0
我在我的数据库行（每行是一个文档）上构建了一个索引，这些索引在MySQL中是unicode类型的（即字符集：utf8和Collation：utf8-bin）。但是当我搜索任何单词英语或非英语时，它不会给我答案。它说：Lucene搜索问题
0总匹配文档
我的代码的Lucene的不同之处在于我已经改变字段名我插入的列名搜索的演示代码。无论如何，它在到达那部分代码之前打印此消息。而且我还将读取的查询编码更改为UTF-8。
我检查了数据库部分的阅读。没关系。
有什么问题？
如果有帮助，这是我的插入代码：
static void indexDocs(IndexWriter writer, Connection conn) throws SQLException, CorruptIndexException, IOException {
String sql = "select id, name, description, text from users";
Statement stmt = conn.createStatement();
ResultSet rs = stmt.executeQuery(sql);
while (rs.next()) {
Document d = new Document();
d.add(new Field("id", rs.getString("id"), Field.Store.YES, Field.Index.NOT_ANALYZED));
d.add(new Field("name", rs.getString("name"), Field.Store.NO, Field.Index.NOT_ANALYZED));
String tmp = rs.getString("description");
if (tmp == null) {
tmp = "";
}
d.add(new Field("description", tmp, Field.Store.NO, Field.Index.ANALYZED));
tmp = rs.getString("text");
if (tmp == null) {
tmp = "";
}
d.add(new Field("text", tmp, Field.Store.NO, Field.Index.ANALYZED));
writer.addDocument(d);
}
}
而且这是我的搜索代码：
import java.io.BufferedReader;
import java.io.File;
import java.io.FileReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.Date;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.FilterIndexReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.Collector;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.Scorer;
import org.apache.lucene.search.Searcher;
import org.apache.lucene.search.TopScoreDocCollector;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
/** Simple command-line based search demo. */
public class Search {
/** Use the norms from one field for all fields. Norms are read into memory,
* using a byte of memory per document per searched field. This can cause
* search of large collections with a large number of fields to run out of
* memory. If all of the fields contain only a single token, then the norms
* are all identical, then single norm vector may be shared. */
private static class OneNormsReader extends FilterIndexReader {
private String field;
public OneNormsReader(IndexReader in, String field) {
super(in);
this.field = field;
}
@Override
public byte[] norms(String field) throws IOException {
return in.norms(this.field);
}
}
private Search() {
}
/** Simple command-line based search demo. */
public static void main(String[] args) throws Exception {
String usage =
"Usage:\tjava org.apache.lucene.demo.SearchFiles [-index dir] [-field f] [-repeat n] [-queries file] [-raw] [-norms field] [-paging hitsPerPage]";
usage += "\n\tSpecify 'false' for hitsPerPage to use streaming instead of paging search.";
if (args.length > 0 && ("-h".equals(args[0]) || "-help".equals(args[0]))) {
System.out.println(usage);
System.exit(0);
}
String index = "index";
String field = "contents";
String queries = null;
int repeat = 0;
boolean raw = false;
String normsField = null;
boolean paging = true;
int hitsPerPage = 10;
for (int i = 0; i < args.length; i++) {
if ("-index".equals(args[i])) {
index = args[i + 1];
i++;
} else if ("-field".equals(args[i])) {
field = args[i + 1];
i++;
} else if ("-queries".equals(args[i])) {
queries = args[i + 1];
i++;
} else if ("-repeat".equals(args[i])) {
repeat = Integer.parseInt(args[i + 1]);
i++;
} else if ("-raw".equals(args[i])) {
raw = true;
} else if ("-norms".equals(args[i])) {
normsField = args[i + 1];
i++;
} else if ("-paging".equals(args[i])) {
if (args[i + 1].equals("false")) {
paging = false;
} else {
hitsPerPage = Integer.parseInt(args[i + 1]);
if (hitsPerPage == 0) {
paging = false;
}
}
i++;
}
}
IndexReader reader = IndexReader.open(FSDirectory.open(new File(index)), true); // only searching, so read-only=true
if (normsField != null) {
reader = new OneNormsReader(reader, normsField);
}
Searcher searcher = new IndexSearcher(reader);
Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_CURRENT);
BufferedReader in = null;
if (queries != null) {
in = new BufferedReader(new FileReader(queries));
} else {
in = new BufferedReader(new InputStreamReader(System.in, "UTF-8"));
}
QueryParser parser = new QueryParser(Version.LUCENE_CURRENT, field, analyzer);
while (true) {
if (queries == null) // prompt the user
{
System.out.println("Enter query: ");
}
String line = in.readLine();
line = new String(line.getBytes("8859_1"), "UTF8");
if (line == null || line.length() == -1) {
break;
}
line = line.trim();
if (line.length() == 0) {
break;
}
Query query = parser.parse(line);
System.out.println("Searching for: " + query.toString(field));
if (repeat > 0) { // repeat & time as benchmark
Date start = new Date();
for (int i = 0; i < repeat; i++) {
searcher.search(query, null, 100);
}
Date end = new Date();
System.out.println("Time: " + (end.getTime() - start.getTime()) + "ms");
}
if (paging) {
doPagingSearch(in, searcher, query, hitsPerPage, raw, queries == null);
} else {
doStreamingSearch(searcher, query);
}
}
reader.close();
}
/**
* This method uses a custom HitCollector implementation which simply prints out
* the docId and score of every matching document.
