{"id":2882,"name":"Fast, Consistent Tokenization of Natural Language Text","description":"Fast, Consistent Tokenization of Natural Language Text - Published in JOSS (2018)","url":"https://github.com/ropensci/tokenizers","last_synced_at":"2025-09-04T16:54:30.627Z","repository":{"id":48672607,"uuid":"54694109","full_name":"ropensci/tokenizers","owner":"ropensci","description":"Fast, Consistent Tokenization of Natural Language Text","archived":false,"fork":false,"pushed_at":"2024-03-27T09:33:53.000Z","size":1299,"stargazers_count":186,"open_issues_count":1,"forks_count":25,"subscribers_count":16,"default_branch":"master","last_synced_at":"2025-08-28T01:14:52.623Z","etag":null,"topics":["nlp","peer-reviewed","r","r-package","rstats","text-mining","tokenizer"],"latest_commit_sha":null,"homepage":"https://docs.ropensci.org/tokenizers","language":"R","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/ropensci.png","metadata":{"files":{"readme":"README.Rmd","changelog":"NEWS.md","contributing":null,"funding":null,"license":"LICENSE","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":"2016-03-25T04:16:33.000Z","updated_at":"2025-03-07T04:38:15.000Z","dependencies_parsed_at":"2024-06-18T22:56:12.787Z","dependency_job_id":"80a285b2-85fe-4bb8-af05-b473969fa920","html_url":"https://github.com/ropensci/tokenizers","commit_stats":{"total_commits":191,"total_committers":12,"mean_commits":"15.916666666666666","dds":"0.17801047120418845","last_synced_commit":"d92b74cdc85a14e98c90407acc17deba37f4b714"},"previous_names":[],"tags_count":8,"template":false,"template_full_name":null,"purl":"pkg:github/ropensci/tokenizers","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ropensci","download_url":"https://codeload.github.com/ropensci/tokenizers/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273514330,"owners_count":25119323,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-09-03T02:00:09.631Z","response_time":76,"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":"ropensci","name":"rOpenSci","uuid":"1200269","kind":"organization","description":"","email":"info@ropensci.org","website":"https://ropensci.org/","location":"Berkeley, CA","twitter":"rOpenSci","company":null,"icon_url":"https://avatars.githubusercontent.com/u/1200269?v=4","repositories_count":307,"last_synced_at":"2023-03-10T20:30:59.242Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/ropensci","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2022-11-02T19:23:08.224Z","updated_at":"2023-03-10T20:30:59.305Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ropensci","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ropensci/repositories"},"packages":[{"id":439646,"name":"tokenizers","ecosystem":"cran","description":"Fast, Consistent Tokenization of Natural Language Text","homepage":"https://docs.ropensci.org/tokenizers/","licenses":"MIT + file LICENSE","normalized_licenses":["MIT"],"repository_url":"https://github.com/ropensci/tokenizers","keywords_array":[],"namespace":null,"versions_count":9,"first_release_published_at":"2016-04-02T23:34:00.000Z","latest_release_published_at":"2022-12-22T00:00:00.000Z","latest_release_number":"0.3.0","last_synced_at":"2025-09-03T21:32:19.501Z","created_at":"2022-04-07T00:19:11.127Z","updated_at":"2025-09-03T21:32:19.501Z","registry_url":"https://cran.r-project.org/package=tokenizers","install_command":null,"documentation_url":"http://cran.r-project.org/web/packages/tokenizers/tokenizers.pdf","metadata":{},"repo_metadata":{"id":48672607,"uuid":"54694109","full_name":"ropensci/tokenizers","owner":"ropensci","description":"Fast, Consistent Tokenization of Natural Language