👽️ Apply default sha256

Author: simonwoerpel

poetry.lock

@@ -77,6 +77,7 @@ sphinx-rtd-theme = "^3.0.2"
 recommonmark = "^0.7.1"
 mkdocs-typer2 = "^0.1.6"
 pytest-asyncio = "^1.3.0"
+griffe = "<2"
 
 [[tool.poetry.packages]]
 include = "memorious"

pyproject.toml

@@ -228,8 +228,8 @@ def test_fetch_archives_content(self, httpbin_url):
         """Test that fetch() stores content in archive."""
         response = fetch(f"{httpbin_url}/json", dataset="fetch-archive")
         assert response.content_hash is not None
-        # Content hash should be a SHA1 hex digest (40 chars)
-        assert len(response.content_hash) == 40
+        # Content hash should be a SHA256 hex digest (64 chars)
+        assert len(response.content_hash) == 64
 
 
 class TestFetchCaching:

tests/test_fetch.py

@@ -134,7 +134,7 @@ def test_fetch_response(self, http, httpbin_url):
         content_hash = context_http_response.fetch()
         # fetch() now returns content_hash, not file_path
         assert isinstance(content_hash, str)
-        assert len(content_hash) == 40  # SHA1 hex digest length
+        assert len(content_hash) == 64  # SHA256 hex digest length
 
     def test_contenttype(self, http, httpbin_url):
         request = httpx.Request("GET", f"{httpbin_url}/get")
@@ -376,7 +376,7 @@ def test_fetch_with_partial_content_resumes(self, http, httpbin_url):
             # the 200 response will reset partial state and download full content)
             content_hash = response.fetch()
             assert content_hash is not None
-            assert len(content_hash) == 40  # SHA1 hex digest length
+            assert len(content_hash) == 64  # SHA256 hex digest length
         finally:
             # Cleanup
             if partial_path.exists():

tests/test_http.py

@@ -420,8 +420,6 @@ def test_directory_same_content(context, mocker, httpbin_url):
 
 def test_lakehouse_default(context, mocker, httpbin_url):
     """Test lakehouse store with default archive."""
-    from ftm_lakehouse import get_lakehouse
-
     url = f"{httpbin_url}/user-agent"
     result = context.http.get(url, headers={"User-Agent": "Memorious Test"})
     data = result.serialize()
@@ -440,6 +438,7 @@ def test_lakehouse_default(context, mocker, httpbin_url):
 
     # Verify entity was created with origin=crawl
     entities_repo = get_entities(context.crawler.name)
+    entities_repo.flush()
     entities = [
         e
         for e in entities_repo.query(origin="crawl")

tests/test_operations.py

@@ -113,7 +113,7 @@ def test_pipeline_auth(httpbin_auth_crawler, auth_output_dir):
     meta_files = [
         f
         for f in auth_output_dir.glob("**/*.json")
-        if re.match(r"^[a-f0-9]{40}$", f.stem)
+        if re.match(r"^[a-f0-9]{64}$", f.stem)
     ]
     assert len(meta_files) > 0, "Expected metadata JSON file (named by content_hash)"