Example usage for org.apache.lucene.index IndexReader document

List of usage examples for org.apache.lucene.index IndexReader document

  1. HOME
  2. Java
  3. org.apache.lucene
  4. org.apache.lucene.index.*
  5. IndexReader
  6. document

Introduction

In this page you can find the example usage for org.apache.lucene.index IndexReader document.

Prototype

public final Document document(int docID, Set<String> fieldsToLoad) throws IOException

Source Link

Document

Like #document(int) but only loads the specified fields.

Usage

From source file:com.esri.gpt.catalog.arcgis.agportal.publication.ItemInfoLuceneAdapter.java

License:Apache License

/**
 * Returns the field values associated with a document
 * //from   w  ww  . j  a  v a 2 s.  co  m
 * @param context
 *          the operation context
 * @param fields
 *          array of fields to fetch
 * @param uuid
 *          the document uuid
 * @return the field values (null if not found)
 * @throws CorruptIndexException
 *           if the index is corrupt
 * @throws IOException
 *           if an I/O exception occurs
 */
public ESRI_ItemInformation makeItemInfoByUuid(RequestContext context, String[] fields, String uuid)
        throws CorruptIndexException, IOException {
    TermDocs termDocs = null;
    IndexReader reader = null;
    MapFieldSelector selector = null;
    try {
        uuid = Val.chkStr(uuid);
        if (uuid.length() > 0) {
            IndexSearcher srch = this.getSearcher(context);
            reader = srch.getIndexReader();
            if (fields != null) {
                selector = new MapFieldSelector(fields);
            }
            termDocs = reader.termDocs();
            termDocs.seek(new Term(Storeables.FIELD_UUID, uuid));
            if (termDocs.next()) {
                Document document = reader.document(termDocs.doc(), selector);
                List<Fieldable> flds = document.getFields();

                ESRI_ItemInformation itemInfo = new ESRI_ItemInformation();
                itemInfo.setType("Map Service");
                itemInfo.setTags(Arrays.asList(new String[] { "ArcGIS", "Server map", "service" }));

                Envelope extent = new Envelope();
                for (Fieldable fld : flds) {
                    String fieldName = fld.name();
                    String[] vals = document.getValues(fieldName);
                    if (fieldName.contains("uuid")) {
                        itemInfo.setId(vals[0].replaceAll("^\\{|\\}$|\\-", ""));
                    } else if (fieldName.contains("title")) {
                        itemInfo.setTitle(vals[0]);
                        itemInfo.setName(vals[0]);
                    } else if (fieldName.contains("resource.url")) {
                        itemInfo.setUrl(vals[0]);
                        String type = Val.chkStr(guessServiceTypeFromUrl(vals[0]));
                        if (type.length() > 0) {
                            itemInfo.setType(type);
                        }
                    } else if (fieldName.contains("contentType")) {
                    } else if (fieldName.contains("keywords")) {
                        itemInfo.setTypeKeywords(Arrays.asList(vals));
                        itemInfo.setTags(Arrays.asList(vals));
                    } else if (fieldName.contains("dataTheme")) {
                        itemInfo.setTags(Arrays.asList(vals));
                    } else if (fieldName.contains("abstract")) {
                        itemInfo.setDescription(vals[0]);
                        //                  } else if (fieldName.contains("xml")) {
                        //                     itemInfo.setXml(vals[0]);
                    } else if (fieldName.contains("minx")) {
                        extent.setMinX(vals[0]);
                    } else if (fieldName.contains("miny")) {
                        extent.setMinY(vals[0]);
                    } else if (fieldName.contains("maxx")) {
                        extent.setMaxX(vals[0]);
                    } else if (fieldName.contains("maxy")) {
                        extent.setMaxY(vals[0]);
                    } else if (fieldName.contains("thumbnail.url")) {
                        itemInfo.setThumbnailUrl(vals[0]);
                    }
                }
                itemInfo.setExtent(extent);
                return itemInfo;
            }
        }
    } finally {
        try {
            if (termDocs != null)
                termDocs.close();
            if (reader != null)
                reader.close();
        } catch (Exception ef) {
        }
    }
    return null;
}

