{"id":16572691,"url":"https://github.com/lemire/htmlscanning","last_synced_at":"2025-10-08T11:05:07.993Z","repository":{"id":250620760,"uuid":"834939218","full_name":"lemire/htmlscanning","owner":"lemire","description":null,"archived":false,"fork":false,"pushed_at":"2025-05-05T20:33:11.000Z","size":129,"stargazers_count":5,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-09-30T13:40:10.299Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/lemire.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":"2024-07-28T19:01:47.000Z","updated_at":"2025-07-23T14:41:10.000Z","dependencies_parsed_at":"2024-07-28T23:08:38.522Z","dependency_job_id":null,"html_url":"https://github.com/lemire/htmlscanning","commit_stats":null,"previous_names":["lemire/htmlscanning"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/lemire/htmlscanning","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lemire%2Fhtmlscanning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lemire%2Fhtmlscanning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lemire%2Fhtmlscanning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lemire%2Fhtmlscanning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lemire","download_url":"https://codeload.github.com/lemire/htmlscanning/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lemire%2Fhtmlscanning/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278931654,"owners_count":26070789,"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":"2025-10-08T02:00:06.501Z","response_time":56,"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"}},"keywords":[],"created_at":"2024-10-11T21:28:18.712Z","updated_at":"2025-10-08T11:05:07.988Z","avatar_url":"https://github.com/lemire.png","language":"HTML","funding_links":[],"categories":[],"sub_categories":[],"readme":"# HTML Scanning benchmark\n\nWe assume a standard Linux/macOS system with development tools.\n\nWe expect a 64-bit ARM system.\n\n## CMake usage\n\nUsage:\n```\ncmake -B build\ncmake --build build\nctest --test-dir build\n./build/benchmark data/bbc.html\n```\n\n## Old-school usage\n\nUsage:\n\n```\nmake\n./unit\n./benchmark data/bbc.html\n```\n\n## Paper\n\n- Daniel Lemire, [Scanning HTML at Tens of Gigabytes Per Second on ARM Processors](https://doi.org/10.1002/spe.3420), Software: Practice and Experience (to appear)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flemire%2Fhtmlscanning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flemire%2Fhtmlscanning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flemire%2Fhtmlscanning/lists"}