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

List of usage examples for org.apache.lucene.search IndexSearcher doc

  1. HOME
  2. Java
  3. org.apache.lucene
  4. org.apache.lucene.search.*
  5. IndexSearcher
  6. doc

Introduction

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

Prototype

public Document doc(int docID) throws IOException

Source Link

Document

Sugar for .getIndexReader().document(docID)

Usage

From source file:com.duroty.service.BookmarkOptimizerThread.java

License:Open Source License

/**
 * DOCUMENT ME!//from ww  w  .  j ava 2s .  com
 *
 * @param childs DOCUMENT ME!
 *
 * @throws Exception DOCUMENT ME!
 */
private void flush(File[] childs) throws Exception {
    if ((childs == null) || (childs.length == 0)) {
        return;
    }

    try {
        Thread.sleep(100);
    } catch (Exception e) {
    }

    File optimized = new File(optimizedPath);
    boolean create = false;
    IndexWriter writer = null;

    try {
        if (!IndexReader.indexExists(optimized)) {
            optimized.mkdirs();
            create = true;
        }

        synchronized (this) {
            if (IndexReader.isLocked(optimizedPath)) {
                return;
            } else {
                Directory dir = FSDirectory.getDirectory(new File(optimizedPath), create);
                writer = new IndexWriter(dir, analyzer, create);
            }

            for (int i = 0; i < childs.length; i++) {
                boolean lock = true;
                File child = childs[i];
                File[] faux = child.listFiles();

                for (int j = 0; j < faux.length; j++) {
                    if (faux[j].getName().equals("is.unlock")) {
                        faux[j].delete();
                        lock = false;

                        break;
                    }
                }

                if (!lock) {
                    Directory[] aux = new Directory[1];
                    aux[0] = FSDirectory.getDirectory(child, false);

                    IndexSearcher searcher = null;

                    try {
                        searcher = new IndexSearcher(aux[0]);

                        Document doc = searcher.doc(0);

                        if (doc != null) {
                            BookmarkIndexer.createSpell(userPath + SPELL, Field_title, doc);
                            BookmarkIndexer.createSpell(userPath + SPELL, Field_keywords, doc);
                            BookmarkIndexer.createSpell(userPath + SPELL, Field_contents, doc);
                            BookmarkIndexer.createSpell(userPath + SPELL, Field_comments, doc);
                        }
                    } catch (Exception ex) {
                        if ((ex != null) && !(ex instanceof NullPointerException)) {
                            DLog.log(DLog.INFO, this.getClass(), ex);
                        }
                    } finally {
                        if (searcher != null) {
                            try {
                                searcher.close();
                            } catch (Exception e) {
                            }
                        }
                    }

                    writer.addIndexes(aux);
                    writer.optimize();

                    for (int j = 0; j < faux.length; j++) {
                        faux[j].delete();
                    }

                    child.delete();
                }
            }

            writer.close();
            writer = null;
        }
    } finally {
        if (writer != null) {
            try {
                writer.close();
            } catch (Exception e) {
            }
        }
    }
}

From source file:com.duroty.service.MailOptimizerThread.java

License:Open Source License

/**
 * DOCUMENT ME!//from   www  .j  a v  a  2  s.c  o  m
 *
 * @param childs DOCUMENT ME!
 *
 * @throws Exception DOCUMENT ME!
 */
private void flush(File[] childs) throws Exception {
    if ((childs == null) || (childs.length == 0)) {
        return;
    }

    try {
        Thread.sleep(500);
    } catch (Exception e) {
    }

    File optimized = new File(optimizedPath);
    boolean create = false;
    IndexWriter writer = null;

    try {
        if (!IndexReader.indexExists(optimized)) {
            optimized.mkdirs();
            create = true;
        }

        synchronized (this) {
            if (IndexReader.isLocked(optimizedPath)) {
                return;
            } else {
                Directory dir = FSDirectory.getDirectory(new File(optimizedPath), create);
                writer = new IndexWriter(dir, analyzer, create);
            }

            for (int i = 0; i < childs.length; i++) {
                boolean lock = true;
                File child = childs[i];
                File[] faux = child.listFiles();

                for (int j = 0; j < faux.length; j++) {
                    if (faux[j].getName().equals("is.unlock")) {
                        faux[j].delete();
                        lock = false;

