Merge pull request #308 from crocs-muni/replace-linters-with-ruff

Replace linters with ruff

46 files changed, 213 insertions, 325 deletions

diff --git a/.flake8 b/.flake8
deleted file mode 100644
index 2d24fa82..00000000
--- a/.flake8
+++ /dev/null
@@ -1,20 +0,0 @@
-[flake8]
-max-line-length = 120
-exclude =
-    .git,
-    __pycache__,
-    build,
-    dist,
-    venv,
-    certsvenv,
-    .eggs,
-    scratches,
-max-complexity = 10
-
-ignore =
-    # line length, should be handleded by black
-    E501,
-    # line break before binary operator, depracated
-    W503,
-    # whitespace before :, not PEP8 compliant
-    E203,
diff --git a/.github/workflows/lint.yml b/.github/workflows/lint.yml
index 95de7f7b..90e4a459 100644
--- a/.github/workflows/lint.yml
+++ b/.github/workflows/lint.yml
@@ -1,4 +1,4 @@
-name: Lint (MyPy, Black, isort, Flake8)
+name: Lint (MyPy, Black, Ruff)
 on:
   push:
   workflow_dispatch:
@@ -24,43 +24,19 @@ jobs:
     steps:
       - uses: actions/checkout@v3
       - uses: psf/black@stable
-  isort:
+        with:
+          version: "23.1.0"
+          options: "--check --target-version py38"
+  ruff:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
       - uses: actions/setup-python@v4
         with:
           python-version: 3.8
-      - uses: isort/isort-action@master
-        with:
-          requirementsFiles: "requirements/requirements.txt requirements/dev_requirements.txt"
-  pyupgrade:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-      - name: Setup python
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.8"
-      - name: Install external dependencies
-        run: sudo apt-get install build-essential libpoppler-cpp-dev pkg-config python3-dev -y
-      - name: Install python dependencies
+      - name: Install dependencies
         run: |
-          pip install -r requirements/requirements.txt
-          pip install -r requirements/dev_requirements.txt
-      - name: Run pyupgrade
-        run: pre-commit run pyupgrade --all-files
-  flake8-lint:
-    runs-on: ubuntu-latest
-    name: Flake8
-    steps:
-      - name: Check out source repository
-        uses: actions/checkout@v3
-      - name: Set up Python environment
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.8"
-      - name: flake8 Lint
-        uses: py-actions/flake8@v2
-        with:
-          plugins: "flake8-future-annotations"
+          python -m pip install --upgrade pip
+          pip install ruff==v0.0.239
+      - name: Run Ruff
+        run: ruff --format=github .
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index 7e4da57e..8501c280 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -1,21 +1,16 @@
 repos:
-  - repo: https://github.com/asottile/pyupgrade
-    rev: v3.2.3
-    hooks:
-      - id: pyupgrade
-        args: ["--py38-plus"]
   - repo: https://github.com/psf/black
-    rev: 22.6.0
+    rev: 23.1.0
     hooks:
       - id: black
         args: ["--check", "--target-version", "py38"]
-  - repo: https://github.com/pycqa/isort
-    rev: 5.10.1
+  - repo: https://github.com/charliermarsh/ruff-pre-commit
+    # Ruff version.
+    rev: "v0.0.239"
     hooks:
-      - id: isort
-        args: ["--check-only"]
+      - id: ruff
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: "v0.982"
+    rev: "v0.991"
     hooks:
       - id: mypy
         additional_dependencies:
@@ -23,9 +18,3 @@ repos:
           - "types-PyYAML"
           - "types-python-dateutil"
           - "types-requests"
-  - repo: https://github.com/pycqa/flake8
-    rev: "4.0.1"
-    hooks:
-      - id: flake8
-        additional_dependencies:
-          - "flake8-future-annotations"
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index dd00667f..3e4c59e0 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -43,8 +43,7 @@ All commits shall pass the lint pipeline of the following tools:
 
 - Mypy (see [pyproject.toml](https://github.com/crocs-muni/sec-certs/blob/main/pyproject.toml) for settings)
 - Black (see [pyproject.toml](https://github.com/crocs-muni/sec-certs/blob/main/pyproject.toml) for settings)
-- isort (see [pyproject.toml](https://github.com/crocs-muni/sec-certs/blob/main/pyproject.toml) for settings)
-- Flake8 (see [.flake8](https://github.com/crocs-muni/sec-certs/blob/main/.flake8) for settings)
+- Ruff (see [pyproject.toml](https://github.com/crocs-muni/sec-certs/blob/main/pyproject.toml) for settings)
 - PyUpgrade
 
 These tools can be installed via [dev_requirements.txt](https://github.com/crocs-muni/sec-certs/blob/main/dev_requirements.txt) You can use [pre-commit](https://pre-commit.com/) tool register git hook that will evalute these checks prior to any commit and abort the commit for you. Note that the pre-commit is not meant to automatically fix the issues, just warn you.
@@ -60,9 +59,7 @@ pre-commit run --all-files
 To ivoke the tools manually, you can, in the repository root, use:
 - Mypy: `mypy .`
 - Black: `black --check .` (without the flag to reformat)
-- isort: `isort --check-only .` (without the flag to actually fix the issue)
-- Flake8: `flake8 .`
-- PyUpgrade: `pyupgrade --py38-plus 'find ./sec_certs/ -name "*.py" -type f'`
+- Ruff: `ruff ." (or with `--fix` flag to apply fixes)
 
 ## Documentation
 
diff --git a/pyproject.toml b/pyproject.toml
index 925265c8..beb1ed33 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -62,7 +62,9 @@
 
   [project.optional-dependencies]
     dev = [
-      "mypy",
+      "mypy==0.991",
+      "black==23.1.0",
+      "ruff==0.0.239",
       "types-PyYAML",
       "types-python-dateutil",
       "types-requests",
@@ -70,9 +72,6 @@
       "pytest-cov",
       "pytest-monitor",
       "pytest-profiling",
-      "black",
-      "isort",
-      "flake8",
       "pre-commit",
       "pip-tools",
       "sphinx",
@@ -80,8 +79,6 @@
       "sphinx-book-theme",
       "sphinx-design",
       "sphinx-copybutton",
-      "pyupgrade",
-      "flake8-future-annotations",
       "ipython!=8.7.0",
     ]
     test = ["pytest", "coverage", "pytest-cov"]
@@ -94,8 +91,33 @@
   [project.scripts]
     sec-certs = "sec_certs.cli:main"
 
-[tool.setuptools.package-data]
-  "*" = ["*.yaml", "*.json"]
+[tool.ruff]
+  select = [
+    "I",   # isort
+    "E",   # pycodestyle
+    "W",   # pycodestyle
+    "F",   # pyflakes
+    "C90", # mccabe
+    "UP",  # pyupgrade
+    "PL",  # pylint
+    "PTH", # enforce pathlib usage
+    "C4",  # comprehensions
+    "SIM",
+  ]
+  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
+  target-version = "py38"
+
+  [tool.ruff.mccabe]
+    max-complexity = 10
+
+  [tool.setuptools.package-data]
+    "*" = ["*.yaml", "*.json"]
 
 
 [tool.setuptools_scm]
@@ -120,15 +142,6 @@
 )/
 '''
 
-[tool.isort]
-  multi_line_output = 3
-  include_trailing_comma = true
-  force_grid_wrap = 0
-  use_parentheses = true
-  ensure_newline_before_comments = true
-  line_length = 120
-  skip = ["certsvenv", "build"]
-
 [tool.mypy]
   plugins = ["numpy.typing.mypy_plugin"]
   ignore_missing_imports = true
diff --git a/requirements/dev_requirements.txt b/requirements/dev_requirements.txt
index 311aef32..51418587 100644
--- a/requirements/dev_requirements.txt
+++ b/requirements/dev_requirements.txt
@@ -21,7 +21,7 @@ beautifulsoup4==4.11.1
     #   sec-certs (./../pyproject.toml)
 billiard==4.0.2
     # via sec-certs (./../pyproject.toml)
-black==22.10.0
+black==23.1.0
     # via sec-certs (./../pyproject.toml)
 blis==0.7.9
     # via thinc
@@ -85,12 +85,6 @@ fastjsonschema==2.16.2
     # via nbformat
 filelock==3.8.2
     # via virtualenv
-flake8==6.0.0
-    # via
-    #   flake8-future-annotations
-    #   sec-certs (./../pyproject.toml)
-flake8-future-annotations==1.0.0
-    # via sec-certs (./../pyproject.toml)
 fonttools==4.38.0
     # via matplotlib
 gprof2dot==2022.7.29
@@ -127,8 +121,6 @@ ipython==8.6.0
     #   sec-certs (./../pyproject.toml)
 ipywidgets==8.0.3
     # via sec-certs (./../pyproject.toml)
-isort==5.10.1
-    # via sec-certs (./../pyproject.toml)
 jedi==0.18.2
     # via ipython
 jinja2==3.1.2
@@ -177,8 +169,6 @@ matplotlib-inline==0.1.6
     # via
     #   ipykernel
     #   ipython
-mccabe==0.7.0
-    # via flake8
 mdit-py-plugins==0.3.3
     # via myst-parser
 mdurl==0.1.2
@@ -234,6 +224,7 @@ numpy==1.23.5
     #   thinc
 packaging==22.0
     # via
+    #   black
     #   build
     #   deprecation
     #   ipykernel
@@ -301,8 +292,6 @@ ptyprocess==0.7.0
     # via pexpect
 pure-eval==0.2.2
     # via stack-data
-pycodestyle==2.10.0
-    # via flake8
 pycryptodome==3.16.0
     # via pypdf
 pydantic==1.10.2
@@ -312,8 +301,6 @@ pydantic==1.10.2
     #   thinc
 pydata-sphinx-theme==0.8.1
     # via sphinx-book-theme
-pyflakes==3.0.1
-    # via flake8
 pygments==2.13.0
     # via
     #   ipython
@@ -348,8 +335,6 @@ pytz==2022.6
     # via
     #   babel
     #   pandas
-pyupgrade==3.3.1
-    # via sec-certs (./../pyproject.toml)
 pyyaml==6.0
     # via
     #   jupyter-cache
@@ -370,6 +355,8 @@ requests==2.28.1
     #   sec-certs (./../pyproject.toml)
     #   spacy
     #   sphinx
+ruff==0.0.239
+    # via sec-certs (./../pyproject.toml)
 scikit-learn==1.2.0
     # via sec-certs (./../pyproject.toml)
 scipy==1.9.3
@@ -444,8 +431,6 @@ thinc==8.1.5
     # via spacy
 threadpoolctl==3.1.0
     # via scikit-learn
-tokenize-rt==5.0.0
-    # via pyupgrade
 toml==0.10.2
     # via pre-commit
 tomli==2.0.1
diff --git a/src/sec_certs/cert_rules.py b/src/sec_certs/cert_rules.py
index 145566f7..c126434b 100644
--- a/src/sec_certs/cert_rules.py
+++ b/src/sec_certs/cert_rules.py
@@ -205,21 +205,19 @@ def _load():
     script_dir = Path(__file__).parent
     filepath = script_dir / "rules.yaml"
     with Path(filepath).open("r") as file:
-        loaded = yaml.load(file, Loader=yaml.FullLoader)
-    return loaded
+        return yaml.load(file, Loader=yaml.FullLoader)
 
 
-def _process(obj):
+def _process(obj: dict | list):
     if isinstance(obj, dict):
         return {k: _process(v) for k, v in obj.items()}
-    elif isinstance(obj, list):
-        return [
-            re.compile(
-                REGEXEC_SEP_START + MATCH_START + rule + MATCH_END + REGEXEC_SEP_END,
-                re.MULTILINE,
-            )
-            for rule in obj
-        ]
+    return [
+        re.compile(
+            REGEXEC_SEP_START + MATCH_START + rule + MATCH_END + REGEXEC_SEP_END,
+            re.MULTILINE,
+        )
+        for rule in obj
+    ]
 
 
 rules = _load()
diff --git a/src/sec_certs/cli.py b/src/sec_certs/cli.py
index 751c4655..96347787 100644
--- a/src/sec_certs/cli.py
+++ b/src/sec_certs/cli.py
@@ -63,7 +63,6 @@ def build_or_load_dataset(
     to_build: bool,
     outputpath: Path | None,
 ) -> CCDataset | FIPSDataset:
-
     constructor: type[CCDataset] | type[FIPSDataset] = CCDataset if framework == "cc" else FIPSDataset
     dset: CCDataset | FIPSDataset
 
diff --git a/src/sec_certs/dataset/cc.py b/src/sec_certs/dataset/cc.py
index 484397e2..bb806d18 100644
--- a/src/sec_certs/dataset/cc.py
+++ b/src/sec_certs/dataset/cc.py
@@ -31,7 +31,7 @@ from sec_certs.sample.cc_certificate_id import CertificateId
 from sec_certs.sample.cc_maintenance_update import CCMaintenanceUpdate
 from sec_certs.sample.protection_profile import ProtectionProfile
 from sec_certs.serialization.json import ComplexSerializableType, CustomJSONDecoder, serialize
-from sec_certs.utils import helpers as helpers
+from sec_certs.utils import helpers
 from sec_certs.utils import parallel_processing as cert_processing
 from sec_certs.utils.sanitization import sanitize_navigable_string as sns
 
@@ -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 = "",
@@ -324,13 +324,9 @@ class CCDataset(Dataset[CCCertificate, CCAuxillaryDatasets], ComplexSerializable
             return CCDataset.BASE_URL + relative_path
 
         def _get_primary_key_str(row: Tag):
-            prim_key = row["category"] + row["cert_name"] + row["report_link"]
-            return prim_key
+            return row["category"] + row["cert_name"] + row["report_link"]
 
-        if "active" in str(file):
-            cert_status = "active"
-        else:
-            cert_status = "archived"
+        cert_status = "active" if "active" in str(file) else "archived"
 
         csv_header = [
             "category",
@@ -394,7 +390,7 @@ class CCDataset(Dataset[CCCertificate, CCAuxillaryDatasets], ComplexSerializable
                 )
             )
 
-        certs = {
+        return {
             x.dgst: CCCertificate(
                 cert_status,
                 x.category,
@@ -416,7 +412,6 @@ class CCDataset(Dataset[CCCertificate, CCAuxillaryDatasets], ComplexSerializable
             )
             for x in df_base.itertuples()
         }
-        return certs
 
     def _get_all_certs_from_html(self, get_active: bool, get_archived: bool) -> dict[str, CCCertificate]:
         """
@@ -483,10 +478,7 @@ class CCDataset(Dataset[CCCertificate, CCAuxillaryDatasets], ComplexSerializable
 
             return table_certs
 
-        if "active" in str(file):
-            cert_status = "active"
-        else:
-            cert_status = "archived"
+        cert_status = "active" if "active" in str(file) else "archived"
 
         cc_cat_abbreviations = ["AC", "BP", "DP", "DB", "DD", "IC", "KM", "MD", "MF", "NS", "OS", "OD", "DG", "TC"]
         cc_table_ids = ["tbl" + x for x in cc_cat_abbreviations]
@@ -719,7 +711,7 @@ class CCDataset(Dataset[CCCertificate, CCAuxillaryDatasets], ComplexSerializable
                     return set()
                 res = set()
                 for scheme, matches in kws["cc_cert_id"].items():
-                    for match in matches.keys():
+                    for match in matches:
                         try:
                             canonical = CertificateId(scheme, match).canonical
                             res.add(canonical)
@@ -819,7 +811,7 @@ 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",
@@ -866,9 +858,7 @@ class CCDatasetMaintenanceUpdates(CCDataset, ComplexSerializableType):
         df.index.name = "dgst"
 
         df.maintenance_date = pd.to_datetime(df.maintenance_date, infer_datetime_format=True)
-        df = df.fillna(value=np.nan)
-
-        return df
+        return df.fillna(value=np.nan)
 
     @classmethod
     def from_web_latest(cls) -> CCDatasetMaintenanceUpdates:
@@ -903,10 +893,7 @@ class CCDatasetMaintenanceUpdates(CCDataset, ComplexSerializableType):
 class CCSchemeDataset:
     @staticmethod
     def _download_page(url, session=None):
-        if session:
-            conn = session
-        else:
-            conn = requests
+        conn = session if session else requests
         resp = conn.get(url, headers={"User-Agent": "seccerts.org"})
         if resp.status_code != requests.codes.ok:
             raise ValueError(f"Unable to download: status={resp.status_code}")
diff --git a/src/sec_certs/dataset/cpe.py b/src/sec_certs/dataset/cpe.py
index 927ce674..1a20c71e 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()
@@ -62,7 +62,7 @@ class CPEDataset(JSONPathDataset, ComplexSerializableType):
     def __contains__(self, item: CPE) -> bool:
         if not isinstance(item, CPE):
             raise ValueError(f"{item} is not of CPE class")
-        return item.uri in self.cpes.keys() and self.cpes[item.uri] == item
+        return item.uri in self.cpes and self.cpes[item.uri] == item
 
     def __eq__(self, other: object) -> bool:
         return isinstance(other, CPEDataset) and self.cpes == other.cpes
@@ -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)
@@ -141,9 +141,7 @@ class CPEDataset(JSONPathDataset, ComplexSerializableType):
 
         :return pd.DataFrame: the resulting DataFrame
         """
-        df = pd.DataFrame([x.pandas_tuple for x in self], columns=CPE.pandas_columns)
-        df = df.set_index("uri")
-        return df
+        return pd.DataFrame([x.pandas_tuple for x in self], columns=CPE.pandas_columns).set_index("uri")
 
     @serialize
     def enhance_with_cpes_from_cve_dataset(self, cve_dset: CVEDataset | str | Path) -> None:
@@ -165,7 +163,7 @@ class CPEDataset(JSONPathDataset, ComplexSerializableType):
                 and (considered_cpe.vendor, considered_cpe.item_name) not in vndr_item_lookup
             ):
                 return True
-            elif (
+            if (
                 considered_cpe.version != constants.CPE_VERSION_NA
                 and (considered_cpe.vendor, considered_cpe.item_name, considered_cpe.version)
                 not in vndr_item_version_lookup
diff --git a/src/sec_certs/dataset/cve.py b/src/sec_certs/dataset/cve.py
index 77ea0152..60438e0b 100644
--- a/src/sec_certs/dataset/cve.py
+++ b/src/sec_certs/dataset/cve.py
@@ -14,12 +14,12 @@ from typing import ClassVar
 import numpy as np
 import pandas as pd
 
-import sec_certs.constants as constants
-import sec_certs.utils.helpers as helpers
+from sec_certs import constants
 from sec_certs.dataset.json_path_dataset import JSONPathDataset
 from sec_certs.sample.cpe import CPE, cached_cpe
 from sec_certs.sample.cve import CVE
 from sec_certs.serialization.json import ComplexSerializableType
+from sec_certs.utils import helpers
 from sec_certs.utils.parallel_processing import process_parallel
 from sec_certs.utils.tqdm import tqdm
 
@@ -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 40ea5611..0066646b 100644
--- a/src/sec_certs/dataset/dataset.py
+++ b/src/sec_certs/dataset/dataset.py
@@ -14,8 +14,7 @@ from typing import Any, Generic, Iterator, TypeVar, cast
 
 import pandas as pd
 
-import sec_certs.constants as constants
-import sec_certs.utils.helpers as helpers
+from sec_certs import constants
 from sec_certs.config.configuration import config
 from sec_certs.dataset.cpe import CPEDataset
 from sec_certs.dataset.cve import CVEDataset
@@ -23,6 +22,7 @@ from sec_certs.model.cpe_matching import CPEClassifier
 from sec_certs.sample.certificate import Certificate
 from sec_certs.sample.cpe import CPE
 from sec_certs.serialization.json import ComplexSerializableType, get_class_fullname, serialize
+from sec_certs.utils import helpers
 from sec_certs.utils.tqdm import tqdm
 
 logger = logging.getLogger(__name__)
@@ -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 = "",
@@ -392,16 +392,16 @@ class Dataset(Generic[CertSubType, AuxillaryDatasetsSubType], ComplexSerializabl
                 and not any(char.isdigit() for char in cpe.title)
             ):
                 return False
-            elif (
+            if (
                 not cpe.title
                 and cpe.item_name
                 and (cpe.version == "-" or cpe.version == "*")
                 and not any(char.isdigit() for char in cpe.item_name)
             ):
                 return False
-            elif re.match(constants.RELEASE_CANDIDATE_REGEX, cpe.update):
+            if re.match(constants.RELEASE_CANDIDATE_REGEX, cpe.update):
                 return False
-            elif cpe in WINDOWS_WEAK_CPES:
+            if cpe in WINDOWS_WEAK_CPES:
                 return False
             return True
 
