java使用POI实现html和word相互转换
时间：2020-12-02 12:15:15 | 栏目：JAVA代码 | 点击：次
项目后端使用了springboot，maven，前端使用了ckeditor富文本编辑器。目前从html转换的word为doc格式，而图片处理支持的是docx格式，所以需要手动把doc另存为docx，然后才可以进行图片替换。
一.添加maven依赖
主要使用了以下和poi相关的依赖，为了便于获取html的图片元素，还使用了jsoup：
<dependency> <groupId>org.apache.poi</groupId> <artifactId>poi</artifactId> <version>3.14</version> </dependency> <dependency> <groupId>org.apache.poi</groupId> <artifactId>poi-scratchpad</artifactId> <version>3.14</version> </dependency> <dependency> <groupId>org.apache.poi</groupId> <artifactId>poi-ooxml</artifactId> <version>3.14</version> </dependency> <dependency> <groupId>fr.opensagres.xdocreport</groupId> <artifactId>xdocreport</artifactId> <version>1.0.6</version> </dependency> <dependency> <groupId>org.apache.poi</groupId> <artifactId>poi-ooxml-schemas</artifactId> <version>3.14</version> </dependency> <dependency> <groupId>org.apache.poi</groupId> <artifactId>ooxml-schemas</artifactId> <version>1.3</version> </dependency> <dependency> <groupId>org.jsoup</groupId> <artifactId>jsoup</artifactId> <version>1.11.3</version> </dependency>
二.word转换为html
在springboot项目的resources目录下新建static文件夹，将需要转换的word文件temp.docx粘贴进去，由于static是springboot的默认资源文件，所以不需要在配置文件里面另行配置了，如果改成其他名字，需要在application.yml进行相应配置。
doc格式转换为html：
public static String docToHtml() throws Exception {
File path = new File(ResourceUtils.getURL("classpath:").getPath());
String imagePathStr = path.getAbsolutePath() + "\\static\\image\\";
String sourceFileName = path.getAbsolutePath() + "\\static\\test.doc";
String targetFileName = path.getAbsolutePath() + "\\static\\test2.html";
File file = new File(imagePathStr);
if(!file.exists()) {
file.mkdirs();
}
HWPFDocument wordDocument = new HWPFDocument(new FileInputStream(sourceFileName));
org.w3c.dom.Document document = DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument();
WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(document);
//保存图片，并返回图片的相对路径
wordToHtmlConverter.setPicturesManager((content, pictureType, name, width, height) -> {
try (FileOutputStream out = new FileOutputStream(imagePathStr + name)) {
out.write(content);
} catch (Exception e) {
e.printStackTrace();
}
return "image/" + name;
});
wordToHtmlConverter.processDocument(wordDocument);
org.w3c.dom.Document htmlDocument = wordToHtmlConverter.getDocument();
DOMSource domSource = new DOMSource(htmlDocument);
StreamResult streamResult = new StreamResult(new File(targetFileName));
TransformerFactory tf = TransformerFactory.newInstance();
Transformer serializer = tf.newTransformer();
serializer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
serializer.setOutputProperty(OutputKeys.INDENT, "yes");
serializer.setOutputProperty(OutputKeys.METHOD, "html");
serializer.transform(domSource, streamResult);
return targetFileName;
}
docx格式转换为html
public static String docxToHtml() throws Exception {
File path = new File(ResourceUtils.getURL("classpath:").getPath());
String imagePath = path.getAbsolutePath() + "\\static\\image";
String sourceFileName = path.getAbsolutePath() + "\\static\\test.docx";
String targetFileName = path.getAbsolutePath() + "\\static\\test.html";
OutputStreamWriter outputStreamWriter = null;
try {
XWPFDocument document = new XWPFDocument(new FileInputStream(sourceFileName));
XHTMLOptions options = XHTMLOptions.create();
// 存放图片的文件夹
options.setExtractor(new FileImageExtractor(new File(imagePath)));
// html中图片的路径
options.URIResolver(new BasicURIResolver("image"));
outputStreamWriter = new OutputStreamWriter(new FileOutputStream(targetFileName), "utf-8");
XHTMLConverter xhtmlConverter = (XHTMLConverter) XHTMLConverter.getInstance();