Text","archived":false,"fork":false,"pushed_at":"2024-03-27T09:33:53.000Z","size":1299,"stargazers_count":184,"open_issues_count":1,"forks_count":25,"subscribers_count":17,"default_branch":"master","last_synced_at":"2024-08-06T03:04:14.533Z","etag":null,"topics":["nlp","peer-reviewed","r","r-package","rstats","text-mining","tokenizer"],"latest_commit_sha":null,"homepage":"https://docs.ropensci.org/tokenizers","language":"R","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/ropensci.png","metadata":{"files":{"readme":"README.Rmd","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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}},"created_at":"2016-03-25T04:16:33.000Z","updated_at":"2024-05-22T07:14:09.000Z","dependencies_parsed_at":"2024-06-18T22:56:12.787Z","dependency_job_id":"80a285b2-85fe-4bb8-af05-b473969fa920","html_url":"https://github.com/ropensci/tokenizers","commit_stats":{"total_commits":191,"total_committers":12,"mean_commits":"15.916666666666666","dds":"0.17801047120418845","last_synced_commit":"d92b74cdc85a14e98c90407acc17deba37f4b714"},"previous_names":[],"tags_count":8,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ropensci","download_url":"https://codeload.github.com/ropensci/tokenizers/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":219853848,"owners_count":16553504,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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_record":{"login":"ropensci","name":"rOpenSci","uuid":"1200269","kind":"organization","description":"","email":"info@ropensci.org","website":"https://ropensci.org/","location":"Berkeley, CA","twitter":"rOpenSci","company":null,"icon_url":"https://avatars.githubusercontent.com/u/1200269?v=4","repositories_count":307,"last_synced_at":"2023-03-10T20:30:59.242Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/ropensci","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2022-11-02T19:23:08.224Z","updated_at":"2023-03-10T20:30:59.305Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ropensci","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ropensci/repositories"},"tags":[{"name":"v0.3.0","sha":"d92b74cdc85a14e98c90407acc17deba37f4b714","kind":"commit","published_at":"2022-12-22T17:02:26.000Z","download_url":"https://codeload.github.com/ropensci/tokenizers/tar.gz/v0.3.0","html_url":"https://github.com/ropensci/tokenizers/releases/tag/v0.3.0","dependencies_parsed_at":null,"dependency_job_id":null,"tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/tags/v0.3.0","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/tags/v0.3.0/manifests"},{"name":"v0.2.1","sha":"964ed405c03dd63856419bec1a1c618057b1cbe6","kind":"tag","published_at":"2018-04-02T17:16:35.000Z","download_url":"https://codeload.github.com/ropensci/tokenizers/tar.gz/v0.2.1","html_url":"https://github.com/ropensci/tokenizers/releases/tag/v0.2.1","dependencies_parsed_at":null,"dependency_job_id":null,"tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/tags/v0.2.1","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/tags/v0.2.1/manifests"},{"name":"v0.2.0","sha":"4549fd9d34ed6286a778b61bca9db2b4d95c6fe4","kind":"tag","published_at":"2018-03-21T15:36:41.000Z","download_url":"https://codeload.github.com/ropensci/tokenizers/tar.gz/v0.2.0","html_url":"https://github.com/ropensci/tokenizers/releases/tag/v0.2.0","dependencies_parsed_at":null,"dependency_job_id":null,"tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/tags/v0.2.0","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/tags/v0.2.0/manifests"},{"name":"v0.1.4","sha":"896438342c60d63513fd1193c45a5581ee00a195","kind":"tag","published_at":"2016-08-29T22:05:50.000Z","download_url":"https://codeload.github.com/ropensci/tokenizers/tar.gz/v0.1.4","html_url":"https://github.com/ropensci/tokenizers/releases/tag/v0.1.4","dependencies_parsed_at":null,"dependency_job_id":null,"tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/tags/v0.1.4","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/tags/v0.1.4/manifests"},{"name":"v0.1.3","sha":"9e911e97732252f00a2715cbe34e0a900df053ef","kind":"commit","published_at":"2016-08-18T18:58:13.000Z","download_url":"https://codeload.github.com/ropensci/tokenizers/tar.gz/v0.1.3","html_url":"https://github.com/ropensci/tokenizers/releases/tag/v0.1.3","dependencies_parsed_at":null,"dependency_job_id":null,"tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/tags/v0.1.3","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/tags/v0.1.3/manifests"},{"name":"v0.1.2","sha":"d240cddbb1d91146b3a30b90f6fc25abd6919edf","kind":"tag","published_at":"2016-04-14T18:40:56.000Z","download_url":"https://codeload.github.com/ropensci/tokenizers/tar.gz/v0.1.2","html_url":"https://github.com/ropensci/tokenizers/releases/tag/v0.1.2","dependencies_parsed_at":null,"dependency_job_id":null,"tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/tags/v0.1.2","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/tags/v0.1.2/manifests"},{"name":"v0.1.1","sha":"05200e1f09a6312afa8cd442e8442415e3a2e746","kind":"tag","published_at":"2016-04-13T16:15:54.000Z","download_url":"https://codeload.github.com/ropensci/tokenizers/tar.gz/v0.1.1","html_url":"https://github.com/ropensci/tokenizers/releases/tag/v0.1.1","dependencies_parsed_at":null,"dependency_job_id":null,"tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/tags/v0.1.1","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/tags/v0.1.1/manifests"},{"name":"v0.1.0","sha":"292d1ab1f6c0ee78949d8adce9e710c36c21fbe3","kind":"tag","published_at":"2016-04-04T02:47:02.000Z","download_url":"https://codeload.github.com/ropensci/tokenizers/tar.gz/v0.1.0","html_url":"https://github.com/ropensci/tokenizers/releases/tag/v0.1.0","dependencies_parsed_at":null,"dependency_job_id":null,"tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/tags/v0.1.0","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/tags/v0.1.0/manifests"}]},"repo_metadata_updated_at":"2024-09-19T07:19:59.434Z","dependent_packages_count":20,"downloads":33219,"downloads_period":"last-month","dependent_repos_count":39,"rankings":{"downloads":2.254571276406888,"dependent_repos_count":4.154091958104029,"dependent_packages_count":3.2975323983667675,"stargazers_count":2.3388957926504528,"forks_count":2.942481803657021,"docker_downloads_count":20.255636428191018,"average":5.873868276229363},"purl":"pkg:cran/tokenizers","advisories":[],"docker_usage_url":"https://docker.ecosyste.ms/usage/cran/tokenizers","docker_dependents_count":78,"docker_downloads_count":142616,"usage_url":"https://repos.ecosyste.ms/usage/cran/tokenizers","dependent_repositories_url":"https://repos.ecosyste.ms/api/v1/usage/cran/tokenizers/dependencies","status":null,"funding_links":[],"critical":null,"issue_metadata":{"last_synced_at":"2024-01-29T09:10:32.981Z","issues_count":62,"pull_requests_count":23,"avg_time_to_close_issue":15595271.758064516,"avg_time_to_close_pull_request":1383812.4347826086,"issues_closed_count":62,"pull_requests_closed_count":23,"pull_request_authors_count":12,"issue_authors_count":28,"avg_comments_per_issue":4.5,"avg_comments_per_pull_request":1.826086956521739,"merged_pull_requests_count":23,"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":19898.0,"past_year_avg_time_to_close_pull_request":null,"past_year_issues_closed_count":1,"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":1.0,"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,"issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/issues","maintainers":[{"login":"lmullen","count":28,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/lmullen"},{"login":"Ironholds","count":6,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/Ironholds"},{"login":"jeroen","count":2,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/jeroen"},{"login