Merge branch 'pyicu' into develop

Switch natsort to use os_sorted
Remove directories when returning a list of files in a comic
Update tests to account for '!cover.jpg'

.github/workflows/build.yaml

@@ -80,11 +80,25 @@ jobs:
         run: |
           choco install -y zip
         if: runner.os == 'Windows'
+      - name: Install macos dependencies
+        run: |
+          brew install icu4c pkg-config
+          export PKG_CONFIG_PATH="/usr/local/opt/icu4c/lib/pkgconfig";
+          export PATH="/usr/local/opt/icu4c/bin:/usr/local/opt/icu4c/sbin:$PATH"
+          python -m pip install --no-binary=:pyicu: pyicu
+        if: runner.os == 'macOS'
+      - name: Install linux dependencies
+        run: |
+          sudo apt-get install pkg-config libicu-dev
+          export PKG_CONFIG_PATH="/usr/local/opt/icu4c/lib/pkgconfig";
+          export PATH="/usr/local/opt/icu4c/bin:/usr/local/opt/icu4c/sbin:$PATH"
+          python -m pip install --no-binary=:pyicu: pyicu
+        if: runner.os == 'Linux'
 
       - name: Build and install PyPi packages
         run: |
           make clean pydist
-          python -m pip install "dist/$(python setup.py --fullname)-py3-none-any.whl[GUI,CBR]"
+          python -m pip install "dist/$(python setup.py --fullname)-py3-none-any.whl[all]"
 
       - name: build
         run: |

.github/workflows/package.yaml

@@ -41,12 +41,25 @@ jobs:
         run: |
           choco install -y zip
         if: runner.os == 'Windows'
+      - name: Install macos dependencies
+        run: |
+          brew install icu4c pkg-config
+          export PKG_CONFIG_PATH="/usr/local/opt/icu4c/lib/pkgconfig";
+          export PATH="/usr/local/opt/icu4c/bin:/usr/local/opt/icu4c/sbin:$PATH"
+          python -m pip install --no-binary=:pyicu: pyicu
+        if: runner.os == 'macOS'
+      - name: Install linux dependencies
+        run: |
+          sudo apt-get install pkg-config libicu-dev
+          export PKG_CONFIG_PATH="/usr/local/opt/icu4c/lib/pkgconfig";
+          export PATH="/usr/local/opt/icu4c/bin:/usr/local/opt/icu4c/sbin:$PATH"
+          python -m pip install --no-binary=:pyicu: pyicu
+        if: runner.os == 'Linux'
 
       - name: Build, Install and Test PyPi packages
         run: |
           make clean pydist
-          python -m pip install "dist/$(python setup.py --fullname)-py3-none-any.whl[GUI,CBR]"
-          echo "CT_FULL_NAME=$(python setup.py --fullname)" >> $GITHUB_ENV
+          python -m pip install "dist/$(python setup.py --fullname)-py3-none-any.whl[all]"
           python -m flake8
           python -m pytest
 
@@ -69,4 +82,4 @@ jobs:
           draft: false
           files: |
             dist/!(*Linux).zip
-            dist/*.whl
+            dist/*${{ fromJSON('["never", ""]')[runner.os == 'Linux'] }}.whl

.pre-commit-config.yaml

@@ -1,7 +1,7 @@
 exclude: ^scripts
 repos:
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.2.0
+    rev: v4.3.0
     hooks:
     -   id: trailing-whitespace
     -   id: end-of-file-fixer
@@ -10,7 +10,7 @@ repos:
     -   id: name-tests-test
     -   id: requirements-txt-fixer
 -   repo: https://github.com/asottile/setup-cfg-fmt
-    rev: v1.20.1
+    rev: v2.0.0
     hooks:
     -   id: setup-cfg-fmt
 -   repo: https://github.com/PyCQA/isort
@@ -19,12 +19,12 @@ repos:
     -   id: isort
         args: [--af,--add-import, 'from __future__ import annotations']
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v2.32.1
+    rev: v2.37.3
     hooks:
     -   id: pyupgrade
         args: [--py39-plus]
 -   repo: https://github.com/psf/black
-    rev: 22.3.0
+    rev: 22.6.0
     hooks:
     -   id: black
 -   repo: https://github.com/PyCQA/autoflake
@@ -33,12 +33,12 @@ repos:
     -   id: autoflake
         args: [-i]
 -   repo: https://github.com/PyCQA/flake8
-    rev: 4.0.1
+    rev: 5.0.4
     hooks:
     -   id: flake8
-        additional_dependencies: [flake8-encodings, flake8-warnings, flake8-builtins, flake8-eradicate, flake8-length, flake8-print]
+        additional_dependencies: [flake8-encodings, flake8-warnings, flake8-builtins, flake8-length, flake8-print]
 -   repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v0.960
+    rev: v0.971
     hooks:
     -   id: mypy
         additional_dependencies: [types-setuptools, types-requests]

README.md

@@ -2,6 +2,7 @@
 [![GitHub release (latest by date)](https://img.shields.io/github/downloads/comictagger/comictagger/latest/total)](https://github.com/comictagger/comictagger/releases/latest)
 [![PyPI](https://img.shields.io/pypi/v/comictagger)](https://pypi.org/project/comictagger/)
 [![PyPI - Downloads](https://img.shields.io/pypi/dm/comictagger)](https://pypistats.org/packages/comictagger)
+[![Chocolatey package](https://img.shields.io/chocolatey/dt/comictagger?color=blue&label=chocolatey)](https://community.chocolatey.org/packages/comictagger)
 [![PyPI - License](https://img.shields.io/pypi/l/comictagger)](https://opensource.org/licenses/Apache-2.0)
 
 [![GitHub Discussions](https://img.shields.io/github/discussions/comictagger/comictagger)](https://github.com/comictagger/comictagger/discussions)
@@ -48,6 +49,12 @@ A pip package is provided, you can install it with:
 
 There are two optional dependencies GUI and CBR. You can install the optional dependencies by specifying one or more of `GUI`,`CBR` or `all` in braces e.g. `comictagger[CBR,GUI]`
 
+### Chocolatey installation (Windows only)
+
+A [Chocolatey package](https://community.chocolatey.org/packages/comictagger), maintained by @Xav83, is provided, you can install it with:
+```powershell
+choco install comictagger
+```
 ### From source
 
  1. Ensure you have python 3.9 installed

comicapi/comicarchive.py

@@ -114,7 +114,7 @@ class SevenZipArchiver(UnknownArchiver):
         return False
 
     def read_file(self, archive_file: str) -> bytes:
-        data = bytes()
+        data = b""
         try:
             with py7zr.SevenZipFile(self.path, "r") as zf:
                 data = zf.read(archive_file)[archive_file].read()
@@ -148,7 +148,7 @@ class SevenZipArchiver(UnknownArchiver):
     def get_filename_list(self) -> list[str]:
         try:
             with py7zr.SevenZipFile(self.path, "r") as zf:
-                namelist: list[str] = zf.getnames()
+                namelist: list[str] = [file.filename for file in zf.list() if not file.is_directory]
 
             return namelist
         except (py7zr.Bad7zFile, OSError) as e:
@@ -248,7 +248,7 @@ class ZipArchiver(UnknownArchiver):
     def get_filename_list(self) -> list[str]:
         try:
             with zipfile.ZipFile(self.path, mode="r") as zf:
-                namelist = zf.namelist()
+                namelist = [file.filename for file in zf.infolist() if not file.is_dir()]
             return namelist
         except (zipfile.BadZipfile, OSError) as e:
             logger.error("Error listing files in zip archive [%s]: %s", e, self.path)
@@ -422,7 +422,7 @@ class RarArchiver(UnknownArchiver):
 
         rarc = self.get_rar_obj()
         if rarc is None:
-            return bytes()
+            return b""
 
         tries = 0
         while tries < 7:
@@ -665,7 +665,7 @@ class FolderArchiver(UnknownArchiver):
 
 
 class ComicArchive:
-    logo_data = bytes()
+    logo_data = b""
 
     class ArchiveType:
         SevenZip, Zip, Rar, Folder, Pdf, Unknown = list(range(6))
@@ -683,7 +683,7 @@ class ComicArchive:
         self._has_cbi: bool | None = None
         self._has_cix: bool | None = None
         self._has_comet: bool | None = None
-        self.path = pathlib.Path(path)
+        self.path = pathlib.Path(path).absolute()
         self.page_count: int | None = None
         self.page_list: list[str] = []
 
@@ -853,13 +853,13 @@ class ComicArchive:
         return retcode
 
     def get_page(self, index: int) -> bytes:
-        image_data = bytes()
+        image_data = b""
 
         filename = self.get_page_name(index)
 
         if filename:
             try:
-                image_data = self.archiver.read_file(filename) or bytes()
+                image_data = self.archiver.read_file(filename) or b""
             except Exception:
                 logger.error("Error reading in page %d. Substituting logo page.", index)
                 image_data = ComicArchive.logo_data
@@ -934,7 +934,7 @@ class ComicArchive:
             # seems like some archive creators are on Windows, and don't know about case-sensitivity!
             if sort_list:
 
-                files = cast(list[str], natsort.natsorted(files, alg=natsort.ns.IC | natsort.ns.I | natsort.ns.U))
+                files = cast(list[str], natsort.os_sorted(files))
 
             # make a sub-list of image files
             self.page_list = []
@@ -1033,7 +1033,7 @@ class ComicArchive:
             raw_cix = self.archiver.read_file(self.ci_xml_filename) or b""
         except Exception as e:
             logger.error("Error reading in raw CIX! for %s: %s", self.path, e)
-            raw_cix = bytes()
+            raw_cix = b""
         return raw_cix
 
     def write_cix(self, metadata: GenericMetadata) -> bool:

comicapi/filenameparser.py

@@ -24,7 +24,8 @@ import logging
 import os
 import re
 from operator import itemgetter
-from typing import Callable, Match, TypedDict
+from re import Match
+from typing import Callable, TypedDict
 from urllib.parse import unquote
 
 from text2digits import text2digits
@@ -67,17 +68,10 @@ class FileNameParser:
 