xhtmlConverter.convert(document, outputStreamWriter, options);
} finally {
if (outputStreamWriter != null) {
outputStreamWriter.close();
}
}
return targetFileName;
}
转换成功后会生成对应的html文件，如果想在前端展示，直接读取文件转换为String返回给前端即可。
public static String readfile(String filePath) {
File file = new File(filePath);
InputStream input = null;
try {
input = new FileInputStream(file);
} catch (FileNotFoundException e) {
e.printStackTrace();
}
StringBuffer buffer = new StringBuffer();
byte[] bytes = new byte[1024];
try {
for (int n; (n = input.read(bytes)) != -1;) {
buffer.append(new String(bytes, 0, n, "utf8"));
}
} catch (IOException e) {
e.printStackTrace();
}
return buffer.toString();
}
在富文本编辑器ckeditor中的显示效果：
三.html转换为word
实现思路就是先把html中的所有图片元素提取出来，统一替换为变量字符”${imgReplace}“，如果多张图片，可以依序排列下去，之后生成对应的doc文件（之前试过直接生成docx文件发现打不开，这个问题尚未找到好的解决方法），我们将其另存为docx文件，之后就可以替换变量为图片了：
public static String writeWordFile(String content) {
String path = "D:/wordFile";
Map<String, Object> param = new HashMap<String, Object>();
if (!"".equals(path)) {
File fileDir = new File(path);
if (!fileDir.exists()) {
fileDir.mkdirs();
}
content = HtmlUtils.htmlUnescape(content);
List<HashMap<String, String>> imgs = getImgStr(content);
int count = 0;
for (HashMap<String, String> img : imgs) {
count++;
//处理替换以“/>”结尾的img标签
content = content.replace(img.get("img"), "${imgReplace" + count + "}");
//处理替换以“>”结尾的img标签
content = content.replace(img.get("img1"), "${imgReplace" + count + "}");
Map<String, Object> header = new HashMap<String, Object>();
try {
File filePath = new File(ResourceUtils.getURL("classpath:").getPath());
String imagePath = filePath.getAbsolutePath() + "\\static\\";
imagePath += img.get("src").replaceAll("/", "\\\\");
//如果没有宽高属性，默认设置为400*300
if(img.get("width") == null || img.get("height") == null) {
header.put("width", 400);
header.put("height", 300);
}else {
header.put("width", (int) (Double.parseDouble(img.get("width"))));
header.put("height", (int) (Double.parseDouble(img.get("height"))));
}
header.put("type", "jpg");
header.put("content", OfficeUtil.inputStream2ByteArray(new FileInputStream(imagePath), true));
} catch (FileNotFoundException e) {
e.printStackTrace();
}
param.put("${imgReplace" + count + "}", header);
}
try {
// 生成doc格式的word文档，需要手动改为docx
byte by[] = content.getBytes("UTF-8");
ByteArrayInputStream bais = new ByteArrayInputStream(by);
POIFSFileSystem poifs = new POIFSFileSystem();
DirectoryEntry directory = poifs.getRoot();
DocumentEntry documentEntry = directory.createDocument("WordDocument", bais);
FileOutputStream ostream = new FileOutputStream("D:\\wordFile\\temp.doc");
poifs.writeFilesystem(ostream);
bais.close();
ostream.close();
// 临时文件（手动改好的docx文件）
CustomXWPFDocument doc = OfficeUtil.generateWord(param, "D:\\wordFile\\temp.docx");
//最终生成的带图片的word文件
FileOutputStream fopts = new FileOutputStream("D:\\wordFile\\final.docx");
doc.write(fopts);
fopts.close();
} catch (Exception e) {
e.printStackTrace();
}
}
return "D:/wordFile/final.docx";
}
//获取html中的图片元素信息
public static List<HashMap<String, String>> getImgStr(String htmlStr) {
List<HashMap<String, String>> pics = new ArrayList<HashMap<String, String>>();
Document doc = Jsoup.parse(htmlStr);
Elements imgs = doc.select("img");
for (Element img : imgs) {
HashMap<String, String> map = new HashMap<String, String>();
if(!"".equals(img.attr("width"))) {
map.put("width", img.attr("width").substring(0, img.attr("width").length() - 2));
}
if(!"".equals(img.attr("height"))) {
map.put("height", img.attr("height").substring(0, img.attr("height").length() - 2));
}
