datacontract-cli 0.11.2__tar.gz → 0.11.3__tar.gz

{datacontract_cli-0.11.2/datacontract_cli.egg-info → datacontract_cli-0.11.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datacontract-cli
-Version: 0.11.2
+Version: 0.11.3
 Summary: The datacontract CLI is an open source command-line tool for working with Data Contracts. It uses data contract YAML files to lint the data contract, connect to data sources and execute schema and quality tests, detect breaking changes, and export to different formats. The tool is written in Python. It can be used as a standalone CLI tool, in a CI/CD pipeline, or directly as a Python library.
 Author-email: Jochen Christ <jochen.christ@innoq.com>, Stefan Negele <stefan.negele@innoq.com>, Simon Harrer <simon.harrer@innoq.com>
 License-Expression: MIT
@@ -16,7 +16,7 @@ Requires-Dist: pydantic<2.13.0,>=2.8.2
 Requires-Dist: pyyaml~=6.0.1
 Requires-Dist: requests<2.33,>=2.31
 Requires-Dist: fastjsonschema<2.22.0,>=2.19.1
-Requires-Dist: fastparquet<2025.0.0,>=2024.5.0
+Requires-Dist: fastparquet<2026.0.0,>=2024.5.0
 Requires-Dist: numpy<2.0.0,>=1.26.4
 Requires-Dist: python-multipart<1.0.0,>=0.0.20
 Requires-Dist: rich<15.0,>=13.7
@@ -29,7 +29,7 @@ Requires-Dist: boto3<2.0.0,>=1.34.41
 Requires-Dist: Jinja2<4.0.0,>=3.1.5
 Requires-Dist: jinja_partials<1.0.0,>=0.2.1
 Requires-Dist: datacontract-specification<2.0.0,>=1.2.3
-Requires-Dist: open-data-contract-standard<4.0.0,>=3.1.0
+Requires-Dist: open-data-contract-standard<4.0.0,>=3.1.2
 Provides-Extra: avro
 Requires-Dist: avro==1.12.1; extra == "avro"
 Provides-Extra: bigquery
@@ -43,18 +43,18 @@ Requires-Dist: soda-core-spark-df<3.6.0,>=3.3.20; extra == "databricks"
 Requires-Dist: soda-core-spark[databricks]<3.6.0,>=3.3.20; extra == "databricks"
 Requires-Dist: databricks-sql-connector<4.3.0,>=3.7.0; extra == "databricks"
 Requires-Dist: databricks-sdk<0.74.0; extra == "databricks"
-Requires-Dist: pyspark<4.0.0,>=3.5.5; extra == "databricks"
+Requires-Dist: pyspark<5.0.0,>=3.5.5; extra == "databricks"
 Provides-Extra: iceberg
 Requires-Dist: pyiceberg==0.10.0; extra == "iceberg"
 Provides-Extra: kafka
 Requires-Dist: datacontract-cli[avro]; extra == "kafka"
 Requires-Dist: soda-core-spark-df<3.6.0,>=3.3.20; extra == "kafka"
-Requires-Dist: pyspark<4.0.0,>=3.5.5; extra == "kafka"
+Requires-Dist: pyspark<5.0.0,>=3.5.5; extra == "kafka"
 Provides-Extra: postgres
 Requires-Dist: soda-core-postgres<3.6.0,>=3.3.20; extra == "postgres"
 Provides-Extra: s3
 Requires-Dist: s3fs<2026.0.0,>=2025.2.0; extra == "s3"
-Requires-Dist: aiobotocore<2.26.0,>=2.17.0; extra == "s3"
+Requires-Dist: aiobotocore<3.2.0,>=2.17.0; extra == "s3"
 Provides-Extra: snowflake
 Requires-Dist: snowflake-connector-python[pandas]<4.2,>=3.6; extra == "snowflake"
 Requires-Dist: soda-core-snowflake<3.6.0,>=3.3.20; extra == "snowflake"
@@ -73,10 +73,10 @@ Requires-Dist: pydbml>=1.1.1; extra == "dbml"
 Provides-Extra: parquet
 Requires-Dist: pyarrow>=18.1.0; extra == "parquet"
 Provides-Extra: rdf
-Requires-Dist: rdflib==7.0.0; extra == "rdf"
+Requires-Dist: rdflib==7.5.0; extra == "rdf"
 Provides-Extra: api
 Requires-Dist: fastapi==0.121.2; extra == "api"
-Requires-Dist: uvicorn==0.38.0; extra == "api"
+Requires-Dist: uvicorn==0.40.0; extra == "api"
 Provides-Extra: protobuf
 Requires-Dist: grpcio-tools>=1.53; extra == "protobuf"
 Provides-Extra: all
@@ -657,8 +657,7 @@ datacontract.yaml
 servers:
   production:
     type: azure
-    storageAccount: datameshdatabricksdemo
-    location: abfss://dataproducts/inventory_events/*.parquet
+    location: abfss://datameshdatabricksdemo.dfs.core.windows.net/inventory_events/*.parquet
     format: parquet
 ```
 

{datacontract_cli-0.11.2 → datacontract_cli-0.11.3}/README.md

@@ -558,8 +558,7 @@ datacontract.yaml
 servers:
   production:
     type: azure
-    storageAccount: datameshdatabricksdemo
-    location: abfss://dataproducts/inventory_events/*.parquet
+    location: abfss://datameshdatabricksdemo.dfs.core.windows.net/inventory_events/*.parquet
     format: parquet
 ```
 

{datacontract_cli-0.11.2 → datacontract_cli-0.11.3}/datacontract/catalog/catalog.py

@@ -14,7 +14,7 @@ from datacontract.export.html_exporter import get_version
 
 def _get_owner(odcs: OpenDataContractStandard) -> Optional[str]:
     """Get the owner from ODCS customProperties or team."""
-    if odcs.team and odcs.team.name:
+    if odcs.team and hasattr(odcs.team, "name") and odcs.team.name:
         return odcs.team.name
     if odcs.customProperties:
         for prop in odcs.customProperties:

{datacontract_cli-0.11.2 → datacontract_cli-0.11.3}/datacontract/cli.py

@@ -67,7 +67,7 @@ def common(
     pass
 
 
-@app.command()
+@app.command(name="init")
 def init(
     location: Annotated[
         str, typer.Argument(help="The location of the data contract file to create.")
@@ -90,7 +90,7 @@ def init(
     console.print("📄 data contract written to " + location)
 
 
-@app.command()
+@app.command(name="lint")
 def lint(
     location: Annotated[
         str,
@@ -125,7 +125,7 @@ def enable_debug_logging(debug: bool):
         )
 
 
-@app.command()
+@app.command(name="test")
 def test(
     location: Annotated[
         str,
@@ -187,7 +187,7 @@ def test(
     write_test_result(run, console, output_format, output, data_contract)
 
 
-@app.command()
+@app.command(name="export")
 def export(
     format: Annotated[ExportFormat, typer.Option(help="The export format.")],
     output: Annotated[
@@ -467,7 +467,7 @@ def _get_uvicorn_arguments(port: int, host: str, context: typer.Context) -> dict
     return default_args | dict(zip(trimmed_keys, context.args[1::2]))
 
 
-@app.command(context_settings={"allow_extra_args": True, "ignore_unknown_options": True})
+@app.command(name="api", context_settings={"allow_extra_args": True, "ignore_unknown_options": True})
 def api(
     ctx: Annotated[typer.Context, typer.Option(help="Extra arguments to pass to uvicorn.run().")],
     port: Annotated[int, typer.Option(help="Bind socket to this port.")] = 4242,

{datacontract_cli-0.11.2 → datacontract_cli-0.11.3}/datacontract/engines/data_contract_checks.py

@@ -161,7 +161,7 @@ def to_schema_name(schema_object: SchemaObject, server_type: str) -> str:
     # Use physicalName if set (ODCS standard way to specify actual table name)
     if schema_object.physicalName:
         return schema_object.physicalName
-    
+
     return schema_object.name
 
 

{datacontract_cli-0.11.2 → datacontract_cli-0.11.3}/datacontract/engines/soda/connections/duckdb_connection.py

@@ -1,10 +1,12 @@
 import os
+import re
 from typing import Any, List, Optional
 
 import duckdb
 from open_data_contract_standard.model import OpenDataContractStandard, SchemaObject, SchemaProperty, Server
 
 from datacontract.export.duckdb_type_converter import convert_to_duckdb_csv_type, convert_to_duckdb_json_type
+from datacontract.export.sql_type_converter import convert_to_duckdb
 from datacontract.model.run import Run
 
 
@@ -57,20 +59,9 @@ def get_duckdb_connection(
                     )
                     add_nested_views(con, model_name, schema_obj.properties)
             elif server.format == "parquet":
-                con.sql(f"""
-                            CREATE VIEW "{model_name}" AS SELECT * FROM read_parquet('{model_path}', hive_partitioning=1);
-                            """)
+                create_view_with_schema_union(con, schema_obj, model_path, "read_parquet", to_parquet_types)
             elif server.format == "csv":
-                columns = to_csv_types(schema_obj)
-                run.log_info("Using columns: " + str(columns))
-                if columns is None:
-                    con.sql(
-                        f"""CREATE VIEW "{model_name}" AS SELECT * FROM read_csv('{model_path}', hive_partitioning=1);"""
-                    )
-                else:
-                    con.sql(
-                        f"""CREATE VIEW "{model_name}" AS SELECT * FROM read_csv('{model_path}', hive_partitioning=1, columns={columns});"""
-                    )
+                create_view_with_schema_union(con, schema_obj, model_path, "read_csv", to_csv_types)
             elif server.format == "delta":
                 con.sql("update extensions;")  # Make sure we have the latest delta extension
                 con.sql(f"""CREATE VIEW "{model_name}" AS SELECT * FROM delta_scan('{model_path}');""")
@@ -80,6 +71,34 @@ def get_duckdb_connection(
     return con
 
 
+def create_view_with_schema_union(con, schema_obj: SchemaObject, model_path: str, read_function: str, type_converter):
+    """Create a view by unioning empty schema table with data files using union_by_name"""
+    converted_types = type_converter(schema_obj)
+    model_name = schema_obj.name
+    if converted_types:
+        # Create empty table with contract schema
+        columns_def = [f'"{col_name}" {col_type}' for col_name, col_type in converted_types.items()]
+        create_empty_table = f"""CREATE TABLE "{model_name}" ({', '.join(columns_def)});"""
+        con.sql(create_empty_table)
+
+        # Read columns existing in both current data contract and data
+        intersecting_columns = con.sql(f"""SELECT column_name
+            FROM (DESCRIBE SELECT * FROM {read_function}('{model_path}', union_by_name=true, hive_partitioning=1))
+            INTERSECT SELECT column_name
+            FROM information_schema.columns
+            WHERE table_name = '{model_name}'""").fetchall()
+        selected_columns = ', '.join([column[0] for column in intersecting_columns])
+
+        # Insert data into table by name, but only columns existing in contract and data
+        insert_data_sql = f"""INSERT INTO {model_name} BY NAME
+            (SELECT {selected_columns} FROM {read_function}('{model_path}', union_by_name=true, hive_partitioning=1));"""
+        con.sql(insert_data_sql)
+    else:
+        # Fallback
+        con.sql(
+            f"""CREATE VIEW "{model_name}" AS SELECT * FROM {read_function}('{model_path}', union_by_name=true, hive_partitioning=1);"""
+        )
+
 def to_csv_types(schema_obj: SchemaObject) -> dict[Any, str | None] | None:
     if schema_obj is None:
         return None
@@ -89,6 +108,15 @@ def to_csv_types(schema_obj: SchemaObject) -> dict[Any, str | None] | None:
             columns[prop.name] = convert_to_duckdb_csv_type(prop)
     return columns
 
