{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:09:33Z","timestamp":1778256573502,"version":"3.51.4"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2023,5,13]],"date-time":"2023-05-13T00:00:00Z","timestamp":1683936000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,5,13]],"date-time":"2023-05-13T00:00:00Z","timestamp":1683936000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Open Fund of Digital Fujian Big Data Modeling and Intelligent Computing Institute"},{"name":"the Natural Science Foundation of Fujian Province of China","award":["2022J01336"],"award-info":[{"award-number":["2022J01336"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1007\/s10586-023-04010-0","type":"journal-article","created":{"date-parts":[[2023,5,13]],"date-time":"2023-05-13T01:02:36Z","timestamp":1683939756000},"page":"1375-1399","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Integrated method for distributed processing of large XML data"],"prefix":"10.1007","volume":"27","author":[{"given":"Rongxin","family":"Chen","sequence":"first","affiliation":[]},{"given":"Guorong","family":"Cai","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Yuling","family":"Hong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,5,13]]},"reference":[{"key":"4010_CR1","doi-asserted-by":"crossref","unstructured":"Zhen, H.L., Murthy, R.: A Decade of XML data management: an industrial experience report from oracle. In: Proceedings of the 25th International Conference on Data Engineering (ICDE 2009), Shanghai, China, March 29 - April 2 2009 2009, pp. 1351\u20131362. IEEE Computer Society","DOI":"10.1109\/ICDE.2009.18"},{"issue":"8","key":"4010_CR2","doi-asserted-by":"publisher","first-page":"1317","DOI":"10.1016\/j.knosys.2011.06.006","volume":"24","author":"H Lee","year":"2011","unstructured":"Lee, H.: Data storage practices and query processing in XML databases: a survey. Knowl.-Based Syst. 24(8), 1317\u20131340 (2011)","journal-title":"Knowl.-Based Syst."},{"key":"4010_CR3","unstructured":"DBLP XML dataset. http:\/\/dblp.uni-trier.de\/xml\/."},{"key":"4010_CR4","unstructured":"Wikimedia XML dataset. http:\/\/download.wikimedia.org\/enwiki\/latest."},{"key":"4010_CR5","unstructured":"OpenStreetMap XML dataset. http:\/\/www.openstreetmap.org\/export."},{"key":"4010_CR6","doi-asserted-by":"crossref","unstructured":"Sankari, S., Bose, S.: Elaborative survey on storage technologies for XML big data: A real-time approach. In: 2016 International Conference on Recent Trends in Information Technology (ICRTIT) 2016","DOI":"10.1109\/ICRTIT.2016.7569569"},{"key":"4010_CR7","doi-asserted-by":"publisher","first-page":"100231","DOI":"10.1016\/j.cosrev.2020.100231","volume":"36","author":"Z Brahmia","year":"2020","unstructured":"Brahmia, Z., Hamrouni, H., Bouaziz, R.: XML data manipulation in conventional and temporal XML databases: a survey. Comput. Sci. Rev. 36, 100231 (2020)","journal-title":"Comput. Sci. Rev."},{"key":"4010_CR8","unstructured":"Berglund, A., Boag, S., Chamberlin, D., Fernandez, M.F., Kay, M., Robie, J., Sim\u00e9on, J.: XML path language (XPath) 2.0 (Second Edition). W3C recommendation (2015)."},{"key":"4010_CR9","unstructured":"Dean, J.: MapReduce : simplified data processing on large clusters. In: Symposium on Operating System Design & Implementation 2004"},{"issue":"4","key":"4010_CR10","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1145\/2094114.2094118","volume":"40","author":"KH Lee","year":"2012","unstructured":"Lee, K.H., Lee, Y.J., Choi, H., Chung, Y.D., Moon, B.: Parallel data processing with MapReduce: a survey. ACM SIGMOD Rec. 40(4), 11\u201320 (2012)","journal-title":"ACM SIGMOD Rec."},{"issue":"10","key":"4010_CR11","doi-asserted-by":"publisher","first-page":"1381","DOI":"10.1109\/TKDE.2007.1060","volume":"19","author":"G Gou","year":"2007","unstructured":"Gou, G., Chirkova, R.: Efficiently querying large XML data repositories: a survey. IEEE Trans. Knowl. Data Eng. 19(10), 1381\u20131403 (2007)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"4010_CR12","first-page":"2","volume":"15","author":"H Fan","year":"2018","unstructured":"Fan, H., Ma, Z., Wang, D., Liu, J.: Handling distributed XML queries over large XML data based on MapReduce framework. Inform. Sci. 15, 2\u201389 (2018)","journal-title":"Inform. Sci."},{"key":"4010_CR13","doi-asserted-by":"crossref","unstructured":"Chen, R., Liao, H.: ParaParse: A parallel method for XML parsing. In: Proceedings of the 3rd IEEE International Conference on Communication Software and Networks (ICCSN2011) 2011, pp. 81\u201385","DOI":"10.1109\/ICCSN.2011.6014223"},{"issue":"19","key":"4010_CR14","first-page":"7583","volume":"9","author":"R Chen","year":"2013","unstructured":"Chen, R., Liao, H., Wang, Z.: Parallel XPath evaluation based on node relation matrix. J. Comput. Inform. Syst. 9(19), 7583\u20137592 (2013)","journal-title":"J. Comput. Inform. Syst."},{"key":"4010_CR15","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-021-04074-y","author":"R Chen","year":"2021","unstructured":"Chen, R., Wang, Z., Su, H., Xie, S., Wang, Z.: Parallel XPath query based on cost optimization. J. Supercomput. (2021). https:\/\/doi.org\/10.1007\/s11227-021-04074-y","journal-title":"J. Supercomput."},{"issue":"2","key":"4010_CR16","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1145\/1328854.1328858","volume":"36","author":"BT Cate","year":"2007","unstructured":"Cate, B.T., Marx, M.: Navigational XPath. ACM. SIGMOD Record 36(2), 19\u201326 (2007)","journal-title":"SIGMOD Record"},{"key":"4010_CR17","doi-asserted-by":"crossref","unstructured":"Bruno, N., Koudas, N., Srivastava, D.: Holistic twig joins: optimal XML pattern matching. In: Proceedings of the 2002 ACM SIGMOD International Conference on Management of Data, Madison, Wisconsin, USA, June 3\u20136, 2002 2002, pp. 310\u2013321. ACM","DOI":"10.1145\/564691.564727"},{"issue":"04","key":"4010_CR18","doi-asserted-by":"publisher","first-page":"1439","DOI":"10.1109\/TKDE.2019.2946157","volume":"33","author":"P Lukas","year":"2021","unstructured":"Lukas, P., Baca, R., Kratky, M., Ling, T.W.: Demythization of structural XML query processing: comparison of holistic and binary approaches. IEEE Trans. Knowl. Data Eng. 33(04), 1439\u20131452 (2021)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"4010_CR19","doi-asserted-by":"crossref","unstructured":"Sato, S., Hao, W., Matsuzaki, K.: Parallelization of XPath Queries Using Modern XQuery Processors. In: New Trends in Databases and Information Systems. ADBIS 2018 2018 (2018)","DOI":"10.1007\/978-3-030-00063-9_7"},{"key":"4010_CR20","doi-asserted-by":"crossref","unstructured":"Mortier, R., Narayanan, D., Donnelly, A., Rowstron, A.: Seaweed: Distributed Scalable Ad Hoc Querying. In: International Conference on Data Engineering Workshops 2006","DOI":"10.1109\/ICDEW.2006.132"},{"issue":"11","key":"4010_CR21","first-page":"1","volume":"215","author":"T White","year":"2012","unstructured":"White, T.: Hadoop: the definitive guide. O\u2019rlly Media Inc Gravenstn Highway North 215(11), 1\u20134 (2012)","journal-title":"O'rlly Media Inc Gravenstn Highway North"},{"key":"4010_CR22","unstructured":"Zaharia, M., Chowdhury, M., Franklin, M.J., Shenker, S., Stoica, I.: Spark: Cluster computing with working sets. (2010)."},{"key":"4010_CR23","doi-asserted-by":"crossref","unstructured":"Choi, H., Lee, K.H., Kim, S.H., Lee, Y.J., Moon, B.: HadoopXML: a suite for parallel processing of massive XML data with multiple twig pattern queries. In: Acm International Conference on Information & Knowledge Management 2012","DOI":"10.1145\/2396761.2398745"},{"key":"4010_CR24","unstructured":"Owen, S., Kwon, H.: Spark-XML. https:\/\/github.com\/databricks\/spark-xml (2015)."},{"key":"4010_CR25","doi-asserted-by":"crossref","unstructured":"Bidoit, N., Colazzo, D., Sartiani, C., Solimando, A., Ulliana, F.: Andromeda: a system for processing queries and updates on big XML documents. In: East European Conference on Advances in Databases & Information Systems 2015","DOI":"10.1007\/978-3-319-23201-0_24"},{"issue":"1","key":"4010_CR26","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/s10796-017-9744-4","volume":"20","author":"N Bidoit","year":"2018","unstructured":"Bidoit, N., Colazzo, D., Malla, N., Sartiani, C.: Evaluating Queries and Updates on Big XML Documents. Inf. Syst. Front. 