Only upgrade icu4c and pkg-config

Fix web_link in md_attributes

.github/workflows/build.yaml

@@ -1,7 +1,7 @@
 name: CI
 
 env:
-  PKG_CONFIG_PATH: /usr/local/opt/icu4c/lib/pkgconfig
+  PKG_CONFIG_PATH: /usr/local/opt/icu4c/lib/pkgconfig:/opt/homebrew/opt/icu4c/lib/pkgconfig
   LC_COLLATE: en_US.UTF-8
 on:
   pull_request:
@@ -23,12 +23,12 @@ jobs:
         os: [ubuntu-latest]
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
 
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v3
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
 
@@ -51,12 +51,12 @@ jobs:
         os: [ubuntu-latest, macos-11, windows-latest]
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
 
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v3
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
 
@@ -66,7 +66,7 @@ jobs:
 
       - name: Install macos dependencies
         run: |
-          brew install icu4c pkg-config
+          brew upgrade icu4c pkg-config || brew install icu4c pkg-config
           # export PKG_CONFIG_PATH="/usr/local/opt/icu4c/lib/pkgconfig";
           # export PATH="/usr/local/opt/icu4c/bin:/usr/local/opt/icu4c/sbin:$PATH"
         if: runner.os == 'macOS'

.github/workflows/contributions.yaml

@@ -23,7 +23,7 @@ jobs:
           use_username: true
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
 

.github/workflows/package.yaml

@@ -1,7 +1,7 @@
 name: Package
 
 env:
-  PKG_CONFIG_PATH: /usr/local/opt/icu4c/lib/pkgconfig
+  PKG_CONFIG_PATH: /usr/local/opt/icu4c/lib/pkgconfig:/opt/homebrew/opt/icu4c/lib/pkgconfig
   LC_COLLATE: en_US.UTF-8
 on:
   push:
@@ -18,12 +18,12 @@ jobs:
         os: [ubuntu-latest, macos-11, windows-latest]
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
 
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v3
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
 
@@ -33,7 +33,7 @@ jobs:
 
       - name: Install macos dependencies
         run: |
-          brew install icu4c pkg-config
+          brew upgrade && brew install icu4c pkg-config
           # export PKG_CONFIG_PATH="/usr/local/opt/icu4c/lib/pkgconfig";
           # export PATH="/usr/local/opt/icu4c/bin:/usr/local/opt/icu4c/sbin:$PATH"
         if: runner.os == 'macOS'
@@ -61,7 +61,7 @@ jobs:
           echo "release_name=$(git tag -l --format "%(refname:strip=2): %(contents:lines=1)" ${{ github.ref_name }})" >> $GITHUB_ENV
 
       - name: Release
-        uses: softprops/action-gh-release@v1
+        uses: softprops/action-gh-release@v2
         if: startsWith(github.ref, 'refs/tags/')
         with:
           name: "${{ env.release_name }}"

.pre-commit-config.yaml

@@ -41,6 +41,6 @@ repos:
     rev: v1.8.0
     hooks:
     -   id: mypy
-        additional_dependencies: [types-setuptools, types-requests, settngs>=0.9.1]
+        additional_dependencies: [types-setuptools, types-requests, settngs>=0.10.0]
 ci:
     skip: [mypy]

build-tools/generate_settngs.py

@@ -11,7 +11,11 @@ def generate() -> str:
     app = comictaggerlib.main.App()
     app.load_plugins(app.initial_arg_parser.parse_known_args()[0])
     app.register_settings()
-    return settngs.generate_ns(app.manager.definitions)
+    imports, types = settngs.generate_dict(app.manager.definitions)
+    imports2, types2 = settngs.generate_ns(app.manager.definitions)
+    i = imports.splitlines()
+    i.extend(set(imports2.splitlines()) - set(i))
+    return "\n\n".join(("\n".join(i), types2, types))
 
 
 if __name__ == "__main__":

comicapi/_url.py

@@ -0,0 +1,468 @@
+# mypy: disable-error-code="no-redef"
+from __future__ import annotations
+
+try:
+    from urllib3.exceptions import HTTPError, LocationParseError, LocationValueError
+    from urllib3.util import Url, parse_url
+except ImportError:
+
+    import re
+    import typing
+
+    class HTTPError(Exception):
+        """Base exception used by this module."""
+
+    class LocationValueError(ValueError, HTTPError):
+        """Raised when there is something wrong with a given URL input."""
+
+    class LocationParseError(LocationValueError):
+        """Raised when get_host or similar fails to parse the URL input."""
+
+        def __init__(self, location: str) -> None:
+            message = f"Failed to parse: {location}"
+            super().__init__(message)
+
+            self.location = location
+
+    def to_str(x: str | bytes, encoding: str | None = None, errors: str | None = None) -> str:
+        if isinstance(x, str):
+            return x
+        elif not isinstance(x, bytes):
+            raise TypeError(f"not expecting type {type(x).__name__}")
+        if encoding or errors:
+            return x.decode(encoding or "utf-8", errors=errors or "strict")
+        return x.decode()
+
+    # We only want to normalize urls with an HTTP(S) scheme.
+    # urllib3 infers URLs without a scheme (None) to be http.
+    _NORMALIZABLE_SCHEMES = ("http", "https", None)
+
+    # Almost all of these patterns were derived from the
+    # 'rfc3986' module: https://github.com/python-hyper/rfc3986
+    _PERCENT_RE = re.compile(r"%[a-fA-F0-9]{2}")
+    _SCHEME_RE = re.compile(r"^(?:[a-zA-Z][a-zA-Z0-9+-]*:|/)")
+    _URI_RE = re.compile(
+        r"^(?:([a-zA-Z][a-zA-Z0-9+.-]*):)?" r"(?://([^\\/?#]*))?" r"([^?#]*)" r"(?:\?([^#]*))?" r"(?:#(.*))?$",
+        re.UNICODE | re.DOTALL,
+    )
+
+    _IPV4_PAT = r"(?:[0-9]{1,3}\.){3}[0-9]{1,3}"
+    _HEX_PAT = "[0-9A-Fa-f]{1,4}"
+    _LS32_PAT = "(?:{hex}:{hex}|{ipv4})".format(hex=_HEX_PAT, ipv4=_IPV4_PAT)
+    _subs = {"hex": _HEX_PAT, "ls32": _LS32_PAT}
+    _variations = [
+        #                            6( h16 ":" ) ls32
+        "(?:%(hex)s:){6}%(ls32)s",
+        #                       "::" 5( h16 ":" ) ls32
+        "::(?:%(hex)s:){5}%(ls32)s",
+        # [               h16 ] "::" 4( h16 ":" ) ls32
+        "(?:%(hex)s)?::(?:%(hex)s:){4}%(ls32)s",
+        # [ *1( h16 ":" ) h16 ] "::" 3( h16 ":" ) ls32
+        "(?:(?:%(hex)s:)?%(hex)s)?::(?:%(hex)s:){3}%(ls32)s",
+        # [ *2( h16 ":" ) h16 ] "::" 2( h16 ":" ) ls32
+        "(?:(?:%(hex)s:){0,2}%(hex)s)?::(?:%(hex)s:){2}%(ls32)s",
+        # [ *3( h16 ":" ) h16 ] "::"    h16 ":"   ls32
+        "(?:(?:%(hex)s:){0,3}%(hex)s)?::%(hex)s:%(ls32)s",
+        # [ *4( h16 ":" ) h16 ] "::"              ls32
+        "(?:(?:%(hex)s:){0,4}%(hex)s)?::%(ls32)s",
+        # [ *5( h16 ":" ) h16 ] "::"              h16
+        "(?:(?:%(hex)s:){0,5}%(hex)s)?::%(hex)s",
+        # [ *6( h16 ":" ) h16 ] "::"
+        "(?:(?:%(hex)s:){0,6}%(hex)s)?::",
+    ]
+
+    _UNRESERVED_PAT = r"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789._\-~"
+    _IPV6_PAT = "(?:" + "|".join([x % _subs for x in _variations]) + ")"
+    _ZONE_ID_PAT = "(?:%25|%)(?:[" + _UNRESERVED_PAT + "]|%[a-fA-F0-9]{2})+"
+    _IPV6_ADDRZ_PAT = r"\[" + _IPV6_PAT + r"(?:" + _ZONE_ID_PAT + r")?\]"
+    _REG_NAME_PAT = r"(?:[^\[\]%:/?#]|%[a-fA-F0-9]{2})*"
+    _TARGET_RE = re.compile(r"^(/[^?#]*)(?:\?([^#]*))?(?:#.*)?$")
+
+    _IPV4_RE = re.compile("^" + _IPV4_PAT + "$")
+    _IPV6_RE = re.compile("^" + _IPV6_PAT + "$")
+    _IPV6_ADDRZ_RE = re.compile("^" + _IPV6_ADDRZ_PAT + "$")
+    _BRACELESS_IPV6_ADDRZ_RE = re.compile("^" + _IPV6_ADDRZ_PAT[2:-2] + "$")
+    _ZONE_ID_RE = re.compile("(" + _ZONE_ID_PAT + r")\]$")
+
+    _HOST_PORT_PAT = ("^(%s|%s|%s)(?::0*?(|0|[1-9][0-9]{0,4}))?$") % (
+        _REG_NAME_PAT,
+        _IPV4_PAT,
+        _IPV6_ADDRZ_PAT,
+    )
+    _HOST_PORT_RE = re.compile(_HOST_PORT_PAT, re.UNICODE | re.DOTALL)
+
+    _UNRESERVED_CHARS = set("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789._-~")
+    _SUB_DELIM_CHARS = set("!$&'()*+,;=")
+    _USERINFO_CHARS = _UNRESERVED_CHARS | _SUB_DELIM_CHARS | {":"}
+    _PATH_CHARS = _USERINFO_CHARS | {"@", "/"}
+    _QUERY_CHARS = _FRAGMENT_CHARS = _PATH_CHARS | {"?"}
+
+    class Url(
+        typing.NamedTuple(
+            "Url",
+            [
+                ("scheme", typing.Optional[str]),
+                ("auth", typing.Optional[str]),
+                ("host", typing.Optional[str]),
+                ("port", typing.Optional[int]),
+                ("path", typing.Optional[str]),
+                ("query", typing.Optional[str]),
+                ("fragment", typing.Optional[str]),
+            ],
+        )
+    ):
+        """
+        Data structure for representing an HTTP URL. Used as a return value for
+        :func:`parse_url`. Both the scheme and host are normalized as they are
+        both case-insensitive according to RFC 3986.
+        """
+
+        def __new__(  # type: ignore[no-untyped-def]
+            cls,
+            scheme: str | None = None,
+            auth: str | None = None,
+            host: str | None = None,
+            port: int | None = None,
+            path: str | None = None,
+            query: str | None = None,
+            fragment: str | None = None,
+        ):
+            if path and not path.startswith("/"):
+                path = "/" + path
+            if scheme is not None:
+                scheme = scheme.lower()
+            return super().__new__(cls, scheme, auth, host, port, path, query, fragment)
+
+        @property
+        def hostname(self) -> str | None:
+            """For backwards-compatibility with urlparse. We're nice like that."""
+            return self.host
+
+        @property
+        def request_uri(self) -> str:
+            """Absolute path including the query string."""
+            uri = self.path or "/"
+
+            if self.query is not None:
+                uri += "?" + self.query
+
+            return uri
+
+        @property
+        def authority(self) -> str | None:
+            """
+            Authority component as defined in RFC 3986 3.2.
+            This includes userinfo (auth), host and port.
+
+            i.e.
+                userinfo@host:port
+            """
+            userinfo = self.auth
+            netloc = self.netloc
+            if netloc is None or userinfo is None:
+                return netloc
+            else:
+                return f"{userinfo}@{netloc}"
+
+        @property
+        def netloc(self) -> str | None:
+            """
+            Network location including host and port.
+
+            If you need the equivalent of urllib.parse's ``netloc``,
+            use the ``authority`` property instead.
+            """
+            if self.host is None:
+                return None
+            if self.port:
+                return f"{self.host}:{self.port}"
+            return self.host
+
+        @property
+        def url(self) -> str:
+            """
+            Convert self into a url
+
+            This function should more or less round-trip with :func:`.parse_url`. The
+            returned url may not be exactly the same as the url inputted to
+            :func:`.parse_url`, but it should be equivalent by the RFC (e.g., urls
+            with a blank port will have : removed).
+
+            Example:
+
+            .. code-block:: python
+
+                import urllib3
+
+                U = urllib3.util.parse_url("https://google.com/mail/")
+
+                print(U.url)
+                # "https://google.com/mail/"
+
+                print( urllib3.util.Url("https", "username:password",
+                                        "host.com", 80, "/path", "query", "fragment"
+                                        ).url
+                    )
+                # "https://username:password@host.com:80/path?query#fragment"
+            """
+            scheme, auth, host, port, path, query, fragment = self
+            url = ""
+
+            # We use "is not None" we want things to happen with empty strings (or 0 port)
+            if scheme is not None:
+                url += scheme + "://"
+            if auth is not None:
+                url += auth + "@"
+            if host is not None:
+                url += host
+            if port is not None:
+                url += ":" + str(port)
+            if path is not None:
+                url += path
+            if query is not None:
+                url += "?" + query
+            if fragment is not None:
+                url += "#" + fragment
+
+            return url
+
+        def __str__(self) -> str:
+            return self.url
+
+    @typing.overload
+    def _encode_invalid_chars(component: str, allowed_chars: typing.Container[str]) -> str:  # Abstract
+        ...
+
+    @typing.overload
+    def _encode_invalid_chars(component: None, allowed_chars: typing.Container[str]) -> None:  # Abstract
+        ...
+
+    def _encode_invalid_chars(component: str | None, allowed_chars: typing.Container[str]) -> str | None:
+        """Percent-encodes a URI component without reapplying
+        onto an already percent-encoded component.
+        """
+        if component is None:
+            return component
+
+        component = to_str(component)
+
+        # Normalize existing percent-encoded bytes.
+        # Try to see if the component we're encoding is already percent-encoded
+        # so we can skip all '%' characters but still encode all others.
+        component, percent_encodings = _PERCENT_RE.subn(lambda match: match.group(0).upper(), component)
+
+        uri_bytes = component.encode("utf-8", "surrogatepass")
+        is_percent_encoded = percent_encodings == uri_bytes.count(b"%")
+        encoded_component = bytearray()
+
+        for i in range(0, len(uri_bytes)):
+            # Will return a single character bytestring
+            byte = uri_bytes[i : i + 1]
+            byte_ord = ord(byte)
+            if (is_percent_encoded and byte == b"%") or (byte_ord < 128 and byte.decode() in allowed_chars):
+                encoded_component += byte
+                continue
+            encoded_component.extend(b"%" + (hex(byte_ord)[2:].encode().zfill(2).upper()))
+
+        return encoded_component.decode()
+
+    def _remove_path_dot_segments(path: str) -> str:
+        # See http://tools.ietf.org/html/rfc3986#section-5.2.4 for pseudo-code
+        segments = path.split("/")  # Turn the path into a list of segments
+        output = []  # Initialize the variable to use to store output
+
+        for segment in segments:
+            # '.' is the current directory, so ignore it, it is superfluous
+            if segment == ".":
+                continue
+            # Anything other than '..', should be appended to the output
+            if segment != "..":
+                output.append(segment)
+            # In this case segment == '..', if we can, we should pop the last
+            # element
+            elif output:
+                output.pop()
+
+        # If the path starts with '/' and the output is empty or the first string
+        # is non-empty
+        if path.startswith("/") and (not output or output[0]):
+            output.insert(0, "")
+
+        # If the path starts with '/.' or '/..' ensure we add one more empty
+        # string to add a trailing '/'
+        if path.endswith(("/.", "/..")):
+            output.append("")
+
+        return "/".join(output)
+
+    @typing.overload
+    def _normalize_host(host: None, scheme: str | None) -> None: ...
+
+    @typing.overload
+    def _normalize_host(host: str, scheme: str | None) -> str: ...
+
+    def _normalize_host(host: str | None, scheme: str | None) -> str | None:
+        if host:
+            if scheme in _NORMALIZABLE_SCHEMES:
+                is_ipv6 = _IPV6_ADDRZ_RE.match(host)
+                if is_ipv6:
+                    # IPv6 hosts of the form 'a::b%zone' are encoded in a URL as
+                    # such per RFC 6874: 'a::b%25zone'. Unquote the ZoneID
+                    # separator as necessary to return a valid RFC 4007 scoped IP.
+                    match = _ZONE_ID_RE.search(host)
+                    if match:
+                        start, end = match.span(1)
+                        zone_id = host[start:end]
+
+                        if zone_id.startswith("%25") and zone_id != "%25":
+                            zone_id = zone_id[3:]
+                        else:
+                            zone_id = zone_id[1:]
+                        zone_id = _encode_invalid_chars(zone_id, _UNRESERVED_CHARS)
+                        return f"{host[:start].lower()}%{zone_id}{host[end:]}"
+                    else:
+                        return host.lower()
+                elif not _IPV4_RE.match(host):
+                    return to_str(
+                        b".".join([_idna_encode(label) for label in host.split(".")]),
+                        "ascii",
+                    )
+        return host
+
+    def _idna_encode(name: str) -> bytes:
+        if not name.isascii():
+            try:
+                import idna
+            except ImportError:
+                raise LocationParseError("Unable to parse URL without the 'idna' module") from None
+
+            try:
+                return idna.encode(name.lower(), strict=True, std3_rules=True)
+            except idna.IDNAError:
+                raise LocationParseError(f"Name '{name}' is not a valid IDNA label") from None
+
+        return name.lower().encode("ascii")
+
+    def _encode_target(target: str) -> str:
+        """Percent-encodes a request target so that there are no invalid characters
+
+        Pre-condition for this function is that 'target' must start with '/'.
+        If that is the case then _TARGET_RE will always produce a match.
+        """
+        match = _TARGET_RE.match(target)
+        if not match:  # Defensive:
+            raise LocationParseError(f"{target!r} is not a valid request URI")
+
+        path, query = match.groups()
+        encoded_target = _encode_invalid_chars(path, _PATH_CHARS)
+        if query is not None:
+            query = _encode_invalid_chars(query, _QUERY_CHARS)
+            encoded_target += "?" + query
+        return encoded_target
+
+    def parse_url(url: str) -> Url:
+        """
+        Given a url, return a parsed :class:`.Url` namedtuple. Best-effort is
+        performed to parse incomplete urls. Fields not provided will be None.
+        This parser is RFC 3986 and RFC 6874 compliant.
+
+        The parser logic and helper functions are based heavily on
+        work done in the ``rfc3986`` module.
+
+        :param str url: URL to parse into a :class:`.Url` namedtuple.
+
+        Partly backwards-compatible with :mod:`urllib.parse`.
+
+        Example:
+
+        .. code-block:: python
+
+            import urllib3
+
+            print( urllib3.util.parse_url('http://google.com/mail/'))
+            # Url(scheme='http', host='google.com', port=None, path='/mail/', ...)
+
+            print( urllib3.util.parse_url('google.com:80'))
+            # Url(scheme=None, host='google.com', port=80, path=None, ...)
+
+            print( urllib3.util.parse_url('/foo?bar'))
+            # Url(scheme=None, host=None, port=None, path='/foo', query='bar', ...)
+        """
+        if not url:
+            # Empty
+            return Url()
+
+        source_url = url
+        if not _SCHEME_RE.search(url):
+            url = "//" + url
+
+        scheme: str | None
+        authority: str | None
+        auth: str | None
+        host: str | None
+        port: str | None
+        port_int: int | None
+        path: str | None
+        query: str | None
+        fragment: str | None
+
+        try:
+            scheme, authority, path, query, fragment = _URI_RE.match(url).groups()  # type: ignore[union-attr]
+            normalize_uri = scheme is None or scheme.lower() in _NORMALIZABLE_SCHEMES
+
+            if scheme:
+                scheme = scheme.lower()
+
+            if authority:
+                auth, _, host_port = authority.rpartition("@")
+                auth = auth or None
+                host, port = _HOST_PORT_RE.match(host_port).groups()  # type: ignore[union-attr]
+                if auth and normalize_uri:
+                    auth = _encode_invalid_chars(auth, _USERINFO_CHARS)
+                if port == "":
+                    port = None
+            else:
+                auth, host, port = None, None, None
+
+            if port is not None:
+                port_int = int(port)
+                if not (0 <= port_int <= 65535):
+                    raise LocationParseError(url)
+            else:
+                port_int = None
+
+            host = _normalize_host(host, scheme)
+
+            if normalize_uri and path:
+                path = _remove_path_dot_segments(path)
+                path = _encode_invalid_chars(path, _PATH_CHARS)
+            if normalize_uri and query:
+                query = _encode_invalid_chars(query, _QUERY_CHARS)
+            if normalize_uri and fragment:
+                fragment = _encode_invalid_chars(fragment, _FRAGMENT_CHARS)
+
+        except (ValueError, AttributeError) as e:
+            raise LocationParseError(source_url) from e
+
+        # For the sake of backwards compatibility we put empty
+        # string values for path if there are any defined values
+        # beyond the path in the URL.
+        # TODO: Remove this when we break backwards compatibility.
+        if not path:
+            if query is not None or fragment is not None:
+                path = ""
+            else:
+                path = None
+
+        return Url(
+            scheme=scheme,
+            auth=auth,
+            host=host,
+            port=port_int,
+            path=path,
+            query=query,
+            fragment=fragment,
+        )
+
+
+__all__ = ("Url", "parse_url", "HTTPError", "LocationParseError", "LocationValueError")

