{"id":17182441,"url":"https://github.com/bertsky/docstruct","last_synced_at":"2025-07-15T12:43:21.876Z","repository":{"id":118132663,"uuid":"533421323","full_name":"bertsky/docstruct","owner":"bertsky","description":"Document structure detection from PAGE-XML to METS-XML","archived":false,"fork":false,"pushed_at":"2025-04-09T18:04:38.000Z","size":29,"stargazers_count":6,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-09T19:22:32.749Z","etag":null,"topics":["ocr-d"],"latest_commit_sha":null,"homepage":"","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/bertsky.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}},"created_at":"2022-09-06T16:57:44.000Z","updated_at":"2025-04-09T18:04:42.000Z","dependencies_parsed_at":null,"dependency_job_id":"53d64a16-41be-41f0-b925-e1a01a3601eb","html_url":"https://github.com/bertsky/docstruct","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bertsky%2Fdocstruct","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bertsky%2Fdocstruct/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bertsky%2Fdocstruct/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bertsky%2Fdocstruct/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bertsky","download_url":"https://codeload.github.com/bertsky/docstruct/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248758449,"owners_count":21156957,"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":["ocr-d"],"created_at":"2024-10-15T00:37:05.756Z","updated_at":"2025-04-13T17:52:39.715Z","avatar_url":"https://github.com/bertsky.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"[![Docker Image CD](https://github.com/bertsky/docstruct/actions/workflows/docker-image.yml/badge.svg)](https://github.com/bertsky/docstruct/actions/workflows/docker-image.yml)\n\n# docstruct\n\n    Document structure detection from PAGE to METS\n\nProvides an [OCR-D processor](https://ocr-d.de/en/spec/cli)\nwhich will parse the input page-level structure (as detected by\nsome [OCR-D](https://ocr-d.de/en/about) workflow including preprocessing,\nlayout analysis and OCR) of a document annotated via [PAGE-XML](https://ocr-d.de/en/spec/page)\nand [METS-XML](https://ocr-d.de/en/spec/mets), further analyse it\n(...) and wrap it into a document-level structure in the METS using\nlogical `mets:structMap` and either …\n- `mets:structLink` ([DFG profile](http://dfg-viewer.de/fileadmin/groups/dfgviewer/METS-Anwendungsprofil_2.3.1.pdf)), or\n- `mets:area` ([ENMAP profile](http://www.europeana-newspapers.eu/wp-content/uploads/2015/05/D5.3_Final_release_ENMAP_1.0.pdf))\n\n… for representation.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbertsky%2Fdocstruct","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbertsky%2Fdocstruct","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbertsky%2Fdocstruct/lists"}