{"id":4128,"name":"datatrove_custom","description":null,"url":"https://github.com/swalbak/datatrove_custom","last_synced_at":"2025-09-04T17:15:52.271Z","repository":{"id":300594242,"uuid":"1006578731","full_name":"Swalbak/datatrove_custom","owner":"Swalbak","description":null,"archived":false,"fork":false,"pushed_at":"2025-06-22T15:25:45.000Z","size":33854,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-06-22T16:31:35.344Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","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/Swalbak.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-06-22T15:20:49.000Z","updated_at":"2025-06-22T15:26:26.000Z","dependencies_parsed_at":"2025-06-22T16:42:23.762Z","dependency_job_id":null,"html_url":"https://github.com/Swalbak/datatrove_custom","commit_stats":null,"previous_names":["swalbak/datatrove_custom"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Swalbak/datatrove_custom","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Swalbak%2Fdatatrove_custom","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Swalbak%2Fdatatrove_custom/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Swalbak%2Fdatatrove_custom/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Swalbak%2Fdatatrove_custom/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Swalbak","download_url":"https://codeload.github.com/Swalbak/datatrove_custom/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Swalbak%2Fdatatrove_custom/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273641941,"owners_count":25142264,"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":"2025-09-04T02:00:08.968Z","response_time":61,"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":"Swalbak","name":"JungHun Yuk","uuid":"83892525","kind":"user","description":"","email":"","website":null,"location":null,"twitter":null,"company":null,"icon_url":"https://avatars.githubusercontent.com/u/83892525?v=4","repositories_count":5,"last_synced_at":"2023-04-05T00:27:04.222Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/Swalbak","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2023-04-05T00:27:04.228Z","updated_at":"2023-04-05T00:27:04.228Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Swalbak","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Swalbak/repositories"},"packages":[],"commits":{"message":"Repository syncing started."},"issues_stats":{"full_name":"swalbak/datatrove_custom","html_url":"https://github.com/swalbak/datatrove_custom","last_synced_at":null,"status":null,"issues_count":null,"pull_requests_count":null,"avg_time_to_close_issue":null,"avg_time_to_close_pull_request":null,"issues_closed_count":null,"pull_requests_closed_count":null,"pull_request_authors_count":null,"issue_authors_count":null,"avg_comments_per_issue":null,"avg_comments_per_pull_request":null,"merged_pull_requests_count":null,"bot_issues_count":null,"bot_pull_requests_count":null,"past_year_issues_count":null,"past_year_pull_requests_count":null,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":null,"past_year_issues_closed_count":null,"past_year_pull_requests_closed_count":null,"past_year_pull_request_authors_count":null,"past_year_issue_authors_count":null,"past_year_avg_comments_per_issue":null,"past_year_avg_comments_per_pull_request":null,"past_year_bot_issues_count":null,"past_year_bot_pull_requests_count":null,"past_year_merged_pull_requests_count":null,"created_at":"2025-09-04T17:15:20.311Z","updated_at":"2025-09-04T17:15:20.311Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/swalbak%2Fdatatrove_custom","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/swalbak%2Fdatatrove_custom/issues","issue_labels_count":{},"pull_request_labels_count":{},"issue_author_associations_count":{},"pull_request_author_associations_count":{},"issue_authors":{},"pull_request_authors":{},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-04T00:00:25.939Z","repositories_count":10079947,"issues_count":31294689,"pull_requests_count":96077738,"authors_count":10693120,"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":{},"past_year_pull_request_author_associations_count":{},"past_year_issue_authors":{},"past_year_pull_request_authors":{},"maintainers":[],"active_maintainers":[]},"events":{"total":{"PushEvent":2,"CreateEvent":2},"last_year":{"PushEvent":2,"CreateEvent":2}},"keywords":[],"dependencies":[{"ecosystem":"actions","filepath":".github/workflows/pypi-release.yml","sha":null,"kind":"manifest","created_at":"2025-06-22T16:42:19.133Z","updated_at":"2025-06-22T16:42:19.133Z","repository_link":"https://github.com/Swalbak/datatrove_custom/blob/main/.github/workflows/pypi-release.yml","dependencies":[{"id":23757901628,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v3","direct":true,"kind":"composite","optional":false},{"id":23757901632,"package_name":"actions/setup-python","ecosystem":"actions","requirements":"v4","direct":true,"kind":"composite","optional":false},{"id":23757901634,"package_name":"actions/github-script","ecosystem":"actions","requirements":"v7","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/testing.yml","sha":null,"kind":"manifest","created_at":"2025-06-22T16:42:19.197Z","updated_at":"2025-06-22T16:42:19.197Z","repository_link":"https://github.com/Swalbak/datatrove_custom/blob/main/.github/workflows/testing.yml","dependencies":[{"id":23757901751,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v3","direct":true,"kind":"composite","optional":false},{"id":23757901752,"package_name":"actions/setup-python","ecosystem":"actions","requirements":"v4","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/trufflehog.yml","sha":null,"kind":"manifest","created_at":"2025-06-22T16:42:19.260Z","updated_at":"2025-06-22T16:42:19.260Z","repository_link":"https://github.com/Swalbak/datatrove_custom/blob/main/.github/workflows/trufflehog.yml","dependencies":[{"id":23757901929,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v4","direct":true,"kind":"composite","optional":false},{"id":23757901930,"package_name":"trufflesecurity/trufflehog","ecosystem":"actions","requirements":"main","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"cargo","filepath":"src/datatrove/tools/fast_mh3/Cargo.lock","sha":null,"kind":"lockfile","created_at":"2025-06-22T16:42:20.194Z","updated_at":"2025-06-22T16:42:20.194Z","repository_link":"https://github.com/Swalbak/datatrove_custom/blob/main/src/datatrove/tools/fast_mh3/Cargo.lock","dependencies":[{"id":23757903393,"package_name":"addr2line","ecosystem":"cargo","requirements":"0.24.2","direct":false,"kind":"runtime","optional":false},{"id":23757903394,"package_name":"adler2","ecosystem":"cargo","requirements":"2.0.0","direct":false,"kind":"runtime","optional":false},{"id":23757903395,"package_name":"allocator-api2","ecosystem":"cargo","requirements":"0.2.20","direct":false,"kind":"runtime","optional":false},{"id":23757903396,"package_name":"anstream","ecosystem":"cargo","requirements":"0.6.18","direct":false,"kind":"runtime","optional":false},{"id":23757903397,"package_name":"anstyle","ecosystem":"cargo","requirements":"1.0.10","direct":false,"kind":"runtime","optional":false},{"id":23757903398,"package_name":"anstyle-parse","ecosystem":"cargo","requirements":"0.2.6","direct":false,"kind":"runtime","optional":false},{"id":23757903399,"package_name":"anstyle-query","ecosystem":"cargo","requirements":"1.1.2","direct":false,"kind":"runtime","optional":false},{"id":23757903400,"package_name":"anstyle-wincon","ecosystem":"cargo","requirements":"3.0.6","direct":false,"kind":"runtime","optional":false},{"id":23757903401,"package_name":"anyhow","ecosystem":"cargo","requirements":"1.0.93","direct":false,"kind":"runtime","optional":false},{"id":23757903402,"package_name":"autocfg","ecosystem":"cargo","requirements":"1.4.0","direct":false,"kind":"runtime","optional":false},{"id":23757903403,"package_name":"aws-config","ecosystem":"cargo","requirements":"1.5.10","direct":false,"kind":"runtime","optional":false},{"id":23757903404,"package_name":"aws-credential-types","ecosystem":"cargo","requirements":"1.2.1","direct":false,"kind":"runtime","optional":false},{"id":23757903405,"package_name":"aws-runtime","ecosystem":"cargo","requirements":"1.4.3","direct":false,"kind":"runtime","optional":false},{"id":23757903406,"package_name":"aws-sdk-s3","ecosystem":"cargo","requirements":"1.63.0","direct":false,"kind":"runtime","optional":false},{"id":23757903407,"package_name":"aws-sdk-sso","ecosystem":"cargo","requirements":"1.49.0","direct":false,"kind":"runtime","optional":false},{"id":23757903408,"package_name":"aws-sdk-ssooidc","ecosystem":"cargo","requirements":"1.50.0","direct":false,"kind":"runtime","optional":false},{"id":23757903409,"package_name":"aws-sdk-sts","ecosystem":"cargo","requirements":"1.50.0","direct":false,"kind":"runtime","optional":false},{"id":23757903410,"package_name":"aws-sigv4","ecosystem":"cargo","requirements":"1.2.5","direct":false,"kind":"runtime","optional":false},{"id":23757903411,"package_name":"aws-smithy-async","ecosystem":"cargo","requirements":"1.2.1","direct":false,"kind":"runtime","optional":false},{"id":23757903412,"package_name":"aws-smithy-checksums","ecosystem":"cargo","requirements":"0.60.13","direct":false,"kind":"runtime","optional":false},{"id":23757903413,"package_name":"aws-smithy-eventstream","ecosystem":"cargo","requirements":"0.60.5","direct":false,"kind":"runtime","optional":false},{"id":23757903414,"package_name":"aws-smithy-http","ecosystem":"cargo","requirements":"0.60.11","direct":false,"kind":"runtime","optional":false},{"id":23757903415,"package_name":"aws-smithy-json","ecosystem":"cargo","requirements":"0.60.7","direct":false,"kind":"runtime","optional":false},{"id":23757903416,"package_name":"aws-smithy-query","ecosystem":"cargo","requirements":"0.60.7","direct":false,"kind":"runtime","optional":false},{"id":23757903417,"package_name":"aws-smithy-runtime","ecosystem":"cargo","requirements":"1.7.3","direct":false,"kind":"runtime","optional":false},{"id":23757903418,"package_name":"aws-smithy-runtime-api","ecosystem":"cargo","requirements":"1.7.3","direct":false,"kind":"runtime","optional":false},{"id":23757903419,"package_name":"aws-smithy-types","ecosystem":"cargo","requirements":"1.2.9","direct":false,"kind":"runtime","optional":false},{"id":23757903420,"package_name":"aws-smithy-xml","ecosystem":"cargo","requirements":"0.60.9","direct":false,"kind":"runtime","optional":false},{"id":23757903421,"package_