ruff enforce comprehensions

20 files changed, 37 insertions, 37 deletions

diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index e4936ff6..391cd6c6 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -6,7 +6,7 @@ repos:
         args: ["--check", "--target-version", "py38"]
   - repo: https://github.com/charliermarsh/ruff-pre-commit
     # Ruff version.
-    rev: "v0.0.236"
+    rev: "v0.0.239"
     hooks:
       - id: ruff
   - repo: https://github.com/pre-commit/mirrors-mypy
diff --git a/pyproject.toml b/pyproject.toml
index 2e4e0c10..d77c8b75 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -101,10 +101,12 @@
     "UP",  # pyupgrade
     "PL",  # pylint
     "PTH", # enforce pathlib usage
+    "C4",  # comprehensions
   ]
   ignore = [
     "E501",    # line-length, should be handled by black
     "PLR2004", # magic numbers, what would a project be without them...
+    "PLR0913", # too many func arguments
   ]
   src = ["src", "tests"]
   line-length = 120
diff --git a/src/sec_certs/dataset/cc.py b/src/sec_certs/dataset/cc.py
index bb8ccc4d..7e2450ba 100644
--- a/src/sec_certs/dataset/cc.py
+++ b/src/sec_certs/dataset/cc.py
@@ -52,7 +52,7 @@ class CCDataset(Dataset[CCCertificate, CCAuxillaryDatasets], ComplexSerializable
 
     def __init__(
         self,
-        certs: dict[str, CCCertificate] = dict(),
+        certs: dict[str, CCCertificate] = {},
         root_dir: str | Path = constants.DUMMY_NONEXISTING_PATH,
         name: str | None = None,
         description: str = "",
@@ -819,7 +819,7 @@ class CCDatasetMaintenanceUpdates(CCDataset, ComplexSerializableType):
     # Quite difficult to achieve correct behaviour with MyPy here, opting for ignore
     def __init__(
         self,
-        certs: dict[str, CCMaintenanceUpdate] = dict(),  # type: ignore
+        certs: dict[str, CCMaintenanceUpdate] = {},  # type: ignore
         root_dir: Path = constants.DUMMY_NONEXISTING_PATH,
         name: str = "dataset name",
         description: str = "dataset_description",
diff --git a/src/sec_certs/dataset/cpe.py b/src/sec_certs/dataset/cpe.py
index 927ce674..e9525847 100644
--- a/src/sec_certs/dataset/cpe.py
+++ b/src/sec_certs/dataset/cpe.py
@@ -40,9 +40,9 @@ class CPEDataset(JSONPathDataset, ComplexSerializableType):
         self.cpes = cpes
         self.json_path = Path(json_path)
 
-        self.vendor_to_versions: dict[str, set[str]] = dict()
-        self.vendor_version_to_cpe: dict[tuple[str, str], set[CPE]] = dict()
-        self.title_to_cpes: dict[str, set[CPE]] = dict()
+        self.vendor_to_versions: dict[str, set[str]] = {}
+        self.vendor_version_to_cpe: dict[tuple[str, str], set[CPE]] = {}
+        self.title_to_cpes: dict[str, set[CPE]] = {}
         self.vendors: set[str] = set()
 
         self.build_lookup_dicts()
@@ -77,8 +77,8 @@ class CPEDataset(JSONPathDataset, ComplexSerializableType):
         """
         logger.info("CPE dataset: building lookup dictionaries.")
         self.vendor_to_versions = {x.vendor: set() for x in self}
-        self.vendor_version_to_cpe = dict()
-        self.title_to_cpes = dict()
+        self.vendor_version_to_cpe = {}
+        self.title_to_cpes = {}
         self.vendors = set(self.vendor_to_versions.keys())
         for cpe in self:
             self.vendor_to_versions[cpe.vendor].add(cpe.version)
diff --git a/src/sec_certs/dataset/cve.py b/src/sec_certs/dataset/cve.py
index 4863ffd2..60438e0b 100644
--- a/src/sec_certs/dataset/cve.py
+++ b/src/sec_certs/dataset/cve.py
@@ -33,7 +33,7 @@ class CVEDataset(JSONPathDataset, ComplexSerializableType):
     def __init__(self, cves: dict[str, CVE], json_path: str | Path = constants.DUMMY_NONEXISTING_PATH):
         self.cves = cves
         self.json_path = Path(json_path)
-        self.cpe_to_cve_ids_lookup: dict[str, set[str]] = dict()
+        self.cpe_to_cve_ids_lookup: dict[str, set[str]] = {}
 
