Rename and streamline get_rule_object_from_match

Signed-off-by: Philippe Ombredanne <pombredanne@nexb.com>

Author: pombredanne

src/licensedcode/detection.py

@@ -29,7 +29,7 @@
 from licensedcode.models import UnDetectedRule
 from licensedcode.models import BasicRule
 from licensedcode.models import compute_relevance
-from licensedcode.models import get_rule_object_from_match
+from licensedcode.models import get_license_rule_from_match
 from licensedcode.spans import Span
 from licensedcode.tokenize import query_tokenizer
 from licensedcode.query import Query
@@ -627,7 +627,7 @@ def matches_from_license_match_mappings(license_match_mappings):
     license_matches = []
 
     for license_match_mapping in license_match_mappings:
-        rule = get_rule_object_from_match(license_match_mapping)
+        rule = get_license_rule_from_match(license_match_mapping)
         license_rule_reference = rule.get_reference_data()
         license_matches.append(
             LicenseMatchFromResult.from_license_match_mapping(

src/licensedcode/licenses_reference.py

@@ -11,7 +11,7 @@
 import logging
 from license_expression import Licensing
 
-from licensedcode.models import get_rule_object_from_match
+from licensedcode.models import get_license_rule_from_match
 
 
 TRACE_REFERENCE = os.environ.get('SCANCODE_DEBUG_LICENSE_REFERENCE', False)
@@ -281,22 +281,19 @@ def get_reference_data(match):
     Get reference data from a LicenseMatch mapping `match` after rehydrating.
     """
 
-    rule = get_rule_object_from_match(license_match=match)
+    rule = get_license_rule_from_match(license_match=match)
 
     ref_data = {}
     ref_data['rule_identifier'] = match['rule_identifier']
     ref_data['license_expression'] = match['license_expression']
     ref_data['rule_url'] = rule.rule_url
-    ref_data['rule_relevance'] = match.pop('rule_relevance')
-    ref_data['rule_length'] = match.pop('rule_length')
-    ref_data['is_license_text'] = match.pop('is_license_text')
-    ref_data['is_license_notice'] = match.pop('is_license_notice')
-    ref_data['is_license_reference'] = match.pop('is_license_reference')
-    ref_data['is_license_tag'] = match.pop('is_license_tag')
-    ref_data['is_license_intro'] = match.pop('is_license_intro')
-    ref_data['referenced_filenames'] = match.pop('referenced_filenames')
+    ref_data['rule_relevance'] = match.get('rule_relevance')
+    ref_data['rule_length'] = match.get('rule_length')
+    ref_data['is_license_text'] = match.get('is_license_text')
+    ref_data['is_license_notice'] = match.get('is_license_notice')
+    ref_data['is_license_reference'] = match.get('is_license_reference')
+    ref_data['is_license_tag'] = match.get('is_license_tag')
+    ref_data['is_license_intro'] = match.get('is_license_intro')
+    ref_data['referenced_filenames'] = match.get('referenced_filenames')
     ref_data['rule_text'] = rule.text
-
-    _ = match.pop('licenses')
-
     return ref_data

src/licensedcode/models.py

@@ -2179,7 +2179,7 @@ def set_relevance(self):
             self.relevance = computed_relevance
 
 
-def get_rule_object_from_match(license_match):
+def get_license_rule_from_match(license_match):
     """
     Return a rehydrated Rule object from a `license_match`
     LicenseMatch mapping.
@@ -2190,18 +2190,20 @@ def get_rule_object_from_match(license_match):
         "license-detection-unknown": UnknownRule,
         "package-manifest": UnDetectedRule,
     }
-
+    
+    prefixes = tuple(rule_subclass_by_identifier_prefix.keys())
     rule_identifier = license_match["rule_identifier"]
-    for prefix, cls in rule_subclass_by_identifier_prefix.items():
-        if rule_identifier.startswith(prefix):
-            return cls(
-                license_expression=license_match["license_expression"],
-                text=license_match.get("matched_text", None),
-                length=license_match["matched_length"],
-            )
-
-    from licensedcode.cache import get_index
-    return get_index().rules_by_id[rule_identifier]
+    if rule_identifier.startswith(prefixes):
+        for prefix, cls in rule_subclass_by_identifier_prefix.items():
+            if rule_identifier.startswith(prefix):
+                return cls(
+                    license_expression=license_match["license_expression"],
+                    text=license_match.get("matched_text", None),
+                    length=license_match["matched_length"],
+                )
+    else:
+        from licensedcode.cache import get_index
+        return get_index().rules_by_id[rule_identifier]
 
 
 def compute_relevance(length):