name":"aws-types","ecosystem":"cargo","requirements":"1.3.3","direct":false,"kind":"runtime","optional":false},{"id":23757903422,"package_name":"backtrace","ecosystem":"cargo","requirements":"0.3.74","direct":false,"kind":"runtime","optional":false},{"id":23757903423,"package_name":"base16ct","ecosystem":"cargo","requirements":"0.1.1","direct":false,"kind":"runtime","optional":false},{"id":23757903424,"package_name":"base64","ecosystem":"cargo","requirements":"0.21.7","direct":false,"kind":"runtime","optional":false},{"id":23757903425,"package_name":"base64-simd","ecosystem":"cargo","requirements":"0.8.0","direct":false,"kind":"runtime","optional":false},{"id":23757903426,"package_name":"base64ct","ecosystem":"cargo","requirements":"1.6.0","direct":false,"kind":"runtime","optional":false},{"id":23757903427,"package_name":"bitflags","ecosystem":"cargo","requirements":"2.6.0","direct":false,"kind":"runtime","optional":false},{"id":23757903428,"package_name":"block-buffer","ecosystem":"cargo","requirements":"0.10.4","direct":false,"kind":"runtime","optional":false},{"id":23757903429,"package_name":"bumpalo","ecosystem":"cargo","requirements":"3.16.0","direct":false,"kind":"runtime","optional":false},{"id":23757903430,"package_name":"byteorder","ecosystem":"cargo","requirements":"1.5.0","direct":false,"kind":"runtime","optional":false},{"id":23757903431,"package_name":"bytes","ecosystem":"cargo","requirements":"1.8.0","direct":false,"kind":"runtime","optional":false},{"id":23757903432,"package_name":"bytes-utils","ecosystem":"cargo","requirements":"0.1.4","direct":false,"kind":"runtime","optional":false},{"id":23757903433,"package_name":"cc","ecosystem":"cargo","requirements":"1.2.20","direct":false,"kind":"runtime","optional":false},{"id":23757903434,"package_name":"cfg-if","ecosystem":"cargo","requirements":"1.0.0","direct":false,"kind":"runtime","optional":false},{"id":23757903435,"package_name":"clap","ecosystem":"cargo","requirements":"4.5.21","direct":false,"kind":"runtime","optional":false},{"id":23757903436,"package_name":"clap_builder","ecosystem":"cargo","requirements":"4.5.21","direct":false,"kind":"runtime","optional":false},{"id":23757903437,"package_name":"clap_derive","ecosystem":"cargo","requirements":"4.5.18","direct":false,"kind":"runtime","optional":false},{"id":23757903438,"package_name":"clap_lex","ecosystem":"cargo","requirements":"0.7.3","direct":false,"kind":"runtime","optional":false},{"id":23757903439,"package_name":"colorchoice","ecosystem":"cargo","requirements":"1.0.3","direct":false,"kind":"runtime","optional":false},{"id":23757903440,"package_name":"console","ecosystem":"cargo","requirements":"0.15.8","direct":false,"kind":"runtime","optional":false},{"id":23757903441,"package_name":"const-oid","ecosystem":"cargo","requirements":"0.9.6","direct":false,"kind":"runtime","optional":false},{"id":23757903442,"package_name":"core-foundation","ecosystem":"cargo","requirements":"0.9.4","direct":false,"kind":"runtime","optional":false},{"id":23757903443,"package_name":"core-foundation-sys","ecosystem":"cargo","requirements":"0.8.7","direct":false,"kind":"runtime","optional":false},{"id":23757903444,"package_name":"cpufeatures","ecosystem":"cargo","requirements":"0.2.16","direct":false,"kind":"runtime","optional":false},{"id":23757903445,"package_name":"crc32c","ecosystem":"cargo","requirements":"0.6.8","direct":false,"kind":"runtime","optional":false},{"id":23757904000,"package_name":"crc32fast","ecosystem":"cargo","requirements":"1.4.2","direct":false,"kind":"runtime","optional":false},{"id":23757904001,"package_name":"crypto-bigint","ecosystem":"cargo","requirements":"0.4.9","direct":false,"kind":"runtime","optional":false},{"id":23757904002,"package_name":"crypto-bigint","ecosystem":"cargo","requirements":"0.5.5","direct":false,"kind":"runtime","optional":false},{"id":23757904003,"package_name":"crypto-common","ecosystem":"cargo","requirements":"0.1.6","direct":false,"kind":"runtime","optional":false},{"id":23757904004,"package_name":"der","ecosystem":"cargo","requirements":"0.6.1","direct":false,"kind":"runtime","optional":false},{"id":23757904005,"package_name":"deranged","ecosystem":"cargo","requirements":"0.3.11","direct":false,"kind":"runtime","optional":false},{"id":23757904006,"package_name":"digest","ecosystem":"cargo","requirements":"0.10.7","direct":false,"kind":"runtime","optional":false},{"id":23757904007,"package_name":"displaydoc","ecosystem":"cargo","requirements":"0.2.5","direct":false,"kind":"runtime","optional":false},{"id":23757904008,"package_name":"ecdsa","ecosystem":"cargo","requirements":"0.14.8","direct":false,"kind":"runtime","optional":false},{"id":23757904009,"package_name":"either","ecosystem":"cargo","requirements":"1.13.0","direct":false,"kind":"runtime","optional":false},{"id":23757904010,"package_name":"elliptic-curve","ecosystem":"cargo","requirements":"0.12.3","direct":false,"kind":"runtime","optional":false},{"id":23757904011,"package_name":"encode_unicode","ecosystem":"cargo","requirements":"0.3.6","direct":false,"kind":"runtime","optional":false},{"id":23757904012,"package_name":"equivalent","ecosystem":"cargo","requirements":"1.0.1","direct":false,"kind":"runtime","optional":false},{"id":23757904013,"package_name":"fastrand","ecosystem":"cargo","requirements":"2.2.0","direct":false,"kind":"runtime","optional":false},{"id":23757904014,"package_name":"ff","ecosystem":"cargo","requirements":"0.12.1","direct":false,"kind":"runtime","optional":false},{"id":23757904015,"package_name":"fnv","ecosystem":"cargo","requirements":"1.0.7","direct":false,"kind":"runtime","optional":false},{"id":23757904016,"package_name":"foldhash","ecosystem":"cargo","requirements":"0.1.3","direct":false,"kind":"runtime","optional":false},{"id":23757904017,"package_name":"form_urlencoded","ecosystem":"cargo","requirements":"1.2.1","direct":false,"kind":"runtime","optional":false},{"id":23757904018,"package_name":"futures-channel","ecosystem":"cargo","requirements":"0.3.31","direct":false,"kind":"runtime","optional":false},{"id":23757904019,"package_name":"futures-core","ecosystem":"cargo","requirements":"0.3.31","direct":false,"kind":"runtime","optional":false},{"id":23757904020,"package_name":"futures-sink","ecosystem":"cargo","requirements":"0.3.31","direct":false,"kind":"runtime","optional":false},{"id":23757904021,"package_name":"futures-task","ecosystem":"cargo","requirements":"0.3.31","direct":false,"kind":"runtime","optional":false},{"id":23757904022,"package_name":"futures-util","ecosystem":"cargo","requirements":"0.3.31","direct":false,"kind":"runtime","optional":false},{"id":23757904023,"package_name":"generic-array","ecosystem":"cargo","requirements":"0.14.7","direct":false,"kind":"runtime","optional":false},{"id":23757904024,"package_name":"getrandom","ecosystem":"cargo","requirements":"0.2.15","direct":false,"kind":"runtime","optional":false},{"id":23757904025,"package_name":"gimli","ecosystem":"cargo","requirements":"0.31.1","direct":false,"kind":"runtime","optional":false},{"id":23757904026,"package_name":"group","ecosystem":"cargo","requirements":"0.12.1","direct":false,"kind":"runtime","optional":false},{"id":23757904027,"package_name":"h2","ecosystem":"cargo","requirements":"0.3.26","direct":false,"kind":"runtime","optional":false},{"id":23757904028,"package_name":"hashbrown","ecosystem":"cargo","requirements":"0.15.2","direct":false,"kind":"runtime","optional":false},{"id":23757904029,"package_name":"heck","ecosystem":"cargo","requirements":"0.5.0","direct":false,"kind":"runtime","optional":false},{"id":23757904030,"package_name":"hermit-abi","ecosystem":"cargo","requirements":"0.3.9","direct":false,"kind":"runtime","optional":false},{"id":23757904031,"package_name":"hex","ecosystem":"cargo","requirements":"0.4.3","direct":false,"kind":"runtime","optional":false},{"id":23757904032,"package_name":"hmac","ecosystem":"cargo","requirements":"0.12.1","direct":false,"kind":"runtime","optional":false},{"id":23757904033,"package_name":"http","ecosystem":"cargo","requirements":"0.2.12","direct":false,"kind":"runtime","optional":false},{"id":23757904034,"package_name":"http","ecosystem":"cargo","requirements":"1.1.0","direct":false,"kind":"runtime","optional":false},{"id":23757904035,"package_name":"http-body","ecosystem":"cargo","requirements":"0.4.6","direct":false,"kind":"runtime","optional":false},{"id":23757904036,"package_name":"http-body","ecosystem":"cargo","requirements":"1.0.1","direct":false,"kind":"runtime","optional":false},{"id":23757904037,"package_name":"http-body-util","ecosystem":"cargo","requirements":"0.1.2","direct":false,"kind":"runtime","optional":false},{"id":23757904038,"package_name":"httparse","ecosystem":"cargo","requirements":"1.9.5","direct":false,"kind":"runtime","optional":false},{"id":23757904039,"package_name":"httpdate","ecosystem":"cargo","requirements":"1.0.3","direct":false,"kind":"runtime","optional":false},{"id":23757904040,"package_name":"hyper","ecosystem":"cargo","requirements":"0.14.31","direct":false,"kind":"runtime","optional":false},{"id":23757904041,"package_name":"hyper-rustls","ecosystem":"cargo","requirements":"0.24.2","direct":false,"kind":"runtime","optional":false},{"id":23757904042,"package_name":"icu_collections","ecosystem":"cargo","requirements":"1.5.0","direct":false,"kind":"runtime","optional":false},{"id":23757904043,"package_name":"icu_locid","ecosystem":"cargo","requirements":"1.5.0","direct":false,"kind":"runtime","optional":false},{"id":23757904044,"package_name":"icu_locid_transform","ecosystem":"cargo","requirements":"1.5.0","direct":false,"kind":"runtime","optional":false},{"id":23757904045,"package_name":"icu_locid_transform_data","ecosystem":"cargo","requirements":"1.5.0","direct":false,"kind":"runtime","optional":false},{"id":23757904046,"package_name":"icu_normalizer","ecosystem":"cargo","requirements":"1.5.0","direct":false,"kind":"runtime","optional":false},{"id":23757904047,"package_name":"icu_normalizer_data","ecosystem":"cargo","requirements":"1.5.0","direct":false,"kind":"runtime","optional":false},{"id":23757904048,"package_name":"icu_properties","ecosystem":"cargo","requirements":"1.5.1","direct":false,"kind":"runtime","optional":false},{"id":23757904049,"package_name":"icu_properties_data","ecosystem":"cargo","requirements":"1.5.0","direct":false,"kind":"runtime","optional":false},{"id":23757904050,"package_name":"icu_provider","ecosystem":"cargo","requirements":"1.5.0","direct