datacontract-cli 0.10.34__tar.gz → 0.10.35__tar.gz

{datacontract_cli-0.10.34/datacontract_cli.egg-info → datacontract_cli-0.10.35}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datacontract-cli
-Version: 0.10.34
+Version: 0.10.35
 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
@@ -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<0.61.0; extra == "databricks"
+Requires-Dist: databricks-sdk<0.64.0; 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<2.24.0,>=2.17.0; 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: soda-core-snowflake<3.6.0,>=3.3.20; extra == "snowflake"
@@ -83,15 +83,15 @@ 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==5.1.8; extra == "dev"
+Requires-Dist: moto==5.1.10; extra == "dev"
 Requires-Dist: pandas>=2.1.0; extra == "dev"
-Requires-Dist: pre-commit<4.3.0,>=3.7.1; extra == "dev"
+Requires-Dist: pre-commit<4.4.0,>=3.7.1; extra == "dev"
 Requires-Dist: pytest; extra == "dev"
 Requires-Dist: pytest-xdist; extra == "dev"
 Requires-Dist: pymssql==2.3.7; extra == "dev"
 Requires-Dist: ruff; extra == "dev"
 Requires-Dist: testcontainers[kafka,minio,mssql,postgres]==4.12.0; extra == "dev"
-Requires-Dist: trino==0.335.0; extra == "dev"
+Requires-Dist: trino==0.336.0; extra == "dev"
 Dynamic: license-file
 
 # Data Contract CLI
@@ -257,6 +257,14 @@ if not run.has_passed():
 
 Choose the most appropriate installation method for your needs:
 
+### uv
+
+If you have [uv](https://docs.astral.sh/uv/) installed, you can run datacontract-cli directly without installing:
+
+```
+uv run --with 'datacontract-cli[all]' datacontract --version
+```
+
 ### pip
 Python 3.10, 3.11, and 3.12 are supported. We recommend to use Python 3.11.
 
@@ -1011,7 +1019,7 @@ models:
 │                      terraform|avro-idl|sql|sql-query|mer                                        │
 │                      maid|html|go|bigquery|dbml|spark|sql                                        │
 │                      alchemy|data-caterer|dcs|markdown|ic                                        │
-│                      eberg|custom|excel]                                                         │
+│                      eberg|custom|excel|dqx]                                                         │
 │    --output          PATH                                  Specify the file path where the       │
 │                                                            exported data will be saved. If no    │
 │                                                            path is provided, the output will be  │
@@ -1057,35 +1065,36 @@ datacontract export --format html --output datacontract.html
 
 Available export options:
 
