Improve tests (#81)

* Fix Codacity warning.
Best practice: https://docs.python.org/3.8/tutorial/modules.html#importing-from-a-package

* Fixes #70

* Revert last change

* Fixes #71

* Remove deprecated methods in preparation for major release.

* Fixes #72

* Fixes #74

* Fixes #75

* Fixes #76

* Fixes #77

* Fixes #78

* Test the actual command line not the script

* Remove unused import

* Add full coverage for generate_logic_hash

* Deprecate rule rebuilding. This function needs to be reworked.
This function does not work on many rulesets and rules.

* Fix docstyle problem

* Actually fix docstring problem.

* Separate parser to function in preparation for unit testing

* Improved path

* Refactor CLI unit test. Fixes #82

* Add unit test for no error

* Fix docstring problem

* Change to multiline assert

* Use hashlib to test CLI output

* Change hash to correct

* Add both possible hashes
This is a workaround for what appears to be a bug in unittest.

* Fixes #83

* Make example executable

* This works from command line.

examples/corpus_stats.py

@@ -1,109 +1,67 @@
+"""Example script that demonstrates using plyara."""
+import argparse
 import operator
-import os
-import sys
-import codecs
 
-sys.path.insert(0, os.getcwd())
 import plyara
 
 
-if __name__ == '__main__':
+def example():
+    """Execute the example code."""
+    parser = argparse.ArgumentParser()
+    parser.add_argument('file', metavar='FILE', help='File containing YARA rules to parse.')
+    args = parser.parse_args()
+
+    print('Parsing file...')
+    with open(args.file, 'r') as fh:
+        data = fh.read()
+
+    parser = plyara.Plyara()
+    rules_dict = parser.parse_string(data)
+    print('Analyzing dictionary...')
+
+    imps = {}
+    tags = {}
+    rule_count = 0
+
+    for rule in rules_dict:
+        rule_count += 1
+
+        # Imports
+        if 'imports' in rule:
+            for imp in rule['imports']:
+                imp = imp.replace('"', '')
+                if imp in imps:
+                    imps[imp] += 1
+                else:
+                    imps[imp] = 1
+
+        # Tags
+        if 'tags' in rule:
+            for tag in rule['tags']:
+                if tag in tags:
+                    tags[tag] += 1
+                else:
+                    tags[tag] = 1
 
-  file_to_analyze = sys.argv[1]
-
-  print("...parsing file...")
-  rulesDict = plyara.Plyara().parse_string(codecs.open(file_to_analyze, encoding='utf-8').read())
-  print("...analyzing dictionary...")
-
-  authors = {}
-  imps = {}
-  meta_keys = {}
-  max_strings = []
-  max_string_len = 0
-  tags = {}
-  rule_count = 0
-
-  for rule in rulesDict:
-    rule_count += 1
-
-    #Imports
-    if 'imports' in rule:
-      for imp in rule['imports']:
-        imp = imp.replace('"','')
-        if imp in imps:
-          imps[imp] += 1
-        else:
-          imps[imp] = 1
-
-    #Tags
-    if 'tags' in rule:
-      for tag in rule['tags']:
-        if tag in tags:
-          tags[tag] += 1
-        else:
-          tags[tag] = 1
-
-    #Metadata
-    if 'metadata' in rule:
-      for key in rule['metadata']:
-        if key in meta_keys:
-          meta_keys[key] += 1
-        else:
-          meta_keys[key] = 1
-        if key in ['Author', 'author']:
-          if rule['metadata'][key] in authors:
-            authors[rule['metadata'][key]] += 1
-          else:
-            authors[rule['metadata'][key]] = 1
-
-    #Strings
-    if 'strings' in rule:
-      for strr in rule['strings']:
-        if len(strr['value']) > max_string_len:
-          max_string_len = len(strr['value'])
-          max_strings = [(rule['rule_name'], strr['name'], strr['value'])]
-        elif len(strr['value']) == max_string_len:
-          max_strings.append((rule['rule_name'], strr['key'], strr['value']))
-
-
-
-  print("\nNumber of rules in file: " + str(rule_count))
-
-  ordered_meta_keys = sorted(meta_keys.items(),
-                               key=operator.itemgetter(1), reverse=True)
-
-  ordered_authors = sorted(authors.items(),
-                           key=operator.itemgetter(1), reverse=True)
-
-  ordered_imps = sorted(imps.items(),
-                           key=operator.itemgetter(1), reverse=True)
-
-  ordered_tags = sorted(tags.items(),
-                           key=operator.itemgetter(1), reverse=True)
-
-  print("\nTop 5 metadata keys:")
-  for i in range(5):
-    if i < len(ordered_meta_keys):
-      print(ordered_meta_keys[i])
-
-  print("\nTop 5 authors based on parsed metadata:")
-  for i in range(5):
-    if i < len(ordered_authors):
-      print(ordered_authors[i])
-
-  print('\nLongest string(s): ')
-  for s in max_strings:
-    print('string named "' + s[1] +'" in rule "'+ s[0]
-          + '" with length ' + str(max_string_len) + '.')
-
-  print("\nTop imports: ")
-  for i in range(5):
-    if i < len(ordered_imps):
-      print(ordered_imps[i])
-
-  print("\nTop tags")
-  for i in range(5):
-    if i < len(ordered_tags):
-      print(ordered_tags[i])
-
-  print("\n")
+    print('\n======================\n')
+    print('Number of rules in file: {}'.format(rule_count))
+
+    ordered_imps = sorted(imps.items(), key=operator.itemgetter(1), reverse=True)
+
+    ordered_tags = sorted(tags.items(), key=operator.itemgetter(1), reverse=True)
+
+    print('\n======================\n')
+    print('Top imports:')
+    for i in range(5):
+        if i < len(ordered_imps):
+            print(ordered_imps[i])
+
+    print('\n======================\n')
+    print('Top tags:')
+    for i in range(5):
+        if i < len(ordered_tags):
+            print(ordered_tags[i])
+
+
+if __name__ == '__main__':
+    example()

plyara/__init__.py

@@ -13,4 +13,5 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-from plyara.core import Plyara
+__all__ = ['Plyara']
+from plyara.core import *

plyara/command_line.py

@@ -23,12 +23,15 @@
 from plyara.core import Plyara
 
 
-def main():
+def main(arguments=None):
     """Run the command line process to parse a yara rule file and output pretty printed JSON."""
     parser = argparse.ArgumentParser(description='Parse YARA rules into a dictionary representation.')
     parser.add_argument('file', metavar='FILE', help='File containing YARA rules to parse.')
     parser.add_argument('--log', help='Enable debug logging to the console.', action='store_true')
-    args = parser.parse_args()
+    if not arguments:
+        args = parser.parse_args()
+    else:
+        args = parser.parse_args(arguments)
 
     with open(args.file, 'r', encoding='utf-8') as fh:
         input_string = fh.read()