Comment qt functions executed in a separate thread

Toasts calculated the duration bar in python this is now a QPropertyAnimation

Series/Issue Selection windows now use signals/slots to communicate

.flake8

@@ -1,6 +0,0 @@
-[flake8]
-max-line-length = 120
-extend-ignore = E203, E501, A003
-extend-exclude = venv, scripts, build, dist, comictaggerlib/ctversion.py
-per-file-ignores =
-    comictaggerlib/cli.py: T20

.github/workflows/build.yaml

@@ -1,8 +1,7 @@
 name: CI
 
 env:
-  PIP: pip
-  PYTHON: python
+  LC_COLLATE: en_US.UTF-8
 on:
   pull_request:
   push:
@@ -23,24 +22,18 @@ jobs:
         os: [ubuntu-latest]
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
 
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
 
-      - uses: syphar/restore-virtualenv@v1.2
-        id: cache-virtualenv
-
-      - uses: syphar/restore-pip-download-cache@v1
-        if: steps.cache-virtualenv.outputs.cache-hit != 'true'
-
       - name: Install build dependencies
         run: |
-          python -m pip install --upgrade --upgrade-strategy eager -r requirements_dev.txt
+          python -m pip install flake8
 
       - uses: reviewdog/action-setup@v1
         with:
@@ -54,65 +47,50 @@ jobs:
     strategy:
       matrix:
         python-version: [3.9]
-        os: [ubuntu-latest, macos-10.15, windows-latest]
+        os: [ubuntu-22.04, macos-13, windows-latest]
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
 
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
 
-      - uses: syphar/restore-virtualenv@v1.2
-        id: cache-virtualenv
-
-      - uses: syphar/restore-pip-download-cache@v1
-        if: steps.cache-virtualenv.outputs.cache-hit != 'true'
-
-      - name: Install build dependencies
+      - name: Install tox
         run: |
-          pip install --force-reinstall git+https://github.com/pyinstaller/pyinstaller
-          python -m pip install --upgrade --upgrade-strategy eager -r requirements_dev.txt
+          python -m pip install --upgrade --upgrade-strategy eager tox
 
-      - name: Install Windows build dependencies
-        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:$PATH"
-          python -m pip install --no-binary=pyicu pyicu
+          brew upgrade icu4c pkg-config || brew install icu4c pkg-config
         if: runner.os == 'macOS'
+
       - name: Install linux dependencies
         run: |
-          sudo apt-get install pkg-config libicu-dev
-          export PKG_CONFIG_PATH="/usr/local/opt/icu4c/lib/pkgconfig";
-          export PATH="/usr/local/opt/icu4c/bin:/usr/local/opt/icu4c/sbin:$PATH"
-          python -m pip install --no-binary=pyicu pyicu
+          sudo apt-get update && sudo apt-get upgrade && sudo apt-get install pkg-config libicu-dev libqt5gui5 libfuse2 desktop-file-utils
         if: runner.os == 'Linux'
 
       - name: Build and install PyPi packages
         run: |
-          make clean pydist
-          python -m pip install "dist/$(python setup.py --fullname)-py3-none-any.whl[all]"
-
-      - name: build
-        run: |
-          make dist
+          export PKG_CONFIG_PATH="/usr/local/opt/icu4c/lib/pkgconfig:/opt/homebrew/opt/icu4c/lib/pkgconfig${PKG_CONFIG_PATH+:$PKG_CONFIG_PATH}";
+          export PATH="/usr/local/opt/icu4c/bin:/usr/local/opt/icu4c/sbin${PATH+:$PATH}"
+          python -m tox r -m build
+        shell: bash
 
       - name: Archive production artifacts
-        uses: actions/upload-artifact@v2
-        if: runner.os != 'Linux' # linux binary currently has a segfault when running on latest fedora
+        uses: actions/upload-artifact@v4
         with:
           name: "${{ format('ComicTagger-{0}', runner.os) }}"
           path: |
-            dist/*.zip
+            dist/*.whl
+            dist/binary/*.zip
+            dist/binary/*.tar.gz
+            dist/binary/*.dmg
+            dist/binary/*.AppImage
 
       - name: PyTest
         run: |
-          python -m pytest
+          python -m tox r

.github/workflows/contributions.yaml

@@ -0,0 +1,43 @@
+name: Contributions
+on:
+  push:
+    branches:
+      - 'develop'
+    tags-ignore:
+      - '**'
+
+jobs:
+  contrib-readme-job:
+    permissions:
+      contents: write
+    runs-on: ubuntu-latest
+    env:
+      CI_COMMIT_AUTHOR: github-actions[bot]
+      CI_COMMIT_EMAIL: <41898282+github-actions[bot]@users.noreply.github.com>
+      CI_COMMIT_MESSAGE: Update AUTHORS
+    name: A job to automate contrib in readme
+    steps:
+      - name: Contribute List
+        uses: akhilmhdh/contributors-readme-action@v2.3.6
+        with:
+          use_username: true
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Update AUTHORS
+        run: |
+          git config --global log.mailmap true
+          git log --reverse '--format=%aN <%aE>' | cat -n | sort -uk2 | sort -n | cut -f2- >AUTHORS
+
+      - name: Commit and push AUTHORS
+        run: |
+          if ! git diff --exit-code; then
+            git pull
+            git config --global user.name "${{ env.CI_COMMIT_AUTHOR }}"
+            git config --global user.email "${{ env.CI_COMMIT_EMAIL }}"
+            git commit -a -m "${{ env.CI_COMMIT_MESSAGE }}"
+            git push
+          fi

.github/workflows/package.yaml

@@ -1,8 +1,7 @@
 name: Package
 
 env:
-  PIP: pip
-  PYTHON: python
+  LC_COLLATE: en_US.UTF-8
 on:
   push:
     tags:
@@ -10,70 +9,46 @@ on:
 jobs:
   package:
     permissions:
+      # IMPORTANT: this permission is mandatory for trusted publishing
+      id-token: write
       contents: write
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
         python-version: [3.9]
-        os: [ubuntu-latest, macos-10.15, windows-latest]
+        os: [ubuntu-22.04, macos-13, windows-latest]
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
 
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
 
-      - uses: syphar/restore-virtualenv@v1.2
-        id: cache-virtualenv
-
-      - uses: syphar/restore-pip-download-cache@v1
-        if: steps.cache-virtualenv.outputs.cache-hit != 'true'
-
-      - name: Install build dependencies
+      - name: Install tox
         run: |
-          pip install --force-reinstall git+https://github.com/pyinstaller/pyinstaller
-          python -m pip install --upgrade --upgrade-strategy eager -r requirements_dev.txt
+          python -m pip install --upgrade --upgrade-strategy eager tox
 
-      - name: Install Windows build dependencies
-        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:$PATH"
-          python -m pip install --no-binary=pyicu pyicu
+          brew upgrade icu4c pkg-config || brew install icu4c pkg-config
         if: runner.os == 'macOS'
+
       - name: Install linux dependencies
         run: |
-          sudo apt-get install pkg-config libicu-dev
-          export PKG_CONFIG_PATH="/usr/local/opt/icu4c/lib/pkgconfig";
-          export PATH="/usr/local/opt/icu4c/bin:/usr/local/opt/icu4c/sbin:$PATH"
-          python -m pip install --no-binary=pyicu pyicu
+          sudo apt-get update && sudo apt-get upgrade && sudo apt-get install pkg-config libicu-dev libqt5gui5 libfuse2 desktop-file-utils
         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[all]"
-          python -m flake8
-          python -m pytest
-
-      - name: "Publish distribution 📦 to PyPI"
-        if: startsWith(github.ref, 'refs/tags/') && runner.os == 'Linux'
-        uses: pypa/gh-action-pypi-publish@release/v1
-        with:
-          password: ${{ secrets.PYPI_API_TOKEN }}
-          packages_dir: dist
-
-      - name: Build PyInstaller package
-        run: |
-          make dist
+          export PKG_CONFIG_PATH="/usr/local/opt/icu4c/lib/pkgconfig:/opt/homebrew/opt/icu4c/lib/pkgconfig${PKG_CONFIG_PATH+:$PKG_CONFIG_PATH}";
+          export PATH="/usr/local/opt/icu4c/bin:/usr/local/opt/icu4c/sbin${PATH+:$PATH}"
+          python -m tox r
+          python -m tox r -m release
+        shell: bash
 
       - name: Get release name
         if: startsWith(github.ref, 'refs/tags/')
@@ -83,12 +58,16 @@ jobs:
           echo "release_name=$(git tag -l --format "%(refname:strip=2): %(contents:lines=1)" ${{ github.ref_name }})" >> $GITHUB_ENV
 
       - name: Release
-        uses: softprops/action-gh-release@v1
+        uses: softprops/action-gh-release@v2
         if: startsWith(github.ref, 'refs/tags/')
         with:
           name: "${{ env.release_name }}"
           prerelease: "${{ contains(github.ref, '-') }}" # alpha-releases should be 1.3.0-alpha.x full releases should be 1.3.0
           draft: false
+          # upload the single application zip file for each OS and include the wheel built on linux
           files: |
-            dist/!(*Linux).zip
+            dist/binary/*.zip
+            dist/binary/*.tar.gz
+            dist/binary/*.dmg
+            dist/binary/*.AppImage
             dist/*${{ fromJSON('["never", ""]')[runner.os == 'Linux'] }}.whl

.gitignore

@@ -155,3 +155,6 @@ dmypy.json
 
 # Cython debug symbols
 cython_debug/
+
+# for testing
+temp/

.mailmap

@@ -0,0 +1,9 @@
+Andrew W. Buchanan <buchanan@difference.com>
+Davide Romanini <d.romanini@cineca.it> <davide.romanini@gmail.com>
+Davide Romanini <d.romanini@cineca.it> <user159033@92-63-141-211.rdns.melbourne.co.uk>
+Michael Fitzurka <MichaelFitzurka@users.noreply.github.com> <MichaelFitzurka@github.com>
+Timmy Welch <timmy@narnian.us>
+beville <beville@users.noreply.github.com> <(no author)@6c5673fe-1810-88d6-992b-cd32ca31540c>
+beville <beville@users.noreply.github.com> <beville@6c5673fe-1810-88d6-992b-cd32ca31540c>
+beville <beville@users.noreply.github.com> <beville@gmail.com@6c5673fe-1810-88d6-992b-cd32ca31540c>
+beville <beville@users.noreply.github.com> <beville@users.noreply.github.com>

.pre-commit-config.yaml

@@ -1,7 +1,7 @@
-exclude: ^scripts
+exclude: ^(scripts|comictaggerlib/graphics/resources.py)
 repos:
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.3.0
+    rev: v5.0.0
     hooks:
     -   id: trailing-whitespace
     -   id: end-of-file-fixer
@@ -10,37 +10,37 @@ repos:
     -   id: name-tests-test
     -   id: requirements-txt-fixer
 -   repo: https://github.com/asottile/setup-cfg-fmt
-    rev: v2.2.0
+    rev: v2.7.0
     hooks:
     -   id: setup-cfg-fmt
--   repo: https://github.com/PyCQA/isort
-    rev: 5.10.1
-    hooks:
-    -   id: isort
-        args: [--af,--add-import, 'from __future__ import annotations']
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v3.1.0
+    rev: v3.18.0
     hooks:
     -   id: pyupgrade
         args: [--py39-plus]
--   repo: https://github.com/psf/black
-    rev: 22.10.0
-    hooks:
-    -   id: black
 -   repo: https://github.com/PyCQA/autoflake
-    rev: v1.7.7
+    rev: v2.3.1
     hooks:
     -   id: autoflake
-        args: [-i]
+        args: [-i, --remove-all-unused-imports, --ignore-init-module-imports]
+-   repo: https://github.com/PyCQA/isort
+    rev: 5.13.2
+    hooks:
+    -   id: isort
+        args: [--af,--add-import, 'from __future__ import annotations']
+-   repo: https://github.com/psf/black
+    rev: 24.4.2
+    hooks:
+    -   id: black
 -   repo: https://github.com/PyCQA/flake8
-    rev: 5.0.4
+    rev: 7.1.1
     hooks:
     -   id: flake8
-        additional_dependencies: [flake8-encodings, flake8-warnings, flake8-builtins, flake8-length, flake8-print]
+        additional_dependencies: [flake8-encodings, flake8-builtins, flake8-print, flake8-no-nested-comprehensions]
 -   repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v0.982
+    rev: v1.11.2
     hooks:
     -   id: mypy
-        additional_dependencies: [types-setuptools, types-requests]
+        additional_dependencies: [types-setuptools, types-requests, settngs>=0.10.4]
 ci:
     skip: [mypy]

.travis.yml

@@ -1,59 +0,0 @@
-language: python
-# Only build tags
-if: type = pull_request OR tag IS present
-branches:
-  only:
-    - develop
-    - /^\d+\.\d+\.\d+.*$/
-env:
-  global:
-    - PYTHON=python3
-    - PIP=pip3
-    - SETUPTOOLS_SCM_PRETEND_VERSION=$TRAVIS_TAG
-    - MAKE=make
-matrix:
-  include:
-    - os: linux
-      python: 3.8
-    - name: "Python: 3.7"
-      os: osx
-      language: shell
-      python: 3.7
-      env: PYTHON=python3 PIP="python3 -m pip"
-      cache:
-        - directories:
-          - $HOME/Library/Caches/pip
-    - os: windows
-      language: bash
-      env: PATH=/C/Python37:/C/Python37/Scripts:$PATH MAKE=mingw32-make PIP=pip PYTHON=python
-before_install:
-  - if [ "$TRAVIS_OS_NAME" = "windows" ]; then choco install -y python --version 3.7.9; choco install -y mingw zip; fi
-install:
-  - $PIP install -r requirements_dev.txt
-  - $PIP install -r requirements-GUI.txt
-  - $PIP install -r requirements-CBR.txt
-script:
-  - if [ "$TRAVIS_OS_NAME" != "linux" ]; then $MAKE dist ; fi
-
-deploy:
-  - name: "$TRAVIS_TAG"
-    body: Released ComicTagger $TRAVIS_TAG
-    provider: releases
-    skip_cleanup: true
-    api_key:
-      secure: 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
-    file_glob: true
-    file: dist/*.zip
-    draft: true
-    on:
-      tags: true
-      condition: $TRAVIS_OS_NAME != "linux"
-  - provider: pypi
-    user: __token__
-    password:
-      secure: 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
-    skip_existing: true
-    skip_cleanup: true
-    on:
-      tags: true
-      condition: $TRAVIS_OS_NAME = "linux"

AUTHORS

@@ -0,0 +1,18 @@
+beville <beville@users.noreply.github.com>
+Davide Romanini <d.romanini@cineca.it>
+fcanc <f.canc@icloud.com>
+Alban Seurat <alkpone@alkpone.com>
+tlc <tlc@users.noreply.github.com>
+Marek Pawlak <francuz14@gmail.com>
+Timmy Welch <timmy@narnian.us>
+J.P. Cranford <philipcranford4@gmail.com>
+thFrgttn <39759781+thFrgttn@users.noreply.github.com>
+Andrew W. Buchanan <buchanan@difference.com>
+Michael Fitzurka <MichaelFitzurka@users.noreply.github.com>
+Richard Haussmann <richard.haussmann@gmail.com>
+Mizaki <jinxybob@hotmail.com>
+Xavier Jouvenot <x.jouvenot@gmail.com>
+github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
+Ben Longman <deck@steamdeck.lan>
+Sven Hesse <drmccoy@drmccoy.de>
+pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

CONTRIBUTING.md

@@ -41,7 +41,7 @@ Please open a [GitHub Pull Request](https://github.com/comictagger/comictagger/p
 
 Currently only python 3.9 is supported however 3.10 will probably work if you try it
 
-Those on linux should install `Pillow` from the system package manager if possible and if the GUI and/or the CBR/RAR comicbooks are going to be used `pyqt5` and `unrar-cffi` should be installed from the system package manager
+Those on linux should install `Pillow` from the system package manager if possible and if the GUI `pyqt5` should be installed from the system package manager
 
 Those on macOS will need to ensure that you are using python3 in x86 mode either by installing an x86 only version of python or using the universal installer and using `python3-intel64` instead of `python3`
 
@@ -50,10 +50,10 @@ Those on macOS will need to ensure that you are using python3 in x86 mode either
 git clone https://github.com/comictagger/comictagger.git
 ```
 
-2. It is preferred to use a virtual env for running from source, adding the `--system-site-packages` allows packages already installed via the system package manager to be used:
+2. It is preferred to use a virtual env for running from source:
 
 ```
-python3 -m venv --system-site-packages venv
+python3 -m venv venv
 ```
 
 3. Activate the virtual env:
@@ -65,73 +65,34 @@ or if on windows PowerShell
 . venv/bin/activate.ps1
 ```
 
-4. install dependencies:
+4. Install tox:
 ```bash
-pip install -r requirements_dev.txt -r requirements.txt
-# if installing optional dependencies
-pip install -r requirements-GUI.txt -r requirements-CBR.txt
+pip install tox
 ```
 
-5. install ComicTagger
+5. If you are on an M1 Mac you will need to export two environment variables for tests to pass.
 ```
-pip install .
+export tox_python=python3.9-intel64
+export tox_env=m1env
 ```
 
-6. (optionally) run pytest to ensure that their are no failures (xfailed means expected failure)
+6. install ComicTagger
 ```
-$ pytest
-============================= test session starts ==============================
-platform darwin -- Python 3.9.12, pytest-7.1.1, pluggy-1.0.0
-rootdir: /Users/timmy/build/source/comictagger
-collected 61 items
-
-tests/test_FilenameParser.py ..x......x.xxx.xx....xxxxxx.xx.x..xxxxxxx   [ 67%]
-tests/test_comicarchive.py x...                                          [ 73%]
-tests/test_rename.py ..xxx.xx..XXX.XX                                    [100%]
-
-================== 27 passed, 29 xfailed, 5 xpassed in 2.68s ===================
+tox run -e venv
 ```
 
 7. Make your changes
-8. run code tools and correct any issues
+8. Build to ensure that your changes work: this will produce a binary build in the dist folder
 ```bash
-black .
-isort .
-flake8 .
-pytest
+tox run -m build
 ```
 
-black: formats all of the code consistently so there are no surprises<br>
+The build runs these formatters and linters automatically
+
+setup-cfg-fmt: Formats the setup.cfg file
+autoflake: Removes unused imports
 isort: sorts imports so that you can always find where an import is located<br>
+black: formats all of the code consistently so there are no surprises<br>
 flake8: checks for code quality and style (warns for unused imports and similar issues)<br>
+mypy: checks the types of variables and functions to catch errors
 pytest: runs tests for ComicTagger functionality
-
-
-if on mac or linux most of this can be accomplished by running
-```
-make install
-# or make PYTHON=python3-intel64 install
-. venv/bin/activate
-make CI
-```
-There is also `make check` which will run all of the code tools in a read-only capacity
-```
-$ make check
-venv/bin/black --check .
-All done! ✨ 🍰 ✨
-52 files would be left unchanged.
-venv/bin/isort --check .
-Skipped 6 files
-venv/bin/flake8 .
-venv/bin/pytest
-============================= test session starts ==============================
-platform darwin -- Python 3.9.12, pytest-7.1.1, pluggy-1.0.0
-rootdir: /Users/timmy/build/source/comictagger
-collected 61 items
-
-tests/test_FilenameParser.py ..x......x.xxx.xx....xxxxxx.xx.x..xxxxxxx   [ 67%]
-tests/test_comicarchive.py x...                                          [ 73%]
-tests/test_rename.py ..xxx.xx..XXX.XX                                    [100%]
-
-================== 27 passed, 29 xfailed, 5 xpassed in 2.68s ===================
-```

LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

MANIFEST.in

@@ -1,7 +0,0 @@
-include README.md
-include release_notes.txt
-include requirements.txt
-recursive-include scripts *.py *.txt
-recursive-include desktop-integration *
-include windows/app.ico
-include mac/app.icns

Makefile

@@ -1,64 +0,0 @@
-PIP ?= pip3
-PYTHON ?= python3
-VERSION_STR := $(shell $(PYTHON) setup.py --version)
-
-SITE_PACKAGES := $(shell $(PYTHON) -c 'import sysconfig; print(sysconfig.get_paths()["purelib"])')
-PACKAGE_PATH = $(SITE_PACKAGES)/comictagger.egg-link
-
-VENV := $(shell echo $${VIRTUAL_ENV-venv})
-PY3 := $(shell command -v $(PYTHON) 2> /dev/null)
-PYTHON_VENV := $(VENV)/bin/python
-INSTALL_STAMP := $(VENV)/.install.stamp
-
-
-ifeq ($(OS),Windows_NT)
-	PYTHON_VENV := $(VENV)/Scripts/python.exe
-	OS_VERSION=win-$(PROCESSOR_ARCHITECTURE)
-	APP_NAME=comictagger.exe
-	FINAL_NAME=ComicTagger-$(VERSION_STR)-$(OS_VERSION).exe
-else ifeq ($(shell uname -s),Darwin)
-	OS_VERSION=osx-$(shell defaults read loginwindow SystemVersionStampAsString)-$(shell uname -m)
-	APP_NAME=ComicTagger.app
-	FINAL_NAME=ComicTagger-$(VERSION_STR)-$(OS_VERSION).app
-else
-	APP_NAME=comictagger
-	FINAL_NAME=ComicTagger-$(VERSION_STR)-$(shell uname -s)
-endif
-
-.PHONY: all clean pydist dist CI check
-
-all: clean dist
-
-$(PYTHON_VENV):
-	@if [ -z $(PY3) ]; then echo "Python 3 could not be found."; exit 2; fi
-	$(PY3) -m venv $(VENV)
-
-clean:
-	find . -maxdepth 4 -type d -name "__pycache__"
-	rm -rf $(PACKAGE_PATH) $(INSTALL_STAMP) build dist MANIFEST comictaggerlib/ctversion.py
-	$(MAKE) -C mac clean
-
-CI: install
-	$(PYTHON_VENV) -m black .
-	$(PYTHON_VENV) -m isort .
-	$(PYTHON_VENV) -m flake8 .
-	$(PYTHON_VENV) -m pytest
-
-check: install
-	$(PYTHON_VENV) -m black --check .
-	$(PYTHON_VENV) -m isort --check .
-	$(PYTHON_VENV) -m flake8 .
-	$(PYTHON_VENV) -m pytest
-
-pydist:
-	$(PYTHON_VENV) -m build
-
-install: $(INSTALL_STAMP)
-$(INSTALL_STAMP): $(PYTHON_VENV) requirements.txt requirements_dev.txt
-	$(PYTHON_VENV) -m pip install -r requirements_dev.txt
-	$(PYTHON_VENV) -m pip install -e .
-	touch $(INSTALL_STAMP)
-
-dist:
-	pyinstaller -y comictagger.spec
-	cd dist && zip -m -r $(FINAL_NAME).zip $(APP_NAME)

README.md

@@ -35,7 +35,7 @@ For details, screen-shots, and more, visit [the Wiki](https://github.com/comicta
 
 ### Binaries
 
-Windows and macOS binaries are provided in the [Releases Page](https://github.com/comictagger/comictagger/releases).
+Windows, Linux and MacOS binaries are provided in the [Releases Page](https://github.com/comictagger/comictagger/releases).
 
 Just unzip the archive in any folder and run, no additional installation steps are required.
 
