datacontract-cli 0.10.29__tar.gz → 0.10.30__tar.gz

{datacontract_cli-0.10.29/datacontract_cli.egg-info → datacontract_cli-0.10.30}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datacontract-cli
-Version: 0.10.29
+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
@@ -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<0.58.0; 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==0.9.1; extra == "iceberg"
@@ -54,7 +54,7 @@ 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]<3.16,>=3.6; extra == "snowflake"
 Requires-Dist: soda-core-snowflake<3.6.0,>=3.3.20; extra == "snowflake"
@@ -71,7 +71,7 @@ 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==0.115.14; 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"
@@ -86,7 +86,7 @@ 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==2.3.6; 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==0.335.0; extra == "dev"

{datacontract_cli-0.10.29 → 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-0.10.29 → 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-0.10.29 → 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-0.10.29 → datacontract_cli-0.10.30}/datacontract/imports/excel_importer.py

@@ -680,7 +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)
@@ -694,7 +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)
@@ -705,13 +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)
@@ -726,7 +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-0.10.29 → datacontract_cli-0.10.30/datacontract_cli.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datacontract-cli
-Version: 0.10.29
+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
@@ -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<0.58.0; 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==0.9.1; extra == "iceberg"
@@ -54,7 +54,7 @@ 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]<3.16,>=3.6; extra == "snowflake"
 Requires-Dist: soda-core-snowflake<3.6.0,>=3.3.20; extra == "snowflake"
@@ -71,7 +71,7 @@ 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==0.115.14; 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"
@@ -86,7 +86,7 @@ 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==2.3.6; 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==0.335.0; extra == "dev"

{datacontract_cli-0.10.29 → datacontract_cli-0.10.30}/datacontract_cli.egg-info/SOURCES.txt

@@ -193,6 +193,7 @@ tests/test_test_bigquery.py
 tests/test_test_databricks.py
 tests/test_test_dataframe.py
 tests/test_test_delta.py
+tests/test_test_gcs_csv_remote.py
 tests/test_test_gcs_json_remote.py
 tests/test_test_kafka.py
 tests/test_test_kafka_remote.py

{datacontract_cli-0.10.29 → datacontract_cli-0.10.30}/datacontract_cli.egg-info/requires.txt

@@ -1,4 +1,4 @@
-typer<0.16,>=0.15.1
+typer<0.17,>=0.15.1
 pydantic<2.12.0,>=2.8.2
 pyyaml~=6.0.1
 requests<2.33,>=2.31
@@ -22,7 +22,7 @@ open-data-contract-standard<4.0.0,>=3.0.4
 datacontract-cli[api,bigquery,csv,databricks,dbml,dbt,excel,iceberg,kafka,parquet,postgres,protobuf,rdf,s3,snowflake,sqlserver,trino]
 
 [api]
-fastapi==0.115.14
+fastapi==0.116.1
 uvicorn==0.35.0
 
 [avro]
@@ -38,7 +38,7 @@ pandas>=2.0.0
 soda-core-spark-df<3.6.0,>=3.3.20
 soda-core-spark[databricks]<3.6.0,>=3.3.20
 databricks-sql-connector<4.1.0,>=3.7.0
-databricks-sdk<0.58.0
+databricks-sdk<0.59.0
 pyspark<4.0.0,>=3.5.5
 
 [dbml]
@@ -56,7 +56,7 @@ pandas>=2.1.0
 pre-commit<4.3.0,>=3.7.1
 pytest
 pytest-xdist
-pymssql==2.3.6
+pymssql==2.3.7
 ruff
 testcontainers[kafka,minio,mssql,postgres]==4.10.0
 trino==0.335.0
@@ -86,7 +86,7 @@ rdflib==7.0.0
 
 [s3]
 s3fs<2026.0.0,>=2025.2.0
-aiobotocore<2.23.0,>=2.17.0
+aiobotocore<2.24.0,>=2.17.0
 
