Merge pull request #742 from mih/decodebytes

fix(`decode_bytes`): always backslashreplace when asked to
datalad · Jul 11, 2024 · b20e779 · b20e779
2 parents bbe6c04 + 7a73d8c
commit b20e779
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 1 deletion.
diff --git a/datalad_next/itertools/decode_bytes.py b/datalad_next/itertools/decode_bytes.py
@@ -103,7 +103,7 @@ def handle_decoding_error(position: int,
         else:
             return (
                 position + exc.end,
-                joined_data[:position + exc.start].decode(encoding)
+                joined_data[position:position + exc.start].decode(encoding)
                 + joined_data[position + exc.start:position + exc.end].decode(
                     encoding,
                     errors='backslashreplace'

diff --git a/datalad_next/itertools/tests/test_decode_bytes.py b/datalad_next/itertools/tests/test_decode_bytes.py
@@ -35,3 +35,8 @@ def test_no_empty_strings():
     # check that empty strings are not yielded
     r = tuple(decode_bytes([b'\xc3', b'\xb6']))
     assert r == ('ö',)
+
+
+def test_multiple_errors():
+    r = ''.join(decode_bytes([b'08 War \xaf No \xaf More \xaf Trouble.shn.mp3']))
+    assert r == '08 War \\xaf No \\xaf More \\xaf Trouble.shn.mp3'