deepdoctection 0.35__py3-none-any.whl → 0.37__py3-none-any.whl

deepdoctection/utils/pdf_utils.py

@@ -26,7 +26,7 @@ from errno import ENOENT
 from io import BytesIO
 from pathlib import Path
 from shutil import copyfile
-from typing import Generator, Literal, Optional
+from typing import Generator, Literal, Optional, Union
 
 from lazy_imports import try_import
 from numpy import uint8
@@ -46,6 +46,7 @@ with try_import() as pt_import_guard:
 
 __all__ = [
     "decrypt_pdf_document",
+    "decrypt_pdf_document_from_bytes",
     "get_pdf_file_reader",
     "get_pdf_file_writer",
     "PDFStreamer",
@@ -68,7 +69,6 @@ def decrypt_pdf_document(path: PathLikeOrStr) -> bool:
     :param path: A path to the pdf file
     :return: True if document has been successfully decrypted
     """
-
     if qpdf_available():
         path_base, file_name = os.path.split(path)
         file_name_tmp = os.path.splitext(file_name)[0] + "tmp.pdf"
@@ -86,41 +86,69 @@ def decrypt_pdf_document(path: PathLikeOrStr) -> bool:
     return False
 
 
-def get_pdf_file_reader(path: PathLikeOrStr) -> PdfReader:
+def decrypt_pdf_document_from_bytes(input_bytes: bytes) -> bytes:
+    """
+    Decrypting a pdf given as bytes. Under the hood, it saves the bytes to a temporary file and then calls
+
+    qpdf: <http://qpdf.sourceforge.net/>
+
+    :param input_bytes: A bytes object representing the pdf file
+    :return: The decrypted bytes object
+    """
+    with save_tmp_file(input_bytes, "pdf_") as (_, input_file_name):
+        is_decrypted = decrypt_pdf_document(input_file_name)
+        if is_decrypted:
+            with open(input_file_name, "rb") as file:
+                return file.read()
+        else:
+            logger.error(LoggingRecord("pdf bytes cannot be decrypted and therefore cannot be processed further."))
+            sys.exit()
+
+
+def get_pdf_file_reader(path_or_bytes: Union[PathLikeOrStr, bytes]) -> PdfReader:
     """
     Creates a file reader object from a pdf document. Will try to decrypt the document if it is
     encrypted. (See `decrypt_pdf_document` to understand what is meant with "decrypt").
 
-    :param path: A path to a pdf document
+    :param path_or_bytes: A path to a pdf document
     :return: A file reader object from which you can iterate through the document.
     """
 
-    if not os.path.isfile(path):
-        raise FileNotFoundError(str(path))
-    file_name = os.path.split(path)[1]
+    if isinstance(path_or_bytes, bytes):
+        try:
+            reader = PdfReader(BytesIO(path_or_bytes))
+        except (errors.PdfReadError, AttributeError):
+            decrypted_bytes = decrypt_pdf_document_from_bytes(path_or_bytes)
+            reader = PdfReader(BytesIO(decrypted_bytes))
+        return reader
+
+    if not os.path.isfile(path_or_bytes):
+        raise FileNotFoundError(str(path_or_bytes))
+    file_name = os.path.split(path_or_bytes)[1]
     if not is_file_extension(file_name, ".pdf"):
         raise FileExtensionError(f"must be a pdf file: {file_name}")
 
-    with open(path, "rb") as file:
+    with open(path_or_bytes, "rb") as file:
         qpdf_called = False
         try:
-            input_pdf_as_bytes = PdfReader(file)
+            reader = PdfReader(file)
         except (errors.PdfReadError, AttributeError):
-            _ = decrypt_pdf_document(path)
+            _ = decrypt_pdf_document(path_or_bytes)
             qpdf_called = True
 
         if not qpdf_called:
-            if input_pdf_as_bytes.is_encrypted:
-                is_decrypted = decrypt_pdf_document(path)
+            if reader.is_encrypted:
+                is_decrypted = decrypt_pdf_document(path_or_bytes)
                 if not is_decrypted:
                     logger.error(
                         LoggingRecord(
-                            f"pdf document {path} cannot be decrypted and therefore cannot be " f"processed further."
+                            f"pdf document {path_or_bytes} cannot be decrypted and therefore cannot "
+                            f"be processed further."
                         )
                     )
                     sys.exit()
 
-    return PdfReader(os.fspath(path))
+    return PdfReader(os.fspath(path_or_bytes))
 
 
 def get_pdf_file_writer() -> PdfWriter:
@@ -157,11 +185,11 @@ class PDFStreamer:
 
     """
 
-    def __init__(self, path: PathLikeOrStr) -> None:
+    def __init__(self, path_or_bytes: Union[PathLikeOrStr, bytes]) -> None:
         """
-        :param path: to a pdf.
+        :param path_or_bytes: to a pdf.
         """
-        self.file_reader = get_pdf_file_reader(path)
+        self.file_reader = get_pdf_file_reader(path_or_bytes)
         self.file_writer = PdfWriter()
 
     def __len__(self) -> int:

