Skip to content

fix: truncate uppercase data image URIs #2122

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

Open
pony-maggie wants to merge 1 commit into
base: main
Choose a base branch
from
+16 −1
Open

fix: truncate uppercase data image URIs #2122

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
2 changes: 1 addition & 1 deletion packages/markitdown/src/markitdown/converters/_markdownify.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,7 +104,7 @@ def convert_img(
return alt

# Remove dataURIs
if src.startswith("data:") and not self.options["keep_data_uris"]:
if src.lower().startswith("data:") and not self.options["keep_data_uris"]:
src = src.split(",")[0] + "..."

return "![%s](%s%s)" % (alt, src, title_part)
Expand Down
15 changes: 15 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 @@ -220,6 +220,21 @@ def test_data_uris() -> None:
assert data == b"Hello, World!"


def test_uppercase_data_image_uri_is_truncated_by_default() -> None:
markitdown = MarkItDown()
html = b'<html><body><img alt="dot" src="DATA:image/png;base64,AAAA"></body></html>'
stream_info = StreamInfo(mimetype="text/html", extension=".html")

result = markitdown.convert_stream(io.BytesIO(html), stream_info=stream_info)
assert result.markdown == "![dot](DATA:image/png;base64...)"
assert "AAAA" not in result.markdown

result = markitdown.convert_stream(
io.BytesIO(html), stream_info=stream_info, keep_data_uris=True
)
assert result.markdown == "![dot](DATA:image/png;base64,AAAA)"


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