1 package com.xxx.xxx.xxx.excel;
2
3 import java.io.File;
4 import java.io.FileInputStream;
5 import java.io.FileOutputStream;
6 import java.io.IOException;
7 import java.io.InputStream;
8 import java.io.OutputStreamWriter;
9 import java.io.StringWriter;
10 import java.util.ArrayList;
11 import java.util.Iterator;
12 import java.util.List;
13
14 import org.dom4j.Attribute;
15 import org.dom4j.Document;
16 import org.dom4j.DocumentHelper;
17 import org.dom4j.Element;
18 import org.dom4j.io.OutputFormat;
19 import org.dom4j.io.SAXReader;
20 import org.dom4j.io.XMLWriter;
21
22 public class XMLHandler {
23
24 /**
25 * xml 编码格式
26 */
27 private static final String ENCODING = "UTF-8";
28
29 /**
30 * SAXReader
31 */
32 private SAXReader saxReader;
33
34 /**
35 * Document
36 */
37 private Document document;
38
39 /**
40 * 根节点
41 */
42 private Element root;
43
44 /**
45 * 记录取null的标签列表
46 */
47 private List<String> nullValues = new ArrayList<String>();
48
49
50
51
52 /**
53 * 构造函数
54 * 直接使用saxReader.read(File file); 出现 The encoding "GBK" is not supported
55 * @param inputXml xml文件
56 */
57 public XMLHandler(File inputXml) {
58 String xml = file2String(inputXml);
59 try {
60 if (inputXml != null) {
61 document = DocumentHelper.parseText(xml);
62 root = document.getRootElement();
63 }
64 } catch (Exception e) {
65 throw new RuntimeException("can't parse xml, please check the xml format", e);
66 }
67 }
68
69 /**
70 * 构造函数
71 * @param inputXml xml文件
72 * @param encoding xml 编码
73 */
74 public XMLHandler(File inputXml, String encoding) {
75 saxReader = new SAXReader();
76 try {
77 if (inputXml != null) {
78 saxReader.setEncoding(encoding);
79 document = saxReader.read(inputXml);
80 root = document.getRootElement();
81 }
82 } catch (Exception e) {
83 throw new RuntimeException("can't parse xml, please check the xml format", e);
84 }
85
86 }
87
88 /**
89 * 构造函数
90 * 直接使用saxReader.read(String str);会出现no protocol:的异常
91 * 使用DocumentHelper.parseText(String str);解决这一问题
92 * @param inputXml xml字符串
93 */
94 public XMLHandler(String inputXml) {
95 saxReader = new SAXReader();
96 try {
97 if (inputXml != null) {
98 document = DocumentHelper.parseText(inputXml);
99 root = document.getRootElement();
100 }
101 } catch (Exception e) {
102 throw new RuntimeException("can't parse xml, please check the xml format", e);
103 }
104 }
105
106 /**
107 * 将xml的document对象转换成xml字符串
108 * @return xml字符串
109 */
110 public String doc2Xml() {
111 StringWriter writer = new StringWriter();
112 try {
113 OutputFormat format = OutputFormat.createPrettyPrint();
114 format.setEncoding(ENCODING);
115 XMLWriter output = new XMLWriter(writer, format);
116 output.write(document);
117 output.close();
118 } catch (Exception e) {
119 e.printStackTrace();
120 }
121 return writer.toString();
122 }
123
124 /**
125 * 将xml的document对象转换成xml字符串
126 * @param encoding 字符串编码
127 * @return xml字符串
128 */
129 public String doc2Xml(String encoding) {
130 StringWriter writer = new StringWriter();
131 try {
132 OutputFormat format = OutputFormat.createPrettyPrint();
133 format.setEncoding(encoding);
134 XMLWriter output = new XMLWriter(writer, format);
135 output.write(document);
136 output.close();
137 } catch (Exception e) {
138 e.printStackTrace();
139 }
140 return writer.toString();
141 }
142
143 /**
144 * 获取root节点
145 * @return root节点
146 */
147 public Element getRootElement() {
148 return root;
149 }
150
151 /**
152 * 获取单个xpath路径的Text值
153 * "//article/date"
154 * @param xpath xpath路径
155 * @return Text值
156 */
157 // @SuppressWarnings("unchecked")
158 public String getElementText(String xpath) {
159 List<?> list = document.selectNodes(xpath);
160 Iterator<?> iter = list.iterator();
161 String value = null;
162 if (iter.hasNext()) {
163 Element element = (Element) iter.next();
164 value = element.getText().trim();
165 }
166
167 if (value == null) {
168 if (!nullValues.contains(xpath)) {
169 nullValues.add(xpath);
170 }
171 value = "";
172 }
173 return value;
174 }
175
176 /**
177 * 设置单个xpath路径的Text值
178 * "//article/date"
179 * "//article/date/book[n]" 取出第N个元素
180 * @param xpath xpath路径
181 * @param value Text值
182 */
