完美解决docx4j变量替换的问题
作者:GreenHand2333 时间:2021-08-19 21:00:25
docx4j变量替换的问题
最近工作上需要自己完成word文档变量替换的问题
把里面的变量给替换成数据库里的值,但是由于在word文档渲染成xml的时候,会通过某些原因把字段放在不同层次的xml标签
上面是docx4j文档说的原因,大概是字体格式不同(我的问题是用了粗体 ${ 和 正常中文是不同格式的),拼写语法问题,编辑顺序。
在StackOverflow 找了很久解决方案,Variableprepare.prepare方法确实测试后能解决部分替换问题,但还是不能满足我的需求。
阅读源码后重新清扫了一下字符串。
测试代码
public static void main(String[] args) throws Exception {
File file = new File("C:\\Users\\scoli\\Desktop\\t.docx");
WordprocessingMLPackage doc = WordprocessingMLPackage.load(new FileInputStream(file));
Docx4jUtils.cleanDocumentPart(doc.getMainDocumentPart());
Map map = new HashMap();
map.put("订单编号", "1");
OutputStream outputStream = new FileOutputStream(new File("C:\\Users\\scoli\\Desktop\\test1.docx"));
MainDocumentPart mainDocumentPart = doc.getMainDocumentPart();
if (!map.isEmpty()) {
// 替换文本内容
mainDocumentPart.variableReplace(map);
}
// 输出word文件
doc.save(outputStream);
outputStream.flush();
}
docx4j版本
<!--docx4j支持 start-->
<dependency>
<groupId>org.docx4j</groupId>
<artifactId>docx4j</artifactId>
<version>3.3.6</version>
<exclusions>
<exclusion>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.docx4j</groupId>
<artifactId>docx4j-export-fo</artifactId>
<version>3.3.6</version>
</dependency>
<!--docx4j支持 end-->
下面是工具类
package zwy.saas.common.util;
import org.docx4j.XmlUtils;
import org.docx4j.jaxb.Context;
import org.docx4j.openpackaging.packages.WordprocessingMLPackage;
import org.docx4j.openpackaging.parts.WordprocessingML.MainDocumentPart;
import org.docx4j.wml.Document;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import javax.servlet.http.HttpServletResponse;
import javax.xml.bind.JAXBContext;
import javax.xml.bind.JAXBException;
import java.io.InputStream;
import java.io.OutputStream;
import java.net.URLEncoder;
import java.util.Map;
import java.util.regex.Pattern;
/**
* 关于文件操作的工具类
*
* @author kaizen
* @date 2018-10-23 17:21:36
*/
public final class Docx4jUtils {
private static final Logger logger = LoggerFactory.getLogger(Docx4jUtils.class);
/**
* 替换变量并下载word文档
*
* @param inputStream
* @param map
* @param response
* @param fileName
*/
public static void downloadDocUseDoc4j(InputStream inputStream, Map<String, String> map,
HttpServletResponse response, String fileName) {
try {
// 设置响应头
fileName = URLEncoder.encode(fileName, "UTF-8");
response.setContentType("application/octet-stream;charset=UTF-8");
response.setCharacterEncoding("utf-8");
response.setHeader("Content-Disposition", "attachment; filename=" + fileName + ".docx");
response.setHeader("Access-Control-Expose-Headers", "Content-Disposition");
OutputStream outs = response.getOutputStream();
Docx4jUtils.replaceDocUseDoc4j(inputStream,map,outs);
} catch (Exception e) {
logger.error(e.getMessage(), e);
}
}
/**
* 替换变量并输出word文档
* @param inputStream
* @param map
* @param outputStream
*/
public static void replaceDocUseDoc4j(InputStream inputStream, Map<String, String> map,
OutputStream outputStream) {
try {
WordprocessingMLPackage doc = WordprocessingMLPackage.load(inputStream);
MainDocumentPart mainDocumentPart = doc.getMainDocumentPart();
if (null != map && !map.isEmpty()) {
// 将${}里的内容结构层次替换为一层
Docx4jUtils .cleanDocumentPart(mainDocumentPart);
// 替换文本内容
mainDocumentPart.variableReplace(map);
}
// 输出word文件
doc.save(outputStream);
outputStream.flush();
} catch (Exception e) {
logger.error(e.getMessage(), e);
}
}
/**
* cleanDocumentPart
*
* @param documentPart
*/
public static boolean cleanDocumentPart(MainDocumentPart documentPart) throws Exception {
if (documentPart == null) {
return false;
}
Document document = documentPart.getContents();
String wmlTemplate =
XmlUtils.marshaltoString(document, true, false, Context.jc);
document = (Document) XmlUtils.unwrap(DocxVariableClearUtils.doCleanDocumentPart(wmlTemplate, Context.jc));
documentPart.setContents(document);
return true;
}
/**
* 清扫 docx4j 模板变量字符,通常以${variable}形式
* <p>
* XXX: 主要在上传模板时处理一下, 后续
