APACH POI แยกวิเคราะห์ HTML ด้วย JSOUP

การแยกวิเคราะห์ข้อความ HTML ที่มีแท็ก ‹font› จะไม่รีเซ็ตขนาดและแบบอักษรของครอบครัวหลังจาก ‹/font›

รหัสของฉันทำงานได้ค่อนข้างดี ยกเว้นหลัง ‹/font›

ก่อน ‹font size=9› blablabla.. ขนาดตัวอักษรคือ 11 ฉันคาดหวังว่าหลังจาก ‹/font› ขนาดตัวอักษรจะถูกรีเซ็ตเป็น 11 แต่ยังคงอยู่ที่ 9 สิ่งเดียวกันสำหรับตระกูลฟอนต์

แน่นอนว่าฉันเข้าใจผิดว่าจะใช้ jsoup อย่างไร ฉันควรใช้ CSS ดีกว่า แต่ฉันไม่รู้ว่าต้องทำอย่างไร

ขอบคุณที่ช่วยเหลือ.

package test;
import java.awt.Color;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.math.BigInteger;
import org.apache.poi.xwpf.usermodel.UnderlinePatterns;
import org.apache.poi.xwpf.usermodel.VerticalAlign;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
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;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.nodes.Node;
import org.jsoup.nodes.TextNode;
import org.jsoup.select.Elements;
import org.jsoup.select.NodeTraversor;
import org.jsoup.select.NodeVisitor;
import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTTblLayoutType;
import org.openxmlformats.schemas.wordprocessingml.x2006.main.STTblLayoutType;

public class ReadHtml 
{
    protected static java.util.Vector<String> contenu = null;
    org.apache.xmlbeans.XmlCursor cursor = null;

   class WStyle
   {
      protected  String  police     =   "Times New Roman";
      protected  int     taille     =   11;
      protected  Color   couleur    =   Color.black;
      protected  boolean gras       =   false;
      protected  boolean italique   =   false;

      public WStyle() // constructeur
      {
          super();
      }

      protected String getPolice()      {return  police;}
      protected int getTaille()         {return  taille;}
      protected Color getCouleur()      {return  couleur;}
      protected boolean getGras()       {return  gras;}  
      protected boolean getItalique()   {return  italique;} 

      protected void    setPolice(String p)     {police=p;}
      protected void    setTaille(int t)        {taille=t;}
      protected void    setCouleur(Color c)     {couleur=c;}
      protected void    setGras(boolean g)      {gras=g;}  
      protected void    setItalique(boolean i)  {italique=i;} 
   }

    public ReadHtml()
    {
        super();
        contenu =  new java.util.Vector<String>();
        createWordFile();

    }



    private  XWPFParagraph getTableParagraph(XWPFTableCell  cell,  String html)
    {
            cell.removeParagraph(0);
            XWPFParagraph paragraph = cell.addParagraph();
            paragraph.setSpacingAfterLines(0);
            paragraph.setSpacingAfter(0);

            Document htmlDocument = Jsoup.parse(html);
            Elements htmlParagraphs = htmlDocument.select("p");
            for(Element htmlParagraph : htmlParagraphs) 
            {
                  System.out.println(htmlParagraph);
                  ParagraphNodeVisitor nodeVisitor = new ParagraphNodeVisitor(paragraph);
                  NodeTraversor.traverse(nodeVisitor, htmlParagraph);
            }
            return paragraph;
    }

    private   void createWordFile()
    {
          XWPFParagraph para =  null;
          try
          {
                XWPFDocument document = new XWPFDocument();
                FileOutputStream out = new FileOutputStream(new File("./", "NewTable.docx"));

                XWPFTable table = document.createTable();
                CTTblLayoutType type = table.getCTTbl().getTblPr().addNewTblLayout();
                type.setType(STTblLayoutType.FIXED);
                table.getCTTbl().addNewTblGrid().addNewGridCol().setW(BigInteger.valueOf(1670));
                table.getCTTbl().getTblGrid().addNewGridCol().setW(BigInteger.valueOf(6000));

                String myTexte =    "<html><head</head><body><p><font face=\"Verdana\" size=11>Good Morning</font>  <font size=9 face=\"Times\"> " +
                                    "<i><b>how are you today </b></i></font> Not so bad.<br>Thanks";  


                // first  line
                XWPFTableRow tableRow= table.getRow(0);
                para = getTableParagraph(tableRow.getCell(0),  "<p>Row #1,  Col. #1");
                tableRow .getCell(0).setParagraph(para);
                XWPFTableCell cell = tableRow.createCell(); 
                para = getTableParagraph(cell,  myTexte);  // Row #1,  Col. #2
                tableRow .getCell(1).setParagraph(para);

