validio-cli 0.29.0__tar.gz → 5.2.0__tar.gz

{validio_cli-0.29.0 → validio_cli-5.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: validio-cli
-Version: 0.29.0
+Version: 5.2.0
 Summary: CLI tool to interact with the Validio platform
 Home-page: https://validio.io/
 License: Apache-2.0

{validio_cli-0.29.0 → validio_cli-5.2.0}/pyproject.toml

@@ -3,7 +3,7 @@ name = "validio-cli"
 # This version does not represent the released version or any tag. For each
 # release we automatically bump this before building and publishing so this
 # should be kept at 0.0.1dev1
-version = "0.29.0"
+version = "5.2.0"
 description = "CLI tool to interact with the Validio platform"
 authors = ["Validio <support@validio.io>"]
 license = "Apache-2.0"

{validio_cli-0.29.0 → validio_cli-5.2.0}/validio_cli/bin/entities/sources.py

@@ -271,13 +271,11 @@ async def _interactive(config_dir: str, filename: Path, namespace: str) -> None:
     credential_type_to_source_type = {
         "AwsCredential": [
             ("kinesis", "Amazon Kinesis"),
-            ("s3", "Amazon S3"),
         ],
         "DatabricksCredential": [("databricks", "Databricks")],
         "DemoCredential": [("demo", "Demo")],
         "GcpCredential": [
             ("bigquery", "Google BigQuery"),
-            ("gcs", "Google Cloud Storage"),
             ("pubsub", "Google Pub/Sub"),
         ],
         "PostgreSqlCredential": [("postgresql", "PostgreSQL")],
@@ -458,29 +456,6 @@ async def _interactive(config_dir: str, filename: Path, namespace: str) -> None:
                 info.get("message_format", ""),
                 info.get("message_schema", ""),
             )
-        case "s3":
-            info = await _multip_prompt(
-                [
-                    ("Bucket", [], ""),
-                    ("File pattern", [], "*.csv"),
-                    ("Prefix", [], ""),
-                    ("CSV delimiter", [",", "|"], ","),
-                ]
-            )
-
-            print()
-            null_marker = await _get_null_marker()
-
-            await _infer_schema_s3(
-                vc,
-                filename,
-                credential_id,
-                info.get("bucket", ""),
-                info.get("file_pattern", ""),
-                info.get("prefix", ""),
-                info.get("csv_delimiter", ""),
-                null_marker,
-            )
         case "postgresql":
             info = await _multip_prompt(
                 [
@@ -549,31 +524,6 @@ async def _interactive(config_dir: str, filename: Path, namespace: str) -> None:
                 info.get("dataset", ""),
                 info.get("table", ""),
             )
-        case "gcs":
-            info = await _multip_prompt(
-                [
-                    ("Project", [], ""),
-                    ("Bucket", [], ""),
-                    ("Folder", [], ""),
-                    ("File pattern", ["*.csv"], "*.csv"),
-                    ("CSV delimiter", [",", "|"], ","),
-                ]
-            )
-
-            print()
-            null_marker = await _get_null_marker()
-
-            await _infer_schema_gcs(
-                vc,
-                filename,
-                credential_id,
-                info.get("project", ""),
-                info.get("bucket", ""),
-                info.get("folder", ""),
-                info.get("file_pattern", ""),
-                info.get("csv_delimiter", ""),
-                null_marker,
-            )
         case _:
             print("Not yet implemented...")
             return
@@ -588,40 +538,6 @@ async def demo(
     await _infer_schema_demo(vc, filename)
 
 
-@infer_schema_app.async_command(help="Infer Amazon S3 schema")
-async def s3(
-    config_dir: str = ConfigDir,
-    filename: Path = schema_filename_option("s3"),
-    namespace: str = Namespace(),
-    credential_id: str = typer.Option(..., help="Credential name or ID"),
-    bucket: str = typer.Option(..., help="S3 bucket name"),
-    file_pattern: str = typer.Option(
-        "*.csv", help="File glob pattern - files to use for inference"
-    ),
-    prefix: str = typer.Option("", help="Prefix in the bucket, a directory"),
-    csv_delimiter: str = typer.Option(",", help="Delimiter between columns in file"),
-    null_marker: str = typer.Option(None, help="Null marker (values to treat as NULL)"),
-) -> None:
-    vc, cfg = get_client(config_dir)
-
-    resolved_credential_id = await credentials.get_credential_id(
-        vc, cfg, credential_id, namespace
-    )
-    if resolved_credential_id is None:
-        return
-
-    await _infer_schema_s3(
-        vc,
-        filename,
-        resolved_credential_id,
-        bucket,
-        file_pattern,
-        prefix,
-        csv_delimiter,
-        null_marker,
-    )
-
-
 @infer_schema_app.async_command(help="Infer Amazon Kinesis schema")
 async def kinesis(
     config_dir: str = ConfigDir,
@@ -792,40 +708,6 @@ async def bigquery(
     )
 
 
-@infer_schema_app.async_command(help="Infer Google Cloud Storage schema")
-async def gcs(
-    config_dir: str = ConfigDir,
-    filename: Path = schema_filename_option("gcs"),
-    namespace: str = Namespace(),
-    credential_id: str = typer.Option(..., help="Credential name or ID"),
-    project: str = typer.Option(..., help="Google project name"),
-    bucket: str = typer.Option(..., help="GCS bucket"),
-    folder: str = typer.Option("", help="Folder in the bucket"),
-    file_pattern: str = typer.Option("*.csv", help="File glob"),
-    csv_delimiter: str = typer.Option(",", help="Delimiter between columns in file"),
-    null_marker: str = typer.Option(None, help="Null marker (values to treat as NULL)"),
-) -> None:
-    vc, cfg = get_client(config_dir)
-
-    resolved_credential_id = await credentials.get_credential_id(
-        vc, cfg, credential_id, namespace
-    )
-    if resolved_credential_id is None:
-        return
-
-    await _infer_schema_gcs(
-        vc,
-        filename,
-        resolved_credential_id,
-        project,
-        bucket,
-        folder,
-        file_pattern,
-        csv_delimiter,
-        null_marker,
-    )
-
-
 async def _infer_schema_databricks(
     vc: APIClient,
     filename: Path,
@@ -855,32 +737,6 @@ async def _infer_schema_demo(
     _write_schema(filename, schema)
 
 
-async def _infer_schema_s3(
-    vc: APIClient,
-    filename: Path,
-    credential_id: str,
-    bucket: str,
-    file_pattern: str,
-    prefix: str,
-    csv_delimiter: str,
-    null_marker: str | None,
-) -> None:
-    schema = await vc.infer_schema(
-        class_name="AwsS3",
-        variable_values={
-            "credentialId": credential_id,
-            "bucket": bucket,
-            "filePattern": file_pattern,
-            "prefix": prefix,
-            "csv": {
-                "delimiter": csv_delimiter,
-                "nullMarker": null_marker,
-            },
-        },
-    )
-    _write_schema(filename, schema)
-
-
 async def _infer_schema_kinesis(
     vc: APIClient,
     filename: Path,
@@ -1029,34 +885,6 @@ async def _infer_schema_bigquery(
     _write_schema(filename, schema)
 
 
-async def _infer_schema_gcs(
-    vc: APIClient,
-    filename: Path,
-    credential_id: str,
-    project: str,
-    bucket: str,
-    folder: str,
-    file_pattern: str,
-    csv_delimiter: str,
-    null_marker: str | None,
-) -> None:
-    schema = await vc.infer_schema(
-        class_name="GcpStorage",
-        variable_values={
-            "credentialId": credential_id,
-            "project": project,
-            "bucket": bucket,
-            "folder": folder,
-            "filePattern": file_pattern,
-            "csv": {
-                "delimiter": csv_delimiter,
-                "nullMarker": null_marker,
-            },
-        },
-    )
-    _write_schema(filename, schema)
-
-
 def _write_schema(filename: Path, schema: Any) -> None:
     filename.write_text(json.dumps(schema, indent=2))
 
@@ -1081,38 +909,6 @@ async def _multip_prompt(questions: list[tuple[str, list[str], str]]) -> dict[st
     return answers
 
 
-async def _get_null_marker() -> str | None:
-    null_marker = await components.radiolist_dialog(
-        title="Null marker - What value should be treated as NULL",
-        values=[
-            ("none", "None (No value is treated as NULL)"),
-            ("NULL", "The literal string 'NULL', f.ex. 'a,NULL,c'"),
-            ("empty", "Empty (\"\", f.ex 'a,,c')"),
-            ("other", "Set manually"),
-        ],
-    )
-
-    # User hit escape sequence, don't return None in this case.
-    if null_marker is None:
-        raise typer.Exit(code=1)
-
-    if null_marker == "other":
-        session: PromptSession = PromptSession()
-        null_marker = await session.prompt_async(
-            validio_cli._fixed_width("Null marker"),
-        )
-
-    if null_marker == "none":
-        return None
-
-    # We can't map the value to '""' because it will make it pre-selected in the
-    # dialog which we don't want.
-    if null_marker == "empty":
-        return ""
-
-    return null_marker
-
-
 async def _get_source_id(
     session: Session,
     cfg: ValidioConfig,