Merge pull request #373 from crocs-muni/switch-black-to-ruff

switch black -> ruff format

10 files changed, 22 insertions, 20 deletions

diff --git a/src/sec_certs/dataset/dataset.py b/src/sec_certs/dataset/dataset.py
index 9e49a347..454e86bd 100644
--- a/src/sec_certs/dataset/dataset.py
+++ b/src/sec_certs/dataset/dataset.py
@@ -502,7 +502,7 @@ class Dataset(Generic[CertSubType, AuxiliaryDatasetsSubType], ComplexSerializabl
             candidates = [cpe_dset[x].title for x in cert.heuristics.cpe_matches]
             candidates += ["No good match"] * (config.cpe_n_max_matches - len(candidates))
             options = ["option_" + str(x) for x in range(1, config.cpe_n_max_matches)]
-            dct.update({o: c for o, c in zip(options, candidates)})
+            dct.update(dict(zip(options, candidates)))
             lst.append(dct)
 
         with Path(output_path).open("w") as handle:
@@ -634,6 +634,6 @@ class Dataset(Generic[CertSubType, AuxiliaryDatasetsSubType], ComplexSerializabl
         Enriches the dataset with `certs`
         :param List[Certificate] certs: new certs to include into the dataset.
         """
-        if any([x not in self for x in certs]):
+        if any(x not in self for x in certs):
             logger.warning("Updating dataset with certificates outside of the dataset!")
         self.certs.update({x.dgst: x for x in certs})
diff --git a/src/sec_certs/dataset/fips_algorithm.py b/src/sec_certs/dataset/fips_algorithm.py
index fbc8351a..f3f27c0b 100644
--- a/src/sec_certs/dataset/fips_algorithm.py
+++ b/src/sec_certs/dataset/fips_algorithm.py
@@ -82,7 +82,7 @@ class FIPSAlgorithmDataset(JSONPathDataset, ComplexSerializableType):
         if failed_tuples:
             failed_urls, failed_paths = zip(*failed_tuples)
             responses = helpers.download_parallel(failed_urls, failed_paths)
-            if any([x != constants.RESPONSE_OK for x in responses]):
+            if any(x != constants.RESPONSE_OK for x in responses):
                 raise ValueError("Failed to download the algorithms HTML data, the dataset won't be constructed.")
 
         return paths
diff --git a/src/sec_certs/model/matching.py b/src/sec_certs/model/matching.py
index 7e48f878..9c0591f9 100644
--- a/src/sec_certs/model/matching.py
+++ b/src/sec_certs/model/matching.py
@@ -28,7 +28,7 @@ class AbstractMatcher(Generic[CertSubType], ABC):
         )
 
     @staticmethod
-    def _match_certs(matchers: Sequence["AbstractMatcher"], certs: list[CertSubType], threshold: float):
+    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()
diff --git a/src/sec_certs/sample/cc.py b/src/sec_certs/sample/cc.py
index c89f67c6..f2087eeb 100644
--- a/src/sec_certs/sample/cc.py
+++ b/src/sec_certs/sample/cc.py
@@ -247,7 +247,7 @@ class CCCertificate(
         st_filename: str | None = field(default=None)
 
         def __bool__(self) -> bool:
-            return any([x is not None for x in vars(self)])
+            return any(x is not None for x in vars(self))
 
         @property
         def bsi_data(self) -> dict[str, Any] | None:
@@ -612,13 +612,12 @@ class CCCertificate(
             )
 
         for att, val in vars(self).items():
-            if not val:
-                setattr(self, att, getattr(other, att))
-            elif other_source == "html" and att == "protection_profiles":
-                setattr(self, att, getattr(other, att))
-            elif other_source == "html" and att == "maintenance_updates":
-                setattr(self, att, getattr(other, att))
-            elif att == "state":
+            if (
+                (not val)
+                or (other_source == "html" and att == "protection_profiles")
+                or (other_source == "html" and att == "maintenance_updates")
+                or (att == "state")
+            ):
                 setattr(self, att, getattr(other, att))
             else:
                 if getattr(self, att) != getattr(other, att):
diff --git a/src/sec_certs/sample/fips.py b/src/sec_certs/sample/fips.py
index 26510191..e0bcb74a 100644
--- a/src/sec_certs/sample/fips.py
+++ b/src/sec_certs/sample/fips.py
@@ -64,7 +64,7 @@ class FIPSHTMLParser:
         )
         entries = [(FIPSHTMLParser.normalize_string(key.text), entry) for key, entry in entries]
         entries = [parse_single_detail_entry(*x) for x in entries if x[0] in DETAILS_KEY_NORMALIZATION_DICT]
-        entries = {x: y for x, y in entries}
+        entries = dict(entries)
 
