BabelDOC 0.3.58__tar.gz → 0.3.59__tar.gz

{babeldoc-0.3.58 → babeldoc-0.3.59}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.3.58
+Version: 0.3.59
 Summary: Yet Another Document Translator
 Project-URL: Homepage, https://github.com/funstory-ai/BabelDOC
 Project-URL: Issues, https://github.com/funstory-ai/BabelDOC/issues
@@ -204,8 +204,14 @@ 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)
+- `--formular-font-pattern`: Font pattern to identify formula text (default: None)
+- `--formular-char-pattern`: Character pattern to identify formula text (default: None)
+- `--show-char-box`: Show character bounding boxes (debug only, default: False)
 - `--skip-scanned-detection`: Skip scanned document detection (default: False). When using split translation, only the first part performs detection if not skipped.
-- `--ocr-workaround`: Use OCR workaround (default: False). When enabled, the tool will use OCR to detect text and fill background for scanned PDF.
+- `--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.
+
+
+- `--rpc-doclayout`: RPC service host address for document layout analysis (default: None)
 - `--working-dir`: Working directory for translation. If not set, use temp directory.
 - `--no-auto-extract-glossary`: Disable automatic term extraction. If this flag is present, the step is skipped. Defaults to enabled.
 
@@ -265,9 +271,13 @@ uv run babeldoc --files example.pdf --files example2.pdf --openai --openai-model
 ### Output Control
 
 - `--output`, `-o`: Output directory for translated files. If not set, use current working directory.
-- `--debug`, `-d`: Enable debug logging level and export detailed intermediate results in `~/.cache/yadt/working`.
+- `--debug`: Enable debug logging level and export detailed intermediate results in `~/.cache/yadt/working`.
 - `--report-interval`: Progress report interval in seconds (default: 0.1).
 
+### General Options
+
+- `--warmup`: Only download and verify required assets then exit (default: False)
+
 ### Offline Assets Management
 
 - `--generate-offline-assets`: Generate an offline assets package in the specified directory. This creates a zip file containing all required models and fonts.
@@ -311,6 +321,12 @@ max-pages-per-part = 50  # Automatically split the document for translation and
 # 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
+formular_font_pattern = "" # Font pattern for formula text
+formular_char_pattern = "" # Character pattern for formula text
+show_char_box = false # Show character bounding boxes (debug)
+ocr_workaround = false # Use OCR workaround for scanned PDFs
+rpc_doclayout = "" # RPC service host for document layout analysis
+working_dir = "" # Working directory for translation
 
 # Translation service
 openai = true

{babeldoc-0.3.58 → babeldoc-0.3.59}/README.md

@@ -154,8 +154,14 @@ 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)
+- `--formular-font-pattern`: Font pattern to identify formula text (default: None)
+- `--formular-char-pattern`: Character pattern to identify formula text (default: None)
+- `--show-char-box`: Show character bounding boxes (debug only, default: False)
 - `--skip-scanned-detection`: Skip scanned document detection (default: False). When using split translation, only the first part performs detection if not skipped.
-- `--ocr-workaround`: Use OCR workaround (default: False). When enabled, the tool will use OCR to detect text and fill background for scanned PDF.
+- `--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.
+
+
+- `--rpc-doclayout`: RPC service host address for document layout analysis (default: None)
 - `--working-dir`: Working directory for translation. If not set, use temp directory.
 - `--no-auto-extract-glossary`: Disable automatic term extraction. If this flag is present, the step is skipped. Defaults to enabled.
 
@@ -215,9 +221,13 @@ uv run babeldoc --files example.pdf --files example2.pdf --openai --openai-model
 ### Output Control
 
 - `--output`, `-o`: Output directory for translated files. If not set, use current working directory.
-- `--debug`, `-d`: Enable debug logging level and export detailed intermediate results in `~/.cache/yadt/working`.
+- `--debug`: Enable debug logging level and export detailed intermediate results in `~/.cache/yadt/working`.
 - `--report-interval`: Progress report interval in seconds (default: 0.1).
 
