deepdoctection 0.29__tar.gz → 0.31__tar.gz

{deepdoctection-0.29 → deepdoctection-0.31}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: deepdoctection
-Version: 0.29
+Version: 0.31
 Summary: Repository for Document AI
 Home-page: https://github.com/deepdoctection/deepdoctection
 Author: Dr. Janis Meyer
@@ -10,42 +10,45 @@ Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Natural Language :: English
 Classifier: Operating System :: POSIX :: Linux
 Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: catalogue==2.0.7
+Requires-Dist: catalogue==2.0.10
 Requires-Dist: huggingface_hub>=0.12.0
-Requires-Dist: importlib-metadata>=4.11.2
-Requires-Dist: jsonlines==3.0.0
+Requires-Dist: importlib-metadata>=5.0.0
+Requires-Dist: jsonlines==3.1.0
 Requires-Dist: mock==4.0.3
 Requires-Dist: networkx>=2.7.1
 Requires-Dist: numpy>=1.21
 Requires-Dist: packaging>=20.0
 Requires-Dist: Pillow>=10.0.0
 Requires-Dist: pypdf>=3.16.0
-Requires-Dist: pyyaml==6.0
+Requires-Dist: pyyaml>=6.0.1
 Requires-Dist: pyzmq>=16
 Requires-Dist: termcolor>=1.1
 Requires-Dist: tabulate>=0.7.7
 Requires-Dist: tqdm==4.64.0
 Provides-Extra: tf
-Requires-Dist: catalogue==2.0.7; extra == "tf"
+Requires-Dist: catalogue==2.0.10; extra == "tf"
 Requires-Dist: huggingface_hub>=0.12.0; extra == "tf"
-Requires-Dist: importlib-metadata>=4.11.2; extra == "tf"
-Requires-Dist: jsonlines==3.0.0; extra == "tf"
+Requires-Dist: importlib-metadata>=5.0.0; extra == "tf"
+Requires-Dist: jsonlines==3.1.0; extra == "tf"
 Requires-Dist: mock==4.0.3; extra == "tf"
 Requires-Dist: networkx>=2.7.1; extra == "tf"
 Requires-Dist: numpy>=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: pyyaml==6.0; extra == "tf"
+Requires-Dist: pyyaml>=6.0.1; extra == "tf"
 Requires-Dist: pyzmq>=16; extra == "tf"
 Requires-Dist: termcolor>=1.1; extra == "tf"
 Requires-Dist: tabulate>=0.7.7; extra == "tf"
 Requires-Dist: tqdm==4.64.0; extra == "tf"
-Requires-Dist: tensorpack; extra == "tf"
+Requires-Dist: tensorpack==0.11; extra == "tf"
 Requires-Dist: protobuf==3.20.1; extra == "tf"
 Requires-Dist: tensorflow-addons>=0.17.1; extra == "tf"
 Requires-Dist: tf2onnx>=1.9.2; extra == "tf"
@@ -53,47 +56,47 @@ Requires-Dist: python-doctr==0.7.0; extra == "tf"
 Requires-Dist: pycocotools>=2.0.2; extra == "tf"
 Requires-Dist: boto3; extra == "tf"
 Requires-Dist: pdfplumber>=0.7.1; extra == "tf"
-Requires-Dist: fasttext; extra == "tf"
-Requires-Dist: jdeskew; extra == "tf"
+Requires-Dist: fasttext==0.9.2; extra == "tf"
+Requires-Dist: jdeskew>=0.2.2; extra == "tf"
 Requires-Dist: apted==1.0.3; extra == "tf"
 Requires-Dist: distance==0.1.3; extra == "tf"
 Requires-Dist: lxml>=4.9.1; extra == "tf"
 Provides-Extra: pt
-Requires-Dist: catalogue==2.0.7; extra == "pt"
+Requires-Dist: catalogue==2.0.10; extra == "pt"
 Requires-Dist: huggingface_hub>=0.12.0; extra == "pt"
-Requires-Dist: importlib-metadata>=4.11.2; extra == "pt"
-Requires-Dist: jsonlines==3.0.0; extra == "pt"
+Requires-Dist: importlib-metadata>=5.0.0; extra == "pt"
+Requires-Dist: jsonlines==3.1.0; extra == "pt"
 Requires-Dist: mock==4.0.3; extra == "pt"
 Requires-Dist: networkx>=2.7.1; extra == "pt"
 Requires-Dist: numpy>=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: pyyaml==6.0; extra == "pt"
+Requires-Dist: pyyaml>=6.0.1; extra == "pt"
 Requires-Dist: pyzmq>=16; extra == "pt"
 Requires-Dist: termcolor>=1.1; extra == "pt"
 Requires-Dist: tabulate>=0.7.7; extra == "pt"
 Requires-Dist: tqdm==4.64.0; extra == "pt"
-Requires-Dist: timm; extra == "pt"
+Requires-Dist: timm>=0.9.16; extra == "pt"
 Requires-Dist: transformers>=4.36.0; extra == "pt"
-Requires-Dist: accelerate; extra == "pt"
