Android開啟 解析 doc,docx,xls,xlsx,ppt等格式檔案的源碼

Android開啟 解析 doc,docx,xls,xlsx,ppt等格式檔案的源碼

可以直接複製實驗，
解析doc，要tm-extractors-0.4.jar這個包
解析xls，要jxl.jar這個包

 

import java.io.File;import java.io.FileInputStream;import java.io.FileNotFoundException;import java.io.FileOutputStream;import java.io.IOException;import java.io.InputStream;import java.net.MalformedURLException;import java.net.URL;import java.net.URLConnection;import java.util.ArrayList;import java.util.List;import java.util.zip.ZipEntry;import java.util.zip.ZipException;import java.util.zip.ZipFile;import jxl.Cell;import jxl.CellType;import jxl.DateCell;import jxl.NumberCell;import jxl.Sheet;import jxl.Workbook;import org.apache.http.util.EncodingUtils;import org.textmining.text.extraction.WordExtractor;import org.xmlpull.v1.XmlPullParser;import org.xmlpull.v1.XmlPullParserException;import android.os.Environment;import android.util.Xml;

public static String readDOC(String path) {                // 建立輸入資料流讀取doc檔案                FileInputStream in;                String text = null;//                Environment.getExternalStorageDirectory().getAbsolutePath()+ "/aa.doc")                try {                        in = new FileInputStream(new File(path));                        int a= in.available();                        WordExtractor extractor = null;                        // 建立WordExtractor                        extractor = new WordExtractor();                        // 對doc檔案進行提取                        text = extractor.extractText(in);                        System.out.println("解析得到的東西"+text);                } catch (FileNotFoundException e) {                        e.printStackTrace();                } catch (Exception e) {                        e.printStackTrace();                }                if (text == null) {                        text = "解析檔案出現問題";                }                return text;        }

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 = "解析檔案出現問題";                }                return str;        }

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 = "解析檔案出現問題";                }                return river;        }

public static String readXLSX(String path) {                String str = "";                String v = null;                boolean flat = false;                List ls = new ArrayList();                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 + "沒有");                                                        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 = "解析檔案出現問題";                }                return str;        }

public static String readPPTX(String path) {                List ls = new ArrayList();                String river = "";                ZipFile xlsxFile = null;                try {                        xlsxFile = new ZipFile(new File(path));// pptx按照讀取zip格式讀取                } catch (ZipException e1) {                        e1.printStackTrace();                } catch (IOException e1) {                        e1.printStackTrace();                }                try {                        ZipEntry sharedStringXML = xlsxFile.getEntry("[Content_Types].xml");// 找到裡面存放內容的檔案                        InputStream inputStream = xlsxFile.getInputStream(sharedStringXML);// 將得到檔案流                        XmlPullParser xmlParser = Xml.newPullParser();// 執行個體化pull                        xmlParser.setInput(inputStream, "utf-8");// 將流放進pull中                        int evtType = xmlParser.getEventType();// 得到標籤類型的狀態                        while (evtType != XmlPullParser.END_DOCUMENT) {// 迴圈讀取流                                switch (evtType) {                                case XmlPullParser.START_TAG: // 判斷標籤開始讀取                                        String tag = xmlParser.getName();// 得到標籤                                        if (tag.equalsIgnoreCase("Override")) {                                                String s = xmlParser                                                                .getAttributeValue(null, "PartName");                                                if (s.lastIndexOf("/ppt/slides/slide") == 0) {                                                        ls.add(s);                                                }                                        }                                        break;                                case XmlPullParser.END_TAG:// 標籤讀取結束                                        break;                                default:                                        break;                                }                                evtType = xmlParser.next();// 讀取下一個標籤                        }                } catch (ZipException e) {                        e.printStackTrace();                } catch (IOException e) {                        e.printStackTrace();                } catch (XmlPullParserException e) {                        e.printStackTrace();                }                for (int i = 1; i < (ls.size() + 1); i++) {// 假設有6張投影片                        river += "第" + i + "張················" + "\n";                        try {                                ZipEntry sharedStringXML = xlsxFile.getEntry("ppt/slides/slide"                                                + i + ".xml");// 找到裡面存放內容的檔案                                InputStream inputStream = xlsxFile                                                .getInputStream(sharedStringXML);// 將得到檔案流                                XmlPullParser xmlParser = Xml.newPullParser();// 執行個體化pull                                xmlParser.setInput(inputStream, "utf-8");// 將流放進pull中                                int evtType = xmlParser.getEventType();// 得到標籤類型的狀態                                while (evtType != XmlPullParser.END_DOCUMENT) {// 迴圈讀取流                                        switch (evtType) {                                        case XmlPullParser.START_TAG: // 判斷標籤開始讀取                                                String tag = xmlParser.getName();// 得到標籤                                                if (tag.equalsIgnoreCase("t")) {                                                        river += xmlParser.nextText() + "\n";                                                }                                                break;                                        case XmlPullParser.END_TAG:// 標籤讀取結束                                                break;                                        default:                                                break;                                        }                                        evtType = xmlParser.next();// 讀取下一個標籤                                }                        } catch (ZipException e) {                                e.printStackTrace();                        } catch (IOException e) {                                e.printStackTrace();                        } catch (XmlPullParserException e) {                                e.printStackTrace();                        }                }                if (river == null) {                        river = "解析檔案出現問題";                }                return river;        }