pdf2zh-next 2.0.0__tar.gz

pdf2zh_next-2.0.0/.dockerignore

@@ -0,0 +1,175 @@
+.github
+docs
+.git
+.pre-commit-config.yaml
+uv.lock
+pdf2zh_files
+gui/pdf2zh_files
+gradio_files
+tmp
+gui/gradio_files
+gui/tmp
+# 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
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__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/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/
+.vscode
+.DS_Store

pdf2zh_next-2.0.0/.github/FUNDING.yml

@@ -0,0 +1,15 @@
+# These are supported funding model platforms
+
+github: [Byaidu, reycn, Wybxc, hellofinch] # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2]
+patreon: # Replace with a single Patreon username
+open_collective: # Replace with a single Open Collective username
+ko_fi: # Replace with a single Ko-fi username
+tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
+community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
+liberapay: # Replace with a single Liberapay username
+issuehunt: # Replace with a single IssueHunt username
+lfx_crowdfunding: # Replace with a single LFX Crowdfunding project-name e.g., cloud-foundry
+polar: # Replace with a single Polar username
+buy_me_a_coffee: # Replace with a single Buy Me a Coffee username
+thanks_dev: # Replace with a single thanks.dev username
+custom: # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']

pdf2zh_next-2.0.0/.github/ISSUE_TEMPLATE/blank.yaml

@@ -0,0 +1,14 @@
+name: Blank Issue
+description: Create a blank issue for discussion
+body:
+  - type: checkboxes
+    id: checks
+    attributes:
+      label: before ...
+      options:
+      - label: This issue is not about question or bug.
+        required: true
+  - type: textarea
+    id: describe
+    attributes:
+      label: Add a description

pdf2zh_next-2.0.0/.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1 @@
+blank_issues_enabled: false

pdf2zh_next-2.0.0/.github/ISSUE_TEMPLATE//345/212/237/350/203/275/350/257/267/346/261/202_cn.yaml

@@ -0,0 +1,25 @@
+name: 功能请求
+description: 使用中文进行功能请求
+labels: ['enhancement']
+body:
+  - type: textarea
+    id: describe
+    attributes:
+      label: 在什么场景下，需要你请求的功能？
+      description: 简要描述相关的使用场景
+    validations:
+      required: false
+  - type: textarea
+    id: solution
+    attributes:
+      label: 解决方案
+      description: 描述你想要的解决方案
+    validations:
+      required: false
+  - type: textarea
+    id: additional
+    attributes:
+      label: 其他内容
+      description: 关于该功能请求的任何其他项目。
+    validations:
+      required: false

pdf2zh_next-2.0.0/.github/ISSUE_TEMPLATE//345/212/237/350/203/275/350/257/267/346/261/202_en.yaml

@@ -0,0 +1,26 @@
+name: Feature request
+description: Suggest an idea for this project
+labels: ['enhancement']
+body:
+  - type: textarea
+    id: describe
+    attributes:
+      label: Is your feature request related to a problem?
+      description: A clear and concise description of what the problem is
+      placeholder: Ex. I'm always frustrated when ...
+    validations:
+      required: false
+  - type: textarea
+    id: solution
+    attributes:
+      label: Describe the solution you'd like
+      description: A clear and concise description of what you want to happen
+    validations:
+      required: false
+  - type: textarea
+    id: additional
+    attributes:
+      label: Additional context
+      description: Add any other projects about the feature request here.
+    validations:
+      required: false

pdf2zh_next-2.0.0/.github/ISSUE_TEMPLATE//351/227/256/351/242/230/345/217/215/351/246/210_cn.yaml

@@ -0,0 +1,94 @@
+name: 上报 Bug
+description: 使用中文进行 Bug 报告
+labels: ['bug']
+body:
+  - type: checkboxes
+    id: checks
+    attributes:
+      label: 在提问之前...
+      options:
+      - label: 我已经搜索了现有的 issues
+        required: true
+      - label: 我在提问题之前至少花费了 5 分钟来思考和准备
+        required: true
+      - label: 我已经认真且完整的阅读了 wiki
+        required: true
+      - label: 我已经认真检查了问题和网络环境无关（包括但不限于Google不可用，模型下载失败）
+        required: true
+  - type: markdown
+    attributes:
+      value: |
+        感谢您使用本项目并反馈！
+        请再次确认上述复选框所述的内容已经认真执行！
+  - type: textarea
+    id: environment
+    attributes:
+      label: 使用的环境
+      placeholder: |
+          - **OS**: Ubuntu 24.10  
+          - **Python**: 3.12.0  
+          - **pdf2zh**: 1.9.0
+      render: markdown
+    validations:
+      required: false
+  - type: dropdown
+    id: install
+    attributes:
+      label: 请选择安装方式
+      options:
+        - pip
+        - exe
+        - 源码
+        - docker
+    validations:
+      required: true
+  - type: textarea
+    id: describe
+    attributes:
+      label: 描述你的问题
+      description: 简要描述你的问题
+    validations:
+      required: true
+  - type: textarea
+    id: reproduce
+    attributes:
+      label: 如何复现
+      description: 重现该行为的步骤
+      value: |
+        1. 执行 '...'
+        2. 选择 '....'
+        3. 出现问题
+    validations:
+      required: false
+  - type: textarea
+    id: expected
+    attributes:
+      label: 预期行为
+      description: 简要描述你期望得到的反馈
+    validations:
+      required: false
+  - type: textarea
+    id: logs
+    attributes:
+      label: 相关 Logs
+      description: 请复制并粘贴任何相关的日志输出。
+      render: Text
+    validations:
+      required: false
+  - type: textarea
+    id: PDFfile
+    attributes:
+      label: 原始PDF文件
+      description: |
+        如果涉及到排版错误的问题，请一定提供原始的PDF文件，方便复现错误。
+    validations:
+      required: false
+  - type: textarea
+    id: others
+    attributes:
+      label: 还有别的吗？
+      description: |
+        相关的配置？链接？参考资料？
+        任何能让我们对你所遇到的问题有更多了解的东西。
+    validations:
+      required: false

pdf2zh_next-2.0.0/.github/ISSUE_TEMPLATE//351/227/256/351/242/230/345/217/215/351/246/210_en.yaml

@@ -0,0 +1,93 @@
+name: Bug Report
+description: Create a report to help us improve
+labels: ['bug']
+body:
+  - type: checkboxes
+    id: checks
+    attributes:
+      label: Before you asking
+      options:
+      - label: I have searched the existing issues
+        required: true
+      - label: I spend at least 5 minutes for thinking and preparing
+        required: true
+      - label: I have thoroughly and completely read the wiki.
+        required: true
+      - label: I have carefully checked the issue, and it is unrelated to the network environment.
+        required: true
+  - type: markdown
+    attributes:
+      value: |
+        Thank you for using this project and providing feedback!
+  - type: textarea
+    id: environment
+    attributes:
+      label: Environment
+      placeholder: |
+          - **OS**: Ubuntu 24.10
+          - **Python**: 3.12.0
+          - **pdf2zh**: 1.9.0
+      render: markdown
+    validations:
+      required: false
+  - type: dropdown
+    id: install
+    attributes:
+      label: How to install pdf2zh_next
+      options:
+        - pip
+        - exe
+        - source
+        - docker
+    validations:
+      required: true
+  - type: textarea
+    id: describe
+    attributes:
+      label: Describe the bug
+      description: A clear and concise description of what the bug is.
+    validations:
+      required: true
+  - type: textarea
+    id: reproduce
+    attributes:
+      label: To Reproduce
+      description: Steps to reproduce the behavior
+      value: |
+        1. execute '...'
+        2. select '....'
+        3. see errors
+    validations:
+      required: false
+  - type: textarea
+    id: expected
+    attributes:
+      label: Expected behavior
+      description: A clear and concise description of what you expected to happen.
+    validations:
+      required: false
+  - type: textarea
+    id: logs
+    attributes:
+      label: Relevant log output
+      description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
+      render: Text
+    validations:
+      required: false
+  - type: textarea
+    id: PDFfile
+    attributes:
+      label: Origin PDF file
+      description: |
+        If the issue involves formatting errors, please provide the original PDF file to facilitate reproduction of the error.
+    validations:
+      required: false
+  - type: textarea
+    id: others
+    attributes:
+      label: Anything else?
+      description: |
+        Related configs? Links? References?
+        Anything that will give us more context about the issue you are encountering!
+    validations:
+      required: false

