chore(source-s3): Update CDK to v5 (old)

airbyte-integrations/connectors/source-s3/integration_tests/cloud_spec.json

@@ -1,5 +1,7 @@
 {
   "documentationUrl": "https://docs.airbyte.com/integrations/sources/s3",
+  "supportsNormalization": false,
+  "supportsDBT": false,
   "connectionSpecification": {
     "title": "Config",
     "description": "NOTE: When this Spec is changed, legacy_config_transformer.py must also be modified to uptake the changes\nbecause it is responsible for converting legacy S3 v3 configs into v4 configs using the File-Based CDK.",
@@ -338,6 +340,19 @@
                   },
                   "description": "Extract text from document formats (.pdf, .docx, .md, .pptx) and emit as one record per file.",
                   "required": ["filetype"]
+                },
+                {
+                  "title": "Excel Format",
+                  "type": "object",
+                  "properties": {
+                    "filetype": {
+                      "title": "Filetype",
+                      "default": "excel",
+                      "const": "excel",
+                      "type": "string"
+                    }
+                  },
+                  "required": ["filetype"]
                 }
               ]
             },

airbyte-integrations/connectors/source-s3/integration_tests/spec.json

@@ -1,5 +1,7 @@
 {
   "documentationUrl": "https://docs.airbyte.com/integrations/sources/s3",
+  "supportsNormalization": false,
+  "supportsDBT": false,
   "connectionSpecification": {
     "title": "Config",
     "description": "NOTE: When this Spec is changed, legacy_config_transformer.py must also be modified to uptake the changes\nbecause it is responsible for converting legacy S3 v3 configs into v4 configs using the File-Based CDK.",
@@ -338,6 +340,19 @@
                   },
                   "description": "Extract text from document formats (.pdf, .docx, .md, .pptx) and emit as one record per file.",
                   "required": ["filetype"]
+                },
+                {
+                  "title": "Excel Format",
+                  "type": "object",
+                  "properties": {
+                    "filetype": {
+                      "title": "Filetype",
+                      "default": "excel",
+                      "const": "excel",
+                      "type": "string"
+                    }
+                  },
+                  "required": ["filetype"]
                 }
               ]
             },

airbyte-integrations/connectors/source-s3/integration_tests/test_acceptance.py

@@ -0,0 +1,110 @@
+# Copyright (c) 2024 Airbyte, Inc., all rights reserved.
+
+"""Run a subset of acceptance tests in PyTest.
+
+This test file provides a means to easily step through a subset of acceptance tests, debugging
+and verifying the behavior of the source-s3 connector. The tests are redundant with CAT, but
+are much faster to run and easier to debug.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+import pytest
+import yaml
+from pydantic import BaseModel
+from source_s3.run import get_source
+
+from airbyte_cdk import AirbyteTracedException, launch
+
+
+class AcceptanceTestExpectRecords(BaseModel):
+    path: str
+    exact_order: bool = False
+
+
+class AcceptanceTestFileTypes(BaseModel):
+    skip_test: bool
+    bypass_reason: str
+
+
+class AcceptanceTestInstance(BaseModel):
+    config_path: str
+    timeout_seconds: int
+    expect_records: AcceptanceTestExpectRecords | None = None
+    file_types: AcceptanceTestFileTypes | None = None
+
+
+class AcceptanceTestFullRefreshInstance(AcceptanceTestInstance):
+    config_path: str
+    timeout_seconds: int
+    expect_records: AcceptanceTestExpectRecords | None = None
+    file_types: AcceptanceTestFileTypes | None = None
+    configured_catalog_path: str
+
+
+def get_tests(category: str) -> list[AcceptanceTestInstance]:
+    all_tests_config = yaml.safe_load(Path("acceptance-test-config.yml").read_text())
+    if category == "basic_read" and category in all_tests_config["acceptance_tests"]:
+        return [AcceptanceTestInstance.model_validate(test) for test in all_tests_config["acceptance_tests"][category]["tests"]]
+
+    if category == "full_refresh" and category in all_tests_config["acceptance_tests"]:
+        return [
+            AcceptanceTestFullRefreshInstance.model_validate(
+                test,
+            )
+            for test in all_tests_config["acceptance_tests"][category]["tests"]
+        ]
+
+    return []
+
+
+@pytest.mark.parametrize("instance", get_tests("full_refresh"), ids=lambda instance: instance.config_path.split("/")[-1])
+def test_full_refresh(instance: AcceptanceTestFullRefreshInstance) -> None:
+    """Run acceptance tests."""
+    args = [
+        "read",
+        "--config",
+        instance.config_path,
+        "--catalog",
+        instance.configured_catalog_path,
+    ]
+    source = get_source(args=args)
+    assert source
+    launch(source, args=args)
+
+
+def test_invalid_config(capsys: pytest.CaptureFixture[str]) -> None:
+    """Ensure that the invalid config is properly reported."""
+
+    args = [
+        "check",
+        "--config",
+        "integration_tests/invalid_config.json",
+    ]
+    source = get_source(args=args)
+    assert source
+    try:
+        launch(source, args=args)
+    except AirbyteTracedException as ex:
+        captured = capsys.readouterr()
+        if "CONNECTOR_CONFIG" not in captured.out:
+            raise AssertionError(  # noqa: TRY003
+                "The `CHECK` exception was raised but not printed.",
+            ) from ex
+
+        # Else, the exception was raised and the status messages was printed as expected.
+
+    except Exception as ex:
+        captured = capsys.readouterr()
+        assert "CONNECTOR_CONFIG" in captured.out, "The `CHECK` exception was not printed."
+
+        raise AssertionError(  # noqa: TRY003
+            "Unexpected exception raised during `CHECK`. Handled exceptions should be of type `AirbyteTracedException`.",
+        ) from ex
+
+    else:
+        # No exception was raised.
+        captured = capsys.readouterr()
+        assert "expected_output" in captured.out, "The `CHECK` exception was not printed."

airbyte-integrations/connectors/source-s3/metadata.yaml

@@ -10,7 +10,7 @@ data:
   connectorSubtype: file
   connectorType: source
   definitionId: 69589781-7828-43c5-9f63-8925b1c1ccc2
-  dockerImageTag: 4.8.1
+  dockerImageTag: 4.9.0
   dockerRepository: airbyte/source-s3
   documentationUrl: https://docs.airbyte.com/integrations/sources/s3
   githubIssueLabel: source-s3