@@ -456,9 +456,7 @@ class Dataset(Generic[CertSubType, AuxillaryDatasetsSubType], ComplexSerializabl
 
         logger.info("Translating label studio matches into their CPE representations and assigning to certificates.")
         for annotation in tqdm(data, desc="Translating label studio matches"):
-            cpe_candidate_keys = {
-                key for key in annotation.keys() if "option_" in key and annotation[key] != "No good match"
-            }
+            cpe_candidate_keys = {key for key in annotation if "option_" in key and annotation[key] != "No good match"}
 
             if "verified_cpe_match" not in annotation:
                 incorrect_keys: set[str] = set()
diff --git a/src/sec_certs/dataset/fips.py b/src/sec_certs/dataset/fips.py
index f6292dca..6f8eff3e 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 = "",
@@ -187,18 +187,18 @@ class FIPSDataset(Dataset[FIPSCertificate, FIPSAuxillaryDatasets], ComplexSerial
     def _download_html_resources(self) -> None:
         logger.info("Downloading HTML files that list FIPS certificates.")
         html_urls = list(FIPSDataset.LIST_OF_CERTS_HTML.values())
-        html_paths = [self.web_dir / x for x in FIPSDataset.LIST_OF_CERTS_HTML.keys()]
+        html_paths = [self.web_dir / x for x in FIPSDataset.LIST_OF_CERTS_HTML]
         helpers.download_parallel(html_urls, html_paths)
 
     def _get_all_certs_from_html_sources(self) -> list[FIPSCertificate]:
         return list(
             itertools.chain.from_iterable(
-                self._get_certificates_from_html(self.web_dir / x) for x in self.LIST_OF_CERTS_HTML.keys()
+                self._get_certificates_from_html(self.web_dir / x) for x in self.LIST_OF_CERTS_HTML
             )
         )
 
     def _get_certificates_from_html(self, html_file: Path) -> list[FIPSCertificate]:
-        with open(html_file, encoding="utf-8") as handle:
+        with html_file.open("r", encoding="utf-8") as handle:
             html = BeautifulSoup(handle.read(), "html5lib")
 
         table = [x for x in html.find(id="searchResultsTable").tbody.contents if x != "\n"]
diff --git a/src/sec_certs/dataset/fips_algorithm.py b/src/sec_certs/dataset/fips_algorithm.py
index c48cff07..df113381 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()
 
@@ -48,7 +46,7 @@ class FIPSAlgorithmDataset(JSONPathDataset, ComplexSerializableType):
     def __contains__(self, item: FIPSAlgorithm) -> bool:
         if not isinstance(item, FIPSAlgorithm):
             raise ValueError(f"{item} is not of FIPSAlgorithm class")
-        return item.dgst in self.algs.keys() and self.algs[item.dgst] == item
+        return item.dgst in self.algs and self.algs[item.dgst] == item
 
     def __eq__(self, other: object) -> bool:
         return isinstance(other, FIPSAlgorithmDataset) and self.algs == other.algs
@@ -109,9 +107,7 @@ class FIPSAlgorithmDataset(JSONPathDataset, ComplexSerializableType):
         return set(df["alg"])
 
     def to_pandas(self) -> pd.DataFrame:
-        df = pd.DataFrame([x.pandas_tuple for x in self], columns=FIPSAlgorithm.pandas_columns)
-        df = df.set_index("dgst")
-        return df
+        return pd.DataFrame([x.pandas_tuple for x in self], columns=FIPSAlgorithm.pandas_columns).set_index("dgst")
 
     def _build_lookup_dicts(self) -> None:
         for alg in self:
diff --git a/src/sec_certs/dataset/protection_profile.py b/src/sec_certs/dataset/protection_profile.py
index edfb6850..9730a477 100644
--- a/src/sec_certs/dataset/protection_profile.py
+++ b/src/sec_certs/dataset/protection_profile.py
@@ -7,11 +7,11 @@ import tempfile
 from dataclasses import dataclass
 from pathlib import Path
 
-import sec_certs.utils.helpers as helpers
 from sec_certs import constants
 from sec_certs.config.configuration import config
 from sec_certs.sample.protection_profile import ProtectionProfile
 from sec_certs.serialization.json import get_class_fullname
+from sec_certs.utils import helpers
 
 logger = logging.getLogger(__name__)
 
@@ -83,7 +83,6 @@ class ProtectionProfileDataset:
 
     @classmethod
     def from_web(cls, store_dataset_path: Path | None = None):
-
         logger.info(f"Downloading static PP dataset from: {config.pp_latest_snapshot}")
         if not store_dataset_path:
             tmp = tempfile.TemporaryDirectory()
diff --git a/src/sec_certs/model/cpe_matching.py b/src/sec_certs/model/cpe_matching.py
index 0febea5d..2c6b3f07 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)
@@ -148,7 +148,7 @@ class CPEClassifier(BaseEstimator):
         def filter_condition(regex: Pattern, cpe: CPE, min_value: int, soft: bool = True):
             if matches := re.findall(regex, cpe.update):
                 return int(re.findall(r"\d+", matches[0])[0]) >= min_value
-            return True if soft else False
+            return soft
 
         update_regexes = [cert_rules.SERVICE_PACK_RE, cert_rules.RELEASE_RE]
 
@@ -161,7 +161,7 @@ class CPEClassifier(BaseEstimator):
         return cpes
 
     def _filter_candidates_by_platform(self, cpes: list[CPE], cert_title: str) -> list[CPE]:
-        def filter_condition(cpe: CPE, cert_platforms: set[str]):
+        def filter_condition(cpe: CPE, cert_platforms: set[str]) -> bool:
             if not cert_platforms and cpe.target_hw == "*":
                 return True
             if cert_platforms and cpe.target_hw == "*":
@@ -180,8 +180,9 @@ class CPEClassifier(BaseEstimator):
                 )
                 if not target_hw_platforms:
                     return can_return_true
-                else:
-                    return can_return_true and target_hw_platforms[0] in cert_platforms
+
+                return can_return_true and target_hw_platforms[0] in cert_platforms
+            return True
 
         crt_platforms = {
             platform for platform, regex in cert_rules.PLATFORM_REGEXES.items() if re.search(regex, cert_title)
@@ -323,7 +324,7 @@ 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_:
@@ -347,10 +348,7 @@ class CPEClassifier(BaseEstimator):
             def simple_startswith(seeked_version: str, checked_string: str) -> bool:
                 if seeked_version == checked_string:
                     return True
-                else:
-                    return (
-                        checked_string.startswith(seeked_version) and not checked_string[len(seeked_version)].isdigit()
-                    )
+                return checked_string.startswith(seeked_version) and not checked_string[len(seeked_version)].isdigit()
 
