处理相关冲突

com.actionsoft.apps.coe.pal.datamigration/src/com/actionsoft/apps/coe/pal/datamigration/util/htmltodocx/CommonConStant.java

@@ -0,0 +1,15 @@
+package com.actionsoft.apps.coe.pal.datamigration.util.htmltodocx;
+
+/**
+ * @author baizp
+ * @Description:
+ * @date 2022/6/24 16:02
+ */
+/**
+ * 公共常量
+ */
+public class CommonConStant {
+    // 固定元素节点
+    public static final String COMMONATTR = "data-class";
+}
+

com.actionsoft.apps.coe.pal.datamigration/src/com/actionsoft/apps/coe/pal/datamigration/util/htmltodocx/ElementEnum.java

@@ -0,0 +1,55 @@
+package com.actionsoft.apps.coe.pal.datamigration.util.htmltodocx;
+
+/**
+ * @author baizp
+ * @Description:
+ * @date 2022/6/24 15:59
+ */
+
+/**
+ * html 元素枚举映射类
+ */
+public enum ElementEnum {
+    H1("h1","h1","一级标题"),
+    H2("h2","h2","二级标题"),
+    H3("h3","h3","三级标题"),
+    H7("h7","h7","小标题"),
+    P("p", "paragraph", "段落"),
+    STRONG("strong","","加粗"),
+    I("i","","斜体"),
+    U("u", "", "字体下划线"),
+    IMG("img", "imgurl", "base64图片"),
+    TABLE("table","table","表格"),
+    BR("br","br","换行");
+
+    private String code;
+    private String value;
+    private String desc;
+
+    public String getCode() {
+        return code;
+    }
+
+    public String getValue() {
+        return value;
+    }
+
+    public String getDesc() {
+        return desc;
+    }
+
+    ElementEnum(String code, String value, String desc) {
+        this.code = code;
+        this.value = value;
+        this.desc = desc;
+    }
+
+    public static String getValueByCode(String code) {
+        for (ElementEnum e : ElementEnum.values()) {
+            if (e.getCode().equalsIgnoreCase(code)) {
+                return e.getValue();
+            }
+        }
+        return null;
+    }
+}

com.actionsoft.apps.coe.pal.datamigration/src/com/actionsoft/apps/coe/pal/datamigration/util/htmltodocx/HtmlToWord.java