+### General Options
+
+- `--warmup`: Only download and verify required assets then exit (default: False)
+
 ### Offline Assets Management
 
 - `--generate-offline-assets`: Generate an offline assets package in the specified directory. This creates a zip file containing all required models and fonts.
@@ -261,6 +271,12 @@ max-pages-per-part = 50  # Automatically split the document for translation and
 # 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
+formular_font_pattern = "" # Font pattern for formula text
+formular_char_pattern = "" # Character pattern for formula text
+show_char_box = false # Show character bounding boxes (debug)
+ocr_workaround = false # Use OCR workaround for scanned PDFs
+rpc_doclayout = "" # RPC service host for document layout analysis
+working_dir = "" # Working directory for translation
 
 # Translation service
 openai = true

babeldoc-0.3.59/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.3.59"

{babeldoc-0.3.58 → babeldoc-0.3.59}/babeldoc/const.py

@@ -3,7 +3,7 @@ import shutil
 import subprocess
 from pathlib import Path
 
-__version__ = "0.3.58"
+__version__ = "0.3.59"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

{babeldoc-0.3.58 → babeldoc-0.3.59}/babeldoc/document_il/midend/automatic_term_extractor.py

@@ -254,7 +254,7 @@ class AutomaticTermExtractor:
                         )
 
         except Exception as e:
-            logger.error(f"Error during automatic terms extract: {e}")
+            logger.warning(f"Error during automatic terms extract: {e}")
             return
         finally:
             pbar.advance(len(paragraphs.paragraphs))

{babeldoc-0.3.58 → babeldoc-0.3.59}/babeldoc/document_il/translator/translator.py

@@ -114,10 +114,13 @@ class BaseTranslator(ABC):
         """
         self.translate_call_count += 1
         if not (self.ignore_cache or ignore_cache):
-            cache = self.cache.get(text)
-            if cache is not None:
-                self.translate_cache_call_count += 1
-                return cache
+            try:
+                cache = self.cache.get(text)
+                if cache is not None:
+                    self.translate_cache_call_count += 1
+                    return cache
+            except Exception as e:
+                logger.debug(f"try get cache failed, ignore it: {e}")
         _translate_rate_limiter.wait()
         translation = self.do_translate(text, rate_limit_params)
         if not (self.ignore_cache or ignore_cache):
@@ -132,10 +135,13 @@ class BaseTranslator(ABC):
         """
         self.translate_call_count += 1
         if not (self.ignore_cache or ignore_cache):
-            cache = self.cache.get(text)
-            if cache is not None:
-                self.translate_cache_call_count += 1
-                return cache
+            try:
+                cache = self.cache.get(text)
+                if cache is not None:
+                    self.translate_cache_call_count += 1
+                    return cache
+            except Exception as e:
+                logger.debug(f"try get cache failed, ignore it: {e}")
         _translate_rate_limiter.wait()
         translation = self.do_llm_translate(text, rate_limit_params)
         if not (self.ignore_cache or ignore_cache):

{babeldoc-0.3.58 → babeldoc-0.3.59}/babeldoc/main.py

@@ -24,7 +24,7 @@ from babeldoc.translation_config import TranslationConfig
 from babeldoc.translation_config import WatermarkOutputMode
 
 logger = logging.getLogger(__name__)
-__version__ = "0.3.58"
+__version__ = "0.3.59"
 
 
 def create_parser():

{babeldoc-0.3.58 → babeldoc-0.3.59}/babeldoc/pdfinterp.py

@@ -319,7 +319,11 @@ class PDFPageInterpreterEx(PDFPageInterpreter):
             (x, y) = apply_matrix_pt(ctm, (x, y))
             (x2, y2) = apply_matrix_pt(ctm, (x2, y2))
             x_id = self.il_creater.on_xobj_begin((x, y, x2, y2), xobj.objid)
-            ctm_inv = np.linalg.inv(np.array(ctm[:4]).reshape(2, 2))
+            try:
+                ctm_inv = np.linalg.inv(np.array(ctm[:4]).reshape(2, 2))
+            except Exception:
+                self.il_creater.on_xobj_end(x_id, " ")
+                return
             np_version = np.__version__
             if np_version.split(".")[0] >= "2":
                 pos_inv = -np.asmatrix(ctm[4:]) * ctm_inv

{babeldoc-0.3.58 → babeldoc-0.3.59}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.3.58"
+version = "0.3.59"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -151,7 +151,7 @@ pythonpath = [".", "src"]
 testpaths = ["tests"]
 
 [bumpver]
-current_version = "0.3.58"
+current_version = "0.3.59"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]

{babeldoc-0.3.58 → babeldoc-0.3.59}/uv.lock

@@ -48,7 +48,7 @@ wheels = [
 
 [[package]]
 name = "babeldoc"
-version = "0.3.58"
+version = "0.3.59"
 source = { editable = "." }
 dependencies = [
     { name = "bitstring" },

babeldoc-0.3.58/babeldoc/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.3.58"