After merge. Testing files still to update.

comicapi/comicarchive.py

@@ -368,7 +368,7 @@ class RarArchiver(UnknownArchiver):
 
     def __init__(self, path: pathlib.Path | str, rar_exe_path: str = "rar") -> None:
         super().__init__(path)
-        self.rar_exe_path = rar_exe_path
+        self.rar_exe_path = shutil.which(rar_exe_path) or ""
 
         # windows only, keeps the cmd.exe from popping up
         if platform.system() == "Windows":
@@ -687,7 +687,7 @@ class ComicArchive:
         self.page_count: int | None = None
         self.page_list: list[str] = []
 
-        self.rar_exe_path = rar_exe_path
+        self.rar_exe_path = shutil.which(rar_exe_path or "rar") or ""
         self.ci_xml_filename = "ComicInfo.xml"
         self.comet_default_filename = "CoMet.xml"
         self.reset_cache()
@@ -746,7 +746,12 @@ class ComicArchive:
             self.read_metadata(style)
 
     def rename(self, path: pathlib.Path | str) -> None:
-        self.path = pathlib.Path(path)
+        new_path = pathlib.Path(path).absolute()
+        if new_path == self.path:
+            return
+        os.makedirs(new_path.parent, 0o777, True)
+        shutil.move(path, new_path)
+        self.path = new_path
         self.archiver.path = pathlib.Path(path)
 
     def sevenzip_test(self) -> bool:
@@ -863,7 +868,7 @@ class ComicArchive:
 
     def get_page_name(self, index: int) -> str:
         if index is None:
-            return None
+            return ""
 
         page_list = self.get_page_name_list()
 
@@ -1148,8 +1153,8 @@ class ComicArchive:
             for n in self.archiver.get_filename_list():
                 if os.path.dirname(n) == "" and os.path.splitext(n)[1].casefold() == ".xml":
                     # read in XML file, and validate it
+                    data = ""
                     try:
-                        data = ""
                         d = self.archiver.read_file(n)
                         if d:
                             data = d.decode("utf-8")
@@ -1247,10 +1252,10 @@ class ComicArchive:
 
         return metadata
 
-    def export_as_zip(self, zipfilename: str) -> bool:
+    def export_as_zip(self, zip_filename: pathlib.Path | str) -> bool:
         if self.archive_type == self.ArchiveType.Zip:
             # nothing to do, we're already a zip
             return True
 
-        zip_archiver = ZipArchiver(zipfilename)
+        zip_archiver = ZipArchiver(zip_filename)
         return zip_archiver.copy_from_archive(self.archiver)

comicapi/comicbookinfo.py

@@ -98,13 +98,11 @@ class ComicBookInfo:
         metadata.critical_rating = utils.xlate(cbi["rating"], True)
 
         metadata.credits = cbi["credits"]
-        metadata.tags = cbi["tags"]
+        metadata.tags = set(cbi["tags"]) if cbi["tags"] is not None else set()
 
         # make sure credits and tags are at least empty lists and not None
         if metadata.credits is None:
             metadata.credits = []
-        if metadata.tags is None:
-            metadata.tags = []
 
         # need the language string to be ISO
         if metadata.language is not None:
@@ -133,7 +131,7 @@ class ComicBookInfo:
 
         cbi_container = CBIContainer(
             {
-                "appID": "ComicTagger/" + "1.0.0",
+                "appID": "ComicTagger/1.0.0",
                 "lastModified": str(datetime.now()),
                 "ComicBookInfo/1.0": {},
             }

comicapi/comicinfoxml.py

@@ -54,13 +54,11 @@ class ComicInfoXml:
         return self.convert_xml_to_metadata(tree)
 
     def string_from_metadata(self, metadata: GenericMetadata, xml: bytes = b"") -> str:
-        tree = self.convert_metadata_to_xml(self, metadata, xml)
+        tree = self.convert_metadata_to_xml(metadata, xml)
         tree_str = ET.tostring(tree.getroot(), encoding="utf-8", xml_declaration=True).decode("utf-8")
         return str(tree_str)
 
-    def convert_metadata_to_xml(
-        self, filename: ComicInfoXml, metadata: GenericMetadata, xml: bytes = b""
-    ) -> ElementTree:
+    def convert_metadata_to_xml(self, metadata: GenericMetadata, xml: bytes = b"") -> ElementTree:
 
         # shorthand for the metadata
         md = metadata
@@ -261,6 +259,8 @@ class ComicInfoXml:
                 p: dict[str, Any] = page.attrib
                 if "Image" in p:
                     p["Image"] = int(p["Image"])
+                if "DoublePage" in p:
+                    p["DoublePage"] = True if p["DoublePage"].casefold() in ("yes", "true", "1") else False
                 md.pages.append(cast(ImageMetadata, p))
 
         md.is_empty = False
@@ -268,7 +268,7 @@ class ComicInfoXml:
         return md
 
     def write_to_external_file(self, filename: str, metadata: GenericMetadata, xml: bytes = b"") -> None:
-        tree = self.convert_metadata_to_xml(self, metadata, xml)
+        tree = self.convert_metadata_to_xml(metadata, xml)
         tree.write(filename, encoding="utf-8", xml_declaration=True)
 
     def read_from_external_file(self, filename: str) -> GenericMetadata:

comicapi/filenamelexer.py

@@ -1,5 +1,5 @@
 # Extracted and mutilated from https://github.com/lordwelch/wsfmt
-# Which was extracted and mutliated from https://github.com/golang/go/tree/master/src/text/template/parse
+# Which was extracted and mutilated from https://github.com/golang/go/tree/master/src/text/template/parse
 from __future__ import annotations
 
 import calendar
@@ -138,7 +138,7 @@ class Lexer:
     # AcceptRun consumes a run of runes from the valid set.
     def accept_run(self, valid: str) -> None:
         while self.get() in valid:
-            pass
+            continue
 
         self.backup()
 

comicapi/filenameparser.py

@@ -114,7 +114,7 @@ class FileNameParser:
 
         # remove any "of NN" phrase with spaces (problem: this could break on
         # some titles)
-        filename = re.sub(r"of [\d]+", self.repl, filename)
+        filename = re.sub(r"of \d+", self.repl, filename)
 
         # we should now have a cleaned up filename version with all the words in
         # the same positions as original filename
@@ -143,7 +143,7 @@ class FileNameParser:
         # first look for a word with "#" followed by digits with optional suffix
         # this is almost certainly the issue number
         for w in reversed(word_list):
-            if re.match(r"#[-]?(([0-9]*\.[0-9]+|[0-9]+)(\w*))", w[0]):
+            if re.match(r"#-?((\d*\.\d+|\d+)(\w*))", w[0]):
                 found = True
                 break
 
@@ -151,7 +151,7 @@ class FileNameParser:
         # list
         if not found:
             w = word_list[-1]
-            if re.match(r"[-]?(([0-9]*\.[0-9]+|[0-9]+)(\w*))", w[0]):
+            if re.match(r"-?((\d*\.\d+|\d+)(\w*))", w[0]):
                 found = True
 
         # now try to look for a # followed by any characters
@@ -245,7 +245,7 @@ class FileNameParser:
         if match:
             year = match.group()
             # remove non-digits
-            year = re.sub(r"[^0-9]", "", year)
+            year = re.sub(r"\D", "", year)
         return year
 
     def get_remainder(self, filename: str, year: str, count: str, volume: str, issue_end: int) -> str:
@@ -332,7 +332,7 @@ eof = filenamelexer.Item(filenamelexer.ItemType.EOF, -1, "")
 
 
 # Extracted and mutilated from https://github.com/lordwelch/wsfmt
-# Which was extracted and mutliated from https://github.com/golang/go/tree/master/src/text/template/parse
+# Which was extracted and mutilated from https://github.com/golang/go/tree/master/src/text/template/parse
 class Parser:
     """docstring for FilenameParser"""
 

comicapi/genericmetadata.py

@@ -20,8 +20,9 @@ possible, however lossy it might be
 # limitations under the License.
 from __future__ import annotations
 
+import copy
+import dataclasses
 import logging
-from dataclasses import dataclass, field
 from typing import Any, TypedDict
 
 from comicapi import utils
@@ -65,7 +66,7 @@ class CreditMetadata(TypedDict):
     primary: bool
 
 
-@dataclass
+@dataclasses.dataclass
 class GenericMetadata:
     writer_synonyms = ["writer", "plotter", "scripter"]
     penciller_synonyms = ["artist", "penciller", "penciler", "breakdowns"]
@@ -115,9 +116,9 @@ class GenericMetadata:
     teams: str | None = None
     locations: str | None = None
 
-    credits: list[CreditMetadata] = field(default_factory=list)
-    tags: list[str] = field(default_factory=list)
-    pages: list[ImageMetadata] = field(default_factory=list)
+    credits: list[CreditMetadata] = dataclasses.field(default_factory=list)
+    tags: set[str] = dataclasses.field(default_factory=set)
+    pages: list[ImageMetadata] = dataclasses.field(default_factory=list)
 
     # Some CoMet-only items
     price: str | None = None
@@ -133,6 +134,14 @@ class GenericMetadata:
                 self.is_empty = False
                 break
 
+    def copy(self) -> GenericMetadata:
+        return copy.deepcopy(self)
+
+    def replace(self, /, **kwargs: Any) -> GenericMetadata:
+        tmp = self.copy()
+        tmp.__dict__.update(kwargs)
+        return tmp
+
     def overlay(self, new_md: GenericMetadata) -> None:
         """Overlay a metadata object on this one
 
@@ -244,7 +253,7 @@ class GenericMetadata:
 
     def add_credit(self, person: str, role: str, primary: bool = False) -> None:
 
-        credit: CreditMetadata = {"person": person, "role": role, "primary": primary}
+        credit = CreditMetadata(person=person, role=role, primary=primary)
 
         # look to see if it's not already there...
         found = False
@@ -360,91 +369,91 @@ class GenericMetadata:
             self.imprint = imprint
 
 
-md_test = GenericMetadata()
-
-md_test.is_empty = False
-md_test.tag_origin = None
-md_test.series = "Cory Doctorow's Futuristic Tales of the Here and Now"
-md_test.issue = "1"
-md_test.title = "Anda's Game"
-md_test.publisher = "IDW Publishing"
-md_test.month = 10
-md_test.year = 2007
-md_test.day = 1
-md_test.issue_count = 6
-md_test.volume = 1
-md_test.genre = "Sci-Fi"
-md_test.language = "en"
-md_test.comments = (
-    "For 12-year-old Anda, getting paid real money to kill the characters of players who were cheating"
-    " in her favorite online computer game was a win-win situation. Until she found out who was paying her,"
-    " and what those characters meant to the livelihood of children around the world."
+md_test: GenericMetadata = GenericMetadata(
+    is_empty=False,
+    tag_origin=None,
+    series="Cory Doctorow's Futuristic Tales of the Here and Now",
+    issue="1",
+    title="Anda's Game",
+    publisher="IDW Publishing",
+    month=10,
+    year=2007,
+    day=1,
+    issue_count=6,
+    volume=1,
+    genre="Sci-Fi",
+    language="en",
+    comments=(
+        "For 12-year-old Anda, getting paid real money to kill the characters of players who were cheating"
+        " in her favorite online computer game was a win-win situation. Until she found out who was paying her,"
+        " and what those characters meant to the livelihood of children around the world."
+    ),
+    volume_count=None,
+    critical_rating=3.0,
+    country=None,
+    alternate_series="Tales",
+    alternate_number="2",
+    alternate_count=7,
+    imprint="craphound.com",
+    notes="Tagged with ComicTagger 1.3.2a5 using info from Comic Vine on 2022-04-16 15:52:26. [Issue ID 140529]",
+    web_link="https://comicvine.gamespot.com/cory-doctorows-futuristic-tales-of-the-here-and-no/4000-140529/",
+    format="Series",
+    manga="No",
+    black_and_white=None,
+    page_count=24,
+    maturity_rating="Everyone 10+",
+    story_arc="Here and Now",
+    series_group="Futuristic Tales",
+    scan_info="(CC BY-NC-SA 3.0)",
+    characters="Anda",
+    teams="Fahrenheit",
+    locations="lonely  cottage ",
+    credits=[
+        CreditMetadata(primary=False, person="Dara Naraghi", role="Writer"),
+        CreditMetadata(primary=False, person="Esteve Polls", role="Penciller"),
+        CreditMetadata(primary=False, person="Esteve Polls", role="Inker"),
+        CreditMetadata(primary=False, person="Neil Uyetake", role="Letterer"),
+        CreditMetadata(primary=False, person="Sam Kieth", role="Cover"),
+        CreditMetadata(primary=False, person="Ted Adams", role="Editor"),
+    ],
+    tags=set(),
+    pages=[
+        ImageMetadata(Image=0, ImageHeight="1280", ImageSize="195977", ImageWidth="800", Type=PageType.FrontCover),
+        ImageMetadata(Image=1, ImageHeight="2039", ImageSize="611993", ImageWidth="1327"),
+        ImageMetadata(Image=2, ImageHeight="2039", ImageSize="783726", ImageWidth="1327"),
+        ImageMetadata(Image=3, ImageHeight="2039", ImageSize="679584", ImageWidth="1327"),
+        ImageMetadata(Image=4, ImageHeight="2039", ImageSize="788179", ImageWidth="1327"),
+        ImageMetadata(Image=5, ImageHeight="2039", ImageSize="864433", ImageWidth="1327"),
+        ImageMetadata(Image=6, ImageHeight="2039", ImageSize="765606", ImageWidth="1327"),
+        ImageMetadata(Image=7, ImageHeight="2039", ImageSize="876427", ImageWidth="1327"),
+        ImageMetadata(Image=8, ImageHeight="2039", ImageSize="852622", ImageWidth="1327"),
+        ImageMetadata(Image=9, ImageHeight="2039", ImageSize="800205", ImageWidth="1327"),
+        ImageMetadata(Image=10, ImageHeight="2039", ImageSize="746243", ImageWidth="1326"),
+        ImageMetadata(Image=11, ImageHeight="2039", ImageSize="718062", ImageWidth="1327"),
+        ImageMetadata(Image=12, ImageHeight="2039", ImageSize="532179", ImageWidth="1326"),
+        ImageMetadata(Image=13, ImageHeight="2039", ImageSize="686708", ImageWidth="1327"),
+        ImageMetadata(Image=14, ImageHeight="2039", ImageSize="641907", ImageWidth="1327"),
+        ImageMetadata(Image=15, ImageHeight="2039", ImageSize="805388", ImageWidth="1327"),
+        ImageMetadata(Image=16, ImageHeight="2039", ImageSize="668927", ImageWidth="1326"),
+        ImageMetadata(Image=17, ImageHeight="2039", ImageSize="710605", ImageWidth="1327"),
+        ImageMetadata(Image=18, ImageHeight="2039", ImageSize="761398", ImageWidth="1326"),
+        ImageMetadata(Image=19, ImageHeight="2039", ImageSize="743807", ImageWidth="1327"),
+        ImageMetadata(Image=20, ImageHeight="2039", ImageSize="552911", ImageWidth="1326"),
+        ImageMetadata(Image=21, ImageHeight="2039", ImageSize="556827", ImageWidth="1327"),
+        ImageMetadata(Image=22, ImageHeight="2039", ImageSize="675078", ImageWidth="1326"),
+        ImageMetadata(
+            Bookmark="Interview",
+            Image=23,
+            ImageHeight="2032",
+            ImageSize="800965",
+            ImageWidth="1338",
+            Type=PageType.Letters,
+        ),
+    ],
+    price=None,
+    is_version_of=None,
+    rights=None,
+    identifier=None,
+    last_mark=None,
+    cover_image=None,
 )
-md_test.volume_count = None
-md_test.critical_rating = 3.0
-md_test.country = None
-md_test.alternate_series = "Tales"
-md_test.alternate_number = "2"
-md_test.alternate_count = 7
-md_test.imprint = "craphound.com"
-md_test.notes = "Tagged with ComicTagger 1.3.2a5 using info from Comic Vine on 2022-04-16 15:52:26. [Issue ID 140529]"
-md_test.web_link = "https://comicvine.gamespot.com/cory-doctorows-futuristic-tales-of-the-here-and-no/4000-140529/"
-md_test.format = "Series"
-md_test.manga = "No"
-md_test.black_and_white = None
-md_test.page_count = 24
-md_test.maturity_rating = "Everyone 10+"
-md_test.story_arc = "Here and Now"
-md_test.series_group = "Futuristic Tales"
-md_test.scan_info = "(CC BY-NC-SA 3.0)"
-md_test.characters = "Anda"
-md_test.teams = "Fahrenheit"
-md_test.locations = "lonely  cottage "
-md_test.credits = [
-    CreditMetadata({"primary": False, "person": "Dara Naraghi", "role": "Writer"}),
-    CreditMetadata({"primary": False, "person": "Esteve Polls", "role": "Penciller"}),
-    CreditMetadata({"primary": False, "person": "Esteve Polls", "role": "Inker"}),
-    CreditMetadata({"primary": False, "person": "Neil Uyetake", "role": "Letterer"}),
-    CreditMetadata({"primary": False, "person": "Sam Kieth", "role": "Cover"}),
-    CreditMetadata({"primary": False, "person": "Ted Adams", "role": "Editor"}),
-]
-md_test.tags = []
-md_test.pages = [
-    {"Image": 0, "ImageHeight": "1280", "ImageSize": "195977", "ImageWidth": "800", "Type": PageType.FrontCover},
-    {"Image": 1, "ImageHeight": "2039", "ImageSize": "611993", "ImageWidth": "1327"},
-    {"Image": 2, "ImageHeight": "2039", "ImageSize": "783726", "ImageWidth": "1327"},
-    {"Image": 3, "ImageHeight": "2039", "ImageSize": "679584", "ImageWidth": "1327"},
-    {"Image": 4, "ImageHeight": "2039", "ImageSize": "788179", "ImageWidth": "1327"},
-    {"Image": 5, "ImageHeight": "2039", "ImageSize": "864433", "ImageWidth": "1327"},
-    {"Image": 6, "ImageHeight": "2039", "ImageSize": "765606", "ImageWidth": "1327"},
-    {"Image": 7, "ImageHeight": "2039", "ImageSize": "876427", "ImageWidth": "1327"},
-    {"Image": 8, "ImageHeight": "2039", "ImageSize": "852622", "ImageWidth": "1327"},
-    {"Image": 9, "ImageHeight": "2039", "ImageSize": "800205", "ImageWidth": "1327"},
-    {"Image": 10, "ImageHeight": "2039", "ImageSize": "746243", "ImageWidth": "1326"},
-    {"Image": 11, "ImageHeight": "2039", "ImageSize": "718062", "ImageWidth": "1327"},
-    {"Image": 12, "ImageHeight": "2039", "ImageSize": "532179", "ImageWidth": "1326"},
-    {"Image": 13, "ImageHeight": "2039", "ImageSize": "686708", "ImageWidth": "1327"},
-    {"Image": 14, "ImageHeight": "2039", "ImageSize": "641907", "ImageWidth": "1327"},
-    {"Image": 15, "ImageHeight": "2039", "ImageSize": "805388", "ImageWidth": "1327"},
-    {"Image": 16, "ImageHeight": "2039", "ImageSize": "668927", "ImageWidth": "1326"},
-    {"Image": 17, "ImageHeight": "2039", "ImageSize": "710605", "ImageWidth": "1327"},
-    {"Image": 18, "ImageHeight": "2039", "ImageSize": "761398", "ImageWidth": "1326"},
-    {"Image": 19, "ImageHeight": "2039", "ImageSize": "743807", "ImageWidth": "1327"},
-    {"Image": 20, "ImageHeight": "2039", "ImageSize": "552911", "ImageWidth": "1326"},
-    {"Image": 21, "ImageHeight": "2039", "ImageSize": "556827", "ImageWidth": "1327"},
-    {"Image": 22, "ImageHeight": "2039", "ImageSize": "675078", "ImageWidth": "1326"},
-    {
-        "Bookmark": "Interview",
-        "Image": 23,
-        "ImageHeight": "2032",
-        "ImageSize": "800965",
-        "ImageWidth": "1338",
-        "Type": PageType.Letters,
-    },
-]
-md_test.price = None
-md_test.is_version_of = None
-md_test.rights = None
-md_test.identifier = None
-md_test.last_mark = None
-md_test.cover_image = None

comicapi/issuestring.py

@@ -113,6 +113,4 @@ class IssueString:
         # return the float, with no suffix
         if len(self.suffix) == 1 and self.suffix.isnumeric():
             return (self.num or 0) + unicodedata.numeric(self.suffix)
-
-            return 0.5
         return self.num

comicapi/utils.py

@@ -26,6 +26,7 @@ from shutil import which  # noqa: F401
 from typing import Any, Mapping
 
 import pycountry
+import thefuzz.fuzz
 
 logger = logging.getLogger(__name__)
 