map.put("img", img.toString().substring(0, img.toString().length() - 1) + "/>");
map.put("img1", img.toString());
map.put("src", img.attr("src"));
pics.add(map);
}
return pics;
}
OfficeUtil工具类，之前发现网上的写法只支持一张图片的修改，多张图片就会报错，是因为添加了图片，processParagraphs方法中的runs的大小改变了，会报ArrayList的异常，就和我们循环list中删除元素会报异常道理一样，解决方法就是复制一个新的Arraylist进行循环即可：
package com.example.demo.util;
import java.io.ByteArrayInputStream;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
import java.util.Map;
import java.util.Map.Entry;
import org.apache.poi.POIXMLDocument;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.openxml4j.opc.OPCPackage;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import org.apache.poi.xwpf.usermodel.XWPFRun;
import org.apache.poi.xwpf.usermodel.XWPFTable;
import org.apache.poi.xwpf.usermodel.XWPFTableCell;
import org.apache.poi.xwpf.usermodel.XWPFTableRow;
/**
* 适用于word 2007
*/
public class OfficeUtil {
/**
* 根据指定的参数值、模板，生成 word 文档
* @param param 需要替换的变量
* @param template 模板
*/
public static CustomXWPFDocument generateWord(Map<String, Object> param, String template) {
CustomXWPFDocument doc = null;
try {
OPCPackage pack = POIXMLDocument.openPackage(template);
doc = new CustomXWPFDocument(pack);
if (param != null && param.size() > 0) {
//处理段落
List<XWPFParagraph> paragraphList = doc.getParagraphs();
processParagraphs(paragraphList, param, doc);
//处理表格
Iterator<XWPFTable> it = doc.getTablesIterator();
while (it.hasNext()) {
XWPFTable table = it.next();
List<XWPFTableRow> rows = table.getRows();
for (XWPFTableRow row : rows) {
List<XWPFTableCell> cells = row.getTableCells();
for (XWPFTableCell cell : cells) {
List<XWPFParagraph> paragraphListTable = cell.getParagraphs();
processParagraphs(paragraphListTable, param, doc);
}
}
}
}
} catch (Exception e) {
e.printStackTrace();
}
return doc;
}
/**
* 处理段落
* @param paragraphList
*/
public static void processParagraphs(List<XWPFParagraph> paragraphList,Map<String, Object> param,CustomXWPFDocument doc){
if(paragraphList != null && paragraphList.size() > 0){
for(XWPFParagraph paragraph:paragraphList){
//poi转换过来的行间距过大，需要手动调整
if(paragraph.getSpacingBefore() >= 1000 || paragraph.getSpacingAfter() > 1000) {
paragraph.setSpacingBefore(0);
paragraph.setSpacingAfter(0);
}
//设置word中左右间距
paragraph.setIndentationLeft(0);
paragraph.setIndentationRight(0);
List<XWPFRun> runs = paragraph.getRuns();
//加了图片，修改了paragraph的runs的size，所以循环不能使用runs
List<XWPFRun> allRuns = new ArrayList<XWPFRun>(runs);
for (XWPFRun run : allRuns) {
String text = run.getText(0);
if(text != null){
boolean isSetText = false;
for (Entry<String, Object> entry : param.entrySet()) {
String key = entry.getKey();
if(text.indexOf(key) != -1){
isSetText = true;
Object value = entry.getValue();
if (value instanceof String) {//文本替换
text = text.replace(key, value.toString());
} else if (value instanceof Map) {//图片替换
text = text.replace(key, "");
Map pic = (Map)value;
int width = Integer.parseInt(pic.get("width").toString());
int height = Integer.parseInt(pic.get("height").toString());
int picType = getPictureType(pic.get("type").toString());
byte[] byteArray = (byte[]) pic.get("content");
ByteArrayInputStream byteInputStream = new ByteArrayInputStream(byteArray);
try {
String blipId = doc.addPictureData(byteInputStream,picType);
doc.createPicture(blipId,doc.getNextPicNameNumber(picType), width, height,paragraph);
} catch (Exception e) {
e.printStackTrace();
}
}
}
}
if(isSetText){
run.setText(text,0);
}
}
}
}
}
}
/**
* 根据图片类型，取得对应的图片类型代码
* @param picType
* @return int
*/
private static int getPictureType(String picType){
int res = CustomXWPFDocument.PICTURE_TYPE_PICT;
if(picType != null){
