{"id":"https://openalex.org/W1603784832","doi":"https://doi.org/10.1137/s0097539702402354","title":"Compressed Suffix Arrays and Suffix Trees with Applications to Text Indexing and String Matching","display_name":"Compressed Suffix Arrays and Suffix Trees with Applications to Text Indexing and String Matching","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W1603784832","doi":"https://doi.org/10.1137/s0097539702402354","mag":"1603784832"},"language":"en","primary_location":{"id":"doi:10.1137/s0097539702402354","is_oa":false,"landing_page_url":"https://doi.org/10.1137/s0097539702402354","pdf_url":null,"source":{"id":"https://openalex.org/S153560523","display_name":"SIAM Journal on Computing","issn_l":"0097-5397","issn":["0097-5397","1095-7111"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1808/7177","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006984021","display_name":"Roberto Grossi","orcid":"https://orcid.org/0000-0002-7985-4222"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Roberto Grossi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Jeffrey Scott Vitter","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeffrey Scott Vitter","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5006984021"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":31.8219,"has_fulltext":false,"cited_by_count":185,"citation_normalized_percentile":{"value":0.99675253,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"35","issue":"2","first_page":"378","last_page":"407"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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":0.9998999834060669,"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":0.974399983882904,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9606000185012817,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/compressed-suffix-array","display_name":"Compressed suffix array","score":0.9068340063095093},{"id":"https://openalex.org/keywords/generalized-suffix-tree","display_name":"Generalized suffix tree","score":0.7076087594032288},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7075955271720886},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.6791545748710632},{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.6758999824523926},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.6687740087509155},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6451502442359924},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.439393550157547},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4344167709350586},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38489386439323425},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3204353451728821},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.31852906942367554},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.23089250922203064},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20000457763671875},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11177873611450195},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07595986127853394}],"concepts":[{"id":"https://openalex.org/C100903775","wikidata":"https://www.wikidata.org/wiki/Q5157028","display_name":"Compressed suffix array","level":4,"score":0.9068340063095093},{"id":"https://openalex.org/C118146561","wikidata":"https://www.wikidata.org/wiki/Q5532514","display_name":"Generalized suffix tree","level":4,"score":0.7076087594032288},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7075955271720886},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.6791545748710632},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.6758999824523926},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.6687740087509155},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6451502442359924},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.439393550157547},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4344167709350586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38489386439323425},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3204353451728821},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.31852906942367554},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.23089250922203064},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20000457763671875},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11177873611450195},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07595986127853394},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"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}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1137/s0097539702402354","is_oa":false,"landing_page_url":"https://doi.org/10.1137/s0097539702402354","pdf_url":null,"source":{"id":"https://openalex.org/S153560523","display_name":"SIAM