I'm using "poi-bin-3.10.1-20140818" library from http://poi.apache.org/
You can copy all paragraphs in the .docx file looping doc.getParagraphs()
But Table is not paragraph, so Table is not copied.
To copy Table, you have to get IBodyElement and looping doc.getBodyElements().
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStream;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import org.apache.xmlbeans.XmlException;
public class WordFinal {
public static void main(String[] args) throws IOException, XmlException {
XWPFDocument doc = new XWPFDocument(new FileInputStream("source.docx"));
XWPFDocument destDoc = new XWPFDocument();
OutputStream out = new FileOutputStream("Destination.docx");
// ** This code will copy just one paragraph. **
XWPFParagraph pr = doc.getParagraphs().get(0);
destDoc.createParagraph();
int pos = destDoc.getParagraphs().size() - 1;
destDoc.setParagraph(pr, pos);
destDoc.write(out);
}
}
So the code that copy all paragraphs and tables is like below.
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStream;
import org.apache.poi.xwpf.usermodel.BodyElementType;
import org.apache.poi.xwpf.usermodel.IBodyElement;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import org.apache.poi.xwpf.usermodel.XWPFTable;
import org.apache.xmlbeans.XmlException;
public class WordFinal {
public static void main(String[] args) throws IOException, XmlException {
XWPFDocument doc = new XWPFDocument(new FileInputStream("source.docx"));
XWPFDocument destDoc = new XWPFDocument();
OutputStream out = new FileOutputStream("Destination.docx");
for (IBodyElement bodyElement : doc.getBodyElements()) {
BodyElementType elementType = bodyElement.getElementType();
if (elementType.name().equals("PARAGRAPH")) {
XWPFParagraph pr = (XWPFParagraph) bodyElement;
destDoc.createParagraph();
int pos = destDoc.getParagraphs().size() - 1;
destDoc.setParagraph(pr, pos);
} else if( elementType.name().equals("TABLE") ) {
XWPFTable table = (XWPFTable) bodyElement;
destDoc.createTable();
int pos = destDoc.getTables().size() - 1;
destDoc.setTable(pos, table);
}
}
destDoc.write(out);
}
}
But even through this way, you can't copy image and style.
So copied document looks different with original document.
It seems that org.apache.poi.xwpf.usermodel.XWPFRun.addPicture() method has bug.
Docx document including image added by XWPFRun.addPicture() is not opened by Microsoft Word.
[ref.] https://issues.apache.org/bugzilla/show_bug.cgi?id=49765
Below code is including next functionality.
copy contents and styles of paragraphs and tables
copy page layout
copy images from source docx file
package com.overflow.heeseok;
import java.io.*;
import java.math.BigInteger;
import java.util.List;
import org.apache.poi.openxml4j.exceptions.InvalidFormatException;
import org.apache.poi.xwpf.usermodel.*;
import org.apache.xmlbeans.XmlException;
import org.openxmlformats.schemas.wordprocessingml.x2006.main.*;
import org.openxmlformats.schemas.wordprocessingml.x2006.main.STPageOrientation.Enum;
public class WordFinal {
public static void main(String[] args) throws IOException, XmlException
{
XWPFDocument srcDoc = new XWPFDocument(new FileInputStream("Source.docx"));
CustomXWPFDocument destDoc = new CustomXWPFDocument();
// Copy document layout.
copyLayout(srcDoc, destDoc);
OutputStream out = new FileOutputStream("Destination.docx");
for (IBodyElement bodyElement : srcDoc.getBodyElements()) {
BodyElementType elementType = bodyElement.getElementType();
if (elementType == BodyElementType.PARAGRAPH) {
XWPFParagraph srcPr = (XWPFParagraph) bodyElement;
copyStyle(srcDoc, destDoc, srcDoc.getStyles().getStyle(srcPr.getStyleID()));
boolean hasImage = false;
XWPFParagraph dstPr = destDoc.createParagraph();
// Extract image from source docx file and insert into destination docx file.
for (XWPFRun srcRun : srcPr.getRuns()) {
// You need next code when you want to call XWPFParagraph.removeRun().
dstPr.createRun();
if (srcRun.getEmbeddedPictures().size() > 0)
hasImage = true;
for (XWPFPicture pic : srcRun.getEmbeddedPictures()) {
byte[] img = pic.getPictureData().getData();
long cx = pic.getCTPicture().getSpPr().getXfrm().getExt().getCx();
long cy = pic.getCTPicture().getSpPr().getXfrm().getExt().getCy();
try {
// Working addPicture Code below...
