deepdoctection 0.44.0__tar.gz → 0.44.1__tar.gz

{deepdoctection-0.44.0 → deepdoctection-0.44.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deepdoctection
-Version: 0.44.0
+Version: 0.44.1
 Summary: Repository for Document AI
 Home-page: https://github.com/deepdoctection/deepdoctection
 Author: Dr. Janis Meyer
@@ -27,7 +27,7 @@ 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: pypdf>=6.0.0
 Requires-Dist: pypdfium2>=4.30.0
 Requires-Dist: pyyaml>=6.0.1
 Requires-Dist: pyzmq>=16
@@ -46,7 +46,7 @@ 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: pypdf>=6.0.0; extra == "tf"
 Requires-Dist: pypdfium2>=4.30.0; extra == "tf"
 Requires-Dist: pyyaml>=6.0.1; extra == "tf"
 Requires-Dist: pyzmq>=16; extra == "tf"
@@ -78,7 +78,7 @@ 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: pypdf>=6.0.0; extra == "pt"
 Requires-Dist: pypdfium2>=4.30.0; extra == "pt"
 Requires-Dist: pyyaml>=6.0.1; extra == "pt"
 Requires-Dist: pyzmq>=16; extra == "pt"

{deepdoctection-0.44.0 → deepdoctection-0.44.1}/deepdoctection/__init__.py

@@ -25,7 +25,7 @@ from .utils.logger import LoggingRecord, logger
 
 # pylint: enable=wrong-import-position
 
-__version__ = "0.44.0"
+__version__ = "0.44.1"
 
 _IMPORT_STRUCTURE = {
     "analyzer": ["config_sanity_checks", "get_dd_analyzer", "ServiceFactory"],
@@ -315,6 +315,8 @@ _IMPORT_STRUCTURE = {
         "get_apted_requirement",
         "distance_available",
         "get_distance_requirement",
+        "numpy_v1_available",
+        "get_numpy_v1_requirement",
         "transformers_available",
         "get_transformers_requirement",
         "detectron2_available",

{deepdoctection-0.44.0 → deepdoctection-0.44.1}/deepdoctection/datapoint/image.py

@@ -42,6 +42,7 @@ from .convert import as_dict, convert_b64_to_np_array, convert_np_array_to_b64,
 
 class MetaAnnotationDict(TypedDict):
     """MetaAnnotationDict"""
+
     image_annotations: list[str]
     sub_categories: dict[str, dict[str, list[str]]]
     relationships: dict[str, list[str]]

{deepdoctection-0.44.0 → deepdoctection-0.44.1}/deepdoctection/datapoint/view.py

@@ -42,13 +42,60 @@ from ..utils.settings import (
     get_type,
 )
 from ..utils.transform import ResizeTransform, box_to_point4, point4_to_box
-from ..utils.types import HTML, AnnotationDict, Chunks, ImageDict, PathLikeOrStr, PixelValues, Text_, csv
+from ..utils.types import HTML, AnnotationDict, Chunks, ImageDict, PathLikeOrStr, PixelValues, csv
 from ..utils.viz import draw_boxes, interactive_imshow, viz_handler
 from .annotation import CategoryAnnotation, ContainerAnnotation, ImageAnnotation, ann_from_dict
 from .box import BoundingBox, crop_box_from_image
 from .image import Image
 
