Allow printing combined CLI tags

comicapi/archivers/archiver.py

@@ -24,6 +24,12 @@ class Archiver(Protocol):
     """
     enabled: bool = True
 
+    """
+    If self.path is a single file that can be hashed.
+    For example directories cannot be hashed.
+    """
+    hashable: bool = True
+
     def __init__(self) -> None:
         self.path = pathlib.Path()
 

comicapi/archivers/folder.py

@@ -12,6 +12,8 @@ logger = logging.getLogger(__name__)
 class FolderArchiver(Archiver):
     """Folder implementation"""
 
+    hashable = False
+
     def __init__(self) -> None:
         super().__init__()
         self.comment_file_name = "ComicTaggerFolderComment.txt"

comicapi/comicarchive.py

@@ -15,7 +15,9 @@
 # limitations under the License.
 from __future__ import annotations
 
+import hashlib
 import importlib.util
+import inspect
 import io
 import itertools
 import logging
@@ -27,7 +29,7 @@ from collections.abc import Iterable
 
 from comicapi import utils
 from comicapi.archivers import Archiver, UnknownArchiver, ZipArchiver
-from comicapi.genericmetadata import GenericMetadata
+from comicapi.genericmetadata import GenericMetadata, Hash
 from comicapi.tags import Tag
 from comictaggerlib.ctversion import version
 
@@ -124,11 +126,15 @@ class ComicArchive:
     pil_available = True
 
     def __init__(
-        self, path: pathlib.Path | str | Archiver, default_image_path: pathlib.Path | str | None = None
+        self,
+        path: pathlib.Path | str | Archiver,
+        default_image_path: pathlib.Path | str | None = None,
+        hash_archive: str = "",
     ) -> None:
         self.md: dict[str, GenericMetadata] = {}
         self.page_count: int | None = None
         self.page_list: list[str] = []
+        self.hash_archive = hash_archive
 
         self.reset_cache()
         self.default_image_path = default_image_path
@@ -230,7 +236,7 @@ class ComicArchive:
         if not tags[tag_id].enabled:
             return False
 
-        self.apply_archive_info_to_metadata(metadata, True, True)
+        self.apply_archive_info_to_metadata(metadata, True, True, hash_archive=self.hash_archive)
         return tags[tag_id].write_tags(metadata, self.archiver)
 
     def has_tags(self, tag_id: str) -> bool:
@@ -333,11 +339,34 @@ class ComicArchive:
         return self.page_count
 
     def apply_archive_info_to_metadata(
-        self, md: GenericMetadata, calc_page_sizes: bool = False, detect_double_page: bool = False
+        self,
+        md: GenericMetadata,
+        calc_page_sizes: bool = False,
+        detect_double_page: bool = False,
+        *,
+        hash_archive: str = "",
     ) -> None:
+        hash_archive = hash_archive
         md.page_count = self.get_number_of_pages()
         md.apply_default_page_list(self.get_page_name_list())
-        if not calc_page_sizes or not self.seems_to_be_a_comic_archive():
+        if not self.seems_to_be_a_comic_archive():
+            return
+
+        if hash_archive in hashlib.algorithms_available and not md.original_hash:
+            hasher = getattr(hashlib, hash_archive, hash_archive)
+            try:
+                with self.archiver.path.open("b+r") as archive:
+                    digest = utils.file_digest(archive, hasher)
+                if len(inspect.signature(digest.hexdigest).parameters) > 0:
+                    length = digest.name.rpartition("_")[2]
+                    if not length.isdigit():
+                        length = "128"
+                    md.original_hash = Hash(digest.name, digest.hexdigest(int(length) // 8))  # type: ignore[call-arg]
+                else:
+                    md.original_hash = Hash(digest.name, digest.hexdigest())
+            except Exception:
+                logger.exception("Failed to calculate original hash for '%s'", self.archiver.path)
+        if not calc_page_sizes:
             return
         for p in md.pages:
 

comicapi/genericmetadata.py

@@ -23,6 +23,7 @@ from __future__ import annotations
 
 import copy
 import dataclasses
+import hashlib
 import logging
 from collections.abc import Sequence
 from typing import TYPE_CHECKING, Any, Union, overload
@@ -136,6 +137,24 @@ class MetadataOrigin(NamedTuple):
         return self.name
 
 
+class Hash(NamedTuple):
+    name: str
+    hash: str
+
+    def __str__(self) -> str:
+        return self.name + ":" + self.hash
+
+    @classmethod
+    def parse(cls, string: str) -> Hash:
+        name, _, parsed_hash = string.partition(":")
+        if name in hashlib.algorithms_available:
+            return Hash(name, parsed_hash)
+        return Hash("", "")
+
+    def __bool__(self) -> bool:
+        return all(self)
+
+
 @dataclasses.dataclass
 class GenericMetadata:
     writer_synonyms = ("writer", "plotter", "scripter", "script")
@@ -151,6 +170,7 @@ class GenericMetadata:
     data_origin: MetadataOrigin | None = None
     issue_id: str | None = None
     series_id: str | None = None
+    original_hash: Hash | None = None
 
     series: str | None = None
     series_aliases: set[str] = dataclasses.field(default_factory=set)
@@ -285,6 +305,9 @@ class GenericMetadata:
         self.issue_id = assign(self.issue_id, new_md.issue_id)
         self.series_id = assign(self.series_id, new_md.series_id)
 