From source file:com.esri.gpt.catalog.lucene.LuceneIndexAdapter.java

License:Apache License

/**
 * Queries the ACL values indexed for a document.
 * @param uuid the document UUID//from  www.jav  a  2 s  .  c o m
 * @return the ACL values (can be null)
 * @throws CatalogIndexException if an exception occurs
 */
@Override
public String[] queryAcls(String uuid) throws CatalogIndexException {
    ArrayList<String> values = new ArrayList<String>();
    IndexSearcher searcher = null;
    TermDocs termDocs = null;
    try {
        uuid = Val.chkStr(uuid);
        if (uuid.length() > 0) {
            searcher = newSearcher();
            String[] aFields = new String[] { Storeables.FIELD_ACL };
            MapFieldSelector selector = new MapFieldSelector(aFields);
            searcher = newSearcher();
            IndexReader reader = searcher.getIndexReader();
            termDocs = reader.termDocs();
            termDocs.seek(new Term(Storeables.FIELD_UUID, uuid));
            if (termDocs.next()) {
                Document document = reader.document(termDocs.doc(), selector);
                Field[] fields = document.getFields(Storeables.FIELD_ACL);
                if ((fields != null) && (fields.length > 0)) {
                    for (Field field : fields) {
                        values.add(field.stringValue());
                    }
                }
            }
        }
    } catch (IOException e) {
        String sMsg = "Error accessing index:\n " + Val.chkStr(e.getMessage());
        throw new CatalogIndexException(sMsg, e);
    } finally {
        try {
            if (termDocs != null)
                termDocs.close();
        } catch (Exception ef) {
        }
        closeSearcher(searcher);
    }
    return values.toArray(new String[0]);
}

From source file:com.esri.gpt.catalog.lucene.LuceneIndexAdapter.java

License:Apache License

/**
 * Queries the system modified date associated with an indexed document.
 * @param uuid the document UUID/*w  w w.j av  a2 s. c o  m*/
 * @return the update date (null if none was found)
 * @throws CatalogIndexException if an exception occurs
 */
@Override
public Timestamp queryModifiedDate(String uuid) throws CatalogIndexException {
    Timestamp tsUpdate = null;
    IndexSearcher searcher = null;
    TermDocs termDocs = null;
    try {
        uuid = Val.chkStr(uuid);
        if (uuid.length() > 0) {
            String[] aFields = new String[] { Storeables.FIELD_DATEMODIFIED };
            MapFieldSelector selector = new MapFieldSelector(aFields);
            searcher = newSearcher();
            IndexReader reader = searcher.getIndexReader();
            termDocs = reader.termDocs();
            termDocs.seek(new Term(Storeables.FIELD_UUID, uuid));
            if (termDocs.next()) {
                Document document = reader.document(termDocs.doc(), selector);
                String sUpdate = document.get(Storeables.FIELD_DATEMODIFIED);
                tsUpdate = new Timestamp(Long.valueOf(sUpdate));
            }
        }
    } catch (IOException e) {
        String sMsg = "Error accessing index:\n " + Val.chkStr(e.getMessage());
        throw new CatalogIndexException(sMsg, e);
    } finally {
        try {
            if (termDocs != null)
                termDocs.close();
        } catch (Exception ef) {
        }
        closeSearcher(searcher);
    }
    return tsUpdate;
}

From source file:com.esri.gpt.control.search.browse.TocIndexAdapter.java

License:Apache License

/**
 * Returns the field values associated with a document
 * @param context the operation context/*from   www . ja v  a  2s.co  m*/
 * @param fieldName the field name
 * @param uuid the document uuid
 * @return the field values (null if not found)
 * @throws CorruptIndexException if the index is corrupt
 * @throws IOException if an I/O exception occurs
 */
public String[] queryFieldByUuid(TocContext context, String fieldName, String uuid)
        throws CorruptIndexException, IOException {
    TermDocs termDocs = null;
    try {
        uuid = Val.chkStr(uuid);
        if (uuid.length() > 0) {
            IndexSearcher searcher = this.getSearcher(context);
            IndexReader reader = searcher.getIndexReader();
            MapFieldSelector selector = new MapFieldSelector(new String[] { fieldName });
            termDocs = reader.termDocs();
            termDocs.seek(new Term(Storeables.FIELD_UUID, uuid));
            if (termDocs.next()) {
                Document document = reader.document(termDocs.doc(), selector);
                return document.getValues(fieldName);
            }
        }
    } finally {
        try {
            if (termDocs != null)
                termDocs.close();
        } catch (Exception ef) {
        }
    }
    return null;
}

