1
|
package edu.ucsb.nceas.metacat.index;
|
2
|
|
3
|
import org.apache.lucene.analysis.standard.StandardAnalyzer;
|
4
|
import org.apache.lucene.document.Document;
|
5
|
import org.apache.lucene.document.Field;
|
6
|
import org.apache.lucene.document.StringField;
|
7
|
import org.apache.lucene.document.TextField;
|
8
|
import org.apache.lucene.index.*;
|
9
|
import org.apache.lucene.queryparser.classic.ParseException;
|
10
|
import org.apache.lucene.queryparser.classic.QueryParser;
|
11
|
import org.apache.lucene.search.IndexSearcher;
|
12
|
import org.apache.lucene.search.ScoreDoc;
|
13
|
import org.apache.lucene.search.TopDocs;
|
14
|
import org.apache.lucene.store.Directory;
|
15
|
import org.apache.lucene.store.FSDirectory;
|
16
|
import org.apache.lucene.util.Version;
|
17
|
|
18
|
import java.io.File;
|
19
|
import java.io.IOException;
|
20
|
import java.util.Map;
|
21
|
|
22
|
public class LuceneIndex implements GenericIndex {
|
23
|
protected final StandardAnalyzer analyzer = new StandardAnalyzer(Version.LUCENE_41);
|
24
|
protected final IndexWriterConfig cfg = new IndexWriterConfig(Version.LUCENE_41, analyzer);
|
25
|
protected final QueryParser parser = new QueryParser(Version.LUCENE_41, MetacatIndex.MCIDFIELD, analyzer);
|
26
|
protected IndexWriter writer = null;
|
27
|
protected DirectoryReader reader = null;
|
28
|
protected Directory index = null;
|
29
|
|
30
|
public LuceneIndex(File fsIndex) {
|
31
|
try {
|
32
|
this.index = FSDirectory.open(fsIndex);
|
33
|
this.cfg.setOpenMode(IndexWriterConfig.OpenMode.APPEND);
|
34
|
this.writer = new IndexWriter(this.index, this.cfg);
|
35
|
this.reader = DirectoryReader.open(this.index);
|
36
|
} catch (Exception e) {
|
37
|
e.printStackTrace();
|
38
|
}
|
39
|
}
|
40
|
|
41
|
public void insert(String docID, Map<String, String[]> fields) throws IOException {
|
42
|
this.update(docID, fields);
|
43
|
}
|
44
|
|
45
|
public void update(String docID, Map<String, String[]> fields) throws IOException {
|
46
|
Document d = new Document();
|
47
|
d.add(new StringField(MetacatIndex.MCIDFIELD, docID, Field.Store.YES));
|
48
|
for (String k : fields.keySet()) {
|
49
|
for (String v : fields.get(k)) {
|
50
|
d.add(new TextField(k, v, Field.Store.NO));
|
51
|
}
|
52
|
}
|
53
|
this.writer.addDocument(d);
|
54
|
this.writer.commit();
|
55
|
}
|
56
|
|
57
|
public void remove(String docID) throws IOException {
|
58
|
this.writer.deleteDocuments(new Term(MetacatIndex.MCIDFIELD, docID));
|
59
|
this.writer.commit();
|
60
|
}
|
61
|
|
62
|
public String[] query(String q) {
|
63
|
try {
|
64
|
DirectoryReader newReader = DirectoryReader.openIfChanged(this.reader);
|
65
|
if (newReader != null) { // not sure if this is right...
|
66
|
this.reader.close();
|
67
|
this.reader = newReader;
|
68
|
}
|
69
|
IndexSearcher searcher = new IndexSearcher(this.reader);
|
70
|
TopDocs docs = searcher.search(this.parser.parse(q), 100);
|
71
|
String docIDs[] = new String[docs.scoreDocs.length];
|
72
|
int i = 0;
|
73
|
for (ScoreDoc sd : docs.scoreDocs) {
|
74
|
Document d = searcher.doc(sd.doc);
|
75
|
docIDs[i++] = d.getField(MetacatIndex.MCIDFIELD).toString();
|
76
|
}
|
77
|
return docIDs;
|
78
|
} catch (IOException e) {
|
79
|
e.printStackTrace();
|
80
|
} catch (ParseException e) {
|
81
|
e.printStackTrace();
|
82
|
}
|
83
|
return new String[0];
|
84
|
}
|
85
|
}
|