BabelDOC 0.1.14__tar.gz → 0.1.16__tar.gz

{babeldoc-0.1.14 → babeldoc-0.1.16}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.1.14
+Version: 0.1.16
 Summary: Yet Another Document Translator
 Project-URL: Homepage, https://github.com/funstory-ai/BabelDOC
 Project-URL: Issues, https://github.com/funstory-ai/BabelDOC/issues
@@ -26,6 +26,7 @@ Requires-Dist: peewee>=3.17.8
 Requires-Dist: pydantic>=2.10.6
 Requires-Dist: pymupdf>=1.25.1
 Requires-Dist: rich>=13.9.4
+Requires-Dist: tenacity>=9.0.0
 Requires-Dist: toml>=0.10.2
 Requires-Dist: tqdm>=4.67.1
 Requires-Dist: xsdata[cli,lxml,soap]>=24.12

babeldoc-0.1.16/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.1.16"

{babeldoc-0.1.14 → babeldoc-0.1.16}/babeldoc/const.py

@@ -2,7 +2,7 @@ import shutil
 import subprocess
 from pathlib import Path
 
-__version__ = "0.1.14"
+__version__ = "0.1.16"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

{babeldoc-0.1.14 → babeldoc-0.1.16}/babeldoc/document_il/backend/pdf_creater.py

@@ -38,6 +38,44 @@ def _subset_fonts_process(pdf_path, output_path):
         os._exit(1)
 
 
+def _save_pdf_clean_process(
+    pdf_path,
+    output_path,
+    garbage=1,
+    deflate=True,
+    clean=True,
+    deflate_fonts=True,
+    linear=False,
+):
+    """Function to run in subprocess for saving PDF with clean=True which can be time-consuming.
+
+    Args:
+        pdf_path: Path to the PDF file to save
+        output_path: Path where to save the result
+        garbage: Garbage collection level (0, 1, 2, 3, 4)
+        deflate: Whether to deflate the PDF
+        clean: Whether to clean the PDF
+        deflate_fonts: Whether to deflate fonts
+        linear: Whether to linearize the PDF
+    """
+    try:
+        pdf = pymupdf.open(pdf_path)
+        pdf.save(
+            output_path,
+            garbage=garbage,
+            deflate=deflate,
+            clean=clean,
+            deflate_fonts=deflate_fonts,
+            linear=linear,
+        )
+        # 返回0表示成功
+        os._exit(0)
+    except Exception as e:
+        logger.error(f"Error in save PDF with clean=True subprocess: {e}")
+        # 返回1表示失败
+        os._exit(1)
+
+
 class PDFCreater:
     stage_name = "Generate drawing instructions"
 
@@ -425,6 +463,11 @@ class PDFCreater:
                     if process.is_alive():
                         logger.warning("Subprocess did not terminate, killing it")
                         process.kill()
+                        process.terminate()
+                        process.kill()
+                        process.terminate()
+                        process.kill()
+                        process.terminate()
                 except Exception as e:
                     logger.error(f"Error terminating font subsetting process: {e}")
 
@@ -450,6 +493,148 @@ class PDFCreater:
             )
             return original_pdf
 