-| Type                 | Description                                             | Status |
-|----------------------|---------------------------------------------------------|--------|
-| `html`               | Export to HTML                                          | ✅      |
-| `jsonschema`         | Export to JSON Schema                                   | ✅      |
-| `odcs`               | Export to Open Data Contract Standard (ODCS) V3         | ✅      |
-| `sodacl`             | Export to SodaCL quality checks in YAML format          | ✅      |
-| `dbt`                | Export to dbt models in YAML format                     | ✅      |
-| `dbt-sources`        | Export to dbt sources in YAML format                    | ✅      |
-| `dbt-staging-sql`    | Export to dbt staging SQL models                        | ✅      |
-| `rdf`                | Export data contract to RDF representation in N3 format | ✅      |
-| `avro`               | Export to AVRO models                                   | ✅      |
-| `protobuf`           | Export to Protobuf                                      | ✅      |
-| `terraform`          | Export to terraform resources                           | ✅      |
-| `sql`                | Export to SQL DDL                                       | ✅      |
-| `sql-query`          | Export to SQL Query                                     | ✅      |
-| `great-expectations` | Export to Great Expectations Suites in JSON Format      | ✅      |
-| `bigquery`           | Export to BigQuery Schemas                              | ✅      |
-| `go`                 | Export to Go types                                      | ✅      |
-| `pydantic-model`     | Export to pydantic models                               | ✅      |
-| `DBML`               | Export to a DBML Diagram description                    | ✅      |
-| `spark`              | Export to a Spark StructType                            | ✅      |
-| `sqlalchemy`         | Export to SQLAlchemy Models                             | ✅      |
-| `data-caterer`       | Export to Data Caterer in YAML format                   | ✅      |
-| `dcs`                | Export to Data Contract Specification in YAML format    | ✅      |
-| `markdown`           | Export to Markdown                                      | ✅      |
+| Type                 | Description                                             | Status  |
+|----------------------|---------------------------------------------------------|---------|
+| `html`               | Export to HTML                                          | ✅       |
+| `jsonschema`         | Export to JSON Schema                                   | ✅       |
+| `odcs`               | Export to Open Data Contract Standard (ODCS) V3         | ✅       |
+| `sodacl`             | Export to SodaCL quality checks in YAML format          | ✅       |
+| `dbt`                | Export to dbt models in YAML format                     | ✅       |
+| `dbt-sources`        | Export to dbt sources in YAML format                    | ✅       |
+| `dbt-staging-sql`    | Export to dbt staging SQL models                        | ✅       |
+| `rdf`                | Export data contract to RDF representation in N3 format | ✅       |
+| `avro`               | Export to AVRO models                                   | ✅       |
+| `protobuf`           | Export to Protobuf                                      | ✅       |
+| `terraform`          | Export to terraform resources                           | ✅       |
+| `sql`                | Export to SQL DDL                                       | ✅       |
+| `sql-query`          | Export to SQL Query                                     | ✅       |
+| `great-expectations` | Export to Great Expectations Suites in JSON Format      | ✅       |
+| `bigquery`           | Export to BigQuery Schemas                              | ✅       |
+| `go`                 | Export to Go types                                      | ✅       |
+| `pydantic-model`     | Export to pydantic models                               | ✅       |
+| `DBML`               | Export to a DBML Diagram description                    | ✅       |
+| `spark`              | Export to a Spark StructType                            | ✅       |
+| `sqlalchemy`         | Export to SQLAlchemy Models                             | ✅       |
+| `data-caterer`       | Export to Data Caterer in YAML format                   | ✅       |
+| `dcs`                | Export to Data Contract Specification in YAML format    | ✅       |
+| `markdown`           | Export to Markdown                                      | ✅       |
 | `iceberg`            | Export to an Iceberg JSON Schema Definition             | partial |
-| `excel`              | Export to ODCS Excel Template                           | ✅      |
-| `custom`             | Export to Custom format with Jinja                      | ✅      |
-| Missing something?   | Please create an issue on GitHub                        | TBD    |
+| `excel`              | Export to ODCS Excel Template                           | ✅       |
+| `custom`             | Export to Custom format with Jinja                      | ✅       |
+| `dqx`                | Export to DQX in YAML format                            | ✅       |
+| Missing something?   | Please create an issue on GitHub                        | TBD     |
 
 #### SQL
 

{datacontract_cli-0.10.34 → datacontract_cli-0.10.35}/README.md

@@ -161,6 +161,14 @@ if not run.has_passed():
 
 Choose the most appropriate installation method for your needs:
 
+### uv
+
+If you have [uv](https://docs.astral.sh/uv/) installed, you can run datacontract-cli directly without installing:
+
+```
+uv run --with 'datacontract-cli[all]' datacontract --version
+```
+
 ### pip
 Python 3.10, 3.11, and 3.12 are supported. We recommend to use Python 3.11.
 
