Merge branch 'refs/heads/main' into fix/3119-pdf-empty-table-cell

# Conflicts:
#	CHANGELOG.md
#	unstructured/__version__.py

CHANGELOG.md

@@ -13,6 +13,7 @@
 ### Fixes
 
 * **Address the issue of unrecognized tables in `UnstructuredTableTransformerModel`** When a table is not recognized, the `element.metadata.text_as_html` attribute is set to an empty string.
+* **Remove root handlers in ingest logger**. Removes root handlers in ingest loggers to ensure secrets aren't accidentally exposed in Colab notebooks.
 * **Fix V2 S3 Destination Connector authentication** Fixes bugs with S3 Destination Connector where the connection config was neither registered nor properly deserialized.
 * **Clarified dependence on particular version of `python-docx`** Pinned `python-docx` version to ensure a particular method `unstructured` uses is included.
 * **Ingest preserves original file extension** Ingest V2 introduced a change that dropped the original extension for upgraded connectors. This reverts that change.

unstructured/ingest/logger.py

@@ -94,6 +94,15 @@ def format(self, record):
         return redact_jsons(s)
 
 
+def remove_root_handlers(logger: logging.Logger) -> None:
+    # NOTE(robinson) - in some environments such as Google Colab, there is a root handler
+    # that doesn't not mask secrets, meaning sensitive info such as api keys appear in logs.
+    # Removing these when they exist prevents this behavior
+    if logger.root.hasHandlers():
+        for handler in logger.root.handlers:
+            logger.root.removeHandler(handler)
+
+
 def ingest_log_streaming_init(level: int) -> None:
     handler = logging.StreamHandler()
     handler.name = "ingest_log_handler"
@@ -104,6 +113,7 @@ def ingest_log_streaming_init(level: int) -> None:
     if "ingest_log_handler" not in [h.name for h in logger.handlers]:
         logger.addHandler(handler)
 
+    remove_root_handlers(logger)
     logger.setLevel(level)
 
 
@@ -116,4 +126,5 @@ def make_default_logger(level: int) -> logging.Logger:
     handler.setFormatter(formatter)
     logger.addHandler(handler)
     logger.setLevel(level)
+    remove_root_handlers(logger)
     return logger