Dear team,
We are extracting images from docx using aspose java, but we are facing below issue please refer input and output, And we are using below source code
Source Code :
public static void textFrameImageWithCaption(Document interimdoc) throws Exception{
try {
Document doc = interimdoc;
if (!AIE.supplementaryFigure) {
ImageExtractor extractor = new ImageExtractor(AIE.pdfFolder,doc);
doc.accept(extractor);
extractor.RemoveImagesFromSourceDocument();
doc.save(AIE.interim);
}
}
catch(Exception e) {
logger.info(e.getMessage());
}
}
}
class ImageExtractor extends DocumentVisitor {
public ImageExtractor(String targetFolder, Document doc) {
mTargetFolder = targetFolder;
sourceDoc=doc;
}
/**
* Removes images from the source document and inserts bookmark at the image position.
*/
public void RemoveImagesFromSourceDocument()
{
try {
for (String key : mNodesToRemove.keySet())
{
Node nodeToRemove = mNodesToRemove.get(key);
DocumentBuilder builder = new DocumentBuilder((Document)nodeToRemove.getDocument());
// In case of table move cursor to the next paragraph.
if (nodeToRemove.getNodeType() == NodeType.TABLE)
builder.moveTo(nodeToRemove.getNextSibling());
else
builder.moveTo(nodeToRemove);
// Insert bookmark.
/*builder.startBookmark(key);
builder.endBookmark(key);*/
// Remove image node.
nodeToRemove.remove();
}}
catch(Exception e){logger.info(e.getMessage());}
}
@Override
public int visitRowStart(Row row) throws Exception {
if(row.getChildNodes(NodeType.SHAPE, true).getCount()>0)
mRows.push(row);
return super.visitRowStart(row);
}
@Override
public int visitGroupShapeStart(GroupShape groupShape) throws Exception {
if (groupShape.isTopLevel())
mTopShapes.push(groupShape);
saveShapeAsPdf();
return super.visitGroupShapeStart(groupShape);
}
@Override
public int visitShapeStart(Shape shape) throws Exception {
if (shape.isTopLevel() &&
shape.getChildNodes(NodeType.PARAGRAPH, true).getCount() == 0 && !FixedGraphic.isOleEquation(shape)) {
mTopShapes.push(shape);
}
saveShapeAsPdf();
return super.visitShapeStart(shape);
}
@Override
public int visitParagraphStart(Paragraph paragraph) throws Exception {
if (isCaptionParagraph(paragraph))
mCaptions.push(paragraph.toString(SaveFormat.TEXT).trim());
saveShapeAsPdf();
return super.visitParagraphStart(paragraph);
}
/**
* Checks whether paragraph is likely to be an image caption.
*/
private static boolean isCaptionParagraph(Paragraph paragraph) throws Exception {
// Get only Run text in account because if caption is in a textbox
// paragraph.toString will return the same value for both
// paragraph inside textbox shape and for paragraph that contains textbox shape.
// Some captions are in textboxes.
boolean isInshape = paragraph.getAncestor(NodeType.SHAPE)!=null;
// Some caption are marked as bold
boolean isBold = false;
// More conditions might be added here to better distinguish captions.
// .........
String paraText = "";
for (Run r : paragraph.getRuns()) {
paraText += r.getText();
isBold |= r.getFont().getBold();
}
return (isInshape || isBold) && (paraText.startsWith("Fig") ||
paraText.startsWith("Scheme") ||
paraText.startsWith("Plate") ||
paraText.startsWith("Figure")) && !paraText.contains(AIE.docName) && !paraText.toLowerCase().startsWith("figs") && !paraText.toLowerCase().startsWith("figures");
}
/**
* Save the last shape as a separate PDF document.
*/
private void saveShapeAsPdf() throws Exception {
try {
if (!mTopShapes.empty() && !mCaptions.empty()) {
String caption = mCaptions.pop();
Node imageNode = mTopShapes.peek();
if(imageNode.getParentNode().getChildNodes(NodeType.TABLE, true) != null) {
// Create e temporary document which will be exported to PDF.
