flake8 compliance

17 files changed, 38 insertions, 49 deletions

diff --git a/cc_cli.py b/cc_cli.py
index bd9e586b..72a8de67 100755
--- a/cc_cli.py
+++ b/cc_cli.py
@@ -86,7 +86,7 @@ def main(
         dset: CCDataset = CCDataset.from_json(Path(inputpath))
         if output:
             print(
-                f"Warning: you provided both input and output paths. The dataset from input path will get copied to output path."
+                "Warning: you provided both input and output paths. The dataset from input path will get copied to output path."
             )
             dset.root_dir = output
 
@@ -101,7 +101,7 @@ def main(
         dset = CCDataset(
             certs={},
             root_dir=output,
-            name=f"CommonCriteria_dataset",
+            name="CommonCriteria_dataset",
             description=f"Full CommonCriteria dataset snapshot {datetime.now().date()}",
         )
         dset.get_certs_from_web()
diff --git a/examples/cc_oop_demo.py b/examples/cc_oop_demo.py
index 60949cd1..46f4d882 100644
--- a/examples/cc_oop_demo.py
+++ b/examples/cc_oop_demo.py
@@ -43,7 +43,7 @@ def main():
     dset._extract_data()
 
     # transform to pandas DataFrame
-    df = dset.to_pandas()
+    # df = dset.to_pandas()
 
     # Compute heuristics on the dataset
     dset._compute_heuristics()
diff --git a/examples/fips_cpe_labeling.py b/examples/fips_cpe_labeling.py
index 8b2d99d2..5cab7829 100644
--- a/examples/fips_cpe_labeling.py
+++ b/examples/fips_cpe_labeling.py
@@ -3,7 +3,6 @@ from datetime import datetime
 from pathlib import Path
 
 from sec_certs.dataset.fips import FIPSDataset
-from sec_certs.model.evaluation import evaluate, get_validation_dgsts
 
 logger = logging.getLogger(__name__)
 
diff --git a/fips_cli.py b/fips_cli.py
index b1bca9c2..149d2f81 100755
--- a/fips_cli.py
+++ b/fips_cli.py
@@ -1,6 +1,5 @@
 #!/usr/bin/env python3
 import logging
-import os
 import sys
 from datetime import datetime
 from pathlib import Path
@@ -117,8 +116,6 @@ def main(
     stream_handler.setFormatter(formatter)
     handlers: List[logging.StreamHandler] = [file_handler]
 
-    script_dir = os.path.dirname(os.path.realpath(__file__))
-
     if output:
         output = Path(output)
 
diff --git a/sec_certs/cert_rules.py b/sec_certs/cert_rules.py
index 50278e83..8d0637b8 100644
--- a/sec_certs/cert_rules.py
+++ b/sec_certs/cert_rules.py
@@ -54,8 +54,8 @@ rules_protection_profiles = [
     "BSI-(?:CC[-_]|)PP[-_]*.+?",
     "PP-SSCD.+?",
     "PP_DBMS_.+?"
-    #    'Protection Profile',
-    #'CCMB-20.+?',
+    #  'Protection Profile',
+    # 'CCMB-20.+?',
     "BSI-CCPP-.+?",
     "ANSSI-CC-PP.+?",
     "WBIS_V[0-9]\\.[0-9]",
@@ -145,8 +145,8 @@ rules_cc_claims = [
 
 
 rules_javacard = [
-    #'(?:Java Card|JavaCard)',
-    #'(?:Global Platform|GlobalPlatform)',
+    # '(?:Java Card|JavaCard)',
+    # '(?:Global Platform|GlobalPlatform)',
     r"(?:Java Card|JavaCard) [2-3]\.[0-9](?:\.[0-9]|)",
     r"JC[2-3]\.[0-9](?:\.[0-9]|)",
     r"(?:Java Card|JavaCard) \(version [2-3]\.[0-9](?:\.[0-9]|)\)",
@@ -404,7 +404,7 @@ rules_fips_remove_algorithm_ids = [
 rules_fips_to_remove = [
     # --- random words found ---
     r"[Ss]lot #\d",  # a card slot, #2069
-    r"[Ss]eals? ?\(?#\d - #\d",  #  #1232
+    r"[Ss]eals? ?\(?#\d - #\d",  # #1232
     r"\[#\d*\]",  # some certs use this as references
     r"CSP ?#\d",  # #2795
     r"[Pp]ower [Ss]upply #\d",  # #604
diff --git a/sec_certs/dataset/common_criteria.py b/sec_certs/dataset/common_criteria.py
index 785f7e62..b0116221 100644
--- a/sec_certs/dataset/common_criteria.py
+++ b/sec_certs/dataset/common_criteria.py
@@ -327,8 +327,8 @@ class CCDataset(Dataset, ComplexSerializableType):
 
         df["dgst"] = df.apply(lambda row: helpers.get_first_16_bytes_sha256(_get_primary_key_str(row)), axis=1)
 
-        df_base = df.loc[df.is_maintenance == False].copy()
-        df_main = df.loc[df.is_maintenance == True].copy()
+        df_base = df.loc[~df.is_maintenance].copy()
+        df_main = df.loc[df.is_maintenance].copy()
 
         df_base.report_link = df_base.report_link.map(map_ip_to_hostname)
         df_base.st_link = df_base.st_link.map(map_ip_to_hostname)
@@ -424,7 +424,8 @@ class CCDataset(Dataset, ComplexSerializableType):
 
             table = tables[0]
             rows = list(table.find_all("tr"))
-            header, footer, body = rows[0], rows[1], rows[2:]
+            # header, footer = rows[0], rows[1]
+            body = rows[2:]
 
             # TODO: It's possible to obtain timestamp of the moment when the list was generated. It's identical for each table and should thus only be obtained once. Not necessarily in each table
             # timestamp = _get_timestamp_from_footer(footer)
diff --git a/sec_certs/dataset/cve.py b/sec_certs/dataset/cve.py
index 49cdad27..6e662ac6 100644
--- a/sec_certs/dataset/cve.py
+++ b/sec_certs/dataset/cve.py
@@ -8,7 +8,7 @@ import tempfile
 import zipfile
 from dataclasses import dataclass, field
 from pathlib import Path
-from typing import Dict, Final, List, Optional, Set, Tuple, Union
+from typing import Dict, Final, List, Optional, Set, Union
 
 import pandas as pd
 
@@ -111,13 +111,13 @@ class CVEDataset(ComplexSerializableType):
 
     @classmethod
     def from_web(cls, start_year: int = 2002, end_year: int = datetime.datetime.now().year):
-        logger.info(f"Building CVE dataset from nist.gov website.")
+        logger.info("Building CVE dataset from nist.gov website.")
         with tempfile.TemporaryDirectory() as tmp_dir:
             cls.download_cves(tmp_dir, start_year, end_year)
             json_files = glob.glob(tmp_dir + "/*.json")
 
             all_cves = dict()
-            logger.info(f"Downloaded required resources. Building CVEDataset from jsons.")
+            logger.info("Downloaded required resources. Building CVEDataset from jsons.")
             results = process_parallel(
                 cls.from_nist_json,
                 json_files,
diff --git a/sec_certs/dataset/fips.py b/sec_certs/dataset/fips.py
index cea42eeb..d1ce2dea 100644
--- a/sec_certs/dataset/fips.py
+++ b/sec_certs/dataset/fips.py
@@ -13,7 +13,7 @@ from sec_certs import constants as constants
 from sec_certs import helpers as helpers
 from sec_certs import parallel_processing as cert_processing
 from sec_certs.config.configuration import config
-from sec_certs.dataset.dataset import Dataset, logger
+from sec_certs.dataset.dataset import Dataset
 from sec_certs.dataset.fips_algorithm import FIPSAlgorithmDataset
 from sec_certs.sample.certificate import Certificate
 from sec_certs.sample.fips import FIPSCertificate
diff --git a/sec_certs/helpers.py b/sec_certs/helpers.py
index 9198f5c5..3637fe38 100644
--- a/sec_certs/helpers.py
+++ b/sec_certs/helpers.py
@@ -1,4 +1,3 @@
-import copy
 import hashlib
 import html
 import logging
@@ -10,14 +9,13 @@ from datetime import date
 from enum import Enum
 from multiprocessing.pool import ThreadPool
 from pathlib import Path
-from typing import Any, Dict, Hashable, List, Optional, Sequence, Set, Tuple, Union
+from typing import Dict, Hashable, List, Optional, Sequence, Set, Tuple, Union
 
 import matplotlib.pyplot as plt
 import numpy as np
 import pandas as pd
 import pikepdf
 import requests
-from packaging.version import VERSION_PATTERN
 from PyPDF2 import PdfFileReader
 from tqdm import tqdm as tqdm_original
 
@@ -227,7 +225,7 @@ def extract_pdf_metadata(filepath: Path):
 
