Model-driven development (MDD) significantly improves web development by generating source code from models at higher abstraction levels, which enhances productivity and enables shorter, less expensive development cycles. However, not all aspects of a web application can be captured in a model, necessitating manual changes to the generated code. To prevent the loss of manual changes due to subsequent code generation, various strategies are recommended in the literature: keeping handwritten and generated code in separate files, utilizing protected regions, or employing a version control system (VCS) to merge handwritten and generated code. Unfortunately, these approaches can introduce complexity into web application architecture and impose an additional burden on developers. This paper presents SeamlessMDD, our novel open-source framework for seamless integration that allows us to maintain handwritten and generated code intertwined without the need to adjust the web application architecture or established workflows. The framework provides the following features: (1) incremental and iterative transformations derived from model versions comparison ensuring that only code for affected model elements is generated or modified; (2) integration of generated and handwritten code using API-based code generators (ABG) that operate on the syntax trees of target programming languages; (3) case-specific support for change propagation and conflict resolution, as opposed to VCS-based systems that operate on a single line. The proposed features were tested in practice within a complex industrial MDD tool.

Several important choices need to be made during the development of domain-specific languages, including the one regarding which concrete syntax to implement.There are several alternatives, with graphical and textual syntaxes being the most common ones.Having in mind that the developers and domain experts often have different preferences, supporting both is sometimes the best option.This means that models created using textual editors might need to be opened using separately developed graphical editors.Graphical elements corresponding to model elements must then be automatically created and positioned.Doing so in an aesthetically pleasing way requires usage of graph layout algorithms.Since implementing them is not an easy task, most developers have to rely on existing solutions.There are many Java libraries which have such capabilities, but they all have certain limitations and room for improvement, some of which are addressed in a new graph drawing and analysis library presented in this paper.• offer a large number of different graph drawing algorithms, including some that haven't been implemented in Java yet• provide a very quick and easy way to lay out elements of any existing graphical editor• offer algorithms for graph analysis, which can later be used to automatically select a suitable layout algorithm• enable the users to specify aesthetic criteria and automatically choose an appropriate layout algorithm based on their wishes

This paper presents Kroki (fr. croquis - sketch), a tool for participatory development of business applications based on mockups. Kroki provides a graphical editor for visual creation of mockups and two engines (Web and desktop) for mockup execution. Kroki is developed in order to foster development agility, communication and better understanding of end-user needs. The mockup editor and engines are based on our EUIS (Enterprise User Interface Specification) DSL for specifying user interfaces of business applications.

The paper presents a generic access control management infrastructure suitable for a broad set of systems. The generic infrastructure is based on our policy metamodel (level M2), which is used for the specification of the needed policy model (level M1) such as RBAC, GTRBAC, etc. Having a defined policy model, the abstract and concrete syntaxes of PolicyDSL, our textual DSL for expressing access control policies, are dynamically generated. A security expert is then able to express the actual access control policies (level M0) for the given access control model using the generated DSL. The presented solution can be applied, with no changes, to a number of systems that are based on different access control models or their variants.