name: dataset
file_type: dataset_file
primary_key: [project_accession]
doc: "Project-level metadata for a QPX dataset (single-row file)"

fields:
  project_accession:
    type: string
    required: true
    doc: "Project accession (e.g., PXD014414)"
  project_title:
    type: string
    doc: "Title of the project"
  project_description:
    type: string
    doc: "Project description"
  pubmed_id:
    type: string
    doc: "PubMed ID"
  software_name:
    type: string
    doc: "Software that generated the data"
  software_version:
    type: string
    doc: "Software version"
  creation_date:
    type: string
    required: true
    doc: "ISO 8601 date when dataset was created"

  # Integrity / packaging
  file_checksums:
    type: "map<string, string>"
    doc: "SHA-256 hex digests keyed by file name (relative to dataset root)"
  file_row_counts:
    type: "map<string, int64>"
    doc: "Row counts keyed by file name"
  file_sizes_bytes:
    type: "map<string, int64>"
    doc: "File sizes in bytes keyed by file name"
  total_structures:
    type: int32
    doc: "Number of Parquet structures in this dataset"
  packaged_at:
    type: string
    doc: "ISO 8601 timestamp when integrity was computed"