Cannot bring all the element from html to docx that have same tag with java -
i have project converting html docx java, in html document have 2 paragraph 2 header title, when converting both of them docx format, 1 paragraph converted, other paragraph doesn't converted have same tag. image below

and code this
import java.io.file; import java.io.fileoutputstream; import java.util.list; import java.util.set; import static org.apache.poi.hslf.model.textproperties.textpropcollection.textproptype.paragraph; import org.apache.poi.openxml4j.opc.opcpackage; 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.zwobble.mammoth.documentconverter; import org.zwobble.mammoth.result; /** * * @author alwan */ public class testword { /** * @param args command line arguments */ public static void main(string[] args) { // todo code application logic here try { file file = new file("src/test/test.docx"); documentconverter converter = new documentconverter(); result<string> result = converter.extractrawtext(file); string html = result.getvalue(); // generated html set<string> warnings = result.getwarnings(); // warnings during conversion string[] part = html.split("<p>"); string[] part2 = html.split("<h1>"); fileoutputstream out = new fileoutputstream(new file("testformat.docx")); xwpfdocument doc = new xwpfdocument(); xwpfparagraph paragraph = doc.createparagraph(); xwpfrun paragraphonerunone = paragraph.createrun(); xwpfrun paragraphonerunthree = paragraph.createrun(); (int = 0; < html.length(); i++) { if (i % 2 != 0) { paragraphonerunone.setbold(true); paragraphonerunone.setitalic(true); paragraphonerunone.settext(part[i].trim()); paragraphonerunone.addbreak(); paragraphonerunthree.setstrike(true); paragraphonerunthree.setfontsize(20); paragraphonerunthree.setsubscript(verticalalign.subscript); paragraphonerunthree.settext(part2[i].trim()); system.out.println(part2[i].trim()); system.out.println(part[i].trim()); doc.write(out); out.close(); } system.out.println("testformat.docx written successully"); } system.out.println("success"); } catch(exception e) { e.printstacktrace(); } } } the question is, how bring paragraph html docx format when have same tag? thank attention before. sorry bad english
Comments
Post a Comment