{"id":23169127,"url":"https://github.com/proprietary/msoffice-document-tokenizer","last_synced_at":"2025-04-04T22:45:38.842Z","repository":{"id":129078599,"uuid":"228307197","full_name":"proprietary/msoffice-document-tokenizer","owner":"proprietary","description":"Create wordlist dictionary from words/tokens in DOCX and PPTX Microsoft Office OpenXML documents","archived":false,"fork":false,"pushed_at":"2019-12-16T05:09:26.000Z","size":1,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-02-10T07:24:52.142Z","etag":null,"topics":["microsoft-office","nlp","nlp-parsing","python","tokenizer"],"latest_commit_sha":null,"homepage":null,"language":"Python","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/proprietary.png","metadata":{},"created_at":"2019-12-16T05:09:03.000Z","updated_at":"2019-12-16T05:09:54.000Z","dependencies_parsed_at":"2023-05-05T09:34:17.047Z","dependency_job_id":null,"html_url":"https://github.com/proprietary/msoffice-document-tokenizer","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/proprietary%2Fmsoffice-document-tokenizer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/proprietary%2Fmsoffice-document-tokenizer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/proprietary%2Fmsoffice-document-tokenizer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/proprietary%2Fmsoffice-document-tokenizer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/proprietary","download_url":"https://codeload.github.com/proprietary/msoffice-document-tokenizer/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247261580,"owners_count":20910107,"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":["microsoft-office","nlp","nlp-parsing","python","tokenizer"],"created_at":"2024-12-18T03:15:33.205Z","updated_at":"2025-04-04T22:45:38.837Z","avatar_url":"https://github.com/proprietary.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":null,"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fproprietary%2Fmsoffice-document-tokenizer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fproprietary%2Fmsoffice-document-tokenizer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fproprietary%2Fmsoffice-document-tokenizer/lists"}