docs(contributor): contrib-readme-action has updated readme

config: always values
setting: always the definition/description not the value

.flake8

@@ -0,0 +1,6 @@
+[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

@@ -0,0 +1,117 @@
+name: CI
+
+env:
+  PIP: pip
+  PYTHON: python
+on:
+  pull_request:
+  push:
+    branches:
+      - '**'
+    tags-ignore:
+      - '**'
+jobs:
+  lint:
+    permissions:
+      checks: write
+      contents: read
+      pull-requests: write
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        python-version: [3.9]
+        os: [ubuntu-latest]
+
+    steps:
+      - uses: actions/checkout@v2
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v2
+        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
+
+      - uses: reviewdog/action-setup@v1
+        with:
+          reviewdog_version: nightly
+      - run: flake8 | reviewdog -f=flake8 -reporter=github-pr-review -tee -level=error -fail-on-error
+        env:
+          REVIEWDOG_GITHUB_API_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+  build-and-test:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        python-version: [3.9]
+        os: [ubuntu-latest, macos-10.15, windows-latest]
+
+    steps:
+      - uses: actions/checkout@v2
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - uses: syphar/restore-virtualenv@v1.2
+        id: cache-virtualenv
+
+      - uses: syphar/restore-pip-download-cache@v1
+        if: steps.cache-virtualenv.outputs.cache-hit != 'true'
+
+      - name: Install build dependencies
+        run: |
+          python -m pip install --upgrade --upgrade-strategy eager -r requirements_dev.txt
+
+      - name: Install Windows build dependencies
+        run: |
+          choco install -y zip
+        if: runner.os == 'Windows'
+      - name: Install macos dependencies
+        run: |
+          brew install icu4c pkg-config
+          export PKG_CONFIG_PATH="/usr/local/opt/icu4c/lib/pkgconfig";
+          export PATH="/usr/local/opt/icu4c/bin:/usr/local/opt/icu4c/sbin:$PATH"
+          python -m pip install --no-binary=pyicu pyicu
+        if: runner.os == 'macOS'
+      - name: Install linux dependencies
+        run: |
+          sudo apt-get install pkg-config libicu-dev
+          export PKG_CONFIG_PATH="/usr/local/opt/icu4c/lib/pkgconfig";
+          export PATH="/usr/local/opt/icu4c/bin:/usr/local/opt/icu4c/sbin:$PATH"
+          python -m pip install --no-binary=pyicu pyicu
+        if: runner.os == 'Linux'
+
+      - name: Build and install PyPi packages
+        run: |
+          make clean pydist
+          python -m pip install "dist/$(python setup.py --fullname)-py3-none-any.whl[all]"
+
+      - name: build
+        run: |
+          make dist
+
+      - name: Archive production artifacts
+        uses: actions/upload-artifact@v2
+        if: runner.os != 'Linux' # linux binary currently has a segfault when running on latest fedora
+        with:
+          name: "${{ format('ComicTagger-{0}', runner.os) }}"
+          path: |
+            dist/*.zip
+
+      - name: PyTest
+        run: |
+          python -m pytest

.github/workflows/contributions.yaml

@@ -0,0 +1,41 @@
+name: Contributions
+on:
+  push:
+    branches:
+      - '**'
+    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: ${{ secrets.GITHUB_TOKEN }}
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Update AUTHORS
+        run: |
+          git config --global log.mailmap true
+          git log --reverse '--format=%aN <%aE>' | cat -n | sort -uk2 | sort -n | cut -f2- >AUTHORS
+
+      - name: Commit and push AUTHORS
+        run: |
+          git pull
+          git config --global user.name "${{ env.CI_COMMIT_AUTHOR }}"
+          git config --global user.email "${{ env.CI_COMMIT_EMAIL }}"
+          git commit -a -m "${{ env.CI_COMMIT_MESSAGE }}"
+          git push

.github/workflows/package.yaml

@@ -0,0 +1,93 @@
+name: Package
+
+env:
+  PIP: pip
+  PYTHON: python
+on:
+  push:
+    tags:
+      - "[0-9]+.[0-9]+.[0-9]+*"
+jobs:
+  package:
+    permissions:
+      contents: write
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        python-version: [3.9]
+        os: [ubuntu-latest, macos-10.15, windows-latest]
+
+    steps:
+      - uses: actions/checkout@v2
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - uses: syphar/restore-virtualenv@v1.2
+        id: cache-virtualenv
+
+      - uses: syphar/restore-pip-download-cache@v1
+        if: steps.cache-virtualenv.outputs.cache-hit != 'true'
+
+      - name: Install build dependencies
+        run: |
+          python -m pip install --upgrade --upgrade-strategy eager -r requirements_dev.txt
+
+      - name: Install Windows build dependencies
+        run: |
+          choco install -y zip
+        if: runner.os == 'Windows'
+      - name: Install macos dependencies
+        run: |
+          brew install icu4c pkg-config
+          export PKG_CONFIG_PATH="/usr/local/opt/icu4c/lib/pkgconfig";
+          export PATH="/usr/local/opt/icu4c/bin:/usr/local/opt/icu4c/sbin:$PATH"
+          python -m pip install --no-binary=pyicu pyicu
+        if: runner.os == 'macOS'
+      - name: Install linux dependencies
+        run: |
+          sudo apt-get install pkg-config libicu-dev
+          export PKG_CONFIG_PATH="/usr/local/opt/icu4c/lib/pkgconfig";
+          export PATH="/usr/local/opt/icu4c/bin:/usr/local/opt/icu4c/sbin:$PATH"
+          python -m pip install --no-binary=pyicu pyicu
+        if: runner.os == 'Linux'
+
+      - name: Build, Install and Test PyPi packages
+        run: |
+          make clean pydist
+          python -m pip install "dist/$(python setup.py --fullname)-py3-none-any.whl[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: ${{ secrets.PYPI_API_TOKEN }}
+          packages_dir: dist
+
+      - name: Build PyInstaller package
+        run: |
+          make dist
+
+      - name: Get release name
+        if: startsWith(github.ref, 'refs/tags/')
+        shell: bash
+        run: |
+          git fetch --depth=1 origin +refs/tags/*:refs/tags/* # github is dumb
+          echo "release_name=$(git tag -l --format "%(refname:strip=2): %(contents:lines=1)" ${{ github.ref_name }})" >> $GITHUB_ENV
+
+      - name: Release
+        uses: softprops/action-gh-release@v1
+        if: startsWith(github.ref, 'refs/tags/')
+        with:
+          name: "${{ env.release_name }}"
+          prerelease: "${{ contains(github.ref, '-') }}" # alpha-releases should be 1.3.0-alpha.x full releases should be 1.3.0
+          draft: false
+          files: |
+            dist/!(*Linux).zip
+            dist/*${{ fromJSON('["never", ""]')[runner.os == 'Linux'] }}.whl

.gitignore

@@ -0,0 +1,160 @@
+# generated by setuptools_scm
+ctversion.py
+
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion
+
+*.iml
+
+## Directory-based project format:
+.idea/
+
+### Other editors
+.*.swp
+nbproject/
+.vscode
+
+comictaggerlib/_version.py
+*.exe
+*.zip
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# 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

@@ -0,0 +1,46 @@
+exclude: ^scripts
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.4.0
+    hooks:
+    -   id: trailing-whitespace
+    -   id: end-of-file-fixer
+    -   id: check-yaml
+    -   id: debug-statements
+    -   id: name-tests-test
+    -   id: requirements-txt-fixer
+-   repo: https://github.com/asottile/setup-cfg-fmt
+    rev: v2.2.0
+    hooks:
+    -   id: setup-cfg-fmt
+-   repo: https://github.com/PyCQA/isort
+    rev: 5.12.0
+    hooks:
+    -   id: isort
+        args: [--af,--add-import, 'from __future__ import annotations']
+-   repo: https://github.com/asottile/pyupgrade
+    rev: v3.3.1
+    hooks:
+    -   id: pyupgrade
+        args: [--py39-plus]
+-   repo: https://github.com/psf/black
+    rev: 23.1.0
+    hooks:
+    -   id: black
+-   repo: https://github.com/PyCQA/autoflake
+    rev: v2.0.1
+    hooks:
+    -   id: autoflake
+        args: [-i, --remove-all-unused-imports, --ignore-init-module-imports]
+-   repo: https://github.com/PyCQA/flake8
+    rev: 6.0.0
+    hooks:
+    -   id: flake8
+        additional_dependencies: [flake8-encodings, flake8-warnings, flake8-builtins, flake8-length, flake8-print]
+-   repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v0.991
+    hooks:
+    -   id: mypy
+        additional_dependencies: [types-setuptools, types-requests]
+ci:
+    skip: [mypy]

.travis.yml

@@ -0,0 +1,59 @@
+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 +1,15 @@
+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>

CONTRIBUTING.md

@@ -0,0 +1,137 @@
+# How to contribute
+
+If your not sure what you can do or you need to ask a question or just want to talk about ComicTagger head over to the [discussions tab](https://github.com/comictagger/comictagger/discussions/categories/general) and start a discussion
+
+## Tests
+
+We have tests written using pytest! Some of them even pass! If you are contributing code any tests you can write are appreciated.
+
+A great place to start is extending the tests that are already made.
+
+For example the file tests/filenames.py has lists of filenames to be parsed in the format:
+```py
+    pytest.param(
+        "Star Wars - War of the Bounty Hunters - IG-88 (2021) (Digital) (Kileko-Empire).cbz",
+        "number ends series, no-issue",
+        {
+            "issue": "",
+            "series": "Star Wars - War of the Bounty Hunters - IG-88",
+            "volume": "",
+            "year": "2021",
+            "remainder": "(Digital) (Kileko-Empire)",
+            "issue_count": "",
+        },
+        marks=pytest.mark.xfail,
+    )
+```
+
+A test consists of 3-4 parts
+1. The filename to be parsed
+2. The reason it might fail
+3. What the result of parsing the filename should be
+4. `marks=pytest.mark.xfail` This marks the test as expected to fail
+
+If you are not comfortable creating a pull request you can [open an issue](https://github.com/comictagger/comictagger/issues/new/choose) or [start a discussion](https://github.com/comictagger/comictagger/discussions/new)
+
+## Submitting changes
+
+Please open a [GitHub Pull Request](https://github.com/comictagger/comictagger/pull/new/develop) with a clear list of what you've done (read more about [pull requests](http://help.github.com/pull-requests/)). When you send a pull request, we will love you forever if you include tests. We can always use more test coverage. Please run the code tools below and make sure all of your commits are atomic (one feature per commit).
+
+## Contributing Code
+
+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 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`
+
+1. Clone the repository
+```
+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:
+
+```
+python3 -m venv --system-site-packages venv
+```
+
+3. Activate the virtual env:
+```
+. venv/bin/activate
+```
+or if on windows PowerShell
+```
+. venv/bin/activate.ps1
+```
+
+4. install dependencies:
+```bash
+pip install -r requirements_dev.txt -r requirements.txt
+# if installing optional dependencies
+pip install -r requirements-GUI.txt -r requirements-CBR.txt
+```
+
+5. install ComicTagger
+```
+pip install .
+```
+
+6. (optionally) run pytest to ensure that their are no failures (xfailed means expected failure)
+```
+$ 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 ===================
+```
+
+7. Make your changes
+8. run code tools and correct any issues
+```bash
+black .
+isort .
+flake8 .
+pytest
+```
+
+black: formats all of the code consistently so there are no surprises<br>
+isort: sorts imports so that you can always find where an import is located<br>
+flake8: checks for code quality and style (warns for unused imports and similar issues)<br>
+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 ===================
+```

MANIFEST.in

@@ -0,0 +1,7 @@
+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

@@ -1,25 +1,64 @@
-TAGGER_BASE := $(HOME)/Dropbox/tagger/comictagger
-VERSION_STR := $(shell grep version $(TAGGER_BASE)/ctversion.py| cut -d= -f2 | sed 's/\"//g')
+PIP ?= pip3
+PYTHON ?= python3
+VERSION_STR := $(shell $(PYTHON) setup.py --version)
 
-all: clean
+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:
-	rm -f *~ *.pyc *.pyo
-	rm -f logdict*.log
-	make -C mac clean
-	make -C windows clean
+	find . -maxdepth 4 -type d -name "__pycache__" -print -depth -exec rm -rf {} \;
+	rm -rf $(PACKAGE_PATH) $(INSTALL_STAMP) build dist MANIFEST comictaggerlib/ctversion.py
+	$(MAKE) -C mac clean
 
-zip:
-	cd release; \
-		rm -rf *zip comictagger-src-$(VERSION_STR) ;  \
-		svn checkout https://comictagger.googlecode.com/svn/trunk/ comictagger-src-$(VERSION_STR); \
-		zip -r comictagger-src-$(VERSION_STR).zip comictagger-src-$(VERSION_STR); \
-		rm -rf comictagger-src-$(VERSION_STR)
-	
-	@echo When satisfied with release, do this:
-	@echo make svn_tag
-	
-svn_tag:
-	svn copy https://comictagger.googlecode.com/svn/trunk \
-      https://comictagger.googlecode.com/svn/tags/$(VERSION_STR) -m "Release $(VERSION_STR)"
-	
+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

@@ -0,0 +1,172 @@
+[![CI](https://github.com/comictagger/comictagger/actions/workflows/build.yaml/badge.svg?branch=develop&event=push)](https://github.com/comictagger/comictagger/actions/workflows/build.yaml)
+[![GitHub release (latest by date)](https://img.shields.io/github/downloads/comictagger/comictagger/latest/total)](https://github.com/comictagger/comictagger/releases/latest)
+[![PyPI](https://img.shields.io/pypi/v/comictagger)](https://pypi.org/project/comictagger/)
+[![PyPI - Downloads](https://img.shields.io/pypi/dm/comictagger)](https://pypistats.org/packages/comictagger)
+[![Chocolatey package](https://img.shields.io/chocolatey/dt/comictagger?color=blue&label=chocolatey)](https://community.chocolatey.org/packages/comictagger)
+[![PyPI - License](https://img.shields.io/pypi/l/comictagger)](https://opensource.org/licenses/Apache-2.0)
+
+[![GitHub Discussions](https://img.shields.io/github/discussions/comictagger/comictagger)](https://github.com/comictagger/comictagger/discussions)
+[![Gitter chat](https://badges.gitter.im/gitterHQ/gitter.png)](https://gitter.im/comictagger/community)
+[![Google Group](https://img.shields.io/badge/discuss-on%20groups-%23207de5)](https://groups.google.com/forum/#!forum/comictagger)
+[![Twitter](https://img.shields.io/badge/%40comictagger-twitter-lightgrey)](https://twitter.com/comictagger)
+[![Facebook](https://img.shields.io/badge/comictagger-facebook-lightgrey)](https://www.facebook.com/ComicTagger-139615369550787/)
+
+# ComicTagger
+
+ComicTagger is a **multi-platform** app for **writing metadata to digital comics**, written in Python and PyQt.
+
+![ComicTagger logo](https://raw.githubusercontent.com/comictagger/comictagger/develop/comictaggerlib/graphics/app.png)
+
+## Features
+
+* Runs on macOS, Microsoft Windows, and Linux systems
+* Get comic information from [Comic Vine](https://comicvine.gamespot.com/)
+* **Automatic issue matching** using advanced image processing techniques
+* **Batch processing** in the GUI for tagging hundreds or more comics at a time
+* Support for **ComicRack** and **ComicBookLover** tagging formats
+* Native full support for **CBZ** digital comics
+* Native read only support for **CBR** digital comics: full support enabled installing additional [rar tools](https://www.rarlab.com/download.htm)
+* Command line interface (CLI) enabling **custom scripting** and **batch operations on large collections**
+
+For details, screen-shots, and more, visit [the Wiki](https://github.com/comictagger/comictagger/wiki)
+
+
+## Installation
+
+### Binaries
+
+Windows 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.
+
+### PIP installation
+
+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]`
+
+### Chocolatey installation (Windows only)
+
+A [Chocolatey package](https://community.chocolatey.org/packages/comictagger), maintained by @Xav83, is provided, you can install it with:
+```powershell
+choco install comictagger
+```
+### From source
+
+ 1. Ensure you have python 3.9 installed
+ 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]`
+
+
+## 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/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>
+    <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></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/Xav83">
+            <img src="https://avatars.githubusercontent.com/u/6787157?v=4" width="100;" alt="Xav83"/>
+            <br />
+            <sub><b>Xav83</b></sub>
+        </a>
+    </td></tr>
+<tr>
+    <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 -->

UnRAR2/UnRARDLL/license.txt

@@ -1,18 +0,0 @@
-      The unrar.dll library is freeware. This means:
-
-   1. All copyrights to RAR and the unrar.dll are exclusively
-      owned by the author - Alexander Roshal.
-
-   2. The unrar.dll library may be used in any software to handle RAR
-      archives without limitations free of charge.
-
-   3. THE RAR ARCHIVER AND THE UNRAR.DLL LIBRARY ARE DISTRIBUTED "AS IS".
-      NO WARRANTY OF ANY KIND IS EXPRESSED OR IMPLIED.  YOU USE AT 
-      YOUR OWN RISK. THE AUTHOR WILL NOT BE LIABLE FOR DATA LOSS, 
-      DAMAGES, LOSS OF PROFITS OR ANY OTHER KIND OF LOSS WHILE USING
-      OR MISUSING THIS SOFTWARE.
-
-      Thank you for your interest in RAR and unrar.dll.
-
-
-                                            Alexander L. Roshal

UnRAR2/UnRARDLL/unrar.h

@@ -1,140 +0,0 @@
-#ifndef _UNRAR_DLL_
-#define _UNRAR_DLL_
-
-#define ERAR_END_ARCHIVE        10
-#define ERAR_NO_MEMORY          11
-#define ERAR_BAD_DATA           12
-#define ERAR_BAD_ARCHIVE        13
-#define ERAR_UNKNOWN_FORMAT     14
-#define ERAR_EOPEN              15
-#define ERAR_ECREATE            16
-#define ERAR_ECLOSE             17
-#define ERAR_EREAD              18
-#define ERAR_EWRITE             19
-#define ERAR_SMALL_BUF          20
-#define ERAR_UNKNOWN            21
-#define ERAR_MISSING_PASSWORD   22
-
-#define RAR_OM_LIST              0
-#define RAR_OM_EXTRACT           1
-#define RAR_OM_LIST_INCSPLIT     2
-
-#define RAR_SKIP              0
-#define RAR_TEST              1
-#define RAR_EXTRACT           2
-
-#define RAR_VOL_ASK           0
-#define RAR_VOL_NOTIFY        1
-
-#define RAR_DLL_VERSION       4
-
-#ifdef _UNIX
-#define CALLBACK
-#define PASCAL
-#define LONG long
-#define HANDLE void *
-#define LPARAM long
-#define UINT unsigned int
-#endif
-
-struct RARHeaderData
-{
-  char         ArcName[260];
-  char         FileName[260];
-  unsigned int Flags;
-  unsigned int PackSize;
-  unsigned int UnpSize;
-  unsigned int HostOS;
-  unsigned int FileCRC;
-  unsigned int FileTime;
-  unsigned int UnpVer;
-  unsigned int Method;
-  unsigned int FileAttr;
-  char         *CmtBuf;
-  unsigned int CmtBufSize;
-  unsigned int CmtSize;
-  unsigned int CmtState;
-};
-
-
-struct RARHeaderDataEx
-{
-  char         ArcName[1024];
-  wchar_t      ArcNameW[1024];
-  char         FileName[1024];
-  wchar_t      FileNameW[1024];
-  unsigned int Flags;
-  unsigned int PackSize;
-  unsigned int PackSizeHigh;
-  unsigned int UnpSize;
-  unsigned int UnpSizeHigh;
-  unsigned int HostOS;
-  unsigned int FileCRC;
-  unsigned int FileTime;
-  unsigned int UnpVer;
-  unsigned int Method;
-  unsigned int FileAttr;
-  char         *CmtBuf;
-  unsigned int CmtBufSize;
-  unsigned int CmtSize;
-  unsigned int CmtState;
-  unsigned int Reserved[1024];
-};
-
-
-struct RAROpenArchiveData
-{
-  char         *ArcName;
-  unsigned int OpenMode;
-  unsigned int OpenResult;
-  char         *CmtBuf;
-  unsigned int CmtBufSize;
-  unsigned int CmtSize;
-  unsigned int CmtState;
-};
-
-struct RAROpenArchiveDataEx
-{
-  char         *ArcName;
-  wchar_t      *ArcNameW;
-  unsigned int OpenMode;
-  unsigned int OpenResult;
-  char         *CmtBuf;
-  unsigned int CmtBufSize;
-  unsigned int CmtSize;
-  unsigned int CmtState;
-  unsigned int Flags;
-  unsigned int Reserved[32];
-};
-
-enum UNRARCALLBACK_MESSAGES {
-  UCM_CHANGEVOLUME,UCM_PROCESSDATA,UCM_NEEDPASSWORD
-};
-
-typedef int (CALLBACK *UNRARCALLBACK)(UINT msg,LPARAM UserData,LPARAM P1,LPARAM P2);
-
-typedef int (PASCAL *CHANGEVOLPROC)(char *ArcName,int Mode);
-typedef int (PASCAL *PROCESSDATAPROC)(unsigned char *Addr,int Size);
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-HANDLE PASCAL RAROpenArchive(struct RAROpenArchiveData *ArchiveData);
-HANDLE PASCAL RAROpenArchiveEx(struct RAROpenArchiveDataEx *ArchiveData);
-int    PASCAL RARCloseArchive(HANDLE hArcData);
-int    PASCAL RARReadHeader(HANDLE hArcData,struct RARHeaderData *HeaderData);
-int    PASCAL RARReadHeaderEx(HANDLE hArcData,struct RARHeaderDataEx *HeaderData);
-int    PASCAL RARProcessFile(HANDLE hArcData,int Operation,char *DestPath,char *DestName);
-int    PASCAL RARProcessFileW(HANDLE hArcData,int Operation,wchar_t *DestPath,wchar_t *DestName);
-void   PASCAL RARSetCallback(HANDLE hArcData,UNRARCALLBACK Callback,LPARAM UserData);
-void   PASCAL RARSetChangeVolProc(HANDLE hArcData,CHANGEVOLPROC ChangeVolProc);
-void   PASCAL RARSetProcessDataProc(HANDLE hArcData,PROCESSDATAPROC ProcessDataProc);
-void   PASCAL RARSetPassword(HANDLE hArcData,char *Password);
-int    PASCAL RARGetDllVersion();
-
-#ifdef __cplusplus
-}
-#endif
-
-#endif

