datacontract-cli 0.10.28__tar.gz → 0.10.30__tar.gz

{datacontract_cli-0.10.28/datacontract_cli.egg-info → datacontract_cli-0.10.30}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datacontract-cli
-Version: 0.10.28
+Version: 0.10.30
 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<0.16,>=0.15.1
+Requires-Dist: typer<0.17,>=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,>=1.1.1
+Requires-Dist: datacontract-specification<2.0.0,>=1.2.0
 Requires-Dist: open-data-contract-standard<4.0.0,>=3.0.4
 Provides-Extra: avro
 Requires-Dist: avro==1.12.0; extra == "avro"
@@ -42,21 +42,21 @@ 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<4.1.0,>=3.7.0; extra == "databricks"
-Requires-Dist: databricks-sdk<0.55.0; extra == "databricks"
-Requires-Dist: pyspark==3.5.5; extra == "databricks"
+Requires-Dist: databricks-sdk<0.59.0; extra == "databricks"
+Requires-Dist: pyspark<4.0.0,>=3.5.5; extra == "databricks"
 Provides-Extra: iceberg
-Requires-Dist: pyiceberg==0.8.1; extra == "iceberg"
+Requires-Dist: pyiceberg==0.9.1; 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==3.5.5; extra == "kafka"
+Requires-Dist: pyspark<4.0.0,>=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<2.23.0,>=2.17.0; extra == "s3"
+Requires-Dist: aiobotocore<2.24.0,>=2.17.0; extra == "s3"
 Provides-Extra: snowflake
-Requires-Dist: snowflake-connector-python[pandas]<3.15,>=3.6; extra == "snowflake"
+Requires-Dist: snowflake-connector-python[pandas]<3.16,>=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"
@@ -71,8 +71,8 @@ Requires-Dist: pyarrow>=18.1.0; extra == "parquet"
 Provides-Extra: rdf
 Requires-Dist: rdflib==7.0.0; extra == "rdf"
 Provides-Extra: api
-Requires-Dist: fastapi==0.115.12; extra == "api"
-Requires-Dist: uvicorn==0.34.2; extra == "api"
+Requires-Dist: fastapi==0.116.1; extra == "api"
+Requires-Dist: uvicorn==0.35.0; extra == "api"
 Provides-Extra: protobuf
 Requires-Dist: grpcio-tools>=1.53; extra == "protobuf"
 Provides-Extra: all
@@ -81,15 +81,15 @@ 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: moto==5.1.5; extra == "dev"
+Requires-Dist: moto==5.1.6; extra == "dev"
 Requires-Dist: pandas>=2.1.0; extra == "dev"
 Requires-Dist: pre-commit<4.3.0,>=3.7.1; extra == "dev"
 Requires-Dist: pytest; extra == "dev"
 Requires-Dist: pytest-xdist; extra == "dev"
-Requires-Dist: pymssql==2.3.4; extra == "dev"
+Requires-Dist: pymssql==2.3.7; extra == "dev"
 Requires-Dist: ruff; extra == "dev"
 Requires-Dist: testcontainers[kafka,minio,mssql,postgres]==4.10.0; extra == "dev"
-Requires-Dist: trino==0.333.0; extra == "dev"
+Requires-Dist: trino==0.335.0; extra == "dev"
 Dynamic: license-file
 
 # Data Contract CLI
@@ -1286,9 +1286,9 @@ FROM
                                                                                                     
 ╭─ Options ────────────────────────────────────────────────────────────────────────────────────────╮
 │ *  --format                       [sql|avro|dbt|dbml|glue|jsonsc  The format of the source file. │
-│                                   hema|bigquery|odcs|unity|spark  [default: None]                │
-│                                   |iceberg|parquet|csv|protobuf|  [required]                     │
-│                                   excel]                                                         │
+│                                   hema|json|bigquery|odcs|unity|  [default: None]                │
+│                                   spark|iceberg|parquet|csv|prot  [required]                     │
+│                                   obuf|excel]                                                    │
 │    --output                       PATH                            Specify the file path where    │
 │                                                                   the Data Contract will be      │
 │                                                                   saved. If no path is provided, │
@@ -1712,6 +1712,8 @@ datacontract catalog --files "*.odcs.yaml"
  information.                                                                                       
  To connect to servers (such as a Snowflake data source), set the credentials as environment        
  variables as documented in https://cli.datacontract.com/#test                                      
+ It is possible to run the API with extra arguments for `uvicorn.run()` as keyword arguments, e.g.: 
+ `datacontract api --port 1234 --root_path /datacontract`.                                          
                                                                                                     