@@ -108,6 +109,10 @@ def remove_articles(text: str) -> str:
         "the",
         "the",
         "with",
+        "ms",
+        "mrs",
+        "mr",
+        "dr",
     ]
     new_text = ""
     for word in text.split(" "):
@@ -121,26 +126,48 @@ def remove_articles(text: str) -> str:
 
 def sanitize_title(text: str, basic: bool = False) -> str:
     # normalize unicode and convert to ascii. Does not work for everything eg ½ to 1⁄2 not 1/2
-    text = unicodedata.normalize("NFKD", text)
-    # comicvine keeps apostrophes a part of the word
-    text = text.replace("'", "")
-    text = text.replace('"', "")
-    if not basic:
-        # comicvine ignores punctuation and accents, TODO: only remove punctuation accents and similar
-        text = re.sub(r"[^A-Za-z0-9]+", " ", text)
+    text = unicodedata.normalize("NFKD", text).casefold()
+    if basic:
+        # comicvine keeps apostrophes a part of the word
+        text = text.replace("'", "")
+        text = text.replace('"', "")
+    else:
+        # comicvine ignores punctuation and accents
+        # remove all characters that are not a letter, separator (space) or number
+        # replace any "dash punctuation" with a space
+        # makes sure that batman-superman and self-proclaimed stay separate words
+        text = "".join(
+            c if not unicodedata.category(c) in ("Pd",) else " "
+            for c in text
+            if unicodedata.category(c)[0] in "LZN" or unicodedata.category(c) in ("Pd",)
+        )
         # remove extra space and articles and all lower case
-        text = remove_articles(text).casefold().strip()
+        text = remove_articles(text).strip()
 
     return text
 
 
-def unique_file(file_name: str) -> str:
+def titles_match(search_title: str, record_title: str, threshold: int = 90) -> int:
+    sanitized_search = sanitize_title(search_title)
+    sanitized_record = sanitize_title(record_title)
+    ratio = thefuzz.fuzz.ratio(sanitized_search, sanitized_record)
+    logger.debug(
+        "search title: %s ; record title: %s ; ratio: %d ; match threshold: %d",
+        search_title,
+        record_title,
+        ratio,
+        threshold,
+    )
+    return ratio >= threshold
+
+
+def unique_file(file_name: pathlib.Path) -> pathlib.Path:
+    name = file_name.name
     counter = 1
-    file_name_parts = os.path.splitext(file_name)
     while True:
-        if not os.path.lexists(file_name):
+        if not file_name.exists():
             return file_name
-        file_name = file_name_parts[0] + " (" + str(counter) + ")" + file_name_parts[1]
+        file_name = file_name.with_name(name + " (" + str(counter) + ")")
         counter += 1
 
 
@@ -204,7 +231,7 @@ class ImprintDict(dict):
     if the key does not exist the key is returned as the publisher unchanged
     """
 
-    def __init__(self, publisher: str, mapping=(), **kwargs) -> None:
+    def __init__(self, publisher: str, mapping: tuple | Mapping = (), **kwargs: dict) -> None:
         super().__init__(mapping, **kwargs)
         self.publisher = publisher
 

comictaggerlib/applicationlogwindow.py

@@ -12,18 +12,18 @@ logger = logging.getLogger(__name__)
 class QTextEditLogger(QtCore.QObject, logging.Handler):
     qlog = QtCore.pyqtSignal(str)
 
-    def __init__(self, formatter: logging.Formatter, level: int):
+    def __init__(self, formatter: logging.Formatter, level: int) -> None:
         super().__init__()
         self.setFormatter(formatter)
         self.setLevel(level)
 
-    def emit(self, record):
+    def emit(self, record: logging.LogRecord) -> None:
         msg = self.format(record)
         self.qlog.emit(msg.strip())
 
 
 class ApplicationLogWindow(QtWidgets.QDialog):
-    def __init__(self, log_handler: QTextEditLogger, parent=None):
+    def __init__(self, log_handler: QTextEditLogger, parent: QtCore.QObject = None) -> None:
         super().__init__(parent)
         uic.loadUi(ComicTaggerSettings.get_ui_file("logwindow.ui"), self)
 
@@ -43,7 +43,7 @@ class ApplicationLogWindow(QtWidgets.QDialog):
         self._button.clicked.connect(self.test)
         self.textEdit.setTabStopDistance(self.textEdit.tabStopDistance() * 2)
 
-    def test(self):
+    def test(self) -> None:
         logger.debug("damn, a bug")
         logger.info("something to remember")
         logger.warning("that's not right")

comictaggerlib/autotagstartwindow.py

@@ -17,7 +17,7 @@ from __future__ import annotations
 
 import logging
 
-from PyQt5 import QtCore, QtGui, QtWidgets, uic
+from PyQt5 import QtCore, QtWidgets, uic
 
 from comictaggerlib.settings import ComicTaggerSettings
 
@@ -39,7 +39,7 @@ class AutoTagStartWindow(QtWidgets.QDialog):
 
         self.cbxSpecifySearchString.setChecked(False)
         self.cbxSplitWords.setChecked(False)
-        self.leNameLengthMatchTolerance.setText(str(self.settings.id_length_delta_thresh))
+        self.sbNameMatchSearchThresh.setValue(self.settings.id_series_match_identify_thresh)
         self.leSearchString.setEnabled(False)
 
         self.cbxSaveOnLowConfidence.setChecked(self.settings.save_on_low_confidence)
@@ -49,13 +49,12 @@ class AutoTagStartWindow(QtWidgets.QDialog):
         self.cbxRemoveAfterSuccess.setChecked(self.settings.remove_archive_after_successful_match)
         self.cbxAutoImprint.setChecked(self.settings.auto_imprint)
 
-        nlmt_tip = """ <html>The <b>Name Length Match Tolerance</b> is for eliminating automatic
-                search matches that are too long compared to your series name search. The higher
+        nlmt_tip = """<html>The <b>Name Match Ratio Threshold: Auto-Identify</b> is for eliminating automatic
+                search matches that are too long compared to your series name search. The lower
                 it is, the more likely to have a good match, but each search will take longer and
-                use more bandwidth. Too low, and only the very closest lexical matches will be
-                explored.</html>"""
+                use more bandwidth. Too high, and only the very closest matches will be explored.</html>"""
 
-        self.leNameLengthMatchTolerance.setToolTip(nlmt_tip)
+        self.sbNameMatchSearchThresh.setToolTip(nlmt_tip)
 
         ss_tip = """<html>
             The <b>series search string</b> specifies the search string to be used for all selected archives.
@@ -65,9 +64,6 @@ class AutoTagStartWindow(QtWidgets.QDialog):
         self.leSearchString.setToolTip(ss_tip)
         self.cbxSpecifySearchString.setToolTip(ss_tip)
 
-        validator = QtGui.QIntValidator(0, 99, self)
-        self.leNameLengthMatchTolerance.setValidator(validator)
-
         self.cbxSpecifySearchString.stateChanged.connect(self.search_string_toggle)
 
         self.auto_save_on_low = False
@@ -76,7 +72,7 @@ class AutoTagStartWindow(QtWidgets.QDialog):
         self.ignore_leading_digits_in_filename = False
         self.remove_after_success = False
         self.search_string = ""
-        self.name_length_match_tolerance = self.settings.id_length_delta_thresh
+        self.name_length_match_tolerance = self.settings.id_series_match_search_thresh
         self.split_words = self.cbxSplitWords.isChecked()
 
     def search_string_toggle(self) -> None:
@@ -91,7 +87,7 @@ class AutoTagStartWindow(QtWidgets.QDialog):
         self.assume_issue_one = self.cbxAssumeIssueOne.isChecked()
         self.ignore_leading_digits_in_filename = self.cbxIgnoreLeadingDigitsInFilename.isChecked()
         self.remove_after_success = self.cbxRemoveAfterSuccess.isChecked()
-        self.name_length_match_tolerance = int(self.leNameLengthMatchTolerance.text())
+        self.name_length_match_tolerance = int(self.leNameMatchThresh.text())
         self.split_words = self.cbxSplitWords.isChecked()
 
         # persist some settings

comictaggerlib/cbltransformer.py

@@ -32,7 +32,7 @@ class CBLTransformer:
         # helper funcs
         def append_to_tags_if_unique(item: str) -> None:
             if item.casefold() not in (tag.casefold() for tag in self.metadata.tags):
-                self.metadata.tags.append(item)
+                self.metadata.tags.add(item)
 
         def add_string_list_to_tags(str_list: str | None) -> None:
             if str_list:

comictaggerlib/cli.py

@@ -20,7 +20,7 @@ import argparse
 import json
 import logging
 import os
-import shutil
+import pathlib
 import sys
 from pprint import pprint
 
@@ -28,7 +28,7 @@ from comicapi import utils
 from comicapi.comicarchive import ComicArchive, MetaDataStyle
 from comicapi.genericmetadata import GenericMetadata
 from comictaggerlib.cbltransformer import CBLTransformer
-from comictaggerlib.filerenamer import FileRenamer
+from comictaggerlib.filerenamer import FileRenamer, get_rename_dir
 from comictaggerlib.issueidentifier import IssueIdentifier
 from comictaggerlib.resulttypes import IssueResult, MultipleMatch, OnlineMatchResults
 from comictaggerlib.settings import ComicTaggerSettings
@@ -514,21 +514,18 @@ def process_file_cli(
             )
             return
 
-        folder = os.path.dirname(os.path.abspath(filename))
-        if settings.rename_move_dir and len(settings.rename_dir.strip()) > 3:
-            folder = settings.rename_dir.strip()
+        folder = get_rename_dir(ca, settings.rename_dir if settings.rename_move_dir else None)
 
-        new_abs_path = utils.unique_file(os.path.join(folder, new_name))
+        full_path = folder / new_name
 
-        if os.path.join(folder, new_name) == os.path.abspath(filename):
+        if full_path == ca.path:
             print(msg_hdr + "Filename is already good!", file=sys.stderr)
             return
 
         suffix = ""
         if not opts.dryrun:
             # rename the file
-            os.makedirs(os.path.dirname(new_abs_path), 0o777, True)
-            shutil.move(filename, new_abs_path)
+            ca.rename(utils.unique_file(full_path))
         else:
             suffix = " (dry-run, no change)"
 
@@ -539,18 +536,18 @@ def process_file_cli(
         if batch_mode:
             msg_hdr = f"{ca.path}: "
 
-        if not ca.is_rar():
-            logger.error(msg_hdr + "Archive is not a RAR.")
+        if ca.is_zip():
+            logger.error(msg_hdr + "Archive is already a zip file.")
             return
 
-        rar_file = os.path.abspath(os.path.abspath(filename))
-        new_file = os.path.splitext(rar_file)[0] + ".cbz"
+        filename_path = pathlib.Path(filename).absolute()
+        new_file = filename_path.with_suffix(".cbz")
 
-        if opts.abort_on_conflict and os.path.lexists(new_file):
-            print(msg_hdr + f"{os.path.split(new_file)[1]} already exists in the that folder.")
+        if opts.abort_on_conflict and new_file.exists():
+            print(msg_hdr + f"{new_file.name} already exists in the that folder.")
             return
 
-        new_file = utils.unique_file(os.path.join(new_file))
+        new_file = utils.unique_file(new_file)
 
         delete_success = False
         export_success = False
@@ -559,16 +556,14 @@ def process_file_cli(
                 export_success = True
                 if opts.delete_after_zip_export:
                     try:
-                        os.unlink(rar_file)
-                    except OSError:
-                        logger.exception(msg_hdr + "Error deleting original RAR after export")
-                        delete_success = False
-                    else:
+                        filename_path.unlink(missing_ok=True)
                         delete_success = True
+                    except OSError:
+                        logger.exception(msg_hdr + "Error deleting original archive after export")
+                        delete_success = False
             else:
                 # last export failed, so remove the zip, if it exists
-                if os.path.lexists(new_file):
-                    os.remove(new_file)
+                new_file.unlink(missing_ok=True)
         else:
             msg = msg_hdr + f"Dry-run:  Would try to create {os.path.split(new_file)[1]}"
             if opts.delete_after_zip_export:

comictaggerlib/coverimagewidget.py

@@ -92,6 +92,7 @@ class CoverImageWidget(QtWidgets.QWidget):
     ) -> None:
         super().__init__(parent)
 
+        self.cover_fetcher = ImageFetcher()
         uic.loadUi(ComicTaggerSettings.get_ui_file("coverimagewidget.ui"), self)
 
         reduce_widget_font_size(self.label)
@@ -195,7 +196,7 @@ class CoverImageWidget(QtWidgets.QWidget):
 
             self.update_content()
 
-    def primary_url_fetch_complete(self, primary_url: str, thumb_url: str | None) -> None:
+    def primary_url_fetch_complete(self, primary_url: str, thumb_url: str | None = None) -> None:
         self.url_list.append(str(primary_url))
         self.imageIndex = 0
         self.imageCount = len(self.url_list)

comictaggerlib/filerenamer.py

@@ -25,12 +25,22 @@ from typing import Any, cast
 
 from pathvalidate import sanitize_filename
 
+from comicapi.comicarchive import ComicArchive
 from comicapi.genericmetadata import GenericMetadata
 from comicapi.issuestring import IssueString
 
 logger = logging.getLogger(__name__)
 
 
+def get_rename_dir(ca: ComicArchive, rename_dir: str | pathlib.Path | None) -> pathlib.Path:
+    folder = ca.path.parent.absolute()
+    if rename_dir is not None:
+        if isinstance(rename_dir, str):
+            rename_dir = rename_dir.strip()
+        folder = pathlib.Path(rename_dir).absolute()
+    return folder
+
+
 class MetadataFormatter(string.Formatter):
     def __init__(self, smart_cleanup: bool = False, platform: str = "auto") -> None:
         super().__init__()
@@ -80,17 +90,9 @@ class MetadataFormatter(string.Formatter):
                 field_name = field_name.casefold()
                 # this is some markup, find the object and do the formatting
 
-                # handle arg indexing when empty field_names are given.
-                if field_name == "":
-                    if auto_arg_index is False:
-                        raise ValueError("cannot switch from manual field specification to automatic field numbering")
-                    field_name = str(auto_arg_index)
-                    auto_arg_index += 1
-                elif field_name.isdigit():
-                    if auto_arg_index:
-                        raise ValueError("cannot switch from manual field specification to automatic field numbering")
-                    # disable auto arg incrementing, if it gets used later on, then an exception will be raised
-                    auto_arg_index = False
+                # handle arg indexing when digit field_names are given.
+                if field_name.isdigit():
+                    raise ValueError("cannot use a number as a field name")
 
                 # given the field_name, find the object it references
                 #  and the argument it came from
@@ -101,8 +103,8 @@ class MetadataFormatter(string.Formatter):
                 obj = self.convert_field(obj, conversion)  # type: ignore
 
                 # expand the format spec, if needed
-                format_spec, auto_arg_index = self._vformat(
-                    cast(str, format_spec), args, kwargs, used_args, recursion_depth - 1, auto_arg_index=auto_arg_index
+                format_spec, _ = self._vformat(
+                    cast(str, format_spec), args, kwargs, used_args, recursion_depth - 1, auto_arg_index=False
                 )
 
                 # format the object and append to the result
@@ -118,7 +120,7 @@ class MetadataFormatter(string.Formatter):
                     fmt_obj = str(sanitize_filename(fmt_obj, platform=self.platform))
                 result.append(fmt_obj)
 
-        return "".join(result), auto_arg_index
+        return "".join(result), False
 
 
 class FileRenamer:
@@ -168,16 +170,17 @@ class FileRenamer:
             md_dict["month_name"] = ""
             md_dict["month_abbr"] = ""
 
-        for Component in pathlib.PureWindowsPath(template).parts:
+        new_basename = ""
+        for component in pathlib.PureWindowsPath(template).parts:
             if (
                 self.platform.casefold() in ["universal", "windows"] or sys.platform.casefold() in ["windows"]
             ) and self.smart_cleanup:
                 # colons get special treatment
-                Component = Component.replace(": ", " - ")
-                Component = Component.replace(":", "-")
+                component = component.replace(": ", " - ")
+                component = component.replace(":", "-")
 
             new_basename = str(
-                sanitize_filename(fmt.vformat(Component, args=[], kwargs=Default(md_dict)), platform=self.platform)
+                sanitize_filename(fmt.vformat(component, args=[], kwargs=Default(md_dict)), platform=self.platform)
             ).strip()
             new_name = os.path.join(new_name, new_basename)
 

comictaggerlib/fileselectionlist.py

@@ -17,13 +17,16 @@ from __future__ import annotations
 
 import logging
 import os
+import platform
 from typing import Callable, cast
 
 from PyQt5 import QtCore, QtWidgets, uic
 
 from comicapi import utils
 from comicapi.comicarchive import ComicArchive
+from comictaggerlib.optionalmsgdialog import OptionalMessageDialog
 from comictaggerlib.settings import ComicTaggerSettings
+from comictaggerlib.settingswindow import linuxRarHelp, macRarHelp, windowsRarHelp
 from comictaggerlib.ui.qtutils import center_window_on_parent, reduce_widget_font_size
 
 logger = logging.getLogger(__name__)
@@ -88,6 +91,7 @@ class FileSelectionList(QtWidgets.QWidget):
         self.addAction(self.separator)
 
         self.dirty_flag_verification = dirty_flag_verification
+        self.rar_ro_shown = False
 
     def get_sorting(self) -> tuple[int, int]:
         col = self.twList.horizontalHeader().sortIndicatorSection()
@@ -190,6 +194,7 @@ class FileSelectionList(QtWidgets.QWidget):
 
         QtCore.QCoreApplication.processEvents()
         first_added = None
+        rar_added = False
         self.twList.setSortingEnabled(False)
         for idx, f in enumerate(filelist):
             QtCore.QCoreApplication.processEvents()
@@ -200,8 +205,12 @@ class FileSelectionList(QtWidgets.QWidget):
             center_window_on_parent(progdialog)
             QtCore.QCoreApplication.processEvents()
             row = self.add_path_item(f)
-            if first_added is None and row is not None:
-                first_added = row
+            if row is not None:
+                ca = self.get_archive_by_row(row)
+                if ca and ca.is_rar():
+                    rar_added = True
+                if first_added is None:
+                    first_added = row
 
         progdialog.hide()
         QtCore.QCoreApplication.processEvents()
@@ -216,6 +225,9 @@ class FileSelectionList(QtWidgets.QWidget):
             else:
                 QtWidgets.QMessageBox.information(self, "File/Folder Open", "No readable comic archives were found.")
 