@@ -915,7 +923,7 @@ models:
 │                      terraform|avro-idl|sql|sql-query|mer                                        │
 │                      maid|html|go|bigquery|dbml|spark|sql                                        │
 │                      alchemy|data-caterer|dcs|markdown|ic                                        │
-│                      eberg|custom|excel]                                                         │
+│                      eberg|custom|excel|dqx]                                                         │
 │    --output          PATH                                  Specify the file path where the       │
 │                                                            exported data will be saved. If no    │
 │                                                            path is provided, the output will be  │
@@ -961,35 +969,36 @@ datacontract export --format html --output datacontract.html
 
 Available export options:
 
-| Type                 | Description                                             | Status |
-|----------------------|---------------------------------------------------------|--------|
-| `html`               | Export to HTML                                          | ✅      |
-| `jsonschema`         | Export to JSON Schema                                   | ✅      |
-| `odcs`               | Export to Open Data Contract Standard (ODCS) V3         | ✅      |
-| `sodacl`             | Export to SodaCL quality checks in YAML format          | ✅      |
-| `dbt`                | Export to dbt models in YAML format                     | ✅      |
-| `dbt-sources`        | Export to dbt sources in YAML format                    | ✅      |
-| `dbt-staging-sql`    | Export to dbt staging SQL models                        | ✅      |
-| `rdf`                | Export data contract to RDF representation in N3 format | ✅      |
-| `avro`               | Export to AVRO models                                   | ✅      |
-| `protobuf`           | Export to Protobuf                                      | ✅      |
-| `terraform`          | Export to terraform resources                           | ✅      |
-| `sql`                | Export to SQL DDL                                       | ✅      |
-| `sql-query`          | Export to SQL Query                                     | ✅      |
-| `great-expectations` | Export to Great Expectations Suites in JSON Format      | ✅      |
-| `bigquery`           | Export to BigQuery Schemas                              | ✅      |
-| `go`                 | Export to Go types                                      | ✅      |
-| `pydantic-model`     | Export to pydantic models                               | ✅      |
-| `DBML`               | Export to a DBML Diagram description                    | ✅      |
-| `spark`              | Export to a Spark StructType                            | ✅      |
-| `sqlalchemy`         | Export to SQLAlchemy Models                             | ✅      |
-| `data-caterer`       | Export to Data Caterer in YAML format                   | ✅      |
-| `dcs`                | Export to Data Contract Specification in YAML format    | ✅      |
-| `markdown`           | Export to Markdown                                      | ✅      |
+| Type                 | Description                                             | Status  |
+|----------------------|---------------------------------------------------------|---------|
+| `html`               | Export to HTML                                          | ✅       |
+| `jsonschema`         | Export to JSON Schema                                   | ✅       |
+| `odcs`               | Export to Open Data Contract Standard (ODCS) V3         | ✅       |
+| `sodacl`             | Export to SodaCL quality checks in YAML format          | ✅       |
+| `dbt`                | Export to dbt models in YAML format                     | ✅       |
+| `dbt-sources`        | Export to dbt sources in YAML format                    | ✅       |
+| `dbt-staging-sql`    | Export to dbt staging SQL models                        | ✅       |
+| `rdf`                | Export data contract to RDF representation in N3 format | ✅       |
+| `avro`               | Export to AVRO models                                   | ✅       |
+| `protobuf`           | Export to Protobuf                                      | ✅       |
+| `terraform`          | Export to terraform resources                           | ✅       |
+| `sql`                | Export to SQL DDL                                       | ✅       |
+| `sql-query`          | Export to SQL Query                                     | ✅       |
+| `great-expectations` | Export to Great Expectations Suites in JSON Format      | ✅       |
+| `bigquery`           | Export to BigQuery Schemas                              | ✅       |
+| `go`                 | Export to Go types                                      | ✅       |
+| `pydantic-model`     | Export to pydantic models                               | ✅       |
+| `DBML`               | Export to a DBML Diagram description                    | ✅       |
+| `spark`              | Export to a Spark StructType                            | ✅       |
+| `sqlalchemy`         | Export to SQLAlchemy Models                             | ✅       |
+| `data-caterer`       | Export to Data Caterer in YAML format                   | ✅       |
+| `dcs`                | Export to Data Contract Specification in YAML format    | ✅       |
+| `markdown`           | Export to Markdown                                      | ✅       |
 | `iceberg`            | Export to an Iceberg JSON Schema Definition             | partial |
-| `excel`              | Export to ODCS Excel Template                           | ✅      |
-| `custom`             | Export to Custom format with Jinja                      | ✅      |
-| Missing something?   | Please create an issue on GitHub                        | TBD    |
+| `excel`              | Export to ODCS Excel Template                           | ✅       |
+| `custom`             | Export to Custom format with Jinja                      | ✅       |
+| `dqx`                | Export to DQX in YAML format                            | ✅       |
+| Missing something?   | Please create an issue on GitHub                        | TBD     |
 
