int dictValueCount = getDictValueCount(reader, fieldName);
BigSegmentedArray order = newInstance(dictValueCount, maxDoc);
this.orderArray = order;
IntArrayList minIDList = new IntArrayList();
IntArrayList maxIDList = new IntArrayList();
IntArrayList freqList = new IntArrayList();
int length = maxDoc + 1;
@SuppressWarnings("unchecked")
TermValueList<T> list = listFactory == null ? (TermValueList<T>) new TermStringList()
: listFactory.createTermList();
int negativeValueCount = getNegativeValueCount(reader, field);
int t = 1; // valid term id starts from 1
list.add(null);
minIDList.add(-1);
maxIDList.add(-1);
freqList.add(0);
int totalFreq = 0;
Terms terms = reader.terms(field);
if (terms != null) {
TermsEnum termsEnum = terms.iterator(null);
BytesRef text;
while ((text = termsEnum.next()) != null) {
// store term text
// we expect that there is at most one term per document
if (t >= length) throw new RuntimeException("there are more terms than "
+ "documents in field \"" + field + "\", but it's impossible to sort on "
+ "tokenized fields");
String strText = text.utf8ToString();
list.add(strText);
Term term = new Term(field, strText);
DocsEnum docsEnum = reader.termDocsEnum(term);
// freqList.add(termEnum.docFreq()); // doesn't take into account
// deldocs
int minID = -1;
int maxID = -1;
int docID = -1;
int df = 0;
int valId = (t - 1 < negativeValueCount) ? (negativeValueCount - t + 1) : t;
while ((docID = docsEnum.nextDoc()) != DocsEnum.NO_MORE_DOCS) {
df++;
order.add(docID, valId);
minID = docID;
while (docsEnum.nextDoc() != DocsEnum.NO_MORE_DOCS) {
docID = docsEnum.docID();
df++;
order.add(docID, valId);
}
maxID = docID;
}
freqList.add(df);
totalFreq += df;
minIDList.add(minID);
maxIDList.add(maxID);
t++;
}
}
list.seal();
this.valArray = list;
this.freqs = freqList.toIntArray();
this.minIDs = minIDList.toIntArray();
this.maxIDs = maxIDList.toIntArray();
int doc = 0;
while (doc < maxDoc && order.get(doc) != 0) {