Example usage for org.apache.solr.handler.extraction SolrContentHandler newDocument

Introduction

In this page you can find the example usage for org.apache.solr.handler.extraction SolrContentHandler newDocument.

Prototype

public SolrInputDocument newDocument() 

Source Link

Document

This is called by a consumer when it is ready to deal with a new SolrInputDocument.

Usage

From source file:com.cloudera.cdk.morphline.solrcell.SolrCellMorphlineTest.java

License:Apache License

/**
 * Test that the ContentHandler properly strips the illegal characters
 *///from  w w w . j  av  a  2s.c  om
@Test
public void testTransformValue() {
    String fieldName = "user_name";
    assertFalse("foobar".equals(getFoobarWithNonChars()));

    Metadata metadata = new Metadata();
    // load illegal char string into a metadata field and generate a new document,
    // which will cause the ContentHandler to be invoked.
    metadata.set(fieldName, getFoobarWithNonChars());
    StripNonCharSolrContentHandlerFactory contentHandlerFactory = new StripNonCharSolrContentHandlerFactory(
            DateUtil.DEFAULT_DATE_FORMATS);
    IndexSchema schema = h.getCore().getLatestSchema();
    SolrContentHandler contentHandler = contentHandlerFactory.createSolrContentHandler(metadata,
            new MapSolrParams(new HashMap()), schema);
    SolrInputDocument doc = contentHandler.newDocument();
    String foobar = doc.getFieldValue(fieldName).toString();
    assertTrue("foobar".equals(foobar));
}

---

From source file:com.ngdata.hbaseindexer.parse.tika.TikaSolrDocumentExtractor.java

License:Apache License

private SolrInputDocument extractInternal(byte[] input) {
    Metadata metadata = new Metadata();
    metadata.add(LiteralMimeDetector.MIME_TYPE, mimeType);

    Map<String, String> cellParams = (params == null || params.isEmpty()) ? DEFAULT_CELL_PARAMS : params;
    SolrContentHandler handler = new SolrContentHandler(metadata, new MapSolrParams(cellParams), indexSchema);

    try {//from ww w .ja v  a 2 s . c  o  m
        parser.parse(new ByteArrayInputStream(input), handler, metadata, new ParseContext());
    } catch (Exception e) {
        throw new RuntimeException(e);
    }

    return handler.newDocument();
}

---