BabelDOC 0.3.66__tar.gz → 0.3.68__tar.gz

{babeldoc-0.3.66 → babeldoc-0.3.68}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.3.66
+Version: 0.3.68
 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-0.3.68/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.3.68"

{babeldoc-0.3.66 → babeldoc-0.3.68}/babeldoc/const.py

@@ -3,7 +3,7 @@ import shutil
 import subprocess
 from pathlib import Path
 
-__version__ = "0.3.66"
+__version__ = "0.3.68"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

{babeldoc-0.3.66 → babeldoc-0.3.68}/babeldoc/document_il/midend/detect_scanned_file.py

@@ -71,7 +71,7 @@ class DetectScannedFile:
                 contents_list = page.get_contents()
                 for index in contents_list:
                     contents = doc.xref_stream(index)
-                    if regex.search(rb"/Artifact(\s*\<\<|\s+BDC)", contents):
+                    if regex.search(rb"/Artifact(\s*\<\<\s*/MCID\s+|\s+BDC)", contents):
                         hit_list[page.number] += 1
                     if regex.search(rb"\s3\s+Tr\s", contents):
                         hit_list[page.number] += 1
@@ -86,6 +86,8 @@ class DetectScannedFile:
             for page in docs.page
             if self.translation_config.should_translate_page(page.page_number + 1)
         ]
+        if not pages_to_translate:
+            return
         mupdf = pymupdf.open(self.translation_config.get_working_file_path("input.pdf"))
         total = len(pages_to_translate)
         threshold = 0.8 * total

{babeldoc-0.3.66 → babeldoc-0.3.68}/babeldoc/document_il/midend/paragraph_finder.py

@@ -130,6 +130,8 @@ class ParagraphFinder:
             self.stage_name,
             len(document.page),
         ) as pbar:
+            if not document.page:
+                return
             for page in document.page:
                 self.translation_config.raise_if_cancelled()
                 self.process_page(page)

{babeldoc-0.3.66 → babeldoc-0.3.68}/babeldoc/high_level.py

@@ -23,6 +23,7 @@ from babeldoc.const import CACHE_FOLDER
 from babeldoc.converter import TranslateConverter
 from babeldoc.document_il import il_version_1
 from babeldoc.document_il.babeldoc_exception.BabelDOCException import ExtractTextError
+from babeldoc.document_il.babeldoc_exception.BabelDOCException import ScannedPDFError
 from babeldoc.document_il.backend.pdf_creater import SAVE_PDF_STAGE_NAME
 from babeldoc.document_il.backend.pdf_creater import SUBSET_FONT_STAGE_NAME
 from babeldoc.document_il.backend.pdf_creater import PDFCreater
@@ -643,6 +644,8 @@ def migrate_toc(
     }
 
     for f in files:
+        if not f:
+            continue
         mig_toc_temp_input = translation_config.get_working_file_path(
             "mig_toc_temp.pdf"
         )
@@ -742,22 +745,21 @@ def _do_translate_single(
     resfont = None
     doc_pdf2zh.save(temp_pdf_path)
 
-    # May cause misjudgment, therefore disabled.
-    # if not translation_config.skip_scanned_detection and DetectScannedFile(
-    #     translation_config
-    # ).fast_check(doc_pdf2zh):
-    #     if translation_config.auto_enable_ocr_workaround:
-    #         logger.warning(
-    #             "Fast scanned check hit, Turning on OCR workaround.",
-    #         )
-    #         translation_config.shared_context_cross_split_part.auto_enabled_ocr_workaround = True
-    #         translation_config.ocr_workaround = True
-    #         translation_config.skip_scanned_detection = True
-    #     else:
-    #         logger.warning(
-    #             "Fast scanned check hit, Please check the input PDF file.",
-    #         )
-    #         raise ScannedPDFError("Scanned PDF detected.")
+    if not translation_config.skip_scanned_detection and DetectScannedFile(
+        translation_config
+    ).fast_check(doc_pdf2zh):
+        if translation_config.auto_enable_ocr_workaround:
+            logger.warning(
+                "Fast scanned check hit, Turning on OCR workaround.",
+            )
+            translation_config.shared_context_cross_split_part.auto_enabled_ocr_workaround = True
+            translation_config.ocr_workaround = True
+            translation_config.skip_scanned_detection = True
+        else:
+            logger.warning(
+                "Fast scanned check hit, Please check the input PDF file.",
+            )
+            raise ScannedPDFError("Scanned PDF detected.")
 
     il_creater = ILCreater(translation_config)
     il_creater.mupdf = doc_pdf2zh

{babeldoc-0.3.66 → babeldoc-0.3.68}/babeldoc/main.py

@@ -21,7 +21,7 @@ from babeldoc.translation_config import TranslationConfig
 from babeldoc.translation_config import WatermarkOutputMode
 
 logger = logging.getLogger(__name__)
-__version__ = "0.3.66"
+__version__ = "0.3.68"
 
 
 def create_parser():

{babeldoc-0.3.66 → babeldoc-0.3.68}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.3.66"
+version = "0.3.68"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -154,7 +154,7 @@ pythonpath = [".", "src"]
 testpaths = ["tests"]
 
 [bumpver]
-current_version = "0.3.66"
+current_version = "0.3.68"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]

{babeldoc-0.3.66 → babeldoc-0.3.68}/uv.lock

@@ -48,7 +48,7 @@ wheels = [
 
 [[package]]
 name = "babeldoc"
-version = "0.3.66"
+version = "0.3.68"
 source = { editable = "." }
 dependencies = [
     { name = "bitstring" },

babeldoc-0.3.66/babeldoc/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.3.66"