+Requires-Dist: accelerate>=0.29.1; extra == "pt"
 Requires-Dist: python-doctr==0.7.0; extra == "pt"
 Requires-Dist: boto3; extra == "pt"
 Requires-Dist: pdfplumber>=0.7.1; extra == "pt"
-Requires-Dist: fasttext; extra == "pt"
-Requires-Dist: jdeskew; extra == "pt"
+Requires-Dist: fasttext==0.9.2; extra == "pt"
+Requires-Dist: jdeskew>=0.2.2; extra == "pt"
 Requires-Dist: apted==1.0.3; extra == "pt"
 Requires-Dist: distance==0.1.3; extra == "pt"
 Requires-Dist: lxml>=4.9.1; extra == "pt"
 Provides-Extra: docs
-Requires-Dist: tensorpack; extra == "docs"
+Requires-Dist: tensorpack==0.11; extra == "docs"
 Requires-Dist: boto3; extra == "docs"
 Requires-Dist: transformers>=4.36.0; extra == "docs"
-Requires-Dist: accelerate; extra == "docs"
+Requires-Dist: accelerate>=0.29.1; extra == "docs"
 Requires-Dist: pdfplumber>=0.7.1; extra == "docs"
 Requires-Dist: lxml>=4.9.1; extra == "docs"
-Requires-Dist: lxml-stubs; extra == "docs"
-Requires-Dist: jdeskew; extra == "docs"
+Requires-Dist: lxml-stubs>=0.5.1; extra == "docs"
+Requires-Dist: jdeskew>=0.2.2; extra == "docs"
 Requires-Dist: jinja2==3.0.3; extra == "docs"
 Requires-Dist: mkdocs-material; extra == "docs"
 Requires-Dist: mkdocstrings-python; extra == "docs"
@@ -102,47 +105,20 @@ Provides-Extra: dev
 Requires-Dist: python-dotenv==1.0.0; extra == "dev"
 Requires-Dist: click; extra == "dev"
 Requires-Dist: black==23.7.0; extra == "dev"
-Requires-Dist: isort; extra == "dev"
+Requires-Dist: isort==5.13.2; extra == "dev"
 Requires-Dist: pylint==2.17.4; extra == "dev"
 Requires-Dist: mypy==1.4.1; extra == "dev"
 Requires-Dist: wandb; extra == "dev"
-Requires-Dist: types-PyYAML; extra == "dev"
-Requires-Dist: types-termcolor==1.1.3; extra == "dev"
-Requires-Dist: types-tabulate; extra == "dev"
-Requires-Dist: types-tqdm; extra == "dev"
-Requires-Dist: lxml-stubs; extra == "dev"
-Requires-Dist: types-Pillow; extra == "dev"
-Requires-Dist: types-urllib3; extra == "dev"
+Requires-Dist: types-PyYAML>=6.0.12.12; extra == "dev"
+Requires-Dist: types-termcolor>=1.1.3; extra == "dev"
+Requires-Dist: types-tabulate>=0.9.0.3; extra == "dev"
+Requires-Dist: types-tqdm>=4.66.0.5; extra == "dev"
+Requires-Dist: lxml-stubs>=0.5.1; extra == "dev"
+Requires-Dist: types-Pillow>=10.2.0.20240406; extra == "dev"
+Requires-Dist: types-urllib3>=1.26.25.14; extra == "dev"
 Provides-Extra: test
-Requires-Dist: pytest; extra == "test"
+Requires-Dist: pytest==8.0.2; extra == "test"
 Requires-Dist: pytest-cov; extra == "test"
-Provides-Extra: hf
-Requires-Dist: catalogue==2.0.7; extra == "hf"
-Requires-Dist: huggingface_hub>=0.12.0; extra == "hf"
-Requires-Dist: importlib-metadata>=4.11.2; extra == "hf"
-Requires-Dist: jsonlines==3.0.0; extra == "hf"
-Requires-Dist: mock==4.0.3; extra == "hf"
-Requires-Dist: networkx>=2.7.1; extra == "hf"
-Requires-Dist: numpy>=1.21; extra == "hf"
-Requires-Dist: packaging>=20.0; extra == "hf"
-Requires-Dist: Pillow>=10.0.0; extra == "hf"
-Requires-Dist: pypdf>=3.16.0; extra == "hf"
-Requires-Dist: pyyaml==6.0; extra == "hf"
-Requires-Dist: pyzmq>=16; extra == "hf"
-Requires-Dist: termcolor>=1.1; extra == "hf"
-Requires-Dist: tabulate>=0.7.7; extra == "hf"
-Requires-Dist: tqdm==4.64.0; extra == "hf"
-Requires-Dist: timm; extra == "hf"
-Requires-Dist: transformers>=4.36.0; extra == "hf"
-Requires-Dist: accelerate; extra == "hf"
-Requires-Dist: python-doctr==0.7.0; extra == "hf"
-Requires-Dist: boto3; extra == "hf"
-Requires-Dist: pdfplumber>=0.7.1; extra == "hf"
-Requires-Dist: fasttext; extra == "hf"
-Requires-Dist: jdeskew; extra == "hf"
-Requires-Dist: apted==1.0.3; extra == "hf"
-Requires-Dist: distance==0.1.3; extra == "hf"
-Requires-Dist: lxml>=4.9.1; extra == "hf"
 
