Improve filename parsing

comicapi/filenamelexer.py

@@ -6,6 +6,7 @@ import calendar
 import os
 import unicodedata
 from enum import Enum, auto
+from itertools import chain
 from typing import Any, Callable, Protocol
 
 
@@ -307,21 +308,20 @@ def lex_text(lex: Lexer) -> LexerFunc:
         if is_alpha_numeric(r):
             if r.isnumeric():  # E.g. v1
                 word = lex.input[lex.start : lex.pos]
-                if word.casefold() in key and key[word.casefold()] == ItemType.InfoSpecifier:
+                if key.get(word.casefold(), None) == ItemType.InfoSpecifier:
                     lex.backup()
                     lex.emit(key[word.casefold()])
                     return lex_filename
         else:
-            if r == "'" and lex.peek() == "s":
+            if r == "'" and lex.peek().casefold() == "s":
                 lex.get()
             else:
                 lex.backup()
             word = lex.input[lex.start : lex.pos + 1]
-            if word.casefold() == "vol" and lex.peek() == ".":
-                lex.get()
-            word = lex.input[lex.start : lex.pos + 1]
 
             if word.casefold() in key:
+                if key[word.casefold()] in (ItemType.Honorific, ItemType.InfoSpecifier):
+                    lex.accept(".")
                 lex.emit(key[word.casefold()])
             elif cal(word):
                 lex.emit(ItemType.Calendar)
@@ -332,12 +332,8 @@ def lex_text(lex: Lexer) -> LexerFunc:
     return lex_filename
 
 
-def cal(value: str) -> set[Any]:
-    month_abbr = [i for i, x in enumerate(calendar.month_abbr) if x == value.title()]
-    month_name = [i for i, x in enumerate(calendar.month_name) if x == value.title()]
-    day_abbr = [i for i, x in enumerate(calendar.day_abbr) if x == value.title()]
-    day_name = [i for i, x in enumerate(calendar.day_name) if x == value.title()]
-    return set(month_abbr + month_name + day_abbr + day_name)
+def cal(value: str) -> bool:
+    return value.title() in set(chain(calendar.month_abbr, calendar.month_name, calendar.day_abbr, calendar.day_name))
 
 
 def lex_number(lex: Lexer) -> LexerFunc | None:

comicapi/filenameparser.py

@@ -417,10 +417,14 @@ class Parser:
             self.remove_from_remainder.append(filenamelexer.ItemType.FCBD)
 
         self.input = lexer_result
-        for i, item in enumerate(self.input):
+        self.error = None
+        for i, item in list(enumerate(self.input)):
             if item.typ == filenamelexer.ItemType.IssueNumber:
                 self.issue_number_at = i
                 self.issue_number_marked = True
+            if item.typ == filenamelexer.ItemType.Error:
+                self.error = item
+                self.input.remove(self.error)
 
     # Get returns the next Item in the input.
     def get(self) -> filenamelexer.Item:
@@ -1043,10 +1047,9 @@ def parse_finish(p: Parser) -> None:
             if item in p.title_parts:
                 p.title_parts.remove(item)
 
+    p.filename_info["series"] = p.filename_info.get("issue", "")
     if p.series_parts:
         p.filename_info["series"] = join_title(p.series_parts)
-    else:
-        p.filename_info["series"] = p.filename_info.get("issue", "")
 
     if "free comic book" in p.filename_info["series"].casefold():
         p.filename_info["fcbd"] = True
@@ -1092,7 +1095,6 @@ def get_remainder(p: Parser) -> str:
         elif (
             item.typ
             in [
-                filenamelexer.ItemType.Space,
                 filenamelexer.ItemType.RightBrace,
                 filenamelexer.ItemType.RightParen,
                 filenamelexer.ItemType.RightSBrace,
@@ -1111,7 +1113,7 @@ def get_remainder(p: Parser) -> str:
 
     # Remove empty parentheses
     remainder = re.sub(r"[\[{(]+[]})]+", "", remainder)
-    return remainder.strip()
+    return remainder.strip().rstrip("[{(")
 
 
 def parse_info_specifier(p: Parser) -> ParserFunc:

comicapi/utils.py

@@ -162,6 +162,8 @@ def parse_filename(
             remove_publisher=remove_publisher,
             protofolius_issue_number_scheme=protofolius_issue_number_scheme,
         )
+        if p.error:
+            logger.info("Issue parsing filename: '%s': %s ", filename, p.error.val)
         fni = p.filename_info
     elif parser == Parser.COMICFN2DICT:
         fn2d = comicfn2dict(filename)

testing/filenames.py

@@ -74,7 +74,7 @@ names: list[tuple[str, str, dict[str, str | bool], tuple[bool, bool]]] = [
     ),
     (
         "Michel Vaillant #5 Nr. 13 aan de start",
-        "Shortened word followed by a number eg No. 13, Mr. 13",
+        "Shortened word followed by a number eg No. 13, Nr. 13",
         {
             "issue": "5",
             "series": "Michel Vaillant",
@@ -276,6 +276,23 @@ names: list[tuple[str, str, dict[str, str | bool], tuple[bool, bool]]] = [
         },
         (False, True),
     ),
+    (
+        "batman #3 title (DC.cbz",
+        "publisher in title",
+        {
+            "archive": "cbz",
+            "issue": "3",
+            "series": "batman",
+            "title": "title",
+            "publisher": "DC",
+            "volume": "",
+            "year": "",
+            "remainder": "",
+            "issue_count": "",
+            "alternate": "",
+        },
+        (False, True),
+    ),
     (
         "ms. Marvel #3.cbz",
         "honorific and publisher in series",
@@ -293,6 +310,23 @@ names: list[tuple[str, str, dict[str, str | bool], tuple[bool, bool]]] = [
         },
         (False, False),
     ),
+    (
+        "Dr. Doom And The Masters Of Evil #1 (2009).cbz",
+        "honorific and publisher in series",
+        {
+            "archive": "cbz",
+            "issue": "1",
+            "series": "Dr. Doom And The Masters Of Evil",
+            "title": "",
+            "publisher": "",
+            "volume": "",
+            "year": "2009",
+            "remainder": "",
+            "issue_count": "",
+            "alternate": "",
+        },
+        (False, False),
+    ),
     (
         f"action comics #{datetime.datetime.now().year}.cbz",
         "issue number is current year (digits == 4)",