Example usage for org.apache.lucene.index DirectoryReader open

List of usage examples for org.apache.lucene.index DirectoryReader open

  1. HOME
  2. Java
  3. org.apache.lucene
  4. org.apache.lucene.index.*
  5. DirectoryReader
  6. open

Introduction

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

Prototype

public static DirectoryReader open(final IndexCommit commit) throws IOException

Source Link

Document

Expert: returns an IndexReader reading the index in the given IndexCommit .

Usage

From source file:com.chimpler.example.FacetLuceneAdvancedSearcher.java

License:Apache License

public static void main(String args[]) throws Exception {
    if (args.length != 5) {
        System.err.println(/*ww w  .  j a va 2  s  .c om*/
                "Parameters: [index directory] [taxonomy directory] [query] [field drilldown] [value drilldown]");
        System.exit(1);
    }

    String indexDirectory = args[0];
    String taxonomyDirectory = args[1];
    String query = args[2];
    String fieldDrilldown = args[3];
    String valueDrilldown = args[4];

    IndexReader indexReader = DirectoryReader.open(FSDirectory.open(new File(indexDirectory)));
    IndexSearcher indexSearcher = new IndexSearcher(indexReader);

    TaxonomyReader taxonomyReader = new DirectoryTaxonomyReader(FSDirectory.open(new File(taxonomyDirectory)));

    CategoryPath drillDownCategoryPath = new CategoryPath(fieldDrilldown + "/" + valueDrilldown, '/');

    FacetSearchParams searchParams = new FacetSearchParams();
    searchParams.facetRequests.add(new CountFacetRequest(new CategoryPath("author"), 100));
    searchParams.facetRequests.add(new CountFacetRequest(new CategoryPath("book_category"), 100));
    searchParams.facetRequests.add(new CountFacetRequest(drillDownCategoryPath, 100));

    ComplexPhraseQueryParser queryParser = new ComplexPhraseQueryParser(LUCENE_VERSION, "title",
            new StandardAnalyzer(LUCENE_VERSION));

    Query luceneQuery = queryParser.parse(query);
    //luceneQuery = DrillDownQuery.query(luceneQuery, drillDownCategoryPath);

    // Collectors to get top results and facets
    TopScoreDocCollector topScoreDocCollector = TopScoreDocCollector.create(10, true);
    FacetsCollector facetsCollector = FacetsCollector.create(searchParams, indexReader, taxonomyReader);
    indexSearcher.search(luceneQuery, MultiCollector.wrap(topScoreDocCollector, facetsCollector));
    System.out.println("Found:");

    for (ScoreDoc scoreDoc : topScoreDocCollector.topDocs().scoreDocs) {
        Document document = indexReader.document(scoreDoc.doc);
        System.out.printf("- book: id=%s, title=%s, book_category=%s, authors=%s, score=%f\n",
                document.get("id"), document.get("title"), document.get("book_category"),
                document.get("authors"), scoreDoc.score);
    }

    System.out.println("Facets:");
    for (FacetResult facetResult : facetsCollector.getFacetResults()) {
        System.out.println("- " + facetResult.getFacetResultNode().label);
        for (FacetResultNode facetResultNode : facetResult.getFacetResultNode().subResults) {
            System.out.printf("    - %s (%f)\n", facetResultNode.label.toString(), facetResultNode.value);
            for (FacetResultNode subFacetResultNode : facetResultNode.subResults) {
                System.out.printf("        - %s (%f)\n", subFacetResultNode.label.toString(),
                        subFacetResultNode.value);
            }
        }
    }
    taxonomyReader.close();
    indexReader.close();
}

From source file:com.chimpler.example.FacetLuceneSearcher.java

License:Apache License

public static void main(String args[]) throws Exception {
    //      if (args.length != 3) {
    //         System.err.println("Parameters: [index directory] [taxonomy directory] [query]");
    //         System.exit(1);
    //      }/*w  w w  .j  av a2 s.  c o  m*/

    String indexDirectory = "index";
    String taxonomyDirectory = "taxonomy";
    String query = "story";