+        if rar_added and not utils.which(self.settings.rar_exe_path or "rar"):
+            self.rar_ro_message()
+
         self.twList.setSortingEnabled(True)
 
         # Adjust column size
@@ -229,6 +241,26 @@ class FileSelectionList(QtWidgets.QWidget):
         if self.twList.columnWidth(FileSelectionList.folderColNum) > 200:
             self.twList.setColumnWidth(FileSelectionList.folderColNum, 200)
 
+    def rar_ro_message(self) -> None:
+        if not self.rar_ro_shown:
+            if platform.system() == "Windows":
+                rar_help = windowsRarHelp
+
+            elif platform.system() == "Darwin":
+                rar_help = macRarHelp
+
+            else:
+                rar_help = linuxRarHelp
+
+            OptionalMessageDialog.msg_no_checkbox(
+                self,
+                "RAR Files are Read-Only",
+                "It looks like you have opened a RAR/CBR archive,\n"
+                "however ComicTagger cannot currently write to them without the rar program and are marked read only!\n\n"
+                f"{rar_help}",
+            )
+            self.rar_ro_shown = True
+
     def is_list_dupe(self, path: str) -> bool:
         return self.get_current_list_row(path) >= 0
 
@@ -344,7 +376,7 @@ class FileSelectionList(QtWidgets.QWidget):
             try:
                 fi.ca.read_cix()
             except Exception:
-                ...
+                pass
             fi.ca.has_cbi()
 
     def get_selected_archive_list(self) -> list[ComicArchive]:

comictaggerlib/imagefetcher.py

@@ -38,7 +38,7 @@ logger = logging.getLogger(__name__)
 
 
 class ImageFetcherException(Exception):
-    pass
+    ...
 
 
 def fetch_complete(image_data: bytes | QtCore.QByteArray) -> None:

comictaggerlib/imagehasher.py

@@ -49,7 +49,7 @@ class ImageHasher:
 
     def average_hash(self) -> int:
         try:
-            image = self.image.resize((self.width, self.height), Image.ANTIALIAS).convert("L")
+            image = self.image.resize((self.width, self.height), Image.Resampling.LANCZOS).convert("L")
         except Exception:
             logger.exception("average_hash error")
             return 0

comictaggerlib/imagepopup.py

@@ -51,7 +51,7 @@ class ImagePopup(QtWidgets.QDialog):
         self.clientBgPixmap = bg.scaled(
             screen_size.width(),
             screen_size.height(),
-            QtCore.Qt.AspectRatioMode.KeepAspectRatio,
+            QtCore.Qt.AspectRatioMode.IgnoreAspectRatio,
             QtCore.Qt.SmoothTransformation,
         )
         self.setMask(self.clientBgPixmap.mask())

comictaggerlib/issueidentifier.py

@@ -59,11 +59,11 @@ class Score(TypedDict):
 
 
 class IssueIdentifierNetworkError(Exception):
-    pass
+    ...
 
 
 class IssueIdentifierCancelled(Exception):
-    pass
+    ...
 
 
 class IssueIdentifier:
@@ -98,7 +98,7 @@ class IssueIdentifier:
 
         # used to eliminate series names that are too long based on our search
         # string
-        self.length_delta_thresh = settings.id_length_delta_thresh
+        self.series_match_thresh = settings.id_series_match_identify_thresh
 
         # used to eliminate unlikely publishers
         self.publisher_filter = [s.strip().casefold() for s in settings.id_publisher_filter.split(",")]
@@ -122,8 +122,8 @@ class IssueIdentifier:
     def set_additional_metadata(self, md: GenericMetadata) -> None:
         self.additional_metadata = md
 
-    def set_name_length_delta_threshold(self, delta: int) -> None:
-        self.length_delta_thresh = delta
+    def set_name_series_match_threshold(self, delta: int) -> None:
+        self.series_match_thresh = delta
 
     def set_publisher_filter(self, flt: list[str]) -> None:
         self.publisher_filter = flt
@@ -177,35 +177,29 @@ class IssueIdentifier:
     def get_search_keys(self) -> SearchKeys:
 
         ca = self.comic_archive
-        search_keys: SearchKeys = {
-            "series": None,
-            "issue_number": None,
-            "month": None,
-            "year": None,
-            "issue_count": None,
-        }
 
         if ca is None:
             return None
-
+        search_keys: SearchKeys
         if self.only_use_additional_meta_data:
-            search_keys["series"] = self.additional_metadata.series
-            search_keys["issue_number"] = self.additional_metadata.issue
-            search_keys["year"] = self.additional_metadata.year
-            search_keys["month"] = self.additional_metadata.month
-            search_keys["issue_count"] = self.additional_metadata.issue_count
+            search_keys = SearchKeys(
+                series=self.additional_metadata.series,
+                issue_number=self.additional_metadata.issue,
+                year=self.additional_metadata.year,
+                month=self.additional_metadata.month,
+                issue_count=self.additional_metadata.issue_count,
+            )
             return search_keys
 
         # see if the archive has any useful meta data for searching with
-        if ca.has_cix():
-            try:
+        try:
+            if ca.has_cix():
                 internal_metadata = ca.read_cix()
-            except Exception as e:
-                logger.error("Failed to load metadata for %s: %s", ca.path, e)
-        elif ca.has_cbi():
-            internal_metadata = ca.read_cbi()
-        else:
-            internal_metadata = ca.read_cbi()
+            else:
+                internal_metadata = ca.read_cbi()
+        except Exception as e:
+            internal_metadata = GenericMetadata()
+            logger.error("Failed to load metadata for %s: %s", ca.path, e)
 
         # try to get some metadata from filename
         md_from_filename = ca.metadata_from_filename(
@@ -215,45 +209,22 @@ class IssueIdentifier:
             self.settings.remove_publisher,
         )
 
+        working_md = md_from_filename.copy()
+
+        working_md.overlay(internal_metadata)
+        working_md.overlay(self.additional_metadata)
+
         # preference order:
         # 1. Additional metadata
         # 1. Internal metadata
         # 1. Filename metadata
-
-        if self.additional_metadata.series is not None:
-            search_keys["series"] = self.additional_metadata.series
-        elif internal_metadata.series is not None:
-            search_keys["series"] = internal_metadata.series
-        else:
-            search_keys["series"] = md_from_filename.series
-
-        if self.additional_metadata.issue is not None:
-            search_keys["issue_number"] = self.additional_metadata.issue
-        elif internal_metadata.issue is not None:
-            search_keys["issue_number"] = internal_metadata.issue
-        else:
-            search_keys["issue_number"] = md_from_filename.issue
-
-        if self.additional_metadata.year is not None:
-            search_keys["year"] = self.additional_metadata.year
-        elif internal_metadata.year is not None:
-            search_keys["year"] = internal_metadata.year
-        else:
-            search_keys["year"] = md_from_filename.year
-
-        if self.additional_metadata.month is not None:
-            search_keys["month"] = self.additional_metadata.month
-        elif internal_metadata.month is not None:
-            search_keys["month"] = internal_metadata.month
-        else:
-            search_keys["month"] = md_from_filename.month
-
-        if self.additional_metadata.issue_count is not None:
-            search_keys["issue_count"] = self.additional_metadata.issue_count
-        elif internal_metadata.issue_count is not None:
-            search_keys["issue_count"] = internal_metadata.issue_count
-        else:
-            search_keys["issue_count"] = md_from_filename.issue_count
+        search_keys = SearchKeys(
+            series=working_md.series,
+            issue_number=working_md.issue,
+            year=working_md.year,
+            month=working_md.month,
+            issue_count=working_md.issue_count,
+        )
 
         return search_keys
 
@@ -294,9 +265,7 @@ class IssueIdentifier:
         if self.cover_url_callback is not None:
             self.cover_url_callback(url_image_data)
 
-        remote_cover_list = []
-
-        remote_cover_list.append(Score({"url": primary_img_url, "hash": self.calculate_hash(url_image_data)}))
+        remote_cover_list = [Score(url=primary_img_url, hash=self.calculate_hash(url_image_data))]
 
         if self.cancel:
             raise IssueIdentifierCancelled
@@ -317,7 +286,7 @@ class IssueIdentifier:
                 if self.cover_url_callback is not None:
                     self.cover_url_callback(alt_url_image_data)
 
-                remote_cover_list.append(Score({"url": alt_url, "hash": self.calculate_hash(alt_url_image_data)}))
+                remote_cover_list.append(Score(url=alt_url, hash=self.calculate_hash(alt_url_image_data)))
 
                 if self.cancel:
                     raise IssueIdentifierCancelled
@@ -332,9 +301,7 @@ class IssueIdentifier:
         for local_cover_hash in local_cover_hash_list:
             for remote_cover_item in remote_cover_list:
                 score = ImageHasher.hamming_distance(local_cover_hash, remote_cover_item["hash"])
-                score_list.append(
-                    Score({"score": score, "url": remote_cover_item["url"], "hash": remote_cover_item["hash"]})
-                )
+                score_list.append(Score(score=score, url=remote_cover_item["url"], hash=remote_cover_item["hash"]))
                 if use_log:
                     self.log_msg(score, False)
 
@@ -431,15 +398,13 @@ class IssueIdentifier:
                 if int(keys["year"]) < int(item["start_year"]):
                     date_approved = False
 
-            # assume that our search name is close to the actual name, say
-            # within ,e.g. 5 chars
-            # sanitize both the search string and the result so that
-            # we are comparing the same type of data
-            shortened_key = utils.sanitize_title(keys["series"])
-            shortened_item_name = utils.sanitize_title(item["name"])
-            if len(shortened_item_name) < (len(shortened_key) + self.length_delta_thresh):
-                length_approved = True
-
+            aliases = []
+            if item["aliases"]:
+                aliases = item["aliases"].split("\n")
+            for name in [item["name"], *aliases]:
+                if utils.titles_match(keys["series"], name, self.series_match_thresh):
+                    length_approved = True
+                    break
             # remove any series from publishers on the filter
             if item["publisher"] is not None:
                 publisher = item["publisher"]

comictaggerlib/issueselectionwindow.py

@@ -138,18 +138,18 @@ class IssueSelectionWindow(QtWidgets.QDialog):
             if len(parts) > 1:
                 item_text = parts[0] + "-" + parts[1]
 
-            QTW_item = QtWidgets.QTableWidgetItem(item_text)
-            QTW_item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, item_text)
-            QTW_item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
-            self.twList.setItem(row, 1, QTW_item)
+            qtw_item = QtWidgets.QTableWidgetItem(item_text)
+            qtw_item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, item_text)
+            qtw_item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
+            self.twList.setItem(row, 1, qtw_item)
 
             item_text = record["name"]
             if item_text is None:
                 item_text = ""
-            QTW_item = QtWidgets.QTableWidgetItem(item_text)
-            QTW_item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, item_text)
-            QTW_item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
-            self.twList.setItem(row, 2, QTW_item)
+            qtw_item = QtWidgets.QTableWidgetItem(item_text)
+            qtw_item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, item_text)
+            qtw_item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
+            self.twList.setItem(row, 2, qtw_item)
 
             if (
                 IssueString(record["issue_number"]).as_string().casefold()

comictaggerlib/main.py

@@ -93,7 +93,7 @@ try:
 except ImportError as e:
 
     def show_exception_box(log_msg: str) -> None:
-        pass
+        ...
 
     logger.error(str(e))
     qt_available = False
@@ -116,7 +116,7 @@ def update_publishers() -> None:
 
 def ctmain() -> None:
     opts = parse_cmd_line()
-    SETTINGS = ComicTaggerSettings(opts.config_path)
+    settings = ComicTaggerSettings(opts.config_path)
 
     os.makedirs(ComicTaggerSettings.get_settings_folder() / "logs", exist_ok=True)
     stream_handler = logging.StreamHandler()
@@ -149,18 +149,18 @@ def ctmain() -> None:
     for pkg in sorted(importlib_metadata.distributions(), key=lambda x: x.name):
         logger.debug("%s\t%s", pkg.name, pkg.version)
 
-    talker_api = ComicTalker(SETTINGS.comic_info_source)
+    talker_api = ComicTalker(settings.comic_info_source)
 
     utils.load_publishers()
     update_publishers()
 
     if not qt_available and not opts.no_gui:
         opts.no_gui = True
-        logger.warn("PyQt5 is not available. ComicTagger is limited to command-line mode.")
+        logger.warning("PyQt5 is not available. ComicTagger is limited to command-line mode.")
 
     if opts.no_gui:
         try:
-            cli.cli_mode(opts, SETTINGS, talker_api)
+            cli.cli_mode(opts, settings, talker_api)
         except Exception:
             logger.exception("CLI mode failed")
     else:
@@ -196,7 +196,7 @@ def ctmain() -> None:
             QtWidgets.QApplication.processEvents()
 
         try:
-            tagger_window = TaggerWindow(opts.files, SETTINGS, talker_api, opts=opts)
+            tagger_window = TaggerWindow(opts.files, settings, talker_api, opts=opts)
             tagger_window.setWindowIcon(QtGui.QIcon(ComicTaggerSettings.get_graphic("app.png")))
             tagger_window.show()
 

comictaggerlib/optionalmsgdialog.py

@@ -112,3 +112,14 @@ class OptionalMessageDialog(QtWidgets.QDialog):
         d.exec()
 
         return d.was_accepted, d.theCheckBox.isChecked()
+
+    @staticmethod
+    def msg_no_checkbox(
+        parent: QtWidgets.QWidget, title: str, msg: str, checked: bool = False, check_text: str = ""
+    ) -> bool:
+
+        d = OptionalMessageDialog(parent, StyleMessage, title, msg, checked=checked, check_text=check_text)
+        d.theCheckBox.hide()
+
+        d.exec()
+        return d.theCheckBox.isChecked()

comictaggerlib/pagelisteditor.py

@@ -120,10 +120,10 @@ class PageListEditor(QtWidgets.QWidget):
         if show_shortcut:
             text = text + " (" + shortcut + ")"
         self.cbPageType.addItem(text, user_data)
-        actionItem = QtWidgets.QAction(shortcut, self)
-        actionItem.triggered.connect(lambda: self.select_page_type_item(self.cbPageType.findData(user_data)))
-        actionItem.setShortcut(shortcut)
-        self.addAction(actionItem)
+        action_item = QtWidgets.QAction(shortcut, self)
+        action_item.triggered.connect(lambda: self.select_page_type_item(self.cbPageType.findData(user_data)))
+        action_item.setShortcut(shortcut)
+        self.addAction(action_item)
 
     def select_page_type_item(self, idx: int) -> None:
         if self.cbPageType.isEnabled():
@@ -133,19 +133,19 @@ class PageListEditor(QtWidgets.QWidget):
     def get_new_indexes(self, movement: int) -> list[tuple[int, int]]:
         selection = self.listWidget.selectionModel().selectedRows()
         selection.sort(reverse=movement > 0)
-        newindexes: list[int] = []
-        oldindexes: list[int] = []
+        new_indexes: list[int] = []
+        old_indexes: list[int] = []
         for x in selection:
             current = x.row()
-            oldindexes.append(current)
+            old_indexes.append(current)
             if 0 <= current + movement <= self.listWidget.count() - 1:
-                if len(newindexes) < 1 or current + movement != newindexes[-1]:
+                if len(new_indexes) < 1 or current + movement != new_indexes[-1]:
                     current += movement
 
-            newindexes.append(current)
-        oldindexes.sort()
-        newindexes.sort()
-        return list(zip(newindexes, oldindexes))
+            new_indexes.append(current)
+        old_indexes.sort()
+        new_indexes.sort()
+        return list(zip(new_indexes, old_indexes))
 
     def set_selection(self, indexes: list[tuple[int, int]]) -> list[tuple[int, int]]:
         selection_ranges: list[tuple[int, int]] = []

comictaggerlib/renamewindow.py

@@ -16,15 +16,13 @@
 from __future__ import annotations
 
 import logging
-import os
-import shutil
-from typing import TypedDict
 
 from PyQt5 import QtCore, QtWidgets, uic
 
 from comicapi import utils
 from comicapi.comicarchive import ComicArchive, MetaDataStyle
-from comictaggerlib.filerenamer import FileRenamer
+from comicapi.genericmetadata import GenericMetadata
+from comictaggerlib.filerenamer import FileRenamer, get_rename_dir
 from comictaggerlib.settings import ComicTaggerSettings
 from comictaggerlib.settingswindow import SettingsWindow
 from comictaggerlib.ui.qtutils import center_window_on_parent
@@ -33,11 +31,6 @@ from comictalker.comictalker import ComicTalker
 logger = logging.getLogger(__name__)
 
 
-class RenameItem(TypedDict):
-    archive: ComicArchive
-    new_name: str
-
-
 class RenameWindow(QtWidgets.QDialog):
     def __init__(
         self,
@@ -64,35 +57,28 @@ class RenameWindow(QtWidgets.QDialog):
         self.talker_api = talker_api
         self.comic_archive_list = comic_archive_list
         self.data_style = data_style
-        self.rename_list: list[RenameItem] = []
+        self.rename_list: list[str] = []
 
         self.btnSettings.clicked.connect(self.modify_settings)
         self.renamer = FileRenamer(None, platform="universal" if self.settings.rename_strict else "auto")
 
-        self.config_renamer()
         self.do_preview()
 
-    def config_renamer(self) -> None:
+    def config_renamer(self, ca: ComicArchive, md: GenericMetadata | None = None) -> str:
         self.renamer.set_template(self.settings.rename_template)
         self.renamer.set_issue_zero_padding(self.settings.rename_issue_number_padding)
         self.renamer.set_smart_cleanup(self.settings.rename_use_smart_string_cleanup)
 
-    def do_preview(self) -> None:
-        self.twList.setRowCount(0)
-
-        self.twList.setSortingEnabled(False)
-
-        for ca in self.comic_archive_list:
-
-            new_ext = ca.path.suffix  # default
-            if self.settings.rename_extension_based_on_archive:
-                if ca.is_sevenzip():
-                    new_ext = ".cb7"
-                elif ca.is_zip():
-                    new_ext = ".cbz"
-                elif ca.is_rar():
-                    new_ext = ".cbr"
+        new_ext = ca.path.suffix  # default
+        if self.settings.rename_extension_based_on_archive:
+            if ca.is_sevenzip():
+                new_ext = ".cb7"
+            elif ca.is_zip():
+                new_ext = ".cbz"
+            elif ca.is_rar():
+                new_ext = ".cbr"
 
+        if md is None:
             md = ca.read_metadata(self.data_style)
             if md.is_empty:
                 md = ca.metadata_from_filename(
@@ -101,9 +87,17 @@ class RenameWindow(QtWidgets.QDialog):
                     self.settings.remove_fcbd,
                     self.settings.remove_publisher,
                 )
-            self.renamer.set_metadata(md)
-            self.renamer.move = self.settings.rename_move_dir
+        self.renamer.set_metadata(md)
+        self.renamer.move = self.settings.rename_move_dir
+        return new_ext
 
+    def do_preview(self) -> None:
+        self.twList.setRowCount(0)
+
+        self.twList.setSortingEnabled(False)
+
+        for ca in self.comic_archive_list:
+            new_ext = self.config_renamer(ca)
             try:
                 new_name = self.renamer.determine_name(new_ext)
             except Exception as e:
@@ -125,13 +119,13 @@ class RenameWindow(QtWidgets.QDialog):
             old_name_item = QtWidgets.QTableWidgetItem()
             new_name_item = QtWidgets.QTableWidgetItem()
 
