deepdoctection 0.39.6__py3-none-any.whl → 0.40.0__py3-none-any.whl

deepdoctection/datasets/registry.py

@@ -24,7 +24,7 @@ import catalogue  # type: ignore
 from tabulate import tabulate
 from termcolor import colored
 
-from .base import DatasetBase, CustomDataset
+from .base import CustomDataset, DatasetBase
 
 __all__ = ["dataset_registry", "get_dataset", "print_dataset_infos"]
 

deepdoctection/mapper/match.py

@@ -34,13 +34,15 @@ from ..utils.settings import TypeOrStr
 
 def match_anns_by_intersection(
     dp: Image,
-    parent_ann_category_names: Union[TypeOrStr, Sequence[TypeOrStr]],
-    child_ann_category_names: Union[TypeOrStr, Sequence[TypeOrStr]],
     matching_rule: Literal["iou", "ioa"],
     threshold: float,
     use_weighted_intersections: bool = False,
+    parent_ann_category_names: Optional[Union[TypeOrStr, Sequence[TypeOrStr]]] = None,
+    child_ann_category_names: Optional[Union[TypeOrStr, Sequence[TypeOrStr]]] = None,
     parent_ann_ids: Optional[Union[Sequence[str], str]] = None,
     child_ann_ids: Optional[Union[str, Sequence[str]]] = None,
+    parent_ann_service_ids: Optional[Union[str, Sequence[str]]] = None,
+    child_ann_service_ids: Optional[Union[str, Sequence[str]]] = None,
     max_parent_only: bool = False,
 ) -> tuple[Any, Any, Sequence[ImageAnnotation], Sequence[ImageAnnotation]]:
     """
@@ -87,13 +89,19 @@ def match_anns_by_intersection(
                            dates which are not in the list.
     :param child_ann_ids: Additional filter condition. If some ids are selected, it will ignore all other children
                           candidates which are not in the list.
+    :param parent_ann_service_ids: Additional filter condition. If some ids are selected, it will ignore all other
+                                   parent candidates which are not in the list.
+    :param child_ann_service_ids: Additional filter condition. If some ids are selected, it will ignore all other
+                                  children candidates which are not in the list.
     :param max_parent_only: Will assign to each child at most one parent with maximum ioa
     :return: child indices, parent indices (see Example), list of parent ids and list of children ids.
     """
 
     assert matching_rule in ["iou", "ioa"], "matching rule must be either iou or ioa"
 
-    child_anns = dp.get_annotation(annotation_ids=child_ann_ids, category_names=child_ann_category_names)
+    child_anns = dp.get_annotation(
+        annotation_ids=child_ann_ids, category_names=child_ann_category_names, service_ids=child_ann_service_ids
+    )
     child_ann_boxes = np.array(
         [
             ann.get_bounding_box(dp.image_id).transform(dp.width, dp.height, absolute_coords=True).to_list(mode="xyxy")
@@ -101,7 +109,9 @@ def match_anns_by_intersection(
         ]
     )
 
-    parent_anns = dp.get_annotation(annotation_ids=parent_ann_ids, category_names=parent_ann_category_names)
+    parent_anns = dp.get_annotation(
+        annotation_ids=parent_ann_ids, category_names=parent_ann_category_names, service_ids=parent_ann_service_ids
+    )
     parent_ann_boxes = np.array(
         [
             ann.get_bounding_box(dp.image_id).transform(dp.width, dp.height, absolute_coords=True).to_list(mode="xyxy")
@@ -147,10 +157,12 @@ def match_anns_by_intersection(
 
 def match_anns_by_distance(
     dp: Image,
-    parent_ann_category_names: Union[TypeOrStr, Sequence[TypeOrStr]],
-    child_ann_category_names: Union[TypeOrStr, Sequence[TypeOrStr]],
+    parent_ann_category_names:  Optional[Union[TypeOrStr, Sequence[TypeOrStr]]]=None,
+    child_ann_category_names:  Optional[Union[TypeOrStr, Sequence[TypeOrStr]]]=None,
     parent_ann_ids: Optional[Union[Sequence[str], str]] = None,
     child_ann_ids: Optional[Union[str, Sequence[str]]] = None,
+    parent_ann_service_ids: Optional[Union[str, Sequence[str]]] = None,
+    child_ann_service_ids: Optional[Union[str, Sequence[str]]] = None,
 ) -> list[tuple[ImageAnnotation, ImageAnnotation]]:
     """
     Generates pairs of parent and child annotations by calculating the euclidean distance between the centers of the
@@ -164,11 +176,19 @@ def match_anns_by_distance(
                            dates which are not in the list.
     :param child_ann_ids: Additional filter condition. If some ids are selected, it will ignore all other children
                           candidates which are not in the list.
+    :param parent_ann_service_ids: Additional filter condition. If some ids are selected, it will ignore all other
+                                   parent candidates which are not in the list.
+    :param child_ann_service_ids: Additional filter condition. If some ids are selected, it will ignore all other
+                                  children candidates which are not in the list.
     :return:
     """
 
