Skip to content

Python tool for converting files and office documents to Markdown.

If puremagic has no guesses, try again after ltrim. (#260)

afourney436407288f01
diff --git a/src/markitdown/_markitdown.py b/src/markitdown/_markitdown.py
index 50c83b46..aceaa86d 100644
--- a/src/markitdown/_markitdown.py
+++ b/src/markitdown/_markitdown.py
@@ -1594,6 +1594,25 @@ class MarkItDown:
# Use puremagic to guess
try:
guesses = puremagic.magic_file(path)
+
+ # Fix for: https://github.com/microsoft/markitdown/issues/222
+ # If there are no guesses, then try again after trimming leading ASCII whitespaces.
+ # ASCII whitespace characters are those byte values in the sequence b' \t\n\r\x0b\f'
+ # (space, tab, newline, carriage return, vertical tab, form feed).
+ if len(guesses) == 0:
+ with open(path, "rb") as file:
+ while True:
+ char = file.read(1)
+ if not char: # End of file
+ break
+ if not char.isspace():
+ file.seek(file.tell() - 1)
+ break
+ try:
+ guesses = puremagic.magic_stream(file)
+ except puremagic.main.PureError:
+ pass
+
extensions = list()
for g in guesses:
ext = g.extension.strip()
diff --git a/tests/test_markitdown.py b/tests/test_markitdown.py
index 9dc7374a..e2d2e75f 100644
--- a/tests/test_markitdown.py
+++ b/tests/test_markitdown.py
@@ -259,7 +259,7 @@ def test_markitdown_local() -> None:
# 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")
+ result = markitdown.convert_stream(io.BytesIO(input_data))
assert "# Test" in result.text_content