BabelDOC 0.3.60__tar.gz → 0.3.62__tar.gz

{babeldoc-0.3.60 → babeldoc-0.3.62}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.3.60
+Version: 0.3.62
 Summary: Yet Another Document Translator
 Project-URL: Homepage, https://github.com/funstory-ai/BabelDOC
 Project-URL: Issues, https://github.com/funstory-ai/BabelDOC/issues
@@ -13,7 +13,9 @@ Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3
 Requires-Python: <3.14,>=3.10
 Requires-Dist: bitstring>=4.3.0
+Requires-Dist: charset-normalizer>=2.0.0
 Requires-Dist: configargparse>=1.7
+Requires-Dist: cryptography>=36.0.0
 Requires-Dist: freetype-py>=2.5.1
 Requires-Dist: httpx[socks]>=0.27.0
 Requires-Dist: huggingface-hub>=0.27.0
@@ -25,7 +27,6 @@ Requires-Dist: onnxruntime>=1.16.1
 Requires-Dist: openai>=1.59.3
 Requires-Dist: opencv-python-headless>=4.10.0.84
 Requires-Dist: orjson>=3.10.14
-Requires-Dist: pdfminer-six==20250416
 Requires-Dist: peewee>=3.17.8
 Requires-Dist: psutil>=7.0.0
 Requires-Dist: pydantic>=2.10.6

babeldoc-0.3.62/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.3.62"

{babeldoc-0.3.60 → babeldoc-0.3.62}/babeldoc/const.py

@@ -3,7 +3,7 @@ import shutil
 import subprocess
 from pathlib import Path
 
-__version__ = "0.3.60"
+__version__ = "0.3.62"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

{babeldoc-0.3.60 → babeldoc-0.3.62}/babeldoc/converter.py

@@ -3,27 +3,27 @@ import re
 import unicodedata
 
 import numpy as np
-from pdfminer.converter import PDFConverter
-from pdfminer.layout import LTChar
-from pdfminer.layout import LTComponent
-from pdfminer.layout import LTFigure
-from pdfminer.layout import LTLine
-from pdfminer.layout import LTPage
-from pdfminer.layout import LTText
-from pdfminer.pdfcolor import PDFColorSpace
-from pdfminer.pdffont import PDFCIDFont
-from pdfminer.pdffont import PDFFont
-from pdfminer.pdffont import PDFUnicodeNotDefined
-from pdfminer.pdfinterp import PDFGraphicState
-from pdfminer.pdfinterp import PDFResourceManager
-from pdfminer.utils import Matrix
-from pdfminer.utils import apply_matrix_pt
-from pdfminer.utils import bbox2str
-from pdfminer.utils import matrix2str
-from pdfminer.utils import mult_matrix
 from pymupdf import Font
 
 from babeldoc.document_il.frontend.il_creater import ILCreater
+from babeldoc.pdfminer.converter import PDFConverter
+from babeldoc.pdfminer.layout import LTChar
+from babeldoc.pdfminer.layout import LTComponent
+from babeldoc.pdfminer.layout import LTFigure
+from babeldoc.pdfminer.layout import LTLine
+from babeldoc.pdfminer.layout import LTPage
+from babeldoc.pdfminer.layout import LTText
+from babeldoc.pdfminer.pdfcolor import PDFColorSpace
+from babeldoc.pdfminer.pdffont import PDFCIDFont
+from babeldoc.pdfminer.pdffont import PDFFont
+from babeldoc.pdfminer.pdffont import PDFUnicodeNotDefined
+from babeldoc.pdfminer.pdfinterp import PDFGraphicState
+from babeldoc.pdfminer.pdfinterp import PDFResourceManager
+from babeldoc.pdfminer.utils import Matrix
+from babeldoc.pdfminer.utils import apply_matrix_pt
+from babeldoc.pdfminer.utils import bbox2str
+from babeldoc.pdfminer.utils import matrix2str
+from babeldoc.pdfminer.utils import mult_matrix
 
 log = logging.getLogger(__name__)
 

{babeldoc-0.3.60 → babeldoc-0.3.62}/babeldoc/document_il/frontend/il_creater.py

@@ -2,26 +2,26 @@ import base64
 import functools
 import logging
 import re
-from functools import wraps
 from io import BytesIO
 from itertools import islice
 
 import freetype
-import pdfminer.pdfinterp
 import pymupdf
-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
 
+import babeldoc.pdfminer.pdfinterp
 from babeldoc.document_il import il_version_1
 from babeldoc.document_il.utils import zstd_helper
 from babeldoc.document_il.utils.style_helper import BLACK
 from babeldoc.document_il.utils.style_helper import YELLOW
+from babeldoc.pdfminer.layout import LTChar
+from babeldoc.pdfminer.layout import LTFigure
+from babeldoc.pdfminer.pdffont import PDFCIDFont
+from babeldoc.pdfminer.pdffont import PDFFont
+
+# from babeldoc.pdfminer.pdfpage import PDFPage as PDFMinerPDFPage
+# from babeldoc.pdfminer.pdftypes import PDFObjRef as PDFMinerPDFObjRef
+# from babeldoc.pdfminer.pdftypes import resolve1 as pdftypes_resolve1
+from babeldoc.pdfminer.psparser import PSLiteral
 from babeldoc.translation_config import TranslationConfig
 
 
@@ -38,28 +38,28 @@ def batched(iterable, n, *, strict=False):
 
 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]
-    try:
-        while isinstance(attrs["MediaBox"], PDFMinerPDFObjRef):
-            attrs["MediaBox"] = pdftypes_resolve1(attrs["MediaBox"])
-    except Exception:
-        logger.exception(f"try to fix mediabox failed: {attrs}")
-
-
-PDFMinerPDFPage.__init__ = create_hook(
-    PDFMinerPDFPage.__init__, hook_pdfminer_pdf_page_init
-)
+#
+# 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]
+#     try:
+#         while isinstance(attrs["MediaBox"], PDFMinerPDFObjRef):
+#             attrs["MediaBox"] = pdftypes_resolve1(attrs["MediaBox"])
+#     except Exception:
+#         logger.exception(f"try to fix mediabox failed: {attrs}")
+#
+#
+# PDFMinerPDFPage.__init__ = create_hook(
+#     PDFMinerPDFPage.__init__, hook_pdfminer_pdf_page_init
+# )
 
 
 def indirect(obj):
@@ -781,7 +781,7 @@ class ILCreater:
             cmap = parse_cmap(self.mupdf.xref_stream(to_unicode_idx).decode("U8"))
         return bbox_list, cmap
 
-    def create_graphic_state(self, gs: pdfminer.pdfinterp.PDFGraphicState):
+    def create_graphic_state(self, gs: babeldoc.pdfminer.pdfinterp.PDFGraphicState):
         graphic_state = il_version_1.GraphicState()
         for k, v in gs.__dict__.items():
             if v is None:

{babeldoc-0.3.60 → babeldoc-0.3.62}/babeldoc/document_il/midend/automatic_term_extractor.py

@@ -195,7 +195,7 @@ class AutomaticTermExtractor:
                 continue
             total_token_count += self.calc_token_count(paragraph.unicode)
             paragraphs.append(paragraph)
-            if total_token_count > 200 or len(paragraphs) > 5:
+            if total_token_count > 600 or len(paragraphs) > 12:
                 executor.submit(
                     self.extract_terms_from_paragraphs,
                     BatchParagraph(paragraphs, tracker),