                // seconde line
                tableRow= table.createRow();
                para = getTableParagraph(tableRow.getCell(0),  "<p>Row #2,  Col. #1");
                tableRow .getCell(0).setParagraph(para);
                para = getTableParagraph(tableRow.getCell(1),  "<p>Row #2,  Col. #2");
                tableRow.getCell(1).setParagraph(para);

                document.write(out);
                document.close();
                out.close();
                System.out.println("NewTable.docx written successully");
          } 
          catch (FileNotFoundException e) {System.out.println("File exception --> "  + e.toString()); } 
          catch (IOException e) {System.out.println("I/O exception --> "  + e.toString()); }  
          catch (Exception e)  {System.out.println("Other exception --> "  + e.toString()); } 
    } 

    public class ParagraphNodeVisitor implements NodeVisitor 
    {
          String nodeName;
          String fontFace;
          String fontType;
          boolean needNewRun;
          boolean isItalic;
          boolean isBold;
          boolean isUnderlined;
          int fontSize;
          String fontColor;
          VerticalAlign align = VerticalAlign.BASELINE ;
          XWPFParagraph paragraph;
          XWPFRun run;

          ParagraphNodeVisitor(XWPFParagraph paragraph) 
          {
               this.paragraph = paragraph;
               this.run = paragraph.createRun();
               this.nodeName = "";
               this.needNewRun = false;
               this.isItalic = false;
               this.isBold = false;
               this.isUnderlined = false;
               this.fontSize = 11;
               this.fontColor = "000000";
               this.fontFace="Times";
          }

          @Override
          public void head(Node node, int depth) 
          {
              nodeName = node.nodeName();
              needNewRun = false;
              if ("#text".equals(nodeName)) 
              {
                  run.setText(((TextNode)node).text());
                  needNewRun = true; //after setting the text in the run a new run is needed
              } 
              else if ("i".equals(nodeName)) {isItalic = true;} 
              else if ("b".equals(nodeName)) {isBold = true;} 
              else if ("sup".equals(nodeName)){align = VerticalAlign.SUPERSCRIPT ;} 
              else if ("u".equals(nodeName)) {isUnderlined = true;} 
              else if ("br".equals(nodeName)) {run.addBreak();} 
              else if ("p".equals(nodeName)) {run.addBreak();} 
              else if ("font".equals(nodeName)) 
              {
                  fontColor = (!"".equals(node.attr("color")))?node.attr("color").substring(1):"000000";
                  fontSize = (!"".equals(node.attr("size")))?Integer.parseInt(node.attr("size")):11;
                  fontFace = (!"".equals(node.attr("face")))?node.attr("face"):"Times";
              } 
              if (needNewRun) run = paragraph.createRun();
              needNewRun = false;
              run.setItalic(isItalic);
              run.setBold(isBold);
              if (isUnderlined) run.setUnderline(UnderlinePatterns.SINGLE); 
              else run.setUnderline(UnderlinePatterns.NONE);
              run.setColor(fontColor); 
              run.setFontSize(fontSize);
              run.setFontFamily(fontFace);
              run.setSubscript(align);
          }

          @Override
          public void tail(Node node, int depth) 
          {

              nodeName = node.nodeName();
              System.out.println("Node=" + nodeName);
              if ("i".equals(nodeName)) {isItalic = false;} 
              else if ("b".equals(nodeName)) {isBold = false;} 
              else if ("u".equals(nodeName)) {isUnderlined = false;} 
              else if ("sup".equals(nodeName)) {align= VerticalAlign.BASELINE ;}
              else if ("font".equals("nodeName")) 
              {
                  fontColor = "000000";
                  fontSize = 11;
                  fontFace="Times";
                  System.out.println("Family=" + fontFace + "   Taille=" + fontSize);
              }

              if (needNewRun) run = paragraph.createRun();
               needNewRun = false;
               run.setItalic(isItalic);
               run.setBold(isBold);
               if (isUnderlined) run.setUnderline(UnderlinePatterns.SINGLE); else run.setUnderline(UnderlinePatterns.NONE);
               run.setColor(fontColor); 
               run.setFontSize(fontSize);

               run.setFontFamily(fontFace);
               run.setSubscript(align);
          }
    }
    public static void main(String[] args) 
    {
              new ReadHtml() ;
    } 
}