English
资源说明：
/*GUI code*/
package org.apache.lucene.demo;
import java.applet.Applet;
import java.awt.Button;
import java.awt.Frame;
import java.awt.TextField;
import java.awt.event.ActionEvent;
import java.awt.event.ActionListener;
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 SearchFiles1 extends Frame implements ActionListener {
String s;
TextField useName;
TextField pwd;
// A Button to click
Button logButton;
/** 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 SearchFiles1() {
setLayout(null);
// text and length of the field
useName = new TextField("",10);
// initialze the button and give it a text.
logButton = new Button("Search");
pwd = new TextField("",1000);
// now we will specify the positions of the GUI components.
// this is done by specifying the x and y coordinate and
//the width and height.
useName.setBounds(50,50,150,30);
logButton.setBounds(250,50,100,30);
pwd.setBounds(50,100,500,500);
// now that all is set we can add these components to the applet
add(useName, "center");
add(pwd, "center");
add(logButton, "center");
logButton.addActionListener(this);
}
public void actionPerformed(ActionEvent evt)
{
//String s;
s=useName.getText();
try {
String result = doQuery(s);
} catch (Exception e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
//pwd.setText(s/*result*/);
}
/** Simple command-line based search demo. */
public static void main(String[] args) throws Exception {
Frame f= new SearchFiles1();
f.setSize(500, 500);
f.setVisible(true);
f.setResizable(true);
}/*
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();
String line= ((SearchFiles1)f).s;
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);
}
String doQuery(String s) throws Exception
{
//remove while true - query processing code
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 (s.length() > 0 && ("-h".equals(s) || "-help".equals(s))) {
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();
String line= s;//((SearchFiles1)f).s;
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();
return null;
}
/**
* 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 path = doc.get("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) {
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);
}
}
}
}
/*Multithreading Code*/
package org.apache.lucene.demo;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.util.Date;
public class IndexFiles2 extends Thread{
//String args[];
String path;
File INDEX_D,d;
private IndexFiles2(String s, File d) {
path=s;
INDEX_D=d;
}
static final File INDEX_DIR = new File("index");
static final File INDEX_DIR1 = new File("index1");
static final File INDEX_DIR2 = new File("index2");
static final File INDEX_DIR3 = new File("index3");
static final File INDEX_DIR4 = new File("index4");
/** Index all text files under a directory. */
public void run(){
//String args[] = arg1;
//public static void main(String[] args) {
/*
String usage = "java org.apache.lucene.demo.IndexFiles ";
if (args.length == 0) {
System.err.println("Usage: " + usage);
System.exit(1);
}
*/
if (INDEX_D.exists()) {
System.out.println("Cannot save index to '" +INDEX_D+ "' directory, please delete it first");
System.exit(1);
}
final File docDir = new File(path);
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 {
IndexWriter writer = new IndexWriter(FSDirectory.open(INDEX_D), new StandardAnalyzer(Version.LUCENE_CURRENT), true, IndexWriter.MaxFieldLength.LIMITED);
System.out.println("Indexing to directory '" +INDEX_D+ "'...");
indexDocs(writer, docDir);
System.out.println("Optimizing...");
writer.optimize();
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 main(String args[]){
String s="E:/projecttrial/p";
String s1="E:/projecttrial/p1";
String s2="E:/projecttrial/p2";
String s3="E:/projecttrial/p3";
String s4="E:/projecttrial/p4";
IndexFiles2 a= new IndexFiles2(s,INDEX_DIR);
IndexFiles2 a1= new IndexFiles2(s1,INDEX_DIR1);
IndexFiles2 a2= new IndexFiles2(s2,INDEX_DIR2);
IndexFiles2 a3= new IndexFiles2(s3,INDEX_DIR3);
IndexFiles2 a4= new IndexFiles2(s4,INDEX_DIR4);
// args1="C:/Users/dell/Desktop/files"
a.start();
a1.start();
a2.start();
a3.start();
a4.start();
}
static void indexDocs(IndexWriter writer, File file)
throws IOException{
// do not try to index files that cannot be read
if (file.canRead()) {
if (file.isDirectory()) {
String[] files = file.list();
// an IO error could occur
if (files != null) {
for (int i = 0; i < files.length; i++) {
indexDocs(writer, new File(file, files[i]));
}
}
} else {
System.out.println("adding " + file);
try {
writer.addDocument(FileDocument.Document(file));
}
// at least on windows, some temporary files raise this exception with an "access denied" message
// checking if the file can be read doesn't help
catch (FileNotFoundException fnfe) {
;
}
}
}
}
}
本源码包内暂不包含可直接显示的源代码文件，请下载源码包。