Journal on Computing","issn_l":"0097-5397","issn":["0097-5397","1095-7111"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Computing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.156.968","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.156.968","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://faculty.cse.tamu.edu/jsv/Papers/GrV05.text_indexing.pdf","raw_type":"text"},{"id":"pmh:oai:arpi.unipi.it:11568/106854","is_oa":false,"landing_page_url":"http://hdl.handle.net/11568/106854","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:arpi.unipi.it:11568/166751","is_oa":false,"landing_page_url":"http://hdl.handle.net/11568/166751","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:arpi.unipi.it:11568/225939","is_oa":false,"landing_page_url":"http://hdl.handle.net/11568/225939","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:kuscholarworks.ku.edu:1808/7177","is_oa":true,"landing_page_url":"http://hdl.handle.net/1808/7177","pdf_url":null,"source":{"id":"https://openalex.org/S4306400421","display_name":"KU ScholarWorks (The University of Kansas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I146416000","host_organization_name":"University of Kansas","host_organization_lineage":["https://openalex.org/I146416000"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"mag:1603784832","is_oa":false,"landing_page_url":"http://ci.nii.ac.jp/naid/10012552297","pdf_url":null,"source":{"id":"https://openalex.org/S4306421003","display_name":"Symposium on the Theory of Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Symposium on the Theory of Computing","raw_type":null}],"best_oa_location":{"id":"pmh:oai:kuscholarworks.ku.edu:1808/7177","is_oa":true,"landing_page_url":"http://hdl.handle.net/1808/7177","pdf_url":null,"source":{"id":"https://openalex.org/S4306400421","display_name":"KU ScholarWorks (The University of Kansas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I146416000","host_organization_name":"University of Kansas","host_organization_lineage":["https://openalex.org/I146416000"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W938539187","https://openalex.org/W1972770363","https://openalex.org/W1983243118","https://openalex.org/W1985108724","https://openalex.org/W1986970296","https://openalex.org/W2003200876","https://openalex.org/W2003608043","https://openalex.org/W2017497752","https://openalex.org/W2018599113","https://openalex.org/W2019724649","https://openalex.org/W2024147613","https://openalex.org/W2030839740","https://openalex.org/W2030962049","https://openalex.org/W2035524445","https://openalex.org/W2041873531","https://openalex.org/W2047619746","https://openalex.org/W2049652268","https://openalex.org/W2057223122","https://openalex.org/W2059513841","https://openalex.org/W2060733691","https://openalex.org/W2078677252","https://openalex.org/W2087721273","https://openalex.org/W2114790712","https://openalex.org/W2121252285","https://openalex.org/W2125203709","https://openalex.org/W2133248397","https://openalex.org/W2135494327","https://openalex.org/W2154104338","https://openalex.org/W2155512447","https://openalex.org/W2158874082","https://openalex.org/W2163652601","https://openalex.org/W2165621523","https://openalex.org/W2912435829"],"related_works":["https://openalex.org/W2533248932","https://openalex.org/W2161488606","https://openalex.org/W2158874082","https://openalex.org/W2158322625","https://openalex.org/W2134696992","https://openalex.org/W2121252285","https://openalex.org/W2056707490","https://openalex.org/W2030962049","https://openalex.org/W1492127831","https://openalex.org/W2149243190","https://openalex.org/W2059513841","https://openalex.org/W2013697960","https://openalex.org/W1990061958","https://openalex.org/W1985174631","https://openalex.org/W2088386938","https://openalex.org/W1975454935","https://openalex.org/W1573714593","https://openalex.org/W2107079154","https://openalex.org/W2046038806","https://openalex.org/W1965853364"],"abstract