pdf2zh_next-2.0.0/.github/dependabot.yml

@@ -0,0 +1,21 @@
+version: 2
+updates:
+  - package-ecosystem: github-actions
+    directory: "/"
+    schedule:
+      interval: weekly
+  # - package-ecosystem: pip
+  #   directory: "/.github/workflows"
+  #   schedule:
+  #     interval: weekly
+  # - package-ecosystem: pip
+  #   directory: "/docs"
+  #   schedule:
+  #     interval: weekly
+  - package-ecosystem: pip
+    directory: "/"
+    schedule:
+      interval: weekly
+    versioning-strategy: lockfile-only
+    allow:
+      - dependency-type: "all"

pdf2zh_next-2.0.0/.github/release-drafter.yml

@@ -0,0 +1,55 @@
+name-template: 'v$RESOLVED_VERSION'
+tag-template: 'v$RESOLVED_VERSION'
+categories:
+  - title: '🚀 Features'
+    labels:
+      - 'feature'
+      - 'enhancement'
+  - title: '🐛 Bug Fixes'
+    labels:
+      - 'fix'
+      - 'bugfix'
+      - 'bug'
+  - title: '🧰 Maintenance'
+    labels:
+      - 'chore'
+      - 'maintenance'
+      - 'refactor'
+  - title: '📝 Documentation'
+    labels:
+      - 'docs'
+      - 'documentation'
+change-template: '- $TITLE @$AUTHOR (#$NUMBER)'
+change-title-escapes: '\<*_&' # You can add # and @ to disable mentions
+version-resolver:
+  major:
+    labels:
+      - 'major'
+  minor:
+    labels:
+      - 'minor'
+  patch:
+    labels:
+      - 'patch'
+  default: patch
+template: |
+  ## Changes
+
+  $CHANGES
+
+  ## Contributors
+  
+  $CONTRIBUTORS
+
+  ## Windows Specific
+
+  If you cannot open it after downloading, please install https://aka.ms/vs/17/release/vc_redist.x64.exe and try again.
+
+  ## Assets
+
+  - pdf2zh-v$RESOLVED_VERSION-win64.zip: pdf2zh **without** assets(font, model, etc.)
+  - pdf2zh-v$RESOLVED_VERSION-with-assets-win64.zip: (**Recommended**) pdf2zh **with** assets(font, model, etc.)
+
+  > [!NOTE]
+  >
+  > The version without assets will also dynamically download resources when running, but the download may fail due to network issues.

pdf2zh_next-2.0.0/.github/workflows/codeql.yml

@@ -0,0 +1,92 @@
+# For most projects, this workflow file will not need changing; you simply need
+# to commit it to your repository.
+#
+# You may wish to alter this file to override the set of languages analyzed,
+# or to provide custom queries or build logic.
+#
+# ******** NOTE ********
+# We have attempted to detect the languages in your repository. Please check
+# the `language` matrix defined below to confirm you have the correct set of
+# supported CodeQL languages.
+#
+name: "CodeQL Advanced"
+
+on:
+  push:
+  pull_request:
+    branches: [ "main" ]
+  schedule:
+    - cron: '36 14 * * 1'
+
+jobs:
+  analyze:
+    name: Analyze (${{ matrix.language }})
+    # Runner size impacts CodeQL analysis time. To learn more, please see:
+    #   - https://gh.io/recommended-hardware-resources-for-running-codeql
+    #   - https://gh.io/supported-runners-and-hardware-resources
+    #   - https://gh.io/using-larger-runners (GitHub.com only)
+    # Consider using larger runners or machines with greater resources for possible analysis time improvements.
+    runs-on: ${{ (matrix.language == 'swift' && 'macos-latest') || 'ubuntu-latest' }}
+    permissions:
+      # required for all workflows
+      security-events: write
+
+      # required to fetch internal or private CodeQL packs
+      packages: read
+
+      # only required for workflows in private repositories
+      actions: read
+      contents: read
+
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+        - language: python
+          build-mode: none
+        - language: actions
+        # CodeQL supports the following values keywords for 'language': 'c-cpp', 'csharp', 'go', 'java-kotlin', 'javascript-typescript', 'python', 'ruby', 'swift'
+        # Use `c-cpp` to analyze code written in C, C++ or both
+        # Use 'java-kotlin' to analyze code written in Java, Kotlin or both
+        # Use 'javascript-typescript' to analyze code written in JavaScript, TypeScript or both
+        # To learn more about changing the languages that are analyzed or customizing the build mode for your analysis,
+        # see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/customizing-your-advanced-setup-for-code-scanning.
+        # If you are analyzing a compiled language, you can modify the 'build-mode' for that language to customize how
+        # your codebase is analyzed, see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/codeql-code-scanning-for-compiled-languages
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v4
+
+    # Initializes the CodeQL tools for scanning.
+    - name: Initialize CodeQL
+      uses: github/codeql-action/init@v3
+      with:
+        languages: ${{ matrix.language }}
+        build-mode: ${{ matrix.build-mode }}
+        # If you wish to specify custom queries, you can do so here or in a config file.
+        # By default, queries listed here will override any specified in a config file.
+        # Prefix the list here with "+" to use these queries and those in the config file.
+
+        # For more details on CodeQL's query packs, refer to: https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs
+        # queries: security-extended,security-and-quality
+
+    # If the analyze step fails for one of the languages you are analyzing with
+    # "We were unable to automatically build your code", modify the matrix above
+    # to set the build mode to "manual" for that language. Then modify this step
+    # to build your code.
+    # ℹ️ Command-line programs to run using the OS shell.
+    # 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
+    - if: matrix.build-mode == 'manual'
+      shell: bash
+      run: |
+        echo 'If you are using a "manual" build mode for one or more of the' \
+          'languages you are analyzing, replace this with the commands to build' \
+          'your code, for example:'
+        echo '  make bootstrap'
+        echo '  make release'
+        exit 1
+
+    - name: Perform CodeQL Analysis
+      uses: github/codeql-action/analyze@v3
+      with:
+        category: "/language:${{matrix.language}}"

pdf2zh_next-2.0.0/.github/workflows/docs.yml

@@ -0,0 +1,50 @@
+name: docs
+on:
+  push:
+    branches:
+      - main
+permissions:
+  contents: write
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - name: Process homepage
+        run: |
+          sed 's|./docs|./|g' README.md > docs/index.md
+      - name: Configure Git Credentials
+        run: |
+          git config user.name github-actions[bot]
+          git config user.email 41898282+github-actions[bot]@users.noreply.github.com
+      - name: Setup uv with Python 3.13
+        uses: astral-sh/setup-uv@f0ec1fc3b38f5e7cd731bb6ce540c5af426746bb # v6.1.0
+        with:
+          python-version: "3.13"
+          enable-cache: true
+          cache-dependency-glob: "uv.lock"
+      - run: echo "cache_id=$(date --utc '+%V')" >> $GITHUB_ENV 
+      - uses: actions/cache@v4
+        with:
+          key: mkdocs-material-${{ env.cache_id }}
+          path: .cache
+          restore-keys: |
+            mkdocs-material-
+      - run: uv sync
+      - run: uv run mkdocs gh-deploy --force
+  clear-cache:
+    needs:
+      - deploy
+    runs-on: ubuntu-latest
+    steps:
+      - name: Sleep for 30 seconds
+        run: sleep 30s
+        shell: bash
+      - name: Cloudflare Purge Cache
+        uses: jakejarvis/cloudflare-purge-action@eee6dba0236093358f25bb1581bd615dc8b3d8e3 # v0.3.0
+        env:
+          # Zone is required by both authentication methods
+          CLOUDFLARE_ZONE: ${{ secrets.PDF2ZH_NEXT_COM_CLOUDFLARE_ZONE }}
+          CLOUDFLARE_TOKEN: ${{ secrets.PDF2ZH_NEXT_COM_CLOUDFLARE_TOKEN }}