[英]Indexing and Searching Lucene Index
我一直在與Lucene合作,嘗試構建索引文件和搜索文件以連接到我的數據庫,對一些行進行索引,然后對它們進行搜索。
我的兩個文件都成功編譯,但是沒有返回搜索結果。 索引器連接到數據庫並正確獲取數據,但是我不知道它是否正確保存到索引中,或者我的問題是否出在搜索文件上。
這些文件來自Lucene演示,並經過修改以查看數據庫而不是.txt文件。
索引器:
package org.apache.lucene.demo;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.LongField;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig.OpenMode;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.io.InputStreamReader;
import java.sql.Connection;
import java.sql.DriverManager;
import java.sql.PreparedStatement;
import java.sql.ResultSet;
import java.sql.SQLException;
import java.sql.Statement;
import java.util.Date;
public class IndexFilesDB {
private IndexFilesDB() {}
public static void main(String[] args) {
String usage = "java org.apache.lucene.demo.IndexFiles"
+ " [-index INDEX_PATH] [-docs DOCS_PATH] [-update]\n\n"
+ "This indexes the documents in DOCS_PATH, creating a Lucene index"
+ "in INDEX_PATH that can be searched with SearchFiles";
String indexPath = "index";
String docsPath = null;
String query = null;
String connection = null;
boolean create = true;
for(int i=0;i<args.length;i++) {
if ("-index".equals(args[i])) {
indexPath = args[i+1];
i++;
} else if ("-update".equals(args[i])) {
create = false;
i++;
} else if ("-q".equals(args[i])) {
query = args[i+1];
i++;
} else if ("-c".equals(args[i])) {
connection = args[i+1];
i++;
}
}
if (query == null) {
System.err.println("Usage: " + usage);
System.exit(1);
}
if (connection == null) {
System.err.println("Usage: " + usage);
System.exit(1);
}
/*final File docDir = new File(docsPath);
if (!docDir.exists() || !docDir.canRead()) {
System.out.println("Document directory '" +docDir.getAbsolutePath()+ "' does not exist or is not readable, please check the path");
System.exit(1);
}*/
Date start = new Date();
try {
System.out.println("Indexing to directory '" + indexPath + "'...");
Directory dir = FSDirectory.open(new File(indexPath));
// :Post-Release-Update-Version.LUCENE_XY:
Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_47);
IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_47, analyzer);
if (create) {
// Create a new index in the directory, removing any
// previously indexed documents:
iwc.setOpenMode(OpenMode.CREATE);
} else {
// Add new documents to an existing index:
iwc.setOpenMode(OpenMode.CREATE_OR_APPEND);
}
// Optional: for better indexing performance, if you
// are indexing many documents, increase the RAM
// buffer. But if you do this, increase the max heap
// size to the JVM (eg add -Xmx512m or -Xmx1g):
//
// iwc.setRAMBufferSizeMB(256.0);
IndexWriter writer = new IndexWriter(dir, iwc);
indexDocs(writer, query, connection);
// NOTE: if you want to maximize search performance,
// you can optionally call forceMerge here. This can be
// a terribly costly operation, so generally it's only
// worth it when your index is relatively static (ie
// you're done adding documents to it):
//
// writer.forceMerge(1);
writer.close();
Date end = new Date();
System.out.println(end.getTime() - start.getTime() + " total milliseconds");
} catch (IOException e) {
System.out.println(" caught a " + e.getClass() +
"\n with message: " + e.getMessage());
}
}
public static void indexDocs(IndexWriter writer, String query, String connection) {
try {
//System.out.println("Query: " + query);
//System.out.println("Connection: " + connection);
Connection connect = null;
Statement statement = null;
ResultSet resultSet = null;
Class.forName("com.mysql.jdbc.Driver");
// Setup the connection with the DB
connect = DriverManager.getConnection("jdbc:mysql://XXXXXX.com/mydata?"
+ "user=username&password=password");
// Statements allow to issue SQL queries to the database
statement = connect.createStatement();
// Result set get the result of the SQL query
resultSet = statement.executeQuery("select * from lists");
while (resultSet.next()) {
String listid = resultSet.getString("list_id");
String listtitle = resultSet.getString("name");
Document doc = new Document();
doc.add(new StringField("listid", listid, Field.Store.YES));
doc.add(new StringField("title", listtitle, Field.Store.YES));
//System.out.println("listid: " + listid);
//System.out.println("name: " + name);
if (writer.getConfig().getOpenMode() == OpenMode.CREATE) {
// New index, so we just add the document (no old document can be there):
System.out.println("adding " + listtitle);
writer.addDocument(doc);
}
}
} catch (Exception e) {
System.out.println(e);
}
}
}
搜索者:
package org.apache.lucene.demo;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
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.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
/** Simple command-line based search demo. */
public class SearchFilesDB {
private SearchFilesDB() {}
/** 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] [-query string] [-raw] [-paging hitsPerPage]\n\nSee http://lucene.apache.org/core/4_1_0/demo/ for details.";
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 queryString = null;
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 ("-query".equals(args[i])) {
queryString = 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 ("-paging".equals(args[i])) {
hitsPerPage = Integer.parseInt(args[i+1]);
if (hitsPerPage <= 0) {
System.err.println("There must be at least 1 hit per page.");
System.exit(1);
}
i++;
}
}
IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(index)));
IndexSearcher searcher = new IndexSearcher(reader);
// :Post-Release-Update-Version.LUCENE_XY:
Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_47);
BufferedReader in = null;
if (queries != null) {
in = new BufferedReader(new InputStreamReader(new FileInputStream(queries), "UTF-8"));
} else {
in = new BufferedReader(new InputStreamReader(System.in, "UTF-8"));
}
// :Post-Release-Update-Version.LUCENE_XY:
QueryParser parser = new QueryParser(Version.LUCENE_47, field, analyzer);
while (true) {
if (queries == null && queryString == null) { // prompt the user
System.out.println("Enter query: ");
}
String line = queryString != null ? queryString : in.readLine();
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");
}
doPagingSearch(in, searcher, query, hitsPerPage, raw, queries == null && queryString == null);
if (queryString != null) {
break;
}
}
reader.close();
}
public static void doPagingSearch(BufferedReader in, IndexSearcher searcher, Query query,
int hitsPerPage, boolean raw, boolean interactive) throws IOException {
// Collect enough docs to show 5 pages
TopDocs results = searcher.search(query, 5 * hitsPerPage);
ScoreDoc[] hits = results.scoreDocs;
int numTotalHits = results.totalHits;
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;
}
hits = searcher.search(query, numTotalHits).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 path = doc.get("listid");
System.out.println("here:" + path);
if (path != null) {
System.out.println((i+1) + ". " + path);
String title = doc.get("title");
if (title != null) {
System.out.println(" Title: " + doc.get("title"));
}
} else {
System.out.println((i+1) + ". " + "No path for this document");
}
}
if (!interactive || end == 0) {
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);
}
}
}
}
如果有人能夠指出我犯錯的正確方向,將不勝感激!
編輯:我已經使用Luke來查看AKS建議的索引,並且可以看到索引中的術語。
我想這一定是搜索文件有問題嗎?
解決了!
在索引器文件中,我正在索引字段“ listid”和“ title”:
doc.add(new StringField("listid", listid, Field.Store.YES));
doc.add(new StringField("title", listtitle, Field.Store.YES));
但在搜索器文件中,將其設置在文件的最上方以查找“內容”字段:
String field = "contents";
如果其他人遇到類似的問題,我建議使用LukeAll,如AKS向我建議的那樣。 我必須使用較低版本的Lucene才能正常工作,但絕對有幫助!
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.