BabelDOC 0.1.28__tar.gz → 0.1.30__tar.gz

{babeldoc-0.1.28 → babeldoc-0.1.30}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.1.28
+Version: 0.1.30
 Summary: Yet Another Document Translator
 Project-URL: Homepage, https://github.com/funstory-ai/BabelDOC
 Project-URL: Issues, https://github.com/funstory-ai/BabelDOC/issues
@@ -369,6 +369,7 @@ And meet the following requirements:
 1. Parsing errors in the author and reference sections; they get merged into one paragraph after translation.
 2. Lines are not supported.
 3. Does not support drop caps.
+4. Large pages will be skipped.
 
 ## How to Contribute
 

{babeldoc-0.1.28 → babeldoc-0.1.30}/README.md

@@ -334,6 +334,7 @@ And meet the following requirements:
 1. Parsing errors in the author and reference sections; they get merged into one paragraph after translation.
 2. Lines are not supported.
 3. Does not support drop caps.
+4. Large pages will be skipped.
 
 ## How to Contribute
 

babeldoc-0.1.30/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.1.30"

{babeldoc-0.1.28 → babeldoc-0.1.30}/babeldoc/const.py

@@ -2,7 +2,7 @@ import shutil
 import subprocess
 from pathlib import Path
 
-__version__ = "0.1.28"
+__version__ = "0.1.30"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

{babeldoc-0.1.28 → babeldoc-0.1.30}/babeldoc/document_il/midend/detect_scanned_file.py

@@ -113,6 +113,10 @@ class DetectScannedFile:
         pdf.update_object(new_xref, "<<>>")
         pdf.update_stream(new_xref, page.base_operations.value.encode("utf-8"))
         pdf[page.page_number].set_contents(new_xref)
+
+        for xobj in page.pdf_xobject:
+            pdf.update_stream(xobj.xref_id, xobj.base_operations.value.encode("utf-8"))
+
         after_page_image = pdf[page.page_number].get_pixmap()
         after_page_image = np.frombuffer(after_page_image.samples, np.uint8).reshape(
             after_page_image.height,

{babeldoc-0.1.28 → babeldoc-0.1.30}/babeldoc/high_level.py

@@ -138,8 +138,18 @@ def start_parse_il(
         if pages and (pageno not in pages):
             continue
         page.pageno = pageno
+
         if not translation_config.should_translate_page(pageno + 1):
             continue
+
+        height, width = (
+            page.cropbox[3] - page.cropbox[1],
+            page.cropbox[2] - page.cropbox[0],
+        )
+        if height > 1200 or width > 2000:
+            logger.warning(f"page {pageno + 1} is too large, skip")
+            continue
+
         translation_config.raise_if_cancelled()
         # The current program no longer relies on
         # the following layout recognition results,

{babeldoc-0.1.28 → babeldoc-0.1.30}/babeldoc/main.py

@@ -25,7 +25,7 @@ from babeldoc.translation_config import TranslationConfig
 from babeldoc.translation_config import WatermarkOutputMode
 
 logger = logging.getLogger(__name__)
-__version__ = "0.1.28"
+__version__ = "0.1.30"
 
 
 def create_parser():

{babeldoc-0.1.28 → babeldoc-0.1.30}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.1.28"
+version = "0.1.30"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -133,7 +133,7 @@ pythonpath = [".", "src"]
 testpaths = ["tests"]
 
 [bumpver]
-current_version = "0.1.28"
+current_version = "0.1.30"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]

{babeldoc-0.1.28 → babeldoc-0.1.30}/uv.lock

@@ -48,7 +48,7 @@ wheels = [
 
 [[package]]
 name = "babeldoc"
-version = "0.1.28"
+version = "0.1.30"
 source = { editable = "." }
 dependencies = [
     { name = "bitstring" },

babeldoc-0.1.28/babeldoc/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.1.28"