datacontract-cli 0.11.4__tar.gz → 0.11.6__tar.gz

{datacontract_cli-0.11.4/datacontract_cli.egg-info → datacontract_cli-0.11.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datacontract-cli
-Version: 0.11.4
+Version: 0.11.6
 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
@@ -11,7 +11,7 @@ Classifier: Operating System :: OS Independent
 Requires-Python: <3.13,>=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: typer<0.22,>=0.15.1
+Requires-Dist: typer<0.25,>=0.18.0
 Requires-Dist: pydantic<2.13.0,>=2.8.2
 Requires-Dist: pyyaml~=6.0.1
 Requires-Dist: requests<2.33,>=2.31
@@ -39,7 +39,7 @@ 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<0.78.0; extra == "databricks"
+Requires-Dist: databricks-sdk<0.86.0; 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
@@ -52,10 +52,10 @@ 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: s3fs<2027.0.0,>=2025.2.0; 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: snowflake-connector-python[pandas]<4.3,>=3.6; extra == "snowflake"
 Requires-Dist: soda-core-snowflake<3.6.0,>=3.3.20; extra == "snowflake"
 Provides-Extra: sqlserver
 Requires-Dist: soda-core-sqlserver<3.6.0,>=3.3.20; extra == "sqlserver"
@@ -75,9 +75,9 @@ 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==7.5.0; extra == "rdf"
+Requires-Dist: rdflib==7.6.0; extra == "rdf"
 Provides-Extra: api
-Requires-Dist: fastapi==0.121.2; extra == "api"
+Requires-Dist: fastapi==0.129.0; extra == "api"
 Requires-Dist: uvicorn==0.40.0; extra == "api"
 Provides-Extra: protobuf
 Requires-Dist: grpcio-tools>=1.53; extra == "protobuf"
@@ -87,15 +87,15 @@ Provides-Extra: dev
 Requires-Dist: datacontract-cli[all]; extra == "dev"
 Requires-Dist: httpx==0.28.1; extra == "dev"
 Requires-Dist: kafka-python; extra == "dev"
-Requires-Dist: minio==7.2.17; extra == "dev"
-Requires-Dist: moto==5.1.18; extra == "dev"
+Requires-Dist: minio==7.2.20; extra == "dev"
+Requires-Dist: moto==5.1.21; extra == "dev"
 Requires-Dist: pandas>=2.1.0; extra == "dev"
 Requires-Dist: pre-commit<4.6.0,>=3.7.1; extra == "dev"
 Requires-Dist: pytest; extra == "dev"
 Requires-Dist: pytest-xdist; extra == "dev"
-Requires-Dist: pymssql==2.3.9; extra == "dev"
-Requires-Dist: ruff; extra == "dev"
-Requires-Dist: testcontainers[kafka,minio,mssql,postgres]==4.13.3; extra == "dev"
+Requires-Dist: pymssql==2.3.13; extra == "dev"
+Requires-Dist: ruff==0.14.3; extra == "dev"
+Requires-Dist: testcontainers[kafka,minio,mssql,postgres]==4.14.1; extra == "dev"
 Requires-Dist: trino==0.336.0; extra == "dev"
 Dynamic: license-file
 
@@ -622,10 +622,11 @@ servers:
 
 #### BigQuery
 
-We support authentication to BigQuery using Service Account Key. The used Service Account should include the roles:
+We support authentication to BigQuery using Service Account Key or Application Default Credentials (ADC). ADC supports Workload Identity Federation (WIF), GCE metadata server, and `gcloud auth application-default login`. The used Service Account should include the roles:
 * BigQuery Job User
 * BigQuery Data Viewer
 
+When no `DATACONTRACT_BIGQUERY_ACCOUNT_INFO_JSON_PATH` is set, the CLI falls back to ADC/WIF automatically via Soda's `use_context_auth`.
 
 ##### Example
 
@@ -646,7 +647,8 @@ models:
 
 | Environment Variable                         | Example                   | Description                                             |
 |----------------------------------------------|---------------------------|---------------------------------------------------------|
-| `DATACONTRACT_BIGQUERY_ACCOUNT_INFO_JSON_PATH` | `~/service-access-key.json` | Service Access key as saved on key creation by BigQuery. If this environment variable isn't set, the cli tries to use `GOOGLE_APPLICATION_CREDENTIALS` as a fallback, so if you have that set for using their Python library anyway, it should work seamlessly. |
+| `DATACONTRACT_BIGQUERY_ACCOUNT_INFO_JSON_PATH` | `~/service-access-key.json` | Service Account key JSON file. If not set, ADC/WIF is used automatically. |
+| `DATACONTRACT_BIGQUERY_IMPERSONATION_ACCOUNT` | `sa@project.iam.gserviceaccount.com` | Optional. Service account to impersonate. Works with both key file and ADC auth. |
 
 
 #### Azure
@@ -678,7 +680,7 @@ Authentication works with an Azure Service Principal (SPN) aka App Registration
 
 #### Sqlserver
 
-Data Contract CLI can test data in MS SQL Server (including Azure SQL, Synapse Analytics SQL Pool).
+Data Contract CLI can test data in MS SQL Server (including Azure SQL, Synapse Analytics SQL Pool, and Microsoft Fabric).
 
 ##### Example
 
@@ -702,14 +704,17 @@ models:
 
 ##### Environment Variables
 
-| Environment Variable                              | Example| Description                                  |
-|---------------------------------------------------|--------|----------------------------------------------|
-| `DATACONTRACT_SQLSERVER_USERNAME`                 | `root` | Username                                     |
-| `DATACONTRACT_SQLSERVER_PASSWORD`                 | `toor` | Password                                     |
-| `DATACONTRACT_SQLSERVER_TRUSTED_CONNECTION`       | `True` | Use windows authentication, instead of login |
-| `DATACONTRACT_SQLSERVER_TRUST_SERVER_CERTIFICATE` | `True` | Trust self-signed certificate                |
-| `DATACONTRACT_SQLSERVER_ENCRYPTED_CONNECTION`     | `True` | Use SSL                                      |
-| `DATACONTRACT_SQLSERVER_DRIVER`                   | `ODBC Driver 18 for SQL Server` | ODBC driver name   |
+| Environment Variable                              | Example                         | Description                                                                                                                       |
+|---------------------------------------------------|---------------------------------|-----------------------------------------------------------------------------------------------------------------------------------|
+| `DATACONTRACT_SQLSERVER_AUTHENTICATION`           | `sql`                           | Supported: `sql` (default), `cli` (uses `az login` session), `windows`, `ActiveDirectoryPassword`, `ActiveDirectoryServicePrincipal`, `ActiveDirectoryInteractive` |
+| `DATACONTRACT_SQLSERVER_USERNAME`                 | `root`                          | Username (for `sql`, `ActiveDirectoryPassword`, `ActiveDirectoryInteractive`)                                                     |
+| `DATACONTRACT_SQLSERVER_PASSWORD`                 | `toor`                          | Password (for `sql` and `ActiveDirectoryPassword`)                                                                                |
+| `DATACONTRACT_SQLSERVER_CLIENT_ID`                | `a3cf5d29-b1a7-...`             | Application/Client ID (for `ActiveDirectoryServicePrincipal`)                                                                     |
+| `DATACONTRACT_SQLSERVER_CLIENT_SECRET`            | `kX9~Qr2Lm.Tz4W...`             | Client secret (for `ActiveDirectoryServicePrincipal`)                                                                             |
+| `DATACONTRACT_SQLSERVER_TRUST_SERVER_CERTIFICATE` | `True`                          | Trust self-signed certificate                                                                                                     |
+| `DATACONTRACT_SQLSERVER_ENCRYPTED_CONNECTION`     | `True`                          | Use SSL                                                                                                                           |
+| `DATACONTRACT_SQLSERVER_DRIVER`                   | `ODBC Driver 18 for SQL Server` | ODBC driver name                                                                                                                  |
+| `DATACONTRACT_SQLSERVER_TRUSTED_CONNECTION`       | `True`                          | Deprecated. Equivalent to `AUTHENTICATION=windows`                                                                                |
 
 
 
@@ -1636,7 +1641,6 @@ Available import options:
 | `spark`            | Import from Spark StructTypes, Variant        | ✅       |
 | `sql`              | Import from SQL DDL                           | ✅       |
 | `unity`            | Import from Databricks Unity Catalog          | partial |
-| `excel`            | Import from ODCS Excel Template               | ✅       |
 | Missing something? | Please create an issue on GitHub              | TBD     |
 
