deepdoctection 0.43__tar.gz → 0.43.1__tar.gz

{deepdoctection-0.43 → deepdoctection-0.43.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deepdoctection
-Version: 0.43
+Version: 0.43.1
 Summary: Repository for Document AI
 Home-page: https://github.com/deepdoctection/deepdoctection
 Author: Dr. Janis Meyer
@@ -245,11 +245,11 @@ alt="text" width="40%">
 
 ## Requirements
 
-![requirements](https://github.com/deepdoctection/deepdoctection/raw/master/docs/tutorials/_imgs/requirements_deepdoctection_220525.png)
+![requirements](https://github.com/deepdoctection/deepdoctection/raw/master/docs/tutorials/_imgs/install_01.png)
 
 - Linux or macOS. Windows is not supported but there is a [Dockerfile](./docker/pytorch-cpu-jupyter/Dockerfile) available.
 - Python >= 3.9
-- 1.13 \<= PyTorch **or** 2.11 \<= Tensorflow < 2.16. (For lower Tensorflow versions the code will only run on a GPU).
+- 2.2 \<= PyTorch **or** 2.11 \<= Tensorflow < 2.16. (For lower Tensorflow versions the code will only run on a GPU).
   Tensorflow support will be stopped from Python 3.11 onwards.
 - To fine-tune models, a GPU is recommended.
 

{deepdoctection-0.43 → deepdoctection-0.43.1}/README.md

@@ -102,11 +102,11 @@ alt="text" width="40%">
 
 ## Requirements
 
-![requirements](https://github.com/deepdoctection/deepdoctection/raw/master/docs/tutorials/_imgs/requirements_deepdoctection_220525.png)
+![requirements](https://github.com/deepdoctection/deepdoctection/raw/master/docs/tutorials/_imgs/install_01.png)
 
 - Linux or macOS. Windows is not supported but there is a [Dockerfile](./docker/pytorch-cpu-jupyter/Dockerfile) available.
 - Python >= 3.9
-- 1.13 \<= PyTorch **or** 2.11 \<= Tensorflow < 2.16. (For lower Tensorflow versions the code will only run on a GPU).
+- 2.2 \<= PyTorch **or** 2.11 \<= Tensorflow < 2.16. (For lower Tensorflow versions the code will only run on a GPU).
   Tensorflow support will be stopped from Python 3.11 onwards.
 - To fine-tune models, a GPU is recommended.
 

{deepdoctection-0.43 → deepdoctection-0.43.1}/deepdoctection/__init__.py

@@ -25,11 +25,11 @@ from .utils.logger import LoggingRecord, logger
 
 # pylint: enable=wrong-import-position
 
-__version__ = "0.43"
+__version__ = "0.43.1"
 
 _IMPORT_STRUCTURE = {
     "analyzer": ["config_sanity_checks", "get_dd_analyzer", "ServiceFactory"],
-    "configs": [],
+    "configs": ["update_cfg_from_defaults"],
     "dataflow": [
         "DataFlowTerminated",
         "DataFlowResetStateNotCalled",
@@ -98,6 +98,7 @@ _IMPORT_STRUCTURE = {
         "List",
         "Cell",
         "Table",
+        "IMAGE_DEFAULTS",
         "Page",
     ],
     "datasets": [

{deepdoctection-0.43 → deepdoctection-0.43.1}/deepdoctection/analyzer/config.py

@@ -902,3 +902,18 @@ cfg.LAYOUT_LINK.CHILD_CATEGORIES = [LayoutType.CAPTION]
 # Freezes the configuration to make it immutable.
 # This prevents accidental modification at runtime.
 cfg.freeze()
+
+def update_cfg_from_defaults() -> None:
+    """
+    Update the configuration with current values from IMAGE_DEFAULTS.
+    """
+    cfg.freeze(False)
+
+    # Update all dependent fields from IMAGE_DEFAULTS
+    cfg.TEXT_CONTAINER = IMAGE_DEFAULTS.TEXT_CONTAINER
+    cfg.WORD_MATCHING.PARENTAL_CATEGORIES = IMAGE_DEFAULTS.TEXT_BLOCK_CATEGORIES
+    cfg.TEXT_ORDERING.TEXT_BLOCK_CATEGORIES = IMAGE_DEFAULTS.TEXT_BLOCK_CATEGORIES
+    cfg.TEXT_ORDERING.FLOATING_TEXT_BLOCK_CATEGORIES = IMAGE_DEFAULTS.FLOATING_TEXT_BLOCK_CATEGORIES
+
+    # Re-freeze the configuration
+    cfg.freeze()

{deepdoctection-0.43 → deepdoctection-0.43.1}/deepdoctection/extern/doctrocr.py

@@ -269,7 +269,10 @@ 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]:
         """
@@ -424,7 +427,7 @@ class DoctrTextRecognizer(TextRecognizer):
         return _get_doctr_requirements()
 
     def clone(self) -> DoctrTextRecognizer:
-        return self.__class__(self.architecture, self.path_weights, self.device, self.lib)
+        return self.__class__(self.architecture, self.path_weights, self.device, self.lib, self.path_config_json)
 
     @staticmethod
     def load_model(

{deepdoctection-0.43 → deepdoctection-0.43.1}/deepdoctection/extern/texocr.py

@@ -60,7 +60,7 @@ def _textract_to_detectresult(response: JsonDict, width: int, height: int, text_
     return all_results
 
 
-def predict_text(np_img: PixelValues, client: boto3.client, text_lines: bool) -> list[DetectionResult]:  # type: ignore
+def predict_text(np_img: PixelValues, client: boto3.client, text_lines: bool) -> list[DetectionResult]:
     """
     Calls AWS Textract client (`detect_document_text`) and returns plain OCR results.
     AWS account required.

{deepdoctection-0.43 → deepdoctection-0.43.1}/deepdoctection/pipe/order.py

@@ -738,10 +738,8 @@ class TextOrderService(TextLineServiceMixin):
                 text_block_anns.extend(residual_text_container_anns)
         for text_block_ann in text_block_anns:
             self.order_text_in_text_block(text_block_ann)
-        floating_text_block_anns_to_order = [
-            ann for ann in text_block_anns if ann.category_name in self.floating_text_block_categories
-        ]
-        self.order_blocks(floating_text_block_anns_to_order)
+        floating_text_block_anns = dp.get_annotation(category_names=self.floating_text_block_categories)
+        self.order_blocks(floating_text_block_anns)
         self._create_columns()
 
     def _create_columns(self) -> None:
@@ -803,9 +801,14 @@ class TextOrderService(TextLineServiceMixin):
         if self.include_residual_text_container:
             add_category.append(LayoutType.LINE)
 
-        assert set(self.floating_text_block_categories) <= set(
+        if set(self.floating_text_block_categories) <= set(
             self.text_block_categories + tuple(add_category)
-        ), "floating_text_block_categories must be a subset of text_block_categories"
+        ):
+            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 → deepdoctection-0.43.1}/deepdoctection/utils/context.py

@@ -38,7 +38,7 @@ __all__ = ["timeout_manager", "save_tmp_file", "timed_operation"]
 
 
 @contextmanager
-def timeout_manager(proc: Any, seconds: Optional[int] = None) -> Iterator[str]:  # type: ignore
+def timeout_manager(proc: Any, seconds: Optional[int] = None) -> Iterator[str]:
     """
     Manager for time handling while some process is being called.
 

{deepdoctection-0.43 → deepdoctection-0.43.1}/deepdoctection/utils/develop.py

@@ -71,6 +71,7 @@ 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 → deepdoctection-0.43.1}/deepdoctection/utils/env_info.py

@@ -462,7 +462,7 @@ def pt_info(data: KeyValEnvInfos) -> KeyValEnvInfos:
                 data.append(("torchvision arch flags", msg))
             except (ImportError, AttributeError):
                 data.append(("torchvision._C", "Not found"))
-    except AttributeError:
+    except (AttributeError, ModuleNotFoundError):
         data.append(("torchvision", "unknown"))
 
     return data

{deepdoctection-0.43 → deepdoctection-0.43.1}/deepdoctection/utils/file_utils.py

@@ -12,7 +12,6 @@ import importlib.util
 import multiprocessing as mp
 import string
 import subprocess
-import sys
 from os import environ, path
 from shutil import which
 from types import ModuleType
@@ -22,7 +21,6 @@ import importlib_metadata
 from packaging import version
 
 from .error import DependencyError
-from .logger import LoggingRecord, logger
 from .metacfg import AttrDict
 from .types import PathLikeOrStr, Requirement
 
@@ -662,13 +660,6 @@ def get_doctr_requirement() -> Requirement:
         On macOS, if `poppler` is not available, this function will recursively check the requirement.
         It is not yet known how to check whether `pango`, `gdk-pixbuf`, and `libffi` are installed.
     """
-    if sys.platform == "darwin":
-        if not get_poppler_version():
-            return get_doctr_requirement()
-        # don't know yet how to check whether pango gdk-pixbuf libffi are installed
-        logger.info(
-            LoggingRecord("package requires weasyprint. Check that poppler pango gdk-pixbuf libffi are installed")
-        )
     return "doctr", doctr_available(), _DOCTR_ERR_MSG
 
 

{deepdoctection-0.43 → deepdoctection-0.43.1}/deepdoctection.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deepdoctection
-Version: 0.43
+Version: 0.43.1
 Summary: Repository for Document AI
 Home-page: https://github.com/deepdoctection/deepdoctection
 Author: Dr. Janis Meyer
@@ -245,11 +245,11 @@ alt="text" width="40%">
 
 ## Requirements
 
-![requirements](https://github.com/deepdoctection/deepdoctection/raw/master/docs/tutorials/_imgs/requirements_deepdoctection_220525.png)
+![requirements](https://github.com/deepdoctection/deepdoctection/raw/master/docs/tutorials/_imgs/install_01.png)
 
 - Linux or macOS. Windows is not supported but there is a [Dockerfile](./docker/pytorch-cpu-jupyter/Dockerfile) available.
 - Python >= 3.9
-- 1.13 \<= PyTorch **or** 2.11 \<= Tensorflow < 2.16. (For lower Tensorflow versions the code will only run on a GPU).
+- 2.2 \<= PyTorch **or** 2.11 \<= Tensorflow < 2.16. (For lower Tensorflow versions the code will only run on a GPU).
   Tensorflow support will be stopped from Python 3.11 onwards.
 - To fine-tune models, a GPU is recommended.