+def to_parquet_types(schema_obj: SchemaObject) -> dict[Any, str | None] | None:
+    """Get proper SQL types for Parquet (preserves decimals, etc.)"""
+    if schema_obj is None:
+        return None
+    columns = {}
+    if schema_obj.properties:
+        for prop in schema_obj.properties:
+            columns[prop.name] = convert_to_duckdb(prop)
+    return columns
 
 def to_json_types(schema_obj: SchemaObject) -> dict[Any, str | None] | None:
     if schema_obj is None:
@@ -140,7 +168,7 @@ def add_nested_views(con: duckdb.DuckDBPyConnection, model_name: str, properties
             add_nested_views(con, nested_model_name, prop.properties)
 
 
-def setup_s3_connection(con, server):
+def setup_s3_connection(con, server: Server):
     s3_region = os.getenv("DATACONTRACT_S3_REGION")
     s3_access_key_id = os.getenv("DATACONTRACT_S3_ACCESS_KEY_ID")
     s3_secret_access_key = os.getenv("DATACONTRACT_S3_SECRET_ACCESS_KEY")
@@ -184,7 +212,7 @@ def setup_s3_connection(con, server):
             """)
 
 
-def setup_gcs_connection(con, server):
+def setup_gcs_connection(con, server: Server):
     key_id = os.getenv("DATACONTRACT_GCS_KEY_ID")
     secret = os.getenv("DATACONTRACT_GCS_SECRET")
 
@@ -202,11 +230,14 @@ def setup_gcs_connection(con, server):
     """)
 
 
-def setup_azure_connection(con, server):
+def setup_azure_connection(con, server: Server):
     tenant_id = os.getenv("DATACONTRACT_AZURE_TENANT_ID")
     client_id = os.getenv("DATACONTRACT_AZURE_CLIENT_ID")
     client_secret = os.getenv("DATACONTRACT_AZURE_CLIENT_SECRET")
-    storage_account = server.storageAccount
+    storage_account = (
+        to_azure_storage_account(server.location) if server.type == "azure" and "://" in server.location
+            else None
+        )
 
     if tenant_id is None:
         raise ValueError("Error: Environment variable DATACONTRACT_AZURE_TENANT_ID is not set")
@@ -239,3 +270,25 @@ def setup_azure_connection(con, server):
             CLIENT_SECRET '{client_secret}'
         );
         """)
+
+def to_azure_storage_account(location: str) -> str | None:
+    """
+    Converts a storage location string to extract the storage account name.
+    ODCS v3.0 has no explicit field for the storage account. It uses the location field, which is a URI.
+    This function parses a storage location string to identify and return the
+    storage account name. It handles two primary patterns:
+    1. Protocol://containerName@storageAccountName
+    2. Protocol://storageAccountName
+    :param location: The storage location string to parse, typically following
+                     the format protocol://containerName@storageAccountName. or
+                     protocol://storageAccountName.
+    :return: The extracted storage account name if found, otherwise None
+    """
+    # to catch protocol://containerName@storageAccountName. pattern from location
+    match = re.search(r"(?<=@)([^.]*)", location, re.IGNORECASE)
+    if match:
+        return match.group()
+    else:
+        # to catch protocol://storageAccountName. pattern from location
+        match = re.search(r"(?<=//)(?!@)([^.]*)", location, re.IGNORECASE)
+    return match.group() if match else None

{datacontract_cli-0.11.2 → datacontract_cli-0.11.3}/datacontract/export/bigquery_exporter.py

@@ -113,8 +113,8 @@ def map_type_to_bigquery(prop: SchemaProperty) -> str:
     # If physicalType is already a BigQuery type, return it directly
     if prop.physicalType:
         bq_types = {
-            "STRING", "BYTES", "INT64", "INTEGER", "FLOAT64", "FLOAT", "NUMERIC",
-            "BIGNUMERIC", "BOOL", "BOOLEAN", "TIMESTAMP", "DATE", "TIME", "DATETIME",
+            "STRING", "BYTES", "INT64", "INTEGER", "FLOAT64", "NUMERIC",
+            "BIGNUMERIC", "BOOL", "TIMESTAMP", "DATE", "TIME", "DATETIME",
             "GEOGRAPHY", "JSON", "RECORD", "STRUCT", "ARRAY"
         }
         if prop.physicalType.upper() in bq_types or prop.physicalType.upper().startswith(("STRUCT<", "ARRAY<", "RANGE<")):

