<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>3734</id>
    <completedYear/>
    <publishedYear>2015</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>4</pageFirst>
    <pageLast>10</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>IEEE</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Safely Managing Data Variety in Big Data Software Development</title>
    <abstract language="eng">We consider the task of building Big Data software systems, offered as software-as-a-service. These applications are commonly backed by NoSQL data stores that address the proverbial Vs of Big Data processing: NoSQL data stores can handle large volumes of data and many systems do not enforce a global schema, to account for structural variety in data. Thus, software engineers can design the data model on the go, a flexibility that is particularly crucial in agile software development. However, NoSQL data stores commonly do not yet account for the veracity of changes when it comes to changes in the structure of persisted data. Yet this is an inevitable consequence of agile software development. In most NoSQL-based application stacks, schema evolution is completely handled within the application code, usually involving object mapper libraries. Yet simple code refactorings, such as renaming a class attribute at the source code level, can cause data loss or runtime errors once the application has been deployed to production. We address this pain point by contributing type checking rules that we have implemented within an IDE plug in. Our plug in ControVol statically type checks the object mapper class declarations against the code release history. ControVol is thus capable of detecting common yet risky cases of mismatched data and schema, and can even suggest automatic fixes.</abstract>
    <parentTitle language="eng">2015 IEEE/ACM 1st International Workshop on Big Data Software Engineering, 23-23 May 2015, Florence, Italy</parentTitle>
    <identifier type="doi">10.1109/BIGDSE.2015.9</identifier>
    <enrichment key="opus.import.date">2022-04-28T18:57:25+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">false</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Thomas Cerqueus</author>
    <author>Eduardo Cunha de Almeida</author>
    <author>Stefanie Scherzinger</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Big data</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>history</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Java</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Loading</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>NoSQL data stores</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>object mapping</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Production</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Runtime</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>schema evolution</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Software</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>type checking</value>
    </subject>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othforschungsschwerpunkt" number="16311">Digitalisierung</collection>
  </doc>
  <doc>
    <id>3777</id>
    <completedYear/>
    <publishedYear>2015</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>1464</pageFirst>
    <pageLast>1467</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>IEEE</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">ControVol: A framework for controlled schema evolution in NoSQL application development</title>
    <abstract language="eng">Building scalable web applications on top of NoSQL data stores is becoming common practice. Many of these data stores can easily be accessed programmatically, and do not enforce a schema. Software engineers can design the data model on the go, a flexibility that is crucial in agile software development. The typical tasks of database schema management are now handled within the application code, usually involving object mapper libraries. However, today’s Integrated Development Environments (IDEs) lack the proper tool support when it comes to managing the combined evolution of the application code and of the schema. Yet simple refactorings such as renaming an attribute at the source code level can cause irretrievable data loss or runtime errors once the application is serving in production. In this demo, we present ControVol, a framework for controlled schema evolution in application development against NoSQL data stores. ControVol is integrated into the IDE and statically type checks object mapper class declarations against the schema evolution history, as recorded by the code repository. ControVol is capable of warning of common yet risky cases of mismatched data and schema. ControVol is further able to suggest quick fixes by which developers can have these issues automatically resolved.</abstract>
    <parentTitle language="eng">2015 IEEE 31st International Conference on Data Engineering, 13-17 April 2015, Seoul, Korea (South)</parentTitle>
    <identifier type="doi">10.1109/ICDE.2015.7113402</identifier>
    <identifier type="isbn">978-1-4799-7964-6</identifier>
    <enrichment key="opus.import.date">2022-04-28T19:28:04+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Stefanie Scherzinger</author>
    <author>Thomas Cerqueus</author>
    <author>Eduardo Cunha de Almeida</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Databases</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Google</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>history</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Java</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Production</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Runtime</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Software</value>
    </subject>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othforschungsschwerpunkt" number="16311">Digitalisierung</collection>
  </doc>
  <doc>
    <id>3731</id>
    <completedYear/>
    <publishedYear>2018</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>1605</pageFirst>
    <pageLast>1608</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>IEEE</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Curating Variational Data in Application Development</title>
    <abstract language="eng">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.</abstract>
    <parentTitle language="eng">2018 IEEE 34th International Conference on Data Engineering, 16-19 April 2018, Paris, France</parentTitle>
    <identifier type="doi">10.1109/ICDE.2018.00187</identifier>
    <enrichment key="opus.import.date">2022-04-28T18:57:25+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">false</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Uta Störl</author>
    <author>Daniel Müller</author>
    <author>Alexander Tekleab</author>
    <author>Stephane Tolale</author>
    <author>Julian Stenzel</author>
    <author>Meike Klettke</author>
    <author>Stefanie Scherzinger</author>
    <author>Uta Storl</author>
    <author>Daniel Muller</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>data migration</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Data mining</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Evolution (biology)</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>history</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>NoSQL databases</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>query rewriting</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>schema evolution</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>schema management</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Software</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Task analysis</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>variational data</value>
    </subject>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othforschungsschwerpunkt" number="16311">Digitalisierung</collection>
  </doc>
  <doc>
    <id>3721</id>
    <completedYear/>
    <publishedYear>2017</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>2462</pageFirst>
    <pageLast>2471</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>IEEE</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Uncovering the evolution history of data lakes</title>
    <abstract language="eng">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.</abstract>
    <parentTitle language="eng">2017 IEEE International Conference on Big Data (Big Data),,11-14 Dec. 2017, Boston, MA, USA</parentTitle>
    <identifier type="doi">10.1109/BigData.2017.8258204</identifier>
    <enrichment key="opus.import.date">2022-04-28T18:57:25+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Meike Klettke</author>
    <author>Hannes Awolin</author>
    <author>Uta Störl</author>
    <author>Daniel Müller</author>
    <author>Stefanie Scherzinger</author>
    <author>Uta Storl</author>
    <author>Daniel Muller</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Data mining</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>evolution operations</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Grippers</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>history</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>inclusion dependencies</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>integrity constraints</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Lakes</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>NoSQL databases</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Protocols</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>schema version extraction</value>
    </subject>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othforschungsschwerpunkt" number="16311">Digitalisierung</collection>
  </doc>
</export-example>
