Skip to content

Document understanding results

The DIS object exposes methods meant to tag/untag and give access to the results of document understanding functionalities that are going to be added soon to Studio and to text intelligence engines.
Document understanding is a separate process from disambiguation, it determines the inner structure of documents, for example it identifies the tables contained in the pages of a PDF document.
For now, those methods perform no action and they are reserved for future use. They are listed below.

Method Purpose
tagCell Tag a tables's cell
untagCell Untag a tables's cell
getTablesCount Get the count of tables that have been identified
getTable Return a table object
getTableCell Return a cell object given a table and row-column coordinates
getCell Return a cell from the sequence of the cells of all the tables
getCellText Return the text of a cell