BabelDOC 0.5.17__tar.gz → 0.5.19__tar.gz

{babeldoc-0.5.17 → babeldoc-0.5.19}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.5.17
+Version: 0.5.19
 Summary: Yet Another Document Translator
 Project-URL: Homepage, https://github.com/funstory-ai/BabelDOC
 Project-URL: Issues, https://github.com/funstory-ai/BabelDOC/issues
@@ -268,6 +268,7 @@ uv run babeldoc --files example.pdf --files example2.pdf --openai --openai-model
 - `--openai-base-url`: Base URL for OpenAI API
 - `--openai-api-key`: API key for OpenAI service
 - `--enable-json-mode-if-requested`: Enable JSON mode for OpenAI requests (default: False)
+- `--term-pool-max-workers`: Maximum number of worker threads dedicated to automatic term extraction. If not specified, this defaults to the value of `--pool-max-workers`, which itself defaults to the QPS value when unset.
 
 > [!TIP]
 >

{babeldoc-0.5.17 → babeldoc-0.5.19}/README.md

@@ -212,6 +212,7 @@ uv run babeldoc --files example.pdf --files example2.pdf --openai --openai-model
 - `--openai-base-url`: Base URL for OpenAI API
 - `--openai-api-key`: API key for OpenAI service
 - `--enable-json-mode-if-requested`: Enable JSON mode for OpenAI requests (default: False)
+- `--term-pool-max-workers`: Maximum number of worker threads dedicated to automatic term extraction. If not specified, this defaults to the value of `--pool-max-workers`, which itself defaults to the QPS value when unset.
 
 > [!TIP]
 >

babeldoc-0.5.19/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.5.19"

{babeldoc-0.5.17 → babeldoc-0.5.19}/babeldoc/const.py

@@ -6,7 +6,7 @@ import subprocess
 import threading
 from pathlib import Path
 
-__version__ = "0.5.17"
+__version__ = "0.5.19"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

{babeldoc-0.5.17 → babeldoc-0.5.19}/babeldoc/format/pdf/document_il/midend/automatic_term_extractor.py

@@ -342,8 +342,12 @@ class AutomaticTermExtractor:
             self.stage_name,
             total,
         ) as pbar:
+            max_workers = self.translation_config.term_pool_max_workers
+            logger.info(
+                f"Using {max_workers} worker threads for automatic term extraction."
+            )
             with PriorityThreadPoolExecutor(
-                max_workers=self.translation_config.pool_max_workers,
+                max_workers=max_workers,
             ) as executor:
                 for page in doc_il.page:
                     self.process_page(page, executor, pbar, tracker.new_page())

{babeldoc-0.5.17 → babeldoc-0.5.19}/babeldoc/format/pdf/document_il/midend/il_translator.py

@@ -978,7 +978,7 @@ class ILTranslator:
 
             if active_glossary_markdown_blocks:
                 llm_input.append(
-                    f"{current_hint_index}. You MUST strictly adhere to the following glossaries. If a source term from a table appears in the text, use the corresponding target term in your translation:"
+                    f"{current_hint_index}. Strictly follow the glossary: use its target terms for all source terms (including variants), do not alter existing translations, and translate any unmatched terms naturally:"
                 )
                 current_hint_index += 1
                 for md_block in active_glossary_markdown_blocks:

{babeldoc-0.5.17 → babeldoc-0.5.19}/babeldoc/format/pdf/document_il/midend/il_translator_llm_only.py

@@ -765,7 +765,7 @@ class ILTranslatorLLMOnly:
 
                 if active_glossary_markdown_blocks:
                     llm_prompt_parts.append(
-                        f"{hint_idx}. You MUST strictly adhere to the following glossaries. please give preference to other glossaries. If a source term from a table appears in the text, use the corresponding target term in your translation:"
+                        f"{hint_idx}. Strictly follow the glossary: use its target terms for all source terms (including variants), do not alter existing translations, and translate any unmatched terms naturally:"
                     )
                     # hint_idx += 1 # No need to increment if tables are part of this point
                     for md_block in active_glossary_markdown_blocks:

{babeldoc-0.5.17 → babeldoc-0.5.19}/babeldoc/format/pdf/translation_config.py

@@ -138,6 +138,8 @@ class TranslationConfig:
     def create_max_pages_per_part_split_strategy(max_pages_per_part: int):
         return PageCountStrategy(max_pages_per_part)
 
+    # for backward compatibility,
+    # new parameters should be added at the end of the function.
     def __init__(
         self,
         translator: BaseTranslator,
@@ -196,6 +198,7 @@ class TranslationConfig:
         skip_formula_offset_calculation: bool = False,
         term_extraction_translator: BaseTranslator | None = None,
         metadata_extra_data: str | None = None,
+        term_pool_max_workers: int | None = None,
     ):
         self.translator = translator
         self.term_extraction_translator = term_extraction_translator or translator
@@ -224,6 +227,13 @@ class TranslationConfig:
         self.pool_max_workers = (
             pool_max_workers if pool_max_workers is not None else qps
         )
+        # Set term_pool_max_workers for automatic term extraction.
+        # If not provided, default to pool_max_workers.
+        self.term_pool_max_workers = (
+            term_pool_max_workers
+            if term_pool_max_workers is not None
+            else self.pool_max_workers
+        )
         self.split_short_lines = split_short_lines
 
         self.short_line_split_factor = short_line_split_factor

{babeldoc-0.5.17 → babeldoc-0.5.19}/babeldoc/main.py

@@ -26,7 +26,7 @@ from babeldoc.translator.translator import OpenAITranslator
 from babeldoc.translator.translator import set_translate_rate_limiter
 
 logger = logging.getLogger(__name__)
-__version__ = "0.5.17"
+__version__ = "0.5.19"
 
 
 def create_parser():
@@ -280,6 +280,11 @@ def create_parser():
         type=int,
         help="Maximum number of worker threads for internal task processing pools. If not specified, defaults to QPS value. This parameter directly sets the worker count, replacing previous QPS-based dynamic calculations.",
     )
+    translation_group.add_argument(
+        "--term-pool-max-workers",
+        type=int,
+        help="Maximum number of worker threads dedicated to automatic term extraction. If not specified, defaults to --pool-max-workers (or QPS value when unset).",
+    )
     translation_group.add_argument(
         "--no-auto-extract-glossary",
         action="store_false",
@@ -694,6 +699,7 @@ async def main():
             figure_table_protection_threshold=args.figure_table_protection_threshold,
             skip_formula_offset_calculation=args.skip_formula_offset_calculation,
             metadata_extra_data=args.metadata_extra_data,
+            term_pool_max_workers=args.term_pool_max_workers,
         )
 
         def nop(_x):

{babeldoc-0.5.17 → babeldoc-0.5.19}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.5.17"
+version = "0.5.19"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -162,7 +162,7 @@ pythonpath = [".", "src"]
 testpaths = ["tests"]
 
 [bumpver]
-current_version = "0.5.17"
+current_version = "0.5.19"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]

babeldoc-0.5.17/babeldoc/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.5.17"