refactor: use SnakeCaseString and NoWhitespaceString for source fields

ericgodwin · Copilot · ericgodwin · commit 2fe0540f11ad · 2026-06-04T11:57:20.000-07:00
Replace inline regex patterns with the existing system string types:
- provider: SnakeCaseString (^[a-z0-9]+(_[a-z0-9]+)*$)
- resource: SnakeCaseString (^[a-z0-9]+(_[a-z0-9]+)*$)
- version: NoWhitespaceString (^\S+$)

Update example to use underscores instead of hyphens for resource
names (e.g., ml_buildings instead of ml-buildings).

Co-authored-by: Copilot &lt;223556219+Copilot@users.noreply.github.com&gt;
Signed-off-by: ericgodwin &lt;eric@overturemaps.org&gt;
diff --git a/examples/buildings/sources-with-version.yaml b/examples/buildings/sources-with-version.yaml
@@ -17,7 +17,7 @@ properties:
     - property: "/properties/name"
       dataset: metaML-buildings
       provider: meta
-      resource: ml-buildings
+      resource: ml_buildings
       version: 'abcdef'
     - property: "/properties/height"
       dataset: microsoft-buildings
diff --git a/packages/overture-schema-addresses-theme/tests/address_baseline_schema.json b/packages/overture-schema-addresses-theme/tests/address_baseline_schema.json
@@ -55,9 +55,9 @@
           "type": "string"
         },
         "provider": {
-          "description": "The provider label (lowercase with no white space) for the entity that contributed this data\n(e.g., osm, meta, esri).",
+          "description": "The provider label for the entity that contributed this data\n(e.g., osm, meta, esri).",
           "minLength": 1,
-          "pattern": "^[a-z0-9][a-z0-9._-]*$",
+          "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
           "title": "Provider",
           "type": "string"
         },
@@ -67,9 +67,9 @@
           "type": "string"
         },
         "resource": {
-          "description": "The subject or type of data contributed by the provider (lowercase with no white space)\n(e.g., planet, buildings, division-names).",
+          "description": "The subject or type of data contributed by the provider\n(e.g., planet, buildings, division_names).",
           "minLength": 1,
-          "pattern": "^[a-z0-9][a-z0-9._-]*$",
+          "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
           "title": "Resource",
           "type": "string"
         },
diff --git a/packages/overture-schema-base-theme/tests/bathymetry_baseline_schema.json b/packages/overture-schema-base-theme/tests/bathymetry_baseline_schema.json
@@ -76,9 +76,9 @@
           "type": "string"
         },
         "provider": {
-          "description": "The provider label (lowercase with no white space) for the entity that contributed this data\n(e.g., osm, meta, esri).",
+          "description": "The provider label for the entity that contributed this data\n(e.g., osm, meta, esri).",
           "minLength": 1,
-          "pattern": "^[a-z0-9][a-z0-9._-]*$",
+          "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
           "title": "Provider",
           "type": "string"
         },
@@ -88,9 +88,9 @@
           "type": "string"
         },
         "resource": {
-          "description": "The subject or type of data contributed by the provider (lowercase with no white space)\n(e.g., planet, buildings, division-names).",
+          "description": "The subject or type of data contributed by the provider\n(e.g., planet, buildings, division_names).",
           "minLength": 1,
-          "pattern": "^[a-z0-9][a-z0-9._-]*$",
+          "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
           "title": "Resource",
           "type": "string"
         },
diff --git a/packages/overture-schema-base-theme/tests/infrastructure_baseline_schema.json b/packages/overture-schema-base-theme/tests/infrastructure_baseline_schema.json
@@ -385,9 +385,9 @@
           "type": "string"
         },
         "provider": {
-          "description": "The provider label (lowercase with no white space) for the entity that contributed this data\n(e.g., osm, meta, esri).",
+          "description": "The provider label for the entity that contributed this data\n(e.g., osm, meta, esri).",
           "minLength": 1,
-          "pattern": "^[a-z0-9][a-z0-9._-]*$",
+          "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
           "title": "Provider",
           "type": "string"
         },
@@ -397,9 +397,9 @@
           "type": "string"
         },
         "resource": {
-          "description": "The subject or type of data contributed by the provider (lowercase with no white space)\n(e.g., planet, buildings, division-names).",
+          "description": "The subject or type of data contributed by the provider\n(e.g., planet, buildings, division_names).",
           "minLength": 1,
-          "pattern": "^[a-z0-9][a-z0-9._-]*$",
+          "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
           "title": "Resource",
           "type": "string"
         },
diff --git a/packages/overture-schema-base-theme/tests/land_baseline_schema.json b/packages/overture-schema-base-theme/tests/land_baseline_schema.json
@@ -258,9 +258,9 @@
           "type": "string"
         },
         "provider": {
-          "description": "The provider label (lowercase with no white space) for the entity that contributed this data\n(e.g., osm, meta, esri).",
+          "description": "The provider label for the entity that contributed this data\n(e.g., osm, meta, esri).",
           "minLength": 1,
-          "pattern": "^[a-z0-9][a-z0-9._-]*$",
+          "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
           "title": "Provider",
           "type": "string"
         },
@@ -270,9 +270,9 @@
           "type": "string"
         },
         "resource": {
-          "description": "The subject or type of data contributed by the provider (lowercase with no white space)\n(e.g., planet, buildings, division-names).",
+          "description": "The subject or type of data contributed by the provider\n(e.g., planet, buildings, division_names).",
           "minLength": 1,
-          "pattern": "^[a-z0-9][a-z0-9._-]*$",
+          "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
           "title": "Resource",
           "type": "string"
         },
diff --git a/packages/overture-schema-base-theme/tests/land_cover_baseline_schema.json b/packages/overture-schema-base-theme/tests/land_cover_baseline_schema.json
@@ -93,9 +93,9 @@
           "type": "string"
         },
         "provider": {
-          "description": "The provider label (lowercase with no white space) for the entity that contributed this data\n(e.g., osm, meta, esri).",
+          "description": "The provider label for the entity that contributed this data\n(e.g., osm, meta, esri).",
           "minLength": 1,
-          "pattern": "^[a-z0-9][a-z0-9._-]*$",
+          "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
           "title": "Provider",
           "type": "string"
         },
@@ -105,9 +105,9 @@
           "type": "string"
         },
         "resource": {
-          "description": "The subject or type of data contributed by the provider (lowercase with no white space)\n(e.g., planet, buildings, division-names).",
+          "description": "The subject or type of data contributed by the provider\n(e.g., planet, buildings, division_names).",
           "minLength": 1,
-          "pattern": "^[a-z0-9][a-z0-9._-]*$",
+          "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
           "title": "Resource",
           "type": "string"
         },
diff --git a/packages/overture-schema-base-theme/tests/land_use_baseline_schema.json b/packages/overture-schema-base-theme/tests/land_use_baseline_schema.json
@@ -336,9 +336,9 @@
           "type": "string"
         },
         "provider": {
-          "description": "The provider label (lowercase with no white space) for the entity that contributed this data\n(e.g., osm, meta, esri).",
+          "description": "The provider label for the entity that contributed this data\n(e.g., osm, meta, esri).",
           "minLength": 1,
-          "pattern": "^[a-z0-9][a-z0-9._-]*$",
+          "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
           "title": "Provider",
           "type": "string"
         },
@@ -348,9 +348,9 @@
           "type": "string"
         },
         "resource": {
-          "description": "The subject or type of data contributed by the provider (lowercase with no white space)\n(e.g., planet, buildings, division-names).",
+          "description": "The subject or type of data contributed by the provider\n(e.g., planet, buildings, division_names).",
           "minLength": 1,
-          "pattern": "^[a-z0-9][a-z0-9._-]*$",
+          "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
           "title": "Resource",
           "type": "string"
         },
diff --git a/packages/overture-schema-base-theme/tests/water_baseline_schema.json b/packages/overture-schema-base-theme/tests/water_baseline_schema.json
@@ -189,9 +189,9 @@
           "type": "string"
         },
         "provider": {
-          "description": "The provider label (lowercase with no white space) for the entity that contributed this data\n(e.g., osm, meta, esri).",
+          "description": "The provider label for the entity that contributed this data\n(e.g., osm, meta, esri).",
           "minLength": 1,
-          "pattern": "^[a-z0-9][a-z0-9._-]*$",
+          "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
           "title": "Provider",
           "type": "string"
         },
@@ -201,9 +201,9 @@
           "type": "string"
         },
         "resource": {
-          "description": "The subject or type of data contributed by the provider (lowercase with no white space)\n(e.g., planet, buildings, division-names).",
+          "description": "The subject or type of data contributed by the provider\n(e.g., planet, buildings, division_names).",
