BabelDOC 0.1.30__tar.gz → 0.1.32__tar.gz

{babeldoc-0.1.30 → babeldoc-0.1.32}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.1.30
+Version: 0.1.32
 Summary: Yet Another Document Translator
 Project-URL: Homepage, https://github.com/funstory-ai/BabelDOC
 Project-URL: Issues, https://github.com/funstory-ai/BabelDOC/issues

babeldoc-0.1.32/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.1.32"

{babeldoc-0.1.30 → babeldoc-0.1.32}/babeldoc/const.py

@@ -2,7 +2,7 @@ import shutil
 import subprocess
 from pathlib import Path
 
-__version__ = "0.1.30"
+__version__ = "0.1.32"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

{babeldoc-0.1.30 → babeldoc-0.1.32}/babeldoc/document_il/frontend/il_creater.py

@@ -1,6 +1,7 @@
 import base64
 import logging
 import re
+from functools import wraps
 
 import pdfminer.pdfinterp
 import pymupdf
@@ -8,6 +9,9 @@ from pdfminer.layout import LTChar
 from pdfminer.layout import LTFigure
 from pdfminer.pdffont import PDFCIDFont
 from pdfminer.pdffont import PDFFont
+from pdfminer.pdfpage import PDFPage as PDFMinerPDFPage
+from pdfminer.pdftypes import PDFObjRef as PDFMinerPDFObjRef
+from pdfminer.pdftypes import resolve1 as pdftypes_resolve1
 from pdfminer.psparser import PSLiteral
 
 from babeldoc.document_il import il_version_1
@@ -16,6 +20,26 @@ from babeldoc.translation_config import TranslationConfig
 logger = logging.getLogger(__name__)
 
 
+def create_hook(func, hook):
+    @wraps(func)
+    def wrapper(*args, **kwargs):
+        hook(*args, **kwargs)
+        return func(*args, **kwargs)
+
+    return wrapper
+
+
+def hook_pdfminer_pdf_page_init(*args):
+    attrs = args[3]
+    while isinstance(attrs["MediaBox"], PDFMinerPDFObjRef):
+        attrs["MediaBox"] = pdftypes_resolve1(attrs["MediaBox"])
+
+
+PDFMinerPDFPage.__init__ = create_hook(
+    PDFMinerPDFPage.__init__, hook_pdfminer_pdf_page_init
+)
+
+
 class ILCreater:
     stage_name = "Parse PDF and Create Intermediate Representation"
 
@@ -313,6 +337,12 @@ class ILCreater:
             pdf_style=pdf_style,
             xobj_id=char.xobj_id,
         )
+        if pdf_style.font_size == 0.0:
+            logger.warning(
+                "Font size is 0.0 for character %s. Skip it.",
+                char_unicode,
+            )
+            return
         self.current_page.pdf_character.append(pdf_char)
 
     def create_il(self):

{babeldoc-0.1.30 → babeldoc-0.1.32}/babeldoc/document_il/midend/styles_and_formulas.py

@@ -479,7 +479,7 @@ class StylesAndFormulas:
         return bool(re.match(r"^[0-9, ]+$", text))
 
     def is_formulas_font(self, font_name: str) -> bool:
-        pattern2 = r"^(Cambria|Cambria-BoldItalic|Cambria-Bold|Cambria-Italic|EUAlbertina.+|NimbusRomNo9L.+)$"
+        pattern2 = r"^(Cambria|Cambria-BoldItalic|Cambria-Bold|Cambria-Italic|EUAlbertina.+|NimbusRomNo9L.+|GlosaMath.+)$"
         if self.translation_config.formular_font_pattern:
             pattern = self.translation_config.formular_font_pattern
         else:

{babeldoc-0.1.30 → babeldoc-0.1.32}/babeldoc/main.py

@@ -25,7 +25,7 @@ from babeldoc.translation_config import TranslationConfig
 from babeldoc.translation_config import WatermarkOutputMode
 
 logger = logging.getLogger(__name__)
-__version__ = "0.1.30"
+__version__ = "0.1.32"
 
 
 def create_parser():

{babeldoc-0.1.30 → babeldoc-0.1.32}/docs/CONTRIBUTING.md

@@ -39,6 +39,8 @@ Please pay special attention to:
 > You can contact the maintainers in the pdf2zh discussion group.
 > 
 > We welcome pull requests and will review your contributions.
+>
+> Sometimes we may not choose to accept your PR, but instead implement the related code ourselves. Please don't be offended if we implement the related code from scratch.
 
 
 1. Fork this repository and clone it locally.

{babeldoc-0.1.30 → babeldoc-0.1.32}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.1.30"
+version = "0.1.32"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -133,7 +133,7 @@ pythonpath = [".", "src"]
 testpaths = ["tests"]
 
 [bumpver]
-current_version = "0.1.30"
+current_version = "0.1.32"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]

{babeldoc-0.1.30 → babeldoc-0.1.32}/uv.lock

@@ -48,7 +48,7 @@ wheels = [
 
 [[package]]
 name = "babeldoc"
-version = "0.1.30"
+version = "0.1.32"
 source = { editable = "." }
 dependencies = [
     { name = "bitstring" },

babeldoc-0.1.30/babeldoc/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.1.30"

{babeldoc-0.1.30 → babeldoc-0.1.32}/babeldoc/document_il/midend/paragraph_finder.py

@@ -307,10 +307,10 @@ class ParagraphFinder:
             "formula_caption",
             "isolate_formula",
             "table_footnote",
-            "table",
-            "figure",
             "table_caption",
             "figure_caption",
+            "table",
+            "figure",
             "abandon",
             "plain text",
             "tiny text",