Example usage for org.apache.solr.common SolrInputField getFirstValue

List of usage examples for org.apache.solr.common SolrInputField getFirstValue

  1. HOME
  2. Java
  3. org.apache.solr
  4. org.apache.solr.common.*
  5. SolrInputField
  6. getFirstValue

Introduction

In this page you can find the example usage for org.apache.solr.common SolrInputField getFirstValue.

Prototype

public Object getFirstValue()

Source Link

Usage

From source file:com.francelabs.datafari.updateprocessor.DatafariUpdateProcessor.java

License:Apache License

@Override
public void processAdd(final AddUpdateCommand cmd) throws IOException {
    final SolrInputDocument doc = cmd.getSolrInputDocument();

    // Sometimes Tika put several ids so we keep the first one which is
    // always the right one
    if (doc.getFieldValues("id").size() > 1) {
        final Object id = doc.getFieldValue("id");
        doc.remove("id");
        doc.addField("id", id);
    }/*from  w  w w . jav a 2s .  co m*/

    // Try to retrieve at the ignored_filelastmodified field to set it's
    // value in the last_modified field
    if (doc.getFieldValue("ignored_filelastmodified") != null) {
        final Object last_modified = doc.getFieldValue("ignored_filelastmodified");
        doc.remove("last_modified");
        doc.addField("last_modified", last_modified);
    }

    // Sometimes Tika put several last_modified dates, so we keep the first
    // one which is always the right one
    if ((doc.getFieldValues("last_modified") != null) && (doc.getFieldValues("last_modified").size() > 1)) {
        final Object last_modified = doc.getFieldValue("last_modified");
        doc.remove("last_modified");
        doc.addField("last_modified", last_modified);
    }

    final String url = (String) doc.getFieldValue("id");

    // Create path hierarchy for facet
    final List<String> urlHierarchy = new ArrayList<>();

    /*
     * // Create path hierarchy for facet
     *
     * final List<String> urlHierarchy = new ArrayList<String>();
     *
     * final String path = url.replace("file:", ""); int previousIndex = 1; int
     * depth = 0; // Tokenize the path and add the depth as first character for
     * each token // (like: 0/home, 1/home/project ...) for (int i = 0; i <
     * path.split("/").length - 2; i++) { int endIndex = path.indexOf('/',
     * previousIndex); if (endIndex == -1) { endIndex = path.length() - 1; }
     * urlHierarchy.add(depth + path.substring(0, endIndex)); depth++;
     * previousIndex = endIndex + 1; }
     *
     * // Add the tokens to the urlHierarchy field doc.addField("urlHierarchy",
     * urlHierarchy);
     */

    doc.addField("url", url);

    String filename = "";
    final SolrInputField streamNameField = doc.get("ignored_stream_name");
    if (streamNameField != null) {
        filename = (String) streamNameField.getFirstValue();
    } else {
        final Pattern pattern = Pattern.compile("[^/]*$");
        final Matcher matcher = pattern.matcher(url);
        if (matcher.find()) {
            filename = matcher.group();
        }
    }

    if (url.startsWith("http")) {
        if (doc.get("title") == null) {
            doc.addField("title", filename);
        }
        doc.addField("source", "web");
    }

    if (url.startsWith("file")) {
        doc.removeField("title");
        doc.addField("title", filename);
        doc.addField("source", "file");
    }

    String extension = "";
    URL urlObject = new URL(url);
    String path = urlObject.getPath();
    final SolrInputField mimeTypeField = doc.get("ignored_content_type");

    String nameExtension = FilenameUtils.getExtension(path);
    String tikaExtension = mimeTypeField == null ? "" : extensionFromMimeTypeField(mimeTypeField);

    if (extensionFromName) {
        extension = nameExtension.length() > 1 && nameExtension.length() < 5 ? nameExtension : tikaExtension;
    } else {
        extension = tikaExtension.length() > 1 && tikaExtension.length() < 5 ? tikaExtension : nameExtension;
    }
    /*
    if (extensionFromName || mimeTypeField == null) {
       if (path.contains(".")){
         extension = FilenameUtils.getExtension(path);
          if (extension.length() > 4 || extension.length() < 1) {
    // If length is too long, try extracting from tika information if available
    String tryExtension = mimeTypeField==null ? null : extensionFromMimeTypeField(mimeTypeField);
    if (tryExtension != null) {
      extension = tryExtension;
    } else {
      // Else default to bin for anything else
      extension = "bin";
    }
          }
       }
       else if (urlObject.getProtocol().equals("http") || urlObject.getProtocol().equals("https")) {
         extension = null;
         if (mimeTypeField != null) {
           extension = extensionFromMimeTypeField(mimeTypeField);
         } 
         if (extension == null) {
           extension = "html";
         }
       }
    } else {
      extension = extensionFromMimeTypeField(mimeTypeField);
      if (extension == null) {
        extension = FilenameUtils.getExtension(path);
      }
    }
    */
    doc.addField("extension", extension.toLowerCase());

    super.processAdd(cmd);
}

From source file:com.ngdata.hbaseindexer.indexer.FusionDocumentWriter.java

License:Apache License

protected void appendField(SolrInputDocument doc, String f, String pfx, List fields) {
    SolrInputField field = doc.getField(f);
    int vc = field.getValueCount();
    if (vc <= 0)
        return; // no values to add for this field

    if (vc == 1) {
        Map<String, Object> fieldMap = mapField(f, pfx, field.getFirstValue());
        if (fieldMap != null)
            fields.add(fieldMap);//from   www  . j a  va  2  s  .co  m
    } else {
        for (Object val : field.getValues()) {
            Map<String, Object> fieldMap = mapField(f, pfx, val);
            if (fieldMap != null)
                fields.add(fieldMap);
        }
    }
}