             if not cpe_version:
                 return False
diff --git a/src/sec_certs/model/evaluation.py b/src/sec_certs/model/evaluation.py
index 4d0243f6..6f14fda5 100644
--- a/src/sec_certs/model/evaluation.py
+++ b/src/sec_certs/model/evaluation.py
@@ -6,11 +6,11 @@ from pathlib import Path
 
 import numpy as np
 
-import sec_certs.utils.helpers as helpers
 from sec_certs.dataset.cpe import CPEDataset
 from sec_certs.sample.cc import CCCertificate
 from sec_certs.sample.fips import FIPSCertificate
 from sec_certs.serialization.json import CustomJSONEncoder
+from sec_certs.utils import helpers
 
 logger = logging.getLogger(__name__)
 
diff --git a/src/sec_certs/model/reference_finder.py b/src/sec_certs/model/reference_finder.py
index 117a8b9d..94a3b29f 100644
--- a/src/sec_certs/model/reference_finder.py
+++ b/src/sec_certs/model/reference_finder.py
@@ -23,7 +23,7 @@ class ReferenceFinder:
     The fit is called on a dictionary of certificates, builds a hashmap of references, and assigns references for each certificate in the dictionary.
     """
 
-    def __init__(self):
+    def __init__(self: ReferenceFinder) -> None:
         self.references: ReferencesType = {}
         self.id_mapping: IDMapping = {}
         self._fitted: bool = False
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..5eafea93 100644
--- a/src/sec_certs/model/transitive_vulnerability_finder.py
+++ b/src/sec_certs/model/transitive_vulnerability_finder.py
@@ -53,7 +53,6 @@ class TransitiveVulnerabilityFinder:
     def _get_cert_transitive_cves(
         self, cert: CertSubType, reference_type: ReferenceType, ref_func: ReferenceLookupFunc
     ) -> set[str] | None:
-
         references = (
             ref_func(cert).directly_referenced_by
             if reference_type == ReferenceType.DIRECT
@@ -98,7 +97,7 @@ 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 603c29f2..3930104b 100644
--- a/src/sec_certs/sample/cc.py
+++ b/src/sec_certs/sample/cc.py
@@ -17,13 +17,12 @@ from bs4 import Tag
 import sec_certs.utils.extract
 import sec_certs.utils.pdf
 import sec_certs.utils.sanitization
-from sec_certs import constants as constants
+from sec_certs import constants
 from sec_certs.cert_rules import SARS_IMPLIED_FROM_EAL, cc_rules, rules, security_level_csv_scan
 from sec_certs.sample.cc_certificate_id import canonicalize
-from sec_certs.sample.certificate import Certificate
+from sec_certs.sample.certificate import Certificate, References, logger
 from sec_certs.sample.certificate import Heuristics as BaseHeuristics
 from sec_certs.sample.certificate import PdfData as BasePdfData
-from sec_certs.sample.certificate import References, logger
 from sec_certs.sample.protection_profile import ProtectionProfile
 from sec_certs.sample.sar import SAR
 from sec_certs.serialization.json import ComplexSerializableType
@@ -472,9 +471,9 @@ class CCCertificate(
         self.manufacturer_web = sec_certs.utils.sanitization.sanitize_link(manufacturer_web)
         self.protection_profiles = protection_profiles
         self.maintenance_updates = maintenance_updates
-        self.state = self.InternalState() if not state else state
-        self.pdf_data = self.PdfData() if not pdf_data else pdf_data
-        self.heuristics: CCCertificate.Heuristics = self.Heuristics() if not heuristics else heuristics
+        self.state = state if state else self.InternalState()
+        self.pdf_data = pdf_data if pdf_data else self.PdfData()
+        self.heuristics: CCCertificate.Heuristics = heuristics if heuristics else self.Heuristics()
 
     @property
     def dgst(self) -> str:
@@ -507,7 +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]]}
 
@@ -795,11 +794,10 @@ class CCCertificate(
         :param CCCertificate cert: cert to download the pdf security target for
         :return CCCertificate: returns the modified certificate with updated state
         """
-        exit_code: str | int
-        if not cert.st_link:
-            exit_code = "No link"
-        else:
-            exit_code = helpers.download_file(cert.st_link, cert.state.st_pdf_path)
+        exit_code: str | int = (
+            helpers.download_file(cert.st_link, cert.state.st_pdf_path) if cert.st_link else "No link"
+        )
+
         if exit_code != requests.codes.ok:
             error_msg = f"failed to download ST from {cert.st_link}, code: {exit_code}"
             logger.error(f"Cert dgst: {cert.dgst} " + error_msg)
diff --git a/src/sec_certs/sample/cc_maintenance_update.py b/src/sec_certs/sample/cc_maintenance_update.py
index d78359fc..4273b25e 100644
--- a/src/sec_certs/sample/cc_maintenance_update.py
+++ b/src/sec_certs/sample/cc_maintenance_update.py
@@ -4,9 +4,9 @@ import logging
 from datetime import date
 from typing import ClassVar
 
-import sec_certs.utils.helpers as helpers
 from sec_certs.sample.cc import CCCertificate
 from sec_certs.serialization.json import ComplexSerializableType
+from sec_certs.utils import helpers
 
 logger = logging.getLogger(__name__)
 
diff --git a/src/sec_certs/sample/fips.py b/src/sec_certs/sample/fips.py
index aec791d4..4a9d573f 100644
--- a/src/sec_certs/sample/fips.py
+++ b/src/sec_certs/sample/fips.py
@@ -14,21 +14,16 @@ import requests
 from bs4 import BeautifulSoup, Tag
 from tabula import read_pdf
 
-import sec_certs.constants as constants
-import sec_certs.utils.extract
-import sec_certs.utils.helpers as helpers
-import sec_certs.utils.pdf
-import sec_certs.utils.pdf as pdf
-import sec_certs.utils.tables as tables
+from sec_certs import constants
 from sec_certs.cert_rules import FIPS_ALGS_IN_TABLE, fips_rules
 from sec_certs.config.configuration import config
-from sec_certs.sample.certificate import Certificate
+from sec_certs.sample.certificate import Certificate, References, logger
 from sec_certs.sample.certificate import Heuristics as BaseHeuristics
 from sec_certs.sample.certificate import PdfData as BasePdfData
-from sec_certs.sample.certificate import References, logger
 from sec_certs.sample.cpe import CPE
 from sec_certs.serialization.json import ComplexSerializableType
 from sec_certs.serialization.pandas import PandasSerializableType
+from sec_certs.utils import extract, helpers, pdf, tables
 from sec_certs.utils.helpers import fips_dgst
 
