docling 2.30.0__py3-none-any.whl → 2.31.0__py3-none-any.whl

docling/models/hf_mlx_model.py

@@ -1,25 +1,22 @@
 import logging
 import time
+from collections.abc import Iterable
 from pathlib import Path
-from typing import Iterable, List, Optional
+from typing import Optional
 
 from docling.datamodel.base_models import Page, VlmPrediction
 from docling.datamodel.document import ConversionResult
 from docling.datamodel.pipeline_options import (
-    AcceleratorDevice,
     AcceleratorOptions,
     HuggingFaceVlmOptions,
 )
-from docling.datamodel.settings import settings
 from docling.models.base_model import BasePageModel
-from docling.utils.accelerator_utils import decide_device
 from docling.utils.profiling import TimeRecorder
 
 _log = logging.getLogger(__name__)
 
 
 class HuggingFaceMlxModel(BasePageModel):
-
     def __init__(
         self,
         enabled: bool,
@@ -32,7 +29,6 @@ class HuggingFaceMlxModel(BasePageModel):
         self.vlm_options = vlm_options
 
         if self.enabled:
-
             try:
                 from mlx_vlm import generate, load  # type: ignore
                 from mlx_vlm.prompt_utils import apply_chat_template  # type: ignore
@@ -125,6 +121,8 @@ class HuggingFaceMlxModel(BasePageModel):
                     generation_time = time.time() - start_time
                     page_tags = output
 
+                    _log.debug(f"Generation time {generation_time:.2f} seconds.")
+
                     # inference_time = time.time() - start_time
                     # tokens_per_second = num_tokens / generation_time
                     # print("")

docling/models/hf_vlm_model.py

@@ -1,16 +1,15 @@
 import logging
 import time
+from collections.abc import Iterable
 from pathlib import Path
-from typing import Iterable, List, Optional
+from typing import Optional
 
 from docling.datamodel.base_models import Page, VlmPrediction
 from docling.datamodel.document import ConversionResult
 from docling.datamodel.pipeline_options import (
-    AcceleratorDevice,
     AcceleratorOptions,
     HuggingFaceVlmOptions,
 )
-from docling.datamodel.settings import settings
 from docling.models.base_model import BasePageModel
 from docling.utils.accelerator_utils import decide_device
 from docling.utils.profiling import TimeRecorder
@@ -19,7 +18,6 @@ _log = logging.getLogger(__name__)
 
 
 class HuggingFaceVlmModel(BasePageModel):
-
     def __init__(
         self,
         enabled: bool,
@@ -42,7 +40,7 @@ class HuggingFaceVlmModel(BasePageModel):
             device = decide_device(accelerator_options.device)
             self.device = device
 
-            _log.debug("Available device for HuggingFace VLM: {}".format(device))
+            _log.debug(f"Available device for HuggingFace VLM: {device}")
 
             repo_cache_folder = vlm_options.repo_id.replace("/", "--")
 
@@ -168,6 +166,10 @@ class HuggingFaceVlmModel(BasePageModel):
                     num_tokens = len(generated_ids[0])
                     page_tags = generated_texts
 
+                    _log.debug(
+                        f"Generated {num_tokens} tokens in time {generation_time:.2f} seconds."
+                    )
+
                     # inference_time = time.time() - start_time
                     # tokens_per_second = num_tokens / generation_time
                     # print("")

docling/models/layout_model.py

@@ -1,8 +1,9 @@
 import copy
 import logging
 import warnings
+from collections.abc import Iterable
 from pathlib import Path
-from typing import Iterable, Optional, Union
+from typing import Optional
 
 from docling_core.types.doc import DocItemLabel
 from docling_ibm_models.layoutmodel.layout_predictor import LayoutPredictor
@@ -142,7 +143,6 @@ class LayoutModel(BasePageModel):
     def __call__(
         self, conv_res: ConversionResult, page_batch: Iterable[Page]
     ) -> Iterable[Page]:
-
         for page in page_batch:
             assert page._backend is not None
             if not page._backend.is_valid():

docling/models/ocr_mac_model.py

@@ -1,8 +1,9 @@
 import logging
 import sys
 import tempfile
+from collections.abc import Iterable
 from pathlib import Path
-from typing import Iterable, Optional, Tuple, Type
+from typing import Optional, Type
 
