Feat/powerbi importer

Dockerfile

@@ -44,17 +44,16 @@ FROM dhi.io/python:3.11-debian13-dev AS runtime
 ENV PYTHONUNBUFFERED=1 \
     PYTHONDONTWRITEBYTECODE=1 \
     VIRTUAL_ENV=/opt/venv \
-    JAVA_HOME=/opt/java/openjdk/17-jre \
-    PATH=/opt/venv/bin:/opt/java/openjdk/17-jre/bin:$PATH
+    JAVA_HOME=/opt/java/openjdk/21-jre \
+    PATH=/opt/venv/bin:/opt/java/openjdk/21-jre/bin:$PATH
 
 # copy the pre-built venv (readable+executable by the nonroot user)
 COPY --from=builder --chown=65532:65532 /opt/venv /opt/venv
 
-# Eclipse Temurin JRE 17 — required by PySpark-backed engines (Kafka, Spark).
-# Without Java, those engines fail at SparkSession startup. Adding the JRE here
-# means `datacontract test` against a kafka/spark server works in the image
-# without users having to extend it.
-COPY --from=dhi.io/eclipse-temurin:17-debian13 /opt/java/openjdk /opt/java/openjdk
+# Eclipse Temurin JRE 21 — required by PySpark-backed engines (Kafka, Spark).
+# Spark 4.0 (what `.[all]` resolves to) supports Java 17 and 21. Without Java,
+# those engines fail at SparkSession startup.
+COPY --from=dhi.io/eclipse-temurin:21-debian13 /opt/java/openjdk /opt/java/openjdk
 
 USER nonroot:nonroot
 WORKDIR /home/datacontract

README.md

@@ -891,7 +891,7 @@ models:
 ```
 
 ##### Environment Variables
-All [parameters supported by Soda](https://docs.soda.io/soda/connect-snowflake.html), uppercased and prepended by `DATACONTRACT_SNOWFLAKE_` prefix.
+Any `DATACONTRACT_SNOWFLAKE_`-prefixed variable is passed (lowercased, prefix stripped) as a connection parameter to the [snowflake-connector-python](https://docs.snowflake.com/en/developer-guide/python-connector/python-connector-api#connect) driver.
 Depending on the `authenticator` mode required by your Snowflake workspace, please set your environment variables accordingly.
 For example:
 
@@ -1824,6 +1824,7 @@ Usage: datacontract import [OPTIONS] COMMAND [ARGS]...
 │ spark       Import a data contract from a Spark schema.                                          │
 │ iceberg     Import a data contract from an Iceberg schema.                                       │
 │ excel       Import a data contract from an Excel file.                                           │
+│ powerbi     Import a data contract from an PowerBI template file.                                │
 │ snowflake   Import a data contract from an Snowflake account                                     │
 ╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
 
@@ -2065,6 +2066,21 @@ Example:
 datacontract import --format snowflake --source account.canada-central.azure --database databaseName --schema schemaName
 ```
 
+<details markdown="1">
+<summary><strong>snowflake</strong></summary>
+
+Importing from snowflake schema. Specify snowflake workspace account in `source` parameter, database name `database` and schema in `schema`. 
+Multiple authentification are supported, 
+login/password using the `DATACONTRACT_SNOWFLAKE_ ...` test environement variable are setup,
+MFA using external browser is selected when `DATACONTRACT_SNOWFLAKE_PASSWORD` is missing
+TOML file authentification using the default profile when `SNOWFLAKE_DEFAULT_CONNECTION_NAME` environment variable is defined
+
+Example:
+
+```bash
+datacontract import snowflake --source account.canada-central.azure --database databaseName --schema schemaName
+```
+</details>
 
 ### catalog
 ```

datacontract/command_import.py

@@ -431,6 +431,24 @@ def import_excel(
     _write_result(result, output)
 
 
+@import_app.command(
+    name="powerbi",
+    epilog="Example: datacontract import powerbi --source datacontract.pbit --output datacontract.yaml",
+)
+def import_powerbi(
+    source: Annotated[Optional[str], typer.Option(help="Path to the Power BI .pbit file.")] = None,
+    output: output_option = None,
+    schema: schema_option = None,
+    owner: owner_option = None,
+    id: id_option = None,
+    debug: debug_option = None,
+):
+    """Import a data contract from a Power BI .pbit file."""
+    enable_debug_logging(debug)
+    result = DataContract.import_from_source(format="powerbi", source=source, schema=schema, owner=owner, id=id)
+    _write_result(result, output)
+
+
 @import_app.command(
     name="snowflake",
     epilog="Example: datacontract import snowflake --source account --database DEMO_DB --schema PUBLIC --output datacontract.yaml",

datacontract/imports/importer.py

@@ -38,6 +38,7 @@ class ImportFormat(str, Enum):
     csv = "csv"
     protobuf = "protobuf"
     excel = "excel"
+    powerbi = "powerbi"
     snowflake = "snowflake"
 
     @classmethod

datacontract/imports/importer_factory.py

@@ -119,12 +119,16 @@ def load_module_class(module_path, class_name):
     module_path="datacontract.imports.excel_importer",
     class_name="ExcelImporter",
 )
+importer_factory.register_lazy_importer(
+    name=ImportFormat.powerbi,
+    module_path="datacontract.imports.powerbi_importer",
+    class_name="PowerBIImporter",
+)
 importer_factory.register_lazy_importer(
     name=ImportFormat.snowflake,
     module_path="datacontract.imports.snowflake_importer",
     class_name="SnowflakeImporter",
 )
-
 importer_factory.register_lazy_importer(
     name=ImportFormat.json,
     module_path="datacontract.imports.json_importer",