一、解析Word文档表格数据
1.解析Word2007文档表格数据（docx格式）
1 public static String getWordContent(String filePath) throws Exception{
2 //定义解析文档图片存储路径
3 String storepicpath = filePath.substring(0, filePath.lastIndexOf("."));//获取路径最后以文件名命名的文件夹路径
4 storepicpath = storepicpath.replaceAll("\\s*", "").replaceAll("\\.", "@@").replaceAll("\\#", "@@@").replaceAll("\\%", "@@@@");//去掉路径中的空格
5 //开始解析文档
6 FileInputStream fis = new FileInputStream(filePath);
7 //解析上传引证商标明细文件
8 XWPFDocument xwpf = new XWPFDocument(fis);//得到word文档的信息
9 Iterator<XWPFTable> it = xwpf.getTablesIterator();//迭代得到word中的表格
10 String content = "";//定义文档表格内容
11 while(it.hasNext()){
12 XWPFTable table = it.next();//获取文档中的表格
13 List<XWPFTableRow> rows=table.getRows();//获取所有行数据
14 //读取每一行数据
15 for (int i = 0; i < rows.size(); i++) {
16 if(i==4 || i==12){
17 XWPFTableRow row = rows.get(i);
18 //读取每一列数据
19 List<XWPFTableCell> cells = row.getTableCells();
20 for (int j = 1; j < cells.size(); j++) {
21 XWPFTableCell cell=cells.get(j);
22 //输出当前的单元格的数据
23 if(j == 2){
24 //******************************开始解析表格中的商标图样图片信息************************//
25 String picPath = "";
26 List<XWPFParagraph> xwpfParagraphs = cell.getParagraphs();
27 if(xwpfParagraphs == null) return null;
28 for(XWPFParagraph xwpfParagraph:xwpfParagraphs){
29 List<XWPFRun> xwpfRunList = xwpfParagraph.getRuns();
30 if(xwpfRunList==null) return null;
31 for(XWPFRun xwpfRun:xwpfRunList){
32 List<XWPFPicture> xwpfPictureList = xwpfRun.getEmbeddedPictures();
33 if(xwpfParagraph==null) return null;
34 for(XWPFPicture xwpfPicture:xwpfPictureList){
35 xwpfPicture.getPictureData().getData();
36 xwpfPicture.getPictureData().getFileName();
37 storepicpath = storepicpath.replace("\\", "/");
38 storepicpath = storepicpath.replaceAll("C:/Users/v-guoxiao/Desktop/Reference-Marks2", "D:/TradeMark/Tomcat8/webapps/ROOT/trademarkimage/ReferencePicture");
39 File file = new File(storepicpath);
40 if(!file.exists()){
41 file.mkdirs();
42 }
43 picPath = storepicpath+"/"+ xwpfPicture.getPictureData().getFileName();//拼写到存放数据的值
44 byte2image( xwpfPicture.getPictureData().getData(),storepicpath+"/"+ xwpfPicture.getPictureData().getFileName());
45 }
46 }
47 }
48 content = content +"&@#"+ picPath;
49 }else{
50 content = content +"&@#"+ cell.getText();
51 }
52 }
53 }else {
54 XWPFTableRow row = rows.get(i);
55 //读取每一列数据
56 List<XWPFTableCell> cells = row.getTableCells();
57 for (int j = 1; j < cells.size(); j++) {
58 XWPFTableCell cell=cells.get(j);
59 //输出当前的单元格的数据
60 content = content +"&@#"+ cell.getText();
61 }
62 }
63 }
64 }
65 fis.close();
66 return content;
67 }
68
69 /**
70 * 解析 DOCX 文档中图片工具方法
71 * @param data
72 * @param path
73 */
74 public static void byte2image(byte[] data,String path){
75 if(data.length<3||path.equals("")) return;
76 FileImageOutputStream imageOutput = null;
77 try{
78 imageOutput = new FileImageOutputStream(new File(path));
79 imageOutput.write(data, 0, data.length);
80 } catch(Exception ex) {
81 System.out.println("Exception: " + ex);
82 ex.printStackTrace();
83 }finally {
84 try {
85 imageOutput.close();
86 } catch (IOException e) {
87 e.printStackTrace();
88 }
89 }
90 }
2.解析Word2003文档表格数据（doc格式）
1 public static List<Map<String, Object>> getBigFotfmContent(String filePath) throws Exception{