-            item_text = os.path.split(ca.path)[0]
+            item_text = str(ca.path.parent)
             folder_item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
             self.twList.setItem(row, 0, folder_item)
             folder_item.setText(item_text)
             folder_item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, item_text)
 
-            item_text = os.path.split(ca.path)[1]
+            item_text = str(ca.path.name)
             old_name_item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
             self.twList.setItem(row, 1, old_name_item)
             old_name_item.setText(item_text)
@@ -142,13 +136,7 @@ class RenameWindow(QtWidgets.QDialog):
             new_name_item.setText(new_name)
             new_name_item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, new_name)
 
-            dict_item = RenameItem(
-                {
-                    "archive": ca,
-                    "new_name": new_name,
-                }
-            )
-            self.rename_list.append(dict_item)
+            self.rename_list.append(new_name)
 
         # Adjust column sizes
         self.twList.setVisible(False)
@@ -165,7 +153,6 @@ class RenameWindow(QtWidgets.QDialog):
         settingswin.show_rename_tab()
         settingswin.exec()
         if settingswin.result():
-            self.config_renamer()
             self.do_preview()
 
     def accept(self) -> None:
@@ -177,34 +164,29 @@ class RenameWindow(QtWidgets.QDialog):
         center_window_on_parent(prog_dialog)
         QtCore.QCoreApplication.processEvents()
 
-        for idx, item in enumerate(self.rename_list):
+        for idx, comic in enumerate(zip(self.comic_archive_list, self.rename_list)):
 
             QtCore.QCoreApplication.processEvents()
             if prog_dialog.wasCanceled():
                 break
             idx += 1
             prog_dialog.setValue(idx)
-            prog_dialog.setLabelText(item["new_name"])
+            prog_dialog.setLabelText(comic[1])
             center_window_on_parent(prog_dialog)
             QtCore.QCoreApplication.processEvents()
 
-            folder = os.path.dirname(os.path.abspath(item["archive"].path))
-            if self.settings.rename_move_dir and len(self.settings.rename_dir.strip()) > 3:
-                folder = self.settings.rename_dir.strip()
+            folder = get_rename_dir(comic[0], self.settings.rename_dir if self.settings.rename_move_dir else None)
 
-            new_abs_path = utils.unique_file(os.path.join(folder, item["new_name"]))
+            full_path = folder / comic[1]
 
-            if os.path.join(folder, item["new_name"]) == item["archive"].path:
-                logger.info(item["new_name"], "Filename is already good!")
+            if full_path == comic[0].path:
+                logger.info("%s: Filename is already good!", comic[1])
                 continue
 
-            if not item["archive"].is_writable(check_rar_status=False):
+            if not comic[0].is_writable(check_rar_status=False):
                 continue
 
-            os.makedirs(os.path.dirname(new_abs_path), 0o777, True)
-            shutil.move(item["archive"].path, new_abs_path)
-
-            item["archive"].rename(new_abs_path)
+            comic[0].rename(utils.unique_file(full_path))
 
         prog_dialog.hide()
         QtCore.QCoreApplication.processEvents()

comictaggerlib/settings.py

@@ -102,7 +102,8 @@ class ComicTaggerSettings:
         self.last_filelist_sorted_order = 0
 
         # identifier settings
-        self.id_length_delta_thresh = 5
+        self.id_series_match_search_thresh = 90
+        self.id_series_match_identify_thresh = 91
         self.id_publisher_filter = "Panini Comics, Abril, Planeta DeAgostini, Editorial Televisa, Dino Comics"
         self.comic_info_source = "comicvine"  # Default to CV as should always be present
 
@@ -181,10 +182,12 @@ class ComicTaggerSettings:
                 elif os.path.exists(r"C:\Program Files (x86)\WinRAR\Rar.exe"):
                     self.rar_exe_path = r"C:\Program Files (x86)\WinRAR\Rar.exe"
             else:
+                if os.path.exists("/opt/homebrew/bin"):
+                    utils.add_to_path("/opt/homebrew/bin")
                 # see if it's in the path of unix user
                 rarpath = utils.which("rar")
                 if rarpath is not None:
-                    self.rar_exe_path = rarpath
+                    self.rar_exe_path = "rar"
             if self.rar_exe_path != "":
                 self.save()
         if self.rar_exe_path != "":
@@ -236,8 +239,10 @@ class ComicTaggerSettings:
         if self.config.has_option("auto", "last_filelist_sorted_order"):
             self.last_filelist_sorted_order = self.config.getint("auto", "last_filelist_sorted_order")
 
-        if self.config.has_option("identifier", "id_length_delta_thresh"):
-            self.id_length_delta_thresh = self.config.getint("identifier", "id_length_delta_thresh")
+        if self.config.has_option("identifier", "id_series_match_search_thresh"):
+            self.id_series_match_search_thresh = self.config.getint("identifier", "id_series_match_search_thresh")
+        if self.config.has_option("identifier", "id_series_match_identify_thresh"):
+            self.id_series_match_identify_thresh = self.config.getint("identifier", "id_series_match_identify_thresh")
         if self.config.has_option("identifier", "id_publisher_filter"):
             self.id_publisher_filter = self.config.get("identifier", "id_publisher_filter")
         if self.config.has_option("identifier", "always_use_publisher_filter"):
@@ -364,7 +369,8 @@ class ComicTaggerSettings:
         if not self.config.has_section("identifier"):
             self.config.add_section("identifier")
 
-        self.config.set("identifier", "id_length_delta_thresh", self.id_length_delta_thresh)
+        self.config.set("identifier", "id_series_match_search_thresh", self.id_series_match_search_thresh)
+        self.config.set("identifier", "id_series_match_identify_thresh", self.id_series_match_identify_thresh)
         self.config.set("identifier", "id_publisher_filter", self.id_publisher_filter)
         self.config.set("identifier", "always_use_publisher_filter", self.always_use_publisher_filter)
 

comictaggerlib/settingswindow.py

@@ -18,6 +18,7 @@ from __future__ import annotations
 import html
 import logging
 import os
+import pathlib
 import platform
 
 from PyQt5 import QtCore, QtGui, QtWidgets, uic
@@ -33,29 +34,29 @@ from comictalker.comictalker import ComicTalker
 logger = logging.getLogger(__name__)
 
 windowsRarHelp = """
-                 <html><head/><body><p>To write to CBR/RAR archives,
-                 you will need to have the tools from
-                 <span style=" text-decoration: underline; color:#0000ff;">
-                 <a href="http://www.win-rar.com/download.html">WINRar</a></span>
-                 installed. (ComicTagger only uses the command-line rar tool,
-                 which is free to use.)</p></body></html>
+                <html><head/><body><p>To write to CBR/RAR archives,
+                you will need to have the tools from
+                <span style=" text-decoration: underline; color:#0000ff;">
+                <a href="http://www.win-rar.com/download.html">WINRar</a></span>
+                installed. (ComicTagger only uses the command-line rar tool.)
+                </p></body></html>
                 """
 
 linuxRarHelp = """
-               <html><head/><body><p>To write to CBR/RAR archives,
-               you will need to have the shareware rar tool from RARLab installed.
-               Your package manager should have rar (e.g. "apt-get install rar"). If not, download it
-               <span style=" text-decoration: underline; color:#0000ff;">
-               <a href="https://www.rarlab.com/download.htm">here</a></span>,
-               and install in your path. </p></body></html>
-               """
+                <html><head/><body><p>To write to CBR/RAR archives,
+                you will need to have the shareware rar tool from RARLab installed.
+                Your package manager should have rar (e.g. "apt-get install rar"). If not, download it
+                <span style=" text-decoration: underline; color:#0000ff;">
+                <a href="https://www.rarlab.com/download.htm">here</a></span>,
+                and install in your path. </p></body></html>
+                """
 
 macRarHelp = """
-                 <html><head/><body><p>To write to CBR/RAR archives,
-                 you will need the rar tool.  The easiest way to get this is
-                 to install <span style=" text-decoration: underline; color:#0000ff;">
-                 <a href="https://brew.sh/">homebrew</a></span>.
-                 </p>Once homebrew is installed, run: <b>brew install caskroom/cask/rar</b></body></html>
+                <html><head/><body><p>To write to CBR/RAR archives,
+                you will need the rar tool.  The easiest way to get this is
+                to install <span style=" text-decoration: underline; color:#0000ff;">
+                <a href="https://brew.sh/">homebrew</a></span>.
+                </p>Once homebrew is installed, run: <b>brew install caskroom/cask/rar</b></body></html>
                 """
 
 
@@ -105,7 +106,7 @@ Accepts the following variables:
 {cover artist}     (string)
 {editor}           (string)
 {tags}             (list of str)
-{pages}            (list of dict({'Image': string(int), 'Type': string, 'Bookmark': string, 'DoublePage': string}))
+{pages}            (list of dict({'Image': string(int), 'Type': string, 'Bookmark': string, 'DoublePage': boolean}))
 
 CoMet-only items:
 {price}            (float)
@@ -155,13 +156,16 @@ class SettingsWindow(QtWidgets.QDialog):
         self.lblDefaultSettings.setText("Revert to default " + self.name.casefold())
         self.btnResetSettings.setText("Default " + self.name)
 
-        nldt_tip = """<html>The <b>Default Name Length Match Tolerance</b> is for eliminating automatic
-                search matches that are too long compared to your series name search. The higher
+        nmit_tip = """<html>The <b>Name Match Ratio Threshold: Auto-Identify</b> is for eliminating automatic
+                search matches that are too long compared to your series name search. The lower
                 it is, the more likely to have a good match, but each search will take longer and
-                use more bandwidth. Too low, and only the very closest lexical matches will be
-                explored.</html>"""
+                use more bandwidth. Too high, and only the very closest matches will be explored.</html>"""
+        nmst_tip = """<html>The <b>Name Match Ratio Threshold: Search</b> is for reducing the total
+                number of results that are returned from a search. The lower it is, the more pages will
+                be returned (max 5 pages or 500 results)</html>"""
 
-        self.leNameLengthDeltaThresh.setToolTip(nldt_tip)
+        self.sbNameMatchIdentifyThresh.setToolTip(nmit_tip)
+        self.sbNameMatchSearchThresh.setToolTip(nmst_tip)
 
         pbl_tip = """<html>
             The <b>Publisher Filter</b> is for eliminating automatic matches to certain publishers
@@ -173,22 +177,21 @@ class SettingsWindow(QtWidgets.QDialog):
         validator = QtGui.QIntValidator(1, 4, self)
         self.leIssueNumPadding.setValidator(validator)
 
-        validator = QtGui.QIntValidator(0, 99, self)
-        self.leNameLengthDeltaThresh.setValidator(validator)
-
         self.leRenameTemplate.setToolTip(f"<pre>{html.escape(template_tooltip)}</pre>")
         self.settings_to_form()
         self.rename_error: Exception | None = None
         self.rename_test()
+        self.dir_test()
 
         self.btnBrowseRar.clicked.connect(self.select_rar)
         self.btnClearCache.clicked.connect(self.clear_cache)
         self.btnResetSettings.clicked.connect(self.reset_settings)
         self.btnTemplateHelp.clicked.connect(self.show_template_help)
-        self.leRenameTemplate.textEdited.connect(self.rename__test)
+        self.leRenameTemplate.textEdited.connect(self._rename_test)
         self.cbxMoveFiles.clicked.connect(self.rename_test)
+        self.cbxMoveFiles.clicked.connect(self.dir_test)
         self.cbxRenameStrict.clicked.connect(self.rename_test)
-        self.leDirectory.textEdited.connect(self.rename_test)
+        self.leDirectory.textEdited.connect(self.dir_test)
         self.cbxComplicatedParser.clicked.connect(self.switch_parser)
 
         self.sources: dict = {}
@@ -282,9 +285,14 @@ class SettingsWindow(QtWidgets.QDialog):
         self.cobxInfoSource.setCurrentIndex(self.cobxInfoSource.findData(self.settings.comic_info_source))
 
     def rename_test(self) -> None:
-        self.rename__test(self.leRenameTemplate.text())
+        self._rename_test(self.leRenameTemplate.text())
 
-    def rename__test(self, template: str) -> None:
+    def dir_test(self) -> None:
+        self.lblDir.setText(
+            str(pathlib.Path(self.leDirectory.text().strip()).absolute()) if self.cbxMoveFiles.isChecked() else ""
+        )
+
+    def _rename_test(self, template: str) -> None:
         fr = FileRenamer(md_test, platform="universal" if self.cbxRenameStrict.isChecked() else "auto")
         fr.move = self.cbxMoveFiles.isChecked()
         fr.set_template(template)
@@ -307,7 +315,8 @@ class SettingsWindow(QtWidgets.QDialog):
     def settings_to_form(self) -> None:
         # Copy values from settings to form
         self.leRarExePath.setText(self.settings.rar_exe_path)
-        self.leNameLengthDeltaThresh.setText(str(self.settings.id_length_delta_thresh))
+        self.sbNameMatchIdentifyThresh.setValue(self.settings.id_series_match_identify_thresh)
+        self.sbNameMatchSearchThresh.setValue(self.settings.id_series_match_search_thresh)
         self.tePublisherFilter.setPlainText(self.settings.id_publisher_filter)
 
         self.cbxCheckForNewVersion.setChecked(self.settings.check_for_new_version)
@@ -364,15 +373,13 @@ class SettingsWindow(QtWidgets.QDialog):
         if self.settings.rar_exe_path:
             utils.add_to_path(os.path.dirname(self.settings.rar_exe_path))
 
-        if not str(self.leNameLengthDeltaThresh.text()).isdigit():
-            self.leNameLengthDeltaThresh.setText("0")
-
         if not str(self.leIssueNumPadding.text()).isdigit():
             self.leIssueNumPadding.setText("0")
 
         self.settings.check_for_new_version = self.cbxCheckForNewVersion.isChecked()
 
-        self.settings.id_length_delta_thresh = int(self.leNameLengthDeltaThresh.text())
+        self.settings.id_series_match_identify_thresh = self.sbNameMatchIdentifyThresh.value()
+        self.settings.id_series_match_search_thresh = self.sbNameMatchSearchThresh.value()
         self.settings.id_publisher_filter = str(self.tePublisherFilter.toPlainText())
         self.settings.comic_info_source = str(self.cobxInfoSource.itemData(self.cobxInfoSource.currentIndex()))
         # Also change current talker_api object

comictaggerlib/taggerwindow.py

@@ -26,7 +26,7 @@ import pprint
 import re
 import sys
 import webbrowser
-from typing import Any, Callable, cast
+from typing import Any, Callable, Iterable, cast
 from urllib.parse import urlparse
 
 import natsort
@@ -449,16 +449,16 @@ Have fun!
 
     def repackage_archive(self) -> None:
         ca_list = self.fileSelectionList.get_selected_archive_list()
-        rar_count = 0
+        non_zip_count = 0
         for ca in ca_list:
-            if ca.is_rar():
-                rar_count += 1
+            if not ca.is_zip():
+                non_zip_count += 1
 
-        if rar_count == 0:
+        if non_zip_count == 0:
             QtWidgets.QMessageBox.information(
-                self, self.tr("Export as Zip Archive"), self.tr("No RAR archives selected!")
+                self, self.tr("Export as Zip Archive"), self.tr("Only ZIP archives are selected!")
             )
-            logger.warning("Export as Zip Archive. No RAR archives selected")
+            logger.warning("Export as Zip Archive. Only ZIP archives are selected")
             return
 
         if not self.dirty_flag_verification(
@@ -467,12 +467,12 @@ Have fun!
         ):
             return
 
-        if rar_count != 0:
+        if non_zip_count != 0:
             EW = ExportWindow(
                 self,
                 self.settings,
                 (
-                    f"You have selected {rar_count} archive(s) to export  to Zip format. "
+                    f"You have selected {non_zip_count} archive(s) to export  to Zip format. "
                     """ New archives will be created in the same folder as the original.
 
    Please choose options below, and select OK.
@@ -484,7 +484,7 @@ Have fun!
             if not EW.exec():
                 return
 
-            prog_dialog = QtWidgets.QProgressDialog("", "Cancel", 0, rar_count, self)
+            prog_dialog = QtWidgets.QProgressDialog("", "Cancel", 0, non_zip_count, self)
             prog_dialog.setWindowTitle("Exporting as ZIP")
             prog_dialog.setWindowModality(QtCore.Qt.WindowModality.ApplicationModal)
             prog_dialog.setMinimumDuration(300)
@@ -499,7 +499,7 @@ Have fun!
             success_count = 0
 
             for ca in ca_list:
-                if ca.is_rar():
+                if not ca.is_zip():
                     QtCore.QCoreApplication.processEvents()
                     if prog_dialog.wasCanceled():
                         break
@@ -509,30 +509,30 @@ Have fun!
                     center_window_on_parent(prog_dialog)
                     QtCore.QCoreApplication.processEvents()
 
-                    original_path = os.path.abspath(ca.path)
-                    export_name = os.path.splitext(original_path)[0] + ".cbz"
+                    export_name = ca.path.with_suffix(".cbz")
+                    export = True
 
-                    if os.path.lexists(export_name):
+                    if export_name.exists():
                         if EW.fileConflictBehavior == ExportConflictOpts.dontCreate:
-                            export_name = ""
+                            export = False
                             skipped_list.append(ca.path)
                         elif EW.fileConflictBehavior == ExportConflictOpts.createUnique:
                             export_name = utils.unique_file(export_name)
 
-                    if export_name:
+                    if export:
                         if ca.export_as_zip(export_name):
                             success_count += 1
                             if EW.addToList:
-                                new_archives_to_add.append(export_name)
+                                new_archives_to_add.append(str(export_name))
                             if EW.deleteOriginal:
                                 archives_to_remove.append(ca)
-                                os.unlink(ca.path)
+                                ca.path.unlink(missing_ok=True)
 
                         else:
                             # last export failed, so remove the zip, if it exists
                             failed_list.append(ca.path)
-                            if os.path.lexists(export_name):
-                                os.remove(export_name)
+                            if export_name.exists():
+                                export_name.unlink(missing_ok=True)
 
             prog_dialog.hide()
             QtCore.QCoreApplication.processEvents()
@@ -542,13 +542,13 @@ Have fun!
             summary = f"Successfully created {success_count} Zip archive(s)."
             if len(skipped_list) > 0:
                 summary += (
-                    f"\n\nThe following {len(skipped_list)} RAR archive(s) were skipped due to file name conflicts:\n"
+                    f"\n\nThe following {len(skipped_list)} archive(s) were skipped due to file name conflicts:\n"
                 )
                 for f in skipped_list:
                     summary += f"\t{f}\n"
             if len(failed_list) > 0:
                 summary += (
-                    f"\n\nThe following {len(failed_list)} RAR archive(s) failed to export due to read/write errors:\n"
+                    f"\n\nThe following {len(failed_list)} archive(s) failed to export due to read/write errors:\n"
                 )
                 for f in failed_list:
                     summary += f"\t{f}\n"
@@ -947,8 +947,8 @@ Have fun!
         tmp = self.teTags.toPlainText()
         if tmp is not None:
 
-            def strip_list(i: list[str]) -> list[str]:
-                return [x.strip() for x in i]
+            def strip_list(i: Iterable[str]) -> set[str]:
+                return {x.strip() for x in i}
 
             md.tags = strip_list(tmp.split(","))
 
@@ -1017,7 +1017,7 @@ Have fun!
 
         self.query_online(autoselect=True)
 
