I am able to identify the table type blocks. But how can I make them group and export them?
I am using JAVA API.
IFRDocument document = engine.CreateFRDocument();
try {
// Add image file to document
displayMessage( "Loading image..." );
IRegionsCollection reg=engine.CreateRegionsCollection();
document.AddImageFile( imagePath, null, null );
IFRPages pages=document.getPages();
IRegion region=engine.CreateRegion();
System.out.println(pages.getCount());
if (pages != null && pages.getCount() > 0)
{
for(int i=0; i<pages.getCount();i++)
{ IFRPage page=pages.Item(i);
ILayout lay_out= page.getLayout();
System.out.println(page.getLayout());
ILayoutBlocks blocks=lay_out.getBlocks();
System.out.println(lay_out.getBlocks());
System.out.println(document.getPages().Item(i).getLayout().getBlocks().getCount());
document.getPages().Item(i).getLayout().getBlocks().DeleteAll();
int c=0;
System.out.println(blocks.getCount());
if(blocks != null && blocks.getCount()>0)
{
for(int j=0;i<blocks.getCount();j++)
{ IBlock block=blocks.Item(j);
System.out.println(block.getType());
if(block.getType()==BlockTypeEnum.BT_Table)
{System.out.println(c);
ITableBlock tblock=block.GetAsTableBlock();
region=block.getRegion();
document.getPages().Item(i).getLayout().getBlocks().AddNew(block.getType(),region,c);
c++;
}
}
}
}
}
//document.ProcessPages(null,null,reg);
document.Recognize(null,null);
document.Synthesize(null);
String texExportPath = SamplesConfig.GetSamplesFolder() + "images/Emely_11111.xls";
document.Export( texExportPath, FileExportFormatEnum.FEF_XLSX, null);
}
Comments
1 comment
Hi Rama!
Please see the answer in the related topic: https://forum.ocrsdk.com/thread/tables-only-from-pdf/
Please sign in to leave a comment.