fix validation workflow and linting

Signed-off-by: Alex Goodman <[email protected]>

.github/workflows/validations.yaml

@@ -40,8 +40,8 @@ jobs:
         with:
           python: false
 
-      - name: Run unit tests
-        run: make unit-go
+      - name: Run go unit tests
+        run: make unit
 
   # Note: changing this job name requires making the same update in the .github/workflows/release.yaml pipeline
   Unit-Test-Python:
@@ -56,8 +56,8 @@ jobs:
         with:
           go: false
 
-      - name: Run unit tests
-        run: make unit-python
+      - name: Run python unit tests
+        run: cd manager && make unit
 
   # Note: changing this job name requires making the same update in the .github/workflows/release.yaml pipeline
   Build-Snapshot-Artifacts:

manager/src/grype_db_manager/cli/db.py

@@ -6,7 +6,6 @@
 import click
 import yardstick
 from tabulate import tabulate
-from yardstick import store
 from yardstick.cli import config as ycfg
 from yardstick.tool.grype import Grype
 from yardstick.tool.syft import Syft

manager/src/grype_db_manager/db/validation.py

@@ -3,7 +3,7 @@
 import collections
 import logging
 from dataclasses import InitVar, dataclass, field
-from typing import TYPE_CHECKING
+from typing import TYPE_CHECKING, Any
 
 import yardstick
 from yardstick import artifact, capture, comparison, store
@@ -31,15 +31,17 @@ class GateConfig:
     introduced_fns_threshold: int = 0
 
 
-_default_gate_config = GateConfig()
+# note: a class property on a dataclass will not work since it is not mutable (cannot convey
+# changes to all future instances)
+_default_gate_config = GateConfig()  # noqa: PLW0603
 
 
 def _get_config() -> GateConfig:
     return _default_gate_config
 
 
 def set_default_gate_config(config: GateConfig) -> None:
-    global _default_gate_config
+    global _default_gate_config  # noqa: PLW0603
     _default_gate_config = config
 
 
@@ -338,37 +340,20 @@ def log_validation_results(
     verbosity: int = 0,
 ) -> None:
     if verbosity > 2:
-        image = sorted(stats_by_image_tool_pair.true_positives.keys())[0]
-        tools = sorted(stats_by_image_tool_pair.true_positives[image].keys())
-        table = format.stats_table_by_tool(
-            tools,
-            image,
-            stats_by_image_tool_pair,
-        )
-
-        logging.info(table)
+        _log_stats(stats_by_image_tool_pair)
 
     if verbosity > 1:
-        # show false negative label entries
-        fns_by_id = {}
-        for result in results:
-            comp = comparisons_by_result_id[result.ID]
-            fns = comp.false_negative_label_entries
-            fns_by_id[result.ID] = fns
-
-        unique_fns_by_id = collections.defaultdict(list)
-        for result_id, fns in fns_by_id.items():
-            for fn in fns:
-                if _is_unique_fn(fns_by_id, result_id, fn):
-                    unique_fns_by_id[result_id].append(fn)
-
-        for result in results:
-            fns = unique_fns_by_id[result.ID]
-            ret = f"false negatives found uniquely in result={result.ID}: {len(fns)}\n"
-            for label in fns:
-                ret += f"{format.space}    {label.summarize()}\n"
-            logging.info(ret.rstrip())
+        _log_fns(results, comparisons_by_result_id)
+
+    _log_differences(relative_comparison, results, comparisons_by_result_id, verbosity)
+
 
+def _log_differences(
+    relative_comparison: comparison.ByPreservedMatch,
+    results: list[artifact.ScanResult],
+    comparisons_by_result_id: dict[str, list[comparison.AgainstLabels]],
+    verbosity: int,
+) -> None:
     latest_release_tool, current_tool = guess_tool_orientation([r.config.tool for r in results])
 
     table, diffs = format.match_differences_table(
@@ -386,7 +371,41 @@ def log_validation_results(
             logging.info(f"match differences found between tooling: {diffs}")
 
 
-def _is_unique_fn(fns_by_id, result_id, fn):
+def _log_stats(stats_by_image_tool_pair: comparison.ImageToolLabelStats) -> None:
+    image = sorted(stats_by_image_tool_pair.true_positives.keys())[0]
+    tools = sorted(stats_by_image_tool_pair.true_positives[image].keys())
+    table = format.stats_table_by_tool(
+        tools,
+        image,
+        stats_by_image_tool_pair,
+    )
+
+    logging.info(table)
+
+
+def _log_fns(results: list[artifact.ScanResult], comparisons_by_result_id: dict[str, list[comparison.AgainstLabels]]) -> None:
+    # show false negative label entries
+    fns_by_id = {}
+    for result in results:
+        comp = comparisons_by_result_id[result.ID]
+        fns = comp.false_negative_label_entries
+        fns_by_id[result.ID] = fns
+
+    unique_fns_by_id = collections.defaultdict(list)
+    for result_id, fns in fns_by_id.items():
+        for fn in fns:
+            if _is_unique_fn(fns_by_id, result_id, fn):
+                unique_fns_by_id[result_id].append(fn)
+
+    for result in results:
+        fns = unique_fns_by_id[result.ID]
+        ret = f"false negatives found uniquely in result={result.ID}: {len(fns)}\n"
+        for label in fns:
+            ret += f"{format.space}    {label.summarize()}\n"
+        logging.info(ret.rstrip())
+
+
+def _is_unique_fn(fns_by_id: dict[str, set[str]], result_id: str, fn: Any) -> bool:
     for other_result_id, other_fns in fns_by_id.items():
         if other_result_id == result_id:
             continue

manager/src/grype_db_manager/distribution.py

@@ -34,7 +34,8 @@ def listing_entries_dbs_in_s3(  # noqa: PLR0913
         suffixes = DB_SUFFIXES
 
     if not download_url_prefix:
-        raise ValueError("download_url_prefix must be specified")
+        msg = "download_url_prefix must be specified"
+        raise ValueError(msg)
 
     # generate metadata from each downloaded archive and add to the listing file
     for basename in basenames: