structurize 3.5.0__tar.gz → 3.5.2__tar.gz

{structurize-3.5.0/structurize.egg-info → structurize-3.5.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: structurize
-Version: 3.5.0
+Version: 3.5.2
 Summary: Tools to convert from and to JSON Structure from various other schema languages.
 Author-email: Clemens Vasters <clemensv@microsoft.com>
 Classifier: Programming Language :: Python :: 3
@@ -36,7 +36,7 @@ Requires-Dist: pydantic>=2.8.2; extra == "dev"
 Requires-Dist: avro>=1.12.0; extra == "dev"
 Requires-Dist: testcontainers>=4.7.2; extra == "dev"
 Requires-Dist: pymysql>=1.1.1; extra == "dev"
-Requires-Dist: psycopg2>=2.9.9; extra == "dev"
+Requires-Dist: psycopg2-binary>=2.9.9; extra == "dev"
 Requires-Dist: pyodbc>=5.1.0; extra == "dev"
 Requires-Dist: pymongo>=4.8.0; extra == "dev"
 Requires-Dist: oracledb>=2.3.0; extra == "dev"

structurize-3.5.2/avrotize/_version.py

@@ -0,0 +1,24 @@
+# file generated by vcs-versioning
+# don't change, don't track in version control
+from __future__ import annotations
+
+__all__ = [
+    "__version__",
+    "__version_tuple__",
+    "version",
+    "version_tuple",
+    "__commit_id__",
+    "commit_id",
+]
+
+version: str
+__version__: str
+__version_tuple__: tuple[int | str, ...]
+version_tuple: tuple[int | str, ...]
+commit_id: str | None
+__commit_id__: str | None
+
+__version__ = version = '3.5.2'
+__version_tuple__ = version_tuple = (3, 5, 2)
+
+__commit_id__ = commit_id = 'gff224504a'

{structurize-3.5.0 → structurize-3.5.2}/avrotize/cddltostructure.py

@@ -165,6 +165,17 @@ class CddlToStructureConverter:
         # Counter for auto-generated type names
         self._auto_name_counter: int = 0
 
+    @staticmethod
+    def _wrap_ref(schema: Dict[str, Any]) -> Dict[str, Any]:
+        """Wrap a bare $ref in a type object per JSON Structure spec Section 3.4.1.
+
+        Bare {"$ref": "..."} is only valid inside a type attribute (e.g. union arrays).
+        In all other positions (items, properties, values), it must be {"type": {"$ref": "..."}}.
+        """
+        if '$ref' in schema and 'type' not in schema:
+            return {'type': {'$ref': schema['$ref']}}
+        return schema
+
     def _create_inline_definition(
         self, type_def: Dict[str, Any], base_name: str
     ) -> Dict[str, Any]:
@@ -900,6 +911,7 @@ class CddlToStructureConverter:
                 keys_type = {'type': 'string'}
 
             values_type = member_type if member_type else {'type': 'any'}
+            values_type = self._wrap_ref(values_type)
 
             return {
                 'keys': keys_type,
@@ -915,6 +927,7 @@ class CddlToStructureConverter:
             prop_schema = member_type.copy() if isinstance(member_type, dict) else member_type
         else:
             prop_schema = {'type': 'any'}
+        prop_schema = self._wrap_ref(prop_schema)
 
         # Handle occurrence indicators
         if occurrence_indicator:
@@ -1073,7 +1086,7 @@ class CddlToStructureConverter:
             tuple_order: List[str] = []
             for idx, item_type in enumerate(items_types):
                 prop_name = f"_{idx}"
-                properties[prop_name] = item_type
+                properties[prop_name] = self._wrap_ref(item_type)
                 tuple_order.append(prop_name)
             return {
                 'type': 'tuple',
@@ -1086,6 +1099,7 @@ class CddlToStructureConverter:
                 items_type = items_types[0]
                 # Extract inline compound types to definitions
                 items_type = self._create_inline_definition(items_type, f"{context_name}_item")
+                items_type = self._wrap_ref(items_type)
             else:
                 # Multiple types that aren't a tuple - use union for items
                 # Extract each inline compound type to definitions
@@ -1528,6 +1542,9 @@ class CddlToStructureConverter:
             else:
                 base_type = {'type': 'any'}
 
+        # Wrap bare $ref so constraints can be added alongside
+        base_type = self._wrap_ref(base_type)
+
         # Extract controller (constraint argument)
         if hasattr(operator_node, 'controller'):
             controller_value = self._extract_controller_value(operator_node.controller)

{structurize-3.5.0 → structurize-3.5.2}/avrotize/choice_inference.py

@@ -214,17 +214,17 @@ def _detect_discriminators(
         if len(values) < 2:
             continue
         
