BabelDOC 0.4.16__tar.gz → 0.4.18__tar.gz

{babeldoc-0.4.16 → babeldoc-0.4.18}/.github/ISSUE_TEMPLATE/bug_report.yaml

@@ -17,6 +17,12 @@ body:
           required: true
         - label: I am certain that this issue is with BabelDOC itself and can be reproduced through the BabelDOC cli
           required: true
+        - label: I have uploaded the original file, or confirmed that this issue is unrelated to the original file
+          required: true
+        - label: I have uploaded the log.
+          required: true
+        - label: I confirm that the latest version of BabelDOC is being used.
+          required: true
 
   - type: markdown
     attributes:
@@ -77,7 +83,7 @@ body:
     id: pdf
     attributes:
       label: Original PDF File
-      description: Upload the input PDF if applicable.
+      description: Upload the input PDF if applicable. (Issues related to specific PDFs but without uploaded files will be closed directly.)
     validations:
       required: false
 

{babeldoc-0.4.16 → babeldoc-0.4.18}/.github/ISSUE_TEMPLATE/feature_request.yaml

@@ -7,6 +7,16 @@ body:
       value: |
         Thank you for helping improve **BabelDOC**! Please fill out the form below to suggest a feature.
 
+  - type: checkboxes
+    id: checks
+    attributes:
+      label: Before you submit
+      options:
+        - label: I have searched existing issues
+          required: true
+        - label: I have fully read and understood the [README](https://github.com/funstory-ai/BabelDOC/blob/main/README.md)
+          required: true
+
   - type: textarea
     id: describe
     attributes:

{babeldoc-0.4.16 → babeldoc-0.4.18}/.github/workflows/docs.yml

@@ -17,7 +17,7 @@ jobs:
           git config user.name github-actions[bot]
           git config user.email 41898282+github-actions[bot]@users.noreply.github.com
       - name: Setup uv with Python 3.12
-        uses: astral-sh/setup-uv@bd01e18f51369d5a26f1651c3cb451d3417e3bba # v6.3.1
+        uses: astral-sh/setup-uv@e92bafb6253dcd438e0484186d7669ea7a8ca1cc # v6.4.3
         with:
           python-version: "3.12"
           enable-cache: true

{babeldoc-0.4.16 → babeldoc-0.4.18}/.github/workflows/publish-to-pypi.yml

@@ -35,7 +35,7 @@ jobs:
           token: ${{ secrets.GITHUB_TOKEN }}
           
       - name: Setup uv with Python 3.12
-        uses: astral-sh/setup-uv@bd01e18f51369d5a26f1651c3cb451d3417e3bba # v6.3.1
+        uses: astral-sh/setup-uv@e92bafb6253dcd438e0484186d7669ea7a8ca1cc # v6.4.3
         with:
           python-version: "3.12"
           enable-cache: true

{babeldoc-0.4.16 → babeldoc-0.4.18}/.github/workflows/test.yml

@@ -28,7 +28,7 @@ jobs:
           path: ~/.cache/babeldoc
           key: babeldoc-assets-${{ hashFiles('babeldoc/assets/embedding_assets_metadata.py') }}
       - name: Setup uv with Python ${{ matrix.python-version }}
-        uses: astral-sh/setup-uv@bd01e18f51369d5a26f1651c3cb451d3417e3bba # v6.3.1
+        uses: astral-sh/setup-uv@e92bafb6253dcd438e0484186d7669ea7a8ca1cc # v6.4.3
         with:
           python-version: ${{ matrix.python-version }}
           enable-cache: true

{babeldoc-0.4.16 → babeldoc-0.4.18}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.4.16
+Version: 0.4.18
 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-0.4.18/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.4.18"

{babeldoc-0.4.16 → babeldoc-0.4.18}/babeldoc/const.py

@@ -3,7 +3,7 @@ import shutil
 import subprocess
 from pathlib import Path
 
-__version__ = "0.4.16"
+__version__ = "0.4.18"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