 #### SQL
 

{datacontract_cli-0.10.34 → datacontract_cli-0.10.35}/datacontract/api.py

@@ -162,15 +162,22 @@ async def test(
     server: Annotated[
         str | None,
         Query(
-            examples=["production"],
             description="The server name to test. Optional, if there is only one server.",
+            examples=["production"],
+        ),
+    ] = None,
+    publish_url: Annotated[
+        str | None,
+        Query(
+            description="URL to publish test results. Optional, if you want to publish the test results to a Data Mesh Manager or Data Contract Manager. Example: https://api.datamesh-manager.com/api/test-results",
+            examples=["https://api.datamesh-manager.com/api/test-results"],
         ),
     ] = None,
 ) -> Run:
     check_api_key(api_key)
     logging.info("Testing data contract...")
     logging.info(body)
-    return DataContract(data_contract_str=body, server=server).test()
+    return DataContract(data_contract_str=body, server=server, publish_url=publish_url).test()
 
 
 @app.post(

{datacontract_cli-0.10.34 → datacontract_cli-0.10.35}/datacontract/cli.py

@@ -126,8 +126,10 @@ def test(
             "servers (default)."
         ),
     ] = "all",
-    publish_test_results: Annotated[bool, typer.Option(help="Publish the results after the test")] = False,
-    publish: Annotated[str, typer.Option(help="DEPRECATED. The url to publish the results after the test.")] = None,
+    publish_test_results: Annotated[
+        bool, typer.Option(help="Deprecated. Use publish parameter. Publish the results after the test")
+    ] = False,
+    publish: Annotated[str, typer.Option(help="The url to publish the results after the test.")] = None,
     output: Annotated[
         Path,
         typer.Option(

{datacontract_cli-0.10.34 → datacontract_cli-0.10.35}/datacontract/engines/fastjsonschema/check_jsonschema.py

@@ -1,8 +1,9 @@
+import glob
 import json
 import logging
 import os
 import threading
-from typing import List, Optional
+from typing import Any, Callable, Generator, List, Optional
 
 import fastjsonschema
 from fastjsonschema import JsonSchemaValueException
@@ -85,7 +86,7 @@ def process_exceptions(run, exceptions: List[DataContractException]):
 
 
 def validate_json_stream(
-    schema: dict, model_name: str, validate: callable, json_stream: list[dict]
+    schema: dict, model_name: str, validate: Callable, json_stream: Generator[Any, Any, None]
 ) -> List[DataContractException]:
     logging.info(f"Validating JSON stream for model: '{model_name}'.")
     exceptions: List[DataContractException] = []
@@ -99,7 +100,7 @@ def validate_json_stream(
                 DataContractException(
                     type="schema",
                     name="Check that JSON has valid schema",
-                    result="failed",
+                    result=ResultEnum.failed,
                     reason=f"{f'#{primary_key_value}: ' if primary_key_value is not None else ''}{e.message}",
                     model=model_name,
                     engine="jsonschema",
@@ -170,24 +171,33 @@ def process_local_file(run, server, schema, model_name, validate):
     if "{model}" in path:
         path = path.format(model=model_name)
 
+    all_files = []
     if os.path.isdir(path):
-        return process_directory(run, path, server, model_name, validate)
+        # Fetch all JSONs in the directory
+        for root, _, files in os.walk(path):
+            for file in files:
+                if file.endswith(".json"):
+                    all_files.append(os.path.join(root, file))
     else:
-        logging.info(f"Processing file {path}")
-        with open(path, "r") as file:
-            process_json_file(run, schema, model_name, validate, file, server.delimiter)
+        # Use glob to fetch all JSONs
+        for file_path in glob.glob(path, recursive=True):
+            if os.path.isfile(file_path):
+                if file_path.endswith(".json"):
+                    all_files.append(file_path)
 
