BabelDOC 0.3.56__tar.gz → 0.3.58__tar.gz

{babeldoc-0.3.56 → babeldoc-0.3.58}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.3.56
+Version: 0.3.58
 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-0.3.58/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.3.58"

{babeldoc-0.3.56 → babeldoc-0.3.58}/babeldoc/const.py

@@ -3,7 +3,7 @@ import shutil
 import subprocess
 from pathlib import Path
 
-__version__ = "0.3.56"
+__version__ = "0.3.58"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

{babeldoc-0.3.56 → babeldoc-0.3.58}/babeldoc/document_il/backend/pdf_creater.py

@@ -781,10 +781,10 @@ class PDFCreater:
             return False
 
     def restore_media_box(self, doc: pymupdf.Document, mediabox_data: dict) -> None:
-        for pageno, page_box_data in mediabox_data.items():
+        for xref, page_box_data in mediabox_data.items():
             for name, box in page_box_data.items():
                 try:
-                    doc.xref_set_key(doc[pageno].xref, name, box)
+                    doc.xref_set_key(xref, name, box)
                 except Exception:
                     logger.debug(f"Error restoring media box {name} from PDF")
 

{babeldoc-0.3.56 → babeldoc-0.3.58}/babeldoc/document_il/midend/automatic_term_extractor.py

@@ -185,6 +185,7 @@ class AutomaticTermExtractor:
         total_token_count = 0
         for paragraph in page.pdf_paragraph:
             if paragraph.debug_id is None or paragraph.unicode is None:
+                pbar.advance(1)
                 continue
             if is_cid_paragraph(paragraph):
                 pbar.advance(1)
@@ -253,7 +254,7 @@ class AutomaticTermExtractor:
                         )
 
         except Exception as e:
-            logger.error(f"Error preparing LLM prompt for automatic terms extract: {e}")
+            logger.error(f"Error during automatic terms extract: {e}")
             return
         finally:
             pbar.advance(len(paragraphs.paragraphs))

{babeldoc-0.3.56 → babeldoc-0.3.58}/babeldoc/document_il/midend/il_translator.py

@@ -346,7 +346,7 @@ class ILTranslator:
             placeholder, regex_pattern = placeholder
         else:
             regex_pattern = re.escape(placeholder)
-        if placeholder in paragraph.unicode:
+        if re.match(regex_pattern, paragraph.unicode, re.IGNORECASE):
             return self.create_formula_placeholder(formula, formula_id + 1, paragraph)
 
         return FormulaPlaceholder(formula_id, formula, placeholder, regex_pattern)
@@ -371,9 +371,10 @@ class ILTranslator:
             right_placeholder, right_placeholder_regex_pattern = right_placeholder
         else:
             right_placeholder_regex_pattern = re.escape(right_placeholder)
-        if (
-            left_placeholder in paragraph.unicode
-            or right_placeholder in paragraph.unicode
+        if re.match(
+            f"{left_placeholder_regex_pattern}|{right_placeholder_regex_pattern}",
+            paragraph.unicode,
+            re.IGNORECASE,
         ):
             return self.create_rich_text_placeholder(
                 composition,
@@ -630,7 +631,8 @@ class ILTranslator:
 
             # 处理占位符
             if any(
-                isinstance(p, FormulaPlaceholder) and matched_text == p.placeholder
+                isinstance(p, FormulaPlaceholder)
+                and re.match(f"^{p.regex_pattern}$", matched_text, re.IGNORECASE)
                 for p in input_text.placeholders
             ):
                 # 处理公式占位符
@@ -638,7 +640,7 @@ class ILTranslator:
                     p
                     for p in input_text.placeholders
                     if isinstance(p, FormulaPlaceholder)
-                    and matched_text == p.placeholder
+                    and re.match(f"^{p.regex_pattern}$", matched_text, re.IGNORECASE)
                 )
                 comp = PdfParagraphComposition()
                 comp.pdf_formula = placeholder.formula
@@ -649,11 +651,14 @@ class ILTranslator:
                     p
                     for p in input_text.placeholders
                     if not isinstance(p, FormulaPlaceholder)
-                    and re.match(f"^{p.left_regex_pattern}", matched_text)
+                    and re.match(
+                        f"^{p.left_regex_pattern}", matched_text, re.IGNORECASE
+                    )
                 )
                 text = re.match(
                     f"^{placeholder.left_regex_pattern}(.*){placeholder.right_regex_pattern}$",
                     matched_text,
+                    re.IGNORECASE,
                 ).group(1)
 
