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

docling/backend/xml/jats_backend.py

@@ -102,13 +102,13 @@ class JatsDocumentBackend(DeclarativeDocumentBackend):
 
             doc_info: etree.DocInfo = self.tree.docinfo
             if doc_info.system_url and any(
-                [kwd in doc_info.system_url for kwd in JATS_DTD_URL]
+                kwd in doc_info.system_url for kwd in JATS_DTD_URL
             ):
                 self.valid = True
                 return
             for ent in doc_info.internalDTD.iterentities():
                 if ent.system_url and any(
-                    [kwd in ent.system_url for kwd in JATS_DTD_URL]
+                    kwd in ent.system_url for kwd in JATS_DTD_URL
                 ):
                     self.valid = True
                     return
@@ -232,10 +232,9 @@ class JatsDocumentBackend(DeclarativeDocumentBackend):
                 # TODO: once superscript is supported, add label with formatting
                 aff = aff.removeprefix(f"{label[0].text}, ")
             affiliation_names.append(aff)
-        affiliation_ids_names = {
-            id: name
-            for id, name in zip(meta.xpath(".//aff[@id]/@id"), affiliation_names)
-        }
+        affiliation_ids_names = dict(
+            zip(meta.xpath(".//aff[@id]/@id"), affiliation_names)
+        )
 
         # Get author names and affiliation names
         for author_node in meta.xpath(
@@ -300,7 +299,6 @@ class JatsDocumentBackend(DeclarativeDocumentBackend):
     def _add_abstract(
         self, doc: DoclingDocument, xml_components: XMLComponents
     ) -> None:
-
         for abstract in xml_components["abstract"]:
             text: str = abstract["content"]
             title: str = abstract["label"] or DEFAULT_HEADER_ABSTRACT
@@ -349,7 +347,7 @@ class JatsDocumentBackend(DeclarativeDocumentBackend):
 
         return
 
-    def _parse_element_citation(self, node: etree._Element) -> str:
+    def _parse_element_citation(self, node: etree._Element) -> str:  # noqa: C901
         citation: Citation = {
             "author_names": "",
             "title": "",
@@ -440,7 +438,7 @@ class JatsDocumentBackend(DeclarativeDocumentBackend):
             citation["page"] = node.xpath("fpage")[0].text.replace("\n", " ").strip()
             if len(node.xpath("lpage")) > 0:
                 citation["page"] += (
-                    "–" + node.xpath("lpage")[0].text.replace("\n", " ").strip()
+                    "–" + node.xpath("lpage")[0].text.replace("\n", " ").strip()  # noqa: RUF001
                 )
 
         # Flatten the citation to string
@@ -595,9 +593,8 @@ class JatsDocumentBackend(DeclarativeDocumentBackend):
 
         try:
             self._add_table(doc, parent, table)
-        except Exception as e:
-            _log.warning(f"Skipping unsupported table in {str(self.file)}")
-            pass
+        except Exception:
+            _log.warning(f"Skipping unsupported table in {self.file!s}")
 
         return
 
@@ -609,7 +606,7 @@ class JatsDocumentBackend(DeclarativeDocumentBackend):
         )
         return
 
-    def _walk_linear(
+    def _walk_linear(  # noqa: C901
         self, doc: DoclingDocument, parent: NodeItem, node: etree._Element
     ) -> str:
         skip_tags = ["term"]

docling/backend/xml/uspto_backend.py

@@ -122,7 +122,6 @@ class PatentUsptoDocumentBackend(DeclarativeDocumentBackend):
 
     @override
     def convert(self) -> DoclingDocument:
-
         if self.parser is not None:
             doc = self.parser.parse(self.patent_content)
             if doc is None:
@@ -163,7 +162,6 @@ class PatentUspto(ABC):
         Returns:
             The patent parsed as a docling document.
         """
-        pass
 
 
 class PatentUsptoIce(PatentUspto):
@@ -265,7 +263,7 @@ class PatentUsptoIce(PatentUspto):
             self.style_html = HtmlEntity()
 
         @override
-        def startElement(self, tag, attributes):  # noqa: N802
+        def startElement(self, tag, attributes):
             """Signal the start of an element.
 