deepdoctection/utils/utils.py

@@ -155,3 +155,42 @@ def is_file_extension(file_name: PathLikeOrStr, extension: Union[str, Sequence[s
     if isinstance(extension, str):
         return os.path.splitext(file_name)[-1].lower() == extension
     return os.path.splitext(file_name)[-1].lower() in extension
+
+
+def partition_list(base_list: list[str], stop_value: str) -> list[list[str]]:
+    """
+    Partitions a list of strings into sublists, where each sublist starts with the first occurrence of the stop value.
+    Consecutive stop values are grouped together in the same sublist.
+
+    :param base_list: The list of strings to be partitioned.
+    :param stop_value: The string value that indicates the start of a new partition.
+    :return: A list of lists, where each sublist is a partition of the original list.
+
+    ** Example:**
+
+        strings = ['a', 'a', 'c', 'c', 'b', 'd', 'c', 'c', 'a', 'b', 'a', 'b', 'a', 'a']
+        stop_string = 'a'
+        partition_list(strings, stop_string)
+
+       # Output [['a', 'a', 'c', 'c', 'b', 'd', 'c', 'c'], ['a', 'b'], ['a', 'b'], ['a', 'a']]
+    """
+
+    partitions = []
+    current_partition: list[str] = []
+    stop_found = False
+
+    for s in base_list:
+        if s == stop_value:
+            if not stop_found and current_partition:
+                partitions.append(current_partition)
+                current_partition = []
+            current_partition.append(s)
+            stop_found = True
+        else:
+            current_partition.append(s)
+            stop_found = False
+
+    if current_partition:
+        partitions.append(current_partition)
+
+    return partitions

deepdoctection/utils/viz.py

@@ -205,6 +205,7 @@ def draw_boxes(
     font_scale: float = 1.0,
     rectangle_thickness: int = 4,
     box_color_by_category: bool = True,
+    show_palette: bool = True,
 ) -> PixelValues:
     """
     Dray bounding boxes with category names into image.
@@ -216,6 +217,7 @@ def draw_boxes(
     :param font_scale: Font scale of text box
     :param rectangle_thickness: Thickness of bounding box
     :param box_color_by_category:
+    :param show_palette: Whether to show a color palette of the categories
     :return: A new image np.ndarray
     """
     if color is not None:
@@ -261,19 +263,20 @@ def draw_boxes(
         )
 
     # draw a (very ugly) color palette
-    y_0 = np_image.shape[0]
-    for category, col in category_to_color.items():
-        if category is not None:
-            np_image = viz_handler.draw_text(
-                np_image,
-                (np_image.shape[1], y_0),
-                category,
-                color=col,
-                font_scale=font_scale * 3,
-                rectangle_thickness=rectangle_thickness,
-            )
-            _, text_h = viz_handler.get_text_size(category, font_scale * 2)
-            y_0 = y_0 - int(10 * text_h)
+    if show_palette:
+        y_0 = np_image.shape[0]
+        for category, col in category_to_color.items():
+            if category is not None:
+                np_image = viz_handler.draw_text(
+                    np_image,
+                    (np_image.shape[1], y_0),
+                    category,
+                    color=col,
+                    font_scale=font_scale,
+                    rectangle_thickness=rectangle_thickness,
+                )
+                _, text_h = viz_handler.get_text_size(category, font_scale * 2)
+                y_0 = y_0 - int(1 * text_h)
 
     return np_image
 
@@ -309,6 +312,7 @@ class VizPackageHandler:
             "interactive_imshow": "_cv2_interactive_imshow",
             "encode": "_cv2_encode",
             "rotate_image": "_cv2_rotate_image",
+            "convert_bytes_to_np": "_cv2_convert_bytes_to_np",
         },
         "pillow": {
             "read_image": "_pillow_read_image",
@@ -322,6 +326,7 @@ class VizPackageHandler:
             "interactive_imshow": "_pillow_interactive_imshow",
             "encode": "_pillow_encode",
             "rotate_image": "_pillow_rotate_image",
+            "convert_bytes_to_np": "_pillow_convert_bytes_to_np",
         },
     }
 
@@ -481,6 +486,37 @@ class VizPackageHandler:
         pil_image = Image.open(im_file)
         return np.array(pil_image)[:, :, ::-1]
 
+    def convert_bytes_to_np(self, image_bytes: bytes) -> PixelValues:
+        """Converting an image as bytes into np.array
+
+        :param image_bytes: Image as np.array
+        """
+        return getattr(self, self.pkg_func_dict["convert_bytes_to_np"])(image_bytes)
+
+    @staticmethod
+    def _cv2_convert_bytes_to_np(image_bytes: bytes) -> PixelValues:
+        """
+        Convert image bytes to a numpy array using OpenCV.
+
+        :param image_bytes: Image bytes
+        :return: Image as numpy array
+        """
+        np_array = np.frombuffer(image_bytes, np.uint8)
+        np_image = cv2.imdecode(np_array, cv2.IMREAD_COLOR)
+        return np_image
+
+    @staticmethod
+    def _pillow_convert_bytes_to_np(image_bytes: bytes) -> PixelValues:
+        """
+        Convert image bytes to a numpy array using Pillow.
+
+        :param image_bytes: Image bytes
+        :return: Image as numpy array
+        """
+        image = Image.open(BytesIO(image_bytes))
+        np_image = np.array(image)
+        return np_image
+
     def resize(self, image: PixelValues, width: int, height: int, interpolation: str) -> PixelValues:
         """
         Resize a given image to new width, height. Specifying an interpolation method is required. Depending on the