{datacontract_cli-0.11.2 → datacontract_cli-0.11.3}/datacontract/export/pydantic_exporter.py

@@ -19,9 +19,9 @@ def _get_description_str(description) -> str | None:
     if isinstance(description, str):
         return description
     # It's a Description object - get purpose or other meaningful field
-    if hasattr(description, 'purpose') and description.purpose:
+    if hasattr(description, "purpose") and description.purpose:
         return description.purpose
-    if hasattr(description, 'usage') and description.usage:
+    if hasattr(description, "usage") and description.usage:
         return description.usage
     return None
 
@@ -41,6 +41,7 @@ def to_pydantic_model_str(contract: OpenDataContractStandard) -> str:
                     ast.Name("datetime", ctx=ast.Load()),
                     ast.Name("typing", ctx=ast.Load()),
                     ast.Name("pydantic", ctx=ast.Load()),
+                    ast.Name("decimal", ctx=ast.Load()),
                 ]
             ),
             *documentation,
@@ -76,14 +77,23 @@ def _get_type(prop: SchemaProperty) -> Optional[str]:
     return prop.logicalType
 
 
+def _get_physical_type(prop: SchemaProperty) -> Optional[str]:
+    """Get the physical type from a schema property."""
+    return prop.physicalType.lower() if prop.physicalType else None
+
+
 def constant_field_annotation(
     field_name: str, prop: SchemaProperty
 ) -> tuple[type_annotation_type, typing.Optional[ast.ClassDef]]:
     prop_type = _get_type(prop)
+    physical_type = _get_physical_type(prop)
+
     match prop_type:
         case "string":
             return (ast.Name("str", ctx=ast.Load()), None)
         case "number":
+            if physical_type == "decimal":
+                return (ast.Attribute(value=ast.Name(id="decimal", ctx=ast.Load()), attr="Decimal"), None)
             # Either integer or float in specification,
             # so we use float.
             return (ast.Name("float", ctx=ast.Load()), None)
@@ -103,7 +113,6 @@ def constant_field_annotation(
             return (ast.Name(field_name.capitalize(), ctx=ast.Load()), classdef)
         case _:
             # Check physical type for more specific mappings
-            physical_type = prop.physicalType.lower() if prop.physicalType else None
             if physical_type:
                 if physical_type in ["text", "varchar", "char", "nvarchar"]:
                     return (ast.Name("str", ctx=ast.Load()), None)
@@ -115,8 +124,10 @@ def constant_field_annotation(
                     return (ast.Name("float", ctx=ast.Load()), None)
                 elif physical_type in ["double", "float64"]:
                     return (ast.Name("float", ctx=ast.Load()), None)
-                elif physical_type in ["decimal", "numeric", "number"]:
+                elif physical_type in ["numeric", "number"]:
                     return (ast.Name("float", ctx=ast.Load()), None)
+                elif physical_type == "decimal":
+                    return (ast.Attribute(value=ast.Name(id="decimal", ctx=ast.Load()), attr="Decimal"), None)
                 elif physical_type in ["timestamp", "datetime", "timestamp_tz", "timestamp_ntz"]:
                     return (ast.Attribute(value=ast.Name(id="datetime", ctx=ast.Load()), attr="datetime"), None)
                 elif physical_type == "date":

{datacontract_cli-0.11.2 → datacontract_cli-0.11.3}/datacontract/init/init_template.py

@@ -3,7 +3,7 @@ import logging
 
 import requests
 
-DEFAULT_DATA_CONTRACT_INIT_TEMPLATE = "datacontract-1.2.1.init.yaml"
+DEFAULT_DATA_CONTRACT_INIT_TEMPLATE = "odcs-3.1.0.init.yaml"
 
 
 def get_init_template(location: str = None) -> str:

datacontract_cli-0.11.3/datacontract/schemas/odcs-3.1.0.init.yaml

@@ -0,0 +1,36 @@
+apiVersion: v3.1.0
+kind: DataContract
+id: my-data-contract-id
+name: My Data Contract
+version: 1.0.0
+status: draft
+
+#team:
+#  name: Owner
+#
+#description:
+#  purpose: Purpose of the dataset.
+#  usage: Intended usage of the dataset.
+#  limitations: Limitations of the dataset.
+#
+#schema:
+#  - name: my_table
+#    description: Description of the table
+#    properties:
+#      - name: my_field
+#        logicalType: string
+#        description: Description of the field
+#
+#servers:
+#  - server: production
+#    type: postgres
+#    host: localhost
+#    port: 5432
+#    database: my_database
+#    schema: public
+#
+#slaProperties:
+#  - property: latency
+#    value: 1h
+#  - property: availability
+#    value: 99.9%

{datacontract_cli-0.11.2 → datacontract_cli-0.11.3/datacontract_cli.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datacontract-cli
-Version: 0.11.2
+Version: 0.11.3
 Summary: The datacontract CLI is an open source command-line tool for working with Data Contracts. It uses data contract YAML files to lint the data contract, connect to data sources and execute schema and quality tests, detect breaking changes, and export to different formats. The tool is written in Python. It can be used as a standalone CLI tool, in a CI/CD pipeline, or directly as a Python library.
 Author-email: Jochen Christ <jochen.christ@innoq.com>, Stefan Negele <stefan.negele@innoq.com>, Simon Harrer <simon.harrer@innoq.com>
 License-Expression: MIT
@@ -16,7 +16,7 @@ Requires-Dist: pydantic<2.13.0,>=2.8.2
 Requires-Dist: pyyaml~=6.0.1
 Requires-Dist: requests<2.33,>=2.31
 Requires-Dist: fastjsonschema<2.22.0,>=2.19.1
-Requires-Dist: fastparquet<2025.0.0,>=2024.5.0
+Requires-Dist: fastparquet<2026.0.0,>=2024.5.0
 Requires-Dist: numpy<2.0.0,>=1.26.4
 Requires-Dist: python-multipart<1.0.0,>=0.0.20
 Requires-Dist: rich<15.0,>=13.7
@@ -29,7 +29,7 @@ Requires-Dist: boto3<2.0.0,>=1.34.41
 Requires-Dist: Jinja2<4.0.0,>=3.1.5
 Requires-Dist: jinja_partials<1.0.0,>=0.2.1
 Requires-Dist: datacontract-specification<2.0.0,>=1.2.3
-Requires-Dist: open-data-contract-standard<4.0.0,>=3.1.0
+Requires-Dist: open-data-contract-standard<4.0.0,>=3.1.2
 Provides-Extra: avro
 Requires-Dist: avro==1.12.1; extra == "avro"
 Provides-Extra: bigquery
@@ -43,18 +43,18 @@ Requires-Dist: soda-core-spark-df<3.6.0,>=3.3.20; extra == "databricks"
 Requires-Dist: soda-core-spark[databricks]<3.6.0,>=3.3.20; extra == "databricks"
 Requires-Dist: databricks-sql-connector<4.3.0,>=3.7.0; extra == "databricks"
 Requires-Dist: databricks-sdk<0.74.0; extra == "databricks"
-Requires-Dist: pyspark<4.0.0,>=3.5.5; extra == "databricks"
+Requires-Dist: pyspark<5.0.0,>=3.5.5; extra == "databricks"
 Provides-Extra: iceberg
 Requires-Dist: pyiceberg==0.10.0; extra == "iceberg"
 Provides-Extra: kafka
 Requires-Dist: datacontract-cli[avro]; extra == "kafka"
 Requires-Dist: soda-core-spark-df<3.6.0,>=3.3.20; extra == "kafka"
-Requires-Dist: pyspark<4.0.0,>=3.5.5; extra == "kafka"
+Requires-Dist: pyspark<5.0.0,>=3.5.5; extra == "kafka"
 Provides-Extra: postgres
 Requires-Dist: soda-core-postgres<3.6.0,>=3.3.20; extra == "postgres"
 Provides-Extra: s3
 Requires-Dist: s3fs<2026.0.0,>=2025.2.0; extra == "s3"
-Requires-Dist: aiobotocore<2.26.0,>=2.17.0; extra == "s3"
+Requires-Dist: aiobotocore<3.2.0,>=2.17.0; extra == "s3"
 Provides-Extra: snowflake
 Requires-Dist: snowflake-connector-python[pandas]<4.2,>=3.6; extra == "snowflake"
 Requires-Dist: soda-core-snowflake<3.6.0,>=3.3.20; extra == "snowflake"
@@ -73,10 +73,10 @@ Requires-Dist: pydbml>=1.1.1; extra == "dbml"
 Provides-Extra: parquet
 Requires-Dist: pyarrow>=18.1.0; extra == "parquet"
 Provides-Extra: rdf
-Requires-Dist: rdflib==7.0.0; extra == "rdf"
+Requires-Dist: rdflib==7.5.0; extra == "rdf"
 Provides-Extra: api
 Requires-Dist: fastapi==0.121.2; extra == "api"
-Requires-Dist: uvicorn==0.38.0; extra == "api"
+Requires-Dist: uvicorn==0.40.0; extra == "api"
 Provides-Extra: protobuf
 Requires-Dist: grpcio-tools>=1.53; extra == "protobuf"
 Provides-Extra: all
@@ -657,8 +657,7 @@ datacontract.yaml
 servers:
   production:
     type: azure
-    storageAccount: datameshdatabricksdemo
-    location: abfss://dataproducts/inventory_events/*.parquet
+    location: abfss://datameshdatabricksdemo.dfs.core.windows.net/inventory_events/*.parquet
     format: parquet
 ```
 

{datacontract_cli-0.11.2 → datacontract_cli-0.11.3}/datacontract_cli.egg-info/SOURCES.txt

@@ -102,6 +102,7 @@ datacontract/schemas/datacontract-1.2.1.init.yaml
 datacontract/schemas/datacontract-1.2.1.schema.json
 datacontract/schemas/odcs-3.0.1.schema.json
 datacontract/schemas/odcs-3.0.2.schema.json
+datacontract/schemas/odcs-3.1.0.init.yaml
 datacontract/schemas/odcs-3.1.0.schema.json
 datacontract/templates/datacontract.html
 datacontract/templates/datacontract_odcs.html
@@ -204,6 +205,7 @@ tests/test_test_s3_json.py
 tests/test_test_s3_json_complex.py
 tests/test_test_s3_json_multiple_models.py
 tests/test_test_s3_json_remote.py
+tests/test_test_schema_evolution.py
 tests/test_test_snowflake.py
 tests/test_test_sqlserver.py
 tests/test_test_trino.py

{datacontract_cli-0.11.2 → datacontract_cli-0.11.3}/datacontract_cli.egg-info/requires.txt

@@ -3,7 +3,7 @@ pydantic<2.13.0,>=2.8.2
 pyyaml~=6.0.1
 requests<2.33,>=2.31
 fastjsonschema<2.22.0,>=2.19.1
-fastparquet<2025.0.0,>=2024.5.0
+fastparquet<2026.0.0,>=2024.5.0
 numpy<2.0.0,>=1.26.4
 python-multipart<1.0.0,>=0.0.20
 rich<15.0,>=13.7
@@ -16,14 +16,14 @@ boto3<2.0.0,>=1.34.41
 Jinja2<4.0.0,>=3.1.5
 jinja_partials<1.0.0,>=0.2.1
 datacontract-specification<2.0.0,>=1.2.3
-open-data-contract-standard<4.0.0,>=3.1.0
+open-data-contract-standard<4.0.0,>=3.1.2
 
 [all]