             Args:
@@ -281,7 +279,7 @@ class PatentUsptoIce(PatentUspto):
             self._start_registered_elements(tag, attributes)
 
         @override
-        def skippedEntity(self, name):  # noqa: N802
+        def skippedEntity(self, name):
             """Receive notification of a skipped entity.
 
             HTML entities will be skipped by the parser. This method will unescape them
@@ -315,7 +313,7 @@ class PatentUsptoIce(PatentUspto):
                         self.text += unescaped
 
         @override
-        def endElement(self, tag):  # noqa: N802
+        def endElement(self, tag):
             """Signal the end of an element.
 
             Args:
@@ -603,7 +601,7 @@ class PatentUsptoGrantV2(PatentUspto):
             self.style_html = HtmlEntity()
 
         @override
-        def startElement(self, tag, attributes):  # noqa: N802
+        def startElement(self, tag, attributes):
             """Signal the start of an element.
 
             Args:
@@ -616,7 +614,7 @@ class PatentUsptoGrantV2(PatentUspto):
             self._start_registered_elements(tag, attributes)
 
         @override
-        def skippedEntity(self, name):  # noqa: N802
+        def skippedEntity(self, name):
             """Receive notification of a skipped entity.
 
             HTML entities will be skipped by the parser. This method will unescape them
@@ -650,7 +648,7 @@ class PatentUsptoGrantV2(PatentUspto):
                         self.text += unescaped
 
         @override
-        def endElement(self, tag):  # noqa: N802
+        def endElement(self, tag):
             """Signal the end of an element.
 
             Args:
@@ -691,7 +689,7 @@ class PatentUsptoGrantV2(PatentUspto):
             if tag in [member.value for member in self.Element]:
                 if (
                     tag == self.Element.HEADING.value
-                    and not self.Element.SDOCL.value in self.property
+                    and self.Element.SDOCL.value not in self.property
                 ):
                     level_attr: str = attributes.get("LVL", "")
                     new_level: int = int(level_attr) if level_attr.isnumeric() else 1
@@ -743,7 +741,7 @@ class PatentUsptoGrantV2(PatentUspto):
                 # headers except claims statement
                 elif (
                     self.Element.HEADING.value in self.property
-                    and not self.Element.SDOCL.value in self.property
+                    and self.Element.SDOCL.value not in self.property
                     and text.strip()
                 ):
                     self.parents[self.level + 1] = self.doc.add_heading(
@@ -1164,7 +1162,7 @@ class PatentUsptoAppV1(PatentUspto):
             self.style_html = HtmlEntity()
 
         @override
-        def startElement(self, tag, attributes):  # noqa: N802
+        def startElement(self, tag, attributes):
             """Signal the start of an element.
 
             Args:
@@ -1177,7 +1175,7 @@ class PatentUsptoAppV1(PatentUspto):
             self._start_registered_elements(tag, attributes)
 
         @override
-        def skippedEntity(self, name):  # noqa: N802
+        def skippedEntity(self, name):
             """Receive notification of a skipped entity.
 
             HTML entities will be skipped by the parser. This method will unescape them
@@ -1211,7 +1209,7 @@ class PatentUsptoAppV1(PatentUspto):
                         self.text += unescaped
 
         @override
-        def endElement(self, tag):  # noqa: N802
+        def endElement(self, tag):
             """Signal the end of an element.
 
             Args:
@@ -1474,9 +1472,7 @@ class XmlTable:
                 if cw == 0:
                     offset_w0.append(col["offset"][ic])
 
-            min_colinfo["offset"] = sorted(
-                list(set(col["offset"] + min_colinfo["offset"]))
-            )
+            min_colinfo["offset"] = sorted(set(col["offset"] + min_colinfo["offset"]))
 
         # add back the 0 width cols to offset list
         offset_w0 = list(set(offset_w0))
@@ -1527,7 +1523,7 @@ class XmlTable:
 
         return ncols_max
 
-    def _parse_table(self, table: Tag) -> TableData:
+    def _parse_table(self, table: Tag) -> TableData:  # noqa: C901
         """Parse the content of a table tag.
 
