extended filtering on MatchingResult

README.md

@@ -117,6 +117,7 @@ in IDA.
 
 
 ## Version History
+ * 2023-06-06 v1.0.7: Extended filtering capabilities on MatchingResult.
  * 2023-06-02 v1.0.6: IDA plugin can now task matching jobs, show their results and batch import labels. Harmonization of MatchingResult.
  * 2023-05-22 v1.0.3: More robustness for path verification when using MCRIT CLI on Malpedia repo folder.
  * 2023-05-12 v1.0.1: Some progress on label import for the IDA plugin. Reflected API extension of MCRITweb in McritClient.

mcrit/config/McritConfig.py

@@ -10,7 +10,7 @@
 class McritConfig(object):
 
     # NOTE to self: always change this in setup.py as well!
-    VERSION = "1.0.6"
+    VERSION = "1.0.7"
     CONFIG_FILE_PATH = str(os.path.abspath(__file__))
     PROJECT_ROOT = str(os.path.abspath(os.sep.join([CONFIG_FILE_PATH, "..", ".."])))
 

mcrit/storage/MatchingResult.py

@@ -93,6 +93,8 @@ def applyFilterValues(self):
             self.filterToUniqueMatchesOnly()
         if self.filter_values.get("filter_exclude_own_family", None):
             self.excludeOwnFamily()
+        if self.filter_values.get("filter_family_name", None):
+            self.filterByFamilyName(self.filter_values["filter_family_name"])
         # filter functions
         if self.filter_values.get("filter_exclude_library", None):
             self.excludeLibraryMatches()
@@ -104,8 +106,12 @@ def applyFilterValues(self):
             self.filterToFunctionScore(min_score=self.filter_values["filter_function_min_score"])
         if self.filter_values.get("filter_function_max_score", None):
             self.filterToFunctionScore(max_score=self.filter_values["filter_function_max_score"])
+        if self.filter_values.get("filter_function_offset", None):
+            self.filterToFunctionOffset(self.filter_values["filter_function_offset"])
         if self.filter_values.get("filter_exclude_pic", None):
             self.excludePicMatches()
+        if self.filter_values.get("filter_func_unique", None):
+            self.filterToUniqueFunctionMatchesOnly()
 
     def getFamilyNameByFamilyId(self, family_id):
         if self.family_id_to_name_map is None:
@@ -119,6 +125,14 @@ def getFamilyIdsMatchedByFunctionId(self, function_id):
             return 0
         return self.function_id_to_family_ids_matched[function_id]
 
+    def filterByFamilyName(self, filter_term):
+        """ reduce families and samples to those where family_name is part of the family_name """
+        filtered_sample_matches = []
+        for sample_match in self.filtered_sample_matches:
+            if filter_term in sample_match.family:
+                filtered_sample_matches.append(sample_match)
+        self.filtered_sample_matches = filtered_sample_matches
+
     def filterToDirectMinScore(self, min_score, nonlib=False):
         """ reduce aggregated sample matches to those with direct score of min_score or higher, but nonlib flag is not applied to library samples """
         filtered_sample_matches = []
@@ -156,6 +170,24 @@ def filterToUniqueMatchesOnly(self):
                 filtered_sample_matches.append(sample_match)
         self.filtered_sample_matches = filtered_sample_matches
 
+    def filterToUniqueFunctionMatchesOnly(self):
+        """ reduce function matches to those with unique matches (with respect to the family) only """
+        aggregated = self.getAggregatedFunctionMatches()
+        filtered_function_matches = []
+        unique_info_by_function_id = {entry["function_id"]: entry["num_families_matched"] == 1 for entry in aggregated}
+        for function_match in self.filtered_function_matches:
+            if unique_info_by_function_id[function_match.function_id]:
+                filtered_function_matches.append(function_match)
+        self.filtered_function_matches = filtered_function_matches
+
+    def filterToFunctionOffset(self, offset):
+        """ reduce function matches to those that match a specific offset """
+        filtered_function_matches = []
+        for function_match in self.filtered_function_matches:
+            if function_match.offset == offset:
+                filtered_function_matches.append(function_match)
+        self.filtered_function_matches = filtered_function_matches
+
     def excludeOwnFamily(self):
         """ remove all sample matches with the same family_id as the reference samples"""
         filtered_sample_matches = []

setup.py

@@ -23,7 +23,7 @@
 
 setup(
     name='mcrit',
-    version="1.0.6",
+    version="1.0.7",
     description='MCRIT is a framework created for simplified application of the MinHash algorithm to code similarity.',
     long_description_content_type="text/markdown",
     long_description=README,