-    parent_anns = dp.get_annotation(annotation_ids=parent_ann_ids, category_names=parent_ann_category_names)
-    child_anns = dp.get_annotation(annotation_ids=child_ann_ids, category_names=child_ann_category_names)
+    parent_anns = dp.get_annotation(
+        annotation_ids=parent_ann_ids, category_names=parent_ann_category_names, service_ids=parent_ann_service_ids
+    )
+    child_anns = dp.get_annotation(
+        annotation_ids=child_ann_ids, category_names=child_ann_category_names, service_ids=child_ann_service_ids
+    )
     child_centers = [block.get_bounding_box(dp.image_id).center for block in child_anns]
     parent_centers = [block.get_bounding_box(dp.image_id).center for block in parent_anns]
     if child_centers and parent_centers:

deepdoctection/pipe/anngen.py

@@ -75,27 +75,6 @@ class DatapointManager:
         """
         assert self.datapoint_is_passed, "Pass datapoint to  DatapointManager before creating anns"
 
-    def maybe_map_category_id(self, category_id: Union[str, int]) -> int:
-        """
-        Maps categories if a category id mapping is provided in `__init__`.
-
-        :param category_id: category id via integer or string.
-        :return: mapped category id
-        """
-        if self.category_id_mapping is None:
-            return int(category_id)
-        return self.category_id_mapping[int(category_id)]
-
-    def set_category_id_mapping(self, category_id_mapping: Mapping[int, int]) -> None:
-        """
-        In many cases the category ids sent back from a model have to be modified. Pass a mapping from model
-        category ids to target annotation category ids.
-
-        :param category_id_mapping: A mapping of model category ids (sent from DetectionResult) to category ids (saved
-                                    in annotations)
-        """
-        self.category_id_mapping = category_id_mapping
-
     def set_image_annotation(
         self,
         detect_result: DetectionResult,
@@ -127,13 +106,10 @@ class DatapointManager:
         :return: the annotation_id of the generated image annotation
         """
         self.assert_datapoint_passed()
-        if detect_result.class_id is None:
-            raise ValueError("class_id of detect_result cannot be None")
         if not isinstance(detect_result.box, (list, np.ndarray)):
             raise TypeError(
                 f"detect_result.box must be of type list or np.ndarray, but is of type {(type(detect_result.box))}"
             )
-        detect_result.class_id = self.maybe_map_category_id(detect_result.class_id)
         with MappingContextManager(
             dp_name=self.datapoint.file_name, filter_level="annotation", detect_result=asdict(detect_result)
         ) as annotation_context:
@@ -155,7 +131,7 @@ class DatapointManager:
             ann = ImageAnnotation(
                 category_name=detect_result.class_name,
                 bounding_box=box,
-                category_id=detect_result.class_id,
+                category_id=detect_result.class_id if detect_result.class_id is not None else DEFAULT_CATEGORY_ID,
                 score=detect_result.score,
                 service_id=self.service_id,
                 model_id=self.model_id,

deepdoctection/pipe/common.py

@@ -22,6 +22,7 @@ from __future__ import annotations
 
 import os
 from copy import deepcopy
+from dataclasses import dataclass, field
 from typing import Literal, Mapping, Optional, Sequence, Union
 
 import numpy as np
@@ -49,24 +50,30 @@ class ImageCroppingService(PipelineComponent):
     generally not stored.
     """
 
