Bump datamodel-codegen to 0.25.2 (#33)

* Bump datamodel-codegen to 0.25.2

* [GENERATE] Pydantic models from JSON Schema

* Python with double quotes for Black compatibility

* [GENERATE] Pydantic models from JSON Schema

* Bump ssb_datadoc_model to 4.1.0

---------

Co-authored-by: dapla-bot[bot] <143391972+dapla-bot[bot]@users.noreply.github.com>

Author: mmwinther

.github/workflows/generate-python.yml

@@ -45,7 +45,7 @@ jobs:
 
       - name: Install datamodel-codegen
         run: |
-            python -m pipx install datamodel-code-generator==0.24.2
+            python -m pipx install datamodel-code-generator==0.25.2
 
       - name: Generate Python
         run: >
@@ -55,8 +55,10 @@ jobs:
             --output-model-type pydantic_v2.BaseModel
             --use-default
             --use-one-literal-as-default
+            --force-optional
             --use-subclass-enum
             --use-standard-collections
+            --use-double-quotes
             --target-python-version 3.10
             --output generated/python/datadoc_model/datadoc_model/model.py
 

generated/python/datadoc_model/datadoc_model/model.py

@@ -1,15 +1,14 @@
 # generated by datamodel-codegen:
 #   filename:  metadata-container-json-schema.json
-#   timestamp: 2023-12-06T10:21:06+00:00
+#   timestamp: 2024-01-04T07:49:11+00:00
 
 from __future__ import annotations
 
-from datetime import datetime
 from enum import Enum
 from typing import Any, Literal, Optional
 from uuid import UUID
 
-from pydantic import AnyUrl, BaseModel, Field
+from pydantic import AnyUrl, AwareDatetime, BaseModel, Field
 
 
 class Assessment(str, Enum):
@@ -51,7 +50,7 @@ class VariableRole(str, Enum):
 class LanguageStringType(BaseModel):
     en: Optional[str] = None
     nn: Optional[str] = None
-    nb: str
+    nb: Optional[str] = None
 
 
 class UnitType(str, Enum):
@@ -86,8 +85,8 @@ class TemporalityTypeType(str, Enum):
 
 
 class PseudoDataset(BaseModel):
-    dataset_pseudo_time: datetime = Field(
-        ...,
+    dataset_pseudo_time: Optional[AwareDatetime] = Field(
+        None,
         description="Time at which the dataset was pseudonymized. In ISO 8601 format.",
         title="Dataset pseudo time",
     )
@@ -106,8 +105,8 @@ class SourceVariableDatatype(str, Enum):
 
 
 class PseudoVariable(BaseModel):
-    short_name: str = Field(
-        ...,
+    short_name: Optional[str] = Field(
+        None,
         description="Physical name of the variable in the dataset. Should match the recommended short name.",
         title="Short name",
     )
@@ -131,13 +130,13 @@ class PseudoVariable(BaseModel):
         description="Version of stable identifier the variable was mapped to prior to pseudonymization.",
         title="Stable identifier version",
     )
-    encryption_algorithm: str = Field(
-        ...,
+    encryption_algorithm: Optional[str] = Field(
+        None,
         description="The encryption algorithm used to pseudonymize the variable.",
         title="Encryption algorithm",
     )
-    encryption_key_reference: str = Field(
-        ...,
+    encryption_key_reference: Optional[str] = Field(
+        None,
         description="Name of or reference to the encryption key used to pseudonymize the variable.",
         title="Encryption key reference",
     )
@@ -158,30 +157,32 @@ class PseudoVariable(BaseModel):
 
 class PseudonymizationJsonSchema(BaseModel):
     document_version: Literal["0.1.0"] = "0.1.0"
-    pseudo_dataset: PseudoDataset
-    pseudo_variables: list[PseudoVariable]
+    pseudo_dataset: Optional[PseudoDataset] = None
+    pseudo_variables: Optional[list[PseudoVariable]] = None
 