 
+@dataclass(frozen=True)
+class Text_:
+    """
+    Immutable dataclass for storing structured text extraction results.
+
+    Attributes:
+        text: The concatenated text string.
+        words: List of word strings.
+        ann_ids: List of annotation IDs for each word.
+        token_classes: List of token class names for each word.
+        token_class_ann_ids: List of annotation IDs for each token class.
+        token_tags: List of token tag names for each word.
+        token_tag_ann_ids: List of annotation IDs for each token tag.
+        token_class_ids: List of token class IDs.
+        token_tag_ids: List of token tag IDs.
+    """
+
+    text: str = ""
+    words: list[str] = field(default_factory=list)
+    ann_ids: list[str] = field(default_factory=list)
+    token_classes: list[str] = field(default_factory=list)
+    token_class_ann_ids: list[str] = field(default_factory=list)
+    token_tags: list[str] = field(default_factory=list)
+    token_tag_ann_ids: list[str] = field(default_factory=list)
+    token_class_ids: list[str] = field(default_factory=list)
+    token_tag_ids: list[str] = field(default_factory=list)
+
+    def as_dict(self) -> dict[str, Union[list[str], str]]:
+        """
+        Returns the Text_ as a dictionary.
+
+        Returns:
+            A dictionary representation of the Text_ dataclass.
+        """
+        return {
+            "text": self.text,
+            "words": self.words,
+            "ann_ids": self.ann_ids,
+            "token_classes": self.token_classes,
+            "token_class_ann_ids": self.token_class_ann_ids,
+            "token_tags": self.token_tags,
+            "token_tag_ann_ids": self.token_tag_ann_ids,
+            "token_class_ids": self.token_class_ids,
+            "token_tag_ids": self.token_tag_ids,
+        }
+
+
 class ImageAnnotationBaseView(ImageAnnotation):
     """
     Consumption class for having easier access to categories added to an `ImageAnnotation`.
@@ -263,13 +310,28 @@ class Layout(ImageAnnotationBaseView):
         """
         words = self.get_ordered_words()
         if words:
-            characters, ann_ids, token_classes, token_tags, token_classes_ids, token_tag_ids = zip(
+            (
+                characters,
+                ann_ids,
+                token_classes,
+                token_class_ann_ids,
+                token_tags,
+                token_tag_ann_ids,
+                token_classes_ids,
+                token_tag_ids,
+            ) = map(list, zip(
                 *[
                     (
                         word.characters,
                         word.annotation_id,
                         word.token_class,
+                        word.get_sub_category(WordType.TOKEN_CLASS).annotation_id
+                        if WordType.TOKEN_CLASS in word.sub_categories
+                        else None,
                         word.token_tag,
+                        word.get_sub_category(WordType.TOKEN_TAG).annotation_id
+                        if WordType.TOKEN_TAG in word.sub_categories
+                        else None,
                         word.get_sub_category(WordType.TOKEN_CLASS).category_id
                         if WordType.TOKEN_CLASS in word.sub_categories
                         else None,
@@ -279,25 +341,40 @@ class Layout(ImageAnnotationBaseView):
                     )
                     for word in words
                 ]
-            )
+            ))
         else:
-            characters, ann_ids, token_classes, token_tags, token_classes_ids, token_tag_ids = (
-                [],  # type: ignore
-                [],  # type: ignore
-                [],  # type: ignore
-                [],  # type: ignore
-                [],  # type: ignore
-                [],  # type: ignore
+            (
+                characters,
+                ann_ids,
+                token_classes,
+                token_class_ann_ids,
+                token_tags,
+                token_tag_ann_ids,
+                token_classes_ids,
+                token_tag_ids,
+            ) = (
+                [],
+                [],
+                [],
+                [],
+                [],
+                [],
+                [],
+                [],
             )
-        return {
-            "text": " ".join(characters),
-            "words": characters,
-            "ann_ids": ann_ids,
-            "token_classes": token_classes,
-            "token_tags": token_tags,
-            "token_class_ids": token_classes_ids,
-            "token_tag_ids": token_tag_ids,
-        }
+
+        return Text_(
+            text=" ".join(characters), # type: ignore
+            words=characters, # type: ignore
+            ann_ids=ann_ids, # type: ignore
+            token_classes=token_classes, # type: ignore
+            token_class_ann_ids=token_class_ann_ids, # type: ignore
+            token_tags=token_tags, # type: ignore
+            token_tag_ann_ids=token_tag_ann_ids, # type: ignore
+            token_class_ids=token_classes_ids, # type: ignore
+            token_tag_ids=token_tag_ids, # type: ignore
+        )
+
 
