datacontract-cli 0.10.30__tar.gz → 0.10.31__tar.gz

{datacontract_cli-0.10.30/datacontract_cli.egg-info → datacontract_cli-0.10.31}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datacontract-cli
-Version: 0.10.30
+Version: 0.10.31
 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
@@ -1018,8 +1018,6 @@ If using Databricks, and an error is thrown when trying to deploy the SQL DDLs w
 
 ```shell
 spark.conf.set(“spark.databricks.delta.schema.typeCheck.enabled”, “false”)
-from datacontract.model import data_contract_specification
-data_contract_specification.DATACONTRACT_TYPES.append(“variant”)
 ```
 
 #### Great Expectations
@@ -2083,7 +2081,6 @@ 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-0.10.30 → datacontract_cli-0.10.31}/README.md

@@ -924,8 +924,6 @@ If using Databricks, and an error is thrown when trying to deploy the SQL DDLs w
 
 ```shell
 spark.conf.set(“spark.databricks.delta.schema.typeCheck.enabled”, “false”)
-from datacontract.model import data_contract_specification
-data_contract_specification.DATACONTRACT_TYPES.append(“variant”)
 ```
 
 #### Great Expectations
@@ -1989,7 +1987,6 @@ 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-0.10.30 → datacontract_cli-0.10.31}/datacontract/export/spark_converter.py

@@ -126,6 +126,8 @@ def to_spark_data_type(field: Field) -> types.DataType:
         return types.StructType(to_struct_type(field.fields))
     if field_type == "map":
         return types.MapType(to_spark_data_type(field.keys), to_spark_data_type(field.values))
+    if field_type == "variant":
+        return types.VariantType()
     if field_type in ["string", "varchar", "text"]:
         return types.StringType()
     if field_type in ["number", "decimal", "numeric"]:
@@ -150,7 +152,7 @@ def to_spark_data_type(field: Field) -> types.DataType:
         return types.DateType()
     if field_type == "bytes":
         return types.BinaryType()
-    return types.BinaryType()
+    return types.StringType() # default if no condition is met
 
 
 def print_schema(dtype: types.DataType) -> str:

{datacontract_cli-0.10.30 → datacontract_cli-0.10.31}/datacontract/imports/sql_importer.py

@@ -230,6 +230,8 @@ def map_type_from_sql(sql_type: str) -> str | None:
         return "int"
     elif sql_type_normed.startswith("float"):
         return "float"
+    elif sql_type_normed.startswith("double"):
+        return "double"
     elif sql_type_normed.startswith("decimal"):
         return "decimal"
     elif sql_type_normed.startswith("numeric"):

{datacontract_cli-0.10.30 → datacontract_cli-0.10.31}/datacontract/imports/unity_importer.py

@@ -200,7 +200,8 @@ def import_table_fields(columns: List[ColumnInfo]) -> dict[str, Field]:
 
 def _to_field(column: ColumnInfo) -> Field:
     field = Field()
-    if column.type_name is not None:
+    # The second condition evaluates for complex types (e.g. variant)
+    if column.type_name is not None or (column.type_name is None and column.type_text is not None):
         sql_type = str(column.type_text)
         field.type = map_type_from_sql(sql_type)
     physical_type_key = to_physical_type_key("databricks")

{datacontract_cli-0.10.30 → datacontract_cli-0.10.31/datacontract_cli.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datacontract-cli
-Version: 0.10.30
+Version: 0.10.31
 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
@@ -1018,8 +1018,6 @@ If using Databricks, and an error is thrown when trying to deploy the SQL DDLs w
 
 ```shell
 spark.conf.set(“spark.databricks.delta.schema.typeCheck.enabled”, “false”)
-from datacontract.model import data_contract_specification
-data_contract_specification.DATACONTRACT_TYPES.append(“variant”)
 ```
 
 #### Great Expectations
@@ -2083,7 +2081,6 @@ 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-0.10.30 → datacontract_cli-0.10.31}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "datacontract-cli"
-version = "0.10.30"
+version = "0.10.31"
 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"

{datacontract_cli-0.10.30 → datacontract_cli-0.10.31}/tests/test_import_spark.py

@@ -162,4 +162,4 @@ def test_prog(spark: SparkSession, df_user, user_datacontract_no_desc, user_data
 
     # does include a table level description (dataframe object method)
     result4 = DataContract().import_from_source("spark", "users", dataframe=df_user, description="description")
-    assert yaml.safe_load(result4.to_yaml()) == yaml.safe_load(expected_desc)
+    assert yaml.safe_load(result4.to_yaml()) == yaml.safe_load(expected_desc)