diff options
| author | Stanislav Boboň | 2020-12-03 12:45:23 +0100 |
|---|---|---|
| committer | Stanislav Boboň | 2020-12-03 12:45:23 +0100 |
| commit | 135c3a61cff884bf7d2610ef33ef53caa6286483 (patch) | |
| tree | fdb8cb9407047adb279bacff5e325ae37cddf630 | |
| parent | 69223f5070cb8fdfe585e2b5a073c9d39d14e48d (diff) | |
| download | sec-certs-135c3a61cff884bf7d2610ef33ef53caa6286483.tar.gz sec-certs-135c3a61cff884bf7d2610ef33ef53caa6286483.tar.zst sec-certs-135c3a61cff884bf7d2610ef33ef53caa6286483.zip | |
ugly import statements and short term goals
| -rw-r--r-- | sec_certs/certificate.py | 14 | ||||
| -rw-r--r-- | sec_certs/dataset.py | 2 |
2 files changed, 8 insertions, 8 deletions
diff --git a/sec_certs/certificate.py b/sec_certs/certificate.py index d58f59f4..5682fb58 100644 --- a/sec_certs/certificate.py +++ b/sec_certs/certificate.py @@ -12,7 +12,7 @@ from abc import ABC, abstractmethod from bs4 import Tag, BeautifulSoup, NavigableString from typing import Union, Optional, List, Dict, ClassVar, TypeVar, Type -from sec_certs import helpers, extract_certificates +from sec_certs import helpers, extract_certificates, dataset from sec_certs.serialization import ComplexSerializableType, CustomJSONDecoder, CustomJSONEncoder import sec_certs.constants as constants @@ -243,7 +243,7 @@ class FIPSCertificate(Certificate, ComplexSerializableType): html_items_found['fips_vendor'] = vendor_string if html_items_found['fips_vendor'] == '': - logger.warning(f"WARNING: NO VENDOR FOUND{current_file}") + logger.warning(f"WARNING: NO VENDOR FOUND {current_file}") @staticmethod def parse_lab(current_div: Tag, html_items_found: Dict, current_file: Path): @@ -254,21 +254,19 @@ class FIPSCertificate(Certificate, ComplexSerializableType): 'div', 'panel-body').children)[2].strip().split('\n')[1].strip() if html_items_found['fips_lab'] == '': - logger.warning(f"WARNING: NO LAB FOUND{current_file}") + logger.warning(f"WARNING: NO LAB FOUND {current_file}") if html_items_found['fips_nvlap_code'] == '': - logger.warning(f"WARNING: NO NVLAP CODE FOUND{current_file}") + logger.warning(f"WARNING: NO NVLAP CODE FOUND {current_file}") @staticmethod def parse_related_files(current_div: Tag, html_items_found: Dict): links = current_div.find_all('a') # TODO: break out of circular imports hell - html_items_found['fips_security_policy_www'] = __import__( - 'sec_certs').certificate.FIPSCertificate.FIPS_BASE_URL + links[0].get('href') + html_items_found['fips_security_policy_www'] = dataset.FIPSDataset.FIPS_BASE_URL + links[0].get('href') if len(links) == 2: - html_items_found['fips_certificate_www'] = __import__( - 'sec_certs').certificate.FIPSCertificate.FIPS_BASE_URL + links[1].get('href') + html_items_found['fips_certificate_www'] = dataset.FIPSDataset.FIPS_BASE_URL + links[1].get('href') @classmethod def html_from_file(cls, file: Path) -> 'FIPSCertificate': diff --git a/sec_certs/dataset.py b/sec_certs/dataset.py index 3f9a4f88..b35adf2f 100644 --- a/sec_certs/dataset.py +++ b/sec_certs/dataset.py @@ -518,6 +518,8 @@ class FIPSDataset(Dataset, ComplexSerializableType): not_available.append(i) return missing, not_available +# TODO: make this work for single certs object instead of the whole dataset, making it parallelizable +# TODO: make this not create a whole new json - that way continuous processing can be done def extract_keywords(self): self.fragments_dir.mkdir(parents=True, exist_ok=True) if self.new_files > 0 or not (self.root_dir / 'fips_full_keywords.json').exists(): |