datacontract-cli 0.10.35__tar.gz → 0.10.36__tar.gz

{datacontract_cli-0.10.35/datacontract_cli.egg-info → datacontract_cli-0.10.36}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datacontract-cli
-Version: 0.10.35
+Version: 0.10.36
 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: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: typer<0.17,>=0.15.1
+Requires-Dist: typer<0.20,>=0.15.1
 Requires-Dist: pydantic<2.12.0,>=2.8.2
 Requires-Dist: pyyaml~=6.0.1
 Requires-Dist: requests<2.33,>=2.31
@@ -28,7 +28,7 @@ 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,>=1.2.0
+Requires-Dist: datacontract-specification<2.0.0,>=1.2.3
 Requires-Dist: open-data-contract-standard<4.0.0,>=3.0.4
 Provides-Extra: avro
 Requires-Dist: avro==1.12.0; extra == "avro"
@@ -42,7 +42,7 @@ 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<4.1.0,>=3.7.0; extra == "databricks"
-Requires-Dist: databricks-sdk<0.64.0; extra == "databricks"
+Requires-Dist: databricks-sdk<0.68.0; extra == "databricks"
 Requires-Dist: pyspark<4.0.0,>=3.5.5; extra == "databricks"
 Provides-Extra: iceberg
 Requires-Dist: pyiceberg==0.9.1; extra == "iceberg"
@@ -56,7 +56,7 @@ Provides-Extra: s3
 Requires-Dist: s3fs<2026.0.0,>=2025.2.0; extra == "s3"
 Requires-Dist: aiobotocore<2.25.0,>=2.17.0; extra == "s3"
 Provides-Extra: snowflake
-Requires-Dist: snowflake-connector-python[pandas]<3.17,>=3.6; extra == "snowflake"
+Requires-Dist: snowflake-connector-python[pandas]<4.1,>=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"
@@ -83,7 +83,7 @@ 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: moto==5.1.10; extra == "dev"
+Requires-Dist: moto==5.1.13; extra == "dev"
 Requires-Dist: pandas>=2.1.0; extra == "dev"
 Requires-Dist: pre-commit<4.4.0,>=3.7.1; extra == "dev"
 Requires-Dist: pytest; extra == "dev"
@@ -119,9 +119,9 @@ We have a _servers_ section with endpoint details to the S3 bucket, _models_ for
 
 This data contract contains all information to connect to S3 and check that the actual data meets the defined schema and quality requirements. We can use this information to test if the actual data product in S3 is compliant to the data contract.
 
-Let's use [pip](https://pip.pypa.io/en/stable/getting-started/) to install the CLI (or use the [Docker image](#docker)),
+Let's use [uv](https://docs.astral.sh/uv/) to install the CLI (or use the [Docker image](#docker)),
 ```bash
-$ python3 -m pip install 'datacontract-cli[all]'
+$ uv tool install --python python3.11 'datacontract-cli[all]'
 ```
 
 
@@ -1540,18 +1540,22 @@ datacontract import --format bigquery --bigquery-project <project_id> --bigquery
 ```
 
 #### Unity Catalog
-
 ```bash
 # Example import from a Unity Catalog JSON file
 datacontract import --format unity --source my_unity_table.json
 ```
 
 ```bash
-# Example import single table from Unity Catalog via HTTP endpoint
+# Example import single table from Unity Catalog via HTTP endpoint using PAT
 export DATACONTRACT_DATABRICKS_SERVER_HOSTNAME="https://xyz.cloud.databricks.com"
-export DATACONTRACT_DATABRICKS_HTTP_PATH="/sql/1.0/warehouses/b053a331fa014fb4"
 export DATACONTRACT_DATABRICKS_TOKEN=<token>
 datacontract import --format unity --unity-table-full-name <table_full_name>
+```
+ Please Refer to  [Databricks documentation](https://docs.databricks.com/aws/en/dev-tools/auth/unified-auth) on how to set up a profile
+```bash
+# Example import single table from Unity Catalog via HTTP endpoint using Profile
+export DATACONTRACT_DATABRICKS_PROFILE="my-profile"
+datacontract import --format unity --unity-table-full-name <table_full_name>
 ```
 
 #### dbt
@@ -1610,20 +1614,20 @@ datacontract import --format spark --source "users,orders"
 
