BabelDOC 0.1.18__tar.gz → 0.1.19__tar.gz

{babeldoc-0.1.18 → babeldoc-0.1.19}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.1.18
+Version: 0.1.19
 Summary: Yet Another Document Translator
 Project-URL: Homepage, https://github.com/funstory-ai/BabelDOC
 Project-URL: Issues, https://github.com/funstory-ai/BabelDOC/issues
@@ -134,7 +134,10 @@ uv run babeldoc --bing --files example.pdf --files example2.pdf
 
 > [!TIP]
 > Currently, this project mainly focuses on English-to-Chinese translation, and other scenarios have not been tested yet.
+> 
 > (2025.3.1 update): Basic English target language support has been added, primarily to minimize line breaks within words([0-9A-Za-z]+).
+> 
+> [HELP WANTED: Collecting word regular expressions for more languages](https://github.com/funstory-ai/BabelDOC/issues/129)
 
 ### PDF Processing Options
 

{babeldoc-0.1.18 → babeldoc-0.1.19}/README.md

@@ -100,7 +100,10 @@ uv run babeldoc --bing --files example.pdf --files example2.pdf
 
 > [!TIP]
 > Currently, this project mainly focuses on English-to-Chinese translation, and other scenarios have not been tested yet.
+> 
 > (2025.3.1 update): Basic English target language support has been added, primarily to minimize line breaks within words([0-9A-Za-z]+).
+> 
+> [HELP WANTED: Collecting word regular expressions for more languages](https://github.com/funstory-ai/BabelDOC/issues/129)
 
 ### PDF Processing Options
 

babeldoc-0.1.19/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.1.19"

{babeldoc-0.1.18 → babeldoc-0.1.19}/babeldoc/const.py

@@ -2,7 +2,7 @@ import shutil
 import subprocess
 from pathlib import Path
 
-__version__ = "0.1.18"
+__version__ = "0.1.19"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

{babeldoc-0.1.18 → babeldoc-0.1.19}/babeldoc/document_il/backend/pdf_creater.py

@@ -413,11 +413,11 @@ class PDFCreater:
 
         # 使用子进程进行字体子集化
         if not translation_config.skip_clean:
-            pdf = self.subset_fonts_in_subprocess(pdf, translation_config)
+            pdf = self.subset_fonts_in_subprocess(pdf, translation_config, tag="debug")
         return pdf
 
     def subset_fonts_in_subprocess(
-        self, pdf: pymupdf.Document, translation_config: TranslationConfig
+        self, pdf: pymupdf.Document, translation_config: TranslationConfig, tag: str
     ) -> pymupdf.Document:
         """Run font subsetting in a subprocess with timeout.
 
@@ -431,14 +431,10 @@ class PDFCreater:
         original_pdf = pdf
         # Create temporary file paths
         temp_input = str(
-            translation_config.get_working_file_path(
-                f"temp_subset_input_{int(time.time())}.pdf"
-            )
+            translation_config.get_working_file_path(f"temp_subset_input_{tag}.pdf")
         )
         temp_output = str(
-            translation_config.get_working_file_path(
-                f"temp_subset_output_{int(time.time())}.pdf"
-            )
+            translation_config.get_working_file_path(f"temp_subset_output_{tag}.pdf")
         )
 
         # Save PDF to temporary file without subsetting
@@ -504,6 +500,7 @@ class PDFCreater:
         deflate_fonts: bool = True,
         linear: bool = False,
         timeout: int = 120,
+        tag: str = "",
     ) -> bool:
         """Save a PDF document with a timeout for the clean=True operation.
 
@@ -523,14 +520,10 @@ class PDFCreater:
         """
         # Create temporary file paths
         temp_input = str(
-            translation_config.get_working_file_path(
-                f"temp_save_input_{int(time.time())}.pdf"
-            )
+            translation_config.get_working_file_path(f"temp_save_input_{tag}.pdf")
         )
         temp_output = str(
-            translation_config.get_working_file_path(
-                f"temp_save_output_{int(time.time())}.pdf"
-            )
+            translation_config.get_working_file_path(f"temp_save_output_{tag}.pdf")
         )
 
         # Save PDF to temporary file first
@@ -614,6 +607,9 @@ class PDFCreater:
                 logger.error(f"Error copying saved PDF: {e}")
                 pdf.save(output_path)  # Fallback to direct save
                 return False
+            finally:
+                Path(temp_input).unlink()
+                Path(temp_output).unlink()
         else:
             logger.warning(
                 f"PDF save with clean=True failed with exit code {exit_code} or produced empty file"
@@ -748,7 +744,9 @@ class PDFCreater:
             1,
         ) as pbar:
             if not translation_config.skip_clean:
-                pdf = self.subset_fonts_in_subprocess(pdf, translation_config)
+                pdf = self.subset_fonts_in_subprocess(
+                    pdf, translation_config, tag="mono"
+                )
 
             pbar.advance()
         with self.translation_config.progress_monitor.stage_start(
@@ -773,6 +771,7 @@ class PDFCreater:
                     clean=not translation_config.skip_clean,
                     deflate_fonts=True,
                     linear=False,
+                    tag="mono",
                 )
             pbar.advance()
             dual_out_path = None
@@ -823,6 +822,7 @@ class PDFCreater:
                     clean=not translation_config.skip_clean,
                     deflate_fonts=True,
                     linear=False,
+                    tag="dual",
                 )
                 if translation_config.debug:
                     translation_config.raise_if_cancelled()

{babeldoc-0.1.18 → babeldoc-0.1.19}/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__ = "0.1.18"
+__version__ = "0.1.19"
 
 
 def create_parser():

{babeldoc-0.1.18 → babeldoc-0.1.19}/babeldoc/pdfinterp.py

@@ -249,7 +249,13 @@ class PDFPageInterpreterEx(PDFPageInterpreter):
         subtype = xobj.get("Subtype")
         if subtype is LITERAL_FORM and "BBox" in xobj:
             interpreter = self.dup()
-            bbox = cast(Rect, list_value(xobj["BBox"]))
+
+            # In extremely rare cases, a none might be mixed in the bbox, for example
+            # /BBox [ 0 3.052 null 274.9 157.3 ]
+            bbox = list(
+                filter(lambda x: x is not None, cast(Rect, list_value(xobj["BBox"])))
+            )
+
             matrix = cast(Matrix, list_value(xobj.get("Matrix", MATRIX_IDENTITY)))
             # According to PDF reference 1.7 section 4.9.1, XObjects in
             # earlier PDFs (prior to v1.2) use the page's Resources entry

{babeldoc-0.1.18 → babeldoc-0.1.19}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.1.18"
+version = "0.1.19"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -132,7 +132,7 @@ pythonpath = [".", "src"]
 testpaths = ["tests"]
 
 [bumpver]
-current_version = "0.1.18"
+current_version = "0.1.19"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]

{babeldoc-0.1.18 → babeldoc-0.1.19}/uv.lock

@@ -48,7 +48,7 @@ wheels = [
 
 [[package]]
 name = "babeldoc"
-version = "0.1.18"
+version = "0.1.19"
 source = { editable = "." }
 dependencies = [
     { name = "bitstring" },

babeldoc-0.1.18/babeldoc/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.1.18"