{"id":18664727,"url":"https://github.com/zlib-ng/corpora","last_synced_at":"2026-02-02T20:34:24.426Z","repository":{"id":144815723,"uuid":"279631981","full_name":"zlib-ng/corpora","owner":"zlib-ng","description":"Common corpora used for lossless compression testing and benchmarking.","archived":false,"fork":false,"pushed_at":"2025-03-18T21:00:40.000Z","size":98633,"stargazers_count":4,"open_issues_count":0,"forks_count":3,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-05-18T05:14:53.034Z","etag":null,"topics":["compression","corpora","testing"],"latest_commit_sha":null,"homepage":"","language":"HTML","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/zlib-ng.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,"zenodo":null}},"created_at":"2020-07-14T16:03:45.000Z","updated_at":"2025-03-18T20:59:55.000Z","dependencies_parsed_at":null,"dependency_job_id":"cff0679d-623e-4a01-b819-14ef86010941","html_url":"https://github.com/zlib-ng/corpora","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/zlib-ng/corpora","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zlib-ng%2Fcorpora","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zlib-ng%2Fcorpora/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zlib-ng%2Fcorpora/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zlib-ng%2Fcorpora/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zlib-ng","download_url":"https://codeload.github.com/zlib-ng/corpora/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zlib-ng%2Fcorpora/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":264086134,"owners_count":23555291,"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":["compression","corpora","testing"],"created_at":"2024-11-07T08:24:44.676Z","updated_at":"2026-02-02T20:34:24.400Z","avatar_url":"https://github.com/zlib-ng.png","language":"HTML","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Corpora\n\nThis repository contains common corpora used for lossless compression testing and benchmarking.\n\n### Sources\n\nDetailed descriptions of the files found in each of the corpus can be found below.\n\n|Corpus|URL|Notes|\n|:-|:-|:-|\n|Canterbury|https://corpus.canterbury.ac.nz/|Includes artificial, calgary, canterbury, large, and miscellaneous corpus.|\n|Silesia|http://sun.aei.polsl.pl/~sdeor/index.php?page=silesia||\n|Snappy|https://github.com/google/snappy|Test data with some duplicates removed that were present in other corpus.|\n|Neuro|https://github.com/neurolabusc/zlib-bench|NIfTI format brain images.|\n\n### License\n\nAll files are the works of their respective authors. Please see the sources above for any licensing information.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzlib-ng%2Fcorpora","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzlib-ng%2Fcorpora","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzlib-ng%2Fcorpora/lists"}