Blacken and isort.

16 files changed, 59 insertions, 57 deletions

diff --git a/sec_certs/cert_rules.py b/sec_certs/cert_rules.py
index ef80ef6a..4a12a272 100644
--- a/sec_certs/cert_rules.py
+++ b/sec_certs/cert_rules.py
@@ -1,8 +1,8 @@
-import copy
 import re
-import yaml
 from pathlib import Path
-from typing import Dict, List, Pattern, Set, Tuple
+from typing import Dict, Set, Tuple
+
+import yaml
 
 REGEXEC_SEP = r"[ ,;\]”)(]"
 
diff --git a/sec_certs/dataset/common_criteria.py b/sec_certs/dataset/common_criteria.py
index a2091f97..e1a1e343 100644
--- a/sec_certs/dataset/common_criteria.py
+++ b/sec_certs/dataset/common_criteria.py
@@ -16,8 +16,6 @@ import pandas as pd
 from bs4 import BeautifulSoup, Tag
 
 import sec_certs.utils.sanitization
-from sec_certs.utils import helpers as helpers
-from sec_certs.utils 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.protection_profile import ProtectionProfileDataset
@@ -28,6 +26,8 @@ from sec_certs.sample.cc_maintenance_update import CommonCriteriaMaintenanceUpda
 from sec_certs.sample.common_criteria import CommonCriteriaCert
 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 parallel_processing as cert_processing
 
 
 class CCDataset(Dataset[CommonCriteriaCert], ComplexSerializableType):
@@ -469,7 +469,10 @@ class CCDataset(Dataset[CommonCriteriaCert], ComplexSerializableType):
 
         profiles = {
             x.dgst: set(
-                [ProtectionProfile(pp_name=y) for y in sec_certs.utils.sanitization.sanitize_protection_profiles(x.protection_profiles)]
+                [
+                    ProtectionProfile(pp_name=y)
+                    for y in sec_certs.utils.sanitization.sanitize_protection_profiles(x.protection_profiles)
+                ]
             )
             for x in df_base.itertuples()
         }
diff --git a/sec_certs/dataset/cpe.py b/sec_certs/dataset/cpe.py
index 6948fd7e..1a8f6860 100644
--- a/sec_certs/dataset/cpe.py
+++ b/sec_certs/dataset/cpe.py
@@ -11,10 +11,10 @@ from typing import Any, ClassVar, Dict, Iterator, List, Set, Tuple, Union, cast
 import pandas as pd
 
 from sec_certs import constants
-from sec_certs.utils import helpers
 from sec_certs.dataset.cve import CVEDataset
 from sec_certs.sample.cpe import CPE, cached_cpe
 from sec_certs.serialization.json import ComplexSerializableType, serialize
+from sec_certs.utils import helpers
 
 logger = logging.getLogger(__name__)
 
diff --git a/sec_certs/dataset/cve.py b/sec_certs/dataset/cve.py
index c7fe69c3..d8bb8ec1 100644
--- a/sec_certs/dataset/cve.py
+++ b/sec_certs/dataset/cve.py
@@ -16,10 +16,10 @@ import pandas as pd
 import sec_certs.constants as constants
 import sec_certs.utils.helpers as helpers
 from sec_certs.config.configuration import config
-from sec_certs.utils.parallel_processing import process_parallel
 from sec_certs.sample.cpe import CPE, cached_cpe
 from sec_certs.sample.cve import CVE
 from sec_certs.serialization.json import ComplexSerializableType, CustomJSONDecoder, CustomJSONEncoder
+from sec_certs.utils.parallel_processing import process_parallel
 
 logger = logging.getLogger(__name__)
 
diff --git a/sec_certs/dataset/fips.py b/sec_certs/dataset/fips.py
index c051a887..10b81475 100644
--- a/sec_certs/dataset/fips.py
+++ b/sec_certs/dataset/fips.py
@@ -6,15 +6,15 @@ from typing import Any, Dict, List, Optional, Set
 from bs4 import BeautifulSoup, NavigableString
 from graphviz import Digraph
 
-from sec_certs.utils import helpers as helpers
-from sec_certs.utils import parallel_processing as cert_processing
 from sec_certs.config.configuration import config
 from sec_certs.dataset.dataset import Dataset
 from sec_certs.dataset.fips_algorithm import FIPSAlgorithmDataset
-from sec_certs.utils.helpers import fips_dgst
 from sec_certs.model.dependency_finder import DependencyFinder
 from sec_certs.sample.fips import FIPSCertificate
 from sec_certs.serialization.json import ComplexSerializableType, serialize
+from sec_certs.utils import helpers as helpers
+from sec_certs.utils import parallel_processing as cert_processing
+from sec_certs.utils.helpers import fips_dgst
 
 logger = logging.getLogger(__name__)
 
diff --git a/sec_certs/dataset/fips_algorithm.py b/sec_certs/dataset/fips_algorithm.py
index 91df0d7f..f0ddca6c 100644
--- a/sec_certs/dataset/fips_algorithm.py
+++ b/sec_certs/dataset/fips_algorithm.py
@@ -7,12 +7,12 @@ from bs4 import BeautifulSoup
 
 import sec_certs.utils.extract
 from sec_certs import constants as constants
-from sec_certs.utils import helpers as helpers
-from sec_certs.utils import parallel_processing as cert_processing
 from sec_certs.config.configuration import config
 from sec_certs.dataset.dataset import Dataset
 from sec_certs.sample.fips import FIPSCertificate
 from sec_certs.serialization.json import ComplexSerializableType, CustomJSONDecoder, CustomJSONEncoder
+from sec_certs.utils import helpers as helpers
+from sec_certs.utils import parallel_processing as cert_processing
 
 logger = logging.getLogger(__name__)
 
diff --git a/sec_certs/dataset/fips_iut.py b/sec_certs/dataset/fips_iut.py
index dfb2884b..b731115c 100644
--- a/sec_certs/dataset/fips_iut.py
+++ b/sec_certs/dataset/fips_iut.py
@@ -3,9 +3,9 @@ from pathlib import Path
 from typing import Dict, Iterator, List, Mapping, Union
 
 from sec_certs.dataset.dataset import logger
-from sec_certs.utils.helpers import tqdm
 from sec_certs.sample.fips_iut import IUTSnapshot
 from sec_certs.serialization.json import ComplexSerializableType
+from sec_certs.utils.helpers import tqdm
 
 
 @dataclass
diff --git a/sec_certs/dataset/fips_mip.py b/sec_certs/dataset/fips_mip.py
index 2ee8deda..91d8120c 100644
--- a/sec_certs/dataset/fips_mip.py
+++ b/sec_certs/dataset/fips_mip.py
@@ -3,9 +3,9 @@ from pathlib import Path
 from typing import Dict, Iterator, List, Mapping, Union
 
 from sec_certs.dataset.dataset import logger
-from sec_certs.utils.helpers import tqdm
 from sec_certs.sample.fips_mip import MIPSnapshot
 from sec_certs.serialization.json import ComplexSerializableType
+from sec_certs.utils.helpers import tqdm
 
 
 @dataclass
diff --git a/sec_certs/sample/common_criteria.py b/sec_certs/sample/common_criteria.py
index a26f4310..9d78274b 100644
--- a/sec_certs/sample/common_criteria.py
+++ b/sec_certs/sample/common_criteria.py
@@ -18,13 +18,13 @@ 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.utils import helpers
-from sec_certs.cert_rules import SARS_IMPLIED_FROM_EAL, security_level_csv_scan, cc_rules
+from sec_certs.cert_rules import SARS_IMPLIED_FROM_EAL, cc_rules, security_level_csv_scan
 from sec_certs.sample.certificate import Certificate, Heuristics, References, logger
 from sec_certs.sample.protection_profile import ProtectionProfile
 from sec_certs.sample.sar import SAR
 from sec_certs.serialization.json import ComplexSerializableType
 from sec_certs.serialization.pandas import PandasSerializableType
+from sec_certs.utils import helpers
 
 HEADERS = {
     "anssi": sec_certs.utils.extract.search_only_headers_anssi,
@@ -67,9 +67,15 @@ class CommonCriteriaCert(
         maintenance_st_link: Optional[str]
 
         def __post_init__(self):
-            super().__setattr__("maintenance_report_link", sec_certs.utils.sanitization.sanitize_link(self.maintenance_report_link))
-            super().__setattr__("maintenance_st_link", sec_certs.utils.sanitization.sanitize_link(self.maintenance_st_link))
-            super().__setattr__("maintenance_title", sec_certs.utils.sanitization.sanitize_string(self.maintenance_title))
+            super().__setattr__(
+                "maintenance_report_link", sec_certs.utils.sanitization.sanitize_link(self.maintenance_report_link)
+            )
+            super().__setattr__(
+                "maintenance_st_link", sec_certs.utils.sanitization.sanitize_link(self.maintenance_st_link)
+            )
+            super().__setattr__(
+                "maintenance_title", sec_certs.utils.sanitization.sanitize_string(self.maintenance_title)
+            )
             super().__setattr__("maintenance_date", sec_certs.utils.sanitization.sanitize_date(self.maintenance_date))
 
         @classmethod
diff --git a/sec_certs/sample/cpe.py b/sec_certs/sample/cpe.py
index ff3416b5..4a026ce1 100644
--- a/sec_certs/sample/cpe.py
+++ b/sec_certs/sample/cpe.py
@@ -3,9 +3,9 @@ from functools import lru_cache
 from typing import Any, ClassVar, Dict, List, Optional, Tuple
 
 from sec_certs import constants
-from sec_certs.utils import helpers
 from sec_certs.serialization.json import ComplexSerializableType
 from sec_certs.serialization.pandas import PandasSerializableType
+from sec_certs.utils import helpers
 
 
 @dataclass(init=False)
diff --git a/sec_certs/sample/fips.py b/sec_certs/sample/fips.py
index 51e795fc..5b2c7367 100644
--- a/sec_certs/sample/fips.py
+++ b/sec_certs/sample/fips.py
@@ -5,7 +5,7 @@ import re
 from dataclasses import dataclass, field
 from datetime import datetime
 from pathlib import Path
-from typing import Any, ClassVar, Dict, List, Match, Optional, Pattern, Set, Tuple, Union
+from typing import Any, ClassVar, Dict, List, Optional, Pattern, Set, Tuple, Union
 
 import requests
 from bs4 import BeautifulSoup, NavigableString, Tag
@@ -19,10 +19,10 @@ import sec_certs.utils.pdf
 import sec_certs.utils.tables
 from sec_certs.cert_rules import fips_rules
 from sec_certs.config.configuration import config
-from sec_certs.utils.helpers import fips_dgst
 from sec_certs.sample.certificate import Certificate, Heuristics, References, logger
 from sec_certs.sample.cpe import CPE
 from sec_certs.serialization.json import ComplexSerializableType
+from sec_certs.utils.helpers import fips_dgst
 
 
 class FIPSCertificate(Certificate["FIPSCertificate", "FIPSCertificate.FIPSHeuristics"], ComplexSerializableType):
diff --git a/sec_certs/sample/fips_iut.py b/sec_certs/sample/fips_iut.py
index bdf90fa6..3182585c 100644
--- a/sec_certs/sample/fips_iut.py
+++ b/sec_certs/sample/fips_iut.py
@@ -6,8 +6,8 @@ from typing import Dict, Iterator, List, Mapping, Optional, Set, Union
 import requests
 from bs4 import BeautifulSoup, Tag
 
-from sec_certs.utils.helpers import to_utc
 from sec_certs.serialization.json import ComplexSerializableType
+from sec_certs.utils.helpers import to_utc
 
 
 @dataclass(frozen=True)
diff --git a/sec_certs/sample/fips_mip.py b/sec_certs/sample/fips_mip.py
index 2a0e480f..0a95c74e 100644
--- a/sec_certs/sample/fips_mip.py
+++ b/sec_certs/sample/fips_mip.py
@@ -9,8 +9,8 @@ import requests
 from bs4 import BeautifulSoup, Tag
 
 from sec_certs.constants import FIPS_MIP_STATUS_RE
-from sec_certs.utils.helpers import to_utc
 from sec_certs.serialization.json import ComplexSerializableType
+from sec_certs.utils.helpers import to_utc
 
 logger = logging.getLogger(__name__)
 
diff --git a/sec_certs/sample/protection_profile.py b/sec_certs/sample/protection_profile.py
index 55fca1c0..b720fa04 100644
--- a/sec_certs/sample/protection_profile.py
+++ b/sec_certs/sample/protection_profile.py
@@ -3,8 +3,7 @@ import logging
 from dataclasses import dataclass
 from typing import Any, Dict, FrozenSet, Optional
 
-import sec_certs.utils.helpers as helpers
-import sec_certs.utils.sanitization
+import sec_certs.utils.sanitization as sanitization
 from sec_certs.serialization.json import ComplexSerializableType
 
 logger = logging.getLogger(__name__)
@@ -21,8 +20,8 @@ class ProtectionProfile(ComplexSerializableType):
     pp_ids: Optional[FrozenSet[str]] = None
 
     def __post_init__(self):
-        super().__setattr__("pp_name", sec_certs.utils.sanitization.sanitize_string(self.pp_name))
-        super().__setattr__("pp_link", sec_certs.utils.sanitization.sanitize_link(self.pp_link))
+        super().__setattr__("pp_name", sanitization.sanitize_string(self.pp_name))
+        super().__setattr__("pp_link", sanitization.sanitize_link(self.pp_link))
 
     @classmethod
     def from_dict(cls, dct: Dict[str, Any]) -> "ProtectionProfile":
@@ -32,8 +31,8 @@ class ProtectionProfile(ComplexSerializableType):
 
     @classmethod
     def from_old_api_dict(cls, dct: Dict[str, Any]) -> "ProtectionProfile":
-        pp_name = sec_certs.utils.sanitization.sanitize_string(dct["csv_scan"]["cc_pp_name"])
-        pp_link = sec_certs.utils.sanitization.sanitize_link(dct["csv_scan"]["link_pp_document"])
+        pp_name = sanitization.sanitize_string(dct["csv_scan"]["cc_pp_name"])
+        pp_link = sanitization.sanitize_link(dct["csv_scan"]["link_pp_document"])
         pp_ids = frozenset(dct["processed"]["cc_pp_csvid"]) if dct["processed"]["cc_pp_csvid"] else None
         return cls(pp_name, pp_link, pp_ids)
 
diff --git a/sec_certs/sample/sar.py b/sec_certs/sample/sar.py
index 96c8f48d..31359299 100644
--- a/sec_certs/sample/sar.py
+++ b/sec_certs/sample/sar.py
@@ -49,7 +49,9 @@ 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])
+        return any(
+            [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:
         if not isinstance(other, SAR):
diff --git a/sec_certs/utils/extract.py b/sec_certs/utils/extract.py
index 49126587..b47e5ec8 100644
--- a/sec_certs/utils/extract.py
+++ b/sec_certs/utils/extract.py
@@ -1,18 +1,14 @@
 import logging
 import os
 import re
+from collections import Counter
 from enum import Enum
 from pathlib import Path
-from collections import Counter
 from typing import Any, Dict, Generator, Hashable, Iterator, Optional, Tuple, Union
 
 from sec_certs import constants as constants
 from sec_certs.cert_rules import REGEXEC_SEP
-from sec_certs.constants import (
-    FILE_ERRORS_STRATEGY,
-    LINE_SEPARATOR,
-    MAX_ALLOWED_MATCH_LENGTH
-)
+from sec_certs.constants import FILE_ERRORS_STRATEGY, LINE_SEPARATOR, MAX_ALLOWED_MATCH_LENGTH
 
 logger = logging.getLogger(__name__)
 
@@ -325,7 +321,7 @@ def search_only_headers_bsi(filepath: Path):  # noqa: C901
                             f"string {from_keyword} detected in certified item - shall not be here, fixing..."
                         )
                         certified_item_first = certified_item[: certified_item.find(from_keyword)]
-                        developer = certified_item[certified_item.find(from_keyword) + from_keyword_len:]
+                        developer = certified_item[certified_item.find(from_keyword) + from_keyword_len :]
                         certified_item = certified_item_first
                         continue
 
@@ -421,7 +417,7 @@ def search_only_headers_nscib(filepath: Path):  # noqa: C901
                 certified_item = ""
                 for name_index in range(item_offset, line_index):
                     certified_item += lines[name_index] + " "
-                developer = line[line.find(SPONSORDEVELOPER_STR) + len(SPONSORDEVELOPER_STR):]
+                developer = line[line.find(SPONSORDEVELOPER_STR) + len(SPONSORDEVELOPER_STR) :]
 
             SPONSOR_STR = "Sponsor:"
 
@@ -437,15 +433,15 @@ def search_only_headers_nscib(filepath: Path):  # noqa: C901
 
             DEVELOPER_STR = "Developer:"
             if DEVELOPER_STR in line:
-                developer = line[line.find(DEVELOPER_STR) + len(DEVELOPER_STR):]
+                developer = line[line.find(DEVELOPER_STR) + len(DEVELOPER_STR) :]
 
             CERTLAB_STR = "Evaluation facility:"
             if CERTLAB_STR in line:
-                cert_lab = line[line.find(CERTLAB_STR) + len(CERTLAB_STR):]
+                cert_lab = line[line.find(CERTLAB_STR) + len(CERTLAB_STR) :]
 
             REPORTNUM_STR = "Report number:"
             if REPORTNUM_STR in line:
-                cert_id = line[line.find(REPORTNUM_STR) + len(REPORTNUM_STR):]
+                cert_id = line[line.find(REPORTNUM_STR) + len(REPORTNUM_STR) :]
 
         if not no_match_yet:
             items_found[constants.TAG_CERT_ID] = normalize_match_string(cert_id)
@@ -496,7 +492,7 @@ def search_only_headers_niap(filepath: Path):
                 certified_item = ""
                 for name_index in range(item_offset, line_index):
                     certified_item += lines[name_index] + " "
-                cert_id = line[line.find(REPORTNUM_STR) + len(REPORTNUM_STR):]
+                cert_id = line[line.find(REPORTNUM_STR) + len(REPORTNUM_STR) :]
                 break
 
         if not no_match_yet:
@@ -542,12 +538,12 @@ def search_only_headers_canada(filepath: Path):  # noqa: C901
                         items_found = {}
                         no_match_yet = False
 
-                    cert_id = line_certid[line_certid.find(matched_number_str) + len(matched_number_str):]
+                    cert_id = line_certid[line_certid.find(matched_number_str) + len(matched_number_str) :]
                     break
 
             if (
-                    "Government of Canada. This document is the property of the Government of Canada. It shall not be altered,"
-                    in line
+                "Government of Canada. This document is the property of the Government of Canada. It shall not be altered,"
+                in line
             ):
                 REPORTNUM_STR = "Evaluation number:"
                 for offset in range(1, 20):
@@ -557,14 +553,14 @@ def search_only_headers_canada(filepath: Path):  # noqa: C901
                             items_found = {}
                             no_match_yet = False
                         line_certid = lines[line_index + offset - 4]
-                        cert_id = line_certid[line_certid.find(REPORTNUM_STR) + len(REPORTNUM_STR):]
+                        cert_id = line_certid[line_certid.find(REPORTNUM_STR) + len(REPORTNUM_STR) :]
                         break
                 if not no_match_yet:
                     break
 
             if (
-                    "UNCLASSIFIED / NON CLASSIFIÉ" in line
-                    and "COMMON CRITERIA CERTIFICATION REPORT" in lines[line_index + 2]
+                "UNCLASSIFIED / NON CLASSIFIÉ" in line
+                and "COMMON CRITERIA CERTIFICATION REPORT" in lines[line_index + 2]
             ):
                 line_certid = lines[line_index + 1]
                 if no_match_yet:
@@ -605,9 +601,7 @@ def save_modified_cert_file(target_file: Union[str, Path], modified_cert_file_te
 
 
 def extract_keywords(filepath: Path, search_rules) -> Optional[Dict[str, Dict[str, int]]]:
-    """
-
-    """
+    """ """
     try:
         return parse_cert_file(filepath, search_rules, -1, constants.LINE_SEPARATOR)
     except Exception as e:
@@ -618,9 +612,7 @@ def extract_keywords(filepath: Path, search_rules) -> Optional[Dict[str, Dict[st
 
 
 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_text_file(
         file_name, limit_max_lines, line_separator
     )
@@ -656,7 +648,7 @@ def normalize_match_string(match: str) -> str:
 
 
 def load_text_file(
-        file_name: Union[str, Path], limit_max_lines: int = -1, line_separator: str = LINE_SEPARATOR
+    file_name: Union[str, Path], limit_max_lines: int = -1, line_separator: str = LINE_SEPARATOR
 ) -> Tuple[str, str, bool]:
     """
     Load the text contents of a file at `file_name`, upto `limit_max_lines` of lines, replace