webmail-client/backend/tests/indexer/test_streaming_parse.py

"""Bounded / streaming MIME parse (refactor §7).

Large messages are parsed from their blob file rather than an in-memory tree, and
all parsing passes through the PARSE_CONCURRENCY semaphore.
"""

from __future__ import annotations

import uuid
from email.message import EmailMessage
from pathlib import Path

from app.indexer import indexer
from app.indexer.mime import parse_message, parse_message_file


def _raw(body: str = "hello") -> bytes:
    msg = EmailMessage()
    msg["Subject"] = "Streamed"
    msg["From"] = "a@example.com"
    msg["To"] = "b@example.com"
    msg["Message-ID"] = "<s1@example.com>"
    msg.set_content(body)
    msg.add_attachment(
        b"x" * 1024, maintype="application", subtype="octet-stream", filename="a.bin"
    )
    return msg.as_bytes()


def test_parse_file_matches_bytes(tmp_path) -> None:  # type: ignore[no-untyped-def]
    raw = _raw()
    path = tmp_path / "msg.eml"
    path.write_bytes(raw)
    # Parsing from the file handle yields exactly the same ParsedEmail as from bytes.
    assert parse_message_file(path) == parse_message(raw)


async def test_parse_bounded_streams_large_messages(monkeypatch) -> None:  # type: ignore[no-untyped-def]
    from app.config import get_settings

    threshold = get_settings().stream_parse_mb * 1024 * 1024
    calls: list[str] = []

    def fake_file(path: object) -> str:
        calls.append("file")
        return "file"

    def fake_bytes(raw: bytes) -> str:
        calls.append("bytes")
        return "bytes"

    monkeypatch.setattr(indexer, "parse_message_file", fake_file)
    monkeypatch.setattr(indexer, "parse_message", fake_bytes)
    # The message's file, written before parsing (blob store or raw cache).
    monkeypatch.setattr(indexer.rawstore, "locate", lambda user_id, sha: Path("/blob"))

    user_id = uuid.uuid4()
    small = await indexer._parse_bounded(user_id, "sha", b"x" * 16)
    big = await indexer._parse_bounded(user_id, "sha", b"x" * (threshold + 1))

    assert small == "bytes"  # small stays in memory
    assert big == "file"  # over threshold => parsed from the blob file
    assert calls == ["bytes", "file"]