                        break;
                    }
                }

                if (!lock) {
                    Directory[] aux = new Directory[1];
                    aux[0] = FSDirectory.getDirectory(child, false);

                    IndexSearcher searcher = null;

                    try {
                        searcher = new IndexSearcher(aux[0]);

                        Document doc = searcher.doc(0);

                        if (doc != null) {
                            MailIndexer.createSpell(userPath + SPELL, Field_from, doc);
                            MailIndexer.createSpell(userPath + SPELL, Field_to, doc);
                            MailIndexer.createSpell(userPath + SPELL, Field_subject, doc);
                            MailIndexer.createSpell(userPath + SPELL, Field_body, doc);
                        }
                    } catch (Exception ex) {
                        if ((ex != null) && !(ex instanceof NullPointerException)) {
                            DLog.log(DLog.INFO, this.getClass(), ex);
                        }
                    } finally {
                        if (searcher != null) {
                            try {
                                searcher.close();
                            } catch (Exception e) {
                            }
                        }
                    }

                    writer.addIndexes(aux);
                    writer.optimize();

                    for (int j = 0; j < faux.length; j++) {
                        faux[j].delete();
                    }

                    child.delete();
                }
            }

            writer.close();
            writer = null;
        }
    } finally {
        if (writer != null) {
            try {
                writer.close();
            } catch (Exception e) {
            }
        }
    }
}

From source file:com.edgenius.wiki.search.service.AbstractSearchService.java

License:Open Source License

private int detach(IndexSearcher searcher, List<SearchResultItem> viewableMatchedResults, TopDocs hits,
        Query hlQuery, int from, int to, User user) throws IOException {

    Assert.isTrue(from <= to && from >= 0 && (to >= 0 || to == -1));

    //For performance issue, we simply return total result set length without permission filter out.
    //This means is total length might be larger than the set that user can view, as some result will be filter out
    //if user doesn't have permission to see.
    int len = hits.totalHits;

    if (len > 0 && from < len) {
        to = to == -1 ? len : (len > to ? to : len);
        //security filter from return result

        List<Integer> resultIdx = new ArrayList<Integer>();
        for (int idx = from; idx < to; idx++) {
            //does not include "to" , For example, from:to is 0:10, then return index is 0-9

            //TODO: if page includes some result that invisible to user, it is better display message to tell user
            //some result is hidden for security reason.
            if (!isAllowView(searcher.doc(hits.scoreDocs[idx].doc), user))
                continue;

            resultIdx.add(idx);//from   w w  w  . j  a v a  2s  .  c om
        }

        //create a highlighter for all fragment parser
        Formatter formatter = new SimpleHTMLFormatter("<span class=\"highlighter\">", "</span>");
        Highlighter hl = null;
        if (hlQuery != null) {
            Scorer scorer = new QueryScorer(hlQuery);
            hl = new Highlighter(formatter, scorer);
            Fragmenter fragmenter = new SimpleFragmenter(FRAGMENT_LEN);
            hl.setTextFragmenter(fragmenter);
        }

        for (int idx : resultIdx) {
            SearchResultItem item = new SearchResultItem();

            Document doc = searcher.doc(hits.scoreDocs[idx].doc);
            String docType = doc.get(FieldName.DOC_TYPE);

            //common items in search results
            item.setType(NumberUtils.toInt(docType));
            item.setDatetime(doc.get(FieldName.UPDATE_DATE));
            if (userReadingService != null
                    && !new Integer(SharedConstants.SEARCH_USER).toString().equals(docType)) {
                String username = doc.get(FieldName.CONTRIBUTOR);
                User contirUser = userReadingService.getUserByName(username);
                if (contirUser != null) {
                    item.setContributor(contirUser.getFullname());
                    item.setContributorUsername(username);
                }
            }
            if (Integer.valueOf(SharedConstants.SEARCH_PAGE).toString().equals(docType)) {
                String content = doc.get(FieldName.PAGE_CONTENT);
                item.setTitle(doc.get(FieldName.PAGE_TITLE));
                item.setSpaceUname(doc.get(FieldName.UNSEARCH_SPACE_UNIXNAME));