 

{datacontract_cli-0.11.4 → datacontract_cli-0.11.6}/README.md

@@ -521,10 +521,11 @@ servers:
 
 #### BigQuery
 
-We support authentication to BigQuery using Service Account Key. The used Service Account should include the roles:
+We support authentication to BigQuery using Service Account Key or Application Default Credentials (ADC). ADC supports Workload Identity Federation (WIF), GCE metadata server, and `gcloud auth application-default login`. The used Service Account should include the roles:
 * BigQuery Job User
 * BigQuery Data Viewer
 
+When no `DATACONTRACT_BIGQUERY_ACCOUNT_INFO_JSON_PATH` is set, the CLI falls back to ADC/WIF automatically via Soda's `use_context_auth`.
 
 ##### Example
 
@@ -545,7 +546,8 @@ models:
 
 | Environment Variable                         | Example                   | Description                                             |
 |----------------------------------------------|---------------------------|---------------------------------------------------------|
-| `DATACONTRACT_BIGQUERY_ACCOUNT_INFO_JSON_PATH` | `~/service-access-key.json` | Service Access key as saved on key creation by BigQuery. If this environment variable isn't set, the cli tries to use `GOOGLE_APPLICATION_CREDENTIALS` as a fallback, so if you have that set for using their Python library anyway, it should work seamlessly. |
+| `DATACONTRACT_BIGQUERY_ACCOUNT_INFO_JSON_PATH` | `~/service-access-key.json` | Service Account key JSON file. If not set, ADC/WIF is used automatically. |
+| `DATACONTRACT_BIGQUERY_IMPERSONATION_ACCOUNT` | `sa@project.iam.gserviceaccount.com` | Optional. Service account to impersonate. Works with both key file and ADC auth. |
 
 
 #### Azure
@@ -577,7 +579,7 @@ Authentication works with an Azure Service Principal (SPN) aka App Registration
 
 #### Sqlserver
 
-Data Contract CLI can test data in MS SQL Server (including Azure SQL, Synapse Analytics SQL Pool).
+Data Contract CLI can test data in MS SQL Server (including Azure SQL, Synapse Analytics SQL Pool, and Microsoft Fabric).
 
 ##### Example
 
@@ -601,14 +603,17 @@ models:
 
 ##### Environment Variables
 
-| Environment Variable                              | Example| Description                                  |
-|---------------------------------------------------|--------|----------------------------------------------|
-| `DATACONTRACT_SQLSERVER_USERNAME`                 | `root` | Username                                     |
-| `DATACONTRACT_SQLSERVER_PASSWORD`                 | `toor` | Password                                     |
-| `DATACONTRACT_SQLSERVER_TRUSTED_CONNECTION`       | `True` | Use windows authentication, instead of login |
-| `DATACONTRACT_SQLSERVER_TRUST_SERVER_CERTIFICATE` | `True` | Trust self-signed certificate                |
-| `DATACONTRACT_SQLSERVER_ENCRYPTED_CONNECTION`     | `True` | Use SSL                                      |
-| `DATACONTRACT_SQLSERVER_DRIVER`                   | `ODBC Driver 18 for SQL Server` | ODBC driver name   |
+| Environment Variable                              | Example                         | Description                                                                                                                       |
+|---------------------------------------------------|---------------------------------|-----------------------------------------------------------------------------------------------------------------------------------|
+| `DATACONTRACT_SQLSERVER_AUTHENTICATION`           | `sql`                           | Supported: `sql` (default), `cli` (uses `az login` session), `windows`, `ActiveDirectoryPassword`, `ActiveDirectoryServicePrincipal`, `ActiveDirectoryInteractive` |
+| `DATACONTRACT_SQLSERVER_USERNAME`                 | `root`                          | Username (for `sql`, `ActiveDirectoryPassword`, `ActiveDirectoryInteractive`)                                                     |
+| `DATACONTRACT_SQLSERVER_PASSWORD`                 | `toor`                          | Password (for `sql` and `ActiveDirectoryPassword`)                                                                                |
+| `DATACONTRACT_SQLSERVER_CLIENT_ID`                | `a3cf5d29-b1a7-...`             | Application/Client ID (for `ActiveDirectoryServicePrincipal`)                                                                     |
+| `DATACONTRACT_SQLSERVER_CLIENT_SECRET`            | `kX9~Qr2Lm.Tz4W...`             | Client secret (for `ActiveDirectoryServicePrincipal`)                                                                             |
+| `DATACONTRACT_SQLSERVER_TRUST_SERVER_CERTIFICATE` | `True`                          | Trust self-signed certificate                                                                                                     |
+| `DATACONTRACT_SQLSERVER_ENCRYPTED_CONNECTION`     | `True`                          | Use SSL                                                                                                                           |
+| `DATACONTRACT_SQLSERVER_DRIVER`                   | `ODBC Driver 18 for SQL Server` | ODBC driver name                                                                                                                  |
+| `DATACONTRACT_SQLSERVER_TRUSTED_CONNECTION`       | `True`                          | Deprecated. Equivalent to `AUTHENTICATION=windows`                                                                                |
 