{deepdoctection-0.35.dist-info → deepdoctection-0.37.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: deepdoctection
-Version: 0.35
+Version: 0.37
 Summary: Repository for Document AI
 Home-page: https://github.com/deepdoctection/deepdoctection
 Author: Dr. Janis Meyer
@@ -16,117 +16,117 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: catalogue ==2.0.10
-Requires-Dist: huggingface-hub <0.26,>=0.12.0
-Requires-Dist: importlib-metadata >=5.0.0
-Requires-Dist: jsonlines ==3.1.0
-Requires-Dist: lazy-imports ==0.3.1
-Requires-Dist: mock ==4.0.3
-Requires-Dist: networkx >=2.7.1
-Requires-Dist: numpy <2.0,>=1.21
-Requires-Dist: packaging >=20.0
-Requires-Dist: Pillow >=10.0.0
-Requires-Dist: pypdf >=3.16.0
-Requires-Dist: pypdfium2 >=4.30.0
-Requires-Dist: pyyaml >=6.0.1
-Requires-Dist: pyzmq >=16
-Requires-Dist: scipy >=1.13.1
-Requires-Dist: termcolor >=1.1
-Requires-Dist: tabulate >=0.7.7
-Requires-Dist: tqdm ==4.64.0
-Provides-Extra: dev
-Requires-Dist: python-dotenv ==1.0.0 ; extra == 'dev'
-Requires-Dist: click ; extra == 'dev'
-Requires-Dist: black ==23.7.0 ; extra == 'dev'
-Requires-Dist: isort ==5.13.2 ; extra == 'dev'
-Requires-Dist: pylint ==2.17.4 ; extra == 'dev'
-Requires-Dist: mypy ==1.4.1 ; extra == 'dev'
-Requires-Dist: wandb ; extra == 'dev'
-Requires-Dist: types-PyYAML >=6.0.12.12 ; extra == 'dev'
-Requires-Dist: types-termcolor >=1.1.3 ; extra == 'dev'
-Requires-Dist: types-tabulate >=0.9.0.3 ; extra == 'dev'
-Requires-Dist: types-tqdm >=4.66.0.5 ; extra == 'dev'
-Requires-Dist: lxml-stubs >=0.5.1 ; extra == 'dev'
-Requires-Dist: types-Pillow >=10.2.0.20240406 ; extra == 'dev'
-Requires-Dist: types-urllib3 >=1.26.25.14 ; extra == 'dev'
-Provides-Extra: docs
-Requires-Dist: tensorpack ==0.11 ; extra == 'docs'
-Requires-Dist: boto3 ==1.34.102 ; extra == 'docs'
-Requires-Dist: transformers >=4.36.0 ; extra == 'docs'
-Requires-Dist: accelerate >=0.29.1 ; extra == 'docs'
-Requires-Dist: pdfplumber >=0.11.0 ; extra == 'docs'
-Requires-Dist: lxml >=4.9.1 ; extra == 'docs'
-Requires-Dist: lxml-stubs >=0.5.1 ; extra == 'docs'
-Requires-Dist: jdeskew >=0.2.2 ; extra == 'docs'
-Requires-Dist: jinja2 ==3.0.3 ; extra == 'docs'
-Requires-Dist: mkdocs-material ; extra == 'docs'
-Requires-Dist: mkdocstrings-python ; extra == 'docs'
-Requires-Dist: griffe ==0.25.0 ; extra == 'docs'
+Requires-Dist: catalogue==2.0.10
+Requires-Dist: huggingface_hub<0.26,>=0.12.0
+Requires-Dist: importlib-metadata>=5.0.0
+Requires-Dist: jsonlines==3.1.0
+Requires-Dist: lazy-imports==0.3.1
+Requires-Dist: mock==4.0.3
+Requires-Dist: networkx>=2.7.1
+Requires-Dist: numpy<2.0,>=1.21
+Requires-Dist: packaging>=20.0
+Requires-Dist: Pillow>=10.0.0
+Requires-Dist: pypdf>=3.16.0
+Requires-Dist: pypdfium2>=4.30.0
+Requires-Dist: pyyaml>=6.0.1
+Requires-Dist: pyzmq>=16
+Requires-Dist: scipy>=1.13.1
+Requires-Dist: termcolor>=1.1
+Requires-Dist: tabulate>=0.7.7
+Requires-Dist: tqdm==4.64.0
+Provides-Extra: tf
+Requires-Dist: catalogue==2.0.10; extra == "tf"
+Requires-Dist: huggingface_hub<0.26,>=0.12.0; extra == "tf"
+Requires-Dist: importlib-metadata>=5.0.0; extra == "tf"
+Requires-Dist: jsonlines==3.1.0; extra == "tf"
+Requires-Dist: lazy-imports==0.3.1; extra == "tf"
+Requires-Dist: mock==4.0.3; extra == "tf"
+Requires-Dist: networkx>=2.7.1; extra == "tf"
+Requires-Dist: numpy<2.0,>=1.21; extra == "tf"
+Requires-Dist: packaging>=20.0; extra == "tf"
+Requires-Dist: Pillow>=10.0.0; extra == "tf"
+Requires-Dist: pypdf>=3.16.0; extra == "tf"
+Requires-Dist: pypdfium2>=4.30.0; extra == "tf"
+Requires-Dist: pyyaml>=6.0.1; extra == "tf"
+Requires-Dist: pyzmq>=16; extra == "tf"
+Requires-Dist: scipy>=1.13.1; extra == "tf"
+Requires-Dist: termcolor>=1.1; extra == "tf"
+Requires-Dist: tabulate>=0.7.7; extra == "tf"
+Requires-Dist: tqdm==4.64.0; extra == "tf"
+Requires-Dist: tensorpack==0.11; extra == "tf"
+Requires-Dist: protobuf==3.20.1; extra == "tf"
+Requires-Dist: tensorflow-addons>=0.17.1; extra == "tf"
+Requires-Dist: tf2onnx>=1.9.2; extra == "tf"
+Requires-Dist: python-doctr==0.8.1; extra == "tf"
+Requires-Dist: pycocotools>=2.0.2; extra == "tf"
+Requires-Dist: boto3==1.34.102; extra == "tf"
+Requires-Dist: pdfplumber>=0.11.0; extra == "tf"
+Requires-Dist: fasttext==0.9.2; extra == "tf"
+Requires-Dist: jdeskew>=0.2.2; extra == "tf"
+Requires-Dist: apted==1.0.3; extra == "tf"
+Requires-Dist: distance==0.1.3; extra == "tf"
+Requires-Dist: lxml>=4.9.1; extra == "tf"
 Provides-Extra: pt
-Requires-Dist: catalogue ==2.0.10 ; extra == 'pt'
-Requires-Dist: huggingface-hub <0.26,>=0.12.0 ; extra == 'pt'
-Requires-Dist: importlib-metadata >=5.0.0 ; extra == 'pt'
-Requires-Dist: jsonlines ==3.1.0 ; extra == 'pt'
-Requires-Dist: lazy-imports ==0.3.1 ; extra == 'pt'
-Requires-Dist: mock ==4.0.3 ; extra == 'pt'
-Requires-Dist: networkx >=2.7.1 ; extra == 'pt'
-Requires-Dist: numpy <2.0,>=1.21 ; extra == 'pt'
-Requires-Dist: packaging >=20.0 ; extra == 'pt'
-Requires-Dist: Pillow >=10.0.0 ; extra == 'pt'
-Requires-Dist: pypdf >=3.16.0 ; extra == 'pt'
-Requires-Dist: pypdfium2 >=4.30.0 ; extra == 'pt'
-Requires-Dist: pyyaml >=6.0.1 ; extra == 'pt'
-Requires-Dist: pyzmq >=16 ; extra == 'pt'
-Requires-Dist: scipy >=1.13.1 ; extra == 'pt'