                //does set item.desc() as content, which maybe very big string. no necessary returned
                item.setFragment(createFragment(hl, StringUtil.join(" ", item.getTitle(), content)));

            } else if (Integer.valueOf(SharedConstants.SEARCH_COMMENT).toString().equals(docType)) {
                String content = doc.get(FieldName.CONTENT);

                item.setItemUid(doc.get(FieldName.COMMENT_UID));
                item.setSpaceUname(doc.get(FieldName.UNSEARCH_SPACE_UNIXNAME));
                item.setTitle(doc.get(FieldName.UNSEARCH_PAGE_TITLE));
                //does set item.desc() as content, which maybe very big string. no necessary returned
                item.setFragment(createFragment(hl, content));

            } else if (Integer.valueOf(SharedConstants.SEARCH_SPACE).toString().equals(docType)) {
                String title = doc.get(FieldName.SPACE_NAME);
                item.setTitle(title);
                item.setSpaceUname(doc.get(FieldName.SPACE_UNIXNAME));
                item.setDesc(doc.get(FieldName.SPACE_DESC));
                item.setFragment(createFragment(hl, StringUtil.join(" ", item.getTitle(), item.getDesc())));

            } else if (Integer.valueOf(SharedConstants.SEARCH_WIDGET).toString().equals(docType)) {
                //wTitle-> title; wDesc-> desc; wTitle(could be pageTitle or markup title) ->spaceUname
                String widgetType = doc.get(FieldName.WIDGET_TYPE);
                String title = doc.get(FieldName.WIDGET_TITLE);

                //does content need transfer back?? so far no
                String content = doc.get(FieldName.WIDGET_CONTENT);
                if (WidgetModel.TYPE_PAGE_LINKER.equals(widgetType)) {
                    //don't use as Highlighter fragment
                    content = "";
                }

                String desc = doc.get(FieldName.WIDGET_DESC);

                item.setDesc(desc);
                item.setTitle(title);

                //add little confuse field mapping :(
                item.setSpaceUname(doc.get(FieldName.WIDGET_KEY));
                item.setItemUid(widgetType);

                item.setFragment(createFragment(hl, StringUtil.join(" ", item.getDesc(), content)));

            } else if (Integer.valueOf(SharedConstants.SEARCH_PAGE_TAG).toString().equals(docType)) {
                //page tag
                item.setTitle(doc.get(FieldName.PAGE_TAG_NAME));
                item.setSpaceUname(doc.get(FieldName.UNSEARCH_SPACE_UNIXNAME));
                item.setFragment(createFragment(hl, item.getTitle()));
            } else if (Integer.valueOf(SharedConstants.SEARCH_SPACE_TAG).toString().equals(docType)) {
                //space tag
                item.setTitle(doc.get(FieldName.SPACE_TAG_NAME));
                item.setFragment(createFragment(hl, item.getTitle()));

            } else if (Integer.valueOf(SharedConstants.SEARCH_USER).toString().equals(docType)) {
                String username = doc.get(FieldName.USER_NAME);
                item.setTitle(username);
                String fullname = doc.get(FieldName.USER_FULLNAME);
                //hacker - contributor is current user fullname
                item.setContributor(fullname);
                if (userReadingService != null)
                    item.setDesc(userReadingService.getUserByName(username).getSetting().getStatus());
                item.setFragment(createFragment(hl, fullname));

            } else if (Integer.valueOf(SharedConstants.SEARCH_ROLE).toString().equals(docType)) {
                item.setSpaceUname(doc.get(FieldName.ROLE_NAME));
                item.setTitle(doc.get(FieldName.ROLE_DISPLAY_NAME));
                item.setDesc(doc.get(FieldName.ROLE_DESC));
                //item.setFragment("");

