/// <summary>
/// Creates an ordinal map that allows mapping ords to/from a merged
/// space from <code>subs</code>. </summary>
/// <param name="owner"> a cache key </param>
/// <param name="subs"> TermsEnums that support <seealso cref="TermsEnum#ord()"/>. They need
/// not be dense (e.g. can be FilteredTermsEnums}. </param>
/// <exception cref="IOException"> if an I/O error occurred. </exception>
public OrdinalMap(object owner, TermsEnum[] subs)
{
// create the ordinal mappings by pulling a termsenum over each sub's
// unique terms, and walking a multitermsenum over those
this.Owner = owner;
GlobalOrdDeltas = new MonotonicAppendingLongBuffer(PackedInts.COMPACT);
FirstSegments = new AppendingPackedLongBuffer(PackedInts.COMPACT);
OrdDeltas = new MonotonicAppendingLongBuffer[subs.Length];
for (int i = 0; i < OrdDeltas.Length; i++)
{
OrdDeltas[i] = new MonotonicAppendingLongBuffer();
}
long[] segmentOrds = new long[subs.Length];
ReaderSlice[] slices = new ReaderSlice[subs.Length];
TermsEnumIndex[] indexes = new TermsEnumIndex[slices.Length];
for (int i = 0; i < slices.Length; i++)
{
slices[i] = new ReaderSlice(0, 0, i);
indexes[i] = new TermsEnumIndex(subs[i], i);
}
MultiTermsEnum mte = new MultiTermsEnum(slices);
mte.Reset(indexes);
long globalOrd = 0;
while (mte.Next() != null)
{
TermsEnumWithSlice[] matches = mte.MatchArray;
for (int i = 0; i < mte.MatchCount; i++)
{
int segmentIndex = matches[i].Index;
long segmentOrd = matches[i].Terms.Ord();
long delta = globalOrd - segmentOrd;
// for each unique term, just mark the first segment index/delta where it occurs
if (i == 0)
{
FirstSegments.Add(segmentIndex);
GlobalOrdDeltas.Add(delta);
}
// for each per-segment ord, map it back to the global term.
while (segmentOrds[segmentIndex] <= segmentOrd)
{
OrdDeltas[segmentIndex].Add(delta);
segmentOrds[segmentIndex]++;
}
}
globalOrd++;
}
FirstSegments.Freeze();
GlobalOrdDeltas.Freeze();
for (int i = 0; i < OrdDeltas.Length; ++i)
{
OrdDeltas[i].Freeze();
}
}
// finalize currentDoc: this deduplicates the current term ids
private void FinishCurrentDoc()
{
Array.Sort(CurrentValues, 0, CurrentUpto);
int lastValue = -1;
int count = 0;
for (int i = 0; i < CurrentUpto; i++)
{
int termID = CurrentValues[i];
// if its not a duplicate
if (termID != lastValue)
{
Pending.Add(termID); // record the term id
count++;
}
lastValue = termID;
}
// record the number of unique term ids for this doc
PendingCounts.Add(count);
MaxCount = Math.Max(MaxCount, count);
CurrentUpto = 0;
CurrentDoc++;
}
/// <summary>
/// Creates an ordinal map that allows mapping ords to/from a merged
/// space from <code>subs</code>. </summary>
/// <param name="owner"> a cache key </param>
/// <param name="subs"> TermsEnums that support <seealso cref="TermsEnum#ord()"/>. They need
/// not be dense (e.g. can be FilteredTermsEnums}. </param>
/// <exception cref="IOException"> if an I/O error occurred. </exception>
public OrdinalMap(object owner, TermsEnum[] subs)
{
// create the ordinal mappings by pulling a termsenum over each sub's
// unique terms, and walking a multitermsenum over those
this.Owner = owner;
GlobalOrdDeltas = new MonotonicAppendingLongBuffer(PackedInts.COMPACT);
FirstSegments = new AppendingPackedLongBuffer(PackedInts.COMPACT);
OrdDeltas = new MonotonicAppendingLongBuffer[subs.Length];
for (int i = 0; i < OrdDeltas.Length; i++)
{
OrdDeltas[i] = new MonotonicAppendingLongBuffer();
}
long[] segmentOrds = new long[subs.Length];
ReaderSlice[] slices = new ReaderSlice[subs.Length];
TermsEnumIndex[] indexes = new TermsEnumIndex[slices.Length];
for (int i = 0; i < slices.Length; i++)
{
slices[i] = new ReaderSlice(0, 0, i);
indexes[i] = new TermsEnumIndex(subs[i], i);
}
MultiTermsEnum mte = new MultiTermsEnum(slices);
mte.Reset(indexes);
long globalOrd = 0;
while (mte.Next() != null)
{
TermsEnumWithSlice[] matches = mte.MatchArray;
for (int i = 0; i < mte.MatchCount; i++)
{
int segmentIndex = matches[i].Index;
long segmentOrd = matches[i].Terms.Ord();
long delta = globalOrd - segmentOrd;
// for each unique term, just mark the first segment index/delta where it occurs
if (i == 0)
{
FirstSegments.Add(segmentIndex);
GlobalOrdDeltas.Add(delta);
}
// for each per-segment ord, map it back to the global term.
while (segmentOrds[segmentIndex] <= segmentOrd)
{
OrdDeltas[segmentIndex].Add(delta);
segmentOrds[segmentIndex]++;
}
}
globalOrd++;
}
FirstSegments.Freeze();
GlobalOrdDeltas.Freeze();
for (int i = 0; i < OrdDeltas.Length; ++i)
{
OrdDeltas[i].Freeze();
}
}