    IndexReader indexReader = DirectoryReader.open(FSDirectory.open(new File(indexDirectory)));
    IndexSearcher indexSearcher = new IndexSearcher(indexReader);

    TaxonomyReader taxonomyReader = new DirectoryTaxonomyReader(FSDirectory.open(new File(taxonomyDirectory)));

    ArrayList<FacetRequest> facetRequests = new ArrayList<FacetRequest>();
    facetRequests.add(new CountFacetRequest(new CategoryPath("author"), 100));
    facetRequests.add(new CountFacetRequest(new CategoryPath("book_category"), 100));

    FacetSearchParams searchParams = new FacetSearchParams(facetRequests);

    ComplexPhraseQueryParser queryParser = new ComplexPhraseQueryParser(LUCENE_VERSION, "title",
            new StandardAnalyzer(LUCENE_VERSION));
    Query luceneQuery = queryParser.parse(query);

    // Collectors to get top results and facets
    TopScoreDocCollector topScoreDocCollector = TopScoreDocCollector.create(10, true);
    FacetsCollector facetsCollector = FacetsCollector.create(searchParams, indexReader, taxonomyReader);
    indexSearcher.search(luceneQuery, MultiCollector.wrap(topScoreDocCollector, facetsCollector));
    System.out.println("Found:");

    for (ScoreDoc scoreDoc : topScoreDocCollector.topDocs().scoreDocs) {
        Document document = indexReader.document(scoreDoc.doc);
        System.out.printf("- book: id=%s, title=%s, book_category=%s, authors=%s, score=%f\n",
                document.get("id"), document.get("title"), document.get("book_category"),
                document.get("authors"), scoreDoc.score);
    }

    System.out.println("Facets:");
    for (FacetResult facetResult : facetsCollector.getFacetResults()) {
        System.out.println("- " + facetResult.getFacetResultNode().label);
        for (FacetResultNode facetResultNode : facetResult.getFacetResultNode().subResults) {
            System.out.printf("    - %s (%f)\n", facetResultNode.label.toString(), facetResultNode.value);
            for (FacetResultNode subFacetResultNode : facetResultNode.subResults) {
                System.out.printf("        - %s (%f)\n", subFacetResultNode.label.toString(),
                        subFacetResultNode.value);
            }
        }
    }
    taxonomyReader.close();
    indexReader.close();
}

From source file:com.codenvy.test.lucene.DeleteFilesWithSameName.java

License:Open Source License

public static void searchAndPrintResult(Path indexPath) throws Exception {
    IndexReader reader = DirectoryReader.open(FSDirectory.open(indexPath));
    IndexSearcher searcher = new IndexSearcher(reader);

    Query query = new PrefixQuery(new Term(PATH, filesDirPath + "/File1"));
    TopDocs topDocs = searcher.search(query, 100);

    System.out.println();/* w w  w .  java2 s  .c  o  m*/
    System.out.println("=========================== search =================================");
    final String[] result = new String[topDocs.scoreDocs.length];
    for (int i = 0, length = result.length; i < length; i++) {
        result[i] = searcher.doc(topDocs.scoreDocs[i].doc).getField(PATH).stringValue();
        System.out.println(result[i]);
    }