 
 <p align="center">
@@ -188,7 +164,9 @@ pipelines. Its core function does not depend on any specific deep learning libra
    Check this [notebook](https://github.com/deepdoctection/notebooks/blob/main/Analyzer_Configuration.ipynb) or the 
    [docs](https://deepdoctection.readthedocs.io/en/latest/tutorials/analyzer_configuration_notebook/) for more infos.
  - Document layout analysis and table recognition now runs with Torchscript (CPU) as well and Detectron2 is 
-   not required anymore for basic inference. 
+   not required anymore for basic inference.
+ - [**new**] More angle predictors for determining the rotation of a document based on Tesseract and DocTr 
+   (not contained in the built-in Analyzer).
 
 **deep**doctection provides on top of that methods for pre-processing inputs to models like cropping or resizing and to 
 post-process results, like validating duplicate outputs, relating words to detected layout segments or ordering words 

{deepdoctection-0.29 → deepdoctection-0.31}/README.md

@@ -42,7 +42,9 @@ pipelines. Its core function does not depend on any specific deep learning libra
    Check this [notebook](https://github.com/deepdoctection/notebooks/blob/main/Analyzer_Configuration.ipynb) or the 
    [docs](https://deepdoctection.readthedocs.io/en/latest/tutorials/analyzer_configuration_notebook/) for more infos.
  - Document layout analysis and table recognition now runs with Torchscript (CPU) as well and Detectron2 is 
-   not required anymore for basic inference. 
+   not required anymore for basic inference.
+ - [**new**] More angle predictors for determining the rotation of a document based on Tesseract and DocTr 
+   (not contained in the built-in Analyzer).
 
 **deep**doctection provides on top of that methods for pre-processing inputs to models like cropping or resizing and to 
 post-process results, like validating duplicate outputs, relating words to detected layout segments or ordering words 

{deepdoctection-0.29 → deepdoctection-0.31}/deepdoctection/__init__.py

@@ -27,7 +27,7 @@ from .utils.logger import logger
 
 # pylint: enable=wrong-import-position
 
-__version__ = 0.29
+__version__ = 0.31
 
 _IMPORT_STRUCTURE = {
     "analyzer": [
@@ -179,6 +179,7 @@ _IMPORT_STRUCTURE = {
         "Jdeskewer",
         "DoctrTextlineDetector",
         "DoctrTextRecognizer",
+        "DocTrRotationTransformer",
         "FasttextLangDetector",
         "HFDetrDerivedDetector",
         "HFLayoutLmTokenClassifierBase",
@@ -194,6 +195,7 @@ _IMPORT_STRUCTURE = {
         "ModelDownloadManager",
         "PdfPlumberTextDetector",
         "TesseractOcrDetector",
+        "TesseractRotationTransformer",
         "TextractOcrDetector",
         "TPFrcnnDetector",
     ],
@@ -279,7 +281,7 @@ _IMPORT_STRUCTURE = {
         "PubtablesSegmentationService",
         "SegmentationResult",
         "TextExtractionService",
-        "SimpleTransformPipelineComponent",
+        "SimpleTransformService",
     ],
     "train": [
         "D2Trainer",
@@ -343,6 +345,8 @@ _IMPORT_STRUCTURE = {
         "get_opencv_requirement",
         "pillow_available",
         "get_pillow_requirement",
+        "spacy_available",
+        "get_spacy_requirement",
         "load_image_from_file",
         "load_bytes_from_pdf_file",
         "get_load_image_func",

{deepdoctection-0.29 → deepdoctection-0.31}/deepdoctection/analyzer/dd.py

@@ -54,7 +54,7 @@ from ..utils.file_utils import (
     tf_available,
 )
 from ..utils.fs import get_configs_dir_path, get_package_path, mkdir_p
-from ..utils.logger import logger
+from ..utils.logger import LoggingRecord, logger
 from ..utils.metacfg import AttrDict, set_config_by_yaml
 from ..utils.settings import CellType, LayoutType
 from ..utils.transform import PadTransform
@@ -113,11 +113,12 @@ def config_sanity_checks(cfg: AttrDict) -> None:
     """Some config sanity checks"""
     if cfg.USE_PDF_MINER and cfg.USE_OCR and cfg.OCR.USE_DOCTR:
         raise ValueError("Configuration USE_PDF_MINER= True and USE_OCR=True and USE_DOCTR=True is not allowed")
-    if cfg.OCR.USE_TESSERACT + cfg.OCR.USE_DOCTR + cfg.OCR.USE_TEXTRACT != 1:
-        raise ValueError(
-            "Choose either OCR.USE_TESSERACT=True or OCR.USE_DOCTR=True or OCR.USE_TEXTRACT=True and set the other two "
-            "to False. Only one OCR system can be activated."
-        )
+    if cfg.USE_OCR:
+        if cfg.OCR.USE_TESSERACT + cfg.OCR.USE_DOCTR + cfg.OCR.USE_TEXTRACT != 1:
+            raise ValueError(
+                "Choose either OCR.USE_TESSERACT=True or OCR.USE_DOCTR=True or OCR.USE_TEXTRACT=True "
+                "and set the other two to False. Only one OCR system can be activated."
+            )
 
 
 def build_detector(
@@ -231,9 +232,13 @@ def build_ocr(cfg: AttrDict) -> Union[TesseractOcrDetector, DoctrTextRecognizer,
         weights = cfg.OCR.WEIGHTS.DOCTR_RECOGNITION.TF if cfg.LIB == "TF" else cfg.OCR.WEIGHTS.DOCTR_RECOGNITION.PT
         weights_path = ModelDownloadManager.maybe_download_weights_and_configs(weights)
         profile = ModelCatalog.get_profile(weights)
+        # get_full_path_configs will complete the path even if the model is not registered
+        config_path = ModelCatalog.get_full_path_configs(weights) if profile.config is not None else None
         if profile.architecture is None:
             raise ValueError("model profile.architecture must be specified")
-        return DoctrTextRecognizer(profile.architecture, weights_path, cfg.DEVICE, lib=cfg.LIB)
+        return DoctrTextRecognizer(
+            profile.architecture, weights_path, cfg.DEVICE, lib=cfg.LIB, path_config_json=config_path
+        )
     if cfg.OCR.USE_TEXTRACT:
         credentials_kwargs = {
             "aws_access_key_id": environ.get("ACCESS_KEY"),
@@ -445,7 +450,7 @@ def get_dd_analyzer(
         cfg.update_args(config_overwrite)
 
     config_sanity_checks(cfg)
-    logger.info("Config: \n %s", str(cfg), cfg.to_dict())
+    logger.info(LoggingRecord(f"Config: \n {str(cfg)}", cfg.to_dict()))  # type: ignore
 
     # will silent all TP logging while building the tower
     if tensorpack_available():

{deepdoctection-0.29 → deepdoctection-0.31}/deepdoctection/dataflow/base.py

@@ -17,25 +17,6 @@ from typing import Any, Iterator, no_type_check
 from ..utils.utils import get_rng
 
 
-class DataFlowTerminated(BaseException):
-    """
-    An exception indicating that the DataFlow is unable to produce any more
-    data, i.e. something wrong happened so that calling `__iter__`
-    cannot give a valid iterator anymore.
-    In most DataFlow this will never be raised.
-    """
-
-
-class DataFlowResetStateNotCalled(BaseException):
-    """
-    An exception indicating that `reset_state()` has not been called before starting
-    iteration.
-    """
-
-    def __init__(self) -> None:
-        super().__init__("Iterating a dataflow requires .reset_state() to be called first")
-
-
 class DataFlowReentrantGuard:
     """
     A tool to enforce non-reentrancy.

{deepdoctection-0.29 → deepdoctection-0.31}/deepdoctection/dataflow/custom.py

@@ -25,10 +25,11 @@ from typing import Any, Callable, Iterable, Iterator, List, Optional
 
 import numpy as np
 
-from ..utils.logger import logger
+from ..utils.error import DataFlowResetStateNotCalledError
+from ..utils.logger import LoggingRecord, logger
 from ..utils.tqdm import get_tqdm
 from ..utils.utils import get_rng
-from .base import DataFlow, DataFlowReentrantGuard, DataFlowResetStateNotCalled, ProxyDataFlow
+from .base import DataFlow, DataFlowReentrantGuard, ProxyDataFlow
 from .serialize import DataFromIterable, DataFromList
 
 __all__ = ["CacheData", "CustomDataFromList", "CustomDataFromIterable"]
@@ -65,7 +66,7 @@ class CacheData(ProxyDataFlow):
 
     def __iter__(self) -> Iterator[Any]:
         if self._guard is None:
-            raise DataFlowResetStateNotCalled()
+            raise DataFlowResetStateNotCalledError()
 
         with self._guard:
             if self.buffer:
@@ -139,10 +140,10 @@ class CustomDataFromList(DataFromList):
 
     def __iter__(self) -> Iterator[Any]:
         if self.rng is None:
-            raise DataFlowResetStateNotCalled()
+            raise DataFlowResetStateNotCalledError()
         if self.rebalance_func is not None:
             lst_tmp = self.rebalance_func(self.lst)
-            logger.info("subset size after re-balancing: %s", len(lst_tmp))
+            logger.info(LoggingRecord(f"CustomDataFromList: subset size after re-balancing: {len(lst_tmp)}"))
         else:
             lst_tmp = self.lst
 

{deepdoctection-0.29 → deepdoctection-0.31}/deepdoctection/dataflow/custom_serialize.py

@@ -23,16 +23,20 @@ import itertools
 import json
 import os
 from collections import defaultdict
+from pathlib import Path
 from typing import DefaultDict, Dict, List, Optional, Sequence, Union
 
 from jsonlines import Reader, Writer
+from tabulate import tabulate
+from termcolor import colored
 
 from ..utils.context import timed_operation
 from ..utils.detection_types import JsonDict, Pathlike
+from ..utils.error import FileExtensionError
 from ..utils.identifier import get_uuid_from_str
 from ..utils.pdf_utils import PDFStreamer
 from ..utils.tqdm import get_tqdm
-from ..utils.utils import FileExtensionError, is_file_extension
+from ..utils.utils import is_file_extension
 from .base import DataFlow
 from .common import FlattenData, JoinData, MapData
 from .custom import CacheData, CustomDataFromIterable, CustomDataFromList
@@ -186,6 +190,11 @@ class SerializerFiles:
         df2: DataFlow
         df3: DataFlow
 
+        if isinstance(path, str):
+            path = Path(path)
+        if not path.exists():
+            raise NotADirectoryError(f"The path {path} to the directory or file does not exist")
+
         if shuffle:
             sort = False
         it1 = os.walk(path, topdown=False)
@@ -217,7 +226,7 @@ class SerializerFiles:
         """
         Not implemented
         """
-        raise NotImplementedError
+        raise NotImplementedError()
 
 
 class CocoParser:
@@ -277,8 +286,14 @@ class CocoParser:
         """
         Print information about the annotation file.
         """
+        rows = []
         for key, value in self.dataset["info"].items():
-            print(f"{key}: {value}")
+            row = [key, value]
+            rows.append(row)
+
+        header = ["key", "value"]
+        table = tabulate(rows, headers=header, tablefmt="fancy_grid", stralign="left", numalign="left")
+        print(colored(table, "cyan"))
 
     def get_ann_ids(
         self,
@@ -493,7 +508,7 @@ class SerializerCoco:
         """
         Not implemented
         """
-        raise NotImplementedError
+        raise NotImplementedError()
 
 
 class SerializerPdfDoc:
@@ -541,7 +556,7 @@ class SerializerPdfDoc:
         """
         Not implemented
         """
-        raise NotImplementedError
+        raise NotImplementedError()
 
     @staticmethod
     def split(path: Pathlike, path_target: Optional[Pathlike] = None, max_datapoint: Optional[int] = None) -> None:

{deepdoctection-0.29 → deepdoctection-0.31}/deepdoctection/dataflow/parallel_map.py

@@ -28,8 +28,9 @@ from typing import Any, Callable, Iterator, List, no_type_check
 import zmq
 
 from ..utils.concurrency import StoppableThread, enable_death_signal, start_proc_mask_signal
-from ..utils.logger import logger
-from .base import DataFlow, DataFlowReentrantGuard, DataFlowTerminated, ProxyDataFlow
+from ..utils.error import DataFlowTerminatedError
+from ..utils.logger import LoggingRecord, logger
+from .base import DataFlow, DataFlowReentrantGuard, ProxyDataFlow
 from .common import RepeatedData
 from .serialize import PickleSerializer
 
@@ -48,15 +49,15 @@ def _zmq_catch_error(name):
     try:
         yield
     except zmq.ContextTerminated as exc:
-        logger.info("[%s] Context terminated.", name)
-        raise DataFlowTerminated() from exc
+        logger.info(LoggingRecord(f"_zmq_catch_error: [{name}] Context terminated."))
+        raise DataFlowTerminatedError() from exc
     except zmq.ZMQError as exc:
         if exc.errno == errno.ENOTSOCK:  # socket closed
-            logger.info("[%s] Socket closed.", name)
-            raise DataFlowTerminated() from exc
-        raise ValueError from exc
+            logger.info(LoggingRecord(f"_zmq_catch_error: [{name}]  Socket closed."))
+            raise DataFlowTerminatedError() from exc
+        raise ValueError() from exc
     except Exception as exc:
-        raise ValueError from exc
+        raise ValueError() from exc
 
 
 @no_type_check
@@ -78,8 +79,8 @@ def _get_pipe_name(name):
 class _ParallelMapData(ProxyDataFlow, ABC):
     def __init__(self, df: DataFlow, buffer_size: int, strict: bool = False) -> None:
         super().__init__(df)
-        if not buffer_size:
-            raise ValueError("buffer_size must be a positive number")
+        if buffer_size <= 0:
+            raise ValueError(f"buffer_size must be a positive number, got {buffer_size}")
         self._buffer_size = buffer_size
         self._buffer_occupancy = 0  # actual #elements in buffer, only useful in strict mode
         self._strict = strict
@@ -95,12 +96,12 @@ class _ParallelMapData(ProxyDataFlow, ABC):
     @no_type_check
     @abstractmethod
     def _recv(self):
-        raise NotImplementedError
+        raise NotImplementedError()
 
     @no_type_check
     @abstractmethod
     def _send(self, dp: Any):
-        raise NotImplementedError
+        raise NotImplementedError()
 
     @no_type_check
     def _recv_filter_none(self):
@@ -312,7 +313,8 @@ class _MultiProcessZMQDataFlow(DataFlow, ABC):
             for x in self._procs:
                 x.terminate()
                 x.join(5)
-            logger.info("%s successfully cleaned-up.", type(self).__name__)
+            logger.info(LoggingRecord(f"_MultiProcessZMQDataFlow [{type(self).__name__}] successfully cleaned-up."))
+
         except Exception:  # pylint: disable=W0703
             pass
 
@@ -323,9 +325,12 @@ def _bind_guard(sock, name):
         sock.bind(name)
     except zmq.ZMQError:
         logger.error(
-            "ZMQError in socket.bind('{name}'). Perhaps you're using pipes on a non-local file system. "
-            "See documentation of MultiProcessRunnerZMQ for more information."
+            LoggingRecord(
+                f"ZMQError in socket.bind('{name}'). Perhaps you're using pipes on a non-local file system. "
+                "See documentation of MultiProcessRunnerZMQ for more information."
+            )
         )
+
         raise
 
 
@@ -394,8 +399,8 @@ class MultiProcessMapData(_ParallelMapData, _MultiProcessZMQDataFlow):
 
         _ParallelMapData.__init__(self, df, buffer_size, strict)
         _MultiProcessZMQDataFlow.__init__(self)
-        if not num_proc:
-            raise ValueError("num_proc must be a positive number")
+        if num_proc <= 0:
+            raise ValueError(f"num_proc must be a positive number, got {num_proc}")
         self.num_proc = num_proc
         self.map_func = map_func
         self._strict = strict

{deepdoctection-0.29 → deepdoctection-0.31}/deepdoctection/dataflow/serialize.py

@@ -16,7 +16,8 @@ from typing import Any, Iterable, Iterator, List, Optional, Tuple, Union
 
 import numpy as np
 
-from .base import DataFlow, DataFlowResetStateNotCalled, RNGDataFlow
+from ..utils.error import DataFlowResetStateNotCalledError
+from .base import DataFlow, RNGDataFlow
 
 
 class DataFromList(RNGDataFlow):
@@ -44,7 +45,7 @@ class DataFromList(RNGDataFlow):
                 for k in idxs:
                     yield self.lst[k]
             else:
-                raise DataFlowResetStateNotCalled()
+                raise DataFlowResetStateNotCalledError()
 
 
 class DataFromIterable(DataFlow):
@@ -63,7 +64,7 @@ class DataFromIterable(DataFlow):
 
     def __len__(self) -> int:
         if self._len is None:
-            raise NotImplementedError
+            raise NotImplementedError()
         return self._len
 
     def __iter__(self) -> Iterator[Any]:
@@ -107,7 +108,7 @@ class FakeData(RNGDataFlow):
 
     def __iter__(self) -> Iterator[Any]:
         if self.rng is None:
-            raise DataFlowResetStateNotCalled()
+            raise DataFlowResetStateNotCalledError()
         if self.random:
             for _ in range(self._size):
                 val = []

{deepdoctection-0.29 → deepdoctection-0.31}/deepdoctection/dataflow/stats.py

@@ -23,7 +23,7 @@ from typing import Any, Optional, Tuple, Union
 import numpy as np
 import numpy.typing as npt
 
-from ..utils.logger import logger
+from ..utils.logger import LoggingRecord, logger
 from ..utils.tqdm import get_tqdm
 from .base import DataFlow, ProxyDataFlow
 
@@ -95,7 +95,7 @@ class MeanFromDataFlow(ProxyDataFlow):
             self.df.reset_state()
         itr = iter(self.df)
 
-        logger.info("Calculating mean")
+        logger.info(LoggingRecord("Calculating mean"))
 
         len_df: Optional[int]
         try:
@@ -139,7 +139,7 @@ class MeanFromDataFlow(ProxyDataFlow):
                     if n == self.max_datapoints:
                         break
 
-        logger.info("Mean from %s datapoints along axis %s: %s", n, self.axis, self.mean)
+        logger.info(LoggingRecord(f"Mean from {n} datapoints along axis {self.axis}: {self.mean}"))
 
         return self.mean
 
@@ -216,7 +216,7 @@ class StdFromDataFlow(ProxyDataFlow):
             self.df.reset_state()
         itr = iter(self.df)
 
-        logger.info("Calculating standard deviation")
+        logger.info(LoggingRecord("Calculating standard deviation"))
         try:
             len_df = len(self.df)
         except NotImplementedError:
@@ -266,6 +266,6 @@ class StdFromDataFlow(ProxyDataFlow):
             var = (ex2 - (ex * ex) / n) / (n - 1)
             self.std = np.sqrt(var)
 
-        logger.info("Standard deviation from %s datapoints along axis %s: %s", n, self.axis, self.std)
+        logger.info(LoggingRecord(f"Standard deviation from  {n} datapoints along axis {self.axis}: {self.std}"))
 
         return self.std