Fixed the rest of the errors that would only concern 1 - 3 files

Signed-off-by: Florian <[email protected]>

Author: schwarbf

docling_core/transforms/chunker/code_chunking/code_chunk.py

@@ -3,7 +3,7 @@
 from __future__ import annotations
 
 from enum import Enum
-from typing import Literal, Optional
+from typing import Literal
 
 from pydantic import Field
 
@@ -28,12 +28,12 @@ class CodeDocMeta(DocMeta):
         default="docling_core.transforms.chunker.CodeDocMeta",
         alias=_KEY_SCHEMA_NAME,
     )
-    part_name: Optional[str] = Field(default=None)
-    docstring: Optional[str] = Field(default=None)
-    sha256: Optional[int] = Field(default=None)
-    start_line: Optional[int] = Field(default=None)
-    end_line: Optional[int] = Field(default=None)
-    end_line_signature: Optional[int] = Field(default=None)
+    part_name: str | None = Field(default=None)
+    docstring: str | None = Field(default=None)
+    sha256: int | None = Field(default=None)
+    start_line: int | None = Field(default=None)
+    end_line: int | None = Field(default=None)
+    end_line_signature: int | None = Field(default=None)
     chunk_type: CodeChunkType = Field(default=CodeChunkType.CODE_BLOCK)
 
 

docling_core/transforms/chunker/hierarchical_chunker.py

@@ -3,7 +3,7 @@
 from __future__ import annotations
 
 import logging
-from typing import Any, Iterator, Optional
+from typing import Any, Iterator
 
 from pydantic import ConfigDict, Field
 from typing_extensions import Annotated, override
@@ -125,7 +125,7 @@ class HierarchicalChunker(BaseChunker):
     model_config = ConfigDict(arbitrary_types_allowed=True)
 
     serializer_provider: BaseSerializerProvider = ChunkingSerializerProvider()
-    code_chunking_strategy: Optional[BaseCodeChunkingStrategy] = Field(default=None)
+    code_chunking_strategy: BaseCodeChunkingStrategy | None = Field(default=None)
 
     # deprecated:
     merge_list_items: Annotated[bool, Field(deprecated=True)] = True

docling_core/transforms/serializer/markdown.py

@@ -175,9 +175,9 @@ def serialize(
 
                 # wrap with outer marker (if applicable)
                 if params.ensure_valid_list_item_marker and not case_already_valid:
-                    assert item.parent and isinstance(
-                        (list_group := item.parent.resolve(doc)), ListGroup
-                    )
+                    assert item.parent
+                    list_group = item.parent.resolve(doc)
+                    assert isinstance(list_group, ListGroup)
                     if list_group.first_item_is_enumerated(doc) and (
                         params.orig_list_item_marker_mode != OrigListItemMarkerMode.AUTO
                         or not item.marker

docling_core/types/doc/page.py

@@ -1253,8 +1253,7 @@ def iterate_pages(
         Returns:
             Iterator of (page number, page) tuples
         """
-        for page_no, page in self.pages.items():
-            yield (page_no, page)
+        yield from self.pages.items()
 
     def export_to_dict(
         self,

docling_core/types/legacy_doc/base.py

@@ -246,8 +246,8 @@ def export_to_html(self) -> str:
             for j in range(ncols):
                 cell: TableCell = self.data[i][j]
 
-                rowspan, rowstart, rowend = self._get_tablecell_span(cell, 0)
-                colspan, colstart, colend = self._get_tablecell_span(cell, 1)
+                rowspan, rowstart, _ = self._get_tablecell_span(cell, 0)
+                colspan, colstart, _ = self._get_tablecell_span(cell, 1)
 
                 if rowstart is not None and rowstart != i:
                     continue

test/test_base.py

@@ -214,7 +214,7 @@ def test_collection_document_info():
     CCSDocumentDescription(**desc_dict)
 
     desc_dict["collection"]["type"] = "Record"
-    with pytest.raises(ValidationError, match="collection.type"):
+    with pytest.raises(ValidationError, match="collection\\.type"):
         CCSDocumentDescription(**desc_dict)
 
 
@@ -251,11 +251,11 @@ def test_collection_record_info():
     RecordDescription(**desc_dict)
 
     desc_dict["collection"]["type"] = "Document"
-    with pytest.raises(ValidationError, match="collection.type"):
+    with pytest.raises(ValidationError, match="collection\\.type"):
         RecordDescription(**desc_dict)
 
     desc_dict["collection"]["type"] = "record"
-    with pytest.raises(ValidationError, match="collection.type"):
+    with pytest.raises(ValidationError, match="collection\\.type"):
         RecordDescription(**desc_dict)
 
 

test/test_code_chunker.py

@@ -62,7 +62,7 @@ def create_documents_from_repository(
             ]
         )
 
-    all_files = sorted(list(set(all_files)))
+    all_files = sorted(set(all_files))
 
     for file_path in all_files:
         with open(file_path, "r", encoding="utf-8") as f:

test/test_rec_schema.py

@@ -37,7 +37,7 @@ def test_predicates_wrong(self):
 
         filename = "test/data/rec/error-predicate-02.json"
         with (
-            pytest.raises(ValidationError, match="geopoint_value.conf"),
+            pytest.raises(ValidationError, match="geopoint_value\\.conf"),
             open(filename, encoding="utf-8") as file_obj,
         ):
             file_json = file_obj.read()

test/test_regions_to_table.py

@@ -67,11 +67,11 @@ def test_regions_to_table_convert():
     assert table_data.table_cells[0].bbox.b == 25.0
 
     assert table_data.table_cells[0].col_span == 2
-    assert table_data.table_cells[0].column_header == True
-    assert table_data.table_cells[1].column_header == True
+    assert table_data.table_cells[0].column_header
+    assert table_data.table_cells[1].column_header
 
-    assert table_data.table_cells[10].row_header == True
-    assert table_data.table_cells[12].row_section == True
+    assert table_data.table_cells[10].row_header
+    assert table_data.table_cells[12].row_section
 
     assert table_data.table_cells[17].bbox.l == 75.0
     assert table_data.table_cells[17].bbox.t == 100.0

test/test_serialization.py

@@ -43,7 +43,7 @@ def verify(exp_file: Path, actual: str):
 
         # Normalize platform-dependent quote escaping for DocTags outputs
         name = exp_file.name
-        if name.endswith(".dt") or name.endswith(".idt.xml"):
+        if name.endswith((".dt", ".idt.xml")):
 
             def _normalize_quotes(s: str) -> str:
                 return s.replace(""", '"').replace(""", '"')