183 // @SuppressWarnings("unchecked")
184 public void setElementText(String xpath, String value) {
185 List<?> list = document.selectNodes(xpath);
186 Iterator<?> iter = list.iterator();
187 if (iter.hasNext()) {
188 Element element = (Element) iter.next();
189 element.setText(value);
190 }
191 }
192
193 /**
194 * 获取单个xpath路径的Attribute值
195 * "//article/@date"
196 * @param xpath xpath路径
197 * @return Attribute值
198 */
199 // @SuppressWarnings("unchecked")
200 public String getElementAttribute(String xpath) {
201 List<?> list = document.selectNodes(xpath);
202 Iterator<?> iter = list.iterator();
203 String value = null;
204 if (iter.hasNext()) {
205 Attribute attribute = (Attribute) iter.next();
206 value = attribute.getValue().trim();
207 }
208 if (value == null) {
209 if (!nullValues.contains(xpath)) {
210 nullValues.add(xpath);
211 }
212 value = "";
213 }
214 return value;
215 }
216
217 /**
218 * 设置单个xpath路径的Attribute值
219 * "//article/@date"
220 * "//article/date/book[n]" 取出第N个元素
221 * @param xpath xpath路径
222 * @param value Attribute值
223 */
224 // @SuppressWarnings("unchecked")
225 public void setElementAttribute(String xpath, String value) {
226 List<?> list = document.selectNodes(xpath);
227 Iterator<?> iter = list.iterator();
228 if (iter.hasNext()) {
229 Attribute attribute = (Attribute) iter.next();
230 attribute.setValue(value);
231 }
232 }
233
234 /**
235 * 获取xpath下的Element列表
236 * @param xpath xpath路径
237 * @return Element列表
238 */
239 // @SuppressWarnings("unchecked")
240 public List<?> getListElement(String xpath) {
241 return document.selectNodes(xpath);
242 }
243
244 /**
245 * 获取元素Element的xpath下的Element列表
246 * @param element 当前元素Element
247 * @param xpath xpath路径
248 * @return Element列表
249 */
250 // @SuppressWarnings("unchecked")
251 public List<?> getListElement(Element element, String xpath) {
252 return element.selectNodes(xpath);
253 }
254
255 /**
256 * 获取xpath下的Element的Attribute值列表
257 * @param xpath xpath路径
258 * @return Attribute值列表
259 */
260 // @SuppressWarnings("unchecked")
261 public List<String> getListElementAttribute(String xpath) {
262 List<String> value = new ArrayList<String>();
263 List<?> list = document.selectNodes(xpath);
264 Iterator<?> iter = list.iterator();
265 while (iter.hasNext()) {
266 Attribute attribute = (Attribute) iter.next();
267 value.add(attribute.getValue().trim());
268 }
269 return value;
270 }
271
272 /**
273 * 获取元素Element的xpath下的Element的Attribute值列表
274 * @param element 当前元素Element
275 * @param xpath xpath路径
276 * @return Attribute值列表
277 */
278 // @SuppressWarnings("unchecked")
279 public List<String> getListElementAttribute(Element element, String xpath) {
280 List<String> value = new ArrayList<String>();
281 List<?> list = element.selectNodes(xpath);
282 Iterator<?> iter = list.iterator();
283 while (iter.hasNext()) {
284 Attribute attribute = (Attribute) iter.next();
285 value.add(attribute.getValue().trim());
286 }
287 return value;
288 }
289
290 /**
291 * 获取xpath下的Element的Text值列表
292 * @param xpath xpath路径
293 * @return Text值列表
294 */
295 // @SuppressWarnings("unchecked")
296 public List<String> getListElementText(String xpath) {
297 List<String> value = new ArrayList<String>();
298 List<?> list = document.selectNodes(xpath);
299 Iterator<?> iter = list.iterator();
300 while (iter.hasNext()) {
301 Element ele = (Element) iter.next();
302 value.add(ele.getText().trim());
303 }
304 return value;
305 }
306
307 /**
308 * 获取元素Element的xpath下的Element的Text值列表
309 * @param element 当前元素Element
310 * @param xpath xpath路径
311 * @return Text值列表
312 */
313 // @SuppressWarnings("unchecked")
314 public List<String> getListElementText(Element element, String xpath) {
315 List<String> value = new ArrayList<String>();
316 List<?> list = element.selectNodes(xpath);
317 Iterator<?> iter = list.iterator();
318 while (iter.hasNext()) {
319 Element ele = (Element) iter.next();
320 value.add(ele.getText().trim());
321 }
322 return value;
323 }
324
325 /**
326 * 获取xpath下的单个Element
327 * @param xpath xpath路径
328 * @return 单个Element
329 */
330 // @SuppressWarnings("unchecked")
331 public Element getElement(String xpath) {