From source file:com.github.hotware.lucene.extension.highlight.BaseObjectFragmentsBuilder.java

License:BEER-WARE LICENSE

private static Field[] getFields(IndexReader reader, int docId, final String fieldName) throws IOException {
    // according to javadoc, doc.getFields(fieldName) cannot be used with
    // lazy loaded field???
    final List<Field> fields = new ArrayList<>();
    reader.document(docId, new StoredFieldVisitor() {

        @Override//from   w w  w .  j a  va 2s .  c  o m
        public void stringField(FieldInfo fieldInfo, String value) {
            FieldType ft = new FieldType(TextField.TYPE_STORED);
            ft.setStoreTermVectors(fieldInfo.hasVectors());
            fields.add(new Field(fieldInfo.name, value, ft));
        }

        @Override
        public Status needsField(FieldInfo fieldInfo) {
            return fieldInfo.name.equals(fieldName) ? Status.YES : Status.NO;
        }

    });
    return fields.toArray(new Field[fields.size()]);
}

From source file:com.gnizr.core.search.SearchIndexManager.java

License:Mozilla Public License

/**
 * Finds the representative bookmark document for a ginve URL hash.
 * //from   www  .ja v  a 2 s .c  om
 * @param urlHash
 *            a URL MD5 Hash.
 * 
 * @return a Lucene document of the representative bookmark
 */
public Document findLeadDocument(String urlHash) {
    IndexReader reader = null;
    TermDocs termDocs = null;
    Document leadDoc = null;
    try {
        boolean exists = IndexReader.indexExists(indexDirectory);
        if (exists == true) {
            reader = IndexReader.open(indexDirectory);
            Term key = new Term(DocumentCreator.FIELD_URL_MD5, urlHash);
            termDocs = reader.termDocs(key);
            boolean found = false;
            while (termDocs.next() && found == false) {
                int pos = termDocs.doc();
                // use FieldSelector for more efficient loading of Fields.
                // load only what's needed to determine a leading document
                Document d = reader.document(pos, new FieldSelector() {
                    private static final long serialVersionUID = 1426724242925499003L;

                    public FieldSelectorResult accept(String field) {
                        if (field.equals(DocumentCreator.FIELD_INDEX_TYPE)) {
                            return FieldSelectorResult.LOAD_AND_BREAK;
                        } else {
                            return FieldSelectorResult.NO_LOAD;
                        }
                    }
                });
                String[] values = d.getValues(DocumentCreator.FIELD_INDEX_TYPE);
                if (values != null) {
                    List<String> vList = Arrays.asList(values);
                    if (vList.contains(DocumentCreator.INDEX_TYPE_LEAD) == true) {
                        leadDoc = reader.document(pos);
                        found = true;
                    }
                }
            }
        }
    } catch (Exception e) {
        logger.error("FindLeadDocument failed to find doc: " + urlHash + ", exception=" + e);
    } finally {
        try {
            if (termDocs != null) {
                termDocs.close();
            }
            if (reader != null) {
                reader.close();
            }
        } catch (Exception e) {
            logger.error("FindLeadDocument can't close reader or termDocs: " + e);
        }
    }
    return leadDoc;
}

From source file:com.gnizr.core.search.SearchIndexManager.java

License:Mozilla Public License

/**
 * Finds a non-representative bookmark document for a given URL hash.
 * /*from   w w w  .j  a v  a2  s.  c om*/
 * @param urlHash
 *            a URL MD5 Hash.
 * 
 * @return a Lucene document of a non-representative bookmark
 */
public Document findNonLeadDocument(String urlHash) {
    IndexReader reader = null;
    TermDocs termDocs = null;
    Document leadDoc = null;
    try {
        boolean exists = IndexReader.indexExists(indexDirectory);
        if (exists == true) {
            reader = IndexReader.open(indexDirectory);
            Term key = new Term(DocumentCreator.FIELD_URL_MD5, urlHash);
            termDocs = reader.termDocs(key);
            boolean found = false;
            while (termDocs.next() && found == false) {
                int pos = termDocs.doc();
                // use FieldSelector for more efficient loading of Fields.
                // load only what's needed to determine a leading document
                Document d = reader.document(pos, new FieldSelector() {
                    private static final long serialVersionUID = 1426724242925499003L;

                    public FieldSelectorResult accept(String field) {
                        if (field.equals(DocumentCreator.FIELD_INDEX_TYPE)) {
                            return FieldSelectorResult.LOAD_AND_BREAK;
                        } else {
                            return FieldSelectorResult.NO_LOAD;
                        }
                    }

