BabelDOC 0.3.69__tar.gz → 0.3.71__tar.gz

{babeldoc-0.3.69 → babeldoc-0.3.71}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.3.69
+Version: 0.3.71
 Summary: Yet Another Document Translator
 Project-URL: Homepage, https://github.com/funstory-ai/BabelDOC
 Project-URL: Issues, https://github.com/funstory-ai/BabelDOC/issues
@@ -212,6 +212,7 @@ uv run babeldoc --files example.pdf --files example2.pdf --openai --openai-model
 - `--ocr-workaround`: Use OCR workaround (default: False). Only suitable for documents with black text on white background. When enabled, white rectangular blocks will be added below the translation to cover the original text content, and all text will be forced to black color.
 - `--auto-enable-ocr-workaround`: Enable automatic OCR workaround (default: False). If a document is detected as heavily scanned, this will attempt to enable OCR processing and skip further scan detection. See "Important Interaction Note" below for crucial details on how this interacts with `--ocr-workaround` and `--skip-scanned-detection`.
 - `--primary-font-family`: Override primary font family for translated text. Choices: 'serif' for serif fonts, 'sans-serif' for sans-serif fonts, 'script' for script/italic fonts. If not specified, uses automatic font selection based on original text properties.
+- `--only-include-translated-page`: Only include translated pages in the output PDF. This option is only effective when `--pages` is used. (default: False)
 
 - `--rpc-doclayout`: RPC service host address for document layout analysis (default: None)
 - `--working-dir`: Working directory for translation. If not set, use temp directory.
@@ -320,6 +321,7 @@ disable-rich-text-translate = false
 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.
+only_include_translated_page = false # Only include translated pages in the output PDF. Effective only when `pages` is used.
 # no-watermark = false  # DEPRECATED: Use watermark-output-mode instead
 skip-scanned-detection = false  # Skip scanned document detection for faster processing
 auto_extract_glossary = true # Set to false to disable automatic term extraction

{babeldoc-0.3.69 → babeldoc-0.3.71}/README.md

@@ -161,6 +161,7 @@ uv run babeldoc --files example.pdf --files example2.pdf --openai --openai-model
 - `--ocr-workaround`: Use OCR workaround (default: False). Only suitable for documents with black text on white background. When enabled, white rectangular blocks will be added below the translation to cover the original text content, and all text will be forced to black color.
 - `--auto-enable-ocr-workaround`: Enable automatic OCR workaround (default: False). If a document is detected as heavily scanned, this will attempt to enable OCR processing and skip further scan detection. See "Important Interaction Note" below for crucial details on how this interacts with `--ocr-workaround` and `--skip-scanned-detection`.
 - `--primary-font-family`: Override primary font family for translated text. Choices: 'serif' for serif fonts, 'sans-serif' for sans-serif fonts, 'script' for script/italic fonts. If not specified, uses automatic font selection based on original text properties.
+- `--only-include-translated-page`: Only include translated pages in the output PDF. This option is only effective when `--pages` is used. (default: False)
 
 - `--rpc-doclayout`: RPC service host address for document layout analysis (default: None)
 - `--working-dir`: Working directory for translation. If not set, use temp directory.
@@ -269,6 +270,7 @@ disable-rich-text-translate = false
 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.
+only_include_translated_page = false # Only include translated pages in the output PDF. Effective only when `pages` is used.
 # no-watermark = false  # DEPRECATED: Use watermark-output-mode instead
 skip-scanned-detection = false  # Skip scanned document detection for faster processing
 auto_extract_glossary = true # Set to false to disable automatic term extraction

babeldoc-0.3.71/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.3.71"

{babeldoc-0.3.69 → babeldoc-0.3.71}/babeldoc/const.py

@@ -3,7 +3,7 @@ import shutil
 import subprocess
 from pathlib import Path
 
-__version__ = "0.3.69"
+__version__ = "0.3.71"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

{babeldoc-0.3.69 → babeldoc-0.3.71}/babeldoc/document_il/backend/pdf_creater.py

@@ -966,6 +966,22 @@ class PDFCreater:
                 self.restore_media_box(pdf, self.mediabox_data)
             except Exception:
                 logger.exception("restore media box failed")
+
+            if translation_config.only_include_translated_page:
+                total_page = set(range(0, len(pdf)))
+
+                pages_to_translate = {
+                    page.page_number
+                    for page in self.docs.page
+                    if self.translation_config.should_translate_page(
+                        page.page_number + 1
+                    )
+                }
+
+                should_removed_page = list(total_page - pages_to_translate)
+
+                pdf.delete_pages(should_removed_page)
+
             with self.translation_config.progress_monitor.stage_start(
                 SAVE_PDF_STAGE_NAME,
                 2,
@@ -998,6 +1014,11 @@ class PDFCreater:
                     )
                     translation_config.raise_if_cancelled()
                     original_pdf = pymupdf.open(self.original_pdf_path)
+                    if (
+                        self.translation_config.only_include_translated_page
+                        and should_removed_page
+                    ):
+                        original_pdf.delete_pages(should_removed_page)
                     translated_pdf = pdf
 
                     # Choose between alternating pages and side-by-side format

{babeldoc-0.3.69 → babeldoc-0.3.71}/babeldoc/document_il/midend/detect_scanned_file.py

