Table image extraction issue2

Aspose.Words Product Family
1

Dear team,

We are extracting images from docx but below case its getting companied 2 images with single image please refer attached source files and source code.

Source code :

if (table.getChildNodes(NodeType.SHAPE, true).getCount() > 0)
{
	// if (table.getChildNodes(NodeType.SHAPE, true).getCount() > 0 && imageCount!=eqCount && mathType.contains(false)) {
	try
	{
		while (table.getNextSibling().toString(SaveFormat.TEXT).trim().length() == 0
				&& (((Paragraph)table.getNextSibling()).getChildNodes(NodeType.SHAPE, true).getCount() == 0
						&& table.getNextSibling().getNextSibling() != null
						&& table.getNextSibling().getNextSibling().getNodeType() != NodeType.TABLE))
		{
			table.getNextSibling().remove();
		}
	}
	catch (ClassCastException e)
	{
		logger.info("ClassCastException occur, {0}", e.getMessage());
	}
	if (table.getNextSibling() != null && table.getNextSibling().getText().trim().matches(matches)
			&& !table.toString(SaveFormat.TEXT).toLowerCase().contains("fig")
			&& !table.toString(SaveFormat.TEXT).trim().contains(SCHEME))
	{
		// supplementary check
		if (AIE.supplymentryCheck(table.getNextSibling().toString(SaveFormat.TEXT).trim()))
		{
			AIE.insertBookmark(interimdoc, (Paragraph)table.getNextSibling(), AIE.fileName);
			continue;
		}
		// supplementary check

		Document tableDoc = docSetup(interimdoc, table);
		//tableDoc.save("D:\\AIE_Samples\\IssueFile\\July\\15.07.2022\\Sprint_005\\REDMINE_AIE\\#90202\\JEST_114574\\Document\\1\\a.docx");
		NodeImporter importers = new NodeImporter(interimdoc, tableDoc,
				ImportFormatMode.KEEP_SOURCE_FORMATTING);
		tableDoc.getFirstSection().getBody().appendChild(importers.importNode(table, true));

		boolean a = tableDoc.getChildNodes(NodeType.TABLE, true) != null;
		//if(a==false) {
		tableDoc.save(AIE.pdfFolder + saveAS);
		//}
		if ((table.getPreviousSibling() != null && !AIE.removeEquationShapes(tableDoc)
				&& table.getPreviousSibling().getNodeType() == NodeType.PARAGRAPH)
				|| ((Paragraph)table.getNextSibling()).getParentSection().getBody().indexOf(table) == 0)
		{
			try
			{
				AIE.imgCaption = table.getNextSibling().toString(SaveFormat.TEXT).trim();
				String saveName = AIE.formatImgcaption(AIE.imgCaption, AIE.fileName);
				//create interim work it-15
				ArrayList list = new ArrayList();
				boolean containsImage = true;
				String bookmarkname = saveName;

				Document dstDoc = tableDoc;
				Paragraph figPara = (Paragraph)table.getNextSibling();
				list.add(containsImage);
				list.add(bookmarkname);
				list.add(AIE.imgCaption);
				list.add(dstDoc);
				list.add(figPara);
				AIE.interimwork(list, interimdoc);
				//create interim work


			}
			catch (Exception e)
			{
				logger.info("Exception occurs, {0}", e.getMessage());
			}

		}
		File delete = new File(AIE.pdfFolder + saveAS);
		Files.deleteIfExists(delete.toPath());

	}
	else if (table.getPreviousSibling() != null
			&& table.getPreviousSibling().toString(SaveFormat.TEXT).trim().matches(matches)
			&& !table.toString(SaveFormat.TEXT).toLowerCase().contains("fig")
			&& !table.toString(SaveFormat.TEXT).trim().contains(SCHEME)
			&& table.getPreviousSibling().getPreviousSibling().getNodeType() != NodeType.SHAPE)
	{
		// supplementary check
		if (AIE.supplymentryCheck(table.getPreviousSibling().toString(SaveFormat.TEXT).trim()))
		{
			AIE.insertBookmark(interimdoc, (Paragraph)table.getPreviousSibling(), AIE.fileName);
			continue;
		}
		// supplementary check
		Document tableDoc = docSetup(interimdoc, table);
		NodeImporter importers = new NodeImporter(interimdoc, tableDoc,
				ImportFormatMode.KEEP_SOURCE_FORMATTING);
		tableDoc.getFirstSection().getBody().appendChild(importers.importNode(table, true));
		tableDoc.save(AIE.pdfFolder + saveAS);




		if (table.getPreviousSibling() != null && !AIE.removeEquationShapes(tableDoc)
				&& table.getPreviousSibling().getNodeType() == NodeType.PARAGRAPH)
		{
			try
			{
				AIE.imgCaption = table.getPreviousSibling().toString(SaveFormat.TEXT).trim();
				String saveName = AIE.formatImgcaption(AIE.imgCaption, AIE.fileName);
				//create interim work it-15
				ArrayList list = new ArrayList();
				boolean containsImage = true;
				String bookmarkname = saveName;
				Document dstDoc = tableDoc;
				Paragraph figPara = (Paragraph)table.getPreviousSibling();
				list.add(containsImage);
				list.add(bookmarkname);
				list.add(AIE.imgCaption);
				list.add(dstDoc);
				list.add(figPara);
				AIE.interimwork(list, interimdoc);

			}

Source File : New Microsoft Word Document.zip (2.0 MB)

Output : pdf.zip (1.1 MB)

3

@e503824 The problem occurs because your code does not properly handle shapes in nested tables:

1320×804 99.3 KB

You can use DocumentExplorer demo to inspect your document structure, that will help you to adjust the logic of your code.

It looks like logic in your code does not properly handle nested tables, that is why whole outer table is extracted including nested tables with another set of images. You should adjust the logic to skip such nested tables.
Aspose.Words in this case behaves correctly and provided access to the document model properly.

By the way, the shapes are extracted properly using the code I have provided to your colleague in this thread:
https://forum.aspose.com/t/table-image-issue/253077