            } else if (Integer.valueOf(SharedConstants.SEARCH_ATTACHMENT).toString().equals(docType)) {
                item.setTitle(doc.get(FieldName.FILE_NAME));
                item.setDesc(doc.get(FieldName.FILE_COMMENT));
                item.setItemUid(doc.get(FieldName.FILE_NODE_UUID));
                item.setSpaceUname(doc.get(FieldName.UNSEARCH_SPACE_UNIXNAME));
                String text = doc.get(FieldName.TEXT);
                //does not mark file content fragment, because it does not store in index
                String fragment = createFragment(hl, StringUtil.join(" ", item.getDesc(), text));
                item.setFragment(
                        (fragment == null || fragment.trim().length() == 0) ? ("Comment: " + item.getDesc())
                                : fragment);
            }
            viewableMatchedResults.add(item);
        }
    }
    return len;
}

From source file:com.edgenius.wiki.search.service.AttachmentSearchServiceImpl.java

License:Open Source License

public Document searchByNodeUuid(final String nodeUuid) throws SearchException {

    return (Document) this.search(new SearcherCallback() {
        public Object doWithSearcher(IndexSearcher searcher) throws SearchException {
            try {
                Term identifierTerm = new Term(FieldName.KEY, nodeUuid.toLowerCase());
                TermQuery query = new TermQuery(identifierTerm);
                TopDocs hits = searcher.search(query, LuceneConfig.MAX_RETURN);
                Document doc = null;

                if (hits.totalHits > 0) {
                    //assume only one
                    doc = searcher.doc(hits.scoreDocs[0].doc);
                }/*from  ww  w  .  j  a  v a2s.c o m*/
                return doc;
            } catch (Exception e) {
                throw new SearchException(e);
            }
        }
    });
}

From source file:com.epam.catgenome.dao.index.FeatureIndexDao.java

License:Open Source License

private FeatureIndexEntry createIndexEntry(ScoreDoc hit, Map<Long, BookmarkIndexEntry> foundBookmarkEntries,
        IndexSearcher searcher, List<String> vcfInfoFields) throws IOException {
    int docId = hit.doc;
    Document d = searcher.doc(docId);
    FeatureType featureType = FeatureType.forValue(d.get(FeatureIndexFields.FEATURE_TYPE.getFieldName()));
    FeatureIndexEntry entry;/*  w  w  w .ja  va2s  .  c  om*/
    switch (featureType) {
    case VARIATION:
        entry = createVcfIndexEntry(d, vcfInfoFields);
        break;
    case BOOKMARK:
        BookmarkIndexEntry bookmarkEntry = new BookmarkIndexEntry();
        foundBookmarkEntries.put(Long.parseLong(d.get(FeatureIndexFields.FILE_ID.getFieldName())),
                bookmarkEntry);
        entry = bookmarkEntry;
        break;
    default:
        entry = new FeatureIndexEntry();
    }

    entry.setFeatureType(featureType);
    BytesRef featureIdBytes = d.getBinaryValue(FeatureIndexFields.FEATURE_ID.getFieldName());
    if (featureIdBytes != null) {
        entry.setFeatureId(featureIdBytes.utf8ToString());
    }

    entry.setStartIndex(d.getField(FeatureIndexFields.START_INDEX.getFieldName()).numericValue().intValue());
    entry.setEndIndex(d.getField(FeatureIndexFields.END_INDEX.getFieldName()).numericValue().intValue());
    entry.setFeatureFileId(Long.parseLong(d.get(FeatureIndexFields.FILE_ID.getFieldName())));
    entry.setFeatureName(d.get(FeatureIndexFields.FEATURE_NAME.getFieldName()));

    String chromosomeId = d.getBinaryValue(FeatureIndexFields.CHROMOSOME_ID.getFieldName()).utf8ToString();
    if (!chromosomeId.isEmpty()) {
        entry.setChromosome(new Chromosome(Long.parseLong(chromosomeId)));
        entry.getChromosome()
                .setName(d.getBinaryValue(FeatureIndexFields.CHROMOSOME_NAME.getFieldName()).utf8ToString());
    }

    return entry;
}

From source file:com.epam.catgenome.dao.index.FeatureIndexDao.java

License:Open Source License

private Set<String> fetchGeneIds(final ScoreDoc[] hits, IndexSearcher searcher) throws IOException {
    Set<String> geneIds = new HashSet<>();

