Java Code Examples for org.apache.lucene.index.FieldInfos#getIndexedFields()

/**
 * Return a query that will return docs like the passed lucene document ID.
 *
 * @param docNum the documentID of the lucene doc to generate the 'More Like This" query for.
 * @return a query that will return docs like the passed lucene document ID.
 */
public Query like(int docNum) throws IOException {
  if (fieldNames == null) {
    // gather list of valid fields from lucene
    Collection<String> fields = FieldInfos.getIndexedFields(ir);
    fieldNames = fields.toArray(new String[fields.size()]);
  }

  return createQuery(retrieveTerms(docNum));
}
 

/**
 * 
 * @param filteredDocument Document with field values extracted for selected fields.
 * @return More Like This query for the passed document.
 */
public Query like(Map<String, Collection<Object>> filteredDocument) throws IOException {
  if (fieldNames == null) {
    // gather list of valid fields from lucene
    Collection<String> fields = FieldInfos.getIndexedFields(ir);
    fieldNames = fields.toArray(new String[fields.size()]);
  }
  return createQuery(retrieveTerms(filteredDocument));
}
 

public String[] listFields()
{
	if(dir==null)
		open();
	
	try (IndexReader indexReader = DirectoryReader.open(dir))
	{
		Collection<String> fields = FieldInfos.getIndexedFields(indexReader);
		return fields.toArray(new String[fields.size()]);
	} catch (IOException e) {
		return new String[0];
	}
}
 

/**
 * Test ReadTokensTask
 */
public void testReadTokens() throws Exception {

  // We will call ReadTokens on this many docs
  final int NUM_DOCS = 20;

  // Read tokens from first NUM_DOCS docs from Reuters and
  // then build index from the same docs
  String algLines1[] = {
    "# ----- properties ",
    "analyzer=org.apache.lucene.analysis.core.WhitespaceAnalyzer",
    "content.source=org.apache.lucene.benchmark.byTask.feeds.LineDocSource",
    "docs.file=" + getReuters20LinesFile(),
    "# ----- alg ",
    "{ReadTokens}: " + NUM_DOCS,
    "ResetSystemErase",
    "CreateIndex",
    "{AddDoc}: " + NUM_DOCS,
    "CloseIndex",
  };

  // Run algo
  Benchmark benchmark = execBenchmark(algLines1);

  List<TaskStats> stats = benchmark.getRunData().getPoints().taskStats();

  // Count how many tokens all ReadTokens saw
  int totalTokenCount1 = 0;
  for (final TaskStats stat : stats) {
    if (stat.getTask().getName().equals("ReadTokens")) {
      totalTokenCount1 += stat.getCount();
    }
  }

  // Separately count how many tokens are actually in the index:
  IndexReader reader = DirectoryReader.open(benchmark.getRunData().getDirectory());
  assertEquals(NUM_DOCS, reader.numDocs());

  int totalTokenCount2 = 0;

  Collection<String> fields = FieldInfos.getIndexedFields(reader);

  for (String fieldName : fields) {
    if (fieldName.equals(DocMaker.ID_FIELD) || fieldName.equals(DocMaker.DATE_MSEC_FIELD) || fieldName.equals(DocMaker.TIME_SEC_FIELD)) {
      continue;
    }
    Terms terms = MultiTerms.getTerms(reader, fieldName);
    if (terms == null) {
      continue;
    }
    TermsEnum termsEnum = terms.iterator();
    PostingsEnum docs = null;
    while(termsEnum.next() != null) {
      docs = TestUtil.docs(random(), termsEnum, docs, PostingsEnum.FREQS);
      while(docs.nextDoc() != DocIdSetIterator.NO_MORE_DOCS) {
        totalTokenCount2 += docs.freq();
      }
    }
  }
  reader.close();

  // Make sure they are the same
  assertEquals(totalTokenCount1, totalTokenCount2);
}
 

/**
 * Creates a new QueryAutoStopWordAnalyzer with stopwords calculated for all
 * indexed fields from terms with a document frequency greater than the given
 * maxDocFreq
 *
 * @param delegate Analyzer whose TokenStream will be filtered
 * @param indexReader IndexReader to identify the stopwords from
 * @param maxDocFreq Document frequency terms should be above in order to be stopwords
 * @throws IOException Can be thrown while reading from the IndexReader
 */
public QueryAutoStopWordAnalyzer(
    Analyzer delegate,
    IndexReader indexReader,
    int maxDocFreq) throws IOException {
  this(delegate, indexReader, FieldInfos.getIndexedFields(indexReader), maxDocFreq);
}
 

/**
 * Creates a new QueryAutoStopWordAnalyzer with stopwords calculated for all
 * indexed fields from terms with a document frequency percentage greater than
 * the given maxPercentDocs
 *
 * @param delegate Analyzer whose TokenStream will be filtered
 * @param indexReader IndexReader to identify the stopwords from
 * @param maxPercentDocs The maximum percentage (between 0.0 and 1.0) of index documents which
 *                      contain a term, after which the word is considered to be a stop word
 * @throws IOException Can be thrown while reading from the IndexReader
 */
public QueryAutoStopWordAnalyzer(
    Analyzer delegate,
    IndexReader indexReader,
    float maxPercentDocs) throws IOException {
  this(delegate, indexReader, FieldInfos.getIndexedFields(indexReader), maxPercentDocs);
}