-    def __init__(self, category_names: Union[TypeOrStr, Sequence[TypeOrStr]]):
+    def __init__(
+        self, category_names: Optional[Union[TypeOrStr, Sequence[TypeOrStr]]] = None,
+             service_ids: Optional[Sequence[str]] = None
+    ) -> None:
         """
         :param category_names: A single name or a list of category names to crop
         """
-
-        self.category_names = (
-            (category_names,)
-            if isinstance(category_names, str)
-            else tuple(get_type(category_name) for category_name in category_names)
-        )
+        if category_names is None:
+            self.category_names = None
+        else:
+            self.category_names = (
+                (category_names,)
+                if isinstance(category_names, str)
+                else tuple(get_type(category_name) for category_name in category_names)
+            )
+        self.service_ids = service_ids
         super().__init__("image_crop")
 
     def serve(self, dp: Image) -> None:
-        for ann in dp.get_annotation(category_names=self.category_names):
+        for ann in dp.get_annotation(category_names=self.category_names, service_ids=self.service_ids):
             dp.image_ann_to_image(ann.annotation_id, crop_image=True)
 
     def clone(self) -> ImageCroppingService:
-        return self.__class__(self.category_names)
+        return self.__class__(self.category_names, self.service_ids)
 
     def get_meta_annotation(self) -> MetaAnnotation:
         return MetaAnnotation(image_annotations=(), sub_categories={}, relationships={}, summaries=())
@@ -124,8 +131,10 @@ class IntersectionMatcher:
     def match(
         self,
         dp: Image,
-        parent_categories: Union[TypeOrStr, Sequence[TypeOrStr]],
-        child_categories: Union[TypeOrStr, Sequence[TypeOrStr]],
+        parent_categories: Optional[Union[TypeOrStr, Sequence[TypeOrStr]]] = None,
+        child_categories: Optional[Union[TypeOrStr, Sequence[TypeOrStr]]] = None,
+        parent_ann_service_ids: Optional[Union[str, Sequence[str]]] = None,
+        child_ann_service_ids: Optional[Union[str, Sequence[str]]] = None,
     ) -> list[tuple[str, str]]:
         """
         The matching algorithm
@@ -133,6 +142,10 @@ class IntersectionMatcher:
         :param dp: datapoint image
         :param parent_categories: list of categories to be used a for parent class. Will generate a child-relationship
         :param child_categories: list of categories to be used for a child class.
+        :param parent_ann_service_ids: Additional filter condition. If some ids are selected, it will ignore all other
+                                        parent candidates which are not in the list.
+        :param child_ann_service_ids: Additional filter condition. If some ids are selected, it will ignore all other
+                                        children candidates which are not in the list.
 
         :return: A list of tuples with parent and child annotation ids
         """
@@ -144,6 +157,8 @@ class IntersectionMatcher:
             threshold=self.threshold,
             use_weighted_intersections=self.use_weighted_intersections,
             max_parent_only=self.max_parent_only,
+            parent_ann_service_ids=parent_ann_service_ids,
+            child_ann_service_ids=child_ann_service_ids,
         )
 
         matched_child_anns = np.take(child_anns, child_index)  # type: ignore
@@ -174,8 +189,10 @@ class NeighbourMatcher:
     def match(
         self,
         dp: Image,
-        parent_categories: Union[TypeOrStr, Sequence[TypeOrStr]],
-        child_categories: Union[TypeOrStr, Sequence[TypeOrStr]],
+        parent_categories: Optional[Union[TypeOrStr, Sequence[TypeOrStr]]] = None,
+        child_categories: Optional[Union[TypeOrStr, Sequence[TypeOrStr]]] = None,
+        parent_ann_service_ids: Optional[Union[str, Sequence[str]]] = None,
+        child_ann_service_ids: Optional[Union[str, Sequence[str]]] = None,
     ) -> list[tuple[str, str]]:
         """
         The matching algorithm
@@ -183,16 +200,54 @@ class NeighbourMatcher:
         :param dp: datapoint image
         :param parent_categories: list of categories to be used a for parent class. Will generate a child-relationship
         :param child_categories: list of categories to be used for a child class.
+        :param parent_ann_service_ids: Additional filter condition. If some ids are selected, it will ignore all other
+                                        parent candidates which are not in the list.
+        :param child_ann_service_ids: Additional filter condition. If some ids are selected, it will ignore all other
+                                        children candidates which are not in the list.
 
         :return: A list of tuples with parent and child annotation ids
         """
 
         return [
             (pair[0].annotation_id, pair[1].annotation_id)
-            for pair in match_anns_by_distance(dp, parent_categories, child_categories)
+            for pair in match_anns_by_distance(
+                dp,
+                parent_ann_category_names=parent_categories,
+                child_ann_category_names=child_categories,
+                parent_ann_service_ids=parent_ann_service_ids,
+                child_ann_service_ids=child_ann_service_ids,
+            )
         ]
 
 
+@dataclass
+class FamilyCompound:
+    """
+    A family compound is a set of parent and child categories that are related by a relationship key. The parent
+    categories will receive a relationship to the child categories.
+    """
+
+    relationship_key: Relationships
+    parent_categories: Optional[Union[ObjectTypes, Sequence[ObjectTypes]]] = field(default=None)
+    child_categories: Optional[Union[ObjectTypes, Sequence[ObjectTypes]]] = field(default=None)
+    parent_ann_service_ids: Optional[Union[str, Sequence[str]]] = field(default=None)
+    child_ann_service_ids: Optional[Union[str, Sequence[str]]] = field(default=None)
+
+    def __post_init__(self) -> None:
+        if isinstance(self.parent_categories, str):
+            self.parent_categories = (get_type(self.parent_categories),)
+        elif self.parent_categories is not None:
+            self.parent_categories = tuple(get_type(parent) for parent in self.parent_categories)
+        if isinstance(self.child_categories, str):
+            self.child_categories = (get_type(self.child_categories),)
+        elif self.child_categories is not None:
+            self.child_categories = tuple(get_type(child) for child in self.child_categories)
+        if isinstance(self.parent_ann_service_ids, str):
+            self.parent_ann_service_ids = (self.parent_ann_service_ids,)
+        if isinstance(self.child_ann_service_ids, str):
+            self.child_ann_service_ids = (self.child_ann_service_ids,)
+
+
 @pipeline_component_registry.register("MatchingService")
 class MatchingService(PipelineComponent):
     """
@@ -202,28 +257,15 @@ class MatchingService(PipelineComponent):
 
     def __init__(
         self,
-        parent_categories: Union[TypeOrStr, Sequence[TypeOrStr]],
-        child_categories: Union[TypeOrStr, Sequence[TypeOrStr]],
+        family_compounds: Sequence[FamilyCompound],
         matcher: Union[IntersectionMatcher, NeighbourMatcher],
-        relationship_key: Relationships,
     ) -> None:
         """
-        :param parent_categories: list of categories to be used a for parent class. Will generate a child-relationship
-        :param child_categories: list of categories to be used for a child class.
-
+        :param family_compounds: A list of FamilyCompounds
+        :param matcher: A matcher object
         """
-        self.parent_categories = (
-            (get_type(parent_categories),)
-            if isinstance(parent_categories, str)
-            else tuple(get_type(category_name) for category_name in parent_categories)
-        )
-        self.child_categories = (
-            (get_type(child_categories),)
-            if isinstance(child_categories, str)
-            else (tuple(get_type(category_name) for category_name in child_categories))
-        )
+        self.family_compounds = family_compounds
         self.matcher = matcher
-        self.relationship_key = relationship_key
         super().__init__("matching")
 
     def serve(self, dp: Image) -> None:
@@ -233,20 +275,31 @@ class MatchingService(PipelineComponent):
 
         :param dp: datapoint image
         """
-
-        matched_pairs = self.matcher.match(dp, self.parent_categories, self.child_categories)
-
-        for pair in matched_pairs:
-            self.dp_manager.set_relationship_annotation(self.relationship_key, pair[0], pair[1])
+        for family_compound in self.family_compounds:
+            matched_pairs = self.matcher.match(
+                dp,
+                parent_categories=family_compound.parent_categories,
+                child_categories=family_compound.child_categories,
+                parent_ann_service_ids=family_compound.parent_ann_service_ids,
+                child_ann_service_ids=family_compound.child_ann_service_ids,
+            )
+
+            for pair in matched_pairs:
+                self.dp_manager.set_relationship_annotation(family_compound.relationship_key, pair[0], pair[1])
 
     def clone(self) -> PipelineComponent:
-        return self.__class__(self.parent_categories, self.child_categories, self.matcher, self.relationship_key)
+        return self.__class__(self.family_compounds, self.matcher)
 
     def get_meta_annotation(self) -> MetaAnnotation:
+        relationships: dict[ObjectTypes, set[ObjectTypes]] = {}
+        for family_compound in self.family_compounds:
+            if family_compound.parent_categories is not None:
+                for parent_category in family_compound.parent_categories:
+                    relationships[parent_category] = {family_compound.relationship_key}  # type: ignore
         return MetaAnnotation(
             image_annotations=(),
             sub_categories={},
-            relationships={parent: {Relationships.CHILD} for parent in self.parent_categories},
+            relationships=relationships,
             summaries=(),
         )
 

deepdoctection/pipe/layout.py

@@ -20,18 +20,41 @@ Module for layout pipeline component
 """
 from __future__ import annotations
 