@@ -47,7 +47,14 @@ A pip package is provided, you can install it with:
  $ pip3 install comictagger[GUI]
 ```
 
-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]`
+There are optional dependencies. You can install the optional dependencies by specifying one or more of them in braces e.g. `comictagger[CBR,GUI]`
+
+Optional dependencies:
+1. `ICU`: Ensures that comic pages are supported correctly. This should always be installed. *Currently only exists in the latest alpha release *
+1. `CBR`: Provides support for CBR/RAR files.
+1. `GUI`: Installs the GUI.
+1. `7Z`: Provides support for CB7/7Z files.
+1. `all`: Installs all of the above optional dependencies.
 
 ### Chocolatey installation (Windows only)
 
@@ -59,5 +66,120 @@ choco install comictagger
 
  1. Ensure you have python 3.9 installed
  2. Clone this repository `git clone https://github.com/comictagger/comictagger.git`
- 3. `pip3 install -r requirements_dev.txt`
- 7. `pip3 install .` or `pip3 install .[GUI]`
+ 7. `pip3 install .[ICU]` or `pip3 install .[GUI,ICU]`
+
+
+## Contributors
+
+<!-- readme: beville,davide-romanini,collaborators,contributors -start -->
+<table>
+<tr>
+    <td align="center">
+        <a href="https://github.com/beville">
+            <img src="https://avatars.githubusercontent.com/u/7294848?v=4" width="100;" alt="beville"/>
+            <br />
+            <sub><b>beville</b></sub>
+        </a>
+    </td>
+    <td align="center">
+        <a href="https://github.com/davide-romanini">
+            <img src="https://avatars.githubusercontent.com/u/731199?v=4" width="100;" alt="davide-romanini"/>
+            <br />
+            <sub><b>davide-romanini</b></sub>
+        </a>
+    </td>
+    <td align="center">
+        <a href="https://github.com/fcanc">
+            <img src="https://avatars.githubusercontent.com/u/4999486?v=4" width="100;" alt="fcanc"/>
+            <br />
+            <sub><b>fcanc</b></sub>
+        </a>
+    </td>
+    <td align="center">
+        <a href="https://github.com/lordwelch">
+            <img src="https://avatars.githubusercontent.com/u/7547075?v=4" width="100;" alt="lordwelch"/>
+            <br />
+            <sub><b>lordwelch</b></sub>
+        </a>
+    </td>
+    <td align="center">
+        <a href="https://github.com/mizaki">
+            <img src="https://avatars.githubusercontent.com/u/1141189?v=4" width="100;" alt="mizaki"/>
+            <br />
+            <sub><b>mizaki</b></sub>
+        </a>
+    </td>
+    <td align="center">
+        <a href="https://github.com/MichaelFitzurka">
+            <img src="https://avatars.githubusercontent.com/u/27830765?v=4" width="100;" alt="MichaelFitzurka"/>
+            <br />
+            <sub><b>MichaelFitzurka</b></sub>
+        </a>
+    </td></tr>
+<tr>
+    <td align="center">
+        <a href="https://github.com/abuchanan920">
+            <img src="https://avatars.githubusercontent.com/u/368793?v=4" width="100;" alt="abuchanan920"/>
+            <br />
+            <sub><b>abuchanan920</b></sub>
+        </a>
+    </td>
+    <td align="center">
+        <a href="https://github.com/AlbanSeurat">
+            <img src="https://avatars.githubusercontent.com/u/500180?v=4" width="100;" alt="AlbanSeurat"/>
+            <br />
+            <sub><b>AlbanSeurat</b></sub>
+        </a>
+    </td>
+    <td align="center">
+        <a href="https://github.com/rhaussmann">
+            <img src="https://avatars.githubusercontent.com/u/7084007?v=4" width="100;" alt="rhaussmann"/>
+            <br />
+            <sub><b>rhaussmann</b></sub>
+        </a>
+    </td>
+    <td align="center">
+        <a href="https://github.com/jpcranford">
+            <img src="https://avatars.githubusercontent.com/u/21347202?v=4" width="100;" alt="jpcranford"/>
+            <br />
+            <sub><b>jpcranford</b></sub>
+        </a>
+    </td>
+    <td align="center">
+        <a href="https://github.com/PawlakMarek">
+            <img src="https://avatars.githubusercontent.com/u/26022173?v=4" width="100;" alt="PawlakMarek"/>
+            <br />
+            <sub><b>PawlakMarek</b></sub>
+        </a>
+    </td>
+    <td align="center">
+        <a href="https://github.com/DrMcCoy">
+            <img src="https://avatars.githubusercontent.com/u/156130?v=4" width="100;" alt="DrMcCoy"/>
+            <br />
+            <sub><b>DrMcCoy</b></sub>
+        </a>
+    </td></tr>
+<tr>
+    <td align="center">
+        <a href="https://github.com/Xav83">
+            <img src="https://avatars.githubusercontent.com/u/6787157?v=4" width="100;" alt="Xav83"/>
+            <br />
+            <sub><b>Xav83</b></sub>
+        </a>
+    </td>
+    <td align="center">
+        <a href="https://github.com/thFrgttn">
+            <img src="https://avatars.githubusercontent.com/u/39759781?v=4" width="100;" alt="thFrgttn"/>
+            <br />
+            <sub><b>thFrgttn</b></sub>
+        </a>
+    </td>
+    <td align="center">
+        <a href="https://github.com/tlc">
+            <img src="https://avatars.githubusercontent.com/u/19436?v=4" width="100;" alt="tlc"/>
+            <br />
+            <sub><b>tlc</b></sub>
+        </a>
+    </td></tr>
+</table>
+<!-- readme: beville,davide-romanini,collaborators,contributors -end -->

build-tools/ComicTagger.desktop

@@ -3,7 +3,7 @@ Encoding=UTF-8
 Name=ComicTagger
 GenericName=Comic Metadata Editor
 Comment=A cross-platform GUI/CLI app for writing metadata to comic archives
-Exec=%%CTSCRIPT%% %F
+Exec=comictagger %F
 Icon=/usr/local/share/comictagger/app.png
 Terminal=false
 Type=Application

build-tools/comictagger.spec

@@ -9,7 +9,7 @@ block_cipher = None
 
 
 a = Analysis(
-    ["comictagger.py"],
+    ["../comictaggerlib/__main__.py"],
     pathex=[],
     binaries=[],
     datas=[],
@@ -93,15 +93,6 @@ if platform.system() not in ["Windows"]:
             "CFBundleShortVersionString": ctversion.version,
             "CFBundleVersion": ctversion.version,
             "CFBundleDocumentTypes": [
-                {
-                    "CFBundleTypeRole": "Viewer",
-                    "LSItemContentTypes": [
-                        "com.rarlab.rar-archive",
-                    ],
-                    "CFBundleTypeName": "RAR Archive",
-                    "CFBundleTypeRole": "Editor",
-                    "LSHandlerRank": "Default",
-                },
                 {
                     "CFBundleTypeRole": "Editor",
                     "LSHandlerRank": "Default",
@@ -118,7 +109,6 @@ if platform.system() not in ["Windows"]:
                     "NSPersistentStoreTypeKey": "Binary",
                     "CFBundleTypeIconSystemGenerated": True,
                     "CFBundleTypeName": "ZIP Comic Archive",
-                    # 'CFBundleTypeIconFile': 'cbz',
                     "LSItemContentTypes": [
                         "public.zip-comic-archive",
                         "com.simplecomic.cbz-archive",
@@ -129,6 +119,7 @@ if platform.system() not in ["Windows"]:
                         "com.milke.cbz-archive",
                         "com.bitcartel.comicbooklover.cbz",
                         "public.archive.cbz",
+                        "public.zip-archive",
                     ],
                     "CFBundleTypeRole": "Editor",
                     "LSHandlerRank": "Default",
@@ -141,8 +132,8 @@ if platform.system() not in ["Windows"]:
                     "NSPersistentStoreTypeKey": "Binary",
                     "CFBundleTypeIconSystemGenerated": True,
                     "CFBundleTypeName": "7-Zip Comic Archive",
-                    # 'CFBundleTypeIconFile': 'cb7',
                     "LSItemContentTypes": [
+                        "org.7-zip.7-zip-archive",
                         "com.simplecomic.cb7-archive",
                         "public.cb7-archive",
                         "com.macitbetter.cb7-archive",
@@ -160,8 +151,8 @@ if platform.system() not in ["Windows"]:
                     "NSPersistentStoreTypeKey": "Binary",
                     "CFBundleTypeIconSystemGenerated": True,
                     "CFBundleTypeName": "RAR Comic Archive",
-                    # 'CFBundleTypeIconFile': 'cbr',
                     "LSItemContentTypes": [
+                        "com.rarlab.rar-archive",
                         "com.rarlab.rar-comic-archive",
                         "com.simplecomic.cbr-archive",
                         "com.macitbetter.cbr-archive",
@@ -195,16 +186,11 @@ if platform.system() not in ["Windows"]:
                     },
                 },
                 {
-                    # 'UTTypeIcons': {
-                    #     'UTTypeIconText': 'cbr',
-                    #     'UTTypeIconBackgroundName': comic-fill
-                    # }
                     "UTTypeConformsTo": [
                         "public.data",
                         "public.archive",
                         "com.rarlab.rar-archive",
                     ],
-                    # 'UTTypeIconFile': 'cbr',
                     "UTTypeIdentifier": "com.rarlab.rar-comic-archive",
                     "UTTypeDescription": "RAR Comic Archive",
                     "UTTypeTagSpecification": {
@@ -218,16 +204,11 @@ if platform.system() not in ["Windows"]:
                     },
                 },
                 {
-                    # 'UTTypeIcons': {
-                    #     'UTTypeIconText': 'cbz',
-                    #     'UTTypeIconBackgroundName': 'comic-fill',
-                    # }
                     "UTTypeConformsTo": [
                         "public.data",
                         "public.archive",
                         "public.zip-archive",
                     ],
-                    # 'UTTypeIconFile': cbz,
                     "UTTypeIdentifier": "public.zip-comic-archive",
                     "UTTypeDescription": "ZIP Comic Archive",
                     "UTTypeTagSpecification": {
@@ -237,16 +218,11 @@ if platform.system() not in ["Windows"]:
                     },
                 },
                 {
-                    # 'UTTypeIcons': {
-                    #     'UTTypeIconText': 'cb7',
-                    #     'UTTypeIconBackgroundName': comic-fill
-                    # }
                     "UTTypeConformsTo": [
                         "public.data",
                         "public.archive",
                         "org.7-zip.7-zip-archive",
                     ],
-                    # 'UTTypeIconFile': cb7
                     "UTTypeIdentifier": "org.7-zip.7-zip-comic-archive",
                     "UTTypeDescription": "7-Zip Comic Archive",
                     "UTTypeTagSpecification": {
@@ -261,5 +237,5 @@ if platform.system() not in ["Windows"]:
                 },
             ],
         },
-        bundle_identifier=None,
+        bundle_identifier="com.comictagger",
     )

build-tools/dmgbuild.conf

@@ -0,0 +1,19 @@
+import pathlib
+
+app = "ComicTagger"
+app_name = f"{app}.app"
+path = f"dist/{app_name}"
+
+
+# dmgbuild settings
+format = 'ULMO'
+files = (str(path),)
+
+symlinks = {'Applications': '/Applications'}
+
+icon = pathlib.Path().cwd() / 'build-tools' / 'mac' / 'volume.icns'
+
+icon_locations = {
+    app_name: (100, 100),
+    'Applications': (300, 100)
+}

build-tools/generate_settngs.py

@@ -0,0 +1,24 @@
+from __future__ import annotations
+
+import pathlib
+
+import settngs
+
+import comictaggerlib.main
+
+
+def generate() -> str:
+    app = comictaggerlib.main.App()
+    app.load_plugins(app.initial_arg_parser.parse_known_args()[0])
+    app.register_settings(True)
+    imports, types = settngs.generate_dict(app.manager.definitions)
+    imports2, types2 = settngs.generate_ns(app.manager.definitions)
+    i = imports.splitlines()
+    i.extend(set(imports2.splitlines()) - set(i))
+    return "\n\n".join(("\n".join(i), types2, types))
+
+
+if __name__ == "__main__":
+    src = generate()
+    pathlib.Path("./comictaggerlib/ctsettings/settngs_namespace.py").write_text(src)
+    print(src, end="")

build-tools/get_appimage.py

@@ -0,0 +1,35 @@
+from __future__ import annotations
+
+import argparse
+import os
+import pathlib
+
+try:
+    import niquests as requests
+except ImportError:
+    import requests
+
+parser = argparse.ArgumentParser()
+parser.add_argument("APPIMAGETOOL", default="build/appimagetool-x86_64.AppImage", type=pathlib.Path, nargs="?")
+
+opts = parser.parse_args()
+opts.APPIMAGETOOL = opts.APPIMAGETOOL.absolute()
+
+
+def urlretrieve(url: str, dest: pathlib.Path) -> None:
+    resp = requests.get(url)
+    if resp.status_code == 200:
+        dest.parent.mkdir(parents=True, exist_ok=True)
+        dest.write_bytes(resp.content)
+
+
+if opts.APPIMAGETOOL.exists():
+    raise SystemExit(0)
+
+urlretrieve(
+    "https://github.com/AppImage/appimagetool/releases/latest/download/appimagetool-x86_64.AppImage", opts.APPIMAGETOOL
+)
+os.chmod(opts.APPIMAGETOOL, 0o0700)
+
+if not opts.APPIMAGETOOL.exists():
+    raise SystemExit(1)

build-tools/oidc-exchange.py

@@ -0,0 +1,267 @@
+from __future__ import annotations
+
+import argparse
+import base64
+import json
+import os
+import sys
+from http import HTTPStatus
+from pathlib import Path
+from typing import NoReturn
+from urllib.parse import urlparse
+
+import keyring
+import requests
+from id import IdentityError, detect_credential
+
+_GITHUB_STEP_SUMMARY = Path(os.getenv("GITHUB_STEP_SUMMARY", "fail.txt"))
+
+# The top-level error message that gets rendered.
+# This message wraps one of the other templates/messages defined below.
+_ERROR_SUMMARY_MESSAGE = """
+Trusted publishing exchange failure:
+
+{message}
+
+You're seeing this because the action wasn't given the inputs needed to
+perform password-based or token-based authentication. If you intended to
+perform one of those authentication methods instead of trusted
+publishing, then you should double-check your secret configuration and variable
+names.
+
+Read more about trusted publishers at https://docs.pypi.org/trusted-publishers/
+
+Read more about how this action uses trusted publishers at
+https://github.com/marketplace/actions/pypi-publish#trusted-publishing
+"""
+
+# Rendered if OIDC identity token retrieval fails for any reason.
+_TOKEN_RETRIEVAL_FAILED_MESSAGE = """
+OpenID Connect token retrieval failed: {identity_error}
+
+This generally indicates a workflow configuration error, such as insufficient
+permissions. Make sure that your workflow has `id-token: write` configured
+at the job level, e.g.:
+
+```yaml
+permissions:
+  id-token: write
+```
+
+Learn more at https://docs.github.com/en/actions/deployment/security-hardening-your-deployments/about-security-hardening-with-openid-connect#adding-permissions-settings.
+"""  # noqa: S105; not a password
+
+# Specialization of the token retrieval failure case, when we know that
+# the failure cause is use within a third-party PR.
+_TOKEN_RETRIEVAL_FAILED_FORK_PR_MESSAGE = """
+OpenID Connect token retrieval failed: {identity_error}
+
+The workflow context indicates that this action was called from a
+pull request on a fork. GitHub doesn't give these workflows OIDC permissions,
+even if `id-token: write` is explicitly configured.
+
+To fix this, change your publishing workflow to use an event that
+forks of your repository cannot trigger (such as tag or release
+creation, or a manually triggered workflow dispatch).
+"""  # noqa: S105; not a password
+
+# Rendered if the package index refuses the given OIDC token.
+_SERVER_REFUSED_TOKEN_EXCHANGE_MESSAGE = """
+Token request failed: the server refused the request for the following reasons:
+
+{reasons}
+
+This generally indicates a trusted publisher configuration error, but could
+also indicate an internal error on GitHub or PyPI's part.
+
+{rendered_claims}
+"""  # noqa: S105; not a password
+
+_RENDERED_CLAIMS = """
+The claims rendered below are **for debugging purposes only**. You should **not**
+use them to configure a trusted publisher unless they already match your expectations.
+
+If a claim is not present in the claim set, then it is rendered as `MISSING`.
+
+* `sub`: `{sub}`
+* `repository`: `{repository}`
+* `repository_owner`: `{repository_owner}`
+* `repository_owner_id`: `{repository_owner_id}`
+* `job_workflow_ref`: `{job_workflow_ref}`
+* `ref`: `{ref}`
+
+See https://docs.pypi.org/trusted-publishers/troubleshooting/ for more help.
+"""
+
+# Rendered if the package index's token response isn't valid JSON.
+_SERVER_TOKEN_RESPONSE_MALFORMED_JSON = """
+Token request failed: the index produced an unexpected
+{status_code} response.
+
+This strongly suggests a server configuration or downtime issue; wait
+a few minutes and try again.
+
+You can monitor PyPI's status here: https://status.python.org/
+"""  # noqa: S105; not a password
+
+# Rendered if the package index's token response isn't a valid API token payload.
+_SERVER_TOKEN_RESPONSE_MALFORMED_MESSAGE = """
+Token response error: the index gave us an invalid response.
+
+This strongly suggests a server configuration or downtime issue; wait
+a few minutes and try again.
+"""  # noqa: S105; not a password
+
+
+def die(msg: str) -> NoReturn:
+    with _GITHUB_STEP_SUMMARY.open("a", encoding="utf-8") as io:
+        print(_ERROR_SUMMARY_MESSAGE.format(message=msg), file=io)
+
+    # HACK: GitHub Actions' annotations don't work across multiple lines naively;
+    # translating `\n` into `%0A` (i.e., HTML percent-encoding) is known to work.
+    # See: https://github.com/actions/toolkit/issues/193
+    msg = msg.replace("\n", "%0A")
+    print(f"::error::Trusted publishing exchange failure: {msg}", file=sys.stderr)
+    sys.exit(1)
+
+
+def debug(msg: str) -> None:
+    print(f"::debug::{msg.title()}", file=sys.stderr)
+
+
+def assert_successful_audience_call(resp: requests.Response, domain: str) -> None:
+    if resp.ok:
+        return
+
+    if resp.status_code == HTTPStatus.FORBIDDEN:
+        # This index supports OIDC, but forbids the client from using
+        # it (either because it's disabled, ratelimited, etc.)
+        die(
+            f"audience retrieval failed: repository at {domain} has trusted publishing disabled",
+        )
+    elif resp.status_code == HTTPStatus.NOT_FOUND:
+        # This index does not support OIDC.
+        die(
+            f"audience retrieval failed: repository at {domain} does not indicate trusted publishing support",
+        )
+    else:
+        status = HTTPStatus(resp.status_code)
+        # Unknown: the index may or may not support OIDC, but didn't respond with
+        # something we expect. This can happen if the index is broken, in maintenance mode,
+        # misconfigured, etc.
+        die(
+            f"audience retrieval failed: repository at {domain} responded with unexpected {resp.status_code}: {status.phrase}",
+        )
+
+
+def render_claims(token: str) -> str:
+    _, payload, _ = token.split(".", 2)
+
+    # urlsafe_b64decode needs padding; JWT payloads don't contain any.
+    payload += "=" * (4 - (len(payload) % 4))
+    claims = json.loads(base64.urlsafe_b64decode(payload))
+
+    def _get(name: str) -> str:
+        return claims.get(name, "MISSING")
+
+    return _RENDERED_CLAIMS.format(
+        sub=_get("sub"),
+        repository=_get("repository"),
+        repository_owner=_get("repository_owner"),
+        repository_owner_id=_get("repository_owner_id"),
+        job_workflow_ref=_get("job_workflow_ref"),
+        ref=_get("ref"),
+    )
+
+
+def event_is_third_party_pr() -> bool:
+    # Non-`pull_request` events cannot be from third-party PRs.
+    if os.getenv("GITHUB_EVENT_NAME") != "pull_request":
+        return False
+
+    event_path = os.getenv("GITHUB_EVENT_PATH")
+    if not event_path:
+        # No GITHUB_EVENT_PATH indicates a weird GitHub or runner bug.
+        debug("unexpected: no GITHUB_EVENT_PATH to check")
+        return False
+
+    try:
+        event = json.loads(Path(event_path).read_bytes())
+    except json.JSONDecodeError:
+        debug("unexpected: GITHUB_EVENT_PATH does not contain valid JSON")
+        return False
+
+    try:
+        return event["pull_request"]["head"]["repo"]["fork"]
+    except KeyError:
+        return False
+
+
+parser = argparse.ArgumentParser()
+parser.add_argument("repository_url", default="https://upload.pypi.org/legacy/", type=urlparse, nargs="?")
+
+opts = parser.parse_args()
+repository_domain = opts.repository_url.netloc
+token_exchange_url = f"https://{repository_domain}/_/oidc/mint-token"
+
+# Indices are expected to support `https://{domain}/_/oidc/audience`,
+# which tells OIDC exchange clients which audience to use.
+audience_url = f"https://{repository_domain}/_/oidc/audience"
+audience_resp = requests.get(audience_url, timeout=5)
+assert_successful_audience_call(audience_resp, repository_domain)
+
+oidc_audience = audience_resp.json()["audience"]
+
+debug(f"selected trusted publishing exchange endpoint: {token_exchange_url}")
+
+try:
+    oidc_token = detect_credential(audience=oidc_audience)
+except IdentityError as identity_error:
+    cause_msg_tmpl = (
+        _TOKEN_RETRIEVAL_FAILED_FORK_PR_MESSAGE if event_is_third_party_pr() else _TOKEN_RETRIEVAL_FAILED_MESSAGE
+    )
+    for_cause_msg = cause_msg_tmpl.format(identity_error=identity_error)
+    die(for_cause_msg)
+if not oidc_token:
+    die("Unabled to detect credentials. Is this runnnig in CI?")
+
+# Now we can do the actual token exchange.
+mint_token_resp = requests.post(
+    token_exchange_url,
+    json={"token": oidc_token},
+    timeout=5,
+)
+
+try:
+    mint_token_payload = mint_token_resp.json()
+except requests.JSONDecodeError:
+    # Token exchange failure normally produces a JSON error response, but
+    # we might have hit a server error instead.
+    die(
+        _SERVER_TOKEN_RESPONSE_MALFORMED_JSON.format(
+            status_code=mint_token_resp.status_code,
+        ),
+    )
+
+# On failure, the JSON response includes the list of errors that
+# occurred during minting.
+if not mint_token_resp.ok:
+    reasons = "\n".join(f'* `{error["code"]}`: {error["description"]}' for error in mint_token_payload["errors"])
+
+    rendered_claims = render_claims(oidc_token)
+
+    die(
+        _SERVER_REFUSED_TOKEN_EXCHANGE_MESSAGE.format(
+            reasons=reasons,
+            rendered_claims=rendered_claims,
+        ),
+    )
+
+pypi_token = mint_token_payload.get("token")
+if pypi_token is None:
+    die(_SERVER_TOKEN_RESPONSE_MALFORMED_MESSAGE)
+
+# Mask the newly minted PyPI token, so that we don't accidentally leak it in logs.
+print(f"::add-mask::{pypi_token}", file=sys.stderr)
+
+keyring.set_password(opts.repository_url.geturl(), "__token__", pypi_token)

build-tools/zip_artifacts.py

@@ -0,0 +1,90 @@
+from __future__ import annotations
+
+import os
+import pathlib
+import platform
+import sys
+import tarfile
+import zipfile
+
+from comictaggerlib.ctversion import __version__
+
+
+def addToZip(zf: zipfile.ZipFile, path: str, zippath: str) -> None:
+    if os.path.isfile(path):
+        zf.write(path, zippath)
+    elif os.path.isdir(path):
+        if zippath:
+            zf.write(path, zippath)
+        for nm in sorted(os.listdir(path)):
+            addToZip(zf, os.path.join(path, nm), os.path.join(zippath, nm))
+
+
+def Zip(zip_file: pathlib.Path, path: pathlib.Path) -> None:
+    zip_file.unlink(missing_ok=True)
+    with zipfile.ZipFile(f"{zip_file}.zip", "w", compression=zipfile.ZIP_DEFLATED, compresslevel=8) as zf:
+        zippath = os.path.basename(path)
+        if not zippath:
+            zippath = os.path.basename(os.path.dirname(path))
+        if zippath in ("", os.curdir, os.pardir):
+            zippath = ""
+        addToZip(zf, str(path), zippath)
+
+
+def addToTar(tf: tarfile.TarFile, path: str, zippath: str) -> None:
+    if os.path.isfile(path):
+        tf.add(path, zippath)
+    elif os.path.isdir(path):
+        if zippath:
+            tf.add(path, zippath, recursive=False)
+        for nm in sorted(os.listdir(path)):
+            addToTar(tf, os.path.join(path, nm), os.path.join(zippath, nm))
+
+
+def Tar(tar_file: pathlib.Path, path: pathlib.Path) -> None:
+    tar_file.unlink(missing_ok=True)
+    with tarfile.open(f"{tar_file}.tar.gz", "w:gz") as tf:
+        zippath = os.path.basename(path)
+        if not zippath:
+            zippath = os.path.basename(os.path.dirname(path))
+        if zippath in ("", os.curdir, os.pardir):
+            zippath = ""
+        addToTar(tf, str(path), zippath)
+
+
+if __name__ == "__main__":
+    app = "ComicTagger"
+    exe = app.casefold()
+    if platform.system() == "Windows":
+        os_version = f"win-{platform.machine()}"
+        app_name = f"{exe}.exe"
+        final_name = f"{app}-{__version__}-{os_version}.exe"
+    elif platform.system() == "Darwin":
+        ver = platform.mac_ver()
+        os_version = f"osx-{ver[0]}-{ver[2]}"
+        app_name = f"{app}.app"
+        final_name = f"{app}-{__version__}-{os_version}"
+    else:
+        app_name = exe
+        final_name = f"ComicTagger-{__version__}-{platform.system()}"
+
+    path = pathlib.Path(f"dist/{app_name}")
+    binary_path = pathlib.Path("dist/binary")
+    binary_path.mkdir(parents=True, exist_ok=True)
+    archive_destination = binary_path / final_name
+
+    if platform.system() == "Darwin":
+        from dmgbuild.__main__ import main as dmg_main
+
+        sys.argv = [
+            "zip_artifacts",
+            "-s",
+            str(pathlib.Path(__file__).parent / "dmgbuild.conf"),
+            f"{app} {__version__}",
+            f"{archive_destination}.dmg",
+        ]
+        dmg_main()
+    elif platform.system() == "Windows":
+        Zip(archive_destination, path)
+    else:
+        Tar(archive_destination, path)

comicapi/__pyinstaller/hook-comicapi.py

@@ -1,6 +1,10 @@
 from __future__ import annotations
 
-from PyInstaller.utils.hooks import collect_data_files
+from PyInstaller.utils.hooks import collect_data_files, collect_entry_point
 
-datas = []
+datas, hiddenimports = collect_entry_point("comicapi.archiver")
+mdatas, mhiddenimports = collect_entry_point("comicapi.tags")
+
+hiddenimports += mhiddenimports
+datas += mdatas
 datas += collect_data_files("comicapi.data")

comicapi/_url.py

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

comicapi/archivers/__init__.py

@@ -0,0 +1,13 @@
+from __future__ import annotations
+
+from comicapi.archivers.archiver import Archiver
+from comicapi.archivers.folder import FolderArchiver
+from comicapi.archivers.zip import ZipArchiver
+
+
+class UnknownArchiver(Archiver):
+    def name(self) -> str:
+        return "Unknown"
+
+
+__all__ = ["Archiver", "UnknownArchiver", "FolderArchiver", "ZipArchiver"]

comicapi/archivers/archiver.py

@@ -0,0 +1,137 @@
+from __future__ import annotations
+
+import pathlib
+from typing import Protocol, runtime_checkable
+
+
+@runtime_checkable
+class Archiver(Protocol):
+    """Archiver Protocol"""
+
+    """The path to the archive"""
+    path: pathlib.Path
+
+    """
+    The name of the executable used for this archiver. This should be the base name of the executable.
+    For example if 'rar.exe' is needed this should be "rar".
+    If an executable is not used this should be the empty string.
+    """
+    exe: str = ""
+
+    """
+    Whether or not this archiver is enabled.
+    If external imports are required and are not available this should be false. See rar.py and sevenzip.py.
+    """
+    enabled: bool = True
+
+    def __init__(self) -> None:
+        self.path = pathlib.Path()
+
+    def get_comment(self) -> str:
+        """
+        Returns the comment from the current archive as a string.
+        Should always return a string. If comments are not supported in the archive the empty string should be returned.
+        """
+        return ""
+
+    def set_comment(self, comment: str) -> bool:
+        """
+        Returns True if the comment was successfully set on the current archive.
+        Should always return a boolean. If comments are not supported in the archive False should be returned.
+        """
+        return False
+
+    def supports_comment(self) -> bool:
+        """
+        Returns True if the current archive supports comments.
+        Should always return a boolean. If comments are not supported in the archive False should be returned.
+        """
+        return False
+
+    def read_file(self, archive_file: str) -> bytes:
+        """
+        Reads the named file from the current archive.
+        archive_file should always come from the output of get_filename_list.
+        Should always return a bytes object. Exceptions should be of the type OSError.
+        """
+        raise NotImplementedError
+
+    def remove_file(self, archive_file: str) -> bool:
+        """
+        Removes the named file from the current archive.
+        archive_file should always come from the output of get_filename_list.
+        Should always return a boolean. Failures should return False.
+
+        Rebuilding the archive without the named file is a standard way to remove a file.
+        """
+        return False
+
+    def write_file(self, archive_file: str, data: bytes) -> bool:
+        """
+        Writes the named file to the current archive.
+        Should always return a boolean. Failures should return False.
+        """
+        return False
+
+    def get_filename_list(self) -> list[str]:
+        """
+        Returns a list of filenames in the current archive.
+        Should always return a list of string. Failures should return an empty list.
+        """
+        return []
+
+    def supports_files(self) -> bool:
+        """
+        Returns True if the current archive supports arbitrary non-picture files.
+        Should always return a boolean.
+        If arbitrary non-picture files are not supported in the archive False should be returned.
+        """
+        return False
+
+    def copy_from_archive(self, other_archive: Archiver) -> bool:
+        """
+        Copies the contents of another achive to the current archive.
+        Should always return a boolean. Failures should return False.
+        """
+        return False
+
+    def is_writable(self) -> bool:
+        """
+        Retuns True if the current archive is writeable
+        Should always return a boolean. Failures should return False.
+        """
+        return False
+
+    def extension(self) -> str:
+        """
+        Returns the extension that this archiver should use eg ".cbz".
+        Should always return a string. Failures should return the empty string.
+        """
+        return ""
+
+    def name(self) -> str:
+        """
+        Returns the name of this archiver for display purposes eg "CBZ".
+        Should always return a string. Failures should return the empty string.
+        """
+        return ""
+
+    @classmethod
+    def is_valid(cls, path: pathlib.Path) -> bool:
+        """
+        Returns True if the given path can be opened by this archiver.
+        Should always return a boolean. Failures should return False.
+        """
+        return False
+
+    @classmethod
+    def open(cls, path: pathlib.Path) -> Archiver:
+        """
+        Opens the given archive.
+        Should always return a an Archver.
+        Should never cause an exception no file operations should take place in this method,
+        is_valid will always be called before open.
+        """
+        archiver = cls()
+        archiver.path = path
+        return archiver

comicapi/archivers/folder.py

@@ -0,0 +1,104 @@
+from __future__ import annotations
+
+import logging
+import os
+import pathlib
+
+from comicapi.archivers import Archiver
+
+logger = logging.getLogger(__name__)
+
+
+class FolderArchiver(Archiver):
+    """Folder implementation"""
+
+    def __init__(self) -> None:
+        super().__init__()
+        self.comment_file_name = "ComicTaggerFolderComment.txt"
+
+    def get_comment(self) -> str:
+        try:
+            return (self.path / self.comment_file_name).read_text()
+        except OSError:
+            return ""
+
+    def set_comment(self, comment: str) -> bool:
+        if (self.path / self.comment_file_name).exists() or comment:
+            return self.write_file(self.comment_file_name, comment.encode("utf-8"))
+        return True
+
+    def supports_comment(self) -> bool:
+        return True
+
+    def read_file(self, archive_file: str) -> bytes:
+        try:
+            data = (self.path / archive_file).read_bytes()
+        except OSError as e:
+            logger.error("Error reading folder archive [%s]: %s :: %s", e, self.path, archive_file)
+            raise
+
+        return data
+
+    def remove_file(self, archive_file: str) -> bool:
+        try:
+            (self.path / archive_file).unlink(missing_ok=True)
+        except OSError as e:
+            logger.error("Error removing file for folder archive [%s]: %s :: %s", e, self.path, archive_file)
+            return False
+        else:
+            return True
+
+    def write_file(self, archive_file: str, data: bytes) -> bool:
+        try:
+            file_path = self.path / archive_file
+            file_path.parent.mkdir(exist_ok=True, parents=True)
+            with open(self.path / archive_file, mode="wb") as f:
+                f.write(data)
+        except OSError as e:
+            logger.error("Error writing folder archive [%s]: %s :: %s", e, self.path, archive_file)
+            return False
+        else:
+            return True
+
+    def get_filename_list(self) -> list[str]:
+        filenames = []
+        try:
+            for root, _dirs, files in os.walk(self.path):
+                for f in files:
+                    filenames.append(os.path.relpath(os.path.join(root, f), self.path).replace(os.path.sep, "/"))
+            return filenames
+        except OSError as e:
+            logger.error("Error listing files in folder archive [%s]: %s", e, self.path)
+            return []
+
+    def supports_files(self) -> bool:
+        return True
+
+    def copy_from_archive(self, other_archive: Archiver) -> bool:
+        """Replace the current zip with one copied from another archive"""
+        try:
+            for filename in other_archive.get_filename_list():
+                data = other_archive.read_file(filename)
+                if data is not None:
+                    self.write_file(filename, data)
+
+            # preserve the old comment
+            comment = other_archive.get_comment()
+            if comment is not None:
+                if not self.set_comment(comment):
+                    return False
+        except Exception:
+            logger.exception("Error while copying archive from %s to %s", other_archive.path, self.path)
+            return False
+        else:
+            return True
+
+    def is_writable(self) -> bool:
+        return True
+
+    def name(self) -> str:
+        return "Folder"
+
+    @classmethod
+    def is_valid(cls, path: pathlib.Path) -> bool:
+        return path.is_dir()

comicapi/archivers/rar.py

@@ -0,0 +1,324 @@
+from __future__ import annotations
+
+import logging
+import os
+import pathlib
+import platform
+import shutil
+import subprocess
+import tempfile
+import time
+
+from comicapi.archivers import Archiver
+
+try:
+    import rarfile
+
+    rar_support = True
+except ImportError:
+    rar_support = False
+
+
+logger = logging.getLogger(__name__)
+
+if not rar_support:
+    logger.error("rar unavailable")
+
+
+class RarArchiver(Archiver):
+    """RAR implementation"""
+
+    enabled = rar_support
+    exe = "rar"
+
+    def __init__(self) -> None:
+        super().__init__()
+
+        # windows only, keeps the cmd.exe from popping up
+        if platform.system() == "Windows":
+            self.startupinfo = subprocess.STARTUPINFO()  # type: ignore
+            self.startupinfo.dwFlags |= subprocess.STARTF_USESHOWWINDOW  # type: ignore
+        else:
+            self.startupinfo = None
+
+    def get_comment(self) -> str:
+        rarc = self.get_rar_obj()
+        return (rarc.comment if rarc else "") or ""
+
+    def set_comment(self, comment: str) -> bool:
+        if rar_support and self.exe:
+            try:
+                # write comment to temp file
+                with tempfile.TemporaryDirectory() as tmp_dir:
+                    tmp_file = pathlib.Path(tmp_dir) / "rar_comment.txt"
+                    tmp_file.write_text(comment, encoding="utf-8")
+
+                    working_dir = os.path.dirname(os.path.abspath(self.path))
+
+                    # use external program to write comment to Rar archive
+                    proc_args = [
+                        self.exe,
+                        "c",
+                        f"-w{working_dir}",
+                        "-c-",
+                        f"-z{tmp_file}",
+                        str(self.path),
+                    ]
+                    result = subprocess.run(
+                        proc_args,
+                        startupinfo=self.startupinfo,
+                        stdin=subprocess.DEVNULL,
+                        capture_output=True,
+                        encoding="utf-8",
+                        cwd=tmp_dir,
+                    )
+                if result.returncode != 0:
+                    logger.error(
+                        "Error writing comment to rar archive [exitcode: %d]: %s :: %s",
+                        result.returncode,
+                        self.path,
+                        result.stderr,
+                    )
+                    return False
+
+                if platform.system() == "Darwin":
+                    time.sleep(1)
+            except OSError as e:
+                logger.exception("Error writing comment to rar archive [%s]: %s", e, self.path)
+                return False
+            else:
+                return True
+        else:
+            return False
+
+    def supports_comment(self) -> bool:
+        return True
+
+    def read_file(self, archive_file: str) -> bytes:
+        rarc = self.get_rar_obj()
+        if rarc is None:
+            return b""
+
+        tries = 0
+        while tries < 7:
+            try:
+                tries = tries + 1
+                data: bytes = rarc.open(archive_file).read()
+                entries = [(rarc.getinfo(archive_file), data)]
+
+                if entries[0][0].file_size != len(entries[0][1]):
+                    logger.info(
+                        "Error reading rar archive [file is not expected size: %d vs %d]  %s :: %s :: tries #%d",
+                        entries[0][0].file_size,
+                        len(entries[0][1]),
+                        self.path,
+                        archive_file,
+                        tries,
+                    )
+                    continue
+
+            except OSError as e:
+                logger.error("Error reading rar archive [%s]: %s :: %s :: tries #%d", e, self.path, archive_file, tries)
+                time.sleep(1)
+            except Exception as e:
+                logger.error(
+                    "Unexpected exception reading rar archive [%s]: %s :: %s :: tries #%d",
+                    e,
+                    self.path,
+                    archive_file,
+                    tries,
+                )
+                break
+
+            else:
+                # Success. Entries is a list of of tuples:  ( rarinfo, filedata)
+                if len(entries) == 1:
+                    return entries[0][1]
+
+                raise OSError
+
+        raise OSError
+
+    def remove_file(self, archive_file: str) -> bool:
+        if self.exe:
+            working_dir = os.path.dirname(os.path.abspath(self.path))
+            # use external program to remove file from Rar archive
+            result = subprocess.run(
+                [self.exe, "d", f"-w{working_dir}", "-c-", self.path, archive_file],
+                startupinfo=self.startupinfo,
+                stdin=subprocess.DEVNULL,
+                capture_output=True,
+                encoding="utf-8",
+                cwd=self.path.absolute().parent,
+            )
+
+            if platform.system() == "Darwin":
+                time.sleep(1)
+            if result.returncode != 0:
+                logger.error(
+                    "Error removing file from rar archive [exitcode: %d]: %s :: %s",
+                    result.returncode,
+                    self.path,
+                    archive_file,
+                )
+                return False
+            return True
+        else:
+            return False
+
+    def write_file(self, archive_file: str, data: bytes) -> bool:
+        if self.exe:
+            archive_path = pathlib.PurePosixPath(archive_file)
+            archive_name = archive_path.name
+            archive_parent = str(archive_path.parent).lstrip("./")
+            working_dir = os.path.dirname(os.path.abspath(self.path))
+
+            # use external program to write file to Rar archive
+            result = subprocess.run(
+                [
+                    self.exe,
+                    "a",
+                    f"-w{working_dir}",
+                    f"-si{archive_name}",
+                    f"-ap{archive_parent}",
+                    "-c-",
+                    "-ep",
+                    self.path,
+                ],
+                input=data,
+                startupinfo=self.startupinfo,
+                capture_output=True,
+                cwd=self.path.absolute().parent,
+            )
+
+            if platform.system() == "Darwin":
+                time.sleep(1)
+            if result.returncode != 0:
+                logger.error(
+                    "Error writing rar archive [exitcode: %d]: %s :: %s :: %s",
+                    result.returncode,
+                    self.path,
+                    archive_file,
+                    result.stderr,
+                )
+                return False
+            else:
+                return True
+        else:
+            return False
+
+    def get_filename_list(self) -> list[str]:
+        rarc = self.get_rar_obj()
+        tries = 0
+        if rar_support and rarc:
+            while tries < 7:
+                try:
+                    tries = tries + 1
+                    namelist = []
+                    for item in rarc.infolist():
+                        if item.file_size != 0:
+                            namelist.append(item.filename)
+
+                except OSError as e:
+                    logger.error("Error listing files in rar archive [%s]: %s :: attempt #%d", e, self.path, tries)
+                    time.sleep(1)
+
+                else:
+                    return namelist
+        return []
+
+    def supports_files(self) -> bool:
+        return True
+
+    def copy_from_archive(self, other_archive: Archiver) -> bool:
+        """Replace the current archive with one copied from another archive"""
+        try:
+            with tempfile.TemporaryDirectory() as tmp_dir:
+                tmp_path = pathlib.Path(tmp_dir)
+                rar_cwd = tmp_path / "rar"
+                rar_cwd.mkdir(exist_ok=True)
+                rar_path = (tmp_path / self.path.name).with_suffix(".rar")
+                working_dir = os.path.dirname(os.path.abspath(self.path))
+
+                for filename in other_archive.get_filename_list():
+                    (rar_cwd / filename).parent.mkdir(exist_ok=True, parents=True)
+                    data = other_archive.read_file(filename)
+                    if data is not None:
+                        with open(rar_cwd / filename, mode="w+b") as tmp_file:
+                            tmp_file.write(data)
+                result = subprocess.run(
+                    [self.exe, "a", f"-w{working_dir}", "-r", "-c-", str(rar_path.absolute()), "."],
+                    cwd=rar_cwd.absolute(),
+                    startupinfo=self.startupinfo,
+                    stdin=subprocess.DEVNULL,
+                    capture_output=True,
+                    encoding="utf-8",
+                )
+                if result.returncode != 0:
+                    logger.error(
+                        "Error while copying to rar archive [exitcode: %d]: %s: %s",
+                        result.returncode,
+                        self.path,
+                        result.stderr,
+                    )
+                    return False
+
+                self.path.unlink(missing_ok=True)
+                shutil.move(rar_path, self.path)
+        except Exception as e:
+            logger.exception("Error while copying to rar archive [%s]: from %s to %s", e, other_archive.path, self.path)
+            return False
+        else:
+            return True
+
+    def is_writable(self) -> bool:
+        try:
+            if bool(self.exe and (os.path.exists(self.exe) or shutil.which(self.exe))):
+                return (
+                    subprocess.run(
+                        (self.exe,),
+                        startupinfo=self.startupinfo,
+                        capture_output=True,
+                        cwd=self.path.absolute().parent,
+                    )
+                    .stdout.strip()
+                    .startswith(b"RAR")
+                )
+        except OSError:
+            ...
+        return False
+
+    def extension(self) -> str:
+        return ".cbr"
+
+    def name(self) -> str:
+        return "RAR"
+
+    @classmethod
+    def is_valid(cls, path: pathlib.Path) -> bool:
+        if rar_support:
+            # Try using exe
+            orig = rarfile.UNRAR_TOOL
+            rarfile.UNRAR_TOOL = cls.exe
+            try:
+                return rarfile.is_rarfile(str(path)) and rarfile.tool_setup(sevenzip=False, sevenzip2=False, force=True)
+            except rarfile.RarCannotExec:
+                rarfile.UNRAR_TOOL = orig
+
+            # Fallback to standard
+            try:
+                return rarfile.is_rarfile(str(path)) and rarfile.tool_setup(force=True)
+            except rarfile.RarCannotExec as e:
+                logger.info(e)
+        return False
+
+    def get_rar_obj(self) -> rarfile.RarFile | None:
+        if rar_support:
+            try:
+                rarc = rarfile.RarFile(str(self.path))
+            except (OSError, rarfile.RarFileError) as e:
+                logger.error("Unable to get rar object [%s]: %s", e, self.path)
+            else:
+                return rarc
+
+        return None

comicapi/archivers/sevenzip.py

@@ -0,0 +1,134 @@
+from __future__ import annotations
+
+import logging
+import os
+import pathlib
+import shutil
+import tempfile
+
+from comicapi.archivers import Archiver
+
+try:
+    import py7zr
+
+    z7_support = True
+except ImportError:
+    z7_support = False
+
+logger = logging.getLogger(__name__)
+
+
+class SevenZipArchiver(Archiver):
+    """7Z implementation"""
+
+    enabled = z7_support
+
+    def __init__(self) -> None:
+        super().__init__()
+
+    # @todo: Implement Comment?
+    def get_comment(self) -> str:
+        return ""
+
+    def set_comment(self, comment: str) -> bool:
+        return False
+
+    def read_file(self, archive_file: str) -> bytes:
+        data = b""
+        try:
+            with py7zr.SevenZipFile(self.path, "r") as zf:
+                data = zf.read([archive_file])[archive_file].read()
+        except (py7zr.Bad7zFile, OSError) as e:
+            logger.error("Error reading 7zip archive [%s]: %s :: %s", e, self.path, archive_file)
+            raise
+
+        return data
+
+    def remove_file(self, archive_file: str) -> bool:
+        return self.rebuild([archive_file])
+
+    def write_file(self, archive_file: str, data: bytes) -> bool:
+        # At the moment, no other option but to rebuild the whole
+        # archive w/o the indicated file. Very sucky, but maybe
+        # another solution can be found
+        files = self.get_filename_list()
+        if archive_file in files:
+            if not self.rebuild([archive_file]):
+                return False
+
+        try:
+            # now just add the archive file as a new one
+            with py7zr.SevenZipFile(self.path, "a") as zf:
+                zf.writestr(data, archive_file)
+            return True
+        except (py7zr.Bad7zFile, OSError) as e:
+            logger.error("Error writing 7zip archive [%s]: %s :: %s", e, self.path, archive_file)
+            return False
+
+    def get_filename_list(self) -> list[str]:
+        try:
+            with py7zr.SevenZipFile(self.path, "r") as zf:
+                namelist: list[str] = [file.filename for file in zf.list() if not file.is_directory]
+
+            return namelist
+        except (py7zr.Bad7zFile, OSError) as e:
+            logger.error("Error listing files in 7zip archive [%s]: %s", e, self.path)
+            return []
+
+    def supports_files(self) -> bool:
+        return True
+
+    def rebuild(self, exclude_list: list[str]) -> bool:
+        """Zip helper func
+
+        This recompresses the zip archive, without the files in the exclude_list
+        """
+
+        try:
+            # py7zr treats all archives as if they used solid compression
+            # so we need to get the filename list first to read all the files at once
+            with py7zr.SevenZipFile(self.path, mode="r") as zin:
+                targets = [f for f in zin.getnames() if f not in exclude_list]
+            with tempfile.NamedTemporaryFile(dir=os.path.dirname(self.path), delete=False) as tmp_file:
+                with py7zr.SevenZipFile(tmp_file.file, mode="w") as zout:
+                    with py7zr.SevenZipFile(self.path, mode="r") as zin:
+                        for filename, buffer in zin.read(targets).items():
+                            zout.writef(buffer, filename)
+
+                self.path.unlink(missing_ok=True)
+                tmp_file.close()  # Required on windows
+
+                shutil.move(tmp_file.name, self.path)
+        except (py7zr.Bad7zFile, OSError) as e:
+            logger.error("Error rebuilding 7zip file [%s]: %s", e, self.path)
+            return False
+        return True
+
+    def copy_from_archive(self, other_archive: Archiver) -> bool:
+        """Replace the current zip with one copied from another archive"""
+        try:
+            with py7zr.SevenZipFile(self.path, "w") as zout:
+                for filename in other_archive.get_filename_list():
+                    data = other_archive.read_file(
+                        filename
+                    )  # This will be very inefficient if other_archive is a 7z file
+                    if data is not None:
+                        zout.writestr(data, filename)
+        except Exception as e:
+            logger.error("Error while copying to 7zip archive [%s]: from %s to %s", e, other_archive.path, self.path)
+            return False
+        else:
+            return True
+
+    def is_writable(self) -> bool:
+        return True
+
+    def extension(self) -> str:
+        return ".cb7"
+
+    def name(self) -> str:
+        return "Seven Zip"
+
+    @classmethod
+    def is_valid(cls, path: pathlib.Path) -> bool:
+        return py7zr.is_7zfile(path)

comicapi/archivers/zip.py

@@ -0,0 +1,248 @@
+from __future__ import annotations
+
+import logging
+import os
+import pathlib
+import shutil
+import tempfile
+import zipfile
+from typing import cast
+
+import chardet
+
+from comicapi.archivers import Archiver
+
+logger = logging.getLogger(__name__)
+
+
+class ZipArchiver(Archiver):
+    """ZIP implementation"""
+
+    def __init__(self) -> None:
+        super().__init__()
+
+    def supports_comment(self) -> bool:
+        return True
+
+    def get_comment(self) -> str:
+        with zipfile.ZipFile(self.path, "r") as zf:
+            encoding = chardet.detect(zf.comment, True)
+            if encoding["confidence"] > 60:
+                try:
+                    comment = zf.comment.decode(encoding["encoding"])
+                except UnicodeDecodeError:
+                    comment = zf.comment.decode("utf-8", errors="replace")
+            else:
+                comment = zf.comment.decode("utf-8", errors="replace")
+        return comment
+
+    def set_comment(self, comment: str) -> bool:
+        with zipfile.ZipFile(self.path, mode="a") as zf:
+            zf.comment = bytes(comment, "utf-8")
+        return True
+
+    def read_file(self, archive_file: str) -> bytes:
+        with zipfile.ZipFile(self.path, mode="r") as zf:
+            try:
+                data = zf.read(archive_file)
+            except (zipfile.BadZipfile, OSError) as e:
+                logger.exception("Error reading zip archive [%s]: %s :: %s", e, self.path, archive_file)
+                raise
+        return data
+
+    def remove_file(self, archive_file: str) -> bool:
+        return self.rebuild([archive_file])
+
+    def write_file(self, archive_file: str, data: bytes) -> bool:
+        # At the moment, no other option but to rebuild the whole
+        # zip archive w/o the indicated file. Very sucky, but maybe
+        # another solution can be found
+        files = self.get_filename_list()
+
+        try:
+            # now just add the archive file as a new one
+            with zipfile.ZipFile(self.path, mode="a", allowZip64=True, compression=zipfile.ZIP_DEFLATED) as zf:
+                _patch_zipfile(zf)
+                if archive_file in files:
+                    zf.remove(archive_file)  # type: ignore
+                zf.writestr(archive_file, data)
+            return True
+        except (zipfile.BadZipfile, OSError) as e:
+            logger.error("Error writing zip archive [%s]: %s :: %s", e, self.path, archive_file)
+            return False
+
+    def get_filename_list(self) -> list[str]:
+        try:
+            with zipfile.ZipFile(self.path, mode="r") as zf:
+                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)
+            return []
+
+    def supports_files(self) -> bool:
+        return True
+
+    def rebuild(self, exclude_list: list[str]) -> bool:
+        """Zip helper func
+
+        This recompresses the zip archive, without the files in the exclude_list
+        """
+        try:
+            with zipfile.ZipFile(
+                tempfile.NamedTemporaryFile(dir=os.path.dirname(self.path), delete=False), "w", allowZip64=True
+            ) as zout:
+                with zipfile.ZipFile(self.path, mode="r") as zin:
+                    for item in zin.infolist():
+                        buffer = zin.read(item.filename)
+                        if item.filename not in exclude_list:
+                            zout.writestr(item, buffer)
+
+                    # preserve the old comment
+                    zout.comment = zin.comment
+
+                # replace with the new file
+                self.path.unlink(missing_ok=True)
+                zout.close()  # Required on windows
+
+                shutil.move(cast(str, zout.filename), self.path)
+
+        except (zipfile.BadZipfile, OSError) as e:
+            logger.error("Error rebuilding zip file [%s]: %s", e, self.path)
+            return False
+        return True
+
+    def copy_from_archive(self, other_archive: Archiver) -> bool:
+        """Replace the current zip with one copied from another archive"""
+        try:
+            with zipfile.ZipFile(self.path, mode="w", allowZip64=True) as zout:
+                for filename in other_archive.get_filename_list():
+                    data = other_archive.read_file(filename)
+                    if data is not None:
+                        zout.writestr(filename, data)
+
+            # preserve the old comment
+            comment = other_archive.get_comment()
+            if comment is not None:
+                if not self.set_comment(comment):
+                    return False
+        except Exception as e:
+            logger.error("Error while copying to zip archive [%s]: from %s to %s", e, other_archive.path, self.path)
+            return False
+        else:
+            return True
+
+    def is_writable(self) -> bool:
+        return True
+
+    def extension(self) -> str:
+        return ".cbz"
+
+    def name(self) -> str:
+        return "ZIP"
+
+    @classmethod
+    def is_valid(cls, path: pathlib.Path) -> bool:
+        if not zipfile.is_zipfile(path):  # only checks central directory ot the end of the archive
+            return False
+        try:
+            # test all the files in the zip. adds about 0.1 to execution time per zip
+            with zipfile.ZipFile(path) as zf:
+                for zipinfo in zf.filelist:
+                    zf.open(zipinfo).close()
+            return True
+        except Exception:
+            return False
+
+
+def _patch_zipfile(zf):  # type: ignore
+    zf.remove = _zip_remove.__get__(zf, zipfile.ZipFile)
+    zf._remove_members = _zip_remove_members.__get__(zf, zipfile.ZipFile)
+
+
+def _zip_remove(self, zinfo_or_arcname):  # type: ignore
+    """Remove a member from the archive."""
+
+    if self.mode not in ("w", "x", "a"):
+        raise ValueError("remove() requires mode 'w', 'x', or 'a'")
+    if not self.fp:
+        raise ValueError("Attempt to write to ZIP archive that was already closed")
+    if self._writing:
+        raise ValueError("Can't write to ZIP archive while an open writing handle exists")
+
+    # Make sure we have an existing info object
+    if isinstance(zinfo_or_arcname, zipfile.ZipInfo):
+        zinfo = zinfo_or_arcname
+        # make sure zinfo exists
+        if zinfo not in self.filelist:
+            raise KeyError("There is no item %r in the archive" % zinfo_or_arcname)
+    else:
+        # get the info object
+        zinfo = self.getinfo(zinfo_or_arcname)
+
+    return self._remove_members({zinfo})
+
+
+def _zip_remove_members(self, members, *, remove_physical=True, chunk_size=2**20):  # type: ignore
+    """Remove members in a zip file.
+    All members (as zinfo) should exist in the zip; otherwise the zip file
+    will erroneously end in an inconsistent state.
+    """
+    fp = self.fp
+    entry_offset = 0
+    member_seen = False
+
+    # get a sorted filelist by header offset, in case the dir order
+    # doesn't match the actual entry order
+    filelist = sorted(self.filelist, key=lambda x: x.header_offset)
+    for i in range(len(filelist)):
+        info = filelist[i]
+        is_member = info in members
+
+        if not (member_seen or is_member):
+            continue
+
+        # get the total size of the entry
+        try:
+            offset = filelist[i + 1].header_offset
+        except IndexError:
+            offset = self.start_dir
+        entry_size = offset - info.header_offset
+
+        if is_member:
+            member_seen = True
+            entry_offset += entry_size
+
+            # update caches
+            self.filelist.remove(info)
+            try:
+                del self.NameToInfo[info.filename]
+            except KeyError:
+                pass
+            continue
+
+        # update the header and move entry data to the new position
+        if remove_physical:
+            old_header_offset = info.header_offset
+            info.header_offset -= entry_offset
+            read_size = 0
+            while read_size < entry_size:
+                fp.seek(old_header_offset + read_size)
+                data = fp.read(min(entry_size - read_size, chunk_size))
+                fp.seek(info.header_offset + read_size)
+                fp.write(data)
+                fp.flush()
+                read_size += len(data)
+
+    # Avoid missing entry if entries have a duplicated name.
+    # Reverse the order as NameToInfo normally stores the last added one.
+    for info in reversed(self.filelist):
+        self.NameToInfo.setdefault(info.filename, info)
+
+    # update state
+    if remove_physical:
+        self.start_dir -= entry_offset
+    self._didModify = True
+
+    # seek to the start of the central dir
+    fp.seek(self.start_dir)

comicapi/comet.py

@@ -1,215 +0,0 @@
-"""A class to encapsulate CoMet data"""
-#
-# Copyright 2012-2014 Anthony Beville
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-from __future__ import annotations
-
-import logging
-import xml.etree.ElementTree as ET
-from typing import Any
-
-from comicapi import utils
-from comicapi.genericmetadata import GenericMetadata
-
-logger = logging.getLogger(__name__)
-
-
-class CoMet:
-
-    writer_synonyms = ["writer", "plotter", "scripter"]
-    penciller_synonyms = ["artist", "penciller", "penciler", "breakdowns"]
-    inker_synonyms = ["inker", "artist", "finishes"]
-    colorist_synonyms = ["colorist", "colourist", "colorer", "colourer"]
-    letterer_synonyms = ["letterer"]
-    cover_synonyms = ["cover", "covers", "coverartist", "cover artist"]
-    editor_synonyms = ["editor"]
-
-    def metadata_from_string(self, string: str) -> GenericMetadata:
-        tree = ET.ElementTree(ET.fromstring(string))
-        return self.convert_xml_to_metadata(tree)
-
-    def string_from_metadata(self, metadata: GenericMetadata) -> str:
-        tree = self.convert_metadata_to_xml(metadata)
-        return str(ET.tostring(tree.getroot(), encoding="utf-8", xml_declaration=True).decode("utf-8"))
-
-    def convert_metadata_to_xml(self, metadata: GenericMetadata) -> ET.ElementTree:
-
-        # shorthand for the metadata
-        md = metadata
-
-        # build a tree structure
-        root = ET.Element("comet")
-        root.attrib["xmlns:comet"] = "http://www.denvog.com/comet/"
-        root.attrib["xmlns:xsi"] = "http://www.w3.org/2001/XMLSchema-instance"
-        root.attrib["xsi:schemaLocation"] = "http://www.denvog.com http://www.denvog.com/comet/comet.xsd"
-
-        # helper func
-        def assign(comet_entry: str, md_entry: Any) -> None:
-            if md_entry is not None:
-                ET.SubElement(root, comet_entry).text = str(md_entry)
-
-        # title is manditory
-        if md.title is None:
-            md.title = ""
-        assign("title", md.title)
-        assign("series", md.series)
-        assign("issue", md.issue)  # must be int??
-        assign("volume", md.volume)
-        assign("description", md.comments)
-        assign("publisher", md.publisher)
-        assign("pages", md.page_count)
-        assign("format", md.format)
-        assign("language", md.language)
-        assign("rating", md.maturity_rating)
-        assign("price", md.price)
-        assign("isVersionOf", md.is_version_of)
-        assign("rights", md.rights)
-        assign("identifier", md.identifier)
-        assign("lastMark", md.last_mark)
-        assign("genre", md.genre)  # TODO repeatable
-
-        if md.characters is not None:
-            char_list = [c.strip() for c in md.characters.split(",")]
-            for c in char_list:
-                assign("character", c)
-
-        if md.manga is not None and md.manga == "YesAndRightToLeft":
-            assign("readingDirection", "rtl")
-
-        if md.year is not None:
-            date_str = f"{md.year:04}"
-            if md.month is not None:
-                date_str += f"-{md.month:02}"
-            assign("date", date_str)
-
-        assign("coverImage", md.cover_image)
-
-        # loop thru credits, and build a list for each role that CoMet supports
-        for credit in metadata.credits:
-
-            if credit["role"].casefold() in set(self.writer_synonyms):
-                ET.SubElement(root, "writer").text = str(credit["person"])
-
-            if credit["role"].casefold() in set(self.penciller_synonyms):
-                ET.SubElement(root, "penciller").text = str(credit["person"])
-
-            if credit["role"].casefold() in set(self.inker_synonyms):
-                ET.SubElement(root, "inker").text = str(credit["person"])
-
-            if credit["role"].casefold() in set(self.colorist_synonyms):
-                ET.SubElement(root, "colorist").text = str(credit["person"])
-
-            if credit["role"].casefold() in set(self.letterer_synonyms):
-                ET.SubElement(root, "letterer").text = str(credit["person"])
-
-            if credit["role"].casefold() in set(self.cover_synonyms):
-                ET.SubElement(root, "coverDesigner").text = str(credit["person"])
-
-            if credit["role"].casefold() in set(self.editor_synonyms):
-                ET.SubElement(root, "editor").text = str(credit["person"])
-
-        ET.indent(root)
-
-        # wrap it in an ElementTree instance, and save as XML
-        tree = ET.ElementTree(root)
-        return tree
-
-    def convert_xml_to_metadata(self, tree: ET.ElementTree) -> GenericMetadata:
-        root = tree.getroot()
-
-        if root.tag != "comet":
-            raise Exception("Not a CoMet file")
-
-        metadata = GenericMetadata()
-        md = metadata
-
-        # Helper function
-        def get(tag: str) -> Any:
-            node = root.find(tag)
-            if node is not None:
-                return node.text
-            return None
-
-        md.series = utils.xlate(get("series"))
-        md.title = utils.xlate(get("title"))
-        md.issue = utils.xlate(get("issue"))
-        md.volume = utils.xlate(get("volume"), True)
-        md.comments = utils.xlate(get("description"))
-        md.publisher = utils.xlate(get("publisher"))
-        md.language = utils.xlate(get("language"))
-        md.format = utils.xlate(get("format"))
-        md.page_count = utils.xlate(get("pages"), True)
-        md.maturity_rating = utils.xlate(get("rating"))
-        md.price = utils.xlate(get("price"), is_float=True)
-        md.is_version_of = utils.xlate(get("isVersionOf"))
-        md.rights = utils.xlate(get("rights"))
-        md.identifier = utils.xlate(get("identifier"))
-        md.last_mark = utils.xlate(get("lastMark"))
-        md.genre = utils.xlate(get("genre"))  # TODO - repeatable field
-
-        _, md.month, md.year = utils.parse_date_str(utils.xlate(get("date")))
-
-        md.cover_image = utils.xlate(get("coverImage"))
-
-        reading_direction = utils.xlate(get("readingDirection"))
-        if reading_direction is not None and reading_direction == "rtl":
-            md.manga = "YesAndRightToLeft"
-
-        # loop for character tags
-        char_list = []
-        for n in root:
-            if n.tag == "character":
-                char_list.append((n.text or "").strip())
-        md.characters = ", ".join(char_list)
-
-        # Now extract the credit info
-        for n in root:
-            if any(
-                [
-                    n.tag == "writer",
-                    n.tag == "penciller",
-                    n.tag == "inker",
-                    n.tag == "colorist",
-                    n.tag == "letterer",
-                    n.tag == "editor",
-                ]
-            ):
-                metadata.add_credit((n.text or "").strip(), n.tag.title())
-
-            if n.tag == "coverDesigner":
-                metadata.add_credit((n.text or "").strip(), "Cover")
-
-        metadata.is_empty = False
-
-        return metadata
-
-    # verify that the string actually contains CoMet data in XML format
-    def validate_string(self, string: str) -> bool:
-        try:
-            tree = ET.ElementTree(ET.fromstring(string))
-            root = tree.getroot()
-            if root.tag != "comet":
-                return False
-        except ET.ParseError:
-            return False
-
-        return True
-
-    def write_to_external_file(self, filename: str, metadata: GenericMetadata) -> None:
-        tree = self.convert_metadata_to_xml(metadata)
-        tree.write(filename, encoding="utf-8")
-
-    def read_from_external_file(self, filename: str) -> GenericMetadata:
-        tree = ET.parse(filename)
-        return self.convert_xml_to_metadata(tree)

comicapi/comicbookinfo.py

@@ -1,175 +0,0 @@
-"""A class to encapsulate the ComicBookInfo data"""
-# Copyright 2012-2014 Anthony Beville
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-from __future__ import annotations
-
-import json
-import logging
-from collections import defaultdict
-from datetime import datetime
-from typing import Any, Literal, TypedDict
-
-from comicapi import utils
-from comicapi.genericmetadata import GenericMetadata
-
-logger = logging.getLogger(__name__)
-
-CBILiteralType = Literal[
-    "series",
-    "title",
-    "issue",
-    "publisher",
-    "publicationMonth",
-    "publicationYear",
-    "numberOfIssues",
-    "comments",
-    "genre",
-    "volume",
-    "numberOfVolumes",
-    "language",
-    "country",
-    "rating",
-    "credits",
-    "tags",
-]
-
-
-class Credits(TypedDict):
-    person: str
-    role: str
-    primary: bool
-
-
-class ComicBookInfoJson(TypedDict, total=False):
-    series: str
-    title: str
-    publisher: str
-    publicationMonth: int
-    publicationYear: int
-    issue: int
-    numberOfIssues: int
-    volume: int
-    numberOfVolumes: int
-    rating: int
-    genre: str
-    language: str
-    country: str
-    credits: list[Credits]
-    tags: list[str]
-    comments: str
-
-
-CBIContainer = TypedDict("CBIContainer", {"appID": str, "lastModified": str, "ComicBookInfo/1.0": ComicBookInfoJson})
-
-
-class ComicBookInfo:
-    def metadata_from_string(self, string: str) -> GenericMetadata:
-
-        cbi_container = json.loads(string)
-
-        metadata = GenericMetadata()
-
-        cbi = defaultdict(lambda: None, cbi_container["ComicBookInfo/1.0"])
-
-        metadata.series = utils.xlate(cbi["series"])
-        metadata.title = utils.xlate(cbi["title"])
-        metadata.issue = utils.xlate(cbi["issue"])
-        metadata.publisher = utils.xlate(cbi["publisher"])
-        metadata.month = utils.xlate(cbi["publicationMonth"], True)
-        metadata.year = utils.xlate(cbi["publicationYear"], True)
-        metadata.issue_count = utils.xlate(cbi["numberOfIssues"], True)
-        metadata.comments = utils.xlate(cbi["comments"])
-        metadata.genre = utils.xlate(cbi["genre"])
-        metadata.volume = utils.xlate(cbi["volume"], True)
-        metadata.volume_count = utils.xlate(cbi["numberOfVolumes"], True)
-        metadata.language = utils.xlate(cbi["language"])
-        metadata.country = utils.xlate(cbi["country"])
-        metadata.critical_rating = utils.xlate(cbi["rating"], True)
-
-        metadata.credits = [
-            Credits(
-                person=x["person"] if "person" in x else "",
-                role=x["role"] if "role" in x else "",
-                primary=x["primary"] if "primary" in x else False,
-            )
-            for x in cbi["credits"]
-        ]
-        metadata.tags = set(cbi["tags"]) if cbi["tags"] is not None else set()
-
-        # make sure credits and tags are at least empty lists and not None
-        if metadata.credits is None:
-            metadata.credits = []
-
-        # need the language string to be ISO
-        if metadata.language:
-            metadata.language = utils.get_language_iso(metadata.language)
-
-        metadata.is_empty = False
-
-        return metadata
-
-    def string_from_metadata(self, metadata: GenericMetadata) -> str:
-        cbi_container = self.create_json_dictionary(metadata)
-        return json.dumps(cbi_container)
-
-    def validate_string(self, string: bytes | str) -> bool:
-        """Verify that the string actually contains CBI data in JSON format"""
-
-        try:
-            cbi_container = json.loads(string)
-        except json.JSONDecodeError:
-            return False
-
-        return "ComicBookInfo/1.0" in cbi_container
-
-    def create_json_dictionary(self, metadata: GenericMetadata) -> CBIContainer:
-        """Create the dictionary that we will convert to JSON text"""
-
-        cbi_container = CBIContainer(
-            {
-                "appID": "ComicTagger/1.0.0",
-                "lastModified": str(datetime.now()),
-                "ComicBookInfo/1.0": {},
-            }
-        )  # TODO: ctversion.version,
-
-        # helper func
-        def assign(cbi_entry: CBILiteralType, md_entry: Any) -> None:
-            if md_entry is not None or isinstance(md_entry, str) and md_entry != "":
-                cbi_container["ComicBookInfo/1.0"][cbi_entry] = md_entry
-
-        assign("series", utils.xlate(metadata.series))
-        assign("title", utils.xlate(metadata.title))
-        assign("issue", utils.xlate(metadata.issue))
-        assign("publisher", utils.xlate(metadata.publisher))
-        assign("publicationMonth", utils.xlate(metadata.month, True))
-        assign("publicationYear", utils.xlate(metadata.year, True))
-        assign("numberOfIssues", utils.xlate(metadata.issue_count, True))
-        assign("comments", utils.xlate(metadata.comments))
-        assign("genre", utils.xlate(metadata.genre))
-        assign("volume", utils.xlate(metadata.volume, True))
-        assign("numberOfVolumes", utils.xlate(metadata.volume_count, True))
-        assign("language", utils.xlate(utils.get_language_from_iso(metadata.language)))
-        assign("country", utils.xlate(metadata.country))
-        assign("rating", utils.xlate(metadata.critical_rating, True))
-        assign("credits", metadata.credits)
-        assign("tags", list(metadata.tags))
-
-        return cbi_container
-
-    def write_to_external_file(self, filename: str, metadata: GenericMetadata) -> None:
-        cbi_container = self.create_json_dictionary(metadata)
-
-        with open(filename, "w", encoding="utf-8") as f:
-            f.write(json.dumps(cbi_container, indent=4))

comicapi/comicinfoxml.py

@@ -1,276 +0,0 @@
-"""A class to encapsulate ComicRack's ComicInfo.xml data"""
-# Copyright 2012-2014 Anthony Beville
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-from __future__ import annotations
-
-import logging
-import xml.etree.ElementTree as ET
-from collections import OrderedDict
-from typing import Any, cast
-from xml.etree.ElementTree import ElementTree
-
-from comicapi import utils
-from comicapi.genericmetadata import GenericMetadata, ImageMetadata
-from comicapi.issuestring import IssueString
-
-logger = logging.getLogger(__name__)
-
-
-class ComicInfoXml:
-
-    writer_synonyms = ["writer", "plotter", "scripter"]
-    penciller_synonyms = ["artist", "penciller", "penciler", "breakdowns"]
-    inker_synonyms = ["inker", "artist", "finishes"]
-    colorist_synonyms = ["colorist", "colourist", "colorer", "colourer"]
-    letterer_synonyms = ["letterer"]
-    cover_synonyms = ["cover", "covers", "coverartist", "cover artist"]
-    editor_synonyms = ["editor"]
-
-    def get_parseable_credits(self) -> list[str]:
-        parsable_credits = []
-        parsable_credits.extend(self.writer_synonyms)
-        parsable_credits.extend(self.penciller_synonyms)
-        parsable_credits.extend(self.inker_synonyms)
-        parsable_credits.extend(self.colorist_synonyms)
-        parsable_credits.extend(self.letterer_synonyms)
-        parsable_credits.extend(self.cover_synonyms)
-        parsable_credits.extend(self.editor_synonyms)
-        return parsable_credits
-
-    def metadata_from_string(self, string: bytes) -> GenericMetadata:
-
-        tree = ET.ElementTree(ET.fromstring(string))
-        return self.convert_xml_to_metadata(tree)
-
-    def string_from_metadata(self, metadata: GenericMetadata, xml: bytes = b"") -> str:
-        tree = self.convert_metadata_to_xml(metadata, xml)
-        tree_str = ET.tostring(tree.getroot(), encoding="utf-8", xml_declaration=True).decode("utf-8")
-        return str(tree_str)
-
-    def convert_metadata_to_xml(self, metadata: GenericMetadata, xml: bytes = b"") -> ElementTree:
-
-        # shorthand for the metadata
-        md = metadata
-
-        if xml:
-            root = ET.ElementTree(ET.fromstring(xml)).getroot()
-        else:
-            # build a tree structure
-            root = ET.Element("ComicInfo")
-            root.attrib["xmlns:xsi"] = "http://www.w3.org/2001/XMLSchema-instance"
-            root.attrib["xmlns:xsd"] = "http://www.w3.org/2001/XMLSchema"
-        # helper func
-
-        def assign(cix_entry: str, md_entry: Any) -> None:
-            if md_entry is not None and md_entry:
-                et_entry = root.find(cix_entry)
-                if et_entry is not None:
-                    et_entry.text = str(md_entry)
-                else:
-                    ET.SubElement(root, cix_entry).text = str(md_entry)
-            else:
-                et_entry = root.find(cix_entry)
-                if et_entry is not None:
-                    root.remove(et_entry)
-
-        assign("Title", md.title)
-        assign("Series", md.series)
-        assign("Number", md.issue)
-        assign("Count", md.issue_count)
-        assign("Volume", md.volume)
-        assign("AlternateSeries", md.alternate_series)
-        assign("AlternateNumber", md.alternate_number)
-        assign("StoryArc", md.story_arc)
-        assign("SeriesGroup", md.series_group)
-        assign("AlternateCount", md.alternate_count)
-        assign("Summary", md.comments)
-        assign("Notes", md.notes)
-        assign("Year", md.year)
-        assign("Month", md.month)
-        assign("Day", md.day)
-
-        # need to specially process the credits, since they are structured
-        # differently than CIX
-        credit_writer_list = []
-        credit_penciller_list = []
-        credit_inker_list = []
-        credit_colorist_list = []
-        credit_letterer_list = []
-        credit_cover_list = []
-        credit_editor_list = []
-
-        # first, loop thru credits, and build a list for each role that CIX
-        # supports
-        for credit in metadata.credits:
-
-            if credit["role"].casefold() in set(self.writer_synonyms):
-                credit_writer_list.append(credit["person"].replace(",", ""))
-
-            if credit["role"].casefold() in set(self.penciller_synonyms):
-                credit_penciller_list.append(credit["person"].replace(",", ""))
-
-            if credit["role"].casefold() in set(self.inker_synonyms):
-                credit_inker_list.append(credit["person"].replace(",", ""))
-
-            if credit["role"].casefold() in set(self.colorist_synonyms):
-                credit_colorist_list.append(credit["person"].replace(",", ""))
-
-            if credit["role"].casefold() in set(self.letterer_synonyms):
-                credit_letterer_list.append(credit["person"].replace(",", ""))
-
-            if credit["role"].casefold() in set(self.cover_synonyms):
-                credit_cover_list.append(credit["person"].replace(",", ""))
-
-            if credit["role"].casefold() in set(self.editor_synonyms):
-                credit_editor_list.append(credit["person"].replace(",", ""))
-
-        # second, convert each list to string, and add to XML struct
-        assign("Writer", ", ".join(credit_writer_list))
-
-        assign("Penciller", ", ".join(credit_penciller_list))
-
-        assign("Inker", ", ".join(credit_inker_list))
-
-        assign("Colorist", ", ".join(credit_colorist_list))
-
-        assign("Letterer", ", ".join(credit_letterer_list))
-
-        assign("CoverArtist", ", ".join(credit_cover_list))
-
-        assign("Editor", ", ".join(credit_editor_list))
-
-        assign("Publisher", md.publisher)
-        assign("Imprint", md.imprint)
-        assign("Genre", md.genre)
-        assign("Web", md.web_link)
-        assign("PageCount", md.page_count)
-        assign("LanguageISO", md.language)
-        assign("Format", md.format)
-        assign("AgeRating", md.maturity_rating)
-        assign("CommunityRating", md.critical_rating)
-        assign("BlackAndWhite", "Yes" if md.black_and_white else None)
-        assign("Manga", md.manga)
-        assign("Characters", md.characters)
-        assign("Teams", md.teams)
-        assign("Locations", md.locations)
-        assign("ScanInformation", md.scan_info)
-
-        #  loop and add the page entries under pages node
-        pages_node = root.find("Pages")
-        if pages_node is not None:
-            pages_node.clear()
-        else:
-            pages_node = ET.SubElement(root, "Pages")
-
-        for page_dict in md.pages:
-            page_node = ET.SubElement(pages_node, "Page")
-            page_node.attrib = OrderedDict(sorted((k, str(v)) for k, v in page_dict.items()))
-
-        ET.indent(root)
-
-        # wrap it in an ElementTree instance, and save as XML
-        tree = ET.ElementTree(root)
-        return tree
-
-    def convert_xml_to_metadata(self, tree: ElementTree) -> GenericMetadata:
-
-        root = tree.getroot()
-
-        if root.tag != "ComicInfo":
-            raise Exception("Not a ComicInfo file")
-
-        def get(name: str) -> str | None:
-            tag = root.find(name)
-            if tag is None:
-                return None
-            return tag.text
-
-        md = GenericMetadata()
-
-        md.series = utils.xlate(get("Series"))
-        md.title = utils.xlate(get("Title"))
-        md.issue = IssueString(utils.xlate(get("Number"))).as_string()
-        md.issue_count = utils.xlate(get("Count"), True)
-        md.volume = utils.xlate(get("Volume"), True)
-        md.alternate_series = utils.xlate(get("AlternateSeries"))
-        md.alternate_number = IssueString(utils.xlate(get("AlternateNumber"))).as_string()
-        md.alternate_count = utils.xlate(get("AlternateCount"), True)
-        md.comments = utils.xlate(get("Summary"))
-        md.notes = utils.xlate(get("Notes"))
-        md.year = utils.xlate(get("Year"), True)
-        md.month = utils.xlate(get("Month"), True)
-        md.day = utils.xlate(get("Day"), True)
-        md.publisher = utils.xlate(get("Publisher"))
-        md.imprint = utils.xlate(get("Imprint"))
-        md.genre = utils.xlate(get("Genre"))
-        md.web_link = utils.xlate(get("Web"))
-        md.language = utils.xlate(get("LanguageISO"))
-        md.format = utils.xlate(get("Format"))
-        md.manga = utils.xlate(get("Manga"))
-        md.characters = utils.xlate(get("Characters"))
-        md.teams = utils.xlate(get("Teams"))
-        md.locations = utils.xlate(get("Locations"))
-        md.page_count = utils.xlate(get("PageCount"), True)
-        md.scan_info = utils.xlate(get("ScanInformation"))
-        md.story_arc = utils.xlate(get("StoryArc"))
-        md.series_group = utils.xlate(get("SeriesGroup"))
-        md.maturity_rating = utils.xlate(get("AgeRating"))
-        md.critical_rating = utils.xlate(get("CommunityRating"), is_float=True)
-
-        tmp = utils.xlate(get("BlackAndWhite"))
-        if tmp is not None and tmp.casefold() in ["yes", "true", "1"]:
-            md.black_and_white = True
-        # Now extract the credit info
-        for n in root:
-            if any(
-                [
-                    n.tag == "Writer",
-                    n.tag == "Penciller",
-                    n.tag == "Inker",
-                    n.tag == "Colorist",
-                    n.tag == "Letterer",
-                    n.tag == "Editor",
-                ]
-            ):
-                if n.text is not None:
-                    for name in n.text.split(","):
-                        md.add_credit(name.strip(), n.tag)
-
-            if n.tag == "CoverArtist":
-                if n.text is not None:
-                    for name in n.text.split(","):
-                        md.add_credit(name.strip(), "Cover")
-
-        # parse page data now
-        pages_node = root.find("Pages")
-        if pages_node is not None:
-            for page in pages_node:
-                p: dict[str, Any] = page.attrib
-                if "Image" in p:
-                    p["Image"] = int(p["Image"])
-                if "DoublePage" in p:
-                    p["DoublePage"] = True if p["DoublePage"].casefold() in ("yes", "true", "1") else False
-                md.pages.append(cast(ImageMetadata, p))
-
-        md.is_empty = False
-
-        return md
-
-    def write_to_external_file(self, filename: str, metadata: GenericMetadata, xml: bytes = b"") -> None:
-        tree = self.convert_metadata_to_xml(metadata, xml)
-        tree.write(filename, encoding="utf-8", xml_declaration=True)
-
-    def read_from_external_file(self, filename: str) -> GenericMetadata:
-        tree = ET.parse(filename)
-        return self.convert_xml_to_metadata(tree)

comicapi/data/__init__.py

@@ -1,5 +1,5 @@
 from __future__ import annotations
 
-import pathlib
+import importlib.resources
 
-data_path = pathlib.Path(__file__).parent
+data_path = importlib.resources.files(__package__)

comicapi/data/publishers.json

@@ -126,5 +126,18 @@
         "radio comics": "Mighty Comics Group",
         "red circle Comics": "Dark Circle Comics",
         "red circle": "Dark Circle Comics"
+    },
+
+    "Image Comics": {
+        "Image": "",
+        "avalon studios": "Avalon Studios",
+        "desperado publishing": "Desperado Publishing",
+        "extreme studios": "Extreme Studios",
+        "gorilla comics": "Gorilla Comics",
+        "highbrow entertainment": "Highbrow Entertainment",
+        "shadowline": "Shadowline",
+        "skybound entertainment": "Skybound Entertainment",
+        "todd mcfarlane productions": "Todd McFarlane Productions",
+        "top cow productions": "Top Cow Productions"
     }
 }

comicapi/filenamelexer.py

@@ -6,7 +6,8 @@ import calendar
 import os
 import unicodedata
 from enum import Enum, auto
-from typing import Any, Callable
+from itertools import chain
+from typing import Any, Callable, Protocol
 
 
 class ItemType(Enum):
@@ -30,10 +31,10 @@ class ItemType(Enum):
     InfoSpecifier = auto()  # Specifies type of info e.g. v1 for 'volume': 1
     ArchiveType = auto()
     Honorific = auto()
+    Publisher = auto()
     Keywords = auto()
     FCBD = auto()
     ComicType = auto()
-    Publisher = auto()
     C2C = auto()
 
 
@@ -60,7 +61,6 @@ key = {
     "tar": ItemType.ArchiveType,
     "7z": ItemType.ArchiveType,
     "annual": ItemType.ComicType,
-    "book": ItemType.ComicType,
     "volume": ItemType.InfoSpecifier,
     "vol.": ItemType.InfoSpecifier,
     "vol": ItemType.InfoSpecifier,
@@ -82,15 +82,21 @@ class Item:
         self.typ: ItemType = typ
         self.pos: int = pos
         self.val: str = val
+        self.no_space = False
 
     def __repr__(self) -> str:
         return f"{self.val}: index: {self.pos}: {self.typ}"
 
 
+class LexerFunc(Protocol):
+    def __call__(self, __origin: Lexer) -> LexerFunc | None: ...
+
+
 class Lexer:
-    def __init__(self, string: str) -> None:
+    def __init__(self, string: str, allow_issue_start_with_letter: bool = False) -> None:
         self.input: str = string  # The string being scanned
-        self.state: Callable[[Lexer], Callable | None] | None = None  # The next lexing function to enter
+        # The next lexing function to enter
+        self.state: LexerFunc | None = None
         self.pos: int = -1  # Current position in the input
         self.start: int = 0  # Start position of this item
         self.lastPos: int = 0  # Position of most recent item returned by nextItem
@@ -98,6 +104,7 @@ class Lexer:
         self.brace_depth: int = 0  # Nesting depth of { }
         self.sbrace_depth: int = 0  # Nesting depth of [ ]
         self.items: list[Item] = []
+        self.allow_issue_start_with_letter = allow_issue_start_with_letter
 
     # Next returns the next rune in the input.
     def get(self) -> str:
@@ -128,38 +135,38 @@ class Lexer:
         self.start = self.pos
 
     # Accept consumes the next rune if it's from the valid se:
-    def accept(self, valid: str) -> bool:
-        if self.get() in valid:
-            return True
+    def accept(self, valid: str | Callable[[str], bool]) -> bool:
+        if isinstance(valid, str):
+            if self.get() in valid:
+                return True
+        else:
+            if valid(self.get()):
+                return True
 
         self.backup()
         return False
 
     # AcceptRun consumes a run of runes from the valid set.
-    def accept_run(self, valid: str) -> None:
-        while self.get() in valid:
-            continue
+    def accept_run(self, valid: str | Callable[[str], bool]) -> bool:
+        initial = self.pos
+        if isinstance(valid, str):
+            while self.get() in valid:
+                continue
+        else:
+            while valid(self.get()):
+                continue
 
         self.backup()
+        return initial != self.pos
 
     def scan_number(self) -> bool:
-        digits = "0123456789"
+        digits = "0123456789.,"
 
-        self.accept_run(digits)
-        if self.accept("."):
-            if self.accept(digits):
-                self.accept_run(digits)
-            else:
-                self.backup()
-        if self.accept("s"):
-            if not self.accept("t"):
-                self.backup()
-        elif self.accept("nr"):
-            if not self.accept("d"):
-                self.backup()
-        elif self.accept("t"):
-            if not self.accept("h"):
-                self.backup()
+        if not self.accept_run(lambda x: x.isnumeric() or x in digits):
+            return False
+        if self.input[self.pos] == ".":
+            self.backup()
+        self.accept_run(str.isalpha)
 
         return True
 
@@ -172,20 +179,22 @@ class Lexer:
 
 # Errorf returns an error token and terminates the scan by passing
 # Back a nil pointer that will be the next state, terminating self.nextItem.
-def errorf(lex: Lexer, message: str) -> Callable[[Lexer], Callable | None] | None:
+def errorf(lex: Lexer, message: str) -> Any:
     lex.items.append(Item(ItemType.Error, lex.start, message))
     return None
 
 
 # Scans the elements inside action delimiters.
-def lex_filename(lex: Lexer) -> Callable[[Lexer], Callable | None] | None:
+def lex_filename(lex: Lexer) -> LexerFunc | None:
     r = lex.get()
     if r == eof:
         if lex.paren_depth != 0:
-            return errorf(lex, "unclosed left paren")
+            errorf(lex, "unclosed left paren")
+            return None
 
         if lex.brace_depth != 0:
-            return errorf(lex, "unclosed left paren")
+            errorf(lex, "unclosed left paren")
+            return None
         lex.emit(ItemType.EOF)
         return None
     elif is_space(r):
@@ -196,23 +205,27 @@ def lex_filename(lex: Lexer) -> Callable[[Lexer], Callable | None] | None:
             return lex_space
     elif r == ".":
         r = lex.peek()
-        if r < "0" or "9" < r:
-            lex.emit(ItemType.Dot)
-            return lex_filename
-
-        lex.backup()
-        return lex_number
+        if r.isnumeric() and lex.pos > 0 and is_space(lex.input[lex.pos - 1]):
+            return lex_number
+        lex.emit(ItemType.Dot)
+        return lex_filename
     elif r == "'":
         r = lex.peek()
-        if r in "0123456789":
+        if r.isdigit():
             return lex_number
-        lex.emit(ItemType.Text)  # TODO: Change to Text
-    elif "0" <= r <= "9":
+        if is_symbol(r):
+            lex.accept_run(is_symbol)
+            lex.emit(ItemType.Symbol)
+        else:
+            return lex_text
+    elif r.isnumeric():
         lex.backup()
         return lex_number
     elif r == "#":
-        if "0" <= lex.peek() <= "9":
-            return lex_number
+        if lex.allow_issue_start_with_letter and is_alpha_numeric(lex.peek()):
+            return lex_issue_number
+        elif lex.peek().isnumeric() or lex.peek() in "-+.":
+            return lex_issue_number
         lex.emit(ItemType.Symbol)
     elif is_operator(r):
         if r == "-" and lex.peek() == "-":
@@ -230,7 +243,8 @@ def lex_filename(lex: Lexer) -> Callable[[Lexer], Callable | None] | None:
         lex.emit(ItemType.RightParen)
         lex.paren_depth -= 1
         if lex.paren_depth < 0:
-            return errorf(lex, "unexpected right paren " + r)
+            errorf(lex, "unexpected right paren " + r)
+            return None
 
     elif r == "{":
         lex.emit(ItemType.LeftBrace)
@@ -239,7 +253,8 @@ def lex_filename(lex: Lexer) -> Callable[[Lexer], Callable | None] | None:
         lex.emit(ItemType.RightBrace)
         lex.brace_depth -= 1
         if lex.brace_depth < 0:
-            return errorf(lex, "unexpected right brace " + r)
+            errorf(lex, "unexpected right brace " + r)
+            return None
 
     elif r == "[":
         lex.emit(ItemType.LeftSBrace)
@@ -248,16 +263,33 @@ def lex_filename(lex: Lexer) -> Callable[[Lexer], Callable | None] | None:
         lex.emit(ItemType.RightSBrace)
         lex.sbrace_depth -= 1
         if lex.sbrace_depth < 0:
-            return errorf(lex, "unexpected right brace " + r)
+            errorf(lex, "unexpected right brace " + r)
+            return None
     elif is_symbol(r):
+        if unicodedata.category(r) == "Sc":
+            return lex_currency
+        lex.accept_run(is_symbol)
         lex.emit(ItemType.Symbol)
     else:
-        return errorf(lex, "unrecognized character in action: " + r)
+        errorf(lex, "unrecognized character in action: " + repr(r))
+        return None
 
     return lex_filename
 
 
-def lex_operator(lex: Lexer) -> Callable:
+def lex_currency(lex: Lexer) -> LexerFunc:
+    orig = lex.pos
+    lex.accept_run(is_space)
+    if lex.peek().isnumeric():
+        return lex_number
+    else:
+        lex.pos = orig
+    # We don't have a number with this currency symbol. Don't treat it special
+    lex.emit(ItemType.Symbol)
+    return lex_filename
+
+
+def lex_operator(lex: Lexer) -> LexerFunc:
     lex.accept_run("-|:;")
     lex.emit(ItemType.Operator)
     return lex_filename
@@ -265,36 +297,31 @@ def lex_operator(lex: Lexer) -> Callable:
 
 # LexSpace scans a run of space characters.
 # One space has already been seen.
-def lex_space(lex: Lexer) -> Callable:
-    while is_space(lex.peek()):
-        lex.get()
+def lex_space(lex: Lexer) -> LexerFunc:
+    lex.accept_run(is_space)
 
     lex.emit(ItemType.Space)
     return lex_filename
 
 
 # Lex_text scans an alphanumeric.
-def lex_text(lex: Lexer) -> Callable:
+def lex_text(lex: Lexer) -> LexerFunc:
     while True:
         r = lex.get()
-        if is_alpha_numeric(r):
+        if is_alpha_numeric(r) or r in "'":
             if r.isnumeric():  # E.g. v1
                 word = lex.input[lex.start : lex.pos]
-                if word.casefold() in key and key[word.casefold()] == ItemType.InfoSpecifier:
+                if key.get(word.casefold(), None) == ItemType.InfoSpecifier:
                     lex.backup()
                     lex.emit(key[word.casefold()])
                     return lex_filename
         else:
-            if r == "'" and lex.peek() == "s":
-                lex.get()
-            else:
-                lex.backup()
-            word = lex.input[lex.start : lex.pos + 1]
-            if word.casefold() == "vol" and lex.peek() == ".":
-                lex.get()
+            lex.backup()
             word = lex.input[lex.start : lex.pos + 1]
 
             if word.casefold() in key:
+                if key[word.casefold()] in (ItemType.Honorific, ItemType.InfoSpecifier):
+                    lex.accept(".")
                 lex.emit(key[word.casefold()])
             elif cal(word):
                 lex.emit(ItemType.Calendar)
@@ -305,26 +332,66 @@ def lex_text(lex: Lexer) -> Callable:
     return lex_filename
 
 
-def cal(value: str) -> set[Any]:
-    month_abbr = [i for i, x in enumerate(calendar.month_abbr) if x == value.title()]
-    month_name = [i for i, x in enumerate(calendar.month_name) if x == value.title()]
-    day_abbr = [i for i, x in enumerate(calendar.day_abbr) if x == value.title()]
-    day_name = [i for i, x in enumerate(calendar.day_name) if x == value.title()]
-    return set(month_abbr + month_name + day_abbr + day_name)
+def cal(value: str) -> bool:
+    return value.title() in set(chain(calendar.month_abbr, calendar.month_name, calendar.day_abbr, calendar.day_name))
 
 
-def lex_number(lex: Lexer) -> Callable[[Lexer], Callable | None] | None:
+def lex_number(lex: Lexer) -> LexerFunc | None:
     if not lex.scan_number():
         return errorf(lex, "bad number syntax: " + lex.input[lex.start : lex.pos])
     # Complex number logic removed. Messes with math operations without space
 
     if lex.input[lex.start] == "#":
         lex.emit(ItemType.IssueNumber)
-    elif not lex.input[lex.pos].isdigit():
+    elif not lex.input[lex.pos].isnumeric():
         # Assume that 80th is just text and not a number
         lex.emit(ItemType.Text)
     else:
-        lex.emit(ItemType.Number)
+        # Used to check for a '$'
+        endNumber = lex.pos
+
+        # Consume any spaces
+        lex.accept_run(is_space)
+
+        # This number starts with a '$' emit it as Text instead of a Number
+        if "Sc" == unicodedata.category(lex.input[lex.start]):
+            lex.pos = endNumber
+            lex.emit(ItemType.Text)
+
+        # This number ends in a '$' if there is a number on the other side we assume it belongs to the following number
+        elif "Sc" == unicodedata.category(lex.get()):
+            # Store the end of the number '$'. We still need to check to see if there is a number coming up
+            endCurrency = lex.pos
+            # Consume any spaces
+            lex.accept_run(is_space)
+
+            # This is a number
+            if lex.peek().isnumeric():
+                # We go back to the original number before the '$' and emit a number
+                lex.pos = endNumber
+                lex.emit(ItemType.Number)
+            else:
+                # There was no following number, reset to the '$' and emit a number
+                lex.pos = endCurrency
+                lex.emit(ItemType.Text)
+        else:
+            # We go back to the original number there is no '$'
+            lex.pos = endNumber
+            lex.emit(ItemType.Number)
+
+    return lex_filename
+
+
+def lex_issue_number(lex: Lexer) -> Callable[[Lexer], Callable | None] | None:  # type: ignore[type-arg]
+    # Only called when lex.input[lex.start] == "#"
+    original_start = lex.pos
+    lex.accept_run(str.isalpha)
+
+    if lex.peek().isnumeric():
+        return lex_number
+    else:
+        lex.pos = original_start
+        lex.emit(ItemType.Symbol)
 
     return lex_filename
 
@@ -343,10 +410,10 @@ def is_operator(character: str) -> bool:
 
 
 def is_symbol(character: str) -> bool:
-    return unicodedata.category(character)[0] in "PS"
+    return unicodedata.category(character)[0] in "PS" and character != "."
 
 
-def Lex(filename: str) -> Lexer:
-    lex = Lexer(string=os.path.basename(filename))
+def Lex(filename: str, allow_issue_start_with_letter: bool = False) -> Lexer:
+    lex = Lexer(os.path.basename(filename), allow_issue_start_with_letter)
     lex.run()
     return lex

comicapi/genericmetadata.py

@@ -5,7 +5,8 @@ tagging schemes and databases, such as ComicVine or GCD.  This makes conversion
 possible, however lossy it might be
 
 """
-# Copyright 2012-2014 Anthony Beville
+
+# Copyright 2012-2014 ComicTagger Authors
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -23,15 +24,29 @@ from __future__ import annotations
 import copy
 import dataclasses
 import logging
-from typing import Any, TypedDict
+from collections.abc import Sequence
+from typing import TYPE_CHECKING, Any, Union, overload
 
-from comicapi import utils
+from typing_extensions import NamedTuple
+
+from comicapi import merge, utils
+from comicapi._url import Url, parse_url
+from comicapi.utils import norm_fold
+
+# needed for runtime type guessing
+if TYPE_CHECKING:
+    Union
 
 logger = logging.getLogger(__name__)
 
 
-class PageType:
+REMOVE = object()
 
+
+Credit = merge.Credit
+
+
+class PageType(merge.StrEnum):
     """
     These page info classes are exactly the same as the CIX scheme, since
     it's unique
@@ -50,85 +65,147 @@ class PageType:
     Deleted = "Deleted"
 
 
-class ImageMetadata(TypedDict, total=False):
-    Type: str
-    Bookmark: str
-    DoublePage: bool
-    Image: int
-    ImageSize: str
-    ImageHeight: str
-    ImageWidth: str
+@dataclasses.dataclass
+class PageMetadata:
+    filename: str
+    type: str
+    bookmark: str
+    display_index: int
+    archive_index: int
+    # These are optional because getting this info requires reading in each page
+    double_page: bool | None = None
+    byte_size: int | None = None
+    height: int | None = None
+    width: int | None = None
+
+    def set_type(self, value: str) -> None:
+        values = {x.casefold(): x for x in PageType}
+        self.type = values.get(value.casefold(), value)
+
+    def is_double_page(self) -> bool:
+        w = self.width or 0
+        h = self.height or 0
+        return self.double_page or (w >= h and w > 0 and h > 0)
+
+    def __lt__(self, other: Any) -> bool:
+        if not isinstance(other, PageMetadata):
+            return False
+        return self.archive_index < other.archive_index
+
+    def __eq__(self, other: Any) -> bool:
+        if not isinstance(other, PageMetadata):
+            return False
+        return self.archive_index == other.archive_index
+
+    def _get_clean_metadata(self, *attributes: str) -> PageMetadata:
+        return PageMetadata(
+            filename=self.filename if "filename" in attributes else "",
+            type=self.type if "type" in attributes else "",
+            bookmark=self.bookmark if "bookmark" in attributes else "",
+            display_index=self.display_index if "display_index" in attributes else 0,
+            archive_index=self.archive_index if "archive_index" in attributes else 0,
+            double_page=self.double_page if "double_page" in attributes else None,
+            byte_size=self.byte_size if "byte_size" in attributes else None,
+            height=self.height if "height" in attributes else None,
+            width=self.width if "width" in attributes else None,
+        )
 
 
-class CreditMetadata(TypedDict):
-    person: str
-    role: str
-    primary: bool
+@dataclasses.dataclass
+class ComicSeries:
+    id: str
+    name: str
+    aliases: set[str]
+    count_of_issues: int | None
+    count_of_volumes: int | None
+    description: str
+    image_url: str
+    publisher: str
+    start_year: int | None
+    format: str | None
+
+    def copy(self) -> ComicSeries:
+        return copy.deepcopy(self)
+
+
+class MetadataOrigin(NamedTuple):
+    id: str
+    name: str
+
+    def __str__(self) -> str:
+        return self.name
 
 
 @dataclasses.dataclass
 class GenericMetadata:
-    writer_synonyms = ["writer", "plotter", "scripter"]
-    penciller_synonyms = ["artist", "penciller", "penciler", "breakdowns"]
-    inker_synonyms = ["inker", "artist", "finishes"]
-    colorist_synonyms = ["colorist", "colourist", "colorer", "colourer"]
-    letterer_synonyms = ["letterer"]
-    cover_synonyms = ["cover", "covers", "coverartist", "cover artist"]
-    editor_synonyms = ["editor"]
+    writer_synonyms = ("writer", "plotter", "scripter", "script")
+    penciller_synonyms = ("artist", "penciller", "penciler", "breakdowns", "pencils", "painting")
+    inker_synonyms = ("inker", "artist", "finishes", "inks", "painting")
+    colorist_synonyms = ("colorist", "colourist", "colorer", "colourer", "colors", "painting")
+    letterer_synonyms = ("letterer", "letters")
+    cover_synonyms = ("cover", "covers", "coverartist", "cover artist")
+    editor_synonyms = ("editor", "edits", "editing")
+    translator_synonyms = ("translator", "translation")
 
     is_empty: bool = True
-    tag_origin: str | None = None
+    data_origin: MetadataOrigin | None = None
+    issue_id: str | None = None
+    series_id: str | None = None
 
     series: str | None = None
+    series_aliases: set[str] = dataclasses.field(default_factory=set)
     issue: str | None = None
-    title: str | None = None
-    publisher: str | None = None
-    month: int | None = None
-    year: int | None = None
-    day: int | None = None
     issue_count: int | None = None
+    title: str | None = None
+    title_aliases: set[str] = dataclasses.field(default_factory=set)
     volume: int | None = None
-    genre: str | None = None
-    language: str | None = None  # 2 letter iso code
-    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
-    country: str | None = None
+    genres: set[str] = dataclasses.field(default_factory=set)
+    description: str | None = None  # use same way as Summary in CIX
+    notes: str | None = None
 
     alternate_series: str | None = None
     alternate_number: str | None = None
     alternate_count: int | None = None
+    story_arcs: list[str] = dataclasses.field(default_factory=list)
+    series_groups: list[str] = dataclasses.field(default_factory=list)
+
+    publisher: str | None = None
     imprint: str | None = None
-    notes: str | None = None
-    web_link: str | None = None
+    day: int | None = None
+    month: int | None = None
+    year: int | None = None
+    language: str | None = None  # 2 letter iso code
+    country: str | None = None
+    web_links: list[Url] = dataclasses.field(default_factory=list)
     format: str | None = None
     manga: str | None = None
     black_and_white: bool | None = None
-    page_count: int | None = None
     maturity_rating: str | None = None
-
-    story_arc: str | None = None
-    series_group: str | None = None
+    critical_rating: float | None = None  # rating in CBL; CommunityRating in CIX
     scan_info: str | None = None
 
-    characters: str | None = None
-    teams: str | None = None
-    locations: str | None = None
-
-    credits: list[CreditMetadata] = dataclasses.field(default_factory=list)
     tags: set[str] = dataclasses.field(default_factory=set)
-    pages: list[ImageMetadata] = dataclasses.field(default_factory=list)
+    pages: list[PageMetadata] = dataclasses.field(default_factory=list)
+    page_count: int | None = None
+
+    characters: set[str] = dataclasses.field(default_factory=set)
+    teams: set[str] = dataclasses.field(default_factory=set)
+    locations: set[str] = dataclasses.field(default_factory=set)
+    credits: list[Credit] = dataclasses.field(default_factory=list)
 
     # Some CoMet-only items
-    price: str | None = None
+    price: float | None = None
     is_version_of: str | None = None
     rights: str | None = None
     identifier: str | None = None
     last_mark: str | None = None
-    cover_image: str | None = None
 
-    def __post_init__(self):
+    # urls to cover image, not generally part of the metadata
+    _cover_image: str | None = None
+    _alternate_images: list[str] = dataclasses.field(default_factory=list)
+
+    def __post_init__(self) -> None:
         for key, value in self.__dict__.items():
             if value and key != "is_empty":
                 self.is_empty = False
@@ -142,125 +219,208 @@ class GenericMetadata:
         tmp.__dict__.update(kwargs)
         return tmp
 
-    def overlay(self, new_md: GenericMetadata) -> None:
-        """Overlay a metadata object on this one
+    def _get_clean_metadata(self, *attributes: str) -> GenericMetadata:
+        new_md = GenericMetadata()
+        list_handled = []
+        for attr in sorted(attributes):
+            if "." in attr:
+                lst, _, name = attr.partition(".")
+                if lst in list_handled:
+                    continue
+                old_value = getattr(self, lst)
+                new_value = getattr(new_md, lst)
+                if old_value:
+                    if hasattr(old_value[0], "_get_clean_metadata"):
+                        list_attributes = [x.removeprefix(lst + ".") for x in attributes if x.startswith(lst)]
+                        for x in old_value:
+                            new_value.append(x._get_clean_metadata(*list_attributes))
+                        list_handled.append(lst)
+                        continue
+                    if not new_value:
+                        for x in old_value:
+                            new_value.append(x.__class__())
+                    for i, x in enumerate(old_value):
+                        if isinstance(x, dict):
+                            if name in x:
+                                new_value[i][name] = x[name]
+                        else:
+                            setattr(new_value[i], name, getattr(x, name))
 
-        That is, when the new object has non-None values, over-write them
-        to this one.
-        """
+            else:
+                old_value = getattr(self, attr)
+                if isinstance(old_value, list):
+                    continue
+                setattr(new_md, attr, old_value)
 
-        def assign(cur: str, new: Any) -> None:
-            if new is not None:
-                if isinstance(new, str) and len(new) == 0:
-                    setattr(self, cur, None)
-                else:
-                    setattr(self, cur, new)
+        new_md.__post_init__()
+        return new_md
+
+    def overlay(
+        self, new_md: GenericMetadata, mode: merge.Mode = merge.Mode.OVERLAY, merge_lists: bool = False
+    ) -> None:
+        """Overlay a new metadata object on this one"""
+
+        attribute_merge = merge.attribute[mode]
+        list_merge = merge.lists[mode]
+
+        def assign(old: Any, new: Any, attribute_merge: Any = attribute_merge) -> Any:
+            if new is REMOVE:
+                return None
+
+            return attribute_merge(old, new)
+
+        def assign_list(old: list[Any] | set[Any], new: list[Any] | set[Any], list_merge: Any = list_merge) -> Any:
+            if new is REMOVE:
+                old.clear()
+                return old
+            if merge_lists:
+                return list_merge(old, new)
+            else:
+                return assign(old, new)
 
         if not new_md.is_empty:
             self.is_empty = False
 
-        assign("series", new_md.series)
-        assign("issue", new_md.issue)
-        assign("issue_count", new_md.issue_count)
-        assign("title", new_md.title)
-        assign("publisher", new_md.publisher)
-        assign("day", new_md.day)
-        assign("month", new_md.month)
-        assign("year", new_md.year)
-        assign("volume", new_md.volume)
-        assign("volume_count", new_md.volume_count)
-        assign("genre", new_md.genre)
-        assign("language", new_md.language)
-        assign("country", new_md.country)
-        assign("critical_rating", new_md.critical_rating)
-        assign("alternate_series", new_md.alternate_series)
-        assign("alternate_number", new_md.alternate_number)
-        assign("alternate_count", new_md.alternate_count)
-        assign("imprint", new_md.imprint)
-        assign("web_link", new_md.web_link)
-        assign("format", new_md.format)
-        assign("manga", new_md.manga)
-        assign("black_and_white", new_md.black_and_white)
-        assign("maturity_rating", new_md.maturity_rating)
-        assign("story_arc", new_md.story_arc)
-        assign("series_group", new_md.series_group)
-        assign("scan_info", new_md.scan_info)
-        assign("characters", new_md.characters)
-        assign("teams", new_md.teams)
-        assign("locations", new_md.locations)
-        assign("comments", new_md.comments)
-        assign("notes", new_md.notes)
+        self.data_origin = assign(self.data_origin, new_md.data_origin)  # TODO use and purpose now?
+        self.issue_id = assign(self.issue_id, new_md.issue_id)
+        self.series_id = assign(self.series_id, new_md.series_id)
 
-        assign("price", new_md.price)
-        assign("is_version_of", new_md.is_version_of)
-        assign("rights", new_md.rights)
-        assign("identifier", new_md.identifier)
-        assign("last_mark", new_md.last_mark)
+        self.series = assign(self.series, new_md.series)
 
-        self.overlay_credits(new_md.credits)
-        # TODO
+        self.series_aliases = assign_list(self.series_aliases, new_md.series_aliases)
+        self.issue = assign(self.issue, new_md.issue)
+        self.issue_count = assign(self.issue_count, new_md.issue_count)
+        self.title = assign(self.title, new_md.title)
+        self.title_aliases = assign_list(self.title_aliases, new_md.title_aliases)
+        self.volume = assign(self.volume, new_md.volume)
+        self.volume_count = assign(self.volume_count, new_md.volume_count)
+        self.genres = assign_list(self.genres, new_md.genres)
+        self.description = assign(self.description, new_md.description)
+        self.notes = assign(self.notes, new_md.notes)
 
-        # not sure if the tags and pages should broken down, or treated
-        # as whole lists....
+        self.alternate_series = assign(self.alternate_series, new_md.alternate_series)
+        self.alternate_number = assign(self.alternate_number, new_md.alternate_number)
+        self.alternate_count = assign(self.alternate_count, new_md.alternate_count)
+        self.story_arcs = assign_list(self.story_arcs, new_md.story_arcs)
+        self.series_groups = assign_list(self.series_groups, new_md.series_groups)
 
-        # For now, go the easy route, where any overlay
-        # value wipes out the whole list
-        if len(new_md.tags) > 0:
-            assign("tags", new_md.tags)
+        self.publisher = assign(self.publisher, new_md.publisher)
+        self.imprint = assign(self.imprint, new_md.imprint)
+        self.day = assign(self.day, new_md.day)
+        self.month = assign(self.month, new_md.month)
+        self.year = assign(self.year, new_md.year)
+        self.language = assign(self.language, new_md.language)
+        self.country = assign(self.country, new_md.country)
+        self.web_links = assign_list(self.web_links, new_md.web_links)
+        self.format = assign(self.format, new_md.format)
+        self.manga = assign(self.manga, new_md.manga)
+        self.black_and_white = assign(self.black_and_white, new_md.black_and_white)
+        self.maturity_rating = assign(self.maturity_rating, new_md.maturity_rating)
+        self.critical_rating = assign(self.critical_rating, new_md.critical_rating)
+        self.scan_info = assign(self.scan_info, new_md.scan_info)
 
-        if len(new_md.pages) > 0:
-            assign("pages", new_md.pages)
+        self.tags = assign_list(self.tags, new_md.tags)
 
-    def overlay_credits(self, new_credits: list[CreditMetadata]) -> None:
-        for c in new_credits:
-            primary = bool("primary" in c and c["primary"])
+        self.characters = assign_list(self.characters, new_md.characters)
+        self.teams = assign_list(self.teams, new_md.teams)
+        self.locations = assign_list(self.locations, new_md.locations)
 
-            # Remove credit role if person is blank
-            if c["person"] == "":
-                for r in reversed(self.credits):
-                    if r["role"].casefold() == c["role"].casefold():
-                        self.credits.remove(r)
-            # otherwise, add it!
-            else:
-                self.add_credit(c["person"], c["role"], primary)
+        # credits are added through add_credit so that some standard checks are observed
+        # which means that we needs self.credits to be empty
+        tmp_credits = self.credits
+        self.credits = []
+        for c in assign_list(tmp_credits, new_md.credits):
+            self.add_credit(c)
 
-    def set_default_page_list(self, count: int) -> None:
-        # generate a default page list, with the first page marked as the cover
-        for i in range(count):
-            page_dict = ImageMetadata(Image=i)
-            if i == 0:
-                page_dict["Type"] = PageType.FrontCover
-            self.pages.append(page_dict)
+        self.price = assign(self.price, new_md.price)
+        self.is_version_of = assign(self.is_version_of, new_md.is_version_of)
+        self.rights = assign(self.rights, new_md.rights)
+        self.identifier = assign(self.identifier, new_md.identifier)
+        self.last_mark = assign(self.last_mark, new_md.last_mark)
+        self._cover_image = assign(self._cover_image, new_md._cover_image)
+        self._alternate_images = assign_list(self._alternate_images, new_md._alternate_images)
+
+        # pages doesn't get merged, if we did merge we would end up with duplicate pages
+        self.pages = assign(self.pages, new_md.pages)
+        self.page_count = assign(self.page_count, new_md.page_count)
+
+    def apply_default_page_list(self, page_list: Sequence[str]) -> None:
+        """apply a default page list, with the first page marked as the cover"""
+
+        # Create a dictionary in the weird case that the metadata doesn't match the archive
+        pages = {p.archive_index: p for p in self.pages}
+        cover_set = False
+
+        # It might be a good idea to validate that each page in `pages` is found in page_list
+        for i, filename in enumerate(page_list):
+            page = pages.get(i, PageMetadata(archive_index=i, display_index=i, filename="", type="", bookmark=""))
+            page.filename = filename
+            pages[i] = page
+
+            # Check if we know what the cover is
+            cover_set = page.type == PageType.FrontCover or cover_set
+        self.pages = sorted(pages.values())
+
+        self.page_count = len(self.pages)
+        if self.page_count != len(page_list):
+            logger.warning("Wrong count of pages: expected %d got %d", len(self.pages), len(page_list))
+        # Set the cover to the first image acording to hte display index if we don't know what the cover is
+        if not cover_set:
+            first_page = self.get_archive_page_index(0)
+            self.pages[first_page].type = PageType.FrontCover
 
     def get_archive_page_index(self, pagenum: int) -> int:
-        # convert the displayed page number to the page index of the file in the archive
+        """convert the displayed page number to the page index of the file in the archive"""
         if pagenum < len(self.pages):
-            return int(self.pages[pagenum]["Image"])
+            return int(sorted(self.pages, key=lambda p: p.display_index)[pagenum].archive_index)
 
         return 0
 
     def get_cover_page_index_list(self) -> list[int]:
         # return a list of archive page indices of cover pages
+        if not self.pages:
+            return [0]
         coverlist = []
         for p in self.pages:
-            if "Type" in p and p["Type"] == PageType.FrontCover:
-                coverlist.append(int(p["Image"]))
+            if p.type == PageType.FrontCover:
+                coverlist.append(p.archive_index)
 
         if len(coverlist) == 0:
-            coverlist.append(0)
+            coverlist.append(self.get_archive_page_index(0))
 
         return coverlist
 
-    def add_credit(self, person: str, role: str, primary: bool = False) -> None:
+    @overload
+    def add_credit(self, person: Credit) -> None: ...
 
-        credit = CreditMetadata(person=person, role=role, primary=primary)
+    @overload
+    def add_credit(self, person: str, role: str, primary: bool = False, language: str = "") -> None: ...
+
+    def add_credit(
+        self, person: str | Credit, role: str | None = None, primary: bool = False, language: str = ""
+    ) -> None:
+
+        credit: Credit
+        if isinstance(person, Credit):
+            credit = person
+        else:
+            assert role is not None
+            credit = Credit(person=person, role=role, primary=primary, language=language)
+
+        if credit.role is None:
+            raise TypeError("GenericMetadata.add_credit takes either a Credit object or a person name and role")
+        if credit.person == "":
+            return
+
+        person = norm_fold(credit.person)
+        role = norm_fold(credit.role)
 
         # look to see if it's not already there...
         found = False
         for c in self.credits:
-            if c["person"].casefold() == person.casefold() and c["role"].casefold() == role.casefold():
+            if norm_fold(c.person) == person and norm_fold(c.role) == role:
                 # no need to add it. just adjust the "primary" flag as needed
-                c["primary"] = primary
+                c.primary = c.primary or primary
                 found = True
                 break
 
@@ -270,12 +430,10 @@ class GenericMetadata:
     def get_primary_credit(self, role: str) -> str:
         primary = ""
         for credit in self.credits:
-            if "role" not in credit or "person" not in credit:
-                continue
-            if (primary == "" and credit["role"].casefold() == role.casefold()) or (
-                credit["role"].casefold() == role.casefold() and "primary" in credit and credit["primary"]
+            if (primary == "" and credit.role.casefold() == role.casefold()) or (
+                credit.role.casefold() == role.casefold() and credit.primary
             ):
-                primary = credit["person"]
+                primary = credit.person
         return primary
 
     def __str__(self) -> str:
@@ -284,59 +442,62 @@ class GenericMetadata:
             return "No metadata"
 
         def add_string(tag: str, val: Any) -> None:
-            if val is not None and str(val) != "":
+            if isinstance(val, (Sequence, set)):
+                if val:
+                    vals.append((tag, val))
+            elif val is not None:
                 vals.append((tag, val))
 
-        def add_attr_string(tag: str) -> None:
-            add_string(tag, getattr(self, tag))
+        add_string("data_origin", self.data_origin)
+        add_string("series", self.series)
+        add_string("series_aliases", ",".join(self.series_aliases))
+        add_string("issue", self.issue)
+        add_string("issue_count", self.issue_count)
+        add_string("title", self.title)
+        add_string("title_aliases", ",".join(self.title_aliases))
+        add_string("publisher", self.publisher)
+        add_string("year", self.year)
+        add_string("month", self.month)
+        add_string("day", self.day)
+        add_string("volume", self.volume)
+        add_string("volume_count", self.volume_count)
+        add_string("genres", ", ".join(self.genres))
+        add_string("language", self.language)
+        add_string("country", self.country)
+        add_string("critical_rating", self.critical_rating)
+        add_string("alternate_series", self.alternate_series)
+        add_string("alternate_number", self.alternate_number)
+        add_string("alternate_count", self.alternate_count)
+        add_string("imprint", self.imprint)
+        add_string("web_links", [str(x) for x in self.web_links])
+        add_string("format", self.format)
+        add_string("manga", self.manga)
 
-        add_attr_string("series")
-        add_attr_string("issue")
-        add_attr_string("issue_count")
-        add_attr_string("title")
-        add_attr_string("publisher")
-        add_attr_string("year")
-        add_attr_string("month")
-        add_attr_string("day")
-        add_attr_string("volume")
-        add_attr_string("volume_count")
-        add_attr_string("genre")
-        add_attr_string("language")
-        add_attr_string("country")
-        add_attr_string("critical_rating")
-        add_attr_string("alternate_series")
-        add_attr_string("alternate_number")
-        add_attr_string("alternate_count")
-        add_attr_string("imprint")
-        add_attr_string("web_link")
-        add_attr_string("format")
-        add_attr_string("manga")
-
-        add_attr_string("price")
-        add_attr_string("is_version_of")
-        add_attr_string("rights")
-        add_attr_string("identifier")
-        add_attr_string("last_mark")
+        add_string("price", self.price)
+        add_string("is_version_of", self.is_version_of)
+        add_string("rights", self.rights)
+        add_string("identifier", self.identifier)
+        add_string("last_mark", self.last_mark)
 
         if self.black_and_white:
-            add_attr_string("black_and_white")
-        add_attr_string("maturity_rating")
-        add_attr_string("story_arc")
-        add_attr_string("series_group")
-        add_attr_string("scan_info")
-        add_attr_string("characters")
-        add_attr_string("teams")
-        add_attr_string("locations")
-        add_attr_string("comments")
-        add_attr_string("notes")
+            add_string("black_and_white", self.black_and_white)
+        add_string("maturity_rating", self.maturity_rating)
+        add_string("story_arcs", self.story_arcs)
+        add_string("series_groups", self.series_groups)
+        add_string("scan_info", self.scan_info)
+        add_string("characters", ", ".join(self.characters))
+        add_string("teams", ", ".join(self.teams))
+        add_string("locations", ", ".join(self.locations))
+        add_string("description", self.description)
+        add_string("notes", self.notes)
 
         add_string("tags", ", ".join(self.tags))
 
         for c in self.credits:
             primary = ""
-            if "primary" in c and c["primary"]:
+            if c.primary:
                 primary = " [P]"
-            add_string("credit", c["role"] + ": " + c["person"] + primary)
+            add_string("credit", f"{c}{primary}")
 
         # find the longest field name
         flen = 0
@@ -373,9 +534,11 @@ class GenericMetadata:
 
 md_test: GenericMetadata = GenericMetadata(
     is_empty=False,
-    tag_origin=None,
+    data_origin=MetadataOrigin("comicvine", "Comic Vine"),
     series="Cory Doctorow's Futuristic Tales of the Here and Now",
+    series_id="23437",
     issue="1",
+    issue_id="140529",
     title="Anda's Game",
     publisher="IDW Publishing",
     month=10,
@@ -383,9 +546,9 @@ md_test: GenericMetadata = GenericMetadata(
     day=1,
     issue_count=6,
     volume=1,
-    genre="Sci-Fi",
+    genres={"Sci-Fi"},
     language="en",
-    comments=(
+    description=(
         "For 12-year-old Anda, getting paid real money to kill the characters of players who were cheating"
         " in her favorite online computer game was a win-win situation. Until she found out who was paying her,"
         " and what those characters meant to the livelihood of children around the world."
@@ -398,58 +561,269 @@ md_test: GenericMetadata = GenericMetadata(
     alternate_count=7,
     imprint="craphound.com",
     notes="Tagged with ComicTagger 1.3.2a5 using info from Comic Vine on 2022-04-16 15:52:26. [Issue ID 140529]",
-    web_link="https://comicvine.gamespot.com/cory-doctorows-futuristic-tales-of-the-here-and-no/4000-140529/",
+    web_links=[
+        parse_url("https://comicvine.gamespot.com/cory-doctorows-futuristic-tales-of-the-here-and-no/4000-140529/")
+    ],
     format="Series",
     manga="No",
     black_and_white=None,
     page_count=24,
     maturity_rating="Everyone 10+",
-    story_arc="Here and Now",
-    series_group="Futuristic Tales",
+    story_arcs=["Here and Now"],
+    series_groups=["Futuristic Tales"],
     scan_info="(CC BY-NC-SA 3.0)",
-    characters="Anda",
-    teams="Fahrenheit",
-    locations="lonely  cottage ",
+    characters={"Anda"},
+    teams={"Fahrenheit"},
+    locations=set(utils.split("lonely  cottage ", ",")),
     credits=[
-        CreditMetadata(primary=False, person="Dara Naraghi", role="Writer"),
-        CreditMetadata(primary=False, person="Esteve Polls", role="Penciller"),
-        CreditMetadata(primary=False, person="Esteve Polls", role="Inker"),
-        CreditMetadata(primary=False, person="Neil Uyetake", role="Letterer"),
-        CreditMetadata(primary=False, person="Sam Kieth", role="Cover"),
-        CreditMetadata(primary=False, person="Ted Adams", role="Editor"),
+        Credit(primary=False, person="Dara Naraghi", role="Writer"),
+        Credit(primary=False, person="Esteve Polls", role="Penciller"),
+        Credit(primary=False, person="Esteve Polls", role="Inker"),
+        Credit(primary=False, person="Neil Uyetake", role="Letterer"),
+        Credit(primary=False, person="Sam Kieth", role="Cover"),
+        Credit(primary=False, person="Ted Adams", role="Editor"),
     ],
     tags=set(),
     pages=[
-        ImageMetadata(Image=0, ImageHeight="1280", ImageSize="195977", ImageWidth="800", Type=PageType.FrontCover),
-        ImageMetadata(Image=1, ImageHeight="2039", ImageSize="611993", ImageWidth="1327"),
-        ImageMetadata(Image=2, ImageHeight="2039", ImageSize="783726", ImageWidth="1327"),
-        ImageMetadata(Image=3, ImageHeight="2039", ImageSize="679584", ImageWidth="1327"),
-        ImageMetadata(Image=4, ImageHeight="2039", ImageSize="788179", ImageWidth="1327"),
-        ImageMetadata(Image=5, ImageHeight="2039", ImageSize="864433", ImageWidth="1327"),
-        ImageMetadata(Image=6, ImageHeight="2039", ImageSize="765606", ImageWidth="1327"),
-        ImageMetadata(Image=7, ImageHeight="2039", ImageSize="876427", ImageWidth="1327"),
-        ImageMetadata(Image=8, ImageHeight="2039", ImageSize="852622", ImageWidth="1327"),
-        ImageMetadata(Image=9, ImageHeight="2039", ImageSize="800205", ImageWidth="1327"),
-        ImageMetadata(Image=10, ImageHeight="2039", ImageSize="746243", ImageWidth="1326"),
-        ImageMetadata(Image=11, ImageHeight="2039", ImageSize="718062", ImageWidth="1327"),
-        ImageMetadata(Image=12, ImageHeight="2039", ImageSize="532179", ImageWidth="1326"),
-        ImageMetadata(Image=13, ImageHeight="2039", ImageSize="686708", ImageWidth="1327"),
-        ImageMetadata(Image=14, ImageHeight="2039", ImageSize="641907", ImageWidth="1327"),
-        ImageMetadata(Image=15, ImageHeight="2039", ImageSize="805388", ImageWidth="1327"),
-        ImageMetadata(Image=16, ImageHeight="2039", ImageSize="668927", ImageWidth="1326"),
-        ImageMetadata(Image=17, ImageHeight="2039", ImageSize="710605", ImageWidth="1327"),
-        ImageMetadata(Image=18, ImageHeight="2039", ImageSize="761398", ImageWidth="1326"),
-        ImageMetadata(Image=19, ImageHeight="2039", ImageSize="743807", ImageWidth="1327"),
-        ImageMetadata(Image=20, ImageHeight="2039", ImageSize="552911", ImageWidth="1326"),
-        ImageMetadata(Image=21, ImageHeight="2039", ImageSize="556827", ImageWidth="1327"),
-        ImageMetadata(Image=22, ImageHeight="2039", ImageSize="675078", ImageWidth="1326"),
-        ImageMetadata(
-            Bookmark="Interview",
-            Image=23,
-            ImageHeight="2032",
-            ImageSize="800965",
-            ImageWidth="1338",
-            Type=PageType.Letters,
+        PageMetadata(
+            archive_index=0,
+            display_index=0,
+            height=1280,
+            byte_size=195977,
+            width=800,
+            type=PageType.FrontCover,
+            filename="!cover.jpg",
+            bookmark="",
+        ),
+        PageMetadata(
+            archive_index=1,
+            display_index=1,
+            height=2039,
+            byte_size=611993,
+            width=1327,
+            filename="01.jpg",
+            bookmark="",
+            type="",
+        ),
+        PageMetadata(
+            archive_index=2,
+            display_index=2,
+            height=2039,
+            byte_size=783726,
+            width=1327,
+            filename="02.jpg",
+            bookmark="",
+            type="",
+        ),
+        PageMetadata(
+            archive_index=3,
+            display_index=3,
+            height=2039,
+            byte_size=679584,
+            width=1327,
+            filename="03.jpg",
+            bookmark="",
+            type="",
+        ),
+        PageMetadata(
+            archive_index=4,
+            display_index=4,
+            height=2039,
+            byte_size=788179,
+            width=1327,
+            filename="04.jpg",
+            bookmark="",
+            type="",
+        ),
+        PageMetadata(
+            archive_index=5,
+            display_index=5,
+            height=2039,
+            byte_size=864433,
+            width=1327,
+            filename="05.jpg",
+            bookmark="",
+            type="",
+        ),
+        PageMetadata(
+            archive_index=6,
+            display_index=6,
+            height=2039,
+            byte_size=765606,
+            width=1327,
+            filename="06.jpg",
+            bookmark="",
+            type="",
+        ),
+        PageMetadata(
+            archive_index=7,
+            display_index=7,
+            height=2039,
+            byte_size=876427,
+            width=1327,
+            filename="07.jpg",
+            bookmark="",
+            type="",
+        ),
+        PageMetadata(
+            archive_index=8,
+            display_index=8,
+            height=2039,
+            byte_size=852622,
+            width=1327,
+            filename="08.jpg",
+            bookmark="",
+            type="",
+        ),
+        PageMetadata(
+            archive_index=9,
+            display_index=9,
+            height=2039,
+            byte_size=800205,
+            width=1327,
+            filename="09.jpg",
+            bookmark="",
+            type="",
+        ),
+        PageMetadata(
+            archive_index=10,
+            display_index=10,
+            height=2039,
+            byte_size=746243,
+            width=1326,
+            filename="10.jpg",
+            bookmark="",
+            type="",
+        ),
+        PageMetadata(
+            archive_index=11,
+            display_index=11,
+            height=2039,
+            byte_size=718062,
+            width=1327,
+            filename="11.jpg",
+            bookmark="",
+            type="",
+        ),
+        PageMetadata(
+            archive_index=12,
+            display_index=12,
+            height=2039,
+            byte_size=532179,
+            width=1326,
+            filename="12.jpg",
+            bookmark="",
+            type="",
+        ),
+        PageMetadata(
+            archive_index=13,
+            display_index=13,
+            height=2039,
+            byte_size=686708,
+            width=1327,
+            filename="13.jpg",
+            bookmark="",
+            type="",
+        ),
+        PageMetadata(
+            archive_index=14,
+            display_index=14,
+            height=2039,
+            byte_size=641907,
+            width=1327,
+            filename="14.jpg",
+            bookmark="",
+            type="",
+        ),
+        PageMetadata(
+            archive_index=15,
+            display_index=15,
+            height=2039,
+            byte_size=805388,
+            width=1327,
+            filename="15.jpg",
+            bookmark="",
+            type="",
+        ),
+        PageMetadata(
+            archive_index=16,
+            display_index=16,
+            height=2039,
+            byte_size=668927,
+            width=1326,
+            filename="16.jpg",
+            bookmark="",
+            type="",
+        ),
+        PageMetadata(
+            archive_index=17,
+            display_index=17,
+            height=2039,
+            byte_size=710605,
+            width=1327,
+            filename="17.jpg",
+            bookmark="",
+            type="",
+        ),
+        PageMetadata(
+            archive_index=18,
+            display_index=18,
+            height=2039,
+            byte_size=761398,
+            width=1326,
+            filename="18.jpg",
+            bookmark="",
+            type="",
+        ),
+        PageMetadata(
+            archive_index=19,
+            display_index=19,
+            height=2039,
+            byte_size=743807,
+            width=1327,
+            filename="19.jpg",
+            bookmark="",
+            type="",
+        ),
+        PageMetadata(
+            archive_index=20,
+            display_index=20,
+            height=2039,
+            byte_size=552911,
+            width=1326,
+            filename="20.jpg",
+            bookmark="",
+            type="",
+        ),
+        PageMetadata(
+            archive_index=21,
+            display_index=21,
+            height=2039,
+            byte_size=556827,
+            width=1327,
+            filename="21.jpg",
+            bookmark="",
+            type="",
+        ),
+        PageMetadata(
+            archive_index=22,
+            display_index=22,
+            height=2039,
+            byte_size=675078,
+            width=1326,
+            filename="22.jpg",
+            bookmark="",
+            type="",
+        ),
+        PageMetadata(
+            bookmark="Interview",
+            archive_index=23,
+            display_index=23,
+            height=2032,
+            byte_size=800965,
+            width=1338,
+            type=PageType.Letters,
+            filename="23.jpg",
         ),
     ],
     price=None,
@@ -457,5 +831,17 @@ md_test: GenericMetadata = GenericMetadata(
     rights=None,
     identifier=None,
     last_mark=None,
-    cover_image=None,
+    _cover_image=None,
+)
+
+
+__all__ = (
+    "Url",
+    "parse_url",
+    "PageType",
+    "PageMetadata",
+    "Credit",
+    "ComicSeries",
+    "MetadataOrigin",
+    "GenericMetadata",
 )

comicapi/issuestring.py

@@ -4,7 +4,8 @@ Class for handling the odd permutations of an 'issue number' that the
 comics industry throws at us.
   e.g.: "12", "12.1", "0", "-1", "5AU", "100-2"
 """
-# Copyright 2012-2014 Anthony Beville
+
+# Copyright 2012-2014 ComicTagger Authors
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -27,12 +28,12 @@ logger = logging.getLogger(__name__)
 
 class IssueString:
     def __init__(self, text: str | None) -> None:
-
         # break up the issue number string into 2 parts: the numeric and suffix string.
         # (assumes that the numeric portion is always first)
 
         self.num = None
         self.suffix = ""
+        self.prefix = ""
 
         if text is None:
             return
@@ -42,18 +43,25 @@ class IssueString:
         if len(text) == 0:
             return
 
+        for idx, r in enumerate(text):
+            if not r.isalpha():
+                break
+        self.prefix = text[:idx]
+        self.num, self.suffix = self.get_number(text[idx:])
+
+    def get_number(self, text: str) -> tuple[float | None, str]:
+        num, suffix = None, ""
+        start = 0
         # skip the minus sign if it's first
-        if text[0] == "-":
+        if text[0] in ("-", "+"):
             start = 1
-        else:
-            start = 0
 
         # if it's still not numeric at start skip it
         if text[start].isdigit() or text[start] == ".":
             # walk through the string, look for split point (the first non-numeric)
             decimal_count = 0
             for idx in range(start, len(text)):
-                if text[idx] not in "0123456789.":
+                if not (text[idx].isdigit() or text[idx] in "."):
                     break
                 # special case: also split on second "."
                 if text[idx] == ".":
@@ -72,42 +80,48 @@ class IssueString:
             if idx == 1 and start == 1:
                 idx = 0
 
-            part1 = text[0:idx]
-            part2 = text[idx : len(text)]
-
-            if part1 != "":
-                self.num = float(part1)
-            self.suffix = part2
+            if text[0:idx]:
+                num = float(text[0:idx])
+            suffix = text[idx : len(text)]
         else:
-            self.suffix = text
+            suffix = text
+        return num, suffix
 
     def as_string(self, pad: int = 0) -> str:
-        # return the float, left side zero-padded, with suffix attached
+        """return the number, left side zero-padded, with suffix attached"""
+
+        # if there is no number return the text
         if self.num is None:
-            return self.suffix
+            return self.prefix + self.suffix
 
+        # negative is added back in last
         negative = self.num < 0
-
         num_f = abs(self.num)
 
+        # used for padding
         num_int = int(num_f)
-        num_s = str(num_int)
-        if float(num_int) != num_f:
-            num_s = str(num_f)
 
-        num_s += self.suffix
+        if num_f.is_integer():
+            num_s = str(num_int)
+        else:
+            num_s = str(num_f)
 
         # create padding
         padding = ""
+        # we only pad the whole number part, we don't care about the decimal
         length = len(str(num_int))
         if length < pad:
             padding = "0" * (pad - length)
 
+        # add the padding to the front
         num_s = padding + num_s
+
+        # finally add the negative back in
         if negative:
             num_s = "-" + num_s
 
-        return num_s
+        # return the prefix + formatted number + suffix
+        return self.prefix + num_s + self.suffix
 
     def as_float(self) -> float | None:
         # return the float, with no suffix

comicapi/merge.py

@@ -0,0 +1,73 @@
+from __future__ import annotations
+
+import dataclasses
+from collections import defaultdict
+from collections.abc import Collection
+from enum import auto
+from typing import Any
+
+from comicapi.utils import StrEnum, norm_fold
+
+
+@dataclasses.dataclass
+class Credit:
+    person: str = ""
+    role: str = ""
+    primary: bool = False
+    language: str = ""  # Should be ISO 639 language code
+
+    def __str__(self) -> str:
+        lang = ""
+        if self.language:
+            lang = f" [{self.language}]"
+        return f"{self.role}: {self.person}{lang}"
+
+
+class Mode(StrEnum):
+    OVERLAY = auto()
+    ADD_MISSING = auto()
+
+
+def merge_lists(old: Collection[Any], new: Collection[Any]) -> list[Any] | set[Any]:
+    """Dedupes normalised (NFKD), casefolded values using 'new' values on collisions"""
+    if len(new) == 0:
+        return old if isinstance(old, set) else list(old)
+    if len(old) == 0:
+        return new if isinstance(new, set) else list(new)
+
+    # Create dict to preserve case
+    new_dict = {norm_fold(str(n)): n for n in new}
+    old_dict = {norm_fold(str(c)): c for c in old}
+
+    old_dict.update(new_dict)
+
+    if isinstance(old, set):
+        return set(old_dict.values())
+
+    return list(old_dict.values())
+
+
+def overlay(old: Any, new: Any) -> Any:
+    """overlay - When the `new` object is not empty, replace `old` with `new`."""
+    if new is None or (isinstance(new, Collection) and len(new) == 0):
+        return old
+
+    return new
+
+
+attribute = defaultdict(
+    lambda: overlay,
+    {
+        Mode.OVERLAY: overlay,
+        Mode.ADD_MISSING: lambda old, new: overlay(new, old),
+    },
+)
+
+
+lists = defaultdict(
+    lambda: overlay,
+    {
+        Mode.OVERLAY: merge_lists,
+        Mode.ADD_MISSING: lambda old, new: merge_lists(new, old),
+    },
+)

