revamp scripts access

Update to Python 3
Use ImageHasher to compare and find images
Use filetype to find all images regardless of imagetype

comicapi/comicarchive.py

@@ -64,6 +64,7 @@ class MetaDataStyle:
     CIX = 1
     COMET = 2
     name = ["ComicBookLover", "ComicRack", "CoMet"]
+    short = ["cbl", "cr", "comet"]
 
 
 class UnknownArchiver:

comicapi/utils.py

@@ -21,7 +21,7 @@ import pathlib
 import re
 import unicodedata
 from collections import defaultdict
-from typing import Any, List, Optional, Union
+from typing import Any, Iterable, List, Optional, Union
 
 import pycountry
 
@@ -233,7 +233,7 @@ class ImprintDict(dict):
     if the key does not exist the key is returned as the publisher unchanged
     """
 
-    def __init__(self, publisher, mapping=(), **kwargs):
+    def __init__(self, publisher: str, mapping: Iterable = (), **kwargs: Any):
         super().__init__(mapping, **kwargs)
         self.publisher = publisher
 

comictaggerlib/cli.py

@@ -16,12 +16,12 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+import argparse
 import json
 import logging
 import os
 import sys
 from pprint import pprint
-from typing import cast
 
 from comicapi import utils
 from comicapi.comicarchive import ComicArchive, MetaDataStyle
@@ -30,18 +30,19 @@ from comictaggerlib.cbltransformer import CBLTransformer
 from comictaggerlib.comicvinetalker import ComicVineTalker, ComicVineTalkerException
 from comictaggerlib.filerenamer import FileRenamer
 from comictaggerlib.issueidentifier import IssueIdentifier
-from comictaggerlib.options import Options
 from comictaggerlib.resulttypes import IssueResult, MultipleMatch, OnlineMatchResults
 from comictaggerlib.settings import ComicTaggerSettings
 
 logger = logging.getLogger(__name__)
 
 
-def actual_issue_data_fetch(match: IssueResult, settings: ComicTaggerSettings, opts: Options) -> GenericMetadata:
+def actual_issue_data_fetch(
+    match: IssueResult, settings: ComicTaggerSettings, opts: argparse.Namespace
+) -> GenericMetadata:
     # now get the particular issue data
     try:
         comic_vine = ComicVineTalker()
-        comic_vine.wait_for_rate_limit = opts.wait_and_retry_on_rate_limit
+        comic_vine.wait_for_rate_limit = opts.wait_on_cv_rate_limit
         cv_md = comic_vine.fetch_issue_data(match["volume_id"], match["issue_number"], settings)
     except ComicVineTalkerException:
         logger.exception("Network error while getting issue details.  Save aborted")
@@ -53,10 +54,10 @@ def actual_issue_data_fetch(match: IssueResult, settings: ComicTaggerSettings, o
     return cv_md
 
 
-def actual_metadata_save(ca: ComicArchive, opts: Options, md: GenericMetadata) -> bool:
+def actual_metadata_save(ca: ComicArchive, opts: argparse.Namespace, md: GenericMetadata) -> bool:
     if not opts.dryrun:
         # write out the new data
-        if not ca.write_metadata(md, opts.data_style if opts.data_style is not None else 0):
+        if not ca.write_metadata(md, opts.type if opts.type is not None else 0):
             logger.error("The tag save seemed to fail!")
             return False
 
@@ -74,7 +75,7 @@ def actual_metadata_save(ca: ComicArchive, opts: Options, md: GenericMetadata) -
 
 
 def display_match_set_for_choice(
-    label: str, match_set: MultipleMatch, opts: Options, settings: ComicTaggerSettings
+    label: str, match_set: MultipleMatch, opts: argparse.Namespace, settings: ComicTaggerSettings
 ) -> None:
     print(f"{match_set.ca.path} -- {label}:")
 
@@ -103,11 +104,9 @@ def display_match_set_for_choice(
             # save the data!
             # we know at this point, that the file is all good to go
             ca = match_set.ca
-            md = create_local_metadata(
-                opts, ca, ca.has_metadata(opts.data_style if opts.data_style is not None else 0), settings
-            )
+            md = create_local_metadata(opts, ca, ca.has_metadata(opts.type if opts.type is not None else 0), settings)
             cv_md = actual_issue_data_fetch(match_set.matches[int(i) - 1], settings, opts)
-            if opts.overwrite_metadata:
+            if opts.overwrite:
                 md = cv_md
             else:
                 md.overlay(cv_md)
@@ -118,7 +117,9 @@ def display_match_set_for_choice(
             actual_metadata_save(ca, opts, md)
 
 
-def post_process_matches(match_results: OnlineMatchResults, opts: Options, settings: ComicTaggerSettings) -> None:
+def post_process_matches(
+    match_results: OnlineMatchResults, opts: argparse.Namespace, settings: ComicTaggerSettings
+) -> None:
     # now go through the match results
     if opts.show_save_summary:
         if len(match_results.good_matches) > 0:
@@ -161,14 +162,14 @@ def post_process_matches(match_results: OnlineMatchResults, opts: Options, setti
             display_match_set_for_choice(label, match_set, opts, settings)
 
 
-def cli_mode(opts: Options, settings: ComicTaggerSettings) -> None:
-    if len(opts.file_list) < 1:
+def cli_mode(opts: argparse.Namespace, settings: ComicTaggerSettings) -> None:
+    if len(opts.files) < 1:
         logger.error("You must specify at least one filename.  Use the -h option for more info")
         return
 
     match_results = OnlineMatchResults()
 
-    for f in opts.file_list:
+    for f in opts.files:
         process_file_cli(f, opts, settings, match_results)
         sys.stdout.flush()
 
@@ -176,7 +177,7 @@ def cli_mode(opts: Options, settings: ComicTaggerSettings) -> None:
 
 
 def create_local_metadata(
-    opts: Options, ca: ComicArchive, has_desired_tags: bool, settings: ComicTaggerSettings
+    opts: argparse.Namespace, ca: ComicArchive, has_desired_tags: bool, settings: ComicTaggerSettings
 ) -> GenericMetadata:
     md = GenericMetadata()
     md.set_default_page_list(ca.get_number_of_pages())
@@ -190,17 +191,17 @@ def create_local_metadata(
             settings.remove_publisher,
             opts.split_words,
         )
-        if opts.overwrite_metadata:
+        if opts.overwrite:
             md = f_md
         else:
             md.overlay(f_md)
 
     if has_desired_tags:
-        t_md = ca.read_metadata(opts.data_style if opts.data_style is not None else 0)
+        t_md = ca.read_metadata(opts.type if opts.type is not None else 0)
         md.overlay(t_md)
 
     # finally, use explicit stuff
-    if opts.overwrite_metadata and not opts.metadata.is_empty:
+    if opts.overwrite and not opts.metadata.is_empty:
         md = opts.metadata
     else:
         md.overlay(opts.metadata)
@@ -209,9 +210,9 @@ def create_local_metadata(
 
 
 def process_file_cli(
-    filename: str, opts: Options, settings: ComicTaggerSettings, match_results: OnlineMatchResults
+    filename: str, opts: argparse.Namespace, settings: ComicTaggerSettings, match_results: OnlineMatchResults
 ) -> None:
-    batch_mode = len(opts.file_list) > 1
+    batch_mode = len(opts.files) > 1
 
     ca = ComicArchive(filename, settings.rar_exe_path, ComicTaggerSettings.get_graphic("nocover.png"))
 
@@ -223,7 +224,7 @@ def process_file_cli(
         logger.error("Sorry, but %s is not a comic archive!", filename)
         return
 
-    if not ca.is_writable() and (opts.delete_tags or opts.copy_tags or opts.save_tags or opts.rename_file):
+    if not ca.is_writable() and (opts.delete or opts.copy or opts.save or opts.rename):
         logger.error("This archive is not writable for that tag type")
         return
 
@@ -235,9 +236,9 @@ def process_file_cli(
     if ca.has_comet():
         has[MetaDataStyle.COMET] = True
 
-    if opts.print_tags:
+    if opts.print:
 
-        if opts.data_style is None:
+        if opts.type is None:
             page_count = ca.get_number_of_pages()
 
             brief = ""
@@ -275,7 +276,7 @@ def process_file_cli(
 
         print()
 
-        if opts.data_style is None or opts.data_style == MetaDataStyle.CIX:
+        if opts.type is None or opts.type == MetaDataStyle.CIX:
             if has[MetaDataStyle.CIX]:
                 print("--------- ComicRack tags ---------")
                 if opts.raw:
@@ -283,7 +284,7 @@ def process_file_cli(
                 else:
                     print(ca.read_cix())
 
-        if opts.data_style is None or opts.data_style == MetaDataStyle.CBI:
+        if opts.type is None or opts.type == MetaDataStyle.CBI:
             if has[MetaDataStyle.CBI]:
                 print("------- ComicBookLover tags -------")
                 if opts.raw:
@@ -291,7 +292,7 @@ def process_file_cli(
                 else:
                     print(ca.read_cbi())
 
-        if opts.data_style is None or opts.data_style == MetaDataStyle.COMET:
+        if opts.type is None or opts.type == MetaDataStyle.COMET:
             if has[MetaDataStyle.COMET]:
                 print("----------- CoMet tags -----------")
                 if opts.raw:
@@ -299,11 +300,11 @@ def process_file_cli(
                 else:
                     print(ca.read_comet())
 
-    elif opts.delete_tags:
-        style_name = MetaDataStyle.name[cast(int, opts.data_style)]
-        if has[cast(int, opts.data_style)]:
+    elif opts.delete:
+        style_name = MetaDataStyle.name[opts.type]
+        if has[opts.type]:
             if not opts.dryrun:
-                if not ca.remove_metadata(cast(int, opts.data_style)):
+                if not ca.remove_metadata(opts.type):
                     print(f"{filename}: Tag removal seemed to fail!")
                 else:
                     print(f"{filename}: Removed {style_name} tags.")
@@ -312,24 +313,24 @@ def process_file_cli(
         else:
             print(f"{filename}: This archive doesn't have {style_name} tags to remove.")
 
-    elif opts.copy_tags:
-        dst_style_name = MetaDataStyle.name[cast(int, opts.data_style)]
-        if opts.no_overwrite and has[cast(int, opts.data_style)]:
+    elif opts.copy:
+        dst_style_name = MetaDataStyle.name[opts.type]
+        if opts.no_overwrite and has[opts.type]:
             print(f"{filename}: Already has {dst_style_name} tags. Not overwriting.")
             return
-        if opts.copy_source == opts.data_style:
+        if opts.copy == opts.type:
             print(f"{filename}: Destination and source are same: {dst_style_name}. Nothing to do.")
             return
 
-        src_style_name = MetaDataStyle.name[cast(int, opts.copy_source)]
-        if has[cast(int, opts.copy_source)]:
+        src_style_name = MetaDataStyle.name[opts.copy]
+        if has[opts.copy]:
             if not opts.dryrun:
-                md = ca.read_metadata(cast(int, opts.copy_source))
+                md = ca.read_metadata(opts.copy)
 
-                if settings.apply_cbl_transform_on_bulk_operation and opts.data_style == MetaDataStyle.CBI:
+                if settings.apply_cbl_transform_on_bulk_operation and opts.type == MetaDataStyle.CBI:
                     md = CBLTransformer(md, settings).apply()
 
-                if not ca.write_metadata(md, cast(int, opts.data_style)):
+                if not ca.write_metadata(md, opts.type):
                     print(f"{filename}: Tag copy seemed to fail!")
                 else:
                     print(f"{filename}: Copied {src_style_name} tags to {dst_style_name}.")
@@ -338,35 +339,35 @@ def process_file_cli(
         else:
             print(f"{filename}: This archive doesn't have {src_style_name} tags to copy.")
 
-    elif opts.save_tags:
+    elif opts.save:
 
-        if opts.no_overwrite and has[cast(int, opts.data_style)]:
-            print(f"{filename}: Already has {MetaDataStyle.name[cast(int, opts.data_style)]} tags. Not overwriting.")
+        if opts.no_overwrite and has[opts.type]:
+            print(f"{filename}: Already has {MetaDataStyle.name[opts.type]} tags. Not overwriting.")
             return
 
         if batch_mode:
             print(f"Processing {ca.path}...")
 