 ```bash
 # Example: Import Spark table
-DataContract().import_from_source("spark", "users")
-DataContract().import_from_source(format = "spark", source = "users")
+DataContract.import_from_source("spark", "users")
+DataContract.import_from_source(format = "spark", source = "users")
 
 # Example: Import Spark dataframe
-DataContract().import_from_source("spark", "users", dataframe = df_user)
-DataContract().import_from_source(format = "spark", source = "users", dataframe = df_user)
+DataContract.import_from_source("spark", "users", dataframe = df_user)
+DataContract.import_from_source(format = "spark", source = "users", dataframe = df_user)
 
 # Example: Import Spark table + table description
-DataContract().import_from_source("spark", "users", description = "description") 
-DataContract().import_from_source(format = "spark", source = "users", description = "description")
+DataContract.import_from_source("spark", "users", description = "description") 
+DataContract.import_from_source(format = "spark", source = "users", description = "description")
 
 # Example: Import Spark dataframe + table description
-DataContract().import_from_source("spark", "users", dataframe = df_user, description = "description")
-DataContract().import_from_source(format = "spark", source = "users", dataframe = df_user, description = "description")
+DataContract.import_from_source("spark", "users", dataframe = df_user, description = "description")
+DataContract.import_from_source(format = "spark", source = "users", dataframe = df_user, description = "description")
 ```
 
 #### DBML
@@ -1868,8 +1872,7 @@ Create a data contract based on the actual data. This is the fastest way to get
    $ datacontract test
    ```
 
-3. Make sure that all the best practices for a `datacontract.yaml` are met using the linter. You
-   probably forgot to document some fields and add the terms and conditions.
+3. Validate that the `datacontract.yaml` is correctly formatted and adheres to the Data Contract Specification.
    ```bash
    $ datacontract lint
    ```
@@ -1890,8 +1893,7 @@ Create a data contract based on the requirements from use cases.
    ```
 
 2. Create the model and quality guarantees based on your business requirements. Fill in the terms,
-   descriptions, etc. Make sure you follow all best practices for a `datacontract.yaml` using the
-   linter.
+   descriptions, etc. Validate that your `datacontract.yaml` is correctly formatted.
     ```bash
     $ datacontract lint
     ```
@@ -2085,7 +2087,7 @@ if __name__ == "__main__":
 Output
 
 ```yaml
-dataContractSpecification: 1.2.0
+dataContractSpecification: 1.2.1
 id: uuid-custom
 info:
   title: my_custom_imported_data
@@ -2111,6 +2113,7 @@ models:
 ```bash
 # make sure uv is installed
 uv python pin 3.11
+uv venv
 uv pip install -e '.[dev]'
 uv run ruff check
 uv run pytest

{datacontract_cli-0.10.35 → datacontract_cli-0.10.36}/README.md

@@ -23,9 +23,9 @@ We have a _servers_ section with endpoint details to the S3 bucket, _models_ for
 
 This data contract contains all information to connect to S3 and check that the actual data meets the defined schema and quality requirements. We can use this information to test if the actual data product in S3 is compliant to the data contract.
 
-Let's use [pip](https://pip.pypa.io/en/stable/getting-started/) to install the CLI (or use the [Docker image](#docker)),
+Let's use [uv](https://docs.astral.sh/uv/) to install the CLI (or use the [Docker image](#docker)),
 ```bash
-$ python3 -m pip install 'datacontract-cli[all]'
+$ uv tool install --python python3.11 'datacontract-cli[all]'
 ```
 
 
@@ -1444,18 +1444,22 @@ datacontract import --format bigquery --bigquery-project <project_id> --bigquery
 ```
 
