BabelDOC 0.2.27__tar.gz → 0.2.29__tar.gz

{babeldoc-0.2.27 → babeldoc-0.2.29}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.2.27
+Version: 0.2.29
 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-0.2.29/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.2.29"

{babeldoc-0.2.27 → babeldoc-0.2.29}/babeldoc/const.py

@@ -3,7 +3,7 @@ import shutil
 import subprocess
 from pathlib import Path
 
-__version__ = "0.2.27"
+__version__ = "0.2.29"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

{babeldoc-0.2.27 → babeldoc-0.2.29}/babeldoc/document_il/midend/il_translator.py

@@ -1,4 +1,3 @@
-import concurrent.futures
 import json
 import logging
 import re
@@ -22,6 +21,9 @@ from babeldoc.document_il.utils.layout_helper import get_char_unicode_string
 from babeldoc.document_il.utils.layout_helper import is_same_style
 from babeldoc.document_il.utils.layout_helper import is_same_style_except_font
 from babeldoc.document_il.utils.layout_helper import is_same_style_except_size
+from babeldoc.document_il.utils.priority_thread_pool_executor import (
+    PriorityThreadPoolExecutor,
+)
 from babeldoc.translation_config import TranslationConfig
 
 logger = logging.getLogger(__name__)
@@ -132,7 +134,10 @@ class ILTranslator:
             self.tokenizer = tokenizer
 
     def calc_token_count(self, text: str) -> int:
-        return len(self.tokenizer.encode(text, disallowed_special=()))
+        try:
+            return len(self.tokenizer.encode(text, disallowed_special=()))
+        except Exception:
+            return 0
 
     def translate(self, docs: Document):
         tracker = DocumentTranslateTracker()
@@ -142,7 +147,7 @@ class ILTranslator:
             self.stage_name,
             total,
         ) as pbar:
-            with concurrent.futures.ThreadPoolExecutor(
+            with PriorityThreadPoolExecutor(
                 max_workers=min(
                     self.translation_config.qps * 2,
                     self.translation_config.qps + 5,
@@ -161,7 +166,7 @@ class ILTranslator:
     def process_page(
         self,
         page: Page,
-        executor: concurrent.futures.ThreadPoolExecutor,
+        executor: PriorityThreadPoolExecutor,
         pbar: tqdm | None = None,
         tracker: PageTranslateTracker = None,
     ):

{babeldoc-0.2.27 → babeldoc-0.2.29}/babeldoc/document_il/midend/il_translator_llm_only.py

@@ -65,7 +65,10 @@ class ILTranslatorLLMOnly:
             raise ValueError("LLM translator not supported") from e
 
     def calc_token_count(self, text: str) -> int:
-        return len(self.tokenizer.encode(text, disallowed_special=()))
+        try:
+            return len(self.tokenizer.encode(text, disallowed_special=()))
+        except Exception:
+            return 0
 
     def find_title_paragraph(self, docs: Document) -> PdfParagraph | None:
         """Find the first paragraph with layout_label 'title' in the document.

{babeldoc-0.2.27 → babeldoc-0.2.29}/babeldoc/document_il/midend/styles_and_formulas.py

@@ -534,6 +534,10 @@ class StylesAndFormulas:
             r"|Arial.*"
             r"|TimesNewRoman.*"
             r"|SegoeUI.*"
+            r"|CMTT9.*"
+            r"|CMSL10.*"
+            r"|CMTI10.*"
+            r"|CMTT10.*"
             r")$"
         )
         if self.translation_config.formular_font_pattern:

{babeldoc-0.2.27 → babeldoc-0.2.29}/babeldoc/high_level.py

@@ -366,6 +366,9 @@ def fix_null_xref(doc: Document) -> None:
             obj = doc.xref_object(i)
             if obj == "null":
                 doc.update_object(i, "[]")
+            elif obj and "/ASCII85Decode" in obj:  # make pdfminer happy
+                data = doc.xref_stream(i)
+                doc.update_stream(i, data)
         except Exception:
             doc.update_object(i, "[]")
 

{babeldoc-0.2.27 → babeldoc-0.2.29}/babeldoc/main.py

@@ -23,7 +23,7 @@ from babeldoc.translation_config import TranslationConfig
 from babeldoc.translation_config import WatermarkOutputMode
 
 logger = logging.getLogger(__name__)
-__version__ = "0.2.27"
+__version__ = "0.2.29"
 
 
 def create_parser():

{babeldoc-0.2.27 → babeldoc-0.2.29}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.2.27"
+version = "0.2.29"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -148,7 +148,7 @@ pythonpath = [".", "src"]
 testpaths = ["tests"]
 
 [bumpver]
-current_version = "0.2.27"
+current_version = "0.2.29"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]

{babeldoc-0.2.27 → babeldoc-0.2.29}/uv.lock

@@ -48,7 +48,7 @@ wheels = [
 
 [[package]]
 name = "babeldoc"
-version = "0.2.27"
+version = "0.2.29"
 source = { editable = "." }
 dependencies = [
     { name = "bitstring" },

babeldoc-0.2.27/babeldoc/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.2.27"