":"maelle","count":2,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/maelle"},{"login":"ChrisMuir","count":1,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/ChrisMuir"},{"login":"karthik","count":1,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/karthik"}],"active_maintainers":[]},"versions_url":"https://packages.ecosyste.ms/api/v1/registries/cran.r-project.org/packages/tokenizers/versions","version_numbers_url":"https://packages.ecosyste.ms/api/v1/registries/cran.r-project.org/packages/tokenizers/version_numbers","dependent_packages_url":"https://packages.ecosyste.ms/api/v1/registries/cran.r-project.org/packages/tokenizers/dependent_packages","related_packages_url":"https://packages.ecosyste.ms/api/v1/registries/cran.r-project.org/packages/tokenizers/related_packages","maintainers":[{"uuid":"lincoln@lincolnmullen.com","login":null,"name":"Lincoln Mullen","email":"lincoln@lincolnmullen.com","url":null,"packages_count":5,"html_url":null,"role":null,"created_at":"2022-11-14T17:25:00.694Z","updated_at":"2022-11-14T17:25:00.694Z","packages_url":"https://packages.ecosyste.ms/api/v1/registries/cran.r-project.org/maintainers/lincoln@lincolnmullen.com/packages"}],"registry":{"name":"cran.r-project.org","url":"https://cran.r-project.org","ecosystem":"cran","default":true,"packages_count":26169,"maintainers_count":14292,"namespaces_count":0,"keywords_count":8317,"github":"r-project-org","metadata":{"funded_packages_count":539},"icon_url":"https://github.com/r-project-org.png","created_at":"2022-04-06T16:32:25.637Z","updated_at":"2025-09-04T07:00:40.033Z","packages_url":"https://packages.ecosyste.ms/api/v1/registries/cran.r-project.org/packages","maintainers_url":"https://packages.ecosyste.ms/api/v1/registries/cran.r-project.org/maintainers","namespaces_url":"https://packages.ecosyste.ms/api/v1/registries/cran.r-project.org/namespaces"}},{"id":11743185,"name":"github.com/ropensci/tokenizers","ecosystem":"go","description":null,"homepage":null,"licenses":"other","normalized_licenses":["GPL-1.0+"],"repository_url":"https://github.com/ropensci/tokenizers","keywords_array":[],"namespace":null,"versions_count":8,"first_release_published_at":"2016-04-02T01:15:40.000Z","latest_release_published_at":"2022-12-22T17:02:26.000Z","latest_release_number":"v0.3.0","last_synced_at":"2025-09-03T21:32:41.182Z","created_at":"2025-06-07T10:00:32.946Z","updated_at":"2025-09-03T21:32:41.183Z","registry_url":"https://pkg.go.dev/github.com/ropensci/tokenizers","install_command":"go get github.com/ropensci/tokenizers","documentation_url":"https://pkg.go.dev/github.com/ropensci/tokenizers#section-documentation","metadata":{},"repo_metadata":{"id":48672607,"uuid":"54694109","full_name":"ropensci/tokenizers","owner":"ropensci","description":"Fast, Consistent Tokenization of Natural Language Text","archived":false,"fork":false,"pushed_at":"2024-03-27T09:33:53.000Z","size":1299,"stargazers_count":186,"open_issues_count":1,"forks_count":25,"subscribers_count":16,"default_branch":"master","last_synced_at":"2025-06-05T04:44:57.758Z","etag":null,"topics":["nlp","peer-reviewed","r","r-package","rstats","text-mining","tokenizer"],"latest_commit_sha":null,"homepage":"https://docs.ropensci.org/tokenizers","language":"R","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/ropensci.png","metadata":{"files":{"readme":"README.Rmd","changelog":"NEWS.md","contributing":null,"funding":null,"license":"LICENSE","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":"2016-03-25T04:16:33.000Z","updated_at":"2025-03-07T04:38:15.000Z","dependencies_parsed_at":"2024-06-18T22:56:12.787Z","dependency_job_id":"80a285b2-85fe-4bb8-af05-b473969fa920","html_url":"https://github.com/ropensci/tokenizers","commit_stats":{"total_commits":191,"total_committers":12,"mean_commits":"15.916666666666666","dds":"0.17801047120418845","last_synced_commit":"d92b74cdc85a14e98c90407acc17deba37f4b714"},"previous_names":[],"tags_count":8,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ropensci","download_url":"https://codeload.github.com/ropensci/tokenizers/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":258642426,"owners_count":22734668,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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"}},"repo_metadata_updated_at":"2025-06-07T23:36:03.638Z","dependent_packages_count":0,"downloads":null,"downloads_period":null,"dependent_repos_count":0,"rankings":{"downloads":null,"dependent_repos_count":5.750499235214139,"dependent_packages_count":5.388553704962611,"stargazers_count":null,"forks_count":null,"docker_downloads_count":null,"average":5.569526470088375},"purl":"pkg:golang/github.com/ropensci/tokenizers","advisories":[],"docker_usage_url":"https://docker.ecosyste.ms/usage/go/github.com/ropensci/tokenizers","docker_dependents_count":null,"docker_downloads_count":null,"usage_url":"https://repos.ecosyste.ms/usage/go/github.com/ropensci/tokenizers","dependent_repositories_url":"https://repos.ecosyste.ms/api/v1/usage/go/github.com/ropensci/tokenizers/dependencies","status":null,"funding_links":[],"critical":null,"issue_metadata":{"last_synced_at":"2025-06-05T02:20:26.362Z","issues_count":64,"pull_requests_count":23,"avg_time_to_close_issue":15423148.333333334,"avg_time_to_close_pull_request":1383812.4347826086,"issues_closed_count":63,"pull_requests_closed_count":23,"pull_request_authors_count":12,"issue_authors_count":29,"avg_comments_per_issue":4.40625,"avg_comments_per_pull_request":1.826086956521739,"merged_pull_requests_count":23,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":0,"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":0,"past_year_avg_comments_per_issue":null,"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,"issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/issues","maintainers":[{"login":"lmullen","count":28,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/lmullen"},{"login":"Ironholds","count":6,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/Ironholds"},{"login":"maelle","count":3,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/maelle"},{"login":"jeroen","count":2,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/jeroen"},{"login":"ChrisMuir","count":1,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/ChrisMuir"},{"login":"karthik","count":1,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/karthik"}],"active_maintainers":[]},"versions_url":"https://packages.ecosyste.ms/api/v1/registries/proxy.golang.org/packages/github.com%2Fropensci%2Ftokenizers/versions","version_numbers_url":"https://packages.ecosyste.ms/api/v1/registries/proxy.golang.org/packages/github.com%2Fropensci%2Ftokenizers/version_numbers","dependent_packages_url":"https://packages.ecosyste.ms/api/v1/registries/proxy.golang.org/packages/github.com%2Fropensci%2Ftokenizers/dependent_packages","related_packages_url":"https://packages.ecosyste.ms/api/v1/registries/proxy.golang.org/packages/github.com%2Fropensci%2Ftokenizers/related_packages","maintainers":[],"registry":{"name":"proxy.golang.org","url":"https://proxy.golang.org","ecosystem":"go","default":true,"packages_count":1951493,"maintainers_count":0,"namespaces_count":741113,"keywords_count":109139,"github":"golang","metadata":{"funded_packages_count":48962},"icon_url":"https://github.com/golang.png","created_at":"2022-04-04T15:19:22.939Z","updated_at":"2025-09-04T05:53:31.480Z","packages_url":"https://packages.ecosyste.ms/api/v1/registries/proxy.golang.org/packages","maintainers_url":"https://packages.ecosyste.ms/api/v1/registries/proxy.golang.org/maintainers","namespaces_url":"https://packages.ecosyste.ms/api/v1/registries/proxy.golang.org/namespaces"}}],"commits":{"id":1330651,"full_name":"ropensci/tokenizers","default_branch":"master","committers":[{"name":"Lincoln