UnRAR2/UnRARDLL/unrardll.txt

@@ -1,606 +0,0 @@
-
-    UnRAR.dll Manual
-    ~~~~~~~~~~~~~~~~
-
-    UnRAR.dll is a 32-bit Windows dynamic-link library which provides
- file extraction from RAR archives.
-
-
-    Exported functions
-
-====================================================================
-HANDLE PASCAL RAROpenArchive(struct RAROpenArchiveData *ArchiveData)
-====================================================================
-
-Description
-~~~~~~~~~~~
-  Open RAR archive and allocate memory structures
-
-Parameters
-~~~~~~~~~~
-ArchiveData       Points to RAROpenArchiveData structure
-
-struct RAROpenArchiveData
-{
-  char *ArcName;
-  UINT OpenMode;
-  UINT OpenResult;
-  char *CmtBuf;
-  UINT CmtBufSize;
-  UINT CmtSize;
-  UINT CmtState;
-};
-
-Structure fields:
-
-ArcName
-  Input parameter which should point to zero terminated string 
-  containing the archive name. 
-
-OpenMode
-  Input parameter.
-
-  Possible values
-
-  RAR_OM_LIST
-    Open archive for reading file headers only.
-
-  RAR_OM_EXTRACT
-    Open archive for testing and extracting files.
-
-  RAR_OM_LIST_INCSPLIT
-    Open archive for reading file headers only. If you open an archive
-    in such mode, RARReadHeader[Ex] will return all file headers,
-    including those with "file continued from previous volume" flag.
-    In case of RAR_OM_LIST such headers are automatically skipped.
-    So if you process RAR volumes in RAR_OM_LIST_INCSPLIT mode, you will
-    get several file header records for same file if file is split between
-    volumes. For such files only the last file header record will contain
-    the correct file CRC and if you wish to get the correct packed size,
-    you need to sum up packed sizes of all parts.
-
-OpenResult
-  Output parameter.
-
-  Possible values
-
-  0                     Success
-  ERAR_NO_MEMORY        Not enough memory to initialize data structures
-  ERAR_BAD_DATA         Archive header broken
-  ERAR_BAD_ARCHIVE      File is not valid RAR archive
-  ERAR_UNKNOWN_FORMAT   Unknown encryption used for archive headers
-  ERAR_EOPEN            File open error
-
-CmtBuf
-  Input parameter which should point to the buffer for archive 
-  comments. Maximum comment size is limited to 64Kb. Comment text is 
-  zero terminated. If the comment text is larger than the buffer 
-  size, the comment text will be truncated. If CmtBuf is set to 
-  NULL, comments will not be read. 
-
-CmtBufSize
-  Input parameter which should contain size of buffer for archive
-  comments.
-
-CmtSize
-  Output parameter containing size of comments actually read into the
-  buffer, cannot exceed CmtBufSize.
-
-CmtState
-  Output parameter.
-
-  Possible values
-
-  0                     comments not present
-  1                     Comments read completely
-  ERAR_NO_MEMORY        Not enough memory to extract comments
-  ERAR_BAD_DATA         Broken comment
-  ERAR_UNKNOWN_FORMAT   Unknown comment format
-  ERAR_SMALL_BUF        Buffer too small, comments not completely read
-
-Return values
-~~~~~~~~~~~~~
-  Archive handle or NULL in case of error
-
-
-========================================================================
-HANDLE PASCAL RAROpenArchiveEx(struct RAROpenArchiveDataEx *ArchiveData)
-========================================================================
-
-Description
-~~~~~~~~~~~
-  Similar to RAROpenArchive, but uses RAROpenArchiveDataEx structure
-  allowing to specify Unicode archive name and returning information
-  about archive flags.
-
-Parameters
-~~~~~~~~~~
-ArchiveData       Points to RAROpenArchiveDataEx structure
-
-struct RAROpenArchiveDataEx
-{
-  char         *ArcName;
-  wchar_t      *ArcNameW;
-  unsigned int OpenMode;
-  unsigned int OpenResult;
-  char         *CmtBuf;
-  unsigned int CmtBufSize;
-  unsigned int CmtSize;
-  unsigned int CmtState;
-  unsigned int Flags;
-  unsigned int Reserved[32];
-};
-
-Structure fields:
-
-ArcNameW
-  Input parameter which should point to zero terminated Unicode string
-  containing the archive name or NULL if Unicode name is not specified.
-
-Flags
-  Output parameter. Combination of bit flags.
-
-  Possible values
-
-    0x0001  - Volume attribute (archive volume)
-    0x0002  - Archive comment present
-    0x0004  - Archive lock attribute
-    0x0008  - Solid attribute (solid archive)
-    0x0010  - New volume naming scheme ('volname.partN.rar')
-    0x0020  - Authenticity information present
-    0x0040  - Recovery record present
-    0x0080  - Block headers are encrypted
-    0x0100  - First volume (set only by RAR 3.0 and later)
-
-Reserved[32]
-  Reserved for future use. Must be zero.
-
-Information on other structure fields and function return values
-is available above, in RAROpenArchive function description.
-
-
-====================================================================
-int PASCAL RARCloseArchive(HANDLE hArcData)
-====================================================================
-
-Description
-~~~~~~~~~~~
-  Close RAR archive and release allocated memory. It must be called when
-  archive processing is finished, even if the archive processing was stopped
-  due to an error.
-
-Parameters
-~~~~~~~~~~
-hArcData
-  This parameter should contain the archive handle obtained from the
-  RAROpenArchive function call.
-
-Return values
-~~~~~~~~~~~~~
-  0                     Success
-  ERAR_ECLOSE           Archive close error
-
-
-====================================================================
-int PASCAL RARReadHeader(HANDLE hArcData,
-                         struct RARHeaderData *HeaderData)
-====================================================================
-
-Description
-~~~~~~~~~~~
-  Read header of file in archive.
-
-Parameters
-~~~~~~~~~~
-hArcData
-  This parameter should contain the archive handle obtained from the
-  RAROpenArchive function call.
-
-HeaderData
-  It should point to RARHeaderData structure:
-
-struct RARHeaderData
-{
-  char ArcName[260];
-  char FileName[260];
-  UINT Flags;
-  UINT PackSize;
-  UINT UnpSize;
-  UINT HostOS;
-  UINT FileCRC;
-  UINT FileTime;
-  UINT UnpVer;
-  UINT Method;
-  UINT FileAttr;
-  char *CmtBuf;
-  UINT CmtBufSize;
-  UINT CmtSize;
-  UINT CmtState;
-};
-
-Structure fields:
-
-ArcName
-  Output parameter which contains a zero terminated string of the
-  current archive name.  May be used to determine the current volume 
-  name. 
-
-FileName
-  Output parameter which contains a zero terminated string of the 
-  file name in OEM (DOS) encoding.
-
-Flags
-  Output parameter which contains file flags:
-
-  0x01 - file continued from previous volume
-  0x02 - file continued on next volume
-  0x04 - file encrypted with password
-  0x08 - file comment present
-  0x10 - compression of previous files is used (solid flag)
-
-  bits 7 6 5
-
-       0 0 0    - dictionary size   64 Kb
-       0 0 1    - dictionary size  128 Kb
-       0 1 0    - dictionary size  256 Kb
-       0 1 1    - dictionary size  512 Kb
-       1 0 0    - dictionary size 1024 Kb
-       1 0 1    - dictionary size 2048 KB
-       1 1 0    - dictionary size 4096 KB
-       1 1 1    - file is directory
-
-  Other bits are reserved.
-
-PackSize
-  Output parameter means packed file size or size of the
-  file part if file was split between volumes.
-
-UnpSize
-  Output parameter - unpacked file size.
-
-HostOS
-  Output parameter - operating system used for archiving:
-
-  0 - MS DOS;
-  1 - OS/2.
-  2 - Win32
-  3 - Unix
-
-FileCRC
-  Output parameter which contains unpacked file CRC. In case of file parts
-  split between volumes only the last part contains the correct CRC
-  and it is accessible only in RAR_OM_LIST_INCSPLIT listing mode.
-
-FileTime
-  Output parameter - contains date and time in standard MS DOS format.
-
-UnpVer
-  Output parameter - RAR version needed to extract file.
-  It is encoded as 10 * Major version + minor version.
-
-Method
-  Output parameter - packing method.
-
-FileAttr
-  Output parameter - file attributes.
-
-CmtBuf
-  File comments support is not implemented in the new DLL version yet.
-  Now CmtState is always 0.
-
-/*
- * Input parameter which should point to the buffer for file
- * comments. Maximum comment size is limited to 64Kb. Comment text is 
- * a zero terminated string in OEM encoding. If the comment text is
- * larger than the buffer size, the comment text will be truncated.
- * If CmtBuf is set to NULL, comments will not be read. 
- */
-
-CmtBufSize
-  Input parameter which should contain size of buffer for archive
-  comments.
-
-CmtSize
-  Output parameter containing size of comments actually read into the
-  buffer, should not exceed CmtBufSize.
-
-CmtState
-  Output parameter.
-
-  Possible values
-
-  0                     Absent comments
-  1                     Comments read completely
-  ERAR_NO_MEMORY        Not enough memory to extract comments
-  ERAR_BAD_DATA         Broken comment
-  ERAR_UNKNOWN_FORMAT   Unknown comment format
-  ERAR_SMALL_BUF        Buffer too small, comments not completely read
-
-Return values
-~~~~~~~~~~~~~
-
-  0                     Success
-  ERAR_END_ARCHIVE      End of archive
-  ERAR_BAD_DATA         File header broken
-
-
-====================================================================
-int PASCAL RARReadHeaderEx(HANDLE hArcData,
-                           struct RARHeaderDataEx *HeaderData)
-====================================================================
-
-Description
-~~~~~~~~~~~
-  Similar to RARReadHeader, but uses RARHeaderDataEx structure,
-containing information about Unicode file names and 64 bit file sizes.
-
-struct RARHeaderDataEx
-{
-  char         ArcName[1024];
-  wchar_t      ArcNameW[1024];
-  char         FileName[1024];
-  wchar_t      FileNameW[1024];
-  unsigned int Flags;
-  unsigned int PackSize;
-  unsigned int PackSizeHigh;
-  unsigned int UnpSize;
-  unsigned int UnpSizeHigh;
-  unsigned int HostOS;
-  unsigned int FileCRC;
-  unsigned int FileTime;
-  unsigned int UnpVer;
-  unsigned int Method;
-  unsigned int FileAttr;
-  char         *CmtBuf;
-  unsigned int CmtBufSize;
-  unsigned int CmtSize;
-  unsigned int CmtState;
-  unsigned int Reserved[1024];
-};
-
-
-====================================================================
-int PASCAL RARProcessFile(HANDLE hArcData,
-                          int Operation,
-                          char *DestPath,
-                          char *DestName)
-====================================================================
-
-Description
-~~~~~~~~~~~
-  Performs action and moves the current position in the archive to 
-  the next file. Extract or test the current file from the archive 
-  opened in RAR_OM_EXTRACT mode. If the mode RAR_OM_LIST is set, 
-  then a call to this function will simply skip the archive position 
-  to the next file. 
-
-Parameters
-~~~~~~~~~~
-hArcData
-  This parameter should contain the archive handle obtained from the
-  RAROpenArchive function call.
-
-Operation
-  File operation.
-
-  Possible values
-
-  RAR_SKIP              Move to the next file in the archive. If the 
-                        archive is solid and RAR_OM_EXTRACT mode was set 
-                        when the archive was opened, the current file will 
-                        be processed - the operation will be performed 
-                        slower than a simple seek. 
-
-  RAR_TEST              Test the current file and move to the next file in 
-                        the archive. If the archive was opened with 
-                        RAR_OM_LIST mode, the operation is equal to 
-                        RAR_SKIP. 
-
-  RAR_EXTRACT           Extract the current file and move to the next file.
-                        If the archive was opened with RAR_OM_LIST mode,
-                        the operation is equal to RAR_SKIP.
-
-
-DestPath
-  This parameter should point to a zero terminated string containing the 
-  destination directory to which to extract files to. If DestPath is equal 
-  to NULL, it means extract to the current directory. This parameter has 
-  meaning only if DestName is NULL. 
-
-DestName
-  This parameter should point to a string containing the full path and name
-  to assign to extracted file or it can be NULL to use the default name.
-  If DestName is defined (not NULL), it overrides both the original file
-  name saved in the archive and path specigied in DestPath setting. 
-
-  Both DestPath and DestName must be in OEM encoding. If necessary,
-  use CharToOem to convert text to OEM before passing to this function.
-
-Return values
-~~~~~~~~~~~~~
-  0                     Success
-  ERAR_BAD_DATA         File CRC error
-  ERAR_BAD_ARCHIVE      Volume is not valid RAR archive
-  ERAR_UNKNOWN_FORMAT   Unknown archive format
-  ERAR_EOPEN            Volume open error
-  ERAR_ECREATE          File create error
-  ERAR_ECLOSE           File close error
-  ERAR_EREAD            Read error
-  ERAR_EWRITE           Write error
-
-
-Note: if you wish to cancel extraction, return -1 when processing
-      UCM_PROCESSDATA callback message.
-
-
-====================================================================
-int PASCAL RARProcessFileW(HANDLE hArcData,
-                           int Operation,
-                           wchar_t *DestPath,
-                           wchar_t *DestName)
-====================================================================
-
-Description
-~~~~~~~~~~~
-  Unicode version of RARProcessFile. It uses Unicode DestPath
-  and DestName parameters, other parameters and return values
-  are the same as in RARProcessFile.
-
-
-====================================================================
-void PASCAL RARSetCallback(HANDLE hArcData,
-            int PASCAL (*CallbackProc)(UINT msg,LPARAM UserData,LPARAM P1,LPARAM P2),
-            LPARAM UserData);
-====================================================================
-
-Description
-~~~~~~~~~~~
-  Set a user-defined callback function to process Unrar events.
-
-Parameters
-~~~~~~~~~~
-hArcData
-  This parameter should contain the archive handle obtained from the
-  RAROpenArchive function call.
-
-CallbackProc
-  It should point to a user-defined callback function.
-
-  The function will be passed four parameters:
-
-
-  msg                    Type of event. Described below.
-
-  UserData               User defined value passed to RARSetCallback.
-
-  P1 and P2              Event dependent parameters. Described below.
-
-
-  Possible events
-
-    UCM_CHANGEVOLUME     Process volume change.
-
-      P1                   Points to the zero terminated name
-                           of the next volume.
-
-      P2                   The function call mode:
-
-        RAR_VOL_ASK          Required volume is absent. The function should
-                             prompt user and return a positive value
-                             to retry or return -1 value to terminate 
-                             operation. The function may also specify a new 
-                             volume name, placing it to the address specified
-                             by P1 parameter. 
-
-        RAR_VOL_NOTIFY       Required volume is successfully opened.
-                             This is a notification call and volume name
-                             modification is not allowed. The function should 
-                             return a positive value to continue or -1
-                             to terminate operation. 
-
-    UCM_PROCESSDATA          Process unpacked data. It may be used to read
-                             a file while it is being extracted or tested
-                             without actual extracting file to disk.
-                             Return a positive value to continue process
-                             or -1 to cancel the archive operation
-
-      P1                   Address pointing to the unpacked data.
-                           Function may refer to the data but must not
-                           change it.
-
-      P2                   Size of the unpacked data. It is guaranteed
-                           only that the size will not exceed the maximum
-                           dictionary size (4 Mb in RAR 3.0).
-
-    UCM_NEEDPASSWORD         DLL needs a password to process archive.
-                             This message must be processed if you wish
-                             to be able to handle archives with encrypted
-                             file names. It can be also used as replacement
-                             of RARSetPassword function even for usual
-                             encrypted files with non-encrypted names.
-
-      P1                   Address pointing to the buffer for a password.
-                           You need to copy a password here.
-
-      P2                   Size of the password buffer.
-
-
-UserData
-  User data passed to callback function.
-
-  Other functions of UnRAR.dll should not be called from the callback
-  function.
-
-Return values
-~~~~~~~~~~~~~
-  None
-
-
-
-====================================================================
-void PASCAL RARSetChangeVolProc(HANDLE hArcData,
-            int PASCAL (*ChangeVolProc)(char *ArcName,int Mode));
-====================================================================
-
-Obsoleted, use RARSetCallback instead.
-
-
-
-====================================================================
-void PASCAL RARSetProcessDataProc(HANDLE hArcData,
-            int PASCAL (*ProcessDataProc)(unsigned char *Addr,int Size))
-====================================================================
-
-Obsoleted, use RARSetCallback instead.
-
-
-====================================================================
-void PASCAL RARSetPassword(HANDLE hArcData,
-                           char *Password);
-====================================================================
-
-Description
-~~~~~~~~~~~
-  Set a password to decrypt files.
-
-Parameters
-~~~~~~~~~~
-hArcData
-  This parameter should contain the archive handle obtained from the
-  RAROpenArchive function call.
-
-Password
-  It should point to a string containing a zero terminated password.
-
-Return values
-~~~~~~~~~~~~~
-  None
-
-
-====================================================================
-void PASCAL RARGetDllVersion();
-====================================================================
-
-Description
-~~~~~~~~~~~
-  Returns API version.
-
-Parameters
-~~~~~~~~~~
-  None.
-
-Return values
-~~~~~~~~~~~~~
-  Returns an integer value denoting UnRAR.dll API version, which is also
-defined in unrar.h as RAR_DLL_VERSION. API version number is incremented
-only in case of noticeable changes in UnRAR.dll API. Do not confuse it
-with version of UnRAR.dll stored in DLL resources, which is incremented
-with every DLL rebuild.
-
-  If RARGetDllVersion() returns a value lower than UnRAR.dll which your
-application was designed for, it may indicate that DLL version is too old
-and it will fail to provide all necessary functions to your application.
-
-  This function is absent in old versions of UnRAR.dll, so it is safer
-to use LoadLibrary and GetProcAddress to access this function.
-

UnRAR2/UnRARDLL/whatsnew.txt

@@ -1,80 +0,0 @@
-List of unrar.dll API changes. We do not include performance and reliability
-improvements into this list, but this library and RAR/UnRAR tools share
-the same source code. So the latest version of unrar.dll usually contains
-same decompression algorithm changes as the latest UnRAR version.
-============================================================================
-
---  18 January 2008
-
-all LONG parameters of CallbackProc function were changed
-to LPARAM type for 64 bit mode compatibility.
-
-
---  12 December 2007
-
-Added new RAR_OM_LIST_INCSPLIT open mode for function RAROpenArchive.
-
-
---  14 August 2007
-
-Added NoCrypt\unrar_nocrypt.dll without decryption code for those
-applications where presence of encryption or decryption code is not
-allowed because of legal restrictions.
-
-
---  14 December 2006
-
-Added ERAR_MISSING_PASSWORD error type. This error is returned
-if empty password is specified for encrypted file.
-
-
---  12 June 2003
-
-Added RARProcessFileW function, Unicode version of RARProcessFile
-
-
---  9 August 2002
-
-Added RAROpenArchiveEx function allowing to specify Unicode archive
-name and get archive flags.
-
-
---  24 January 2002
-
-Added RARReadHeaderEx function allowing to read Unicode file names
-and 64 bit file sizes.
-
-
---  23 January 2002
-
-Added ERAR_UNKNOWN error type (it is used for all errors which
-do not have special ERAR code yet) and UCM_NEEDPASSWORD callback
-message.
-
-Unrar.dll automatically opens all next volumes not only when extracting,
-but also in RAR_OM_LIST mode.
-
-
---  27 November 2001
-
-RARSetChangeVolProc and RARSetProcessDataProc are replaced by
-the single callback function installed with RARSetCallback.
-Unlike old style callbacks, the new function accepts the user defined
-parameter. Unrar.dll still supports RARSetChangeVolProc and
-RARSetProcessDataProc for compatibility purposes, but if you write
-a new application, better use RARSetCallback.
-
-File comments support is not implemented in the new DLL version yet.
-Now CmtState is always 0.
-
-
---  13 August 2001
-
-Added RARGetDllVersion function, so you may distinguish old unrar.dll,
-which used C style callback functions and the new one with PASCAL callbacks.
-
-
---  10 May 2001
-
-Callback functions in RARSetChangeVolProc and RARSetProcessDataProc
-use PASCAL style call convention now.

UnRAR2/UnRARDLL/x64/readme.txt

@@ -1 +0,0 @@
-This is x64 version of unrar.dll.

UnRAR2/__init__.py

@@ -1,177 +0,0 @@
-# Copyright (c) 2003-2005 Jimmy Retzlaff, 2008 Konstantin Yegupov
-#
-# Permission is hereby granted, free of charge, to any person obtaining
-# a copy of this software and associated documentation files (the
-# "Software"), to deal in the Software without restriction, including
-# without limitation the rights to use, copy, modify, merge, publish,
-# distribute, sublicense, and/or sell copies of the Software, and to
-# permit persons to whom the Software is furnished to do so, subject to
-# the following conditions:
-#
-# The above copyright notice and this permission notice shall be
-# included in all copies or substantial portions of the Software.
-#
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
-# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
-# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
-# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
-# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-# SOFTWARE.
-
-"""
-pyUnRAR2 is a ctypes based wrapper around the free UnRAR.dll. 
-
-It is an modified version of Jimmy Retzlaff's pyUnRAR - more simple,
-stable and foolproof.
-Notice that it has INCOMPATIBLE interface.
-
-It enables reading and unpacking of archives created with the
-RAR/WinRAR archivers. There is a low-level interface which is very
-similar to the C interface provided by UnRAR. There is also a
-higher level interface which makes some common operations easier.
-"""
-
-__version__ = '0.99.2'
-
-try:
-    WindowsError
-    in_windows = True
-except NameError:
-    in_windows = False
-
-if in_windows:
-    from windows import RarFileImplementation
-else:
-    from unix import RarFileImplementation
-    
-    
-import fnmatch, time, weakref
-
-class RarInfo(object):
-    """Represents a file header in an archive. Don't instantiate directly.
-    Use only to obtain information about file.
-    YOU CANNOT EXTRACT FILE CONTENTS USING THIS OBJECT.
-    USE METHODS OF RarFile CLASS INSTEAD.
-
-    Properties:
-        index - index of file within the archive
-        filename - name of the file in the archive including path (if any)
-        datetime - file date/time as a struct_time suitable for time.strftime
-        isdir - True if the file is a directory
-        size - size in bytes of the uncompressed file
-        comment - comment associated with the file
-        
-    Note - this is not currently intended to be a Python file-like object.
-    """
-
-    def __init__(self, rarfile, data):
-        self.rarfile = weakref.proxy(rarfile)
-        self.index = data['index']
-        self.filename = data['filename']
-        self.isdir = data['isdir']
-        self.size = data['size']
-        self.datetime = data['datetime']
-        self.comment = data['comment']
-            
-
-
-    def __str__(self):
-        try :
-            arcName = self.rarfile.archiveName
-        except ReferenceError:
-            arcName = "[ARCHIVE_NO_LONGER_LOADED]"
-        return '<RarInfo "%s" in "%s">' % (self.filename, arcName)
-
-class RarFile(RarFileImplementation):
-
-    def __init__(self, archiveName, password=None):
-        """Instantiate the archive.
-
-        archiveName is the name of the RAR file.
-        password is used to decrypt the files in the archive.
-
-        Properties:
-            comment - comment associated with the archive
-
-        >>> print RarFile('test.rar').comment
-        This is a test.
-        """
-        self.archiveName = archiveName
-        RarFileImplementation.init(self, password)
-
-    def __del__(self):
-        self.destruct()
-
-    def infoiter(self):
-        """Iterate over all the files in the archive, generating RarInfos.
-
-        >>> import os
-        >>> for fileInArchive in RarFile('test.rar').infoiter():
-        ...     print os.path.split(fileInArchive.filename)[-1],
-        ...     print fileInArchive.isdir,
-        ...     print fileInArchive.size,
-        ...     print fileInArchive.comment,
-        ...     print tuple(fileInArchive.datetime)[0:5],
-        ...     print time.strftime('%a, %d %b %Y %H:%M', fileInArchive.datetime)
-        test True 0 None (2003, 6, 30, 1, 59) Mon, 30 Jun 2003 01:59
-        test.txt False 20 None (2003, 6, 30, 2, 1) Mon, 30 Jun 2003 02:01
-        this.py False 1030 None (2002, 2, 8, 16, 47) Fri, 08 Feb 2002 16:47
-        """
-        for params in RarFileImplementation.infoiter(self):
-            yield RarInfo(self, params)
-
-    def infolist(self):
-        """Return a list of RarInfos, descripting the contents of the archive."""
-        return list(self.infoiter())
-
-    def read_files(self, condition='*'):
-        """Read specific files from archive into memory.
-        If "condition" is a list of numbers, then return files which have those positions in infolist.
-        If "condition" is a string, then it is treated as a wildcard for names of files to extract.
-        If "condition" is a function, it is treated as a callback function, which accepts a RarInfo object 
-            and returns boolean True (extract) or False (skip).
-        If "condition" is omitted, all files are returned.
-        
-        Returns list of tuples (RarInfo info, str contents)
-        """
-        checker = condition2checker(condition)
-        return RarFileImplementation.read_files(self, checker)
-        
-
-    def extract(self,  condition='*', path='.', withSubpath=True, overwrite=True):
-        """Extract specific files from archive to disk.
-        
-        If "condition" is a list of numbers, then extract files which have those positions in infolist.
-        If "condition" is a string, then it is treated as a wildcard for names of files to extract.
-        If "condition" is a function, it is treated as a callback function, which accepts a RarInfo object
-            and returns either boolean True (extract) or boolean False (skip).
-        DEPRECATED: If "condition" callback returns string (only supported for Windows) - 
-            that string will be used as a new name to save the file under.
-        If "condition" is omitted, all files are extracted.
-        
-        "path" is a directory to extract to
-        "withSubpath" flag denotes whether files are extracted with their full path in the archive.
-        "overwrite" flag denotes whether extracted files will overwrite old ones. Defaults to true.
-        
-        Returns list of RarInfos for extracted files."""
-        checker = condition2checker(condition)
-        return RarFileImplementation.extract(self, checker, path, withSubpath, overwrite)
-
-def condition2checker(condition):
-    """Converts different condition types to callback"""
-    if type(condition) in [str, unicode]:
-        def smatcher(info):
-            return fnmatch.fnmatch(info.filename, condition)
-        return smatcher
-    elif type(condition) in [list, tuple] and type(condition[0]) in [int, long]:
-        def imatcher(info):
-            return info.index in condition
-        return imatcher
-    elif callable(condition):
-        return condition
-    else:
-        raise TypeError
-
-

UnRAR2/rar_exceptions.py

@@ -1,30 +0,0 @@
-# Copyright (c) 2003-2005 Jimmy Retzlaff, 2008 Konstantin Yegupov
-#
-# Permission is hereby granted, free of charge, to any person obtaining
-# a copy of this software and associated documentation files (the
-# "Software"), to deal in the Software without restriction, including
-# without limitation the rights to use, copy, modify, merge, publish,
-# distribute, sublicense, and/or sell copies of the Software, and to
-# permit persons to whom the Software is furnished to do so, subject to
-# the following conditions:
-#
-# The above copyright notice and this permission notice shall be
-# included in all copies or substantial portions of the Software.
-#
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
-# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
-# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
-# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
-# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-# SOFTWARE.
-
-# Low level interface - see UnRARDLL\UNRARDLL.TXT
-
-
-class ArchiveHeaderBroken(Exception): pass
-class InvalidRARArchive(Exception): pass
-class FileOpenError(Exception): pass
-class IncorrectRARPassword(Exception): pass
-class InvalidRARArchiveUsage(Exception): pass

UnRAR2/test_UnRAR2.py

@@ -1,139 +0,0 @@
-import os, sys
-
-import UnRAR2
-from UnRAR2.rar_exceptions import *
-
-
-def cleanup(dir='test'):
-    for path, dirs, files in os.walk(dir):
-        for fn in files:
-            os.remove(os.path.join(path, fn))
-        for dir in dirs:
-            os.removedirs(os.path.join(path, dir))
-
-
-
-
-
-# reuse RarArchive object, en
-cleanup()
-rarc = UnRAR2.RarFile('test.rar')
-rarc.infolist()
-for info in rarc.infoiter():
-    saveinfo = info
-    assert (str(info)=="""<RarInfo "test" in "test.rar">""")
-    break
-rarc.extract()
-assert os.path.exists('test'+os.sep+'test.txt')
-assert os.path.exists('test'+os.sep+'this.py')
-del rarc
-assert (str(saveinfo)=="""<RarInfo "test" in "[ARCHIVE_NO_LONGER_LOADED]">""")
-cleanup()
-
-# extract all the files in test.rar
-cleanup()
-UnRAR2.RarFile('test.rar').extract()
-assert os.path.exists('test'+os.sep+'test.txt')
-assert os.path.exists('test'+os.sep+'this.py')
-cleanup()
-
-# extract all the files in test.rar matching the wildcard *.txt
-cleanup()
-UnRAR2.RarFile('test.rar').extract('*.txt')
-assert os.path.exists('test'+os.sep+'test.txt')
-assert not os.path.exists('test'+os.sep+'this.py')
-cleanup()
-
-
-# check the name and size of each file, extracting small ones
-cleanup()
-archive = UnRAR2.RarFile('test.rar')
-assert archive.comment == 'This is a test.'
-archive.extract(lambda rarinfo: rarinfo.size <= 1024)
-for rarinfo in archive.infoiter():
-    if rarinfo.size <= 1024 and not rarinfo.isdir:
-        assert rarinfo.size == os.stat(rarinfo.filename).st_size
-assert file('test'+os.sep+'test.txt', 'rt').read() == 'This is only a test.'
-assert not os.path.exists('test'+os.sep+'this.py')
-cleanup()
-
-
-# extract this.py, overriding it's destination
-cleanup('test2')
-archive = UnRAR2.RarFile('test.rar')
-archive.extract('*.py', 'test2', False)
-assert os.path.exists('test2'+os.sep+'this.py')
-cleanup('test2')
-
-
-# extract test.txt to memory
-cleanup()
-archive = UnRAR2.RarFile('test.rar')
-entries = UnRAR2.RarFile('test.rar').read_files('*test.txt')
-assert len(entries)==1
-assert entries[0][0].filename.endswith('test.txt')
-assert entries[0][1]=='This is only a test.'
-
-
-# extract all the files in test.rar with overwriting
-cleanup()
-fo = open('test'+os.sep+'test.txt',"wt")
-fo.write("blah")
-fo.close()
-UnRAR2.RarFile('test.rar').extract('*.txt')
-assert open('test'+os.sep+'test.txt',"rt").read()!="blah"
-cleanup()
-
-# extract all the files in test.rar without overwriting
-cleanup()
-fo = open('test'+os.sep+'test.txt',"wt")
-fo.write("blahblah")
-fo.close()
-UnRAR2.RarFile('test.rar').extract('*.txt', overwrite = False)
-assert open('test'+os.sep+'test.txt',"rt").read()=="blahblah"
-cleanup()
-
-# list big file in an archive
-list(UnRAR2.RarFile('test_nulls.rar').infoiter())
-
-# extract files from an archive with protected files
-cleanup()
-UnRAR2.RarFile('test_protected_files.rar', password="protected").extract()
-assert os.path.exists('test'+os.sep+'top_secret_xxx_file.txt')
-cleanup()
-errored = False
-try:
-    UnRAR2.RarFile('test_protected_files.rar', password="proteqted").extract()
-except IncorrectRARPassword:
-    errored = True
-assert not os.path.exists('test'+os.sep+'top_secret_xxx_file.txt')
-assert errored
-cleanup()
-
-# extract files from an archive with protected headers
-cleanup()
-UnRAR2.RarFile('test_protected_headers.rar', password="secret").extract()
-assert os.path.exists('test'+os.sep+'top_secret_xxx_file.txt')
-cleanup()
-errored = False
-try:
-    UnRAR2.RarFile('test_protected_headers.rar', password="seqret").extract()
-except IncorrectRARPassword:
-    errored = True
-assert not os.path.exists('test'+os.sep+'top_secret_xxx_file.txt')
-assert errored
-cleanup()
-
-# make sure docstring examples are working
-import doctest
-doctest.testmod(UnRAR2)
-
-# update documentation
-import pydoc
-pydoc.writedoc(UnRAR2)
-
-# cleanup
-try:
-    os.remove('__init__.pyc')
-except:
-    pass

UnRAR2/unix.py

@@ -1,175 +0,0 @@
-# Copyright (c) 2003-2005 Jimmy Retzlaff, 2008 Konstantin Yegupov
-#
-# Permission is hereby granted, free of charge, to any person obtaining
-# a copy of this software and associated documentation files (the
-# "Software"), to deal in the Software without restriction, including
-# without limitation the rights to use, copy, modify, merge, publish,
-# distribute, sublicense, and/or sell copies of the Software, and to
-# permit persons to whom the Software is furnished to do so, subject to
-# the following conditions:
-#
-# The above copyright notice and this permission notice shall be
-# included in all copies or substantial portions of the Software.
-#
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
-# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
-# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
-# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
-# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-# SOFTWARE.
-
-# Unix version uses unrar command line executable
-
-import subprocess
-import gc
-
-import os, os.path
-import time, re
-
-from rar_exceptions import *
-
-class UnpackerNotInstalled(Exception): pass
-
-rar_executable_cached = None
-
-def call_unrar(params):
-    "Calls rar/unrar command line executable, returns stdout pipe"
-    global rar_executable_cached
-    if rar_executable_cached is None:
-        for command in ('unrar', 'rar'):
-            try:
-                subprocess.Popen([command], stdout=subprocess.PIPE)
-                rar_executable_cached = command
-                break
-            except OSError:
-                pass
-        if rar_executable_cached is None:
-            raise UnpackerNotInstalled("No suitable RAR unpacker installed")
-            
-    assert type(params) == list, "params must be list"
-    args = [rar_executable_cached] + params
-    try:
-        gc.disable() # See http://bugs.python.org/issue1336
-        return subprocess.Popen(args, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
-    finally:
-        gc.enable()
-
-class RarFileImplementation(object):
-
-    def init(self, password=None):
-        self.password = password
-        
-        
-
-        stdoutdata, stderrdata = self.call('v', []).communicate()
-        
-        for line in stderrdata.splitlines():
-            if line.strip().startswith("Cannot open"):
-                raise FileOpenError
-            if line.find("CRC failed")>=0:
-                raise IncorrectRARPassword   
-        accum = []
-        source = iter(stdoutdata.splitlines())
-        line = ''
-        while not (line.startswith('Comment:') or line.startswith('Pathname/Comment')):
-            if line.strip().endswith('is not RAR archive'):
-                raise InvalidRARArchive
-            line = source.next()
-        while not line.startswith('Pathname/Comment'):
-            accum.append(line.rstrip('\n'))
-            line = source.next()
-        if len(accum):
-            accum[0] = accum[0][9:]
-            self.comment = '\n'.join(accum[:-1])
-        else:
-            self.comment = None
-                
-    def escaped_password(self):
-        return '-' if self.password == None else self.password
-        
-        
-    def call(self, cmd, options=[], files=[]):
-        options2 = options + ['p'+self.escaped_password()]
-        soptions = ['-'+x for x in options2]
-        return call_unrar([cmd]+soptions+['--',self.archiveName]+files)
-
-    def infoiter(self):
-        
-        stdoutdata, stderrdata = self.call('v', ['c-']).communicate()
-        
-        for line in stderrdata.splitlines():
-            if line.strip().startswith("Cannot open"):
-                raise FileOpenError
-            
-        accum = []
-        source = iter(stdoutdata.splitlines())
-        line = ''
-        while not line.startswith('--------------'):
-            if line.strip().endswith('is not RAR archive'):
-                raise InvalidRARArchive
-            if line.find("CRC failed")>=0:
-                raise IncorrectRARPassword  
-            line = source.next()
-        line = source.next()
-        i = 0
-        re_spaces = re.compile(r"\s+")
-        while not line.startswith('--------------'):
-            accum.append(line)
-            if len(accum)==2:
-                data = {}
-                data['index'] = i
-                data['filename'] = accum[0].strip()
-                info = re_spaces.split(accum[1].strip())
-                data['size'] = int(info[0])
-                attr = info[5]
-                data['isdir'] = 'd' in attr.lower()
-                data['datetime'] = time.strptime(info[3]+" "+info[4], '%d-%m-%y %H:%M')
-                data['comment'] = None
-                yield data
-                accum = []
-                i += 1
-            line = source.next()
-
-    def read_files(self, checker):
-        res = []
-        for info in self.infoiter():
-            checkres = checker(info)
-            if checkres==True and not info.isdir:
-                pipe = self.call('p', ['inul'], [info.filename]).stdout
-                res.append((info, pipe.read()))
-        return res            
-
-          
-    def extract(self, checker, path, withSubpath, overwrite):
-        res = []
-        command = 'x'
-        if not withSubpath:
-            command = 'e'
-        options = []
-        if overwrite:
-            options.append('o+')
-        else:
-			options.append('o-')
-        if not path.endswith(os.sep):
-            path += os.sep
-        names = []
-        for info in self.infoiter():
-            checkres = checker(info)
-            if type(checkres) in [str, unicode]:
-                raise NotImplementedError("Condition callbacks returning strings are deprecated and only supported in Windows")
-            if checkres==True and not info.isdir:
-                names.append(info.filename)
-                res.append(info)
-        names.append(path)
-        proc = self.call(command, options, names)
-        stdoutdata, stderrdata = proc.communicate()
-        if stderrdata.find("CRC failed")>=0:
-            raise IncorrectRARPassword  
-        return res            
-            
-    def destruct(self):
-        pass
-
-    

UnRAR2/windows.py

@@ -1,309 +0,0 @@
-# Copyright (c) 2003-2005 Jimmy Retzlaff, 2008 Konstantin Yegupov
-#
-# Permission is hereby granted, free of charge, to any person obtaining
-# a copy of this software and associated documentation files (the
-# "Software"), to deal in the Software without restriction, including
-# without limitation the rights to use, copy, modify, merge, publish,
-# distribute, sublicense, and/or sell copies of the Software, and to
-# permit persons to whom the Software is furnished to do so, subject to
-# the following conditions:
-#
-# The above copyright notice and this permission notice shall be
-# included in all copies or substantial portions of the Software.
-#
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
-# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
-# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
-# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
-# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-# SOFTWARE.
-
-# Low level interface - see UnRARDLL\UNRARDLL.TXT
-
-from __future__ import generators
-
-import ctypes, ctypes.wintypes
-import os, os.path, sys
-import Queue
-import time
-
-from rar_exceptions import *
-
-ERAR_END_ARCHIVE = 10
-ERAR_NO_MEMORY = 11
-ERAR_BAD_DATA = 12
-ERAR_BAD_ARCHIVE = 13
-ERAR_UNKNOWN_FORMAT = 14
-ERAR_EOPEN = 15
-ERAR_ECREATE = 16
-ERAR_ECLOSE = 17
-ERAR_EREAD = 18
-ERAR_EWRITE = 19
-ERAR_SMALL_BUF = 20
-ERAR_UNKNOWN = 21
-
-RAR_OM_LIST = 0
-RAR_OM_EXTRACT = 1
-
-RAR_SKIP = 0
-RAR_TEST = 1
-RAR_EXTRACT = 2
-
-RAR_VOL_ASK = 0
-RAR_VOL_NOTIFY = 1
-
-RAR_DLL_VERSION = 3
-
-# enum UNRARCALLBACK_MESSAGES
-UCM_CHANGEVOLUME = 0
-UCM_PROCESSDATA = 1
-UCM_NEEDPASSWORD = 2
-
-architecture_bits = ctypes.sizeof(ctypes.c_voidp)*8
-dll_name = "unrar.dll"
-if architecture_bits == 64:
-    dll_name = "x64\\unrar64.dll"
-    
-    
-try:
-    unrar = ctypes.WinDLL(os.path.join(os.path.split(__file__)[0], 'UnRARDLL', dll_name))
-except WindowsError:
-    unrar = ctypes.WinDLL(dll_name)
-
-
-class RAROpenArchiveDataEx(ctypes.Structure):
-    def __init__(self, ArcName=None, ArcNameW=u'', OpenMode=RAR_OM_LIST):
-        self.CmtBuf = ctypes.c_buffer(64*1024)
-        ctypes.Structure.__init__(self, ArcName=ArcName, ArcNameW=ArcNameW, OpenMode=OpenMode, _CmtBuf=ctypes.addressof(self.CmtBuf), CmtBufSize=ctypes.sizeof(self.CmtBuf))
-
-    _fields_ = [