 
 
@@ -1535,7 +1540,6 @@ Available import options:
 | `spark`            | Import from Spark StructTypes, Variant        | ✅       |
 | `sql`              | Import from SQL DDL                           | ✅       |
 | `unity`            | Import from Databricks Unity Catalog          | partial |
-| `excel`            | Import from ODCS Excel Template               | ✅       |
 | Missing something? | Please create an issue on GitHub              | TBD     |
 
 

{datacontract_cli-0.11.4 → datacontract_cli-0.11.6}/datacontract/catalog/catalog.py

@@ -32,7 +32,11 @@ def create_data_contract_html(contracts, file: Path, path: Path, schema: str):
     odcs = data_contract.get_data_contract()
     file_without_suffix = file.with_suffix(".html")
     html_filepath = path / file_without_suffix
-    html_filepath.parent.mkdir(parents=True, exist_ok=True)
+    try:
+        html_filepath.parent.mkdir(parents=True, exist_ok=True)
+    except FileExistsError:
+        if not html_filepath.parent.is_dir():
+            raise
     with open(html_filepath, "w", encoding="utf-8") as f:
         f.write(html)
     contracts.append(
@@ -48,6 +52,7 @@ def create_data_contract_html(contracts, file: Path, path: Path, schema: str):
 @dataclass
 class _InfoView:
     """Unified info view for templates."""
+
     title: str
     version: str
     owner: Optional[str]
@@ -57,6 +62,7 @@ class _InfoView:
 @dataclass
 class _SpecView:
     """Unified spec view for templates, compatible with DCS template structure."""
+
     info: _InfoView
     models: dict
 

{datacontract_cli-0.11.4 → datacontract_cli-0.11.6}/datacontract/cli.py

@@ -199,10 +199,7 @@ def export(
     server: Annotated[str, typer.Option(help="The server name to export.")] = None,
     schema_name: Annotated[
         str,
-        typer.Option(
-            help="The name of the schema to export, e.g., `orders`, or `all` for all "
-            "schemas (default)."
-        ),
+        typer.Option(help="The name of the schema to export, e.g., `orders`, or `all` for all schemas (default)."),
     ] = "all",
     # TODO: this should be a subcommand
     rdf_base: Annotated[
@@ -431,7 +428,11 @@ def catalog(
     enable_debug_logging(debug)
 
     path = Path(output)
-    path.mkdir(parents=True, exist_ok=True)
+    try:
+        path.mkdir(parents=True, exist_ok=True)
+    except FileExistsError:
+        if not path.is_dir():
+            raise
     console.print(f"Created {output}")
 
     contracts = []

{datacontract_cli-0.11.4 → datacontract_cli-0.11.6}/datacontract/data_contract.py

@@ -202,9 +202,7 @@ class DataContract:
         id = kwargs.get("id")
         owner = kwargs.get("owner")
 
-        odcs_imported = importer_factory.create(format).import_source(
-            source=source, import_args=kwargs
-        )
+        odcs_imported = importer_factory.create(format).import_source(source=source, import_args=kwargs)
 
         cls._overwrite_id_in_odcs(odcs_imported, id)
         cls._overwrite_owner_in_odcs(odcs_imported, owner)

{datacontract_cli-0.11.4 → datacontract_cli-0.11.6}/datacontract/engines/data_contract_checks.py