    reader.close();
}

From source file:com.codeReading.core.opengrok.SearchHelper.java

License:Open Source License

/**
 * Create the searcher to use wrt. to currently set parameters and the given
 * projects. Does not produce any {@link #redirect} link. It also does
 * nothing if {@link #redirect} or {@link #errorMsg} have a
 * none-{@code null} value. <p> Parameters which should be populated/set at
 * this time: <ul> <li>{@link #builder}</li> <li>{@link #dataRoot}</li>
 * <li>{@link #order} (falls back to relevance if unset)</li>
 * <li>{@link #parallel} (default: false)</li> </ul> Populates/sets: <ul>
 * <li>{@link #query}</li> <li>{@link #searcher}</li> <li>{@link #sort}</li>
 * <li>{@link #projects}</li> <li>{@link #errorMsg} if an error occurs</li>
 * </ul>//from  w w w. ja v  a  2 s.c o  m
 *
 * @param projects project to use query. If empty, a none-project opengrok
 * setup is assumed (i.e. DATA_ROOT/index will be used instead of possible
 * multiple DATA_ROOT/$project/index).
 * @return this instance
 */
public SearchHelper prepareExec(SortedSet<String> projects) {
    if (redirect != null || errorMsg != null) {
        return this;
    }
    // the Query created by the QueryBuilder
    try {
        indexDir = new File(dataRoot, "index");
        query = builder.build();
        if (projects == null) {
            errorMsg = "No project selected!";
            return this;
        }
        this.projects = projects;
        if (projects.isEmpty()) {
            //no project setup
            FSDirectory dir = FSDirectory.open(indexDir);
            searcher = new IndexSearcher(DirectoryReader.open(dir));
        } else if (projects.size() == 1) {
            // just 1 project selected
            FSDirectory dir = FSDirectory.open(new File(indexDir, projects.first()));
            searcher = new IndexSearcher(DirectoryReader.open(dir));
        } else {
            //more projects                                
            IndexReader[] subreaders = new IndexReader[projects.size()];
            int ii = 0;
            //TODO might need to rewrite to Project instead of
            // String , need changes in projects.jspf too
            for (String proj : projects) {
                FSDirectory dir = FSDirectory.open(new File(indexDir, proj));
                subreaders[ii++] = DirectoryReader.open(dir);
            }
            MultiReader searchables = new MultiReader(subreaders, true);
            if (parallel) {
                int noThreads = 2 + (2 * Runtime.getRuntime().availableProcessors()); //TODO there might be a better way for counting this
                executor = Executors.newFixedThreadPool(noThreads);
            }
            searcher = parallel ? new IndexSearcher(searchables, executor) : new IndexSearcher(searchables);
        }
        // TODO check if below is somehow reusing sessions so we don't
        // requery again and again, I guess 2min timeout sessions could be
        // usefull, since you click on the next page within 2mins, if not,
        // then wait ;)
        switch (order) {
        case LASTMODIFIED:
            sort = new Sort(new SortField("date", SortField.Type.STRING, true));
            break;
        case BY_PATH:
            sort = new Sort(new SortField("fullpath", SortField.Type.STRING));
            break;
        default:
            sort = Sort.RELEVANCE;
            break;
        }
        checker = new DirectSpellChecker();
    } catch (ParseException e) {
        errorMsg = PARSE_ERROR_MSG + e.getMessage();
    } catch (FileNotFoundException e) {
        //          errorMsg = "Index database(s) not found: " + e.getMessage();
        errorMsg = "Index database(s) not found.";
    } catch (Exception e) {
        errorMsg = e.getMessage();
    }
    return this;
}