 
 class Dataset(BaseModel):
-    short_name: str = Field(
-        ...,
+    short_name: Optional[str] = Field(
+        None,
         description="Name of (physical) data file, data table or dataset",
         title="Short name",
     )
-    assessment: Assessment = Field(
-        ...,
+    assessment: Optional[Assessment] = Field(
+        None,
         description="Value assessment (sensitivity classification) for the data set",
         title="Assessment",
     )
-    dataset_status: DatasetStatus = Field(
-        ..., description="Life cycle for data set", title="Data set status"
+    dataset_status: Optional[DatasetStatus] = Field(
+        None, description="Life cycle for data set", title="Data set status"
     )
-    dataset_state: DatasetState = Field(
-        ..., description="Steady state of data", title="Data set state"
+    dataset_state: Optional[DatasetState] = Field(
+        None, description="Steady state of data", title="Data set state"
     )
-    name: LanguageStringType = Field(..., description="Name of data set", title="Name")
-    description: LanguageStringType = Field(
-        ..., description="Free text description of the data set", title="Description"
+    name: Optional[LanguageStringType] = Field(
+        None, description="Name of data set", title="Name"
+    )
+    description: Optional[LanguageStringType] = Field(
+        None, description="Free text description of the data set", title="Description"
     )
     data_source: Optional[LanguageStringType] = Field(
         None,
@@ -191,19 +192,21 @@ class Dataset(BaseModel):
     register_uri: Optional[LanguageStringType] = Field(
         None, description="Link to register", title="Register"
     )
-    population_description: LanguageStringType = Field(
-        ...,
+    population_description: Optional[LanguageStringType] = Field(
+        None,
         description="Description of the population covered in the data set. Includes unit type, spatial coverage and period of time.",
         title="Description of population",
     )
-    version: str = Field(..., description="Version of data set", title="Version")
+    version: Optional[str] = Field(
+        None, description="Version of data set", title="Version"
+    )
     version_description: Optional[LanguageStringType] = Field(
         None,
         description="Dataset version information in the form of descriptive text",
         title="Version description",
     )
-    unit_type: UnitType = Field(
-        ...,
+    unit_type: Optional[UnitType] = Field(
+        None,
         description="Unit Type for data file, table or data set. See Definitions of Unit Types https://www.ssb.no/en/metadata/definisjoner-av-statistiske-enheter",
         title="Unit type",
     )
@@ -212,8 +215,8 @@ class Dataset(BaseModel):
         description="Temporality type. Either for the instance variable or the data set",
         title="Temporality type",
     )
-    subject_field: LanguageStringType = Field(
-        ...,
+    subject_field: Optional[LanguageStringType] = Field(
+        None,
         description="Primary area of statistics in which the data set is included",
         title="Subject field",
     )
@@ -227,34 +230,34 @@ class Dataset(BaseModel):
         description="Description of the data set's spatial coverage",
         title="Spatial coverage description",
     )
-    id: UUID = Field(
-        ..., description="Unique identifier for the data set", title="Identifier"
+    id: Optional[UUID] = Field(
+        None, description="Unique identifier for the data set", title="Identifier"
     )
-    owner: LanguageStringType = Field(
-        ...,
+    owner: Optional[LanguageStringType] = Field(
+        None,
         description="Owner of the data set (responsible division in Statistics Norway). See also Classification of organisational units https://www.ssb.no/en/klass/klassifikasjoner/83",
         title="Owner",
     )
-    file_path: str = Field(
-        ...,
+    file_path: Optional[str] = Field(
+        None,
         description="The file path contains the data set's name and the path to where it is stored",
         title="File path",
     )
-    metadata_created_date: datetime = Field(
-        ...,
+    metadata_created_date: Optional[AwareDatetime] = Field(
+        None,
         description="Created date for metadata about the data set",
         title="Metadata created date",
     )
-    metadata_created_by: str = Field(
-        ..., description="Created by identifiable person.", title="Metadata created by"
+    metadata_created_by: Optional[str] = Field(
+        None, description="Created by identifiable person.", title="Metadata created by"
     )
-    metadata_last_updated_date: datetime = Field(
-        ...,
+    metadata_last_updated_date: Optional[AwareDatetime] = Field(
+        None,
         description="Last updated date for metadata about the dataset",
         title="Metadata last updated date",
     )
-    metadata_last_updated_by: str = Field(
-        ...,
+    metadata_last_updated_by: Optional[str] = Field(
+        None,
         description="Last change made by identifiable person. ",
         title="Metadata last updated by",
     )
@@ -271,19 +274,21 @@ class Dataset(BaseModel):
 
