deepdoctection 0.43.3__tar.gz → 0.43.4__tar.gz

{deepdoctection-0.43.3 → deepdoctection-0.43.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deepdoctection
-Version: 0.43.3
+Version: 0.43.4
 Summary: Repository for Document AI
 Home-page: https://github.com/deepdoctection/deepdoctection
 Author: Dr. Janis Meyer

{deepdoctection-0.43.3 → deepdoctection-0.43.4}/deepdoctection/__init__.py

@@ -25,7 +25,7 @@ from .utils.logger import LoggingRecord, logger
 
 # pylint: enable=wrong-import-position
 
-__version__ = "0.43.3"
+__version__ = "0.43.4"
 
 _IMPORT_STRUCTURE = {
     "analyzer": ["config_sanity_checks", "get_dd_analyzer", "ServiceFactory"],

{deepdoctection-0.43.3 → deepdoctection-0.43.4}/deepdoctection/analyzer/config.py

@@ -903,6 +903,7 @@ cfg.LAYOUT_LINK.CHILD_CATEGORIES = [LayoutType.CAPTION]
 # This prevents accidental modification at runtime.
 cfg.freeze()
 
+
 def update_cfg_from_defaults() -> None:
     """
     Update the configuration with current values from IMAGE_DEFAULTS.

{deepdoctection-0.43.3 → deepdoctection-0.43.4}/deepdoctection/datapoint/view.py

@@ -72,6 +72,18 @@ class ImageAnnotationBaseView(ImageAnnotation):
 
     base_page: Page
 
+    @property
+    def b64_image(self) -> Optional[str]:
+        """
+        Returns:
+            The base64 encoded image of the page if available, otherwise None.
+        """
+
+        if self.image is not None:
+            if self.image.image is not None:
+                return viz_handler.convert_np_to_b64(self.image.image)
+        return None
+
     @property
     def bbox(self) -> list[float]:
         """
@@ -157,7 +169,7 @@ class ImageAnnotationBaseView(ImageAnnotation):
         """
 
         # sub categories and summary sub categories are valid attribute names
-        attr_names = {"bbox", "np_image"}.union({cat.value for cat in self.sub_categories})
+        attr_names = {"bbox", "np_image", "b64_image"}.union({cat.value for cat in self.sub_categories})
         if self.image:
             attr_names = attr_names.union({cat.value for cat in self.image.summary.sub_categories.keys()})
         return {attr_name.value if isinstance(attr_name, ObjectTypes) else attr_name for attr_name in attr_names}
@@ -774,6 +786,7 @@ class Page(Image):
         "residual_layouts",
         "document_summary",
         "document_mapping",
+        "b64_image",
     }
     include_residual_text_container: bool = True
 
@@ -902,6 +915,17 @@ class Page(Image):
         """
         return self.get_annotation(category_names=self.residual_text_block_categories)
 
+    @property
+    def b64_image(self) -> Optional[str]:
+        """
+        Returns:
+            The base64 encoded image of the page if available, otherwise None.
+        """
+
+        if self.image_orig.image is not None:
+            return viz_handler.convert_np_to_b64(self.image_orig.image)
+        return None
+
     @classmethod
     def from_image(
         cls,
@@ -1410,10 +1434,12 @@ class Page(Image):
         for block in block_with_order:
             all_words.extend(block.get_ordered_words())  # type: ignore
         return [
-            {"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}
+            {
+                "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)
         ]

{deepdoctection-0.43.3 → deepdoctection-0.43.4}/deepdoctection/extern/doctrocr.py

@@ -269,10 +269,7 @@ class DoctrTextlineDetector(DoctrTextlineDetectorMixin):
         if self.lib == "PT":
             self.device = get_torch_device(device)
 
-        self.doctr_predictor = self.get_wrapped_model(self.architecture,
-                                                      self.path_weights,
-                                                      self.device,
-                                                      self.lib)
+        self.doctr_predictor = self.get_wrapped_model(self.architecture, self.path_weights, self.device, self.lib)
 
     def predict(self, np_img: PixelValues) -> list[DetectionResult]:
         """

{deepdoctection-0.43.3 → deepdoctection-0.43.4}/deepdoctection/pipe/anngen.py

@@ -19,7 +19,7 @@
 Datapoint manager
 """
 from dataclasses import asdict
-from typing import Optional, Union, Sequence
+from typing import Optional, Sequence, Union
 
 import numpy as np
 

{deepdoctection-0.43.3 → deepdoctection-0.43.4}/deepdoctection/pipe/order.py

@@ -801,14 +801,13 @@ class TextOrderService(TextLineServiceMixin):
         if self.include_residual_text_container:
             add_category.append(LayoutType.LINE)
 
-        if set(self.floating_text_block_categories) <= set(
-            self.text_block_categories + tuple(add_category)
-        ):
-            logger.warning("In most cases floating_text_block_categories must be a subset of text_block_categories. "
-                           "Adding categories to floating_text_block_categories, that do not belong to "
-                           "text_block_categories makes only sense for categories set have CHILD relationships with"
-                           " annotations that belong to text_block_categories.")
-
+        if set(self.floating_text_block_categories) <= set(self.text_block_categories + tuple(add_category)):
+            logger.warning(
+                "In most cases floating_text_block_categories must be a subset of text_block_categories. "
+                "Adding categories to floating_text_block_categories, that do not belong to "
+                "text_block_categories makes only sense for categories set have CHILD relationships with"
+                " annotations that belong to text_block_categories."
+            )
 
     def get_meta_annotation(self) -> MetaAnnotation:
         add_category = [self.text_container]

{deepdoctection-0.43.3 → deepdoctection-0.43.4}/deepdoctection/utils/develop.py

@@ -71,7 +71,6 @@ def log_deprecated(name: str, text: str, eos: str = "", max_num_warnings: Option
     logger.info(LoggingRecord(f"[Deprecated] {info_msg}"))
 
 
-
 def deprecated(
     text: str = "", eos: str = "", max_num_warnings: Optional[int] = None
 ) -> Callable[[Callable[..., T]], Callable[..., T]]:

{deepdoctection-0.43.3 → deepdoctection-0.43.4}/deepdoctection.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deepdoctection
-Version: 0.43.3
+Version: 0.43.4
 Summary: Repository for Document AI
 Home-page: https://github.com/deepdoctection/deepdoctection
 Author: Dr. Janis Meyer