Print and log better exceptions when file conversions fail. (#1080)

* Print and log better exceptions when file conversions fail.
* Added unit tests for exceptions.

packages/markitdown/src/markitdown/__init__.py

@@ -7,6 +7,7 @@ from ._markitdown import MarkItDown
 from ._exceptions import (
     MarkItDownException,
     ConverterPrerequisiteException,
+    FailedConversionAttempt,
     FileConversionException,
     UnsupportedFormatException,
 )
@@ -19,6 +20,7 @@ __all__ = [
     "DocumentConverterResult",
     "MarkItDownException",
     "ConverterPrerequisiteException",
+    "FailedConversionAttempt",
     "FileConversionException",
     "UnsupportedFormatException",
 ]

packages/markitdown/src/markitdown/_exceptions.py

@@ -1,3 +1,6 @@
+from typing import Optional, List, Any
+
+
 class MarkItDownException(BaseException):
     """
     Base exception class for MarkItDown.
@@ -20,18 +23,43 @@ class ConverterPrerequisiteException(MarkItDownException):
     pass
 
 
-class FileConversionException(MarkItDownException):
-    """
-    Thrown when a suitable converter was found, but the conversion
-    process fails for any reason.
-    """
-
-    pass
-
-
 class UnsupportedFormatException(MarkItDownException):
     """
     Thrown when no suitable converter was found for the given file.
     """
 
     pass
+
+
+class FailedConversionAttempt(object):
+    """
+    Represents an a single attempt to convert a file.
+    """
+
+    def __init__(self, converter: Any, exc_info: Optional[tuple] = None):
+        self.converter = converter
+        self.exc_info = exc_info
+
+
+class FileConversionException(MarkItDownException):
+    """
+    Thrown when a suitable converter was found, but the conversion
+    process fails for any reason.
+    """
+
+    def __init__(
+        self,
+        message: Optional[str] = None,
+        attempts: Optional[List[FailedConversionAttempt]] = None,
+    ):
+        self.attempts = attempts
+
+        if message is None:
+            if attempts is None:
+                message = "File conversion failed."
+            else:
+                message = f"File conversion failed after {len(attempts)} attempts:\n"
+                for attempt in attempts:
+                    message += f" - {type(attempt.converter).__name__} threw {attempt.exc_info[0].__name__} with message: {attempt.exc_info[1]}\n"
+
+        super().__init__(message)

packages/markitdown/src/markitdown/_markitdown.py

@@ -2,6 +2,7 @@ import copy
 import mimetypes
 import os
 import re
+import sys
 import tempfile
 import warnings
 import traceback
@@ -42,6 +43,7 @@ from ._exceptions import (
     FileConversionException,
     UnsupportedFormatException,
     ConverterPrerequisiteException,
+    FailedConversionAttempt,
 )
 
 # Override mimetype for csv to fix issue on windows
@@ -313,7 +315,9 @@ class MarkItDown:
         self, local_path: str, extensions: List[Union[str, None]], **kwargs
     ) -> DocumentConverterResult:
         res: Union[None, DocumentConverterResult] = None
-        error_trace = ""
+
+        # Keep track of which converters throw exceptions
+        failed_attempts: List[FailedConversionAttempt] = []
 
         # Create a copy of the page_converters list, sorted by priority.
         # We do this with each call to _convert because the priority of converters may change between calls.
@@ -351,7 +355,11 @@ class MarkItDown:
                 try:
                     res = converter.convert(local_path, **_kwargs)
                 except Exception:
-                    error_trace = ("\n\n" + traceback.format_exc()).strip()
+                    failed_attempts.append(
+                        FailedConversionAttempt(
+                            converter=converter, exc_info=sys.exc_info()
+                        )
+                    )
 
                 if res is not None:
                     # Normalize the content
@@ -364,14 +372,12 @@ class MarkItDown:
                     return res
 
         # If we got this far without success, report any exceptions
-        if len(error_trace) > 0:
-            raise FileConversionException(
-                f"Could not convert '{local_path}' to Markdown. File type was recognized as {extensions}. While converting the file, the following error was encountered:\n\n{error_trace}"
-            )
+        if len(failed_attempts) > 0:
+            raise FileConversionException(attempts=failed_attempts)
 
         # Nothing can handle it!
         raise UnsupportedFormatException(
-            f"Could not convert '{local_path}' to Markdown. The formats {extensions} are not supported."
+            f"Could not convert '{local_path}' to Markdown. No converter attempted a conversion, suggesting that the filetype is simply not supported."
         )
 
     def _append_ext(self, extensions, ext):

packages/markitdown/tests/test_markitdown.py

@@ -8,7 +8,7 @@ import requests
 
 from warnings import catch_warnings, resetwarnings
 
-from markitdown import MarkItDown
+from markitdown import MarkItDown, UnsupportedFormatException, FileConversionException
 
 skip_remote = (
     True if os.environ.get("GITHUB_ACTIONS") else False
@@ -272,6 +272,21 @@ def test_markitdown_local() -> None:
     assert "# Test" in result.text_content
 
 
+def test_exceptions() -> None:
+    # Check that an exception is raised when trying to convert an unsupported format
+    markitdown = MarkItDown()
+    with pytest.raises(UnsupportedFormatException):
+        markitdown.convert(os.path.join(TEST_FILES_DIR, "random.bin"))
+
+    # Check that an exception is raised when trying to convert a file that is corrupted
+    with pytest.raises(FileConversionException) as exc_info:
+        markitdown.convert(
+            os.path.join(TEST_FILES_DIR, "random.bin"), file_extension=".pptx"
+        )
+    assert len(exc_info.value.attempts) == 1
+    assert type(exc_info.value.attempts[0].converter).__name__ == "PptxConverter"
+
+
 @pytest.mark.skipif(
     skip_exiftool,
     reason="do not run if exiftool is not installed",
@@ -329,6 +344,7 @@ if __name__ == "__main__":
     """Runs this file's tests from the command line."""
     test_markitdown_remote()
     test_markitdown_local()
+    test_exceptions()
     test_markitdown_exiftool()
     # test_markitdown_llm()
     print("All tests passed!")