{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T07:07:26Z","timestamp":1750230446770,"version":"3.40.4"},"publisher-location":"Berlin, Heidelberg","reference-count":30,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642375736"},{"type":"electronic","value":"9783642375743"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-37574-3_1","type":"book-chapter","created":{"date-parts":[[2013,4,18]],"date-time":"2013-04-18T04:12:53Z","timestamp":1366258373000},"page":"1-31","source":"Crossref","is-referenced-by-count":12,"title":["ETLMR: A Highly Scalable Dimensional ETL Framework Based on MapReduce"],"prefix":"10.1007","author":[{"given":"Xiufeng","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christian","family":"Thomsen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Torben Bach","family":"Pedersen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"1","key":"1_CR1","first-page":"22","volume":"2","author":"A. Abouzeid","year":"2009","unstructured":"Abouzeid, A., Bajda-Pawlikowski, K., Abadi, D., Silberschatz, A., Rasin, A.: HadoopDB: An Architectural Hybrid of MapReduce and DBMS Technologies for Analytical Workloads. PVLDB\u00a02(1), 22\u2013933 (2009)","journal-title":"PVLDB"},{"key":"1_CR2","unstructured":"AsterData (September 10, 2012), www.asterdata.com"},{"key":"1_CR3","unstructured":"Applications and organizations using Hadoop (September 10, 2012), wiki.apache.org\/hadoop\/PoweredBy"},{"key":"1_CR4","unstructured":"Disco project (September 10, 2012), discoproject.org"},{"key":"1_CR5","unstructured":"Shelve - Python object persistence (September 10, 2012), docs.python.org\/library\/shelve.html"},{"key":"1_CR6","unstructured":"The Apache Hadoop Project (October 6, 2011), hadoop.apache.org"},{"key":"1_CR7","unstructured":"(September 10, 2012), www.pentaho.com"},{"issue":"2","key":"1_CR8","first-page":"1265","volume":"1","author":"R. Chaiken","year":"2008","unstructured":"Chaiken, R., Jenkins, B., Larson, P., Ramsey, B., Shakib, D., Weaver, S., Zhou, J.: SCOPE: Easy and Efficient Parallel Processing of Massive Data Sets. PVLDB\u00a01(2), 1265\u20131276 (2008)","journal-title":"PVLDB"},{"issue":"1","key":"1_CR9","first-page":"1459","volume":"3","author":"S. Chen","year":"2010","unstructured":"Chen, S.: Cheetah: A High Performance, Custom Data Warehouse on Top of MapReduce. PVLDB\u00a03(1), 1459\u20131468 (2010)","journal-title":"PVLDB"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Cuzzocrea, A., Song, I.Y., Davis, K.C.: Analytics Over Large-scale Multidimensional Data: the Big Data Revolution! In: Proc. of the ACM 14th International Workshop on Data Warehousing and OLAP, pp. 101\u2013104 (2011)","DOI":"10.1145\/2064676.2064695"},{"issue":"1","key":"1_CR11","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1145\/1629175.1629198","volume":"53","author":"J. Dean","year":"2010","unstructured":"Dean, J., Ghemawat, S.: MapReduce: A Flexible Data Processing Tool. CACM\u00a053(1), 72\u201377 (2010)","journal-title":"CACM"},{"key":"1_CR12","unstructured":"Dean, J., Ghemawat, S.: MapReduce: Simplified Data Processing on Large Clusters. In: Proc. of OSDI, pp. 137\u2013150 (2004)"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Dittrich, J., Quiane-Ruiz, J.A., Jindal, A., Kargin, Y., Setty, V., Schad, J.: Hadoop++: Making a Yellow Elephant Run Like a Cheetah (Without It Even Noticing). PVLDB\u00a03(1) (2010)","DOI":"10.14778\/1920841.1920908"},{"issue":"1","key":"1_CR14","first-page":"28","volume":"1","author":"D. DeWitt","year":"2008","unstructured":"DeWitt, D., Robinson, E., Shankar, S., Paulson, E., Naughton, J., Krioukov, A., Royalty, J.: Clustera: An Integrated Computation and Data Management System. PVLDB\u00a01(1), 28\u201341 (2008)","journal-title":"PVLDB"},{"issue":"2","key":"1_CR15","first-page":"1402","volume":"2","author":"E. Friedman","year":"2009","unstructured":"Friedman, E., Pawlowski, P., Cieslewicz, J.: SQL\/MapReduce: A Practical Approach to Self-describing, Polymorphic, and Parallelizable User-defined