feat: Add minimum text length translation parameter

- Introduce `--min-text-length` CLI option to skip translating short texts
- Set default minimum text length to 5 characters
- Update README.md with new CLI parameter documentation
- Implement text length check in translation process

README.md

@@ -123,6 +123,7 @@ uv run babeldoc --bing --files example.pdf --files example2.pdf
 - `--ignore-cache`: Ignore translation cache and force retranslation
 - `--no-dual`: Do not output bilingual PDF files
 - `--no-mono`: Do not output monolingual PDF files
+- `--min-text-length`: Minimum text length to translate (default: 5)
 - `--openai`: Use OpenAI for translation (default: False)
 - `--bing`: Use Bing for translation (default: False)
 - `--google`: Use Google Translate for translation (default: False)

babeldoc/document_il/midend/il_translator.py

@@ -2,7 +2,6 @@
 import json
 import logging
 from pathlib import Path
-from typing import List, Union
 
 from tqdm import tqdm
 
@@ -179,7 +178,7 @@ class TranslateInput:
         def __init__(
             self,
             unicode: str,
-            placeholders: List[Union[RichTextPlaceholder, FormulaPlaceholder]],
+            placeholders: list[RichTextPlaceholder | FormulaPlaceholder],
             base_style: PdfStyle = None,
         ):
             self.unicode = unicode
@@ -489,7 +488,8 @@ def remove_placeholder(text: str):
                 ) and text.replace(" ", "") == "".join(
                     x.char_unicode for x in placeholder.composition.pdf_character
                 ).replace(
-                    " ", ""
+                    " ",
+                    "",
                 ):
                     comp = PdfParagraphComposition(
                         pdf_same_style_characters=placeholder.composition,
@@ -547,6 +547,13 @@ def translate_paragraph(
                 tracker.set_input(translate_input.unicode)
 
                 text = translate_input.unicode
+
+                if len(text) < self.translation_config.min_text_length:
+                    logger.debug(
+                        f"Text too short to translate, skip. Text: {text}. Paragraph id: {paragraph.debug_id}.",
+                    )
+                    return
+
                 translated_text = self.translate_engine.translate(text)
 
                 tracker.set_output(translated_text)

babeldoc/main.py

@@ -75,6 +75,12 @@ def create_parser():
         type=str,
         help="Pages to translate. If not set, translate all pages. like: 1,2,1-,-3,3-5",
     )
+    translation_params.add_argument(
+        "--min-text-length",
+        type=int,
+        default=5,
+        help="Minimum text length to translate (default: 5)",
+    )
     translation_params.add_argument(
         "--lang-in",
         "-li",
@@ -421,6 +427,7 @@ async def main():
             disable_rich_text_translate=args.disable_rich_text_translate,
             enhance_compatibility=args.enhance_compatibility,
             report_interval=args.report_interval,
+            min_text_length=args.min_text_length,
         )
 
         # Create progress handler

babeldoc/translation_config.py

@@ -36,6 +36,7 @@ def __init__(
         disable_rich_text_translate: bool = False,  # 是否禁用富文本翻译
         enhance_compatibility: bool = False,  # 增强兼容性模式
         report_interval: float = 0.1,  # Progress report interval in seconds
+        min_text_length: int = 5,  # Minimum text length to translate
     ):
         self.input_file = input_file
         self.translator = translator
@@ -60,6 +61,7 @@ def __init__(
             disable_rich_text_translate or enhance_compatibility
         )
         self.report_interval = report_interval
+        self.min_text_length = min_text_length
         if progress_monitor:
             if progress_monitor.cancel_event is None:
                 progress_monitor.cancel_event = threading.Event()