Mullen","email":"lincoln@lincolnmullen.com","login":"lmullen","count":157},{"name":"Oliver Keyes","email":"ironholds@gmail.com","login":null,"count":13},{"name":"Dmitriy Selivanov","email":"selivanov.dmitriy@gmail.com","login":"dselivanov","count":6},{"name":"jrnold","email":"jeffrey.arnold@gmail.com","login":"jrnold","count":4},{"name":"Kenneth Benoit","email":"kbenoit@lse.ac.uk","login":"kbenoit","count":4},{"name":"tcharlon","email":"charlon@protonmail.com","login":"ThomasChln","count":1},{"name":"Maëlle Salmon","email":"maelle.salmon@yahoo.se","login":"maelle","count":1},{"name":"Karthik Ram","email":"karthik.ram@gmail.com","login":"karthik","count":1},{"name":"Julia Silge","email":"julia.silge@gmail.com","login":"juliasilge","count":1},{"name":"Jeroen Ooms","email":"jeroenooms@gmail.com","login":"jeroen","count":1},{"name":"Hideaki Hayashi","email":"hihayash@gmail.com","login":"hideaki","count":1},{"name":"Emil Hvitfeldt","email":"emilhhvitfeldt@gmail.com","login":"EmilHvitfeldt","count":1},{"name":"ChrisMuir","email":"chrismuirRVA@gmail.com","login":"ChrisMuir","count":1}],"total_commits":192,"total_committers":13,"total_bot_commits":0,"total_bot_committers":0,"mean_commits":14.76923076923077,"dds":0.18229166666666663,"past_year_committers":[],"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":"2025-08-07T07:20:56.503Z","last_synced_commit":"b80863d088d4b39695b602ca11e061ac34770ec7","created_at":"2023-09-11T16:54:43.768Z","updated_at":"2025-08-07T07:20:56.663Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-08-14T00:00:13.429Z","repositories_count":5478170,"commits_count":853210674,"contributors_count":31091312,"owners_count":906502,"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_stats":{"full_name":"ropensci/tokenizers","html_url":"https://github.com/ropensci/tokenizers","last_synced_at":"2025-08-31T20:05:56.698Z","status":"error","issues_count":64,"pull_requests_count":23,"avg_time_to_close_issue":15423148.333333334,"avg_time_to_close_pull_request":1383812.4347826086,"issues_closed_count":63,"pull_requests_closed_count":23,"pull_request_authors_count":12,"issue_authors_count":29,"avg_comments_per_issue":4.40625,"avg_comments_per_pull_request":1.826086956521739,"merged_pull_requests_count":23,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":0,"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":0,"past_year_avg_comments_per_issue":null,"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":"2023-09-11T16:55:14.156Z","updated_at":"2025-09-01T07:32:19.679Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/ropensci%2Ftokenizers/issues","issue_labels_count":{"bug":1,"help wanted":1},"pull_request_labels_count":{},"issue_author_associations_count":{"MEMBER":29,"NONE":25,"CONTRIBUTOR":10},"pull_request_author_associations_count":{"MEMBER":12,"CONTRIBUTOR":11},"issue_authors":{"lmullen":24,"dselivanov":5,"juliasilge":2,"fschaffner":2,"hope-data-science":2,"EmilHvitfeldt":2,"alanault":2,"randomgambit":2,"maelle":2,"Ironholds":2,"rlumor":1,"jeroen":1,"fahadshery":1,"statspro1":1,"harshakap":1,"everdark":1,"sanjesk1":1,"MichaelChirico":1,"soodoku":1,"kevinbsc":1,"ablaette":1,"ekstroem":1,"kbenoit":1,"rajkorde":1,"syumet":1,"rsjohnso":1,"patperry":1,"koheiw":1,"Legallois":1},"pull_request_authors":{"Ironholds":4,"lmullen":4,"kbenoit":4,"dselivanov":3,"maelle":1,"jrnold":1,"hideaki":1,"jeroen":1,"EmilHvitfeldt":1,"karthik":1,"juliasilge":1,"ChrisMuir":1},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-01T00:00:07.725Z","repositories_count":9927554,"issues_count":29319774,"pull_requests_count":84416271,"authors_count":9124532,"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