BabelDOC 0.5.23__tar.gz → 0.5.24__tar.gz

{babeldoc-0.5.23 → babeldoc-0.5.24}/.github/workflows/codeql.yml

@@ -55,7 +55,7 @@ jobs:
         # 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@v5
+      uses: actions/checkout@v6
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL

{babeldoc-0.5.23 → babeldoc-0.5.24}/.github/workflows/docs.yml

@@ -9,7 +9,7 @@ jobs:
   deploy:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
         with:
           fetch-depth: 0
       - name: Configure Git Credentials
@@ -24,7 +24,7 @@ jobs:
           cache-dependency-glob: "uv.lock"
           activate-environment: true
       - run: echo "cache_id=$(date --utc '+%V')" >> $GITHUB_ENV 
-      - uses: actions/cache@v4
+      - uses: actions/cache@v5
         with:
           key: mkdocs-material-${{ env.cache_id }}
           path: .cache

{babeldoc-0.5.23 → babeldoc-0.5.24}/.github/workflows/labeler.yml

@@ -22,10 +22,10 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Check out the repository
-        uses: actions/checkout@v5
+        uses: actions/checkout@v6
 
       - name: Run Labeler
-        uses: crazy-max/ghaction-github-labeler@24d110aa46a59976b8a7f35518cb7f14f434c916 # v5.3.0
+        uses: crazy-max/ghaction-github-labeler@548a7c3603594ec17c819e1239f281a3b801ab4d # v6.0.0
         with:
           skip-delete: true
           dry-run: ${{ github.event_name == 'pull_request' }}

{babeldoc-0.5.23 → babeldoc-0.5.24}/.github/workflows/lint.yml

@@ -10,7 +10,7 @@ jobs:
       fail-fast: false
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
       - name: Ruff
         uses: astral-sh/ruff-action@v3
       - name: AutoCorrect

{babeldoc-0.5.23 → babeldoc-0.5.24}/.github/workflows/pr-lint.yml

@@ -9,7 +9,7 @@ jobs:
     name: runner / ruff
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
       
       - name: Install Python
         uses: actions/setup-python@v6
@@ -20,7 +20,7 @@ jobs:
         run: pip install ruff
         
       - name: Install reviewdog
-        uses: reviewdog/action-setup@d8edfce3dd5e1ec6978745e801f9c50b5ef80252 # v1.4.0
+        uses: reviewdog/action-setup@d8a7baabd7f3e8544ee4dbde3ee41d0011c3a93f # v1.5.0
         with:
           reviewdog_version: latest
           
@@ -34,7 +34,7 @@ jobs:
     name: runner / autocorrect
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
       - name: AutoCorrect
         uses: huacnlee/autocorrect-action@bf91ab3904c2908dd8e71312a8a83ed1eb632997 # v2.13.3
       - name: Report ReviewDog

{babeldoc-0.5.23 → babeldoc-0.5.24}/.github/workflows/publish-to-pypi.yml

@@ -28,7 +28,7 @@ jobs:
     outputs:
       is_release: ${{ steps.check-version.outputs.tag }}
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
         with:
           persist-credentials: true
           fetch-depth: 2
@@ -69,7 +69,7 @@ jobs:
         run: "uv build"
 
       - name: Store the distribution packages
-        uses: actions/upload-artifact@v4.6.2
+        uses: actions/upload-artifact@v7.0.0
         with:
           name: python-package-distributions
           path: dist/
@@ -139,7 +139,7 @@ jobs:
       contents: write
       pull-requests: write
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
         with:
           persist-credentials: true
           fetch-depth: 2

{babeldoc-0.5.23 → babeldoc-0.5.24}/.github/workflows/test.yml

@@ -18,12 +18,12 @@ jobs:
         python-version: ["3.10", "3.11", "3.12", "3.13"]
 
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
         with:
           persist-credentials: false
       - name: Cached Assets
         id: cache-assets
-        uses: actions/cache@v4.2.0
+        uses: actions/cache@v5
         with:
           path: ~/.cache/babeldoc
           key: babeldoc-assets-${{ hashFiles('babeldoc/assets/embedding_assets_metadata.py') }}

{babeldoc-0.5.23 → babeldoc-0.5.24}/.gitignore

@@ -47,3 +47,4 @@ CLAUDE.md
 babeldoc/format/playground
 temp.jpg
 AGENTS.md
+.serena

{babeldoc-0.5.23 → babeldoc-0.5.24}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.5.23
+Version: 0.5.24
 Summary: Yet Another Document Translator
 Project-URL: Homepage, https://github.com/funstory-ai/BabelDOC
 Project-URL: Issues, https://github.com/funstory-ai/BabelDOC/issues

babeldoc-0.5.24/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.5.24"

{babeldoc-0.5.23 → babeldoc-0.5.24}/babeldoc/const.py

@@ -6,7 +6,7 @@ import subprocess
 import threading
 from pathlib import Path
 
-__version__ = "0.5.23"
+__version__ = "0.5.24"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

{babeldoc-0.5.23 → babeldoc-0.5.24}/babeldoc/docvision/doclayout.py

@@ -37,6 +37,8 @@ os_name = platform.system()
 
 
 class OnnxModel(DocLayoutModel):
+    _FIXED_IMGSZ = 1024  # fixed input size for static-shape CoreML
+
     def __init__(self, model_path: str):
         self.model_path = model_path
 
@@ -47,18 +49,52 @@ class OnnxModel(DocLayoutModel):
         providers = []
 
         available_providers = onnxruntime.get_available_providers()
-        for provider in available_providers:
-            # disable dml|cuda|
-            # directml/cuda may encounter problems under special circumstances
-            if re.match(r"cpu", provider, re.IGNORECASE):
-                logger.info(f"Available Provider: {provider}")
-                providers.append(provider)
+        use_coreml = os_name == "Darwin" and any(
+            re.match(r"coreml", p, re.IGNORECASE) for p in available_providers
+        )
+        if use_coreml:
+            # Fix input shapes to [1, 3, 1024, 1024] so CoreML can take over
+            # 96%+ of the graph nodes (658/681) instead of just 3/823.
+            model = self._make_static_model(model, self._FIXED_IMGSZ)
+            providers = [
+                "CoreMLExecutionProvider",
+                "CPUExecutionProvider",
+            ]
+            logger.info(
+                "Using CoreMLExecutionProvider with static input "
+                f"[1, 3, {self._FIXED_IMGSZ}, {self._FIXED_IMGSZ}]"
+            )
+        else:
+            for provider in available_providers:
+                # disable dml|cuda|
+                # directml/cuda may encounter problems under special circumstances
+                if re.match(r"cpu", provider, re.IGNORECASE):
+                    logger.info(f"Available Provider: {provider}")
+                    providers.append(provider)
         self.model = onnxruntime.InferenceSession(
             model.SerializeToString(),
             providers=providers,
         )
         self.lock = threading.Lock()
 
+    @staticmethod
+    def _make_static_model(model, imgsz):
+        """Rewrite dynamic input dims to fixed [1, 3, imgsz, imgsz] and run
+        shape inference so all intermediate shapes become static."""
+        from onnx import shape_inference
+
+        for inp in model.graph.input:
+            if inp.name == "images":
+                dim = inp.type.tensor_type.shape.dim
+                for i, val in enumerate([1, 3, imgsz, imgsz]):
+                    dim[i].ClearField("dim_param")
+                    dim[i].dim_value = val
+        try:
+            model = shape_inference.infer_shapes(model)
+        except Exception:
+            pass  # best-effort; CoreML still benefits from fixed input
+        return model
+
     @staticmethod
     def from_pretrained():
         pth = get_doclayout_onnx_model_path()
@@ -97,9 +133,9 @@ class OnnxModel(DocLayoutModel):
             interpolation=cv2.INTER_LINEAR,
         )
 
-        # Calculate padding size and align to stride multiple
-        pad_w = (new_w - resized_w) % self.stride
-        pad_h = (new_h - resized_h) % self.stride
+        # Pad to full target size (enables static-shape CoreML acceleration)
+        pad_w = new_w - resized_w
+        pad_h = new_h - resized_h
         top, bottom = pad_h // 2, pad_h - pad_h // 2
         left, right = pad_w // 2, pad_w - pad_w // 2
 