         Args:
@@ -1722,7 +1718,7 @@ class HtmlEntity:
                 "0": "⁰",
                 "+": "⁺",
                 "-": "⁻",
-                "−": "⁻",
+                "−": "⁻",  # noqa: RUF001
                 "=": "⁼",
                 "(": "⁽",
                 ")": "⁾",
@@ -1746,7 +1742,7 @@ class HtmlEntity:
                 "0": "₀",
                 "+": "₊",
                 "-": "₋",
-                "−": "₋",
+                "−": "₋",  # noqa: RUF001
                 "=": "₌",
                 "(": "₍",
                 ")": "₎",

docling/cli/main.py

@@ -6,14 +6,16 @@ import sys
 import tempfile
 import time
 import warnings
+from collections.abc import Iterable
 from pathlib import Path
-from typing import Annotated, Dict, Iterable, List, Optional, Type
+from typing import Annotated, Dict, List, Optional, Type
 
 import rich.table
 import typer
 from docling_core.types.doc import ImageRefMode
 from docling_core.utils.file import resolve_source_to_path
 from pydantic import TypeAdapter
+from rich.console import Console
 
 from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
 from docling.backend.docling_parse_v2_backend import DoclingParseV2DocumentBackend
@@ -53,7 +55,6 @@ warnings.filterwarnings(action="ignore", category=UserWarning, module="pydantic|
 warnings.filterwarnings(action="ignore", category=FutureWarning, module="easyocr")
 
 _log = logging.getLogger(__name__)
-from rich.console import Console
 
 console = Console()
 err_console = Console(stderr=True)
@@ -160,7 +161,6 @@ def export_documents(
     export_doctags: bool,
     image_export_mode: ImageRefMode,
 ):
-
     success_count = 0
     failure_count = 0
 
@@ -233,7 +233,7 @@ def _split_list(raw: Optional[str]) -> Optional[List[str]]:
 
 
 @app.command(no_args_is_help=True)
-def convert(
+def convert(  # noqa: C901
     input_sources: Annotated[
         List[str],
         typer.Argument(
@@ -289,7 +289,7 @@ def convert(
             ...,
             help=(
                 f"The OCR engine to use. When --allow-external-plugins is *not* set, the available values are: "
-                f"{', '.join((o.value for o in ocr_engines_enum_internal))}. "
+                f"{', '.join(o.value for o in ocr_engines_enum_internal)}. "
                 f"Use the option --show-external-plugins to see the options allowed with external plugins."
             ),
         ),
@@ -421,7 +421,7 @@ def convert(
         logging.basicConfig(level=logging.WARNING)
     elif verbose == 1:
         logging.basicConfig(level=logging.INFO)
-    elif verbose == 2:
+    else:
         logging.basicConfig(level=logging.DEBUG)
 
     settings.debug.visualize_cells = debug_visualize_cells
@@ -430,7 +430,7 @@ def convert(
     settings.debug.visualize_ocr = debug_visualize_ocr
 
     if from_formats is None:
-        from_formats = [e for e in InputFormat]
+        from_formats = list(InputFormat)
 
     parsed_headers: Optional[Dict[str, str]] = None
     if headers is not None:

docling/cli/models.py

@@ -62,7 +62,7 @@ def download(
     models: Annotated[
         Optional[list[_AvailableModels]],
         typer.Argument(
-            help=f"Models to download (default behavior: a predefined set of models will be downloaded).",
+            help="Models to download (default behavior: a predefined set of models will be downloaded).",
         ),
     ] = None,
     all: Annotated[
@@ -89,14 +89,13 @@ def download(
             "Cannot simultaneously set 'all' parameter and specify models to download."
         )
     if not quiet:
-        FORMAT = "%(message)s"
         logging.basicConfig(
             level=logging.INFO,
             format="[blue]%(message)s[/blue]",
             datefmt="[%X]",
             handlers=[RichHandler(show_level=False, show_time=False, markup=True)],
         )
-    to_download = models or ([m for m in _AvailableModels] if all else _default_models)
+    to_download = models or (list(_AvailableModels) if all else _default_models)
     output_dir = download_models(
         output_dir=output_dir,
         force=force,

