Merge branch 'datacontract:main' into main

Author: dmaresma

.gitignore

@@ -4,6 +4,7 @@
 datacontract.sh
 /cli
 tmp
+/venv
 /contracts/
 /quality/
 db.duckdb

CHANGELOG.md

@@ -6,12 +6,16 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
 ## Unreleased
+### Added
+- `datacontract import --format json`: Import from JSON files
 
 ### Added
 
 ### Changed
+- `datacontract api [OPTIONS]`: Added option to pass extra arguments for `uvicorn.run()`
 
 ### Fixed
+- `pytest tests\test_api.py`: Fixed an issue where special characters were not read correctly from file.
 
 ## [0.10.28] - 2025-06-05
 

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]                                 │
@@ -2000,6 +2002,7 @@ 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.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")
@@ -488,14 +506,21 @@ 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
 
     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/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/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/imports/importer_factory.py

@@ -119,3 +119,10 @@ def load_module_class(module_path, class_name):
     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",
+)