comicapi/tags/__init__.py

@@ -0,0 +1,5 @@
+from __future__ import annotations
+
+from comicapi.tags.tag import Tag
+
+__all__ = ["Tag"]

comicapi/tags/comicrack.py

@@ -0,0 +1,400 @@
+"""A class to encapsulate ComicRack's ComicInfo.xml data"""
+
+# Copyright 2012-2014 ComicTagger Authors
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+from __future__ import annotations
+
+import logging
+import xml.etree.ElementTree as ET
+from typing import Any
+
+from comicapi import utils
+from comicapi.archivers import Archiver
+from comicapi.genericmetadata import GenericMetadata, PageMetadata
+from comicapi.tags import Tag
+
+logger = logging.getLogger(__name__)
+
+
+class ComicRack(Tag):
+    enabled = True
+
+    id = "cr"
+
+    def __init__(self, version: str) -> None:
+        super().__init__(version)
+
+        self.file = "ComicInfo.xml"
+        self.supported_attributes = {
+            "series",
+            "issue",
+            "issue_count",
+            "title",
+            "volume",
+            "genres",
+            "description",
+            "notes",
+            "alternate_series",
+            "alternate_number",
+            "alternate_count",
+            "story_arcs",
+            "series_groups",
+            "publisher",
+            "imprint",
+            "day",
+            "month",
+            "year",
+            "language",
+            "web_links",
+            "format",
+            "manga",
+            "black_and_white",
+            "maturity_rating",
+            "critical_rating",
+            "scan_info",
+            "pages",
+            "pages.bookmark",
+            "pages.double_page",
+            "pages.height",
+            "pages.image_index",
+            "pages.size",
+            "pages.type",
+            "pages.width",
+            "page_count",
+            "characters",
+            "teams",
+            "locations",
+            "credits",
+            "credits.person",
+            "credits.role",
+        }
+
+    def supports_credit_role(self, role: str) -> bool:
+        return role.casefold() in self._get_parseable_credits()
+
+    def supports_tags(self, archive: Archiver) -> bool:
+        return archive.supports_files()
+
+    def has_tags(self, archive: Archiver) -> bool:
+        try:  # read_file can cause an exception
+            return (
+                self.supports_tags(archive)
+                and self.file in archive.get_filename_list()
+                and self._validate_bytes(archive.read_file(self.file))
+            )
+        except Exception:
+            return False
+
+    def remove_tags(self, archive: Archiver) -> bool:
+        return self.has_tags(archive) and archive.remove_file(self.file)
+
+    def read_tags(self, archive: Archiver) -> GenericMetadata:
+        if self.has_tags(archive):
+            try:  # read_file can cause an exception
+                metadata = archive.read_file(self.file) or b""
+                if self._validate_bytes(metadata):
+                    return self._metadata_from_bytes(metadata)
+            except Exception:
+                ...
+        return GenericMetadata()
+
+    def read_raw_tags(self, archive: Archiver) -> str:
+        try:  # read_file can cause an exception
+            if self.has_tags(archive):
+                b = archive.read_file(self.file)
+                # ET.fromstring is used as xml can declare the encoding
+                return ET.tostring(ET.fromstring(b), encoding="unicode", xml_declaration=True)
+        except Exception:
+            ...
+        return ""
+
+    def write_tags(self, metadata: GenericMetadata, archive: Archiver) -> bool:
+        if self.supports_tags(archive):
+            xml = b""
+            try:  # read_file can cause an exception
+                if self.has_tags(archive):
+                    xml = archive.read_file(self.file)
+                return archive.write_file(self.file, self._bytes_from_metadata(metadata, xml))
+            except Exception:
+                ...
+        else:
+            logger.warning(f"Archive ({archive.name()}) does not support {self.name()} metadata")
+        return False
+
+    def name(self) -> str:
+        return "Comic Rack"
+
+    @classmethod
+    def _get_parseable_credits(cls) -> list[str]:
+        parsable_credits: list[str] = []
+        parsable_credits.extend(GenericMetadata.writer_synonyms)
+        parsable_credits.extend(GenericMetadata.penciller_synonyms)
+        parsable_credits.extend(GenericMetadata.inker_synonyms)
+        parsable_credits.extend(GenericMetadata.colorist_synonyms)
+        parsable_credits.extend(GenericMetadata.letterer_synonyms)
+        parsable_credits.extend(GenericMetadata.cover_synonyms)
+        parsable_credits.extend(GenericMetadata.editor_synonyms)
+        return parsable_credits
+
+    def _metadata_from_bytes(self, string: bytes) -> GenericMetadata:
+        root = ET.fromstring(string)
+        return self._convert_xml_to_metadata(root)
+
+    def _bytes_from_metadata(self, metadata: GenericMetadata, xml: bytes = b"") -> bytes:
+        root = self._convert_metadata_to_xml(metadata, xml)
+        return ET.tostring(root, encoding="utf-8", xml_declaration=True)
+
+    def _convert_metadata_to_xml(self, metadata: GenericMetadata, xml: bytes = b"") -> ET.Element:
+        # shorthand for the metadata
+        md = metadata
+
+        if xml:
+            root = ET.fromstring(xml)
+        else:
+            # build a tree structure
+            root = ET.Element("ComicInfo")
+            root.attrib["xmlns:xsi"] = "http://www.w3.org/2001/XMLSchema-instance"
+            root.attrib["xmlns:xsd"] = "http://www.w3.org/2001/XMLSchema"
+        # helper func
+
+        def assign(cr_entry: str, md_entry: Any) -> None:
+            if md_entry:
+                text = str(md_entry)
+                if isinstance(md_entry, (list, set)):
+                    text = ",".join(md_entry)
+                et_entry = root.find(cr_entry)
+                if et_entry is not None:
+                    et_entry.text = text
+                else:
+                    ET.SubElement(root, cr_entry).text = text
+            else:
+                et_entry = root.find(cr_entry)
+                if et_entry is not None:
+                    root.remove(et_entry)
+
+        # need to specially process the credits, since they are structured
+        # differently than CIX
+        credit_writer_list = []
+        credit_penciller_list = []
+        credit_inker_list = []
+        credit_colorist_list = []
+        credit_letterer_list = []
+        credit_cover_list = []
+        credit_editor_list = []
+
+        # first, loop thru credits, and build a list for each role that CIX
+        # supports
+        for credit in metadata.credits:
+            if credit.role.casefold() in set(GenericMetadata.writer_synonyms):
+                credit_writer_list.append(credit.person.replace(",", ""))
+
+            if credit.role.casefold() in set(GenericMetadata.penciller_synonyms):
+                credit_penciller_list.append(credit.person.replace(",", ""))
+
+            if credit.role.casefold() in set(GenericMetadata.inker_synonyms):
+                credit_inker_list.append(credit.person.replace(",", ""))
+
+            if credit.role.casefold() in set(GenericMetadata.colorist_synonyms):
+                credit_colorist_list.append(credit.person.replace(",", ""))
+
+            if credit.role.casefold() in set(GenericMetadata.letterer_synonyms):
+                credit_letterer_list.append(credit.person.replace(",", ""))
+
+            if credit.role.casefold() in set(GenericMetadata.cover_synonyms):
+                credit_cover_list.append(credit.person.replace(",", ""))
+
+            if credit.role.casefold() in set(GenericMetadata.editor_synonyms):
+                credit_editor_list.append(credit.person.replace(",", ""))
+
+        assign("Series", md.series)
+        assign("Number", md.issue)
+        assign("Count", md.issue_count)
+        assign("Title", md.title)
+        assign("Volume", md.volume)
+        assign("Genre", md.genres)
+        assign("Summary", md.description)
+        assign("Notes", md.notes)
+
+        assign("AlternateSeries", md.alternate_series)
+        assign("AlternateNumber", md.alternate_number)
+        assign("AlternateCount", md.alternate_count)
+        assign("StoryArc", md.story_arcs)
+        assign("SeriesGroup", md.series_groups)
+
+        assign("Publisher", md.publisher)
+        assign("Imprint", md.imprint)
+        assign("Day", md.day)
+        assign("Month", md.month)
+        assign("Year", md.year)
+        assign("LanguageISO", md.language)
+        assign("Web", " ".join(u.url for u in md.web_links))
+        assign("Format", md.format)
+        assign("Manga", md.manga)
+        assign("BlackAndWhite", "Yes" if md.black_and_white else None)
+        assign("AgeRating", md.maturity_rating)
+        assign("CommunityRating", md.critical_rating)
+        assign("ScanInformation", md.scan_info)
+
+        assign("PageCount", md.page_count)
+
+        assign("Characters", md.characters)
+        assign("Teams", md.teams)
+        assign("Locations", md.locations)
+        assign("Writer", ", ".join(credit_writer_list))
+        assign("Penciller", ", ".join(credit_penciller_list))
+        assign("Inker", ", ".join(credit_inker_list))
+        assign("Colorist", ", ".join(credit_colorist_list))
+        assign("Letterer", ", ".join(credit_letterer_list))
+        assign("CoverArtist", ", ".join(credit_cover_list))
+        assign("Editor", ", ".join(credit_editor_list))
+
+        #  loop and add the page entries under pages node
+        pages_node = root.find("Pages")
+        if pages_node is not None:
+            pages_node.clear()
+        else:
+            pages_node = ET.SubElement(root, "Pages")
+
+        for page in sorted(md.pages, key=lambda x: x.archive_index):
+            page_node = ET.SubElement(pages_node, "Page")
+            page_node.attrib = {"Image": str(page.display_index)}
+            if page.bookmark:
+                page_node.attrib["Bookmark"] = page.bookmark
+            if page.type:
+                page_node.attrib["Type"] = page.type
+
+            if page.double_page is not None:
+                page_node.attrib["DoublePage"] = str(page.double_page)
+            if page.height is not None:
+                page_node.attrib["ImageHeight"] = str(page.height)
+            if page.byte_size is not None:
+                page_node.attrib["ImageSize"] = str(page.byte_size)
+            if page.width is not None:
+                page_node.attrib["ImageWidth"] = str(page.width)
+            page_node.attrib = dict(sorted(page_node.attrib.items()))
+
+        ET.indent(root)
+
+        return root
+
+    def _convert_xml_to_metadata(self, root: ET.Element) -> GenericMetadata:
+        if root.tag != "ComicInfo":
+            raise Exception("Not a ComicInfo file")
+
+        def get(name: str) -> str | None:
+            tag = root.find(name)
+            if tag is None:
+                return None
+            return tag.text
+
+        md = GenericMetadata()
+
+        md.series = utils.xlate(get("Series"))
+        md.issue = utils.xlate(get("Number"))
+        md.issue_count = utils.xlate_int(get("Count"))
+        md.title = utils.xlate(get("Title"))
+        md.volume = utils.xlate_int(get("Volume"))
+        md.genres = set(utils.split(get("Genre"), ","))
+        md.description = utils.xlate(get("Summary"))
+        md.notes = utils.xlate(get("Notes"))
+
+        md.alternate_series = utils.xlate(get("AlternateSeries"))
+        md.alternate_number = utils.xlate(get("AlternateNumber"))
+        md.alternate_count = utils.xlate_int(get("AlternateCount"))
+        md.story_arcs = utils.split(get("StoryArc"), ",")
+        md.series_groups = utils.split(get("SeriesGroup"), ",")
+
+        md.publisher = utils.xlate(get("Publisher"))
+        md.imprint = utils.xlate(get("Imprint"))
+        md.day = utils.xlate_int(get("Day"))
+        md.month = utils.xlate_int(get("Month"))
+        md.year = utils.xlate_int(get("Year"))
+        md.language = utils.xlate(get("LanguageISO"))
+        md.web_links = utils.split_urls(utils.xlate(get("Web")))
+        md.format = utils.xlate(get("Format"))
+        md.manga = utils.xlate(get("Manga"))
+        md.maturity_rating = utils.xlate(get("AgeRating"))
+        md.critical_rating = utils.xlate_float(get("CommunityRating"))
+        md.scan_info = utils.xlate(get("ScanInformation"))
+
+        md.page_count = utils.xlate_int(get("PageCount"))
+
+        md.characters = set(utils.split(get("Characters"), ","))
+        md.teams = set(utils.split(get("Teams"), ","))
+        md.locations = set(utils.split(get("Locations"), ","))
+
+        tmp = utils.xlate(get("BlackAndWhite"))
+        if tmp is not None:
+            md.black_and_white = tmp.casefold() in ["yes", "true", "1"]
+
+        # Now extract the credit info
+        for n in root:
+            if any(
+                [
+                    n.tag == "Writer",
+                    n.tag == "Penciller",
+                    n.tag == "Inker",
+                    n.tag == "Colorist",
+                    n.tag == "Letterer",
+                    n.tag == "Editor",
+                ]
+            ):
+                if n.text is not None:
+                    for name in utils.split(n.text, ","):
+                        md.add_credit(name.strip(), n.tag)
+
+            if n.tag == "CoverArtist":
+                if n.text is not None:
+                    for name in utils.split(n.text, ","):
+                        md.add_credit(name.strip(), "Cover")
+
+        # parse page data now
+        pages_node = root.find("Pages")
+        if pages_node is not None:
+            for i, page in enumerate(pages_node):
+                p: dict[str, Any] = page.attrib
+                md_page = PageMetadata(
+                    filename="",  # cr doesn't record the filename it just assumes it's always ordered the same
+                    display_index=int(p.get("Image", i)),
+                    archive_index=i,
+                    bookmark=p.get("Bookmark", ""),
+                    type="",
+                )
+                md_page.set_type(p.get("Type", ""))
+
+                if isinstance(p.get("DoublePage", None), str):
+                    md_page.double_page = p["DoublePage"].casefold() in ("yes", "true", "1")
+                if p.get("ImageHeight", "").isnumeric():
+                    md_page.height = int(float(p["ImageHeight"]))
+                if p.get("ImageWidth", "").isnumeric():
+                    md_page.width = int(float(p["ImageWidth"]))
+                if p.get("ImageSize", "").isnumeric():
+                    md_page.byte_size = int(float(p["ImageSize"]))
+
+                md.pages.append(md_page)
+
+        md.is_empty = False
+
+        return md
+
+    def _validate_bytes(self, string: bytes) -> bool:
+        """verify that the string actually contains CIX data in XML format"""
+        try:
+            root = ET.fromstring(string)
+            if root.tag != "ComicInfo":
+                return False
+        except ET.ParseError:
+            return False
+
+        return True

comicapi/tags/tag.py

@@ -0,0 +1,124 @@
+from __future__ import annotations
+
+from comicapi.archivers import Archiver
+from comicapi.genericmetadata import GenericMetadata
+
+
+class Tag:
+    enabled: bool = False
+    id: str = ""
+
+    def __init__(self, version: str) -> None:
+        self.version: str = version
+        self.supported_attributes = {
+            "data_origin",
+            "issue_id",
+            "series_id",
+            "series",
+            "series_aliases",
+            "issue",
+            "issue_count",
+            "title",
+            "title_aliases",
+            "volume",
+            "volume_count",
+            "genres",
+            "description",
+            "notes",
+            "alternate_series",
+            "alternate_number",
+            "alternate_count",
+            "story_arcs",
+            "series_groups",
+            "publisher",
+            "imprint",
+            "day",
+            "month",
+            "year",
+            "language",
+            "country",
+            "web_link",
+            "format",
+            "manga",
+            "black_and_white",
+            "maturity_rating",
+            "critical_rating",
+            "scan_info",
+            "tags",
+            "pages",
+            "pages.type",
+            "pages.bookmark",
+            "pages.double_page",
+            "pages.image_index",
+            "pages.size",
+            "pages.height",
+            "pages.width",
+            "page_count",
+            "characters",
+            "teams",
+            "locations",
+            "credits",
+            "credits.person",
+            "credits.role",
+            "credits.primary",
+            "credits.language",
+            "price",
+            "is_version_of",
+            "rights",
+            "identifier",
+            "last_mark",
+        }
+
+    def supports_credit_role(self, role: str) -> bool:
+        return False
+
+    def supports_tags(self, archive: Archiver) -> bool:
+        """
+        Checks the given archive for the ability to save these tags.
+        Should always return a bool. Failures should return False.
+        Typically consists of a call to either `archive.supports_comment` or `archive.supports_file`
+        """
+        return False
+
+    def has_tags(self, archive: Archiver) -> bool:
+        """
+        Checks the given archive for tags.
+        Should always return a bool. Failures should return False.
+        """
+        return False
+
+    def remove_tags(self, archive: Archiver) -> bool:
+        """
+        Removes the tags from the given archive.
+        Should always return a bool. Failures should return False.
+        """
+        return False
+
+    def read_tags(self, archive: Archiver) -> GenericMetadata:
+        """
+        Returns a GenericMetadata representing the tags saved in the given archive.
+        Should always return a GenericMetadata. Failures should return an empty metadata object.
+        """
+        return GenericMetadata()
+
+    def read_raw_tags(self, archive: Archiver) -> str:
+        """
+        Returns the raw tags as a string.
+        If the tags are a binary format a roughly similar text format should be used.
+        Should always return a string. Failures should return the empty string.
+        """
+        return ""
+
+    def write_tags(self, metadata: GenericMetadata, archive: Archiver) -> bool:
+        """
+        Saves the given metadata to the given archive.
+        Should always return a bool. Failures should return False.
+        """
+        return False
+
+    def name(self) -> str:
+        """
+        Returns the name of these tags for display purposes eg "Comic Rack".
+        Should always return a string. Failures should return the empty string.
+        """
+        return ""

comicapi/utils.py

@@ -1,5 +1,6 @@
 """Some generic utilities"""
-# Copyright 2012-2014 Anthony Beville
+
+# Copyright 2012-2014 ComicTagger Authors
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -14,53 +15,313 @@
 # limitations under the License.
 from __future__ import annotations
 
-import glob
 import json
 import logging
 import os
 import pathlib
+import platform
+import sys
 import unicodedata
 from collections import defaultdict
-from collections.abc import Mapping
+from collections.abc import Iterable, Mapping
+from enum import Enum, auto
 from shutil import which  # noqa: F401
-from typing import Any
+from typing import Any, TypeVar, cast
 
-import pycountry
-import rapidfuzz.fuzz
+from comicfn2dict import comicfn2dict
 
 import comicapi.data
+from comicapi import filenamelexer, filenameparser
+from comicapi._url import LocationParseError as LocationParseError  # noqa: F401
+from comicapi._url import Url as Url
+from comicapi._url import parse_url as parse_url
+
+try:
+    import icu
+
+    del icu
+    icu_available = True
+except ImportError:
+    icu_available = False
+
+
+if sys.version_info < (3, 11):
+
+    class StrEnum(str, Enum):
+        """
+        Enum where members are also (and must be) strings
+        """
+
+        def __new__(cls, *values: Any) -> Any:
+            "values must already be of type `str`"
+            if len(values) > 3:
+                raise TypeError(f"too many arguments for str(): {values!r}")
+            if len(values) == 1:
+                # it must be a string
+                if not isinstance(values[0], str):
+                    raise TypeError(f"{values[0]!r} is not a string")
+            if len(values) >= 2:
+                # check that encoding argument is a string
+                if not isinstance(values[1], str):
+                    raise TypeError(f"encoding must be a string, not {values[1]!r}")
+            if len(values) == 3:
+                # check that errors argument is a string
+                if not isinstance(values[2], str):
+                    raise TypeError("errors must be a string, not %r" % (values[2]))
+            value = str(*values)
+            member = str.__new__(cls, value)
+            member._value_ = value
+            return member
+
+        @staticmethod
+        def _generate_next_value_(name: str, start: int, count: int, last_values: Any) -> str:
+            """
+            Return the lower-cased version of the member name.
+            """
+            return name.lower()
+
+        @classmethod
+        def _missing_(cls, value: Any) -> str | None:
+            if not isinstance(value, str):
+                return None
+            if not hasattr(cls, "_lower_members"):
+                cls._lower_members = {x.casefold(): x for x in cls}  # type: ignore[attr-defined]
+            return cls._lower_members.get(value.casefold(), None)  # type: ignore[attr-defined]
+
+        def __str__(self) -> str:
+            return self.value
+
+else:
+    from enum import StrEnum as s
+
+    class StrEnum(s):
+        @classmethod
+        def _missing_(cls, value: Any) -> str | None:
+            if not isinstance(value, str):
+                return None
+            if not hasattr(cls, "_lower_members"):
+                cls._lower_members = {x.casefold(): x for x in cls}  # type: ignore[attr-defined]
+            return cls._lower_members.get(value.casefold(), None)  # type: ignore[attr-defined]
+
 
 logger = logging.getLogger(__name__)
 
 
-class UtilsVars:
-    already_fixed_encoding = False
+class Parser(StrEnum):
+    ORIGINAL = auto()
+    COMPLICATED = auto()
+    COMICFN2DICT = auto()
 
 
-def parse_date_str(date_str: str) -> tuple[int | None, int | None, int | None]:
+def _custom_key(tup: Any) -> Any:
+    import natsort
+
+    lst = []
+    for x in natsort.os_sort_keygen()(tup):
+        ret = x
+        if len(x) > 1 and isinstance(x[1], int) and isinstance(x[0], str) and x[0] == "":
+            ret = ("a", *x[1:])
+
+        lst.append(ret)
+    return tuple(lst)
+
+
+T = TypeVar("T")
+
+
+def os_sorted(lst: Iterable[T]) -> Iterable[T]:
+    import natsort
+
+    key = _custom_key
+    if icu_available or platform.system() == "Windows":
+        key = natsort.os_sort_keygen()
+    return sorted(lst, key=key)
+
+
+def parse_filename(
+    filename: str,
+    parser: Parser = Parser.ORIGINAL,
+    remove_c2c: bool = False,
+    remove_fcbd: bool = False,
+    remove_publisher: bool = False,
+    split_words: bool = False,
+    allow_issue_start_with_letter: bool = False,
+    protofolius_issue_number_scheme: bool = False,
+) -> filenameparser.FilenameInfo:
+    fni = filenameparser.FilenameInfo(
+        alternate="",
+        annual=False,
+        archive="",
+        c2c=False,
+        fcbd=False,
+        format="",
+        issue="",
+        issue_count="",
+        publisher="",
+        remainder="",
+        series="",
+        title="",
+        volume="",
+        volume_count="",
+        year="",
+    )
+    if not filename:
+        return fni
+    if split_words:
+        import wordninja
+
+        filename, ext = os.path.splitext(filename)
+        filename = " ".join(wordninja.split(filename)) + ext
+
+    if parser == Parser.COMPLICATED:
+        lex = filenamelexer.Lex(filename, allow_issue_start_with_letter)
+        p = filenameparser.Parse(
+            lex.items,
+            remove_c2c=remove_c2c,
+            remove_fcbd=remove_fcbd,
+            remove_publisher=remove_publisher,
+            protofolius_issue_number_scheme=protofolius_issue_number_scheme,
+        )
+        if p.error:
+            logger.info("Issue parsing filename: '%s': %s ", filename, p.error.val)
+        fni = p.filename_info
+    elif parser == Parser.COMICFN2DICT:
+        fn2d = comicfn2dict(filename)
+        fni = filenameparser.FilenameInfo(
+            alternate="",
+            annual=False,
+            archive=fn2d.get("ext", ""),
+            c2c=False,
+            fcbd=False,
+            issue=fn2d.get("issue", ""),
+            issue_count=fn2d.get("issue_count", ""),
+            publisher=fn2d.get("publisher", ""),
+            remainder=fn2d.get("scan_info", ""),
+            series=fn2d.get("series", ""),
+            title=fn2d.get("title", ""),
+            volume=fn2d.get("volume", ""),
+            volume_count=fn2d.get("volume_count", ""),
+            year=fn2d.get("year", ""),
+            format=fn2d.get("original_format", ""),
+        )
+    else:
+        fnp = filenameparser.FileNameParser()
+        fnp.parse_filename(filename)
+        fni = filenameparser.FilenameInfo(
+            alternate="",
+            annual=False,
+            archive="",
+            c2c=False,
+            fcbd=False,
+            issue=fnp.issue,
+            issue_count=fnp.issue_count,
+            publisher="",
+            remainder=fnp.remainder,
+            series=fnp.series,
+            title="",
+            volume=fnp.volume,
+            volume_count="",
+            year=fnp.year,
+            format="",
+        )
+    return fni
+
+
+def norm_fold(string: str) -> str:
+    """Normalise and casefold string"""
+    return unicodedata.normalize("NFKD", string).casefold()
+
+
+def combine_notes(existing_notes: str | None, new_notes: str | None, split: str) -> str:
+    split_notes, split_str, untouched_notes = (existing_notes or "").rpartition(split)
+    if split_notes or split_str:
+        return (split_notes + (new_notes or "")).strip()
+    else:
+        return (untouched_notes + "\n" + (new_notes or "")).strip()
+
+
+def parse_date_str(date_str: str | None) -> tuple[int | None, int | None, int | None]:
     day = None
     month = None
     year = None
     if date_str:
         parts = date_str.split("-")
-        year = xlate(parts[0], True)
+        year = xlate_int(parts[0])
         if len(parts) > 1:
-            month = xlate(parts[1], True)
+            month = xlate_int(parts[1])
             if len(parts) > 2:
-                day = xlate(parts[2], True)
+                day = xlate_int(parts[2])
     return day, month, year
 
 
+def shorten_path(path: pathlib.Path, path2: pathlib.Path | None = None) -> tuple[pathlib.Path, pathlib.Path]:
+    if path2:
+        path2 = path2.absolute()
+
+    path = path.absolute()
+    shortened_path: pathlib.Path = path
+    relative_path = pathlib.Path(path.anchor)
+
+    if path.is_relative_to(path.home()):
+        relative_path = path.home()
+        shortened_path = path.relative_to(path.home())
+    if path.is_relative_to(path.cwd()):
+        relative_path = path.cwd()
+        shortened_path = path.relative_to(path.cwd())
+
+    if path2 and shortened_path.is_relative_to(path2.parent):
+        relative_path = path2
+        shortened_path = shortened_path.relative_to(path2)
+
+    return relative_path, shortened_path
+
+
+def path_to_short_str(original_path: pathlib.Path, renamed_path: pathlib.Path | None = None) -> str:
+    rel, _original_path = shorten_path(original_path)
+    path_str = str(_original_path)
+    if rel.samefile(rel.cwd()):
+        path_str = f"./{_original_path}"
+    elif rel.samefile(rel.home()):
+        path_str = f"~/{_original_path}"
+
+    if renamed_path:
+        rel, path = shorten_path(renamed_path, original_path.parent)
+        rename_str = f" -> {path}"
+        if rel.samefile(rel.cwd()):
+            rename_str = f" -> ./{_original_path}"
+        elif rel.samefile(rel.home()):
+            rename_str = f" -> ~/{_original_path}"
+        path_str += rename_str
+
+    return path_str
+
+
+def get_page_name_list(files: list[str]) -> list[str]:
+    # get the list file names in the archive, and sort
+    files = cast(list[str], os_sorted(files))
+
+    # make a sub-list of image files
+    page_list = []
+    for name in files:
+        if (
+            os.path.splitext(name)[1].casefold() in [".jpg", ".jpeg", ".png", ".gif", ".webp", ".avif"]
+            and os.path.basename(name)[0] != "."
+        ):
+            page_list.append(name)
+    return page_list
+
+
 def get_recursive_filelist(pathlist: list[str]) -> list[str]:
     """Get a recursive list of of all files under all path items in the list"""
 
     filelist: list[str] = []
     for p in pathlist:
-
         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))
-        elif str(p) not in filelist:
-            filelist.append(str(p))
+            for root, _, files in os.walk(p):
+                for f in files:
+                    filelist.append(os.path.join(root, f))
+        elif os.path.exists(p):
+            filelist.append(p)
 
     return filelist
 
@@ -68,32 +329,76 @@ def get_recursive_filelist(pathlist: list[str]) -> list[str]:
 def add_to_path(dirname: str) -> None:
     if dirname:
         dirname = os.path.abspath(dirname)
-        paths = [os.path.normpath(x) for x in os.environ["PATH"].split(os.pathsep)]
+        paths = [os.path.normpath(x) for x in split(os.environ["PATH"], os.pathsep)]
 
         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:
+def remove_from_path(dirname: str) -> None:
+    if dirname:
+        dirname = os.path.abspath(dirname)
+        paths = [os.path.normpath(x) for x in split(os.environ["PATH"], os.pathsep) if dirname != os.path.normpath(x)]
+
+        os.environ["PATH"] = os.pathsep.join(paths)
+
+
+def xlate_int(data: Any) -> int | None:
+    data = xlate_float(data)
+    if data is None:
+        return None
+    return int(data)
+
+
+def xlate_float(data: Any) -> float | None:
+    if isinstance(data, str):
+        data = data.strip()
     if data is None or data == "":
         return None
-    if is_int or is_float:
-        i: str | int | float
-        if isinstance(data, (int, float)):
-            i = data
-        else:
-            i = str(data).translate(defaultdict(lambda: None, zip((ord(c) for c in "1234567890."), "1234567890.")))
-        if i == "":
-            return None
-        try:
-            if is_float:
-                return float(i)
-            return int(float(i))
-        except ValueError:
-            return None
+    i: str | int | float
+    if isinstance(data, (int, float)):
+        i = data
+    else:
+        i = str(data).translate(defaultdict(lambda: None, zip((ord(c) for c in "1234567890."), "1234567890.")))
+    if i == "":
+        return None
+    try:
+        return float(i)
+    except ValueError:
+        return None
 
-    return str(data)
+
+def xlate(data: Any) -> str | None:
+    if data is None or isinstance(data, str) and data.strip() == "":
+        return None
+
+    return str(data).strip()
+
+
+def split(s: str | None, c: str) -> list[str]:
+    s = xlate(s)
+    if s:
+        return [x.strip() for x in s.strip().split(c) if x.strip()]
+    return []
+
+
+def split_urls(s: str | None) -> list[Url]:
+    if s is None:
+        return []
+    # Find occurences of ' http'
+    if s.count("http") > 1 and s.count(" http") >= 1:
+        urls = []
+        # Split urls out
+        url_strings = split(s, " http")
+        # Return the scheme 'http' and parse the url
+        for i, url_string in enumerate(url_strings):
+            if not url_string.startswith("http"):
+                url_string = "http" + url_string
+            urls.append(parse_url(url_string))
+        return urls
+    else:
+        return [parse_url(s)]
 
 
 def remove_articles(text: str) -> str:
@@ -155,9 +460,11 @@ def sanitize_title(text: str, basic: bool = False) -> str:
 
 
 def titles_match(search_title: str, record_title: str, threshold: int = 90) -> bool:
+    import rapidfuzz.fuzz
+
     sanitized_search = sanitize_title(search_title)
     sanitized_record = sanitize_title(record_title)
-    ratio: int = rapidfuzz.fuzz.ratio(sanitized_search, sanitized_record)
+    ratio = int(rapidfuzz.fuzz.ratio(sanitized_search, sanitized_record))
     logger.debug(
         "search title: %s ; record title: %s ; ratio: %d ; match threshold: %d",
         search_title,
@@ -178,35 +485,66 @@ def unique_file(file_name: pathlib.Path) -> pathlib.Path:
         counter += 1
 
 
-languages: dict[str | None, str | None] = defaultdict(lambda: None)
+def parse_version(s: str) -> tuple[int, int, int]:
+    str_parts = s.split(".")[:3]
+    parts = [int(x) if x.isdigit() else 0 for x in str_parts]
+    parts.extend([0] * (3 - len(parts)))  # Ensure exactly three elements in the resulting list
 
-countries: dict[str | None, str | None] = defaultdict(lambda: None)
+    return (parts[0], parts[1], parts[2])
 
-for c in pycountry.countries:
-    if "alpha_2" in c._fields:
-        countries[c.alpha_2] = c.name
 
-for lng in pycountry.languages:
-    if "alpha_2" in lng._fields:
-        languages[lng.alpha_2] = lng.name
+_languages: dict[str | None, str | None] = defaultdict(lambda: None)
+
+_countries: dict[str | None, str | None] = defaultdict(lambda: None)
+
+
+def countries() -> dict[str | None, str | None]:
+    if not _countries:
+        import isocodes
+
+        for alpha_2, c in isocodes.countries.by_alpha_2:
+            _countries[alpha_2] = c["name"]
+    return _countries
+
+
+def languages() -> dict[str | None, str | None]:
+    if not _languages:
+        import isocodes
+
+        for alpha_2, lng in isocodes.extendend_languages._sorted_by_index(index="alpha_2"):
+            _languages[alpha_2] = lng["name"]
+    return _languages
 
 
 def get_language_from_iso(iso: str | None) -> str | None:
-    return languages[iso]
+    return languages()[iso]
 
 
 def get_language_iso(string: str | None) -> str | None:
     if string is None:
         return None
+    import isocodes
+
+    # Return current string if all else fails
     lang = string.casefold()
 
-    try:
-        return getattr(pycountry.languages.lookup(string), "alpha_2", None)
-    except LookupError:
-        pass
+    found = None
+    for lng in isocodes.extendend_languages.items:
+        for x in ("alpha_2", "alpha_3", "bibliographic", "common_name", "name"):
+            if x in lng and lng[x].casefold() == lang:
+                found = lng
+        if found:
+            break
+
+    if found:
+        return found.get("alpha_2", None)
     return lang
 
 
+def get_country_from_iso(iso: str | None) -> str | None:
+    return countries()[iso]
+
+
 def get_publisher(publisher: str) -> tuple[str, str]:
     imprint = ""
 
@@ -215,7 +553,7 @@ def get_publisher(publisher: str) -> tuple[str, str]:
         if ok:
             break
 
-    return (imprint, publisher)
+    return imprint, publisher
 
 
 def update_publishers(new_publishers: Mapping[str, Mapping[str, str]]) -> None:
@@ -226,7 +564,7 @@ def update_publishers(new_publishers: Mapping[str, Mapping[str, str]]) -> None:
             publishers[publisher] = ImprintDict(publisher, new_publishers[publisher])
 
 
-class ImprintDict(dict):
+class ImprintDict(dict):  # type: ignore
     """
     ImprintDict takes a publisher and a dict or mapping of lowercased
     imprint names to the proper imprint name. Retrieving a value from an
@@ -234,7 +572,7 @@ class ImprintDict(dict):
     if the key does not exist the key is returned as the publisher unchanged
     """
 
-    def __init__(self, publisher: str, mapping: tuple | Mapping = (), **kwargs: dict) -> None:
+    def __init__(self, publisher: str, mapping: tuple | Mapping = (), **kwargs: dict) -> None:  # type: ignore
         super().__init__(mapping, **kwargs)
         self.publisher = publisher
 
@@ -244,11 +582,11 @@ class ImprintDict(dict):
     def __getitem__(self, k: str) -> tuple[str, str, bool]:
         item = super().__getitem__(k.casefold())
         if k.casefold() == self.publisher.casefold():
-            return ("", self.publisher, True)
+            return "", self.publisher, True
         if item is None:
-            return ("", k, False)
+            return "", k, False
         else:
-            return (item, self.publisher, True)
+            return item, self.publisher, True
 
     def copy(self) -> ImprintDict:
         return ImprintDict(self.publisher, super().copy())

comictagger.py

@@ -1,9 +0,0 @@
-#!/usr/bin/env python3
-from __future__ import annotations
-
-import localefix
-from comictaggerlib.main import ctmain
-
-if __name__ == "__main__":
-    localefix.configure_locale()
-    ctmain()

comictaggerlib/__main__.py

@@ -0,0 +1,5 @@
+from __future__ import annotations
+
+from comictaggerlib.main import main
+
+main()

comictaggerlib/__pyinstaller/hook-comictaggerlib.py

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

comictaggerlib/applicationlogwindow.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import logging
+import pathlib
 
 from PyQt5 import QtCore, QtGui, QtWidgets, uic
 
@@ -23,9 +24,12 @@ class QTextEditLogger(QtCore.QObject, logging.Handler):
 
 
 class ApplicationLogWindow(QtWidgets.QDialog):
-    def __init__(self, log_handler: QTextEditLogger, parent: QtCore.QObject = None) -> None:
+    def __init__(
+        self, log_folder: pathlib.Path, log_handler: QTextEditLogger, parent: QtCore.QObject | None = None
+    ) -> None:
         super().__init__(parent)
-        uic.loadUi(ui_path / "logwindow.ui", self)
+        with (ui_path / "applicationlogwindow.ui").open(encoding="utf-8") as uifile:
+            uic.loadUi(uifile, self)
 
         self.log_handler = log_handler
         self.log_handler.qlog.connect(self.textEdit.append)
@@ -36,6 +40,9 @@ class ApplicationLogWindow(QtWidgets.QDialog):
         self._button = QtWidgets.QPushButton(self)
         self._button.setText("Test Me")
 
+        self.log_folder = log_folder
+        self.lblLogLocation.setText(f'Log Location: <a href="file://{log_folder}">{log_folder}</a>')
+
         layout = self.layout()
         layout.addWidget(self._button)
 

comictaggerlib/autotagmatchwindow.py

@@ -1,6 +1,7 @@
 """A PyQT4 dialog to select from automated issue matches"""
+
 #
-# Copyright 2012-2014 Anthony Beville
+# Copyright 2012-2014 ComicTagger Authors
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -17,53 +18,50 @@ from __future__ import annotations
 
 import logging
 import os
-from typing import Callable
 
 from PyQt5 import QtCore, QtGui, QtWidgets, uic
 
-from comicapi.comicarchive import MetaDataStyle
-from comicapi.genericmetadata import GenericMetadata
+from comicapi.comicarchive import ComicArchive, tags
 from comictaggerlib.coverimagewidget import CoverImageWidget
-from comictaggerlib.resulttypes import IssueResult, MultipleMatch
-from comictaggerlib.settings import ComicTaggerSettings
+from comictaggerlib.ctsettings import ct_ns
+from comictaggerlib.md import prepare_metadata
+from comictaggerlib.resulttypes import IssueResult, Result
 from comictaggerlib.ui import ui_path
-from comictaggerlib.ui.qtutils import reduce_widget_font_size
+from comictalker.comictalker import ComicTalker, TalkerError
 
 logger = logging.getLogger(__name__)
 
 
 class AutoTagMatchWindow(QtWidgets.QDialog):
-    volume_id = 0
-
     def __init__(
         self,
         parent: QtWidgets.QWidget,
-        match_set_list: list[MultipleMatch],
-        style: int,
-        fetch_func: Callable[[IssueResult], GenericMetadata],
-        settings: ComicTaggerSettings,
+        match_set_list: list[Result],
+        read_tags: list[str],
+        config: ct_ns,
+        talker: ComicTalker,
     ) -> None:
         super().__init__(parent)
 
-        uic.loadUi(ui_path / "matchselectionwindow.ui", self)
+        with (ui_path / "matchselectionwindow.ui").open(encoding="utf-8") as uifile:
+            uic.loadUi(uifile, self)
 
-        self.settings = settings
+        self.config = config
 
-        self.current_match_set: MultipleMatch = match_set_list[0]
+        self.current_match_set: Result = match_set_list[0]
 
-        self.altCoverWidget = CoverImageWidget(self.altCoverContainer, CoverImageWidget.AltCoverMode)
+        self.altCoverWidget = CoverImageWidget(
+            self.altCoverContainer, CoverImageWidget.AltCoverMode, config.Runtime_Options__config.user_cache_dir
+        )
         gridlayout = QtWidgets.QGridLayout(self.altCoverContainer)
         gridlayout.addWidget(self.altCoverWidget)
         gridlayout.setContentsMargins(0, 0, 0, 0)
 
-        self.archiveCoverWidget = CoverImageWidget(self.archiveCoverContainer, CoverImageWidget.ArchiveMode)
+        self.archiveCoverWidget = CoverImageWidget(self.archiveCoverContainer, CoverImageWidget.ArchiveMode, None)
         gridlayout = QtWidgets.QGridLayout(self.archiveCoverContainer)
         gridlayout.addWidget(self.archiveCoverWidget)
         gridlayout.setContentsMargins(0, 0, 0, 0)
 
-        reduce_widget_font_size(self.twList)
-        reduce_widget_font_size(self.teDescription, 1)
-
         self.setWindowFlags(
             QtCore.Qt.WindowType(
                 self.windowFlags()
@@ -77,8 +75,8 @@ class AutoTagMatchWindow(QtWidgets.QDialog):
         self.buttonBox.button(QtWidgets.QDialogButtonBox.StandardButton.Ok).setText("Accept and Write Tags")
 
         self.match_set_list = match_set_list
-        self._style = style
-        self.fetch_func = fetch_func
+        self._tags = read_tags
+        self.talker = talker
 
         self.current_match_set_idx = 0
 
@@ -89,7 +87,6 @@ class AutoTagMatchWindow(QtWidgets.QDialog):
         self.update_data()
 
     def update_data(self) -> None:
-
         self.current_match_set = self.match_set_list[self.current_match_set_idx]
 
         if self.current_match_set_idx + 1 == len(self.match_set_list):
@@ -101,7 +98,7 @@ class AutoTagMatchWindow(QtWidgets.QDialog):
         self.twList.resizeColumnsToContents()
         self.twList.selectRow(0)
 
-        path = self.current_match_set.ca.path
+        path = self.current_match_set.original_path
         self.setWindowTitle(
             "Select correct match or skip ({} of {}): {}".format(
                 self.current_match_set_idx + 1,
@@ -118,19 +115,18 @@ class AutoTagMatchWindow(QtWidgets.QDialog):
 
         self.twList.setSortingEnabled(False)
 
-        row = 0
-        for match in self.current_match_set.matches:
+        for row, match in enumerate(self.current_match_set.online_results):
             self.twList.insertRow(row)
 
-            item_text = match["series"]
+            item_text = match.series
             item = QtWidgets.QTableWidgetItem(item_text)
             item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, item_text)
             item.setData(QtCore.Qt.ItemDataRole.UserRole, (match,))
             item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
             self.twList.setItem(row, 0, item)
 
-            if match["publisher"] is not None:
-                item_text = str(match["publisher"])
+            if match.publisher is not None:
+                item_text = str(match.publisher)
             else:
                 item_text = "Unknown"
             item = QtWidgets.QTableWidgetItem(item_text)
@@ -140,10 +136,10 @@ class AutoTagMatchWindow(QtWidgets.QDialog):
 
             month_str = ""
             year_str = "????"
-            if match["month"] is not None:
-                month_str = f"-{int(match['month']):02d}"
-            if match["year"] is not None:
-                year_str = str(match["year"])
+            if match.month is not None:
+                month_str = f"-{int(match.month):02d}"
+            if match.year is not None:
+                year_str = str(match.year)
 
             item_text = year_str + month_str
             item = QtWidgets.QTableWidgetItem(item_text)
@@ -151,7 +147,7 @@ class AutoTagMatchWindow(QtWidgets.QDialog):
             item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
             self.twList.setItem(row, 2, item)
 
-            item_text = match["issue_title"]
+            item_text = match.issue_title
             if item_text is None:
                 item_text = ""
             item = QtWidgets.QTableWidgetItem(item_text)
@@ -159,8 +155,6 @@ class AutoTagMatchWindow(QtWidgets.QDialog):
             item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
             self.twList.setItem(row, 3, item)
 
-            row += 1
-
         self.twList.resizeColumnsToContents()
         self.twList.setSortingEnabled(True)
         self.twList.sortItems(2, QtCore.Qt.SortOrder.AscendingOrder)
@@ -172,20 +166,20 @@ class AutoTagMatchWindow(QtWidgets.QDialog):
         self.accept()
 
     def current_item_changed(self, curr: QtCore.QModelIndex, prev: QtCore.QModelIndex) -> None:
-
         if curr is None:
             return None
         if prev is not None and prev.row() == curr.row():
             return None
 
-        self.altCoverWidget.set_issue_id(self.current_match()["issue_id"])
-        if self.current_match()["description"] is None:
+        match = self.current_match()
+        self.altCoverWidget.set_issue_details(match.issue_id, [match.image_url, *match.alt_image_urls])
+        if match.description is None:
             self.teDescription.setText("")
         else:
-            self.teDescription.setText(self.current_match()["description"])
+            self.teDescription.setText(match.description)
 
     def set_cover_image(self) -> None:
-        ca = self.current_match_set.ca
+        ca = ComicArchive(self.current_match_set.original_path)
         self.archiveCoverWidget.set_archive(ca)
 
     def current_match(self) -> IssueResult:
@@ -194,7 +188,6 @@ class AutoTagMatchWindow(QtWidgets.QDialog):
         return match
 
     def accept(self) -> None:
-
         self.save_match()
         self.current_match_set_idx += 1
 
@@ -228,33 +221,51 @@ class AutoTagMatchWindow(QtWidgets.QDialog):
         QtWidgets.QDialog.reject(self)
 
     def save_match(self) -> None:
-
         match = self.current_match()
-        ca = self.current_match_set.ca
-
-        md = ca.read_metadata(self._style)
-        if md.is_empty:
-            md = ca.metadata_from_filename(
-                self.settings.complicated_parser,
-                self.settings.remove_c2c,
-                self.settings.remove_fcbd,
-                self.settings.remove_publisher,
-            )
-
-        # now get the particular issue data
-        cv_md = self.fetch_func(match)
-        if cv_md is None:
+        ca = ComicArchive(self.current_match_set.original_path)
+        md, _, error = self.parent().read_selected_tags(self._tags, ca)
+        if error is not None:
+            logger.error("Failed to load tags for %s: %s", ca.path, error)
+            QtWidgets.QApplication.restoreOverrideCursor()
             QtWidgets.QMessageBox.critical(
-                self, "Network Issue", "Could not connect to Comic Vine to get issue details!"
+                self,
+                "Read Failed!",
+                f"One or more of the read tags failed to load for {ca.path}, check log for details",
             )
             return
 
+        if md.is_empty:
+            md = ca.metadata_from_filename(
+                self.config.Filename_Parsing__filename_parser,
+                self.config.Filename_Parsing__remove_c2c,
+                self.config.Filename_Parsing__remove_fcbd,
+                self.config.Filename_Parsing__remove_publisher,
+            )
+
+        # now get the particular issue data
+
+        try:
+            self.current_match_set.md = ct_md = self.talker.fetch_comic_data(issue_id=match.issue_id)
+        except TalkerError as e:
+            QtWidgets.QApplication.restoreOverrideCursor()
+            QtWidgets.QMessageBox.critical(self, f"{e.source} {e.code_name} Error", f"{e}")
+            return
+
+        if ct_md is None or ct_md.is_empty:
+            QtWidgets.QMessageBox.critical(self, "Network Issue", "Could not retrieve issue details!")
+            return
+
         QtWidgets.QApplication.setOverrideCursor(QtGui.QCursor(QtCore.Qt.CursorShape.WaitCursor))
-        md.overlay(cv_md)
-        success = ca.write_metadata(md, self._style)
-        ca.load_cache([MetaDataStyle.CBI, MetaDataStyle.CIX])
+        md = prepare_metadata(md, ct_md, self.config)
+        for tag_id in self._tags:
+            success = ca.write_tags(md, tag_id)
+            QtWidgets.QApplication.restoreOverrideCursor()
+            if not success:
+                QtWidgets.QMessageBox.warning(
+                    self,
+                    "Write Error",
+                    f"Saving {tags[tag_id].name()} the tags to the archive seemed to fail!",
+                )
+                break
 
-        QtWidgets.QApplication.restoreOverrideCursor()
-
-        if not success:
-            QtWidgets.QMessageBox.warning(self, "Write Error", "Saving the tags to the archive seemed to fail!")
+        ca.reset_cache()

comictaggerlib/autotagprogresswindow.py

@@ -1,6 +1,7 @@
 """A PyQT4 dialog to show ID log and progress"""
+
 #
-# Copyright 2012-2014 Anthony Beville
+# Copyright 2012-2014 ComicTagger Authors
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -16,34 +17,225 @@
 from __future__ import annotations
 
 import logging
+import pathlib
+import re
 
 from PyQt5 import QtCore, QtWidgets, uic
 
+from comicapi import utils
+from comicapi.comicarchive import ComicArchive, tags
+from comicapi.genericmetadata import GenericMetadata
 from comictaggerlib.coverimagewidget import CoverImageWidget
+from comictaggerlib.ctsettings.settngs_namespace import SettngsNS
+from comictaggerlib.issueidentifier import IssueIdentifierCancelled
+from comictaggerlib.md import read_selected_tags
+from comictaggerlib.resulttypes import Action, OnlineMatchResults, Result, Status
+from comictaggerlib.tag import identify_comic
 from comictaggerlib.ui import ui_path
-from comictaggerlib.ui.qtutils import reduce_widget_font_size
+from comictalker.comictalker import ComicTalker, RLCallBack
 
 logger = logging.getLogger(__name__)
 
 
+class AutoTagThread(QtCore.QThread):
+    autoTagComplete = QtCore.pyqtSignal(OnlineMatchResults, list)
+    autoTagLogMsg = QtCore.pyqtSignal(str)
+    autoTagProgress = QtCore.pyqtSignal(object, object, object, bytes, bytes)  # see progress_callback
+    ratelimit = QtCore.pyqtSignal(float, float)
+
+    def __init__(
+        self, series_override: str, ca_list: list[ComicArchive], config: SettngsNS, talker: ComicTalker
+    ) -> None:
+        QtCore.QThread.__init__(self)
+        self.series_override = series_override
+        self.ca_list = ca_list
+        self.config = config
+        self.talker = talker
+        self.canceled = False
+
+    def log_output(self, text: str) -> None:
+        self.autoTagLogMsg.emit(str(text))
+
+    def progress_callback(
+        self, cur: int | None, total: int | None, path: pathlib.Path | None, archive_image: bytes, remote_image: bytes
+    ) -> None:
+        self.autoTagProgress.emit(cur, total, path, archive_image, remote_image)
+
+    def run(self) -> None:
+        match_results = OnlineMatchResults()
+        archives_to_remove = []
+        for prog_idx, ca in enumerate(self.ca_list):
+            self.log_output("==========================================================================\n")
+            self.log_output(f"Auto-Tagging {prog_idx} of {len(self.ca_list)}\n")
+            self.log_output(f"{ca.path}\n")
+            try:
+                cover_idx = ca.read_tags(self.config.internal__read_tags[0]).get_cover_page_index_list()[0]
+            except Exception as e:
+                cover_idx = 0
+                logger.error("Failed to load metadata for %s: %s", ca.path, e)
+            image_data = ca.get_page(cover_idx)
+            self.progress_callback(prog_idx, len(self.ca_list), ca.path, image_data, b"")
+
+            if self.canceled:
+                break
+
+            if ca.is_writable():
+                success, match_results = self.identify_and_tag_single_archive(ca, match_results)
+                if self.canceled:
+                    break
+
+                if success and self.config.internal__remove_archive_after_successful_match:
+                    archives_to_remove.append(ca)
+        self.autoTagComplete.emit(match_results, archives_to_remove)
+
+    def on_rate_limit(self, full_time: float, sleep_time: float) -> None:
+        if self.canceled:
+            raise IssueIdentifierCancelled
+        self.log_output(
+            f"Rate limit reached: {full_time:.0f}s until next request. Waiting {sleep_time:.0f}s for ratelimit"
+        )
+        self.ratelimit.emit(full_time, sleep_time)
+
+    def identify_and_tag_single_archive(
+        self, ca: ComicArchive, match_results: OnlineMatchResults
+    ) -> tuple[Result, OnlineMatchResults]:
+
+        ratelimit_callback = RLCallBack(
+            self.on_rate_limit,
+            60,
+        )
+
+        # read in tags, and parse file name if not there
+        md, tags_used, error = read_selected_tags(self.config.internal__read_tags, ca)
+        if error is not None:
+            QtWidgets.QMessageBox.warning(
+                None,
+                "Aborting...",
+                f"One or more of the read tags failed to load for {ca.path}. Aborting to prevent any possible further damage. Check log for details.",
+            )
+            logger.error("Failed to load tags from %s: %s", ca.path, error)
+            return (
+                Result(
+                    Action.save,
+                    original_path=ca.path,
+                    status=Status.read_failure,
+                ),
+                match_results,
+            )
+
+        if md.is_empty:
+            md = ca.metadata_from_filename(
+                self.config.Filename_Parsing__filename_parser,
+                self.config.Filename_Parsing__remove_c2c,
+                self.config.Filename_Parsing__remove_fcbd,
+                self.config.Filename_Parsing__remove_publisher,
+                self.config.Filename_Parsing__split_words,
+                self.config.Filename_Parsing__allow_issue_start_with_letter,
+                self.config.Filename_Parsing__protofolius_issue_number_scheme,
+            )
+            if self.config.Auto_Tag__ignore_leading_numbers_in_filename and md.series is not None:
+                # remove all leading numbers
+                md.series = re.sub(r"(^[\d.]*)(.*)", r"\2", md.series)
+
+        # use the dialog specified search string
+        if self.series_override:
+            md.series = self.series_override
+
+        if not self.config.Auto_Tag__use_year_when_identifying:
+            md.year = None
+        # If it's empty we need it to stay empty for identify_comic to report the correct error
+        if (md.issue is None or md.issue == "") and not md.is_empty:
+            if self.config.Auto_Tag__assume_issue_one:
+                md.issue = "1"
+            else:
+                md.issue = utils.xlate(md.volume)
+
+        def on_progress(x: int, y: int, image: bytes) -> None:
+            # We don't (currently) care about the progress of an individual comic here we just want the cover for the autotagprogresswindow
+            self.progress_callback(None, None, None, b"", image)
+
+        if self.canceled:
+            return (
+                Result(
+                    Action.save,
+                    original_path=ca.path,
+                    status=Status.read_failure,
+                ),
+                match_results,
+            )
+
+        try:
+            res, match_results = identify_comic(
+                ca,
+                md,
+                tags_used,
+                match_results,
+                self.config,
+                self.talker,
+                self.log_output,
+                on_rate_limit=ratelimit_callback,
+                on_progress=on_progress,
+            )
+        except IssueIdentifierCancelled:
+            return (
+                Result(
+                    Action.save,
+                    original_path=ca.path,
+                    status=Status.fetch_data_failure,
+                ),
+                match_results,
+            )
+        if self.canceled:
+            return res, match_results
+
+        if res.status == Status.success:
+            assert res.md
+
+            def write_Tags(ca: ComicArchive, md: GenericMetadata) -> bool:
+                for tag_id in self.config.Runtime_Options__tags_write:
+                    # write out the new data
+                    if not ca.write_tags(md, tag_id):
+                        self.log_output(f"{tags[tag_id].name()} save failed! Aborting any additional tag saves.\n")
+                        return False
+                return True
+
+            # Save tags
+            if write_Tags(ca, res.md):
+                match_results.good_matches.append(res)
+                res.tags_written = self.config.Runtime_Options__tags_write
+                self.log_output("Save complete!\n")
+            else:
+                res.status = Status.write_failure
+                match_results.write_failures.append(res)
+
+            ca.reset_cache()
+            ca.load_cache({*self.config.Runtime_Options__tags_read})
+
+        return res, match_results
+
+    def cancel(self) -> None:
+        self.canceled = True
+
+
 class AutoTagProgressWindow(QtWidgets.QDialog):
-    def __init__(self, parent: QtWidgets.QWidget) -> None:
+    def __init__(self, parent: QtWidgets.QWidget, talker: ComicTalker) -> None:
         super().__init__(parent)
 
-        uic.loadUi(ui_path / "autotagprogresswindow.ui", self)
+        with (ui_path / "autotagprogresswindow.ui").open(encoding="utf-8") as uifile:
+            uic.loadUi(uifile, self)
 
-        self.archiveCoverWidget = CoverImageWidget(self.archiveCoverContainer, CoverImageWidget.DataMode, False)
+        self.lblSourceName.setText(talker.attribution)
+
+        self.archiveCoverWidget = CoverImageWidget(self.archiveCoverContainer, CoverImageWidget.DataMode, None, False)
         gridlayout = QtWidgets.QGridLayout(self.archiveCoverContainer)
         gridlayout.addWidget(self.archiveCoverWidget)
         gridlayout.setContentsMargins(0, 0, 0, 0)
 
-        self.testCoverWidget = CoverImageWidget(self.testCoverContainer, CoverImageWidget.DataMode, False)
+        self.testCoverWidget = CoverImageWidget(self.testCoverContainer, CoverImageWidget.DataMode, None, False)
         gridlayout = QtWidgets.QGridLayout(self.testCoverContainer)
         gridlayout.addWidget(self.testCoverWidget)
         gridlayout.setContentsMargins(0, 0, 0, 0)
 
-        self.isdone = False
-
         self.setWindowFlags(
             QtCore.Qt.WindowType(
                 self.windowFlags()
@@ -52,8 +244,6 @@ class AutoTagProgressWindow(QtWidgets.QDialog):
             )
         )
 
-        reduce_widget_font_size(self.textEdit)
-
     def set_archive_image(self, img_data: bytes) -> None:
         self.set_cover_image(img_data, self.archiveCoverWidget)
 
@@ -65,6 +255,20 @@ class AutoTagProgressWindow(QtWidgets.QDialog):
         QtCore.QCoreApplication.processEvents()
         QtCore.QCoreApplication.processEvents()
 
+    # @QtCore.pyqtSlot(int, int, 'Optional[pathlib.Path]', bytes, bytes)
+    def on_progress(
+        self, x: int | None, y: int | None, title: pathlib.Path | None, archive_image: bytes, remote_image: bytes
+    ) -> None:
+        if x is not None and y is not None:
+            self.progressBar: QtWidgets.QProgressBar
+            self.progressBar.setValue(x)
+            self.progressBar.setMaximum(y)
+        if title:
+            self.setWindowTitle(str(title))
+        if archive_image:
+            self.set_archive_image(archive_image)
+        if remote_image:
+            self.set_test_image(remote_image)
+
     def reject(self) -> None:
         QtWidgets.QDialog.reject(self)
-        self.isdone = True

comictaggerlib/autotagstartwindow.py

@@ -1,6 +1,7 @@
-"""A PyQT4 dialog to confirm and set options for auto-tag"""
+"""A PyQT4 dialog to confirm and set config for auto-tag"""
+
 #
-# Copyright 2012-2014 Anthony Beville
+# Copyright 2012-2014 ComicTagger Authors
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -19,37 +20,37 @@ import logging
 
 from PyQt5 import QtCore, QtWidgets, uic
 
-from comictaggerlib.settings import ComicTaggerSettings
+from comictaggerlib.ctsettings import ct_ns
 from comictaggerlib.ui import ui_path
 
 logger = logging.getLogger(__name__)
 
 
 class AutoTagStartWindow(QtWidgets.QDialog):
-    def __init__(self, parent: QtWidgets.QWidget, settings: ComicTaggerSettings, msg: str) -> None:
+    def __init__(self, parent: QtWidgets.QWidget, config: ct_ns, msg: str) -> None:
         super().__init__(parent)
 
-        uic.loadUi(ui_path / "autotagstartwindow.ui", self)
+        with (ui_path / "autotagstartwindow.ui").open(encoding="utf-8") as uifile:
+            uic.loadUi(uifile, self)
         self.label.setText(msg)
 
         self.setWindowFlags(
             QtCore.Qt.WindowType(self.windowFlags() & ~QtCore.Qt.WindowType.WindowContextHelpButtonHint)
         )
 
-        self.settings = settings
+        self.config = config
 
         self.cbxSpecifySearchString.setChecked(False)
         self.cbxSplitWords.setChecked(False)
-        self.sbNameMatchSearchThresh.setValue(self.settings.id_series_match_identify_thresh)
+        self.sbNameMatchSearchThresh.setValue(self.config.Issue_Identifier__series_match_identify_thresh)
         self.leSearchString.setEnabled(False)
 
-        self.cbxSaveOnLowConfidence.setChecked(self.settings.save_on_low_confidence)
-        self.cbxDontUseYear.setChecked(self.settings.dont_use_year_when_identifying)
-        self.cbxAssumeIssueOne.setChecked(self.settings.assume_1_if_no_issue_num)
-        self.cbxIgnoreLeadingDigitsInFilename.setChecked(self.settings.ignore_leading_numbers_in_filename)
-        self.cbxRemoveAfterSuccess.setChecked(self.settings.remove_archive_after_successful_match)
-        self.cbxWaitForRateLimit.setChecked(self.settings.wait_and_retry_on_rate_limit)
-        self.cbxAutoImprint.setChecked(self.settings.auto_imprint)
+        self.cbxSaveOnLowConfidence.setChecked(self.config.Auto_Tag__save_on_low_confidence)
+        self.cbxDontUseYear.setChecked(not self.config.Auto_Tag__use_year_when_identifying)
+        self.cbxAssumeIssueOne.setChecked(self.config.Auto_Tag__assume_issue_one)
+        self.cbxIgnoreLeadingDigitsInFilename.setChecked(self.config.Auto_Tag__ignore_leading_numbers_in_filename)
+        self.cbxRemoveAfterSuccess.setChecked(self.config.internal__remove_archive_after_successful_match)
+        self.cbxAutoImprint.setChecked(self.config.Auto_Tag__auto_imprint)
 
         nlmt_tip = """<html>The <b>Name Match Ratio Threshold: Auto-Identify</b> is for eliminating automatic
                 search matches that are too long compared to your series name search. The lower
@@ -73,9 +74,8 @@ class AutoTagStartWindow(QtWidgets.QDialog):
         self.assume_issue_one = False
         self.ignore_leading_digits_in_filename = False
         self.remove_after_success = False
-        self.wait_and_retry_on_rate_limit = False
         self.search_string = ""
-        self.name_length_match_tolerance = self.settings.id_series_match_search_thresh
+        self.name_length_match_tolerance = self.config.Issue_Identifier__series_match_search_thresh
         self.split_words = self.cbxSplitWords.isChecked()
 
     def search_string_toggle(self) -> None:
@@ -91,16 +91,14 @@ class AutoTagStartWindow(QtWidgets.QDialog):
         self.ignore_leading_digits_in_filename = self.cbxIgnoreLeadingDigitsInFilename.isChecked()
         self.remove_after_success = self.cbxRemoveAfterSuccess.isChecked()
         self.name_length_match_tolerance = self.sbNameMatchSearchThresh.value()
-        self.wait_and_retry_on_rate_limit = self.cbxWaitForRateLimit.isChecked()
         self.split_words = self.cbxSplitWords.isChecked()
 
         # persist some settings
-        self.settings.save_on_low_confidence = self.auto_save_on_low
-        self.settings.dont_use_year_when_identifying = self.dont_use_year
-        self.settings.assume_1_if_no_issue_num = self.assume_issue_one
-        self.settings.ignore_leading_numbers_in_filename = self.ignore_leading_digits_in_filename
-        self.settings.remove_archive_after_successful_match = self.remove_after_success
-        self.settings.wait_and_retry_on_rate_limit = self.wait_and_retry_on_rate_limit
+        self.config.Auto_Tag__save_on_low_confidence = self.auto_save_on_low
+        self.config.Auto_Tag__use_year_when_identifying = not self.dont_use_year
+        self.config.Auto_Tag__assume_issue_one = self.assume_issue_one
+        self.config.Auto_Tag__ignore_leading_numbers_in_filename = self.ignore_leading_digits_in_filename
+        self.config.internal__remove_archive_after_successful_match = self.remove_after_success
 
         if self.cbxSpecifySearchString.isChecked():
             self.search_string = self.leSearchString.text()

comictaggerlib/cbltransformer.py

@@ -1,6 +1,7 @@
 """A class to manage modifying metadata specifically for CBL/CBI"""
+
 #
-# Copyright 2012-2014 Anthony Beville
+# Copyright 2012-2014 ComicTagger Authors
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -17,44 +18,32 @@ from __future__ import annotations
 
 import logging
 
-from comicapi.genericmetadata import CreditMetadata, GenericMetadata
-from comictaggerlib.settings import ComicTaggerSettings
+from comicapi.genericmetadata import Credit, GenericMetadata
+from comictaggerlib.ctsettings import ct_ns
 
 logger = logging.getLogger(__name__)
 
 
 class CBLTransformer:
-    def __init__(self, metadata: GenericMetadata, settings: ComicTaggerSettings) -> None:
-        self.metadata = metadata
-        self.settings = settings
+    def __init__(self, metadata: GenericMetadata, config: ct_ns) -> None:
+        self.metadata = metadata.copy()
+        self.config = config
 
     def apply(self) -> GenericMetadata:
-        # helper funcs
-        def append_to_tags_if_unique(item: str) -> None:
-            if item.casefold() not in (tag.casefold() for tag in self.metadata.tags):
-                self.metadata.tags.add(item)
-
-        def add_string_list_to_tags(str_list: str | None) -> None:
-            if str_list:
-                items = [s.strip() for s in str_list.split(",")]
-                for item in items:
-                    append_to_tags_if_unique(item)
-
-        if self.settings.assume_lone_credit_is_primary:
-
+        if self.config.Metadata_Options__assume_lone_credit_is_primary:
             # helper
-            def set_lone_primary(role_list: list[str]) -> tuple[CreditMetadata | None, int]:
-                lone_credit: CreditMetadata | None = None
+            def set_lone_primary(role_list: list[str]) -> tuple[Credit | None, int]:
+                lone_credit: Credit | None = None
                 count = 0
                 for c in self.metadata.credits:
-                    if c["role"].casefold() in role_list:
+                    if c.role.casefold() in role_list:
                         count += 1
                         lone_credit = c
                     if count > 1:
                         lone_credit = None
                         break
                 if lone_credit is not None:
-                    lone_credit["primary"] = True
+                    lone_credit.primary = True
                 return lone_credit, count
 
             # need to loop three times, once for 'writer', 'artist', and then
@@ -64,37 +53,38 @@ class CBLTransformer:
             if c is None and count == 0:
                 c, count = set_lone_primary(["penciler", "penciller"])
                 if c is not None:
-                    c["primary"] = False
-                    self.metadata.add_credit(c["person"], "Artist", True)
+                    c.primary = False
+                    self.metadata.add_credit(c.person, "Artist", True)
 
-        if self.settings.copy_characters_to_tags:
-            add_string_list_to_tags(self.metadata.characters)
+        if self.config.Metadata_Options__copy_characters_to_tags:
+            self.metadata.tags.update(x for x in self.metadata.characters)
 
-        if self.settings.copy_teams_to_tags:
-            add_string_list_to_tags(self.metadata.teams)
+        if self.config.Metadata_Options__copy_teams_to_tags:
+            self.metadata.tags.update(x for x in self.metadata.teams)
 
-        if self.settings.copy_locations_to_tags:
-            add_string_list_to_tags(self.metadata.locations)
+        if self.config.Metadata_Options__copy_locations_to_tags:
+            self.metadata.tags.update(x for x in self.metadata.locations)
 
-        if self.settings.copy_storyarcs_to_tags:
-            add_string_list_to_tags(self.metadata.story_arc)
+        if self.config.Metadata_Options__copy_storyarcs_to_tags:
+            self.metadata.tags.update(x for x in self.metadata.story_arcs)
 
-        if self.settings.copy_notes_to_comments:
+        if self.config.Metadata_Options__copy_notes_to_comments:
             if self.metadata.notes is not None:
-                if self.metadata.comments is None:
-                    self.metadata.comments = ""
+                if self.metadata.description is None:
+                    self.metadata.description = ""
                 else:
-                    self.metadata.comments += "\n\n"
-                if self.metadata.notes not in self.metadata.comments:
-                    self.metadata.comments += self.metadata.notes
+                    self.metadata.description += "\n\n"
+                if self.metadata.notes not in self.metadata.description:
+                    self.metadata.description += self.metadata.notes
 
-        if self.settings.copy_weblink_to_comments:
-            if self.metadata.web_link is not None:
-                if self.metadata.comments is None:
-                    self.metadata.comments = ""
+        if self.config.Metadata_Options__copy_weblink_to_comments:
+            for web_link in self.metadata.web_links:
+                temp_desc = self.metadata.description
+                if temp_desc is None:
+                    temp_desc = ""
                 else:
-                    self.metadata.comments += "\n\n"
-                if self.metadata.web_link not in self.metadata.comments:
-                    self.metadata.comments += self.metadata.web_link
+                    temp_desc += "\n\n"