-Requires-Dist: termcolor >=1.1 ; extra == 'pt'
-Requires-Dist: tabulate >=0.7.7 ; extra == 'pt'
-Requires-Dist: tqdm ==4.64.0 ; extra == 'pt'
-Requires-Dist: timm >=0.9.16 ; extra == 'pt'
-Requires-Dist: transformers >=4.36.0 ; extra == 'pt'
-Requires-Dist: accelerate >=0.29.1 ; extra == 'pt'
-Requires-Dist: python-doctr ==0.8.1 ; extra == 'pt'
-Requires-Dist: boto3 ==1.34.102 ; extra == 'pt'
-Requires-Dist: pdfplumber >=0.11.0 ; extra == 'pt'
-Requires-Dist: fasttext ==0.9.2 ; extra == 'pt'
-Requires-Dist: jdeskew >=0.2.2 ; extra == 'pt'
-Requires-Dist: apted ==1.0.3 ; extra == 'pt'
-Requires-Dist: distance ==0.1.3 ; extra == 'pt'
-Requires-Dist: lxml >=4.9.1 ; extra == 'pt'
+Requires-Dist: catalogue==2.0.10; extra == "pt"
+Requires-Dist: huggingface_hub<0.26,>=0.12.0; extra == "pt"
+Requires-Dist: importlib-metadata>=5.0.0; extra == "pt"
+Requires-Dist: jsonlines==3.1.0; extra == "pt"
+Requires-Dist: lazy-imports==0.3.1; extra == "pt"
+Requires-Dist: mock==4.0.3; extra == "pt"
+Requires-Dist: networkx>=2.7.1; extra == "pt"
+Requires-Dist: numpy<2.0,>=1.21; extra == "pt"
+Requires-Dist: packaging>=20.0; extra == "pt"
+Requires-Dist: Pillow>=10.0.0; extra == "pt"
+Requires-Dist: pypdf>=3.16.0; extra == "pt"
+Requires-Dist: pypdfium2>=4.30.0; extra == "pt"
+Requires-Dist: pyyaml>=6.0.1; extra == "pt"
+Requires-Dist: pyzmq>=16; extra == "pt"
+Requires-Dist: scipy>=1.13.1; extra == "pt"
+Requires-Dist: termcolor>=1.1; extra == "pt"
+Requires-Dist: tabulate>=0.7.7; extra == "pt"
+Requires-Dist: tqdm==4.64.0; extra == "pt"
+Requires-Dist: timm>=0.9.16; extra == "pt"
+Requires-Dist: transformers>=4.36.0; extra == "pt"
+Requires-Dist: accelerate>=0.29.1; extra == "pt"
+Requires-Dist: python-doctr==0.8.1; extra == "pt"
+Requires-Dist: boto3==1.34.102; extra == "pt"
+Requires-Dist: pdfplumber>=0.11.0; extra == "pt"
+Requires-Dist: fasttext==0.9.2; extra == "pt"
+Requires-Dist: jdeskew>=0.2.2; extra == "pt"
+Requires-Dist: apted==1.0.3; extra == "pt"
+Requires-Dist: distance==0.1.3; extra == "pt"
+Requires-Dist: lxml>=4.9.1; extra == "pt"
+Provides-Extra: docs
+Requires-Dist: tensorpack==0.11; extra == "docs"
+Requires-Dist: boto3==1.34.102; extra == "docs"
+Requires-Dist: transformers>=4.36.0; extra == "docs"
+Requires-Dist: accelerate>=0.29.1; extra == "docs"
+Requires-Dist: pdfplumber>=0.11.0; extra == "docs"
+Requires-Dist: lxml>=4.9.1; extra == "docs"
+Requires-Dist: lxml-stubs>=0.5.1; extra == "docs"
+Requires-Dist: jdeskew>=0.2.2; extra == "docs"
+Requires-Dist: jinja2==3.0.3; extra == "docs"
+Requires-Dist: mkdocs-material; extra == "docs"
+Requires-Dist: mkdocstrings-python; extra == "docs"
+Requires-Dist: griffe==0.25.0; extra == "docs"
+Provides-Extra: dev
+Requires-Dist: python-dotenv==1.0.0; extra == "dev"
+Requires-Dist: click; extra == "dev"
+Requires-Dist: black==23.7.0; extra == "dev"
+Requires-Dist: isort==5.13.2; extra == "dev"
+Requires-Dist: pylint==2.17.4; extra == "dev"
+Requires-Dist: mypy==1.4.1; extra == "dev"
+Requires-Dist: wandb; extra == "dev"
+Requires-Dist: types-PyYAML>=6.0.12.12; extra == "dev"
+Requires-Dist: types-termcolor>=1.1.3; extra == "dev"
+Requires-Dist: types-tabulate>=0.9.0.3; extra == "dev"
+Requires-Dist: types-tqdm>=4.66.0.5; extra == "dev"
+Requires-Dist: lxml-stubs>=0.5.1; extra == "dev"
+Requires-Dist: types-Pillow>=10.2.0.20240406; extra == "dev"
+Requires-Dist: types-urllib3>=1.26.25.14; extra == "dev"
 Provides-Extra: test
-Requires-Dist: pytest ==8.0.2 ; extra == 'test'
-Requires-Dist: pytest-cov ; extra == 'test'
-Provides-Extra: tf
-Requires-Dist: catalogue ==2.0.10 ; extra == 'tf'
-Requires-Dist: huggingface-hub <0.26,>=0.12.0 ; extra == 'tf'
-Requires-Dist: importlib-metadata >=5.0.0 ; extra == 'tf'
-Requires-Dist: jsonlines ==3.1.0 ; extra == 'tf'
-Requires-Dist: lazy-imports ==0.3.1 ; extra == 'tf'
-Requires-Dist: mock ==4.0.3 ; extra == 'tf'
-Requires-Dist: networkx >=2.7.1 ; extra == 'tf'
-Requires-Dist: numpy <2.0,>=1.21 ; extra == 'tf'
-Requires-Dist: packaging >=20.0 ; extra == 'tf'
-Requires-Dist: Pillow >=10.0.0 ; extra == 'tf'
-Requires-Dist: pypdf >=3.16.0 ; extra == 'tf'
-Requires-Dist: pypdfium2 >=4.30.0 ; extra == 'tf'
-Requires-Dist: pyyaml >=6.0.1 ; extra == 'tf'
-Requires-Dist: pyzmq >=16 ; extra == 'tf'
-Requires-Dist: scipy >=1.13.1 ; extra == 'tf'
-Requires-Dist: termcolor >=1.1 ; extra == 'tf'
-Requires-Dist: tabulate >=0.7.7 ; extra == 'tf'
-Requires-Dist: tqdm ==4.64.0 ; extra == 'tf'
-Requires-Dist: tensorpack ==0.11 ; extra == 'tf'
-Requires-Dist: protobuf ==3.20.1 ; extra == 'tf'
-Requires-Dist: tensorflow-addons >=0.17.1 ; extra == 'tf'
-Requires-Dist: tf2onnx >=1.9.2 ; extra == 'tf'
-Requires-Dist: python-doctr ==0.8.1 ; extra == 'tf'
-Requires-Dist: pycocotools >=2.0.2 ; extra == 'tf'
-Requires-Dist: boto3 ==1.34.102 ; extra == 'tf'
-Requires-Dist: pdfplumber >=0.11.0 ; extra == 'tf'
-Requires-Dist: fasttext ==0.9.2 ; extra == 'tf'
-Requires-Dist: jdeskew >=0.2.2 ; extra == 'tf'
-Requires-Dist: apted ==1.0.3 ; extra == 'tf'
-Requires-Dist: distance ==0.1.3 ; extra == 'tf'
-Requires-Dist: lxml >=4.9.1 ; extra == 'tf'
+Requires-Dist: pytest==8.0.2; extra == "test"
+Requires-Dist: pytest-cov; extra == "test"
 
