refactor(mail): address PR #935 round-1 review

- models/mail.py: lowercase `list` generics per CLAUDE.md convention. - client/mail.py: _ocs_get now inspects ocs.meta.statuscode (re-raises >=400 as HTTPStatusError carrying the OCS code so callers' 404/403 handling applies) and guards response.json() against non-JSON bodies (RequestError). - Extract the duplicated _format_addresses + content reconstruction into vector/mail_content.py, used by both processor.py and context.py (fixes the SonarCloud new_duplicated_lines_density gate). - processor.py: add the missing mail_message Qdrant payload block so the computed mail metadata (subject/from/to/cc/date_int/has_attachments/ account_id/mailbox_id) is actually stored, not dropped. - Rename the list_messages `filter` param to `search_filter` (avoid shadowing builtins.filter); still maps to the OCS `filter` query param. - Docstring notes: has_more heuristic, attachment content size. - Tests: OCS meta-failure + non-JSON client paths; initial-sync scanner tests (tests/unit/vector/test_scanner_mail.py). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-20 12:31:32 +02:00
parent 3074622455
commit 62ee3e9f32
8 changed files with 303 additions and 94 deletions
@@ -108,7 +108,7 @@ async def test_list_messages_builds_params(mocker):

    client = MailClient(mock_client, "testuser")
    messages = await client.list_messages(
-        10, cursor=42, filter="hello", limit=50, view="threaded"
+        10, cursor=42, search_filter="hello", limit=50, view="threaded"
    )

    assert len(messages) == 1
@@ -204,3 +204,40 @@ async def test_empty_data_returns_empty_list(mocker):