@@ -20,10 +20,22 @@ from datacontract.model.run import Check
 @dataclass
 class QuotingConfig:
     quote_field_name: bool = False
+    quote_field_name_with_backticks: bool = False
     quote_model_name: bool = False
     quote_model_name_with_backticks: bool = False
 
 
+def _quote_field_name(field_name: str, quoting_config: QuotingConfig) -> str:
+    """Quote a field name according to the quoting configuration."""
+    if field_name is None:
+        return field_name
+    if quoting_config.quote_field_name:
+        return f'"{field_name}"'
+    elif quoting_config.quote_field_name_with_backticks:
+        return f"`{field_name}`"
+    return field_name
+
+
 def _get_logical_type_option(prop: SchemaProperty, key: str):
     """Get a logical type option value."""
     if prop.logicalTypeOptions is None:
@@ -72,8 +84,9 @@ def to_schema_checks(schema_object: SchemaObject, server: Server) -> List[Check]
 
     type1 = server.type if server and server.type else None
     config = QuotingConfig(
-        quote_field_name=type1 in ["postgres", "sqlserver"],
-        quote_model_name=type1 in ["postgres", "sqlserver"],
+        quote_field_name=type1 in ["postgres", "sqlserver", "snowflake", "azure", "s3", "gcs", "local"],
+        quote_field_name_with_backticks=type1 in ["databricks"],
+        quote_model_name=type1 in ["postgres", "sqlserver", "snowflake", "azure", "s3", "gcs", "local"],
         quote_model_name_with_backticks=type1 == "bigquery",
     )
     quoting_config = config
@@ -165,7 +178,6 @@ def to_schema_name(schema_object: SchemaObject, server_type: str) -> str:
     return schema_object.name
 
 
-
 def check_property_is_present(model_name, field_name, quoting_config: QuotingConfig = QuotingConfig()) -> Check:
     check_type = "field_is_present"
     check_key = f"{model_name}__{field_name}__{check_type}"
@@ -229,10 +241,7 @@ def check_property_type(
 
 
 def check_property_required(model_name: str, field_name: str, quoting_config: QuotingConfig = QuotingConfig()):
-    if quoting_config.quote_field_name:
-        field_name_for_soda = f'"{field_name}"'
-    else:
-        field_name_for_soda = field_name
+    field_name_for_soda = _quote_field_name(field_name, quoting_config)
 
     check_type = "field_required"
     check_key = f"{model_name}__{field_name}__{check_type}"
@@ -260,10 +269,7 @@ def check_property_required(model_name: str, field_name: str, quoting_config: Qu
 
 
 def check_property_unique(model_name: str, field_name: str, quoting_config: QuotingConfig = QuotingConfig()):
-    if quoting_config.quote_field_name:
-        field_name_for_soda = f'"{field_name}"'
-    else:
-        field_name_for_soda = field_name
+    field_name_for_soda = _quote_field_name(field_name, quoting_config)
 
     check_type = "field_unique"
     check_key = f"{model_name}__{field_name}__{check_type}"
@@ -293,10 +299,7 @@ def check_property_unique(model_name: str, field_name: str, quoting_config: Quot
 def check_property_min_length(
     model_name: str, field_name: str, min_length: int, quoting_config: QuotingConfig = QuotingConfig()
 ):
-    if quoting_config.quote_field_name:
-        field_name_for_soda = f'"{field_name}"'
-    else:
-        field_name_for_soda = field_name
+    field_name_for_soda = _quote_field_name(field_name, quoting_config)
 
     check_type = "field_min_length"
     check_key = f"{model_name}__{field_name}__{check_type}"
@@ -327,10 +330,7 @@ def check_property_min_length(
 def check_property_max_length(
     model_name: str, field_name: str, max_length: int, quoting_config: QuotingConfig = QuotingConfig()
 ):
-    if quoting_config.quote_field_name:
-        field_name_for_soda = f'"{field_name}"'
-    else:
-        field_name_for_soda = field_name
+    field_name_for_soda = _quote_field_name(field_name, quoting_config)
 
     check_type = "field_max_length"
     check_key = f"{model_name}__{field_name}__{check_type}"
@@ -361,10 +361,7 @@ def check_property_max_length(
 def check_property_minimum(
     model_name: str, field_name: str, minimum: int, quoting_config: QuotingConfig = QuotingConfig()
 ):
-    if quoting_config.quote_field_name:
-        field_name_for_soda = f'"{field_name}"'
-    else:
-        field_name_for_soda = field_name
+    field_name_for_soda = _quote_field_name(field_name, quoting_config)
 
