BabelDOC 0.1.6rc0__tar.gz → 0.1.8__tar.gz

babeldoc-0.1.8/.github/ISSUE_TEMPLATE/bug_report.yaml

@@ -0,0 +1,85 @@
+name: Bug Report
+description: Create a report to help us improve
+labels: ['bug']
+body:
+  - type: checkboxes
+    id: checks
+    attributes:
+      label: Before you asking
+      options:
+      - label: I have searched the existing issues
+        required: true
+      - label: I spend at least 5 minutes for thinking and preparing
+        required: true
+      - label: I have carefully checked the issue, and it is unrelated to the network environment.
+        required: true
+  - type: markdown
+    attributes:
+      value: |
+        Thank you for using this project and providing feedback!
+  - type: textarea
+    id: environment
+    attributes:
+      label: Environment
+      description: |
+        examples:
+          - **OS**: Ubuntu 24.10
+          - **Python**: 3.12.0
+          - **BalbelDOC**: 1.9.0
+      value: |
+          - OS:
+          - Python:
+          - BalbelDOC:
+      render: markdown
+    validations:
+      required: false
+  - type: textarea
+    id: describe
+    attributes:
+      label: Describe the bug
+      description: A clear and concise description of what the bug is.
+    validations:
+      required: true
+  - type: textarea
+    id: reproduce
+    attributes:
+      label: To Reproduce
+      description: Steps to reproduce the behavior
+      value: |
+        1. Go to '...'
+        2. Click on '....'
+        3. Scroll down to '....'
+        4. See error
+    validations:
+      required: false
+  - type: textarea
+    id: expected
+    attributes:
+      label: Expected behavior
+      description: A clear and concise description of what you expected to happen.
+    validations:
+      required: false
+  - type: textarea
+    id: logs
+    attributes:
+      label: Relevant log output and screenshots
+      description: Please copy and paste any relevant log output and screenshots. This will be automatically formatted into code, so no need for backticks.
+      render: Text
+    validations:
+      required: false
+  - type: textarea
+    id: PDFfile
+    attributes:
+      label: Origin PDF file
+      description: |
+        if applicable, attach the input PDF file here.
+    validations:
+      required: false
+  - type: textarea
+    id: others
+    attributes:
+      label: Anything else?
+      description: |
+        Add any other context about the problem here.
+    validations:
+      required: false

babeldoc-0.1.8/.github/ISSUE_TEMPLATE/feature_request.yaml

@@ -0,0 +1,33 @@
+name: Feature request
+description: Suggest an idea for this project
+labels: ['enhancement']
+body:
+  - type: textarea
+    id: describe
+    attributes:
+      label: Is your feature request related to a problem?
+      description: A clear and concise description of what the problem is
+      placeholder: Ex. I'm always frustrated when ...
+    validations:
+      required: false
+  - type: textarea
+    id: solution
+    attributes:
+      label: Describe the solution you'd like
+      description: A clear and concise description of what you want to happen
+    validations:
+      required: false
+  - type: textarea
+    id: 
+    attributes:
+      label: Describe alternatives you've considered
+      description: A clear and concise description of any alternative solutions or features you've considered.
+    validations:
+      required: false
+  - type: textarea
+    id: additional
+    attributes:
+      label: Additional context
+      description: Add any other projects about the feature request here.
+    validations:
+      required: false

{babeldoc-0.1.6rc0 → babeldoc-0.1.8}/.github/workflows/publish-to-pypi.yml

@@ -82,7 +82,7 @@ jobs:
     runs-on: ubuntu-latest
     environment:
       name: pypi
-      url: https://pypi.org/p/yadt
+      url: https://pypi.org/p/BabelDOC
 
     permissions:
       id-token: write
@@ -106,7 +106,7 @@ jobs:
     runs-on: ubuntu-latest
     environment:
       name: testpypi
-      url: https://test.pypi.org/p/yadt
+      url: https://test.pypi.org/p/BabelDOC
 
     permissions:
       id-token: write

{babeldoc-0.1.6rc0 → babeldoc-0.1.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.1.6rc0
+Version: 0.1.8
 Summary: Yet Another Document Translator
 Project-URL: Homepage, https://github.com/funstory-ai/BabelDOC
 Project-URL: Issues, https://github.com/funstory-ai/BabelDOC/issues
@@ -12,7 +12,7 @@ Classifier: Programming Language :: Python :: 3
 Requires-Python: <3.13,>=3.10
 Requires-Dist: bitstring>=4.3.0
 Requires-Dist: configargparse>=1.7
-Requires-Dist: httpx>=0.27.0
+Requires-Dist: httpx[socks]>=0.27.0
 Requires-Dist: huggingface-hub>=0.27.0
 Requires-Dist: msgpack>=1.1.0
 Requires-Dist: numpy>=2.0.2
@@ -40,15 +40,15 @@ Description-Content-Type: text/markdown
 