+                if web_link.url and web_link.url not in temp_desc:
+                    self.metadata.description = temp_desc + web_link.url
 
         return self.metadata

comictaggerlib/comiccacher.py

@@ -1,469 +0,0 @@
-"""A python class to manage caching of data from Comic Vine"""
-#
-# Copyright 2012-2014 Anthony Beville
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-from __future__ import annotations
-
-import datetime
-import logging
-import os
-import sqlite3 as lite
-from typing import Any
-
-from comictaggerlib import ctversion
-from comictaggerlib.resulttypes import CVImage, CVIssuesResults, CVPublisher, CVVolumeResults, SelectDetails
-from comictaggerlib.settings import ComicTaggerSettings
-
-logger = logging.getLogger(__name__)
-
-
-class ComicCacher:
-    def __init__(self) -> None:
-        self.settings_folder = ComicTaggerSettings.get_settings_folder()
-        self.db_file = os.path.join(self.settings_folder, "comic_cache.db")
-        self.version_file = os.path.join(self.settings_folder, "cache_version.txt")
-
-        # verify that cache is from same version as this one
-        data = ""
-        try:
-            with open(self.version_file, "rb") as f:
-                data = f.read().decode("utf-8")
-                f.close()
-        except Exception:
-            pass
-        if data != ctversion.version:
-            self.clear_cache()
-
-        if not os.path.exists(self.db_file):
-            self.create_cache_db()
-
-    def clear_cache(self) -> None:
-        try:
-            os.unlink(self.db_file)
-        except Exception:
-            pass
-        try:
-            os.unlink(self.version_file)
-        except Exception:
-            pass
-
-    def create_cache_db(self) -> None:
-
-        # create the version file
-        with open(self.version_file, "w", encoding="utf-8") as f:
-            f.write(ctversion.version)
-
-        # this will wipe out any existing version
-        open(self.db_file, "wb").close()
-
-        con = lite.connect(self.db_file)
-
-        # create tables
-        with con:
-            cur = con.cursor()
-            # source_name,name,id,start_year,publisher,image,description,count_of_issues
-            cur.execute(
-                "CREATE TABLE VolumeSearchCache("
-                + "search_term TEXT,"
-                + "id INT NOT NULL,"
-                + "name TEXT,"
-                + "start_year INT,"
-                + "publisher TEXT,"
-                + "count_of_issues INT,"
-                + "image_url TEXT,"
-                + "description TEXT,"
-                + "timestamp DATE DEFAULT (datetime('now','localtime')),"
-                + "source_name TEXT NOT NULL,"
-                + "aliases TEXT)"  # Newline separated
-            )
-
-            cur.execute(
-                "CREATE TABLE Volumes("
-                + "id INT NOT NULL,"
-                + "name TEXT,"
-                + "publisher TEXT,"
-                + "count_of_issues INT,"
-                + "start_year INT,"
-                + "timestamp DATE DEFAULT (datetime('now','localtime')), "
-                + "source_name TEXT NOT NULL,"
-                + "aliases TEXT,"  # Newline separated
-                + "PRIMARY KEY (id, source_name))"
-            )
-
-            cur.execute(
-                "CREATE TABLE AltCovers("
-                + "issue_id INT NOT NULL,"
-                + "url_list TEXT,"
-                + "timestamp DATE DEFAULT (datetime('now','localtime')), "
-                + "source_name TEXT NOT NULL,"
-                + "aliases TEXT,"  # Newline separated
-                + "PRIMARY KEY (issue_id, source_name))"
-            )
-
-            cur.execute(
-                "CREATE TABLE Issues("
-                + "id INT NOT NULL,"
-                + "volume_id INT,"
-                + "name TEXT,"
-                + "issue_number TEXT,"
-                + "super_url TEXT,"
-                + "thumb_url TEXT,"
-                + "cover_date TEXT,"
-                + "site_detail_url TEXT,"
-                + "description TEXT,"
-                + "timestamp DATE DEFAULT (datetime('now','localtime')), "
-                + "source_name TEXT NOT NULL,"
-                + "aliases TEXT,"  # Newline separated
-                + "PRIMARY KEY (id, source_name))"
-            )
-
-    def add_search_results(self, source_name: str, search_term: str, cv_search_results: list[CVVolumeResults]) -> None:
-
-        con = lite.connect(self.db_file)
-
-        with con:
-            con.text_factory = str
-            cur = con.cursor()
-
-            # remove all previous entries with this search term
-            cur.execute(
-                "DELETE FROM VolumeSearchCache WHERE search_term = ? AND source_name = ?",
-                [search_term.casefold(), source_name],
-            )
-
-            # now add in new results
-            for record in cv_search_results:
-
-                if record["publisher"] is None:
-                    pub_name = ""
-                else:
-                    pub_name = record["publisher"]["name"]
-
-                if record["image"] is None:
-                    url = ""
-                else:
-                    url = record["image"]["super_url"]
-
-                cur.execute(
-                    "INSERT INTO VolumeSearchCache "
-                    + "(source_name, search_term, id, name, start_year, publisher, count_of_issues, image_url, description, aliases) "
-                    + "VALUES(?, ?, ?, ?, ?, ?, ?, ?, ?, ?)",
-                    (
-                        source_name,
-                        search_term.casefold(),
-                        record["id"],
-                        record["name"],
-                        record["start_year"],
-                        pub_name,
-                        record["count_of_issues"],
-                        url,
-                        record["description"],
-                        record["aliases"],
-                    ),
-                )
-
-    def get_search_results(self, source_name: str, search_term: str) -> list[CVVolumeResults]:
-
-        results = []
-        con = lite.connect(self.db_file)
-        with con:
-            con.text_factory = str
-            cur = con.cursor()
-
-            # purge stale search results
-            a_day_ago = datetime.datetime.today() - datetime.timedelta(days=1)
-            cur.execute("DELETE FROM VolumeSearchCache WHERE timestamp  < ?", [str(a_day_ago)])
-
-            # fetch
-            cur.execute(
-                "SELECT * FROM VolumeSearchCache WHERE search_term=? AND source_name=?",
-                [search_term.casefold(), source_name],
-            )
-            rows = cur.fetchall()
-            # now process the results
-            for record in rows:
-                result = CVVolumeResults(
-                    id=record[1],
-                    name=record[2],
-                    start_year=record[3],
-                    count_of_issues=record[5],
-                    description=record[7],
-                    publisher=CVPublisher(name=record[4]),
-                    image=CVImage(super_url=record[6]),
-                    aliases=record[10],
-                )
-
-                results.append(result)
-
-        return results
-
-    def add_alt_covers(self, source_name: str, issue_id: int, url_list: list[str]) -> None:
-
-        con = lite.connect(self.db_file)
-
-        with con:
-            con.text_factory = str
-            cur = con.cursor()
-
-            # remove all previous entries with this search term
-            cur.execute("DELETE FROM AltCovers WHERE issue_id=? AND source_name=?", [issue_id, source_name])
-
-            url_list_str = ",".join(url_list)
-            # now add in new record
-            cur.execute(
-                "INSERT INTO AltCovers (source_name, issue_id, url_list) VALUES(?, ?, ?)",
-                (source_name, issue_id, url_list_str),
-            )
-
-    def get_alt_covers(self, source_name: str, issue_id: int) -> list[str]:
-
-        con = lite.connect(self.db_file)
-        with con:
-            cur = con.cursor()
-            con.text_factory = str
-
-            # purge stale issue info - probably issue data won't change
-            # much....
-            a_month_ago = datetime.datetime.today() - datetime.timedelta(days=30)
-            cur.execute("DELETE FROM AltCovers WHERE timestamp  < ?", [str(a_month_ago)])
-
-            cur.execute("SELECT url_list FROM AltCovers WHERE issue_id=? AND source_name=?", [issue_id, source_name])
-            row = cur.fetchone()
-            if row is None:
-                return []
-
-            url_list_str = row[0]
-            if not url_list_str:
-                return []
-            url_list = str(url_list_str).split(",")
-            return url_list
-
-    def add_volume_info(self, source_name: str, cv_volume_record: CVVolumeResults) -> None:
-
-        con = lite.connect(self.db_file)
-
-        with con:
-
-            cur = con.cursor()
-
-            timestamp = datetime.datetime.now()
-
-            if cv_volume_record["publisher"] is None:
-                pub_name = ""
-            else:
-                pub_name = cv_volume_record["publisher"]["name"]
-
-            data = {
-                "id": cv_volume_record["id"],
-                "source_name": source_name,
-                "name": cv_volume_record["name"],
-                "publisher": pub_name,
-                "count_of_issues": cv_volume_record["count_of_issues"],
-                "start_year": cv_volume_record["start_year"],
-                "timestamp": timestamp,
-                "aliases": cv_volume_record["aliases"],
-            }
-            self.upsert(cur, "volumes", data)
-
-    def add_volume_issues_info(self, source_name: str, volume_id: int, cv_volume_issues: list[CVIssuesResults]) -> None:
-
-        con = lite.connect(self.db_file)
-
-        with con:
-            cur = con.cursor()
-
-            timestamp = datetime.datetime.now()
-
-            # add in issues
-
-            for issue in cv_volume_issues:
-                data = {
-                    "id": issue["id"],
-                    "volume_id": volume_id,
-                    "source_name": source_name,
-                    "name": issue["name"],
-                    "issue_number": issue["issue_number"],
-                    "site_detail_url": issue["site_detail_url"],
-                    "cover_date": issue["cover_date"],
-                    "super_url": issue["image"]["super_url"],
-                    "thumb_url": issue["image"]["thumb_url"],
-                    "description": issue["description"],
-                    "timestamp": timestamp,
-                    "aliases": issue["aliases"],
-                }
-                self.upsert(cur, "issues", data)
-
-    def get_volume_info(self, volume_id: int, source_name: str) -> CVVolumeResults | None:
-
-        result: CVVolumeResults | None = None
-
-        con = lite.connect(self.db_file)
-        with con:
-            cur = con.cursor()
-            con.text_factory = str
-
-            # purge stale volume info
-            a_week_ago = datetime.datetime.today() - datetime.timedelta(days=7)
-            cur.execute("DELETE FROM Volumes WHERE timestamp  < ?", [str(a_week_ago)])
-
-            # fetch
-            cur.execute(
-                "SELECT source_name,id,name,publisher,count_of_issues,start_year,aliases FROM Volumes"
-                " WHERE id=? AND source_name=?",
-                [volume_id, source_name],
-            )
-
-            row = cur.fetchone()
-
-            if row is None:
-                return result
-
-            # since ID is primary key, there is only one row
-            result = CVVolumeResults(
-                id=row[1],
-                name=row[2],
-                count_of_issues=row[4],
-                start_year=row[5],
-                publisher=CVPublisher(name=row[3]),
-                aliases=row[6],
-            )
-
-        return result
-
-    def get_volume_issues_info(self, volume_id: int, source_name: str) -> list[CVIssuesResults]:
-
-        con = lite.connect(self.db_file)
-        with con:
-            cur = con.cursor()
-            con.text_factory = str
-
-            # purge stale issue info - probably issue data won't change
-            # much....
-            a_week_ago = datetime.datetime.today() - datetime.timedelta(days=7)
-            cur.execute("DELETE FROM Issues WHERE timestamp  < ?", [str(a_week_ago)])
-
-            # fetch
-            results: list[CVIssuesResults] = []
-
-            cur.execute(
-                (
-                    "SELECT source_name,id,name,issue_number,site_detail_url,cover_date,super_url,thumb_url,description,aliases"
-                    " FROM Issues WHERE volume_id=? AND source_name=?"
-                ),
-                [volume_id, source_name],
-            )
-            rows = cur.fetchall()
-
-            # now process the results
-            for row in rows:
-                record = CVIssuesResults(
-                    id=row[1],
-                    name=row[2],
-                    issue_number=row[3],
-                    site_detail_url=row[4],
-                    cover_date=row[5],
-                    image=CVImage(super_url=row[6], thumb_url=row[7]),
-                    description=row[8],
-                    aliases=row[9],
-                )
-
-                results.append(record)
-
-        return results
-
-    def add_issue_select_details(
-        self,
-        source_name: str,
-        issue_id: int,
-        image_url: str,
-        thumb_image_url: str,
-        cover_date: str,
-        site_detail_url: str,
-    ) -> None:
-
-        con = lite.connect(self.db_file)
-
-        with con:
-            cur = con.cursor()
-            con.text_factory = str
-            timestamp = datetime.datetime.now()
-
-            data = {
-                "id": issue_id,
-                "source_name": source_name,
-                "super_url": image_url,
-                "thumb_url": thumb_image_url,
-                "cover_date": cover_date,
-                "site_detail_url": site_detail_url,
-                "timestamp": timestamp,
-            }
-            self.upsert(cur, "issues", data)
-
-    def get_issue_select_details(self, issue_id: int, source_name: str) -> SelectDetails:
-
-        con = lite.connect(self.db_file)
-        with con:
-            cur = con.cursor()
-            con.text_factory = str
-
-            cur.execute(
-                "SELECT super_url,thumb_url,cover_date,site_detail_url FROM Issues WHERE id=? AND source_name=?",
-                [issue_id, source_name],
-            )
-            row = cur.fetchone()
-
-            details = SelectDetails(
-                image_url=None,
-                thumb_image_url=None,
-                cover_date=None,
-                site_detail_url=None,
-            )
-            if row is not None and row[0] is not None:
-                details["image_url"] = row[0]
-                details["thumb_image_url"] = row[1]
-                details["cover_date"] = row[2]
-                details["site_detail_url"] = row[3]
-
-            return details
-
-    def upsert(self, cur: lite.Cursor, tablename: str, data: dict[str, Any]) -> None:
-        """This does an insert if the given PK doesn't exist, and an
-        update it if does
-
-        TODO: should the cursor be created here, and not up the stack?
-        """
-
-        keys = ""
-        vals = []
-        ins_slots = ""
-        set_slots = ""
-
-        for key in data:
-            if data[key] is None:
-                continue
-
-            if keys != "":
-                keys += ", "
-            if ins_slots != "":
-                ins_slots += ", "
-            if set_slots != "":
-                set_slots += ", "
-
-            keys += key
-            vals.append(data[key])
-            ins_slots += "?"
-            set_slots += key + " = ?"
-
-        sql_ins = f"INSERT OR REPLACE INTO {tablename} ({keys}) VALUES ({ins_slots})"
-        cur.execute(sql_ins, vals)

comictaggerlib/comicvinetalker.py

@@ -1,808 +0,0 @@
-"""A python class to manage communication with Comic Vine's REST API"""
-#
-# Copyright 2012-2014 Anthony Beville
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-from __future__ import annotations
-
-import json
-import logging
-import re
-import time
-from datetime import datetime
-from typing import Any, Callable, cast
-from urllib.parse import urlencode, urljoin, urlsplit
-
-import requests
-from bs4 import BeautifulSoup
-
-from comicapi import utils
-from comicapi.genericmetadata import GenericMetadata
-from comicapi.issuestring import IssueString
-from comictaggerlib import ctversion, resulttypes
-from comictaggerlib.comiccacher import ComicCacher
-from comictaggerlib.settings import ComicTaggerSettings
-
-logger = logging.getLogger(__name__)
-
-try:
-    from PyQt5 import QtCore, QtNetwork
-
-    qt_available = True
-except ImportError:
-    qt_available = False
-
-logger = logging.getLogger(__name__)
-
-
-class CVTypeID:
-    Volume = "4050"
-    Issue = "4000"
-
-
-class ComicVineTalkerException(Exception):
-    Unknown = -1
-    Network = -2
-    InvalidKey = 100
-    RateLimit = 107
-
-    def __init__(self, code: int = -1, desc: str = "") -> None:
-        super().__init__()
-        self.desc = desc
-        self.code = code
-
-    def __str__(self) -> str:
-        if self.code in (ComicVineTalkerException.Unknown, ComicVineTalkerException.Network):
-            return self.desc
-
-        return f"CV error #{self.code}:  [{self.desc}]. \n"
-
-
-def list_fetch_complete(url_list: list[str]) -> None:
-    ...
-
-
-def url_fetch_complete(image_url: str, thumb_url: str | None) -> None:
-    ...
-
-
-class ComicVineTalker:
-    logo_url = "http://static.comicvine.com/bundles/comicvinesite/images/logo.png"
-    api_key = ""
-    api_base_url = ""
-
-    alt_url_list_fetch_complete = list_fetch_complete
-    url_fetch_complete = url_fetch_complete
-
-    @staticmethod
-    def get_rate_limit_message() -> str:
-        if ComicVineTalker.api_key == "":
-            return "Comic Vine rate limit exceeded.  You should configure your own Comic Vine API key."
-
-        return "Comic Vine rate limit exceeded.  Please wait a bit."
-
-    def __init__(self, series_match_thresh: int = 90) -> None:
-        # Identity name for the information source
-        self.source_name = "comicvine"
-
-        self.wait_for_rate_limit = False
-        self.series_match_thresh = series_match_thresh
-
-        # key that is registered to comictagger
-        default_api_key = "27431e6787042105bd3e47e169a624521f89f3a4"
-        default_url = "https://comicvine.gamespot.com/api"
-
-        self.issue_id: int | None = None
-
-        self.api_key = ComicVineTalker.api_key or default_api_key
-        tmp_url = urlsplit(ComicVineTalker.api_base_url or default_url)
-
-        # joinurl only works properly if there is a trailing slash
-        if tmp_url.path and tmp_url.path[-1] != "/":
-            tmp_url = tmp_url._replace(path=tmp_url.path + "/")
-
-        self.api_base_url = tmp_url.geturl()
-
-        self.log_func: Callable[[str], None] | None = None
-
-        if qt_available:
-            self.nam = QtNetwork.QNetworkAccessManager()
-
-    def set_log_func(self, log_func: Callable[[str], None]) -> None:
-        self.log_func = log_func
-
-    def write_log(self, text: str) -> None:
-        if self.log_func is None:
-            logger.info(text)
-        else:
-            self.log_func(text)
-
-    def parse_date_str(self, date_str: str) -> tuple[int | None, int | None, int | None]:
-        return utils.parse_date_str(date_str)
-
-    def test_key(self, key: str, url: str) -> bool:
-        if not url:
-            url = self.api_base_url
-        try:
-            test_url = urljoin(url, "issue/1/")
-
-            cv_response: resulttypes.CVResult = requests.get(
-                test_url,
-                headers={"user-agent": "comictagger/" + ctversion.version},
-                params={
-                    "api_key": key,
-                    "format": "json",
-                    "field_list": "name",
-                },
-            ).json()
-
-            # Bogus request, but if the key is wrong, you get error 100: "Invalid API Key"
-            return cv_response["status_code"] != 100
-        except Exception:
-            return False
-
-    def get_cv_content(self, url: str, params: dict[str, Any]) -> resulttypes.CVResult:
-        """
-        Get the content from the CV server.  If we're in "wait mode" and status code is a rate limit error
-        sleep for a bit and retry.
-        """
-        total_time_waited = 0
-        limit_wait_time = 1
-        counter = 0
-        wait_times = [1, 2, 3, 4]
-        while True:
-            cv_response: resulttypes.CVResult = self.get_url_content(url, params)
-            if self.wait_for_rate_limit and cv_response["status_code"] == ComicVineTalkerException.RateLimit:
-                self.write_log(f"Rate limit encountered.  Waiting for {limit_wait_time} minutes\n")
-                time.sleep(limit_wait_time * 60)
-                total_time_waited += limit_wait_time
-                limit_wait_time = wait_times[counter]
-                if counter < 3:
-                    counter += 1
-                # don't wait much more than 20 minutes
-                if total_time_waited < 20:
-                    continue
-            if cv_response["status_code"] != 1:
-                self.write_log(
-                    f"Comic Vine query failed with error #{cv_response['status_code']}:  [{cv_response['error']}]. \n"
-                )
-                raise ComicVineTalkerException(cv_response["status_code"], cv_response["error"])
-
-            # it's all good
-            break
-        return cv_response
-
-    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
-        for tries in range(3):
-            try:
-                resp = requests.get(url, params=params, headers={"user-agent": "comictagger/" + ctversion.version})
-                if resp.status_code == 200:
-                    return resp.json()
-                if resp.status_code == 500:
-                    self.write_log(f"Try #{tries + 1}: ")
-                    time.sleep(1)
-                    self.write_log(str(resp.status_code) + "\n")
-                else:
-                    break
-
-            except requests.exceptions.RequestException as e:
-                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, f"Error on Comic Vine server: {resp.status_code}"
-        )
-
-    def search_for_series(
-        self,
-        series_name: str,
-        callback: Callable[[int, int], None] | None = None,
-        refresh_cache: bool = False,
-        literal: bool = False,
-    ) -> list[resulttypes.CVVolumeResults]:
-
-        # Sanitize the series name for comicvine searching, comicvine search ignore symbols
-        search_series_name = utils.sanitize_title(series_name, literal)
-        logger.info("Searching: %s", search_series_name)
-
-        # Before we search online, look in our cache, since we might have done this same search recently
-        # For literal searches always retrieve from online
-        cvc = ComicCacher()
-        if not refresh_cache and not literal:
-            cached_search_results = cvc.get_search_results(self.source_name, series_name)
-
-            if len(cached_search_results) > 0:
-                return cached_search_results
-
-        params = {
-            "api_key": self.api_key,
-            "format": "json",
-            "resources": "volume",
-            "query": search_series_name,
-            "field_list": "volume,name,id,start_year,publisher,image,description,count_of_issues,aliases",
-            "page": 1,
-            "limit": 100,
-        }
-
-        cv_response = self.get_cv_content(urljoin(self.api_base_url, "search"), params)
-
-        search_results: list[resulttypes.CVVolumeResults] = []
-
-        # see http://api.comicvine.com/documentation/#handling_responses
-
-        current_result_count = cv_response["number_of_page_results"]
-        total_result_count = cv_response["number_of_total_results"]
-
-        # 8 Dec 2018 - Comic Vine changed query results again. Terms are now
-        # ORed together, and we get thousands of results.  Good news is the
-        # results are sorted by relevance, so we can be smart about halting the search.
-        # 1. Don't fetch more than some sane amount of pages.
-        # 2. Halt when any result on the current page is less than or equal to a set ratio using rapidfuzz
-        max_results = 500  # 5 pages
-
-        total_result_count = min(total_result_count, max_results)
-
-        if callback is None:
-            self.write_log(
-                f"Found {cv_response['number_of_page_results']} of {cv_response['number_of_total_results']} results\n"
-            )
-        search_results.extend(cast(list[resulttypes.CVVolumeResults], cv_response["results"]))
-        page = 1
-
-        if callback is not None:
-            callback(current_result_count, total_result_count)
-
-        # see if we need to keep asking for more pages...
-        while current_result_count < total_result_count:
-
-            if not literal:
-                # Stop searching once any entry falls below the threshold
-                stop_searching = any(
-                    not utils.titles_match(search_series_name, volume["name"], self.series_match_thresh)
-                    for volume in cast(list[resulttypes.CVVolumeResults], cv_response["results"])
-                )
-
-                if stop_searching:
-                    break
-
-            if callback is None:
-                self.write_log(f"getting another page of results {current_result_count} of {total_result_count}...\n")
-            page += 1
-
-            params["page"] = page
-            cv_response = self.get_cv_content(urljoin(self.api_base_url, "search"), params)
-
-            search_results.extend(cast(list[resulttypes.CVVolumeResults], cv_response["results"]))
-            current_result_count += cv_response["number_of_page_results"]
-
-            if callback is not None:
-                callback(current_result_count, total_result_count)
-
-        # Cache these search results, even if it's literal we cache the results
-        # The most it will cause is extra processing time
-        cvc.add_search_results(self.source_name, series_name, search_results)
-
-        return search_results
-
-    def fetch_volume_data(self, series_id: int) -> resulttypes.CVVolumeResults:
-
-        # before we search online, look in our cache, since we might already have this info
-        cvc = ComicCacher()
-        cached_volume_result = cvc.get_volume_info(series_id, self.source_name)
-
-        if cached_volume_result is not None:
-            return cached_volume_result
-
-        volume_url = urljoin(self.api_base_url, f"volume/{CVTypeID.Volume}-{series_id}")
-
-        params = {
-            "api_key": self.api_key,
-            "format": "json",
-            "field_list": "name,id,start_year,publisher,count_of_issues,aliases",
-        }
-        cv_response = self.get_cv_content(volume_url, params)
-
-        volume_results = cast(resulttypes.CVVolumeResults, cv_response["results"])
-
-        if volume_results:
-            cvc.add_volume_info(self.source_name, volume_results)
-
-        return volume_results
-
-    def fetch_issues_by_volume(self, series_id: int) -> list[resulttypes.CVIssuesResults]:
-        # before we search online, look in our cache, since we might already have this info
-        volume_data = self.fetch_volume_data(series_id)
-        cvc = ComicCacher()
-        cached_volume_issues_result = cvc.get_volume_issues_info(series_id, self.source_name)
-
-        if len(cached_volume_issues_result) >= volume_data["count_of_issues"]:
-            return cached_volume_issues_result
-
-        params = {
-            "api_key": self.api_key,
-            "filter": f"volume:{series_id}",
-            "format": "json",
-            "field_list": "id,volume,issue_number,name,image,cover_date,site_detail_url,description,aliases",
-            "offset": 0,
-        }
-        cv_response = self.get_cv_content(urljoin(self.api_base_url, "issues/"), params)
-
-        current_result_count = cv_response["number_of_page_results"]
-        total_result_count = cv_response["number_of_total_results"]
-
-        volume_issues_result = cast(list[resulttypes.CVIssuesResults], cv_response["results"])
-        page = 1
-        offset = 0
-
-        # see if we need to keep asking for more pages...
-        while current_result_count < total_result_count:
-            page += 1
-            offset += cv_response["number_of_page_results"]
-
-            params["offset"] = offset
-            cv_response = self.get_cv_content(urljoin(self.api_base_url, "issues/"), params)
-
-            volume_issues_result.extend(cast(list[resulttypes.CVIssuesResults], cv_response["results"]))
-            current_result_count += cv_response["number_of_page_results"]
-
-        self.repair_urls(volume_issues_result)
-
-        cvc.add_volume_issues_info(self.source_name, series_id, volume_issues_result)
-
-        return volume_issues_result
-
-    def fetch_issues_by_volume_issue_num_and_year(
-        self, volume_id_list: list[int], issue_number: str, year: str | int | None
-    ) -> list[resulttypes.CVIssuesResults]:
-        volume_filter = ""
-        for vid in volume_id_list:
-            volume_filter += str(vid) + "|"
-        flt = f"volume:{volume_filter},issue_number:{issue_number}"
-
-        int_year = utils.xlate(year, True)
-        if int_year is not None:
-            flt += f",cover_date:{int_year}-1-1|{int_year+1}-1-1"
-
-        params: dict[str, str | int] = {
-            "api_key": self.api_key,
-            "format": "json",
-            "field_list": "id,volume,issue_number,name,image,cover_date,site_detail_url,description,aliases",
-            "filter": flt,
-        }
-
-        cv_response = self.get_cv_content(urljoin(self.api_base_url, "issues/"), params)
-
-        current_result_count = cv_response["number_of_page_results"]
-        total_result_count = cv_response["number_of_total_results"]
-
-        filtered_issues_result = cast(list[resulttypes.CVIssuesResults], cv_response["results"])
-        page = 1
-        offset = 0
-
-        # see if we need to keep asking for more pages...
-        while current_result_count < total_result_count:
-            page += 1
-            offset += cv_response["number_of_page_results"]
-
-            params["offset"] = offset
-            cv_response = self.get_cv_content(urljoin(self.api_base_url, "issues/"), params)
-
-            filtered_issues_result.extend(cast(list[resulttypes.CVIssuesResults], cv_response["results"]))
-            current_result_count += cv_response["number_of_page_results"]
-
-        self.repair_urls(filtered_issues_result)
-
-        cvc = ComicCacher()
-        for c in filtered_issues_result:
-            cvc.add_volume_issues_info(self.source_name, c["volume"]["id"], [c])
-
-        return filtered_issues_result
-
-    def fetch_issue_data(self, series_id: int, issue_number: str, settings: ComicTaggerSettings) -> GenericMetadata:
-        volume_results = self.fetch_volume_data(series_id)
-        issues_list_results = self.fetch_issues_by_volume(series_id)
-
-        f_record = None
-        for record in issues_list_results:
-            if not IssueString(issue_number).as_string():
-                issue_number = "1"
-            if (
-                IssueString(record["issue_number"]).as_string().casefold()
-                == IssueString(issue_number).as_string().casefold()
-            ):
-                f_record = record
-                break
-
-        if f_record is not None:
-            issue_url = urljoin(self.api_base_url, f"issue/{CVTypeID.Issue}-{f_record['id']}")
-            params = {"api_key": self.api_key, "format": "json"}
-            cv_response = self.get_cv_content(issue_url, params)
-            issue_results = cast(resulttypes.CVIssueDetailResults, cv_response["results"])
-
-        else:
-            return GenericMetadata()
-
-        # 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: int, settings: ComicTaggerSettings) -> GenericMetadata:
-
-        issue_url = urljoin(self.api_base_url, f"issue/{CVTypeID.Issue}-{issue_id}")
-        params = {"api_key": self.api_key, "format": "json"}
-        cv_response = self.get_cv_content(issue_url, params)
-
-        issue_results = cast(resulttypes.CVIssueDetailResults, cv_response["results"])
-
-        volume_results = self.fetch_volume_data(issue_results["volume"]["id"])
-
-        # Now, map the Comic Vine data to generic metadata
-        md = self.map_cv_data_to_metadata(volume_results, issue_results, settings)
-        md.is_empty = False
-        return md
-
-    def map_cv_data_to_metadata(
-        self,
-        volume_results: resulttypes.CVVolumeResults,
-        issue_results: resulttypes.CVIssueDetailResults,
-        settings: ComicTaggerSettings,
-    ) -> GenericMetadata:
-
-        # Now, map the Comic Vine data to generic metadata
-        metadata = GenericMetadata()
-        metadata.is_empty = False
-
-        metadata.series = utils.xlate(issue_results["volume"]["name"])
-        metadata.issue = IssueString(issue_results["issue_number"]).as_string()
-        metadata.title = utils.xlate(issue_results["name"])
-
-        if volume_results["publisher"] is not None:
-            metadata.publisher = utils.xlate(volume_results["publisher"]["name"])
-        metadata.day, metadata.month, metadata.year = self.parse_date_str(issue_results["cover_date"])
-
-        metadata.comments = self.cleanup_html(issue_results["description"], settings.remove_html_tables)
-        if settings.use_series_start_as_volume:
-            metadata.volume = int(volume_results["start_year"])
-
-        metadata.notes = (
-            f"Tagged with ComicTagger {ctversion.version} using info from Comic Vine on"
-            f" {datetime.now():%Y-%m-%d %H:%M:%S}.  [Issue ID {issue_results['id']}]"
-        )
-        metadata.web_link = issue_results["site_detail_url"]
-
-        person_credits = issue_results["person_credits"]
-        for person in person_credits:
-            if "role" in person:
-                roles = person["role"].split(",")
-                for role in roles:
-                    # can we determine 'primary' from CV??
-                    metadata.add_credit(person["name"], role.title().strip(), False)
-
-        character_credits = issue_results["character_credits"]
-        character_list = []
-        for character in character_credits:
-            character_list.append(character["name"])
-        metadata.characters = ", ".join(character_list)
-
-        team_credits = issue_results["team_credits"]
-        team_list = []
-        for team in team_credits:
-            team_list.append(team["name"])
-        metadata.teams = ", ".join(team_list)
-
-        location_credits = issue_results["location_credits"]
-        location_list = []
-        for location in location_credits:
-            location_list.append(location["name"])
-        metadata.locations = ", ".join(location_list)
-
-        story_arc_credits = issue_results["story_arc_credits"]
-        arc_list = []
-        for arc in story_arc_credits:
-            arc_list.append(arc["name"])
-        if len(arc_list) > 0:
-            metadata.story_arc = ", ".join(arc_list)
-
-        return metadata
-
-    def cleanup_html(self, string: str, remove_html_tables: bool) -> str:
-        if string is None:
-            return ""
-        # find any tables
-        soup = BeautifulSoup(string, "html.parser")
-        tables = soup.findAll("table")
-
-        # remove all newlines first
-        string = string.replace("\n", "")
-
-        # put in our own
-        string = string.replace("<br>", "\n")
-        string = string.replace("</li>", "\n")
-        string = string.replace("</p>", "\n\n")
-        string = string.replace("<h1>", "*")
-        string = string.replace("</h1>", "*\n")
-        string = string.replace("<h2>", "*")
-        string = string.replace("</h2>", "*\n")
-        string = string.replace("<h3>", "*")
-        string = string.replace("</h3>", "*\n")
-        string = string.replace("<h4>", "*")
-        string = string.replace("</h4>", "*\n")
-        string = string.replace("<h5>", "*")
-        string = string.replace("</h5>", "*\n")
-        string = string.replace("<h6>", "*")
-        string = string.replace("</h6>", "*\n")
-
-        # remove the tables
-        p = re.compile(r"<table[^<]*?>.*?</table>")
-        if remove_html_tables:
-            string = p.sub("", string)
-            string = string.replace("*List of covers and their creators:*", "")
-        else:
-            string = p.sub("{}", string)
-
-        # now strip all other tags
-        p = re.compile(r"<[^<]*?>")
-        newstring = p.sub("", string)
-
-        newstring = newstring.replace("&nbsp;", " ")
-        newstring = newstring.replace("&amp;", "&")
-
-        newstring = newstring.strip()
-
-        if not remove_html_tables:
-            # now rebuild the tables into text from BSoup
-            try:
-                table_strings = []
-                for table in tables:
-                    rows = []
-                    hdrs = []
-                    col_widths = []
-                    for hdr in table.findAll("th"):
-                        item = hdr.string.strip()
-                        hdrs.append(item)
-                        col_widths.append(len(item))
-                    rows.append(hdrs)
-
-                    for row in table.findAll("tr"):
-                        cols = []
-                        col = row.findAll("td")
-                        i = 0
-                        for c in col:
-                            item = c.string.strip()
-                            cols.append(item)
-                            if len(item) > col_widths[i]:
-                                col_widths[i] = len(item)
-                            i += 1
-                        if len(cols) != 0:
-                            rows.append(cols)
-                    # now we have the data, make it into text
-                    fmtstr = ""
-                    for w in col_widths:
-                        fmtstr += f" {{:{w + 1}}}|"
-                    width = sum(col_widths) + len(col_widths) * 2
-                    table_text = ""
-                    counter = 0
-                    for row in rows:
-                        table_text += fmtstr.format(*row) + "\n"
-                        if counter == 0 and len(hdrs) != 0:
-                            table_text += "-" * width + "\n"
-                        counter += 1
-
-                    table_strings.append(table_text)
-
-                newstring = newstring.format(*table_strings)
-            except Exception:
-                # we caught an error rebuilding the table.
-                # just bail and remove the formatting
-                logger.exception("table parse error")
-                newstring.replace("{}", "")
-
-        return newstring
-
-    def fetch_issue_date(self, issue_id: int) -> tuple[int | None, int | None]:
-        details = self.fetch_issue_select_details(issue_id)
-        _, month, year = self.parse_date_str(details["cover_date"] or "")
-        return month, year
-
-    def fetch_issue_cover_urls(self, issue_id: int) -> tuple[str | None, str | None]:
-        details = self.fetch_issue_select_details(issue_id)
-        return details["image_url"], details["thumb_image_url"]
-
-    def fetch_issue_page_url(self, issue_id: int) -> str | None:
-        details = self.fetch_issue_select_details(issue_id)
-        return details["site_detail_url"]
-
-    def fetch_issue_select_details(self, issue_id: int) -> resulttypes.SelectDetails:
-        cached_details = self.fetch_cached_issue_select_details(issue_id)
-        if cached_details["image_url"] is not None:
-            return cached_details
-
-        issue_url = urljoin(self.api_base_url, f"issue/{CVTypeID.Issue}-{issue_id}")
-        logger.error("%s, %s", self.api_base_url, issue_url)
-
-        params = {"api_key": self.api_key, "format": "json", "field_list": "image,cover_date,site_detail_url"}
-
-        cv_response = self.get_cv_content(issue_url, params)
-        results = cast(resulttypes.CVIssueDetailResults, cv_response["results"])
-
-        details = resulttypes.SelectDetails(
-            image_url=results["image"]["super_url"],
-            thumb_image_url=results["image"]["thumb_url"],
-            cover_date=results["cover_date"],
-            site_detail_url=results["site_detail_url"],
-        )
-
-        if (
-            details["image_url"] is not None
-            and details["thumb_image_url"] is not None
-            and details["cover_date"] is not None
-            and details["site_detail_url"] is not None
-        ):
-            self.cache_issue_select_details(
-                issue_id,
-                details["image_url"],
-                details["thumb_image_url"],
-                details["cover_date"],
-                details["site_detail_url"],
-            )
-        return details
-
-    def fetch_cached_issue_select_details(self, issue_id: int) -> resulttypes.SelectDetails:
-
-        # before we search online, look in our cache, since we might already have this info
-        cvc = ComicCacher()
-        return cvc.get_issue_select_details(issue_id, self.source_name)
-
-    def cache_issue_select_details(
-        self, issue_id: int, image_url: str, thumb_url: str, cover_date: str, page_url: str
-    ) -> None:
-        cvc = ComicCacher()
-        cvc.add_issue_select_details(self.source_name, issue_id, image_url, thumb_url, cover_date, page_url)
-
-    def fetch_alternate_cover_urls(self, issue_id: int, issue_page_url: str) -> list[str]:
-        url_list = self.fetch_cached_alternate_cover_urls(issue_id)
-        if url_list:
-            return url_list
-
-        # scrape the CV issue page URL to get the alternate cover URLs
-        content = requests.get(issue_page_url, headers={"user-agent": "comictagger/" + ctversion.version}).text
-        alt_cover_url_list = self.parse_out_alt_cover_urls(content)
-
-        # cache this alt cover URL list
-        self.cache_alternate_cover_urls(issue_id, alt_cover_url_list)
-
-        return alt_cover_url_list
-
-    def parse_out_alt_cover_urls(self, page_html: str) -> list[str]:
-        soup = BeautifulSoup(page_html, "html.parser")
-
-        alt_cover_url_list = []
-
-        # Using knowledge of the layout of the Comic Vine issue page here:
-        # look for the divs that are in the classes 'imgboxart' and 'issue-cover'
-        div_list = soup.find_all("div")
-        covers_found = 0
-        for d in div_list:
-            if "class" in d.attrs:
-                c = d["class"]
-                if "imgboxart" in c and "issue-cover" in c:
-                    if d.img["src"].startswith("http"):
-                        covers_found += 1
-                        if covers_found != 1:
-                            alt_cover_url_list.append(d.img["src"])
-                    elif d.img["data-src"].startswith("http"):
-                        covers_found += 1
-                        if covers_found != 1:
-                            alt_cover_url_list.append(d.img["data-src"])
-
-        return alt_cover_url_list
-
-    def fetch_cached_alternate_cover_urls(self, issue_id: int) -> list[str]:
-
-        # before we search online, look in our cache, since we might already have this info
-        cvc = ComicCacher()
-        url_list = cvc.get_alt_covers(self.source_name, issue_id)
-
-        return url_list
-
-    def cache_alternate_cover_urls(self, issue_id: int, url_list: list[str]) -> None:
-        cvc = ComicCacher()
-        cvc.add_alt_covers(self.source_name, issue_id, url_list)
-
-    def async_fetch_issue_cover_urls(self, issue_id: int) -> None:
-
-        self.issue_id = issue_id
-        details = self.fetch_cached_issue_select_details(issue_id)
-        if details["image_url"] is not None:
-            ComicVineTalker.url_fetch_complete(details["image_url"], details["thumb_image_url"])
-            return
-
-        issue_url = urlsplit(self.api_base_url)
-        issue_url = issue_url._replace(
-            query=urlencode(
-                {
-                    "api_key": self.api_key,
-                    "format": "json",
-                    "field_list": "image,cover_date,site_detail_url",
-                }
-            ),
-            path=f"issue/{CVTypeID.Issue}-{issue_id}",
-        )
-
-        self.nam.finished.connect(self.async_fetch_issue_cover_url_complete)
-        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
-        data = reply.readAll()
-
-        try:
-            cv_response = cast(resulttypes.CVResult, json.loads(bytes(data)))
-        except Exception:
-            logger.exception("Comic Vine query failed to get JSON data\n%s", str(data))
-            return
-
-        if cv_response["status_code"] != 1:
-            logger.error("Comic Vine query failed with error:  [%s]. ", cv_response["error"])
-            return
-
-        result = cast(resulttypes.CVIssuesResults, cv_response["results"])
-
-        image_url = result["image"]["super_url"]
-        thumb_url = result["image"]["thumb_url"]
-        cover_date = result["cover_date"]
-        page_url = result["site_detail_url"]
-
-        self.cache_issue_select_details(cast(int, self.issue_id), image_url, thumb_url, cover_date, page_url)
-
-        ComicVineTalker.url_fetch_complete(image_url, thumb_url)
-
-    def async_fetch_alternate_cover_urls(self, issue_id: int, issue_page_url: str) -> None:
-        # This async version requires the issue page url to be provided!
-        self.issue_id = issue_id
-        url_list = self.fetch_cached_alternate_cover_urls(issue_id)
-        if url_list:
-            ComicVineTalker.alt_url_list_fetch_complete(url_list)
-            return
-
-        self.nam.finished.connect(self.async_fetch_alternate_cover_urls_complete)
-        self.nam.get(QtNetwork.QNetworkRequest(QtCore.QUrl(str(issue_page_url))))
-
-    def async_fetch_alternate_cover_urls_complete(self, reply: QtNetwork.QNetworkReply) -> None:
-        # read in the response
-        html = str(reply.readAll())
-        alt_cover_url_list = self.parse_out_alt_cover_urls(html)
-
-        # cache this alt cover URL list
-        self.cache_alternate_cover_urls(cast(int, self.issue_id), alt_cover_url_list)
-
-        ComicVineTalker.alt_url_list_fetch_complete(alt_cover_url_list)
-
-    def repair_urls(
-        self,
-        issue_list: list[resulttypes.CVIssuesResults]
-        | list[resulttypes.CVVolumeResults]
-        | list[resulttypes.CVIssueDetailResults],
-    ) -> None:
-        # make sure there are URLs for the image fields
-        for issue in issue_list:
-            if issue["image"] is None:
-                issue["image"] = resulttypes.CVImage(
-                    super_url=ComicVineTalker.logo_url,
-                    thumb_url=ComicVineTalker.logo_url,
-                )

comictaggerlib/coverimagewidget.py

@@ -1,10 +1,11 @@
 """A PyQt5 widget to display cover images
 
-Display cover images from either a local archive, or from Comic Vine.
+Display cover images from either a local archive, or from comic source metadata.
 TODO: This should be re-factored using subclasses!
 """
+
 #
-# Copyright 2012-2014 Anthony Beville
+# Copyright 2012-2014 ComicTagger Authors
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -20,19 +21,16 @@ TODO: This should be re-factored using subclasses!
 from __future__ import annotations
 
 import logging
-from typing import Callable, cast
+import pathlib
 
 from PyQt5 import QtCore, QtGui, QtWidgets, uic
 
-from comicapi import utils
 from comicapi.comicarchive import ComicArchive
-from comictaggerlib.comicvinetalker import ComicVineTalker
-from comictaggerlib.graphics import graphics_path
 from comictaggerlib.imagefetcher import ImageFetcher
 from comictaggerlib.imagepopup import ImagePopup
 from comictaggerlib.pageloader import PageLoader
 from comictaggerlib.ui import ui_path
-from comictaggerlib.ui.qtutils import get_qimage_from_data, reduce_widget_font_size
+from comictaggerlib.ui.qtutils import get_qimage_from_data
 
 logger = logging.getLogger(__name__)
 
@@ -41,7 +39,6 @@ def clickable(widget: QtWidgets.QWidget) -> QtCore.pyqtBoundSignal:
     """Allow a label to be clickable"""
 
     class Filter(QtCore.QObject):
-
         dblclicked = QtCore.pyqtSignal()
 
         def eventFilter(self, obj: QtCore.QObject, event: QtCore.QEvent) -> bool:
@@ -56,58 +53,45 @@ def clickable(widget: QtWidgets.QWidget) -> QtCore.pyqtBoundSignal:
     return flt.dblclicked
 
 
-class Signal(QtCore.QObject):
-    alt_url_list_fetch_complete = QtCore.pyqtSignal(list)
-    url_fetch_complete = QtCore.pyqtSignal(str, str)
-    image_fetch_complete = QtCore.pyqtSignal(QtCore.QByteArray)
-
-    def __init__(
-        self,
-        list_fetch: Callable[[list[str]], None],
-        url_fetch: Callable[[str, str], None],
-        image_fetch: Callable[[bytes], None],
-    ) -> None:
-        super().__init__()
-        self.alt_url_list_fetch_complete.connect(list_fetch)
-        self.url_fetch_complete.connect(url_fetch)
-        self.image_fetch_complete.connect(image_fetch)
-
-    def emit_list(self, url_list: list[str]) -> None:
-        self.alt_url_list_fetch_complete.emit(url_list)
-
-    def emit_url(self, image_url: str, thumb_url: str | None) -> None:
-        self.url_fetch_complete.emit(image_url, thumb_url)
-
-    def emit_image(self, image_data: bytes | QtCore.QByteArray) -> None:
-        self.image_fetch_complete.emit(image_data)
-
-
 class CoverImageWidget(QtWidgets.QWidget):
     ArchiveMode = 0
     AltCoverMode = 1
     URLMode = 1
     DataMode = 3
 
-    def __init__(self, parent: QtWidgets.QWidget, mode: int, expand_on_click: bool = True) -> None:
+    image_fetch_complete = QtCore.pyqtSignal(str, QtCore.QByteArray)
+
+    def __init__(
+        self,
+        parent: QtWidgets.QWidget,
+        mode: int,
+        cache_folder: pathlib.Path | None,
+        blur: bool = False,
+        expand_on_click: bool = True,
+    ) -> None:
         super().__init__(parent)
 
-        self.cover_fetcher = ImageFetcher()
-        uic.loadUi(ui_path / "coverimagewidget.ui", self)
-
-        reduce_widget_font_size(self.label)
-
-        self.sig = Signal(
-            self.alt_cover_url_list_fetch_complete, self.primary_url_fetch_complete, self.cover_remote_fetch_complete
-        )
+        if mode not in (self.AltCoverMode, self.URLMode) or cache_folder is None:
+            self.cover_fetcher = None
+            self.talker = None
+        else:
+            self.cover_fetcher = ImageFetcher(cache_folder)
+            self.talker = None
+        with (ui_path / "coverimagewidget.ui").open(encoding="utf-8") as uifile:
+            uic.loadUi(uifile, self)
 
+        self.cache_folder = cache_folder
         self.mode: int = mode
         self.page_loader: PageLoader | None = None
         self.showControls = True
+        self.blur = blur
+        self.scene = QtWidgets.QGraphicsScene(parent=self)
 
         self.current_pixmap = QtGui.QPixmap()
 
         self.comic_archive: ComicArchive | None = None
-        self.issue_id: int | None = None
+        self.issue_id: str = ""
+        self.issue_url: str | None = None
         self.url_list: list[str] = []
         if self.page_loader is not None:
             self.page_loader.abandoned = True
@@ -116,21 +100,24 @@ class CoverImageWidget(QtWidgets.QWidget):
         self.imageCount = 1
         self.imageData = b""
 
-        self.btnLeft.setIcon(QtGui.QIcon(str(graphics_path / "left.png")))
-        self.btnRight.setIcon(QtGui.QIcon(str(graphics_path / "right.png")))
+        self.btnLeft.setIcon(QtGui.QIcon(":/graphics/left.png"))
+        self.btnRight.setIcon(QtGui.QIcon(":/graphics/right.png"))
 
         self.btnLeft.clicked.connect(self.decrement_image)
         self.btnRight.clicked.connect(self.increment_image)
+        self.image_fetch_complete.connect(self.cover_remote_fetch_complete)
         if expand_on_click:
-            clickable(self.lblImage).connect(self.show_popup)
+            clickable(self.graphicsView).connect(self.show_popup)
         else:
-            self.lblImage.setToolTip("")
+            self.graphicsView.setToolTip("")
+        self.graphicsView.setScene(self.scene)
 
         self.update_content()
 
     def reset_widget(self) -> None:
         self.comic_archive = None
-        self.issue_id = None
+        self.issue_id = ""
+        self.issue_url = None
         self.url_list = []
         if self.page_loader is not None:
             self.page_loader.abandoned = True
@@ -173,15 +160,13 @@ class CoverImageWidget(QtWidgets.QWidget):
             self.imageCount = 1
             self.update_content()
 
-    def set_issue_id(self, issue_id: int) -> None:
+    def set_issue_details(self, issue_id: str, url_list: list[str]) -> None:
         if self.mode == CoverImageWidget.AltCoverMode:
             self.reset_widget()
             self.update_content()
             self.issue_id = issue_id
 
-            comic_vine = ComicVineTalker()
-            ComicVineTalker.url_fetch_complete = self.sig.emit_url
-            comic_vine.async_fetch_issue_cover_urls(self.issue_id)
+            self.set_url_list(url_list)
 
     def set_image_data(self, image_data: bytes) -> None:
         if self.mode == CoverImageWidget.DataMode:
@@ -195,31 +180,11 @@ class CoverImageWidget(QtWidgets.QWidget):
 
             self.update_content()
 
-    def primary_url_fetch_complete(self, primary_url: str, thumb_url: str | None = None) -> None:
-        self.url_list.append(str(primary_url))
+    def set_url_list(self, url_list: list[str]) -> None:
+        self.url_list = url_list
         self.imageIndex = 0
         self.imageCount = len(self.url_list)
         self.update_content()
-
-        # defer the alt cover search
-        QtCore.QTimer.singleShot(1, self.start_alt_cover_search)
-
-    def start_alt_cover_search(self) -> None:
-
-        if self.issue_id is not None:
-            # now we need to get the list of alt cover URLs
-            self.label.setText("Searching for alt. covers...")
-
-            # page URL should already be cached, so no need to defer
-            comic_vine = ComicVineTalker()
-            issue_page_url = comic_vine.fetch_issue_page_url(self.issue_id)
-            ComicVineTalker.alt_url_list_fetch_complete = self.sig.emit_list
-            comic_vine.async_fetch_alternate_cover_urls(utils.xlate(self.issue_id), cast(str, issue_page_url))
-
-    def alt_cover_url_list_fetch_complete(self, url_list: list[str]) -> None:
-        if url_list:
-            self.url_list.extend(url_list)
-            self.imageCount = len(self.url_list)
         self.update_controls()
 
     def set_page(self, pagenum: int) -> None:
@@ -237,7 +202,7 @@ class CoverImageWidget(QtWidgets.QWidget):
         elif self.mode in [CoverImageWidget.AltCoverMode, CoverImageWidget.URLMode]:
             self.load_url()
         elif self.mode == CoverImageWidget.DataMode:
-            self.cover_remote_fetch_complete(self.imageData)
+            self.cover_remote_fetch_complete("", self.imageData)
         else:
             self.load_page()
 
@@ -267,13 +232,18 @@ class CoverImageWidget(QtWidgets.QWidget):
             self.label.setText(f"Page {self.imageIndex + 1} (of {self.imageCount})")
 
     def load_url(self) -> None:
+        assert isinstance(self.cache_folder, pathlib.Path)
         self.load_default()
-        self.cover_fetcher = ImageFetcher()
-        ImageFetcher.image_fetch_complete = self.sig.emit_image
-        self.cover_fetcher.fetch(self.url_list[self.imageIndex])
+        self.cover_fetcher = ImageFetcher(self.cache_folder)
+        ImageFetcher.image_fetch_complete = self.image_fetch_complete.emit
+        data = self.cover_fetcher.fetch(self.url_list[self.imageIndex])
+        if data:
+            self.cover_remote_fetch_complete(self.url_list[self.imageIndex], data)
 
     # called when the image is done loading from internet
-    def cover_remote_fetch_complete(self, image_data: bytes) -> None:
+    def cover_remote_fetch_complete(self, url: str, image_data: bytes) -> None:
+        if url and url not in self.url_list:
+            return
         img = get_qimage_from_data(image_data)
         self.current_pixmap = QtGui.QPixmap.fromImage(img)
         self.set_display_pixmap()
@@ -293,7 +263,7 @@ class CoverImageWidget(QtWidgets.QWidget):
         self.page_loader = None
 
     def load_default(self) -> None:
-        self.current_pixmap = QtGui.QPixmap(str(graphics_path / "nocover.png"))
+        self.current_pixmap = QtGui.QPixmap(":/graphics/nocover.png")
         self.set_display_pixmap()
 
     def resizeEvent(self, resize_event: QtGui.QResizeEvent) -> None:
@@ -303,28 +273,36 @@ class CoverImageWidget(QtWidgets.QWidget):
     def set_display_pixmap(self) -> None:
         """The deltas let us know what the new width and height of the label will be"""
 
-        new_h = self.frame.height()
         new_w = self.frame.width()
+        new_h = self.frame.height()
         frame_w = self.frame.width()
         frame_h = self.frame.height()
 
-        new_h -= 4
-        new_w -= 4
+        new_h -= 8
+        new_w -= 8
 
         new_h = max(new_h, 0)
         new_w = max(new_w, 0)
 
         # scale the pixmap to fit in the frame
         scaled_pixmap = self.current_pixmap.scaled(
-            new_w, new_h, QtCore.Qt.AspectRatioMode.KeepAspectRatio, QtCore.Qt.SmoothTransformation
+            new_w, new_h, QtCore.Qt.AspectRatioMode.KeepAspectRatio, QtCore.Qt.TransformationMode.SmoothTransformation
         )
-        self.lblImage.setPixmap(scaled_pixmap)
+        self.scene.clear()
+        qpix = self.scene.addPixmap(scaled_pixmap)
+        assert qpix
+        if self.blur:
+            blur = QtWidgets.QGraphicsBlurEffect(parent=self)
+            blur.setBlurHints(QtWidgets.QGraphicsBlurEffect.BlurHint.PerformanceHint)
+            blur.setBlurRadius(30)
+            qpix.setGraphicsEffect(blur)
 
         # move and resize the label to be centered in the fame
         img_w = scaled_pixmap.width()
         img_h = scaled_pixmap.height()
-        self.lblImage.resize(img_w, img_h)
-        self.lblImage.move(int((frame_w - img_w) / 2), int((frame_h - img_h) / 2))
+        self.scene.setSceneRect(0, 0, img_w, img_h)
+        self.graphicsView.resize(img_w + 2, img_h + 2)
+        self.graphicsView.move(int((frame_w - img_w) / 2), int((frame_h - img_h) / 2))
 
     def show_popup(self) -> None:
         ImagePopup(self, self.current_pixmap)

comictaggerlib/crediteditorwindow.py

@@ -1,6 +1,7 @@
 """A PyQT4 dialog to edit credits"""
+
 #
-# Copyright 2012-2014 Anthony Beville
+# Copyright 2012-2014 ComicTagger Authors
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -16,10 +17,13 @@
 from __future__ import annotations
 
 import logging
-from typing import Any
+import operator
 
+import natsort
 from PyQt5 import QtWidgets, uic
 
+from comicapi import utils
+from comicapi.genericmetadata import Credit
 from comictaggerlib.ui import ui_path
 
 logger = logging.getLogger(__name__)
@@ -29,10 +33,11 @@ class CreditEditorWindow(QtWidgets.QDialog):
     ModeEdit = 0
     ModeNew = 1
 
-    def __init__(self, parent: QtWidgets.QWidget, mode: int, role: str, name: str, primary: bool) -> None:
+    def __init__(self, parent: QtWidgets.QWidget, mode: int, credit: Credit) -> None:
         super().__init__(parent)
 
-        uic.loadUi(ui_path / "crediteditorwindow.ui", self)
+        with (ui_path / "crediteditorwindow.ui").open(encoding="utf-8") as uifile:
+            uic.loadUi(uifile, self)
 
         self.mode = mode
 
@@ -43,54 +48,47 @@ class CreditEditorWindow(QtWidgets.QDialog):
 
         # Add the entries to the role combobox
         self.cbRole.addItem("")
-        self.cbRole.addItem("Writer")
         self.cbRole.addItem("Artist")
-        self.cbRole.addItem("Penciller")
-        self.cbRole.addItem("Inker")
         self.cbRole.addItem("Colorist")
-        self.cbRole.addItem("Letterer")
         self.cbRole.addItem("Cover Artist")
         self.cbRole.addItem("Editor")
-        self.cbRole.addItem("Other")
+        self.cbRole.addItem("Inker")
+        self.cbRole.addItem("Letterer")
+        self.cbRole.addItem("Penciller")
         self.cbRole.addItem("Plotter")
         self.cbRole.addItem("Scripter")
+        self.cbRole.addItem("Translator")
+        self.cbRole.addItem("Writer")
+        self.cbRole.addItem("Other")
 
-        self.leName.setText(name)
+        self.cbLanguage.addItem("", "")
+        for f in natsort.humansorted(utils.languages().items(), operator.itemgetter(1)):
+            self.cbLanguage.addItem(f[1], f[0])
 
-        if role is not None and role != "":
-            i = self.cbRole.findText(role)
+        self.leName.setText(credit.person)
+
+        if credit.role is not None and credit.role != "":
+            i = self.cbRole.findText(credit.role)
             if i == -1:
-                self.cbRole.setEditText(role)
+                self.cbRole.setEditText(credit.role)
             else:
                 self.cbRole.setCurrentIndex(i)
 
-        self.cbPrimary.setChecked(primary)
+        if credit.language != "":
+            i = self.cbLanguage.findText(credit.language)
+            if i == -1:
+                self.cbLanguage.setEditText(credit.language)
+            else:
+                self.cbLanguage.setCurrentIndex(i)
 
-        self.cbRole.currentIndexChanged.connect(self.role_changed)
-        self.cbRole.editTextChanged.connect(self.role_changed)
+        self.cbPrimary.setChecked(credit.primary)
 
-        self.update_primary_button()
-
-    def update_primary_button(self) -> None:
-        enabled = self.current_role_can_be_primary()
-        self.cbPrimary.setEnabled(enabled)
-
-    def current_role_can_be_primary(self) -> bool:
-        role = self.cbRole.currentText()
-        if role.casefold() in ("artist", "writer"):
-            return True
-
-        return False
-
-    def role_changed(self, s: Any) -> None:
-        self.update_primary_button()
-
-    def get_credits(self) -> tuple[str, str, bool]:
+    def get_credit(self) -> Credit:
         primary = self.current_role_can_be_primary() and self.cbPrimary.isChecked()
-        return self.cbRole.currentText(), self.leName.text(), primary
+        return Credit(self.leName.text(), self.cbRole.currentText(), primary, self.cbLanguage.currentText())
 
     def accept(self) -> None:
-        if self.cbRole.currentText() == "" or self.leName.text() == "":
-            QtWidgets.QMessageBox.warning(self, "Whoops", "You need to enter both role and name for a credit.")
+        if self.leName.text() == "":
+            QtWidgets.QMessageBox.warning(self, "Whoops", "You need to enter a name for a credit.")
         else:
             QtWidgets.QDialog.accept(self)

comictaggerlib/ctsettings/__init__.py

@@ -0,0 +1,120 @@
+from __future__ import annotations
+
+import json
+import logging
+import pathlib
+from enum import Enum
+from typing import Any
+
+import settngs
+
+from comictaggerlib.ctsettings.commandline import (
+    initial_commandline_parser,
+    register_commandline_settings,
+    validate_commandline_settings,
+)
+from comictaggerlib.ctsettings.file import register_file_settings, validate_file_settings
+from comictaggerlib.ctsettings.plugin import group_for_plugin, register_plugin_settings, validate_plugin_settings
+from comictaggerlib.ctsettings.settngs_namespace import SettngsNS as ct_ns
+from comictaggerlib.ctsettings.types import ComicTaggerPaths
+from comictalker import ComicTalker
+
+logger = logging.getLogger(__name__)
+
+talkers: dict[str, ComicTalker] = {}
+
+__all__ = [
+    "initial_commandline_parser",
+    "register_commandline_settings",
+    "register_file_settings",
+    "register_plugin_settings",
+    "validate_commandline_settings",
+    "validate_file_settings",
+    "validate_plugin_settings",
+    "ComicTaggerPaths",
+    "ct_ns",
+    "group_for_plugin",
+]
+
+
+class SettingsEncoder(json.JSONEncoder):
+    def default(self, obj: Any) -> Any:
+        if isinstance(obj, pathlib.Path):
+            return str(obj)
+
+        # Let the base class default method raise the TypeError
+        return json.JSONEncoder.default(self, obj)
+
+
+def validate_types(config: settngs.Config[settngs.Values]) -> settngs.Config[settngs.Values]:
+    # Go through each setting
+    for group in config.definitions.values():
+        for setting in group.v.values():
+            # Get the value and if it is the default
+            value, default = settngs.get_option(config.values, setting)
+            if not default:
+                if setting.type is not None:
+                    # If it is not the default and the type attribute is not None
+                    # use it to convert the loaded string into the expected value
+                    if (
+                        isinstance(value, str)
+                        or isinstance(default, Enum)
+                        or (isinstance(setting.type, type) and issubclass(setting.type, Enum))
+                    ):
+                        config.values[setting.group][setting.dest] = setting.type(value)
+    return config
+
+
+def parse_config(
+    manager: settngs.Manager,
+    config_path: pathlib.Path,
+    args: list[str] | None = None,
+) -> tuple[settngs.Config[settngs.Values], bool]:
+    """
+    Function to parse options from a json file and passes the resulting Config object to parse_cmdline.
+
+    Args:
+        manager: settngs Manager object
+        config_path: A `pathlib.Path` object
+        args: Passed to argparse.ArgumentParser.parse_args
+    """
+    file_options, success = settngs.parse_file(manager.definitions, config_path)
+    file_options = validate_types(file_options)
+    cmdline_options = settngs.parse_cmdline(
+        manager.definitions,
+        manager.description,
+        manager.epilog,
+        args,
+        file_options,
+    )
+
+    final_options = settngs.normalize_config(cmdline_options, file=True, cmdline=True)
+    return final_options, success
+
+
+def save_file(
+    config: settngs.Config[settngs.T],
+    filename: pathlib.Path,
+) -> bool:
+    """
+    Helper function to save options from a json dictionary to a file
+
+    Args:
+        config: The options to save to a json dictionary
+        filename: A pathlib.Path object to save the json dictionary to
+    """
+    file_options = settngs.clean_config(config, file=True)
+    if "Quick Tag" in file_options and "url" in file_options["Quick Tag"]:
+        file_options["Quick Tag"]["url"] = str(file_options["Quick Tag"]["url"])
+
+    try:
+        if not filename.exists():
+            filename.parent.mkdir(exist_ok=True, parents=True)
+            filename.touch()
+
+        json_str = json.dumps(file_options, cls=SettingsEncoder, indent=2)
+        filename.write_text(json_str + "\n", encoding="utf-8")
+    except Exception:
+        logger.exception("Failed to save config file: %s", filename)
+        return False
+    return True

comictaggerlib/ctsettings/commandline.py

@@ -0,0 +1,331 @@
+"""CLI settings for ComicTagger"""
+
+#
+# Copyright 2012-2014 ComicTagger Authors
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+from __future__ import annotations
+
+import argparse
+import logging
+import os
+import platform
+import shlex
+import subprocess
+
+import settngs
+
+from comicapi import utils
+from comicapi.comicarchive import tags
+from comictaggerlib import ctversion, quick_tag
+from comictaggerlib.ctsettings.settngs_namespace import SettngsNS as ct_ns
+from comictaggerlib.ctsettings.types import ComicTaggerPaths, tag
+from comictaggerlib.resulttypes import Action
+
+logger = logging.getLogger(__name__)
+
+
+def initial_commandline_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(add_help=False)
+    # Ensure this stays up to date with register_runtime
+    parser.add_argument(
+        "--config",
+        help="Config directory for ComicTagger to use.\ndefault: %(default)s\n\n",
+        type=ComicTaggerPaths,
+        default=ComicTaggerPaths(),
+    )
+    parser.add_argument(
+        "-v",
+        "--verbose",
+        action="count",
+        default=0,
+        help="Be noisy when doing what it does. Use a second time to enable debug logs.\nShort option cannot be combined with other options.",
+    )
+    parser.add_argument(
+        "--enable-quick-tag",
+        action=argparse.BooleanOptionalAction,
+        default=False,
+        help='Enable the expiremental "quick tagger"',
+    )
+    return parser
+
+
+def register_runtime(parser: settngs.Manager) -> None:
+    parser.add_setting(
+        "--config",
+        help="Config directory for ComicTagger to use.\ndefault: %(default)s\n\n",
+        type=ComicTaggerPaths,
+        default=ComicTaggerPaths(),
+        file=False,
+    )
+    parser.add_setting(
+        "-v",
+        "--verbose",
+        action="count",
+        default=0,
+        help="Be noisy when doing what it does. Use a second time to enable debug logs.\nShort option cannot be combined with other options.",
+        file=False,
+    )
+    parser.add_setting(
+        "--enable-quick-tag",
+        action=argparse.BooleanOptionalAction,
+        default=False,
+        help='Enable the expiremental "quick tagger"',
+        file=False,
+    )
+    parser.add_setting("-q", "--quiet", action="store_true", help="Don't say much (for print mode).", file=False)
+    parser.add_setting(
+        "-j",
+        "--json",
+        action="store_true",
+        help="Output json on stdout. Ignored in interactive mode.\n\n",
+        file=False,
+    )
+    parser.add_setting(
+        "--raw",
+        action="store_true",
+        help="""With -p, will print out the raw tag block(s) from the file.""",
+        file=False,
+    )
+    parser.add_setting(
+        "-i",
+        "--interactive",
+        action="store_true",
+        help="""Interactively query the user when there are\nmultiple matches for an online search. Disabled json output\n\n""",
+        file=False,
+    )
+    parser.add_setting(
+        "--abort",
+        dest="abort_on_low_confidence",
+        action=argparse.BooleanOptionalAction,
+        default=True,
+        help="""Abort save operation when online match is of low confidence.\ndefault: %(default)s""",
+        file=False,
+    )
+    parser.add_setting(
+        "-n",
+        "--dryrun",
+        action="store_true",
+        help="Don't actually modify file (only relevant for -d, -s, or -r).\n\n",
+        file=False,
+    )
+    parser.add_setting(
+        "--summary",
+        default=True,
+        action=argparse.BooleanOptionalAction,
