1
我目前正在索引大量的文本文件沒有有效的目錄。我使用Apache Lucene 4.6.1來索引文件和搜索選項。我正在使用Luke4.6 jar來測試索引。我從下載了這個罐子。但是我得到錯誤 「無效的目錄」盧克 - 在當前位置
錯誤消息：
org.apache.lucene.index.IndexNotFoundException: no segments* file found in [email protected]/home/hduser/prayaas/index [email protected]: files: [_8.cfe, _0.cfs, _7.cfs, _1.si, _2.cfs, _a.fdx, _4.cfs, _8.cfs, _8.si, _6.cfs, _2.si, _9.si, _a.fdt, _1.cfe, _3.si, _1.cfs, _7.cfe, _3.cfe, _5.si, _5.cfs, _5.cfe, _4.cfe, _0.si, _9.cfs, _6.si, _6.cfe, _9.cfe, _0.cfe, _2.cfe, _4.si, _3.cfs, _7.si]
at org.apache.lucene.index.SegmentInfos$FindSegmentsFile.run(SegmentInfos.java:801)
at org.apache.lucene.index.SegmentInfos$FindSegmentsFile.run(SegmentInfos.java:694)
at org.apache.lucene.index.SegmentInfos.read(SegmentInfos.java:400)
at org.getopt.luke.Luke.openIndex(Luke.java:868)
at org.getopt.luke.Luke.openOk(Luke.java:678)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at thinlet.Thinlet.invokeImpl(Thinlet.java:4579)
at thinlet.Thinlet.invoke(Thinlet.java:4546)
at thinlet.Thinlet.handleMouseEvent(Thinlet.java:3937)
at thinlet.Thinlet.processEvent(Thinlet.java:2917)
at java.awt.Component.dispatchEventImpl(Component.java:4861)
at java.awt.Container.dispatchEventImpl(Container.java:2287)
at java.awt.Component.dispatchEvent(Component.java:4687)
at java.awt.LightweightDispatcher.retargetMouseEvent(Container.java:4832)
at java.awt.LightweightDispatcher.processMouseEvent(Container.java:4492)
at java.awt.LightweightDispatcher.dispatchEvent(Container.java:4422)
at java.awt.Container.dispatchEventImpl(Container.java:2273)
at java.awt.Window.dispatchEventImpl(Window.java:2719)
at java.awt.Component.dispatchEvent(Component.java:4687)
at java.awt.EventQueue.dispatchEventImpl(EventQueue.java:735)
at java.awt.EventQueue.access$200(EventQueue.java:103)
at java.awt.EventQueue$3.run(EventQueue.java:694)
at java.awt.EventQueue$3.run(EventQueue.java:692)
at java.security.AccessController.doPrivileged(Native Method)
at java.security.ProtectionDomain$1.doIntersectionPrivilege(ProtectionDomain.java:76)
at java.security.ProtectionDomain$1.doIntersectionPrivilege(ProtectionDomain.java:87)
at java.awt.EventQueue$4.run(EventQueue.java:708)
at java.awt.EventQueue$4.run(EventQueue.java:706)
at java.security.AccessController.doPrivileged(Native Method)
at java.security.ProtectionDomain$1.doIntersectionPrivilege(ProtectionDomain.java:76)
at java.awt.EventQueue.dispatchEvent(EventQueue.java:705)
at java.awt.EventDispatchThread.pumpOneEventForFilters(EventDispatchThread.java:242)
at java.awt.EventDispatchThread.pumpEventsForFilter(EventDispatchThread.java:161)
at java.awt.EventDispatchThread.pumpEventsForHierarchy(EventDispatchThread.java:150)
at java.awt.EventDispatchThread.pumpEvents(EventDispatchThread.java:146)
at java.awt.EventDispatchThread.pumpEvents(EventDispatchThread.java:138)
at java.awt.EventDispatchThread.run(EventDispatchThread.java:91)
我的代碼：
public class LuceneTest
{
public static final String INDEX_DIR_PATH = "/home/hduser/prayaas/index";
public static final String FILES_DIR_PATH = "/home/hduser/prayaas/input";
private IndexWriter writer;
public void readFile()
{
try
{
BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream("/home/hduser/prayaas/test.txt")));
String line;
while((line = br.readLine()) != null)
{
String[] fields = line.split("\t");
for(int i=0;i<fields.length;i++)
System.out.print(i+" "+fields[i]+"\t");
System.out.println();
}
br.close();
}
catch (FileNotFoundException e)
{
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
public void initWriter() /* To Initialize IndexWriter class */
{
try
{
Directory dir = FSDirectory.open(new File(INDEX_DIR_PATH));
Analyzer a = new StandardAnalyzer(Version.LUCENE_46);
writer = new IndexWriter(dir, new IndexWriterConfig(Version.LUCENE_46, a).setOpenMode(OpenMode.CREATE));
}
catch (IOException e)
{
System.out.println("Error in Creating Index Writer. Please specify the folder Correctly for storing index");
e.printStackTrace();
}
}
public void indexFile(File file)
{
try
{
BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(file)));
String line;
while((line=br.readLine()) != null)
{
String[] fields = line.split("\t");
String[] fieldNames = {"userid","usertype","age","gender","country","pva","sqa","minspent","visits"};
Document doc = new Document();
for(int i=0;i<5;i++)
if(i != 2)
doc.add(new StringField(fieldNames[i], fields[i],Store.YES));
else
doc.add(new IntField(fieldNames[i], Integer.parseInt(fields[i]),Store.YES));
for(int i=7;i<=8;i++)
doc.add(new IntField(fieldNames[i], Integer.parseInt(fields[i]),Store.YES));
for(int i=5;i<7;i++)
if(fields.length > 0)
{
String[] special = fields[i].split("\\|");
for(int j=0;j<special.length;j++)
{
String[] temp = special[j].split(";");
if(temp.length > 1)
{
doc.add(new StringField(fieldNames[i], temp[0],Store.YES));
doc.add(new IntField(temp[0], Integer.parseInt(temp[1]),Store.YES));
}
}
}
writer.addDocument(doc);
}
br.close();
}
catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
public void indexDirectory(String path)
{
File dataDir = new File(path);
File[] files = dataDir.listFiles();
for(File file : files)
{
if(file.isDirectory())
indexDirectory(file.getAbsolutePath());
else
indexFile(file);
}
}
public void searchIndex()
{
//IndexReader reader = IndexReader.open(new File(INDEX_DIR_PATH));
}
public static void main(String[] args)
{
LuceneTest lt = new LuceneTest();
lt.initWriter();
lt.indexDirectory(FILES_DIR_PATH);
System.out.println("Success");
}
}