@Override
public Document document(int docid) throws IOException {
if (_subReaders != null) {
int readerIndex = readerIndex(docid, _starts, _subReaders.length);
BoboIndexReader subReader = _subReaders[readerIndex];
return subReader.document(docid - _starts[readerIndex]);
} else {
Document doc = super.document(docid);
Collection<FacetHandler<?>> facetHandlers = _facetHandlerMap.values();
for (FacetHandler<?> facetHandler : facetHandlers) {
String[] vals = facetHandler.getFieldValues(this, docid);
if (vals != null) {
String[] values = doc.getValues(facetHandler.getName());
Set<String> storedVals = new HashSet<String>(Arrays.asList(values));
for (String val : vals) {
storedVals.add(val);
}
doc.removeField(facetHandler.getName());
for (String val : storedVals) {
doc.add(
new Field(facetHandler.getName(), val, Field.Store.NO, Field.Index.NOT_ANALYZED));
}
}
}
return doc;
}
}
@Override
public void analyze(Document doc, InputStream in) throws IOException {
if (in.read() != 'B') {
throw new IOException("Not BZIP2 format");
}
if (in.read() != 'Z') {
throw new IOException("Not BZIP2 format");
}
BufferedInputStream gzis = new BufferedInputStream(new CBZip2InputStream(in));
String path = doc.get("path");
if (path != null && (path.endsWith(".bz2") || path.endsWith(".BZ2") || path.endsWith(".bz"))) {
String newname = path.substring(0, path.lastIndexOf('.'));
// System.err.println("BZIPPED OF = " + newname);
fa = AnalyzerGuru.getAnalyzer(gzis, newname);
if (fa instanceof BZip2Analyzer) {
fa = null;
} else {
if (fa.getGenre() == Genre.PLAIN || fa.getGenre() == Genre.XREFABLE) {
this.g = Genre.XREFABLE;
} else {
this.g = Genre.DATA;
}
fa.analyze(doc, gzis);
if (doc.get("t") != null) {
doc.removeField("t");
if (g == Genre.XREFABLE) {
doc.add(new Field("t", g.typeName(), Field.Store.YES, Field.Index.NOT_ANALYZED));
}
}
}
}
}
@Test(expected = FailedPopulateException.class)
public void populateShouldFailWithDocumentMissingMandatoryField()
throws IndexFailureException, InitializationException {
Populator<HostPathogen> pop = new HostPathogenPopulator<HostPathogen>();
Document d = makeValidDocument();
d.removeField(BasePopulator.stored(LuceneFields.FK_PATHOGEN_ID));
HostPathogen ht = pop.populate(d);
}
@Test
public void populateShouldSucceedWithDocumentMissingNonMandatoryField()
throws IndexFailureException, InitializationException {
Populator<HostPathogen> pop = new HostPathogenPopulator<HostPathogen>();
Document d = makeValidDocument();
d.removeField(BasePopulator.stored(LuceneFields.RUST_STATE));
HostPathogen ht = pop.populate(d);
Assert.assertTrue(ht != null);
}
private byte[] extractSource(Document doc, DocumentMapper documentMapper) {
byte[] source = null;
Fieldable sourceField = doc.getFieldable(documentMapper.sourceMapper().names().indexName());
if (sourceField != null) {
source = documentMapper.sourceMapper().nativeValue(sourceField);
doc.removeField(documentMapper.sourceMapper().names().indexName());
}
return source;
}
/**
* Reads the snapshots information from the given {@link Directory}. This method can be used if
* the snapshots information is needed, however you cannot instantiate the deletion policy
* (because e.g., some other process keeps a lock on the snapshots directory).
*/
public static Map<String, String> readSnapshotsInfo(Directory dir) throws IOException {
IndexReader r = DirectoryReader.open(dir);
Map<String, String> snapshots = new HashMap<String, String>();
try {
int numDocs = r.numDocs();
// index is allowed to have exactly one document or 0.
if (numDocs == 1) {
Document doc = r.document(r.maxDoc() - 1);
if (doc.getField(SNAPSHOTS_ID) == null) {
throw new IllegalStateException("directory is not a valid snapshots store!");
}
doc.removeField(SNAPSHOTS_ID);
for (IndexableField f : doc) {
snapshots.put(f.name(), f.stringValue());
}
} else if (numDocs != 0) {
throw new IllegalStateException(
"should be at most 1 document in the snapshots directory: " + numDocs);
}
} finally {
r.close();
}
return snapshots;
}