2 List<Map<String, Object>> list = new ArrayList<Map<String, Object>>();
3 FileInputStream fis = new FileInputStream(filePath);
4 String storepath = filePath.substring(0, filePath.lastIndexOf("."));//获取图片存储路径
5 storepath = storepath.replaceAll("\\s*", "").replaceAll("\\.", "@@").replaceAll("\\#", "@@@").replaceAll("\\%", "@@@@");
6 String content = "";//定义文档表格内容
7 POIFSFileSystem pfs = new POIFSFileSystem(fis);//得到word文档的信息
8 HWPFDocument hd = new HWPFDocument(pfs);
9 Range range = hd.getRange();
10 TableIterator it = new TableIterator(range);
11 int p = 1;
12 while(it.hasNext()){
13 Table table = it.next();//获取表格
14 //读取每一行数据
15 for (int i = 0; i < table.numRows(); i++) {
16 if(i == 0){
17 TableRow row = table.getRow(i);
18 //读取每一列数据
19 for (int j = 0; j < row.numCells(); j++) {
20 if(j == 1){
21 TableCell cell = row.getCell(j);
22 PicturesTable pt = hd.getPicturesTable();
23 CharacterRun cr = cell.getCharacterRun(0);
24 if(pt.hasPicture(cr)){
25 Picture picture = pt.extractPicture(cr, true);
26 byte[] picbyte = picture.getContent();
27 storepath = storepath.replace("\\", "/");
28 storepath = storepath.replaceAll("C:/Users/v-guoxiao/Desktop/Reference-Marks2", "D:/TradeMark/Tomcat8/webapps/ROOT/trademarkimage/ReferencePicture");
29 File file = new File(storepath);
30 if(!file.exists()){
31 file.mkdirs();
32 }
33 String picpath = storepath + "/image" + p + ".jpg";
34 FileOutputStream fos = new FileOutputStream(picpath);
35 fos.write(picbyte);
36 fos.close();
37 content = content + "&@#" + picpath;
38 }
39 }else{
40 TableCell cell=row.getCell(j);
41 //输出当前的单元格的数据
42 for(int k =0; k < cell.numParagraphs(); k++){
43 Paragraph paragraph = cell.getParagraph(k);
44 String tradmark = paragraph.text().replaceAll("", "");
45 if(!tradmark.equals("") && !tradmark.equals(null)){
46 content = content + "&@#" + tradmark.replaceAll(":", "");
47 }
48 }
49 }
50 }
51 }else {
52 TableRow row = table.getRow(i);//获取行数据
53 //读取每一列数据
54 for (int j = 0; j < row.numCells(); j++) {
55 TableCell cell=row.getCell(j);//获取单元格数据
56 //输出当前的单元格的数据
57 for(int k =0; k < cell.numParagraphs(); k++){
58 Paragraph paragraph = cell.getParagraph(k);
59 String cellcontent = paragraph.text().replaceAll("", "");
60 if(!cellcontent.equals("") && !cellcontent.equals(null)){
61 content = content + "&@#" + cellcontent.replaceAll(":", "");
62 }
63 }
64 }
65 }
66 }
67 p++;
68 }
69 //分割文档内容，存储到map集合中
70 String[] tables = content.split("Trademark");
71 for(int i = 1; i < tables.length; i++){
72 String data = "Trademark"+tables[i];
73 data = data.replaceAll("\\s*", "").replaceAll("Trademark&@#&@#&@#", "Trademark&@#").replaceAll("Goods/Services&@#&@#", "Goods/Services&@#").replaceAll("Address&@#&@#", "Address&@#");
74 String[] cellData = data.split("&@#",-1);
75 Map<String, Object> map =new HashMap<String, Object>();
76 if(i < tables.length-1){
77 if (cellData.length > 17) {
78 for(int m = 0; m < cellData.length-1; m++){
79 if(m < 10 || m > 15){
80 if(m%2 == 0 && m < cellData.length-1){
81 map.put(cellData[m], cellData[m+1]);
82 }
83 }else if(m == 10 || m == 13){
84 map.put(cellData[m], cellData[m+1] + cellData[m+2]);
85 }
86 }
87 }else{
88 for(int m = 0; m < cellData.length-1; m++){
