Example usage for org.apache.lucene.index IndexableField binaryValue

List of usage examples for org.apache.lucene.index IndexableField binaryValue

  1. HOME
  2. Java
  3. org.apache.lucene
  4. org.apache.lucene.index.*
  5. IndexableField
  6. binaryValue

Introduction

In this page you can find the example usage for org.apache.lucene.index IndexableField binaryValue.

Prototype

public BytesRef binaryValue();

Source Link

Document

Non-null if this field has a binary value

Usage

From source file:com.basistech.lucene.tools.LuceneQueryTool.java

License:Apache License

private void printDocument(Document doc, int id, float score, PrintStream out) {
    Multimap<String, String> data = ArrayListMultimap.create();
    List<String> orderedFieldNames = Lists.newArrayList();
    if (showId) {
        orderedFieldNames.add("<id>");
        data.put("<id>", Integer.toString(id));
    }//w w w . j  a v a2s.c  o m
    if (showScore) {
        orderedFieldNames.add("<score>");
        data.put("<score>", Double.toString(score));
    }
    orderedFieldNames.addAll(fieldNames);

    Set<String> setFieldNames = Sets.newHashSet();
    if (fieldNames.isEmpty()) {
        for (IndexableField f : doc.getFields()) {
            if (!setFieldNames.contains(f.name())) {
                orderedFieldNames.add(f.name());
            }
            setFieldNames.add(f.name());
        }
    } else {
        setFieldNames.addAll(fieldNames);
    }
    if (sortFields) {
        Collections.sort(orderedFieldNames);
    }

    for (IndexableField f : doc.getFields()) {
        if (setFieldNames.contains(f.name())) {
            if (f.stringValue() != null) {
                data.put(f.name(), f.stringValue());
            } else if (f.binaryValue() != null) {
                data.put(f.name(), formatBinary(f.binaryValue().bytes));
            } else {
                data.put(f.name(), "null");
            }
        }
    }

    if (docsPrinted == 0 && formatter.getFormat() == Formatter.Format.TABULAR && !formatter.suppressNames()) {

        out.println(Joiner.on('\t').join(orderedFieldNames));
    }

    String formatted = formatter.format(orderedFieldNames, data);
    if (!formatted.isEmpty()) {
        if (docsPrinted > 0 && formatter.getFormat() == Formatter.Format.MULTILINE) {
            out.println();
        }
        out.println(formatted);
        ++docsPrinted;
    }
}

From source file:com.codeReading.core.opengrok.search.Results.java

License:Open Source License

/**
 * Prints out results in html form. The following search helper fields are
 * required to be properly initialized: <ul>
 * <li>{@link SearchHelper#dataRoot}</li>
 * <li>{@link SearchHelper#contextPath}</li>
 * <li>{@link SearchHelper#searcher}</li> <li>{@link SearchHelper#hits}</li>
 * <li>{@link SearchHelper#historyContext} (ignored if {@code null})</li>
 * <li>{@link SearchHelper#sourceContext} (ignored if {@code null})</li>
 * <li>{@link SearchHelper#summerizer} (if sourceContext is not
 * {@code null})</li> <li>{@link SearchHelper#compressed} (if sourceContext
 * is not {@code null})</li> <li>{@link SearchHelper#sourceRoot} (if
 * sourceContext or historyContext is not {@code null})</li> </ul>
 *
 * @param out write destination//from  w  w w. j  av a2s  . c om
 * @param sh search helper which has all required fields set
 * @param start index of the first hit to print
 * @param end index of the last hit to print
 * @throws HistoryException
 * @throws IOException
 * @throws ClassNotFoundException
 */
public static void prettyPrint(Writer out, SearchHelper sh, int start, int end)
        throws HistoryException, IOException, ClassNotFoundException {
    String ctxE = Util.URIEncodePath(sh.contextPath);
    String xrefPrefix = sh.contextPath + Prefix.XREF_P;
    String morePrefix = sh.contextPath + Prefix.MORE_P;
    String xrefPrefixE = ctxE + Prefix.XREF_P;
    File xrefDataDir = new File(sh.dataRoot, Prefix.XREF_P.toString());