+        help="Show the summary after a save operation.\ndefault: %(default)s",
+        file=False,
+    )
+    parser.add_setting(
+        "-R",
+        "--recursive",
+        action="store_true",
+        help="Recursively include files in sub-folders.",
+        file=False,
+    )
+    parser.add_setting("-g", "--glob", action="store_true", help="Windows only. Enable globbing", file=False)
+    parser.add_setting("--darkmode", action="store_true", help="Windows only. Force a dark pallet", file=False)
+    parser.add_setting("--no-gui", action="store_true", help="Do not open the GUI, force the commandline", file=False)
+
+    parser.add_setting(
+        "--abort-on-conflict",
+        action="store_true",
+        help="""Don't export to zip if intended new filename exists\n(otherwise, creates a new unique filename).\n\n""",
+        file=False,
+    )
+    parser.add_setting(
+        "--delete-original",
+        action="store_true",
+        help="""Delete original archive after successful export to Zip.\n(only relevant for -e)\n\n""",
+        file=False,
+    )
+    parser.add_setting(
+        "-t",
+        "--tags-read",
+        metavar=f"{{{','.join(tags).upper()}}}",
+        default=[],
+        type=tag,
+        help="""Specify the tags to read.\nUse commas for multiple tags.\nSee --list-plugins for the available tags.\nThe tags used will be 'overlaid' in order:\ne.g. '-t cbl,cr' with no CBL tags, CR will be used if they exist and CR will overwrite any shared CBL tags.\n\n""",
+        file=False,
+    )
+    parser.add_setting(
+        "--tags-write",
+        metavar=f"{{{','.join(tags).upper()}}}",
+        default=[],
+        type=tag,
+        help="""Specify the tags to write.\nUse commas for multiple tags.\nRead tags will be used if unspecified\nSee --list-plugins for the available tags.\n\n""",
+        file=False,
+    )
+    parser.add_setting(
+        "--skip-existing-tags",
+        action=argparse.BooleanOptionalAction,
+        default=False,
+        help="""Skip archives that already have tags specified with -t,\notherwise merges new tags with existing tags (relevant for -s or -c).\ndefault: %(default)s""",
+        file=False,
+    )
+    parser.add_setting("files", nargs="*", default=[], file=False)
+
+
+def register_commands(parser: settngs.Manager) -> None:
+    parser.add_setting("--version", action="store_true", help="Display version.", file=False)
+
+    parser.add_setting(
+        "-p",
+        "--print",
+        dest="command",
+        action="store_const",
+        const=Action.print,
+        default=Action.gui,
+        help="""Print out tag info from file. Specify via -t to only print specific tags.\n\n""",
+        file=False,
+    )
+    parser.add_setting(
+        "-d",
+        "--delete",
+        dest="command",
+        action="store_const",
+        const=Action.delete,
+        help="Deletes the tags specified via -t.",
+        file=False,
+    )
+    parser.add_setting(
+        "-c",
+        "--copy",
+        type=tag,
+        default=[],
+        metavar=f"{{{','.join(tags).upper()}}}",
+        help="Copy the specified source tags to\ndestination tags specified via --tags-write\n(potentially lossy operation).\n\n",
+        file=False,
+    )
+    parser.add_setting(
+        "-s",
+        "--save",
+        dest="command",
+        action="store_const",
+        const=Action.save,
+        help="Save out tags as specified tags (via --tags-write).\nMust specify also at least -o, -f, or -m.\n\n",
+        file=False,
+    )
+    parser.add_setting(
+        "-r",
+        "--rename",
+        dest="command",
+        action="store_const",
+        const=Action.rename,
+        help="Rename the file based on specified tags.",
+        file=False,
+    )
+    parser.add_setting(
+        "-e",
+        "--export-to-zip",
+        dest="command",
+        action="store_const",
+        const=Action.export,
+        help="Export archive to Zip format.",
+        file=False,
+    )
+    parser.add_setting(
+        "--only-save-config",
+        dest="command",
+        action="store_const",
+        const=Action.save_config,
+        help="Only save the configuration (eg, Comic Vine API key) and quit.",
+        file=False,
+    )
+    parser.add_setting(
+        "--list-plugins",
+        dest="command",
+        action="store_const",
+        const=Action.list_plugins,
+        default=Action.gui,
+        help="List the available plugins.\n\n",
+        file=False,
+    )
+
+
+def register_commandline_settings(parser: settngs.Manager, enable_quick_tag: bool) -> None:
+    parser.add_group("Commands", register_commands, True)
+    parser.add_persistent_group("Runtime Options", register_runtime)
+    if enable_quick_tag:
+        parser.add_group("Quick Tag", quick_tag.settings)
+
+
+def validate_commandline_settings(config: settngs.Config[ct_ns], parser: settngs.Manager) -> settngs.Config[ct_ns]:
+    if config[0].Commands__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",
+        )
+
+    config[0].Runtime_Options__no_gui = any(
+        (config[0].Commands__command != Action.gui, config[0].Runtime_Options__no_gui, config[0].Commands__copy)
+    )
+
+    if platform.system() == "Windows" and config[0].Runtime_Options__glob:
+        # no globbing on windows shell, so do it for them
+        import glob
+
+        globs = config[0].Runtime_Options__files
+        config[0].Runtime_Options__files = []
+        for item in globs:
+            config[0].Runtime_Options__files.extend(glob.glob(item))
+
+    if config[0].Runtime_Options__json and config[0].Runtime_Options__interactive:
+        config[0].Runtime_Options__json = False
+
+    if config[0].Runtime_Options__tags_read and not config[0].Runtime_Options__tags_write:
+        config[0].Runtime_Options__tags_write = config[0].Runtime_Options__tags_read
+
+    if config[0].Runtime_Options__no_gui and not config[0].Runtime_Options__files:
+        if config[0].Commands__command == Action.print and not config[0].Auto_Tag__metadata.is_empty:
+            ...  # allow printing the metadata provided on the commandline
+        elif config[0].Commands__command not in (Action.save_config, Action.list_plugins):
+            parser.exit(message="Command requires at least one filename!\n", status=1)
+
+    if config[0].Commands__command == Action.delete and not config[0].Runtime_Options__tags_write:
+        parser.exit(message="Please specify the tags to delete with --tags-write\n", status=1)
+
+    if config[0].Commands__command == Action.save and not config[0].Runtime_Options__tags_write:
+        parser.exit(message="Please specify the tags to save with --tags-write\n", status=1)
+
+    if config[0].Commands__copy:
+        config[0].Commands__command = Action.copy
+        if not config[0].Runtime_Options__tags_write:
+            parser.exit(message="Please specify the tags to copy to with --tags-write\n", status=1)
+
+    if config[0].Runtime_Options__recursive:
+        config[0].Runtime_Options__files = utils.get_recursive_filelist(config[0].Runtime_Options__files)
+
+    # take a crack at finding rar exe if it's not in the path
+    if not utils.which("rar"):
+        if platform.system() == "Windows":
+            letters = ["C"]
+            letters.extend({f"{d}" for d in "ABCDEFGHIJKLMNOPQRSTUVWXYZ" if os.path.exists(f"{d}:\\")} - {"C"})
+            for letter in letters:
+                # look in some likely places for Windows machines
+                utils.add_to_path(rf"{letter}:\Program Files\WinRAR")
+                utils.add_to_path(rf"{letter}:\Program Files (x86)\WinRAR")
+        else:
+            if platform.system() == "Darwin":
+                result = subprocess.run(("/usr/libexec/path_helper", "-s"), capture_output=True)
+                for path in reversed(
+                    shlex.split(result.stdout.decode("utf-8", errors="ignore"))[0]
+                    .partition("=")[2]
+                    .rstrip(";")
+                    .split(os.pathsep)
+                ):
+                    utils.add_to_path(path)
+            utils.add_to_path("/opt/homebrew/bin")
+
+    return config

comictaggerlib/ctsettings/file.py

@@ -0,0 +1,397 @@
+from __future__ import annotations
+
+import argparse
+import uuid
+
+import settngs
+
+from comicapi import merge, utils
+from comicapi.genericmetadata import GenericMetadata
+from comictaggerlib.ctsettings.settngs_namespace import SettngsNS as ct_ns
+from comictaggerlib.ctsettings.types import parse_metadata_from_string
+from comictaggerlib.defaults import DEFAULT_REPLACEMENTS, Replacement, Replacements
+
+
+def general(parser: settngs.Manager) -> None:
+    # General Settings
+    parser.add_setting("check_for_new_version", default=False, cmdline=False)
+    parser.add_setting("blur", default=False, cmdline=False)
+    parser.add_setting(
+        "--prompt-on-save",
+        default=True,
+        action=argparse.BooleanOptionalAction,
+        help="Prompts the user to confirm saving tags when using the GUI.\ndefault: %(default)s",
+    )
+
+
+def internal(parser: settngs.Manager) -> None:
+    # automatic settings
+    parser.add_setting("install_id", default=uuid.uuid4().hex, cmdline=False)
+    parser.add_setting("write_tags", default=["cr"], cmdline=False)
+    parser.add_setting("read_tags", default=["cr"], cmdline=False)
+    parser.add_setting("last_opened_folder", default="", cmdline=False)
+    parser.add_setting("window_width", default=0, cmdline=False)
+    parser.add_setting("window_height", default=0, cmdline=False)
+    parser.add_setting("window_x", default=0, cmdline=False)
+    parser.add_setting("window_y", default=0, cmdline=False)
+    parser.add_setting("form_width", default=-1, cmdline=False)
+    parser.add_setting("list_width", default=-1, cmdline=False)
+    parser.add_setting("sort_column", default=-1, cmdline=False)
+    parser.add_setting("sort_direction", default=0, cmdline=False)
+    parser.add_setting("remove_archive_after_successful_match", default=False, cmdline=False)
+
+
+def identifier(parser: settngs.Manager) -> None:
+    parser.add_setting(
+        "--series-match-identify-thresh",
+        default=91,
+        type=int,
+        help="The minimum Series name similarity needed to auto-identify an issue default: %(default)s",
+    )
+    parser.add_setting(
+        "--series-match-search-thresh",
+        default=90,
+        type=int,
+        help="The minimum Series name similarity to return from a search result default: %(default)s",
+    )
+    parser.add_setting(
+        "-b",
+        "--border-crop-percent",
+        default=10,
+        type=int,
+        help="ComicTagger will automatically add an additional cover that has any black borders cropped.\nIf the difference in height is less than %(default)s%% the cover will not be cropped.\ndefault: %(default)s\n\n",
+    )
+
+    parser.add_setting(
+        "--sort-series-by-year",
+        default=True,
+        action=argparse.BooleanOptionalAction,
+        help="Sorts series by year default: %(default)s",
+    )
+    parser.add_setting(
+        "--exact-series-matches-first",
+        default=True,
+        action=argparse.BooleanOptionalAction,
+        help="Puts series that are an exact match at the top of the list default: %(default)s",
+    )
+
+
+def dialog(parser: settngs.Manager) -> None:
+    parser.add_setting("show_disclaimer", default=True, cmdline=False)
+    parser.add_setting("dont_notify_about_this_version", default="", cmdline=False)
+    parser.add_setting("notify_plugin_changes", default=True, cmdline=False)
+
+
+def filename(parser: settngs.Manager) -> None:
+    parser.add_setting(
+        "--filename-parser",
+        default=utils.Parser.ORIGINAL,
+        metavar=f"{{{','.join(utils.Parser)}}}",
+        type=utils.Parser,
+        choices=utils.Parser,
+        help="Select the filename parser.\ndefault: %(default)s",
+    )
+    parser.add_setting(
+        "--remove-c2c",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        help="Removes c2c from filenames.\nRequires --complicated-parser\ndefault: %(default)s\n\n",
+    )
+    parser.add_setting(
+        "--remove-fcbd",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        help="Removes FCBD/free comic book day from filenames.\nRequires --complicated-parser\ndefault: %(default)s\n\n",
+    )
+    parser.add_setting(
+        "--remove-publisher",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        help="Attempts to remove publisher names from filenames, currently limited to Marvel and DC.\nRequires --complicated-parser\ndefault: %(default)s\n\n",
+    )
+    parser.add_setting(
+        "--split-words",
+        action="store_true",
+        help="""Splits words before parsing the filename.\ne.g. 'judgedredd' to 'judge dredd'\ndefault: %(default)s\n\n""",
+        file=False,
+    )
+    parser.add_setting(
+        "--protofolius-issue-number-scheme",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        help="Use an issue number scheme devised by protofolius for encoding format information as a letter in front of an issue number.\nImplies --allow-issue-start-with-letter.  Requires --complicated-parser\ndefault: %(default)s\n\n",
+    )
+    parser.add_setting(
+        "--allow-issue-start-with-letter",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        help="Allows an issue number to start with a single letter (e.g. '#X01').\nRequires --complicated-parser\ndefault: %(default)s\n\n",
+    )
+
+
+def talker(parser: settngs.Manager) -> None:
+    parser.add_setting(
+        "--source",
+        default="comicvine",
+        help="Use a specified source by source ID (use --list-plugins to list all sources).\ndefault: %(default)s",
+    )
+
+
+def md_options(parser: settngs.Manager) -> None:
+    # CBL Transform settings
+    parser.add_setting("--assume-lone-credit-is-primary", default=False, action=argparse.BooleanOptionalAction)
+    parser.add_setting("--copy-characters-to-tags", default=False, action=argparse.BooleanOptionalAction)
+    parser.add_setting("--copy-teams-to-tags", default=False, action=argparse.BooleanOptionalAction)
+    parser.add_setting("--copy-locations-to-tags", default=False, action=argparse.BooleanOptionalAction)
+    parser.add_setting("--copy-storyarcs-to-tags", default=False, action=argparse.BooleanOptionalAction)
+    parser.add_setting("--copy-notes-to-comments", default=False, action=argparse.BooleanOptionalAction)
+    parser.add_setting("--copy-weblink-to-comments", default=False, action=argparse.BooleanOptionalAction)
+    parser.add_setting("--apply-transform-on-import", default=False, action=argparse.BooleanOptionalAction)
+    parser.add_setting("--apply-transform-on-bulk-operation", default=False, action=argparse.BooleanOptionalAction)
+
+    parser.add_setting(
+        "--remove-html-tables",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        display_name="Remove HTML tables",
+        help="Removes html tables instead of converting them to text",
+    )
+    parser.add_setting("use_short_tag_names", default=False, action=argparse.BooleanOptionalAction, cmdline=False)
+    parser.add_setting(
+        "--cr",
+        default=True,
+        action=argparse.BooleanOptionalAction,
+        help="Enable ComicRack tags. Turn off to only use CIX tags.\ndefault: %(default)s",
+    )
+    parser.add_setting(
+        "--tag-merge",
+        metavar=f"{{{','.join(merge.Mode)}}}",
+        default=merge.Mode.OVERLAY,
+        choices=merge.Mode,
+        type=merge.Mode,
+        help="How to merge fields when reading enabled tags (CR, CBL, etc.) See -t, --tags-read default: %(default)s",
+    )
+    parser.add_setting(
+        "--metadata-merge",
+        metavar=f"{{{','.join(merge.Mode)}}}",
+        default=merge.Mode.OVERLAY,
+        choices=merge.Mode,
+        type=merge.Mode,
+        help="How to merge fields when downloading new metadata (CV, Metron, GCD, etc.) default: %(default)s",
+    )
+    parser.add_setting(
+        "--tag-merge-lists",
+        action=argparse.BooleanOptionalAction,
+        default=True,
+        help="Merge lists when reading enabled tags (genres, characters, etc.) default: %(default)s",
+    )
+    parser.add_setting(
+        "--metadata-merge-lists",
+        action=argparse.BooleanOptionalAction,
+        default=True,
+        help="Merge lists when downloading new metadata (genres, characters, etc.) default: %(default)s",
+    )
+
+
+def rename(parser: settngs.Manager) -> None:
+    parser.add_setting(
+        "--template",
+        default="{series} #{issue} ({year})",
+        help="The teplate to use when renaming.\ndefault: %(default)s",
+    )
+    parser.add_setting(
+        "--issue-number-padding",
+        default=3,
+        type=int,
+        help="The minimum number of digits to use for the issue number when renaming.\ndefault: %(default)s",
+    )
+    parser.add_setting(
+        "--use-smart-string-cleanup",
+        default=True,
+        action=argparse.BooleanOptionalAction,
+        help="Attempts to intelligently cleanup whitespace when renaming.\ndefault: %(default)s",
+    )
+    parser.add_setting(
+        "--auto-extension",
+        default=True,
+        action=argparse.BooleanOptionalAction,
+        help="Automatically sets the extension based on the archive type e.g. cbr for rar, cbz for zip.\ndefault: %(default)s",
+    )
+    parser.add_setting("--dir", default="", help="The directory to move renamed files to.")
+    parser.add_setting(
+        "--move",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        help="Enables moving renamed files to a separate directory.\ndefault: %(default)s",
+    )
+    parser.add_setting(
+        "--only-move",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        help="Ignores the filename when moving renamed files to a separate directory.\ndefault: %(default)s",
+    )
+    parser.add_setting(
+        "--strict-filenames",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        help="Ensures that filenames are valid for all OSs.\ndefault: %(default)s",
+    )
+    parser.add_setting("replacements", default=DEFAULT_REPLACEMENTS, cmdline=False)
+
+
+def autotag(parser: settngs.Manager) -> None:
+    parser.add_setting(
+        "-o",
+        "--online",
+        action="store_true",
+        help="""Search online and attempt to identify file\nusing existing tags and images in archive.\nMay be used in conjunction with -f and -m.\n\n""",
+        file=False,
+    )
+    parser.add_setting(
+        "--save-on-low-confidence",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        help="Automatically save tags on low-confidence matches.\ndefault: %(default)s",
+        cmdline=False,
+    )
+    parser.add_setting(
+        "--use-year-when-identifying",
+        default=True,
+        action=argparse.BooleanOptionalAction,
+        help="Use the year metadata attribute when auto-tagging a comic.\ndefault: %(default)s",
+    )
+    parser.add_setting(
+        "-1",
+        "--assume-issue-one",
+        action=argparse.BooleanOptionalAction,
+        help="Assume issue number is 1 if not found (relevant for -s).\ndefault: %(default)s\n\n",
+        default=False,
+    )
+    parser.add_setting(
+        "--ignore-leading-numbers-in-filename",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        help="When searching ignore leading numbers in the filename.\ndefault: %(default)s",
+    )
+    parser.add_setting(
+        "-f",
+        "--parse-filename",
+        action="store_true",
+        help="""Parse the filename to get some info,\nspecifically series name, issue number,\nvolume, and publication year.\n\n""",
+        file=False,
+    )
+    parser.add_setting(
+        "--prefer-filename",
+        action="store_true",
+        help="""Prefer metadata parsed from the filename. CLI only.\n\n""",
+        file=False,
+    )
+    parser.add_setting(
+        "--id",
+        dest="issue_id",
+        type=str,
+        help="""Use the issue ID when searching online.\nOverrides all other metadata.\n\n""",
+        file=False,
+    )
+    parser.add_setting(
+        "-m",
+        "--metadata",
+        default=GenericMetadata(),
+        type=parse_metadata_from_string,
+        help="""Explicitly define some metadata to be used in YAML syntax.  Use @file.yaml to read from a file.  e.g.:\n"series: Plastic Man, publisher: Quality Comics, year: "\n"series: 'Kickers, Inc.', issue: '1', year: 1986"\nIf you want to erase a tag leave the value blank.\nSome names that can be used: series, issue, issue_count, year,\npublisher, title\n\n""",
+        file=False,
+    )
+    parser.add_setting(
+        "--clear-tags",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        help="Clears all existing tags during import, default is to merge tags.\nMay be used in conjunction with -o, -f and -m.\ndefault: %(default)s\n\n",
+    )
+    parser.add_setting(
+        "--publisher-filter",
+        default=["Panini Comics", "Abril", "Planeta DeAgostini", "Editorial Televisa", "Dino Comics"],
+        action="extend",
+        nargs="+",
+        help="When enabled, filters the listed publishers from all search results.\nEnding a publisher with a '-' removes a publisher from this list\ndefault: %(default)s\n\n",
+    )
+    parser.add_setting(
+        "--use-publisher-filter",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        help="Enables the publisher filter.\ndefault: %(default)s",
+    )
+    parser.add_setting(
+        "-a",
+        "--auto-imprint",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        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'.\ndefault: %(default)s\n\n",
+    )
+
+
+def parse_filter(config: settngs.Config[ct_ns]) -> settngs.Config[ct_ns]:
+    new_filter = []
+    remove = []
+    for x in config[0].Auto_Tag__publisher_filter:
+        x = x.strip()
+        if x:  # ignore empty arguments
+            if x[-1] == "-":  # this publisher needs to be removed. We remove after all publishers have been enumerated
+                remove.append(x.strip("-"))
+            else:
+                if x not in new_filter:
+                    new_filter.append(x)
+    for x in remove:  # remove publishers
+        if x in new_filter:
+            new_filter.remove(x)
+    config[0].Auto_Tag__publisher_filter = new_filter
+    return config
+
+
+def migrate_settings(config: settngs.Config[ct_ns]) -> settngs.Config[ct_ns]:
+    original_types = ("cbi", "cr", "comet")
+    write_Tags = config[0].internal__write_tags
+    if not isinstance(write_Tags, list):
+        if isinstance(write_Tags, int) and write_Tags in (0, 1, 2):
+            config[0].internal__write_tags = [original_types[write_Tags]]
+        elif isinstance(write_Tags, str):
+            config[0].internal__write_tags = [write_Tags]
+        else:
+            config[0].internal__write_tags = ["cr"]
+
+    read_tags = config[0].internal__read_tags
+    if not isinstance(read_tags, list):
+        if isinstance(read_tags, int) and read_tags in (0, 1, 2):
+            config[0].internal__read_tags = [original_types[read_tags]]
+        elif isinstance(read_tags, str):
+            config[0].internal__read_tags = [read_tags]
+        else:
+            config[0].internal__read_tags = ["cr"]
+
+    return config
+
+
+def validate_file_settings(config: settngs.Config[ct_ns]) -> settngs.Config[ct_ns]:
+    config = parse_filter(config)
+
+    config = migrate_settings(config)
+
+    if config[0].Filename_Parsing__protofolius_issue_number_scheme:
+        config[0].Filename_Parsing__allow_issue_start_with_letter = True
+
+    config[0].File_Rename__replacements = Replacements(
+        [Replacement(x[0], x[1], x[2]) for x in config[0].File_Rename__replacements[0]],
+        [Replacement(x[0], x[1], x[2]) for x in config[0].File_Rename__replacements[1]],
+    )
+    return config
+
+
+def register_file_settings(parser: settngs.Manager) -> None:
+    parser.add_group("internal", internal, False)
+    parser.add_group("Issue Identifier", identifier, False)
+    parser.add_group("Filename Parsing", filename, False)
+    parser.add_group("Sources", talker, False)
+    parser.add_group("Metadata Options", md_options, False)
+    parser.add_group("File Rename", rename, False)
+    parser.add_group("Auto-Tag", autotag, False)
+    parser.add_group("General", general, False)
+    parser.add_group("Dialog Flags", dialog, False)

comictaggerlib/ctsettings/plugin.py

@@ -0,0 +1,107 @@
+from __future__ import annotations
+
+import logging
+import os
+from typing import Any, cast
+
+import settngs
+
+import comicapi.comicarchive
+import comicapi.utils
+import comictaggerlib.ctsettings
+from comicapi.comicarchive import Archiver
+from comictaggerlib.ctsettings.settngs_namespace import SettngsNS as ct_ns
+from comictalker.comictalker import ComicTalker
+
+logger = logging.getLogger("comictagger")
+
+
+def group_for_plugin(plugin: Archiver | ComicTalker | type[Archiver]) -> str:
+    if isinstance(plugin, ComicTalker):
+        return f"Source {plugin.id}"
+    if isinstance(plugin, Archiver) or plugin == Archiver:
+        return "Archive"
+    raise NotImplementedError(f"Invalid plugin received: {plugin=}")
+
+
+def archiver(manager: settngs.Manager) -> None:
+    for archiver in comicapi.comicarchive.archivers:
+        if archiver.exe:
+            # add_setting will overwrite anything with the same name.
+            # So we only end up with one option even if multiple archivers use the same exe.
+            manager.add_setting(
+                f"--{settngs.sanitize_name(archiver.exe)}",
+                default=archiver.exe,
+                help="Path to the %(default)s executable",
+            )
+
+
+def register_talker_settings(manager: settngs.Manager, talkers: dict[str, ComicTalker]) -> None:
+    for talker in talkers.values():
+
+        def api_options(manager: settngs.Manager) -> None:
+            # The default needs to be unset or None.
+            # This allows this setting to be unset with the empty string, allowing the default to change
+            manager.add_setting(
+                f"--{talker.id}-key",
+                display_name="API Key",
+                help=f"API Key for {talker.name} (default: {talker.default_api_key})",
+            )
+            manager.add_setting(
+                f"--{talker.id}-url",
+                display_name="URL",
+                help=f"URL for {talker.name} (default: {talker.default_api_url})",
+            )
+
+        try:
+            manager.add_persistent_group(group_for_plugin(talker), api_options, False)
+            if hasattr(talker, "register_settings"):
+                manager.add_persistent_group(group_for_plugin(talker), talker.register_settings, False)
+        except Exception:
+            logger.exception("Failed to register settings for %s", talker.id)
+
+
+def validate_archive_settings(config: settngs.Config[ct_ns]) -> settngs.Config[ct_ns]:
+    cfg = settngs.normalize_config(config, file=True, cmdline=True, default=False)
+    for archiver in comicapi.comicarchive.archivers:
+        group = group_for_plugin(archiver())
+        exe_name = settngs.sanitize_name(archiver.exe)
+        if not exe_name:
+            continue
+
+        if exe_name in cfg[0][group] and cfg[0][group][exe_name]:
+            path = cfg[0][group][exe_name]
+            name = os.path.basename(path)
+            # If the path is not the basename then this is a relative or absolute path.
+            # Ensure it is absolute
+            if path != name:
+                path = os.path.abspath(path)
+
+            archiver.exe = path
+
+    return config
+
+
+def validate_talker_settings(config: settngs.Config[ct_ns], talkers: dict[str, ComicTalker]) -> settngs.Config[ct_ns]:
+    # Apply talker settings from config file
+    cfg = cast(settngs.Config[dict[str, Any]], settngs.normalize_config(config, True, True))
+    for talker in list(talkers.values()):
+        try:
+            cfg[0][group_for_plugin(talker)] = talker.parse_settings(cfg[0][group_for_plugin(talker)])
+        except Exception as e:
+            # Remove talker as we failed to apply the settings
+            del comictaggerlib.ctsettings.talkers[talker.id]
+            logger.exception("Failed to initialize talker settings: %s", e)
+
+    return cast(settngs.Config[ct_ns], settngs.get_namespace(cfg, file=True, cmdline=True))
+
+
+def validate_plugin_settings(config: settngs.Config[ct_ns], talkers: dict[str, ComicTalker]) -> settngs.Config[ct_ns]:
+    config = validate_archive_settings(config)
+    config = validate_talker_settings(config, talkers)
+    return config
+
+
+def register_plugin_settings(manager: settngs.Manager, talkers: dict[str, ComicTalker]) -> None:
+    manager.add_persistent_group("Archive", archiver, False)
+    register_talker_settings(manager, talkers)

comictaggerlib/ctsettings/plugin_finder.py

@@ -0,0 +1,185 @@
+"""Functions related to finding and loading plugins."""
+
+# Lifted from flake8 https://github.com/PyCQA/flake8/blob/main/src/flake8/plugins/finder.py#L127
+
+from __future__ import annotations
+
+import importlib.util
+import logging
+import pathlib
+import platform
+import re
+import sys
+from collections.abc import Generator, Iterable
+from typing import Any, NamedTuple, TypeVar
+
+if sys.version_info < (3, 10):
+    import importlib_metadata
+else:
+    import importlib.metadata as importlib_metadata
+
+logger = logging.getLogger(__name__)
+
+NORMALIZE_PACKAGE_NAME_RE = re.compile(r"[-_.]+")
+PLUGIN_GROUPS = frozenset(("comictagger.talker", "comicapi.archiver", "comicapi.tags"))
+icu_available = importlib.util.find_spec("icu") is not None
+
+
+def _custom_key(tup: Any) -> Any:
+    import natsort
+
+    lst = []
+    for x in natsort.os_sort_keygen()(tup):
+        ret = x
+        if len(x) > 1 and isinstance(x[1], int) and isinstance(x[0], str) and x[0] == "":
+            ret = ("a", *x[1:])
+
+        lst.append(ret)
+    return tuple(lst)
+
+
+T = TypeVar("T")
+
+
+def os_sorted(lst: Iterable[T]) -> Iterable[T]:
+    import natsort
+
+    key = _custom_key
+    if icu_available or platform.system() == "Windows":
+        key = natsort.os_sort_keygen()
+    return sorted(lst, key=key)
+
+
+class FailedToLoadPlugin(Exception):
+    """Exception raised when a plugin fails to load."""
+
+    FORMAT = 'ComicTagger failed to load local plugin "{name}" due to {exc}.'
+
+    def __init__(self, plugin_name: str, exception: Exception) -> None:
+        """Initialize our FailedToLoadPlugin exception."""
+        self.plugin_name = plugin_name
+        self.original_exception = exception
+        super().__init__(plugin_name, exception)
+
+    def __str__(self) -> str:
+        """Format our exception message."""
+        return self.FORMAT.format(
+            name=self.plugin_name,
+            exc=self.original_exception,
+        )
+
+
+def normalize_pypi_name(s: str) -> str:
+    """Normalize a distribution name according to PEP 503."""
+    return NORMALIZE_PACKAGE_NAME_RE.sub("-", s).lower()
+
+
+class Plugin(NamedTuple):
+    """A plugin before loading."""
+
+    package: str
+    version: str
+    entry_point: importlib_metadata.EntryPoint
+    path: pathlib.Path
+
+    def load(self) -> LoadedPlugin:
+        return LoadedPlugin(self, self.entry_point.load())
+
+
+class LoadedPlugin(NamedTuple):
+    """Represents a plugin after being imported."""
+
+    plugin: Plugin
+    obj: Any
+
+    @property
+    def entry_name(self) -> str:
+        """Return the name given in the packaging metadata."""
+        return self.plugin.entry_point.name
+
+    @property
+    def display_name(self) -> str:
+        """Return the name for use in user-facing / error messages."""
+        return f"{self.plugin.package}[{self.entry_name}]"
+
+
+class Plugins(NamedTuple):
+    """Classified plugins."""
+
+    archivers: list[LoadedPlugin]
+    tags: list[LoadedPlugin]
+    talkers: list[LoadedPlugin]
+
+    def all_plugins(self) -> Generator[LoadedPlugin]:
+        """Return an iterator over all :class:`LoadedPlugin`s."""
+        yield from self.archivers
+        yield from self.tags
+        yield from self.talkers
+
+    def versions_str(self) -> str:
+        """Return a user-displayed list of plugin versions."""
+        return ", ".join(sorted({f"{plugin.plugin.package}: {plugin.plugin.version}" for plugin in self.all_plugins()}))
+
+
+def _find_local_plugins(plugin_path: pathlib.Path) -> Generator[Plugin]:
+    logger.debug("Checking for distributions in %s", plugin_path)
+    for dist in importlib_metadata.distributions(path=[str(plugin_path)]):
+        logger.debug("found distribution %s", dist.name)
+        eps = dist.entry_points
+        for group in PLUGIN_GROUPS:
+            for ep in eps.select(group=group):
+                logger.debug("found EntryPoint group %s %s=%s", group, ep.name, ep.value)
+                yield Plugin(plugin_path.name, dist.version, ep, plugin_path)
+
+
+def find_plugins(plugin_folder: pathlib.Path) -> Plugins:
+    """Discovers all plugins (but does not load them)."""
+    ret: list[LoadedPlugin] = []
+    if not plugin_folder.is_dir():
+        return _classify_plugins(ret)
+
+    zips = [x for x in plugin_folder.iterdir() if x.is_file() and x.suffix in (".zip", ".whl")]
+
+    for plugin_path in os_sorted(zips):
+        logger.debug("looking for plugins in %s", plugin_path)
+        try:
+            sys.path.append(str(plugin_path))
+            for plugin in _find_local_plugins(plugin_path):
+                logger.debug("Attempting to load %s from %s", plugin.entry_point.name, plugin.path)
+                ret.append(plugin.load())
+        except Exception as err:
+            logger.exception(FailedToLoadPlugin(plugin_path.name, err))
+        finally:
+            sys.path.remove(str(plugin_path))
+            for mod in list(sys.modules.values()):
+                if (
+                    mod is not None
+                    and hasattr(mod, "__spec__")
+                    and mod.__spec__
+                    and str(plugin_path) in (mod.__spec__.origin or "")
+                ):
+                    sys.modules.pop(mod.__name__)
+
+    return _classify_plugins(ret)
+
+
+def _classify_plugins(plugins: list[LoadedPlugin]) -> Plugins:
+    archivers = []
+    tags = []
+    talkers = []
+
+    for p in plugins:
+        if p.plugin.entry_point.group == "comictagger.talker":
+            talkers.append(p)
+        elif p.plugin.entry_point.group == "comicapi.tags":
+            tags.append(p)
+        elif p.plugin.entry_point.group == "comicapi.archiver":
+            archivers.append(p)
+        else:
+            logger.warning(NotImplementedError(f"what plugin type? {p}"))
+
+    return Plugins(
+        tags=tags,
+        archivers=archivers,
+        talkers=talkers,
+    )

comictaggerlib/ctsettings/settngs_namespace.py

@@ -0,0 +1,300 @@
+from __future__ import annotations
+
+import typing
+
+import settngs
+import urllib3.util.url
+
+import comicapi.genericmetadata
+import comicapi.merge
+import comicapi.utils
+import comictaggerlib.ctsettings.types
+import comictaggerlib.defaults
+import comictaggerlib.resulttypes
+
+
+class SettngsNS(settngs.TypedNS):
+    Commands__version: bool
+    Commands__command: comictaggerlib.resulttypes.Action
+    Commands__copy: list[str]
+
+    Runtime_Options__config: comictaggerlib.ctsettings.types.ComicTaggerPaths
+    Runtime_Options__verbose: int
+    Runtime_Options__enable_quick_tag: bool
+    Runtime_Options__quiet: bool
+    Runtime_Options__json: bool
+    Runtime_Options__raw: bool
+    Runtime_Options__interactive: bool
+    Runtime_Options__abort_on_low_confidence: bool
+    Runtime_Options__dryrun: bool
+    Runtime_Options__summary: bool
+    Runtime_Options__recursive: bool
+    Runtime_Options__glob: bool
+    Runtime_Options__darkmode: bool
+    Runtime_Options__no_gui: bool
+    Runtime_Options__abort_on_conflict: bool
+    Runtime_Options__delete_original: bool
+    Runtime_Options__tags_read: list[str]
+    Runtime_Options__tags_write: list[str]
+    Runtime_Options__skip_existing_tags: bool
+    Runtime_Options__files: list[str]
+
+    Quick_Tag__url: urllib3.util.url.Url
+    Quick_Tag__max: int
+    Quick_Tag__simple: bool
+    Quick_Tag__aggressive_filtering: bool
+    Quick_Tag__hash: list[comictaggerlib.quick_tag.HashType]
+    Quick_Tag__exact_only: bool
+
+    internal__install_id: str
+    internal__write_tags: list[str]
+    internal__read_tags: list[str]
+    internal__last_opened_folder: str
+    internal__window_width: int
+    internal__window_height: int
+    internal__window_x: int
+    internal__window_y: int
+    internal__form_width: int
+    internal__list_width: int
+    internal__sort_column: int
+    internal__sort_direction: int
+    internal__remove_archive_after_successful_match: bool
+
+    Issue_Identifier__series_match_identify_thresh: int
+    Issue_Identifier__series_match_search_thresh: int
+    Issue_Identifier__border_crop_percent: int
+    Issue_Identifier__sort_series_by_year: bool
+    Issue_Identifier__exact_series_matches_first: bool
+
+    Filename_Parsing__filename_parser: comicapi.utils.Parser
+    Filename_Parsing__remove_c2c: bool
+    Filename_Parsing__remove_fcbd: bool
+    Filename_Parsing__remove_publisher: bool
+    Filename_Parsing__split_words: bool
+    Filename_Parsing__protofolius_issue_number_scheme: bool
+    Filename_Parsing__allow_issue_start_with_letter: bool
+
+    Sources__source: str
+
+    Metadata_Options__assume_lone_credit_is_primary: bool
+    Metadata_Options__copy_characters_to_tags: bool
+    Metadata_Options__copy_teams_to_tags: bool
+    Metadata_Options__copy_locations_to_tags: bool
+    Metadata_Options__copy_storyarcs_to_tags: bool
+    Metadata_Options__copy_notes_to_comments: bool
+    Metadata_Options__copy_weblink_to_comments: bool
+    Metadata_Options__apply_transform_on_import: bool
+    Metadata_Options__apply_transform_on_bulk_operation: bool
+    Metadata_Options__remove_html_tables: bool
+    Metadata_Options__use_short_tag_names: bool
+    Metadata_Options__cr: bool
+    Metadata_Options__tag_merge: comicapi.merge.Mode
+    Metadata_Options__metadata_merge: comicapi.merge.Mode
+    Metadata_Options__tag_merge_lists: bool
+    Metadata_Options__metadata_merge_lists: bool
+
+    File_Rename__template: str
+    File_Rename__issue_number_padding: int
+    File_Rename__use_smart_string_cleanup: bool
+    File_Rename__auto_extension: bool
+    File_Rename__dir: str
+    File_Rename__move: bool
+    File_Rename__only_move: bool
+    File_Rename__strict_filenames: bool
+    File_Rename__replacements: comictaggerlib.defaults.Replacements
+
+    Auto_Tag__online: bool
+    Auto_Tag__save_on_low_confidence: bool
+    Auto_Tag__use_year_when_identifying: bool
+    Auto_Tag__assume_issue_one: bool
+    Auto_Tag__ignore_leading_numbers_in_filename: bool
+    Auto_Tag__parse_filename: bool
+    Auto_Tag__prefer_filename: bool
+    Auto_Tag__issue_id: str | None
+    Auto_Tag__metadata: comicapi.genericmetadata.GenericMetadata
+    Auto_Tag__clear_tags: bool
+    Auto_Tag__publisher_filter: list[str]
+    Auto_Tag__use_publisher_filter: bool
+    Auto_Tag__auto_imprint: bool
+
+    General__check_for_new_version: bool
+    General__blur: bool
+    General__prompt_on_save: bool
+
+    Dialog_Flags__show_disclaimer: bool
+    Dialog_Flags__dont_notify_about_this_version: str
+    Dialog_Flags__notify_plugin_changes: bool
+
+    Archive__rar: str
+
+    Source_comicvine__comicvine_key: str | None
+    Source_comicvine__comicvine_url: str | None
+    Source_comicvine__cv_use_series_start_as_volume: bool
+    Source_comicvine__comicvine_custom_parameters: str | None
+
+
+class Commands(typing.TypedDict):
+    version: bool
+    command: comictaggerlib.resulttypes.Action
+    copy: list[str]
+
+
+class Runtime_Options(typing.TypedDict):
+    config: comictaggerlib.ctsettings.types.ComicTaggerPaths
+    verbose: int
+    enable_quick_tag: bool
+    quiet: bool
+    json: bool
+    raw: bool
+    interactive: bool
+    abort_on_low_confidence: bool
+    dryrun: bool
+    summary: bool
+    recursive: bool
+    glob: bool
+    darkmode: bool
+    no_gui: bool
+    abort_on_conflict: bool
+    delete_original: bool
+    tags_read: list[str]
+    tags_write: list[str]
+    skip_existing_tags: bool
+    files: list[str]
+
+
+class Quick_Tag(typing.TypedDict):
+    url: urllib3.util.url.Url
+    max: int
+    simple: bool
+    aggressive_filtering: bool
+    hash: list[comictaggerlib.quick_tag.HashType]
+    exact_only: bool
+
+
+class internal(typing.TypedDict):
+    install_id: str
+    write_tags: list[str]
+    read_tags: list[str]
+    last_opened_folder: str
+    window_width: int
+    window_height: int
+    window_x: int
+    window_y: int
+    form_width: int
+    list_width: int
+    sort_column: int
+    sort_direction: int
+    remove_archive_after_successful_match: bool
+
+
+class Issue_Identifier(typing.TypedDict):
+    series_match_identify_thresh: int
+    series_match_search_thresh: int
+    border_crop_percent: int
+    sort_series_by_year: bool
+    exact_series_matches_first: bool
+
+
+class Filename_Parsing(typing.TypedDict):
+    filename_parser: comicapi.utils.Parser
+    remove_c2c: bool
+    remove_fcbd: bool
+    remove_publisher: bool
+    split_words: bool
+    protofolius_issue_number_scheme: bool
+    allow_issue_start_with_letter: bool
+
+
+class Sources(typing.TypedDict):
+    source: str
+
+
+class Metadata_Options(typing.TypedDict):
+    assume_lone_credit_is_primary: bool
+    copy_characters_to_tags: bool
+    copy_teams_to_tags: bool
+    copy_locations_to_tags: bool
+    copy_storyarcs_to_tags: bool
+    copy_notes_to_comments: bool
+    copy_weblink_to_comments: bool
+    apply_transform_on_import: bool
+    apply_transform_on_bulk_operation: bool
+    remove_html_tables: bool
+    use_short_tag_names: bool
+    cr: bool
+    tag_merge: comicapi.merge.Mode
+    metadata_merge: comicapi.merge.Mode
+    tag_merge_lists: bool
+    metadata_merge_lists: bool
+
+
+class File_Rename(typing.TypedDict):
+    template: str
+    issue_number_padding: int
+    use_smart_string_cleanup: bool
+    auto_extension: bool
+    dir: str
+    move: bool
+    only_move: bool
+    strict_filenames: bool
+    replacements: comictaggerlib.defaults.Replacements
+
+
+class Auto_Tag(typing.TypedDict):
+    online: bool
+    save_on_low_confidence: bool
+    use_year_when_identifying: bool
+    assume_issue_one: bool
+    ignore_leading_numbers_in_filename: bool
+    parse_filename: bool
+    prefer_filename: bool
+    issue_id: str | None
+    metadata: comicapi.genericmetadata.GenericMetadata
+    clear_tags: bool
+    publisher_filter: list[str]
+    use_publisher_filter: bool
+    auto_imprint: bool
+
+
+class General(typing.TypedDict):
+    check_for_new_version: bool
+    blur: bool
+    prompt_on_save: bool
+
+
+class Dialog_Flags(typing.TypedDict):
+    show_disclaimer: bool
+    dont_notify_about_this_version: str
+    notify_plugin_changes: bool
+
+
+class Archive(typing.TypedDict):
+    rar: str
+
+
+class Source_comicvine(typing.TypedDict):
+    comicvine_key: str | None
+    comicvine_url: str | None
+    cv_use_series_start_as_volume: bool
+    comicvine_custom_parameters: str | None
+
+
+SettngsDict = typing.TypedDict(
+    "SettngsDict",
+    {
+        "Commands": Commands,
+        "Runtime Options": Runtime_Options,
+        "Quick Tag": Quick_Tag,
+        "internal": internal,
+        "Issue Identifier": Issue_Identifier,
+        "Filename Parsing": Filename_Parsing,
+        "Sources": Sources,
+        "Metadata Options": Metadata_Options,
+        "File Rename": File_Rename,
+        "Auto-Tag": Auto_Tag,
+        "General": General,
+        "Dialog Flags": Dialog_Flags,
+        "Archive": Archive,
+        "Source comicvine": Source_comicvine,
+    },
+)

comictaggerlib/ctsettings/types.py

@@ -0,0 +1,245 @@
+from __future__ import annotations
+
+import argparse
+import logging
+import pathlib
+import sys
+import types
+import typing
+from collections.abc import Collection, Mapping
+from typing import Any
+
+import yaml
+from appdirs import AppDirs
+
+from comicapi import utils
+from comicapi.comicarchive import tags
+from comicapi.genericmetadata import REMOVE, GenericMetadata
+
+logger = logging.getLogger(__name__)
+
+if sys.version_info < (3, 10):
+
+    @typing.no_type_check
+    def get_type_hints(obj, globalns=None, localns=None, include_extras=False):
+        if getattr(obj, "__no_type_check__", None):
+            return {}
+        # Classes require a special treatment.
+        if isinstance(obj, type):
+            hints = {}
+            for base in reversed(obj.__mro__):
+                if globalns is None:
+                    base_globals = getattr(sys.modules.get(base.__module__, None), "__dict__", {})
+                else:
+                    base_globals = globalns
+                ann = base.__dict__.get("__annotations__", {})
+                if isinstance(ann, types.GetSetDescriptorType):
+                    ann = {}
+                base_locals = dict(vars(base)) if localns is None else localns
+                if localns is None and globalns is None:
+                    # This is surprising, but required.  Before Python 3.10,
+                    # get_type_hints only evaluated the globalns of
+                    # a class.  To maintain backwards compatibility, we reverse
+                    # the globalns and localns order so that eval() looks into
+                    # *base_globals* first rather than *base_locals*.
+                    # This only affects ForwardRefs.
+                    base_globals, base_locals = base_locals, base_globals
+                for name, value in ann.items():
+                    if value is None:
+                        value = type(None)
+                    if isinstance(value, str):
+                        if "|" in value:
+                            value = "Union[" + value.replace(" |", ",") + "]"
+                        value = typing.ForwardRef(value, is_argument=False, is_class=True)
+                    value = typing._eval_type(value, base_globals, base_locals)
+                    hints[name] = value
+            return hints if include_extras else {k: typing._strip_annotations(t) for k, t in hints.items()}
+
+        if globalns is None:
+            if isinstance(obj, types.ModuleType):
+                globalns = obj.__dict__
+            else:
+                nsobj = obj
+                # Find globalns for the unwrapped object.
+                while hasattr(nsobj, "__wrapped__"):
+                    nsobj = nsobj.__wrapped__
+                globalns = getattr(nsobj, "__globals__", {})
+            if localns is None:
+                localns = globalns
+        elif localns is None:
+            localns = globalns
+        hints = getattr(obj, "__annotations__", None)
+        if hints is None:
+            # Return empty annotations for something that _could_ have them.
+            if isinstance(obj, typing._allowed_types):
+                return {}
+            else:
+                raise TypeError("{!r} is not a module, class, method, " "or function.".format(obj))
+        hints = dict(hints)
+        for name, value in hints.items():
+            if value is None:
+                value = type(None)
+            if isinstance(value, str):
+                if "|" in value:
+                    value = "Union[" + value.replace(" |", ",") + "]"
+                # class-level forward refs were handled above, this must be either
+                # a module-level annotation or a function argument annotation
+                value = typing.ForwardRef(
+                    value,
+                    is_argument=not isinstance(obj, types.ModuleType),
+                    is_class=False,
+                )
+            hints[name] = typing._eval_type(value, globalns, localns)
+        return hints if include_extras else {k: typing._strip_annotations(t) for k, t in hints.items()}
+
+else:
+    from typing import get_type_hints
+
+
+class ComicTaggerPaths(AppDirs):
+    def __init__(self, config_path: pathlib.Path | str | None = None) -> None:
+        super().__init__("ComicTagger", None, None, False, False)
+        self.path: pathlib.Path | None = None
+        if config_path:
+            self.path = pathlib.Path(config_path).absolute()
+
+    @property
+    def user_data_dir(self) -> pathlib.Path:
+        if self.path:
+            return self.path
+        return pathlib.Path(super().user_data_dir)
+
+    @property
+    def user_config_dir(self) -> pathlib.Path:
+        if self.path:
+            return self.path
+        return pathlib.Path(super().user_config_dir)
+
+    @property
+    def user_cache_dir(self) -> pathlib.Path:
+        if self.path:
+            return self.path / "cache"
+        return pathlib.Path(super().user_cache_dir)
+
+    @property
+    def user_state_dir(self) -> pathlib.Path:
+        if self.path:
+            return self.path
+        return pathlib.Path(super().user_state_dir)
+
+    @property
+    def user_log_dir(self) -> pathlib.Path:
+        if self.path:
+            return self.path / "log"
+        return pathlib.Path(super().user_log_dir)
+
+    @property
+    def user_plugin_dir(self) -> pathlib.Path:
+        if self.path:
+            return self.path / "plugins"
+        return pathlib.Path(super().user_config_dir) / "plugins"
+
+    @property
+    def site_data_dir(self) -> pathlib.Path:
+        return pathlib.Path(super().site_data_dir)
+
+    @property
+    def site_config_dir(self) -> pathlib.Path:
+        return pathlib.Path(super().site_config_dir)
+
+    def __str__(self) -> str:
+        return f"logs: {self.user_log_dir}, config: {self.user_config_dir}, cache: {self.user_cache_dir}"
+
+
+def tag(types: str) -> list[str]:
+    result = []
+    types = types.casefold()
+    for typ in utils.split(types, ","):
+        if typ not in tags:
+            choices = ", ".join(tags)
+            raise argparse.ArgumentTypeError(f"invalid choice: {typ} (choose from {choices.upper()})")
+        result.append(tags[typ].id)
+    return result
+
+
+def parse_metadata_from_string(mdstr: str) -> GenericMetadata:
+
+    def get_type(key: str, tt: Any = get_type_hints(GenericMetadata)) -> Any:
+        t: Any = tt.get(key, None)
+        if t is None:
+            return None
+        if getattr(t, "__origin__", None) is typing.Union and len(t.__args__) == 2 and t.__args__[1] is type(None):
+            t = t.__args__[0]
+        elif isinstance(t, types.GenericAlias) and issubclass(t.mro()[0], Collection):
+            t = t.mro()[0], t.__args__[0]
+
+        if isinstance(t, tuple) and issubclass(t[1], dict):
+            return (t[0], dict)
+        if isinstance(t, type) and issubclass(t, dict):
+            return dict
+        return t
+
+    def convert_value(t: type, value: Any) -> Any:
+        if isinstance(value, t):
+            return value
+        try:
+            if isinstance(value, (Mapping)):
+                value = t(**value)
+            elif not isinstance(value, str) and isinstance(value, (Collection)):
+                value = t(*value)
+            else:
+                if t is utils.Url and isinstance(value, str):
+                    value = utils.parse_url(value)
+                else:
+                    value = t(value)
+        except (ValueError, TypeError):
+            raise argparse.ArgumentTypeError(f"Invalid syntax for tag '{key}': {value}")
+        return value
+
+    md = GenericMetadata()
+
+    try:
+        if not mdstr:
+            return md
+        if mdstr[0] == "@":
+            p = pathlib.Path(mdstr[1:])
+            if not p.is_file():
+                raise argparse.ArgumentTypeError("Invalid filepath")
+            mdstr = p.read_text()
+        if mdstr[0] != "{":
+            mdstr = "{" + mdstr + "}"
+
+        md_dict = yaml.safe_load(mdstr)
+
+        empty = True
+        # Map the dict to the metadata object
+        for key, value in md_dict.items():
+            if hasattr(md, key):
+                t = get_type(key)
+                if value is None:
+                    value = REMOVE
+                elif isinstance(t, tuple):
+                    if value == "":
+                        value = t[0]()
+                    else:
+                        if isinstance(value, str):
+                            value = [value]
+                        if not isinstance(value, Collection):
+                            raise argparse.ArgumentTypeError(f"Invalid syntax for tag '{key}'")
+                        values = list(value)
+                        for idx, v in enumerate(values):
+                            if not isinstance(v, t[1]):
+                                values[idx] = convert_value(t[1], v)
+                        value = t[0](values)
+                else:
+                    value = convert_value(t, value)
+
+                empty = False
+                setattr(md, key, value)
+            else:
+                raise argparse.ArgumentTypeError(f"'{key}' is not a valid tag name")
+        md.is_empty = empty
+    except Exception as e:
+        logger.exception("Unable to read metadata from the commandline '%s'", mdstr)
+        raise Exception("Unable to read metadata from the commandline") from e
+    return md

comictaggerlib/defaults.py

@@ -0,0 +1,29 @@
+from __future__ import annotations
+
+from typing import NamedTuple
+
+
+class Replacement(NamedTuple):
+    find: str
+    replce: str
+    strict_only: bool
+
+
+class Replacements(NamedTuple):
+    literal_text: list[Replacement]
+    format_value: list[Replacement]
+
+
+DEFAULT_REPLACEMENTS = Replacements(
+    literal_text=[
+        Replacement(": ", " - ", True),
+        Replacement(":", "-", True),
+    ],
+    format_value=[
+        Replacement(": ", " - ", True),
+        Replacement(":", "-", True),
+        Replacement("/", "-", False),
+        Replacement("//", "--", False),
+        Replacement("\\", "-", True),
+    ],
+)

comictaggerlib/exportwindow.py

@@ -1,6 +1,7 @@
 """A PyQT4 dialog to confirm and set options for export to zip"""
+
 #
-# Copyright 2012-2014 Anthony Beville
+# Copyright 2012-2014 ComicTagger Authors
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -19,7 +20,6 @@ import logging
 
 from PyQt5 import QtCore, QtWidgets, uic
 
-from comictaggerlib.settings import ComicTaggerSettings
 from comictaggerlib.ui import ui_path
 
 logger = logging.getLogger(__name__)
@@ -32,18 +32,17 @@ class ExportConflictOpts:
 
 
 class ExportWindow(QtWidgets.QDialog):
-    def __init__(self, parent: QtWidgets.QWidget, settings: ComicTaggerSettings, msg: str) -> None:
+    def __init__(self, parent: QtWidgets.QWidget, msg: str) -> None:
         super().__init__(parent)
 
-        uic.loadUi(ui_path / "exportwindow.ui", self)
+        with (ui_path / "exportwindow.ui").open(encoding="utf-8") as uifile:
+            uic.loadUi(uifile, self)
         self.label.setText(msg)
 
         self.setWindowFlags(
             QtCore.Qt.WindowType(self.windowFlags() & ~QtCore.Qt.WindowType.WindowContextHelpButtonHint)
         )
 
-        self.settings = settings
-
         self.cbxDeleteOriginal.setChecked(False)
         self.cbxAddToList.setChecked(True)
         self.radioDontCreate.setChecked(True)

comictaggerlib/filerenamer.py

@@ -1,6 +1,7 @@
 """Functions for renaming files based on metadata"""
+
 #
-# Copyright 2012-2014 Anthony Beville
+# Copyright 2012-2014 ComicTagger Authors
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -16,58 +17,50 @@
 from __future__ import annotations
 
 import calendar
+import datetime
 import logging
 import os
 import pathlib
 import string
-from typing import Any, NamedTuple, cast
+from collections.abc import Collection, Iterable, Mapping, Sequence, Sized
+from typing import Any, cast
 
 from pathvalidate import Platform, normalize_platform, sanitize_filename
 
 from comicapi.comicarchive import ComicArchive
 from comicapi.genericmetadata import GenericMetadata
 from comicapi.issuestring import IssueString
+from comictaggerlib.defaults import DEFAULT_REPLACEMENTS, Replacement, Replacements
 
 logger = logging.getLogger(__name__)
 
 
-class Replacement(NamedTuple):
-    find: str
-    replce: str
-    strict_only: bool
-
-
-class Replacements(NamedTuple):
-    literal_text: list[Replacement]
-    format_value: list[Replacement]
-
-
-REPLACEMENTS = Replacements(
-    literal_text=[
-        Replacement(": ", " - ", True),
-        Replacement(":", "-", True),
-    ],
-    format_value=[
-        Replacement(": ", " - ", True),
-        Replacement(":", "-", True),
-        Replacement("/", "-", False),
-        Replacement("\\", "-", True),
-    ],
-)
-
-
 def get_rename_dir(ca: ComicArchive, rename_dir: str | pathlib.Path | None) -> pathlib.Path:
     folder = ca.path.parent.absolute()
     if rename_dir is not None:
         if isinstance(rename_dir, str):
-            rename_dir = rename_dir.strip()
-        folder = pathlib.Path(rename_dir).absolute()
+            rename_dir = pathlib.Path(rename_dir.strip())
+        folder = rename_dir.absolute()
     return folder
 
 
+def _isnamedtupleinstance(x: Any) -> bool:  # pragma: no cover
+    t = type(x)
+    b = t.__bases__
+
+    if len(b) != 1 or b[0] != tuple:
+        return False
+
+    f = getattr(t, "_fields", None)
+    if not isinstance(f, tuple):
+        return False
+
+    return all(isinstance(n, str) for n in f)
+
+
 class MetadataFormatter(string.Formatter):
     def __init__(
-        self, smart_cleanup: bool = False, platform: str = "auto", replacements: Replacements = REPLACEMENTS
+        self, smart_cleanup: bool = False, platform: str = "auto", replacements: Replacements = DEFAULT_REPLACEMENTS
     ) -> None:
         super().__init__()
         self.smart_cleanup = smart_cleanup
@@ -79,7 +72,36 @@ class MetadataFormatter(string.Formatter):
             return ""
         return cast(str, super().format_field(value, format_spec))
 
-    def convert_field(self, value: Any, conversion: str) -> str:
+    def convert_field(self, value: Any, conversion: str | None) -> str:
+        if value is None:
+            return ""
+        if isinstance(value, Iterable) and not isinstance(value, (str, tuple)):
+            if conversion == "C":
+                if isinstance(value, Sized):
+                    return str(len(value))
+                return ""
+            if conversion and conversion.isdecimal():
+                if not isinstance(value, Collection):
+                    return ""
+                i = int(conversion) - 1
+                if i < 0:
+                    i = 0
+                if i < len(value):
+                    try:
+                        return sorted(value)[i]
+                    except Exception:
+                        ...
+                    return list(value)[i]
+                return ""
+            if conversion == "j":
+                conversion = "s"
+            try:
+                return ", ".join(list(self.convert_field(v, conversion) for v in sorted(value) if v is not None))
+            except Exception:
+                ...
+            return ", ".join(list(self.convert_field(v, conversion) for v in value if v is not None))
+        if not conversion:
+            return cast(str, super().convert_field(value, conversion))
         if conversion == "u":
             return str(value).upper()
         if conversion == "l":
@@ -90,6 +112,8 @@ class MetadataFormatter(string.Formatter):
             return str(value).swapcase()
         if conversion == "t":
             return str(value).title()
+        if conversion.isdecimal():
+            return ""
         return cast(str, super().convert_field(value, conversion))
 
     def handle_replacements(self, string: str, replacements: list[Replacement]) -> str:
@@ -118,8 +142,8 @@ class MetadataFormatter(string.Formatter):
     def _vformat(
         self,
         format_string: str,
-        args: list[Any],
-        kwargs: dict[str, Any],
+        args: Sequence[Any],
+        kwargs: Mapping[str, Any],
         used_args: set[Any],
         recursion_depth: int,
         auto_arg_index: int = 0,
@@ -129,7 +153,6 @@ class MetadataFormatter(string.Formatter):
         result = []
         lstrip = False
         for literal_text, field_name, format_spec, conversion in self.parse(format_string):
-
             # output the literal text
             if literal_text:
                 if lstrip:
@@ -161,13 +184,17 @@ class MetadataFormatter(string.Formatter):
 
                 # given the field_name, find the object it references
                 #  and the argument it came from
-                obj, arg_used = self.get_field(field_name, args, kwargs)
-                used_args.add(arg_used)
+                try:
+                    obj, arg_used = self.get_field(field_name, args, kwargs)
+                    used_args.add(arg_used)
+                except Exception:
+                    obj = None
 
                 obj = self.none_replacement(obj, replacement, r)
-
                 # do any conversion on the resulting object
-                obj = self.convert_field(obj, conversion)  # type: ignore
+                obj = self.convert_field(obj, conversion)
+                if r == "-":
+                    obj = self.none_replacement(obj, replacement, r)
 
                 # expand the format spec, if needed
                 format_spec, _ = self._vformat(
@@ -200,16 +227,25 @@ class MetadataFormatter(string.Formatter):
 
 
 class FileRenamer:
-    def __init__(self, metadata: GenericMetadata | None, platform: str = "auto") -> None:
+    def __init__(
+        self,
+        metadata: GenericMetadata | None,
+        platform: str = "auto",
+        replacements: Replacements = DEFAULT_REPLACEMENTS,
+    ) -> None:
         self.template = "{publisher}/{series}/{series} v{volume} #{issue} (of {issue_count}) ({year})"
         self.smart_cleanup = True
         self.issue_zero_padding = 3
         self.metadata = metadata or GenericMetadata()
         self.move = False
         self.platform = platform
+        self.replacements = replacements
+        self.original_name = ""
+        self.move_only = False
 
-    def set_metadata(self, metadata: GenericMetadata) -> None:
+    def set_metadata(self, metadata: GenericMetadata, original_name: str) -> None:
         self.metadata = metadata
+        self.original_name = original_name
 
     def set_issue_zero_padding(self, count: int) -> None:
         self.issue_zero_padding = count
@@ -221,30 +257,58 @@ class FileRenamer:
         self.template = template
 
     def determine_name(self, ext: str) -> str:
-        class Default(dict):
+        class Default(dict[str, Any]):
             def __missing__(self, key: str) -> str:
                 return "{" + key + "}"
 
         md = self.metadata
 
-        # padding for issue
-        md.issue = IssueString(md.issue).as_string(pad=self.issue_zero_padding)
-
         template = self.template
 
         new_name = ""
 
-        fmt = MetadataFormatter(self.smart_cleanup, platform=self.platform)
+        fmt = MetadataFormatter(self.smart_cleanup, platform=self.platform, replacements=self.replacements)
         md_dict = vars(md)
-        for role in ["writer", "penciller", "inker", "colorist", "letterer", "cover artist", "editor"]:
+        md_dict.update(
+            dict(
+                month_name=None,
+                month_abbr=None,
+                date=None,
+                genre=None,
+                story_arc=None,
+                series_group=None,
+                web_link=None,
+                character=None,
+                team=None,
+                location=None,
+            )
+        )
+
+        md_dict["issue"] = IssueString(md.issue).as_string(pad=self.issue_zero_padding)
+        for role in ["writer", "penciller", "inker", "colorist", "letterer", "cover artist", "editor", "translator"]:
             md_dict[role] = md.get_primary_credit(role)
 
         if (isinstance(md.month, int) or isinstance(md.month, str) and md.month.isdigit()) and 0 < int(md.month) < 13:
             md_dict["month_name"] = calendar.month_name[int(md.month)]
             md_dict["month_abbr"] = calendar.month_abbr[int(md.month)]
-        else:
-            md_dict["month_name"] = ""
-            md_dict["month_abbr"] = ""
+
+        if md.year is not None and datetime.MINYEAR <= md.year <= datetime.MAXYEAR:
+            md_dict["date"] = datetime.datetime(year=md.year, month=md.month or 1, day=md.day or 1)
+
+        if md.genres:
+            md_dict["genre"] = sorted(md.genres)[0]
+        if md.story_arcs:
+            md_dict["story_arc"] = md.story_arcs[0]
+        if md.series_groups:
+            md_dict["series_group"] = md.series_groups[0]
+        if md.web_links:
+            md_dict["web_link"] = md.web_links[0]
+        if md.characters:
+            md_dict["character"] = sorted(md.characters)[0]
+        if md.teams:
+            md_dict["team"] = sorted(md.teams)[0]
+        if md.locations:
+            md_dict["location"] = sorted(md.locations)[0]
 
         new_basename = ""
         for component in pathlib.PureWindowsPath(template).parts:
@@ -253,11 +317,9 @@ class FileRenamer:
             ).strip()
             new_name = os.path.join(new_name, new_basename)
 
-        new_name += ext
-        new_basename += ext
-
-        # remove padding
-        md.issue = IssueString(md.issue).as_string()
+        if self.move_only:
+            new_folder = os.path.join(new_name, os.path.splitext(self.original_name)[0])
+            return new_folder + ext
         if self.move:
-            return new_name.strip()
-        return new_basename.strip()
+            return new_name.strip() + ext
+        return new_basename.strip() + ext

comictaggerlib/fileselectionlist.py

@@ -1,6 +1,7 @@
 """A PyQt5 widget for managing list of comic archive files"""
+
 #
-# Copyright 2012-2014 Anthony Beville
+# Copyright 2012-2014 ComicTagger Authors
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -24,53 +25,38 @@ from PyQt5 import QtCore, QtWidgets, uic
 
 from comicapi import utils
 from comicapi.comicarchive import ComicArchive
+from comictaggerlib.ctsettings import ct_ns
 from comictaggerlib.graphics import graphics_path
 from comictaggerlib.optionalmsgdialog import OptionalMessageDialog
-from comictaggerlib.settings import ComicTaggerSettings
 from comictaggerlib.settingswindow import linuxRarHelp, macRarHelp, windowsRarHelp
 from comictaggerlib.ui import ui_path
-from comictaggerlib.ui.qtutils import center_window_on_parent, reduce_widget_font_size
+from comictaggerlib.ui.qtutils import center_window_on_parent
 
 logger = logging.getLogger(__name__)
 
 
-class FileTableWidgetItem(QtWidgets.QTableWidgetItem):
-    def __lt__(self, other: object) -> bool:
-        return self.data(QtCore.Qt.ItemDataRole.UserRole) < other.data(QtCore.Qt.ItemDataRole.UserRole)  # type: ignore
-
-
-class FileInfo:
-    def __init__(self, ca: ComicArchive) -> None:
-        self.ca: ComicArchive = ca
-
-
 class FileSelectionList(QtWidgets.QWidget):
     selectionChanged = QtCore.pyqtSignal(QtCore.QVariant)
     listCleared = QtCore.pyqtSignal()
 
     fileColNum = 0
-    CRFlagColNum = 1
-    CBLFlagColNum = 2
-    typeColNum = 3
-    readonlyColNum = 4
-    folderColNum = 5
+    MDFlagColNum = 1
+    typeColNum = 2
+    readonlyColNum = 3
+    folderColNum = 4
     dataColNum = fileColNum
 
     def __init__(
-        self,
-        parent: QtWidgets.QWidget,
-        settings: ComicTaggerSettings,
-        dirty_flag_verification: Callable[[str, str], bool],
+        self, parent: QtWidgets.QWidget, config: ct_ns, dirty_flag_verification: Callable[[str, str], bool]
     ) -> None:
         super().__init__(parent)
 
-        uic.loadUi(ui_path / "fileselectionlist.ui", self)
+        with (ui_path / "fileselectionlist.ui").open(encoding="utf-8") as uifile:
+            uic.loadUi(uifile, self)
 
-        self.settings = settings
+        self.config = config
 
-        reduce_widget_font_size(self.twList)
-
-        self.twList.setColumnCount(6)
+        self.twList.horizontalHeader().setMinimumSectionSize(50)
         self.twList.currentItemChanged.connect(self.current_item_changed_cb)
 
         self.currentItem = None
@@ -83,7 +69,7 @@ class FileSelectionList(QtWidgets.QWidget):
         self.separator.setSeparator(True)
 
         select_all_action.setShortcut("Ctrl+A")
-        remove_action.setShortcut("Ctrl+X")
+        remove_action.setShortcut("Backspace" if platform.system() == "Darwin" else "Delete")
 
         select_all_action.triggered.connect(self.select_all)
         remove_action.triggered.connect(self.remove_selection)
@@ -110,10 +96,14 @@ class FileSelectionList(QtWidgets.QWidget):
         self.dirty_flag = modified
 
     def select_all(self) -> None:
-        self.twList.setRangeSelected(QtWidgets.QTableWidgetSelectionRange(0, 0, self.twList.rowCount() - 1, 5), True)
+        self.twList.setRangeSelected(
+            QtWidgets.QTableWidgetSelectionRange(0, 0, self.twList.rowCount() - 1, self.twList.columnCount() - 1), True
+        )
 
     def deselect_all(self) -> None:
-        self.twList.setRangeSelected(QtWidgets.QTableWidgetSelectionRange(0, 0, self.twList.rowCount() - 1, 5), False)
+        self.twList.setRangeSelected(
+            QtWidgets.QTableWidgetSelectionRange(0, 0, self.twList.rowCount() - 1, self.twList.columnCount() - 1), False
+        )
 
     def remove_archive_list(self, ca_list: list[ComicArchive]) -> None:
         self.twList.setSortingEnabled(False)
@@ -139,8 +129,8 @@ class FileSelectionList(QtWidgets.QWidget):
 
     def get_archive_by_row(self, row: int) -> ComicArchive | None:
         if row >= 0:
-            fi: FileInfo = self.twList.item(row, FileSelectionList.dataColNum).data(QtCore.Qt.ItemDataRole.UserRole)
-            return fi.ca
+            ca: ComicArchive = self.twList.item(row, FileSelectionList.dataColNum).data(QtCore.Qt.ItemDataRole.UserRole)
+            return ca
         return None
 
     def get_current_archive(self) -> ComicArchive | None:
@@ -183,38 +173,42 @@ class FileSelectionList(QtWidgets.QWidget):
             self.listCleared.emit()
 
     def add_path_list(self, pathlist: list[str]) -> None:
-
+        if not pathlist:
+            return
         filelist = utils.get_recursive_filelist(pathlist)
         # we now have a list of files to add
 
-        # Prog dialog on Linux flakes out for small range, so scale up
-        progdialog = QtWidgets.QProgressDialog("", "Cancel", 0, len(filelist), parent=self)
-        progdialog.setWindowTitle("Adding Files")
-        progdialog.setWindowModality(QtCore.Qt.WindowModality.ApplicationModal)
-        progdialog.setMinimumDuration(300)
-        center_window_on_parent(progdialog)
+        progdialog = None
+        if len(filelist) < 3:
+            # Prog dialog on Linux flakes out for small range, so scale up
+            progdialog = QtWidgets.QProgressDialog("", "Cancel", 0, len(filelist), parent=self)