+        # This should not usually be set by a talker or other online datasource
+        self.original_hash = assign(self.original_hash, new_md.original_hash)
+
         self.series = assign(self.series, new_md.series)
 
         self.series_aliases = assign_list(self.series_aliases, new_md.series_aliases)
@@ -450,6 +473,7 @@ class GenericMetadata:
 
         add_string("data_origin", self.data_origin)
         add_string("series", self.series)
+        add_string("original_hash", self.original_hash)
         add_string("series_aliases", ",".join(self.series_aliases))
         add_string("issue", self.issue)
         add_string("issue_count", self.issue_count)

comicapi/merge.py

@@ -1,11 +1,12 @@
 from __future__ import annotations
 
 import dataclasses
+from collections import defaultdict
 from collections.abc import Collection
 from enum import auto
 from typing import Any
 
-from comicapi.utils import DefaultDict, StrEnum, norm_fold
+from comicapi.utils import StrEnum, norm_fold
 
 
 @dataclasses.dataclass
@@ -54,19 +55,19 @@ def overlay(old: Any, new: Any) -> Any:
     return new
 
 
-attribute = DefaultDict(
+attribute = defaultdict(
+    lambda: overlay,
     {
         Mode.OVERLAY: overlay,
         Mode.ADD_MISSING: lambda old, new: overlay(new, old),
     },
-    default=lambda x: overlay,
 )
 
 
-lists = DefaultDict(
+lists = defaultdict(
+    lambda: overlay,
     {
         Mode.OVERLAY: merge_lists,
         Mode.ADD_MISSING: lambda old, new: merge_lists(new, old),
     },
-    default=lambda x: overlay,
 )

comicapi/tags/comicrack.py

@@ -21,7 +21,7 @@ from typing import Any
 
 from comicapi import utils
 from comicapi.archivers import Archiver
-from comicapi.genericmetadata import GenericMetadata, PageMetadata
+from comicapi.genericmetadata import GenericMetadata, Hash, PageMetadata
 from comicapi.tags import Tag
 
 logger = logging.getLogger(__name__)
@@ -37,6 +37,7 @@ class ComicRack(Tag):
 
         self.file = "ComicInfo.xml"
         self.supported_attributes = {
+            "original_hash",
             "series",
             "issue",
             "issue_count",
@@ -244,7 +245,11 @@ class ComicRack(Tag):
         assign("BlackAndWhite", "Yes" if md.black_and_white else None)
         assign("AgeRating", md.maturity_rating)
         assign("CommunityRating", md.critical_rating)
-        assign("ScanInformation", md.scan_info)
+
+        scan_info = md.scan_info or ""
+        if md.original_hash:
+            scan_info += f" {md.original_hash}"
+        assign("ScanInformation", scan_info)
 
         assign("PageCount", md.page_count)
 
@@ -326,7 +331,16 @@ class ComicRack(Tag):
         md.manga = utils.xlate(get("Manga"))
         md.maturity_rating = utils.xlate(get("AgeRating"))
         md.critical_rating = utils.xlate_float(get("CommunityRating"))
-        md.scan_info = utils.xlate(get("ScanInformation"))
+        scan_info_list = (utils.xlate(get("ScanInformation")) or "").split()
+        for word in scan_info_list.copy():
+            original_hash = Hash.parse(word)
+            if original_hash:
+                md.original_hash = original_hash
+                scan_info_list.remove(word)
+                break
+        if scan_info_list:
+            md.scan_info = " ".join(scan_info_list)
+        md.is_empty = False
 
         md.page_count = utils.xlate_int(get("PageCount"))
 

comicapi/tags/tag.py

@@ -14,6 +14,7 @@ class Tag:
             "data_origin",
             "issue_id",
             "series_id",
+            "original_hash",
             "series",
             "series_aliases",
             "issue",

comicapi/utils.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 from __future__ import annotations
 
+import hashlib
 import json
 import logging
 import os
@@ -22,10 +23,11 @@ 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, Callable, TypeVar, cast
+from typing import Any, TypeVar, cast
 
 from comicfn2dict import comicfn2dict
 
@@ -46,6 +48,45 @@ except ImportError:
 
 if sys.version_info < (3, 11):
 