         # replace any name separators with spaces
         tmpstr = self.fix_spaces(filename)
-        found = False
 
-        match = re.search(r"(?<=\sof\s)\d+(?=\s)", tmpstr, re.IGNORECASE)
+        match = re.search(r"(?:\s\(?of\s)(\d+)(?: |\))", tmpstr, re.IGNORECASE)
         if match:
-            count = match.group()
-            found = True
-
-        if not found:
-            match = re.search(r"(?<=\(of\s)\d+(?=\))", tmpstr, re.IGNORECASE)
-            if match:
-                count = match.group()
+            count = match.group(1)
 
         return count.lstrip("0")
 
@@ -180,10 +174,12 @@ class FileNameParser:
         if "--" in filename:
             # the pattern seems to be that anything to left of the first "--" is the series name followed by issue
             filename = re.sub(r"--.*", self.repl, filename)
+            # never happens
 
         elif "__" in filename:
             # the pattern seems to be that anything to left of the first "__" is the series name followed by issue
             filename = re.sub(r"__.*", self.repl, filename)
+            # never happens
 
         filename = filename.replace("+", " ")
         tmpstr = self.fix_spaces(filename, remove_dashes=False)
@@ -425,6 +421,7 @@ def parse(p: Parser) -> Callable[[Parser], Callable | None] | None:
         likely_year = False
         if p.firstItem and p.first_is_alt:
             p.alt = True
+            p.firstItem = False
             return parse_issue_number
 
         # The issue number should hopefully not be in parentheses
@@ -440,9 +437,6 @@ def parse(p: Parser) -> Callable[[Parser], Callable | None] | None:
                             # Series has already been started/parsed,
                             # filters out leading alternate numbers leading alternate number
                             if len(p.series_parts) > 0:
-                                # Unset first item
-                                if p.firstItem:
-                                    p.firstItem = False
                                 return parse_issue_number
             else:
                 p.operator_rejected.append(item)
@@ -506,9 +500,6 @@ def parse(p: Parser) -> Callable[[Parser], Callable | None] | None:
             p.series_parts.append(item)
             p.used_items.append(item)
 
-            # Unset first item
-            if p.firstItem:
-                p.firstItem = False
             p.get()
             return parse_series
 
@@ -590,6 +581,8 @@ def parse(p: Parser) -> Callable[[Parser], Callable | None] | None:
         if series_append:
             p.series_parts.append(item)
             p.used_items.append(item)
+            if p.firstItem:
+                p.firstItem = False
             return parse_series
 
     # We found text, it's probably the title or series
@@ -602,6 +595,8 @@ def parse(p: Parser) -> Callable[[Parser], Callable | None] | None:
 
     # Usually the word 'of' eg 1 (of 6)
     elif item.typ == filenamelexer.ItemType.InfoSpecifier:
+        if p.firstItem:
+            p.firstItem = False
         return parse_info_specifier
 
     # Operator is a symbol that acts as some sort of separator eg - : ;
@@ -622,9 +617,13 @@ def parse(p: Parser) -> Callable[[Parser], Callable | None] | None:
                 p.irrelevant.extend([item, p.input[p.pos], p.get()])
             else:
                 p.backup()
+                if p.firstItem:
+                    p.firstItem = False
                 return parse_series
         # This is text that just happens to also be a month/day
         else:
+            if p.firstItem:
+                p.firstItem = False
             return parse_series
 
     # Specifically '__' or '--', no further title/series parsing is done to keep compatibility with wiki
@@ -853,10 +852,11 @@ def resolve_year(p: Parser) -> None:
             p.used_items.append(vol)
 
             # Remove volume from series and title
-            if selected_year in p.series_parts:
-                p.series_parts.remove(selected_year)
-            if selected_year in p.title_parts:
-                p.title_parts.remove(selected_year)
+            # note: this never happens
+            if vol in p.series_parts:
+                p.series_parts.remove(vol)
+            if vol in p.title_parts:
+                p.title_parts.remove(vol)
 
         # Remove year from series and title
         if selected_year in p.series_parts:

comicapi/genericmetadata.py

@@ -93,7 +93,7 @@ class GenericMetadata:
     comments: str | None = None  # use same way as Summary in CIX
 
     volume_count: int | None = None
-    critical_rating: float | None = None  # rating in cbl; CommunityRating in CIX
+    critical_rating: float | None = None  # rating in CBL; CommunityRating in CIX
     country: str | None = None
 
     alternate_series: str | None = None

comicapi/utils.py

@@ -19,11 +19,11 @@ import json
 import logging
 import os
 import pathlib
-import re
 import unicodedata
 from collections import defaultdict
+from collections.abc import Mapping
 from shutil import which  # noqa: F401
-from typing import Any, Mapping
+from typing import Any
 
 import pycountry
 import thefuzz.fuzz
@@ -57,22 +57,20 @@ def get_recursive_filelist(pathlist: list[str]) -> list[str]:
 
         if os.path.isdir(p):
             filelist.extend(x for x in glob.glob(f"{p}{os.sep}/**", recursive=True) if not os.path.isdir(x))
-        else:
-            filelist.append(p)
+        elif str(p) not in filelist:
+            filelist.append(str(p))
 
     return filelist
 
 
 def add_to_path(dirname: str) -> None:
-    if dirname is not None and dirname != "":
+    if dirname:
+        dirname = os.path.abspath(dirname)
+        paths = [os.path.normpath(x) for x in os.environ["PATH"].split(os.pathsep)]
 