-        md = create_local_metadata(opts, ca, has[cast(int, opts.data_style)], settings)
+        md = create_local_metadata(opts, ca, has[opts.type], settings)
         if md.issue is None or md.issue == "":
-            if opts.assume_issue_is_one_if_not_set:
+            if opts.assume_issue_one:
                 md.issue = "1"
 
         # now, search online
-        if opts.search_online:
-            if opts.issue_id is not None:
+        if opts.online:
+            if opts.id is not None:
                 # we were given the actual ID to search with
                 try:
                     comic_vine = ComicVineTalker()
-                    comic_vine.wait_for_rate_limit = opts.wait_and_retry_on_rate_limit
-                    cv_md = comic_vine.fetch_issue_data_by_issue_id(opts.issue_id, settings)
+                    comic_vine.wait_for_rate_limit = opts.wait_on_cv_rate_limit
+                    cv_md = comic_vine.fetch_issue_data_by_issue_id(opts.id, settings)
                 except ComicVineTalkerException:
                     logger.exception("Network error while getting issue details. Save aborted")
                     match_results.fetch_data_failures.append(str(ca.path.absolute()))
                     return
 
                 if cv_md is None:
-                    logger.error("No match for ID %s was found.", opts.issue_id)
+                    logger.error("No match for ID %s was found.", opts.id)
                     match_results.no_matches.append(str(ca.path.absolute()))
                     return
 
@@ -387,7 +388,7 @@ def process_file_cli(
                 # use our overlayed MD struct to search
                 ii.set_additional_metadata(md)
                 ii.only_use_additional_meta_data = True
-                ii.wait_and_retry_on_rate_limit = opts.wait_and_retry_on_rate_limit
+                ii.wait_and_retry_on_rate_limit = opts.wait_on_cv_rate_limit
                 ii.set_output_function(myoutput)
                 ii.cover_page_index = md.get_cover_page_index_list()[0]
                 matches = ii.search()
@@ -422,7 +423,7 @@ def process_file_cli(
                     logger.error("Online search: Multiple good matches. Save aborted")
                     match_results.multiple_matches.append(MultipleMatch(ca, matches))
                     return
-                if low_confidence and opts.abortOnLowConfidence:
+                if low_confidence and opts.abort_on_low_confidence:
                     logger.error("Online search: Low confidence match. Save aborted")
                     match_results.low_confidence_matches.append(MultipleMatch(ca, matches))
                     return
@@ -439,7 +440,7 @@ def process_file_cli(
                     match_results.fetch_data_failures.append(str(ca.path.absolute()))
                     return
 
-            if opts.overwrite_metadata:
+            if opts.overwrite:
                 md = cv_md
             else:
                 md.overlay(cv_md)
@@ -453,14 +454,14 @@ def process_file_cli(
         else:
             match_results.good_matches.append(str(ca.path.absolute()))
 
-    elif opts.rename_file:
+    elif opts.rename:
 
         msg_hdr = ""
         if batch_mode:
             msg_hdr = f"{ca.path}: "
 
-        if opts.data_style is not None:
-            use_tags = has[opts.data_style]
+        if opts.type is not None:
+            use_tags = has[opts.type]
         else:
             use_tags = False
 
@@ -529,7 +530,7 @@ def process_file_cli(
         rar_file = os.path.abspath(os.path.abspath(filename))
         new_file = os.path.splitext(rar_file)[0] + ".cbz"
 
-        if opts.abort_export_on_conflict and os.path.lexists(new_file):
+        if opts.abort_on_conflict and os.path.lexists(new_file):
             print(msg_hdr + f"{os.path.split(new_file)[1]} already exists in the that folder.")
             return
 

comictaggerlib/comicvinetalker.py

@@ -438,9 +438,9 @@ class ComicVineTalker:
         # Now, map the Comic Vine data to generic metadata
         return self.map_cv_data_to_metadata(volume_results, issue_results, settings)
 
-    def fetch_issue_data_by_issue_id(self, issue_id: str, settings: ComicTaggerSettings) -> GenericMetadata:
+    def fetch_issue_data_by_issue_id(self, issue_id: int, settings: ComicTaggerSettings) -> GenericMetadata:
 
-        issue_url = self.api_base_url + "/issue/" + CVTypeID.Issue + "-" + issue_id
+        issue_url = self.api_base_url + "/issue/" + CVTypeID.Issue + "-" + str(issue_id)
         params = {"api_key": self.api_key, "format": "json"}
         cv_response = self.get_cv_content(issue_url, params)
 

comictaggerlib/fileselectionlist.py

@@ -108,6 +108,34 @@ class FileSelectionList(QtWidgets.QWidget):
     def deselect_all(self) -> None:
         self.twList.setRangeSelected(QtWidgets.QTableWidgetSelectionRange(0, 0, self.twList.rowCount() - 1, 5), False)
 
+    def remove_paths(self, file_list: list[str]) -> None:
+        flist = file_list
+        current_removed = False
+        self.twList.setSortingEnabled(False)
+        for row in reversed(range(self.twList.rowCount())):
+            print(row)
+            ca = self.get_archive_by_row(row)
+            print(flist, str(ca.path.absolute()))
+            if ca and str(ca.path.absolute()) in flist:
+                flist.remove(str(ca.path.absolute()))
+                self.twList.removeRow(row)
+                if row == self.twList.currentRow():
+                    current_removed = True
+
+        self.twList.setSortingEnabled(True)
+
+        self.items_removed(current_removed)
+
+    def items_removed(self, current_removed: bool):
+        if self.twList.rowCount() > 0 and current_removed:
+            # since on a removal, we select row 0, make sure callback occurs if
+            # we're already there
+            if self.twList.currentRow() == 0:
+                self.current_item_changed_cb(self.twList.currentItem(), None)
+            self.twList.selectRow(0)
+        elif self.twList.rowCount() <= 0:
+            self.listCleared.emit()
+
     def remove_archive_list(self, ca_list: list[ComicArchive]) -> None:
         self.twList.setSortingEnabled(False)
         current_removed = False
@@ -120,15 +148,7 @@ class FileSelectionList(QtWidgets.QWidget):
                     self.twList.removeRow(row)
                     break
         self.twList.setSortingEnabled(True)
-
-        if self.twList.rowCount() > 0 and current_removed:
-            # since on a removal, we select row 0, make sure callback occurs if
-            # we're already there
-            if self.twList.currentRow() == 0:
-                self.current_item_changed_cb(self.twList.currentItem(), None)
-            self.twList.selectRow(0)
-        elif self.twList.rowCount() <= 0:
-            self.listCleared.emit()
+        self.items_removed(current_removed)
 
     def get_archive_by_row(self, row: int) -> Optional[ComicArchive]:
         if row >= 0:
@@ -166,14 +186,7 @@ class FileSelectionList(QtWidgets.QWidget):
         self.twList.setSortingEnabled(True)
         self.twList.currentItemChanged.connect(self.current_item_changed_cb)
 
-        if self.twList.rowCount() > 0:
-            # since on a removal, we select row 0, make sure callback occurs if
-            # we're already there
-            if self.twList.currentRow() == 0:
-                self.current_item_changed_cb(self.twList.currentItem(), None)
-            self.twList.selectRow(0)
-        else:
-            self.listCleared.emit()
+        self.items_removed(True)
 
     def add_path_list(self, pathlist: list[str]) -> None:
 
@@ -345,11 +358,11 @@ class FileSelectionList(QtWidgets.QWidget):
             fi.ca.read_cix()
             fi.ca.has_cbi()
 
-    def get_selected_archive_list(self) -> List[ComicArchive]:
+    def get_archive_list(self, all_comics=False) -> List[ComicArchive]:
         ca_list: List[ComicArchive] = []
         for r in range(self.twList.rowCount()):
             item = self.twList.item(r, FileSelectionList.dataColNum)
-            if item.isSelected():
+            if item.isSelected() or all_comics:
                 fi: FileInfo = item.data(QtCore.Qt.ItemDataRole.UserRole)
                 ca_list.append(fi.ca)
 

comictaggerlib/main.py

@@ -32,7 +32,7 @@ from comicapi import utils
 from comictaggerlib import cli
 from comictaggerlib.comicvinetalker import ComicVineTalker
 from comictaggerlib.ctversion import version
-from comictaggerlib.options import Options
+from comictaggerlib.options import parse_cmd_line
 from comictaggerlib.settings import ComicTaggerSettings
 
 logger = logging.getLogger("comictagger")
@@ -111,8 +111,7 @@ def update_publishers() -> None:
 
 
 def ctmain() -> None:
-    opts = Options()
-    opts.parse_cmd_line_args()
+    opts = parse_cmd_line()
     SETTINGS = ComicTaggerSettings(opts.config_path)
 
     os.makedirs(ComicTaggerSettings.get_settings_folder() / "logs", exist_ok=True)
@@ -138,7 +137,7 @@ def ctmain() -> None:
         if opts.cv_api_key != SETTINGS.cv_api_key:
             SETTINGS.cv_api_key = opts.cv_api_key
             SETTINGS.save()
-    if opts.only_set_key:
+    if opts.only_set_cv_key:
         print("Key set")
         return
 
@@ -203,7 +202,7 @@ def ctmain() -> None:
             QtWidgets.QApplication.processEvents()
 
         try:
-            tagger_window = TaggerWindow(opts.file_list, SETTINGS, opts=opts)
+            tagger_window = TaggerWindow(opts.files, SETTINGS, opts=opts)
             tagger_window.setWindowIcon(QtGui.QIcon(ComicTaggerSettings.get_graphic("app.png")))
             tagger_window.show()
 

comictaggerlib/options.py

@@ -14,12 +14,11 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-import getopt
+import argparse
 import logging
 import os
 import platform
 import sys
-from typing import Optional
 
 from comicapi import utils
 from comicapi.comicarchive import MetaDataStyle
@@ -29,440 +28,367 @@ from comictaggerlib import ctversion
 logger = logging.getLogger(__name__)
 
 
-class Options:
-    help_text = """Usage: {0} [option] ... [file [files ...]]
+def define_args() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(
+        description="""A utility for reading and writing metadata to comic archives.
 