 
 <p align="center">
@@ -176,12 +176,16 @@ pipelines. Its core function does not depend on any specific deep learning libra
    [**Torchscript**](https://pytorch.org/docs/stable/jit.html) (CPU) as well and [**Detectron2**](https://github.com/facebookresearch/detectron2/tree/main/detectron2) is not required 
    anymore for basic inference.
  - More angle predictors for determining the rotation of a document based on [**Tesseract**](https://github.com/tesseract-ocr/tesseract) and [**DocTr**](https://github.com/mindee/doctr)
-   (not contained in the built-in Analyzer).
  - Token classification with [**LiLT**](https://github.com/jpWang/LiLT) via 
    [**transformers**](https://github.com/huggingface/transformers). 
    We have added a model wrapper for token classification with LiLT and added a some LiLT models to the model catalog 
    that seem to look promising, especially if you want to train a model on non-english data. The training script for 
-   LayoutLM can be used for LiLT as well and we will be providing a notebook on how to train a model on a custom dataset soon.
+   LayoutLM can be used for LiLT as well.
+ - [**new**] There are two notebooks available that show, how to write a 
+   [custom predictor](https://github.com/deepdoctection/notebooks/blob/main/Doclaynet_Analyzer_Config.ipynb) based on 
+   a third party library that has not been supported yet and how to use 
+   [advanced configuration](https://github.com/deepdoctection/notebooks/blob/main/Doclaynet_Analyzer_Config.ipynb) to 
+   get links between layout segments e.g. captions and tables or figures.
 
