Make CCSchemeDataset an actual dataset.

3 files changed, 12 insertions, 9 deletions

diff --git a/src/sec_certs/model/cc_matching.py b/src/sec_certs/model/cc_matching.py
index fdb16d70..3cc38a40 100644
--- a/src/sec_certs/model/cc_matching.py
+++ b/src/sec_certs/model/cc_matching.py
@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from typing import Any, Iterable, Mapping
+from typing import Any, Iterable, Mapping, Sequence
 
 from sec_certs.configuration import config
 from sec_certs.model.matching import AbstractMatcher
@@ -79,7 +79,7 @@ class CCSchemeMatcher(AbstractMatcher[CCCertificate]):
     @classmethod
     def match_all(
         cls, entries: list[dict[str, Any]], scheme: str, certificates: Iterable[CCCertificate]
-    ) -> dict[str, Mapping]:
+    ) -> dict[str, dict[str, Any]]:
         """
         Match all entries of a given CC scheme to certificates from the dataset.
 
@@ -89,5 +89,5 @@ class CCSchemeMatcher(AbstractMatcher[CCCertificate]):
         :return: A mapping of certificate digests to entries, without duplicates, not all entries may be present.
         """
         certs: list[CCCertificate] = list(filter(lambda cert: cert.scheme == scheme, certificates))
-        matchers = [CCSchemeMatcher(entry, scheme) for entry in entries]
-        return cls._match_certs(matchers, certs, config.cc_matching_threshold)
+        matchers: Sequence[CCSchemeMatcher] = [CCSchemeMatcher(entry, scheme) for entry in entries]
+        return cls._match_certs(matchers, certs, config.cc_matching_threshold)  # type: ignore
diff --git a/src/sec_certs/model/fips_matching.py b/src/sec_certs/model/fips_matching.py
index 8cf3cb9c..53d75c61 100644
--- a/src/sec_certs/model/fips_matching.py
+++ b/src/sec_certs/model/fips_matching.py
@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 import typing
-from typing import Iterable, Mapping
+from typing import Iterable, Mapping, Sequence
 
 from sec_certs.configuration import config
 from sec_certs.model.matching import AbstractMatcher
@@ -60,5 +60,6 @@ class FIPSProcessMatcher(AbstractMatcher[FIPSCertificate]):
         :return: A mapping of certificate digests to entries, without duplicates, not all entries may be present.
         """
         certs: list[FIPSCertificate] = list(certificates)
-        matchers = [FIPSProcessMatcher(entry) for entry in snapshot]
-        return cls._match_certs(matchers, certs, config.fips_matching_threshold)
+        matchers: Sequence[FIPSProcessMatcher] = [FIPSProcessMatcher(entry) for entry in snapshot]
+        # mypy is ridiculous
+        return cls._match_certs(matchers, certs, config.fips_matching_threshold)  # type: ignore
diff --git a/src/sec_certs/model/matching.py b/src/sec_certs/model/matching.py
index 6d49f34f..fc71b2ad 100644
--- a/src/sec_certs/model/matching.py
+++ b/src/sec_certs/model/matching.py
@@ -1,7 +1,7 @@
 import typing
 from abc import ABC, abstractmethod
 from heapq import heappop, heappush
-from typing import Generic
+from typing import Any, Generic, Sequence
 
 from rapidfuzz import fuzz
 
@@ -11,6 +11,8 @@ CertSubType = typing.TypeVar("CertSubType", bound=Certificate)
 
 
 class AbstractMatcher(Generic[CertSubType], ABC):
+    entry: Any
+
     @abstractmethod
     def match(self, cert: CertSubType) -> float:
         raise NotImplementedError
@@ -25,7 +27,7 @@ class AbstractMatcher(Generic[CertSubType], ABC):
         )
 
     @staticmethod
-    def _match_certs(matchers, certs, threshold):
+    def _match_certs(matchers: Sequence["AbstractMatcher"], certs: list[CertSubType], threshold: float):
         scores: list[tuple[float, int, int]] = []
         matched_is: set[int] = set()
         matched_js: set[int] = set()