 ╭─ Options ────────────────────────────────────────────────────────────────────────────────────────╮
 │ --port        INTEGER  Bind socket to this port. [default: 4242]                                 │
@@ -1978,7 +1980,7 @@ if __name__ == "__main__":
 Output
 
 ```yaml
-dataContractSpecification: 1.1.0
+dataContractSpecification: 1.2.0
 id: uuid-custom
 info:
   title: my_custom_imported_data
@@ -1997,22 +1999,9 @@ models:
 ```
 ## Development Setup
 
-Python base interpreter should be 3.11.x (unless working on 3.12 release candidate).
-
-```bash
-# create venv
-python3.11 -m venv venv
-source venv/bin/activate
-
-# Install Requirements
-pip install --upgrade pip setuptools wheel
-pip install -e '.[dev]'
-pre-commit install
-pre-commit run --all-files
-pytest
-```
-
-### Use uv (recommended)
+- Install [uv](https://docs.astral.sh/uv/)
+- Python base interpreter should be 3.11.x .
+- Docker engine must be running to execute the tests.
 
 ```bash
 # make sure uv is installed
@@ -2094,6 +2083,7 @@ We are happy to receive your contributions. Propose your change in an issue or d
 - [INNOQ](https://innoq.com)
 - [Data Catering](https://data.catering/)
 - [Oliver Wyman](https://www.oliverwyman.com/)
+- [dmTECH](https://www.dmtech.tech/de)
 - And many more. To add your company, please create a pull request.
 
 ## Related Tools

{datacontract_cli-0.10.28 → datacontract_cli-0.10.30}/README.md

@@ -1192,9 +1192,9 @@ FROM
                                                                                                     
 ╭─ Options ────────────────────────────────────────────────────────────────────────────────────────╮
 │ *  --format                       [sql|avro|dbt|dbml|glue|jsonsc  The format of the source file. │
-│                                   hema|bigquery|odcs|unity|spark  [default: None]                │
-│                                   |iceberg|parquet|csv|protobuf|  [required]                     │
-│                                   excel]                                                         │
+│                                   hema|json|bigquery|odcs|unity|  [default: None]                │
+│                                   spark|iceberg|parquet|csv|prot  [required]                     │
+│                                   obuf|excel]                                                    │
 │    --output                       PATH                            Specify the file path where    │
 │                                                                   the Data Contract will be      │
 │                                                                   saved. If no path is provided, │
@@ -1618,6 +1618,8 @@ datacontract catalog --files "*.odcs.yaml"
  information.                                                                                       
  To connect to servers (such as a Snowflake data source), set the credentials as environment        
  variables as documented in https://cli.datacontract.com/#test                                      
+ It is possible to run the API with extra arguments for `uvicorn.run()` as keyword arguments, e.g.: 
+ `datacontract api --port 1234 --root_path /datacontract`.                                          
                                                                                                     
 ╭─ Options ────────────────────────────────────────────────────────────────────────────────────────╮
 │ --port        INTEGER  Bind socket to this port. [default: 4242]                                 │
@@ -1884,7 +1886,7 @@ if __name__ == "__main__":
 Output
 
 ```yaml
-dataContractSpecification: 1.1.0
+dataContractSpecification: 1.2.0
 id: uuid-custom
 info:
   title: my_custom_imported_data
@@ -1903,22 +1905,9 @@ models:
 ```
 ## Development Setup
 
-Python base interpreter should be 3.11.x (unless working on 3.12 release candidate).
-
-```bash
-# create venv
-python3.11 -m venv venv
-source venv/bin/activate
-
-# Install Requirements
-pip install --upgrade pip setuptools wheel
-pip install -e '.[dev]'
-pre-commit install
-pre-commit run --all-files
-pytest
-```
-
-### Use uv (recommended)
+- Install [uv](https://docs.astral.sh/uv/)
+- Python base interpreter should be 3.11.x .
+- Docker engine must be running to execute the tests.
 
