deepdoctection 1.2.2__tar.gz → 1.2.4__tar.gz

{deepdoctection-1.2.2 → deepdoctection-1.2.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deepdoctection
-Version: 1.2.2
+Version: 1.2.4
 Summary: Repository for Document AI - server/inference core package
 Author: Dr. Janis Meyer
 License: Apache License 2.0

{deepdoctection-1.2.2 → deepdoctection-1.2.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "deepdoctection"
-version = "1.2.2"
+version = "1.2.4"
 authors = [
     {name = "Dr. Janis Meyer"}
 ]

{deepdoctection-1.2.2 → deepdoctection-1.2.4}/src/deepdoctection/__init__.py

@@ -12,7 +12,7 @@ from dd_core.utils.env_info import collect_env_info
 from dd_core.utils.file_utils import _LazyModule
 from dd_core.utils.logger import LoggingRecord, logger
 
-__version__ = "1.2.2"
+__version__ = "1.2.4"
 _IMPORT_STRUCTURE = {
     "analyzer": ["config_sanity_checks", "get_dd_analyzer", "ServiceFactory", "update_cfg_from_defaults"],
     "eval": [

{deepdoctection-1.2.2 → deepdoctection-1.2.4}/src/deepdoctection/pipe/anngen.py

@@ -45,15 +45,12 @@ class DataPointCacheStore(ABC):
     """
 
     @abstractmethod
-    def put_datapoint(
-        self, document_id: str, image_id: str, page_number: int, image: Image, job_id: str | None = None
-    ) -> None:
+    def put_datapoint(self, document_id: str, page_number: int, image: Image, job_id: str | None = None) -> None:
         """
         Persist a datapoint (image) for a specific document and page number.
 
         Args:
             document_id (str): The identifier of the document the image belongs to.
-            image_id (str): The unique identifier of the image.
             page_number (int): The 0-based page number inside the document.
             image (Image): The image object to store (may be serialized by the store).
             job_id (str | None): Optional job identifier to distinguish between different processing runs.
@@ -137,9 +134,7 @@ class LocalDataPointCacheStore(DataPointCacheStore):
             return document_id
         return f"{document_id}::{job_id}"
 
-    def put_datapoint(
-        self, document_id: str, image_id: str, page_number: int, image: Image, job_id: str | None = None
-    ) -> None:
+    def put_datapoint(self, document_id: str, page_number: int, image: Image, job_id: str | None = None) -> None:
         """
         Store a serialized version of ``image`` for ``document_id`` at ``page_number``.
 
@@ -148,8 +143,6 @@ class LocalDataPointCacheStore(DataPointCacheStore):
 
         Args:
             document_id (str): Document identifier the image belongs to.
-            image_id (str): Image identifier (not directly used by this store but included for API
-                compatibility with other stores).
             page_number (int): 0-based page number of the image.
             image (Image): The Image object to serialize and store.
             job_id (str | None): Optional job identifier to distinguish between different processing runs.
@@ -251,7 +244,6 @@ class DatapointManager:
 
         self._cache_store.put_datapoint(
             document_id=image.document_id,
-            image_id=image.image_id,
             page_number=image.page_number,
             image=image,
             job_id=job_id,

{deepdoctection-1.2.2 → deepdoctection-1.2.4}/src/deepdoctection/pipe/base.py

@@ -259,6 +259,85 @@ class PipelineComponent(ABC):
         return MapData(df, self._undo)
 
 
+def get_meta_annotation(pipeline_component_list: list[PipelineComponent]) -> MetaAnnotation:
+    """
+    Collects meta annotations from all pipeline components and summarizes the returned results.
+
+    Returns:
+        Meta annotations with information about image annotations (list), sub categories (dict with category
+        names and generated sub categories), relationships (dict with category names and generated relationships)
+        as well as summaries (list with sub categories).
+    """
+    image_annotations: list[ObjectTypes] = []
+    sub_categories: dict[ObjectTypes, dict[ObjectTypes, set[ObjectTypes]]] = {}
+    relationships = defaultdict(set[ObjectTypes])  # type: ignore
+    summaries: list[ObjectTypes] = []
+    for component in pipeline_component_list:
+        meta_anns = component.get_meta_annotation()
+        image_annotations.extend(meta_anns.image_annotations)
+        for key, value in meta_anns.sub_categories.items():
+            sub_dict = meta_anns.sub_categories[key]
+            for sub_cat, sub_cat_value in value.items():
+                if sub_cat in sub_dict:
+                    sub_dict[sub_cat].update(sub_cat_value)
+                else:
+                    sub_dict[sub_cat] = {sub_cat_value}  # type: ignore
+            if key in sub_categories:
+                sub_categories[key].update(sub_dict)
+            else:
+                sub_categories[key] = sub_dict
+        for key, value in meta_anns.relationships.items():  # type: ignore
+            relationships[key].update(value)
+        summaries.extend(meta_anns.summaries)
+    return MetaAnnotation(
+        image_annotations=tuple(image_annotations),
+        sub_categories=sub_categories,
+        relationships=relationships,
+        summaries=tuple(summaries),
+    )
+
+
+def get_service_id_to_meta_annotation(pipeline_component_list: list[PipelineComponent]) -> Mapping[str, MetaAnnotation]:
+    """
+    Collects meta annotations from all pipeline components and return a dict of service id to its meta annotation.
+
+    Returns:
+        `service_id` to `MetaAnnotation` with information about image annotations (list), sub categories (dict with
+        category names and generated sub categories), relationships (dict with category names and generated
+        relationships) as well as summaries (list with sub categories).
+    """
+    service_id_to_meta_annotation = {}
+    for component in pipeline_component_list:
+        meta_anns = component.get_meta_annotation()
+        service_id_to_meta_annotation[component.service_id] = meta_anns
+    return service_id_to_meta_annotation
+
+
+def get_pipeline_info(
+    pipeline_component_list: list[PipelineComponent], service_id: str | None = None, name: str | None = None
+) -> Union[str, Mapping[str, str]]:
+    """
+    Get pipeline information.
+
+    Returns a dictionary with a description of each pipeline component.
+
+    Args:
+        service_id: Service id of the pipeline component to search for.
+        name: Name of the pipeline component to search for.
+
+    Returns:
+        Either a full dictionary with position and name of all pipeline components or the name, if
+        the position has been passed or the position if the name has been passed.
+    """
+    comp_info = {comp.service_id: comp.name for comp in pipeline_component_list}
+    comp_info_name_as_key = {value: key for key, value in comp_info.items()}
+    if service_id is not None:
+        return comp_info[service_id]
+    if name is not None:
+        return comp_info_name_as_key[name]
+    return comp_info
+
+
 class Pipeline(ABC):
     """
     Abstract base class for creating pipelines.
@@ -394,33 +473,7 @@ class Pipeline(ABC):
             names and generated sub categories), relationships (dict with category names and generated relationships)
             as well as summaries (list with sub categories).
         """
-        image_annotations: list[ObjectTypes] = []
-        sub_categories: dict[ObjectTypes, dict[ObjectTypes, set[ObjectTypes]]] = {}
-        relationships = defaultdict(set[ObjectTypes])  # type: ignore
-        summaries: list[ObjectTypes] = []
-        for component in self.pipe_component_list:
-            meta_anns = component.get_meta_annotation()
-            image_annotations.extend(meta_anns.image_annotations)
-            for key, value in meta_anns.sub_categories.items():
-                sub_dict = meta_anns.sub_categories[key]
-                for sub_cat, sub_cat_value in value.items():
-                    if sub_cat in sub_dict:
-                        sub_dict[sub_cat].update(sub_cat_value)
-                    else:
-                        sub_dict[sub_cat] = {sub_cat_value}  # type: ignore
-                if key in sub_categories:
-                    sub_categories[key].update(sub_dict)
-                else:
-                    sub_categories[key] = sub_dict
-            for key, value in meta_anns.relationships.items():  # type: ignore
-                relationships[key].update(value)
-            summaries.extend(meta_anns.summaries)
-        return MetaAnnotation(
-            image_annotations=tuple(image_annotations),
-            sub_categories=dict(sub_categories),
-            relationships=dict(relationships),
-            summaries=tuple(summaries),
-        )
+        return get_meta_annotation(self.pipe_component_list)
 
     def get_service_id_to_meta_annotation(self) -> Mapping[str, MetaAnnotation]:
         """
@@ -431,11 +484,7 @@ class Pipeline(ABC):
             category names and generated sub categories), relationships (dict with category names and generated
             relationships) as well as summaries (list with sub categories).
         """
-        service_id_to_meta_annotation = {}
-        for component in self.pipe_component_list:
-            meta_anns = component.get_meta_annotation()
-            service_id_to_meta_annotation[component.service_id] = meta_anns
-        return service_id_to_meta_annotation
+        return get_service_id_to_meta_annotation(self.pipe_component_list)
 
     def get_pipeline_info(
         self, service_id: Optional[str] = None, name: Optional[str] = None
@@ -453,13 +502,7 @@ class Pipeline(ABC):
             Either a full dictionary with position and name of all pipeline components or the name, if
             the position has been passed or the position if the name has been passed.
         """
-        comp_info = {comp.service_id: comp.name for comp in self.pipe_component_list}
-        comp_info_name_as_key = {value: key for key, value in comp_info.items()}
-        if service_id is not None:
-            return comp_info[service_id]
-        if name is not None:
-            return comp_info_name_as_key[name]
-        return comp_info
+        return get_pipeline_info(self.pipe_component_list, service_id=service_id, name=name)
 
     def get_pipeline_component(self, service_id: Optional[str] = None, name: Optional[str] = None) -> PipelineComponent:
         """

{deepdoctection-1.2.2 → deepdoctection-1.2.4}/src/deepdoctection.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deepdoctection
-Version: 1.2.2
+Version: 1.2.4
 Summary: Repository for Document AI - server/inference core package
 Author: Dr. Janis Meyer
 License: Apache License 2.0