datacontract-cli 0.10.6__tar.gz → 0.10.7__tar.gz

{datacontract_cli-0.10.6/datacontract_cli.egg-info → datacontract_cli-0.10.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datacontract-cli
-Version: 0.10.6
+Version: 0.10.7
 Summary: Test data contracts
 Author-email: Jochen Christ <jochen.christ@innoq.com>, Stefan Negele <stefan.negele@innoq.com>
 Project-URL: Homepage, https://cli.datacontract.com
@@ -49,10 +49,11 @@ Requires-Dist: pytest; extra == "dev"
 Requires-Dist: pytest-xdist; extra == "dev"
 Requires-Dist: moto; extra == "dev"
 Requires-Dist: pymssql==2.3.0; extra == "dev"
-Requires-Dist: testcontainers<4.0.0; extra == "dev"
-Requires-Dist: testcontainers-minio; extra == "dev"
-Requires-Dist: testcontainers-postgres; extra == "dev"
-Requires-Dist: testcontainers-kafka; extra == "dev"
+Requires-Dist: kafka-python; extra == "dev"
+Requires-Dist: testcontainers~=4.5.0; extra == "dev"
+Requires-Dist: testcontainers[minio]; extra == "dev"
+Requires-Dist: testcontainers[postgres]; extra == "dev"
+Requires-Dist: testcontainers[kafka]; extra == "dev"
 Requires-Dist: testcontainers[mssql]; extra == "dev"
 
 # Data Contract CLI
@@ -333,8 +334,10 @@ Supported server types:
 - [s3](#S3)
 - [bigquery](#bigquery)
 - [azure](#azure)
+- [sqlserver](#sqlserver)
 - [databricks](#databricks)
 - [databricks (programmatic)](#databricks-programmatic)
+- [dataframr (programmatic)](#dataframe-programmatic)
 - [snowflake](#snowflake)
 - [kafka](#kafka)
 - [postgres](#postgres)
@@ -448,6 +451,43 @@ Authentication works with an Azure Service Principal (SPN) aka App Registration
 
 
 
+### Sqlserver
+
+Data Contract CLI can test data in MS SQL Server (including Azure SQL, Synapse Analytics SQL Pool).
+
+#### Example
+
+datacontract.yaml
+```yaml
+servers:
+  production:
+    type: sqlserver
+    host: localhost
+    port: 5432
+    database: tempdb
+    schema: dbo
+    driver: ODBC Driver 18 for SQL Server
+models:
+  my_table_1: # corresponds to a table
+    type: table
+    fields:
+      my_column_1: # corresponds to a column
+        type: varchar
+```
+
+#### Environment Variables
+
+| Environment Variable             | Example            | Description |
+|----------------------------------|--------------------|-------------|
+| `DATACONTRACT_SQLSERVER_USERNAME` | `root`         | Username    |
+| `DATACONTRACT_SQLSERVER_PASSWORD` | `toor` | Password    |
+| `DATACONTRACT_SQLSERVER_TRUSTED_CONNECTION` | `True` | Use windows authentication, instead of login    |
+| `DATACONTRACT_SQLSERVER_TRUST_SERVER_CERTIFICATE` | `True` | Trust self-signed certificate    |
+| `DATACONTRACT_SQLSERVER_ENCRYPTED_CONNECTION` | `True` | Use SSL    |
+
+
+
+
 ### Databricks
 