-A utility for reading and writing metadata to comic archives.
+    If no options are given, %(prog)s will run in windowed mode.""",
+        epilog="For more help visit the wiki at: https://github.com/comictagger/comictagger/wiki",
+        formatter_class=argparse.RawTextHelpFormatter,
+    )
+    parser.add_argument(
+        "--version",
+        action="store_true",
+        help="Display version.",
+    )
+    commands = parser.add_mutually_exclusive_group()
+    commands.add_argument(
+        "-p",
+        "--print",
+        action="store_true",
+        help="""Print out tag info from file. Specify type\n(via -t) to get only info of that tag type.\n\n""",
+    )
+    commands.add_argument(
+        "-d",
+        "--delete",
+        action="store_true",
+        help="Deletes the tag block of specified type (via -t).\n",
+    )
+    commands.add_argument(
+        "-c",
+        "--copy",
+        type=metadata_type,
+        metavar="{CR,CBL,COMET}",
+        help="Copy the specified source tag block to\ndestination style specified via -t\n(potentially lossy operation).\n\n",
+    )
+    commands.add_argument(
+        "-s",
+        "--save",
+        action="store_true",
+        help="Save out tags as specified type (via -t).\nMust specify also at least -o, -f, or -m.\n\n",
+    )
+    commands.add_argument(
+        "-r",
+        "--rename",
+        action="store_true",
+        help="Rename the file based on specified tag style.",
+    )
+    commands.add_argument(
+        "-e",
+        "--export-to-zip",
+        action="store_true",
+        help="Export RAR archive to Zip format.",
+    )
+    commands.add_argument(
+        "--only-set-cv-key",
+        action="store_true",
+        help="Only set the Comic Vine API key and quit.\n\n",
+    )
+    parser.add_argument(
+        "-1",
+        "--assume-issue-one",
+        action="store_true",
+        help="""Assume issue number is 1 if not found (relevant for -s).\n\n""",
+    )
+    parser.add_argument(
+        "--abort-on-conflict",
+        action="store_true",
+        help="""Don't export to zip if intended new filename\nexists (otherwise, creates a new unique filename).\n\n""",
+    )
+    parser.add_argument(
+        "-a",
+        "--auto-imprint",
+        action="store_true",
+        help="""Enables the auto imprint functionality.\ne.g. if the publisher is set to 'vertigo' it\nwill be updated to 'DC Comics' and the imprint\nproperty will be set to 'Vertigo'.\n\n""",
+    )
+    parser.add_argument(
+        "--config",
+        dest="config_path",
+        help="""Config directory defaults to ~/.ComicTagger\non Linux/Mac and %%APPDATA%% on Windows\n""",
+    )
+    parser.add_argument(
+        "--cv-api-key",
+        help="Use the given Comic Vine API Key (persisted in settings).",
+    )
+    parser.add_argument(
+        "--delete-rar",
+        action="store_true",
+        dest="delete_after_zip_export",
+        help="""Delete original RAR archive after successful\nexport to Zip.""",
+    )
+    parser.add_argument(
+        "-f",
+        "--parse-filename",
+        "--parsefilename",
+        action="store_true",
+        help="""Parse the filename to get some info,\nspecifically series name, issue number,\nvolume, and publication year.\n\n""",
+    )
+    parser.add_argument(
+        "--id",
+        dest="issue_id",
+        type=int,
+        help="""Use the issue ID when searching online.\nOverrides all other metadata.\n\n""",
+    )
+    parser.add_argument(
+        "-t",
+        "--type",
+        metavar="{CR,CBL,COMET}",
+        type=metadata_type,
+        help="""Specify TYPE as either CR, CBL, COMET\n(as either ComicRack, ComicBookLover,\nor CoMet style tags, respectively).\n\n""",
+    )
+    parser.add_argument(
+        "-o",
+        "--online",
+        action="store_true",
+        help="""Search online and attempt to identify file\nusing existing metadata and images in archive.\nMay be used in conjunction with -f and -m.\n\n""",
+    )
+    parser.add_argument(
+        "-m",
+        "--metadata",
+        type=parse_metadata_from_string,
+        help="""Explicitly define, as a list, some tags to be used.  e.g.:\n"series=Plastic Man, publisher=Quality Comics"\n"series=Kickers^, Inc., issue=1, year=1986"\nName-Value pairs are comma separated. Use a\n"^" to escape an "=" or a ",", as shown in\nthe example above.  Some names that can be\nused: series, issue, issue_count, year,\npublisher, title\n\n""",
+    )
+    parser.add_argument(
+        "-i",
+        "--interactive",
+        action="store_true",
+        help="""Interactively query the user when there are\nmultiple matches for an online search.\n\n""",
+    )
+    parser.add_argument(
+        "--no-overwrite",
+        "--nooverwrite",
+        action="store_true",
+        help="""Don't modify tag block if it already exists (relevant for -s or -c).""",
+    )
+    parser.add_argument(
+        "--noabort",
+        dest="abort_on_low_confidence",
+        action="store_false",
+        help="""Don't abort save operation when online match\nis of low confidence.\n\n""",
+    )
+    parser.add_argument(
+        "--nosummary",
+        dest="show_save_summary",
+        action="store_false",
+        help="Suppress the default summary after a save operation.\n\n",
+    )
+    parser.add_argument(
+        "--overwrite",
+        action="store_true",
+        help="""Overwite all existing metadata.\nMay be used in conjunction with -o, -f and -m.\n\n""",
+    )
+    parser.add_argument(
+        "--raw", action="store_true", help="""With -p, will print out the raw tag block(s)\nfrom the file.\n"""
+    )
+    parser.add_argument(
+        "-R",
+        "--recursive",
+        action="store_true",
+        help="Recursively include files in sub-folders.",
+    )
+    parser.add_argument(
+        "-S",
+        "--script",
+        help="""Run an "add-on" python script that uses the\nComicTagger library for custom processing.\nScript arguments can follow the script name.\n\n""",
+    )
+    parser.add_argument(
+        "--split-words",
+        action="store_true",
+        help="""Splits words before parsing the filename.\ne.g. 'judgedredd' to 'judge dredd'\n\n""",
+    )
+    parser.add_argument(
+        "--terse",
+        action="store_true",
+        help="Don't say much (for print mode).",
+    )
+    parser.add_argument(
+        "-v",
+        "--verbose",
+        action="store_true",
+        help="Be noisy when doing what it does.",
+    )
+    parser.add_argument(
+        "-w",
+        "--wait-on-cv-rate-limit",
+        action="store_true",
+        help="""When encountering a Comic Vine rate limit\nerror, wait and retry query.\n\n""",
+    )
+    parser.add_argument(
+        "-n", "--dryrun", action="store_true", help="Don't actually modify file (only relevant for -d, -s, or -r).\n\n"
+    )
+    parser.add_argument(
+        "--darkmode",
+        action="store_true",
+        help="Windows only. Force a dark pallet",
+    )
+    parser.add_argument(
+        "-g",
+        "--glob",
+        action="store_true",
+        help="Windows only. Enable globbing",
+    )
+    parser.add_argument("files", nargs="*")
+    return parser
 
-If no options are given, {0} will run in windowed mode.
 
--p, --print                 Print out tag info from file. Specify type
-                            (via -t) to get only info of that tag type.
-    --raw                   With -p, will print out the raw tag block(s)
-                            from the file.
--d, --delete                Deletes the tag block of specified type (via
-                            -t).
--c, --copy=SOURCE           Copy the specified source tag block to
-                            destination style specified via -t
-                            (potentially lossy operation).
--s, --save                  Save out tags as specified type (via -t).
-                            Must specify also at least -o, -p, or -m.
-    --nooverwrite           Don't modify tag block if it already exists
-                            (relevant for -s or -c).
--1, --assume-issue-one      Assume issue number is 1 if not found
-                            (relevant for -s).
--n, --dryrun                Don't actually modify file (only relevant for
-                            -d, -s, or -r).
--t, --type=TYPE             Specify TYPE as either "CR", "CBL", or
-                            "COMET" (as either ComicRack, ComicBookLover,
-                            or CoMet style tags, respectively).
--f, --parsefilename         Parse the filename to get some info,
-                            specifically series name, issue number,
-                            volume, and publication year.
-    --split-words           Splits words before parsing the filename.
-                            e.g. 'judgedredd' to 'judge dredd'
--i, --interactive           Interactively query the user when there are
-                            multiple matches for an online search.
-    --nosummary             Suppress the default summary after a save
-                            operation.
--o, --online                Search online and attempt to identify file
-                            using existing metadata and images in archive.
-                            May be used in conjunction with -f and -m.
-    --overwrite             Overwite any existing metadata.
-                            May be used in conjunction with -o, -f and -m.
-    --id=ID                 Use the issue ID when searching online.
-                            Overrides all other metadata.
--m, --metadata=LIST         Explicitly define, as a list, some tags to be
-                            used.  e.g.:
-                            "series=Plastic Man, publisher=Quality Comics"
-                            "series=Kickers^, Inc., issue=1, year=1986"
-                            Name-Value pairs are comma separated. Use a
-                            "^" to escape an "=" or a ",", as shown in
-                            the example above.  Some names that can be
-                            used: series, issue, issueCount, year,
-                            publisher, title
--a, --auto-imprint          Enables the auto imprint functionality.
-                            e.g. if the publisher is set to 'vertigo' it
-                            will be updated to 'DC Comics' and the imprint
-                            property will be set to 'Vertigo'.
--r, --rename                Rename the file based on specified tag style.
-    --noabort               Don't abort save operation when online match
-                            is of low confidence.
--e, --export-to-zip         Export RAR archive to Zip format.
-    --delete-rar            Delete original RAR archive after successful
-                            export to Zip.
-    --abort-on-conflict     Don't export to zip if intended new filename
-                            exists (otherwise, creates a new unique
-                            filename).
--S, --script=FILE           Run an "add-on" python script that uses the
-                            ComicTagger library for custom processing.
-                            Script arguments can follow the script name.
--R, --recursive             Recursively include files in sub-folders.
-    --cv-api-key=KEY        Use the given Comic Vine API Key (persisted
-                            in settings).
-    --only-set-cv-key       Only set the Comic Vine API key and quit.
--w, --wait-on-cv-rate-limit When encountering a Comic Vine rate limit
-                            error, wait and retry query.
--v, --verbose               Be noisy when doing what it does.
-    --terse                 Don't say much (for print mode).
-    --darkmode              Windows only. Force a dark pallet
-    --config=CONFIG_DIR     Config directory defaults to ~/.ComicTagger
-                            on Linux/Mac and %APPDATA% on Windows
-    --version               Display version.
--h, --help                  Display this message.
+def metadata_type(typ: str) -> int:
+    if typ.casefold() not in MetaDataStyle.short:
+        choices = ", ".join(MetaDataStyle.short)
+        raise argparse.ArgumentTypeError(f"invalid choice: {typ} (choose from {choices.upper()})")
+    return MetaDataStyle.short.index(typ)
 
-For more help visit the wiki at: https://github.com/comictagger/comictagger/wiki
-"""
 
-    def __init__(self) -> None:
-        self.data_style: Optional[int] = None
-        self.no_gui = False
-        self.filename: Optional[str] = None
-        self.verbose = False
-        self.terse = False
-        self.metadata = GenericMetadata()
-        self.auto_imprint = False
-        self.print_tags = False
-        self.copy_tags = False
-        self.delete_tags = False
-        self.export_to_zip = False
-        self.abort_export_on_conflict = False
-        self.delete_after_zip_export = False
-        self.search_online = False
-        self.dryrun = False
-        self.abortOnLowConfidence = True
-        self.save_tags = False
-        self.parse_filename = False
-        self.show_save_summary = True
-        self.raw = False
-        self.cv_api_key: Optional[str] = None
-        self.only_set_key = False
-        self.rename_file = False
-        self.no_overwrite = False
-        self.interactive = False
-        self.issue_id: Optional[str] = None
-        self.recursive = False
-        self.run_script = False
-        self.script: Optional[str] = None
-        self.wait_and_retry_on_rate_limit = False
-        self.assume_issue_is_one_if_not_set = False
-        self.file_list: list[str] = []
-        self.darkmode = False
-        self.copy_source: Optional[int] = None
-        self.config_path = ""
-        self.overwrite_metadata = False
-        self.split_words = False
+def parse_metadata_from_string(mdstr: str) -> GenericMetadata:
+    """The metadata string is a comma separated list of name-value pairs
+    The names match the attributes of the internal metadata struct (for now)
+    The caret is the special "escape character", since it's not common in
+    natural language text
 
-    def display_msg_and_quit(self, msg: Optional[str], code: int, show_help: bool = False) -> None:
-        appname = os.path.basename(sys.argv[0])
-        if msg is not None:
-            print(msg)
-        if show_help:
-            print((self.help_text.format(appname)))
+    example = "series=Kickers^, Inc. ,issue=1, year=1986"
+    """
+
+    escaped_comma = "^,"
+    escaped_equals = "^="
+    replacement_token = "<_~_>"
+
+    md = GenericMetadata()
+
+    # First, replace escaped commas with with a unique token (to be changed back later)
+    mdstr = mdstr.replace(escaped_comma, replacement_token)
+    tmp_list = mdstr.split(",")
+    md_list = []
+    for item in tmp_list:
+        item = item.replace(replacement_token, ",")
+        md_list.append(item)
+
+    # Now build a nice dict from the list
+    md_dict = {}
+    for item in md_list:
+        # Make sure to fix any escaped equal signs
+        i = item.replace(escaped_equals, replacement_token)
+        key, value = i.split("=")
+        value = value.replace(replacement_token, "=").strip()
+        key = key.strip()
+        if key.lower() == "credit":
+            cred_attribs = value.split(":")
+            role = cred_attribs[0]
+            person = cred_attribs[1] if len(cred_attribs) > 1 else ""
+            primary = len(cred_attribs) > 2
+            md.add_credit(person.strip(), role.strip(), primary)
         else:
-            print("For more help, run with '--help'")
-        sys.exit(code)
+            md_dict[key] = value
 