    for (Map.Entry<String, ArrayList<Document>> entry : createMap(sh.searcher, sh.hits, start, end)
            .entrySet()) {
        String parent = entry.getKey();
        out.write("<tr class=\"dir\"><td colspan=\"3\"><a href=\"");
        out.write(xrefPrefixE);
        out.write(Util.URIEncodePath(parent));
        out.write("/\">");
        out.write(parent); // htmlize ???
        out.write("/</a>");
        if (sh.desc != null) {
            out.write(" - <i>");
            out.write(sh.desc.get(parent)); // htmlize ???
            out.write("</i>");
        }
        out.write("</td></tr>");
        for (Document doc : entry.getValue()) {
            String rpath = doc.get("path");
            String rpathE = Util.URIEncodePath(rpath);
            out.write("<tr>");
            //Util.writeHAD(out, sh.contextPath, rpathE, false);
            out.write("<td class=\"f\"><a href=\"");
            out.write(xrefPrefixE);
            out.write(rpathE);
            out.write("\">");
            out.write(rpath.substring(rpath.lastIndexOf('/') + 1)); // htmlize ???
            out.write("</a></td><td><tt class=\"con\">");
            if (sh.sourceContext != null) {
                Genre genre = Genre.get(doc.get("t"));
                Definitions tags = null;
                IndexableField tagsField = doc.getField("tags");
                if (tagsField != null) {
                    tags = Definitions.deserialize(tagsField.binaryValue().bytes);
                }
                if (Genre.XREFABLE == genre && sh.summerizer != null) {
                    String xtags = getTags(xrefDataDir, rpath, sh.compressed);
                    // FIXME use Highlighter from lucene contrib here,
                    // instead of summarizer, we'd also get rid of
                    // apache lucene in whole source ...
                    out.write(sh.summerizer.getSummary(xtags).toString());
                } else if (Genre.HTML == genre && sh.summerizer != null) {
                    String htags = getTags(sh.sourceRoot, rpath, false);
                    out.write(sh.summerizer.getSummary(htags).toString());
                } else {
                    FileReader r = genre == Genre.PLAIN ? new FileReader(new File(sh.sourceRoot, rpath)) : null;
                    sh.sourceContext.getContext(r, out, xrefPrefix, morePrefix, rpath, tags, true,
                            sh.builder.isDefSearch(), null);
                }
            }
            if (sh.historyContext != null) {
                sh.historyContext.getContext(new File(sh.sourceRoot, rpath), rpath, out, sh.contextPath);
            }
            out.write("</tt></td></tr>\n");
        }
    }
}

From source file:com.core.nlp.document.Document.java

License:Apache License

/**
* Returns an array of byte arrays for of the fields that have the name specified
* as the method parameter.  This method returns an empty
* array when there are no matching fields.  It never
* returns null.//ww w  .  ja  va2 s.  co  m
*
* @param name the name of the field
* @return a <code>BytesRef[]</code> of binary field values
*/
public final BytesRef[] getBinaryValues(String name) {
    final List<BytesRef> result = new ArrayList<>();
    for (IndexableField field : fields) {
        if (field.name().equals(name)) {
            final BytesRef bytes = field.binaryValue();
            if (bytes != null) {
                result.add(bytes);
            }
        }
    }

    return result.toArray(new BytesRef[result.size()]);
}

From source file:com.core.nlp.document.Document.java

License:Apache License

/**
* Returns an array of bytes for the first (or only) field that has the name
* specified as the method parameter. This method will return <code>null</code>
* if no binary fields with the specified name are available.
* There may be non-binary fields with the same name.
*
* @param name the name of the field.//from  ww w  .j a v a 2  s .co  m
* @return a <code>BytesRef</code> containing the binary field value or <code>null</code>
*/
public final BytesRef getBinaryValue(String name) {
    for (IndexableField field : fields) {
        if (field.name().equals(name)) {
            final BytesRef bytes = field.binaryValue();
            if (bytes != null) {
                return bytes;
            }
        }
    }
    return null;
}

From source file:com.doculibre.constellio.services.ImportExportServicesImpl.java

License:Open Source License

@SuppressWarnings("unchecked")
@Override//from www.  java  2 s. co  m
public void importData(Directory directory, RecordCollection collection, ProgressInfo progressInfo) {
    try {
        ConnectorInstance connectorInstance = collection.getConnectorInstances().iterator().next();
        RecordServices recordServices = ConstellioSpringUtils.getRecordServices();

