https://forum.andowson.com/posts/list/5.page JForum - http://www.jforum.net 可以給個起手式嗎？

懇請賜教～

Lucene 3.0.0 API
[url]http://www.jarvana.com/jarvana/view/org/apache/lucene/lucene-core/3.0.0/lucene-core-3.0.0-javadoc.jar!/index.html?org/apache/lucene/util/Version.html[/url]


[code]
[Index code]

import java.io.File;
import java.io.FileReader;
import java.io.IOException;
import java.util.Date;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.DateTools;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.SimpleFSDirectory;
import org.apache.lucene.util.Version;

public class Indexer
{
public static void main(String[] args) throws IOException
{
String Idx = "C:\\test\\Idx";
String dateDir = "C:\\test\\Data";
IndexWriter indexWriter = null;

Directory dir = new SimpleFSDirectory(new File(Idx));
indexWriter = new IndexWriter(dir,new StandardAnalyzer(Version.LUCENE_30),true,IndexWriter.MaxFieldLength.UNLIMITED);

File[] files = new File(dateDir).listFiles();

for (int i = 0; i < files.length; i++)
{
Document doc = new Document();
doc.add(new Field("contents", new FileReader(files[i])));
doc.add(new Field("filename", files[i].getName(), Field.Store.YES, Field.Index.NOT_ANALYZED));
doc.add(new Field("indexDate",DateTools.dateToString(new Date(), DateTools.Resolution.DAY),Field.Store.YES,Field.Index.NOT_ANALYZED));
indexWriter.addDocument(doc);
}
System.out.println("numDocs"+indexWriter.numDocs());
indexWriter.close();

}

}
[END]

[Searcher code]

import java.io.File;
import java.io.IOException;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.queryParser.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.Directory;
import org.apache.lucene.store.SimpleFSDirectory;
import org.apache.lucene.util.Version;

public class Searcher
{
public static void main(String[] args) throws IOException, ParseException
{
String Idx = "C:\\test\\Idx";
Directory dir = new SimpleFSDirectory(new File(Idx));
IndexSearcher indexSearch = new IndexSearcher(dir);

QueryParser queryParser = new QueryParser(Version.LUCENE_30, "contents", new StandardAnalyzer(Version.LUCENE_30));
Query query = queryParser.parse("鼻涕"); //key Query term
TopDocs hits = indexSearch.search(query, 500);
System.out.println("找到"+hits.totalHits+"個");
for (int i = 0; i < hits.scoreDocs.length; i++)
{
ScoreDoc sdoc = hits.scoreDocs[i];
Document doc = indexSearch.doc(sdoc.doc);
System.out.println(doc.get("filename"));
}
indexSearch.close();
}
}
[END]
[/code]

訊息回應如下圖：
http://img263.imageshack.us/f/bug03.jpg/

]]> https://forum.andowson.com/posts/preList/467/961.page https://forum.andowson.com/posts/preList/467/961.page GMT 1.首先下載[url=http://ftp.stut.edu.tw/var/ftp/pub/OpenSource/apache//lucene/java/lucene-3.0.3.zip]Lucene 3.0.3[/url]，然後解壓縮，並將下列jar檔加入CLASSPATH
lucene-3.0.3\lucene-core-3.0.3.jar
lucene-3.0.3\contrib\analyzers\common\lucene-analyzers-3.0.3.jar

2.接著建立C:\test目錄，並在C:\test底下再建立兩個子目錄Idx和Data

3.接著透過Google搜尋[google]鼻涕[/google]，找到任何一篇文章後，將它的內容另存成一個文字檔，如1.txt，存到C:\test\Data目錄下。

4.執行Indexer

5.再執行Searcher





]]> https://forum.andowson.com/posts/preList/467/962.page https://forum.andowson.com/posts/preList/467/962.page GMT 編碼的屬性是UTF-8應更改為ANSI才對囧rz...]]> https://forum.andowson.com/posts/preList/467/963.page https://forum.andowson.com/posts/preList/467/963.page GMT 我想可以用高亮方式來處理：
Searcher.java:
[code]
import java.io.BufferedInputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.StringReader;

import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.queryParser.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.search.highlight.Highlighter;
import org.apache.lucene.search.highlight.InvalidTokenOffsetsException;
import org.apache.lucene.search.highlight.QueryScorer;
import org.apache.lucene.search.highlight.Scorer;
import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.SimpleFSDirectory;
import org.apache.lucene.util.Version;

public class Searcher {
public static void main(String[] args) throws IOException, ParseException, InvalidTokenOffsetsException {
String Idx = "C:\\test\\Idx";
String dataDir = "C:\\test\\Data";
Directory dir = new SimpleFSDirectory(new File(Idx));
IndexSearcher indexSearch = new IndexSearcher(dir);

QueryParser queryParser = new QueryParser(Version.LUCENE_30,
"contents", new StandardAnalyzer(Version.LUCENE_30));
Query query = queryParser.parse("鼻涕"); // key Query term
TopDocs hits = indexSearch.search(query, 500);
System.out.println("找到" + hits.totalHits + "個");
for (int i = 0; i < hits.scoreDocs.length; i++) {
ScoreDoc sdoc = hits.scoreDocs[i];
Document doc = indexSearch.doc(sdoc.doc);
System.out.println(doc.get("filename"));
Scorer scorer = new QueryScorer(query);
SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter("", "");
Highlighter highlighter = new Highlighter(simpleHTMLFormatter, scorer);
String content = readFileAsString(dataDir+File.separator+doc.get("filename"));
TokenStream tokenStream = queryParser.getAnalyzer().tokenStream(
"contents", new StringReader(content));

String fragment = highlighter.getBestFragment(tokenStream, content);
System.out.println(fragment != null ? fragment : content);

}
indexSearch.close();
}
private static String readFileAsString(String filePath) throws java.io.IOException{
byte[] buffer = new byte[(int) new File(filePath).length()];
BufferedInputStream f = null;
try {
f = new BufferedInputStream(new FileInputStream(filePath));
f.read(buffer);
} finally {
if (f != null) try { f.close(); } catch (IOException ignored) { }
}
return new String(buffer);
}
}
[/code]
需另外加入下列jar檔到CLASSPATH:
lucene-3.0.3\contrib\highlighter\lucene-highlighter-3.0.3.jar
lucene-3.0.3\contrib\memory\lucene-memory-3.0.3.jar]]> https://forum.andowson.com/posts/preList/467/966.page https://forum.andowson.com/posts/preList/467/966.page GMT