89 if(m%2 == 0 && m < cellData.length-1){
90 map.put(cellData[m], cellData[m+1]);
91 }
92 }
93 }
94 }else{
95 if(cellData.length > 17){
96 for(int m = 0; m < cellData.length; m++){
97 if(m < 10 || m > 15){
98 if(m%2 == 0 && m < cellData.length-1){
99 map.put(cellData[m], cellData[m+1]);
100 }
101 }else if(m == 10 || m == 13){
102 map.put(cellData[m], cellData[m+1] + cellData[m+2]);
103 }
104 }
105 }else{
106 for(int m = 0; m < cellData.length; m++){
107 if(m%2 == 0 && m < cellData.length-1){
108 map.put(cellData[m], cellData[m+1]);
109 }
110 }
111 }
112 }
113 list.add(map);
114 }
115 return list;
116 }
3.解析Excel2003表格数据（xls格式）
1 public static String getDataFromExcelXls(String filePath) throws Exception{
2 //获取路径中的Excel表的文件名称
3 File file = new File(filePath.trim());
4 String fileName = file.getName();//文件名称
5 fileName = fileName.substring(0, fileName.lastIndexOf(".")).replaceAll("\\s*", "");
6 String exContent = "";//定义接收循环表格的数据
7 FileInputStream fis = null;//定义输出流
8 Workbook workbook = null;//定义工作簿
9 Sheet sheet = null;//定义sheet
10 //根据扩展名判断解析Excel格式
11 fis = new FileInputStream(filePath);
12 workbook = new HSSFWorkbook(fis);//获取工作簿
13 Map<String, PictureData> maplist = null;
14 //开始遍历Excel表中多个sheet
15 for(int i = 0; i < workbook.getNumberOfSheets(); i++){//工作簿中多个sheet，循环遍历出获取每个sheet表中数据
16 sheet = workbook.getSheetAt(i);//获取sheet表
17 String sheetName = sheet.getSheetName().replaceAll("\\s*", "").replaceAll("\\.", "");//获取sheet名称
18 maplist = getXlsPicture((HSSFSheet)sheet);
19 //取存图片
20 try {
21 getExcelImage(maplist, fileName, sheetName);
22 } catch (Exception e) {
23 e.printStackTrace();
24 }
25
26 //开始解析表格数据
27 Date date;//定义所有日期
28 //获取数据的总行数
29 int totalRowNum = sheet.getLastRowNum();
30 //定义获取的数据属性名称
31 String filingNum = "";//申请/注册号
32 String type = "";//类型
33 String mark = "";//图样
34 String properter = "";//申请人
35 String filingDate = "";//申请日期
36 String startDate = "";//开始日期
37 String endDate = "";//结束日期
38 String status = "";//当前状态
39 String isCancel= "";//是否取消
40 String goodsDescriptionEN = "";//商品英文描述
41 for(int m = 6; m <= totalRowNum; m++){
42 Row row = sheet.getRow(m);//获取第 m 行的数据
43 //获取每列数据
44 Cell cell = row.getCell(0);
45 if(cell.getCellTypeEnum() != CellType.BLANK){//****************************************申请/注册号
46 cell.setCellType(CellType.STRING);
47 filingNum = cell.getStringCellValue();
48 exContent = exContent + "&@#filingNum&@#" + filingNum;
49 }
50 cell = row.getCell(1);
51 String picPath = "D:/TradeMark/Tomcat8/webapps/ROOT/trademarkimage/ReferencePicture/" + fileName + "/" + sheetName;//定义图片存储地址
52 if(cell.getCellTypeEnum() == CellType.BLANK){//****************************************图片地址
53 cell.setCellType(CellType.STRING);
54 mark = picPath + "/" + (m+1) + "_" + 2 + ".jpg";
55 exContent = exContent + "&@#mark&@#" + mark;
56 }
57 cell = row.getCell(2);
58 if(cell.getCellTypeEnum() != CellType.BLANK){//****************************************申请日期
59 if (cell.getCellTypeEnum() == CellType.STRING) {//判断单元格内容的类型
60 cell.setCellType(CellType.STRING);
61 filingDate = cell.getStringCellValue();
62 exContent = exContent + "&@#filingDate&@#" + filingDate;
63 }else{
64 cell.setCellType(CellType.NUMERIC);
65 date = cell.getDateCellValue();