     @property
     def serialized_attributes(self) -> list[str]:
@@ -64,7 +64,7 @@ class CVEDataset(JSONPathDataset, ComplexSerializableType):
             - CPE(uri='cpe:2.3:a:bayashi:dopvcomet\\*:0009:b:*:*:*:*:*:*', title=None, version='0009', vendor='bayashi', item_name='dopvcomet\\*', start_version=None, end_version=None)
             - CPE(uri='cpe:2.3:a:bayashi:dopvstar\\*:0091:*:*:*:*:*:*:*', title=None, version='0091', vendor='bayashi', item_name='dopvstar\\*', start_version=None, end_version=None)
         """
-        self.cpe_to_cve_ids_lookup = dict()
+        self.cpe_to_cve_ids_lookup = {}
         self.cves = {x.cve_id.upper(): x for x in self}
 
         logger.info("Getting CPE matching dictionary from NIST.gov")
@@ -124,7 +124,7 @@ class CVEDataset(JSONPathDataset, ComplexSerializableType):
             cls.download_cves(tmp_dir, start_year, end_year)
             json_files = glob.glob(tmp_dir + "/*.json")
 
-            all_cves = dict()
+            all_cves = {}
             logger.info("Downloaded required resources. Building CVEDataset from jsons.")
             results = process_parallel(
                 cls.from_nist_json,
@@ -210,7 +210,7 @@ class CVEDataset(JSONPathDataset, ComplexSerializableType):
             with input_filepath.open("r") as handle:
                 match_data = json.load(handle)
 
-        mapping_dict = dict()
+        mapping_dict = {}
         for match in tqdm(match_data["matches"], desc="parsing cpe matching (by NIST) dictionary"):
             key = parse_key_cpe(match)
             value = parse_values_cpe(match)
diff --git a/src/sec_certs/dataset/dataset.py b/src/sec_certs/dataset/dataset.py
index 3d106486..726cd681 100644
--- a/src/sec_certs/dataset/dataset.py
+++ b/src/sec_certs/dataset/dataset.py
@@ -58,7 +58,7 @@ class Dataset(Generic[CertSubType, AuxillaryDatasetsSubType], ComplexSerializabl
 
     def __init__(
         self,
-        certs: dict[str, CertSubType] = dict(),
+        certs: dict[str, CertSubType] = {},
         root_dir: str | Path = constants.DUMMY_NONEXISTING_PATH,
         name: str | None = None,
         description: str = "",
diff --git a/src/sec_certs/dataset/fips.py b/src/sec_certs/dataset/fips.py
index 14bcfcf1..c051cce8 100644
--- a/src/sec_certs/dataset/fips.py
+++ b/src/sec_certs/dataset/fips.py
@@ -41,7 +41,7 @@ class FIPSDataset(Dataset[FIPSCertificate, FIPSAuxillaryDatasets], ComplexSerial
 
     def __init__(
         self,
-        certs: dict[str, FIPSCertificate] = dict(),
+        certs: dict[str, FIPSCertificate] = {},
         root_dir: str | Path = constants.DUMMY_NONEXISTING_PATH,
         name: str | None = None,
         description: str = "",
diff --git a/src/sec_certs/dataset/fips_algorithm.py b/src/sec_certs/dataset/fips_algorithm.py
index c48cff07..f4826dd2 100644
--- a/src/sec_certs/dataset/fips_algorithm.py
+++ b/src/sec_certs/dataset/fips_algorithm.py
@@ -20,12 +20,10 @@ logger = logging.getLogger(__name__)
 