-    def parse_metadata_from_string(self, mdstr: str) -> GenericMetadata:
-        """The metadata string is a comma separated list of name-value pairs
-        The names match the attributes of the internal metadata struct (for now)
-        The caret is the special "escape character", since it's not common in
-        natural language text
-
-        example = "series=Kickers^, Inc. ,issue=1, year=1986"
-        """
-
-        escaped_comma = "^,"
-        escaped_equals = "^="
-        replacement_token = "<_~_>"
-
-        md = GenericMetadata()
-
-        # First, replace escaped commas with with a unique token (to be changed back later)
-        mdstr = mdstr.replace(escaped_comma, replacement_token)
-        tmp_list = mdstr.split(",")
-        md_list = []
-        for item in tmp_list:
-            item = item.replace(replacement_token, ",")
-            md_list.append(item)
-
-        # Now build a nice dict from the list
-        md_dict = {}
-        for item in md_list:
-            # Make sure to fix any escaped equal signs
-            i = item.replace(escaped_equals, replacement_token)
-            key, value = i.split("=")
-            value = value.replace(replacement_token, "=").strip()
-            key = key.strip()
-            if key.lower() == "credit":
-                cred_attribs = value.split(":")
-                role = cred_attribs[0]
-                person = cred_attribs[1] if len(cred_attribs) > 1 else ""
-                primary = len(cred_attribs) > 2
-                md.add_credit(person.strip(), role.strip(), primary)
-            else:
-                md_dict[key] = value
-
-        # Map the dict to the metadata object
-        for key, value in md_dict.items():
-            if not hasattr(md, key):
-                logger.warning("'%s' is not a valid tag name", key)
-            else:
-                md.is_empty = False
-                setattr(md, key, value)
-        return md
-
-    def launch_script(self, scriptfile: str) -> None:
-        # we were given a script.  special case for the args:
-        # 1. ignore everything before the -S,
-        # 2. pass all the ones that follow (including script name) to the script
-        script_args = []
-        for idx, arg in enumerate(sys.argv):
-            if arg in ["-S", "--script"]:
-                # found script!
-                script_args = sys.argv[idx + 1 :]
-                break
-        sys.argv = script_args
-        if not os.path.exists(scriptfile):
-            logger.error("Can't find %s", scriptfile)
+    # Map the dict to the metadata object
+    for key, value in md_dict.items():
+        if not hasattr(md, key):
+            raise argparse.ArgumentTypeError(f"'{key}' is not a valid tag name")
         else:
-            # I *think* this makes sense:
-            # assume the base name of the file is the module name
-            # add the folder of the given file to the python path import module
-            dirname = os.path.dirname(scriptfile)
-            module_name = os.path.splitext(os.path.basename(scriptfile))[0]
-            sys.path = [dirname] + sys.path
-            try:
-                script = __import__(module_name)
+            md.is_empty = False
+            setattr(md, key, value)
+    return md
 
-                # Determine if the entry point exists before trying to run it
-                if "main" in dir(script):
-                    script.main()
-                else:
-                    logger.error("Can't find entry point 'main()' in module '%s'", module_name)
-            except Exception:
-                logger.exception("Script: %s raised an unhandled exception: ", module_name)
 
-        sys.exit(0)
-
-    def parse_cmd_line_args(self) -> None:
-
-        if platform.system() == "Darwin" and hasattr(sys, "frozen") and sys.frozen == 1:
-            # remove the PSN (process serial number) argument from OS/X
-            input_args = [a for a in sys.argv[1:] if "-psn_0_" not in a]
-        else:
-            input_args = sys.argv[1:]
-
-        # first check if we're launching a script:
-        for n, _ in enumerate(input_args):
-            if input_args[n] in ["-S", "--script"] and n + 1 < len(input_args):
-                # insert a "--" which will cause getopt to ignore the remaining args
-                # so they will be passed to the script
-                input_args.insert(n + 2, "--")
-                break
-
-        # parse command line options
+def launch_script(scriptfile: str, args: list[str]) -> None:
+    # we were given a script.  special case for the args:
+    # 1. ignore everything before the -S,
+    # 2. pass all the ones that follow (including script name) to the script
+    if not os.path.exists(scriptfile):
+        logger.error("Can't find %s", scriptfile)
+    else:
+        # I *think* this makes sense:
+        # assume the base name of the file is the module name
+        # add the folder of the given file to the python path import module
+        dirname = os.path.dirname(scriptfile)
+        module_name = os.path.splitext(os.path.basename(scriptfile))[0]
+        sys.path = [dirname] + sys.path
         try:
-            opts, args = getopt.getopt(
-                input_args,
-                "hpdt:fm:vownsrc:ieRS:1",
-                [
-                    "help",
-                    "print",
-                    "delete",
-                    "type=",
-                    "copy=",
-                    "parsefilename",
-                    "metadata=",
-                    "verbose",
-                    "online",
-                    "dryrun",
-                    "save",
-                    "rename",
-                    "raw",
-                    "noabort",
-                    "terse",
-                    "nooverwrite",
-                    "interactive",
-                    "nosummary",
-                    "version",
-                    "id=",
-                    "recursive",
-                    "script=",
-                    "export-to-zip",
-                    "delete-rar",
-                    "abort-on-conflict",
-                    "assume-issue-one",
-                    "cv-api-key=",
-                    "only-set-cv-key",
-                    "wait-on-cv-rate-limit",
-                    "darkmode",
-                    "config=",
-                    "overwrite",
-                    "split-words",
-                ],
-            )
+            script = __import__(module_name)
 
-        except getopt.GetoptError as err:
-            self.display_msg_and_quit(str(err), 2)
-
-        # process options
-        for o, a in opts:
-            if o in ("-h", "--help"):
-                self.display_msg_and_quit(None, 0, show_help=True)
-            if o in ("-v", "--verbose"):
-                self.verbose = True
-            if o in ("-S", "--script"):
-                self.run_script = True
-                self.script = a
-            if o in ("-R", "--recursive"):
-                self.recursive = True
-            if o in ("-p", "--print"):
-                self.print_tags = True
-            if o in ("-d", "--delete"):
-                self.delete_tags = True
-            if o in ("-i", "--interactive"):
-                self.interactive = True
-            if o in ("-a", "--auto-imprint"):
-                self.auto_imprint = True
-            if o in ("-c", "--copy"):
-                self.copy_tags = True
-
-                if a.lower() == "cr":
-                    self.copy_source = MetaDataStyle.CIX
-                elif a.lower() == "cbl":
-                    self.copy_source = MetaDataStyle.CBI
-                elif a.lower() == "comet":
-                    self.copy_source = MetaDataStyle.COMET
-                else:
-                    self.display_msg_and_quit("Invalid copy tag source type", 1)
-            if o in ("-o", "--online"):
-                self.search_online = True
-            if o == "--overwrite":
-                self.overwrite_metadata = True
-            if o in ("-n", "--dryrun"):
-                self.dryrun = True
-            if o in ("-m", "--metadata"):
-                self.metadata = self.parse_metadata_from_string(a)
-            if o in ("-s", "--save"):
-                self.save_tags = True
-            if o in ("-r", "--rename"):
-                self.rename_file = True
-            if o in ("-e", "--export_to_zip"):
-                self.export_to_zip = True
-            if o == "--delete-rar":
-                self.delete_after_zip_export = True
-            if o == "--abort-on-conflict":
-                self.abort_export_on_conflict = True
-            if o in ("-f", "--parsefilename"):
-                self.parse_filename = True
-            if o == "--split-words":
-                self.split_words = True
-            if o in ("-w", "--wait-on-cv-rate-limit"):
-                self.wait_and_retry_on_rate_limit = True
-            if o == "--config":
-                self.config_path = os.path.abspath(a)
-            if o == "--id":
-                self.issue_id = a
-            if o == "--raw":
-                self.raw = True
-            if o == "--noabort":
-                self.abortOnLowConfidence = False
-            if o == "--terse":
-                self.terse = True
-            if o == "--nosummary":
-                self.show_save_summary = False
-            if o in ("-1", "--assume-issue-one"):
-                self.assume_issue_is_one_if_not_set = True
-            if o == "--nooverwrite":
-                self.no_overwrite = True
-            if o == "--cv-api-key":
-                self.cv_api_key = a
-            if o == "--only-set-cv-key":
-                self.only_set_key = True
-            if o == "--version":
-                print(f"ComicTagger {ctversion.version}:  Copyright (c) 2012-2022 ComicTagger Team")
-                print("Distributed under Apache License 2.0 (http://www.apache.org/licenses/LICENSE-2.0)")
-                sys.exit(0)
-            if o in ("-t", "--type"):
-                if a.lower() == "cr":
-                    self.data_style = MetaDataStyle.CIX
-                elif a.lower() == "cbl":
-                    self.data_style = MetaDataStyle.CBI
-                elif a.lower() == "comet":
-                    self.data_style = MetaDataStyle.COMET
-                else:
-                    self.display_msg_and_quit("Invalid tag type", 1)
-            if o == "--darkmode":
-                self.darkmode = True
-
-        if any(
-            [
-                self.print_tags,
-                self.delete_tags,
-                self.save_tags,
-                self.copy_tags,
-                self.rename_file,
-                self.export_to_zip,
-                self.only_set_key,
-            ]
-        ):
-            self.no_gui = True
-
-        count = 0
-        if self.run_script:
-            count += 1
-        if self.print_tags:
-            count += 1
-        if self.delete_tags:
-            count += 1
-        if self.save_tags:
-            count += 1
-        if self.copy_tags:
-            count += 1
-        if self.rename_file:
-            count += 1
-        if self.export_to_zip:
-            count += 1
-        if self.only_set_key:
-            count += 1
-
-        if count > 1:
-            self.display_msg_and_quit(
-                "Must choose only one action of print, delete, save, copy, rename, export, set key, or run script", 1
-            )
-
-        if self.script is not None:
-            self.launch_script(self.script)
-
-        if len(args) > 0:
-            if platform.system() == "Windows":
-                # no globbing on windows shell, so do it for them
-                import glob
-
-                self.file_list = []
-                for item in args:
-                    self.file_list.extend(glob.glob(item))
-                if len(self.file_list) > 0:
-                    self.filename = self.file_list[0]
+            # Determine if the entry point exists before trying to run it
+            if "main" in dir(script):
+                script.main(args)
             else:
-                self.filename = args[0]
-                self.file_list = args
+                logger.error("Can't find entry point 'main()' in module '%s'", module_name)
+        except Exception:
+            logger.exception("Script: %s raised an unhandled exception: ", module_name)
 
-        if self.only_set_key and self.cv_api_key is None:
-            self.display_msg_and_quit("Key not given!", 1)
+    sys.exit(0)
 
-        if not self.only_set_key and self.no_gui and self.filename is None:
-            self.display_msg_and_quit("Command requires at least one filename!", 1)
 
-        if self.delete_tags and self.data_style is None:
-            self.display_msg_and_quit("Please specify the type to delete with -t", 1)
+def parse_cmd_line() -> argparse.Namespace:
 
-        if self.save_tags and self.data_style is None:
-            self.display_msg_and_quit("Please specify the type to save with -t", 1)
+    if platform.system() == "Darwin" and hasattr(sys, "frozen") and sys.frozen == 1:
+        # remove the PSN (process serial number) argument from OS/X
+        input_args = [a for a in sys.argv[1:] if "-psn_0_" not in a]
+    else:
+        input_args = sys.argv[1:]
 
-        if self.copy_tags and self.data_style is None:
-            self.display_msg_and_quit("Please specify the type to copy to with -t", 1)
+    script_args = []
 