66 SimpleDateFormat sdf = new SimpleDateFormat("yyyyMMdd");
67 filingDate = sdf.format(date);
68 exContent = exContent + "&@#filingDate&@#" + filingDate;
69 }
70 }else{
71 cell.setCellType(CellType.STRING);
72 filingDate = cell.getStringCellValue();
73 exContent = exContent + "&@#filingDate&@#" + filingDate;
74 }
75 cell = row.getCell(3);
76 if(cell.getCellTypeEnum() != CellType.BLANK){//****************************************注册日期
77 if (cell.getCellTypeEnum() == CellType.STRING) {
78 cell.setCellType(CellType.STRING);
79 startDate = cell.getStringCellValue();
80 exContent = exContent + "&@#startDate&@#" + startDate;
81 }else{
82 cell.setCellType(CellType.NUMERIC);
83 date = cell.getDateCellValue();
84 SimpleDateFormat sdf = new SimpleDateFormat("yyyyMMdd");
85 startDate = sdf.format(date);
86 exContent = exContent + "&@#startDate&@#" + startDate;
87 }
88 }else{
89 cell.setCellType(CellType.STRING);
90 startDate = cell.getStringCellValue();
91 exContent = exContent + "&@#startDate&@#" + startDate;
92 }
93 cell = row.getCell(4);
94 if(cell.getCellTypeEnum() != CellType.BLANK){//****************************************类型
95 cell.setCellType(CellType.STRING);
96 type = cell.getStringCellValue();
97 exContent = exContent + "&@#type&@#" + type;
98 }
99 cell = row.getCell(5);
100 if(cell.getCellTypeEnum() != CellType.BLANK){//****************************************商品英文描述
101 cell.setCellType(CellType.STRING);
102 goodsDescriptionEN = cell.getStringCellValue();
103 exContent = exContent + "&@#goodsDescriptionEN&@#" + goodsDescriptionEN;
104 }else{
105 exContent = exContent + "&@#goodsDescriptionEN&@#" + goodsDescriptionEN;
106 }
107 cell = row.getCell(6);
108 if(cell.getCellTypeEnum() != CellType.BLANK){//****************************************申请人
109 cell.setCellType(CellType.STRING);
110 properter = cell.getStringCellValue();
111 exContent = exContent + "&@#properter&@#" + properter;
112 }
113 cell = row.getCell(7);
114 if(cell.getCellTypeEnum() != CellType.BLANK){//****************************************注册到期日
115 if (cell.getCellTypeEnum() == CellType.STRING) {
116 cell.setCellType(CellType.STRING);
117 endDate = cell.getStringCellValue();
118 exContent = exContent + "&@#endDate&@#" + endDate;
119 }else{
120 cell.setCellType(CellType.NUMERIC);
121 date = cell.getDateCellValue();
122 SimpleDateFormat sdf = new SimpleDateFormat("yyyyMMdd");
123 endDate = sdf.format(date);
124 exContent = exContent + "&@#endDate&@#" + endDate;
125 }
126 }else{
127 cell.setCellType(CellType.STRING);
128 endDate = cell.getStringCellValue();
129 exContent = exContent + "&@#endDate&@#" + endDate;
130 }
131 cell = row.getCell(8);
132 if(cell.getCellTypeEnum() != CellType.BLANK){//****************************************当前状态
133 cell.setCellType(CellType.STRING);
134 status = cell.getStringCellValue();
135 exContent = exContent + "&@#status&@#" + status;
136 }
137 cell = row.getCell(9);
138 if(cell.getCellTypeEnum() != CellType.BLANK){//****************************************是否取消
139 cell.setCellType(CellType.STRING);
140 isCancel = cell.getStringCellValue();
141 exContent = exContent + "&@#isCancel&@#" + isCancel;
142 }
143 }
144 }
145 return exContent;
146 }
4.解析Excel2007表格数据（xlsx格式）