{babeldoc-0.5.23 → babeldoc-0.5.24}/babeldoc/format/pdf/document_il/backend/pdf_creater.py

@@ -1402,7 +1402,7 @@ class PDFCreater:
                 auto_extracted_glossary_path = self.translation_config.get_output_file_path(
                     f"{basename}{debug_suffix}.{translation_config.lang_out}.glossary.csv"
                 )
-                with auto_extracted_glossary_path.open("w", encoding="utf-8") as f:
+                with auto_extracted_glossary_path.open("w", encoding="utf-8-sig") as f:
                     logger.info(
                         f"save auto extracted glossary to {auto_extracted_glossary_path}"
                     )

{babeldoc-0.5.23 → babeldoc-0.5.24}/babeldoc/format/pdf/document_il/midend/automatic_term_extractor.py

@@ -413,7 +413,7 @@ class AutomaticTermExtractor:
                 "auto_extractor_glossary.csv"
             )
             logger.debug(f"save auto extracted glossary to {path}")
-            with Path(path).open("w", encoding="utf-8") as f:
+            with Path(path).open("w", encoding="utf-8-sig") as f:
                 auto_extracted_glossary = self.shared_context.auto_extracted_glossary
                 if auto_extracted_glossary:
                     f.write(auto_extracted_glossary.to_csv())

{babeldoc-0.5.23 → babeldoc-0.5.24}/babeldoc/format/pdf/result_merger.py

@@ -135,7 +135,7 @@ class ResultMerger:
             auto_extracted_glossary_path = self.config.get_output_file_path(
                 f"{basename}{debug_suffix}.{self.config.lang_out}.glossary.csv"
             )
-            with auto_extracted_glossary_path.open("w", encoding="utf-8") as f:
+            with auto_extracted_glossary_path.open("w", encoding="utf-8-sig") as f:
                 logger.info(
                     f"save auto extracted glossary to {auto_extracted_glossary_path}"
                 )

{babeldoc-0.5.23 → babeldoc-0.5.24}/babeldoc/main.py

@@ -26,7 +26,7 @@ from babeldoc.translator.translator import OpenAITranslator
 from babeldoc.translator.translator import set_translate_rate_limiter
 
 logger = logging.getLogger(__name__)
-__version__ = "0.5.23"
+__version__ = "0.5.24"
 
 
 def create_parser():

{babeldoc-0.5.23 → babeldoc-0.5.24}/docs/CONTRIBUTING.md

@@ -48,6 +48,9 @@ Please pay special attention to:
 >
 > In addition, we do not accept PRs involving the following changes:
 > 1. PRs that modify prompts.
+> 2. Adding GUI or other features directly targeting end users to this project. (Exceptions granted by maintainers in issues are excluded.)
+> 3. PRs that do not comply with this specification.
+> 4. Other PRs that maintainers deem inappropriate.
 >
 > **This project cannot accept all PRs. We recommend that you discuss with the maintainers via [Issue](https://github.com/funstory-ai/BabelDOC/issues) before submitting a PR.**
 

{babeldoc-0.5.23 → babeldoc-0.5.24}/mkdocs.yml

@@ -30,6 +30,7 @@ site_description: >-
 repo_name: funstory-ai/BabelDOC
 repo_url: https://github.com/funstory-ai/BabelDOC
 edit_uri: edit/main/docs/
+docs_dir: docs
 
 # Copyright
 copyright: Copyright © 2025 funstory.ai

{babeldoc-0.5.23 → babeldoc-0.5.24}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.5.23"
+version = "0.5.24"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -162,7 +162,7 @@ pythonpath = [".", "src"]
 testpaths = ["tests"]
 
 [bumpver]
-current_version = "0.5.23"
+current_version = "0.5.24"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]

babeldoc-0.5.23/.cursorignore

@@ -1,2 +0,0 @@
-# Project notes and templates
-xnotes/

babeldoc-0.5.23/babeldoc/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.5.23"