{"id":15345830,"url":"https://github.com/chucheng92/hadoopdedup","last_synced_at":"2025-04-15T02:37:13.403Z","repository":{"id":95899229,"uuid":"67604480","full_name":"chucheng92/HadoopDedup","owner":"chucheng92","description":":watermelon:基于Hadoop和HBase的大规模海量数据去重","archived":false,"fork":false,"pushed_at":"2018-04-08T10:15:11.000Z","size":12572,"stargazers_count":29,"open_issues_count":0,"forks_count":16,"subscribers_count":9,"default_branch":"master","last_synced_at":"2025-03-28T15:11:35.424Z","etag":null,"topics":["big-data","cdc","dedup","fsp","mapreduce"],"latest_commit_sha":null,"homepage":"http://rann.cc","language":"Java","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/chucheng92.png","metadata":{"files":{"readme":"README.md","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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2016-09-07T12:27:39.000Z","updated_at":"2024-09-01T14:37:20.000Z","dependencies_parsed_at":null,"dependency_job_id":"47b2bfa2-0e16-4fb6-8108-d7f87c207ae5","html_url":"https://github.com/chucheng92/HadoopDedup","commit_stats":{"total_commits":133,"total_committers":2,"mean_commits":66.5,"dds":0.1428571428571429,"last_synced_commit":"ebfd5078ea148256db868a03ec43e183c0e629ea"},"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chucheng92%2FHadoopDedup","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chucheng92%2FHadoopDedup/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chucheng92%2FHadoopDedup/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chucheng92%2FHadoopDedup/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/chucheng92","download_url":"https://codeload.github.com/chucheng92/HadoopDedup/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248995104,"owners_count":21195497,"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":["big-data","cdc","dedup","fsp","mapreduce"],"created_at":"2024-10-01T11:16:08.924Z","updated_at":"2025-04-15T02:37:13.386Z","avatar_url":"https://github.com/chucheng92.png","language":"Java","funding_links":[],"categories":[],"sub_categories":[],"readme":"## 基于Hadoop和HBase的大规模海量数据去重\n\n## 目录\n\ndata - 数据集\n\ndocs - 文档\n\nsrc - MapReduce\n\n## 环境\n\nHadoop版本1.1.2\n\nHBase 0.94.8","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchucheng92%2Fhadoopdedup","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fchucheng92%2Fhadoopdedup","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchucheng92%2Fhadoopdedup/lists"}