java使⽤POI实现html和word相互转换
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>
pdf转html<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l进⾏相应配置。
doc格式转换为html：
public static String docToHtml() throws Exception {
File path = new URL("classpath:").getPath());
String imagePathStr = AbsolutePath() + "\\static\\image\\";
String sourceFileName = AbsolutePath() + "\\static\\test.doc";
String targetFileName = AbsolutePath() + "\\static\\test2.html";
File file = new File(imagePathStr);
if(!ists()) {
file.mkdirs();
}
HWPFDocument wordDocument = new HWPFDocument(new FileInputStream(sourceFileName));
org.w3c.dom.Document document = wInstance().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 = Document();
DOMSource domSource = new DOMSource(htmlDocument);
StreamResult streamResult = new StreamResult(new File(targetFileName));
TransformerFactory tf = wInstance();
Transformer serializer = tf.newTransformer();
serializer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
serializer.setOutputProperty(OutputKeys.INDENT, "yes");
serializer.setOutputProperty(OutputKeys.METHOD, "html");
return targetFileName;
}
docx格式转换为html
public static String docxToHtml() throws Exception {
File path = new URL("classpath:").getPath());
String imagePath = AbsolutePath() + "\\static\\image";
String sourceFileName = AbsolutePath() + "\\static\\test.docx";
String targetFileName = AbsolutePath() + "\\static\\test.html";
OutputStreamWriter outputStreamWriter = null;
try {
XWPFDocument document = new XWPFDocument(new FileInputStream(sourceFileName));
XHTMLOptions options = ate();
// 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) Instance();
} 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 = ad(bytes)) != -1;) {
buffer.append(new String(bytes, 0, n, "utf8"));
}
} catch (IOException e) {
e.printStackTrace();
}
String();
}
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”${imgReplace}“，如果多张图⽚，可以依序排列下去，之后⽣成对应的doc⽂件（之前试过直接⽣成docx⽂件发现打不开，这个问题尚未到好的解决⽅法），我们将其另存为docx⽂件，之后就可以替换变量为图⽚了：
public static String writeWordFile(String content) {
String path = "D:/wordFile";
Map<String, Object> param = new HashMap<String, Object>();
if (!"".equals(path)) {
File fileDir = new File(path);
if (!ists()) {
fileDir.mkdirs();
}
content = HtmlUtils.htmlUnescape(content);
List<HashMap<String, String>> imgs = getImgStr(content);
int count = 0;
for (HashMap<String, String> img : imgs) {
count++;
//处理替换以“/>”结尾的img标签
content = ("img"), "${imgReplace" + count + "}");
//处理替换以“>”结尾的img标签
content = ("img1"), "${imgReplace" + count + "}");
Map<String, Object> header = new HashMap<String, Object>();
try {
File filePath = new URL("classpath:").getPath());
String imagePath = AbsolutePath() + "\\static\\";
imagePath += ("src").replaceAll("/", "\\\\");
//如果没有宽⾼属性，默认设置为400*300
("width") == null || ("height") == null) {
header.put("width", 400);
header.put("height", 300);
}else {
header.put("width", (int) (Double.("width"))));
header.put("height", (int) (Double.("height"))));
}
header.put("type", "jpg");
header.put("content", OfficeUtil.inputStream2ByteArray(new FileInputStream(imagePath), true));
} catch (FileNotFoundException e) {
e.printStackTrace();
}
param.put("${imgReplace" + count + "}", header);
}
try {
// ⽣成doc格式的word⽂档，需要⼿动改为docx
byte by[] = Bytes("UTF-8");
ByteArrayInputStream bais = new ByteArrayInputStream(by);
POIFSFileSystem poifs = new POIFSFileSystem();
DirectoryEntry directory = Root();
DocumentEntry documentEntry = ateDocument("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 = ateWord(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", String().substring(0, String().length() - 1) + "/>");
map.put("img1", String());
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：
ample.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.actor.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 = Paragraphs();
processParagraphs(paragraphList, param, doc);
//处理表格
Iterator<XWPFTable> it = TablesIterator();
while (it.hasNext()) {
XWPFTable table = it.next();
List<XWPFTableRow> rows = Rows();
for (XWPFTableRow row : rows) {
List<XWPFTableCell> cells = TableCells();
for (XWPFTableCell cell : cells) {
List<XWPFParagraph> paragraphListTable = Paragraphs();
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
SpacingBefore() >= 1000 || SpacingAfter() > 1000) {
paragraph.setSpacingBefore(0);
paragraph.setSpacingAfter(0);
}
//设置word中左右间距
paragraph.setIndentationLeft(0);
paragraph.setIndentationRight(0);
List<XWPFRun> runs = Runs();
//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 = Text(0);
if(text != null){
boolean isSetText = false;
for (Entry<String, Object> entry : Set()) {
String key = Key();
if(text.indexOf(key) != -1){
isSetText = true;
Object value = Value();
if (value instanceof String) {//⽂本替换
text = place(key, String());
} else if (value instanceof Map) {//图⽚替换
text = place(key, "");
Map pic = (Map)value;
int width = Integer.("width").toString());
int height = Integer.("height").toString());
int picType = ("type").toString());
byte[] byteArray = (byte[]) ("content");
ByteArrayInputStream byteInputStream = new ByteArrayInputStream(byteArray);
try {
String blipId = doc.addPictureData(byteInputStream,picType);