 
 class FIPSAlgorithmDataset(JSONPathDataset, ComplexSerializableType):
-    def __init__(
-        self, algs: dict[str, FIPSAlgorithm] = dict(), json_path: str | Path = constants.DUMMY_NONEXISTING_PATH
-    ):
+    def __init__(self, algs: dict[str, FIPSAlgorithm] = {}, json_path: str | Path = constants.DUMMY_NONEXISTING_PATH):
         self.algs = algs
         self.json_path = Path(json_path)
-        self.alg_number_to_algs: dict[str, set[FIPSAlgorithm]] = dict()
+        self.alg_number_to_algs: dict[str, set[FIPSAlgorithm]] = {}
 
         self._build_lookup_dicts()
 
diff --git a/src/sec_certs/model/cpe_matching.py b/src/sec_certs/model/cpe_matching.py
index 0febea5d..35bb5d7e 100644
--- a/src/sec_certs/model/cpe_matching.py
+++ b/src/sec_certs/model/cpe_matching.py
@@ -66,7 +66,7 @@ class CPEClassifier(BaseEstimator):
         sufficiently_long_cpes = self._filter_short_cpes(X)
         self.vendor_to_versions_ = {x.vendor: set() for x in sufficiently_long_cpes}
         self.vendors_ = set(self.vendor_to_versions_.keys())
-        self.vendor_version_to_cpe_ = dict()
+        self.vendor_version_to_cpe_ = {}
 
         for cpe in tqdm(sufficiently_long_cpes, desc="Fitting the CPE classifier"):
             self.vendor_to_versions_[cpe.vendor].add(cpe.version)
@@ -323,7 +323,7 @@ class CPEClassifier(BaseEstimator):
                 itertools.chain.from_iterable([x.strip() for x in manufacturer.split(s)] for s in splits)
             )
             result_aux = [self._get_candidate_list_of_vendors(x) for x in vendor_tokens]
-            result_used = set(set(itertools.chain.from_iterable(x for x in result_aux if x)))
+            result_used = set(itertools.chain.from_iterable(x for x in result_aux if x))
             return result_used if result_used else set()
 
         if manufacturer in self.vendors_:
diff --git a/src/sec_certs/model/sar_transformer.py b/src/sec_certs/model/sar_transformer.py
index 45c4f7d5..20ce9dec 100644
--- a/src/sec_certs/model/sar_transformer.py
+++ b/src/sec_certs/model/sar_transformer.py
@@ -128,7 +128,7 @@ class SARTransformer(BaseEstimator, TransformerMixin):
         :param dgst: DIgest of the processed certificate.
         :return: _description_
         """
-        sars: dict[str, tuple[SAR, int]] = dict()
+        sars: dict[str, tuple[SAR, int]] = {}
         for sar_class, class_matches in dct.items():
             for sar_string, n_occurences in class_matches.items():
                 try:
diff --git a/src/sec_certs/model/transitive_vulnerability_finder.py b/src/sec_certs/model/transitive_vulnerability_finder.py
index 1d4c8243..6ae6fa0b 100644
--- a/src/sec_certs/model/transitive_vulnerability_finder.py
+++ b/src/sec_certs/model/transitive_vulnerability_finder.py
@@ -98,7 +98,7 @@ class TransitiveVulnerabilityFinder:
                 thrown_away_cert_counter += 1
                 continue
 
-            self.vulnerabilities[cert.dgst] = dict()
+            self.vulnerabilities[cert.dgst] = {}
             self.vulnerabilities[cert.dgst][ReferenceType.DIRECT.value] = self._get_cert_transitive_cves(
                 cert, ReferenceType.DIRECT, ref_func
             )
diff --git a/src/sec_certs/sample/cc.py b/src/sec_certs/sample/cc.py
index b7e97408..1441a7b4 100644
--- a/src/sec_certs/sample/cc.py
+++ b/src/sec_certs/sample/cc.py
@@ -506,7 +506,7 @@ class CCCertificate(
         Computes actual SARs. First, SARs implied by EAL are computed. Then, these are augmented with heuristically extracted SARs
         :return Optional[Set[SAR]]: Set of actual SARs of a certificate, None if empty
         """
-        sars = dict()
+        sars = {}
         if self.eal:
             sars = {x[0]: SAR(x[0], x[1]) for x in SARS_IMPLIED_FROM_EAL[self.eal[:4]]}
 