+    if not all_files:
+        raise DataContractException(
+            type="schema",
+            name="Check that JSON has valid schema",
+            result=ResultEnum.warning,
+            reason=f"No files found in '{path}'.",
+            engine="datacontract",
+        )
 
-def process_directory(run, path, server, model_name, validate):
-    success = True
-    for filename in os.listdir(path):
-        if filename.endswith(".json"):  # or make this a parameter
-            file_path = os.path.join(path, filename)
-            with open(file_path, "r") as file:
-                if not process_json_file(run, model_name, validate, file, server.delimiter):
-                    success = False
-                    break
-    return success
+    for file in all_files:
+        logging.info(f"Processing file: {file}")
+        with open(file, "r") as f:
+            process_json_file(run, schema, model_name, validate, f, server.delimiter)
 
 
 def process_s3_file(run, server, schema, model_name, validate):
@@ -209,7 +219,7 @@ def process_s3_file(run, server, schema, model_name, validate):
         raise DataContractException(
             type="schema",
             name="Check that JSON has valid schema",
-            result="warning",
+            result=ResultEnum.warning,
             reason=f"Cannot find any file in {s3_location}",
             engine="datacontract",
         )
@@ -230,7 +240,7 @@ def check_jsonschema(run: Run, data_contract: DataContractSpecification, server:
             Check(
                 type="schema",
                 name="Check that JSON has valid schema",
-                result="warning",
+                result=ResultEnum.warning,
                 reason="Server format is not 'json'. Skip validating jsonschema.",
                 engine="jsonschema",
             )

datacontract_cli-0.10.35/datacontract/export/dqx_converter.py

@@ -0,0 +1,121 @@
+from typing import Any, Dict, List, Union
+
+import yaml
+
+from datacontract.export.exporter import Exporter, _check_models_for_export
+from datacontract.model.data_contract_specification import DataContractSpecification, Field, Model, Quality
+
+
+class DqxKeys:
+    CHECK = "check"
+    ARGUMENTS = "arguments"
+    SPECIFICATION = "specification"
+    COL_NAME = "column"
+    COL_NAMES = "for_each_column"
+    COLUMNS = "columns"
+    FUNCTION = "function"
+
+
+class DqxExporter(Exporter):
+    """Exporter implementation for converting data contracts to DQX YAML file."""
+
+    def export(
+        self,
+        data_contract: DataContractSpecification,
+        model: Model,
+        server: str,
+        sql_server_type: str,
+        export_args: Dict[str, Any],
+    ) -> str:
+        """Exports a data contract to DQX format."""
+        model_name, model_value = _check_models_for_export(data_contract, model, self.export_format)
+        return to_dqx_yaml(model_value)
+
+
+def to_dqx_yaml(model_value: Model) -> str:
+    """
+    Converts the data contract's quality checks to DQX YAML format.
+
+    Args:
+        model_value (Model): The data contract to convert.
+
+    Returns:
+        str: YAML representation of the data contract's quality checks.
+    """
+    extracted_rules = extract_quality_rules(model_value)
+    return yaml.dump(extracted_rules, sort_keys=False, allow_unicode=True, default_flow_style=False)
+
+
+def process_quality_rule(rule: Quality, column_name: str) -> Dict[str, Any]:
+    """
+    Processes a single quality rule by injecting the column path into its arguments if absent.
+
+    Args:
+        rule (Quality): The quality rule to process.
+        column_name (str): The full path to the current column.
+
+    Returns:
+        dict: The processed quality rule specification.
+    """
+    rule_data = rule.model_extra
+    specification = rule_data[DqxKeys.SPECIFICATION]
+    check = specification[DqxKeys.CHECK]
+
+    arguments = check.setdefault(DqxKeys.ARGUMENTS, {})
+
+    if DqxKeys.COL_NAME not in arguments and DqxKeys.COL_NAMES not in arguments and DqxKeys.COLUMNS not in arguments:
+        if check[DqxKeys.FUNCTION] not in ("is_unique", "foreign_key"):
+            arguments[DqxKeys.COL_NAME] = column_name
+        else:
+            arguments[DqxKeys.COLUMNS] = [column_name]
+
+    return specification
+
+
+def extract_quality_rules(data: Union[Model, Field, Quality], column_path: str = "") -> List[Dict[str, Any]]:
+    """
+    Recursively extracts all quality rules from a data contract structure.
+
+    Args:
+        data (Union[Model, Field, Quality]): The data contract model, field, or quality rule.
+        column_path (str, optional): The current path in the schema hierarchy. Defaults to "".
+
+    Returns:
+        List[Dict[str, Any]]: A list of quality rule specifications.
+    """
+    quality_rules = []
+
+    if isinstance(data, Quality):
+        return [process_quality_rule(data, column_path)]
+
+    if isinstance(data, (Model, Field)):
+        for key, field in data.fields.items():
+            current_path = build_column_path(column_path, key)
+
+            if field.fields:
+                # Field is a struct-like object, recurse deeper
+                quality_rules.extend(extract_quality_rules(field, current_path))
+            else:
+                # Process quality rules at leaf fields
+                for rule in field.quality:
+                    quality_rules.append(process_quality_rule(rule, current_path))
+
+        # Process any quality rules attached directly to this level
+        for rule in data.quality:
+            quality_rules.append(process_quality_rule(rule, column_path))
+
+    return quality_rules
+
+
+def build_column_path(current_path: str, key: str) -> str:
+    """
+    Builds the full column path by concatenating parent path with current key.
+
+    Args:
+        current_path (str): The current path prefix.
+        key (str): The current field's key.
+
+    Returns:
+        str: The full path.
+    """
+    return f"{current_path}.{key}" if current_path else key

