/**
* Note: if you use a counting {@link Facets} implementation, you can amortize the sampled counts
* by calling this method. Uses the {@link FacetsConfig} and the {@link IndexSearcher} to
* determine the upper bound for each facet value.
*/
public FacetResult amortizeFacetCounts(
FacetResult res, FacetsConfig config, IndexSearcher searcher) throws IOException {
if (res == null || totalHits <= sampleSize) {
return res;
}
LabelAndValue[] fixedLabelValues = new LabelAndValue[res.labelValues.length];
IndexReader reader = searcher.getIndexReader();
DimConfig dimConfig = config.getDimConfig(res.dim);
// +2 to prepend dimension, append child label
String[] childPath = new String[res.path.length + 2];
childPath[0] = res.dim;
System.arraycopy(res.path, 0, childPath, 1, res.path.length); // reuse
for (int i = 0; i < res.labelValues.length; i++) {
childPath[res.path.length + 1] = res.labelValues[i].label;
String fullPath = FacetsConfig.pathToString(childPath, childPath.length);
int max = reader.docFreq(new Term(dimConfig.indexFieldName, fullPath));
int correctedCount = (int) (res.labelValues[i].value.doubleValue() / samplingRate);
correctedCount = Math.min(max, correctedCount);
fixedLabelValues[i] = new LabelAndValue(res.labelValues[i].label, correctedCount);
}
// cap the total count on the total number of non-deleted documents in the reader
int correctedTotalCount = res.value.intValue();
if (correctedTotalCount > 0) {
correctedTotalCount =
Math.min(reader.numDocs(), (int) (res.value.doubleValue() / samplingRate));
}
return new FacetResult(
res.dim, res.path, correctedTotalCount, fixedLabelValues, res.childCount);
}
public void testTermNonDefault() {
String aField = config.getDimConfig("a").indexFieldName;
Term termA = DrillDownQuery.term(aField, "a");
assertEquals(new Term(aField, "a"), termA);
String bField = config.getDimConfig("b").indexFieldName;
Term termB = DrillDownQuery.term(bField, "b");
assertEquals(new Term(bField, "b"), termB);
}
@BeforeClass
public static void beforeClassDrillDownQueryTest() throws Exception {
dir = newDirectory();
Random r = random();
RandomIndexWriter writer =
new RandomIndexWriter(
r,
dir,
newIndexWriterConfig(
TEST_VERSION_CURRENT, new MockAnalyzer(r, MockTokenizer.KEYWORD, false)));
taxoDir = newDirectory();
TaxonomyWriter taxoWriter = new DirectoryTaxonomyWriter(taxoDir);
config = new FacetsConfig();
// Randomize the per-dim config:
config.setHierarchical("a", random().nextBoolean());
config.setMultiValued("a", random().nextBoolean());
if (random().nextBoolean()) {
config.setIndexFieldName("a", "$a");
}
config.setRequireDimCount("a", true);
config.setHierarchical("b", random().nextBoolean());
config.setMultiValued("b", random().nextBoolean());
if (random().nextBoolean()) {
config.setIndexFieldName("b", "$b");
}
config.setRequireDimCount("b", true);
for (int i = 0; i < 100; i++) {
Document doc = new Document();
if (i % 2 == 0) { // 50
doc.add(new TextField("content", "foo", Field.Store.NO));
}
if (i % 3 == 0) { // 33
doc.add(new TextField("content", "bar", Field.Store.NO));
}
if (i % 4 == 0) { // 25
if (r.nextBoolean()) {
doc.add(new FacetField("a", "1"));
} else {
doc.add(new FacetField("a", "2"));
}
}
if (i % 5 == 0) { // 20
doc.add(new FacetField("b", "1"));
}
writer.addDocument(config.build(taxoWriter, doc));
}
taxoWriter.close();
reader = writer.getReader();
writer.close();
taxo = new DirectoryTaxonomyReader(taxoDir);
}