1 public static String getDataFromExcelXlsx(String filePath) throws Exception{
2 //获取路径中的Excel表的文件名称
3 File file = new File(filePath.trim());
4 String fileName = file.getName();//文件名称
5 fileName = fileName.substring(0, fileName.lastIndexOf(".")).replaceAll("\\s*", "");
6 String exContent = "";//定义接收循环表格的数据
7 FileInputStream fis = null;//定义输出流
8 Workbook workbook = null;//定义工作簿
9 Sheet sheet = null;//定义sheet
10 //根据扩展名判断解析Excel格式
11 fis = new FileInputStream(filePath);
12 workbook = new XSSFWorkbook(fis);//获取工作簿
13 Map<String, PictureData> maplist = null;
14 //开始遍历Excel表中多个sheet
15 for(int i = 0; i < workbook.getNumberOfSheets(); i++){//工作簿中多个sheet，循环遍历出获取每个sheet表中数据
16 sheet = workbook.getSheetAt(i);//获取sheet表
17 String sheetName = sheet.getSheetName().replaceAll("\\s*", "");//获取sheet名称
18 maplist = getXlsxPicture((XSSFSheet)sheet);
19 //取存图片
20 try {
21 getExcelImage(maplist, fileName, sheetName);
22 } catch (Exception e) {
23 e.printStackTrace();
24 }
25 //开始解析表格数据
26 Date date;//定义所有日期
27 //获取数据的总行数
28 int totalRowNum = sheet.getLastRowNum();
29 //定义获取的数据属性名称
30 String filingNum = "";//申请/注册号
31 String type = "";//类型
32 String mark = "";//图样
33 String properter = "";//申请人
34 String filingDate = "";//申请日期
35 String startDate = "";//开始日期
36 String endDate = "";//结束日期
37 String filingAddress = "";//申请地址
38 String goodsDescriptionCN = "";//商品中文描述
39 String goodsDescriptionEN = "";//商品英文描述
40 for(int m = 1; m <= totalRowNum; m++){
41 Row row = sheet.getRow(m);//获取第 m 行的数据
42 //获取每列数据
43 Cell cell = row.getCell(1);
44 if(cell.getCellTypeEnum() != CellType.BLANK){//****************************************申请/注册号
45 cell.setCellType(CellType.STRING);
46 filingNum = cell.getStringCellValue();
47 exContent = exContent +"&@#filingNum&@#"+filingNum;
48 }
49 cell = row.getCell(2);
50 if(cell.getCellTypeEnum() != CellType.BLANK){//****************************************类型
51 cell.setCellType(CellType.STRING);
52 type = cell.getStringCellValue();
53 exContent = exContent + "&@#type&@#" + type;
54 }
55 cell = row.getCell(3);//此处图片得到的单元格内容为空值
56 String picPath = "D:/TradeMark/Tomcat8/webapps/ROOT/trademarkimage/ReferencePicture/" + fileName + "/" + sheetName;//定义图片存储地址
57 if(cell.getCellTypeEnum() == CellType.BLANK){//****************************************存储图片地址
58 cell.setCellType(CellType.STRING);
59 mark = picPath + "/" + (m+1) + "_" + 4 + ".jpg";
60 exContent = exContent + "&@#mark&@#" + mark;
61 }
62 cell = row.getCell(4);
63 String[] filingPerson;
64 String CNproperter = "";
65 String ENproperter = "";
66 String regp = "[^\u4e00-\u9fa5]";//定义中文正则表达式
67 String sp = "";
68 if(cell.getCellTypeEnum() != CellType.BLANK){//****************************************申请人
69 cell.setCellType(CellType.STRING);
70 properter = cell.getStringCellValue();
71 sp = properter.replaceAll(regp, "");
72 if(!sp.equals("") && !sp.equals(null)){
73 if(properter.contains(";")){
74 filingPerson = properter.split(";");
75 CNproperter = filingPerson[0].toString();
76 ENproperter = filingPerson[1].toUpperCase();
77 exContent = exContent + "&@#CNproperter&@#" + CNproperter;
78 exContent = exContent + "&@#ENproperter&@#" + ENproperter;
79 }else if(properter.contains("；")){
80 filingPerson = properter.split("；");
