BabelDOC 0.3.44__tar.gz → 0.3.47__tar.gz

babeldoc-0.3.47/.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,65 @@
+### PR Title
+
+<!-- Please fill in a concise and clear PR title below -->
+[PR] <Your concise title here>
+
+### Related Issue(s)
+
+<!-- If this PR closes or is related to one or more issues, please list them here (e.g., #37) -->
+<!-- e.g.: Closes #37, Relates to #42 -->
+
+### Motivation and Context
+
+<!-- Why is this change required? What problem does it solve? -->
+<!-- If it fixes an open issue, please link to the issue here. -->
+
+### Summary of Changes
+
+<!-- What does this PR introduce or fix? Please describe concisely. -->
+
+### PR Type
+
+<!-- What kind of change is this? Please select one or more -->
+- [ ] ✨ Enhancement
+- [ ] 🐛 Bug Fix
+- [ ] 📚 Documentation
+- [ ] 🏗️ Refactor
+- [ ] 🧪 Test
+- [ ] 🧹 Chore
+
+### Breaking Changes
+
+<!-- Does this PR introduce any breaking changes? If so, please describe them. -->
+<!-- - [ ] Yes, this PR introduces breaking changes.
+<!-- - [ ] No, this PR does not introduce breaking changes. -->
+<!-- Detailed description of breaking changes (if any): -->
+
+### Contributor Checklist
+
+- [ ] I have fully read and understood the **[CONTRIBUTING.md](https://funstory-ai.github.io/BabelDOC/CONTRIBUTING/)** guide.
+- [ ] I have performed a self-review of my own code.
+- [ ] My changes follow the project's code style and guidelines
+- [ ] I have linked the related issue(s) in the description above (if applicable)
+- [ ] I have updated relevant documentation (if applicable)
+- [ ] I have added necessary tests that prove my fix is effective or that my feature works (if applicable)
+- [ ] All new and existing tests passed locally with my changes
+- [ ] My changes generate no new warnings or errors
+- [ ] I understand that due to limited maintainer resources, only small PRs are accepted. Suggestions with proof-of-concept patches are appreciated, and my patch may be rewritten if necessary.
+
+### Testing Instructions
+
+<!-- Please provide clear and concise step-by-step instructions on how to test your changes. -->
+<!-- e.g.: -->
+<!-- 1. Check out this branch. -->
+<!-- 2. Run `...` to install dependencies. -->
+<!-- 3. Run `...` to start the application/run the script. -->
+<!-- 4. Navigate to `...` or observe `...` -->
+<!-- 5. Verify that `...` (expected outcome). -->
+
+### Screenshots (if applicable)
+
+<!-- If your changes include UI modifications, please add screenshots or GIFs to show the before and after. -->
+
+### Additional Notes
+
+<!-- Is there anything else the reviewer should know? For example, any dependencies, or potential impacts. --> 

{babeldoc-0.3.44 → babeldoc-0.3.47}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.3.44
+Version: 0.3.47
 Summary: Yet Another Document Translator
 Project-URL: Homepage, https://github.com/funstory-ai/BabelDOC
 Project-URL: Issues, https://github.com/funstory-ai/BabelDOC/issues
@@ -205,6 +205,7 @@ uv run babeldoc --files example.pdf --files example2.pdf --openai --openai-model
 - `--translate-table-text`: Translate table text (experimental, default: False)
 - `--skip-scanned-detection`: Skip scanned document detection (default: False). When using split translation, only the first part performs detection if not skipped.
 - `--ocr-workaround`: Use OCR workaround (default: False). When enabled, the tool will use OCR to detect text and fill background for scanned PDF.
+- `--working-dir`: Working directory for translation. If not set, use temp directory.
 
 > [!TIP]
 > - Both `--skip-clean` and `--dual-translate-first` may help improve compatibility with some PDF readers

{babeldoc-0.3.44 → babeldoc-0.3.47}/README.md

@@ -156,6 +156,7 @@ uv run babeldoc --files example.pdf --files example2.pdf --openai --openai-model
 - `--translate-table-text`: Translate table text (experimental, default: False)
 - `--skip-scanned-detection`: Skip scanned document detection (default: False). When using split translation, only the first part performs detection if not skipped.
 - `--ocr-workaround`: Use OCR workaround (default: False). When enabled, the tool will use OCR to detect text and fill background for scanned PDF.
+- `--working-dir`: Working directory for translation. If not set, use temp directory.
 
