BabelDOC 0.2.3__tar.gz → 0.2.5__tar.gz

{babeldoc-0.2.3 → babeldoc-0.2.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.2.3
+Version: 0.2.5
 Summary: Yet Another Document Translator
 Project-URL: Homepage, https://github.com/funstory-ai/BabelDOC
 Project-URL: Issues, https://github.com/funstory-ai/BabelDOC/issues
@@ -138,6 +138,16 @@ uv run babeldoc --files example.pdf --files example2.pdf --openai --openai-model
 
 ## Advanced Options
 
+> [!NOTE]
+> This CLI is mainly for debugging purposes. Although end users can use this CLI to translate files, we do not provide any technical support for this purpose.
+>
+> End users should directly use **Online Service**: Beta version launched [Immersive Translate - BabelDOC](https://app.immersivetranslate.com/babel-doc/) 1000 free pages per month.
+>
+> End users who need self-deployment should use [PDFMathTranslate](https://github.com/Byaidu/PDFMathTranslate)
+> 
+> If you find that an option is not listed below, it means that this option is a debugging option for maintainers. Please do not use these options.
+
+
 ### Language Options
 
 - `--lang-in`, `-li`: Source language code (default: en)
@@ -181,7 +191,7 @@ uv run babeldoc --files example.pdf --files example2.pdf --openai --openai-model
 
 > [!TIP]
 >
-> 1. You must specify one translation service among `--openai`.
+> 1. Currently, only OpenAI-compatible LLM is supported. For more translator support, please use [PDFMathTranslate](https://github.com/Byaidu/PDFMathTranslate).
 > 2. It is recommended to use models with strong compatibility with OpenAI, such as: `glm-4-flash`, `deepseek-chat`, etc.
 > 3. Currently, it has not been optimized for traditional translation engines like Bing/Google, it is recommended to use LLMs.
 

{babeldoc-0.2.3 → babeldoc-0.2.5}/README.md

@@ -100,6 +100,16 @@ uv run babeldoc --files example.pdf --files example2.pdf --openai --openai-model
 
 ## Advanced Options
 
+> [!NOTE]
+> This CLI is mainly for debugging purposes. Although end users can use this CLI to translate files, we do not provide any technical support for this purpose.
+>
+> End users should directly use **Online Service**: Beta version launched [Immersive Translate - BabelDOC](https://app.immersivetranslate.com/babel-doc/) 1000 free pages per month.
+>
+> End users who need self-deployment should use [PDFMathTranslate](https://github.com/Byaidu/PDFMathTranslate)
+> 
+> If you find that an option is not listed below, it means that this option is a debugging option for maintainers. Please do not use these options.
+
+
 ### Language Options
 
 - `--lang-in`, `-li`: Source language code (default: en)
@@ -143,7 +153,7 @@ uv run babeldoc --files example.pdf --files example2.pdf --openai --openai-model
 
 > [!TIP]
 >
-> 1. You must specify one translation service among `--openai`.
+> 1. Currently, only OpenAI-compatible LLM is supported. For more translator support, please use [PDFMathTranslate](https://github.com/Byaidu/PDFMathTranslate).
 > 2. It is recommended to use models with strong compatibility with OpenAI, such as: `glm-4-flash`, `deepseek-chat`, etc.
 > 3. Currently, it has not been optimized for traditional translation engines like Bing/Google, it is recommended to use LLMs.
 

babeldoc-0.2.5/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.2.5"

{babeldoc-0.2.3 → babeldoc-0.2.5}/babeldoc/const.py

@@ -3,7 +3,7 @@ import shutil
 import subprocess
 from pathlib import Path
 
-__version__ = "0.2.3"
+__version__ = "0.2.5"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

{babeldoc-0.2.3 → babeldoc-0.2.5}/babeldoc/document_il/midend/il_translator_llm_only.py