-    def literal_search(self):
+    def literal_search(self) -> None:
         self.query_online(autoselect=False, literal=True)
 
     def query_online(self, autoselect: bool = False, literal: bool = False) -> None:
@@ -1162,7 +1162,6 @@ Have fun!
 
         if self.save_data_style == MetaDataStyle.CIX:
             # loop over credit table, mark selected rows
-            r = 0
             for r in range(self.twCredits.rowCount()):
                 if str(self.twCredits.item(r, 1).text()).casefold() not in cix_credits:
                     self.twCredits.item(r, 1).setBackground(inactive_brush)
@@ -1173,7 +1172,6 @@ Have fun!
 
         if self.save_data_style == MetaDataStyle.CBI:
             # loop over credit table, make all active color
-            r = 0
             for r in range(self.twCredits.rowCount()):
                 self.twCredits.item(r, 0).setBackground(active_brush)
                 self.twCredits.item(r, 1).setBackground(active_brush)
@@ -1357,16 +1355,11 @@ Have fun!
     def open_web_link(self) -> None:
         if self.leWebLink is not None:
             web_link = self.leWebLink.text().strip()
-            valid = False
             try:
                 result = urlparse(web_link)
-                valid = all([result.scheme in ["http", "https"], result.netloc])
-            except ValueError:
-                pass
-
-            if valid:
+                all([result.scheme in ["http", "https"], result.netloc])
                 webbrowser.open_new_tab(web_link)
-            else:
+            except ValueError:
                 QtWidgets.QMessageBox.warning(self, self.tr("Web Link"), self.tr("Web Link is invalid."))
 
     def show_settings(self) -> None:
@@ -1374,8 +1367,7 @@ Have fun!
         settingswin = SettingsWindow(self, self.settings, self.talker_api)
         settingswin.setModal(True)
         settingswin.exec()
-        if settingswin.result():
-            pass
+        settingswin.result()
 
     def set_app_position(self) -> None:
         if self.settings.last_main_window_width != 0:
@@ -1750,7 +1742,7 @@ Have fun!
         ii.cover_page_index = md.get_cover_page_index_list()[0]
         if self.atprogdialog is not None:
             ii.set_cover_url_callback(self.atprogdialog.set_test_image)
-        ii.set_name_length_delta_threshold(dlg.name_length_match_tolerance)
+        ii.set_name_series_match_threshold(dlg.name_length_match_tolerance)
 
         matches: list[IssueResult] = ii.search()
 
@@ -1950,7 +1942,7 @@ Have fun!
             QtWidgets.QMessageBox.information(self, self.tr("Auto-Tag Summary"), self.tr(summary))
         logger.info(summary)
 
-    def exception(self, message):
+    def exception(self, message: str) -> None:
         errorbox = QtWidgets.QMessageBox()
         errorbox.setText(message)
         errorbox.exec()
@@ -2067,6 +2059,7 @@ Have fun!
             "File Rename", "If you rename files now, unsaved data in the form will be lost.  Are you sure?"
         ):
 
+            # TODO Check talker required
             dlg = RenameWindow(self, ca_list, self.load_data_style, self.settings, self.talker_api)
             dlg.setModal(True)
             if dlg.exec() and self.comic_archive is not None:

comictaggerlib/ui/TemplateHelp.ui

@@ -106,7 +106,7 @@ tr:nth-child(even) {
      <tr><td>{cover artist}</td><td>(string)</td></tr>
      <tr><td>{editor}</td><td>(string)</td></tr>
      <tr><td>{tags}</td><td>list of str</td></tr>
-     <tr><td>{pages}</td><td>list of dict({'Image': string(int), 'Type': string, 'Bookmark': string, 'DoublePage': string})</td></tr>
+     <tr><td>{pages}</td><td>list of dict({'Image': string(int), 'Type': string, 'Bookmark': string, 'DoublePage': boolean})</td></tr>
      <tr><td>{price}</td><td>float</td></tr>
      <tr><td>{is_version_of}</td><td>string</td></tr>
      <tr><td>{rights}</td><td>string</td></tr>

comictaggerlib/ui/settingswindow.ui

@@ -139,7 +139,7 @@
          <item row="0" column="0">
           <widget class="QLabel" name="label_5">
            <property name="text">
-            <string>&lt;html&gt;&lt;head/&gt;&lt;body&gt;&lt;p&gt;These settings are for the automatic issue identifier which searches online for matches. They will not affect &amp;quot;manual&amp;quot; searching.&lt;/p&gt;&lt;p&gt;Hover the mouse over an entry field for more info.&lt;/p&gt;&lt;/body&gt;&lt;/html&gt;</string>
+            <string>&lt;html&gt;&lt;head/&gt;&lt;body&gt;&lt;p&gt;These settings are for the automatic issue identifier which searches online for matches. &lt;/p&gt;&lt;p&gt;Hover the mouse over an entry field for more info.&lt;/p&gt;&lt;/body&gt;&lt;/html&gt;</string>
            </property>
            <property name="wordWrap">
             <bool>true</bool>
@@ -164,47 +164,28 @@
               <string/>
              </property>
              <property name="text">
-              <string>Default Name Length Match Tolerance:</string>
+              <string>Default Name Match Ratio Threshold: Search:</string>
              </property>
             </widget>
            </item>
-           <item row="0" column="1">
-            <widget class="QLineEdit" name="leNameLengthDeltaThresh">
-             <property name="sizePolicy">
-              <sizepolicy hsizetype="Maximum" vsizetype="Fixed">
-               <horstretch>0</horstretch>
-               <verstretch>0</verstretch>
-              </sizepolicy>
+           <item row="1" column="0">
+            <widget class="QLabel" name="label">
+             <property name="text">
+              <string>Default Name Match Ratio Threshold: Auto-Identify:</string>
              </property>
-             <property name="maximumSize">
-              <size>
-               <width>50</width>
-               <height>16777215</height>
-              </size>
-             </property>
-             <property name="toolTip">
-              <string/>
+             <property name="alignment">
+              <set>Qt::AlignRight|Qt::AlignTrailing|Qt::AlignVCenter</set>
              </property>
             </widget>
            </item>
            <item row="2" column="0">
-            <widget class="QLabel" name="label_4">
+            <widget class="QLabel" name="label_9">
              <property name="text">
-              <string>Publisher Filter:</string>
+              <string>Always use Publisher Filter on &quot;manual&quot; searches:</string>
              </property>
             </widget>
            </item>
            <item row="2" column="1">
-            <widget class="QPlainTextEdit" name="tePublisherFilter">
-             <property name="sizePolicy">
-              <sizepolicy hsizetype="Expanding" vsizetype="Expanding">
-               <horstretch>0</horstretch>
-               <verstretch>0</verstretch>
-              </sizepolicy>
-             </property>
-            </widget>
-           </item>
-           <item row="1" column="1">
             <widget class="QCheckBox" name="cbxUseFilter">
              <property name="toolTip">
               <string>&lt;html&gt;&lt;head/&gt;&lt;body&gt;&lt;p&gt;Applies the &lt;span style=&quot; font-weight:600;&quot;&gt;Publisher Filter&lt;/span&gt; on all searches.&lt;br/&gt;The search window has a dynamic toggle to show the unfiltered results.&lt;/p&gt;&lt;/body&gt;&lt;/html&gt;</string>
@@ -214,10 +195,58 @@
              </property>
             </widget>
            </item>
-           <item row="1" column="0">
-            <widget class="QLabel" name="label_9">
+           <item row="3" column="0">
+            <widget class="QLabel" name="label_4">
              <property name="text">
-              <string>Always use Publisher Filter on &quot;manual&quot; searches:</string>
+              <string>Publisher Filter:</string>
+             </property>
+            </widget>
+           </item>
+           <item row="3" column="1">
+            <widget class="QPlainTextEdit" name="tePublisherFilter">
+             <property name="sizePolicy">
+              <sizepolicy hsizetype="Expanding" vsizetype="Expanding">
+               <horstretch>0</horstretch>
+               <verstretch>0</verstretch>
+              </sizepolicy>
+             </property>
+            </widget>
+           </item>
+           <item row="0" column="1">
+            <widget class="QSpinBox" name="sbNameMatchSearchThresh">
+             <property name="maximumSize">
+              <size>
+               <width>60</width>
+               <height>16777215</height>
+              </size>
+             </property>
+             <property name="suffix">
+              <string>%</string>
+             </property>
+             <property name="minimum">
+              <number>1</number>
+             </property>
+             <property name="maximum">
+              <number>100</number>
+             </property>
+            </widget>
+           </item>
+           <item row="1" column="1">
+            <widget class="QSpinBox" name="sbNameMatchIdentifyThresh">
+             <property name="maximumSize">
+              <size>
+               <width>60</width>
+               <height>16777215</height>
+              </size>
+             </property>
+             <property name="suffix">
+              <string>%</string>
+             </property>
+             <property name="minimum">
+              <number>1</number>
+             </property>
+             <property name="maximum">
+              <number>100</number>
              </property>
             </widget>
            </item>
@@ -591,6 +620,9 @@ By default only removes restricted characters and filenames for the current Oper
              </property>
             </widget>
            </item>
+           <item row="10" column="1">
+            <widget class="QLabel" name="lblDir"/>
+           </item>
           </layout>
          </item>
         </layout>

comictaggerlib/volumeselectionwindow.py

@@ -19,7 +19,7 @@ import itertools
 import logging
 from collections import deque
 
-from PyQt5 import QtCore, QtWidgets, uic
+from PyQt5 import QtCore, QtGui, QtWidgets, uic
 from PyQt5.QtCore import pyqtSignal
 
 from comicapi import utils
@@ -43,7 +43,14 @@ class SearchThread(QtCore.QThread):
     searchComplete = pyqtSignal()
     progressUpdate = pyqtSignal(int, int)
 
-    def __init__(self, talker_api: ComicTalker, series_name: str, refresh: bool, literal: bool = False) -> None:
+    def __init__(
+        self,
+        talker_api: ComicTalker,
+        series_name: str,
+        refresh: bool,
+        literal: bool = False,
+        series_match_thresh: int = 90,
+    ) -> None:
         QtCore.QThread.__init__(self)
         self.talker_api = talker_api
         self.series_name = series_name
@@ -52,6 +59,7 @@ class SearchThread(QtCore.QThread):
         self.ct_error = False
         self.ct_search_results: list[ComicVolume] = []
         self.literal = literal
+        self.series_match_thresh = series_match_thresh
 
     def run(self) -> None:
         try:
@@ -326,7 +334,9 @@ class VolumeSelectionWindow(QtWidgets.QDialog):
         self.progdialog.canceled.connect(self.search_canceled)
         self.progdialog.setModal(True)
         self.progdialog.setMinimumDuration(300)
-        self.search_thread = SearchThread(self.talker_api, self.series_name, refresh, self.literal)
+        self.search_thread = SearchThread(
+            self.talker_api, self.series_name, refresh, self.literal, self.settings.id_series_match_search_thresh
+        )
         self.search_thread.searchComplete.connect(self.search_complete)
         self.search_thread.progressUpdate.connect(self.search_progress_update)
         self.search_thread.start()
@@ -408,7 +418,7 @@ class VolumeSelectionWindow(QtWidgets.QDialog):
 
                     deques: list[deque[ComicVolume]] = [deque(), deque(), deque()]
 
-                    def categorize(result):
+                    def categorize(result: ComicVolume) -> int:
                         # We don't remove anything on this one so that we only get exact matches
                         if utils.sanitize_title(result["name"], True).casefold() == sanitized_no_articles:
                             return 0
@@ -468,15 +478,16 @@ class VolumeSelectionWindow(QtWidgets.QDialog):
             self.twList.selectRow(0)
             self.twList.resizeColumnsToContents()
 
-            if not self.ct_search_results:
-                QtCore.QCoreApplication.processEvents()
-                QtWidgets.QMessageBox.information(self, "Search Result", "No matches found!")
-                QtCore.QTimer.singleShot(200, self.close_me)
+    def showEvent(self, event: QtGui.QShowEvent) -> None:
+        if not self.ct_search_results:
+            QtCore.QCoreApplication.processEvents()
+            QtWidgets.QMessageBox.information(self, "Search Result", "No matches found!")
+            QtCore.QTimer.singleShot(200, self.close_me)
 
-            if self.immediate_autoselect and self.ct_search_results:
-                # defer the immediate autoselect so this dialog has time to pop up
-                QtCore.QCoreApplication.processEvents()
-                QtCore.QTimer.singleShot(10, self.do_immediate_autoselect)
+        elif self.immediate_autoselect:
+            # defer the immediate autoselect so this dialog has time to pop up
+            QtCore.QCoreApplication.processEvents()
+            QtCore.QTimer.singleShot(10, self.do_immediate_autoselect)
 
     def do_immediate_autoselect(self) -> None:
         self.immediate_autoselect = False

comictalker/comiccacher.py

@@ -84,7 +84,8 @@ class ComicCacher:
                 + "image_url TEXT,"
                 + "description TEXT,"
                 + "timestamp DATE DEFAULT (datetime('now','localtime')),"
-                + "source_name TEXT NOT NULL)"
+                + "source_name TEXT NOT NULL,"
+                + "aliases TEXT)"  # Newline separated
             )
 
             cur.execute(
@@ -96,6 +97,7 @@ class ComicCacher:
                 + "start_year INT,"
                 + "timestamp DATE DEFAULT (datetime('now','localtime')), "
                 + "source_name TEXT NOT NULL,"
+                + "aliases TEXT,"  # Newline separated
                 + "PRIMARY KEY (id, source_name))"
             )
 
@@ -105,6 +107,7 @@ class ComicCacher:
                 + "url_list TEXT,"
                 + "timestamp DATE DEFAULT (datetime('now','localtime')), "
                 + "source_name TEXT NOT NULL,"
+                + "aliases TEXT,"  # Newline separated
                 + "PRIMARY KEY (issue_id, source_name))"
             )
 
@@ -121,11 +124,11 @@ class ComicCacher:
                 + "description TEXT,"
                 + "timestamp DATE DEFAULT (datetime('now','localtime')), "
                 + "source_name TEXT NOT NULL,"
+                + "aliases TEXT,"  # Newline separated
                 + "PRIMARY KEY (id, source_name))"
             )
 
     def add_search_results(self, source_name: str, search_term: str, ct_search_results: list[ComicVolume]) -> None:
-
         con = lite.connect(self.db_file)
 
         with con:
@@ -133,16 +136,18 @@ class ComicCacher:
             cur = con.cursor()
 
             # remove all previous entries with this search term
-            cur.execute("DELETE FROM VolumeSearchCache WHERE search_term = ?", [search_term.casefold()])
+            cur.execute(
+                "DELETE FROM VolumeSearchCache WHERE search_term = ? AND source_name = ?",
+                [search_term.casefold(), source_name],
+            )
 
             # now add in new results
             for record in ct_search_results:
 
                 cur.execute(
                     "INSERT INTO VolumeSearchCache "
-                    + "(source_name, search_term, id, name, start_year, publisher, count_of_issues, image_url, "
-                    + "description) "
-                    + "VALUES(?, ?, ?, ?, ?, ?, ?, ?, ?)",
+                    + "(source_name, search_term, id, name, start_year, publisher, count_of_issues, image_url, description, aliases) "
+                    + "VALUES(?, ?, ?, ?, ?, ?, ?, ?, ?, ?)",
                     (
                         source_name,
                         search_term.casefold(),
@@ -153,11 +158,11 @@ class ComicCacher:
                         record["count_of_issues"],
                         record["image"],
                         record["description"],
+                        record["aliases"],
                     ),
                 )
 
     def get_search_results(self, source_name: str, search_term: str) -> list[ComicVolume]:
-
         results = []
         con = lite.connect(self.db_file)
         with con:
@@ -184,7 +189,7 @@ class ComicCacher:
                     description=record[7],
                     publisher=record[4],
                     image=record[6],
-                    #  "source": record[9],  # Not needed?
+                    aliases=record[10],
                 )
 
                 results.append(result)
@@ -202,7 +207,7 @@ class ComicCacher:
             # remove all previous entries with this search term
             cur.execute("DELETE FROM AltCovers WHERE issue_id=? AND source_name=?", [issue_id, source_name])
 
-            url_list_str = ", ".join(url_list)
+            url_list_str = ",".join(url_list)
             # now add in new record
             cur.execute(
                 "INSERT INTO AltCovers (source_name, issue_id, url_list) VALUES(?, ?, ?)",
@@ -227,16 +232,12 @@ class ComicCacher:
                 return []
 
             url_list_str = row[0]
-            if len(url_list_str) == 0:
+            if not url_list_str:
                 return []
-            raw_list = url_list_str.split(",")
-            url_list = []
-            for item in raw_list:
-                url_list.append(str(item).strip())
+            url_list = str(url_list_str).split(",")
             return url_list
 
     def add_volume_info(self, source_name: str, volume_record: ComicVolume) -> None:
-
         con = lite.connect(self.db_file)
 
         with con:
@@ -253,11 +254,11 @@ class ComicCacher:
                 "count_of_issues": volume_record["count_of_issues"],
                 "start_year": volume_record["start_year"],
                 "timestamp": timestamp,
+                "aliases": volume_record["aliases"],
             }
             self.upsert(cur, "volumes", data)
 
     def add_volume_issues_info(self, source_name: str, volume_id: int, volume_issues: list[ComicIssue]) -> None:
-
         con = lite.connect(self.db_file)
 
         with con:
@@ -280,11 +281,11 @@ class ComicCacher:
                     "thumb_url": issue["image_thumb"],
                     "description": issue["description"],
                     "timestamp": timestamp,
+                    "aliases": issue["aliases"],
                 }
                 self.upsert(cur, "issues", data)
 
     def get_volume_info(self, volume_id: int, source_name: str) -> ComicVolume | None:
-
         result: ComicVolume | None = None
 
         con = lite.connect(self.db_file)
@@ -298,7 +299,8 @@ class ComicCacher:
 
             # fetch
             cur.execute(
-                "SELECT source_name,id,name,publisher,count_of_issues,start_year FROM Volumes WHERE id=? AND source_name=?",
+                "SELECT source_name,id,name,publisher,count_of_issues,start_year,aliases FROM Volumes"
+                " WHERE id=? AND source_name=?",
                 [volume_id, source_name],
             )
 
@@ -309,18 +311,17 @@ class ComicCacher:
 
             # since ID is primary key, there is only one row
             result = ComicVolume(
-                # source_name: row[0],
                 id=row[1],
                 name=row[2],
                 count_of_issues=row[4],
                 start_year=row[5],
                 publisher=row[3],
+                aliases=row[6],
             )
 
         return result
 
     def get_volume_issues_info(self, volume_id: int, source_name: str) -> list[ComicIssue]:
-
         con = lite.connect(self.db_file)
         with con:
             cur = con.cursor()
@@ -336,8 +337,8 @@ class ComicCacher:
 
             cur.execute(
                 (
-                    "SELECT source_name,id,name,issue_number,site_detail_url,cover_date,super_url,thumb_url,description"
-                    + " FROM Issues WHERE volume_id=? AND source_name=?"
+                    "SELECT source_name,id,name,issue_number,site_detail_url,cover_date,super_url,thumb_url,description,aliases"
+                    " FROM Issues WHERE volume_id=? AND source_name=?"
                 ),
                 [volume_id, source_name],
             )
@@ -352,9 +353,9 @@ class ComicCacher:
                     site_detail_url=row[4],
                     cover_date=row[5],
                     image=row[6],
-                    image_thumb=row[7],
                     description=row[8],
                     volume={"id": volume_id, "name": row[2]},
+                    aliases=row[9],
                 )
 
                 results.append(record)
@@ -362,7 +363,13 @@ class ComicCacher:
         return results
 
     def add_issue_select_details(
-        self, issue_id: int, image_url: str, thumb_image_url: str, cover_date: str, site_detail_url: str
+        self,
+        source_name: str,
+        issue_id: int,
+        image_url: str,
+        thumb_image_url: str,
+        cover_date: str,
+        site_detail_url: str,
     ) -> None:
 
         con = lite.connect(self.db_file)
@@ -374,6 +381,7 @@ class ComicCacher:
 
             data = {
                 "id": issue_id,
+                "source_name": source_name,
                 "super_url": image_url,
                 "thumb_url": thumb_image_url,
                 "cover_date": cover_date,
@@ -390,7 +398,7 @@ class ComicCacher:
             con.text_factory = str
 
             cur.execute(
-                "SELECT super_url,thumb_url,cover_date,site_detail_url FROM Issues WHERE id=? " + "AND source_name=?",
+                "SELECT super_url,thumb_url,cover_date,site_detail_url FROM Issues WHERE id=? AND source_name=?",
                 [issue_id, source_name],
             )
             row = cur.fetchone()

comictalker/resulttypes.py

@@ -11,6 +11,7 @@ class SelectDetails(TypedDict):
 
 
 class ComicVolume(TypedDict, total=False):
+    aliases: str  # Newline separated
     count_of_issues: int
     description: str
     id: Required[int]
@@ -21,6 +22,7 @@ class ComicVolume(TypedDict, total=False):
 
 
 class ComicIssue(TypedDict, total=False):
+    aliases: str  # Newline separated
     cover_date: str
     description: str
     id: int

comictalker/talkers/comicvine.py

@@ -99,6 +99,7 @@ class CVPersonCredits(TypedDict):
 
 
 class CVVolumeResults(TypedDict):
+    aliases: str
     count_of_issues: int
     description: str
     id: int
@@ -128,6 +129,7 @@ class CVResult(TypedDict):
 
 
 class CVIssuesResults(TypedDict):
+    aliases: str
     cover_date: str
     description: str
     id: int
@@ -186,7 +188,7 @@ class CVIssueDetailResults(TypedDict):
 
 
 class ComicVineTalker(TalkerBase):
-    def __init__(self) -> None:
+    def __init__(self, series_match_thresh: int = 90) -> None:
         super().__init__()
         self.source_details = source_details = SourceDetails(
             name="Comic Vine",
@@ -256,11 +258,9 @@ class ComicVineTalker(TalkerBase):
                 ),
             },
         )
-
         # Identity name for the information source
         self.source_name = self.source_details.id
         self.source_name_friendly = self.source_details.name
-
         # Overwrite any source_details.options that have saved settings
         source_settings = ComicTaggerSettings.get_source_settings(
             self.source_name, self.source_details.settings_options
@@ -268,7 +268,6 @@ class ComicVineTalker(TalkerBase):
         if not source_settings:
             # No saved settings, do something?
             ...
-
         self.wait_for_rate_limit = source_details.settings_options["wait_on_ratelimit"]["value"]
         self.wait_for_rate_limit_time = source_details.settings_options["ratelimit_waittime"]["value"]
 
@@ -277,6 +276,8 @@ class ComicVineTalker(TalkerBase):
         self.api_key = source_details.settings_options["api_key"]["value"]
         self.api_base_url = source_details.settings_options["url_root"]["value"]
 
+        self.series_match_thresh = series_match_thresh
+
         # Used for async cover loading etc.
         if qt_available:
             self.nam = QtNetwork.QNetworkAccessManager()
@@ -387,6 +388,7 @@ class ComicVineTalker(TalkerBase):
 
             formatted_results.append(
                 ComicVolume(
+                    aliases=record["aliases"],
                     count_of_issues=record.get("count_of_issues", 0),
                     description=record.get("description", ""),
                     id=record["id"],
@@ -412,6 +414,7 @@ class ComicVineTalker(TalkerBase):
 
             formatted_results.append(
                 ComicIssue(
+                    aliases=record["aliases"],
                     cover_date=record.get("cover_date", ""),
                     description=record.get("description", ""),
                     id=record["id"],
@@ -452,7 +455,7 @@ class ComicVineTalker(TalkerBase):
             "format": "json",
             "resources": "volume",
             "query": search_series_name,
-            "field_list": "volume,name,id,start_year,publisher,image,description,count_of_issues",
+            "field_list": "volume,name,id,start_year,publisher,image,description,count_of_issues,aliases",
             "page": 1,
             "limit": 100,
         }
@@ -470,10 +473,8 @@ class ComicVineTalker(TalkerBase):
         # ORed together, and we get thousands of results.  Good news is the
         # results are sorted by relevance, so we can be smart about halting the search.
         # 1. Don't fetch more than some sane amount of pages.
-        max_results = 500
-        # 2. Halt when not all of our search terms are present in a result
-        # 3. Halt when the results contain more (plus threshold) words than our search
-        result_word_count_max = len(search_series_name.split()) + 3
+        # 2. Halt when any result on the current page is less than or equal to a set ratio using thefuzz
+        max_results = 500  # 5 pages
 
         total_result_count = min(total_result_count, max_results)
 
@@ -488,23 +489,14 @@ class ComicVineTalker(TalkerBase):
             callback(current_result_count, total_result_count)
 
         # see if we need to keep asking for more pages...
-        stop_searching = False
         while current_result_count < total_result_count:
 
             if not literal:
-                # Sanitize the series name for comicvine searching, comicvine search ignore symbols
-                last_result = utils.sanitize_title(search_results[-1]["name"])
-
-                # See if the last result's name has all the of the search terms.
-                # If not, break out of this, loop, we're done.
-                for term in search_series_name.split():
-                    if term not in last_result:
-                        stop_searching = True
-                        break
-
-                # Also, stop searching when the word count of last results is too much longer than our search terms list
-                if len(last_result) > result_word_count_max:
-                    stop_searching = True
+                # Stop searching once any entry falls below the threshold
+                stop_searching = any(
+                    not utils.titles_match(search_series_name, volume["name"], self.series_match_thresh)
+                    for volume in cast(list[CVVolumeResults], cv_response["results"])
+                )
 
                 if stop_searching:
                     break
@@ -522,17 +514,6 @@ class ComicVineTalker(TalkerBase):
             if callback is not None:
                 callback(current_result_count, total_result_count)
 
-        # Literal searches simply return the matches no extra processing is doneo
-        if not literal:
-            # Remove any search results that don't contain all the search terms (iterate backwards for easy removal)
-            for record in reversed(search_results):
-                # Sanitize the series name for comicvine searching, comicvine search ignore symbols
-                record_name = utils.sanitize_title(record["name"])
-                for term in search_series_name.split():
-                    if term not in record_name:
-                        search_results.remove(record)
-                        break
-
         # Format result to ComicSearchResult
         formatted_search_results = self.format_search_results(search_results)
 
@@ -573,7 +554,7 @@ class ComicVineTalker(TalkerBase):
         params = {
             "api_key": self.api_key,
             "format": "json",
-            "field_list": "name,id,start_year,publisher,count_of_issues",
+            "field_list": "name,id,start_year,publisher,count_of_issues,aliases",
         }
         cv_response = self.get_cv_content(volume_url, params)
 
@@ -597,7 +578,7 @@ class ComicVineTalker(TalkerBase):
             "api_key": self.api_key,
             "filter": "volume:" + str(series_id),
             "format": "json",
-            "field_list": "id,volume,issue_number,name,image,cover_date,site_detail_url,description",
+            "field_list": "id,volume,issue_number,name,image,cover_date,site_detail_url,description,aliases",
             "offset": 0,
         }
         cv_response = self.get_cv_content(self.api_base_url + "/issues/", params)
@@ -644,11 +625,11 @@ class ComicVineTalker(TalkerBase):
         params: dict[str, str | int] = {
             "api_key": self.api_key,
             "format": "json",
-            "field_list": "id,volume,issue_number,name,image,cover_date,site_detail_url,description",
+            "field_list": "id,volume,issue_number,name,image,cover_date,site_detail_url,description,aliases",
             "filter": flt,
         }
 
-        cv_response = self.get_cv_content(self.api_base_url + "/issues", params)
+        cv_response = self.get_cv_content(self.api_base_url + "/issues/", params)
 
         current_result_count = cv_response["number_of_page_results"]
         total_result_count = cv_response["number_of_total_results"]
@@ -680,7 +661,7 @@ class ComicVineTalker(TalkerBase):
 
         f_record = None
         for record in issues_list_results:
-            if IssueString(issue_number).as_string() is None:
+            if not IssueString(issue_number).as_string():
                 issue_number = "1"
             if (
                 IssueString(record["issue_number"]).as_string().casefold()
@@ -710,6 +691,7 @@ class ComicVineTalker(TalkerBase):
 
         volume_results = self.fetch_partial_volume_data(issue_results["volume"]["id"])
 
+        # Now, map the Comic Vine data to generic metadata
         md = self.map_cv_data_to_metadata(volume_results, issue_results)
         md.is_empty = False
         return md
@@ -949,12 +931,12 @@ class ComicVineTalker(TalkerBase):
         cv_response = self.get_cv_content(issue_url, params)
         results = cast(CVIssueDetailResults, cv_response["results"])
 
-        details: SelectDetails = {
-            "image_url": results["image"]["super_url"],
-            "thumb_image_url": results["image"]["thumb_url"],
-            "cover_date": results["cover_date"],
-            "site_detail_url": results["site_detail_url"],
-        }
+        details = SelectDetails(
+            image_url=results["image"]["super_url"],
+            thumb_image_url=results["image"]["thumb_url"],
+            cover_date=results["cover_date"],
+            site_detail_url=results["site_detail_url"],
+        )
 
         if (
             details["image_url"] is not None
@@ -981,7 +963,7 @@ class ComicVineTalker(TalkerBase):
         self, issue_id: int, image_url: str, thumb_url: str, cover_date: str, page_url: str
     ) -> None:
         cvc = ComicCacher()
-        cvc.add_issue_select_details(issue_id, image_url, thumb_url, cover_date, page_url)
+        cvc.add_issue_select_details(self.source_name, issue_id, image_url, thumb_url, cover_date, page_url)
 
     def fetch_alternate_cover_urls(self, issue_id: int, issue_page_url: str) -> list[str]:
         url_list = self.fetch_cached_alternate_cover_urls(issue_id)

requirements.txt

@@ -7,5 +7,6 @@ py7zr
 pycountry
 requests==2.*
 text2digits
+thefuzz[speedup]>=0.19.0
 typing_extensions
 wordninja

testing/comicdata.py

@@ -0,0 +1,140 @@
+from __future__ import annotations
+
+import comicapi.genericmetadata
+import comictaggerlib.resulttypes
+from comicapi import utils
+
+search_results = [
+    comictaggerlib.resulttypes.CVVolumeResults(
+        count_of_issues=1,
+        description="this is a description",
+        id=1,
+        image={"super_url": "https://test.org/image/1"},
+        name="test",
+        publisher=comictaggerlib.resulttypes.CVPublisher(name="test"),
+        start_year="",  # This is currently submitted as a string and returned as an int
+        aliases=None,
+    ),
+    comictaggerlib.resulttypes.CVVolumeResults(
+        count_of_issues=1,
+        description="this is a description",
+        id=1,
+        image={"super_url": "https://test.org/image/2"},
+        name="test 2",
+        publisher=comictaggerlib.resulttypes.CVPublisher(name="test"),
+        start_year="",  # This is currently submitted as a string and returned as an int
+        aliases=None,
+    ),
+]
+
+alt_covers = [
+    {"issue_id": 1, "url_list": ["https://test.org/image/1"]},
+    {"issue_id": 2, "url_list": ["https://test.org/image/2"]},
+]
+
+select_details = [
+    {
+        "issue_id": 1,
+        "image_url": "https://test.org/image/1",
+        "thumb_image_url": "https://test.org/thumb/1",
+        "cover_date": "1998",
+        "site_detail_url": "https://test.org/1",
+    },
+    {
+        "issue_id": 2,
+        "image_url": "https://test.org/image/2",
+        "thumb_image_url": "https://test.org/thumb/2",
+        "cover_date": "1998",
+        "site_detail_url": "https://test.org/2",
+    },
+]
+
+# Used to test GenericMetadata.overlay
+metadata = [
+    (
+        comicapi.genericmetadata.GenericMetadata(series="test", issue="2", title="never"),
+        comicapi.genericmetadata.md_test.replace(series="test", issue="2", title="never"),
+    ),
+    (
+        comicapi.genericmetadata.GenericMetadata(series="", issue="2", title="never"),
+        comicapi.genericmetadata.md_test.replace(series=None, issue="2", title="never"),
+    ),
+    (
+        comicapi.genericmetadata.GenericMetadata(),
+        comicapi.genericmetadata.md_test.copy(),
+    ),
+]
+
+metadata_keys = [
+    (
+        comicapi.genericmetadata.GenericMetadata(),
+        {
+            "issue_count": 6,
+            "issue_number": "1",
+            "month": 10,
+            "series": "Cory Doctorow's Futuristic Tales of the Here and Now",
+            "year": 2007,
+        },
+    ),
+    (
+        comicapi.genericmetadata.GenericMetadata(series="test"),
+        {
+            "issue_count": 6,
+            "issue_number": "1",
+            "month": 10,
+            "series": "test",
+            "year": 2007,
+        },
+    ),
+    (
+        comicapi.genericmetadata.GenericMetadata(series="test", issue="3"),
+        {
+            "issue_count": 6,
+            "issue_number": "3",
+            "month": 10,
+            "series": "test",
+            "year": 2007,
+        },
+    ),
+]
+
+credits = [
+    ("writer", "Dara Naraghi"),
+    ("writeR", "Dara Naraghi"),
+]
+
+imprints = [
+    ("marvel", ("", "Marvel")),
+    ("marvel comics", ("", "Marvel")),
+    ("aircel", ("Aircel Comics", "Marvel")),
+]
+
+additional_imprints = [
+    ("test", ("Test", "Marvel")),
+    ("temp", ("Temp", "DC Comics")),
+]
+
+all_imprints = imprints + additional_imprints
+
+seed_imprints = {
+    "Marvel": utils.ImprintDict(
+        "Marvel",
+        {
+            "marvel comics": "",
+            "aircel": "Aircel Comics",
+        },
+    )
+}
+
+additional_seed_imprints = {
+    "Marvel": utils.ImprintDict("Marvel", {"test": "Test"}),
+    "DC Comics": utils.ImprintDict("DC Comics", {"temp": "Temp"}),
+}
+
+all_seed_imprints = {
+    "Marvel": seed_imprints["Marvel"].copy(),
+    "DC Comics": additional_seed_imprints["DC Comics"].copy(),
+}
+all_seed_imprints["Marvel"].update(additional_seed_imprints["Marvel"])
+
+conflicting_seed_imprints = {"Marvel": {"test": "Never"}}

testing/comicvine.py

@@ -0,0 +1,222 @@
+from __future__ import annotations
+
+from typing import Any
+
+import comicapi.genericmetadata
+import comictaggerlib.comicvinetalker
+
+
+def filter_field_list(cv_result, kwargs):
+    if "field_list" in kwargs["params"]:
+        for key in list(cv_result.keys()):
+            if key not in kwargs["params"]["field_list"]:
+                del cv_result[key]
+
+
+cv_issue_result: dict[str, Any] = {
+    "error": "OK",
+    "limit": 1,
+    "offset": 0,
+    "number_of_page_results": 1,
+    "number_of_total_results": 1,
+    "status_code": 1,
+    "results": {
+        "aliases": None,
+        "api_detail_url": "https://comicvine.gamespot.com/api/issue/4000-140529/",
+        "associated_images": [],
+        "character_credits": [],
+        "character_died_in": [],
+        "concept_credits": [],
+        "cover_date": "2007-10-01",
+        "date_added": "2008-10-16 05:25:47",
+        "date_last_updated": "2010-06-09 18:05:49",
+        "deck": None,
+        "description": "<i>For 12-year-old Anda, getting paid real money to kill the characters of players who were cheating in her favorite online computer game was a win-win situation. Until she found out who was paying her, and what those characters meant to the livelihood of children around the world.</i>",
+        "first_appearance_characters": None,
+        "first_appearance_concepts": None,
+        "first_appearance_locations": None,
+        "first_appearance_objects": None,
+        "first_appearance_storyarcs": None,
+        "first_appearance_teams": None,
+        "has_staff_review": False,
+        "id": 140529,
+        "image": {
+            "icon_url": "https://comicvine.gamespot.com/a/uploads/square_avatar/0/574/585444-109004_20080707014047_large.jpg",
+            "medium_url": "https://comicvine.gamespot.com/a/uploads/scale_medium/0/574/585444-109004_20080707014047_large.jpg",
+            "screen_url": "https://comicvine.gamespot.com/a/uploads/screen_medium/0/574/585444-109004_20080707014047_large.jpg",
+            "screen_large_url": "https://comicvine.gamespot.com/a/uploads/screen_kubrick/0/574/585444-109004_20080707014047_large.jpg",
+            "small_url": "https://comicvine.gamespot.com/a/uploads/scale_small/0/574/585444-109004_20080707014047_large.jpg",
+            "super_url": "https://comicvine.gamespot.com/a/uploads/scale_large/0/574/585444-109004_20080707014047_large.jpg",
+            "thumb_url": "https://comicvine.gamespot.com/a/uploads/scale_avatar/0/574/585444-109004_20080707014047_large.jpg",
+            "tiny_url": "https://comicvine.gamespot.com/a/uploads/square_mini/0/574/585444-109004_20080707014047_large.jpg",
+            "original_url": "https://comicvine.gamespot.com/a/uploads/original/0/574/585444-109004_20080707014047_large.jpg",
+            "image_tags": "All Images",
+        },
+        "issue_number": "1",
+        "location_credits": [],
+        "name": "Anda's Game",
+        "object_credits": [],
+        "person_credits": [
+            {
+                "api_detail_url": "https://comicvine.gamespot.com/api/person/4040-56410/",
+                "id": 56410,
+                "name": "Dara Naraghi",
+                "site_detail_url": "https://comicvine.gamespot.com/dara-naraghi/4040-56410/",
+                "role": "writer",
+            },
+            {
+                "api_detail_url": "https://comicvine.gamespot.com/api/person/4040-57222/",
+                "id": 57222,
+                "name": "Esteve Polls",
+                "site_detail_url": "https://comicvine.gamespot.com/esteve-polls/4040-57222/",
+                "role": "artist",
+            },
+            {
+                "api_detail_url": "https://comicvine.gamespot.com/api/person/4040-48472/",
+                "id": 48472,
+                "name": "Neil Uyetake",
+                "site_detail_url": "https://comicvine.gamespot.com/neil-uyetake/4040-48472/",
+                "role": "letterer",
+            },
+            {
+                "api_detail_url": "https://comicvine.gamespot.com/api/person/4040-5329/",
+                "id": 5329,
+                "name": "Sam Kieth",
+                "site_detail_url": "https://comicvine.gamespot.com/sam-kieth/4040-5329/",
+                "role": "cover",
+            },
+            {
+                "api_detail_url": "https://comicvine.gamespot.com/api/person/4040-58534/",
+                "id": 58534,
+                "name": "Ted Adams",
+                "site_detail_url": "https://comicvine.gamespot.com/ted-adams/4040-58534/",
+                "role": "editor",
+            },
+        ],
+        "site_detail_url": "https://comicvine.gamespot.com/cory-doctorows-futuristic-tales-of-the-here-and-no/4000-140529/",
+        "store_date": None,
+        "story_arc_credits": [],
+        "team_credits": [],
+        "team_disbanded_in": [],
+        "volume": {
+            "api_detail_url": "https://comicvine.gamespot.com/api/volume/4050-23437/",
+            "id": 23437,
+            "name": "Cory Doctorow's Futuristic Tales of the Here and Now",
+            "site_detail_url": "https://comicvine.gamespot.com/cory-doctorows-futuristic-tales-of-the-here-and-no/4050-23437/",
+        },
+    },
+    "version": "1.0",
+}
+
+cv_volume_result: dict[str, Any] = {
+    "error": "OK",
+    "limit": 1,
+    "offset": 0,
+    "number_of_page_results": 1,
+    "number_of_total_results": 1,
+    "status_code": 1,
+    "results": {
+        "aliases": None,
+        "api_detail_url": "https://comicvine.gamespot.com/api/volume/4050-23437/",
+        "count_of_issues": 6,
+        "date_added": "2008-10-16 05:25:47",
+        "date_last_updated": "2012-01-18 17:21:57",
+        "deck": None,
+        "description": "<p>Writer and <em>BoingBoing.net</em> co-editor <strong>Cory Doctorow</strong> has won acclaim for his science-fiction writing as well as his Creative Commons presentation of his material. Now, IDW Publishing is proud to present six standalone stories adapted from Doctorow's work, each featuring cover art by some of comics' top talents.</p>",
+        "id": 23437,
+        "image": {
+            "icon_url": "https://comicvine.gamespot.com/a/uploads/square_avatar/0/574/585444-109004_20080707014047_large.jpg",
+            "medium_url": "https://comicvine.gamespot.com/a/uploads/scale_medium/0/574/585444-109004_20080707014047_large.jpg",
+            "screen_url": "https://comicvine.gamespot.com/a/uploads/screen_medium/0/574/585444-109004_20080707014047_large.jpg",
+            "screen_large_url": "https://comicvine.gamespot.com/a/uploads/screen_kubrick/0/574/585444-109004_20080707014047_large.jpg",
+            "small_url": "https://comicvine.gamespot.com/a/uploads/scale_small/0/574/585444-109004_20080707014047_large.jpg",
+            "super_url": "https://comicvine.gamespot.com/a/uploads/scale_large/0/574/585444-109004_20080707014047_large.jpg",
+            "thumb_url": "https://comicvine.gamespot.com/a/uploads/scale_avatar/0/574/585444-109004_20080707014047_large.jpg",
+            "tiny_url": "https://comicvine.gamespot.com/a/uploads/square_mini/0/574/585444-109004_20080707014047_large.jpg",
+            "original_url": "https://comicvine.gamespot.com/a/uploads/original/0/574/585444-109004_20080707014047_large.jpg",
+            "image_tags": "All Images",
+        },
+        "name": "Cory Doctorow's Futuristic Tales of the Here and Now",
+        "publisher": {
+            "api_detail_url": "https://comicvine.gamespot.com/api/publisher/4010-1190/",
+            "id": 1190,
+            "name": "IDW Publishing",
+        },
+        "site_detail_url": "https://comicvine.gamespot.com/cory-doctorows-futuristic-tales-of-the-here-and-no/4050-23437/",
+        "start_year": "2007",
+    },
+    "version": "1.0",
+}
+cv_not_found = {
+    "error": "Object Not Found",
+    "limit": 0,
+    "offset": 0,
+    "number_of_page_results": 0,
+    "number_of_total_results": 0,
+    "status_code": 101,
+    "results": [],
+}
+date = comictaggerlib.comicvinetalker.ComicVineTalker().parse_date_str(cv_issue_result["results"]["cover_date"])
+
+cv_md = comicapi.genericmetadata.GenericMetadata(
+    is_empty=False,
+    tag_origin=None,
+    series=cv_issue_result["results"]["volume"]["name"],
+    issue=cv_issue_result["results"]["issue_number"],
+    title=cv_issue_result["results"]["name"],
+    publisher=cv_volume_result["results"]["publisher"]["name"],
+    month=date[1],
+    year=date[2],
+    day=date[0],
+    issue_count=None,
+    volume=None,
+    genre=None,
+    language=None,
+    comments=comictaggerlib.comicvinetalker.ComicVineTalker().cleanup_html(
+        cv_issue_result["results"]["description"], False
+    ),
+    volume_count=None,
+    critical_rating=None,
+    country=None,
+    alternate_series=None,
+    alternate_number=None,
+    alternate_count=None,
+    imprint=None,
+    notes="Tagged with ComicTagger 1.4.4a9.dev20 using info from Comic Vine on 2022-07-11 17:42:41.  [Issue ID 140529]",
+    web_link=cv_issue_result["results"]["site_detail_url"],
+    format=None,
+    manga=None,
+    black_and_white=None,
+    page_count=None,
+    maturity_rating=None,
+    story_arc=None,
+    series_group=None,
+    scan_info=None,
+    characters="",
+    teams="",
+    locations="",
+    credits=[
+        comicapi.genericmetadata.CreditMetadata(person=x["name"], role=x["role"].title(), primary=False)
+        for x in cv_issue_result["results"]["person_credits"]
+    ],
+    tags=set(),
+    pages=[],
+    price=None,
+    is_version_of=None,
+    rights=None,
+    identifier=None,
+    last_mark=None,
+    cover_image=None,
+)
+
+
+class MockResponse:
+    """Mocks the response object from requests"""
+
+    def __init__(self, result: dict[str, Any], content=None) -> None:
+        self.status_code = 200
+        self.result = result
+        self.content = content
+
+    def json(self) -> dict[str, list]:
+        return self.result

testing/filenames.py

@@ -11,6 +11,16 @@ format is
 """
 from __future__ import annotations
 
+import os
+import os.path
+import pathlib
+from contextlib import nullcontext as does_not_raise
+
+import pytest
+
+datadir = pathlib.Path(__file__).parent / "data"
+cbz_path = datadir / "Cory Doctorow's Futuristic Tales of the Here and Now #001 - Anda's Game (2007).cbz"
+
 fnames = [
     (
         "batman 3 title (DC).cbz",
@@ -731,89 +741,125 @@ rnames = [
         False,
         "universal",
         "Cory Doctorow's Futuristic Tales of the Here and Now #001 - Anda's Game (2007).cbz",
+        does_not_raise(),
     ),
     (
         "{series} #{issue} - {title} ({year})({price})",  # price should be none, test no  space between ')('
         False,
         "universal",
         "Cory Doctorow's Futuristic Tales of the Here and Now #001 - Anda's Game (2007).cbz",
+        does_not_raise(),
     ),
     (
         "{series} #{issue} - {title} ({year})  ({price})",  # price should be none, test double space ')  ('
         False,
         "universal",
         "Cory Doctorow's Futuristic Tales of the Here and Now #001 - Anda's Game (2007).cbz",
+        does_not_raise(),
     ),
     (
         "{series} #{issue} - {title} ({year})",
         False,
         "universal",
         "Cory Doctorow's Futuristic Tales of the Here and Now #001 - Anda's Game (2007).cbz",
+        does_not_raise(),
     ),
     (
         "{series}: {title} #{issue} ({year})",  # on windows the ':' is replaced
         False,
         "universal",
         "Cory Doctorow's Futuristic Tales of the Here and Now - Anda's Game #001 (2007).cbz",
+        does_not_raise(),
     ),
     (
         "{series}: {title} #{issue} ({year})",  # on linux the ':' is preserved
         False,
         "Linux",
         "Cory Doctorow's Futuristic Tales of the Here and Now: Anda's Game #001 (2007).cbz",
+        does_not_raise(),
     ),
     (
         "{publisher}/  {series} #{issue} - {title} ({year})",  # leading whitespace is removed when moving
         True,
         "universal",
         "IDW Publishing/Cory Doctorow's Futuristic Tales of the Here and Now #001 - Anda's Game (2007).cbz",
+        does_not_raise(),
     ),
     (
         "{publisher}/  {series} #{issue} - {title} ({year})",  # leading whitespace is removed when only renaming
         False,
         "universal",
         "Cory Doctorow's Futuristic Tales of the Here and Now #001 - Anda's Game (2007).cbz",
+        does_not_raise(),
     ),
     (
         r"{publisher}\  {series} #{issue} - {title} ({year})",  # backslashes separate directories
         False,
         "universal",
         "Cory Doctorow's Futuristic Tales of the Here and Now #001 - Anda's Game (2007).cbz",
+        does_not_raise(),
     ),
     (
         "{series} #  {issue} - {title} ({year})",  # double spaces are reduced to one
         False,
         "universal",
         "Cory Doctorow's Futuristic Tales of the Here and Now # 001 - Anda's Game (2007).cbz",
+        does_not_raise(),
     ),
     (
         "{series} #  {issue} - {locations} ({year})",
         False,
         "universal",
         "Cory Doctorow's Futuristic Tales of the Here and Now # 001 - lonely cottage (2007).cbz",
+        does_not_raise(),
     ),
     (
         "{series} #{issue} - {title} - {WriteR}, {EDITOR} ({year})",  # fields are case in-sensitive
         False,
         "universal",
         "Cory Doctorow's Futuristic Tales of the Here and Now #001 - Anda's Game - Dara Naraghi, Ted Adams (2007).cbz",
+        does_not_raise(),
     ),
     (
         "{series} v{price} #{issue} ({year})",  # Remove previous text if value is ""
         False,
         "universal",
         "Cory Doctorow's Futuristic Tales of the Here and Now #001 (2007).cbz",
+        does_not_raise(),
     ),
     (
         "{series} {price} #{issue} ({year})",  # Ensure that a single space remains
         False,
         "universal",
         "Cory Doctorow's Futuristic Tales of the Here and Now #001 (2007).cbz",
+        does_not_raise(),
     ),
     (
         "{series} - {title}{price} #{issue} ({year})",  # Ensure removal before None values only impacts literal text
         False,
         "universal",
         "Cory Doctorow's Futuristic Tales of the Here and Now - Anda's Game #001 (2007).cbz",
+        does_not_raise(),
+    ),
+    (
+        "{series} - {title} {test} #{issue} ({year})",  # Test non-existent key
+        False,
+        "universal",
+        "Cory Doctorow's Futuristic Tales of the Here and Now - Anda's Game {test} #001 (2007).cbz",
+        does_not_raise(),
+    ),
+    (
+        "{series} - {title} {1} #{issue} ({year})",  # Test numeric key
+        False,
+        "universal",
+        "Cory Doctorow's Futuristic Tales of the Here and Now - Anda's Game {test} #001 (2007).cbz",
+        pytest.raises(ValueError),
     ),
 ]
+
+rfnames = [
+    (None, lambda x: x.path.parent.absolute()),
+    ("", lambda x: pathlib.Path(os.getcwd())),
+    ("test", lambda x: (pathlib.Path(os.getcwd()) / "test")),
+    (pathlib.Path(os.getcwd()) / "test", lambda x: pathlib.Path(os.getcwd()) / "test"),
+]

tests/autoimprint_test.py

@@ -3,59 +3,7 @@ from __future__ import annotations
 import pytest
 
 from comicapi import utils
-
-imprints = [
-    ("marvel", ("", "Marvel")),
-    ("marvel comics", ("", "Marvel")),
-    ("aircel", ("Aircel Comics", "Marvel")),
-]
-
-additional_imprints = [
-    ("test", ("Test", "Marvel")),
-    ("temp", ("Temp", "DC Comics")),
-]
-
-all_imprints = imprints + additional_imprints
-
-seed = {
-    "Marvel": utils.ImprintDict(
-        "Marvel",
-        {
-            "marvel comics": "",
-            "aircel": "Aircel Comics",
-        },
-    )
-}
-
-additional_seed = {
-    "Marvel": utils.ImprintDict("Marvel", {"test": "Test"}),
-    "DC Comics": utils.ImprintDict("DC Comics", {"temp": "Temp"}),
-}
-
-all_seed = {
-    "Marvel": seed["Marvel"].copy(),
-    "DC Comics": additional_seed["DC Comics"].copy(),
-}
-all_seed["Marvel"].update(additional_seed["Marvel"])
-
-conflicting_seed = {"Marvel": {"test": "Never"}}
-
-
-# manually seeds publishers
-@pytest.fixture
-def seed_publishers(monkeypatch):
-    publisher_seed = {}
-    for publisher, imprint in seed.items():
-        publisher_seed[publisher] = imprint
-    monkeypatch.setattr(utils, "publishers", publisher_seed)
-
-
-@pytest.fixture
-def seed_all_publishers(monkeypatch):
-    publisher_seed = {}
-    for publisher, imprint in all_seed.items():
-        publisher_seed[publisher] = imprint
-    monkeypatch.setattr(utils, "publishers", publisher_seed)
+from testing.comicdata import additional_seed_imprints, all_imprints, conflicting_seed_imprints, imprints, seed_imprints
 
 
 # test that that an empty list returns the input unchanged
@@ -73,14 +21,14 @@ def test_get_publisher(publisher: str, expected: tuple[str, str], seed_publisher
 # tests that update_publishers will initially set values
 @pytest.mark.parametrize("publisher, expected", imprints)
 def test_set_publisher(publisher: str, expected: tuple[str, str]):
-    utils.update_publishers(seed)
+    utils.update_publishers(seed_imprints)
     assert expected == utils.get_publisher(publisher)
 
 
 # tests that update_publishers will add to existing values
 @pytest.mark.parametrize("publisher, expected", all_imprints)
 def test_update_publisher(publisher: str, expected: tuple[str, str], seed_publishers):
-    utils.update_publishers(additional_seed)
+    utils.update_publishers(additional_seed_imprints)
     assert expected == utils.get_publisher(publisher)
 
 
@@ -88,6 +36,6 @@ def test_update_publisher(publisher: str, expected: tuple[str, str], seed_publis
 def test_conflict_publisher(seed_all_publishers):
     assert ("Test", "Marvel") == utils.get_publisher("test")
 
-    utils.update_publishers(conflicting_seed)
+    utils.update_publishers(conflicting_seed_imprints)
 
     assert ("Never", "Marvel") == utils.get_publisher("test")

tests/comicarchive_test.py

@@ -1,20 +1,17 @@
 from __future__ import annotations
 
-import pathlib
 import shutil
 
 import pytest
 
 import comicapi.comicarchive
 import comicapi.genericmetadata
-
-thisdir = pathlib.Path(__file__).parent
-cbz_path = thisdir / "data" / "Cory Doctorow's Futuristic Tales of the Here and Now #001 - Anda's Game (2007).cbz"
+from testing.filenames import datadir
 
 
 @pytest.mark.xfail(not comicapi.comicarchive.rar_support, reason="rar support")
 def test_getPageNameList():
-    c = comicapi.comicarchive.ComicArchive(thisdir / "data" / "fake_cbr.cbr")
+    c = comicapi.comicarchive.ComicArchive(datadir / "fake_cbr.cbr")
     pageNameList = c.get_page_name_list()
 
     assert pageNameList == [
@@ -27,67 +24,42 @@ def test_getPageNameList():
     ]
 
 
-def test_set_default_page_list(tmp_path):
-    md = comicapi.genericmetadata.GenericMetadata()
-    md.overlay(comicapi.genericmetadata.md_test)
-    md.pages = []
-    md.set_default_page_list(len(comicapi.genericmetadata.md_test.pages))
-
-    assert isinstance(md.pages[0]["Image"], int)
-
-
-def test_page_type_read():
-    c = comicapi.comicarchive.ComicArchive(cbz_path)
-    md = c.read_cix()
+def test_page_type_read(cbz):
+    md = cbz.read_cix()
 
     assert isinstance(md.pages[0]["Type"], str)
 
 
-def test_metadata_read():
-    c = comicapi.comicarchive.ComicArchive(
-        thisdir / "data" / "Cory Doctorow's Futuristic Tales of the Here and Now #001 - Anda's Game (2007).cbz"
-    )
-    md = c.read_cix()
+def test_metadata_read(cbz):
+    md = cbz.read_cix()
     assert md == comicapi.genericmetadata.md_test
 
 
-def test_save_cix(tmp_path):
-    comic_path = tmp_path / cbz_path.name
-    shutil.copy(cbz_path, comic_path)
+def test_save_cix(tmp_comic):
+    md = tmp_comic.read_cix()
+    md.set_default_page_list(tmp_comic.get_number_of_pages())
 
-    c = comicapi.comicarchive.ComicArchive(comic_path)
-    md = c.read_cix()
-    md.set_default_page_list(c.get_number_of_pages())
+    assert tmp_comic.write_cix(md)
 
-    assert c.write_cix(md)
-
-    md = c.read_cix()
+    md = tmp_comic.read_cix()
 
 
-def test_page_type_save(tmp_path):
-    comic_path = tmp_path / cbz_path.name
-
-    shutil.copy(cbz_path, comic_path)
-
-    c = comicapi.comicarchive.ComicArchive(comic_path)
-    md = c.read_cix()
+def test_page_type_save(tmp_comic):
+    md = tmp_comic.read_cix()
     t = md.pages[0]
     t["Type"] = ""
 
-    assert c.write_cix(md)
+    assert tmp_comic.write_cix(md)
 
-    md = c.read_cix()
+    md = tmp_comic.read_cix()
 
 
-def test_invalid_zip(tmp_path):
-    comic_path = tmp_path / cbz_path.name
+def test_invalid_zip(tmp_comic):
+    with open(tmp_comic.path, mode="b+r") as f:
+        f.write(b"PK\000\000")
 
-    with open(cbz_path, mode="b+r") as f:
-        comic_path.write_bytes(b"PK\003\004" + f.read()[4:].replace(b"PK\003\004", b"PK\000\000"))
-
-    c = comicapi.comicarchive.ComicArchive(comic_path)
-
-    assert not c.write_cix(comicapi.genericmetadata.md_test)
+    result = tmp_comic.write_cix(comicapi.genericmetadata.md_test)
+    assert not result
 
 
 archivers = [
@@ -102,10 +74,9 @@ archivers = [
 
 
 @pytest.mark.parametrize("archiver", archivers)
-def test_copy_to_archive(archiver, tmp_path):
-    comic_path = tmp_path / cbz_path.with_suffix("").name
+def test_copy_from_archive(archiver, tmp_path, cbz):
+    comic_path = tmp_path / cbz.path.with_suffix("").name
 