        String uniqueKeyMetaName = null;
        IndexField uniqueKeyIndexField = collection.getUniqueKeyIndexField();
        for (ConnectorInstanceMeta connectorInstanceMeta : uniqueKeyIndexField.getConnectorInstanceMetas()) {
            if (connectorInstance.equals(connectorInstanceMeta.getConnectorInstance())) {
                uniqueKeyMetaName = connectorInstanceMeta.getName();
                break;
            }
        }

        Pattern invalidDatePattern = Pattern
                .compile("^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}(\\.[0-9]*)?$");

        IndexReader indexReader = DirectoryReader.open(directory);
        if (progressInfo != null) {
            progressInfo.setTotal(indexReader.numDocs());
        }
        for (int i = 0; i < indexReader.numDocs(); i++) {
            Document document = indexReader.document(i);

            Record record = new Record();
            record.setLastModified(new Date());
            record.setConnectorInstance(connectorInstance);

            for (IndexableField field : document.getFields()) {
                // for (String fieldName : (Collection<String>)
                // indexReader.getFieldNames(FieldOption.ALL)) {
                if (field != null && field.fieldType().stored() && field.binaryValue() == null) {
                    String metaName = field.name();
                    String metaContent = field.stringValue();

                    Matcher invalidDateMatcher = invalidDatePattern.matcher(metaContent);
                    if (invalidDateMatcher.matches()) {
                        metaContent = metaContent + "Z";
                    }

                    if (uniqueKeyMetaName.equals(metaName)) {
                        record.setUrl(metaContent);
                    }

                    RecordMeta meta = new RecordMeta();
                    ConnectorInstanceMeta connectorInstanceMeta = connectorInstance.getOrCreateMeta(metaName);
                    meta.setConnectorInstanceMeta(connectorInstanceMeta);
                    meta.setRecord(record);
                    meta.setContent(metaContent);
                    record.addContentMeta(meta);
                }
            }

            try {
                recordServices.makePersistent(record);

                // if (i % 500 == 0) {
                // EntityManager entityManager =
                // ConstellioPersistenceContext.getCurrentEntityManager();
                // entityManager.getTransaction().commit();
                // entityManager.getTransaction().begin();
                // }
            } catch (Exception e) {
                e.printStackTrace();
            }

            if (progressInfo != null) {
                progressInfo.setCurrentIndex(i);
            }
        }

        indexReader.close();
    } catch (IOException e) {
        throw new RuntimeException(e);
    }
}

From source file:com.doculibre.constellio.services.ImportExportServicesImpl.java

License:Open Source License

@SuppressWarnings("unchecked")
@Override// w  w w.  j a v a 2s . c  o  m
public void convertData(Directory directory, OutputStream output) {
    try {
        WritableWorkbook workbook = Workbook.createWorkbook(output);
        WritableSheet sheet = workbook.createSheet("fields", 0);

        WritableFont arial10font = new WritableFont(WritableFont.ARIAL, 10);
        WritableCellFormat arial10format = new WritableCellFormat(arial10font);
        IndexReader indexReader = DirectoryReader.open(directory);

        //         {
        //         int column = 0;
        //         for (String fieldName : (Collection<String>) indexReader.getFieldNames()) {
        //            Label label = new Label(column, 0, fieldName, arial10format);
        //            sheet.addCell(label);
        //            column++;
        //         }
        //         }

        int row = 1;
        for (int i = 0; i < indexReader.numDocs() /* && i != 502 */; i++) {
            Document document = indexReader.document(i);
            int column = 0;
            for (IndexableField field : document.getFields()) {
                if (row == 1) {
                    Label label = new Label(column, 0, field.name(), arial10format);
                    sheet.addCell(label);
                }

                if (field != null && field.fieldType().stored() && field.binaryValue() == null) {
                    String indexedContent = field.stringValue();
                    indexedContent = convertText(indexedContent);
                    Label label = new Label(column, row, indexedContent, arial10format);
                    sheet.addCell(label);
                }
                column++;
            }
            row++;
            // if (i == 502) {
            // break;
            // }
        }

        indexReader.close();
        workbook.write();
        workbook.close();
    } catch (IOException e) {
        throw new RuntimeException(e);
    } catch (RowsExceededException e) {
        throw new RuntimeException(e);
    } catch (WriteException e) {
        throw new RuntimeException(e);
    }
}