From source file:com.talis.rdf.solr.DefaultDocumentBuilderTest.java

License:Apache License

@Test
public void literalValuesAreIndexedByPredicateUri() {
    String predicateURI = PREDICATE_BASE + "first";
    ArrayList<Quad> quads = new ArrayList<Quad>();
    quads.add(new Quad(Node.createURI(GRAPH_URI), Node.createURI(SUBJECT_URI), Node.createURI(predicateURI),
            Node.createURI("http://example.com/resource")));
    quads.add(new Quad(Node.createURI(GRAPH_URI), Node.createURI(SUBJECT_URI), Node.createURI(predicateURI),
            Node.createLiteral("Aloha")));
    SolrInputDocument doc = quadsToDoc.getDocument(DOCUMENT_KEY, quads);
    SolrInputField field = doc.getField(predicateURI);
    assertEquals("Aloha", field.getFirstValue());
    assertEquals(1, field.getValues().size());
}

From source file:edu.cornell.mannlib.vitro.webapp.search.solr.ThumbnailImageURLTest.java

License:Open Source License

/**
 * Test method for {@link edu.cornell.mannlib.vitro.webapp.search.solr.documentBuilding.ThumbnailImageURL#modifyDocument(edu.cornell.mannlib.vitro.webapp.beans.Individual, org.apache.solr.common.SolrInputDocument, java.lang.StringBuffer)}.
 *///w w  w.ja  v a2s  .c  o  m
@Test
public void testModifyDocument() {
    SolrInputDocument doc = new SolrInputDocument();
    ThumbnailImageURL testMe = new ThumbnailImageURL(testModel);
    Individual ind = new IndividualImpl();
    ind.setURI(personsURI);
    try {
        testMe.modifyDocument(ind, doc, null);
    } catch (SkipIndividualException e) {
        Assert.fail("person was skipped: " + e.getMessage());
    }

    SolrInputField thumbnailField = doc.getField(fieldForThumbnailURL);
    Assert.assertNotNull(thumbnailField);

    Assert.assertNotNull(thumbnailField.getValues());
    Assert.assertEquals(1, thumbnailField.getValueCount());

    Assert.assertEquals("http://vivo.cornell.edu/individual/n54945", thumbnailField.getFirstValue());
}

From source file:fr.cnes.sitools.metacatalogue.index.solr.SolrMetadataIndexer.java

License:Open Source License

/**
 * Builds the solr input./*w ww . j a  va 2  s  . c o m*/
 * 
 * @param fields
 *          the {@link MetadataRecords} object containing the document field
 * @return the solr input document
 * @throws Exception
 *           if there is an error
 */
protected SolrInputDocument buildSolrInput(MetadataRecords fields) throws Exception {
    SolrInputDocument document = new SolrInputDocument();
    String text;
    SolrInputField solrField;
    MetacatalogField indexField;
    for (Field field : fields.getList()) {
        String name = field.getName();
        indexField = MetacatalogField.getField(name);
        if (indexField == null) {
            logger.info("Unknown field " + name + " add it to the index as a String object");
            indexField = MetacatalogField._ANY;
        }
        if (field.getValue() != null) {
            text = field.getValue().toString();
            solrField = document.getField(indexField.getField());
            if (StringUtils.isNotBlank(text)
                    && (solrField == null || !text.equals(solrField.getFirstValue()))) {
                if (indexField.isDate()) {
                    Date date = parseDate(text.toUpperCase());
                    if (date != null) {
                        document.addField(name, date);
                    }
                } else if (indexField.isBoolean()) {
                    Boolean bool = Boolean.parseBoolean(text);
                    if (bool != null) {
                        document.addField(name, bool);
                    }
                } else {
                    document.addField(name, indexField.valueToString(text));
                }
            }
        }
    }
    return document;
}

From source file:lux.solr.LuxUpdateProcessor.java

License:Mozilla Public License

@Override
public void processAdd(final AddUpdateCommand cmd) throws IOException {
    SolrInputDocument solrInputDocument = cmd.getSolrInputDocument();
    String xmlFieldName = indexConfig.getFieldName(FieldRole.XML_STORE);
    String idFieldName = indexConfig.getFieldName(FieldRole.ID);