20(1), 63\u201390 (2018)","journal-title":"Inf. Syst. Front."},{"issue":"7","key":"4010_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TKDE.2015.2391110","volume":"27","author":"J Camacho-Rodriguez","year":"2015","unstructured":"Camacho-Rodriguez, J., Colazzo, D., Manolescu, I.: PAXQuery: Efficient Parallel Processing of Complex XQuery. IEEE Trans. Knowl. Data Eng. 27(7), 1\u20131 (2015)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"4010_CR28","unstructured":"Boag, S., Chamberlin, D., Fern\u00e1ndez, M.F., Florescu, D., Robie, J., Sim\u00e9on, J., Stefanescu, M.: XQuery 1.0: An XML query language (Second Edition). W3C working draft (2010)."},{"key":"4010_CR29","unstructured":"Carman, E.P., Westmann, T., Borkar, V.R., Carey, M.J., Tsotras, V.J.: A scalable parallel XQuery processor. In: IEEE International Conference on Big Data 2015"},{"key":"4010_CR30","unstructured":"Using Oracle XQuery for Hadoop. http:\/\/docs.oracle.com\/cd\/E63064_01\/doc.42\/e63063\/oxh.htm #BDCUG527 (2016)."},{"key":"4010_CR31","doi-asserted-by":"crossref","unstructured":"Hricov, R., \u0160enk, A., Kroha, P., Valenta, M.: Evaluation of XPath Queries Over XML Documents Using SparkSQL Framework. In: International Conference: Beyond Databases, Architectures and Structures 2017","DOI":"10.1007\/978-3-319-58274-0_3"},{"key":"4010_CR32","unstructured":"Khatchadourian, S., Mariano P. Consens, Sim\u00e9on, J.: Having a ChuQL at XML on the Cloud. In: AMW 2011"},{"key":"4010_CR33","unstructured":"Fegaras, L., Philip, J.J.: XML Query Optimization in Map-Reduce. In: International Workshop on the Web & Databases 2011"},{"key":"4010_CR34","doi-asserted-by":"crossref","unstructured":"Senk, A., Valenta, M., Benn, W.: Distributed Evaluation of XPath Axes Queries over Large XML Documents Stored in MapReduce Clusters Paper presented at the DEXA.2014,","DOI":"10.1109\/DEXA.2014.59"},{"key":"4010_CR35","doi-asserted-by":"crossref","unstructured":"Damigos, M., Gergatsoulis, M., Plitsos, S.: Distributed Processing of XPath Queries Using MapReduce. (2014).","DOI":"10.1007\/978-3-319-01863-8_8"},{"issue":"3","key":"4010_CR36","doi-asserted-by":"publisher","first-page":"70","DOI":"10.4018\/IJGHPC.2016070105","volume":"8","author":"S Kunfang","year":"2016","unstructured":"Kunfang, S., Lu, H.: Efficient querying distributed big-XML Data using MapReduce. Int. J. Grid High Perf. Comput. 8(3), 70\u201379 (2016)","journal-title":"Int. J. Grid High Perf. Comput."},{"key":"4010_CR37","first-page":"83","volume":"161","author":"BA Liang","year":"2021","unstructured":"Liang, B.A., Jin, Y.A., Cqw, B., Hq, A., Xin, Z.A., Sc, A.: XML2HBase: Storing and querying large collections of XML documents using a NoSQL database system. J. Parall. Distrib.Comput. 161, 83\u201399 (2021)","journal-title":"J. Parall. Distrib.Comput."},{"key":"4010_CR38","unstructured":"Apache HBase. https:\/\/hbase.apache.org\/."},{"issue":"6","key":"4010_CR39","doi-asserted-by":"publisher","first-page":"1994","DOI":"10.1109\/TCBB.2019.2915811","volume":"17","author":"J Liu","year":"2020","unstructured":"Liu, J., Liu, Q., Zhang, L., Su, S., Liu, Y.: Enabling massive XML-based biological data management in HBase. IEEE\/ACM Trans. Comput. Biol. Bioinf. 17(6), 1994\u20132004 (2020)","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinf."},{"key":"4010_CR40","doi-asserted-by":"crossref","unstructured":"Longjian, Y., Koide, H., Cavendish, D., Sakurai, K.: Efficient Shortest Path Routing Algorithms for Distributed XML Processing. In: Proceedings of the 15th International Conference on Web Information Systems and Technologies 2019, pp. 265\u2013272","DOI":"10.5220\/0008162002650272"},{"issue":"1","key":"4010_CR41","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1007\/s11390-017-1707-1","volume":"32","author":"X Bi","year":"2017","unstructured":"Bi, X., Zhao, X.G., Wang, G.R.: Efficient processing of distributed twig queries based on node distribution. J. Comput. Sci. Technol. 