 
@@ -69,7 +64,7 @@ class FIPSHTMLParser:
             [x.find("div", class_="col-md-3") for x in entries], [x.find("div", class_="col-md-9") for x in entries]
         )
         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.keys()]
+        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}
 
         if "caveat" in entries:
@@ -131,7 +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)}
@@ -144,7 +139,7 @@ class FIPSHTMLParser:
     @staticmethod
     def parse_tested_configurations(tested_configurations: Tag) -> list[str] | None:
         configurations = [y.text for y in tested_configurations.find_all("li")]
-        return configurations if not configurations == ["N/A"] else None
+        return None if configurations == ["N/A"] else configurations
 
     @staticmethod
     def normalize_embodiment(embodiment_element: Tag) -> str:
@@ -389,8 +384,8 @@ 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())
-                matches = {re.search(r"#\s{0,1}\d{1,4}", x) for x in fips_certlike.keys()}
+                fips_certlike = self.keywords["fips_certlike"].get("Certlike", {})
+                matches = {re.search(r"#\s{0,1}\d{1,4}", x) for x in fips_certlike}
                 return {"".join([x for x in match.group() if x.isdigit()]) for match in matches if match}
             else:
                 return set()
@@ -543,9 +538,7 @@ class FIPSCertificate(
         """
         Converts policy pdf -> txt
         """
-        ocr_done, ok_result = sec_certs.utils.pdf.convert_pdf_file(
-            cert.state.policy_pdf_path, cert.state.policy_txt_path
-        )
+        ocr_done, ok_result = pdf.convert_pdf_file(cert.state.policy_pdf_path, cert.state.policy_txt_path)
 
         # If OCR was done and the result was garbage
         cert.state.policy_convert_garbage = ocr_done
@@ -565,12 +558,12 @@ class FIPSCertificate(
         """
         Extract the PDF metadata from the security policy.
         """
-        _, metadata = sec_certs.utils.pdf.extract_pdf_metadata(cert.state.policy_pdf_path)
+        _, metadata = pdf.extract_pdf_metadata(cert.state.policy_pdf_path)
 
         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
 
@@ -579,7 +572,7 @@ class FIPSCertificate(
         """
         Extract keywords from policy document
         """
-        keywords = sec_certs.utils.extract.extract_keywords(cert.state.policy_txt_path, fips_rules)
+        keywords = extract.extract_keywords(cert.state.policy_txt_path, fips_rules)
         if not keywords:
             cert.state.policy_extract_ok = False
         else:
@@ -618,7 +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()
@@ -649,6 +642,6 @@ class FIPSCertificate(
         prunned = {x for x in attribute_to_prune if x != self.cert_id}
         prunned = {x for x in prunned if int(x) > config.always_false_positive_fips_cert_id_threshold}
         prunned = {x for x in prunned if x not in self.heuristics.algorithm_numbers}
-        prunned = {x for x in prunned if x not in self.pdf_data.certlike_algorithm_numbers}
+        return {x for x in prunned if x not in self.pdf_data.certlike_algorithm_numbers}
 
         return prunned
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..7e0ddff0 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)
@@ -150,14 +150,12 @@ class MIPSnapshot(ComplexSerializableType):
     @classmethod
     def _extract_entries(cls, lines, snapshot_date):
         if snapshot_date <= datetime(2020, 10, 28):
-            entries = cls._extract_entries_1(lines)
-        elif snapshot_date <= datetime(2021, 4, 20):
-            entries = cls._extract_entries_2(lines)
-        elif snapshot_date <= datetime(2022, 3, 23):
-            entries = cls._extract_entries_3(lines)
-        else:
-            entries = cls._extract_entries_4(lines)
-        return entries
+            return cls._extract_entries_1(lines)
+        if snapshot_date <= datetime(2021, 4, 20):
+            return cls._extract_entries_2(lines)
+        if snapshot_date <= datetime(2022, 3, 23):
+            return cls._extract_entries_3(lines)
+        return cls._extract_entries_4(lines)
 
     @classmethod
     def from_page(cls, content: bytes, snapshot_date: datetime) -> MIPSnapshot:
diff --git a/src/sec_certs/sample/protection_profile.py b/src/sec_certs/sample/protection_profile.py
index b7c2ec34..4c26a1c7 100644
--- a/src/sec_certs/sample/protection_profile.py
+++ b/src/sec_certs/sample/protection_profile.py
@@ -5,8 +5,8 @@ import logging
 from dataclasses import dataclass
 from typing import Any
 
-import sec_certs.utils.sanitization as sanitization
 from sec_certs.serialization.json import ComplexSerializableType
+from sec_certs.utils import sanitization
 
 logger = logging.getLogger(__name__)
 
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..7b523b9b 100644
--- a/src/sec_certs/serialization/json.py
+++ b/src/sec_certs/serialization/json.py
@@ -67,8 +67,7 @@ class ComplexSerializableType:
     def from_json(cls: type[T], input_path: str | Path) -> T:
         input_path = Path(input_path)
         with input_path.open("r") as handle:
-            obj = json.load(handle, cls=CustomJSONDecoder)
-        return obj
+            return json.load(handle, cls=CustomJSONDecoder)
 
 
 # Decorator for serialization
@@ -95,10 +94,7 @@ def serialize(func: Callable):
 
 
 def get_class_fullname(obj: Any) -> str:
-    if isinstance(obj, type):
-        klass = obj
-    else:
-        klass = obj.__class__
+    klass = obj if isinstance(obj, type) else obj.__class__
     module = klass.__module__
     if module == "builtins":
         return klass.__qualname__
@@ -112,9 +108,9 @@ 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):
@@ -136,10 +132,10 @@ class CustomJSONDecoder(json.JSONDecoder):
     def object_hook(self, obj):
         if "_type" in obj and obj["_type"] == "Set":
             return set(obj["elements"])
-        if "_type" in obj and obj["_type"] in self.serializable_complex_types.keys():
+        if "_type" in obj and obj["_type"] in self.serializable_complex_types:
             complex_type = obj.pop("_type")
             return self.serializable_complex_types[complex_type].from_dict(obj)
-        elif "_type" in obj:
+        if "_type" in obj:
             raise SerializationError(f"JSONDecoder doesn't know how to handle {obj}")
 
         return obj
diff --git a/src/sec_certs/utils/extract.py b/src/sec_certs/utils/extract.py
index 09460fb7..933db4b8 100644
--- a/src/sec_certs/utils/extract.py
+++ b/src/sec_certs/utils/extract.py
@@ -6,11 +6,11 @@ import re
 from collections import Counter
 from enum import Enum
 from pathlib import Path
-from typing import Any, Iterator
+from typing import Any
 
 import numpy as np
 
-from sec_certs import constants as constants
+from sec_certs import constants
 from sec_certs.cert_rules import REGEXEC_SEP, cc_rules
 from sec_certs.constants import FILE_ERRORS_STRATEGY, LINE_SEPARATOR, MAX_ALLOWED_MATCH_LENGTH
 
@@ -585,11 +585,6 @@ def search_only_headers_canada(filepath: Path):  # noqa: C901
     return constants.RETURNCODE_OK, items_found
 
