怎样在Android中解析doc、docx、xls、xlsx格式文件？
16lz
2021-01-25
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
01 | publicstaticString readDOC(String path) { |
02 | // 创建输入流读取doc文件 |
03 | FileInputStream in; |
04 | String text =null; |
05 | // Environment.getExternalStorageDirectory().getAbsolutePath()+ "/aa.doc") |
06 | try{ |
07 | in =newFileInputStream(newFile(path)); |
08 | inta= in.available(); |
09 | WordExtractor extractor =null; |
10 | // 创建WordExtractor |
11 | extractor =newWordExtractor(); |
12 | // 对doc文件进行提取 |
13 | text = extractor.extractText(in); |
14 | System.out.println("解析得到的东西"+text); |
15 | }catch(FileNotFoundException e) { |
16 | e.printStackTrace(); |
17 | }catch(Exception e) { |
18 | e.printStackTrace(); |
19 | } |
20 | if(text ==null) { |
21 | text ="解析文件出现问题"; |
22 | } |
23 | returntext; |
24 | } |
01 | publicstaticString readXLS(String path) { |
02 | String str =""; |
03 | try{ |
04 | Workbook workbook =null; |
05 | workbook = Workbook.getWorkbook(newFile(path)); |
06 | Sheet sheet = workbook.getSheet(0); |
07 | Cell cell =null; |
08 | intcolumnCount = sheet.getColumns(); |
09 | introwCount = sheet.getRows(); |
10 | for(inti =0; i < rowCount; i++) { |
11 | for(intj =0; j < columnCount; j++) { |
12 | cell = sheet.getCell(j, i); |
13 | String temp2 =""; |
14 | if(cell.getType() == CellType.NUMBER) { |
15 | temp2 = ((NumberCell) cell).getValue() +""; |
16 | }elseif(cell.getType() == CellType.DATE) { |
17 | temp2 =""+ ((DateCell) cell).getDate(); |
18 | }else{ |
19 | temp2 =""+ cell.getContents(); |
20 | } |
21 | str = str +" "+ temp2; |
22 | } |
23 | str +="\n"; |
24 | } |
25 | workbook.close(); |
26 | }catch(Exception e) { |
27 | } |
28 | if(str ==null) { |
29 | str ="解析文件出现问题"; |
30 | } |
31 | returnstr; |
32 | } |
解析docx
publicstaticString readDOCX(String path) { |
02 | String river =""; |
03 | try{ |
04 | ZipFile xlsxFile =newZipFile(newFile(path)); |
05 | ZipEntry sharedStringXML = xlsxFile.getEntry("word/document.xml"); |
06 | InputStream inputStream = xlsxFile.getInputStream(sharedStringXML); |
07 | XmlPullParser xmlParser = Xml.newPullParser(); |
08 | xmlParser.setInput(inputStream,"utf-8"); |
09 | intevtType = xmlParser.getEventType(); |
10 | while(evtType != XmlPullParser.END_DOCUMENT) { |
11 | switch(evtType) { |
12 | caseXmlPullParser.START_TAG: |
13 | String tag = xmlParser.getName(); |
14 | System.out.println(tag); |
15 | if(tag.equalsIgnoreCase("t")) { |
16 | river += xmlParser.nextText() +"\n"; |
17 | } |
18 | break; |
19 | caseXmlPullParser.END_TAG: |
20 | break; |
21 | default: |
22 | break; |
23 | } |
24 | evtType = xmlParser.next(); |
25 | } |
26 | }catch(ZipException e) { |
27 | e.printStackTrace(); |
28 | }catch(IOException e) { |
29 | e.printStackTrace(); |
30 | }catch(XmlPullParserException e) { |
31 | e.printStackTrace(); |
32 | } |
33 | if(river ==null) { |
34 | river ="解析文件出现问题"; |
35 | } |
36 | returnriver; |
37 | } |
01 | publicstaticString readXLSX(String path) { |
02 | String str =""; |
03 | String v =null; |
04 | booleanflat =false; |
05 | List<String> ls =newArrayList<String>(); |
06 | try{ |
07 | ZipFile xlsxFile =newZipFile(newFile(path)); |
08 | ZipEntry sharedStringXML = xlsxFile |
09 | .getEntry("xl/sharedStrings.xml"); |
10 | InputStream inputStream = xlsxFile.getInputStream(sharedStringXML); |
11 | XmlPullParser xmlParser = Xml.newPullParser(); |
12 | xmlParser.setInput(inputStream,"utf-8"); |
13 | intevtType = xmlParser.getEventType(); |
14 | while(evtType != XmlPullParser.END_DOCUMENT) { |
15 | switch(evtType) { |
16 | caseXmlPullParser.START_TAG: |
17 | String tag = xmlParser.getName(); |
18 | if(tag.equalsIgnoreCase("t")) { |
19 | ls.add(xmlParser.nextText()); |
20 | } |
21 | break; |
22 | caseXmlPullParser.END_TAG: |
23 | break; |
24 | default: |
25 | break; |
26 | } |
27 | evtType = xmlParser.next(); |
28 | } |
29 | ZipEntry sheetXML = xlsxFile.getEntry("xl/worksheets/sheet1.xml"); |
30 | InputStream inputStreamsheet = xlsxFile.getInputStream(sheetXML); |
31 | XmlPullParser xmlParsersheet = Xml.newPullParser(); |
32 | xmlParsersheet.setInput(inputStreamsheet,"utf-8"); |
33 | intevtTypesheet = xmlParsersheet.getEventType(); |
34 | while(evtTypesheet != XmlPullParser.END_DOCUMENT) { |
35 | switch(evtTypesheet) { |
36 | caseXmlPullParser.START_TAG: |
37 | String tag = xmlParsersheet.getName(); |
38 | if(tag.equalsIgnoreCase("row")) { |
39 | }elseif(tag.equalsIgnoreCase("c")) { |
40 | String t = xmlParsersheet.getAttributeValue(null,"t"); |
41 | if(t !=null) { |
42 | flat =true; |
43 | System.out.println(flat +"有"); |
44 | }else{ |
45 | System.out.println(flat +"没有"); |
46 | flat =false; |
47 | } |
48 | }elseif(tag.equalsIgnoreCase("v")) { |
49 | v = xmlParsersheet.nextText(); |
50 | if(v !=null) { |
51 | if(flat) { |
52 | str += ls.get(Integer.parseInt(v)) +" "; |
53 | }else{ |
54 | str += v +" "; |
55 | } |
56 | } |
57 | } |
58 | break; |
59 | caseXmlPullParser.END_TAG: |
60 | if(xmlParsersheet.getName().equalsIgnoreCase("row") |
61 | && v !=null) { |
62 | str +="\n"; |
63 | } |
64 | break; |
65 | } |
66 | evtTypesheet = xmlParsersheet.next(); |
67 | } |
68 | System.out.println(str); |
69 | }catch(ZipException e) { |
70 | e.printStackTrace(); |
71 | }catch(IOException e) { |
72 | e.printStackTrace(); |
73 | }catch(XmlPullParserException e) { |
74 | e.printStackTrace(); |
75 | } |
76 | if(str ==null) { |
77 | str ="解析文件出现问题"; |
78 | } |
79 | returnstr; |
80 | } |
更多相关文章
- 一款常用的 Squid 日志分析工具
- GitHub 标星 8K+！一款开源替代 ls 的工具你值得拥有！
- RHEL 6 下 DHCP+TFTP+FTP+PXE+Kickstart 实现无人值守安装
- Linux 环境下实战 Rsync 备份工具及配置 rsync+inotify 实时同步
- android io写入读取 txt 数据 封装
- 单元测试;Android应用程序架构;电话拔号器;短信发送器
- Eclipse中开发Android应用出现的error及solution汇总
- Android(安卓)webview 一些奇怪的问题
- [转]Windows下用Git下载android源码