babeldoc-0.3.62/babeldoc/docvision/base_doclayout.py

@@ -0,0 +1,79 @@
+import abc
+import logging
+from collections.abc import Generator
+
+import pymupdf
+
+from babeldoc.document_il.il_version_1 import Page
+
+logger = logging.getLogger(__name__)
+
+
+class YoloResult:
+    """Helper class to store detection results from ONNX model."""
+
+    def __init__(self, names, boxes=None, boxes_data=None):
+        if boxes is not None:
+            self.boxes = boxes
+        else:
+            assert boxes_data is not None
+            self.boxes = [YoloBox(data=d) for d in boxes_data]
+        self.boxes.sort(key=lambda x: x.conf, reverse=True)
+        self.names = names
+
+
+class YoloBox:
+    """Helper class to store detection results from ONNX model."""
+
+    def __init__(self, data=None, xyxy=None, conf=None, cls=None):
+        if data is not None:
+            self.xyxy = data[:4]
+            self.conf = data[-2]
+            self.cls = data[-1]
+            return
+        assert xyxy is not None and conf is not None and cls is not None
+        self.xyxy = xyxy
+        self.conf = conf
+        self.cls = cls
+
+
+class DocLayoutModel(abc.ABC):
+    @staticmethod
+    def load_onnx():
+        logger.info("Loading ONNX model...")
+        from babeldoc.docvision.doclayout import OnnxModel
+
+        model = OnnxModel.from_pretrained()
+        return model
+
+    @staticmethod
+    def load_available():
+        return DocLayoutModel.load_onnx()
+
+    @property
+    @abc.abstractmethod
+    def stride(self) -> int:
+        """Stride of the model input."""
+
+    @abc.abstractmethod
+    def predict(self, image: bytes, imgsz: int = 1024, **kwargs) -> list[int]:
+        """
+        Predict the layout of a document page.
+
+        Args:
+            image: The image of the document page.
+            imgsz: Resize the image to this size. Must be a multiple of the stride.
+            **kwargs: Additional arguments.
+        """
+
+    @abc.abstractmethod
+    def handle_document(
+        self,
+        pages: list[Page],
+        mupdf_doc: pymupdf.Document,
+        translate_config,
+        save_debug_image,
+    ) -> Generator[tuple[Page, YoloResult], None, None]:
+        """
+        Handle a document.
+        """

{babeldoc-0.3.60 → babeldoc-0.3.62}/babeldoc/docvision/doclayout.py

@@ -1,4 +1,3 @@
-import abc
 import ast
 import logging
 import platform
@@ -10,6 +9,8 @@ import cv2
 import numpy as np
 
 from babeldoc.document_il.utils.mupdf_helper import get_no_rotation_img
+from babeldoc.docvision.base_doclayout import DocLayoutModel
+from babeldoc.docvision.base_doclayout import YoloResult
 
 try:
     import onnx
@@ -31,76 +32,6 @@ from babeldoc.assets.assets import get_doclayout_onnx_model_path
 logger = logging.getLogger(__name__)
 
 
-class YoloResult:
-    """Helper class to store detection results from ONNX model."""
-
-    def __init__(self, names, boxes=None, boxes_data=None):
-        if boxes is not None:
-            self.boxes = boxes
-        else:
-            assert boxes_data is not None
-            self.boxes = [YoloBox(data=d) for d in boxes_data]
-        self.boxes.sort(key=lambda x: x.conf, reverse=True)
-        self.names = names
-
-
-class DocLayoutModel(abc.ABC):
-    @staticmethod
-    def load_onnx():
-        logger.info("Loading ONNX model...")
-        model = OnnxModel.from_pretrained()
-        return model
-
-    @staticmethod
-    def load_available():
-        return DocLayoutModel.load_onnx()
-
-    @property
-    @abc.abstractmethod
-    def stride(self) -> int:
-        """Stride of the model input."""
-
-    @abc.abstractmethod
-    def predict(self, image: bytes, imgsz: int = 1024, **kwargs) -> list[int]:
-        """
-        Predict the layout of a document page.
-
-        Args:
-            image: The image of the document page.
-            imgsz: Resize the image to this size. Must be a multiple of the stride.
-            **kwargs: Additional arguments.
-        """
-
-    @abc.abstractmethod
-    def handle_document(
-        self,
-        pages: list[babeldoc.document_il.il_version_1.Page],
-        mupdf_doc: pymupdf.Document,
-        translate_config,
-        save_debug_image,
-    ) -> Generator[
-        tuple[babeldoc.document_il.il_version_1.Page, YoloResult], None, None
-    ]:
-        """
-        Handle a document.
-        """
-
-
-class YoloBox:
-    """Helper class to store detection results from ONNX model."""
-
-    def __init__(self, data=None, xyxy=None, conf=None, cls=None):
-        if data is not None:
-            self.xyxy = data[:4]
-            self.conf = data[-2]
-            self.cls = data[-1]
-            return
-        assert xyxy is not None and conf is not None and cls is not None
-        self.xyxy = xyxy
-        self.conf = conf
-        self.cls = cls
-
-
 # 检测操作系统类型
 os_name = platform.system()
 

{babeldoc-0.3.60 → babeldoc-0.3.62}/babeldoc/docvision/rpc_doclayout.py

@@ -15,9 +15,9 @@ from tenacity import wait_exponential
 
 import babeldoc
 from babeldoc.document_il.utils.mupdf_helper import get_no_rotation_img
-from babeldoc.docvision.doclayout import DocLayoutModel
-from babeldoc.docvision.doclayout import YoloBox
-from babeldoc.docvision.doclayout import YoloResult
+from babeldoc.docvision.base_doclayout import DocLayoutModel
+from babeldoc.docvision.base_doclayout import YoloBox
+from babeldoc.docvision.base_doclayout import YoloResult
 
 logger = logging.getLogger(__name__)
 

{babeldoc-0.3.60 → babeldoc-0.3.62}/babeldoc/docvision/table_detection/rapidocr.py

@@ -7,8 +7,8 @@ import cv2
 import numpy as np
 from babeldoc.assets.assets import get_table_detection_rapidocr_model_path
 from babeldoc.document_il.utils.mupdf_helper import get_no_rotation_img
-from babeldoc.docvision.doclayout import YoloBox
-from babeldoc.docvision.doclayout import YoloResult
+from babeldoc.docvision.base_doclayout import YoloBox
+from babeldoc.docvision.base_doclayout import YoloResult
 from rapidocr_onnxruntime import RapidOCR
 
 try:

{babeldoc-0.3.60 → babeldoc-0.3.62}/babeldoc/high_level.py

@@ -5,7 +5,6 @@ import io
 import logging
 import pathlib
 import shutil
-import struct
 import threading
 import time
 from asyncio import CancelledError
@@ -14,11 +13,6 @@ from typing import Any
 from typing import BinaryIO
 
 import pymupdf
-from pdfminer.cmapdb import IdentityCMap
-from pdfminer.pdfdocument import PDFDocument
-from pdfminer.pdfinterp import PDFResourceManager
-from pdfminer.pdfpage import PDFPage
-from pdfminer.pdfparser import PDFParser
 from pymupdf import Document
 from pymupdf import Font
 
@@ -45,6 +39,10 @@ from babeldoc.document_il.midend.typesetting import Typesetting
 from babeldoc.document_il.utils.fontmap import FontMapper
 from babeldoc.document_il.xml_converter import XMLConverter
 from babeldoc.pdfinterp import PDFPageInterpreterEx
+from babeldoc.pdfminer.pdfdocument import PDFDocument
+from babeldoc.pdfminer.pdfinterp import PDFResourceManager
+from babeldoc.pdfminer.pdfpage import PDFPage
+from babeldoc.pdfminer.pdfparser import PDFParser
 from babeldoc.progress_monitor import ProgressMonitor
 from babeldoc.result_merger import ResultMerger
 from babeldoc.split_manager import SplitManager
@@ -52,17 +50,6 @@ from babeldoc.translation_config import TranslateResult
 from babeldoc.translation_config import TranslationConfig
 from babeldoc.translation_config import WatermarkOutputMode
 
-
-def decode(_, code: bytes) -> tuple[int, ...]:
-    n = len(code) // 2
-    if n:
-        return struct.unpack_from(f">{n}H", code)
-    else:
-        return ()
-
-
-IdentityCMap.decode = decode
-
 logger = logging.getLogger(__name__)
 
 TRANSLATE_STAGES = [
@@ -608,6 +595,12 @@ def do_translate(
         # not being able to copy translated text can be fixed,
         # the macOS preview is broken
         # fix_cmap(result, translation_config)
+        try:
+            migrate_toc(translation_config, result)
+        except Exception as e:
+            logger.error(
+                f"Failed to migrate TOC from {translation_config.input_file}: {e}"
+            )
         pm.translate_done(result)
         return result
 
@@ -625,6 +618,51 @@ def do_translate(
         translation_config.cleanup_temp_files()
 
 
+def migrate_toc(
+    translation_config: TranslationConfig, translate_result: TranslateResult
+):
+    old_doc = Document(translation_config.input_file)
+    if not old_doc:
+        return
+
+    try:
+        fix_filter(old_doc)
+        fix_null_xref(old_doc)
+    except Exception:
+        logger.exception("auto fix failed, please check the pdf file")
+
+    toc_data = old_doc.get_toc()
+
+    if not toc_data:
+        logger.info("No TOC found in the original PDF, skipping migration.")
+        return
+
+    files = {
+        translate_result.dual_pdf_path,
+        # translate_result.mono_pdf_path,
+        translate_result.no_watermark_dual_pdf_path,
+        # translate_result.no_watermark_mono_pdf_path
+    }
+
+    for f in files:
+        mig_toc_temp_input = translation_config.get_working_file_path(
+            "mig_toc_temp.pdf"
+        )
+        shutil.copy(f, mig_toc_temp_input)
+        new_doc = Document(mig_toc_temp_input.as_posix())
+        if not new_doc:
+            continue
+
+        new_doc.set_toc(toc_data)
+        PDFCreater.save_pdf_with_timeout(
+            new_doc,
+            f.as_posix(),
+            translation_config=translation_config,
+            clean=not translation_config.skip_clean,
+            tag="mig_toc",
+        )
+
+
 def fix_media_box(doc: Document) -> None:
     mediabox_data = {}
     for x in range(1, doc.xref_length()):

{babeldoc-0.3.60 → babeldoc-0.3.62}/babeldoc/main.py

@@ -16,15 +16,12 @@ import babeldoc.assets.assets
 import babeldoc.high_level
 from babeldoc.document_il.translator.translator import OpenAITranslator
 from babeldoc.document_il.translator.translator import set_translate_rate_limiter
-from babeldoc.docvision.doclayout import DocLayoutModel
-from babeldoc.docvision.rpc_doclayout import RpcDocLayoutModel
-from babeldoc.docvision.table_detection.rapidocr import RapidOCRModel
 from babeldoc.glossary import Glossary
 from babeldoc.translation_config import TranslationConfig
 from babeldoc.translation_config import WatermarkOutputMode
 
 logger = logging.getLogger(__name__)
-__version__ = "0.3.60"
+__version__ = "0.3.62"
 
 
 def create_parser():
@@ -329,14 +326,19 @@ async def main():
 
     # 设置翻译速率限制
     set_translate_rate_limiter(args.qps)
-
     # 初始化文档布局模型
     if args.rpc_doclayout:
+        from babeldoc.docvision.rpc_doclayout import RpcDocLayoutModel
+
         doc_layout_model = RpcDocLayoutModel(host=args.rpc_doclayout)
     else:
+        from babeldoc.docvision.doclayout import DocLayoutModel
+
         doc_layout_model = DocLayoutModel.load_onnx()
 
     if args.translate_table_text:
+        from babeldoc.docvision.table_detection.rapidocr import RapidOCRModel
+
         table_model = RapidOCRModel()
     else:
         table_model = None

{babeldoc-0.3.60 → babeldoc-0.3.62}/babeldoc/pdfinterp.py

@@ -4,42 +4,42 @@ from typing import Any
 from typing import cast
 
 import numpy as np
-from pdfminer import settings
-from pdfminer.pdfcolor import PREDEFINED_COLORSPACE
-from pdfminer.pdfcolor import PDFColorSpace
-from pdfminer.pdfdevice import PDFDevice
-from pdfminer.pdfdevice import PDFTextSeq
-from pdfminer.pdffont import PDFFont
-from pdfminer.pdfinterp import LITERAL_FORM
-from pdfminer.pdfinterp import LITERAL_IMAGE
-from pdfminer.pdfinterp import Color
-from pdfminer.pdfinterp import PDFContentParser
-from pdfminer.pdfinterp import PDFInterpreterError
-from pdfminer.pdfinterp import PDFPageInterpreter
-from pdfminer.pdfinterp import PDFResourceManager
-from pdfminer.pdfinterp import PDFStackT
-from pdfminer.pdfpage import PDFPage
-from pdfminer.pdftypes import LITERALS_ASCII85_DECODE
-from pdfminer.pdftypes import PDFObjRef
-from pdfminer.pdftypes import PDFStream
-from pdfminer.pdftypes import dict_value
-from pdfminer.pdftypes import list_value
-from pdfminer.pdftypes import resolve1
-from pdfminer.pdftypes import stream_value
-from pdfminer.psexceptions import PSEOF
-from pdfminer.psexceptions import PSTypeError
-from pdfminer.psparser import PSKeyword
-from pdfminer.psparser import PSLiteral
-from pdfminer.psparser import keyword_name
-from pdfminer.psparser import literal_name
-from pdfminer.utils import MATRIX_IDENTITY
-from pdfminer.utils import Matrix
-from pdfminer.utils import Rect
-from pdfminer.utils import apply_matrix_pt
-from pdfminer.utils import choplist
-from pdfminer.utils import mult_matrix
 