-        if self.recursive:
-            self.file_list = utils.get_recursive_filelist(self.file_list)
+    # first check if we're launching a script and split off script args
+    for n, _ in enumerate(input_args):
+        if input_args[n] == "--":
+            break
+
+        if input_args[n] in ["-S", "--script"] and n + 1 < len(input_args):
+            # insert a "--" which will cause getopt to ignore the remaining args
+            # so they will be passed to the script
+            script_args = input_args[n + 2 :]
+            input_args = input_args[: n + 2]
+            break
+
+    parser = define_args()
+    opts = parser.parse_args(input_args)
+
+    if opts.config_path:
+        opts.config_path = os.path.abspath(opts.config_path)
+    if opts.version:
+        parser.exit(
+            status=1,
+            message=f"ComicTagger {ctversion.version}:  Copyright (c) 2012-2022 ComicTagger Team\n"
+            "Distributed under Apache License 2.0 (http://www.apache.org/licenses/LICENSE-2.0)\n",
+        )
+
+    opts.no_gui = any(
+        [
+            opts.print,
+            opts.delete,
+            opts.save,
+            opts.copy,
+            opts.rename,
+            opts.export_to_zip,
+            opts.only_set_cv_key,
+        ]
+    )
+
+    if opts.script is not None:
+        launch_script(opts.script, script_args)
+
+    if platform.system() == "Windows" and opts.glob:
+        # no globbing on windows shell, so do it for them
+        import glob
+
+        globs = opts.files
+        opts.files = []
+        for item in globs:
+            opts.files.extend(glob.glob(item))
+
+    if opts.only_set_cv_key and opts.cv_api_key is None:
+        parser.exit(message="Key not given!", status=1)
+
+    if not opts.only_set_cv_key and opts.no_gui and not opts.files:
+        parser.exit(message="Command requires at least one filename!\n", status=1)
+
+    if opts.delete and opts.type is None:
+        parser.exit(message="Please specify the type to delete with -t\n", status=1)
+
+    if opts.save and opts.type is None:
+        parser.exit(message="Please specify the type to save with -t\n", status=1)
+
+    if opts.copy and opts.type is None:
+        parser.exit(message="Please specify the type to copy to with -t\n", status=1)
+
+    if opts.recursive:
+        opts.file_list = utils.get_recursive_filelist(opts.file_list)
+
+    return opts

comictaggerlib/resulttypes.py

@@ -38,7 +38,7 @@ class OnlineMatchResults:
 class MultipleMatch:
     def __init__(self, ca: ComicArchive, match_list: List[IssueResult]) -> None:
         self.ca: ComicArchive = ca
-        self.matches = match_list
+        self.matches: list[IssueResult] = match_list
 
 
 class SelectDetails(TypedDict):

comictaggerlib/taggerwindow.py

@@ -49,7 +49,6 @@ from comictaggerlib.fileselectionlist import FileInfo, FileSelectionList
 from comictaggerlib.issueidentifier import IssueIdentifier
 from comictaggerlib.logwindow import LogWindow
 from comictaggerlib.optionalmsgdialog import OptionalMessageDialog
-from comictaggerlib.options import Options
 from comictaggerlib.pagebrowser import PageBrowserWindow
 from comictaggerlib.pagelisteditor import PageListEditor
 from comictaggerlib.renamewindow import RenameWindow
@@ -76,13 +75,15 @@ class TaggerWindow(QtWidgets.QMainWindow):
         file_list: list[str],
         settings: ComicTaggerSettings,
         parent: Optional[QtWidgets.QWidget] = None,
-        opts: Optional[Options] = None,
+        opts = None,
     ) -> None:
         super().__init__(parent)
 
         uic.loadUi(ComicTaggerSettings.get_ui_file("taggerwindow.ui"), self)
         self.settings = settings
 
+        self.window_ref = {}
+
         # prevent multiple instances
         socket = QtNetwork.QLocalSocket(self)
         socket.connectToServer(settings.install_id)
@@ -148,10 +149,10 @@ class TaggerWindow(QtWidgets.QMainWindow):
 
         self.setWindowIcon(QtGui.QIcon(ComicTaggerSettings.get_graphic("app.png")))
         # TODO: this needs to be looked at
-        if opts is not None and opts.data_style is not None:
+        if opts is not None and opts.type is not None:
             # respect the command line option tag type
-            settings.last_selected_save_data_style = opts.data_style
-            settings.last_selected_load_data_style = opts.data_style
+            settings.last_selected_save_data_style = opts.type
+            settings.last_selected_load_data_style = opts.type
 
         self.save_data_style = settings.last_selected_save_data_style
         self.load_data_style = settings.last_selected_load_data_style
@@ -387,6 +388,8 @@ Have fun!
         self.actionPageBrowser.setStatusTip("Show the page browser")
         self.actionPageBrowser.triggered.connect(self.show_page_browser)
 
+        self.actionFind_Duplicate_Comics.triggered.connect(self.find_dupes)
+
         # Help Menu
         self.actionAbout.setStatusTip("Show the " + self.appName + " info")
         self.actionAbout.triggered.connect(self.about_app)
@@ -420,8 +423,20 @@ Have fun!
         self.toolBar.addAction(self.actionPageBrowser)
         self.toolBar.addAction(self.actionAutoImprint)
 
+    def find_dupes(self):
+        import comictaggerscripts.find_dupes
+        window = comictaggerscripts.find_dupes.main((str(x.path.absolute()) for x in self.fileSelectionList.get_archive_list(True)), self.settings)
+        window.closed.connect(self.finish_dupes)
+        window.show()
+        self.window_ref['comictaggerscripts.find_dupes'] = window
+
+    def finish_dupes(self, files: list[str]):
+        self.fileSelectionList.remove_paths(files)
+        if 'comictaggerscripts.find_dupes' in self.window_ref:
+            del self.window_ref['comictaggerscripts.find_dupes']
+
     def repackage_archive(self) -> None:
-        ca_list = self.fileSelectionList.get_selected_archive_list()
+        ca_list = self.fileSelectionList.get_archive_list()
         rar_count = 0
         for ca in ca_list:
             if ca.is_rar():
@@ -1485,7 +1500,7 @@ Please choose options below, and select OK.
 
     def remove_tags(self, style: int) -> None:
         # remove the indicated tags from the archive
-        ca_list = self.fileSelectionList.get_selected_archive_list()
+        ca_list = self.fileSelectionList.get_archive_list()
         has_md_count = 0
         for ca in ca_list:
             if ca.has_metadata(style):
@@ -1560,7 +1575,7 @@ Please choose options below, and select OK.
 
     def copy_tags(self) -> None:
         # copy the indicated tags in the archive
-        ca_list = self.fileSelectionList.get_selected_archive_list()
+        ca_list = self.fileSelectionList.get_archive_list()
         has_src_count = 0
 
         src_style = self.load_data_style
@@ -1787,7 +1802,7 @@ Please choose options below, and select OK.
         return success, match_results
 
     def auto_tag(self) -> None:
-        ca_list = self.fileSelectionList.get_selected_archive_list()
+        ca_list = self.fileSelectionList.get_archive_list()
         style = self.save_data_style
 
         if len(ca_list) == 0:
@@ -2011,7 +2026,7 @@ Please choose options below, and select OK to Auto-Tag.
         QtWidgets.QApplication.restoreOverrideCursor()
 
     def rename_archive(self) -> None:
-        ca_list = self.fileSelectionList.get_selected_archive_list()
+        ca_list = self.fileSelectionList.get_archive_list()
 
         if len(ca_list) == 0:
             QtWidgets.QMessageBox.information(self, "Rename", "No archives selected!")
@@ -2134,7 +2149,7 @@ Please choose options below, and select OK to Auto-Tag.
             self.setWindowFlags(flags)
             self.show()
 
-    def auto_imprint(self):
+    def auto_imprint(self) -> None:
         self.form_to_metadata()
         self.metadata.fix_publisher()
         self.metadata_to_form()

comictaggerlib/ui/taggerwindow.ui

@@ -1182,7 +1182,7 @@
      <x>0</x>
      <y>0</y>
      <width>1096</width>
-     <height>21</height>
+     <height>30</height>
     </rect>
    </property>
    <widget class="QMenu" name="menuComicTagger">
@@ -1245,6 +1245,7 @@
      <string>Window</string>
     </property>
     <addaction name="actionPageBrowser"/>
+    <addaction name="actionFind_Duplicate_Comics"/>
    </widget>
    <addaction name="menuComicTagger"/>
    <addaction name="menuTags"/>
@@ -1455,6 +1456,11 @@
     <string>Parse Filename and split words</string>
    </property>
   </action>
+  <action name="actionFind_Duplicate_Comics">
+   <property name="text">
+    <string>Find Duplicate Comics</string>
+   </property>
+  </action>
  </widget>
  <layoutdefault spacing="6" margin="11"/>
  <resources/>

comictaggerscripts/dupe.ui

@@ -0,0 +1,158 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<ui version="4.0">
+ <class>Form</class>
+ <widget class="QWidget" name="Form">
+  <property name="geometry">
+   <rect>
+    <x>0</x>
+    <y>0</y>
+    <width>729</width>
+    <height>406</height>
+   </rect>
+  </property>
+  <property name="windowTitle">
+   <string>Form</string>
+  </property>
+  <layout class="QHBoxLayout" name="horizontalLayout">
+   <property name="sizeConstraint">
+    <enum>QLayout::SetMinAndMaxSize</enum>
+   </property>
+   <item>
+    <widget class="QListWidget" name="dupeList">
+     <property name="sizePolicy">
+      <sizepolicy hsizetype="Minimum" vsizetype="Minimum">
+       <horstretch>0</horstretch>
+       <verstretch>0</verstretch>
+      </sizepolicy>
+     </property>
+     <property name="selectionMode">
+      <enum>QAbstractItemView::ExtendedSelection</enum>
+     </property>
+     <property name="selectionBehavior">
+      <enum>QAbstractItemView::SelectRows</enum>
+     </property>
+    </widget>
+   </item>
+   <item>
+    <widget class="QSplitter" name="splitter">
+     <property name="enabled">
+      <bool>true</bool>
+     </property>
+     <property name="orientation">
+      <enum>Qt::Horizontal</enum>
+     </property>
+     <property name="childrenCollapsible">
+      <bool>false</bool>
+     </property>
+     <widget class="QTableWidget" name="pageList">
+      <property name="sizePolicy">
+       <sizepolicy hsizetype="Preferred" vsizetype="Expanding">
+        <horstretch>0</horstretch>
+        <verstretch>0</verstretch>
+       </sizepolicy>
+      </property>
+      <property name="editTriggers">
+       <set>QAbstractItemView::NoEditTriggers</set>
+      </property>
+      <property name="showDropIndicator" stdset="0">
+       <bool>false</bool>
+      </property>
+      <property name="selectionMode">
+       <enum>QAbstractItemView::SingleSelection</enum>
+      </property>
+      <property name="selectionBehavior">
+       <enum>QAbstractItemView::SelectRows</enum>
+      </property>
+      <property name="sortingEnabled">
+       <bool>true</bool>
+      </property>
+      <property name="columnCount">
+       <number>3</number>
+      </property>
+      <column>
+       <property name="text">
+        <string>name</string>
+       </property>
+      </column>
+      <column>
+       <property name="text">
+        <string>score</string>
+       </property>
+      </column>
+      <column>
+       <property name="text">
+        <string>dupe name</string>
+       </property>
+      </column>
+     </widget>
+     <widget class="QFrame" name="comicData">
+      <property name="frameShape">
+       <enum>QFrame::StyledPanel</enum>
+      </property>
+      <property name="frameShadow">
+       <enum>QFrame::Raised</enum>
+      </property>
+      <layout class="QHBoxLayout" name="horizontalLayout_2">
+       <item>
+        <widget class="QFrame" name="comic1Data">
+         <property name="frameShape">
+          <enum>QFrame::StyledPanel</enum>
+         </property>
+         <property name="frameShadow">
+          <enum>QFrame::Raised</enum>
+         </property>
+         <layout class="QVBoxLayout" name="verticalLayout" stretch="0,0">
+          <item>
+           <widget class="QWidget" name="comic1Image" native="true">
+            <layout class="QVBoxLayout" name="verticalLayout_3"/>
+           </widget>
+          </item>
+          <item>
+           <widget class="QPushButton" name="comic1Delete">
+            <property name="toolTip">
+             <string>Delete Comic 1</string>
+            </property>
+            <property name="text">
+             <string>Delete</string>
+            </property>
+           </widget>
+          </item>
+         </layout>
+        </widget>
+       </item>
+       <item>
+        <widget class="QFrame" name="comic2Data">
+         <property name="frameShape">
+          <enum>QFrame::StyledPanel</enum>
+         </property>
+         <property name="frameShadow">
+          <enum>QFrame::Raised</enum>
+         </property>
+         <layout class="QVBoxLayout" name="verticalLayout_2">
+          <item>
+           <widget class="QWidget" name="comic2Image" native="true">
+            <layout class="QVBoxLayout" name="verticalLayout_4"/>
+           </widget>
+          </item>
+          <item>
+           <widget class="QPushButton" name="comic2Delete">
+            <property name="toolTip">
+             <string>Delete Comic 2</string>
+            </property>
+            <property name="text">
+             <string>Delete</string>
+            </property>
+           </widget>
+          </item>
+         </layout>
+        </widget>
+       </item>
+      </layout>
+     </widget>
+    </widget>
+   </item>
+  </layout>
+ </widget>
+ <resources/>
+ <connections/>
+</ui>

