datacontract-cli 0.11.2__tar.gz → 0.11.4__tar.gz

{datacontract_cli-0.11.2/datacontract_cli.egg-info → datacontract_cli-0.11.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datacontract-cli
-Version: 0.11.2
+Version: 0.11.4
 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
@@ -11,25 +11,22 @@ Classifier: Operating System :: OS Independent
 Requires-Python: <3.13,>=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: typer<0.20,>=0.15.1
+Requires-Dist: typer<0.22,>=0.15.1
 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: numpy<2.0.0,>=1.26.4
+Requires-Dist: pytz>=2024.1
 Requires-Dist: python-multipart<1.0.0,>=0.0.20
 Requires-Dist: rich<15.0,>=13.7
 Requires-Dist: sqlglot<29.0.0,>=26.6.0
-Requires-Dist: duckdb<1.4.0,>=1.0.0
-Requires-Dist: soda-core-duckdb<3.6.0,>=3.3.20
 Requires-Dist: setuptools>=60
 Requires-Dist: python-dotenv<2.0.0,>=1.0.0
 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
@@ -42,19 +39,21 @@ Provides-Extra: databricks
 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: databricks-sdk<0.78.0; extra == "databricks"
+Requires-Dist: pyspark<5.0.0,>=3.5.0; extra == "databricks"
+Requires-Dist: numpy<2.0.0,>=1.26.4; 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,>=3.5.0; extra == "kafka"
+Requires-Dist: numpy<2.0.0,>=1.26.4; 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"
@@ -70,17 +69,20 @@ Provides-Extra: dbt
 Requires-Dist: dbt-core>=1.8.0; extra == "dbt"
 Provides-Extra: dbml
 Requires-Dist: pydbml>=1.1.1; extra == "dbml"
+Provides-Extra: duckdb
+Requires-Dist: duckdb<1.5.0,>=1.0.0; extra == "duckdb"
+Requires-Dist: soda-core-duckdb<3.6.0,>=3.3.20; extra == "duckdb"
 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
-Requires-Dist: datacontract-cli[api,athena,bigquery,csv,databricks,dbml,dbt,excel,iceberg,kafka,oracle,parquet,postgres,protobuf,rdf,s3,snowflake,sqlserver,trino]; extra == "all"
+Requires-Dist: datacontract-cli[api,athena,bigquery,csv,databricks,dbml,dbt,duckdb,excel,iceberg,kafka,oracle,parquet,postgres,protobuf,rdf,s3,snowflake,sqlserver,trino]; extra == "all"
 Provides-Extra: dev
 Requires-Dist: datacontract-cli[all]; extra == "dev"
 Requires-Dist: httpx==0.28.1; extra == "dev"
@@ -335,6 +337,7 @@ A list of available extras:
 | Avro Support            | `pip install datacontract-cli[avro]`       |
 | Google BigQuery         | `pip install datacontract-cli[bigquery]`   |
 | Databricks Integration  | `pip install datacontract-cli[databricks]` |
+| DuckDB (local/S3/GCS/Azure file testing) | `pip install datacontract-cli[duckdb]` |
 | Iceberg                 | `pip install datacontract-cli[iceberg]`    |
 | Kafka Integration       | `pip install datacontract-cli[kafka]`      |
 | PostgreSQL Integration  | `pip install datacontract-cli[postgres]`   |
@@ -657,8 +660,7 @@ 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-0.11.4}/README.md

@@ -236,6 +236,7 @@ A list of available extras:
 | Avro Support            | `pip install datacontract-cli[avro]`       |
 | Google BigQuery         | `pip install datacontract-cli[bigquery]`   |
 | Databricks Integration  | `pip install datacontract-cli[databricks]` |
+| DuckDB (local/S3/GCS/Azure file testing) | `pip install datacontract-cli[duckdb]` |
 | Iceberg                 | `pip install datacontract-cli[iceberg]`    |
 | Kafka Integration       | `pip install datacontract-cli[kafka]`      |
 | PostgreSQL Integration  | `pip install datacontract-cli[postgres]`   |
@@ -558,8 +559,7 @@ 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-0.11.4}/datacontract/api.py