 #### Unity Catalog
-
 ```bash
 # Example import from a Unity Catalog JSON file
 datacontract import --format unity --source my_unity_table.json
 ```
 
 ```bash
-# Example import single table from Unity Catalog via HTTP endpoint
+# Example import single table from Unity Catalog via HTTP endpoint using PAT
 export DATACONTRACT_DATABRICKS_SERVER_HOSTNAME="https://xyz.cloud.databricks.com"
-export DATACONTRACT_DATABRICKS_HTTP_PATH="/sql/1.0/warehouses/b053a331fa014fb4"
 export DATACONTRACT_DATABRICKS_TOKEN=<token>
 datacontract import --format unity --unity-table-full-name <table_full_name>
+```
+ Please Refer to  [Databricks documentation](https://docs.databricks.com/aws/en/dev-tools/auth/unified-auth) on how to set up a profile
+```bash
+# Example import single table from Unity Catalog via HTTP endpoint using Profile
+export DATACONTRACT_DATABRICKS_PROFILE="my-profile"
+datacontract import --format unity --unity-table-full-name <table_full_name>
 ```
 
 #### dbt
@@ -1514,20 +1518,20 @@ datacontract import --format spark --source "users,orders"
 
 ```bash
 # Example: Import Spark table
-DataContract().import_from_source("spark", "users")
-DataContract().import_from_source(format = "spark", source = "users")
+DataContract.import_from_source("spark", "users")
+DataContract.import_from_source(format = "spark", source = "users")
 
 # Example: Import Spark dataframe
-DataContract().import_from_source("spark", "users", dataframe = df_user)
-DataContract().import_from_source(format = "spark", source = "users", dataframe = df_user)
+DataContract.import_from_source("spark", "users", dataframe = df_user)
+DataContract.import_from_source(format = "spark", source = "users", dataframe = df_user)
 
 # Example: Import Spark table + table description
-DataContract().import_from_source("spark", "users", description = "description") 
-DataContract().import_from_source(format = "spark", source = "users", description = "description")
+DataContract.import_from_source("spark", "users", description = "description") 
+DataContract.import_from_source(format = "spark", source = "users", description = "description")
 
 # Example: Import Spark dataframe + table description
-DataContract().import_from_source("spark", "users", dataframe = df_user, description = "description")
-DataContract().import_from_source(format = "spark", source = "users", dataframe = df_user, description = "description")
+DataContract.import_from_source("spark", "users", dataframe = df_user, description = "description")
+DataContract.import_from_source(format = "spark", source = "users", dataframe = df_user, description = "description")
 ```
 
 #### DBML
@@ -1772,8 +1776,7 @@ Create a data contract based on the actual data. This is the fastest way to get
    $ datacontract test
    ```
 
-3. Make sure that all the best practices for a `datacontract.yaml` are met using the linter. You
-   probably forgot to document some fields and add the terms and conditions.
+3. Validate that the `datacontract.yaml` is correctly formatted and adheres to the Data Contract Specification.
    ```bash
    $ datacontract lint
    ```
@@ -1794,8 +1797,7 @@ Create a data contract based on the requirements from use cases.
    ```
 
 2. Create the model and quality guarantees based on your business requirements. Fill in the terms,
-   descriptions, etc. Make sure you follow all best practices for a `datacontract.yaml` using the
-   linter.
+   descriptions, etc. Validate that your `datacontract.yaml` is correctly formatted.
     ```bash
     $ datacontract lint
     ```
@@ -1989,7 +1991,7 @@ if __name__ == "__main__":
 Output
 
 ```yaml
-dataContractSpecification: 1.2.0
+dataContractSpecification: 1.2.1
 id: uuid-custom
 info:
   title: my_custom_imported_data
@@ -2015,6 +2017,7 @@ models:
 ```bash
 # make sure uv is installed
 uv python pin 3.11
+uv venv
 uv pip install -e '.[dev]'
 uv run ruff check
 uv run pytest

