deepdoctection 0.43.1__py3-none-any.whl → 0.43.3__py3-none-any.whl

deepdoctection/__init__.py

@@ -25,7 +25,7 @@ from .utils.logger import LoggingRecord, logger
 
 # pylint: enable=wrong-import-position
 
-__version__ = "0.43.1"
+__version__ = "0.43.3"
 
 _IMPORT_STRUCTURE = {
     "analyzer": ["config_sanity_checks", "get_dd_analyzer", "ServiceFactory"],

deepdoctection/datapoint/image.py

@@ -479,8 +479,8 @@ class Image:
 
     def remove(
         self,
-        annotation_ids: Optional[Union[str, list[str]]] = None,
-        service_ids: Optional[Union[str, list[str]]] = None,
+        annotation_ids: Optional[Union[str, Sequence[str]]] = None,
+        service_ids: Optional[Union[str, Sequence[str]]] = None,
     ) -> None:
         """
         Instead of removing consider deactivating annotations.

deepdoctection/datapoint/view.py

@@ -183,7 +183,7 @@ class Word(ImageAnnotationBaseView):
         attr_names = (
             set(WordType)
             .union(super().get_attribute_names())
-            .union({Relationships.READING_ORDER, Relationships.LAYOUT_LINK})
+            .union({Relationships.READING_ORDER, Relationships.LAYOUT_LINK, Relationships.LINK})
         )
         return {attr_name.value if isinstance(attr_name, ObjectTypes) else attr_name for attr_name in attr_names}
 
@@ -773,6 +773,7 @@ class Page(Image):
         "figures",
         "residual_layouts",
         "document_summary",
+        "document_mapping",
     }
     include_residual_text_container: bool = True
 
@@ -1389,19 +1390,32 @@ class Page(Image):
             include_residual_text_container=include_residual_text_container,
         )
 
-    def get_token(self) -> list[Mapping[str, str]]:
+    def get_entities(self) -> list[Mapping[str, str]]:
         """
         Returns:
-             A list of tuples with word and non default token tags
+             A list of dicts with the following structure:
+
+            ```python
+            {
+                "word": str,  # word characters
+                "entity": str, # token tag
+                "annotation_id": str, # annotation id of the word
+                "successor_annotation_id": Optional[str] # annotation_id of the successor word, if any
+            }
+            ```
+
         """
         block_with_order = self._order("layouts")
         all_words = []
         for block in block_with_order:
             all_words.extend(block.get_ordered_words())  # type: ignore
         return [
-            {"word": word.CHARACTERS, "entity": word.TOKEN_TAG}
+            {"word": word.characters,
+             "entity": word.token_tag.value,
+             "annotation_id": word.annotation_id,
+             "successor_annotation_id": word.successor[0].annotation_id if word.successor else None}
             for word in all_words
-            if word.TOKEN_TAG not in (TokenClasses.OTHER, None)
+            if word.token_tag not in (TokenClasses.OTHER, None)
         ]
 
     def __copy__(self) -> Page:

deepdoctection/extern/base.py

@@ -502,6 +502,7 @@ class TokenClassResult:
        semantic_name: semantic name
        bio_tag: bio tag
        score: prediction score
+       successor_uuid: uuid of the next token in the sequence
     """
 
     uuid: str
@@ -512,6 +513,7 @@ class TokenClassResult:
     bio_tag: ObjectTypes = DefaultType.DEFAULT_TYPE
     score: Optional[float] = None
     token_id: Optional[int] = None
+    successor_uuid: Optional[str] = None
 
 
 @dataclass

deepdoctection/mapper/xfundstruct.py

@@ -200,7 +200,7 @@ def xfund_to_image(
                 ann_ids.extend(entity_id_to_ann_id[linked_entity])
             for ann_id in ann_ids:
                 if ann_id != word.annotation_id:
-                    word.dump_relationship(Relationships.SEMANTIC_ENTITY_LINK, ann_id)
+                    word.dump_relationship(Relationships.LINK, ann_id)
 
     if mapping_context.context_error:
         return None

deepdoctection/pipe/anngen.py

@@ -19,7 +19,7 @@
 Datapoint manager
 """
 from dataclasses import asdict
-from typing import Optional, Union
+from typing import Optional, Union, Sequence
 
 import numpy as np
 
@@ -372,6 +372,19 @@ class DatapointManager:
             return None
         return ann.annotation_id
 