{datacontract_cli-0.10.34 → datacontract_cli-0.10.35}/datacontract/export/exporter.py

@@ -46,6 +46,7 @@ class ExportFormat(str, Enum):
     iceberg = "iceberg"
     custom = "custom"
     excel = "excel"
+    dqx = "dqx"
 
     @classmethod
     def get_supported_formats(cls):

{datacontract_cli-0.10.34 → datacontract_cli-0.10.35}/datacontract/export/exporter_factory.py

@@ -197,6 +197,12 @@ exporter_factory.register_lazy_exporter(
     class_name="MarkdownExporter",
 )
 
+exporter_factory.register_lazy_exporter(
+    name=ExportFormat.dqx,
+    module_path="datacontract.export.dqx_converter",
+    class_name="DqxExporter",
+)
+
 exporter_factory.register_lazy_exporter(
     name=ExportFormat.iceberg, module_path="datacontract.export.iceberg_converter", class_name="IcebergExporter"
 )

{datacontract_cli-0.10.34 → datacontract_cli-0.10.35}/datacontract/export/mermaid_exporter.py

@@ -27,31 +27,33 @@ def dcs_to_mermaid(data_contract_spec: DataContractSpecification) -> str | None:
         mmd_references = []
 
         for model_name, model in data_contract_spec.models.items():
+            clean_model = _sanitize_name(model_name)
             entity_block = ""
 
             for field_name, field in model.fields.items():
                 clean_name = _sanitize_name(field_name)
-                indicators = ""
+                field_type = field.type or "unknown"
 
-                if field.primaryKey or (field.unique and field.required):
-                    indicators += "🔑"
-                if field.references:
-                    indicators += "⌘"
+                is_pk = bool(field.primaryKey or (field.unique and field.required))
+                is_fk = bool(field.references)
 
