Add label collection to help with multiple label comparisons (#116)

* add label collection Signed-off-by: Alex Goodman <[email protected]> * update lock file Signed-off-by: Alex Goodman <[email protected]> --------- Signed-off-by: Alex Goodman <[email protected]>
anchore · Aug 17, 2023 · dc54ea7 · dc54ea7
1 parent a7ea334
commit dc54ea7
Show file tree

Hide file tree

Showing 5 changed files with 15 additions and 73 deletions.
diff --git a/poetry.lock b/poetry.lock
diff --git a/pyproject.toml b/pyproject.toml
@@ -13,7 +13,7 @@ exclude = [
 ]
 
 [tool.poetry.dependencies]
-python = "^3.7"
+python = "^3.9"
 click = "^8"
 dataclasses-json = "^0.5.8"
 tabulate = "^0.9.0"

diff --git a/src/yardstick/__init__.py b/src/yardstick/__init__.py
@@ -75,7 +75,7 @@ def compare_results_against_labels(  # pylint: disable=too-many-arguments
         for result in results:
             result.matches = matches_filter(result.matches)
 
-    if not label_entries:
+    if label_entries is None:
         label_entries = store.labels.load_all(
             year_max_limit=year_max_limit,
             year_from_cve_only=year_from_cve_only,
@@ -102,7 +102,7 @@ def compare_results_against_labels_by_ecosystem(
     results = store.result_set.load_scan_results(result_set, year_max_limit=year_max_limit, skip_sbom_results=True)
     results_by_image = arrange.scan_results_by_image(results)
 
-    if not label_entries:
+    if label_entries is None:
         label_entries = store.labels.load_all(year_max_limit=year_max_limit, year_from_cve_only=year_from_cve_only)
 
     stats = comparison.of_results_against_label_by_ecosystem(

diff --git a/src/yardstick/artifact.py b/src/yardstick/artifact.py
@@ -1,4 +1,5 @@
 import collections
+import functools
 import getpass
 import hashlib
 import json
@@ -499,6 +500,15 @@ def effective_year(self, by_cve=False) -> Optional[int]:
         return year
 
 
+class LabelEntryCollection:
+    def __init__(self, entries: List[LabelEntry]):
+        self.entries = entries
+
+    @functools.cache
+    def for_image(self, image: str) -> List[LabelEntry]:
+        return [e for e in self.entries if e.matches_image(image)]
+
+
 @dataclass()
 class ScanRequest:
     image: str

diff --git a/src/yardstick/store/labels.py b/src/yardstick/store/labels.py
@@ -115,7 +115,6 @@ def load_label_file(
     # why note take a file path? in this way we control that all input/output data was derived from the same store,
     # and not another store.
     path = store_path(filename=filename, store_root=store_root)
-    logging.debug(f"loading labels location={path}")
 
     try:
         with open(path, "r", encoding="utf-8") as data_file: