怎样在Android中解析doc、docx、xls、xlsx格式文件

导读：有的时候我们在开发android中需要解析一些我们比较常用的格式，比如doc、docx、xls、xlsx，那么我们要是正常的话就解析不了。这时我们就要用tm-extractors-0.4.jar。

 可以直接复制实验，
       解析doc，要tm-extractors-0.4.jar这个包
       解析xls，要jxl.jar这个包

解析doc

public static String readDOC(String path) {
// 创建输入流读取doc文件
                FileInputStream in;
                String text = null;
//                Environment.getExternalStorageDirectory().getAbsolutePath()+ "/aa.doc")
                try {
                        in = new FileInputStream(new File(path));
int a= in.available();
                        WordExtractor extractor = null;
// 创建WordExtractor
                        extractor = new WordExtractor();
// 对doc文件进行提取
                        text = extractor.extractText(in);
                        System.out.println("解析得到的东西"+text);
                } catch (FileNotFoundException e) {
                        e.printStackTrace();
                } catch (Exception e) {
                        e.printStackTrace();
                }
if (text == null) {
                        text = "解析文件出现问题";
                }
return text;
        }

解析xls

public static String readXLS(String path) {
                String str = "";
try {
                        Workbook workbook = null;
                        workbook = Workbook.getWorkbook(new File(path));
                        Sheet sheet = workbook.getSheet(0);
                        Cell cell = null;
int columnCount = sheet.getColumns();
int rowCount = sheet.getRows();
for (int i = 0; i < rowCount; i++) {
for (int j = 0; j < columnCount; j++) {
                                        cell = sheet.getCell(j, i);
                                        String temp2 = "";
if (cell.getType() == CellType.NUMBER) {
                                                temp2 = ((NumberCell) cell).getValue() + "";
                                        } else if (cell.getType() == CellType.DATE) {
                                                temp2 = "" + ((DateCell) cell).getDate();
                                        } else {
                                                temp2 = "" + cell.getContents();
                                        }
                                        str = str + "  " + temp2;
                                }
                                str += "\n";
                        }
                        workbook.close();
                } catch (Exception e) {
                }
if (str == null) {
                        str = "解析文件出现问题";
                }
return str;
        }

 

  解析docx

public static String readDOCX(String path) {
                String river = "";
try {
                        ZipFile xlsxFile = new ZipFile(new File(path));
                        ZipEntry sharedStringXML = xlsxFile.getEntry("word/document.xml");
                        InputStream inputStream = xlsxFile.getInputStream(sharedStringXML);
                        XmlPullParser xmlParser = Xml.newPullParser();
                        xmlParser.setInput(inputStream, "utf-8");
int evtType = xmlParser.getEventType();
while (evtType != XmlPullParser.END_DOCUMENT) {
switch (evtType) {
case XmlPullParser.START_TAG:
                                        String tag = xmlParser.getName();
                                        System.out.println(tag);
if (tag.equalsIgnoreCase("t")) {
                                                river += xmlParser.nextText() + "\n";
                                        }
break;
case XmlPullParser.END_TAG:
break;
default:
break;
                                }
                                evtType = xmlParser.next();
                        }
                } catch (ZipException e) {
                        e.printStackTrace();
                } catch (IOException e) {
                        e.printStackTrace();
                } catch (XmlPullParserException e) {
                        e.printStackTrace();
                }
if (river == null) {
                        river = "解析文件出现问题";
                }
return river;
        }

解析xlsx

public static String readXLSX(String path) {
                String str = "";
                String v = null;
boolean flat = false;
                List<String> ls = new ArrayList<String>();
try {
                        ZipFile xlsxFile = new ZipFile(new File(path));
                        ZipEntry sharedStringXML = xlsxFile
                                        .getEntry("xl/sharedStrings.xml");
                        InputStream inputStream = xlsxFile.getInputStream(sharedStringXML);
                        XmlPullParser xmlParser = Xml.newPullParser();
                        xmlParser.setInput(inputStream, "utf-8");
int evtType = xmlParser.getEventType();
while (evtType != XmlPullParser.END_DOCUMENT) {
switch (evtType) {
case XmlPullParser.START_TAG:
                                        String tag = xmlParser.getName();
if (tag.equalsIgnoreCase("t")) {
                                                ls.add(xmlParser.nextText());
                                        }
break;
case XmlPullParser.END_TAG:
break;
default:
break;
                                }
                                evtType = xmlParser.next();
                        }
                        ZipEntry sheetXML = xlsxFile.getEntry("xl/worksheets/sheet1.xml");
                        InputStream inputStreamsheet = xlsxFile.getInputStream(sheetXML);
                        XmlPullParser xmlParsersheet = Xml.newPullParser();
                        xmlParsersheet.setInput(inputStreamsheet, "utf-8");
int evtTypesheet = xmlParsersheet.getEventType();
while (evtTypesheet != XmlPullParser.END_DOCUMENT) {
switch (evtTypesheet) {
case XmlPullParser.START_TAG:
                                        String tag = xmlParsersheet.getName();
if (tag.equalsIgnoreCase("row")) {
                                        } else if (tag.equalsIgnoreCase("c")) {
                                                String t = xmlParsersheet.getAttributeValue(null, "t");
if (t != null) {
                                                        flat = true;
                                                        System.out.println(flat + "有");
                                                } else {
                                                        System.out.println(flat + "没有");
                                                        flat = false;
                                                }
                                        } else if (tag.equalsIgnoreCase("v")) {
                                                v = xmlParsersheet.nextText();
if (v != null) {
if (flat) {
                                                                str += ls.get(Integer.parseInt(v)) + "  ";
                                                        } else {
                                                                str += v + "  ";
                                                        }
                                                }
                                        }
break;
case XmlPullParser.END_TAG:
if (xmlParsersheet.getName().equalsIgnoreCase("row")
                                                        && v != null) {
                                                str += "\n";
                                        }
break;
                                }
                                evtTypesheet = xmlParsersheet.next();
                        }
                        System.out.println(str);
                } catch (ZipException e) {
                        e.printStackTrace();
                } catch (IOException e) {
                        e.printStackTrace();
                } catch (XmlPullParserException e) {
                        e.printStackTrace();
                }
if (str == null) {
                        str = "解析文件出现问题";
                }
return str;
        }

原文：http://www.eoeandroid.com/qa/2011/1227/504.html

转载于:https://www.cnblogs.com/shanzei/archive/2012/04/06/2419372.html