":{},"past_year_pull_request_labels_count":{},"past_year_issue_author_associations_count":{},"past_year_pull_request_author_associations_count":{},"past_year_issue_authors":{},"past_year_pull_request_authors":{},"maintainers":[{"login":"lmullen","count":28,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/lmullen"},{"login":"Ironholds","count":6,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/Ironholds"},{"login":"maelle","count":3,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/maelle"},{"login":"jeroen","count":2,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/jeroen"},{"login":"ChrisMuir","count":1,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/ChrisMuir"},{"login":"karthik","count":1,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/karthik"}],"active_maintainers":[]},"events":{"total":{"WatchEvent":3},"last_year":{"WatchEvent":3}},"keywords":["nlp","peer-reviewed","r","r-package","rstats","text-mining","tokenizer"],"dependencies":[{"ecosystem":"cran","filepath":"DESCRIPTION","sha":null,"kind":"manifest","created_at":"2022-08-27T08:21:44.272Z","updated_at":"2022-08-27T08:21:44.272Z","repository_link":"https://github.com/ropensci/tokenizers/blob/master/DESCRIPTION","dependencies":[{"id":2904203928,"package_name":"R","ecosystem":"cran","requirements":"\u003e= 3.1.3","direct":true,"kind":"depends","optional":false},{"id":2904203929,"package_name":"stringi","ecosystem":"cran","requirements":"\u003e= 1.0.1","direct":true,"kind":"imports","optional":false},{"id":2904203930,"package_name":"Rcpp","ecosystem":"cran","requirements":"\u003e= 0.12.3","direct":true,"kind":"imports","optional":false},{"id":2904203931,"package_name":"SnowballC","ecosystem":"cran","requirements":"\u003e= 0.5.1","direct":true,"kind":"imports","optional":false},{"id":2904203932,"package_name":"covr","ecosystem":"cran","requirements":"*","direct":true,"kind":"suggests","optional":false},{"id":2904203933,"package_name":"knitr","ecosystem":"cran","requirements":"*","direct":true,"kind":"suggests","optional":false},{"id":2904203934,"package_name":"rmarkdown","ecosystem":"cran","requirements":"*","direct":true,"kind":"suggests","optional":false},{"id":2904203935,"package_name":"stopwords","ecosystem":"cran","requirements":"\u003e= 0.9.0","direct":true,"kind":"suggests","optional":false},{"id":2904203936,"package_name":"testthat","ecosystem":"cran","requirements":"*","direct":true,"kind":"suggests","optional":false}]},{"ecosystem":"docker","filepath":"Dockerfile","sha":null,"kind":"manifest","created_at":"2024-06-18T22:56:11.822Z","updated_at":"2024-06-18T22:56:11.822Z","repository_link":"https://github.com/ropensci/tokenizers/blob/master/Dockerfile","dependencies":[{"id":18683962907,"package_name":"rocker/shiny-verse","ecosystem":"docker","requirements":"4.3.2","direct":true,"kind":"build","optional":false}]},{"ecosystem":"docker","filepath":"docker-compose.yml","sha":null,"kind":"manifest","created_at":"2024-06-18T22:56:12.640Z","updated_at":"2024-06-18T22:56:12.640Z","repository_link":"https://github.com/ropensci/tokenizers/blob/master/docker-compose.yml","dependencies":[]}],"score":19.874143827477123,"created_at":"2025-09-04T09:18:07.389Z","updated_at":"2025-10-07T08:04:42.772Z","avatar_url":"https://github.com/ropensci.png","language":"R","category":"Scientific Software","sub_category":"Peer-reviewed","monthly_downloads":33219,"funding_links":[],"readme_doi_urls":["https://doi.org/10.21105/joss.00655"],"works":{},"citation_counts":{},"total_citations":0,"keywords_from_contributors":["tidyverse","tidy-data","digital-history","history","spatial-data","osm-data","overpass-api","pm25","rti-micropem","data60uk"],"project_url":"https://science.ecosyste.ms/api/v1/projects/2882","html_url":"https://science.ecosyste.ms/projects/2882"}