lucene开发中有关读取pdf,html,word,rtf,txt,powerpoint,excel等文档的操作

关于这七种文档，我相信应该是最常用的文档了

在以下的介绍中会提到POI，现介绍下POI吧

poi处理WORD,EXCEL比较好:http://jakarta.apache.org/poi/

poi处理至少需要如下几个JAR包

dom4j-1.6.1.jar
geronimo-stax-api_1.0_spec-1.0.jar
ooxml-schemas-1.0.jar
poi-3.5-final-20090828.jar
poi-contrib-3.5-FiNAL-20090828.jar
poi-ooxml-3.5-Final-20090828.jar
poi-scratchpad-3.5-Final-20090828.jar
xmlbeans-2.3.0.jar


PDFbox处理PDF比较好：http://pdfbox.apache.org/download.html

下面一一介绍了

第一和第二是只支持03版的word和excel文档

第一、首先来看WORD文档：
我这里用的是poi，相关jar包自己去下载，然后加到工程中（以下所要用的jar包也是，不再重复说）

public static String readWord(String path) throws Exception {
String bodyText = null;
try {
FileInputStream is = new FileInputStream(path);
bodyText = new WordExtractor(is).getText();
} catch (Exception e) {
System.out.println("=======");
}
return bodyText;
} 


  第二、Exel的文档

 public static String ReadExcel(String path) throws IOException {
InputStream inputStream = null;
String content = null;
try {
inputStream = new FileInputStream(path);
HSSFWorkbook wb = new HSSFWorkbook(inputStream);
ExcelExtractor extractor = new ExcelExtractor(wb);
extractor.setFormulasNotResults(true);
extractor.setIncludeSheetNames(false);
content = extractor.getText();
} catch (FileNotFoundException e) {
e.printStackTrace();
}
return content;
}

真对07版的word和excel的操作

package com.test;

   
/**   
 * 需要的jar包：   
 * poi-3.0.2-FINAL-20080204.jar   
 * poi-contrib-3.0.2-FINAL-20080204.jar   
 * poi-scratchpad-3.0.2-FINAL-20080204.jar   
 * poi-3.5-beta6-20090622.jar   
 * geronimo-stax-api_1.0_spec-1.0.jar   
 * ooxml-schemas-1.0.jar   
 * openxml4j-bin-beta.jar   
 * poi-ooxml-3.5-beta6-20090622.jar   
 * xmlbeans-2.3.0.jar   
 * dom4j-1.6.1.jar   
 */   

import java.io.FileInputStream;    
import java.io.IOException;    
import java.io.InputStream;    

import org.apache.poi.POIXMLDocument;    
import org.apache.poi.POIXMLTextExtractor;    
import org.apache.poi.hssf.usermodel.HSSFCell;    
import org.apache.poi.hssf.usermodel.HSSFRow;    
import org.apache.poi.hssf.usermodel.HSSFSheet;    
import org.apache.poi.hssf.usermodel.HSSFWorkbook;    
import org.apache.poi.hwpf.extractor.WordExtractor;    
import org.apache.poi.openxml4j.exceptions.OpenXML4JException;    
import org.apache.poi.openxml4j.opc.OPCPackage;    
import org.apache.poi.xssf.usermodel.XSSFCell;    
import org.apache.poi.xssf.usermodel.XSSFRow;    
import org.apache.poi.xssf.usermodel.XSSFSheet;    
import org.apache.poi.xssf.usermodel.XSSFWorkbook;    
import org.apache.poi.xwpf.extractor.XWPFWordExtractor;    
import org.apache.xmlbeans.XmlException;    

public class WordAndExcelExtractor {    
 public static void main(String[] args){    
  try{    
   String wordFile = "D:/松山血战.docx";    
   String wordText2007 = WordAndExcelExtractor.extractTextFromDOC2007(wordFile);    
   System.out.println("wordText2007======="+wordText2007);    

   InputStream is = new FileInputStream("D:/XXX研发中心技术岗位职位需求.xls");       
   String excelText = WordAndExcelExtractor.extractTextFromXLS(is);       
   System.out.println("text2003==========" + excelText);    

   String excelFile = "D:/Hello2007.xlsx";       
   String excelText2007 = WordAndExcelExtractor.extractTextFromXLS2007(excelFile);    
   System.out.println("excelText2007==========" + excelText2007);    


  }catch(Exception e ){    
   e.printStackTrace();    
  }    
 }    

 /**   
  * @Method: extractTextFromDOCX   
  * @Description: 从word 2003文档中提取纯文本   
  *   
  * @param    
  * @return String   
  * @throws   
  */   
    public static String extractTextFromDOC(InputStream is) throws IOException {    
        WordExtractor ex = new WordExtractor(is); //is是WORD文件的InputStream     

        return ex.getText();    
    }    

 /**   
  * @Method: extractTextFromDOCX   
  * @Description: 从word 2007文档中提取纯文本   
  *   
  * @param    
  * @return String   
  * @throws   
  */   
    public static String extractTextFromDOC2007(String fileName) throws IOException, OpenXML4JException, XmlException {    
     OPCPackage opcPackage = POIXMLDocument.openPackage(fileName);    
     POIXMLTextExtractor ex = new XWPFWordExtractor(opcPackage);       

        return ex.getText();    
    }    

 /**   
  * @Method: extractTextFromXLS   
  * @Description: 从excel 2003文档中提取纯文本   
  *   
  * @param    
  * @return String   
  * @throws   
  */   
    @SuppressWarnings("deprecation")    
 private static String extractTextFromXLS(InputStream is)    
        throws IOException {    
        StringBuffer content  = new StringBuffer();    
        HSSFWorkbook workbook = new HSSFWorkbook(is); //创建对Excel工作簿文件的引用     

        for (int numSheets = 0; numSheets < workbook.getNumberOfSheets(); numSheets++) {    
            if (null != workbook.getSheetAt(numSheets)) {    
                HSSFSheet aSheet = workbook.getSheetAt(numSheets); //获得一个sheet    

                for (int rowNumOfSheet = 0; rowNumOfSheet <= aSheet.getLastRowNum(); rowNumOfSheet++) {    
                    if (null != aSheet.getRow(rowNumOfSheet)) {    
                        HSSFRow aRow = aSheet.getRow(rowNumOfSheet); //获得一行    

                        for (short cellNumOfRow = 0; cellNumOfRow <= aRow.getLastCellNum(); cellNumOfRow++) {    
                            if (null != aRow.getCell(cellNumOfRow)) {    
                                HSSFCell aCell = aRow.getCell(cellNumOfRow); //获得列值    

                                if(aCell.getCellType() == HSSFCell.CELL_TYPE_NUMERIC){    
                                 content.append(aCell.getNumericCellValue());    
                                }else if(aCell.getCellType() == HSSFCell.CELL_TYPE_BOOLEAN){    
                                 content.append(aCell.getBooleanCellValue());    
                                }else {    
                                 content.append(aCell.getStringCellValue());    
                                }    
                            }    
                        }    
                    }    
                }    
            }    
        }    

        return content.toString();    
    }    

    /**   
     * @Method: extractTextFromXLS2007   
     * @Description: 从excel 2007文档中提取纯文本   
     *   
     * @param    
     * @return String   
     * @throws   
     */   
    private static String extractTextFromXLS2007(String fileName) throws Exception{    
     StringBuffer content = new StringBuffer();    

     //构造 XSSFWorkbook 对象，strPath 传入文件路径        
  XSSFWorkbook xwb = new XSSFWorkbook(fileName);    

  //循环工作表Sheet    
  for(int numSheet = 0; numSheet < xwb.getNumberOfSheets(); numSheet++){    
   XSSFSheet xSheet = xwb.getSheetAt(numSheet);     
   if(xSheet == null){    
    continue;    
   }    

   //循环行Row    
   for(int rowNum = 0; rowNum <= xSheet.getLastRowNum(); rowNum++){    
    XSSFRow xRow = xSheet.getRow(rowNum);    
    if(xRow == null){    
     continue;    
    }    

