pdf2zh-next 2.0.0rc1__tar.gz

pdf2zh_next-2.0.0rc1/.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-2.0.0rc1/.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-2.0.0rc1/.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-2.0.0rc1/.github/ISSUE_TEMPLATE/config.yml

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

pdf2zh_next-2.0.0rc1/.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-2.0.0rc1/.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-2.0.0rc1/.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-2.0.0rc1/.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-2.0.0rc1/.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-2.0.0rc1/.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-2.0.0rc1/.github/workflows/exe-build.yml

@@ -0,0 +1,171 @@
+name: windows exe Release Workflow
+
+on:
+  workflow_dispatch:
+    inputs:
+      release_version:
+        description: 'Release Version (e.g., v1.0.0)'
+        required: true
+        type: string
+  # push:
+    # debug purpose
+env:
+  WIN_EXE_PYTHON_VERSION: 3.13.3
+jobs:
+  build-win64-exe:
+    runs-on: windows-latest
+    steps:
+      - name: checkout babeldoc metadata
+        uses: actions/checkout@v4
+        with:
+          repository: funstory-ai/BabelDOC
+          path: babeldoctemp1234567
+          token: ${{ secrets.GITHUB_TOKEN }}
+          sparse-checkout: babeldoc/assets/embedding_assets_metadata.py
+      - name: Cached Assets
+        id: cache-assets
+        uses: actions/cache@v4.2.2
+        with:
+          path: ~/.cache/babeldoc
+          key: test-1-babeldoc-assets-${{ hashFiles('babeldoctemp1234567/babeldoc/assets/embedding_assets_metadata.py') }}
+      - name: 检出代码
+        uses: actions/checkout@v4
+
+      - name: Setup uv with Python ${{ env.WIN_EXE_PYTHON_VERSION }}
+        uses: astral-sh/setup-uv@f94ec6bedd8674c4426838e6b50417d36b6ab231 # v5.3.1
+        with:
+          python-version: ${{ env.WIN_EXE_PYTHON_VERSION }}
+          enable-cache: true
+          cache-dependency-glob: "pyproject.toml"
+
+      - name: 执行所有任务（创建目录、下载、解压、复制文件、安装依赖）
+        shell: pwsh
+        run: |
+          Write-Host "==== 删除 babeldoctemp1234567 文件夹 ===="
+          if (Test-Path "./babeldoctemp1234567") {
+              Remove-Item -Path "./babeldoctemp1234567" -Recurse -Force
+              Write-Host "babeldoctemp1234567 文件夹已成功删除"
+          } else {
+              Write-Host "babeldoctemp1234567 文件夹不存在，无需删除"
+          }
+          Write-Host "==== 创建必要的目录 ===="
+          New-Item -Path "./build" -ItemType Directory -Force
+          New-Item -Path "./build/runtime" -ItemType Directory -Force
+          New-Item -Path "./dep_build" -ItemType Directory -Force
+
+          Write-Host "==== 复制代码到 dep_build ===="
+          Get-ChildItem -Path "./" -Exclude "dep_build", "build" | Copy-Item -Destination "./dep_build" -Recurse -Force
+
+          Write-Host "==== 下载并解压 Python ${{ env.WIN_EXE_PYTHON_VERSION }} ===="
+          Write-Host "pythonUrl: https://www.python.org/ftp/python/${{ env.WIN_EXE_PYTHON_VERSION }}/python-${{ env.WIN_EXE_PYTHON_VERSION }}-embed-amd64.zip"
+          $pythonUrl = "https://www.python.org/ftp/python/${{ env.WIN_EXE_PYTHON_VERSION }}/python-${{ env.WIN_EXE_PYTHON_VERSION }}-embed-amd64.zip"
+          $pythonZip = "./dep_build/python.zip"
+          Invoke-WebRequest -Uri $pythonUrl -OutFile $pythonZip
+          Expand-Archive -Path $pythonZip -DestinationPath "./build/runtime" -Force
+
+          Write-Host "==== 下载并解压 PyStand ===="
+          $pystandUrl = "https://github.com/skywind3000/PyStand/releases/download/1.1.4/PyStand-v1.1.4-exe.zip"
+          $pystandZip = "./dep_build/PyStand.zip"
+          Invoke-WebRequest -Uri $pystandUrl -OutFile $pystandZip
+          Expand-Archive -Path $pystandZip -DestinationPath "./dep_build/PyStand" -Force
+
+          Write-Host "==== 复制 PyStand.exe 到 build 并重命名 ===="
+          $pystandExe = "./dep_build/PyStand/PyStand-x64-CLI/PyStand.exe"
+          $destExe = "./build/pdf2zh.exe"
+          if (Test-Path $pystandExe) {
+              Copy-Item -Path $pystandExe -Destination $destExe -Force
+          } else {
+              Write-Host "错误: PyStand.exe 未找到！"
+              exit 1
+          }
+          Write-Host "==== 创建 Python venv 在 dep_build ===="
+          uv venv ./dep_build/venv
+
+          ./dep_build/venv/Scripts/activate
+
+          Write-Host "==== 在 venv 环境中安装项目依赖 ===="
+          uv pip install .
+
+          Write-Host "==== 复制 venv/Lib/site-packages 到 build/ ===="
+          Copy-Item -Path "./dep_build/venv/Lib/site-packages" -Destination "./build/site-packages" -Recurse -Force
+
+          Write-Host "==== 复制 script/_pystand_static.int 到 build/ ===="
+          $staticFile = "./script/_pystand_static.int"
+          $destStatic = "./build/_pystand_static.int"
+          if (Test-Path $staticFile) {
+              Copy-Item -Path $staticFile -Destination $destStatic -Force
+          } else {
+              Write-Host "错误: script/_pystand_static.int 未找到！"
+              exit 1
+          }
+
+          uv run --active babeldoc --generate-offline-assets ./build
+
+      - name: Upload build artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: win64-exe
+          path: ./build
+          if-no-files-found: error
+          compression-level: 9
+          include-hidden-files: true
+
+  test-win64-exe:
+    needs: 
+      - build-win64-exe
+    runs-on: windows-latest
+    steps:
+      - name: 检出代码
+        uses: actions/checkout@v4
+
+      - name: Download build artifact
+        uses: actions/download-artifact@v4
+        with:
+          name: win64-exe
+          path: ./build
+
+      - name: Test show version
+        run: |
+          ./build/pdf2zh.exe --version
+      
+      - name: Test - Translate a PDF file with plain text only
+        run: |
+          ./build/pdf2zh.exe ./test/file/translate.cli.plain.text.pdf -o ./test/file
+
+      - name: Test - Translate a PDF file figure
+        run: |
+          ./build/pdf2zh.exe ./test/file/translate.cli.text.with.figure.pdf -o ./test/file
+
+      - name: Delete offline assets and cache
+        shell: pwsh
+        run: |
+          Write-Host "==== 查找并删除离线资源包 ===="
+          $offlineAssetsPath = Get-ChildItem -Path "./build" -Filter "offline_assets_*.zip" -Recurse | Select-Object -First 1 -ExpandProperty FullName
+          if ($offlineAssetsPath) {
+            Write-Host "找到离线资源包: $offlineAssetsPath"
+            Remove-Item -Path $offlineAssetsPath -Force
+            Write-Host "已删除离线资源包"
+          } else {
+            Write-Host "未找到离线资源包"
+          }
+          
+          Write-Host "==== 删除缓存目录 ===="
+          $cachePath = "$env:USERPROFILE/.cache/babeldoc"
+          if (Test-Path $cachePath) {
+            Remove-Item -Path $cachePath -Recurse -Force
+            Write-Host "已删除缓存目录: $cachePath"
+          } else {
+            Write-Host "缓存目录不存在: $cachePath"
+          }
+
+      - name: Test - Translate without offline assets
+        run: |
+          ./build/pdf2zh.exe ./test/file/translate.cli.plain.text.pdf -o ./test/file
+          
+      - name: Upload test results
+        uses: actions/upload-artifact@v4
+        with:
+          name: test-results
+          path: ./test/file/
+
+