 from docling_core.types.doc import BoundingBox, CoordOrigin
 from docling_core.types.doc.page import BoundingRectangle, TextCell
@@ -41,7 +42,7 @@ class OcrMacModel(BaseOcrModel):
 
         if self.enabled:
             if "darwin" != sys.platform:
-                raise RuntimeError(f"OcrMac is only supported on Mac.")
+                raise RuntimeError("OcrMac is only supported on Mac.")
             install_errmsg = (
                 "ocrmac is not correctly installed. "
                 "Please install it via `pip install ocrmac` to use this OCR engine. "
@@ -58,7 +59,6 @@ class OcrMacModel(BaseOcrModel):
     def __call__(
         self, conv_res: ConversionResult, page_batch: Iterable[Page]
     ) -> Iterable[Page]:
-
         if not self.enabled:
             yield from page_batch
             return
@@ -69,7 +69,6 @@ class OcrMacModel(BaseOcrModel):
                 yield page
             else:
                 with TimeRecorder(conv_res, "ocr"):
-
                     ocr_rects = self.get_ocr_rects(page)
 
                     all_ocr_cells = []

docling/models/page_assemble_model.py

@@ -1,6 +1,7 @@
 import logging
 import re
-from typing import Iterable, List
+from collections.abc import Iterable
+from typing import List
 
 from pydantic import BaseModel
 
@@ -53,9 +54,9 @@ class PageAssembleModel(BasePageModel):
         sanitized_text = "".join(lines)
 
         # Text normalization
-        sanitized_text = sanitized_text.replace("⁄", "/")
-        sanitized_text = sanitized_text.replace("’", "'")
-        sanitized_text = sanitized_text.replace("‘", "'")
+        sanitized_text = sanitized_text.replace("⁄", "/")  # noqa: RUF001
+        sanitized_text = sanitized_text.replace("’", "'")  # noqa: RUF001
+        sanitized_text = sanitized_text.replace("‘", "'")  # noqa: RUF001
         sanitized_text = sanitized_text.replace("“", '"')
         sanitized_text = sanitized_text.replace("”", '"')
         sanitized_text = sanitized_text.replace("•", "·")
@@ -71,7 +72,6 @@ class PageAssembleModel(BasePageModel):
                 yield page
             else:
                 with TimeRecorder(conv_res, "page_assemble"):
-
                     assert page.predictions.layout is not None
 
                     # assembles some JSON output page by page.
@@ -83,7 +83,6 @@ class PageAssembleModel(BasePageModel):
                     for cluster in page.predictions.layout.clusters:
                         # _log.info("Cluster label seen:", cluster.label)
                         if cluster.label in LayoutModel.TEXT_ELEM_LABELS:
-
                             textlines = [
                                 cell.text.replace("\x02", "-").strip()
                                 for cell in cluster.cells
@@ -109,9 +108,7 @@ class PageAssembleModel(BasePageModel):
                                 tbl = page.predictions.tablestructure.table_map.get(
                                     cluster.id, None
                                 )
-                            if (
-                                not tbl
-                            ):  # fallback: add table without structure, if it isn't present
+                            if not tbl:  # fallback: add table without structure, if it isn't present
                                 tbl = Table(
                                     label=cluster.label,
                                     id=cluster.id,
@@ -130,9 +127,7 @@ class PageAssembleModel(BasePageModel):
                                 fig = page.predictions.figures_classification.figure_map.get(
                                     cluster.id, None
                                 )
-                            if (
-                                not fig
-                            ):  # fallback: add figure without classification, if it isn't present
+                            if not fig:  # fallback: add figure without classification, if it isn't present
                                 fig = FigureElement(
                                     label=cluster.label,
                                     id=cluster.id,

docling/models/page_preprocessing_model.py

@@ -1,5 +1,6 @@
+from collections.abc import Iterable
 from pathlib import Path
-from typing import Iterable, Optional
+from typing import Optional
 
 from PIL import ImageDraw
 from pydantic import BaseModel

docling/models/picture_description_api_model.py

@@ -1,5 +1,6 @@
+from collections.abc import Iterable
 from pathlib import Path
-from typing import Iterable, Optional, Type, Union
+from typing import Optional, Type, Union
 