     def get_attribute_names(self) -> set[str]:
         attr_names = (
@@ -626,26 +703,34 @@ class Table(Layout):
         words: list[str] = []
         ann_ids: list[str] = []
         token_classes: list[str] = []
+        token_class_ann_ids: list[str] = []
         token_tags: list[str] = []
+        token_tag_ann_ids: list[str] = []
         token_class_ids: list[str] = []
         token_tag_ids: list[str] = []
         for cell in cells:
-            text.append(cell.text_["text"])
-            words.extend(cell.text_["words"])
-            ann_ids.extend(cell.text_["ann_ids"])
-            token_classes.extend(cell.text_["token_classes"])
-            token_tags.extend(cell.text_["token_tags"])
-            token_class_ids.extend(cell.text_["token_class_ids"])
-            token_tag_ids.extend(cell.text_["token_tag_ids"])
-        return {
-            "text": " ".join(text),
-            "words": words,
-            "ann_ids": ann_ids,
-            "token_classes": token_classes,
-            "token_tags": token_tags,
-            "token_class_ids": token_class_ids,
-            "token_tag_ids": token_tag_ids,
-        }
+            text_ = cell.text_
+            text.append(text_.text)
+            words.extend(text_.words)
+            ann_ids.extend(text_.ann_ids)
+            token_classes.extend(text_.token_classes)
+            token_class_ann_ids.extend(text_.token_class_ann_ids)
+            token_tags.extend(text_.token_tags)
+            token_tag_ann_ids.extend(text_.token_tag_ann_ids)
+            token_class_ids.extend(text_.token_class_ids)
+            token_tag_ids.extend(text_.token_tag_ids)
+        return Text_(
+            text=" ".join(text),
+            words=words,
+            ann_ids=ann_ids,
+            token_classes=token_classes,
+            token_class_ann_ids=token_class_ann_ids,
+            token_tags=token_tags,
+            token_tag_ann_ids=token_tag_ann_ids,
+            token_class_ids=token_class_ids,
+            token_tag_ids=token_tag_ids,
+        )
+
 
     @property
     def words(self) -> list[ImageAnnotationBaseView]:
@@ -1053,7 +1138,7 @@ class Page(Image):
 
             ```python
                 {"text": text string,
-                 "text_list": list of single words,
+                 "words": list of single words,
                  "annotation_ids": word annotation ids}
          ```
         """
@@ -1062,26 +1147,34 @@ class Page(Image):
         words: list[str] = []
         ann_ids: list[str] = []
         token_classes: list[str] = []
+        token_class_ann_ids: list[str] = []
         token_tags: list[str] = []
+        token_tag_ann_ids: list[str] = []
         token_class_ids: list[str] = []
         token_tag_ids: list[str] = []
         for block in block_with_order:
-            text.append(block.text_["text"])  # type: ignore
-            words.extend(block.text_["words"])  # type: ignore
-            ann_ids.extend(block.text_["ann_ids"])  # type: ignore
-            token_classes.extend(block.text_["token_classes"])  # type: ignore
-            token_tags.extend(block.text_["token_tags"])  # type: ignore
-            token_class_ids.extend(block.text_["token_class_ids"])  # type: ignore
-            token_tag_ids.extend(block.text_["token_tag_ids"])  # type: ignore
-        return {
-            "text": " ".join(text),
-            "words": words,
-            "ann_ids": ann_ids,
-            "token_classes": token_classes,
-            "token_tags": token_tags,
-            "token_class_ids": token_class_ids,
-            "token_tag_ids": token_tag_ids,
-        }
+            text_ = block.text_
+            text.append(text_.text)  # type: ignore
+            words.extend(text_.words)  # type: ignore
+            ann_ids.extend(text_.ann_ids)  # type: ignore
+            token_classes.extend(text_.token_classes)  # type: ignore
+            token_class_ann_ids.extend(text_.token_class_ann_ids)  # type: ignore
+            token_tags.extend(text_.token_tags)  # type: ignore
+            token_tag_ann_ids.extend(text_.token_tag_ann_ids)  # type: ignore
+            token_class_ids.extend(text_.token_class_ids)  # type: ignore
+            token_tag_ids.extend(text_.token_tag_ids)  # type: ignore
+        return Text_(
+            text=" ".join(text),
+            words=words,
+            ann_ids=ann_ids,
+            token_classes=token_classes,
+            token_class_ann_ids=token_class_ann_ids,
+            token_tags=token_tags,
+            token_tag_ann_ids=token_tag_ann_ids,
+            token_class_ids=token_class_ids,
+            token_tag_ids=token_tag_ann_ids,
+        )
+
 
     def get_layout_context(self, annotation_id: str, context_size: int = 3) -> list[ImageAnnotationBaseView]:
         """