comictaggerscripts/find_dupes.py

@@ -0,0 +1,755 @@
+#!/usr/bin/python3
+"""Find all duplicate comics"""
+
+import argparse
+import hashlib
+import os
+import shutil
+import signal
+import sys
+import tempfile
+import typing
+from operator import itemgetter
+from pathlib import Path
+from typing import Optional
+
+import filetype
+from PyQt5 import QtCore, QtGui, QtWidgets, uic
+
+from comicapi import utils
+from comicapi.comicarchive import ComicArchive, MetaDataStyle
+from comicapi.genericmetadata import GenericMetadata
+from comictaggerlib.filerenamer import FileRenamer
+from comictaggerlib.imagehasher import ImageHasher
+from comictaggerlib.settings import ComicTaggerSettings
+from comictaggerlib.ui.qtutils import center_window_on_parent
+
+root = 1 << 31 - 1
+something = 1 << 31 - 1
+
+
+class ImageMeta:
+    def __init__(self, name, file_hash, image_hash, image_type, score=-1, score_file_hash=""):
+        self.name = name
+        self.file_hash = file_hash
+        self.image_hash = image_hash
+        self.type = image_type
+        self.score = score
+        self.score_file_hash = score_file_hash
+
+
+class Duplicate:
+    """docstring for Duplicate"""
+
+    imageHashes: dict[str, ImageMeta]
+
+    def __init__(self, path, metadata: GenericMetadata, ca: ComicArchive, cover):
+        self.path = path
+        self.digest = ""
+        self.ca: ComicArchive = ca
+        self.metadata = metadata
+        self.imageHashes = {}
+        self.duplicateImages = set()
+        self.extras = set()
+        self.extractedPath = ""
+        self.deletable = False
+        self.keeping = False
+        self.fileCount = 0  # Excluding comicinfo.xml
+        self.imageCount = 0
+        self.cover = cover
+        blake2b = hashlib.blake2b(digest_size=16)
+
+        with open(self.path, "rb") as f:
+            for line in f:
+                blake2b.update(line)
+
+        self.digest = blake2b.hexdigest()
+
+    def extract(self, directory):
+        if self.ca.seems_to_be_a_comic_archive():
+            self.extractedPath = directory
+            for filepath in self.ca.archiver.get_filename_list():
+                filename = os.path.basename(filepath)
+                if filename.lower() in ["comicinfo.xml"]:
+                    continue
+
+                self.fileCount += 1
+                archived_file = self.ca.archiver.read_file(filepath)
+
+                image_type = filetype.image_match(archived_file)
+                if image_type is not None:
+                    self.imageCount += 1
+                    file_hash = hashlib.blake2b(archived_file, digest_size=16).hexdigest().upper()
+                    if file_hash in self.imageHashes:
+                        self.duplicateImages.add(filename)
+                    else:
+                        image_hash = ImageHasher(data=archived_file, width=12, height=12).average_hash()
+                        self.imageHashes[file_hash] = ImageMeta(
+                            os.path.join(self.extractedPath, filename), file_hash, image_hash, image_type.extension
+                        )
+                else:
+                    self.extras.add(filename)
+
+                os.makedirs(self.extractedPath, 0o777, True)
+
+                unarchived_file = Path(os.path.join(self.extractedPath, filename))
+                unarchived_file.write_bytes(archived_file)
+
+    def clean(self):
+        shutil.rmtree(self.extractedPath, ignore_errors=True)
+
+    def delete(self):
+        if not self.keeping:
+            self.clean()
+            try:
+                os.remove(self.path)
+            except Exception:
+                pass
+        return not (os.path.exists(self.path) or os.path.exists(self.extractedPath))
+
+
+class Tree(QtCore.QAbstractListModel):
+    def __init__(self, item: list[list[Duplicate]]):
+        super().__init__()
+        self.rootItem = item
+
+    def rowCount(self, index: QtCore.QModelIndex = ...) -> int:
+        if not index.isValid():
+            return len(self.rootItem)
+
+        return 0
+
+    def columnCount(self, index: QtCore.QModelIndex = ...) -> int:
+        if index.isValid():
+            return 1
+
+        return 0
+
+    def data(self, index: QtCore.QModelIndex, role: int = ...) -> typing.Any:
+        if not index.isValid():
+            return QtCore.QVariant()
+
+        f = FileRenamer(self.rootItem[index.row()][0].metadata)
+        f.set_template("{series} #{issue} - {title} ({year})")
+        if role in [QtCore.Qt.DisplayRole, QtCore.Qt.UserRole]:
+            return f.determine_name("")
+        return QtCore.QVariant()
+
+
+class MainWindow(QtWidgets.QMainWindow):
+    closed = QtCore.pyqtSignal(list)
+
+    def __init__(self, file_list, style, work_path, settings, parent=None):
+        super().__init__(parent)
+        uic.loadUi(ComicTaggerSettings.get_ui_file("../../comictaggerscripts/mainwindow.ui"), self)
+        self.dupes = []
+        self.removed: list[str] = []
+        self.firstRun = 0
+        self.dupe_set_list: list[list[Duplicate]] = []
+        self.style = style
+        if work_path == "":
+            self.work_path = tempfile.mkdtemp()
+        else:
+            self.work_path = work_path
+        self.initFiles = file_list
+        self.settings = settings
+        self.dupe_set_qlist.clicked.connect(self.dupe_set_clicked)
+        self.dupe_set_qlist.doubleClicked.connect(self.dupe_set_double_clicked)
+        self.actionCompare_Comic.triggered.connect(self.compare_action)
+
+    def __del__(self):
+        print("fuck this")
+        shutil.rmtree(self.work_path, True)
+
+    def closeEvent(self, event: QtGui.QCloseEvent):
+        self.closed.emit(self.removed)
+        event.accept()
+
+    def comic_deleted(self, archive_path: str):
+        self.removed.append(archive_path)
+
+    def update_dupes(self):
+        # print("updating duplicates")
+        new_set_list = []
+        for dupe in self.dupe_set_list:
+            dupe_list = []
+            for d in dupe:
+                QtCore.QCoreApplication.processEvents()
+                if os.path.exists(d.path):
+                    dupe_list.append(d)
+                else:
+                    d.clean()
+
+            if len(dupe_list) > 1:
+                new_set_list.append(dupe_list)
+            else:
+                dupe_list[0].clean()
+        self.dupe_set_list: list[list[Duplicate]] = new_set_list
+        self.dupe_set_qlist.setModel(Tree(self.dupe_set_list))
+        if new_set_list:
+            self.dupe_set_qlist.setSelection(QtCore.QRect(0, 0, 0, 1), QtCore.QItemSelectionModel.ClearAndSelect)
+
+            self.dupe_set_clicked(self.dupe_set_qlist.model().index(0, 0))
+        else:
+            self.clear_dupe_list()
+
+    def compare(self, i):
+        if len(self.dupe_set_list) > i:
+            dw = DupeWindow(self.dupe_set_list[i], self.work_path, self)
+            dw.closed.connect(self.update_dupes)
+            dw.comic_deleted.connect(self.comic_deleted)
+            dw.show()
+
+    def compare_action(self, b):
+        selection = self.dupe_set_qlist.selectedIndexes()
+        if len(selection) > 0:
+            self.compare(selection[0].row())
+
+    def dupe_set_double_clicked(self, index: QtCore.QModelIndex):
+        self.compare(index.row())
+
+    def clear_dupe_list(self):
+        for f in self.dupe_list.children():
+            if isinstance(f, DupeImage):
+                f.deleteLater()
+
+    def dupe_set_clicked(self, index: QtCore.QModelIndex):
+        self.clear_dupe_list()
+        if self.dupe_set_list:
+            self.dupe_set_list[index.row()].sort(key=lambda k: k.digest)
+            for i, f in enumerate(self.dupe_set_list[index.row()]):
+                color = "black"
+                if i > 0:
+                    if self.dupe_set_list[index.row()][i - 1].digest == f.digest:
+                        color = "green"
+                elif i == 0:
+                    if len(self.dupe_set_list[index.row()]) > 1:
+                        if self.dupe_set_list[index.row()][i + 1].digest == f.digest:
+                            color = "green"
+                ql = DupeImage(
+                    duplicate=f, style=f".path {{color: black;}}.hash {{color: {color};}}", parent=self.dupe_list
+                )
+                ql.deleted.connect(self.update_dupes)
+                ql.deleted.connect(self.comic_deleted)
+                ql.setMinimumWidth(300)
+                ql.setMinimumHeight(500)
+                print(self.dupe_list.layout())
+
+                layout = self.dupe_list.layout()
+                layout.addWidget(ql)
+
+    def showEvent(self, event: QtGui.QShowEvent):
+        if self.firstRun == 0:
+            self.firstRun = 1
+
+            self.load_files(self.initFiles)
+        if len(self.dupe_set_list) < 1:
+            dialog = QtWidgets.QMessageBox(
+                QtWidgets.QMessageBox.NoIcon,
+                "ComicTagger Duplicate finder",
+                "No duplicate comics found",
+                QtWidgets.QMessageBox.Ok,
+                parent=self,
+            )
+            dialog.setWindowModality(QtCore.Qt.ApplicationModal)
+            qw = QtWidgets.QWidget()
+            qw.setFixedWidth(90)
+            dialog.layout().addWidget(qw, 3, 2, 1, 3)
+            dialog.exec()
+            QtCore.QTimer.singleShot(1, self.close)
+            self.close()
+        self.dupe_set_qlist.setSelection(QtCore.QRect(0, 0, 0, 1), QtCore.QItemSelectionModel.ClearAndSelect)
+        self.dupe_set_clicked(self.dupe_set_qlist.model().index(0, 0))
+
+    def load_files(self, file_list):
+        # Progress dialog on Linux flakes out for small range, so scale up
+        dialog = QtWidgets.QProgressDialog("", "Cancel", 0, len(file_list), parent=self)
+        dialog.setWindowTitle("Reading Comics")
+        dialog.setWindowModality(QtCore.Qt.ApplicationModal)
+        dialog.setMinimumDuration(300)
+        dialog.setMinimumWidth(400)
+        center_window_on_parent(dialog)
+
+        comic_list = []
+        max_name_len = 2
+        for filename in file_list:
+            QtCore.QCoreApplication.processEvents()
+            if dialog.wasCanceled():
+                break
+            dialog.setValue(dialog.value() + 1)
+            dialog.setLabelText(filename)
+            ca = ComicArchive(
+                path=filename,
+                rar_exe_path=self.settings.rar_exe_path,
+                default_image_path=ComicTaggerSettings.get_graphic("nocover.png"),
+            )
+            if ca.seems_to_be_a_comic_archive() and ca.has_metadata(self.style):
+                # fmt_str = "{{0:{0}}}".format(max_name_len)
+                # print(fmt_str.format(filename) + "\r", end='', file=sys.stderr)
+                # sys.stderr.flush()
+                md = ca.read_metadata(self.style)
+                cover = ca.get_page(0)
+                comic_list.append((make_key(md), filename, ca, md, cover))
+                # max_name_len = len(filename)
+
+        comic_list.sort(key=itemgetter(0), reverse=False)
+
+        # look for duplicate blocks
+        dupe_set = []
+        prev_key = ""
+
+        dialog.setWindowTitle("Finding Duplicates")
+        dialog.setMaximum(len(comic_list))
+        dialog.setValue(dialog.minimum())
+
+        set_list = []
+        for new_key, filename, ca, md, cover in comic_list:
+            dialog.setValue(dialog.value() + 1)
+            QtCore.QCoreApplication.processEvents()
+            if dialog.wasCanceled():
+                break
+            dialog.setLabelText(filename)
+
+            # if the new key same as the last, add to to dupe set
+            if new_key == prev_key:
+                dupe_set.append((filename, ca, md, cover))
+            # else we're on a new potential block
+            else:
+                # only add if the dupe list has 2 or more
+                if len(dupe_set) > 1:
+                    set_list.append(dupe_set)
+                dupe_set = []
+                dupe_set.append((filename, ca, md, cover))
+
+            prev_key = new_key
+
+        # Final dupe_set
+        if len(dupe_set) > 1:
+            set_list.append(dupe_set)
+
+        for d_set in set_list:
+            new_set = []
+            for filename, ca, md, cover in d_set:
+                new_set.append(Duplicate(filename, md, ca, cover))
+            self.dupe_set_list.append(new_set)
+
+        self.dupe_set_qlist.setModel(Tree(self.dupe_set_list))
+        # print()
+        dialog.close()
+
+    # def delete_hashes(self):
+    #     working_dir = os.path.join(self.tmp, "working")
+    #     s = False
+    #     # while working and len(dupe_set) > 1:
+    #     remaining = []
+    #     for dupe_set in self.dupe_set_list:
+    #         not_deleted = True
+    #         if os.path.exists(working_dir):
+    #             shutil.rmtree(working_dir, ignore_errors=True)
+    #
+    #         os.mkdir(working_dir)
+    #         extract(dupe_set, working_dir)
+    #         if mark_hashes(dupe_set):
+    #             if s:  # Auto delete if s flag or if there are not any non image extras
+    #                 dupe_set.sort(key=attrgetter("fileCount"))
+    #                 dupe_set.sort(key=lambda x: len(x.duplicateImages))
+    #                 dupe_set[0].keeping = True
+    #             else:
+    #                 dupe_set[select_archive("Select archive to keep: ", dupe_set)].keeping = True
+    #         else:
+    #             # app.exec_()
+    #             compare_dupe(dupe_set[0], dupe_set[1])
+    #         for i, dupe in enumerate(dupe_set):
+    #             print("{0}. {1}: {2.series} #{2.issue:0>3} {2.year}; extras: {3}; deletable: {4}".format(
+    #                 i,
+    #                 dupe.path,
+    #                 dupe.metadata,
+    #                 ", ".join(sorted(dupe.extras)), dupe.deletable))
+    #         dupe_set = delete(dupe_set)
+    #         if not_deleted:
+    #             remaining.append(dupe_set)
+    #     self.dupe_set_list = remaining
+
+
+class DupeWindow(QtWidgets.QWidget):
+    closed = QtCore.pyqtSignal()
+    comic_deleted = QtCore.pyqtSignal(str)
+
+    def __init__(self, duplicates: list[Duplicate], tmp, parent=None):