 
 # TODO: Please, refactor me. I reallyyyyyyyyyyyyy need it!!!!!!
-def search_only_headers_anssi(filepath: Path):
+def search_only_headers_anssi(filepath: Path):  # noqa: C901
     class HEADER_TYPE(Enum):
         HEADER_FULL = 1
         HEADER_MISSING_CERT_ITEM_VERSION = 2
@@ -273,11 +271,11 @@ def search_only_headers_anssi(filepath: Path):
         ),
         (
             HEADER_TYPE.HEADER_FULL,
-            "Référence du rapport de certification(.+)Nom du produit(.+)Référence/version du produit(.+)Conformité aux profils de protection(.+)Critères d\’évaluation et version(.+)Niveau d\’évaluation(.+)Développeurs(.+)Centre d\’évaluation(.+)Accords de reconnaissance applicables",
+            "Référence du rapport de certification(.+)Nom du produit(.+)Référence/version du produit(.+)Conformité aux profils de protection(.+)Critères d\’évaluation et version(.+)Niveau d\’évaluation(.+)Développeurs(.+)Centre d\’évaluation(.+)Accords de reconnaissance applicables",  # noqa: W605
         ),
         (
             HEADER_TYPE.HEADER_FULL,
-            "Référence du rapport de certification(.+)Nom du produit \\(référence/version\\)(.+)Nom de la TOE \\(référence/version\\)(.+)Conformité à un profil de protection(.+)Critères d\’évaluation et version(.+)Niveau d\’évaluation(.+)Développeurs(.+)Centre d’évaluation(.+)Accords de reconnaissance applicables",
+            "Référence du rapport de certification(.+)Nom du produit \\(référence/version\\)(.+)Nom de la TOE \\(référence/version\\)(.+)Conformité à un profil de protection(.+)Critères d\’évaluation et version(.+)Niveau d\’évaluation(.+)Développeurs(.+)Centre d’évaluation(.+)Accords de reconnaissance applicables",  # noqa: W605
         ),
         (
             HEADER_TYPE.HEADER_FULL,
@@ -491,7 +489,7 @@ def search_only_headers_anssi(filepath: Path):
 
 
 # TODO: Please refactor me. I need it so badlyyyyyy!!!
-def search_only_headers_bsi(filepath: Path):
+def search_only_headers_bsi(filepath: Path):  # noqa: C901
     LINE_SEPARATOR_STRICT = " "
     NUM_LINES_TO_INVESTIGATE = 15
     rules_certificate_preface = [
@@ -561,7 +559,7 @@ def search_only_headers_bsi(filepath: Path):
 
             for m in re.finditer(rule_and_sep, whole_text):
                 # check if previous rules had at least one match
-                if not constants.TAG_CERT_ID in items_found.keys():
+                if constants.TAG_CERT_ID not in items_found.keys():
                     logger.error("ERROR: front page not found for file: {}".format(filepath))
 
                 match_groups = m.groups()
@@ -649,13 +647,14 @@ def save_modified_cert_file(target_file, modified_cert_file_text, is_unicode_tex
 
     try:
         write_file.write(modified_cert_file_text)
-    except UnicodeEncodeError as e:
+    except UnicodeEncodeError:
         print("UnicodeDecodeError while writing file fragments back")
     finally:
         write_file.close()
 
 
-def parse_cert_file(file_name, search_rules, limit_max_lines=-1, line_separator=LINE_SEPARATOR):
+# TODO: Please, refactor me.
+def parse_cert_file(file_name, search_rules, limit_max_lines=-1, line_separator=LINE_SEPARATOR):  # noqa: C901
     whole_text, whole_text_with_newlines, was_unicode_decode_error = load_cert_file(
         file_name, limit_max_lines, line_separator
     )
@@ -758,7 +757,7 @@ def load_cert_file(file_name, limit_max_lines=-1, line_separator=LINE_SEPARATOR)
     # we will estimate the line for searched matches
     # => we need to known how much lines were modified (removal of eoln..)
     # for removed newline and for any added separator
-    line_length_compensation = 1 - len(LINE_SEPARATOR)
+    # line_length_compensation = 1 - len(LINE_SEPARATOR)
     lines_included = 0
     for line in lines:
         if limit_max_lines != -1 and lines_included >= limit_max_lines:
diff --git a/sec_certs/model/cpe_matching.py b/sec_certs/model/cpe_matching.py
index 042f6705..610b409a 100644
--- a/sec_certs/model/cpe_matching.py
+++ b/sec_certs/model/cpe_matching.py
@@ -1,13 +1,10 @@
 import itertools
-import json
 import logging
-import operator
 import re
-from pathlib import Path
-from typing import Dict, List, Optional, Set, Tuple, Union
+from typing import Dict, List, Optional, Set, Tuple
 
 from packaging.version import parse
-from rapidfuzz import fuzz, process
+from rapidfuzz import fuzz
 from sklearn.base import BaseEstimator
 
