int64_t TermInfosReader::getPosition(TermPtr term)
{
if (_size == 0)
return -1;
ensureIndexIsRead();
int32_t indexOffset = getIndexOffset(term);
SegmentTermEnumPtr enumerator(getThreadResources()->termEnum);
seekEnum(enumerator, indexOffset);
while (term->compareTo(enumerator->term()) > 0 && enumerator->next())
{
}
return term->compareTo(enumerator->term()) == 0 ? enumerator->position : -1;
}
TermInfoPtr TermInfosReader::get(TermPtr term, bool useCache)
{
if (_size == 0)
return TermInfoPtr();
ensureIndexIsRead();
TermInfoPtr ti;
TermInfosReaderThreadResourcesPtr resources(getThreadResources());
TermInfoCachePtr cache;
if (useCache)
{
cache = resources->termInfoCache;
// check the cache first if the term was recently looked up
ti = cache->get(term);
if (ti)
return ti;
}
// optimize sequential access: first try scanning cached enum without seeking
SegmentTermEnumPtr enumerator = resources->termEnum;
if (enumerator->term() && // term is at or past current
((enumerator->prev() && term->compareTo(enumerator->prev()) > 0) ||
term->compareTo(enumerator->term()) >= 0))
{
int32_t enumOffset = (int32_t)(enumerator->position / totalIndexInterval ) + 1;
if (indexTerms.size() == enumOffset || // but before end of block
term->compareTo(indexTerms[enumOffset]) < 0)
{
// no need to seek
int32_t numScans = enumerator->scanTo(term);
if (enumerator->term() && term->compareTo(enumerator->term()) == 0)
{
ti = enumerator->termInfo();
if (cache && numScans > 1)
{
// we only want to put this TermInfo into the cache if scanEnum skipped more
// than one dictionary entry. This prevents RangeQueries or WildcardQueries to
// wipe out the cache when they iterate over a large numbers of terms in order.
cache->put(term, ti);
}
}
else
ti.reset();
return ti;
}
}
// random-access: must seek
seekEnum(enumerator, getIndexOffset(term));
enumerator->scanTo(term);
if (enumerator->term() && term->compareTo(enumerator->term()) == 0)
{
ti = enumerator->termInfo();
if (cache)
cache->put(term, ti);
}
else
ti.reset();
return ti;
}
