Validate doc type data during build

src/nrsk/documents/validate.py

@@ -0,0 +1,19 @@
+"""
+Validate document data during build.
+
+In particular, check doc types.
+"""
+
+import pathlib
+
+import yaml
+
+from nrsk.models import InformationTypes
+
+
+def validate_doc_types(app):
+    """Ensure doc type data is valid."""
+    fpath = pathlib.Path(app.srcdir) / "_data" / "doc-types.yaml"
+    with open(fpath) as f:
+        data = yaml.safe_load(f)
+        data = InformationTypes.validate_python(data)

src/nrsk/models.py

@@ -48,6 +48,7 @@ from typing import Annotated, Any
 from pydantic import (
     AnyUrl,
     BaseModel,
+    ConfigDict,
     EmailStr,
     Field,
     PositiveInt,
@@ -209,6 +210,26 @@ class ITSystem(BaseModel):
     quality_related: bool
 
 
+class InformationType(BaseModel):
+    """A type/kind/class of Information, Document, or Record."""
+
+    model_config = ConfigDict(extra="forbid")
+
+    name: str
+    abbrev: str
+    examples: list[str] | None = None
+    description: str = ""
+    retention: str | None = ""
+    record: bool = True
+    use_cases: str = ""
+    notes: str = ""
+    parent: InformationType | None = None
+
+
+InformationTypes = TypeAdapter(list[InformationType])
+"""A list of document types."""
+
+
 class Document(BaseModel):
     """
     Data dictionary entry for Documents and Records.
@@ -363,6 +384,9 @@ class Document(BaseModel):
 
         Retention plans define how long the document or record is to be
         kept before it is destroyed.
+
+        .. note:: May want this to actually be a timedelta
+
         """
 
         LIFETIME = "LIFETIME"
@@ -411,6 +435,10 @@ class Document(BaseModel):
         description="Filenames of files attached to this Document. Main file should be the first.",
         default=[],
     )
+    file_notes: list[str] = Field(
+        description="Short description of each file represented in filenames.",
+        default=[],
+    )
     checksums: list[str] = Field(
         description="SHA-256 checksum of each file for data integrity", default=[]
     )
@@ -420,9 +448,12 @@ class Document(BaseModel):
     easier periodic re-verification of large data libraries."""
 
     physical_location: str | None = Field(
-        description="Location of a media when not stored as an electronic file.",
+        description="Location of a media (only valid when not stored as an electronic file).",
         default=None,
     )
+    notes: str = Field(
+        description="Additional information about the Document/Record", default=""
+    )
 
     @field_validator("type", mode="after")
     @classmethod