if(picType.equalsIgnoreCase("png")){
res = CustomXWPFDocument.PICTURE_TYPE_PNG;
}else if(picType.equalsIgnoreCase("dib")){
res = CustomXWPFDocument.PICTURE_TYPE_DIB;
}else if(picType.equalsIgnoreCase("emf")){
res = CustomXWPFDocument.PICTURE_TYPE_EMF;
}else if(picType.equalsIgnoreCase("jpg") || picType.equalsIgnoreCase("jpeg")){
res = CustomXWPFDocument.PICTURE_TYPE_JPEG;
}else if(picType.equalsIgnoreCase("wmf")){
res = CustomXWPFDocument.PICTURE_TYPE_WMF;
}
}
return res;
}
/**
* 将输入流中的数据写入字节数组
* @param in
* @return
*/
public static byte[] inputStream2ByteArray(InputStream in,boolean isClose){
byte[] byteArray = null;
try {
int total = in.available();
byteArray = new byte[total];
in.read(byteArray);
} catch (IOException e) {
e.printStackTrace();
}finally{
if(isClose){
try {
in.close();
} catch (Exception e2) {
System.out.println("关闭流失败");
}
}
}
return byteArray;
}
}
我认为之所以word2003不支持图片替换，主要是处理2003版本的HWPFDocument对象被声明为了final，我们就无法重写他的方法了。而处理2007版本的类为XWPFDocument，是可以继承的，通过继承XWPFDocument，重写createPicture方法即可实现图片替换，以下为对应的CustomXWPFDocument类：
package com.example.demo.util;
import java.io.IOException;
import java.io.InputStream;
import org.apache.poi.openxml4j.opc.OPCPackage;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import org.apache.xmlbeans.XmlException;
import org.apache.xmlbeans.XmlToken;
import org.openxmlformats.schemas.drawingml.x2006.main.CTNonVisualDrawingProps;
import org.openxmlformats.schemas.drawingml.x2006.main.CTPositiveSize2D;
import org.openxmlformats.schemas.drawingml.x2006.wordprocessingDrawing.CTInline;
/**
* 自定义 XWPFDocument，并重写 createPicture()方法
*/
public class CustomXWPFDocument extends XWPFDocument {
public CustomXWPFDocument(InputStream in) throws IOException {
super(in);
}
public CustomXWPFDocument() {
super();
}
public CustomXWPFDocument(OPCPackage pkg) throws IOException {
super(pkg);
}
/**
* @param ind
* @param width 宽
* @param height 高
* @param paragraph 段落
*/
public void createPicture(String blipId, int ind, int width, int height,XWPFParagraph paragraph) {
final int EMU = 9525;
width *= EMU;
height *= EMU;
CTInline inline = paragraph.createRun().getCTR().addNewDrawing().addNewInline();
String picXml = ""
+ "<a:graphic xmlns:a=\"http://schemas.openxmlformats.org/drawingml/2006/main\">"
+ " <a:graphicData uri=\"http://schemas.openxmlformats.org/drawingml/2006/picture\">"
+ " <pic:pic xmlns:pic=\"http://schemas.openxmlformats.org/drawingml/2006/picture\">"
+ " <pic:nvPicPr>" + " <pic:cNvPr id=\""
+ ind
+ "\" name=\"Generated\"/>"
+ " <pic:cNvPicPr/>"
+ " </pic:nvPicPr>"
+ " <pic:blipFill>"
+ " <a:blip r:embed=\""
+ blipId
+ "\" xmlns:r=\"http://schemas.openxmlformats.org/officeDocument/2006/relationships\"/>"
+ " <a:stretch>"
+ " <a:fillRect/>"
+ " </a:stretch>"
+ " </pic:blipFill>"
+ " <pic:spPr>"
+ " <a:xfrm>"
+ " <a:off x=\"0\" y=\"0\"/>"
+ " <a:ext cx=\""
+ width
+ "\" cy=\""
+ height
+ "\"/>"
+ " </a:xfrm>"
+ " <a:prstGeom prst=\"rect\">"
+ " <a:avLst/>"
+ " </a:prstGeom>"
+ " </pic:spPr>"
+ " </pic:pic>"
+ " </a:graphicData>" + "</a:graphic>";
inline.addNewGraphic().addNewGraphicData();
XmlToken xmlToken = null;
try {
xmlToken = XmlToken.Factory.parse(picXml);
} catch (XmlException xe) {
xe.printStackTrace();
}
inline.set(xmlToken);
inline.setDistT(0);
inline.setDistB(0);
inline.setDistL(0);
inline.setDistR(0);
CTPositiveSize2D extent = inline.addNewExtent();
extent.setCx(width);
extent.setCy(height);
CTNonVisualDrawingProps docPr = inline.addNewDocPr();
docPr.setId(ind);
docPr.setName("图片" + ind);
docPr.setDescr("测试");
}
}
以上就是通过POI实现html和word的相互转换，对于html无法转换为可读的docx这个问题尚未解决，如果大家有好的解决方法可以交流一下。