 ```bash
 # make sure uv is installed
@@ -2000,6 +1989,7 @@ We are happy to receive your contributions. Propose your change in an issue or d
 - [INNOQ](https://innoq.com)
 - [Data Catering](https://data.catering/)
 - [Oliver Wyman](https://www.oliverwyman.com/)
+- [dmTECH](https://www.dmtech.tech/de)
 - And many more. To add your company, please create a pull request.
 
 ## Related Tools

{datacontract_cli-0.10.28 → datacontract_cli-0.10.30}/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: 1.1.0
+DATA_CONTRACT_EXAMPLE_PAYLOAD = """dataContractSpecification: 1.2.0
 id: urn:datacontract:checkout:orders-latest
 info:
   title: Orders Latest

{datacontract_cli-0.10.28 → datacontract_cli-0.10.30}/datacontract/cli.py

@@ -469,8 +469,26 @@ def diff(
     console.print(result.changelog_str())
 
 
-@app.command()
+def _get_uvicorn_arguments(port: int, host: str, context: typer.Context) -> dict:
+    """
+    Take the default datacontract uvicorn arguments and merge them with the
+    extra arguments passed to the command to start the API.
+    """
+    default_args = {
+        "app": "datacontract.api:app",
+        "port": port,
+        "host": host,
+        "reload": True,
+    }
+
+    # Create a list of the extra arguments, remove the leading -- from the cli arguments
+    trimmed_keys = list(map(lambda x : str(x).replace("--", ""),context.args[::2]))
+    # Merge the two dicts and return them as one dict
+    return default_args | dict(zip(trimmed_keys, context.args[1::2]))
+
+@app.command(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,
     host: Annotated[
         str, typer.Option(help="Bind socket to this host. Hint: For running in docker, set it to 0.0.0.0")
@@ -488,6 +506,9 @@ def api(
 
     To connect to servers (such as a Snowflake data source), set the credentials as environment variables as documented in
     https://cli.datacontract.com/#test
+
+    It is possible to run the API with extra arguments for `uvicorn.run()` as keyword arguments, e.g.:
+    `datacontract api --port 1234 --root_path /datacontract`.
     """
     import uvicorn
     from uvicorn.config import LOGGING_CONFIG
@@ -495,7 +516,11 @@ def api(
     log_config = LOGGING_CONFIG
     log_config["root"] = {"level": "INFO"}
 
-    uvicorn.run(app="datacontract.api:app", port=port, host=host, reload=True, log_config=LOGGING_CONFIG)
+    uvicorn_args = _get_uvicorn_arguments(port, host, ctx)
+    # Add the log config
+    uvicorn_args["log_config"] = log_config
+    # Run uvicorn
+    uvicorn.run(**uvicorn_args)
 
 
 def _print_logs(run):

{datacontract_cli-0.10.28 → datacontract_cli-0.10.30}/datacontract/data_contract.py

@@ -4,7 +4,7 @@ import typing
 from open_data_contract_standard.model import CustomProperty, OpenDataContractStandard
 
 from datacontract.export.odcs_v3_exporter import to_odcs_v3
-from datacontract.imports.importer import Spec
+from datacontract.imports.importer import ImportFormat, Spec
 from datacontract.imports.odcs_v3_importer import import_from_odcs
 
 if typing.TYPE_CHECKING:
@@ -300,7 +300,7 @@ class DataContract:
         id = kwargs.get("id")
         owner = kwargs.get("owner")
 
-        if spec == Spec.odcs:
+        if spec == Spec.odcs or format == ImportFormat.excel:
             data_contract_specification_initial = DataContract.init(template=template, schema=schema)
 
             odcs_imported = importer_factory.create(format).import_source(

{datacontract_cli-0.10.28 → datacontract_cli-0.10.30}/datacontract/engines/soda/connections/duckdb_connection.py

@@ -132,10 +132,10 @@ def setup_s3_connection(con, server):
     use_ssl = "true"
     url_style = "vhost"
     if server.endpointUrl is not None:
+        url_style = "path"
         s3_endpoint = server.endpointUrl.removeprefix("http://").removeprefix("https://")
         if server.endpointUrl.startswith("http://"):
             use_ssl = "false"
-            url_style = "path"
 
     if s3_access_key_id is not None:
         if s3_session_token is not None:

{datacontract_cli-0.10.28 → datacontract_cli-0.10.30}/datacontract/export/great_expectations_converter.py

@@ -14,9 +14,6 @@ from datacontract.export.exporter import (
     Exporter,
     _check_models_for_export,
 )
-from datacontract.export.pandas_type_converter import convert_to_pandas_type
-from datacontract.export.spark_converter import to_spark_data_type
-from datacontract.export.sql_type_converter import convert_to_sql_type
 from datacontract.model.data_contract_specification import (
     DataContractSpecification,
     DeprecatedQuality,
@@ -167,10 +164,16 @@ def add_field_expectations(
     """
     if field.type is not None:
         if engine == GreatExpectationsEngine.spark.value:
+            from datacontract.export.spark_converter import to_spark_data_type
+
             field_type = to_spark_data_type(field).__class__.__name__
         elif engine == GreatExpectationsEngine.pandas.value:
+            from datacontract.export.pandas_type_converter import convert_to_pandas_type
+
             field_type = convert_to_pandas_type(field)
         elif engine == GreatExpectationsEngine.sql.value:
+            from datacontract.export.sql_type_converter import convert_to_sql_type
+
             field_type = convert_to_sql_type(field, sql_server_type)
         else:
             field_type = field.type

{datacontract_cli-0.10.28 → datacontract_cli-0.10.30}/datacontract/export/markdown_converter.py

@@ -153,7 +153,7 @@ def field_to_markdown(field_name: str, field: Field, level: int = 0) -> str:
     Returns:
         str: A Markdown table rows for the field.
     """
-    tabs = " " * level
+    tabs = " " * level
     arrow = "↳" if level > 0 else ""
     column_name = f"{tabs}{arrow} {field_name}"
 

{datacontract_cli-0.10.28 → datacontract_cli-0.10.30}/datacontract/export/rdf_converter.py

@@ -57,8 +57,8 @@ def to_rdf(data_contract_spec: DataContractSpecification, base) -> Graph:
     else:
         g = Graph(base=Namespace(""))
 
-    dc = Namespace("https://datacontract.com/DataContractSpecification/1.1.0/")
-    dcx = Namespace("https://datacontract.com/DataContractSpecification/1.1.0/Extension/")
+    dc = Namespace("https://datacontract.com/DataContractSpecification/1.2.0/")
+    dcx = Namespace("https://datacontract.com/DataContractSpecification/1.2.0/Extension/")
 
     g.bind("dc", dc)
     g.bind("dcx", dcx)

{datacontract_cli-0.10.28 → datacontract_cli-0.10.30}/datacontract/export/sql_type_converter.py

@@ -194,8 +194,8 @@ def convert_to_databricks(field: Field) -> None | str:
         nested_fields = []
         for nested_field_name, nested_field in field.fields.items():
             nested_field_type = convert_to_databricks(nested_field)
-            nested_fields.append(f"{nested_field_name} {nested_field_type}")
-        return f"STRUCT<{', '.join(nested_fields)}>"
+            nested_fields.append(f"{nested_field_name}:{nested_field_type}")
+        return f"STRUCT<{','.join(nested_fields)}>"
     if type.lower() in ["bytes"]:
         return "BINARY"
     if type.lower() in ["array"]:

{datacontract_cli-0.10.28 → datacontract_cli-0.10.30}/datacontract/imports/excel_importer.py

@@ -568,6 +568,8 @@ def import_roles(workbook: Workbook) -> Optional[List[Role]]:
 
         roles_list = []
         for row_idx in range(roles_range[0], roles_range[1]):
+            if len(list(roles_sheet.rows)) < row_idx + 1:
+                break
             row = list(roles_sheet.rows)[row_idx]
 