-                ('ArcName', ctypes.c_char_p),
-                ('ArcNameW', ctypes.c_wchar_p),
-                ('OpenMode', ctypes.c_uint),
-                ('OpenResult', ctypes.c_uint),
-                ('_CmtBuf', ctypes.c_voidp),
-                ('CmtBufSize', ctypes.c_uint),
-                ('CmtSize', ctypes.c_uint),
-                ('CmtState', ctypes.c_uint),
-                ('Flags', ctypes.c_uint),
-                ('Reserved', ctypes.c_uint*32),
-               ]
-
-class RARHeaderDataEx(ctypes.Structure):
-    def __init__(self):
-        self.CmtBuf = ctypes.c_buffer(64*1024)
-        ctypes.Structure.__init__(self, _CmtBuf=ctypes.addressof(self.CmtBuf), CmtBufSize=ctypes.sizeof(self.CmtBuf))
-
-    _fields_ = [
-                ('ArcName', ctypes.c_char*1024),
-                ('ArcNameW', ctypes.c_wchar*1024),
-                ('FileName', ctypes.c_char*1024),
-                ('FileNameW', ctypes.c_wchar*1024),
-                ('Flags', ctypes.c_uint),
-                ('PackSize', ctypes.c_uint),
-                ('PackSizeHigh', ctypes.c_uint),
-                ('UnpSize', ctypes.c_uint),
-                ('UnpSizeHigh', ctypes.c_uint),
-                ('HostOS', ctypes.c_uint),
-                ('FileCRC', ctypes.c_uint),
-                ('FileTime', ctypes.c_uint),
-                ('UnpVer', ctypes.c_uint),
-                ('Method', ctypes.c_uint),
-                ('FileAttr', ctypes.c_uint),
-                ('_CmtBuf', ctypes.c_voidp),
-                ('CmtBufSize', ctypes.c_uint),
-                ('CmtSize', ctypes.c_uint),
-                ('CmtState', ctypes.c_uint),
-                ('Reserved', ctypes.c_uint*1024),
-               ]
-
-def DosDateTimeToTimeTuple(dosDateTime):
-    """Convert an MS-DOS format date time to a Python time tuple.
-    """
-    dosDate = dosDateTime >> 16
-    dosTime = dosDateTime & 0xffff
-    day = dosDate & 0x1f
-    month = (dosDate >> 5) & 0xf
-    year = 1980 + (dosDate >> 9)
-    second = 2*(dosTime & 0x1f)
-    minute = (dosTime >> 5) & 0x3f
-    hour = dosTime >> 11
-    return time.localtime(time.mktime((year, month, day, hour, minute, second, 0, 1, -1)))
-
-def _wrap(restype, function, argtypes):
-    result = function
-    result.argtypes = argtypes
-    result.restype = restype
-    return result
-
-RARGetDllVersion = _wrap(ctypes.c_int, unrar.RARGetDllVersion, [])
-
-RAROpenArchiveEx = _wrap(ctypes.wintypes.HANDLE, unrar.RAROpenArchiveEx, [ctypes.POINTER(RAROpenArchiveDataEx)])
-
-RARReadHeaderEx = _wrap(ctypes.c_int, unrar.RARReadHeaderEx, [ctypes.wintypes.HANDLE, ctypes.POINTER(RARHeaderDataEx)])
-
-_RARSetPassword = _wrap(ctypes.c_int, unrar.RARSetPassword, [ctypes.wintypes.HANDLE, ctypes.c_char_p])
-def RARSetPassword(*args, **kwargs):
-    _RARSetPassword(*args, **kwargs)
-
-RARProcessFile = _wrap(ctypes.c_int, unrar.RARProcessFile, [ctypes.wintypes.HANDLE, ctypes.c_int, ctypes.c_char_p, ctypes.c_char_p])
-
-RARCloseArchive = _wrap(ctypes.c_int, unrar.RARCloseArchive, [ctypes.wintypes.HANDLE])
-
-UNRARCALLBACK = ctypes.WINFUNCTYPE(ctypes.c_int, ctypes.c_uint, ctypes.c_long, ctypes.c_long, ctypes.c_long)
-RARSetCallback = _wrap(ctypes.c_int, unrar.RARSetCallback, [ctypes.wintypes.HANDLE, UNRARCALLBACK, ctypes.c_long])
-
-
-
-RARExceptions = {
-                 ERAR_NO_MEMORY : MemoryError,
-                 ERAR_BAD_DATA : ArchiveHeaderBroken,
-                 ERAR_BAD_ARCHIVE : InvalidRARArchive,
-                 ERAR_EOPEN : FileOpenError,
-                }
-
-class PassiveReader:
-    """Used for reading files to memory"""
-    def __init__(self, usercallback = None):
-        self.buf = []
-        self.ucb = usercallback
-    
-    def _callback(self, msg, UserData, P1, P2):
-        if msg == UCM_PROCESSDATA:
-            data = (ctypes.c_char*P2).from_address(P1).raw
-            if self.ucb!=None:
-                self.ucb(data)
-            else:
-                self.buf.append(data)
-        return 1
-    
-    def get_result(self):
-        return ''.join(self.buf)
-
-class RarInfoIterator(object):
-    def __init__(self, arc):
-        self.arc = arc
-        self.index = 0
-        self.headerData = RARHeaderDataEx()
-        self.res = RARReadHeaderEx(self.arc._handle, ctypes.byref(self.headerData))
-        if self.res==ERAR_BAD_DATA:
-            raise IncorrectRARPassword
-        self.arc.lockStatus = "locked"
-        self.arc.needskip = False
-        
-    def __iter__(self):
-        return self
-        
-    def next(self):
-        if self.index>0:
-            if self.arc.needskip:
-                RARProcessFile(self.arc._handle, RAR_SKIP, None, None)
-            self.res = RARReadHeaderEx(self.arc._handle, ctypes.byref(self.headerData))
-
-        if self.res:
-            raise StopIteration 
-        self.arc.needskip = True
-        
-        data = {}
-        data['index'] = self.index
-        data['filename'] = self.headerData.FileName
-        data['datetime'] = DosDateTimeToTimeTuple(self.headerData.FileTime)
-        data['isdir'] = ((self.headerData.Flags & 0xE0) == 0xE0)
-        data['size'] = self.headerData.UnpSize + (self.headerData.UnpSizeHigh << 32)
-        if self.headerData.CmtState == 1:
-            data['comment'] = self.headerData.CmtBuf.value
-        else:
-            data['comment'] = None
-        self.index += 1
-        return data
-
-            
-    def __del__(self):
-        self.arc.lockStatus = "finished"
-
-def generate_password_provider(password):
-    def password_provider_callback(msg, UserData, P1, P2):
-        if msg == UCM_NEEDPASSWORD and password!=None:
-            (ctypes.c_char*P2).from_address(P1).value = password
-        return 1
-    return password_provider_callback
-
-class RarFileImplementation(object):
-
-    def init(self, password=None):
-        self.password = password
-        archiveData = RAROpenArchiveDataEx(ArcNameW=self.archiveName, OpenMode=RAR_OM_EXTRACT)
-        self._handle = RAROpenArchiveEx(ctypes.byref(archiveData))
-        self.c_callback = UNRARCALLBACK(generate_password_provider(self.password))
-        RARSetCallback(self._handle, self.c_callback, 1)
-
-        if archiveData.OpenResult != 0:
-            raise RARExceptions[archiveData.OpenResult]
-
-        if archiveData.CmtState == 1:
-            self.comment = archiveData.CmtBuf.value
-        else:
-            self.comment = None
-
-        if password:
-            RARSetPassword(self._handle, password)
-            
-        self.lockStatus = "ready"
-            
-
-
-    def destruct(self):
-        if self._handle and RARCloseArchive:
-            RARCloseArchive(self._handle)
-
-    def make_sure_ready(self):
-        if self.lockStatus == "locked":
-            raise InvalidRARArchiveUsage("cannot execute infoiter() without finishing previous one")
-        if self.lockStatus == "finished":
-            self.destruct()
-            self.init(self.password)
-
-    def infoiter(self):
-        self.make_sure_ready()
-        return RarInfoIterator(self)
-
-    def read_files(self, checker):
-        res = []
-        for info in self.infoiter():
-            if checker(info) and not info.isdir:
-                reader = PassiveReader()
-                c_callback = UNRARCALLBACK(reader._callback)
-                RARSetCallback(self._handle, c_callback, 1)
-                tmpres = RARProcessFile(self._handle, RAR_TEST, None, None)
-                if tmpres==ERAR_BAD_DATA:
-                    raise IncorrectRARPassword
-                self.needskip = False
-                res.append((info, reader.get_result()))
-        return res
-        
-
-    def extract(self,  checker, path, withSubpath, overwrite):
-        res = []
-        for info in self.infoiter():
-            checkres = checker(info)
-            if checkres!=False and not info.isdir:
-                if checkres==True:
-                    fn = info.filename
-                    if not withSubpath:
-                        fn = os.path.split(fn)[-1]
-                    target = os.path.join(path, fn)
-                else:
-                    raise DeprecationWarning, "Condition callbacks returning strings are deprecated and only supported in Windows"                    
-                    target = checkres
-                if overwrite or (not os.path.exists(target)):
-                    tmpres = RARProcessFile(self._handle, RAR_EXTRACT, None, target)
-                    if tmpres==ERAR_BAD_DATA:
-                        raise IncorrectRARPassword
-
-                self.needskip = False
-                res.append(info)
-        return res
-
-

autotagmatchwindow.py

@@ -1,202 +0,0 @@
-"""
-A PyQT4 dialog to select from automated issue matches
-"""
-
-"""
-Copyright 2012  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.
-"""
-
-import sys
-import os
-from PyQt4 import QtCore, QtGui, uic
-
-from PyQt4.QtCore import QUrl, pyqtSignal, QByteArray
-
-from imagefetcher import  ImageFetcher
-from settings import ComicTaggerSettings
-
-class AutoTagMatchWindow(QtGui.QDialog):
-	
-	volume_id = 0
-	
-	def __init__(self, parent, match_set_list, style, fetch_func):
-		super(AutoTagMatchWindow, self).__init__(parent)
-		
-		uic.loadUi(os.path.join(ComicTaggerSettings.baseDir(), 'autotagmatchwindow.ui' ), self)
-
-		self.skipButton = QtGui.QPushButton(self.tr("Skip"))
-		self.buttonBox.addButton(self.skipButton, QtGui.QDialogButtonBox.ActionRole)		
-		self.buttonBox.button(QtGui.QDialogButtonBox.Ok).setText("Accept and Next")		
-
-		self.match_set_list = match_set_list
-		self.style = style
-		self.fetch_func = fetch_func
-
-		self.current_match_set_idx = 0
-		
-		self.twList.currentItemChanged.connect(self.currentItemChanged)	
-		self.twList.cellDoubleClicked.connect(self.cellDoubleClicked)
-		self.skipButton.clicked.connect(self.skipToNext)
-		
-		self.updateData()		
-
-	def updateData( self):
-
-		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 ):
-			self.skipButton.setDisabled(True)
-			
-		self.setCoverImage()
-		self.populateTable()
-		self.twList.resizeColumnsToContents()	
-		self.current_row = 0
-		self.twList.selectRow( 0 )
-		
-		path = self.current_match_set.ca.path
-		self.setWindowTitle( "Select correct match ({0} of {1}): {2}".format(
-						self.current_match_set_idx+1,
-						len( self.match_set_list ),
-						os.path.split(path)[1] ))
-		
-	def populateTable( self  ):
-
-		while self.twList.rowCount() > 0:
-			self.twList.removeRow(0)
-		
-		self.twList.setSortingEnabled(False)
-
-		row = 0
-		for match in self.current_match_set.matches: 
-			self.twList.insertRow(row)
-			
-			item_text = match['series']  
-			item = QtGui.QTableWidgetItem(item_text)			
-			item.setFlags(QtCore.Qt.ItemIsSelectable| QtCore.Qt.ItemIsEnabled)
-			self.twList.setItem(row, 0, item)
-
-			if match['publisher'] is not None:
-				item_text = u"{0}".format(match['publisher'])
-			else:
-				item_text = u"Unknown"
-			item = QtGui.QTableWidgetItem(item_text)
-			item.setFlags(QtCore.Qt.ItemIsSelectable| QtCore.Qt.ItemIsEnabled)
-			self.twList.setItem(row, 1, item)
-			
-			item_text = ""
-			if match['month'] is not None:
-				item_text = u"{0}/".format(match['month'])
-			if match['year'] is not None:
-				item_text += u"{0}".format(match['year'])
-			else:
-				item_text += u"????"
-			item = QtGui.QTableWidgetItem(item_text)			
-			item.setFlags(QtCore.Qt.ItemIsSelectable| QtCore.Qt.ItemIsEnabled)
-			self.twList.setItem(row, 2, item)
-			
-			row += 1
-			
-
-	def cellDoubleClicked( self, r, c ):
-		self.accept()
-			
-	def currentItemChanged( self, curr, prev ):
-
-		if curr is None:
-			return
-		if prev is not None and prev.row() == curr.row():
-				return
-
-		self.current_row = curr.row()
-		
-		# list selection was changed, update the the issue cover				
-		self.labelThumbnail.setPixmap(QtGui.QPixmap(os.path.join(ComicTaggerSettings.baseDir(), 'graphics/nocover.png' )))
-				
-		self.cover_fetcher = ImageFetcher( )
-		self.cover_fetcher.fetchComplete.connect(self.coverFetchComplete)
-		self.cover_fetcher.fetch( self.current_match_set.matches[self.current_row]['img_url'] )
-				
-	# called when the image is done loading
-	def coverFetchComplete( self, image_data, issue_id ):
-		img = QtGui.QImage()
-		img.loadFromData( image_data )
-		self.labelThumbnail.setPixmap(QtGui.QPixmap(img))
-		
-	def setCoverImage( self ):
-		ca = self.current_match_set.ca
-		cover_idx = ca.readMetadata(self.style).getCoverPageIndexList()[0]
-		image_data = ca.getPage( cover_idx )		
-		self.labelCover.setScaledContents(True)
-		if image_data is not None:
-			img = QtGui.QImage()
-			img.loadFromData( image_data )
-			self.labelCover.setPixmap(QtGui.QPixmap(img))
-		else:
-			self.labelCover.setPixmap(QtGui.QPixmap(os.path.join(ComicTaggerSettings.baseDir(), 'graphics/nocover.png' )))
-
-	def accept(self):
-
-		self.saveMatch()
-		self.current_match_set_idx += 1
-		
-		if self.current_match_set_idx == len( self.match_set_list ):
-			# no more items
-			QtGui.QDialog.accept(self)				
-		else:
-			self.updateData()
-
-	def skipToNext( self ):
-		self.current_match_set_idx += 1
-		
-		if self.current_match_set_idx == len( self.match_set_list ):
-			# no more items
-			QtGui.QDialog.reject(self)				
-		else:
-			self.updateData()
-		
-	def reject(self):
-		reply = QtGui.QMessageBox.question(self, 
-			 self.tr("Cancel Matching"), 
-			 self.tr("Are you sure you wish to cancel the matching process?"),
-			 QtGui.QMessageBox.Yes, QtGui.QMessageBox.No )
-			 
-		if reply == QtGui.QMessageBox.No:
-			return
-
-		QtGui.QDialog.reject(self)				
-			
-	def saveMatch( self ):
-		
-		match = self.current_match_set.matches[self.current_row]
-		ca = self.current_match_set.ca
-
-		md = ca.readMetadata( self.style )
-		if md.isEmpty:
-			md = ca.metadataFromFilename()		
-		
-		# now get the particular issue data
-		cv_md = self.fetch_func( match )
-		if cv_md is None:
-			QtGui.QMessageBox.critical(self, self.tr("Network Issue"), self.tr("Could not connect to ComicVine to get issue details!"))
-			return
-
-		QtGui.QApplication.setOverrideCursor(QtGui.QCursor(QtCore.Qt.WaitCursor))			
-		md.overlay( cv_md )
-		success = ca.writeMetadata( md, self.style )
-		QtGui.QApplication.restoreOverrideCursor()
-		
-		if not success:		
-			QtGui.QMessageBox.warning(self, self.tr("Write Error"), self.tr("Saving the tags to the archive seemed to fail!"))

autotagmatchwindow.ui

@@ -1,161 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<ui version="4.0">
- <class>dialogMatchSelect</class>
- <widget class="QDialog" name="dialogMatchSelect">
-  <property name="geometry">
-   <rect>
-    <x>0</x>
-    <y>0</y>
-    <width>831</width>
-    <height>506</height>
-   </rect>
-  </property>
-  <property name="windowTitle">
-   <string>Select Match</string>
-  </property>
-  <layout class="QGridLayout" name="gridLayout">
-   <item row="0" column="1">
-    <layout class="QVBoxLayout" name="verticalLayout">
-     <item>
-      <layout class="QHBoxLayout" name="horizontalLayout">
-       <item>
-        <widget class="QLabel" name="labelCover">
-         <property name="minimumSize">
-          <size>
-           <width>200</width>
-           <height>0</height>
-          </size>
-         </property>
-         <property name="maximumSize">
-          <size>
-           <width>200</width>
-           <height>300</height>
-          </size>
-         </property>
-         <property name="text">
-          <string>TextLabel</string>
-         </property>
-        </widget>
-       </item>
-       <item>
-        <widget class="QTableWidget" name="twList">
-         <property name="font">
-          <font>
-           <pointsize>9</pointsize>
-          </font>
-         </property>
-         <property name="selectionMode">
-          <enum>QAbstractItemView::SingleSelection</enum>
-         </property>
-         <property name="selectionBehavior">
-          <enum>QAbstractItemView::SelectRows</enum>
-         </property>
-         <property name="rowCount">
-          <number>0</number>
-         </property>
-         <property name="columnCount">
-          <number>3</number>
-         </property>
-         <attribute name="horizontalHeaderStretchLastSection">
-          <bool>true</bool>
-         </attribute>
-         <attribute name="verticalHeaderVisible">
-          <bool>false</bool>
-         </attribute>
-         <column>
-          <property name="text">
-           <string>Series</string>
-          </property>
-         </column>
-         <column>
-          <property name="text">
-           <string>Publisher</string>
-          </property>
-         </column>
-         <column>
-          <property name="text">
-           <string>Date</string>
-          </property>
-         </column>
-        </widget>
-       </item>
-       <item>
-        <widget class="QLabel" name="labelThumbnail">
-         <property name="minimumSize">
-          <size>
-           <width>200</width>
-           <height>0</height>
-          </size>
-         </property>
-         <property name="maximumSize">
-          <size>
-           <width>200</width>
-           <height>300</height>
-          </size>
-         </property>
-         <property name="frameShape">
-          <enum>QFrame::Panel</enum>
-         </property>
-         <property name="frameShadow">
-          <enum>QFrame::Sunken</enum>
-         </property>
-         <property name="text">
-          <string/>
-         </property>
-         <property name="scaledContents">
-          <bool>true</bool>
-         </property>
-        </widget>
-       </item>
-      </layout>
-     </item>
-     <item>
-      <widget class="QDialogButtonBox" name="buttonBox">
-       <property name="orientation">
-        <enum>Qt::Horizontal</enum>
-       </property>
-       <property name="standardButtons">
-        <set>QDialogButtonBox::Cancel|QDialogButtonBox::Ok</set>
-       </property>
-      </widget>
-     </item>
-    </layout>
-   </item>
-  </layout>
- </widget>
- <resources/>
- <connections>
-  <connection>
-   <sender>buttonBox</sender>
-   <signal>accepted()</signal>
-   <receiver>dialogMatchSelect</receiver>
-   <slot>accept()</slot>
-   <hints>
-    <hint type="sourcelabel">
-     <x>248</x>
-     <y>254</y>
-    </hint>
-    <hint type="destinationlabel">
-     <x>157</x>
-     <y>274</y>
-    </hint>
-   </hints>
-  </connection>
-  <connection>
-   <sender>buttonBox</sender>
-   <signal>rejected()</signal>
-   <receiver>dialogMatchSelect</receiver>
-   <slot>reject()</slot>
-   <hints>
-    <hint type="sourcelabel">
-     <x>316</x>
-     <y>260</y>
-    </hint>
-    <hint type="destinationlabel">
-     <x>286</x>
-     <y>274</y>
-    </hint>
-   </hints>
-  </connection>
- </connections>
-</ui>

autotagprogresswindow.py

@@ -1,67 +0,0 @@
-"""
-A PyQT4 dialog to show ID log and progress
-"""
-
-"""
-Copyright 2012  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.
-"""
-
-import sys
-from PyQt4 import QtCore, QtGui, uic
-import os
-from settings import ComicTaggerSettings
-
-
-class AutoTagProgressWindow(QtGui.QDialog):
-	
-	
-	def __init__(self, parent):
-		super(AutoTagProgressWindow, self).__init__(parent)
-		
-		uic.loadUi(os.path.join(ComicTaggerSettings.baseDir(), 'autotagprogresswindow.ui' ), self)
-		self.lblTest.setPixmap(QtGui.QPixmap(os.path.join(ComicTaggerSettings.baseDir(), 'graphics/nocover.png' )))
-		self.lblArchive.setPixmap(QtGui.QPixmap(os.path.join(ComicTaggerSettings.baseDir(), 'graphics/nocover.png' )))
-		self.isdone = False
-		
-		# we can't specify relative font sizes in the UI designer, so
-		# make font for scroll window a smidge smaller
-		f = self.textEdit.font()
-		if f.pointSize() > 10:
-			f.setPointSize( f.pointSize() - 2 )
-		self.textEdit.setFont( f )		
-		
-	def setArchiveImage( self, img_data):
-		self.setCoverImage( img_data, self.lblArchive )
-
-	def setTestImage( self, img_data):
-		self.setCoverImage( img_data, self.lblTest )
-
-	def setCoverImage( self, img_data , label):
-		if img_data is not None:
-			img = QtGui.QImage()
-			img.loadFromData( img_data )
-			label.setPixmap(QtGui.QPixmap(img))
-			label.setScaledContents(True)
-		else:
-			label.setPixmap(QtGui.QPixmap(os.path.join(ComicTaggerSettings.baseDir(), 'graphics/nocover.png' )))
-			label.setScaledContents(True)
-		QtCore.QCoreApplication.processEvents()
-		QtCore.QCoreApplication.processEvents()
-			
-	def reject(self):
-		QtGui.QDialog.reject(self)		
-		self.isdone = True
-
-		

autotagstartwindow.py

@@ -1,55 +0,0 @@
-"""
-A PyQT4 dialog to confirm and set options for auto-tag
-"""
-
-"""
-Copyright 2012  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 PyQt4 import QtCore, QtGui, uic
-from settings import ComicTaggerSettings
-from settingswindow import SettingsWindow
-from filerenamer import FileRenamer
-import os
-import utils
-
-	
-class AutoTagStartWindow(QtGui.QDialog):
-		
-	def __init__( self, parent,  settings, msg ):
-		super(AutoTagStartWindow, self).__init__(parent)
-		
-		uic.loadUi(os.path.join(ComicTaggerSettings.baseDir(), 'autotagstartwindow.ui' ), self)
-		self.label.setText( msg )
-
-		self.settings = settings
-		
-		self.cbxSaveOnLowConfidence.setCheckState( QtCore.Qt.Unchecked )
-		self.cbxDontUseYear.setCheckState( QtCore.Qt.Unchecked )
-		self.cbxAssumeIssueOne.setCheckState( QtCore.Qt.Unchecked )
-		
-		self.autoSaveOnLow = False
-		self.dontUseYear = False
-		self.assumeIssueOne = False
-
-
-	def accept( self ):
-		QtGui.QDialog.accept(self)		
-
-		self.autoSaveOnLow = self.cbxSaveOnLowConfidence.isChecked()
-		self.dontUseYear = self.cbxDontUseYear.isChecked()
-		self.assumeIssueOne = self.cbxAssumeIssueOne.isChecked()
-	

autotagstartwindow.ui

@@ -1,124 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<ui version="4.0">
- <class>dialogExport</class>
- <widget class="QDialog" name="dialogExport">
-  <property name="windowModality">
-   <enum>Qt::NonModal</enum>
-  </property>
-  <property name="geometry">
-   <rect>
-    <x>0</x>
-    <y>0</y>
-    <width>524</width>
-    <height>248</height>
-   </rect>
-  </property>
-  <property name="windowTitle">
-   <string>Auto-Tag</string>
-  </property>
-  <property name="modal">
-   <bool>false</bool>
-  </property>
-  <layout class="QGridLayout" name="gridLayout_3">
-   <item row="0" column="0">
-    <layout class="QVBoxLayout" name="verticalLayout">
-     <item>
-      <widget class="QLabel" name="label">
-       <property name="sizePolicy">
-        <sizepolicy hsizetype="Preferred" vsizetype="Preferred">
-         <horstretch>0</horstretch>
-         <verstretch>0</verstretch>
-        </sizepolicy>
-       </property>
-       <property name="text">
-        <string/>
-       </property>
-       <property name="wordWrap">
-        <bool>true</bool>
-       </property>
-      </widget>
-     </item>
-     <item>
-      <layout class="QFormLayout" name="formLayout">
-       <property name="fieldGrowthPolicy">
-        <enum>QFormLayout::AllNonFixedFieldsGrow</enum>
-       </property>
-       <item row="1" column="1">
-        <widget class="QCheckBox" name="cbxDontUseYear">
-         <property name="text">
-          <string>Don't use publication year in indentification process</string>
-         </property>
-        </widget>
-       </item>
-       <item row="0" column="1">
-        <widget class="QCheckBox" name="cbxSaveOnLowConfidence">
-         <property name="sizePolicy">
-          <sizepolicy hsizetype="Minimum" vsizetype="Preferred">
-           <horstretch>0</horstretch>
-           <verstretch>0</verstretch>
-          </sizepolicy>
-         </property>
-         <property name="text">
-          <string>Save on low confidence match</string>
-         </property>
-        </widget>
-       </item>
-       <item row="2" column="1">
-        <widget class="QCheckBox" name="cbxAssumeIssueOne">
-         <property name="text">
-          <string>If no issue number, assume &quot;1&quot;</string>
-         </property>
-        </widget>
-       </item>
-      </layout>
-     </item>
-     <item>
-      <widget class="QDialogButtonBox" name="buttonBox">
-       <property name="orientation">
-        <enum>Qt::Horizontal</enum>
-       </property>
-       <property name="standardButtons">
-        <set>QDialogButtonBox::Cancel|QDialogButtonBox::Ok</set>
-       </property>
-      </widget>
-     </item>
-    </layout>
-   </item>
-  </layout>
- </widget>
- <resources/>
- <connections>
-  <connection>
-   <sender>buttonBox</sender>
-   <signal>accepted()</signal>
-   <receiver>dialogExport</receiver>
-   <slot>accept()</slot>
-   <hints>
-    <hint type="sourcelabel">
-     <x>346</x>
-     <y>187</y>
-    </hint>
-    <hint type="destinationlabel">
-     <x>277</x>
-     <y>104</y>
-    </hint>
-   </hints>
-  </connection>
-  <connection>
-   <sender>buttonBox</sender>
-   <signal>rejected()</signal>
-   <receiver>dialogExport</receiver>
-   <slot>reject()</slot>
-   <hints>
-    <hint type="sourcelabel">
-     <x>346</x>
-     <y>187</y>
-    </hint>
-    <hint type="destinationlabel">
-     <x>277</x>
-     <y>104</y>
-    </hint>
-   </hints>
-  </connection>
- </connections>
-</ui>

cbltransformer.py

@@ -1,99 +0,0 @@
-"""
-Class to manage modifying metadata specifically for CBL/CBI
-"""
-
-"""
-Copyright 2012  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.
-"""
-
-import os
-import utils
-
-
-class CBLTransformer:
-	def __init__( self, metadata, settings ):
-		self.metadata = metadata
-		self.settings = settings
-
-	
-	def apply( self ):
-		# helper funcs
-		def append_to_tags_if_unique( item ):
-			if item.lower() not in (tag.lower() for tag in self.metadata.tags):
-				self.metadata.tags.append( item )
-				
-		def add_string_list_to_tags( str_list ):
-			if str_list is not None and 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:
-		
-			# helper
-			def setLonePrimary( role_list ):
-				lone_credit = None
-				count = 0
-				for c in self.metadata.credits:
-					if c['role'].lower() 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
-				return lone_credit, count
-				
-			#need to loop three times, once for 'writer', 'artist', and then 'penciler' if no artist
-			setLonePrimary( ['writer'] )
-			c, count = setLonePrimary( ['artist'] )
-			if c is None and count == 0:
-				c, count = setLonePrimary( ['penciler', 'penciller'] )
-				if c is not None:
-					c['primary'] = False
-					self.metadata.addCredit( c['person'], 'Artist', True )		
-
-		if self.settings.copy_characters_to_tags:
-			add_string_list_to_tags( self.metadata.characters )
-
-		if self.settings.copy_teams_to_tags:
-			add_string_list_to_tags( self.metadata.teams )
-			
-		if self.settings.copy_locations_to_tags:
-			add_string_list_to_tags( self.metadata.locations )
-			
-		if self.settings.copy_notes_to_comments:
-			if self.metadata.notes is not None:
-				if self.metadata.comments is None:
-					self.metadata.comments = ""
-				else:
-					self.metadata.comments += "\n\n"
-				if self.metadata.notes not in self.metadata.comments:
-					self.metadata.comments += self.metadata.notes
-
-		if self.settings.copy_weblink_to_comments:
-			if self.metadata.webLink is not None:
-				if self.metadata.comments is None:
-					self.metadata.comments = ""
-				else:
-					self.metadata.comments += "\n\n"
-				if self.metadata.webLink not in self.metadata.comments:
-					self.metadata.comments += self.metadata.webLink
-
-		return self.metadata
-
-	
-	

comet.py

@@ -1,260 +0,0 @@
-"""
-A python class to encapsulate CoMet data 
-"""
-
-"""
-Copyright 2012  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 datetime import datetime
-import zipfile
-from pprint import pprint 
-import xml.etree.ElementTree as ET
-from genericmetadata import GenericMetadata
-import utils
-
-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 metadataFromString( self, string ):
-
-		tree = ET.ElementTree(ET.fromstring( string ))
-		return self.convertXMLToMetadata( tree )
-
-	def stringFromMetadata( self, metadata ):
-
-		header = '<?xml version="1.0" encoding="UTF-8"?>\n'
-		
-		tree = self.convertMetadataToXML( self, metadata )
-		return header + ET.tostring(tree.getroot())
-
-	def indent( self, elem, level=0 ):
-		# for making the XML output readable
-		i = "\n" + level*"  "
-		if len(elem):
-			if not elem.text or not elem.text.strip():
-				elem.text = i + "  "
-			if not elem.tail or not elem.tail.strip():
-				elem.tail = i
-			for elem in elem:
-				self.indent( elem, level+1 )
-			if not elem.tail or not elem.tail.strip():
-				elem.tail = i
-		else:
-			if level and (not elem.tail or not elem.tail.strip()):
-				elem.tail = i
-	
-	def convertMetadataToXML( self, filename, metadata ):
-
-		#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, md_entry):
-			if md_entry is not None:
-				ET.SubElement(root, comet_entry).text = u"{0}".format(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.pageCount )
-		assign( 'format', md.format )
-		assign( 'language', md.language )
-		assign( 'rating', md.maturityRating )
-		assign( 'price', md.price )
-		assign( 'isVersionOf', md.isVersionOf )
-		assign( 'rights', md.rights )
-		assign( 'identifier', md.identifier )
-		assign( 'lastMark', md.lastMark )		
-		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")
-		
-		date_str = ""
-		if md.year is not None:
-			date_str = str(md.year).zfill(4) 
-			if md.month is not None:
-				date_str += "-" + str(md.month).zfill(2)
-			assign( 'date', date_str )  
-
-		assign( 'coverImage', md.coverImage )
-
-		# need to specially process the credits, since they are structured differently than CIX	
-		credit_writer_list    = list()
-		credit_penciller_list = list()
-		credit_inker_list     = list()
-		credit_colorist_list  = list()
-		credit_letterer_list  = list()
-		credit_cover_list     = list()
-		credit_editor_list    = list()
-		
-		#  loop thru credits, and build a list for each role that CoMet supports
-		for credit in metadata.credits:
-
-			if credit['role'].lower() in set( self.writer_synonyms ):
-				ET.SubElement(root, 'writer').text = u"{0}".format(credit['person'])
-
-			if credit['role'].lower() in set( self.penciller_synonyms ):
-				ET.SubElement(root, 'penciller').text = u"{0}".format(credit['person'])
-				
-			if credit['role'].lower() in set( self.inker_synonyms ):
-				ET.SubElement(root, 'inker').text = u"{0}".format(credit['person'])
-				
-			if credit['role'].lower() in set( self.colorist_synonyms ):
-				ET.SubElement(root, 'colorist').text = u"{0}".format(credit['person'])
-
-			if credit['role'].lower() in set( self.letterer_synonyms ):
-				ET.SubElement(root, 'letterer').text = u"{0}".format(credit['person'])
-
-			if credit['role'].lower() in set( self.cover_synonyms ):
-				ET.SubElement(root, 'coverDesigner').text = u"{0}".format(credit['person'])
-
-			if credit['role'].lower() in set( self.editor_synonyms ):
-				ET.SubElement(root, 'editor').text = u"{0}".format(credit['person'])
-		
-
-		# self pretty-print
-		self.indent(root)
-
-		# wrap it in an ElementTree instance, and save as XML
-		tree = ET.ElementTree(root)
-		return tree
-				 
-
-	def convertXMLToMetadata( self, tree ):
-			
-		root = tree.getroot()
-
-		if root.tag != 'comet':
-			raise 1
-			return None
-
-		metadata = GenericMetadata()
-		md = metadata
-	
-		# Helper function
-		def xlate( tag ):
-			node = root.find( tag )
-			if node is not None:
-				return node.text
-			else:
-				return None
-				
-		md.series =           xlate( 'series' )
-		md.title =            xlate( 'title' )
-		md.issue =            xlate( 'issue' )
-		md.volume =           xlate( 'volume' )
-		md.comments =         xlate( 'description' )
-		md.publisher =        xlate( 'publisher' )
-		md.language =         xlate( 'language' )
-		md.format =           xlate( 'format' )
-		md.pageCount =        xlate( 'pages' )
-		md.maturityRating =   xlate( 'rating' )
-		md.price =            xlate( 'price' )
-		md.isVersionOf =      xlate( 'isVersionOf' )
-		md.rights =           xlate( 'rights' )
-		md.identifier =       xlate( 'identifier' )
-		md.lastMark =         xlate( 'lastMark' )
-		md.genre =            xlate( 'genre' ) # TODO - repeatable field
-
-		date = xlate( 'date' )
-		if date is not None:
-			parts = date.split('-')
-			if len( parts) > 0:
-				md.year = parts[0]
-			if len( parts) > 1:
-				md.month = parts[1]
-				
-		md.coverImage = xlate( 'coverImage' )
-		
-		readingDirection = xlate( 'readingDirection' )
-		if readingDirection is not None and readingDirection == "rtl":
-			md.manga = "YesAndRightToLeft"
-	
-		# loop for character tags		
-		char_list =  []
-		for n in root:
-			if n.tag == 'character':
-				char_list.append(n.text.strip())
-		md.characters = utils.listToString( char_list )
-
-		# Now extract the credit info
-		for n in root:
-			if (  n.tag == 'writer' or 
-				n.tag == 'penciller' or
-				n.tag == 'inker' or
-				n.tag == 'colorist' or
-				n.tag == 'letterer' or
-				n.tag == 'editor' 
-			):
-				metadata.addCredit( n.text.strip(), n.tag.title() )
-
-			if n.tag == 'coverDesigner':
-				metadata.addCredit( n.text.strip(), "Cover" )
-
-
-		metadata.isEmpty = False
-		
-		return metadata
-
-	#verify that the string actually contains CoMet data in XML format
-	def validateString( self, string ):
-		try:
-			tree = ET.ElementTree(ET.fromstring( string ))
-			root = tree.getroot()
-			if root.tag != 'comet':
-				raise Exception
-		except:
-			return False
-		
-		return True
-
-
-	def writeToExternalFile( self, filename, metadata ):
-		
-		tree = self.convertMetadataToXML( self, metadata )
-		#ET.dump(tree)		
-		tree.write(filename, encoding='utf-8')
-	
-	def readFromExternalFile( self, filename ):
-
-		tree = ET.parse( filename )
-		return self.convertXMLToMetadata( tree )
-

comicapi/__init__.py

@@ -0,0 +1,3 @@
+from __future__ import annotations
+
+__author__ = "dromanin"

comicapi/__pyinstaller/__init__.py

@@ -0,0 +1,7 @@
+from __future__ import annotations
+
+import os
+
+
+def get_hook_dirs() -> list[str]:
+    return [os.path.dirname(__file__)]

comicapi/__pyinstaller/hook-comicapi.py

@@ -0,0 +1,6 @@
+from __future__ import annotations
+
+from PyInstaller.utils.hooks import collect_data_files, collect_entry_point
+
+datas, hiddenimports = collect_entry_point("comicapi.archiver")
+datas += collect_data_files("comicapi.data")

comicapi/archivers/__init__.py

@@ -0,0 +1,15 @@
+from __future__ import annotations
+
+from comicapi.archivers.archiver import Archiver
+from comicapi.archivers.folder import FolderArchiver
+from comicapi.archivers.rar import RarArchiver
+from comicapi.archivers.sevenzip import SevenZipArchiver
+from comicapi.archivers.zip import ZipArchiver
+
+
+class UnknownArchiver(Archiver):
+    def name(self) -> str:
+        return "Unknown"
+
+
+__all__ = ["Archiver", "UnknownArchiver", "FolderArchiver", "RarArchiver", "ZipArchiver", "SevenZipArchiver"]

comicapi/archivers/archiver.py

@@ -0,0 +1,130 @@
+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):
+        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 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 +1,97 @@
+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.read_file(self.comment_file_name).decode("utf-8")
+        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 read_file(self, archive_file: str) -> bytes:
+        try:
+            with open(self.path / archive_file, mode="rb") as f:
+                data = f.read()
+        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 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 name(self) -> str:
+        return "Folder"
+
+    @classmethod
+    def is_valid(cls, path: pathlib.Path) -> bool:
+        return path.is_dir()

comicapi/archivers/rar.py

@@ -0,0 +1,262 @@
+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:
+    from unrar.cffi import rarfile
+
+    rar_support = True
+except ImportError:
+    rar_support = False
+
+
+logger = logging.getLogger(__name__)
+
+if not rar_support:
+    logger.error("unrar-cffi 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.decode("utf-8") if rarc else ""
+
+    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),
+                    ]
+                    subprocess.run(
+                        proc_args,
+                        startupinfo=self.startupinfo,
+                        stdout=subprocess.DEVNULL,
+                        stdin=subprocess.DEVNULL,
+                        stderr=subprocess.DEVNULL,
+                        check=True,
+                    )
+
+                if platform.system() == "Darwin":
+                    time.sleep(1)
+            except (subprocess.CalledProcessError, 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 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:
+            # use external program to remove file from Rar archive
+            result = subprocess.run(
+                [self.exe, "d", "-c-", self.path, archive_file],
+                startupinfo=self.startupinfo,
+                stdout=subprocess.DEVNULL,
+                stdin=subprocess.DEVNULL,
+                stderr=subprocess.DEVNULL,
+            )
+
+            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("./")
+
+            # use external program to write file to Rar archive
+            result = subprocess.run(
+                [self.exe, "a", f"-si{archive_name}", f"-ap{archive_parent}", "-c-", "-ep", self.path],
+                input=data,
+                startupinfo=self.startupinfo,
+                stdout=subprocess.DEVNULL,
+                stderr=subprocess.DEVNULL,
+            )
+
+            if platform.system() == "Darwin":
+                time.sleep(1)
+            if result.returncode != 0:
+                logger.error(
+                    "Error writing rar archive [exitcode: %d]: %s :: %s", result.returncode, self.path, archive_file
+                )
+                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 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")
+
+                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", "-r", "-c-", str(rar_path.absolute()), "."],
+                    cwd=rar_cwd.absolute(),
+                    startupinfo=self.startupinfo,
+                    stdout=subprocess.DEVNULL,
+                    stdin=subprocess.DEVNULL,
+                    stderr=subprocess.DEVNULL,
+                )
+                if result.returncode != 0:
+                    logger.error("Error while copying to rar archive [exitcode: %d]: %s", result.returncode, self.path)
+                    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:
+        return bool(self.exe and (os.path.exists(self.exe) or shutil.which(self.exe)))
+
+    def extension(self) -> str:
+        return ".cbr"
+
+    def name(self) -> str:
+        return "RAR"
+
+    @classmethod
+    def is_valid(cls, path: pathlib.Path) -> bool:
+        if rar_support:
+            return rarfile.is_rarfile(str(path))
+        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 +1,131 @@
+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 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 +1,190 @@
+from __future__ import annotations
+
+import logging
+import os
+import pathlib
+import shutil
+import struct
+import tempfile
+import zipfile
+from typing import cast
+
+from comicapi.archivers import Archiver
+
+logger = logging.getLogger(__name__)
+
+
+class ZipArchiver(Archiver):
+
+    """ZIP implementation"""
+
+    def __init__(self) -> None:
+        super().__init__()
+
+    def get_comment(self) -> str:
+        with zipfile.ZipFile(self.path, "r") as zf:
+            comment = zf.comment.decode("utf-8")
+        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.error("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()
+        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 zipfile.ZipFile(self.path, mode="a", allowZip64=True, compression=zipfile.ZIP_DEFLATED) as zf:
+                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 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.write_zip_comment(self.path, 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:
+        return zipfile.is_zipfile(path)
+
+    def write_zip_comment(self, filename: pathlib.Path | str, comment: str) -> bool:
+        """
+        This is a custom function for writing a comment to a zip file,
+        since the built-in one doesn't seem to work on Windows and Mac OS/X
+
+        Fortunately, the zip comment is at the end of the file, and it's
+        easy to manipulate.  See this website for more info:
+        see: http://en.wikipedia.org/wiki/Zip_(file_format)#Structure
+        """
+
+        # get file size
+        statinfo = os.stat(filename)
+        file_length = statinfo.st_size
+
+        try:
+            with open(filename, mode="r+b") as file:
+                # the starting position, relative to EOF
+                pos = -4
+                found = False
+
+                # walk backwards to find the "End of Central Directory" record
+                while (not found) and (-pos != file_length):
+                    # seek, relative to EOF
+                    file.seek(pos, 2)
+                    value = file.read(4)
+
+                    # look for the end of central directory signature
+                    if bytearray(value) == bytearray([0x50, 0x4B, 0x05, 0x06]):
+                        found = True
+                    else:
+                        # not found, step back another byte
+                        pos = pos - 1
+
+                if found:
+                    # now skip forward 20 bytes to the comment length word
+                    pos += 20
+                    file.seek(pos, 2)
+
+                    # Pack the length of the comment string
+                    fmt = "H"  # one 2-byte integer
+                    comment_length = struct.pack(fmt, len(comment))  # pack integer in a binary string
+
+                    # write out the length
+                    file.write(comment_length)
+                    file.seek(pos + 2, 2)
+
+                    # write out the comment itself
+                    file.write(comment.encode("utf-8"))
+                    file.truncate()
+                else:
+                    raise Exception("Could not find the End of Central Directory record!")
+        except Exception as e:
+            logger.error("Error writing comment to zip archive [%s]: %s", e, self.path)
+            return False
+        else:
+            return True

comicapi/comet.py

@@ -0,0 +1,212 @@
+"""A class to encapsulate CoMet 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.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/comicarchive.py

@@ -0,0 +1,604 @@
+"""A class to represent a single comic, be it file or folder of images"""
+# 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 io
+import logging
+import os
+import pathlib
+import shutil
+import sys
+from typing import cast
+
+import natsort
+import wordninja
+
+from comicapi import filenamelexer, filenameparser, utils
+from comicapi.archivers import Archiver, UnknownArchiver, ZipArchiver
+from comicapi.comet import CoMet
+from comicapi.comicbookinfo import ComicBookInfo
+from comicapi.comicinfoxml import ComicInfoXml
+from comicapi.genericmetadata import GenericMetadata, PageType
+
+if sys.version_info < (3, 10):
+    from importlib_metadata import entry_points
+else:
+    from importlib.metadata import entry_points
+
+try:
+    from PIL import Image
+
+    pil_available = True
+except ImportError:
+    pil_available = False
+
+logger = logging.getLogger(__name__)
+
+if not pil_available:
+    logger.error("PIL unavalable")
+
+archivers: list[type[Archiver]] = []
+
+
+def load_archive_plugins() -> None:
+    if not archivers:
+        builtin: list[type[Archiver]] = []
+        for arch in entry_points(group="comicapi.archiver"):
+            try:
+                archiver: type[Archiver] = arch.load()
+                if archiver.enabled:
+                    if arch.module.startswith("comicapi"):
+                        builtin.append(archiver)
+                    else:
+                        archivers.append(archiver)
+            except Exception:
+                logger.warning("Failed to load talker: %s", arch.name)
+        archivers.extend(builtin)
+
+
+class MetaDataStyle:
+    CBI = 0
+    CIX = 1
+    COMET = 2
+    name = ["ComicBookLover", "ComicRack", "CoMet"]
+    short_name = ["cbl", "cr", "comet"]
+
+
+class ComicArchive:
+    logo_data = b""
+
+    def __init__(self, path: pathlib.Path | str, default_image_path: pathlib.Path | str | None = None) -> None:
+        self.cbi_md: GenericMetadata | None = None
+        self.cix_md: GenericMetadata | None = None
+        self.comet_filename: str | None = None
+        self.comet_md: GenericMetadata | None = None
+        self._has_cbi: bool | None = None
+        self._has_cix: bool | None = None
+        self._has_comet: bool | None = None
+        self.path = pathlib.Path(path).absolute()
+        self.page_count: int | None = None
+        self.page_list: list[str] = []
+
+        self.ci_xml_filename = "ComicInfo.xml"
+        self.comet_default_filename = "CoMet.xml"
+        self.reset_cache()
+        self.default_image_path = default_image_path
+
+        self.archiver: Archiver = UnknownArchiver.open(self.path)
+
+        load_archive_plugins()
+        for archiver in archivers:
+            if archiver.is_valid(self.path):
+                self.archiver = archiver.open(self.path)
+                break
+
+        if not ComicArchive.logo_data and self.default_image_path:
+            with open(self.default_image_path, mode="rb") as fd:
+                ComicArchive.logo_data = fd.read()
+
+    def reset_cache(self) -> None:
+        """Clears the cached data"""
+
+        self._has_cix = None
+        self._has_cbi = None
+        self._has_comet = None
+        self.comet_filename = None
+        self.page_count = None
+        self.page_list = []
+        self.cix_md = None
+        self.cbi_md = None
+        self.comet_md = None
+
+    def load_cache(self, style_list: list[int]) -> None:
+        for style in style_list:
+            self.read_metadata(style)
+
+    def rename(self, path: pathlib.Path | str) -> None:
+        new_path = pathlib.Path(path).absolute()
+        if new_path == self.path:
+            return
+        os.makedirs(new_path.parent, 0o777, True)
+        shutil.move(self.path, new_path)
+        self.path = new_path
+        self.archiver.path = pathlib.Path(path)
+
+    def is_writable(self, check_archive_status: bool = True) -> bool:
+        if isinstance(self.archiver, UnknownArchiver):
+            return False
+
+        if check_archive_status and not self.archiver.is_writable():
+            return False
+
+        if not (os.access(self.path, os.W_OK) or os.access(self.path.parent, os.W_OK)):
+            return False
+
+        return True
+
+    def is_writable_for_style(self, data_style: int) -> bool:
+        return not (data_style == MetaDataStyle.CBI and not self.archiver.supports_comment)
+
+    def is_zip(self) -> bool:
+        return self.archiver.name() == "ZIP"
+
+    def seems_to_be_a_comic_archive(self) -> bool:
+        if not (isinstance(self.archiver, UnknownArchiver)) and self.get_number_of_pages() > 0:
+            return True
+
+        return False
+
+    def extension(self) -> str:
+        return self.archiver.extension()
+
+    def read_metadata(self, style: int) -> GenericMetadata:
+        if style == MetaDataStyle.CIX:
+            return self.read_cix()
+        if style == MetaDataStyle.CBI:
+            return self.read_cbi()
+        if style == MetaDataStyle.COMET:
+            return self.read_comet()
+        return GenericMetadata()
+
+    def write_metadata(self, metadata: GenericMetadata, style: int) -> bool:
+        retcode = False
+        if style == MetaDataStyle.CIX:
+            retcode = self.write_cix(metadata)
+        if style == MetaDataStyle.CBI:
+            retcode = self.write_cbi(metadata)
+        if style == MetaDataStyle.COMET:
+            retcode = self.write_comet(metadata)
+        return retcode
+
+    def has_metadata(self, style: int) -> bool:
+        if style == MetaDataStyle.CIX:
+            return self.has_cix()
+        if style == MetaDataStyle.CBI:
+            return self.has_cbi()
+        if style == MetaDataStyle.COMET:
+            return self.has_comet()
+        return False
+
+    def remove_metadata(self, style: int) -> bool:
+        retcode = True
+        if style == MetaDataStyle.CIX:
+            retcode = self.remove_cix()
+        elif style == MetaDataStyle.CBI:
+            retcode = self.remove_cbi()
+        elif style == MetaDataStyle.COMET:
+            retcode = self.remove_co_met()
+        return retcode
+
+    def get_page(self, index: int) -> bytes:
+        image_data = b""
+
+        filename = self.get_page_name(index)
+
+        if filename:
+            try:
+                image_data = self.archiver.read_file(filename) or b""
+            except Exception:
+                logger.error("Error reading in page %d. Substituting logo page.", index)
+                image_data = ComicArchive.logo_data
+
+        return image_data
+
+    def get_page_name(self, index: int) -> str:
+        if index is None:
+            return ""
+
+        page_list = self.get_page_name_list()
+
+        num_pages = len(page_list)
+        if num_pages == 0 or index >= num_pages:
+            return ""
+
+        return page_list[index]
+
+    def get_scanner_page_index(self) -> int | None:
+        scanner_page_index = None
+
+        # make a guess at the scanner page
+        name_list = self.get_page_name_list()
+        count = self.get_number_of_pages()
+
+        # too few pages to really know
+        if count < 5:
+            return None
+
+        # count the length of every filename, and count occurrences
+        length_buckets: dict[int, int] = {}
+        for name in name_list:
+            fname = os.path.split(name)[1]
+            length = len(fname)
+            if length in length_buckets:
+                length_buckets[length] += 1
+            else:
+                length_buckets[length] = 1
+
+        # sort by most common
+        sorted_buckets = sorted(length_buckets.items(), key=lambda tup: (tup[1], tup[0]), reverse=True)
+
+        # statistical mode occurrence is first
+        mode_length = sorted_buckets[0][0]
+
+        # we are only going to consider the final image file:
+        final_name = os.path.split(name_list[count - 1])[1]
+
+        common_length_list = []
+        for name in name_list:
+            if len(os.path.split(name)[1]) == mode_length:
+                common_length_list.append(os.path.split(name)[1])
+
+        prefix = os.path.commonprefix(common_length_list)
+
+        if mode_length <= 7 and prefix == "":
+            # probably all numbers
+            if len(final_name) > mode_length:
+                scanner_page_index = count - 1
+
+        # see if the last page doesn't start with the same prefix as most others
+        elif not final_name.startswith(prefix):
+            scanner_page_index = count - 1
+
+        return scanner_page_index
+
+    def get_page_name_list(self, sort_list: bool = True) -> list[str]:
+        if not self.page_list:
+            # get the list file names in the archive, and sort
+            files: list[str] = self.archiver.get_filename_list()
+
+            # seems like some archive creators are on Windows, and don't know about case-sensitivity!
+            if sort_list:
+                files = cast(list[str], natsort.os_sorted(files))
+
+            # make a sub-list of image files
+            self.page_list = []
+            for name in files:
+                if (
+                    os.path.splitext(name)[1].casefold() in [".jpg", ".jpeg", ".png", ".gif", ".webp"]
+                    and os.path.basename(name)[0] != "."
+                ):
+                    self.page_list.append(name)
+
+        return self.page_list
+
+    def get_number_of_pages(self) -> int:
+        if self.page_count is None:
+            self.page_count = len(self.get_page_name_list())
+        return self.page_count
+
+    def read_cbi(self) -> GenericMetadata:
+        if self.cbi_md is None:
+            raw_cbi = self.read_raw_cbi()
+            if raw_cbi:
+                self.cbi_md = ComicBookInfo().metadata_from_string(raw_cbi)
+            else:
+                self.cbi_md = GenericMetadata()
+
+            self.cbi_md.set_default_page_list(self.get_number_of_pages())
+
+        return self.cbi_md
+
+    def read_raw_cbi(self) -> str:
+        if not self.has_cbi():
+            return ""
+
+        return self.archiver.get_comment()
+
+    def has_cbi(self) -> bool:
+        if self._has_cbi is None:
+            if not self.seems_to_be_a_comic_archive():
+                self._has_cbi = False
+            else:
+                comment = self.archiver.get_comment()
+                self._has_cbi = ComicBookInfo().validate_string(comment)
+
+        return self._has_cbi
+
+    def write_cbi(self, metadata: GenericMetadata) -> bool:
+        if metadata is not None:
+            try:
+                self.apply_archive_info_to_metadata(metadata)
+                cbi_string = ComicBookInfo().string_from_metadata(metadata)
+                write_success = self.archiver.set_comment(cbi_string)
+                if write_success:
+                    self._has_cbi = True
+                    self.cbi_md = metadata
+                self.reset_cache()
+                return write_success
+            except Exception as e:
+                logger.error("Error saving CBI! for %s: %s", self.path, e)
+
+        return False
+
+    def remove_cbi(self) -> bool:
+        if self.has_cbi():
+            write_success = self.archiver.set_comment("")
+            if write_success:
+                self._has_cbi = False
+                self.cbi_md = None
+            self.reset_cache()
+            return write_success
+        return True
+
+    def read_cix(self) -> GenericMetadata:
+        if self.cix_md is None:
+            raw_cix = self.read_raw_cix()
+            if raw_cix:
+                self.cix_md = ComicInfoXml().metadata_from_string(raw_cix)
+            else:
+                self.cix_md = GenericMetadata()
+
+            # validate the existing page list (make sure count is correct)
+            if len(self.cix_md.pages) != 0:
+                if len(self.cix_md.pages) != self.get_number_of_pages():
+                    # pages array doesn't match the actual number of images we're seeing
+                    # in the archive, so discard the data
+                    self.cix_md.pages = []
+
+            if len(self.cix_md.pages) == 0:
+                self.cix_md.set_default_page_list(self.get_number_of_pages())
+
+        return self.cix_md
+
+    def read_raw_cix(self) -> bytes:
+        if not self.has_cix():
+            return b""
+        try:
+            raw_cix = self.archiver.read_file(self.ci_xml_filename) or b""
+        except Exception as e:
+            logger.error("Error reading in raw CIX! for %s: %s", self.path, e)
+            raw_cix = b""
+        return raw_cix
+
+    def write_cix(self, metadata: GenericMetadata) -> bool:
+        if metadata is not None:
+            try:
+                self.apply_archive_info_to_metadata(metadata, calc_page_sizes=True)
+                raw_cix = self.read_raw_cix()
+                cix_string = ComicInfoXml().string_from_metadata(metadata, xml=raw_cix)
+                write_success = self.archiver.write_file(self.ci_xml_filename, cix_string.encode("utf-8"))
+                if write_success:
+                    self._has_cix = True
+                    self.cix_md = metadata
+                self.reset_cache()
+                return write_success
+            except Exception as e:
+                logger.error("Error saving CIX! for %s: %s", self.path, e)
+
+        return False
+
+    def remove_cix(self) -> bool:
+        if self.has_cix():
+            write_success = self.archiver.remove_file(self.ci_xml_filename)
+            if write_success:
+                self._has_cix = False
+                self.cix_md = None
+            self.reset_cache()
+            return write_success
+        return True
+
+    def has_cix(self) -> bool:
+        if self._has_cix is None:
+            if not self.seems_to_be_a_comic_archive():
+                self._has_cix = False
+            elif self.ci_xml_filename in self.archiver.get_filename_list():
+                self._has_cix = True
+            else:
+                self._has_cix = False
+        return self._has_cix
+
+    def read_comet(self) -> GenericMetadata:
+        if self.comet_md is None:
+            raw_comet = self.read_raw_comet()
+            if raw_comet is None or raw_comet == "":
+                self.comet_md = GenericMetadata()
+            else:
+                self.comet_md = CoMet().metadata_from_string(raw_comet)
+
+            self.comet_md.set_default_page_list(self.get_number_of_pages())
+            # use the coverImage value from the comet_data to mark the cover in this struct
+            # walk through list of images in file, and find the matching one for md.coverImage
+            # need to remove the existing one in the default
+            if self.comet_md.cover_image is not None:
+                cover_idx = 0
+                for idx, f in enumerate(self.get_page_name_list()):
+                    if self.comet_md.cover_image == f:
+                        cover_idx = idx
+                        break
+                if cover_idx != 0:
+                    del self.comet_md.pages[0]["Type"]
+                    self.comet_md.pages[cover_idx]["Type"] = PageType.FrontCover
+
+        return self.comet_md
+
+    def read_raw_comet(self) -> str:
+        raw_comet = ""
+        if not self.has_comet():
+            raw_comet = ""
+        else:
+            try:
+                raw_bytes = self.archiver.read_file(cast(str, self.comet_filename))
+                if raw_bytes:
+                    raw_comet = raw_bytes.decode("utf-8")
+            except OSError as e:
+                logger.exception("Error reading in raw CoMet!: %s", e)
+        return raw_comet
+
+    def write_comet(self, metadata: GenericMetadata) -> bool:
+        if metadata is not None:
+            if not self.has_comet():
+                self.comet_filename = self.comet_default_filename
+
+            self.apply_archive_info_to_metadata(metadata)
+            # Set the coverImage value, if it's not the first page
+            cover_idx = int(metadata.get_cover_page_index_list()[0])
+            if cover_idx != 0:
+                metadata.cover_image = self.get_page_name(cover_idx)
+
+            comet_string = CoMet().string_from_metadata(metadata)
+            write_success = self.archiver.write_file(cast(str, self.comet_filename), comet_string.encode("utf-8"))
+            if write_success:
+                self._has_comet = True
+                self.comet_md = metadata
+            self.reset_cache()
+            return write_success
+
+        return False
+
+    def remove_co_met(self) -> bool:
+        if self.has_comet():
+            write_success = self.archiver.remove_file(cast(str, self.comet_filename))
+            if write_success:
+                self._has_comet = False
+                self.comet_md = None
+            self.reset_cache()
+            return write_success
+        return True
+
+    def has_comet(self) -> bool:
+        if self._has_comet is None:
+            self._has_comet = False
+            if not self.seems_to_be_a_comic_archive():
+                return self._has_comet
+
+            # look at all xml files in root, and search for CoMet data, get first
+            for n in self.archiver.get_filename_list():
+                if os.path.dirname(n) == "" and os.path.splitext(n)[1].casefold() == ".xml":
+                    # read in XML file, and validate it
+                    data = ""
+                    try:
+                        d = self.archiver.read_file(n)
+                        if d:
+                            data = d.decode("utf-8")
+                    except Exception as e:
+                        logger.warning("Error reading in Comet XML for validation! from %s: %s", self.path, e)
+                    if CoMet().validate_string(data):
+                        # since we found it, save it!
+                        self.comet_filename = n
+                        self._has_comet = True
+                        break
+
+        return self._has_comet
+
+    def apply_archive_info_to_metadata(self, md: GenericMetadata, calc_page_sizes: bool = False) -> None:
+        md.page_count = self.get_number_of_pages()
+
+        if calc_page_sizes:
+            for index, p in enumerate(md.pages):
+                idx = int(p["Image"])
+                if pil_available:
+                    if "ImageSize" not in p or "ImageHeight" not in p or "ImageWidth" not in p:
+                        data = self.get_page(idx)
+                        if data:
+                            try:
+                                if isinstance(data, bytes):
+                                    im = Image.open(io.BytesIO(data))
+                                else:
+                                    im = Image.open(io.StringIO(data))
+                                w, h = im.size
+
+                                p["ImageSize"] = str(len(data))
+                                p["ImageHeight"] = str(h)
+                                p["ImageWidth"] = str(w)
+                            except Exception as e:
+                                logger.warning("Error decoding image [%s] %s :: image %s", e, self.path, index)
+                                p["ImageSize"] = str(len(data))
+
+                else:
+                    if "ImageSize" not in p:
+                        data = self.get_page(idx)
+                        p["ImageSize"] = str(len(data))
+
+    def metadata_from_filename(
+        self,
+        complicated_parser: bool = False,
+        remove_c2c: bool = False,
+        remove_fcbd: bool = False,
+        remove_publisher: bool = False,
+        split_words: bool = False,
+    ) -> GenericMetadata:
+        metadata = GenericMetadata()
+
+        filename = self.path.name
+        if split_words:
+            filename = " ".join(wordninja.split(self.path.stem)) + self.path.suffix
+
+        if complicated_parser:
+            lex = filenamelexer.Lex(filename)
+            p = filenameparser.Parse(
+                lex.items, remove_c2c=remove_c2c, remove_fcbd=remove_fcbd, remove_publisher=remove_publisher
+            )
+            metadata.alternate_number = utils.xlate(p.filename_info["alternate"])
+            metadata.issue = utils.xlate(p.filename_info["issue"])
+            metadata.issue_count = utils.xlate(p.filename_info["issue_count"])
+            metadata.publisher = utils.xlate(p.filename_info["publisher"])
+            metadata.series = utils.xlate(p.filename_info["series"])
+            metadata.title = utils.xlate(p.filename_info["title"])
+            metadata.volume = utils.xlate(p.filename_info["volume"])
+            metadata.volume_count = utils.xlate(p.filename_info["volume_count"])
+            metadata.year = utils.xlate(p.filename_info["year"])
+
+            metadata.scan_info = utils.xlate(p.filename_info["remainder"])
+            metadata.format = "FCBD" if p.filename_info["fcbd"] else None
+            if p.filename_info["annual"]:
+                metadata.format = "Annual"
+        else:
+            fnp = filenameparser.FileNameParser()
+            fnp.parse_filename(filename)
+
+            if fnp.issue:
+                metadata.issue = fnp.issue
+            if fnp.series:
+                metadata.series = fnp.series
+            if fnp.volume:
+                metadata.volume = utils.xlate(fnp.volume, True)
+            if fnp.year:
+                metadata.year = utils.xlate(fnp.year, True)
+            if fnp.issue_count:
+                metadata.issue_count = utils.xlate(fnp.issue_count, True)
+            if fnp.remainder:
+                metadata.scan_info = fnp.remainder
+
+        metadata.is_empty = False
+
+        return metadata
+
+    def export_as_zip(self, zip_filename: pathlib.Path) -> bool:
+        if self.archiver.name() == "ZIP":
+            # nothing to do, we're already a zip
+            return True
+
+        zip_archiver = ZipArchiver.open(zip_filename)
+        return zip_archiver.copy_from_archive(self.archiver)

comicapi/comicbookinfo.py

@@ -0,0 +1,174 @@
+"""A class to encapsulate the ComicBookInfo 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 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

@@ -0,0 +1,265 @@
+"""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 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

@@ -0,0 +1,5 @@
+from __future__ import annotations
+
+import pathlib
+
+data_path = pathlib.Path(__file__).parent

comicapi/data/publishers.json

@@ -0,0 +1,130 @@
+{
+    "Marvel":{
+        "marvel comics": "",
+        "aircel comics": "Aircel Comics",
+        "aircel": "Aircel Comics",
+        "atlas comics": "Atlas Comics",
+        "atlas": "Atlas Comics",
+        "crossgen comics": "CrossGen comics",
+        "crossgen": "CrossGen comics",
+        "curtis magazines": "Curtis Magazines",
+        "disney books group": "Disney Books Group",
+        "disney books": "Disney Books Group",
+        "disney kingdoms": "Disney Kingdoms",
+        "epic comics group": "Epic Comics",
+        "epic comics": "Epic Comics",
+        "epic": "Epic Comics",
+        "eternity comics": "Eternity Comics",
+        "humorama": "Humorama",
+        "icon comics": "Icon Comics",
+        "infinite comics": "Infinite Comics",
+        "malibu comics": "Malibu Comics",
+        "malibu": "Malibu Comics",
+        "marvel 2099": "Marvel 2099",
+        "marvel absurd": "Marvel Absurd",
+        "marvel adventures": "Marvel Adventures",
+        "marvel age": "Marvel Age",
+        "marvel books": "Marvel Books",
+        "marvel comics 2": "Marvel Comics 2",
+        "marvel digital comics unlimited": "Marvel Unlimited",
+        "marvel edge": "Marvel Edge",
+        "marvel frontier": "Marvel Frontier",
+        "marvel illustrated": "Marvel Illustrated",
+        "marvel knights": "Marvel Knights",
+        "marvel magazine group": "Marvel Magazine Group",
+        "marvel mangaverse": "Marvel Mangaverse",
+        "marvel monsters group": "Marvel Monsters Group",
+        "marvel music": "Marvel Music",
+        "marvel next": "Marvel Next",
+        "marvel noir": "Marvel Noir",
+        "marvel press": "Marvel Press",
+        "marvel uk": "Marvel UK",
+        "marvel unlimited": "Marvel Unlimited",
+        "max": "MAX",
+        "mc2": "Marvel Comics 2",
+        "new universe": "New Universe",
+        "non-pareil publishing corp.": "Non-Pareil Publishing Corp.",
+        "paramount comics": "Paramount Comics",
+        "power comics": "Power Comics",
+        "razorline": "Razorline",
+        "star comics": "Star Comics",
+        "timely comics": "Timely Comics",
+        "timely": "Timely Comics",
+        "tsunami": "Tsunami",
+        "ultimate comics": "Ultimate Comics",
+        "ultimate marvel": "Ultimate Marvel",
+        "vital publications, inc.": "Vital Publications, Inc."
+    },
+
+    "DC Comics":{
+        "dc_comics": "",
+        "dc": "",
+        "dccomics": "",
+        "!mpact comics": "Impact Comics",
+        "all star dc": "All-Star",
+        "all star": "All-Star",
+        "all-star dc": "All-Star",
+        "all-star": "All-Star",
+        "america's best comics": "America's Best Comics",
+        "black label": "DC Black Label",
+        "cliffhanger": "Cliffhanger",
+        "cmx manga": "CMX Manga",
+        "dc black label": "DC Black Label",
+        "dc focus": "DC Focus",
+        "dc ink": "DC Ink",
+        "dc zoom": "DC Zoom",
+        "earth m": "Earth M",
+        "earth one": "Earth One",
+        "earth-m": "Earth M",
+        "elseworlds": "Elseworlds",
+        "eo": "Earth One",
+        "first wave": "First Wave",
+        "focus": "DC Focus",
+        "helix": "Helix",
+        "homage comics": "Homage Comics",
+        "impact comics": "Impact Comics",
+        "impact! comics": "Impact Comics",
+        "johnny dc": "Johnny DC",
+        "mad": "Mad",
+        "minx": "Minx",
+        "paradox press": "Paradox Press",
+        "piranha press": "Piranha Press",
+        "sandman universe": "Sandman Universe",
+        "tangent comics": "Tangent Comics",
+        "tsr": "TSR",
+        "vertigo": "Vertigo",
+        "wildstorm productions": "WildStorm Productions",
+        "wildstorm signature": "WildStorm Productions",
+        "wildstorm": "WildStorm Productions",
+        "wonder comics": "Wonder Comics",
+        "young animal": "Young Animal",
+        "zuda comics": "Zuda Comics",
+        "zuda": "Zuda Comics"
+    },
+
+    "Dark Horse Comics":{
+        "berger books": "Berger Books",
+        "comics' greatest world": "Dark Horse Heroes",
+        "dark horse digital": "Dark Horse Digital",
+        "dark horse heroes": "Dark Horse Heroes",
+        "dark horse manga": "Dark Horse Manga",
+        "dh deluxe": "DH Deluxe",
+        "dh press": "DH Press",
+        "kitchen sink books": "Kitchen Sink Books",
+        "legend": "Legend",
+        "m press": "M Press",
+        "maverick": "Maverick"
+    },
+
+    "Archie Comics":{
+        "archie action": "Archie Action",
+        "archie adventure Series": "Archie Adventure Series",
+        "archie horror": "Archie Horror",
+        "dark circle Comics": "Dark Circle Comics",
+        "dark circle": "Dark Circle Comics",
+        "mighty comics Group": "Mighty Comics Group",
+        "radio comics": "Mighty Comics Group",
+        "red circle Comics": "Dark Circle Comics",
+        "red circle": "Dark Circle Comics"
+    }
+}

comicapi/filenamelexer.py

@@ -0,0 +1,352 @@
+# Extracted and mutilated from https://github.com/lordwelch/wsfmt
+# Which was extracted and mutilated from https://github.com/golang/go/tree/master/src/text/template/parse
+from __future__ import annotations
+
+import calendar
+import os
+import unicodedata
+from enum import Enum, auto
+from typing import Any, Callable
+
+
+class ItemType(Enum):
+    Error = auto()  # Error occurred; value is text of error
+    EOF = auto()
+    Text = auto()  # Text
+    LeftParen = auto()
+    Number = auto()  # Simple number
+    IssueNumber = auto()  # Preceded by a # Symbol
+    RightParen = auto()
+    Space = auto()  # Run of spaces separating arguments
+    Dot = auto()
+    LeftBrace = auto()
+    RightBrace = auto()
+    LeftSBrace = auto()
+    RightSBrace = auto()
+    Symbol = auto()
+    Skip = auto()  # __ or -- no title, issue or series information beyond
+    Operator = auto()
+    Calendar = auto()
+    InfoSpecifier = auto()  # Specifies type of info e.g. v1 for 'volume': 1
+    ArchiveType = auto()
+    Honorific = auto()
+    Keywords = auto()
+    FCBD = auto()
+    ComicType = auto()
+    Publisher = auto()
+    C2C = auto()
+
+
+braces = [
+    ItemType.LeftBrace,
+    ItemType.LeftParen,
+    ItemType.LeftSBrace,
+    ItemType.RightBrace,
+    ItemType.RightParen,
+    ItemType.RightSBrace,
+]
+
+eof = chr(0)
+
+key = {
+    "fcbd": ItemType.FCBD,
+    "freecomicbookday": ItemType.FCBD,
+    "cbr": ItemType.ArchiveType,
+    "cbz": ItemType.ArchiveType,
+    "cbt": ItemType.ArchiveType,
+    "cb7": ItemType.ArchiveType,
+    "rar": ItemType.ArchiveType,
+    "zip": ItemType.ArchiveType,
+    "tar": ItemType.ArchiveType,
+    "7z": ItemType.ArchiveType,
+    "annual": ItemType.ComicType,
+    "volume": ItemType.InfoSpecifier,
+    "vol.": ItemType.InfoSpecifier,
+    "vol": ItemType.InfoSpecifier,
+    "v": ItemType.InfoSpecifier,
+    "of": ItemType.InfoSpecifier,
+    "dc": ItemType.Publisher,
+    "marvel": ItemType.Publisher,
+    "covers": ItemType.InfoSpecifier,
+    "c2c": ItemType.C2C,
+    "mr": ItemType.Honorific,
+    "ms": ItemType.Honorific,
+    "mrs": ItemType.Honorific,
+    "dr": ItemType.Honorific,
+}
+
+
+class Item:
+    def __init__(self, typ: ItemType, pos: int, val: str) -> None:
+        self.typ: ItemType = typ
+        self.pos: int = pos
+        self.val: str = val
+
+    def __repr__(self) -> str:
+        return f"{self.val}: index: {self.pos}: {self.typ}"
+
+
+class Lexer:
+    def __init__(self, string: str) -> None:
+        self.input: str = string  # The string being scanned
+        # The next lexing function to enter
+        self.state: Callable[[Lexer], Callable | None] | None = None  # type: ignore[type-arg]
+        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
+        self.paren_depth: int = 0  # Nesting depth of ( ) exprs
+        self.brace_depth: int = 0  # Nesting depth of { }
+        self.sbrace_depth: int = 0  # Nesting depth of [ ]
+        self.items: list[Item] = []
+
+    # Next returns the next rune in the input.
+    def get(self) -> str:
+        if int(self.pos) >= len(self.input) - 1:
+            self.pos += 1
+            return eof
+
+        self.pos += 1
+        return self.input[self.pos]
+
+    # Peek returns but does not consume the next rune in the input.
+    def peek(self) -> str:
+        if int(self.pos) >= len(self.input) - 1:
+            return eof
+
+        return self.input[self.pos + 1]
+
+    def backup(self) -> None:
+        self.pos -= 1
+
+    # Emit passes an item back to the client.
+    def emit(self, t: ItemType) -> None:
+        self.items.append(Item(t, self.start, self.input[self.start : self.pos + 1]))
+        self.start = self.pos + 1
+
+    # Ignore skips over the pending input before this point.
+    def ignore(self) -> None:
+        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
+
+        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
+
+        self.backup()
+
+    def scan_number(self) -> bool:
+        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()
+
+        return True
+
+    # Runs the state machine for the lexer.
+    def run(self) -> None:
+        self.state = lex_filename
+        while self.state is not None:
+            self.state = self.state(self)
+
+
+# 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:  # type: ignore[type-arg]
+    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:  # type: ignore[type-arg]
+    r = lex.get()
+    if r == eof:
+        if lex.paren_depth != 0:
+            return errorf(lex, "unclosed left paren")
+
+        if lex.brace_depth != 0:
+            return errorf(lex, "unclosed left paren")
+        lex.emit(ItemType.EOF)
+        return None
+    elif is_space(r):
+        if r == "_" and lex.peek() == "_":
+            lex.get()
+            lex.emit(ItemType.Skip)
+        else:
+            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
+    elif r == "'":
+        r = lex.peek()
+        if r in "0123456789":
+            return lex_number
+        lex.emit(ItemType.Text)  # TODO: Change to Text
+    elif "0" <= r <= "9":
+        lex.backup()
+        return lex_number
+    elif r == "#":
+        if "0" <= lex.peek() <= "9":
+            return lex_number
+        lex.emit(ItemType.Symbol)
+    elif is_operator(r):
+        if r == "-" and lex.peek() == "-":
+            lex.get()
+            lex.emit(ItemType.Skip)
+        else:
+            return lex_operator
+    elif is_alpha_numeric(r):
+        lex.backup()
+        return lex_text
+    elif r == "(":
+        lex.emit(ItemType.LeftParen)
+        lex.paren_depth += 1
+    elif r == ")":
+        lex.emit(ItemType.RightParen)
+        lex.paren_depth -= 1
+        if lex.paren_depth < 0:
+            return errorf(lex, "unexpected right paren " + r)
+
+    elif r == "{":
+        lex.emit(ItemType.LeftBrace)
+        lex.brace_depth += 1
+    elif r == "}":
+        lex.emit(ItemType.RightBrace)
+        lex.brace_depth -= 1
+        if lex.brace_depth < 0:
+            return errorf(lex, "unexpected right brace " + r)
+
+    elif r == "[":
+        lex.emit(ItemType.LeftSBrace)
+        lex.sbrace_depth += 1
+    elif r == "]":
+        lex.emit(ItemType.RightSBrace)
+        lex.sbrace_depth -= 1
+        if lex.sbrace_depth < 0:
+            return errorf(lex, "unexpected right brace " + r)
+    elif is_symbol(r):
+        lex.emit(ItemType.Symbol)
+    else:
+        return errorf(lex, "unrecognized character in action: " + r)
+
+    return lex_filename
+
+
+def lex_operator(lex: Lexer) -> Callable:  # type: ignore[type-arg]
+    lex.accept_run("-|:;")
+    lex.emit(ItemType.Operator)
+    return lex_filename
+
+
+# LexSpace scans a run of space characters.
+# One space has already been seen.
+def lex_space(lex: Lexer) -> Callable:  # type: ignore[type-arg]
+    while is_space(lex.peek()):
+        lex.get()
+
+    lex.emit(ItemType.Space)
+    return lex_filename
+
+
+# Lex_text scans an alphanumeric.
+def lex_text(lex: Lexer) -> Callable:  # type: ignore[type-arg]
+    while True:
+        r = lex.get()
+        if is_alpha_numeric(r):
+            if r.isnumeric():  # E.g. v1
+                word = lex.input[lex.start : lex.pos]
+                if word.casefold() in key and key[word.casefold()] == 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()
+            word = lex.input[lex.start : lex.pos + 1]
+
+            if word.casefold() in key:
+                lex.emit(key[word.casefold()])
+            elif cal(word):
+                lex.emit(ItemType.Calendar)
+            else:
+                lex.emit(ItemType.Text)
+            break
+
+    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 lex_number(lex: Lexer) -> Callable[[Lexer], Callable | None] | None:  # type: ignore[type-arg]
+    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():
+        # Assume that 80th is just text and not a number
+        lex.emit(ItemType.Text)
+    else:
+        lex.emit(ItemType.Number)
+
+    return lex_filename
+
+
+def is_space(character: str) -> bool:
+    return character in "_ \t"
+
+
+# IsAlphaNumeric reports whether r is an alphabetic, digit, or underscore.
+def is_alpha_numeric(character: str) -> bool:
+    return character.isalpha() or character.isnumeric()
+
+
+def is_operator(character: str) -> bool:
+    return character in "-|:;/\\"
+
+
+def is_symbol(character: str) -> bool:
+    return unicodedata.category(character)[0] in "PS"
+
+
+def Lex(filename: str) -> Lexer:
+    lex = Lexer(string=os.path.basename(filename))
+    lex.run()
+    return lex

comicapi/genericmetadata.py

@@ -0,0 +1,461 @@
+"""A class for internal metadata storage
+
+The goal of this class is to handle ALL the data that might come from various
+tagging schemes and databases, such as ComicVine or GCD.  This makes conversion
+possible, however lossy it might be
+
+"""
+# 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 copy
+import dataclasses
+import logging
+from typing import Any, TypedDict
+
+from comicapi import utils
+
+logger = logging.getLogger(__name__)
+
+
+class PageType:
+
+    """
+    These page info classes are exactly the same as the CIX scheme, since
+    it's unique
+    """
+
+    FrontCover = "FrontCover"
+    InnerCover = "InnerCover"
+    Roundup = "Roundup"
+    Story = "Story"
+    Advertisement = "Advertisement"
+    Editorial = "Editorial"
+    Letters = "Letters"
+    Preview = "Preview"
+    BackCover = "BackCover"
+    Other = "Other"
+    Deleted = "Deleted"
+
+
+class ImageMetadata(TypedDict, total=False):
+    Type: str
+    Bookmark: str
+    DoublePage: bool
+    Image: int
+    ImageSize: str
+    ImageHeight: str
+    ImageWidth: str
+
+
+class CreditMetadata(TypedDict):
+    person: str
+    role: str
+    primary: bool
+
+
+@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"]
+
+    is_empty: bool = True
+    tag_origin: str | None = None
+    issue_id: str | None = None
+
+    series: str | None = None
+    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
+    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
+
+    alternate_series: str | None = None
+    alternate_number: str | None = None
+    alternate_count: int | None = None
+    imprint: str | None = None
+    notes: str | None = None
+    web_link: str | None = None
+    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
+    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)
+
+    # Some CoMet-only items
+    price: str | 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) -> None:
+        for key, value in self.__dict__.items():
+            if value and key != "is_empty":
+                self.is_empty = False
+                break
+
+    def copy(self) -> GenericMetadata:
+        return copy.deepcopy(self)
+
+    def replace(self, /, **kwargs: Any) -> GenericMetadata:
+        tmp = self.copy()
+        tmp.__dict__.update(kwargs)
+        return tmp
+
+    def overlay(self, new_md: GenericMetadata) -> None:
+        """Overlay a metadata object on this one
+
+        That is, when the new object has non-None values, over-write them
+        to this one.
+        """
+
+        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)
+
+        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)
+
+        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.overlay_credits(new_md.credits)
+        # TODO
+
+        # not sure if the tags and pages should broken down, or treated
+        # as whole lists....
+
+        # 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)
+
+        if len(new_md.pages) > 0:
+            assign("pages", new_md.pages)
+
+    def overlay_credits(self, new_credits: list[CreditMetadata]) -> None:
+        for c in new_credits:
+            primary = bool("primary" in c and c["primary"])
+
+            # 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)
+
+    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)
+
+    def get_archive_page_index(self, pagenum: int) -> int:
+        # 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 0
+
+    def get_cover_page_index_list(self) -> list[int]:
+        # return a list of archive page indices of cover pages
+        coverlist = []
+        for p in self.pages:
+            if "Type" in p and p["Type"] == PageType.FrontCover:
+                coverlist.append(int(p["Image"]))
+
+        if len(coverlist) == 0:
+            coverlist.append(0)
+
+        return coverlist
+
+    def add_credit(self, person: str, role: str, primary: bool = False) -> None:
+        credit = CreditMetadata(person=person, role=role, primary=primary)
+
+        # 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():
+                # no need to add it. just adjust the "primary" flag as needed
+                c["primary"] = primary
+                found = True
+                break
+
+        if not found:
+            self.credits.append(credit)
+
+    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"]
+            ):
+                primary = credit["person"]
+        return primary
+
+    def __str__(self) -> str:
+        vals: list[tuple[str, Any]] = []
+        if self.is_empty:
+            return "No metadata"
+
+        def add_string(tag: str, val: Any) -> None:
+            if val is not None and str(val) != "":
+                vals.append((tag, val))
+
+        def add_attr_string(tag: str) -> None:
+            add_string(tag, getattr(self, tag))
+
+        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")
+
+        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("tags", ", ".join(self.tags))
+
+        for c in self.credits:
+            primary = ""
+            if "primary" in c and c["primary"]:
+                primary = " [P]"
+            add_string("credit", c["role"] + ": " + c["person"] + primary)
+
+        # find the longest field name
+        flen = 0
+        for i in vals:
+            flen = max(flen, len(i[0]))
+        flen += 1
+
+        # format the data nicely
+        outstr = ""
+        fmt_str = "{0: <" + str(flen) + "} {1}\n"
+        for i in vals:
+            outstr += fmt_str.format(i[0] + ":", i[1])
+
+        return outstr
+
+    def fix_publisher(self) -> None:
+        if self.publisher is None:
+            return
+        if self.imprint is None:
+            self.imprint = ""
+
+        imprint, publisher = utils.get_publisher(self.publisher)
+
+        self.publisher = publisher
+
+        if self.imprint.casefold() in publisher.casefold():
+            self.imprint = None
+
+        if self.imprint is None or self.imprint == "":
+            self.imprint = imprint
+        elif self.imprint.casefold() in imprint.casefold():
+            self.imprint = imprint
+
+
+md_test: GenericMetadata = GenericMetadata(
+    is_empty=False,
+    tag_origin=None,
+    series="Cory Doctorow's Futuristic Tales of the Here and Now",
+    issue="1",
+    title="Anda's Game",
+    publisher="IDW Publishing",
+    month=10,
+    year=2007,
+    day=1,
+    issue_count=6,
+    volume=1,
+    genre="Sci-Fi",
+    language="en",
+    comments=(
+        "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."
+    ),
+    volume_count=None,
+    critical_rating=3.0,
+    country=None,
+    alternate_series="Tales",
+    alternate_number="2",
+    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/",
+    format="Series",
+    manga="No",
+    black_and_white=None,
+    page_count=24,
+    maturity_rating="Everyone 10+",
+    story_arc="Here and Now",
+    series_group="Futuristic Tales",
+    scan_info="(CC BY-NC-SA 3.0)",
+    characters="Anda",
+    teams="Fahrenheit",
+    locations="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"),
+    ],
+    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,
+        ),
+    ],
+    price=None,
+    is_version_of=None,
+    rights=None,
+    identifier=None,
+    last_mark=None,
+    cover_image=None,
+)

comicapi/issuestring.py

@@ -0,0 +1,115 @@
+"""Support for mixed digit/string type Issue field
+
+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 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 unicodedata
+
+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 = ""
+
+        if text is None:
+            return
+
+        text = str(text)
+
+        if len(text) == 0:
+            return
+
+        # skip the minus sign if it's first
+        if text[0] == "-":
+            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.":
+                    break
+                # special case: also split on second "."
+                if text[idx] == ".":
+                    decimal_count += 1
+                    if decimal_count > 1:
+                        break
+            else:
+                idx = len(text)
+
+            # move trailing numeric decimal to suffix
+            # (only if there is other junk after )
+            if text[idx - 1] == "." and len(text) != idx:
+                idx = idx - 1
+
+            # if there is no numeric after the minus, make the minus part of the suffix
+            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
+        else:
+            self.suffix = text
+
+    def as_string(self, pad: int = 0) -> str:
+        # return the float, left side zero-padded, with suffix attached
+        if self.num is None:
+            return self.suffix
+
+        negative = self.num < 0
+
+        num_f = abs(self.num)
+
+        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
+
+        # create padding
+        padding = ""
+        length = len(str(num_int))
+        if length < pad:
+            padding = "0" * (pad - length)
+
+        num_s = padding + num_s
+        if negative:
+            num_s = "-" + num_s
+
+        return num_s
+
+    def as_float(self) -> float | None:
+        # return the float, with no suffix
+        if len(self.suffix) == 1 and self.suffix.isnumeric():
+            return (self.num or 0) + unicodedata.numeric(self.suffix)
+        return self.num

comicapi/utils.py

@@ -0,0 +1,271 @@
+"""Some generic utilities"""
+# 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 glob
+import json
+import logging
+import os
+import pathlib
+import unicodedata
+from collections import defaultdict
+from collections.abc import Mapping
+from shutil import which  # noqa: F401
+from typing import Any
+
+import pycountry
+import rapidfuzz.fuzz
+
+import comicapi.data
+
+logger = logging.getLogger(__name__)
+
+
+class UtilsVars:
+    already_fixed_encoding = False
+
+
+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) -> 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)
+        if len(parts) > 1:
+            month = xlate(parts[1], True)
+            if len(parts) > 2:
+                day = xlate(parts[2], True)
+    return day, month, year
+
+
+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))
+
+    return filelist
+
+
+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)]
+
+        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:
+    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
+
+    return str(data)
+
+
+def remove_articles(text: str) -> str:
+    text = text.casefold()
+    articles = [
+        "&",
+        "a",
+        "am",
+        "an",
+        "and",
+        "as",
+        "at",
+        "be",
+        "but",
+        "by",
+        "for",
+        "if",
+        "is",
+        "issue",
+        "it",
+        "it's",
+        "its",
+        "itself",
+        "of",
+        "or",
+        "so",
+        "the",
+        "the",
+        "with",
+    ]
+    new_text = ""
+    for word in text.split():
+        if word not in articles:
+            new_text += word + " "
+
+    new_text = new_text[:-1]
+
+    return new_text
+
+
+def sanitize_title(text: str, basic: bool = False) -> str:
+    # normalize unicode and convert to ascii. Does not work for everything eg ½ to 1⁄2 not 1/2
+    text = unicodedata.normalize("NFKD", text).casefold()
+    # comicvine keeps apostrophes a part of the word
+    text = text.replace("'", "")
+    text = text.replace('"', "")
+    if not basic:
+        # comicvine ignores punctuation and accents
+        # remove all characters that are not a letter, separator (space) or number
+        # replace any "dash punctuation" with a space
+        # makes sure that batman-superman and self-proclaimed stay separate words
+        text = "".join(
+            c if unicodedata.category(c)[0] not in "P" else " " for c in text if unicodedata.category(c)[0] in "LZNP"
+        )
+        # remove extra space and articles and all lower case
+        text = remove_articles(text).strip()
+
+    return text
+
+
+def titles_match(search_title: str, record_title: str, threshold: int = 90) -> bool:
+    sanitized_search = sanitize_title(search_title)
+    sanitized_record = sanitize_title(record_title)
+    ratio = int(rapidfuzz.fuzz.ratio(sanitized_search, sanitized_record))
+    logger.debug(
+        "search title: %s ; record title: %s ; ratio: %d ; match threshold: %d",
+        search_title,
+        record_title,
+        ratio,
+        threshold,
+    )
+    return ratio >= threshold
+
+
+def unique_file(file_name: pathlib.Path) -> pathlib.Path:
+    name = file_name.stem
+    counter = 1
+    while True:
+        if not file_name.exists():
+            return file_name
+        file_name = file_name.with_stem(name + " (" + str(counter) + ")")
+        counter += 1
+
+
+languages: dict[str | None, str | None] = defaultdict(lambda: None)
+
+countries: dict[str | None, str | None] = defaultdict(lambda: None)
+
+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
+
+
+def get_language_from_iso(iso: str | None) -> str | None:
+    return languages[iso]
+
+
+def get_language_iso(string: str | None) -> str | None:
+    if string is None:
+        return None
+    lang = string.casefold()
+
+    try:
+        return getattr(pycountry.languages.lookup(string), "alpha_2", None)
+    except LookupError:
+        pass
+    return lang
+
+
+def get_publisher(publisher: str) -> tuple[str, str]:
+    imprint = ""
+
+    for pub in publishers.values():
+        imprint, publisher, ok = pub[publisher]
+        if ok:
+            break
+
+    return (imprint, publisher)
+
+
+def update_publishers(new_publishers: Mapping[str, Mapping[str, str]]) -> None:
+    for publisher in new_publishers:
+        if publisher in publishers:
+            publishers[publisher].update(new_publishers[publisher])
+        else:
+            publishers[publisher] = ImprintDict(publisher, new_publishers[publisher])
+
+
+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
+    ImprintDict returns a tuple of (imprint, publisher, keyExists).
+    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:  # type: ignore
+        super().__init__(mapping, **kwargs)
+        self.publisher = publisher
+
+    def __missing__(self, key: str) -> None:
+        return None
+
+    def __getitem__(self, k: str) -> tuple[str, str, bool]:
+        item = super().__getitem__(k.casefold())
+        if k.casefold() == self.publisher.casefold():
+            return ("", self.publisher, True)
+        if item is None:
+            return ("", k, False)
+        else:
+            return (item, self.publisher, True)
+
+    def copy(self) -> ImprintDict:
+        return ImprintDict(self.publisher, super().copy())
+
+
+publishers: dict[str, ImprintDict] = {}
+
+
+def load_publishers() -> None:
+    try:
+        update_publishers(json.loads((comicapi.data.data_path / "publishers.json").read_text("utf-8")))
+    except Exception:
+        logger.exception("Failed to load publishers.json; The are no publishers or imprints loaded")

comicarchive.py

@@ -1,977 +0,0 @@
-"""
-A python class to represent a single comic, be it file or folder of images
-"""
-
-"""
-Copyright 2012  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.
-"""
-
-import zipfile
-import os
-import struct
-import sys
-import tempfile
-import subprocess
-import platform
-if platform.system() == "Windows":
-	import _subprocess
-import time
-
-import StringIO
-try: 
-	import Image
-	pil_available = True
-except ImportError:
-	pil_available = False
-	
-sys.path.insert(0, os.path.abspath(".") )
-import UnRAR2
-from UnRAR2.rar_exceptions import *
-
-from options import Options, MetaDataStyle
-from comicinfoxml import ComicInfoXml
-from comicbookinfo import ComicBookInfo
-from comet import CoMet
-from genericmetadata import GenericMetadata, PageType
-from filenameparser import FileNameParser
-from settings import ComicTaggerSettings
-
-class ZipArchiver:
-	
-	def __init__( self, path ):
-		self.path = path
-	
-	def getArchiveComment( self ):
-		zf = zipfile.ZipFile( self.path, 'r' )
-		comment = zf.comment
-		zf.close()
-		return comment
-
-	def setArchiveComment( self, comment ):
-		return self.writeZipComment( self.path, comment )
-
-	def readArchiveFile( self, archive_file ):
-		data = ""
-		zf = zipfile.ZipFile( self.path, 'r' )
-		try:
-			data = zf.read( archive_file )
-		except zipfile.BadZipfile as e:
-			print "bad zipfile [{0}]: {1} :: {2}".format(e, self.path, archive_file)
-			zf.close()	
-			raise IOError
-		except Exception as e:
-			zf.close()	
-			print "bad zipfile [{0}]: {1} :: {2}".format(e, self.path, archive_file)
-			raise IOError
-		finally:
-			zf.close()
-		return data
-
-	def removeArchiveFile( self, archive_file ):
-		try:
-			self.rebuildZipFile(  [ archive_file ] )
-		except:
-			return False
-		else:
-			return True
-			
-	def writeArchiveFile( self, archive_file, data ):
-		#  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
-		try:
-			self.rebuildZipFile(  [ archive_file ] )
-			
-			#now just add the archive file as a new one
-			zf = zipfile.ZipFile(self.path, mode='a', compression=zipfile.ZIP_DEFLATED ) 
-			zf.writestr( archive_file, data )
-			zf.close()
-			return True
-		except:
-			return False
-			
-	def getArchiveFilenameList( self ):		
-		zf = zipfile.ZipFile( self.path, 'r' )
-		namelist = zf.namelist()
-		zf.close()
-		return namelist
-	
-	# zip helper func
-	def rebuildZipFile( self, exclude_list ):
-		
-		# this recompresses the zip archive, without the files in the exclude_list
-		#print "Rebuilding zip {0} without {1}".format( self.path, exclude_list )
-		
-		# generate temp file
-		tmp_fd, tmp_name = tempfile.mkstemp( dir=os.path.dirname(self.path) )
-		os.close( tmp_fd )
-		
-		zin = zipfile.ZipFile (self.path, 'r')
-		zout = zipfile.ZipFile (tmp_name, 'w')
-		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
-		
-		zout.close()
-		zin.close()
-		
-		# replace with the new file 
-		os.remove( self.path )
-		os.rename( tmp_name, self.path )
-
-
-	def writeZipComment( self, filename, comment ):
-		"""
-		This is a custom function for writing a comment to a zip file,
-		since the built-in one doesn't seem to work on Windows and Mac OS/X
-
-		Fortunately, the zip comment is at the end of the file, and it's
-		easy to manipulate.  See this website for more info:
-		see: http://en.wikipedia.org/wiki/Zip_(file_format)#Structure
-		"""
-
-		#get file size
-		statinfo = os.stat(filename)
-		file_length = statinfo.st_size
-
-		try:
-			fo = open(filename, "r+b")
-
-			#the starting position, relative to EOF
-			pos = -4
-
-			found = False
-			value = bytearray()
-		
-			# walk backwards to find the "End of Central Directory" record
-			while ( not found ) and ( -pos != file_length ):
-				# seek, relative to EOF	
-				fo.seek( pos,  2)
-
-				value = fo.read( 4 )
-
-				#look for the end of central directory signature
-				if bytearray(value) == bytearray([ 0x50, 0x4b, 0x05, 0x06 ]):
-					found = True
-				else:
-					# not found, step back another byte
-					pos = pos - 1
-				#print pos,"{1} int: {0:x}".format(bytearray(value)[0], value)
-			
-			if found:
-				
-				# now skip forward 20 bytes to the comment length word
-				pos += 20
-				fo.seek( pos,  2)
-
-				# Pack the length of the comment string
-				format = "H"                   # one 2-byte integer
-				comment_length = struct.pack(format, len(comment)) # pack integer in a binary string
-				
-				# write out the length
-				fo.write( comment_length )
-				fo.seek( pos+2,  2)
-				
-				# write out the comment itself
-				fo.write( comment )
-				fo.truncate()
-				fo.close()
-			else:
-				raise Exception('Failed to write comment to zip file!')
-		except:
-			return False
-		else:
-			return True
-
-	def copyFromArchive( self, otherArchive ):
-		# Replace the current zip with one copied from another archive
-		try:		
-			zout = zipfile.ZipFile (self.path, 'w')
-			for fname in otherArchive.getArchiveFilenameList():
-				data = otherArchive.readArchiveFile( fname )	
-				if data is not None:
-					zout.writestr( fname, data )
-			zout.close()
-			
-			#preserve the old comment
-			comment = otherArchive.getArchiveComment()
-			if comment is not None:
-				if not self.writeZipComment( self.path, comment ):
-					return False
-		except  Exception as e:
-			print "Error while copying to {0}: {1}".format(self.path, e)
-			return False
-		else:
-			return True
-
-		
-#------------------------------------------
-# RAR implementation
-	
-class RarArchiver:
-	
-	devnull = None
-	def __init__( self, path ):
-		self.path = path
-		self.rar_exe_path = None
-
-		if RarArchiver.devnull is None:
-			RarArchiver.devnull = open(os.devnull, "w")
-
-		# windows only, keeps the cmd.exe from popping up
-		if platform.system() == "Windows":
-			self.startupinfo = subprocess.STARTUPINFO()
-			self.startupinfo.dwFlags |= _subprocess.STARTF_USESHOWWINDOW
-		else:
-			self.startupinfo = None
-
-	def __del__(self):
-		#RarArchiver.devnull.close()
-		pass
-
-	def getArchiveComment( self ):
-		
-		rarc = self.getRARObj()
-		return rarc.comment		
-
-	def setArchiveComment( self, comment ):
-
-		if self.rar_exe_path is not None:
-			try:
-				# write comment to temp file
-				tmp_fd, tmp_name = tempfile.mkstemp()
-				f = os.fdopen(tmp_fd, 'w+b')
-				f.write( comment )		
-				f.close()
-
-				working_dir = os.path.dirname( os.path.abspath( self.path ) )
-
-				# use external program to write comment to Rar archive
-				subprocess.call([self.rar_exe_path, 'c', '-w' + working_dir , '-c-', '-z' + tmp_name, self.path], 
-					startupinfo=self.startupinfo, 
-					stdout=RarArchiver.devnull)
-				
-				if platform.system() == "Darwin":
-					time.sleep(1)
-					
-				os.remove( tmp_name)
-			except:
-				return False
-			else:
-				return True
-		else:
-			return False
-			
-	def readArchiveFile( self, archive_file ):
-
-		# Make sure to escape brackets, since some funky stuff is going on
-		# underneath with "fnmatch"
-		archive_file = archive_file.replace("[", '[[]')
-		entries = []
-
-		rarc = self.getRARObj()
-
-		tries = 0
-		while tries < 10:
-			try:
-				tries = tries+1
-				entries = rarc.read_files( archive_file )
-
-				if entries[0][0].size != len(entries[0][1]):
-					print "readArchiveFile(): [file is not expected size: {0} vs {1}]  {2}:{3} [attempt # {4}]".format(
-								entries[0][0].size,len(entries[0][1]), self.path, archive_file, tries)
-					continue
-				
-			except (OSError, IOError) as e:
-				print "readArchiveFile(): [{0}]  {1}:{2} attempt#{3}".format(str(e), self.path, archive_file, tries)
-				time.sleep(1)
-			except Exception as e:
-				print "Unexpected exception in readArchiveFile(): [{0}] for {1}:{2} attempt#{3}".format(str(e), self.path, archive_file, tries)
-				break
-
-			else:
-				#Success"
-				#entries is a list of of tuples:  ( rarinfo, filedata)
-				if tries > 1:
-					print "Attempted read_files() {0} times".format(tries)
-				if (len(entries) == 1):
-					return entries[0][1]
-				else:
-					raise IOError
-			
-		raise IOError
-		
-
-		
-	def writeArchiveFile( self, archive_file, data ):
-
-		if self.rar_exe_path is not None:
-			try:
-				tmp_folder = tempfile.mkdtemp()
-
-				tmp_file = os.path.join( tmp_folder, archive_file )
-				
-				working_dir = os.path.dirname( os.path.abspath( self.path ) )
-
-				# TODO: will this break if 'archive_file' is in a subfolder. i.e. "foo/bar.txt"
-				# will need to create the subfolder above, I guess...
-				f = open(tmp_file, 'w')
-				f.write( data )		
-				f.close()
-				
-				# use external program to write file to Rar archive
-				subprocess.call([self.rar_exe_path, 'a', '-w' + working_dir ,'-c-', '-ep', self.path, tmp_file], 
-					startupinfo=self.startupinfo,
-					stdout=RarArchiver.devnull)
-
-				if platform.system() == "Darwin":
-					time.sleep(1)
-				os.remove( tmp_file)
-				os.rmdir( tmp_folder)
-			except:
-				return False
-			else:
-				return True
-		else:
-			return False
-			
-	def removeArchiveFile( self, archive_file ):
-		if self.rar_exe_path is not None:
-			try:
-				# use external program to remove file from Rar archive
-				subprocess.call([self.rar_exe_path, 'd','-c-', self.path, archive_file], 
-					startupinfo=self.startupinfo, 				   
-					stdout=RarArchiver.devnull)
-
-				if platform.system() == "Darwin":
-					time.sleep(1)
-			except:
-				return False
-			else:
-				return True
-		else:
-			return False
-			
-	def getArchiveFilenameList( self ):
-
-		rarc = self.getRARObj()
-		#namelist = [ item.filename for item in rarc.infolist() ]
-		#return namelist
-
-		tries = 0
-		while tries < 10:
-			try:
-				tries = tries+1
-				namelist = [ item.filename for item in rarc.infolist() ]
-			
-			except (OSError, IOError) as e:
-				print "getArchiveFilenameList(): [{0}] {1} attempt#{2}".format(str(e), self.path, tries)
-				time.sleep(1)
-
-			else:
-				#Success"
-				return namelist
-			
-		raise e
-			
-		
-	def getRARObj( self ):
-		tries = 0
-		while tries < 10:
-			try:
-				tries = tries+1
-				rarc = UnRAR2.RarFile( self.path )
-			
-			except (OSError, IOError) as e:
-				print "getRARObj(): [{0}] {1} attempt#{2}".format(str(e), self.path, tries)
-				time.sleep(1)
-
-			else:
-				#Success"
-				return rarc
-			
-		raise e
-		
-#------------------------------------------
-# Folder implementation
-class FolderArchiver:
-	
-	def __init__( self, path ):
-		self.path = path
-		self.comment_file_name = "ComicTaggerFolderComment.txt" 
-
-	def getArchiveComment( self ):
-		return self.readArchiveFile( self.comment_file_name )
-	
-	def setArchiveComment( self, comment ):
-		return self.writeArchiveFile( self.comment_file_name, comment )
-		
-	def readArchiveFile( self, archive_file ):
-		
-		data = ""
-		fname = os.path.join( self.path, archive_file )
-		try:
-			with open( fname, 'rb' ) as f: 
-				data = f.read()
-				f.close()			
-		except IOError as e:
-			pass
-		
-		return data
-
-	def writeArchiveFile( self, archive_file, data ):
-
-		fname = os.path.join( self.path, archive_file )
-		try:
-			with open(fname, 'w+') as f: 
-				f.write( data )
-				f.close()
-		except:
-			return False
-		else:
-			return True
-		
-	def removeArchiveFile( self, archive_file ):
-
-		fname = os.path.join( self.path, archive_file )
-		try:
-			os.remove( fname )
-		except:
-			return False
-		else:
-			return True
-		
-	def getArchiveFilenameList( self ):
-		return self.listFiles( self.path )
-		
-	def listFiles( self, folder ):
-		
-		itemlist = list()
-
-		for item in os.listdir( folder ):
-			itemlist.append( item )
-			if os.path.isdir( item ):
-				itemlist.extend( self.listFiles( os.path.join( folder, item ) ))
-
-		return itemlist
-
-#------------------------------------------
-# Unknown implementation
-class UnknownArchiver:
-	
-	def __init__( self, path ):
-		self.path = path
-
-	def getArchiveComment( self ):
-		return ""
-	def setArchiveComment( self, comment ):
-		return False
-	def readArchiveFile( self ):
-		return ""
-	def writeArchiveFile( self, archive_file, data ):
-		return False
-	def removeArchiveFile( self, archive_file ):
-		return False
-	def getArchiveFilenameList( self ):
-		return []
-
-#------------------------------------------------------------------
-class ComicArchive:
-
-	logo_data = None
-
-	class ArchiveType:
-		Zip, Rar, Folder, Unknown = range(4)
-    
-	def __init__( self, path ):
-		self.path = path
-		self.ci_xml_filename = 'ComicInfo.xml'
-		self.comet_default_filename = 'CoMet.xml'
-		self.resetCache()
-		
-		if self.zipTest():
-			self.archive_type =  self.ArchiveType.Zip
-			self.archiver = ZipArchiver( self.path )
-			
-		elif self.rarTest(): 
-			self.archive_type =  self.ArchiveType.Rar
-			self.archiver = RarArchiver( self.path )
-			
-		elif os.path.isdir( self.path ):
-			self.archive_type =  self.ArchiveType.Folder
-			self.archiver = FolderArchiver( self.path )			
-		else:
-			self.archive_type =  self.ArchiveType.Unknown
-			self.archiver = UnknownArchiver( self.path )
-
-		if ComicArchive.logo_data is None:
-			fname = os.path.join(ComicTaggerSettings.baseDir(), 'graphics','nocover.png' )
-			with open(fname, 'rb') as fd:
-				ComicArchive.logo_data = fd.read()				
-				print len(ComicArchive.logo_data)
-
-	# Clears the cached data
-	def resetCache( self ):
-		self.has_cix = None
-		self.has_cbi = None
-		self.has_comet = None
-		self.comet_filename = None
-		self.page_count  = None
-		self.page_list  = None
-		self.cix_md  = None
-		self.cbi_md  = None
-		self.comet_md  = None
-	
-	def rename( self, path ):
-		self.path = path
-		self.archiver.path = path
-		
-	def setExternalRarProgram( self, rar_exe_path ):
-		if self.isRar():
-			self.archiver.rar_exe_path = rar_exe_path
-
-	def zipTest( self ):
-		return zipfile.is_zipfile( self.path )
-
-	def rarTest( self ):
-		try:
-			rarc = UnRAR2.RarFile( self.path )
-		except: # InvalidRARArchive:
-			return False
-		else:
-			return True
-
-			
-	def isZip( self ):
-		return self.archive_type ==  self.ArchiveType.Zip
-		
-	def isRar( self ):
-		return self.archive_type ==  self.ArchiveType.Rar
-	
-	def isFolder( self ):
-		return self.archive_type ==  self.ArchiveType.Folder
-
-	def isWritable( self, check_rar_status=True ):	
-		if self.archive_type == self.ArchiveType.Unknown :
-			return False
-		
-		elif check_rar_status and self.isRar() and self.archiver.rar_exe_path is None:
-			return False
-			
-		elif not os.access(self.path, os.W_OK):
-			return False
-		
-		elif ((self.archive_type != self.ArchiveType.Folder) and 
-		        (not os.access( os.path.dirname( os.path.abspath(self.path)), os.W_OK ))):
-			return False
-
-		return True
-
-	def isWritableForStyle( self, data_style ):
-
-		if self.isRar() and data_style == MetaDataStyle.CBI:
-			return False
-
-		return self.isWritable()
-
-	def seemsToBeAComicArchive( self ):
-
-		# Do we even care about extensions??
-		ext = os.path.splitext(self.path)[1].lower()
-
-		if ( 
-		      ( self.isZip() or  self.isRar() or self.isFolder() )
-		      and
-		      ( self.getNumberOfPages() > 2)
-
-			):
-			return True
-		else:	
-			return False
-
-	def readMetadata( self, style ):
-		
-		if style == MetaDataStyle.CIX:
-			return self.readCIX()
-		elif style == MetaDataStyle.CBI:
-			return self.readCBI()
-		elif style == MetaDataStyle.COMET:
-			return self.readCoMet()
-		else:
-			return GenericMetadata()
-
-	def writeMetadata( self, metadata, style ):
-		
-		retcode = None
-		if style == MetaDataStyle.CIX:
-			retcode = self.writeCIX( metadata )
-		elif style == MetaDataStyle.CBI:
-			retcode = self.writeCBI( metadata )
-		elif style == MetaDataStyle.COMET:
-			retcode = self.writeCoMet( metadata )
-		return retcode
-		
-
-	def hasMetadata( self, style ):
-		
-		if style == MetaDataStyle.CIX:
-			return self.hasCIX()
-		elif style == MetaDataStyle.CBI:
-			return self.hasCBI()
-		elif style == MetaDataStyle.COMET:
-			return self.hasCoMet()
-		else:
-			return False
-	
-	def removeMetadata( self, style ):
-		retcode = True
-		if style == MetaDataStyle.CIX:
-			retcode = self.removeCIX()
-		elif style == MetaDataStyle.CBI:
-			retcode = self.removeCBI()
-		elif style == MetaDataStyle.COMET:
-			retcode = self.removeCoMet()
-		return retcode
-
-	def getPage( self, index ):
-		
-		image_data = None
-		
-		filename = self.getPageName( index )
-
-		if filename is not None:
-			try:
-				image_data = self.archiver.readArchiveFile( filename )
-			except IOError:
-				print "Error reading in page.  Substituting logo page."
-				image_data = ComicArchive.logo_data				
-
-		return image_data
-
-	def getPageName( self, index ):
-		
-		page_list = self.getPageNameList()
-		
-		num_pages = len( page_list )
-		if num_pages == 0 or index >= num_pages:
-			return None
-	
-		return  page_list[index]
-
-	def getPageNameList( self , sort_list=True):
-		
-		if self.page_list is None:
-			# get the list file names in the archive, and sort
-			files = self.archiver.getArchiveFilenameList()
-			
-			# seems like some archive creators are on  Windows, and don't know about case-sensitivity!
-			if sort_list:
-				files.sort(key=lambda x: x.lower())
-			
-			# make a sub-list of image files
-			self.page_list = []
-			for name in files:
-				if ( name[-4:].lower() in [ ".jpg", "jpeg", ".png" ] and os.path.basename(name)[0] != "." ):
-					self.page_list.append(name)
-				
-		return self.page_list
-
-	def getNumberOfPages( self ):
-		
-		if self.page_count is None:
-			self.page_count = len( self.getPageNameList( ) )
-		return self.page_count
-
-	def readCBI( self ):
-		if self.cbi_md is None:
-			raw_cbi = self.readRawCBI()
-			if raw_cbi is None:
-				self.cbi_md = GenericMetadata()
-			else:
-				self.cbi_md = ComicBookInfo().metadataFromString( raw_cbi )
-			
-			self.cbi_md.setDefaultPageList( self.getNumberOfPages() )
-				
-		return self.cbi_md
-	
-	def readRawCBI( self ):
-		if ( not self.hasCBI() ):
-			return None
-
-		return self.archiver.getArchiveComment()
-
-	def hasCBI(self):
-		if self.has_cbi is None:
-
-			#if ( not ( self.isZip() or self.isRar()) or not self.seemsToBeAComicArchive() ): 
-			if not self.seemsToBeAComicArchive(): 
-				self.has_cbi = False
-			else:
-				comment = self.archiver.getArchiveComment()
-				self.has_cbi = ComicBookInfo().validateString( comment )
-			
-		return self.has_cbi
-	
-	def writeCBI( self, metadata ):
-		if metadata is not None:
-			self.applyArchiveInfoToMetadata( metadata )
-			cbi_string = ComicBookInfo().stringFromMetadata( metadata )
-			write_success =  self.archiver.setArchiveComment( cbi_string )
-			if write_success:
-				self.has_cbi = True
-				self.cbi_md = metadata
-			else:
-				self.resetCache()
-			return write_success
-		else:
-			return False
-		
-	def removeCBI( self ):
-		if self.hasCBI():
-			write_success = self.archiver.setArchiveComment( "" )
-			if write_success:
-				self.has_cbi = False
-				self.cbi_md = None
-			else:
-				self.resetCache()
-			return write_success
-		return True	
-		
-	def readCIX( self ):
-		if self.cix_md is None:
-			raw_cix = self.readRawCIX()
-			if raw_cix is None or raw_cix == "":
-				self.cix_md = GenericMetadata()
-			else:
-				self.cix_md = ComicInfoXml().metadataFromString( raw_cix )
-
-			#validate the existing page list (make sure count is correct)
-			if len ( self.cix_md.pages ) !=  0 :
-				if len ( self.cix_md.pages ) != self.getNumberOfPages():
-					# pages array doesn't match the actual number of images we're seeing
-					# in the archive, so discard the data
-					self.cix_md.pages = []
-				
-			if len( self.cix_md.pages ) == 0:
-				self.cix_md.setDefaultPageList( self.getNumberOfPages() )
-			
-		return self.cix_md
-
-	def readRawCIX( self ):
-		if not self.hasCIX():
-			return None
-		try:
-			raw_cix = self.archiver.readArchiveFile( self.ci_xml_filename )
-		except IOError:
-			print "Error reading in raw CIX!"
-			raw_cix = ""
-		return  raw_cix
-		
-	def writeCIX(self, metadata):
-
-		if metadata is not None:
-			self.applyArchiveInfoToMetadata( metadata, calc_page_sizes=True )
-			cix_string = ComicInfoXml().stringFromMetadata( metadata )
-			write_success = self.archiver.writeArchiveFile( self.ci_xml_filename, cix_string )
-			if write_success:
-				self.has_cix = True
-				self.cix_md = metadata
-			else:
-				self.resetCache()
-			return write_success
-		else:
-			return False
-			
-	def removeCIX( self ):
-		if self.hasCIX():
-			write_success = self.archiver.removeArchiveFile( self.ci_xml_filename )
-			if write_success:
-				self.has_cix = False
-				self.cix_md = None
-			else:
-				self.resetCache()
-			return write_success
-		return True
-		
-		
-	def hasCIX(self):
-		if self.has_cix is None:
-
-			if not self.seemsToBeAComicArchive():
-				self.has_cix = False
-			elif self.ci_xml_filename in self.archiver.getArchiveFilenameList():
-				self.has_cix = True
-			else:
-				self.has_cix = False
-		return self.has_cix
-
-
-	def readCoMet( self ):
-		if self.comet_md is None:
-			raw_comet = self.readRawCoMet()
-			if raw_comet is None or raw_comet == "":
-				self.comet_md = GenericMetadata()
-			else:
-				self.comet_md = CoMet().metadataFromString( raw_comet )
-			
-			self.comet_md.setDefaultPageList( self.getNumberOfPages() )
-			#use the coverImage value from the comet_data to mark the cover in this struct
-			# walk through list of images in file, and find the matching one for md.coverImage
-			# need to remove the existing one in the default
-			if self.comet_md.coverImage is not None:
-				cover_idx = 0
-				for idx,f in enumerate(self.getPageNameList()):
-					if self.comet_md.coverImage == f:
-						cover_idx = idx
-						break
-				if cover_idx != 0:
-					del (self.comet_md.pages[0]['Type'] )
-					self.comet_md.pages[ cover_idx ]['Type'] = PageType.FrontCover
-
-		return self.comet_md	
-
-	def readRawCoMet( self ):
-		if not self.hasCoMet():
-			print self.path, "doesn't have CoMet data!"
-			return None
-
-		try:
-			raw_comet = self.archiver.readArchiveFile( self.comet_filename )
-		except IOError:
-			print "Error reading in raw CoMet!"
-			raw_comet = ""
-		return  raw_comet
-		
-	def writeCoMet(self, metadata):
-
-		if metadata is not None:
-			if not self.hasCoMet():
-				self.comet_filename = self.comet_default_filename
-			
-			self.applyArchiveInfoToMetadata( metadata )
-			# Set the coverImage value, if it's not the first page
-			cover_idx = int(metadata.getCoverPageIndexList()[0])
-			if cover_idx != 0:
-				metadata.coverImage = self.getPageName( cover_idx )
-		
-			comet_string = CoMet().stringFromMetadata( metadata )
-			write_success = self.archiver.writeArchiveFile( self.comet_filename, comet_string )
-			if write_success:
-				self.has_comet = True
-				self.comet_md = metadata
-			else:
-				self.resetCache()
-			return write_success
-		else:
-			return False
-			
-	def removeCoMet( self ):
-		if self.hasCoMet():
-			write_success = self.archiver.removeArchiveFile( self.comet_filename )
-			if write_success:
-				self.has_comet = False
-				self.comet_md = None
-			else:
-				self.resetCache()
-			return write_success
-		return True
-		
-	def hasCoMet(self):
-		if self.has_comet is None:
-			self.has_comet = False
-			if not self.seemsToBeAComicArchive():
-				return self.has_comet
-			
-			#look at all xml files in root, and search for CoMet data, get first
-			for n in self.archiver.getArchiveFilenameList():
-				if ( os.path.dirname(n) == "" and
-					os.path.splitext(n)[1].lower() == '.xml'):
-					# read in XML file, and validate it
-					try:
-						data = self.archiver.readArchiveFile( n )
-					except:
-						data = ""
-						print "Error reading in Comet XML for validation!"
-					if CoMet().validateString( data ):
-						# since we found it, save it!
-						self.comet_filename = n
-						self.has_comet = True
-						break
-						
-			return self.has_comet
-				
-
-
-	def applyArchiveInfoToMetadata( self, md, calc_page_sizes=False):
-		md.pageCount = self.getNumberOfPages()
-		
-		if calc_page_sizes:
-			for p in md.pages:
-				idx = int( p['Image'] )
-				if pil_available:
-					if 'ImageSize' not in p or 'ImageHeight' not in p or 'ImageWidth' not in p:
-						data = self.getPage( idx )
-						if data is not None:
-							try:
-								im = Image.open(StringIO.StringIO(data))
-								w,h = im.size
-								
-								p['ImageSize'] = str(len(data))
-								p['ImageHeight'] = str(h)
-								p['ImageWidth'] = str(w)
-							except IOError:
-								p['ImageSize'] = str(len(data))
-									
-				else:
-					if 'ImageSize' not in p:
-						data = self.getPage( idx )
-						p['ImageSize'] = str(len(data))
-
-
-			
-	def metadataFromFilename( self ):
-		 
-		metadata = GenericMetadata()
-		
-		fnp = FileNameParser()
-		fnp.parseFilename( self.path )
-
-		if fnp.issue != "":
-			metadata.issue = fnp.issue
-		if fnp.series != "":
-			metadata.series = fnp.series
-		if fnp.volume != "":
-			metadata.volume = fnp.volume
-		if fnp.year != "":
-			metadata.year = fnp.year
-		if fnp.issue_count != "":
-			metadata.issueCount = fnp.issue_count
-
-		metadata.isEmpty = False
-
-		return metadata
-
-	def exportAsZip( self, zipfilename ):
-		if self.archive_type == self.ArchiveType.Zip:
-			# nothing to do, we're already a zip
-			return True
-		
-		zip_archiver = ZipArchiver( zipfilename )
-		return zip_archiver.copyFromArchive( self.archiver )
-		

comicbookinfo.py

@@ -1,152 +0,0 @@
-"""
-A python class to encapsulate the ComicBookInfo data 
-"""
-
-"""
-Copyright 2012  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.
-"""
-
-
-import json
-from datetime import datetime
-import zipfile
-
-from genericmetadata import GenericMetadata
-import utils
-import ctversion
-
-class ComicBookInfo:
-		 
-
-	def metadataFromString( self, string ):
-	
-		cbi_container = json.loads( unicode(string, 'utf-8') )
-
-		metadata = GenericMetadata()
-
-		cbi = cbi_container[ 'ComicBookInfo/1.0' ]
-
-		#helper func 
-		# If item is not in CBI, return None
-		def xlate( cbi_entry):
-			if cbi_entry in cbi:
-				return cbi[cbi_entry] 
-			else:	
-				return None 
-		
-		metadata.series =            xlate( 'series' )
-		metadata.title =             xlate( 'title' )
-		metadata.issue =             xlate( 'issue' )
-		metadata.publisher =         xlate( 'publisher' )
-		metadata.month =             xlate( 'publicationMonth' )
-		metadata.year =              xlate( 'publicationYear' )
-		metadata.issueCount =        xlate( 'numberOfIssues' )
-		metadata.comments =          xlate( 'comments' )
-		metadata.credits =           xlate( 'credits' )
-		metadata.genre =             xlate( 'genre' )
-		metadata.volume =            xlate( 'volume' )
-		metadata.volumeCount =       xlate( 'numberOfVolumes' )
-		metadata.language =          xlate( 'language' )
-		metadata.country =           xlate( 'country' )
-		metadata.criticalRating =    xlate( 'rating' )
-		metadata.tags =              xlate( 'tags' )
-		
-		# make sure credits and tags are at least empty lists and not None
-		if metadata.credits is None:
-			metadata.credits = []
-		if metadata.tags is None:
-			metadata.tags = []
-			
-		#need to massage the language string to be ISO
-		if metadata.language is not None:
-			# reverse look-up
-			pattern = metadata.language
-			metadata.language = None
-			for key in utils.getLanguageDict():
-				if utils.getLanguageDict()[ key ] == pattern.encode('utf-8'):
-					metadata.language = key
-					break
-		
-		metadata.isEmpty = False
-		
-		return metadata
-
-	def stringFromMetadata( self, metadata ):
-
-		cbi_container = self.createJSONDictionary( metadata )
-		return json.dumps( cbi_container )
-	
-	#verify that the string actually contains CBI data in JSON format
-	def validateString( self, string ):
-		
-		try:
-			cbi_container = json.loads( string )
-		except:
-			return False
-			
-		return ( 'ComicBookInfo/1.0' in cbi_container )
-
-
-	def createJSONDictionary( self, metadata ):
-		
-		# Create the dictionary that we will convert to JSON text
-		cbi = dict()
-		cbi_container = {'appID' : 'ComicTagger/' + ctversion.version, 
-		                 'lastModified' : str(datetime.now()), 
-		                 'ComicBookInfo/1.0' : cbi }
-		
-		#helper func
-		def assign( cbi_entry, md_entry):
-			if md_entry is not None:
-				cbi[cbi_entry] = md_entry
-			
-		#helper func
-		def toInt(s):
-			i = None
-			if type(s) == str or type(s) == int:
-				try:
-					i = int(s)
-				except ValueError:
-					pass
-			return i
-				
-		assign( 'series', metadata.series )
-		assign( 'title', metadata.title )
-		assign( 'issue', metadata.issue )
-		assign( 'publisher', metadata.publisher )
-		assign( 'publicationMonth', toInt(metadata.month) )
-		assign( 'publicationYear', toInt(metadata.year) )
-		assign( 'numberOfIssues', toInt(metadata.issueCount) )
-		assign( 'comments', metadata.comments )
-		assign( 'genre', metadata.genre )
-		assign( 'volume', toInt(metadata.volume) )
-		assign( 'numberOfVolumes', toInt(metadata.volumeCount) )
-		assign( 'language', utils.getLanguageFromISO(metadata.language) )
-		assign( 'country', metadata.country )
-		assign( 'rating', metadata.criticalRating )
-		assign( 'credits', metadata.credits )
-		assign( 'tags', metadata.tags )
-		
-		return cbi_container
-	
-
-	def writeToExternalFile( self, filename,  metadata ):
-
-		cbi_container = self.createJSONDictionary(metadata)
-
-		f = open(filename, 'w')
-		f.write(json.dumps(cbi_container, indent=4))
-		f.close
-

comicinfoxml.py

@@ -1,289 +0,0 @@
-"""
-A python class to encapsulate ComicRack's ComicInfo.xml data 
-"""
-
-"""
-Copyright 2012  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 datetime import datetime
-import zipfile
-from pprint import pprint 
-import xml.etree.ElementTree as ET
-from genericmetadata import GenericMetadata
-import utils
-
-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 getParseableCredits( self ):
-		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 metadataFromString( self, string ):
-
-		tree = ET.ElementTree(ET.fromstring( string ))
-		return self.convertXMLToMetadata( tree )
-
-	def stringFromMetadata( self, metadata ):
-
-		header = '<?xml version="1.0"?>\n'
-		
-		tree = self.convertMetadataToXML( self, metadata )
-		return header + ET.tostring(tree.getroot())
-
-	def indent( self, elem, level=0 ):
-		# for making the XML output readable
-		i = "\n" + level*"  "
-		if len(elem):
-			if not elem.text or not elem.text.strip():
-				elem.text = i + "  "
-			if not elem.tail or not elem.tail.strip():
-				elem.tail = i
-			for elem in elem:
-				self.indent( elem, level+1 )
-			if not elem.tail or not elem.tail.strip():
-				elem.tail = i
-		else:
-			if level and (not elem.tail or not elem.tail.strip()):
-				elem.tail = i
-	
-	def convertMetadataToXML( self, filename, metadata ):
-
-		#shorthand for the metadata
-		md = metadata
-
-		# 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, md_entry):
-			if md_entry is not None:
-				ET.SubElement(root, cix_entry).text = u"{0}".format(md_entry)
-
-		assign( 'Series', md.series )
-		assign( 'Number', md.issue )
-		assign( 'Title', md.title )
-		assign( 'Count', md.issueCount )
-		assign( 'Volume', md.volume )
-		assign( 'AlternateSeries', md.alternateSeries )
-		assign( 'AlternateNumber', md.alternateNumber )
-		assign( 'AlternateCount', md.alternateCount )
-		assign( 'Summary', md.comments )
-		assign( 'Notes', md.notes )
-		assign( 'Year', md.year )
-		assign( 'Month', md.month )
-		assign( 'Publisher', md.publisher )
-		assign( 'Imprint', md.imprint )
-		assign( 'Genre', md.genre )
-		assign( 'Web', md.webLink )
-		assign( 'PageCount', md.pageCount )
-		assign( 'Format', md.format )
-		assign( 'LanguageISO', md.language )
-		assign( 'Manga', md.manga )
-		assign( 'Characters', md.characters )
-		assign( 'Teams', md.teams )
-		assign( 'Locations', md.locations )
-		assign( 'ScanInformation', md.scanInfo )
-		assign( 'StoryArc', md.storyArc )
-		assign( 'SeriesGroup', md.seriesGroup )
-		assign( 'AgeRating', md.maturityRating )
-
-		if md.blackAndWhite is not None and md.blackAndWhite:
-			ET.SubElement(root, 'BlackAndWhite').text = "Yes"
-
-		# need to specially process the credits, since they are structured differently than CIX	
-		credit_writer_list    = list()
-		credit_penciller_list = list()
-		credit_inker_list     = list()
-		credit_colorist_list  = list()
-		credit_letterer_list  = list()
-		credit_cover_list     = list()
-		credit_editor_list    = list()
-		
-		# first, loop thru credits, and build a list for each role that CIX supports
-		for credit in metadata.credits:
-
-			if credit['role'].lower() in set( self.writer_synonyms ):
-				credit_writer_list.append(credit['person'].replace(",",""))
-
-			if credit['role'].lower() in set( self.penciller_synonyms ):
-				credit_penciller_list.append(credit['person'].replace(",",""))
-				
-			if credit['role'].lower() in set( self.inker_synonyms ):
-				credit_inker_list.append(credit['person'].replace(",",""))
-				
-			if credit['role'].lower() in set( self.colorist_synonyms ):
-				credit_colorist_list.append(credit['person'].replace(",",""))
-
-			if credit['role'].lower() in set( self.letterer_synonyms ):
-				credit_letterer_list.append(credit['person'].replace(",",""))
-
-			if credit['role'].lower() in set( self.cover_synonyms ):
-				credit_cover_list.append(credit['person'].replace(",",""))
-
-			if credit['role'].lower() in set( self.editor_synonyms ):
-				credit_editor_list.append(credit['person'].replace(",",""))
-				
-		# second, convert each list to string, and add to XML struct
-		if len( credit_writer_list ) > 0:
-			node = ET.SubElement(root, 'Writer')
-			node.text = utils.listToString( credit_writer_list )
-
-		if len( credit_penciller_list ) > 0:
-			node = ET.SubElement(root, 'Penciller')
-			node.text = utils.listToString( credit_penciller_list )
-
-		if len( credit_inker_list ) > 0:
-			node = ET.SubElement(root, 'Inker')
-			node.text = utils.listToString( credit_inker_list )
-
-		if len( credit_colorist_list ) > 0:
-			node = ET.SubElement(root, 'Colorist')
-			node.text = utils.listToString( credit_colorist_list )
-
-		if len( credit_letterer_list ) > 0:
-			node = ET.SubElement(root, 'Letterer')
-			node.text = utils.listToString( credit_letterer_list )
-
-		if len( credit_cover_list ) > 0:
-			node = ET.SubElement(root, 'CoverArtist')
-			node.text = utils.listToString( credit_cover_list )
-		
-		if len( credit_editor_list ) > 0:
-			node = ET.SubElement(root, 'Editor')
-			node.text = utils.listToString( credit_editor_list )
-		
-		#  loop and add the page entries under pages node
-		if len( md.pages ) > 0:
-			pages_node = ET.SubElement(root, 'Pages')
-			for page_dict in md.pages:
-				page_node = ET.SubElement(pages_node, 'Page')
-				page_node.attrib = page_dict
-
-		# self pretty-print
-		self.indent(root)
-
-		# wrap it in an ElementTree instance, and save as XML
-		tree = ET.ElementTree(root)
-		return tree
-				 
-
-	def convertXMLToMetadata( self, tree ):
-			
-		root = tree.getroot()
-
-		if root.tag != 'ComicInfo':
-			raise 1
-			return None
-
-		metadata = GenericMetadata()
-		md = metadata
-	
-		
-		# Helper function
-		def xlate( tag ):
-			node = root.find( tag )
-			if node is not None:
-				return node.text
-			else:
-				return None
-				
-		md.series =           xlate( 'Series' )
-		md.title =            xlate( 'Title' )
-		md.issue =            xlate( 'Number' )
-		md.issueCount =       xlate( 'Count' )
-		md.volume =           xlate( 'Volume' )
-		md.alternateSeries =  xlate( 'AlternateSeries' )
-		md.alternateNumber =  xlate( 'AlternateNumber' )
-		md.alternateCount =   xlate( 'AlternateCount' )
-		md.comments =         xlate( 'Summary' )
-		md.notes =            xlate( 'Notes' )
-		md.year =             xlate( 'Year' )
-		md.month =            xlate( 'Month' )
-		md.publisher =        xlate( 'Publisher' )
-		md.imprint =          xlate( 'Imprint' )
-		md.genre =            xlate( 'Genre' )
-		md.webLink =          xlate( 'Web' )
-		md.language =         xlate( 'LanguageISO' )
-		md.format =           xlate( 'Format' )
-		md.manga =            xlate( 'Manga' )
-		md.characters =       xlate( 'Characters' )
-		md.teams =            xlate( 'Teams' )
-		md.locations =        xlate( 'Locations' )
-		md.pageCount =        xlate( 'PageCount' )
-		md.scanInfo =         xlate( 'ScanInformation' )
-		md.storyArc =         xlate( 'StoryArc' )
-		md.seriesGroup =      xlate( 'SeriesGroup' )
-		md.maturityRating =   xlate( 'AgeRating' )
-
-		tmp = xlate( 'BlackAndWhite' )
-		md.blackAndWhite = False
-		if tmp is not None and tmp.lower() in [ "yes", "true", "1" ]:
-			md.blackAndWhite = True
-		# Now extract the credit info
-		for n in root:
-			if (  n.tag == 'Writer' or 
-				n.tag == 'Penciller' or
-				n.tag == 'Inker' or
-				n.tag == 'Colorist' or
-				n.tag == 'Letterer' or
-				n.tag == 'Editor' 
-			):
-				for name in n.text.split(','):
-					metadata.addCredit( name.strip(), n.tag )
-
-			if n.tag == 'CoverArtist':
-				for name in n.text.split(','):
-					metadata.addCredit( name.strip(), "Cover" )
-
-		# parse page data now	
-		pages_node = root.find( "Pages" )
-		if pages_node is not None:			
-			for page in pages_node:
-				metadata.pages.append( page.attrib )
-				#print page.attrib
-
-		metadata.isEmpty = False
-		
-		return metadata
-
-	def writeToExternalFile( self, filename, metadata ):
-		
-		tree = self.convertMetadataToXML( self, metadata )
-		#ET.dump(tree)		
-		tree.write(filename, encoding='utf-8')
-	
-	def readFromExternalFile( self, filename ):
-
-		tree = ET.parse( filename )
-		return self.convertXMLToMetadata( tree )
-

comictagger.py

@@ -1,507 +1,10 @@
-#!/usr/bin/python
+#!/usr/bin/env python3
+from __future__ import annotations
 
-"""
-A python script to tag comic archives
-"""
+import localefix
+from comictaggerlib.main import App
 
-"""
-Copyright 2012  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.
-"""
-
-import sys
-import signal
-import os
-import traceback
-import time
-from pprint import pprint
-import json
-import platform
-import locale
-
-filename_encoding = sys.getfilesystemencoding()
-	
-try:
-	qt_available = True
-	from PyQt4 import QtCore, QtGui
-	from taggerwindow import TaggerWindow
-except ImportError as e:
-	qt_available = False
-
-
-from settings import ComicTaggerSettings
-from options import Options, MetaDataStyle
-from comicarchive import ComicArchive
-from issueidentifier import IssueIdentifier
-from genericmetadata import GenericMetadata
-from comicvinetalker import ComicVineTalker, ComicVineTalkerException
-from filerenamer import FileRenamer
-from cbltransformer import CBLTransformer
-
-import utils
-import codecs
-
-class MultipleMatch():
-	def __init__( self, filename, match_list):
-		self.filename = filename  
-		self.matches = match_list  
-
-class OnlineMatchResults():
-	def __init__(self):
-		self.goodMatches = []  
-		self.noMatches = []    
-		self.multipleMatches = []  
-		self.writeFailures = []  
-
-#-----------------------------
-
-def actual_issue_data_fetch( match, settings ):
-
-	# now get the particular issue data
-	try:
-		cv_md = ComicVineTalker().fetchIssueData( match['volume_id'],  match['issue_number'], settings )
-	except ComicVineTalkerException:
-		print "Network error while getting issue details.  Save aborted"
-		return None
-
-	if settings.apply_cbl_transform_on_cv_import:
-		cv_md = CBLTransformer( cv_md, settings ).apply()
-		
-	return cv_md
-
-def actual_metadata_save( ca, opts, md ):
-
-	if not opts.dryrun:
-		# write out the new data
-		if not ca.writeMetadata( md, opts.data_style ):
-			print "The tag save seemed to fail!"
-			return False
-		else:
-			print "Save complete."				
-	else:
-		if opts.terse:
-			print "dry-run option was set, so nothing was written"
-		else:
-			print "dry-run option was set, so nothing was written, but here is the final set of tags:"
-			print u"{0}".format(md)
-	return True
-		
-
-def post_process_matches( match_results, opts, settings ):
-	# now go through the match results
-	if opts.show_save_summary:
-		if len( match_results.goodMatches ) > 0:
-			print "\nSuccessful matches:"
-			print "------------------"
-			for f in match_results.goodMatches:
-				print f
-				
-		if len( match_results.noMatches ) > 0:
-			print "\nNo matches:"
-			print "------------------"
-			for f in match_results.noMatches:
-				print f
-	
-		if len( match_results.writeFailures ) > 0:
-			print "\nFile Write Failures:"
-			print "------------------"
-			for f in match_results.writeFailures:
-				print f
-
-	if not opts.show_save_summary and not opts.interactive:
-		#jusr quit if we're not interactive or showing the summary
-		return
-	
-	if len( match_results.multipleMatches ) > 0:
-		print "\nMultiple matches:"
-		print "------------------"
-		for mm in match_results.multipleMatches:
-			print mm.filename
-			for (counter,m) in enumerate(mm.matches):
-				print u"  {0}. {1} #{2} [{3}] ({4}/{5}) - {6}".format(counter,
-											   m['series'],
-											   m['issue_number'],
-											   m['publisher'],
-											   m['month'],
-											   m['year'],
-											   m['issue_title'])
-			if opts.interactive:
-				while True:
-					i = raw_input("Choose a match #, or 's' to skip: ")
-					if (i.isdigit() and int(i) in range(len(mm.matches))) or i == 's':
-						break
-				if i != 's':
-					# save the data!
-					# we know at this point, that the file is all good to go
-					ca = ComicArchive( mm.filename )
-					md = create_local_metadata( opts, ca, ca.hasMetadata(opts.data_style) )
-					cv_md = actual_issue_data_fetch(mm.matches[int(i)], settings)
-					md.overlay( cv_md )
-					actual_metadata_save( ca, opts, md )
-					
-					
-			print
-
-
-def cli_mode( opts, settings ):
-	if len( opts.file_list ) < 1:
-		print "You must specify at least one filename.  Use the -h option for more info"
-		return
-	
-	match_results = OnlineMatchResults()
-	
-	for f in opts.file_list:
-		f = f.decode(filename_encoding, 'replace')
-		process_file_cli( f, opts, settings, match_results )
-		sys.stdout.flush()
-		
-	post_process_matches( match_results, opts, settings )	
-
-
-def create_local_metadata( opts, ca, has_desired_tags ):
-	
-	md = GenericMetadata()
-	md.setDefaultPageList( ca.getNumberOfPages() )
-	
-	if has_desired_tags:
-		md = ca.readMetadata( opts.data_style )
-		
-	# now, overlay the parsed filename info	
-	if opts.parse_filename:
-		md.overlay( ca.metadataFromFilename() )
-	
-	# finally, use explicit stuff	
-	if opts.metadata is not None:
-		md.overlay( opts.metadata )
-
-	return md
-
-def process_file_cli( filename, opts, settings, match_results ):
-
-	batch_mode = len( opts.file_list ) > 1
-		
-	ca = ComicArchive(filename)
-	if settings.rar_exe_path != "":
-		ca.setExternalRarProgram( settings.rar_exe_path )	
-	
-	if not ca.seemsToBeAComicArchive():
-		print "Sorry, but "+ filename + "  is not a comic archive!"
-		return
-	
-	#if not ca.isWritableForStyle( opts.data_style ) and ( opts.delete_tags or opts.save_tags or opts.rename_file ):
-	if not ca.isWritable(  ) and ( opts.delete_tags or opts.copy_tags or opts.save_tags or opts.rename_file ):
-		print "This archive is not writable for that tag type"
-		return
-
-	has = [ False, False, False ]
-	if ca.hasCIX(): has[ MetaDataStyle.CIX ] = True
-	if ca.hasCBI(): has[ MetaDataStyle.CBI ] = True
-	if ca.hasCoMet(): has[ MetaDataStyle.COMET ] = True
-
-	if opts.print_tags:
-
-
-		if opts.data_style is None:
-			page_count = ca.getNumberOfPages()
-
-			brief = ""
-
-			if batch_mode:
-				brief = "{0}: ".format(filename)
-
-			if ca.isZip():      brief += "ZIP archive    "
-			elif ca.isRar():    brief += "RAR archive    "
-			elif ca.isFolder(): brief += "Folder archive "
-				
-			brief += "({0: >3} pages)".format(page_count)			
-			brief += "  tags:[ "
-
-			if not ( has[ MetaDataStyle.CBI ] or has[ MetaDataStyle.CIX ] or has[ MetaDataStyle.COMET ] ):
-				brief += "none "
-			else:
-				if has[ MetaDataStyle.CBI ]: brief += "CBL "
-				if has[ MetaDataStyle.CIX ]: brief += "CR "
-				if has[ MetaDataStyle.COMET ]: brief += "CoMet "
-			brief += "]"
-				
-			print brief
-
-		if opts.terse:
-			return
-
-		print
-		
-		if opts.data_style is None or opts.data_style == MetaDataStyle.CIX:
-			if has[ MetaDataStyle.CIX ]:
-				print "------ComicRack tags--------"
-				if opts.raw:
-					print u"{0}".format(unicode(ca.readRawCIX(), errors='ignore'))
-				else:
-					print u"{0}".format(ca.readCIX())
-				
-		if opts.data_style is None or opts.data_style == MetaDataStyle.CBI:
-			if has[ MetaDataStyle.CBI ]:
-				print "------ComicBookLover tags--------"
-				if opts.raw:
-					pprint(json.loads(ca.readRawCBI()))
-				else:
-					print u"{0}".format(ca.readCBI())
-					
-		if opts.data_style is None or opts.data_style == MetaDataStyle.COMET:
-			if has[ MetaDataStyle.COMET ]:
-				print "------CoMet tags--------"
-				if opts.raw:
-					print u"{0}".format(ca.readRawCoMet())
-				else:
-					print u"{0}".format(ca.readCoMet())
-			
-			
-	elif opts.delete_tags:
-		style_name = MetaDataStyle.name[ opts.data_style ]
-		if has[ opts.data_style ]:
-			if not opts.dryrun:
-				if not ca.removeMetadata( opts.data_style ):
-					print "{0}: Tag removal seemed to fail!".format( filename )
-				else:
-					print "{0}: Removed {1} tags.".format( filename, style_name )
-			else:
-				print "{0}: dry-run.  {1} tags not removed".format( filename, style_name )		
-		else:
-			print "{0}: This archive doesn't have {1} tags to remove.".format( filename, style_name )
-
-	elif opts.copy_tags:
-		dst_style_name = MetaDataStyle.name[ opts.data_style ]
-		if opts.no_overwrite and has[ opts.data_style ]:
-			print "{0}: Already has {1} tags.  Not overwriting.".format(filename, dst_style_name)
-			return
-		if opts.copy_source == opts.data_style:
-			print "{0}: Destination and source are same: {1}.  Nothing to do.".format(filename, dst_style_name)
-			return
-			
-		src_style_name = MetaDataStyle.name[ opts.copy_source ]
-		if has[ opts.copy_source ]:
-			if not opts.dryrun:
-				md = ca.readMetadata( opts.copy_source )
-				
-				if settings.apply_cbl_transform_on_bulk_operation and opts.data_style == MetaDataStyle.CBI:
-					md = CBLTransformer( md, settings ).apply()
-				
-				if not ca.writeMetadata( md, opts.data_style ):
-					print u"{0}: Tag copy seemed to fail!".format( filename )
-				else:
-					print u"{0}: Copied {1} tags to {2} .".format( filename, src_style_name, dst_style_name )
-			else:
-				print u"{0}: dry-run.  {1} tags not copied".format( filename, src_style_name )		
-		else:
-			print u"{0}: This archive doesn't have {1} tags to copy.".format( filename, src_style_name )
-
-		
-	elif opts.save_tags:
-
-		if opts.no_overwrite and has[ opts.data_style ]:
-			print u"{0}: Already has {1} tags.  Not overwriting.".format(filename, MetaDataStyle.name[ opts.data_style ])
-			return
-		
-		if batch_mode:
-			print u"Processing {0}: ".format(filename)
-			
-		md = create_local_metadata( opts, ca, has[ opts.data_style ] )
-
-		# now, search online
-		if opts.search_online:
-			if opts.issue_id is not None:
-				# we were given the actual ID to search with
-				try:
-					cv_md = ComicVineTalker().fetchIssueDataByIssueID( opts.issue_id, settings )
-				except ComicVineTalkerException:
-					print "Network error while getting issue details.  Save aborted"
-					return None
-				
-				if cv_md is None:
-					print "No match for ID {0} was found.".format(opts.issue_id)
-					return None
-				
-				if settings.apply_cbl_transform_on_cv_import:
-					cv_md = CBLTransformer( cv_md, settings ).apply()
-			else:
-				ii = IssueIdentifier( ca, settings )
-	
-				if md is None or md.isEmpty:
-					print "No metadata given to search online with!"
-					return
-	
-				def myoutput( text ):
-					if opts.verbose:
-						IssueIdentifier.defaultWriteOutput( text )
-					
-				# use our overlayed MD struct to search
-				ii.setAdditionalMetadata( md )
-				ii.onlyUseAdditionalMetaData = True
-				ii.setOutputFunction( myoutput )
-				ii.cover_page_index = md.getCoverPageIndexList()[0]
-				matches = ii.search()
-				
-				result = ii.search_result
-				
-				found_match = False
-				choices = False
-				low_confidence = False
-				
-				if result == ii.ResultNoMatches:
-					pass
-				elif result == ii.ResultFoundMatchButBadCoverScore:
-					low_confidence = True
-					found_match = True
-				elif result == ii.ResultFoundMatchButNotFirstPage :
-					found_match = True
-				elif result == ii.ResultMultipleMatchesWithBadImageScores:
-					low_confidence = True
-					choices = True
-				elif result == ii.ResultOneGoodMatch:
-					found_match = True
-				elif result == ii.ResultMultipleGoodMatches:
-					choices = True
-	
-				if choices:
-					print "Online search: Multiple matches.  Save aborted"
-					match_results.multipleMatches.append(MultipleMatch(filename,matches))
-					return
-				if low_confidence and opts.abortOnLowConfidence:
-					print "Online search: Low confidence match.  Save aborted"
-					match_results.noMatches.append(filename)
-					return
-				if not found_match:
-					print "Online search: No match found.  Save aborted"
-					match_results.noMatches.append(filename)
-					return
-	
-	
-				# we got here, so we have a single match
-				
-				# now get the particular issue data
-				cv_md = actual_issue_data_fetch(matches[0], settings)
-				if cv_md is None:
-					return
-			
-			md.overlay( cv_md )
-			
-		# ok, done building our metadata. time to save
-		if not actual_metadata_save( ca, opts, md ):
-				match_results.writeFailures.append(filename)
-		else:
-				match_results.goodMatches.append(filename)
-
-	elif opts.rename_file:
-
-		msg_hdr = ""
-		if batch_mode:
-			msg_hdr = u"{0}: ".format(filename)
-
-		if opts.data_style is not None:
-			use_tags = has[ opts.data_style ]
-		else:
-			use_tags = False
-			
-		md = create_local_metadata( opts, ca, use_tags )
-		
-		if md.series is None:
-			print msg_hdr + "Can't rename without series name"
-			return
-
-		new_ext = None  # default
-		if settings.rename_extension_based_on_archive:
-			if ca.isZip():
-				new_ext = ".cbz"
-			elif ca.isRar():
-				new_ext = ".cbr"
-			
-		renamer = FileRenamer( md )
-		renamer.setTemplate( settings.rename_template )
-		renamer.setIssueZeroPadding( settings.rename_issue_number_padding )
-		renamer.setSmartCleanup( settings.rename_use_smart_string_cleanup )
-		
-		new_name = renamer.determineName( filename, ext=new_ext )
-			
-		if new_name == os.path.basename(filename):
-			print msg_hdr + "Filename is already good!"
-			return
-		
-		folder = os.path.dirname( os.path.abspath( filename ) )
-		new_abs_path = utils.unique_file( os.path.join( folder, new_name ) )
-
-		suffix = ""
-		if not opts.dryrun:
-			# rename the file
-			os.rename( filename, new_abs_path )
-		else:
-			suffix = " (dry-run, no change)"
-
-		print u"renamed '{0}' -> '{1}' {2}".format(os.path.basename(filename), new_name, suffix)
-
-#-----------------------------
-
-def main():
-	
-	# try to make stdout encodings happy for unicode
-	if platform.system() == "Darwin":
-		preferred_encoding = "utf-8"
-	else:
-		preferred_encoding = locale.getpreferredencoding()
-	sys.stdout = codecs.getwriter(preferred_encoding)(sys.stdout)
-
-	opts = Options()
-	opts.parseCmdLineArgs()
-
-	settings = ComicTaggerSettings()
-	# make sure unrar program is in the path for the UnRAR class
-	utils.addtopath(os.path.dirname(settings.unrar_exe_path))
-	
-	signal.signal(signal.SIGINT, signal.SIG_DFL)
-	
-	if not qt_available and not opts.no_gui:
-		opts.no_gui = True
-		print "QT is not available."
-	
-	if opts.no_gui:
-		cli_mode( opts, settings )
-		
-	else:
-
-		app = QtGui.QApplication(sys.argv)
-		
-		if platform.system() != "Linux":
-			img =  QtGui.QPixmap(os.path.join(ComicTaggerSettings.baseDir(), 'graphics/tags.png' ))
-			splash = QtGui.QSplashScreen(img)
-			splash.show()
-			splash.raise_()
-			app.processEvents()
-	
-		try:			
-			tagger_window = TaggerWindow( opts.file_list, settings )
-			tagger_window.show()
-
-			if platform.system() != "Linux":
-				splash.finish( tagger_window )
-
-			sys.exit(app.exec_())
-		except Exception, e:
-			QtGui.QMessageBox.critical(QtGui.QMainWindow(), "Error", "Unhandled exception in app:\n" + traceback.format_exc() )
-			
-			
 if __name__ == "__main__":
-	main()
-    
-    
-    
-    
+    localefix.configure_locale()
+
+    App().run()

comictagger.spec

@@ -0,0 +1,241 @@
+# -*- mode: python ; coding: utf-8 -*-
+
+import platform
+
+from comictaggerlib import ctversion
+
+enable_console = False
+block_cipher = None
+
+
+a = Analysis(
+    ["comictagger.py"],
+    pathex=[],
+    binaries=[],
+    datas=[],
+    hiddenimports=[],
+    hookspath=[],
+    hooksconfig={},
+    runtime_hooks=[],
+    excludes=[],
+    win_no_prefer_redirects=False,
+    win_private_assemblies=False,
+    cipher=block_cipher,
+    noarchive=False,
+)
+
+exe_binaries = []
+exe_zipfiles = []
+exe_datas = []
+exe_exclude_binaries = True
+
+coll_binaries = a.binaries
+coll_zipfiles = a.zipfiles
+coll_datas = a.datas
+
+if platform.system() in ["Windows"]:
+    enable_console = True
+    exe_binaries = a.binaries
+    exe_zipfiles = a.zipfiles
+    exe_datas = a.datas
+    exe_exclude_binaries = False
+
+    coll_binaries = []
+    coll_zipfiles = []
+    coll_datas = []
+
+
+pyz = PYZ(a.pure, a.zipped_data, cipher=block_cipher)
+
+exe = EXE(
+    pyz,
+    a.scripts,
+    exe_binaries,
+    exe_zipfiles,
+    exe_datas,
+    [],
+    exclude_binaries=exe_exclude_binaries,
+    name="comictagger",
+    debug=False,
+    bootloader_ignore_signals=False,
+    strip=False,
+    upx=True,
+    upx_exclude=[],
+    runtime_tmpdir=None,
+    console=enable_console,
+    disable_windowed_traceback=False,
+    argv_emulation=False,
+    target_arch=None,
+    codesign_identity=None,
+    entitlements_file=None,
+    icon="windows/app.ico",
+)
+if platform.system() not in ["Windows"]:
+    coll = COLLECT(
+        exe,
+        coll_binaries,
+        coll_zipfiles,
+        coll_datas,
+        strip=False,
+        upx=True,
+        upx_exclude=[],
+        name="comictagger",
+    )
+    app = BUNDLE(
+        coll,
+        name="ComicTagger.app",
+        icon="mac/app.icns",
+        info_plist={
+            "NSHighResolutionCapable": "True",
+            "NSPrincipalClass": "NSApplication",
+            "NSRequiresAquaSystemAppearance": "False",
+            "CFBundleDisplayName": "ComicTagger",
+            "CFBundleShortVersionString": ctversion.version,
+            "CFBundleVersion": ctversion.version,
+            "CFBundleDocumentTypes": [
+                {
+                    "CFBundleTypeRole": "Editor",
+                    "LSHandlerRank": "Default",
+                    "LSItemContentTypes": [
+                        "public.folder",
+                    ],
+                    "CFBundleTypeName": "Folder",
+                },
+                {
+                    "CFBundleTypeExtensions": [
+                        "cbz",
+                    ],
+                    "LSTypeIsPackage": False,
+                    "NSPersistentStoreTypeKey": "Binary",
+                    "CFBundleTypeIconSystemGenerated": True,
+                    "CFBundleTypeName": "ZIP Comic Archive",
+                    "LSItemContentTypes": [
+                        "public.zip-comic-archive",
+                        "com.simplecomic.cbz-archive",
+                        "com.macitbetter.cbz-archive",
+                        "public.cbz-archive",
+                        "cx.c3.cbz-archive",
+                        "com.yacreader.yacreader.cbz",
+                        "com.milke.cbz-archive",
+                        "com.bitcartel.comicbooklover.cbz",
+                        "public.archive.cbz",
+                        "public.zip-archive",
+                    ],
+                    "CFBundleTypeRole": "Editor",
+                    "LSHandlerRank": "Default",
+                },
+                {
+                    "CFBundleTypeExtensions": [
+                        "cb7",
+                    ],
+                    "LSTypeIsPackage": False,
+                    "NSPersistentStoreTypeKey": "Binary",
+                    "CFBundleTypeIconSystemGenerated": True,
+                    "CFBundleTypeName": "7-Zip Comic Archive",
+                    "LSItemContentTypes": [
+                        "org.7-zip.7-zip-archive",
+                        "com.simplecomic.cb7-archive",
+                        "public.cb7-archive",
+                        "com.macitbetter.cb7-archive",
+                        "cx.c3.cb7-archive",
+                        "org.7-zip.7-zip-comic-archive",
+                    ],
+                    "CFBundleTypeRole": "Editor",
+                    "LSHandlerRank": "Default",
+                },
+                {
+                    "CFBundleTypeExtensions": [
+                        "cbr",
+                    ],
+                    "LSTypeIsPackage": False,
+                    "NSPersistentStoreTypeKey": "Binary",
+                    "CFBundleTypeIconSystemGenerated": True,
+                    "CFBundleTypeName": "RAR Comic Archive",
+                    "LSItemContentTypes": [
+                        "com.rarlab.rar-archive",
+                        "com.rarlab.rar-comic-archive",
+                        "com.simplecomic.cbr-archive",
+                        "com.macitbetter.cbr-archive",
+                        "public.cbr-archive",
+                        "cx.c3.cbr-archive",
+                        "com.bitcartel.comicbooklover.cbr",
+                        "com.milke.cbr-archive",
+                        "public.archive.cbr",
+                        "com.yacreader.yacreader.cbr",
+                    ],
+                    "CFBundleTypeRole": "Editor",
+                    "LSHandlerRank": "Default",
+                },
+            ],
+            "UTImportedTypeDeclarations": [
+                {
+                    "UTTypeIdentifier": "com.rarlab.rar-archive",
+                    "UTTypeDescription": "RAR Archive",
+                    "UTTypeConformsTo": [
+                        "public.data",
+                        "public.archive",
+                    ],
+                    "UTTypeTagSpecification": {
+                        "public.mime-type": [
+                            "application/x-rar",
+                            "application/x-rar-compressed",
+                        ],
+                        "public.filename-extension": [
+                            "rar",
+                        ],
+                    },
+                },
+                {
+                    "UTTypeConformsTo": [
+                        "public.data",
+                        "public.archive",
+                        "com.rarlab.rar-archive",
+                    ],
+                    "UTTypeIdentifier": "com.rarlab.rar-comic-archive",
+                    "UTTypeDescription": "RAR Comic Archive",
+                    "UTTypeTagSpecification": {
+                        "public.mime-type": [
+                            "application/vnd.comicbook-rar",
+                            "application/x-cbr",
+                        ],
+                        "public.filename-extension": [
+                            "cbr",
+                        ],
+                    },
+                },
+                {
+                    "UTTypeConformsTo": [
+                        "public.data",
+                        "public.archive",
+                        "public.zip-archive",
+                    ],
+                    "UTTypeIdentifier": "public.zip-comic-archive",
+                    "UTTypeDescription": "ZIP Comic Archive",
+                    "UTTypeTagSpecification": {
+                        "public.filename-extension": [
+                            "cbz",
+                        ],
+                    },
+                },
+                {
+                    "UTTypeConformsTo": [
+                        "public.data",
+                        "public.archive",
+                        "org.7-zip.7-zip-archive",
+                    ],
+                    "UTTypeIdentifier": "org.7-zip.7-zip-comic-archive",
+                    "UTTypeDescription": "7-Zip Comic Archive",
+                    "UTTypeTagSpecification": {
+                        "public.mime-type": [
+                            "application/vnd.comicbook+7-zip",
+                            "application/x-cb7-compressed",
+                        ],
+                        "public.filename-extension": [
+                            "cb7",
+                        ],
+                    },
+                },
+            ],
+        },
+        bundle_identifier=None,
+    )

comictaggerlib/__init__.py

@@ -0,0 +1 @@
+from __future__ import annotations

comictaggerlib/__pyinstaller/__init__.py

@@ -0,0 +1,11 @@
+from __future__ import annotations
+
+import os
+
+import comicapi.__pyinstaller
+
+
+def get_hook_dirs() -> list[str]:
+    hooks = [os.path.dirname(__file__)]
+    hooks.extend(comicapi.__pyinstaller.get_hook_dirs())
+    return hooks

comictaggerlib/__pyinstaller/hook-comictaggerlib.py

@@ -0,0 +1,7 @@
+from __future__ import annotations
+
+from PyInstaller.utils.hooks import collect_data_files
+
+datas = []
+datas += collect_data_files("comictaggerlib.ui")
+datas += collect_data_files("comictaggerlib.graphics")

comictaggerlib/__pyinstaller/hook-wordninja.py

@@ -0,0 +1,7 @@
+from __future__ import annotations
+
+import os
+
+from PyInstaller.utils.hooks import get_module_file_attribute
+
+datas = [(os.path.join(os.path.dirname(get_module_file_attribute("wordninja")), "wordninja"), "wordninja")]

comictaggerlib/applicationlogwindow.py

@@ -0,0 +1,50 @@
+from __future__ import annotations
+
+import logging
+
+from PyQt5 import QtCore, QtGui, QtWidgets, uic
+
+from comictaggerlib.ui import ui_path
+
+logger = logging.getLogger(__name__)
+
+
+class QTextEditLogger(QtCore.QObject, logging.Handler):
+    qlog = QtCore.pyqtSignal(str)
+
+    def __init__(self, formatter: logging.Formatter, level: int) -> None:
+        super().__init__()
+        self.setFormatter(formatter)
+        self.setLevel(level)
+
+    def emit(self, record: logging.LogRecord) -> None:
+        msg = self.format(record)
+        self.qlog.emit(msg.strip())
+
+
+class ApplicationLogWindow(QtWidgets.QDialog):
+    def __init__(self, log_handler: QTextEditLogger, parent: QtCore.QObject | None = None) -> None:
+        super().__init__(parent)
+        uic.loadUi(ui_path / "logwindow.ui", self)
+
+        self.log_handler = log_handler
+        self.log_handler.qlog.connect(self.textEdit.append)
+
+        f = QtGui.QFont("menlo")
+        f.setStyleHint(QtGui.QFont.Monospace)
+        self.setFont(f)
+        self._button = QtWidgets.QPushButton(self)
+        self._button.setText("Test Me")
+
+        layout = self.layout()
+        layout.addWidget(self._button)
+
+        # Connect signal to slot
+        self._button.clicked.connect(self.test)
+        self.textEdit.setTabStopDistance(self.textEdit.tabStopDistance() * 2)
+
+    def test(self) -> None:
+        logger.debug("damn, a bug")
+        logger.info("something to remember")
+        logger.warning("that's not right")
+        logger.error("foobar")

comictaggerlib/autotagmatchwindow.py

@@ -0,0 +1,259 @@
+"""A PyQT4 dialog to select from automated issue matches"""
+#
+# 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 os
+from typing import Callable
+
+import settngs
+from PyQt5 import QtCore, QtGui, QtWidgets, uic
+
+from comicapi.comicarchive import MetaDataStyle
+from comicapi.genericmetadata import GenericMetadata
+from comictaggerlib.coverimagewidget import CoverImageWidget
+from comictaggerlib.resulttypes import IssueResult, MultipleMatch
+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 AutoTagMatchWindow(QtWidgets.QDialog):
+    def __init__(
+        self,
+        parent: QtWidgets.QWidget,
+        match_set_list: list[MultipleMatch],
+        style: int,
+        fetch_func: Callable[[IssueResult], GenericMetadata],
+        config: settngs.Namespace,
+        talker: ComicTalker,
+    ) -> None:
+        super().__init__(parent)
+
+        uic.loadUi(ui_path / "matchselectionwindow.ui", self)
+
+        self.config = config
+
+        self.current_match_set: MultipleMatch = match_set_list[0]
+
+        self.altCoverWidget = CoverImageWidget(
+            self.altCoverContainer, CoverImageWidget.AltCoverMode, config.runtime_config.user_cache_dir, talker
+        )
+        gridlayout = QtWidgets.QGridLayout(self.altCoverContainer)
+        gridlayout.addWidget(self.altCoverWidget)
+        gridlayout.setContentsMargins(0, 0, 0, 0)
+
+        self.archiveCoverWidget = CoverImageWidget(self.archiveCoverContainer, CoverImageWidget.ArchiveMode, None, 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()
+                | QtCore.Qt.WindowType.WindowSystemMenuHint
+                | QtCore.Qt.WindowType.WindowMaximizeButtonHint
+            )
+        )
+
+        self.skipButton = QtWidgets.QPushButton("Skip to Next")
+        self.buttonBox.addButton(self.skipButton, QtWidgets.QDialogButtonBox.ButtonRole.ActionRole)
+        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.current_match_set_idx = 0
+
+        self.twList.currentItemChanged.connect(self.current_item_changed)
+        self.twList.cellDoubleClicked.connect(self.cell_double_clicked)
+        self.skipButton.clicked.connect(self.skip_to_next)
+
+        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):
+            self.buttonBox.button(QtWidgets.QDialogButtonBox.StandardButton.Cancel).setDisabled(True)
+            self.skipButton.setText("Skip")
+
+        self.set_cover_image()
+        self.populate_table()
+        self.twList.resizeColumnsToContents()
+        self.twList.selectRow(0)
+
+        path = self.current_match_set.ca.path
+        self.setWindowTitle(
+            "Select correct match or skip ({} of {}): {}".format(
+                self.current_match_set_idx + 1,
+                len(self.match_set_list),
+                os.path.split(path)[1],
+            )
+        )
+
+    def populate_table(self) -> None:
+        if not self.current_match_set:
+            return
+
+        self.twList.setRowCount(0)
+
+        self.twList.setSortingEnabled(False)
+
+        row = 0
+        for match in self.current_match_set.matches:
+            self.twList.insertRow(row)
+
+            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"])
+            else:
+                item_text = "Unknown"
+            item = QtWidgets.QTableWidgetItem(item_text)
+            item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, item_text)
+            item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
+            self.twList.setItem(row, 1, item)
+
+            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"])
+
+            item_text = year_str + month_str
+            item = QtWidgets.QTableWidgetItem(item_text)
+            item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, item_text)
+            item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
+            self.twList.setItem(row, 2, item)
+
+            item_text = match["issue_title"]
+            if item_text is None:
+                item_text = ""
+            item = QtWidgets.QTableWidgetItem(item_text)
+            item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, item_text)
+            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)
+        self.twList.selectRow(0)
+        self.twList.resizeColumnsToContents()
+        self.twList.horizontalHeader().setStretchLastSection(True)
+
+    def cell_double_clicked(self, r: int, c: int) -> None:
+        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_details(
+            self.current_match()["issue_id"],
+            [self.current_match()["image_url"], *self.current_match()["alt_image_urls"]],
+        )
+        if self.current_match()["description"] is None:
+            self.teDescription.setText("")
+        else:
+            self.teDescription.setText(self.current_match()["description"])
+
+    def set_cover_image(self) -> None:
+        ca = self.current_match_set.ca
+        self.archiveCoverWidget.set_archive(ca)
+
+    def current_match(self) -> IssueResult:
+        row = self.twList.currentRow()
+        match: IssueResult = self.twList.item(row, 0).data(QtCore.Qt.ItemDataRole.UserRole)[0]
+        return match
+
+    def accept(self) -> None:
+        self.save_match()
+        self.current_match_set_idx += 1
+
+        if self.current_match_set_idx == len(self.match_set_list):
+            # no more items
+            QtWidgets.QDialog.accept(self)
+        else:
+            self.update_data()
+
+    def skip_to_next(self) -> None:
+        self.current_match_set_idx += 1
+
+        if self.current_match_set_idx == len(self.match_set_list):
+            # no more items
+            QtWidgets.QDialog.reject(self)
+        else:
+            self.update_data()
+
+    def reject(self) -> None:
+        reply = QtWidgets.QMessageBox.question(
+            self,
+            "Cancel Matching",
+            "Are you sure you wish to cancel the matching process?",
+            QtWidgets.QMessageBox.StandardButton.Yes,
+            QtWidgets.QMessageBox.StandardButton.No,
+        )
+
+        if reply == QtWidgets.QMessageBox.StandardButton.No:
+            return
+
+        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.config.filename_complicated_parser,
+                self.config.filename_remove_c2c,
+                self.config.filename_remove_fcbd,
+                self.config.filename_remove_publisher,
+            )
+
+        # now get the particular issue data
+        ct_md = self.fetch_func(match)
+        if ct_md is None:
+            QtWidgets.QMessageBox.critical(self, "Network Issue", "Could not retrieve issue details!")
+            return
+
+        QtWidgets.QApplication.setOverrideCursor(QtGui.QCursor(QtCore.Qt.CursorShape.WaitCursor))
+        md.overlay(ct_md)
+        success = ca.write_metadata(md, self._style)
+        ca.load_cache([MetaDataStyle.CBI, MetaDataStyle.CIX])
+
+        QtWidgets.QApplication.restoreOverrideCursor()
+
+        if not success:
+            QtWidgets.QMessageBox.warning(self, "Write Error", "Saving the tags to the archive seemed to fail!")

comictaggerlib/autotagprogresswindow.py

@@ -0,0 +1,73 @@
+"""A PyQT4 dialog to show ID log and progress"""
+#
+# 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
+
+from PyQt5 import QtCore, QtWidgets, uic
+
+from comictaggerlib.coverimagewidget import CoverImageWidget
+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 AutoTagProgressWindow(QtWidgets.QDialog):
+    def __init__(self, parent: QtWidgets.QWidget, talker: ComicTalker) -> None:
+        super().__init__(parent)
+
+        uic.loadUi(ui_path / "autotagprogresswindow.ui", self)
+
+        self.archiveCoverWidget = CoverImageWidget(
+            self.archiveCoverContainer, CoverImageWidget.DataMode, None, None, False
+        )
+        gridlayout = QtWidgets.QGridLayout(self.archiveCoverContainer)
+        gridlayout.addWidget(self.archiveCoverWidget)
+        gridlayout.setContentsMargins(0, 0, 0, 0)
+
+        self.testCoverWidget = CoverImageWidget(self.testCoverContainer, CoverImageWidget.DataMode, None, 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()
+                | QtCore.Qt.WindowType.WindowSystemMenuHint
+                | QtCore.Qt.WindowType.WindowMaximizeButtonHint
+            )
+        )
+
+        reduce_widget_font_size(self.textEdit)
+
+    def set_archive_image(self, img_data: bytes) -> None:
+        self.set_cover_image(img_data, self.archiveCoverWidget)
+
+    def set_test_image(self, img_data: bytes) -> None:
+        self.set_cover_image(img_data, self.testCoverWidget)
+
+    def set_cover_image(self, img_data: bytes, widget: CoverImageWidget) -> None:
+        widget.set_image_data(img_data)
+        QtCore.QCoreApplication.processEvents()
+        QtCore.QCoreApplication.processEvents()
+
+    def reject(self) -> None:
+        QtWidgets.QDialog.reject(self)
+        self.isdone = True

comictaggerlib/autotagstartwindow.py

@@ -0,0 +1,106 @@
+"""A PyQT4 dialog to confirm and set config for auto-tag"""
+#
+# 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 settngs
+from PyQt5 import QtCore, QtWidgets, uic
+
+from comictaggerlib.ui import ui_path
+
+logger = logging.getLogger(__name__)
+
+
+class AutoTagStartWindow(QtWidgets.QDialog):
+    def __init__(self, parent: QtWidgets.QWidget, config: settngs.Namespace, msg: str) -> None:
+        super().__init__(parent)
+
+        uic.loadUi(ui_path / "autotagstartwindow.ui", self)
+        self.label.setText(msg)
+
+        self.setWindowFlags(
+            QtCore.Qt.WindowType(self.windowFlags() & ~QtCore.Qt.WindowType.WindowContextHelpButtonHint)
+        )
+
+        self.config = config
+
+        self.cbxSpecifySearchString.setChecked(False)
+        self.cbxSplitWords.setChecked(False)
+        self.sbNameMatchSearchThresh.setValue(self.config.identifier_series_match_identify_thresh)
+        self.leSearchString.setEnabled(False)
+
+        self.cbxSaveOnLowConfidence.setChecked(self.config.autotag_save_on_low_confidence)
+        self.cbxDontUseYear.setChecked(self.config.autotag_dont_use_year_when_identifying)
+        self.cbxAssumeIssueOne.setChecked(self.config.autotag_assume_1_if_no_issue_num)
+        self.cbxIgnoreLeadingDigitsInFilename.setChecked(self.config.autotag_ignore_leading_numbers_in_filename)
+        self.cbxRemoveAfterSuccess.setChecked(self.config.autotag_remove_archive_after_successful_match)
+        self.cbxWaitForRateLimit.setChecked(self.config.autotag_wait_and_retry_on_rate_limit)
+        self.cbxAutoImprint.setChecked(self.config.talker_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
+                it is, the more likely to have a good match, but each search will take longer and
+                use more bandwidth. Too high, and only the very closest matches will be explored.</html>"""
+
+        self.sbNameMatchSearchThresh.setToolTip(nlmt_tip)
+
+        ss_tip = """<html>
+            The <b>series search string</b> specifies the search string to be used for all selected archives.
+            Use this when trying to match archives with hard-to-parse or incorrect filenames.  All archives selected
+            should be from the same series.
+            </html>"""
+        self.leSearchString.setToolTip(ss_tip)
+        self.cbxSpecifySearchString.setToolTip(ss_tip)
+
+        self.cbxSpecifySearchString.stateChanged.connect(self.search_string_toggle)
+
+        self.auto_save_on_low = False
+        self.dont_use_year = False
+        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.config.talker_series_match_search_thresh
+        self.split_words = self.cbxSplitWords.isChecked()
+
+    def search_string_toggle(self) -> None:
+        enable = self.cbxSpecifySearchString.isChecked()
+        self.leSearchString.setEnabled(enable)
+
+    def accept(self) -> None:
+        QtWidgets.QDialog.accept(self)
+
+        self.auto_save_on_low = self.cbxSaveOnLowConfidence.isChecked()
+        self.dont_use_year = self.cbxDontUseYear.isChecked()
+        self.assume_issue_one = self.cbxAssumeIssueOne.isChecked()
+        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.config.autotag_save_on_low_confidence = self.auto_save_on_low
+        self.config.autotag_dont_use_year_when_identifying = self.dont_use_year
+        self.config.autotag_assume_1_if_no_issue_num = self.assume_issue_one
+        self.config.autotag_ignore_leading_numbers_in_filename = self.ignore_leading_digits_in_filename
+        self.config.autotag_remove_archive_after_successful_match = self.remove_after_success
+        self.config.autotag_wait_and_retry_on_rate_limit = self.wait_and_retry_on_rate_limit
+
+        if self.cbxSpecifySearchString.isChecked():
+            self.search_string = self.leSearchString.text()

comictaggerlib/cbltransformer.py

@@ -0,0 +1,100 @@
+"""A class to manage modifying metadata specifically for CBL/CBI"""
+#
+# 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 settngs
+
+from comicapi.genericmetadata import CreditMetadata, GenericMetadata
+
+logger = logging.getLogger(__name__)
+
+
+class CBLTransformer:
+    def __init__(self, metadata: GenericMetadata, config: settngs.Namespace) -> None:
+        self.metadata = metadata
+        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.config.cbl_assume_lone_credit_is_primary:
+            # helper