+        super().__init__(parent, QtCore.Qt.Window)
+        uic.loadUi(ComicTaggerSettings.get_ui_file("../../comictaggerscripts/dupe.ui"), self)
+
+        for f in self.comic1Image.children():
+            f.deleteLater()
+        for f in self.comic2Image.children():
+            f.deleteLater()
+        self.deleting = -1
+        self.duplicates: list[Duplicate] = duplicates
+        self.dupe1 = -1
+        self.dupe2 = -1
+
+        self.tmp = tmp
+
+        self.setWindowTitle("ComicTagger Duplicate compare")
+
+        self.pageList.currentItemChanged.connect(self.current_item_changed)
+        self.comic1Delete.clicked.connect(self.delete_1)
+        self.comic2Delete.clicked.connect(self.delete_2)
+        self.dupeList.itemSelectionChanged.connect(self.show_dupe_list)
+        # self.dupeList = QtWidgets.QListWidget()
+        self.dupeList.setIconSize(QtCore.QSize(100, 50))
+
+        while self.pageList.rowCount() > 0:
+            self.pageList.removeRow(0)
+
+        self.pageList.setSortingEnabled(False)
+
+        if len(duplicates) < 2:
+            return
+        extract(duplicates, tmp)
+
+        tmp1 = DupeImage(self.duplicates[0])
+        tmp2 = DupeImage(self.duplicates[1])
+        self.comic1Data.layout().replaceWidget(self.comic1Image, tmp1)
+        self.comic2Data.layout().replaceWidget(self.comic2Image, tmp2)
+        self.comic1Image = tmp1
+        self.comic2Image = tmp2
+        self.comic1Image.deleted.connect(self.update_dupes)
+        self.comic2Image.deleted.connect(self.update_dupes)
+
+    def showEvent(self, event: QtGui.QShowEvent) -> None:
+        self.update_dupes()
+
+    def closeEvent(self, event: QtGui.QCloseEvent) -> None:
+        self.closed.emit()
+        event.accept()
+
+    def show_dupe_list(self):
+        dupes = self.dupeList.selectedItems()
+        if len(dupes) != 2:
+            return
+        self.dupe1 = int(dupes[0].data(QtCore.Qt.UserRole))
+        self.dupe2 = int(dupes[1].data(QtCore.Qt.UserRole))
+        if len(self.duplicates[self.dupe2].imageHashes) > len(self.duplicates[self.dupe1].imageHashes):
+            self.dupe1, self.dupe2 = self.dupe2, self.dupe1
+        compare_dupe(self.duplicates[self.dupe1].imageHashes, self.duplicates[self.dupe2].imageHashes)
+        self.display_dupe()
+
+    def update_dupes(self):
+        dupes: list[Duplicate] = []
+        for f in self.duplicates:
+            if os.path.exists(f.path):
+                dupes.append(f)
+            else:
+                f.clean()
+        self.duplicates = dupes
+        if len(self.duplicates) < 2:
+            self.close()
+        self.dupeList.clear()
+
+        for i, dupe in enumerate(self.duplicates):
+            item = QtWidgets.QListWidgetItem()
+            item.setText(dupe.path)
+            item.setToolTip(dupe.path)
+            pm = QtGui.QPixmap()
+            pm.loadFromData(dupe.cover)
+            item.setIcon(QtGui.QIcon(pm))
+            item.setData(QtCore.Qt.UserRole, i)
+            self.dupeList.addItem(item)
+        self.dupeList.setCurrentRow(0)
+        self.dupeList.setCurrentRow(1, QtCore.QItemSelectionModel.Select)
+
+    def delete_1(self):
+        self.duplicates[self.dupe1].delete()
+        self.comic_deleted.emit(self.duplicates[self.dupe1].path)
+        self.update_dupes()
+
+    def delete_2(self):
+        self.duplicates[self.dupe2].delete()
+        self.comic_deleted.emit(self.duplicates[self.dupe2].path)
+        self.update_dupes()
+
+    def display_dupe(self):
+        for _ in range(self.pageList.rowCount()):
+            self.pageList.removeRow(0)
+        for h in self.duplicates[self.dupe1].imageHashes.values():
+            row = self.pageList.rowCount()
+            self.pageList.insertRow(row)
+            name = QtWidgets.QTableWidgetItem()
+            score = QtWidgets.QTableWidgetItem()
+            dupe_name = QtWidgets.QTableWidgetItem()
+
+            item_text = os.path.basename(h.name)
+            name.setFlags(QtCore.Qt.ItemIsSelectable | QtCore.Qt.ItemIsEnabled)
+            name.setText(item_text)
+            name.setData(QtCore.Qt.UserRole, h.file_hash)
+            name.setData(QtCore.Qt.ToolTipRole, item_text)
+            self.pageList.setItem(row, 0, name)
+
+            item_text = str(h.score)
+            score.setFlags(QtCore.Qt.ItemIsSelectable | QtCore.Qt.ItemIsEnabled)
+            score.setText(item_text)
+            score.setData(QtCore.Qt.UserRole, h.file_hash)
+            score.setData(QtCore.Qt.ToolTipRole, item_text)
+            self.pageList.setItem(row, 1, score)
+
+            item_text = os.path.basename(self.duplicates[self.dupe2].imageHashes[h.score_file_hash].name)
+            dupe_name.setFlags(QtCore.Qt.ItemIsSelectable | QtCore.Qt.ItemIsEnabled)
+            dupe_name.setText(item_text)
+            dupe_name.setData(QtCore.Qt.UserRole, h.file_hash)
+            dupe_name.setData(QtCore.Qt.ToolTipRole, item_text)
+            self.pageList.setItem(row, 2, dupe_name)
+
+        self.pageList.resizeColumnsToContents()
+        self.pageList.selectRow(0)
+
+    def current_item_changed(self, curr, prev):
+
+        if curr is None:
+            return
+        if prev is not None and prev.row() == curr.row():
+            return
+
+        file_hash = str(self.pageList.item(curr.row(), 0).data(QtCore.Qt.UserRole))
+        image_hash = self.duplicates[self.dupe1].imageHashes[file_hash]
+        score_hash = self.duplicates[self.dupe2].imageHashes[image_hash.score_file_hash]
+
+        image1 = QtGui.QPixmap(image_hash.name)
+        image2 = QtGui.QPixmap(score_hash.name)
+
+        page_color = "red"
+        size_color = "red"
+        type_color = "red"
+        file_color = "black"
+        image_color = "black"
+        if image1.width() == image2.width() and image2.height() == image1.height():
+            size_color = "green"
+        if len(self.duplicates[self.dupe1].imageHashes) == len(self.duplicates[self.dupe2].imageHashes):
+            page_color = "green"
+        if image_hash.type == score_hash.type:
+            type_color = "green"
+        if image_hash.image_hash == score_hash.image_hash:
+            image_color = "green"
+        if image_hash.file_hash == score_hash.file_hash:
+            file_color = "green"
+        style = f"""
+            .page {{
+                color: {page_color};
+            }}
+            .size {{
+                color: {size_color};
+            }}
+            .type {{
+                color: {type_color};
+            }}
+            .file {{
+                color: {file_color};
+            }}
+            .image {{
+                color: {image_color};
+            }}"""
+        text = ( # this is a format string that creates a format string
+            "name: {{duplicate.path}}<br/>"
+            "page count: <span class='page'>{len}</span><br/>"
+            "size/type: <span class='size'>{{width}}x{{height}}</span>/<span class='type'>{meta.type}</span><br/>"
+            "file_hash: <span class='file'>{meta.file_hash}</span><br/>"
+            "image_hash: <span class='image'>{meta.image_hash}</span>".format(
+                meta=image_hash, style=style, len=len(self.duplicates[self.dupe1].imageHashes)
+            )
+        )
+        self.comic1Image.setDuplicate(self.duplicates[self.dupe1])
+        self.comic1Image.setImage(image_hash.name)
+        self.comic1Image.setText(text)
+        self.comic1Image.setLabelStyle(style)
+
+        text = (
+            "name: {{duplicate.path}}<br/>"
+            "page count: <span class='page'>{len}</span><br/>"
+            "size/type: <span class='size'>{{width}}x{{height}}</span>/<span class='type'>{score.type}</span><br/>"
+            "file_hash: <span class='file'>{score.file_hash}</span><br/>"
+            "image_hash: <span class='image'>{score.image_hash}</span>".format(
+                score=score_hash, style=style, len=len(self.duplicates[self.dupe2].imageHashes)
+            )
+        )
+        self.comic2Image.setDuplicate(self.duplicates[self.dupe2])
+        self.comic2Image.setImage(score_hash.name)
+        self.comic2Image.setText(text)
+        self.comic2Image.setLabelStyle(style)
+
+
+class QQlabel(QtWidgets.QLabel):
+    def __init__(self, parent=None):
+        super().__init__(parent)
+        self.image = None
+        self.setMinimumSize(1, 1)
+        self.setSizePolicy(QtWidgets.QSizePolicy.Expanding, QtWidgets.QSizePolicy.Expanding)
+
+    def setPixmap(self, pixmap: QtGui.QPixmap) -> None:
+        self.image = pixmap
+        self.setMaximumWidth(pixmap.width())
+        self.setMaximumHeight(pixmap.height())
+        super().setPixmap(
+            self.image.scaled(self.width(), self.height(), QtCore.Qt.KeepAspectRatio, QtCore.Qt.SmoothTransformation)
+        )
+
+    def resizeEvent(self, a0: QtGui.QResizeEvent) -> None:
+        if self.image is not None:
+            super().setPixmap(
+                self.image.scaled(
+                    self.width(), self.height(), QtCore.Qt.KeepAspectRatio, QtCore.Qt.SmoothTransformation
+                )
+            )
+
+
+class DupeImage(QtWidgets.QWidget):
+    deleted = QtCore.pyqtSignal(str)
+
+    def __init__(
+        self,
+        duplicate: Duplicate,
+        style=".path {color: black;}.hash {color: black;}",
+        text="path: <span class='path'>{duplicate.path}</span><br/>hash: <span class='hash'>{duplicate.digest}</span>",
+        image="cover",
+        parent=None,
+    ):
+        super().__init__(parent)
+        self.setLayout(QtWidgets.QVBoxLayout())
+        self.image = QQlabel()
+        self.label = QtWidgets.QLabel()
+        self.duplicate = duplicate
+        self.text = text
+        self.labelStyle = style
+
+        self.iHeight = 0
+        self.iWidth = 0
+        self.setStyleSheet("color: black;")
+        self.label.setWordWrap(True)
+
+        self.setImage(image)
+        self.setLabelStyle(self.labelStyle)
+        self.setText(self.text)
+
+        # label.setSizePolicy(QtWidgets.QSizePolicy.Minimum, QtWidgets.QSizePolicy.Minimum)
+        self.layout().addWidget(self.image)
+        self.layout().addWidget(self.label)
+
+    def contextMenuEvent(self, event: QtGui.QContextMenuEvent):
+        menu = QtWidgets.QMenu()
+        delete_action = menu.addAction("delete")
+        action = menu.exec(self.mapToGlobal(event.pos()))
+        if action == delete_action:
+            if self.duplicate.delete():
+                self.hide()
+                self.deleteLater()
+                # print("signal emitted")
+                self.deleted.emit(self.duplicate.path)
+
+    def setDuplicate(self, duplicate: Duplicate):
+        self.duplicate = duplicate
+        self.setImage("cover")
+        self.label.setText(
+            f"<style>{self.labelStyle}</style>"
+            + self.text.format(duplicate=self.duplicate, width=self.iWidth, height=self.iHeight)
+        )
+
+    def setText(self, text):
+        self.text = text
+        self.label.setText(
+            f"<style>{self.labelStyle}</style>"
+            + self.text.format(duplicate=self.duplicate, width=self.iWidth, height=self.iHeight)
+        )
+
+    def setImage(self, image):
+        if self.duplicate is not None:
+            pm = QtGui.QPixmap()
+            if image == "cover":
+                pm.loadFromData(self.duplicate.cover)
+            else:
+                pm.load(image)
+            self.iHeight = pm.height()
+            self.iWidth = pm.width()
+            self.image.setPixmap(pm)
+
+    def setLabelStyle(self, style):
+        self.labelStyle = style
+        self.label.setText(
+            f"<style>{self.labelStyle}</style>"
+            + self.text.format(duplicate=self.duplicate, width=self.iWidth, height=self.iHeight)
+        )
+
+
+def extract(dupe_set, directory):
+    for dupe in dupe_set:
+        dupe.extract(unique_dir(os.path.join(directory, os.path.basename(dupe.path))))
+
+
+def compare_dupe(dupe1: dict[str, ImageMeta], dupe2: dict[str, ImageMeta]):
+    for k, image1 in dupe1.items():
+        score = sys.maxsize
+        file_hash = ""
+        for _, image2 in dupe2.items():
+            tmp = ImageHasher.hamming_distance(image1.image_hash, image2.image_hash)
+            if tmp < score:
+                score = tmp
+                file_hash = image2.file_hash
+
+        dupe1[k].score = score
+        dupe1[k].score_file_hash = file_hash
+
+
+def make_key(x):
+    return "<" + str(x.series) + " #" + str(x.issue) + " - " + str(x.title) + " - " + str(x.year) + ">"
+
+
+def unique_dir(file_name):
+    counter = 1
+    file_name_parts = os.path.splitext(file_name)
+    while True:
+        if not os.path.lexists(file_name):
+            return file_name
+        file_name = file_name_parts[0] + " (" + str(counter) + ")" + file_name_parts[1]
+        counter += 1
+
+
+def parse_args(args: list[str], config=True):
+    parser = argparse.ArgumentParser(description="ComicTagger Duplicate comparison script")
+    parser.add_argument(
+        "-w",
+        metavar="workdir",
+        type=str,
+        nargs=1,
+        default=tempfile.mkdtemp(),
+        help="work directory, will be deleted on close",
+    )
+    parser.add_argument("paths", metavar="PATH", type=str, nargs="+", help="Path(s) to search for duplicates")
+    if config:
+        parser.add_argument(
+            "--config",
+            help="""Config directory defaults to ~/.ComicTagger\non Linux/Mac and %%APPDATA%% on Windows\n""",
+        )
+    return parser.parse_args(args)
+
+
+def main(args: Optional[list[str]] = None, settings: Optional[ComicTaggerSettings] = None):
+    opts = parse_args(args)
+    if not settings:
+        settings = ComicTaggerSettings(opts.config)
+
+    style = MetaDataStyle.CIX
+    file_list = utils.get_recursive_filelist(opts.paths)
+
+    return MainWindow(file_list, style, opts.w, settings)
+
+
+def sigint_handler(*args):
+    """Handler for the SIGINT signal."""
+    sys.stderr.write("\r")
+    QtWidgets.QApplication.quit()
+
+
+if __name__ == "__main__":
+    signal.signal(signal.SIGINT, sigint_handler)
+    app = QtWidgets.QApplication([])
+    window = main()
+    window.show()
+    app.exec()