     check_type = "field_minimum"
     check_key = f"{model_name}__{field_name}__{check_type}"
@@ -395,10 +392,7 @@ def check_property_minimum(
 def check_property_maximum(
     model_name: str, field_name: str, maximum: int, quoting_config: QuotingConfig = QuotingConfig()
 ):
-    if quoting_config.quote_field_name:
-        field_name_for_soda = f'"{field_name}"'
-    else:
-        field_name_for_soda = field_name
+    field_name_for_soda = _quote_field_name(field_name, quoting_config)
 
     check_type = "field_maximum"
     check_key = f"{model_name}__{field_name}__{check_type}"
@@ -429,10 +423,7 @@ def check_property_maximum(
 def check_property_not_equal(
     model_name: str, field_name: str, value: int, quoting_config: QuotingConfig = QuotingConfig()
 ):
-    if quoting_config.quote_field_name:
-        field_name_for_soda = f'"{field_name}"'
-    else:
-        field_name_for_soda = field_name
+    field_name_for_soda = _quote_field_name(field_name, quoting_config)
 
     check_type = "field_not_equal"
     check_key = f"{model_name}__{field_name}__{check_type}"
@@ -461,10 +452,7 @@ def check_property_not_equal(
 
 
 def check_property_enum(model_name: str, field_name: str, enum: list, quoting_config: QuotingConfig = QuotingConfig()):
-    if quoting_config.quote_field_name:
-        field_name_for_soda = f'"{field_name}"'
-    else:
-        field_name_for_soda = field_name
+    field_name_for_soda = _quote_field_name(field_name, quoting_config)
 
     check_type = "field_enum"
     check_key = f"{model_name}__{field_name}__{check_type}"
@@ -492,11 +480,10 @@ def check_property_enum(model_name: str, field_name: str, enum: list, quoting_co
     )
 
 
-def check_property_regex(model_name: str, field_name: str, pattern: str, quoting_config: QuotingConfig = QuotingConfig()):
-    if quoting_config.quote_field_name:
-        field_name_for_soda = f'"{field_name}"'
-    else:
-        field_name_for_soda = field_name
+def check_property_regex(
+    model_name: str, field_name: str, pattern: str, quoting_config: QuotingConfig = QuotingConfig()
+):
+    field_name_for_soda = _quote_field_name(field_name, quoting_config)
 
     check_type = "field_regex"
     check_key = f"{model_name}__{field_name}__{check_type}"
@@ -553,7 +540,7 @@ def check_model_duplicate_values(
 ):
     check_type = "model_duplicate_values"
     check_key = f"{model_name}__{check_type}"
-    col_joined = ", ".join(cols)
+    col_joined = ", ".join(_quote_field_name(col, quoting_config) for col in cols)
     sodacl_check_dict = {
         checks_for(model_name, quoting_config, check_type): [
             {
@@ -578,10 +565,7 @@ def check_model_duplicate_values(
 def check_property_duplicate_values(
     model_name: str, field_name: str, threshold: str, quoting_config: QuotingConfig = QuotingConfig()
 ):
-    if quoting_config.quote_field_name:
-        field_name_for_soda = f'"{field_name}"'
-    else:
-        field_name_for_soda = field_name
+    field_name_for_soda = _quote_field_name(field_name, quoting_config)
 
     check_type = "field_duplicate_values"
     check_key = f"{model_name}__{field_name}__{check_type}"
@@ -611,10 +595,7 @@ def check_property_duplicate_values(
 def check_property_null_values(
     model_name: str, field_name: str, threshold: str, quoting_config: QuotingConfig = QuotingConfig()
 ):
-    if quoting_config.quote_field_name:
-        field_name_for_soda = f'"{field_name}"'
-    else:
-        field_name_for_soda = field_name
+    field_name_for_soda = _quote_field_name(field_name, quoting_config)
 
