feat: support vendorization through config

This commit uses `pydantic-settings` to
establish a configuration mechanism, and
through this mechanism, it adds support
for "vendorization".

Author: candleindark

dandischema/conf.py

@@ -0,0 +1,35 @@
+# This file defines the configuration for the DANDI schema
+
+from __future__ import annotations
+
+from pydantic_settings import BaseSettings, SettingsConfigDict
+
+
+class Config(BaseSettings):
+    """
+    Configuration for the DANDI schema
+
+    Note
+    ----
+        Since this class is subclass of `pydantic.BaseSettings`, each field of an
+        instance of this class can be populated from an environment variable of the
+        same name prefixed with the prefix defined in `model_config` with the name
+        of the environment variable interpreted **case-insensitively**.
+        For details, see https://docs.pydantic.dev/latest/concepts/pydantic_settings/
+    """
+
+    model_config = SettingsConfigDict(env_prefix="dandi_schema_")
+
+    id_pattern: str = r"[A-Z]+"
+    """Regex pattern for the prefix of identifiers"""
+
+    datacite_doi_id_pattern: str = r"\d{4,}"
+    """
+    The registrant code pattern of the DOI prefix at DataCite
+
+    The number sequence that follows "10." within the DOI prefix as documented
+    at https://support.datacite.org/docs/prefixes.
+    """
+
+
+CONFIG = Config()

dandischema/consts.py

@@ -1,4 +1,4 @@
-DANDI_SCHEMA_VERSION = "0.6.11"
+DANDI_SCHEMA_VERSION = "0.6.12"
 ALLOWED_INPUT_SCHEMAS = [
     "0.4.4",
     "0.5.1",
@@ -14,6 +14,7 @@
     "0.6.8",
     "0.6.9",
     "0.6.10",
+    "0.6.11",
     DANDI_SCHEMA_VERSION,
 ]
 

dandischema/models.py

@@ -36,11 +36,17 @@
 from pydantic_core import CoreSchema
 from zarr_checksum.checksum import InvalidZarrChecksum, ZarrDirectoryDigest
 
+from dandischema.conf import CONFIG
+
 from .consts import DANDI_SCHEMA_VERSION
 from .digests.dandietag import DandiETag
 from .types import ByteSizeJsonSchema
 from .utils import name2title
 
+# Load needed configurations into constants
+ID_PATTERN = CONFIG.id_pattern
+DATACITE_DOI_ID_PATTERN = CONFIG.datacite_doi_id_pattern
+
 # Use DJANGO_DANDI_WEB_APP_URL to point to a specific deployment.
 DANDI_INSTANCE_URL: Optional[str]
 try:
@@ -58,18 +64,11 @@
 )
 ASSET_UUID_PATTERN = r"^dandiasset:" + UUID_PATTERN
 VERSION_PATTERN = r"\d{6}/\d+\.\d+\.\d+"
-# Vendored
-# DANDI_DOI_PATTERN = rf"^10.(48324|80507)/dandi\.{VERSION_PATTERN}"
-# Unvendored, only with 10. prefix, as likely all would have for datacite
-DANDI_DOI_PATTERN = rf"^10.\d+/[a-z]+\.{VERSION_PATTERN}"
-# Vendored:
-# DANDI_PUBID_PATTERN = rf"^DANDI:{VERSION_PATTERN}"
-# Unvendored:
-DANDI_PUBID_PATTERN = rf"^[A-Z]+:{VERSION_PATTERN}"
-# Vendored:
-#  potentially could be set to alternative namespace
-# Unvendored: use "dandi" by default
-DANDI_NSKEY = "dandi"
+DANDI_DOI_PATTERN = (
+    rf"^10\.{DATACITE_DOI_ID_PATTERN}/{ID_PATTERN.lower()}\.{VERSION_PATTERN}"
+)
+DANDI_PUBID_PATTERN = rf"^{ID_PATTERN}:{VERSION_PATTERN}"
+DANDI_NSKEY = "dandi"  # Namespace for DANDI ontology
 
 PUBLISHED_VERSION_URL_PATTERN = (
     rf"^{DANDI_INSTANCE_URL_PATTERN}/dandiset/{VERSION_PATTERN}$"
@@ -1624,20 +1623,16 @@ def contributor_musthave_contact(
 
     id: str = Field(
         description="Uniform resource identifier",
-        # Vendored:
-        # pattern=r"^(dandi|DANDI):\d{6}(/(draft|\d+\.\d+\.\d+))$",
-        # Unvendored:
-        pattern=r"^([a-z]+|[A-Z]+):\d{6}(/(draft|\d+\.\d+\.\d+))$",
+        pattern=(
+            rf"^({ID_PATTERN}|{ID_PATTERN.lower()}):\d{{6}}(/(draft|\d+\.\d+\.\d+))$"
+        ),
         json_schema_extra={"readOnly": True},
     )
 
     identifier: DANDI = Field(
         title="Dandiset identifier",
         description="A Dandiset identifier that can be resolved by identifiers.org.",
-        # Vendored:
-        # pattern=r"^DANDI:\d{6}$",
-        # Unvendored:
-        pattern=r"^[A-Z]+:\d{6}$",
+        pattern=rf"^{ID_PATTERN}:\d{{6}}$",
         json_schema_extra={"readOnly": True, "nskey": "schema"},
     )
     name: str = Field(

setup.cfg

@@ -29,6 +29,7 @@ project_urls =
 python_requires = >=3.9
 install_requires =
     jsonschema[format]
+    pydantic-settings
     pydantic[email] ~= 2.4
     requests
     zarr_checksum