comictaggerscripts/mainwindow.ui

@@ -0,0 +1,92 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<ui version="4.0">
+ <class>MainWindow</class>
+ <widget class="QMainWindow" name="MainWindow">
+  <property name="geometry">
+   <rect>
+    <x>0</x>
+    <y>0</y>
+    <width>800</width>
+    <height>600</height>
+   </rect>
+  </property>
+  <property name="windowTitle">
+   <string>ComicTagger Duplicate finder</string>
+  </property>
+  <widget class="QWidget" name="centralwidget">
+   <layout class="QHBoxLayout" name="horizontalLayout">
+    <property name="sizeConstraint">
+     <enum>QLayout::SetMinAndMaxSize</enum>
+    </property>
+    <item>
+     <widget class="QSplitter" name="splitter">
+      <property name="enabled">
+       <bool>true</bool>
+      </property>
+      <property name="acceptDrops">
+       <bool>true</bool>
+      </property>
+      <property name="orientation">
+       <enum>Qt::Horizontal</enum>
+      </property>
+      <property name="childrenCollapsible">
+       <bool>false</bool>
+      </property>
+      <widget class="QTreeView" name="dupe_set_qlist"/>
+      <widget class="QScrollArea" name="dupe_list_p">
+       <property name="minimumSize">
+        <size>
+         <width>400</width>
+         <height>0</height>
+        </size>
+       </property>
+       <property name="widgetResizable">
+        <bool>true</bool>
+       </property>
+       <widget class="QWidget" name="dupe_list">
+        <property name="geometry">
+         <rect>
+          <x>0</x>
+          <y>0</y>
+          <width>396</width>
+          <height>520</height>
+         </rect>
+        </property>
+        <layout class="QVBoxLayout" name="verticalLayout"/>
+       </widget>
+      </widget>
+     </widget>
+    </item>
+   </layout>
+  </widget>
+  <widget class="QMenuBar" name="menubar">
+   <property name="geometry">
+    <rect>
+     <x>0</x>
+     <y>0</y>
+     <width>800</width>
+     <height>30</height>
+    </rect>
+   </property>
+  </widget>
+  <widget class="QToolBar" name="toolBar">
+   <property name="windowTitle">
+    <string>toolBar</string>
+   </property>
+   <attribute name="toolBarArea">
+    <enum>TopToolBarArea</enum>
+   </attribute>
+   <attribute name="toolBarBreak">
+    <bool>false</bool>
+   </attribute>
+   <addaction name="actionCompare_Comic"/>
+  </widget>
+  <action name="actionCompare_Comic">
+   <property name="text">
+    <string>Compare Comic</string>
+   </property>
+  </action>
+ </widget>
+ <resources/>
+ <connections/>
+</ui>

scripts/find_dupes.py

@@ -1,86 +0,0 @@
-#!/usr/bin/python
-"""Find all duplicate comics"""
-
-# import sys
-
-from comictaggerlib.comicarchive import *
-from comictaggerlib.settings import *
-
-# from comictaggerlib.issuestring import *
-# import comictaggerlib.utils
-
-
-def main():
-    utils.fix_output_encoding()
-    settings = ComicTaggerSettings()
-
-    style = MetaDataStyle.CIX
-
-    if len(sys.argv) < 2:
-        print >> sys.stderr, "Usage:  {0} [comic_folder]".format(sys.argv[0])
-        return
-
-    filelist = utils.get_recursive_filelist(sys.argv[1:])
-
-    # first find all comics with metadata
-    print >> sys.stderr, "Reading in all comics..."
-    comic_list = []
-    fmt_str = ""
-    max_name_len = 2
-    for filename in filelist:
-        ca = ComicArchive(filename, settings.rar_exe_path)
-        if ca.seemsToBeAComicArchive() and ca.hasMetadata(style):
-            max_name_len = max(max_name_len, len(filename))
-            fmt_str = u"{{0:{0}}}".format(max_name_len)
-            print >> sys.stderr, fmt_str.format(filename) + "\r",
-            sys.stderr.flush()
-            comic_list.append((filename, ca.readMetadata(style)))
-
-    print >> sys.stderr, fmt_str.format("") + "\r",
-    print "--------------------------------------------------------------------------"
-    print "Found {0} comics with {1} tags".format(len(comic_list), MetaDataStyle.name[style])
-    print "--------------------------------------------------------------------------"
-
-    # sort the list by series+issue+year, to put all the dupes together
-    def makeKey(x):
-        return "<" + unicode(x[1].series) + u" #" + unicode(x[1].issue) + u" - " + unicode(x[1].year) + ">"
-
-    comic_list.sort(key=makeKey, reverse=False)
-
-    # look for duplicate blocks
-    dupe_set_list = []
-    dupe_set = []
-    prev_key = ""
-    for filename, md in comic_list:
-        print >> sys.stderr, fmt_str.format(filename) + "\r",
-        sys.stderr.flush()
-
-        new_key = makeKey((filename, md))
-
-        # if the new key same as the last, add to to dupe set
-        if new_key == prev_key:
-            dupe_set.append(filename)
-
-        # else we're on a new potential block
-        else:
-            # only add if the dupe list has 2 or more
-            if len(dupe_set) > 1:
-                dupe_set_list.append(dupe_set)
-            dupe_set = []
-            dupe_set.append(filename)
-
-        prev_key = new_key
-
-    print >> sys.stderr, fmt_str.format("") + "\r",
-    print "Found {0} duplicate sets".format(len(dupe_set_list))
-
-    for dupe_set in dupe_set_list:
-        ca = ComicArchive(dupe_set[0], settings.rar_exe_path)
-        md = ca.readMetadata(style)
-        print "{0} #{1} ({2})".format(md.series, md.issue, md.year)
-        for filename in dupe_set:
-            print "------>{0}".format(filename)
-
-
-if __name__ == "__main__":
-    main()

setup.py

@@ -53,7 +53,8 @@ setup(
     author="ComicTagger team",
     author_email="comictagger@gmail.com",
     url="https://github.com/comictagger/comictagger",
-    packages=["comictaggerlib", "comicapi"],
+    packages=["comictaggerlib", "comicapi", "comictaggerscripts"],
+    package_dir={"comictaggerscripts": "scripts"},
     package_data={"comictaggerlib": ["ui/*", "graphics/*"], "comicapi": ["data/*"]},
     entry_points=dict(console_scripts=["comictagger=comictaggerlib.main:ctmain"]),
     classifiers=[