Initial commit

src/watfag/parsers/generic/group.py

@@ -0,0 +1,45 @@
+import regex as re
+
+from parsers.generic import GenericParser
+from parsers.generic.watfag import Group
+from parsers.generic.parsers import DataParser
+
+patterns = [
+    re.compile(r"(?:-| - )(?P<group>[a-zA-Z0-9 &]*)\)?$", re.UNICODE),
+    re.compile(r"(?: )\[?(?P<group>[a-zA-Z0-9]*?)]?\)?$", re.UNICODE)
+]
+
+invalid_group_substrs = [  # lowercase-only matches that can be any substring of a group name
+    ' hevc ',  # Can appear at end of release name while not being a group
+    ' x264 ',
+    ' x265 ',
+    ' truehd ',
+    'bluray'
+]
+invalid_groups = [  # Case sensitive full group names that are invalid
+    'MP4'
+]
+
+class GroupParser(DataParser, GenericParser):
+    """Parses the SCENE release group from the unparsed text."""
+    def parse(self) -> bool:
+        for pattern in patterns:
+            match = pattern.search(self.release.metadata_text)
+            if match:
+                if any(substr in match.group("group").lower() for substr in invalid_group_substrs):
+                    continue  # Skip this match if it contains any invalid substrings
+
+                if match.group("group").strip() in invalid_groups:
+                    continue  # Skip this match if it is in the list of invalid group names
+
+                if len(match.group("group").strip()) < 2:
+                    continue  # Skip groups that are too short to be valid
+
+                group = match.group("group").strip()
+                self.release.group = Group.from_string(group)
+                self.release.group_name = group
+
+                self.release.metadata_text = self.release.metadata_text[:match.span()[0]] + self.release.metadata_text[match.span()[1]:]
+                self.release.metadata_text = re.sub(r"\s+", " ", self.release.metadata_text).strip()  # Clean up extra spaces
+                return True
+        return False