feat (docker): onnx model and font embedded (Byaidu#276)

* 将onnx模型和字体打包进docker镜像

* 调整docker构建顺序，先下模型后装包，并将预热更改为dockerfile RUN指令

* 移除无用import

* 正确处理authorized为None

* translate函数中更好的处理envs和prompt不存在的情况

* 移除docker镜像中无用文件

---------

Co-authored-by: Byaidu <[email protected]>

Author: awwaawwa

.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

.gitignore

@@ -165,6 +165,7 @@ cython_debug/
 #  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/
+.idea/
 .vscode
 .DS_Store
+uv.lock

Dockerfile

@@ -1,15 +1,19 @@
-FROM python:3.12
+FROM ghcr.io/astral-sh/uv:python3.12-bookworm-slim
 
 WORKDIR /app
 
-COPY . .
 
 EXPOSE 7860
 
 ENV PYTHONUNBUFFERED=1
+ADD "https://github.com/satbyy/go-noto-universal/releases/download/v7.0/GoNotoKurrent-Regular.ttf" /app
+RUN apt-get update && \
+     apt-get install --no-install-recommends -y libgl1 && \
+     rm -rf /var/lib/apt/lists/* && uv pip install --system --no-cache huggingface-hub && \
+     python3 -c "from huggingface_hub import hf_hub_download; hf_hub_download('wybxc/DocLayout-YOLO-DocStructBench-onnx','doclayout_yolo_docstructbench_imgsz1024.onnx');"
 
-RUN apt-get update && apt-get install -y libgl1
+COPY . .
 
-RUN pip install .
+RUN uv pip install --system --no-cache .
 
 CMD ["pdf2zh", "-i"]

pdf2zh/gui.py

@@ -445,7 +445,7 @@ def on_select_filetype(file_type):
 def readuserandpasswd(file_path):
     tuple_list = []
     content = ""
-    if file_path is None or len(file_path) == 0:
+    if file_path is None:
         return tuple_list, content
     if len(file_path) == 2:
         try:

pdf2zh/high_level.py

@@ -187,7 +187,10 @@ def translate_stream(
         font_list.append((resfont, None))
     elif lang_out.lower() in noto_list:  # noto
         resfont = "noto"
-        ttf_path = os.path.join(tempfile.gettempdir(), "GoNotoKurrent-Regular.ttf")
+        # docker
+        ttf_path = '/app/GoNotoKurrent-Regular.ttf'
+        if not os.path.exists(ttf_path):
+            ttf_path = os.path.join(tempfile.gettempdir(), "GoNotoKurrent-Regular.ttf")
         if not os.path.exists(ttf_path):
             print("Downloading Noto font...")
             urllib.request.urlretrieve(
@@ -294,7 +297,7 @@ def translate(
         doc_raw = open(file, "rb")
         s_raw = doc_raw.read()
         s_mono, s_dual = translate_stream(
-            s_raw, envs=kwarg.get("envs"), prompt=kwarg["prompt"], **locals()
+            s_raw, envs=kwarg.get("envs", {}), prompt=kwarg.get("prompt", []), **locals()
         )
         file_mono = Path(output) / f"{filename}-mono.pdf"
         file_dual = Path(output) / f"{filename}-dual.pdf"