81 CNproperter = filingPerson[0].toString();
82 ENproperter = filingPerson[1].toUpperCase();
83 exContent = exContent + "&@#CNproperter&@#" + CNproperter;
84 exContent = exContent + "&@#ENproperter&@#" + ENproperter;
85 }else{
86 CNproperter = properter;
87 exContent = exContent + "&@#CNproperter&@#" + CNproperter;
88 exContent = exContent + "&@#ENproperter&@#" + ENproperter;
89 }
90 }else{
91 ENproperter = properter;
92 exContent = exContent + "&@#CNproperter&@#" + CNproperter;
93 exContent = exContent + "&@#ENproperter&@#" + ENproperter;
94 }
95 }
96 cell = row.getCell(5);
97 if(cell.getCellTypeEnum() != CellType.BLANK){//****************************************申请日期
98 if (cell.getCellTypeEnum() == CellType.STRING) {//判断单元格内容的数据类型
99 cell.setCellType(CellType.STRING);
100 filingDate = cell.getStringCellValue();
101 exContent = exContent + "&@#filingDate&@#" + filingDate;
102 }else{
103 cell.setCellType(CellType.NUMERIC);
104 date = cell.getDateCellValue();
105 SimpleDateFormat sdf = new SimpleDateFormat("yyyyMMdd");
106 filingDate = sdf.format(date);
107 exContent = exContent + "&@#filingDate&@#" + filingDate;
108 }
109 }else{//申请日期单元格为空
110 cell.setCellType(CellType.STRING);
111 filingDate = cell.getStringCellValue();
112 exContent = exContent + "&@#filingDate&@#" + filingDate;
113 }
114 cell = row.getCell(6);
115 if(cell.getCellTypeEnum() != CellType.BLANK){//****************************************注册日期
116 if (cell.getCellTypeEnum() == CellType.STRING) {
117 cell.setCellType(CellType.STRING);
118 startDate = cell.getStringCellValue();
119 exContent = exContent + "&@#startDate&@#" + startDate;
120 }else{
121 cell.setCellType(CellType.NUMERIC);
122 date = cell.getDateCellValue();
123 SimpleDateFormat sdf = new SimpleDateFormat("yyyyMMdd");
124 startDate = sdf.format(date);
125 exContent = exContent + "&@#startDate&@#" + startDate;
126 }
127 }else{//注册日期单元格为空
128 cell.setCellType(CellType.STRING);
129 startDate = cell.getStringCellValue();
130 exContent = exContent + "&@#startDate&@#" + startDate;
131 }
132 cell = row.getCell(7);
133 if(cell.getCellTypeEnum() != CellType.BLANK){//****************************************注册到期日
134 if (cell.getCellTypeEnum() == CellType.STRING) {
135 cell.setCellType(CellType.STRING);
136 endDate = cell.getStringCellValue();
137 exContent = exContent + "&@#endDate&@#" + endDate;
138 }else{
139 cell.setCellType(CellType.NUMERIC);
140 date = cell.getDateCellValue();
141 SimpleDateFormat sdf = new SimpleDateFormat("yyyyMMdd");
142 endDate = sdf.format(date);
143 exContent = exContent + "&@#endDate&@#" + endDate;
144 }
145 }else{//注册到期日单元格为空
146 cell.setCellType(CellType.STRING);
147 endDate = cell.getStringCellValue();
148 exContent = exContent + "&@#endDate&@#" + endDate;
149 }
150 cell = row.getCell(8);
151 String[] address;//定义注册地址分割
152 String CNAddress = "";//定义中文地址
153 String ENAddress = "";//定义英文地址
154 String reg = "[^\u4e00-\u9fa5]";//定义中文正则表达式
155 String cc = "";
156 if(cell.getCellTypeEnum() != CellType.BLANK){//****************************************注册地址
157 cell.setCellType(CellType.STRING);
158 filingAddress = cell.getStringCellValue();
159 cc = filingAddress.replaceAll(reg, "");
160 if(!cc.equals(null) && !cc.equals("")){