 Works with Unity Catalog and Hive metastore.
@@ -516,6 +556,41 @@ run = data_contract.test()
 run.result
 ```
 
+### Dataframe (programmatic)
+
+Works with Spark DataFrames.
+DataFrames need to be created as named temporary views.
+Multiple temporary views are suppored if your data contract contains multiple models.
+
+Testing DataFrames is useful to test your datasets in a pipeline before writing them to a data source.
+
+#### Example
+
+datacontract.yaml
+```yaml
+servers:
+  production:
+    type: dataframe
+models:
+  my_table: # corresponds to a temporary view
+    type: table
+    fields: ...
+```
+
+Example code
+```python
+from datacontract.data_contract import DataContract
+
+df.createOrReplaceTempView("my_table")
+
+data_contract = DataContract(
+  data_contract_file="datacontract.yaml",
+  spark=spark,
+)
+run = data_contract.test()
+assert run.result == "passed"
+```
+
 
 ### Snowflake
 
@@ -608,41 +683,6 @@ models:
 
 
 
-### Postgres
-
-Data Contract CLI can test data in Postgres or Postgres-compliant databases (e.g., RisingWave).
-
-#### Example
-
-datacontract.yaml
-```yaml
-servers:
-  postgres:
-    type: sqlserver
-    host: localhost
-    port: 5432
-    database: tempdb
-    schema: dbo
-    driver: ODBC Driver 18 for SQL Server
-models:
-  my_table_1: # corresponds to a table
-    type: table
-    fields:
-      my_column_1: # corresponds to a column
-        type: varchar
-```
-
-#### Environment Variables
-
-| Environment Variable             | Example            | Description |
-|----------------------------------|--------------------|-------------|
-| `DATACONTRACT_SQLSERVER_USERNAME` | `root`         | Username    |
-| `DATACONTRACT_SQLSERVER_PASSWORD` | `toor` | Password    |
-| `DATACONTRACT_SQLSERVER_TRUSTED_CONNECTION` | `True` | Use windows authentication, instead of login    |
-| `DATACONTRACT_SQLSERVER_TRUST_SERVER_CERTIFICATE` | `True` | Trust self-signed certificate    |
-| `DATACONTRACT_SQLSERVER_ENCRYPTED_CONNECTION` | `True` | Use SSL    |
-
-
 
 ### export
 
@@ -802,41 +842,30 @@ models:
 ```
  Usage: datacontract import [OPTIONS]
 
- Create a data contract from the given source location. Prints to stdout.
-
-╭─ Options ─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
-│ *  --format                  [sql|avro|glue|bigquery|jsonschema]  The format of the source file. [default: None] [required]                                   │
-│    --source                  TEXT                      The path to the file or Glue Database that should be imported. [default: None]                         │
-│    --bigquery-project        TEXT                      The bigquery project id. [default: None]                                                               │
-│    --bigquery-dataset        TEXT                      The bigquery dataset id. [default: None]                                                               │
-│    --bigquery-table          TEXT                      List of table ids to import from the bigquery API (repeat for multiple table ids, leave empty for all  │
-│                                                        tables in the dataset).                                                                                │
-│                                                        [default: None]                                                                                        │
-│    --help                                              Show this message and exit.                                                                            │
-╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
+ Create a data contract from the given source location. Prints to stdout.                                                              
+                                                                                                                                       
+╭─ Options ───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
+│ *  --format                  [sql|avro|glue|bigquery|jsonschema]  The format of the source file. [default: None] [required]         │
+│    --source                  TEXT                                 The path to the file or Glue Database that should be imported.    │
+│                                                                   [default: None]                                                   │
+│    --glue-table              TEXT                                 List of table ids to import from the Glue Database (repeat for    │
+│                                                                   multiple table ids, leave empty for all tables in the dataset).   │
+│                                                                   [default: None]                                                   │
+│    --bigquery-project        TEXT                                 The bigquery project id. [default: None]                          │
+│    --bigquery-dataset        TEXT                                 The bigquery dataset id. [default: None]                          │
+│    --bigquery-table          TEXT                                 List of table ids to import from the bigquery API (repeat for     │
+│                                                                   multiple table ids, leave empty for all tables in the dataset).   │
+│                                                                   [default: None]                                                   │
+│    --help                                                         Show this message and exit.                                       │
+╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
 ```
 
-As shown, some options are only relevant in certain conditions: For `format` Bigtable we support to directly read off the Bigtable APIs.
-In this case there's no need to specify `source` but instead `bt-project-id`, `bt-dataset-id` and `table` must be specified.
-
-For providing authentication to the Client, please see [the google documentation](https://cloud.google.com/docs/authentication/provide-credentials-adc#how-to) or the one [about authorizing client libraries](https://cloud.google.com/bigquery/docs/authentication#client-libs).
-
 Example:
 ```bash
 # Example import from SQL DDL
 datacontract import --format sql --source my_ddl.sql
 ```
 
-```bash
-# Example import from Bigquery JSON
-datacontract import --format bigquery --source my_bigquery_table.json
-```
-
-```bash
-# Example import from Bigquery API
-datacontract import --format bigquery --btProjectId <project_id> --btDatasetId <dataset_id> --table <tableid_1> --table <tableid_2> --table <tableid_3>
-```
-
 Available import options:
 
 | Type               | Description                                    | Status  |
@@ -852,6 +881,49 @@ Available import options:
 | Missing something? | Please create an issue on GitHub               | TBD     |
 
 
+#### BigQuery
+
+Bigquery data can either be imported off of JSON Files generated from the table descriptions or directly from the Bigquery API. In case you want to use JSON Files, specify the `source` parameter with a path to the JSON File.
+
+To import from the Bigquery API, you have to _omit_ `source` and instead need to provide `bigquery-project` and `bigquery-dataset`. Additionally you may specify `bigquery-table` to enumerate the tables that should be imported. If no tables are given, _all_ available tables of the dataset will be imported.
+
+For providing authentication to the Client, please see [the google documentation](https://cloud.google.com/docs/authentication/provide-credentials-adc#how-to) or the one [about authorizing client libraries](https://cloud.google.com/bigquery/docs/authentication#client-libs).
+
+Examples: 
+
+```bash
+# Example import from Bigquery JSON
+datacontract import --format bigquery --source my_bigquery_table.json
+```
+
+```bash
+# Example import from Bigquery API with specifying the tables to import
+datacontract import --format bigquery --bigquery-project <project_id> --bigquery-dataset <dataset_id> --bigquery-table <tableid_1> --bigquery-table <tableid_2> --bigquery-table <tableid_3>
+```
+
+```bash
+# Example import from Bigquery API importing all tables in the dataset
+datacontract import --format bigquery --bigquery-project <project_id> --bigquery-dataset <dataset_id>
+```
+
+### Glue
+
+Importing from Glue reads the necessary Data directly off of the AWS API.
+You may give the `glue-table` parameter to enumerate the tables that should be imported. If no tables are given, _all_ available tables of the database will be imported.
+
+Examples: 
+
+```bash
+# Example import from AWS Glue with specifying the tables to import
+datacontract import --format glue --source <database_name> --glue-table <table_name_1> --glue-table <table_name_2> --glue-table <table_name_3>
+```
+
+```bash
+# Example import from AWS Glue importing all tables in the database
+datacontract import --format glue --source <database_name>
+```
+
+
 ### breaking
 
 ```

{datacontract_cli-0.10.6 → datacontract_cli-0.10.7}/README.md

@@ -276,8 +276,10 @@ Supported server types:
 - [s3](#S3)
 - [bigquery](#bigquery)
 - [azure](#azure)
+- [sqlserver](#sqlserver)
 - [databricks](#databricks)
 - [databricks (programmatic)](#databricks-programmatic)
+- [dataframr (programmatic)](#dataframe-programmatic)
 - [snowflake](#snowflake)
 - [kafka](#kafka)
 - [postgres](#postgres)
@@ -391,6 +393,43 @@ Authentication works with an Azure Service Principal (SPN) aka App Registration
 
 
 
+### Sqlserver
+
+Data Contract CLI can test data in MS SQL Server (including Azure SQL, Synapse Analytics SQL Pool).
+
+#### Example
+
+datacontract.yaml
+```yaml
+servers:
+  production:
+    type: sqlserver
+    host: localhost
+    port: 5432
+    database: tempdb
+    schema: dbo
+    driver: ODBC Driver 18 for SQL Server
+models:
+  my_table_1: # corresponds to a table
+    type: table
+    fields:
+      my_column_1: # corresponds to a column
+        type: varchar
+```
+
+#### Environment Variables
+
+| Environment Variable             | Example            | Description |
+|----------------------------------|--------------------|-------------|
+| `DATACONTRACT_SQLSERVER_USERNAME` | `root`         | Username    |
+| `DATACONTRACT_SQLSERVER_PASSWORD` | `toor` | Password    |
+| `DATACONTRACT_SQLSERVER_TRUSTED_CONNECTION` | `True` | Use windows authentication, instead of login    |
+| `DATACONTRACT_SQLSERVER_TRUST_SERVER_CERTIFICATE` | `True` | Trust self-signed certificate    |
+| `DATACONTRACT_SQLSERVER_ENCRYPTED_CONNECTION` | `True` | Use SSL    |
+
+
+
+
 ### Databricks
 
 Works with Unity Catalog and Hive metastore.
@@ -459,6 +498,41 @@ run = data_contract.test()
 run.result
 ```
 
+### Dataframe (programmatic)
+
+Works with Spark DataFrames.
+DataFrames need to be created as named temporary views.
+Multiple temporary views are suppored if your data contract contains multiple models.
+
+Testing DataFrames is useful to test your datasets in a pipeline before writing them to a data source.
+
+#### Example
+
+datacontract.yaml
+```yaml
+servers:
+  production:
+    type: dataframe
+models:
+  my_table: # corresponds to a temporary view
+    type: table
+    fields: ...
+```
+
+Example code
+```python
+from datacontract.data_contract import DataContract
+
+df.createOrReplaceTempView("my_table")
+
+data_contract = DataContract(
+  data_contract_file="datacontract.yaml",
+  spark=spark,
+)
+run = data_contract.test()
+assert run.result == "passed"
+```
+
 
 ### Snowflake
 
@@ -551,41 +625,6 @@ models:
 
 
 
-### Postgres
-
-Data Contract CLI can test data in Postgres or Postgres-compliant databases (e.g., RisingWave).
-
-#### Example
-
-datacontract.yaml
-```yaml
-servers:
-  postgres:
-    type: sqlserver
-    host: localhost
-    port: 5432
-    database: tempdb
-    schema: dbo
-    driver: ODBC Driver 18 for SQL Server
-models:
-  my_table_1: # corresponds to a table
-    type: table
-    fields:
-      my_column_1: # corresponds to a column
-        type: varchar
-```
-
-#### Environment Variables
-
-| Environment Variable             | Example            | Description |
-|----------------------------------|--------------------|-------------|
-| `DATACONTRACT_SQLSERVER_USERNAME` | `root`         | Username    |
-| `DATACONTRACT_SQLSERVER_PASSWORD` | `toor` | Password    |
-| `DATACONTRACT_SQLSERVER_TRUSTED_CONNECTION` | `True` | Use windows authentication, instead of login    |
-| `DATACONTRACT_SQLSERVER_TRUST_SERVER_CERTIFICATE` | `True` | Trust self-signed certificate    |
-| `DATACONTRACT_SQLSERVER_ENCRYPTED_CONNECTION` | `True` | Use SSL    |
-
-
 
 ### export
 
@@ -745,41 +784,30 @@ models:
 ```
  Usage: datacontract import [OPTIONS]
 
- Create a data contract from the given source location. Prints to stdout.
-
-╭─ Options ─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
-│ *  --format                  [sql|avro|glue|bigquery|jsonschema]  The format of the source file. [default: None] [required]                                   │
-│    --source                  TEXT                      The path to the file or Glue Database that should be imported. [default: None]                         │
-│    --bigquery-project        TEXT                      The bigquery project id. [default: None]                                                               │
-│    --bigquery-dataset        TEXT                      The bigquery dataset id. [default: None]                                                               │
-│    --bigquery-table          TEXT                      List of table ids to import from the bigquery API (repeat for multiple table ids, leave empty for all  │
-│                                                        tables in the dataset).                                                                                │
-│                                                        [default: None]                                                                                        │
-│    --help                                              Show this message and exit.                                                                            │
-╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
+ Create a data contract from the given source location. Prints to stdout.                                                              
+                                                                                                                                       
+╭─ Options ───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
+│ *  --format                  [sql|avro|glue|bigquery|jsonschema]  The format of the source file. [default: None] [required]         │
+│    --source                  TEXT                                 The path to the file or Glue Database that should be imported.    │
+│                                                                   [default: None]                                                   │
+│    --glue-table              TEXT                                 List of table ids to import from the Glue Database (repeat for    │
+│                                                                   multiple table ids, leave empty for all tables in the dataset).   │
+│                                                                   [default: None]                                                   │
+│    --bigquery-project        TEXT                                 The bigquery project id. [default: None]                          │
+│    --bigquery-dataset        TEXT                                 The bigquery dataset id. [default: None]                          │
+│    --bigquery-table          TEXT                                 List of table ids to import from the bigquery API (repeat for     │
+│                                                                   multiple table ids, leave empty for all tables in the dataset).   │
+│                                                                   [default: None]                                                   │
+│    --help                                                         Show this message and exit.                                       │
+╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
 ```
 
-As shown, some options are only relevant in certain conditions: For `format` Bigtable we support to directly read off the Bigtable APIs.
-In this case there's no need to specify `source` but instead `bt-project-id`, `bt-dataset-id` and `table` must be specified.
-
-For providing authentication to the Client, please see [the google documentation](https://cloud.google.com/docs/authentication/provide-credentials-adc#how-to) or the one [about authorizing client libraries](https://cloud.google.com/bigquery/docs/authentication#client-libs).
-
 Example:
 ```bash
 # Example import from SQL DDL
 datacontract import --format sql --source my_ddl.sql
 ```
 
-```bash
-# Example import from Bigquery JSON
-datacontract import --format bigquery --source my_bigquery_table.json
-```
-
-```bash
-# Example import from Bigquery API
-datacontract import --format bigquery --btProjectId <project_id> --btDatasetId <dataset_id> --table <tableid_1> --table <tableid_2> --table <tableid_3>
-```
-
 Available import options:
 
 | Type               | Description                                    | Status  |
@@ -795,6 +823,49 @@ Available import options:
 | Missing something? | Please create an issue on GitHub               | TBD     |
 
 
+#### BigQuery
+
+Bigquery data can either be imported off of JSON Files generated from the table descriptions or directly from the Bigquery API. In case you want to use JSON Files, specify the `source` parameter with a path to the JSON File.
+
+To import from the Bigquery API, you have to _omit_ `source` and instead need to provide `bigquery-project` and `bigquery-dataset`. Additionally you may specify `bigquery-table` to enumerate the tables that should be imported. If no tables are given, _all_ available tables of the dataset will be imported.
+
+For providing authentication to the Client, please see [the google documentation](https://cloud.google.com/docs/authentication/provide-credentials-adc#how-to) or the one [about authorizing client libraries](https://cloud.google.com/bigquery/docs/authentication#client-libs).
+
+Examples: 
+
+```bash
+# Example import from Bigquery JSON
+datacontract import --format bigquery --source my_bigquery_table.json
+```
+
+```bash
+# Example import from Bigquery API with specifying the tables to import
+datacontract import --format bigquery --bigquery-project <project_id> --bigquery-dataset <dataset_id> --bigquery-table <tableid_1> --bigquery-table <tableid_2> --bigquery-table <tableid_3>
+```
+
+```bash
+# Example import from Bigquery API importing all tables in the dataset
+datacontract import --format bigquery --bigquery-project <project_id> --bigquery-dataset <dataset_id>
+```
+
+### Glue
+
+Importing from Glue reads the necessary Data directly off of the AWS API.
+You may give the `glue-table` parameter to enumerate the tables that should be imported. If no tables are given, _all_ available tables of the database will be imported.
+
+Examples: 
+
+```bash
+# Example import from AWS Glue with specifying the tables to import
+datacontract import --format glue --source <database_name> --glue-table <table_name_1> --glue-table <table_name_2> --glue-table <table_name_3>
+```
+
+```bash
+# Example import from AWS Glue importing all tables in the database
+datacontract import --format glue --source <database_name>
+```
+
+
 ### breaking
 
 ```

{datacontract_cli-0.10.6 → datacontract_cli-0.10.7}/datacontract/cli.py

@@ -13,7 +13,7 @@ from typer.core import TyperGroup
 from typing_extensions import Annotated
 
 from datacontract.catalog.catalog import create_index_html, create_data_contract_html
-from datacontract.data_contract import DataContract
+from datacontract.data_contract import DataContract, ExportFormat
 from datacontract.init.download_datacontract_file import download_datacontract_file, FileExistsException
 from datacontract.publish.publish import publish_to_datamesh_manager
 
@@ -141,28 +141,6 @@ def test(
     _handle_result(run)
 
 
-class ExportFormat(str, Enum):
-    jsonschema = "jsonschema"
-    pydantic_model = "pydantic-model"
-    sodacl = "sodacl"
-    dbt = "dbt"
-    dbt_sources = "dbt-sources"
-    dbt_staging_sql = "dbt-staging-sql"
-    odcs = "odcs"
-    rdf = "rdf"
-    avro = "avro"
-    protobuf = "protobuf"
-    great_expectations = "great-expectations"
-    terraform = "terraform"
-    avro_idl = "avro-idl"
-    sql = "sql"
-    sql_query = "sql-query"
-    html = "html"
-    go = "go"
-    bigquery = "bigquery"
-    dbml = "dbml"
-
-
 @app.command()
 def export(
     format: Annotated[ExportFormat, typer.Option(help="The export format.")],
@@ -231,6 +209,12 @@ def import_(
     source: Annotated[
         Optional[str], typer.Option(help="The path to the file or Glue Database that should be imported.")
     ] = None,
+    glue_table: Annotated[
+        Optional[List[str]],
+        typer.Option(
+            help="List of table ids to import from the Glue Database (repeat for multiple table ids, leave empty for all tables in the dataset)."
+        ),
+    ] = None,
     bigquery_project: Annotated[Optional[str], typer.Option(help="The bigquery project id.")] = None,
     bigquery_dataset: Annotated[Optional[str], typer.Option(help="The bigquery dataset id.")] = None,
     bigquery_table: Annotated[
@@ -243,7 +227,7 @@ def import_(
     """
     Create a data contract from the given source location. Prints to stdout.
     """
-    result = DataContract().import_from_source(format, source, bigquery_table, bigquery_project, bigquery_dataset)
+    result = DataContract().import_from_source(format, source, glue_table, bigquery_table, bigquery_project, bigquery_dataset)
     console.print(result.to_yaml())
 
 

{datacontract_cli-0.10.6 → datacontract_cli-0.10.7}/datacontract/data_contract.py

@@ -2,6 +2,7 @@ import json
 import logging
 import tempfile
 import typing
+from enum import Enum
 
 import yaml
 from pyspark.sql import SparkSession
@@ -49,6 +50,28 @@ from datacontract.model.exceptions import DataContractException
 from datacontract.model.run import Run, Check
 
 
+class ExportFormat(str, Enum):
+    jsonschema = "jsonschema"
+    pydantic_model = "pydantic-model"
+    sodacl = "sodacl"
+    dbt = "dbt"
+    dbt_sources = "dbt-sources"
+    dbt_staging_sql = "dbt-staging-sql"
+    odcs = "odcs"
+    rdf = "rdf"
+    avro = "avro"
+    protobuf = "protobuf"
+    great_expectations = "great-expectations"
+    terraform = "terraform"
+    avro_idl = "avro-idl"
+    sql = "sql"
+    sql_query = "sql-query"
+    html = "html"
+    go = "go"
+    bigquery = "bigquery"
+    dbml = "dbml"
+
+
 class DataContract:
     def __init__(
         self,
@@ -195,10 +218,13 @@ class DataContract:
                 run.outputPortId = server.outputPortId
                 run.server = server_name
 
-                # 5. check server is supported type
-                # 6. check server credentials are complete
+                # TODO check server is supported type for nicer error messages
+
+                # TODO check server credentials are complete for nicer error messages
+
                 if server.format == "json" and server.type != "kafka":
                     check_jsonschema(run, data_contract, server)
+
                 check_soda_execute(run, data_contract, server, self._spark, tmp_dir)
 
         except DataContractException as e:
@@ -275,7 +301,9 @@ class DataContract:
             inline_quality=self._inline_quality,
         )
 
-    def export(self, export_format, model: str = "all", rdf_base: str = None, sql_server_type: str = "auto") -> str:
+    def export(
+        self, export_format: ExportFormat, model: str = "all", rdf_base: str = None, sql_server_type: str = "auto"
+    ) -> str:
         data_contract = resolve.resolve_data_contract(
             self._data_contract_file,
             self._data_contract_str,
@@ -422,6 +450,7 @@ class DataContract:
         self,
         format: str,
         source: typing.Optional[str] = None,
+        glue_tables: typing.Optional[typing.List[str]] = None,
         bigquery_tables: typing.Optional[typing.List[str]] = None,
         bigquery_project: typing.Optional[str] = None,
         bigquery_dataset: typing.Optional[str] = None,
@@ -433,7 +462,7 @@ class DataContract:
         elif format == "avro":
             data_contract_specification = import_avro(data_contract_specification, source)
         elif format == "glue":
-            data_contract_specification = import_glue(data_contract_specification, source)
+            data_contract_specification = import_glue(data_contract_specification, source, glue_tables)
         elif format == "jsonschema":
             data_contract_specification = import_jsonschema(data_contract_specification, source)
         elif format == "bigquery":

{datacontract_cli-0.10.6 → datacontract_cli-0.10.7}/datacontract/engines/soda/check_soda_execute.py

@@ -64,6 +64,15 @@ def check_soda_execute(
             soda_configuration_str = to_databricks_soda_configuration(server)
             scan.add_configuration_yaml_str(soda_configuration_str)
             scan.set_data_source_name(server.type)
+    elif server.type == "dataframe":
+        if spark is None:
+            run.log_warn("Server type dataframe only works with the Python library and requires a Spark session, "
+                         "please provide one with the DataContract class")
+            return
+        else:
+            logging.info("Use Spark to connect to data source")
+            scan.add_spark_session(spark, data_source_name="datacontract-cli")
+            scan.set_data_source_name("datacontract-cli")
     elif server.type == "kafka":
         if spark is None:
             spark = create_spark_session(tmp_dir)