From source file:com.codeReading.core.opengrok.SearchHelper.java

License:Open Source License

/**
 * If a search did not return a hit, one may use this method to obtain
 * suggestions for a new search.//from   w  w  w.ja  v  a2s . c  o m
 *
 * <p> Parameters which should be populated/set at this time: <ul>
 * <li>{@link #projects}</li> <li>{@link #dataRoot}</li>
 * <li>{@link #builder}</li> </ul>
 *
 * @return a possible empty list of suggestions.
 */
public List<Suggestion> getSuggestions() {
    if (projects == null) {
        return new ArrayList<>(0);
    }
    String name[];
    if (projects.isEmpty()) {
        name = new String[] { "/" };
    } else if (projects.size() == 1) {
        name = new String[] { projects.first() };
    } else {
        name = new String[projects.size()];
        int ii = 0;
        for (String proj : projects) {
            name[ii++] = proj;
        }
    }
    List<Suggestion> res = new ArrayList<>();
    List<String> dummy = new ArrayList<>();
    FSDirectory dir;
    IndexReader ir = null;
    Term t;
    for (int idx = 0; idx < name.length; idx++) {
        Suggestion s = new Suggestion(name[idx]);
        try {
            dir = FSDirectory.open(new File(indexDir, name[idx]));
            ir = DirectoryReader.open(dir);
            if (builder.getFreetext() != null && !builder.getFreetext().isEmpty()) {
                t = new Term(QueryBuilder.FULL, builder.getFreetext());
                getSuggestion(t, ir, dummy);
                s.freetext = dummy.toArray(new String[dummy.size()]);
                dummy.clear();
            }
            if (builder.getRefs() != null && !builder.getRefs().isEmpty()) {
                t = new Term(QueryBuilder.REFS, builder.getRefs());
                getSuggestion(t, ir, dummy);
                s.refs = dummy.toArray(new String[dummy.size()]);
                dummy.clear();
            }
            if (builder.getDefs() != null && !builder.getDefs().isEmpty()) {
                t = new Term(QueryBuilder.DEFS, builder.getDefs());
                getSuggestion(t, ir, dummy);
                s.defs = dummy.toArray(new String[dummy.size()]);
                dummy.clear();
            }
            //TODO suggest also for path and history?
            if ((s.freetext != null && s.freetext.length > 0) || (s.defs != null && s.defs.length > 0)
                    || (s.refs != null && s.refs.length > 0)) {
                res.add(s);
            }
        } catch (IOException e) {
            log.log(Level.WARNING, "Got exception while getting " + "spelling suggestions: ", e);
        } finally {
            if (ir != null) {
                try {
                    ir.close();
                } catch (IOException ex) {
                    log.log(Level.WARNING, "Got exception while " + "getting spelling suggestions: ", ex);
                }
            }
        }
    }
    return res;
}

From source file:com.cohesionforce.search.EMFIndex.java

License:Open Source License

/**
 * Searches the index for an attribute with a matching value.
 * /*from w  w w. j  ava 2s . c  o  m*/
 * @param feature
 *            - the attribute to match when searching
 * @param value
 *            - the value to match when searching
 * @return a list of search results
 * @throws IllegalArgumentException
 *             if any parameters are null, or if the attribute is not marked
 *             with the search annotation
 * @throws IOException
 *             if there are issues reading the index
 */
public List<SearchResult> search(EStructuralFeature feature, String value)
        throws IllegalArgumentException, IOException {

    if (feature == null) {
        throw new IllegalArgumentException("Attribute cannot be null");
    }
    if (value == null) {
        throw new IllegalArgumentException("Value cannot be null");
    }

    List<SearchResult> rvalue = new ArrayList<SearchResult>();
    boolean tokenize = false;
    EAnnotation annotation = feature.getEAnnotation(EMFIndexUtil.SOURCE);
    if (annotation != null) {
        if (annotation.getDetails().containsKey(EMFIndexUtil.TOKENIZE_KEY)) {
            tokenize = true;
        }
    } else {
        // Bail out early if this feature should not be indexed
        throw new IllegalArgumentException("Attribute is not annotated to be indexed");
    }

    String key = EMFIndexUtil.getKey(feature);
    DirectoryReader reader = DirectoryReader.open(fsDir);
    IndexSearcher searcher = new IndexSearcher(reader);
    try {

        Query query = null;

        if (tokenize) {
            QueryParser parser = new QueryParser(version, key, analyzer);
            query = parser.parse(value);
        } else {
            Term term = new Term(key, value);
            query = new TermQuery(term);
        }

        ScoreDoc[] hits = searcher.search(query, null, MAX_SEARCH_RESULT).scoreDocs;

        // Iterate through the results:
        for (int i = 0; i < hits.length; i++) {
            Document hitDoc = searcher.doc(hits[i].doc);
            SearchResult result = new SearchResult(hitDoc);
            rvalue.add(result);
            logger.debug(hitDoc.toString());
        }
    } catch (ParseException e) {
        logger.error(e.getMessage());
    } finally {
        reader.close();
    }
    return rvalue;
}

From source file:com.cohesionforce.search.EMFIndex.java

License:Open Source License

/**
 * Searches the index for an attribute with a matching value and a matching
 * eclass//w w w .ja v a2  s  .c  om
 * 
 * @param eclass
 *            - the EClass to match when searching
 * @param attr
 *            - the EAttribute to match when searching
 * @param value
 *            - the value to match when searching
 * @return a list of search results
 * @throws IllegalArgumentException
 *             if any parameters are null, or if the attribute is not marked
 *             with the search annotation
 * @throws IOException
 *             if there are issues reading the index
 */
public List<SearchResult> search(EClass eclass, EAttribute attr, String value)
        throws IllegalArgumentException, IOException {

    if (eclass == null) {
        throw new IllegalArgumentException("EClass cannot be null");
    }
    if (attr == null) {
        throw new IllegalArgumentException("Attribute cannot be null");
    }
    if (value == null) {
        throw new IllegalArgumentException("Value cannot be null");
    }

    EAnnotation annotation = eclass.getEAnnotation(EMFIndexUtil.SOURCE);
    if (annotation == null) {
        // Bail out early if this feature should not be indexed
        throw new IllegalArgumentException("EClass is not annotated to be indexed");
    }
    List<SearchResult> rvalue = new ArrayList<SearchResult>();
    boolean tokenize = false;
    annotation = attr.getEAnnotation(EMFIndexUtil.SOURCE);
    if (annotation != null) {
        if (annotation.getDetails().containsKey(EMFIndexUtil.TOKENIZE_KEY)) {
            tokenize = true;
        }
    } else {
        // Bail out early if this feature should not be indexed
        throw new IllegalArgumentException("Attribute is not annotated to be indexed");
    }

    String key = EMFIndexUtil.getKey(attr);

    DirectoryReader reader = DirectoryReader.open(fsDir);
    IndexSearcher searcher = new IndexSearcher(reader);
    try {

        BooleanQuery bquery = new BooleanQuery();

        TermQuery classQuery = new TermQuery(new Term(EMFIndexUtil.ETYPE_KEY, eclass.getName()));
        bquery.add(classQuery, Occur.MUST);

        Query query = null;
        if (tokenize) {
            QueryParser parser = new QueryParser(version, key, analyzer);
            query = parser.parse(value);
        } else {
            Term term = new Term(key, value);
            query = new TermQuery(term);
        }
        bquery.add(query, Occur.MUST);

        ScoreDoc[] hits = searcher.search(bquery, null, MAX_SEARCH_RESULT).scoreDocs;
        // Iterate through the results:
        for (int i = 0; i < hits.length; i++) {
            Document hitDoc = searcher.doc(hits[i].doc);
            SearchResult result = new SearchResult(hitDoc);
            rvalue.add(result);
            logger.debug(hitDoc.toString());
        }
    } catch (ParseException e) {
        logger.error(e.getMessage());
    } finally {
        reader.close();
    }
    return rvalue;
}

From source file:com.cohesionforce.search.EMFIndex.java

License:Open Source License

/**
 * Searches the index for a matching eclass
 * //from  w ww.j  av  a 2  s.  co  m
 * @param eclass
 *            - the EClass to match when searching
 * @return a list of search results
 * @throws IllegalArgumentException
 *             if the eclass is null or is not annotated for indexing
 * @throws IOException
 *             if there are issues reading the index
 */
public List<SearchResult> search(EClass eclass) throws IllegalArgumentException, IOException {

    if (eclass == null) {
        throw new IllegalArgumentException("EClass cannot be null");
    }
    EAnnotation annotation = eclass.getEAnnotation(EMFIndexUtil.SOURCE);
    if (annotation == null) {
        throw new IllegalArgumentException("EClass is not annotated for indexing");
    }
    List<SearchResult> rvalue = new ArrayList<SearchResult>();

    DirectoryReader reader = DirectoryReader.open(fsDir);
    IndexSearcher searcher = new IndexSearcher(reader);
    try {
        TermQuery classQuery = new TermQuery(new Term(EMFIndexUtil.ETYPE_KEY, eclass.getName()));

