Abstract:
With the progression and innovations of the Information Technology industry, computer
systems have become not only a part of an organization but the heart of it that drives their
daily routines and manages and tracks the entire business process for most enterprises and
for decades Advanced Business Languages (ABL) have been evolving to provide successful
economic solutions to drive these businesses. Progress 4GL (Fourth Generation Language) is
one such Advanced Business Language where organizations have developed entire business
process on for 30 years. However, with the advancement of Free and Open Sourced Software
providing business solutions, some organizations using these legacy systems are looking for
means of migration. Even though proprietary service providers exists for the migration
process, organizations with decades old data are reluctant to use them for both cost and
security reasons. Yet, in house development is also costly since ABL experts are very few
and would require much time and effort to complete the process.
This research project is focused on a solution to develop such expert system that can
interpret progress 4GL code to aid not only enterprises with migration but also engineers to
learn and understand the language logic with ease. With the use of the Machine Learning
technologies where research concerning modelling human thinking into machines are
popular, this thesis provides a Proof of Concept for a methodology in which, an expert
system can be created to read 4GL code, analyse the code, understand and infer the code
logic and output the workflow in a graphical Flow Chart format. The prototype is run
through several training 4GL programs to evaluate the implementation of the proposed
theory. Current application proves to be successful for code with simple syntax and leaves
room for further improvements to the system that can be enhanced to process 4GL’s many
complex and evolving constructs and also the possibility of translating to a different
language.