@@ -11,50 +11,192 @@ from fastapi.security.api_key import APIKeyHeader
 from datacontract.data_contract import DataContract, ExportFormat
 from datacontract.model.run import Run
 
-DATA_CONTRACT_EXAMPLE_PAYLOAD = """dataContractSpecification: 1.2.1
-id: urn:datacontract:checkout:orders-latest
-info:
-  title: Orders Latest
-  version: 2.0.0
-  owner: Sales Team
-servers:
-  production:
-    type: s3
-    location: s3://datacontract-example-orders-latest/v2/{model}/*.json
-    format: json
-    delimiter: new_line
-models:
-  orders:
-    description: One record per order. Includes cancelled and deleted orders.
-    type: table
-    fields:
-      order_id:
-        type: string
+DATA_CONTRACT_EXAMPLE_PAYLOAD = """apiVersion: v3.1.0
+kind: DataContract
+id: orders
+name: Orders
+version: 1.0.0
+status: active
+description:
+  purpose: "Provides order and line item data for analytics and reporting"
+  usage: "Used by analytics team for sales analysis and business intelligence"
+  limitations: "Contains only the last 2 years of data"
+  customProperties:
+    - property: "sensitivity"
+      value: "secret"
+      description: "Data contains personally identifiable information"
+  authoritativeDefinitions:
+    - url: "https://entropy-data.com/policies/gdpr-compliance"
+      type: "businessDefinition"
+      description: "GDPR compliance policy for handling customer data"
+schema:
+  - name: orders
+    physicalType: TABLE
+    description: All historic web shop orders since 2020-01-01. Includes successful and cancelled orders.
+    properties:
+      - name: order_id
+        logicalType: string
+        description: The internal order id for every orders. Do not show this to a customer.
+        businessName: Internal Order ID
+        physicalType: UUID
+        examples:
+          - 99e8bb10-3785-4634-9664-8dc79eb69d43
         primaryKey: true
-      order_timestamp:
-        description: The business timestamp in UTC when the order was successfully registered in the source system and the payment was successful.
-        type: timestamp
+        classification: internal
         required: true
+        unique: true
+      - name: customer_id
+        logicalType: string
+        description: A reference to the customer number
+        businessName: Customer Number
+        physicalType: TEXT
         examples:
-          - "2024-09-09T08:30:00Z"
-      order_total:
-        description: Total amount the smallest monetary unit (e.g., cents).
-        type: long
+          - c123456789
         required: true
+        unique: false
+        logicalTypeOptions:
+          minLength: 10
+          maxLength: 10
+        authoritativeDefinitions:
+          - type: definition
+            url: https://example.com/definitions/sales/customer/customer_id
+        tags:
+          - pii:true
+        classification: internal
+        criticalDataElement: true
+      - name: order_total
+        logicalType: integer
+        description: The order total amount in cents, including tax, after discounts.
+          Includes shipping costs.
+        physicalType: INTEGER
         examples:
-          - 9999
+          - "9999"
+        quality:
+          - type: text
+            description: The order_total equals the sum of all related line items.
+        required: true
+        businessName: Order Amount
+      - name: order_timestamp
+        logicalType: timestamp
+        description: The time including timezone when the order payment was successfully
+          confirmed.
+        physicalType: TIMESTAMPTZ
+        businessName: Order Date
+        examples:
+          - "2025-03-01 14:30:00+01"