From source file:com.epimorphics.server.indexers.LuceneResult.java

License:Apache License

/**
 * Returns all the values of a field. These will be either Strings (for literals and labels),
 * Resources (for URI fields) or Longs (for numeric fields)
 *//*from w w  w. j a  v  a 2 s  .  c  o m*/
public Object[] fieldValues(String fieldName) {
    IndexableField[] fields = doc.getFields(fieldName);
    Object[] results = new Object[fields.length];
    for (int i = 0; i < fields.length; i++) {
        IndexableField field = fields[i];
        Object value = field.numericValue();
        if (value == null) {
            value = field.stringValue();
        }
        if (value == null) {
            BytesRef ref = field.binaryValue();
            value = ResourceFactory.createResource(ref.utf8ToString());
        }
        results[i] = value;
    }
    return results;
}

From source file:com.gemstone.gemfire.cache.lucene.internal.repository.serializer.SerializerUtil.java

License:Apache License

/**
 * Extract the gemfire key from a lucene document
 *//*from  w w w  .j a v  a  2  s .  com*/
public static Object getKey(Document doc) {
    IndexableField field = doc.getField(KEY_FIELD);
    if (field.stringValue() != null) {
        return field.stringValue();
    } else {
        return keyFromBytes(field.binaryValue());
    }
}

From source file:com.gemstone.gemfire.cache.lucene.internal.repository.serializer.SerializerUtil.java

License:Apache License

/**
 * Extract the gemfire key term from a lucene document
 *///  w w w  . j a v  a2  s .  com
public static Term getKeyTerm(Document doc) {
    IndexableField field = doc.getField(KEY_FIELD);
    if (field.stringValue() != null) {
        return new Term(KEY_FIELD, field.stringValue());
    } else {
        return new Term(KEY_FIELD, field.binaryValue());
    }
}

From source file:com.lucure.core.codec.CompressingStoredFieldsWriter.java

License:Apache License

@Override
public void writeField(FieldInfo info, IndexableField field) throws IOException {

    ++numStoredFieldsInDoc;/*  w ww.  j av a  2 s.c  o  m*/

    int bits = 0;
    final BytesRef bytes;

    Number number = field.numericValue();
    if (number != null) {
        if (number instanceof Byte || number instanceof Short || number instanceof Integer) {
            bits = NUMERIC_INT;
        } else if (number instanceof Long) {
            bits = NUMERIC_LONG;
        } else if (number instanceof Float) {
            bits = NUMERIC_FLOAT;
        } else if (number instanceof Double) {
            bits = NUMERIC_DOUBLE;
        } else {
            throw new IllegalArgumentException("cannot store numeric type " + number.getClass());
        }
        bytes = null;
    } else {
        bytes = field.binaryValue();
        if (bytes != null) {
            bits = BYTE_ARR;
        } else {
            bits = STRING;
            if (field.stringValue() == null) {
                throw new IllegalArgumentException("field " + field.name()
                        + " is stored but does not have binaryValue, stringValue nor numericValue");
            }
        }
    }

    final long infoAndBits = (((long) info.number) << TYPE_BITS) | bits;
    bufferedDocs.writeVLong(infoAndBits);

    boolean isRestricted = field instanceof RestrictedField;

    //set restricted
    bufferedDocs.writeByte((byte) (isRestricted ? 1 : 0));
    if (isRestricted) {
        RestrictedField restrictedField = (RestrictedField) field;
        byte[] expression = restrictedField.getFieldVisibility().getExpression();
        bufferedDocs.writeVInt(expression.length);
        bufferedDocs.writeBytes(expression, 0, expression.length);
    }

    switch (bits) {
    case BYTE_ARR:
        bufferedDocs.writeVInt(bytes.length);
        bufferedDocs.writeBytes(bytes.bytes, bytes.offset, bytes.length);
        break;
    case STRING:
        bufferedDocs.writeString(field.stringValue());
        break;
    default:
        if (number instanceof Byte || number instanceof Short || number instanceof Integer) {
            bufferedDocs.writeInt(number.intValue());
        } else if (number instanceof Long) {
            bufferedDocs.writeLong(number.longValue());
        } else if (number instanceof Float) {
            bufferedDocs.writeInt(Float.floatToIntBits(number.floatValue()));
        } else {
            bufferedDocs.writeLong(Double.doubleToLongBits(number.doubleValue()));
        }
        break;
    }
}