Document tmp = (Document) imageNode.getDocument().deepClone(false);
Node tmpSection = tmp.importNode(imageNode.getAncestor(NodeType.SECTION), false, ImportFormatMode.USE_DESTINATION_STYLES);
tmp.appendChild(tmpSection);
tmp.ensureMinimum();
if(mTopShapes.size() > 1 && !mRows.isEmpty())
{
Table imagesTable = (Table)mRows.peek().getParentTable().deepClone(false);
while (!mRows.isEmpty())
imagesTable.prependChild(mRows.pop().deepClone(true));
imageNode = imagesTable;
}
Node resultImage = tmp.importNode(imageNode, true, ImportFormatMode.USE_DESTINATION_STYLES);
if(resultImage.getNodeType() == NodeType.TABLE)
tmp.getFirstSection().getBody().prependChild(resultImage);
else
tmp.getFirstSection().getBody().getFirstParagraph().appendChild(resultImage);
if(resultImage.isComposite()) {
resultImage.getRange().unlinkFields();
//((CompositeNode) resultImage).getChildNodes(NodeType.RUN, true).clear();
Iterable<Paragraph> paragraphs = ((CompositeNode) resultImage).getChildNodes(NodeType.PARAGRAPH, true);
for (Paragraph p : paragraphs)
{
if(isCaptionParagraph(p))
p.remove();
}
}
//System.out.println("caption: "+caption);
String bookmarkname = AIE.formatImgcaption(caption, AIE.fileName);
String newBookmarkName=bookmarkname.substring(bookmarkname.lastIndexOf('_') + 1);
// Format the output file path.
String outFilePath = mTargetFolder +newBookmarkName + ".pdf";
File f = new File(outFilePath);
if(!f.exists()) {
PdfSaveOptions opts = new PdfSaveOptions();
opts.getDownsampleOptions().setDownsampleImages(false);
opts.setCompliance(PdfCompliance.PDF_A_1_B);
tmp.save(outFilePath);
Paragraph pa=(Paragraph) imageNode.getParentNode();
AIE.insertBookmark(sourceDoc, pa, bookmarkname);
mNodesToRemove.put(newBookmarkName, imageNode);
//imageNode.remove();
AIE.configurationWork(bookmarkname, tmp, outFilePath);
}
mShapeCounter++;
// Empty stacks.
mTopShapes.clear();
mRows.clear();
mCaptions.clear();
}
}
}
catch(Exception e) {
logger.info(e.getMessage());
}
}
// Upon visiting the shapes captions and shapes are pushed in stack.
// only top level shapes will be collected.
private Stack<ShapeBase> mTopShapes = new Stack<ShapeBase>();
private Stack<Row> mRows = new Stack<Row>();
private Stack<String> mCaptions = new Stack<String>();
private int mShapeCounter = 0;
private String mTargetFolder;
private Document sourceDoc;
HashMap<String, Node> mNodesToRemove = new HashMap<String, Node>();
private static org.apache.logging.log4j.Logger logger = LogManager.getLogger(TextFrameImage.class);
}
input and output : New folder.zip (781.6 KB)
@e503824 I cannot reproduce the problem with my implementation of ImageExtractor:
Document doc = new Document("C:\\Temp\\in.docx");
doc.updateListLabels();
ImageExtractor extractor = new ImageExtractor("C:\\Temp\\");
doc.accept(extractor);
private static class ImageExtractor extends DocumentVisitor {
public ImageExtractor(String targetFolder) {
mTargetFolder = targetFolder;
}
@Override
public int visitRowStart(Row row) throws Exception {
if(rowHasImage(row))
mRows.push(row);
return super.visitRowStart(row);
}
@Override
public int visitGroupShapeStart(GroupShape groupShape) throws Exception {
if (groupShape.isTopLevel())
mTopShapes.push(groupShape);
saveShapeAsPdf();
return super.visitGroupShapeStart(groupShape);
}
@Override
public int visitShapeStart(Shape shape) throws Exception {
if (shape.isTopLevel() &&
(shape.getChildNodes(NodeType.PARAGRAPH, true).getCount() == 0) &&
!isOleEquation(shape)) {
mTopShapes.push(shape);
}
saveShapeAsPdf();
return super.visitShapeStart(shape);
}
@Override
public int visitParagraphStart(Paragraph paragraph) throws Exception {
if (isCaptionParagraph(paragraph)) {
mCaptions.push(paragraph.toString(SaveFormat.TEXT).trim());
saveShapeAsPdf();
return VisitorAction.SKIP_THIS_NODE;
}
return super.visitParagraphStart(paragraph);
}
/**
* Removes images from the source document and inserts bookmark at the image position.