-        # verify that path doesn't already contain the given dirname
-        tmpdirname = re.escape(dirname)
-        pattern = r"(^|{sep}){dir}({sep}|$)".format(dir=tmpdirname, sep=os.pathsep)
-
-        match = re.search(pattern, os.environ["PATH"])
-        if not match:
-            os.environ["PATH"] = dirname + os.pathsep + os.environ["PATH"]
+        if dirname not in paths:
+            paths.insert(0, dirname)
+            os.environ["PATH"] = os.pathsep.join(paths)
 
 
 def xlate(data: Any, is_int: bool = False, is_float: bool = False) -> Any:
@@ -123,13 +121,9 @@ def remove_articles(text: str) -> str:
         "the",
         "the",
         "with",
-        "ms",
-        "mrs",
-        "mr",
-        "dr",
     ]
     new_text = ""
-    for word in text.split(" "):
+    for word in text.split():
         if word not in articles:
             new_text += word + " "
 
@@ -141,19 +135,16 @@ def remove_articles(text: str) -> str:
 def sanitize_title(text: str, basic: bool = False) -> str:
     # normalize unicode and convert to ascii. Does not work for everything eg ½ to 1⁄2 not 1/2
     text = unicodedata.normalize("NFKD", text).casefold()
-    if basic:
-        # comicvine keeps apostrophes a part of the word
-        text = text.replace("'", "")
-        text = text.replace('"', "")
-    else:
+    # comicvine keeps apostrophes a part of the word
+    text = text.replace("'", "")
+    text = text.replace('"', "")
+    if not basic:
         # comicvine ignores punctuation and accents
         # remove all characters that are not a letter, separator (space) or number
         # replace any "dash punctuation" with a space
         # makes sure that batman-superman and self-proclaimed stay separate words
         text = "".join(
-            c if not unicodedata.category(c) in ("Pd",) else " "
-            for c in text
-            if unicodedata.category(c)[0] in "LZN" or unicodedata.category(c) in ("Pd",)
+            c if unicodedata.category(c)[0] not in "P" else " " for c in text if unicodedata.category(c)[0] in "LZNP"
         )
         # remove extra space and articles and all lower case
         text = remove_articles(text).strip()
@@ -161,10 +152,10 @@ def sanitize_title(text: str, basic: bool = False) -> str:
     return text
 
 
-def titles_match(search_title: str, record_title: str, threshold: int = 90) -> int:
+def titles_match(search_title: str, record_title: str, threshold: int = 90) -> bool:
     sanitized_search = sanitize_title(search_title)
     sanitized_record = sanitize_title(record_title)
-    ratio = thefuzz.fuzz.ratio(sanitized_search, sanitized_record)
+    ratio: int = thefuzz.fuzz.ratio(sanitized_search, sanitized_record)
     logger.debug(
         "search title: %s ; record title: %s ; ratio: %d ; match threshold: %d",
         search_title,
@@ -176,12 +167,12 @@ def titles_match(search_title: str, record_title: str, threshold: int = 90) -> i
 
 
 def unique_file(file_name: pathlib.Path) -> pathlib.Path:
-    name = file_name.name
+    name = file_name.stem
     counter = 1
     while True:
         if not file_name.exists():
             return file_name
-        file_name = file_name.with_name(name + " (" + str(counter) + ")")
+        file_name = file_name.with_stem(name + " (" + str(counter) + ")")
         counter += 1
 
 
@@ -205,6 +196,7 @@ def get_language_from_iso(iso: str | None) -> str | None:
 def get_language(string: str | None) -> str | None:
     if string is None:
         return None
+    string = string.casefold()
 
     lang = get_language_from_iso(string)
 
@@ -217,8 +209,6 @@ def get_language(string: str | None) -> str | None:
 
 
 def get_publisher(publisher: str) -> tuple[str, str]:
-    if publisher is None:
-        return ("", "")
     imprint = ""
 
     for pub in publishers.values():

comictaggerlib/cli.py

@@ -165,13 +165,13 @@ def post_process_matches(
 
 
 def cli_mode(opts: argparse.Namespace, settings: ComicTaggerSettings) -> None:
-    if len(opts.files) < 1:
+    if len(opts.file_list) < 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.files:
+    for f in opts.file_list:
         process_file_cli(f, opts, settings, match_results)
         sys.stdout.flush()
 