 
 class Variable(BaseModel):
-    short_name: str = Field(
-        ...,
+    short_name: Optional[str] = Field(
+        None,
         description="Physical name of the variable in the dataset. Should match the recommended short name.",
         title="Short name",
     )
-    name: LanguageStringType = Field(
-        ...,
+    name: Optional[LanguageStringType] = Field(
+        None,
         description="Variable names can be inherited from VarDef, but can also be documented/changed here",
         title="Name",
     )
-    data_type: DataType = Field(..., description="Data type", title="Data type")
-    variable_role: VariableRole = Field(
-        ...,
+    data_type: Optional[DataType] = Field(
+        None, description="Data type", title="Data type"
+    )
+    variable_role: Optional[VariableRole] = Field(
+        None,
         description="Role of the instance variable in the data set",
         title="Variable role",
     )
@@ -292,8 +297,8 @@ class Variable(BaseModel):
         description="A link (URI) to the variable's definition in Vardok/VarDef",
         title="Definition URI",
     )
-    direct_person_identifying: bool = Field(
-        ...,
+    direct_person_identifying: Optional[bool] = Field(
+        None,
         description="Direct Person identifying Information (DPI). Some of the values \u200b\u200bin an instance variable kan be DPI, others not. In this case, DPI is set equal to true. For example, the variable exporter where some of the values \u200b\u200bcan be organization number, others social security numbers (sole proprietorships).",
         title="Direct Person identifying Information (DPI)",
     )
@@ -340,17 +345,17 @@ class Variable(BaseModel):
         description="Invalid value(s) description used in addition (or as an alternative) to standard sentinel values.",
         title="Invalid value(s) description",
     )
-    id: UUID = Field(
-        ...,
+    id: Optional[UUID] = Field(
+        None,
         description="Unique SSB identifier for the instance variable in the data set",
         title="Identifier",
     )
-    contains_data_from: Optional[datetime] = Field(
+    contains_data_from: Optional[AwareDatetime] = Field(
         None,
         description="The instance variable in the data set contains data from and including this date. This can be useful information for data sets that contain many instance variables in addition to data for many periods/years. In many cases, it will then be the case that some variables only contain data for the most recent periods/years, e.g. if the entire data set contains data from 1970 to 2020, while some instance variables only contain data from 1998 onwards.",
         title="Contains data from",
     )
-    contains_data_until: Optional[datetime] = Field(
+    contains_data_until: Optional[AwareDatetime] = Field(
         None,
         description="The instance variable in the data set contains data up to and including this date. This can be useful information for data sets that contain many instance variables in addition to data for many periods/years. In many cases, it will then be the case that some of the instance variables in the data set are terminated (no longer updated) after a given point in time.",
         title="Contains data up until",
@@ -364,11 +369,11 @@ class DatadocJsonSchema(BaseModel):
     document_version: Literal["2.0.0"] = Field(
         "2.0.0", description="Version of this model"
     )
-    dataset: Dataset
-    variables: list[Variable]
+    dataset: Optional[Dataset] = None
+    variables: Optional[list[Variable]] = None
 
 
 class MetadataContainer(BaseModel):
-    document_version: Literal["0.0.1"] = None
+    document_version: Literal["0.0.1"] = "0.0.1"
     datadoc: Optional[DatadocJsonSchema] = None
     pseudonymization: Optional[PseudonymizationJsonSchema] = None

generated/python/datadoc_model/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "ssb-datadoc-model"
-version = "4.0.2"
+version = "4.1.0"
 description = "Data Model for use in Statistics Norway's Metadata system"
 authors = ["Statistics Norway <stat-dev@ssb.no>"]
 license = "MIT"