Fix markitdown.convert_stream handling of leading blanks

Fixes #222 Address issue with `markitdown.convert_stream` crashing on input with leading blank characters or line breaks. * Modify `convert_stream` function in `src/markitdown/_markitdown.py` to strip leading blank characters or line breaks from the input stream using a new helper function `_strip_leading_blanks`. * Add a test case in `tests/test_markitdown.py` to verify that `markitdown.convert_stream` handles input with leading blank characters or line breaks correctly. --- For more details, open the [Copilot Workspace session](https://copilot-workspace.githubnext.com/microsoft/markitdown/issues/222?shareId=XXXX-XXXX-XXXX-XXXX).
microsoft · Dec 27, 2024 · bf72b4a · bf72b4a
1 parent 125e206
commit bf72b4a
Show file tree

Hide file tree

Showing 2 changed files with 15 additions and 1 deletion.
diff --git a/src/markitdown/_markitdown.py b/src/markitdown/_markitdown.py
@@ -1344,7 +1344,7 @@ def convert_stream(
         result = None
         try:
             # Write to the temporary file
-            content = stream.read()
+            content = self._strip_leading_blanks(stream.read())
             if isinstance(content, str):
                 fh.write(content.encode("utf-8"))
             else:
@@ -1367,6 +1367,10 @@ def convert_stream(
 
         return result
 
+    def _strip_leading_blanks(self, content: bytes) -> bytes:
+        """Helper function to strip leading blank characters or line breaks from content."""
+        return content.lstrip()
+
     def convert_url(
         self, url: str, **kwargs: Any
     ) -> DocumentConverterResult:  # TODO: fix kwargs type

diff --git a/tests/test_markitdown.py b/tests/test_markitdown.py
@@ -300,10 +300,20 @@ def test_markitdown_llm() -> None:
         assert test_string in result.text_content.lower()
 
 
+def test_markitdown_strip_leading_blanks() -> None:
+    markitdown = MarkItDown()
+
+    # Test input with leading blank characters
+    input_data = b"   \n\n\n<html><body><h1>Test</h1></body></html>"
+    result = markitdown.convert_stream(io.BytesIO(input_data), file_extension=".html")
+    assert "<h1>Test</h1>" in result.text_content
+
+
 if __name__ == "__main__":
     """Runs this file's tests from the command line."""
     test_markitdown_remote()
     test_markitdown_local()
     test_markitdown_exiftool()
     test_markitdown_deprecation()
     test_markitdown_llm()
+    test_markitdown_strip_leading_blanks()