 from PIL import Image
 

docling/models/picture_description_base_model.py

@@ -1,12 +1,11 @@
-import logging
 from abc import abstractmethod
+from collections.abc import Iterable
 from pathlib import Path
-from typing import Any, Iterable, List, Optional, Type, Union
+from typing import List, Optional, Type, Union
 
 from docling_core.types.doc import (
     DoclingDocument,
     NodeItem,
-    PictureClassificationClass,
     PictureItem,
 )
 from docling_core.types.doc.document import (  # TODO: move import to docling_core.types.doc

docling/models/picture_description_vlm_model.py

@@ -1,5 +1,6 @@
+from collections.abc import Iterable
 from pathlib import Path
-from typing import Iterable, Optional, Type, Union
+from typing import Optional, Type, Union
 
 from PIL import Image
 
@@ -13,7 +14,6 @@ from docling.utils.accelerator_utils import decide_device
 
 
 class PictureDescriptionVlmModel(PictureDescriptionBaseModel):
-
     @classmethod
     def get_options_type(cls) -> Type[PictureDescriptionBaseOptions]:
         return PictureDescriptionVlmOptions
@@ -36,7 +36,6 @@ class PictureDescriptionVlmModel(PictureDescriptionBaseModel):
         self.options: PictureDescriptionVlmOptions
 
         if self.enabled:
-
             if artifacts_path is None:
                 artifacts_path = self.download_models(repo_id=self.options.repo_id)
             else:

docling/models/rapid_ocr_model.py

@@ -1,6 +1,7 @@
 import logging
+from collections.abc import Iterable
 from pathlib import Path
-from typing import Iterable, Optional, Type
+from typing import Optional, Type
 
 import numpy
 from docling_core.types.doc import BoundingBox, CoordOrigin
@@ -74,13 +75,11 @@ class RapidOcrModel(BaseOcrModel):
     def __call__(
         self, conv_res: ConversionResult, page_batch: Iterable[Page]
     ) -> Iterable[Page]:
-
         if not self.enabled:
             yield from page_batch
             return
 
         for page in page_batch:
-
             assert page._backend is not None
             if not page._backend.is_valid():
                 yield page

docling/models/readingorder_model.py

@@ -1,12 +1,7 @@
-import copy
-import random
 from pathlib import Path
 from typing import Dict, List
 
 from docling_core.types.doc import (
-    BoundingBox,
-    CoordOrigin,
-    DocItem,
     DocItemLabel,
     DoclingDocument,
     DocumentOrigin,
@@ -17,13 +12,10 @@ from docling_core.types.doc import (
     TableData,
 )
 from docling_core.types.doc.document import ContentLayer
-from docling_core.types.legacy_doc.base import Ref
-from docling_core.types.legacy_doc.document import BaseText
 from docling_ibm_models.reading_order.reading_order_rb import (
     PageElement as ReadingOrderPageElement,
+    ReadingOrderPredictor,
 )
-from docling_ibm_models.reading_order.reading_order_rb import ReadingOrderPredictor
-from PIL import ImageDraw
 from pydantic import BaseModel, ConfigDict
 
 from docling.datamodel.base_models import (
@@ -35,7 +27,6 @@ from docling.datamodel.base_models import (
     TextElement,
 )
 from docling.datamodel.document import ConversionResult
-from docling.datamodel.settings import settings
 from docling.utils.profiling import ProfilingScope, TimeRecorder
 
 
@@ -53,12 +44,10 @@ class ReadingOrderModel:
     def _assembled_to_readingorder_elements(
         self, conv_res: ConversionResult
     ) -> List[ReadingOrderPageElement]:
-
         elements: List[ReadingOrderPageElement] = []
         page_no_to_pages = {p.page_no: p for p in conv_res.pages}
 
         for element in conv_res.assembled.elements:
-
             page_height = page_no_to_pages[element.page_no].size.height  # type: ignore
             bbox = element.cluster.bbox.to_bottom_left_origin(page_height)
             text = element.text or ""
@@ -84,7 +73,6 @@ class ReadingOrderModel:
     def _add_child_elements(
         self, element: BasePageElement, doc_item: NodeItem, doc: DoclingDocument
     ):
-
         child: Cluster
         for child in element.cluster.children:
             c_label = child.label
@@ -110,7 +98,7 @@ class ReadingOrderModel:
             else:
                 doc.add_text(parent=doc_item, label=c_label, text=c_text, prov=c_prov)
 
-    def _readingorder_elements_to_docling_doc(
+    def _readingorder_elements_to_docling_doc(  # noqa: C901
         self,
         conv_res: ConversionResult,
         ro_elements: List[ReadingOrderPageElement],
@@ -118,7 +106,6 @@ class ReadingOrderModel:
         el_to_footnotes_mapping: Dict[int, List[int]],
         el_merges_mapping: Dict[int, List[int]],
     ) -> DoclingDocument:
-
         id_to_elem = {
             RefItem(cref=f"#/{elem.page_no}/{elem.cluster.id}").cref: elem
             for elem in conv_res.assembled.elements
@@ -192,7 +179,6 @@ class ReadingOrderModel:
 
                             code_item.footnotes.append(new_footnote_item.get_ref())
                 else:
-
                     new_item, current_list = self._handle_text_element(
                         element, out_doc, current_list, page_height
                     )
@@ -206,7 +192,6 @@ class ReadingOrderModel:
                             )
 
             elif isinstance(element, Table):
-
                 tbl_data = TableData(
                     num_rows=element.num_rows,
                     num_cols=element.num_cols,
@@ -342,12 +327,12 @@ class ReadingOrderModel:
         return new_item, current_list
 
     def _merge_elements(self, element, merged_elem, new_item, page_height):
-        assert isinstance(
-            merged_elem, type(element)
-        ), "Merged element must be of same type as element."
-        assert (
-            merged_elem.label == new_item.label
-        ), "Labels of merged elements must match."
+        assert isinstance(merged_elem, type(element)), (
+            "Merged element must be of same type as element."
+        )
+        assert merged_elem.label == new_item.label, (
+            "Labels of merged elements must match."
+        )
         prov = ProvenanceItem(
             page_no=element.page_no + 1,
             charspan=(

docling/models/table_structure_model.py

@@ -1,13 +1,13 @@
 import copy
 import warnings
+from collections.abc import Iterable
 from pathlib import Path
-from typing import Iterable, Optional, Union
+from typing import Optional
 
 import numpy
 from docling_core.types.doc import BoundingBox, DocItemLabel, TableCell
 from docling_core.types.doc.page import (
     BoundingRectangle,
-    SegmentedPdfPage,
     TextCellUnit,
 )
 from docling_ibm_models.tableformer.data_management.tf_predictor import TFPredictor
@@ -44,7 +44,6 @@ class TableStructureModel(BasePageModel):
 
         self.enabled = enabled
         if self.enabled:
-
             if artifacts_path is None:
                 artifacts_path = self.download_models() / self._model_path
             else:
@@ -175,7 +174,6 @@ class TableStructureModel(BasePageModel):
     def __call__(
         self, conv_res: ConversionResult, page_batch: Iterable[Page]
     ) -> Iterable[Page]:
-
         if not self.enabled:
             yield from page_batch
             return
@@ -186,7 +184,6 @@ class TableStructureModel(BasePageModel):
                 yield page
             else:
                 with TimeRecorder(conv_res, "table_structure"):
-
                     assert page.predictions.layout is not None
                     assert page.size is not None
 
@@ -260,7 +257,6 @@ class TableStructureModel(BasePageModel):
                             table_out = tf_output[0]
                             table_cells = []
                             for element in table_out["tf_responses"]:
-
                                 if not self.do_cell_matching:
                                     the_bbox = BoundingBox.model_validate(
                                         element["bbox"]

docling/models/tesseract_ocr_cli_model.py

@@ -3,9 +3,10 @@ import io
 import logging
 import os
 import tempfile
+from collections.abc import Iterable
 from pathlib import Path
 from subprocess import DEVNULL, PIPE, Popen
-from typing import Iterable, List, Optional, Tuple, Type
+from typing import List, Optional, Tuple, Type
 
 import pandas as pd
 from docling_core.types.doc import BoundingBox, CoordOrigin
@@ -63,8 +64,7 @@ class TesseractOcrCliModel(BaseOcrModel):
                 )
 
     def _get_name_and_version(self) -> Tuple[str, str]:
-
-        if self._name != None and self._version != None:
+        if self._name is not None and self._version is not None:
             return self._name, self._version  # type: ignore
 
         cmd = [self.options.tesseract_cmd, "--version"]
@@ -125,14 +125,16 @@ class TesseractOcrCliModel(BaseOcrModel):
         # _log.info(decoded_data)
 
         # Read the TSV file generated by Tesseract
-        df = pd.read_csv(io.StringIO(decoded_data), quoting=csv.QUOTE_NONE, sep="\t")
+        df_result = pd.read_csv(
+            io.StringIO(decoded_data), quoting=csv.QUOTE_NONE, sep="\t"
+        )
 
         # Display the dataframe (optional)
         # _log.info("df: ", df.head())
 
         # Filter rows that contain actual text (ignore header or empty rows)
-        df_filtered = df[
-            df["text"].notnull() & (df["text"].apply(str).str.strip() != "")
+        df_filtered = df_result[
+            df_result["text"].notna() & (df_result["text"].apply(str).str.strip() != "")
         ]
 
         return df_filtered
@@ -149,10 +151,10 @@ class TesseractOcrCliModel(BaseOcrModel):
         proc = Popen(cmd, stdout=PIPE, stderr=DEVNULL)
         output, _ = proc.communicate()
         decoded_data = output.decode("utf-8")
-        df = pd.read_csv(
+        df_detected = pd.read_csv(
             io.StringIO(decoded_data), sep=":", header=None, names=["key", "value"]
         )
-        scripts = df.loc[df["key"] == "Script"].value.tolist()
+        scripts = df_detected.loc[df_detected["key"] == "Script"].value.tolist()
         if len(scripts) == 0:
             _log.warning("Tesseract cannot detect the script of the page")
             return None
@@ -183,11 +185,11 @@ class TesseractOcrCliModel(BaseOcrModel):
         proc = Popen(cmd, stdout=PIPE, stderr=DEVNULL)
         output, _ = proc.communicate()
         decoded_data = output.decode("utf-8")
-        df = pd.read_csv(io.StringIO(decoded_data), header=None)
-        self._tesseract_languages = df[0].tolist()[1:]
+        df_list = pd.read_csv(io.StringIO(decoded_data), header=None)
+        self._tesseract_languages = df_list[0].tolist()[1:]
 
         # Decide the script prefix
-        if any([l.startswith("script/") for l in self._tesseract_languages]):
+        if any(lang.startswith("script/") for lang in self._tesseract_languages):
             script_prefix = "script/"
         else:
             script_prefix = ""
@@ -197,7 +199,6 @@ class TesseractOcrCliModel(BaseOcrModel):
     def __call__(
         self, conv_res: ConversionResult, page_batch: Iterable[Page]
     ) -> Iterable[Page]:
-
         if not self.enabled:
             yield from page_batch
             return
@@ -225,19 +226,19 @@ class TesseractOcrCliModel(BaseOcrModel):
                                 fname = image_file.name
                                 high_res_image.save(image_file)
 
-                            df = self._run_tesseract(fname)
+                            df_result = self._run_tesseract(fname)
                         finally:
                             if os.path.exists(fname):
                                 os.remove(fname)
 
-                        # _log.info(df)
+                        # _log.info(df_result)
 
                         # Print relevant columns (bounding box and text)
-                        for ix, row in df.iterrows():
+                        for ix, row in df_result.iterrows():
                             text = row["text"]
                             conf = row["conf"]
 
-                            l = float(row["left"])
+                            l = float(row["left"])  # noqa: E741
                             b = float(row["top"])
                             w = float(row["width"])
                             h = float(row["height"])

docling/models/tesseract_ocr_model.py

@@ -1,6 +1,7 @@
 import logging
+from collections.abc import Iterable
 from pathlib import Path
-from typing import Iterable, Optional, Type
+from typing import Optional, Type
 
 from docling_core.types.doc import BoundingBox, CoordOrigin
 from docling_core.types.doc.page import BoundingRectangle, TextCell
@@ -37,9 +38,6 @@ class TesseractOcrModel(BaseOcrModel):
         self.options: TesseractOcrOptions
 
         self.scale = 3  # multiplier for 72 dpi == 216 dpi.
-        self.reader = None
-        self.osd_reader = None
-        self.script_readers: dict[str, tesserocr.PyTessBaseAPI] = {}
 
         if self.enabled:
             install_errmsg = (
@@ -64,7 +62,7 @@ class TesseractOcrModel(BaseOcrModel):
                 raise ImportError(install_errmsg)
             try:
                 tesseract_version = tesserocr.tesseract_version()
-            except:
+            except Exception:
                 raise ImportError(install_errmsg)
 