+    def file_digest(fileobj, digest, /, *, _bufsize=2**18):
+        """Hash the contents of a file-like object. Returns a digest object.
+
+        *fileobj* must be a file-like object opened for reading in binary mode.
+        It accepts file objects from open(), io.BytesIO(), and SocketIO objects.
+        The function may bypass Python's I/O and use the file descriptor *fileno*
+        directly.
+
+        *digest* must either be a hash algorithm name as a *str*, a hash
+        constructor, or a callable that returns a hash object.
+        """
+        # On Linux we could use AF_ALG sockets and sendfile() to archive zero-copy
+        # hashing with hardware acceleration.
+        if isinstance(digest, str):
+            digestobj = hashlib.new(digest)
+        else:
+            digestobj = digest()
+
+        if hasattr(fileobj, "getbuffer"):
+            # io.BytesIO object, use zero-copy buffer
+            digestobj.update(fileobj.getbuffer())
+            return digestobj
+
+        # Only binary files implement readinto().
+        if not (hasattr(fileobj, "readinto") and hasattr(fileobj, "readable") and fileobj.readable()):
+            raise ValueError(f"'{fileobj!r}' is not a file-like object in binary reading mode.")
+
+        # binary file, socket.SocketIO object
+        # Note: socket I/O uses different syscalls than file I/O.
+        buf = bytearray(_bufsize)  # Reusable buffer to reduce allocations.
+        view = memoryview(buf)
+        while True:
+            size = fileobj.readinto(buf)
+            if size == 0:
+                break  # EOF
+            digestobj.update(view[:size])
+
+        return digestobj
+
     class StrEnum(str, Enum):
         """
         Enum where members are also (and must be) strings
@@ -91,9 +132,10 @@ if sys.version_info < (3, 11):
             return self.value
 
 else:
-    from enum import StrEnum as s
+    from enum import StrEnum as _StrEnum
+    from hashlib import file_digest
 
-    class StrEnum(s):
+    class StrEnum(_StrEnum):
         @classmethod
         def _missing_(cls, value: Any) -> str | None:
             if not isinstance(value, str):
@@ -106,17 +148,6 @@ else:
 logger = logging.getLogger(__name__)
 
 
-class DefaultDict(dict):
-    def __init__(self, *args, default: Callable[[Any], Any] | None = None) -> None:
-        super().__init__(*args)
-        self.default = default
-
-    def __missing__(self, key: Any) -> Any:
-        if self.default is None:
-            return key
-        return self.default(key)
-
-
 class Parser(StrEnum):
     ORIGINAL = auto()
     COMPLICATED = auto()
@@ -370,9 +401,7 @@ def xlate_float(data: Any) -> float | None:
     if isinstance(data, (int, float)):
         i = data
     else:
-        i = str(data).translate(
-            DefaultDict(zip((ord(c) for c in "1234567890."), "1234567890."), default=lambda x: None)
-        )
+        i = str(data).translate(defaultdict(lambda: None, zip((ord(c) for c in "1234567890."), "1234567890.")))
     if i == "":
         return None
     try:
@@ -505,9 +534,9 @@ def parse_version(s: str) -> tuple[int, int, int]:
     return (parts[0], parts[1], parts[2])
 
 
-_languages: dict[str | None, str | None] = DefaultDict(default=lambda x: None)
+_languages: dict[str | None, str | None] = defaultdict(lambda: None)
 
-_countries: dict[str | None, str | None] = DefaultDict(default=lambda x: None)
+_countries: dict[str | None, str | None] = defaultdict(lambda: None)
 
 
 def countries() -> dict[str | None, str | None]:
@@ -529,8 +558,6 @@ def languages() -> dict[str | None, str | None]:
 
 
 def get_language_from_iso(iso: str | None) -> str | None:
-    if not _languages:
-        return languages()[iso]
     return _languages[iso]
 
 
@@ -543,12 +570,10 @@ def get_language_iso(string: str | None) -> str | None:
     lang = string.casefold()
 
     found = None
-
     for lng in isocodes.extendend_languages.items:
         for x in ("alpha_2", "alpha_3", "bibliographic", "common_name", "name"):
             if x in lng and lng[x].casefold() == lang:
                 found = lng
-                # break
         if found:
             break
 
@@ -558,8 +583,6 @@ def get_language_iso(string: str | None) -> str | None:
 
 
 def get_country_from_iso(iso: str | None) -> str | None:
-    if not _countries:
-        return countries()[iso]
     return _countries[iso]
 
 
@@ -618,3 +641,40 @@ def load_publishers() -> None:
         update_publishers(json.loads((comicapi.data.data_path / "publishers.json").read_text("utf-8")))
     except Exception:
         logger.exception("Failed to load publishers.json; The are no publishers or imprints loaded")
+
+
+__all__ = (
+    "load_publishers",
+    "file_digest",
+    "Parser",
+    "ImprintDict",
+    "os_sorted",
+    "parse_filename",
+    "norm_fold",
+    "combine_notes",
+    "parse_date_str",
+    "shorten_path",
+    "path_to_short_str",
+    "get_page_name_list",
+    "get_recursive_filelist",
+    "add_to_path",
+    "remove_from_path",
+    "xlate_int",
+    "xlate_float",
+    "xlate",
+    "split",
+    "split_urls",
+    "remove_articles",
+    "sanitize_title",
+    "titles_match",
+    "unique_file",
+    "parse_version",
+    "countries",
+    "languages",
+    "get_language_from_iso",
+    "get_language_iso",
+    "get_country_from_iso",
+    "get_publisher",
+    "update_publishers",
+    "load_publishers",
+)