@@ -71,7 +71,9 @@ class DetectScannedFile:
                 contents_list = page.get_contents()
                 for index in contents_list:
                     contents = doc.xref_stream(index)
-                    if regex.search(rb"/Artifact(\s*\<\<\s*/MCID\s+|\s+BDC)", contents):
+                    if regex.search(
+                        rb"(/Artifact|/P)(\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
@@ -112,7 +114,7 @@ class DetectScannedFile:
                     non_scanned += 1
                 progress.advance(1)
 
-        if scanned > threshold:
+        if scanned >= threshold:
             if self.translation_config.auto_enable_ocr_workaround:
                 logger.warning(
                     f"Detected {scanned} scanned pages, which is more than 80% of the total pages. "
@@ -156,4 +158,5 @@ class DetectScannedFile:
         )[:, :, ::-1]
         before_page_image = cv2.cvtColor(before_page_image, cv2.COLOR_RGB2GRAY)
         after_page_image = cv2.cvtColor(after_page_image, cv2.COLOR_RGB2GRAY)
-        return structural_similarity(before_page_image, after_page_image) > 0.97
+        similarity = structural_similarity(before_page_image, after_page_image)
+        return similarity > 0.95

{babeldoc-0.3.69 → babeldoc-0.3.71}/babeldoc/high_level.py

@@ -398,6 +398,18 @@ class MemoryMonitor:
             time.sleep(self.interval)
 
 
+def fix_null_page_content(doc: Document) -> list[int]:
+    invalid_page = []
+    for x in range(len(doc)):
+        xref = doc[x].xref
+        if doc.xref_object(xref) == "null":
+            invalid_page.append(x)
+    for x in invalid_page:
+        doc.delete_page(x)
+        doc.insert_page(x)
+    return invalid_page
+
+
 def fix_null_xref(doc: Document) -> None:
     """Fix null xref in PDF file by replacing them with empty arrays.
 
@@ -718,6 +730,7 @@ def _do_translate_single(
         )
         # Fix null xref in PDF file
         try:
+            _ = fix_null_page_content(doc_input)
             fix_filter(doc_input)
             fix_null_xref(doc_input)
         except Exception:
@@ -731,7 +744,9 @@ def _do_translate_single(
     resfont = "china-ss"
 
     # Fix null xref in PDF file
+    invalid_pages = []
     try:
+        invalid_pages = fix_null_page_content(doc_pdf2zh)
         fix_filter(doc_pdf2zh)
         fix_null_xref(doc_pdf2zh)
     except Exception:

{babeldoc-0.3.69 → babeldoc-0.3.71}/babeldoc/main.py

@@ -21,7 +21,7 @@ from babeldoc.translation_config import TranslationConfig
 from babeldoc.translation_config import WatermarkOutputMode
 
 logger = logging.getLogger(__name__)
-__version__ = "0.3.69"
+__version__ = "0.3.71"
 
 
 def create_parser():
@@ -261,6 +261,12 @@ def create_parser():
         default=None,
         help="Override primary font family for translated text. Choices: 'serif' for serif fonts, 'sans-serif' for sans-serif fonts, 'script' for script/italic fonts. If not specified, uses automatic font selection based on original text properties.",
     )
+    translation_group.add_argument(
+        "--only-include-translated-page",
+        action="store_true",
+        default=False,
+        help="Only include translated pages in the output PDF. Effective only when --pages is used.",
+    )
     # service option argument group
     service_group = translation_group.add_mutually_exclusive_group()
     service_group.add_argument(
@@ -483,6 +489,7 @@ async def main():
             auto_extract_glossary=args.auto_extract_glossary,
             auto_enable_ocr_workaround=args.auto_enable_ocr_workaround,
             primary_font_family=args.primary_font_family,
+            only_include_translated_page=args.only_include_translated_page,
         )
 
         # Create progress handler

{babeldoc-0.3.69 → babeldoc-0.3.71}/babeldoc/translation_config.py

@@ -153,6 +153,7 @@ class TranslationConfig:
         auto_extract_glossary: bool = True,
         auto_enable_ocr_workaround: bool = False,
         primary_font_family: str | None = None,
+        only_include_translated_page: bool | None = False,
     ):
         self.translator = translator
         initial_user_glossaries = list(glossaries) if glossaries else []
@@ -268,6 +269,11 @@ class TranslationConfig:
         ]
         self.primary_font_family = primary_font_family
 
+        if only_include_translated_page is None:
+            only_include_translated_page = False
+
+        self.only_include_translated_page = only_include_translated_page
+
     def parse_pages(self, pages_str: str | None) -> list[tuple[int, int]] | None:
         """解析页码字符串，返回页码范围列表
 

{babeldoc-0.3.69 → babeldoc-0.3.71}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.3.69"
+version = "0.3.71"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -154,7 +154,7 @@ pythonpath = [".", "src"]
 testpaths = ["tests"]
 
 [bumpver]
-current_version = "0.3.69"
+current_version = "0.3.71"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]

{babeldoc-0.3.69 → babeldoc-0.3.71}/uv.lock

@@ -48,7 +48,7 @@ wheels = [
 
 [[package]]
 name = "babeldoc"
-version = "0.3.69"
+version = "0.3.71"
 source = { editable = "." }
 dependencies = [
     { name = "bitstring" },

babeldoc-0.3.69/babeldoc/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.3.69"