{deepdoctection-0.44.0 → deepdoctection-0.44.1}/deepdoctection/datasets/base.py

@@ -408,6 +408,7 @@ class MergeDataset(DatasetBase):
 
 class DatasetCardDict(TypedDict):
     """DatasetCardDict"""
+
     name: str
     dataset_type: Union[str, Any]
     location: str

{deepdoctection-0.44.0 → deepdoctection-0.44.1}/deepdoctection/extern/fastlang.py

@@ -29,7 +29,8 @@ from typing import Any, Mapping, Union
 
 from lazy_imports import try_import
 
-from ..utils.file_utils import Requirement, get_fasttext_requirement
+from ..utils.develop import deprecated
+from ..utils.file_utils import Requirement, get_fasttext_requirement, get_numpy_v1_requirement
 from ..utils.settings import TypeOrStr, get_type
 from ..utils.types import PathLikeOrStr
 from .base import DetectionResult, LanguageDetector, ModelCategories
@@ -69,6 +70,7 @@ class FasttextLangDetectorMixin(LanguageDetector, ABC):
         return "fasttext_" + "_".join(Path(path_weights).parts[-2:])
 
 
+@deprecated("As FastText archived, it will be deprecated in the near future.", "2025-08-17")
 class FasttextLangDetector(FasttextLangDetectorMixin):
     """
     Fasttext language detector wrapper. Two models provided in the fasttext library can be used to identify languages.
@@ -114,7 +116,7 @@ class FasttextLangDetector(FasttextLangDetectorMixin):
 
     @classmethod
     def get_requirements(cls) -> list[Requirement]:
-        return [get_fasttext_requirement()]
+        return [get_numpy_v1_requirement(), get_fasttext_requirement()]
 
     def clone(self) -> FasttextLangDetector:
         return self.__class__(self.path_weights, self.categories.get_categories(), self.categories_orig)

{deepdoctection-0.44.0 → deepdoctection-0.44.1}/deepdoctection/mapper/laylmstruct.py

@@ -806,17 +806,17 @@ def image_to_raw_lm_features(
     raw_features["image_id"] = page.image_id
     raw_features["width"] = page.width
     raw_features["height"] = page.height
-    raw_features["ann_ids"] = text_["ann_ids"]
-    raw_features["words"] = text_["words"]
+    raw_features["ann_ids"] = text_.ann_ids
+    raw_features["words"] = text_.words
     # We use a dummy bounding box for all bounding boxes so that we can pass the raw features to
     # raw_features_to_layoutlm_features
-    raw_features["bbox"] = [_CLS_BOX] * len(text_["words"])
+    raw_features["bbox"] = [_CLS_BOX] * len(text_.words)
     raw_features["dataset_type"] = dataset_type
 
-    if use_token_tag and text_["token_tags"]:
-        raw_features["labels"] = text_["token_tags"]
-    elif text_["token_classes"]:
-        raw_features["labels"] = text_["token_classes"]
+    if use_token_tag and text_.token_tags:
+        raw_features["labels"] = text_.token_tags
+    elif text_.token_classes:
+        raw_features["labels"] = text_.token_classes
     elif page.document_type is not None:
         document_type_id = page.image_orig.summary.get_sub_category(PageType.DOCUMENT_TYPE).category_id - 1
         raw_features["labels"] = [document_type_id]

{deepdoctection-0.44.0 → deepdoctection-0.44.1}/deepdoctection/utils/file_utils.py

@@ -18,6 +18,7 @@ from types import ModuleType
 from typing import Any, Union, no_type_check
 
 import importlib_metadata
+import numpy as np
 from packaging import version
 
 from .error import DependencyError
@@ -249,6 +250,39 @@ def get_distance_requirement() -> Requirement:
     return "distance", distance_available(), _DISTANCE_ERR_MSG
 