@@ -79,7 +79,13 @@ class ILTranslatorLLMOnly:
         # count total paragraph
         total = sum(
             [
-                len([p for p in page.pdf_paragraph if p.debug_id is not None])
+                len(
+                    [
+                        p
+                        for p in page.pdf_paragraph
+                        if p.debug_id is not None and p.unicode is not None
+                    ]
+                )
                 for page in docs.page
             ]
         )

{babeldoc-0.2.3 → babeldoc-0.2.5}/babeldoc/document_il/midend/paragraph_finder.py

@@ -417,7 +417,7 @@ class ParagraphFinder:
                         ),
                         unicode="",
                         debug_id=generate_base58_id(),
-                        layout_label=prev_composition.layout_label,
+                        layout_label=paragraph.layout_label,
                     )
                     # 更新原段落
                     paragraph.pdf_paragraph_composition = (
@@ -446,7 +446,7 @@ class ParagraphFinder:
                         ),
                         unicode="",
                         debug_id=generate_base58_id(),
-                        layout_label=prev_composition.layout_label,
+                        layout_label=paragraph.layout_label,
                     )
                     # 更新原段落
                     paragraph.pdf_paragraph_composition = (

{babeldoc-0.2.3 → babeldoc-0.2.5}/babeldoc/document_il/midend/typesetting.py

@@ -854,9 +854,15 @@ class Typesetting:
                     ],
                 )
             elif composition.pdf_same_style_unicode_characters:
-                font_id = (
-                    composition.pdf_same_style_unicode_characters.pdf_style.font_id
-                )
+                style = composition.pdf_same_style_unicode_characters.pdf_style
+                if style is None:
+                    logger.warning(
+                        f"Style is None. "
+                        f"Composition: {composition}. "
+                        f"Paragraph: {paragraph}. ",
+                    )
+                    continue
+                font_id = style.font_id
                 font = get_font(font_id, paragraph.xobj_id)
                 result.extend(
                     [
@@ -867,8 +873,8 @@ class Typesetting:
                                 char_unicode,
                             ),
                             original_font=font,
-                            font_size=composition.pdf_same_style_unicode_characters.pdf_style.font_size,
-                            style=composition.pdf_same_style_unicode_characters.pdf_style,
+                            font_size=style.font_size,
+                            style=style,
                             xobj_id=paragraph.xobj_id,
                             debug_info=composition.pdf_same_style_unicode_characters.debug_info,
                         )

{babeldoc-0.2.3 → babeldoc-0.2.5}/babeldoc/document_il/translator/translator.py

@@ -6,7 +6,6 @@ import unicodedata
 from abc import ABC
 from abc import abstractmethod
 
-import httpx
 import openai
 from tenacity import retry
 from tenacity import retry_if_exception_type
@@ -260,52 +259,3 @@ class OpenAITranslator(BaseTranslator):
 
     def get_rich_text_right_placeholder(self, placeholder_id: int):
         return self.get_formular_placeholder(placeholder_id + 1)
-
-
-class TranslateTranslator(BaseTranslator):
-    # https://github.com/openai/openai-python
-    name = "openai"
-
-    def __init__(
-        self,
-        lang_in,
-        lang_out,
-        url=None,
-        ignore_cache=False,
-    ):
-        super().__init__(lang_in, lang_out, ignore_cache)
-        self.client = httpx.Client()
-        self.url = url
-
-    def do_translate(self, text) -> str:
-        response = self.client.post(
-            self.url,
-            json={
-                "text": [text],
-                "src": "Englih",
-                "tgt": "Simplifed Chinese",
-            },
-        )
-        return response.json()["text"][0]
-
-    def prompt(self, text):
-        return [
-            {
-                "role": "system",
-                "content": "You are a professional,authentic machine translation engine.",
-            },
-            {
-                "role": "user",
-                "content": f";; Treat next line as plain text input and translate it into {self.lang_out}, output translation ONLY. If translation is unnecessary (e.g. proper nouns, codes, {'{{1}}, etc. '}), return the original text. NO explanations. NO notes. Input:\n\n{text}",
-            },
-        ]
-
-    def get_formular_placeholder(self, placeholder_id: int):
-        return "{{v" + str(placeholder_id) + "}}"
-        return "{{" + str(placeholder_id) + "}}"
-
-    def get_rich_text_left_placeholder(self, placeholder_id: int):
-        return self.get_formular_placeholder(placeholder_id)
-
-    def get_rich_text_right_placeholder(self, placeholder_id: int):
-        return self.get_formular_placeholder(placeholder_id + 1)

