Complicated volume parsing

comicfn2dict/parse.py

@@ -7,21 +7,23 @@ from re import Pattern
 from typing import Any
 
 from comicfn2dict.regex import (
-    NON_NUMBER_DOT_RE,
+    BOOK_VOLUME_RE,
-    YEAR_FIRST_DATE_RE,
     ISSUE_ANYWHERE_RE,
-    REGEX_SUBS,
-    TOKEN_DELIMETER,
-    ISSUE_COUNT_RE,
-    ISSUE_NUMBER_RE,
     ISSUE_BEGIN_RE,
     ISSUE_END_RE,
-    YEAR_END_RE,
+    ISSUE_NUMBER_RE,
-    ORIGINAL_FORMAT_SCAN_INFO_SEPARATE_RE,
+    ISSUE_WITH_COUNT_RE,
-    ORIGINAL_FORMAT_SCAN_INFO_RE,
-    REMAINING_GROUP_RE,
-    VOLUME_RE,
     MONTH_FIRST_DATE_RE,
+    NON_NUMBER_DOT_RE,
+    ORIGINAL_FORMAT_SCAN_INFO_RE,
+    ORIGINAL_FORMAT_SCAN_INFO_SEPARATE_RE,
+    REGEX_SUBS,
+    REMAINING_GROUP_RE,
+    TOKEN_DELIMETER,
+    VOLUME_RE,
+    VOLUME_WITH_COUNT_RE,
+    YEAR_END_RE,
+    YEAR_FIRST_DATE_RE,
     YEAR_TOKEN_RE,
 )
 
@@ -172,6 +174,8 @@ class ComicFilenameParser:
         tokens = self._unparsed_path.split(TOKEN_DELIMETER)
         while tokens and remaining_key_index < len(_REMAINING_GROUP_KEYS):
             key = _REMAINING_GROUP_KEYS[remaining_key_index]
+            if key in self.metadata:
+                continue
             token = tokens.pop(0)
             match = REMAINING_GROUP_RE.search(token)
             if match:
@@ -218,15 +222,19 @@ class ComicFilenameParser:
         self._clean_dividers()
         self._log_progress("CLEANED")
 
-        # Main issue parsing
+        # Issue
         #
         self._parse_items(ISSUE_NUMBER_RE)
-        self._parse_items(ISSUE_COUNT_RE)
+        if "issue" not in self.metadata:
+            self._parse_items(ISSUE_WITH_COUNT_RE)
+        # self._parse_items(ISSUE_COUNT_RE)
         self._log_progress("AFTER ISSUE")
 
-        # Volume and date
+        # Volume and Date
         #
         self._parse_items(VOLUME_RE)
+        if "volume" not in self.metadata:
+            self._parse_items(VOLUME_WITH_COUNT_RE)
         self._parse_dates()
         self._log_progress("AFTER VOLUME & DATE")
 
@@ -244,13 +252,17 @@ class ComicFilenameParser:
 
         # Series and Title
         #
-        # Match years on the end of series and title tokens
+        # Volume left on the end of string tokens
+        if "volume" not in self.metadata:
+            self._parse_items(BOOK_VOLUME_RE)
+
+        # Years left on the end of string tokens
         year_end_matched = False
         if "year" not in self.metadata:
             self._parse_items(YEAR_END_RE, pop=False)
             year_end_matched = "year" in self.metadata
 
-        # Pickup issue if it's out on the end of a token
+        # Issue left on the end of string tokens
         if "issue" not in self.metadata and not year_end_matched:
             exclude: str = self.metadata.get("year", "")  # type: ignore
             self._parse_items(ISSUE_END_RE, exclude=exclude)

comicfn2dict/regex.py

@@ -111,7 +111,6 @@ YEAR_TOKEN_RE = re_compile(_YEAR_RE_EXP, parenthify=True)
 YEAR_END_RE = re_compile(_YEAR_RE_EXP + r"\/|$")
 
 # PAREN GROUPS
-ISSUE_COUNT_RE = re_compile(r"of\s*(?P<issue_count>\d+)", parenthify=True)
 _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>[^()]*)"
@@ -125,18 +124,34 @@ ORIGINAL_FORMAT_SCAN_INFO_SEPARATE_RE = re_compile(
     r"\(" + _ORIGINAL_FORMAT_RE_EXP + r"\).*\(" + _SCAN_INFO_RE_EXP + r"\)"
 )
 