*/
public void RemoveImagesFromSourceDocument()
{
for (String key : mNodesToRemove.keySet()) {
ArrayList<Node> nodesToRemove = mNodesToRemove.get(key);
if(nodesToRemove.size() == 0)
continue;
Node firstNode = nodesToRemove.get(0);
DocumentBuilder builder = new DocumentBuilder((Document)firstNode.getDocument());
// In case of table move cursor to the next paragraph.
if(firstNode.getNodeType() == NodeType.TABLE)
builder.moveTo(firstNode.getNextSibling());
else
builder.moveTo(firstNode);
// Insert bookmark.
builder.startBookmark(key);
builder.endBookmark(key);
// Remove all image nodes.
for (Node n : nodesToRemove) {
n.remove();
}
}
}
/**
* Checks whether row has shapes except formulas.
*/
private static boolean rowHasImage(Row row)
{
NodeCollection shapes = row.getChildNodes(NodeType.SHAPE, true);
if(shapes.getCount() == 0)
return false;
boolean hasImage = false;
for (Shape s : (Iterable<Shape>)shapes) {
hasImage |= !isOleEquation(s);
}
return hasImage;
}
/**
* Checks whether paragraph is likely to be an image caption.
*/
private static boolean isCaptionParagraph(Paragraph paragraph) throws Exception {
// Get only Run text in account because if caption is in a textbox
// paragraph.toString will return the same value for both
// paragraph inside textbox shape and for paragraph that contains textbox shape.
// Caption often contain SEQ fields.
boolean hasSeqFields = false;
for (Field f : paragraph.getRange().getFields())
hasSeqFields |= (f.getType() == FieldType.FIELD_SEQUENCE);
// More conditions might be added here to better distinguish captions.
// .........
String paraText = paragraph.isListItem() ? paragraph.getListLabel().getLabelString() : "";
for (Run r : paragraph.getRuns()) {
paraText += r.getText();
}
boolean hasCaptionLikeContent = (paraText.startsWith("Fig") ||
paraText.startsWith("Scheme") ||
paraText.startsWith("Plate") ||
paraText.startsWith("Figure") ||
paraText.startsWith("Flowchart"));
return (hasSeqFields || hasCaptionLikeContent) && (paraText.length()<200);
}
/**
* Check whether shape is an embedded Equation.DSMT4 OLE object
*/
private static boolean isOleEquation(Shape shape)
{
return (shape.getOleFormat() != null) && (shape.getOleFormat().getProgId().equals("Equation.DSMT4"));
}
/**
* Save the last shape as a separate PDF document.
*/
private void saveShapeAsPdf() throws Exception {
if (!mTopShapes.empty() && !mCaptions.empty()) {
String caption = mCaptions.pop();
System.out.println(mShapeCounter);
System.out.println(caption);
// Create e temporary document which will be exported to PDF.
Document tmp = (Document) mTopShapes.peek().getDocument().deepClone(false);
Node tmpSection = tmp.importNode(mTopShapes.peek().getAncestor(NodeType.SECTION), false, ImportFormatMode.USE_DESTINATION_STYLES);
tmp.appendChild(tmpSection);
tmp.ensureMinimum();
// There might be several shape to import under one caption.
ArrayList<Node> nodesToImport = new ArrayList<Node>();
if(mTopShapes.size() > 1 && !mRows.isEmpty())
{
Table imagesTable = (Table)mRows.peek().getParentTable().deepClone(false);
while (!mRows.isEmpty()) {
Row r = mRows.pop();
imagesTable.prependChild(r.deepClone(true));
}
nodesToImport.add(imagesTable);
}
else
{
while (!mTopShapes.isEmpty()) {
ShapeBase s = mTopShapes.pop();
nodesToImport.add(s);
}
}
String key = "image_" + mShapeCounter;
mNodesToRemove.put(key, nodesToImport);
for (Node imageNode : nodesToImport) {
Node resultImage = tmp.importNode(imageNode, true, ImportFormatMode.USE_DESTINATION_STYLES);
if (resultImage.isComposite()) {
resultImage.getRange().unlinkFields();
Iterable<Paragraph> paragraphs = ((CompositeNode) resultImage).getChildNodes(NodeType.PARAGRAPH, true);
for (Paragraph p : paragraphs)
{
if(isCaptionParagraph(p))
p.remove();
}
//((CompositeNode) resultImage).getChildNodes(NodeType.RUN, true).clear();
}
if (resultImage.getNodeType() == NodeType.TABLE)
tmp.getFirstSection().getBody().prependChild(resultImage);
else
tmp.getFirstSection().getBody().getFirstParagraph().prependChild(resultImage);
}
// Format the output file path.
String outFilePath = mTargetFolder + key + ".pdf";
tmp.save(outFilePath);
mShapeCounter++;
// Empty stacks.
mTopShapes.clear();
mRows.clear();
mCaptions.clear();
}
}
// Upon visiting the shapes captions and shapes are pushed in stack.
// only top level shapes will be collected.
private Stack<ShapeBase> mTopShapes = new Stack<ShapeBase>();
private Stack<Row> mRows = new Stack<Row>();
private Stack<String> mCaptions = new Stack<String>();
private int mShapeCounter = 0;
private String mTargetFolder;
// Dictionary with nodes that should be deleted and replaced with bookmark.
HashMap<String, ArrayList<Node>> mNodesToRemove = new HashMap<String, ArrayList<Node>>();
}
Dear team,
Still we are facing same issue please find below source code and File
public void RemoveImagesFromSourceDocument()
{
try {
for (String key : mNodesToRemove.keySet())
{
Node nodeToRemove = mNodesToRemove.get(key);
DocumentBuilder builder = new DocumentBuilder((Document)nodeToRemove.getDocument());
// In case of table move cursor to the next paragraph.
if (nodeToRemove.getNodeType() == NodeType.TABLE)
builder.moveTo(nodeToRemove.getNextSibling());
else
builder.moveTo(nodeToRemove);
// Insert bookmark.
/*builder.startBookmark(key);
builder.endBookmark(key);*/
// Remove image node.
nodeToRemove.remove();
}}
catch(Exception e){logger.info(e.getMessage());}
}
@Override
public int visitRowStart(Row row) throws Exception {
if(rowHasImage(row))
mRows.push(row);
return super.visitRowStart(row);
}
@Override
public int visitGroupShapeStart(GroupShape groupShape) throws Exception {
if (groupShape.isTopLevel())
mTopShapes.push(groupShape);
saveShapeAsPdf();
return super.visitGroupShapeStart(groupShape);
}
@Override
public int visitShapeStart(Shape shape) throws Exception {
if (shape.isTopLevel() &&
shape.getChildNodes(NodeType.PARAGRAPH, true).getCount() == 0 && !FixedGraphic.isOleEquation(shape)) {
mTopShapes.push(shape);
}
saveShapeAsPdf();
return super.visitShapeStart(shape);
}
@Override
public int visitParagraphStart(Paragraph paragraph) throws Exception {
if (isCaptionParagraph(paragraph))
mCaptions.push(paragraph.toString(SaveFormat.TEXT).trim());
saveShapeAsPdf();
return super.visitParagraphStart(paragraph);
}
/**
* Checks whether paragraph is likely to be an image caption.
*/
private static boolean isCaptionParagraph(Paragraph paragraph) throws Exception {
// Get only Run text in account because if caption is in a textbox
// paragraph.toString will return the same value for both
// paragraph inside textbox shape and for paragraph that contains textbox shape.
// Some captions are in textboxes.
boolean isInshape = paragraph.getAncestor(NodeType.SHAPE)!=null;
// Some caption are marked as bold
boolean isBold = false;
// More conditions might be added here to better distinguish captions.
// .........
String paraText = "";
for (Run r : paragraph.getRuns()) {
paraText += r.getText();
isBold |= r.getFont().getBold();
}
return (isInshape || isBold) && (paraText.startsWith("Fig") ||
paraText.startsWith("Scheme") ||
paraText.startsWith("Plate") ||
paraText.startsWith("Figure")) && !paraText.contains(AIE.docName) && !paraText.toLowerCase().startsWith("figs") && !paraText.toLowerCase().startsWith("figures");
}
private static boolean rowHasImage(Row row)
{
NodeCollection shapes = row.getChildNodes(NodeType.SHAPE, true);
if(shapes.getCount() == 0)
return false;
boolean hasImage = false;
for (Shape s : (Iterable<Shape>)shapes) {
hasImage |= !isOleEquation(s);
}
return hasImage;
}
private static boolean isOleEquation(Shape shape)
{
return (shape.getOleFormat() != null) && (shape.getOleFormat().getProgId().equals("Equation.DSMT4"));
}
/**
* Save the last shape as a separate PDF document.
*/
private void saveShapeAsPdf() throws Exception {
try {
if (!mTopShapes.empty() && !mCaptions.empty()) {
String caption = mCaptions.pop();
Node imageNode = mTopShapes.peek();
if(imageNode.getParentNode().getChildNodes(NodeType.TABLE, true) != null) {
// Create e temporary document which will be exported to PDF.
Document tmp = (Document) imageNode.getDocument().deepClone(false);
Node tmpSection = tmp.importNode(imageNode.getAncestor(NodeType.SECTION), false, ImportFormatMode.USE_DESTINATION_STYLES);
tmp.appendChild(tmpSection);
tmp.ensureMinimum();
if(mTopShapes.size() > 1 && !mRows.isEmpty())
{
Table imagesTable = (Table)mRows.peek().getParentTable().deepClone(false);
while (!mRows.isEmpty())
imagesTable.prependChild(mRows.pop().deepClone(true));
imageNode = imagesTable;
}
Node resultImage = tmp.importNode(imageNode, true, ImportFormatMode.USE_DESTINATION_STYLES);
if(resultImage.getNodeType() == NodeType.TABLE)
tmp.getFirstSection().getBody().prependChild(resultImage);
else
tmp.getFirstSection().getBody().getFirstParagraph().appendChild(resultImage);
if(resultImage.isComposite()) {
resultImage.getRange().unlinkFields();
//((CompositeNode) resultImage).getChildNodes(NodeType.RUN, true).clear();
Iterable<Paragraph> paragraphs = ((CompositeNode) resultImage).getChildNodes(NodeType.PARAGRAPH, true);
for (Paragraph p : paragraphs)
{
if(isCaptionParagraph(p))
p.remove();
}
}
//System.out.println("caption: "+caption);
String bookmarkname = AIE.formatImgcaption(caption, AIE.fileName);
String newBookmarkName=bookmarkname.substring(bookmarkname.lastIndexOf('_') + 1);
// Format the output file path.
String outFilePath = mTargetFolder +newBookmarkName + ".pdf";
File f = new File(outFilePath);
if(!f.exists()) {
PdfSaveOptions opts = new PdfSaveOptions();
opts.getDownsampleOptions().setDownsampleImages(false);
opts.setCompliance(PdfCompliance.PDF_A_1_B);
tmp.save(outFilePath);
Paragraph pa=(Paragraph) imageNode.getParentNode();
AIE.insertBookmark(sourceDoc, pa, bookmarkname);
mNodesToRemove.put(newBookmarkName, imageNode);
//imageNode.remove();
AIE.configurationWork(bookmarkname, tmp, outFilePath);
}
mShapeCounter++;
// Empty stacks.
mTopShapes.clear();
mRows.clear();
mCaptions.clear();
}
}
}
catch(Exception e) {
logger.info(e.getMessage());
}
}
// Upon visiting the shapes captions and shapes are pushed in stack.
// only top level shapes will be collected.
private Stack<ShapeBase> mTopShapes = new Stack<ShapeBase>();
private Stack<Row> mRows = new Stack<Row>();
private Stack<String> mCaptions = new Stack<String>();
private int mShapeCounter = 0;
private String mTargetFolder;
private Document sourceDoc;
HashMap<String, Node> mNodesToRemove = new HashMap<String, Node>();
private static org.apache.logging.log4j.Logger logger = LogManager.getLogger(TextFrameImage.class);
}
New folder.zip (784.2 KB)
@e503824 Please try using the implementation I have provided in my previous answer. As I mentioned I cannot preproduce the problem with my implementation. Here is output produced on my side: image_0.pdf (149.1 KB)
image_1.pdf (762.2 KB)