@@ -0,0 +1,610 @@
+package com.actionsoft.apps.coe.pal.datamigration.util.htmltodocx;
+
+/**
+ * @author baizp
+ * @Description:
+ * @date 2022/6/24 16:01
+ */
+
+import org.docx4j.dml.wordprocessingDrawing.Inline;
+import org.docx4j.jaxb.Context;
+import org.docx4j.model.structure.SectionWrapper;
+import org.docx4j.openpackaging.exceptions.Docx4JException;
+import org.docx4j.openpackaging.exceptions.InvalidFormatException;
+import org.docx4j.openpackaging.packages.WordprocessingMLPackage;
+import org.docx4j.openpackaging.parts.WordprocessingML.BinaryPartAbstractImage;
+import org.docx4j.openpackaging.parts.WordprocessingML.FooterPart;
+import org.docx4j.openpackaging.parts.WordprocessingML.MainDocumentPart;
+import org.docx4j.openpackaging.parts.WordprocessingML.StyleDefinitionsPart;
+import org.docx4j.relationships.Relationship;
+import org.docx4j.wml.*;
+import org.docx4j.wml.PPrBase.Ind;
+import org.jsoup.Jsoup;
+import org.jsoup.nodes.Document;
+import org.jsoup.nodes.Element;
+import org.jsoup.select.Elements;
+
+import java.io.*;
+import java.math.BigInteger;
+import java.util.List;
+
+/**
+ * @program: htmltoword
+ * @description: html 转 docx
+ * @author: corey
+ * @create: 2020-04-29 14:10
+ **/
+public class HtmlToWord {
+    private static ObjectFactory factory;
+    private static WordprocessingMLPackage wordMLPackage;
+
+    /**
+     * 将一段富文本字符串转为一个字节数组
+     *
+     * @param data
+     * @return
+     */
+    public static byte[] resolveHtml(String data) {
+        Document document = Jsoup.parseBodyFragment(data, "UTF-8");
+        ByteArrayOutputStream out = null;
+        try {
+            wordMLPackage = WordprocessingMLPackage.createPackage();
+            factory = Context.getWmlObjectFactory();
+            Relationship relationship = createFooterPart();
+            createFooterReference(relationship);
+            MainDocumentPart documentPart = wordMLPackage.getMainDocumentPart();
+            alterStyleSheet();
+            // 添加固定元素
+            HtmlUtils.addElement(document);
+            Elements elements = document.select("[" + CommonConStant.COMMONATTR + "]");
+            for (Element em : elements) {
+                String type = em.attr(CommonConStant.COMMONATTR);
+                if (em.childNodeSize() > 0) {
+                    if (em.childNodeSize() == 2) {
+                        em.childNode(1);
+                    }
+                }
+                switch (em.attr(CommonConStant.COMMONATTR)) {
+                    case "title":
+                        documentPart.addStyledParagraphOfText("Title", em.text());
+                        break;
+                    case "subtitle":
+                        documentPart.addStyledParagraphOfText("Subtitle", em.text());
+                        break;
+                    case "imgurl":
+                        String imgSrc = em.attr("src");
+                        File file = new File(imgSrc);
+                        byte[] bytes = convertImageToByteArray(file);
+                        addImageToPackage(wordMLPackage, bytes);
+                        break;
+                    case "imgbase64":
+                        break;
+                    case "table":
+                        Tbl table = addTable(em);
+                        documentPart.addObject(table);
+                        break;
+                    case "h1":
+                        P tmp = documentPart.addStyledParagraphOfText("Heading1", em.text());
+                        //setNum(1, tmpstyle);
+                        setNum1(1, tmp);
+                        break;
+                    case "h2":
+                        P tmp1 = documentPart.addStyledParagraphOfText("Heading2", em.text());
+                        //setNum(2, tmpstyle1);
+                        setNum1(2, tmp1);
+                        break;
+                    case "h3":
+                        P tmp2 = documentPart.addStyledParagraphOfText("Heading3", em.text());
+                        //setNum(3, tmpstyle2);
+                        setNum1(3, tmp2);
+                        break;
+                    case "paragraph":
+                        P p = addParapraph(em.text());
+                        //设置首行缩进
+                        setFirstLine(p, "400");
+                        documentPart.getContent().add(p);
+                        break;
+                    default:
+                        documentPart.addParagraphOfText(em.text());
+                        break;
+                }
+            }
+            addPageBreak(documentPart);
+            out = new ByteArrayOutputStream();
+            wordMLPackage.save(out);
+            return out.toByteArray();
+        } catch (Exception e) {
+            e.printStackTrace();
+            return null;
+        } finally {
+            if (out != null) {
+                try {
+                    out.close();
+                } catch (IOException e) {
+                    e.printStackTrace();
+                }
+            }
+        }
+    }
+
+    public static void setNum(int level,Style style) {
+        ObjectFactory factory = Context.getWmlObjectFactory();
+        //Create and add <w:pPr> to style
+        PPr ppr = factory.createPPr();
+        style.setPPr(ppr);
+        PPrBase.NumPr numPr = factory.createPPrBaseNumPr();
+        PPrBase.NumPr.Ilvl ilvlElement = factory.createPPrBaseNumPrIlvl();
+        numPr.setIlvl(ilvlElement);
+        ilvlElement.setVal(BigInteger.valueOf(level));
