{"id":189251,"name":null,"description":"Index Common Crawl archives in tabular format","url":"https://github.com/commoncrawl/cc-index-table","last_synced_at":"2025-09-10T03:38:49.709Z","repository":{"id":31348292,"uuid":"110119350","full_name":"commoncrawl/cc-index-table","owner":"commoncrawl","description":"Index Common Crawl archives in tabular format","archived":false,"fork":false,"pushed_at":"2025-07-28T17:52:42.000Z","size":211,"stargazers_count":123,"open_issues_count":6,"forks_count":12,"subscribers_count":15,"default_branch":"main","last_synced_at":"2025-07-28T19:33:00.291Z","etag":null,"topics":["apache-parquet","aws-athena","columnar-storage","commoncrawl","spark","sql"],"latest_commit_sha":null,"homepage":null,"language":"Java","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/commoncrawl.png","metadata":{"files":{"readme":"README.md","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,"zenodo":null}},"created_at":"2017-11-09T13:33:36.000Z","updated_at":"2025-07-28T17:52:46.000Z","dependencies_parsed_at":"2025-03-10T19:30:16.977Z","dependency_job_id":"9274494c-31a6-4fd0-aac8-d1e0a3d66be2","html_url":"https://github.com/commoncrawl/cc-index-table","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/commoncrawl/cc-index-table","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-index-table","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-index-table/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-index-table/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-index-table/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/commoncrawl","download_url":"https://codeload.github.com/commoncrawl/cc-index-table/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-index-table/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274407397,"owners_count":25279277,"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":"2025-09-10T02:00:12.551Z","response_time":83,"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":"commoncrawl","name":"Common Crawl Foundation","uuid":"1194841","kind":"organization","description":"Common Crawl provides an archive of webpages going back to 2007.","email":"info@commoncrawl.org","website":"https://commoncrawl.org","location":null,"twitter":"commoncrawl","company":null,"icon_url":"https://avatars.githubusercontent.com/u/1194841?v=4","repositories_count":50,"last_synced_at":"2024-05-07T18:12:30.238Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/commoncrawl","funding_links":[],"total_stars":2106,"followers":290,"following":0,"created_at":"2022-11-03T05:10:17.348Z","updated_at":"2024-05-07T18:12:39.767Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/commoncrawl","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/commoncrawl/repositories"},"packages":[],"commits":{"id":10323888,"full_name":"commoncrawl/cc-index-table","default_branch":"main","committers":[{"name":"Sebastian Nagel","email":"sebastian@commoncrawl.org","login":"sebastian-nagel","count":97},{"name":"Jason Grey","email":"jason@jason-grey.com","login":"jt55401","count":5},{"name":"Greg Lindahl","email":"greg@commomncrawl.org","login":null,"count":3},{"name":"dependabot[bot]","email":"49699333+dependabot[bot]","login":"dependabot[bot]","count":1}],"total_commits":106,"total_committers":4,"total_bot_commits":1,"total_bot_committers":1,"mean_commits":26.5,"dds":0.08490566037735847,"past_year_committers":[{"name":"Sebastian Nagel","email":"sebastian@commoncrawl.org","login":"sebastian-nagel","count":15},{"name":"Jason Grey","email":"jason@jason-grey.com","login":"jt55401","count":5}],"past_year_total_commits":20,"past_year_total_committers":2,"past_year_total_bot_commits":0,"past_year_total_bot_committers":0,"past_year_mean_commits":10.0,"past_year_dds":0.25,"last_synced_at":"2025-06-12T20:03:04.556Z","last_synced_commit":"d5d71455955e1c3af5cd5bd870df9f22f35ba7f1","created_at":"2025-06-12T08:40:58.129Z","updated_at":"2025-06-12T20:03:29.515Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-index-table/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-10T00:25:43.995Z","repositories_count":5545114,"commits_count":878229909,"contributors_count":32458717,"owners_count":919815,"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":"commoncrawl/cc-index-table","html_url":"https://github.com/commoncrawl/cc-index-table","last_synced_at":"2025-07-16T13:14:40.053Z","status":null,"issues_count":24,"pull_requests_count":14,"avg_time_to_close_issue":11461908.823529411,"avg_time_to_close_pull_request":11684836.5,"issues_closed_count":17,"pull_requests_closed_count":14,"pull_request_authors_count":4,"issue_authors_count":12,"avg_comments_per_issue":2.0416666666666665,"avg_comments_per_pull_request":0.8571428571428571,"merged_pull_requests_count":10,"bot_issues_count":0,"bot_pull_requests_count":3,"past_year_issues_count":2,"past_year_pull_requests_count":4,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":1144645.5,"past_year_issues_closed_count":0,"past_year_pull_requests_closed_count":4,"past_year_pull_request_authors_count":1,"past_year_issue_authors_count":2,"past_year_avg_comments_per_issue":0.0,"past_year_avg_comments_per_pull_request":0.0,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":4,"created_at":"2025-06-12T08:41:04.330Z","updated_at":"2025-09-02T15:24:05.330Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-index-table","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-index-table/issues","issue_labels_count":{"question":3,"bug":1},"pull_request_labels_count":{"dependencies":4},"issue_author_associations_count":{"NONE":13,"CONTRIBUTOR":11},"pull_request_author_associations_count":{"CONTRIBUTOR":18,"NONE":2},"issue_authors":{"sebastian-nagel":11,"brad-safetonet":2,"aliebrahiiimi":2,"AmrSheta22":1,"safer-bot":1,"e06084":1,"cirosantilli":1,"imfht":1,"bbrancar":1,"vansenic":1,"vphill":1,"lukaskawerau":1},"pull_request_authors":{"sebastian-nagel":13,"dependabot[bot]":4,"jt55401":2,"athulj":1},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-03T00:00:08.273Z","repositories_count":10046913,"issues_count":30708618,"pull_requests_count":91842089,"authors_count":10502051,"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":{"NONE":2},"past_year_pull_request_author_associations_count":{"CONTRIBUTOR":8},"past_year_issue_authors":{"e06084":1,"safer-bot":1},"past_year_pull_request_authors":{"sebastian-nagel":8},"maintainers":[],"active_maintainers":[]},"events":{"total":{"IssuesEvent":2,"WatchEvent":17,"DeleteEvent":3,"IssueCommentEvent":7,"PushEvent":10,"PullRequestReviewEvent":1,"PullRequestEvent":8,"ForkEvent":4,"CreateEvent":4},"last_year":{"IssuesEvent":2,"WatchEvent":17,"DeleteEvent":3,"IssueCommentEvent":7,"PushEvent":10,"PullRequestReviewEvent":1,"PullRequestEvent":8,"ForkEvent":4,"CreateEvent":4}},"keywords":["apache-parquet","aws-athena","columnar-storage","commoncrawl","spark","sql"],"dependencies":[{"ecosystem":"maven","filepath":"pom.xml","sha":null,"kind":"manifest","created_at":"2022-09-01T17:03:38.323Z","updated_at":"2022-09-01T17:03:38.323Z","repository_link":"https://github.com/commoncrawl/cc-index-table/blob/main/pom.xml","dependencies":[{"id":3529040503,"package_name":"org.apache.spark:spark-core_2.12","ecosystem":"maven","requirements":"3.2.1","direct":true,"kind":"provided","optional":false},{"id":3529040504,"package_name":"org.apache.spark:spark-sql_2.12","ecosystem":"maven","requirements":"3.2.1","direct":true,"kind":"provided","optional":false},{"id":3529040505,"package_name":"org.slf4j:slf4j-api","ecosystem":"maven","requirements":"1.7.36","direct":true,"kind":"runtime","optional":false},{"id":3529040506,"package_name":"com.google.code.gson:gson","ecosystem":"maven","requirements":"2.8.9","direct":true,"kind":"runtime","optional":false},{"id":3529040507,"package_name":"com.github.crawler-commons:crawler-commons","ecosystem":"maven","requirements":"1.2","direct":true,"kind":"runtime","optional":false},{"id":3529040508,"package_name":"commons-cli:commons-cli","ecosystem":"maven","requirements":"1.2","direct":true,"kind":"runtime","optional":false},{"id":3529040509,"package_name":"software.amazon.awssdk:s3","ecosystem":"maven","requirements":null,"direct":true,"kind":"runtime","optional":false},{"id":3529040510,"package_name":"org.junit.jupiter:junit-jupiter-engine","ecosystem":"maven","requirements":"5.8.2","direct":true,"kind":"test","optional":false},{"id":3529040511,"package_name":"software.amazon.awssdk:bom","ecosystem":"maven","requirements":"2.17.177","direct":true,"kind":"import","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/build.yml","sha":null,"kind":"manifest","created_at":"2024-10-22T17:25:51.501Z","updated_at":"2024-10-22T17:25:51.501Z","repository_link":"https://github.com/commoncrawl/cc-index-table/blob/main/.github/workflows/build.yml","dependencies":[{"id":20350675695,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v4","direct":true,"kind":"composite","optional":false},{"id":20350675696,"package_name":"actions/setup-java","ecosystem":"actions","requirements":"v4","direct":true,"kind":"composite","optional":false}]}],"score":6.246106765481563,"created_at":"2025-09-09T02:58:07.635Z","updated_at":"2025-10-07T08:42:12.308Z","avatar_url":"https://github.com/commoncrawl.png","language":"Java","category":null,"sub_category":null,"monthly_downloads":0,"funding_links":[],"readme_doi_urls":[],"works":{},"citation_counts":{},"total_citations":0,"keywords_from_contributors":["archive","projection","interactive","generic","sequences","profiles","embedded","genomics","observability","autograding"],"project_url":"https://science.ecosyste.ms/api/v1/projects/189251","html_url":"https://science.ecosyste.ms/projects/189251"}