feat(notion-search): add Notion search execution with workspace/DB modes

For each expanded query variant: hit Notion's workspace search OR
per-database data_sources.query (when --databases is specified).
Union and dedupe by page ID, cap at 30 candidates total. Filters out
non-page objects (databases) from workspace search results.
Property filters (--filter JSON) pass through to data_sources.query
when in per-database mode.

5 tests: workspace dedup, 30-cap, DB-mode dispatch, page-only filter,
property-filter passthrough. 17 passing total.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-04-28 07:52:00 +09:00
parent 5f6438ecf3
commit a4da24b15c
2 changed files with 162 additions and 1 deletions

View File

@@ -163,6 +163,104 @@ def test_expand_query_falls_back_on_llm_exception():
_assert(variants == ["AI agents"], "LLM exception falls back to original only")
def test_search_unions_and_dedupes_workspace():
"""Two variants returning overlapping pages produce a deduped candidate set."""
from unittest.mock import MagicMock
import notion_search
notion = MagicMock()
notion.search.side_effect = [
{"results": [
{"id": "page-a", "object": "page", "url": "https://notion.so/a"},
{"id": "page-b", "object": "page", "url": "https://notion.so/b"},
]},
{"results": [
{"id": "page-b", "object": "page", "url": "https://notion.so/b"},
{"id": "page-c", "object": "page", "url": "https://notion.so/c"},
]},
]
candidates = notion_search.search_candidates(
notion, ["query1", "query2"], databases=None
)
ids = [c["id"] for c in candidates]
_assert(set(ids) == {"page-a", "page-b", "page-c"}, "union of pages from both variants")
_assert(len(ids) == 3, "duplicate page-b deduped")
def test_search_caps_candidates_at_30():
"""If total candidates exceed 30, cap to 30."""
from unittest.mock import MagicMock
import notion_search
notion = MagicMock()
notion.search.return_value = {
"results": [
{"id": f"page-{i:02d}", "object": "page", "url": f"https://notion.so/{i}"}
for i in range(40)
]
}
candidates = notion_search.search_candidates(notion, ["query"], databases=None)
_assert(len(candidates) == 30, f"capped to 30 (got {len(candidates)})")
def test_search_uses_data_source_query_when_databases_specified():
"""--databases flag → per-DB data_sources.query instead of workspace search."""
from unittest.mock import MagicMock, patch
import notion_search
notion = MagicMock()
notion.data_sources.query.return_value = {
"results": [{"id": "page-a", "url": "https://notion.so/a"}]
}
with patch("notion_search.compat.resolve_data_source_id",
side_effect=lambda c, ds: ds):
candidates = notion_search.search_candidates(
notion, ["query"], databases=["db-id-1"]
)
_assert(notion.data_sources.query.called, "data_sources.query was called")
_assert(not notion.search.called, "workspace search NOT called when databases specified")
_assert(len(candidates) == 1, "candidate from data source returned")
def test_search_filters_only_pages():
"""search() may return databases too; we keep only object='page'."""
from unittest.mock import MagicMock
import notion_search
notion = MagicMock()
notion.search.return_value = {"results": [
{"id": "page-a", "object": "page", "url": "https://notion.so/a"},
{"id": "db-1", "object": "database", "url": "https://notion.so/db1"},
]}
candidates = notion_search.search_candidates(notion, ["query"], databases=None)
ids = [c["id"] for c in candidates]
_assert("page-a" in ids, "page kept")
_assert("db-1" not in ids, "database object filtered out")
def test_search_passes_property_filter_to_data_sources_query():
"""--filter JSON is passed through to data_sources.query as the `filter` parameter."""
from unittest.mock import MagicMock, patch
import notion_search
notion = MagicMock()
notion.data_sources.query.return_value = {"results": []}
prop_filter = {"property": "Status", "status": {"equals": "Done"}}
with patch("notion_search.compat.resolve_data_source_id",
side_effect=lambda c, ds: ds):
notion_search.search_candidates(
notion, ["query"], databases=["db-id-1"], prop_filter=prop_filter,
)
_assert(notion.data_sources.query.called, "data_sources.query was called")
call_kwargs = notion.data_sources.query.call_args.kwargs
_assert(call_kwargs.get("filter") == prop_filter,
"prop_filter passed through as `filter` keyword argument")
def run_all():
tests = [
test_call_claude_dispatches_to_sdk_when_available,
@@ -177,6 +275,11 @@ def run_all():
test_expand_query_dedupes_and_caps,
test_expand_query_falls_back_on_invalid_json,
test_expand_query_falls_back_on_llm_exception,
test_search_unions_and_dedupes_workspace,
test_search_caps_candidates_at_30,
test_search_uses_data_source_query_when_databases_specified,
test_search_filters_only_pages,
test_search_passes_property_filter_to_data_sources_query,
]
for t in tests:
print(f"\n{t.__name__}")