{"id":19557390,"url":"https://github.com/andrefs/lingua-en-tokenizer-offsets","last_synced_at":"2025-10-09T17:08:30.223Z","repository":{"id":56839639,"uuid":"4533166","full_name":"andrefs/Lingua-EN-Tokenizer-Offsets","owner":"andrefs","description":"Finds word (token) boundaries, and returns their offsets.","archived":false,"fork":false,"pushed_at":"2012-11-17T01:44:45.000Z","size":112,"stargazers_count":1,"open_issues_count":2,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-01-08T21:41:14.296Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Perl","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/andrefs.png","metadata":{"files":{"readme":null,"changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2012-06-02T23:06:41.000Z","updated_at":"2014-09-09T02:25:07.000Z","dependencies_parsed_at":"2022-08-28T23:30:57.175Z","dependency_job_id":null,"html_url":"https://github.com/andrefs/Lingua-EN-Tokenizer-Offsets","commit_stats":null,"previous_names":[],"tags_count":5,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andrefs%2FLingua-EN-Tokenizer-Offsets","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andrefs%2FLingua-EN-Tokenizer-Offsets/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andrefs%2FLingua-EN-Tokenizer-Offsets/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andrefs%2FLingua-EN-Tokenizer-Offsets/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/andrefs","download_url":"https://codeload.github.com/andrefs/Lingua-EN-Tokenizer-Offsets/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":240814865,"owners_count":19861958,"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"}},"keywords":[],"created_at":"2024-11-11T04:42:08.054Z","updated_at":"2025-10-09T17:08:25.215Z","avatar_url":"https://github.com/andrefs.png","language":"Perl","funding_links":[],"categories":[],"sub_categories":[],"readme":null,"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fandrefs%2Flingua-en-tokenizer-offsets","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fandrefs%2Flingua-en-tokenizer-offsets","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fandrefs%2Flingua-en-tokenizer-offsets/lists"}