Lucene检索WORD等文件

###Lucene是什么&＃xff1f;
####lucene是apache开源的全文检索的框架&＃xff0c;不像百度那样的搜索引擎拿来就能用&＃xff01;
###Lucene实现检索的过程&＃xff1f;
####Lucene实际上是先将文本写入&＃xff0c;然后再搜索出来。
###写入&＃xff1a;
####涉及的类: Document 、Field 、IndexWriter
####Document相当于数据库表的一行&＃xff0c;Field相当于数据库表的一个字段&＃xff0c;Document可以包含多个Field&＃xff0c;用IndexWriter对象将Document对象写在磁盘上或内存里&＃xff0c;这就实现了字符串的写入&＃xff01;
###搜索&＃xff1a;
####对写入的文本进行搜索&＃xff01;

###如何检索WORD等microsoft文件&＃xff1f;
####要实现Lucene检索WORD等文件&＃xff0c;首先需要读取出WORD文件中的内容&＃xff0c;再使用Lucene将内容写入。

###如何读取microsoft文件&＃xff1f;
####可以使用apache的POI开源项目进行读取。

#####javaCode:

package org.fazlan.lucene.demo;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.document.Field;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;public class Indexer {// location where the index will be stored.public static final String INDEX_DIR &＃61; "src/main/resources/index";private IndexWriter writer &＃61; null;public Indexer() {try {writer &＃61; new IndexWriter(FSDirectory.open(new File(INDEX_DIR)),new IndexWriterConfig(Version.LUCENE_36, new StandardAnalyzer(Version.LUCENE_36)));} catch (Exception e) {e.printStackTrace();}}/*** This method will add the items into index*/public void writeIndex(IndexItem indexItem) throws IOException {// deleting the item, if already existswriter.deleteDocuments(new Term(IndexItem.ID, indexItem.getId().toString()));Document doc &＃61; new Document();doc.add(new Field(IndexItem.ID, indexItem.getId().toString(), Field.Store.YES, Field.Index.NOT_ANALYZED));doc.add(new Field(IndexItem.TITLE, indexItem.getTitle(), Field.Store.YES, Field.Index.ANALYZED));doc.add(new Field(IndexItem.FILENAME, indexItem.getFilename(), Field.Store.YES, Field.Index.NOT_ANALYZED));doc.add(new Field(IndexItem.CONTENT, indexItem.getContent(), Field.Store.YES, Field.Index.ANALYZED));doc.add(new Field(IndexItem.DATE, indexItem.getDate(), Field.Store.YES, Field.Index.NOT_ANALYZED));doc.add(new Field(IndexItem.USER_NAME, indexItem.getUserName(), Field.Store.YES, Field.Index.NOT_ANALYZED));doc.add(new Field(IndexItem.URL, indexItem.getUrl(), Field.Store.YES, Field.Index.NOT_ANALYZED));// add the document to the indexwriter.addDocument(doc);}/*** Closing the writer*/public void close() throws IOException {writer.close();}
}


package org.fazlan.lucene.demo;/*** 索引对象&＃xff0c;根据业务要求改动* * &＃64;author JiaJiCheng**/
public class IndexItem {private Long id;private String title;private String filename;private String content;private String date;private String userName;private String url;public static final String ID &＃61; "id";public static final String TITLE &＃61; "title";public static final String CONTENT &＃61; "content";public static final String DATE &＃61; "date";public static final String USER_NAME &＃61; "userName";public static final String FILENAME &＃61; "filename";public static final String URL &＃61; "url";public IndexItem(Long id, String title, String filename, String content, String date, String userName, String url) {this.id &＃61; id;this.title &＃61; title;this.content &＃61; content;this.date &＃61; date;this.userName &＃61; userName;this.filename &＃61; filename;this.url &＃61; url;}public String getFilename() {return filename;}public String getUrl() {return url;}public String getDate() {return date;}public String getUserName() {return userName;}public Long getId() {return id;}public String getTitle() {return title;}public String getContent() {return content;}&＃64;Overridepublic String toString() {return "IndexItem{" &＃43; "id&＃61;" &＃43; id &＃43; ", title&＃61;&＃39;" &＃43; title &＃43; ", content&＃61;&＃39;" &＃43; content &＃43; &＃39;\&＃39;&＃39; &＃43; "date&＃61;" &＃43; date&＃43; "userName&＃61;" &＃43; userName &＃43; &＃39;}&＃39;;}
}

package org.fazlan.lucene.demo;import org.apache.poi.extractor.ExtractorFactory;import java.io.File;
import java.io.IOException;/*** 文件转换器* * &＃64;author JiaJiCheng**/
public class MSDocumentParser {private static String getFilename(String filename) {return filename.substring(0, filename.lastIndexOf("."));}public static IndexItem parser(File file, String date, String userName, String url) throws IOException {String content &＃61; null;try {content &＃61; ExtractorFactory.createExtractor(file).getText();} catch (Exception e) {e.printStackTrace();}return new IndexItem((long) file.hashCode(), getFilename(file.getName()), file.getName(), content, date,userName, url);}
}

package org.fazlan.lucene.demo;import java.io.File;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexReader;
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.store.FSDirectory;
import org.apache.lucene.util.Version;public class Searcher {private IndexSearcher searcher;private QueryParser titleQueryParser;private QueryParser contentQueryParser;private static final StandardAnalyzer analyzer &＃61; new StandardAnalyzer(Version.LUCENE_36);// default find result size.private static final int DEFAULT_RESULT_SIZE &＃61; 100;public Searcher() throws IOException {// open the index directory to searchsearcher &＃61; new IndexSearcher(IndexReader.open(FSDirectory.open(new File(Indexer.INDEX_DIR))));// defining the query parser to search items by title field.titleQueryParser &＃61; new QueryParser(Version.LUCENE_36, IndexItem.TITLE, analyzer);// defining the query parser to search items by content field.contentQueryParser &＃61; new QueryParser(Version.LUCENE_36, IndexItem.CONTENT, analyzer);}/*** This method is used to find the indexed items by the title.* * &＃64;param queryString* - the query string to search for*/public List findByTitle(String queryString) throws ParseException, IOException {// create query from the incoming query string.Query query &＃61; titleQueryParser.parse(queryString);// execute the query and get the resultsScoreDoc[] queryResults &＃61; searcher.search(query, DEFAULT_RESULT_SIZE).scoreDocs;List results &＃61; new ArrayList();// process the resultsfor (ScoreDoc scoreDoc : queryResults) {Document doc &＃61; searcher.doc(scoreDoc.doc);results.add(new IndexItem(Long.parseLong(doc.get(IndexItem.ID)), doc.get(IndexItem.TITLE),doc.get(IndexItem.FILENAME), doc.get(IndexItem.CONTENT), doc.get(IndexItem.DATE),doc.get(IndexItem.USER_NAME), doc.get(IndexItem.URL)));}return results;}/*** This method is used to find the indexed items by the content.* * &＃64;param queryString* - the query string to search for*/public List findByContent(String queryString) throws ParseException, IOException {// create query from the incoming query string.Query query &＃61; contentQueryParser.parse(queryString);// execute the query and get the resultsScoreDoc[] queryResults &＃61; searcher.search(query, DEFAULT_RESULT_SIZE).scoreDocs;List results &＃61; new ArrayList();// process the resultsfor (ScoreDoc scoreDoc : queryResults) {Document doc &＃61; searcher.doc(scoreDoc.doc);results.add(new IndexItem(Long.parseLong(doc.get(IndexItem.ID)), doc.get(IndexItem.TITLE),doc.get(IndexItem.FILENAME), doc.get(IndexItem.CONTENT), doc.get(IndexItem.DATE),doc.get(IndexItem.USER_NAME), doc.get(IndexItem.URL)));}return results;}public void close() throws IOException {searcher.close();}
}

package org.fazlan.lucene.demo;import org.apache.lucene.queryParser.ParseException;import java.io.File;
import java.io.IOException;
import java.util.List;/*** 实例* * &＃64;author JiaJiCheng**/
public class FileIndexApplication {public static void main(String[] args) throws IOException, ParseException {File msWordFile &＃61; new File("src/main/resources/files/MSWord.doc");File msWord2003File &＃61; new File("src/main/resources/files/MSWord.docx");File msExcellFile &＃61; new File("src/main/resources/files/招商局系统.xls");// creating the indexer and indexing the itemsIndexer indexer &＃61; new Indexer();indexer.writeIndex(MSDocumentParser.parser(msWordFile, "1990-0-0", "zhangsan", "www.baidu.com"));indexer.writeIndex(MSDocumentParser.parser(msWord2003File, "1990-0-0", "zhangsan", "www.baidu.com"));indexer.writeIndex(MSDocumentParser.parser(msExcellFile, "1990-0-0", "zhangsan", "www.baidu.com"));// close the index to enable them indexindexer.close();// creating the Searcher to the same index location as the IndexerSearcher searcher &＃61; new Searcher();// List result &＃61; searcher.findByContent("Microfost",// DEFAULT_RESULT_SIZE);List result &＃61; searcher.findByTitle("招");print(result);searcher.close();}/*** print the results.*/private static void print(List result) {System.out.println("Result Size: " &＃43; result.size());for (IndexItem item : result) {System.out.println(item);}}
}

org.apache.lucenelucene-core3.6.0org.apache.poipoi3.8org.apache.poipoi-ooxml3.8org.apache.poipoi-scratchpad3.8junitjunit3.8.1test


##完整的项目代码见附件