Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
9 changes: 8 additions & 1 deletion src/backend/services/blob_store.py
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@
import shutil
from collections.abc import Mapping
from dataclasses import dataclass
from email.header import Header
from pathlib import Path, PurePosixPath
from typing import Any, Protocol
from urllib.parse import urlsplit
Expand Down Expand Up @@ -123,7 +124,13 @@ def _normalise_s3_metadata(metadata: Mapping[str, str] | None) -> dict[str, str]
raise ValueError(
f"S3 metadata keys collide after normalisation: {wire_key!r}"
)
wire_metadata[wire_key] = str(value)
wire_value = str(value)
if not wire_value.isascii():
# Botocore requires ASCII metadata headers. S3 specifies RFC 2047
# for Unicode values; preserve the original in the returned BlobRef
# and canonical file metadata, encoding only the transport value.
wire_value = Header(wire_value, "utf-8").encode(linesep=" ")
wire_metadata[wire_key] = wire_value
return wire_metadata


Expand Down
42 changes: 42 additions & 0 deletions tests/test_blob_store.py
Original file line number Diff line number Diff line change
Expand Up @@ -603,6 +603,48 @@ def put_object(self, **kwargs):
assert ref.metadata == metadata


@pytest.mark.parametrize("upload_mode", ["bytes", "file"])
@pytest.mark.parametrize(
"filename",
["Research \u2013 \u201csummary\u201d.pdf", "\u7814\u7a76\u8a08\u753b.pdf", "\u7814\u7a76\u8a08\u753b " * 25 + ".pdf"],
)
def test_s3_blob_store_preserves_unicode_metadata_on_upload(
tmp_path, upload_mode, filename
):
from email.header import decode_header, make_header

from botocore.handlers import validate_ascii_metadata

class _DummyClient:
def put_object(self, **kwargs):
validate_ascii_metadata(kwargs)
self.metadata = kwargs["Metadata"]

def upload_fileobj(self, handle, bucket, key, *, ExtraArgs):
assert handle.read() == b"source bytes"
self.put_object(**ExtraArgs)

store = S3BlobStore.__new__(S3BlobStore)
store._bucket = "demo-bucket"
store._prefix = ""
store._public_base_url = None
store._client = _DummyClient()
metadata = {"original_filename": filename, "sha256": "abc123"}
store._endpoint_url = "https://storage.example"
if upload_mode == "file":
source = tmp_path / "source.pdf"
source.write_bytes(b"source bytes")
ref = store.put_file("source.pdf", source, metadata=metadata)
else:
ref = store.put_bytes("source.pdf", b"source bytes", metadata=metadata)

wire_filename = store._client.metadata["original-filename"]
assert "\n" not in wire_filename and "\r" not in wire_filename
assert str(make_header(decode_header(wire_filename))) == filename
assert store._client.metadata["sha256"] == "abc123"
assert ref.metadata == metadata


def test_s3_blob_store_exists_returns_false_for_missing_object():
class _MissingObject(Exception):
def __init__(self):
Expand Down
Loading