+            progdialog.setWindowTitle("Adding Files")
+            progdialog.setWindowModality(QtCore.Qt.WindowModality.WindowModal)
+            progdialog.setMinimumDuration(300)
+            progdialog.show()
+            center_window_on_parent(progdialog)
 
         QtCore.QCoreApplication.processEvents()
         first_added = None
-        rar_added = False
+        rar_added_ro = False
         self.twList.setSortingEnabled(False)
         for idx, f in enumerate(filelist):
             QtCore.QCoreApplication.processEvents()
-            if progdialog.wasCanceled():
-                break
-            progdialog.setValue(idx + 1)
-            progdialog.setLabelText(f)
-            center_window_on_parent(progdialog)
+            if progdialog is not None:
+                if progdialog.wasCanceled():
+                    break
+                progdialog.setValue(idx + 1)
+                progdialog.setLabelText(f)
             QtCore.QCoreApplication.processEvents()
             row = self.add_path_item(f)
             if row is not None:
                 ca = self.get_archive_by_row(row)
-                if ca and ca.is_rar():
-                    rar_added = True
-                if first_added is None:
+                rar_added_ro = bool(ca and ca.archiver.name() == "RAR" and not ca.archiver.is_writable())
+                if first_added is None and row != -1:
                     first_added = row
 
-        progdialog.hide()
+        if progdialog is not None:
+            progdialog.hide()
         QtCore.QCoreApplication.processEvents()
 
         if first_added is not None:
@@ -227,15 +221,14 @@ class FileSelectionList(QtWidgets.QWidget):
             else:
                 QtWidgets.QMessageBox.information(self, "File/Folder Open", "No readable comic archives were found.")
 
-        if rar_added and not utils.which(self.settings.rar_exe_path or "rar"):
+        if rar_added_ro:
             self.rar_ro_message()
 
         self.twList.setSortingEnabled(True)
 
         # Adjust column size
         self.twList.resizeColumnsToContents()
-        self.twList.setColumnWidth(FileSelectionList.CRFlagColNum, 35)
-        self.twList.setColumnWidth(FileSelectionList.CBLFlagColNum, 35)
+        self.twList.setColumnWidth(FileSelectionList.MDFlagColNum, 35)
         self.twList.setColumnWidth(FileSelectionList.readonlyColNum, 35)
         self.twList.setColumnWidth(FileSelectionList.typeColNum, 45)
         if self.twList.columnWidth(FileSelectionList.fileColNum) > 250:
@@ -258,7 +251,7 @@ class FileSelectionList(QtWidgets.QWidget):
                 self,
                 "RAR Files are Read-Only",
                 "It looks like you have opened a RAR/CBR archive,\n"
-                "however ComicTagger cannot currently write to them without the rar program and are marked read only!\n\n"
+                "however ComicTagger cannot write to them without the rar program and are marked read only!\n\n"
                 f"{rar_help}",
             )
             self.rar_ro_shown = True
@@ -281,23 +274,20 @@ class FileSelectionList(QtWidgets.QWidget):
         if self.is_list_dupe(path):
             return self.get_current_list_row(path)
 
-        ca = ComicArchive(path, self.settings.rar_exe_path, str(graphics_path / "nocover.png"))
+        ca = ComicArchive(path, str(graphics_path / "nocover.png"))
 
         if ca.seems_to_be_a_comic_archive():
             row: int = self.twList.rowCount()
             self.twList.insertRow(row)
 
-            fi = FileInfo(ca)
-
             filename_item = QtWidgets.QTableWidgetItem()
             folder_item = QtWidgets.QTableWidgetItem()
-            cix_item = FileTableWidgetItem()
-            cbi_item = FileTableWidgetItem()
-            readonly_item = FileTableWidgetItem()
+            md_item = QtWidgets.QTableWidgetItem()
+            readonly_item = QtWidgets.QTableWidgetItem()
             type_item = QtWidgets.QTableWidgetItem()
 
             filename_item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
-            filename_item.setData(QtCore.Qt.ItemDataRole.UserRole, fi)
+            filename_item.setData(QtCore.Qt.ItemDataRole.UserRole, ca)
             self.twList.setItem(row, FileSelectionList.fileColNum, filename_item)
 
             folder_item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
@@ -306,13 +296,9 @@ class FileSelectionList(QtWidgets.QWidget):
             type_item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
             self.twList.setItem(row, FileSelectionList.typeColNum, type_item)
 
-            cix_item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
-            cix_item.setTextAlignment(QtCore.Qt.AlignmentFlag.AlignHCenter)
-            self.twList.setItem(row, FileSelectionList.CRFlagColNum, cix_item)
-
-            cbi_item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
-            cbi_item.setTextAlignment(QtCore.Qt.AlignmentFlag.AlignHCenter)
-            self.twList.setItem(row, FileSelectionList.CBLFlagColNum, cbi_item)
+            md_item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
+            md_item.setTextAlignment(QtCore.Qt.AlignmentFlag.AlignHCenter)
+            self.twList.setItem(row, FileSelectionList.MDFlagColNum, md_item)
 
             readonly_item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
             readonly_item.setTextAlignment(QtCore.Qt.AlignmentFlag.AlignHCenter)
@@ -325,69 +311,45 @@ class FileSelectionList(QtWidgets.QWidget):
 
     def update_row(self, row: int) -> None:
         if row >= 0:
-            fi: FileInfo = self.twList.item(row, FileSelectionList.dataColNum).data(QtCore.Qt.ItemDataRole.UserRole)
+            ca: ComicArchive = self.twList.item(row, FileSelectionList.dataColNum).data(QtCore.Qt.ItemDataRole.UserRole)
 
             filename_item = self.twList.item(row, FileSelectionList.fileColNum)
             folder_item = self.twList.item(row, FileSelectionList.folderColNum)
-            cix_item = self.twList.item(row, FileSelectionList.CRFlagColNum)
-            cbi_item = self.twList.item(row, FileSelectionList.CBLFlagColNum)
+            md_item = self.twList.item(row, FileSelectionList.MDFlagColNum)
             type_item = self.twList.item(row, FileSelectionList.typeColNum)
             readonly_item = self.twList.item(row, FileSelectionList.readonlyColNum)
 
-            item_text = os.path.split(fi.ca.path)[0]
+            item_text = os.path.split(ca.path)[0]
             folder_item.setText(item_text)
             folder_item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, item_text)
 
-            item_text = os.path.split(fi.ca.path)[1]
+            item_text = os.path.split(ca.path)[1]
             filename_item.setText(item_text)
             filename_item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, item_text)
 
-            if fi.ca.is_sevenzip():
-                item_text = "7Z"
-            elif fi.ca.is_zip():
-                item_text = "ZIP"
-            elif fi.ca.is_rar():
-                item_text = "RAR"
-            else:
-                item_text = ""
+            item_text = ca.archiver.name()
             type_item.setText(item_text)
             type_item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, item_text)
 
-            if fi.ca.has_cix():
-                cix_item.setCheckState(QtCore.Qt.CheckState.Checked)
-                cix_item.setData(QtCore.Qt.ItemDataRole.UserRole, True)
-            else:
-                cix_item.setData(QtCore.Qt.ItemDataRole.UserRole, False)
-                cix_item.setCheckState(QtCore.Qt.CheckState.Unchecked)
+            md_item.setText(", ".join(x for x in ca.get_supported_tags() if ca.has_tags(x)))
 
-            if fi.ca.has_cbi():
-                cbi_item.setCheckState(QtCore.Qt.CheckState.Checked)
-                cbi_item.setData(QtCore.Qt.ItemDataRole.UserRole, True)
-            else:
-                cbi_item.setData(QtCore.Qt.ItemDataRole.UserRole, False)
-                cbi_item.setCheckState(QtCore.Qt.CheckState.Unchecked)
-
-            if not fi.ca.is_writable():
+            if not ca.is_writable():
                 readonly_item.setCheckState(QtCore.Qt.CheckState.Checked)
                 readonly_item.setData(QtCore.Qt.ItemDataRole.UserRole, True)
+                readonly_item.setText(" ")
             else:
                 readonly_item.setData(QtCore.Qt.ItemDataRole.UserRole, False)
                 readonly_item.setCheckState(QtCore.Qt.CheckState.Unchecked)
-
-            # Reading these will force them into the ComicArchive's cache
-            try:
-                fi.ca.read_cix()
-            except Exception:
-                pass
-            fi.ca.has_cbi()
+                # This is a nbsp it sorts after a space ' '
+                readonly_item.setText("\xa0")
 
     def get_selected_archive_list(self) -> list[ComicArchive]:
         ca_list: list[ComicArchive] = []
         for r in range(self.twList.rowCount()):
             item = self.twList.item(r, FileSelectionList.dataColNum)
             if item.isSelected():
-                fi: FileInfo = item.data(QtCore.Qt.ItemDataRole.UserRole)
-                ca_list.append(fi.ca)
+                ca: ComicArchive = item.data(QtCore.Qt.ItemDataRole.UserRole)
+                ca_list.append(ca)
 
         return ca_list
 

comictaggerlib/graphics/__init__.py

@@ -1,5 +1,5 @@
 from __future__ import annotations
 
-import pathlib
+import importlib.resources
 
-graphics_path = pathlib.Path(__file__).parent
+graphics_path = importlib.resources.files(__package__)

comictaggerlib/graphics/eye.svg

@@ -0,0 +1,102 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Generator: Adobe Illustrator 19.0.0, SVG Export Plug-In . SVG Version: 6.00 Build 0)  -->
+
+<svg
+   version="1.1"
+   id="Capa_1"
+   x="0px"
+   y="0px"
+   viewBox="0 0 469.333 469.333"
+   style="enable-background:new 0 0 469.333 469.333;"
+   xml:space="preserve"
+   sodipodi:docname="eye.svg"
+   inkscape:version="1.2.2 (b0a8486541, 2022-12-01)"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:svg="http://www.w3.org/2000/svg"><defs
+   id="defs45" /><sodipodi:namedview
+   id="namedview43"
+   pagecolor="#505050"
+   bordercolor="#eeeeee"
+   borderopacity="1"
+   inkscape:showpageshadow="0"
+   inkscape:pageopacity="0"
+   inkscape:pagecheckerboard="0"
+   inkscape:deskcolor="#505050"
+   showgrid="false"
+   inkscape:zoom="2.1882117"
+   inkscape:cx="234.6665"
+   inkscape:cy="234.6665"
+   inkscape:window-width="2560"
+   inkscape:window-height="1361"
+   inkscape:window-x="0"
+   inkscape:window-y="42"
+   inkscape:window-maximized="1"
+   inkscape:current-layer="Capa_1" />
+<g
+   id="g10"
+   style="fill:#333333">
+	<g
+   id="g8"
+   style="fill:#333333">
+		<g
+   id="g6"
+   style="fill:#333333">
+			<path
+   d="M234.667,170.667c-35.307,0-64,28.693-64,64s28.693,64,64,64s64-28.693,64-64S269.973,170.667,234.667,170.667z"
+   id="path2"
+   style="fill:#333333" />
+			<path
+   d="M234.667,74.667C128,74.667,36.907,141.013,0,234.667c36.907,93.653,128,160,234.667,160     c106.773,0,197.76-66.347,234.667-160C432.427,141.013,341.44,74.667,234.667,74.667z M234.667,341.333     c-58.88,0-106.667-47.787-106.667-106.667S175.787,128,234.667,128s106.667,47.787,106.667,106.667     S293.547,341.333,234.667,341.333z"
+   id="path4"
+   style="fill:#333333" />
+		</g>
+	</g>
+</g>
+<g
+   id="g12">
+</g>
+<g
+   id="g14">
+</g>
+<g
+   id="g16">
+</g>
+<g
+   id="g18">
+</g>
+<g
+   id="g20">
+</g>
+<g
+   id="g22">
+</g>
+<g
+   id="g24">
+</g>
+<g
+   id="g26">
+</g>
+<g
+   id="g28">
+</g>
+<g
+   id="g30">
+</g>
+<g
+   id="g32">
+</g>
+<g
+   id="g34">
+</g>
+<g
+   id="g36">
+</g>
+<g
+   id="g38">
+</g>
+<g
+   id="g40">
+</g>
+</svg>

comictaggerlib/graphics/graphics.qrc

@@ -0,0 +1,24 @@
+<RCC>
+  <qresource prefix="graphics">
+    <file>about.png</file>
+    <file>app.png</file>
+    <file>auto.png</file>
+    <file>autotag.png</file>
+    <file>browse.png</file>
+    <file>clear.png</file>
+    <file>down.png</file>
+    <file>eye.svg</file>
+    <file>hidden.svg</file>
+    <file>left.png</file>
+    <file>longbox.png</file>
+    <file>nocover.png</file>
+    <file>open.png</file>
+    <file>parse.png</file>
+    <file>popup_bg.png</file>
+    <file>right.png</file>
+    <file>save.png</file>
+    <file>search.png</file>
+    <file>tags.png</file>
+    <file>up.png</file>
+  </qresource>
+</RCC>

comictaggerlib/graphics/hidden.svg

@@ -0,0 +1,106 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Generator: Adobe Illustrator 19.0.0, SVG Export Plug-In . SVG Version: 6.00 Build 0)  -->
+
+<svg
+   version="1.1"
+   id="Capa_1"
+   x="0px"
+   y="0px"
+   viewBox="0 0 469.44 469.44"
+   style="enable-background:new 0 0 469.44 469.44;"
+   xml:space="preserve"
+   sodipodi:docname="hidden.svg"
+   inkscape:version="1.2.2 (b0a8486541, 2022-12-01)"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:svg="http://www.w3.org/2000/svg"><defs
+   id="defs47" /><sodipodi:namedview
+   id="namedview45"
+   pagecolor="#505050"
+   bordercolor="#eeeeee"
+   borderopacity="1"
+   inkscape:showpageshadow="0"
+   inkscape:pageopacity="0"
+   inkscape:pagecheckerboard="0"
+   inkscape:deskcolor="#505050"
+   showgrid="false"
+   inkscape:zoom="2.187713"
+   inkscape:cx="234.72"
+   inkscape:cy="234.72"
+   inkscape:window-width="2560"
+   inkscape:window-height="1361"
+   inkscape:window-x="0"
+   inkscape:window-y="42"
+   inkscape:window-maximized="1"
+   inkscape:current-layer="Capa_1" />
+<g
+   id="g12"
+   style="fill:#333333">
+	<g
+   id="g10"
+   style="fill:#333333">
+		<g
+   id="g8"
+   style="fill:#333333">
+			<path
+   d="M231.147,160.373l67.2,67.2l0.32-3.52c0-35.307-28.693-64-64-64L231.147,160.373z"
+   id="path2"
+   style="fill:#333333" />
+			<path
+   d="M234.667,117.387c58.88,0,106.667,47.787,106.667,106.667c0,13.76-2.773,26.88-7.573,38.933l62.4,62.4     c32.213-26.88,57.6-61.653,73.28-101.333c-37.013-93.653-128-160-234.773-160c-29.867,0-58.453,5.333-85.013,14.933l46.08,45.973     C207.787,120.267,220.907,117.387,234.667,117.387z"
+   id="path4"
+   style="fill:#333333" />
+			<path
+   d="M21.333,59.253l48.64,48.64l9.707,9.707C44.48,145.12,16.64,181.707,0,224.053c36.907,93.653,128,160,234.667,160     c33.067,0,64.64-6.4,93.547-18.027l9.067,9.067l62.187,62.293l27.2-27.093L48.533,32.053L21.333,59.253z M139.307,177.12     l32.96,32.96c-0.96,4.587-1.6,9.173-1.6,13.973c0,35.307,28.693,64,64,64c4.8,0,9.387-0.64,13.867-1.6l32.96,32.96     c-14.187,7.04-29.973,11.307-46.827,11.307C175.787,330.72,128,282.933,128,224.053C128,207.2,132.267,191.413,139.307,177.12z"
+   id="path6"
+   style="fill:#333333" />
+		</g>
+	</g>
+</g>
+<g
+   id="g14">
+</g>
+<g
+   id="g16">
+</g>
+<g
+   id="g18">
+</g>
+<g
+   id="g20">
+</g>
+<g
+   id="g22">
+</g>
+<g
+   id="g24">
+</g>
+<g
+   id="g26">
+</g>
+<g
+   id="g28">
+</g>
+<g
+   id="g30">
+</g>
+<g
+   id="g32">
+</g>
+<g
+   id="g34">
+</g>
+<g
+   id="g36">
+</g>
+<g
+   id="g38">
+</g>
+<g
+   id="g40">
+</g>
+<g
+   id="g42">
+</g>
+</svg>

comictaggerlib/gui.py

@@ -0,0 +1,154 @@
+from __future__ import annotations
+
+import logging.handlers
+import os
+import platform
+import sys
+import traceback
+import types
+
+import settngs
+
+from comictaggerlib.ctsettings import ct_ns
+from comictaggerlib.graphics import graphics_path
+from comictalker.comictalker import ComicTalker
+
+logger = logging.getLogger("comictagger")
+try:
+    qt_available = True
+    from PyQt5 import QtCore, QtGui, QtWidgets
+
+    def show_exception_box(log_msg: str) -> None:
+        """Checks if a QApplication instance is available and shows a messagebox with the exception message.
+        If unavailable (non-console application), log an additional notice.
+        """
+        if QtWidgets.QApplication.instance() is not None:
+            errorbox = QtWidgets.QMessageBox()
+            errorbox.setStandardButtons(
+                QtWidgets.QMessageBox.StandardButton.Abort | QtWidgets.QMessageBox.StandardButton.Ignore
+            )
+            errorbox.setText(log_msg)
+            if errorbox.exec() == QtWidgets.QMessageBox.StandardButton.Abort:
+                QtWidgets.QApplication.exit(1)
+            else:
+                logger.warning("Exception ignored")
+        else:
+            logger.debug("No QApplication instance available.")
+
+    class UncaughtHook(QtCore.QObject):
+        _exception_caught = QtCore.pyqtSignal(object)
+
+        def __init__(self) -> None:
+            super().__init__()
+
+            # this registers the exception_hook() function as hook with the Python interpreter
+            sys.excepthook = self.exception_hook
+
+            # connect signal to execute the message box function always on main thread
+            self._exception_caught.connect(show_exception_box)
+
+        def exception_hook(
+            self, exc_type: type[BaseException], exc_value: BaseException, exc_traceback: types.TracebackType | None
+        ) -> None:
+            """Function handling uncaught exceptions.
+            It is triggered each time an uncaught exception occurs.
+            """
+            if issubclass(exc_type, KeyboardInterrupt):
+                # ignore keyboard interrupt to support console applications
+                sys.__excepthook__(exc_type, exc_value, exc_traceback)
+            else:
+                exc_info = (exc_type, exc_value, exc_traceback)
+                trace_back = "".join(traceback.format_tb(exc_traceback))
+                log_msg = f"{exc_type.__name__}: {exc_value}\n\n{trace_back}"
+                logger.critical("Uncaught exception: %s: %s", exc_type.__name__, exc_value, exc_info=exc_info)
+
+                # trigger message box show
+                self._exception_caught.emit(f"Oops. An unexpected error occurred:\n{log_msg}")
+
+    qt_exception_hook = UncaughtHook()
+    from comictaggerlib.taggerwindow import TaggerWindow
+
+    try:
+        # needed here to initialize QWebEngine
+        from PyQt5.QtWebEngineWidgets import QWebEngineView  # noqa: F401
+
+        qt_webengine_available = True
+    except ImportError:
+        qt_webengine_available = False
+
+    class Application(QtWidgets.QApplication):
+        openFileRequest = QtCore.pyqtSignal(QtCore.QUrl, name="openfileRequest")
+
+        # Handles "Open With" from Finder on macOS
+        def event(self, event: QtCore.QEvent) -> bool:
+            if event.type() == QtCore.QEvent.FileOpen:
+                logger.info(event.url().toLocalFile())
+                self.openFileRequest.emit(event.url())
+                return True
+            return super().event(event)
+
+except ImportError as e:
+
+    def show_exception_box(log_msg: str) -> None: ...
+
+    logger.exception("Qt unavailable")
+    qt_available = False
+    import_error = e
+
+
+def open_tagger_window(
+    talkers: dict[str, ComicTalker], config: settngs.Config[ct_ns], error: tuple[str, bool] | None
+) -> None:
+    os.environ["QtWidgets.QT_AUTO_SCREEN_SCALE_FACTOR"] = "1"
+    args = [sys.argv[0]]
+    if config[0].Runtime_Options__darkmode:
+        args.extend(["-platform", "windows:darkmode=2"])
+    app = Application(args)
+    if error is not None:
+        show_exception_box(error[0])
+        if error[1]:
+            raise SystemExit(1)
+
+    # needed to catch initial open file events (macOS)
+    app.openFileRequest.connect(lambda x: config[0].Runtime_Options__files.append(x.toLocalFile()))
+    # The window Icon needs to be set here. It's also set in taggerwindow.ui but it doesn't seem to matter
+    app.setWindowIcon(QtGui.QIcon(":/graphics/app.png"))
+
+    if platform.system() == "Windows":
+        # For pure python, tell windows that we're not python,
+        # so we can have our own taskbar icon
+        import ctypes
+
+        myappid = "comictagger"  # arbitrary string
+        ctypes.windll.shell32.SetCurrentProcessExplicitAppUserModelID(myappid)  # type: ignore[attr-defined]
+        # force close of console window
+        swp_hidewindow = 0x0080
+        console_wnd = ctypes.windll.kernel32.GetConsoleWindow()  # type: ignore[attr-defined]
+        if console_wnd != 0:
+            ctypes.windll.user32.SetWindowPos(console_wnd, None, 0, 0, 0, 0, swp_hidewindow)  # type: ignore[attr-defined]
+
+    if platform.system() != "Linux":
+        img = QtGui.QPixmap()
+        img.loadFromData((graphics_path / "tags.png").read_bytes())
+
+        splash = QtWidgets.QSplashScreen(img)
+        splash.show()
+        splash.raise_()
+        QtWidgets.QApplication.processEvents()
+
+    try:
+        tagger_window = TaggerWindow(config[0].Runtime_Options__files, config, talkers)
+        tagger_window.show()
+
+        # Catch open file events (macOS)
+        app.openFileRequest.connect(tagger_window.open_file_event)
+
+        if platform.system() != "Linux":
+            splash.finish(tagger_window)
+
+        sys.exit(app.exec())
+    except Exception:
+        logger.exception("GUI mode failed")
+        QtWidgets.QMessageBox.critical(
+            QtWidgets.QMainWindow(), "Error", "Unhandled exception in app:\n" + traceback.format_exc()
+        )

comictaggerlib/imagefetcher.py

@@ -1,6 +1,7 @@
 """A class to manage fetching and caching of images by URL"""
+
 #
-# Copyright 2012-2014 Anthony Beville
+# Copyright 2012-2014 ComicTagger Authors
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -18,56 +19,60 @@ from __future__ import annotations
 import datetime
 import logging
 import os
+import pathlib
 import shutil
 import sqlite3 as lite
 import tempfile
-
-import requests
-
-from comictaggerlib import ctversion
-from comictaggerlib.settings import ComicTaggerSettings
+from typing import TYPE_CHECKING
 
 try:
-    from PyQt5 import QtCore, QtNetwork
-
-    qt_available = True
+    import niquests as requests
 except ImportError:
-    qt_available = False
+    import requests
+
+from comictaggerlib import ctversion
+
+if TYPE_CHECKING:
+    from PyQt5 import QtCore, QtNetwork
 
 logger = logging.getLogger(__name__)
 
 
-class ImageFetcherException(Exception):
-    ...
+class ImageFetcherException(Exception): ...
 
 
-def fetch_complete(image_data: bytes | QtCore.QByteArray) -> None:
-    ...
+def fetch_complete(url: str, image_data: bytes | QtCore.QByteArray) -> None: ...
 
 
 class ImageFetcher:
-
     image_fetch_complete = fetch_complete
+    qt_available = True
 
-    def __init__(self) -> None:
-
-        self.settings_folder = ComicTaggerSettings.get_settings_folder()
-        self.db_file = os.path.join(self.settings_folder, "image_url_cache.db")
-        self.cache_folder = os.path.join(self.settings_folder, "image_cache")
+    def __init__(self, cache_folder: pathlib.Path) -> None:
+        self.db_file = cache_folder / "image_url_cache.db"
+        self.cache_folder = cache_folder / "image_cache"
 
         self.user_data = None
         self.fetched_url = ""
 
+        if self.qt_available:
+            try:
+                from PyQt5 import QtNetwork
+
+                self.qt_available = True
+            except ImportError:
+                self.qt_available = False
         if not os.path.exists(self.db_file):
             self.create_image_db()
 
-        if qt_available:
+        if self.qt_available:
             self.nam = QtNetwork.QNetworkAccessManager()
 
     def clear_cache(self) -> None:
         os.unlink(self.db_file)
         if os.path.isdir(self.cache_folder):
             shutil.rmtree(self.cache_folder)
+        self.cache_folder.mkdir(parents=True, exist_ok=True)
 
     def fetch(self, url: str, blocking: bool = False) -> bytes:
         """
@@ -81,22 +86,24 @@ class ImageFetcher:
 
         # first look in the DB
         image_data = self.get_image_from_cache(url)
-        if blocking or not qt_available:
+        # Async for retrieving covers seems to work well
+        if blocking or not self.qt_available:
             if not image_data:
                 try:
                     image_data = requests.get(url, headers={"user-agent": "comictagger/" + ctversion.version}).content
+                    # save the image to the cache
+                    self.add_image_to_cache(self.fetched_url, image_data)
                 except Exception as e:
                     logger.exception("Fetching url failed: %s")
                     raise ImageFetcherException("Network Error!") from e
-
-            # save the image to the cache
-            self.add_image_to_cache(self.fetched_url, image_data)
             return image_data
 
-        if qt_available:
+        if self.qt_available:
+            from PyQt5 import QtCore, QtNetwork
+
             # if we found it, just emit the signal asap
             if image_data:
-                ImageFetcher.image_fetch_complete(QtCore.QByteArray(image_data))
+                ImageFetcher.image_fetch_complete(url, QtCore.QByteArray(image_data))
                 return b""
 
             # didn't find it.  look online
@@ -112,12 +119,11 @@ class ImageFetcher:
         image_data = reply.readAll()
 
         # save the image to the cache
-        self.add_image_to_cache(self.fetched_url, image_data)
+        self.add_image_to_cache(reply.request().url().toString(), image_data)
 
-        ImageFetcher.image_fetch_complete(image_data)
+        ImageFetcher.image_fetch_complete(reply.request().url().toString(), image_data)
 
     def create_image_db(self) -> None:
-
         # this will wipe out any existing version
         open(self.db_file, "wb").close()
 
@@ -126,19 +132,14 @@ class ImageFetcher:
             shutil.rmtree(self.cache_folder)
         os.makedirs(self.cache_folder)
 
-        con = lite.connect(self.db_file)
-
         # create tables
-        with con:
+        with lite.connect(self.db_file) as con:
             cur = con.cursor()
 
             cur.execute("CREATE TABLE Images(url TEXT,filename TEXT,timestamp TEXT,PRIMARY KEY (url))")
 
     def add_image_to_cache(self, url: str, image_data: bytes | QtCore.QByteArray) -> None:
-
-        con = lite.connect(self.db_file)
-
-        with con:
+        with lite.connect(self.db_file) as con:
             cur = con.cursor()
 
             timestamp = datetime.datetime.now()
@@ -150,9 +151,7 @@ class ImageFetcher:
             cur.execute("INSERT or REPLACE INTO Images VALUES(?, ?, ?)", (url, filename, timestamp))
 
     def get_image_from_cache(self, url: str) -> bytes:
-
-        con = lite.connect(self.db_file)
-        with con:
+        with lite.connect(self.db_file) as con:
             cur = con.cursor()
 
             cur.execute("SELECT filename FROM Images WHERE url=?", [url])

comictaggerlib/imagehasher.py

@@ -1,6 +1,7 @@
 """A class to manage creating image content hashes, and calculate hamming distances"""
+
 #
-# Copyright 2013 Anthony Beville
+# Copyright 2013 ComicTagger Authors
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -16,8 +17,11 @@
 from __future__ import annotations
 
 import io
+import itertools
 import logging
-from functools import reduce
+import math
+from collections.abc import Sequence
+from statistics import median
 from typing import TypeVar
 
 try:
@@ -30,13 +34,19 @@ logger = logging.getLogger(__name__)
 
 
 class ImageHasher:
-    def __init__(self, path: str | None = None, data: bytes = b"", width: int = 8, height: int = 8) -> None:
+    def __init__(
+        self, path: str | None = None, image: Image | None = None, data: bytes = b"", width: int = 8, height: int = 8
+    ) -> None:
         self.width = width
         self.height = height
 
-        if path is None and not data:
+        if path is None and not data and not image:
             raise OSError
 
+        if image is not None:
+            self.image = image
+            return
+
         try:
             if path is not None:
                 self.image = Image.open(path)
@@ -57,115 +67,104 @@ class ImageHasher:
         pixels = list(image.getdata())
         avg = sum(pixels) / len(pixels)
 
-        def compare_value_to_avg(i: int) -> int:
-            return 1 if i > avg else 0
+        diff = "".join(str(int(p > avg)) for p in pixels)
 
-        bitlist = list(map(compare_value_to_avg, pixels))
-
-        # build up an int value from the bit list, one bit at a time
-        def set_bit(x: int, idx_val: tuple[int, int]) -> int:
-            (idx, val) = idx_val
-            return x | (val << idx)
-
-        result = reduce(set_bit, enumerate(bitlist), 0)
+        result = int(diff, 2)
 
         return result
 
-    def average_hash2(self) -> None:
-        """
-        # Got this one from somewhere on the net.  Not a clue how the 'convolve2d' works!
+    def difference_hash(self) -> int:
+        try:
+            image = self.image.resize((self.width + 1, self.height), Image.Resampling.LANCZOS).convert("L")
+        except Exception:
+            logger.exception("difference_hash error")
+            return 0
 
-        from numpy import array
-        from scipy.signal import convolve2d
-
-        im = self.image.resize((self.width, self.height), Image.ANTIALIAS).convert('L')
-
-        in_data = array((im.getdata())).reshape(self.width, self.height)
-        filt = array([[0,1,0],[1,-4,1],[0,1,0]])
-        filt_data = convolve2d(in_data,filt,mode='same',boundary='symm').flatten()
-
-        result = reduce(lambda x, (y, z): x | (z << y),
-                         enumerate(map(lambda i: 0 if i < 0 else 1, filt_data)),
-                         0)
-        return result
-        """
-
-    def dct_average_hash(self) -> None:
-        """
-        # Algorithm source: http://syntaxcandy.blogspot.com/2012/08/perceptual-hash.html
-
-        1. Reduce size. Like Average Hash, pHash starts with a small image.
-        However, the image is larger than 8x8; 32x32 is a     good size. This
-        is really done to simplify the DCT computation and not because it
-        is needed to reduce the high frequencies.
-
-        2. Reduce color. The image is reduced to a grayscale just to further
-        simplify the number of computations.
-
-        3. Compute the DCT. The DCT separates the image into a collection of
-        frequencies and scalars. While JPEG uses     an 8x8 DCT, this algorithm
-        uses a 32x32 DCT.
-
-        4. Reduce the DCT. This is the magic step. While the DCT is 32x32,
-        just keep the top-left 8x8. Those represent the lowest frequencies in
-        the picture.
-
-        5. Compute the average value. Like the Average Hash, compute the mean DCT
-        value (using only the 8x8 DCT low-frequency values and excluding the first
-        term since the DC coefficient can be significantly different     from the other
-        values and will throw off the average). Thanks to David Starkweather for the
-        added information about pHash. He wrote: "the dct hash is based on the low 2D
-        DCT coefficients starting at the second from lowest, leaving out the first DC
-        term. This excludes completely flat image information (i.e. solid colors) from
-        being included in the hash description."
-
-        6. Further reduce the DCT. This is the magic step. Set the 64 hash bits to 0 or
-        1 depending on whether     each of the 64 DCT values is above or below the average
-        value. The result doesn't tell us the actual low frequencies; it just tells us
-        the very-rough relative scale of the frequencies to the mean. The result will not
-        vary as long as the overall structure of the image remains the same; this can
-        survive gamma and color histogram adjustments without a problem.
-
-        7. Construct the hash. Set the 64 bits into a 64-bit integer. The order does not
-        matter, just as long as you are consistent.
-
-
-        import numpy
-        import scipy.fftpack
-        numpy.set_printoptions(threshold=10000, linewidth=200, precision=2, suppress=True)
-
-        # Step 1,2
-        im = self.image.resize((32, 32), Image.ANTIALIAS).convert("L")
-        in_data = numpy.asarray(im)
-
-        # Step 3
-        dct = scipy.fftpack.dct(in_data.astype(float))
-
-        # Step 4
-        # Just skip the top and left rows when slicing, as suggested somewhere else...
-        lofreq_dct = dct[1:9, 1:9].flatten()
-
-        # Step 5
-        avg = (lofreq_dct.sum()) / (lofreq_dct.size)
-        median = numpy.median(lofreq_dct)
-
-        thresh = avg
-
-        # Step 6
-        def compare_value_to_thresh(i):
-            return (1 if i > thresh else 0)
-
-        bitlist = map(compare_value_to_thresh, lofreq_dct)
-
-        #Step 7
-        def set_bit(x, (idx, val)):
-            return (x | (val << idx))
-
-        result = reduce(set_bit, enumerate(bitlist), long(0))
+        pixels = list(image.getdata())
+        diff = ""
+        for y in range(self.height):
+            for x in range(self.width):
+                idx = x + (self.width + 1 * y)
+                diff += str(int(pixels[idx] < pixels[idx + 1]))
 
+        result = int(diff, 2)
 
         return result
+
+    def p_hash(self) -> int:
         """
+        Pure python version of Perceptual Hash computation of https://github.com/JohannesBuchner/imagehash/tree/master
+        Implementation follows http://www.hackerfactor.com/blog/index.php?/archives/432-Looks-Like-It.html
+        """
+
+        def generate_dct2(block: Sequence[Sequence[float]], axis: int = 0) -> list[list[float]]:
+            def dct1(block: Sequence[float]) -> list[float]:
+                """Perform 1D Discrete Cosine Transform (DCT) on a given block."""
+                N = len(block)
+                dct_block = [0.0] * N
+
+                for k in range(N):
+                    sum_val = 0.0
+                    for n in range(N):
+                        cos_val = math.cos(math.pi * k * (2 * n + 1) / (2 * N))
+                        sum_val += block[n] * cos_val
+                    dct_block[k] = sum_val
+
+                return dct_block
+
+            """Perform 2D Discrete Cosine Transform (DCT) on a given block along the specified axis."""
+            rows = len(block)
+            cols = len(block[0])
+            dct_block = [[0.0] * cols for _ in range(rows)]
+
+            if axis == 0:
+                # Apply 1D DCT on each row
+                for i in range(rows):
+                    dct_block[i] = dct1(block[i])
+            elif axis == 1:
+                # Apply 1D DCT on each column
+                for j in range(cols):
+                    column = [block[i][j] for i in range(rows)]
+                    dct_column = dct1(column)
+                    for i in range(rows):
+                        dct_block[i][j] = dct_column[i]
+            else:
+                raise ValueError("Invalid axis value. Must be either 0 or 1.")
+
+            return dct_block
+
+        def convert_image_to_ndarray(image: Image.Image) -> Sequence[Sequence[float]]:
+            width, height = image.size
+
+            pixels2 = []
+            for y in range(height):
+                row = []
+                for x in range(width):
+                    pixel = image.getpixel((x, y))
+                    row.append(pixel)
+                pixels2.append(row)
+
+            return pixels2
+
+        highfreq_factor = 4
+        img_size = 8 * highfreq_factor
+
+        try:
+            image = self.image.convert("L").resize((img_size, img_size), Image.Resampling.LANCZOS)
+        except Exception:
+            logger.exception("p_hash error converting to greyscale and resizing")
+            return 0
+
+        pixels = convert_image_to_ndarray(image)
+        dct = generate_dct2(generate_dct2(pixels, axis=0), axis=1)
+        dctlowfreq = list(itertools.chain.from_iterable(row[:8] for row in dct[:8]))
+        med = median(dctlowfreq)
+        # Convert to a bit string
+        diff = "".join(str(int(item > med)) for item in dctlowfreq)
+
+        result = int(diff, 2)
+
+        return result
 
     # accepts 2 hashes (longs or hex strings) and returns the hamming distance
 
@@ -173,12 +172,14 @@ class ImageHasher:
 
     @staticmethod
     def hamming_distance(h1: T, h2: T) -> int:
-        if isinstance(h1, int) or isinstance(h2, int):
+        if isinstance(h1, int):
             n1 = h1
+        else:
+            n1 = int(h1, 16)
+
+        if isinstance(h2, int):
             n2 = h2
         else:
-            # convert hex strings to ints
-            n1 = int(h1, 16)
             n2 = int(h2, 16)
 
         # xor the two numbers

comictaggerlib/imagepopup.py

@@ -1,6 +1,7 @@
 """A PyQT4 widget to display a popup image"""
+
 #
-# Copyright 2012-2014 Anthony Beville
+# Copyright 2012-2014 ComicTagger Authors
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -16,20 +17,39 @@
 from __future__ import annotations
 
 import logging
+import platform
 
 from PyQt5 import QtCore, QtGui, QtWidgets, sip, uic
 
-from comictaggerlib.graphics import graphics_path
 from comictaggerlib.ui import ui_path
 
 logger = logging.getLogger(__name__)
 
 
+def clickable(widget: QtWidgets.QWidget) -> QtCore.pyqtBoundSignal:
+    """Allow a label to be clickable"""
+
+    class Filter(QtCore.QObject):
+        clicked = QtCore.pyqtSignal()
+
+        def eventFilter(self, obj: QtCore.QObject, event: QtCore.QEvent) -> bool:
+            if obj == widget:
+                if event.type() == QtCore.QEvent.Type.MouseButtonPress:
+                    self.clicked.emit()
+                    return True
+            return False
+
+    flt = Filter(widget)
+    widget.installEventFilter(flt)
+    return flt.clicked
+
+
 class ImagePopup(QtWidgets.QDialog):
     def __init__(self, parent: QtWidgets.QWidget, image_pixmap: QtGui.QPixmap) -> None:
         super().__init__(parent)
 
-        uic.loadUi(ui_path / "imagepopup.ui", self)
+        with (ui_path / "imagepopup.ui").open(encoding="utf-8") as uifile:
+            uic.loadUi(uifile, self)
 
         QtWidgets.QApplication.setOverrideCursor(QtGui.QCursor(QtCore.Qt.CursorShape.WaitCursor))
 
@@ -38,28 +58,36 @@ class ImagePopup(QtWidgets.QDialog):
 
         self.imagePixmap = image_pixmap
 
-        screen_size = QtGui.QGuiApplication.primaryScreen().geometry()
+        screen = QtWidgets.QApplication.primaryScreen()
+        screen_size = screen.geometry()
+        if platform.system() == "Darwin":
+            screen_size = screen.availableGeometry()
         QtWidgets.QApplication.primaryScreen()
         self.resize(screen_size.width(), screen_size.height())
         self.move(0, 0)
 
-        # This is a total hack.  Uses a snapshot of the desktop, and overlays a
-        # translucent screen over it.  Probably can do it better by setting opacity of a widget
-        # TODO: macOS denies this
-        screen = QtWidgets.QApplication.primaryScreen()
-        self.desktopBg = screen.grabWindow(sip.voidptr(0), 0, 0, screen_size.width(), screen_size.height())
-        bg = QtGui.QPixmap(str(graphics_path / "popup_bg.png"))
-        self.clientBgPixmap = bg.scaled(
-            screen_size.width(),
-            screen_size.height(),
-            QtCore.Qt.AspectRatioMode.IgnoreAspectRatio,
-            QtCore.Qt.SmoothTransformation,
-        )
-        self.setMask(self.clientBgPixmap.mask())
-
         self.apply_image_pixmap()
-        self.showFullScreen()
-        self.raise_()
+        if platform.system() == "Darwin":
+            self.lblImage: QtWidgets.QLabel
+            splash = QtWidgets.QSplashScreen(self.lblImage.pixmap())
+            clickable(splash).connect(lambda *x: splash.close())
+            splash.show()
+        else:
+            # This is a total hack.  Uses a snapshot of the desktop, and overlays a
+            # translucent screen over it.  Probably can do it better by setting opacity of a widget
+            # TODO: macOS denies this
+            self.desktopBg = screen.grabWindow(sip.voidptr(0), 0, 0, screen_size.width(), screen_size.height())
+            bg = QtGui.QPixmap(":/graphics/popup_bg.png")
+            self.clientBgPixmap = bg.scaled(
+                screen_size.width(),
+                screen_size.height(),
+                QtCore.Qt.AspectRatioMode.IgnoreAspectRatio,
+                QtCore.Qt.SmoothTransformation,
+            )
+            self.setMask(self.clientBgPixmap.mask())
+
+            self.showFullScreen()
+            self.raise_()
         QtWidgets.QApplication.restoreOverrideCursor()
 
     def paintEvent(self, event: QtGui.QPaintEvent) -> None:

comictaggerlib/issueselectionwindow.py

@@ -1,6 +1,7 @@
 """A PyQT4 dialog to select specific issue from list"""
+
 #
-# Copyright 2012-2014 Anthony Beville
+# Copyright 2012-2014 ComicTagger Authors
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -17,15 +18,15 @@ from __future__ import annotations
 
 import logging
 
-from PyQt5 import QtCore, QtGui, QtWidgets, uic
+from PyQt5 import QtCore, QtGui, QtWidgets
 
+from comicapi.genericmetadata import GenericMetadata
 from comicapi.issuestring import IssueString
-from comictaggerlib.comicvinetalker import ComicVineTalker, ComicVineTalkerException
 from comictaggerlib.coverimagewidget import CoverImageWidget
-from comictaggerlib.resulttypes import CVIssuesResults
-from comictaggerlib.settings import ComicTaggerSettings
+from comictaggerlib.ctsettings import ct_ns
+from comictaggerlib.seriesselectionwindow import SelectionWindow
 from comictaggerlib.ui import ui_path
-from comictaggerlib.ui.qtutils import reduce_widget_font_size
+from comictalker.comictalker import ComicTalker, RLCallBack, TalkerError
 
 logger = logging.getLogger(__name__)
 
@@ -38,147 +39,149 @@ class IssueNumberTableWidgetItem(QtWidgets.QTableWidgetItem):
         return (IssueString(self_str).as_float() or 0) < (IssueString(other_str).as_float() or 0)
 
 
-class IssueSelectionWindow(QtWidgets.QDialog):
-    volume_id = 0
-
+class QueryThread(QtCore.QThread):
     def __init__(
-        self, parent: QtWidgets.QWidget, settings: ComicTaggerSettings, series_id: int, issue_number: str
+        self,
+        talker: ComicTalker,
+        series_id: str,
+        finish: QtCore.pyqtSignal,
+        on_ratelimit: QtCore.pyqtSignal,
     ) -> None:
-        super().__init__(parent)
-
-        uic.loadUi(ui_path / "issueselectionwindow.ui", self)
-
-        self.coverWidget = CoverImageWidget(self.coverImageContainer, CoverImageWidget.AltCoverMode)
-        gridlayout = QtWidgets.QGridLayout(self.coverImageContainer)
-        gridlayout.addWidget(self.coverWidget)
-        gridlayout.setContentsMargins(0, 0, 0, 0)
-
-        reduce_widget_font_size(self.twList)
-        reduce_widget_font_size(self.teDescription, 1)
-
-        self.setWindowFlags(
-            QtCore.Qt.WindowType(
-                self.windowFlags()
-                | QtCore.Qt.WindowType.WindowSystemMenuHint
-                | QtCore.Qt.WindowType.WindowMaximizeButtonHint
-            )
-        )
-
+        super().__init__()
         self.series_id = series_id
-        self.issue_id: int | None = None
-        self.settings = settings
-        self.url_fetch_thread = None
-        self.issue_list: list[CVIssuesResults] = []
+        self.talker = talker
+        self.finish = finish
+        self.on_ratelimit = on_ratelimit
 
-        if issue_number is None or issue_number == "":
-            self.issue_number = "1"
-        else:
-            self.issue_number = issue_number
-
-        self.initial_id: int | None = None
-        self.perform_query()
-
-        self.twList.resizeColumnsToContents()
-        self.twList.currentItemChanged.connect(self.current_item_changed)
-        self.twList.cellDoubleClicked.connect(self.cell_double_clicked)
-
-        # now that the list has been sorted, find the initial record, and
-        # select it
-        if self.initial_id is None:
-            self.twList.selectRow(0)
-        else:
-            for r in range(0, self.twList.rowCount()):
-                issue_id = self.twList.item(r, 0).data(QtCore.Qt.ItemDataRole.UserRole)
-                if issue_id == self.initial_id:
-                    self.twList.selectRow(r)
-                    break
-
-    def perform_query(self) -> None:
-
-        QtWidgets.QApplication.setOverrideCursor(QtGui.QCursor(QtCore.Qt.CursorShape.WaitCursor))
+    def run(self) -> None:
+        # QtWidgets.QApplication.setOverrideCursor(QtGui.QCursor(QtCore.Qt.CursorShape.WaitCursor))
 
         try:
-            comic_vine = ComicVineTalker(self.settings.id_series_match_search_thresh)
-            comic_vine.fetch_volume_data(self.series_id)
-            self.issue_list = comic_vine.fetch_issues_by_volume(self.series_id)
-        except ComicVineTalkerException as e:
-            QtWidgets.QApplication.restoreOverrideCursor()
-            if e.code == ComicVineTalkerException.RateLimit:
-                QtWidgets.QMessageBox.critical(self, "Comic Vine Error", ComicVineTalker.get_rate_limit_message())
-            else:
-                QtWidgets.QMessageBox.critical(self, "Network Issue", "Could not connect to Comic Vine to list issues!")
+            issue_list = [
+                x
+                for x in self.talker.fetch_issues_in_series(
+                    self.series_id, on_rate_limit=RLCallBack(lambda x, y: self.on_ratelimit.emit(x, y), 10)
+                )
+                if x.issue_id is not None
+            ]
+        except TalkerError as e:
+            # QtWidgets.QApplication.restoreOverrideCursor()
+            # QtWidgets.QMessageBox.critical(None, f"{e.source} {e.code_name} Error", f"{e}")
             return
 
+        # QtWidgets.QApplication.restoreOverrideCursor()
+        self.finish.emit(issue_list)
+
+
+class IssueSelectionWindow(SelectionWindow):
+    ui_file = ui_path / "issueselectionwindow.ui"
+    CoverImageMode = CoverImageWidget.AltCoverMode
+    finish = QtCore.pyqtSignal(list)
+
+    def __init__(
+        self,
+        parent: QtWidgets.QWidget,
+        config: ct_ns,
+        talker: ComicTalker,
+        series_id: str = "",
+        issue_number: str = "",
+    ) -> None:
+        super().__init__(parent, config, talker)
+        self.series_id = series_id
+        self.issue_list: dict[str, GenericMetadata] = {}
+
+        self.issue_number = issue_number
+        if issue_number is None or issue_number == "":
+            self.issue_number = "1"
+
+        self.initial_id: str = ""
+        self.leFilter.textChanged.connect(self.filter)
+        self.finish.connect(self.query_finished)
+
+    def showEvent(self, event: QtGui.QShowEvent) -> None:
+        self.perform_query()
+
+    def perform_query(self) -> None:  # type: ignore[override]
+        self.querythread = QueryThread(
+            self.talker,
+            self.series_id,
+            self.finish,
+            self.ratelimit,
+        )
+        self.querythread.start()
+
+    def query_finished(self, issues: list[GenericMetadata]) -> None:
         self.twList.setRowCount(0)
 
         self.twList.setSortingEnabled(False)
-
-        row = 0
-        for record in self.issue_list:
+        self.issue_list = {i.issue_id: i for i in issues if i.issue_id is not None}
+        self.twList.clear()
+        for row, issue in enumerate(issues):
             self.twList.insertRow(row)
+            self.twList.setItem(row, 0, IssueNumberTableWidgetItem())
+            self.twList.setItem(row, 1, QtWidgets.QTableWidgetItem())
+            self.twList.setItem(row, 2, QtWidgets.QTableWidgetItem())
 
-            item_text = record["issue_number"]
-            item = IssueNumberTableWidgetItem(item_text)
-            item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, item_text)
-            item.setData(QtCore.Qt.ItemDataRole.UserRole, record["id"])
-            item.setData(QtCore.Qt.ItemDataRole.DisplayRole, item_text)
-            item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
-            self.twList.setItem(row, 0, item)
+            self.update_row(row, issue)
 
-            item_text = record["cover_date"]
-            if item_text is None:
-                item_text = ""
-            # remove the day of "YYYY-MM-DD"
-            parts = item_text.split("-")
-            if len(parts) > 1:
-                item_text = parts[0] + "-" + parts[1]
-
-            qtw_item = QtWidgets.QTableWidgetItem(item_text)
-            qtw_item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, item_text)
-            qtw_item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
-            self.twList.setItem(row, 1, qtw_item)
-
-            item_text = record["name"]
-            if item_text is None:
-                item_text = ""
-            qtw_item = QtWidgets.QTableWidgetItem(item_text)
-            qtw_item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, item_text)
-            qtw_item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
-            self.twList.setItem(row, 2, qtw_item)
-
-            if (
-                IssueString(record["issue_number"]).as_string().casefold()
-                == IssueString(self.issue_number).as_string().casefold()
-            ):
-                self.initial_id = record["id"]
-
-            row += 1
+            if IssueString(issue.issue).as_string().casefold() == IssueString(self.issue_number).as_string().casefold():
+                self.initial_id = issue.issue_id or ""
 
         self.twList.setSortingEnabled(True)
         self.twList.sortItems(0, QtCore.Qt.SortOrder.AscendingOrder)
-
-        QtWidgets.QApplication.restoreOverrideCursor()
+        self.twList: QtWidgets.QTableWidget
+        if self.initial_id:
+            for r in range(0, self.twList.rowCount()):
+                item = self.twList.item(r, 0)
+                issue_id = item.data(QtCore.Qt.ItemDataRole.UserRole)
+                if issue_id == self.initial_id:
+                    self.twList.selectRow(r)
+                    self.twList.scrollToItem(item, QtWidgets.QAbstractItemView.ScrollHint.EnsureVisible)
+                    break
 
     def cell_double_clicked(self, r: int, c: int) -> None:
         self.accept()
 
-    def current_item_changed(self, curr: QtCore.QModelIndex | None, prev: QtCore.QModelIndex | None) -> None:
+    def update_row(self, row: int, issue: GenericMetadata) -> None:  # type: ignore[override]
+        self.twList.setStyleSheet(self.twList.styleSheet())
+        item_text = issue.issue or ""
+        item = self.twList.item(row, 0)
+        item.setText(item_text)
+        item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, item_text)
+        item.setData(QtCore.Qt.ItemDataRole.UserRole, issue.issue_id)
+        item.setData(QtCore.Qt.ItemDataRole.DisplayRole, item_text)
+        item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
 
-        if curr is None:
-            return
-        if prev is not None and prev.row() == curr.row():
-            return
+        item_text = ""
+        if issue.year is not None:
+            item_text += f"-{issue.year:04}"
+        if issue.month is not None:
+            item_text += f"-{issue.month:02}"
 
-        self.issue_id = self.twList.item(curr.row(), 0).data(QtCore.Qt.ItemDataRole.UserRole)
+        qtw_item = self.twList.item(row, 1)
+        qtw_item.setText(item_text.strip("-"))
+        qtw_item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, item_text)
+        qtw_item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
 
-        # list selection was changed, update the the issue cover
-        for record in self.issue_list:
-            if record["id"] == self.issue_id:
-                self.issue_number = record["issue_number"]
-                self.coverWidget.set_issue_id(self.issue_id)
-                if record["description"] is None:
-                    self.teDescription.setText("")
-                else:
-                    self.teDescription.setText(record["description"])
+        item_text = issue.title or ""
+        qtw_item = self.twList.item(row, 2)
+        qtw_item.setText(item_text)
+        qtw_item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, item_text)
+        qtw_item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
 
-                break
+    def _fetch(self, row: int) -> GenericMetadata:  # type: ignore[override]
+        self.issue_id = self.twList.item(row, 0).data(QtCore.Qt.ItemDataRole.UserRole)
+        # list selection was changed, update the issue cover
+        issue = self.issue_list[self.issue_id]
+        if not (issue.issue and issue.year and issue.month and issue._cover_image and issue.title):
+            QtWidgets.QApplication.setOverrideCursor(QtGui.QCursor(QtCore.Qt.CursorShape.WaitCursor))
+            try:
+                issue = self.talker.fetch_comic_data(
+                    issue_id=self.issue_id, on_rate_limit=RLCallBack(self.on_ratelimit, 10)
+                )
+            except TalkerError:
+                pass
+        self.issue_number = issue.issue or ""
+        self.cover_widget.set_issue_details(self.issue_id, [issue._cover_image or "", *issue._alternate_images])
+        self.set_description(self.teDescription, issue.description or "")
+        return issue

comictaggerlib/log.py

@@ -0,0 +1,57 @@
+from __future__ import annotations
+
+import logging.handlers
+import pathlib
+import platform
+import sys
+
+from comictaggerlib.ctversion import version
+
+logger = logging.getLogger("comictagger")
+
+
+def get_filename(filename: str) -> str:
+    filename, _, number = filename.rpartition(".")
+    return filename.removesuffix("log") + number + ".log"
+
+
+def get_file_handler(filename: pathlib.Path) -> logging.FileHandler:
+    file_handler = logging.handlers.RotatingFileHandler(filename, encoding="utf-8", backupCount=10)
+    file_handler.namer = get_filename
+
+    if filename.is_file() and filename.stat().st_size > 0:
+        file_handler.doRollover()
+    return file_handler
+
+
+def setup_logging(verbose: int, log_dir: pathlib.Path) -> None:
+    logging.getLogger("comicapi").setLevel(logging.DEBUG)
+    logging.getLogger("comictaggerlib").setLevel(logging.DEBUG)
+    logging.getLogger("comictalker").setLevel(logging.DEBUG)
+
+    log_file = log_dir / "ComicTagger.log"
+    log_dir.mkdir(parents=True, exist_ok=True)
+
+    stream_handler = logging.StreamHandler()
+    file_handler = get_file_handler(log_file)
+
+    if verbose > 1:
+        stream_handler.setLevel(logging.DEBUG)
+    elif verbose > 0:
+        stream_handler.setLevel(logging.INFO)
+    else:
+        stream_handler.setLevel(logging.WARNING)
+
+    logging.basicConfig(
+        handlers=[stream_handler, file_handler],
+        level=logging.WARNING,
+        format="%(asctime)s | %(name)s | %(levelname)s | %(message)s",
+        datefmt="%Y-%m-%dT%H:%M:%S",
+    )
+
+    logger.info(
+        "ComicTagger Version: %s running on: %s PyInstaller: %s",
+        version,
+        platform.system(),
+        "Yes" if getattr(sys, "frozen", None) else "No",
+    )

comictaggerlib/logwindow.py

@@ -1,6 +1,7 @@
 """A PyQT4 dialog to a text file or log"""
+
 #
-# Copyright 2012-2014 Anthony Beville
+# Copyright 2012-2014 ComicTagger Authors
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -28,7 +29,8 @@ class LogWindow(QtWidgets.QDialog):
     def __init__(self, parent: QtWidgets.QWidget) -> None:
         super().__init__(parent)
 
-        uic.loadUi(ui_path / "logwindow.ui", self)
+        with (ui_path / "logwindow.ui").open(encoding="utf-8") as uifile:
+            uic.loadUi(uifile, self)
 
         self.setWindowFlags(
             QtCore.Qt.WindowType(

comictaggerlib/main.py

@@ -1,6 +1,7 @@
 """A python app to (automatically) tag comic archives"""
+
 #
-# Copyright 2012-2014 Anthony Beville
+# Copyright 2012-2014 ComicTagger Authors
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -15,226 +16,304 @@
 # limitations under the License.
 from __future__ import annotations
 
+import argparse
 import json
+import locale
+import logging
 import logging.handlers
 import os
-import pathlib
-import platform
 import signal
+import subprocess
 import sys
-import traceback
-import types
+from collections.abc import Collection
+from typing import cast
 
-from comicapi import utils
-from comictaggerlib import cli
-from comictaggerlib.comicvinetalker import ComicVineTalker
+import settngs
+
+import comicapi.comicarchive
+import comicapi.utils
+import comictalker
+from comictaggerlib import cli, ctsettings
+from comictaggerlib.ctsettings import ct_ns, plugin_finder
 from comictaggerlib.ctversion import version
-from comictaggerlib.graphics import graphics_path
-from comictaggerlib.options import parse_cmd_line
-from comictaggerlib.settings import ComicTaggerSettings
+from comictaggerlib.log import setup_logging
+from comictaggerlib.resulttypes import Action
+from comictalker.comictalker import ComicTalker
 
 if sys.version_info < (3, 10):
     import importlib_metadata
 else:
     import importlib.metadata as importlib_metadata
-
 logger = logging.getLogger("comictagger")
-logging.getLogger("comicapi").setLevel(logging.DEBUG)
-logging.getLogger("comictaggerlib").setLevel(logging.DEBUG)
+
+
 logger.setLevel(logging.DEBUG)
 
-try:
-    qt_available = True
-    from PyQt5 import QtCore, QtGui, QtWidgets
 
-    def show_exception_box(log_msg: str) -> None:
-        """Checks if a QApplication instance is available and shows a messagebox with the exception message.
-        If unavailable (non-console application), log an additional notice.
-        """
-        if QtWidgets.QApplication.instance() is not None:
-            errorbox = QtWidgets.QMessageBox()
-            errorbox.setText(f"Oops. An unexpected error occurred:\n{log_msg}")
-            errorbox.exec()
-            QtWidgets.QApplication.exit(1)
-        else:
-            logger.debug("No QApplication instance available.")
+def _lang_code_mac() -> str:
+    """
+    stolen from https://github.com/mu-editor/mu
+    Returns the user's language preference as defined in the Language & Region
+    preference pane in macOS's System Preferences.
+    """
 
-    class UncaughtHook(QtCore.QObject):
-        _exception_caught = QtCore.pyqtSignal(object)
+    # Uses the shell command `defaults read -g AppleLocale` that prints out a
+    # language code to standard output. Assumptions about the command:
+    # - It exists and is in the shell's PATH.
+    # - It accepts those arguments.
+    # - It returns a usable language code.
+    #
+    # Reference documentation:
+    # - The man page for the `defaults` command on macOS.
+    # - The macOS underlying API:
+    #   https://developer.apple.com/documentation/foundation/nsuserdefaults.
 
-        def __init__(self) -> None:
-            super().__init__()
+    lang_detect_command = "defaults read -g AppleLocale"
 
-            # this registers the exception_hook() function as hook with the Python interpreter
-            sys.excepthook = self.exception_hook
+    status, output = subprocess.getstatusoutput(lang_detect_command)
+    if status == 0:
+        # Command was successful.
+        lang_code = output
+    else:
+        logging.warning("Language detection command failed: %r", output)
+        lang_code = ""
 
-            # connect signal to execute the message box function always on main thread
-            self._exception_caught.connect(show_exception_box)
-
-        def exception_hook(
-            self, exc_type: type[BaseException], exc_value: BaseException, exc_traceback: types.TracebackType | None
-        ) -> None:
-            """Function handling uncaught exceptions.
-            It is triggered each time an uncaught exception occurs.
-            """
-            if issubclass(exc_type, KeyboardInterrupt):
-                # ignore keyboard interrupt to support console applications
-                sys.__excepthook__(exc_type, exc_value, exc_traceback)
-            else:
-                exc_info = (exc_type, exc_value, exc_traceback)
-                log_msg = "\n".join(["".join(traceback.format_tb(exc_traceback)), f"{exc_type.__name__}: {exc_value}"])
-                logger.critical("Uncaught exception: %s: %s", exc_type.__name__, exc_value, exc_info=exc_info)
-
-                # trigger message box show
-                self._exception_caught.emit(log_msg)
-
-    qt_exception_hook = UncaughtHook()
-    from comictaggerlib.taggerwindow import TaggerWindow
-
-    class Application(QtWidgets.QApplication):
-        openFileRequest = QtCore.pyqtSignal(QtCore.QUrl, name="openfileRequest")
-
-        def event(self, event):
-            if event.type() == QtCore.QEvent.FileOpen:
-                logger.info(event.url().toLocalFile())
-                self.openFileRequest.emit(event.url())
-                return True
-            return super().event(event)
-
-except ImportError as e:
-
-    def show_exception_box(log_msg: str) -> None:
-        ...
-
-    logger.error(str(e))
-    qt_available = False
+    return lang_code
 
 
-def rotate(handler: logging.handlers.RotatingFileHandler, filename: pathlib.Path) -> None:
-    if filename.is_file() and filename.stat().st_size > 0:
-        handler.doRollover()
+def configure_locale() -> None:
+    if sys.platform == "darwin" and "LANG" not in os.environ:
+        code = _lang_code_mac()
+        if code != "":
+            os.environ["LANG"] = f"{code}.utf-8"
+
+    locale.setlocale(locale.LC_ALL, "")
+    sys.stdout.reconfigure(encoding=sys.getdefaultencoding())  # type: ignore[union-attr]
+    sys.stderr.reconfigure(encoding=sys.getdefaultencoding())  # type: ignore[union-attr]
+    sys.stdin.reconfigure(encoding=sys.getdefaultencoding())  # type: ignore[union-attr]
 
 
-def update_publishers() -> None:
-    json_file = ComicTaggerSettings.get_settings_folder() / "publishers.json"
+def update_publishers(config: settngs.Config[ct_ns]) -> None:
+    json_file = config[0].Runtime_Options__config.user_config_dir / "publishers.json"
     if json_file.exists():
         try:
-            utils.update_publishers(json.loads(json_file.read_text("utf-8")))
+            comicapi.utils.update_publishers(json.loads(json_file.read_text("utf-8")))
         except Exception as e:
-            logger.exception("Failed to load publishers from %s", json_file)
-            show_exception_box(str(e))
+            logger.exception("Failed to load publishers from %s: %s", json_file, e)
 
 
-def ctmain() -> None:
-    opts = parse_cmd_line()
-    settings = ComicTaggerSettings(opts.config_path)
+class App:
+    """docstring for App"""
 
-    os.makedirs(ComicTaggerSettings.get_settings_folder() / "logs", exist_ok=True)
-    stream_handler = logging.StreamHandler()
-    stream_handler.setLevel(logging.WARNING)
-    file_handler = logging.handlers.RotatingFileHandler(
-        ComicTaggerSettings.get_settings_folder() / "logs" / "ComicTagger.log", encoding="utf-8", backupCount=10
-    )
-    rotate(file_handler, ComicTaggerSettings.get_settings_folder() / "logs" / "ComicTagger.log")
-    logging.basicConfig(
-        handlers=[
-            stream_handler,
-            file_handler,
-        ],
-        level=logging.WARNING,
-        format="%(asctime)s | %(name)s | %(levelname)s | %(message)s",
-        datefmt="%Y-%m-%dT%H:%M:%S",
-    )
-    # Need to load setting before anything else
+    def __init__(self) -> None:
+        self.config: settngs.Config[ct_ns]
+        self.initial_arg_parser = ctsettings.initial_commandline_parser()
+        self.config_load_success = False
+        self.talkers: dict[str, ComicTalker]
 
-    # manage the CV API key
-    # None comparison is used so that the empty string can unset the value
-    if opts.cv_api_key is not None or opts.cv_url is not None:
-        settings.cv_api_key = opts.cv_api_key if opts.cv_api_key is not None else settings.cv_api_key
-        settings.cv_url = opts.cv_url if opts.cv_url is not None else settings.cv_url
-        settings.save()
-    if opts.only_set_cv_key:
-        print("Key set")  # noqa: T201
-        return
+    def run(self) -> None:
+        configure_locale()
+        conf = self.initialize()
+        self.initialize_dirs(conf.config)
+        self.load_plugins(conf)
+        self.register_settings(conf.enable_quick_tag)
+        self.config = self.parse_settings(conf.config)
 
-    ComicVineTalker.api_key = settings.cv_api_key
-    ComicVineTalker.api_base_url = settings.cv_url
+        self.main()
 
-    signal.signal(signal.SIGINT, signal.SIG_DFL)
+    def load_plugins(self, opts: argparse.Namespace) -> None:
+        local_plugins = plugin_finder.find_plugins(opts.config.user_plugin_dir)
 
-    logger.info(
-        "ComicTagger Version: %s running on: %s PyInstaller: %s",
-        version,
-        platform.system(),
-        "Yes" if getattr(sys, "frozen", None) else "No",
-    )
+        comicapi.comicarchive.load_archive_plugins(local_plugins=[p.obj for p in local_plugins.archivers])
+        comicapi.comicarchive.load_tag_plugins(version=version, local_plugins=[p.obj for p in local_plugins.tags])
+        self.talkers = comictalker.get_talkers(
+            version, opts.config.user_cache_dir, local_plugins=[p.obj for p in local_plugins.talkers]
+        )
 
-    logger.debug("Installed Packages")
-    for pkg in sorted(importlib_metadata.distributions(), key=lambda x: x.name):
-        logger.debug("%s\t%s", pkg.metadata["Name"], pkg.metadata["Version"])
+    def list_plugins(
+        self,
+        talkers: Collection[comictalker.ComicTalker],
+        archivers: Collection[type[comicapi.comicarchive.Archiver]],
+        tags: Collection[comicapi.comicarchive.Tag],
+    ) -> None:
+        if self.config[0].Runtime_Options__json:
+            for talker in talkers:
+                print(  # noqa: T201
+                    json.dumps(
+                        {
+                            "type": "talker",
+                            "id": talker.id,
+                            "name": talker.name,
+                            "website": talker.website,
+                        }
+                    )
+                )
 
-    utils.load_publishers()
-    update_publishers()
+            for archiver in archivers:
+                try:
+                    a = archiver()
+                    print(  # noqa: T201
+                        json.dumps(
+                            {
+                                "type": "archiver",
+                                "enabled": a.enabled,
+                                "name": a.name(),
+                                "extension": a.extension(),
+                                "exe": a.exe,
+                            }
+                        )
+                    )
+                except Exception:
+                    print(  # noqa: T201
+                        json.dumps(
+                            {
+                                "type": "archiver",
+                                "enabled": archiver.enabled,
+                                "name": "",
+                                "extension": "",
+                                "exe": archiver.exe,
+                            }
+                        )
+                    )
 
-    if not qt_available and not opts.no_gui:
-        opts.no_gui = True
-        logger.warning("PyQt5 is not available. ComicTagger is limited to command-line mode.")
+            for tag in tags:
+                print(  # noqa: T201
+                    json.dumps(
+                        {
+                            "type": "tag",
+                            "enabled": tag.enabled,
+                            "name": tag.name(),
+                            "id": tag.id,
+                        }
+                    )
+                )
+        else:
+            print("Metadata Sources: (ID: Name, URL)")  # noqa: T201
+            for talker in talkers:
+                print(f"{talker.id:<10}: {talker.name:<21}, {talker.website}")  # noqa: T201
+
+            print("\nComic Archive: (Enabled, Name: extension, exe)")  # noqa: T201
+            for archiver in archivers:
+                a = archiver()
+                print(f"{a.enabled!s:<5}, {a.name():<10}: {a.extension():<5}, {a.exe}")  # noqa: T201
+
+            print("\nTags: (Enabled, ID: Name)")  # noqa: T201
+            for tag in tags:
+                print(f"{tag.enabled!s:<5}, {tag.id:<10}: {tag.name()}")  # noqa: T201
+
+    def initialize(self) -> argparse.Namespace:
+        conf, _ = self.initial_arg_parser.parse_known_intermixed_args()
+
+        assert conf is not None
+        setup_logging(conf.verbose, conf.config.user_log_dir)
+        return conf
+
+    def register_settings(self, enable_quick_tag: bool) -> None:
+        self.manager = settngs.Manager(
+            description="A utility for reading and writing metadata to comic archives.\n\n\n"
+            + "If no options are given, %(prog)s will run in windowed mode.\nPlease keep the '-v' option separated '-so -v' not '-sov'",
+            epilog="For more help visit the wiki at: https://github.com/comictagger/comictagger/wiki",
+        )
+        ctsettings.register_commandline_settings(self.manager, enable_quick_tag)
+        ctsettings.register_file_settings(self.manager)
+        ctsettings.register_plugin_settings(self.manager, getattr(self, "talkers", {}))
+
+    def parse_settings(self, config_paths: ctsettings.ComicTaggerPaths, *args: str) -> settngs.Config[ct_ns]:
+        cfg, self.config_load_success = ctsettings.parse_config(
+            self.manager, config_paths.user_config_dir / "settings.json", list(args) or None
+        )
+        config = cast(settngs.Config[ct_ns], self.manager.get_namespace(cfg, file=True, cmdline=True))
+        config[0].Runtime_Options__config = config_paths
+
+        config = ctsettings.validate_commandline_settings(config, self.manager)
+        config = ctsettings.validate_file_settings(config)
+        config = ctsettings.validate_plugin_settings(config, getattr(self, "talkers", {}))
+        return config
+
+    def initialize_dirs(self, paths: ctsettings.ComicTaggerPaths) -> None:
+        paths.user_config_dir.mkdir(parents=True, exist_ok=True)
+        paths.user_cache_dir.mkdir(parents=True, exist_ok=True)
+        paths.user_log_dir.mkdir(parents=True, exist_ok=True)
+        paths.user_plugin_dir.mkdir(parents=True, exist_ok=True)
+        logger.debug("user_config_dir: %s", paths.user_config_dir)
+        logger.debug("user_cache_dir: %s", paths.user_cache_dir)
+        logger.debug("user_log_dir: %s", paths.user_log_dir)
+        logger.debug("user_plugin_dir: %s", paths.user_plugin_dir)
+
+    def main(self) -> None:
+        assert self.config is not None
+        # config already loaded
+        error = None
+
+        if (
+            not self.config[0].Metadata_Options__cr
+            and "cr" in comicapi.comicarchive.tags
+            and comicapi.comicarchive.tags["cr"].enabled
+        ):
+            comicapi.comicarchive.tags["cr"].enabled = False
+
+        if len(self.talkers) < 1:
+            error = (
+                "Failed to load any talkers, please re-install and check the log located in '"
+                + str(self.config[0].Runtime_Options__config.user_log_dir)
+                + "' for more details",
+                True,
+            )
+
+        signal.signal(signal.SIGINT, signal.SIG_DFL)
+
+        logger.debug("Installed Packages")
