import java.io.File;
import java.io.FileInputStream;
import java.io.InputStream;import org.apache.poi.POIXMLDocument;
import org.apache.poi.POIXMLTextExtractor;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.openxml4j.opc.OPCPackage;
import org.apache.poi.xwpf.extractor.XWPFWordExtractor;/*** POI 读取 word 2003 和 word 2007 中文字内容的测试类<br />* @createDate 2009-07-25* @author Carl He*/
public class Test {public static void main(String[] args) {try {//word 2003： 图片不会被读取InputStream is = new FileInputStream(new File("c://files//2003.doc"));WordExtractor ex = new WordExtractor(is);String text2003 = ex.getText();System.out.println(text2003);//word 2007 图片不会被读取， 表格中的数据会被放在字符串的最后OPCPackage opcPackage = POIXMLDocument.openPackage("c://files//2007.docx");POIXMLTextExtractor extractor = new XWPFWordExtractor(opcPackage);String text2007 = extractor.getText();System.out.println(text2007);} catch (Exception e) {e.printStackTrace();}}
}

    public static Document getDocument2007(File file) throws Exception {String docPath = file.getAbsolutePath();String title = file.getName();// 鍒涘缓DocumentDocument document = new Document();OPCPackage opcPackage = POIXMLDocument.openPackage(docPath);POIXMLTextExtractor extractor = new XWPFWordExtractor(opcPackage);String cont = extractor.getText();document.add(new StringField("filename", title, Field.Store.YES));//TOKENIZED//document.add(new Field("contents", contents));document.add(new TextField("contents", cont,Field.Store.YES));document.add(new TextField("path", docPath, Field.Store.YES));document.add(new StringField("indexDate",DateTools.dateToString(new Date(), DateTools.Resolution.DAY),Field.Store.YES));return document;}public static Document getDocument2003(File file) throws Exception {String docPath = file.getAbsolutePath();String title = file.getName();// 鍒涘缓DocumentDocument document = new Document();InputStream is = new FileInputStream(new File(docPath));WordExtractor ex = new WordExtractor(is);//is鏄疻ORD鏂囦欢鐨処nputStream String cont =  ex.getText();document.add(new StringField("filename", title, Field.Store.YES));//TOKENIZEDdocument.add(new TextField("contents", cont,Field.Store.YES));document.add(new TextField("path", docPath, Field.Store.YES));document.add(new StringField("indexDate",DateTools.dateToString(new Date(), DateTools.Resolution.DAY),Field.Store.YES));return document;}