        ScoreDoc[] hits = searcher.search(classQuery, null, MAX_SEARCH_RESULT).scoreDocs;
        // Iterate through the results:
        for (int i = 0; i < hits.length; i++) {
            Document hitDoc = searcher.doc(hits[i].doc);
            SearchResult result = new SearchResult(hitDoc);
            rvalue.add(result);
            logger.debug(hitDoc.toString());
        }
    } finally {
        reader.close();
    }
    return rvalue;
}

From source file:com.cohesionforce.search.EMFIndex.java

License:Open Source License

/**
 * Finds a document matching the object and returns the query used
 * /*from   w  w  w  .  j  ava2s  .co  m*/
 * @param object
 *            to search for in the index
 * @return the query that returns the document
 * @throws IllegalArgumentException
 *             if the object is null
 * @throws IOException
 *             if there are problems searching the index
 */
protected Query findDocument(EObject object) throws IllegalArgumentException, IOException {

    if (object == null) {
        throw new IllegalArgumentException("EObject cannot be null");
    }

    Query rvalue = null;

    DirectoryReader reader = DirectoryReader.open(fsDir);
    IndexSearcher searcher = new IndexSearcher(reader);
    try {

        BooleanQuery bquery = new BooleanQuery();

        TermQuery classQuery = new TermQuery(new Term(EMFIndexUtil.ETYPE_KEY, object.eClass().getName()));
        bquery.add(classQuery, Occur.MUST);

        TermQuery uriQuery = new TermQuery(
                new Term(EMFIndexUtil.DOCUMENT_URI_KEY, object.eResource().getURI().toString()));
        bquery.add(uriQuery, Occur.MUST);

        TermQuery fragmentQuery = new TermQuery(
                new Term(EMFIndexUtil.FRAGMENT_URI_KEY, object.eResource().getURIFragment(object)));
        bquery.add(fragmentQuery, Occur.MUST);

        ScoreDoc[] hits = searcher.search(bquery, null, 1).scoreDocs;
        // Iterate through the results:
        if (hits.length > 0) {
            rvalue = bquery;
        }
    } finally {
        reader.close();
    }
    return rvalue;
}

From source file:com.cohesionforce.search.EMFIndex.java

License:Open Source License

/**
 * Deletes a document matching the EObject
 * // ww w.ja va 2  s. c  om
 * @param obj
 * @throws IllegalArgumentException
 *             if EObject is null or the EObject is not contained in a
 *             resource
 * @throws IOException
 *             if there are issues saving the index
 */
public void deleteDocument(EObject obj) throws IllegalArgumentException, IOException {
    if (obj == null) {
        throw new IllegalArgumentException("EObject cannot be null");
    }
    if (obj.eResource() == null) {
        throw new IllegalArgumentException("EObject must be contained in a Resource");
    }

    Query query = findDocument(obj);
    if (query != null) {
        logger.debug("Deleting existing index for {}:{}", obj.eResource().getURI(),
                obj.eResource().getURIFragment(obj));
        writer.deleteDocuments(query);
        if (!holdCommits) {
            writer.commit();
        }
    }

    DirectoryReader reader = DirectoryReader.open(fsDir);

    ArrayList<String> names = new ArrayList<String>();
    for (AtomicReaderContext context : reader.leaves()) {
        for (FieldInfo fi : context.reader().getFieldInfos()) {
            if (!names.contains(fi.name)) {
                names.add(fi.name);
            }

        }
    }
    if (names.size() > 0) {
        MultiFieldQueryParser parser = new MultiFieldQueryParser(version, names.toArray(new String[] {}),
                analyzer);
        try {
            query = parser.parse(obj.eResource().getURIFragment(obj));
            IndexSearcher searcher = new IndexSearcher(reader);

            ScoreDoc[] hits = searcher.search(query, null, MAX_SEARCH_RESULT).scoreDocs;
            for (ScoreDoc hit : hits) {
                Document hitDoc = searcher.doc(hit.doc);
                logger.debug("Hanging reference in: {}",
                        hitDoc.getField(EMFIndexUtil.DOCUMENT_URI_KEY).stringValue());
            }
        } catch (ParseException e) {
            logger.error(e.getMessage());
        }

    }
}