docling/datamodel/base_models.py

@@ -10,7 +10,9 @@ from docling_core.types.doc import (
     TableCell,
 )
 from docling_core.types.doc.page import SegmentedPdfPage, TextCell
-from docling_core.types.io import (  # DO ΝΟΤ REMOVE; explicitly exposed from this location
+
+# DO NOT REMOVE; explicitly exposed from this location
+from docling_core.types.io import (
     DocumentStream,
 )
 from PIL.Image import Image
@@ -233,9 +235,9 @@ class Page(BaseModel):
         None  # Internal PDF backend. By default it is cleared during assembling.
     )
     _default_image_scale: float = 1.0  # Default image scale for external usage.
-    _image_cache: Dict[float, Image] = (
-        {}
-    )  # Cache of images in different scales. By default it is cleared during assembling.
+    _image_cache: Dict[
+        float, Image
+    ] = {}  # Cache of images in different scales. By default it is cleared during assembling.
 
     def get_image(
         self, scale: float = 1.0, cropbox: Optional[BoundingBox] = None
@@ -243,7 +245,7 @@ class Page(BaseModel):
         if self._backend is None:
             return self._image_cache.get(scale, None)
 
-        if not scale in self._image_cache:
+        if scale not in self._image_cache:
             if cropbox is None:
                 self._image_cache[scale] = self._backend.get_page_image(scale=scale)
             else:

docling/datamodel/document.py

@@ -1,13 +1,13 @@
 import csv
 import logging
 import re
+from collections.abc import Iterable
 from enum import Enum
 from io import BytesIO
 from pathlib import Path, PurePath
 from typing import (
     TYPE_CHECKING,
     Dict,
-    Iterable,
     List,
     Literal,
     Optional,
@@ -17,6 +17,8 @@ from typing import (
 )
 
 import filetype
+
+# DO NOT REMOVE; explicitly exposed from this location
 from docling_core.types.doc import (
     DocItem,
     DocItemLabel,
@@ -35,14 +37,14 @@ from docling_core.types.legacy_doc.base import (
     PageReference,
     Prov,
     Ref,
+    Table as DsSchemaTable,
+    TableCell,
 )
-from docling_core.types.legacy_doc.base import Table as DsSchemaTable
-from docling_core.types.legacy_doc.base import TableCell
 from docling_core.types.legacy_doc.document import (
     CCSDocumentDescription as DsDocumentDescription,
+    CCSFileInfoObject as DsFileInfoObject,
+    ExportedCCSDocument as DsDocument,
 )
-from docling_core.types.legacy_doc.document import CCSFileInfoObject as DsFileInfoObject
-from docling_core.types.legacy_doc.document import ExportedCCSDocument as DsDocument
 from docling_core.utils.file import resolve_source_to_stream
 from docling_core.utils.legacy import docling_document_to_legacy
 from pydantic import BaseModel
@@ -65,7 +67,7 @@ from docling.datamodel.base_models import (
 )
 from docling.datamodel.settings import DocumentLimits
 from docling.utils.profiling import ProfilingItem
-from docling.utils.utils import create_file_hash, create_hash
+from docling.utils.utils import create_file_hash
 
 if TYPE_CHECKING:
     from docling.document_converter import FormatOption
@@ -134,9 +136,9 @@ class InputDocument(BaseModel):
                     self._init_doc(backend, path_or_stream)
 
             elif isinstance(path_or_stream, BytesIO):
-                assert (
-                    filename is not None
-                ), "Can't construct InputDocument from stream without providing filename arg."
+                assert filename is not None, (
+                    "Can't construct InputDocument from stream without providing filename arg."
+                )
                 self.file = PurePath(filename)
                 self.filesize = path_or_stream.getbuffer().nbytes
 
