runs 1 on linter issues

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

docling/backend/md_backend.py

@@ -168,7 +168,7 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
             )
         self.inline_texts = []
 
-    def _iterate_elements(
+    def _iterate_elements(  # noqa: C901
         self,
         element: marko.element.Element,
         depth: int,

docling/backend/msexcel_backend.py

@@ -493,7 +493,7 @@ class MsExcelDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentBacken
                             ),
                         ),
                     )
-                except:
+                except Exception:
                     _log.error("could not extract the image from excel sheets")
 
         return doc

docling/backend/msword_backend.py

@@ -418,7 +418,7 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
             else prev_parent
         )
 
-    def _handle_text_elements(
+    def _handle_text_elements(  # noqa: C901
         self,
         element: BaseOxmlElement,
         docx_obj: DocxDocument,

docling/backend/xml/jats_backend.py

@@ -606,7 +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/cli/main.py

@@ -15,6 +15,7 @@ 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
@@ -54,7 +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)
@@ -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(

docling/datamodel/base_models.py

@@ -12,7 +12,7 @@ from docling_core.types.doc import (
 from docling_core.types.doc.page import SegmentedPdfPage, TextCell
 
 # DO NOT REMOVE; explicitly exposed from this location
-from docling_core.types.io import (  # noqa: F401
+from docling_core.types.io import (
     DocumentStream,
 )
 from PIL.Image import Image

docling/datamodel/document.py

@@ -19,7 +19,7 @@ from typing import (
 import filetype
 
 # DO NOT REMOVE; explicitly exposed from this location
-from docling_core.types.doc import (  # noqa: F401
+from docling_core.types.doc import (
     DocItem,
     DocItemLabel,
     DoclingDocument,
@@ -28,8 +28,8 @@ from docling_core.types.doc import (  # noqa: F401
     TableItem,
     TextItem,
 )
-from docling_core.types.doc.document import ListItem  # noqa: F401
-from docling_core.types.legacy_doc.base import (  # noqa: F401
+from docling_core.types.doc.document import ListItem
+from docling_core.types.legacy_doc.base import (
     BaseText,
     Figure,
     GlmTableCell,
@@ -37,14 +37,14 @@ from docling_core.types.legacy_doc.base import (  # noqa: F401
     PageReference,
     Prov,
     Ref,
+    Table as DsSchemaTable,
+    TableCell,
 )
-from docling_core.types.legacy_doc.base import Table as DsSchemaTable  # noqa: F401
-from docling_core.types.legacy_doc.base import TableCell  # noqa: F401
-from docling_core.types.legacy_doc.document import (  # noqa: F401
+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  # noqa: F401
-from docling_core.types.legacy_doc.document import ExportedCCSDocument as DsDocument  # noqa: F401
 from docling_core.utils.file import resolve_source_to_stream
 from docling_core.utils.legacy import docling_document_to_legacy
 from pydantic import BaseModel

docling/models/readingorder_model.py

@@ -98,7 +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],

docling/models/tesseract_ocr_model.py

@@ -65,7 +65,7 @@ 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()

tests/test_document_picture_classifier.py

@@ -47,7 +47,7 @@ def test_picture_classifier():
 
     res = results[0]
     assert len(res.annotations) == 1
-    assert type(res.annotations[0]) == PictureClassificationData
+    assert isinstance(res.annotations[0], PictureClassificationData)
     classification_data = res.annotations[0]
     assert classification_data.provenance == "DocumentPictureClassifier"
     assert len(classification_data.predicted_classes) == 16, (
@@ -63,7 +63,7 @@ def test_picture_classifier():
 
     res = results[1]
     assert len(res.annotations) == 1
-    assert type(res.annotations[0]) == PictureClassificationData
+    assert isinstance(res.annotations[0], PictureClassificationData)
     classification_data = res.annotations[0]
     assert classification_data.provenance == "DocumentPictureClassifier"
     assert len(classification_data.predicted_classes) == 16, (