comictaggerlib/autotagmatchwindow.py

@@ -182,7 +182,9 @@ class AutoTagMatchWindow(QtWidgets.QDialog):
             self.teDescription.setText(match.description)
 
     def set_cover_image(self) -> None:
-        ca = ComicArchive(self.current_match_set.original_path)
+        ca = ComicArchive(
+            self.current_match_set.original_path, hash_archive=self.config.Runtime_Options__preferred_hash
+        )
         self.archiveCoverWidget.set_archive(ca)
 
     def current_match(self) -> IssueResult:
@@ -225,7 +227,9 @@ class AutoTagMatchWindow(QtWidgets.QDialog):
 
     def save_match(self) -> None:
         match = self.current_match()
-        ca = ComicArchive(self.current_match_set.original_path)
+        ca = ComicArchive(
+            self.current_match_set.original_path, hash_archive=self.config.Runtime_Options__preferred_hash
+        )
         md, error = self.parent().read_selected_tags(self._tags, ca)
         if error is not None:
             logger.error("Failed to load tags for %s: %s", ca.path, error)

comictaggerlib/cli.py

@@ -184,7 +184,7 @@ class CLI:
             if i != "s":
                 # save the data!
                 # we know at this point, that the file is all good to go
-                ca = ComicArchive(match_set.original_path)
+                ca = ComicArchive(match_set.original_path, hash_archive=self.config.Runtime_Options__preferred_hash)
                 md, match_set.tags_read = self.create_local_metadata(ca, self.config.Runtime_Options__tags_read)
                 ct_md = self.fetch_metadata(match_set.online_results[int(i) - 1].issue_id)
 
@@ -330,6 +330,17 @@ class CLI:
                             self.output(md)
                     except Exception as e:
                         logger.error("Failed to read tags from %s: %s", ca.path, e)
+        if not self.config.Auto_Tag__metadata.is_empty and not self.config.Runtime_Options__raw:
+            try:
+                md, tags_read = self.create_local_metadata(
+                    ca, self.config.Runtime_Options__tags_read or list(tags.keys())
+                )
+                tags_read_names = ", ".join(["CLI"] + [tags[t].name() for t in tags_read])
+                self.output(f"--------- Combined {tags_read_names} tags ---------")
+                self.output(md)
+            except Exception as e:
+                logger.error("Failed to read tags from %s: %s", ca.path, e)
+
         return Result(Action.print, Status.success, ca.path, md=md)
 
     def delete_tags(self, ca: ComicArchive, tag_id: str) -> Status:
@@ -790,7 +801,9 @@ class CLI:
             logger.error("Cannot find %s", filename)
             return Result(command, Status.read_failure, pathlib.Path(filename)), match_results
 
-        ca = ComicArchive(filename, str(graphics_path / "nocover.png"))
+        ca = ComicArchive(
+            filename, str(graphics_path / "nocover.png"), hash_archive=self.config.Runtime_Options__preferred_hash
+        )
 
         if not ca.seems_to_be_a_comic_archive():
             logger.error("Sorry, but %s is not a comic archive!", filename)

comictaggerlib/crediteditorwindow.py

@@ -20,7 +20,7 @@ import logging
 import operator
 
 import natsort
-from PyQt5 import QtCore, QtWidgets, uic
+from PyQt5 import QtWidgets, uic
 
 from comicapi import utils
 from comicapi.genericmetadata import Credit
@@ -75,11 +75,7 @@ class CreditEditorWindow(QtWidgets.QDialog):
                 self.cbRole.setCurrentIndex(i)
 
         if credit.language != "":
-            i = (
-                self.cbLanguage.findData(credit.language, QtCore.Qt.ItemDataRole.UserRole)
-                if self.cbLanguage.findData(credit.language, QtCore.Qt.ItemDataRole.UserRole) > -1
-                else self.cbLanguage.findText(credit.language)
-            )
+            i = self.cbLanguage.findText(credit.language)
             if i == -1:
                 self.cbLanguage.setEditText(credit.language)
             else:
@@ -88,8 +84,9 @@ class CreditEditorWindow(QtWidgets.QDialog):
         self.cbPrimary.setChecked(credit.primary)
 
     def get_credit(self) -> Credit:
-        lang = self.cbLanguage.currentData() or self.cbLanguage.currentText()
-        return Credit(self.leName.text(), self.cbRole.currentText(), self.cbPrimary.isChecked(), lang)
+        return Credit(
+            self.leName.text(), self.cbRole.currentText(), self.cbPrimary.isChecked(), self.cbLanguage.currentText()
+        )
 
     def accept(self) -> None:
         if self.leName.text() == "":

comictaggerlib/ctsettings/commandline.py

@@ -17,6 +17,7 @@
 from __future__ import annotations
 
 import argparse
+import hashlib
 import logging
 import os
 import platform
@@ -83,6 +84,20 @@ def register_runtime(parser: settngs.Manager) -> None:
         help='Enable the expiremental "quick tagger"',
         file=False,
     )
+    parser.add_setting(
+        "--enable-embedding-hashes",
+        action=argparse.BooleanOptionalAction,
+        default=False,
+        help="Enable embedding hashes in metadata (currently only CR/CIX has support)",
+        file=False,
+    )
+    parser.add_setting(
+        "--preferred-hash",
+        default="shake_256",
+        choices=hashlib.algorithms_available,
+        help="The type of embedded hash to save when --enable-embedding-hashes is set\n\n",
+        file=False,
+    )
     parser.add_setting("-q", "--quiet", action="store_true", help="Don't say much (for print mode).", file=False)
     parser.add_setting(
         "-j",
@@ -307,6 +322,9 @@ def validate_commandline_settings(config: settngs.Config[ct_ns], parser: settngs
     if config[0].Runtime_Options__recursive:
         config[0].Runtime_Options__files = utils.get_recursive_filelist(config[0].Runtime_Options__files)
 
