Init CBZ Volume Combiner v0.2.0

cbz_volume_combiner/parsing.py

@@ -0,0 +1,71 @@
+# File: /home/code/projects/manga-organizer-1/cbz-volume-combiner/cbz_volume_combiner/parsing.py
+import os
+import re
+
+def normalize_filename(filename):
+    """Normalize a filename to handle encoding issues and special characters."""
+    # Replace common problematic characters
+    replacements = {
+        '?': "'",  # Replace question marks that might be incorrectly encoded apostrophes
+        '?': "'",  # Another possible encoding of apostrophe
+        '?': '"',  # Possible encoding of double quote
+        '?': '-',  # Possible encoding of dash
+        '?': ' '   # Possible encoding of space
+    }
+    
+    for bad_char, good_char in replacements.items():
+        filename = filename.replace(bad_char, good_char)
+        
+    return filename
+
+def parse_manga_filename(filename):
+    """Extract volume, chapter and title information from a manga filename."""
+    # Pattern to match: manga_name v## c### [optional title] [optional group]
+    base_filename = os.path.basename(filename)
+    
+    # Try to normalize the filename to handle encoding issues
+    normalized_filename = normalize_filename(base_filename)
+    
+    # Use a more flexible pattern to handle apostrophes and other special characters
+    pattern = r'(.*?)\s+v(\d+)\s+c(\d+[.\d-]*)\s+(.*)\.cbz$'
+    match = re.match(pattern, normalized_filename)
+    
+    if match:
+        manga_name = match.group(1).strip()
+        volume = int(match.group(2))
+        chapter_str = match.group(3)
+        rest = match.group(4)
+        
+        # Try to extract title and group if available
+        group_match = re.search(r'\[(.*?)\]$', rest)
+        if group_match:
+            group = group_match.group(1)
+            title = rest[:rest.rfind('[')-1].strip()
+        else:
+            group = ""
+            title = rest.strip()
+        
+        # Handle chapter numbers like "005.5" or "005-006"
+        try:
+            chapter = float(chapter_str)
+        except ValueError:
+            try:
+                chapter = float(chapter_str.split('-')[0])  # Take first number for ranges
+            except ValueError:
+                chapter = 0  # Fallback for unparseable chapter numbers
+        
+        return {
+            'manga_name': manga_name,
+            'volume': volume,
+            'chapter': chapter,
+            'chapter_str': chapter_str,
+            'title': title,
+            'group': group,
+            'filename': filename
+        }
+    
+    if os.path.exists(filename):
+        # For debugging: print the filename that couldn't be parsed
+        print(f"WARNING: Could not parse filename: {base_filename}")
+    
+    return None