aarmens702-hub opened a new pull request, #76389: URL: https://github.com/apache/airflow/pull/76389
LLMFileAnalysisOperator showed CSV sample rows with their quotes removed, so a value holding a comma or a line break looked like several values to the model. Values that need quoting are now quoted the way CSV quotes them, and all other values render as before. Tested with a new `test_csv_values_keep_their_quotes` in `test_file_analysis.py` (a quoted comma, an escaped quote and a line break). It fails on main and passes with this change. `test_file_analysis.py`, `test_llm_file_analysis.py` and `test_object_storage.py` pass (120 passed, 8 skipped because fastavro isn't installed). `ruff format`, `ruff check` and `mypy` on the changed file are clean. I didn't run the full `prek` set or breeze. closes: #76386 --- ##### Was generative AI tooling used to co-author this PR? - [X] Yes (please specify the tool below) Generated-by: Claude Code (Opus 5.5) following [the guidelines](https://github.com/apache/airflow/blob/main/contributing-docs/05_pull_requests.rst#gen-ai-assisted-contributions) -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