String blipId = dstPr.getDocument().addPictureData(new ByteArrayInputStream(img),
Document.PICTURE_TYPE_PNG);
destDoc.createPictureCxCy(blipId, destDoc.getNextPicNameNumber(Document.PICTURE_TYPE_PNG),
cx, cy);
} catch (InvalidFormatException e1) {
e1.printStackTrace();
}
}
}
if (hasImage == false)
{
int pos = destDoc.getParagraphs().size() - 1;
destDoc.setParagraph(srcPr, pos);
}
} else if (elementType == BodyElementType.TABLE) {
XWPFTable table = (XWPFTable) bodyElement;
copyStyle(srcDoc, destDoc, srcDoc.getStyles().getStyle(table.getStyleID()));
destDoc.createTable();
int pos = destDoc.getTables().size() - 1;
destDoc.setTable(pos, table);
}
}
destDoc.write(out);
out.close();
}
// Copy Styles of Table and Paragraph.
private static void copyStyle(XWPFDocument srcDoc, XWPFDocument destDoc, XWPFStyle style)
{
if (destDoc == null || style == null)
return;
if (destDoc.getStyles() == null) {
destDoc.createStyles();
}
List<XWPFStyle> usedStyleList = srcDoc.getStyles().getUsedStyleList(style);
for (XWPFStyle xwpfStyle : usedStyleList) {
destDoc.getStyles().addStyle(xwpfStyle);
}
}
// Copy Page Layout.
//
// if next error message shows up, download "ooxml-schemas-1.1.jar" file and
// add it to classpath.
//
// [Error]
// The type org.openxmlformats.schemas.wordprocessingml.x2006.main.CTPageMar
// cannot be resolved.
// It is indirectly referenced from required .class files
//
// This error happens because there is no CTPageMar class in
// poi-ooxml-schemas-3.10.1-20140818.jar.
//
// [ref.] http://poi.apache.org/faq.html#faq-N10025
// [ref.] http://poi.apache.org/overview.html#components
//
// < ooxml-schemas 1.1 download >
// http://repo.maven.apache.org/maven2/org/apache/poi/ooxml-schemas/1.1/
//
private static void copyLayout(XWPFDocument srcDoc, XWPFDocument destDoc)
{
CTPageMar pgMar = srcDoc.getDocument().getBody().getSectPr().getPgMar();
BigInteger bottom = pgMar.getBottom();
BigInteger footer = pgMar.getFooter();
BigInteger gutter = pgMar.getGutter();
BigInteger header = pgMar.getHeader();
BigInteger left = pgMar.getLeft();
BigInteger right = pgMar.getRight();
BigInteger top = pgMar.getTop();
CTPageMar addNewPgMar = destDoc.getDocument().getBody().addNewSectPr().addNewPgMar();
addNewPgMar.setBottom(bottom);
addNewPgMar.setFooter(footer);
addNewPgMar.setGutter(gutter);
addNewPgMar.setHeader(header);
addNewPgMar.setLeft(left);
addNewPgMar.setRight(right);
addNewPgMar.setTop(top);
CTPageSz pgSzSrc = srcDoc.getDocument().getBody().getSectPr().getPgSz();
BigInteger code = pgSzSrc.getCode();
BigInteger h = pgSzSrc.getH();
Enum orient = pgSzSrc.getOrient();
BigInteger w = pgSzSrc.getW();
CTPageSz addNewPgSz = destDoc.getDocument().getBody().addNewSectPr().addNewPgSz();
addNewPgSz.setCode(code);
addNewPgSz.setH(h);
addNewPgSz.setOrient(orient);
addNewPgSz.setW(w);
}
}
And CustomXWPFDocument class source.
package com.overflow.heeseok;
import java.io.IOException;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.xmlbeans.*;
import org.openxmlformats.schemas.drawingml.x2006.main.*;
import org.openxmlformats.schemas.drawingml.x2006.wordprocessingDrawing.CTInline;
/**
* [ref] https://issues.apache.org/bugzilla/show_bug.cgi?id=49765
* [ref] http://pastebin.com/index/CbQ3iw8t, http://pastebin.com/2YAneYgt
*/
public class CustomXWPFDocument extends XWPFDocument
{
public CustomXWPFDocument() throws IOException
{
super();
}
public void createPictureCxCy(String blipId,int id, long cx, long cy)
{
CTInline inline = createParagraph().createRun().getCTR().addNewDrawing().addNewInline();
String picXml = "" +
"<a:graphic xmlns:a="http://schemas.openxmlformats.org/drawingml/2006/main">" +
" <a:graphicData uri="http://schemas.openxmlformats.org/drawingml/2006/picture">" +
" <pic:pic xmlns:pic="http://schemas.openxmlformats.org/drawingml/2006/picture">" +
" <pic:nvPicPr>" +
" <pic:cNvPr id="" + id + "" name="Generated"/>" +
" <pic:cNvPicPr/>" +
" </pic:nvPicPr>" +
" <pic:blipFill>" +
" <a:blip r:embed="" + blipId + "" xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships"/>" +
" <a:stretch>" +
" <a:fillRect/>" +
" </a:stretch>" +
" </pic:blipFill>" +
" <pic:spPr>" +
" <a
