Skip to content

fix: propagate zip converter options to nested files #2143

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
zaidazmi wants to merge 1 commit into from
Closed

fix: propagate zip converter options to nested files #2143

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions packages/markitdown/src/markitdown/converters/_zip_converter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,6 +104,7 @@ def convert(
result = self._markitdown.convert_stream(
stream=z_file_stream,
stream_info=z_file_stream_info,
**kwargs,
)
if result is not None:
md_content += f"## File: {name}\n\n"
Expand Down
20 changes: 20 additions & 0 deletions packages/markitdown/tests/test_module_misc.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,7 @@
import os
import re
import shutil
import zipfile
import pytest
from unittest.mock import MagicMock

Expand Down Expand Up @@ -220,6 +221,25 @@ def test_data_uris() -> None:
assert data == b"Hello, World!"


def test_zip_conversion_propagates_keep_data_uris() -> None:
archive = io.BytesIO()
html = (
"<html><body><img alt='example' "
"src='data:image/png;base64,SGVsbG8='></body></html>"
)
with zipfile.ZipFile(archive, "w") as zf:
zf.writestr("index.html", html)
archive.seek(0)

result = MarkItDown().convert_stream(
archive,
stream_info=StreamInfo(extension=".zip", mimetype="application/zip"),
keep_data_uris=True,
)

assert "data:image/png;base64,SGVsbG8=" in result.markdown


def test_file_uris() -> None:
# Test file URI with an empty host
file_uri = "file:///path/to/file.txt"
Expand Down