BabelDOC 0.4.6__tar.gz → 0.4.7__tar.gz

{babeldoc-0.4.6 → babeldoc-0.4.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.4.6
+Version: 0.4.7
 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-0.4.7/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.4.7"

{babeldoc-0.4.6 → babeldoc-0.4.7}/babeldoc/const.py

@@ -3,7 +3,7 @@ import shutil
 import subprocess
 from pathlib import Path
 
-__version__ = "0.4.6"
+__version__ = "0.4.7"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

{babeldoc-0.4.6 → babeldoc-0.4.7}/babeldoc/format/pdf/document_il/backend/pdf_creater.py

@@ -289,7 +289,7 @@ class PDFCreater:
                 )
                 continue
             chars.append(composition.pdf_character)
-        if not chars and paragraph.unicode:
+        if not chars and paragraph.unicode and paragraph.debug_id:
             logger.error(
                 f"Unable to export paragraphs that have "
                 f"not yet been formatted: {paragraph}",

{babeldoc-0.4.6 → babeldoc-0.4.7}/babeldoc/format/pdf/document_il/frontend/il_creater.py

@@ -348,11 +348,14 @@ def parse_font_file(doc, idx, encoding, differences):
     data = doc.xref_stream(idx)
     face = freetype.Face(BytesIO(data))
     scale = 1000 / face.units_per_EM
-    for charmap in face.charmaps:
-        if charmap.encoding_name == "FT_ENCODING_ADOBE_CUSTOM":
-            face.select_charmap(freetype.FT_ENCODING_ADOBE_CUSTOM)
-            break
-    bbox_list = [get_char_cbox(face, x) for x in encoding]
+    enc_name, enc_vector = encoding
+    if enc_name == "Custom":
+        for charmap in face.charmaps:
+            face.select_charmap(charmap.encoding)
+            if charmap.encoding_name == "FT_ENCODING_ADOBE_CUSTOM":
+                face.select_charmap(charmap.encoding)
+                break
+    bbox_list = [get_char_cbox(face, x) for x in enc_vector]
     if differences:
         for code, name in differences:
             bbox_list[code] = get_name_cbox(face, name.encode("U8"))
@@ -765,10 +768,13 @@ class ILCreater:
 
     def parse_font_xobj_id(self, xobj_id: int):
         bbox_list = []
-        encoding = list(range(256))
+        encoding = ("Custom", list(range(256)))
         font_encoding = self.mupdf.xref_get_key(xobj_id, "Encoding")
         if font_encoding[1] == "/WinAnsiEncoding":
-            encoding = WinAnsiEncoding
+            encoding = ("WinAnsi", WinAnsiEncoding)
+        base_encoding = self.mupdf.xref_get_key(xobj_id, "Encoding/BaseEncoding")
+        if base_encoding[1] == "/WinAnsiEncoding":
+            encoding = ("WinAnsi", WinAnsiEncoding)
         differences = []
         font_differences = self.mupdf.xref_get_key(xobj_id, "Encoding/Differences")
         if font_differences:

{babeldoc-0.4.6 → babeldoc-0.4.7}/babeldoc/format/pdf/document_il/midend/il_translator_llm_only.py

@@ -479,9 +479,20 @@ class ILTranslatorLLMOnly:
                     input_unicode = inputs[id_][2].unicode
                     output_unicode = translated_text
 
+                    trimed_input = re.sub(r"[. 。…，]{20,}", ".", output)
+
                     input_token_count = self.calc_token_count(input_unicode)
                     output_token_count = self.calc_token_count(output_unicode)
 
+                    if trimed_input == output_unicode and input_token_count > 20:
+                        llm_translate_tracker.set_error_message(
+                            "Translation result is the same as input, fallback."
+                        )
+                        logger.warning(
+                            "Translation result is the same as input, fallback."
+                        )
+                        continue
+
                     if not (0.3 < output_token_count / input_token_count < 3):
                         llm_translate_tracker.set_error_message(
                             f"Translation result is too long or too short. Input: {input_token_count}, Output: {output_token_count}"

{babeldoc-0.4.6 → babeldoc-0.4.7}/babeldoc/format/pdf/document_il/midend/typesetting.py

@@ -871,7 +871,8 @@ class Typesetting:
                             PdfParagraphComposition(pdf_character=char),
                         )
                 return
-
+            if not paragraph.debug_id:
+                return
             # 如果当前行距大于最小行距，先减小行距
             if line_spacing > min_line_spacing:
                 line_spacing -= 0.1

{babeldoc-0.4.6 → babeldoc-0.4.7}/babeldoc/format/pdf/document_il/utils/layout_helper.py

@@ -710,7 +710,7 @@ def is_text_layout(layout: Layout):
         "figure_caption",
         "table_caption",
         "table_text",
-        "reference",
+        # "reference",
         "title",
         "paragraph_title",
         "abstract",

{babeldoc-0.4.6 → babeldoc-0.4.7}/babeldoc/main.py

@@ -21,7 +21,7 @@ from babeldoc.translator.translator import OpenAITranslator
 from babeldoc.translator.translator import set_translate_rate_limiter
 
 logger = logging.getLogger(__name__)
-__version__ = "0.4.6"
+__version__ = "0.4.7"
 
 
 def create_parser():

{babeldoc-0.4.6 → babeldoc-0.4.7}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.4.6"
+version = "0.4.7"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -157,7 +157,7 @@ pythonpath = [".", "src"]
 testpaths = ["tests"]
 
 [bumpver]
-current_version = "0.4.6"
+current_version = "0.4.7"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]

{babeldoc-0.4.6 → babeldoc-0.4.7}/uv.lock

@@ -48,7 +48,7 @@ wheels = [
 
 [[package]]
 name = "babeldoc"
-version = "0.4.6"
+version = "0.4.7"
 source = { editable = "." }
 dependencies = [
     { name = "bitstring" },

babeldoc-0.4.6/babeldoc/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.4.6"