 **deep**doctection provides on top of that methods for pre-processing inputs to models like cropping or resizing and to 
 post-process results, like validating duplicate outputs, relating words to detected layout segments or ordering words 

{deepdoctection-0.35.dist-info → deepdoctection-0.37.dist-info}/RECORD

@@ -1,33 +1,33 @@
-deepdoctection/__init__.py,sha256=RZpawNRTJPKNPFuONawVOsYWdr-rI8PPNXZhlPtOKtc,12580
+deepdoctection/__init__.py,sha256=7VELexCFRaBTCXHQpBoKhVi4hqUUgpcsLTqvHXHjufQ,12651
 deepdoctection/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 deepdoctection/analyzer/__init__.py,sha256=icClxrd20XutD6LxLgEPIWceSs4j_QfI3szCE-9BL2w,729
-deepdoctection/analyzer/_config.py,sha256=0cWtaI2e3jHNhufHZAqMje0YTTDAogKAHVl4VpYojAo,4874
+deepdoctection/analyzer/_config.py,sha256=NZl_REM8Ge2xfxvHN-mZR5KURcHfZii3xfMlKQwckbA,4864
 deepdoctection/analyzer/dd.py,sha256=DUOhOtwipHw5nabYqn3WGR9aZcgP0ma_bi_tjf9xscw,5973
-deepdoctection/analyzer/factory.py,sha256=T9jxtVLNFhocbsfWIGLPfFrEv21zQJzM6VdFt0yxMyg,23849
+deepdoctection/analyzer/factory.py,sha256=xmo5F9X7I6lp0ZWJv8QavpMyG8UWYLvMi4qogsZV1_s,31507
 deepdoctection/configs/__init__.py,sha256=TX_P6tqDOF1LK1mi9ruAl7x0mtv1Asm8cYWCz3Pe2dk,646
-deepdoctection/configs/conf_dd_one.yaml,sha256=orP-oeqtWbz5S9FJZJKxy1UqMwOYjL9g0DOX-wbamqU,2239
+deepdoctection/configs/conf_dd_one.yaml,sha256=td7XsyVhdXkhh5Pie7sT_WNjGTaxBOWgpxhkobHd1H0,2325
 deepdoctection/configs/conf_tesseract.yaml,sha256=oF6szDyoi15FHvq7yFUNIEjfA_jNLhGxoowiRsz_zY4,35
 deepdoctection/dataflow/__init__.py,sha256=CWRHMpmJaPk4xY_oIIFubCt-z11SguWrMWxHZ7rdrvY,845
 deepdoctection/dataflow/base.py,sha256=z4DCComSj5wStEPjtk0093cNNGfUMiDqx8dqz36nS_o,6221
 deepdoctection/dataflow/common.py,sha256=MyGA2VWlNMjQdIN_Jd-o0Ec3bDJmjQit4Nv0v43OCSQ,10119
 deepdoctection/dataflow/custom.py,sha256=3CK_1oL9p6nbOq8WtH5_vQUo70_8Z8pXY7kG0OFqzug,6803
-deepdoctection/dataflow/custom_serialize.py,sha256=CKeyw2Ayq_qAl0O5BoKkIOFJgteCt78h9QFTI23XhmQ,22818
+deepdoctection/dataflow/custom_serialize.py,sha256=WocuiYo2gkih5Z9lWAoIIfUewwYSDOhHzG7ZZjKlUic,22827
 deepdoctection/dataflow/parallel_map.py,sha256=8FhxJBWV-kjJrJ27jQtP3yYF6Ev6rz98worO60oi96c,15837
 deepdoctection/dataflow/serialize.py,sha256=4pYC7m9h53JCu99waVeKpHDpsCDDdYCrSZpP2QYSsgs,4555
 deepdoctection/dataflow/stats.py,sha256=Bsr6v7lcesKXUYtO9wjqlzx_Yq_uyIF3Lel-tQ0i4wI,9619
 deepdoctection/datapoint/__init__.py,sha256=3K406GbOPhoEp8koVaSbMocmSsmWifnSZ1SPb7C1lOY,1643
 deepdoctection/datapoint/annotation.py,sha256=FEgz4COxVDfjic0gG7kS6iHnWLBIgFnquQ63Cbj2a4Y,22531
 deepdoctection/datapoint/box.py,sha256=tkFuVM6xfx2jL7W4UED4qHXV572LSRdIsVJbrEiyIxI,23524
-deepdoctection/datapoint/convert.py,sha256=Gw2IjNiEotPu1yuMZqrIYB0mCAwafKt-VgMnrHj6S7U,6808
-deepdoctection/datapoint/image.py,sha256=EvZlVwJjMAcL1z8RNPBvZ8fwdJvkGuGpcFxCP1y26Go,33045
-deepdoctection/datapoint/view.py,sha256=7qSX4DQw9OPQQSKfSjV8e5i6jLyu6hOMceSKJAob2N8,42154
+deepdoctection/datapoint/convert.py,sha256=O7920pIomyEkzXwxpFsrzfhn7Pl6UzVGhNzv90VcuKU,7099
+deepdoctection/datapoint/image.py,sha256=DIXXXD2yKsacg47Wt_GEYEIe1MQkrd06Yr5xAWv_n64,33047
+deepdoctection/datapoint/view.py,sha256=1rVMuqucCrI5zlwyXMADJQBV38V_zSNFqFyBi3cMA1E,44914
 deepdoctection/datasets/__init__.py,sha256=-A3aR90aDsHPmVM35JavfnQ2itYSCn3ujl4krRni1QU,1076
 deepdoctection/datasets/adapter.py,sha256=Ly_vbOAgVI73V41FUccnSX1ECTOyesW_qsuvQuvOZbw,7796
 deepdoctection/datasets/base.py,sha256=DT4i-d74sIEiUNC6UspIHNJuHSK0t1dBv7qwadg4rLw,22341
