{"id":"https://openalex.org/W2945198755","doi":"https://doi.org/10.1145/3308558.3314132","title":"Querying Data Lakes using Spark and Presto","display_name":"Querying Data Lakes using Spark and Presto","publication_year":2019,"publication_date":"2019-05-13","ids":{"openalex":"https://openalex.org/W2945198755","doi":"https://doi.org/10.1145/3308558.3314132","mag":"2945198755"},"language":"en","primary_location":{"id":"doi:10.1145/3308558.3314132","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308558.3314132","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The World Wide Web Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3308558.3314132","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056893640","display_name":"Mohamed Nadjib Mami","orcid":"https://orcid.org/0000-0002-2093-4148"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Mohamed Nadjib Mami","raw_affiliation_strings":["Fraunhofer IAIS and University of Bonn"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IAIS and University of Bonn","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056690478","display_name":"Damien Graux","orcid":"https://orcid.org/0000-0003-3392-3162"},"institutions":[{"id":"https://openalex.org/I4210144576","display_name":"Fraunhofer Institute for Intelligent Analysis and Information Systems","ror":"https://ror.org/04nc32781","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144576","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Damien Graux","raw_affiliation_strings":["Fraunhofer IAIS"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IAIS","institution_ids":["https://openalex.org/I4210144576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077513270","display_name":"Simon Scerri","orcid":null},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Simon Scerri","raw_affiliation_strings":["Fraunhofer IAIS and University of Bonn"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IAIS and University of Bonn","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034642813","display_name":"Hajira Jabeen","orcid":"https://orcid.org/0000-0003-1476-2121"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hajira Jabeen","raw_affiliation_strings":["University of Bonn"],"affiliations":[{"raw_affiliation_string":"University of Bonn","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071765665","display_name":"S\u00f6ren Auer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"S\u00f6ren Auer","raw_affiliation_strings":["TIB and L3S Research Center"],"affiliations":[{"raw_affiliation_string":"TIB and L3S Research Center","institution_ids":["https://openalex.org/I4210136150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5056893640"],"corresponding_institution_ids":["https://openalex.org/I135140700"],"apc_list":null,"apc_paid":null,"fwci":1.7825,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.8578776,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3574","last_page":"3578"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8410696387290955},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.8366482853889465},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5689542889595032},{"id":"https://openalex.org/keywords/graphical-user-interface","display_name":"Graphical user interface","score":0.47658297419548035},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4732185900211334},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2111002802848816},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12381115555763245}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8410696387290955},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8366482853889465},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5689542889595032},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.47658297419548035},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4732185900211334},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2111002802848816},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12381115555763245}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3308558.3314132","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308558.3314132","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The World Wide Web Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:fraunhofer.de:N-565632","is_oa":false,"landing_page_url":"http://publica.fraunhofer.de/documents/N-565632.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer IAIS","raw_type":"conferenceObject"},{"id":"pmh:oai:publica.fraunhofer.de:publica/405905","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/405905","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":{"id":"doi:10.1145/3308558.3314132","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308558.3314132","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The World Wide Web Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1482134990","https://openalex.org/W1892261149","https://openalex.org/W2004817090","https://openalex.org/W2015191210","https://openalex.org/W2061253631","https://openalex.org/W2101241649","https://openalex.org/W2131975293","https://openalex.org/W2180737804","https://openalex.org/W2295890767","https://openalex.org/W2465312143","https://openalex.org/W2610669233","https://openalex.org/W2639544096"],"related_works":["https://openalex.org/W4247566972","https://openalex.org/W3017846737","https://openalex.org/W2980795771","https://openalex.org/W3012903882","https://openalex.org/W3202731209","https://openalex.org/W3154228395","https://openalex.org/W3006311829","https://openalex.org/W3109411864","https://openalex.org/W3007547586","https://openalex.org/W2968118396"],"abstract_inverted_index":{"Squerall":[0],"is":[1],"a":[2,28],"tool":[3],"that":[4],"allows":[5],"the":[6,34,56],"querying":[7],"of":[8],"heterogeneous,":[9],"large-scale":[10],"data":[11,36,41,51,71,84],"sources":[12,37],"by":[13],"leveraging":[14],"state-of-the-art":[15],"Big":[16],"Data":[17,29],"processing":[18],"engines:":[19],"Spark":[20],"and":[21,59,73,100],"Presto.":[22],"Queries":[23],"are":[24,90],"posed":[25],"on-demand":[26],"against":[27],"Lake,":[30],"i.e.,":[31],"directly":[32],"on":[33],"original":[35],"without":[38],"requiring":[39],"prior":[40],"transformation.":[42],"We":[43],"showcase":[44],"Squerall's":[45],"ability":[46],"to":[47,81,92],"query":[48,69],"five":[49],"different":[50],"sources,":[52,72],"including":[53],"inter":[54],"alia":[55],"popular":[57],"Cassandra":[58],"MongoDB.":[60],"In":[61],"particular,":[62],"we":[63],"demonstrate":[64],"how":[65,74],"it":[66,80],"can":[67,77],"jointly":[68],"heterogeneous":[70],"interested":[75],"developers":[76],"easily":[78],"extend":[79],"support":[82,93],"additional":[83],"sources.":[85],"Graphical":[86],"user":[87],"interfaces":[88],"(GUIs)":[89],"offered":[91],"users":[94],"in":[95],"(1)":[96],"building":[97],"intra-source":[98],"queries,":[99],"(2)":[101],"creating":[102],"required":[103],"input":[104],"files.":[105]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
