BabelDOC 0.2.32__tar.gz → 0.2.33__tar.gz

{babeldoc-0.2.32 → babeldoc-0.2.33}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.2.32
+Version: 0.2.33
 Summary: Yet Another Document Translator
 Project-URL: Homepage, https://github.com/funstory-ai/BabelDOC
 Project-URL: Issues, https://github.com/funstory-ai/BabelDOC/issues
@@ -187,6 +187,7 @@ uv run babeldoc --files example.pdf --files example2.pdf --openai --openai-model
 - `--max-pages-per-part`: Maximum number of pages per part for split translation. If not set, no splitting will be performed.
 - `--no-watermark`: [DEPRECATED] Use --watermark-output-mode=no_watermark instead.
 - `--translate-table-text`: Translate table text (experimental, default: False)
+- `--skip-scanned-detection`: Skip scanned document detection (default: False). When using split translation, only the first part performs detection if not skipped.
 
 > [!TIP]
 > - Both `--skip-clean` and `--dual-translate-first` may help improve compatibility with some PDF readers
@@ -194,6 +195,7 @@ uv run babeldoc --files example.pdf --files example2.pdf --openai --openai-model
 > - However, using `--skip-clean` will result in larger file sizes
 > - If you encounter any compatibility issues, try using `--enhance-compatibility` first
 > - Use `--max-pages-per-part` for large documents to split them into smaller parts for translation and automatically merge them back.
+> - Use `--skip-scanned-detection` to speed up processing when you know your document is not a scanned PDF.
 
 ### Translation Service Options
 
@@ -268,6 +270,7 @@ use-alternating-pages-dual = false
 watermark-output-mode = "watermarked"  # Choices: "watermarked", "no_watermark", "both"
 max-pages-per-part = 50  # Automatically split the document for translation and merge it back.
 # no-watermark = false  # DEPRECATED: Use watermark-output-mode instead
+skip-scanned-detection = false  # Skip scanned document detection for faster processing
 
 # Translation service
 openai = true

{babeldoc-0.2.32 → babeldoc-0.2.33}/README.md

@@ -141,6 +141,7 @@ uv run babeldoc --files example.pdf --files example2.pdf --openai --openai-model
 - `--max-pages-per-part`: Maximum number of pages per part for split translation. If not set, no splitting will be performed.
 - `--no-watermark`: [DEPRECATED] Use --watermark-output-mode=no_watermark instead.
 - `--translate-table-text`: Translate table text (experimental, default: False)
+- `--skip-scanned-detection`: Skip scanned document detection (default: False). When using split translation, only the first part performs detection if not skipped.
 
 > [!TIP]
 > - Both `--skip-clean` and `--dual-translate-first` may help improve compatibility with some PDF readers
@@ -148,6 +149,7 @@ uv run babeldoc --files example.pdf --files example2.pdf --openai --openai-model
 > - However, using `--skip-clean` will result in larger file sizes
 > - If you encounter any compatibility issues, try using `--enhance-compatibility` first
 > - Use `--max-pages-per-part` for large documents to split them into smaller parts for translation and automatically merge them back.
+> - Use `--skip-scanned-detection` to speed up processing when you know your document is not a scanned PDF.
 
 ### Translation Service Options
 
@@ -222,6 +224,7 @@ use-alternating-pages-dual = false
 watermark-output-mode = "watermarked"  # Choices: "watermarked", "no_watermark", "both"
 max-pages-per-part = 50  # Automatically split the document for translation and merge it back.
 # no-watermark = false  # DEPRECATED: Use watermark-output-mode instead
+skip-scanned-detection = false  # Skip scanned document detection for faster processing
 
 # Translation service
 openai = true

babeldoc-0.2.33/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.2.33"

{babeldoc-0.2.32 → babeldoc-0.2.33}/babeldoc/const.py

@@ -3,7 +3,7 @@ import shutil
 import subprocess
 from pathlib import Path
 
-__version__ = "0.2.32"
+__version__ = "0.2.33"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

{babeldoc-0.2.32 → babeldoc-0.2.33}/babeldoc/document_il/midend/styles_and_formulas.py