                 if isinstance(

{babeldoc-0.3.56 → babeldoc-0.3.58}/babeldoc/high_level.py

@@ -425,6 +425,8 @@ def fix_null_xref(doc: Document) -> None:
             elif obj and "/LZWDecode" in obj:
                 data = doc.xref_stream(i)
                 doc.update_stream(i, data)
+            elif obj and "/Annots" in obj:
+                doc.xref_set_key(i, "Annots", "null")
         except Exception:
             doc.update_object(i, "[]")
 
@@ -625,28 +627,22 @@ def do_translate(
 
 def fix_media_box(doc: Document) -> None:
     mediabox_data = {}
-    for page in doc:
-        page_box_data = {}
-        mediabox = doc.xref_get_key(page.xref, "MediaBox")
-        if mediabox[0] == "null":
-            mediabox = ("array", "[0 0 612 792]")
-            doc.xref_set_key(page.xref, "MediaBox", mediabox[1])
-        if page.mediabox.x0 != 0 or page.mediabox.y0 != 0:
-            x0 = page.mediabox.x0
-            y0 = page.mediabox.y0
-            x1 = page.mediabox.x1
-            y1 = page.mediabox.y1
-            page_box_data["MediaBox"] = doc.xref_get_key(page.xref, "MediaBox")[1]
-            doc.xref_set_key(page.xref, "MediaBox", f"[0 0 {x1 - x0} {y1 - y0}]")
-        if page.cropbox.x0 != 0 or page.cropbox.y0 != 0:
-            x0 = page.cropbox.x0
-            y0 = page.cropbox.y0
-            x1 = page.cropbox.x1
-            y1 = page.cropbox.y1
-            page_box_data["CropBox"] = doc.xref_get_key(page.xref, "CropBox")[1]
-            doc.xref_set_key(page.xref, "CropBox", f"[0 0 {x1 - x0} {y1 - x0}]")
-        if page_box_data:
-            mediabox_data[page.number] = page_box_data
+    for x in range(1, doc.xref_length()):
+        t = doc.xref_get_key(x, "Type")
+        box_set = {}
+        if t[1] in ["/Pages", "/Page"]:
+            mediabox = doc.xref_get_key(x, "MediaBox")
+            if mediabox[0] != "null":
+                _, _, x1, y1 = mediabox[1].replace("[", "").replace("]", "").split(" ")
+                doc.xref_set_key(x, "MediaBox", f"[0 0 {x1} {y1}]")
+                box_set["MediaBox"] = mediabox[1]
+            for k in ["CropBox", "BleedBox", "TrimBox", "ArtBox"]:
+                box = doc.xref_get_key(x, k)
+                if box[0] != "null":
+                    box_set[k] = box[1]
+                    doc.xref_set_key(x, k, "null")
+        if box_set:
+            mediabox_data[x] = box_set
     return mediabox_data
 
 

{babeldoc-0.3.56 → babeldoc-0.3.58}/babeldoc/main.py

@@ -24,7 +24,7 @@ from babeldoc.translation_config import TranslationConfig
 from babeldoc.translation_config import WatermarkOutputMode
 
 logger = logging.getLogger(__name__)
-__version__ = "0.3.56"
+__version__ = "0.3.58"
 
 
 def create_parser():

{babeldoc-0.3.56 → babeldoc-0.3.58}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.3.56"
+version = "0.3.58"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -151,7 +151,7 @@ pythonpath = [".", "src"]
 testpaths = ["tests"]
 
 [bumpver]
-current_version = "0.3.56"
+current_version = "0.3.58"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]