BabelDOC 0.3.27__tar.gz → 0.3.29__tar.gz

{babeldoc-0.3.27 → babeldoc-0.3.29}/.github/ISSUE_TEMPLATE/bug_report.yaml

@@ -13,6 +13,10 @@ body:
           required: true
         - label: I confirmed this is not caused by a network issue
           required: true
+        - label: I have fully read and understood the [README](https://github.com/funstory-ai/BabelDOC/blob/main/README.md)
+          required: true
+        - label: I am certain that this issue is with BabelDOC itself and can be reproduced through the BabelDOC cli
+          required: true
 
   - type: markdown
     attributes:

{babeldoc-0.3.27 → babeldoc-0.3.29}/.github/PULL_REQUEST_TEMPLATE/pr_form.yml

@@ -52,7 +52,7 @@ body:
     attributes:
       label: Contributor Checklist
       options:
-        - label: I’ve read the **CONTRIBUTING.md** guide
+        - label: I’ve fully read and understood the **[CONTRIBUTING.md](https://funstory-ai.github.io/BabelDOC/CONTRIBUTING/)** guide
           required: true
         - label: My changes follow the project’s code style and guidelines
           required: true

{babeldoc-0.3.27 → babeldoc-0.3.29}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.3.27
+Version: 0.3.29
 Summary: Yet Another Document Translator
 Project-URL: Homepage, https://github.com/funstory-ai/BabelDOC
 Project-URL: Issues, https://github.com/funstory-ai/BabelDOC/issues
@@ -306,6 +306,10 @@ report-interval = 0.5
 > 1. Before pdf2zh 2.0 is released, you can temporarily use BabelDOC's Python API. However, after pdf2zh 2.0 is released, please directly use pdf2zh's Python API.
 >
 > 2. This project's Python API does not guarantee any compatibility. However, the Python API from pdf2zh will guarantee a certain level of compatibility.
+>
+> 3. We do not provide any technical support for the BabelDOC API.
+>
+> 4. When performing secondary development, please refer to [pdf2zh 2.0 high level](https://github.com/awwaawwa/PDFMathTranslate/blob/v2-rc/pdf2zh/high_level.py) and ensure that BabelDOC runs in a subprocess.
 
 You can refer to the example in [main.py](https://github.com/funstory-ai/yadt/blob/main/babeldoc/main.py) to use BabelDOC's Python API.
 

{babeldoc-0.3.27 → babeldoc-0.3.29}/README.md

@@ -257,6 +257,10 @@ report-interval = 0.5
 > 1. Before pdf2zh 2.0 is released, you can temporarily use BabelDOC's Python API. However, after pdf2zh 2.0 is released, please directly use pdf2zh's Python API.
 >
 > 2. This project's Python API does not guarantee any compatibility. However, the Python API from pdf2zh will guarantee a certain level of compatibility.
+>
+> 3. We do not provide any technical support for the BabelDOC API.
+>
+> 4. When performing secondary development, please refer to [pdf2zh 2.0 high level](https://github.com/awwaawwa/PDFMathTranslate/blob/v2-rc/pdf2zh/high_level.py) and ensure that BabelDOC runs in a subprocess.
 
 You can refer to the example in [main.py](https://github.com/funstory-ai/yadt/blob/main/babeldoc/main.py) to use BabelDOC's Python API.
 

babeldoc-0.3.29/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.3.29"

{babeldoc-0.3.27 → babeldoc-0.3.29}/babeldoc/const.py

@@ -3,7 +3,7 @@ import shutil
 import subprocess
 from pathlib import Path
 
-__version__ = "0.3.27"
+__version__ = "0.3.29"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

{babeldoc-0.3.27 → babeldoc-0.3.29}/babeldoc/document_il/midend/styles_and_formulas.py

@@ -586,6 +586,7 @@ class StylesAndFormulas:
             r"|.*SabonLTPro.*"
             r"|.*ArnoPro.*"
             r"|.*CharisSIL.*"
+            r"|.*MSReference.*"
             r"|.*CMUSerif-Roman.*"
             r"|.*CourierNewPS.*"
             r"|.*XCharter.*"
@@ -604,6 +605,7 @@ class StylesAndFormulas:
             r"|.*Macmillan.*"
             r"|.*NimbusSan.*"
             r"|.*Mincho.*"
+            r"|.*Amerigo.*"
             r")$"
         )
         precise_formula_font_pattern = (

