🐛 Source S3: fix exception when setting CSV stream delimiter to \t. (airbytehq#35246)

Co-authored-by: Marcos Marx <[email protected]>
Co-authored-by: marcosmarxm <[email protected]>

Author: 2 people

airbyte-cdk/python/airbyte_cdk/sources/file_based/config/csv_format.py

@@ -150,6 +150,8 @@ class Config(OneOfOptionConfig):
 
     @validator("delimiter")
     def validate_delimiter(cls, v: str) -> str:
+        if v == r"\t":
+            return v
         if len(v) != 1:
             raise ValueError("delimiter should only be one character")
         if v in {"\r", "\n"}:

airbyte-cdk/python/unit_tests/sources/file_based/config/test_csv_format.py

@@ -5,7 +5,7 @@
 import unittest
 
 import pytest
-from airbyte_cdk.sources.file_based.config.csv_format import CsvHeaderAutogenerated, CsvHeaderFromCsv, CsvHeaderUserProvided
+from airbyte_cdk.sources.file_based.config.csv_format import CsvFormat, CsvHeaderAutogenerated, CsvHeaderFromCsv, CsvHeaderUserProvided
 from pydantic import ValidationError
 
 
@@ -26,3 +26,8 @@ def test_given_autogenerated_then_csv_does_not_have_header_row(self) -> None:
 
     def test_given_from_csv_then_csv_has_header_row(self) -> None:
         assert CsvHeaderFromCsv().has_header_row()
+
+
+class CsvDelimiterTest(unittest.TestCase):
+    def test_tab_delimter(self):
+        assert CsvFormat(delimiter=r"\t").delimiter == '\\t'

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

@@ -10,7 +10,7 @@ data:
   connectorSubtype: file
   connectorType: source
   definitionId: 69589781-7828-43c5-9f63-8925b1c1ccc2
-  dockerImageTag: 4.5.5
+  dockerImageTag: 4.5.6
   dockerRepository: airbyte/source-s3
   documentationUrl: https://docs.airbyte.com/integrations/sources/s3
   githubIssueLabel: source-s3

airbyte-integrations/connectors/source-s3/pyproject.toml

@@ -3,7 +3,7 @@ requires = [ "poetry-core>=1.0.0",]
 build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
-version = "4.5.5"
+version = "4.5.6"
 name = "source-s3"
 description = "Source implementation for S3."
 authors = [ "Airbyte <[email protected]>",]

docs/integrations/sources/s3.md

@@ -264,6 +264,7 @@ To perform the text extraction from PDF and Docx files, the connector uses the [
 
 | Version | Date       | Pull Request                                                                                                    | Subject                                                                                                              |
 |:--------|:-----------|:----------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------|
+| 4.5.6   | 2024-02-21 | [35246](https://github.com/airbytehq/airbyte/pull/35246)                                                        | Fixes bug that occurred when creating CSV streams with tab delimiter.                                                |
 | 4.5.5   | 2024-02-18 | [35392](https://github.com/airbytehq/airbyte/pull/35392)                                                        | Add support filtering by start date                                                                                  |
 | 4.5.4   | 2024-02-15 | [35055](https://github.com/airbytehq/airbyte/pull/35055)                                                        | Temporarily revert concurrency                                                                                       |
 | 4.5.3   | 2024-02-12 | [35164](https://github.com/airbytehq/airbyte/pull/35164)                                                        | Manage dependencies with Poetry.                                                                                     |