{datacontract_cli-0.10.35 → datacontract_cli-0.10.36}/datacontract/api.py

@@ -10,7 +10,7 @@ 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: 1.2.0
+DATA_CONTRACT_EXAMPLE_PAYLOAD = """dataContractSpecification: 1.2.1
 id: urn:datacontract:checkout:orders-latest
 info:
   title: Orders Latest

{datacontract_cli-0.10.35 → datacontract_cli-0.10.36}/datacontract/cli.py

@@ -331,7 +331,7 @@ def import_(
     """
     Create a data contract from the given source location. Saves to file specified by `output` option if present, otherwise prints to stdout.
     """
-    result = DataContract().import_from_source(
+    result = DataContract.import_from_source(
         format=format,
         source=source,
         spec=spec,

{datacontract_cli-0.10.35 → datacontract_cli-0.10.36}/datacontract/data_contract.py

@@ -26,11 +26,6 @@ from datacontract.imports.importer_factory import importer_factory
 from datacontract.init.init_template import get_init_template
 from datacontract.integration.datamesh_manager import publish_test_results_to_datamesh_manager
 from datacontract.lint import resolve
-from datacontract.lint.linters.description_linter import DescriptionLinter
-from datacontract.lint.linters.field_pattern_linter import FieldPatternLinter
-from datacontract.lint.linters.field_reference_linter import FieldReferenceLinter
-from datacontract.lint.linters.notice_period_linter import NoticePeriodLinter
-from datacontract.lint.linters.valid_constraints_linter import ValidFieldConstraintsLinter
 from datacontract.model.data_contract_specification import DataContractSpecification, Info
 from datacontract.model.exceptions import DataContractException
 from datacontract.model.run import Check, ResultEnum, Run
@@ -64,24 +59,14 @@ class DataContract:
         self._inline_definitions = inline_definitions
         self._inline_quality = inline_quality
         self._ssl_verification = ssl_verification
-        self.all_linters = {
-            FieldPatternLinter(),
-            FieldReferenceLinter(),
-            NoticePeriodLinter(),
-            ValidFieldConstraintsLinter(),
-            DescriptionLinter(),
-        }
 
     @classmethod
     def init(cls, template: typing.Optional[str], schema: typing.Optional[str] = None) -> DataContractSpecification:
         template_str = get_init_template(template)
         return resolve.resolve_data_contract(data_contract_str=template_str, schema_location=schema)
 
-    def lint(self, enabled_linters: typing.Union[str, set[str]] = "all") -> Run:
-        """Lint the data contract by deserializing the contract and checking the schema, as well as calling the configured linters.
-
-        enabled_linters can be either "all" or "none", or a set of linter IDs. The "schema" linter is always enabled, even with enabled_linters="none".
-        """
+    def lint(self) -> Run:
+        """Lint the data contract by validating it against the JSON schema."""
         run = Run.create_run()
         try:
             run.log_info("Linting data contract")
@@ -101,27 +86,6 @@ class DataContract:
                     engine="datacontract",
                 )
             )
-            if enabled_linters == "none":
-                linters_to_check = set()
-            elif enabled_linters == "all":
-                linters_to_check = self.all_linters
-            elif isinstance(enabled_linters, set):
-                linters_to_check = {linter for linter in self.all_linters if linter.id in enabled_linters}
-            else:
-                raise RuntimeError(f"Unknown argument enabled_linters={enabled_linters} for lint()")
-            for linter in linters_to_check:
-                try:
-                    run.checks.extend(linter.lint(data_contract))
-                except Exception as e:
-                    run.checks.append(
-                        Check(
-                            type="general",
-                            result=ResultEnum.error,
-                            name=f"Linter '{linter.name}'",
-                            reason=str(e),
-                            engine="datacontract",
-                        )
-                    )
             run.dataContractId = data_contract.id
             run.dataContractVersion = data_contract.info.version
         except DataContractException as e:
@@ -292,10 +256,9 @@ class DataContract:
                 export_args=kwargs,
             )
 
