{"id":"https://openalex.org/W4417070178","doi":"https://doi.org/10.1145/3769820","title":"Regular Expression Indexing for Log Analysis","display_name":"Regular Expression Indexing for Log Analysis","publication_year":2025,"publication_date":"2025-12-04","ids":{"openalex":"https://openalex.org/W4417070178","doi":"https://doi.org/10.1145/3769820"},"language":"en","primary_location":{"id":"doi:10.1145/3769820","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769820","pdf_url":null,"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://doi.org/10.1145/3769820","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":false,"raw_author_name":"Ling Zhang","raw_affiliation_strings":["University of Wisconsin Madison, Madison, WI, USA"],"raw_orcid":"https://orcid.org/0009-0003-2228-3945","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"],"raw_orcid":"https://orcid.org/0000-0003-2342-4060","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/A5069237428","display_name":"Jignesh M. Patel","orcid":"https://orcid.org/0000-0003-3653-2538"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jignesh M. Patel","raw_affiliation_strings":["Carneige Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0003-3653-2538","affiliations":[{"raw_affiliation_string":"Carneige Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028943049","display_name":"Karthikeyan Sankaralingam","orcid":"https://orcid.org/0000-0002-8315-2389"},"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":"Karthikeyan Sankaralingam","raw_affiliation_strings":["University of Wisconsin Madison, Madison, WI, USA"],"raw_orcid":"https://orcid.org/0000-0002-8315-2389","affiliations":[{"raw_affiliation_string":"University of Wisconsin Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38627128,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":"6","first_page":"1","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","score":0.15770000219345093,"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":0.15770000219345093,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.15719999372959137,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.13670000433921814,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/search-engine-indexing","display_name":"Search engine indexing","score":0.8543999791145325},{"id":"https://openalex.org/keywords/regular-expression","display_name":"Regular expression","score":0.7703999876976013},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4982999861240387},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.49790000915527344},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.47850000858306885},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.44760000705718994},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4296000003814697},{"id":"https://openalex.org/keywords/host","display_name":"Host (biology)","score":0.38190001249313354}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8543999791145325},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7770000100135803},{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.7703999876976013},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4982999861240387},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.49790000915527344},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.47850000858306885},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.44760000705718994},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4296000003814697},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.38190001249313354},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.374099999666214},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33629998564720154},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3199999928474426},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.31859999895095825},{"id":"https://openalex.org/C3115412","wikidata":"https://www.wikidata.org/wiki/Q1194708","display_name":"Bitmap","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.3050999939441681},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2637999951839447}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3769820","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769820","pdf_url":null,"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:10.1145/3769820","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769820","pdf_url":null,"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/G2324882205","display_name":null,"funder_award_id":"CCF-2407690","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W22160234","https://openalex.org/W1490635997","https://openalex.org/W1529203176","https://openalex.org/W1534635981","https://openalex.org/W1775135849","https://openalex.org/W1967029277","https://openalex.org/W1973130965","https://openalex.org/W1981663733","https://openalex.org/W1983496540","https://openalex.org/W1985108724","https://openalex.org/W1985291494","https://openalex.org/W1986106281","https://openalex.org/W1989215876","https://openalex.org/W1992020000","https://openalex.org/W2003648673","https://openalex.org/W2004620064","https://openalex.org/W2011820176","https://openalex.org/W2022551085","https://openalex.org/W2028094098","https://openalex.org/W2030428223","https://openalex.org/W2034128808","https://openalex.org/W2049804814","https://openalex.org/W2058658645","https://openalex.org/W2063050588","https://openalex.org/W2093416030","https://openalex.org/W2100751585","https://openalex.org/W2103933781","https://openalex.org/W2104144328","https://openalex.org/W2114312434","https://openalex.org/W2115345034","https://openalex.org/W2115417456","https://openalex.org/W2117156932","https://openalex.org/W2124070418","https://openalex.org/W2124863430","https://openalex.org/W2124886189","https://openalex.org/W2126870677","https://openalex.org/W2134387601","https://openalex.org/W2134826720","https://openalex.org/W2138312296","https://openalex.org/W2143642163","https://openalex.org/W2150993465","https://openalex.org/W2153122359","https://openalex.org/W2162325900","https://openalex.org/W2162481186","https://openalex.org/W2163652601","https://openalex.org/W2165833575","https://openalex.org/W2396336861","https://openalex.org/W2480391288","https://openalex.org/W2781079711","https://openalex.org/W2963399841","https://openalex.org/W2997780732","https://openalex.org/W2998118360","https://openalex.org/W3023462877","https://openalex.org/W3025471711","https://openalex.org/W3126986378","https://openalex.org/W3144157896","https://openalex.org/W3157818565","https://openalex.org/W3159492355","https://openalex.org/W4251494677","https://openalex.org/W4252446498","https://openalex.org/W4294310703","https://openalex.org/W4381326842","https://openalex.org/W4398234629"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,124],"paper,":[2],"we":[3,85],"present":[4],"the":[5,68,72,75,119],"design":[6],"and":[7,30,74,142],"architecture":[8],"of":[9,40,58,71,92,158,162],"REI,":[10],"a":[11,38,63,127,156],"novel":[12],"system":[13],"for":[14,18,111],"indexing":[15,28,113],"log":[16,115,136],"data":[17],"regular":[19,132,147],"expression":[20,133,148],"queries.":[21],"Our":[22],"main":[23],"contribution":[24],"is":[25,139,164],"an":[26,31,89],"n-gram-based":[27],"strategy":[29],"efficient":[32],"storage":[33],"mechanism":[34],"that":[35,50,66,87],"results":[36],"in":[37,77,102,123,155],"speedup":[39],"up":[41],"to":[42,45,108,153],"14x":[43],"compared":[44],"state-of-the-art":[46],"regex":[47,112],"processing":[48,104],"engines":[49],"do":[51],"not":[52],"use":[53],"indexing,":[54,97],"using":[55],"only":[56],"2.1%":[57],"extra":[59],"space.":[60],"We":[61],"perform":[62],"detailed":[64],"study":[65],"analyzes":[67],"space":[69],"usage":[70],"index":[73],"improvement":[76],"workload":[78],"execution":[79],"time,":[80],"uncovering":[81],"interesting":[82],"insights.":[83],"Specifically,":[84],"show":[86],"even":[88],"optimized":[90],"implementation":[91],"strategies":[93],"such":[94],"as":[95],"inverted":[96],"which":[98],"are":[99],"widely":[100],"used":[101],"text":[103],"libraries,":[105],"may":[106],"lead":[107],"suboptimal":[109],"performance":[110],"on":[114,135],"analysis":[116],"tasks.":[117],"Overall,":[118],"REI":[120,138,163],"approach":[121],"presented":[122],"paper":[125],"provides":[126],"significant":[128],"boost":[129],"when":[130],"evaluating":[131],"queries":[134],"data.":[137],"also":[140],"modular":[141],"can":[143],"work":[144],"with":[145],"existing":[146],"packages,":[149],"making":[150],"it":[151],"easy":[152],"deploy":[154],"variety":[157],"settings.":[159],"The":[160],"code":[161],"available":[165],"at":[166],"https://github.com/mush-zhang/REI-Regular-Expression-Indexing.":[167]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-12-06T00:00:00"}