     check_type = "field_null_values"
     check_key = f"{model_name}__{field_name}__{check_type}"
@@ -648,10 +629,7 @@ def check_property_invalid_values(
     valid_values: list = None,
     quoting_config: QuotingConfig = QuotingConfig(),
 ):
-    if quoting_config.quote_field_name:
-        field_name_for_soda = f'"{field_name}"'
-    else:
-        field_name_for_soda = field_name
+    field_name_for_soda = _quote_field_name(field_name, quoting_config)
 
     check_type = "field_invalid_values"
     check_key = f"{model_name}__{field_name}__{check_type}"
@@ -691,10 +669,7 @@ def check_property_missing_values(
     missing_values: list = None,
     quoting_config: QuotingConfig = QuotingConfig(),
 ):
-    if quoting_config.quote_field_name:
-        field_name_for_soda = f'"{field_name}"'
-    else:
-        field_name_for_soda = field_name
+    field_name_for_soda = _quote_field_name(field_name, quoting_config)
 
     check_type = "field_missing_values"
     check_key = f"{model_name}__{field_name}__{check_type}"
@@ -819,7 +794,9 @@ def check_quality_list(
                         )
                     )
                 else:
-                    checks.append(check_property_duplicate_values(schema_name, property_name, threshold, quoting_config))
+                    checks.append(
+                        check_property_duplicate_values(schema_name, property_name, threshold, quoting_config)
+                    )
             elif quality.metric == "nullValues":
                 if property_name is not None:
                     checks.append(check_property_null_values(schema_name, property_name, threshold, quoting_config))
@@ -829,7 +806,9 @@ def check_quality_list(
                 if property_name is not None:
                     valid_values = quality.arguments.get("validValues") if quality.arguments else None
                     checks.append(
-                        check_property_invalid_values(schema_name, property_name, threshold, valid_values, quoting_config)
+                        check_property_invalid_values(
+                            schema_name, property_name, threshold, valid_values, quoting_config
+                        )
                     )
                 else:
                     logger.warning("Quality check invalidValues is only supported at field level")
@@ -837,7 +816,9 @@ def check_quality_list(
                 if property_name is not None:
                     missing_values = quality.arguments.get("missingValues") if quality.arguments else None
                     checks.append(
-                        check_property_missing_values(schema_name, property_name, threshold, missing_values, quoting_config)
+                        check_property_missing_values(
+                            schema_name, property_name, threshold, missing_values, quoting_config
+                        )
                     )
                 else:
                     logger.warning("Quality check missingValues is only supported at field level")
@@ -863,10 +844,7 @@ def prepare_query(
 
     query = quality.query
 
-    if quoting_config.quote_field_name:
-        field_name_for_soda = f'"{field_name}"'
-    else:
-        field_name_for_soda = field_name
+    field_name_for_soda = _quote_field_name(field_name, quoting_config)
 
     if quoting_config.quote_model_name:
         model_name_for_soda = f'"{model_name}"'
@@ -1050,11 +1028,12 @@ def to_servicelevel_retention_check(data_contract: OpenDataContractStandard, sla
         logger.info(f"Model {model_name} not found in schema, skipping retention check")
         return None
 
-    # Parse ISO 8601 duration to seconds
-    retention_period = sla.value
-    seconds = _parse_iso8601_to_seconds(retention_period)
+    # Convert retention value to seconds
+    # Supports both numeric value + unit (ODCS style: value=3, unit=y)
+    # and ISO 8601 duration strings (e.g., "P1Y")
+    seconds = _retention_value_to_seconds(sla.value, sla.unit)
     if seconds is None:
-        logger.info(f"Could not parse retention period {retention_period}, skipping retention check")
+        logger.info(f"Could not parse retention period (value={sla.value}, unit={sla.unit}), skipping retention check")
         return None
 
     check_type = "servicelevel_retention"
@@ -1083,6 +1062,43 @@ def to_servicelevel_retention_check(data_contract: OpenDataContractStandard, sla
     )
 
