BabelDOC 0.3.4__tar.gz → 0.3.5__tar.gz

babeldoc-0.3.5/.github/ISSUE_TEMPLATE/bug_report.yaml

@@ -0,0 +1,86 @@
+name: "🐞 Bug Report"
+description: Create a report to help us improve
+labels: ['bug']
+body:
+  - type: checkboxes
+    id: checks
+    attributes:
+      label: Before you submit
+      options:
+        - label: I have searched existing issues
+          required: true
+        - label: I spent at least 5 minutes investigating and preparing this report
+          required: true
+        - label: I confirmed this is not caused by a network issue
+          required: true
+
+  - type: markdown
+    attributes:
+      value: |
+        Thank you for using **BabelDOC** and helping us improve it! 🙏
+
+  - type: textarea
+    id: environment
+    attributes:
+      label: Environment
+      description: Provide your system details (required)
+      value: |
+        - OS:
+        - Python:
+        - BabelDOC:
+      render: markdown
+    validations:
+      required: true
+
+  - 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: Steps to Reproduce
+      description: Help us reproduce the issue
+      value: |
+        1. Go to '...'
+        2. Click on '...'
+        3. See error
+    validations:
+      required: false
+
+  - type: textarea
+    id: expected
+    attributes:
+      label: Expected Behavior
+      description: What did you expect to happen?
+    validations:
+      required: false
+
+  - type: textarea
+    id: logs
+    attributes:
+      label: Relevant Log Output or Screenshots
+      description: Copy and paste any logs or attach screenshots. This will be formatted automatically.
+      render: text
+    validations:
+      required: false
+
+  - type: file
+    id: pdf
+    attributes:
+      label: Original PDF File
+      description: Upload the input PDF if applicable.
+    validations:
+      required: false
+
+  - type: textarea
+    id: others
+    attributes:
+      label: Additional Context
+      description: Anything else we should know?
+    validations:
+      required: false

{babeldoc-0.3.4 → babeldoc-0.3.5}/.github/ISSUE_TEMPLATE/feature_request.yaml

@@ -1,33 +1,41 @@
-name: Feature request
-description: Suggest an idea for this project
+name: "✨ Feature Request"
+description: Suggest a new idea or improvement for BabelDOC
 labels: ['enhancement']
 body:
+  - type: markdown
+    attributes:
+      value: |
+        Thank you for helping improve **BabelDOC**! Please fill out the form below to suggest a feature.
+
   - 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
+      description: If applicable, describe what problem this feature would solve.
       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
+      description: What would you like to see happen?
     validations:
-      required: false
+      required: true
+
   - type: textarea
-    id: 
+    id: alternatives
     attributes:
       label: Describe alternatives you've considered
-      description: A clear and concise description of any alternative solutions or features you've considered.
+      description: Have you thought of other ways to solve this?
     validations:
       required: false
+
   - type: textarea
     id: additional
     attributes:
       label: Additional context
-      description: Add any other projects about the feature request here.
+      description: Any other context, examples, or screenshots?
     validations:
-      required: false
+      required: false

babeldoc-0.3.5/.github/PULL_REQUEST_TEMPLATE/pr_form.yml

@@ -0,0 +1,92 @@
+name: Pull Request
+description: Submit a pull request to contribute to BabelDOC
+title: "[PR] <Your concise title here>"
+labels:
+  - needs triage
+body:
+  - type: markdown
+    attributes:
+      value: |
+        ## 👋 Thanks for contributing to **BabelDOC**!
+
+        Please fill out this form to help us review your pull request effectively.
+
+  - type: input
+    id: issue
+    attributes:
+      label: Related Issue(s)
+      description: If this pull request closes or is related to one or more issues, list them here (e.g., #37)
+      placeholder: "#37"
+    validations:
+      required: false
+
+  - type: textarea
+    id: summary
+    attributes:
+      label: Description
+      description: Describe the purpose of this pull request and what was changed.
+      placeholder: |
+        - What does this PR introduce or fix?
+        - What is the motivation behind it?
+    validations:
+      required: true
+
+  - type: dropdown
+    id: pr_type
+    attributes:
+      label: PR Type
+      description: What kind of change is this?
+      multiple: true
+      options:
+        - enhancement
+        - bug
+        - documentation
+        - refactor
+        - test
+        - chore
+    validations:
+      required: true
+
+  - type: checkboxes
+    id: checklist
+    attributes:
+      label: Contributor Checklist
+      options:
+        - label: I’ve read the **CONTRIBUTING.md** guide
+          required: true
+        - label: My changes follow the project’s code style and guidelines
+          required: true
+        - label: I’ve linked the related issue(s) in the description above
+        - label: I’ve updated relevant documentation (if applicable)
+        - label: I’ve added necessary tests (if applicable)
+        - label: All new and existing tests passed locally
+        - label: I understand that due to limited maintainer resources, only small pull requests are accepted. Suggestions with proof-of-concept patches are appreciated, and my patch may be rewritten if necessary.
+
+  - type: textarea
+    id: testing
+    attributes:
+      label: Testing Instructions
+      description: Provide step-by-step instructions on how to test your changes
+      placeholder: |
+        1. Run `...`
+        2. Visit `...`
+        3. Click `...`
+        4. Verify `...`
+    validations:
+      required: false
+
+  - type: textarea
+    id: screenshots
+    attributes:
+      label: Screenshots (if applicable)
+      description: If UI changes were made, please attach before/after screenshots.
+    validations:
+      required: false
+
+  - type: textarea
+    id: notes
+    attributes:
+      label: Additional Notes
+      description: Anything else the reviewer should know?
+    validations:
+      required: false

