honeymoose
/
OpenSearch
mirror of https://github.com/honeymoose/OpenSearch.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

improve field data loader to bulk read doc ids

This commit is contained in:
Shay Banon 2012-05-23 22:18:20 +02:00
parent f87632fabd
commit 9f706c6f6e
1 changed files with 19 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
src/main/java/org/elasticsearch/index/field/data/support/FieldDataLoader.java
View File

@ -49,22 +49,31 @@ public class FieldDataLoader {
TermDocs termDocs = reader.termDocs(); TermDocs termDocs = reader.termDocs();
TermEnum termEnum = reader.terms(new Term(field)); TermEnum termEnum = reader.terms(new Term(field));
try { try {
// bulk read (in lucene 4 it won't be needed).
int size = Math.min(128, reader.maxDoc());
int[] docs = new int[size];
int[] freqs = new int[size];
do { do {
Term term = termEnum.term(); Term term = termEnum.term();
if (term == null || term.field() != field) break; if (term == null || term.field() != field) break;
loader.collectTerm(term.text()); loader.collectTerm(term.text());
termDocs.seek(termEnum); termDocs.seek(termEnum);
while (termDocs.next()) {
int doc = termDocs.doc(); int number = termDocs.read(docs, freqs);
int[] ordinal; while (number > 0) {
if (idx[doc] >= ordinals.size()) { for (int i = 0; i < number; i++) {
ordinal = new int[reader.maxDoc()]; int doc = docs[i];
ordinals.add(ordinal); int[] ordinal;
} else { if (idx[doc] >= ordinals.size()) {
ordinal = ordinals.get(idx[doc]); ordinal = new int[reader.maxDoc()];
ordinals.add(ordinal);
} else {
ordinal = ordinals.get(idx[doc]);
}
ordinal[doc] = t;
idx[doc]++;
} }
ordinal[doc] = t; number = termDocs.read(docs, freqs);
idx[doc]++;
} }
t++; t++;
} while (termEnum.next()); } while (termEnum.next());