+        PPrBase.NumPr.NumId numIdElement = factory.createPPrBaseNumPrNumId();
+        numPr.setNumId(numIdElement);
+        numIdElement.setVal(BigInteger.valueOf(level));
+        ppr.setNumPr(numPr);
+    }
+    public static void setNum1(int level,P p){
+
+
+        /*ObjectFactory factory = new org.docx4j.wml.ObjectFactory();
+        P p = factory.createP();*/
+
+        /*org.docx4j.wml.Text t = factory.createText();
+        t.setValue(em.text());*/
+
+        /*org.docx4j.wml.R run = factory.createR();
+        run.getContent().add(t);
+
+        p.getContent().add(run);*/
+
+        /*org.docx4j.wml.PPr ppr = factory.createPPr();
+
+        p.setPPr(ppr);*/
+        org.docx4j.wml.PPr ppr =p.getPPr();
+        // Create and add <w:numPr>
+        PPrBase.NumPr numPr = factory.createPPrBaseNumPr();
+        ppr.setNumPr(numPr);
+
+        // The <w:ilvl> element
+        PPrBase.NumPr.Ilvl ilvlElement = factory.createPPrBaseNumPrIlvl();
+        numPr.setIlvl(ilvlElement);
+        ilvlElement.setVal(BigInteger.valueOf(level));
+
+        // The <w:numId> element
+        PPrBase.NumPr.NumId numIdElement = factory.createPPrBaseNumPrNumId();
+        numPr.setNumId(numIdElement);
+        numIdElement.setVal(BigInteger.valueOf(level));
+
+        //wordMLPackage.getMainDocumentPart().addObject(p);
+    }
+
+    /**
+     * @param @param  text
+     * @param @return 设定文件
+     * @return P    返回类型
+     * @throws
+     * @Title: addParapraph
+     * @Description: (文本转段落)
+     */
+    private static P addParapraph(String text) {
+        factory = Context.getWmlObjectFactory();
+        P paragraph = factory.createP();
+        Text t = factory.createText();
+        t.setValue(text);
+        R run = factory.createR();
+        run.getContent().add(t);
+        paragraph.getContent().add(run);
+        RPr runProperties = factory.createRPr();
+        run.setRPr(runProperties);
+        return paragraph;
+    }
+
+    /**
+     * @param @param p
+     * @param @param str    设定文件
+     * @return void    返回类型
+     * @throws
+     * @Title: setFirstLine
+     */
+    private static void setFirstLine(P p, String str) {
+        PPr ppr = getPPr(p);
+        Ind ind = ppr.getInd();
+        if (ind == null) {
+            ind = new Ind();
+            ppr.setInd(ind);
+        }
+        ind.setFirstLine(new BigInteger(str));
+    }
+
+    ;
+
+    private static PPr getPPr(P p) {
+        PPr ppr = p.getPPr();
+        if (ppr == null) {
+            ppr = new PPr();
+            p.setPPr(ppr);
+        }
+        return ppr;
+    }
+
+    /**
+     * table @param @return 设定文件 @return Tbl 返回类型 @throws
+     */
+    private static Tbl addTable(Element table) {
+        factory = Context.getWmlObjectFactory();
+        Tbl tbl = factory.createTbl();
+        addBorders(tbl);
+        Elements trs = table.getElementsByTag("tr");
+        for (Element tr : trs) {
+            Tr fTr = addTableTr(tr);
+            tbl.getContent().add(fTr);
+        }
+        return tbl;
+    }
+
+    /**
+     * tr @param @return 设定文件 @return Tr 返回类型 @throws
+     */
+    private static Tr addTableTr(Element tr) {
+        Elements tds = tr.getElementsByTag("th").isEmpty() ? tr.getElementsByTag("td") : tr.getElementsByTag("th");
+        Tr ftr = factory.createTr();
+        for (int i = 0, j = tds.size(); i < j; i++) {
+            Tc ftd = factory.createTc();
+            setCellWidth(ftd, 1000);
+            ftd.getContent().add(wordMLPackage.getMainDocumentPart().createParagraphOfText(tds.get(i).text()));
+            ftr.getContent().add(ftd);
+        }
+        return ftr;
+    }
+
+    /**
+     * 本方法创建一个单元格属性集对象和一个表格宽度对象. 将给定的宽度设置到宽度对象然后将其添加到 属性集对象. 最后将属性集对象设置到单元格中.
+     */
+    private static void setCellWidth(Tc tableCell, int width) {
+        TcPr tableCellProperties = new TcPr();
+        TblWidth tableWidth = new TblWidth();
+        tableWidth.setW(BigInteger.valueOf(width));
+        tableCellProperties.setTcW(tableWidth);
+        tableCell.setTcPr(tableCellProperties);
+    }
+
+    /**
+     * 本方法为表格添加边框
+     */
+    private static void addBorders(Tbl table) {
+        table.setTblPr(new TblPr());
+        CTBorder border = new CTBorder();
+        border.setColor("auto");
+        border.setSz(new BigInteger("4"));
+        border.setSpace(new BigInteger("0"));
+        border.setVal(STBorder.SINGLE);
+
+        TblBorders borders = new TblBorders();
+        borders.setBottom(border);
+        borders.setLeft(border);
+        borders.setRight(border);
+        borders.setTop(border);
+        borders.setInsideH(border);
+        borders.setInsideV(border);
+        table.getTblPr().setTblBorders(borders);
+    }
+
+    /**
+     * 将图片从文件对象转换成字节数组.
+     *
+     * @param file 将要转换的文件
+     * @return 包含图片字节数据的字节数组
+     * @throws FileNotFoundException
+     * @throws IOException
+     */
+    private static byte[] convertImageToByteArray(File file) throws FileNotFoundException, IOException {
+        InputStream is = new FileInputStream(file);
+        long length = file.length();
+        // 不能使用long类型创建数组, 需要用int类型.
+        if (length > Integer.MAX_VALUE) {
+            System.out.println("File too large!!");
+        }
+        byte[] bytes = new byte[(int) length];
+        int offset = 0;
+        int numRead = 0;
+        while (offset < bytes.length && (numRead = is.read(bytes, offset, bytes.length - offset)) >= 0) {
+            offset += numRead;
+        }
+        // 确认所有的字节都没读取
+        if (offset < bytes.length) {