    client = MailClient(mock_client, "testuser")
    assert await client.list_accounts() == []
+
+
+async def test_ocs_meta_failure_raises_httpstatuserror(mocker):
+    """HTTP 200 with an OCS meta failure code is re-raised as HTTPStatusError.
+
+    The synthetic response carries the OCS statuscode so callers' 404/403
+    handling applies (e.g. nc_mail_get_message maps 404 to 'not found').
+    """
+    mock_response = create_mock_response(
+        status_code=200,
+        json_data={
+            "ocs": {
+                "meta": {"status": "failure", "statuscode": 404, "message": "nope"},
+                "data": None,
+            }
+        },
+    )
+    mock_client = mocker.AsyncMock(spec=httpx.AsyncClient)
+    mocker.patch.object(MailClient, "_make_request", return_value=mock_response)
+
+    client = MailClient(mock_client, "testuser")
+    with pytest.raises(httpx.HTTPStatusError) as excinfo:
+        await client.get_message(100)
+    assert excinfo.value.response.status_code == 404
+
+
+async def test_non_json_response_raises_requesterror(mocker):
+    """A non-JSON 200 body (e.g. Mail app absent) raises a RequestError."""
+    mock_response = create_mock_response(
+        status_code=200, content=b"<html>not found</html>"
+    )
+    mock_client = mocker.AsyncMock(spec=httpx.AsyncClient)
+    mocker.patch.object(MailClient, "_make_request", return_value=mock_response)
+
+    client = MailClient(mock_client, "testuser")
+    with pytest.raises(httpx.RequestError):
+        await client.list_accounts()
@@ -0,0 +1,123 @@
+"""Unit tests for the mail-message scanner (initial-sync path).
+
+The incremental path depends on live Qdrant lookups (``_scroll_all_points`` /
+``query_document_metadata``); these tests cover the initial-sync enumeration —
+accounts → mailboxes → newest-N messages — which is the bulk of the new logic
+and needs no Qdrant.
+"""
+
+from unittest.mock import AsyncMock, MagicMock
+
+import pytest
+
+from nextcloud_mcp_server.vector import scanner as scanner_module
+from nextcloud_mcp_server.vector.scanner import DocumentTask, scan_mail_messages
+
+pytestmark = pytest.mark.unit
+
+
+class _CollectingStream:
+    """Minimal TaskProducer stand-in that records sent DocumentTasks."""
+
+    def __init__(self) -> None:
+        self.tasks: list[DocumentTask] = []
+
+    async def send(self, task: DocumentTask) -> None:
+        self.tasks.append(task)
+
+
+async def test_initial_sync_enumerates_accounts_mailboxes_messages(mocker):
+    nc_client = MagicMock()
+    nc_client.mail.list_accounts = AsyncMock(return_value=[{"id": 1}])
+    nc_client.mail.get_mailboxes = AsyncMock(
+        return_value=[{"databaseId": 10}, {"databaseId": 11}]
+    )
+
+    async def list_messages(mailbox_id, *, limit):
+        if mailbox_id == 10:
+            return [
+                {"databaseId": 100, "dateInt": 1700000000},
+                {"databaseId": 101, "dateInt": 1700000001},
+            ]
+        return [{"databaseId": 200, "dateInt": 1700000002}]
+
+    nc_client.mail.list_messages = AsyncMock(side_effect=list_messages)
+
+    placeholder = mocker.patch.object(
+        scanner_module, "write_placeholder_point", new=AsyncMock()
+    )
+    mocker.patch.object(scanner_module, "record_vector_sync_scan")
+
+    stream = _CollectingStream()
+    queued = await scan_mail_messages(
+        user_id="alice",
+        send_stream=stream,
+        nc_client=nc_client,
+        initial_sync=True,
+        scan_id=1,
+    )
+
+    assert queued == 3
+    assert len(stream.tasks) == 3
+    # All are mail_message index tasks carrying account/mailbox metadata.
+    assert {t.doc_id for t in stream.tasks} == {"100", "101", "200"}
+    assert all(t.doc_type == "mail_message" for t in stream.tasks)
+    assert all(t.operation == "index" for t in stream.tasks)
+    t100 = next(t for t in stream.tasks if t.doc_id == "100")
+    assert t100.modified_at == 1700000000
+    assert t100.metadata == {"account_id": 1, "mailbox_id": 10}
+    # A placeholder is written per message before queueing.
+    assert placeholder.await_count == 3
+    # The per-mailbox cap is passed through.
+    nc_client.mail.list_messages.assert_any_await(
+        10, limit=scanner_module.MAIL_SCAN_MAX_PER_MAILBOX
+    )
+
+
+async def test_initial_sync_skips_mailbox_on_list_error(mocker):
+    """A failing mailbox is logged and skipped; other mailboxes still index."""
+    nc_client = MagicMock()
+    nc_client.mail.list_accounts = AsyncMock(return_value=[{"id": 1}])
+    nc_client.mail.get_mailboxes = AsyncMock(
+        return_value=[{"databaseId": 10}, {"databaseId": 11}]
+    )
+
+    async def list_messages(mailbox_id, *, limit):
+        if mailbox_id == 10:
+            raise RuntimeError("imap hiccup")
+        return [{"databaseId": 200, "dateInt": 1700000002}]
+
+    nc_client.mail.list_messages = AsyncMock(side_effect=list_messages)
+    mocker.patch.object(scanner_module, "write_placeholder_point", new=AsyncMock())
+    mocker.patch.object(scanner_module, "record_vector_sync_scan")
+
+    stream = _CollectingStream()
+    queued = await scan_mail_messages(
+        user_id="alice",
+        send_stream=stream,
+        nc_client=nc_client,
+        initial_sync=True,
+        scan_id=1,
+    )
+
+    assert queued == 1
+    assert {t.doc_id for t in stream.tasks} == {"200"}
+
+
+async def test_no_accounts_queues_nothing(mocker):
+    nc_client = MagicMock()
+    nc_client.mail.list_accounts = AsyncMock(return_value=[])
+    mocker.patch.object(scanner_module, "write_placeholder_point", new=AsyncMock())
+    mocker.patch.object(scanner_module, "record_vector_sync_scan")
+
+    stream = _CollectingStream()
+    queued = await scan_mail_messages(
+        user_id="alice",
+        send_stream=stream,
+        nc_client=nc_client,
+        initial_sync=True,
+        scan_id=1,
+    )
+
+    assert queued == 0
+    assert stream.tasks == []