+      - name: order_status
+        businessName: Status
+        description: The business status of the order
+        logicalType: string
+        physicalType: TEXT
+        examples:
+          - shipped
         quality:
-          - type: sql
-            description: 95% of all order total values are expected to be between 10 and 499 EUR.
-            query: |
-              SELECT quantile_cont(order_total, 0.95) AS percentile_95
-              FROM orders
-            mustBeBetween: [1000, 99900]
-      customer_id:
-        description: Unique identifier for the customer.
-        type: text
-        minLength: 10
-        maxLength: 20
+          - type: library
+            description: Ensure that there are no other status values.
+            metric: invalidValues
+            arguments:
+              validValues:
+                - pending
+                - paid
+                - processing
+                - shipped
+                - delivered
+                - cancelled
+                - refunded
+            mustBe: 0
+    quality:
+      - type: library
+        metric: rowCount
+        mustBeGreaterThan: 100000
+        description: If there are less than 100k rows, something is wrong.
+  - name: line_items
+    physicalType: table
+    description: Details for each item in an order
+    properties:
+      - name: line_item_id
+        logicalType: string
+        description: Unique identifier for the line item
+        physicalType: UUID
+        examples:
+          - 12c9ba21-0c44-4e29-ba72-b8fd01c1be30
+        logicalTypeOptions:
+          format: uuid
+        required: true
+        primaryKey: true
+      - name: sku
+        logicalType: string
+        businessName: Stock Keeping Unit
+        description: Identifier for the purchased product
+        physicalType: TEXT
+        examples:
+          - 111222333
+        required: true
+      - name: price
+        logicalType: integer
+        description: Price in cents for this line item including tax
+        physicalType: INTEGER
+        examples:
+          - 9999
+        required: true
+      - name: order_id
+        required: false
+        primaryKey: false
+        logicalType: string
+        physicalType: UUID
+        relationships:
+          - type: foreignKey
+            to: orders.order_id
+servers:
+  - server: production
+    environment: prod
+    type: postgres
+    host: aws-1-eu-central-2.pooler.supabase.com
+    port: 6543
+    database: postgres
+    schema: dp_orders_v1
+team:
+  name: sales
+  description: This data product is owned by the "Sales" team
+  members:
+    - username: john@example.com
+      name: John Doe
+      role: Owner
+  authoritativeDefinitions:
+    - type: slack
+      url: https://slack.example.com/teams/sales
+roles:
+  - role: analyst_us
+    description: Read access for analytics to US orders
+  - role: analyst_eu
+    description: Read access for analytics to EU orders
+slaProperties:
+  - property: availability
+    value: 99.9%
+    description: Data platform uptime guarantee
+  - property: retention
+    value: "1"
+    unit: year
+    description: Data will be deleted after 1 year
+  - property: freshness
+    value: "24"
+    unit: hours
+    description: Within 24 hours of order placement
+  - property: support
+    value: business hours
+    description: Support only during business hours
+price:
+  priceAmount: 0
+  priceCurrency: USD
+  priceUnit: monthly
+tags:
+  - e-commerce
+  - transactions
+  - pii
+customProperties:
+  - property: dataPlatformRole
+    value: role_orders_v1
+contractCreatedTs: "2025-01-15T10:00:00Z"
 """
 
 app = FastAPI(

{datacontract_cli-0.11.2 → datacontract_cli-0.11.4}/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-0.11.4}/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-0.11.4}/datacontract/data_contract.py

@@ -4,10 +4,9 @@ import typing
 from open_data_contract_standard.model import OpenDataContractStandard, Team
 
 if typing.TYPE_CHECKING:
+    from duckdb.duckdb import DuckDBPyConnection
     from pyspark.sql import SparkSession
 
-from duckdb.duckdb import DuckDBPyConnection
-
 from datacontract.engines.data_contract_test import execute_data_contract_test
 from datacontract.export.exporter import ExportFormat
 from datacontract.export.exporter_factory import exporter_factory
@@ -29,7 +28,7 @@ class DataContract:
         server: str = None,
         publish_url: str = None,
         spark: "SparkSession" = None,
-        duckdb_connection: DuckDBPyConnection = None,
+        duckdb_connection: "DuckDBPyConnection" = None,
         inline_definitions: bool = True,
         ssl_verification: bool = True,
         publish_test_results: bool = False,

{datacontract_cli-0.11.2 → datacontract_cli-0.11.4}/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-0.11.4}/datacontract/engines/data_contract_test.py

@@ -4,12 +4,12 @@ import tempfile
 import typing
 
 import requests
-from duckdb.duckdb import DuckDBPyConnection
 from open_data_contract_standard.model import OpenDataContractStandard, Server
 
 from datacontract.engines.data_contract_checks import create_checks
 
 if typing.TYPE_CHECKING:
+    from duckdb.duckdb import DuckDBPyConnection
     from pyspark.sql import SparkSession
 
 from datacontract.engines.datacontract.check_that_datacontract_contains_valid_servers_configuration import (
@@ -26,7 +26,7 @@ def execute_data_contract_test(
     run: Run,
     server_name: str = None,
     spark: "SparkSession" = None,
-    duckdb_connection: DuckDBPyConnection = None,
+    duckdb_connection: "DuckDBPyConnection" = None,
 ):
     if data_contract.schema_ is None or len(data_contract.schema_) == 0:
         raise DataContractException(

{datacontract_cli-0.11.2 → datacontract_cli-0.11.4}/datacontract/engines/soda/check_soda_execute.py

@@ -6,9 +6,9 @@ from datacontract.engines.soda.connections.athena import to_athena_soda_configur
 from datacontract.engines.soda.connections.oracle import initialize_client_and_create_soda_configuration
 
 if typing.TYPE_CHECKING:
+    from duckdb.duckdb import DuckDBPyConnection
     from pyspark.sql import SparkSession
 
-from duckdb.duckdb import DuckDBPyConnection
 from open_data_contract_standard.model import OpenDataContractStandard, Server
 
 from datacontract.engines.soda.connections.bigquery import to_bigquery_soda_configuration
@@ -29,7 +29,7 @@ def check_soda_execute(
     data_contract: OpenDataContractStandard,
     server: Server,
     spark: "SparkSession" = None,
-    duckdb_connection: DuckDBPyConnection = None,
+    duckdb_connection: "DuckDBPyConnection" = None,
 ):
     from soda.common.config_helper import ConfigHelper
 

{datacontract_cli-0.11.2 → datacontract_cli-0.11.4}/datacontract/engines/soda/connections/duckdb_connection.py

@@ -1,19 +1,32 @@
 import os
-from typing import Any, List, Optional
+import re
+from typing import TYPE_CHECKING, 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
 
+if TYPE_CHECKING:
+    import duckdb
+
+
+def _import_duckdb():
+    try:
+        import duckdb
+        return duckdb
+    except ImportError:
+        raise ImportError("duckdb is required for this server type. Install with: pip install datacontract-cli[duckdb]")
+
 
 def get_duckdb_connection(
     data_contract: OpenDataContractStandard,
     server: Server,
     run: Run,
-    duckdb_connection: duckdb.DuckDBPyConnection | None = None,
-) -> duckdb.DuckDBPyConnection:
+    duckdb_connection: "duckdb.DuckDBPyConnection | None" = None,
+) -> "duckdb.DuckDBPyConnection":
+    duckdb = _import_duckdb()
     if duckdb_connection is None:
         con = duckdb.connect(database=":memory:")
     else:
@@ -57,29 +70,46 @@ 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}');""")
-            table_info = con.sql(f"PRAGMA table_info('{model_name}');").fetchdf()
-            if table_info is not None and not table_info.empty:
-                run.log_info(f"DuckDB Table Info: {table_info.to_string(index=False)}")
+            table_info = con.sql(f"PRAGMA table_info('{model_name}');").fetchall()
+            if table_info:
+                run.log_info(f"DuckDB Table Info: {table_info}")
     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 +119,15 @@ 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:
@@ -109,7 +148,7 @@ def _get_type(prop: SchemaProperty) -> Optional[str]:
     return None
 
 
-def add_nested_views(con: duckdb.DuckDBPyConnection, model_name: str, properties: List[SchemaProperty] | None):
+def add_nested_views(con: "duckdb.DuckDBPyConnection", model_name: str, properties: List[SchemaProperty] | None):
     model_name = model_name.strip('"')
     if properties is None:
         return
@@ -140,7 +179,7 @@ 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 +223,7 @@ 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 +241,14 @@ 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 +281,25 @@ 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