 <p>
   <!-- PyPI -->
-  <a href="https://pypi.org/project/babeldoc/">
-    <img src="https://img.shields.io/pypi/v/babeldoc"></a>
-  <a href="https://pepy.tech/projects/babeldoc">
-    <img src="https://static.pepy.tech/badge/babeldoc"></a>
-  <!-- <a href="https://github.com/funstory-ai/babeldoc/pulls">
+  <a href="https://pypi.org/project/BabelDOC/">
+    <img src="https://img.shields.io/pypi/v/BabelDOC"></a>
+  <a href="https://pepy.tech/projects/BabelDOC">
+    <img src="https://static.pepy.tech/badge/BabelDOC"></a>
+  <!-- <a href="https://github.com/funstory-ai/BabelDOC/pulls">
     <img src="https://img.shields.io/badge/contributions-welcome-green"></a> -->
   <!-- License -->
   <a href="./LICENSE">
-    <img src="https://img.shields.io/github/license/funstory-ai/babeldoc"></a>
+    <img src="https://img.shields.io/github/license/funstory-ai/BabelDOC"></a>
   <a href="https://t.me/+Z9_SgnxmsmA5NzBl">
     <img src="https://img.shields.io/badge/Telegram-2CA5E0?style=flat-squeare&logo=telegram&logoColor=white"></a>
 </p>
@@ -77,7 +77,7 @@ We recommend using the Tool feature of [uv](https://github.com/astral-sh/uv) to
 2. Use the following command to install yadt:
 
 ```bash
-uv tool install --python 3.12 babeldoc
+uv tool install --python 3.12 BabelDOC
 
 babeldoc --help
 ```
@@ -101,10 +101,10 @@ We still recommend using [uv](https://github.com/astral-sh/uv) to manage virtual
 
 ```bash
 # clone the project
-git clone https://github.com/funstory-ai/yadt
+git clone https://github.com/funstory-ai/BabelDOC
 
 # enter the project directory
-cd babeldoc
+cd BabelDOC
 
 # install dependencies and run babeldoc
 uv run babeldoc --help
@@ -140,10 +140,14 @@ uv run babeldoc --bing --files example.pdf --files example2.pdf
 - `--short-line-split-factor`: Split threshold factor (default: 0.8). The actual threshold is the median length of all lines on the current page \* this factor
 - `--skip-clean`: Skip PDF cleaning step
 - `--dual-translate-first`: Put translated pages first in dual PDF mode (default: original pages first)
+- `--disable-rich-text-translate`: Disable rich text translation (may help improve compatibility with some PDFs)
+- `--enhance-compatibility`: Enable all compatibility enhancement options (equivalent to --skip-clean --dual-translate-first --disable-rich-text-translate)
 
 > [!TIP]
 > - Both `--skip-clean` and `--dual-translate-first` may help improve compatibility with some PDF readers
+> - `--disable-rich-text-translate` can also help with compatibility by simplifying translation input
 > - However, using `--skip-clean` will result in larger file sizes
+> - If you encounter any compatibility issues, try using `--enhance-compatibility` first
 
 ### Translation Service Options
 
@@ -167,10 +171,16 @@ uv run babeldoc --bing --files example.pdf --files example2.pdf
 - `--openai-base-url`: Base URL for OpenAI API
 - `--openai-api-key`: API key for OpenAI service
 
+> [!TIP]
+>
+> 1. This tool supports any OpenAI-compatible API endpoints. Just set the correct base URL and API key. (e.g. `https://xxx.custom.xxx/v1`)
+> 2. For local models like Ollama, you can use any value as the API key (e.g. `--openai-api-key a`).
+
 ### Output Control
 
 - `--output`, `-o`: Output directory for translated files. If not set, use current working directory.
 - `--debug`, `-d`: Enable debug logging level and export detailed intermediate results in `~/.cache/yadt/working`.
+- `--report-interval`: Progress report interval in seconds (default: 0.1).
 
 ### Configuration File
 
@@ -264,6 +274,8 @@ We encourage you to contribute to YADT! Please check out the [CONTRIBUTING](http
 
 Everyone interacting in YADT and its sub-projects' codebases, issue trackers, chat rooms, and mailing lists is expected to follow the YADT [Code of Conduct](https://github.com/funstory-ai/yadt/blob/main/docs/CODE_OF_CONDUCT.md).
 
+[Immersive Translation](https://immersivetranslate.com) sponsors monthly Pro membership redemption codes for active contributors to this project, see details at: [CONTRIBUTOR_REWARD.md](https://github.com/funstory-ai/BabelDOC/blob/main/docs/CONTRIBUTOR_REWARD.md)
+
 ## Acknowledgements
 
 - [PDFMathTranslate](https://github.com/Byaidu/PDFMathTranslate)
@@ -276,8 +288,8 @@ Everyone interacting in YADT and its sub-projects' codebases, issue trackers, ch
 
 <a href="https://star-history.com/#funstory-ai/babeldoc&Date">
  <picture>
-   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=funstory-ai/yadt&type=Date&theme=dark" />
-   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=funstory-ai/yadt&type=Date" />
-   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=funstory-ai/yadt&type=Date"/>
+   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=funstory-ai/babeldoc&type=Date&theme=dark" />
+   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=funstory-ai/babeldoc&type=Date" />
+   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=funstory-ai/babeldoc&type=Date"/>
  </picture>
 </a>

{babeldoc-0.1.6rc0 → babeldoc-0.1.8}/README.md

@@ -8,15 +8,15 @@
 
 <p>
   <!-- PyPI -->
-  <a href="https://pypi.org/project/babeldoc/">
-    <img src="https://img.shields.io/pypi/v/babeldoc"></a>
-  <a href="https://pepy.tech/projects/babeldoc">
-    <img src="https://static.pepy.tech/badge/babeldoc"></a>
-  <!-- <a href="https://github.com/funstory-ai/babeldoc/pulls">
+  <a href="https://pypi.org/project/BabelDOC/">
+    <img src="https://img.shields.io/pypi/v/BabelDOC"></a>
+  <a href="https://pepy.tech/projects/BabelDOC">
+    <img src="https://static.pepy.tech/badge/BabelDOC"></a>
+  <!-- <a href="https://github.com/funstory-ai/BabelDOC/pulls">
     <img src="https://img.shields.io/badge/contributions-welcome-green"></a> -->
   <!-- License -->
   <a href="./LICENSE">
-    <img src="https://img.shields.io/github/license/funstory-ai/babeldoc"></a>
+    <img src="https://img.shields.io/github/license/funstory-ai/BabelDOC"></a>
   <a href="https://t.me/+Z9_SgnxmsmA5NzBl">
     <img src="https://img.shields.io/badge/Telegram-2CA5E0?style=flat-squeare&logo=telegram&logoColor=white"></a>
 </p>
@@ -45,7 +45,7 @@ We recommend using the Tool feature of [uv](https://github.com/astral-sh/uv) to
 2. Use the following command to install yadt:
 
 ```bash
-uv tool install --python 3.12 babeldoc
+uv tool install --python 3.12 BabelDOC
 
 babeldoc --help
 ```
@@ -69,10 +69,10 @@ We still recommend using [uv](https://github.com/astral-sh/uv) to manage virtual
 
 ```bash
 # clone the project
-git clone https://github.com/funstory-ai/yadt
+git clone https://github.com/funstory-ai/BabelDOC
 
 # enter the project directory
-cd babeldoc
+cd BabelDOC
 
 # install dependencies and run babeldoc
 uv run babeldoc --help
@@ -108,10 +108,14 @@ uv run babeldoc --bing --files example.pdf --files example2.pdf
 - `--short-line-split-factor`: Split threshold factor (default: 0.8). The actual threshold is the median length of all lines on the current page \* this factor
 - `--skip-clean`: Skip PDF cleaning step
 - `--dual-translate-first`: Put translated pages first in dual PDF mode (default: original pages first)
+- `--disable-rich-text-translate`: Disable rich text translation (may help improve compatibility with some PDFs)
+- `--enhance-compatibility`: Enable all compatibility enhancement options (equivalent to --skip-clean --dual-translate-first --disable-rich-text-translate)
 
 > [!TIP]
 > - Both `--skip-clean` and `--dual-translate-first` may help improve compatibility with some PDF readers
+> - `--disable-rich-text-translate` can also help with compatibility by simplifying translation input
 > - However, using `--skip-clean` will result in larger file sizes
+> - If you encounter any compatibility issues, try using `--enhance-compatibility` first
 
 ### Translation Service Options
 
@@ -135,10 +139,16 @@ uv run babeldoc --bing --files example.pdf --files example2.pdf
 - `--openai-base-url`: Base URL for OpenAI API
 - `--openai-api-key`: API key for OpenAI service
 
+> [!TIP]
+>
+> 1. This tool supports any OpenAI-compatible API endpoints. Just set the correct base URL and API key. (e.g. `https://xxx.custom.xxx/v1`)
+> 2. For local models like Ollama, you can use any value as the API key (e.g. `--openai-api-key a`).
+
 ### Output Control
 
 - `--output`, `-o`: Output directory for translated files. If not set, use current working directory.
 - `--debug`, `-d`: Enable debug logging level and export detailed intermediate results in `~/.cache/yadt/working`.
+- `--report-interval`: Progress report interval in seconds (default: 0.1).
 
 ### Configuration File
 
@@ -232,6 +242,8 @@ We encourage you to contribute to YADT! Please check out the [CONTRIBUTING](http
 
 Everyone interacting in YADT and its sub-projects' codebases, issue trackers, chat rooms, and mailing lists is expected to follow the YADT [Code of Conduct](https://github.com/funstory-ai/yadt/blob/main/docs/CODE_OF_CONDUCT.md).
 
+[Immersive Translation](https://immersivetranslate.com) sponsors monthly Pro membership redemption codes for active contributors to this project, see details at: [CONTRIBUTOR_REWARD.md](https://github.com/funstory-ai/BabelDOC/blob/main/docs/CONTRIBUTOR_REWARD.md)
+
 ## Acknowledgements
 
 - [PDFMathTranslate](https://github.com/Byaidu/PDFMathTranslate)
@@ -244,8 +256,8 @@ Everyone interacting in YADT and its sub-projects' codebases, issue trackers, ch
 
 <a href="https://star-history.com/#funstory-ai/babeldoc&Date">
  <picture>
-   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=funstory-ai/yadt&type=Date&theme=dark" />
-   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=funstory-ai/yadt&type=Date" />
-   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=funstory-ai/yadt&type=Date"/>
+   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=funstory-ai/babeldoc&type=Date&theme=dark" />
+   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=funstory-ai/babeldoc&type=Date" />
+   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=funstory-ai/babeldoc&type=Date"/>
  </picture>
 </a>

babeldoc-0.1.8/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.1.8"

{babeldoc-0.1.6rc0 → babeldoc-0.1.8}/babeldoc/document_il/backend/pdf_creater.py

@@ -14,7 +14,7 @@ logger = logging.getLogger(__name__)
 
 
 class PDFCreater:
-    stage_name = "创建PDF文件"
+    stage_name = "Create PDF file"
 
     def __init__(
         self,
@@ -176,7 +176,8 @@ class PDFCreater:
             page_op = BitStream()
             # q {ops_base}Q 1 0 0 1 {x0} {y0} cm {ops_new}
             page_op.append(b"q ")
-            page_op.append(base_op)
+            if base_op is not None:
+                page_op.append(base_op)
             page_op.append(b" Q ")
             page_op.append(
                 f"q Q 1 0 0 1 {page.cropbox.box.x} {page.cropbox.box.y} cm \n".encode(),
@@ -375,7 +376,13 @@ class PDFCreater:
                 dual = pymupdf.open(self.original_pdf_path)
                 if translation_config.debug:
                     translation_config.raise_if_cancelled()
-                    self.write_debug_info(dual, translation_config)
+                    try:
+                        self.write_debug_info(dual, translation_config)
+                    except Exception:
+                        logger.warning(
+                            "Failed to write debug info to dual PDF",
+                            exc_info=True,
+                        )
                 dual.insert_file(pdf)
                 page_count = pdf.page_count
                 for page_id in range(page_count):

{babeldoc-0.1.6rc0 → babeldoc-0.1.8}/babeldoc/document_il/frontend/il_creater.py

@@ -17,7 +17,7 @@ logger = logging.getLogger(__name__)
 
 
 class ILCreater:
-    stage_name = "解析PDF并创建中间表示"
+    stage_name = "Parse PDF and Create Intermediate Representation"
 
     def __init__(self, translation_config: TranslationConfig):
         self.progress = None

{babeldoc-0.1.6rc0 → babeldoc-0.1.8}/babeldoc/document_il/midend/add_debug_information.py

@@ -11,7 +11,7 @@ logger = logging.getLogger(__name__)
 
 
 class AddDebugInformation:
-    stage_name = "添加DEBUG信息"
+    stage_name = "Add Debug Information"
 
     def __init__(self, translation_config: TranslationConfig):
         self.translation_config = translation_config

{babeldoc-0.1.6rc0 → babeldoc-0.1.8}/babeldoc/document_il/midend/il_translator.py

@@ -2,6 +2,7 @@ import concurrent.futures
 import json
 import logging
 from pathlib import Path
+from typing import List, Union
 
 from tqdm import tqdm
 
@@ -112,7 +113,7 @@ class ParagraphTranslateTracker:
 
 
 class ILTranslator:
-    stage_name = "翻译段落"
+    stage_name = "Translate Paragraphs"
 
     def __init__(
         self,
@@ -178,7 +179,7 @@ class ILTranslator:
         def __init__(
             self,
             unicode: str,
-            placeholders: [RichTextPlaceholder | FormulaPlaceholder],
+            placeholders: List[Union[RichTextPlaceholder, FormulaPlaceholder]],
             base_style: PdfStyle = None,
         ):
             self.unicode = unicode
@@ -230,6 +231,7 @@ class ILTranslator:
         self,
         paragraph: PdfParagraph,
         page_font_map: dict[str, PdfFont] = None,
+        disable_rich_text_translate: bool | None = None,
     ):
         if not paragraph.pdf_paragraph_composition:
             return
@@ -256,6 +258,12 @@ class ILTranslator:
                 )
                 return None
 
+        # 如果没有指定 disable_rich_text_translate，使用配置中的值
+        if disable_rich_text_translate is None:
+            disable_rich_text_translate = (
+                self.translation_config.disable_rich_text_translate
+            )
+
         placeholder_id = 1
         placeholders = []
         chars = []
@@ -275,6 +283,11 @@ class ILTranslator:
             elif composition.pdf_character:
                 chars.append(composition.pdf_character)
             elif composition.pdf_same_style_characters:
+                if disable_rich_text_translate:
+                    # 如果禁用富文本翻译，直接添加字符
+                    chars.extend(composition.pdf_same_style_characters.pdf_character)
+                    continue
+
                 fonta = self.font_mapper.map(
                     page_font_map[
                         composition.pdf_same_style_characters.pdf_style.font_id
@@ -330,6 +343,14 @@ class ILTranslator:
                 )
                 return None
 
+        # 如果占位符数量超过50，且未禁用富文本翻译，则递归调用并禁用富文本翻译
+        if len(placeholders) > 50 and not disable_rich_text_translate:
+            logger.warning(
+                f"Too many placeholders ({len(placeholders)}) in paragraph[{paragraph.debug_id}], "
+                "disabling rich text translation for this paragraph",
+            )
+            return self.get_translate_input(paragraph, page_font_map, True)
+
         text = get_char_unicode_string(chars)
         return self.TranslateInput(text, placeholders, paragraph.pdf_style)
 
@@ -467,7 +488,9 @@ class ILTranslator:
                     PdfSameStyleCharacters,
                 ) and text.replace(" ", "") == "".join(
                     x.char_unicode for x in placeholder.composition.pdf_character
-                ).replace(" ", ""):
+                ).replace(
+                    " ", ""
+                ):
                     comp = PdfParagraphComposition(
                         pdf_same_style_characters=placeholder.composition,
                     )

{babeldoc-0.1.6rc0 → babeldoc-0.1.8}/babeldoc/document_il/midend/layout_parser.py

@@ -13,7 +13,7 @@ logger = logging.getLogger(__name__)
 
 
 class LayoutParser:
-    stage_name = "解析页面布局"
+    stage_name = "Parse Page Layout"
 
     def __init__(self, translation_config: TranslationConfig):
         self.translation_config = translation_config

{babeldoc-0.1.6rc0 → babeldoc-0.1.8}/babeldoc/document_il/midend/paragraph_finder.py

@@ -26,7 +26,7 @@ def generate_base58_id(length: int = 5) -> str:
 
 
 class ParagraphFinder:
-    stage_name = "解析段落"
+    stage_name = "Parse Paragraphs"
 
     def __init__(self, translation_config: TranslationConfig):
         self.translation_config = translation_config

{babeldoc-0.1.6rc0 → babeldoc-0.1.8}/babeldoc/document_il/midend/remove_descent.py

@@ -9,7 +9,7 @@ logger = logging.getLogger(__name__)
 
 
 class RemoveDescent:
-    stage_name = "移除字体下沉"
+    stage_name = "Remove Char Descent"
 
     def __init__(self, translation_config: TranslationConfig):
         self.translation_config = translation_config

{babeldoc-0.1.6rc0 → babeldoc-0.1.8}/babeldoc/document_il/midend/styles_and_formulas.py

@@ -22,7 +22,7 @@ from babeldoc.translation_config import TranslationConfig
 
 
 class StylesAndFormulas:
-    stage_name = "解析公式与样式"
+    stage_name = "Parse Formulas and Styles"
 
     def __init__(self, translation_config: TranslationConfig):
         self.translation_config = translation_config

{babeldoc-0.1.6rc0 → babeldoc-0.1.8}/babeldoc/document_il/midend/typesetting.py

@@ -355,7 +355,7 @@ class TypesettingUnit:
 
 
 class Typesetting:
-    stage_name = "排版"
+    stage_name = "Typesetting"
 
     def __init__(self, translation_config: TranslationConfig):
         self.font_mapper = FontMapper(translation_config)
@@ -397,7 +397,7 @@ class Typesetting:
             font_size=6,
             graphic_state=il_version_1.GraphicState(),
         )
-        text = "本文档由funstory.ai的开源PDF翻译库yadt(http://yadt.io)翻译，本仓库正在积极的建设当中，欢迎star和关注。"
+        text = "本文档由funstory.ai的开源PDF翻译库BabelDOC(http://yadt.io)翻译，本仓库正在积极的建设当中，欢迎star和关注。"
         if self.translation_config.debug:
             text += "\n 当前为DEBUG模式，将显示更多辅助信息。请注意，部分框的位置对应原文，但在译文中可能不正确。"
         page.pdf_paragraph.append(

{babeldoc-0.1.6rc0 → babeldoc-0.1.8}/babeldoc/document_il/translator/cache.py

@@ -8,6 +8,8 @@ from peewee import Model
 from peewee import SqliteDatabase
 from peewee import TextField
 
+from babeldoc.const import CACHE_FOLDER as cache_folder
+
 # we don't init the database here
 db = SqliteDatabase(None)
 
@@ -92,7 +94,6 @@ class TranslationCache:
 
 
 def init_db(remove_exists=False):
-    cache_folder = Path.home() / ".cache" / "pdf2zh"
     cache_folder.mkdir(parents=True, exist_ok=True)
     # The current version does not support database migration, so add the version number to the file name.
     cache_db_path = cache_folder / "cache.v1.db"

{babeldoc-0.1.6rc0 → babeldoc-0.1.8}/babeldoc/document_il/utils/fontmap.py

@@ -13,7 +13,7 @@ logger = logging.getLogger(__name__)
 
 
 class FontMapper:
-    stage_name = "添加字体"
+    stage_name = "Add Fonts"
 
     def __init__(self, translation_config: TranslationConfig):
         self.font_names = [

{babeldoc-0.1.6rc0 → babeldoc-0.1.8}/babeldoc/docvision/rpc_doclayout.py

@@ -75,7 +75,8 @@ def predict_layout(
                 "Content-Type": "application/msgpack",
                 "Accept": "application/msgpack",
             },
-            timeout=30,
+            timeout=300,
+            follow_redirects=True,
         )
 
         logger.debug(f"Response status: {response.status_code}")

{babeldoc-0.1.6rc0 → babeldoc-0.1.8}/babeldoc/high_level.py

@@ -287,6 +287,7 @@ async def async_translate(translation_config: TranslationConfig):
         finish_event=finish_event,
         cancel_event=cancel_event,
         loop=loop,
+        report_interval=translation_config.report_interval,
     ) as pm:
         future = loop.run_in_executor(None, do_translate, pm, translation_config)
         try:

{babeldoc-0.1.6rc0 → babeldoc-0.1.8}/babeldoc/main.py

@@ -20,7 +20,7 @@ from babeldoc.document_il.translator.translator import set_translate_rate_limite
 from babeldoc.translation_config import TranslationConfig
 
 logger = logging.getLogger(__name__)
-__version__ = "0.1.6.rc0"
+__version__ = "0.1.8"
 
 
 def create_parser():
@@ -158,6 +158,24 @@ def create_parser():
         action="store_true",
         help="Put translated pages first in dual PDF mode",
     )
+    translation_params.add_argument(
+        "--disable-rich-text-translate",
+        default=False,
+        action="store_true",
+        help="Disable rich text translation (may help improve compatibility with some PDFs)",
+    )
+    translation_params.add_argument(
+        "--enhance-compatibility",
+        default=False,
+        action="store_true",
+        help="Enable all compatibility enhancement options (equivalent to --skip-clean --dual-translate-first --disable-rich-text-translate)",
+    )
+    translation_params.add_argument(
+        "--report-interval",
+        type=float,
+        default=0.1,
+        help="Progress report interval in seconds (default: 0.1)",
+    )
     service_params = translation_params.add_mutually_exclusive_group()
     service_params.add_argument(
         "--openai",
@@ -400,6 +418,9 @@ async def main():
             doc_layout_model=doc_layout_model,
             skip_clean=args.skip_clean,
             dual_translate_first=args.dual_translate_first,
+            disable_rich_text_translate=args.disable_rich_text_translate,
+            enhance_compatibility=args.enhance_compatibility,
+            report_interval=args.report_interval,
         )
 
         # Create progress handler

{babeldoc-0.1.6rc0 → babeldoc-0.1.8}/babeldoc/progress_monitor.py

@@ -24,6 +24,7 @@ class ProgressMonitor:
         self.progress_change_callback = progress_change_callback
         self.finish_callback = finish_callback
         self.report_interval = report_interval
+        logger.debug(f"report_interval: {self.report_interval}")
         self.last_report_time = 0
         self.finish_stage_count = 0
         self.finish_event = finish_event
@@ -31,6 +32,18 @@ class ProgressMonitor:
         self.loop = loop
         if finish_event and not loop:
             raise ValueError("finish_event requires a loop")
+        if self.progress_change_callback:
+            self.progress_change_callback(
+                type="stage_summary",
+                stages=[
+                    {
+                        "name": name,
+                        "percent": 1.0 / len(stages),
+                    }
+                    for name in stages
+                ],
+            )
+        self.lock = threading.Lock()
 
     def stage_start(self, stage_name: str, total: int):
         stage = self.stage[stage_name]
@@ -48,7 +61,9 @@ class ProgressMonitor:
                 stage_progress=0.0,
                 stage_current=0,
                 stage_total=total,
+                overall_progress=self.calculate_current_progress(),
             )
+        self.last_report_time = 0.0
         return stage
 
     def __enter__(self):
@@ -66,7 +81,7 @@ class ProgressMonitor:
             self.finish_callback(type="error", error=CancelledError)
 
     def stage_done(self, stage):
-        self.last_report_time = 0
+        self.last_report_time = 0.0
         self.finish_stage_count += 1
         if (
             stage.current != stage.total
@@ -94,19 +109,20 @@ class ProgressMonitor:
         return progress
 
     def stage_update(self, stage, n: int):
-        if (
-            self.progress_change_callback
-            and time.time() - self.last_report_time > self.report_interval
-        ):
-            self.progress_change_callback(
-                type="progress_update",
-                stage=stage.display_name,
-                stage_progress=stage.current * 100 / stage.total,
-                stage_current=stage.current,
-                stage_total=stage.total,
-                overall_progress=self.calculate_current_progress(stage),
-            )
-            self.last_report_time = time.time()
+        with self.lock:
+            report_time_delta = time.time() - self.last_report_time
+            if report_time_delta < self.report_interval:
+                return
+            if self.progress_change_callback:
+                self.progress_change_callback(
+                    type="progress_update",
+                    stage=stage.display_name,
+                    stage_progress=stage.current * 100 / stage.total,
+                    stage_current=stage.current,
+                    stage_total=stage.total,
+                    overall_progress=self.calculate_current_progress(stage),
+                )
+                self.last_report_time = time.time()
 
     def translate_done(self, translate_result):
         if self.finish_callback:

{babeldoc-0.1.6rc0 → babeldoc-0.1.8}/babeldoc/translation_config.py

@@ -33,6 +33,9 @@ class TranslationConfig:
         doc_layout_model=None,
         skip_clean: bool = False,
         dual_translate_first: bool = False,
+        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
     ):
         self.input_file = input_file
         self.translator = translator
@@ -51,8 +54,12 @@ class TranslationConfig:
         self.short_line_split_factor = short_line_split_factor
         self.use_rich_pbar = use_rich_pbar
         self.progress_monitor = progress_monitor
-        self.skip_clean = skip_clean
-        self.dual_translate_first = dual_translate_first
+        self.skip_clean = skip_clean or enhance_compatibility
+        self.dual_translate_first = dual_translate_first or enhance_compatibility
+        self.disable_rich_text_translate = (
+            disable_rich_text_translate or enhance_compatibility
+        )
+        self.report_interval = report_interval
         if progress_monitor:
             if progress_monitor.cancel_event is None:
                 progress_monitor.cancel_event = threading.Event()

{babeldoc-0.1.6rc0 → babeldoc-0.1.8}/docs/CONTRIBUTING.md

@@ -40,7 +40,7 @@ Please pay special attention to:
 
 
 1. Fork this repository and clone it locally.
-2. Use `doc/deploy.sh` to set up the development  environment.
+2. Use `doc/deploy.sh` to set up the development environment.
 3. Create a new branch and make code changes on that branch. `git checkout -b feature/<feature-name>`
 4. Perform development and ensure the code meets the requirements.
 
@@ -72,6 +72,8 @@ git commit -m "<semantic commit message>"
 
 - Use the `uv run yadt` command for development and testing.
 
+- When you need print log, please use `log.debug()` to print info. **DO NOT USE `print()`**
+
 - Code formatting
 
 3. Dependency Updates

babeldoc-0.1.8/docs/CONTRIBUTOR_REWARD.md

@@ -0,0 +1,81 @@
+# BabelDOC/PDFMathTranslate 贡献者奖励规则
+
+### **月度活跃贡献者奖励规则**
+**一、资格标准**
+1. **贡献类型要求**
+   - 需提交 **至少 1 个有效 PR**（Pull Request），或进行 **PR 审核、文档编写** 等贡献。
+   - 有效贡献定义：
+     - 非简单的文档错别字修复
+     - 非简单的代码格式化调整（如仅调整缩进、空格等）
+     - 需做出实质性贡献（如功能开发、Bug 修复、性能优化、架构调整、技术文档编写、PR 审核等）
+   - 示例合格贡献：新增功能模块、修复逻辑错误、优化算法效率、编写技术文档等
+
+2. **时间范围**
+   - 每月 1 日至月末最后一天合并的 PR 计入当月统计
+
+**二、申请流程**
+1. **申请条件**
+   - PR 需被成功合并至[funstory-ai/BabelDOC](https://github.com/funstory-ai/BabelDOC/pulls) 仓库或 [Byaidu/PDFMathTranslate](https://github.com/Byaidu/PDFMathTranslate/pulls)的主分支。
+   - 审核 PR、撰写 wiki 等贡献也必须是以上两个仓库。
+   - 同一贡献者每月仅可申请一次（无论提交 PR 数量）
+   - 同一贡献者每月最多可以获得 1 个兑换码
+   - 对于 PR，只有发起者可以申请兑换码
+   - 仅可使用当月的贡献申请兑换码（特殊情况请联系 aw@funstory.ai 说明）
+
+2. **申请方式**
+   - 发送邮件至 **aw@funstory.ai**
+   - 邮件标题格式：`[贡献者会员兑换码申请] GitHub用户名-月份`（例：`[贡献者会员兑换码申请] awwaawwa-2024-07`）
+   - 邮件正文需包含：
+     - GitHub 用户名
+     - 合并 PR 的完整链接
+   - 附件要求：
+     - PR 页面完整截图（需包含合并状态、仓库名称及点击头像后弹出来的侧边栏，如下图所示）
+
+![附件示例](images/contributor_reward_example.png)
+
+3. **奖励说明**
+   - 奖励内容：[沉浸式翻译（Immersive Translate）](https://immersivetranslate.com/zh-Hans/pricing/)月度会员兑换码
+   - 兑换码使用：在[沉浸式翻译官网兑换页](https://immersivetranslate.com/zh-Hans/exchange)输入即可激活
+   - 会员权益：沉浸式翻译 Pro 会员一个月（详见[官网价格页](https://immersivetranslate.com/zh-Hans/pricing/)说明）
+   - 兑换码为专属福利，不可转让
+
+**三、审核与发放**
+1. **审核周期**
+   - 我们会尽力在收到申请邮件后 1 个工作日内完成审核
+   - 审核时间可能因申请数量、审核复杂度等因素有所延长
+   - 审核通过后，兑换码将通过邮件方式发送
+   - 若审核未通过，我们会通过邮件说明原因
+
+2. 兑换码规则：
+   - 使用方式：[官网兑换页](https://immersivetranslate.com/zh-Hans/exchange)输入兑换码激活
+   - 权益内容：月度会员（具体权益见[官网价格页](https://immersivetranslate.com/zh-Hans/pricing/)说明）
+   - 不可转让
+
+**四、注意事项**
+1. **禁止行为**
+   - 将完整功能拆分为多个无关 PR 提交
+   - 提交质量不合格或具有潜在危害的代码
+   - 提供虚假或误导性的申请材料
+
+2. **特别说明**
+   - funstory.ai 保留对贡献价值的评估权、规则的最终解释权等所有必要权利
+   - 规则如有更新，将提前 1 天在 [BabelDOC GitHub PR](https://github.com/funstory-ai/BabelDOC/pulls) 公告
+   - 过期未使用的兑换码不予补发
+   - 自 2025 年 2 月 1 日起的贡献可以申请兑换码
+   - 为了确认您是 Pull Request (PR) 的发起者，防止他人冒领，我们可能会要求您使用发起者账号在 PR 下方留言指定的随机数字。
+
+
+---
+### **常见问题解答（FAQ）**
+
+Q：如何判断文档翻译贡献是否有效？
+A：系统性的人工翻译（如完整章节的翻译并经过人工校对）视为有效贡献。零散段落翻译或仅依赖机器翻译的内容不计入有效贡献。
+
+Q：兑换码过期了可以补发吗？
+A：为确保公平性，过期的兑换码将不予补发，请在有效期内及时使用。
+
+Q：为什么这个文档是中文的？
+A：因为目前应该是中文贡献者多吧，所以就先写中文的。后面再撰写英文版的。
+
+---
+**规则公示**：本规则文档存放于 BabelDOC 仓库 [CONTRIBUTOR_REWARD.md](https://github.com/funstory-ai/BabelDOC/blob/main/docs/CONTRIBUTOR_REWARD.md)。

