Use default_factories (#314)

src/kohlrahbi/ahb/__init__.py

@@ -153,6 +153,7 @@ def extract_pruefis_from_docx(docx_path: Path) -> Dict[str, str]:
             and table_header_starts_with_text_edifact_struktur(item)
             and table_header_contains_text_pruefidentifikator(item)
         ):
+            # pylint:disable=not-an-iterable
             pruefis.update({pruefi: docx_path.name for pruefi in extract_pruefis_from_table(item)})
     return pruefis
 

src/kohlrahbi/ahbtable/ahbcondtions.py

@@ -6,7 +6,7 @@
 
 from docx.table import Table as DocxTable
 from maus.edifact import EdifactFormat
-from pydantic import BaseModel, ConfigDict
+from pydantic import BaseModel, ConfigDict, Field
 
 from kohlrahbi.logger import logger
 
@@ -16,7 +16,7 @@ class AhbConditions(BaseModel):
     Class which contains a dict of conditions for each edifact format
     """
 
-    conditions_dict: dict[EdifactFormat, dict[str, str]] = {}
+    conditions_dict: dict[EdifactFormat, dict[str, str]] = Field(default_factory=dict)
 
     model_config = ConfigDict(arbitrary_types_allowed=True)
 
@@ -60,15 +60,19 @@ def include_condition_dict(self, to_add: dict[EdifactFormat, dict[str, str]] | N
             return
         for edifact_format, edi_cond_dict in to_add.items():
             for condition_key, condition_text in edi_cond_dict.items():
-                if edifact_format in self.conditions_dict:
+                if edifact_format in self.conditions_dict:  # pylint:disable=unsupported-membership-test
                     if (
+                        # pylint:disable=unsubscriptable-object
                         condition_key in self.conditions_dict[edifact_format]
                         and len(condition_text) > len(self.conditions_dict[edifact_format][condition_key])
+                        # pylint:disable=unsubscriptable-object
                         or condition_key not in self.conditions_dict[edifact_format]
                     ):
                         self.conditions_dict[edifact_format][condition_key] = condition_text
                 else:
-                    self.conditions_dict[edifact_format] = {condition_key: condition_text}
+                    self.conditions_dict[edifact_format] = {  # pylint:disable=unsupported-assignment-operation
+                        condition_key: condition_text
+                    }
 
         logger.info("Conditions were updated.")
 
@@ -78,6 +82,7 @@ def dump_as_json(self, output_directory_path: Path) -> None:
         The file will be stored in the directory:
             'output_directory_path/<edifact_format>/conditions.json'
         """
+        # pylint:disable=no-member
         for edifact_format, format_cond_dict in self.conditions_dict.items():
             condition_json_output_directory_path = output_directory_path / str(edifact_format)
             condition_json_output_directory_path.mkdir(parents=True, exist_ok=True)

src/kohlrahbi/ahbtable/ahbpackagetable.py

@@ -9,7 +9,7 @@ class which contains AHB package condition table
 import pandas as pd
 from docx.table import Table as DocxTable
 from maus.edifact import EdifactFormat
-from pydantic import BaseModel, ConfigDict
+from pydantic import BaseModel, ConfigDict, Field
 
 from kohlrahbi.ahbtable.ahbcondtions import parse_conditions_from_string
 from kohlrahbi.logger import logger
@@ -23,7 +23,7 @@ class AhbPackageTable(BaseModel):
     """
 
     table: pd.DataFrame = pd.DataFrame()
-    package_dict: dict[EdifactFormat, dict[str, str]] = {}
+    package_dict: dict[EdifactFormat, dict[str, str]] = Field(default_factory=dict)
     model_config = ConfigDict(arbitrary_types_allowed=True)
 
     @classmethod

src/kohlrahbi/ahbtable/ahbtable.py

@@ -8,7 +8,7 @@
 import pandas as pd
 from maus.edifact import get_format_of_pruefidentifikator
 from more_itertools import peekable
-from pydantic import BaseModel, ConfigDict
+from pydantic import BaseModel, ConfigDict, Field
 
 from kohlrahbi.ahbtable.ahbsubtable import AhbSubTable
 from kohlrahbi.logger import logger
@@ -32,7 +32,7 @@ class AhbTable(BaseModel):
     """
 
     table: pd.DataFrame
-    metadata: list[PruefiMetaData] = []
+    metadata: list[PruefiMetaData] = Field(default_factory=list)
 
     model_config = ConfigDict(arbitrary_types_allowed=True)
 

src/kohlrahbi/read_functions.py

@@ -174,7 +174,7 @@ def process_table(
     """Processes tables to find and build the AHB table."""
     if is_item_table_with_pruefidentifikatoren(item):
         seed = Seed.from_table(docx_table=item)
-
+        # pylint:disable=unsupported-membership-test
         if pruefi in seed.pruefidentifikatoren and not searched_pruefi_is_found:
             log_found_pruefi(pruefi)
             ahb_sub_table = AhbSubTable.from_table_with_header(docx_table=item)

src/kohlrahbi/seed.py

@@ -3,7 +3,7 @@
 """
 
 from docx.table import Table
-from pydantic import BaseModel
+from pydantic import BaseModel, Field
 
 from kohlrahbi.enums import RowType
 from kohlrahbi.table_header import PruefiMetaData, TableHeader, get_tabstop_positions
@@ -15,13 +15,13 @@ class Seed(BaseModel):
     helper class to store all values to extract the AHB and the final AHB as dataframe
     """
 
-    pruefidentifikatoren: list[str] = []
-    column_headers: list[str] = []
+    pruefidentifikatoren: list[str] = Field(default_factory=list)
+    column_headers: list[str] = Field(default_factory=list)
     edifact_struktur_left_indent_position: int = 0
     middle_cell_left_indent_position: int = 0
-    tabstop_positions: list[int] = []
-    last_two_row_types: list[RowType] = []
-    metadata: list[PruefiMetaData] = []
+    tabstop_positions: list[int] = Field(default_factory=list)
+    last_two_row_types: list[RowType] = Field(default_factory=list)
+    metadata: list[PruefiMetaData] = Field(default_factory=list)
 
     # why this classmethod?
     # to decouple the data structure of Elixir from the input data

src/kohlrahbi/table_header.py

@@ -8,7 +8,7 @@
 from docx.table import _Cell
 from docx.text.paragraph import Paragraph
 from more_itertools import first, last
-from pydantic import BaseModel
+from pydantic import BaseModel, Field
 
 
 class HeaderSection(StrEnum):
@@ -93,7 +93,7 @@ class TableHeader(BaseModel):
     It contains the information about the Prüfidentifikatoren.
     """
 
-    pruefi_meta_data: List[PruefiMetaData] = []
+    pruefi_meta_data: List[PruefiMetaData] = Field(default_factory=list)
 
     @classmethod
     def from_header_cell(cls, row_cell: _Cell) -> "TableHeader":
@@ -188,4 +188,5 @@ def get_pruefidentifikatoren(self) -> List[str]:
         The order of the Prüfidentifikatoren is the same as in the docx table headers.
         So there should be no duplicates.
         """
+        # pylint:disable=not-an-iterable
         return [pruefi.pruefidentifikator for pruefi in self.pruefi_meta_data]