    for (ScoreDoc hit : hits) {
        int docId = hit.doc;
        Document d = searcher.doc(docId);
        String geneId = d.get(FeatureIndexFields.GENE_ID.getFieldName());
        String geneName = d.get(FeatureIndexFields.GENE_NAME.getFieldName());
        if (geneId != null) {
            geneIds.add(geneId);//from   ww w  .j a v a2s. c o  m
        }
        if (geneName != null) {
            geneIds.add(geneName);
        }
    }

    return geneIds;
}

From source file:com.evoapps.lucene.SearchFiles.java

License:Apache License

/**
 * This demonstrates a typical paging search scenario, where the search engine presents 
 * pages of size n to the user. The user can then go to the next page if interested in
 * the next hits.//from  ww  w .  ja  v a2  s  . c  o m
 * 
 * When the query is executed for the first time, then only enough results are collected
 * to fill 5 result pages. If the user wants to page beyond this limit, then the query
 * is executed another time and all hits are collected.
 * 
 */
public ArrayList<Publication> doPagingSearch(BufferedReader in, IndexSearcher searcher, Query query,
        int hitsPerPage, boolean raw, boolean interactive) throws IOException {

    // Collect enough docs to show 5 pages
    TopDocs results = searcher.search(query, 5 * hitsPerPage);
    ScoreDoc[] hits = results.scoreDocs;

    int numTotalHits = results.totalHits;
    System.out.println(numTotalHits + "total matching documents");

    int start = 0;
    int end = Math.min(numTotalHits, hitsPerPage);

    while (true) {
        if (end > hits.length) {
            System.out.println("Only results 1 - " + hits.length + " of " + numTotalHits
                    + " total matching documents collected.");
            System.out.println("Collect more (y/n) ?");
            String line = in.readLine();
            if (line.length() == 0 || line.charAt(0) == 'n') {
                break;
            }

            hits = searcher.search(query, numTotalHits).scoreDocs;
        }

        end = Math.min(hits.length, start + hitsPerPage);

        for (int i = start; i < end; i++) {
            if (raw) { // output raw format
                System.out.println("doc=" + hits[i].doc + " score=" + hits[i].score);
                continue;
            }

            Document doc = searcher.doc(hits[i].doc);
            String path = doc.get("path");
            String content = doc.get("contents");
            if (path != null) {
                //   System.out.println((i+1) + ". " + path+">>"+content);
                list.add(new Publication(content, path));
                String title = doc.get("title");
                if (title != null) {
                    System.out.println("   Title: " + doc.get("title"));
                }
            } else {
                System.out.println((i + 1) + ". " + "No path for this document");
            }

        }

        if (!interactive || end == 0) {
            break;
        }

        if (numTotalHits >= end) {
            boolean quit = false;
            while (true) {
                System.out.print("Press ");
                if (start - hitsPerPage >= 0) {
                    System.out.print("(p)revious page, ");
                }
                if (start + hitsPerPage < numTotalHits) {
                    System.out.print("(n)ext page, ");
                }
                System.out.println("(q)uit or enter number to jump to a page.");

                String line = in.readLine();
                if (line.length() == 0 || line.charAt(0) == 'q') {
                    quit = true;
                    break;
                }
                if (line.charAt(0) == 'p') {
                    start = Math.max(0, start - hitsPerPage);
                    break;
                } else if (line.charAt(0) == 'n') {
                    if (start + hitsPerPage < numTotalHits) {
                        start += hitsPerPage;
                    }
                    break;
                } else {
                    int page = Integer.parseInt(line);
                    if ((page - 1) * hitsPerPage < numTotalHits) {
                        start = (page - 1) * hitsPerPage;
                        break;
                    } else {
                        System.out.println("No such page");
                    }
                }
            }
            if (quit)
                break;
            end = Math.min(numTotalHits, start + hitsPerPage);
        }
    }
    return list;
}