-# REGULAR TOKENS
-VOLUME_RE = re_compile(r"((?:v(?:ol(?:ume)?)?\.?)\s*(?P<volume>\d+))")
-
 # ISSUE
 _ISSUE_RE_EXP = r"(?P<issue>\w*(½|\d+)[\.\d+]*\w*)"
-ISSUE_NUMBER_RE = re_compile(r"(\(?#" + _ISSUE_RE_EXP + r"\)?)")
+_ISSUE_COUNT_RE_EXP = r"\(of\s*(?P<issue_count>\d+)\)"
+ISSUE_NUMBER_RE = re_compile(
+    r"(\(?#" + _ISSUE_RE_EXP + r"\)?)" + r"(\W*" + _ISSUE_COUNT_RE_EXP + r")?"
+)
+ISSUE_WITH_COUNT_RE = re_compile(
+    r"(\(?" + _ISSUE_RE_EXP + r"\)?" + r"\W*" + _ISSUE_COUNT_RE_EXP + r")"
+)
+
 ISSUE_END_RE = re_compile(r"([\/\s]\(?" + _ISSUE_RE_EXP + r"\)?(\/|$))")
 ISSUE_BEGIN_RE = re_compile(r"((^|\/)\(?" + _ISSUE_RE_EXP + r"\)?[\/|\s])")
 
 # TODO unused
 ISSUE_ANYWHERE_RE = re_compile(r"\b(\(?" + _ISSUE_RE_EXP + r"\)?)\b")
 
+# Volume
+_VOLUME_COUNT_RE_EXP = r"\(of\s*(?P<volume_count>\d+)\)"
+VOLUME_RE = re_compile(
+    r"(" + r"(?:v(?:ol(?:ume)?)?\.?)\s*(?P<volume>\d+)"
+    r"(\W*" + _VOLUME_COUNT_RE_EXP + r")?" + r")"
+)
+VOLUME_WITH_COUNT_RE = re_compile(
+    r"(\(?" + r"(?P<volume>\d+)" + r"\)?" + r"\W*" + _VOLUME_COUNT_RE_EXP + r")"
+)
+BOOK_VOLUME_RE = re_compile(r"(?P<title>" + r"book\s*(?P<volume>\d+)" + r")")
+
+
 # LONG STRINGS
 REMAINING_GROUP_RE = re_compile(r"^[^\()].*[^\)]")
 NON_NUMBER_DOT_RE = re_compile(r"(\D)\.(\D)")

tests/comic_filenames.py

@@ -397,24 +397,7 @@ FNS.update(
             "volume": "1957",
             "year": "1969",
         },
-    }
-)
-VOLUME = {
-    # CT treats book like 'v' but also adds it as the title (matches ComicVine for this particular series)
-    #
-    # Book \d  is a non-popped volume not an issue
-    "Bloodshot Book 03 (2020).cbr": {
-        "ext": "cbr",
-        "issue": "03",
-        "series": "Bloodshot",
-        "title": "Book 03",
-        "volume": "03",
-        "year": "2020",
-    },
         # CT checks for the following '(of 06)' after the '03' and marks it as the volume
-    #
-    # issue count is not popped if does not occur near issue
-    # \d (of \d) is volume & volume count if not issue
         "Elephantmen 2259 #008 - Simple Truth 03 (of 06) (2021).cbr": {
             "ext": "cbr",
             "issue": "008",
@@ -424,7 +407,17 @@ VOLUME = {
             "year": "2021",
             "volume_count": "06",
         },
-}
+        # CT treats book like 'v' but also adds it as the title (matches ComicVine for this particular series)
+        "Bloodshot Book 03 (2020).cbr": {
+            "ext": "cbr",
+            "issue": "03",
+            "series": "Bloodshot",
+            "title": "Book 03",
+            "volume": "03",
+            "year": "2020",
+        },
+    }
+)
 PUBLISHER = {
     # c2c aka "cover to cover" is fairly common and CT moves it to scan_info/remainder
     #
@@ -452,7 +445,7 @@ PUBLISHER = {
     },
 }
 
-# first_key, first_val = YEAR.popitem()
+# first_key, first_val = VOLUME.popitem()
 # FNS[first_key] = first_val
 
 WONFIX = {