+    def save_pdf_with_timeout(
+        self,
+        pdf: pymupdf.Document,
+        output_path: str,
+        translation_config: TranslationConfig,
+        garbage: int = 1,
+        deflate: bool = True,
+        clean: bool = True,
+        deflate_fonts: bool = True,
+        linear: bool = False,
+        timeout: int = 120,
+    ) -> bool:
+        """Save a PDF document with a timeout for the clean=True operation.
+
+        Args:
+            pdf: The PDF document object
+            output_path: Path where to save the PDF
+            translation_config: Translation configuration
+            garbage: Garbage collection level (0, 1, 2, 3, 4)
+            deflate: Whether to deflate the PDF
+            clean: Whether to clean the PDF
+            deflate_fonts: Whether to deflate fonts
+            linear: Whether to linearize the PDF
+            timeout: Timeout in seconds (default: 2 minutes)
+
+        Returns:
+            True if saved with clean=True successfully, False if fallback to clean=False was used
+        """
+        # Create temporary file paths
+        temp_input = str(
+            translation_config.get_working_file_path(
+                f"temp_save_input_{int(time.time())}.pdf"
+            )
+        )
+        temp_output = str(
+            translation_config.get_working_file_path(
+                f"temp_save_output_{int(time.time())}.pdf"
+            )
+        )
+
+        # Save PDF to temporary file first
+        pdf.save(temp_input)
+
+        # Try to save with clean=True in a subprocess
+        process = Process(
+            target=_save_pdf_clean_process,
+            args=(
+                temp_input,
+                temp_output,
+                garbage,
+                deflate,
+                clean,
+                deflate_fonts,
+                linear,
+            ),
+        )
+        process.start()
+
+        # Wait for subprocess with timeout
+        start_time = time.time()
+
+        while process.is_alive():
+            if time.time() - start_time > timeout:
+                logger.warning(
+                    f"PDF save with clean=True timeout after {timeout} seconds, terminating subprocess"
+                )
+                process.terminate()
+                try:
+                    process.join(5)  # Give it 5 seconds to clean up
+                    if process.is_alive():
+                        logger.warning("Subprocess did not terminate, killing it")
+                        process.kill()
+                        process.terminate()
+                        process.kill()
+                        process.terminate()
+                        process.kill()
+                        process.terminate()
+                except Exception as e:
+                    logger.error(f"Error terminating PDF save process: {e}")
+
+                # Fallback to save without clean parameter
+                logger.info("Falling back to save without clean=True")
+                try:
+                    pdf.save(
+                        output_path,
+                        garbage=garbage,
+                        deflate=deflate,
+                        clean=False,
+                        deflate_fonts=deflate_fonts,
+                        linear=linear,
+                    )
+                    return False
+                except Exception as e:
+                    logger.error(f"Error in fallback save: {e}")
+                    # Last resort: basic save
+                    pdf.save(output_path)
+                    return False
+
+            time.sleep(0.5)  # Check every half second
+
+        # Process completed, check exit code
+        exit_code = process.exitcode
+        success = exit_code == 0
+
+        # Check if save was successful
+        if (
+            success
+            and Path(temp_output).exists()
+            and Path(temp_output).stat().st_size > 0
+        ):
+            logger.info("PDF save with clean=True completed successfully")
+            # Copy the successfully created file to the target path
+            try:
+                import shutil
+
+                shutil.copy2(temp_output, output_path)
+                return True
+            except Exception as e:
+                logger.error(f"Error copying saved PDF: {e}")
+                pdf.save(output_path)  # Fallback to direct save
+                return False
+        else:
+            logger.warning(
+                f"PDF save with clean=True failed with exit code {exit_code} or produced empty file"
+            )
+            # Fallback to save without clean parameter
+            try:
+                pdf.save(
+                    output_path,
+                    garbage=garbage,
+                    deflate=deflate,
+                    clean=False,
+                    deflate_fonts=deflate_fonts,
+                    linear=linear,
+                )
+            except Exception as e:
+                logger.error(f"Error in fallback save: {e}")
+                # Last resort: basic save
+                pdf.save(output_path)
+
+            return False
+
     def write(self, translation_config: TranslationConfig) -> TranslateResult:
         basename = Path(translation_config.input_file).stem
         debug_suffix = ".debug" if translation_config.debug else ""
@@ -579,8 +764,10 @@ class PDFCreater:
                         pretty=True,
                     )
                 translation_config.raise_if_cancelled()
-                pdf.save(
+                self.save_pdf_with_timeout(
+                    pdf,
                     mono_out_path,
+                    translation_config,
                     garbage=1,
                     deflate=True,
                     clean=not translation_config.skip_clean,
@@ -627,8 +814,10 @@ class PDFCreater:
                             exc_info=True,
                         )
 
-                dual.save(
+                self.save_pdf_with_timeout(
+                    dual,
                     dual_out_path,
+                    translation_config,
                     garbage=1,
                     deflate=True,
                     clean=not translation_config.skip_clean,

{babeldoc-0.1.14 → babeldoc-0.1.16}/babeldoc/docvision/rpc_doclayout.py

@@ -5,6 +5,10 @@ import cv2
 import httpx
 import msgpack
 import numpy as np
+from tenacity import retry
+from tenacity import retry_if_exception_type
+from tenacity import stop_after_attempt
+from tenacity import wait_exponential
 
 from babeldoc.docvision.doclayout import DocLayoutModel
 from babeldoc.docvision.doclayout import YoloBox
@@ -34,6 +38,17 @@ def encode_image(image) -> bytes:
     return encoded
 
 
+@retry(
+    stop=stop_after_attempt(3),  # 最多重试3次
+    wait=wait_exponential(
+        multiplier=1, min=1, max=10
+    ),  # 指数退避策略，初始1秒，最大10秒
+    retry=retry_if_exception_type((httpx.HTTPError, Exception)),  # 针对哪些异常重试
+    before_sleep=lambda retry_state: logger.warning(
+        f"Request failed, retrying in {retry_state.next_action.sleep} seconds... "
+        f"(Attempt {retry_state.attempt_number}/3)"
+    ),
+)
 def predict_layout(
     image,
     host: str = "http://localhost:8000",
@@ -50,53 +65,49 @@ def predict_layout(
     Returns:
         List of predictions containing bounding boxes and classes
     """
-    try:
-        # Prepare request data
-        if not isinstance(image, list):
-            image = [image]
-        image_data = [encode_image(image) for image in image]
-        data = {
-            "image": image_data,
-            "imgsz": imgsz,
-        }
-
-        # Pack data using msgpack
-        packed_data = msgpack.packb(data, use_bin_type=True)
-        logger.debug(f"Packed data size: {len(packed_data)} bytes")
-
-        # Send request
-        logger.debug(f"Sending request to {host}/inference")
-        response = httpx.post(
-            f"{host}/inference",
-            data=packed_data,
-            headers={
-                "Content-Type": "application/msgpack",
-                "Accept": "application/msgpack",
-            },
-            timeout=300,
-            follow_redirects=True,
+    # Prepare request data
+    if not isinstance(image, list):
+        image = [image]
+    image_data = [encode_image(image) for image in image]
+    data = {
+        "image": image_data,
+        "imgsz": imgsz,
+    }
+
+    # Pack data using msgpack
+    packed_data = msgpack.packb(data, use_bin_type=True)
+    logger.debug(f"Packed data size: {len(packed_data)} bytes")
+
+    # Send request
+    logger.debug(f"Sending request to {host}/inference")
+    response = httpx.post(
+        f"{host}/inference",
+        data=packed_data,
+        headers={
+            "Content-Type": "application/msgpack",
+            "Accept": "application/msgpack",
+        },
+        timeout=300,
+        follow_redirects=True,
+    )
+
+    logger.debug(f"Response status: {response.status_code}")
+    logger.debug(f"Response headers: {response.headers}")
+
+    if response.status_code == 200:
+        try:
+            result = msgpack.unpackb(response.content, raw=False)
+            return result
+        except Exception as e:
+            logger.exception(f"Failed to unpack response: {e!s}")
+            raise
+    else:
+        logger.error(f"Request failed with status {response.status_code}")
+        logger.error(f"Response content: {response.content}")
+        raise Exception(
+            f"Request failed with status {response.status_code}: {response.text}",
         )
 
-        logger.debug(f"Response status: {response.status_code}")
-        logger.debug(f"Response headers: {response.headers}")
-
-        if response.status_code == 200:
-            try:
-                result = msgpack.unpackb(response.content, raw=False)
-                return result
-            except Exception as e:
-                logger.exception(f"Failed to unpack response: {e!s}")
-                raise
-        else:
-            logger.error(f"Request failed with status {response.status_code}")
-            logger.error(f"Response content: {response.content}")
-            raise Exception(
-                f"Request failed with status {response.status_code}: {response.text}",
-            )
-    except Exception as e:
-        logger.exception(f"Unexpected error: {e!s}")
-        raise
-
 
 class RpcDocLayoutModel(DocLayoutModel):
     """DocLayoutModel implementation that uses RPC service."""

{babeldoc-0.1.14 → babeldoc-0.1.16}/babeldoc/main.py

@@ -23,7 +23,7 @@ from babeldoc.docvision.rpc_doclayout import RpcDocLayoutModel
 from babeldoc.translation_config import TranslationConfig
 
 logger = logging.getLogger(__name__)
-__version__ = "0.1.14"
+__version__ = "0.1.16"
 
 
 def create_parser():

{babeldoc-0.1.14 → babeldoc-0.1.16}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.1.14"
+version = "0.1.16"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -30,6 +30,7 @@ dependencies = [
     "xsdata[cli,lxml,soap]>=24.12",
     "msgpack>=1.1.0",
     "pydantic>=2.10.6",
+    "tenacity>=9.0.0",
 ]
 
 [project.urls]
@@ -131,7 +132,7 @@ pythonpath = [".", "src"]
 testpaths = ["tests"]
 
 [bumpver]
-current_version = "0.1.14"
+current_version = "0.1.16"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]
@@ -147,4 +148,4 @@ version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 ]
 "babeldoc/const.py" = [
     '__version__ = "{version}"'
-]
+]

{babeldoc-0.1.14 → babeldoc-0.1.16}/uv.lock

@@ -48,7 +48,7 @@ wheels = [
 
 [[package]]
 name = "babeldoc"
-version = "0.1.14"
+version = "0.1.16"
 source = { editable = "." }
 dependencies = [
     { name = "bitstring" },
@@ -67,6 +67,7 @@ dependencies = [
     { name = "pydantic" },
     { name = "pymupdf" },
     { name = "rich" },
+    { name = "tenacity" },
     { name = "toml" },
     { name = "tqdm" },
     { name = "xsdata", extra = ["cli", "lxml", "soap"] },
@@ -105,6 +106,7 @@ requires-dist = [
     { name = "pydantic", specifier = ">=2.10.6" },
     { name = "pymupdf", specifier = ">=1.25.1" },
     { name = "rich", specifier = ">=13.9.4" },
+    { name = "tenacity", specifier = ">=9.0.0" },
     { name = "toml", specifier = ">=0.10.2" },
     { name = "tqdm", specifier = ">=4.67.1" },
     { name = "xsdata", extras = ["cli", "lxml", "soap"], specifier = ">=24.12" },
@@ -1753,6 +1755,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/99/ff/c87e0622b1dadea79d2fb0b25ade9ed98954c9033722eb707053d310d4f3/sympy-1.13.3-py3-none-any.whl", hash = "sha256:54612cf55a62755ee71824ce692986f23c88ffa77207b30c1368eda4a7060f73", size = 6189483 },
 ]
 
+[[package]]
+name = "tenacity"
+version = "9.0.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/cd/94/91fccdb4b8110642462e653d5dcb27e7b674742ad68efd146367da7bdb10/tenacity-9.0.0.tar.gz", hash = "sha256:807f37ca97d62aa361264d497b0e31e92b8027044942bfa756160d908320d73b", size = 47421 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/b6/cb/b86984bed139586d01532a587464b5805f12e397594f19f931c4c2fbfa61/tenacity-9.0.0-py3-none-any.whl", hash = "sha256:93de0c98785b27fcf659856aa9f54bfbd399e29969b0621bc7f762bd441b4539", size = 28169 },
+]
+
 [[package]]
 name = "toml"
 version = "0.10.2"

babeldoc-0.1.14/babeldoc/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.1.14"