared index");
        } else {
            LOG.error("Could not delete all index files");
        }
        try {
            dba.purgeDatabaseEntries();
            LOG.debug("Cleared code analysis index");
        } catch (DatabaseAccessException ex) {
            LOG.warn("Could not clear code analysis index: \n" + ex);
        }
    } else { // Clear specific repository from the index
        StringBuilder repos = new StringBuilder();
        for (RepositoryDto repositoryDto : repositories) {
            repos.append(repositoryDto.getName()).append(" ");
        }
        LOG.info("Clearing index for repositories: " + repos.toString().trim());
        if (job != null) {
            job.getJobDataMap().put(IndexingJob.FIELD_CURRENT_STEPS, repositories.size());
        }
        IndexSearcher searcher = null;
        try {
            FSDirectory fsd = FSDirectory.open(indexLocation);
            searcher = new IndexSearcher(fsd, false);

            int index = 0;
            for (RepositoryDto repositoryDto : repositories) {
                if (job != null) {
                    // set the status
                    job.setCurrentRepository(index);
                    job.getJobDataMap().put(IndexingJob.FIELD_FINISHED_STEPS, index);
                }
                Term term = new Term(IndexConstants.INDEX_FIELD_REPOSITORY,
                        repositoryDto.getName().toLowerCase());

                LOG.debug("Deleting documents where field '" + term.field() + "' is '" + term.text() + "'");
                int deleteCount = 0;
                try {
                    deleteCount = searcher.getIndexReader().deleteDocuments(term);
                } catch (IOException ex) {
                    LOG.error("Error encountered while clearing index: " + ex);
                }

                indexStatusManager.setStatus(repositoryDto.getName(), VersionControlPlugin.UNDEFINED_VERSION);

                LOG.debug("Cleared " + deleteCount + " documents for repository " + repositoryDto.getName());
                index++;
            }
        } catch (CorruptIndexException ex) {
            LOG.error("Could not clear index because it is corrupt: \n" + ex);
        } catch (LockObtainFailedException ex) {
            LOG.error("Could not clear index because it is locked.");
        } catch (StaleReaderException ex) {
            LOG.error("The index was modified by another program/instance while clearing.");
        } catch (IOException ex) {
            // if there is no index nothing has to be cleared
        } finally {
            if (searcher != null) {
                try {
                    searcher.close();
                } catch (IOException ex) {
                }
            }
        }

        for (RepositoryDto repositoryDto : repositories) {
            try {
                dba.deleteRepository(repositoryDto.getName());
                LOG.debug("Cleared code analysis index for repository " + repositoryDto.getName());
            } catch (DatabaseAccessException ex) {
                LOG.warn("Could not clear code analysis index for repository: " + repositoryDto.getName()
                        + ", ignore if code analysis is not enabled \n" + ex);
            }
        }
    }

    LOG.info("Finished clearing index");
}

---

From source file:org.compass.core.lucene.engine.manager.LuceneIndexHolder.java

License:Apache License

public LuceneIndexHolder(IndexHoldersCache indexHoldersCache, String subIndex, IndexSearcher indexSearcher) {
    this.indexHoldersCache = indexHoldersCache;
    this.subIndex = subIndex;
    this.indexSearcher = indexSearcher;
    this.indexReader = indexSearcher.getIndexReader();
    if (indexHoldersCache.isDebug()) {
        AtomicInteger count = indexHoldersCache.getDebugHoldersCount().get(subIndex);
        if (count == null) {
            AtomicInteger newCount = new AtomicInteger();
            count = indexHoldersCache.getDebugHoldersCount().putIfAbsent(subIndex, newCount);
            if (count == null) {
                count = newCount;/*from ww w  .j  ava2 s  .  com*/
            }
        }
        count.incrementAndGet();
    }
}

---

From source file:org.compass.core.lucene.engine.spellcheck.DefaultLuceneSpellCheckManager.java

License:Apache License

public CompassSpellChecker createSpellChecker(final String[] subIndexes, final String[] aliases) {
    String[] calcSubIndexes = indexStore.calcSubIndexes(subIndexes, aliases);
    ArrayList<Searchable> searchers = new ArrayList<Searchable>(calcSubIndexes.length);
    ArrayList<IndexReader> readers = new ArrayList<IndexReader>(calcSubIndexes.length);
    for (String subIndex : calcSubIndexes) {
        synchronized (indexLocks.get(subIndex)) {
            IndexSearcher searcher = searcherMap.get(subIndex);
            if (searcher != null) {
                searchers.add(searcher);
                readers.add(searcher.getIndexReader());
            }/*from  w  w w  . ja v a 2 s  . c  om*/
        }
    }

    if (searchers.isEmpty()) {
        return null;
    }

    MultiSearcher searcher;
    try {
        searcher = searchEngineFactory.getLuceneIndexManager()
                .openMultiSearcher(searchers.toArray(new Searchable[searchers.size()]));
    } catch (IOException e) {
        throw new SearchEngineException("Failed to open searcher for spell check", e);
    }
    MultiReader reader = new CacheableMultiReader(readers.toArray(new IndexReader[readers.size()]), false);

    return new CompassSpellChecker(searcher, reader);
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• 20
• 21
• 22
• 23
• 24
• 25
• 26
• 27
• 28
• 29
• 30
• 31
• 32
• 33
• 34
• 35
• 36
• »