{"id":"https://openalex.org/W3091491979","doi":"https://doi.org/10.1145/3428286","title":"Regex matching with counting-set automata","display_name":"Regex matching with counting-set automata","publication_year":2020,"publication_date":"2020-11-13","ids":{"openalex":"https://openalex.org/W3091491979","doi":"https://doi.org/10.1145/3428286","mag":"3091491979"},"language":"en","primary_location":{"id":"doi:10.1145/3428286","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3428286","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3428286","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Programming Languages","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3428286","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040652386","display_name":"Lenka Turo\u0148ov\u00e1","orcid":"https://orcid.org/0000-0003-1450-6136"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lenka Turo\u0148ov\u00e1","raw_affiliation_strings":["Brno University of Technology, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059358773","display_name":"Luk\u00e1\u0161 Hol\u00edk","orcid":"https://orcid.org/0000-0001-6957-1651"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Luk\u00e1\u0161 Hol\u00edk","raw_affiliation_strings":["Brno University of Technology, Czechia"],"raw_orcid":"https://orcid.org/0000-0001-6957-1651","affiliations":[{"raw_affiliation_string":"Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063557188","display_name":"Ond\u0159ej Leng\u00e1l","orcid":"https://orcid.org/0000-0002-3038-5875"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Ond\u0159ej Leng\u00e1l","raw_affiliation_strings":["Brno University of Technology, Czechia"],"raw_orcid":"https://orcid.org/0000-0002-3038-5875","affiliations":[{"raw_affiliation_string":"Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001454502","display_name":"Olli Saarikivi","orcid":"https://orcid.org/0000-0001-7596-4734"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Olli Saarikivi","raw_affiliation_strings":["Microsoft, USA"],"raw_orcid":"https://orcid.org/0000-0001-7596-4734","affiliations":[{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060114046","display_name":"Margus Veanes","orcid":"https://orcid.org/0009-0008-8427-7977"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Margus Veanes","raw_affiliation_strings":["Microsoft, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086446392","display_name":"Tom\u00e1\u0161 Vojnar","orcid":"https://orcid.org/0000-0002-2746-8792"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Tom\u00e1\u0161 Vojnar","raw_affiliation_strings":["Brno University of Technology, Czechia"],"raw_orcid":"https://orcid.org/0000-0002-2746-8792","affiliations":[{"raw_affiliation_string":"Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3813,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.85822464,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"4","issue":"OOPSLA","first_page":"1","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11567","display_name":"semigroups and automata theory","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11567","display_name":"semigroups and automata theory","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9991999864578247,"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/T10911","display_name":"Chemical Synthesis and Analysis","score":0.9976999759674072,"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/computer-science","display_name":"Computer science","score":0.6864607930183411},{"id":"https://openalex.org/keywords/repetition","display_name":"Repetition (rhetorical device)","score":0.6626732349395752},{"id":"https://openalex.org/keywords/nondeterministic-algorithm","display_name":"Nondeterministic algorithm","score":0.6393730640411377},{"id":"https://openalex.org/keywords/regular-expression","display_name":"Regular expression","score":0.6039817929267883},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.5845998525619507},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.5793734788894653},{"id":"https://openalex.org/keywords/nondeterministic-finite-automaton","display_name":"Nondeterministic finite automaton","score":0.507373034954071},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5004997253417969},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4798588156700134},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.45284026861190796},{"id":"https://openalex.org/keywords/deterministic-pushdown-automaton","display_name":"Deterministic pushdown automaton","score":0.443433552980423},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.43271806836128235},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4123152494430542},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.364709734916687},{"id":"https://openalex.org/keywords/automata-theory","display_name":"Automata theory","score":0.2637760043144226},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25340914726257324},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09986722469329834}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6864607930183411},{"id":"https://openalex.org/C2776141515","wikidata":"https://www.wikidata.org/wiki/Q1274479","display_name":"Repetition (rhetorical device)","level":2,"score":0.6626732349395752},{"id":"https://openalex.org/C176181172","wikidata":"https://www.wikidata.org/wiki/Q3490301","display_name":"Nondeterministic algorithm","level":2,"score":0.6393730640411377},{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.6039817929267883},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.5845998525619507},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5793734788894653},{"id":"https://openalex.org/C158008952","wikidata":"https://www.wikidata.org/wiki/Q617295","display_name":"Nondeterministic finite automaton","level":4,"score":0.507373034954071},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5004997253417969},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4798588156700134},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.45284026861190796},{"id":"https://openalex.org/C74919329","wikidata":"https://www.wikidata.org/wiki/Q378713","display_name":"Deterministic pushdown automaton","level":5,"score":0.443433552980423},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.43271806836128235},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4123152494430542},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.364709734916687},{"id":"https://openalex.org/C116248031","wikidata":"https://www.wikidata.org/wiki/Q214526","display_name":"Automata theory","level":3,"score":0.2637760043144226},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25340914726257324},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09986722469329834},{"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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3428286","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3428286","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3428286","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Programming Languages","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3428286","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3428286","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3428286","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Programming Languages","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3091491979.pdf","grobid_xml":"https://content.openalex.org/works/W3091491979.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W129467524","https://openalex.org/W170989275","https://openalex.org/W563794187","https://openalex.org/W1501213188","https://openalex.org/W1503601067","https://openalex.org/W1511341314","https://openalex.org/W1608897385","https://openalex.org/W1822301642","https://openalex.org/W1834456443","https://openalex.org/W1842051783","https://openalex.org/W1968420454","https://openalex.org/W1975180460","https://openalex.org/W1975501418","https://openalex.org/W1994584977","https://openalex.org/W2031276295","https://openalex.org/W2041340246","https://openalex.org/W2057841333","https://openalex.org/W2060986421","https://openalex.org/W2072607050","https://openalex.org/W2077263738","https://openalex.org/W2077450865","https://openalex.org/W2090901599","https://openalex.org/W2092860912","https://openalex.org/W2094985106","https://openalex.org/W2108962885","https://openalex.org/W2128475506","https://openalex.org/W2134826720","https://openalex.org/W2156429182","https://openalex.org/W2157260510","https://openalex.org/W2161151447","https://openalex.org/W2204191597","https://openalex.org/W2899462170","https://openalex.org/W2912608078","https://openalex.org/W2913561688","https://openalex.org/W2922634639","https://openalex.org/W2968339949","https://openalex.org/W2968966662"],"related_works":["https://openalex.org/W4249650827","https://openalex.org/W2090734721","https://openalex.org/W2089404966","https://openalex.org/W3094387502","https://openalex.org/W2115419634","https://openalex.org/W3143588635","https://openalex.org/W2089302579","https://openalex.org/W2621024811","https://openalex.org/W3021003646","https://openalex.org/W2167032348"],"abstract_inverted_index":{"We":[0,52],"propose":[1],"a":[2,46,58,69,93],"solution":[3],"to":[4,63,77,133],"the":[5,108,111,118,123,126,129,153],"problem":[6],"of":[7,38,49,61,73,95,103,110,128,171,173],"efficient":[8],"matching":[9],"regular":[10],"expressions":[11],"(regexes)":[12],"with":[13,32,75,84,146,168,179,181],"bounded":[14,39,85],"repetition,":[15],"such":[16],"as":[17],"(ab){1,100},":[18],"using":[19],"deterministic":[20,64,140],"automata.":[21],"For":[22],"this,":[23],"we":[24],"introduce":[25],"novel":[26,70],"counting-set":[27],"automata":[28,31,79,83],"(CsAs)":[29],",":[30,81],"registers":[33],"that":[34,56,97,107,139],"can":[35,42],"hold":[36],"sets":[37],"integers":[40],"and":[41,87],"be":[43],"manipulated":[44],"by":[45],"limited":[47],"portfolio":[48],"constant-time":[50],"operations.":[51],"present":[53],"an":[54],"algorithm":[55],"compiles":[57],"large":[59],"sub-class":[60],"regexes":[62,74,145,167,180],"CsAs.":[65,99],"This":[66],"includes":[67],"(1)":[68],"Antimirov-style":[71],"translation":[72],"counting":[76,78],"(CAs)":[80],"nondeterministic":[82],"counters,":[86],"(2)":[88],"our":[89,158],"main":[90,101],"technical":[91],"contribution,":[92],"determinization":[94],"CAs":[96],"outputs":[98],"The":[100],"advantage":[102],"this":[104],"workflow":[105],"is":[106,131],"size":[109,127],"produced":[112,142],"CsAs":[113,141],"does":[114],"not":[115],"depend":[116],"on":[117,162],"repetition":[119,147,169,182],"bounds":[120],"used":[121],"in":[122],"regex":[124],"(while":[125],"DFA":[130],"exponential":[132],"them).":[134],"Our":[135],"experimental":[136],"results":[137],"confirm":[138],"from":[143],"practical":[144,166],"are":[148],"indeed":[149],"vastly":[150],"smaller":[151],"than":[152],"corresponding":[154],"DFAs.":[155],"More":[156],"importantly,":[157],"prototype":[159],"matcher":[160],"based":[161],"CsA":[163],"simulation":[164],"handles":[165],"regardless":[170],"sizes":[172],"counter":[174],"bounds.":[175],"It":[176],"easily":[177],"copes":[178],"where":[183],"state-of-the-art":[184],"matchers":[185],"struggle.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
