BabelDOC 0.3.64__tar.gz → 0.3.66__tar.gz

{babeldoc-0.3.64 → babeldoc-0.3.66}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.3.64
+Version: 0.3.66
 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-0.3.66/babeldoc/__init__.py

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

{babeldoc-0.3.64 → babeldoc-0.3.66}/babeldoc/const.py

@@ -3,7 +3,7 @@ import shutil
 import subprocess
 from pathlib import Path
 
-__version__ = "0.3.64"
+__version__ = "0.3.66"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

{babeldoc-0.3.64 → babeldoc-0.3.66}/babeldoc/document_il/utils/layout_helper.py

@@ -39,7 +39,7 @@ LEFT_BRACKET = ("(cid:8)", "(", "(cid:16)", "{", "[", "(cid:104)", "(cid:2)")
 RIGHT_BRACKET = ("(cid:9)", ")", "(cid:17)", "}", "]", "(cid:105)", "(cid:3)")
 
 BULLET_POINT_PATTERN = re.compile(
-    r"[■•⚫⬤◆◇○●◦‣⁃▪▫∗†‡¹²³⁴⁵⁶⁷⁸⁹⁰₁₂₃₄₅₆₇₈₉₀ᵃᵇᶜᵈᵉᶠᵍʰⁱʲᵏˡᵐⁿᵒᵖᵍʳˢᵗᵘᵛʷˣʸᶻ†‡§¶※⁑⁂⁕⁎⁜⁑❧☙⁋‖‽]"
+    r"[■•⚫⬤◆◇○●◦‣⁃▪▫∗†‡¹²³⁴⁵⁶⁷⁸⁹⁰₁₂₃₄₅₆₇₈₉₀ᵃᵇᶜᵈᵉᶠᵍʰⁱʲᵏˡᵐⁿᵒᵖᵍʳˢᵗᵘᵛʷˣʸᶻ†‡§¶※⁑⁂⁕⁎⁜⁑❧☙⁋‖‽·]"
 )
 
 

{babeldoc-0.3.64 → babeldoc-0.3.66}/babeldoc/high_level.py

@@ -23,7 +23,6 @@ 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
@@ -92,7 +91,7 @@ def fix_cmap(translate_result: TranslateResult, translate_config: TranslationCon
         "no_watermark_dual_pdf_path",
     ):
         path = getattr(translate_result, attr)
-        if path in processed:
+        if not path or path in processed:
             continue
         processed.append(path)
 
@@ -743,21 +742,22 @@ def _do_translate_single(
     resfont = None
     doc_pdf2zh.save(temp_pdf_path)
 
-    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.")
+    # 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.")
 
     il_creater = ILCreater(translation_config)
     il_creater.mupdf = doc_pdf2zh

{babeldoc-0.3.64 → babeldoc-0.3.66}/babeldoc/main.py

@@ -21,7 +21,7 @@ from babeldoc.translation_config import TranslationConfig
 from babeldoc.translation_config import WatermarkOutputMode
 
 logger = logging.getLogger(__name__)
-__version__ = "0.3.64"
+__version__ = "0.3.66"
 
 
 def create_parser():

{babeldoc-0.3.64 → babeldoc-0.3.66}/babeldoc/tools/italic_assistance.py

@@ -5,6 +5,10 @@ from pathlib import Path
 
 import orjson
 from babeldoc.const import CACHE_FOLDER
+from babeldoc.document_il.midend.styles_and_formulas import StylesAndFormulas
+from babeldoc.translation_config import TranslationConfig
+from rich.console import Console
+from rich.table import Table
 
 WORKING_FOLDER = Path(CACHE_FOLDER) / "working"
 
@@ -210,6 +214,80 @@ def main():
             f"No fonts found for paragraphs matching debug_id pattern: {args.debug_id_regex}"
         )
 
+    fonts = []
+
+    # Read intermediate representation
+    with json_path.open(encoding="utf-8") as f:
+        pdf_data = json.load(f)
+
+    for page_index, page in enumerate(pdf_data["page"]):
+        for paragraph_index, paragraph_content in enumerate(page["pdf_paragraph"]):
+            font_debug_id = paragraph_content["debug_id"]
+            if font_debug_id:
+                # Create page font mapping
+                page_font_map = {}
+                for font in page["pdf_font"]:
+                    if "font_id" in font and "name" in font:
+                        page_font_map[font["font_id"]] = (font["font_id"], font["name"])
+
+                # Extract fonts from paragraph
+                name_list = []
+                paragraph_fonts = extract_fonts_from_paragraph(
+                    paragraph_content, page_font_map
+                )
+                for _font_id, font_name in paragraph_fonts:
+                    name_list.append(font_name)
+
+                font_list = []
+                for each in fonts:
+                    font_list.append(each[1])
+
+                for each_name in name_list:
+                    if each_name not in font_list:
+                        fonts.append(
+                            (page_index, each_name, paragraph_index, font_debug_id)
+                        )
+
+    # Initialize checker
+    translation_config = TranslationConfig(
+        *[None for _ in range(3)], lang_out="zh_cn", doc_layout_model=1
+    )
+    checker = StylesAndFormulas(translation_config)
+
+    # Create table
+    table = Table(title="Font Recognition Results")
+    table.add_column("Page #", justify="center", style="cyan")
+    table.add_column("Paragraph #", justify="center", style="cyan")
+    table.add_column("DEBUG_ID", justify="center", style="cyan")
+    table.add_column("Font Name", style="magenta")
+    table.add_column("Recognition Result", justify="center")
+
+    # Output results
+    for each_font in fonts:
+        page_index, font_name, paragraph_index, font_debug_id = each_font
+
+        if checker.is_formulas_font(font_name):
+            table.add_row(
+                str(page_index),
+                str(paragraph_index),
+                str(font_debug_id),
+                font_name,
+                "[bold red]Formula Font[/bold red]",
+            )
+        else:
+            table.add_row(
+                str(page_index),
+                str(paragraph_index),
+                str(font_debug_id),
+                font_name,
+                "[bold blue]Non-Formula Font[/bold blue]",
+            )
+
+    # Print table
+    console = Console()
+
+    console.print(table)
+
     return 0
 
 

{babeldoc-0.3.64 → babeldoc-0.3.66}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.3.64"
+version = "0.3.66"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -154,7 +154,7 @@ pythonpath = [".", "src"]
 testpaths = ["tests"]
 
 [bumpver]
-current_version = "0.3.64"
+current_version = "0.3.66"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]

{babeldoc-0.3.64 → babeldoc-0.3.66}/uv.lock

@@ -48,7 +48,7 @@ wheels = [
 
 [[package]]
 name = "babeldoc"
-version = "0.3.64"
+version = "0.3.66"
 source = { editable = "." }
 dependencies = [
     { name = "bitstring" },

babeldoc-0.3.64/babeldoc/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.3.64"