-        # Discriminators must be identifier-like strings (type names, enum values)
-        # Valid: "PlayerTracking", "ball_data", "goal-event", "Event.Type"
-        # Invalid: "1", "2024/2025", "true", "2024-01-15T10:30:00Z", UUIDs
+        # Discriminators must be identifier-like strings (type names, enum values, codes)
+        # Valid: "PlayerTracking", "ball_data", "goal-event", "1", "用户", "true"
+        # Invalid: "2024/2025", "2024-01-15T10:30:00Z", UUIDs
         import re
         def is_valid_discriminator(s: str) -> bool:
-            """Check if a string looks like a type name or identifier."""
+            """Check if a string looks like a type name, identifier, or short code."""
             if not s or not isinstance(s, str):
                 return False
-            # Must start with a letter, contain only alphanumeric, underscore, hyphen, dot
-            # This matches typical identifiers: PascalCase, camelCase, snake_case, kebab-case
-            return bool(re.match(r'^[A-Za-z][A-Za-z0-9_\-\.]*$', s))
+            # Accept word characters (Unicode letters, digits, underscore), hyphens, dots
+            # Reject slashes, colons, and other URI/date characters
+            return bool(re.match(r'^[\w][\w\-\.]*$', s, re.UNICODE))
         
         if not all(is_valid_discriminator(v) for v in values):
             continue

{structurize-3.5.0 → structurize-3.5.2}/avrotize/schema_inference.py

@@ -1236,11 +1236,14 @@ class JsonStructureSchemaInferrer(SchemaInferrer):
         
         # For inline unions with selector, we need $extends pointing to a base type
         # Compute common fields across all variants to create a proper base type
+        disc_safe = avro_name(result.discriminator_field)
         all_variant_props = [c.get("properties", {}) for c in choices_map.values()]
         if all_variant_props:
             common_prop_names = set(all_variant_props[0].keys())
             for props in all_variant_props[1:]:
                 common_prop_names &= set(props.keys())
+            # Exclude discriminator from common props - each variant has a different default
+            common_prop_names.discard(disc_safe)
             
             # Build base type with common properties
             base_name = avro_name(f"{type_name.rsplit('.', 1)[-1]}Base")
@@ -1277,7 +1280,6 @@ class JsonStructureSchemaInferrer(SchemaInferrer):
                 definitions[variant_name] = variant_record
                 new_choices_map[variant_name] = {"type": {"$ref": f"#/definitions/{variant_name}"}}
             
-            disc_safe = avro_name(result.discriminator_field)
             return {
                 "type": "choice",
                 "name": avro_name(type_name.rsplit('.', 1)[-1]),
@@ -1477,7 +1479,8 @@ class JsonStructureSchemaInferrer(SchemaInferrer):
             if all_items:
                 item_types = self.consolidated_jstruct_type_list(type_name, all_items)
                 if len(item_types) == 1:
-                    return [{"type": "array", "items": item_types[0]}]
+                    items_schema = item_types[0] if isinstance(item_types[0], dict) else {"type": item_types[0]}
+                    return [{"type": "array", "items": items_schema}]
                 else:
                     # Build choice from multiple item types
                     choices_map: Dict[str, Any] = {}
@@ -1539,7 +1542,8 @@ class JsonStructureSchemaInferrer(SchemaInferrer):
                 item_types.append(item2)
         if item_types:
             if len(item_types) == 1:
-                list_types.append({"type": "array", "items": item_types[0]})
+                items_schema = item_types[0] if isinstance(item_types[0], dict) else {"type": item_types[0]}
+                list_types.append({"type": "array", "items": items_schema})
             else:
                 # Build choices map from item types
                 choices_map: Dict[str, Any] = {}
@@ -1563,7 +1567,8 @@ class JsonStructureSchemaInferrer(SchemaInferrer):
                 value_types.append(item3)
         if value_types:
             if len(value_types) == 1:
-                list_types.append({"type": "map", "values": value_types[0]})
+                values_schema = value_types[0] if isinstance(value_types[0], dict) else {"type": value_types[0]}
+                list_types.append({"type": "map", "values": values_schema})
             else:
                 list_types.append({"type": "map", "values": {"type": "choice", "choices": value_types}})
 

{structurize-3.5.0 → structurize-3.5.2}/avrotize/structuretojava.py

@@ -4,7 +4,7 @@
 import json
 import os
 from typing import Dict, List, Tuple, Union, Set, Optional, Any
-from avrotize.constants import JACKSON_VERSION
+from avrotize.constants import JACKSON_VERSION, JACKSON_ANNOTATIONS_VERSION
 
 from avrotize.common import pascal, camel, process_template
 
@@ -878,7 +878,8 @@ class StructureToJava:
                 "structuretojava/pom.xml.jinja",
                 groupid=groupid,
                 artifactid=artifactid,
-                jackson_version=JACKSON_VERSION
+                jackson_version=JACKSON_VERSION,
+                jackson_annotations_version=JACKSON_ANNOTATIONS_VERSION
             )
             with open(pom_path, 'w', encoding='utf-8') as file:
                 file.write(pom_content)