-    cbz = comicapi.comicarchive.ComicArchive(cbz_path)
     archive = archiver(comic_path)
 
     assert archive.copy_from_archive(cbz.archiver)
@@ -117,12 +88,3 @@ def test_copy_to_archive(archiver, tmp_path):
 
     md = comic_archive.read_cix()
     assert md == comicapi.genericmetadata.md_test
-
-    md = comicapi.genericmetadata.GenericMetadata()
-    md.overlay(comicapi.genericmetadata.md_test)
-    md.series = "test"
-
-    assert comic_archive.write_cix(md)
-
-    test_md = comic_archive.read_cix()
-    assert md == test_md

tests/comiccacher_test.py

@@ -0,0 +1,44 @@
+from __future__ import annotations
+
+import pytest
+
+import comictaggerlib.comiccacher
+import comictaggerlib.resulttypes
+from testing.comicdata import alt_covers, search_results, select_details
+
+
+def test_create_cache(settings):
+    comictaggerlib.comiccacher.ComicCacher()
+    assert (settings.get_settings_folder() / "settings").exists()
+
+
+def test_search_results(comic_cache):
+    comic_cache.add_search_results(
+        "test",
+        "test search",
+        search_results,
+    )
+    assert search_results == comic_cache.get_search_results("test", "test search")
+
+
+@pytest.mark.parametrize("alt_cover", alt_covers)
+def test_alt_covers(comic_cache, alt_cover):
+    comic_cache.add_alt_covers(**alt_cover, source_name="test")
+    assert alt_cover["url_list"] == comic_cache.get_alt_covers(issue_id=alt_cover["issue_id"], source_name="test")
+
+
+@pytest.mark.parametrize("volume_info", search_results)
+def test_volume_info(comic_cache, volume_info):
+    comic_cache.add_volume_info(cv_volume_record=volume_info, source_name="test")
+    vi = volume_info.copy()
+    del vi["description"]
+    del vi["image"]
+    assert vi == comic_cache.get_volume_info(volume_id=volume_info["id"], source_name="test")
+
+
+@pytest.mark.parametrize("details", select_details)
+def test_issue_select_details(comic_cache, details):
+    comic_cache.add_issue_select_details(**details, source_name="test")
+    det = details.copy()
+    del det["issue_id"]
+    assert det == comic_cache.get_issue_select_details(details["issue_id"], "test")

tests/comicvinetalker_test.py

@@ -0,0 +1,101 @@
+from __future__ import annotations
+
+import pytest
+
+import comicapi.genericmetadata
+import comictaggerlib.comicvinetalker
+import testing.comicvine
+from testing.comicdata import select_details
+
+
+def test_search_for_series(comicvine_api, comic_cache):
+    ct = comictaggerlib.comicvinetalker.ComicVineTalker()
+    results = ct.search_for_series("cory doctorows futuristic tales of the here and now")
+    for r in results:
+        r["image"] = {"super_url": r["image"]["super_url"]}
+        r["start_year"] = int(r["start_year"])
+        del r["publisher"]["id"]
+        del r["publisher"]["api_detail_url"]
+    cache_issues = comic_cache.get_search_results(ct.source_name, "cory doctorows futuristic tales of the here and now")
+    assert results == cache_issues
+
+
+def test_fetch_volume_data(comicvine_api, comic_cache):
+    ct = comictaggerlib.comicvinetalker.ComicVineTalker()
+    result = ct.fetch_volume_data(23437)
+    result["start_year"] = int(result["start_year"])
+    del result["publisher"]["id"]
+    del result["publisher"]["api_detail_url"]
+    assert result == comic_cache.get_volume_info(23437, ct.source_name)
+
+
+def test_fetch_issues_by_volume(comicvine_api, comic_cache):
+    ct = comictaggerlib.comicvinetalker.ComicVineTalker()
+    results = ct.fetch_issues_by_volume(23437)
+    cache_issues = comic_cache.get_volume_issues_info(23437, ct.source_name)
+    for r in results:
+        r["image"] = {"super_url": r["image"]["super_url"], "thumb_url": r["image"]["thumb_url"]}
+        del r["volume"]
+    assert results == cache_issues
+
+
+def test_fetch_issue_data_by_issue_id(comicvine_api, settings, mock_now, mock_version):
+    ct = comictaggerlib.comicvinetalker.ComicVineTalker()
+    result = ct.fetch_issue_data_by_issue_id(140529, settings)
+    assert result == testing.comicvine.cv_md
+
+
+def test_fetch_issues_by_volume_issue_num_and_year(comicvine_api):
+    ct = comictaggerlib.comicvinetalker.ComicVineTalker()
+    results = ct.fetch_issues_by_volume_issue_num_and_year([23437], "1", None)
+    cv_expected = testing.comicvine.cv_issue_result["results"].copy()
+    testing.comicvine.filter_field_list(
+        cv_expected,
+        {"params": {"field_list": "id,volume,issue_number,name,image,cover_date,site_detail_url,description,aliases"}},
+    )
+    for r, e in zip(results, [cv_expected]):
+        assert r == e
+
+
+cv_issue = [
+    (23437, "", testing.comicvine.cv_md),
+    (23437, "1", testing.comicvine.cv_md),
+    (23437, "0", comicapi.genericmetadata.GenericMetadata()),
+]
+
+
+@pytest.mark.parametrize("volume_id, issue_number, expected", cv_issue)
+def test_fetch_issue_data(comicvine_api, settings, mock_now, mock_version, volume_id, issue_number, expected):
+    ct = comictaggerlib.comicvinetalker.ComicVineTalker()
+    results = ct.fetch_issue_data(volume_id, issue_number, settings)
+    assert results == expected
+
+
+def test_fetch_issue_select_details(comicvine_api, mock_now, mock_version):
+    ct = comictaggerlib.comicvinetalker.ComicVineTalker()
+    result = ct.fetch_issue_select_details(140529)
+    expected = {
+        "cover_date": testing.comicvine.cv_issue_result["results"]["cover_date"],
+        "site_detail_url": testing.comicvine.cv_issue_result["results"]["site_detail_url"],
+        "image_url": testing.comicvine.cv_issue_result["results"]["image"]["super_url"],
+        "thumb_image_url": testing.comicvine.cv_issue_result["results"]["image"]["thumb_url"],
+    }
+    assert result == expected
+
+
+@pytest.mark.parametrize("details", select_details)
+def test_issue_select_details(comic_cache, details):
+    expected = details.copy()
+    del expected["issue_id"]
+
+    ct = comictaggerlib.comicvinetalker.ComicVineTalker()
+    ct.cache_issue_select_details(
+        issue_id=details["issue_id"],
+        image_url=details["image_url"],
+        thumb_url=details["thumb_image_url"],
+        cover_date=details["cover_date"],
+        page_url=details["site_detail_url"],
+    )
+    result = comic_cache.get_issue_select_details(details["issue_id"], ct.source_name)
+
+    assert result == expected

tests/conftest.py

@@ -0,0 +1,169 @@
+from __future__ import annotations
+
+import copy
+import datetime
+import io
+import shutil
+import unittest.mock
+from typing import Any, Generator
+
+import pytest
+import requests
+from PIL import Image
+
+import comicapi.comicarchive
+import comicapi.genericmetadata
+import comictaggerlib.comiccacher
+import comictaggerlib.comicvinetalker
+import comictaggerlib.settings
+from comicapi import utils
+from testing import comicvine, filenames
+from testing.comicdata import all_seed_imprints, seed_imprints
+
+
+@pytest.fixture
+def cbz():
+    yield comicapi.comicarchive.ComicArchive(filenames.cbz_path)
+
+
+@pytest.fixture
+def tmp_comic(tmp_path):
+    shutil.copy(filenames.cbz_path, tmp_path)
+    yield comicapi.comicarchive.ComicArchive(tmp_path / filenames.cbz_path.name)
+
+
+@pytest.fixture
+def cbz_double_cover(tmp_path, tmp_comic):
+
+    cover = Image.open(io.BytesIO(tmp_comic.get_page(0)))
+
+    other_page = Image.open(io.BytesIO(tmp_comic.get_page(tmp_comic.get_number_of_pages() - 1)))
+
+    double_cover = Image.new("RGB", (cover.width * 2, cover.height))
+    double_cover.paste(other_page, (0, 0))
+    double_cover.paste(cover, (cover.width, 0))
+
+    tmp_comic.archiver.write_file("double_cover.jpg", double_cover.tobytes("jpeg", "RGB"))
+    yield tmp_comic
+
+
+@pytest.fixture(autouse=True)
+def no_requests(monkeypatch) -> None:
+    """Remove requests.sessions.Session.request for all tests."""
+    monkeypatch.delattr("requests.sessions.Session.request")
+
+
+@pytest.fixture
+def comicvine_api(monkeypatch, cbz, comic_cache) -> unittest.mock.Mock:
+    # Any arguments may be passed and mock_get() will always return our
+    # mocked object, which only has the .json() method or None for invalid urls.
+
+    def make_list(cv_result):
+        cv_list = copy.deepcopy(cv_result)
+        if isinstance(cv_list["results"], dict):
+            cv_list["results"] = [cv_list["results"]]
+        return cv_list
+
+    def mock_get(*args, **kwargs):
+
+        if args:
+            if args[0].startswith("https://comicvine.gamespot.com/api/volume/4050-23437"):
+                cv_result = copy.deepcopy(comicvine.cv_volume_result)
+                comicvine.filter_field_list(cv_result["results"], kwargs)
+                return comicvine.MockResponse(cv_result)
+            if args[0].startswith("https://comicvine.gamespot.com/api/issue/4000-140529"):
+                return comicvine.MockResponse(comicvine.cv_issue_result)
+            if (
+                args[0].startswith("https://comicvine.gamespot.com/api/issues/")
+                and "params" in kwargs
+                and "filter" in kwargs["params"]
+                and "23437" in kwargs["params"]["filter"]
+            ):
+                cv_list = make_list(comicvine.cv_issue_result)
+                for cv in cv_list["results"]:
+                    comicvine.filter_field_list(cv, kwargs)
+                return comicvine.MockResponse(cv_list)
+            if (
+                args[0].startswith("https://comicvine.gamespot.com/api/search")
+                and "params" in kwargs
+                and "resources" in kwargs["params"]
+                and "volume" == kwargs["params"]["resources"]
+            ):
+                cv_list = make_list(comicvine.cv_volume_result)
+                for cv in cv_list["results"]:
+                    comicvine.filter_field_list(cv, kwargs)
+                return comicvine.MockResponse(cv_list)
+            if (
+                args[0]
+                == "https://comicvine.gamespot.com/a/uploads/scale_large/0/574/585444-109004_20080707014047_large.jpg"
+            ):
+                return comicvine.MockResponse({}, cbz.get_page(0))
+            if (
+                args[0]
+                == "https://comicvine.gamespot.com/a/uploads/scale_avatar/0/574/585444-109004_20080707014047_large.jpg"
+            ):
+                thumb = Image.open(io.BytesIO(cbz.get_page(0)))
+                thumb.resize((105, 160), Image.Resampling.LANCZOS)
+                return comicvine.MockResponse({}, thumb.tobytes("jpeg", "RGB"))
+        return comicvine.MockResponse(comicvine.cv_not_found)
+
+    m_get = unittest.mock.Mock(side_effect=mock_get)
+
+    # apply the monkeypatch for requests.get to mock_get
+    monkeypatch.setattr(requests, "get", m_get)
+    return m_get
+
+
+@pytest.fixture
+def mock_now(monkeypatch):
+    class mydatetime:
+        time = datetime.datetime(2022, 7, 11, 17, 42, 41)
+
+        @classmethod
+        def now(cls):
+            return cls.time
+
+    monkeypatch.setattr(comictaggerlib.comicvinetalker, "datetime", mydatetime)
+
+
+@pytest.fixture
+def mock_version(monkeypatch):
+    version = "1.4.4a9.dev20"
+    version_tuple = (1, 4, 4, "dev20")
+
+    monkeypatch.setattr(comictaggerlib.ctversion, "version", version)
+    monkeypatch.setattr(comictaggerlib.ctversion, "__version__", version)
+    monkeypatch.setattr(comictaggerlib.ctversion, "version_tuple", version_tuple)
+    monkeypatch.setattr(comictaggerlib.ctversion, "__version_tuple__", version_tuple)
+
+
+@pytest.fixture
+def md():
+    yield comicapi.genericmetadata.md_test.copy()
+
+
+# manually seeds publishers
+@pytest.fixture
+def seed_publishers(monkeypatch):
+    publisher_seed = {}
+    for publisher, imprint in seed_imprints.items():
+        publisher_seed[publisher] = imprint
+    monkeypatch.setattr(utils, "publishers", publisher_seed)
+
+
+@pytest.fixture
+def seed_all_publishers(monkeypatch):
+    publisher_seed = {}
+    for publisher, imprint in all_seed_imprints.items():
+        publisher_seed[publisher] = imprint
+    monkeypatch.setattr(utils, "publishers", publisher_seed)
+
+
+@pytest.fixture
+def settings(tmp_path):
+    yield comictaggerlib.settings.ComicTaggerSettings(tmp_path / "settings")
+
+
+@pytest.fixture
+def comic_cache(settings) -> Generator[comictaggerlib.comiccacher.ComicCacher, Any, None]:
+    yield comictaggerlib.comiccacher.ComicCacher()

tests/genericmetadata_test.py

@@ -1,37 +1,23 @@
 from __future__ import annotations
 
-import dataclasses
-
 import pytest
 
 import comicapi.genericmetadata
+from testing.comicdata import credits, metadata
 
 
-@pytest.fixture
-def md():
-    yield dataclasses.replace(comicapi.genericmetadata.md_test)
+def test_set_default_page_list(tmp_path):
+    md = comicapi.genericmetadata.GenericMetadata()
+    md.overlay(comicapi.genericmetadata.md_test)
+    md.pages = []
+    md.set_default_page_list(len(comicapi.genericmetadata.md_test.pages))
+
+    assert isinstance(md.pages[0]["Image"], int)
 
 
-stuff = [
-    (
-        {"series": "test", "issue": "2", "title": "never"},
-        dataclasses.replace(comicapi.genericmetadata.md_test, series="test", issue="2", title="never"),
-    ),
-    (
-        {"series": "", "issue": "2", "title": "never"},
-        dataclasses.replace(comicapi.genericmetadata.md_test, series=None, issue="2", title="never"),
-    ),
-    (
-        {},
-        dataclasses.replace(comicapi.genericmetadata.md_test),
-    ),
-]
-
-
-@pytest.mark.parametrize("replaced, expected", stuff)
+@pytest.mark.parametrize("replaced, expected", metadata)
 def test_metadata_overlay(md: comicapi.genericmetadata.GenericMetadata, replaced, expected):
-    md_overlay = comicapi.genericmetadata.GenericMetadata(**replaced)
-    md.overlay(md_overlay)
+    md.overlay(replaced)
 
     assert md == expected
 
@@ -40,7 +26,7 @@ def test_add_credit():
     md = comicapi.genericmetadata.GenericMetadata()
 
     md.add_credit(person="test", role="writer", primary=False)
-    md.credits == [{"person": "test", "role": "writer", "primary": False}]
+    assert md.credits == [comicapi.genericmetadata.CreditMetadata(person="test", role="writer", primary=False)]
 
 
 def test_add_credit_primary():
@@ -48,13 +34,7 @@ def test_add_credit_primary():
 
     md.add_credit(person="test", role="writer", primary=False)
     md.add_credit(person="test", role="writer", primary=True)
-    md.credits == [{"person": "test", "role": "writer", "primary": True}]
-
-
-credits = [
-    ("writer", "Dara Naraghi"),
-    ("writeR", "Dara Naraghi"),
-]
+    assert md.credits == [comicapi.genericmetadata.CreditMetadata(person="test", role="writer", primary=True)]
 
 
 @pytest.mark.parametrize("role, expected", credits)

tests/issueidentifier_test.py

@@ -0,0 +1,75 @@
+from __future__ import annotations
+
+import pytest
+
+import comicapi.comicarchive
+import comicapi.issuestring
+import comictaggerlib.comicvinetalker
+import comictaggerlib.issueidentifier
+import testing.comicdata
+import testing.comicvine
+
+
+def test_crop(cbz_double_cover, settings, tmp_path):
+    ii = comictaggerlib.issueidentifier.IssueIdentifier(cbz_double_cover, settings)
+    cropped = ii.crop_cover(cbz_double_cover.archiver.read_file("double_cover.jpg"))
+    original_cover = cbz_double_cover.get_page(0)
+
+    original_hash = ii.calculate_hash(original_cover)
+    cropped_hash = ii.calculate_hash(cropped)
+
+    assert original_hash == cropped_hash
+
+
+@pytest.mark.parametrize("additional_md, expected", testing.comicdata.metadata_keys)
+def test_get_search_keys(cbz, settings, additional_md, expected):
+    ii = comictaggerlib.issueidentifier.IssueIdentifier(cbz, settings)
+    ii.set_additional_metadata(additional_md)
+
+    assert expected == ii.get_search_keys()
+
+
+def test_get_issue_cover_match_score(cbz, settings, comicvine_api):
+    ii = comictaggerlib.issueidentifier.IssueIdentifier(cbz, settings)
+    score = ii.get_issue_cover_match_score(
+        comictaggerlib.comicvinetalker.ComicVineTalker(),
+        int(
+            comicapi.issuestring.IssueString(
+                cbz.read_metadata(comicapi.comicarchive.MetaDataStyle.CIX).issue
+            ).as_float()
+        ),
+        "https://comicvine.gamespot.com/a/uploads/scale_large/0/574/585444-109004_20080707014047_large.jpg",
+        "https://comicvine.gamespot.com/a/uploads/scale_avatar/0/574/585444-109004_20080707014047_large.jpg",
+        "https://comicvine.gamespot.com/cory-doctorows-futuristic-tales-of-the-here-and-no/4000-140529/",
+        [ii.calculate_hash(cbz.get_page(0))],
+    )
+    expected = {
+        "hash": 1747255366011518976,
+        "score": 0,
+        "url": "https://comicvine.gamespot.com/a/uploads/scale_large/0/574/585444-109004_20080707014047_large.jpg",
+    }
+    assert expected == score
+
+
+def test_search(cbz, settings, comicvine_api):
+    ii = comictaggerlib.issueidentifier.IssueIdentifier(cbz, settings)
+    results = ii.search()
+    cv_expected = {
+        "series": f"{testing.comicvine.cv_volume_result['results']['name']} ({testing.comicvine.cv_volume_result['results']['start_year']})",
+        "distance": 0,
+        "issue_number": testing.comicvine.cv_issue_result["results"]["issue_number"],
+        "cv_issue_count": testing.comicvine.cv_volume_result["results"]["count_of_issues"],
+        "issue_title": testing.comicvine.cv_issue_result["results"]["name"],
+        "issue_id": testing.comicvine.cv_issue_result["results"]["id"],
+        "volume_id": testing.comicvine.cv_volume_result["results"]["id"],
+        "month": testing.comicvine.date[1],
+        "year": testing.comicvine.date[2],
+        "publisher": testing.comicvine.cv_volume_result["results"]["publisher"]["name"],
+        "image_url": testing.comicvine.cv_issue_result["results"]["image"]["super_url"],
+        "thumb_url": testing.comicvine.cv_issue_result["results"]["image"]["thumb_url"],
+        "page_url": testing.comicvine.cv_issue_result["results"]["site_detail_url"],
+        "description": testing.comicvine.cv_issue_result["results"]["description"],
+    }
+    for r, e in zip(results, [cv_expected]):
+        del r["url_image_hash"]
+        assert r == e

tests/rename_test.py

@@ -5,13 +5,19 @@ import pathlib
 import pytest
 
 from comicapi.genericmetadata import md_test
-from comictaggerlib.filerenamer import FileRenamer
-from testing.filenames import rnames
+from comictaggerlib import filerenamer
+from testing.filenames import rfnames, rnames
 
 
-@pytest.mark.parametrize("template, move, platform, expected", rnames)
-def test_rename(template, platform, move, expected):
-    fr = FileRenamer(md_test, platform=platform)
+@pytest.mark.parametrize("template, move, platform, expected, exception", rnames)
+def test_rename(template, platform, move, expected, exception):
+    fr = filerenamer.FileRenamer(md_test, platform=platform)
     fr.move = move
     fr.set_template(template)
-    assert str(pathlib.PureWindowsPath(fr.determine_name(".cbz"))) == str(pathlib.PureWindowsPath(expected))
+    with exception:
+        assert str(pathlib.PureWindowsPath(fr.determine_name(".cbz"))) == str(pathlib.PureWindowsPath(expected))
+
+
+@pytest.mark.parametrize("inp, result", rfnames)
+def test_get_rename_dir(inp, result, cbz):
+    assert result(cbz) == filerenamer.get_rename_dir(cbz, inp)