diff --git a/src/sec_certs/sample/fips.py b/src/sec_certs/sample/fips.py
index 9988d629..435c9315 100644
--- a/src/sec_certs/sample/fips.py
+++ b/src/sec_certs/sample/fips.py
@@ -126,7 +126,7 @@ class FIPSHTMLParser:
     @staticmethod
     def parse_algorithms(algorithms_div: Tag) -> dict[str, set[str]]:
         rows = algorithms_div.find("tbody").find_all("tr")
-        dct: dict[str, set[str]] = dict()
+        dct: dict[str, set[str]] = {}
         for row in rows:
             cells = row.find_all("td")
             dct[cells[0].text] = {m.group() for m in re.finditer(FIPS_ALGS_IN_TABLE, cells[1].text)}
@@ -384,7 +384,7 @@ class FIPSCertificate(
         def certlike_algorithm_numbers(self) -> set[str]:
             """Returns numbers of certificates from keywords["fips_certlike"]["Certlike"]"""
             if self.keywords and "fips_certlike" in self.keywords:
-                fips_certlike = self.keywords["fips_certlike"].get("Certlike", dict())
+                fips_certlike = self.keywords["fips_certlike"].get("Certlike", {})
                 matches = {re.search(r"#\s{0,1}\d{1,4}", x) for x in fips_certlike.keys()}
                 return {"".join([x for x in match.group() if x.isdigit()]) for match in matches if match}
             else:
@@ -563,7 +563,7 @@ class FIPSCertificate(
         if metadata:
             cert.pdf_data.policy_metadata = metadata
         else:
-            cert.pdf_data.policy_metadata = dict()
+            cert.pdf_data.policy_metadata = {}
             cert.state.policy_extract_ok = False
         return cert
 
@@ -611,7 +611,7 @@ class FIPSCertificate(
         self.heuristics.module_prunned_references = self._prune_reference_ids_variable(html_module_ids)
 
         if self.pdf_data.keywords:
-            pdf_policy_ids = set(self.pdf_data.keywords["fips_cert_id"].get("Cert", dict()).keys())
+            pdf_policy_ids = set(self.pdf_data.keywords["fips_cert_id"].get("Cert", {}).keys())
             pdf_policy_ids = {"".join([y for y in x if y.isdigit()]) for x in pdf_policy_ids}
         else:
             pdf_policy_ids = set()
diff --git a/src/sec_certs/sample/fips_iut.py b/src/sec_certs/sample/fips_iut.py
index 968ee3fc..f6010346 100644
--- a/src/sec_certs/sample/fips_iut.py
+++ b/src/sec_certs/sample/fips_iut.py
@@ -101,7 +101,7 @@ class IUTSnapshot(ComplexSerializableType):
                 str(line[2].string),
                 datetime.strptime(str(line[3].string), "%m/%d/%Y").date(),
             )
-            for line in map(lambda tr: tr.find_all("td"), lines)
+            for line in (tr.find_all("td") for tr in lines)
         }
 
         # Parse footer
diff --git a/src/sec_certs/sample/fips_mip.py b/src/sec_certs/sample/fips_mip.py
index 6918d2aa..7debec65 100644
--- a/src/sec_certs/sample/fips_mip.py
+++ b/src/sec_certs/sample/fips_mip.py
@@ -114,7 +114,7 @@ class MIPSnapshot(ComplexSerializableType):
             MIPEntry(
                 str(line[0].string), str(line[1].string), str(line[2].string), MIPStatus(str(line[3].string)), None
             )
-            for line in map(lambda tr: tr.find_all("td"), lines)
+            for line in (tr.find_all("td") for tr in lines)
         }
 
