{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T13:40:04Z","timestamp":1748439604139,"version":"3.41.0"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319204239"},{"type":"electronic","value":"9783319204246"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-20424-6_14","type":"book-chapter","created":{"date-parts":[[2015,6,10]],"date-time":"2015-06-10T20:01:23Z","timestamp":1433966483000},"page":"139-151","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["NotaQL Is Not a Query Language! It\u2019s for Data Transformation on Wide-Column Stores"],"prefix":"10.1007","author":[{"given":"Johannes","family":"Schildgen","sequence":"first","affiliation":[]},{"given":"Stefan","family":"De\u00dfloch","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,6,11]]},"reference":[{"key":"14_CR1","first-page":"6512","volume":"123","author":"P Buneman","year":"2005","unstructured":"Buneman, P., Cheney, J.: A copy-and-paste model for provenance in curated databases. Notes 123, 6512 (2005)","journal-title":"Notes"},{"issue":"2","key":"14_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1365815.1365816","volume":"26","author":"F Chang","year":"2008","unstructured":"Chang, F., Dean, J., Ghemawat, S., Hsieh, W.C., Wallach, D.A., Burrows, M., Chandra, T., Fikes, A., Gruber, R.E.: Bigtable: a distributed storage system for structured data. ACM Trans. Comput. Syst. (TOCS) 26(2), 1\u201314 (2008). Article 4","journal-title":"ACM Trans. Comput. Syst. (TOCS)"},{"key":"14_CR3","unstructured":"Dean, J., Ghemawat, S.: MapReduce: simplified data processing on large clusters. In: OSDI, pp. 137\u2013150 (2004)"},{"key":"14_CR4","unstructured":"Emde, M.: GUI und testumgebung f\u00fcr die HBase-schematransformationssprache NotaQL. Bachelor\u2019s thesis, Kaiserslautern University (2014)"},{"key":"14_CR5","volume-title":"HBase: The Definitive Guide","author":"L George","year":"2011","unstructured":"George, L.: HBase: The Definitive Guide, 1st edn. O\u2019Reilly Media, Sebastopol (2011)","edition":"1"},{"key":"14_CR6","unstructured":"Gonzalez, J.E., Low, Y., Gu, H., Bickson, D., Guestrin, C.: Powergraph: distributed graph-parallel computation on natural graphs. In: OSDI, vol. 12, p. 2 (2012)"},{"key":"14_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1007\/BFb0014149","volume-title":"Advances in Database Technology EDBT 1996","author":"A Gupta","year":"1996","unstructured":"Gupta, A., Jagadish, H.V., Mumick, I.S.: Data integration using self-maintainable views. In: Apers, P.M.G., Bouzeghoub, M., Gardarin, G. (eds.) EDBT 1996. LNCS, vol. 1057, pp. 140\u2013144. Springer, Heidelberg (1996)"},{"issue":"2","key":"14_CR8","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1145\/376284.375767","volume":"30","author":"MA Hern\u00e1ndez","year":"2001","unstructured":"Hern\u00e1ndez, M.A., Miller, R.J., Haas, L.M.: Clio: A semi-automatic tool for schema mapping. ACM SIGMOD Rec. 30(2), 607 (2001)","journal-title":"ACM SIGMOD Rec."},{"issue":"1","key":"14_CR9","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1145\/2189750.2151013","volume":"40","author":"S Hong","year":"2012","unstructured":"Hong, S., Chafi, H., Sedlar, E., Olukotun, K.: Green-marl: a DSL for easy and efficient graph analysis. ACM SIGARCH Comput. Archit. News 40(1), 349\u2013362 (2012)","journal-title":"ACM SIGARCH Comput. Archit. News"},{"key":"14_CR10","unstructured":"Lakshmanan, L.V.S., Sadri, F., Subramanian, I.N.: SchemaSQL-a language for interoperability in relational multi-database systems. In: VLDB, vol. 96, pp. 239\u2013250 (1996)"},{"issue":"1","key":"14_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2200\/S00274ED1V01Y201006HLT007","volume":"3","author":"J Lin","year":"2010","unstructured":"Lin, J., Dyer, C.: Data-intensive text processing with MapReduce. Synth. Lect. Hum. Lang. Technol. 3(1), 1\u2013177 (2010)","journal-title":"Synth. Lect. Hum. Lang. Technol."