@inproceedings{StoerlMuellerTekleabetal., author = {St{\"o}rl, Uta and M{\"u}ller, Daniel and Tekleab, Alexander and Tolale, Stephane and Stenzel, Julian and Klettke, Meike and Scherzinger, Stefanie and Storl, Uta and Muller, Daniel}, title = {Curating Variational Data in Application Development}, series = {2018 IEEE 34th International Conference on Data Engineering, 16-19 April 2018, Paris, France}, booktitle = {2018 IEEE 34th International Conference on Data Engineering, 16-19 April 2018, Paris, France}, publisher = {IEEE}, doi = {10.1109/ICDE.2018.00187}, pages = {1605 -- 1608}, abstract = {Building applications for processing data lakes is a software engineering challenge. We present Darwin, a middleware for applications that operate on variational data. This concerns data with heterogeneous structure, usually stored within a schema-flexible NoSQL database. Darwin assists application developers in essential data and schema curation tasks: Upon request, Darwin extracts a schema description, discovers the history of schema versions, and proposes mappings between these versions. Users of Darwin may interactively choose which mappings are most realistic. Darwin is further capable of rewriting queries at runtime, to ensure that queries also comply with legacy data. Alternatively, Darwin can migrate legacy data to reduce the structural heterogeneity. Using Darwin, developers may thus evolve their data in sync with their code. In our hands-on demo, we curate synthetic as well as real-life datasets.}, language = {en} } @inproceedings{KlettkeAwolinStoerletal., author = {Klettke, Meike and Awolin, Hannes and St{\"o}rl, Uta and M{\"u}ller, Daniel and Scherzinger, Stefanie and Storl, Uta and Muller, Daniel}, title = {Uncovering the evolution history of data lakes}, series = {2017 IEEE International Conference on Big Data (Big Data),,11-14 Dec. 2017, Boston, MA, USA}, booktitle = {2017 IEEE International Conference on Big Data (Big Data),,11-14 Dec. 2017, Boston, MA, USA}, publisher = {IEEE}, doi = {10.1109/BigData.2017.8258204}, pages = {2462 -- 2471}, abstract = {Data accumulating in data lakes can become inaccessible in the long run when its semantics are not available. The heterogeneity of data formats and the sheer volumes of data collections prohibit cleaning and unifying the data manually. Thus, tools for automated data lake analysis are of great interest. In this paper, we target the particular problem of reconstructing the schema evolution history from data lakes. Knowing how the data is structured, and how this structure has evolved over time, enables programmatic access to the lake. By deriving a sequence of schema versions, rather than a single schema, we take into account structural changes over time. Moreover, we address the challenge of detecting inclusion dependencies. This is a prerequisite for mapping between succeeding schema versions, and in particular, detecting nontrivial changes such as a property having been moved or copied. We evaluate our approach for detecting inclusion dependencies using the MovieLens dataset, as well an adaption of a dataset containing botanical descriptions, to cover specific edge cases.}, language = {en} } @misc{LautenschlaegerLeisDendorferetal., author = {Lautenschl{\"a}ger, Toni and Leis, Alexander and Dendorfer, Sebastian and Palm, Christoph and Schreiner, Rupert and Langer, Christoph and Prommesberger, Christian and Ɓawrowski, Robert Damian and Dams, Florian and Bornmann, Benjamin and Navitski, Aliaksandr and Serbun, Pavel and M{\"u}ller, G{\"u}nter and Liebetruth, Thomas and Kohlert, Dieter and Pernsteiner, Jochen and Schreier, Franz and Heerklotz, Sabrina and Heerklotz, Allwin and Boos, Alexander and Herwald, Dominik and Monkman, Gareth J. and Treiber, Daniel and Mayer, Matthias and H{\"o}rner, Eva and Bentz, Alexander and Shamonin (Chamonine), Mikhail and Johansen, S{\o}ren Peter and Reichel, Marco and Stoll, Andrea and Briem, Ulrich and Dullien, Silvia and Renkawitz, Tobias and Weber, Tim and Dendorfer, Sebastian and Grifka, Joachim and Penzkofer, Rainer and Barnsteiner, K. and Jovanovik, M. and Wernecke, P. and V{\"o}gele, A. and Bachmann, T. and Pl{\"o}tz, Martin and Schliekmann, Claus and Wels, Harald and Helmberger, Paul and Kaspar, M. and H{\"o}nicka, M. and Schrammel, Siegfried and Enser, Markus and Schmidmeier, Monika and Schroll-Decker, Irmgard and Haug, Sonja and Gelfert, Verena and Vernim, Matthias}, title = {Forschungsbericht 2012}, editor = {Baier, Wolfgang}, address = {Regensburg}, organization = {Ostbayerische Technische Hochschule Regensburg}, doi = {10.35096/othr/pub-783}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-7834}, pages = {64}, language = {de} } @incollection{StoerlMuellerKlettkeetal., author = {St{\"o}rl, Uta and M{\"u}ller, Daniel and Klettke, Meike and Scherzinger, Stefanie}, title = {Enabling Efficient Agile Software Development of NoSQL-backed Applications}, series = {Datenbanksysteme f{\"u}r Business, Technologie und Web (BTW 2017) : 17. Fachtagung des GI-Fachbereichs "Datenbanken und Informationssyteme" (DBIS) : 06.-10.03.2017 in Stuttgart Deutschland}, booktitle = {Datenbanksysteme f{\"u}r Business, Technologie und Web (BTW 2017) : 17. Fachtagung des GI-Fachbereichs "Datenbanken und Informationssyteme" (DBIS) : 06.-10.03.2017 in Stuttgart Deutschland}, editor = {Mitschang, Bernhard}, publisher = {Gesellschaft f{\"u}r Informatik e.V. (GI)}, address = {Bonn}, isbn = {978-3-88579-659-6}, abstract = {NoSQL databases are popular in agile software development, where a frequently changing database schema imposes challenges for the production database. In this demo, we present Darwin, a middleware for systematic, tool-based support specifically designed for NoSQL database systems. Darwin carries out schema evolution and data migration tasks. To the best of our knowledge, Darwin is the first tool of its kind that supports both eager and lazy NoSQL data migration.}, language = {en} }