{babeldoc-0.3.27 → babeldoc-0.3.29}/babeldoc/document_il/midend/typesetting.py

@@ -111,8 +111,36 @@ class TypesettingUnit:
             r"\uAB30-\uAB6F"  # Latin Extended E
             r"\u0250-\u02A0"  # IPA Extensions
             r"\u0400-\u04FF"  # Cyrillic
+            r"\u0300-\u036F"  # Combining Diacritical Marks
+            r"\u0500-\u052F"  # Cyrillic Supplement
+            r"\u0370-\u03FF"  # Greek and Coptic
+            r"\u2DE0-\u2DFF"  # Cyrillic Extended-A
+            r"\uA650-\uA69F"  # Cyrillic Extended-B
+            r"\u1200-\u137F"  # Ethiopic
+            r"\u1380-\u139F"  # Ethiopic Supplement
+            r"\u2D80-\u2DDF"  # Ethiopic Extended
+            r"\uAB00-\uAB2F"  # Ethiopic Extended-A
+            r"\U0001E7E0-\U0001E7FF"  # Ethiopic Extended-B
+            r"\u0E80-\u0EFF"  # Lao
+            r"\u0D00-\u0D7F"  # Malayalam
+            r"\u0A80-\u0AFF"  # Gujarati
+            r"\u0E00-\u0E7F"  # Thai
+            r"\u1000-\u109F"  # Myanmar
+            r"\uAA60-\uAA7F"  # Myanmar Extended-A
+            r"\uA9E0-\uA9FF"  # Myanmar Extended-B
+            r"\U000116D0-\U000116FF"  # Myanmar Extended-C
+            r"\u0B80-\u0BFF"  # Tamil
+            r"\u0C00-\u0C7F"  # Telugu
+            r"\u0B00-\u0B7F"  # Oriya
+            r"\u0530-\u058F"  # Armenian
+            r"\u10A0-\u10FF"  # Georgian
+            r"\u1C90-\u1CBF"  # Georgian Extended
+            r"\u2D00-\u2D2F"  # Georgian Supplement
+            r"\u1780-\u17FF"  # Khmer
+            r"\u19E0-\u19FF"  # Khmer Symbols
             r"'"
             r"-"  # Hyphen
+            r"·"  # Middle Dot (U+00B7) For Català
             r"]+$",
             unicode,
         ):
@@ -120,7 +148,7 @@ class TypesettingUnit:
         return True
 
     @property
-    def is_chinese_char(self):
+    def is_cjk_char(self):
         if self.formular:
             return False
         unicode = self.try_get_unicode()
@@ -157,6 +185,30 @@ class TypesettingUnit:
         ]:
             return True
         if unicode:
+            if re.match(
+                r"^["
+                r"\u3000-\u303f"  # CJK Symbols and Punctuation
+                r"\u3040-\u309f"  # Hiragana
+                r"\u30a0-\u30ff"  # Katakana
+                r"\u3100-\u312f"  # Bopomofo
+                r"\uac00-\ud7af"  # Hangul Syllables
+                r"\u1100-\u11ff"  # Hangul Jamo
+                r"\u3130-\u318f"  # Hangul Compatibility Jamo
+                r"\ua960-\ua97f"  # Hangul Jamo Extended-A
+                r"\ud7b0-\ud7ff"  # Hangul Jamo Extended-B
+                r"\u3190-\u319f"  # Kanbun
+                r"\u3200-\u32ff"  # Enclosed CJK Letters and Months
+                r"\u3300-\u33ff"  # CJK Compatibility
+                r"\ufe30-\ufe4f"  # CJK Compatibility Forms
+                r"\u4e00-\u9fff"  # CJK Unified Ideographs
+                r"\u2e80-\u2eff"  # CJK Radicals Supplement
+                r"\u31c0-\u31ef"  # CJK Strokes
+                r"\u2f00-\u2fdf"  # Kangxi Radicals
+                r"\ufe10-\ufe1f"  # Vertical Forms
+                r"]+$",
+                unicode,
+            ):
+                return True
             try:
                 unicodedata_name = unicodedata.name(unicode)
                 return (
@@ -668,7 +720,7 @@ class Typesetting:
 
             if (
                 last_unit  # 有上一个单元
-                and last_unit.is_chinese_char ^ unit.is_chinese_char  # 中英文交界处
+                and last_unit.is_cjk_char ^ unit.is_cjk_char  # 中英文交界处
                 and (
                     last_unit.box
                     and last_unit.box.y

{babeldoc-0.3.27 → babeldoc-0.3.29}/babeldoc/high_level.py

@@ -479,13 +479,23 @@ def do_translate(
                                 part_config.input_file = part_temp_input_path
 
                                 temp_doc = Document()
+                                for x in range(
+                                    split_point.start_page, split_point.end_page + 1
+                                ):
+                                    xref = original_doc[x].xref
+                                    if (
+                                        original_doc.xref_get_key(xref, "Annots")[0]
+                                        != "null"
+                                    ):
+                                        original_doc.xref_set_key(
+                                            xref, "Annots", "null"
+                                        )
                                 temp_doc.insert_pdf(
                                     original_doc,
                                     from_page=split_point.start_page,
                                     to_page=split_point.end_page,
                                 )
                                 temp_doc.save(part_temp_input_path)
-
                                 assert (
                                     temp_doc.page_count
                                     == split_point.end_page - split_point.start_page + 1

{babeldoc-0.3.27 → babeldoc-0.3.29}/babeldoc/main.py

@@ -23,7 +23,7 @@ from babeldoc.translation_config import TranslationConfig
 from babeldoc.translation_config import WatermarkOutputMode
 
 logger = logging.getLogger(__name__)
-__version__ = "0.3.27"
+__version__ = "0.3.29"
 
 
 def create_parser():

{babeldoc-0.3.27 → babeldoc-0.3.29}/docs/CONTRIBUTING.md

@@ -39,6 +39,8 @@ Please pay special attention to:
 > You can contact the maintainers in the pdf2zh discussion group.
 > 
 > Due to the current high rate of code changes, this project only accepts small PRs. If you would like to suggest a change and you include a patch as a proof-of-concept, that would be great. However, please do not be offended if we rewrite your patch from scratch.
+>
+> Please discuss with the maintainers in the [Issue](https://github.com/funstory-ai/BabelDOC/issues) before sending a PR.
 
 [//]: # (> We welcome pull requests and will review your contributions.)
 

{babeldoc-0.3.27 → babeldoc-0.3.29}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.3.27"
+version = "0.3.29"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -150,7 +150,7 @@ pythonpath = [".", "src"]
 testpaths = ["tests"]
 
 [bumpver]
-current_version = "0.3.27"
+current_version = "0.3.29"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]