 
-def search_files(folder: str | Path) -> Iterator[str]:
-    for root, _, files in os.walk(str(folder)):
-        yield from [os.path.join(root, x) for x in files]
-
-
 def flatten_matches(dct: dict) -> dict:
     """
     Function to flatten dictionary of matches.
@@ -663,13 +658,13 @@ def extract_keywords(filepath: Path, search_rules) -> dict[str, dict[str, int]]
         def extract(rules):
             if isinstance(rules, dict):
                 return {k: extract(v) for k, v in rules.items()}
-            elif isinstance(rules, list):
+            if isinstance(rules, list):
                 matches = [extract(rule) for rule in rules]
                 c = Counter()
                 for match_list in matches:
                     c += Counter(match_list)
                 return dict(c)
-            elif isinstance(rules, re.Pattern):
+            if isinstance(rules, re.Pattern):
                 rule = rules
                 matches = []
                 for match in rule.finditer(whole_text):
@@ -719,7 +714,7 @@ def load_text_file(
             logger.warning("UnicodeDecodeError, opening as utf8")
 
     if was_unicode_decode_error:
-        with open(file_name, encoding="utf8", errors=FILE_ERRORS_STRATEGY) as f2:
+        with Path(file_name).open("r", encoding="utf8", errors=FILE_ERRORS_STRATEGY) as f2:
             # coding failure, try line by line
             line = " "
             while line:
@@ -746,23 +741,31 @@ def load_text_file(
     return whole_text, whole_text_with_newlines, was_unicode_decode_error
 
 
-def load_cert_html_file(file_name: str) -> str:
-    with open(file_name, errors=FILE_ERRORS_STRATEGY) as f:
-        try:
-            return f.read()
-        except UnicodeDecodeError:
-            logger.warning("UnicodeDecodeError, opening as utf8")
+def rules_get_subset(desired_path: str) -> dict:
+    """
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
 
-    with open(file_name, encoding="utf8", errors=FILE_ERRORS_STRATEGY) as f2:
-        try:
-            return f2.read()
-        except UnicodeDecodeError:
-            logger.error(f"Failed to read file {file_name}")
-    return ""
 
 
-def rules_get_subset(desired_path: str) -> dict:
-    """
     Recursively applies cc_certs.get(key) on tokens from desired_path,
     returns the keys of the inner-most layer.
     """
diff --git a/src/sec_certs/utils/helpers.py b/src/sec_certs/utils/helpers.py
index e22feacf..596ecf62 100644
--- a/src/sec_certs/utils/helpers.py
+++ b/src/sec_certs/utils/helpers.py
@@ -14,7 +14,7 @@ import numpy as np
 import pkgconfig
 import requests
 
-import sec_certs.constants as constants
+from sec_certs import constants
 from sec_certs.utils import parallel_processing
 from sec_certs.utils.tqdm import tqdm
 
@@ -44,12 +44,11 @@ def download_file(
             ctx = nullcontext
 
         if r.status_code == requests.codes.ok:
-            with ctx() as pbar:
-                with output.open("wb") as f:
-                    for data in r.iter_content(1024):
-                        f.write(data)
-                        if show_progress_bar:
-                            pbar.update(len(data))
+            with ctx() as pbar, output.open("wb") as f:
+                for data in r.iter_content(1024):
+                    f.write(data)
+                    if show_progress_bar:
+                        pbar.update(len(data))
 
             return r.status_code
     except requests.exceptions.Timeout:
@@ -97,8 +96,7 @@ def to_utc(timestamp: datetime) -> datetime:
     if offset is None:
         return timestamp
     timestamp -= offset
-    timestamp = timestamp.replace(tzinfo=None)
-    return timestamp
+    return timestamp.replace(tzinfo=None)
 
 
 def is_in_dict(target_dict: dict, path: str) -> bool:
@@ -106,8 +104,7 @@ def is_in_dict(target_dict: dict, path: str) -> bool:
     for item in path:
         if item not in current_level:
             return False
-        else:
-            current_level = current_level[item]
+        current_level = current_level[item]
     return True
 
 
diff --git a/src/sec_certs/utils/pandas.py b/src/sec_certs/utils/pandas.py
index 97068e77..749292e3 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
@@ -252,7 +252,6 @@ def filter_to_cves_within_validity_period(cc_df: pd.DataFrame, cve_dset: CVEData
     def filter_cves(
         cve_dset: CVEDataset, cves: set[str], not_valid_before: pd.Timestamp, not_valid_after: pd.Timestamp
     ) -> set[str] | float:
-
         # Mypy is complaining, but the Optional date is resolved at the beginning of the and condition
         result: set[str] = {
             x
diff --git a/src/sec_certs/utils/parallel_processing.py b/src/sec_certs/utils/parallel_processing.py
index ab0b4266..b3016695 100644
--- a/src/sec_certs/utils/parallel_processing.py
+++ b/src/sec_certs/utils/parallel_processing.py
@@ -21,7 +21,6 @@ def process_parallel(
     unpack: bool = False,
     progress_bar_desc: str | None = None,
 ) -> list[Any]:
-
     if max_workers == -1:
         max_workers = cpu_count()
 
diff --git a/src/sec_certs/utils/pdf.py b/src/sec_certs/utils/pdf.py
index e22076a1..edda0570 100644
--- a/src/sec_certs/utils/pdf.py
+++ b/src/sec_certs/utils/pdf.py
@@ -14,7 +14,7 @@ import pikepdf
 from pypdf import PdfReader
 from pypdf.generic import BooleanObject, ByteStringObject, FloatObject, IndirectObject, NumberObject, TextStringObject
 
-from sec_certs import constants as constants
+from sec_certs import constants
 from sec_certs.constants import (
     GARBAGE_ALPHA_CHARS_THRESHOLD,
     GARBAGE_AVG_LLEN_THRESHOLD,
@@ -181,12 +181,11 @@ def extract_pdf_metadata(filepath: Path) -> tuple[str, dict[str, Any] | None]:
     def resolve_indirect(val, bound=10):
         if isinstance(val, list) and bound:
             return [resolve_indirect(v, bound - 1) for v in val]
-        elif isinstance(val, IndirectObject) and bound:
+        if isinstance(val, IndirectObject) and bound:
             return resolve_indirect(val.get_object(), bound - 1)
-        else:
-            return val
+        return val
 
-    metadata: dict[str, Any] = dict()
+    metadata: dict[str, Any] = {}
 
     try:
         metadata["pdf_file_size_bytes"] = filepath.stat().st_size
@@ -252,14 +251,8 @@ def text_is_garbage(text: str) -> bool:
         if len(set(line[1::2])) > 1:
             every_second += 1
 
-    if lines:
-        avg_line_len = content_len / lines
-    else:
-        avg_line_len = 0
-    if size:
-        alpha = alpha_len / size
-    else:
-        alpha = 0
+    avg_line_len = content_len / lines if lines else 0
+    alpha = alpha_len / size if size else 0
 
