利用POI读取word、Excel文件的最佳实践教程

 private static String readDoc(String filePath, InputStream is) {
  String text= "";
  try {
   if (filePath.endsWith("doc")) {
    WordExtractor ex = new WordExtractor(is);
    text = ex.getText();
    ex.close();
    is.close();
   } else if(filePath.endsWith("docx")) {
    XWPFDocument doc = new XWPFDocument(is);
    XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
    text = extractor.getText();
    extractor.close();
    is.close();
   }
  } catch (Exception e) {
   logger.error(filePath, e);
  } finally {
   if (is != null) {
    is.close();
   }
  }
  return text;
 }

org.apache.poi.poifs.filesystem.OfficeXmlFileException: The supplied data appears to be in the Office 2007+ XML. You are calling the part of POI that deals with OLE2 Office Documents.

boolean isZip = new ZipInputStream( fileStream ).getNextEntry() != null;

public enum FileMagic {
 /** OLE2 / BIFF8+ stream used for Office 97 and higher documents */
 OLE2(HeaderBlockConstants._signature),
 /** OOXML / ZIP stream */
 OOXML(OOXML_FILE_HEADER),
 /** XML file */
 XML(RAW_XML_FILE_HEADER),
 /** BIFF2 raw stream - for Excel 2 */
 BIFF2(new byte[]{
   0x09, 0x00, // sid=0x0009
   0x04, 0x00, // size=0x0004
   0x00, 0x00, // unused
   0x70, 0x00 // 0x70 = multiple values
 }),
 /** BIFF3 raw stream - for Excel 3 */
 BIFF3(new byte[]{
   0x09, 0x02, // sid=0x0209
   0x06, 0x00, // size=0x0006
   0x00, 0x00, // unused
   0x70, 0x00 // 0x70 = multiple values
 }),
 /** BIFF4 raw stream - for Excel 4 */
 BIFF4(new byte[]{
   0x09, 0x04, // sid=0x0409
   0x06, 0x00, // size=0x0006
   0x00, 0x00, // unused
   0x70, 0x00 // 0x70 = multiple values
 },new byte[]{
   0x09, 0x04, // sid=0x0409
   0x06, 0x00, // size=0x0006
   0x00, 0x00, // unused
   0x00, 0x01
 }),
 /** Old MS Write raw stream */
 MSWRITE(
   new byte[]{0x31, (byte)0xbe, 0x00, 0x00 },
   new byte[]{0x32, (byte)0xbe, 0x00, 0x00 }),
 /** RTF document */
 RTF("{\\rtf"),
 /** PDF document */
 PDF("%PDF"),
 // keep UNKNOWN always as last enum!
 /** UNKNOWN magic */
 UNKNOWN(new byte[0]);

 final byte[][] magic;

 FileMagic(long magic) {
  this.magic = new byte[1][8];
  LittleEndian.putLong(this.magic[0], 0, magic);
 }

 FileMagic(byte[]... magic) {
  this.magic = magic;
 }

 FileMagic(String magic) {
  this(magic.getBytes(LocaleUtil.CHARSET_1252));
 }

 public static FileMagic valueOf(byte[] magic) {
  for (FileMagic fm : values()) {
   int i=0;
   boolean found = true;
   for (byte[] ma : fm.magic) {
    for (byte m : ma) {
     byte d = magic[i++];
     if (!(d == m || (m == 0x70 && (d == 0x10 || d == 0x20 || d == 0x40)))) {
      found = false;
      break;
     }
    }
    if (found) {
     return fm;
    }
   }
  }
  return UNKNOWN;
 }

 /**
  * Get the file magic of the supplied InputStream (which MUST
  * support mark and reset).

  *
  * If unsure if your InputStream does support mark / reset,
  * use {@link #prepareToCheckMagic(InputStream)} to wrap it and make
  * sure to always use that, and not the original!