@@ -212,7 +212,7 @@ def create_local_metadata(opts: argparse.Namespace, ca: ComicArchive, settings:
 def process_file_cli(
     filename: str, opts: argparse.Namespace, settings: ComicTaggerSettings, match_results: OnlineMatchResults
 ) -> None:
-    batch_mode = len(opts.files) > 1
+    batch_mode = len(opts.file_list) > 1
 
     ca = ComicArchive(filename, settings.rar_exe_path, ComicTaggerSettings.get_graphic("nocover.png"))
 
@@ -472,7 +472,7 @@ def process_file_cli(
             match_results.good_matches.append(str(ca.path.absolute()))
 
     elif opts.rename:
-
+        original_path = ca.path
         msg_hdr = ""
         if batch_mode:
             msg_hdr = f"{ca.path}: "
@@ -529,7 +529,7 @@ def process_file_cli(
         else:
             suffix = " (dry-run, no change)"
 
-        print(f"renamed '{os.path.basename(ca.path)}' -> '{new_name}' {suffix}")
+        print(f"renamed '{original_path.name}' -> '{new_name}' {suffix}")
 
     elif opts.export_to_zip:
         msg_hdr = ""

comictaggerlib/comicvinetalker.py

@@ -184,8 +184,8 @@ class ComicVineTalker:
 
     def get_url_content(self, url: str, params: dict[str, Any]) -> Any:
         # connect to server:
-        #  if there is a 500 error, try a few more times before giving up
-        #  any other error, just bail
+        # if there is a 500 error, try a few more times before giving up
+        # any other error, just bail
         for tries in range(3):
             try:
                 resp = requests.get(url, params=params, headers={"user-agent": "comictagger/" + ctversion.version})
@@ -199,10 +199,15 @@ class ComicVineTalker:
                     break
 
             except requests.exceptions.RequestException as e:
-                self.write_log(str(e) + "\n")
+                self.write_log(f"{e}\n")
                 raise ComicVineTalkerException(ComicVineTalkerException.Network, "Network Error!") from e
+            except json.JSONDecodeError as e:
+                self.write_log(f"{e}\n")
+                raise ComicVineTalkerException(ComicVineTalkerException.Unknown, "ComicVine did not provide json")
 
-        raise ComicVineTalkerException(ComicVineTalkerException.Unknown, "Error on Comic Vine server")
+        raise ComicVineTalkerException(
+            ComicVineTalkerException.Unknown, f"Error on Comic Vine server: {resp.status_code}"
+        )
 
     def search_for_series(
         self,
@@ -735,7 +740,7 @@ class ComicVineTalker:
         )
 
         self.nam.finished.connect(self.async_fetch_issue_cover_url_complete)
-        self.nam.get(QtNetwork.QNetworkRequest(QtCore.QUrl(issue_url)))
+        self.nam.get(QtNetwork.QNetworkRequest(QtCore.QUrl(issue_url.geturl())))
 
     def async_fetch_issue_cover_url_complete(self, reply: QtNetwork.QNetworkReply) -> None:
         # read in the response

comictaggerlib/coverimagewidget.py

@@ -113,7 +113,7 @@ class CoverImageWidget(QtWidgets.QWidget):
         self.page_loader = None
         self.imageIndex = -1
         self.imageCount = 1
-        self.imageData = bytes()
+        self.imageData = b""
 
         self.btnLeft.setIcon(QtGui.QIcon(ComicTaggerSettings.get_graphic("left.png")))
         self.btnRight.setIcon(QtGui.QIcon(ComicTaggerSettings.get_graphic("right.png")))
@@ -136,7 +136,7 @@ class CoverImageWidget(QtWidgets.QWidget):
         self.page_loader = None
         self.imageIndex = -1
         self.imageCount = 1
-        self.imageData = bytes()
+        self.imageData = b""
 
     def clear(self) -> None:
         self.reset_widget()

comictaggerlib/filerenamer.py

@@ -20,10 +20,9 @@ import logging
 import os
 import pathlib
 import string
-import sys
-from typing import Any, cast
+from typing import Any, NamedTuple, cast
 
-from pathvalidate import sanitize_filename
+from pathvalidate import Platform, normalize_platform, sanitize_filename
 
 from comicapi.comicarchive import ComicArchive
 from comicapi.genericmetadata import GenericMetadata
@@ -32,6 +31,16 @@ from comicapi.issuestring import IssueString
 logger = logging.getLogger(__name__)
 
 
+class Replacements(NamedTuple):
+    literal_text: list[tuple[str, str]]
+    format_value: list[tuple[str, str]]
+
+
+REPLACEMENTS = Replacements(
+    literal_text=[(": ", " - "), (":", "-")], format_value=[(": ", " - "), (":", "-"), ("/", "-"), ("\\", "-")]
+)
+
+
 def get_rename_dir(ca: ComicArchive, rename_dir: str | pathlib.Path | None) -> pathlib.Path:
     folder = ca.path.parent.absolute()
     if rename_dir is not None:
@@ -42,16 +51,24 @@ def get_rename_dir(ca: ComicArchive, rename_dir: str | pathlib.Path | None) -> p
 
 
 class MetadataFormatter(string.Formatter):
-    def __init__(self, smart_cleanup: bool = False, platform: str = "auto") -> None:
+    def __init__(
+        self, smart_cleanup: bool = False, platform: str = "auto", replacements: Replacements = REPLACEMENTS
+    ) -> None:
         super().__init__()
         self.smart_cleanup = smart_cleanup
-        self.platform = platform
+        self.platform = normalize_platform(platform)
+        self.replacements = replacements
 
     def format_field(self, value: Any, format_spec: str) -> str:
         if value is None or value == "":
             return ""
         return cast(str, super().format_field(value, format_spec))
 
