{"id":"https://openalex.org/W2082932857","doi":"https://doi.org/10.1145/1376616.1376683","title":"Improving suffix array locality for fast pattern matching on disk","display_name":"Improving suffix array locality for fast pattern matching on disk","publication_year":2008,"publication_date":"2008-06-09","ids":{"openalex":"https://openalex.org/W2082932857","doi":"https://doi.org/10.1145/1376616.1376683","mag":"2082932857"},"language":"en","primary_location":{"id":"doi:10.1145/1376616.1376683","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1376616.1376683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2008 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103352210","display_name":"Ranjan Sinha","orcid":null},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Ranjan Sinha","raw_affiliation_strings":["The University of Melbourne, Melbourne, Australia","The University of Melbourne, Melbourne, Australia;"],"affiliations":[{"raw_affiliation_string":"The University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"The University of Melbourne, Melbourne, Australia;","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021097696","display_name":"Simon J. Puglisi","orcid":"https://orcid.org/0000-0001-7668-7636"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Simon Puglisi","raw_affiliation_strings":["RMIT University, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081861848","display_name":"Alistair Moffat","orcid":"https://orcid.org/0000-0002-6638-0232"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Alistair Moffat","raw_affiliation_strings":["The University of Melbourne, Melbourne, Australia","The University of Melbourne, Melbourne, Australia;"],"affiliations":[{"raw_affiliation_string":"The University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"The University of Melbourne, Melbourne, Australia;","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014748363","display_name":"Andrew Turpin","orcid":"https://orcid.org/0000-0003-2559-8769"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Andrew Turpin","raw_affiliation_strings":["RMIT University, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103352210"],"corresponding_institution_ids":["https://openalex.org/I165779595"],"apc_list":null,"apc_paid":null,"fwci":7.0246,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.96573833,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"661","last_page":"672"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9843000173568726,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/compressed-suffix-array","display_name":"Compressed suffix array","score":0.9223451018333435},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.8593008518218994},{"id":"https://openalex.org/keywords/generalized-suffix-tree","display_name":"Generalized suffix tree","score":0.8374933004379272},{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.8286008834838867},{"id":"https://openalex.org/keywords/suffix-array","display_name":"Suffix array","score":0.8225952386856079},{"id":"https://openalex.org/keywords/trie","display_name":"Trie","score":0.7776305079460144},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7706709504127502},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.5658718943595886},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.5327603220939636},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.5193617939949036},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4596523642539978},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4147580862045288},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3840155005455017},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3718219995498657},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3270654082298279},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1713988482952118},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1666719615459442},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.12386542558670044},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.084841787815094}],"concepts":[{"id":"https://openalex.org/C100903775","wikidata":"https://www.wikidata.org/wiki/Q5157028","display_name":"Compressed suffix array","level":4,"score":0.9223451018333435},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.8593008518218994},{"id":"https://openalex.org/C118146561","wikidata":"https://www.wikidata.org/wiki/Q5532514","display_name":"Generalized suffix tree","level":4,"score":0.8374933004379272},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.8286008834838867},{"id":"https://openalex.org/C2779259728","wikidata":"https://www.wikidata.org/wiki/Q281472","display_name":"Suffix array","level":3,"score":0.8225952386856079},{"id":"https://openalex.org/C190290938","wikidata":"https://www.wikidata.org/wiki/Q387015","display_name":"Trie","level":3,"score":0.7776305079460144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7706709504127502},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.5658718943595886},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.5327603220939636},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.5193617939949036},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4596523642539978},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4147580862045288},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3840155005455017},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3718219995498657},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3270654082298279},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1713988482952118},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1666719615459442},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.12386542558670044},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.084841787815094},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1145/1376616.1376683","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1376616.1376683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2008 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:researchbank.rmit.edu.au:rmit:12177","is_oa":false,"landing_page_url":"http://researchbank.rmit.edu.au/view/rmit:12177","pdf_url":null,"source":{"id":"https://openalex.org/S4306402074","display_name":"RMIT Research Repository (RMIT University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I82951845","host_organization_name":"RMIT University","host_organization_lineage":["https://openalex.org/I82951845"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.183.9556","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.183.9556","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.seg.rmit.edu.au/research/download.php?manuscript=247","raw_type":"text"},{"id":"pmh:oai:alma.61RMIT_INST:11247453910001341","is_oa":false,"landing_page_url":"http://doi.org/10.1145/1376616.1376683","pdf_url":null,"source":{"id":"https://openalex.org/S4306402074","display_name":"RMIT Research Repository (RMIT University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I82951845","host_organization_name":"RMIT University","host_organization_lineage":["https://openalex.org/I82951845"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:figshare.com:article/27363711","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:jupiter.its.unimelb.edu.au:11343/31646","is_oa":false,"landing_page_url":"http://hdl.handle.net/11343/31646","pdf_url":null,"source":{"id":"https://openalex.org/S4377196259","display_name":"Minerva Access (University of Melbourne)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I165779595","host_organization_name":"The University of Melbourne","host_organization_lineage":["https://openalex.org/I165779595"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"the 2008 ACM SIGMOD international conference","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/27363711","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W96331545","https://openalex.org/W1485516007","https://openalex.org/W1489909987","https://openalex.org/W1726445723","https://openalex.org/W1974956214","https://openalex.org/W1976682045","https://openalex.org/W1990061958","https://openalex.org/W2030962049","https://openalex.org/W2032459394","https://openalex.org/W2055043387","https://openalex.org/W2059513841","https://openalex.org/W2077333702","https://openalex.org/W2079721227","https://openalex.org/W2088386938","https://openalex.org/W2096967468","https://openalex.org/W2109062349","https://openalex.org/W2117666586","https://openalex.org/W2121252285","https://openalex.org/W2124348703","https://openalex.org/W2133363953","https://openalex.org/W2134283755","https://openalex.org/W2152506638","https://openalex.org/W2158874082","https://openalex.org/W2159742629","https://openalex.org/W2533248932","https://openalex.org/W4245145908","https://openalex.org/W4251728543","https://openalex.org/W4285719527","https://openalex.org/W6728628127","https://openalex.org/W7008733651"],"related_works":["https://openalex.org/W2063841356","https://openalex.org/W2405149725","https://openalex.org/W2003608043","https://openalex.org/W2118703123","https://openalex.org/W1527782099","https://openalex.org/W2067974452","https://openalex.org/W4385595111","https://openalex.org/W1543263356","https://openalex.org/W2082932857","https://openalex.org/W3157818565"],"abstract_inverted_index":{"The":[0],"suffix":[1,7,39,61,82,103],"tree":[2],"(or":[3],"equivalently,":[4],"the":[5,34,53,78,102],"enhanced":[6],"array)":[8],"provides":[9],"efficient":[10],"solutions":[11],"to":[12,68,100],"many":[13],"problems":[14],"involving":[15],"pattern":[16,19],"matching":[17],"and":[18,59,105],"discovery":[20],"in":[21,28,48],"large":[22],"strings,":[23],"such":[24],"as":[25,71,73],"those":[26],"arising":[27],"computational":[29],"biology.":[30],"Here":[31],"we":[32],"address":[33],"problem":[35],"of":[36,55,86,97],"arranging":[37],"a":[38,56,60],"array":[40,83],"on":[41,95],"disk":[42],"so":[43],"that":[44,52,98],"querying":[45],"is":[46],"fast":[47],"practice.":[49],"We":[50],"show":[51],"combination":[54],"small":[57],"trie":[58],"array-like":[62],"blocked":[63],"data":[64,88],"structure":[65,89],"allows":[66],"queries":[67],"be":[69],"answered":[70],"much":[72],"three":[74],"times":[75],"faster":[76],"than":[77],"best":[79],"alternative":[80],"disk-based":[81],"arrangement.":[84],"Construction":[85],"our":[87],"requires":[90,106],"only":[91],"modest":[92],"processing":[93],"time":[94],"top":[96],"required":[99],"build":[101],"tree,":[104],"negligible":[107],"extra":[108],"memory.":[109]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}