+    if not config[0].Runtime_Options__enable_embedding_hashes:
+        config[0].Runtime_Options__preferred_hash = ""
+
     # take a crack at finding rar exe if it's not in the path
     if not utils.which("rar"):
         if platform.system() == "Windows":

comictaggerlib/ctsettings/file.py

@@ -27,6 +27,7 @@ def general(parser: settngs.Manager) -> None:
 def internal(parser: settngs.Manager) -> None:
     # automatic settings
     parser.add_setting("install_id", default=uuid.uuid4().hex, cmdline=False)
+    parser.add_setting("embedded_hash_type", default="shake_256", cmdline=False)
     parser.add_setting("write_tags", default=["cr"], cmdline=False)
     parser.add_setting("read_tags", default=["cr"], cmdline=False)
     parser.add_setting("last_opened_folder", default="", cmdline=False)

comictaggerlib/ctsettings/settngs_namespace.py

@@ -21,6 +21,8 @@ class SettngsNS(settngs.TypedNS):
     Runtime_Options__config: comictaggerlib.ctsettings.types.ComicTaggerPaths
     Runtime_Options__verbose: int
     Runtime_Options__enable_quick_tag: bool
+    Runtime_Options__enable_embedding_hashes: bool
+    Runtime_Options__preferred_hash: str
     Runtime_Options__quiet: bool
     Runtime_Options__json: bool
     Runtime_Options__raw: bool
@@ -47,6 +49,7 @@ class SettngsNS(settngs.TypedNS):
     Quick_Tag__exact_only: bool
 
     internal__install_id: str
+    internal__embedded_hash_type: str
     internal__write_tags: list[str]
     internal__read_tags: list[str]
     internal__last_opened_folder: str
@@ -143,6 +146,8 @@ class Runtime_Options(typing.TypedDict):
     config: comictaggerlib.ctsettings.types.ComicTaggerPaths
     verbose: int
     enable_quick_tag: bool
+    enable_embedding_hashes: bool
+    preferred_hash: str
     quiet: bool
     json: bool
     raw: bool
@@ -173,6 +178,7 @@ class Quick_Tag(typing.TypedDict):
 
 class internal(typing.TypedDict):
     install_id: str
+    embedded_hash_type: str
     write_tags: list[str]
     read_tags: list[str]
     last_opened_folder: str

comictaggerlib/fileselectionlist.py

@@ -274,7 +274,9 @@ class FileSelectionList(QtWidgets.QWidget):
         if self.is_list_dupe(path):
             return self.get_current_list_row(path)
 
-        ca = ComicArchive(path, str(graphics_path / "nocover.png"))
+        ca = ComicArchive(
+            path, str(graphics_path / "nocover.png"), hash_archive=self.config.Runtime_Options__preferred_hash
+        )
 
         if ca.seems_to_be_a_comic_archive():
             row: int = self.twList.rowCount()

comictaggerlib/pagelisteditor.py

@@ -170,7 +170,7 @@ class PageListEditor(QtWidgets.QWidget):
             return
         md = GenericMetadata(pages=self.get_page_list())
         double_pages = [bool(x.double_page) for x in md.pages]
-        self.comic_archive.apply_archive_info_to_metadata(md, True, True)
+        self.comic_archive.apply_archive_info_to_metadata(md, True, True, hash_archive="")
         self.set_data(self.comic_archive, pages_list=md.pages)
         if double_pages != [bool(x.double_page) for x in md.pages]:
             self.modified.emit()

comictaggerlib/taggerwindow.py

@@ -17,6 +17,7 @@
 from __future__ import annotations
 
 import functools
+import hashlib
 import logging
 import operator
 import os
@@ -38,7 +39,7 @@ import comictaggerlib.ui
 from comicapi import utils
 from comicapi.comicarchive import ComicArchive, tags
 from comicapi.filenameparser import FileNameParser
-from comicapi.genericmetadata import Credit, GenericMetadata
+from comicapi.genericmetadata import Credit, GenericMetadata, Hash
 from comicapi.issuestring import IssueString
 from comictaggerlib import ctsettings, ctversion
 from comictaggerlib.applicationlogwindow import ApplicationLogWindow, QTextEditLogger
@@ -93,6 +94,7 @@ class TaggerWindow(QtWidgets.QMainWindow):
         self.md_attributes = {
             "data_origin": None,
             "issue_id": None,
+            "original_hash": (self.cbHashName, self.leOriginalHash),
             "series": self.leSeries,
             "issue": self.leIssueNum,
             "title": self.leTitle,
@@ -229,6 +231,8 @@ class TaggerWindow(QtWidgets.QMainWindow):
         for tag_id in config[0].internal__read_tags.copy():
             if tag_id not in self.enabled_tags():
                 config[0].internal__read_tags.remove(tag_id)
+        if self.config[0].Runtime_Options__preferred_hash:
+            self.config[0].internal__embedded_hash_type = self.config[0].Runtime_Options__preferred_hash
 
         self.selected_write_tags: list[str] = config[0].internal__write_tags or [self.enabled_tags()[0]]
         self.selected_read_tags: list[str] = config[0].internal__read_tags or [self.enabled_tags()[0]]
@@ -432,6 +436,16 @@ class TaggerWindow(QtWidgets.QMainWindow):
 
             self.setWindowTitle(f"{self.appName} - {self.comic_archive.path}{mod_str}{ro_str}")
 
+    def toggle_enable_embedding_hashes(self) -> None:
+        self.config[0].Runtime_Options__enable_embedding_hashes = self.actionEnableEmbeddingHashes.isChecked()
+        enable_widget(self.md_attributes["original_hash"], self.config[0].Runtime_Options__enable_embedding_hashes)
+        if not self.leOriginalHash.text().strip():
+            self.cbHashName.setCurrentText(self.config[0].internal__embedded_hash_type)
+        if self.config[0].Runtime_Options__enable_embedding_hashes:
+            self.config[0].Runtime_Options__preferred_hash = self.config[0].internal__embedded_hash_type
+        else:
+            self.config[0].Runtime_Options__preferred_hash = ""
+
     def config_menus(self) -> None:
         # File Menu
         self.actionAutoTag.triggered.connect(self.auto_tag)
@@ -453,8 +467,11 @@ class TaggerWindow(QtWidgets.QMainWindow):
         self.actionLiteralSearch.triggered.connect(self.literal_search)
         self.actionParse_Filename.triggered.connect(self.use_filename)
         self.actionParse_Filename_split_words.triggered.connect(self.use_filename_split)
-        self.actionReCalcPageDims.triggered.connect(self.recalc_page_dimensions)
+        self.actionReCalcArchiveInfo.triggered.connect(self.recalc_archive_info)
         self.actionSearchOnline.triggered.connect(self.query_online)
+        self.actionEnableEmbeddingHashes: QtWidgets.QAction
+        self.actionEnableEmbeddingHashes.triggered.connect(self.toggle_enable_embedding_hashes)
+        self.actionEnableEmbeddingHashes.setChecked(self.config[0].Runtime_Options__enable_embedding_hashes)
         # Window Menu
         self.actionLogWindow.triggered.connect(self.log_window.show)
         self.actionPageBrowser.triggered.connect(self.show_page_browser)
@@ -658,8 +675,6 @@ class TaggerWindow(QtWidgets.QMainWindow):
             self.page_browser.set_comic_archive(self.comic_archive)
             self.page_browser.metadata = self.metadata
 
-        if self.comic_archive is not None:
-            self.page_list_editor.set_data(self.comic_archive, self.metadata.pages)
         self.metadata_to_form()
         self.clear_dirty_flag()  # also updates the app title
         self.update_info_box()
@@ -680,7 +695,7 @@ class TaggerWindow(QtWidgets.QMainWindow):
         self.actionCopyTags.setEnabled(enabled)
         self.actionParse_Filename.setEnabled(enabled)
         self.actionParse_Filename_split_words.setEnabled(enabled)
-        self.actionReCalcPageDims.setEnabled(enabled)
+        self.actionReCalcArchiveInfo.setEnabled(enabled)
         self.actionRemoveAuto.setEnabled(enabled)
         self.actionRename.setEnabled(enabled)
         self.actionRepackage.setEnabled(enabled)
@@ -795,6 +810,9 @@ class TaggerWindow(QtWidgets.QMainWindow):
 
         md = self.metadata
 
+        original_hash = md.original_hash or Hash("", "")
+        self.cbHashName.setCurrentText(original_hash.name or self.config[0].internal__embedded_hash_type)
+        assign_text(self.leOriginalHash, original_hash.hash)
         assign_text(self.leSeries, md.series)
         assign_text(self.leIssueNum, md.issue)
         assign_text(self.leIssueCount, md.issue_count)
@@ -876,9 +894,12 @@ class TaggerWindow(QtWidgets.QMainWindow):
                     continue
 
                 self.add_new_credit_entry(row, credit)
+        if self.comic_archive:
+            self.page_list_editor.set_data(self.comic_archive, self.metadata.pages)
 
         self.twCredits.setSortingEnabled(True)
         self.update_credit_colors()
+        self.toggle_enable_embedding_hashes()
 
     def add_new_credit_entry(self, row: int, credit: Credit) -> None:
         self.twCredits.insertRow(row)
@@ -891,7 +912,6 @@ class TaggerWindow(QtWidgets.QMainWindow):
         language = utils.get_language_from_iso(credit.language) or credit.language
         item = QtWidgets.QTableWidgetItem(language)
         item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, credit.language)
-        item.setData(QtCore.Qt.ItemDataRole.UserRole, credit.language)
         item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
         self.twCredits.setItem(row, self.md_attributes["credits.language"], item)
 