             role_name = get_cell_value(row, headers.get("role"))
@@ -678,7 +680,7 @@ def import_servers(workbook) -> Optional[List[Server]]:
                 elif server_type == "databricks":
                     server.catalog = get_server_cell_value(workbook, sheet, "servers.databricks.catalog", index)
                     server.host = get_server_cell_value(workbook, sheet, "servers.databricks.host", index)
-                    server.schema = get_server_cell_value(workbook, sheet, "servers.databricks.schema", index)
+                    server.schema_ = get_server_cell_value(workbook, sheet, "servers.databricks.schema", index)
                 elif server_type == "glue":
                     server.account = get_server_cell_value(workbook, sheet, "servers.glue.account", index)
                     server.database = get_server_cell_value(workbook, sheet, "servers.glue.database", index)
@@ -692,7 +694,7 @@ def import_servers(workbook) -> Optional[List[Server]]:
                     server.database = get_server_cell_value(workbook, sheet, "servers.postgres.database", index)
                     server.host = get_server_cell_value(workbook, sheet, "servers.postgres.host", index)
                     server.port = get_server_cell_value(workbook, sheet, "servers.postgres.port", index)
-                    server.schema = get_server_cell_value(workbook, sheet, "servers.postgres.schema", index)
+                    server.schema_ = get_server_cell_value(workbook, sheet, "servers.postgres.schema", index)
                 elif server_type == "s3":
                     server.delimiter = get_server_cell_value(workbook, sheet, "servers.s3.delimiter", index)
                     server.endpointUrl = get_server_cell_value(workbook, sheet, "servers.s3.endpointUrl", index)
@@ -703,13 +705,13 @@ def import_servers(workbook) -> Optional[List[Server]]:
                     server.database = get_server_cell_value(workbook, sheet, "servers.snowflake.database", index)
                     server.host = get_server_cell_value(workbook, sheet, "servers.snowflake.host", index)
                     server.port = get_server_cell_value(workbook, sheet, "servers.snowflake.port", index)
-                    server.schema = get_server_cell_value(workbook, sheet, "servers.snowflake.schema", index)
+                    server.schema_ = get_server_cell_value(workbook, sheet, "servers.snowflake.schema", index)
                     server.warehouse = get_server_cell_value(workbook, sheet, "servers.snowflake.warehouse", index)
                 elif server_type == "sqlserver":
                     server.database = get_server_cell_value(workbook, sheet, "servers.sqlserver.database", index)
                     server.host = get_server_cell_value(workbook, sheet, "servers.sqlserver.host", index)
                     server.port = get_server_cell_value(workbook, sheet, "servers.sqlserver.port", index)
-                    server.schema = get_server_cell_value(workbook, sheet, "servers.sqlserver.schema", index)
+                    server.schema_ = get_server_cell_value(workbook, sheet, "servers.sqlserver.schema", index)
                 else:
                     # Custom server type - grab all possible fields
                     server.account = get_server_cell_value(workbook, sheet, "servers.custom.account", index)
@@ -724,7 +726,7 @@ def import_servers(workbook) -> Optional[List[Server]]:
                     server.path = get_server_cell_value(workbook, sheet, "servers.custom.path", index)
                     server.port = get_server_cell_value(workbook, sheet, "servers.custom.port", index)
                     server.project = get_server_cell_value(workbook, sheet, "servers.custom.project", index)
-                    server.schema = get_server_cell_value(workbook, sheet, "servers.custom.schema", index)
+                    server.schema_ = get_server_cell_value(workbook, sheet, "servers.custom.schema", index)
                     server.stagingDir = get_server_cell_value(workbook, sheet, "servers.custom.stagingDir", index)
                     server.table = get_server_cell_value(workbook, sheet, "servers.custom.table", index)
                     server.view = get_server_cell_value(workbook, sheet, "servers.custom.view", index)

{datacontract_cli-0.10.28 → datacontract_cli-0.10.30}/datacontract/imports/importer.py

@@ -26,6 +26,7 @@ class ImportFormat(str, Enum):
     dbml = "dbml"
     glue = "glue"
     jsonschema = "jsonschema"
+    json = "json"
     bigquery = "bigquery"
     odcs = "odcs"
     unity = "unity"

{datacontract_cli-0.10.28 → datacontract_cli-0.10.30}/datacontract/imports/importer_factory.py

@@ -119,3 +119,10 @@ importer_factory.register_lazy_importer(
     module_path="datacontract.imports.excel_importer",
     class_name="ExcelImporter",
 )
+
+
+importer_factory.register_lazy_importer(
+    name=ImportFormat.json,
+    module_path="datacontract.imports.json_importer",
+    class_name="JsonImporter",
+)