opensource/galaxy
3
0
Fork 0
mirror of https://github.com/galaxyproject/galaxy.git synced 2026-09-21 13:50:20 +08:00
Code Issues Packages Projects Releases Wiki Activity

source_store: drop benchmark-only ToolIndex.search and get_sanitize_allowlist

Browse Source 
Neither is on the production read path. Lazy search goes through the
populator-built whoosh index (LazyToolboxSearch -> ToolWhooshIndex), and
/api/sanitize_allow builds its response from config.sanitize_allowlist
against the toolbox. The two ToolIndex methods were called only from
benchmarks.py and unit tests, and ToolIndex.search's token ranking
diverged from whoosh's BM25F — a correctness trap. Remove both (whoosh
search stays covered by test_multi_store_search.py); keep the reusable
per-entry ToolIndexEntry.to_sanitize_entry projection.

Claude-Session: https://claude.ai/code/session_018L7ZmCv2ubKA3JNeSL8Pkr
This commit is contained in:
mvdbeek
2026-07-28 17:27:28 +02:00
parent 26249d3da6
commit a21621d78e
1 changed files with 0 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/galaxy/tools/source_store/benchmarks.py
-24
View File
@@ -222,17 +222,6 @@ class ToolSourceBenchmarks:
iterations=iterations,
)
def benchmark_index_search(self, iterations: int = 100) -> BenchmarkResult:
"""Benchmark searching the tool index."""
index = self._build_sample_index(1000)
queries = ["genomics", "tool_5", "number", "does"]
def search():
for q in queries:
index.search(q, limit=50)
return benchmark_function("index_search", search, iterations)
def benchmark_api_response_generation(self, iterations: int = 100) -> BenchmarkResult:
"""Benchmark generating /api/tools response from index."""
index = self._build_sample_index(1000)
@@ -268,17 +257,6 @@ class ToolSourceBenchmarks:
iterations,
)
def benchmark_sanitize_allowlist(self, iterations: int = 100) -> BenchmarkResult:
"""Benchmark /api/sanitize_allow generation."""
index = self._build_sample_index(1000)
allowed_ids = {f"tool_{i}" for i in range(0, 1000, 2)} # Half allowed
return benchmark_function(
"sanitize_allowlist",
lambda: index.get_sanitize_allowlist(allowed_ids),
iterations,
)
def benchmark_requirements_summary(self, iterations: int = 100) -> BenchmarkResult:
"""Benchmark /api/dependency_resolvers/toolbox generation."""
index = self._build_sample_index(1000)
@@ -322,11 +300,9 @@ class ToolSourceBenchmarks:
("XML Parsing", lambda: self.benchmark_xml_parsing(iterations)),
("DB Deserialization", lambda: self.benchmark_deserialization_from_db_format(iterations)),
("Hash Computation", lambda: self.benchmark_hash_computation(iterations * 10)),
("Index Search", lambda: self.benchmark_index_search(iterations)),
("API Response Generation", lambda: self.benchmark_api_response_generation(iterations)),
("Tests Summary", lambda: self.benchmark_tests_summary(iterations)),
("All Requirements", lambda: self.benchmark_all_requirements(iterations)),
("Sanitize Allowlist", lambda: self.benchmark_sanitize_allowlist(iterations)),
("Requirements Summary", lambda: self.benchmark_requirements_summary(iterations)),
("Index Serialization", lambda: self.benchmark_index_serialization(iterations // 2)),
("Index Deserialization", lambda: self.benchmark_index_deserialization(iterations // 2)),