1.功能实现
使用poi对进行word文件进行解析处理,使用aspose进行pdf转换
aspose下载路径：https://pan.baidu.com/s/1vJWgYAAaHpnXmyKhZa4ljg 提取码：jdwp
注：如果导入了easyExcel，则只需要导入一部分poi(关于doc文件的解析)，防止版本不一致的问题
2.导入依赖
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi-ooxml</artifactId>
<version>3.17</version>
</dependency>
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi</artifactId>
<version>3.17</version>
</dependency>
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi-ooxml-schemas</artifactId>
<version>3.17</version>
</dependency>
<!--如果导入了easyExcel的，只需要导入下面这个-->
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi-scratchpad</artifactId>
<version>3.17</version>
</dependency>
<!--aspose,用于word转pdf,此处我是将本地jar包导入了maven(将jar导入maven的方法前面有说过)-->
<dependency>
<groupId>com.aspose.words</groupId>
<artifactId>com-aspose-words-1.1</artifactId>
<version>1.1.1</version>
</dependency>
3.获取word文件，替换其中的特殊字符：${name}
处理docx文件必须表格和段落分开处理，doc文件则不需要单独处理
/**
* 替換word模板的字符预览或者下载
*
* @param inputStream 文件输入流
* @param outputStream 文件输出流
* @param map ${name}的key的数据
* @param type 下载或者预览
* @return
*/
public static byte[] replaceWord(InputStream inputStream, OutputStream outputStream, Map<String, String> map, Integer type, String fileType) {
try {
//doc文件处理
if ("doc".equals(fileType)) {
HWPFDocument document = new HWPFDocument(inputStream);
replaceDocText(map, document);
//预览
if (type == 1) {
ByteArrayOutputStream baos = new ByteArrayOutputStream();
//3.输出流
document.write(baos);
return baos.toByteArray();
}
//下载
document.write(outputStream);
}
if ("docx".equals(fileType)) {
//docx文件处理
XWPFDocument document = new XWPFDocument(inputStream);
//替換段落
replaceDocxTable(map, document);
//替換文本
replaceDocxText(map, document);
//预览
if (type == 1) {
ByteArrayOutputStream baos = new ByteArrayOutputStream();
//3.输出流
document.write(baos);
return baos.toByteArray();
}
//下载
document.write(outputStream);
}
} catch (Exception e) {
e.printStackTrace();
}
return null;
}
/**
* 替換Docx表格
*
* @param map
* @param document
*/
private static void replaceDocxTable(Map<String, String> map, XWPFDocument document) {
//2. 替换表格中的指定文字（本人模板中 对应的姓名、性别等）
Iterator<XWPFTable> itTable = document.getTablesIterator();
XWPFTable table;
int rowsCount;
while (itTable.hasNext()) {
table = itTable.next();
rowsCount = table.getNumberOfRows();
for (int i = 0; i < rowsCount; i++) {
XWPFTableRow row = table.getRow(i);
List<XWPFTableCell> cells = row.getTableCells();
for (XWPFTableCell cell : cells) {
for (Map.Entry<String, String> e : map.entrySet()) {
if (cell.getText().equals(e.getKey())) {
XWPFParagraph xwpfParagraph = cell.addParagraph();
cell.removeParagraph(0);
//设置单元格文本样式
XWPFRun run1 = xwpfParagraph.createRun();
run1.setFontSize(11);
run1.setText(e.getValue());
//设置内容水平居中
CTTc cttc = cell.getCTTc();
CTTcPr ctPr = cttc.addNewTcPr();
ctPr.addNewVAlign().setVal(STVerticalJc.CENTER);
}
}
}
}
}
}
/**
* 替換Docx文本或者段落
*
* @param map
* @param document
*/
private static void replaceDocxText(Map<String, String> map, XWPFDocument document) {