         if "caveat" in entries:
             entries["mentioned_certs"] = FIPSHTMLParser.get_mentioned_certs_from_caveat(entries["caveat"])
diff --git a/src/sec_certs/sample/sar.py b/src/sec_certs/sample/sar.py
index 8f48f417..e3d7bd2b 100644
--- a/src/sec_certs/sample/sar.py
+++ b/src/sec_certs/sample/sar.py
@@ -50,7 +50,7 @@ class SAR(ComplexSerializableType):
     @staticmethod
     def matches_re(string: str) -> bool:
         return any(
-            [re.match(sar_class + "(?:_[A-Z]{3,4}){1,2}(?:\\.[0-9]){0,2}", string) for sar_class in SAR_CLASS_MAPPING]
+            re.match(sar_class + "(?:_[A-Z]{3,4}){1,2}(?:\\.[0-9]){0,2}", string) for sar_class in SAR_CLASS_MAPPING
         )
 
     def __lt__(self, other: Any) -> bool:
diff --git a/src/sec_certs/utils/extract.py b/src/sec_certs/utils/extract.py
index 933db4b8..e6312b8d 100644
--- a/src/sec_certs/utils/extract.py
+++ b/src/sec_certs/utils/extract.py
@@ -353,7 +353,7 @@ def search_only_headers_bsi(filepath: Path):  # noqa: C901
 
             for m in re.finditer(rule_and_sep, whole_text):
                 # check if previous rules had at least one match
-                if constants.TAG_CERT_ID not in items_found.keys():
+                if constants.TAG_CERT_ID not in items_found:
                     logger.error(f"ERROR: front page not found for file: {filepath}")
 
                 match_groups = m.groups()
diff --git a/src/sec_certs/utils/helpers.py b/src/sec_certs/utils/helpers.py
index 596ecf62..c103a2d3 100644
--- a/src/sec_certs/utils/helpers.py
+++ b/src/sec_certs/utils/helpers.py
@@ -28,7 +28,11 @@ def download_file(
         time.sleep(delay)
         # See https://github.com/psf/requests/issues/3953 for header justification
         r = requests.get(
-            url, allow_redirects=True, timeout=constants.REQUEST_TIMEOUT, stream=True, headers={"Accept-Encoding": None}  # type: ignore
+            url,
+            allow_redirects=True,
+            timeout=constants.REQUEST_TIMEOUT,
+            stream=True,
+            headers={"Accept-Encoding": None},  # type: ignore
         )
         ctx: Any
         if show_progress_bar:
diff --git a/src/sec_certs/utils/pandas.py b/src/sec_certs/utils/pandas.py
index 5b0a668d..661b669c 100644
--- a/src/sec_certs/utils/pandas.py
+++ b/src/sec_certs/utils/pandas.py
@@ -141,7 +141,7 @@ 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 {}
-    if sar_family not in family_sars_dict.keys():
+    if sar_family not in family_sars_dict:
         return None
     return family_sars_dict[sar_family].level
 
@@ -211,7 +211,7 @@ def compute_cve_correlations(
     tuples = list(
         zip(n_cves_corrs, n_cves_pvalues, worst_cve_corrs, worst_cve_pvalues, avg_cve_corrs, avg_cve_pvalues, supports)
     )
-    dct = {family: correlations for family, correlations in zip(["eal"] + families, tuples)}
+    dct = dict(zip(["eal"] + families, tuples))
     df_corr = pd.DataFrame.from_dict(
         dct,
         orient="index",
diff --git a/src/sec_certs/utils/pdf.py b/src/sec_certs/utils/pdf.py
index 7736b5d0..f2c2c58e 100644
--- a/src/sec_certs/utils/pdf.py
+++ b/src/sec_certs/utils/pdf.py
@@ -1,6 +1,5 @@
 from __future__ import annotations
 
-import glob
 import logging
 import subprocess
 from datetime import datetime, timedelta, timezone
@@ -54,7 +53,7 @@ def ocr_pdf_file(pdf_path: Path) -> str:
         if ppm.returncode != 0:
             raise ValueError(f"pdftoppm failed: {ppm.returncode}")
 
-        for ppm_path in map(Path, glob.glob(str(tmppath / "image*.ppm"))):
+        for ppm_path in tmppath.rglob("image*.ppm"):
             base = ppm_path.with_suffix("")
             content = pytesseract.image_to_string(Image.open(ppm_path), lang="eng+deu+fra")