{"id":"https://openalex.org/W4381326842","doi":"https://doi.org/10.1145/3589297","title":"Exploiting Structure in Regular Expression Queries","display_name":"Exploiting Structure in Regular Expression Queries","publication_year":2023,"publication_date":"2023-06-13","ids":{"openalex":"https://openalex.org/W4381326842","doi":"https://doi.org/10.1145/3589297"},"language":"en","primary_location":{"id":"doi:10.1145/3589297","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589297","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589297","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"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 Management of Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3589297","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002967874","display_name":"Zhang Ling","orcid":"https://orcid.org/0009-0003-2228-3945"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ling Zhang","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, WI, USA"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036934715","display_name":"Shaleen Deep","orcid":"https://orcid.org/0000-0003-2342-4060"},"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":"Shaleen Deep","raw_affiliation_strings":["Microsoft Gray Systems Lab, Madison, WI, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Gray Systems Lab, Madison, WI, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020678151","display_name":"Avrilia Floratou","orcid":"https://orcid.org/0009-0007-5760-8657"},"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":"Avrilia Floratou","raw_affiliation_strings":["Microsoft Gray Systems Lab, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Gray Systems Lab, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043472177","display_name":"Anja Gruenheid","orcid":"https://orcid.org/0009-0009-2547-8610"},"institutions":[{"id":"https://openalex.org/I4210139986","display_name":"Microsoft (Switzerland)","ror":"https://ror.org/03zryq964","country_code":"CH","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210139986"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Anja Gruenheid","raw_affiliation_strings":["Microsoft Gray Systems Lab, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Microsoft Gray Systems Lab, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210139986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069237428","display_name":"Jignesh M. Patel","orcid":"https://orcid.org/0000-0003-3653-2538"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jignesh M. Patel","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, WI, USA"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101749826","display_name":"Yiwen Zhu","orcid":"https://orcid.org/0009-0005-6857-7505"},"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":"Yiwen Zhu","raw_affiliation_strings":["Microsoft Gray Systems Lab, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Gray Systems Lab, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5002967874"],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":0.919,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70032174,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"1","issue":"2","first_page":"1","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","score":1.0,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9973000288009644,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/regular-expression","display_name":"Regular expression","score":0.9264621734619141},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8214396238327026},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.5008823871612549},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.461882084608078},{"id":"https://openalex.org/keywords/nondeterministic-finite-automaton","display_name":"Nondeterministic finite automaton","score":0.44636979699134827},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.43297019600868225},{"id":"https://openalex.org/keywords/pushdown-automaton","display_name":"Pushdown automaton","score":0.4134080111980438},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.4113346338272095},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.39024072885513306},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2961183190345764},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.291753351688385},{"id":"https://openalex.org/keywords/automata-theory","display_name":"Automata theory","score":0.20902404189109802},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07718667387962341}],"concepts":[{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.9264621734619141},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8214396238327026},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.5008823871612549},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.461882084608078},{"id":"https://openalex.org/C158008952","wikidata":"https://www.wikidata.org/wiki/Q617295","display_name":"Nondeterministic finite automaton","level":4,"score":0.44636979699134827},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.43297019600868225},{"id":"https://openalex.org/C77944639","wikidata":"https://www.wikidata.org/wiki/Q751443","display_name":"Pushdown automaton","level":3,"score":0.4134080111980438},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.4113346338272095},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.39024072885513306},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2961183190345764},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.291753351688385},{"id":"https://openalex.org/C116248031","wikidata":"https://www.wikidata.org/wiki/Q214526","display_name":"Automata theory","level":3,"score":0.20902404189109802},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07718667387962341},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3589297","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589297","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589297","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"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 Management of Data","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3589297","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589297","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589297","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"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 Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7538461470","display_name":"Elements: Software: Towards Efficient Embedded Data