Skip to content

fix: poll for search-index visibility in three flaky query tests #7

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
goharanwar wants to merge 1 commit into from
Closed

fix: poll for search-index visibility in three flaky query tests #7

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
62 changes: 35 additions & 27 deletions tests/services/corpus/test_filter_attributes_types.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,15 +60,31 @@ def test_text_integer_boolean_filters(self, client, unique_id):
description="both documents indexed",
)

text_query = client.post(
"/v2/query",
data={
"query": "research and data",
"search": {
"corpora": [{"corpus_key": corpus_key, "metadata_filter": "part.category = 'tech'"}],
"limit": 10,
},
},
def _filter_query_returns_results(metadata_filter):
def _check():
resp = client.post(
"/v2/query",
data={
"query": "research and data",
"search": {
"corpora": [{"corpus_key": corpus_key, "metadata_filter": metadata_filter}],
"limit": 10,
},
},
)
if not resp.success:
return None
if not resp.data.get("search_results"):
return None
return resp

return _check

text_query = wait_for(
_filter_query_returns_results("part.category = 'tech'"),
timeout=30,
interval=2,
description="text filter query to return results",
)
assert text_query.success, f"Text filter query failed: {text_query.status_code}"
text_results = text_query.data.get("search_results", [])
Expand All @@ -77,15 +93,11 @@ def test_text_integer_boolean_filters(self, client, unique_id):
"quantum" in r.get("text", "").lower() for r in text_results
), f"Text filter for 'tech' should only return tech doc: {[r.get('text', '')[:50] for r in text_results]}"

int_query = client.post(
"/v2/query",
data={
"query": "research and data",
"search": {
"corpora": [{"corpus_key": corpus_key, "metadata_filter": "part.priority >= 3"}],
"limit": 10,
},
},
int_query = wait_for(
_filter_query_returns_results("part.priority >= 3"),
timeout=30,
interval=2,
description="integer filter query to return results",
)
assert int_query.success, f"Integer filter query failed: {int_query.status_code}"
int_results = int_query.data.get("search_results", [])
Expand All @@ -94,15 +106,11 @@ def test_text_integer_boolean_filters(self, client, unique_id):
"climate" in r.get("text", "").lower() for r in int_results
), f"Integer filter >= 3 should only return science doc: {[r.get('text', '')[:50] for r in int_results]}"

bool_query = client.post(
"/v2/query",
data={
"query": "research and data",
"search": {
"corpora": [{"corpus_key": corpus_key, "metadata_filter": "part.is_public = true"}],
"limit": 10,
},
},
bool_query = wait_for(
_filter_query_returns_results("part.is_public = true"),
timeout=30,
interval=2,
description="boolean filter query to return results",
)
assert bool_query.success, f"Boolean filter query failed: {bool_query.status_code}"
bool_results = bool_query.data.get("search_results", [])
Expand Down
16 changes: 15 additions & 1 deletion tests/services/indexing/test_document_lifecycle.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,21 @@ def test_index_query_delete_query_cycle(self, client, test_corpus, unique_id):
description="document to be indexed",
)

query_resp = client.query(test_corpus, "Krakatoa volcano eruption", limit=10)
def _krakatoa_in_results():
qr = client.query(test_corpus, "Krakatoa volcano eruption", limit=10)
if not qr.success:
return None
hits = qr.data.get("search_results", [])
if any("krakatoa" in r.get("text", "").lower() for r in hits):
return qr
return None

query_resp = wait_for(
_krakatoa_in_results,
timeout=30,
interval=2,
description="Krakatoa to appear in search",
)
assert query_resp.success, f"Query failed: {query_resp.status_code}"
results = query_resp.data.get("search_results", [])
found = any("krakatoa" in r.get("text", "").lower() for r in results)
Expand Down
29 changes: 21 additions & 8 deletions tests/services/query/test_query_filters.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,15 +53,28 @@ def test_query_with_valid_metadata_filter(self, client, unique_id):
description="document to be indexed",
)

query_resp = client.post(
"/v2/query",
data={
"query": "artificial intelligence",
"search": {
"corpora": [{"corpus_key": corpus_key, "metadata_filter": "part.topic = 'ai'"}],
"limit": 10,
def _query_returns_results():
resp = client.post(
"/v2/query",
data={
"query": "artificial intelligence",
"search": {
"corpora": [{"corpus_key": corpus_key, "metadata_filter": "part.topic = 'ai'"}],
"limit": 10,
},
},
},
)
if not resp.success:
return None
if not resp.data.get("search_results"):
return None
return resp

query_resp = wait_for(
_query_returns_results,
timeout=30,
interval=2,
description="filter query to return results",
)
assert query_resp.success, f"Query failed: {query_resp.status_code} - {query_resp.data}"
results = query_resp.data.get("search_results", [])
Expand Down
Loading