Merge pull request #15 from PiratesIRC/claude/investigate-fuzzy-matcher-bug-01R5rQiHwBMwKZfAUCcJMzKW

Claude/investigate fuzzy matcher bug 01 r5r qi hw b mw k zf au cc j mz kw

Stream-Mapparr/fuzzy_matcher.py

@@ -11,7 +11,7 @@ import logging
 from glob import glob
 
 # Version: YY.DDD.HHMM (Julian date format: Year.DayOfYear.Time)
-__version__ = "25.314.1907"
+__version__ = "25.317.1200"
 
 # Setup logging
 LOGGER = logging.getLogger("plugins.fuzzy_matcher")
@@ -213,6 +213,9 @@ class FuzzyMatcher:
         if user_ignored_tags is None:
             user_ignored_tags = []
 
+        # Store original for logging
+        original_name = name
+
         # Remove leading parenthetical prefixes like (SP2), (D1), etc.
         name = re.sub(r'^\([^\)]+\)\s*', '', name)
 
@@ -223,7 +226,8 @@ class FuzzyMatcher:
             quality_tags = {'HD', 'SD', 'FD', 'UHD', 'FHD'}
 
             # Check for 2-3 letter prefix with colon or space at start
-            prefix_match = re.match(r'^([A-Z]{2,3})[:|\s]\s*', name)
+            # Fixed regex: [:\s] instead of [:|\s] (pipe and backslash were incorrect)
+            prefix_match = re.match(r'^([A-Z]{2,3})[:\s]\s*', name)
             if prefix_match:
                 prefix = prefix_match.group(1).upper()
                 # Only remove if it's NOT a quality tag
@@ -280,7 +284,11 @@ class FuzzyMatcher:
         
         # Clean up whitespace
         name = re.sub(r'\s+', ' ', name).strip()
-        
+
+        # Log warning if normalization resulted in empty string (indicates overly aggressive stripping)
+        if not name:
+            self.logger.warning(f"normalize_name returned empty string for input: '{original_name}' (original input was stripped too aggressively)")
+
         return name
     
     def extract_tags(self, name, user_ignored_tags=None):
@@ -346,15 +354,17 @@ class FuzzyMatcher:
     def calculate_similarity(self, str1, str2):
         """
         Calculate Levenshtein distance-based similarity ratio between two strings.
-        
+
         Returns:
             Similarity ratio between 0.0 and 1.0
         """
         if len(str1) < len(str2):
             str1, str2 = str2, str1
-        
-        if len(str2) == 0:
-            return 1.0 if len(str1) == 0 else 0.0
+
+        # Empty strings should not match anything (including other empty strings)
+        # This prevents false positives when normalization strips everything
+        if len(str2) == 0 or len(str1) == 0:
+            return 0.0
         
         previous_row = list(range(len(str2) + 1))
         
@@ -429,9 +439,14 @@ class FuzzyMatcher:
         for candidate in candidate_names:
             # Normalize candidate (stream name) with Cinemax removal if requested
             candidate_normalized = self.normalize_name(candidate, user_ignored_tags, remove_cinemax=remove_cinemax)
+
+            # Skip candidates that normalize to empty or very short strings
+            if not candidate_normalized or len(candidate_normalized) < 2:
+                continue
+
             processed_candidate = self.process_string_for_matching(candidate_normalized)
             score = self.calculate_similarity(processed_query, processed_candidate)
-            
+
             if score > best_score:
                 best_score = score
                 best_match = candidate
@@ -481,6 +496,12 @@ class FuzzyMatcher:
         for candidate in candidate_names:
             # Normalize candidate (stream name) with Cinemax removal if requested
             candidate_normalized = self.normalize_name(candidate, user_ignored_tags, remove_cinemax=remove_cinemax)
+
+            # Skip candidates that normalize to empty or very short strings (< 2 chars)
+            # This prevents false positives where multiple streams all normalize to ""
+            if not candidate_normalized or len(candidate_normalized) < 2:
+                continue
+
             candidate_lower = candidate_normalized.lower()
             candidate_nospace = re.sub(r'[\s&\-]+', '', candidate_lower)
 
@@ -502,6 +523,11 @@ class FuzzyMatcher:
         for candidate in candidate_names:
             # Normalize candidate (stream name) with Cinemax removal if requested
             candidate_normalized = self.normalize_name(candidate, user_ignored_tags, remove_cinemax=remove_cinemax)
+
+            # Skip candidates that normalize to empty or very short strings
+            if not candidate_normalized or len(candidate_normalized) < 2:
+                continue
+
             candidate_lower = candidate_normalized.lower()
 
             # Check if one is a substring of the other

Stream-Mapparr/plugin.py

@@ -33,7 +33,7 @@ class Plugin:
     """Dispatcharr Stream-Mapparr Plugin"""
 
     name = "Stream-Mapparr"
-    version = "0.5.0"
+    version = "0.5.1"
     description = "🎯 Automatically add matching streams to channels based on name similarity and quality precedence with enhanced fuzzy matching"
 
     @property
@@ -149,13 +149,6 @@ class Plugin:
             },
         ]
 
-        # Add channel database section header
-        static_fields.append({
-            "id": "channel_databases_header",
-            "type": "info",
-            "label": "📚 Channel Databases",
-        })
-
         # Dynamically add channel database enable/disable fields
         try:
             databases = self._get_channel_databases()
@@ -753,7 +746,8 @@ class Plugin:
         # Remove country code prefix if requested
         if remove_country_prefix:
             quality_tags = {'HD', 'SD', 'FD', 'UHD', 'FHD'}
-            prefix_match = re.match(r'^([A-Z]{2,3})[:|\s]\s*', cleaned)
+            # Fixed regex: [:\s] instead of [:|\s] (pipe and backslash were incorrect)
+            prefix_match = re.match(r'^([A-Z]{2,3})[:\s]\s*', cleaned)
             if prefix_match:
                 prefix = prefix_match.group(1).upper()
                 if prefix not in quality_tags:
@@ -1025,6 +1019,12 @@ class Plugin:
                         ignore_geographic, ignore_misc, remove_cinemax=channel_has_max
                     )
 
+                    # Skip if either cleaned name is empty or too short (prevents false positives)
+                    if not cleaned_stream or len(cleaned_stream) < 2:
+                        continue
+                    if not cleaned_matched or len(cleaned_matched) < 2:
+                        continue
+
                     if cleaned_stream.lower() == cleaned_matched.lower():
                         matching_streams.append(stream)
 
@@ -1064,6 +1064,12 @@ class Plugin:
                     ignore_geographic, ignore_misc, remove_cinemax=channel_has_max
                 )
 
+                # Skip if either cleaned name is empty or too short (prevents false positives)
+                if not cleaned_stream_name or len(cleaned_stream_name) < 2:
+                    continue
+                if not cleaned_channel_name or len(cleaned_channel_name) < 2:
+                    continue
+
                 if cleaned_stream_name.lower() == cleaned_channel_name.lower():
                     matching_streams.append(stream)
 
@@ -1086,6 +1092,12 @@ class Plugin:
                 ignore_geographic, ignore_misc, remove_cinemax=channel_has_max
             )
 
+            # Skip if either cleaned name is empty or too short (prevents false positives)
+            if not cleaned_stream_name or len(cleaned_stream_name) < 2:
+                continue
+            if not cleaned_channel_name or len(cleaned_channel_name) < 2:
+                continue
+
             # Simple case-insensitive substring matching
             if cleaned_channel_name.lower() in cleaned_stream_name.lower() or cleaned_stream_name.lower() in cleaned_channel_name.lower():
                 matching_streams.append(stream)