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

switch black -> ruff format

4 files changed, 9 insertions, 6 deletions

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")