{babeldoc-0.1.6rc0 → babeldoc-0.1.8}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.1.6.rc0"
+version = "0.1.8"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -13,7 +13,7 @@ keywords = ["PDF"]
 dependencies = [
     "bitstring>=4.3.0",
     "configargparse>=1.7",
-    "httpx>=0.27.0",
+    "httpx[socks]>=0.27.0",
     "huggingface-hub>=0.27.0",
     "numpy>=2.0.2",
     "onnx>=1.17.0",
@@ -117,7 +117,7 @@ dev = [
 ]
 
 [bumpver]
-current_version = "0.1.6.rc0"
+current_version = "0.1.8"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]

{babeldoc-0.1.6rc0 → babeldoc-0.1.8}/uv.lock

@@ -1,4 +1,5 @@
 version = 1
+revision = 1
 requires-python = ">=3.10, <3.13"
 resolution-markers = [
     "python_full_version >= '3.12' and sys_platform == 'darwin'",
@@ -38,12 +39,12 @@ wheels = [
 
 [[package]]
 name = "babeldoc"
-version = "0.1.6rc0"
+version = "0.1.8"
 source = { editable = "." }
 dependencies = [
     { name = "bitstring" },
     { name = "configargparse" },
-    { name = "httpx" },
+    { name = "httpx", extra = ["socks"] },
     { name = "huggingface-hub" },
     { name = "msgpack" },
     { name = "numpy" },
@@ -72,7 +73,7 @@ dev = [
 requires-dist = [
     { name = "bitstring", specifier = ">=4.3.0" },
     { name = "configargparse", specifier = ">=1.7" },
-    { name = "httpx", specifier = ">=0.27.0" },
+    { name = "httpx", extras = ["socks"], specifier = ">=0.27.0" },
     { name = "huggingface-hub", specifier = ">=0.27.0" },
     { name = "msgpack", specifier = ">=1.1.0" },
     { name = "numpy", specifier = ">=2.0.2" },
@@ -489,6 +490,11 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/2a/39/e50c7c3a983047577ee07d2a9e53faf5a69493943ec3f6a384bdc792deb2/httpx-0.28.1-py3-none-any.whl", hash = "sha256:d909fcccc110f8c7faf814ca82a9a4d816bc5a6dbfea25d6591d6985b8ba59ad", size = 73517 },
 ]
 
+[package.optional-dependencies]
+socks = [
+    { name = "socksio" },
+]
+
 [[package]]
 name = "huggingface-hub"
 version = "0.27.1"
@@ -1245,6 +1251,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/e9/44/75a9c9421471a6c4805dbf2356f7c181a29c1879239abab1ea2cc8f38b40/sniffio-1.3.1-py3-none-any.whl", hash = "sha256:2f6da418d1f1e0fddd844478f41680e794e6051915791a034ff65e5f100525a2", size = 10235 },
 ]
 
+[[package]]
+name = "socksio"
+version = "1.0.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/f8/5c/48a7d9495be3d1c651198fd99dbb6ce190e2274d0f28b9051307bdec6b85/socksio-1.0.0.tar.gz", hash = "sha256:f88beb3da5b5c38b9890469de67d0cb0f9d494b78b106ca1845f96c10b91c4ac", size = 19055 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/37/c3/6eeb6034408dac0fa653d126c9204ade96b819c936e136c5e8a6897eee9c/socksio-1.0.0-py3-none-any.whl", hash = "sha256:95dc1f15f9b34e8d7b16f06d74b8ccf48f609af32ab33c608d08761c5dcbb1f3", size = 12763 },
+]
+
 [[package]]
 name = "sympy"
 version = "1.13.3"

babeldoc-0.1.6rc0/.github/ISSUE_TEMPLATE/bug_report.md

@@ -1,34 +0,0 @@
----
-name: Bug report
-about: Create a report to help us improve
-title: ''
-labels: 'bug'
-assignees: ''
-
----
-
-**Describe the bug**
-A clear and concise description of what the bug is.
-
-**To Reproduce**
-Steps to reproduce the behavior:
-1. Go to '...'
-2. Click on '....'
-3. Scroll down to '....'
-4. See error
-
-**Expected behavior**
-A clear and concise description of what you expected to happen.
-
-**Screenshots**
-If applicable, add screenshots to help explain your problem.
-
-**Desktop (please complete the following information):**
- - OS: [e.g. macOS Sequoia 15.3, Windows 11]
- - Version [e.g. 0.1.0]
-
-**Input PDF file:**
-if applicable, attach the input PDF file here.
-
-**Additional context**
-Add any other context about the problem here.

babeldoc-0.1.6rc0/.github/ISSUE_TEMPLATE/feature_request.md

@@ -1,20 +0,0 @@
----
-name: Feature request
-about: Suggest an idea for this project
-title: ''
-labels: 'enhancement'
-assignees: ''
-
----
-
-**Is your feature request related to a problem? Please describe.**
-A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
-
-**Describe the solution you'd like**
-A clear and concise description of what you want to happen.
-
-**Describe alternatives you've considered**
-A clear and concise description of any alternative solutions or features you've considered.
-
-**Additional context**
-Add any other context or screenshots about the feature request here.

babeldoc-0.1.6rc0/babeldoc/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.1.6.rc0"