161 if(filingAddress.contains(";")){
162 address = filingAddress.split(";");
163 CNAddress = address[0].toString();//截取中文地址
164 ENAddress = address[1].toUpperCase();//截取英文地址并转换成大写
165 exContent = exContent + "&@#CNAddress&@#" + CNAddress;
166 exContent = exContent + "&@#ENAddress&@#" + ENAddress;
167 }else{
168 address = filingAddress.split("；");
169 CNAddress = address[0].toString();//截取中文地址
170 ENAddress = address[1].toUpperCase();//截取英文地址并转换成大写
171 exContent = exContent + "&@#CNAddress&@#" + CNAddress;
172 exContent = exContent + "&@#ENAddress&@#" + ENAddress;
173 }
174 }else{
175 ENAddress = filingAddress;
176 exContent = exContent + "&@#CNAddress&@#" + CNAddress;
177 exContent = exContent + "&@#ENAddress&@#" + ENAddress;
178 }
179 }else{//注册地址为空
180 exContent = exContent + "&@#CNAddress&@#" + CNAddress;
181 exContent = exContent + "&@#ENAddress&@#" + ENAddress;
182 }
183 cell = row.getCell(9);
184 if(cell.getCellTypeEnum() != CellType.BLANK){//****************************************商品中文描述
185 cell.setCellType(CellType.STRING);
186 goodsDescriptionCN = cell.getStringCellValue();
187 exContent = exContent + "&@#goodsDescriptionCN&@#" + goodsDescriptionCN;
188 }else{//商品中文描述为空
189 exContent = exContent + "&@#goodsDescriptionCN&@#" + goodsDescriptionCN;
190 }
191 cell = row.getCell(10);
192 if(cell.getCellTypeEnum() != CellType.BLANK){//****************************************商品英文描述
193 cell.setCellType(CellType.STRING);
194 goodsDescriptionEN = cell.getStringCellValue();
195 exContent = exContent + "&@#goodsDescriptionEN&@#" + goodsDescriptionEN;
196 }else{//商品英文描述为空
197 exContent = exContent + "&@#goodsDescriptionEN&@#" + goodsDescriptionEN;
198 }
199 }
200 }
201 return exContent;
202 }
上述解析文档方法工具方法：
1 /**
2 * 一键解析所有文档工具方法,获取多层文件夹下全部的最终文件
3 * @param filePath
4 * @param listName
5 */
6 public static void getAllFiles(String filePath, ArrayList<String> listName){
7 File file = new File(filePath);
8 File[] files = file.listFiles();
9 String[] names = file.list();
10 if (names != null) {
11 String[] completNames = new String[names.length];
12 for(int i = 0; i < names.length; i++){
13 completNames[i] = filePath + names[i];
14 }
15 listName.addAll(Arrays.asList(completNames));
16 }
17 for(File f : files){
18 if (f.isDirectory()) {
19 getAllFiles(f.getAbsolutePath()+"\\", listName);
20 }
21 }
22 }
23
24
25
26 /**
27 * 拷贝文件，文件夹及子文件夹
28 * @param data
29 * @param dest
30 */
31 public static void copyFolderAndFiles(String oldPath, String newPath){
32 try {
33 File file = new File(newPath);
34 if(!file.exists()){
35 file.mkdirs();
36 }
37 File oFile = new File(oldPath);
38 String[] files = oFile.list();
39 File temp = null;
40 for(int i = 0; i < files.length; i++){
41 if(oldPath.endsWith(File.separator)){
42 temp = new File(oldPath+files[i]);
43 }else{
44 temp = new File(oldPath+File.separator+files[i]);
45 }
46 if(temp.isFile()){//判断是否为文件
47 FileInputStream fis = new FileInputStream(temp);
48 FileOutputStream fos = new FileOutputStream(newPath + "/" + (temp.getName()).toString());
49 byte[] bs = new byte[1024*5];
50 int len;
51 while((len=fis.read(bs)) != -1){
52 fos.write(bs, 0, len);
53 }
54 fos.flush();
55 fos.close();
56 fis.close();
57 }
58 if(temp.isDirectory()){
59 copyFolderAndFiles(oldPath+"/"+files[i], newPath+"/"+files[i]);
60 }
61 }
62 } catch (FileNotFoundException e) {
63 // TODO Auto-generated catch block
64 e.printStackTrace();
65 } catch (IOException e) {
66 // TODO Auto-generated catch block
67 e.printStackTrace();
68 }
69 }
Excel表格工具方法（图片）
1 /**
2 * 解析获取2003版xls文件的图片
3 * @param sheet
4 * @return
5 */
6 public static Map<String, PictureData> getXlsPicture(HSSFSheet sheet){
7 Map<String, PictureData> map = new HashMap<String, PictureData>();
8 List<HSSFShape> list = sheet.getDrawingPatriarch().getChildren();
9 for(HSSFShape shape : list){
10 if(shape instanceof HSSFPicture){
11 HSSFPicture picture = (HSSFPicture) shape;
12 HSSFClientAnchor anchor = (HSSFClientAnchor) picture.getAnchor();
13 PictureData data = picture.getPictureData();
14 String key = (anchor.getRow1()+1) + "_" + (anchor.getCol1()+1);
15 map.put(key, data);
16 }
17 }
18 return map;
19 }
20
21
22 public static Map<String, PictureData> getXlsPicture2(HSSFSheet sheet, HSSFWorkbook workbook){
23 Map<String, PictureData> map = new HashMap<String, PictureData>();
24 List<HSSFPictureData> list = workbook.getAllPictures();
25 if(!list.isEmpty()){
26 for(HSSFShape shape : sheet.getDrawingPatriarch().getChildren()){
27 HSSFClientAnchor anchor = (HSSFClientAnchor) shape.getAnchor();
28 if(shape instanceof HSSFPicture){
29 HSSFPicture picture = (HSSFPicture) shape;
30 int pictureIndex = picture.getPictureIndex() - 1;
31 HSSFPictureData pictureData = list.get(pictureIndex);
32 String picIndex = String.valueOf(anchor.getRow1()+1) + "_" + String.valueOf(anchor.getCol1()+1);
33 map.put(picIndex, pictureData);
34 }
35 }
36 return map;
37 }else{
38 return map;
39 }
40 }
41
42
43
44 /**
45 * 解析获取2007版xlsx文件的图片
46 * @param sheet
47 * @return
48 */
49 public static Map<String, PictureData> getXlsxPicture(XSSFSheet sheet){
50 Map<String, PictureData> map = new HashMap<String, PictureData>();
51 List<POIXMLDocumentPart> list = sheet.getRelations();
52 for(POIXMLDocumentPart part : list){
53 if(part instanceof XSSFDrawing){
54 XSSFDrawing drawing = (XSSFDrawing) part;
55 List<XSSFShape> shapes = drawing.getShapes();
56 for(XSSFShape shape : shapes){
57 XSSFPicture picture = (XSSFPicture) shape;
58 XSSFClientAnchor anchor = picture.getPreferredSize();
59 CTMarker marker = anchor.getFrom();
60 String key = (marker.getRow()+1) + "_" + (marker.getCol()+1);
61 map.put(key, picture.getPictureData());
62 }
63 }
64 }
65 return map;
66 }
67
68 /**
69 * 解析输出保存获取的图片
70 * @throws Exception
71 */
72 public static void getExcelImage(Map<String, PictureData> sheetlist, String fileName, String sheetName) throws Exception{
73 Object[] key = sheetlist.keySet().toArray();
74 String filepath = "";
75 for(int i = 0; i < sheetlist.size(); i++){
76 PictureData data = sheetlist.get(key[i]);
77 String picName = key[i].toString();
78 byte[] bs = data.getData();
79 String path = "D:/TradeMark/Tomcat8/webapps/ROOT/trademarkimage/ReferencePicture/" + fileName + "/" + sheetName;
80 filepath = path + "/" + picName + ".jpg";
81 File file = new File(path);
82 if(!file.exists()){
83 file.mkdirs();
84 }
85 //保存输出图片
86 FileOutputStream fos = new FileOutputStream(filepath);
87 fos.write(bs);
88 fos.close();
89 }
90 }