From source file:com.example.search.SearchFiles.java

License:Apache License

/**
 * This demonstrates a typical paging search scenario, where the search
 * engine presents pages of size n to the user. The user can then go to the
 * next page if interested in the next hits.
 * /*from ww  w.  ja  v a 2s.  co  m*/
 * When the query is executed for the first time, then only enough results
 * are collected to fill 5 result pages. If the user wants to page beyond
 * this limit, then the query is executed another time and all hits are
 * collected.
 * 
 * @throws InvalidTokenOffsetsException
 * 
 */
public static void doPagingSearch(BufferedReader in, IndexSearcher searcher, Query query, int hitsPerPage,
        boolean raw, boolean interactive, ArrayList<SearchResult> result, int startPage)
        throws IOException, InvalidTokenOffsetsException {
    startPage = Math.max(0, startPage);
    // Collect enough docs to show 5 pages 10
    //      System.out.println("need " + startPage);
    TopDocs results = searcher.search(query, startPage + hitsPerPage);// 5 *
    // hitsPerPage
    ScoreDoc[] hits = results.scoreDocs;
    if (startPage > hits.length)
        return;
    int numTotalHits = results.totalHits;
    //      System.out.println("judge " + hits.length + " " + numTotalHits);
    System.out.println(numTotalHits + " total matching documents");

    int start = startPage;
    // int end = Math.min(numTotalHits, hitsPerPage);

    /*
     * if (end > hits.length) { System.out .println("Only results 1 - " +
     * hits.length + " of " + numTotalHits +
     * " total matching documents collected.");
     * System.out.println("Collect more (y/n) ?"); String line =
     * in.readLine(); if (line.length() == 0 || line.charAt(0) == 'n') {
     * break; }
     * 
     * hits = searcher.search(query, numTotalHits).scoreDocs; }
     */
    int end = Math.min(hits.length, start + hitsPerPage);
    //       ICTCLASAnalyzer    analyzer = new ICTCLASAnalyzer();
    for (int i = start; i < end; i++) {
        if (raw) { // output raw format
            // System.out.println("doc="+hits[i].doc+" score="+hits[i].score);
            System.out.println(" score=" + hits[i].score);
            // continue;
        }

        Document doc = searcher.doc(hits[i].doc);

        String path = doc.get("url");
        if (path != null) {
            // System.out.println((i + 1) + ". " + path);
            String title = doc.get("title");// 
            // if (title != null) {
            // System.out.println("   Title: " + title);
            String content = doc.get("content");
            // if (content != null)
            // System.out.println("Content: " + content);
            SearchResult item = new SearchResult();

            item.title = i + " " + title;
            item.url = path;
            item.score = hits[i].score;
            /*SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter(
                              "<font color='red'>", "</font>");
                                 
                        Highlighter highlighter = new Highlighter(simpleHTMLFormatter,
                              new QueryScorer(query));
                        highlighter.setTextFragmenter(new SimpleFragmenter(100));*/
            //   if (content != null) {
            /*   TokenStream tokenStream = analyzer.tokenStream("content",
             new StringReader(content));
                     String highLightText = highlighter.getBestFragment(
             tokenStream, content);
                     System.out.println(" " + (i + 1) + " ");
                     System.out.println(highLightText);
                  item.content=highLightText;*/
            if (content.length() > 403)
                content = content.substring(0, 399) + "...";
            item.content = content;
            result.add(item);
            //}
        } else {
            System.out.println((i + 1) + ". " + "No path for this document");
        }

    } // end for
    //     analyzer.close();
    // if (numTotalHits >= end) {
    // boolean quit = false;
    // while (true) {
    // System.out.print("Press ");
    // if (start - hitsPerPage >= 0) {
    // System.out.print("(p)revious page, ");
    SearchResult.hasPrePage = (start - hitsPerPage >= 0);
    // }
    // if (start + hitsPerPage < numTotalHits) {
    // System.out.print("(n)ext page, ");
    // }
    SearchResult.hasNextPage = (start + hitsPerPage < numTotalHits);
    System.out.println("hasNextPage" + SearchResult.hasNextPage);
    // System.out
    // .println("(q)uit or enter number to jump to a page.");