             _, self._tesserocr_languages = tesserocr.get_languages()
@@ -75,7 +73,7 @@ class TesseractOcrModel(BaseOcrModel):
             _log.debug("Initializing TesserOCR: %s", tesseract_version)
             lang = "+".join(self.options.lang)
 
-            if any([l.startswith("script/") for l in self._tesserocr_languages]):
+            if any(lang.startswith("script/") for lang in self._tesserocr_languages):
                 self.script_prefix = "script/"
             else:
                 self.script_prefix = ""
@@ -86,6 +84,10 @@ class TesseractOcrModel(BaseOcrModel):
                 "oem": tesserocr.OEM.DEFAULT,
             }
 
+            self.reader = None
+            self.osd_reader = None
+            self.script_readers: dict[str, tesserocr.PyTessBaseAPI] = {}
+
             if self.options.path is not None:
                 tesserocr_kwargs["path"] = self.options.path
 

docling/pipeline/base_pipeline.py

@@ -3,9 +3,10 @@ import logging
 import time
 import traceback
 from abc import ABC, abstractmethod
-from typing import Any, Callable, Iterable, List
+from collections.abc import Iterable
+from typing import Any, Callable, List
 
-from docling_core.types.doc import DoclingDocument, NodeItem
+from docling_core.types.doc import NodeItem
 
 from docling.backend.abstract_backend import AbstractDocumentBackend
 from docling.backend.pdf_backend import PdfDocumentBackend
@@ -64,7 +65,6 @@ class BasePipeline(ABC):
         return conv_res
 
     def _enrich_document(self, conv_res: ConversionResult) -> ConversionResult:
-
         def _prepare_elements(
             conv_res: ConversionResult, model: GenericEnrichmentModel[Any]
         ) -> Iterable[NodeItem]:
@@ -113,7 +113,6 @@ class BasePipeline(ABC):
 
 
 class PaginatedPipeline(BasePipeline):  # TODO this is a bad name.
-
     def __init__(self, pipeline_options: PipelineOptions):
         super().__init__(pipeline_options)
         self.keep_backend = False
@@ -127,7 +126,6 @@ class PaginatedPipeline(BasePipeline):  # TODO this is a bad name.
         yield from page_batch
 
     def _build_document(self, conv_res: ConversionResult) -> ConversionResult:
-
         if not isinstance(conv_res.input._backend, PdfDocumentBackend):
             raise RuntimeError(
                 f"The selected backend {type(conv_res.input._backend).__name__} for {conv_res.input.file} is not a PDF backend. "
@@ -139,8 +137,7 @@ class PaginatedPipeline(BasePipeline):  # TODO this is a bad name.
 
         total_elapsed_time = 0.0
         with TimeRecorder(conv_res, "doc_build", scope=ProfilingScope.DOCUMENT):
-
-            for i in range(0, conv_res.input.page_count):
+            for i in range(conv_res.input.page_count):
                 start_page, end_page = conv_res.input.limits.page_range
                 if (start_page - 1) <= i <= (end_page - 1):
                     conv_res.pages.append(Page(page_no=i))
@@ -161,7 +158,6 @@ class PaginatedPipeline(BasePipeline):  # TODO this is a bad name.
                     pipeline_pages = self._apply_on_pages(conv_res, init_pages)
 
                     for p in pipeline_pages:  # Must exhaust!
-
                         # Cleanup cached images
                         if not self.keep_images:
                             p._image_cache = {}

docling/pipeline/simple_pipeline.py

@@ -24,7 +24,6 @@ class SimplePipeline(BasePipeline):
         super().__init__(pipeline_options)
 
     def _build_document(self, conv_res: ConversionResult) -> ConversionResult:
-
         if not isinstance(conv_res.input._backend, DeclarativeDocumentBackend):
             raise RuntimeError(
                 f"The selected backend {type(conv_res.input._backend).__name__} for {conv_res.input.file} is not a declarative backend. "

docling/pipeline/standard_pdf_pipeline.py

@@ -1,5 +1,4 @@
 import logging
-import sys
 import warnings
 from pathlib import Path
 from typing import Optional, cast