comicapi/archivers/sevenzip.py

@@ -37,7 +37,7 @@ class SevenZipArchiver(Archiver):
         data = b""
         try:
             with py7zr.SevenZipFile(self.path, "r") as zf:
-                data = zf.read(archive_file)[archive_file].read()
+                data = zf.read([archive_file])[archive_file].read()
         except (py7zr.Bad7zFile, OSError) as e:
             logger.error("Error reading 7zip archive [%s]: %s :: %s", e, self.path, archive_file)
             raise

comicapi/comicarchive.py

@@ -364,7 +364,7 @@ class ComicArchive:
 
     def metadata_from_filename(
         self,
-        complicated_parser: bool = False,
+        parser: utils.Parser = utils.Parser.ORIGINAL,
         remove_c2c: bool = False,
         remove_fcbd: bool = False,
         remove_publisher: bool = False,
@@ -376,7 +376,7 @@ class ComicArchive:
 
         filename_info = utils.parse_filename(
             self.path.name,
-            complicated_parser=complicated_parser,
+            parser=parser,
             remove_c2c=remove_c2c,
             remove_fcbd=remove_fcbd,
             remove_publisher=remove_publisher,

comicapi/genericmetadata.py

@@ -31,6 +31,8 @@ from typing_extensions import NamedTuple, Required
 
 from comicapi import utils
 
+from ._url import Url, parse_url
+
 logger = logging.getLogger(__name__)
 
 
@@ -133,7 +135,7 @@ class GenericMetadata:
     year: int | None = None
     language: str | None = None  # 2 letter iso code
     country: str | None = None
-    web_link: str | None = None
+    web_links: list[Url] = dataclasses.field(default_factory=list)
     format: str | None = None
     manga: str | None = None
     black_and_white: bool | None = None
@@ -253,7 +255,7 @@ class GenericMetadata:
         assign("year", new_md.year)
         assign("language", new_md.language)
         assign("country", new_md.country)
-        assign("web_link", new_md.web_link)
+        assign("web_links", new_md.web_links)
         assign("format", new_md.format)
         assign("manga", new_md.manga)
         assign("black_and_white", new_md.black_and_white)
@@ -487,7 +489,9 @@ md_test: GenericMetadata = GenericMetadata(
     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/",
+    web_links=[
+        parse_url("https://comicvine.gamespot.com/cory-doctorows-futuristic-tales-of-the-here-and-no/4000-140529/")
+    ],
     format="Series",
     manga="No",
     black_and_white=None,
@@ -551,3 +555,15 @@ md_test: GenericMetadata = GenericMetadata(
     last_mark=None,
     _cover_image=None,
 )
+
+
+__all__ = (
+    "Url",
+    "parse_url",
+    "PageType",
+    "ImageMetadata",
+    "Credit",
+    "ComicSeries",
+    "TagOrigin",
+    "GenericMetadata",
+)

comicapi/metadata/comicrack.py

@@ -57,7 +57,7 @@ class ComicRack(Metadata):
             "month",
             "year",
             "language",
-            "web_link",
+            "web_links",
             "format",
             "manga",
             "black_and_white",
@@ -229,7 +229,7 @@ class ComicRack(Metadata):
         assign("Month", md.month)
         assign("Year", md.year)
         assign("LanguageISO", md.language)
-        assign("Web", md.web_link)
+        assign("Web", " ".join(u.url for u in md.web_links))
         assign("Format", md.format)
         assign("Manga", md.manga)
         assign("BlackAndWhite", "Yes" if md.black_and_white else None)
@@ -313,7 +313,7 @@ class ComicRack(Metadata):
         md.month = utils.xlate_int(get("Month"))
         md.year = utils.xlate_int(get("Year"))
         md.language = utils.xlate(get("LanguageISO"))
-        md.web_link = utils.xlate(get("Web"))
+        md.web_links = utils.split_urls(utils.xlate(get("Web")))
         md.format = utils.xlate(get("Format"))
         md.manga = utils.xlate(get("Manga"))
         md.maturity_rating = utils.xlate(get("AgeRating"))

comicapi/utils.py

@@ -20,15 +20,21 @@ import logging
 import os
 import pathlib
 import platform
+import sys
 import unicodedata
 from collections import defaultdict
 from collections.abc import Iterable, Mapping
+from enum import Enum, auto
 from shutil import which  # noqa: F401
 from typing import Any, TypeVar, cast
 
+from comicfn2dict import comicfn2dict
+
 import comicapi.data
 from comicapi import filenamelexer, filenameparser
 
+from ._url import Url, parse_url
+
 try:
     import icu
 
@@ -37,9 +43,55 @@ try:
 except ImportError:
     icu_available = False
 
+
+if sys.version_info < (3, 11):
+
+    class StrEnum(str, Enum):
+        """
+        Enum where members are also (and must be) strings
+        """
+
+        def __new__(cls, *values: Any) -> Any:
+            "values must already be of type `str`"
+            if len(values) > 3:
+                raise TypeError(f"too many arguments for str(): {values!r}")
+            if len(values) == 1:
+                # it must be a string
+                if not isinstance(values[0], str):
+                    raise TypeError(f"{values[0]!r} is not a string")
+            if len(values) >= 2:
+                # check that encoding argument is a string
+                if not isinstance(values[1], str):
+                    raise TypeError(f"encoding must be a string, not {values[1]!r}")
+            if len(values) == 3:
+                # check that errors argument is a string
+                if not isinstance(values[2], str):
+                    raise TypeError("errors must be a string, not %r" % (values[2]))
+            value = str(*values)
+            member = str.__new__(cls, value)
+            member._value_ = value
+            return member
+
+        @staticmethod
+        def _generate_next_value_(name: str, start: int, count: int, last_values: Any) -> str:
+            """
+            Return the lower-cased version of the member name.
+            """
+            return name.lower()
+
+else:
+    from enum import StrEnum
+
+
 logger = logging.getLogger(__name__)
 
 
+class Parser(StrEnum):
+    ORIGINAL = auto()
+    COMPLICATED = auto()
+    COMICFN2DICT = auto()
+
+
 def _custom_key(tup: Any) -> Any:
     import natsort
 
@@ -67,7 +119,7 @@ def os_sorted(lst: Iterable[T]) -> Iterable[T]:
 
 def parse_filename(
     filename: str,
-    complicated_parser: bool = False,
+    parser: Parser = Parser.ORIGINAL,
     remove_c2c: bool = False,
     remove_fcbd: bool = False,
     remove_publisher: bool = False,
@@ -99,7 +151,25 @@ def parse_filename(
         filename, ext = os.path.splitext(filename)
         filename = " ".join(wordninja.split(filename)) + ext
 
-    if complicated_parser:
+    fni = filenameparser.FilenameInfo(
+        alternate="",
+        annual=False,
+        archive="",
+        c2c=False,
+        fcbd=False,
+        format="",
+        issue="",
+        issue_count="",
+        publisher="",
+        remainder="",
+        series="",
+        title="",
+        volume="",
+        volume_count="",
+        year="",
+    )
+
+    if parser == Parser.COMPLICATED:
         lex = filenamelexer.Lex(filename, allow_issue_start_with_letter)
         p = filenameparser.Parse(
             lex.items,
@@ -108,7 +178,26 @@ def parse_filename(
             remove_publisher=remove_publisher,
             protofolius_issue_number_scheme=protofolius_issue_number_scheme,
         )
-        return p.filename_info
+        fni = p.filename_info
+    elif parser == Parser.COMICFN2DICT:
+        fn2d = comicfn2dict(filename)
+        fni = filenameparser.FilenameInfo(
+            alternate="",
+            annual=False,
+            archive=fn2d.get("ext", ""),
+            c2c=False,
+            fcbd=False,
+            issue=fn2d.get("issue", ""),
+            issue_count=fn2d.get("issue_count", ""),
+            publisher=fn2d.get("publisher", ""),
+            remainder=fn2d.get("scan_info", ""),
+            series=fn2d.get("series", ""),
+            title=fn2d.get("title", ""),
+            volume=fn2d.get("volume", ""),
+            volume_count=fn2d.get("volume_count", ""),
+            year=fn2d.get("year", ""),
+            format=fn2d.get("original_format", ""),
+        )
     else:
         fnp = filenameparser.FileNameParser()
         fnp.parse_filename(filename)
@@ -129,7 +218,7 @@ def parse_filename(
             year=fnp.year,
             format="",
         )
-        return fni
+    return fni
 
 
 def combine_notes(existing_notes: str | None, new_notes: str | None, split: str) -> str:
@@ -283,6 +372,24 @@ def split(s: str | None, c: str) -> list[str]:
     return []
 
 
+def split_urls(s: str | None) -> list[Url]:
+    if s is None:
+        return []
+    # Find occurences of ' http'
+    if s.count("http") > 1 and s.count(" http") >= 1:
+        urls = []
+        # Split urls out
+        url_strings = split(s, " http")
+        # Return the scheme 'http' and parse the url
+        for i, url_string in enumerate(url_strings):
+            if not url_string.startswith("http"):
+                url_string = "http" + url_string
+            urls.append(parse_url(url_string))
+        return urls
+    else:
+        return [parse_url(s)]
+
+
 def remove_articles(text: str) -> str:
     text = text.casefold()
     articles = [

comictaggerlib/__pyinstaller/hook-comictaggerlib.py

@@ -1,7 +1,8 @@
 from __future__ import annotations
 
-from PyInstaller.utils.hooks import collect_data_files, collect_entry_point
+from PyInstaller.utils.hooks import collect_data_files, collect_entry_point, collect_submodules
 
 datas, hiddenimports = collect_entry_point("comictagger.talker")
+hiddenimports += collect_submodules("comictaggerlib")
 datas += collect_data_files("comictaggerlib.ui")
 datas += collect_data_files("comictaggerlib.graphics")

comictaggerlib/autotagmatchwindow.py

@@ -233,7 +233,7 @@ class AutoTagMatchWindow(QtWidgets.QDialog):
         md = ca.read_metadata(self.config.internal__load_data_style)
         if md.is_empty:
             md = ca.metadata_from_filename(
-                self.config.Filename_Parsing__complicated_parser,
+                self.config.Filename_Parsing__filename_parser,
                 self.config.Filename_Parsing__remove_c2c,
                 self.config.Filename_Parsing__remove_fcbd,
                 self.config.Filename_Parsing__remove_publisher,

comictaggerlib/cbltransformer.py

@@ -78,12 +78,13 @@ class CBLTransformer:
                     self.metadata.description += self.metadata.notes
 
         if self.config.Comic_Book_Lover__copy_weblink_to_comments:
-            if self.metadata.web_link is not None:
-                if self.metadata.description is None:
-                    self.metadata.description = ""
+            for web_link in self.metadata.web_links:
+                temp_desc = self.metadata.description
+                if temp_desc is None:
+                    temp_desc = ""
                 else:
-                    self.metadata.description += "\n\n"
-                if self.metadata.web_link not in self.metadata.description:
-                    self.metadata.description += self.metadata.web_link
+                    temp_desc += "\n\n"
+                if web_link.url and web_link.url not in temp_desc:
+                    self.metadata.description = temp_desc + web_link.url
 
         return self.metadata

comictaggerlib/cli.py

@@ -250,7 +250,7 @@ class CLI:
         # now, overlay the parsed filename info
         if self.config.Runtime_Options__parse_filename:
             f_md = ca.metadata_from_filename(
-                self.config.Filename_Parsing__complicated_parser,
+                self.config.Filename_Parsing__filename_parser,
                 self.config.Filename_Parsing__remove_c2c,
                 self.config.Filename_Parsing__remove_fcbd,
                 self.config.Filename_Parsing__remove_publisher,
@@ -458,32 +458,27 @@ class CLI:
                     if self.config.Runtime_Options__verbose:
                         self.output(text)
 
-                # use our overlaid MD struct to search
-                ii.set_additional_metadata(md)
-                ii.only_use_additional_meta_data = True
                 ii.set_output_function(functools.partial(self.output, already_logged=True))
-                ii.cover_page_index = md.get_cover_page_index_list()[0]
-                matches = ii.search()
-
-                result = ii.search_result
+                # use our overlaid MD to search
+                result, matches = ii.identify(ca, md)
 
                 found_match = False
                 choices = False
                 low_confidence = False
 
-                if result == ii.result_no_matches:
+                if result == IssueIdentifier.result_no_matches:
                     pass
-                elif result == ii.result_found_match_but_bad_cover_score:
+                elif result == IssueIdentifier.result_found_match_but_bad_cover_score:
                     low_confidence = True
                     found_match = True
-                elif result == ii.result_found_match_but_not_first_page:
+                elif result == IssueIdentifier.result_found_match_but_not_first_page:
                     found_match = True
-                elif result == ii.result_multiple_matches_with_bad_image_scores:
+                elif result == IssueIdentifier.result_multiple_matches_with_bad_image_scores:
                     low_confidence = True
                     choices = True
-                elif result == ii.result_one_good_match:
+                elif result == IssueIdentifier.result_one_good_match:
                     found_match = True
-                elif result == ii.result_multiple_good_matches:
+                elif result == IssueIdentifier.result_multiple_good_matches:
                     choices = True
 
                 if choices:

comictaggerlib/ctsettings/__init__.py

@@ -14,7 +14,7 @@ from comictaggerlib.ctsettings.commandline import (
 )
 from comictaggerlib.ctsettings.file import register_file_settings, validate_file_settings
 from comictaggerlib.ctsettings.plugin import group_for_plugin, register_plugin_settings, validate_plugin_settings
-from comictaggerlib.ctsettings.settngs_namespace import settngs_namespace as ct_ns
+from comictaggerlib.ctsettings.settngs_namespace import SettngsNS as ct_ns
 from comictaggerlib.ctsettings.types import ComicTaggerPaths
 from comictalker import ComicTalker
 

comictaggerlib/ctsettings/commandline.py

@@ -29,7 +29,7 @@ from comicapi import utils
 from comicapi.comicarchive import metadata_styles
 from comicapi.genericmetadata import GenericMetadata
 from comictaggerlib import ctversion
-from comictaggerlib.ctsettings.settngs_namespace import settngs_namespace as ct_ns
+from comictaggerlib.ctsettings.settngs_namespace import SettngsNS as ct_ns
 from comictaggerlib.ctsettings.types import (
     ComicTaggerPaths,
     metadata_type,
@@ -308,9 +308,12 @@ def validate_commandline_settings(config: settngs.Config[ct_ns], parser: settngs
     # take a crack at finding rar exe if it's not in the path
     if not utils.which("rar"):
         if platform.system() == "Windows":
-            # look in some likely places for Windows machines
-            utils.add_to_path(r"C:\Program Files\WinRAR")
-            utils.add_to_path(r"C:\Program Files (x86)\WinRAR")
+            letters = ["C"]
+            letters.extend({f"{d}" for d in "ABCDEFGHIJKLMNOPQRSTUVWXYZ" if os.path.exists(f"{d}:\\")} - {"C"})
+            for letter in letters:
+                # look in some likely places for Windows machines
+                utils.add_to_path(rf"{letters}:\Program Files\WinRAR")
+                utils.add_to_path(rf"{letters}:\Program Files (x86)\WinRAR")
         else:
             if platform.system() == "Darwin":
                 result = subprocess.run(("/usr/libexec/path_helper", "-s"), capture_output=True)

comictaggerlib/ctsettings/file.py

@@ -5,7 +5,8 @@ import uuid
 
 import settngs
 
-from comictaggerlib.ctsettings.settngs_namespace import settngs_namespace as ct_ns
+from comicapi import utils
+from comictaggerlib.ctsettings.settngs_namespace import SettngsNS as ct_ns
 from comictaggerlib.defaults import DEFAULT_REPLACEMENTS, Replacement, Replacements
 
 
@@ -19,6 +20,12 @@ def general(parser: settngs.Manager) -> None:
         help="Disable the ComicRack metadata type",
     )
     parser.add_setting("use_short_metadata_names", default=False, action=argparse.BooleanOptionalAction, cmdline=False)
+    parser.add_setting(
+        "--prompt-on-save",
+        default=True,
+        action=argparse.BooleanOptionalAction,
+        help="Prompts the user to confirm saving tags when using the GUI.",
+    )
 
 
 def internal(parser: settngs.Manager) -> None:
@@ -96,10 +103,12 @@ def dialog(parser: settngs.Manager) -> None:
 def filename(parser: settngs.Manager) -> None:
     # filename parsing settings
     parser.add_setting(
-        "--complicated-parser",
-        default=False,
-        action=argparse.BooleanOptionalAction,
-        help="Enables the new parser which tries to extract more information from filenames",
+        "--filename-parser",
+        default=utils.Parser.ORIGINAL,
+        metavar=f"{{{','.join(utils.Parser)}}}",
+        type=utils.Parser,
+        choices=[p.value for p in utils.Parser],
+        help="Select the filename parser, defaults to original",
     )
     parser.add_setting(
         "--remove-c2c",
@@ -254,12 +263,24 @@ def parse_filter(config: settngs.Config[ct_ns]) -> settngs.Config[ct_ns]:
     return config
 
 
+def migrate_settings(config: settngs.Config[ct_ns]) -> settngs.Config[ct_ns]:
+    original_types = ("cbi", "cr", "comet")
+    save_style = config[0].internal__save_data_style
+    if not isinstance(save_style, list):
+        if isinstance(save_style, int) and save_style in (0, 1, 2):
+            config[0].internal__save_data_style = [original_types[save_style]]
+        elif isinstance(save_style, str):
+            config[0].internal__save_data_style = [save_style]
+        else:
+            config[0].internal__save_data_style = ["cbi"]
+
+    return config
+
+
 def validate_file_settings(config: settngs.Config[ct_ns]) -> settngs.Config[ct_ns]:
     config = parse_filter(config)
 
-    # TODO Remove this conversion check at a later date
-    if isinstance(config[0].internal__save_data_style, str):
-        config[0].internal__save_data_style = [config[0].internal__save_data_style]
+    config = migrate_settings(config)
 
     if config[0].Filename_Parsing__protofolius_issue_number_scheme:
         config[0].Filename_Parsing__allow_issue_start_with_letter = True

comictaggerlib/ctsettings/plugin.py

@@ -10,16 +10,16 @@ import comicapi.comicarchive
 import comicapi.utils
 import comictaggerlib.ctsettings
 from comicapi.comicarchive import Archiver
-from comictaggerlib.ctsettings.settngs_namespace import settngs_namespace as ct_ns
+from comictaggerlib.ctsettings.settngs_namespace import SettngsNS as ct_ns
 from comictalker.comictalker import ComicTalker
 
 logger = logging.getLogger("comictagger")
 
 
-def group_for_plugin(plugin: Archiver | ComicTalker) -> str:
+def group_for_plugin(plugin: Archiver | ComicTalker | type[Archiver]) -> str:
     if isinstance(plugin, ComicTalker):
         return f"Source {plugin.id}"
-    if isinstance(plugin, Archiver):
+    if isinstance(plugin, Archiver) or plugin == Archiver:
         return "Archive"
     raise NotImplementedError(f"Invalid plugin received: {plugin=}")
 

comictaggerlib/ctsettings/settngs_namespace.py

@@ -1,14 +1,17 @@
 from __future__ import annotations
 
+import typing
+
 import settngs
 
 import comicapi.genericmetadata
+import comicapi.utils
 import comictaggerlib.ctsettings.types
 import comictaggerlib.defaults
 import comictaggerlib.resulttypes
 
 
-class settngs_namespace(settngs.TypedNS):
+class SettngsNS(settngs.TypedNS):
     Commands__version: bool
     Commands__command: comictaggerlib.resulttypes.Action
     Commands__copy: str
@@ -59,7 +62,7 @@ class settngs_namespace(settngs.TypedNS):
     Issue_Identifier__exact_series_matches_first: bool
     Issue_Identifier__always_use_publisher_filter: bool
 
-    Filename_Parsing__complicated_parser: bool
+    Filename_Parsing__filename_parser: comicapi.utils.Parser
     Filename_Parsing__remove_c2c: bool
     Filename_Parsing__remove_fcbd: bool
     Filename_Parsing__remove_publisher: bool
@@ -98,6 +101,7 @@ class settngs_namespace(settngs.TypedNS):
     General__check_for_new_version: bool
     General__disable_cr: bool
     General__use_short_metadata_names: bool
+    General__prompt_on_save: bool
 
     Dialog_Flags__show_disclaimer: bool
     Dialog_Flags__dont_notify_about_this_version: str
@@ -108,3 +112,150 @@ class settngs_namespace(settngs.TypedNS):
     Source_comicvine__comicvine_key: str
     Source_comicvine__comicvine_url: str
     Source_comicvine__cv_use_series_start_as_volume: bool
+
+
+class Commands(typing.TypedDict):
+    version: bool
+    command: comictaggerlib.resulttypes.Action
+    copy: str
+
+
+class Runtime_Options(typing.TypedDict):
+    config: comictaggerlib.ctsettings.types.ComicTaggerPaths
+    verbose: int
+    abort_on_conflict: bool
+    delete_original: bool
+    parse_filename: bool
+    issue_id: str
+    online: bool
+    metadata: comicapi.genericmetadata.GenericMetadata
+    interactive: bool
+    abort_on_low_confidence: bool
+    summary: bool
+    raw: bool
+    recursive: bool
+    dryrun: bool
+    darkmode: bool
+    glob: bool
+    quiet: bool
+    json: bool
+    type: list[str]
+    overwrite: bool
+    no_gui: bool
+    files: list[str]
+
+
+class internal(typing.TypedDict):
+    install_id: str
+    save_data_style: list[str]
+    load_data_style: str
+    last_opened_folder: str
+    window_width: int
+    window_height: int
+    window_x: int
+    window_y: int
+    form_width: int
+    list_width: int
+    sort_column: int
+    sort_direction: int
+
+
+class Issue_Identifier(typing.TypedDict):
+    series_match_identify_thresh: int
+    border_crop_percent: int
+    publisher_filter: list[str]
+    series_match_search_thresh: int
+    clear_metadata: bool
+    auto_imprint: bool
+    sort_series_by_year: bool
+    exact_series_matches_first: bool
+    always_use_publisher_filter: bool
+
+
+class Filename_Parsing(typing.TypedDict):
+    filename_parser: comicapi.utils.Parser
+    remove_c2c: bool
+    remove_fcbd: bool
+    remove_publisher: bool
+    split_words: bool
+    protofolius_issue_number_scheme: bool
+    allow_issue_start_with_letter: bool
+
+
+class Sources(typing.TypedDict):
+    source: str
+    remove_html_tables: bool
+
+
+class Comic_Book_Lover(typing.TypedDict):
+    assume_lone_credit_is_primary: bool
+    copy_characters_to_tags: bool
+    copy_teams_to_tags: bool
+    copy_locations_to_tags: bool
+    copy_storyarcs_to_tags: bool
+    copy_notes_to_comments: bool
+    copy_weblink_to_comments: bool
+    apply_transform_on_import: bool
+    apply_transform_on_bulk_operation: bool
+
+
+class File_Rename(typing.TypedDict):
+    template: str
+    issue_number_padding: int
+    use_smart_string_cleanup: bool
+    auto_extension: bool
+    dir: str
+    move_to_dir: bool
+    strict: bool
+    replacements: comictaggerlib.defaults.Replacements
+
+
+class Auto_Tag(typing.TypedDict):
+    save_on_low_confidence: bool
+    dont_use_year_when_identifying: bool
+    assume_issue_one: bool
+    ignore_leading_numbers_in_filename: bool
+    remove_archive_after_successful_match: bool
+
+
+class General(typing.TypedDict):
+    check_for_new_version: bool
+    disable_cr: bool
+    use_short_metadata_names: bool
+    prompt_on_save: bool
+
+
+class Dialog_Flags(typing.TypedDict):
+    show_disclaimer: bool
+    dont_notify_about_this_version: str
+    ask_about_usage_stats: bool
+
+
+class Archive(typing.TypedDict):
+    rar: str
+
+
+class Source_comicvine(typing.TypedDict):
+    comicvine_key: str
+    comicvine_url: str
+    cv_use_series_start_as_volume: bool
+
+
+SettngsDict = typing.TypedDict(
+    "SettngsDict",
+    {
+        "Commands": Commands,
+        "Runtime Options": Runtime_Options,
+        "internal": internal,
+        "Issue Identifier": Issue_Identifier,
+        "Filename Parsing": Filename_Parsing,
+        "Sources": Sources,
+        "Comic Book Lover": Comic_Book_Lover,
+        "File Rename": File_Rename,
+        "Auto-Tag": Auto_Tag,
+        "General": General,
+        "Dialog Flags": Dialog_Flags,
+        "Archive": Archive,
+        "Source comicvine": Source_comicvine,
+    },
+)

comictaggerlib/filerenamer.py

@@ -69,7 +69,7 @@ class MetadataFormatter(string.Formatter):
         if conversion == "t":
             return str(value).title()
         if conversion == "j":
-            return ", ".join(list(value))
+            return ", ".join(list(str(v) for v in value))
         return cast(str, super().convert_field(value, conversion))
 
     def handle_replacements(self, string: str, replacements: list[Replacement]) -> str:
@@ -218,6 +218,10 @@ class FileRenamer:
 
         fmt = MetadataFormatter(self.smart_cleanup, platform=self.platform, replacements=self.replacements)
         md_dict = vars(md)
+        md_dict["web_link"] = ""
+        if md.web_links:
+            md_dict["web_link"] = md.web_links[0]
+
         md_dict["issue"] = IssueString(md.issue).as_string(pad=self.issue_zero_padding)
         for role in ["writer", "penciller", "inker", "colorist", "letterer", "cover artist", "editor"]:
             md_dict[role] = md.get_primary_credit(role)

comictaggerlib/fileselectionlist.py

@@ -35,11 +35,6 @@ from comictaggerlib.ui.qtutils import center_window_on_parent, reduce_widget_fon
 logger = logging.getLogger(__name__)
 
 
-class FileTableWidgetItem(QtWidgets.QTableWidgetItem):
-    def __lt__(self, other: object) -> bool:
-        return self.data(QtCore.Qt.ItemDataRole.UserRole) < other.data(QtCore.Qt.ItemDataRole.UserRole)  # type: ignore
-
-
 class FileSelectionList(QtWidgets.QWidget):
     selectionChanged = QtCore.pyqtSignal(QtCore.QVariant)
     listCleared = QtCore.pyqtSignal()
@@ -63,7 +58,7 @@ class FileSelectionList(QtWidgets.QWidget):
 
         reduce_widget_font_size(self.twList)
 
-        self.twList.setColumnCount(6)
+        self.twList.horizontalHeader().setMinimumSectionSize(50)
         self.twList.currentItemChanged.connect(self.current_item_changed_cb)
 
         self.currentItem = None
@@ -278,8 +273,8 @@ class FileSelectionList(QtWidgets.QWidget):
 
             filename_item = QtWidgets.QTableWidgetItem()
             folder_item = QtWidgets.QTableWidgetItem()
-            md_item = FileTableWidgetItem()
-            readonly_item = FileTableWidgetItem()
+            md_item = QtWidgets.QTableWidgetItem()
+            readonly_item = QtWidgets.QTableWidgetItem()
             type_item = QtWidgets.QTableWidgetItem()
 
             filename_item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
@@ -333,9 +328,12 @@ class FileSelectionList(QtWidgets.QWidget):
             if not ca.is_writable():
                 readonly_item.setCheckState(QtCore.Qt.CheckState.Checked)
                 readonly_item.setData(QtCore.Qt.ItemDataRole.UserRole, True)
+                readonly_item.setText(" ")
             else:
                 readonly_item.setData(QtCore.Qt.ItemDataRole.UserRole, False)
                 readonly_item.setCheckState(QtCore.Qt.CheckState.Unchecked)
+                # This is a nbsp it sorts after a space ' '
+                readonly_item.setText("\xa0")
 
     def get_selected_archive_list(self) -> list[ComicArchive]:
         ca_list: list[ComicArchive] = []

comictaggerlib/imagehasher.py

@@ -34,13 +34,19 @@ logger = logging.getLogger(__name__)
 
 
 class ImageHasher:
-    def __init__(self, path: str | None = None, data: bytes = b"", width: int = 8, height: int = 8) -> None:
+    def __init__(
+        self, path: str | None = None, image: Image | None = None, data: bytes = b"", width: int = 8, height: int = 8
+    ) -> None:
         self.width = width
         self.height = height
 
