";// 段落开始,标记开始? 111 | String tagEnd = "
";// 段落结束 112 | String tableBegin = "".getBytes());
154 | isRight = true;
155 | }
156 | }
157 | if (tag.equalsIgnoreCase("color")) { // 判断颜色
158 | String color = xmlParser.getAttributeValue(0);
159 | output.write(("").getBytes());
160 | isColor = true;
161 | }
162 | if (tag.equalsIgnoreCase("sz")) { // 判断大小
163 | if (isR) {
164 | int size = decideSize(Integer.valueOf(xmlParser.getAttributeValue(0)));
165 | output.write(("").getBytes());
166 | isSize = true;
167 | }
168 | }
169 | // 下面是表格处理
170 | if (tag.equalsIgnoreCase("tbl")) { // 检测到tbl 表格开始
171 | output.write(tableBegin.getBytes());
172 | isTable = true;
173 | }
174 | if (tag.equalsIgnoreCase("tr")) { // 行
175 | output.write(rowBegin.getBytes());
176 | }
177 | if (tag.equalsIgnoreCase("tc")) { // 列
178 | output.write(colBegin.getBytes());
179 | }
180 | if (tag.equalsIgnoreCase("pic")) { // 检测到标签 pic 图片
181 | String entryNameJPG = "word/media/image" + pictureIndex + ".jpeg";
182 | String entryNamePNG = "word/media/image" + pictureIndex + ".png";
183 | String entryNameGIF = "word/media/image" + pictureIndex + ".gif";
184 | String entryNameWMF = "word/media/image" + pictureIndex + ".wmf";
185 | String suffix = ".jpg";
186 | ZipEntry sharePicture = file.getEntry(entryNameJPG);
187 | // 一下为读取docx的图片 转化为流数组
188 | if (sharePicture == null) {
189 | suffix = ".png";
190 | sharePicture = file.getEntry(entryNamePNG);
191 | }
192 | if (sharePicture == null) {
193 | suffix = ".gif";
194 | sharePicture = file.getEntry(entryNameGIF);
195 | }
196 | if (sharePicture == null) {
197 | suffix = ".wmf";
198 | sharePicture = file.getEntry(entryNameWMF);
199 | }
200 | if (sharePicture != null) {
201 | InputStream pictIS = file.getInputStream(sharePicture);
202 | String picPath = imagePath + "/" + pictureIndex + suffix;
203 | FileOutputStream pOut = new FileOutputStream(new File(picPath));
204 | byte[] buffer = new byte[512];
205 | int len;
206 | while ((len = pictIS.read(buffer)) != -1) {
207 | pOut.write(buffer, 0, len);
208 | }
209 | pictIS.close();
210 | pOut.close();
211 | String imageString = "![](\"")
";
212 | try {
213 | output.write(imageString.getBytes());
214 | } catch (Throwable t) {
215 | t.printStackTrace();
216 | }
217 | }
218 | // 转换一张后 索引+1
219 | pictureIndex++;
220 | }
221 |
222 | if (tag.equalsIgnoreCase("b")) { // 检测到加粗标签
223 | isBold = true;
224 | }
225 | if (tag.equalsIgnoreCase("p")) {// 检测到 p 标签
226 | if (!isTable) { // 如果在表格中 就无视
227 | output.write(tagBegin.getBytes());
228 | }
229 | }
230 | if (tag.equalsIgnoreCase("i")) { // 斜体
231 | isItalic = true;
232 | }
233 | // 检测到值 标签
234 | if (tag.equalsIgnoreCase("t")) {
235 | if (isBold) { // 加粗
236 | output.write("".getBytes());
237 | }
238 | if (isUnderline) { // 检测到下划线标签,输入
239 | output.write("".getBytes());
240 | }
241 | if (isItalic) { // 检测到斜体标签,输入
242 | output.write("".getBytes());
243 | }
244 | output.write(xmlParser.nextText().getBytes()); // 写入数值
245 | if (isItalic) { // 检测到斜体标签,在输入值之后,输入,并且斜体状态=false
246 | output.write("".getBytes());
247 | isItalic = false;
248 | }
249 | if (isUnderline) {// 检测到下划线标签,在输入值之后,输入,并且下划线状态=false
250 | output.write("".getBytes());
251 | isUnderline = false;
252 | }
253 | if (isBold) { // 加粗
254 | output.write("".getBytes());
255 | isBold = false;
256 | }
257 | if (isSize) { // 检测到大小设置,输入结束标签
258 | output.write("".getBytes());
259 | isSize = false;
260 | }
261 | if (isColor) { // 检测到颜色设置存在,输入结束标签
262 | output.write("".getBytes());
263 | isColor = false;
264 | }
265 | if (isCenter) { // 检测到居中,输入结束标签
266 | output.write("".getBytes());
267 | isCenter = false;
268 | }
269 | if (isRight) { // 居右不能使用
".getBytes());
271 | isRight = false;
272 | }
273 | }
274 | } break;
275 | // 结束标签
276 | case XmlPullParser.END_TAG: {
277 | String tag2 = xmlParser.getName();
278 | if (tag2.equalsIgnoreCase("tbl")) { // 检测到表格结束,更改表格状态
279 | output.write(tableEnd.getBytes());
280 | isTable = false;
281 | }
282 | if (tag2.equalsIgnoreCase("tr")) { // 行结束
283 | output.write(rowEnd.getBytes());
284 | }
285 | if (tag2.equalsIgnoreCase("tc")) { // 列结束
286 | output.write(colEnd.getBytes());
287 | }
288 | if (tag2.equalsIgnoreCase("p")) { // p结束,如果在表格中就无视
289 | if (!isTable) {
290 | output.write(tagEnd.getBytes());
291 | }
292 | }
293 | if (tag2.equalsIgnoreCase("r")) {
294 | isR = false;
295 | }
296 | } break;
297 | }
298 | evtType = xmlParser.next();
299 | }
300 | output.write(end.getBytes());
301 | output.close();
302 | }
303 |
304 | private void xlsToHtml() throws Throwable {
305 | FileOutputStream output = new FileOutputStream(new File(htmlPath));
306 | StringBuffer htmlHeaderSB = new StringBuffer();
307 | htmlHeaderSB.append("");
309 | htmlHeaderSB.append(""
310 | + "");
311 | output.write(htmlHeaderSB.toString().getBytes());
312 | HSSFSheet sheet;
313 | HSSFWorkbook workbook = new HSSFWorkbook(new FileInputStream(filePath)); // 获整个Excel
314 | for (int sheetIndex = 0; sheetIndex < workbook.getNumberOfSheets(); sheetIndex++) {
315 | if (workbook.getSheetAt(sheetIndex) != null) {
316 | sheet = workbook.getSheetAt(sheetIndex);// 获得不为空的这个sheet
317 | if (sheet != null) {
318 | int firstRowNum = sheet.getFirstRowNum(); // 第一行
319 | int lastRowNum = sheet.getLastRowNum(); // 最后一行
320 | // 构造Table
321 | output.write(("| " + getCellValue(cell) + " | ").getBytes()); 372 | } 373 | } 374 | } 375 | output.write("
";
391 | String end = "
";
392 | output.write(head.getBytes());
393 | InputStreamReader isr = new InputStreamReader(new FileInputStream(filePath), getCharset(filePath));
394 | BufferedReader br = new BufferedReader(isr);
395 | String line;
396 | while ((line = br.readLine()) != null) {
397 | output.write(line.getBytes());
398 | output.write("".getBytes("UTF-8")); 399 | } 400 | br.close(); 401 | isr.close(); 402 | output.write(end.getBytes()); 403 | output.close(); 404 | } 405 | 406 | private String getCharset(String fileName) throws IOException { 407 | BufferedInputStream bin = new BufferedInputStream(new FileInputStream(fileName)); 408 | int p = (bin.read() << 8) + bin.read(); 409 | String code = "GBK"; 410 | switch (p) { 411 | case 0xefbb: { 412 | code = "UTF-8"; 413 | } break; 414 | case 0xfffe: { 415 | code = "Unicode"; 416 | } break; 417 | case 0xfeff: { 418 | code = "UTF-16BE"; 419 | } break; 420 | } 421 | return code; 422 | } 423 | 424 | private void xlsxToHtml() throws Throwable { 425 | FileOutputStream output = new FileOutputStream(new File(htmlPath)); 426 | String head = "" 427 | + "";// 定义头文件,我在这里加了utf-8,不然会出现乱码 428 | String tableBegin = "