     # If number of lines is small, this is garbage.
     if lines < GARBAGE_LINES_THRESHOLD:
diff --git a/src/sec_certs/utils/sanitization.py b/src/sec_certs/utils/sanitization.py
index 2f9cd046..3563e1f4 100644
--- a/src/sec_certs/utils/sanitization.py
+++ b/src/sec_certs/utils/sanitization.py
@@ -26,9 +26,9 @@ def sanitize_link(record: str | None) -> str | None:
 def sanitize_date(record: pd.Timestamp | date | np.datetime64) -> date | None:
     if pd.isnull(record):
         return None
-    elif isinstance(record, pd.Timestamp):
+    if isinstance(record, pd.Timestamp):
         return record.date()
-    elif isinstance(record, (date, type(None))):
+    if isinstance(record, (date, type(None))):
         return record
     raise ValueError("Unsupported type given as input")
 
diff --git a/tests/cc/test_cc_analysis.py b/tests/cc/test_cc_analysis.py
index ff9fe3c0..d8eeba12 100644
--- a/tests/cc/test_cc_analysis.py
+++ b/tests/cc/test_cc_analysis.py
@@ -4,8 +4,8 @@ import shutil
 from pathlib import Path
 
 import pytest
-
 import tests.data.cc.analysis
+
 from sec_certs.cert_rules import SARS_IMPLIED_FROM_EAL
 from sec_certs.dataset import CCDataset
 from sec_certs.dataset.cpe import CPEDataset
diff --git a/tests/cc/test_cc_certificate.py b/tests/cc/test_cc_certificate.py
index 2234ee11..2a5ff222 100644
--- a/tests/cc/test_cc_certificate.py
+++ b/tests/cc/test_cc_certificate.py
@@ -4,9 +4,9 @@ from datetime import date
 from pathlib import Path
 
 import pytest
-
 import tests.data.cc.analysis
 import tests.data.cc.certificate
+
 from sec_certs.dataset import CCDataset
 from sec_certs.sample import CCCertificate
 from sec_certs.sample.protection_profile import ProtectionProfile
diff --git a/tests/cc/test_cc_dataset.py b/tests/cc/test_cc_dataset.py
index 5d0b8fc5..2b37c2f8 100644
--- a/tests/cc/test_cc_dataset.py
+++ b/tests/cc/test_cc_dataset.py
@@ -5,8 +5,8 @@ from pathlib import Path
 from tempfile import TemporaryDirectory
 
 import pytest
-
 import tests.data.cc.dataset
+
 from sec_certs import constants
 from sec_certs.dataset import CCDataset
 from sec_certs.sample.cc import CCCertificate
diff --git a/tests/cc/test_cc_maintenance_updates.py b/tests/cc/test_cc_maintenance_updates.py
index 833391ef..b0c0bd5d 100644
--- a/tests/cc/test_cc_maintenance_updates.py
+++ b/tests/cc/test_cc_maintenance_updates.py
@@ -2,8 +2,8 @@ import json
 from pathlib import Path
 
 import pytest
-
 import tests.data.cc.dataset
+
 from sec_certs.dataset import CCDataset, CCDatasetMaintenanceUpdates
 from sec_certs.sample.cc_maintenance_update import CCMaintenanceUpdate
 
diff --git a/tests/fips/test_fips_algorithm_dataset.py b/tests/fips/test_fips_algorithm_dataset.py
index 88016f4f..1d45e67c 100644
--- a/tests/fips/test_fips_algorithm_dataset.py
+++ b/tests/fips/test_fips_algorithm_dataset.py
@@ -4,8 +4,8 @@ from pathlib import Path
 from typing import Any
 
 import pytest
-
 import tests.data.fips.dataset
+
 from sec_certs.dataset.fips_algorithm import FIPSAlgorithmDataset
 from sec_certs.sample.fips_algorithm import FIPSAlgorithm
 from sec_certs.serialization.json import SerializationError
diff --git a/tests/fips/test_fips_analysis.py b/tests/fips/test_fips_analysis.py
index b7b5d89f..d88047b5 100644
--- a/tests/fips/test_fips_analysis.py
+++ b/tests/fips/test_fips_analysis.py
@@ -3,8 +3,8 @@ from __future__ import annotations
 from pathlib import Path
 
 import pytest
-
 import tests.data.fips.dataset
+
 from sec_certs.dataset import CPEDataset, CVEDataset
 from sec_certs.dataset.fips import FIPSDataset
 from sec_certs.sample.cpe import CPE
diff --git a/tests/fips/test_fips_certificate.py b/tests/fips/test_fips_certificate.py
index b612834c..8f68238e 100644
--- a/tests/fips/test_fips_certificate.py
+++ b/tests/fips/test_fips_certificate.py
@@ -3,9 +3,9 @@ import shutil
 from pathlib import Path
 
 import pytest
-
 import tests.data.fips.certificate
 import tests.data.fips.dataset
+
 from sec_certs.dataset.fips import FIPSDataset
 from sec_certs.sample.fips import FIPSCertificate
 
diff --git a/tests/fips/test_fips_dataset.py b/tests/fips/test_fips_dataset.py
index b5f09aa9..4c89d37c 100644
--- a/tests/fips/test_fips_dataset.py
+++ b/tests/fips/test_fips_dataset.py
@@ -4,9 +4,9 @@ from pathlib import Path
 from tempfile import TemporaryDirectory
 
 import pytest
-
-import sec_certs.constants as constants
 import tests.data.fips.dataset
+
+from sec_certs import constants
 from sec_certs.dataset.fips import FIPSDataset
 from sec_certs.sample.fips import FIPSCertificate
 
diff --git a/tests/fips/test_fips_iut.py b/tests/fips/test_fips_iut.py
index 5a478a20..1dca086c 100644
--- a/tests/fips/test_fips_iut.py
+++ b/tests/fips/test_fips_iut.py
@@ -1,8 +1,8 @@
 from pathlib import Path
 
 import pytest
-
 import tests.data.fips.iut
+
 from sec_certs.dataset import IUTDataset
 from sec_certs.sample import IUTSnapshot
 
diff --git a/tests/fips/test_fips_mip.py b/tests/fips/test_fips_mip.py
index 8748bf23..4918a4c6 100644
--- a/tests/fips/test_fips_mip.py
+++ b/tests/fips/test_fips_mip.py
@@ -1,8 +1,8 @@
 from pathlib import Path
 
 import pytest
-
 import tests.data.fips.mip
+
 from sec_certs.dataset import MIPDataset
 from sec_certs.sample import MIPSnapshot
 
diff --git a/tests/test_common.py b/tests/test_common.py
index d5e62cc4..fa7a3775 100644
--- a/tests/test_common.py
+++ b/tests/test_common.py
@@ -6,4 +6,4 @@ def test_rules():
     assert "fips_cert_id" in fips_rules
     for rule_group in rules:
         if rule_group not in ("cc_rules", "fips_rules"):
-            assert rule_group in cc_rules.keys() or rule_group in fips_rules.keys()
+            assert rule_group in cc_rules or rule_group in fips_rules
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()