{"id":16219640,"url":"https://github.com/ololobus/slavic_text_scht","last_synced_at":"2025-08-17T05:06:26.136Z","repository":{"id":150988194,"uuid":"54147078","full_name":"ololobus/slavic_text_scht","owner":"ololobus","description":"St. Petersburg corpus of hagiographic texts","archived":false,"fork":false,"pushed_at":"2016-04-24T22:25:18.000Z","size":2172,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-07T23:42:42.368Z","etag":null,"topics":["corpora","hagiographic-texts","linguistics","slavic-languages"],"latest_commit_sha":null,"homepage":null,"language":"Python","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/ololobus.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":"2016-03-17T19:51:48.000Z","updated_at":"2017-06-12T11:46:16.000Z","dependencies_parsed_at":null,"dependency_job_id":"c9e35893-89f1-489f-8b8a-3e086d45b52e","html_url":"https://github.com/ololobus/slavic_text_scht","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ololobus/slavic_text_scht","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ololobus%2Fslavic_text_scht","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ololobus%2Fslavic_text_scht/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ololobus%2Fslavic_text_scht/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ololobus%2Fslavic_text_scht/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ololobus","download_url":"https://codeload.github.com/ololobus/slavic_text_scht/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ololobus%2Fslavic_text_scht/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":270807934,"owners_count":24649346,"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":"2025-08-17T02:00:09.016Z","response_time":129,"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":["corpora","hagiographic-texts","linguistics","slavic-languages"],"created_at":"2024-10-10T11:55:17.238Z","updated_at":"2025-08-17T05:06:26.115Z","avatar_url":"https://github.com/ololobus.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"### St. Petersburg Corpus of Hagiographic Texts\n\nOld Church Slavic corpus\n\nhttp://project.phil.spbu.ru/scat/page.php?page=project\n\n\n### Parser\nRun to get entire xml text.\n\n```\n./tei_parser.py xml/Aleksandr_svirskij.xml\n```\n\nTODO:\n * return text sentence by sentence\n * return text clause by clause\n * keep info about named entities (`\u003cname\u003e` tag)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fololobus%2Fslavic_text_scht","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fololobus%2Fslavic_text_scht","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fololobus%2Fslavic_text_scht/lists"}