@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} } @inproceedings{HauboldSchildgenScherzingeretal., author = {Haubold, Florian and Schildgen, Johannes and Scherzinger, Stefanie and Deßloch, Stefan}, title = {ControVol Flex: Flexible Schema Evolution for NoSQL Application Development}, 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}, abstract = {We demonstrate ControVol Flex, an Eclipse plugin for controlled schema evolution in Java applications backed by NoSQL document stores. The sweet spot of our tool are applications that are deployed continuously against the same production data store: Each new release may bring about schema changes that conflict with legacy data already stored in production. The type system internal to the predecessor tool ControVol is able to detect common schema conflicts, and enables developers to resolve them with the help of object-mapper annotations. Our new tool ControVol Flex lets developers choose their schema-migration strategy, whether all legacy data is to be migrated eagerly by means of NotaQL transformation scripts, or lazily, as declared by object-mapper annotations. Our tool is even capable of carrying out both strategies in combination, eagerly migrating data in the background, while lazily migrating data that is meanwhile accessed by the application. From the viewpoint of the application, it remains transparent how legacy data is migrated: Every read access yields an entity that matches the structure that the current application code expects. Our live demo shows how ControVol Flex gracefully solves a broad range of common schema-evolution tasks.}, language = {en} } @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} } @misc{WeberDendorferSuessetal., author = {Weber, Karsten and Dendorfer, Sebastian and S{\"u}ß, Franz and Kubowitsch, Simone and Schratzenstaller, Thomas and Haug, Sonja and Mohr, Christa and Kiesl, Hans and Drechsler, J{\"o}rg and Westner, Markus and Kobus, J{\"o}rn and Schubert, Martin J. W. and Zenger, Stefan and Pietsch, Alexander and Weiß, Josef and Hinterseer, Sebastian and Schieck, Roland and Scherzinger, Stefanie and Klettke, Meike and Ringlstetter, Andreas and St{\"o}rl, Uta and Bissyand{\´e}, Tegawend{\´e} F. and Seeburger, Achim and Schindler, Timo and Ramsauer, Ralf and Kiszka, Jan and K{\"o}lbl, Andreas and Lohmann, Daniel and Mauerer, Wolfgang and Maier, Johannes and Scorna, Ulrike and Palm, Christoph and Soska, Alexander and Mottok, J{\"u}rgen and Ellermeier, Andreas and V{\"o}gele, Daniel and Hierl, Stefan and Briem, Ulrich and Buschmann, Knut and Ehrlich, Ingo and Pongratz, Christian and Pielmeier, Benjamin and Tyroller, Quirin and Monkman, Gareth J. and Gut, Franz and Roth, Carina and Hausler, Peter and Bierl, Rudolf and Prommesberger, Christian and Ławrowski, Robert Damian and Langer, Christoph and Schreiner, Rupert and Huang, Yifeng and She, Juncong and Ottl, Andreas and Rieger, Walter and Kraml, Agnes and Poxleitner, Thomas and Hofer, Simon and Heisterkamp, Benjamin and Lerch, Maximilian and Sammer, Nike and Golde, Olivia and Wellnitz, Felix and Schmid, Sandra and Muntschick, Claudia and Kusterle, Wolfgang and Paric, Ivan and Br{\"u}ckl, Oliver and Haslbeck, Matthias and Schmidt, Ottfried and Schwanzer, Peter and Rabl, Hans-Peter and Sterner, Michael and Bauer, Franz and Steinmann, Sven and Eckert, Fabian and Hofrichter, Andreas}, title = {Forschungsbericht 2017}, editor = {Baier, Wolfgang}, address = {Regensburg}, organization = {Ostbayerische Technische Hochschule Regensburg}, isbn = {978-3-9818209-3-5}, doi = {10.35096/othr/pub-1383}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-13835}, subject = {Forschung}, language = {de} }