{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T13:53:36Z","timestamp":1781877216465,"version":"3.54.5"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819538263","type":"print"},{"value":"9789819538270","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-3827-0_36","type":"book-chapter","created":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T13:06:52Z","timestamp":1781874412000},"page":"492-508","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["NanoCSV: Enabling Efficient Parallel CSV Extraction with\u00a0Hierarchical Finite-State Transducer"],"prefix":"10.1007","author":[{"given":"Peiyuan","family":"Dai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,20]]},"reference":[{"key":"36_CR1","doi-asserted-by":"crossref","unstructured":"Alagiannis, I., Borovica, R., Branco, M., Idreos, S., Ailamaki, A.: NoDB: efficient query execution on raw data files. In: ACM International Conference on Management of Data (SIGMOD), pp. 241\u2013252 (2012)","DOI":"10.1145\/2213836.2213864"},{"key":"36_CR2","unstructured":"Apache Spark (2024). https:\/\/spark.apache.org. Accessed 18 Oct 2024"},{"issue":"6","key":"36_CR3","doi-asserted-by":"publisher","first-page":"1799","DOI":"10.1007\/s10618-019-00646-y","volume":"33","author":"GJJ van\u00a0den Burg","year":"2019","unstructured":"van\u00a0den Burg, G.J.J., Naz\u00e1bal, A., Sutton, C.: Wrangling messy CSV files by detecting row and type patterns. Data Min. Knowl. Disc. 33(6), 1799\u20131820 (2019). https:\/\/doi.org\/10.1007\/s10618-019-00646-y","journal-title":"Data Min. Knowl. Disc."},{"key":"36_CR4","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Rusu, F.: Parallel in-situ data processing with speculative loading. In: ACM International Conference on Management of Data (SIGMOD), pp. 1287\u20131298 (2014)","DOI":"10.1145\/2588555.2593673"},{"issue":"11","key":"36_CR5","doi-asserted-by":"publisher","first-page":"2075","DOI":"10.14778\/3407790.3407810","volume":"13","author":"C Christodoulakis","year":"2020","unstructured":"Christodoulakis, C., Munson, E.B., Gabel, M., Brown, A.D., Miller, R.J.: Pytheas: Pattern-based table discovery in CSV files. VLDB Endowment 13(11), 2075\u20132089 (2020)","journal-title":"VLDB Endowment"},{"key":"36_CR6","doi-asserted-by":"crossref","unstructured":"Ding, C., Tang, D., Liang, X., Elmore, A.J., Krishnan, S.: CIAO: an optimization framework for client-assisted data loading. In: IEEE International Conference on Data Engineering (ICDE), pp. 1979\u20131984 (2021)","DOI":"10.1109\/ICDE51399.2021.00187"},{"key":"36_CR7","doi-asserted-by":"crossref","unstructured":"D\u00f6hmen, T., M\u00fchleisen, H., Boncz, P.A.: Multi-hypothesis CSV parsing. In: International Conference on Scientific and Statistical Database Management (SSDBM), pp. 16:1\u201316:12 (2017)","DOI":"10.1145\/3085504.3085520"},{"key":"36_CR8","doi-asserted-by":"crossref","unstructured":"Fathollahzadeh, S., Boehm, M.: GIO: generating efficient matrix and frame readers for custom data formats by example. Proc. ACM Manag. Data 1(2), 120:1\u2013120:26 (2023)","DOI":"10.1145\/3589265"},{"key":"36_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2023.102183","volume":"115","author":"H Gavriilidis","year":"2023","unstructured":"Gavriilidis, H., Henze, F., Zacharatou, E.T., Markl, V.: SheetReader: efficient specialized spreadsheet parsing. Inf. Syst. 115, 102183 (2023)","journal-title":"Inf. Syst."},{"key":"36_CR10","doi-asserted-by":"crossref","unstructured":"Ge, C., Li, Y., Eilebrecht, E., Chandramouli, B., Kossmann, D.: Speculative distributed CSV data parsing for big data analytics. In: ACM International Conference on Management of Data (SIGMOD), pp. 883\u2013899 (2019)","DOI":"10.1145\/3299869.3319898"},{"key":"36_CR11","doi-asserted-by":"publisher","unstructured":"Haesendonck, G., Maroy, W., Heyvaert, P., Verborgh, R., Dimou, A.: Parallel RDF generation from heterogeneous big data. In: Groppe, S., Gruenwald, L. (eds.) Proceedings of the International Workshop on Semantic Big Data, SBD@SIGMOD 2019, Amsterdam, The Netherlands, 5 July 2019, pp. 1:1\u20131:6. ACM (2019). https:\/\/doi.org\/10.1145\/3323878.3325802","DOI":"10.1145\/3323878.3325802"},{"key":"36_CR12","doi-asserted-by":"crossref","unstructured":"Jiang, L., Zhao, Z.: JSONSki: streaming semi-structured data with bit-parallel fast-forwarding. In: ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), pp. 200\u2013211 (2022)","DOI":"10.1145\/3503222.3507719"},{"issue":"12","key":"36_CR13","doi-asserted-by":"publisher","first-page":"972","DOI":"10.14778\/2994509.2994516","volume":"9","author":"M Karpathiotakis","year":"2016","unstructured":"Karpathiotakis, M., Alagiannis, I., Ailamaki, A.: Fast queries over heterogeneous data through engine customization. VLDB Endowment 9(12), 972\u2013983 (2016)","journal-title":"VLDB Endowment"},{"key":"36_CR14","unstructured":"Kirk, D.B., Hwu, W.W.: Programming Massively Parallel Processors - A Hands-on Approach. Morgan Kaufmann (2010)"},{"issue":"12","key":"36_CR15","doi-asserted-by":"publisher","first-page":"2871","DOI":"10.14778\/3476311.3476366","volume":"14","author":"C Koutras","year":"2021","unstructured":"Koutras, C., et al.: Valentine in action: matching tabular data at scale. VLDB Endowment 14(12), 2871\u20132874 (2021)","journal-title":"VLDB Endowment"},{"key":"36_CR16","unstructured":"Kumaigorodski, A., Lutz, C., Markl, V.: Fast CSV loading using GPUs and RDMA for in-memory data processing. In: Sattler, K., Herschel, M., Lehner, W. (eds.) Datenbanksysteme f\u00fcr Business, Technologie und Web (BTW). LNI, vol. 311, pp. 19\u201338 (2021)"},{"issue":"6","key":"36_CR17","doi-asserted-by":"publisher","first-page":"941","DOI":"10.1007\/s00778-019-00578-5","volume":"28","author":"G Langdale","year":"2019","unstructured":"Langdale, G., Lemire, D.: Parsing gigabytes of JSON per second. VLDB J. 28(6), 941\u2013960 (2019). https:\/\/doi.org\/10.1007\/s00778-019-00578-5","journal-title":"VLDB J."