+            System.out.println("Could not completely read file " + file.getName());
+        }
+        is.close();
+        return bytes;
+    }
+
+    /**
+     * Docx4j拥有一个由字节数组创建图片部件的工具方法, 随后将其添加到给定的包中. 为了能将图片添加 到一个段落中, 我们需要将图片转换成内联对象.
+     * 这也有一个方法, 方法需要文件名提示, 替换文本, 两个id标识符和一个是嵌入还是链接到的指示作为参数. 一个id用于文档中绘图对象不可见的属性,
+     * 另一个id用于图片本身不可见的绘制属性. 最后我们将内联 对象添加到段落中并将段落添加到包的主文档部件.
+     *
+     * @param wordMLPackage 要添加图片的包
+     * @param bytes         图片对应的字节数组
+     * @throws Exception 不幸的createImageInline方法抛出一个异常(没有更多具体的异常类型)
+     */
+    private static void addImageToPackage(WordprocessingMLPackage wordMLPackage, byte[] bytes) throws Exception {
+        BinaryPartAbstractImage imagePart = BinaryPartAbstractImage.createImagePart(wordMLPackage, bytes);
+
+        int docPrId = 1;
+        int cNvPrId = 2;
+        Inline inline = imagePart.createImageInline("Filename hint", "Alternative text", docPrId, cNvPrId, false);
+
+        P paragraph = addInlineImageToParagraph(inline);
+
+        wordMLPackage.getMainDocumentPart().addObject(paragraph);
+    }
+
+    /**
+     * 创建一个对象工厂并用它创建一个段落和一个可运行块R. 然后将可运行块添加到段落中. 接下来创建一个图画并将其添加到可运行块R中. 最后我们将内联
+     * 对象添加到图画中并返回段落对象.
+     *
+     * @param inline 包含图片的内联对象.
+     * @return 包含图片的段落
+     */
+    private static P addInlineImageToParagraph(Inline inline) {
+        // 添加内联对象到一个段落中
+        ObjectFactory factory = new ObjectFactory();
+        P paragraph = factory.createP();
+        R run = factory.createR();
+        paragraph.getContent().add(run);
+        Drawing drawing = factory.createDrawing();
+        run.getContent().add(drawing);
+        drawing.getAnchorOrInline().add(inline);
+        return paragraph;
+    }
+
+    /**
+     * This method alters the default style sheet that is part of each document.
+     * <p>
+     * To do this, we first retrieve the style sheet from the package and then get
+     * the Styles object from it. From this object, we get the list of actual styles
+     * and iterate over them. We check against all styles we want to alter and apply
+     * the alterations if applicable.
+     *
+     * @param
+     */
+    public static void alterStyleSheet() {
+        StyleDefinitionsPart styleDefinitionsPart = wordMLPackage.getMainDocumentPart().getStyleDefinitionsPart();
+        Styles styles = null;
+        try {
+            styles = styleDefinitionsPart.getContents();
+        } catch (Docx4JException e) {
+            e.printStackTrace();
+        }
+
+        List<Style> stylesList = styles.getStyle();
+        for (Style style : stylesList) {
+            if (style.getStyleId().equals("Normal")) {
+                alterNormalStyle(style);
+            } else if (style.getStyleId().equals("Heading1")) {
+                alterHeading1Style(style);
+            } else if (style.getStyleId().equals("Heading2")) {
+                alterHeading2Style(style);
+            } else if (style.getStyleId().equals("Title") || style.getStyleId().equals("Subtitle")) {
+                getRunPropertiesAndRemoveThemeInfo(style);
+            }
+        }
+    }
+
+    /**
+     * First we create a run properties object as we want to remove nearly all of
+     * the existing styling. Then we change the font and font size and set the run
+     * properties on the given style. As in previous examples, the font size is
+     * defined to be in half-point size.
+     */
+    private static void alterNormalStyle(Style style) {
+        // we want to change (or remove) almost all the run properties of the
+        // normal style, so we create a new one.
+        RPr rpr = new RPr();
+        changeFontToArial(rpr);
+        changeFontSize(rpr, 20);
+        style.setRPr(rpr);
+    }
+
+    /**
+     * For this style, we get the existing run properties from the style and remove
+     * the theme font information from them. Then we also remove the bold styling,
+     * change the font size (half-points) and add an underline.
+     */
+    private static void alterHeading1Style(Style style) {
+        RPr rpr = getRunPropertiesAndRemoveThemeInfo(style);
+        removeBoldStyle(rpr);
+        changeFontSize(rpr, 28);
+        /* addUnderline(rpr); */
+    }
+
+    private static void alterHeading2Style(Style style) {
+        RPr rpr = getRunPropertiesAndRemoveThemeInfo(style);
+        removeBoldStyle(rpr);
+        changeFontSize(rpr, 24);
+
+        /* addUnderline(rpr); */
+    }
+
+    private static RPr getRunPropertiesAndRemoveThemeInfo(Style style) {
+        // We only want to change some settings, so we get the existing run
+        // properties from the style.
+        RPr rpr = style.getRPr();
+        removeThemeFontInformation(rpr);
+        return rpr;
+    }
+
+    /**
+     * Change the font of the given run properties to Arial.
+     * <p>
+     * A run font specifies the fonts which shall be used to display the contents of
+     * the run. Of the four possible types of content, we change the styling of two
+     * of them: ASCII and High ANSI. Finally we add the run font to the run
+     * properties.
+     *
+     * @param runProperties
+     */
+    private static void changeFontToArial(RPr runProperties) {
+        RFonts runFont = new RFonts();
+        runFont.setAscii("Arial");
+        runFont.setHAnsi("Arial");
+        runProperties.setRFonts(runFont);
+    }
+
+    /**
+     * Change the font size of the given run properties to the given value.
+     *
+     * @param runProperties
+     * @param fontSize      Twice the size needed, as it is specified as half-point value