  *
  * Even if this method returns {@link FileMagic#UNKNOWN} it could potentially mean,
  * that the ZIP stream has leading junk bytes
  *
  * @param inp An InputStream which supports either mark/reset
  */
 public static FileMagic valueOf(InputStream inp) throws IOException {
  if (!inp.markSupported()) {
   throw new IOException("getFileMagic() only operates on streams which support mark(int)");
  }

  // Grab the first 8 bytes
  byte[] data = IOUtils.peekFirst8Bytes(inp);

  return FileMagic.valueOf(data);
 }


 /**
  * Checks if an {@link InputStream} can be reseted (i.e. used for checking the header magic) and wraps it if not
  *
  * @param stream stream to be checked for wrapping
  * @return a mark enabled stream
  */
 public static InputStream prepareToCheckMagic(InputStream stream) {
  if (stream.markSupported()) {
   return stream;
  }
  // we used to process the data via a PushbackInputStream, but user code could provide a too small one
  // so we use a BufferedInputStream instead now
  return new BufferedInputStream(stream);
 }
}

 private static String readDoc (String filePath, InputStream is) {
  String text= "";
  is = FileMagic.prepareToCheckMagic(is);
  try {
   if (FileMagic.valueOf(is) == FileMagic.OLE2) {
    WordExtractor ex = new WordExtractor(is);
    text = ex.getText();
    ex.close();
   } else if(FileMagic.valueOf(is) == FileMagic.OOXML) {
    XWPFDocument doc = new XWPFDocument(is);
    XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
    text = extractor.getText();
    extractor.close();
   }
  } catch (Exception e) {
   logger.error("for file " + filePath, e);
  } finally {
   if (is != null) {
    is.close();
   }
  }
  return text;
 }

 @SuppressWarnings("deprecation" )
 private static String readExcel(String filePath, InputStream inp) throws Exception {
  Workbook wb;
  StringBuilder sb = new StringBuilder();
  try {
   if (filePath.endsWith(".xls")) {
    wb = new HSSFWorkbook(inp);
   } else {
    wb = StreamingReader.builder()
      .rowCacheSize(1000) // number of rows to keep in memory (defaults to 10)
      .bufferSize(4096)  // buffer size to use when reading InputStream to file (defaults to 1024)
      .open(inp);   // InputStream or File for XLSX file (required)
   }
   sb = readSheet(wb, sb, filePath.endsWith(".xls"));
   wb.close();
  } catch (OLE2NotOfficeXmlFileException e) {
   logger.error(filePath, e);
  } finally {
   if (inp != null) {
    inp.close();
   }
  }
  return sb.toString();
 }

 private static String readExcelByFile(String filepath, File file) {
  Workbook wb;
  StringBuilder sb = new StringBuilder();
  try {
   if (filepath.endsWith(".xls")) {
    wb = WorkbookFactory.create(file);
   } else {
    wb = StreamingReader.builder()
      .rowCacheSize(1000) // number of rows to keep in memory (defaults to 10)
      .bufferSize(4096)  // buffer size to use when reading InputStream to file (defaults to 1024)
      .open(file);   // InputStream or File for XLSX file (required)
   }
   sb = readSheet(wb, sb, filepath.endsWith(".xls"));
   wb.close();
  } catch (Exception e) {
   logger.error(filepath, e);
  }
  return sb.toString();
 }

 private static StringBuilder readSheet(Workbook wb, StringBuilder sb, boolean isXls) throws Exception {
  for (Sheet sheet: wb) {
   for (Row r: sheet) {
    for (Cell cell: r) {
     if (cell.getCellType() == Cell.CELL_TYPE_STRING) {
      sb.append(cell.getStringCellValue());
      sb.append(" ");
     } else if (cell.getCellType() == Cell.CELL_TYPE_NUMERIC) {
      if (isXls) {
       DataFormatter formatter = new DataFormatter();
       sb.append(formatter.formatCellValue(cell));
      } else {
       sb.append(cell.getStringCellValue());
      }
      sb.append(" ");
     }
    }
   }
  }
  return sb;
 }