                });
                String[] values = d.getValues(DocumentCreator.FIELD_INDEX_TYPE);
                if (values != null) {
                    List<String> vList = Arrays.asList(values);
                    if (vList.contains(DocumentCreator.INDEX_TYPE_LEAD) == false) {
                        leadDoc = reader.document(pos);
                        found = true;
                    }
                } else {
                    leadDoc = reader.document(pos);
                    found = true;
                }
            }
        }
    } catch (Exception e) {
        logger.error("FindLeadDocument failed to find doc hash: " + urlHash + ", exception=" + e);
    } finally {
        try {
            if (termDocs != null) {
                termDocs.close();
            }
            if (reader != null) {
                reader.close();
            }
        } catch (Exception e) {
            logger.error("FindLeadDocument can't close reader or termDocs: " + e);
        }
    }
    return leadDoc;
}

From source file:com.nearinfinity.blur.manager.IndexManager.java

License:Apache License

public static void fetchRow(IndexReader reader, String table, Selector selector, FetchResult fetchResult)
        throws CorruptIndexException, IOException {
    fetchResult.table = table;//w ww. j a  v  a 2 s.co m
    String locationId = selector.locationId;
    int lastSlash = locationId.lastIndexOf('/');
    int docId = Integer.parseInt(locationId.substring(lastSlash + 1));
    if (docId >= reader.maxDoc()) {
        throw new RuntimeException("Location id [" + locationId + "] with docId [" + docId + "] is not valid.");
    }
    if (selector.isRecordOnly()) {
        // select only the row for the given data or location id.
        if (reader.isDeleted(docId)) {
            fetchResult.exists = false;
            fetchResult.deleted = true;
            return;
        } else {
            fetchResult.exists = true;
            fetchResult.deleted = false;
            Document document = reader.document(docId, getFieldSelector(selector));
            fetchResult.recordResult = getColumns(document);
            return;
        }
    } else {
        if (reader.isDeleted(docId)) {
            fetchResult.exists = false;
            fetchResult.deleted = true;
            return;
        } else {
            fetchResult.exists = true;
            fetchResult.deleted = false;
            String rowId = getRowId(reader, docId);
            TermDocs termDocs = reader.termDocs(new Term(ROW_ID, rowId));
            fetchResult.rowResult = new FetchRowResult(
                    getRow(new TermDocIterable(termDocs, reader, getFieldSelector(selector))));
            return;
        }
    }
}

From source file:com.nearinfinity.blur.manager.IndexManager.java

License:Apache License

private static String getRowId(IndexReader reader, int docId) throws CorruptIndexException, IOException {
    Document document = reader.document(docId, new FieldSelector() {
        private static final long serialVersionUID = 4912420100148752051L;

        @Override//from   ww w .ja va 2  s  . c o  m
        public FieldSelectorResult accept(String fieldName) {
            if (ROW_ID.equals(fieldName)) {
                return FieldSelectorResult.LOAD_AND_BREAK;
            }
            return FieldSelectorResult.NO_LOAD;
        }
    });
    return document.get(ROW_ID);
}

From source file:com.o19s.solr.swan.highlight.BaseFragmentsBuilder.java

License:Apache License

protected Field[] getFields(IndexReader reader, int docId, final String fieldName) throws IOException {
    // according to javadoc, doc.getFields(fieldName) cannot be used with lazy loaded field???
    final List<Field> fields = new ArrayList<Field>();
    reader.document(docId, new StoredFieldVisitor() {

        @Override/*w  w w .  jav a 2 s  .com*/
        public void stringField(FieldInfo fieldInfo, String value) {
            FieldType ft = new FieldType(TextField.TYPE_STORED);
            ft.setStoreTermVectors(fieldInfo.hasVectors());
            fields.add(new Field(fieldInfo.name, value, ft));
        }

        @Override
        public Status needsField(FieldInfo fieldInfo) {
            return fieldInfo.name.equals(fieldName) ? Status.YES : Status.NO;
        }
    });
    return fields.toArray(new Field[fields.size()]);
}