我一直在使用下面的脚本,该脚本是从这里的某处获取的,它查看单元格中的单词,如果有重复,则将它们放在下一列中,效果很好。
我的问题是,如果有逗号,例如看不到
大红色大,绿色大应该在下一列中显示大大,但是由于逗号而只显示其中的2个,我不想删除逗号,只需在脚本运行时将其删除
import java.io.FileOutputStream;
import org.apache.poi.xwpf.usermodel.*;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Node;
import org.jsoup.nodes.TextNode;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import org.jsoup.select.NodeVisitor;
import org.jsoup.select.NodeTraversor;
public class HTMLtoDOCX {
private XWPFDocument document;
public HTMLtoDOCX(String html, String docxPath) throws Exception {
this.document = new XWPFDocument();
XWPFParagraph paragraph = null;
Document htmlDocument = Jsoup.parse(html);
Elements htmlParagraphs = htmlDocument.select("p");
for(Element htmlParagraph : htmlParagraphs) {
System.out.println(htmlParagraph);
paragraph = document.createParagraph();
createParagraphFromHTML(paragraph, htmlParagraph);
}
FileOutputStream out = new FileOutputStream(docxPath);
document.write(out);
out.close();
document.close();
}
void createParagraphFromHTML(XWPFParagraph paragraph, Element htmlParagraph) {
ParagraphNodeVisitor nodeVisitor = new ParagraphNodeVisitor(paragraph);
NodeTraversor.traverse(nodeVisitor, htmlParagraph);
}
private class ParagraphNodeVisitor implements NodeVisitor {
String nodeName;
boolean needNewRun;
boolean isItalic;
boolean isBold;
boolean isUnderlined;
int fontSize;
String fontColor;
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";
}
@Override
public void head(Node node, int depth) {
nodeName = node.nodeName();
System.out.println("Start "+nodeName+": " + node);
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 ("u".equals(nodeName)) {
isUnderlined = true;
} else if ("br".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;
}
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);
}
@Override
public void tail(Node node, int depth) {
nodeName = node.nodeName();
System.out.println("End "+nodeName);
if ("i".equals(nodeName)) {
isItalic = false;
} else if ("b".equals(nodeName)) {
isBold = false;
} else if ("u".equals(nodeName)) {
isUnderlined = false;
} else if ("font".equals(nodeName)) {
fontColor = "000000";
fontSize = 11;
}
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);
}
}
public static void main(String[] args) throws Exception {
String html =
"<p><font size='32' color='#0000FF'><b>First paragraph.</font></b><br/>Just like a heading</p>"
+"<p>This is my text <i>which now is in italic <b>but also in bold</b> depending on its <u>importance</u></i>.<br/>Now a <b><i><u>new</u></i></b> line starts <i>within <b>the same</b> paragraph</i>.</p>"
+"<p><b>Last <u>paragraph <i>comes</u> here</b> finally</i>.</p>"
+"<p>But yet <u><i><b>another</i></u></b> paragraph having <i><font size='22' color='#FF0000'>special <u>font</u> settings</font></i>. Now default font again.</p>";
HTMLtoDOCX htmlToDOCX = new HTMLtoDOCX(html, "./CreateWordParagraphFromHTML.docx");
}
}
我不了解VBA,我尝试过类似 WordArr = Split(WS.Cells(i,1).Value,“”) WordArr = Replace(WordArr,“,”,“”)
但这会引发错误13
谁能指出我正确的方向
谢谢