{babeldoc-0.4.16 → babeldoc-0.4.18}/babeldoc/docvision/rpc_doclayout3.py

@@ -82,12 +82,12 @@ def predict_layout(
     # Send request
     # logger.debug(f"Sending request to {host}/inference")
     response = httpx.post(
-        f"{host}/analyze?min_sim=0.7&early_stop=0.99&timeout=480",
+        f"{host}/analyze?min_sim=0.7&early_stop=0.99&timeout=1800",
         files={"file": ("image.jpg", image_data, "image/jpeg")},
         headers={
             "Accept": "application/json",
         },
-        timeout=480,
+        timeout=1800,
         follow_redirects=True,
     )
 

{babeldoc-0.4.16 → babeldoc-0.4.18}/babeldoc/format/pdf/document_il/frontend/il_creater.py

@@ -1,6 +1,7 @@
 import base64
 import functools
 import logging
+import math
 import re
 from io import BytesIO
 from itertools import islice
@@ -221,6 +222,18 @@ pattern = "^[" + "".join(unicode_spaces) + "]+$"
 space_regex = re.compile(pattern)
 
 
+def get_rotation_angle(matrix):
+    """
+    根据 PDF 的字符矩阵计算旋转角度（单位：度）
+    matrix: tuple/list, 格式 (a, b, c, d, e, f)
+    """
+    a, b, c, d, e, f = matrix
+    # 旋转角度：arctan2(b, a)
+    angle_rad = math.atan2(b, a)
+    angle_deg = math.degrees(angle_rad)
+    return angle_deg
+
+
 class ILCreater:
     stage_name = "Parse PDF and Create Intermediate Representation"
 
@@ -582,6 +595,15 @@ class ILCreater:
     def on_lt_char(self, char: LTChar):
         if char.aw_font_id is None:
             return
+        try:
+            rotation_angle = get_rotation_angle(char.matrix)
+            if not (-0.1 <= rotation_angle <= 0.1 or 89.9 <= rotation_angle <= 90.1):
+                return
+        except Exception:
+            logger.warning(
+                "Failed to get rotation angle for char %s",
+                char.get_text(),
+            )
         gs = self.create_graphic_state(char.graphicstate)
         # Get font from current page or xobject
         font = None

{babeldoc-0.4.16 → babeldoc-0.4.18}/babeldoc/format/pdf/high_level.py

@@ -88,6 +88,15 @@ resfont_map = {
 }
 
 
+def safe_save(doc, *args, **kwargs):
+    try:
+        # first try, saving without options
+        doc.save(*args, **kwargs)
+    except Exception:
+        # second try, saving with 'garbage=3' for object missing
+        doc.ez_save(*args, **kwargs)
+
+
 def fix_cmap(translate_result: TranslateResult, translate_config: TranslationConfig):
     processed = []
     for attr in (
@@ -104,7 +113,7 @@ def fix_cmap(translate_result: TranslateResult, translate_config: TranslationCon
         temp_path = translate_config.get_working_file_path(f"{path.stem}.cmap.pdf")
         pdf = pymupdf.open(path)
         reproduce_cmap(pdf)
-        pdf.save(temp_path)
+        safe_save(pdf, temp_path)
         shutil.move(temp_path, path)
 
 
@@ -563,7 +572,7 @@ def do_translate(
                                     from_page=split_point.start_page,
                                     to_page=split_point.end_page,
                                 )
-                                temp_doc.save(part_temp_input_path)
+                                safe_save(temp_doc, part_temp_input_path)
                                 assert (
                                     temp_doc.page_count
                                     == split_point.end_page - split_point.start_page + 1
@@ -695,6 +704,7 @@ def migrate_toc(
         )
 
 
+# mediabox -> '[0 nul 792]'
 def fix_media_box(doc: Document) -> None:
     mediabox_data = {}
     for x in range(1, doc.xref_length()):
@@ -703,9 +713,16 @@ def fix_media_box(doc: Document) -> None:
         if t[1] in ["/Pages", "/Page"]:
             mediabox = doc.xref_get_key(x, "MediaBox")
             if mediabox[0] == "array":
-                _, _, x1, y1 = mediabox[1].replace("[", "").replace("]", "").split(" ")
-                doc.xref_set_key(x, "MediaBox", f"[0 0 {x1} {y1}]")
-                box_set["MediaBox"] = mediabox[1]
+                try:
+                    _, _, x1, y1 = (
+                        mediabox[1].replace("[", "").replace("]", "").split(" ")
+                    )
+                    doc.xref_set_key(x, "MediaBox", f"[0 0 {x1} {y1}]")
+                    box_set["MediaBox"] = mediabox[1]
+                except Exception:
+                    logger.warning(
+                        "Attempt to fix media box failed; some pages may not have been processed correctly."
+                    )
             for k in ["CropBox", "BleedBox", "TrimBox", "ArtBox"]:
                 box = doc.xref_get_key(x, k)
                 if box[0] != "null":
@@ -754,13 +771,13 @@ def _do_translate_single(
             fix_null_xref(doc_input)
         except Exception:
             logger.exception("auto fix failed, please check the pdf file")
-        doc_input.save(output_path, expand=True, pretty=True)
+        safe_save(doc_input, output_path, expand=True, pretty=True)
         del doc_input
 