{babeldoc-0.3.4 → babeldoc-0.3.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.3.4
+Version: 0.3.5
 Summary: Yet Another Document Translator
 Project-URL: Homepage, https://github.com/funstory-ai/BabelDOC
 Project-URL: Issues, https://github.com/funstory-ai/BabelDOC/issues
@@ -72,6 +72,9 @@ Description-Content-Type: text/markdown
   <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>
+
+<a href="https://trendshift.io/repositories/13358" target="_blank"><img src="https://trendshift.io/api/badge/repositories/13358" alt="funstory-ai%2FBabelDOC | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+
 </div>
 
 PDF scientific paper translation and bilingual comparison library.
@@ -211,6 +214,7 @@ uv run babeldoc --files example.pdf --files example2.pdf --openai --openai-model
 > 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.
+> 4. You can use [litellm](https://github.com/BerriAI/litellm) to access multiple models.
 
 ### OpenAI Specific Options
 

{babeldoc-0.3.4 → babeldoc-0.3.5}/README.md

@@ -26,6 +26,9 @@
   <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>
+
+<a href="https://trendshift.io/repositories/13358" target="_blank"><img src="https://trendshift.io/api/badge/repositories/13358" alt="funstory-ai%2FBabelDOC | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+
 </div>
 
 PDF scientific paper translation and bilingual comparison library.
@@ -165,6 +168,7 @@ uv run babeldoc --files example.pdf --files example2.pdf --openai --openai-model
 > 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.
+> 4. You can use [litellm](https://github.com/BerriAI/litellm) to access multiple models.
 
 ### OpenAI Specific Options
 

babeldoc-0.3.5/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.3.5"

{babeldoc-0.3.4 → babeldoc-0.3.5}/babeldoc/const.py

@@ -3,7 +3,7 @@ import shutil
 import subprocess
 from pathlib import Path
 
-__version__ = "0.3.4"
+__version__ = "0.3.5"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

{babeldoc-0.3.4 → babeldoc-0.3.5}/babeldoc/document_il/frontend/il_creater.py

@@ -1,4 +1,5 @@
 import base64
+import functools
 import logging
 import re
 from functools import wraps
@@ -180,6 +181,7 @@ class ILCreater:
         self.xobj_stack = []
         self.current_page_font_name_id_map = {}
         self.current_page_font_char_bounding_box_map = {}
+        self.mupdf_font_map: dict[int, pymupdf.Font] = {}
 
     def on_finish(self):
         self.progress.__exit__(None, None, None)
@@ -364,11 +366,20 @@ class ILCreater:
                 else:
                     encoding_length = 1
         try:
-            mupdf_font = pymupdf.Font(fontbuffer=self.mupdf.extract_font(xref_id)[3])
+            if xref_id in self.mupdf_font_map:
+                mupdf_font = self.mupdf_font_map[xref_id]
+            else:
+                mupdf_font = pymupdf.Font(
+                    fontbuffer=self.mupdf.extract_font(xref_id)[3]
+                )
+                mupdf_font.has_glyph = functools.lru_cache(maxsize=10240, typed=True)(
+                    mupdf_font.has_glyph,
+                )
             bold = mupdf_font.is_bold
             italic = mupdf_font.is_italic
             monospaced = mupdf_font.is_monospaced
             serif = mupdf_font.is_serif
+            self.mupdf_font_map[xref_id] = mupdf_font
         except Exception:
             bold = None
             italic = None
@@ -547,6 +558,15 @@ class ILCreater:
             font_size=char.size,
             graphic_state=gs,
         )
+
+        if font:
+            font_xref_id = font.xref_id
+            if font_xref_id in self.mupdf_font_map:
+                mupdf_font = self.mupdf_font_map[font_xref_id]
+                # if "(cid:" not in char_unicode:
+                #     if mupdf_cid := mupdf_font.has_glyph(ord(char_unicode)):
+                #         char_id = mupdf_cid
+
         pdf_char = il_version_1.PdfCharacter(
             box=bbox,
             pdf_character_id=char_id,