-from typing import Optional
+from typing import Optional, Sequence, Union
 
 import numpy as np
 
 from ..datapoint.image import Image
 from ..extern.base import ObjectDetector, PdfMiner
+from ..mapper.misc import curry
 from ..utils.error import ImageError
+from ..utils.settings import ObjectTypes
 from ..utils.transform import PadTransform
 from .base import MetaAnnotation, PipelineComponent
 from .registry import pipeline_component_registry
 
 
+@curry
+def skip_if_category_or_service_extracted(
+    dp: Image,
+    category_names: Optional[Union[str, Sequence[ObjectTypes]]] = None,
+    service_ids: Optional[Union[str, Sequence[str]]] = None,
+) -> bool:
+    """
+    Skip the processing of the pipeline component if the category or service is already extracted.
+
+    **Example**
+
+        detector = # some detector
+        item_component = ImageLayoutService(detector)
+        item_component.set_inbound_filter(skip_if_category_or_service_extracted(detector.get_categories(as_dict=False)))
+    """
+
+    if dp.get_annotation(category_names=category_names, service_ids=service_ids):
+        return True
+    return False
+
+
 @pipeline_component_registry.register("ImageLayoutService")
 class ImageLayoutService(PipelineComponent):
     """
@@ -45,7 +68,7 @@ class ImageLayoutService(PipelineComponent):
 
     **Example**
 
-            d_items = TPFrcnnDetector(item_config_path, item_weights_path, {"1": "ROW", "2": "COLUMNS"})
+            d_items = TPFrcnnDetector(item_config_path, item_weights_path, {1: 'row', 2: 'column'})
             item_component = ImageLayoutService(d_items)
     """
 
@@ -55,7 +78,6 @@ class ImageLayoutService(PipelineComponent):
         to_image: bool = False,
         crop_image: bool = False,
         padder: Optional[PadTransform] = None,
-        skip_if_layout_extracted: bool = False,
     ):
         """
         :param layout_detector: object detector
@@ -65,23 +87,14 @@ class ImageLayoutService(PipelineComponent):
                            to its bounding box and populate the resulting sub image to
                            `ImageAnnotation.image.image`.
         :param padder: If not `None`, will apply the padder to the image before prediction and inverse apply the padder
-        :param skip_if_layout_extracted: When `True` will check, if there are already `ImageAnnotation` of a category
-                                         available that will be predicted by the `layout_detector`. If yes, will skip
-                                         the prediction process.
         """
         self.to_image = to_image
         self.crop_image = crop_image
         self.padder = padder
-        self.skip_if_layout_extracted = skip_if_layout_extracted
         self.predictor = layout_detector
         super().__init__(self._get_name(layout_detector.name), self.predictor.model_id)
 
     def serve(self, dp: Image) -> None:
-        if self.skip_if_layout_extracted:
-            categories = self.predictor.get_category_names()
-            anns = dp.get_annotation(category_names=categories)
-            if anns:
-                return
         if dp.image is None:
             raise ImageError("image cannot be None")
         np_image = dp.image
@@ -117,7 +130,7 @@ class ImageLayoutService(PipelineComponent):
             padder_clone = self.padder.clone()
         if not isinstance(predictor, ObjectDetector):
             raise TypeError(f"predictor must be of type ObjectDetector, but is of type {type(predictor)}")
-        return self.__class__(predictor, self.to_image, self.crop_image, padder_clone, self.skip_if_layout_extracted)
+        return self.__class__(predictor, self.to_image, self.crop_image, padder_clone)
 
     def clear_predictor(self) -> None:
         self.predictor.clear_model()

deepdoctection/pipe/order.py

@@ -347,19 +347,15 @@ class TextLineGenerator:
     a paragraph break threshold. This allows to detect a multi column structure just by observing sub lines.
     """
 
-    def __init__(
-        self, make_sub_lines: bool, line_category_id: Union[int, str], paragraph_break: Optional[float] = None
-    ):
+    def __init__(self, make_sub_lines: bool, paragraph_break: Optional[float] = None):
         """
         :param make_sub_lines: Whether to build sub lines from lines.
-        :param line_category_id: category_id to give a text line
         :param paragraph_break: threshold of two consecutive words. If distance is larger than threshold, two sub-lines
                                 will be built. We use relative coordinates to calculate the distance between two
                                 consecutive words. A reasonable value is 0.035
         """
         if make_sub_lines and paragraph_break is None:
             raise ValueError("You must specify paragraph_break when setting make_sub_lines to True")
-        self.line_category_id = int(line_category_id)
         self.make_sub_lines = make_sub_lines
         self.paragraph_break = paragraph_break
 
@@ -367,7 +363,6 @@ class TextLineGenerator:
         return DetectionResult(
             box=box.to_list(mode="xyxy"),
             class_name=LayoutType.LINE,
-            class_id=self.line_category_id,
             absolute_coords=box.absolute_coords,
             relationships=relationships,
         )
@@ -475,18 +470,14 @@ class TextLineServiceMixin(PipelineComponent, ABC):
     def __init__(
         self,
         name: str,
-        line_category_id: int = 1,
         include_residual_text_container: bool = True,
         paragraph_break: Optional[float] = None,
     ):
         """
-        Initialize the TextLineService with a line_category_id and a TextLineGenerator instance.
+        Initialize the TextLineServiceMixin with a TextLineGenerator instance.
         """
-        self.line_category_id = line_category_id
         self.include_residual_text_container = include_residual_text_container
-        self.text_line_generator = TextLineGenerator(
-            self.include_residual_text_container, self.line_category_id, paragraph_break
-        )
+        self.text_line_generator = TextLineGenerator(self.include_residual_text_container, paragraph_break)
         super().__init__(name)
 
     def _create_lines_for_words(self, word_anns: Sequence[ImageAnnotation]) -> Sequence[ImageAnnotation]:
@@ -523,17 +514,15 @@ class TextLineService(TextLineServiceMixin):
     text lines and the words contained in the text lines. The reading order is not arranged.
     """
 
-    def __init__(self, line_category_id: int = 1, paragraph_break: Optional[float] = None):
+    def __init__(self, paragraph_break: Optional[float] = None):
         """
         Initialize `TextLineService`
 
-        :param line_category_id: category_id to give a text line
         :param paragraph_break: threshold of two consecutive words. If distance is larger than threshold, two sublines
                                 will be built
         """
         super().__init__(
             name="text_line",
-            line_category_id=line_category_id,
             include_residual_text_container=True,
             paragraph_break=paragraph_break,
         )
@@ -542,7 +531,7 @@ class TextLineService(TextLineServiceMixin):
         """
         This method returns a new instance of the class with the same configuration.
         """
-        return self.__class__(self.line_category_id, self.text_line_generator.paragraph_break)
+        return self.__class__(self.text_line_generator.paragraph_break)
 
     def serve(self, dp: Image) -> None:
         text_container_anns = dp.get_annotation(category_names=LayoutType.WORD)
@@ -605,7 +594,6 @@ class TextOrderService(TextLineServiceMixin):
         broken_line_tolerance: float = 0.003,
         height_tolerance: float = 2.0,
         paragraph_break: Optional[float] = 0.035,
-        line_category_id: int = 1,
     ):
         """
         :param text_container: name of an image annotation that has a CHARS sub category. These annotations will be
@@ -647,12 +635,9 @@ class TextOrderService(TextLineServiceMixin):
             self.floating_text_block_categories = self.floating_text_block_categories + (LayoutType.LINE,)
         self.include_residual_text_container = include_residual_text_container
         self.order_generator = OrderGenerator(starting_point_tolerance, broken_line_tolerance, height_tolerance)
-        self.text_line_generator = TextLineGenerator(
-            self.include_residual_text_container, line_category_id, paragraph_break
-        )
+        self.text_line_generator = TextLineGenerator(self.include_residual_text_container, paragraph_break)
         super().__init__(
             name="text_order",
-            line_category_id=line_category_id,
             include_residual_text_container=include_residual_text_container,
             paragraph_break=paragraph_break,
         )
@@ -763,7 +748,6 @@ class TextOrderService(TextLineServiceMixin):
             self.order_generator.broken_line_tolerance,
             self.order_generator.height_tolerance,
             self.text_line_generator.paragraph_break,
-            self.text_line_generator.line_category_id,
         )
 
     def clear_predictor(self) -> None: