r-orderanalyzer

Functions for extracting text and tables from PDF-based order documents. It provides an n-gram-based approach for identifying the language of an order document. It furthermore uses R-package 'pdftools' to extract the text from an order document. In the case that the PDF document is only including an image (because it is scanned document), R package 'tesseract' is used for OCR. Furthermore, the package provides functionality for identifying and extracting order position tables in order documents based on a clustering approach.