+     */
+    private static void changeFontSize(RPr runProperties, int fontSize) {
+        HpsMeasure size = new HpsMeasure();
+        size.setVal(BigInteger.valueOf(fontSize));
+        runProperties.setSz(size);
+    }
+
+    /**
+     * Removes the theme font information from the run properties. If this is not
+     * removed then the styles based on the normal style won't inherit the Arial
+     * font from the normal style.
+     *
+     * @param runProperties
+     */
+    private static void removeThemeFontInformation(RPr runProperties) {
+        runProperties.getRFonts().setAsciiTheme(null);
+        runProperties.getRFonts().setHAnsiTheme(null);
+    }
+
+    /**
+     * Removes the Bold styling from the run properties.
+     *
+     * @param runProperties
+     */
+    private static void removeBoldStyle(RPr runProperties) {
+        runProperties.getB().setVal(false);
+    }
+
+
+    /**
+     * As in the previous example, this method creates a footer part and adds it to
+     * the main document and then returns the corresponding relationship.
+     *
+     * @return
+     * @throws InvalidFormatException
+     */
+    private static Relationship createFooterPart() throws InvalidFormatException {
+        FooterPart footerPart = new FooterPart();
+        footerPart.setPackage(wordMLPackage);
+
+        footerPart.setJaxbElement(createFooterWithPageNr());
+
+        return wordMLPackage.getMainDocumentPart().addTargetPart(footerPart);
+    }
+
+    /**
+     * As in the previous example, we create a footer and a paragraph object. But
+     * this time, instead of adding text to a run, we add a field. And just as with
+     * the table of content, we have to add a begin and end character around the
+     * actual field with the page number. Finally we add the paragraph to the
+     * content of the footer and then return it.
+     *
+     * @return
+     */
+    public static Ftr createFooterWithPageNr() {
+        Ftr ftr = factory.createFtr();
+        P paragraph = factory.createP();
+
+        addFieldBegin(paragraph);
+        addPageNumberField(paragraph);
+        addFieldEnd(paragraph);
+
+        ftr.getContent().add(paragraph);
+        return ftr;
+    }
+
+    /**
+     * Creating the page number field is nearly the same as creating the field in
+     * the TOC example. The only difference is in the value. We use the PAGE
+     * command, which prints the number of the current page, together with the
+     * MERGEFORMAT switch, which indicates that the current formatting should be
+     * preserved when the field is updated.
+     *
+     * @param paragraph
+     */
+    private static void addPageNumberField(P paragraph) {
+        R run = factory.createR();
+        Text txt = new Text();
+        txt.setSpace("preserve");
+        txt.setValue(" PAGE   \\* MERGEFORMAT ");
+        run.getContent().add(factory.createRInstrText(txt));
+        paragraph.getContent().add(run);
+    }
+
+    /**
+     * Every fields needs to be delimited by complex field characters. This method
+     * adds the delimiter that precedes the actual field to the given paragraph.
+     *
+     * @param paragraph
+     */
+    private static void addFieldBegin(P paragraph) {
+        R run = factory.createR();
+        FldChar fldchar = factory.createFldChar();
+        fldchar.setFldCharType(STFldCharType.BEGIN);
+        run.getContent().add(fldchar);
+        paragraph.getContent().add(run);
+    }
+
+    /**
+     * Every fields needs to be delimited by complex field characters. This method
+     * adds the delimiter that follows the actual field to the given paragraph.
+     *
+     * @param paragraph
+     */
+    private static void addFieldEnd(P paragraph) {
+        FldChar fldcharend = factory.createFldChar();
+        fldcharend.setFldCharType(STFldCharType.END);
+        R run3 = factory.createR();
+        run3.getContent().add(fldcharend);
+        paragraph.getContent().add(run3);
+    }
+
+    /**
+     * This method fetches the document final section properties, and adds a newly
+     * created footer reference to them.
+     *
+     * @param relationship
+     */
+    public static void createFooterReference(Relationship relationship) {
+
+        List<SectionWrapper> sections = wordMLPackage.getDocumentModel().getSections();
+
+        SectPr sectPr = sections.get(sections.size() - 1).getSectPr();
+        // There is always a section wrapper, but it might not contain a sectPr
+        if (sectPr == null) {
+            sectPr = factory.createSectPr();
+            wordMLPackage.getMainDocumentPart().addObject(sectPr);
+            sections.get(sections.size() - 1).setSectPr(sectPr);
+        }
+
+        FooterReference footerReference = factory.createFooterReference();
+        footerReference.setId(relationship.getId());
+        footerReference.setType(HdrFtrRef.DEFAULT);
+        sectPr.getEGHdrFtrReferences().add(footerReference);
+    }
+
+    /**
+     * Adds a page break to the document.
+     *
+     * @param documentPart
+     */
+    private static void addPageBreak(MainDocumentPart documentPart) {
+        Br breakObj = new Br();
+        breakObj.setType(STBrType.PAGE);
+
+        P paragraph = factory.createP();
+        paragraph.getContent().add(breakObj);
+        try {
+            documentPart.getContents().getBody().getContent().add(paragraph);
+        } catch (Docx4JException e) {
+            e.printStackTrace();
+        }
+    }
+}