@@ -922,6 +942,11 @@ class TaggerWindow(QtWidgets.QMainWindow):
         # copy the data from the form into the metadata
         md = GenericMetadata()
         md.is_empty = False
+
+        if utils.xlate(self.cbHashName.currentText()) and utils.xlate(self.leOriginalHash.text()):
+            md.original_hash = Hash(
+                utils.xlate(self.cbHashName.currentText()) or "", utils.xlate(self.leOriginalHash.text()) or ""
+            )
         md.alternate_number = utils.xlate(IssueString(self.leAltIssueNum.text()).as_string())
         md.issue = utils.xlate(IssueString(self.leIssueNum.text()).as_string())
         md.issue_count = utils.xlate_int(self.leIssueCount.text())
@@ -971,10 +996,7 @@ class TaggerWindow(QtWidgets.QMainWindow):
 
         for row in range(self.twCredits.rowCount()):
             role = self.twCredits.item(row, self.md_attributes["credits.role"]).text()
-            lang = (
-                self.twCredits.item(row, self.md_attributes["credits.language"]).data(QtCore.Qt.ItemDataRole.UserRole)
-                or self.twCredits.item(row, self.md_attributes["credits.language"]).text()
-            )
+            lang = self.twCredits.item(row, self.md_attributes["credits.language"]).text()
             name = self.twCredits.item(row, self.md_attributes["credits.person"]).text()
             primary_flag = self.twCredits.item(row, self.md_attributes["credits.primary"]).text() != ""
 
@@ -1237,6 +1259,7 @@ class TaggerWindow(QtWidgets.QMainWindow):
 
         self.update_credit_colors()
         self.page_list_editor.select_read_tags(self.selected_write_tags)
+        self.toggle_enable_embedding_hashes()
 
     def cell_double_clicked(self, r: int, c: int) -> None:
         self.edit_credit()
@@ -1272,15 +1295,11 @@ class TaggerWindow(QtWidgets.QMainWindow):
         old = Credit()
         if edit:
             row = self.twCredits.currentRow()
-            lang = str(
-                self.twCredits.item(row, self.md_attributes["credits.language"]).data(QtCore.Qt.ItemDataRole.UserRole)
-                or utils.get_language_iso(self.twCredits.item(row, self.md_attributes["credits.language"]).text())
-            )
             old = Credit(
                 self.twCredits.item(row, self.md_attributes["credits.person"]).text(),
                 self.twCredits.item(row, self.md_attributes["credits.role"]).text(),
                 self.twCredits.item(row, self.md_attributes["credits.primary"]).text() != "",
-                lang,
+                self.twCredits.item(row, self.md_attributes["credits.language"]).text(),
             )
 
         editor = CreditEditorWindow(self, CreditEditorWindow.ModeEdit, old)
@@ -1317,13 +1336,9 @@ class TaggerWindow(QtWidgets.QMainWindow):
             if ok_to_mod:
                 # modify it
                 if edit:
-                    lang = utils.get_language_from_iso(new.language) or new.language
                     self.twCredits.item(row, self.md_attributes["credits.role"]).setText(new.role)
                     self.twCredits.item(row, self.md_attributes["credits.person"]).setText(new.person)
-                    self.twCredits.item(row, self.md_attributes["credits.language"]).setText(lang)
-                    self.twCredits.item(row, self.md_attributes["credits.language"]).setData(
-                        QtCore.Qt.ItemDataRole.UserRole, new.language
-                    )
+                    self.twCredits.item(row, self.md_attributes["credits.language"]).setText(new.language)
                     self.update_credit_primary_flag(row, new.primary)
                 else:
                     # add new entry
@@ -1415,6 +1430,9 @@ class TaggerWindow(QtWidgets.QMainWindow):
 
         self.adjust_tags_combo()
 
+        self.cbHashName: QtWidgets.QComboBox
+        self.cbHashName.addItems(sorted(hashlib.algorithms_available))
+
         # Add talker entries
         for t_id, talker in self.talkers.items():
             self.cbx_sources.addItem(talker.name, t_id)
@@ -2114,12 +2132,22 @@ class TaggerWindow(QtWidgets.QMainWindow):
         self.metadata = CBLTransformer(self.metadata, self.config[0]).apply()
         self.metadata_to_form()
 
-    def recalc_page_dimensions(self) -> None:
+    def recalc_archive_info(self) -> None:
         QtWidgets.QApplication.setOverrideCursor(QtGui.QCursor(QtCore.Qt.CursorShape.WaitCursor))
         for p in self.metadata.pages:
             p.byte_size = None
             p.height = None
             p.width = None
+        if self.comic_archive and self.config[0].Runtime_Options__preferred_hash:
+            self.metadata.original_hash = None
+            self.comic_archive.apply_archive_info_to_metadata(
+                self.metadata, True, hash_archive=self.cbHashName.currentText()
+            )
+            original_hash = self.metadata.original_hash or Hash("", "")
+            self.leOriginalHash.setText(original_hash.hash)
+            self.cbHashName.setCurrentText(original_hash.name or self.config[0].internal__embedded_hash_type)
+            self.page_list_editor.set_data(self.comic_archive, self.metadata.pages)
+
         self.set_dirty_flag()
         QtWidgets.QApplication.restoreOverrideCursor()
 

comictaggerlib/ui/qtutils.py

@@ -6,7 +6,7 @@ import io
 import logging
 import traceback
 import webbrowser
-from collections.abc import Sequence
+from collections.abc import Collection, Sequence
 
 from PyQt5.QtCore import QUrl
 from PyQt5.QtWidgets import QWidget
@@ -147,7 +147,7 @@ if qt_available:
 
     active_palette = None
 
-    def enable_widget(widget: QtWidgets.QWidget | list[QtWidgets.QWidget], enable: bool) -> None:
+    def enable_widget(widget: QtWidgets.QWidget | Collection[QtWidgets.QWidget], enable: bool) -> None:
         if isinstance(widget, Sequence):
             for w in widget:
                 _enable_widget(w, enable)

comictaggerlib/ui/taggerwindow.ui

@@ -955,7 +955,7 @@ Source</string>
                   <item>
                    <layout class="QFormLayout" name="formLayout_8">
                     <property name="fieldGrowthPolicy">
-                     <enum>QFormLayout::ExpandingFieldsGrow</enum>
+                     <enum>QFormLayout::AllNonFixedFieldsGrow</enum>
                     </property>
                     <item row="0" column="0">
                      <widget class="QLabel" name="label_20">
@@ -970,6 +970,30 @@ Source</string>
                     <item row="0" column="1">
                      <widget class="QLineEdit" name="leScanInfo"/>
                     </item>
+                    <item row="2" column="1">
+                     <widget class="QLineEdit" name="leOriginalHash"/>
+                    </item>
+                    <item row="2" column="0">
+                     <widget class="QLabel" name="lblOriginalHash">
+                      <property name="text">
+                       <string>Original Hash</string>
+                      </property>
+                      <property name="buddy">
+                       <cstring>leOriginalHash</cstring>
+                      </property>
+                     </widget>
+                    </item>
+                    <item row="1" column="1">
+                     <widget class="QComboBox" name="cbHashName">
+                     </widget>
+                    </item>
+                    <item row="1" column="0">
+                     <widget class="QLabel" name="lblHashName">
+                      <property name="text">
+                       <string>Hash Type</string>
+                      </property>
+                     </widget>
+                    </item>
                    </layout>
                   </item>
                  </layout>
@@ -1428,7 +1452,8 @@ Source</string>
     <addaction name="actionLiteralSearch"/>
     <addaction name="separator"/>
     <addaction name="actionApplyCBLTransform"/>
-    <addaction name="actionReCalcPageDims"/>
+    <addaction name="actionReCalcArchiveInfo"/>
+    <addaction name="actionEnableEmbeddingHashes"/>
    </widget>
    <widget class="QMenu" name="menuWindow">
     <property name="title">
@@ -1717,9 +1742,12 @@ Source</string>
     <string>Ctrl+Shift+F</string>
    </property>
   </action>
-  <action name="actionReCalcPageDims">
+  <action name="actionReCalcArchiveInfo">
    <property name="text">
-    <string>Re-Calculate Page Dimensions</string>
+    <string>Re-Calculate Archive Information</string>
+   </property>
+   <property name="toolTip">
+    <string>Only includes page size info and original hash, original hash wil be overwritten</string>
    </property>
    <property name="shortcut">
     <string>Ctrl+Shift+R</string>
@@ -1814,6 +1842,14 @@ Source</string>
     <string>Ctrl+S</string>
    </property>
   </action>
+  <action name="actionEnableEmbeddingHashes">
+   <property name="checkable">
+    <bool>true</bool>
+   </property>
+   <property name="text">
+    <string>Enable Embedding Hashes</string>
+   </property>
+  </action>
  </widget>
  <layoutdefault spacing="6" margin="11"/>
  <customwidgets>

comictalker/talkers/comicvine.py

@@ -22,6 +22,7 @@ import json
 import logging
 import pathlib
 import time
+from collections import defaultdict
 from typing import Any, Callable, Generic, TypeVar, cast
 from urllib.parse import parse_qsl, urljoin
 
@@ -185,7 +186,7 @@ class ComicVineTalker(ComicTalker):
         self.default_api_url = self.api_url = f"{self.website}/api/"
         self.default_api_key = self.api_key = "27431e6787042105bd3e47e169a624521f89f3a4"
         self.use_series_start_as_volume: bool = False
-        self.total_requests_made: dict[str, int] = utils.DefaultDict(default=lambda x: 0)
+        self.total_requests_made: dict[str, int] = defaultdict(int)
         self.custom_url_parameters: dict[str, str] = {}
 
     def _log_total_requests(self) -> None: