Files
our-claude-skills/custom-skills/31-notion-organizer/code/scripts/test_notion_search.py
Andrew Yim 8aa0fa26e9 feat(notion-search): add candidate enrichment (title, properties, excerpt)
For each candidate page, extract the title, flatten common property
types (status/select/multi_select/date/checkbox/number/url/etc.) to
display values, and fetch the first text-bearing block as a 200-char
excerpt. Empty excerpt is acceptable when the page has no leading text.

4 tests: title+properties, paragraph excerpt, empty fallback,
truncation. 21 passing total.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-28 07:56:35 +09:00

397 lines
15 KiB
Python

#!/usr/bin/env python3
"""Tests for notion_search.py — run with `python3 test_notion_search.py`."""
import sys
from pathlib import Path
sys.path.insert(0, str(Path(__file__).parent))
def _assert(cond, msg):
if not cond:
print(f" ✗ FAIL: {msg}")
raise SystemExit(1)
print(f"{msg}")
def test_call_claude_dispatches_to_sdk_when_available():
"""When SDK is available and ANTHROPIC_API_KEY is set, use SDK path."""
import os
from unittest.mock import patch
import _search_llm
with patch.object(_search_llm, "_have_anthropic_sdk", return_value=True), \
patch.dict(os.environ, {"ANTHROPIC_API_KEY": "sk-fake"}), \
patch.object(_search_llm, "_call_via_sdk", return_value="sdk-response") as sdk_mock, \
patch.object(_search_llm, "_call_via_cli", return_value="cli-response") as cli_mock:
result = _search_llm.call_claude("hello")
_assert(result == "sdk-response", "SDK path returned its response")
_assert(sdk_mock.called, "SDK path was invoked")
_assert(not cli_mock.called, "CLI path was NOT invoked")
def test_call_claude_falls_back_to_cli_when_no_sdk():
"""When SDK is missing but CLI is available, use CLI path."""
from unittest.mock import patch
import _search_llm
with patch.object(_search_llm, "_have_anthropic_sdk", return_value=False), \
patch.object(_search_llm, "_have_claude_cli", return_value=True), \
patch.object(_search_llm, "_call_via_cli", return_value="cli-response") as cli_mock:
result = _search_llm.call_claude("hello")
_assert(result == "cli-response", "CLI path returned its response")
_assert(cli_mock.called, "CLI path was invoked")
def test_call_claude_raises_when_neither_available():
"""Both clients missing → RuntimeError with setup hint."""
from unittest.mock import patch
import _search_llm
with patch.object(_search_llm, "_have_anthropic_sdk", return_value=False), \
patch.object(_search_llm, "_have_claude_cli", return_value=False):
try:
_search_llm.call_claude("hello")
_assert(False, "should have raised RuntimeError")
except RuntimeError as exc:
_assert("ANTHROPIC_API_KEY" in str(exc) or "claude" in str(exc).lower(),
"error mentions setup options")
def test_cache_miss_returns_none():
import tempfile
from pathlib import Path
import _search_cache
with tempfile.TemporaryDirectory() as tmpdir:
result = _search_cache.cache_get("query", ["id1", "id2"], cache_dir=Path(tmpdir))
_assert(result is None, "cache miss returns None")
def test_cache_hit_returns_cached_results():
import tempfile
from pathlib import Path
import _search_cache
with tempfile.TemporaryDirectory() as tmpdir:
cache_dir = Path(tmpdir)
results = [{"id": "abc", "title": "Test"}]
_search_cache.cache_put("query", ["id1", "id2"], results, cache_dir=cache_dir)
hit = _search_cache.cache_get("query", ["id1", "id2"], cache_dir=cache_dir)
_assert(hit == results, "cache hit returns the stored results")
def test_cache_miss_on_different_candidates():
import tempfile
from pathlib import Path
import _search_cache
with tempfile.TemporaryDirectory() as tmpdir:
cache_dir = Path(tmpdir)
_search_cache.cache_put("query", ["id1", "id2"], [{"x": 1}], cache_dir=cache_dir)
miss = _search_cache.cache_get("query", ["id1", "id3"], cache_dir=cache_dir)
_assert(miss is None, "different candidate set hashes to different key")
def test_cache_miss_after_ttl_expires():
import tempfile
from pathlib import Path
import _search_cache
with tempfile.TemporaryDirectory() as tmpdir:
cache_dir = Path(tmpdir)
_search_cache.cache_put("query", ["id1"], [{"x": 1}], cache_dir=cache_dir)
# TTL=0 means immediately expired
miss = _search_cache.cache_get("query", ["id1"], cache_dir=cache_dir, ttl_seconds=0)
_assert(miss is None, "expired cache returns None")
def test_cache_handles_corrupted_file():
import tempfile
import hashlib
from pathlib import Path
import _search_cache
with tempfile.TemporaryDirectory() as tmpdir:
cache_dir = Path(tmpdir)
cache_dir.mkdir(exist_ok=True)
# Write garbage to the expected key path
key = hashlib.sha256("query|id1".encode()).hexdigest()
(cache_dir / f"{key}.json").write_text("not json {{{")
result = _search_cache.cache_get("query", ["id1"], cache_dir=cache_dir)
_assert(result is None, "corrupted cache file returns None")
def test_expand_query_returns_variants_with_original_first():
"""LLM mock returns variants; expansion includes original verbatim as first item."""
import notion_search
fake_llm = lambda prompt, **kw: '["AI agents", "multi-agent systems", "autonomous LLMs"]'
variants = notion_search.expand_query("AI agents", llm_caller=fake_llm)
_assert(variants[0] == "AI agents", "original query is first variant")
_assert(len(variants) >= 2, "at least 2 variants returned")
_assert("multi-agent systems" in variants, "LLM-suggested variant included")
def test_expand_query_dedupes_and_caps():
"""Duplicates removed; total ≤ max_variants."""
import notion_search
fake_llm = lambda prompt, **kw: '["AI", "AI", "agents", "agents", "systems", "tools", "models"]'
variants = notion_search.expand_query("AI", llm_caller=fake_llm, max_variants=3)
_assert(len(variants) <= 3, "capped at max_variants=3")
_assert(len(variants) == len(set(variants)), "no duplicates in result")
def test_expand_query_falls_back_on_invalid_json():
"""LLM returns prose instead of JSON → fall back to [original]."""
import notion_search
fake_llm = lambda prompt, **kw: "I'm sorry, I can't help with that."
variants = notion_search.expand_query("AI agents", llm_caller=fake_llm)
_assert(variants == ["AI agents"], "non-JSON response falls back to original only")
def test_expand_query_falls_back_on_llm_exception():
"""LLM raises → fall back to [original]."""
import notion_search
def boom(prompt, **kw):
raise RuntimeError("API error")
variants = notion_search.expand_query("AI agents", llm_caller=boom)
_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 test_enrich_extracts_title_and_properties():
"""Candidate with properties → title and properties extracted."""
from unittest.mock import MagicMock
import notion_search
notion = MagicMock()
notion.blocks.children.list.return_value = {"results": []} # no body
candidate = {
"id": "page-a",
"url": "https://notion.so/a",
"properties": {
"Name": {
"type": "title",
"title": [{"plain_text": "Test Page"}],
},
"Status": {
"type": "status",
"status": {"name": "Done"},
},
"Topic": {
"type": "multi_select",
"multi_select": [{"name": "AI"}, {"name": "MCP"}],
},
},
}
enriched = notion_search.enrich_candidates(notion, [candidate])
_assert(len(enriched) == 1, "one enriched candidate")
e = enriched[0]
_assert(e["title"] == "Test Page", "title extracted from title property")
_assert(e["properties"]["Status"] == "Done", "status flattened to name")
_assert(e["properties"]["Topic"] == ["AI", "MCP"], "multi_select flattened to names list")
def test_enrich_extracts_first_paragraph_excerpt():
"""First paragraph block → excerpt (200-char max)."""
from unittest.mock import MagicMock
import notion_search
notion = MagicMock()
notion.blocks.children.list.return_value = {
"results": [
{
"type": "paragraph",
"paragraph": {
"rich_text": [{"plain_text": "This is the first paragraph of the page."}]
},
}
]
}
candidate = {
"id": "page-a", "url": "https://notion.so/a",
"properties": {"Name": {"type": "title", "title": [{"plain_text": "Test"}]}},
}
enriched = notion_search.enrich_candidates(notion, [candidate])
_assert(enriched[0]["excerpt"] == "This is the first paragraph of the page.",
"excerpt is first paragraph plain text")
def test_enrich_falls_back_to_empty_excerpt():
"""Page leads with image/table only → excerpt is empty string, no crash."""
from unittest.mock import MagicMock
import notion_search
notion = MagicMock()
notion.blocks.children.list.return_value = {
"results": [
{"type": "image", "image": {}},
{"type": "divider", "divider": {}},
]
}
candidate = {
"id": "page-a", "url": "https://notion.so/a",
"properties": {"Name": {"type": "title", "title": [{"plain_text": "Test"}]}},
}
enriched = notion_search.enrich_candidates(notion, [candidate])
_assert(enriched[0]["excerpt"] == "", "empty excerpt when no text-bearing block")
def test_enrich_truncates_long_excerpt():
"""Excerpt is capped at 200 chars."""
from unittest.mock import MagicMock
import notion_search
notion = MagicMock()
long_text = "x" * 500
notion.blocks.children.list.return_value = {
"results": [
{"type": "paragraph", "paragraph": {"rich_text": [{"plain_text": long_text}]}}
]
}
candidate = {
"id": "page-a", "url": "https://notion.so/a",
"properties": {"Name": {"type": "title", "title": [{"plain_text": "Test"}]}},
}
enriched = notion_search.enrich_candidates(notion, [candidate])
_assert(len(enriched[0]["excerpt"]) == 200, "excerpt truncated to 200 chars")
def run_all():
tests = [
test_call_claude_dispatches_to_sdk_when_available,
test_call_claude_falls_back_to_cli_when_no_sdk,
test_call_claude_raises_when_neither_available,
test_cache_miss_returns_none,
test_cache_hit_returns_cached_results,
test_cache_miss_on_different_candidates,
test_cache_miss_after_ttl_expires,
test_cache_handles_corrupted_file,
test_expand_query_returns_variants_with_original_first,
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,
test_enrich_extracts_title_and_properties,
test_enrich_extracts_first_paragraph_excerpt,
test_enrich_falls_back_to_empty_excerpt,
test_enrich_truncates_long_excerpt,
]
for t in tests:
print(f"\n{t.__name__}")
t()
print("\n" + "=" * 50)
print(f"✅ All {len(tests)} tests passed")
print("=" * 50)
if __name__ == "__main__":
run_all()