":false,"kind":"runtime","optional":false},{"id":23757904051,"package_name":"icu_provider_macros","ecosystem":"cargo","requirements":"1.5.0","direct":false,"kind":"runtime","optional":false},{"id":23757904052,"package_name":"idna","ecosystem":"cargo","requirements":"1.0.3","direct":false,"kind":"runtime","optional":false},{"id":23757904053,"package_name":"idna_adapter","ecosystem":"cargo","requirements":"1.2.0","direct":false,"kind":"runtime","optional":false},{"id":23757904054,"package_name":"indexmap","ecosystem":"cargo","requirements":"2.6.0","direct":false,"kind":"runtime","optional":false},{"id":23757904055,"package_name":"indicatif","ecosystem":"cargo","requirements":"0.17.9","direct":false,"kind":"runtime","optional":false},{"id":23757904056,"package_name":"is_terminal_polyfill","ecosystem":"cargo","requirements":"1.70.1","direct":false,"kind":"runtime","optional":false},{"id":23757904057,"package_name":"itoa","ecosystem":"cargo","requirements":"1.0.14","direct":false,"kind":"runtime","optional":false},{"id":23757904058,"package_name":"js-sys","ecosystem":"cargo","requirements":"0.3.72","direct":false,"kind":"runtime","optional":false},{"id":23757904059,"package_name":"lazy_static","ecosystem":"cargo","requirements":"1.5.0","direct":false,"kind":"runtime","optional":false},{"id":23757904060,"package_name":"libc","ecosystem":"cargo","requirements":"0.2.172","direct":false,"kind":"runtime","optional":false},{"id":23757904061,"package_name":"litemap","ecosystem":"cargo","requirements":"0.7.4","direct":false,"kind":"runtime","optional":false},{"id":23757904062,"package_name":"lock_api","ecosystem":"cargo","requirements":"0.4.12","direct":false,"kind":"runtime","optional":false},{"id":23757904063,"package_name":"log","ecosystem":"cargo","requirements":"0.4.22","direct":false,"kind":"runtime","optional":false},{"id":23757904064,"package_name":"lru","ecosystem":"cargo","requirements":"0.12.5","direct":false,"kind":"runtime","optional":false},{"id":23757904065,"package_name":"md-5","ecosystem":"cargo","requirements":"0.10.6","direct":false,"kind":"runtime","optional":false},{"id":23757904066,"package_name":"memchr","ecosystem":"cargo","requirements":"2.7.4","direct":false,"kind":"runtime","optional":false},{"id":23757904067,"package_name":"miniz_oxide","ecosystem":"cargo","requirements":"0.8.0","direct":false,"kind":"runtime","optional":false},{"id":23757904068,"package_name":"mio","ecosystem":"cargo","requirements":"1.0.2","direct":false,"kind":"runtime","optional":false},{"id":23757904069,"package_name":"num-conv","ecosystem":"cargo","requirements":"0.1.0","direct":false,"kind":"runtime","optional":false},{"id":23757904070,"package_name":"num-integer","ecosystem":"cargo","requirements":"0.1.46","direct":false,"kind":"runtime","optional":false},{"id":23757904071,"package_name":"num-traits","ecosystem":"cargo","requirements":"0.2.19","direct":false,"kind":"runtime","optional":false},{"id":23757904072,"package_name":"number_prefix","ecosystem":"cargo","requirements":"0.4.0","direct":false,"kind":"runtime","optional":false},{"id":23757904073,"package_name":"object","ecosystem":"cargo","requirements":"0.36.5","direct":false,"kind":"runtime","optional":false},{"id":23757904074,"package_name":"once_cell","ecosystem":"cargo","requirements":"1.20.2","direct":false,"kind":"runtime","optional":false},{"id":23757904075,"package_name":"openssl-probe","ecosystem":"cargo","requirements":"0.1.5","direct":false,"kind":"runtime","optional":false},{"id":23757904076,"package_name":"outref","ecosystem":"cargo","requirements":"0.5.1","direct":false,"kind":"runtime","optional":false},{"id":23757904077,"package_name":"p256","ecosystem":"cargo","requirements":"0.11.1","direct":false,"kind":"runtime","optional":false},{"id":23757904078,"package_name":"parking_lot","ecosystem":"cargo","requirements":"0.12.3","direct":false,"kind":"runtime","optional":false},{"id":23757904079,"package_name":"parking_lot_core","ecosystem":"cargo","requirements":"0.9.10","direct":false,"kind":"runtime","optional":false},{"id":23757904080,"package_name":"percent-encoding","ecosystem":"cargo","requirements":"2.3.1","direct":false,"kind":"runtime","optional":false},{"id":23757904081,"package_name":"pin-project","ecosystem":"cargo","requirements":"1.1.7","direct":false,"kind":"runtime","optional":false},{"id":23757904082,"package_name":"pin-project-internal","ecosystem":"cargo","requirements":"1.1.7","direct":false,"kind":"runtime","optional":false},{"id":23757904083,"package_name":"pin-project-lite","ecosystem":"cargo","requirements":"0.2.15","direct":false,"kind":"runtime","optional":false},{"id":23757904084,"package_name":"pin-utils","ecosystem":"cargo","requirements":"0.1.0","direct":false,"kind":"runtime","optional":false},{"id":23757904085,"package_name":"pkcs8","ecosystem":"cargo","requirements":"0.9.0","direct":false,"kind":"runtime","optional":false},{"id":23757904086,"package_name":"portable-atomic","ecosystem":"cargo","requirements":"1.10.0","direct":false,"kind":"runtime","optional":false},{"id":23757904087,"package_name":"powerfmt","ecosystem":"cargo","requirements":"0.2.0","direct":false,"kind":"runtime","optional":false},{"id":23757904088,"package_name":"ppv-lite86","ecosystem":"cargo","requirements":"0.2.20","direct":false,"kind":"runtime","optional":false},{"id":23757904089,"package_name":"proc-macro2","ecosystem":"cargo","requirements":"1.0.92","direct":false,"kind":"runtime","optional":false},{"id":23757904090,"package_name":"quote","ecosystem":"cargo","requirements":"1.0.37","direct":false,"kind":"runtime","optional":false},{"id":23757904091,"package_name":"rand","ecosystem":"cargo","requirements":"0.8.5","direct":false,"kind":"runtime","optional":false},{"id":23757904092,"package_name":"rand_chacha","ecosystem":"cargo","requirements":"0.3.1","direct":false,"kind":"runtime","optional":false},{"id":23757904093,"package_name":"rand_core","ecosystem":"cargo","requirements":"0.6.4","direct":false,"kind":"runtime","optional":false},{"id":23757904094,"package_name":"redox_syscall","ecosystem":"cargo","requirements":"0.5.7","direct":false,"kind":"runtime","optional":false},{"id":23757904095,"package_name":"regex-lite","ecosystem":"cargo","requirements":"0.1.6","direct":false,"kind":"runtime","optional":false},{"id":23757904096,"package_name":"rfc6979","ecosystem":"cargo","requirements":"0.3.1","direct":false,"kind":"runtime","optional":false},{"id":23757904097,"package_name":"ring","ecosystem":"cargo","requirements":"0.17.14","direct":false,"kind":"runtime","optional":false},{"id":23757904098,"package_name":"rustc-demangle","ecosystem":"cargo","requirements":"0.1.24","direct":false,"kind":"runtime","optional":false},{"id":23757904099,"package_name":"rustc_version","ecosystem":"cargo","requirements":"0.4.1","direct":false,"kind":"runtime","optional":false},{"id":23757904100,"package_name":"rustls","ecosystem":"cargo","requirements":"0.21.12","direct":false,"kind":"runtime","optional":false},{"id":23757904101,"package_name":"rustls-native-certs","ecosystem":"cargo","requirements":"0.6.3","direct":false,"kind":"runtime","optional":false},{"id":23757904102,"package_name":"rustls-pemfile","ecosystem":"cargo","requirements":"1.0.4","direct":false,"kind":"runtime","optional":false},{"id":23757904103,"package_name":"rustls-webpki","ecosystem":"cargo","requirements":"0.101.7","direct":false,"kind":"runtime","optional":false},{"id":23757904104,"package_name":"ryu","ecosystem":"cargo","requirements":"1.0.18","direct":false,"kind":"runtime","optional":false},{"id":23757904105,"package_name":"schannel","ecosystem":"cargo","requirements":"0.1.27","direct":false,"kind":"runtime","optional":false},{"id":23757904106,"package_name":"scopeguard","ecosystem":"cargo","requirements":"1.2.0","direct":false,"kind":"runtime","optional":false},{"id":23757904107,"package_name":"sct","ecosystem":"cargo","requirements":"0.7.1","direct":false,"kind":"runtime","optional":false},{"id":23757904108,"package_name":"sec1","ecosystem":"cargo","requirements":"0.3.0","direct":false,"kind":"runtime","optional":false},{"id":23757904109,"package_name":"security-framework","ecosystem":"cargo","requirements":"2.11.1","direct":false,"kind":"runtime","optional":false},{"id":23757904110,"package_name":"security-framework-sys","ecosystem":"cargo","requirements":"2.12.1","direct":false,"kind":"runtime","optional":false},{"id":23757904111,"package_name":"semver","ecosystem":"cargo","requirements":"1.0.23","direct":false,"kind":"runtime","optional":false},{"id":23757904112,"package_name":"serde","ecosystem":"cargo","requirements":"1.0.215","direct":false,"kind":"runtime","optional":false},{"id":23757904113,"package_name":"serde_derive","ecosystem":"cargo","requirements":"1.0.215","direct":false,"kind":"runtime","optional":false},{"id":23757904114,"package_name":"sha1","ecosystem":"cargo","requirements":"0.10.6","direct":false,"kind":"runtime","optional":false},{"id":23757904115,"package_name":"sha2","ecosystem":"cargo","requirements":"0.10.8","direct":false,"kind":"runtime","optional":false},{"id":23757904116,"package_name":"shlex","ecosystem":"cargo","requirements":"1.3.0","direct":false,"kind":"runtime","optional":false},{"id":23757904117,"package_name":"signal-hook-registry","ecosystem":"cargo","requirements":"1.4.2","direct":false,"kind":"runtime","optional":false},{"id":23757904118,"package_name":"signature","ecosystem":"cargo","requirements":"1.6.4","direct":false,"kind":"runtime","optional":false},{"id":23757904119,"package_name":"slab","ecosystem":"cargo","requirements":"0.4.9","direct":false,"kind":"runtime","optional":false},{"id":23757904120,"package_name":"smallvec","ecosystem":"cargo","requirements":"1.13.2","direct":false,"kind":"runtime","optional":false},{"id":23757904121,"package_name":"socket2","ecosystem":"cargo","requirements":"0.5.7","direct":false,"kind":"runtime","optional":false},{"id":23757904122,"package_name":"spki","ecosystem":"cargo","requirements":"0.6.0","direct":false,"kind":"runtime","optional":false},{"id":23757904123,"package_name":"stable_deref_trait","ecosystem":"cargo","requirements":"1.2.0","direct":false,"kind":"runtime","optional":false},{"id":23757904124,"package_name":"strsim","ecosystem":"cargo","requirements":"0.11.1","direct":false,"kind":"runtime","optional":false},{"id":23757904125,"package_name":"subtle","ecosystem":"cargo","requirements":"2.6.1","direct":false,"kind":"runtime","optional":false},{"id":23757904126,"package_name":"syn","ecosystem":"cargo","requirements":"2.0.89","direct":false,"kind":"runtime","optional":false},{"id":23757904127,"package_name":"synstructure","ecosystem":"cargo","requirements":"0.13.1","direct":false,"kind":"runtime","optional":false},{"id":23757904128,"package_name":"time","ecosystem":"cargo","requirements":"0.3.36","direct":false,"kind":"runtime","optional":false},{"id":23757904129,"package_name":"time-core","ecosystem":"cargo","requirements":"0.1.2","direct":false,"kind":"runtime","optional":false},{"id":23757904130,"package_name":"time-macros","ecosystem":"cargo","requirements":"0.2.18","direct":false,"kind":"runtime","optional":false},{"id":23757904131,"package_name":"tinystr","ecosystem":"cargo","requirements":"0.7.6","direct":false,"kind":"runtime","optional":false},{"id":23757904132,"package_name":"tokio","ecosystem":"cargo","requirements":"1.43.1","direct":false,"kind":"runtime","optional":false},{"id":23757904133,"package_name":"tokio-macros","ecosystem":"cargo","requirements":"2.5.0","direct":false,"kind":"runtime","optional":false},{"id":23757904134,"package_name":"tokio-retry","ecosystem":"cargo","requirements":"0.3.0","direct":false,"kind":"runtime","optional":false},{"id":23757904628,"package_name":"tokio-rustls","ecosystem":"cargo","requirements":"0.24.1","direct":false,"kind":"runtime","optional":false},{"id":23757904629,"package_name":"tokio-util","ecosystem":"cargo","requirements":"0.7.12","direct":false,"kind":"runtime","optional":false},{"id":23757904630,"package_name":"tower-service","ecosystem":"cargo","requirements":"0.3.3","direct":false,"kind":"runtime","optional":false},{"id":23757904631,"package_name":"tracing","ecosystem":"cargo","requirements":"0.1.40","direct":false,"kind":"runtime","optional":false},{"id":23757904632,"package_name":"tracing-attributes","ecosystem":"cargo","requirements":"0.1.27","direct":false,"kind":"runtime","optional":false},{"id":23757904633,"package_name":"tracing-core","ecosystem":"cargo","requirements":"0.1.33","direct":false,"kind":"runtime","optional":false},{"id":23757904634,"package_name":"try-lock","ecosystem":"cargo","requirements":"0.2.5","direct":false,"kind":"runtime","optional":false},{"id":23757904635,"package_name":"typenum","ecosystem":"cargo","requirements":"1.17.0","direct":false,"kind":"runtime","optional":false},{"id":23757904636,"package_name":"unicode-ident","ecosystem":"cargo","requirements":"1.0.14","direct":false,"kind":"runtime","optional":false},{"id":23757904637,"package_name":"unicode-width","ecosystem":"cargo","requirements":"0.1.14","direct":false,"kind":"runtime","optional":false},{"id":23757904638,"package_name":"unicode-width","ecosystem":"cargo","requirements":"0.2.0","direct":false,"kind":"runtime","optional":false},{"id":23757904639,"package_name":"untrusted","ecosystem":"cargo","requirements":"0.9.0","direct":false,"kind":"runtime","optional":false},{"id":23757904640,"package_name":"url","ecosystem":"cargo","requirements":"2.5.4","direct":false,"kind":"runtime","optional":false},{"id":23757904641,"package_name":"urlencoding","ecosystem":"cargo","requirements":"2.1.3","direct":false,"kind":"runtime","optional":false},{"id":23757904642,"package_name":"utf16_iter","ecosystem":"cargo","requirements":"1.0.5","direct":false,"kind":"runtime","optional":false},{"id":23757904643,"package_name":"utf8_iter","ecosystem":"cargo","requirements":"1.0.4","direct":false,"kind":"runtime","optional":false},{"id":23757904644,"package_name":"utf8parse","ecosystem":"cargo","requirements":"0.2.2","direct":false,"kind":"runtime","optional":false},{"id":23757904645,"package_name":"uuid","ecosystem":"cargo","requirements":"1.11.0","direct":false,"kind":"runtime","optional":false},{"id":23757904646,"package_name":"version_check","ecosystem":"cargo","requirements":"0.9.5","direct":false,"kind":"runtime","optional":false},{"id":23757904647,"package_name":"vsimd","ecosystem":"cargo","requirements":"0.8.0","direct":false,"kind":"runtime","optional":false},{"id":23757904962,"package_name":"want","ecosystem":"cargo","requirements":"0.3.1","direct":false,"kind":"runtime","optional":false},{"id":23757904963,"package_name":"wasi","ecosystem":"cargo","requirements":"0.11.0+wasi-snapshot-preview1","direct":false,"kind":"runtime","optional":false},{"id":23757904964,"package_name":"wasm-bindgen","ecosystem":"cargo","requirements":"0.2.95","direct":false,"kind":"runtime","optional":false},{"id":23757904965,"package_name":"wasm-bindgen-backend","ecosystem":"cargo","requirements":"0.2.95","direct":false,"kind":"runtime","optional":false},{"id":23757904966,"package_name":"wasm-bindgen-macro","ecosystem":"cargo","requirements":"0.2.95","direct":false,"kind":"runtime","optional":false},{"id":23757904967,"package_name":"wasm-bindgen-macro-support","ecosystem":"cargo","requirements":"0.2.95","direct":false,"kind":"runtime","optional":false},{"id":23757904968,"package_name":"wasm-bindgen-shared","ecosystem":"cargo","requirements":"0.2.95","direct":false,"kind":"runtime","optional":false},{"id":23757904969,"package_name":"web-time","ecosystem":"cargo","requirements":"1.1.0","direct":false,"kind":"runtime","optional":false},{"id":23757904970,"package_name":"windows-sys","ecosystem":"cargo","requirements":"0