Functions. PVLDB\u00a02(2), 1402\u20131413 (2009)","journal-title":"PVLDB"},{"key":"1_CR16","unstructured":"GreenPlum (September 10, 2012), www.greenplum.com"},{"key":"1_CR17","unstructured":"Kovoor, G., Singer, J., Lujan, M.: Building a Java MapReduce Framework for Multi-core Architectures. In: Proc. of MULTIPROG (2010)"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Isard, M., Budiu, M., Yu, Y., Birrell, A., Fetterly, D.: Dryad: Distributed Data-Parallel Programs from Sequential Building Blocks. In: Proc. of EuroSys, pp. 59\u201372 (2007)","DOI":"10.1145\/1272998.1273005"},{"key":"1_CR19","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: Proc. of SIGMOD, pp. 1099\u20131110 (2008)","DOI":"10.1145\/1376616.1376726"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Pavlo, A., Paulson, E., Rasin, A., Abadi, D., DeWitt, D., Madden, S., Stonebraker, M.: A Comparison of Approaches to Large-scale Data Analysis. In: Proc. of SIGMOD, pp. 165\u2013178 (2009)","DOI":"10.1145\/1559845.1559865"},{"key":"1_CR21","unstructured":"Peng, D., Dabek, F.: Large-scale Incremental Processing Using Distributed Transactions and Notifications. In: Proc. of OSDI, pp. 251\u2013264 (2010)"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Ranger, C., Raghuraman, R., Penmetsa, A., Bradski, G., Kozyrakis, C.: Evaluating MapReduce for Multi-core and Multiprocessor Systems. In: Proc. of HPCA, pp. 13\u201324 (2007)","DOI":"10.1109\/HPCA.2007.346181"},{"issue":"1","key":"1_CR23","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1145\/1629175.1629197","volume":"53","author":"M. Stonebraker","year":"2010","unstructured":"Stonebraker, M., Abadi, D., DeWitt, D., Madden, S., Paulson, E., Pavlo, A., Rasin, A.: MapReduce and Parallel DBMSs: friends or foes? CACM\u00a053(1), 64\u201371 (2010)","journal-title":"CACM"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Thomsen, C., Pedersen, T.B.: Building a Web Warehouse for Accessibility Data. In: Proc. of DOLAP, pp. 43\u201350 (2009)","DOI":"10.1145\/1183512.1183522"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Thomsen, C., Pedersen, T.B.: pygrametl: A Powerful Programming Framework for Extract-Transform-Load Programmers. In: Proc. of DOLAP, pp. 49\u201356 (2009)","DOI":"10.1145\/1651291.1651301"},{"issue":"2","key":"1_CR26","first-page":"1626","volume":"2","author":"A. Thusoo","year":"2009","unstructured":"Thusoo, A., Sarma, J., Jain, N., Shao, Z., Chakka, P., Anthony, S., Liu, H., Wyckoff, P., Murthy, R.: Hive: A Warehousing Solution Over a Map-reduce Framework. PVLDB\u00a02(2), 1626\u20131629 (2009)","journal-title":"PVLDB"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Thusoo, A., Sarma, J., Jain, N., Shao, Z., Chakka, P., Zhang, N., Anthony, S., Liu, H., Murthy, R.: Hive-A Petabyte Scale Data Warehouse Using Hadoop. In: Proc. of ICDE, pp. 996\u20131005 (2010)","DOI":"10.1109\/ICDE.2010.5447738"},{"key":"1_CR28","unstructured":"TPC-H (September 10, 2012), http:\/\/tpc.org\/tpch\/"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Vassiliadis, P., Simitsis, A.: Near Real Time ETL. In: Kozielski, S., Wrembel, R. (eds.) New Trends in Data Warehousing and Data Analysis, pp. 1\u201331. Springer (2008)","DOI":"10.1007\/978-0-387-87431-9_2"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Yoo, R., Romano, A., Kozyrakis, C.: Phoenix Rebirth: Scalable MapReduce on a Large-scale Shared-memory System. In: Proc. of IISWC, pp. 198\u2013207 (2009)","DOI":"10.1109\/IISWC.2009.5306783"}],"container-title":["Lecture Notes in Computer Science","Transactions on Large-Scale Data- and Knowledge-Centered Systems VIII"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-37574-3_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T05:35:18Z","timestamp":1745991318000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-37574-3_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642375736","9783642375743"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-37574-3_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}