{babeldoc-0.3.4 → babeldoc-0.3.5}/babeldoc/document_il/midend/il_translator.py

@@ -449,11 +449,11 @@ class ILTranslator:
         combined_placeholder_pattern = "|".join(placeholder_patterns)
 
         def remove_placeholder(text: str):
-            return re.sub(combined_placeholder_pattern, "", text)
+            return re.sub(combined_placeholder_pattern, "", text, flags=re.IGNORECASE)
 
         # 找到所有匹配
         last_end = 0
-        for match in re.finditer(combined_pattern, output):
+        for match in re.finditer(combined_pattern, output, flags=re.IGNORECASE):
             # 处理匹配之前的普通文本
             if match.start() > last_end:
                 text = output[last_end : match.start()]

{babeldoc-0.3.4 → babeldoc-0.3.5}/babeldoc/document_il/midend/styles_and_formulas.py

@@ -547,6 +547,7 @@ class StylesAndFormulas:
             r"|.*FranklinGothic.*"
             r"|.*AGaramondPro.*"
             r"|.*PalatinoItalCOR.*"
+            r"|.*ITCSymbolStd.*"
             r")$"
         )
         if self.translation_config.formular_font_pattern:

{babeldoc-0.3.4 → babeldoc-0.3.5}/babeldoc/document_il/utils/fontmap.py

@@ -60,11 +60,6 @@ class FontMapper:
             f.font_id: f for f in self.fonts.values()
         }
 
-        for font in self.fontid2font.values():
-            font.char_lengths = functools.lru_cache(maxsize=10240, typed=True)(
-                font.char_lengths,
-            )
-
         self.fontid2font["base"] = self.fontid2font[self.base_font_ids[0]]
 
         self.normal_fonts: list[pymupdf.Font] = [

{babeldoc-0.3.4 → babeldoc-0.3.5}/babeldoc/high_level.py

@@ -381,7 +381,7 @@ def do_translate(
         original_pdf_path = translation_config.input_file
         logger.info(f"start to translate: {original_pdf_path}")
         start_time = time.time()
-
+        peak_memory_usage = 0
         with MemoryMonitor() as memory_monitor:
             # Check if split translation is enabled
             if not translation_config.split_strategy:
@@ -504,6 +504,7 @@ def do_translate(
                         logger.info("start merge results")
                         result = merger.merge_results(results)
                         logger.info("finish merge results")
+            peak_memory_usage = memory_monitor.peak_memory_usage
 
         finish_time = time.time()
         result.total_seconds = finish_time - start_time
@@ -512,6 +513,7 @@ def do_translate(
             f"finish translate: {original_pdf_path}, cost: {finish_time - start_time} s",
         )
         result.original_pdf_path = translation_config.input_file
+        result.peak_memory_usage = peak_memory_usage
         pm.translate_done(result)
         return result
 

{babeldoc-0.3.4 → babeldoc-0.3.5}/babeldoc/main.py

@@ -23,7 +23,7 @@ from babeldoc.translation_config import TranslationConfig
 from babeldoc.translation_config import WatermarkOutputMode
 
 logger = logging.getLogger(__name__)
-__version__ = "0.3.4"
+__version__ = "0.3.5"
 
 
 def create_parser():

{babeldoc-0.3.4 → babeldoc-0.3.5}/babeldoc/translation_config.py

@@ -256,6 +256,7 @@ class TranslateResult:
     dual_pdf_path: str | None
     no_watermark_mono_pdf_path: str | None
     no_watermark_dual_pdf_path: str | None
+    peak_memory_usage: int | None
 
     def __init__(self, mono_pdf_path: str | None, dual_pdf_path: str | None):
         self.mono_pdf_path = mono_pdf_path
@@ -299,6 +300,9 @@ class TranslateResult:
                 f"\tNo-watermark Dual-language PDF: {self.no_watermark_dual_pdf_path}"
             )
 
+        if hasattr(self, "peak_memory_usage") and self.peak_memory_usage:
+            result.append(f"\tPeak memory usage: {self.peak_memory_usage} MB")
+
         if result:
             result.insert(0, "Translation results:")
 

{babeldoc-0.3.4 → babeldoc-0.3.5}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.3.4"
+version = "0.3.5"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -148,7 +148,7 @@ pythonpath = [".", "src"]
 testpaths = ["tests"]
 
 [bumpver]
-current_version = "0.3.4"
+current_version = "0.3.5"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]

{babeldoc-0.3.4 → babeldoc-0.3.5}/uv.lock

@@ -48,7 +48,7 @@ wheels = [
 
 [[package]]
 name = "babeldoc"
-version = "0.3.4"
+version = "0.3.5"
 source = { editable = "." }
 dependencies = [
     { name = "bitstring" },

babeldoc-0.3.4/.github/ISSUE_TEMPLATE/bug_report.yaml

@@ -1,85 +0,0 @@
-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-0.3.4/babeldoc/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.3.4"