// 替换段落中的指定文字
Iterator<XWPFParagraph> itPara = document.getParagraphsIterator();
while (itPara.hasNext()) {
XWPFParagraph paragraph = itPara.next();
List<XWPFRun> runs = paragraph.getRuns();
for (XWPFRun run : runs) {
String oneparaString = run.getText(run.getTextPosition());
if (StringUtils.isBlank(oneparaString)) {
continue;
}
for (Map.Entry<String, String> entry : map.entrySet()) {
oneparaString = oneparaString.replace(entry.getKey(), entry.getValue());
}
run.setText(oneparaString, 0);
}
}
}
/**
* 替换doc文件
*
* @param map
* @param document
*/
private static void replaceDocText(Map<String, String> map, HWPFDocument document) {
Range range = document.getRange();
for (Map.Entry<String, String> entry : map.entrySet()) {
if (entry.getValue() == null) {
entry.setValue(" ");
}
range.replaceText(entry.getKey(), entry.getValue());
}
}
4.生成pdf预览
破解生成的水印
<!--将以下内容放在新建文件license.xml中-->
<License>
<Data>
<Products>
<Product>Aspose.Total for Java</Product>
<Product>Aspose.Words for Java</Product>
</Products>
<EditionType>Enterprise</EditionType>
<SubscriptionExpiry>20991231</SubscriptionExpiry>
<LicenseExpiry>20991231</LicenseExpiry>
<SerialNumber>8bfe198c-7f0c-4ef8-8ff0-acc3237bf0d7</SerialNumber>
</Data>
<Signature>sNLLKGMUdF0r8O1kKilWAGdgfs2BvJb/2Xp8p5iuDVfZXmhppo+d0Ran1P9TKdjV4ABwAgKXxJ3jcQTqE/2IRfqwnPf8itN8aFZlV3TJPYeD3yWE7IT55Gz6EijUpC7aKeoohTb4w2fpox58wWoF3SNp6sK6jDfiAUGEHYJ9pjU=</Signature>
</License>
读取破解文件
/**
* 去掉aspose的水印
*
* @return
*/
private static boolean getLicense() {
boolean result = false;
try {
ClassPathResource cpr = new ClassPathResource("static" + File.separator + "license.xml");
InputStream is = cpr.getInputStream();
License aposeLic = new License();
aposeLic.setLicense(is);
result = true;
} catch (Exception e) {
e.printStackTrace();
}
return result;
}
//word转pdf
public static void wordToPdf(InputStream inputStream, OutputStream outputStream) {
if (!getLicense()) { // 验证License 若不验证则转化出的pdf文档会有水印产生
return;
}
try {
long old = System.currentTimeMillis();
com.aspose.words.Document doc = new com.aspose.words.Document(inputStream); //inputStream是将要被转化的word文档
doc.save(outputStream, com.aspose.words.SaveFormat.PDF);//全面支持DOC, DOCX, OOXML, RTF HTML, OpenDocument, PDF, EPUB, XPS, SWF 相互转换
long now = System.currentTimeMillis();
outputStream.close();
System.out.println("共耗时：" + ((now - old) / 1000.0) + "秒"); //转化用时
} catch (Exception e) {
e.printStackTrace();
}
}
5.下载和预览中的response设置
//预览
response.setContentType("application/pdf;charset=UTF-8");
//inline设置是强制浏览器显示，attachment设置时强制浏览器下载
response.setHeader("Content-Disposition", "inline; filename= file");
//下载
response.setContentType("application/octet-stream");
String fileName = fileEntity.getFileName();
response.setHeader("Content-Disposition", "attachment;fileName=" + URLEncoder.encode(fileName, "utf-8"));
response.flushBuffer();
6.问题
1.如果发现读取word文件失败，可能是word文件后缀与原始后缀不一致，如：新建一个doc,修改为后缀docx,这是读取不了的。
2.部署在linux，预览出现乱码或者空白，是因为缺少字体导致
3.建议优先选择doc格式文件，因为docx文件替换出来的字体不能匹配。
