{"id":358301,"url":"https://github.com/JuliaText/WordTokenizers.jl/","last_synced_at":"2026-06-22T23:00:35.942Z","repository":{"id":31796851,"uuid":"128929229","full_name":"JuliaText/WordTokenizers.jl","owner":"JuliaText","description":"High performance tokenizers for natural language processing and other related tasks","archived":false,"fork":false,"pushed_at":"2021-12-30T22:37:59.000Z","size":268,"stargazers_count":100,"open_issues_count":12,"forks_count":25,"subscribers_count":8,"default_branch":"master","last_synced_at":"2026-06-04T14:02:44.750Z","etag":null,"topics":["data-mining","information-retrieval","lexer","nlp","tokenization"],"latest_commit_sha":null,"homepage":"","language":"Julia","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/JuliaText.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2018-04-10T12:29:17.000Z","updated_at":"2026-02-20T21:56:40.000Z","dependencies_parsed_at":"2022-08-04T12:45:33.605Z","dependency_job_id":null,"html_url":"https://github.com/JuliaText/WordTokenizers.jl","commit_stats":null,"previous_names":[],"tags_count":13,"template":false,"template_full_name":null,"purl":"pkg:github/JuliaText/WordTokenizers.jl","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JuliaText%2FWordTokenizers.jl","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JuliaText%2FWordTokenizers.jl/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JuliaText%2FWordTokenizers.jl/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JuliaText%2FWordTokenizers.jl/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/JuliaText","download_url":"https://codeload.github.com/JuliaText/WordTokenizers.jl/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JuliaText%2FWordTokenizers.jl/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34256188,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-12T02:00:06.859Z","response_time":109,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"owner":{"login":"JuliaText","name":"JuliaText","uuid":"6527714","kind":"organization","description":"JuliaLang Organisation for Natual Language Processing, (textual) Information Retrieval, and Computational Linguistics","email":null,"website":null,"location":null,"twitter":null,"company":null,"icon_url":"https://avatars.githubusercontent.com/u/6527714?v=4","repositories_count":12,"last_synced_at":"2024-03-26T12:24:51.444Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/JuliaText","funding_links":[],"total_stars":776,"followers":44,"following":0,"created_at":"2022-11-03T18:59:09.582Z","updated_at":"2024-03-26T12:24:51.587Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/JuliaText","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/JuliaText/repositories"},"packages":[],"commits":{"id":710403,"full_name":"JuliaText/WordTokenizers.jl","default_branch":"master","total_commits":211,"total_committers":17,"total_bot_commits":1,"total_bot_committers":1,"mean_commits":12.411764705882353,"dds":0.6635071090047393,"past_year_total_commits":0,"past_year_total_committers":0,"past_year_total_bot_commits":0,"past_year_total_bot_committers":0,"past_year_mean_commits":0.0,"past_year_dds":0.0,"last_synced_at":"2026-06-20T22:01:57.636Z","last_synced_commit":"c924822fdf7a5e1c150f667ceda5483303fb4b3c","created_at":"2023-03-09T12:31:11.493Z","updated_at":"2026-06-20T22:01:12.846Z","committers":[{"name":"Ayushk4","email":"ayushk4@gmail.com","login":"Ayushk4","count":71},{"name":"tejasvaidhyadev","email":"iamtejasvaidhya@gmail.com","login":"tejasvaidhyadev","count":36},{"name":"Lyndon White","email":"lyndon.white@research.uwa.edu.au","login":null,"count":28},{"name":"Lyndon White","email":"lyndon.white@invenialabs.co.uk","login":"oxinabox","count":25},{"name":"aquatiko","email":"rohit970819@gmail.com","login":"aquatiko","count":21},{"name":"Mike J Innes","email":"mike.j.innes@gmail.com","login":"MikeInnes","count":14},{"name":"Kristen Thyng","email":"kthyng@gmail.com","login":"kthyng","count":2},{"name":"Nick To","email":"nickto0x64@gmail.com","login":"nickto","count":2},{"name":"Waldir Pimenta","email":"waldyrious@gmail.com","login":"waldyrious","count":2},{"name":"James Schloss","email":"jrs.schloss@gmail.com","login":"leios","count":2},{"name":"Sambhaw Kumar","email":"vampiresambhaw@gmail.com","login":"SambhawDrag","count":2},{"name":"Daniel S. Katz","email":"d.katz@ieee.org","login":"danielskatz","count":1},{"name":"Julia TagBot","email":"50554310+JuliaTagBot","login":"JuliaTagBot","count":1},{"name":"KristofferC","email":"kcarlsson89@gmail.com","login":"KristofferC","count":1},{"name":"Rupal Sharma","email":"39291744+rsdel2007","login":"rsdel2007","count":1},{"name":"Sebastian