void checkNorms(IndexReaderPtr reader)
{
// test omit norms
for (int32_t i = 0; i < DocHelper::fields.size(); ++i)
{
FieldPtr f = DocHelper::fields[i];
if (f->isIndexed())
{
BOOST_CHECK_EQUAL(reader->hasNorms(f->name()), !f->getOmitNorms());
BOOST_CHECK_EQUAL(reader->hasNorms(f->name()), !DocHelper::noNorms.contains(f->name()));
if (!reader->hasNorms(f->name()))
{
// test for fake norms of 1.0 or null depending on the flag
ByteArray norms = reader->norms(f->name());
uint8_t norm1 = DefaultSimilarity::encodeNorm(1.0);
BOOST_CHECK(!norms);
norms.resize(reader->maxDoc());
reader->norms(f->name(), norms, 0);
for (int32_t j = 0; j < reader->maxDoc(); ++j)
BOOST_CHECK_EQUAL(norms[j], norm1);
}
}
}
}
void checkNorms(IndexReaderPtr reader)
{
for (Collection<FieldPtr>::iterator field = DocHelper::fields.begin(); field != DocHelper::fields.end(); ++field)
{
if ((*field)->isIndexed())
{
BOOST_CHECK_EQUAL(reader->hasNorms((*field)->name()), !(*field)->getOmitNorms());
BOOST_CHECK_EQUAL(reader->hasNorms((*field)->name()), !DocHelper::noNorms.contains((*field)->name()));
if (!reader->hasNorms((*field)->name()))
{
// test for fake norms of 1.0 or null depending on the flag
ByteArray norms = reader->norms((*field)->name());
uint8_t norm1 = DefaultSimilarity::encodeNorm(1.0);
BOOST_CHECK(!norms);
norms = ByteArray::newInstance(reader->maxDoc());
reader->norms((*field)->name(), norms, 0);
for (int32_t j = 0; j < reader->maxDoc(); ++j)
BOOST_CHECK_EQUAL(norms[j], norm1);
}
}
}
}
void verifyIndex(const IndexReaderPtr& ir) {
for (int32_t i = 0; i < NUM_FIELDS; ++i) {
String field = L"f" + StringUtils::toString(i);
ByteArray b = ir->norms(field);
EXPECT_EQ(numDocNorms, b.size());
Collection<double> storedNorms = (i == 1 ? modifiedNorms : norms);
for (int32_t j = 0; j < b.size(); ++j) {
double norm = Similarity::decodeNorm(b[j]);
double norm1 = storedNorms[j];
EXPECT_EQ(norm, norm1); // 0.000001 ??
}
}
}
ExplanationPtr PhraseWeight::explain(IndexReaderPtr reader, int32_t doc)
{
ExplanationPtr result(newLucene<Explanation>());
result->setDescription(L"weight(" + query->toString() + L" in " + StringUtils::toString(doc) + L"), product of:");
StringStream docFreqsBuffer;
StringStream queryBuffer;
queryBuffer << L"\"";
docFreqsBuffer << idfExp->explain();
for (Collection<TermPtr>::iterator term = query->terms.begin(); term != query->terms.end(); ++term)
{
if (term != query->terms.begin())
queryBuffer << L" ";
queryBuffer << (*term)->text();
}
queryBuffer << L"\"";
ExplanationPtr idfExpl(newLucene<Explanation>(idf, L"idf(" + query->field + L":" + docFreqsBuffer.str() + L")"));
// explain query weight
ExplanationPtr queryExpl(newLucene<Explanation>());
queryExpl->setDescription(L"queryWeight(" + query->toString() + L"), product of:");
ExplanationPtr boostExpl(newLucene<Explanation>(query->getBoost(), L"boost"));
if (query->getBoost() != 1.0)
queryExpl->addDetail(boostExpl);
queryExpl->addDetail(idfExpl);
ExplanationPtr queryNormExpl(newLucene<Explanation>(queryNorm, L"queryNorm"));
queryExpl->addDetail(queryNormExpl);
queryExpl->setValue(boostExpl->getValue() * idfExpl->getValue() * queryNormExpl->getValue());
result->addDetail(queryExpl);
// explain field weight
ExplanationPtr fieldExpl(newLucene<Explanation>());
fieldExpl->setDescription(L"fieldWeight(" + query->field + L":" + query->toString() + L" in " + StringUtils::toString(doc) + L"), product of:");
PhraseScorerPtr phraseScorer(boost::dynamic_pointer_cast<PhraseScorer>(scorer(reader, true, false)));
if (!phraseScorer)
return newLucene<Explanation>(0.0, L"no matching docs");
ExplanationPtr tfExplanation(newLucene<Explanation>());
int32_t d = phraseScorer->advance(doc);
double phraseFreq = d == doc ? phraseScorer->currentFreq() : 0.0;
tfExplanation->setValue(similarity->tf(phraseFreq));
tfExplanation->setDescription(L"tf(phraseFreq=" + StringUtils::toString(phraseFreq) + L")");
fieldExpl->addDetail(tfExplanation);
fieldExpl->addDetail(idfExpl);
ExplanationPtr fieldNormExpl(newLucene<Explanation>());
ByteArray fieldNorms(reader->norms(query->field));
double fieldNorm = fieldNorms ? Similarity::decodeNorm(fieldNorms[doc]) : 1.0;
fieldNormExpl->setValue(fieldNorm);
fieldNormExpl->setDescription(L"fieldNorm(field=" + query->field + L", doc=" + StringUtils::toString(doc) + L")");
fieldExpl->addDetail(fieldNormExpl);
fieldExpl->setValue(tfExplanation->getValue() * idfExpl->getValue() * fieldNormExpl->getValue());
result->addDetail(fieldExpl);
// combine them
result->setValue(queryExpl->getValue() * fieldExpl->getValue());
if (queryExpl->getValue() == 1.0)
return fieldExpl;
return result;
}
ScorerPtr PhraseWeight::scorer(IndexReaderPtr reader, bool scoreDocsInOrder, bool topScorer)
{
if (query->terms.empty()) // optimize zero-term case
return ScorerPtr();
Collection<TermPositionsPtr> tps(Collection<TermPositionsPtr>::newInstance(query->terms.size()));
for (int32_t i = 0; i < tps.size(); ++i)
{
TermPositionsPtr p(reader->termPositions(query->terms[i]));
if (!p)
return ScorerPtr();
tps[i] = p;
}
if (query->slop == 0) // optimize exact case
return newLucene<ExactPhraseScorer>(shared_from_this(), tps, query->getPositions(), similarity, reader->norms(query->field));
else
return newLucene<SloppyPhraseScorer>(shared_from_this(), tps, query->getPositions(), similarity, query->slop, reader->norms(query->field));
}
ScorerPtr PayloadTermWeight::scorer(const IndexReaderPtr& reader, bool scoreDocsInOrder, bool topScorer) {
return newLucene<PayloadTermSpanScorer>(boost::dynamic_pointer_cast<TermSpans>(query->getSpans(reader)), shared_from_this(), similarity, reader->norms(query->getField()));
}