BabelDOC 0.1.6__tar.gz → 0.1.7__tar.gz

babeldoc-0.1.7/.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-0.1.7/.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-0.1.6 → babeldoc-0.1.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.1.6
+Version: 0.1.7
 Summary: Yet Another Document Translator
 Project-URL: Homepage, https://github.com/funstory-ai/BabelDOC
 Project-URL: Issues, https://github.com/funstory-ai/BabelDOC/issues
@@ -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
 

{babeldoc-0.1.6 → babeldoc-0.1.7}/README.md

@@ -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
 

babeldoc-0.1.7/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.1.7"

{babeldoc-0.1.6 → babeldoc-0.1.7}/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-0.1.6 → babeldoc-0.1.7}/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-0.1.6 → babeldoc-0.1.7}/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-0.1.6 → babeldoc-0.1.7}/babeldoc/document_il/midend/il_translator.py

@@ -112,7 +112,7 @@ class ParagraphTranslateTracker:
 
 
 class ILTranslator:
-    stage_name = "翻译段落"
+    stage_name = "Translate Paragraphs"
 
     def __init__(
         self,
@@ -230,6 +230,7 @@ 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 +257,12 @@ 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 +282,11 @@ 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 +342,14 @@ 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)
 

{babeldoc-0.1.6 → babeldoc-0.1.7}/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-0.1.6 → babeldoc-0.1.7}/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-0.1.6 → babeldoc-0.1.7}/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-0.1.6 → babeldoc-0.1.7}/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-0.1.6 → babeldoc-0.1.7}/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-0.1.6 → babeldoc-0.1.7}/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-0.1.6 → babeldoc-0.1.7}/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-0.1.6 → babeldoc-0.1.7}/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"
+__version__ = "0.1.7"
 
 
 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-0.1.6 → babeldoc-0.1.7}/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]
@@ -49,6 +62,7 @@ class ProgressMonitor:
                 stage_current=0,
                 stage_total=total,
             )
+        self.last_report_time = 0.0
         return stage
 
     def __enter__(self):
@@ -66,7 +80,7 @@ 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 +108,20 @@ 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-0.1.6 → babeldoc-0.1.7}/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-0.1.6 → babeldoc-0.1.7}/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-0.1.6 → babeldoc-0.1.7}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.1.6"
+version = "0.1.7"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -117,7 +117,7 @@ dev = [
 ]
 
 [bumpver]
-current_version = "0.1.6"
+current_version = "0.1.7"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]

{babeldoc-0.1.6 → babeldoc-0.1.7}/uv.lock

@@ -38,7 +38,7 @@ wheels = [
 
 [[package]]
 name = "babeldoc"
-version = "0.1.6"
+version = "0.1.7"
 source = { editable = "." }
 dependencies = [
     { name = "bitstring" },

babeldoc-0.1.6/.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-0.1.6/.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-0.1.6/babeldoc/__init__.py

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