Stabinger","email":"sebastian@stabinger.name","login":"Paethon","count":1},{"name":"femtocleaner[bot]","email":"femtocleaner[bot]","login":"femtocleaner[bot]","count":1}],"past_year_committers":[],"commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/JuliaText%2FWordTokenizers.jl/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2026-06-22T00:00:10.186Z","repositories_count":6266062,"commits_count":874697496,"contributors_count":35091139,"owners_count":1170207,"icon_url":"https://github.com/github.png","host_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories"}},"issues":{"table":{"full_name":"JuliaText/WordTokenizers.jl","html_url":"https://github.com/JuliaText/WordTokenizers.jl","last_synced_at":"2025-08-31T19:41:13.423Z","status":"error","issues_count":18,"pull_requests_count":47,"avg_time_to_close_issue":6259629.090909091,"avg_time_to_close_pull_request":2329573.023809524,"issues_closed_count":11,"pull_requests_closed_count":42,"pull_request_authors_count":20,"issue_authors_count":11,"avg_comments_per_issue":3.7222222222222223,"avg_comments_per_pull_request":3.8936170212765955,"merged_pull_requests_count":39,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":1,"past_year_pull_requests_count":0,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":null,"past_year_issues_closed_count":0,"past_year_pull_requests_closed_count":0,"past_year_pull_request_authors_count":0,"past_year_issue_authors_count":1,"past_year_avg_comments_per_issue":0.0,"past_year_avg_comments_per_pull_request":null,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":0,"created_at":"2023-05-10T16:04:29.445Z","updated_at":"2025-09-01T09:09:36.981Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/JuliaText%2FWordTokenizers.jl","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/JuliaText%2FWordTokenizers.jl/issues","issue_labels_count":{"table":{"help wanted":1,"good first issue":1}},"pull_request_labels_count":{"table":{}},"issue_author_associations_count":{"table":{"MEMBER":9,"NONE":7,"COLLABORATOR":2}},"pull_request_author_associations_count":{"table":{"MEMBER":26,"CONTRIBUTOR":15,"NONE":5,"COLLABORATOR":1}},"issue_authors":{"table":{"oxinabox":6,"Ayushk4":2,"MikeInnes":2,"haampie":1,"sambitdash":1,"ablaom":1,"chengchingwen":1,"TheCedarPrince":1,"AbrJA":1,"shikhargoswami":1,"tejasvaidhyadev":1}},"pull_request_authors":{"table":{"Ayushk4":18,"oxinabox":7,"aquatiko":4,"kthyng":2,"JuliaTagBot":1,"aria42":1,"danielskatz":1,"MikeInnes":1,"shikhargoswami":1,"AShedko":1,"dhruvil410":1,"Paethon":1,"rsdel2007":1,"KristofferC":1,"waldyrious":1,"nickto":1,"leios":1,"SambhawDrag":1,"tejasvaidhyadev":1,"RohitPingale":1}},"host":{"table":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2026-06-16T00:00:20.494Z","repositories_count":14812318,"issues_count":33160166,"pull_requests_count":109467532,"authors_count":11308383,"icon_url":"https://github.com/github.png","host_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories","owners_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/owners","authors_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors"}},"past_year_issue_labels_count":{"table":{}},"past_year_pull_request_labels_count":{"table":{}},"past_year_issue_author_associations_count":{"table":{}},"past_year_pull_request_author_associations_count":{"table":{}},"past_year_issue_authors":{"table":{}},"past_year_pull_request_authors":{"table":{}},"maintainers":[{"table":{"login":"Ayushk4","count":20,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/Ayushk4"}},{"table":{"login":"oxinabox","count":13,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/oxinabox"}},{"table":{"login":"MikeInnes","count":3,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/MikeInnes"}},{"table":{"login":"tejasvaidhyadev","count":2,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/tejasvaidhyadev"}}],"active_maintainers":[]}},"events":{"total":{"WatchEvent":2},"last_year":{}},"keywords":["data-mining","information-retrieval","lexer","nlp","tokenization"],"dependencies":[{"ecosystem":"julia","filepath":"REQUIRE","sha":null,"kind":"manifest","created_at":"2022-08-04T12:45:33.356Z","updated_at":"2022-08-04T12:45:33.356Z","repository_link":"https://github.com/JuliaText/WordTokenizers.jl/blob/master/REQUIRE","dependencies":[{"id":574154948,"package_name":"julia","ecosystem":"julia","requirements":"0.7","direct":true,"kind":"runtime","optional":false},{"id":574154949,"package_name":"HTML_Entities","ecosystem":"julia","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":574154950,"package_name":"StrTables","ecosystem":"julia","requirements":"*","direct":true,"kind":"runtime","optional":false}]}],"score":7.55171221535131,"created_at":"2025-04-11T10:22:23.031Z","updated_at":"2026-06-22T23:00:35.942Z","avatar_url":"https://github.com/JuliaText.png","language":"Julia","codemeta":null,"publiccode":null,"project_url":"https://summary.ecosyste.ms/api/v1/projects/358301","html_url":"https://summary.ecosyste.ms/projects/358301"}