    // String line = in.readLine();
    /*
     * String line=new String(); if (line.length() == 0 || line.charAt(0) ==
     * 'q') { quit = true; break; }
     */
    /*
     * if (line.charAt(0) == 'p') { start = Math.max(0, start -
     * hitsPerPage); break; } else if (line.charAt(0) == 'n') { if (start +
     * hitsPerPage < numTotalHits) { start += hitsPerPage; } break; } else {
     * int page = Integer.parseInt(line); if ((page - 1) * hitsPerPage <
     * numTotalHits) { start = (page - 1) * hitsPerPage; break; } else {
     * System.out.println("No such page"); } } // } if (quit) break;
     */
    // end = Math.min(numTotalHits, start + hitsPerPage);

}

From source file:com.flaptor.hounder.indexer.IndexManager.java

License:Apache License

/**
 * Performs the deletes and remove duplicates from the index.
 *//* w w  w  .  j a  v  a 2  s  . c  o  m*/
private synchronized void applyDeletes() {
    IndexReader reader = null;
    IndexSearcher searcher = null;
    try {
        reader = IndexReader.open(indexDirectory);
        Set<Integer> documentsToDelete = new HashSet<Integer>();
        Enumeration keysEnum = lastOperation.keys();
        //First we collect the lucene ids of document to be deleted.
        while (keysEnum.hasMoreElements()) {
            searcher = new IndexSearcher(reader);
            String key = (String) keysEnum.nextElement();
            // if the last operation is a delete lastAddition will be 0 and we'll find no match in the index.
            //This way, all the documents with that DocumentId will be erased.
            String lastAddition = String.valueOf((Long) (lastOperation.get(key)));
            if (logger.isEnabledFor(Level.DEBUG)) {
                logger.debug("Applying deletes: searching " + docIdName + " = [" + key + "]");
            }
            ScorelessHitCollector collector = new HashSetScorelessHitCollector();
            searcher.search(new TermQuery(new Term(docIdName, key)), collector);
            Set<Integer> docIds = collector.getMatchingDocuments();
            if (logger.isEnabledFor(Level.DEBUG)) {
                logger.debug("Applying deletes: found matches: " + docIds.size());
            }
            for (Integer docId : docIds) {
                Document d = searcher.doc(docId);
                String addId = d.get("AddId");
                if (!lastAddition.equals(addId)) {
                    if (logger.isEnabledFor(Level.DEBUG)) {
                        logger.debug("Applying deletes: deleting AddId:" + addId);
                    }
                    documentsToDelete.add(docId);
                }
            }
        }
        //Now we have all lucene's ids of documents to be deleted and we can
        //proceed with the actual deletion.
        for (Integer i : documentsToDelete) {
            reader.deleteDocument(i);
        }

    } catch (IOException e) {
        logger.fatal("applyDeletes: IOException caught.", e);
        throw new RuntimeException(e);
    } finally {
        if (searcher != null) {
            try {
                searcher.close();
            } catch (Exception e) {
                String s = "applyDeletes: Couldn't close searcher, nothing I can do about it" + e;
                logger.error(s);
                throw new IllegalStateException(s);
            }
        }
        if (reader != null) {
            try {
                reader.close();
            } catch (Exception e) {
                logger.warn("Couldn't close reader, nothing I can do about it", e);
            }
        }
    }

    lastOperation.clear();
}

From source file:com.flaptor.hounder.indexer.LuceneUnicodeTest.java

License:Apache License

@TestInfo(testType = TestInfo.TestType.UNIT)
public void testIndexedContent() {
    try {/*from  w  ww. j  a  va 2  s .  com*/
        String testString = "otorrinolaring\u00f3logo";
        logger.debug("Using test string: " + testString);
        Document doc = new Document();
        doc.add(new Field("field1", testString, Field.Store.YES, Field.Index.ANALYZED));
        writer.addDocument(doc);
        writer.optimize();
        writer.close();
        IndexReader reader = IndexReader.open(dir);
        IndexSearcher searcher = new IndexSearcher(reader);
        int docId = searcher.search(new TermQuery(new Term("field1", testString)), null, 10).scoreDocs[0].doc;
        Document doc2 = searcher.doc(docId);
        String recoveredString = doc2.get("field1");
        logger.debug("Recovered String: " + recoveredString);
        assertTrue("Strings do not match", testString.equals(recoveredString));
    } catch (Exception e) {
        logger.error("Exception caught:" + e);
        assertTrue("exception", false);
    }
}