32(1), 78\u201392 (2017)","journal-title":"J. Comput. Sci. Technol."},{"key":"4010_CR42","doi-asserted-by":"publisher","first-page":"29127","DOI":"10.1109\/ACCESS.2021.3058383","volume":"9","author":"S Subramaniam","year":"2021","unstructured":"Subramaniam, S., Haw, S.C., Soon, L.K.: Improved centralized XML query processing using distributed query workload. IEEE Access 9, 29127\u201329142 (2021)","journal-title":"IEEE Access"},{"key":"4010_CR43","doi-asserted-by":"crossref","unstructured":"Fan, H., Yang, H., Ma, Z., Liu, J.: TwigStack-MR: An Approach to Distributed XML Twig Query Using MapReduce. In: IEEE International Congress on Big Data 2016, pp. 133\u2013140","DOI":"10.1109\/BigDataCongress.2016.79"},{"key":"4010_CR44","doi-asserted-by":"crossref","unstructured":"Braganholo, V., Mattoso, M.: A Survey on XML Fragmentation. ACM SIGMOD Record (2014).","DOI":"10.1145\/2694428.2694434"},{"issue":"2","key":"4010_CR45","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1007\/s11227-013-1008-6","volume":"67","author":"H Choi","year":"2014","unstructured":"Choi, H., Lee, K.H., Lee, Y.J.: Parallel labeling of massive XML data with MapReduce. J. Supercomput. 67(2), 408\u2013437 (2014)","journal-title":"J. Supercomput."},{"key":"4010_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, C., Naughton, J., DeWitt, D., Luo, Q., Lohman, G.: On supporting containment queries in relational database management systems. In: ACM SIGMOD Record, 2001 2001, vol. 2, pp. 425\u2013436. ACM","DOI":"10.1145\/376284.375722"},{"issue":"1","key":"4010_CR47","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.datak.2010.08.001","volume":"70","author":"J Lu","year":"2011","unstructured":"Lu, J., Meng, X., Ling, T.W.: Indexing and querying XML using extended Dewey labeling scheme. Data Knowl. Eng. 70(1), 35\u201359 (2011)","journal-title":"Data Knowl. Eng."},{"key":"4010_CR48","doi-asserted-by":"crossref","unstructured":"Hsu, W.-C., Shih, H.-C., Liao, I.-E.: A scalable XML indexing method using MapReduce. In: Fourth edition of the International Conference on the Innovative Computing Technology (INTECH 2014) 2014, pp. 81\u201386. IEEE","DOI":"10.1109\/INTECH.2014.6927757"},{"key":"4010_CR49","doi-asserted-by":"crossref","unstructured":"Schmidt, A., Waas, F., Kersten, M., Carey, M.J., Manolescu, I., Busse, R.: XMark: A benchmark for XML data management. In: Proceedings of the 28th international conference on Very Large Data Bases 2002, pp. 974\u2013985. VLDB Endowment","DOI":"10.1016\/B978-155860869-6\/50096-2"},{"key":"4010_CR50","doi-asserted-by":"crossref","unstructured":"Afrati, F., Damigos, M., Gergatsoulis, M.: Lower bounds on the communication of XPath queries in MapReduce. (2015).","DOI":"10.1007\/978-3-319-01863-8_8"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-023-04010-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10586-023-04010-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-023-04010-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T09:13:35Z","timestamp":1729415615000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10586-023-04010-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,13]]},"references-count":50,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["4010"],"URL":"https:\/\/doi.org\/10.1007\/s10586-023-04010-0","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"value":"1386-7857","type":"print"},{"value":"1573-7543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,13]]},"assertion":[{"value":"20 January 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 March 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 April 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"There is no conflict of interest by any of the authors of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}