BabelDOC 0.5.9__tar.gz → 0.5.10__tar.gz

{babeldoc-0.5.9 → babeldoc-0.5.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.5.9
+Version: 0.5.10
 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-0.5.10/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.5.10"

{babeldoc-0.5.9 → babeldoc-0.5.10}/babeldoc/const.py

@@ -3,7 +3,7 @@ import shutil
 import subprocess
 from pathlib import Path
 
-__version__ = "0.5.9"
+__version__ = "0.5.10"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

{babeldoc-0.5.9 → babeldoc-0.5.10}/babeldoc/format/pdf/converter.py

@@ -92,8 +92,10 @@ class PDFConverterEx(PDFConverter):
             text = self.handle_undefined_char(font, cid)
         textwidth = font.char_width(cid)
         textdisp = font.char_disp(cid)
-
-        if not hasattr(font, "xobj_id"):
+        font_id = font.font_id_temp
+        if font_id is not None:
+            pass
+        elif not hasattr(font, "xobj_id"):
             log.debug(
                 f"Font {font.fontname} does not have xobj_id attribute.",
             )

{babeldoc-0.5.9 → babeldoc-0.5.10}/babeldoc/format/pdf/document_il/frontend/il_creater.py

@@ -348,6 +348,7 @@ class ILCreater:
         self.xobj_stack = []
         self.current_page_font_name_id_map = {}
         self.current_page_font_char_bounding_box_map = {}
+        self.current_available_fonts = {}
         self.mupdf_font_map: dict[int, pymupdf.Font] = {}
         self.graphic_state_pool = {}
         self.enable_graphic_element_process = (
@@ -504,15 +505,15 @@ class ILCreater:
             (
                 self.xobj_id,
                 self.current_clip_paths.copy(),
+                self.current_available_fonts.copy(),
             ),
         )
         self.current_clip_paths = []
 
     def pop_xobj(self):
-        (
-            self.xobj_id,
-            self.current_clip_paths,
-        ) = self.xobj_stack.pop()
+        (self.xobj_id, self.current_clip_paths, self.current_available_fonts) = (
+            self.xobj_stack.pop()
+        )
 
     def on_xobj_begin(self, bbox, xref_id):
         logger.debug(f"on_xobj_begin: {bbox} @ {xref_id}")
@@ -529,9 +530,11 @@ class ILCreater:
             ),
             xobj_id=self.xobj_id,
             xref_id=xref_id,
+            pdf_font=[],
         )
         self.current_page.pdf_xobject.append(xobject)
         self.xobj_map[self.xobj_id] = xobject
+        xobject.pdf_font.extend(self.current_available_fonts.values())
         return self.xobj_id
 
     def on_xobj_end(self, xobj_id, base_op):
@@ -719,10 +722,18 @@ class ILCreater:
             else:
                 logger.error("failed to parse font xobj id %d: %s", xref_id, e)
         self.current_page_font_name_id_map[xref_id] = font_id
+        self.current_available_fonts[font_id] = il_font_metadata
+
+        fonts = self.current_page.pdf_font
         if self.xobj_id in self.xobj_map:
-            self.xobj_map[self.xobj_id].pdf_font.append(il_font_metadata)
-        else:
-            self.current_page.pdf_font.append(il_font_metadata)
+            fonts = self.xobj_map[self.xobj_id].pdf_font
+        should_remove = []
+        for f in fonts:
+            if f.font_id == font_id:
+                should_remove.append(f)
+        for sr in should_remove:
+            fonts.remove(sr)
+        fonts.append(il_font_metadata)
 
     def parse_font_xobj_id(self, xobj_id: int):
         if xobj_id is None:

{babeldoc-0.5.9 → babeldoc-0.5.10}/babeldoc/format/pdf/document_il/midend/il_translator_llm_only.py

@@ -912,6 +912,8 @@ class ILTranslatorLLMOnly:
             for llm_translate_tracker in llm_translate_trackers:
                 llm_translate_tracker.set_error_message(error_message)
                 llm_translate_tracker.set_fallback_to_translate()
+            self.total_count += len(llm_translate_trackers)
+            self.fallback_count += len(llm_translate_trackers)
             for input_ in inputs:
                 input_[2].unicode = input_[5]
             if not should_translate_paragraph:

{babeldoc-0.5.9 → babeldoc-0.5.10}/babeldoc/main.py

@@ -22,7 +22,7 @@ from babeldoc.translator.translator import OpenAITranslator
 from babeldoc.translator.translator import set_translate_rate_limiter
 
 logger = logging.getLogger(__name__)
-__version__ = "0.5.9"
+__version__ = "0.5.10"
 
 
 def create_parser():

{babeldoc-0.5.9 → babeldoc-0.5.10}/babeldoc/pdfminer/pdfdevice.py

@@ -107,6 +107,7 @@ class PDFTextDevice(PDFDevice):
         assert self.ctm is not None
         matrix = utils.mult_matrix(textstate.matrix, self.ctm)
         font = textstate.font
+        font.font_id_temp = getattr(textstate, "font_id", None)
         fontsize = textstate.fontsize
         scaling = textstate.scaling * 0.01
         charspace = textstate.charspace * scaling

{babeldoc-0.5.9 → babeldoc-0.5.10}/babeldoc/pdfminer/pdfinterp.py

@@ -1007,6 +1007,7 @@ class PDFPageInterpreter:
         """
         try:
             self.textstate.font = self.fontmap[literal_name(fontid)]
+            self.textstate.font_id = literal_name(fontid)
         except KeyError:
             if settings.STRICT:
                 raise PDFInterpreterError("Undefined Font id: %r" % fontid)

{babeldoc-0.5.9 → babeldoc-0.5.10}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.5.9"
+version = "0.5.10"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -162,7 +162,7 @@ pythonpath = [".", "src"]
 testpaths = ["tests"]
 
 [bumpver]
-current_version = "0.5.9"
+current_version = "0.5.10"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]

babeldoc-0.5.9/babeldoc/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.5.9"