*
* This simulates the streaming search use case, where all hits are supposed to
* be processed, regardless of their relevance.
*/
public static void doStreamingSearch(final Searcher searcher, Query query) throws IOException {
Collector streamingHitCollector = new Collector() {
private Scorer scorer;
private int docBase;
// simply print docId and score of every matching document
@Override
public void collect(int doc) throws IOException {
System.out.println("doc=" + doc + docBase + " score=" + scorer.score());
}
@Override
public boolean acceptsDocsOutOfOrder() {
return true;
}
@Override
public void setNextReader(IndexReader reader, int docBase)
throws IOException {
this.docBase = docBase;
}
@Override
public void setScorer(Scorer scorer) throws IOException {
this.scorer = scorer;
}
};
searcher.search(query, streamingHitCollector);
}
/**
* This demonstrates a typical paging search scenario, where the search engine presents
* pages of size n to the user. The user can then go to the next page if interested in
* the next hits.
*
* When the query is executed for the first time, then only enough results are collected
* to fill 5 result pages. If the user wants to page beyond this limit, then the query
* is executed another time and all hits are collected.
*
*/
public static void doPagingSearch(BufferedReader in, Searcher searcher, Query query,
int hitsPerPage, boolean raw, boolean interactive) throws IOException {
// Collect enough docs to show 5 pages
TopScoreDocCollector collector = TopScoreDocCollector.create(
5 * hitsPerPage, false);
searcher.search(query, collector);
ScoreDoc[] hits = collector.topDocs().scoreDocs;
int numTotalHits = collector.getTotalHits();
System.out.println(numTotalHits + " total matching documents");
int start = 0;
int end = Math.min(numTotalHits, hitsPerPage);
while (true) {
if (end > hits.length) {
System.out.println("Only results 1 - " + hits.length + " of " + numTotalHits + " total matching documents collected.");
System.out.println("Collect more (y/n) ?");
String line = in.readLine();
if (line.length() == 0 || line.charAt(0) == 'n') {
break;
}
collector = TopScoreDocCollector.create(numTotalHits, false);
searcher.search(query, collector);
hits = collector.topDocs().scoreDocs;
}
end = Math.min(hits.length, start + hitsPerPage);
for (int i = start; i < end; i++) {
if (raw) { // output raw format
System.out.println("doc=" + hits[i].doc + " score=" + hits[i].score);
continue;
}
Document doc = searcher.doc(hits[i].doc);
String id = doc.get("id");
if (id != null) {
System.out.println((i + 1) + ". " + id);
String name = doc.get("name");
if (name != null) {
System.out.println(" name: " + doc.get("name"));
}
String description = doc.get("description");
if (description != null) {
System.out.println(" description: " + doc.get("description"));
}
String text= doc.get("text");
if (text != null) {
System.out.println(" text: " + doc.get("text"));
}
} else {
System.out.println((i + 1) + ". " + "No path for this document");
}
}
if (!interactive) {
break;
}
if (numTotalHits >= end) {
boolean quit = false;
while (true) {
System.out.print("Press ");
if (start - hitsPerPage >= 0) {
System.out.print("(p)revious page, ");
}
if (start + hitsPerPage < numTotalHits) {
System.out.print("(n)ext page, ");
}
System.out.println("(q)uit or enter number to jump to a page.");
String line = in.readLine();
if (line.length() == 0 || line.charAt(0) == 'q') {
quit = true;
break;
}
if (line.charAt(0) == 'p') {
start = Math.max(0, start - hitsPerPage);
break;
} else if (line.charAt(0) == 'n') {
if (start + hitsPerPage < numTotalHits) {
start += hitsPerPage;
}
break;
} else {
int page = Integer.parseInt(line);
if ((page - 1) * hitsPerPage < numTotalHits) {
start = (page - 1) * hitsPerPage;
break;
} else {
System.out.println("No such page");
}
}
}
if (quit) {
break;
}
end = Math.min(numTotalHits, start + hitsPerPage);
}
}
}
}
谢谢。