 from babeldoc.document_il.frontend.il_creater import ILCreater
+from babeldoc.pdfminer import settings
+from babeldoc.pdfminer.pdfcolor import PREDEFINED_COLORSPACE
+from babeldoc.pdfminer.pdfcolor import PDFColorSpace
+from babeldoc.pdfminer.pdfdevice import PDFDevice
+from babeldoc.pdfminer.pdfdevice import PDFTextSeq
+from babeldoc.pdfminer.pdffont import PDFFont
+from babeldoc.pdfminer.pdfinterp import LITERAL_FORM
+from babeldoc.pdfminer.pdfinterp import LITERAL_IMAGE
+from babeldoc.pdfminer.pdfinterp import Color
+from babeldoc.pdfminer.pdfinterp import PDFContentParser
+from babeldoc.pdfminer.pdfinterp import PDFInterpreterError
+from babeldoc.pdfminer.pdfinterp import PDFPageInterpreter
+from babeldoc.pdfminer.pdfinterp import PDFResourceManager
+from babeldoc.pdfminer.pdfinterp import PDFStackT
+from babeldoc.pdfminer.pdfpage import PDFPage
+from babeldoc.pdfminer.pdftypes import LITERALS_ASCII85_DECODE
+from babeldoc.pdfminer.pdftypes import PDFObjRef
+from babeldoc.pdfminer.pdftypes import PDFStream
+from babeldoc.pdfminer.pdftypes import dict_value
+from babeldoc.pdfminer.pdftypes import list_value
+from babeldoc.pdfminer.pdftypes import resolve1
+from babeldoc.pdfminer.pdftypes import stream_value
+from babeldoc.pdfminer.psexceptions import PSEOF
+from babeldoc.pdfminer.psexceptions import PSTypeError
+from babeldoc.pdfminer.psparser import PSKeyword
+from babeldoc.pdfminer.psparser import PSLiteral
+from babeldoc.pdfminer.psparser import keyword_name
+from babeldoc.pdfminer.psparser import literal_name
+from babeldoc.pdfminer.utils import MATRIX_IDENTITY
+from babeldoc.pdfminer.utils import Matrix
+from babeldoc.pdfminer.utils import Rect
+from babeldoc.pdfminer.utils import apply_matrix_pt
+from babeldoc.pdfminer.utils import choplist
+from babeldoc.pdfminer.utils import mult_matrix
 
 log = logging.getLogger(__name__)
 

babeldoc-0.3.62/babeldoc/pdfminer/LICENSE

@@ -0,0 +1,22 @@
+Copyright (c) 2004-2016  Yusuke Shinyama <yusuke at shinyama dot jp>
+
+Permission is hereby granted, free of charge, to any person
+obtaining a copy of this software and associated documentation
+files (the "Software"), to deal in the Software without
+restriction, including without limitation the rights to use,
+copy, modify, merge, publish, distribute, sublicense, and/or
+sell copies of the Software, and to permit persons to whom the
+Software is furnished to do so, subject to the following
+conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY
+KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE
+WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR
+PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
+COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

babeldoc-0.3.62/babeldoc/pdfminer/__init__.py

@@ -0,0 +1,11 @@
+from importlib.metadata import PackageNotFoundError
+from importlib.metadata import version
+
+try:
+    __version__ = version("pdfminer.six")
+except PackageNotFoundError:
+    # package is not installed, return default
+    __version__ = "0.0"
+
+if __name__ == "__main__":
+    print(__version__)