-        if path is None and not data:
+        if path is None and not data and not image:
             raise OSError
 
+        if image is not None:
+            self.image = image
+            return
+
         try:
             if path is not None:
                 self.image = Image.open(path)

comictaggerlib/issueidentifier.py

@@ -24,8 +24,8 @@ from typing import Any, Callable
 from typing_extensions import NotRequired, TypedDict
 
 from comicapi import utils
-from comicapi.comicarchive import ComicArchive, metadata_styles
-from comicapi.genericmetadata import GenericMetadata
+from comicapi.comicarchive import ComicArchive
+from comicapi.genericmetadata import ComicSeries, GenericMetadata
 from comicapi.issuestring import IssueString
 from comictaggerlib.ctsettings import ct_ns
 from comictaggerlib.imagefetcher import ImageFetcher, ImageFetcherException
@@ -44,17 +44,23 @@ except ImportError:
 
 
 class SearchKeys(TypedDict):
-    series: str | None
-    issue_number: str | None
+    series: str
+    issue_number: str
+    alternate_number: str | None
     month: int | None
     year: int | None
     issue_count: int | None
+    alternate_count: int | None
+    publisher: str | None
+    imprint: str | None
 
 
 class Score(TypedDict):
     score: NotRequired[int]
     url: str
-    hash: int
+    remote_hash: int
+    local_hash_name: str
+    local_hash: int
 
 
 class IssueIdentifierNetworkError(Exception): ...
@@ -71,10 +77,17 @@ class IssueIdentifier:
     result_one_good_match = 4
     result_multiple_good_matches = 5
 
-    def __init__(self, comic_archive: ComicArchive, config: ct_ns, talker: ComicTalker) -> None:
+    def __init__(
+        self,
+        comic_archive: ComicArchive,
+        config: ct_ns,
+        talker: ComicTalker,
+        metadata: GenericMetadata = GenericMetadata(),
+    ) -> None:
         self.config = config
         self.talker = talker
         self.comic_archive: ComicArchive = comic_archive
+        self.md = metadata
         self.image_hasher = 1
 
         self.only_use_additional_meta_data = False
@@ -139,35 +152,21 @@ class IssueIdentifier:
 
         return ImageHasher(data=image_data).average_hash()
 
-    def get_aspect_ratio(self, image_data: bytes) -> float:
-        try:
-            im = Image.open(io.BytesIO(image_data))
-            w, h = im.size
-            return float(h) / float(w)
-        except Exception:
-            return 1.5
-
-    def crop_cover(self, image_data: bytes) -> bytes:
-        im = Image.open(io.BytesIO(image_data))
+    def _crop_double_page(self, im: Image.Image) -> Image.Image | None:
         w, h = im.size
 
         try:
             cropped_im = im.crop((int(w / 2), 0, w, h))
         except Exception:
             logger.exception("cropCover() error")
-            return b""
+            return None
 
-        output = io.BytesIO()
-        cropped_im.convert("RGB").save(output, format="PNG")
-        cropped_image_data = output.getvalue()
-        output.close()
-
-        return cropped_image_data
+        return cropped_im
 
     # Adapted from https://stackoverflow.com/a/10616717/20629671
-    def crop_border(self, image_data: bytes, ratio: int) -> bytes | None:
-        im = Image.open(io.BytesIO(image_data))
-
+    def _crop_border(self, im: Image.Image, ratio: int) -> Image.Image | None:
+        assert Image
+        assert ImageChops
         # RGBA doesn't work????
         tmp = im.convert("RGB")
 
@@ -199,11 +198,7 @@ class IssueIdentifier:
 
         # If there is a difference return the image otherwise return None
         if width_percent > ratio or height_percent > ratio:
-            output = io.BytesIO()
-            im.crop(bbox).save(output, format="PNG")
-            cropped_image_data = output.getvalue()
-            output.close()
-            return cropped_image_data
+            return im.crop(bbox)
         return None
 
     def set_progress_callback(self, cb_func: Callable[[int, int], None]) -> None:
@@ -212,57 +207,6 @@ class IssueIdentifier:
     def set_cover_url_callback(self, cb_func: Callable[[bytes], None]) -> None:
         self.cover_url_callback = cb_func
 
-    def get_search_keys(self) -> SearchKeys:
-        ca = self.comic_archive
-
-        search_keys: SearchKeys
-        if self.only_use_additional_meta_data:
-            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
-        try:
-            for style in metadata_styles:
-                internal_metadata = ca.read_metadata(style)
-                if not internal_metadata.is_empty:
-                    break
-        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(
-            self.config.Filename_Parsing__complicated_parser,
-            self.config.Filename_Parsing__remove_c2c,
-            self.config.Filename_Parsing__remove_fcbd,
-            self.config.Filename_Parsing__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
-        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
-
     def log_msg(self, msg: Any) -> None:
         msg = str(msg)
         for handler in logging.getLogger().handlers:
@@ -291,70 +235,62 @@ class IssueIdentifier:
         # default output is stdout
         self.output_function(*args, **kwargs)
 
-    def get_issue_cover_match_score(
+    def _get_remote_hashes(self, urls: list[str]) -> list[tuple[str, int]]:
+        remote_hashes: list[tuple[str, int]] = []
+        for url in urls:
+            try:
+                alt_url_image_data = ImageFetcher(self.config.Runtime_Options__config.user_cache_dir).fetch(
+                    url, blocking=True
+                )
+            except ImageFetcherException as e:
+                self.log_msg(f"Network issue while fetching alt. cover image from {self.talker.name}. Aborting...")
+                raise IssueIdentifierNetworkError from e
+
+            self._user_canceled(self.cover_url_callback, alt_url_image_data)
+
+            remote_hashes.append((url, self.calculate_hash(alt_url_image_data)))
+
+            if self.cancel:
+                raise IssueIdentifierCancelled
+        return remote_hashes
+
+    def _get_issue_cover_match_score(
         self,
         primary_img_url: str,
         alt_urls: list[str],
-        local_cover_hash_list: list[int],
-        use_remote_alternates: bool = False,
+        local_hashes: list[tuple[str, int]],
+        use_alt_urls: bool = False,
     ) -> Score:
-        # local_cover_hash_list is a list of pre-calculated hashes.
-        # use_remote_alternates - indicates to use alternate covers from CV
+        # local_hashes is a list of pre-calculated hashes.
+        # use_alt_urls - indicates to use alternate covers from CV
 
         # If there is no URL return 100
         if not primary_img_url:
-            return Score(score=100, url="", hash=0)
+            return Score(score=100, url="", remote_hash=0)
 
-        try:
-            url_image_data = ImageFetcher(self.config.Runtime_Options__config.user_cache_dir).fetch(
-                primary_img_url, blocking=True
-            )
-        except ImageFetcherException as e:
-            self.log_msg(f"Network issue while fetching cover image from {self.talker.name}. Aborting...")
-            raise IssueIdentifierNetworkError from e
+        self._user_canceled()
 
-        if self.cancel:
-            raise IssueIdentifierCancelled
+        urls = [primary_img_url]
+        if use_alt_urls:
+            urls.extend(alt_urls)
+            self.log_msg(f"[{len(alt_urls)} alt. covers]")
 
-        # alert the GUI, if needed
-        if self.cover_url_callback is not None:
-            self.cover_url_callback(url_image_data)
-
-        remote_cover_list = [Score(url=primary_img_url, hash=self.calculate_hash(url_image_data))]
-
-        if self.cancel:
-            raise IssueIdentifierCancelled
-
-        if use_remote_alternates:
-            for alt_url in alt_urls:
-                try:
-                    alt_url_image_data = ImageFetcher(self.config.Runtime_Options__config.user_cache_dir).fetch(
-                        alt_url, blocking=True
-                    )
-                except ImageFetcherException as e:
-                    self.log_msg(f"Network issue while fetching alt. cover image from {self.talker.name}. Aborting...")
-                    raise IssueIdentifierNetworkError from e
-
-                if self.cancel:
-                    raise IssueIdentifierCancelled
-
-                # alert the GUI, if needed
-                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)))
-
-                if self.cancel:
-                    raise IssueIdentifierCancelled
-
-            self.log_msg(f"[{len(remote_cover_list) - 1} alt. covers]")
+        remote_hashes = self._get_remote_hashes(urls)
 
         score_list = []
         done = False
-        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"]))
+        for local_hash in local_hashes:
+            for remote_hash in remote_hashes:
+                score = ImageHasher.hamming_distance(local_hash[1], remote_hash[1])
+                score_list.append(
+                    Score(
+                        score=score,
+                        url=remote_hash[0],
+                        remote_hash=remote_hash[1],
+                        local_hash_name=local_hash[0],
+                        local_hash=local_hash[1],
+                    )
+                )
 
                 self.log_msg(f" -  {score:03}")
 
@@ -369,167 +305,181 @@ class IssueIdentifier:
 
         return best_score_item
 
-    def search(self) -> list[IssueResult]:
-        ca = self.comic_archive
-        self.match_list = []
-        self.cancel = False
-        self.search_result = self.result_no_matches
+    def _check_requirements(self, ca: ComicArchive) -> bool:
 
         if not pil_available:
             self.log_msg("Python Imaging Library (PIL) is not available and is needed for issue identification.")
-            return self.match_list
+            return False
 
         if not ca.seems_to_be_a_comic_archive():
             self.log_msg(f"Sorry, but {ca.path} is not a comic archive!")
-            return self.match_list
+            return False
+        return True
 
-        cover_image_data = ca.get_page(self.cover_page_index)
-        cover_hash = self.calculate_hash(cover_image_data)
+    def _process_cover(self, name: str, image_data: bytes) -> list[tuple[str, Image.Image]]:
+        assert Image
+        cover_image = Image.open(io.BytesIO(image_data))
+        images = [(name, cover_image)]
 
         # check the aspect ratio
-        # if it's wider than it is high, it's probably a two page spread
+        # if it's wider than it is high, it's probably a two page spread (back_cover, front_cover)
         # if so, crop it and calculate a second hash
-        narrow_cover_hash = None
-        aspect_ratio = self.get_aspect_ratio(cover_image_data)
+        aspect_ratio = float(cover_image.height) / float(cover_image.width)
         if aspect_ratio < 1.0:
-            right_side_image_data = self.crop_cover(cover_image_data)
-            if right_side_image_data is not None:
-                narrow_cover_hash = self.calculate_hash(right_side_image_data)
+            im = self._crop_double_page(cover_image)
+            if im is not None:
+                images.append(("double page", im))
 
-        keys = self.get_search_keys()
-        # normalize the issue number, None will return as ""
-        keys["issue_number"] = IssueString(keys["issue_number"]).as_string()
+        # Check and remove black borders. Helps in identifying comics with an excessive black border like https://comicvine.gamespot.com/marvel-graphic-novel-1-the-death-of-captain-marvel/4000-21782/
+        cropped = self._crop_border(cover_image, self.config.Issue_Identifier__border_crop_percent)
+        if cropped is not None:
+            images.append(("black border cropped", cropped))
 
-        # we need, at minimum, a series and issue number
-        if not (keys["series"] and keys["issue_number"]):
-            self.log_msg("Not enough info for a search!")
-            return []
+        return images
 
+    def _get_images(self, ca: ComicArchive, md: GenericMetadata) -> list[tuple[str, Image.Image]]:
+        covers: list[tuple[str, Image.Image]] = []
+        for cover_index in md.get_cover_page_index_list():
+            image_data = ca.get_page(cover_index)
+            covers.extend(self._process_cover(f"{cover_index}", image_data))
+        return covers
+
+    def _get_extra_images(self, ca: ComicArchive, md: GenericMetadata) -> list[tuple[str, Image.Image]]:
+        assert md
+        covers: list[tuple[str, Image.Image]] = []
+        for cover_index in range(1, min(3, ca.get_number_of_pages())):
+            image_data = ca.get_page(cover_index)
+            covers.extend(self._process_cover(f"{cover_index}", image_data))
+        return covers
+
+    def _get_search_keys(self, md: GenericMetadata) -> Any:
+        search_keys = SearchKeys(
+            series=md.series,
+            issue_number=IssueString(md.issue).as_string(),
+            alternate_number=IssueString(md.alternate_number).as_string(),
+            month=md.month,
+            year=md.year,
+            issue_count=md.issue_count,
+            alternate_count=md.alternate_count,
+            publisher=md.publisher,
+            imprint=md.imprint,
+        )
+        return search_keys
+
+    def _get_search_terms(
+        self, ca: ComicArchive, md: GenericMetadata
+    ) -> tuple[SearchKeys, list[tuple[str, Image.Image]], list[tuple[str, Image.Image]]]:
+        return self._get_search_keys(md), self._get_images(ca, md), self._get_extra_images(ca, md)
+
+    def _user_canceled(self, callback: Callable[..., Any] | None = None, *args: Any) -> Any:
+        if self.cancel:
+            raise IssueIdentifierCancelled
+        if callback is not None:
+            return callback(*args)
+
+    def _print_terms(self, keys: SearchKeys, images: list[tuple[str, Image.Image]]) -> None:
+        assert keys["series"]
+        assert keys["issue_number"]
         self.log_msg(f"Using {self.talker.name} to search for:")
         self.log_msg("\tSeries: " + keys["series"])
         self.log_msg("\tIssue:  " + keys["issue_number"])
-        if keys["issue_count"] is not None:
-            self.log_msg("\tCount:  " + str(keys["issue_count"]))
-        if keys["year"] is not None:
-            self.log_msg("\tYear:   " + str(keys["year"]))
+        # if keys["alternate_number"] is not None:
+        #     self.log_msg("\tAlternate Issue:  " + str(keys["alternate_number"]))
         if keys["month"] is not None:
             self.log_msg("\tMonth:  " + str(keys["month"]))
+        if keys["year"] is not None:
+            self.log_msg("\tYear:   " + str(keys["year"]))
+        if keys["issue_count"] is not None:
+            self.log_msg("\tCount:  " + str(keys["issue_count"]))
+        # if keys["alternate_count"] is not None:
+        #     self.log_msg("\tAlternate Count:  " + str(keys["alternate_count"]))
+        # if keys["publisher"] is not None:
+        #     self.log_msg("\tPublisher:  " + str(keys["publisher"]))
+        # if keys["imprint"] is not None:
+        #     self.log_msg("\tImprint:  " + str(keys["imprint"]))
+        for name, _ in images:
+            self.log_msg("Cover: " + name)
 
         self.log_msg(f"Searching for {keys['series']} #{keys['issue_number']} ...")
-        try:
-            ct_search_results = self.talker.search_for_series(keys["series"])
-        except TalkerError as e:
-            self.log_msg(f"Error searching for series.\n{e}")
-            return []
 
-        if self.cancel:
-            return []
+    def _filter_series(self, terms: SearchKeys, search_results: list[ComicSeries]) -> list[ComicSeries]:
+        assert terms["series"]
 
-        if ct_search_results is None:
-            return []
-
-        series_second_round_list = []
-
-        for item in ct_search_results:
+        filtered_results = []
+        for item in search_results:
             length_approved = False
             publisher_approved = True
             date_approved = True
 
             # remove any series that starts after the issue year
-            if keys["year"] is not None and item.start_year is not None:
-                if keys["year"] < item.start_year:
+            if terms["year"] is not None and item.start_year is not None:
+                if terms["year"] < item.start_year:
                     date_approved = False
 
             for name in [item.name, *item.aliases]:
-                if utils.titles_match(keys["series"], name, self.series_match_thresh):
+                if utils.titles_match(terms["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
-                if publisher is not None and publisher.casefold() in self.publisher_filter:
+                if item.publisher is not None and item.publisher.casefold() in self.publisher_filter:
                     publisher_approved = False
 
             if length_approved and publisher_approved and date_approved:
-                series_second_round_list.append(item)
-
-        self.log_msg("Searching in " + str(len(series_second_round_list)) + " series")
-
-        if self.progress_callback is not None:
-            self.progress_callback(0, len(series_second_round_list))
-
-        # now sort the list by name length
-        series_second_round_list.sort(key=lambda x: len(x.name), reverse=False)
-
-        series_by_id = {series.id: series for series in series_second_round_list}
-
-        issue_list = None
-        try:
-            if len(series_by_id) > 0:
-                issue_list = self.talker.fetch_issues_by_series_issue_num_and_year(
-                    list(series_by_id.keys()), keys["issue_number"], keys["year"]
+                filtered_results.append(item)
+            else:
+                logger.debug(
+                    "Filtered out series: '%s' length approved: '%s', publisher approved: '%s', date approved: '%s'",
+                    item.name,
+                    length_approved,
+                    publisher_approved,
+                    date_approved,
                 )
-        except TalkerError as e:
-            self.log_msg(f"Issue with while searching for series details. Aborting...\n{e}")
-            return []
+        return filtered_results
 
-        if issue_list is None:
-            return []
+    def _calculate_hashes(self, images: list[tuple[str, Image.Image]]) -> list[tuple[str, int]]:
+        hashes = []
+        for name, image in images:
+            hashes.append((name, ImageHasher(image=image).average_hash()))
+        return hashes
 
-        shortlist = []
-        # now re-associate the issues and series
-        # is this really needed?
-        for issue in issue_list:
-            if issue.series_id in series_by_id:
-                shortlist.append((series_by_id[issue.series_id], issue))
-
-        if keys["year"] is None:
-            self.log_msg(f"Found {len(shortlist)} series that have an issue #{keys['issue_number']}")
-        else:
-            self.log_msg(
-                f"Found {len(shortlist)} series that have an issue #{keys['issue_number']} from {keys['year']}"
-            )
-
-        # now we have a shortlist of series with the desired issue number
-        # Do first round of cover matching
-        counter = len(shortlist)
-        for series, issue in shortlist:
-            if self.progress_callback is not None:
-                self.progress_callback(counter, len(shortlist) * 3)
-                counter += 1
+    def _match_covers(
+        self,
+        terms: SearchKeys,
+        images: list[tuple[str, Image.Image]],
+        issues: list[tuple[ComicSeries, GenericMetadata]],
+        use_alternates: bool,
+    ) -> list[IssueResult]:
+        assert terms["issue_number"]
+        match_results: list[IssueResult] = []
+        hashes = self._calculate_hashes(images)
+        counter = 0
+        alternate = ""
+        if use_alternates:
+            alternate = " Alternate"
+        for series, issue in issues:
+            self._user_canceled(self.progress_callback, counter, len(issues))
+            counter += 1
 
             self.log_msg(
-                f"Examining covers for  ID: {series.id} {series.name} ({series.start_year}):",
+                f"Examining{alternate} covers for Series ID: {series.id} {series.name} ({series.start_year}):",
             )
 
-            # Now check the cover match against the primary image
-            hash_list = [cover_hash]
-            if narrow_cover_hash is not None:
-                hash_list.append(narrow_cover_hash)
-
-            cropped_border = self.crop_border(cover_image_data, self.config.Issue_Identifier__border_crop_percent)
-            if cropped_border is not None:
-                hash_list.append(self.calculate_hash(cropped_border))
-                logger.info("Adding cropped cover to the hashlist")
-
             try:
                 image_url = issue._cover_image or ""
                 alt_urls = issue._alternate_images
 
-                score_item = self.get_issue_cover_match_score(
-                    image_url, alt_urls, hash_list, use_remote_alternates=False
-                )
+                score_item = self._get_issue_cover_match_score(image_url, alt_urls, hashes, use_alt_urls=use_alternates)
             except Exception:
-                logger.exception("Scoring series failed")
-                self.match_list = []
-                return self.match_list
+                logger.exception(f"Scoring series{alternate} covers failed")
+                return []
 
             match = IssueResult(
                 series=f"{series.name} ({series.start_year})",
                 distance=score_item["score"],
-                issue_number=keys["issue_number"],
-                cv_issue_count=series.count_of_issues,
-                url_image_hash=score_item["hash"],
+                issue_number=terms["issue_number"],
+                issue_count=series.count_of_issues,
+                url_image_hash=score_item["remote_hash"],
                 issue_title=issue.title or "",
                 issue_id=issue.issue_id or "",
                 series_id=series.id,
@@ -543,142 +493,188 @@ class IssueIdentifier:
             if series.publisher is not None:
                 match.publisher = series.publisher
 
-            self.match_list.append(match)
+            match_results.append(match)
 
             self.log_msg(f"best score {match.distance:03}")
 
             self.log_msg("")
+        return match_results
 
-        if len(self.match_list) == 0:
+    def _print_match(self, item: IssueResult) -> None:
+        self.log_msg(
+            "-----> {} #{} {} ({}/{}) -- score: {}".format(
+                item.series,
+                item.issue_number,
+                item.issue_title,
+                item.month,
+                item.year,
+                item.distance,
+            )
+        )
+
+    def _search_for_issues(self, terms: SearchKeys) -> list[tuple[ComicSeries, GenericMetadata]]:
+        try:
+            search_results = self.talker.search_for_series(
+                terms["series"],
+                callback=lambda x, y: self._user_canceled(self.progress_callback, x, y),
+                series_match_thresh=self.config.Issue_Identifier__series_match_search_thresh,
+            )
+        except TalkerError as e:
+            self.log_msg(f"Error searching for series.\n{e}")
+            return []
+        # except IssueIdentifierCancelled:
+        #     return []
+
+        if not search_results:
+            return []
+
+        filtered_series = self._filter_series(terms, search_results)
+        if not filtered_series:
+            return []
+
+        self.log_msg(f"Searching in {len(filtered_series)} series")
+
+        self._user_canceled(self.progress_callback, 0, len(filtered_series))
+
+        series_by_id = {series.id: series for series in filtered_series}
+
+        try:
+            talker_result = self.talker.fetch_issues_by_series_issue_num_and_year(
+                list(series_by_id.keys()), terms["issue_number"], terms["year"]
+            )
+        except TalkerError as e:
+            self.log_msg(f"Issue with while searching for series details. Aborting...\n{e}")
+            return []
+        # except IssueIdentifierCancelled:
+        #     return []
+
+        if not talker_result:
+            return []
+
+        self._user_canceled(self.progress_callback, 0, 0)
+
+        issues: list[tuple[ComicSeries, GenericMetadata]] = []
+
+        # now re-associate the issues and series
+        for issue in talker_result:
+            if issue.series_id in series_by_id:
+                issues.append((series_by_id[issue.series_id], issue))
+            else:
+                logger.warning("Talker '%s' is returning arbitrary series when searching by id", self.talker.id)
+        return issues
+
+    def _cover_matching(
+        self,
+        terms: SearchKeys,
+        images: list[tuple[str, Image.Image]],
+        extra_images: list[tuple[str, Image.Image]],
+        issues: list[tuple[ComicSeries, GenericMetadata]],
+    ) -> list[IssueResult]:
+        cover_matching_1 = self._match_covers(terms, images, issues, use_alternates=False)
+
+        if len(cover_matching_1) == 0:
             self.log_msg(":-( no matches!")
-            self.search_result = self.result_no_matches
-            return self.match_list
+            return cover_matching_1
 
         # sort list by image match scores
-        self.match_list.sort(key=attrgetter("distance"))
+        cover_matching_1.sort(key=attrgetter("distance"))
 
         lst = []
-        for i in self.match_list:
+        for i in cover_matching_1:
             lst.append(i.distance)
 
-        self.log_msg(f"Compared to covers in {len(self.match_list)} issue(s): {lst}")
+        self.log_msg(f"Compared to covers in {len(cover_matching_1)} issue(s): {lst}")
 
-        def print_match(item: IssueResult) -> None:
-            self.log_msg(
-                "-----> {} #{} {} ({}/{}) -- score: {}".format(
-                    item.series,
-                    item.issue_number,
-                    item.issue_title,
-                    item.month,
-                    item.year,
-                    item.distance,
-                )
-            )
-
-        best_score: int = self.match_list[0].distance
-
-        if best_score >= self.min_score_thresh:
+        cover_matching_2 = []
+        final_cover_matching = cover_matching_1
+        if cover_matching_1[0].distance >= self.min_score_thresh:
             # we have 1 or more low-confidence matches (all bad cover scores)
             # look at a few more pages in the archive, and also alternate covers online
             self.log_msg("Very weak scores for the cover. Analyzing alternate pages and covers...")
-            hash_list = [cover_hash]
-            if narrow_cover_hash is not None:
-                hash_list.append(narrow_cover_hash)
-            for page_index in range(1, min(3, ca.get_number_of_pages())):
-                image_data = ca.get_page(page_index)
-                page_hash = self.calculate_hash(image_data)
-                hash_list.append(page_hash)
 
-            second_match_list = []
-            counter = 2 * len(self.match_list)
-            for m in self.match_list:
-                if self.progress_callback is not None:
-                    self.progress_callback(counter, len(self.match_list) * 3)
-                    counter += 1
-                self.log_msg(f"Examining alternate covers for ID: {m.series_id} {m.series}:")
-                try:
-                    score_item = self.get_issue_cover_match_score(
-                        m.image_url,
-                        m.alt_image_urls,
-                        hash_list,
-                        use_remote_alternates=True,
-                    )
-                except Exception:
-                    logger.exception("failed examining alt covers")
-                    self.match_list = []
-                    return self.match_list
-                self.log_msg(f"--->{score_item['score']}")
-                self.log_msg("")
+            temp = self._match_covers(terms, images + extra_images, issues, use_alternates=True)
+            for score in temp:
+                if score.distance < self.min_alternate_score_thresh:
+                    cover_matching_2.append(score)
 
-                if score_item["score"] < self.min_alternate_score_thresh:
-                    second_match_list.append(m)
-                    m.distance = score_item["score"]
+            if len(cover_matching_2) > 0:
+                # We did good, found something!
+                self.log_msg("Success in secondary/alternate cover matching!")
 
-            if len(second_match_list) == 0:
-                if len(self.match_list) == 1:
-                    self.log_msg("No matching pages in the issue.")
-                    self.log_msg("--------------------------------------------------------------------------")
-                    print_match(self.match_list[0])
-                    self.log_msg("--------------------------------------------------------------------------")
-                    self.search_result = self.result_found_match_but_bad_cover_score
-                else:
-                    self.log_msg("--------------------------------------------------------------------------")
-                    self.log_msg("Multiple bad cover matches!  Need to use other info...")
-                    self.log_msg("--------------------------------------------------------------------------")
-                    self.search_result = self.result_multiple_matches_with_bad_image_scores
-                return self.match_list
-
-            # We did good, found something!
-            self.log_msg("Success in secondary/alternate cover matching!")
-
-            self.match_list = second_match_list
-            # sort new list by image match scores
-            self.match_list.sort(key=attrgetter("distance"))
-            best_score = self.match_list[0].distance
-            self.log_msg("[Second round cover matching: best score = {best_score}]")
-            # now drop down into the rest of the processing
-
-        if self.progress_callback is not None:
-            self.progress_callback(99, 100)
+                final_cover_matching = cover_matching_2
+                # sort new list by image match scores
+                final_cover_matching.sort(key=attrgetter("distance"))
+                self.log_msg("[Second round cover matching: best score = {best_score}]")
+                # now drop down into the rest of the processing
 
+        best_score = final_cover_matching[0].distance
         # now pare down list, remove any item more than specified distant from the top scores
-        for match_item in reversed(self.match_list):
-            if match_item.distance > best_score + self.min_score_distance:
-                self.match_list.remove(match_item)
+        for match_item in reversed(final_cover_matching):
+            if match_item.distance > (best_score + self.min_score_distance):
+                final_cover_matching.remove(match_item)
+        return final_cover_matching
+
+    def identify(self, ca: ComicArchive, md: GenericMetadata) -> tuple[int, list[IssueResult]]:
+        if not self._check_requirements(ca):
+            return self.result_no_matches, []
+
+        terms, images, extra_images = self._get_search_terms(ca, md)
+
+        # we need, at minimum, a series and issue number
+        if not (terms["series"] and terms["issue_number"]):
+            self.log_msg("Not enough info for a search!")
+            return self.result_no_matches, []
+
+        self._print_terms(terms, images)
+
+        issues = self._search_for_issues(terms)
+
+        self.log_msg(f"Found {len(issues)} series that have an issue #{terms['issue_number']}")
+
+        final_cover_matching = self._cover_matching(terms, images, extra_images, issues)
 
         # One more test for the case choosing limited series first issue vs a trade with the same cover:
         # if we have a given issue count > 1 and the series from CV has count==1, remove it from match list
-        if len(self.match_list) >= 2 and keys["issue_count"] is not None and keys["issue_count"] != 1:
-            new_list = []
-            for match in self.match_list:
-                if match.cv_issue_count != 1:
-                    new_list.append(match)
-                else:
+        if len(final_cover_matching) > 1 and terms["issue_count"] is not None and terms["issue_count"] != 1:
+            for match in final_cover_matching.copy():
+                if match.issue_count == 1:
                     self.log_msg(
                         f"Removing series {match.series} [{match.series_id}] from consideration (only 1 issue)"
                     )
+                    final_cover_matching.remove(match)
 
-            if len(new_list) > 0:
-                self.match_list = new_list
-
-        if len(self.match_list) == 1:
-            self.log_msg("--------------------------------------------------------------------------")
-            print_match(self.match_list[0])
-            self.log_msg("--------------------------------------------------------------------------")
-            self.search_result = self.result_one_good_match
-
-        elif len(self.match_list) == 0:
-            self.log_msg("--------------------------------------------------------------------------")
-            self.log_msg("No matches found :(")
-            self.log_msg("--------------------------------------------------------------------------")
-            self.search_result = self.result_no_matches
+        best_score = final_cover_matching[0].distance
+        if best_score >= self.min_score_thresh:
+            if len(final_cover_matching) == 1:
+                self.log_msg("No matching pages in the issue.")
+                self.log_msg("--------------------------------------------------------------------------")
+                self._print_match(final_cover_matching[0])
+                self.log_msg("--------------------------------------------------------------------------")
+                search_result = self.result_found_match_but_bad_cover_score
+            else:
+                self.log_msg("--------------------------------------------------------------------------")
+                self.log_msg("Multiple bad cover matches!  Need to use other info...")
+                self.log_msg("--------------------------------------------------------------------------")
+                search_result = self.result_multiple_matches_with_bad_image_scores
         else:
-            # we've got multiple good matches:
-            self.log_msg("More than one likely candidate.")
-            self.search_result = self.result_multiple_good_matches
-            self.log_msg("--------------------------------------------------------------------------")
-            for match_item in self.match_list:
-                print_match(match_item)
-            self.log_msg("--------------------------------------------------------------------------")
+            if len(final_cover_matching) == 1:
+                self.log_msg("--------------------------------------------------------------------------")
+                self._print_match(final_cover_matching[0])
+                self.log_msg("--------------------------------------------------------------------------")
+                search_result = self.result_one_good_match
 
-        return self.match_list
+            elif len(self.match_list) == 0:
+                self.log_msg("--------------------------------------------------------------------------")
+                self.log_msg("No matches found :(")
+                self.log_msg("--------------------------------------------------------------------------")
+                search_result = self.result_no_matches
+            else:
+                # we've got multiple good matches:
+                self.log_msg("More than one likely candidate.")
+                search_result = self.result_multiple_good_matches
+                self.log_msg("--------------------------------------------------------------------------")
+                for match_item in final_cover_matching:
+                    self._print_match(match_item)
+                self.log_msg("--------------------------------------------------------------------------")
+
+        return search_result, final_cover_matching

comictaggerlib/renamewindow.py

@@ -84,7 +84,7 @@ class RenameWindow(QtWidgets.QDialog):
             md = ca.read_metadata(self.data_style)
             if md.is_empty:
                 md = ca.metadata_from_filename(
-                    self.config[0].Filename_Parsing__complicated_parser,
+                    self.config[0].Filename_Parsing__filename_parser,
                     self.config[0].Filename_Parsing__remove_c2c,
                     self.config[0].Filename_Parsing__remove_fcbd,
                     self.config[0].Filename_Parsing__remove_publisher,

comictaggerlib/resulttypes.py

@@ -2,58 +2,18 @@ from __future__ import annotations
 
 import dataclasses
 import pathlib
-import sys
-from enum import Enum, auto
-from typing import Any
+from enum import auto
 
 from comicapi import utils
 from comicapi.genericmetadata import GenericMetadata
 
-if sys.version_info < (3, 11):
-
-    class StrEnum(str, Enum):
-        """
-        Enum where members are also (and must be) strings
-        """
-
-        def __new__(cls, *values: Any) -> Any:
-            "values must already be of type `str`"
-            if len(values) > 3:
-                raise TypeError(f"too many arguments for str(): {values!r}")
-            if len(values) == 1:
-                # it must be a string
-                if not isinstance(values[0], str):
-                    raise TypeError(f"{values[0]!r} is not a string")
-            if len(values) >= 2:
-                # check that encoding argument is a string
-                if not isinstance(values[1], str):
-                    raise TypeError(f"encoding must be a string, not {values[1]!r}")
-            if len(values) == 3:
-                # check that errors argument is a string
-                if not isinstance(values[2], str):
-                    raise TypeError("errors must be a string, not %r" % (values[2]))
-            value = str(*values)
-            member = str.__new__(cls, value)
-            member._value_ = value
-            return member
-
-        @staticmethod
-        def _generate_next_value_(name: str, start: int, count: int, last_values: Any) -> str:
-            """
-            Return the lower-cased version of the member name.
-            """
-            return name.lower()
-
-else:
-    from enum import StrEnum
-
 
 @dataclasses.dataclass
 class IssueResult:
     series: str
     distance: int
     issue_number: str
-    cv_issue_count: int | None
+    issue_count: int | None
     url_image_hash: int
     issue_title: str
     issue_id: str
@@ -69,7 +29,7 @@ class IssueResult:
         return f"series: {self.series}; series id: {self.series_id}; issue number: {self.issue_number}; issue id: {self.issue_id}; published: {self.month} {self.year}"
 
 
-class Action(StrEnum):
+class Action(utils.StrEnum):
     print = auto()
     delete = auto()
     copy = auto()
@@ -80,14 +40,14 @@ class Action(StrEnum):
     list_plugins = auto()
 
 
-class MatchStatus(StrEnum):
+class MatchStatus(utils.StrEnum):
     good_match = auto()
     no_match = auto()
     multiple_match = auto()
     low_confidence_match = auto()
 
 
-class Status(StrEnum):
+class Status(utils.StrEnum):
     success = auto()
     match_failure = auto()
     write_failure = auto()

comictaggerlib/seriesselectionwindow.py

@@ -33,6 +33,7 @@ from comictaggerlib.issueidentifier import IssueIdentifier
 from comictaggerlib.issueselectionwindow import IssueSelectionWindow
 from comictaggerlib.matchselectionwindow import MatchSelectionWindow
 from comictaggerlib.progresswindow import IDProgressWindow
+from comictaggerlib.resulttypes import IssueResult
 from comictaggerlib.ui import qtutils, ui_path
 from comictaggerlib.ui.qtutils import new_web_view, reduce_widget_font_size
 from comictalker.comictalker import ComicTalker, TalkerError
@@ -76,15 +77,17 @@ class SearchThread(QtCore.QThread):
 
 
 class IdentifyThread(QtCore.QThread):
-    identifyComplete = pyqtSignal()
+    identifyComplete = pyqtSignal((int, list))
     identifyLogMsg = pyqtSignal(str)
     identifyProgress = pyqtSignal(int, int)
 
-    def __init__(self, identifier: IssueIdentifier) -> None:
+    def __init__(self, identifier: IssueIdentifier, ca: ComicArchive, md: GenericMetadata) -> None:
         QtCore.QThread.__init__(self)
         self.identifier = identifier
         self.identifier.set_output_function(self.log_output)
         self.identifier.set_progress_callback(self.progress_callback)
+        self.ca = ca
+        self.md = md
 
     def log_output(self, text: str) -> None:
         self.identifyLogMsg.emit(str(text))
@@ -93,8 +96,7 @@ class IdentifyThread(QtCore.QThread):
         self.identifyProgress.emit(cur, total)
 
     def run(self) -> None:
-        self.identifier.search()
-        self.identifyComplete.emit()
+        self.identifyComplete.emit(*self.identifier.identify(self.ca, self.md))
 
 
 class SeriesSelectionWindow(QtWidgets.QDialog):
@@ -245,12 +247,7 @@ class SeriesSelectionWindow(QtWidgets.QDialog):
         md.year = self.year
         md.issue_count = self.issue_count
 
-        self.ii.set_additional_metadata(md)
-        self.ii.only_use_additional_meta_data = True
-
-        self.ii.cover_page_index = int(self.cover_index_list[0])
-
-        self.id_thread = IdentifyThread(self.ii)
+        self.id_thread = IdentifyThread(self.ii, self.comic_archive, md)
         self.id_thread.identifyComplete.connect(self.identify_complete)
         self.id_thread.identifyLogMsg.connect(self.log_id_output)
         self.id_thread.identifyProgress.connect(self.identify_progress)
@@ -276,35 +273,33 @@ class SeriesSelectionWindow(QtWidgets.QDialog):
         if self.ii is not None:
             self.ii.cancel = True
 
-    def identify_complete(self) -> None:
-        if self.ii is not None and self.iddialog is not None and self.comic_archive is not None:
-            matches = self.ii.match_list
-            result = self.ii.search_result
+    def identify_complete(self, result: int, issues: list[IssueResult]) -> None:
+        if self.iddialog is not None and self.comic_archive is not None:
 
             found_match = None
             choices = False
-            if result == self.ii.result_no_matches:
-                QtWidgets.QMessageBox.information(self, "Auto-Select Result", " No matches found :-(")
-            elif result == self.ii.result_found_match_but_bad_cover_score:
+            if result == IssueIdentifier.result_no_matches:
+                QtWidgets.QMessageBox.information(self, "Auto-Select Result", " No issues found :-(")
+            elif result == IssueIdentifier.result_found_match_but_bad_cover_score:
                 QtWidgets.QMessageBox.information(
                     self,
                     "Auto-Select Result",
                     " Found a match, but cover doesn't seem the same.  Verify before committing!",
                 )
-                found_match = matches[0]
-            elif result == self.ii.result_found_match_but_not_first_page:
+                found_match = issues[0]
+            elif result == IssueIdentifier.result_found_match_but_not_first_page:
                 QtWidgets.QMessageBox.information(
                     self, "Auto-Select Result", " Found a match, but not with the first page of the archive."
                 )
-                found_match = matches[0]
-            elif result == self.ii.result_multiple_matches_with_bad_image_scores:
+                found_match = issues[0]
+            elif result == IssueIdentifier.result_multiple_matches_with_bad_image_scores:
                 QtWidgets.QMessageBox.information(
                     self, "Auto-Select Result", " Found some possibilities, but no confidence. Proceed manually."
                 )
                 choices = True
-            elif result == self.ii.result_one_good_match:
-                found_match = matches[0]
-            elif result == self.ii.result_multiple_good_matches:
+            elif result == IssueIdentifier.result_one_good_match:
+                found_match = issues[0]
+            elif result == IssueIdentifier.result_multiple_good_matches:
                 QtWidgets.QMessageBox.information(
                     self, "Auto-Select Result", " Found multiple likely matches.  Please select."
                 )
@@ -312,7 +307,7 @@ class SeriesSelectionWindow(QtWidgets.QDialog):
 
             if choices:
                 selector = MatchSelectionWindow(
-                    self, matches, self.comic_archive, talker=self.talker, config=self.config
+                    self, issues, self.comic_archive, talker=self.talker, config=self.config
                 )
                 selector.setModal(True)
                 selector.exec()

comictaggerlib/settingswindow.py

@@ -29,9 +29,11 @@ from PyQt5 import QtCore, QtGui, QtWidgets, uic
 
 import comictaggerlib.ui.talkeruigenerator
 from comicapi import utils
+from comicapi.archivers.archiver import Archiver
 from comicapi.genericmetadata import md_test
 from comictaggerlib import ctsettings
 from comictaggerlib.ctsettings import ct_ns
+from comictaggerlib.ctsettings.plugin import group_for_plugin
 from comictaggerlib.filerenamer import FileRenamer, Replacement, Replacements
 from comictaggerlib.ui import ui_path
 from comictalker.comictalker import ComicTalker
@@ -155,7 +157,6 @@ class SettingsWindow(QtWidgets.QDialog):
             self.lblRarHelp.setText(linuxRarHelp)
 
         elif platform.system() == "Darwin":
-            self.leRarExePath.setReadOnly(False)
 
             self.lblRarHelp.setText(macRarHelp)
             self.name = "Preferences"
@@ -191,6 +192,8 @@ class SettingsWindow(QtWidgets.QDialog):
         self.sources = comictaggerlib.ui.talkeruigenerator.generate_source_option_tabs(
             self.tComicTalkers, self.config, self.talkers
         )
+        self.cbFilenameParser.clear()
+        self.cbFilenameParser.addItems(utils.Parser)
         self.connect_signals()
         self.settings_to_form()
         self.rename_test()
@@ -208,7 +211,7 @@ class SettingsWindow(QtWidgets.QDialog):
         self.btnTemplateHelp.clicked.connect(self.show_template_help)
         self.cbxMoveFiles.clicked.connect(self.dir_test)
         self.leDirectory.textEdited.connect(self.dir_test)
-        self.cbxComplicatedParser.clicked.connect(self.switch_parser)
+        self.cbFilenameParser.currentIndexChanged.connect(self.switch_parser)
 
         self.btnAddLiteralReplacement.clicked.connect(self.addLiteralReplacement)
         self.btnAddValueReplacement.clicked.connect(self.addValueReplacement)
@@ -243,7 +246,7 @@ class SettingsWindow(QtWidgets.QDialog):
         self.btnResetSettings.clicked.disconnect()
         self.btnTemplateHelp.clicked.disconnect()
         self.cbxChangeExtension.clicked.disconnect()
-        self.cbxComplicatedParser.clicked.disconnect()
+        self.cbFilenameParser.currentIndexChanged.disconnect()
         self.cbxMoveFiles.clicked.disconnect()
         self.cbxRenameStrict.clicked.disconnect()
         self.cbxSmartCleanup.clicked.disconnect()
@@ -272,9 +275,10 @@ class SettingsWindow(QtWidgets.QDialog):
         self._filename_parser_test(self.leFilenameParserTest.text())
 
     def _filename_parser_test(self, filename: str) -> None:
+        self.cbFilenameParser: QtWidgets.QComboBox
         filename_info = utils.parse_filename(
             filename=filename,
-            complicated_parser=self.cbxComplicatedParser.isChecked(),
+            parser=utils.Parser(self.cbFilenameParser.currentText()),
             remove_c2c=self.cbxRemoveC2C.isChecked(),
             remove_fcbd=self.cbxRemoveFCBD.isChecked(),
             remove_publisher=self.cbxRemovePublisher.isChecked(),
@@ -357,18 +361,22 @@ class SettingsWindow(QtWidgets.QDialog):
             self.lblRenameTest.setText(str(e))
 
     def switch_parser(self) -> None:
-        complicated = self.cbxComplicatedParser.isChecked()
+        currentParser = utils.Parser(self.cbFilenameParser.currentText())
 
+        complicated = currentParser == utils.Parser.COMPLICATED
         self.cbxRemoveC2C.setEnabled(complicated)
         self.cbxRemoveFCBD.setEnabled(complicated)
         self.cbxRemovePublisher.setEnabled(complicated)
+        self.cbxProtofoliusIssueNumberScheme.setEnabled(complicated)
+        self.cbxAllowIssueStartWithLetter.setEnabled(complicated)
         self.filename_parser_test()
 
     def settings_to_form(self) -> None:
         self.disconnect_signals()
         # Copy values from settings to form
-        if "archiver" in self.config[1] and "rar" in self.config[1]["archiver"].v:
-            self.leRarExePath.setText(getattr(self.config[0], self.config[1]["archiver"].v["rar"].internal_name))
+        archive_group = group_for_plugin(Archiver)
+        if archive_group in self.config[1] and "rar" in self.config[1][archive_group].v:
+            self.leRarExePath.setText(getattr(self.config[0], self.config[1][archive_group].v["rar"].internal_name))
         else:
             self.leRarExePath.setEnabled(False)
         self.sbNameMatchIdentifyThresh.setValue(self.config[0].Issue_Identifier__series_match_identify_thresh)
@@ -378,7 +386,7 @@ class SettingsWindow(QtWidgets.QDialog):
         self.cbxCheckForNewVersion.setChecked(self.config[0].General__check_for_new_version)
         self.cbxShortMetadataNames.setChecked(self.config[0].General__use_short_metadata_names)
 
-        self.cbxComplicatedParser.setChecked(self.config[0].Filename_Parsing__complicated_parser)
+        self.cbFilenameParser.setCurrentText(self.config[0].Filename_Parsing__filename_parser)
         self.cbxRemoveC2C.setChecked(self.config[0].Filename_Parsing__remove_c2c)
         self.cbxRemoveFCBD.setChecked(self.config[0].Filename_Parsing__remove_fcbd)
         self.cbxRemovePublisher.setChecked(self.config[0].Filename_Parsing__remove_publisher)
@@ -482,11 +490,12 @@ class SettingsWindow(QtWidgets.QDialog):
                 )
 
         # Copy values from form to settings and save
-        if "archiver" in self.config[1] and "rar" in self.config[1]["archiver"].v:
-            setattr(self.config[0], self.config[1]["archiver"].v["rar"].internal_name, str(self.leRarExePath.text()))
+        archive_group = group_for_plugin(Archiver)
+        if archive_group in self.config[1] and "rar" in self.config[1][archive_group].v:
+            setattr(self.config[0], self.config[1][archive_group].v["rar"].internal_name, str(self.leRarExePath.text()))
 
             # make sure rar program is now in the path for the rar class
-            if self.config[0].archiver_rar:  # type: ignore[attr-defined]
+            if self.config[0].Archive__rar:
                 utils.add_to_path(os.path.dirname(str(self.leRarExePath.text())))
 
         if not str(self.leIssueNumPadding.text()).isdigit():
@@ -504,7 +513,7 @@ class SettingsWindow(QtWidgets.QDialog):
         self.config[0].Issue_Identifier__series_match_search_thresh = self.sbNameMatchSearchThresh.value()
         self.config[0].Issue_Identifier__publisher_filter = utils.split(self.tePublisherFilter.toPlainText(), "\n")
 
-        self.config[0].Filename_Parsing__complicated_parser = self.cbxComplicatedParser.isChecked()
+        self.config[0].Filename_Parsing__filename_parser = utils.Parser(self.cbFilenameParser.currentText())
         self.config[0].Filename_Parsing__remove_c2c = self.cbxRemoveC2C.isChecked()
         self.config[0].Filename_Parsing__remove_fcbd = self.cbxRemoveFCBD.isChecked()
         self.config[0].Filename_Parsing__remove_publisher = self.cbxRemovePublisher.isChecked()

comictaggerlib/taggerwindow.py

@@ -27,11 +27,12 @@ import sys
 import webbrowser
 from datetime import datetime
 from typing import Any, Callable
-from urllib.parse import urlparse
 
 import natsort
 import settngs
+import urllib3.util
 from PyQt5 import QtCore, QtGui, QtNetwork, QtWidgets, uic
+from urllib3.util.url import LocationParseError
 
 import comictaggerlib.ui
 from comicapi import utils
@@ -112,7 +113,7 @@ class TaggerWindow(QtWidgets.QMainWindow):
             "alternate_count": self.leAltIssueCount,
             "imprint": self.leImprint,
             "notes": self.teNotes,
-            "web_link": self.leWebLink,
+            "web_links": (self.leWebLink, self.btnOpenWebLink, self.btnAddWebLink, self.btnRemoveWebLink),
             "format": self.cbFormat,
             "manga": self.cbManga,
             "black_and_white": self.cbBW,
@@ -124,7 +125,7 @@ class TaggerWindow(QtWidgets.QMainWindow):
             "characters": self.teCharacters,
             "teams": self.teTeams,
             "locations": self.teLocations,
-            "credits": [self.twCredits, self.btnAddCredit, self.btnEditCredit, self.btnRemoveCredit],
+            "credits": (self.twCredits, self.btnAddCredit, self.btnEditCredit, self.btnRemoveCredit),
             "credits.person": 2,
             "credits.role": 1,
             "credits.primary": 0,
@@ -532,6 +533,31 @@ class TaggerWindow(QtWidgets.QMainWindow):
         self.toolBar.addAction(self.actionPageBrowser)
         self.toolBar.addAction(self.actionAutoImprint)
 
+        self.leWebLink.addAction(self.actionAddWebLink)
+        self.leWebLink.addAction(self.actionRemoveWebLink)
+
+        self.actionAddWebLink.triggered.connect(self.add_weblink_item)
+        self.actionRemoveWebLink.triggered.connect(self.remove_weblink_item)
+
+    def add_weblink_item(self, url: str = "") -> None:
+        item = ""
+        if isinstance(url, str):
+            item = url
+        self.leWebLink.addItem(item)
+        self.leWebLink.item(self.leWebLink.count() - 1).setFlags(
+            QtCore.Qt.ItemFlag.ItemIsEditable
+            | QtCore.Qt.ItemFlag.ItemIsEnabled
+            | QtCore.Qt.ItemFlag.ItemIsDragEnabled
+            | QtCore.Qt.ItemFlag.ItemIsSelectable
+        )
+        self.leWebLink.item(self.leWebLink.count() - 1).setSelected(True)
+        if not url:
+            self.leWebLink.editItem(self.leWebLink.item(self.leWebLink.count() - 1))
+
+    def remove_weblink_item(self) -> None:
+        item = self.leWebLink.takeItem(self.leWebLink.currentRow())
+        del item
+
     def repackage_archive(self) -> None:
         ca_list = self.fileSelectionList.get_selected_archive_list()
         non_zip_count = 0
@@ -784,6 +810,8 @@ class TaggerWindow(QtWidgets.QMainWindow):
             widget.currentIndexChanged.connect(self.set_dirty_flag)
         if isinstance(widget, QtWidgets.QCheckBox):
             widget.stateChanged.connect(self.set_dirty_flag)
+        if isinstance(widget, QtWidgets.QListWidget):
+            widget.itemChanged.connect(self.set_dirty_flag)
 
         # recursive call on children
         for child in widget.children():
@@ -844,7 +872,9 @@ class TaggerWindow(QtWidgets.QMainWindow):
         assign_text(self.leAltSeries, md.alternate_series)
         assign_text(self.leAltIssueNum, md.alternate_number)
         assign_text(self.leAltIssueCount, md.alternate_count)
-        assign_text(self.leWebLink, md.web_link)
+        self.leWebLink.clear()
+        for u in md.web_links:
+            self.add_weblink_item(u.url)
         assign_text(self.teCharacters, "\n".join(md.characters))
         assign_text(self.teTeams, "\n".join(md.teams))
         assign_text(self.teLocations, "\n".join(md.locations))
@@ -967,7 +997,7 @@ class TaggerWindow(QtWidgets.QMainWindow):
         md.scan_info = utils.xlate(self.leScanInfo.text())
         md.series_groups = utils.split(self.leSeriesGroup.text(), ",")
         md.alternate_series = self.leAltSeries.text()
-        md.web_link = utils.xlate(self.leWebLink.text())
+        md.web_links = [urllib3.util.parse_url(self.leWebLink.item(i).text()) for i in range(self.leWebLink.count())]
         md.characters = set(utils.split(self.teCharacters.toPlainText(), "\n"))
         md.teams = set(utils.split(self.teTeams.toPlainText(), "\n"))
         md.locations = set(utils.split(self.teLocations.toPlainText(), "\n"))
@@ -1004,7 +1034,7 @@ class TaggerWindow(QtWidgets.QMainWindow):
             # copy the form onto metadata object
             self.form_to_metadata()
             new_metadata = self.comic_archive.metadata_from_filename(
-                self.config[0].Filename_Parsing__complicated_parser,
+                self.config[0].Filename_Parsing__filename_parser,
                 self.config[0].Filename_Parsing__remove_c2c,
                 self.config[0].Filename_Parsing__remove_fcbd,
                 self.config[0].Filename_Parsing__remove_publisher,
@@ -1044,6 +1074,9 @@ class TaggerWindow(QtWidgets.QMainWindow):
             dialog.setNameFilters(filters)
             dialog.setFileMode(QtWidgets.QFileDialog.FileMode.ExistingFiles)
 
+        if os.environ.get("XDG_SESSION_DESKTOP", "") == "KDE":
+            dialog.setOption(QtWidgets.QFileDialog.Option.DontUseNativeDialog)
+
         if self.config[0].internal__last_opened_folder is not None:
             dialog.setDirectory(self.config[0].internal__last_opened_folder)
         return dialog
@@ -1144,40 +1177,44 @@ class TaggerWindow(QtWidgets.QMainWindow):
 
     def commit_metadata(self) -> None:
         if self.metadata is not None and self.comic_archive is not None:
-            reply = QtWidgets.QMessageBox.question(
-                self,
-                "Save Tags",
-                f"Are you sure you wish to save {', '.join([metadata_styles[style].name() for style in self.save_data_styles])} tags to this archive?",
-                QtWidgets.QMessageBox.StandardButton.Yes,
-                QtWidgets.QMessageBox.StandardButton.No,
-            )
+            if self.config[0].General__prompt_on_save:
+                reply = QtWidgets.QMessageBox.question(
+                    self,
+                    "Save Tags",
+                    f"Are you sure you wish to save {', '.join([metadata_styles[style].name() for style in self.save_data_styles])} tags to this archive?",
+                    QtWidgets.QMessageBox.StandardButton.Yes,
+                    QtWidgets.QMessageBox.StandardButton.No,
+                )
+            else:
+                reply = QtWidgets.QMessageBox.StandardButton.Yes
 
-            if reply == QtWidgets.QMessageBox.StandardButton.Yes:
-                QtWidgets.QApplication.setOverrideCursor(QtGui.QCursor(QtCore.Qt.CursorShape.WaitCursor))
-                self.form_to_metadata()
+            if reply != QtWidgets.QMessageBox.StandardButton.Yes:
+                return
+            QtWidgets.QApplication.setOverrideCursor(QtGui.QCursor(QtCore.Qt.CursorShape.WaitCursor))
+            self.form_to_metadata()
 
-                failed_style: str = ""
-                # Save each style
-                for style in self.save_data_styles:
-                    success = self.comic_archive.write_metadata(self.metadata, style)
-                    if not success:
-                        failed_style = metadata_styles[style].name()
-                        break
+            failed_style: str = ""
+            # Save each style
+            for style in self.save_data_styles:
+                success = self.comic_archive.write_metadata(self.metadata, style)
+                if not success:
+                    failed_style = metadata_styles[style].name()
+                    break
 
-                self.comic_archive.load_cache(list(metadata_styles))
-                QtWidgets.QApplication.restoreOverrideCursor()
+            self.comic_archive.load_cache(list(metadata_styles))
+            QtWidgets.QApplication.restoreOverrideCursor()
 
-                if failed_style:
-                    QtWidgets.QMessageBox.warning(
-                        self,
-                        "Save failed",
-                        f"The tag save operation seemed to fail for: {failed_style}",
-                    )
-                else:
-                    self.clear_dirty_flag()
-                    self.update_info_box()
-                    self.update_menus()
-                self.fileSelectionList.update_current_row()
+            if failed_style:
+                QtWidgets.QMessageBox.warning(
+                    self,
+                    "Save failed",
+                    f"The tag save operation seemed to fail for: {failed_style}",
+                )
+            else:
+                self.clear_dirty_flag()
+                self.update_info_box()
+                self.update_menus()
+            self.fileSelectionList.update_current_row()
 
             self.metadata = self.comic_archive.read_metadata(self.load_data_style)
             self.update_ui_for_archive()
@@ -1336,14 +1373,17 @@ class TaggerWindow(QtWidgets.QMainWindow):
         self.set_dirty_flag()
 
     def open_web_link(self) -> None:
-        if self.leWebLink is not None:
-            web_link = self.leWebLink.text().strip()
-            try:
-                result = urlparse(web_link)
-                all([result.scheme in ["http", "https"], result.netloc])
-                webbrowser.open_new_tab(web_link)
-            except ValueError:
-                QtWidgets.QMessageBox.warning(self, self.tr("Web Link"), self.tr("Web Link is invalid."))
+        row = self.leWebLink.currentRow()
+        if row < 0:
+            if self.leWebLink.count() < 1:
+                return
+            row = 0
+        web_link = self.leWebLink.item(row).text()
+        try:
+            urllib3.util.parse_url(web_link)
+            webbrowser.open_new_tab(web_link)
+        except LocationParseError:
+            QtWidgets.QMessageBox.warning(self, "Web Link", "Web Link is invalid.")
 
     def show_settings(self) -> None:
         settingswin = SettingsWindow(self, self.config, self.talkers)
@@ -1725,7 +1765,7 @@ class TaggerWindow(QtWidgets.QMainWindow):
             logger.error("Failed to load metadata for %s: %s", ca.path, e)
         if md.is_empty:
             md = ca.metadata_from_filename(
-                self.config[0].Filename_Parsing__complicated_parser,
+                self.config[0].Filename_Parsing__filename_parser,
                 self.config[0].Filename_Parsing__remove_c2c,
                 self.config[0].Filename_Parsing__remove_fcbd,
                 self.config[0].Filename_Parsing__remove_publisher,
@@ -1752,17 +1792,13 @@ class TaggerWindow(QtWidgets.QMainWindow):
                 md.issue = "1"
             else:
                 md.issue = utils.xlate(md.volume)
-        ii.set_additional_metadata(md)
-        ii.only_use_additional_meta_data = True
+
         ii.set_output_function(self.auto_tag_log)
-        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_series_match_threshold(dlg.name_length_match_tolerance)
 
-        matches: list[IssueResult] = ii.search()
-
-        result = ii.search_result
+        result, matches = ii.identify(ca, md)
 
         found_match = False
         choices = False

comictaggerlib/ui/qtutils.py

@@ -6,6 +6,7 @@ import io
 import logging
 import traceback
 import webbrowser
+from collections.abc import Sequence
 
 from PyQt5.QtCore import QUrl
 from PyQt5.QtWidgets import QWidget
@@ -155,7 +156,7 @@ if qt_available:
     active_palette = None
 
     def enable_widget(widget: QtWidgets.QWidget | list[QtWidgets.QWidget], enable: bool) -> None:
-        if isinstance(widget, list):
+        if isinstance(widget, Sequence):
             for w in widget:
                 _enable_widget(w, enable)
         else:
@@ -214,6 +215,8 @@ if qt_available:
                 widget.setReadOnly(True)
                 widget.setPalette(inactive_palette[0])
             elif isinstance(widget, QtWidgets.QListWidget):
+                inactive_palette = palettes()
+                widget.setPalette(inactive_palette[0])
                 widget.setMovement(QtWidgets.QListWidget.Static)
 
     def replaceWidget(

comictaggerlib/ui/settingswindow.ui

@@ -41,64 +41,6 @@
             <string/>
            </property>
            <layout class="QGridLayout" name="gridLayout_4">
-            <item row="2" column="0">
-             <widget class="QPushButton" name="btnResetSettings">
-              <property name="sizePolicy">
-               <sizepolicy hsizetype="Maximum" vsizetype="Fixed">
-                <horstretch>0</horstretch>
-                <verstretch>0</verstretch>
-               </sizepolicy>
-              </property>
-              <property name="text">
-               <string>Default Settings</string>
-              </property>
-             </widget>
-            </item>
-            <item row="3" column="0">
-             <widget class="QPushButton" name="btnClearCache">
-              <property name="sizePolicy">
-               <sizepolicy hsizetype="Maximum" vsizetype="Fixed">
-                <horstretch>0</horstretch>
-                <verstretch>0</verstretch>
-               </sizepolicy>
-              </property>
-              <property name="text">
-               <string>Clear Cache</string>
-              </property>
-             </widget>
-            </item>
-            <item row="3" column="1">
-             <widget class="QLabel" name="label_2">
-              <property name="sizePolicy">
-               <sizepolicy hsizetype="Expanding" vsizetype="Expanding">
-                <horstretch>0</horstretch>
-                <verstretch>0</verstretch>
-               </sizepolicy>
-              </property>
-              <property name="text">
-               <string>If you need to free up the disk space, or the responses seems out of date, clear the online cache.</string>
-              </property>
-              <property name="wordWrap">
-               <bool>true</bool>
-              </property>
-             </widget>
-            </item>
-            <item row="2" column="1">
-             <widget class="QLabel" name="lblDefaultSettings">
-              <property name="sizePolicy">
-               <sizepolicy hsizetype="Expanding" vsizetype="Expanding">
-                <horstretch>0</horstretch>
-                <verstretch>0</verstretch>
-               </sizepolicy>
-              </property>
-              <property name="text">
-               <string>Revert to default settings</string>
-              </property>
-              <property name="wordWrap">
-               <bool>true</bool>
-              </property>
-             </widget>
-            </item>
             <item row="0" column="0" colspan="2">
              <widget class="QCheckBox" name="cbxCheckForNewVersion">
               <property name="text">
@@ -116,6 +58,77 @@
               </property>
              </widget>
             </item>
+            <item row="3" column="0">
+             <widget class="QPushButton" name="btnResetSettings">
+              <property name="sizePolicy">
+               <sizepolicy hsizetype="Maximum" vsizetype="Fixed">
+                <horstretch>0</horstretch>
+                <verstretch>0</verstretch>
+               </sizepolicy>
+              </property>
+              <property name="text">
+               <string>Default Settings</string>
+              </property>
+             </widget>
+            </item>
+            <item row="4" column="0">
+             <widget class="QPushButton" name="btnClearCache">
+              <property name="sizePolicy">
+               <sizepolicy hsizetype="Maximum" vsizetype="Fixed">
+                <horstretch>0</horstretch>
+                <verstretch>0</verstretch>
+               </sizepolicy>
+              </property>
+              <property name="text">
+               <string>Clear Cache</string>
+              </property>
+             </widget>
+            </item>
+            <item row="3" column="1">
+             <widget class="QLabel" name="lblDefaultSettings">
+              <property name="sizePolicy">
+               <sizepolicy hsizetype="Expanding" vsizetype="Expanding">
+                <horstretch>0</horstretch>
+                <verstretch>0</verstretch>
+               </sizepolicy>
+              </property>
+              <property name="text">
+               <string>Revert to default settings</string>
+              </property>
+              <property name="wordWrap">
+               <bool>true</bool>
+              </property>
+              <property name="buddy">
+               <cstring>btnResetSettings</cstring>
+              </property>
+             </widget>
+            </item>
+            <item row="4" column="1">
+             <widget class="QLabel" name="label_2">
+              <property name="sizePolicy">
+               <sizepolicy hsizetype="Expanding" vsizetype="Expanding">
+                <horstretch>0</horstretch>
+                <verstretch>0</verstretch>
+               </sizepolicy>
+              </property>
+              <property name="text">
+               <string>If you need to free up the disk space, or the responses seems out of date, clear the online cache.</string>
+              </property>
+              <property name="wordWrap">
+               <bool>true</bool>
+              </property>
+              <property name="buddy">
+               <cstring>btnClearCache</cstring>
+              </property>
+             </widget>
+            </item>
+            <item row="2" column="0">
+             <widget class="QCheckBox" name="cbxPromptOnSave">
+              <property name="text">
+               <string>Prompts the user to confirm saving tags</string>
+              </property>
+             </widget>
+            </item>
            </layout>
           </widget>
          </item>
@@ -166,6 +179,9 @@
              <property name="text">
               <string>Default Name Match Ratio Threshold: Search:</string>
              </property>
+             <property name="buddy">
+              <cstring>sbNameMatchSearchThresh</cstring>
+             </property>
             </widget>
            </item>
            <item row="1" column="0">
@@ -176,6 +192,9 @@
              <property name="alignment">
               <set>Qt::AlignRight|Qt::AlignTrailing|Qt::AlignVCenter</set>
              </property>
+             <property name="buddy">
+              <cstring>sbNameMatchIdentifyThresh</cstring>
+             </property>
             </widget>
            </item>
            <item row="2" column="0">
@@ -183,6 +202,9 @@
              <property name="text">
               <string>Always use Publisher Filter on &quot;manual&quot; searches:</string>
              </property>
+             <property name="buddy">
+              <cstring>cbxUseFilter</cstring>
+             </property>
             </widget>
            </item>
            <item row="2" column="1">
@@ -200,6 +222,9 @@
              <property name="text">
               <string>Publisher Filter:</string>
              </property>
+             <property name="buddy">
+              <cstring>tePublisherFilter</cstring>
+             </property>
             </widget>
            </item>
            <item row="3" column="1">
@@ -301,9 +326,19 @@
           <widget class="QGroupBox" name="groupBox_2">
            <layout class="QVBoxLayout" name="verticalLayout_7">
             <item>
-             <widget class="QCheckBox" name="cbxComplicatedParser">
+             <widget class="QLabel" name="lblFilenamearser">
               <property name="text">
-               <string>Use &quot;Complicated&quot; Parser</string>
+               <string>Select the filename parser</string>
+              </property>
+              <property name="buddy">
+               <cstring>cbFilenameParser</cstring>
+              </property>
+             </widget>
+            </item>
+            <item>
+             <widget class="QComboBox" name="cbFilenameParser">
+              <property name="insertPolicy">
+               <enum>QComboBox::NoInsert</enum>
               </property>
              </widget>
             </item>
@@ -539,6 +574,9 @@
              <property name="text">
               <string>Template:</string>
              </property>
+             <property name="buddy">
+              <cstring>leRenameTemplate</cstring>
+             </property>
             </widget>
            </item>
            <item row="1" column="1">
@@ -569,6 +607,9 @@
              <property name="text">
               <string>Issue # Zero Padding</string>
              </property>
+             <property name="buddy">
+              <cstring>leIssueNumPadding</cstring>
+             </property>
             </widget>
            </item>
            <item row="3" column="1">
@@ -622,6 +663,9 @@
              <property name="text">
               <string>Destination Directory:</string>
              </property>
+             <property name="buddy">
+              <cstring>leDirectory</cstring>
+             </property>
             </widget>
            </item>
            <item row="9" column="1">
@@ -727,6 +771,9 @@
            <property name="text">
             <string>Value Text Replacements</string>
            </property>
+           <property name="buddy">
+            <cstring>twValueReplacements</cstring>
+           </property>
           </widget>
          </item>
          <item row="1" column="0" colspan="2">
@@ -734,6 +781,9 @@
            <property name="text">
             <string>Literal Text Replacements</string>
            </property>
+           <property name="buddy">
+            <cstring>twLiteralReplacements</cstring>
+           </property>
           </widget>
          </item>
         </layout>
@@ -769,6 +819,9 @@
               <property name="text">
                <string>RAR program</string>
               </property>
+              <property name="buddy">
+               <cstring>leRarExePath</cstring>
+              </property>
              </widget>
             </item>
             <item row="1" column="1">
@@ -780,7 +833,7 @@
                </sizepolicy>
               </property>
               <property name="readOnly">
-               <bool>true</bool>
+               <bool>false</bool>
               </property>
              </widget>
             </item>

comictaggerlib/ui/taggerwindow.ui

@@ -927,6 +927,9 @@
                   <property name="acceptDrops">
                    <bool>false</bool>
                   </property>
+                  <property name="acceptRichText">
+                   <bool>false</bool>
+                  </property>
                  </widget>
                 </item>
                 <item row="1" column="0">
@@ -941,6 +944,9 @@
                   <property name="acceptDrops">
                    <bool>false</bool>
                   </property>
+                  <property name="acceptRichText">
+                   <bool>false</bool>
+                  </property>
                  </widget>
                 </item>
                 <item row="2" column="0">
@@ -952,10 +958,32 @@
                 </item>
                 <item row="2" column="1">
                  <layout class="QGridLayout" name="gridLayout_7">
-                  <item row="0" column="0">
-                   <widget class="QLineEdit" name="leWebLink">
-                    <property name="acceptDrops">
-                     <bool>false</bool>
+                  <item row="0" column="0" rowspan="3">
+                   <widget class="QListWidget" name="leWebLink">
+                    <property name="contextMenuPolicy">
+                     <enum>Qt::ActionsContextMenu</enum>
+                    </property>
+                    <property name="dragEnabled">
+                     <bool>true</bool>
+                    </property>
+                    <property name="dragDropMode">
+                     <enum>QAbstractItemView::DropOnly</enum>
+                    </property>
+                    <property name="defaultDropAction">
+                     <enum>Qt::MoveAction</enum>
+                    </property>
+                    <property name="alternatingRowColors">
+                     <bool>true</bool>
+                    </property>
+                    <property name="selectionMode">
+                     <enum>QAbstractItemView::SingleSelection</enum>
+                    </property>
+                   </widget>
+                  </item>
+                  <item row="2" column="1">
+                   <widget class="QPushButton" name="btnRemoveWebLink">
+                    <property name="text">
+                     <string>Delete Item</string>
                     </property>
                    </widget>
                   </item>
@@ -975,6 +1003,13 @@
                     </property>
                    </widget>
                   </item>
+                  <item row="1" column="1">
+                   <widget class="QPushButton" name="btnAddWebLink">
+                    <property name="text">
+                     <string>Add Item</string>
+                    </property>
+                   </widget>
+                  </item>
                  </layout>
                 </item>
                 <item row="4" column="0">
@@ -1053,6 +1088,9 @@
                   <property name="acceptDrops">
                    <bool>false</bool>
                   </property>
+                  <property name="acceptRichText">
+                   <bool>false</bool>
+                  </property>
                  </widget>
                 </item>
                 <item row="2" column="0">
@@ -1079,6 +1117,9 @@
                   <property name="acceptDrops">
                    <bool>false</bool>
                   </property>
+                  <property name="acceptRichText">
+                   <bool>false</bool>
+                  </property>
                  </widget>
                 </item>
                 <item row="3" column="0">
@@ -1105,6 +1146,9 @@
                   <property name="acceptDrops">
                    <bool>false</bool>
                   </property>
+                  <property name="acceptRichText">
+                   <bool>false</bool>
+                  </property>
                  </widget>
                 </item>
                 <item row="4" column="0">
@@ -1137,6 +1181,9 @@
                   <property name="acceptDrops">
                    <bool>false</bool>
                   </property>
+                  <property name="acceptRichText">
+                   <bool>false</bool>
+                  </property>
                  </widget>
                 </item>
                </layout>
@@ -1169,7 +1216,7 @@
      <x>0</x>
      <y>0</y>
      <width>1096</width>
-     <height>28</height>
+     <height>30</height>
     </rect>
    </property>
    <widget class="QMenu" name="menuComicTagger">
@@ -1459,6 +1506,16 @@
     <string>Open Folder as Comic</string>
    </property>
   </action>
+  <action name="actionAddWebLink">
+   <property name="text">
+    <string>Add Item</string>
+   </property>
+  </action>
+  <action name="actionRemoveWebLink">
+   <property name="text">
+    <string>Remove Web Link</string>
+   </property>
+  </action>
  </widget>
  <layoutdefault spacing="6" margin="11"/>
  <customwidgets>
@@ -1469,5 +1526,38 @@
   </customwidget>
  </customwidgets>
  <resources/>
- <connections/>
+ <connections>
+  <connection>
+   <sender>btnAddWebLink</sender>
+   <signal>clicked()</signal>
+   <receiver>actionAddWebLink</receiver>
+   <slot>trigger()</slot>
+   <hints>
+    <hint type="sourcelabel">
+     <x>900</x>
+     <y>536</y>
+    </hint>
+    <hint type="destinationlabel">
+     <x>-1</x>
+     <y>-1</y>
+    </hint>
+   </hints>
+  </connection>
+  <connection>
+   <sender>btnRemoveWebLink</sender>
+   <signal>clicked()</signal>
+   <receiver>actionRemoveWebLink</receiver>
+   <slot>trigger()</slot>
+   <hints>
+    <hint type="sourcelabel">
+     <x>900</x>
+     <y>576</y>
+    </hint>
+    <hint type="destinationlabel">
+     <x>-1</x>
+     <y>-1</y>
+    </hint>
+   </hints>
+  </connection>
+ </connections>
 </ui>

comictalker/talkers/comicvine.py

@@ -29,6 +29,8 @@ import requests
 import settngs
 from pyrate_limiter import Limiter, RequestRate
 from typing_extensions import Required, TypedDict
+from urllib3.exceptions import LocationParseError
+from urllib3.util import parse_url
 
 from comicapi import utils
 from comicapi.genericmetadata import ComicSeries, GenericMetadata, TagOrigin
@@ -643,10 +645,15 @@ class ComicVineTalker(ComicTalker):
             format=utils.xlate(series.format),
             volume_count=utils.xlate_int(series.count_of_volumes),
             title=utils.xlate(issue.get("name")),
-            web_link=utils.xlate(issue.get("site_detail_url")),
             series=utils.xlate(series.name),
             series_aliases=series.aliases,
         )
+        url = utils.xlate(issue.get("site_detail_url"))
+        if url:
+            try:
+                md.web_links = [parse_url(url)]
+            except LocationParseError:
+                ...
         if issue.get("image") is None:
             md._cover_image = ""
         else:

setup.cfg

@@ -37,6 +37,7 @@ install_requires =
     appdirs==1.4.4
     beautifulsoup4>=4.1
     chardet>=5.1.0,<6
+    comicfn2dict>=0.2.1
     importlib-metadata>=3.3.0
     isocodes>=2023.11.26
     natsort>=8.1.0
@@ -46,7 +47,7 @@ install_requires =
     pyrate-limiter>=2.6,<3
     rapidfuzz>=2.12.0
     requests==2.*
-    settngs==0.9.2
+    settngs==0.10.0
     text2digits
     typing-extensions>=4.3.0
     wordninja
@@ -86,7 +87,7 @@ QTW =
 all =
     PyQt5
     PyQtWebEngine
-    comicinfoxml
+    comicinfoxml>=0.2.0
     gcd-talker>=0.1.0
     metron-talker>=0.1.5
     pillow-avif-plugin>=1.4.1
@@ -96,7 +97,7 @@ all =
 avif =
     pillow-avif-plugin>=1.4.1
 cix =
-    comicinfoxml
+    comicinfoxml>=0.2.0
 gcd =
     gcd-talker>=0.1.0
 metron =

testing/comicdata.py

@@ -78,33 +78,17 @@ metadata = [
 
 metadata_keys = [
     (
-        comicapi.genericmetadata.GenericMetadata(),
+        comicapi.genericmetadata.md_test,
         {
             "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,
+            "alternate_count": 7,
+            "alternate_number": "2",
+            "imprint": "craphound.com",
+            "publisher": "IDW Publishing",
         },
     ),
 ]

testing/comicvine.py

@@ -185,7 +185,7 @@ comic_issue_result = comicapi.genericmetadata.GenericMetadata(
     issue=cv_issue_result["results"]["issue_number"],
     volume=None,
     title=cv_issue_result["results"]["name"],
-    web_link=cv_issue_result["results"]["site_detail_url"],
+    web_links=[comicapi.genericmetadata.parse_url(cv_issue_result["results"]["site_detail_url"])],
 )
 
 cv_md = comicapi.genericmetadata.GenericMetadata(
@@ -213,7 +213,7 @@ cv_md = comicapi.genericmetadata.GenericMetadata(
     alternate_count=None,
     imprint=None,
     notes=None,
-    web_link=cv_issue_result["results"]["site_detail_url"],
+    web_links=[comicapi.genericmetadata.parse_url(cv_issue_result["results"]["site_detail_url"])],
     format=None,
     manga=None,
     black_and_white=None,

testing/filenames.py

@@ -1152,6 +1152,13 @@ rnames = [
         "Anda's Game https:--comicvine.gamespot.com-cory-doctorows-futuristic-tales-of-the-here-and-no-4000-140529-.cbz",
         does_not_raise(),
     ),
+    (
+        "{title} {web_links!j}",  # Test that join forces str conversion
+        False,
+        "Linux",
+        "Anda's Game https:--comicvine.gamespot.com-cory-doctorows-futuristic-tales-of-the-here-and-no-4000-140529-.cbz",
+        does_not_raise(),
+    ),
     (
         "{series}:{title} #{issue} ({year})",  # on windows the ':' is replaced
         False,

tests/issueidentifier_test.py

@@ -5,6 +5,7 @@ import io
 import pytest
 from PIL import Image
 
+import comictaggerlib.imagehasher
 import comictaggerlib.issueidentifier
 import testing.comicdata
 import testing.comicvine
@@ -13,12 +14,16 @@ from comictaggerlib.resulttypes import IssueResult
 
 def test_crop(cbz_double_cover, config, tmp_path, comicvine_api):
     config, definitions = config
-    ii = comictaggerlib.issueidentifier.IssueIdentifier(cbz_double_cover, config, comicvine_api)
-    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)
+    ii = comictaggerlib.issueidentifier.IssueIdentifier(cbz_double_cover, config, comicvine_api)
+
+    im = Image.open(io.BytesIO(cbz_double_cover.archiver.read_file("double_cover.jpg")))
+
+    cropped = ii._crop_double_page(im)
+    original = cbz_double_cover.get_page(0)
+
+    original_hash = comictaggerlib.imagehasher.ImageHasher(data=original).average_hash()
+    cropped_hash = comictaggerlib.imagehasher.ImageHasher(image=cropped).average_hash()
 
     assert original_hash == cropped_hash
 
@@ -27,23 +32,24 @@ def test_crop(cbz_double_cover, config, tmp_path, comicvine_api):
 def test_get_search_keys(cbz, config, additional_md, expected, comicvine_api):
     config, definitions = config
     ii = comictaggerlib.issueidentifier.IssueIdentifier(cbz, config, comicvine_api)
-    ii.set_additional_metadata(additional_md)
 
-    assert expected == ii.get_search_keys()
+    assert expected == ii._get_search_keys(additional_md)
 
 
 def test_get_issue_cover_match_score(cbz, config, comicvine_api):
     config, definitions = config
     ii = comictaggerlib.issueidentifier.IssueIdentifier(cbz, config, comicvine_api)
-    score = ii.get_issue_cover_match_score(
+    score = ii._get_issue_cover_match_score(
         "https://comicvine.gamespot.com/a/uploads/scale_large/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))],
+        [("Cover 1", ii.calculate_hash(cbz.get_page(0)))],
     )
     expected = {
-        "hash": 212201432349720,
+        "remote_hash": 212201432349720,
         "score": 0,
         "url": "https://comicvine.gamespot.com/a/uploads/scale_large/0/574/585444-109004_20080707014047_large.jpg",
+        "local_hash": 212201432349720,
+        "local_hash_name": "Cover 1",
     }
     assert expected == score
 
@@ -51,13 +57,13 @@ def test_get_issue_cover_match_score(cbz, config, comicvine_api):
 def test_search(cbz, config, comicvine_api):
     config, definitions = config
     ii = comictaggerlib.issueidentifier.IssueIdentifier(cbz, config, comicvine_api)
-    results = ii.search()
+    result, issues = ii.identify(cbz, cbz.read_metadata("cr"))
     cv_expected = IssueResult(
         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"],
         alt_image_urls=[],
-        cv_issue_count=testing.comicvine.cv_volume_result["results"]["count_of_issues"],
+        issue_count=testing.comicvine.cv_volume_result["results"]["count_of_issues"],
         issue_title=testing.comicvine.cv_issue_result["results"]["name"],
         issue_id=str(testing.comicvine.cv_issue_result["results"]["id"]),
         series_id=str(testing.comicvine.cv_volume_result["results"]["id"]),
@@ -68,7 +74,7 @@ def test_search(cbz, config, comicvine_api):
         description=testing.comicvine.cv_issue_result["results"]["description"],
         url_image_hash=212201432349720,
     )
-    for r, e in zip(results, [cv_expected]):
+    for r, e in zip(issues, [cv_expected]):
         assert r == e
 
 
@@ -80,14 +86,10 @@ def test_crop_border(cbz, config, comicvine_api):
     bg = Image.new("RGBA", (100, 100), (0, 0, 0, 255))
     fg = Image.new("RGBA", (50, 50), (255, 255, 255, 255))
     bg.paste(fg, (bg.width // 2 - (fg.width // 2), bg.height // 2 - (fg.height // 2)))
-    output = io.BytesIO()
-    bg.save(output, format="PNG")
-    image_data = output.getvalue()
-    output.close()
 
-    cropped = ii.crop_border(image_data, 49)
+    cropped = ii._crop_border(bg, 49)
 
-    im = Image.open(io.BytesIO(cropped))
-    assert im.width == fg.width
-    assert im.height == fg.height
-    assert list(im.getdata()) == list(fg.getdata())
+    assert cropped
+    assert cropped.width == fg.width
+    assert cropped.height == fg.height
+    assert list(cropped.getdata()) == list(fg.getdata())