-    # REFACTOR THIS
-    # could be a class method, not using anything from the instance
+    @classmethod
     def import_from_source(
-        self,
+        cls,
         format: str,
         source: typing.Optional[str] = None,
         template: typing.Optional[str] = None,
@@ -307,7 +270,7 @@ class DataContract:
         owner = kwargs.get("owner")
 
         if spec == Spec.odcs or format == ImportFormat.excel:
-            data_contract_specification_initial = DataContract.init(template=template, schema=schema)
+            data_contract_specification_initial = cls.init(template=template, schema=schema)
 
             odcs_imported = importer_factory.create(format).import_source(
                 data_contract_specification=data_contract_specification_initial, source=source, import_args=kwargs
@@ -317,12 +280,12 @@ class DataContract:
                 # convert automatically
                 odcs_imported = to_odcs_v3(odcs_imported)
 
-            self._overwrite_id_in_odcs(odcs_imported, id)
-            self._overwrite_owner_in_odcs(odcs_imported, owner)
+            cls._overwrite_id_in_odcs(odcs_imported, id)
+            cls._overwrite_owner_in_odcs(odcs_imported, owner)
 
             return odcs_imported
         elif spec == Spec.datacontract_specification:
-            data_contract_specification_initial = DataContract.init(template=template, schema=schema)
+            data_contract_specification_initial = cls.init(template=template, schema=schema)
 
             data_contract_specification_imported = importer_factory.create(format).import_source(
                 data_contract_specification=data_contract_specification_initial, source=source, import_args=kwargs
@@ -334,8 +297,8 @@ class DataContract:
                     data_contract_specification_initial, data_contract_specification_imported
                 )
 
-            self._overwrite_id_in_data_contract_specification(data_contract_specification_imported, id)
-            self._overwrite_owner_in_data_contract_specification(data_contract_specification_imported, owner)
+            cls._overwrite_id_in_data_contract_specification(data_contract_specification_imported, id)
+            cls._overwrite_owner_in_data_contract_specification(data_contract_specification_imported, owner)
 
             return data_contract_specification_imported
         else:
@@ -347,16 +310,18 @@ class DataContract:
                 engine="datacontract",
             )
 
+    @staticmethod
     def _overwrite_id_in_data_contract_specification(
-        self, data_contract_specification: DataContractSpecification, id: str | None
+        data_contract_specification: DataContractSpecification, id: str | None
     ):
         if not id:
             return
 
         data_contract_specification.id = id
 
+    @staticmethod
     def _overwrite_owner_in_data_contract_specification(
-        self, data_contract_specification: DataContractSpecification, owner: str | None
+        data_contract_specification: DataContractSpecification, owner: str | None
     ):
         if not owner:
             return
@@ -365,7 +330,8 @@ class DataContract:
             data_contract_specification.info = Info()
         data_contract_specification.info.owner = owner
 
-    def _overwrite_owner_in_odcs(self, odcs: OpenDataContractStandard, owner: str | None):
+    @staticmethod
+    def _overwrite_owner_in_odcs(odcs: OpenDataContractStandard, owner: str | None):
         if not owner:
             return
 
@@ -377,7 +343,8 @@ class DataContract:
                 return
         odcs.customProperties.append(CustomProperty(property="owner", value=owner))
 
-    def _overwrite_id_in_odcs(self, odcs: OpenDataContractStandard, id: str | None):
+    @staticmethod
+    def _overwrite_id_in_odcs(odcs: OpenDataContractStandard, id: str | None):
         if not id:
             return