},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Malewicz, G., Austern, M.H., Bik, A.J.C., Dehnert, J.C., Horn, I., Leiser, N., Czajkowski, G.: Pregel: a system for large-scale graph processing. In: Proceedings of the 2010 ACM SIGMOD International Conference on Management of Data, pp. 135\u2013146. ACM (2010)","DOI":"10.1145\/1807167.1807184"},{"key":"14_CR13","unstructured":"Grinev, M.: Do You Really Need SQL to Do It All in Cassandra? (2010). http:\/\/wp.me\/pZn7Z-o"},{"issue":"6","key":"14_CR14","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1145\/1953122.1953148","volume":"54","author":"M Sergey","year":"2011","unstructured":"Sergey, M., Andrey, A., Long, J.J., Romer, G., Shivakumar, S., Tolton, M., Vassilakis, T.: Dremel: interactive analysis of web-scale datasets. Commun. ACM 54(6), 114\u2013123 (2011)","journal-title":"Commun. ACM"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Murray, D.G., Sherry, F.M.C., Isaacs, R., Isard, M., Barham, P., Abadi, M.: Naiad: a timely dataflow system. In: Proceedings of the Twenty-Fourth ACM Symposium on Operating Systems Principles, pp. 439\u2013455. ACM (2013)","DOI":"10.1145\/2517349.2522738"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Olston, C., Chiou, G., Chitnis, L., Liu, F., Han, Y., Larsson, M., Neumann, A., Rao, V.B.N., Sankarasubramanian, V., Seth, S., et al.: Nova: continuous pig\/hadoop workflows. In: Proceedings of the 2011 ACM SIGMOD International Conference on Management of Data, pp. 1081\u20131090. ACM (2011)","DOI":"10.1145\/1989323.1989439"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Olston, C., Reed, B., Srivastava, U., Kumar, R., Tomkins, A.: Pig latin: a not-so-foreign language for data processing. In: Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data, pp. 1099\u20131110. ACM (2008)","DOI":"10.1145\/1376616.1376726"},{"key":"14_CR18","unstructured":"Page, L., Brin, S., Motwani, R., Winograd, T.: The pagerank citation ranking: bringing order to the web. Technical report 1999\u201366, Stanford InfoLab, November 1999. Previous number = SIDL-WP-1999-0120"},{"issue":"4","key":"14_CR19","first-page":"277","volume":"13","author":"R Pike","year":"2005","unstructured":"Pike, R., Dorward, S., Griesemer, R., Quinlan, S.: Interpreting the data: parallel analysis with sawzall. Sci. Program. 13(4), 277\u2013298 (2005)","journal-title":"Sci. Program."},{"key":"14_CR20","unstructured":"Sato, K.: An inside look at google bigquery. White paper (2012). https:\/\/cloud.google.com\/files\/BigQueryTechnicalWP.pdf"},{"issue":"2","key":"14_CR21","doi-asserted-by":"publisher","first-page":"1626","DOI":"10.14778\/1687553.1687609","volume":"2","author":"A Thusoo","year":"2009","unstructured":"Thusoo, A., Sarma, J.S., Jain, N., Shao, Z., Chakka, P., Anthony, S., Liu, H., Wyckoff, P., Murthy, R.: Hive: a warehousing solution over a map-reduce framework. Proc. VLDB Endow. 2(2), 1626\u20131629 (2009)","journal-title":"Proc. VLDB Endow."},{"issue":"2","key":"14_CR22","doi-asserted-by":"publisher","first-page":"624","DOI":"10.1145\/1071610.1071618","volume":"30","author":"CM Wyss","year":"2005","unstructured":"Wyss, C.M., Robertson, E.L.: Relational languages for metadata integration. ACM Trans. Database Syst. (TODS) 30(2), 624\u2013660 (2005)","journal-title":"ACM Trans. Database Syst. (TODS)"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Xin, R.S., Gonzalez, J.E., Franklin, M.J., Stoica, I.: Graphx: a resilient distributed graph system on spark. In: First International Workshop on Graph Data Management Experiences and Systems, p. 2. ACM (2013)","DOI":"10.1145\/2484425.2484427"},{"key":"14_CR24","unstructured":"Zaharia, M., Chowdhury, M., Das, T., Dave, A., Ma, J., McCauley, M., Franklin, M.J., Shenker, S., Stoica, I.: Resilient distributed datasets: a fault-tolerant abstraction for in-memory cluster computing. In: Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation, p. 2. USENIX Association (2012)"}],"container-title":["Lecture Notes in Computer Science","Data Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-20424-6_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T13:17:07Z","timestamp":1748438227000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-20424-6_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319204239","9783319204246"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-20424-6_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"11 June 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}