com.actionsoft.apps.coe.pal.datamigration/src/com/actionsoft/apps/coe/pal/datamigration/util/htmltodocx/HtmlUtils.java

@@ -0,0 +1,202 @@
+package com.actionsoft.apps.coe.pal.datamigration.util.htmltodocx;
+
+/**
+ * @author baizp
+ * @Description:
+ * @date 2022/6/24 15:55
+ */
+
+import org.apache.poi.util.Units;
+import org.apache.poi.xwpf.usermodel.*;
+import org.apache.xmlbeans.XmlCursor;
+import org.jsoup.Jsoup;
+import org.jsoup.nodes.Document;
+import org.jsoup.nodes.Element;
+import org.jsoup.select.Elements;
+import org.springframework.util.ObjectUtils;
+import org.springframework.util.StringUtils;
+
+import java.io.*;
+import java.net.URL;
+import java.net.URLConnection;
+
+public class HtmlUtils {
+
+    /**
+     * 给document添加指定元素
+     *
+     * @param document
+     */
+    public static void addElement(Document document) {
+        if (ObjectUtils.isEmpty(document)) {
+            throw new NullPointerException("不允许为空的对象添加元素");
+        }
+        Elements elements = document.getAllElements();
+        for (Element e : elements) {
+            String attrName = ElementEnum.getValueByCode(e.tag().getName());
+            if (!StringUtils.isEmpty(attrName)) {
+                e.attr(CommonConStant.COMMONATTR, attrName);
+            }
+        }
+    }
+
+
+    /**
+     * 将富文本内容写入到Word
+     * 因富文本样式种类繁多，不能一一枚举，目前实现了H1、H2、H3、段落、图片、表格枚举
+     *
+     * @param ritchText 富文本内容
+     * @param doc       需要写入富文本内容的Word 写入图片和表格需要用到
+     * @param paragraph
+     * @param
+     */
+    public static void resolveHtml(String ritchText, XWPFDocument doc, XWPFParagraph paragraph) {
+        Document document = Jsoup.parseBodyFragment(ritchText, "UTF-8");
+        try {
+            // 添加固定元素
+            HtmlUtils.addElement(document);
+            Elements elements = document.select("[" + CommonConStant.COMMONATTR + "]");
+            for (Element em : elements) {
+                XmlCursor xmlCursor = paragraph.getCTP().newCursor();
+                switch (em.attr(CommonConStant.COMMONATTR)) {
+                    case "title":
+                        break;
+                    case "subtitle":
+                        break;
+                    case "imgurl":
+                        String src = em.attr("src");
+                        URL url = new URL(src);
+                        URLConnection uc = url.openConnection();
+                        InputStream inputStream = uc.getInputStream();
+                        XWPFParagraph imgurlparagraph = doc.insertNewParagraph(xmlCursor);
+                        ParagraphStyleUtil.setImageCenter(imgurlparagraph);
+                        imgurlparagraph.createRun().addPicture(inputStream, XWPFDocument.PICTURE_TYPE_PNG, "图片.jpeg", Units.toEMU(150), Units.toEMU(150));
+                        closeStream(inputStream);
+                        File file = new File("picture.jpg");
+                        boolean exists = file.exists();
+                        if (exists) {
+                            file.delete();
+                        }
+                        break;
+                    case "imgbase64":
+                        break;
+                    case "table":
+                        XWPFTable xwpfTable = doc.insertNewTbl(xmlCursor);
+                        addTable(xwpfTable, em);
+                        // 设置表格居中
+                        ParagraphStyleUtil.setTableLocation(xwpfTable, "center");
+                        // 设置内容居中
+                        ParagraphStyleUtil.setCellLocation(xwpfTable, "CENTER", "center");
+                        break;
+                    case "h1":
+                        XWPFParagraph h1paragraph = doc.insertNewParagraph(xmlCursor);
+                        XWPFRun xwpfRun_1 = h1paragraph.createRun();
+                        xwpfRun_1.setText(em.text());
+                        //居中
+                        ParagraphStyleUtil.setImageCenter(h1paragraph);
+                        // 设置字体
+                        ParagraphStyleUtil.setTitle(xwpfRun_1, TitleFontEnum.H1.getTitle());
+                        break;
+                    case "h2":
+                        XWPFParagraph h2paragraph = doc.insertNewParagraph(xmlCursor);
+                        XWPFRun xwpfRun_2 = h2paragraph.createRun();
+                        xwpfRun_2.setText(em.text());
+                        //居中
+                        ParagraphStyleUtil.setImageCenter(h2paragraph);
+                        // 设置字体
+                        ParagraphStyleUtil.setTitle(xwpfRun_2, TitleFontEnum.H2.getTitle());
+                        break;
+                    case "h3":
+                        XWPFParagraph h3paragraph = doc.insertNewParagraph(xmlCursor);
+                        XWPFRun xwpfRun_3 = h3paragraph.createRun();
+                        xwpfRun_3.setText(em.text());
+                        // 设置字体
+                        ParagraphStyleUtil.setTitle(xwpfRun_3, TitleFontEnum.H3.getTitle());
+                        break;
+                    case "paragraph":
+                        XWPFParagraph paragraphd = doc.insertNewParagraph(xmlCursor);
+                        // 设置段落缩进 4个空格
+                        paragraphd.createRun().setText("    " + em.text());
+                        break;
+                    case "br":
+                        XWPFParagraph br = doc.insertNewParagraph(xmlCursor);
+                        XWPFRun run = br.createRun();
+                        run.addBreak(BreakType.TEXT_WRAPPING);
+                    case "h7":
+                        XWPFParagraph h7paragraph = doc.insertNewParagraph(xmlCursor);
+                        XWPFRun xwpfRun_7 = h7paragraph.createRun();
+                        xwpfRun_7.setText(em.text());
+                        //居左
+                        ParagraphStyleUtil.AlignmentRight(h7paragraph);
+                        // 设置字体
+                        ParagraphStyleUtil.setTitle(xwpfRun_7, TitleFontEnum.H7.getTitle());
+                    default:
+                        break;
+                }
+            }
+
+        } catch (Exception e) {
+            e.printStackTrace();
+        }
+    }
+
+    /**
+     * 关闭输入流
+     *
+     * @param closeables
+     */
+    public static void closeStream(Closeable... closeables) {
+        for (Closeable c : closeables) {
+            if (c != null) {
+                try {
+                    c.close();
+                } catch (IOException e) {
+                    e.printStackTrace();
+                }
+            }
+        }
+
+    }
+
+    /**
+     * 将富文本的表格转换为Word里面的表格
+     */
+    private static void addTable(XWPFTable xwpfTable, Element table) {
+        Elements trs = table.getElementsByTag("tr");
+        // XWPFTableRow 第0行特殊处理
+        int rownum = 0;
+        for (Element tr : trs) {
+            addTableTr(xwpfTable, tr, rownum);
+            rownum++;
+        }
+    }
+
+
+    /**
+     * 将元素里面的tr 提取到 xwpfTabel
+     */
+    private static void addTableTr(XWPFTable xwpfTable, Element tr, int rownum) {
+        Elements tds = tr.getElementsByTag("th").isEmpty() ? tr.getElementsByTag("td") : tr.getElementsByTag("th");
+        XWPFTableRow row_1 = null;
+        for (int i = 0, j = tds.size(); i < j; i++) {
+            if (0 == rownum) {
+                // XWPFTableRow 第0行特殊处理,
+                XWPFTableRow row_0 = xwpfTable.getRow(0);
+                if (i == 0) {
+                    row_0.getCell(0).setText(tds.get(i).text());
+                } else {
+                    row_0.addNewTableCell().setText(tds.get(i).text());
+                }
+            } else {
+                if (i == 0) {
+                    // 换行需要创建一个新行
+                    row_1 = xwpfTable.createRow();
+                    row_1.getCell(i).setText(tds.get(i).text());
+                } else {
+                    row_1.getCell(i).setText(tds.get(i).text());
+                }
+            }
+        }
+
+    }
+}

com.actionsoft.apps.coe.pal.datamigration/src/com/actionsoft/apps/coe/pal/datamigration/util/htmltodocx/ParagraphStyleUtil.java

@@ -0,0 +1,105 @@
+package com.actionsoft.apps.coe.pal.datamigration.util.htmltodocx;
+
+/**
+ * @author baizp
+ * @Description:
+ * @date 2022/6/24 15:57
+ */
+import org.apache.poi.xwpf.usermodel.*;
+import org.openxmlformats.schemas.wordprocessingml.x2006.main.*;
+
+import java.util.List;
+
+/**
+ * 设置文本样式工具，因为Word样式种类繁多，不能一一枚举
+ * @author corey
+ * @version 1.0
+ * @date 2020/5/5 9:36 下午
+ */
+public class ParagraphStyleUtil {
+
+    /**
+     * 段落缩进
+     * @param paragraph
+     */
+    public static void setIndentationFirstLine(XWPFParagraph paragraph){
+        paragraph.setFirstLineIndent(400);
+    }
+
+    /**
+     * 设置标题 根据富文本的tag来判断
+     * @param run
+     * @param title
+     */
+    public static void setTitle(XWPFRun run, String title){
+        // 加粗
+        run.setBold(true);
+        run.setFontSize(TitleFontEnum.getFontByTitle(title));
+    }
+
+    /**
+     * 设置单元格水平位置和垂直位置
+     *
+     * @param xwpfTable
+     * @param verticalLoction    单元格中内容垂直上TOP，下BOTTOM，居中CENTER，BOTH两端对齐
+     * @param horizontalLocation 单元格中内容水平居中center,left居左，right居右，both两端对齐
+     */
+    public static void setCellLocation(XWPFTable xwpfTable, String verticalLoction, String horizontalLocation) {
+        List<XWPFTableRow> rows = xwpfTable.getRows();
+        for (XWPFTableRow row : rows) {
+            List<XWPFTableCell> cells = row.getTableCells();
+            for (XWPFTableCell cell : cells) {
+                CTTc cttc = cell.getCTTc();
+                CTP ctp = cttc.getPList().get(0);
+                CTPPr ctppr = ctp.getPPr();
+                if (ctppr == null) {
+                    ctppr = ctp.addNewPPr();
+                }
+                CTJc ctjc = ctppr.getJc();
+                if (ctjc == null) {
+                    ctjc = ctppr.addNewJc();
+                }
+                ctjc.setVal(STJc.Enum.forString(horizontalLocation)); //水平居中
+                cell.setVerticalAlignment(XWPFTableCell.XWPFVertAlign.valueOf(verticalLoction));//垂直居中
+            }
+        }
+    }
+
+    /**
+     * 设置表格位置
+     *
+     * @param xwpfTable
+     * @param location  整个表格居中center,left居左，right居右，both两端对齐
+     */
+    public static void setTableLocation(XWPFTable xwpfTable, String location) {
+        CTTbl cttbl = xwpfTable.getCTTbl();
+        CTTblPr tblpr = cttbl.getTblPr() == null ? cttbl.addNewTblPr() : cttbl.getTblPr();
+        CTJc cTJc = tblpr.addNewJc();
+        cTJc.setVal(STJc.Enum.forString(location));
+    }
+
+    /**
+     * 设置图片居中
+     * @param xwpfParagraph
+     */
+    public static void setImageCenter(XWPFParagraph xwpfParagraph){
+        //居中
+        xwpfParagraph.setAlignment(ParagraphAlignment.CENTER);
+    }
+
+    /**
+     *居左
+     */
+    public static void AlignmentLeft(XWPFParagraph xwpfParagraph){
+        //左
+        xwpfParagraph.setAlignment(ParagraphAlignment.LEFT);
+    }
+
+    /**
+     *居右
+     */
+    public static void AlignmentRight(XWPFParagraph xwpfParagraph){
+        //右
+        xwpfParagraph.setAlignment(ParagraphAlignment.RIGHT);
+    }
+}