 deepdoctection/datasets/dataflow_builder.py,sha256=cYU2zV3gZW2bFvMHimlO9VIl3BAUaCwML08cCIQ8Em4,4107
 deepdoctection/datasets/info.py,sha256=6y5TfiUhQppynbMFP5JmUPk95ggsVCtGIw4dYh2lVus,20501
 deepdoctection/datasets/registry.py,sha256=ZjzVzjsCgNXJuZZZtR98_yKocADmh4EBGV5JqJbGjWk,2543
-deepdoctection/datasets/save.py,sha256=khYQ4t94FOu9RWMimP9E4kASq25f61SIow78NHaX1pg,3349
+deepdoctection/datasets/save.py,sha256=Y9508Qqp8gIGN7pbGgVBBnkiC6NdCb9L2YR4wVvEUxM,3350
 deepdoctection/datasets/instances/__init__.py,sha256=XEc_4vT5lDn6bbZID9ujDEumWu8Ec2W-QS4pI_bfWWE,1388
 deepdoctection/datasets/instances/doclaynet.py,sha256=wRZT7wMTilZBLZ1gKY2cWReD1EGT735vOOTy0pD0N6M,12038
 deepdoctection/datasets/instances/fintabnet.py,sha256=qYzFK1dWF6MEPkHamP255DvAzlQT_GnkvDe1aM7CgjA,12006
@@ -44,13 +44,13 @@ deepdoctection/datasets/instances/xsl/pascal_voc.xsl,sha256=DlzFV2P8NtQKXVe96i-m
 deepdoctection/eval/__init__.py,sha256=rbns4tSEQ30QLj8h0mm3A0dCaKuN9LDxxpVypKKSXSE,932
 deepdoctection/eval/accmetric.py,sha256=4bND-xz9AZu9ACYRkEzn9V6Jn8MEiqnF7kxSp4k_baE,19655
 deepdoctection/eval/base.py,sha256=gCvhTdwEaCKplYTWPMjGvtB_0Vbq2KBJWFHq8mMlLPA,4814
-deepdoctection/eval/cocometric.py,sha256=Co7XaLQzp7qxw8UQaG2D68PzY6eA9aRNueeo_zaMJLM,8777
+deepdoctection/eval/cocometric.py,sha256=4cpNmF3xZjInCOWOoVU_7itQxLI-zr0O6suNjPU2xWc,11020
 deepdoctection/eval/eval.py,sha256=B9PUZBjj6KzXHLOxUVn3QHiOcBQogfJmp9mjopbMo9k,19721
 deepdoctection/eval/registry.py,sha256=v4mp-s67vBVRu1nQzuGlYPViQnMSeIXEcF_WmvfUCoU,1051
 deepdoctection/eval/tedsmetric.py,sha256=rKw-734Y9CpBtIfkBSPQF2vAZxnIdWrI9Zc723P7RxI,9529
 deepdoctection/eval/tp_eval_callback.py,sha256=SXsXumoyxq-MIH9Cep5eUOwnNshMbKmC6mYOGwCg0pM,5283
 deepdoctection/extern/__init__.py,sha256=9Iks9b4Q_LynjcV167TVCoK8YsQRUcA2jjmAmDNA_X8,1056
-deepdoctection/extern/base.py,sha256=ajzFzD9BrFwnly4SziN8PadI-PBOzzVRlIGPm_sNllE,24142
+deepdoctection/extern/base.py,sha256=ONPgappl_P5HSwQr42FatuRnwMTvUPecPsCztDTN0Hw,24108
 deepdoctection/extern/d2detect.py,sha256=zrKv1yurApnjD7QZIZk_8LYCahjmN82MQUjHjv8zvkQ,22127
 deepdoctection/extern/deskew.py,sha256=sPoixu8S9he-0wbs-jgxtPE2V9BiP4-3uZlb6F5Y1SA,3077
 deepdoctection/extern/doctrocr.py,sha256=T3_tvlih22_dVCBZypS1Y8tjQQB1fkAxIbGdUGHIapQ,24473
@@ -94,8 +94,8 @@ deepdoctection/mapper/d2struct.py,sha256=Dx-YnycsIQH4a5-9Gn_yMhiQ-gOFgMueNeH3rhX
 deepdoctection/mapper/hfstruct.py,sha256=2PjGKsYturVJBimLT1CahYh09KSRAFEHz_QNtC162kQ,5551
 deepdoctection/mapper/laylmstruct.py,sha256=abMZkYU2W0e_VcCm_c0ZXNFuv-lfMFWcTedcZS5EYvE,42935
 deepdoctection/mapper/maputils.py,sha256=eI6ZcDg9W5uB6xQNBZpMIdEd86HlCxTtkJuyROdTqiw,8146
-deepdoctection/mapper/match.py,sha256=E7Qna6zLDIxlI7puOL9BjjZKuRry-zONs8TLWmyEMIQ,9580
-deepdoctection/mapper/misc.py,sha256=rCqHOcsCfVPXs36AWK0rZ2kk0CUM3yXV370_zyIGBJ4,6518
+deepdoctection/mapper/match.py,sha256=pCWZpz2R8JahiKXCw7dxKRTLiPgJXeVDgkddDPLy_c0,9643
+deepdoctection/mapper/misc.py,sha256=NLSSgk066Tkrrdi075HkqV7cP-iqT9fv_MtyAJ-8gOg,6743
 deepdoctection/mapper/pascalstruct.py,sha256=TzVU1p0oiw0nOuxTFFbEB9vXJxH1v6VUvTJ7MD0manU,3828
 deepdoctection/mapper/prodigystruct.py,sha256=Re4Sd_zAp6qOvbXZLmMJeG0IGEfMQxebuyDeZgMcTa8,6827
 deepdoctection/mapper/pubstruct.py,sha256=YxsrZ-E0pD45Mm_VCPQB9yEgHsTPkw4htt-3DwCRX1k,23361
@@ -106,7 +106,7 @@ deepdoctection/pipe/anngen.py,sha256=3319l4aaXzcY4w6ItVBNPX8LGS5fHFDVtyVY9KMefac
 deepdoctection/pipe/base.py,sha256=Davjkf3D837y9AIITcx7yXdebmVaz6Moyw_5Wi3nfmg,13561