 
+_NUMPY_V1_ERR_MSG = "numpy v1 must be installed."
+
+
+def numpy_v1_available() -> bool:
+    """
+    Check if the installed NumPy version is version 1.
+
+    This helper function determines whether the currently installed version
+    of NumPy is version 1 by inspecting its major version number.
+
+    Returns:
+        True if the installed NumPy version is 1, otherwise False
+    """
+    major_version = np.__version__.split('.', maxsplit=1)[0]
+    print(f"major version: {major_version}")
+    if major_version in (1, "1"):
+        return True
+    return False
+
+
+def get_numpy_v1_requirement() -> Requirement:
+    """
+    Retrieves the requirement details for numpy version 1.
+
+    Returns:
+        A tuple containing three elements:
+            - The requirement name for numpy version 1.
+            - A Boolean value indicating whether numpy version 1 is available.
+            - An error message in case numpy version 1 is not available.
+    """
+    return "numpy v1", numpy_v1_available(), _NUMPY_V1_ERR_MSG
+
+
 # Transformers
 _TRANSFORMERS_AVAILABLE = importlib.util.find_spec("transformers") is not None
 _TRANSFORMERS_ERR_MSG = f"transformers must be installed. {_GENERIC_ERR_MSG}"

{deepdoctection-0.44.0 → deepdoctection-0.44.1}/deepdoctection/utils/types.py

@@ -70,7 +70,6 @@ AnnotationDict: TypeAlias = dict[str, Any]
 ImageDict: TypeAlias = dict[str, Any]
 
 # We use these types for output types of the Page object
-Text_: TypeAlias = dict[str, Any]
 HTML: TypeAlias = str
 csv: TypeAlias = list[list[str]]
 Chunks: TypeAlias = list[tuple[str, str, int, str, str, str, str]]

{deepdoctection-0.44.0 → deepdoctection-0.44.1}/deepdoctection.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deepdoctection
-Version: 0.44.0
+Version: 0.44.1
 Summary: Repository for Document AI
 Home-page: https://github.com/deepdoctection/deepdoctection
 Author: Dr. Janis Meyer
@@ -27,7 +27,7 @@ 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: pypdf>=6.0.0
 Requires-Dist: pypdfium2>=4.30.0
 Requires-Dist: pyyaml>=6.0.1
 Requires-Dist: pyzmq>=16
@@ -46,7 +46,7 @@ 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: pypdf>=6.0.0; extra == "tf"
 Requires-Dist: pypdfium2>=4.30.0; extra == "tf"
 Requires-Dist: pyyaml>=6.0.1; extra == "tf"
 Requires-Dist: pyzmq>=16; extra == "tf"
@@ -78,7 +78,7 @@ 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: pypdf>=6.0.0; extra == "pt"
 Requires-Dist: pypdfium2>=4.30.0; extra == "pt"
 Requires-Dist: pyyaml>=6.0.1; extra == "pt"
 Requires-Dist: pyzmq>=16; extra == "pt"

{deepdoctection-0.44.0 → deepdoctection-0.44.1}/deepdoctection.egg-info/requires.txt

@@ -8,7 +8,7 @@ networkx>=2.7.1
 numpy<2.0,>=1.21
 packaging>=20.0
 Pillow>=10.0.0
-pypdf>=3.16.0
+pypdf>=6.0.0
 pypdfium2>=4.30.0
 pyyaml>=6.0.1
 pyzmq>=16
@@ -58,7 +58,7 @@ networkx>=2.7.1
 numpy<2.0,>=1.21
 packaging>=20.0
 Pillow>=10.0.0
-pypdf>=3.16.0
+pypdf>=6.0.0
 pypdfium2>=4.30.0
 pyyaml>=6.0.1
 pyzmq>=16
@@ -94,7 +94,7 @@ networkx>=2.7.1
 numpy<2.0,>=1.21
 packaging>=20.0
 Pillow>=10.0.0
-pypdf>=3.16.0
+pypdf>=6.0.0
 pypdfium2>=4.30.0
 pyyaml>=6.0.1
 pyzmq>=16

{deepdoctection-0.44.0 → deepdoctection-0.44.1}/setup.py

@@ -56,7 +56,7 @@ _DEPS = [
     "packaging>=20.0",
     "Pillow>=10.0.0",
     "pycocotools>=2.0.2",
-    "pypdf>=3.16.0",
+    "pypdf>=6.0.0",
     "pypdfium2>=4.30.0",
     "python-prctl",
     "pyyaml>=6.0.1",