332 List<?> list = document.selectNodes(xpath);
333 Iterator<?> iter = list.iterator();
334 if (iter.hasNext()) {
335 return (Element) iter.next();
336 }
337 return null;
338 }
339
340 /**
341 * 获取元素Element的xpath下的单个Element
342 * @param element 当前元素Element
343 * @param xpath xpath路径
344 * @return 单个Element
345 */
346 // @SuppressWarnings("unchecked")
347 public Element getElement(Element element, String xpath) {
348 List<?> list = element.selectNodes(xpath);
349 Iterator<?> iter = list.iterator();
350 if (iter.hasNext()) {
351 return (Element) iter.next();
352 }
353 return null;
354 }
355
356 /**
357 * 获取元素Element的xpath下的Element的Attribute值
358 * @param element 当前元素Element
359 * @param xpath xpath路径
360 * @return Attribute值
361 */
362 // @SuppressWarnings("unchecked")
363 public String getElementAttribute(Element element, String xpath) {
364 List<?> list = element.selectNodes(xpath);
365 Iterator<?> iter = list.iterator();
366 String value = null;
367 if (iter.hasNext()) {
368 Attribute attribute = (Attribute) iter.next();
369 value = attribute.getValue().trim();
370 }
371 if (value == null) {
372 String path = element.getUniquePath() + "/" + xpath;
373 if (!nullValues.contains(path)) {
374 nullValues.add(path);
375 }
376 value = "";
377 }
378 return value;
379 }
380
381 /**
382 * 设置元素Element的xpath下的Element的Attribute值
383 * @param element 当前元素Element
384 * @param xpath xpath路径
385 * @param value Attribute值
386 */
387 // @SuppressWarnings("unchecked")
388 public void setElementAttribute(Element element, String xpath, String value) {
389 List<?> list = element.selectNodes(xpath);
390 Iterator<?> iter = list.iterator();
391 if (iter.hasNext()) {
392 Attribute attribute = (Attribute) iter.next();
393 attribute.setValue(value);
394 }
395 }
396
397 /**
398 * 获取元素Element的xpath下的Element的Text值
399 * @param element 当前元素Element
400 * @param xpath xpath路径
401 * @return Text值
402 */
403 // @SuppressWarnings("unchecked")
404 public String getElementText(Element element, String xpath) {
405 if (element == null) {
406 return "";
407 }
408 List<?> list = element.selectNodes(xpath);
409 Iterator<?> iter = list.iterator();
410 String value = null;
411 if (iter.hasNext()) {
412 Element ele = (Element) iter.next();
413 value = ele.getText().trim();
414 }
415 if (value == null) {
416 String path = element.getUniquePath() + "/" + xpath;
417 if (!nullValues.contains(path)) {
418 nullValues.add(path);
419 }
420 value = "";
421 }
422 return value;
423 }
424
425
426 /**
427 * 设置元素Element的xpath下的Element的Text值
428 * @param element 当前元素Element
429 * @param xpath xpath路径
430 * @param value Text值
431 */
432 // @SuppressWarnings("unchecked")
433 public void setElementText(Element element, String xpath, String value) {
434 List<?> list = element.selectNodes(xpath);
435 Iterator<?> iter = list.iterator();
436 if (iter.hasNext()) {
437 Element ele = (Element) iter.next();
438 ele.setText(value);
439 }
440 }
441
442 /**
443 * 读取File的内容
444 * @param file 文件
445 * @return 内容
446 */
447 public static String file2String(File file) {
448 try {
449 InputStream fs = new FileInputStream(file);
450 byte[] b = new byte[(int) file.length()];
451 fs.read(b);
452 fs.close();
453 return new String(b);
454 } catch (Exception e) {
455 e.printStackTrace();
456 }
457 return null;
458 }
459
460 /**
461 * 读取xml字符串，获取Document对象
462 * @param xml xml字符串
463 * @return Document对象
464 */
465 public static Document xml2Doc(String xml) {
466 try {
467 return DocumentHelper.parseText(xml);
468 } catch (Exception e) {
469 e.printStackTrace();
470 }
471 return null;
472 }
473
474 /**
475 * @return List
476 */
477 public List<String> getNullValues() {
478 return nullValues;
479 }
480
481 public void writeXmlFile(String file,String code) {
482 try {
483 OutputFormat format = OutputFormat.createPrettyPrint();
484 //format.setEncoding("UTF-8"); // 指定XML编码
485 //XMLWriter writer = new XMLWriter(new FileWriter(file),format);
486 XMLWriter writer = new XMLWriter(new OutputStreamWriter(new FileOutputStream(file),"utf-8"),format);
487 writer.write(document);
488 writer.close();
489 } catch (IOException e) {
490
491 e.printStackTrace();
492 }
493 }
494 }