 deepdoctection/pipe/common.py,sha256=haOb4v0jLX3r41BSC8cVseX2E320_HkSrGlZsQiKE2g,17728
 deepdoctection/pipe/concurrency.py,sha256=AAKRsVgaBEYNluntbDa46SBF1JZ_XqnWLDSWrNvAzEo,9657
-deepdoctection/pipe/doctectionpipe.py,sha256=I6B6HT_BG2ByQ3Rjsui3-Ct31yLmodx-iuZnujXaiSc,8953
+deepdoctection/pipe/doctectionpipe.py,sha256=uhsrSuwaHcOMj8b8i6wCpPaZlSxCTaeHVhMokJ8vRSI,11835
 deepdoctection/pipe/language.py,sha256=5zI0UQC6Fh12_r2pfVL42HoCGz2hpHrOhpXAn5m-rYw,5451
 deepdoctection/pipe/layout.py,sha256=xIhnJpyUSbvLbhTXyAKXY1hmG9352jihGYFSclTH_1g,5567
 deepdoctection/pipe/lm.py,sha256=Sp-b7smeslNDyioEfNjuNBUxAuFKn3-OKpCZkGXri_c,16643
@@ -129,20 +129,20 @@ deepdoctection/utils/develop.py,sha256=4HyTarkFbJwctL-Hgu1TU_LSJppHvaroDbcyHsxhI
 deepdoctection/utils/env_info.py,sha256=TnCA-LOTj4WIHd9yvn1AaoPWsLmPgc42l-BJmGV6zmM,19147
 deepdoctection/utils/error.py,sha256=_3q9VepKfEhsM3H033_Fu0hwBzMSjsWALsjyJbGAZr8,2367
 deepdoctection/utils/file_utils.py,sha256=IRElrcND0YEiU1QELw5hfXeNA39uE2_nyzh9-X7YcxI,19477
-deepdoctection/utils/fs.py,sha256=C4ktrzjoVtX9kgycv5YrEigDI9byi65b6_D0aKsGM4Y,10161
+deepdoctection/utils/fs.py,sha256=x842BxUP5bbjJ2cofw-g4dKJv4QAaGzda4qnAazabO4,10281
 deepdoctection/utils/identifier.py,sha256=QkNaGGqPynHwDPnd3_m8iur4Cv64rcQa7qolCE7Qphk,2159
 deepdoctection/utils/logger.py,sha256=J0OVKiXP_2A82MWbbJoOeMEJ-75aZu5npgaS_yI6mVA,10003
 deepdoctection/utils/metacfg.py,sha256=hD76KQ_RnD_5B02qLI2Zxf3WfnsnXhEI_KUTKpw91RI,5711
 deepdoctection/utils/mocks.py,sha256=IkN3-IzAl4eX0ibgKIHg8IY7ykVw6BnpF6XnxKnKaZI,2389
-deepdoctection/utils/pdf_utils.py,sha256=OAQjE9xHVNcDsFqAvX47Lu-mgmoMpVXqIf5pOK8AwxY,11595
+deepdoctection/utils/pdf_utils.py,sha256=G0m8kUn2HwwyZWH_BcrDkm-m3MP9GN9SWHj5VhB7swY,12845
 deepdoctection/utils/settings.py,sha256=k6OyuWbj-IPeaO9zT9RZ-5Yad1wNhWGYqGLZdtgXAZY,12464
 deepdoctection/utils/tqdm.py,sha256=cBUtR0L1x0KMeYrLP2rrzyzCamCjpQAKroHXLv81_pk,1820
 deepdoctection/utils/transform.py,sha256=3kCgsEeRkG1efCdkfvj7tUFMs-e2jbjbflq826F2GPU,8502
 deepdoctection/utils/types.py,sha256=_3dmPdCIZNLbgU5QP5k_c5phDf18xLe1kYL6t2nM45s,2953
-deepdoctection/utils/utils.py,sha256=ANzyIX6AY1yc-4gcn6yxksV84sPrJDaUurUNVatAFu8,5168
-deepdoctection/utils/viz.py,sha256=Xm6pKlhM29UWBBGZHlWFl9XYFDAqaYDdwHXwe26Hvqo,25728
-deepdoctection-0.35.dist-info/LICENSE,sha256=GQ0rUvuGdrMNEI3iHK5UQx6dIMU1QwAuyXsxUHn5MEQ,11351
-deepdoctection-0.35.dist-info/METADATA,sha256=B6pPQjRYWcqd1p-3ul3PhflYOcKq2ZpP5D-i8kr7qgk,19403
-deepdoctection-0.35.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
-deepdoctection-0.35.dist-info/top_level.txt,sha256=hs2DdoOL9h4mnHhmO82BT4pz4QATIoOZ20PZmlnxFI8,15
-deepdoctection-0.35.dist-info/RECORD,,
+deepdoctection/utils/utils.py,sha256=csVs_VvCq4QBETPoE2JdTTL4MFYnD4xh-Js5vRb612g,6492
+deepdoctection/utils/viz.py,sha256=Jf8ePNYWlpuyaS6SeTYQ4OyA3eNhtgjvAQZnGNdgHC0,27051
+deepdoctection-0.37.dist-info/LICENSE,sha256=GQ0rUvuGdrMNEI3iHK5UQx6dIMU1QwAuyXsxUHn5MEQ,11351
+deepdoctection-0.37.dist-info/METADATA,sha256=0qGgmf07xmNRJx55yfMagHcfAoQG6GO9KTw6b0tv0uA,19543
+deepdoctection-0.37.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+deepdoctection-0.37.dist-info/top_level.txt,sha256=hs2DdoOL9h4mnHhmO82BT4pz4QATIoOZ20PZmlnxFI8,15
+deepdoctection-0.37.dist-info/RECORD,,

{deepdoctection-0.35.dist-info → deepdoctection-0.37.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.3.0)
+Generator: setuptools (75.6.0)
 Root-Is-Purelib: true
 Tag: py3-none-any