@@ -228,7 +230,6 @@ class _DummyBackend(AbstractDocumentBackend):
 
 
 class _DocumentConversionInput(BaseModel):
-
     path_or_stream_iterator: Iterable[Union[Path, str, DocumentStream]]
     headers: Optional[Dict[str, str]] = None
     limits: Optional[DocumentLimits] = DocumentLimits()

docling/datamodel/pipeline_options.py

@@ -380,7 +380,6 @@ class PaginatedPipelineOptions(PipelineOptions):
 
 
 class VlmPipelineOptions(PaginatedPipelineOptions):
-
     generate_page_images: bool = True
     force_backend_text: bool = (
         False  # (To be used with vlms, or other generative models)

docling/document_converter.py

@@ -1,11 +1,11 @@
 import hashlib
 import logging
-import math
 import sys
 import time
+from collections.abc import Iterable, Iterator
 from functools import partial
 from pathlib import Path
-from typing import Dict, Iterable, Iterator, List, Optional, Tuple, Type, Union
+from typing import Dict, List, Optional, Tuple, Type, Union
 
 from pydantic import BaseModel, ConfigDict, model_validator, validate_call
 
@@ -172,7 +172,7 @@ class DocumentConverter:
         format_options: Optional[Dict[InputFormat, FormatOption]] = None,
     ):
         self.allowed_formats = (
-            allowed_formats if allowed_formats is not None else [e for e in InputFormat]
+            allowed_formats if allowed_formats is not None else list(InputFormat)
         )
         self.format_to_options = {
             format: (
@@ -254,7 +254,7 @@ class DocumentConverter:
 
         if not had_result and raises_on_error:
             raise ConversionError(
-                f"Conversion failed because the provided file has no recognizable format or it wasn't in the list of allowed formats."
+                "Conversion failed because the provided file has no recognizable format or it wasn't in the list of allowed formats."
             )
 
     def _convert(
@@ -266,7 +266,7 @@ class DocumentConverter:
             conv_input.docs(self.format_to_options),
             settings.perf.doc_batch_size,  # pass format_options
         ):
-            _log.info(f"Going to convert document batch...")
+            _log.info("Going to convert document batch...")
 
             # parallel processing only within input_batch
             # with ThreadPoolExecutor(

docling/models/api_vlm_model.py

@@ -1,4 +1,4 @@
-from typing import Iterable
+from collections.abc import Iterable
 
 from docling.datamodel.base_models import Page, VlmPrediction
 from docling.datamodel.document import ConversionResult
@@ -10,7 +10,6 @@ from docling.utils.profiling import TimeRecorder
 
 
 class ApiVlmModel(BasePageModel):
-
     def __init__(
         self,
         enabled: bool,

docling/models/base_model.py

@@ -1,5 +1,6 @@
 from abc import ABC, abstractmethod
-from typing import Any, Generic, Iterable, Optional, Protocol, Type
+from collections.abc import Iterable
+from typing import Generic, Optional, Protocol, Type
 
 from docling_core.types.doc import BoundingBox, DocItem, DoclingDocument, NodeItem
 from typing_extensions import TypeVar
@@ -29,7 +30,6 @@ EnrichElementT = TypeVar("EnrichElementT", default=NodeItem)
 
 
 class GenericEnrichmentModel(ABC, Generic[EnrichElementT]):
-
     elements_batch_size: int = settings.perf.elements_batch_size
 
     @abstractmethod
@@ -50,7 +50,6 @@ class GenericEnrichmentModel(ABC, Generic[EnrichElementT]):
 
 
 class BaseEnrichmentModel(GenericEnrichmentModel[NodeItem]):
-
     def prepare_element(
         self, conv_res: ConversionResult, element: NodeItem
     ) -> Optional[NodeItem]:
@@ -62,7 +61,6 @@ class BaseEnrichmentModel(GenericEnrichmentModel[NodeItem]):
 class BaseItemAndImageEnrichmentModel(
     GenericEnrichmentModel[ItemAndImageEnrichmentElement]
 ):
-
     images_scale: float
     expansion_factor: float = 0.0
 

docling/models/base_ocr_model.py

@@ -1,12 +1,12 @@
 import copy
 import logging
 from abc import abstractmethod
+from collections.abc import Iterable
 from pathlib import Path
-from typing import Iterable, List, Optional, Type
+from typing import List, Optional, Type
 
 import numpy as np
 from docling_core.types.doc import BoundingBox, CoordOrigin
-from docling_core.types.doc.page import BoundingRectangle, PdfTextCell, TextCell
 from PIL import Image, ImageDraw
 from rtree import index
 from scipy.ndimage import binary_dilation, find_objects, label

docling/models/code_formula_model.py

@@ -1,7 +1,8 @@
 import re
 from collections import Counter
+from collections.abc import Iterable
 from pathlib import Path
-from typing import Iterable, List, Literal, Optional, Tuple, Union
+from typing import List, Literal, Optional, Tuple, Union
 
 import numpy as np
 from docling_core.types.doc import (

docling/models/document_picture_classifier.py

@@ -1,5 +1,6 @@
+from collections.abc import Iterable
 from pathlib import Path
-from typing import Iterable, List, Literal, Optional, Tuple, Union
+from typing import List, Literal, Optional, Union
 
 import numpy as np
 from docling_core.types.doc import (

docling/models/easyocr_model.py

@@ -1,8 +1,9 @@
 import logging
 import warnings
 import zipfile
+from collections.abc import Iterable
 from pathlib import Path
-from typing import Iterable, List, Optional, Type
+from typing import List, Optional, Type
 
 import numpy
 from docling_core.types.doc import BoundingBox, CoordOrigin
@@ -58,12 +59,10 @@ class EasyOcrModel(BaseOcrModel):
                 device = decide_device(accelerator_options.device)
                 # Enable easyocr GPU if running on CUDA, MPS
                 use_gpu = any(
-                    [
-                        device.startswith(x)
-                        for x in [
-                            AcceleratorDevice.CUDA.value,
-                            AcceleratorDevice.MPS.value,
-                        ]
+                    device.startswith(x)
+                    for x in [
+                        AcceleratorDevice.CUDA.value,
+                        AcceleratorDevice.MPS.value,
                     ]
                 )
             else:
@@ -98,8 +97,10 @@ class EasyOcrModel(BaseOcrModel):
         progress: bool = False,
     ) -> Path:
         # Models are located in https://github.com/JaidedAI/EasyOCR/blob/master/easyocr/config.py
-        from easyocr.config import detection_models as det_models_dict
-        from easyocr.config import recognition_models as rec_models_dict
+        from easyocr.config import (
+            detection_models as det_models_dict,
+            recognition_models as rec_models_dict,
+        )
 
         if local_dir is None:
             local_dir = settings.cache_dir / "models" / EasyOcrModel._model_repo_folder
@@ -126,13 +127,11 @@ class EasyOcrModel(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/factories/__init__.py

@@ -9,7 +9,7 @@ from docling.models.factories.picture_description_factory import (
 logger = logging.getLogger(__name__)
 
 
-@lru_cache()
+@lru_cache
 def get_ocr_factory(allow_external_plugins: bool = False) -> OcrFactory:
     factory = OcrFactory()
     factory.load_from_plugins(allow_external_plugins=allow_external_plugins)
@@ -17,7 +17,7 @@ def get_ocr_factory(allow_external_plugins: bool = False) -> OcrFactory:
     return factory
 
 
-@lru_cache()
+@lru_cache
 def get_picture_description_factory(
     allow_external_plugins: bool = False,
 ) -> PictureDescriptionFactory:

docling/models/factories/base_factory.py

@@ -33,7 +33,7 @@ class BaseFactory(Generic[A], metaclass=ABCMeta):
 
     @property
     def registered_kind(self) -> list[str]:
-        return list(opt.kind for opt in self._classes.keys())
+        return [opt.kind for opt in self._classes.keys()]
 
     def get_enum(self) -> enum.Enum:
         return enum.Enum(