-                field_type = field.type or "unknown"
-                entity_block += f"\t{clean_name}{indicators} {field_type}\n"
+                entity_block += _field_line(clean_name, field_type, pk=is_pk, uk=bool(field.unique), fk=is_fk)
 
                 if field.references:
-                    referenced_model = field.references.split(".")[0] if "." in field.references else ""
+                    references = field.references.replace(".", "·")
+                    parts = references.split("·")
+                    referenced_model = _sanitize_name(parts[0]) if len(parts) > 0 else ""
+                    referenced_field = _sanitize_name(parts[1]) if len(parts) > 1 else ""
                     if referenced_model:
-                        mmd_references.append(f'"📑{referenced_model}"' + "}o--{ ||" + f'"📑{model_name}"')
+                        label = referenced_field or clean_name
+                        mmd_references.append(f'"**{referenced_model}**" ||--o{{ "**{clean_model}**" : {label}')
 
-            mmd_entity += f'\t"**{model_name}**"' + "{\n" + entity_block + "}\n"
+            mmd_entity += f'\t"**{clean_model}**" {{\n{entity_block}}}\n'
 
         if mmd_references:
             mmd_entity += "\n" + "\n".join(mmd_references)
 
-        return f"{mmd_entity}\n"
+        return mmd_entity + "\n"
 
     except Exception as e:
         print(f"Error generating DCS mermaid diagram: {e}")
@@ -95,3 +97,14 @@ def odcs_to_mermaid(data_contract_spec: OpenDataContractStandard) -> str | None:
 
 def _sanitize_name(name: str) -> str:
     return name.replace("#", "Nb").replace(" ", "_").replace("/", "by")
+
+
+def _field_line(name: str, field_type: str, pk: bool = False, uk: bool = False, fk: bool = False) -> str:
+    indicators = ""
+    if pk:
+        indicators += "🔑"
+    if uk:
+        indicators += "🔒"
+    if fk:
+        indicators += "⌘"
+    return f"\t{name}{indicators} {field_type}\n"

{datacontract_cli-0.10.34 → datacontract_cli-0.10.35}/datacontract/export/spark_converter.py

@@ -1,3 +1,5 @@
+import json
+
 from pyspark.sql import types
 
 from datacontract.export.exporter import Exporter
@@ -104,7 +106,8 @@ def to_struct_field(field: Field, field_name: str) -> types.StructField:
         types.StructField: The corresponding Spark StructField.
     """
     data_type = to_spark_data_type(field)
-    return types.StructField(name=field_name, dataType=data_type, nullable=not field.required)
+    metadata = to_spark_metadata(field)
+    return types.StructField(name=field_name, dataType=data_type, nullable=not field.required, metadata=metadata)
 
 
 def to_spark_data_type(field: Field) -> types.DataType:
@@ -152,7 +155,25 @@ def to_spark_data_type(field: Field) -> types.DataType:
         return types.DateType()
     if field_type == "bytes":
         return types.BinaryType()
-    return types.StringType() # default if no condition is met
+    return types.StringType()  # default if no condition is met
+
+
+def to_spark_metadata(field: Field) -> dict[str, str]:
+    """
+    Convert a field to a Spark metadata dictonary.
+
+    Args:
+        field (Field): The field to convert.
+
+    Returns:
+        dict: dictionary that can be supplied to Spark as metadata for a StructField
+    """
+
+    metadata = {}
+    if field.description:
+        metadata["comment"] = field.description
+
+    return metadata
 
 
 def print_schema(dtype: types.DataType) -> str:
@@ -192,7 +213,11 @@ def print_schema(dtype: types.DataType) -> str:
         name = f'"{column.name}"'
         data_type = indent(print_schema(column.dataType), 1)
         nullable = indent(f"{column.nullable}", 1)
-        return f"StructField({name},\n{data_type},\n{nullable}\n)"
+        if column.metadata:
+            metadata = indent(f"{json.dumps(column.metadata)}", 1)
+            return f"StructField({name},\n{data_type},\n{nullable},\n{metadata}\n)"
+        else:
+            return f"StructField({name},\n{data_type},\n{nullable}\n)"
 
     def format_struct_type(struct_type: types.StructType) -> str:
         """