*
* @author liliang
* @since 2018-11-07
*/
private static class DocxVariableClearUtils {
/**
* 去任意XML标签
*/
private static final Pattern XML_PATTERN = Pattern.compile("<[^>]*>");
private DocxVariableClearUtils() {
}
/**
* start符号
*/
private static final char PREFIX = '$';
/**
* 中包含
*/
private static final char LEFT_BRACE = '{';
/**
* 结尾
*/
private static final char RIGHT_BRACE = '}';
/**
* 未开始
*/
private static final int NONE_START = -1;
/**
* 未开始
*/
private static final int NONE_START_INDEX = -1;
/**
* 开始
*/
private static final int PREFIX_STATUS = 1;
/**
* 左括号
*/
private static final int LEFT_BRACE_STATUS = 2;
/**
* 右括号
*/
private static final int RIGHT_BRACE_STATUS = 3;
/**
* doCleanDocumentPart
*
* @param wmlTemplate
* @param jc
* @return
* @throws JAXBException
*/
private static Object doCleanDocumentPart(String wmlTemplate, JAXBContext jc) throws JAXBException {
// 进入变量块位置
int curStatus = NONE_START;
// 开始位置
int keyStartIndex = NONE_START_INDEX;
// 当前位置
int curIndex = 0;
char[] textCharacters = wmlTemplate.toCharArray();
StringBuilder documentBuilder = new StringBuilder(textCharacters.length);
documentBuilder.append(textCharacters);
// 新文档
StringBuilder newDocumentBuilder = new StringBuilder(textCharacters.length);
// 最后一次写位置
int lastWriteIndex = 0;
for (char c : textCharacters) {
switch (c) {
case PREFIX:
// TODO 不管其何状态直接修改指针,这也意味着变量名称里面不能有PREFIX
keyStartIndex = curIndex;
curStatus = PREFIX_STATUS;
break;
case LEFT_BRACE:
if (curStatus == PREFIX_STATUS) {
curStatus = LEFT_BRACE_STATUS;
}
break;
case RIGHT_BRACE:
if (curStatus == LEFT_BRACE_STATUS) {
// 接上之前的字符
newDocumentBuilder.append(documentBuilder.substring(lastWriteIndex, keyStartIndex));
// 结束位置
int keyEndIndex = curIndex + 1;
// 替换
String rawKey = documentBuilder.substring(keyStartIndex, keyEndIndex);
// 干掉多余标签
String mappingKey = XML_PATTERN.matcher(rawKey).replaceAll("");
if (!mappingKey.equals(rawKey)) {
char[] rawKeyChars = rawKey.toCharArray();
// 保留原格式
StringBuilder rawStringBuilder = new StringBuilder(rawKey.length());
// 去掉变量引用字符
for (char rawChar : rawKeyChars) {
if (rawChar == PREFIX || rawChar == LEFT_BRACE || rawChar == RIGHT_BRACE) {
continue;
}
rawStringBuilder.append(rawChar);
}
// FIXME 要求变量连在一起
String variable = mappingKey.substring(2, mappingKey.length() - 1);
int variableStart = rawStringBuilder.indexOf(variable);
if (variableStart > 0) {
rawStringBuilder = rawStringBuilder.replace(variableStart, variableStart + variable.length(), mappingKey);
}
newDocumentBuilder.append(rawStringBuilder.toString());
} else {
newDocumentBuilder.append(mappingKey);
}
lastWriteIndex = keyEndIndex;
curStatus = NONE_START;
keyStartIndex = NONE_START_INDEX;
}
default:
break;
}
curIndex++;
}
// 余部
if (lastWriteIndex < documentBuilder.length()) {
newDocumentBuilder.append(documentBuilder.substring(lastWriteIndex));
}
return XmlUtils.unmarshalString(newDocumentBuilder.toString(), jc);
}
}
}
来源:https://blog.csdn.net/qq_35598240/article/details/84439929
标签:docx4j,变量,替换
0
投稿
猜你喜欢
Java倒计时三种实现方式代码实例
2021-09-22 00:20:59
Java输出链表倒数第k个节点
2023-03-22 01:22:34
java跟踪执行的sql语句示例分享
2022-07-30 20:13:18
mybatis-plus3.0.1枚举返回为null解决办法
2023-11-07 16:59:50
WCF和Remoting之间的消息传输
2023-04-15 01:01:20
Java单例模式下的MongoDB数据库操作工具类
2023-11-20 12:55:01
Android中SeekBar和RatingBar用法实例分析
2023-07-28 00:13:59
Java获取时间年、月、日的方法
2022-02-10 16:58:36
详解IntelliJ IDEA 自带的 HTTP Client 接口调用插件吊打 Postman
2023-08-06 07:56:08
使用JPA自定义VO类型转换(EntityUtils工具类)
2023-08-26 14:56:17
通过实例了解Java 8创建Stream流的5种方法
2023-04-13 22:41:02
Monaco Editor实现sql和java代码提示实现示例
2023-01-31 16:59:48
分析java中全面的单例模式多种实现方式
2021-12-28 05:40:29
SpringBoot执行定时任务@Scheduled的方法
2022-08-13 03:43:31
Java详解实现多线程的四种方式总结
2023-04-04 19:43:34
java + dom4j.jar提取xml文档内容
2023-11-29 03:55:10
Java Stream流零基础教程
2023-08-15 19:33:20
java 文件上传到读取文件内容的实例
2023-11-09 22:00:27
java实战之猜字小游戏
2022-03-31 14:48:01
java LRU(Least Recently Used )详解及实例代码
2022-10-08 10:42:43