Dear team,
We are extracting images from document, now we need to extract extract images from double column layout please find sample document and please provide source code and Extracted files
Input : manuscript(clean version) - without author.docx (9.6 MB)
@e503824 The code for extraction images is the same. In this case the problem is that by default paragraph has exact line spacing and inline image is truncated. You can reset line spacing to get the correction output. Here is the modified code of ImageExtractor:
public class ImageExtractor extends DocumentVisitor {
public ImageExtractor(String targetFolder) {
mTargetFolder = targetFolder;
}
@Override
public int visitTableStart(Table table) throws Exception {
// If table has two rows and each row has the same number of cells
// and there is a caption paragraph in the last row - do special processing.
if((table.getRows().getCount() == 2) &&
(table.getFirstRow().getCells().getCount() == table.getLastRow().getCells().getCount()) &&
isCaptionParagraph(table.getLastRow().getFirstCell().getFirstParagraph()))
{
for(int i=0; i<table.getFirstRow().getCells().getCount(); i++)
{
Cell firstRowCell = table.getFirstRow().getCells().get(i);
Cell lastRowCell = table.getLastRow().getCells().get(i);
Shape shape = (Shape)firstRowCell.getChild(NodeType.SHAPE, 0, true);
if(shape!=null && shape.isTopLevel())
mTopShapes.push(shape);
if(isCaptionParagraph(lastRowCell.getFirstParagraph()))
mCaptions.push(lastRowCell.getFirstParagraph().toString(SaveFormat.TEXT).trim());
saveShapeAsPdf();
}
return VisitorAction.SKIP_THIS_NODE;
}
return VisitorAction.CONTINUE;
}
@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();
tmp.getFirstSection().getBody().getFirstParagraph().getParagraphFormat().setLineSpacingRule(LineSpacingRule.AT_LEAST);
// 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.
int captionLength = caption.length() > 40 ? 40 : caption.length();
String outFilePath = mTargetFolder + caption.substring(0, captionLength) + ".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>>();
}