Processing","funder_award_id":"1835446","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4381326842.pdf","grobid_xml":"https://content.openalex.org/works/W4381326842.grobid-xml"},"referenced_works_count":84,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W613690151","https://openalex.org/W1541094831","https://openalex.org/W1674493795","https://openalex.org/W1834037038","https://openalex.org/W1969783316","https://openalex.org/W1969792688","https://openalex.org/W1970898202","https://openalex.org/W1971927246","https://openalex.org/W1976580206","https://openalex.org/W1985108724","https://openalex.org/W1988422900","https://openalex.org/W2003648673","https://openalex.org/W2003683276","https://openalex.org/W2006291142","https://openalex.org/W2008175851","https://openalex.org/W2022407883","https://openalex.org/W2028094098","https://openalex.org/W2028795750","https://openalex.org/W2030102079","https://openalex.org/W2038810743","https://openalex.org/W2056865152","https://openalex.org/W2067889717","https://openalex.org/W2068421750","https://openalex.org/W2070669822","https://openalex.org/W2076238443","https://openalex.org/W2083826366","https://openalex.org/W2099964107","https://openalex.org/W2108235229","https://openalex.org/W2110034858","https://openalex.org/W2110153733","https://openalex.org/W2110459974","https://openalex.org/W2113422425","https://openalex.org/W2114312434","https://openalex.org/W2115345034","https://openalex.org/W2119423764","https://openalex.org/W2124070418","https://openalex.org/W2126632912","https://openalex.org/W2134684274","https://openalex.org/W2134826720","https://openalex.org/W2135611729","https://openalex.org/W2139245703","https://openalex.org/W2139325411","https://openalex.org/W2142529424","https://openalex.org/W2147025186","https://openalex.org/W2148148676","https://openalex.org/W2148544545","https://openalex.org/W2149099978","https://openalex.org/W2153244370","https://openalex.org/W2162080541","https://openalex.org/W2162325900","https://openalex.org/W2166864323","https://openalex.org/W2168160104","https://openalex.org/W2171177618","https://openalex.org/W2236116266","https://openalex.org/W2244876453","https://openalex.org/W2393727648","https://openalex.org/W2409939811","https://openalex.org/W2480391288","https://openalex.org/W2536393303","https://openalex.org/W2604165918","https://openalex.org/W2613514830","https://openalex.org/W2792264844","https://openalex.org/W2970836712","https://openalex.org/W2974690168","https://openalex.org/W2983964464","https://openalex.org/W2998389348","https://openalex.org/W3100199031","https://openalex.org/W3108948262","https://openalex.org/W3144157896","https://openalex.org/W3159492355","https://openalex.org/W3176075086","https://openalex.org/W3179148751","https://openalex.org/W3197661828","https://openalex.org/W3200051020","https://openalex.org/W3207286602","https://openalex.org/W4206547457","https://openalex.org/W4234221848","https://openalex.org/W4242309756","https://openalex.org/W4251494677","https://openalex.org/W4256218935","https://openalex.org/W4282843300","https://openalex.org/W4294310703","https://openalex.org/W4312292115"],"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/W2396272923","https://openalex.org/W1990473086","https://openalex.org/W2481495589"],"abstract_inverted_index":{"Regular":[0,92],"expression,":[1],"or":[2],"regex,":[3],"is":[4,33,78,100,157,194,293],"widely":[5],"used":[6,107,214],"to":[7,116,187,238,245,274],"extract":[8],"critical":[9],"information":[10],"from":[11],"a":[12,67,71,94,113,133,160,171,183,283],"large":[13,83],"corpus":[14],"of":[15,21,30,73,123,163,203,257,270,286],"formatted":[16],"text":[17],"by":[18,102,272],"finding":[19],"patterns":[20],"interest.":[22],"In":[23],"tasks":[24],"like":[25],"log":[26],"processing,":[27],"the":[28,58,103,126,148,164,258,262,268,278],"speed":[29,284],"regex":[31,41,60,68,134,137,166,206,215],"matching":[32,48,97],"crucial.":[34],"Data":[35],"scientists":[36],"and":[37,138,141,197,221,224,231,243],"developers":[38],"regularly":[39],"use":[40,112],"libraries":[42],"that":[43,99,105,156],"implement":[44],"optimized":[45],"regular":[46,95],"expression":[47,96],"using":[49,170,227],"modern":[50],"automata":[51],"theory.":[52],"However,":[53],"computing":[54],"state":[55],"transitions":[56],"in":[57,108,146,153],"underlying":[59],"evaluation":[61,144],"engine":[62],"can":[63,150,198],"be":[64,151,199],"inefficient":[65],"when":[66,81],"query":[69],"contains":[70],"multitude":[72],"string":[74,139],"literals.":[75],"This":[76,86],"inefficiency":[77],"further":[79],"exasperated":[80],"analyzing":[82],"data":[84],"volumes.":[85],"paper":[87],"presents":[88],"BLARE,":[89],"Blazingly":[90],"Fast":[91],"Expression,":[93],"framework":[98,115],"inspired":[101],"mechanisms":[104],"are":[106],"database":[109],"engines,":[110],"which":[111,124,147],"declarative":[114],"explore":[117],"multiple":[118,136],"equivalent":[119],"execution":[120,191],"plans,":[121],"all":[122],"produce":[125],"correct":[127],"final":[128],"result.":[129],"Similarly,":[130],"BLARE":[131,175,193,210,235,266,281,291],"decomposes":[132],"into":[135],"components":[140,149],"then":[142],"creates":[143],"strategies":[145],"evaluated":[152,225],"an":[154,177,189],"order":[155],"not":[158,253],"strictly":[159],"left-to-right":[161],"translation":[162],"input":[165],"query.":[167],"Rather":[168],"than":[169,241,248],"cost-based":[172],"optimization":[173],"approach,":[174],"uses":[176],"adaptive":[178],"runtime":[179],"strategy":[180],"based":[181],"on":[182,201,211,255,261],"multi-armed":[184],"bandit":[185],"approach":[186],"find":[188],"efficient":[190],"plan.":[192],"also":[195],"modular":[196],"built":[200],"top":[202],"any":[204],"existing":[205],"library.":[207],"We":[208],"implemented":[209],"four":[212],"commonly":[213],"libraries,":[216],"RE2,":[217],"PCRE2,":[218],"Boost":[219,249],"Regex,":[220,223],"ICU":[222,289],"it":[226],"two":[228,264],"production":[229],"workloads":[230],"one":[232,256],"open-source":[233,279],"workload.":[234],"was":[236],"1.6\u00d7":[237],"3.7\u00d7":[239],"faster":[240,247],"RE2":[242],"3.4\u00d7":[244],"7.9\u00d7":[246],"Regex.":[250,290],"PCRE2":[251,271],"did":[252],"finish":[254],"workloads,":[259,265],"but":[260],"remaining":[263],"improved":[267],"performance":[269],"3.1\u00d7":[273],"over":[275],"100\u00d7.":[276],"For":[277],"dataset,":[280],"provided":[282],"up":[285],"61.7\u00d7":[287],"for":[288],"code":[292],"publicly":[294],"available":[295],"at":[296],"https://github.com/mush-zhang/Blare.":[297]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}