+    def handle_replacements(self, string: str, replacements: list[tuple[str, str]]) -> str:
+        for f, r in replacements:
+            string = string.replace(f, r)
+        return string
+
     def _vformat(
         self,
         format_string: str,
@@ -72,6 +89,8 @@ class MetadataFormatter(string.Formatter):
                 if lstrip:
                     literal_text = literal_text.lstrip("-_)}]#")
                 if self.smart_cleanup:
+                    if self.platform in [Platform.UNIVERSAL, Platform.WINDOWS]:
+                        literal_text = self.handle_replacements(literal_text, self.replacements.literal_text)
                     lspace = literal_text[0].isspace() if literal_text else False
                     rspace = literal_text[-1].isspace() if literal_text else False
                     literal_text = " ".join(literal_text.split())
@@ -109,19 +128,29 @@ class MetadataFormatter(string.Formatter):
 
                 # format the object and append to the result
                 fmt_obj = self.format_field(obj, format_spec)
-                if fmt_obj == "" and len(result) > 0 and self.smart_cleanup and literal_text:
-                    lstrip = True
+                if fmt_obj == "" and result and self.smart_cleanup and literal_text:
+                    if self.str_contains(result[-1], "({["):
+                        lstrip = True
                     if result:
                         if " " in result[-1]:
-                            result[-1], _, _ = result[-1].rpartition(" ")
+                            result[-1], _, _ = result[-1].rstrip().rpartition(" ")
                         result[-1] = result[-1].rstrip("-_({[#")
                 if self.smart_cleanup:
+                    if self.platform in [Platform.UNIVERSAL, Platform.WINDOWS]:
+                        # colons and slashes get special treatment
+                        fmt_obj = self.handle_replacements(fmt_obj, self.replacements.format_value)
                     fmt_obj = " ".join(fmt_obj.split())
                     fmt_obj = str(sanitize_filename(fmt_obj, platform=self.platform))
                 result.append(fmt_obj)
 
         return "".join(result), False
 
+    def str_contains(self, chars: str, string: str) -> bool:
+        for char in chars:
+            if char in string:
+                return True
+        return False
+
 
 class FileRenamer:
     def __init__(self, metadata: GenericMetadata | None, platform: str = "auto") -> None:
@@ -172,13 +201,6 @@ class FileRenamer:
 
         new_basename = ""
         for component in pathlib.PureWindowsPath(template).parts:
-            if (
-                self.platform.casefold() in ["universal", "windows"] or sys.platform.casefold() in ["windows"]
-            ) and self.smart_cleanup:
-                # colons get special treatment
-                component = component.replace(": ", " - ")
-                component = component.replace(":", "-")
-
             new_basename = str(
                 sanitize_filename(fmt.vformat(component, args=[], kwargs=Default(md_dict)), platform=self.platform)
             ).strip()

comictaggerlib/imagefetcher.py

@@ -97,14 +97,14 @@ class ImageFetcher:
             # if we found it, just emit the signal asap
             if image_data:
                 ImageFetcher.image_fetch_complete(QtCore.QByteArray(image_data))
-                return bytes()
+                return b""
 
             # didn't find it.  look online
             self.nam.finished.connect(self.finish_request)
             self.nam.get(QtNetwork.QNetworkRequest(QtCore.QUrl(url)))
 
             # we'll get called back when done...
-        return bytes()
+        return b""
 
     def finish_request(self, reply: QtNetwork.QNetworkReply) -> None:
         # read in the image data
@@ -159,10 +159,10 @@ class ImageFetcher:
             row = cur.fetchone()
 
             if row is None:
-                return bytes()
+                return b""
 
             filename = row[0]
-            image_data = bytes()
+            image_data = b""
 
             try:
                 with open(filename, "rb") as f:

comictaggerlib/issueidentifier.py

@@ -157,7 +157,7 @@ class IssueIdentifier:
             cropped_im = im.crop((int(w / 2), 0, w, h))
         except Exception:
             logger.exception("cropCover() error")
-            return bytes()
+            return b""
 
         output = io.BytesIO()
         cropped_im.save(output, format="PNG")

comictaggerlib/options.py

@@ -405,6 +405,8 @@ def parse_cmd_line() -> argparse.Namespace:
         opts.copy = opts.copy[0]
 
     if opts.recursive:
-        opts.file_list = utils.get_recursive_filelist(opts.file_list)
+        opts.file_list = utils.get_recursive_filelist(opts.files)
+    else:
+        opts.file_list = opts.files
 
