Skip to content

Preserve percent-encoded href octets #2200

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
mturac wants to merge 1 commit into from
Closed

Preserve percent-encoded href octets #2200

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
21 changes: 19 additions & 2 deletions packages/markitdown/src/markitdown/converters/_markdownify.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,18 @@
import markdownify

from typing import Any, Optional
from urllib.parse import quote, unquote, urlparse, urlunparse
from urllib.parse import quote, urlparse, urlunparse


def _quote_path_preserving_percent_encoded_octets(path: str) -> str:
parts = []
start = 0
for match in re.finditer(r"%[0-9A-Fa-f]{2}", path):
parts.append(quote(path[start : match.start()], safe="/"))
parts.append(match.group(0))
start = match.end()
parts.append(quote(path[start:], safe="/"))
return "".join(parts)


class _CustomMarkdownify(markdownify.MarkdownConverter):
Expand Down Expand Up @@ -60,7 +71,13 @@ def convert_a(
parsed_url = urlparse(href) # type: ignore
if parsed_url.scheme and parsed_url.scheme.lower() not in ["http", "https", "file"]: # type: ignore
return "%s%s%s" % (prefix, text, suffix)
href = urlunparse(parsed_url._replace(path=quote(unquote(parsed_url.path)))) # type: ignore
href = urlunparse(
parsed_url._replace(
path=_quote_path_preserving_percent_encoded_octets(
parsed_url.path
)
)
) # type: ignore
except ValueError: # It's not clear if this ever gets thrown
return "%s%s%s" % (prefix, text, suffix)

Expand Down
24 changes: 24 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 @@ -288,6 +288,30 @@ def test_input_as_strings() -> None:
assert "# Test" in result.text_content


def test_html_preserves_percent_encoded_href_octets() -> None:
markitdown = MarkItDown()
href = "https://abc.com/hist/%a5%c8%a5%c3%a5%d7%a5%da%a1%bc%a5%b8"
input_data = f'<html><body><a href="{href}">example</a></body></html>'

result = markitdown.convert_stream(
io.BytesIO(input_data.encode("utf-8")),
file_extension=".html",
)

assert f"[example]({href})" in result.text_content
assert "%EF%BF%BD" not in result.text_content

raw_percent_href = "https://abc.com/hist/100% ready.html"
input_data = f'<html><body><a href="{raw_percent_href}">raw</a></body></html>'

result = markitdown.convert_stream(
io.BytesIO(input_data.encode("utf-8")),
file_extension=".html",
)

assert "[raw](https://abc.com/hist/100%25%20ready.html)" in result.text_content


def test_deeply_nested_html_fallback() -> None:
"""Large, deeply nested HTML should fall back to plain-text extraction
instead of silently returning unconverted HTML (issue #1636).
Expand Down