Fix path building to use os.path.join.

5 files changed, 36 insertions, 37 deletions

diff --git a/sec_certs/analyze_certificates.py b/sec_certs/analyze_certificates.py
index cc0beba4..e2e0358c 100644
--- a/sec_certs/analyze_certificates.py
+++ b/sec_certs/analyze_certificates.py
@@ -1,19 +1,20 @@
 import operator
+import string
+import os
+import datetime
+import numpy as np
+import matplotlib.pyplot as plt
+
+from matplotlib.pyplot import figure
+from dateutil import parser
 from graphviz import Digraph
 from tabulate import tabulate
-import matplotlib.pyplot as plt;
 
 import sanity
+from tags_constants import *
+
 
 plt.rcdefaults()
-import numpy as np
-import matplotlib.pyplot as plt
-from matplotlib.pyplot import figure
-from dateutil import parser
-import datetime
-from tags_constants import *
-import string
-import os
 
 STOP_ON_UNEXPECTED_NUMS = False
 
diff --git a/sec_certs/download_files.py b/sec_certs/download_files.py
index a877593c..d4334b7f 100644
--- a/sec_certs/download_files.py
+++ b/sec_certs/download_files.py
@@ -1,5 +1,7 @@
 import extract_certificates
 
+import os
+
 FILE_ERRORS_STRATEGY = extract_certificates.FILE_ERRORS_STRATEGY
 
 
@@ -16,8 +18,8 @@ def generate_fips_download_script(file_name, fips_dir):
     :param file_name: name of the download file
     :param fips_dir: directory for saved files
     """
-    html_dir = fips_dir + '/html/'
-    sp_dir = fips_dir + '/security_policies/'
+    html_dir = os.path.join(fips_dir, 'html')
+    sp_dir = os.path.join(fips_dir, 'security_policies')
 
     with open(file_name, 'w', errors=FILE_ERRORS_STRATEGY) as write_file:
         # make directories for both html and security policies, scraping in one go
diff --git a/sec_certs/extract_certificates.py b/sec_certs/extract_certificates.py
index 07ff1707..ed09e41a 100644
--- a/sec_certs/extract_certificates.py
+++ b/sec_certs/extract_certificates.py
@@ -1,19 +1,19 @@
-from PyPDF2 import PdfFileReader
-
-import sanity
-from tags_constants import *
+import csv
+import json
 import re
 import os
 import operator
-from graphviz import Digraph
-import json
-import csv
 import string
 
-from analyze_certificates import is_in_dict
-from cert_rules import rules, fips_rules
 from enum import Enum
 import matplotlib.pyplot as plt
+from PyPDF2 import PdfFileReader
+from graphviz import Digraph
+
+import sanity
+from analyze_certificates import is_in_dict
+from cert_rules import rules, fips_rules
+from tags_constants import *
 
 plt.rcdefaults()
 
@@ -321,10 +321,9 @@ 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:
-        write_file.close()
         print('UnicodeDecodeError while writing file fragments back')
-
-    write_file.close()
+    finally:
+        write_file.close()
 
 
 def process_raw_header(items_found):
@@ -2408,7 +2407,7 @@ def generate_failed_download_script(base_dir):
     MIN_CORRECT_CERT_SIZE = 5000
     download_again = []
     for sub_folder in sub_folders:
-        target_dir = '{}{}{}'.format(base_dir, os.sep, sub_folder)
+        target_dir = os.path.join(base_dir, sub_folder)
         # obtain list of all downloaded pdf files and their size
         files = search_files(target_dir)
         for file_name in files:
diff --git a/sec_certs/fips_certificates.py b/sec_certs/fips_certificates.py
index 035b35ae..3f473ecd 100755
--- a/sec_certs/fips_certificates.py
+++ b/sec_certs/fips_certificates.py
@@ -2,6 +2,7 @@
 import json
 import os
 import re
+import time
 
 from graphviz import Digraph
 from PyPDF2 import PdfFileReader, utils
@@ -13,8 +14,6 @@ import extract_certificates
 from process_certificates import load_json_files
 from cert_rules import rules_fips_htmls as RE_FIPS_HTMLS
 
-import time
-
 FILE_ERRORS_STRATEGY = extract_certificates.FILE_ERRORS_STRATEGY
 FIPS_BASE_URL = 'https://csrc.nist.gov'
 FIPS_MODULE_URL = 'https://csrc.nist.gov/projects/cryptographic-module-validation-program/certificate/'
@@ -406,11 +405,11 @@ def main():
 
     for file in files_to_load:
         if not os.path.isfile(file):
-            fips_items = fips_search_html(FIPS_BASE_DIR + 'html/',
-                                          FIPS_RESULTS_DIR + 'fips_html_all.json', True)
+            fips_items = fips_search_html(os.path.join(FIPS_BASE_DIR, 'html'),
+                                          os.path.join(FIPS_RESULTS_DIR,'fips_html_all.json'), True)
             items = extract_certificates.extract_certificates_keywords(
-                FIPS_BASE_DIR + 'security_policies/',
-                FIPS_BASE_DIR + 'fragments/', 'fips', fips_items=fips_items,
+                os.path.join(FIPS_BASE_DIR, 'security_policies'),
+                os.path.join(FIPS_BASE_DIR, 'fragments'), 'fips', fips_items=fips_items,
                 should_censure_right_away=True, write_output_file=True)
             with open(FIPS_RESULTS_DIR + 'fips_data_keywords_all.json', 'w') as f:
                 f.write(json.dumps(items, indent=4, sort_keys=True))
diff --git a/sec_certs/process_certificates.py b/sec_certs/process_certificates.py
index 49c2a6d1..3612eafe 100755
--- a/sec_certs/process_certificates.py
+++ b/sec_certs/process_certificates.py
@@ -1,12 +1,10 @@
 #!/usr/bin/env python3
-import sys
+import os
+import json
 
 from extract_certificates import *
 from analyze_certificates import *
 
-import os
-import json
-
 
 def do_all_analysis(all_cert_items, filter_label):
     generate_dot_graphs(all_cert_items, filter_label)
@@ -27,7 +25,7 @@ def do_analysis_everything(all_cert_items, current_dir):
 
 
 def do_analysis_09_01_2019_archival(all_cert_items, current_dir):
-    target_folder = current_dir + '\\results_archived01092019_only\\'
+    target_folder = os.path.join(current_dir, 'results_archived01092019_only')
     if not os.path.exists(target_folder):
         os.makedirs(target_folder)
     os.chdir(target_folder)
@@ -81,11 +79,11 @@ def do_analysis_only_category(all_cert_items, current_dir, category):
 
 
 def do_analysis_only_smartcards(all_cert_items, current_dir):
-    do_analysis_only_filtered(all_cert_items, current_dir, ['csv_scan', 'cc_category'], 'ICs, Smart Cards and Smart Card-Related Devices and Systems')
+    do_analysis_only_category(all_cert_items, current_dir, 'ICs, Smart Cards and Smart Card-Related Devices and Systems')
 
 
 def do_analysis_only_operatingsystems(all_cert_items, current_dir):
-    do_analysis_only_category(all_cert_items, current_dir, ['csv_scan', 'cc_category'], 'Operating Systems')
+    do_analysis_only_category(all_cert_items, current_dir, 'Operating Systems')
 
 
 def load_json_files(files_list):