     @classmethod
@@ -128,14 +128,14 @@ class MIPSnapshot(ComplexSerializableType):
                 MIPStatus(str(line[3].string)),
                 None,
             )
-            for line in map(lambda tr: tr.find_all("td"), lines)
+            for line in (tr.find_all("td") for tr in lines)
         }
 
     @classmethod
     def _extract_entries_4(cls, lines):
         """Works now."""
         entries = set()
-        for line in map(lambda tr: tr.find_all("td"), lines):
+        for line in (tr.find_all("td") for tr in lines):
             module_name = str(line[0].string)
             vendor_name = str(" ".join(line[1].find_all(text=True, recursive=False)).strip())
             standard = str(line[2].string)
diff --git a/src/sec_certs/sample/sar.py b/src/sec_certs/sample/sar.py
index 31359299..8f48f417 100644
--- a/src/sec_certs/sample/sar.py
+++ b/src/sec_certs/sample/sar.py
@@ -18,7 +18,7 @@ SAR_CLASS_MAPPING = {
     "ACO": "Comoposition",
 }
 
-SAR_CLASSES = {x for x in SAR_CLASS_MAPPING}
+SAR_CLASSES = set(SAR_CLASS_MAPPING)
 SAR_DICT_KEY = "cc_sar"
 
 
diff --git a/src/sec_certs/serialization/json.py b/src/sec_certs/serialization/json.py
index 69bbc2ff..c8c0f83d 100644
--- a/src/sec_certs/serialization/json.py
+++ b/src/sec_certs/serialization/json.py
@@ -112,9 +112,9 @@ class CustomJSONEncoder(json.JSONEncoder):
         if isinstance(obj, dict):
             return obj
         if isinstance(obj, set):
-            return {"_type": "Set", "elements": sorted(list(obj))}
+            return {"_type": "Set", "elements": sorted(obj)}
         if isinstance(obj, frozenset):
-            return sorted(list(obj))
+            return sorted(obj)
         if isinstance(obj, date):
             return str(obj)
         if isinstance(obj, Path):
diff --git a/src/sec_certs/utils/pandas.py b/src/sec_certs/utils/pandas.py
index 97068e77..b8a6bef7 100644
--- a/src/sec_certs/utils/pandas.py
+++ b/src/sec_certs/utils/pandas.py
@@ -140,7 +140,7 @@ def get_sar_level_from_set(sars: set[SAR], sar_family: str) -> int | None:
     """
     Given a set of SARs and a family name, will return level of the seeked SAR from the set.
     """
-    family_sars_dict = {x.family: x for x in sars} if (sars and not pd.isnull(sars)) else dict()
+    family_sars_dict = {x.family: x for x in sars} if (sars and not pd.isnull(sars)) else {}
     if sar_family not in family_sars_dict.keys():
         return None
     return family_sars_dict[sar_family].level
diff --git a/src/sec_certs/utils/pdf.py b/src/sec_certs/utils/pdf.py
index ea2487b0..1c5ff684 100644
--- a/src/sec_certs/utils/pdf.py
+++ b/src/sec_certs/utils/pdf.py
@@ -186,7 +186,7 @@ def extract_pdf_metadata(filepath: Path) -> tuple[str, dict[str, Any] | None]:
         else:
             return val
 
-    metadata: dict[str, Any] = dict()
+    metadata: dict[str, Any] = {}
 
     try:
         metadata["pdf_file_size_bytes"] = filepath.stat().st_size
diff --git a/tests/test_cpe.py b/tests/test_cpe.py
index 26d0cbf3..ab2f4cba 100644
--- a/tests/test_cpe.py
+++ b/tests/test_cpe.py
@@ -135,6 +135,6 @@ def test_to_pandas(cpe_dset: CPEDataset):
 
 
 def test_serialization_missing_path():
-    dummy_dset = CPEDataset(False, dict())
+    dummy_dset = CPEDataset(False, {})
     with pytest.raises(SerializationError):
         dummy_dset.to_json()