 
+def _retention_value_to_seconds(value, unit: str | None) -> int | None:
+    """Convert a retention value to seconds.
+
+    Supports:
+    - Numeric value with unit (ODCS style): value=3, unit="y"
+    - ISO 8601 duration string: value="P1Y"
+    """
+    if value is None:
+        return None
+
+    # If value is numeric, use the unit to convert to seconds
+    if isinstance(value, (int, float)):
+        numeric_value = int(value)
+        unit_lower = unit.lower() if unit else "d"
+        if unit_lower in ("y", "yr", "year", "years"):
+            return numeric_value * 365 * 24 * 60 * 60
+        elif unit_lower in ("m", "mo", "month", "months"):
+            return numeric_value * 30 * 24 * 60 * 60
+        elif unit_lower in ("d", "day", "days"):
+            return numeric_value * 24 * 60 * 60
+        elif unit_lower in ("h", "hr", "hour", "hours"):
+            return numeric_value * 60 * 60
+        elif unit_lower in ("min", "minute", "minutes"):
+            return numeric_value * 60
+        elif unit_lower in ("s", "sec", "second", "seconds"):
+            return numeric_value
+        else:
+            logger.info(f"Unsupported retention unit: {unit}")
+            return None
+
+    # If value is a string, try ISO 8601 parsing
+    if isinstance(value, str):
+        return _parse_iso8601_to_seconds(value)
+
+    return None
+
+
 def _parse_iso8601_to_seconds(duration: str) -> int | None:
     """Parse ISO 8601 duration to seconds."""
     if not duration:
@@ -1125,4 +1141,3 @@ def _parse_iso8601_to_seconds(duration: str) -> int | None:
         return int(match.group(1))
 
     return None
-

{datacontract_cli-0.11.4 → datacontract_cli-0.11.6}/datacontract/engines/data_contract_test.py

@@ -36,11 +36,7 @@ def execute_data_contract_test(
             reason="Schema block is missing. Skip executing tests.",
             engine="datacontract",
         )
-    if (
-        server_name is None
-        and data_contract.servers is not None
-        and len(data_contract.servers) > 0
-    ):
+    if server_name is None and data_contract.servers is not None and len(data_contract.servers) > 0:
         server_name = data_contract.servers[0].server
     server = get_server(data_contract, server_name)
     run.log_info(f"Running tests for data contract {data_contract.id} with server {server_name}")

{datacontract_cli-0.11.4 → datacontract_cli-0.11.6}/datacontract/engines/soda/check_soda_execute.py

@@ -96,7 +96,7 @@ def check_soda_execute(
             logging.info("Use Spark to connect to data source")
             scan.add_spark_session(spark, data_source_name="datacontract-cli")
             scan.set_data_source_name("datacontract-cli")
-    
+
     # ------------------------------------------------------------------
     # NEW: native Impala server type
     # ------------------------------------------------------------------
@@ -107,7 +107,6 @@ def check_soda_execute(
         # data source name must match what we configure in to_impala_soda_configuration
         scan.set_data_source_name("impala")
 
-    
     elif server.type == "kafka":
         if spark is None:
             spark = create_spark_session()
@@ -231,4 +230,4 @@ def update_reason(check, c):
                 # print(check.reason)
             break  # Exit the loop once the desired block is found
     if "fail" in c["diagnostics"]:
-        check.reason = f"Value: {c['diagnostics']['value']} Fail: {c['diagnostics']['fail']}"
+        check.reason = f"Value: {c['diagnostics']['value']} Fail: {c['diagnostics']['fail']}"

datacontract_cli-0.11.6/datacontract/engines/soda/connections/bigquery.py

@@ -0,0 +1,24 @@
+import os
+
+import yaml
+
+
+# https://docs.soda.io/soda/connect-bigquery.html#authentication-methods
+def to_bigquery_soda_configuration(server):
+    data_source = {
+        "type": "bigquery",
+        "project_id": server.project,
+        "dataset": server.dataset,
+    }
+
+    if "DATACONTRACT_BIGQUERY_ACCOUNT_INFO_JSON_PATH" in os.environ:
+        data_source["account_info_json_path"] = os.environ["DATACONTRACT_BIGQUERY_ACCOUNT_INFO_JSON_PATH"]
+        data_source["auth_scopes"] = ["https://www.googleapis.com/auth/bigquery"]
+    else:
+        data_source["use_context_auth"] = True
+
+    if "DATACONTRACT_BIGQUERY_IMPERSONATION_ACCOUNT" in os.environ:
+        data_source["impersonation_account"] = os.environ["DATACONTRACT_BIGQUERY_IMPERSONATION_ACCOUNT"]
+
+    soda_configuration_str = yaml.dump({f"data_source {server.type}": data_source})
+    return soda_configuration_str