.52.0","direct":false,"kind":"runtime","optional":false},{"id":23757904971,"package_name":"windows-sys","ecosystem":"cargo","requirements":"0.59.0","direct":false,"kind":"runtime","optional":false},{"id":23757904972,"package_name":"windows-targets","ecosystem":"cargo","requirements":"0.52.6","direct":false,"kind":"runtime","optional":false},{"id":23757904973,"package_name":"windows_aarch64_gnullvm","ecosystem":"cargo","requirements":"0.52.6","direct":false,"kind":"runtime","optional":false},{"id":23757904974,"package_name":"windows_aarch64_msvc","ecosystem":"cargo","requirements":"0.52.6","direct":false,"kind":"runtime","optional":false},{"id":23757904975,"package_name":"windows_i686_gnu","ecosystem":"cargo","requirements":"0.52.6","direct":false,"kind":"runtime","optional":false},{"id":23757904976,"package_name":"windows_i686_gnullvm","ecosystem":"cargo","requirements":"0.52.6","direct":false,"kind":"runtime","optional":false},{"id":23757904977,"package_name":"windows_i686_msvc","ecosystem":"cargo","requirements":"0.52.6","direct":false,"kind":"runtime","optional":false},{"id":23757904978,"package_name":"windows_x86_64_gnu","ecosystem":"cargo","requirements":"0.52.6","direct":false,"kind":"runtime","optional":false},{"id":23757904979,"package_name":"windows_x86_64_gnullvm","ecosystem":"cargo","requirements":"0.52.6","direct":false,"kind":"runtime","optional":false},{"id":23757904980,"package_name":"windows_x86_64_msvc","ecosystem":"cargo","requirements":"0.52.6","direct":false,"kind":"runtime","optional":false},{"id":23757904981,"package_name":"write16","ecosystem":"cargo","requirements":"1.0.0","direct":false,"kind":"runtime","optional":false},{"id":23757904982,"package_name":"writeable","ecosystem":"cargo","requirements":"0.5.5","direct":false,"kind":"runtime","optional":false},{"id":23757904983,"package_name":"xmlparser","ecosystem":"cargo","requirements":"0.13.6","direct":false,"kind":"runtime","optional":false},{"id":23757904984,"package_name":"yoke","ecosystem":"cargo","requirements":"0.7.5","direct":false,"kind":"runtime","optional":false},{"id":23757904985,"package_name":"yoke-derive","ecosystem":"cargo","requirements":"0.7.5","direct":false,"kind":"runtime","optional":false},{"id":23757904986,"package_name":"zerocopy","ecosystem":"cargo","requirements":"0.7.35","direct":false,"kind":"runtime","optional":false},{"id":23757904987,"package_name":"zerocopy-derive","ecosystem":"cargo","requirements":"0.7.35","direct":false,"kind":"runtime","optional":false},{"id":23757904988,"package_name":"zerofrom","ecosystem":"cargo","requirements":"0.1.5","direct":false,"kind":"runtime","optional":false},{"id":23757904989,"package_name":"zerofrom-derive","ecosystem":"cargo","requirements":"0.1.5","direct":false,"kind":"runtime","optional":false},{"id":23757904990,"package_name":"zeroize","ecosystem":"cargo","requirements":"1.8.1","direct":false,"kind":"runtime","optional":false},{"id":23757904991,"package_name":"zerovec","ecosystem":"cargo","requirements":"0.10.4","direct":false,"kind":"runtime","optional":false},{"id":23757904992,"package_name":"zerovec-derive","ecosystem":"cargo","requirements":"0.10.3","direct":false,"kind":"runtime","optional":false}]},{"ecosystem":"cargo","filepath":"src/datatrove/tools/fast_mh3/Cargo.toml","sha":null,"kind":"manifest","created_at":"2025-06-22T16:42:23.651Z","updated_at":"2025-06-22T16:42:23.651Z","repository_link":"https://github.com/Swalbak/datatrove_custom/blob/main/src/datatrove/tools/fast_mh3/Cargo.toml","dependencies":[]},{"ecosystem":"pypi","filepath":"pyproject.toml","sha":null,"kind":"manifest","created_at":"2025-06-22T16:42:23.694Z","updated_at":"2025-06-22T16:42:23.694Z","repository_link":"https://github.com/Swalbak/datatrove_custom/blob/main/pyproject.toml","dependencies":[{"id":23757905239,"package_name":"dill","ecosystem":"pypi","requirements":"\u003e=0.3.0","direct":true,"kind":"runtime","optional":false},{"id":23757905240,"package_name":"fsspec","ecosystem":"pypi","requirements":"\u003e=2023.12.2","direct":true,"kind":"runtime","optional":false},{"id":23757905241,"package_name":"huggingface-hub","ecosystem":"pypi","requirements":"\u003e=0.17.0","direct":true,"kind":"runtime","optional":false},{"id":23757905242,"package_name":"humanize","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":23757905243,"package_name":"loguru","ecosystem":"pypi","requirements":"\u003e=0.7.0","direct":true,"kind":"runtime","optional":false},{"id":23757905244,"package_name":"multiprocess","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":23757905245,"package_name":"numpy","ecosystem":"pypi","requirements":"\u003e=2.0.0","direct":true,"kind":"runtime","optional":false},{"id":23757905246,"package_name":"tqdm","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]}],"score":null,"created_at":"2025-09-04T15:50:10.370Z","updated_at":"2025-10-07T08:04:57.707Z","avatar_url":"https://github.com/Swalbak.png","language":"Python","category":null,"sub_category":null,"monthly_downloads":0,"funding_links":[],"readme_doi_urls":[],"works":{},"citation_counts":{},"total_citations":0,"keywords_from_contributors":[],"project_url":"https://science.ecosyste.ms/api/v1/projects/4128","html_url":"https://science.ecosyste.ms/projects/4128"}