    // remove and stash the xml field value
    SolrInputField xmlField = solrInputDocument.removeField(xmlFieldName);
    SolrInputField luxIdField = solrInputDocument.removeField(idFieldName);
    String uri = (String) solrInputDocument.getFieldValue(indexConfig.getFieldName(FieldRole.URI));
    Document luceneDocument = cmd.getLuceneDocument();
    UpdateDocCommand luxCommand = null;// www. j a  v a 2 s.c  o  m
    if (uri != null && xmlField != null) {
        // restore the xml field value
        solrInputDocument.put(xmlFieldName, xmlField);
        XmlIndexer xmlIndexer = solrIndexConfig.checkoutXmlIndexer();
        Object xml = xmlField.getFirstValue();
        try {
            try {
                if (xml instanceof String) {
                    xmlIndexer.index(new StringReader((String) xml), uri);
                } else if (xml instanceof byte[]) {
                    TinyBinary xmlbin = new TinyBinary((byte[]) xml, Charset.forName("utf-8"));
                    xmlIndexer.index(xmlbin.getTinyDocument(saxonConfig), uri);
                } else if (xml instanceof NodeInfo) {
                    xmlIndexer.index((NodeInfo) xml, uri);
                }
                // why is this here?  we're getting double values now since we also call 
                // addDocumentFIelds below?
                //luceneDocument = xmlIndexer.createLuceneDocument();
            } catch (XMLStreamException e) {
                logger.error("Failed to parse " + FieldRole.XML_STORE, e);
            }
            addDocumentFields(xmlIndexer, solrIndexConfig.getSchema(), luceneDocument);
            if (luxIdField != null) {
                Object id = luxIdField.getValue();
                if (!(id instanceof Long)) {
                    // solr cloud distributes these as Strings
                    id = Long.valueOf(id.toString());
                }
                luceneDocument.add(new LongField(idFieldName, (Long) id, Store.YES));
            }
            luxCommand = new UpdateDocCommand(req, solrInputDocument, luceneDocument, uri);
        } catch (Exception e) {
            logger.error("An error occurred while indexing " + uri, e);
            throw new IOException(e);
        } finally {
            solrIndexConfig.returnXmlIndexer(xmlIndexer);
        }
        // logger.debug ("Indexed XML document " + uri);
    }
    if (next != null) {
        next.processAdd(luxCommand == null ? cmd : luxCommand);
    }
}

From source file:nl.knaw.huygens.timbuctoo.index.solr.SolrInputDocGeneratorTest.java

License:Open Source License

@Test
public void testGetResultOneDocumentWithoutEmptyFields() throws NoSuchMethodException, SecurityException {
    String expected = "test";
    Entity entity = createEntity(expected);
    SolrInputDocGenerator generator = new SolrInputDocGenerator(entity);

    processMethod(entity, generator, GET_DISPLAY_NAME, false, "desc", FacetType.LIST);

    SolrInputDocument solrInputDocument = generator.getResult();
    SolrInputField field = solrInputDocument.getField("desc");
    Object actual = field.getFirstValue();

    assertEquals(expected, actual);/*from  www  .  ja  va 2  s  . co  m*/
}

From source file:nl.knaw.huygens.timbuctoo.index.solr.SolrInputDocGeneratorTest.java

License:Open Source License

@Test
public void testGetResultOneDocumentWithEmptyFieldsThatShouldBeIndexed() throws NoSuchMethodException {
    String description = null;//  w  ww .ja v a  2s.  c o  m
    String expected = "(empty)";
    Entity entity = createEntity(description);
    SolrInputDocGenerator generator = new SolrInputDocGenerator(entity);

    processMethod(entity, generator, GET_DISPLAY_NAME, false, "desc", FacetType.LIST);

    SolrInputDocument solrInputDocument = generator.getResult();
    SolrInputField field = solrInputDocument.getField("desc");
    Object actual = field.getFirstValue();

    assertEquals(expected, actual);
}

From source file:org.apache.blur.slur.RowMutationHelper.java

License:Apache License

private static RecordMutation createRecordMutation(SolrInputDocument doc, String id) {
    RecordMutation recordMutation = new RecordMutation();
    // TODO: what's solr default behavior?
    recordMutation.setRecordMutationType(RecordMutationType.REPLACE_ENTIRE_RECORD);
    Record record = new Record();
    record.setFamily(findFamily(doc));//from w  w  w.  ja v  a2 s .c  o  m
    record.setRecordId(id);

    for (String fieldName : doc.getFieldNames()) {
        if (!fieldName.contains(".")) {
            continue;
        }
        SolrInputField field = doc.getField(fieldName);
        String rawColumnName = fieldName.substring(fieldName.indexOf(".") + 1, fieldName.length());

        if (field.getValueCount() > 1) {
            for (Object fieldVal : field.getValues()) {
                record.addToColumns(new Column(rawColumnName, fieldVal.toString()));
            }
        } else {
            record.addToColumns(new Column(rawColumnName, field.getFirstValue().toString()));
        }
    }
    recordMutation.setRecord(record);
    return recordMutation;
}

From source file:org.opencastproject.archive.opencast.solr.Schema.java

License:Educational Community License

public static String getId(SolrInputDocument doc) {
    SolrInputField f = doc.get(ID);
    return f != null ? mkString(f.getFirstValue()) : null;
}