@@ -541,6 +541,8 @@ class StylesAndFormulas:
             r"|Times-Italic.*"
             r"|MeridienLTStd.*"
             r"|Calibri.*"
+            r"|STIXMathJax_Main-Regular.*"
+            r"|STIXMathJax_Main-Italic.*"
             r")$"
         )
         if self.translation_config.formular_font_pattern:

{babeldoc-0.2.32 → babeldoc-0.2.33}/babeldoc/high_level.py

@@ -431,6 +431,10 @@ def do_translate(
                                     (x, x) for x in should_translate_pages
                                 ]
 
+                                # Only first part should do scanned detection if enabled
+                                if i > 0:
+                                    part_config.skip_scanned_detection = True
+
                                 part_config.working_dir = (
                                     translation_config.get_part_working_dir(i)
                                 )
@@ -576,14 +580,17 @@ def _do_translate_single(
     # [Previous implementation of do_translate continues here]
 
     # 检测是否为扫描文件
-    logger.debug("start detect scanned file")
-    DetectScannedFile(translation_config).process(docs)
-    logger.debug("finish detect scanned file")
-    if translation_config.debug:
-        xml_converter.write_json(
-            docs,
-            translation_config.get_working_file_path("detect_scanned_file.json"),
-        )
+    if translation_config.skip_scanned_detection:
+        logger.debug("skipping scanned file detection")
+    else:
+        logger.debug("start detect scanned file")
+        DetectScannedFile(translation_config).process(docs)
+        logger.debug("finish detect scanned file")
+        if translation_config.debug:
+            xml_converter.write_json(
+                docs,
+                translation_config.get_working_file_path("detect_scanned_file.json"),
+            )
 
     # Generate layouts for all pages
     logger.debug("start generating layouts")

{babeldoc-0.2.32 → babeldoc-0.2.33}/babeldoc/main.py

@@ -23,7 +23,7 @@ from babeldoc.translation_config import TranslationConfig
 from babeldoc.translation_config import WatermarkOutputMode
 
 logger = logging.getLogger(__name__)
-__version__ = "0.2.32"
+__version__ = "0.2.33"
 
 
 def create_parser():
@@ -204,6 +204,12 @@ def create_parser():
         default=False,
         help="Show character box (debug only)",
     )
+    translation_group.add_argument(
+        "--skip-scanned-detection",
+        action="store_true",
+        default=False,
+        help="Skip scanned document detection (speeds up processing for non-scanned documents)",
+    )
     # service option argument group
     service_group = translation_group.add_mutually_exclusive_group()
     service_group.add_argument(
@@ -370,6 +376,7 @@ async def main():
             split_strategy=split_strategy,
             table_model=table_model,
             show_char_box=args.show_char_box,
+            skip_scanned_detection=args.skip_scanned_detection,
         )
 
         # Create progress handler

{babeldoc-0.2.32 → babeldoc-0.2.33}/babeldoc/translation_config.py

@@ -67,6 +67,7 @@ class TranslationConfig:
         split_strategy: BaseSplitStrategy | None = None,
         table_model=None,
         show_char_box: bool = False,
+        skip_scanned_detection: bool = False,
     ):
         self.translator = translator
 
@@ -97,6 +98,7 @@ class TranslationConfig:
         self.doc_layout_model = doc_layout_model
 
         self.skip_clean = skip_clean or enhance_compatibility
+        self.skip_scanned_detection = skip_scanned_detection
 
         self.dual_translate_first = dual_translate_first or enhance_compatibility
         self.disable_rich_text_translate = (

{babeldoc-0.2.32 → babeldoc-0.2.33}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.2.32"
+version = "0.2.33"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -148,7 +148,7 @@ pythonpath = [".", "src"]
 testpaths = ["tests"]
 
 [bumpver]
-current_version = "0.2.32"
+current_version = "0.2.33"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]

{babeldoc-0.2.32 → babeldoc-0.2.33}/uv.lock

@@ -48,7 +48,7 @@ wheels = [
 
 [[package]]
 name = "babeldoc"
-version = "0.2.32"
+version = "0.2.33"
 source = { editable = "." }
 dependencies = [
     { name = "bitstring" },

babeldoc-0.2.32/babeldoc/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.2.32"