           "minLength": 1,
-          "pattern": "^[a-z0-9][a-z0-9._-]*$",
+          "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
           "title": "Resource",
           "type": "string"
         },
diff --git a/packages/overture-schema-buildings-theme/tests/building_baseline_schema.json b/packages/overture-schema-buildings-theme/tests/building_baseline_schema.json
@@ -372,9 +372,9 @@
           "type": "string"
         },
         "provider": {
-          "description": "The provider label (lowercase with no white space) for the entity that contributed this data\n(e.g., osm, meta, esri).",
+          "description": "The provider label for the entity that contributed this data\n(e.g., osm, meta, esri).",
           "minLength": 1,
-          "pattern": "^[a-z0-9][a-z0-9._-]*$",
+          "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
           "title": "Provider",
           "type": "string"
         },
@@ -384,9 +384,9 @@
           "type": "string"
         },
         "resource": {
-          "description": "The subject or type of data contributed by the provider (lowercase with no white space)\n(e.g., planet, buildings, division-names).",
+          "description": "The subject or type of data contributed by the provider\n(e.g., planet, buildings, division_names).",
           "minLength": 1,
-          "pattern": "^[a-z0-9][a-z0-9._-]*$",
+          "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
           "title": "Resource",
           "type": "string"
         },
diff --git a/packages/overture-schema-buildings-theme/tests/building_part_baseline_schema.json b/packages/overture-schema-buildings-theme/tests/building_part_baseline_schema.json
@@ -258,9 +258,9 @@
           "type": "string"
         },
         "provider": {
-          "description": "The provider label (lowercase with no white space) for the entity that contributed this data\n(e.g., osm, meta, esri).",
+          "description": "The provider label for the entity that contributed this data\n(e.g., osm, meta, esri).",
           "minLength": 1,
-          "pattern": "^[a-z0-9][a-z0-9._-]*$",
+          "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
           "title": "Provider",
           "type": "string"
         },
@@ -270,9 +270,9 @@
           "type": "string"
         },
         "resource": {
-          "description": "The subject or type of data contributed by the provider (lowercase with no white space)\n(e.g., planet, buildings, division-names).",
+          "description": "The subject or type of data contributed by the provider\n(e.g., planet, buildings, division_names).",
           "minLength": 1,
-          "pattern": "^[a-z0-9][a-z0-9._-]*$",
+          "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
           "title": "Resource",
           "type": "string"
         },
diff --git a/packages/overture-schema-common/src/overture/schema/common/sources.py b/packages/overture-schema-common/src/overture/schema/common/sources.py
@@ -12,7 +12,12 @@
 from overture.schema.common.types import ConfidenceScore
 from overture.schema.system.field_constraint import UniqueItemsConstraint
 from overture.schema.system.model_constraint import no_extra_fields
-from overture.schema.system.string import JsonPointer, StrippedString
+from overture.schema.system.string import (
+    JsonPointer,
+    NoWhitespaceString,
+    SnakeCaseString,
+    StrippedString,
+)
 
 
 @no_extra_fields
@@ -87,32 +92,29 @@ class SourceItem(BaseModel):
         ),
     ] = None
     provider: Annotated[
-        str | None,
+        SnakeCaseString | None,
         Field(
             min_length=1,
-            pattern=r"^[a-z0-9][a-z0-9._-]*$",
             description=textwrap.dedent("""
-                The provider label (lowercase with no white space) for the entity that contributed this data
+                The provider label for the entity that contributed this data
                 (e.g., osm, meta, esri).
             """).strip(),
         ),
     ] = None
     resource: Annotated[
-        str | None,
+        SnakeCaseString | None,
         Field(
             min_length=1,
-            pattern=r"^[a-z0-9][a-z0-9._-]*$",
             description=textwrap.dedent("""
-                The subject or type of data contributed by the provider (lowercase with no white space)
-                (e.g., planet, buildings, division-names).
+                The subject or type of data contributed by the provider
+                (e.g., planet, buildings, division_names).
             """).strip(),
         ),
     ] = None
     version: Annotated[
-        str | None,
+        NoWhitespaceString | None,
         Field(
             min_length=1,
-            pattern=r"^\S+$",
             description=textwrap.dedent("""
                 A sortable identifier for the specific snapshot of the resource
                 (e.g., 2026-02-13, 5.3, A5692).