     return opts

comictaggerlib/settings.py

@@ -22,7 +22,8 @@ import pathlib
 import platform
 import sys
 import uuid
-from typing import Iterator, TextIO, no_type_check
+from collections.abc import Iterator
+from typing import TextIO, no_type_check
 
 from comicapi import utils
 

comictaggerlib/taggerwindow.py

@@ -26,7 +26,8 @@ import pprint
 import re
 import sys
 import webbrowser
-from typing import Any, Callable, Iterable, cast
+from collections.abc import Iterable
+from typing import Any, Callable, cast
 from urllib.parse import urlparse
 
 import natsort
@@ -1854,7 +1855,7 @@ Have fun!
                 logger.error("Failed to load metadata for %s: %s", ca.path, e)
             image_data = ca.get_page(cover_idx)
             self.atprogdialog.set_archive_image(image_data)
-            self.atprogdialog.set_test_image(bytes())
+            self.atprogdialog.set_test_image(b"")
 
             QtCore.QCoreApplication.processEvents()
             if self.atprogdialog.isdone:

requirements-speedup.txt

@@ -0,0 +1 @@
+thefuzz[speedup]>=0.19.0

requirements.txt

@@ -2,11 +2,12 @@ beautifulsoup4 >= 4.1
 importlib_metadata
 natsort>=8.1.0
 pathvalidate
-pillow>=4.3.0
+pillow>=9.1.0
 py7zr
 pycountry
+pyicu; sys_platform == 'linux' or sys_platform == 'darwin'
 requests==2.*
 text2digits
-thefuzz[speedup]>=0.19.0
+thefuzz>=0.19.0
 typing_extensions
 wordninja

testing/comicdata.py

@@ -114,6 +114,7 @@ imprints = [
     ("marvel", ("", "Marvel")),
     ("marvel comics", ("", "Marvel")),
     ("aircel", ("Aircel Comics", "Marvel")),
+    ("nothing", ("", "nothing")),
 ]
 
 additional_imprints = [

testing/filenames.py

@@ -733,6 +733,20 @@ fnames = [
         },
         True,
     ),
+    (
+        "Cory Doctorow's Futuristic Tales of the Here and Now: Anda's Game #001 (2007).cbz",
+        "full-date, issue in parenthesis",
+        {
+            "issue": "1",
+            "series": "Cory Doctorow's Futuristic Tales of the Here and Now",
+            "title": "Anda's Game",
+            "volume": "",
+            "year": "2007",
+            "remainder": "",
+            "issue_count": "",
+        },
+        True,
+    ),
 ]
 
 rnames = [
@@ -743,6 +757,13 @@ rnames = [
         "Cory Doctorow's Futuristic Tales of the Here and Now #001 - Anda's Game (2007).cbz",
         does_not_raise(),
     ),
+    (
+        "{series} #{issue} - {title} {volume:02} ({year})",  # Ensure format specifier works
+        False,
+        "universal",
+        "Cory Doctorow's Futuristic Tales of the Here and Now #001 - Anda's Game 01 (2007).cbz",
+        does_not_raise(),
+    ),
     (
         "{series} #{issue} - {title} ({year})({price})",  # price should be none, test no  space between ')('
         False,
@@ -764,6 +785,20 @@ rnames = [
         "Cory Doctorow's Futuristic Tales of the Here and Now #001 - Anda's Game (2007).cbz",
         does_not_raise(),
     ),
+    (
+        "{title} {web_link}",  # Ensure colon is replaced in metadata
+        False,
+        "universal",
+        "Anda's Game https---comicvine.gamespot.com-cory-doctorows-futuristic-tales-of-the-here-and-no-4000-140529-.cbz",
+        does_not_raise(),
+    ),
+    (
+        "{series}:{title} #{issue} ({year})",  # on windows the ':' is replaced
+        False,
+        "universal",
+        "Cory Doctorow's Futuristic Tales of the Here and Now-Anda's Game #001 (2007).cbz",
+        does_not_raise(),
+    ),
     (
         "{series}: {title} #{issue} ({year})",  # on windows the ':' is replaced
         False,
@@ -795,7 +830,7 @@ rnames = [
     (
         r"{publisher}\  {series} #{issue} - {title} ({year})",  # backslashes separate directories
         False,
-        "universal",
+        "Linux",
         "Cory Doctorow's Futuristic Tales of the Here and Now #001 - Anda's Game (2007).cbz",
         does_not_raise(),
     ),
@@ -807,10 +842,10 @@ rnames = [
         does_not_raise(),
     ),
     (
-        "{series} #  {issue} - {locations} ({year})",
+        "{series} #{issue} - {locations} ({year})",
         False,
         "universal",
-        "Cory Doctorow's Futuristic Tales of the Here and Now # 001 - lonely cottage (2007).cbz",
+        "Cory Doctorow's Futuristic Tales of the Here and Now #001 - lonely cottage (2007).cbz",
         does_not_raise(),
     ),
     (
@@ -848,6 +883,20 @@ rnames = [
         "Cory Doctorow's Futuristic Tales of the Here and Now - Anda's Game {test} #001 (2007).cbz",
         does_not_raise(),
     ),
+    (
+        "{series} - {title} #{issue} ({year} {price})",  # Test null value in parenthesis with a non-null value
+        False,
+        "universal",
+        "Cory Doctorow's Futuristic Tales of the Here and Now - Anda's Game #001 (2007).cbz",
+        does_not_raise(),
+    ),
+    (
+        "{series} - {title} #{issue} (of {price})",  # null value with literal text in parenthesis
+        False,
+        "universal",
+        "Cory Doctorow's Futuristic Tales of the Here and Now - Anda's Game #001.cbz",
+        does_not_raise(),
+    ),
     (
         "{series} - {title} {1} #{issue} ({year})",  # Test numeric key
         False,

