/**
* Tests the IndexReader.getFieldNames implementation
* @throws Exception on error
*/
public void testGetFieldNames() throws Exception {
Directory d = newDirectory();
// set up writer
IndexWriter writer = new IndexWriter(
d,
newIndexWriterConfig(TEST_VERSION_CURRENT, new MockAnalyzer(random))
);
Document doc = new Document();
doc.add(new Field("keyword","test1", Field.Store.YES, Field.Index.NOT_ANALYZED));
doc.add(new Field("text","test1", Field.Store.YES, Field.Index.ANALYZED));
doc.add(new Field("unindexed","test1", Field.Store.YES, Field.Index.NO));
doc.add(new Field("unstored","test1", Field.Store.NO, Field.Index.ANALYZED));
writer.addDocument(doc);
writer.close();
// set up reader
IndexReader reader = IndexReader.open(d, false);
Collection<String> fieldNames = reader.getFieldNames(IndexReader.FieldOption.ALL);
assertTrue(fieldNames.contains("keyword"));
assertTrue(fieldNames.contains("text"));
assertTrue(fieldNames.contains("unindexed"));
assertTrue(fieldNames.contains("unstored"));
reader.close();
// add more documents
writer = new IndexWriter(
d,
newIndexWriterConfig(TEST_VERSION_CURRENT, new MockAnalyzer(random)).
setOpenMode(OpenMode.APPEND).
setMergePolicy(newLogMergePolicy())
);
// want to get some more segments here
int mergeFactor = ((LogMergePolicy) writer.getConfig().getMergePolicy()).getMergeFactor();
for (int i = 0; i < 5*mergeFactor; i++) {
doc = new Document();
doc.add(new Field("keyword","test1", Field.Store.YES, Field.Index.NOT_ANALYZED));
doc.add(new Field("text","test1", Field.Store.YES, Field.Index.ANALYZED));
doc.add(new Field("unindexed","test1", Field.Store.YES, Field.Index.NO));
doc.add(new Field("unstored","test1", Field.Store.NO, Field.Index.ANALYZED));
writer.addDocument(doc);
}
// new fields are in some different segments (we hope)
for (int i = 0; i < 5*mergeFactor; i++) {
doc = new Document();
doc.add(new Field("keyword2","test1", Field.Store.YES, Field.Index.NOT_ANALYZED));
doc.add(new Field("text2","test1", Field.Store.YES, Field.Index.ANALYZED));
doc.add(new Field("unindexed2","test1", Field.Store.YES, Field.Index.NO));
doc.add(new Field("unstored2","test1", Field.Store.NO, Field.Index.ANALYZED));
writer.addDocument(doc);
}
// new termvector fields
for (int i = 0; i < 5*mergeFactor; i++) {
doc = new Document();
doc.add(new Field("tvnot","tvnot", Field.Store.YES, Field.Index.ANALYZED, Field.TermVector.NO));
doc.add(new Field("termvector","termvector", Field.Store.YES, Field.Index.ANALYZED, Field.TermVector.YES));
doc.add(new Field("tvoffset","tvoffset", Field.Store.YES, Field.Index.ANALYZED, Field.TermVector.WITH_OFFSETS));
doc.add(new Field("tvposition","tvposition", Field.Store.YES, Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS));
doc.add(newField("tvpositionoffset","tvpositionoffset", Field.Store.YES, Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS));
writer.addDocument(doc);
}
writer.close();
// verify fields again
reader = IndexReader.open(d, false);
fieldNames = reader.getFieldNames(IndexReader.FieldOption.ALL);
assertEquals(13, fieldNames.size()); // the following fields
assertTrue(fieldNames.contains("keyword"));
assertTrue(fieldNames.contains("text"));
assertTrue(fieldNames.contains("unindexed"));
assertTrue(fieldNames.contains("unstored"));
assertTrue(fieldNames.contains("keyword2"));
assertTrue(fieldNames.contains("text2"));
assertTrue(fieldNames.contains("unindexed2"));
assertTrue(fieldNames.contains("unstored2"));
assertTrue(fieldNames.contains("tvnot"));
assertTrue(fieldNames.contains("termvector"));
assertTrue(fieldNames.contains("tvposition"));
assertTrue(fieldNames.contains("tvoffset"));
assertTrue(fieldNames.contains("tvpositionoffset"));
// verify that only indexed fields were returned
fieldNames = reader.getFieldNames(IndexReader.FieldOption.INDEXED);
assertEquals(11, fieldNames.size()); // 6 original + the 5 termvector fields
assertTrue(fieldNames.contains("keyword"));
assertTrue(fieldNames.contains("text"));
assertTrue(fieldNames.contains("unstored"));
assertTrue(fieldNames.contains("keyword2"));
assertTrue(fieldNames.contains("text2"));
assertTrue(fieldNames.contains("unstored2"));
assertTrue(fieldNames.contains("tvnot"));
assertTrue(fieldNames.contains("termvector"));
assertTrue(fieldNames.contains("tvposition"));
assertTrue(fieldNames.contains("tvoffset"));
assertTrue(fieldNames.contains("tvpositionoffset"));
// verify that only unindexed fields were returned
fieldNames = reader.getFieldNames(IndexReader.FieldOption.UNINDEXED);
assertEquals(2, fieldNames.size()); // the following fields
assertTrue(fieldNames.contains("unindexed"));
assertTrue(fieldNames.contains("unindexed2"));
// verify index term vector fields
fieldNames = reader.getFieldNames(IndexReader.FieldOption.TERMVECTOR);
assertEquals(1, fieldNames.size()); // 1 field has term vector only
assertTrue(fieldNames.contains("termvector"));
fieldNames = reader.getFieldNames(IndexReader.FieldOption.TERMVECTOR_WITH_POSITION);
assertEquals(1, fieldNames.size()); // 4 fields are indexed with term vectors
assertTrue(fieldNames.contains("tvposition"));
fieldNames = reader.getFieldNames(IndexReader.FieldOption.TERMVECTOR_WITH_OFFSET);
assertEquals(1, fieldNames.size()); // 4 fields are indexed with term vectors
assertTrue(fieldNames.contains("tvoffset"));
fieldNames = reader.getFieldNames(IndexReader.FieldOption.TERMVECTOR_WITH_POSITION_OFFSET);
assertEquals(1, fieldNames.size()); // 4 fields are indexed with term vectors
assertTrue(fieldNames.contains("tvpositionoffset"));
reader.close();
d.close();
}