},{"issue":"10","key":"36_CR18","doi-asserted-by":"publisher","first-page":"1118","DOI":"10.14778\/3115404.3115416","volume":"10","author":"Y Li","year":"2017","unstructured":"Li, Y., Katsipoulakis, N.R., Chandramouli, B., et al.: Mison: a fast JSON parser for data analytics. Proc. VLDB Endowment 10(10), 1118\u20131129 (2017)","journal-title":"Proc. VLDB Endowment"},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"Luong, J., Habich, D., Lehner, W.: A technical perspective of DataCalc - ad-hoc analyses on heterogeneous data sources. In: IEEE International Conference on Big Data (IEEE BigData), pp. 3864\u20133873 (2019)","DOI":"10.1109\/BigData47090.2019.9006029"},{"key":"36_CR20","unstructured":"MongoDB (2024). https:\/\/www.mongodb.com. Accessed 18 Oct 2024"},{"issue":"14","key":"36_CR21","doi-asserted-by":"publisher","first-page":"1702","DOI":"10.14778\/2556549.2556555","volume":"6","author":"T M\u00fchlbauer","year":"2013","unstructured":"M\u00fchlbauer, T., R\u00f6diger, W., Seilbeck, R., Reiser, A., Kemper, A., Neumann, T.: Instant loading for main memory databases. VLDB Endowment 6(14), 1702\u20131713 (2013)","journal-title":"VLDB Endowment"},{"key":"36_CR22","unstructured":"Pandas (2024). https:\/\/pandas.pydata.org. Accessed 18 Oct 2024"},{"key":"36_CR23","doi-asserted-by":"crossref","unstructured":"Raasveldt, M., M\u00fchleisen, H.: DuckDB: an embeddable analytical database. In: Boncz, P.A., Manegold, S., Ailamaki, A., Deshpande, A., Kraska, T. (eds.) Proceedings of the 2019 International Conference on Management of Data, SIGMOD Conference 2019, Amsterdam, The Netherlands, 30 June\u20135 July 2019, pp. 1981\u20131984. ACM (2019)","DOI":"10.1145\/3299869.3320212"},{"key":"36_CR24","first-page":"1","volume":"4180","author":"Y Shafranovich","year":"2005","unstructured":"Shafranovich, Y.: Common format and MIME type for comma-separated values (CSV) files. RFC 4180, 1\u20138 (2005)","journal-title":"RFC"},{"issue":"5","key":"36_CR25","doi-asserted-by":"publisher","first-page":"1119","DOI":"10.14778\/3510397.3510408","volume":"15","author":"M Sichert","year":"2022","unstructured":"Sichert, M., Neumann, T.: User-defined operators: efficiently integrating custom algorithms into modern databases. VLDB Endowment 15(5), 1119\u20131131 (2022)","journal-title":"VLDB Endowment"},{"key":"36_CR26","unstructured":"SIMDCSV (2024). https:\/\/github.com\/geofflangdale\/simdcsv. Accessed 18 Oct 2024"},{"key":"36_CR27","unstructured":"TensorFlow (2024). https:\/\/www.tensorflow.org. Accessed 18 Oct 2024"},{"issue":"8","key":"36_CR28","doi-asserted-by":"publisher","first-page":"1870","DOI":"10.14778\/3594512.3594518","volume":"16","author":"G Vitagliano","year":"2023","unstructured":"Vitagliano, G., Hameed, M., Jiang, L., Reisener, L., Wu, E., Naumann, F.: Pollock: a data loading benchmark. VLDB Endowment 16(8), 1870\u20131882 (2023)","journal-title":"VLDB Endowment"},{"issue":"2","key":"36_CR29","first-page":"393","volume":"21","author":"J Wang","year":"2020","unstructured":"Wang, J., Yang, Y., Wang, T., et al.: Big data service architecture: a survey. J. Internet Technol. 21(2), 393\u2013405 (2020)","journal-title":"J. Internet Technol."},{"key":"36_CR30","doi-asserted-by":"crossref","unstructured":"Xie, D., Chandramouli, B., Li, Y., Kossmann, D.: FishStore: faster ingestion with subset hashing. In: ACM International Conference on Management of Data (SIGMOD), pp. 1711\u20131728 (2019)","DOI":"10.1145\/3299869.3319896"}],"container-title":["Lecture Notes in Computer Science","Database Systems for Advanced Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3827-0_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T13:07:07Z","timestamp":1781874427000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3827-0_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819538263","9789819538270"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3827-0_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"20 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DASFAA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Database Systems for Advanced Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 May 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 May 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dasfaa2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/dasfaa2025.github.io","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}