 [snowflake]
 snowflake-connector-python[pandas]<3.16,>=3.6

{datacontract_cli-0.10.29 → datacontract_cli-0.10.30}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "datacontract-cli"
-version = "0.10.29"
+version = "0.10.30"
 description = "The datacontract CLI is an open source command-line tool for working with Data Contracts. It uses data contract YAML files to lint the data contract, connect to data sources and execute schema and quality tests, detect breaking changes, and export to different formats. The tool is written in Python. It can be used as a standalone CLI tool, in a CI/CD pipeline, or directly as a Python library."
 license = "MIT"
 readme = "README.md"
@@ -15,7 +15,7 @@ classifiers = [
 ]
 requires-python = ">=3.10"
 dependencies = [
-  "typer>=0.15.1,<0.16",
+  "typer>=0.15.1,<0.17",
   "pydantic>=2.8.2,<2.12.0",
   "pyyaml~=6.0.1",
   "requests>=2.31,<2.33",
@@ -60,7 +60,7 @@ databricks = [
   "soda-core-spark-df>=3.3.20,<3.6.0",
   "soda-core-spark[databricks]>=3.3.20,<3.6.0",
   "databricks-sql-connector>=3.7.0,<4.1.0",
-  "databricks-sdk<0.58.0",
+  "databricks-sdk<0.59.0",
   "pyspark>=3.5.5,<4.0.0",
 ]
 
@@ -80,7 +80,7 @@ postgres = [
 
 s3 = [
   "s3fs>=2025.2.0,<2026.0.0",
-  "aiobotocore>=2.17.0,<2.23.0",
+  "aiobotocore>=2.17.0,<2.24.0",
 ]
 
 snowflake = [
@@ -113,7 +113,7 @@ rdf = [
 ]
 
 api = [
-  "fastapi==0.115.14",
+  "fastapi==0.116.1",
   "uvicorn==0.35.0",
 ]
 
@@ -135,7 +135,7 @@ dev = [
   "pre-commit>=3.7.1,<4.3.0",
   "pytest",
   "pytest-xdist",
-  "pymssql==2.3.6",
+  "pymssql==2.3.7",
   "ruff",
   "testcontainers[minio,postgres,kafka,mssql]==4.10.0",
   "trino==0.335.0",

{datacontract_cli-0.10.29 → datacontract_cli-0.10.30}/tests/test_import_excel.py

@@ -23,6 +23,7 @@ def test_cli():
         ],
     )
     assert result.exit_code == 0
+    assert "kind: DataContract" in result.stdout
 
 
 def test_import_excel_odcs():

datacontract_cli-0.10.30/tests/test_test_gcs_csv_remote.py

@@ -0,0 +1,45 @@
+import os
+
+import pytest
+from dotenv import load_dotenv
+
+from datacontract.data_contract import DataContract
+
+datacontract = "fixtures/gcs-csv-remote/datacontract.yaml"
+load_dotenv(override=True)
+
+
+@pytest.mark.skipif(
+    os.environ.get("DATACONTRACT_GCS_KEY_ID") is None or os.environ.get("DATACONTRACT_GCS_SECRET") is None,
+    reason="Requires DATACONTRACT_GCS_KEY_ID, and DATACONTRACT_GCS_SECRET to be set",
+)
+def test_test_gcs_csv_remote_gcs_url():
+    data_contract = DataContract(
+        data_contract_file=datacontract,
+        server="gcs-url",
+    )
+
+    run = data_contract.test()
+
+    print(run)
+    assert run.result == "passed"
+
+
+@pytest.mark.skipif(
+    os.environ.get("DATACONTRACT_GCS_KEY_ID") is None or os.environ.get("DATACONTRACT_GCS_SECRET") is None,
+    reason="Requires DATACONTRACT_GCS_KEY_ID, and DATACONTRACT_GCS_SECRET to be set",
+)
+def test_test_gcs_csv_remote_s3_style(monkeypatch):
+    monkeypatch.setenv("DATACONTRACT_S3_ACCESS_KEY_ID", os.environ.get("DATACONTRACT_GCS_KEY_ID"))
+    monkeypatch.setenv("DATACONTRACT_S3_SECRET_ACCESS_KEY", os.environ.get("DATACONTRACT_GCS_SECRET"))
+
+    data_contract = DataContract(
+        data_contract_file=datacontract,
+        server="s3-style",
+    )
+
+    run = data_contract.test()
+
+    print(run)
+    assert run.result == "passed"
+    assert all(check.result == "passed" for check in run.checks)

{datacontract_cli-0.10.29 → datacontract_cli-0.10.30}/tests/test_test_s3_csv.py

@@ -33,6 +33,7 @@ def test_test_s3_csv(minio_container, monkeypatch):
     print(run)
     assert run.result == "passed"
     assert all(check.result == "passed" for check in run.checks)
+    assert 8 == len(run.checks), "Expected 5 checks to be executed"
 
 
 def _prepare_s3_files(minio_container):