{structurize-3.5.0 → structurize-3.5.2}/avrotize/structuretokusto.py

@@ -120,6 +120,21 @@ class StructureToKusto:
         """Check if a type is concrete (not abstract)."""
         return not schema.get('abstract', False)
 
+    def normalize_structure_type(self, structure_type: Union[str, dict, list]) -> Union[str, dict, list]:
+        """Normalize wrapped type expressions into the shapes the converter expects."""
+        if isinstance(structure_type, list):
+            non_null_types = [t for t in structure_type if t != 'null']
+            if len(non_null_types) == 1:
+                return self.normalize_structure_type(non_null_types[0])
+            return structure_type
+
+        if isinstance(structure_type, dict) and 'type' in structure_type and '$ref' not in structure_type:
+            nested_type = structure_type['type']
+            if isinstance(nested_type, (dict, list)):
+                return self.normalize_structure_type(nested_type)
+
+        return structure_type
+
     def find_all_object_types(self, schema: Dict, schema_doc: Dict) -> List[Dict]:
         """
         Find all concrete object types in the schema, including those in definitions.
@@ -516,6 +531,7 @@ class StructureToKusto:
 
     def convert_structure_type_to_kusto_type(self, structure_type: Union[str, dict, list], schema_doc: Optional[Dict] = None) -> str:
         """Converts a JSON Structure type to a Kusto type."""
+        structure_type = self.normalize_structure_type(structure_type)
         if isinstance(structure_type, list):
             # Handle type unions
             non_null_types = [t for t in structure_type if t != 'null']

{structurize-3.5.0 → structurize-3.5.2}/pyproject.toml

@@ -46,7 +46,7 @@ dev = [
     "avro>=1.12.0",
     "testcontainers>=4.7.2",
     "pymysql>=1.1.1",
-    "psycopg2>=2.9.9",
+    "psycopg2-binary>=2.9.9",
     "pyodbc>=5.1.0",
     "pymongo>=4.8.0",
     "oracledb>=2.3.0",

{structurize-3.5.0 → structurize-3.5.2/structurize.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: structurize
-Version: 3.5.0
+Version: 3.5.2
 Summary: Tools to convert from and to JSON Structure from various other schema languages.
 Author-email: Clemens Vasters <clemensv@microsoft.com>
 Classifier: Programming Language :: Python :: 3
@@ -36,7 +36,7 @@ Requires-Dist: pydantic>=2.8.2; extra == "dev"
 Requires-Dist: avro>=1.12.0; extra == "dev"
 Requires-Dist: testcontainers>=4.7.2; extra == "dev"
 Requires-Dist: pymysql>=1.1.1; extra == "dev"
-Requires-Dist: psycopg2>=2.9.9; extra == "dev"
+Requires-Dist: psycopg2-binary>=2.9.9; extra == "dev"
 Requires-Dist: pyodbc>=5.1.0; extra == "dev"
 Requires-Dist: pymongo>=4.8.0; extra == "dev"
 Requires-Dist: oracledb>=2.3.0; extra == "dev"

{structurize-3.5.0 → structurize-3.5.2}/structurize.egg-info/requires.txt

@@ -26,7 +26,7 @@ pydantic>=2.8.2
 avro>=1.12.0
 testcontainers>=4.7.2
 pymysql>=1.1.1
-psycopg2>=2.9.9
+psycopg2-binary>=2.9.9
 pyodbc>=5.1.0
 pymongo>=4.8.0
 oracledb>=2.3.0

structurize-3.5.0/avrotize/_version.py

@@ -1,34 +0,0 @@
-# file generated by setuptools-scm
-# don't change, don't track in version control
-
-__all__ = [
-    "__version__",
-    "__version_tuple__",
-    "version",
-    "version_tuple",
-    "__commit_id__",
-    "commit_id",
-]
-
-TYPE_CHECKING = False
-if TYPE_CHECKING:
-    from typing import Tuple
-    from typing import Union
-
-    VERSION_TUPLE = Tuple[Union[int, str], ...]
-    COMMIT_ID = Union[str, None]
-else:
-    VERSION_TUPLE = object
-    COMMIT_ID = object
-
-version: str
-__version__: str
-__version_tuple__: VERSION_TUPLE
-version_tuple: VERSION_TUPLE
-commit_id: COMMIT_ID
-__commit_id__: COMMIT_ID
-
-__version__ = version = '3.5.0'
-__version_tuple__ = version_tuple = (3, 5, 0)
-
-__commit_id__ = commit_id = 'g95f637e11'