com.actionsoft.apps.coe.pal.datamigration/src/com/actionsoft/apps/coe/pal/datamigration/util/htmltodocx/Test.java

@@ -0,0 +1,61 @@
+package com.actionsoft.apps.coe.pal.datamigration.util.htmltodocx;
+
+import java.io.*;
+import java.util.List;
+
+/**
+ * @author baizp
+ * @Description:
+ * @date 2022/6/24 15:53
+ */
+public class Test {
+    public static void main(String[] args) {
+        //富文本转制度
+        String content = "富文本的内容";
+        StringBuffer sbf = new StringBuffer();
+        sbf.append("<html><body>");
+        sbf.append(content);
+        sbf.append("</body></html");
+        String contents = txt2String(sbf.toString());
+        byte[] result = HtmlToWord.resolveHtml(contents);
+        String plRid = UUIDGener.getUUID();
+        InputStream sbs = new ByteArrayInputStream(result);
+        new CreateMaps().updateMaps(plRid, sbs, name);
+    }
+    public static void outRichTextToDocx(String contents ,String outFilePath) {
+        String content = txt2String(contents);
+        InputStream inputStream=null;
+        OutputStream out = null;
+        try {
+            // 输入富文本内容，返回字节数组
+            byte[] result = HtmlToWord.resolveHtml(content);
+            //输出文件
+            out = new FileOutputStream(outFilePath);
+            out.write(result);
+        } catch (IOException e) {
+            e.printStackTrace();
+        } finally {
+            try {
+                out.close();
+            } catch (IOException e) {
+                e.printStackTrace();
+            }
+        }
+    }
+    /**
+     * 读取html文件的内容
+     *
+     * @param content 读取富文本
+     * @return 返回文件内容
+     */
+    public static String txt2String(String content) {
+        StringBuilder result = new StringBuilder();
+        try {
+            // 构造一个BufferedReader类来读取富文本
+            result.append(System.lineSeparator()+content);
+        } catch (Exception e) {
+            e.printStackTrace();
+        }
+        return result.toString();
+    }
+}

com.actionsoft.apps.coe.pal.datamigration/src/com/actionsoft/apps/coe/pal/datamigration/util/htmltodocx/TitleFontEnum.java

@@ -0,0 +1,38 @@
+package com.actionsoft.apps.coe.pal.datamigration.util.htmltodocx;
+
+/**
+ * @author baizp
+ * @Description:
+ * @date 2022/6/24 15:58
+ */
+public enum TitleFontEnum {
+    H1("h1", 24),
+    H2("h2", 22),
+    H3("h3", 12),
+    H7("h7",12)
+    ;
+    private String title;
+    private Integer font;
+
+    public String getTitle() {
+        return title;
+    }
+
+    public Integer getFont() {
+        return font;
+    }
+
+    TitleFontEnum(String title, Integer font) {
+        this.title = title;
+        this.font = font;
+    }
+
+    public static Integer getFontByTitle(String title){
+        for (TitleFontEnum e : TitleFontEnum.values()) {
+            if (title.equals(e.getTitle())) {
+                return e.getFont();
+            }
+        }
+        return null;
+    }
+}

com.actionsoft.apps.coe.pal.datamigration/src/com/actionsoft/apps/coe/pal/datamigration/util/htmltodocx/XWPFDocumentUtil.java

@@ -0,0 +1,41 @@
+package com.actionsoft.apps.coe.pal.datamigration.util.htmltodocx;
+
+import org.apache.poi.xwpf.usermodel.XWPFDocument;
+import org.apache.poi.xwpf.usermodel.XWPFParagraph;
+
+import java.util.List;
+import java.util.Map;
+
+/**
+ * @author baizp
+ * @Description:
+ * @date 2022/6/24 15:54
+ */
+public class XWPFDocumentUtil {
+    public static void wordInsertRitchText(XWPFDocument doc, List<Map<String, Object>> ritchtextMap) {
+        try {
+            int i = 0;
+            long beginTime = System.currentTimeMillis();
+            // 如果需要替换多份富文本，通过Map来操作，key:要替换的标记，value：要替换的富文本内容
+            for (Map<String, Object> mapList : ritchtextMap) {
+                for (Map.Entry<String, Object> entry : mapList.entrySet()) {
+                    i++;
+                    for (XWPFParagraph paragraph : doc.getParagraphs()) {
+                        if (entry.getKey().equals(paragraph.getText().trim())) {
+                            // 在标记处插入指定富文本内容
+                            HtmlUtils.resolveHtml(entry.getValue().toString(), doc, paragraph);
+                            if (i == ritchtextMap.size()) {
+                                //当导出最后一个富文本时 删除需要替换的标记
+                                doc.removeBodyElement(doc.getPosOfParagraph(paragraph));
+                            }
+                            break;
+                        }
+                    }
+
+                }
+            }
+        } catch (Exception e) {
+            e.printStackTrace();
+        }
+    }
+}