_inverted_index":{"The":[0,50,69,102],"proliferation":[1],"of":[2,41,83,114,124,148,164,173,226,267,288,343,392],"online":[3,15,75],"text,":[4],"such":[5,176],"as":[6,34,177,366],"found":[7],"on":[8],"the":[9,18,95,108,127,133,157,183,210,245,274,286,289,292,299,310,328,348,357,370],"World":[10],"Wide":[11],"Web":[12],"and":[13,140,229,295,341],"in":[14,56,107,112,126,132,178,192,198,244,285,291,304,356,381],"databases,":[16],"motivates":[17],"need":[19,143],"for":[20,77,208,248,273,296,314],"space-efficient":[21],"text":[22,38,51,103,158,218,290],"indexing":[23,104,345],"methods":[24],"that":[25,220],"support":[26,73,188],"fast":[27,74,189,235],"string":[28,80],"searching.":[29],"We":[30,214],"model":[31],"this":[32],"scenario":[33],"follows:":[35],"Consider":[36],"a":[37,46,161,216,234,307,315,352,367,388],"T":[39,52,87],"consisting":[40],"n":[42,238,263,395],"symbols":[43],"drawn":[44],"from":[45],"fixed":[47],"alphabet":[48],"$\\Sigma$.":[49],"can":[53,321,376],"be":[54],"represented":[55],"$n":[57],"\\lg":[58,120,194,264,383],"|\\Sigma|$":[59,67],"bits":[60,123,266,385],"by":[61,160],"encoding":[62],"each":[63,147],"symbol":[64],"with":[65,86],"$\\lg":[66],"bits.":[68,151],"goal":[70],"is":[71,97,168,172,221,282,301,400],"to":[72,386],"queries":[76],"searching":[78],"any":[79,249],"pattern":[81,212,349],"P":[82],"m":[84],"symbols,":[85],"being":[88],"fully":[89],"scanned":[90],"only":[91],"once,":[92],"namely,":[93],"when":[94,170],"index":[96,219,279],"created":[98],"at":[99,257],"preprocessing":[100],"time.":[101],"schemes":[105],"published":[106],"literature":[109],"are":[110,154,372],"greedy":[111],"terms":[113],"space":[115,125,300,342],"usage:":[116],"they":[117],"require":[118,322],"$\\Omega(n":[119],"n)$":[121,150,201],"additional":[122],"worst":[128,246,293],"case.":[129],"For":[130],"example,":[131,309],"standard":[134],"unit":[135],"cost":[136,206],"RAM,":[137],"suffix":[138,141,227,230,312,330],"trees":[139],"arrays":[142,228],"$\\Omega(n)$":[144],"memory":[145],"words,":[146],"$\\Omega(\\lg":[149],"These":[152],"indexes":[153,187],"larger":[155],"than":[156],"itself":[159],"multiplicative":[162],"factor":[163,355],"$\\Omega(\\smash{\\lg_{|\\Sigma|}":[165],"n})$,":[166],"which":[167,399],"significant":[169],"$\\Sigma$":[171],"constant":[174,250],"size,":[175],"\\textsc{ascii}":[179,319],"or":[180,197,325],"\\textsc{unicode}.":[181],"On":[182],"other":[184],"hand,":[185],"these":[186],"searching,":[190],"either":[191],"$O(m":[193,199,393],"|\\Sigma|)$":[195,384],"time":[196,243,276,340,365],"+\\lg":[200],"time,":[202,398],"plus":[203],"an":[204,277],"output-sensitive":[205,358],"$O(\\mathit{occ})$":[207],"listing":[209],"$\\mathit{occ}$":[211],"occurrences.":[213],"present":[215],"new":[217],"based":[222],"upon":[223],"compressed":[224,311],"representations":[225],"trees.":[231],"It":[232],"achieves":[233],"$\\smash{O(m":[236],"/\\lg_{|\\Sigma|}":[237,394],"+":[239,260,396],"\\lg_{|\\Sigma|}^\\epsilon":[240],"n)}$":[241],"search":[242,390],"case,":[247,294],"$0":[251],"<":[252],"\\epsilon":[253],"\\leq":[254],"1$,":[255],"using":[256],"most":[258],"$\\smash{\\bigl(\\epsilon^{-1}":[259],"O(1)\\bigr)":[261],"\\,":[262,362],"|\\Sigma|}$":[265],"storage.":[268],"Our":[269,335],"result":[270],"thus":[271],"presents":[272],"first":[275],"efficient":[278],"whose":[280],"size":[281,287],"provably":[283],"linear":[284],"many":[297],"scenarios,":[298],"actually":[302],"sublinear":[303],"practice.":[305],"As":[306],"concrete":[308],"array":[313,331],"typical":[316],"100":[317],"MB":[318,324],"file":[320],"30--40":[323],"less,":[326],"while":[327],"raw":[329],"requires":[332],"500":[333],"MB.":[334],"theoretical":[336],"bounds":[337],"improve":[338],"\\emph{both}":[339],"previous":[344],"schemes.":[346],"Listing":[347],"occurrences":[350],"introduces":[351],"sublogarithmic":[353],"slowdown":[354],"cost,":[359],"giving":[360],"$O(\\mathit{occ}":[361],"\\smash{\\lg_{|\\Sigma|}^\\epsilon":[363],"n})$":[364],"result.":[368],"When":[369],"patterns":[371],"sufficiently":[373],"long,":[374],"we":[375],"use":[377],"auxiliary":[378],"data":[379],"structures":[380],"$O(n":[382],"obtain":[387],"total":[389],"bound":[391],"\\mathit{occ})$":[397],"optimal.":[401]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":12}],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2025-10-10T00:00:00"}