 datacontract-cli[api,athena,bigquery,csv,databricks,dbml,dbt,excel,iceberg,kafka,oracle,parquet,postgres,protobuf,rdf,s3,snowflake,sqlserver,trino]
 
 [api]
 fastapi==0.121.2
-uvicorn==0.38.0
+uvicorn==0.40.0
 
 [athena]
 soda-core-athena<3.6.0,>=3.3.20
@@ -42,7 +42,7 @@ soda-core-spark-df<3.6.0,>=3.3.20
 soda-core-spark[databricks]<3.6.0,>=3.3.20
 databricks-sql-connector<4.3.0,>=3.7.0
 databricks-sdk<0.74.0
-pyspark<4.0.0,>=3.5.5
+pyspark<5.0.0,>=3.5.5
 
 [dbml]
 pydbml>=1.1.1
@@ -74,7 +74,7 @@ pyiceberg==0.10.0
 [kafka]
 datacontract-cli[avro]
 soda-core-spark-df<3.6.0,>=3.3.20
-pyspark<4.0.0,>=3.5.5
+pyspark<5.0.0,>=3.5.5
 
 [oracle]
 soda-core-oracle<3.6.0,>=3.3.20
@@ -89,11 +89,11 @@ soda-core-postgres<3.6.0,>=3.3.20
 grpcio-tools>=1.53
 
 [rdf]
-rdflib==7.0.0
+rdflib==7.5.0
 
 [s3]
 s3fs<2026.0.0,>=2025.2.0
-aiobotocore<2.26.0,>=2.17.0
+aiobotocore<3.2.0,>=2.17.0
 
 [snowflake]
 snowflake-connector-python[pandas]<4.2,>=3.6

{datacontract_cli-0.11.2 → datacontract_cli-0.11.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "datacontract-cli"
-version = "0.11.2"
+version = "0.11.3"
 description = "The datacontract CLI is an open source command-line tool for working with Data Contracts. It uses data contract YAML files to lint the data contract, connect to data sources and execute schema and quality tests, detect breaking changes, and export to different formats. The tool is written in Python. It can be used as a standalone CLI tool, in a CI/CD pipeline, or directly as a Python library."
 license = "MIT"
 readme = "README.md"
@@ -20,7 +20,7 @@ dependencies = [
   "pyyaml~=6.0.1",
   "requests>=2.31,<2.33",
   "fastjsonschema>=2.19.1,<2.22.0",
-  "fastparquet>=2024.5.0,<2025.0.0",
+  "fastparquet>=2024.5.0,<2026.0.0",
   "numpy>=1.26.4,<2.0.0", # transitive dependency, needs to be <2.0.0 https://github.com/datacontract/datacontract-cli/issues/575
   "python-multipart>=0.0.20,<1.0.0",
   "rich>=13.7,<15.0",
@@ -34,7 +34,7 @@ dependencies = [
   "Jinja2>=3.1.5,<4.0.0",
   "jinja_partials>=0.2.1,<1.0.0",
   "datacontract-specification>=1.2.3,<2.0.0",
-  "open-data-contract-standard>=3.1.0,<4.0.0",
+  "open-data-contract-standard>=3.1.2,<4.0.0",
 ]
 
 [project.optional-dependencies]
@@ -61,7 +61,7 @@ databricks = [
   "soda-core-spark[databricks]>=3.3.20,<3.6.0",
   "databricks-sql-connector>=3.7.0,<4.3.0",
   "databricks-sdk<0.74.0",
-  "pyspark>=3.5.5,<4.0.0",
+  "pyspark>=3.5.5,<5.0.0",
 ]
 
 iceberg = [
@@ -71,7 +71,7 @@ iceberg = [
 kafka = [
   "datacontract-cli[avro]",
   "soda-core-spark-df>=3.3.20,<3.6.0",
-  "pyspark>=3.5.5,<4.0.0",
+  "pyspark>=3.5.5,<5.0.0",
 ]
 
 postgres = [
@@ -80,7 +80,7 @@ postgres = [
 
 s3 = [
   "s3fs>=2025.2.0,<2026.0.0",
-  "aiobotocore>=2.17.0,<2.26.0",
+  "aiobotocore>=2.17.0,<3.2.0",
 ]
 
 snowflake = [
@@ -117,12 +117,12 @@ parquet = [
 ]
 
 rdf = [
-  "rdflib==7.0.0",
+  "rdflib==7.5.0",
 ]
 
 api = [
   "fastapi==0.121.2",
-  "uvicorn==0.38.0",
+  "uvicorn==0.40.0",
 ]
 
 protobuf = [