{babeldoc-0.2.3 → babeldoc-0.2.5}/babeldoc/high_level.py

@@ -304,8 +304,11 @@ def do_translate(pm, translation_config):
 
         # 修复 pdf 文件中 xref 为 null 的情况
         for i in range(1, doc_pdf2zh.xref_length()):
-            if doc_pdf2zh.xref_object(i) == "null":
-                doc_pdf2zh.update_object(i, "null")
+            try:
+                if doc_pdf2zh.xref_object(i) == "null":
+                    doc_pdf2zh.update_object(i, "null")
+            except Exception:
+                logger.warning(f"try fix xref {i} fail, continue")
 
         for page in doc_pdf2zh:
             page.insert_font(resfont, None)

{babeldoc-0.2.3 → babeldoc-0.2.5}/babeldoc/main.py

@@ -15,7 +15,6 @@ from rich.progress import TimeRemainingColumn
 import babeldoc.assets.assets
 import babeldoc.high_level
 from babeldoc.document_il.translator.translator import OpenAITranslator
-from babeldoc.document_il.translator.translator import TranslateTranslator
 from babeldoc.document_il.translator.translator import set_translate_rate_limiter
 from babeldoc.docvision.doclayout import DocLayoutModel
 from babeldoc.docvision.rpc_doclayout import RpcDocLayoutModel
@@ -23,7 +22,7 @@ from babeldoc.translation_config import TranslationConfig
 from babeldoc.translation_config import WatermarkOutputMode
 
 logger = logging.getLogger(__name__)
-__version__ = "0.2.3"
+__version__ = "0.2.5"
 
 
 def create_parser():
@@ -194,11 +193,6 @@ def create_parser():
         action="store_true",
         help="Use OpenAI translator.",
     )
-    service_group.add_argument(
-        "--translate",
-        action="store_true",
-        help="Use translate translator.",
-    )
     service_group = parser.add_argument_group(
         "Translation - OpenAI Options",
         description="OpenAI specific options",
@@ -217,14 +211,6 @@ def create_parser():
         "-k",
         help="The API key for the OpenAI API.",
     )
-    service_group = parser.add_argument_group(
-        "Translation - Translate Options",
-        description="Translate specific options",
-    )
-    service_group.add_argument(
-        "--translate-url",
-        help="The base URL for the Translation API.",
-    )
 
     return parser
 
@@ -273,13 +259,6 @@ async def main():
             api_key=args.openai_api_key,
             ignore_cache=args.ignore_cache,
         )
-    elif args.translate:
-        translator = TranslateTranslator(
-            lang_in=args.lang_in,
-            lang_out=args.lang_out,
-            ignore_cache=args.ignore_cache,
-            url=args.translate_url,
-        )
     else:
         raise ValueError("Invalid translator type")
 

{babeldoc-0.2.3 → babeldoc-0.2.5}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.2.3"
+version = "0.2.5"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -136,7 +136,7 @@ pythonpath = [".", "src"]
 testpaths = ["tests"]
 
 [bumpver]
-current_version = "0.2.3"
+current_version = "0.2.5"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]

{babeldoc-0.2.3 → babeldoc-0.2.5}/uv.lock

@@ -48,7 +48,7 @@ wheels = [
 
 [[package]]
 name = "babeldoc"
-version = "0.2.3"
+version = "0.2.5"
 source = { editable = "." }
 dependencies = [
     { name = "bitstring" },

babeldoc-0.2.3/babeldoc/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.2.3"