     # Continue with original processing
     temp_pdf_path = translation_config.get_working_file_path("input.pdf")
     doc_pdf2zh = Document(original_pdf_path)
-    resfont = "china-ss"
+    safe_save(doc_pdf2zh, temp_pdf_path)
 
     # Fix null xref in PDF file
     invalid_pages = []
@@ -777,7 +794,7 @@ def _do_translate_single(
     #     page.insert_font(resfont, None)
 
     resfont = None
-    doc_pdf2zh.save(temp_pdf_path)
+    safe_save(doc_pdf2zh, temp_pdf_path)
 
     # if not translation_config.skip_scanned_detection and DetectScannedFile(
     #     translation_config
@@ -978,7 +995,7 @@ def generate_first_page_with_watermark(
         watermarked_temp_pdf_path = watermarked_config.get_working_file_path(
             "watermarked_temp_input.pdf"
         )
-        first_page_doc.save(watermarked_temp_pdf_path)
+        safe_save(first_page_doc, watermarked_temp_pdf_path)
 
         Typesetting(watermarked_config).typsetting_document(il_only_first_page_doc)
         pdf_creater = PDFCreater(

{babeldoc-0.4.16 → babeldoc-0.4.18}/babeldoc/format/pdf/pdfinterp.py

@@ -283,6 +283,8 @@ class PDFPageInterpreterEx(PDFPageInterpreter):
         self.il_creater.on_passthrough_per_char("sc", args)
         return args
 
+    # Ensure bbox has four numbers, otherwise determine it as an illegal image
+    # For example, some Form's bbox is '[ null -.00487 1.00412 .99393 ]'
     def do_Do(self, xobjid_arg: PDFStackT) -> None:
         # 重载设置 xobj 的 obj_patch
         """Invoke named XObject"""
@@ -303,6 +305,8 @@ class PDFPageInterpreterEx(PDFPageInterpreter):
             bbox = list(
                 filter(lambda x: x is not None, cast(Rect, list_value(xobj["BBox"])))
             )
+            if len(bbox) < 4:
+                return
 
             matrix = cast(Matrix, list_value(xobj.get("Matrix", MATRIX_IDENTITY)))
             # According to PDF reference 1.7 section 4.9.1, XObjects in

{babeldoc-0.4.16 → babeldoc-0.4.18}/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__ = "0.4.16"
+__version__ = "0.4.18"
 
 
 def create_parser():

{babeldoc-0.4.16 → babeldoc-0.4.18}/babeldoc/pdfminer/pdfpage.py

@@ -80,7 +80,10 @@ class PDFPage:
             log.exception(f"try to fix mediabox failed: {attrs}")
 
         self.mediabox = self._parse_mediabox(self.attrs.get("MediaBox"))
-        self.cropbox = self._parse_cropbox(self.attrs.get("CropBox"), self.mediabox)
+        try:
+            self.cropbox = self._parse_cropbox(self.attrs.get("CropBox"), self.mediabox)
+        except Exception:
+            self.cropbox = self.mediabox
         self.contents = self._parse_contents(self.attrs.get("Contents"))
 
         self.rotate = (int_value(self.attrs.get("Rotate", 0)) + 360) % 360

{babeldoc-0.4.16 → babeldoc-0.4.18}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.4.16"
+version = "0.4.18"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -161,7 +161,7 @@ pythonpath = [".", "src"]
 testpaths = ["tests"]
 
 [bumpver]
-current_version = "0.4.16"
+current_version = "0.4.18"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]

babeldoc-0.4.16/babeldoc/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.4.16"