+    def remove_annotations(self, annotation_ids: Sequence[str]) -> None:
+        """
+        Removes the annotation by the given `annotation_id`.
+
+        Args:
+            annotation_ids: The `annotation_id` to remove.
+        """
+        self.assert_datapoint_passed()
+        self.datapoint.remove(annotation_ids)
+        for ann_id in annotation_ids:
+            if ann_id in self._cache_anns:
+                self._cache_anns.pop(ann_id)
+
     def deactivate_annotation(self, annotation_id: str) -> None:
         """
         Deactivates the annotation by the given `annotation_id`.

deepdoctection/utils/settings.py

@@ -80,6 +80,7 @@ class SummaryType(ObjectTypes):
 
     SUMMARY = "summary"
     DOCUMENT_SUMMARY = "document_summary"
+    DOCUMENT_MAPPING = "document_mapping"
 
 
 @object_types_registry.register("DocumentType")
@@ -228,8 +229,9 @@ class Relationships(ObjectTypes):
 
     CHILD = "child"
     READING_ORDER = "reading_order"
-    SEMANTIC_ENTITY_LINK = "semantic_entity_link"
+    LINK = "link"
     LAYOUT_LINK = "layout_link"
+    SUCCESSOR = "successor"
 
 
 @object_types_registry.register("Languages")

{deepdoctection-0.43.1.dist-info → deepdoctection-0.43.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deepdoctection
-Version: 0.43.1
+Version: 0.43.3
 Summary: Repository for Document AI
 Home-page: https://github.com/deepdoctection/deepdoctection
 Author: Dr. Janis Meyer
@@ -192,7 +192,7 @@ Check the demo of a document layout analysis pipeline with OCR on 🤗
 - Fine-tuning and evaluation tools.
 - Lot's of [tutorials](https://github.com/deepdoctection/notebooks)
 
-Have a look at the [**introduction notebook**](https://github.com/deepdoctection/notebooks/blob/main/Get_Started.ipynb)
+Have a look at the [**introduction notebook**](https://github.com/deepdoctection/notebooks/blob/main/Analyzer_Get_Started.ipynb)
 for an easy start.
 
 Check the [**release notes**](https://github.com/deepdoctection/deepdoctection/releases) for recent updates.
@@ -344,8 +344,7 @@ pip install ".[tf]" # or "pip install -e .[tf]"
 
 ### Running a Docker container from Docker hub
 
-Pre-existing Docker images can be downloaded from the [Docker hub](https://hub.docker.
-com/r/deepdoctection/deepdoctection).
+Pre-existing Docker images can be downloaded from the [Docker hub](https://hub.docker.com/r/deepdoctection/deepdoctection).
 
 ```
 docker pull deepdoctection/deepdoctection:<release_tag> 

{deepdoctection-0.43.1.dist-info → deepdoctection-0.43.3.dist-info}/RECORD

@@ -1,4 +1,4 @@
-deepdoctection/__init__.py,sha256=QYGjP3fSt1deLMEKIb7LUDVlzZgi1Q7phZQADkOjlGk,12964
+deepdoctection/__init__.py,sha256=nJ6cTH9fWxNIGSDjMS7AoU9hbJwfbb-SvTwOw6eiPAg,12964
 deepdoctection/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 deepdoctection/analyzer/__init__.py,sha256=wg0BcFwdCeREwzZfa--Yx8HUJ9LPv5z5PmLwtkZdPH8,772
 deepdoctection/analyzer/config.py,sha256=Uwi9MYOym0QXzFcip7bRXoy732P4tZVMFBUnUZk9c1w,41761
@@ -20,8 +20,8 @@ deepdoctection/datapoint/__init__.py,sha256=DOhcN81MhyPUuFw9F4pyEDyZseeD9qxb8NdB
 deepdoctection/datapoint/annotation.py,sha256=f32BNmzUGJoNMeGst2RGC2jmjJpzzjxyBRKFG8FCubY,23092
 deepdoctection/datapoint/box.py,sha256=QAS8sK2Ge4_ysW6zOYkLlzNwhSyw_mhYcYsxscClEno,31453
 deepdoctection/datapoint/convert.py,sha256=6ENXX3tBdY8ogb2NBPxsOsQMGnQux8ol5nrUfWS5tYE,7352
-deepdoctection/datapoint/image.py,sha256=nDaWUtdD5j6l_iXW9d2PoIyXBC8M3_idoEIXm7JWGyQ,35139
-deepdoctection/datapoint/view.py,sha256=5TYmKpNNZwJb-NrUXv08H3_zSfHKDHhg6LnEZjBqVns,56622
+deepdoctection/datapoint/image.py,sha256=kqwCz8DSc19hQpkl_4L1_Ek7_2KrH5KsV9e0S-R4n5w,35147
+deepdoctection/datapoint/view.py,sha256=lVUTi2vfh6w7k92kcwQNpKmfOGgZmM12bYJUFrO5Pno,57163
 deepdoctection/datasets/__init__.py,sha256=4ifjIwWCPYiS31GzUlVDScrkNOrb1eo5xHlRXNyg_58,994
 deepdoctection/datasets/adapter.py,sha256=VSLM_980aHi4TpgOxfxiBHiF_fUXyh348PXet6zTo-4,7779
 deepdoctection/datasets/base.py,sha256=HTIquJir2BZRTLl1HSQM0ICfvjIaWAjJeyz3BEHgdb0,23175
@@ -51,7 +51,7 @@ deepdoctection/eval/registry.py,sha256=us6EGN_tAia1Mk1mwWQwDeE-xqxcuopztdi8n-ieG
 deepdoctection/eval/tedsmetric.py,sha256=EcNeJynsmxyl5bOH3bjy2wE647ONf0SF5OZyGbVu35Q,9963
 deepdoctection/eval/tp_eval_callback.py,sha256=lqrOn2tdaRiF_Vr_9CwBr2ryatcWu3mQKya8YZ2pA9A,5261
 deepdoctection/extern/__init__.py,sha256=jG2qe5_X7fJFnJlx04Lf1KUTXKKKYtCkKR7WQ7looUk,991
-deepdoctection/extern/base.py,sha256=vs4EO9vkfyTW-nVM0dnlqsmnPPeHIXI2wW5b4Wpiz-Y,31547
+deepdoctection/extern/base.py,sha256=LomTR9HXcBU55MPDIA8D1rIamk7DUmToJmgcRXzCoeU,31650
 deepdoctection/extern/d2detect.py,sha256=I0oEkprr5iVpKpM3a3nknAU-sXwNoDQdp_B1gzzODsk,22374
 deepdoctection/extern/deskew.py,sha256=L_jU0rXh03qzwaT79EIqE_zYMUVeFwWDbsGbtahuL2k,3124
 deepdoctection/extern/doctrocr.py,sha256=vOI67NCeEznHzdY4zu1tggwg3_PfwV1eigsr2Z8EPzc,25543
@@ -101,9 +101,9 @@ deepdoctection/mapper/pascalstruct.py,sha256=PviZjhTk4p5HDUTlF8qhWPyraKD0uh51f2h
 deepdoctection/mapper/prodigystruct.py,sha256=OWzPUbNDrqwFipH8YWI5eSxwMdA7qYczaFdsHNrE_4c,7001
 deepdoctection/mapper/pubstruct.py,sha256=UTyfUmzMSuf2BXtdYwHjK7ngsIwAxSZjwTxDtz6DySg,23416
 deepdoctection/mapper/tpstruct.py,sha256=dxtEVHYVnkH-zjjbHzkFrPgS9eheys6E-CMlsjaOnxo,5468
-deepdoctection/mapper/xfundstruct.py,sha256=XLUZ-yBMWtKFQ40vxHl6p8EZZvl68JdwJlV00A93Zy8,9108
+deepdoctection/mapper/xfundstruct.py,sha256=JVs92T5l3HedQvdc6ZMACj2mq5Co4WCS9B-CnQ01opA,9092
 deepdoctection/pipe/__init__.py,sha256=E3cYAVWOvMzIN7jbKFyqLjFXahcFGcAGkb1uChM_XCY,1034
-deepdoctection/pipe/anngen.py,sha256=Hfi7C6-iOv7t8tjFoz4FuIhcz6yMZx52f5SG9bsVnLg,16365
+deepdoctection/pipe/anngen.py,sha256=I7VFoTTa-sJCBwFJNaZeLD7pcrLjRPTX2I6-ZDCDHPI,16819
 deepdoctection/pipe/base.py,sha256=oszB_DepcFtORvDdGTZZPWMhk01C68RUWXHjeX7SF3M,18163
 deepdoctection/pipe/common.py,sha256=OcsqHr_c66Yqt98hFeKwaa0mciWMCauw0HZ3YnHx8MU,24586
 deepdoctection/pipe/concurrency.py,sha256=_EKZi4eCeF3mVHytZL_fMwyqa25C2aR9g8vrIFB8iR4,9780
@@ -136,14 +136,14 @@ deepdoctection/utils/logger.py,sha256=ddQ0xBStluf8OvoRlEB8YkqyRR-ZYgyJYLClTmJJMA
 deepdoctection/utils/metacfg.py,sha256=5M390--ZMoyJEt5oZOwFMGt2i8OF_ayeb0NVmUO_3OQ,7235
 deepdoctection/utils/mocks.py,sha256=IkN3-IzAl4eX0ibgKIHg8IY7ykVw6BnpF6XnxKnKaZI,2389
 deepdoctection/utils/pdf_utils.py,sha256=BrxTuY9j0COyIRkJchJ0tt2h6ZsA2an6z-H8E8QwgUQ,13490
-deepdoctection/utils/settings.py,sha256=OrFEe9Mll3UuDhjyS-cTCv_q1ZSr30Jpl9nQxk__t2I,12824
+deepdoctection/utils/settings.py,sha256=0P6nh9-84wWyMm9J7w9I7gI1xo8mN4M4xZ0IXzcqDbE,12862
 deepdoctection/utils/tqdm.py,sha256=kx3Ivf0x85S0ZmEaN5mImu0V6isOgygOU8iyr2U99XU,1850
 deepdoctection/utils/transform.py,sha256=jgeCyQWLN9q79jCGW7jysyKUKcJ1AVMk8OslF-3fbag,16095
 deepdoctection/utils/types.py,sha256=ti4WdtIJSg3TGK_YPkkoY9PYGMnR2tTX6Xfik8U1pNk,2986
 deepdoctection/utils/utils.py,sha256=NBUb1qbx8Jm-AvYN1Sdbk0huXhbAKxZ-ZtOcMespsMM,7064
 deepdoctection/utils/viz.py,sha256=bujRIujvX317rPz4jBrj0yd3WP8wPjDUiI5GUrw9MzQ,27339
-deepdoctection-0.43.1.dist-info/licenses/LICENSE,sha256=GQ0rUvuGdrMNEI3iHK5UQx6dIMU1QwAuyXsxUHn5MEQ,11351
-deepdoctection-0.43.1.dist-info/METADATA,sha256=jD_6fJFeK-4XpVsjUL0BgFooiuhFPNE9rK0RR6-_2gY,13381
-deepdoctection-0.43.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-deepdoctection-0.43.1.dist-info/top_level.txt,sha256=hs2DdoOL9h4mnHhmO82BT4pz4QATIoOZ20PZmlnxFI8,15
-deepdoctection-0.43.1.dist-info/RECORD,,
+deepdoctection-0.43.3.dist-info/licenses/LICENSE,sha256=GQ0rUvuGdrMNEI3iHK5UQx6dIMU1QwAuyXsxUHn5MEQ,11351
+deepdoctection-0.43.3.dist-info/METADATA,sha256=tFoZH2VB3ZkiTwzVmd1OBlg1f6eFLrKwwcLyYo6BX1g,13389
+deepdoctection-0.43.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+deepdoctection-0.43.3.dist-info/top_level.txt,sha256=hs2DdoOL9h4mnHhmO82BT4pz4QATIoOZ20PZmlnxFI8,15
+deepdoctection-0.43.3.dist-info/RECORD,,