epub-translator 0.0.4__tar.gz → 0.0.5__tar.gz

{epub_translator-0.0.4 → epub_translator-0.0.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: epub-translator
-Version: 0.0.4
+Version: 0.0.5
 Summary: Translate the epub book using LLM. The translated book will retain the original text and list the translated text side by side with the original text.
 License: MIT
 Keywords: epub,llm,translation,translator

{epub_translator-0.0.4 → epub_translator-0.0.5}/epub_translator/translation/translation.py

@@ -1,3 +1,4 @@
+from math import ceil
 from typing import Callable, Iterator, Generator
 from pathlib import Path
 from concurrent.futures import as_completed, ThreadPoolExecutor
@@ -158,7 +159,7 @@ def _translate_texts(
     text_tag="TXT",
     user_data=user_data,
     parser=lambda r: r,
-    max_tokens=texts_tokens * _PLAIN_TEXT_SCALE,
+    max_tokens=ceil(texts_tokens * _PLAIN_TEXT_SCALE),
     params={
       "target_language": language_chinese_name(target_language),
       "user_prompt": user_prompt,
@@ -179,7 +180,7 @@ def _translate_texts(
   return llm.request_xml(
     template_name="format",
     user_data=request_text,
-    max_tokens=texts_tokens * _XML_TEXT_SCALE,
+    max_tokens=ceil(texts_tokens * _XML_TEXT_SCALE),
     parser=lambda r: _parse_translated_response(r, len(texts)),
     params={
       "target_language": language_chinese_name(target_language),

epub_translator-0.0.5/epub_translator/translation/types.py

@@ -0,0 +1,40 @@
+from enum import Enum
+from dataclasses import dataclass
+from resource_segmentation import Incision
+
+
+@dataclass
+class Fragment:
+  text: str
+  start_incision: Incision
+  end_incision: Incision
+
+class Language(Enum):
+  SIMPLIFIED_CHINESE = "zh-Hans"
+  TRADITIONAL_CHINESE = "zh-Hant"
+  ENGLISH = "en"
+  FRENCH = "fr"
+  GERMAN = "de"
+  SPANISH = "es"
+  RUSSIAN = "ru"
+  ITALIAN = "it"
+  PORTUGUESE = "pt"
+  JAPANESE = "ja"
+  KOREAN = "ko"
+
+_LANGUAGE_NAMES = {
+  Language.SIMPLIFIED_CHINESE: "简体中文",
+  Language.TRADITIONAL_CHINESE: "繁体中文",
+  Language.ENGLISH: "英语",
+  Language.FRENCH: "法语",
+  Language.GERMAN: "德语",
+  Language.SPANISH: "西班牙语",
+  Language.RUSSIAN: "俄语",
+  Language.ITALIAN: "意大利语",
+  Language.PORTUGUESE: "葡萄牙语",
+  Language.JAPANESE: "日语",
+  Language.KOREAN: "韩语",
+}
+
+def language_chinese_name(language: Language) -> str:
+  return _LANGUAGE_NAMES[language]

{epub_translator-0.0.4 → epub_translator-0.0.5}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "epub-translator"
-version = "0.0.4"
+version = "0.0.5"
 description = "Translate the epub book using LLM. The translated book will retain the original text and list the translated text side by side with the original text."
 keywords=["epub", "llm", "translation", "translator"]
 authors = [

epub_translator-0.0.4/epub_translator/translation/types.py

@@ -1,49 +0,0 @@
-from enum import Enum
-from dataclasses import dataclass
-from resource_segmentation import Incision
-
-
-@dataclass
-class Fragment:
-  text: str
-  start_incision: Incision
-  end_incision: Incision
-
-class Language(Enum):
-  SIMPLIFIED_CHINESE = "zh-Hans"
-  TRADITIONAL_CHINESE = "zh-Hant"
-  ENGLISH = "en"
-  FRENCH = "fr"
-  GERMAN = "de"
-  SPANISH = "es"
-  RUSSIAN = "ru"
-  ITALIAN = "it"
-  PORTUGUESE = "pt"
-  JAPANESE = "ja"
-  KOREAN = "ko"
-
-def language_chinese_name(language: Language) -> str:
-  if language == Language.SIMPLIFIED_CHINESE:
-    return "简体中文"
-  elif language == Language.TRADITIONAL_CHINESE:
-    return "繁体中文"
-  elif language == Language.ENGLISH:
-    return "英语"
-  elif language == Language.FRENCH:
-    return "法语"
-  elif language == Language.GERMAN:
-    return "德语"
-  elif language == Language.SPANISH:
-    return "西班牙语"
-  elif language == Language.RUSSIAN:
-    return "俄语"
-  elif language == Language.ITALIAN:
-    return "意大利语"
-  elif language == Language.PORTUGUESE:
-    return "葡萄牙语"
-  elif language == Language.JAPANESE:
-    return "日语"
-  elif language == Language.KOREAN:
-    return "韩语"
-  else:
-    raise ValueError(f"Unknown language: {language}")