tests/comicarchive_test.py

@@ -15,6 +15,8 @@ def test_getPageNameList():
     pageNameList = c.get_page_name_list()
 
     assert pageNameList == [
+        "!cover.jpg",
+        "00.jpg",
         "page0.jpg",
         "Page1.jpeg",
         "Page2.png",

tests/conftest.py

@@ -5,7 +5,8 @@ import datetime
 import io
 import shutil
 import unittest.mock
-from typing import Any, Generator
+from collections.abc import Generator
+from typing import Any
 
 import pytest
 import requests

tests/utils_test.py

@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+import os
+
 import pytest
 
 import comicapi.utils
@@ -22,13 +24,16 @@ def test_recursive_list_with_file(tmp_path) -> None:
     temp_txt = tmp_path / "info.txt"
     temp_txt.write_text("this is here")
 
-    expected_result = {str(foo_png), str(temp_cbr), str(temp_file), str(temp_txt)}
-    result = set(comicapi.utils.get_recursive_filelist([tmp_path]))
+    temp_txt2 = tmp_path / "info2.txt"
+    temp_txt2.write_text("this is here")
+
+    expected_result = {str(foo_png), str(temp_cbr), str(temp_file), str(temp_txt), str(temp_txt2)}
+    result = set(comicapi.utils.get_recursive_filelist([str(temp_txt2), tmp_path]))
 
     assert result == expected_result
 
 
-values = [
+xlate_values = [
     ({"data": "", "is_int": False, "is_float": False}, None),
     ({"data": None, "is_int": False, "is_float": False}, None),
     ({"data": None, "is_int": True, "is_float": False}, None),
@@ -52,6 +57,70 @@ values = [
 ]
 
 
-@pytest.mark.parametrize("value, result", values)
+@pytest.mark.parametrize("value, result", xlate_values)
 def test_xlate(value, result):
     assert comicapi.utils.xlate(**value) == result
+
+
+language_values = [
+    ("en", "English"),
+    ("EN", "English"),
+    ("En", "English"),
+    ("", None),
+    (None, None),
+]
+
+
+@pytest.mark.parametrize("value, result", language_values)
+def test_get_language(value, result):
+    assert result == comicapi.utils.get_language(value)
+
+
+def test_unique_file(tmp_path):
+    file = tmp_path / "test.cbz"
+    assert file == comicapi.utils.unique_file(file)
+
+    file.mkdir()
+    assert (tmp_path / "test (1).cbz") == comicapi.utils.unique_file(file)
+
+
+def test_add_to_path(monkeypatch):
+    monkeypatch.setenv("PATH", os.path.abspath("/usr/bin"))
+    comicapi.utils.add_to_path("/bin")
+    assert os.environ["PATH"] == (os.path.abspath("/bin") + os.pathsep + os.path.abspath("/usr/bin"))
+
+    comicapi.utils.add_to_path("/usr/bin")
+    comicapi.utils.add_to_path("/usr/bin/")
+    assert os.environ["PATH"] == (os.path.abspath("/bin") + os.pathsep + os.path.abspath("/usr/bin"))
+
+
+titles = [
+    (("", ""), True),
+    (("Conan el Barbaro", "Conan el Bárbaro"), True),
+    (("鋼の錬金術師", "鋼の錬金術師"), True),
+    (("钢之炼金术师", "鋼の錬金術師"), False),
+    (("batmans grave", "The Batman's Grave"), True),
+    (("batman grave", "The Batman's Grave"), True),
+    (("bats grave", "The Batman's Grave"), False),
+]
+
+
+@pytest.mark.parametrize("value, result", titles)
+def test_titles_match(value, result):
+    assert comicapi.utils.titles_match(value[0], value[1]) == result
+
+
+titles_2 = [
+    ("", ""),
+    ("鋼の錬金術師", "鋼の錬金術師"),
+    ("Conan el Bárbaro", "Conan el Barbaro"),
+    ("The Batman's Grave", "batmans grave"),
+    ("A+X", "ax"),
+    ("ms. marvel", "ms marvel"),
+    ("spider-man/deadpool", "spider man deadpool"),
+]
+
+
+@pytest.mark.parametrize("value, result", titles_2)
+def test_sanitize_title(value, result):
+    assert comicapi.utils.sanitize_title(value) == result.casefold()