Add webrip info type, fix test for Worlds Finest

comicfn2dict/regex.py

@@ -35,7 +35,7 @@ ORIGINAL_FORMAT_PATTERNS = (
     r"Sketch",
     r"TPB",
     r"Trade[-\s]Paper[-\s]?Back",
-    r"Web([-\s]?Comic)?",
+    r"Web([-\s]?(Comic|Rip))?",
 )
 
 
@@ -51,7 +51,7 @@ YEAR_BEGIN_RE = re_compile(r"^" + _YEAR_RE_EXP + r"\b")
 YEAR_END_RE = re_compile(r"\b" + _YEAR_RE_EXP + r"$")
 _OF_PATTERNS = r"|".join(ORIGINAL_FORMAT_PATTERNS)
 _ORIGINAL_FORMAT_RE_EXP = r"(?P<original_format>" + _OF_PATTERNS + r")"
-_SCAN_INFO_RE_EXP = r"(?P<scan_info>[^()]+?)"
+_SCAN_INFO_RE_EXP = r"(?P<scan_info>[^()]*)"
 _ORIGINAL_FORMAT_SCAN_INFO_RE_EXP = (
     _ORIGINAL_FORMAT_RE_EXP + r"\s*[\(:-]" + _SCAN_INFO_RE_EXP  # + r")?"
 )
@@ -70,8 +70,6 @@ _ISSUE_RE_EXP = r"(?P<issue>[\d½]+\.?\d*\w*)"
 
 ISSUE_END_RE = re_compile(r"([\/\s]" + _ISSUE_RE_EXP + r"(\/|$))")
 ISSUE_BEGIN_RE = re_compile(r"((^|\/)" + _ISSUE_RE_EXP + r"[\/|\s])")
-
-# TODO is this used?
 ISSUE_ANYWHERE_RE = re_compile(r"\b(" + _ISSUE_RE_EXP + r")\b")
 
 # LONG STRINGS

tests/comic_filenames.py

@@ -246,9 +246,9 @@ FNS.update(  # Newly fixed.
         "'Batman - Superman - World's Finest 022 (2024) (Webrip) (The Last Kryptonian-DCP).cbz": {
             "ext": "cbz",
             "issue": "022",
-            "remainders": ("(The Last Kryptonian-DCP)",),
-            "scan_info": "Webrip",
+            "original_format": "Webrip",
             "series": "Batman - Superman - World's Finest",
+            "scan_info": "The Last Kryptonian-DCP",
             "year": "2024",
         },
         # Issue number starting with a letter requested in https://github.com/comictagger/comictagger/issues/543
@@ -259,6 +259,13 @@ FNS.update(  # Newly fixed.
             "series": "batman",
             "title": "title",
         },
+        "Monster_Island_v1_#2__repaired__c2c.cbz": {
+            "ext": "cbz",
+            "issue": "2",
+            "series": "Monster Island",
+            "volume": "1",
+            "remainders": ("repaired c2c",),
+        },
     }
 )
 
@@ -292,16 +299,6 @@ LATER = {
 
 FNS.update(
     {
-        # CT treats double-underscore the same as double-dash
-        #    BUG: should be title right now.
-        #    FEATURE: double dash should be a token delimiter?
-        "Monster_Island_v1_#2__repaired__c2c.cbz": {
-            "ext": "cbz",
-            "issue": "2",
-            "series": "Monster Island",
-            "volume": "1",
-            "remainders": ("repaired c2c",),
-        },
         # I'm not sure there's a right way to parse this. This might also be a madeup filename I don't remember
         "Super Strange Yarns (1957) #92 (1969).cbz": {
             "ext": "cbz",