+            def set_lone_primary(role_list: list[str]) -> tuple[CreditMetadata | None, int]:
+                lone_credit: CreditMetadata | None = None
+                count = 0
+                for c in self.metadata.credits:
+                    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
+                return lone_credit, count
+
+            # need to loop three times, once for 'writer', 'artist', and then
+            # 'penciler' if no artist
+            set_lone_primary(["writer"])
+            c, count = set_lone_primary(["artist"])
+            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)
+
+        if self.config.cbl_copy_characters_to_tags:
+            add_string_list_to_tags(self.metadata.characters)
+
+        if self.config.cbl_copy_teams_to_tags:
+            add_string_list_to_tags(self.metadata.teams)
+
+        if self.config.cbl_copy_locations_to_tags:
+            add_string_list_to_tags(self.metadata.locations)
+
+        if self.config.cbl_copy_storyarcs_to_tags:
+            add_string_list_to_tags(self.metadata.story_arc)
+
+        if self.config.cbl_copy_notes_to_comments:
+            if self.metadata.notes is not None:
+                if self.metadata.comments is None:
+                    self.metadata.comments = ""
+                else:
+                    self.metadata.comments += "\n\n"
+                if self.metadata.notes not in self.metadata.comments:
+                    self.metadata.comments += self.metadata.notes
+
+        if self.config.cbl_copy_weblink_to_comments:
+            if self.metadata.web_link is not None:
+                if self.metadata.comments is None:
+                    self.metadata.comments = ""
+                else:
+                    self.metadata.comments += "\n\n"
+                if self.metadata.web_link not in self.metadata.comments:
+                    self.metadata.comments += self.metadata.web_link
+
+        return self.metadata

comictaggerlib/cli.py

@@ -0,0 +1,600 @@
+#!/usr/bin/python
+"""ComicTagger CLI functions"""
+#
+# 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.
+# 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 os
+import sys
+from datetime import datetime
+from pprint import pprint
+
+import settngs
+
+from comicapi import utils
+from comicapi.comicarchive import ComicArchive, MetaDataStyle
+from comicapi.genericmetadata import GenericMetadata
+from comictaggerlib import ctversion
+from comictaggerlib.cbltransformer import CBLTransformer
+from comictaggerlib.filerenamer import FileRenamer, get_rename_dir
+from comictaggerlib.graphics import graphics_path
+from comictaggerlib.issueidentifier import IssueIdentifier
+from comictaggerlib.resulttypes import MultipleMatch, OnlineMatchResults
+from comictalker.comictalker import ComicTalker, TalkerError
+
+logger = logging.getLogger(__name__)
+
+
+class CLI:
+    def __init__(self, config: settngs.Namespace, talkers: dict[str, ComicTalker]):
+        self.config = config
+        self.talkers = talkers
+        self.batch_mode = False
+
+    def current_talker(self) -> ComicTalker:
+        if self.config[0].talker_source in self.talkers:
+            return self.talkers[self.config[0].talker_source]
+        logger.error("Could not find the '%s' talker", self.config[0].talker_source)
+        raise SystemExit(2)
+
+    def actual_issue_data_fetch(self, issue_id: str) -> GenericMetadata:
+        # now get the particular issue data
+        try:
+            ct_md = self.current_talker().fetch_comic_data(issue_id)
+        except TalkerError as e:
+            logger.exception(f"Error retrieving issue details. Save aborted.\n{e}")
+            return GenericMetadata()
+
+        if self.config.cbl_apply_transform_on_import:
+            ct_md = CBLTransformer(ct_md, self.config).apply()
+
+        return ct_md
+
+    def actual_metadata_save(self, ca: ComicArchive, md: GenericMetadata) -> bool:
+        if not self.config.runtime_dryrun:
+            for metadata_style in self.config.runtime_type:
+                # write out the new data
+                if not ca.write_metadata(md, metadata_style):
+                    logger.error("The tag save seemed to fail for style: %s!", MetaDataStyle.name[metadata_style])
+                    return False
+
+            print("Save complete.")
+            logger.info("Save complete.")
+        else:
+            if self.config.runtime_quiet:
+                logger.info("dry-run option was set, so nothing was written")
+                print("dry-run option was set, so nothing was written")
+            else:
+                logger.info("dry-run option was set, so nothing was written, but here is the final set of tags:")
+                print("dry-run option was set, so nothing was written, but here is the final set of tags:")
+                print(f"{md}")
+        return True
+
+    def display_match_set_for_choice(self, label: str, match_set: MultipleMatch) -> None:
+        print(f"{match_set.ca.path} -- {label}:")
+
+        # sort match list by year
+        match_set.matches.sort(key=lambda k: k["year"] or 0)
+
+        for counter, m in enumerate(match_set.matches):
+            counter += 1
+            print(
+                "    {}. {} #{} [{}] ({}/{}) - {}".format(
+                    counter,
+                    m["series"],
+                    m["issue_number"],
+                    m["publisher"],
+                    m["month"],
+                    m["year"],
+                    m["issue_title"],
+                )
+            )
+        if self.config.runtime_interactive:
+            while True:
+                i = input("Choose a match #, or 's' to skip: ")
+                if (i.isdigit() and int(i) in range(1, len(match_set.matches) + 1)) or i == "s":
+                    break
+            if i != "s":
+                # save the data!
+                # we know at this point, that the file is all good to go
+                ca = match_set.ca
+                md = self.create_local_metadata(ca)
+                ct_md = self.actual_issue_data_fetch(match_set.matches[int(i) - 1]["issue_id"])
+                if self.config.talker_clear_metadata_on_import:
+                    md = ct_md
+                else:
+                    notes = (
+                        f"Tagged with ComicTagger {ctversion.version} using info from Comic Vine on"
+                        f" {datetime.now():%Y-%m-%d %H:%M:%S}.  [Issue ID {ct_md.issue_id}]"
+                    )
+                    md.overlay(ct_md.replace(notes=utils.combine_notes(md.notes, notes, "Tagged with ComicTagger")))
+
+                if self.config.talker_auto_imprint:
+                    md.fix_publisher()
+
+                self.actual_metadata_save(ca, md)
+
+    def post_process_matches(self, match_results: OnlineMatchResults) -> None:
+        # now go through the match results
+        if self.config.runtime_summary:
+            if len(match_results.good_matches) > 0:
+                print("\nSuccessful matches:\n------------------")
+                for f in match_results.good_matches:
+                    print(f)
+
+            if len(match_results.no_matches) > 0:
+                print("\nNo matches:\n------------------")
+                for f in match_results.no_matches:
+                    print(f)
+
+            if len(match_results.write_failures) > 0:
+                print("\nFile Write Failures:\n------------------")
+                for f in match_results.write_failures:
+                    print(f)
+
+            if len(match_results.fetch_data_failures) > 0:
+                print("\nNetwork Data Fetch Failures:\n------------------")
+                for f in match_results.fetch_data_failures:
+                    print(f)
+
+        if not self.config.runtime_summary and not self.config.runtime_interactive:
+            # just quit if we're not interactive or showing the summary
+            return
+
+        if len(match_results.multiple_matches) > 0:
+            print("\nArchives with multiple high-confidence matches:\n------------------")
+            for match_set in match_results.multiple_matches:
+                self.display_match_set_for_choice("Multiple high-confidence matches", match_set)
+
+        if len(match_results.low_confidence_matches) > 0:
+            print("\nArchives with low-confidence matches:\n------------------")
+            for match_set in match_results.low_confidence_matches:
+                if len(match_set.matches) == 1:
+                    label = "Single low-confidence match"
+                else:
+                    label = "Multiple low-confidence matches"
+
+                self.display_match_set_for_choice(label, match_set)
+
+    def run(self) -> None:
+        if len(self.config.runtime_file_list) < 1:
+            logger.error("You must specify at least one filename.  Use the -h option for more info")
+            return
+
+        match_results = OnlineMatchResults()
+        self.batch_mode = len(self.config.runtime_file_list) > 1
+
+        for f in self.config.runtime_file_list:
+            self.process_file_cli(f, match_results)
+            sys.stdout.flush()
+
+        self.post_process_matches(match_results)
+
+    def create_local_metadata(self, ca: ComicArchive) -> GenericMetadata:
+        md = GenericMetadata()
+        md.set_default_page_list(ca.get_number_of_pages())
+
+        # now, overlay the parsed filename info
+        if self.config.runtime_parse_filename:
+            f_md = ca.metadata_from_filename(
+                self.config.filename_complicated_parser,
+                self.config.filename_remove_c2c,
+                self.config.filename_remove_fcbd,
+                self.config.filename_remove_publisher,
+                self.config.runtime_split_words,
+            )
+
+            md.overlay(f_md)
+
+        for metadata_style in self.config.runtime_type:
+            if ca.has_metadata(metadata_style):
+                try:
+                    t_md = ca.read_metadata(metadata_style)
+                    md.overlay(t_md)
+                    break
+                except Exception as e:
+                    logger.error("Failed to load metadata for %s: %s", ca.path, e)
+
+        # finally, use explicit stuff
+        md.overlay(self.config.runtime_metadata)
+
+        return md
+
+    def print(self, ca: ComicArchive) -> None:
+        if not self.config.runtime_type:
+            page_count = ca.get_number_of_pages()
+
+            brief = ""
+
+            if self.batch_mode:
+                brief = f"{ca.path}: "
+
+            brief += ca.archiver.name() + " archive "
+
+            brief += f"({page_count: >3} pages)"
+            brief += "  tags:[ "
+
+            if not (
+                ca.has_metadata(MetaDataStyle.CBI)
+                or ca.has_metadata(MetaDataStyle.CIX)
+                or ca.has_metadata(MetaDataStyle.COMET)
+            ):
+                brief += "none "
+            else:
+                if ca.has_metadata(MetaDataStyle.CBI):
+                    brief += "CBL "
+                if ca.has_metadata(MetaDataStyle.CIX):
+                    brief += "CR "
+                if ca.has_metadata(MetaDataStyle.COMET):
+                    brief += "CoMet "
+            brief += "]"
+
+            print(brief)
+
+        if self.config.runtime_quiet:
+            return
+
+        print()
+
+        if not self.config.runtime_type or MetaDataStyle.CIX in self.config.runtime_type:
+            if ca.has_metadata(MetaDataStyle.CIX):
+                print("--------- ComicRack tags ---------")
+                try:
+                    if self.config.runtime_raw:
+                        print(ca.read_raw_cix())
+                    else:
+                        print(ca.read_cix())
+                except Exception as e:
+                    logger.error("Failed to load metadata for %s: %s", ca.path, e)
+
+        if not self.config.runtime_type or MetaDataStyle.CBI in self.config.runtime_type:
+            if ca.has_metadata(MetaDataStyle.CBI):
+                print("------- ComicBookLover tags -------")
+                try:
+                    if self.config.runtime_raw:
+                        pprint(json.loads(ca.read_raw_cbi()))
+                    else:
+                        print(ca.read_cbi())
+                except Exception as e:
+                    logger.error("Failed to load metadata for %s: %s", ca.path, e)
+
+        if not self.config.runtime_type or MetaDataStyle.COMET in self.config.runtime_type:
+            if ca.has_metadata(MetaDataStyle.COMET):
+                print("----------- CoMet tags -----------")
+                try:
+                    if self.config.runtime_raw:
+                        print(ca.read_raw_comet())
+                    else:
+                        print(ca.read_comet())
+                except Exception as e:
+                    logger.error("Failed to load metadata for %s: %s", ca.path, e)
+
+    def delete(self, ca: ComicArchive) -> None:
+        for metadata_style in self.config.runtime_type:
+            style_name = MetaDataStyle.name[metadata_style]
+            if ca.has_metadata(metadata_style):
+                if not self.config.runtime_dryrun:
+                    if not ca.remove_metadata(metadata_style):
+                        print(f"{ca.path}: Tag removal seemed to fail!")
+                    else:
+                        print(f"{ca.path}: Removed {style_name} tags.")
+                else:
+                    print(f"{ca.path}: dry-run. {style_name} tags not removed")
+            else:
+                print(f"{ca.path}: This archive doesn't have {style_name} tags to remove.")
+
+    def copy(self, ca: ComicArchive) -> None:
+        for metadata_style in self.config.runtime_type:
+            dst_style_name = MetaDataStyle.name[metadata_style]
+            if not self.config.runtime_overwrite and ca.has_metadata(metadata_style):
+                print(f"{ca.path}: Already has {dst_style_name} tags. Not overwriting.")
+                return
+            if self.config.commands_copy == metadata_style:
+                print(f"{ca.path}: Destination and source are same: {dst_style_name}. Nothing to do.")
+                return
+
+            src_style_name = MetaDataStyle.name[self.config.commands_copy]
+            if ca.has_metadata(self.config.commands_copy):
+                if not self.config.runtime_dryrun:
+                    try:
+                        md = ca.read_metadata(self.config.commands_copy)
+                    except Exception as e:
+                        md = GenericMetadata()
+                        logger.error("Failed to load metadata for %s: %s", ca.path, e)
+
+                    if self.config.apply_transform_on_bulk_operation_ndetadata_style == MetaDataStyle.CBI:
+                        md = CBLTransformer(md, self.config).apply()
+
+                    if not ca.write_metadata(md, metadata_style):
+                        print(f"{ca.path}: Tag copy seemed to fail!")
+                    else:
+                        print(f"{ca.path}: Copied {src_style_name} tags to {dst_style_name}.")
+                else:
+                    print(f"{ca.path}: dry-run.  {src_style_name} tags not copied")
+            else:
+                print(f"{ca.path}: This archive doesn't have {src_style_name} tags to copy.")
+
+    def save(self, ca: ComicArchive, match_results: OnlineMatchResults) -> None:
+        if not self.config.runtime_overwrite:
+            for metadata_style in self.config.runtime_type:
+                if ca.has_metadata(metadata_style):
+                    print(f"{ca.path}: Already has {MetaDataStyle.name[metadata_style]} tags. Not overwriting.")
+                    return
+
+        if self.batch_mode:
+            print(f"Processing {ca.path}...")
+
+        md = self.create_local_metadata(ca)
+        if md.issue is None or md.issue == "":
+            if self.config.runtime_assume_issue_one:
+                md.issue = "1"
+
+        # now, search online
+        if self.config.runtime_online:
+            if self.config.runtime_issue_id is not None:
+                # we were given the actual issue ID to search with
+                try:
+                    ct_md = self.current_talker().fetch_comic_data(self.config.runtime_issue_id)
+                except TalkerError as e:
+                    logger.exception(f"Error retrieving issue details. Save aborted.\n{e}")
+                    match_results.fetch_data_failures.append(str(ca.path.absolute()))
+                    return
+
+                if ct_md is None:
+                    logger.error("No match for ID %s was found.", self.config.runtime_issue_id)
+                    match_results.no_matches.append(str(ca.path.absolute()))
+                    return
+
+                if self.config.cbl_apply_transform_on_import:
+                    ct_md = CBLTransformer(ct_md, self.config).apply()
+            else:
+                if md is None or md.is_empty:
+                    logger.error("No metadata given to search online with!")
+                    match_results.no_matches.append(str(ca.path.absolute()))
+                    return
+
+                ii = IssueIdentifier(ca, self.config, self.current_talker())
+
+                def myoutput(text: str) -> None:
+                    if self.config.runtime_verbose:
+                        IssueIdentifier.default_write_output(text)
+
+                # use our overlaid MD struct to search
+                ii.set_additional_metadata(md)
+                ii.only_use_additional_meta_data = True
+                ii.set_output_function(myoutput)
+                ii.cover_page_index = md.get_cover_page_index_list()[0]
+                matches = ii.search()
+
+                result = ii.search_result
+
+                found_match = False
+                choices = False
+                low_confidence = False
+
+                if result == ii.result_no_matches:
+                    pass
+                elif result == ii.result_found_match_but_bad_cover_score:
+                    low_confidence = True
+                    found_match = True
+                elif result == ii.result_found_match_but_not_first_page:
+                    found_match = True
+                elif result == ii.result_multiple_matches_with_bad_image_scores:
+                    low_confidence = True
+                    choices = True
+                elif result == ii.result_one_good_match:
+                    found_match = True
+                elif result == ii.result_multiple_good_matches:
+                    choices = True
+
+                if choices:
+                    if low_confidence:
+                        logger.error("Online search: Multiple low confidence matches. Save aborted")
+                        match_results.low_confidence_matches.append(MultipleMatch(ca, matches))
+                        return
+
+                    logger.error("Online search: Multiple good matches. Save aborted")
+                    match_results.multiple_matches.append(MultipleMatch(ca, matches))
+                    return
+                if low_confidence and self.config.runtime_abort_on_low_confidence:
+                    logger.error("Online search: Low confidence match. Save aborted")
+                    match_results.low_confidence_matches.append(MultipleMatch(ca, matches))
+                    return
+                if not found_match:
+                    logger.error("Online search: No match found. Save aborted")
+                    match_results.no_matches.append(str(ca.path.absolute()))
+                    return
+
+                # we got here, so we have a single match
+
+                # now get the particular issue data
+                ct_md = self.actual_issue_data_fetch(matches[0]["issue_id"])
+                if ct_md.is_empty:
+                    match_results.fetch_data_failures.append(str(ca.path.absolute()))
+                    return
+
+            if self.config.talker_clear_metadata_on_import:
+                md = ct_md
+            else:
+                notes = (
+                    f"Tagged with ComicTagger {ctversion.version} using info from Comic Vine on"
+                    f" {datetime.now():%Y-%m-%d %H:%M:%S}.  [Issue ID {ct_md.issue_id}]"
+                )
+                md.overlay(ct_md.replace(notes=utils.combine_notes(md.notes, notes, "Tagged with ComicTagger")))
+
+            if self.config.talker_auto_imprint:
+                md.fix_publisher()
+
+        # ok, done building our metadata. time to save
+        if not self.actual_metadata_save(ca, md):
+            match_results.write_failures.append(str(ca.path.absolute()))
+        else:
+            match_results.good_matches.append(str(ca.path.absolute()))
+
+    def rename(self, ca: ComicArchive) -> None:
+        original_path = ca.path
+        msg_hdr = ""
+        if self.batch_mode:
+            msg_hdr = f"{ca.path}: "
+
+        md = self.create_local_metadata(ca)
+
+        if md.series is None:
+            logger.error(msg_hdr + "Can't rename without series name")
+            return
+
+        new_ext = ""  # default
+        if self.config.filename_rename_set_extension_based_on_archive:
+            new_ext = ca.extension()
+
+        renamer = FileRenamer(
+            md,
+            platform="universal" if self.config.filename_rename_strict else "auto",
+            replacements=self.config.rename_replacements,
+        )
+        renamer.set_template(self.config.filename_rename_template)
+        renamer.set_issue_zero_padding(self.config.filename_rename_issue_number_padding)
+        renamer.set_smart_cleanup(self.config.filename_rename_use_smart_string_cleanup)
+        renamer.move = self.config.filename_rename_move_to_dir
+
+        try:
+            new_name = renamer.determine_name(ext=new_ext)
+        except ValueError:
+            logger.exception(
+                msg_hdr + "Invalid format string!\n"
+                "Your rename template is invalid!\n\n"
+                "%s\n\n"
+                "Please consult the template help in the settings "
+                "and the documentation on the format at "
+                "https://docs.python.org/3/library/string.html#format-string-syntax",
+                self.config.filename_rename_template,
+            )
+            return
+        except Exception:
+            logger.exception(
+                "Formatter failure: %s metadata: %s", self.config.filename_rename_template, renamer.metadata
+            )
+
+        folder = get_rename_dir(
+            ca, self.config.filename_rename_dir if self.config.filename_rename_move_to_dir else None
+        )
+
+        full_path = folder / new_name
+
+        if full_path == ca.path:
+            print(msg_hdr + "Filename is already good!", file=sys.stderr)
+            return
+
+        suffix = ""
+        if not self.config.runtime_dryrun:
+            # rename the file
+            try:
+                ca.rename(utils.unique_file(full_path))
+            except OSError:
+                logger.exception("Failed to rename comic archive: %s", ca.path)
+        else:
+            suffix = " (dry-run, no change)"
+
+        print(f"renamed '{original_path.name}' -> '{new_name}' {suffix}")
+
+    def export(self, ca: ComicArchive) -> None:
+        msg_hdr = ""
+        if self.batch_mode:
+            msg_hdr = f"{ca.path}: "
+
+        if ca.is_zip():
+            logger.error(msg_hdr + "Archive is already a zip file.")
+            return
+
+        filename_path = ca.path
+        new_file = filename_path.with_suffix(".cbz")
+
+        if self.config.runtime_abort_on_conflict and new_file.exists():
+            print(msg_hdr + f"{new_file.name} already exists in the that folder.")
+            return
+
+        new_file = utils.unique_file(new_file)
+
+        delete_success = False
+        export_success = False
+        if not self.config.runtime_dryrun:
+            if ca.export_as_zip(new_file):
+                export_success = True
+                if self.config.runtime_delete_after_zip_export:
+                    try:
+                        filename_path.unlink(missing_ok=True)
+                        delete_success = True
+                    except OSError:
+                        logger.exception(msg_hdr + "Error deleting original archive after export")
+                        delete_success = False
+            else:
+                # last export failed, so remove the zip, if it exists
+                new_file.unlink(missing_ok=True)
+        else:
+            msg = msg_hdr + f"Dry-run:  Would try to create {os.path.split(new_file)[1]}"
+            if self.config.runtime_delete_after_zip_export:
+                msg += " and delete original."
+            print(msg)
+            return
+
+        msg = msg_hdr
+        if export_success:
+            msg += f"Archive exported successfully to: {os.path.split(new_file)[1]}"
+            if self.config.runtime_delete_after_zip_export and delete_success:
+                msg += " (Original deleted) "
+        else:
+            msg += "Archive failed to export!"
+
+        print(msg)
+
+    def process_file_cli(self, filename: str, match_results: OnlineMatchResults) -> None:
+        if not os.path.lexists(filename):
+            logger.error("Cannot find %s", filename)
+            return
+
+        ca = ComicArchive(filename, str(graphics_path / "nocover.png"))
+
+        if not ca.seems_to_be_a_comic_archive():
+            logger.error("Sorry, but %s is not a comic archive!", filename)
+            return
+
+        if not ca.is_writable() and (
+            self.config.commands_delete
+            or self.config.commands_copy
+            or self.config.commands_save
+            or self.config.commands_rename
+        ):
+            logger.error("This archive is not writable")
+            return
+
+        if self.config.commands_print:
+            self.print(ca)
+
+        elif self.config.commands_delete:
+            self.delete(ca)
+
+        elif self.config.commands_copy is not None:
+            self.copy(ca)
+
+        elif self.config.commands_save:
+            self.save(ca, match_results)
+
+        elif self.config.commands_rename:
+            self.rename(ca)
+
+        elif self.config.commands_export_to_zip:
+            self.export(ca)

comictaggerlib/coverimagewidget.py

@@ -0,0 +1,295 @@
+"""A PyQt5 widget to display cover images
+
+Display cover images from either a local archive, or from Comic Vine.
+TODO: This should be re-factored using subclasses!
+"""
+#
+# 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 pathlib
+
+from PyQt5 import QtCore, QtGui, QtWidgets, uic
+
+from comicapi.comicarchive import ComicArchive
+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 comictalker.comictalker import ComicTalker
+
+logger = logging.getLogger(__name__)
+
+
+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:
+            if obj == widget:
+                if event.type() == QtCore.QEvent.Type.MouseButtonDblClick:
+                    self.dblclicked.emit()
+                    return True
+            return False
+
+    flt = Filter(widget)
+    widget.installEventFilter(flt)
+    return flt.dblclicked
+
+
+class CoverImageWidget(QtWidgets.QWidget):
+    ArchiveMode = 0
+    AltCoverMode = 1
+    URLMode = 1
+    DataMode = 3
+
+    image_fetch_complete = QtCore.pyqtSignal(QtCore.QByteArray)
+
+    def __init__(
+        self,
+        parent: QtWidgets.QWidget,
+        mode: int,
+        cache_folder: pathlib.Path | None,
+        talker: ComicTalker | None,
+        expand_on_click: bool = True,
+    ) -> None:
+        super().__init__(parent)
+
+        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
+        uic.loadUi(ui_path / "coverimagewidget.ui", self)
+
+        reduce_widget_font_size(self.label)
+
+        self.cache_folder = cache_folder
+        self.mode: int = mode
+        self.page_loader: PageLoader | None = None
+        self.showControls = True
+
+        self.current_pixmap = QtGui.QPixmap()
+
+        self.comic_archive: ComicArchive | 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
+        self.page_loader = None
+        self.imageIndex = -1
+        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.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)
+        else:
+            self.lblImage.setToolTip("")
+
+        self.update_content()
+
+    def reset_widget(self) -> None:
+        self.comic_archive = None
+        self.issue_id = ""
+        self.issue_url = None
+        self.url_list = []
+        if self.page_loader is not None:
+            self.page_loader.abandoned = True
+        self.page_loader = None
+        self.imageIndex = -1
+        self.imageCount = 1
+        self.imageData = b""
+
+    def clear(self) -> None:
+        self.reset_widget()
+        self.update_content()
+
+    def increment_image(self) -> None:
+        self.imageIndex += 1
+        if self.imageIndex == self.imageCount:
+            self.imageIndex = 0
+        self.update_content()
+
+    def decrement_image(self) -> None:
+        self.imageIndex -= 1
+        if self.imageIndex == -1:
+            self.imageIndex = self.imageCount - 1
+        self.update_content()
+
+    def set_archive(self, ca: ComicArchive, page: int = 0) -> None:
+        if self.mode == CoverImageWidget.ArchiveMode:
+            self.reset_widget()
+            self.comic_archive = ca
+            self.imageIndex = page
+            self.imageCount = ca.get_number_of_pages()
+            self.update_content()
+
+    def set_url(self, url: str) -> None:
+        if self.mode == CoverImageWidget.URLMode:
+            self.reset_widget()
+            self.update_content()
+
+            self.url_list = [url]
+            self.imageIndex = 0
+            self.imageCount = 1
+            self.update_content()
+
+    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
+
+            self.set_url_list(url_list)
+
+    def set_image_data(self, image_data: bytes) -> None:
+        if self.mode == CoverImageWidget.DataMode:
+            self.reset_widget()
+
+            if image_data:
+                self.imageIndex = 0
+                self.imageData = image_data
+            else:
+                self.imageIndex = -1
+
+            self.update_content()
+
+    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()
+        self.update_controls()
+
+    def set_page(self, pagenum: int) -> None:
+        if self.mode == CoverImageWidget.ArchiveMode:
+            self.imageIndex = pagenum
+            self.update_content()
+
+    def update_content(self) -> None:
+        self.update_image()
+        self.update_controls()
+
+    def update_image(self) -> None:
+        if self.imageIndex == -1:
+            self.load_default()
+        elif self.mode in [CoverImageWidget.AltCoverMode, CoverImageWidget.URLMode]:
+            self.load_url()
+        elif self.mode == CoverImageWidget.DataMode:
+            self.cover_remote_fetch_complete(self.imageData)
+        else:
+            self.load_page()
+
+    def update_controls(self) -> None:
+        if not self.showControls or self.mode == CoverImageWidget.DataMode:
+            self.btnLeft.hide()
+            self.btnRight.hide()
+            self.label.hide()
+            return
+
+        if self.imageIndex == -1 or self.imageCount == 1:
+            self.btnLeft.setEnabled(False)
+            self.btnRight.setEnabled(False)
+            self.btnLeft.hide()
+            self.btnRight.hide()
+        else:
+            self.btnLeft.setEnabled(True)
+            self.btnRight.setEnabled(True)
+            self.btnLeft.show()
+            self.btnRight.show()
+
+        if self.imageIndex == -1 or self.imageCount == 1:
+            self.label.setText("")
+        elif self.mode == CoverImageWidget.AltCoverMode:
+            self.label.setText(f"Cover {self.imageIndex + 1} (of {self.imageCount})")
+        else:
+            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(self.cache_folder)
+        ImageFetcher.image_fetch_complete = self.image_fetch_complete.emit
+        self.cover_fetcher.fetch(self.url_list[self.imageIndex])
+
+    # called when the image is done loading from internet
+    def cover_remote_fetch_complete(self, image_data: bytes) -> None:
+        img = get_qimage_from_data(image_data)
+        self.current_pixmap = QtGui.QPixmap.fromImage(img)
+        self.set_display_pixmap()
+
+    def load_page(self) -> None:
+        if self.comic_archive is not None:
+            if self.page_loader is not None:
+                self.page_loader.abandoned = True
+            self.page_loader = PageLoader(self.comic_archive, self.imageIndex)
+            self.page_loader.loadComplete.connect(self.page_load_complete)
+            self.page_loader.start()
+
+    def page_load_complete(self, image_data: bytes) -> None:
+        img = get_qimage_from_data(image_data)
+        self.current_pixmap = QtGui.QPixmap.fromImage(img)
+        self.set_display_pixmap()
+        self.page_loader = None
+
+    def load_default(self) -> None:
+        self.current_pixmap = QtGui.QPixmap(str(graphics_path / "nocover.png"))
+        self.set_display_pixmap()
+
+    def resizeEvent(self, resize_event: QtGui.QResizeEvent) -> None:
+        if self.current_pixmap is not None:
+            self.set_display_pixmap()
+
+    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()
+        frame_w = self.frame.width()
+        frame_h = self.frame.height()
+
+        new_h -= 4
+        new_w -= 4
+
+        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
+        )
+        self.lblImage.setPixmap(scaled_pixmap)
+
+        # 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))
+
+    def show_popup(self) -> None:
+        ImagePopup(self, self.current_pixmap)

comictaggerlib/crediteditorwindow.py

@@ -0,0 +1,96 @@
+"""A PyQT4 dialog to edit credits"""
+#
+# 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
+from typing import Any
+
+from PyQt5 import QtWidgets, uic
+
+from comictaggerlib.ui import ui_path
+
+logger = logging.getLogger(__name__)
+
+
+class CreditEditorWindow(QtWidgets.QDialog):
+    ModeEdit = 0
+    ModeNew = 1
+
+    def __init__(self, parent: QtWidgets.QWidget, mode: int, role: str, name: str, primary: bool) -> None:
+        super().__init__(parent)
+
+        uic.loadUi(ui_path / "crediteditorwindow.ui", self)
+
+        self.mode = mode
+
+        if self.mode == self.ModeEdit:
+            self.setWindowTitle("Edit Credit")
+        else:
+            self.setWindowTitle("New Credit")
+
+        # 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("Plotter")
+        self.cbRole.addItem("Scripter")
+
+        self.leName.setText(name)
+
+        if role is not None and role != "":
+            i = self.cbRole.findText(role)
+            if i == -1:
+                self.cbRole.setEditText(role)
+            else:
+                self.cbRole.setCurrentIndex(i)
+
+        self.cbPrimary.setChecked(primary)
+
+        self.cbRole.currentIndexChanged.connect(self.role_changed)
+        self.cbRole.editTextChanged.connect(self.role_changed)
+
+        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]:
+        primary = self.current_role_can_be_primary() and self.cbPrimary.isChecked()
+        return self.cbRole.currentText(), self.leName.text(), primary
+
+    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.")
+        else:
+            QtWidgets.QDialog.accept(self)

comictaggerlib/ctsettings/__init__.py

@@ -0,0 +1,24 @@
+from __future__ import annotations
+
+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 register_plugin_settings, validate_plugin_settings
+from comictaggerlib.ctsettings.types import ComicTaggerPaths
+from comictalker import ComicTalker
+
+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",
+]

comictaggerlib/ctsettings/commandline.py

@@ -0,0 +1,306 @@
+"""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 settngs
+
+from comicapi import utils
+from comicapi.genericmetadata import GenericMetadata
+from comictaggerlib import ctversion
+from comictaggerlib.ctsettings.types import ComicTaggerPaths, metadata_type, parse_metadata_from_string
+
+logger = logging.getLogger(__name__)
+
+
+def initial_commandline_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(add_help=False)
+    # Ensure this stays up to date with register_settings
+    parser.add_argument(
+        "--config",
+        help="Config directory defaults to ~/.ComicTagger\non Linux/Mac and %%APPDATA%% on Windows\n",
+        type=ComicTaggerPaths,
+        default=ComicTaggerPaths(),
+    )
+    parser.add_argument("-v", "--verbose", action="count", default=0, help="Be noisy when doing what it does.")
+    return parser
+
+
+def register_settings(parser: settngs.Manager) -> None:
+    parser.add_setting(
+        "--config",
+        help="Config directory defaults to ~/.Config/ComicTagger\non Linux, ~/Library/Application Support/ComicTagger on Mac and %%APPDATA%%\\ComicTagger on Windows\n",
+        type=ComicTaggerPaths,
+        default=ComicTaggerPaths(),
+        file=False,
+    )
+    parser.add_setting(
+        "-v",
+        "--verbose",
+        action="count",
+        default=0,
+        help="Be noisy when doing what it does.",
+        file=False,
+    )
+    parser.add_setting(
+        "--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""",
+        file=False,
+    )
+    parser.add_setting(
+        "--delete-original",
+        action="store_true",
+        dest="delete_after_zip_export",
+        help="""Delete original archive after successful\nexport to Zip. (only relevant for -e)""",
+        file=False,
+    )
+    parser.add_setting(
+        "-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""",
+        file=False,
+    )
+    parser.add_setting(
+        "--id",
+        dest="issue_id",
+        type=int,
+        help="""Use the issue ID when searching online.\nOverrides all other metadata.\n\n""",
+        file=False,
+    )
+    parser.add_setting(
+        "-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""",
+        file=False,
+    )
+    parser.add_setting(
+        "-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""",
+        file=False,
+    )
+    parser.add_setting(
+        "-i",
+        "--interactive",
+        action="store_true",
+        help="""Interactively query the user when there are\nmultiple matches for an online search.\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\nis of low confidence.\n\n""",
+        file=False,
+    )
+    parser.add_setting(
+        "--summary",
+        default=True,
+        action=argparse.BooleanOptionalAction,
+        help="Show the summary after a save operation.\n\n",
+        file=False,
+    )
+    parser.add_setting(
+        "--raw",
+        action="store_true",
+        help="""With -p, will print out the raw tag block(s)\nfrom the file.\n""",
+        file=False,
+    )
+    parser.add_setting(
+        "-R",
+        "--recursive",
+        action="store_true",
+        help="Recursively include files in sub-folders.",
+        file=False,
+    )
+    parser.add_setting(
+        "-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""",
+        file=False,
+    )
+    parser.add_setting(
+        "--split-words",
+        action="store_true",
+        help="""Splits words before parsing the filename.\ne.g. 'judgedredd' to 'judge dredd'\n\n""",
+        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("--darkmode", action="store_true", help="Windows only. Force a dark pallet", file=False)
+    parser.add_setting("-g", "--glob", action="store_true", help="Windows only. Enable globbing", file=False)
+    parser.add_setting("--quiet", "-q", action="store_true", help="Don't say much (for print mode).", file=False)
+
+    parser.add_setting(
+        "-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""",
+        file=False,
+    )
+    parser.add_setting(
+        "--overwrite",
+        dest="overwrite",
+        action=argparse.BooleanOptionalAction,
+        default=True,
+        help="""Apply metadata to already tagged archives (relevant for -s or -c).""",
+        file=False,
+    )
+    parser.add_setting("files", nargs="*", 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",
+        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""",
+        file=False,
+    )
+    parser.add_setting(
+        "-d",
+        "--delete",
+        action="store_true",
+        help="Deletes the tag block of specified type (via -t).\n",
+        file=False,
+    )
+    parser.add_setting(
+        "-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",
+        file=False,
+    )
+    parser.add_setting(
+        "-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",
+        file=False,
+    )
+    parser.add_setting(
+        "-r",
+        "--rename",
+        action="store_true",
+        help="Rename the file based on specified tag style.",
+        file=False,
+    )
+    parser.add_setting(
+        "-e",
+        "--export-to-zip",
+        action="store_true",
+        help="Export RAR archive to Zip format.",
+        file=False,
+    )
+    parser.add_setting(
+        "--only-set-cv-key",
+        action="store_true",
+        help="Only set the Comic Vine API key and quit.\n\n",
+        file=False,
+    )
+
+
+def register_commandline_settings(parser: settngs.Manager) -> None:
+    parser.add_group("commands", register_commands, True)
+    parser.add_group("runtime", register_settings)
+
+
+def validate_commandline_settings(
+    config: settngs.Config[settngs.Namespace], parser: settngs.Manager
+) -> settngs.Config[settngs.Namespace]:
+    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_no_gui = any(
+        [
+            config[0].commands_print,
+            config[0].commands_delete,
+            config[0].commands_save,
+            config[0].commands_copy,
+            config[0].commands_rename,
+            config[0].commands_export_to_zip,
+            config[0].commands_only_set_cv_key,
+        ]
+    )
+
+    if platform.system() == "Windows" and config[0].runtime_glob:
+        # no globbing on windows shell, so do it for them
+        import glob
+
+        globs = config[0].runtime_files
+        config[0].runtime_files = []
+        for item in globs:
+            config[0].runtime_files.extend(glob.glob(item))
+
+    if not config[0].commands_only_set_cv_key and config[0].runtime_no_gui and not config[0].runtime_files:
+        parser.exit(message="Command requires at least one filename!\n", status=1)
+
+    if config[0].commands_delete and not config[0].runtime_type:
+        parser.exit(message="Please specify the type to delete with -t\n", status=1)
+
+    if config[0].commands_save and not config[0].runtime_type:
+        parser.exit(message="Please specify the type to save with -t\n", status=1)
+
+    if config[0].commands_copy:
+        if not config[0].runtime_type:
+            parser.exit(message="Please specify the type to copy to with -t\n", status=1)
+        if len(config[0].commands_copy) > 1:
+            parser.exit(message="Please specify only one type to copy to with -c\n", status=1)
+        config[0].commands_copy = config[0].commands_copy[0]
+
+    if config[0].runtime_recursive:
+        config[0].runtime_file_list = utils.get_recursive_filelist(config[0].runtime_files)
+    else:
+        config[0].runtime_file_list = config[0].runtime_files
+
+    # take a crack at finding rar exe if it's not in the path
+    if not utils.which("rar"):
+        if platform.system() == "Windows":
+            # look in some likely places for Windows machines
+            if os.path.exists(r"C:\Program Files\WinRAR\Rar.exe"):
+                utils.add_to_path(r"C:\Program Files\WinRAR")
+            elif os.path.exists(r"C:\Program Files (x86)\WinRAR\Rar.exe"):
+                utils.add_to_path(r"C:\Program Files (x86)\WinRAR")
+        else:
+            if os.path.exists("/opt/homebrew/bin"):
+                utils.add_to_path("/opt/homebrew/bin")
+
+    return config

comictaggerlib/ctsettings/file.py

@@ -0,0 +1,243 @@
+from __future__ import annotations
+
+import argparse
+import uuid
+
+import settngs
+
+from comictaggerlib.ctsettings.types import AppendAction
+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)
+
+
+def internal(parser: settngs.Manager) -> None:
+    # automatic settings
+    parser.add_setting("install_id", default=uuid.uuid4().hex, cmdline=False)
+    parser.add_setting("save_data_style", default=0, cmdline=False)
+    parser.add_setting("load_data_style", default=0, 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)
+
+
+def identifier(parser: settngs.Manager) -> None:
+    # identifier settings
+    parser.add_setting("--series-match-identify-thresh", default=91, type=int, help="")
+    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. If the difference in height is less than %(default)s%% the cover will not be cropped.",
+    )
+    parser.add_setting(
+        "--publisher-filter",
+        default=["Panini Comics", "Abril", "Planeta DeAgostini", "Editorial Televisa", "Dino Comics"],
+        action=AppendAction,
+        help="When enabled filters the listed publishers from all search results",
+    )
+    parser.add_setting(
+        "--tpb-detection",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        help="Enables TPB detection. May stop comics not marked as a TPB in ComicVine from being found.",
+    )
+
+
+def dialog(parser: settngs.Manager) -> None:
+    # Show/ask dialog flags
+    parser.add_setting("show_disclaimer", default=True, cmdline=False)
+    parser.add_setting("dont_notify_about_this_version", default="", cmdline=False)
+    parser.add_setting("ask_about_usage_stats", default=True, cmdline=False)
+
+
+def filename(parser: settngs.Manager) -> None:
+    # filename parsing settings
+    parser.add_setting(
+        "--complicated-parser",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        help="Enables the new parser which tries to extract more information from filenames",
+    )
+    parser.add_setting(
+        "--remove-c2c",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        help="Removes c2c from filenames. Requires --complicated-parser",
+    )
+    parser.add_setting(
+        "--remove-fcbd",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        help="Removes FCBD/free comic book day from filenames. Requires --complicated-parser",
+    )
+    parser.add_setting(
+        "--remove-publisher",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        help="Attempts to remove publisher names from filenames, currently limited to Marvel and DC. Requires --complicated-parser",
+    )
+
+
+def talker(parser: settngs.Manager) -> None:
+    # General settings for talkers
+    parser.add_setting("--source", default="comicvine", help="Use a specified source by source ID")
+    parser.add_setting("--series-match-search-thresh", default=90, type=int)
+    parser.add_setting(
+        "--clear-metadata",
+        default=True,
+        help="Clears all existing metadata during import, default is to merges metadata.\nMay be used in conjunction with -o, -f and -m.\n\n",
+        dest="clear_metadata_on_import",
+        action=argparse.BooleanOptionalAction,
+    )
+    parser.add_setting(
+        "-a",
+        "--auto-imprint",
+        action=argparse.BooleanOptionalAction,
+        default=False,
+        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_setting(
+        "--sort-series-by-year", default=True, action=argparse.BooleanOptionalAction, help="Sorts series by year"
+    )
+    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",
+    )
+    parser.add_setting(
+        "--always-use-publisher-filter",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        help="Enables the publisher filter",
+    )
+    parser.add_setting(
+        "--clear-form-before-populating",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        help="Clears all existing metadata when applying metadata from comic source",
+    )
+
+
+def cbl(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)
+
+
+def rename(parser: settngs.Manager) -> None:
+    # Rename settings
+    parser.add_setting("--template", default="{series} #{issue} ({year})", help="The teplate to use when renaming")
+    parser.add_setting(
+        "--issue-number-padding",
+        default=3,
+        type=int,
+        help="The minimum number of digits to use for the issue number when renaming",
+    )
+    parser.add_setting(
+        "--use-smart-string-cleanup",
+        default=True,
+        action=argparse.BooleanOptionalAction,
+        help="Attempts to intelligently cleanup whitespace when renaming",
+    )
+    parser.add_setting(
+        "--auto-extension",
+        dest="set_extension_based_on_archive",
+        default=True,
+        action=argparse.BooleanOptionalAction,
+        help="Automatically sets the extension based on the archive type e.g. cbr for rar, cbz for zip",
+    )
+    parser.add_setting("--dir", default="", help="The directory to move renamed files to")
+    parser.add_setting(
+        "--move",
+        dest="move_to_dir",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        help="Enables moving renamed files to a separate directory",
+    )
+    parser.add_setting(
+        "--strict",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        help="Ensures that filenames are valid for all OSs",
+    )
+    parser.add_setting("replacements", default=DEFAULT_REPLACEMENTS, cmdline=False)
+
+
+def autotag(parser: settngs.Manager) -> None:
+    # Auto-tag stickies
+    parser.add_setting(
+        "--save-on-low-confidence",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        help="Automatically save metadata on low-confidence matches",
+    )
+    parser.add_setting(
+        "--dont-use-year-when-identifying",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        help="Ignore the year metadata attribute when identifying a comic",
+    )
+    parser.add_setting(
+        "-1",
+        "--assume-issue-one",
+        dest="assume_1_if_no_issue_num",
+        action=argparse.BooleanOptionalAction,
+        help="Assume issue number is 1 if not found (relevant for -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",
+    )
+    parser.add_setting("remove_archive_after_successful_match", default=False, cmdline=False)
+    parser.add_setting(
+        "-w",
+        "--wait-on-rate-limit",
+        dest="wait_and_retry_on_rate_limit",
+        action=argparse.BooleanOptionalAction,
+        default=True,
+        help="When encountering a Comic Vine rate limit\nerror, wait and retry query.\n\n",
+    )
+
+
+def validate_file_settings(config: settngs.Config[settngs.Namespace]) -> settngs.Config[settngs.Namespace]:
+    config[0].identifier_publisher_filter = [x.strip() for x in config[0].identifier_publisher_filter if x.strip()]
+    config[0].rename_replacements = Replacements(
+        [Replacement(x[0], x[1], x[2]) for x in config[0].rename_replacements[0]],
+        [Replacement(x[0], x[1], x[2]) for x in config[0].rename_replacements[1]],
+    )
+    return config
+
+
+def register_file_settings(parser: settngs.Manager) -> None:
+    parser.add_group("general", general, False)
+    parser.add_group("internal", internal, False)
+    parser.add_group("identifier", identifier, False)
+    parser.add_group("dialog", dialog, False)
+    parser.add_group("filename", filename, False)
+    parser.add_group("talker", talker, False)
+    parser.add_group("cbl", cbl, False)
+    parser.add_group("rename", rename, False)
+    parser.add_group("autotag", autotag, False)

comictaggerlib/ctsettings/plugin.py

@@ -0,0 +1,75 @@
+from __future__ import annotations
+
+import logging
+import os
+
+import settngs
+
+import comicapi.comicarchive
+import comictaggerlib.ctsettings
+
+logger = logging.getLogger("comictagger")
+
+
+def archiver(manager: settngs.Manager) -> None:
+    exe_registered: set[str] = set()
+    for archiver in comicapi.comicarchive.archivers:
+        if archiver.exe and archiver.exe not in exe_registered:
+            manager.add_setting(
+                f"--{archiver.exe.replace(' ', '-').replace('_', '-').strip().strip('-')}",
+                default=archiver.exe,
+                help="Path to the %(default)s executable\n\n",
+            )
+            exe_registered.add(archiver.exe)
+
+
+def register_talker_settings(manager: settngs.Manager) -> None:
+    for talker_name, talker in comictaggerlib.ctsettings.talkers.items():
+        try:
+            manager.add_persistent_group("talker_" + talker_name, talker.register_settings, False)
+        except Exception:
+            logger.exception("Failed to register settings for %s", talker_name)
+
+
+def validate_archive_settings(config: settngs.Config[settngs.Namespace]) -> settngs.Config[settngs.Namespace]:
+    if "archiver" not in config[1]:
+        return config
+    cfg = settngs.normalize_config(config, file=True, cmdline=True, defaults=False)
+    for archiver in comicapi.comicarchive.archivers:
+        exe_name = settngs.sanitize_name(archiver.exe)
+        if (
+            exe_name in cfg[0]["archiver"]
+            and cfg[0]["archiver"][exe_name]
+            and cfg[0]["archiver"][exe_name] != archiver.exe
+        ):
+            if os.path.basename(cfg[0]["archiver"][exe_name]) == archiver.exe:
+                comicapi.utils.add_to_path(os.path.dirname(cfg[0]["archiver"][exe_name]))
+            else:
+                archiver.exe = cfg[0]["archiver"][exe_name]
+
+    return config
+
+
+def validate_talker_settings(config: settngs.Config[settngs.Namespace]) -> settngs.Config[settngs.Namespace]:
+    # Apply talker settings from config file
+    cfg = settngs.normalize_config(config, True, True)
+    for talker_name, talker in list(comictaggerlib.ctsettings.talkers.items()):
+        try:
+            talker.parse_settings(cfg[0]["talker_" + talker_name])
+        except Exception as e:
+            # Remove talker as we failed to apply the settings
+            del comictaggerlib.ctsettings.talkers[talker_name]
+            logger.exception("Failed to initialize talker settings: %s", e)
+
+    return config
+
+
+def validate_plugin_settings(config: settngs.Config[settngs.Namespace]) -> settngs.Config[settngs.Namespace]:
+    config = validate_archive_settings(config)
+    config = validate_talker_settings(config)
+    return config
+
+
+def register_plugin_settings(manager: settngs.Manager) -> None:
+    manager.add_persistent_group("archiver", archiver, False)
+    register_talker_settings(manager)

comictaggerlib/ctsettings/types.py

@@ -0,0 +1,186 @@
+from __future__ import annotations
+
+import argparse
+import pathlib
+from collections.abc import Sequence
+from typing import Any, Callable
+
+from appdirs import AppDirs
+
+from comicapi.comicarchive import MetaDataStyle
+from comicapi.genericmetadata import GenericMetadata
+
+
+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:
+            path = self.path / "cache"
+            return path
+        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:
+            path = self.path / "log"
+            return path
+        return pathlib.Path(super().user_log_dir)
+
+    @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 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 _copy_items(items: Sequence[Any] | None) -> Sequence[Any]:
+    if items is None:
+        return []
+    # The copy module is used only in the 'append' and 'append_const'
+    # actions, and it is needed only when the default value isn't a list.
+    # Delay its import for speeding up the common case.
+    if type(items) is list:
+        return items[:]
+    import copy
+
+    return copy.copy(items)
+
+
+class AppendAction(argparse.Action):
+    def __init__(
+        self,
+        option_strings: list[str],
+        dest: str,
+        nargs: str | None = None,
+        const: Any = None,
+        default: Any = None,
+        type: Callable[[str], Any] | None = None,  # noqa: A002
+        choices: list[Any] | None = None,
+        required: bool = False,
+        help: str | None = None,  # noqa: A002
+        metavar: str | None = None,
+    ):
+        self.called = False
+        if nargs == 0:
+            raise ValueError(
+                "nargs for append actions must be != 0; if arg "
+                "strings are not supplying the value to append, "
+                "the append const action may be more appropriate"
+            )
+        if const is not None and nargs != argparse.OPTIONAL:
+            raise ValueError("nargs must be %r to supply const" % argparse.OPTIONAL)
+        super().__init__(
+            option_strings=option_strings,
+            dest=dest,
+            nargs=nargs,
+            const=const,
+            default=default,
+            type=type,
+            choices=choices,
+            required=required,
+            help=help,
+            metavar=metavar,
+        )
+
+    def __call__(
+        self,
+        parser: argparse.ArgumentParser,
+        namespace: argparse.Namespace,
+        values: str | Sequence[Any] | None,
+        option_string: str | None = None,
+    ) -> None:
+        if values:
+            if not self.called:
+                setattr(namespace, self.dest, [])
+            items = getattr(namespace, self.dest, None)
+            items = _copy_items(items)
+            items.append(values)  # type: ignore
+            setattr(namespace, self.dest, items)
+
+
+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

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

@@ -0,0 +1,60 @@
+"""A PyQT4 dialog to confirm and set options for export to zip"""
+#
+# 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
+
+from PyQt5 import QtCore, QtWidgets, uic
+
+from comictaggerlib.ui import ui_path
+
+logger = logging.getLogger(__name__)
+
+
+class ExportConflictOpts:
+    dontCreate = 1
+    overwrite = 2
+    createUnique = 3
+
+
+class ExportWindow(QtWidgets.QDialog):
+    def __init__(self, parent: QtWidgets.QWidget, msg: str) -> None:
+        super().__init__(parent)
+
+        uic.loadUi(ui_path / "exportwindow.ui", self)
+        self.label.setText(msg)
+
+        self.setWindowFlags(
+            QtCore.Qt.WindowType(self.windowFlags() & ~QtCore.Qt.WindowType.WindowContextHelpButtonHint)
+        )
+
+        self.cbxDeleteOriginal.setChecked(False)
+        self.cbxAddToList.setChecked(True)
+        self.radioDontCreate.setChecked(True)
+
+        self.deleteOriginal = False
+        self.addToList = True
+        self.fileConflictBehavior = ExportConflictOpts.dontCreate
+
+    def accept(self) -> None:
+        QtWidgets.QDialog.accept(self)
+
+        self.deleteOriginal = self.cbxDeleteOriginal.isChecked()
+        self.addToList = self.cbxAddToList.isChecked()
+        if self.radioDontCreate.isChecked():
+            self.fileConflictBehavior = ExportConflictOpts.dontCreate
+        elif self.radioCreateNew.isChecked():
+            self.fileConflictBehavior = ExportConflictOpts.createUnique

comictaggerlib/filerenamer.py

@@ -0,0 +1,244 @@
+"""Functions for renaming files based on metadata"""
+#
+# 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 calendar
+import logging
+import os
+import pathlib
+import string
+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__)
+
+
+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()
+    return folder
+
+
+class MetadataFormatter(string.Formatter):
+    def __init__(
+        self, smart_cleanup: bool = False, platform: str = "auto", replacements: Replacements = DEFAULT_REPLACEMENTS
+    ) -> None:
+        super().__init__()
+        self.smart_cleanup = smart_cleanup
+        self.platform = normalize_platform(platform)
+        self.replacements = replacements
+
+    def format_field(self, value: Any, format_spec: str) -> str:
+        if value is None or value == "":
+            return ""
+        return cast(str, super().format_field(value, format_spec))
+
+    def convert_field(self, value: Any, conversion: str) -> str:
+        if conversion == "u":
+            return str(value).upper()
+        if conversion == "l":
+            return str(value).casefold()
+        if conversion == "c":
+            return str(value).capitalize()
+        if conversion == "S":
+            return str(value).swapcase()
+        if conversion == "t":
+            return str(value).title()
+        return cast(str, super().convert_field(value, conversion))
+
+    def handle_replacements(self, string: str, replacements: list[Replacement]) -> str:
+        for find, replace, strict_only in replacements:
+            if self.is_strict() or not strict_only:
+                string = string.replace(find, replace)
+        return string
+
+    def none_replacement(self, value: Any, replacement: str, r: str) -> Any:
+        if r == "-" and value is None or value == "":
+            return replacement
+        if r == "+" and value is not None:
+            return replacement
+        return value
+
+    def split_replacement(self, field_name: str) -> tuple[str, str, str]:
+        if "-" in field_name:
+            return field_name.rpartition("-")
+        if "+" in field_name:
+            return field_name.rpartition("+")
+        return field_name, "", ""
+
+    def is_strict(self) -> bool:
+        return self.platform in [Platform.UNIVERSAL, Platform.WINDOWS]
+
+    def _vformat(
+        self,
+        format_string: str,
+        args: list[Any],
+        kwargs: dict[str, Any],
+        used_args: set[Any],
+        recursion_depth: int,
+        auto_arg_index: int = 0,
+    ) -> tuple[str, int]:
+        if recursion_depth < 0:
+            raise ValueError("Max string recursion exceeded")
+        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:
+                    literal_text = literal_text.lstrip("-_)}]#")
+                if self.smart_cleanup:
+                    literal_text = self.handle_replacements(literal_text, self.replacements.literal_text)
+                    lspace = literal_text[0].isspace() if literal_text else False
+                    rspace = literal_text[-1].isspace() if literal_text else False
+                    literal_text = " ".join(literal_text.split())
+                    if literal_text == "":
+                        literal_text = " "
+                    else:
+                        if lspace:
+                            literal_text = " " + literal_text
+                        if rspace:
+                            literal_text += " "
+                result.append(literal_text)
+
+            lstrip = False
+            # if there's a field, output it
+            if field_name is not None and field_name != "":
+                field_name, r, replacement = self.split_replacement(field_name)
+                field_name = field_name.casefold()
+                # this is some markup, find the object and do the formatting
+
+                # handle arg indexing when digit field_names are given.
+                if field_name.isdigit():
+                    raise ValueError("cannot use a number as a field name")
+
+                # 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)
+
+                obj = self.none_replacement(obj, replacement, r)
+
+                # do any conversion on the resulting object
+                obj = self.convert_field(obj, conversion)  # type: ignore
+
+                # expand the format spec, if needed
+                format_spec, _ = self._vformat(
+                    cast(str, format_spec), args, kwargs, used_args, recursion_depth - 1, auto_arg_index=False
+                )
+
+                # format the object and append to the result
+                fmt_obj = self.format_field(obj, format_spec)
+                if fmt_obj == "" and result and self.smart_cleanup and literal_text:
+                    if self.str_contains(result[-1], "({["):
+                        lstrip = True
+                    if result:
+                        if " " in result[-1]:
+                            result[-1], _, _ = result[-1].rstrip().rpartition(" ")
+                        result[-1] = result[-1].rstrip("-_({[#")
+                if self.smart_cleanup:
+                    # colons and slashes get special treatment
+                    fmt_obj = self.handle_replacements(fmt_obj, self.replacements.format_value)
+                    fmt_obj = " ".join(fmt_obj.split())
+                    fmt_obj = str(sanitize_filename(fmt_obj, platform=self.platform))
+                result.append(fmt_obj)
+
+        return "".join(result), False
+
+    def str_contains(self, chars: str, string: str) -> bool:
+        for char in chars:
+            if char in string:
+                return True
+        return False
+
+
+class FileRenamer:
+    def __init__(
+        self,
+        metadata: GenericMetadata | None,
+        platform: str = "auto",
+        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
+
+    def set_metadata(self, metadata: GenericMetadata) -> None:
+        self.metadata = metadata
+
+    def set_issue_zero_padding(self, count: int) -> None:
+        self.issue_zero_padding = count
+
+    def set_smart_cleanup(self, on: bool) -> None:
+        self.smart_cleanup = on
+
+    def set_template(self, template: str) -> None:
+        self.template = template
+
+    def determine_name(self, ext: str) -> str:
+        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, replacements=self.replacements)
+        md_dict = vars(md)
+        for role in ["writer", "penciller", "inker", "colorist", "letterer", "cover artist", "editor"]:
+            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"] = ""
+
+        new_basename = ""
+        for component in pathlib.PureWindowsPath(template).parts:
+            new_basename = str(
+                sanitize_filename(fmt.vformat(component, args=[], kwargs=Default(md_dict)), platform=self.platform)
+            ).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:
+            return new_name.strip()
+        return new_basename.strip()

comictaggerlib/fileselectionlist.py

@@ -0,0 +1,419 @@
+"""A PyQt5 widget for managing list of comic archive files"""
+#
+# 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 os
+import platform
+from typing import Callable, cast
+
+import settngs
+from PyQt5 import QtCore, QtWidgets, uic
+
+from comicapi import utils
+from comicapi.comicarchive import ComicArchive
+from comictaggerlib.graphics import graphics_path
+from comictaggerlib.optionalmsgdialog import OptionalMessageDialog
+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
+
+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
+    dataColNum = fileColNum
+
+    def __init__(
+        self, parent: QtWidgets.QWidget, config: settngs.Namespace, dirty_flag_verification: Callable[[str, str], bool]
+    ) -> None:
+        super().__init__(parent)
+
+        uic.loadUi(ui_path / "fileselectionlist.ui", self)
+
+        self.config = config
+
+        reduce_widget_font_size(self.twList)
+
+        self.twList.setColumnCount(6)
+        self.twList.currentItemChanged.connect(self.current_item_changed_cb)
+
+        self.currentItem = None
+        self.setContextMenuPolicy(QtCore.Qt.ContextMenuPolicy.ActionsContextMenu)
+        self.dirty_flag = False
+
+        select_all_action = QtWidgets.QAction("Select All", self)
+        remove_action = QtWidgets.QAction("Remove Selected Items", self)
+        self.separator = QtWidgets.QAction("", self)
+        self.separator.setSeparator(True)
+
+        select_all_action.setShortcut("Ctrl+A")
+        remove_action.setShortcut("Ctrl+X")
+
+        select_all_action.triggered.connect(self.select_all)
+        remove_action.triggered.connect(self.remove_selection)
+
+        self.addAction(select_all_action)
+        self.addAction(remove_action)
+        self.addAction(self.separator)
+
+        self.dirty_flag_verification = dirty_flag_verification
+        self.rar_ro_shown = False
+
+    def get_sorting(self) -> tuple[int, int]:
+        col = self.twList.horizontalHeader().sortIndicatorSection()
+        order = self.twList.horizontalHeader().sortIndicatorOrder()
+        return int(col), int(order)
+
+    def set_sorting(self, col: int, order: QtCore.Qt.SortOrder) -> None:
+        self.twList.horizontalHeader().setSortIndicator(col, order)
+
+    def add_app_action(self, action: QtWidgets.QAction) -> None:
+        self.insertAction(QtWidgets.QAction(), action)
+
+    def set_modified_flag(self, modified: bool) -> None:
+        self.dirty_flag = modified
+
+    def select_all(self) -> None:
+        self.twList.setRangeSelected(QtWidgets.QTableWidgetSelectionRange(0, 0, self.twList.rowCount() - 1, 5), True)
+
+    def deselect_all(self) -> None:
+        self.twList.setRangeSelected(QtWidgets.QTableWidgetSelectionRange(0, 0, self.twList.rowCount() - 1, 5), False)
+
+    def remove_archive_list(self, ca_list: list[ComicArchive]) -> None:
+        self.twList.setSortingEnabled(False)
+        current_removed = False
+        for ca in ca_list:
+            for row in range(self.twList.rowCount()):
+                row_ca = self.get_archive_by_row(row)
+                if row_ca == ca:
+                    if row == self.twList.currentRow():
+                        current_removed = True
+                    self.twList.removeRow(row)
+                    break
+        self.twList.setSortingEnabled(True)
+
+        if self.twList.rowCount() > 0 and current_removed:
+            # since on a removal, we select row 0, make sure callback occurs if
+            # we're already there
+            if self.twList.currentRow() == 0:
+                self.current_item_changed_cb(self.twList.currentItem(), None)
+            self.twList.selectRow(0)
+        elif self.twList.rowCount() <= 0:
+            self.listCleared.emit()
+
+    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
+        return None
+
+    def get_current_archive(self) -> ComicArchive | None:
+        return self.get_archive_by_row(self.twList.currentRow())
+
+    def remove_selection(self) -> None:
+        row_list = []
+        for item in self.twList.selectedItems():
+            if item.column() == 0:
+                row_list.append(item.row())
+
+        if len(row_list) == 0:
+            return
+
+        if self.twList.currentRow() in row_list:
+            if not self.dirty_flag_verification(
+                "Remove Archive", "If you close this archive, data in the form will be lost.  Are you sure?"
+            ):
+                return
+
+        row_list.sort()
+        row_list.reverse()
+
+        self.twList.currentItemChanged.disconnect(self.current_item_changed_cb)
+        self.twList.setSortingEnabled(False)
+
+        for i in row_list:
+            self.twList.removeRow(i)
+
+        self.twList.setSortingEnabled(True)
+        self.twList.currentItemChanged.connect(self.current_item_changed_cb)
+
+        if self.twList.rowCount() > 0:
+            # since on a removal, we select row 0, make sure callback occurs if
+            # we're already there
+            if self.twList.currentRow() == 0:
+                self.current_item_changed_cb(self.twList.currentItem(), None)
+            self.twList.selectRow(0)
+        else:
+            self.listCleared.emit()
+
+    def add_path_list(self, pathlist: list[str]) -> None:
+        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)
+
+        QtCore.QCoreApplication.processEvents()
+        first_added = None
+        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)
+            QtCore.QCoreApplication.processEvents()
+            row = self.add_path_item(f)
+            if row is not None:
+                ca = self.get_archive_by_row(row)
+                rar_added_ro = bool(ca and ca.archiver.name() == "RAR" and not ca.archiver.is_writable())
+                if first_added is None:
+                    first_added = row
+
+        progdialog.hide()
+        QtCore.QCoreApplication.processEvents()
+
+        if first_added is not None:
+            self.twList.selectRow(first_added)
+        else:
+            if len(pathlist) == 1 and os.path.isfile(pathlist[0]):
+                QtWidgets.QMessageBox.information(
+                    self, "File Open", "Selected file doesn't seem to be a comic archive."
+                )
+            else:
+                QtWidgets.QMessageBox.information(self, "File/Folder Open", "No readable comic archives were found.")
+
+        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.readonlyColNum, 35)
+        self.twList.setColumnWidth(FileSelectionList.typeColNum, 45)
+        if self.twList.columnWidth(FileSelectionList.fileColNum) > 250:
+            self.twList.setColumnWidth(FileSelectionList.fileColNum, 250)
+        if self.twList.columnWidth(FileSelectionList.folderColNum) > 200:
+            self.twList.setColumnWidth(FileSelectionList.folderColNum, 200)
+
+    def rar_ro_message(self) -> None:
+        if not self.rar_ro_shown:
+            if platform.system() == "Windows":
+                rar_help = windowsRarHelp
+
+            elif platform.system() == "Darwin":
+                rar_help = macRarHelp
+
+            else:
+                rar_help = linuxRarHelp
+
+            OptionalMessageDialog.msg_no_checkbox(
+                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"
+                f"{rar_help}",
+            )
+            self.rar_ro_shown = True
+
+    def is_list_dupe(self, path: str) -> bool:
+        return self.get_current_list_row(path) >= 0
+
+    def get_current_list_row(self, path: str) -> int:
+        for r in range(self.twList.rowCount()):
+            ca = cast(ComicArchive, self.get_archive_by_row(r))
+            if str(ca.path) == path:
+                return r
+
+        return -1
+
+    def add_path_item(self, path: str) -> int:
+        path = str(path)
+        path = os.path.abspath(path)
+
+        if self.is_list_dupe(path):
+            return self.get_current_list_row(path)
+
+        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()
+            type_item = QtWidgets.QTableWidgetItem()
+
+            filename_item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
+            filename_item.setData(QtCore.Qt.ItemDataRole.UserRole, fi)
+            self.twList.setItem(row, FileSelectionList.fileColNum, filename_item)
+
+            folder_item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
+            self.twList.setItem(row, FileSelectionList.folderColNum, folder_item)
+
+            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)
+
+            readonly_item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
+            readonly_item.setTextAlignment(QtCore.Qt.AlignmentFlag.AlignHCenter)
+            self.twList.setItem(row, FileSelectionList.readonlyColNum, readonly_item)
+
+            self.update_row(row)
+
+            return row
+        return -1
+
+    def update_row(self, row: int) -> None:
+        if row >= 0:
+            fi: FileInfo = 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)
+            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]
+            folder_item.setText(item_text)
+            folder_item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, item_text)
+
+            item_text = os.path.split(fi.ca.path)[1]
+            filename_item.setText(item_text)
+            filename_item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, item_text)
+
+            item_text = fi.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)
+
+            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():
+                readonly_item.setCheckState(QtCore.Qt.CheckState.Checked)
+                readonly_item.setData(QtCore.Qt.ItemDataRole.UserRole, True)
+            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()
+
+    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)
+
+        return ca_list
+
+    def update_current_row(self) -> None:
+        self.update_row(self.twList.currentRow())
+
+    def update_selected_rows(self) -> None:
+        self.twList.setSortingEnabled(False)
+        for r in range(self.twList.rowCount()):
+            item = self.twList.item(r, FileSelectionList.dataColNum)
+            if item.isSelected():
+                self.update_row(r)
+        self.twList.setSortingEnabled(True)
+
+    def current_item_changed_cb(self, curr: QtCore.QModelIndex | None, prev: QtCore.QModelIndex | None) -> None:
+        if curr is not None:
+            new_idx = curr.row()
+            old_idx = -1
+            if prev is not None:
+                old_idx = prev.row()
+
+            if old_idx == new_idx:
+                return
+
+            # don't allow change if modified
+            if prev is not None and new_idx != old_idx:
+                if not self.dirty_flag_verification(
+                    "Change Archive", "If you change archives now, data in the form will be lost.  Are you sure?"
+                ):
+                    self.twList.currentItemChanged.disconnect(self.current_item_changed_cb)
+                    self.twList.setCurrentItem(prev)
+                    self.twList.currentItemChanged.connect(self.current_item_changed_cb)
+                    # Need to defer this revert selection, for some reason
+                    QtCore.QTimer.singleShot(1, self.revert_selection)
+                    return
+
+            fi = self.twList.item(new_idx, FileSelectionList.dataColNum).data(QtCore.Qt.ItemDataRole.UserRole)
+            self.selectionChanged.emit(QtCore.QVariant(fi))
+
+    def revert_selection(self) -> None:
+        self.twList.selectRow(self.twList.currentRow())

comictaggerlib/graphics/__init__.py

@@ -0,0 +1,5 @@
+from __future__ import annotations
+
+import pathlib
+
+graphics_path = pathlib.Path(__file__).parent

comictaggerlib/gui.py

@@ -0,0 +1,143 @@
+from __future__ import annotations
+
+import logging.handlers
+import os
+import platform
+import sys
+import traceback
+import types
+
+import settngs
+
+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.setText(log_msg)
+            errorbox.exec()
+            QtWidgets.QApplication.exit(1)
+        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
+
+    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.error(str(e))
+    qt_available = False
+
+
+def open_tagger_window(
+    talkers: dict[str, ComicTalker], config: settngs.Config[settngs.Namespace], error: tuple[str, bool] | None
+) -> None:
+    os.environ["QtWidgets.QT_AUTO_SCREEN_SCALE_FACTOR"] = "1"
+    args = []
+    if config[0].runtime_darkmode:
+        args.extend(["-platform", "windows:darkmode=2"])
+    args.extend(sys.argv)
+    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_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(config[0].runtime_files, config, talkers)
+        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()
+        )

comictaggerlib/imagefetcher.py

@@ -0,0 +1,169 @@
+"""A class to manage fetching and caching of images by URL"""
+#
+# 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 datetime
+import logging
+import os
+import pathlib
+import shutil
+import sqlite3 as lite
+import tempfile
+
+import requests
+
+from comictaggerlib import ctversion
+
+try:
+    from PyQt5 import QtCore, QtNetwork
+
+    qt_available = True
+except ImportError:
+    qt_available = False
+
+logger = logging.getLogger(__name__)
+
+
+class ImageFetcherException(Exception):
+    ...
+
+
+def fetch_complete(image_data: bytes | QtCore.QByteArray) -> None:
+    ...
+
+
+class ImageFetcher:
+    image_fetch_complete = fetch_complete
+
+    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 not os.path.exists(self.db_file):
+            self.create_image_db()
+
+        if 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)
+
+    def fetch(self, url: str, blocking: bool = False) -> bytes:
+        """
+        If called with blocking=True, this will block until the image is
+        fetched.
+        If called with blocking=False, this will run the fetch in the
+        background, and emit a signal when done
+        """
+
+        self.fetched_url = url
+
+        # first look in the DB
+        image_data = self.get_image_from_cache(url)
+        # Async for retrieving covers seems to work well
+        if blocking:  # if blocking or not qt_available:
+            if not image_data:
+                try:
+                    image_data = requests.get(url, headers={"user-agent": "comictagger/" + ctversion.version}).content
+                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 we found it, just emit the signal asap
+            if image_data:
+                ImageFetcher.image_fetch_complete(QtCore.QByteArray(image_data))
+                return b""
+
+            # didn't find it.  look online
+            self.nam.finished.connect(self.finish_request)
+            self.nam.get(QtNetwork.QNetworkRequest(QtCore.QUrl(url)))
+
+            # we'll get called back when done...
+        return b""
+
+    def finish_request(self, reply: QtNetwork.QNetworkReply) -> None:
+        # read in the image data
+        logger.debug("request finished")
+        image_data = reply.readAll()
+
+        # save the image to the cache
+        self.add_image_to_cache(self.fetched_url, image_data)
+
+        ImageFetcher.image_fetch_complete(image_data)
+
+    def create_image_db(self) -> None:
+        # this will wipe out any existing version
+        open(self.db_file, "wb").close()
+
+        # wipe any existing image cache folder too
+        if os.path.isdir(self.cache_folder):
+            shutil.rmtree(self.cache_folder)
+        os.makedirs(self.cache_folder)
+
+        con = lite.connect(self.db_file)
+
+        # create tables
+        with 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:
+            cur = con.cursor()
+
+            timestamp = datetime.datetime.now()
+
+            tmp_fd, filename = tempfile.mkstemp(dir=self.cache_folder, prefix="img")
+            with os.fdopen(tmp_fd, "w+b") as f:
+                f.write(bytes(image_data))
+
+            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:
+            cur = con.cursor()
+
+            cur.execute("SELECT filename FROM Images WHERE url=?", [url])
+            row = cur.fetchone()
+
+            if row is None:
+                return b""
+
+            filename = row[0]
+            image_data = b""
+
+            try:
+                with open(filename, "rb") as f:
+                    image_data = f.read()
+                    f.close()
+            except OSError:
+                pass
+
+            return image_data

comictaggerlib/imagehasher.py

@@ -0,0 +1,188 @@
+"""A class to manage creating image content hashes, and calculate hamming distances"""
+#
+# 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.
+# 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 io
+import logging
+from functools import reduce
+from typing import TypeVar
+
+try:
+    from PIL import Image
+
+    pil_available = True
+except ImportError:
+    pil_available = False
+logger = logging.getLogger(__name__)
+
+
+class ImageHasher:
+    def __init__(self, path: str | 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:
+            raise OSError
+
+        try:
+            if path is not None:
+                self.image = Image.open(path)
+            else:
+                self.image = Image.open(io.BytesIO(data))
+        except Exception:
+            logger.exception("Image data seems corrupted!")
+            # just generate a bogus image
+            self.image = Image.new("L", (1, 1))
+
+    def average_hash(self) -> int:
+        try:
+            image = self.image.resize((self.width, self.height), Image.Resampling.LANCZOS).convert("L")
+        except Exception:
+            logger.exception("average_hash error")
+            return 0
+
+        pixels = list(image.getdata())
+        avg = sum(pixels) / len(pixels)
+
+        def compare_value_to_avg(i: int) -> int:
+            return 1 if i > avg else 0
+
+        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)
+
+        return result
+
+    def average_hash2(self) -> None:
+        """
+        # Got this one from somewhere on the net.  Not a clue how the 'convolve2d' works!
+
+        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))
+
+
+        return result
+        """
+
+    # accepts 2 hashes (longs or hex strings) and returns the hamming distance
+
+    T = TypeVar("T", int, str)
+
+    @staticmethod
+    def hamming_distance(h1: T, h2: T) -> int:
+        if isinstance(h1, int) or isinstance(h2, int):
+            n1 = h1
+            n2 = h2
+        else:
+            # convert hex strings to ints
+            n1 = int(h1, 16)
+            n2 = int(h2, 16)
+
+        # xor the two numbers
+        n = n1 ^ n2
+
+        # count up the 1's in the binary string
+        return sum(b == "1" for b in bin(n)[2:])