+        for pkg in sorted(importlib_metadata.distributions(), key=lambda x: x.name):
+            logger.debug("%s\t%s", pkg.metadata["Name"], pkg.metadata["Version"])
+
+        comicapi.utils.load_publishers()
+        update_publishers(self.config)
+
+        if self.config[0].Commands__command == Action.list_plugins:
+            self.list_plugins(
+                list(self.talkers.values()),
+                comicapi.comicarchive.archivers,
+                comicapi.comicarchive.tags.values(),
+            )
+            return
+
+        if self.config[0].Commands__command == Action.save_config:
+            if self.config_load_success:
+                settings_path = self.config[0].Runtime_Options__config.user_config_dir / "settings.json"
+                if self.config_load_success:
+                    ctsettings.save_file(self.config, settings_path)
+                print("Settings saved")  # noqa: T201
+                return
+
+        if not self.config_load_success:
+            error = (
+                "Failed to load settings, check the log located in '"
+                + str(self.config[0].Runtime_Options__config.user_log_dir)
+                + "' for more details",
+                True,
+            )
+
+        if not self.config[0].Runtime_Options__no_gui:
+            try:
+                from comictaggerlib import gui
+
+                if not gui.qt_available:
+                    raise gui.import_error
+                return gui.open_tagger_window(self.talkers, self.config, error)
+            except ImportError:
+                self.config[0].Runtime_Options__no_gui = True
+                logger.warning("PyQt5 is not available. ComicTagger is limited to command-line mode.")
+
+        # GUI mode is not available or CLI mode was requested
+        if error and error[1]:
+            print(f"A fatal error occurred please check the log for more information: {error[0]}")  # noqa: T201
+            raise SystemExit(1)
 
-    if opts.no_gui:
         try:
-            cli.cli_mode(opts, settings)
+            raise SystemExit(cli.CLI(self.config[0], self.talkers).run())
         except Exception:
             logger.exception("CLI mode failed")
-    else:
-        os.environ["QtWidgets.QT_AUTO_SCREEN_SCALE_FACTOR"] = "1"
-        args = []
-        if opts.darkmode:
-            args.extend(["-platform", "windows:darkmode=2"])
-        args.extend(sys.argv)
-        app = Application(args)
 
-        # needed to catch initial open file events (macOS)
-        app.openFileRequest.connect(lambda x: opts.files.append(x.toLocalFile()))
 
-        if platform.system() == "Darwin":
-            # Set the MacOS dock icon
-            app.setWindowIcon(QtGui.QIcon(str(graphics_path / "app.png")))
-
-        if platform.system() == "Windows":
-            # For pure python, tell windows that we're not python,
-            # so we can have our own taskbar icon
-            import ctypes
-
-            myappid = "comictagger"  # arbitrary string
-            ctypes.windll.shell32.SetCurrentProcessExplicitAppUserModelID(myappid)  # type: ignore[attr-defined]
-            # force close of console window
-            swp_hidewindow = 0x0080
-            console_wnd = ctypes.windll.kernel32.GetConsoleWindow()  # type: ignore[attr-defined]
-            if console_wnd != 0:
-                ctypes.windll.user32.SetWindowPos(console_wnd, None, 0, 0, 0, 0, swp_hidewindow)  # type: ignore[attr-defined]
-
-        if platform.system() != "Linux":
-            img = QtGui.QPixmap(str(graphics_path / "tags.png"))
-
-            splash = QtWidgets.QSplashScreen(img)
-            splash.show()
-            splash.raise_()
-            QtWidgets.QApplication.processEvents()
-
-        try:
-            tagger_window = TaggerWindow(opts.files, settings, opts=opts)
-            tagger_window.setWindowIcon(QtGui.QIcon(str(graphics_path / "app.png")))
-            tagger_window.show()
-
-            # Catch open file events (macOS)
-            app.openFileRequest.connect(tagger_window.open_file_event)
-
-            if platform.system() != "Linux":
-                splash.finish(tagger_window)
-
-            sys.exit(app.exec())
-        except Exception:
-            logger.exception("GUI mode failed")
-            QtWidgets.QMessageBox.critical(
-                QtWidgets.QMainWindow(), "Error", "Unhandled exception in app:\n" + traceback.format_exc()
-            )
+def main() -> None:
+    App().run()

comictaggerlib/matchselectionwindow.py

@@ -1,6 +1,7 @@
 """A PyQT4 dialog to select from automated issue matches"""
+
 #
-# Copyright 2012-2014 Anthony Beville
+# Copyright 2012-2014 ComicTagger Authors
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -22,34 +23,40 @@ from PyQt5 import QtCore, QtWidgets, uic
 
 from comicapi.comicarchive import ComicArchive
 from comictaggerlib.coverimagewidget import CoverImageWidget
+from comictaggerlib.ctsettings import ct_ns
 from comictaggerlib.resulttypes import IssueResult
 from comictaggerlib.ui import ui_path
-from comictaggerlib.ui.qtutils import reduce_widget_font_size
+from comictalker.comictalker import ComicTalker
 
 logger = logging.getLogger(__name__)
 
 
 class MatchSelectionWindow(QtWidgets.QDialog):
-    volume_id = 0
-
-    def __init__(self, parent: QtWidgets.QWidget, matches: list[IssueResult], comic_archive: ComicArchive) -> None:
+    def __init__(
+        self,
+        parent: QtWidgets.QWidget,
+        matches: list[IssueResult],
+        comic_archive: ComicArchive,
+        config: ct_ns,
+        talker: ComicTalker,
+    ) -> None:
         super().__init__(parent)
 
-        uic.loadUi(ui_path / "matchselectionwindow.ui", self)
+        with (ui_path / "matchselectionwindow.ui").open(encoding="utf-8") as uifile:
+            uic.loadUi(uifile, self)
 
-        self.altCoverWidget = CoverImageWidget(self.altCoverContainer, CoverImageWidget.AltCoverMode)
+        self.altCoverWidget = CoverImageWidget(
+            self.altCoverContainer, CoverImageWidget.AltCoverMode, config.Runtime_Options__config.user_cache_dir
+        )
         gridlayout = QtWidgets.QGridLayout(self.altCoverContainer)
         gridlayout.addWidget(self.altCoverWidget)
         gridlayout.setContentsMargins(0, 0, 0, 0)
 
-        self.archiveCoverWidget = CoverImageWidget(self.archiveCoverContainer, CoverImageWidget.ArchiveMode)
+        self.archiveCoverWidget = CoverImageWidget(self.archiveCoverContainer, CoverImageWidget.ArchiveMode, None)
         gridlayout = QtWidgets.QGridLayout(self.archiveCoverContainer)
         gridlayout.addWidget(self.archiveCoverWidget)
         gridlayout.setContentsMargins(0, 0, 0, 0)
 
-        reduce_widget_font_size(self.twList)
-        reduce_widget_font_size(self.teDescription, 1)
-
         self.setWindowFlags(
             QtCore.Qt.WindowType(
                 self.windowFlags()
@@ -67,7 +74,6 @@ class MatchSelectionWindow(QtWidgets.QDialog):
         self.update_data()
 
     def update_data(self) -> None:
-
         self.set_cover_image()
         self.populate_table()
         self.twList.resizeColumnsToContents()
@@ -77,24 +83,22 @@ class MatchSelectionWindow(QtWidgets.QDialog):
         self.setWindowTitle(f"Select correct match: {os.path.split(path)[1]}")
 
     def populate_table(self) -> None:
-
         self.twList.setRowCount(0)
 
         self.twList.setSortingEnabled(False)
 
-        row = 0
-        for match in self.matches:
+        for row, match in enumerate(self.matches):
             self.twList.insertRow(row)
 
-            item_text = match["series"]
+            item_text = match.series
             item = QtWidgets.QTableWidgetItem(item_text)
             item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, item_text)
             item.setData(QtCore.Qt.ItemDataRole.UserRole, (match,))
             item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
             self.twList.setItem(row, 0, item)
 
-            if match["publisher"] is not None:
-                item_text = str(match["publisher"])
+            if match.publisher is not None:
+                item_text = str(match.publisher)
             else:
                 item_text = "Unknown"
             item = QtWidgets.QTableWidgetItem(item_text)
@@ -104,10 +108,10 @@ class MatchSelectionWindow(QtWidgets.QDialog):
 
             month_str = ""
             year_str = "????"
-            if match["month"] is not None:
-                month_str = f"-{int(match['month']):02d}"
-            if match["year"] is not None:
-                year_str = str(match["year"])
+            if match.month is not None:
+                month_str = f"-{int(match.month):02d}"
+            if match.year is not None:
+                year_str = str(match.year)
 
             item_text = year_str + month_str
             item = QtWidgets.QTableWidgetItem(item_text)
@@ -115,7 +119,7 @@ class MatchSelectionWindow(QtWidgets.QDialog):
             item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
             self.twList.setItem(row, 2, item)
 
-            item_text = match["issue_title"]
+            item_text = match.issue_title
             if item_text is None:
                 item_text = ""
             item = QtWidgets.QTableWidgetItem(item_text)
@@ -123,8 +127,6 @@ class MatchSelectionWindow(QtWidgets.QDialog):
             item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
             self.twList.setItem(row, 3, item)
 
-            row += 1
-
         self.twList.resizeColumnsToContents()
         self.twList.setSortingEnabled(True)
         self.twList.sortItems(2, QtCore.Qt.SortOrder.AscendingOrder)
@@ -136,17 +138,20 @@ class MatchSelectionWindow(QtWidgets.QDialog):
         self.accept()
 
     def current_item_changed(self, curr: QtCore.QModelIndex, prev: QtCore.QModelIndex) -> None:
-
         if curr is None:
             return
         if prev is not None and prev.row() == curr.row():
             return
 
-        self.altCoverWidget.set_issue_id(self.current_match()["issue_id"])
-        if self.current_match()["description"] is None:
+        match = self.current_match()
+        self.altCoverWidget.set_issue_details(
+            match.issue_id,
+            [match.image_url, *match.alt_image_urls],
+        )
+        if match.description is None:
             self.teDescription.setText("")
         else:
-            self.teDescription.setText(self.current_match()["description"])
+            self.teDescription.setText(match.description)
 
     def set_cover_image(self) -> None:
         self.archiveCoverWidget.set_archive(self.comic_archive)

comictaggerlib/md.py

@@ -0,0 +1,62 @@
+from __future__ import annotations
+
+from datetime import datetime
+
+from comicapi import merge, utils
+from comicapi.comicarchive import ComicArchive
+from comicapi.genericmetadata import GenericMetadata
+from comictaggerlib import ctversion
+from comictaggerlib.cbltransformer import CBLTransformer
+from comictaggerlib.ctsettings.settngs_namespace import SettngsNS
+from comictalker.talker_utils import cleanup_html
+
+
+def prepare_metadata(md: GenericMetadata, new_md: GenericMetadata, config: SettngsNS) -> GenericMetadata:
+    if config.Metadata_Options__apply_transform_on_import:
+        new_md = CBLTransformer(new_md, config).apply()
+
+    final_md = md.copy()
+    if config.Auto_Tag__clear_tags:
+        final_md = GenericMetadata()
+
+    final_md.overlay(new_md, config.Metadata_Options__metadata_merge, config.Metadata_Options__metadata_merge_lists)
+
+    issue_id = ""
+    if final_md.issue_id:
+        issue_id = f" [Issue ID {final_md.issue_id}]"
+
+    origin = ""
+    if final_md.data_origin is not None:
+        origin = f" using info from {final_md.data_origin.name}"
+    notes = f"Tagged with ComicTagger {ctversion.version}{origin} on {datetime.now():%Y-%m-%d %H:%M:%S}.{issue_id}"
+
+    if config.Auto_Tag__auto_imprint:
+        final_md.fix_publisher()
+
+    return final_md.replace(
+        is_empty=False,
+        notes=utils.combine_notes(final_md.notes, notes, "Tagged with ComicTagger"),
+        description=cleanup_html(final_md.description, config.Metadata_Options__remove_html_tables) or None,
+    )
+
+
+def read_selected_tags(
+    tag_ids: list[str], ca: ComicArchive, mode: merge.Mode = merge.Mode.OVERLAY, merge_lists: bool = False
+) -> tuple[GenericMetadata, list[str], Exception | None]:
+    md = GenericMetadata()
+    error = None
+    tags_used = []
+    try:
+        for tag_id in tag_ids:
+            metadata = ca.read_tags(tag_id)
+            if not metadata.is_empty:
+                md.overlay(
+                    metadata,
+                    mode=mode,
+                    merge_lists=merge_lists,
+                )
+                tags_used.append(tag_id)
+    except Exception as e:
+        error = e
+
+    return md, tags_used, error

comictaggerlib/optionalmsgdialog.py

@@ -10,8 +10,9 @@ said_yes, checked = OptionalMessageDialog.question(self, "QtWidgets.Question",
                             "Are you sure you wish to do this?",
                          )
 """
+
 #
-# Copyright 2012-2014 Anthony Beville
+# Copyright 2012-2014 ComicTagger Authors
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -77,10 +78,7 @@ class OptionalMessageDialog(QtWidgets.QDialog):
         else:
             btnbox_style = QtWidgets.QDialogButtonBox.StandardButton.Ok
 
-        self.theButtonBox = QtWidgets.QDialogButtonBox(
-            btnbox_style,
-            parent=self,
-        )
+        self.theButtonBox = QtWidgets.QDialogButtonBox(btnbox_style, parent=self)
         self.theButtonBox.accepted.connect(self.accept)
         self.theButtonBox.rejected.connect(self.reject)
 
@@ -96,7 +94,6 @@ class OptionalMessageDialog(QtWidgets.QDialog):
 
     @staticmethod
     def msg(parent: QtWidgets.QWidget, title: str, msg: str, checked: bool = False, check_text: str = "") -> bool:
-
         d = OptionalMessageDialog(parent, StyleMessage, title, msg, checked=checked, check_text=check_text)
 
         d.exec()
@@ -106,7 +103,6 @@ class OptionalMessageDialog(QtWidgets.QDialog):
     def question(
         parent: QtWidgets.QWidget, title: str, msg: str, checked: bool = False, check_text: str = ""
     ) -> tuple[bool, bool]:
-
         d = OptionalMessageDialog(parent, StyleQuestion, title, msg, checked=checked, check_text=check_text)
 
         d.exec()
@@ -117,7 +113,6 @@ class OptionalMessageDialog(QtWidgets.QDialog):
     def msg_no_checkbox(
         parent: QtWidgets.QWidget, title: str, msg: str, checked: bool = False, check_text: str = ""
     ) -> bool:
-
         d = OptionalMessageDialog(parent, StyleMessage, title, msg, checked=checked, check_text=check_text)
         d.theCheckBox.hide()
 

comictaggerlib/options.py

@@ -1,412 +0,0 @@
-"""CLI options class for ComicTagger app"""
-#
-# Copyright 2012-2014 Anthony Beville
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-from __future__ import annotations
-
-import argparse
-import logging
-import os
-import platform
-import sys
-
-from comicapi import utils
-from comicapi.comicarchive import MetaDataStyle
-from comicapi.genericmetadata import GenericMetadata
-from comictaggerlib import ctversion
-
-logger = logging.getLogger(__name__)
-
-
-def define_args() -> argparse.ArgumentParser:
-    parser = argparse.ArgumentParser(
-        description="""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(
-        "--cv-url",
-        help="Use the given Comic Vine URL (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}",
-        default=[],
-        type=metadata_type,
-        help="""Specify TYPE as either CR, CBL or COMET\n(as either ComicRack, ComicBookLover,\nor CoMet style tags, respectively).\nUse commas for multiple types.\nFor searching the metadata will use the first listed:\neg '-t cbl,cr' with no CBL tags, CR will be used if they exist\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",
-        default=GenericMetadata(),
-        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="""Overwrite 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
-
-
-def metadata_type(types: str) -> list[int]:
-    result = []
-    types = types.casefold()
-    for typ in types.split(","):
-        typ = typ.strip()
-        if typ not in MetaDataStyle.short_name:
-            choices = ", ".join(MetaDataStyle.short_name)
-            raise argparse.ArgumentTypeError(f"invalid choice: {typ} (choose from {choices.upper()})")
-        result.append(MetaDataStyle.short_name.index(typ))
-    return result
-
-
-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
-
-    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.casefold() == "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):
-            raise argparse.ArgumentTypeError(f"'{key}' is not a valid tag name")
-        else:
-            md.is_empty = False
-            setattr(md, key, value)
-    return md
-
-
-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:
-            script = __import__(module_name)
-
-            # Determine if the entry point exists before trying to run it
-            if "main" in dir(script):
-                script.main(args)
-            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() -> argparse.Namespace:
-
-    if platform.system() == "Darwin" and getattr(sys, "frozen", False):
-        # 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:]
-
-    script_args = []
-
-    # 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 and opts.cv_url is None:
-        parser.exit(message="Key not given!\n", 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 not opts.type:
-        parser.exit(message="Please specify the type to delete with -t\n", status=1)
-
-    if opts.save and not opts.type:
-        parser.exit(message="Please specify the type to save with -t\n", status=1)
-
-    if opts.copy:
-        if not opts.type:
-            parser.exit(message="Please specify the type to copy to with -t\n", status=1)
-        if len(opts.copy) > 1:
-            parser.exit(message="Please specify only one type to copy to with -c\n", status=1)
-        opts.copy = opts.copy[0]
-
-    if opts.recursive:
-        opts.file_list = utils.get_recursive_filelist(opts.files)
-    else:
-        opts.file_list = opts.files
-
-    return opts

comictaggerlib/pagebrowser.py

@@ -1,6 +1,7 @@
 """A PyQT4 dialog to show pages of a comic archive"""
+
 #
-# Copyright 2012-2014 Anthony Beville
+# Copyright 2012-2014 ComicTagger Authors
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -16,14 +17,12 @@
 from __future__ import annotations
 
 import logging
-import platform
 
 from PyQt5 import QtCore, QtGui, QtWidgets, uic
 
 from comicapi.comicarchive import ComicArchive
 from comicapi.genericmetadata import GenericMetadata
 from comictaggerlib.coverimagewidget import CoverImageWidget
-from comictaggerlib.graphics import graphics_path
 from comictaggerlib.ui import ui_path
 
 logger = logging.getLogger(__name__)
@@ -33,9 +32,10 @@ class PageBrowserWindow(QtWidgets.QDialog):
     def __init__(self, parent: QtWidgets.QWidget, metadata: GenericMetadata) -> None:
         super().__init__(parent)
 
-        uic.loadUi(ui_path / "pagebrowser.ui", self)
+        with (ui_path / "pagebrowser.ui").open(encoding="utf-8") as uifile:
+            uic.loadUi(uifile, self)
 
-        self.pageWidget = CoverImageWidget(self.pageContainer, CoverImageWidget.ArchiveMode)
+        self.pageWidget = CoverImageWidget(self.pageContainer, CoverImageWidget.ArchiveMode, None)
         gridlayout = QtWidgets.QGridLayout(self.pageContainer)
         gridlayout.addWidget(self.pageWidget)
         gridlayout.setContentsMargins(0, 0, 0, 0)
@@ -55,12 +55,8 @@ class PageBrowserWindow(QtWidgets.QDialog):
         self.metadata = metadata
 
         self.buttonBox.button(QtWidgets.QDialogButtonBox.StandardButton.Close).setDefault(True)
-        if platform.system() == "Darwin":
-            self.btnPrev.setText("<<")
-            self.btnNext.setText(">>")
-        else:
-            self.btnPrev.setIcon(QtGui.QIcon(str(graphics_path / "left.png")))
-            self.btnNext.setIcon(QtGui.QIcon(str(graphics_path / "right.png")))
+        self.btnPrev.setIcon(QtGui.QIcon(":/graphics/left.png"))
+        self.btnNext.setIcon(QtGui.QIcon(":/graphics/right.png"))
 
         self.btnNext.clicked.connect(self.next_page)
         self.btnPrev.clicked.connect(self.prev_page)
@@ -80,7 +76,6 @@ class PageBrowserWindow(QtWidgets.QDialog):
         self.pageWidget.clear()
 
     def set_comic_archive(self, ca: ComicArchive) -> None:
-
         self.comic_archive = ca
         self.page_count = ca.get_number_of_pages()
         self.current_page_num = 0
@@ -92,7 +87,6 @@ class PageBrowserWindow(QtWidgets.QDialog):
             self.btnPrev.setEnabled(True)
 
     def next_page(self) -> None:
-
         if self.current_page_num + 1 < self.page_count:
             self.current_page_num += 1
         else:
@@ -100,7 +94,6 @@ class PageBrowserWindow(QtWidgets.QDialog):
         self.set_page()
 
     def prev_page(self) -> None:
-
         if self.current_page_num - 1 >= 0:
             self.current_page_num -= 1
         else:
@@ -109,9 +102,9 @@ class PageBrowserWindow(QtWidgets.QDialog):
 
     def set_page(self) -> None:
         if not self.metadata.is_empty:
-            archive_page_index = self.metadata.get_archive_page_index(self.current_page_num)
+            selected_page_index = self.metadata.get_archive_page_index(self.current_page_num)
         else:
-            archive_page_index = self.current_page_num
+            selected_page_index = self.current_page_num
 
-        self.pageWidget.set_page(archive_page_index)
-        self.setWindowTitle(f"Page Browser - Page {self.current_page_num + 1} (of {self.page_count}) ")
+        self.pageWidget.set_page(selected_page_index)
+        self.setWindowTitle(f"Page Browser - Page {self.current_page_num+1} (of {self.page_count})")

comictaggerlib/pagelisteditor.py

@@ -1,6 +1,7 @@
 """A PyQt5 widget for editing the page list info"""
+
 #
-# Copyright 2012-2014 Anthony Beville
+# Copyright 2012-2014 ComicTagger Authors
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -17,23 +18,22 @@ from __future__ import annotations
 
 import logging
 
-from PyQt5 import QtCore, QtGui, QtWidgets, uic
+from PyQt5 import QtCore, QtWidgets, uic
 
-from comicapi.comicarchive import ComicArchive, MetaDataStyle
-from comicapi.genericmetadata import ImageMetadata, PageType
+from comicapi.comicarchive import ComicArchive, tags
+from comicapi.genericmetadata import GenericMetadata, PageMetadata, PageType
 from comictaggerlib.coverimagewidget import CoverImageWidget
 from comictaggerlib.ui import ui_path
+from comictaggerlib.ui.qtutils import enable_widget
 
 logger = logging.getLogger(__name__)
 
 
 def item_move_events(widget: QtWidgets.QWidget) -> QtCore.pyqtBoundSignal:
     class Filter(QtCore.QObject):
-
         mysignal = QtCore.pyqtSignal(str)
 
         def eventFilter(self, obj: QtCore.QObject, event: QtCore.QEvent) -> bool:
-
             if obj == widget:
                 if event.type() == QtCore.QEvent.Type.ChildRemoved:
                     self.mysignal.emit("finish")
@@ -70,14 +70,24 @@ class PageListEditor(QtWidgets.QWidget):
     def __init__(self, parent: QtWidgets.QWidget) -> None:
         super().__init__(parent)
 
-        uic.loadUi(ui_path / "pagelisteditor.ui", self)
+        with (ui_path / "pagelisteditor.ui").open(encoding="utf-8") as uifile:
+            uic.loadUi(uifile, self)
 
-        self.pageWidget = CoverImageWidget(self.pageContainer, CoverImageWidget.ArchiveMode)
+        self.md_attributes = {
+            "pages.image_index": [self.btnDown, self.btnUp],
+            "pages.type": self.cbPageType,
+            "pages.double_page": self.chkDoublePage,
+            "pages.bookmark": self.leBookmark,
+            "pages": self,
+        }
+
+        self.pageWidget = CoverImageWidget(self.pageContainer, CoverImageWidget.ArchiveMode, None)
         gridlayout = QtWidgets.QGridLayout(self.pageContainer)
         gridlayout.addWidget(self.pageWidget)
         gridlayout.setContentsMargins(0, 0, 0, 0)
         self.pageWidget.showControls = False
 
+        self.blur = False
         self.reset_page()
 
         # Add the entries to the page type combobox
@@ -98,22 +108,38 @@ class PageListEditor(QtWidgets.QWidget):
         item_move_events(self.listWidget).connect(self.item_move_event)
         self.cbPageType.activated.connect(self.change_page_type)
         self.chkDoublePage.clicked.connect(self.toggle_double_page)
+        self.cbxBlur.clicked.connect(self._toggle_blur)
         self.leBookmark.editingFinished.connect(self.save_bookmark)
         self.btnUp.clicked.connect(self.move_current_up)
         self.btnDown.clicked.connect(self.move_current_down)
+        self.btnIdentifyScannerPage.clicked.connect(self.identify_scanner_page)
+        self.btnIdentifyDoublePage.clicked.connect(self.identify_double_page)
         self.pre_move_row = -1
         self.first_front_page: int | None = None
 
         self.comic_archive: ComicArchive | None = None
-        self.pages_list: list[ImageMetadata] = []
+        self.pages_list: list[PageMetadata] = []
+        self.tag_ids: list[str] = []
+
+    def set_blur(self, blur: bool) -> None:
+        self.pageWidget.blur = self.blur = blur
+        self.cbxBlur.setChecked(blur)
+        self.pageWidget.update_content()
+
+    def _toggle_blur(self) -> None:
+        self.pageWidget.blur = self.blur = not self.blur
+        self.cbxBlur.setChecked(self.blur)
+        self.pageWidget.update_content()
 
     def reset_page(self) -> None:
         self.pageWidget.clear()
-        self.cbPageType.setDisabled(True)
-        self.chkDoublePage.setDisabled(True)
-        self.leBookmark.setDisabled(True)
+        self.cbPageType.setEnabled(False)
+        self.chkDoublePage.setEnabled(False)
+        self.leBookmark.setEnabled(False)
+        self.listWidget.clear()
         self.comic_archive = None
         self.pages_list = []
+        self.cbxBlur.setChecked(self.blur)
 
     def add_page_type_item(self, text: str, user_data: str, shortcut: str, show_shortcut: bool = True) -> None:
         if show_shortcut:
@@ -124,8 +150,33 @@ class PageListEditor(QtWidgets.QWidget):
         action_item.setShortcut(shortcut)
         self.addAction(action_item)
 
+    def identify_scanner_page(self) -> None:
+        if self.comic_archive is None:
+            return
+        row = self.comic_archive.get_scanner_page_index()
+        if row is None:
+            return
+        page: PageMetadata = self.listWidget.item(row).data(QtCore.Qt.ItemDataRole.UserRole)
+
+        page.type = PageType.Deleted
+
+        item = self.listWidget.item(row)
+        item.setData(QtCore.Qt.ItemDataRole.UserRole, page)
+        item.setText(self.list_entry_text(page))
+        self.change_page()
+
+    def identify_double_page(self) -> None:
+        if self.comic_archive is None:
+            return
+        md = GenericMetadata(pages=self.get_page_list())
+        double_pages = [bool(x.double_page) for x in md.pages]
+        self.comic_archive.apply_archive_info_to_metadata(md, True, True)
+        self.set_data(self.comic_archive, pages_list=md.pages)
+        if double_pages != [bool(x.double_page) for x in md.pages]:
+            self.modified.emit()
+
     def select_page_type_item(self, idx: int) -> None:
-        if self.cbPageType.isEnabled():
+        if self.cbPageType.isEnabled() and self.listWidget.count() > 0:
             self.cbPageType.setCurrentIndex(idx)
             self.change_page_type(idx)
 
@@ -209,7 +260,7 @@ class PageListEditor(QtWidgets.QWidget):
 
     def change_page_type(self, i: int) -> None:
         new_type = self.cbPageType.itemData(i)
-        if self.get_current_page_type() != new_type:
+        if self.listWidget.count() > 0 and self.get_current_page_type() != new_type:
             self.set_current_page_type(new_type)
             self.emit_front_cover_change()
             self.modified.emit()
@@ -221,135 +272,123 @@ class PageListEditor(QtWidgets.QWidget):
         i = self.cbPageType.findData(pagetype)
         self.cbPageType.setCurrentIndex(i)
 
-        self.chkDoublePage.setChecked("DoublePage" in self.listWidget.item(row).data(QtCore.Qt.UserRole)[0])
+        page: PageMetadata = self.listWidget.item(row).data(QtCore.Qt.ItemDataRole.UserRole)
+        self.chkDoublePage.setChecked(bool(page.double_page))
 
-        if "Bookmark" in self.listWidget.item(row).data(QtCore.Qt.UserRole)[0]:
-            self.leBookmark.setText(self.listWidget.item(row).data(QtCore.Qt.UserRole)[0]["Bookmark"])
-        else:
-            self.leBookmark.setText("")
-
-        idx = int(self.listWidget.item(row).data(QtCore.Qt.ItemDataRole.UserRole)[0]["Image"])
+        self.leBookmark.setText(page.bookmark)
 
         if self.comic_archive is not None:
-            self.pageWidget.set_archive(self.comic_archive, idx)
+            self.pageWidget.set_archive(self.comic_archive, page.archive_index)
 
     def get_first_front_cover(self) -> int:
         front_cover = 0
+        if self.listWidget.count() > 0:
+            page: PageMetadata = self.listWidget.item(0).data(QtCore.Qt.ItemDataRole.UserRole)
+            front_cover = page.archive_index
         for i in range(self.listWidget.count()):
             item = self.listWidget.item(i)
-            page_dict: ImageMetadata = item.data(QtCore.Qt.ItemDataRole.UserRole)[0]
-            if "Type" in page_dict and page_dict["Type"] == PageType.FrontCover:
-                front_cover = int(page_dict["Image"])
+            page = item.data(QtCore.Qt.ItemDataRole.UserRole)
+            if page.type == PageType.FrontCover:
+                front_cover = page.archive_index
                 break
         return front_cover
 
     def get_current_page_type(self) -> str:
         row = self.listWidget.currentRow()
-        page_dict: ImageMetadata = self.listWidget.item(row).data(QtCore.Qt.ItemDataRole.UserRole)[0]
-        if "Type" in page_dict:
-            return page_dict["Type"]
-
-        return ""
+        page: PageMetadata = self.listWidget.item(row).data(QtCore.Qt.ItemDataRole.UserRole)
+        return page.type
 
     def set_current_page_type(self, t: str) -> None:
-        row = self.listWidget.currentRow()
-        page_dict: ImageMetadata = self.listWidget.item(row).data(QtCore.Qt.ItemDataRole.UserRole)[0]
+        rows = self.listWidget.selectionModel().selectedRows()
+        for index in rows:
+            row = index.row()
+            page: PageMetadata = self.listWidget.item(row).data(QtCore.Qt.ItemDataRole.UserRole)
 
-        if t == "":
-            if "Type" in page_dict:
-                del page_dict["Type"]
-        else:
-            page_dict["Type"] = t
+            page.type = t
 
-        item = self.listWidget.item(row)
-        # wrap the dict in a tuple to keep from being converted to QtWidgets.QStrings
-        item.setData(QtCore.Qt.ItemDataRole.UserRole, (page_dict,))
-        item.setText(self.list_entry_text(page_dict))
+            item = self.listWidget.item(row)
+            item.setData(QtCore.Qt.ItemDataRole.UserRole, page)
+            item.setText(self.list_entry_text(page))
 
     def toggle_double_page(self) -> None:
-        row = self.listWidget.currentRow()
-        page_dict: ImageMetadata = self.listWidget.item(row).data(QtCore.Qt.UserRole)[0]
+        rows = self.listWidget.selectionModel().selectedRows()
+        for index in rows:
+            row = index.row()
+            page: PageMetadata = self.listWidget.item(row).data(QtCore.Qt.ItemDataRole.UserRole)
 
-        cbx = self.sender()
+            cbx = self.sender()
 
-        if isinstance(cbx, QtWidgets.QCheckBox) and cbx.isChecked():
-            if "DoublePage" not in page_dict:
-                page_dict["DoublePage"] = True
+            if isinstance(cbx, QtWidgets.QCheckBox):
+                page.double_page = cbx.isChecked()
                 self.modified.emit()
-        elif "DoublePage" in page_dict:
-            del page_dict["DoublePage"]
-            self.modified.emit()
 
-        item = self.listWidget.item(row)
-        # wrap the dict in a tuple to keep from being converted to QStrings
-        item.setData(QtCore.Qt.UserRole, (page_dict,))
-        item.setText(self.list_entry_text(page_dict))
+            item = self.listWidget.item(row)
+            item.setData(QtCore.Qt.ItemDataRole.UserRole, page)
+            item.setText(self.list_entry_text(page))
 
         self.listWidget.setFocus()
 
     def save_bookmark(self) -> None:
         row = self.listWidget.currentRow()
-        page_dict: ImageMetadata = self.listWidget.item(row).data(QtCore.Qt.UserRole)[0]
+        page: PageMetadata = self.listWidget.item(row).data(QtCore.Qt.ItemDataRole.UserRole)
 
-        current_bookmark = ""
-        if "Bookmark" in page_dict:
-            current_bookmark = page_dict["Bookmark"]
+        previous_bookmark = page.bookmark
+        new_bookmark = self.leBookmark.text().strip()
 
-        if self.leBookmark.text().strip():
-            new_bookmark = str(self.leBookmark.text().strip())
-            if current_bookmark != new_bookmark:
-                page_dict["Bookmark"] = new_bookmark
-                self.modified.emit()
-        elif current_bookmark != "":
-            del page_dict["Bookmark"]
-            self.modified.emit()
+        if previous_bookmark == new_bookmark:
+            return
 
+        page.bookmark = new_bookmark
+        self.modified.emit()
         item = self.listWidget.item(row)
-        # wrap the dict in a tuple to keep from being converted to QStrings
-        item.setData(QtCore.Qt.UserRole, (page_dict,))
-        item.setText(self.list_entry_text(page_dict))
+        item.setData(QtCore.Qt.ItemDataRole.UserRole, page)
+        item.setText(self.list_entry_text(page))
 
         self.listWidget.setFocus()
 
-    def set_data(self, comic_archive: ComicArchive, pages_list: list[ImageMetadata]) -> None:
+    def set_data(self, comic_archive: ComicArchive, pages_list: list[PageMetadata]) -> None:
+        self.cbxBlur.setChecked(self.blur)
         self.comic_archive = comic_archive
         self.pages_list = pages_list
-        if pages_list is not None and len(pages_list) > 0:
-            self.cbPageType.setDisabled(False)
-            self.chkDoublePage.setDisabled(False)
-            self.leBookmark.setDisabled(False)
+        if pages_list:
+            self.select_read_tags(self.tag_ids)
+        else:
+            self.cbPageType.setEnabled(False)
+            self.chkDoublePage.setEnabled(False)
+            self.leBookmark.setEnabled(False)
 
         self.listWidget.itemSelectionChanged.disconnect(self.change_page)
 
         self.listWidget.clear()
-        for p in pages_list:
+        for p in sorted(pages_list, key=lambda p: p.display_index):
             item = QtWidgets.QListWidgetItem(self.list_entry_text(p))
-            # wrap the dict in a tuple to keep from being converted to QtWidgets.QStrings
-            item.setData(QtCore.Qt.ItemDataRole.UserRole, (p,))
+            item.setData(QtCore.Qt.ItemDataRole.UserRole, p)
 
             self.listWidget.addItem(item)
         self.first_front_page = self.get_first_front_cover()
         self.listWidget.itemSelectionChanged.connect(self.change_page)
         self.listWidget.setCurrentRow(0)
 
-    def list_entry_text(self, page_dict: ImageMetadata) -> str:
-        text = str(int(page_dict["Image"]) + 1)
-        if "Type" in page_dict:
-            if page_dict["Type"] in self.pageTypeNames:
-                text += " (" + self.pageTypeNames[page_dict["Type"]] + ")"
+    def list_entry_text(self, page: PageMetadata) -> str:
+        # indexes start at 0 but we display starting at 1. This should be consistent for all indexes in ComicTagger
+        text = str(int(page.archive_index) + 1)
+        if page.type:
+            if page.type.casefold() in {x.casefold() for x in PageType}:
+                text += " (" + self.pageTypeNames[PageType(page.type)] + ")"
             else:
-                text += " (Error: " + page_dict["Type"] + ")"
-        if "DoublePage" in page_dict:
+                text += f" (Unknown: {page.type})"
+        if page.double_page:
             text += " ②"
-        if "Bookmark" in page_dict:
+        if page.bookmark:
             text += " 🔖"
         return text
 
-    def get_page_list(self) -> list[ImageMetadata]:
-        page_list = []
+    def get_page_list(self) -> list[PageMetadata]:
+        page_list: list[PageMetadata] = []
         for i in range(self.listWidget.count()):
             item = self.listWidget.item(i)
-            page_list.append(item.data(QtCore.Qt.ItemDataRole.UserRole)[0])
+            page_list.append(item.data(QtCore.Qt.ItemDataRole.UserRole))
+            page_list[i].display_index = i
         return page_list
 
     def emit_front_cover_change(self) -> None:
@@ -357,42 +396,20 @@ class PageListEditor(QtWidgets.QWidget):
             self.first_front_page = self.get_first_front_cover()
             self.firstFrontCoverChanged.emit(self.first_front_page)
 
-    def set_metadata_style(self, data_style: int) -> None:
-        # depending on the current data style, certain fields are disabled
+    def select_read_tags(self, tag_ids: list[str]) -> None:
+        # depending on the current tags, certain fields are disabled
+        if not tag_ids:
+            return
 
-        inactive_color = QtGui.QColor(255, 170, 150)
-        active_palette = self.cbPageType.palette()
+        enabled_widgets = set()
+        for tag_id in tag_ids:
+            if not tags[tag_id].enabled:
+                continue
+            enabled_widgets.update(tags[tag_id].supported_attributes)
 
-        inactive_palette3 = self.cbPageType.palette()
-        inactive_palette3.setColor(QtGui.QPalette.ColorRole.Base, inactive_color)
+        self.tag_ids = tag_ids
 
-        if data_style == MetaDataStyle.CIX:
-            self.btnUp.setEnabled(True)
-            self.btnDown.setEnabled(True)
-            self.cbPageType.setEnabled(True)
-            self.chkDoublePage.setEnabled(True)
-            self.leBookmark.setEnabled(True)
-            self.listWidget.setEnabled(True)
+        for md_field, widget in self.md_attributes.items():
+            enable_widget(widget, md_field in enabled_widgets)
 
-            self.leBookmark.setPalette(active_palette)
-            self.listWidget.setPalette(active_palette)
-
-        elif data_style == MetaDataStyle.CBI:
-            self.btnUp.setEnabled(False)
-            self.btnDown.setEnabled(False)
-            self.cbPageType.setEnabled(False)
-            self.chkDoublePage.setEnabled(False)
-            self.leBookmark.setEnabled(False)
-            self.listWidget.setEnabled(False)
-
-            self.leBookmark.setPalette(inactive_palette3)
-            self.listWidget.setPalette(inactive_palette3)
-
-        elif data_style == MetaDataStyle.COMET:
-            pass
-
-        # make sure combo is disabled when no list
-        if self.comic_archive is None:
-            self.cbPageType.setEnabled(False)
-            self.chkDoublePage.setEnabled(False)
-            self.leBookmark.setEnabled(False)
+        self.listWidget.setDragEnabled(not ("pages.image_index" not in enabled_widgets and "pages" in enabled_widgets))

comictaggerlib/pageloader.py

@@ -1,6 +1,7 @@
 """A PyQT4 class to load a page image from a ComicArchive in a background thread"""
+
 #
-# Copyright 2012-2014 Anthony Beville
+# Copyright 2012-2014 ComicTagger Authors
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

comictaggerlib/progresswindow.py

@@ -1,6 +1,7 @@
 """A PyQt5 dialog to show ID log and progress"""
+
 #
-# Copyright 2012-2014 Anthony Beville
+# Copyright 2012-2014 ComicTagger Authors
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -20,7 +21,6 @@ import logging
 from PyQt5 import QtCore, QtWidgets, uic
 
 from comictaggerlib.ui import ui_path
-from comictaggerlib.ui.qtutils import reduce_widget_font_size
 
 logger = logging.getLogger(__name__)
 
@@ -29,7 +29,8 @@ class IDProgressWindow(QtWidgets.QDialog):
     def __init__(self, parent: QtWidgets.QWidget) -> None:
         super().__init__(parent)
 
-        uic.loadUi(ui_path / "progresswindow.ui", self)
+        with (ui_path / "progresswindow.ui").open(encoding="utf-8") as uifile:
+            uic.loadUi(uifile, self)
 
         self.setWindowFlags(
             QtCore.Qt.WindowType(
@@ -38,5 +39,3 @@ class IDProgressWindow(QtWidgets.QDialog):
                 | QtCore.Qt.WindowType.WindowMaximizeButtonHint
             )
         )
-
-        reduce_widget_font_size(self.textEdit)

comictaggerlib/quick_tag.py

@@ -0,0 +1,391 @@
+from __future__ import annotations
+
+import argparse
+import itertools
+import logging
+from enum import auto
+from io import BytesIO
+from typing import Callable, TypedDict, cast
+from urllib.parse import urljoin
+
+import requests
+import settngs
+
+from comicapi import comicarchive, utils
+from comicapi.genericmetadata import GenericMetadata
+from comicapi.issuestring import IssueString
+from comictaggerlib.ctsettings.settngs_namespace import SettngsNS
+from comictaggerlib.imagehasher import ImageHasher
+from comictalker import ComicTalker
+
+logger = logging.getLogger(__name__)
+
+__version__ = "0.1"
+
+
+class HashType(utils.StrEnum):
+    AHASH = auto()
+    DHASH = auto()
+    PHASH = auto()
+
+
+class SimpleResult(TypedDict):
+    Distance: int
+    # Mapping of domains (eg comicvine.gamespot.com) to IDs
+    IDList: dict[str, list[str]]
+
+
+class Hash(TypedDict):
+    Hash: int
+    Kind: str
+
+
+class Result(TypedDict):
+    # Mapping of domains (eg comicvine.gamespot.com) to IDs
+    IDs: dict[str, list[str]]
+    Distance: int
+    Hash: Hash
+
+
+def ihash(types: str) -> list[HashType]:
+    result: list[HashType] = []
+    types = types.casefold()
+    choices = ", ".join(HashType)
+    for typ in utils.split(types, ","):
+        if typ not in list(HashType):
+            raise argparse.ArgumentTypeError(f"invalid choice: {typ} (choose from {choices.upper()})")
+        result.append(HashType[typ.upper()])
+
+    if not result:
+        raise argparse.ArgumentTypeError(f"invalid choice: {types} (choose from {choices.upper()})")
+    return result
+
+
+def settings(manager: settngs.Manager) -> None:
+    manager.add_setting(
+        "--url",
+        "-u",
+        default="https://comic-hasher.narnian.us",
+        type=utils.parse_url,
+        help="Website to use for searching cover hashes",
+    )
+    manager.add_setting(
+        "--max",
+        default=8,
+        type=int,
+        help="Maximum score to allow. Lower score means more accurate",
+    )
+    manager.add_setting(
+        "--simple",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        help="Whether to retrieve simple results or full results",
+    )
+    manager.add_setting(
+        "--aggressive-filtering",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        help="Will filter out worse matches if better matches are found",
+    )
+    manager.add_setting(
+        "--hash",
+        default="ahash, dhash, phash",
+        type=ihash,
+        help="Pick what hashes you want to use to search (default: %(default)s)",
+    )
+    manager.add_setting(
+        "--exact-only",
+        default=True,
+        action=argparse.BooleanOptionalAction,
+        help="Skip non-exact matches if we have exact matches",
+    )
+
+
+class QuickTag:
+    def __init__(
+        self, url: utils.Url, domain: str, talker: ComicTalker, config: SettngsNS, output: Callable[[str], None]
+    ):
+        self.output = output
+        self.url = url
+        self.talker = talker
+        self.domain = domain
+        self.config = config
+
+    def id_comic(
+        self,
+        ca: comicarchive.ComicArchive,
+        tags: GenericMetadata,
+        simple: bool,
+        hashes: set[HashType],
+        exact_only: bool,
+        interactive: bool,
+        aggressive_filtering: bool,
+        max_hamming_distance: int,
+    ) -> GenericMetadata | None:
+        if not ca.seems_to_be_a_comic_archive():
+            raise Exception(f"{ca.path} is not an archive")
+        from PIL import Image
+
+        cover_index = tags.get_cover_page_index_list()[0]
+        cover_image = Image.open(BytesIO(ca.get_page(cover_index)))
+
+        self.output(f"Tagging: {ca.path}")
+
+        self.output("hashing cover")
+        phash = dhash = ahash = ""
+        hasher = ImageHasher(image=cover_image)
+        if HashType.AHASH in hashes:
+            ahash = hex(hasher.average_hash())[2:]
+        if HashType.DHASH in hashes:
+            dhash = hex(hasher.difference_hash())[2:]
+        if HashType.PHASH in hashes:
+            phash = hex(hasher.p_hash())[2:]
+
+        logger.info(f"Searching with {ahash=}, {dhash=}, {phash=}")
+
+        self.output("Searching hashes")
+        results = self.SearchHashes(simple, max_hamming_distance, ahash, dhash, phash, exact_only)
+        logger.debug(f"{results=}")
+
+        if simple:
+            filtered_simple_results = self.filter_simple_results(
+                cast(list[SimpleResult], results), interactive, aggressive_filtering
+            )
+            metadata_simple_results = self.get_simple_results(filtered_simple_results)
+            chosen_result = self.display_simple_results(metadata_simple_results, tags, interactive)
+        else:
+            filtered_results = self.filter_results(cast(list[Result], results), interactive, aggressive_filtering)
+            metadata_results = self.get_results(filtered_results)
+            chosen_result = self.display_results(metadata_results, tags, interactive)
+
+        return self.talker.fetch_comic_data(issue_id=chosen_result.issue_id, on_rate_limit=None)
+
+    def SearchHashes(
+        self, simple: bool, max_hamming_distance: int, ahash: str, dhash: str, phash: str, exact_only: bool
+    ) -> list[SimpleResult] | list[Result]:
+
+        resp = requests.get(
+            urljoin(self.url.url, "/match_cover_hash"),
+            params={
+                "simple": str(simple),
+                "max": str(max_hamming_distance),
+                "ahash": ahash,
+                "dhash": dhash,
+                "phash": phash,
+                "exactOnly": str(exact_only),
+            },
+        )
+        if resp.status_code != 200:
+            try:
+                text = resp.json()["msg"]
+            except Exception:
+                text = resp.text
+            if text == "No hashes found":
+                return []
+            logger.error("message from server: %s", text)
+            raise Exception(f"Failed to retrieve results from the server: {text}")
+        return resp.json()["results"]
+
+    def get_mds(self, results: list[SimpleResult] | list[Result]) -> list[GenericMetadata]:
+        md_results: list[GenericMetadata] = []
+        results.sort(key=lambda r: r["Distance"])
+        all_ids = set()
+        for res in results:
+            all_ids.update(res.get("IDList", res.get("IDs", {})).get(self.domain, []))  # type: ignore[attr-defined]
+
+        self.output(f"Retrieving basic {self.talker.name} data")
+        # Try to do a bulk feth of basic issue data
+        if hasattr(self.talker, "fetch_comics"):
+            md_results = self.talker.fetch_comics(issue_ids=list(all_ids), on_rate_limit=None)
+        else:
+            for md_id in all_ids:
+                md_results.append(self.talker.fetch_comic_data(issue_id=md_id, on_rate_limit=None))
+        return md_results
+
+    def get_simple_results(self, results: list[SimpleResult]) -> list[tuple[int, GenericMetadata]]:
+        md_results = []
+        mds = self.get_mds(results)
+
+        # Re-associate the md to the distance
+        for res in results:
+            for md in mds:
+                if md.issue_id in res["IDList"].get(self.domain, []):
+                    md_results.append((res["Distance"], md))
+        return md_results
+
+    def get_results(self, results: list[Result]) -> list[tuple[int, Hash, GenericMetadata]]:
+        md_results = []
+        mds = self.get_mds(results)
+
+        # Re-associate the md to the distance
+        for res in results:
+            for md in mds:
+                if md.issue_id in res["IDs"].get(self.domain, []):
+                    md_results.append((res["Distance"], res["Hash"], md))
+        return md_results
+
+    def filter_simple_results(
+        self, results: list[SimpleResult], interactive: bool, aggressive_filtering: bool
+    ) -> list[SimpleResult]:
+        # If there is a single exact match return it
+        exact = [r for r in results if r["Distance"] == 0]
+        if len(exact) == 1:
+            logger.info("Exact result found. Ignoring any others")
+            return exact
+
+        # If ther are more than 4 results and any are better than 6 return the first group of results
+        if len(results) > 4:
+            dist: list[tuple[int, list[SimpleResult]]] = []
+            filtered_results: list[SimpleResult] = []
+            for distance, group in itertools.groupby(results, key=lambda r: r["Distance"]):
+                dist.append((distance, list(group)))
+            if aggressive_filtering and dist[0][0] < 6:
+                logger.info(f"Aggressive filtering is enabled. Dropping matches above {dist[0]}")
+                for _, res in dist[:1]:
+                    filtered_results.extend(res)
+                logger.debug(f"{filtered_results=}")
+                return filtered_results
+        return results
+
+    def filter_results(self, results: list[Result], interactive: bool, aggressive_filtering: bool) -> list[Result]:
+        ahash_results = sorted([r for r in results if r["Hash"]["Kind"] == "ahash"], key=lambda r: r["Distance"])
+        dhash_results = sorted([r for r in results if r["Hash"]["Kind"] == "dhash"], key=lambda r: r["Distance"])
+        phash_results = sorted([r for r in results if r["Hash"]["Kind"] == "phash"], key=lambda r: r["Distance"])
+        hash_results = [phash_results, dhash_results, ahash_results]
+
+        # If any of the hash types have a single exact match return it. Prefer phash for no particular reason
+        for hashed_result in hash_results:
+            exact = [r for r in hashed_result if r["Distance"] == 0]
+            if len(exact) == 1:
+                logger.info(f"Exact {exact[0]['Hash']['Kind']} result found. Ignoring any others")
+                return exact
+
+        results_filtered = False
+        # If any of the hash types have more than 4 results and they have results better than 6 return the first group of results for each hash type
+        for i, hashed_results in enumerate(hash_results):
+            filtered_results: list[Result] = []
+            if len(hashed_results) > 4:
+                dist: list[tuple[int, list[Result]]] = []
+                for distance, group in itertools.groupby(hashed_results, key=lambda r: r["Distance"]):
+                    dist.append((distance, list(group)))
+                if aggressive_filtering and dist[0][0] < 6:
+                    logger.info(
+                        f"Aggressive filtering is enabled. Dropping {dist[0][1][0]['Hash']['Kind']} matches above {dist[0][0]}"
+                    )
+                    for _, res in dist[:1]:
+                        filtered_results.extend(res)
+
+            if filtered_results:
+                hash_results[i] = filtered_results
+                results_filtered = True
+        if results_filtered:
+            logger.debug(f"filtered_results={list(itertools.chain(*hash_results))}")
+        return list(itertools.chain(*hash_results))
+
+    def display_simple_results(
+        self, md_results: list[tuple[int, GenericMetadata]], tags: GenericMetadata, interactive: bool
+    ) -> GenericMetadata:
+        if len(md_results) < 1:
+            return GenericMetadata()
+        if len(md_results) == 1 and md_results[0][0] <= 4:
+            self.output("Found a single match <=4. Assuming it's correct")
+            return md_results[0][1]
+        series_match: list[GenericMetadata] = []
+        for score, md in md_results:
+            if (
+                score < 10
+                and tags.series
+                and md.series
+                and utils.titles_match(tags.series, md.series)
+                and IssueString(tags.issue).as_string() == IssueString(md.issue).as_string()
+            ):
+                series_match.append(md)
+        if len(series_match) == 1:
+            self.output(f"Found match with series name {series_match[0].series!r}")
+            return series_match[0]
+
+        if not interactive:
+            return GenericMetadata()
+
+        md_results.sort(key=lambda r: (r[0], len(r[1].publisher or "")))
+        for counter, r in enumerate(md_results, 1):
+            self.output(
+                "    {:2}. score: {} [{:15}] ({:02}/{:04}) - {} #{} - {}".format(
+                    counter,
+                    r[0],
+                    r[1].publisher,
+                    r[1].month or 0,
+                    r[1].year or 0,
+                    r[1].series,
+                    r[1].issue,
+                    r[1].title,
+                ),
+            )
+        while True:
+            i = input(
+                f'Please select a result to tag the comic with or "q" to quit: [1-{len(md_results)}] ',
+            ).casefold()
+            if i.isdigit() and int(i) in range(1, len(md_results) + 1):
+                break
+            if i == "q":
+                logger.warning("User quit without saving metadata")
+                return GenericMetadata()
+
+        return md_results[int(i) - 1][1]
+
+    def display_results(
+        self,
+        md_results: list[tuple[int, Hash, GenericMetadata]],
+        tags: GenericMetadata,
+        interactive: bool,
+    ) -> GenericMetadata:
+        if len(md_results) < 1:
+            return GenericMetadata()
+        if len(md_results) == 1 and md_results[0][0] <= 4:
+            self.output("Found a single match <=4. Assuming it's correct")
+            return md_results[0][2]
+        series_match: dict[str, tuple[int, Hash, GenericMetadata]] = {}
+        for score, cover_hash, md in md_results:
+            if (
+                score < 10
+                and tags.series
+                and md.series
+                and utils.titles_match(tags.series, md.series)
+                and IssueString(tags.issue).as_string() == IssueString(md.issue).as_string()
+            ):
+                assert md.issue_id
+                series_match[md.issue_id] = (score, cover_hash, md)
+
+        if len(series_match) == 1:
+            score, cover_hash, md = list(series_match.values())[0]
+            self.output(f"Found {cover_hash['Kind']} {score=} match with series name {md.series!r}")
+            return md
+        if not interactive:
+            return GenericMetadata()
+        md_results.sort(key=lambda r: (r[0], len(r[2].publisher or ""), r[1]["Kind"]))
+        for counter, r in enumerate(md_results, 1):
+            self.output(
+                "    {:2}. score: {} {}: {:064b} [{:15}] ({:02}/{:04}) - {} #{} - {}".format(
+                    counter,
+                    r[0],
+                    r[1]["Kind"],
+                    r[1]["Hash"],
+                    r[2].publisher or "",
+                    r[2].month or 0,
+                    r[2].year or 0,
+                    r[2].series or "",
+                    r[2].issue or "",
+                    r[2].title or "",
+                ),
+            )
+        while True:
+            i = input(
+                f'Please select a result to tag the comic with or "q" to quit: [1-{len(md_results)}] ',
+            ).casefold()
+            if i.isdigit() and int(i) in range(1, len(md_results) + 1):
+                break
+            if i == "q":
+                self.output("User quit without saving metadata")
+                return GenericMetadata()
+
+        return md_results[int(i) - 1][2]

comictaggerlib/renamewindow.py

@@ -1,6 +1,7 @@
 """A PyQT4 dialog to confirm rename"""
+
 #
-# Copyright 2012-2014 Anthony Beville
+# Copyright 2012-2014 ComicTagger Authors
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -17,16 +18,18 @@ from __future__ import annotations
 
 import logging
 
+import settngs
 from PyQt5 import QtCore, QtWidgets, uic
 
 from comicapi import utils
-from comicapi.comicarchive import ComicArchive, MetaDataStyle
+from comicapi.comicarchive import ComicArchive, tags
 from comicapi.genericmetadata import GenericMetadata
+from comictaggerlib.ctsettings import ct_ns
 from comictaggerlib.filerenamer import FileRenamer, get_rename_dir
-from comictaggerlib.settings import ComicTaggerSettings
 from comictaggerlib.settingswindow import SettingsWindow
 from comictaggerlib.ui import ui_path
 from comictaggerlib.ui.qtutils import center_window_on_parent
+from comictalker.comictalker import ComicTalker
 
 logger = logging.getLogger(__name__)
 
@@ -36,13 +39,16 @@ class RenameWindow(QtWidgets.QDialog):
         self,
         parent: QtWidgets.QWidget,
         comic_archive_list: list[ComicArchive],
-        data_style: int,
-        settings: ComicTaggerSettings,
+        read_tag_ids: list[str],
+        config: settngs.Config[ct_ns],
+        talkers: dict[str, ComicTalker],
     ) -> None:
         super().__init__(parent)
 
-        uic.loadUi(ui_path / "renamewindow.ui", self)
-        self.label.setText(f"Preview (based on {MetaDataStyle.name[data_style]} tags):")
+        with (ui_path / "renamewindow.ui").open(encoding="utf-8") as uifile:
+            uic.loadUi(uifile, self)
+
+        self.label.setText(f"Preview (based on {', '.join(tags[tag].name() for tag in read_tag_ids)} tags):")
 
         self.setWindowFlags(
             QtCore.Qt.WindowType(
@@ -52,42 +58,48 @@ class RenameWindow(QtWidgets.QDialog):
             )
         )
 
-        self.settings = settings
+        self.config = config
+        self.talkers = talkers
         self.comic_archive_list = comic_archive_list
-        self.data_style = data_style
+        self.read_tag_ids = read_tag_ids
         self.rename_list: list[str] = []
 
         self.btnSettings.clicked.connect(self.modify_settings)
-        platform = "universal" if self.settings.rename_strict else "auto"
-        self.renamer = FileRenamer(None, platform=platform)
+        platform = "universal" if self.config[0].File_Rename__strict_filenames else "auto"
+        self.renamer = FileRenamer(None, platform=platform, replacements=self.config[0].File_Rename__replacements)
 
         self.do_preview()
 
-    def config_renamer(self, ca: ComicArchive, md: GenericMetadata | None = None) -> str:
-        self.renamer.set_template(self.settings.rename_template)
-        self.renamer.set_issue_zero_padding(self.settings.rename_issue_number_padding)
-        self.renamer.set_smart_cleanup(self.settings.rename_use_smart_string_cleanup)
+    def config_renamer(self, ca: ComicArchive, md: GenericMetadata = GenericMetadata()) -> str:
+        self.renamer.set_template(self.config[0].File_Rename__template)
+        self.renamer.set_issue_zero_padding(self.config[0].File_Rename__issue_number_padding)
+        self.renamer.set_smart_cleanup(self.config[0].File_Rename__use_smart_string_cleanup)
+        self.renamer.replacements = self.config[0].File_Rename__replacements
+        self.renamer.move_only = self.config[0].File_Rename__only_move
 
         new_ext = ca.path.suffix  # default
-        if self.settings.rename_extension_based_on_archive:
-            if ca.is_sevenzip():
-                new_ext = ".cb7"
-            elif ca.is_zip():
-                new_ext = ".cbz"
-            elif ca.is_rar():
-                new_ext = ".cbr"
+        if self.config[0].File_Rename__auto_extension:
+            new_ext = ca.extension()
+
+        if md is None or md.is_empty:
+            md, _, error = self.parent().read_selected_tags(self.read_tag_ids, ca)
+            if error is not None:
+                logger.error("Failed to load tags from %s: %s", ca.path, error)
+                QtWidgets.QMessageBox.warning(
+                    self,
+                    "Read Failed!",
+                    f"One or more of the read tags failed to load for {ca.path}, check log for details",
+                )
 
-        if md is None:
-            md = ca.read_metadata(self.data_style)
             if md.is_empty:
                 md = ca.metadata_from_filename(
-                    self.settings.complicated_parser,
-                    self.settings.remove_c2c,
-                    self.settings.remove_fcbd,
-                    self.settings.remove_publisher,
+                    self.config[0].Filename_Parsing__filename_parser,
+                    self.config[0].Filename_Parsing__remove_c2c,
+                    self.config[0].Filename_Parsing__remove_fcbd,
+                    self.config[0].Filename_Parsing__remove_publisher,
                 )
-        self.renamer.set_metadata(md)
-        self.renamer.move = self.settings.rename_move_dir
+        self.renamer.set_metadata(md, ca.path.name)
+        self.renamer.move = self.config[0].File_Rename__move
         return new_ext
 
     def do_preview(self) -> None:
@@ -100,7 +112,7 @@ class RenameWindow(QtWidgets.QDialog):
             try:
                 new_name = self.renamer.determine_name(new_ext)
             except ValueError as e:
-                logger.exception("Invalid format string: %s", self.settings.rename_template)
+                logger.exception("Invalid format string: %s", self.config[0].File_Rename__template)
                 QtWidgets.QMessageBox.critical(
                     self,
                     "Invalid format string!",
@@ -114,7 +126,7 @@ class RenameWindow(QtWidgets.QDialog):
                 return
             except Exception as e:
                 logger.exception(
-                    "Formatter failure: %s metadata: %s", self.settings.rename_template, self.renamer.metadata
+                    "Formatter failure: %s metadata: %s", self.config[0].File_Rename__template, self.renamer.metadata
                 )
                 QtWidgets.QMessageBox.critical(
                     self,
@@ -125,6 +137,7 @@ class RenameWindow(QtWidgets.QDialog):
                     "<a href='https://github.com/comictagger/comictagger'>"
                     "https://github.com/comictagger/comictagger</a>",
                 )
+                return
 
             row = self.twList.rowCount()
             self.twList.insertRow(row)
@@ -161,7 +174,7 @@ class RenameWindow(QtWidgets.QDialog):
         self.twList.setSortingEnabled(True)
 
     def modify_settings(self) -> None:
-        settingswin = SettingsWindow(self, self.settings)
+        settingswin = SettingsWindow(self, self.config, self.talkers)
         settingswin.setModal(True)
         settingswin.show_rename_tab()
         settingswin.exec()
@@ -169,7 +182,6 @@ class RenameWindow(QtWidgets.QDialog):
             self.do_preview()
 
     def accept(self) -> None:
-
         prog_dialog = QtWidgets.QProgressDialog("", "Cancel", 0, len(self.rename_list), self)
         prog_dialog.setWindowTitle("Renaming Archives")
         prog_dialog.setWindowModality(QtCore.Qt.WindowModality.WindowModal)
@@ -178,18 +190,19 @@ class RenameWindow(QtWidgets.QDialog):
         QtCore.QCoreApplication.processEvents()
 
         try:
-            for idx, comic in enumerate(zip(self.comic_archive_list, self.rename_list)):
-
+            for idx, comic in enumerate(zip(self.comic_archive_list, self.rename_list), 1):
                 QtCore.QCoreApplication.processEvents()
                 if prog_dialog.wasCanceled():
                     break
-                idx += 1
+
                 prog_dialog.setValue(idx)
                 prog_dialog.setLabelText(comic[1])
-                center_window_on_parent(prog_dialog)
                 QtCore.QCoreApplication.processEvents()
 
-                folder = get_rename_dir(comic[0], self.settings.rename_dir if self.settings.rename_move_dir else None)
+                folder = get_rename_dir(
+                    comic[0],
+                    self.config[0].File_Rename__dir if self.config[0].File_Rename__move else None,
+                )
 
                 full_path = folder / comic[1]
 
@@ -197,7 +210,7 @@ class RenameWindow(QtWidgets.QDialog):
                     logger.info("%s: Filename is already good!", comic[1])
                     continue
 
-                if not comic[0].is_writable(check_rar_status=False):
+                if not comic[0].is_writable(check_archive_status=False):
                     continue
 
                 comic[0].rename(utils.unique_file(full_path))

comictaggerlib/resulttypes.py

@@ -1,162 +1,97 @@
 from __future__ import annotations
 
-from typing_extensions import NotRequired, Required, TypedDict
+import dataclasses
+import pathlib
+from enum import auto
 
-from comicapi.comicarchive import ComicArchive
+from comicapi import utils
+from comicapi.genericmetadata import GenericMetadata
 
 
-class IssueResult(TypedDict):
+@dataclasses.dataclass
+class IssueResult:
     series: str
     distance: int
     issue_number: str
-    cv_issue_count: int
+    issue_count: int | None
     url_image_hash: int
     issue_title: str
-    issue_id: int  # int?
-    volume_id: int  # int?
+    issue_id: str
+    series_id: str
     month: int | None
     year: int | None
     publisher: str | None
     image_url: str
-    thumb_url: str
-    page_url: str
+    alt_image_urls: list[str]
     description: str
 
+    def __str__(self) -> str:
+        return f"series: {self.series}; series id: {self.series_id}; issue number: {self.issue_number}; issue id: {self.issue_id}; published: {self.month} {self.year}"
 
+
+class Action(utils.StrEnum):
+    gui = auto()
+    print = auto()
+    delete = auto()
+    copy = auto()
+    save = auto()
+    rename = auto()
+    export = auto()
+    save_config = auto()
+    list_plugins = auto()
+
+
+class MatchStatus(utils.StrEnum):
+    good_match = auto()
+    no_match = auto()
+    multiple_match = auto()
+    low_confidence_match = auto()
+
+
+class Status(utils.StrEnum):
+    success = auto()
+    match_failure = auto()
+    write_failure = auto()
+    fetch_data_failure = auto()
+    existing_tags = auto()
+    read_failure = auto()
+    write_permission_failure = auto()
+    rename_failure = auto()
+
+
+@dataclasses.dataclass
 class OnlineMatchResults:
-    def __init__(self) -> None:
-        self.good_matches: list[str] = []
-        self.no_matches: list[str] = []
-        self.multiple_matches: list[MultipleMatch] = []
-        self.low_confidence_matches: list[MultipleMatch] = []
-        self.write_failures: list[str] = []
-        self.fetch_data_failures: list[str] = []
+    good_matches: list[Result] = dataclasses.field(default_factory=list)
+    no_matches: list[Result] = dataclasses.field(default_factory=list)
+    multiple_matches: list[Result] = dataclasses.field(default_factory=list)
+    low_confidence_matches: list[Result] = dataclasses.field(default_factory=list)
+    write_failures: list[Result] = dataclasses.field(default_factory=list)
+    fetch_data_failures: list[Result] = dataclasses.field(default_factory=list)
 
 
-class MultipleMatch:
-    def __init__(self, ca: ComicArchive, match_list: list[IssueResult]) -> None:
-        self.ca: ComicArchive = ca
-        self.matches: list[IssueResult] = match_list
+@dataclasses.dataclass
+class Result:
+    action: Action
+    status: Status | None
 
+    original_path: pathlib.Path
+    renamed_path: pathlib.Path | None = None
 
-class SelectDetails(TypedDict):
-    image_url: str | None
-    thumb_image_url: str | None
-    cover_date: str | None
-    site_detail_url: str | None
+    online_results: list[IssueResult] = dataclasses.field(default_factory=list)
+    match_status: MatchStatus | None = None
 
+    md: GenericMetadata | None = None
 
-class CVResult(TypedDict):
-    error: str
-    limit: int
-    offset: int
-    number_of_page_results: int
-    number_of_total_results: int
-    status_code: int
-    results: (
-        CVIssuesResults
-        | CVIssueDetailResults
-        | CVVolumeResults
-        | list[CVIssuesResults]
-        | list[CVVolumeResults]
-        | list[CVIssueDetailResults]
-    )
-    version: str
+    tags_read: list[str] = dataclasses.field(default_factory=list)
+    tags_deleted: list[str] = dataclasses.field(default_factory=list)
+    tags_written: list[str] = dataclasses.field(default_factory=list)
 
-
-class CVImage(TypedDict, total=False):
-    icon_url: str
-    medium_url: str
-    screen_url: str
-    screen_large_url: str
-    small_url: str
-    super_url: Required[str]
-    thumb_url: str
-    tiny_url: str
-    original_url: str
-    image_tags: str
-
-
-class CVVolume(TypedDict):
-    api_detail_url: str
-    id: int
-    name: str
-    site_detail_url: str
-
-
-class CVIssuesResults(TypedDict):
-    cover_date: str
-    description: str
-    id: int
-    image: CVImage
-    issue_number: str
-    name: str
-    site_detail_url: str
-    volume: NotRequired[CVVolume]
-    aliases: str
-
-
-class CVPublisher(TypedDict, total=False):
-    api_detail_url: str
-    id: int
-    name: Required[str]
-
-
-class CVVolumeResults(TypedDict):
-    count_of_issues: int
-    description: NotRequired[str]
-    id: int
-    image: NotRequired[CVImage]
-    name: str
-    publisher: CVPublisher
-    start_year: str
-    resource_type: NotRequired[str]
-    aliases: NotRequired[str | None]
-
-
-class CVCredits(TypedDict):
-    api_detail_url: str
-    id: int
-    name: str
-    site_detail_url: str
-
-
-class CVPersonCredits(TypedDict):
-    api_detail_url: str
-    id: int
-    name: str
-    site_detail_url: str
-    role: str
-
-
-class CVIssueDetailResults(TypedDict):
-    aliases: None
-    api_detail_url: str
-    character_credits: list[CVCredits]
-    character_died_in: None
-    concept_credits: list[CVCredits]
-    cover_date: str
-    date_added: str
-    date_last_updated: str
-    deck: None
-    description: str
-    first_appearance_characters: None
-    first_appearance_concepts: None
-    first_appearance_locations: None
-    first_appearance_objects: None
-    first_appearance_storyarcs: None
-    first_appearance_teams: None
-    has_staff_review: bool
-    id: int
-    image: CVImage
-    issue_number: str
-    location_credits: list[CVCredits]
-    name: str
-    object_credits: list[CVCredits]
-    person_credits: list[CVPersonCredits]
-    site_detail_url: str
-    store_date: str
-    story_arc_credits: list[CVCredits]
-    team_credits: list[CVCredits]
-    team_disbanded_in: None
-    volume: CVVolume
+    def __str__(self) -> str:
+        if len(self.online_results) == 0:
+            matches = None
+        elif len(self.online_results) == 1:
+            matches = str(self.online_results[0])
+        else:
+            matches = "\n" + "".join([f" -  {x}" for x in self.online_results])
+        path_str = utils.path_to_short_str(self.original_path, self.renamed_path)
+        return f"{path_str}: {matches}"