    //循环列Cell    
    for(int cellNum = 0; cellNum <= xRow.getLastCellNum(); cellNum++){    
     XSSFCell xCell = xRow.getCell(cellNum);    
     if(xCell == null){    
      continue;    
     }    

     if(xCell.getCellType() == XSSFCell.CELL_TYPE_BOOLEAN){    
      content.append(xCell.getBooleanCellValue());    
     }else if(xCell.getCellType() == XSSFCell.CELL_TYPE_NUMERIC){    
      content.append(xCell.getNumericCellValue());    
     }else{    
      content.append(xCell.getStringCellValue());    
     }    
    }    
   }    
  }    

  return content.toString();    
    }    

}    

  第三、PowerPoint的文档



public static String readPowerPoint(String path) {
StringBuffer content = new StringBuffer("");
try {
SlideShow ss = new SlideShow(new HSLFSlideShow(new FileInputStream(
path)));// is
// 为文件的InputStream，建立SlideShow
Slide[] slides = ss.getSlides();// 获得每一张幻灯片
for (int i = 0; i < slides.length; i++) {
TextRun[] t = slides[i].getTextRuns();// 为了取得幻灯片的文字内容，建立TextRun
for (int j = 0; j < t.length; j++) {
content.append(t[j].getText());// 这里会将文字内容加到content中去
}
}
} catch (Exception ex) {
System.out.println(ex.toString());
}
return content.toString();
}

第四、PDF的文档

public static String readPdf(String path) throws Exception {
StringBuffer content = new StringBuffer("");
FileInputStream fis = new FileInputStream(path);
PDFParser p = new PDFParser(fis);
p.parse();
PDFTextStripper ts = new PDFTextStripper();
content.append(ts.getText(p.getPDDocument()));
fis.close();
return content.toString().trim();
}

第五、HTML的文档，要说明的是，HTML文档我们要获取其TITLE，BODY中的内容就要先获取源文件，然后再对源文件进行标签上的过滤，很麻烦

第六、TXT的文档，给TXT文本建立索引时要注意
本项目实现了组合查询的功能
//这一步如果不设置为GBK，TXT内容将全部乱码 BufferedReader reader=new

BufferedReader(new InputStreamReader(is,"GBK")); 具体代码如下 


public static String readTxt(String path) throws IOException {
StringBuffer sb = new StringBuffer("");
InputStream is = new FileInputStream(path);
// 必须设置成GBK，否则将出现乱码
BufferedReader reader = new BufferedReader(new InputStreamReader(is,
"GBK"));
try {
String line = "";
while ((line = reader.readLine()) != null) {
sb.append(line + "\r");
}
} catch (FileNotFoundException e) {
e.printStackTrace();
}
return sb.toString().trim();
}



第七、RTF文档，rtf的转换则在javax中就有
public static String readRtf(String path) {
String result = null;
File file = new File(path);
try {
DefaultStyledDocument styledDoc = new DefaultStyledDocument();
InputStream is = new FileInputStream(file);
new RTFEditorKit().read(is, styledDoc, 0);
result = new String(styledDoc.getText(0, styledDoc.getLength())
.getBytes("iso8859-1"), "gbk");
// 提取文本，读取中文需要使用gbk编码，否则会出现乱码
} catch (IOException e) {
e.printStackTrace();
} catch (BadLocationException e) {
e.printStackTrace();
}
return result;
}

public static String readHtml(String urlString) {
StringBuffer content = new StringBuffer("");
File file = new File(urlString);
FileInputStream fis = null;
try {
fis = new FileInputStream(file);
BufferedReader reader = new BufferedReader(new InputStreamReader(
fis, "utf-8"));
String line = null;
while ((line = reader.readLine()) != null) {
content.append(line + "\n");
}
reader.close();
} catch (Exception e) {
e.printStackTrace();
}
String contentString = content.toString();
String htmlStr = contentString; // 含html标签的字符串
String textStr = "";
java.util.regex.Pattern p_script;
java.util.regex.Matcher m_script;
java.util.regex.Pattern p_style;
java.util.regex.Matcher m_style;
java.util.regex.Pattern p_html;
java.util.regex.Matcher m_html;
try {
String regEx_script = "<[\\s]*?script[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?script[\\
String regEx_style = "<[\\s]*?style[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?style[\\s]*
String regEx_html = "<[^>]+>"; // 定义HTML标签的正则表达式
p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);
m_script = p_script.matcher(htmlStr);
htmlStr = m_script.replaceAll(""); // 过滤script标签
p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);
m_style = p_style.matcher(htmlStr);
htmlStr = m_style.replaceAll(""); // 过滤style标签
p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
m_html = p_html.matcher(htmlStr);
htmlStr = m_html.replaceAll(""); // 过滤html标签
textStr = htmlStr;
} catch (Exception e) {
System.err.println("Html2Text: " + e.getMessage());
}
return textStr;// 返回文本字符串
}