 > [!TIP]
 > - Both `--skip-clean` and `--dual-translate-first` may help improve compatibility with some PDF readers

babeldoc-0.3.47/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.3.47"

{babeldoc-0.3.44 → babeldoc-0.3.47}/babeldoc/const.py

@@ -3,7 +3,7 @@ import shutil
 import subprocess
 from pathlib import Path
 
-__version__ = "0.3.44"
+__version__ = "0.3.47"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

{babeldoc-0.3.44 → babeldoc-0.3.47}/babeldoc/document_il/midend/il_translator.py

@@ -649,7 +649,7 @@ class ILTranslator:
                     and re.match(f"^{p.left_regex_pattern}", matched_text)
                 )
                 text = re.match(
-                    f"^{placeholder.left_regex_pattern}(.+){placeholder.right_regex_pattern}$",
+                    f"^{placeholder.left_regex_pattern}(.*){placeholder.right_regex_pattern}$",
                     matched_text,
                 ).group(1)
 

{babeldoc-0.3.44 → babeldoc-0.3.47}/babeldoc/document_il/midend/styles_and_formulas.py

@@ -607,6 +607,9 @@ class StylesAndFormulas:
             r"|.*Mincho.*"
             r"|.*Amerigo.*"
             r"|.*MSGloriolaIIStd.*"
+            r"|.*CMU.+"
+            r"|.*LinLibertine.*"
+            r"|.*txsys.*"
             r")$"
         )
         precise_formula_font_pattern = (
@@ -644,7 +647,7 @@ class StylesAndFormulas:
             r"|.*KpMath.*"
             r"|.*Lete Sans Math.*"
             r"|.*LeteSansMath.*"
-            r"|.*LinLibertineO.*"
+            # r"|.*LinLibertineO.*"
             r"|.*Linux Libertine O.*"
             r"|.*LibertinusMath-Regular.*"
             r"|.*Libertinus Math.*"

{babeldoc-0.3.44 → babeldoc-0.3.47}/babeldoc/main.py

@@ -23,7 +23,7 @@ from babeldoc.translation_config import TranslationConfig
 from babeldoc.translation_config import WatermarkOutputMode
 
 logger = logging.getLogger(__name__)
-__version__ = "0.3.44"
+__version__ = "0.3.47"
 
 
 def create_parser():
@@ -70,6 +70,11 @@ def create_parser():
         default=None,
         help="Restore offline assets package from the specified file",
     )
+    parser.add_argument(
+        "--working-dir",
+        default=None,
+        help="Working directory for translation. If not set, use temp directory.",
+    )
     # translation option argument group
     translation_group = parser.add_argument_group(
         "Translation",
@@ -320,7 +325,7 @@ async def main():
         if not Path(file).exists():
             logger.error(f"文件不存在：{file}")
             exit(1)
-        if not file.endswith(".pdf"):
+        if not file.lower().endswith(".pdf"):
             logger.error(f"文件不是 PDF 文件：{file}")
             exit(1)
         pending_files.append(file)
@@ -339,6 +344,21 @@ async def main():
     else:
         args.output = None
 
+    if args.working_dir:
+        working_dir = Path(args.working_dir)
+        if not working_dir.exists():
+            logger.info(f"工作目录不存在，创建：{working_dir}")
+            try:
+                working_dir.mkdir(parents=True, exist_ok=True)
+            except OSError:
+                logger.critical(
+                    f"Failed to create working directory at {working_dir}",
+                    exc_info=True,
+                )
+                exit(1)
+    else:
+        working_dir = None
+
     watermark_output_mode = WatermarkOutputMode.Watermarked
     if args.no_watermark:
         watermark_output_mode = WatermarkOutputMode.NoWatermark
@@ -390,6 +410,7 @@ async def main():
             skip_scanned_detection=args.skip_scanned_detection,
             ocr_workaround=args.ocr_workaround,
             custom_system_prompt=args.custom_system_prompt,
+            working_dir=working_dir,
         )
 
         # Create progress handler

{babeldoc-0.3.44 → babeldoc-0.3.47}/babeldoc/translation_config.py

@@ -130,6 +130,10 @@ class TranslationConfig:
             else:
                 working_dir = tempfile.mkdtemp()
                 self._is_temp_dir = True
+        else:
+            working_dir = Path(working_dir) / Path(input_file).stem
+            self._is_temp_dir = False
+
         self.working_dir = working_dir
 
         Path(working_dir).mkdir(parents=True, exist_ok=True)

{babeldoc-0.3.44 → babeldoc-0.3.47}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.3.44"
+version = "0.3.47"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -150,7 +150,7 @@ pythonpath = [".", "src"]
 testpaths = ["tests"]
 
 [bumpver]
-current_version = "0.3.44"
+current_version = "0.3.47"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]

{babeldoc-0.3.44 → babeldoc-0.3.47}/uv.lock

@@ -48,7 +48,7 @@ wheels = [
 
 [[package]]
 name = "babeldoc"
-version = "0.3.44"
+version = "0.3.47"
 source = { editable = "." }
 dependencies = [
     { name = "bitstring" },

babeldoc-0.3.44/babeldoc/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.3.44"