diff --git a/packages/overture-schema-common/tests/test_models.py b/packages/overture-schema-common/tests/test_models.py
@@ -61,12 +61,12 @@ def test_feature_json_schema() -> None:
                     "dataset": {"type": "string"},
                     "provider": {
                         "minLength": 1,
-                        "pattern": "^[a-z0-9][a-z0-9._-]*$",
+                        "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
                         "type": "string",
                     },
                     "resource": {
                         "minLength": 1,
-                        "pattern": "^[a-z0-9][a-z0-9._-]*$",
+                        "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
                         "type": "string",
                     },
                     "version": {
diff --git a/packages/overture-schema-divisions-theme/tests/division_area_baseline_schema.json b/packages/overture-schema-divisions-theme/tests/division_area_baseline_schema.json
@@ -217,9 +217,9 @@
           "type": "string"
         },
         "provider": {
-          "description": "The provider label (lowercase with no white space) for the entity that contributed this data\n(e.g., osm, meta, esri).",
+          "description": "The provider label for the entity that contributed this data\n(e.g., osm, meta, esri).",
           "minLength": 1,
-          "pattern": "^[a-z0-9][a-z0-9._-]*$",
+          "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
           "title": "Provider",
           "type": "string"
         },
@@ -229,9 +229,9 @@
           "type": "string"
         },
         "resource": {
-          "description": "The subject or type of data contributed by the provider (lowercase with no white space)\n(e.g., planet, buildings, division-names).",
+          "description": "The subject or type of data contributed by the provider\n(e.g., planet, buildings, division_names).",
           "minLength": 1,
-          "pattern": "^[a-z0-9][a-z0-9._-]*$",
+          "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
           "title": "Resource",
           "type": "string"
         },
diff --git a/packages/overture-schema-divisions-theme/tests/division_baseline_schema.json b/packages/overture-schema-divisions-theme/tests/division_baseline_schema.json
@@ -320,9 +320,9 @@
           "type": "string"
         },
         "provider": {
-          "description": "The provider label (lowercase with no white space) for the entity that contributed this data\n(e.g., osm, meta, esri).",
+          "description": "The provider label for the entity that contributed this data\n(e.g., osm, meta, esri).",
           "minLength": 1,
-          "pattern": "^[a-z0-9][a-z0-9._-]*$",
+          "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
           "title": "Provider",
           "type": "string"
         },
@@ -332,9 +332,9 @@
           "type": "string"
         },
         "resource": {
-          "description": "The subject or type of data contributed by the provider (lowercase with no white space)\n(e.g., planet, buildings, division-names).",
+          "description": "The subject or type of data contributed by the provider\n(e.g., planet, buildings, division_names).",
           "minLength": 1,
-          "pattern": "^[a-z0-9][a-z0-9._-]*$",
+          "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
           "title": "Resource",
           "type": "string"
         },
diff --git a/packages/overture-schema-divisions-theme/tests/division_boundary_baseline_schema.json b/packages/overture-schema-divisions-theme/tests/division_boundary_baseline_schema.json
@@ -107,9 +107,9 @@
           "type": "string"
         },
         "provider": {
-          "description": "The provider label (lowercase with no white space) for the entity that contributed this data\n(e.g., osm, meta, esri).",
+          "description": "The provider label for the entity that contributed this data\n(e.g., osm, meta, esri).",
           "minLength": 1,
-          "pattern": "^[a-z0-9][a-z0-9._-]*$",
+          "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
           "title": "Provider",
           "type": "string"
         },
@@ -119,9 +119,9 @@
           "type": "string"
         },
         "resource": {
-          "description": "The subject or type of data contributed by the provider (lowercase with no white space)\n(e.g., planet, buildings, division-names).",
+          "description": "The subject or type of data contributed by the provider\n(e.g., planet, buildings, division_names).",
           "minLength": 1,
-          "pattern": "^[a-z0-9][a-z0-9._-]*$",
+          "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
           "title": "Resource",
           "type": "string"
         },
diff --git a/packages/overture-schema-places-theme/tests/place_baseline_schema.json b/packages/overture-schema-places-theme/tests/place_baseline_schema.json
@@ -284,9 +284,9 @@
           "type": "string"
         },
         "provider": {
-          "description": "The provider label (lowercase with no white space) for the entity that contributed this data\n(e.g., osm, meta, esri).",
+          "description": "The provider label for the entity that contributed this data\n(e.g., osm, meta, esri).",
           "minLength": 1,
-          "pattern": "^[a-z0-9][a-z0-9._-]*$",
+          "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
           "title": "Provider",
           "type": "string"
         },
@@ -296,9 +296,9 @@
           "type": "string"
         },
         "resource": {
-          "description": "The subject or type of data contributed by the provider (lowercase with no white space)\n(e.g., planet, buildings, division-names).",
+          "description": "The subject or type of data contributed by the provider\n(e.g., planet, buildings, division_names).",
           "minLength": 1,
-          "pattern": "^[a-z0-9][a-z0-9._-]*$",
+          "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$",
           "title": "Resource",
           "type": "string"
         },
diff --git a/packages/overture-schema-transportation-theme/tests/connector_baseline_schema.json b/packages/overture-schema-transportation-theme/tests/connector_baseline_schema.json
diff --git a/packages/overture-schema-transportation-theme/tests/segment_baseline_schema.json b/packages/overture-schema-transportation-theme/tests/segment_baseline_schema.json