 import sec_certs.helpers as helpers
diff --git a/sec_certs/sample/common_criteria.py b/sec_certs/sample/common_criteria.py
index 994f56ca..a353ff61 100644
--- a/sec_certs/sample/common_criteria.py
+++ b/sec_certs/sample/common_criteria.py
@@ -432,11 +432,11 @@ class CommonCriteriaCert(Certificate, PandasSerializableType, ComplexSerializabl
                 main_report_link = None
                 main_st_link = None
                 links = u.find_all("a")
-                for l in links:
-                    if l.get("title").startswith("Maintenance Report:"):
-                        main_report_link = CommonCriteriaCert.cc_url + l.get("href")
-                    elif l.get("title").startswith("Maintenance ST"):
-                        main_st_link = CommonCriteriaCert.cc_url + l.get("href")
+                for link in links:
+                    if link.get("title").startswith("Maintenance Report:"):
+                        main_report_link = CommonCriteriaCert.cc_url + link.get("href")
+                    elif link.get("title").startswith("Maintenance ST"):
+                        main_st_link = CommonCriteriaCert.cc_url + link.get("href")
                     else:
                         logger.error("Unknown link in Maintenance part!")
                 maintenance_updates.add(
diff --git a/sec_certs/sample/cve.py b/sec_certs/sample/cve.py
index 94484374..2bc28c4a 100644
--- a/sec_certs/sample/cve.py
+++ b/sec_certs/sample/cve.py
@@ -1,7 +1,7 @@
 import datetime
 import itertools
 from dataclasses import dataclass
-from typing import Any, ClassVar, Dict, List, Optional, Tuple
+from typing import ClassVar, Dict, List, Optional, Tuple
 
 from dateutil.parser import isoparse
 
diff --git a/sec_certs/sample/fips.py b/sec_certs/sample/fips.py
index 01ac3f2d..b66d11df 100644
--- a/sec_certs/sample/fips.py
+++ b/sec_certs/sample/fips.py
@@ -11,7 +11,6 @@ from dateutil import parser
 from tabula import read_pdf
 
 import sec_certs.constants as constants
-from sec_certs import constants as constants
 from sec_certs import helpers
 from sec_certs.cert_rules import REGEXEC_SEP, fips_common_rules, fips_rules
 from sec_certs.config.configuration import config
@@ -572,7 +571,7 @@ class FIPSCertificate(Certificate, ComplexSerializableType):
         algs_vals = list(cert.pdf_scan.keywords["rules_fips_algorithms"].values())
         table_vals = [x["Certificate"] for x in cert.pdf_scan.algorithms]
         tables = [x.strip() for y in table_vals for x in y]
-        iterable = [l for x in algs_vals for l in list(x.keys())]
+        iterable = [alg for x in algs_vals for alg in list(x.keys())]
         iterable += tables
         all_algorithms = set()
         for x in iterable:
diff --git a/tests/fips_test_utils.py b/tests/fips_test_utils.py
index 89b61e7e..2fce325b 100644
--- a/tests/fips_test_utils.py
+++ b/tests/fips_test_utils.py
@@ -47,6 +47,6 @@ def generate_html(ids: List[str], path: Path):
             </tbody>
         </table>
     </body>
-	"""
+    """
     with open(path, "w") as f:
         f.write(f"{html_head}\n{html_body}\n")
diff --git a/tests/test_cc_heuristics.py b/tests/test_cc_heuristics.py
index 13bff947..caa6b1fb 100644
--- a/tests/test_cc_heuristics.py
+++ b/tests/test_cc_heuristics.py
@@ -1,5 +1,3 @@
-import copy
-import datetime
 import shutil
 import tempfile
 from pathlib import Path
diff --git a/tests/test_cc_oop.py b/tests/test_cc_oop.py
index 0149a23d..2426476d 100644
--- a/tests/test_cc_oop.py
+++ b/tests/test_cc_oop.py
@@ -1,11 +1,10 @@
 import filecmp
-import json
 import os
 import shutil
 import tempfile
 from datetime import date, datetime
 from pathlib import Path
-from tempfile import NamedTemporaryFile, TemporaryDirectory, mkstemp
+from tempfile import NamedTemporaryFile, TemporaryDirectory
 from unittest import TestCase
 
 import sec_certs.constants as constants
diff --git a/tests/test_fips_oop.py b/tests/test_fips_oop.py
index 9eb04d67..17b3325a 100644
--- a/tests/test_fips_oop.py
+++ b/tests/test_fips_oop.py
@@ -1,7 +1,7 @@
 import shutil
 from pathlib import Path
 from tempfile import TemporaryDirectory
-from typing import ClassVar, Dict, Final, List, Optional, Union
+from typing import Dict, Final, List
 from unittest import TestCase
 
 import tests.data.test_fips_oop