{"id": "D01", "tags": ["golden"], "inputs": {"doc_path": "/ABSOLUTE/PATH/TO/cookbooks/04-document-extraction-structuring-lab/assets/dataset/sources/invoice-clean.docx", "document_type": "invoice"}, "expectations": {"validation_status": "pass", "must_contain_fields": ["invoice_id", "vendor", "line_items", "total", "currency", "issue_date"]}}
{"id": "D02", "tags": ["golden"], "inputs": {"doc_path": "/ABSOLUTE/PATH/TO/cookbooks/04-document-extraction-structuring-lab/assets/dataset/sources/invoice-clean.xlsx", "document_type": "spreadsheet"}, "expectations": {"validation_status": "pass", "must_contain_fields": ["invoice_id", "vendor", "line_items", "total", "currency", "issue_date"]}}
{"id": "D03", "tags": ["edge", "missing_field"], "inputs": {"doc_path": "/ABSOLUTE/PATH/TO/cookbooks/04-document-extraction-structuring-lab/assets/dataset/sources/invoice-partial.docx", "document_type": "invoice"}, "expectations": {"validation_status": "partial", "must_contain_fields": ["invoice_id", "vendor", "line_items", "currency", "issue_date"], "missing_fields": ["total"]}}
{"id": "D04", "tags": ["edge", "missing_field"], "inputs": {"doc_path": "/ABSOLUTE/PATH/TO/cookbooks/04-document-extraction-structuring-lab/assets/dataset/sources/invoice-no-vendor.docx", "document_type": "invoice"}, "expectations": {"validation_status": "partial", "must_contain_fields": ["invoice_id", "line_items", "total", "currency", "issue_date"], "missing_fields": ["vendor"]}}
{"id": "D05", "tags": ["negative", "unsupported_format"], "inputs": {"doc_path": "/ABSOLUTE/PATH/TO/cookbooks/04-document-extraction-structuring-lab/assets/dataset/sources/invoice-legacy.doc", "document_type": "unsupported"}, "expectations": {"validation_status": "fail", "error_kind": "unsupported", "error_readable": true, "must_contain_fields": []}}
{"id": "D06", "tags": ["negative", "corrupt"], "inputs": {"doc_path": "/ABSOLUTE/PATH/TO/cookbooks/04-document-extraction-structuring-lab/assets/dataset/sources/invoice-corrupt.docx", "document_type": "invoice"}, "expectations": {"validation_status": "fail", "error_readable": true, "must_contain_fields": []}}